1351 files changed, 77936 insertions, 21165 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-thunderbolt b/Documentation/ABI/testing/sysfs-bus-thunderbolt
index 392bef5bd399..93798c02e28b 100644
--- a/Documentation/ABI/testing/sysfs-bus-thunderbolt
+++ b/Documentation/ABI/testing/sysfs-bus-thunderbolt
@@ -110,3 +110,51 @@ Description:	When new NVM image is written to the non-active NVM
 		is directly the status value from the DMA configuration
 		based mailbox before the device is power cycled. Writing
 		0 here clears the status.
+
+What:		/sys/bus/thunderbolt/devices/<xdomain>.<service>/key
+Date:		Jan 2018
+KernelVersion:	4.15
+Contact:	thunderbolt-software@lists.01.org
+Description:	This contains name of the property directory the XDomain
+		service exposes. This entry describes the protocol in
+		question. Following directories are already reserved by
+		the Apple XDomain specification:
+
+		network:  IP/ethernet over Thunderbolt
+		targetdm: Target disk mode protocol over Thunderbolt
+		extdisp:  External display mode protocol over Thunderbolt
+
+What:		/sys/bus/thunderbolt/devices/<xdomain>.<service>/modalias
+Date:		Jan 2018
+KernelVersion:	4.15
+Contact:	thunderbolt-software@lists.01.org
+Description:	Stores the same MODALIAS value emitted by uevent for
+		the XDomain service. Format: tbtsvc:kSpNvNrN
+
+What:		/sys/bus/thunderbolt/devices/<xdomain>.<service>/prtcid
+Date:		Jan 2018
+KernelVersion:	4.15
+Contact:	thunderbolt-software@lists.01.org
+Description:	This contains XDomain protocol identifier the XDomain
+		service supports.
+
+What:		/sys/bus/thunderbolt/devices/<xdomain>.<service>/prtcvers
+Date:		Jan 2018
+KernelVersion:	4.15
+Contact:	thunderbolt-software@lists.01.org
+Description:	This contains XDomain protocol version the XDomain
+		service supports.
+
+What:		/sys/bus/thunderbolt/devices/<xdomain>.<service>/prtcrevs
+Date:		Jan 2018
+KernelVersion:	4.15
+Contact:	thunderbolt-software@lists.01.org
+Description:	This contains XDomain software version the XDomain
+		service supports.
+
+What:		/sys/bus/thunderbolt/devices/<xdomain>.<service>/prtcstns
+Date:		Jan 2018
+KernelVersion:	4.15
+Contact:	thunderbolt-software@lists.01.org
+Description:	This contains XDomain service specific settings as
+		bitmask. Format: %x
diff --git a/Documentation/admin-guide/thunderbolt.rst b/Documentation/admin-guide/thunderbolt.rst
index 6a4cd1f159ca..5c62d11d77e8 100644
--- a/Documentation/admin-guide/thunderbolt.rst
+++ b/Documentation/admin-guide/thunderbolt.rst
@@ -197,3 +197,27 @@ information is missing.
 
 To recover from this mode, one needs to flash a valid NVM image to the
 host host controller in the same way it is done in the previous chapter.
+
+Networking over Thunderbolt cable
+---------------------------------
+Thunderbolt technology allows software communication across two hosts
+connected by a Thunderbolt cable.
+
+It is possible to tunnel any kind of traffic over Thunderbolt link but
+currently we only support Apple ThunderboltIP protocol.
+
+If the other host is running Windows or macOS only thing you need to
+do is to connect Thunderbolt cable between the two hosts, the
+``thunderbolt-net`` is loaded automatically. If the other host is also
+Linux you should load ``thunderbolt-net`` manually on one host (it does
+not matter which one)::
+
+  # modprobe thunderbolt-net
+
+This triggers module load on the other host automatically. If the driver
+is built-in to the kernel image, there is no need to do anything.
+
+The driver will create one virtual ethernet interface per Thunderbolt
+port which are named like ``thunderbolt0`` and so on. From this point
+you can either use standard userspace tools like ``ifconfig`` to
+configure the interface or let your GUI to handle it automatically.
diff --git a/Documentation/bpf/bpf_design_QA.txt b/Documentation/bpf/bpf_design_QA.txt
new file mode 100644
index 000000000000..f3e458a0bb2f
--- /dev/null
+++ b/Documentation/bpf/bpf_design_QA.txt
@@ -0,0 +1,156 @@
+BPF extensibility and applicability to networking, tracing, security
+in the linux kernel and several user space implementations of BPF
+virtual machine led to a number of misunderstanding on what BPF actually is.
+This short QA is an attempt to address that and outline a direction
+of where BPF is heading long term.
+
+Q: Is BPF a generic instruction set similar to x64 and arm64?
+A: NO.
+
+Q: Is BPF a generic virtual machine ?
+A: NO.
+
+BPF is generic instruction set _with_ C calling convention.
+
+Q: Why C calling convention was chosen?
+A: Because BPF programs are designed to run in the linux kernel
+   which is written in C, hence BPF defines instruction set compatible
+   with two most used architectures x64 and arm64 (and takes into
+   consideration important quirks of other architectures) and
+   defines calling convention that is compatible with C calling
+   convention of the linux kernel on those architectures.
+
+Q: can multiple return values be supported in the future?
+A: NO. BPF allows only register R0 to be used as return value.
+
+Q: can more than 5 function arguments be supported in the future?
+A: NO. BPF calling convention only allows registers R1-R5 to be used
+   as arguments. BPF is not a standalone instruction set.
+   (unlike x64 ISA that allows msft, cdecl and other conventions)
+
+Q: can BPF programs access instruction pointer or return address?
+A: NO.
+
+Q: can BPF programs access stack pointer ?
+A: NO. Only frame pointer (register R10) is accessible.
+   From compiler point of view it's necessary to have stack pointer.
+   For example LLVM defines register R11 as stack pointer in its
+   BPF backend, but it makes sure that generated code never uses it.
+
+Q: Does C-calling convention diminishes possible use cases?
+A: YES. BPF design forces addition of major functionality in the form
+   of kernel helper functions and kernel objects like BPF maps with
+   seamless interoperability between them. It lets kernel call into
+   BPF programs and programs call kernel helpers with zero overhead.
+   As all of them were native C code. That is particularly the case
+   for JITed BPF programs that are indistinguishable from
+   native kernel C code.
+
+Q: Does it mean that 'innovative' extensions to BPF code are disallowed?
+A: Soft yes. At least for now until BPF core has support for
+   bpf-to-bpf calls, indirect calls, loops, global variables,
+   jump tables, read only sections and all other normal constructs
+   that C code can produce.
+
+Q: Can loops be supported in a safe way?
+A: It's not clear yet. BPF developers are trying to find a way to
+   support bounded loops where the verifier can guarantee that
+   the program terminates in less than 4096 instructions.
+
+Q: How come LD_ABS and LD_IND instruction are present in BPF whereas
+   C code cannot express them and has to use builtin intrinsics?
+A: This is artifact of compatibility with classic BPF. Modern
+   networking code in BPF performs better without them.
+   See 'direct packet access'.
+
+Q: It seems not all BPF instructions are one-to-one to native CPU.
+   For example why BPF_JNE and other compare and jumps are not cpu-like?
+A: This was necessary to avoid introducing flags into ISA which are
+   impossible to make generic and efficient across CPU architectures.
+
+Q: why BPF_DIV instruction doesn't map to x64 div?
+A: Because if we picked one-to-one relationship to x64 it would have made
+   it more complicated to support on arm64 and other archs. Also it
+   needs div-by-zero runtime check.
+
+Q: why there is no BPF_SDIV for signed divide operation?
+A: Because it would be rarely used. llvm errors in such case and
+   prints a suggestion to use unsigned divide instead
+
+Q: Why BPF has implicit prologue and epilogue?
+A: Because architectures like sparc have register windows and in general
+   there are enough subtle differences between architectures, so naive
+   store return address into stack won't work. Another reason is BPF has
+   to be safe from division by zero (and legacy exception path
+   of LD_ABS insn). Those instructions need to invoke epilogue and
+   return implicitly.
+
+Q: Why BPF_JLT and BPF_JLE instructions were not introduced in the beginning?
+A: Because classic BPF didn't have them and BPF authors felt that compiler
+   workaround would be acceptable. Turned out that programs lose performance
+   due to lack of these compare instructions and they were added.
+   These two instructions is a perfect example what kind of new BPF
+   instructions are acceptable and can be added in the future.
+   These two already had equivalent instructions in native CPUs.
+   New instructions that don't have one-to-one mapping to HW instructions
+   will not be accepted.
+
+Q: BPF 32-bit subregisters have a requirement to zero upper 32-bits of BPF
+   registers which makes BPF inefficient virtual machine for 32-bit
+   CPU architectures and 32-bit HW accelerators. Can true 32-bit registers
+   be added to BPF in the future?
+A: NO. The first thing to improve performance on 32-bit archs is to teach
+   LLVM to generate code that uses 32-bit subregisters. Then second step
+   is to teach verifier to mark operations where zero-ing upper bits
+   is unnecessary. Then JITs can take advantage of those markings and
+   drastically reduce size of generated code and improve performance.
+
+Q: Does BPF have a stable ABI?
+A: YES. BPF instructions, arguments to BPF programs, set of helper
+   functions and their arguments, recognized return codes are all part
+   of ABI. However when tracing programs are using bpf_probe_read() helper
+   to walk kernel internal datastructures and compile with kernel
+   internal headers these accesses can and will break with newer
+   kernels. The union bpf_attr -> kern_version is checked at load time
+   to prevent accidentally loading kprobe-based bpf programs written
+   for a different kernel. Networking programs don't do kern_version check.
+
+Q: How much stack space a BPF program uses?
+A: Currently all program types are limited to 512 bytes of stack
+   space, but the verifier computes the actual amount of stack used
+   and both interpreter and most JITed code consume necessary amount.
+
+Q: Can BPF be offloaded to HW?
+A: YES. BPF HW offload is supported by NFP driver.
+
+Q: Does classic BPF interpreter still exist?
+A: NO. Classic BPF programs are converted into extend BPF instructions.
+
+Q: Can BPF call arbitrary kernel functions?
+A: NO. BPF programs can only call a set of helper functions which
+   is defined for every program type.
+
+Q: Can BPF overwrite arbitrary kernel memory?
+A: NO. Tracing bpf programs can _read_ arbitrary memory with bpf_probe_read()
+   and bpf_probe_read_str() helpers. Networking programs cannot read
+   arbitrary memory, since they don't have access to these helpers.
+   Programs can never read or write arbitrary memory directly.
+
+Q: Can BPF overwrite arbitrary user memory?
+A: Sort-of. Tracing BPF programs can overwrite the user memory
+   of the current task with bpf_probe_write_user(). Every time such
+   program is loaded the kernel will print warning message, so
+   this helper is only useful for experiments and prototypes.
+   Tracing BPF programs are root only.
+
+Q: When bpf_trace_printk() helper is used the kernel prints nasty
+   warning message. Why is that?
+A: This is done to nudge program authors into better interfaces when
+   programs need to pass data to user space. Like bpf_perf_event_output()
+   can be used to efficiently stream data via perf ring buffer.
+   BPF maps can be used for asynchronous data sharing between kernel
+   and user space. bpf_trace_printk() should only be used for debugging.
+
+Q: Can BPF functionality such as new program or map types, new
+   helpers, etc be added out of kernel module code?
+A: NO.
diff --git a/Documentation/devicetree/bindings/net/bluetooth.txt b/Documentation/devicetree/bindings/net/bluetooth.txt
new file mode 100644
index 000000000000..94797df751b8
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/bluetooth.txt
@@ -0,0 +1,5 @@
+The following properties are common to the Bluetooth controllers:
+
+- local-bd-address: array of 6 bytes, specifies the BD address that was
+  uniquely assigned to the Bluetooth device, formatted with least significant
+  byte first (little-endian).
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index 16723535e1aa..c902261893b9 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -17,6 +17,8 @@ Required properties:
 
       - "renesas,etheravb-r8a7795" for the R8A7795 SoC.
       - "renesas,etheravb-r8a7796" for the R8A7796 SoC.
+      - "renesas,etheravb-r8a77970" for the R8A77970 SoC.
+      - "renesas,etheravb-r8a77995" for the R8A77995 SoC.
       - "renesas,etheravb-rcar-gen3" as a fallback for the above
 		R-Car Gen3 devices.
 
@@ -40,7 +42,7 @@ Optional properties:
 - interrupt-parent: the phandle for the interrupt controller that services
 		    interrupts for this device.
 - interrupt-names: A list of interrupt names.
-		   For the R8A779[56] SoCs this property is mandatory;
+		   For the R-Car Gen 3 SoCs this property is mandatory;
 		   it should include one entry per channel, named "ch%u",
 		   where %u is the channel number ranging from 0 to 24.
 		   For other SoCs this property is optional; if present
diff --git a/Documentation/devicetree/bindings/net/sh_eth.txt b/Documentation/devicetree/bindings/net/sh_eth.txt
index 0115c85a2425..5172799a7f1a 100644
--- a/Documentation/devicetree/bindings/net/sh_eth.txt
+++ b/Documentation/devicetree/bindings/net/sh_eth.txt
@@ -4,7 +4,8 @@ This file provides information on what the device node for the SH EtherMAC
 interface contains.
 
 Required properties:
-- compatible: "renesas,gether-r8a7740" if the device is a part of R8A7740 SoC.
+- compatible: Must contain one or more of the following:
+	      "renesas,gether-r8a7740" if the device is a part of R8A7740 SoC.
 	      "renesas,ether-r8a7743"  if the device is a part of R8A7743 SoC.
 	      "renesas,ether-r8a7745"  if the device is a part of R8A7745 SoC.
 	      "renesas,ether-r8a7778"  if the device is a part of R8A7778 SoC.
@@ -14,6 +15,14 @@ Required properties:
 	      "renesas,ether-r8a7793"  if the device is a part of R8A7793 SoC.
 	      "renesas,ether-r8a7794"  if the device is a part of R8A7794 SoC.
 	      "renesas,ether-r7s72100" if the device is a part of R7S72100 SoC.
+	      "renesas,rcar-gen1-ether" for a generic R-Car Gen1 device.
+	      "renesas,rcar-gen2-ether" for a generic R-Car Gen2 or RZ/G1
+	                                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: offset and length of (1) the E-DMAC/feLic register block (required),
        (2) the TSU register block (optional).
 - interrupts: interrupt specifier for the sole interrupt.
@@ -36,7 +45,8 @@ Optional properties:
 Example (Lager board):
 
 	ethernet@ee700000 {
-		compatible = "renesas,ether-r8a7790";
+		compatible = "renesas,ether-r8a7790",
+		             "renesas,rcar-gen2-ether";
 		reg = <0 0xee700000 0 0x400>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 162 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,wcnss.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,wcnss.txt
index 4ea39e9186a7..042a2e4159bd 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,wcnss.txt
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,wcnss.txt
@@ -37,6 +37,11 @@ The following properties are defined to the bluetooth node:
 	Definition: must be:
 		    "qcom,wcnss-bt"
 
+- local-bd-address:
+	Usage: optional
+	Value type: <u8 array>
+	Definition: see Documentation/devicetree/bindings/net/bluetooth.txt
+
 == WiFi
 The following properties are defined to the WiFi node:
 
@@ -91,6 +96,9 @@ smd {
 
 			bt {
 				compatible = "qcom,wcnss-bt";
+
+				/* BD address 00:11:22:33:44:55 */
+				local-bd-address = [ 55 44 33 22 11 00 ];
 			};
 
 			wlan {
diff --git a/Documentation/driver-api/80211/cfg80211.rst b/Documentation/driver-api/80211/cfg80211.rst
index 8ffac57e1f5b..eeab91b59457 100644
--- a/Documentation/driver-api/80211/cfg80211.rst
+++ b/Documentation/driver-api/80211/cfg80211.rst
@@ -300,9 +300,6 @@ Data path helpers
    :functions: ieee80211_data_to_8023
 
 .. kernel-doc:: include/net/cfg80211.h
-   :functions: ieee80211_data_from_8023
-
-.. kernel-doc:: include/net/cfg80211.h
    :functions: ieee80211_amsdu_to_8023s
 
 .. kernel-doc:: include/net/cfg80211.h
diff --git a/Documentation/networking/dsa/lan9303.txt b/Documentation/networking/dsa/lan9303.txt
new file mode 100644
index 000000000000..ec28683d107d
--- /dev/null
+++ b/Documentation/networking/dsa/lan9303.txt
@@ -0,0 +1,37 @@
+LAN9303 Ethernet switch driver
+==============================
+
+The LAN9303 is a three port 10/100 ethernet switch with integrated phys for the
+two external ethernet ports. The third port is an RMII/MII interface to a host
+master network interface (e.g. fixed link).
+
+
+Driver details
+==============
+
+The driver is implemented as a DSA driver, see
+Documentation/networking/dsa/dsa.txt.
+
+See Documentation/devicetree/bindings/net/dsa/lan9303.txt for device tree
+binding.
+
+The LAN9303 can be managed both via MDIO and I2C, both supported by this driver.
+
+At startup the driver configures the device to provide two separate network
+interfaces (which is the default state of a DSA device). Due to HW limitations,
+no HW MAC learning takes place in this mode.
+
+When both user ports are joined to the same bridge, the normal HW MAC learning
+is enabled. This means that unicast traffic is forwarded in HW. Broadcast and
+multicast is flooded in HW. STP is also supported in this mode. The driver
+support fdb/mdb operations as well, meaning IGMP snooping is supported.
+
+If one of the user ports leave the bridge, the ports goes back to the initial
+separated operation.
+
+
+Driver limitations
+==================
+
+ - Support for VLAN filtering is not implemented
+ - The HW does not support VLAN-specific fdb entries
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 77f4de59dc9c..e6661b205f72 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1385,6 +1385,30 @@ mld_qrv - INTEGER
 	Default: 2 (as specified by RFC3810 9.1)
 	Minimum: 1 (as specified by RFC6636 4.5)
 
+max_dst_opts_cnt - INTEGER
+	Maximum number of non-padding TLVs allowed in a Destination
+	options extension header. If this value is less than zero
+	then unknown options are disallowed and the number of known
+	TLVs allowed is the absolute value of this number.
+	Default: 8
+
+max_hbh_opts_cnt - INTEGER
+	Maximum number of non-padding TLVs allowed in a Hop-by-Hop
+	options extension header. If this value is less than zero
+	then unknown options are disallowed and the number of known
+	TLVs allowed is the absolute value of this number.
+	Default: 8
+
+max dst_opts_len - INTEGER
+	Maximum length allowed for a Destination options extension
+	header.
+	Default: INT_MAX (unlimited)
+
+max hbh_opts_len - INTEGER
+	Maximum length allowed for a Hop-by-Hop options extension
+	header.
+	Default: INT_MAX (unlimited)
+
 IPv6 Fragmentation:
 
 ip6frag_high_thresh - INTEGER
diff --git a/Documentation/networking/ipvlan.txt b/Documentation/networking/ipvlan.txt
index 1fe42a874aae..812ef003e0a8 100644
--- a/Documentation/networking/ipvlan.txt
+++ b/Documentation/networking/ipvlan.txt
@@ -22,9 +22,21 @@ The driver can be built into the kernel (CONFIG_IPVLAN=y) or as a module
 	There are no module parameters for this driver and it can be configured
 using IProute2/ip utility.
 
-	ip link add link <master-dev> name <slave-dev> type ipvlan mode { l2 | l3 | l3s }
-
-	e.g. ip link add link eth0 name ipvl0 type ipvlan mode l2
+    ip link add link <master> name <slave> type ipvlan [ mode MODE ] [ FLAGS ]
+       where
+         MODE: l3 (default) | l3s | l2
+         FLAGS: bridge (default) | private | vepa
+
+    e.g.
+    (a) Following will create IPvlan link with eth0 as master in
+        L3 bridge mode
+          bash# ip link add link eth0 name ipvl0 type ipvlan
+    (b) This command will create IPvlan link in L2 bridge mode.
+          bash# ip link add link eth0 name ipvl0 type ipvlan mode l2 bridge
+    (c) This command will create an IPvlan device in L2 private mode.
+          bash# ip link add link eth0 name ipvlan type ipvlan mode l2 private
+    (d) This command will create an IPvlan device in L2 vepa mode.
+          bash# ip link add link eth0 name ipvlan type ipvlan mode l2 vepa
 
 
 4. Operating modes:
@@ -54,7 +66,29 @@ works in this mode and hence it is L3-symmetric (L3s). This will have slightly l
 performance but that shouldn't matter since you are choosing this mode over plain-L3
 mode to make conn-tracking work.
 
-5. What to choose (macvlan vs. ipvlan)?
+5. Mode flags:
+	At this time following mode flags are available
+
+5.1 bridge:
+	This is the default option. To configure the IPvlan port in this mode,
+user can choose to either add this option on the command-line or don't specify
+anything. This is the traditional mode where slaves can cross-talk among
+themseleves apart from talking through the master device.
+
+5.2 private:
+	If this option is added to the command-line, the port is set in private
+mode. i.e. port wont allow cross communication between slaves.
+
+5.3 vepa:
+	If this is added to the command-line, the port is set in VEPA mode.
+i.e. port will offload switching functionality to the external entity as
+described in 802.1Qbg
+Note: VEPA mode in IPvlan has limitations. IPvlan uses the mac-address of the
+master-device, so the packets which are emitted in this mode for the adjacent
+neighbor will have source and destination mac same. This will make the switch /
+router send the redirect message.
+
+6. What to choose (macvlan vs. ipvlan)?
 	These two devices are very similar in many regards and the specific use
 case could very well define which device to choose. if one of the following
 situations defines your use case then you can choose to use ipvlan -
diff --git a/Documentation/networking/netvsc.txt b/Documentation/networking/netvsc.txt
index 93560fb1170a..92f5b31392fa 100644
--- a/Documentation/networking/netvsc.txt
+++ b/Documentation/networking/netvsc.txt
@@ -19,12 +19,12 @@ Features
 
   Receive Side Scaling
   --------------------
-  Hyper-V supports receive side scaling. For TCP, packets are
-  distributed among available queues based on IP address and port
+  Hyper-V supports receive side scaling. For TCP & UDP, packets can
+  be distributed among available queues based on IP address and port
   number.
 
-  For UDP, we can switch UDP hash level between L3 and L4 by ethtool
-  command. UDP over IPv4 and v6 can be set differently. The default
+  For TCP & UDP, we can switch hash level between L3 and L4 by ethtool
+  command. TCP/UDP over IPv4 and v6 can be set differently. The default
   hash level is L4. We currently only allow switching TX hash level
   from within the guests.
 
diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt
index 7818b5fe448b..381e5b23d61d 100644
--- a/Documentation/networking/regulatory.txt
+++ b/Documentation/networking/regulatory.txt
@@ -19,6 +19,14 @@ core regulatory domain all wireless devices should adhere to.
 How to get regulatory domains to the kernel
 -------------------------------------------
 
+When the regulatory domain is first set up, the kernel will request a
+database file (regulatory.db) containing all the regulatory rules. It
+will then use that database when it needs to look up the rules for a
+given country.
+
+How to get regulatory domains to the kernel (old CRDA solution)
+---------------------------------------------------------------
+
 Userspace gets a regulatory domain in the kernel by having
 a userspace agent build it and send it via nl80211. Only
 expected regulatory domains will be respected by the kernel.
@@ -192,23 +200,5 @@ Then in some part of your code after your wiphy has been registered:
 Statically compiled regulatory database
 ---------------------------------------
 
-In most situations the userland solution using CRDA as described
-above is the preferred solution.  However in some cases a set of
-rules built into the kernel itself may be desirable.  To account
-for this situation, a configuration option has been provided
-(i.e. CONFIG_CFG80211_INTERNAL_REGDB).  With this option enabled,
-the wireless database information contained in net/wireless/db.txt is
-used to generate a data structure encoded in net/wireless/regdb.c.
-That option also enables code in net/wireless/reg.c which queries
-the data in regdb.c as an alternative to using CRDA.
-
-The file net/wireless/db.txt should be kept up-to-date with the db.txt
-file available in the git repository here:
-
-    git://git.kernel.org/pub/scm/linux/kernel/git/sforshee/wireless-regdb.git
-
-Again, most users in most situations should be using the CRDA package
-provided with their distribution, and in most other situations users
-should be building and using CRDA on their own rather than using
-this option.  If you are not absolutely sure that you should be using
-CONFIG_CFG80211_INTERNAL_REGDB then _DO_NOT_USE_IT_.
+When a database should be fixed into the kernel, it can be provided as a
+firmware file at build time that is then linked into the kernel.
diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt
index 810620153a44..b5407163d53b 100644
--- a/Documentation/networking/rxrpc.txt
+++ b/Documentation/networking/rxrpc.txt
@@ -280,6 +280,18 @@ Interaction with the user of the RxRPC socket:
      nominated by a socket option.
 
 
+Notes on sendmsg:
+
+ (*) MSG_WAITALL can be set to tell sendmsg to ignore signals if the peer is
+     making progress at accepting packets within a reasonable time such that we
+     manage to queue up all the data for transmission.  This requires the
+     client to accept at least one packet per 2*RTT time period.
+
+     If this isn't set, sendmsg() will return immediately, either returning
+     EINTR/ERESTARTSYS if nothing was consumed or returning the amount of data
+     consumed.
+
+
 Notes on recvmsg:
 
  (*) If there's a sequence of data messages belonging to a particular call on
@@ -782,7 +794,9 @@ The kernel interface functions are as follows:
 				struct key *key,
 				unsigned long user_call_ID,
 				s64 tx_total_len,
-				gfp_t gfp);
+				gfp_t gfp,
+				rxrpc_notify_rx_t notify_rx,
+				bool upgrade);
 
      This allocates the infrastructure to make a new RxRPC call and assigns
      call and connection numbers.  The call will be made on the UDP port that
@@ -803,6 +817,13 @@ The kernel interface functions are as follows:
      allows the kernel to encrypt directly to the packet buffers, thereby
      saving a copy.  The value may not be less than -1.
 
+     notify_rx is a pointer to a function to be called when events such as
+     incoming data packets or remote aborts happen.
+
+     upgrade should be set to true if a client operation should request that
+     the server upgrade the service to a better one.  The resultant service ID
+     is returned by rxrpc_kernel_recv_data().
+
      If this function is successful, an opaque reference to the RxRPC call is
      returned.  The caller now holds a reference on this and it must be
      properly ended.
@@ -850,7 +871,8 @@ The kernel interface functions are as follows:
 				   size_t size,
 				   size_t *_offset,
 				   bool want_more,
-				   u32 *_abort)
+				   u32 *_abort,
+				   u16 *_service)
 
       This is used to receive data from either the reply part of a client call
       or the request part of a service call.  buf and size specify how much
@@ -873,6 +895,9 @@ The kernel interface functions are as follows:
       If a remote ABORT is detected, the abort code received will be stored in
       *_abort and ECONNABORTED will be returned.
 
+      The service ID that the call ended up with is returned into *_service.
+      This can be used to see if a call got a service upgrade.
+
  (*) Abort a call.
 
 	void rxrpc_kernel_abort_call(struct socket *sock,
@@ -1020,6 +1045,30 @@ The kernel interface functions are as follows:
 
      It returns 0 if the call was requeued and an error otherwise.
 
+ (*) Get call RTT.
+
+	u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call);
+
+     Get the RTT time to the peer in use by a call.  The value returned is in
+     nanoseconds.
+
+ (*) Check call still alive.
+
+	u32 rxrpc_kernel_check_life(struct socket *sock,
+				    struct rxrpc_call *call);
+
+     This returns a number that is updated when ACKs are received from the peer
+     (notably including PING RESPONSE ACKs which we can elicit by sending PING
+     ACKs to see if the call still exists on the server).  The caller should
+     compare the numbers of two calls to see if the call is still alive after
+     waiting for a suitable interval.
+
+     This allows the caller to work out if the server is still contactable and
+     if the call is still alive on the server whilst waiting for the server to
+     process a client operation.
+
+     This function may transmit a PING ACK.
+
 
 =======================
 CONFIGURABLE PARAMETERS
diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt
index 3918dae964d4..8ff7b4c8f91b 100644
--- a/Documentation/networking/vrf.txt
+++ b/Documentation/networking/vrf.txt
@@ -71,7 +71,12 @@ Setup
        ip ru add iif vrf-blue table 10
 
 3. Set the default route for the table (and hence default route for the VRF).
-       ip route add table 10 unreachable default
+       ip route add table 10 unreachable default metric 4278198272
+
+   This high metric value ensures that the default unreachable route can
+   be overridden by a routing protocol suite.  FRRouting interprets
+   kernel metrics as a combined admin distance (upper byte) and priority
+   (lower 3 bytes).  Thus the above metric translates to [255/8192].
 
 4. Enslave L3 interfaces to a VRF device.
        ip link set dev eth1 master vrf-blue
@@ -256,7 +261,7 @@ older form without it.
 
    For example:
    $ ip route show vrf red
-   prohibit default
+   unreachable default  metric 4278198272
    broadcast 10.2.1.0 dev eth1  proto kernel  scope link  src 10.2.1.2
    10.2.1.0/24 dev eth1  proto kernel  scope link  src 10.2.1.2
    local 10.2.1.2 dev eth1  proto kernel  scope host  src 10.2.1.2
@@ -282,7 +287,7 @@ older form without it.
    ff00::/8 dev red  metric 256  pref medium
    ff00::/8 dev eth1  metric 256  pref medium
    ff00::/8 dev eth2  metric 256  pref medium
-
+   unreachable default dev lo  metric 4278198272  error -101 pref medium
 
 8. Route Lookup for a VRF
 
@@ -331,7 +336,7 @@ function vrf_create
     ip link add ${VRF} type vrf table ${TBID}
 
     if [ "${VRF}" != "mgmt" ]; then
-        ip route add table ${TBID} unreachable default
+        ip route add table ${TBID} unreachable default metric 4278198272
     fi
     ip link set dev ${VRF} up
 }
diff --git a/MAINTAINERS b/MAINTAINERS
index 00b0fda6c2e1..d20c9a483c42 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -700,9 +700,9 @@ F:	include/linux/altera_uart.h
 F:	include/linux/altera_jtaguart.h
 
 AMAZON ETHERNET DRIVERS
-M:	Netanel Belgazal <netanel@annapurnalabs.com>
-R:	Saeed Bishara <saeed@annapurnalabs.com>
-R:	Zorik Machulsky <zorik@annapurnalabs.com>
+M:	Netanel Belgazal <netanel@amazon.com>
+R:	Saeed Bishara <saeedb@amazon.com>
+R:	Zorik Machulsky <zorik@amazon.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/ena.txt
@@ -2713,6 +2713,7 @@ L:	linux-kernel@vger.kernel.org
 S:	Supported
 F:	arch/x86/net/bpf_jit*
 F:	Documentation/networking/filter.txt
+F:	Documentation/bpf/
 F:	include/linux/bpf*
 F:	include/linux/filter.h
 F:	include/uapi/linux/bpf*
@@ -2725,7 +2726,7 @@ F:	net/core/filter.c
 F:	net/sched/act_bpf.c
 F:	net/sched/cls_bpf.c
 F:	samples/bpf/
-F:	tools/net/bpf*
+F:	tools/bpf/
 F:	tools/testing/selftests/bpf/
 
 BROADCOM B44 10/100 ETHERNET DRIVER
@@ -2897,6 +2898,7 @@ F:	drivers/gpio/gpio-brcmstb.c
 F:	Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
 
 BROADCOM GENET ETHERNET DRIVER
+M:	Doug Berger <opendmb@gmail.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -3329,17 +3331,22 @@ S:	Maintained
 F:	drivers/auxdisplay/cfag12864bfb.c
 F:	include/linux/cfag12864b.h
 
-CFG80211 and NL80211
+802.11 (including CFG80211/NL80211)
 M:	Johannes Berg <johannes@sipsolutions.net>
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git
 S:	Maintained
+F:	net/wireless/
 F:	include/uapi/linux/nl80211.h
+F:	include/linux/ieee80211.h
+F:	include/net/wext.h
 F:	include/net/cfg80211.h
-F:	net/wireless/*
-X:	net/wireless/wext*
+F:	include/net/iw_handler.h
+F:	include/net/ieee80211_radiotap.h
+F:	Documentation/driver-api/80211/cfg80211.rst
+F:	Documentation/networking/regulatory.txt
 
 CHAR and MISC DRIVERS
 M:	Arnd Bergmann <arnd@arndb.de>
@@ -3415,7 +3422,7 @@ F:	drivers/scsi/snic/
 CISCO VIC ETHERNET NIC DRIVER
 M:	Christian Benvenuti <benve@cisco.com>
 M:	Govindarajulu Varadarajan <_govind@gmx.com>
-M:	Neel Patel <neepatel@cisco.com>
+M:	Parvi Kaustubhi <pkaustub@cisco.com>
 S:	Supported
 F:	drivers/net/ethernet/cisco/enic/
 
@@ -8208,6 +8215,7 @@ F:	Documentation/networking/mac80211-injection.txt
 F:	include/net/mac80211.h
 F:	net/mac80211/
 F:	drivers/net/wireless/mac80211_hwsim.[ch]
+F:	Documentation/networking/mac80211_hwsim/README
 
 MAILBOX API
 M:	Jassi Brar <jassisinghbrar@gmail.com>
@@ -9408,6 +9416,7 @@ M:	Florian Fainelli <f.fainelli@gmail.com>
 S:	Maintained
 F:	net/dsa/
 F:	include/net/dsa.h
+F:	include/linux/dsa/
 F:	drivers/net/dsa/
 
 NETWORKING [GENERAL]
@@ -9428,8 +9437,8 @@ F:	include/uapi/linux/in.h
 F:	include/uapi/linux/net.h
 F:	include/uapi/linux/netdevice.h
 F:	include/uapi/linux/net_namespace.h
-F:	tools/net/
 F:	tools/testing/selftests/net/
+F:	lib/net_utils.c
 F:	lib/random32.c
 
 NETWORKING [IPSEC]
@@ -11493,6 +11502,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git
 S:	Maintained
 F:	Documentation/rfkill.txt
+F:	Documentation/ABI/stable/sysfs-class-rfkill
 F:	net/rfkill/
 
 RHASHTABLE
@@ -13291,6 +13301,15 @@ M:	Mika Westerberg <mika.westerberg@linux.intel.com>
 M:	Yehezkel Bernat <yehezkel.bernat@intel.com>
 S:	Maintained
 F:	drivers/thunderbolt/
+F:	include/linux/thunderbolt.h
+
+THUNDERBOLT NETWORK DRIVER
+M:	Michael Jamet <michael.jamet@intel.com>
+M:	Mika Westerberg <mika.westerberg@linux.intel.com>
+M:	Yehezkel Bernat <yehezkel.bernat@intel.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/thunderbolt.c
 
 THUNDERX GPIO DRIVER
 M:	David Daney <david.daney@cavium.com>
@@ -14279,12 +14298,15 @@ S:	Maintained
 F:	include/linux/virtio_vsock.h
 F:	include/uapi/linux/virtio_vsock.h
 F:	include/uapi/linux/vsockmon.h
+F:	include/uapi/linux/vm_sockets_diag.h
+F:	net/vmw_vsock/diag.c
 F:	net/vmw_vsock/af_vsock_tap.c
 F:	net/vmw_vsock/virtio_transport_common.c
 F:	net/vmw_vsock/virtio_transport.c
 F:	drivers/net/vsockmon.c
 F:	drivers/vhost/vsock.c
 F:	drivers/vhost/vsock.h
+F:	tools/testing/vsock/
 
 VIRTIO CONSOLE DRIVER
 M:	Amit Shah <amit@kernel.org>
diff --git a/arch/blackfin/mach-bf518/boards/ezbrd.c b/arch/blackfin/mach-bf518/boards/ezbrd.c
index d022112927c2..c51d1b810ac3 100644
--- a/arch/blackfin/mach-bf518/boards/ezbrd.c
+++ b/arch/blackfin/mach-bf518/boards/ezbrd.c
@@ -25,7 +25,6 @@
 #include <asm/dpmc.h>
 #include <asm/bfin_sdh.h>
 #include <linux/spi/ad7877.h>
-#include <net/dsa.h>
 
 /*
  * Name the Board for the /proc/cpuinfo
@@ -105,11 +104,7 @@ static const unsigned short bfin_mac_peripherals[] = {
 
 static struct bfin_phydev_platform_data bfin_phydev_data[] = {
 	{
-#if IS_ENABLED(CONFIG_NET_DSA_KSZ8893M)
-		.addr = 3,
-#else
 		.addr = 1,
-#endif
 		.irq = IRQ_MAC_PHYINT,
 	},
 };
@@ -119,9 +114,6 @@ static struct bfin_mii_bus_platform_data bfin_mii_bus_data = {
 	.phydev_data = bfin_phydev_data,
 	.phy_mode = PHY_INTERFACE_MODE_MII,
 	.mac_peripherals = bfin_mac_peripherals,
-#if IS_ENABLED(CONFIG_NET_DSA_KSZ8893M)
-	.phy_mask = 0xfff7, /* Only probe the port phy connect to the on chip MAC */
-#endif
 	.vlan1_mask = 1,
 	.vlan2_mask = 2,
 };
@@ -140,29 +132,6 @@ static struct platform_device bfin_mac_device = {
 	}
 };
 
-#if IS_ENABLED(CONFIG_NET_DSA_KSZ8893M)
-static struct dsa_chip_data ksz8893m_switch_chip_data = {
-	.mii_bus = &bfin_mii_bus.dev,
-	.port_names = {
-		NULL,
-		"eth%d",
-		"eth%d",
-		"cpu",
-	},
-};
-static struct dsa_platform_data ksz8893m_switch_data = {
-	.nr_chips = 1,
-	.netdev = &bfin_mac_device.dev,
-	.chip = &ksz8893m_switch_chip_data,
-};
-
-static struct platform_device ksz8893m_switch_device = {
-	.name		= "dsa",
-	.id		= 0,
-	.num_resources	= 0,
-	.dev.platform_data = &ksz8893m_switch_data,
-};
-#endif
 #endif
 
 #if IS_ENABLED(CONFIG_MTD_M25P80)
@@ -228,19 +197,6 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = {
 	},
 #endif
 
-#if IS_ENABLED(CONFIG_BFIN_MAC)
-#if IS_ENABLED(CONFIG_NET_DSA_KSZ8893M)
-	{
-		.modalias = "ksz8893m",
-		.max_speed_hz = 5000000,
-		.bus_num = 0,
-		.chip_select = 1,
-		.platform_data = NULL,
-		.mode = SPI_MODE_3,
-	},
-#endif
-#endif
-
 #if IS_ENABLED(CONFIG_MMC_SPI)
 	{
 		.modalias = "mmc_spi",
@@ -714,9 +670,6 @@ static struct platform_device *stamp_devices[] __initdata = {
 #if IS_ENABLED(CONFIG_BFIN_MAC)
 	&bfin_mii_bus,
 	&bfin_mac_device,
-#if IS_ENABLED(CONFIG_NET_DSA_KSZ8893M)
-	&ksz8893m_switch_device,
-#endif
 #endif
 
 #if IS_ENABLED(CONFIG_SPI_BFIN5XX)
diff --git a/arch/blackfin/mach-bf518/boards/tcm-bf518.c b/arch/blackfin/mach-bf518/boards/tcm-bf518.c
index 240d5cb1f02c..37d868085f6a 100644
--- a/arch/blackfin/mach-bf518/boards/tcm-bf518.c
+++ b/arch/blackfin/mach-bf518/boards/tcm-bf518.c
@@ -25,7 +25,6 @@
 #include <asm/dpmc.h>
 #include <asm/bfin_sdh.h>
 #include <linux/spi/ad7877.h>
-#include <net/dsa.h>
 
 /*
  * Name the Board for the /proc/cpuinfo
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 1669240c7a25..b305f8247909 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -168,7 +168,6 @@ static int uml_net_open(struct net_device *dev)
 		goto out_close;
 	}
 
-	lp->tl.data = (unsigned long) &lp->user;
 	netif_start_queue(dev);
 
 	/* clear buffer - it can happen that the host side of the interface
@@ -278,10 +277,11 @@ static const struct ethtool_ops uml_net_ethtool_ops = {
 	.get_ts_info	= ethtool_op_get_ts_info,
 };
 
-static void uml_net_user_timer_expire(unsigned long _conn)
+static void uml_net_user_timer_expire(struct timer_list *t)
 {
 #ifdef undef
-	struct connection *conn = (struct connection *)_conn;
+	struct uml_net_private *lp = from_timer(lp, t, tl);
+	struct connection *conn = &lp->user;
 
 	dprintk(KERN_INFO "uml_net_user_timer_expire [%p]\n", conn);
 	do_connect(conn);
@@ -458,9 +458,8 @@ static void eth_configure(int n, void *init, char *mac,
 		  .add_address 		= transport->user->add_address,
 		  .delete_address  	= transport->user->delete_address });
 
-	init_timer(&lp->tl);
+	timer_setup(&lp->tl, uml_net_user_timer_expire, 0);
 	spin_lock_init(&lp->lock);
-	lp->tl.function = uml_net_user_timer_expire;
 	memcpy(lp->mac, dev->dev_addr, sizeof(lp->mac));
 
 	if ((transport->user->init != NULL) &&
diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c
index f8b7e86907cc..126855e6cb7d 100644
--- a/drivers/atm/fore200e.c
+++ b/drivers/atm/fore200e.c
@@ -358,26 +358,33 @@ fore200e_shutdown(struct fore200e* fore200e)
     case FORE200E_STATE_COMPLETE:
 	kfree(fore200e->stats);
 
+	/* fall through */
     case FORE200E_STATE_IRQ:
 	free_irq(fore200e->irq, fore200e->atm_dev);
 
+	/* fall through */
     case FORE200E_STATE_ALLOC_BUF:
 	fore200e_free_rx_buf(fore200e);
 
+	/* fall through */
     case FORE200E_STATE_INIT_BSQ:
 	fore200e_uninit_bs_queue(fore200e);
 
+	/* fall through */
     case FORE200E_STATE_INIT_RXQ:
 	fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_rxq.status);
 	fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_rxq.rpd);
 
+	/* fall through */
     case FORE200E_STATE_INIT_TXQ:
 	fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_txq.status);
 	fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_txq.tpd);
 
+	/* fall through */
     case FORE200E_STATE_INIT_CMDQ:
 	fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_cmdq.status);
 
+	/* fall through */
     case FORE200E_STATE_INITIALIZE:
 	/* nothing to do for that state */
 
@@ -390,6 +397,7 @@ fore200e_shutdown(struct fore200e* fore200e)
     case FORE200E_STATE_MAP:
 	fore200e->bus->unmap(fore200e);
 
+	/* fall through */
     case FORE200E_STATE_CONFIGURE:
 	/* nothing to do for that state */
 
diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c
index 082aa02abc57..d781b3f87693 100644
--- a/drivers/atm/idt77105.c
+++ b/drivers/atm/idt77105.c
@@ -306,11 +306,9 @@ static int idt77105_start(struct atm_dev *dev)
 	if (start_timer) {
 		start_timer = 0;
                 
-		setup_timer(&stats_timer, idt77105_stats_timer_func, 0UL);
 		stats_timer.expires = jiffies+IDT77105_STATS_TIMER_PERIOD;
 		add_timer(&stats_timer);
                 
-		setup_timer(&restart_timer, idt77105_restart_timer_func, 0UL);
 		restart_timer.expires = jiffies+IDT77105_RESTART_TIMER_PERIOD;
 		add_timer(&restart_timer);
 	}
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index 47f3c4ae0594..0e3b9c44c808 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -2073,21 +2073,19 @@ idt77252_rate_logindex(struct idt77252_dev *card, int pcr)
 }
 
 static void
-idt77252_est_timer(unsigned long data)
+idt77252_est_timer(struct timer_list *t)
 {
-	struct vc_map *vc = (struct vc_map *)data;
+	struct rate_estimator *est = from_timer(est, t, timer);
+	struct vc_map *vc = est->vc;
 	struct idt77252_dev *card = vc->card;
-	struct rate_estimator *est;
 	unsigned long flags;
 	u32 rate, cps;
 	u64 ncells;
 	u8 lacr;
 
 	spin_lock_irqsave(&vc->lock, flags);
-	est = vc->estimator;
-	if (!est)
+	if (!vc->estimator)
 		goto out;
-
 	ncells = est->cells;
 
 	rate = ((u32)(ncells - est->last_cells)) << (7 - est->interval);
@@ -2126,10 +2124,11 @@ idt77252_init_est(struct vc_map *vc, int pcr)
 	est->maxcps = pcr < 0 ? -pcr : pcr;
 	est->cps = est->maxcps;
 	est->avcps = est->cps << 5;
+	est->vc = vc;
 
 	est->interval = 2;		/* XXX: make this configurable */
 	est->ewma_log = 2;		/* XXX: make this configurable */
-	setup_timer(&est->timer, idt77252_est_timer, (unsigned long)vc);
+	timer_setup(&est->timer, idt77252_est_timer, 0);
 	mod_timer(&est->timer, jiffies + ((HZ / 4) << est->interval));
 
 	return est;
@@ -2209,16 +2208,20 @@ static int
 idt77252_init_ubr(struct idt77252_dev *card, struct vc_map *vc,
 		  struct atm_vcc *vcc, struct atm_qos *qos)
 {
+	struct rate_estimator *est = NULL;
 	unsigned long flags;
 	int tcr;
 
 	spin_lock_irqsave(&vc->lock, flags);
 	if (vc->estimator) {
-		del_timer(&vc->estimator->timer);
-		kfree(vc->estimator);
+		est = vc->estimator;
 		vc->estimator = NULL;
 	}
 	spin_unlock_irqrestore(&vc->lock, flags);
+	if (est) {
+		del_timer_sync(&est->timer);
+		kfree(est);
+	}
 
 	tcr = atm_pcr_goal(&qos->txtp);
 	if (tcr == 0)
diff --git a/drivers/atm/idt77252.h b/drivers/atm/idt77252.h
index 3a82cc23a053..9339197d701c 100644
--- a/drivers/atm/idt77252.h
+++ b/drivers/atm/idt77252.h
@@ -184,6 +184,8 @@ struct aal1 {
 	unsigned char		sequence;
 };
 
+struct vc_map;
+
 struct rate_estimator {
 	struct timer_list	timer;
 	unsigned int		interval;
@@ -193,6 +195,7 @@ struct rate_estimator {
 	long			avcps;
 	u32			cps;
 	u32			maxcps;
+	struct vc_map		*vc;
 };
 
 struct vc_map {
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index fc72b763fdd7..a785c6e69757 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -880,7 +880,7 @@ static void ia_phy_write(struct iadev_priv *iadev,
 
 static void ia_suni_pm7345_init_ds3(struct iadev_priv *iadev)
 {
-	static const struct ia_reg suni_ds3_init [] = {
+	static const struct ia_reg suni_ds3_init[] = {
 		{ SUNI_DS3_FRM_INTR_ENBL,	0x17 },
 		{ SUNI_DS3_FRM_CFG,		0x01 },
 		{ SUNI_DS3_TRAN_CFG,		0x01 },
@@ -898,7 +898,7 @@ static void ia_suni_pm7345_init_ds3(struct iadev_priv *iadev)
 
 static void ia_suni_pm7345_init_e3(struct iadev_priv *iadev)
 {
-	static const struct ia_reg suni_e3_init [] = {
+	static const struct ia_reg suni_e3_init[] = {
 		{ SUNI_E3_FRM_FRAM_OPTIONS,		0x04 },
 		{ SUNI_E3_FRM_MAINT_OPTIONS,		0x20 },
 		{ SUNI_E3_FRM_FRAM_INTR_ENBL,		0x1d },
@@ -918,7 +918,7 @@ static void ia_suni_pm7345_init_e3(struct iadev_priv *iadev)
 
 static void ia_suni_pm7345_init(struct iadev_priv *iadev)
 {
-	static const struct ia_reg suni_init [] = {
+	static const struct ia_reg suni_init[] = {
 		/* Enable RSOP loss of signal interrupt. */
 		{ SUNI_INTR_ENBL,		0x28 },
 		/* Clear error counters. */
diff --git a/drivers/atm/suni.c b/drivers/atm/suni.c
index b0363149b2fd..b8825f2d79e0 100644
--- a/drivers/atm/suni.c
+++ b/drivers/atm/suni.c
@@ -53,7 +53,7 @@ static DEFINE_SPINLOCK(sunis_lock);
     if (atomic_read(&stats->s) < 0) atomic_set(&stats->s,INT_MAX);
 
 
-static void suni_hz(unsigned long from_timer)
+static void suni_hz(struct timer_list *timer)
 {
 	struct suni_priv *walk;
 	struct atm_dev *dev;
@@ -85,7 +85,7 @@ static void suni_hz(unsigned long from_timer)
 		    ((GET(TACP_TCC) & 0xff) << 8) |
 		    ((GET(TACP_TCCM) & 7) << 16));
 	}
-	if (from_timer) mod_timer(&poll_timer,jiffies+HZ);
+	if (timer) mod_timer(&poll_timer,jiffies+HZ);
 }
 
 
@@ -322,13 +322,11 @@ static int suni_start(struct atm_dev *dev)
 		printk(KERN_WARNING "%s(itf %d): no signal\n",dev->type,
 		    dev->number);
 	PRIV(dev)->loop_mode = ATM_LM_NONE;
-	suni_hz(0); /* clear SUNI counters */
+	suni_hz(NULL); /* clear SUNI counters */
 	(void) fetch_stats(dev,NULL,1); /* clear kernel counters */
 	if (first) {
-		init_timer(&poll_timer);
+		timer_setup(&poll_timer, suni_hz, 0);
 		poll_timer.expires = jiffies+HZ;
-		poll_timer.function = suni_hz;
-		poll_timer.data = 1;
 #if 0
 printk(KERN_DEBUG "[u] p=0x%lx,n=0x%lx\n",(unsigned long) poll_timer.list.prev,
     (unsigned long) poll_timer.list.next);
diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig
index a2df1ad03463..02d78f6cecbb 100644
--- a/drivers/bcma/Kconfig
+++ b/drivers/bcma/Kconfig
@@ -11,14 +11,15 @@ menuconfig BCMA
 	  Bus driver for Broadcom specific Advanced Microcontroller Bus
 	  Architecture.
 
+if BCMA
+
 # Support for Block-I/O. SELECT this from the driver that needs it.
 config BCMA_BLOCKIO
 	bool
-	depends on BCMA
 
 config BCMA_HOST_PCI_POSSIBLE
 	bool
-	depends on BCMA && PCI = y
+	depends on PCI = y
 	default y
 
 config BCMA_HOST_PCI
@@ -29,7 +30,6 @@ config BCMA_HOST_PCI
 
 config BCMA_HOST_SOC
 	bool "Support for BCMA in a SoC"
-	depends on BCMA
 	help
 	  Host interface for a Broadcom AIX bus directly mapped into
 	  the memory. This only works with the Broadcom SoCs from the
@@ -39,7 +39,7 @@ config BCMA_HOST_SOC
 
 config BCMA_DRIVER_PCI
 	bool "BCMA Broadcom PCI core driver"
-	depends on BCMA && PCI
+	depends on PCI
 	default y
 	help
 	  BCMA bus may have many versions of PCIe core. This driver
@@ -55,13 +55,13 @@ config BCMA_DRIVER_PCI
 
 config BCMA_DRIVER_PCI_HOSTMODE
 	bool "Driver for PCI core working in hostmode"
-	depends on BCMA && MIPS && BCMA_DRIVER_PCI
+	depends on MIPS && BCMA_DRIVER_PCI
 	help
 	  PCI core hostmode operation (external PCI bus).
 
 config BCMA_DRIVER_MIPS
 	bool "BCMA Broadcom MIPS core driver"
-	depends on BCMA && MIPS
+	depends on MIPS
 	help
 	  Driver for the Broadcom MIPS core attached to Broadcom specific
 	  Advanced Microcontroller Bus.
@@ -92,7 +92,6 @@ config BCMA_NFLASH
 
 config BCMA_DRIVER_GMAC_CMN
 	bool "BCMA Broadcom GBIT MAC COMMON core driver"
-	depends on BCMA
 	help
 	  Driver for the Broadcom GBIT MAC COMMON core attached to Broadcom
 	  specific Advanced Microcontroller Bus.
@@ -101,7 +100,7 @@ config BCMA_DRIVER_GMAC_CMN
 
 config BCMA_DRIVER_GPIO
 	bool "BCMA GPIO driver"
-	depends on BCMA && GPIOLIB
+	depends on GPIOLIB
 	select GPIOLIB_IRQCHIP if BCMA_HOST_SOC
 	help
 	  Driver to provide access to the GPIO pins of the bcma bus.
@@ -110,8 +109,9 @@ config BCMA_DRIVER_GPIO
 
 config BCMA_DEBUG
 	bool "BCMA debugging"
-	depends on BCMA
 	help
 	  This turns on additional debugging messages.
 
 	  If unsure, say N
+
+endif # BCMA
diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c
index 89af807cf29c..5904ef1aa624 100644
--- a/drivers/bcma/driver_mips.c
+++ b/drivers/bcma/driver_mips.c
@@ -184,10 +184,11 @@ static void bcma_core_mips_print_irq(struct bcma_device *dev, unsigned int irq)
 {
 	int i;
 	static const char *irq_name[] = {"2(S)", "3", "4", "5", "6", "D", "I"};
-	printk(KERN_DEBUG KBUILD_MODNAME ": core 0x%04x, irq :", dev->id.id);
+
+	bcma_debug(dev->bus, "core 0x%04x, irq :", dev->id.id);
 	for (i = 0; i <= 6; i++)
-		printk(" %s%s", irq_name[i], i == irq ? "*" : " ");
-	printk("\n");
+		pr_cont(" %s%s", irq_name[i], i == irq ? "*" : " ");
+	pr_cont("\n");
 }
 
 static void bcma_core_mips_dump_irq(struct bcma_bus *bus)
diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index 98a60db8e5d1..60e1c7d6986d 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -66,6 +66,7 @@ config BT_HCIBTSDIO
 
 config BT_HCIUART
 	tristate "HCI UART driver"
+	depends on SERIAL_DEV_BUS || !SERIAL_DEV_BUS
 	depends on TTY
 	help
 	  Bluetooth HCI UART driver.
@@ -80,7 +81,6 @@ config BT_HCIUART
 config BT_HCIUART_SERDEV
 	bool
 	depends on SERIAL_DEV_BUS && BT_HCIUART
-	depends on SERIAL_DEV_BUS=y || SERIAL_DEV_BUS=BT_HCIUART
 	default y
 
 config BT_HCIUART_H4
@@ -170,6 +170,7 @@ config BT_HCIUART_BCM
 	bool "Broadcom protocol support"
 	depends on BT_HCIUART
 	depends on BT_HCIUART_SERDEV
+	depends on (!ACPI || SERIAL_DEV_CTRL_TTYPORT)
 	select BT_HCIUART_H4
 	select BT_BCM
 	help
diff --git a/drivers/bluetooth/bcm203x.c b/drivers/bluetooth/bcm203x.c
index 5ce6d4176dc3..8e9547f195ef 100644
--- a/drivers/bluetooth/bcm203x.c
+++ b/drivers/bluetooth/bcm203x.c
@@ -121,7 +121,7 @@ static void bcm203x_complete(struct urb *urb)
 		}
 
 		data->state = BCM203X_LOAD_FIRMWARE;
-
+		/* fall through */
 	case BCM203X_LOAD_FIRMWARE:
 		if (data->fw_sent == data->fw_size) {
 			usb_fill_int_urb(urb, udev, usb_rcvintpipe(udev, BCM203X_IN_EP),
diff --git a/drivers/bluetooth/bluecard_cs.c b/drivers/bluetooth/bluecard_cs.c
index b07ca9565291..d513ef4743dc 100644
--- a/drivers/bluetooth/bluecard_cs.c
+++ b/drivers/bluetooth/bluecard_cs.c
@@ -156,9 +156,9 @@ static void bluecard_detach(struct pcmcia_device *p_dev);
 /* ======================== LED handling routines ======================== */
 
 
-static void bluecard_activity_led_timeout(u_long arg)
+static void bluecard_activity_led_timeout(struct timer_list *t)
 {
-	struct bluecard_info *info = (struct bluecard_info *)arg;
+	struct bluecard_info *info = from_timer(info, t, timer);
 	unsigned int iobase = info->p_dev->resource[0]->start;
 
 	if (test_bit(CARD_ACTIVITY, &(info->hw_state))) {
@@ -691,8 +691,7 @@ static int bluecard_open(struct bluecard_info *info)
 
 	spin_lock_init(&(info->lock));
 
-	setup_timer(&(info->timer), &bluecard_activity_led_timeout,
-		    (u_long)info);
+	timer_setup(&info->timer, bluecard_activity_led_timeout, 0);
 
 	skb_queue_head_init(&(info->txq));
 
diff --git a/drivers/bluetooth/bpa10x.c b/drivers/bluetooth/bpa10x.c
index 48d10cb5c9a1..7971bfbd4321 100644
--- a/drivers/bluetooth/bpa10x.c
+++ b/drivers/bluetooth/bpa10x.c
@@ -117,7 +117,7 @@ static void bpa10x_rx_complete(struct urb *urb)
 						bpa10x_recv_pkts,
 						ARRAY_SIZE(bpa10x_recv_pkts));
 		if (IS_ERR(data->rx_skb[idx])) {
-			BT_ERR("%s corrupted event packet", hdev->name);
+			bt_dev_err(hdev, "corrupted event packet");
 			hdev->stat.err_rx++;
 			data->rx_skb[idx] = NULL;
 		}
@@ -127,8 +127,7 @@ static void bpa10x_rx_complete(struct urb *urb)
 
 	err = usb_submit_urb(urb, GFP_ATOMIC);
 	if (err < 0) {
-		BT_ERR("%s urb %p failed to resubmit (%d)",
-						hdev->name, urb, -err);
+		bt_dev_err(hdev, "urb %p failed to resubmit (%d)", urb, -err);
 		usb_unanchor_urb(urb);
 	}
 }
@@ -164,8 +163,7 @@ static inline int bpa10x_submit_intr_urb(struct hci_dev *hdev)
 
 	err = usb_submit_urb(urb, GFP_KERNEL);
 	if (err < 0) {
-		BT_ERR("%s urb %p submission failed (%d)",
-						hdev->name, urb, -err);
+		bt_dev_err(hdev, "urb %p submission failed (%d)", urb, -err);
 		usb_unanchor_urb(urb);
 	}
 
@@ -205,8 +203,7 @@ static inline int bpa10x_submit_bulk_urb(struct hci_dev *hdev)
 
 	err = usb_submit_urb(urb, GFP_KERNEL);
 	if (err < 0) {
-		BT_ERR("%s urb %p submission failed (%d)",
-						hdev->name, urb, -err);
+		bt_dev_err(hdev, "urb %p submission failed (%d)", urb, -err);
 		usb_unanchor_urb(urb);
 	}
 
@@ -272,7 +269,7 @@ static int bpa10x_setup(struct hci_dev *hdev)
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
-	BT_INFO("%s: %s", hdev->name, (char *)(skb->data + 1));
+	bt_dev_info(hdev, "%s", (char *)(skb->data + 1));
 
 	hci_set_fw_info(hdev, "%s", skb->data + 1);
 
@@ -348,7 +345,7 @@ static int bpa10x_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 
 	err = usb_submit_urb(urb, GFP_ATOMIC);
 	if (err < 0) {
-		BT_ERR("%s urb %p submission failed", hdev->name, urb);
+		bt_dev_err(hdev, "urb %p submission failed", urb);
 		kfree(urb->setup_packet);
 		usb_unanchor_urb(urb);
 	}
diff --git a/drivers/bluetooth/bt3c_cs.c b/drivers/bluetooth/bt3c_cs.c
index 194788739a83..25b0cf952b91 100644
--- a/drivers/bluetooth/bt3c_cs.c
+++ b/drivers/bluetooth/bt3c_cs.c
@@ -355,7 +355,7 @@ static irqreturn_t bt3c_interrupt(int irq, void *dev_inst)
 		} else if ((stat & 0xff) != 0xff) {
 			if (stat & 0x0020) {
 				int status = bt3c_read(iobase, 0x7002) & 0x10;
-				BT_INFO("%s: Antenna %s", info->hdev->name,
+				bt_dev_info(info->hdev, "Antenna %s",
 							status ? "out" : "in");
 			}
 			if (stat & 0x0001)
diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c
index cc4bdefa6648..afa4cb3b16e3 100644
--- a/drivers/bluetooth/btbcm.c
+++ b/drivers/bluetooth/btbcm.c
@@ -45,13 +45,12 @@ int btbcm_check_bdaddr(struct hci_dev *hdev)
 			     HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		int err = PTR_ERR(skb);
-		BT_ERR("%s: BCM: Reading device address failed (%d)",
-		       hdev->name, err);
+		bt_dev_err(hdev, "BCM: Reading device address failed (%d)", err);
 		return err;
 	}
 
 	if (skb->len != sizeof(*bda)) {
-		BT_ERR("%s: BCM: Device address length mismatch", hdev->name);
+		bt_dev_err(hdev, "BCM: Device address length mismatch");
 		kfree_skb(skb);
 		return -EIO;
 	}
@@ -74,8 +73,8 @@ int btbcm_check_bdaddr(struct hci_dev *hdev)
 	if (!bacmp(&bda->bdaddr, BDADDR_BCM20702A0) ||
 	    !bacmp(&bda->bdaddr, BDADDR_BCM4324B3) ||
 	    !bacmp(&bda->bdaddr, BDADDR_BCM4330B1)) {
-		BT_INFO("%s: BCM: Using default device address (%pMR)",
-			hdev->name, &bda->bdaddr);
+		bt_dev_info(hdev, "BCM: Using default device address (%pMR)",
+			    &bda->bdaddr);
 		set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
 	}
 
@@ -93,8 +92,7 @@ int btbcm_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 	skb = __hci_cmd_sync(hdev, 0xfc01, 6, bdaddr, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
-		BT_ERR("%s: BCM: Change address command failed (%d)",
-		       hdev->name, err);
+		bt_dev_err(hdev, "BCM: Change address command failed (%d)", err);
 		return err;
 	}
 	kfree_skb(skb);
@@ -116,8 +114,8 @@ int btbcm_patchram(struct hci_dev *hdev, const struct firmware *fw)
 	skb = __hci_cmd_sync(hdev, 0xfc2e, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
-		BT_ERR("%s: BCM: Download Minidrv command failed (%d)",
-		       hdev->name, err);
+		bt_dev_err(hdev, "BCM: Download Minidrv command failed (%d)",
+			   err);
 		goto done;
 	}
 	kfree_skb(skb);
@@ -136,7 +134,7 @@ int btbcm_patchram(struct hci_dev *hdev, const struct firmware *fw)
 		fw_size -= sizeof(*cmd);
 
 		if (fw_size < cmd->plen) {
-			BT_ERR("%s: BCM: Patch is corrupted", hdev->name);
+			bt_dev_err(hdev, "BCM: Patch is corrupted");
 			err = -EINVAL;
 			goto done;
 		}
@@ -151,8 +149,8 @@ int btbcm_patchram(struct hci_dev *hdev, const struct firmware *fw)
 				     HCI_INIT_TIMEOUT);
 		if (IS_ERR(skb)) {
 			err = PTR_ERR(skb);
-			BT_ERR("%s: BCM: Patch command %04x failed (%d)",
-			       hdev->name, opcode, err);
+			bt_dev_err(hdev, "BCM: Patch command %04x failed (%d)",
+				   opcode, err);
 			goto done;
 		}
 		kfree_skb(skb);
@@ -173,7 +171,7 @@ static int btbcm_reset(struct hci_dev *hdev)
 	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		int err = PTR_ERR(skb);
-		BT_ERR("%s: BCM: Reset failed (%d)", hdev->name, err);
+		bt_dev_err(hdev, "BCM: Reset failed (%d)", err);
 		return err;
 	}
 	kfree_skb(skb);
@@ -191,13 +189,13 @@ static struct sk_buff *btbcm_read_local_name(struct hci_dev *hdev)
 	skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_NAME, 0, NULL,
 			     HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s: BCM: Reading local name failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		bt_dev_err(hdev, "BCM: Reading local name failed (%ld)",
+			   PTR_ERR(skb));
 		return skb;
 	}
 
 	if (skb->len != sizeof(struct hci_rp_read_local_name)) {
-		BT_ERR("%s: BCM: Local name length mismatch", hdev->name);
+		bt_dev_err(hdev, "BCM: Local name length mismatch");
 		kfree_skb(skb);
 		return ERR_PTR(-EIO);
 	}
@@ -212,13 +210,13 @@ static struct sk_buff *btbcm_read_local_version(struct hci_dev *hdev)
 	skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL,
 			     HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s: BCM: Reading local version info failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		bt_dev_err(hdev, "BCM: Reading local version info failed (%ld)",
+			   PTR_ERR(skb));
 		return skb;
 	}
 
 	if (skb->len != sizeof(struct hci_rp_read_local_version)) {
-		BT_ERR("%s: BCM: Local version length mismatch", hdev->name);
+		bt_dev_err(hdev, "BCM: Local version length mismatch");
 		kfree_skb(skb);
 		return ERR_PTR(-EIO);
 	}
@@ -232,13 +230,13 @@ static struct sk_buff *btbcm_read_verbose_config(struct hci_dev *hdev)
 
 	skb = __hci_cmd_sync(hdev, 0xfc79, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s: BCM: Read verbose config info failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		bt_dev_err(hdev, "BCM: Read verbose config info failed (%ld)",
+			   PTR_ERR(skb));
 		return skb;
 	}
 
 	if (skb->len != 7) {
-		BT_ERR("%s: BCM: Verbose config length mismatch", hdev->name);
+		bt_dev_err(hdev, "BCM: Verbose config length mismatch");
 		kfree_skb(skb);
 		return ERR_PTR(-EIO);
 	}
@@ -252,14 +250,13 @@ static struct sk_buff *btbcm_read_controller_features(struct hci_dev *hdev)
 
 	skb = __hci_cmd_sync(hdev, 0xfc6e, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s: BCM: Read controller features failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		bt_dev_err(hdev, "BCM: Read controller features failed (%ld)",
+			   PTR_ERR(skb));
 		return skb;
 	}
 
 	if (skb->len != 9) {
-		BT_ERR("%s: BCM: Controller features length mismatch",
-		       hdev->name);
+		bt_dev_err(hdev, "BCM: Controller features length mismatch");
 		kfree_skb(skb);
 		return ERR_PTR(-EIO);
 	}
@@ -273,13 +270,13 @@ static struct sk_buff *btbcm_read_usb_product(struct hci_dev *hdev)
 
 	skb = __hci_cmd_sync(hdev, 0xfc5a, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s: BCM: Read USB product info failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		bt_dev_err(hdev, "BCM: Read USB product info failed (%ld)",
+			   PTR_ERR(skb));
 		return skb;
 	}
 
 	if (skb->len != 5) {
-		BT_ERR("%s: BCM: USB product length mismatch", hdev->name);
+		bt_dev_err(hdev, "BCM: USB product length mismatch");
 		kfree_skb(skb);
 		return ERR_PTR(-EIO);
 	}
@@ -296,7 +293,7 @@ static int btbcm_read_info(struct hci_dev *hdev)
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
-	BT_INFO("%s: BCM: chip id %u", hdev->name, skb->data[1]);
+	bt_dev_info(hdev, "BCM: chip id %u", skb->data[1]);
 	kfree_skb(skb);
 
 	/* Read Controller Features */
@@ -304,7 +301,7 @@ static int btbcm_read_info(struct hci_dev *hdev)
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
-	BT_INFO("%s: BCM: features 0x%2.2x", hdev->name, skb->data[1]);
+	bt_dev_info(hdev, "BCM: features 0x%2.2x", skb->data[1]);
 	kfree_skb(skb);
 
 	/* Read Local Name */
@@ -312,7 +309,7 @@ static int btbcm_read_info(struct hci_dev *hdev)
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
-	BT_INFO("%s: %s", hdev->name, (char *)(skb->data + 1));
+	bt_dev_info(hdev, "%s", (char *)(skb->data + 1));
 	kfree_skb(skb);
 
 	return 0;
@@ -327,6 +324,8 @@ static const struct {
 	{ 0x4406, "BCM4324B3"	},	/* 002.004.006 */
 	{ 0x610c, "BCM4354"	},	/* 003.001.012 */
 	{ 0x2209, "BCM43430A1"  },	/* 001.002.009 */
+	{ 0x6119, "BCM4345C0"	},	/* 003.001.025 */
+	{ 0x230f, "BCM4356A2"	},	/* 001.003.015 */
 	{ }
 };
 
@@ -361,6 +360,7 @@ int btbcm_initialize(struct hci_dev *hdev, char *fw_name, size_t len)
 	switch ((rev & 0xf000) >> 12) {
 	case 0:
 	case 1:
+	case 2:
 	case 3:
 		for (i = 0; bcm_uart_subver_table[i].name; i++) {
 			if (subver == bcm_uart_subver_table[i].subver) {
@@ -375,9 +375,9 @@ int btbcm_initialize(struct hci_dev *hdev, char *fw_name, size_t len)
 		return 0;
 	}
 
-	BT_INFO("%s: %s (%3.3u.%3.3u.%3.3u) build %4.4u", hdev->name,
-		hw_name ? : "BCM", (subver & 0xe000) >> 13,
-		(subver & 0x1f00) >> 8, (subver & 0x00ff), rev & 0x0fff);
+	bt_dev_info(hdev, "%s (%3.3u.%3.3u.%3.3u) build %4.4u",
+		    hw_name ? : "BCM", (subver & 0xe000) >> 13,
+		    (subver & 0x1f00) >> 8, (subver & 0x00ff), rev & 0x0fff);
 
 	return 0;
 }
@@ -405,9 +405,9 @@ int btbcm_finalize(struct hci_dev *hdev)
 	subver = le16_to_cpu(ver->lmp_subver);
 	kfree_skb(skb);
 
-	BT_INFO("%s: BCM (%3.3u.%3.3u.%3.3u) build %4.4u", hdev->name,
-		(subver & 0xe000) >> 13, (subver & 0x1f00) >> 8,
-		(subver & 0x00ff), rev & 0x0fff);
+	bt_dev_info(hdev, "BCM (%3.3u.%3.3u.%3.3u) build %4.4u",
+		    (subver & 0xe000) >> 13, (subver & 0x1f00) >> 8,
+		    (subver & 0x00ff), rev & 0x0fff);
 
 	btbcm_check_bdaddr(hdev);
 
@@ -502,13 +502,13 @@ int btbcm_setup_patchram(struct hci_dev *hdev)
 		return 0;
 	}
 
-	BT_INFO("%s: %s (%3.3u.%3.3u.%3.3u) build %4.4u", hdev->name,
-		hw_name ? : "BCM", (subver & 0xe000) >> 13,
-		(subver & 0x1f00) >> 8, (subver & 0x00ff), rev & 0x0fff);
+	bt_dev_info(hdev, "%s (%3.3u.%3.3u.%3.3u) build %4.4u",
+		    hw_name ? : "BCM", (subver & 0xe000) >> 13,
+		    (subver & 0x1f00) >> 8, (subver & 0x00ff), rev & 0x0fff);
 
 	err = request_firmware(&fw, fw_name, &hdev->dev);
 	if (err < 0) {
-		BT_INFO("%s: BCM: Patch %s not found", hdev->name, fw_name);
+		bt_dev_info(hdev, "BCM: Patch %s not found", fw_name);
 		goto done;
 	}
 
@@ -531,16 +531,16 @@ int btbcm_setup_patchram(struct hci_dev *hdev)
 	subver = le16_to_cpu(ver->lmp_subver);
 	kfree_skb(skb);
 
-	BT_INFO("%s: %s (%3.3u.%3.3u.%3.3u) build %4.4u", hdev->name,
-		hw_name ? : "BCM", (subver & 0xe000) >> 13,
-		(subver & 0x1f00) >> 8, (subver & 0x00ff), rev & 0x0fff);
+	bt_dev_info(hdev, "%s (%3.3u.%3.3u.%3.3u) build %4.4u",
+		    hw_name ? : "BCM", (subver & 0xe000) >> 13,
+		    (subver & 0x1f00) >> 8, (subver & 0x00ff), rev & 0x0fff);
 
 	/* Read Local Name */
 	skb = btbcm_read_local_name(hdev);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
-	BT_INFO("%s: %s", hdev->name, (char *)(skb->data + 1));
+	bt_dev_info(hdev, "%s", (char *)(skb->data + 1));
 	kfree_skb(skb);
 
 done:
@@ -565,31 +565,31 @@ int btbcm_setup_apple(struct hci_dev *hdev)
 	/* Read Verbose Config Version Info */
 	skb = btbcm_read_verbose_config(hdev);
 	if (!IS_ERR(skb)) {
-		BT_INFO("%s: BCM: chip id %u build %4.4u", hdev->name,
-			skb->data[1], get_unaligned_le16(skb->data + 5));
+		bt_dev_info(hdev, "BCM: chip id %u build %4.4u",
+			    skb->data[1], get_unaligned_le16(skb->data + 5));
 		kfree_skb(skb);
 	}
 
 	/* Read USB Product Info */
 	skb = btbcm_read_usb_product(hdev);
 	if (!IS_ERR(skb)) {
-		BT_INFO("%s: BCM: product %4.4x:%4.4x", hdev->name,
-			get_unaligned_le16(skb->data + 1),
-			get_unaligned_le16(skb->data + 3));
+		bt_dev_info(hdev, "BCM: product %4.4x:%4.4x",
+			    get_unaligned_le16(skb->data + 1),
+			    get_unaligned_le16(skb->data + 3));
 		kfree_skb(skb);
 	}
 
 	/* Read Controller Features */
 	skb = btbcm_read_controller_features(hdev);
 	if (!IS_ERR(skb)) {
-		BT_INFO("%s: BCM: features 0x%2.2x", hdev->name, skb->data[1]);
+		bt_dev_info(hdev, "BCM: features 0x%2.2x", skb->data[1]);
 		kfree_skb(skb);
 	}
 
 	/* Read Local Name */
 	skb = btbcm_read_local_name(hdev);
 	if (!IS_ERR(skb)) {
-		BT_INFO("%s: %s", hdev->name, (char *)(skb->data + 1));
+		bt_dev_info(hdev, "%s", (char *)(skb->data + 1));
 		kfree_skb(skb);
 	}
 
diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index d32e109bd5cb..4459555c9d88 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -43,13 +43,13 @@ int btintel_check_bdaddr(struct hci_dev *hdev)
 			     HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		int err = PTR_ERR(skb);
-		BT_ERR("%s: Reading Intel device address failed (%d)",
-		       hdev->name, err);
+		bt_dev_err(hdev, "Reading Intel device address failed (%d)",
+			   err);
 		return err;
 	}
 
 	if (skb->len != sizeof(*bda)) {
-		BT_ERR("%s: Intel device address length mismatch", hdev->name);
+		bt_dev_err(hdev, "Intel device address length mismatch");
 		kfree_skb(skb);
 		return -EIO;
 	}
@@ -62,8 +62,8 @@ int btintel_check_bdaddr(struct hci_dev *hdev)
 	 * and that in turn can cause problems with Bluetooth operation.
 	 */
 	if (!bacmp(&bda->bdaddr, BDADDR_INTEL)) {
-		BT_ERR("%s: Found Intel default device address (%pMR)",
-		       hdev->name, &bda->bdaddr);
+		bt_dev_err(hdev, "Found Intel default device address (%pMR)",
+			   &bda->bdaddr);
 		set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
 	}
 
@@ -123,8 +123,8 @@ int btintel_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 	skb = __hci_cmd_sync(hdev, 0xfc31, 6, bdaddr, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
-		BT_ERR("%s: Changing Intel device address failed (%d)",
-		       hdev->name, err);
+		bt_dev_err(hdev, "Changing Intel device address failed (%d)",
+			   err);
 		return err;
 	}
 	kfree_skb(skb);
@@ -154,8 +154,8 @@ int btintel_set_diag(struct hci_dev *hdev, bool enable)
 		err = PTR_ERR(skb);
 		if (err == -ENODATA)
 			goto done;
-		BT_ERR("%s: Changing Intel diagnostic mode failed (%d)",
-		       hdev->name, err);
+		bt_dev_err(hdev, "Changing Intel diagnostic mode failed (%d)",
+			   err);
 		return err;
 	}
 	kfree_skb(skb);
@@ -189,30 +189,30 @@ void btintel_hw_error(struct hci_dev *hdev, u8 code)
 	struct sk_buff *skb;
 	u8 type = 0x00;
 
-	BT_ERR("%s: Hardware error 0x%2.2x", hdev->name, code);
+	bt_dev_err(hdev, "Hardware error 0x%2.2x", code);
 
 	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s: Reset after hardware error failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		bt_dev_err(hdev, "Reset after hardware error failed (%ld)",
+			   PTR_ERR(skb));
 		return;
 	}
 	kfree_skb(skb);
 
 	skb = __hci_cmd_sync(hdev, 0xfc22, 1, &type, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s: Retrieving Intel exception info failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		bt_dev_err(hdev, "Retrieving Intel exception info failed (%ld)",
+			   PTR_ERR(skb));
 		return;
 	}
 
 	if (skb->len != 13) {
-		BT_ERR("%s: Exception info size mismatch", hdev->name);
+		bt_dev_err(hdev, "Exception info size mismatch");
 		kfree_skb(skb);
 		return;
 	}
 
-	BT_ERR("%s: Exception info %s", hdev->name, (char *)(skb->data + 1));
+	bt_dev_err(hdev, "Exception info %s", (char *)(skb->data + 1));
 
 	kfree_skb(skb);
 }
@@ -233,9 +233,10 @@ void btintel_version_info(struct hci_dev *hdev, struct intel_version *ver)
 		return;
 	}
 
-	BT_INFO("%s: %s revision %u.%u build %u week %u %u", hdev->name,
-		variant, ver->fw_revision >> 4, ver->fw_revision & 0x0f,
-		ver->fw_build_num, ver->fw_build_ww, 2000 + ver->fw_build_yy);
+	bt_dev_info(hdev, "%s revision %u.%u build %u week %u %u",
+		    variant, ver->fw_revision >> 4, ver->fw_revision & 0x0f,
+		    ver->fw_build_num, ver->fw_build_ww,
+		    2000 + ver->fw_build_yy);
 }
 EXPORT_SYMBOL_GPL(btintel_version_info);
 
@@ -321,8 +322,7 @@ int btintel_set_event_mask(struct hci_dev *hdev, bool debug)
 	skb = __hci_cmd_sync(hdev, 0xfc52, 8, mask, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
-		BT_ERR("%s: Setting Intel event mask failed (%d)",
-		       hdev->name, err);
+		bt_dev_err(hdev, "Setting Intel event mask failed (%d)", err);
 		return err;
 	}
 	kfree_skb(skb);
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index 03341ce98c32..7dbb4463b539 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -64,7 +64,7 @@ static irqreturn_t btmrvl_wake_irq_bt(int irq, void *priv)
 	struct btmrvl_sdio_card *card = priv;
 	struct btmrvl_plt_wake_cfg *cfg = card->plt_wake_cfg;
 
-	pr_info("%s: wake by bt", __func__);
+	pr_info("%s: wake by bt\n", __func__);
 	cfg->wake_by_bt = true;
 	disable_irq_nosync(irq);
 
@@ -87,7 +87,7 @@ static int btmrvl_sdio_probe_of(struct device *dev,
 
 	if (!dev->of_node ||
 	    !of_match_node(btmrvl_sdio_of_match_table, dev->of_node)) {
-		pr_err("sdio platform data not available");
+		pr_err("sdio platform data not available\n");
 		return -1;
 	}
 
@@ -99,7 +99,7 @@ static int btmrvl_sdio_probe_of(struct device *dev,
 	if (cfg && card->plt_of_node) {
 		cfg->irq_bt = irq_of_parse_and_map(card->plt_of_node, 0);
 		if (!cfg->irq_bt) {
-			dev_err(dev, "fail to parse irq_bt from device tree");
+			dev_err(dev, "fail to parse irq_bt from device tree\n");
 			cfg->irq_bt = -1;
 		} else {
 			ret = devm_request_irq(dev, cfg->irq_bt,
diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index 0bbdfcef2aa8..2793d4180d2f 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -287,7 +287,7 @@ static int rome_download_firmware(struct hci_dev *hdev,
 	const struct firmware *fw;
 	int ret;
 
-	BT_INFO("%s: ROME Downloading %s", hdev->name, config->fwname);
+	bt_dev_info(hdev, "ROME Downloading %s", config->fwname);
 
 	ret = request_firmware(&fw, config->fwname, &hdev->dev);
 	if (ret) {
@@ -351,7 +351,7 @@ int qca_uart_setup_rome(struct hci_dev *hdev, uint8_t baudrate)
 		return err;
 	}
 
-	BT_INFO("%s: ROME controller version 0x%08x", hdev->name, rome_ver);
+	bt_dev_info(hdev, "ROME controller version 0x%08x", rome_ver);
 
 	/* Download rampatch file */
 	config.type = TLV_TYPE_PATCH;
@@ -380,7 +380,7 @@ int qca_uart_setup_rome(struct hci_dev *hdev, uint8_t baudrate)
 		return err;
 	}
 
-	BT_INFO("%s: ROME setup on UART is completed", hdev->name);
+	bt_dev_info(hdev, "ROME setup on UART is completed");
 
 	return 0;
 }
diff --git a/drivers/bluetooth/btqcomsmd.c b/drivers/bluetooth/btqcomsmd.c
index d00c4fdae924..663bed63b871 100644
--- a/drivers/bluetooth/btqcomsmd.c
+++ b/drivers/bluetooth/btqcomsmd.c
@@ -15,6 +15,8 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/rpmsg.h>
+#include <linux/of.h>
+
 #include <linux/soc/qcom/wcnss_ctrl.h>
 #include <linux/platform_device.h>
 
@@ -26,6 +28,7 @@
 struct btqcomsmd {
 	struct hci_dev *hdev;
 
+	bdaddr_t bdaddr;
 	struct rpmsg_endpoint *acl_channel;
 	struct rpmsg_endpoint *cmd_channel;
 };
@@ -100,6 +103,38 @@ static int btqcomsmd_close(struct hci_dev *hdev)
 	return 0;
 }
 
+static int btqcomsmd_setup(struct hci_dev *hdev)
+{
+	struct btqcomsmd *btq = hci_get_drvdata(hdev);
+	struct sk_buff *skb;
+	int err;
+
+	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+	kfree_skb(skb);
+
+	/* Devices do not have persistent storage for BD address. If no
+	 * BD address has been retrieved during probe, mark the device
+	 * as having an invalid BD address.
+	 */
+	if (!bacmp(&btq->bdaddr, BDADDR_ANY)) {
+		set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
+		return 0;
+	}
+
+	/* When setting a configured BD address fails, mark the device
+	 * as having an invalid BD address.
+	 */
+	err = qca_set_bdaddr_rome(hdev, &btq->bdaddr);
+	if (err) {
+		set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
+		return 0;
+	}
+
+	return 0;
+}
+
 static int btqcomsmd_probe(struct platform_device *pdev)
 {
 	struct btqcomsmd *btq;
@@ -123,6 +158,15 @@ static int btqcomsmd_probe(struct platform_device *pdev)
 	if (IS_ERR(btq->cmd_channel))
 		return PTR_ERR(btq->cmd_channel);
 
+	/* The local-bd-address property is usually injected by the
+	 * bootloader which has access to the allocated BD address.
+	 */
+	if (!of_property_read_u8_array(pdev->dev.of_node, "local-bd-address",
+				       (u8 *)&btq->bdaddr, sizeof(bdaddr_t))) {
+		dev_info(&pdev->dev, "BD address %pMR retrieved from device-tree",
+			 &btq->bdaddr);
+	}
+
 	hdev = hci_alloc_dev();
 	if (!hdev)
 		return -ENOMEM;
@@ -135,6 +179,7 @@ static int btqcomsmd_probe(struct platform_device *pdev)
 	hdev->open = btqcomsmd_open;
 	hdev->close = btqcomsmd_close;
 	hdev->send = btqcomsmd_send;
+	hdev->setup = btqcomsmd_setup;
 	hdev->set_bdaddr = qca_set_bdaddr_rome;
 
 	ret = hci_register_dev(hdev);
diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index d9a99b4302ea..6e2ad748abba 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -55,8 +55,8 @@ static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version)
 	}
 
 	rom_version = (struct rtl_rom_version_evt *)skb->data;
-	BT_INFO("%s: rom_version status=%x version=%x",
-		hdev->name, rom_version->status, rom_version->version);
+	bt_dev_info(hdev, "rom_version status=%x version=%x",
+		    rom_version->status, rom_version->version);
 
 	*version = rom_version->version;
 
@@ -273,7 +273,7 @@ static int rtl_load_config(struct hci_dev *hdev, const char *name, u8 **buff)
 	const struct firmware *fw;
 	int ret;
 
-	BT_INFO("%s: rtl: loading %s", hdev->name, name);
+	bt_dev_info(hdev, "rtl: loading %s", name);
 	ret = request_firmware(&fw, name, &hdev->dev);
 	if (ret < 0)
 		return ret;
@@ -292,7 +292,7 @@ static int btrtl_setup_rtl8723a(struct hci_dev *hdev)
 	const struct firmware *fw;
 	int ret;
 
-	BT_INFO("%s: rtl: loading rtl_bt/rtl8723a_fw.bin", hdev->name);
+	bt_dev_info(hdev, "rtl: loading rtl_bt/rtl8723a_fw.bin");
 	ret = request_firmware(&fw, "rtl_bt/rtl8723a_fw.bin", &hdev->dev);
 	if (ret < 0) {
 		BT_ERR("%s: Failed to load rtl_bt/rtl8723a_fw.bin", hdev->name);
@@ -363,7 +363,7 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver,
 	} else
 		cfg_sz = 0;
 
-	BT_INFO("%s: rtl: loading %s", hdev->name, fw_name);
+	bt_dev_info(hdev, "rtl: loading %s", fw_name);
 	ret = request_firmware(&fw, fw_name, &hdev->dev);
 	if (ret < 0) {
 		BT_ERR("%s: Failed to load %s", hdev->name, fw_name);
@@ -390,7 +390,7 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver,
 		fw_data = tbuff;
 	}
 
-	BT_INFO("cfg_sz %d, total size %d", cfg_sz, ret);
+	bt_dev_info(hdev, "cfg_sz %d, total size %d", cfg_sz, ret);
 
 	ret = rtl_download_firmware(hdev, fw_data, ret);
 
@@ -436,9 +436,10 @@ int btrtl_setup_realtek(struct hci_dev *hdev)
 		return -PTR_ERR(skb);
 
 	resp = (struct hci_rp_read_local_version *)skb->data;
-	BT_INFO("%s: rtl: examining hci_ver=%02x hci_rev=%04x lmp_ver=%02x "
-		"lmp_subver=%04x", hdev->name, resp->hci_ver, resp->hci_rev,
-		resp->lmp_ver, resp->lmp_subver);
+	bt_dev_info(hdev, "rtl: examining hci_ver=%02x hci_rev=%04x "
+		    "lmp_ver=%02x lmp_subver=%04x",
+		    resp->hci_ver, resp->hci_rev,
+		    resp->lmp_ver, resp->lmp_subver);
 
 	lmp_subver = le16_to_cpu(resp->lmp_subver);
 	kfree_skb(skb);
@@ -466,7 +467,7 @@ int btrtl_setup_realtek(struct hci_dev *hdev)
 		return btrtl_setup_rtl8723b(hdev, lmp_subver,
 					    "rtl_bt/rtl8822b_fw.bin");
 	default:
-		BT_INFO("rtl: assuming no firmware upload needed.");
+		bt_dev_info(hdev, "rtl: assuming no firmware upload needed");
 		return 0;
 	}
 }
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 7a5c06aaa181..f7120c9eb9bd 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -66,7 +66,6 @@ static struct usb_driver btusb_driver;
 #define BTUSB_BCM2045		0x40000
 #define BTUSB_IFNUM_2		0x80000
 #define BTUSB_CW6622		0x100000
-#define BTUSB_BCM_NO_PRODID	0x200000
 
 static const struct usb_device_id btusb_table[] = {
 	/* Generic Bluetooth USB device */
@@ -171,10 +170,6 @@ static const struct usb_device_id btusb_table[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0930, 0xff, 0x01, 0x01),
 	  .driver_info = BTUSB_BCM_PATCHRAM },
 
-	/* Broadcom devices with missing product id */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x0000, 0x0000, 0xff, 0x01, 0x01),
-	  .driver_info = BTUSB_BCM_PATCHRAM | BTUSB_BCM_NO_PRODID },
-
 	/* Intel Bluetooth USB Bootloader (RAM module) */
 	{ USB_DEVICE(0x8087, 0x0a5a),
 	  .driver_info = BTUSB_INTEL_BOOT | BTUSB_BROKEN_ISOC },
@@ -272,6 +267,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0cf3, 0xe301), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe360), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0489, 0xe092), .driver_info = BTUSB_QCA_ROME },
+	{ USB_DEVICE(0x0489, 0xe09f), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0489, 0xe0a2), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x04ca, 0x3011), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x04ca, 0x3016), .driver_info = BTUSB_QCA_ROME },
@@ -401,6 +397,7 @@ struct btusb_data {
 	struct usb_interface *intf;
 	struct usb_interface *isoc;
 	struct usb_interface *diag;
+	unsigned isoc_ifnum;
 
 	unsigned long flags;
 
@@ -647,7 +644,7 @@ static void btusb_intr_complete(struct urb *urb)
 
 		if (btusb_recv_intr(data, urb->transfer_buffer,
 				    urb->actual_length) < 0) {
-			BT_ERR("%s corrupted event packet", hdev->name);
+			bt_dev_err(hdev, "corrupted event packet");
 			hdev->stat.err_rx++;
 		}
 	} else if (urb->status == -ENOENT) {
@@ -667,8 +664,8 @@ static void btusb_intr_complete(struct urb *urb)
 		 * -ENODEV: device got disconnected
 		 */
 		if (err != -EPERM && err != -ENODEV)
-			BT_ERR("%s urb %p failed to resubmit (%d)",
-			       hdev->name, urb, -err);
+			bt_dev_err(hdev, "urb %p failed to resubmit (%d)",
+				   urb, -err);
 		usb_unanchor_urb(urb);
 	}
 }
@@ -710,8 +707,8 @@ static int btusb_submit_intr_urb(struct hci_dev *hdev, gfp_t mem_flags)
 	err = usb_submit_urb(urb, mem_flags);
 	if (err < 0) {
 		if (err != -EPERM && err != -ENODEV)
-			BT_ERR("%s urb %p submission failed (%d)",
-			       hdev->name, urb, -err);
+			bt_dev_err(hdev, "urb %p submission failed (%d)",
+				   urb, -err);
 		usb_unanchor_urb(urb);
 	}
 
@@ -737,7 +734,7 @@ static void btusb_bulk_complete(struct urb *urb)
 
 		if (data->recv_bulk(data, urb->transfer_buffer,
 				    urb->actual_length) < 0) {
-			BT_ERR("%s corrupted ACL packet", hdev->name);
+			bt_dev_err(hdev, "corrupted ACL packet");
 			hdev->stat.err_rx++;
 		}
 	} else if (urb->status == -ENOENT) {
@@ -757,8 +754,8 @@ static void btusb_bulk_complete(struct urb *urb)
 		 * -ENODEV: device got disconnected
 		 */
 		if (err != -EPERM && err != -ENODEV)
-			BT_ERR("%s urb %p failed to resubmit (%d)",
-			       hdev->name, urb, -err);
+			bt_dev_err(hdev, "urb %p failed to resubmit (%d)",
+				   urb, -err);
 		usb_unanchor_urb(urb);
 	}
 }
@@ -799,8 +796,8 @@ static int btusb_submit_bulk_urb(struct hci_dev *hdev, gfp_t mem_flags)
 	err = usb_submit_urb(urb, mem_flags);
 	if (err < 0) {
 		if (err != -EPERM && err != -ENODEV)
-			BT_ERR("%s urb %p submission failed (%d)",
-			       hdev->name, urb, -err);
+			bt_dev_err(hdev, "urb %p submission failed (%d)",
+				   urb, -err);
 		usb_unanchor_urb(urb);
 	}
 
@@ -833,7 +830,7 @@ static void btusb_isoc_complete(struct urb *urb)
 
 			if (btusb_recv_isoc(data, urb->transfer_buffer + offset,
 					    length) < 0) {
-				BT_ERR("%s corrupted SCO packet", hdev->name);
+				bt_dev_err(hdev, "corrupted SCO packet");
 				hdev->stat.err_rx++;
 			}
 		}
@@ -853,8 +850,8 @@ static void btusb_isoc_complete(struct urb *urb)
 		 * -ENODEV: device got disconnected
 		 */
 		if (err != -EPERM && err != -ENODEV)
-			BT_ERR("%s urb %p failed to resubmit (%d)",
-			       hdev->name, urb, -err);
+			bt_dev_err(hdev, "urb %p failed to resubmit (%d)",
+				   urb, -err);
 		usb_unanchor_urb(urb);
 	}
 }
@@ -921,8 +918,8 @@ static int btusb_submit_isoc_urb(struct hci_dev *hdev, gfp_t mem_flags)
 	err = usb_submit_urb(urb, mem_flags);
 	if (err < 0) {
 		if (err != -EPERM && err != -ENODEV)
-			BT_ERR("%s urb %p submission failed (%d)",
-			       hdev->name, urb, -err);
+			bt_dev_err(hdev, "urb %p submission failed (%d)",
+				   urb, -err);
 		usb_unanchor_urb(urb);
 	}
 
@@ -966,8 +963,8 @@ static void btusb_diag_complete(struct urb *urb)
 		 * -ENODEV: device got disconnected
 		 */
 		if (err != -EPERM && err != -ENODEV)
-			BT_ERR("%s urb %p failed to resubmit (%d)",
-			       hdev->name, urb, -err);
+			bt_dev_err(hdev, "urb %p failed to resubmit (%d)",
+				   urb, -err);
 		usb_unanchor_urb(urb);
 	}
 }
@@ -1008,8 +1005,8 @@ static int btusb_submit_diag_urb(struct hci_dev *hdev, gfp_t mem_flags)
 	err = usb_submit_urb(urb, mem_flags);
 	if (err < 0) {
 		if (err != -EPERM && err != -ENODEV)
-			BT_ERR("%s urb %p submission failed (%d)",
-			       hdev->name, urb, -err);
+			bt_dev_err(hdev, "urb %p submission failed (%d)",
+				   urb, -err);
 		usb_unanchor_urb(urb);
 	}
 
@@ -1270,8 +1267,8 @@ static int submit_tx_urb(struct hci_dev *hdev, struct urb *urb)
 	err = usb_submit_urb(urb, GFP_KERNEL);
 	if (err < 0) {
 		if (err != -EPERM && err != -ENODEV)
-			BT_ERR("%s urb %p submission failed (%d)",
-			       hdev->name, urb, -err);
+			bt_dev_err(hdev, "urb %p submission failed (%d)",
+				   urb, -err);
 		kfree(urb->setup_packet);
 		usb_unanchor_urb(urb);
 	} else {
@@ -1364,9 +1361,9 @@ static inline int __set_isoc_interface(struct hci_dev *hdev, int altsetting)
 	if (!data->isoc)
 		return -ENODEV;
 
-	err = usb_set_interface(data->udev, 1, altsetting);
+	err = usb_set_interface(data->udev, data->isoc_ifnum, altsetting);
 	if (err < 0) {
-		BT_ERR("%s setting interface failed (%d)", hdev->name, -err);
+		bt_dev_err(hdev, "setting interface failed (%d)", -err);
 		return err;
 	}
 
@@ -1390,7 +1387,7 @@ static inline int __set_isoc_interface(struct hci_dev *hdev, int altsetting)
 	}
 
 	if (!data->isoc_tx_ep || !data->isoc_rx_ep) {
-		BT_ERR("%s invalid SCO descriptors", hdev->name);
+		bt_dev_err(hdev, "invalid SCO descriptors");
 		return -ENODEV;
 	}
 
@@ -1485,7 +1482,7 @@ static int btusb_setup_bcm92035(struct hci_dev *hdev)
 
 	skb = __hci_cmd_sync(hdev, 0xfc3b, 1, &val, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb))
-		BT_ERR("BCM92035 command failed (%ld)", -PTR_ERR(skb));
+		bt_dev_err(hdev, "BCM92035 command failed (%ld)", PTR_ERR(skb));
 	else
 		kfree_skb(skb);
 
@@ -1503,12 +1500,12 @@ static int btusb_setup_csr(struct hci_dev *hdev)
 			     HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		int err = PTR_ERR(skb);
-		BT_ERR("%s: CSR: Local version failed (%d)", hdev->name, err);
+		bt_dev_err(hdev, "CSR: Local version failed (%d)", err);
 		return err;
 	}
 
 	if (skb->len != sizeof(struct hci_rp_read_local_version)) {
-		BT_ERR("%s: CSR: Local version length mismatch", hdev->name);
+		bt_dev_err(hdev, "CSR: Local version length mismatch");
 		kfree_skb(skb);
 		return -EIO;
 	}
@@ -1570,7 +1567,7 @@ static const struct firmware *btusb_setup_intel_get_fw(struct hci_dev *hdev,
 		}
 	}
 
-	BT_INFO("%s: Intel Bluetooth firmware file: %s", hdev->name, fwname);
+	bt_dev_info(hdev, "Intel Bluetooth firmware file: %s", fwname);
 
 	return fw;
 }
@@ -1726,18 +1723,18 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 	if (err)
 		return err;
 
-	BT_INFO("%s: read Intel version: %02x%02x%02x%02x%02x%02x%02x%02x%02x",
-		hdev->name, ver.hw_platform, ver.hw_variant, ver.hw_revision,
-		ver.fw_variant,  ver.fw_revision, ver.fw_build_num,
-		ver.fw_build_ww, ver.fw_build_yy, ver.fw_patch_num);
+	bt_dev_info(hdev, "read Intel version: %02x%02x%02x%02x%02x%02x%02x%02x%02x",
+		    ver.hw_platform, ver.hw_variant, ver.hw_revision,
+		    ver.fw_variant,  ver.fw_revision, ver.fw_build_num,
+		    ver.fw_build_ww, ver.fw_build_yy, ver.fw_patch_num);
 
 	/* fw_patch_num indicates the version of patch the device currently
 	 * have. If there is no patch data in the device, it is always 0x00.
 	 * So, if it is other than 0x00, no need to patch the device again.
 	 */
 	if (ver.fw_patch_num) {
-		BT_INFO("%s: Intel device is already patched. patch num: %02x",
-			hdev->name, ver.fw_patch_num);
+		bt_dev_info(hdev, "Intel device is already patched. "
+			    "patch num: %02x", ver.fw_patch_num);
 		goto complete;
 	}
 
@@ -1805,8 +1802,7 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 	if (err)
 		return err;
 
-	BT_INFO("%s: Intel Bluetooth firmware patch completed and activated",
-		hdev->name);
+	bt_dev_info(hdev, "Intel firmware patch completed and activated");
 
 	goto complete;
 
@@ -1816,7 +1812,7 @@ exit_mfg_disable:
 	if (err)
 		return err;
 
-	BT_INFO("%s: Intel Bluetooth firmware patch completed", hdev->name);
+	bt_dev_info(hdev, "Intel firmware patch completed");
 
 	goto complete;
 
@@ -1830,8 +1826,7 @@ exit_mfg_deactivate:
 	if (err)
 		return err;
 
-	BT_INFO("%s: Intel Bluetooth firmware patch completed and deactivated",
-		hdev->name);
+	bt_dev_info(hdev, "Intel firmware patch completed and deactivated");
 
 complete:
 	/* Set the event mask for Intel specific vendor events. This enables
@@ -2112,24 +2107,24 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 
 	params = (struct intel_boot_params *)skb->data;
 
-	BT_INFO("%s: Device revision is %u", hdev->name,
-		le16_to_cpu(params->dev_revid));
+	bt_dev_info(hdev, "Device revision is %u",
+		    le16_to_cpu(params->dev_revid));
 
-	BT_INFO("%s: Secure boot is %s", hdev->name,
-		params->secure_boot ? "enabled" : "disabled");
+	bt_dev_info(hdev, "Secure boot is %s",
+		    params->secure_boot ? "enabled" : "disabled");
 
-	BT_INFO("%s: OTP lock is %s", hdev->name,
-		params->otp_lock ? "enabled" : "disabled");
+	bt_dev_info(hdev, "OTP lock is %s",
+		    params->otp_lock ? "enabled" : "disabled");
 
-	BT_INFO("%s: API lock is %s", hdev->name,
-		params->api_lock ? "enabled" : "disabled");
+	bt_dev_info(hdev, "API lock is %s",
+		    params->api_lock ? "enabled" : "disabled");
 
-	BT_INFO("%s: Debug lock is %s", hdev->name,
-		params->debug_lock ? "enabled" : "disabled");
+	bt_dev_info(hdev, "Debug lock is %s",
+		    params->debug_lock ? "enabled" : "disabled");
 
-	BT_INFO("%s: Minimum firmware build %u week %u %u", hdev->name,
-		params->min_fw_build_nn, params->min_fw_build_cw,
-		2000 + params->min_fw_build_yy);
+	bt_dev_info(hdev, "Minimum firmware build %u week %u %u",
+		    params->min_fw_build_nn, params->min_fw_build_cw,
+		    2000 + params->min_fw_build_yy);
 
 	/* It is required that every single firmware fragment is acknowledged
 	 * with a command complete event. If the boot parameters indicate
@@ -2146,24 +2141,49 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	 * also be no valid address for the operational firmware.
 	 */
 	if (!bacmp(&params->otp_bdaddr, BDADDR_ANY)) {
-		BT_INFO("%s: No device address configured", hdev->name);
+		bt_dev_info(hdev, "No device address configured");
 		set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
 	}
 
 	/* With this Intel bootloader only the hardware variant and device
-	 * revision information are used to select the right firmware.
+	 * revision information are used to select the right firmware for SfP
+	 * and WsP.
 	 *
 	 * The firmware filename is ibt-<hw_variant>-<dev_revid>.sfi.
 	 *
 	 * Currently the supported hardware variants are:
 	 *   11 (0x0b) for iBT3.0 (LnP/SfP)
 	 *   12 (0x0c) for iBT3.5 (WsP)
+	 *
+	 * For ThP/JfP and for future SKU's, the FW name varies based on HW
+	 * variant, HW revision and FW revision, as these are dependent on CNVi
+	 * and RF Combination.
+	 *
 	 *   17 (0x11) for iBT3.5 (JfP)
 	 *   18 (0x12) for iBT3.5 (ThP)
+	 *
+	 * The firmware file name for these will be
+	 * ibt-<hw_variant>-<hw_revision>-<fw_revision>.sfi.
+	 *
 	 */
-	snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.sfi",
-		 le16_to_cpu(ver.hw_variant),
-		 le16_to_cpu(params->dev_revid));
+	switch (ver.hw_variant) {
+	case 0x0b:	/* SfP */
+	case 0x0c:	/* WsP */
+		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.sfi",
+			 le16_to_cpu(ver.hw_variant),
+			 le16_to_cpu(params->dev_revid));
+		break;
+	case 0x11:	/* JfP */
+	case 0x12:	/* ThP */
+		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.sfi",
+			 le16_to_cpu(ver.hw_variant),
+			 le16_to_cpu(ver.hw_revision),
+			 le16_to_cpu(ver.fw_revision));
+		break;
+	default:
+		BT_ERR("%s: Unsupported Intel firmware naming", hdev->name);
+		return -EINVAL;
+	}
 
 	err = request_firmware(&fw, fwname, &hdev->dev);
 	if (err < 0) {
@@ -2173,14 +2193,29 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 		return err;
 	}
 
-	BT_INFO("%s: Found device firmware: %s", hdev->name, fwname);
+	bt_dev_info(hdev, "Found device firmware: %s", fwname);
 
 	/* Save the DDC file name for later use to apply once the firmware
 	 * downloading is done.
 	 */
-	snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.ddc",
-		 le16_to_cpu(ver.hw_variant),
-		 le16_to_cpu(params->dev_revid));
+	switch (ver.hw_variant) {
+	case 0x0b:	/* SfP */
+	case 0x0c:	/* WsP */
+		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.ddc",
+			 le16_to_cpu(ver.hw_variant),
+			 le16_to_cpu(params->dev_revid));
+		break;
+	case 0x11:	/* JfP */
+	case 0x12:	/* ThP */
+		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.ddc",
+			 le16_to_cpu(ver.hw_variant),
+			 le16_to_cpu(ver.hw_revision),
+			 le16_to_cpu(ver.fw_revision));
+		break;
+	default:
+		BT_ERR("%s: Unsupported Intel firmware naming", hdev->name);
+		return -EINVAL;
+	}
 
 	kfree_skb(skb);
 
@@ -2254,7 +2289,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 
 	set_bit(BTUSB_FIRMWARE_LOADED, &data->flags);
 
-	BT_INFO("%s: Waiting for firmware download to complete", hdev->name);
+	bt_dev_info(hdev, "Waiting for firmware download to complete");
 
 	/* Before switching the device into operational mode and with that
 	 * booting the loaded firmware, wait for the bootloader notification
@@ -2291,7 +2326,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	delta = ktime_sub(rettime, calltime);
 	duration = (unsigned long long) ktime_to_ns(delta) >> 10;
 
-	BT_INFO("%s: Firmware loaded in %llu usecs", hdev->name, duration);
+	bt_dev_info(hdev, "Firmware loaded in %llu usecs", duration);
 
 done:
 	release_firmware(fw);
@@ -2317,7 +2352,7 @@ done:
 	 * 1 second. However if that happens, then just fail the setup
 	 * since something went wrong.
 	 */
-	BT_INFO("%s: Waiting for device to boot", hdev->name);
+	bt_dev_info(hdev, "Waiting for device to boot");
 
 	err = wait_on_bit_timeout(&data->flags, BTUSB_BOOTING,
 				  TASK_INTERRUPTIBLE,
@@ -2337,7 +2372,7 @@ done:
 	delta = ktime_sub(rettime, calltime);
 	duration = (unsigned long long) ktime_to_ns(delta) >> 10;
 
-	BT_INFO("%s: Device booted in %llu usecs", hdev->name, duration);
+	bt_dev_info(hdev, "Device booted in %llu usecs", duration);
 
 	clear_bit(BTUSB_BOOTLOADER, &data->flags);
 
@@ -2440,8 +2475,8 @@ static int btusb_set_bdaddr_marvell(struct hci_dev *hdev,
 	skb = __hci_cmd_sync(hdev, 0xfc22, sizeof(buf), buf, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		ret = PTR_ERR(skb);
-		BT_ERR("%s: changing Marvell device address failed (%ld)",
-		       hdev->name, ret);
+		bt_dev_err(hdev, "changing Marvell device address failed (%ld)",
+			   ret);
 		return ret;
 	}
 	kfree_skb(skb);
@@ -2465,8 +2500,7 @@ static int btusb_set_bdaddr_ath3012(struct hci_dev *hdev,
 	skb = __hci_cmd_sync(hdev, 0xfc0b, sizeof(buf), buf, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		ret = PTR_ERR(skb);
-		BT_ERR("%s: Change address command failed (%ld)",
-		       hdev->name, ret);
+		bt_dev_err(hdev, "Change address command failed (%ld)", ret);
 		return ret;
 	}
 	kfree_skb(skb);
@@ -2532,7 +2566,7 @@ static int btusb_qca_send_vendor_req(struct hci_dev *hdev, u8 request,
 	err = usb_control_msg(udev, pipe, request, USB_TYPE_VENDOR | USB_DIR_IN,
 			      0, 0, buf, size, USB_CTRL_SET_TIMEOUT);
 	if (err < 0) {
-		BT_ERR("%s: Failed to access otp area (%d)", hdev->name, err);
+		bt_dev_err(hdev, "Failed to access otp area (%d)", err);
 		goto done;
 	}
 
@@ -2572,7 +2606,7 @@ static int btusb_setup_qca_download_fw(struct hci_dev *hdev,
 	err = usb_control_msg(udev, pipe, QCA_DFU_DOWNLOAD, USB_TYPE_VENDOR,
 			      0, 0, buf, size, USB_CTRL_SET_TIMEOUT);
 	if (err < 0) {
-		BT_ERR("%s: Failed to send headers (%d)", hdev->name, err);
+		bt_dev_err(hdev, "Failed to send headers (%d)", err);
 		goto done;
 	}
 
@@ -2588,13 +2622,13 @@ static int btusb_setup_qca_download_fw(struct hci_dev *hdev,
 		err = usb_bulk_msg(udev, pipe, buf, size, &len,
 				   QCA_DFU_TIMEOUT);
 		if (err < 0) {
-			BT_ERR("%s: Failed to send body at %zd of %zd (%d)",
-			       hdev->name, sent, firmware->size, err);
+			bt_dev_err(hdev, "Failed to send body at %zd of %zd (%d)",
+				   sent, firmware->size, err);
 			break;
 		}
 
 		if (size != len) {
-			BT_ERR("%s: Failed to get bulk buffer", hdev->name);
+			bt_dev_err(hdev, "Failed to get bulk buffer");
 			err = -EILSEQ;
 			break;
 		}
@@ -2626,24 +2660,23 @@ static int btusb_setup_qca_load_rampatch(struct hci_dev *hdev,
 
 	err = request_firmware(&fw, fwname, &hdev->dev);
 	if (err) {
-		BT_ERR("%s: failed to request rampatch file: %s (%d)",
-		       hdev->name, fwname, err);
+		bt_dev_err(hdev, "failed to request rampatch file: %s (%d)",
+			   fwname, err);
 		return err;
 	}
 
-	BT_INFO("%s: using rampatch file: %s", hdev->name, fwname);
+	bt_dev_info(hdev, "using rampatch file: %s", fwname);
 
 	rver = (struct qca_rampatch_version *)(fw->data + info->ver_offset);
 	rver_rom = le16_to_cpu(rver->rom_version);
 	rver_patch = le16_to_cpu(rver->patch_version);
 
-	BT_INFO("%s: QCA: patch rome 0x%x build 0x%x, firmware rome 0x%x "
-		"build 0x%x", hdev->name, rver_rom, rver_patch, ver_rom,
-		ver_patch);
+	bt_dev_info(hdev, "QCA: patch rome 0x%x build 0x%x, "
+		    "firmware rome 0x%x build 0x%x",
+		    rver_rom, rver_patch, ver_rom, ver_patch);
 
 	if (rver_rom != ver_rom || rver_patch <= ver_patch) {
-		BT_ERR("%s: rampatch file version did not match with firmware",
-		       hdev->name);
+		bt_dev_err(hdev, "rampatch file version did not match with firmware");
 		err = -EINVAL;
 		goto done;
 	}
@@ -2669,12 +2702,12 @@ static int btusb_setup_qca_load_nvm(struct hci_dev *hdev,
 
 	err = request_firmware(&fw, fwname, &hdev->dev);
 	if (err) {
-		BT_ERR("%s: failed to request NVM file: %s (%d)",
-		       hdev->name, fwname, err);
+		bt_dev_err(hdev, "failed to request NVM file: %s (%d)",
+			   fwname, err);
 		return err;
 	}
 
-	BT_INFO("%s: using NVM file: %s", hdev->name, fwname);
+	bt_dev_info(hdev, "using NVM file: %s", fwname);
 
 	err = btusb_setup_qca_download_fw(hdev, fw, info->nvm_hdr);
 
@@ -2702,8 +2735,7 @@ static int btusb_setup_qca(struct hci_dev *hdev)
 			info = &qca_devices_table[i];
 	}
 	if (!info) {
-		BT_ERR("%s: don't support firmware rome 0x%x", hdev->name,
-		       ver_rom);
+		bt_dev_err(hdev, "don't support firmware rome 0x%x", ver_rom);
 		return -ENODEV;
 	}
 
@@ -2757,7 +2789,7 @@ static inline int __set_diag_interface(struct hci_dev *hdev)
 	}
 
 	if (!data->diag_tx_ep || !data->diag_rx_ep) {
-		BT_ERR("%s invalid diagnostic descriptors", hdev->name);
+		bt_dev_err(hdev, "invalid diagnostic descriptors");
 		return -ENODEV;
 	}
 
@@ -2909,19 +2941,6 @@ static int btusb_probe(struct usb_interface *intf,
 	if (id->driver_info == BTUSB_IGNORE)
 		return -ENODEV;
 
-	if (id->driver_info & BTUSB_BCM_NO_PRODID) {
-		struct usb_device *udev = interface_to_usbdev(intf);
-
-		/* For the broken Broadcom devices that show 0000:0000
-		 * as USB vendor and product information, check that the
-		 * manufacturer string identifies them as Broadcom based
-		 * devices.
-		 */
-		if (!udev->manufacturer ||
-		    strcmp(udev->manufacturer, "Broadcom Corp"))
-			return -ENODEV;
-	}
-
 	if (id->driver_info & BTUSB_ATH3012) {
 		struct usb_device *udev = interface_to_usbdev(intf);
 
@@ -3124,6 +3143,7 @@ static int btusb_probe(struct usb_interface *intf,
 	} else {
 		/* Interface orders are hardcoded in the specification */
 		data->isoc = usb_ifnum_to_if(data->udev, ifnum_base + 1);
+		data->isoc_ifnum = ifnum_base + 1;
 	}
 
 	if (!reset)
diff --git a/drivers/bluetooth/hci_ath.c b/drivers/bluetooth/hci_ath.c
index 0ccf6bf01ed4..14ae7ee88acb 100644
--- a/drivers/bluetooth/hci_ath.c
+++ b/drivers/bluetooth/hci_ath.c
@@ -50,6 +50,17 @@ struct ath_struct {
 	struct work_struct ctxtsw;
 };
 
+#define OP_WRITE_TAG	0x01
+
+#define INDEX_BDADDR	0x01
+
+struct ath_vendor_cmd {
+	__u8 opcode;
+	__le16 index;
+	__u8 len;
+	__u8 data[251];
+} __packed;
+
 static int ath_wakeup_ar3k(struct tty_struct *tty)
 {
 	int status = tty->driver->ops->tiocmget(tty);
@@ -144,30 +155,34 @@ static int ath_flush(struct hci_uart *hu)
 	return 0;
 }
 
-static int ath_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
+static int ath_vendor_cmd(struct hci_dev *hdev, uint8_t opcode, uint16_t index,
+			  const void *data, size_t dlen)
 {
 	struct sk_buff *skb;
-	u8 buf[10];
-	int err;
-
-	buf[0] = 0x01;
-	buf[1] = 0x01;
-	buf[2] = 0x00;
-	buf[3] = sizeof(bdaddr_t);
-	memcpy(buf + 4, bdaddr, sizeof(bdaddr_t));
-
-	skb = __hci_cmd_sync(hdev, 0xfc0b, sizeof(buf), buf, HCI_INIT_TIMEOUT);
-	if (IS_ERR(skb)) {
-		err = PTR_ERR(skb);
-		BT_ERR("%s: Change address command failed (%d)",
-		       hdev->name, err);
-		return err;
-	}
+	struct ath_vendor_cmd cmd;
+
+	if (dlen > sizeof(cmd.data))
+		return -EINVAL;
+
+	cmd.opcode = opcode;
+	cmd.index = cpu_to_le16(index);
+	cmd.len = dlen;
+	memcpy(cmd.data, data, dlen);
+
+	skb = __hci_cmd_sync(hdev, 0xfc0b, dlen + 4, &cmd, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
 	kfree_skb(skb);
 
 	return 0;
 }
 
+static int ath_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
+{
+	return ath_vendor_cmd(hdev, OP_WRITE_TAG, INDEX_BDADDR, bdaddr,
+			      sizeof(*bdaddr));
+}
+
 static int ath_setup(struct hci_uart *hu)
 {
 	BT_DBG("hu %p", hu);
@@ -191,7 +206,7 @@ static int ath_recv(struct hci_uart *hu, const void *data, int count)
 				  ath_recv_pkts, ARRAY_SIZE(ath_recv_pkts));
 	if (IS_ERR(ath->rx_skb)) {
 		int err = PTR_ERR(ath->rx_skb);
-		BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err);
+		bt_dev_err(hu->hdev, "Frame reassembly failed (%d)", err);
 		ath->rx_skb = NULL;
 		return err;
 	}
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index e2540113d0da..707c2d1b84c7 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -52,11 +52,13 @@
 
 #define BCM_AUTOSUSPEND_DELAY	5000 /* default autosleep delay */
 
-/* platform device driver resources */
+/* device driver resources */
 struct bcm_device {
+	/* Must be the first member, hci_serdev.c expects this. */
+	struct hci_uart		serdev_hu;
 	struct list_head	list;
 
-	struct platform_device	*pdev;
+	struct device		*dev;
 
 	const char		*name;
 	struct gpio_desc	*device_wakeup;
@@ -68,7 +70,7 @@ struct bcm_device {
 	u32			init_speed;
 	u32			oper_speed;
 	int			irq;
-	u8			irq_polarity;
+	bool			irq_active_low;
 
 #ifdef CONFIG_PM
 	struct hci_uart		*hu;
@@ -76,11 +78,6 @@ struct bcm_device {
 #endif
 };
 
-/* serdev driver resources */
-struct bcm_serdev {
-	struct hci_uart hu;
-};
-
 /* generic bcm uart resources */
 struct bcm_data {
 	struct sk_buff		*rx_skb;
@@ -155,6 +152,12 @@ static bool bcm_device_exists(struct bcm_device *device)
 {
 	struct list_head *p;
 
+#ifdef CONFIG_PM
+	/* Devices using serdev always exist */
+	if (device && device->hu && device->hu->serdev)
+		return true;
+#endif
+
 	list_for_each(p, &bcm_device_list) {
 		struct bcm_device *dev = list_entry(p, struct bcm_device, list);
 
@@ -188,9 +191,9 @@ static irqreturn_t bcm_host_wake(int irq, void *data)
 
 	bt_dev_dbg(bdev, "Host wake IRQ");
 
-	pm_runtime_get(&bdev->pdev->dev);
-	pm_runtime_mark_last_busy(&bdev->pdev->dev);
-	pm_runtime_put_autosuspend(&bdev->pdev->dev);
+	pm_runtime_get(bdev->dev);
+	pm_runtime_mark_last_busy(bdev->dev);
+	pm_runtime_put_autosuspend(bdev->dev);
 
 	return IRQ_HANDLED;
 }
@@ -200,7 +203,6 @@ static int bcm_request_irq(struct bcm_data *bcm)
 	struct bcm_device *bdev = bcm->dev;
 	int err;
 
-	/* If this is not a platform device, do not enable PM functionalities */
 	mutex_lock(&bcm_device_lock);
 	if (!bcm_device_exists(bdev)) {
 		err = -ENODEV;
@@ -212,18 +214,20 @@ static int bcm_request_irq(struct bcm_data *bcm)
 		goto unlock;
 	}
 
-	err = devm_request_irq(&bdev->pdev->dev, bdev->irq, bcm_host_wake,
-			       IRQF_TRIGGER_RISING, "host_wake", bdev);
+	err = devm_request_irq(bdev->dev, bdev->irq, bcm_host_wake,
+			       bdev->irq_active_low ? IRQF_TRIGGER_FALLING :
+						      IRQF_TRIGGER_RISING,
+			       "host_wake", bdev);
 	if (err)
 		goto unlock;
 
-	device_init_wakeup(&bdev->pdev->dev, true);
+	device_init_wakeup(bdev->dev, true);
 
-	pm_runtime_set_autosuspend_delay(&bdev->pdev->dev,
+	pm_runtime_set_autosuspend_delay(bdev->dev,
 					 BCM_AUTOSUSPEND_DELAY);
-	pm_runtime_use_autosuspend(&bdev->pdev->dev);
-	pm_runtime_set_active(&bdev->pdev->dev);
-	pm_runtime_enable(&bdev->pdev->dev);
+	pm_runtime_use_autosuspend(bdev->dev);
+	pm_runtime_set_active(bdev->dev);
+	pm_runtime_enable(bdev->dev);
 
 unlock:
 	mutex_unlock(&bcm_device_lock);
@@ -253,7 +257,7 @@ static int bcm_setup_sleep(struct hci_uart *hu)
 	struct sk_buff *skb;
 	struct bcm_set_sleep_mode sleep_params = default_sleep_params;
 
-	sleep_params.host_wake_active = !bcm->dev->irq_polarity;
+	sleep_params.host_wake_active = !bcm->dev->irq_active_low;
 
 	skb = __hci_cmd_sync(hu->hdev, 0xfc27, sizeof(sleep_params),
 			     &sleep_params, HCI_INIT_TIMEOUT);
@@ -311,18 +315,17 @@ static int bcm_open(struct hci_uart *hu)
 
 	hu->priv = bcm;
 
-	/* If this is a serdev defined device, then only use
-	 * serdev open primitive and skip the rest.
-	 */
+	mutex_lock(&bcm_device_lock);
+
 	if (hu->serdev) {
 		serdev_device_open(hu->serdev);
+		bcm->dev = serdev_device_get_drvdata(hu->serdev);
 		goto out;
 	}
 
 	if (!hu->tty->dev)
 		goto out;
 
-	mutex_lock(&bcm_device_lock);
 	list_for_each(p, &bcm_device_list) {
 		struct bcm_device *dev = list_entry(p, struct bcm_device, list);
 
@@ -330,50 +333,56 @@ static int bcm_open(struct hci_uart *hu)
 		 * platform device (saved during device probe) and
 		 * parent of tty device used by hci_uart
 		 */
-		if (hu->tty->dev->parent == dev->pdev->dev.parent) {
+		if (hu->tty->dev->parent == dev->dev->parent) {
 			bcm->dev = dev;
-			hu->init_speed = dev->init_speed;
-			hu->oper_speed = dev->oper_speed;
 #ifdef CONFIG_PM
 			dev->hu = hu;
 #endif
-			bcm_gpio_set_power(bcm->dev, true);
 			break;
 		}
 	}
 
-	mutex_unlock(&bcm_device_lock);
 out:
+	if (bcm->dev) {
+		hu->init_speed = bcm->dev->init_speed;
+		hu->oper_speed = bcm->dev->oper_speed;
+		bcm_gpio_set_power(bcm->dev, true);
+	}
+
+	mutex_unlock(&bcm_device_lock);
 	return 0;
 }
 
 static int bcm_close(struct hci_uart *hu)
 {
 	struct bcm_data *bcm = hu->priv;
-	struct bcm_device *bdev = bcm->dev;
+	struct bcm_device *bdev = NULL;
 
 	bt_dev_dbg(hu->hdev, "hu %p", hu);
 
-	/* If this is a serdev defined device, only use serdev
-	 * close primitive and then continue as usual.
-	 */
-	if (hu->serdev)
-		serdev_device_close(hu->serdev);
-
 	/* Protect bcm->dev against removal of the device or driver */
 	mutex_lock(&bcm_device_lock);
-	if (bcm_device_exists(bdev)) {
+
+	if (hu->serdev) {
+		serdev_device_close(hu->serdev);
+		bdev = serdev_device_get_drvdata(hu->serdev);
+	} else if (bcm_device_exists(bcm->dev)) {
+		bdev = bcm->dev;
+#ifdef CONFIG_PM
+		bdev->hu = NULL;
+#endif
+	}
+
+	if (bdev) {
 		bcm_gpio_set_power(bdev, false);
 #ifdef CONFIG_PM
-		pm_runtime_disable(&bdev->pdev->dev);
-		pm_runtime_set_suspended(&bdev->pdev->dev);
+		pm_runtime_disable(bdev->dev);
+		pm_runtime_set_suspended(bdev->dev);
 
-		if (device_can_wakeup(&bdev->pdev->dev)) {
-			devm_free_irq(&bdev->pdev->dev, bdev->irq, bdev);
-			device_init_wakeup(&bdev->pdev->dev, false);
+		if (device_can_wakeup(bdev->dev)) {
+			devm_free_irq(bdev->dev, bdev->irq, bdev);
+			device_init_wakeup(bdev->dev, false);
 		}
-
-		bdev->hu = NULL;
 #endif
 	}
 	mutex_unlock(&bcm_device_lock);
@@ -504,9 +513,9 @@ static int bcm_recv(struct hci_uart *hu, const void *data, int count)
 		/* Delay auto-suspend when receiving completed packet */
 		mutex_lock(&bcm_device_lock);
 		if (bcm->dev && bcm_device_exists(bcm->dev)) {
-			pm_runtime_get(&bcm->dev->pdev->dev);
-			pm_runtime_mark_last_busy(&bcm->dev->pdev->dev);
-			pm_runtime_put_autosuspend(&bcm->dev->pdev->dev);
+			pm_runtime_get(bcm->dev->dev);
+			pm_runtime_mark_last_busy(bcm->dev->dev);
+			pm_runtime_put_autosuspend(bcm->dev->dev);
 		}
 		mutex_unlock(&bcm_device_lock);
 	}
@@ -537,15 +546,15 @@ static struct sk_buff *bcm_dequeue(struct hci_uart *hu)
 
 	if (bcm_device_exists(bcm->dev)) {
 		bdev = bcm->dev;
-		pm_runtime_get_sync(&bdev->pdev->dev);
+		pm_runtime_get_sync(bdev->dev);
 		/* Shall be resumed here */
 	}
 
 	skb = skb_dequeue(&bcm->txq);
 
 	if (bdev) {
-		pm_runtime_mark_last_busy(&bdev->pdev->dev);
-		pm_runtime_put_autosuspend(&bdev->pdev->dev);
+		pm_runtime_mark_last_busy(bdev->dev);
+		pm_runtime_put_autosuspend(bdev->dev);
 	}
 
 	mutex_unlock(&bcm_device_lock);
@@ -556,7 +565,7 @@ static struct sk_buff *bcm_dequeue(struct hci_uart *hu)
 #ifdef CONFIG_PM
 static int bcm_suspend_device(struct device *dev)
 {
-	struct bcm_device *bdev = platform_get_drvdata(to_platform_device(dev));
+	struct bcm_device *bdev = dev_get_drvdata(dev);
 
 	bt_dev_dbg(bdev, "");
 
@@ -579,7 +588,7 @@ static int bcm_suspend_device(struct device *dev)
 
 static int bcm_resume_device(struct device *dev)
 {
-	struct bcm_device *bdev = platform_get_drvdata(to_platform_device(dev));
+	struct bcm_device *bdev = dev_get_drvdata(dev);
 
 	bt_dev_dbg(bdev, "");
 
@@ -601,16 +610,18 @@ static int bcm_resume_device(struct device *dev)
 #endif
 
 #ifdef CONFIG_PM_SLEEP
-/* Platform suspend callback */
+/* suspend callback */
 static int bcm_suspend(struct device *dev)
 {
-	struct bcm_device *bdev = platform_get_drvdata(to_platform_device(dev));
+	struct bcm_device *bdev = dev_get_drvdata(dev);
 	int error;
 
 	bt_dev_dbg(bdev, "suspend: is_suspended %d", bdev->is_suspended);
 
-	/* bcm_suspend can be called at any time as long as platform device is
-	 * bound, so it should use bcm_device_lock to protect access to hci_uart
+	/*
+	 * When used with a device instantiated as platform_device, bcm_suspend
+	 * can be called at any time as long as the platform device is bound,
+	 * so it should use bcm_device_lock to protect access to hci_uart
 	 * and device_wake-up GPIO.
 	 */
 	mutex_lock(&bcm_device_lock);
@@ -621,7 +632,7 @@ static int bcm_suspend(struct device *dev)
 	if (pm_runtime_active(dev))
 		bcm_suspend_device(dev);
 
-	if (device_may_wakeup(&bdev->pdev->dev)) {
+	if (device_may_wakeup(dev)) {
 		error = enable_irq_wake(bdev->irq);
 		if (!error)
 			bt_dev_dbg(bdev, "BCM irq: enabled");
@@ -633,15 +644,17 @@ unlock:
 	return 0;
 }
 
-/* Platform resume callback */
+/* resume callback */
 static int bcm_resume(struct device *dev)
 {
-	struct bcm_device *bdev = platform_get_drvdata(to_platform_device(dev));
+	struct bcm_device *bdev = dev_get_drvdata(dev);
 
 	bt_dev_dbg(bdev, "resume: is_suspended %d", bdev->is_suspended);
 
-	/* bcm_resume can be called at any time as long as platform device is
-	 * bound, so it should use bcm_device_lock to protect access to hci_uart
+	/*
+	 * When used with a device instantiated as platform_device, bcm_resume
+	 * can be called at any time as long as platform device is bound,
+	 * so it should use bcm_device_lock to protect access to hci_uart
 	 * and device_wake-up GPIO.
 	 */
 	mutex_lock(&bcm_device_lock);
@@ -649,7 +662,7 @@ static int bcm_resume(struct device *dev)
 	if (!bdev->hu)
 		goto unlock;
 
-	if (device_may_wakeup(&bdev->pdev->dev)) {
+	if (device_may_wakeup(dev)) {
 		disable_irq_wake(bdev->irq);
 		bt_dev_dbg(bdev, "BCM irq: disabled");
 	}
@@ -690,10 +703,8 @@ static const struct acpi_gpio_mapping acpi_bcm_int_first_gpios[] = {
 };
 
 #ifdef CONFIG_ACPI
-static u8 acpi_active_low = ACPI_ACTIVE_LOW;
-
 /* IRQ polarity of some chipsets are not defined correctly in ACPI table. */
-static const struct dmi_system_id bcm_wrong_irq_dmi_table[] = {
+static const struct dmi_system_id bcm_active_low_irq_dmi_table[] = {
 	{
 		.ident = "Asus T100TA",
 		.matches = {
@@ -701,7 +712,6 @@ static const struct dmi_system_id bcm_wrong_irq_dmi_table[] = {
 					"ASUSTeK COMPUTER INC."),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"),
 		},
-		.driver_data = &acpi_active_low,
 	},
 	{
 		.ident = "Asus T100CHI",
@@ -710,7 +720,6 @@ static const struct dmi_system_id bcm_wrong_irq_dmi_table[] = {
 					"ASUSTeK COMPUTER INC."),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100CHI"),
 		},
-		.driver_data = &acpi_active_low,
 	},
 	{	/* Handle ThinkPad 8 tablets with BCM2E55 chipset ACPI ID */
 		.ident = "Lenovo ThinkPad 8",
@@ -718,7 +727,13 @@ static const struct dmi_system_id bcm_wrong_irq_dmi_table[] = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
 			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "ThinkPad 8"),
 		},
-		.driver_data = &acpi_active_low,
+	},
+	{
+		.ident = "MINIX Z83-4",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "MINIX"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Z83-4"),
+		},
 	},
 	{ }
 };
@@ -733,13 +748,13 @@ static int bcm_resource(struct acpi_resource *ares, void *data)
 	switch (ares->type) {
 	case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
 		irq = &ares->data.extended_irq;
-		dev->irq_polarity = irq->polarity;
+		dev->irq_active_low = irq->polarity == ACPI_ACTIVE_LOW;
 		break;
 
 	case ACPI_RESOURCE_TYPE_GPIO:
 		gpio = &ares->data.gpio;
 		if (gpio->connection_type == ACPI_RESOURCE_GPIO_TYPE_INT)
-			dev->irq_polarity = gpio->polarity;
+			dev->irq_active_low = gpio->polarity == ACPI_ACTIVE_LOW;
 		break;
 
 	case ACPI_RESOURCE_TYPE_SERIAL_BUS:
@@ -754,36 +769,32 @@ static int bcm_resource(struct acpi_resource *ares, void *data)
 		break;
 	}
 
-	/* Always tell the ACPI core to skip this resource */
-	return 1;
+	return 0;
 }
 #endif /* CONFIG_ACPI */
 
-static int bcm_platform_probe(struct bcm_device *dev)
+static int bcm_get_resources(struct bcm_device *dev)
 {
-	struct platform_device *pdev = dev->pdev;
-
-	dev->name = dev_name(&pdev->dev);
+	dev->name = dev_name(dev->dev);
 
-	dev->clk = devm_clk_get(&pdev->dev, NULL);
+	dev->clk = devm_clk_get(dev->dev, NULL);
 
-	dev->device_wakeup = devm_gpiod_get_optional(&pdev->dev,
+	dev->device_wakeup = devm_gpiod_get_optional(dev->dev,
 						     "device-wakeup",
 						     GPIOD_OUT_LOW);
 	if (IS_ERR(dev->device_wakeup))
 		return PTR_ERR(dev->device_wakeup);
 
-	dev->shutdown = devm_gpiod_get_optional(&pdev->dev, "shutdown",
+	dev->shutdown = devm_gpiod_get_optional(dev->dev, "shutdown",
 						GPIOD_OUT_LOW);
 	if (IS_ERR(dev->shutdown))
 		return PTR_ERR(dev->shutdown);
 
 	/* IRQ can be declared in ACPI table as Interrupt or GpioInt */
-	dev->irq = platform_get_irq(pdev, 0);
 	if (dev->irq <= 0) {
 		struct gpio_desc *gpio;
 
-		gpio = devm_gpiod_get_optional(&pdev->dev, "host-wakeup",
+		gpio = devm_gpiod_get_optional(dev->dev, "host-wakeup",
 					       GPIOD_IN);
 		if (IS_ERR(gpio))
 			return PTR_ERR(gpio);
@@ -791,54 +802,48 @@ static int bcm_platform_probe(struct bcm_device *dev)
 		dev->irq = gpiod_to_irq(gpio);
 	}
 
-	dev_info(&pdev->dev, "BCM irq: %d\n", dev->irq);
-
-	/* Make sure at-least one of the GPIO is defined and that
-	 * a name is specified for this instance
-	 */
-	if ((!dev->device_wakeup && !dev->shutdown) || !dev->name) {
-		dev_err(&pdev->dev, "invalid platform data\n");
-		return -EINVAL;
-	}
-
+	dev_info(dev->dev, "BCM irq: %d\n", dev->irq);
 	return 0;
 }
 
 #ifdef CONFIG_ACPI
 static int bcm_acpi_probe(struct bcm_device *dev)
 {
-	struct platform_device *pdev = dev->pdev;
 	LIST_HEAD(resources);
 	const struct dmi_system_id *dmi_id;
 	const struct acpi_gpio_mapping *gpio_mapping = acpi_bcm_int_last_gpios;
 	const struct acpi_device_id *id;
+	struct resource_entry *entry;
 	int ret;
 
 	/* Retrieve GPIO data */
-	id = acpi_match_device(pdev->dev.driver->acpi_match_table, &pdev->dev);
+	id = acpi_match_device(dev->dev->driver->acpi_match_table, dev->dev);
 	if (id)
 		gpio_mapping = (const struct acpi_gpio_mapping *) id->driver_data;
 
-	ret = devm_acpi_dev_add_driver_gpios(&pdev->dev, gpio_mapping);
-	if (ret)
-		return ret;
-
-	ret = bcm_platform_probe(dev);
+	ret = devm_acpi_dev_add_driver_gpios(dev->dev, gpio_mapping);
 	if (ret)
 		return ret;
 
 	/* Retrieve UART ACPI info */
-	ret = acpi_dev_get_resources(ACPI_COMPANION(&dev->pdev->dev),
+	ret = acpi_dev_get_resources(ACPI_COMPANION(dev->dev),
 				     &resources, bcm_resource, dev);
 	if (ret < 0)
 		return ret;
+
+	resource_list_for_each_entry(entry, &resources) {
+		if (resource_type(entry->res) == IORESOURCE_IRQ) {
+			dev->irq = entry->res->start;
+			break;
+		}
+	}
 	acpi_dev_free_resource_list(&resources);
 
-	dmi_id = dmi_first_match(bcm_wrong_irq_dmi_table);
+	dmi_id = dmi_first_match(bcm_active_low_irq_dmi_table);
 	if (dmi_id) {
-		bt_dev_warn(dev, "%s: Overwriting IRQ polarity to active low",
+		dev_warn(dev->dev, "%s: Overwriting IRQ polarity to active low",
 			    dmi_id->ident);
-		dev->irq_polarity = *(u8 *)dmi_id->driver_data;
+		dev->irq_active_low = true;
 	}
 
 	return 0;
@@ -850,6 +855,12 @@ static int bcm_acpi_probe(struct bcm_device *dev)
 }
 #endif /* CONFIG_ACPI */
 
+static int bcm_of_probe(struct bcm_device *bdev)
+{
+	device_property_read_u32(bdev->dev, "max-speed", &bdev->oper_speed);
+	return 0;
+}
+
 static int bcm_probe(struct platform_device *pdev)
 {
 	struct bcm_device *dev;
@@ -859,12 +870,16 @@ static int bcm_probe(struct platform_device *pdev)
 	if (!dev)
 		return -ENOMEM;
 
-	dev->pdev = pdev;
+	dev->dev = &pdev->dev;
+	dev->irq = platform_get_irq(pdev, 0);
 
-	if (has_acpi_companion(&pdev->dev))
+	if (has_acpi_companion(&pdev->dev)) {
 		ret = bcm_acpi_probe(dev);
-	else
-		ret = bcm_platform_probe(dev);
+		if (ret)
+			return ret;
+	}
+
+	ret = bcm_get_resources(dev);
 	if (ret)
 		return ret;
 
@@ -926,14 +941,16 @@ static const struct acpi_device_id bcm_acpi_match[] = {
 	{ "BCM2E71", (kernel_ulong_t)&acpi_bcm_int_last_gpios },
 	{ "BCM2E7B", (kernel_ulong_t)&acpi_bcm_int_last_gpios },
 	{ "BCM2E7C", (kernel_ulong_t)&acpi_bcm_int_last_gpios },
+	{ "BCM2E7E", (kernel_ulong_t)&acpi_bcm_int_first_gpios },
 	{ "BCM2E95", (kernel_ulong_t)&acpi_bcm_int_first_gpios },
 	{ "BCM2E96", (kernel_ulong_t)&acpi_bcm_int_first_gpios },
+	{ "BCM2EA4", (kernel_ulong_t)&acpi_bcm_int_first_gpios },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, bcm_acpi_match);
 #endif
 
-/* Platform suspend and resume callbacks */
+/* suspend and resume callbacks */
 static const struct dev_pm_ops bcm_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(bcm_suspend, bcm_resume)
 	SET_RUNTIME_PM_OPS(bcm_suspend_device, bcm_resume_device, NULL)
@@ -951,29 +968,41 @@ static struct platform_driver bcm_driver = {
 
 static int bcm_serdev_probe(struct serdev_device *serdev)
 {
-	struct bcm_serdev *bcmdev;
-	u32 speed;
+	struct bcm_device *bcmdev;
 	int err;
 
 	bcmdev = devm_kzalloc(&serdev->dev, sizeof(*bcmdev), GFP_KERNEL);
 	if (!bcmdev)
 		return -ENOMEM;
 
-	bcmdev->hu.serdev = serdev;
+	bcmdev->dev = &serdev->dev;
+#ifdef CONFIG_PM
+	bcmdev->hu = &bcmdev->serdev_hu;
+#endif
+	bcmdev->serdev_hu.serdev = serdev;
 	serdev_device_set_drvdata(serdev, bcmdev);
 
-	err = device_property_read_u32(&serdev->dev, "max-speed", &speed);
-	if (!err)
-		bcmdev->hu.oper_speed = speed;
+	if (has_acpi_companion(&serdev->dev))
+		err = bcm_acpi_probe(bcmdev);
+	else
+		err = bcm_of_probe(bcmdev);
+	if (err)
+		return err;
+
+	err = bcm_get_resources(bcmdev);
+	if (err)
+		return err;
+
+	bcm_gpio_set_power(bcmdev, false);
 
-	return hci_uart_register_device(&bcmdev->hu, &bcm_proto);
+	return hci_uart_register_device(&bcmdev->serdev_hu, &bcm_proto);
 }
 
 static void bcm_serdev_remove(struct serdev_device *serdev)
 {
-	struct bcm_serdev *bcmdev = serdev_device_get_drvdata(serdev);
+	struct bcm_device *bcmdev = serdev_device_get_drvdata(serdev);
 
-	hci_uart_unregister_device(&bcmdev->hu);
+	hci_uart_unregister_device(&bcmdev->serdev_hu);
 }
 
 #ifdef CONFIG_OF
@@ -990,6 +1019,8 @@ static struct serdev_device_driver bcm_serdev_driver = {
 	.driver = {
 		.name = "hci_uart_bcm",
 		.of_match_table = of_match_ptr(bcm_bluetooth_of_match),
+		.acpi_match_table = ACPI_PTR(bcm_acpi_match),
+		.pm = &bcm_pm_ops,
 	},
 };
 
diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c
index d880f4e33c75..1a7f0c82fb36 100644
--- a/drivers/bluetooth/hci_bcsp.c
+++ b/drivers/bluetooth/hci_bcsp.c
@@ -65,6 +65,7 @@ struct bcsp_struct {
 	u8	rxseq_txack;		/* rxseq == txack. */
 	u8	rxack;			/* Last packet sent by us that the peer ack'ed */
 	struct	timer_list tbcsp;
+	struct	hci_uart *hu;
 
 	enum {
 		BCSP_W4_PKT_DELIMITER,
@@ -697,10 +698,10 @@ static int bcsp_recv(struct hci_uart *hu, const void *data, int count)
 }
 
 	/* Arrange to retransmit all messages in the relq. */
-static void bcsp_timed_event(unsigned long arg)
+static void bcsp_timed_event(struct timer_list *t)
 {
-	struct hci_uart *hu = (struct hci_uart *)arg;
-	struct bcsp_struct *bcsp = hu->priv;
+	struct bcsp_struct *bcsp = from_timer(bcsp, t, tbcsp);
+	struct hci_uart *hu = bcsp->hu;
 	struct sk_buff *skb;
 	unsigned long flags;
 
@@ -729,11 +730,12 @@ static int bcsp_open(struct hci_uart *hu)
 		return -ENOMEM;
 
 	hu->priv = bcsp;
+	bcsp->hu = hu;
 	skb_queue_head_init(&bcsp->unack);
 	skb_queue_head_init(&bcsp->rel);
 	skb_queue_head_init(&bcsp->unrel);
 
-	setup_timer(&bcsp->tbcsp, bcsp_timed_event, (u_long)hu);
+	timer_setup(&bcsp->tbcsp, bcsp_timed_event, 0);
 
 	bcsp->rx_state = BCSP_W4_PKT_DELIMITER;
 
diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c
index 3b82a87224a9..fb97a3bf069b 100644
--- a/drivers/bluetooth/hci_h4.c
+++ b/drivers/bluetooth/hci_h4.c
@@ -132,7 +132,7 @@ static int h4_recv(struct hci_uart *hu, const void *data, int count)
 				 h4_recv_pkts, ARRAY_SIZE(h4_recv_pkts));
 	if (IS_ERR(h4->rx_skb)) {
 		int err = PTR_ERR(h4->rx_skb);
-		BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err);
+		bt_dev_err(hu->hdev, "Frame reassembly failed (%d)", err);
 		h4->rx_skb = NULL;
 		return err;
 	}
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index c0e4e26dc30d..6a8d0d06aba7 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -78,6 +78,7 @@ struct h5 {
 	int			(*rx_func)(struct hci_uart *hu, u8 c);
 
 	struct timer_list	timer;		/* Retransmission timer */
+	struct hci_uart		*hu;		/* Parent HCI UART */
 
 	u8			tx_seq;		/* Next seq number to send */
 	u8			tx_ack;		/* Next ack number to send */
@@ -120,12 +121,12 @@ static u8 h5_cfg_field(struct h5 *h5)
 	return h5->tx_win & 0x07;
 }
 
-static void h5_timed_event(unsigned long arg)
+static void h5_timed_event(struct timer_list *t)
 {
 	const unsigned char sync_req[] = { 0x01, 0x7e };
 	unsigned char conf_req[3] = { 0x03, 0xfc };
-	struct hci_uart *hu = (struct hci_uart *)arg;
-	struct h5 *h5 = hu->priv;
+	struct h5 *h5 = from_timer(h5, t, timer);
+	struct hci_uart *hu = h5->hu;
 	struct sk_buff *skb;
 	unsigned long flags;
 
@@ -197,6 +198,7 @@ static int h5_open(struct hci_uart *hu)
 		return -ENOMEM;
 
 	hu->priv = h5;
+	h5->hu = hu;
 
 	skb_queue_head_init(&h5->unack);
 	skb_queue_head_init(&h5->rel);
@@ -204,7 +206,7 @@ static int h5_open(struct hci_uart *hu)
 
 	h5_reset_rx(h5);
 
-	setup_timer(&h5->timer, h5_timed_event, (unsigned long)hu);
+	timer_setup(&h5->timer, h5_timed_event, 0);
 
 	h5->tx_win = H5_TX_WIN_MAX;
 
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index a746627e784e..c823914b3a80 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -41,6 +41,7 @@
 #include <linux/ioctl.h>
 #include <linux/skbuff.h>
 #include <linux/firmware.h>
+#include <linux/serdev.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@@ -114,12 +115,12 @@ static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu)
 	struct sk_buff *skb = hu->tx_skb;
 
 	if (!skb) {
-		read_lock(&hu->proto_lock);
+		percpu_down_read(&hu->proto_lock);
 
 		if (test_bit(HCI_UART_PROTO_READY, &hu->flags))
 			skb = hu->proto->dequeue(hu);
 
-		read_unlock(&hu->proto_lock);
+		percpu_up_read(&hu->proto_lock);
 	} else {
 		hu->tx_skb = NULL;
 	}
@@ -129,7 +130,14 @@ static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu)
 
 int hci_uart_tx_wakeup(struct hci_uart *hu)
 {
-	read_lock(&hu->proto_lock);
+	/* This may be called in an IRQ context, so we can't sleep. Therefore
+	 * we try to acquire the lock only, and if that fails we assume the
+	 * tty is being closed because that is the only time the write lock is
+	 * acquired. If, however, at some point in the future the write lock
+	 * is also acquired in other situations, then this must be revisited.
+	 */
+	if (!percpu_down_read_trylock(&hu->proto_lock))
+		return 0;
 
 	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags))
 		goto no_schedule;
@@ -144,7 +152,7 @@ int hci_uart_tx_wakeup(struct hci_uart *hu)
 	schedule_work(&hu->write_work);
 
 no_schedule:
-	read_unlock(&hu->proto_lock);
+	percpu_up_read(&hu->proto_lock);
 
 	return 0;
 }
@@ -246,12 +254,12 @@ static int hci_uart_flush(struct hci_dev *hdev)
 	tty_ldisc_flush(tty);
 	tty_driver_flush_buffer(tty);
 
-	read_lock(&hu->proto_lock);
+	percpu_down_read(&hu->proto_lock);
 
 	if (test_bit(HCI_UART_PROTO_READY, &hu->flags))
 		hu->proto->flush(hu);
 
-	read_unlock(&hu->proto_lock);
+	percpu_up_read(&hu->proto_lock);
 
 	return 0;
 }
@@ -274,15 +282,15 @@ static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	BT_DBG("%s: type %d len %d", hdev->name, hci_skb_pkt_type(skb),
 	       skb->len);
 
-	read_lock(&hu->proto_lock);
+	percpu_down_read(&hu->proto_lock);
 
 	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) {
-		read_unlock(&hu->proto_lock);
+		percpu_up_read(&hu->proto_lock);
 		return -EUNATCH;
 	}
 
 	hu->proto->enqueue(hu, skb);
-	read_unlock(&hu->proto_lock);
+	percpu_up_read(&hu->proto_lock);
 
 	hci_uart_tx_wakeup(hu);
 
@@ -298,6 +306,12 @@ void hci_uart_set_flow_control(struct hci_uart *hu, bool enable)
 	unsigned int set = 0;
 	unsigned int clear = 0;
 
+	if (hu->serdev) {
+		serdev_device_set_flow_control(hu->serdev, !enable);
+		serdev_device_set_rts(hu->serdev, !enable);
+		return;
+	}
+
 	if (enable) {
 		/* Disable hardware flow control */
 		ktermios = tty->termios;
@@ -479,7 +493,7 @@ static int hci_uart_tty_open(struct tty_struct *tty)
 	INIT_WORK(&hu->init_ready, hci_uart_init_work);
 	INIT_WORK(&hu->write_work, hci_uart_write_work);
 
-	rwlock_init(&hu->proto_lock);
+	percpu_init_rwsem(&hu->proto_lock);
 
 	/* Flush any pending characters in the driver */
 	tty_driver_flush_buffer(tty);
@@ -496,7 +510,6 @@ static void hci_uart_tty_close(struct tty_struct *tty)
 {
 	struct hci_uart *hu = tty->disc_data;
 	struct hci_dev *hdev;
-	unsigned long flags;
 
 	BT_DBG("tty %p", tty);
 
@@ -510,12 +523,12 @@ static void hci_uart_tty_close(struct tty_struct *tty)
 	if (hdev)
 		hci_uart_close(hdev);
 
-	cancel_work_sync(&hu->write_work);
-
 	if (test_bit(HCI_UART_PROTO_READY, &hu->flags)) {
-		write_lock_irqsave(&hu->proto_lock, flags);
+		percpu_down_write(&hu->proto_lock);
 		clear_bit(HCI_UART_PROTO_READY, &hu->flags);
-		write_unlock_irqrestore(&hu->proto_lock, flags);
+		percpu_up_write(&hu->proto_lock);
+
+		cancel_work_sync(&hu->write_work);
 
 		if (hdev) {
 			if (test_bit(HCI_UART_REGISTERED, &hu->flags))
@@ -575,10 +588,10 @@ static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data,
 	if (!hu || tty != hu->tty)
 		return;
 
-	read_lock(&hu->proto_lock);
+	percpu_down_read(&hu->proto_lock);
 
 	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) {
-		read_unlock(&hu->proto_lock);
+		percpu_up_read(&hu->proto_lock);
 		return;
 	}
 
@@ -586,7 +599,7 @@ static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data,
 	 * tty caller
 	 */
 	hu->proto->recv(hu, data, count);
-	read_unlock(&hu->proto_lock);
+	percpu_up_read(&hu->proto_lock);
 
 	if (hu->hdev)
 		hu->hdev->stat.byte_rx += count;
diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c
index 424c15aa7bb7..e2c078d61730 100644
--- a/drivers/bluetooth/hci_ll.c
+++ b/drivers/bluetooth/hci_ll.c
@@ -242,7 +242,7 @@ static void ll_device_want_to_wakeup(struct hci_uart *hu)
 		 * perfectly safe to always send one.
 		 */
 		BT_DBG("dual wake-up-indication");
-		/* deliberate fall-through - do not add break */
+		/* fall through */
 	case HCILL_ASLEEP:
 		/* acknowledge device wake up */
 		if (send_hcill_cmd(HCILL_WAKE_UP_ACK, hu) < 0) {
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 392f412b4575..bbd7db7384e6 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -307,10 +307,10 @@ static void qca_wq_serial_tx_clock_vote_off(struct work_struct *work)
 	serial_clock_vote(HCI_IBS_TX_VOTE_CLOCK_OFF, hu);
 }
 
-static void hci_ibs_tx_idle_timeout(unsigned long arg)
+static void hci_ibs_tx_idle_timeout(struct timer_list *t)
 {
-	struct hci_uart *hu = (struct hci_uart *)arg;
-	struct qca_data *qca = hu->priv;
+	struct qca_data *qca = from_timer(qca, t, tx_idle_timer);
+	struct hci_uart *hu = qca->hu;
 	unsigned long flags;
 
 	BT_DBG("hu %p idle timeout in %d state", hu, qca->tx_ibs_state);
@@ -342,10 +342,10 @@ static void hci_ibs_tx_idle_timeout(unsigned long arg)
 	spin_unlock_irqrestore(&qca->hci_ibs_lock, flags);
 }
 
-static void hci_ibs_wake_retrans_timeout(unsigned long arg)
+static void hci_ibs_wake_retrans_timeout(struct timer_list *t)
 {
-	struct hci_uart *hu = (struct hci_uart *)arg;
-	struct qca_data *qca = hu->priv;
+	struct qca_data *qca = from_timer(qca, t, wake_retrans_timer);
+	struct hci_uart *hu = qca->hu;
 	unsigned long flags, retrans_delay;
 	bool retransmit = false;
 
@@ -438,11 +438,10 @@ static int qca_open(struct hci_uart *hu)
 
 	hu->priv = qca;
 
-	setup_timer(&qca->wake_retrans_timer, hci_ibs_wake_retrans_timeout,
-		    (u_long)hu);
+	timer_setup(&qca->wake_retrans_timer, hci_ibs_wake_retrans_timeout, 0);
 	qca->wake_retrans = IBS_WAKE_RETRANS_TIMEOUT_MS;
 
-	setup_timer(&qca->tx_idle_timer, hci_ibs_tx_idle_timeout, (u_long)hu);
+	timer_setup(&qca->tx_idle_timer, hci_ibs_tx_idle_timeout, 0);
 	qca->tx_idle_delay = IBS_TX_IDLE_TIMEOUT_MS;
 
 	BT_DBG("HCI_UART_QCA open, tx_idle_delay=%u, wake_retrans=%u",
@@ -801,7 +800,7 @@ static int qca_recv(struct hci_uart *hu, const void *data, int count)
 				  qca_recv_pkts, ARRAY_SIZE(qca_recv_pkts));
 	if (IS_ERR(qca->rx_skb)) {
 		int err = PTR_ERR(qca->rx_skb);
-		BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err);
+		bt_dev_err(hu->hdev, "Frame reassembly failed (%d)", err);
 		qca->rx_skb = NULL;
 		return err;
 	}
@@ -864,7 +863,7 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
 
 	skb = bt_skb_alloc(sizeof(cmd), GFP_ATOMIC);
 	if (!skb) {
-		BT_ERR("Failed to allocate memory for baudrate packet");
+		bt_dev_err(hdev, "Failed to allocate baudrate packet");
 		return -ENOMEM;
 	}
 
@@ -893,7 +892,7 @@ static int qca_setup(struct hci_uart *hu)
 	unsigned int speed, qca_baudrate = QCA_BAUDRATE_115200;
 	int ret;
 
-	BT_INFO("%s: ROME setup", hdev->name);
+	bt_dev_info(hdev, "ROME setup");
 
 	/* Patch downloading has to be done without IBS mode */
 	clear_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags);
@@ -918,11 +917,11 @@ static int qca_setup(struct hci_uart *hu)
 	if (speed) {
 		qca_baudrate = qca_get_baudrate_value(speed);
 
-		BT_INFO("%s: Set UART speed to %d", hdev->name, speed);
+		bt_dev_info(hdev, "Set UART speed to %d", speed);
 		ret = qca_set_baudrate(hdev, qca_baudrate);
 		if (ret) {
-			BT_ERR("%s: Failed to change the baud rate (%d)",
-			       hdev->name, ret);
+			bt_dev_err(hdev, "Failed to change the baud rate (%d)",
+				   ret);
 			return ret;
 		}
 		hci_uart_set_baudrate(hu, speed);
diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c
index b725ac4f7ff6..71664b22ec9d 100644
--- a/drivers/bluetooth/hci_serdev.c
+++ b/drivers/bluetooth/hci_serdev.c
@@ -185,7 +185,7 @@ static int hci_uart_setup(struct hci_dev *hdev)
 	if (hu->proto->set_baudrate && speed) {
 		err = hu->proto->set_baudrate(hu, speed);
 		if (err)
-			BT_ERR("%s: failed to set baudrate", hdev->name);
+			bt_dev_err(hdev, "Failed to set baudrate");
 		else
 			serdev_device_set_baudrate(hu->serdev, speed);
 	}
@@ -199,14 +199,13 @@ static int hci_uart_setup(struct hci_dev *hdev)
 	skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL,
 			     HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s: Reading local version information failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		bt_dev_err(hdev, "Reading local version info failed (%ld)",
+			   PTR_ERR(skb));
 		return 0;
 	}
 
 	if (skb->len != sizeof(*ver)) {
-		BT_ERR("%s: Event length mismatch for version information",
-		       hdev->name);
+		bt_dev_err(hdev, "Event length mismatch for version info");
 	}
 
 	kfree_skb(skb);
diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h
index d9cd95d81149..66e8c68e4607 100644
--- a/drivers/bluetooth/hci_uart.h
+++ b/drivers/bluetooth/hci_uart.h
@@ -87,7 +87,7 @@ struct hci_uart {
 	struct work_struct	write_work;
 
 	const struct hci_uart_proto *proto;
-	rwlock_t		proto_lock;	/* Stop work for proto close */
+	struct percpu_rw_semaphore proto_lock;	/* Stop work for proto close */
 	void			*priv;
 
 	struct sk_buff		*tx_skb;
diff --git a/drivers/connector/cn_queue.c b/drivers/connector/cn_queue.c
index 1f8bf054d11c..9c54fdf7acea 100644
--- a/drivers/connector/cn_queue.c
+++ b/drivers/connector/cn_queue.c
@@ -45,7 +45,7 @@ cn_queue_alloc_callback_entry(struct cn_queue_dev *dev, const char *name,
 		return NULL;
 	}
 
-	atomic_set(&cbq->refcnt, 1);
+	refcount_set(&cbq->refcnt, 1);
 
 	atomic_inc(&dev->refcnt);
 	cbq->pdev = dev;
@@ -58,7 +58,7 @@ cn_queue_alloc_callback_entry(struct cn_queue_dev *dev, const char *name,
 
 void cn_queue_release_callback(struct cn_callback_entry *cbq)
 {
-	if (!atomic_dec_and_test(&cbq->refcnt))
+	if (!refcount_dec_and_test(&cbq->refcnt))
 		return;
 
 	atomic_dec(&cbq->pdev->refcnt);
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 25693b045371..8615594bd065 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -157,7 +157,7 @@ static int cn_call_callback(struct sk_buff *skb)
 	spin_lock_bh(&dev->cbdev->queue_lock);
 	list_for_each_entry(i, &dev->cbdev->queue_list, callback_entry) {
 		if (cn_cb_equal(&i->id.id, &msg->id)) {
-			atomic_inc(&i->refcnt);
+			refcount_inc(&i->refcnt);
 			cbq = i;
 			break;
 		}
diff --git a/drivers/infiniband/hw/qedr/Kconfig b/drivers/infiniband/hw/qedr/Kconfig
index 6c9f3923e838..60e867d80b88 100644
--- a/drivers/infiniband/hw/qedr/Kconfig
+++ b/drivers/infiniband/hw/qedr/Kconfig
@@ -2,6 +2,7 @@ config INFINIBAND_QEDR
 	tristate "QLogic RoCE driver"
 	depends on 64BIT && QEDE
 	select QED_LL2
+	select QED_OOO
 	select QED_RDMA
 	---help---
 	  This driver provides low-level InfiniBand over Ethernet
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 6cd61638b441..fe690f82af29 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -893,13 +893,17 @@ dev_stop:
 void ipoib_pkey_dev_check_presence(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
+	struct rdma_netdev *rn = netdev_priv(dev);
 
 	if (!(priv->pkey & 0x7fff) ||
 	    ib_find_pkey(priv->ca, priv->port, priv->pkey,
-			 &priv->pkey_index))
+			 &priv->pkey_index)) {
 		clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
-	else
+	} else {
+		if (rn->set_id)
+			rn->set_id(dev, priv->pkey_index);
 		set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
+	}
 }
 
 void ipoib_ib_dev_up(struct net_device *dev)
@@ -1203,10 +1207,15 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 		ipoib_ib_dev_down(dev);
 
 	if (level == IPOIB_FLUSH_HEAVY) {
+		rtnl_lock();
 		if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
 			ipoib_ib_dev_stop(dev);
-		if (ipoib_ib_dev_open(dev) != 0)
+
+		result = ipoib_ib_dev_open(dev);
+		rtnl_unlock();
+		if (result)
 			return;
+
 		if (netif_queue_stopped(dev))
 			netif_start_queue(dev);
 	}
diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c
index 2da3ff650e1d..20d0a080a2b0 100644
--- a/drivers/isdn/gigaset/bas-gigaset.c
+++ b/drivers/isdn/gigaset/bas-gigaset.c
@@ -89,6 +89,7 @@ static int start_cbsend(struct cardstate *);
 
 struct bas_cardstate {
 	struct usb_device	*udev;		/* USB device pointer */
+	struct cardstate	*cs;
 	struct usb_interface	*interface;	/* interface for this device */
 	unsigned char		minor;		/* starting minor number */
 
@@ -433,10 +434,10 @@ static void check_pending(struct bas_cardstate *ucs)
  * argument:
  *	controller state structure
  */
-static void cmd_in_timeout(unsigned long data)
+static void cmd_in_timeout(struct timer_list *t)
 {
-	struct cardstate *cs = (struct cardstate *) data;
-	struct bas_cardstate *ucs = cs->hw.bas;
+	struct bas_cardstate *ucs = from_timer(ucs, t, timer_cmd_in);
+	struct cardstate *cs = ucs->cs;
 	int rc;
 
 	if (!ucs->rcvbuf_size) {
@@ -639,10 +640,10 @@ static void int_in_work(struct work_struct *work)
  * argument:
  *	controller state structure
  */
-static void int_in_resubmit(unsigned long data)
+static void int_in_resubmit(struct timer_list *t)
 {
-	struct cardstate *cs = (struct cardstate *) data;
-	struct bas_cardstate *ucs = cs->hw.bas;
+	struct bas_cardstate *ucs = from_timer(ucs, t, timer_int_in);
+	struct cardstate *cs = ucs->cs;
 	int rc;
 
 	if (ucs->retry_int_in++ >= BAS_RETRY) {
@@ -1441,10 +1442,10 @@ error:
  * argument:
  *	controller state structure
  */
-static void req_timeout(unsigned long data)
+static void req_timeout(struct timer_list *t)
 {
-	struct cardstate *cs = (struct cardstate *) data;
-	struct bas_cardstate *ucs = cs->hw.bas;
+	struct bas_cardstate *ucs = from_timer(ucs, t, timer_ctrl);
+	struct cardstate *cs = ucs->cs;
 	int pending;
 	unsigned long flags;
 
@@ -1837,10 +1838,10 @@ static void write_command_callback(struct urb *urb)
  * argument:
  *	controller state structure
  */
-static void atrdy_timeout(unsigned long data)
+static void atrdy_timeout(struct timer_list *t)
 {
-	struct cardstate *cs = (struct cardstate *) data;
-	struct bas_cardstate *ucs = cs->hw.bas;
+	struct bas_cardstate *ucs = from_timer(ucs, t, timer_atrdy);
+	struct cardstate *cs = ucs->cs;
 
 	dev_warn(cs->dev, "timeout waiting for HD_READY_SEND_ATDATA\n");
 
@@ -2200,7 +2201,7 @@ static int gigaset_initcshw(struct cardstate *cs)
 {
 	struct bas_cardstate *ucs;
 
-	cs->hw.bas = ucs = kmalloc(sizeof *ucs, GFP_KERNEL);
+	cs->hw.bas = ucs = kzalloc(sizeof(*ucs), GFP_KERNEL);
 	if (!ucs) {
 		pr_err("out of memory\n");
 		return -ENOMEM;
@@ -2212,19 +2213,12 @@ static int gigaset_initcshw(struct cardstate *cs)
 		return -ENOMEM;
 	}
 
-	ucs->urb_cmd_in = NULL;
-	ucs->urb_cmd_out = NULL;
-	ucs->rcvbuf = NULL;
-	ucs->rcvbuf_size = 0;
-
 	spin_lock_init(&ucs->lock);
-	ucs->pending = 0;
-
-	ucs->basstate = 0;
-	setup_timer(&ucs->timer_ctrl, req_timeout, (unsigned long) cs);
-	setup_timer(&ucs->timer_atrdy, atrdy_timeout, (unsigned long) cs);
-	setup_timer(&ucs->timer_cmd_in, cmd_in_timeout, (unsigned long) cs);
-	setup_timer(&ucs->timer_int_in, int_in_resubmit, (unsigned long) cs);
+	ucs->cs = cs;
+	timer_setup(&ucs->timer_ctrl, req_timeout, 0);
+	timer_setup(&ucs->timer_atrdy, atrdy_timeout, 0);
+	timer_setup(&ucs->timer_cmd_in, cmd_in_timeout, 0);
+	timer_setup(&ucs->timer_int_in, int_in_resubmit, 0);
 	init_waitqueue_head(&ucs->waitqueue);
 	INIT_WORK(&ucs->int_in_wq, int_in_work);
 
diff --git a/drivers/isdn/gigaset/common.c b/drivers/isdn/gigaset/common.c
index 7c7814497e3e..15482c5de33c 100644
--- a/drivers/isdn/gigaset/common.c
+++ b/drivers/isdn/gigaset/common.c
@@ -153,9 +153,9 @@ static int test_timeout(struct at_state_t *at_state)
 	return 1;
 }
 
-static void timer_tick(unsigned long data)
+static void timer_tick(struct timer_list *t)
 {
-	struct cardstate *cs = (struct cardstate *) data;
+	struct cardstate *cs = from_timer(cs, t, timer);
 	unsigned long flags;
 	unsigned channel;
 	struct at_state_t *at_state;
@@ -687,7 +687,7 @@ struct cardstate *gigaset_initcs(struct gigaset_driver *drv, int channels,
 	cs->ignoreframes = ignoreframes;
 	INIT_LIST_HEAD(&cs->temp_at_states);
 	cs->running = 0;
-	init_timer(&cs->timer); /* clear next & prev */
+	timer_setup(&cs->timer, timer_tick, 0);
 	spin_lock_init(&cs->ev_lock);
 	cs->ev_tail = 0;
 	cs->ev_head = 0;
@@ -768,7 +768,6 @@ struct cardstate *gigaset_initcs(struct gigaset_driver *drv, int channels,
 	spin_lock_irqsave(&cs->lock, flags);
 	cs->running = 1;
 	spin_unlock_irqrestore(&cs->lock, flags);
-	setup_timer(&cs->timer, timer_tick, (unsigned long) cs);
 	cs->timer.expires = jiffies + msecs_to_jiffies(GIG_TICK);
 	add_timer(&cs->timer);
 
diff --git a/drivers/isdn/hardware/eicon/message.c b/drivers/isdn/hardware/eicon/message.c
index eadd1ed1e014..def7992a38e6 100644
--- a/drivers/isdn/hardware/eicon/message.c
+++ b/drivers/isdn/hardware/eicon/message.c
@@ -4501,6 +4501,7 @@ static void control_rc(PLCI *plci, byte req, byte rc, byte ch, byte global_req,
 					plci->channels++;
 					a->ncci_state[ncci] = OUTG_CON_PENDING;
 				}
+				/* fall through */
 
 			default:
 				if (plci->internal_command_queue[0])
@@ -7020,6 +7021,7 @@ static void nl_ind(PLCI *plci)
 			plci->NL.RNum = 1;
 			return;
 		}
+		/* fall through */
 	case N_BDATA:
 	case N_DATA:
 		if (((a->ncci_state[ncci] != CONNECTED) && (plci->B2_prot == 1)) /* transparent */
@@ -9626,9 +9628,9 @@ static void dtmf_command(dword Id, PLCI *plci, byte Rc)
 	{
 
 	case DTMF_LISTEN_TONE_START:
-		mask <<= 1;
+		mask <<= 1; /* fall through */
 	case DTMF_LISTEN_MF_START:
-		mask <<= 1;
+		mask <<= 1; /* fall through */
 
 	case DTMF_LISTEN_START:
 		switch (internal_command)
@@ -9636,6 +9638,7 @@ static void dtmf_command(dword Id, PLCI *plci, byte Rc)
 		default:
 			adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities |
 								  B1_FACILITY_DTMFR), DTMF_COMMAND_1);
+			/* fall through */
 		case DTMF_COMMAND_1:
 			if (adjust_b_process(Id, plci, Rc) != GOOD)
 			{
@@ -9646,6 +9649,7 @@ static void dtmf_command(dword Id, PLCI *plci, byte Rc)
 			}
 			if (plci->internal_command)
 				return;
+			/* fall through */
 		case DTMF_COMMAND_2:
 			if (plci_nl_busy(plci))
 			{
@@ -9673,9 +9677,9 @@ static void dtmf_command(dword Id, PLCI *plci, byte Rc)
 
 
 	case DTMF_LISTEN_TONE_STOP:
-		mask <<= 1;
+		mask <<= 1; /* fall through */
 	case DTMF_LISTEN_MF_STOP:
-		mask <<= 1;
+		mask <<= 1; /* fall through */
 
 	case DTMF_LISTEN_STOP:
 		switch (internal_command)
@@ -9710,6 +9714,7 @@ static void dtmf_command(dword Id, PLCI *plci, byte Rc)
 */
 			adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities &
 								  ~(B1_FACILITY_DTMFX | B1_FACILITY_DTMFR)), DTMF_COMMAND_3);
+			/* fall through */
 		case DTMF_COMMAND_3:
 			if (adjust_b_process(Id, plci, Rc) != GOOD)
 			{
@@ -9726,9 +9731,9 @@ static void dtmf_command(dword Id, PLCI *plci, byte Rc)
 
 
 	case DTMF_SEND_TONE:
-		mask <<= 1;
+		mask <<= 1; /* fall through */
 	case DTMF_SEND_MF:
-		mask <<= 1;
+		mask <<= 1; /* fall through */
 
 	case DTMF_DIGITS_SEND:
 		switch (internal_command)
@@ -9737,6 +9742,7 @@ static void dtmf_command(dword Id, PLCI *plci, byte Rc)
 			adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities |
 								  ((plci->dtmf_parameter_length != 0) ? B1_FACILITY_DTMFX | B1_FACILITY_DTMFR : B1_FACILITY_DTMFX)),
 					   DTMF_COMMAND_1);
+			/* fall through */
 		case DTMF_COMMAND_1:
 			if (adjust_b_process(Id, plci, Rc) != GOOD)
 			{
@@ -9747,6 +9753,7 @@ static void dtmf_command(dword Id, PLCI *plci, byte Rc)
 			}
 			if (plci->internal_command)
 				return;
+			/* fall through */
 		case DTMF_COMMAND_2:
 			if (plci_nl_busy(plci))
 			{
@@ -9863,7 +9870,7 @@ static byte dtmf_request(dword Id, word Number, DIVA_CAPI_ADAPTER *a, PLCI *plci
 
 			case DTMF_LISTEN_TONE_START:
 			case DTMF_LISTEN_TONE_STOP:
-				mask <<= 1;
+				mask <<= 1; /* fall through */
 			case DTMF_LISTEN_MF_START:
 			case DTMF_LISTEN_MF_STOP:
 				mask <<= 1;
@@ -9875,6 +9882,7 @@ static byte dtmf_request(dword Id, word Number, DIVA_CAPI_ADAPTER *a, PLCI *plci
 					PUT_WORD(&result[1], DTMF_UNKNOWN_REQUEST);
 					break;
 				}
+				/* fall through */
 
 			case DTMF_LISTEN_START:
 			case DTMF_LISTEN_STOP:
@@ -9904,7 +9912,7 @@ static byte dtmf_request(dword Id, word Number, DIVA_CAPI_ADAPTER *a, PLCI *plci
 
 
 			case DTMF_SEND_TONE:
-				mask <<= 1;
+				mask <<= 1; /* fall through */
 			case DTMF_SEND_MF:
 				mask <<= 1;
 				if (!((plci->requested_options_conn | plci->requested_options | plci->adapter->requested_options_table[appl->Id - 1])
@@ -9915,6 +9923,7 @@ static byte dtmf_request(dword Id, word Number, DIVA_CAPI_ADAPTER *a, PLCI *plci
 					PUT_WORD(&result[1], DTMF_UNKNOWN_REQUEST);
 					break;
 				}
+				/* fall through */
 
 			case DTMF_DIGITS_SEND:
 				if (api_parse(&msg[1].info[1], msg[1].length, "wwws", dtmf_parms))
@@ -11315,6 +11324,7 @@ static word mixer_restore_config(dword Id, PLCI *plci, byte Rc)
 			}
 			plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_5;
 			Rc = OK;
+			/* fall through */
 		case ADJUST_B_RESTORE_MIXER_2:
 		case ADJUST_B_RESTORE_MIXER_3:
 		case ADJUST_B_RESTORE_MIXER_4:
@@ -11344,10 +11354,12 @@ static word mixer_restore_config(dword Id, PLCI *plci, byte Rc)
 				plci->internal_command = plci->adjust_b_command;
 				break;
 			}
+			/* fall through */
 		case ADJUST_B_RESTORE_MIXER_5:
 			xconnect_write_coefs(plci, plci->adjust_b_command);
 			plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_6;
 			Rc = OK;
+			/* fall through */
 		case ADJUST_B_RESTORE_MIXER_6:
 			if (!xconnect_write_coefs_process(Id, plci, Rc))
 			{
@@ -11392,6 +11404,7 @@ static void mixer_command(dword Id, PLCI *plci, byte Rc)
 				adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities |
 									  B1_FACILITY_MIXER), MIXER_COMMAND_1);
 			}
+			/* fall through */
 		case MIXER_COMMAND_1:
 			if (plci->li_channel_bits & LI_CHANNEL_INVOLVED)
 			{
@@ -11419,6 +11432,7 @@ static void mixer_command(dword Id, PLCI *plci, byte Rc)
 					mixer_indication_coefs_set(Id, plci);
 				} while (plci->li_plci_b_read_pos != plci->li_plci_b_req_pos);
 			}
+			/* fall through */
 		case MIXER_COMMAND_2:
 			if ((plci->li_channel_bits & LI_CHANNEL_INVOLVED)
 			    || ((get_b1_facilities(plci, plci->B1_resource) & B1_FACILITY_MIXER)
@@ -11450,6 +11464,7 @@ static void mixer_command(dword Id, PLCI *plci, byte Rc)
 				adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities &
 									  ~B1_FACILITY_MIXER), MIXER_COMMAND_3);
 			}
+			/* fall through */
 		case MIXER_COMMAND_3:
 			if (!(plci->li_channel_bits & LI_CHANNEL_INVOLVED))
 			{
@@ -12602,6 +12617,7 @@ static void ec_command(dword Id, PLCI *plci, byte Rc)
 		default:
 			adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities |
 								  B1_FACILITY_EC), EC_COMMAND_1);
+			/* fall through */
 		case EC_COMMAND_1:
 			if (adjust_b_process(Id, plci, Rc) != GOOD)
 			{
@@ -12612,6 +12628,7 @@ static void ec_command(dword Id, PLCI *plci, byte Rc)
 			}
 			if (plci->internal_command)
 				return;
+			/* fall through */
 		case EC_COMMAND_2:
 			if (plci->sig_req)
 			{
@@ -12650,6 +12667,7 @@ static void ec_command(dword Id, PLCI *plci, byte Rc)
 				return;
 			}
 			Rc = OK;
+			/* fall through */
 		case EC_COMMAND_2:
 			if ((Rc != OK) && (Rc != OK_FC))
 			{
@@ -12660,6 +12678,7 @@ static void ec_command(dword Id, PLCI *plci, byte Rc)
 			}
 			adjust_b1_resource(Id, plci, NULL, (word)(plci->B1_facilities &
 								  ~B1_FACILITY_EC), EC_COMMAND_3);
+			/* fall through */
 		case EC_COMMAND_3:
 			if (adjust_b_process(Id, plci, Rc) != GOOD)
 			{
@@ -13485,6 +13504,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_SAVE_MIXER_1;
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_SAVE_MIXER_1:
 		if (plci->adjust_b_mode & ADJUST_B_MODE_SAVE)
 		{
@@ -13496,6 +13516,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_SAVE_DTMF_1;
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_SAVE_DTMF_1:
 		if (plci->adjust_b_mode & ADJUST_B_MODE_SAVE)
 		{
@@ -13506,6 +13527,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 
 		}
 		plci->adjust_b_state = ADJUST_B_REMOVE_L23_1;
+		/* fall through */
 	case ADJUST_B_REMOVE_L23_1:
 		if ((plci->adjust_b_mode & ADJUST_B_MODE_REMOVE_L23)
 		    && plci->NL.Id && !plci->nl_remove_id)
@@ -13530,6 +13552,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_REMOVE_L23_2;
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_REMOVE_L23_2:
 		if ((Rc != OK) && (Rc != OK_FC))
 		{
@@ -13548,6 +13571,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_SAVE_EC_1;
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_SAVE_EC_1:
 		if (plci->adjust_b_mode & ADJUST_B_MODE_SAVE)
 		{
@@ -13559,6 +13583,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_SAVE_DTMF_PARAMETER_1;
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_SAVE_DTMF_PARAMETER_1:
 		if (plci->adjust_b_mode & ADJUST_B_MODE_SAVE)
 		{
@@ -13570,6 +13595,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_SAVE_VOICE_1;
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_SAVE_VOICE_1:
 		if (plci->adjust_b_mode & ADJUST_B_MODE_SAVE)
 		{
@@ -13578,6 +13604,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 				break;
 		}
 		plci->adjust_b_state = ADJUST_B_SWITCH_L1_1;
+		/* fall through */
 	case ADJUST_B_SWITCH_L1_1:
 		if (plci->adjust_b_mode & ADJUST_B_MODE_SWITCH_L1)
 		{
@@ -13608,6 +13635,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_SWITCH_L1_2;
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_SWITCH_L1_2:
 		if ((Rc != OK) && (Rc != OK_FC))
 		{
@@ -13619,6 +13647,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_RESTORE_VOICE_1;
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_RESTORE_VOICE_1:
 	case ADJUST_B_RESTORE_VOICE_2:
 		if (plci->adjust_b_mode & ADJUST_B_MODE_RESTORE)
@@ -13629,6 +13658,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_RESTORE_DTMF_PARAMETER_1;
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_RESTORE_DTMF_PARAMETER_1:
 	case ADJUST_B_RESTORE_DTMF_PARAMETER_2:
 		if (plci->adjust_b_mode & ADJUST_B_MODE_RESTORE)
@@ -13641,6 +13671,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_RESTORE_EC_1;
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_RESTORE_EC_1:
 	case ADJUST_B_RESTORE_EC_2:
 		if (plci->adjust_b_mode & ADJUST_B_MODE_RESTORE)
@@ -13652,6 +13683,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 
 		}
 		plci->adjust_b_state = ADJUST_B_ASSIGN_L23_1;
+		/* fall through */
 	case ADJUST_B_ASSIGN_L23_1:
 		if (plci->adjust_b_mode & ADJUST_B_MODE_ASSIGN_L23)
 		{
@@ -13681,6 +13713,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_ASSIGN_L23_2;
 		Rc = ASSIGN_OK;
+		/* fall through */
 	case ADJUST_B_ASSIGN_L23_2:
 		if ((Rc != OK) && (Rc != OK_FC) && (Rc != ASSIGN_OK))
 		{
@@ -13703,6 +13736,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 			break;
 		}
 		plci->adjust_b_state = ADJUST_B_CONNECT_1;
+		/* fall through */
 	case ADJUST_B_CONNECT_1:
 		if (plci->adjust_b_mode & ADJUST_B_MODE_CONNECT)
 		{
@@ -13716,6 +13750,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_RESTORE_DTMF_1;
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_CONNECT_2:
 	case ADJUST_B_CONNECT_3:
 	case ADJUST_B_CONNECT_4:
@@ -13751,6 +13786,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 			break;
 		}
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_RESTORE_DTMF_1:
 	case ADJUST_B_RESTORE_DTMF_2:
 		if (plci->adjust_b_mode & ADJUST_B_MODE_RESTORE)
@@ -13763,6 +13799,7 @@ static word adjust_b_process(dword Id, PLCI *plci, byte Rc)
 		}
 		plci->adjust_b_state = ADJUST_B_RESTORE_MIXER_1;
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_RESTORE_MIXER_1:
 	case ADJUST_B_RESTORE_MIXER_2:
 	case ADJUST_B_RESTORE_MIXER_3:
@@ -13827,6 +13864,7 @@ static void adjust_b_restore(dword Id, PLCI *plci, byte Rc)
 			break;
 		}
 		Rc = OK;
+		/* fall through */
 	case ADJUST_B_RESTORE_1:
 		if ((Rc != OK) && (Rc != OK_FC))
 		{
@@ -13841,6 +13879,7 @@ static void adjust_b_restore(dword Id, PLCI *plci, byte Rc)
 		plci->adjust_b_state = ADJUST_B_START;
 		dbug(1, dprintf("[%06lx] %s,%d: Adjust B restore...",
 				UnMapId(Id), (char *)(FILE_), __LINE__));
+		/* fall through */
 	case ADJUST_B_RESTORE_2:
 		if (adjust_b_process(Id, plci, Rc) != GOOD)
 		{
@@ -13877,6 +13916,7 @@ static void reset_b3_command(dword Id, PLCI *plci, byte Rc)
 		plci->adjust_b_state = ADJUST_B_START;
 		dbug(1, dprintf("[%06lx] %s,%d: Reset B3...",
 				UnMapId(Id), (char *)(FILE_), __LINE__));
+		/* fall through */
 	case RESET_B3_COMMAND_1:
 		Info = adjust_b_process(Id, plci, Rc);
 		if (Info != GOOD)
@@ -13930,6 +13970,7 @@ static void select_b_command(dword Id, PLCI *plci, byte Rc)
 		plci->adjust_b_state = ADJUST_B_START;
 		dbug(1, dprintf("[%06lx] %s,%d: Select B protocol...",
 				UnMapId(Id), (char *)(FILE_), __LINE__));
+		/* fall through */
 	case SELECT_B_COMMAND_1:
 		Info = adjust_b_process(Id, plci, Rc);
 		if (Info != GOOD)
@@ -13965,7 +14006,7 @@ static void fax_connect_ack_command(dword Id, PLCI *plci, byte Rc)
 	switch (internal_command)
 	{
 	default:
-		plci->command = 0;
+		plci->command = 0; /* fall through */
 	case FAX_CONNECT_ACK_COMMAND_1:
 		if (plci_nl_busy(plci))
 		{
@@ -14013,6 +14054,7 @@ static void fax_edata_ack_command(dword Id, PLCI *plci, byte Rc)
 	{
 	default:
 		plci->command = 0;
+		/* fall through */
 	case FAX_EDATA_ACK_COMMAND_1:
 		if (plci_nl_busy(plci))
 		{
@@ -14052,7 +14094,7 @@ static void fax_connect_info_command(dword Id, PLCI *plci, byte Rc)
 	switch (internal_command)
 	{
 	default:
-		plci->command = 0;
+		plci->command = 0; /* fall through */
 	case FAX_CONNECT_INFO_COMMAND_1:
 		if (plci_nl_busy(plci))
 		{
@@ -14112,6 +14154,7 @@ static void fax_adjust_b23_command(dword Id, PLCI *plci, byte Rc)
 		plci->adjust_b_state = ADJUST_B_START;
 		dbug(1, dprintf("[%06lx] %s,%d: FAX adjust B23...",
 				UnMapId(Id), (char *)(FILE_), __LINE__));
+		/* fall through */
 	case FAX_ADJUST_B23_COMMAND_1:
 		Info = adjust_b_process(Id, plci, Rc);
 		if (Info != GOOD)
@@ -14122,6 +14165,7 @@ static void fax_adjust_b23_command(dword Id, PLCI *plci, byte Rc)
 		}
 		if (plci->internal_command)
 			return;
+		/* fall through */
 	case FAX_ADJUST_B23_COMMAND_2:
 		if (plci_nl_busy(plci))
 		{
@@ -14194,7 +14238,7 @@ static void rtp_connect_b3_req_command(dword Id, PLCI *plci, byte Rc)
 	switch (internal_command)
 	{
 	default:
-		plci->command = 0;
+		plci->command = 0; /* fall through */
 	case RTP_CONNECT_B3_REQ_COMMAND_1:
 		if (plci_nl_busy(plci))
 		{
@@ -14245,7 +14289,7 @@ static void rtp_connect_b3_res_command(dword Id, PLCI *plci, byte Rc)
 	switch (internal_command)
 	{
 	default:
-		plci->command = 0;
+		plci->command = 0; /* fall through */
 	case RTP_CONNECT_B3_RES_COMMAND_1:
 		if (plci_nl_busy(plci))
 		{
@@ -14310,6 +14354,7 @@ static void hold_save_command(dword Id, PLCI *plci, byte Rc)
 		plci->adjust_b_state = ADJUST_B_START;
 		dbug(1, dprintf("[%06lx] %s,%d: HOLD save...",
 				UnMapId(Id), (char *)(FILE_), __LINE__));
+		/* fall through */
 	case HOLD_SAVE_COMMAND_1:
 		Info = adjust_b_process(Id, plci, Rc);
 		if (Info != GOOD)
@@ -14349,6 +14394,7 @@ static void retrieve_restore_command(dword Id, PLCI *plci, byte Rc)
 		plci->adjust_b_state = ADJUST_B_START;
 		dbug(1, dprintf("[%06lx] %s,%d: RETRIEVE restore...",
 				UnMapId(Id), (char *)(FILE_), __LINE__));
+		/* fall through */
 	case RETRIEVE_RESTORE_COMMAND_1:
 		Info = adjust_b_process(Id, plci, Rc);
 		if (Info != GOOD)
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index d2e401a8090e..e4ebbee863a1 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -2265,7 +2265,7 @@ static struct pci_driver hfc_driver = {
 };
 
 static int
-_hfcpci_softirq(struct device *dev, void *arg)
+_hfcpci_softirq(struct device *dev, void *unused)
 {
 	struct hfc_pci  *hc = dev_get_drvdata(dev);
 	struct bchannel *bch;
@@ -2290,9 +2290,9 @@ _hfcpci_softirq(struct device *dev, void *arg)
 }
 
 static void
-hfcpci_softirq(void *arg)
+hfcpci_softirq(struct timer_list *unused)
 {
-	WARN_ON_ONCE(driver_for_each_device(&hfc_driver.driver, NULL, arg,
+	WARN_ON_ONCE(driver_for_each_device(&hfc_driver.driver, NULL, NULL,
 				      _hfcpci_softirq) != 0);
 
 	/* if next event would be in the past ... */
@@ -2327,9 +2327,7 @@ HFC_init(void)
 	if (poll != HFCPCI_BTRANS_THRESHOLD) {
 		printk(KERN_INFO "%s: Using alternative poll value of %d\n",
 		       __func__, poll);
-		hfc_tl.function = (void *)hfcpci_softirq;
-		hfc_tl.data = 0;
-		init_timer(&hfc_tl);
+		timer_setup(&hfc_tl, hfcpci_softirq, 0);
 		hfc_tl.expires = jiffies + tics;
 		hfc_jiffies = hfc_tl.expires;
 		add_timer(&hfc_tl);
diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c
index e240010b93fa..4d78f870435e 100644
--- a/drivers/isdn/hardware/mISDN/mISDNipac.c
+++ b/drivers/isdn/hardware/mISDN/mISDNipac.c
@@ -172,7 +172,6 @@ isac_fill_fifo(struct isac_hw *isac)
 		pr_debug("%s: %s dbusytimer running\n", isac->name, __func__);
 		del_timer(&isac->dch.timer);
 	}
-	init_timer(&isac->dch.timer);
 	isac->dch.timer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ)/1000);
 	add_timer(&isac->dch.timer);
 	if (isac->dch.debug & DEBUG_HW_DFIFO) {
@@ -727,8 +726,9 @@ isac_release(struct isac_hw *isac)
 }
 
 static void
-dbusy_timer_handler(struct isac_hw *isac)
+dbusy_timer_handler(struct timer_list *t)
 {
+	struct isac_hw *isac = from_timer(isac, t, dch.timer);
 	int rbch, star;
 	u_long flags;
 
@@ -796,8 +796,7 @@ isac_init(struct isac_hw *isac)
 	}
 	isac->mon_tx = NULL;
 	isac->mon_rx = NULL;
-	setup_timer(&isac->dch.timer, (void *)dbusy_timer_handler,
-		    (long)isac);
+	timer_setup(&isac->dch.timer, dbusy_timer_handler, 0);
 	isac->mocr = 0xaa;
 	if (isac->type & IPAC_TYPE_ISACX) {
 		/* Disable all IRQ */
diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c
index d80072fef434..536d5137f49d 100644
--- a/drivers/isdn/hardware/mISDN/w6692.c
+++ b/drivers/isdn/hardware/mISDN/w6692.c
@@ -311,7 +311,6 @@ W6692_fill_Dfifo(struct w6692_hw *card)
 		pr_debug("%s: fill_Dfifo dbusytimer running\n", card->name);
 		del_timer(&dch->timer);
 	}
-	init_timer(&dch->timer);
 	dch->timer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ) / 1000);
 	add_timer(&dch->timer);
 	if (debug & DEBUG_HW_DFIFO) {
@@ -819,8 +818,9 @@ w6692_irq(int intno, void *dev_id)
 }
 
 static void
-dbusy_timer_handler(struct dchannel *dch)
+dbusy_timer_handler(struct timer_list *t)
 {
+	struct dchannel *dch = from_timer(dch, t, timer);
 	struct w6692_hw	*card = dch->hw;
 	int		rbch, star;
 	u_long		flags;
@@ -852,8 +852,7 @@ static void initW6692(struct w6692_hw *card)
 {
 	u8	val;
 
-	setup_timer(&card->dch.timer, (void *)dbusy_timer_handler,
-		    (u_long)&card->dch);
+	timer_setup(&card->dch.timer, dbusy_timer_handler, 0);
 	w6692_mode(&card->bc[0], ISDN_P_NONE);
 	w6692_mode(&card->bc[1], ISDN_P_NONE);
 	WriteW6692(card, W_D_CTL, 0x00);
diff --git a/drivers/isdn/hisax/amd7930_fn.c b/drivers/isdn/hisax/amd7930_fn.c
index dcf4c2a9fcea..77debda2221b 100644
--- a/drivers/isdn/hisax/amd7930_fn.c
+++ b/drivers/isdn/hisax/amd7930_fn.c
@@ -398,7 +398,6 @@ Amd7930_fill_Dfifo(struct IsdnCardState *cs)
 		debugl1(cs, "Amd7930: fill_Dfifo dbusytimer running");
 		del_timer(&cs->dbusytimer);
 	}
-	init_timer(&cs->dbusytimer);
 	cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ) / 1000);
 	add_timer(&cs->dbusytimer);
 
@@ -686,8 +685,9 @@ DC_Close_Amd7930(struct IsdnCardState *cs) {
 
 
 static void
-dbusy_timer_handler(struct IsdnCardState *cs)
+dbusy_timer_handler(struct timer_list *t)
 {
+	struct IsdnCardState *cs = from_timer(cs, t, dbusytimer);
 	u_long flags;
 	struct PStack *stptr;
 	WORD dtcr, der;
@@ -790,5 +790,5 @@ void Amd7930_init(struct IsdnCardState *cs)
 void setup_Amd7930(struct IsdnCardState *cs)
 {
 	INIT_WORK(&cs->tqueue, Amd7930_bh);
-	setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
+	timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0);
 }
diff --git a/drivers/isdn/hisax/arcofi.c b/drivers/isdn/hisax/arcofi.c
index 9826bad49e2c..2f784f96d439 100644
--- a/drivers/isdn/hisax/arcofi.c
+++ b/drivers/isdn/hisax/arcofi.c
@@ -23,7 +23,6 @@ add_arcofi_timer(struct IsdnCardState *cs) {
 	if (test_and_set_bit(FLG_ARCOFI_TIMER, &cs->HW_Flags)) {
 		del_timer(&cs->dc.isac.arcofitimer);
 	}
-	init_timer(&cs->dc.isac.arcofitimer);
 	cs->dc.isac.arcofitimer.expires = jiffies + ((ARCOFI_TIMER_VALUE * HZ) / 1000);
 	add_timer(&cs->dc.isac.arcofitimer);
 }
@@ -112,7 +111,8 @@ arcofi_fsm(struct IsdnCardState *cs, int event, void *data) {
 }
 
 static void
-arcofi_timer(struct IsdnCardState *cs) {
+arcofi_timer(struct timer_list *t) {
+	struct IsdnCardState *cs = from_timer(cs, t, dc.isac.arcofitimer);
 	arcofi_fsm(cs, ARCOFI_TIMEOUT, NULL);
 }
 
@@ -125,7 +125,7 @@ clear_arcofi(struct IsdnCardState *cs) {
 
 void
 init_arcofi(struct IsdnCardState *cs) {
-	setup_timer(&cs->dc.isac.arcofitimer, (void *)arcofi_timer, (long)cs);
+	timer_setup(&cs->dc.isac.arcofitimer, arcofi_timer, 0);
 	init_waitqueue_head(&cs->dc.isac.arcofi_wait);
 	test_and_set_bit(HW_ARCOFI, &cs->HW_Flags);
 }
diff --git a/drivers/isdn/hisax/diva.c b/drivers/isdn/hisax/diva.c
index 3fc94e7741ae..38bdd3f7b960 100644
--- a/drivers/isdn/hisax/diva.c
+++ b/drivers/isdn/hisax/diva.c
@@ -798,8 +798,9 @@ reset_diva(struct IsdnCardState *cs)
 #define DIVA_ASSIGN 1
 
 static void
-diva_led_handler(struct IsdnCardState *cs)
+diva_led_handler(struct timer_list *t)
 {
+	struct IsdnCardState *cs = from_timer(cs, t, hw.diva.tl);
 	int blink = 0;
 
 	if ((cs->subtyp == DIVA_IPAC_ISA) ||
@@ -828,7 +829,6 @@ diva_led_handler(struct IsdnCardState *cs)
 
 	byteout(cs->hw.diva.ctrl, cs->hw.diva.ctrl_reg);
 	if (blink) {
-		init_timer(&cs->hw.diva.tl);
 		cs->hw.diva.tl.expires = jiffies + ((blink * HZ) / 1000);
 		add_timer(&cs->hw.diva.tl);
 	}
@@ -900,7 +900,7 @@ Diva_card_msg(struct IsdnCardState *cs, int mt, void *arg)
 	    (cs->subtyp != DIVA_IPAC_PCI) &&
 	    (cs->subtyp != DIVA_IPACX_PCI)) {
 		spin_lock_irqsave(&cs->lock, flags);
-		diva_led_handler(cs);
+		diva_led_handler(&cs->hw.diva.tl);
 		spin_unlock_irqrestore(&cs->lock, flags);
 	}
 	return (0);
@@ -978,8 +978,7 @@ static int setup_diva_common(struct IsdnCardState *cs)
 		printk(KERN_INFO "Diva: IPACX Design Id: %x\n",
 		       MemReadISAC_IPACX(cs, IPACX_ID) & 0x3F);
 	} else { /* DIVA 2.0 */
-		setup_timer(&cs->hw.diva.tl, (void *)diva_led_handler,
-			    (long)cs);
+		timer_setup(&cs->hw.diva.tl, diva_led_handler, 0);
 		cs->readisac  = &ReadISAC;
 		cs->writeisac = &WriteISAC;
 		cs->readisacfifo  = &ReadISACfifo;
diff --git a/drivers/isdn/hisax/elsa.c b/drivers/isdn/hisax/elsa.c
index 03bc5d504e22..b21c05820f44 100644
--- a/drivers/isdn/hisax/elsa.c
+++ b/drivers/isdn/hisax/elsa.c
@@ -606,8 +606,9 @@ check_arcofi(struct IsdnCardState *cs)
 #endif /* ARCOFI_USE */
 
 static void
-elsa_led_handler(struct IsdnCardState *cs)
+elsa_led_handler(struct timer_list *t)
 {
+	struct IsdnCardState *cs = from_timer(cs, t, hw.elsa.tl);
 	int blink = 0;
 
 	if (cs->subtyp == ELSA_PCMCIA || cs->subtyp == ELSA_PCMCIA_IPAC)
@@ -640,7 +641,6 @@ elsa_led_handler(struct IsdnCardState *cs)
 	} else
 		byteout(cs->hw.elsa.ctrl, cs->hw.elsa.ctrl_reg);
 	if (blink) {
-		init_timer(&cs->hw.elsa.tl);
 		cs->hw.elsa.tl.expires = jiffies + ((blink * HZ) / 1000);
 		add_timer(&cs->hw.elsa.tl);
 	}
@@ -715,7 +715,7 @@ Elsa_card_msg(struct IsdnCardState *cs, int mt, void *arg)
 			init_modem(cs);
 		}
 #endif
-		elsa_led_handler(cs);
+		elsa_led_handler(&cs->hw.elsa.tl);
 		return (ret);
 	case (MDL_REMOVE | REQUEST):
 		cs->hw.elsa.status &= 0;
@@ -767,7 +767,7 @@ Elsa_card_msg(struct IsdnCardState *cs, int mt, void *arg)
 		else
 			cs->hw.elsa.status &= ~ELSA_BAD_PWR;
 	}
-	elsa_led_handler(cs);
+	elsa_led_handler(&cs->hw.elsa.tl);
 	return (ret);
 }
 
@@ -1147,7 +1147,7 @@ static int setup_elsa_common(struct IsdnCard *card)
 	init_arcofi(cs);
 #endif
 	setup_isac(cs);
-	setup_timer(&cs->hw.elsa.tl, (void *)elsa_led_handler, (long)cs);
+	timer_setup(&cs->hw.elsa.tl, elsa_led_handler, 0);
 	/* Teste Timer */
 	if (cs->hw.elsa.timer) {
 		byteout(cs->hw.elsa.trig, 0xff);
diff --git a/drivers/isdn/hisax/fsm.c b/drivers/isdn/hisax/fsm.c
index d63266fa8cbd..3e020ec0f65e 100644
--- a/drivers/isdn/hisax/fsm.c
+++ b/drivers/isdn/hisax/fsm.c
@@ -85,8 +85,9 @@ FsmChangeState(struct FsmInst *fi, int newstate)
 }
 
 static void
-FsmExpireTimer(struct FsmTimer *ft)
+FsmExpireTimer(struct timer_list *t)
 {
+	struct FsmTimer *ft = from_timer(ft, t, tl);
 #if FSM_TIMER_DEBUG
 	if (ft->fi->debug)
 		ft->fi->printdebug(ft->fi, "FsmExpireTimer %lx", (long) ft);
@@ -102,7 +103,7 @@ FsmInitTimer(struct FsmInst *fi, struct FsmTimer *ft)
 	if (ft->fi->debug)
 		ft->fi->printdebug(ft->fi, "FsmInitTimer %lx", (long) ft);
 #endif
-	setup_timer(&ft->tl, (void *)FsmExpireTimer, (long)ft);
+	timer_setup(&ft->tl, FsmExpireTimer, 0);
 }
 
 void
@@ -131,7 +132,6 @@ FsmAddTimer(struct FsmTimer *ft,
 		ft->fi->printdebug(ft->fi, "FsmAddTimer already active!");
 		return -1;
 	}
-	init_timer(&ft->tl);
 	ft->event = event;
 	ft->arg = arg;
 	ft->tl.expires = jiffies + (millisec * HZ) / 1000;
@@ -152,7 +152,6 @@ FsmRestartTimer(struct FsmTimer *ft,
 
 	if (timer_pending(&ft->tl))
 		del_timer(&ft->tl);
-	init_timer(&ft->tl);
 	ft->event = event;
 	ft->arg = arg;
 	ft->tl.expires = jiffies + (millisec * HZ) / 1000;
diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c
index 9090cc1e1f29..e9bb8fb67ad0 100644
--- a/drivers/isdn/hisax/hfc4s8s_l1.c
+++ b/drivers/isdn/hisax/hfc4s8s_l1.c
@@ -591,8 +591,9 @@ bch_l2l1(struct hisax_if *ifc, int pr, void *arg)
 /* layer 1 timer function */
 /**************************/
 static void
-hfc_l1_timer(struct hfc4s8s_l1 *l1)
+hfc_l1_timer(struct timer_list *t)
 {
+	struct hfc4s8s_l1 *l1 = from_timer(l1, t, l1_timer);
 	u_long flags;
 
 	if (!l1->enabled)
@@ -1396,8 +1397,7 @@ setup_instance(hfc4s8s_hw *hw)
 		l1p = hw->l1 + i;
 		spin_lock_init(&l1p->lock);
 		l1p->hw = hw;
-		setup_timer(&l1p->l1_timer, (void *)hfc_l1_timer,
-			    (long)(l1p));
+		timer_setup(&l1p->l1_timer, hfc_l1_timer, 0);
 		l1p->st_num = i;
 		skb_queue_head_init(&l1p->d_tx_queue);
 		l1p->d_if.ifc.priv = hw->l1 + i;
diff --git a/drivers/isdn/hisax/hfc_2bds0.c b/drivers/isdn/hisax/hfc_2bds0.c
index ad8597a1a07e..86b82172e992 100644
--- a/drivers/isdn/hisax/hfc_2bds0.c
+++ b/drivers/isdn/hisax/hfc_2bds0.c
@@ -1014,7 +1014,7 @@ setstack_hfcd(struct PStack *st, struct IsdnCardState *cs)
 }
 
 static void
-hfc_dbusy_timer(struct IsdnCardState *cs)
+hfc_dbusy_timer(struct timer_list *t)
 {
 }
 
@@ -1073,6 +1073,6 @@ set_cs_func(struct IsdnCardState *cs)
 	cs->writeisacfifo = &dummyf;
 	cs->BC_Read_Reg = &ReadReg;
 	cs->BC_Write_Reg = &WriteReg;
-	setup_timer(&cs->dbusytimer, (void *)hfc_dbusy_timer, (long)cs);
+	timer_setup(&cs->dbusytimer, hfc_dbusy_timer, 0);
 	INIT_WORK(&cs->tqueue, hfcd_bh);
 }
diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c
index f9ca35cc32b1..8e5b03161b2f 100644
--- a/drivers/isdn/hisax/hfc_pci.c
+++ b/drivers/isdn/hisax/hfc_pci.c
@@ -165,8 +165,9 @@ reset_hfcpci(struct IsdnCardState *cs)
 /* Timer function called when kernel timer expires */
 /***************************************************/
 static void
-hfcpci_Timer(struct IsdnCardState *cs)
+hfcpci_Timer(struct timer_list *t)
 {
+	struct IsdnCardState *cs = from_timer(cs, t, hw.hfcpci.timer);
 	cs->hw.hfcpci.timer.expires = jiffies + 75;
 	/* WD RESET */
 /*      WriteReg(cs, HFCD_DATA, HFCD_CTMT, cs->hw.hfcpci.ctmt | 0x80);
@@ -1095,7 +1096,7 @@ hfcpci_interrupt(int intno, void *dev_id)
 /* timer callback for D-chan busy resolution. Currently no function */
 /********************************************************************/
 static void
-hfcpci_dbusy_timer(struct IsdnCardState *cs)
+hfcpci_dbusy_timer(struct timer_list *t)
 {
 }
 
@@ -1582,7 +1583,7 @@ inithfcpci(struct IsdnCardState *cs)
 	cs->bcs[1].BC_SetStack = setstack_2b;
 	cs->bcs[0].BC_Close = close_hfcpci;
 	cs->bcs[1].BC_Close = close_hfcpci;
-	setup_timer(&cs->dbusytimer, (void *)hfcpci_dbusy_timer, (long)cs);
+	timer_setup(&cs->dbusytimer, hfcpci_dbusy_timer, 0);
 	mode_hfcpci(cs->bcs, 0, 0);
 	mode_hfcpci(cs->bcs + 1, 0, 1);
 }
@@ -1744,7 +1745,7 @@ setup_hfcpci(struct IsdnCard *card)
 	cs->BC_Write_Reg = NULL;
 	cs->irq_func = &hfcpci_interrupt;
 	cs->irq_flags |= IRQF_SHARED;
-	setup_timer(&cs->hw.hfcpci.timer, (void *)hfcpci_Timer, (long)cs);
+	timer_setup(&cs->hw.hfcpci.timer, hfcpci_Timer, 0);
 	cs->cardmsg = &hfcpci_card_msg;
 	cs->auxcmd = &hfcpci_auxcmd;
 
diff --git a/drivers/isdn/hisax/hfc_sx.c b/drivers/isdn/hisax/hfc_sx.c
index 3aef8e1a90e4..d925f579bc80 100644
--- a/drivers/isdn/hisax/hfc_sx.c
+++ b/drivers/isdn/hisax/hfc_sx.c
@@ -418,8 +418,9 @@ reset_hfcsx(struct IsdnCardState *cs)
 /* Timer function called when kernel timer expires */
 /***************************************************/
 static void
-hfcsx_Timer(struct IsdnCardState *cs)
+hfcsx_Timer(struct timer_list *t)
 {
+	struct IsdnCardState *cs = from_timer(cs, t, hw.hfcsx.timer);
 	cs->hw.hfcsx.timer.expires = jiffies + 75;
 	/* WD RESET */
 /*      WriteReg(cs, HFCD_DATA, HFCD_CTMT, cs->hw.hfcsx.ctmt | 0x80);
@@ -860,7 +861,7 @@ hfcsx_interrupt(int intno, void *dev_id)
 /* timer callback for D-chan busy resolution. Currently no function */
 /********************************************************************/
 static void
-hfcsx_dbusy_timer(struct IsdnCardState *cs)
+hfcsx_dbusy_timer(struct timer_list *t)
 {
 }
 
@@ -1495,7 +1496,7 @@ int setup_hfcsx(struct IsdnCard *card)
 	} else
 		return (0);	/* no valid card type */
 
-	setup_timer(&cs->dbusytimer, (void *)hfcsx_dbusy_timer, (long)cs);
+	timer_setup(&cs->dbusytimer, hfcsx_dbusy_timer, 0);
 	INIT_WORK(&cs->tqueue, hfcsx_bh);
 	cs->readisac = NULL;
 	cs->writeisac = NULL;
@@ -1507,7 +1508,7 @@ int setup_hfcsx(struct IsdnCard *card)
 
 	cs->hw.hfcsx.b_fifo_size = 0; /* fifo size still unknown */
 	cs->hw.hfcsx.cirm = ccd_sp_irqtab[cs->irq & 0xF]; /* RAM not evaluated */
-	setup_timer(&cs->hw.hfcsx.timer, (void *)hfcsx_Timer, (long)cs);
+	timer_setup(&cs->hw.hfcsx.timer, hfcsx_Timer, 0);
 
 	reset_hfcsx(cs);
 	cs->cardmsg = &hfcsx_card_msg;
diff --git a/drivers/isdn/hisax/hfc_usb.c b/drivers/isdn/hisax/hfc_usb.c
index e8212185d386..97ecb3073045 100644
--- a/drivers/isdn/hisax/hfc_usb.c
+++ b/drivers/isdn/hisax/hfc_usb.c
@@ -343,8 +343,9 @@ handle_led(hfcusb_data *hfc, int event)
 
 /* ISDN l1 timer T3 expires */
 static void
-l1_timer_expire_t3(hfcusb_data *hfc)
+l1_timer_expire_t3(struct timer_list *t)
 {
+	hfcusb_data *hfc = from_timer(hfc, t, t3_timer);
 	hfc->d_if.ifc.l1l2(&hfc->d_if.ifc, PH_DEACTIVATE | INDICATION,
 			   NULL);
 
@@ -360,8 +361,9 @@ l1_timer_expire_t3(hfcusb_data *hfc)
 
 /* ISDN l1 timer T4 expires */
 static void
-l1_timer_expire_t4(hfcusb_data *hfc)
+l1_timer_expire_t4(struct timer_list *t)
 {
+	hfcusb_data *hfc = from_timer(hfc, t, t4_timer);
 	hfc->d_if.ifc.l1l2(&hfc->d_if.ifc, PH_DEACTIVATE | INDICATION,
 			   NULL);
 
@@ -1165,10 +1167,10 @@ hfc_usb_init(hfcusb_data *hfc)
 	hfc->old_led_state = 0;
 
 	/* init the t3 timer */
-	setup_timer(&hfc->t3_timer, (void *)l1_timer_expire_t3, (long)hfc);
+	timer_setup(&hfc->t3_timer, l1_timer_expire_t3, 0);
 
 	/* init the t4 timer */
-	setup_timer(&hfc->t4_timer, (void *)l1_timer_expire_t4, (long)hfc);
+	timer_setup(&hfc->t4_timer, l1_timer_expire_t4, 0);
 
 	/* init the background machinery for control requests */
 	hfc->ctrl_read.bRequestType = 0xc0;
diff --git a/drivers/isdn/hisax/hfcscard.c b/drivers/isdn/hisax/hfcscard.c
index 467287096918..380bbeda9c74 100644
--- a/drivers/isdn/hisax/hfcscard.c
+++ b/drivers/isdn/hisax/hfcscard.c
@@ -41,8 +41,9 @@ hfcs_interrupt(int intno, void *dev_id)
 }
 
 static void
-hfcs_Timer(struct IsdnCardState *cs)
+hfcs_Timer(struct timer_list *t)
 {
+	struct IsdnCardState *cs = from_timer(cs, t, hw.hfcD.timer);
 	cs->hw.hfcD.timer.expires = jiffies + 75;
 	/* WD RESET */
 /*	WriteReg(cs, HFCD_DATA, HFCD_CTMT, cs->hw.hfcD.ctmt | 0x80);
@@ -253,7 +254,7 @@ int setup_hfcs(struct IsdnCard *card)
 		outb(0x57, cs->hw.hfcD.addr | 1);
 	}
 	set_cs_func(cs);
-	setup_timer(&cs->hw.hfcD.timer, (void *)hfcs_Timer, (long)cs);
+	timer_setup(&cs->hw.hfcD.timer, hfcs_Timer, 0);
 	cs->cardmsg = &hfcs_card_msg;
 	cs->irq_func = &hfcs_interrupt;
 	return (1);
diff --git a/drivers/isdn/hisax/icc.c b/drivers/isdn/hisax/icc.c
index 8d1804572b32..831dd1bb81ef 100644
--- a/drivers/isdn/hisax/icc.c
+++ b/drivers/isdn/hisax/icc.c
@@ -168,7 +168,6 @@ icc_fill_fifo(struct IsdnCardState *cs)
 		debugl1(cs, "icc_fill_fifo dbusytimer running");
 		del_timer(&cs->dbusytimer);
 	}
-	init_timer(&cs->dbusytimer);
 	cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ)/1000);
 	add_timer(&cs->dbusytimer);
 	if (cs->debug & L1_DEB_ISAC_FIFO) {
@@ -580,8 +579,9 @@ DC_Close_icc(struct IsdnCardState *cs) {
 }
 
 static void
-dbusy_timer_handler(struct IsdnCardState *cs)
+dbusy_timer_handler(struct timer_list *t)
 {
+	struct IsdnCardState *cs = from_timer(cs, t, dbusytimer);
 	struct PStack *stptr;
 	int	rbch, star;
 
@@ -676,5 +676,5 @@ clear_pending_icc_ints(struct IsdnCardState *cs)
 void setup_icc(struct IsdnCardState *cs)
 {
 	INIT_WORK(&cs->tqueue, icc_bh);
-	setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
+	timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0);
 }
diff --git a/drivers/isdn/hisax/ipacx.c b/drivers/isdn/hisax/ipacx.c
index c426b4fea28a..c7086c1534bd 100644
--- a/drivers/isdn/hisax/ipacx.c
+++ b/drivers/isdn/hisax/ipacx.c
@@ -35,7 +35,7 @@
 static void ph_command(struct IsdnCardState *cs, unsigned int command);
 static inline void cic_int(struct IsdnCardState *cs);
 static void dch_l2l1(struct PStack *st, int pr, void *arg);
-static void dbusy_timer_handler(struct IsdnCardState *cs);
+static void dbusy_timer_handler(struct timer_list *t);
 static void dch_empty_fifo(struct IsdnCardState *cs, int count);
 static void dch_fill_fifo(struct IsdnCardState *cs);
 static inline void dch_int(struct IsdnCardState *cs);
@@ -198,8 +198,9 @@ dch_l2l1(struct PStack *st, int pr, void *arg)
 //----------------------------------------------------------
 //----------------------------------------------------------
 static void
-dbusy_timer_handler(struct IsdnCardState *cs)
+dbusy_timer_handler(struct timer_list *t)
 {
+	struct IsdnCardState *cs = from_timer(cs, t, dbusytimer);
 	struct PStack *st;
 	int	rbchd, stard;
 
@@ -298,7 +299,6 @@ dch_fill_fifo(struct IsdnCardState *cs)
 		debugl1(cs, "dch_fill_fifo dbusytimer running");
 		del_timer(&cs->dbusytimer);
 	}
-	init_timer(&cs->dbusytimer);
 	cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ)/1000);
 	add_timer(&cs->dbusytimer);
 
@@ -424,7 +424,7 @@ dch_init(struct IsdnCardState *cs)
 
 	cs->setstack_d      = dch_setstack;
 
-	setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
+	timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0);
 
 	cs->writeisac(cs, IPACX_TR_CONF0, 0x00);  // clear LDD
 	cs->writeisac(cs, IPACX_TR_CONF2, 0x00);  // enable transmitter
diff --git a/drivers/isdn/hisax/isac.c b/drivers/isdn/hisax/isac.c
index ea965f29a555..bd40e0671ded 100644
--- a/drivers/isdn/hisax/isac.c
+++ b/drivers/isdn/hisax/isac.c
@@ -171,7 +171,6 @@ isac_fill_fifo(struct IsdnCardState *cs)
 		debugl1(cs, "isac_fill_fifo dbusytimer running");
 		del_timer(&cs->dbusytimer);
 	}
-	init_timer(&cs->dbusytimer);
 	cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ)/1000);
 	add_timer(&cs->dbusytimer);
 	if (cs->debug & L1_DEB_ISAC_FIFO) {
@@ -584,8 +583,9 @@ DC_Close_isac(struct IsdnCardState *cs)
 }
 
 static void
-dbusy_timer_handler(struct IsdnCardState *cs)
+dbusy_timer_handler(struct timer_list *t)
 {
+	struct IsdnCardState *cs = from_timer(cs, t, dbusytimer);
 	struct PStack *stptr;
 	int	rbch, star;
 
@@ -677,5 +677,5 @@ void clear_pending_isac_ints(struct IsdnCardState *cs)
 void setup_isac(struct IsdnCardState *cs)
 {
 	INIT_WORK(&cs->tqueue, isac_bh);
-	setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
+	timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0);
 }
diff --git a/drivers/isdn/hisax/isar.c b/drivers/isdn/hisax/isar.c
index 98b4b67ea337..d01ff116797b 100644
--- a/drivers/isdn/hisax/isar.c
+++ b/drivers/isdn/hisax/isar.c
@@ -1267,7 +1267,8 @@ isar_int_main(struct IsdnCardState *cs)
 }
 
 static void
-ftimer_handler(struct BCState *bcs) {
+ftimer_handler(struct timer_list *t) {
+	struct BCState *bcs = from_timer(bcs, t, hw.isar.ftimer);
 	if (bcs->cs->debug)
 		debugl1(bcs->cs, "ftimer flags %04lx",
 			bcs->Flag);
@@ -1902,8 +1903,6 @@ void initisar(struct IsdnCardState *cs)
 	cs->bcs[1].BC_SetStack = setstack_isar;
 	cs->bcs[0].BC_Close = close_isarstate;
 	cs->bcs[1].BC_Close = close_isarstate;
-	setup_timer(&cs->bcs[0].hw.isar.ftimer, (void *)ftimer_handler,
-		    (long)&cs->bcs[0]);
-	setup_timer(&cs->bcs[1].hw.isar.ftimer, (void *)ftimer_handler,
-		    (long)&cs->bcs[1]);
+	timer_setup(&cs->bcs[0].hw.isar.ftimer, ftimer_handler, 0);
+	timer_setup(&cs->bcs[1].hw.isar.ftimer, ftimer_handler, 0);
 }
diff --git a/drivers/isdn/hisax/isdnl3.c b/drivers/isdn/hisax/isdnl3.c
index 569ce52c567b..bb3f9ec62749 100644
--- a/drivers/isdn/hisax/isdnl3.c
+++ b/drivers/isdn/hisax/isdnl3.c
@@ -160,8 +160,9 @@ newl3state(struct l3_process *pc, int state)
 }
 
 static void
-L3ExpireTimer(struct L3Timer *t)
+L3ExpireTimer(struct timer_list *timer)
 {
+	struct L3Timer *t = from_timer(t, timer, tl);
 	t->pc->st->lli.l4l3(t->pc->st, t->event, t->pc);
 }
 
@@ -169,7 +170,7 @@ void
 L3InitTimer(struct l3_process *pc, struct L3Timer *t)
 {
 	t->pc = pc;
-	setup_timer(&t->tl, (void *)L3ExpireTimer, (long)t);
+	timer_setup(&t->tl, L3ExpireTimer, 0);
 }
 
 void
@@ -186,7 +187,6 @@ L3AddTimer(struct L3Timer *t,
 		printk(KERN_WARNING "L3AddTimer: timer already active!\n");
 		return -1;
 	}
-	init_timer(&t->tl);
 	t->event = event;
 	t->tl.expires = jiffies + (millisec * HZ) / 1000;
 	add_timer(&t->tl);
diff --git a/drivers/isdn/hisax/saphir.c b/drivers/isdn/hisax/saphir.c
index 6b2d0eccdd56..db906cb37a3f 100644
--- a/drivers/isdn/hisax/saphir.c
+++ b/drivers/isdn/hisax/saphir.c
@@ -159,8 +159,9 @@ Start_ISAC:
 }
 
 static void
-SaphirWatchDog(struct IsdnCardState *cs)
+SaphirWatchDog(struct timer_list *t)
 {
+	struct IsdnCardState *cs = from_timer(cs, t, hw.saphir.timer);
 	u_long flags;
 
 	spin_lock_irqsave(&cs->lock, flags);
@@ -268,9 +269,7 @@ int setup_saphir(struct IsdnCard *card)
 	       cs->irq, cs->hw.saphir.cfg_reg);
 
 	setup_isac(cs);
-	cs->hw.saphir.timer.function = (void *) SaphirWatchDog;
-	cs->hw.saphir.timer.data = (long) cs;
-	init_timer(&cs->hw.saphir.timer);
+	timer_setup(&cs->hw.saphir.timer, SaphirWatchDog, 0);
 	cs->hw.saphir.timer.expires = jiffies + 4 * HZ;
 	add_timer(&cs->hw.saphir.timer);
 	if (saphir_reset(cs)) {
diff --git a/drivers/isdn/hisax/teleint.c b/drivers/isdn/hisax/teleint.c
index 950399f066ef..247aa33076b1 100644
--- a/drivers/isdn/hisax/teleint.c
+++ b/drivers/isdn/hisax/teleint.c
@@ -179,8 +179,9 @@ Start_ISAC:
 }
 
 static void
-TeleInt_Timer(struct IsdnCardState *cs)
+TeleInt_Timer(struct timer_list *t)
 {
+	struct IsdnCardState *cs = from_timer(cs, t, hw.hfc.timer);
 	int stat = 0;
 	u_long flags;
 
@@ -278,7 +279,7 @@ int setup_TeleInt(struct IsdnCard *card)
 	cs->bcs[0].hw.hfc.send = NULL;
 	cs->bcs[1].hw.hfc.send = NULL;
 	cs->hw.hfc.fifosize = 7 * 1024 + 512;
-	setup_timer(&cs->hw.hfc.timer, (void *)TeleInt_Timer, (long)cs);
+	timer_setup(&cs->hw.hfc.timer, TeleInt_Timer, 0);
 	if (!request_region(cs->hw.hfc.addr, 2, "TeleInt isdn")) {
 		printk(KERN_WARNING
 		       "HiSax: TeleInt config port %x-%x already in use\n",
diff --git a/drivers/isdn/hisax/w6692.c b/drivers/isdn/hisax/w6692.c
index 6f6733b7c1e4..c4be1644f5bb 100644
--- a/drivers/isdn/hisax/w6692.c
+++ b/drivers/isdn/hisax/w6692.c
@@ -188,7 +188,6 @@ W6692_fill_fifo(struct IsdnCardState *cs)
 		debugl1(cs, "W6692_fill_fifo dbusytimer running");
 		del_timer(&cs->dbusytimer);
 	}
-	init_timer(&cs->dbusytimer);
 	cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ) / 1000);
 	add_timer(&cs->dbusytimer);
 	if (cs->debug & L1_DEB_ISAC_FIFO) {
@@ -684,8 +683,9 @@ DC_Close_W6692(struct IsdnCardState *cs)
 }
 
 static void
-dbusy_timer_handler(struct IsdnCardState *cs)
+dbusy_timer_handler(struct timer_list *t)
 {
+	struct IsdnCardState *cs = from_timer(cs, t, dbusytimer);
 	struct PStack *stptr;
 	int rbch, star;
 	u_long flags;
@@ -904,8 +904,7 @@ static void initW6692(struct IsdnCardState *cs, int part)
 	if (part & 1) {
 		cs->setstack_d = setstack_W6692;
 		cs->DC_Close = DC_Close_W6692;
-		setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler,
-			    (long)cs);
+		timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0);
 		resetW6692(cs);
 		ph_command(cs, W_L1CMD_RST);
 		cs->dc.w6692.ph_state = W_L1CMD_RST;
diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c
index e97232646ba1..a4597e96c916 100644
--- a/drivers/isdn/isdnloop/isdnloop.c
+++ b/drivers/isdn/isdnloop/isdnloop.c
@@ -90,9 +90,9 @@ isdnloop_bchan_send(isdnloop_card *card, int ch)
  *   data = pointer to card struct, set by kernel timer.data
  */
 static void
-isdnloop_pollbchan(unsigned long data)
+isdnloop_pollbchan(struct timer_list *t)
 {
-	isdnloop_card *card = (isdnloop_card *) data;
+	isdnloop_card *card = from_timer(card, t, rb_timer);
 	unsigned long flags;
 
 	if (card->flags & ISDNLOOP_FLAGS_B1ACTIVE)
@@ -305,9 +305,9 @@ isdnloop_putmsg(isdnloop_card *card, unsigned char c)
  *   data = pointer to card struct
  */
 static void
-isdnloop_polldchan(unsigned long data)
+isdnloop_polldchan(struct timer_list *t)
 {
-	isdnloop_card *card = (isdnloop_card *) data;
+	isdnloop_card *card = from_timer(card, t, st_timer);
 	struct sk_buff *skb;
 	int avail;
 	int left;
@@ -373,8 +373,6 @@ isdnloop_polldchan(unsigned long data)
 			card->flags |= ISDNLOOP_FLAGS_RBTIMER;
 			spin_lock_irqsave(&card->isdnloop_lock, flags);
 			del_timer(&card->rb_timer);
-			card->rb_timer.function = isdnloop_pollbchan;
-			card->rb_timer.data = (unsigned long) card;
 			card->rb_timer.expires = jiffies + ISDNLOOP_TIMER_BCREAD;
 			add_timer(&card->rb_timer);
 			spin_unlock_irqrestore(&card->isdnloop_lock, flags);
@@ -588,9 +586,10 @@ isdnloop_atimeout(isdnloop_card *card, int ch)
  * Wrapper for isdnloop_atimeout().
  */
 static void
-isdnloop_atimeout0(unsigned long data)
+isdnloop_atimeout0(struct timer_list *t)
 {
-	isdnloop_card *card = (isdnloop_card *) data;
+	isdnloop_card *card = from_timer(card, t, c_timer[0]);
+
 	isdnloop_atimeout(card, 0);
 }
 
@@ -598,9 +597,10 @@ isdnloop_atimeout0(unsigned long data)
  * Wrapper for isdnloop_atimeout().
  */
 static void
-isdnloop_atimeout1(unsigned long data)
+isdnloop_atimeout1(struct timer_list *t)
 {
-	isdnloop_card *card = (isdnloop_card *) data;
+	isdnloop_card *card = from_timer(card, t, c_timer[1]);
+
 	isdnloop_atimeout(card, 1);
 }
 
@@ -617,13 +617,9 @@ isdnloop_start_ctimer(isdnloop_card *card, int ch)
 	unsigned long flags;
 
 	spin_lock_irqsave(&card->isdnloop_lock, flags);
-	init_timer(&card->c_timer[ch]);
+	timer_setup(&card->c_timer[ch], ch ? isdnloop_atimeout1
+					   : isdnloop_atimeout0, 0);
 	card->c_timer[ch].expires = jiffies + ISDNLOOP_TIMER_ALERTWAIT;
-	if (ch)
-		card->c_timer[ch].function = isdnloop_atimeout1;
-	else
-		card->c_timer[ch].function = isdnloop_atimeout0;
-	card->c_timer[ch].data = (unsigned long) card;
 	add_timer(&card->c_timer[ch]);
 	spin_unlock_irqrestore(&card->isdnloop_lock, flags);
 }
@@ -1113,10 +1109,9 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp)
 		       sdef.ptype);
 		return -EINVAL;
 	}
-	init_timer(&card->st_timer);
+	timer_setup(&card->rb_timer, isdnloop_pollbchan, 0);
+	timer_setup(&card->st_timer, isdnloop_polldchan, 0);
 	card->st_timer.expires = jiffies + ISDNLOOP_TIMER_DCREAD;
-	card->st_timer.function = isdnloop_polldchan;
-	card->st_timer.data = (unsigned long) card;
 	add_timer(&card->st_timer);
 	card->flags |= ISDNLOOP_FLAGS_RUNNING;
 	spin_unlock_irqrestore(&card->isdnloop_lock, flags);
diff --git a/drivers/isdn/mISDN/dsp.h b/drivers/isdn/mISDN/dsp.h
index fc1733a08845..fa09d511a8ed 100644
--- a/drivers/isdn/mISDN/dsp.h
+++ b/drivers/isdn/mISDN/dsp.h
@@ -259,7 +259,7 @@ extern u8 *dsp_dtmf_goertzel_decode(struct dsp *dsp, u8 *data, int len,
 
 extern int dsp_tone(struct dsp *dsp, int tone);
 extern void dsp_tone_copy(struct dsp *dsp, u8 *data, int len);
-extern void dsp_tone_timeout(void *arg);
+extern void dsp_tone_timeout(struct timer_list *t);
 
 extern void dsp_bf_encrypt(struct dsp *dsp, u8 *data, int len);
 extern void dsp_bf_decrypt(struct dsp *dsp, u8 *data, int len);
diff --git a/drivers/isdn/mISDN/dsp_core.c b/drivers/isdn/mISDN/dsp_core.c
index 880e9d367a39..cd036e87335a 100644
--- a/drivers/isdn/mISDN/dsp_core.c
+++ b/drivers/isdn/mISDN/dsp_core.c
@@ -1092,7 +1092,7 @@ dspcreate(struct channel_req *crq)
 	ndsp->pcm_bank_tx = -1;
 	ndsp->hfc_conf = -1; /* current conference number */
 	/* set tone timer */
-	setup_timer(&ndsp->tone.tl, (void *)dsp_tone_timeout, (long)ndsp);
+	timer_setup(&ndsp->tone.tl, dsp_tone_timeout, 0);
 
 	if (dtmfthreshold < 20 || dtmfthreshold > 500)
 		dtmfthreshold = 200;
@@ -1202,9 +1202,7 @@ static int __init dsp_init(void)
 	}
 
 	/* set sample timer */
-	dsp_spl_tl.function = (void *)dsp_cmx_send;
-	dsp_spl_tl.data = 0;
-	init_timer(&dsp_spl_tl);
+	timer_setup(&dsp_spl_tl, (void *)dsp_cmx_send, 0);
 	dsp_spl_tl.expires = jiffies + dsp_tics;
 	dsp_spl_jiffies = dsp_spl_tl.expires;
 	add_timer(&dsp_spl_tl);
diff --git a/drivers/isdn/mISDN/dsp_tones.c b/drivers/isdn/mISDN/dsp_tones.c
index 057e0d6a369b..8389e2105cdc 100644
--- a/drivers/isdn/mISDN/dsp_tones.c
+++ b/drivers/isdn/mISDN/dsp_tones.c
@@ -457,9 +457,9 @@ dsp_tone_hw_message(struct dsp *dsp, u8 *sample, int len)
  * timer expires *
  *****************/
 void
-dsp_tone_timeout(void *arg)
+dsp_tone_timeout(struct timer_list *t)
 {
-	struct dsp *dsp = arg;
+	struct dsp *dsp = from_timer(dsp, t, tone.tl);
 	struct dsp_tone *tone = &dsp->tone;
 	struct pattern *pat = (struct pattern *)tone->pattern;
 	int index = tone->index;
@@ -478,7 +478,6 @@ dsp_tone_timeout(void *arg)
 	else
 		dsp_tone_hw_message(dsp, pat->data[index], *(pat->siz[index]));
 	/* set timer */
-	init_timer(&tone->tl);
 	tone->tl.expires = jiffies + (pat->seq[index] * HZ) / 8000;
 	add_timer(&tone->tl);
 }
@@ -541,7 +540,6 @@ dsp_tone(struct dsp *dsp, int tone)
 		/* set timer */
 		if (timer_pending(&tonet->tl))
 			del_timer(&tonet->tl);
-		init_timer(&tonet->tl);
 		tonet->tl.expires = jiffies + (pat->seq[0] * HZ) / 8000;
 		add_timer(&tonet->tl);
 	} else {
diff --git a/drivers/isdn/mISDN/fsm.c b/drivers/isdn/mISDN/fsm.c
index 92e6570b1143..cabcb906e0b5 100644
--- a/drivers/isdn/mISDN/fsm.c
+++ b/drivers/isdn/mISDN/fsm.c
@@ -100,8 +100,9 @@ mISDN_FsmChangeState(struct FsmInst *fi, int newstate)
 EXPORT_SYMBOL(mISDN_FsmChangeState);
 
 static void
-FsmExpireTimer(struct FsmTimer *ft)
+FsmExpireTimer(struct timer_list *t)
 {
+	struct FsmTimer *ft = from_timer(ft, t, tl);
 #if FSM_TIMER_DEBUG
 	if (ft->fi->debug)
 		ft->fi->printdebug(ft->fi, "FsmExpireTimer %lx", (long) ft);
@@ -117,7 +118,7 @@ mISDN_FsmInitTimer(struct FsmInst *fi, struct FsmTimer *ft)
 	if (ft->fi->debug)
 		ft->fi->printdebug(ft->fi, "mISDN_FsmInitTimer %lx", (long) ft);
 #endif
-	setup_timer(&ft->tl, (void *)FsmExpireTimer, (long)ft);
+	timer_setup(&ft->tl, FsmExpireTimer, 0);
 }
 EXPORT_SYMBOL(mISDN_FsmInitTimer);
 
@@ -153,7 +154,6 @@ mISDN_FsmAddTimer(struct FsmTimer *ft,
 		}
 		return -1;
 	}
-	init_timer(&ft->tl);
 	ft->event = event;
 	ft->arg = arg;
 	ft->tl.expires = jiffies + (millisec * HZ) / 1000;
@@ -175,7 +175,6 @@ mISDN_FsmRestartTimer(struct FsmTimer *ft,
 
 	if (timer_pending(&ft->tl))
 		del_timer(&ft->tl);
-	init_timer(&ft->tl);
 	ft->event = event;
 	ft->arg = arg;
 	ft->tl.expires = jiffies + (millisec * HZ) / 1000;
diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c
index 6be2041248d3..b5d590e378ac 100644
--- a/drivers/isdn/mISDN/l1oip_core.c
+++ b/drivers/isdn/mISDN/l1oip_core.c
@@ -842,17 +842,18 @@ l1oip_send_bh(struct work_struct *work)
  * timer stuff
  */
 static void
-l1oip_keepalive(void *data)
+l1oip_keepalive(struct timer_list *t)
 {
-	struct l1oip *hc = (struct l1oip *)data;
+	struct l1oip *hc = from_timer(hc, t, keep_tl);
 
 	schedule_work(&hc->workq);
 }
 
 static void
-l1oip_timeout(void *data)
+l1oip_timeout(struct timer_list *t)
 {
-	struct l1oip			*hc = (struct l1oip *)data;
+	struct l1oip			*hc = from_timer(hc, t,
+								  timeout_tl);
 	struct dchannel		*dch = hc->chan[hc->d_idx].dch;
 
 	if (debug & DEBUG_L1OIP_MSG)
@@ -1437,13 +1438,11 @@ init_card(struct l1oip *hc, int pri, int bundle)
 	if (ret)
 		return ret;
 
-	hc->keep_tl.function = (void *)l1oip_keepalive;
-	hc->keep_tl.data = (ulong)hc;
-	init_timer(&hc->keep_tl);
+	timer_setup(&hc->keep_tl, l1oip_keepalive, 0);
 	hc->keep_tl.expires = jiffies + 2 * HZ; /* two seconds first time */
 	add_timer(&hc->keep_tl);
 
-	setup_timer(&hc->timeout_tl, (void *)l1oip_timeout, (ulong)hc);
+	timer_setup(&hc->timeout_tl, l1oip_timeout, 0);
 	hc->timeout_on = 0; /* state that we have timer off */
 
 	return 0;
diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c
index b1e135fc1fb5..c50a34340f67 100644
--- a/drivers/isdn/mISDN/timerdev.c
+++ b/drivers/isdn/mISDN/timerdev.c
@@ -162,9 +162,9 @@ mISDN_poll(struct file *filep, poll_table *wait)
 }
 
 static void
-dev_expire_timer(unsigned long data)
+dev_expire_timer(struct timer_list *t)
 {
-	struct mISDNtimer *timer = (void *)data;
+	struct mISDNtimer *timer = from_timer(timer, t, tl);
 	u_long			flags;
 
 	spin_lock_irqsave(&timer->dev->lock, flags);
@@ -189,7 +189,7 @@ misdn_add_timer(struct mISDNtimerdev *dev, int timeout)
 		if (!timer)
 			return -ENOMEM;
 		timer->dev = dev;
-		setup_timer(&timer->tl, dev_expire_timer, (long)timer);
+		timer_setup(&timer->tl, dev_expire_timer, 0);
 		spin_lock_irq(&dev->lock);
 		id = timer->id = dev->next_id++;
 		if (dev->next_id < 0)
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index aba0d652095b..0936da592e12 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -483,6 +483,18 @@ config FUJITSU_ES
 	  This driver provides support for Extended Socket network device
           on Extended Partitioning of FUJITSU PRIMEQUEST 2000 E2 series.
 
+config THUNDERBOLT_NET
+	tristate "Networking over Thunderbolt cable"
+	depends on THUNDERBOLT && INET
+	help
+	  Select this if you want to create network between two
+	  computers over a Thunderbolt cable. The driver supports Apple
+	  ThunderboltIP protocol and allows communication with any host
+	  supporting the same protocol including Windows and macOS.
+
+	  To compile this driver a module, choose M here. The module will be
+	  called thunderbolt-net.
+
 source "drivers/net/hyperv/Kconfig"
 
 endif # NETDEVICES
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 676a75f4182a..766f62d02a0b 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -75,3 +75,6 @@ obj-$(CONFIG_HYPERV_NET) += hyperv/
 obj-$(CONFIG_NTB_NETDEV) += ntb_netdev.o
 
 obj-$(CONFIG_FUJITSU_ES) += fjes/
+
+thunderbolt-net-y += thunderbolt.o
+obj-$(CONFIG_THUNDERBOLT_NET) += thunderbolt-net.o
diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c
index 486e1e6997fc..bb49f6e40a19 100644
--- a/drivers/net/appletalk/cops.c
+++ b/drivers/net/appletalk/cops.c
@@ -155,6 +155,7 @@ static int cops_irqlist[] = {
 };
 
 static struct timer_list cops_timer;
+static struct net_device *cops_timer_dev;
 
 /* use 0 for production, 1 for verification, 2 for debug, 3 for verbose debug */
 #ifndef COPS_DEBUG
@@ -187,7 +188,7 @@ static void cops_load (struct net_device *dev);
 static int  cops_nodeid (struct net_device *dev, int nodeid);
 
 static irqreturn_t cops_interrupt (int irq, void *dev_id);
-static void cops_poll (unsigned long ltdev);
+static void cops_poll(struct timer_list *t);
 static void cops_timeout(struct net_device *dev);
 static void cops_rx (struct net_device *dev);
 static netdev_tx_t  cops_send_packet (struct sk_buff *skb,
@@ -424,9 +425,8 @@ static int cops_open(struct net_device *dev)
 		 */
 		if(lp->board==TANGENT)	/* Poll 20 times per second */
 		{
-		    init_timer(&cops_timer);
-		    cops_timer.function = cops_poll;
-		    cops_timer.data 	= (unsigned long)dev;
+		    cops_timer_dev = dev;
+		    timer_setup(&cops_timer, cops_poll, 0);
 		    cops_timer.expires 	= jiffies + HZ/20;
 		    add_timer(&cops_timer);
 		} 
@@ -673,12 +673,11 @@ static int cops_nodeid (struct net_device *dev, int nodeid)
  *	Poll the Tangent type cards to see if we have work.
  */
  
-static void cops_poll(unsigned long ltdev)
+static void cops_poll(struct timer_list *unused)
 {
 	int ioaddr, status;
 	int boguscount = 0;
-
-	struct net_device *dev = (struct net_device *)ltdev;
+	struct net_device *dev = cops_timer_dev;
 
 	del_timer(&cops_timer);
 
diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c
index ac755d2950a6..75a5a9b87c5a 100644
--- a/drivers/net/appletalk/ltpc.c
+++ b/drivers/net/appletalk/ltpc.c
@@ -694,6 +694,7 @@ static int do_read(struct net_device *dev, void *cbuf, int cbuflen,
 /* end of idle handlers -- what should be seen is do_read, do_write */
 
 static struct timer_list ltpc_timer;
+static struct net_device *ltpc_timer_dev;
 
 static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev);
 
@@ -867,10 +868,8 @@ static void set_multicast_list(struct net_device *dev)
 
 static int ltpc_poll_counter;
 
-static void ltpc_poll(unsigned long l)
+static void ltpc_poll(struct timer_list *unused)
 {
-	struct net_device *dev = (struct net_device *) l;
-
 	del_timer(&ltpc_timer);
 
 	if(debug & DEBUG_VERBOSE) {
@@ -880,14 +879,10 @@ static void ltpc_poll(unsigned long l)
 		}
 		ltpc_poll_counter--;
 	}
-  
-	if (!dev)
-		return;  /* we've been downed */
 
 	/* poll 20 times per second */
-	idle(dev);
+	idle(ltpc_timer_dev);
 	ltpc_timer.expires = jiffies + HZ/20;
-	
 	add_timer(&ltpc_timer);
 }
 
@@ -1165,9 +1160,8 @@ struct net_device * __init ltpc_probe(void)
 		dev->irq = 0;
 		/* polled mode -- 20 times per second */
 		/* this is really, really slow... should it poll more often? */
-		init_timer(&ltpc_timer);
-		ltpc_timer.function=ltpc_poll;
-		ltpc_timer.data = (unsigned long) dev;
+		ltpc_timer_dev = dev;
+		timer_setup(&ltpc_timer, ltpc_poll, 0);
 
 		ltpc_timer.expires = jiffies + HZ/20;
 		add_timer(&ltpc_timer);
@@ -1254,8 +1248,6 @@ static void __exit ltpc_cleanup(void)
 	if(debug & DEBUG_VERBOSE) printk("unregister_netdev\n");
 	unregister_netdev(dev_ltpc);
 
-	ltpc_timer.data = 0;  /* signal the poll routine that we're done */
-
 	del_timer_sync(&ltpc_timer);
 
 	if(debug & DEBUG_VERBOSE) printk("freeing irq\n");
diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c
index fcfccbb3d9a2..8459115d9d4e 100644
--- a/drivers/net/arcnet/arcnet.c
+++ b/drivers/net/arcnet/arcnet.c
@@ -382,9 +382,10 @@ static void arcdev_setup(struct net_device *dev)
 	dev->flags = IFF_BROADCAST;
 }
 
-static void arcnet_timer(unsigned long data)
+static void arcnet_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
+	struct arcnet_local *lp = from_timer(lp, t, timer);
+	struct net_device *dev = lp->dev;
 
 	if (!netif_carrier_ok(dev)) {
 		netif_carrier_on(dev);
@@ -450,9 +451,7 @@ struct net_device *alloc_arcdev(const char *name)
 
 		lp->dev = dev;
 		spin_lock_init(&lp->lock);
-		init_timer(&lp->timer);
-		lp->timer.data = (unsigned long) dev;
-		lp->timer.function = arcnet_timer;
+		timer_setup(&lp->timer, arcnet_timer, 0);
 	}
 
 	return dev;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index c99dc59d729b..18b58e1376f1 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1217,25 +1217,21 @@ static enum netdev_lag_tx_type bond_lag_tx_type(struct bonding *bond)
 	}
 }
 
-static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave)
+static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave,
+				      struct netlink_ext_ack *extack)
 {
 	struct netdev_lag_upper_info lag_upper_info;
-	int err;
 
 	lag_upper_info.tx_type = bond_lag_tx_type(bond);
-	err = netdev_master_upper_dev_link(slave->dev, bond->dev, slave,
-					   &lag_upper_info);
-	if (err)
-		return err;
-	rtmsg_ifinfo(RTM_NEWLINK, slave->dev, IFF_SLAVE, GFP_KERNEL);
-	return 0;
+
+	return netdev_master_upper_dev_link(slave->dev, bond->dev, slave,
+					    &lag_upper_info, extack);
 }
 
 static void bond_upper_dev_unlink(struct bonding *bond, struct slave *slave)
 {
 	netdev_upper_dev_unlink(slave->dev, bond->dev);
 	slave->dev->flags &= ~IFF_SLAVE;
-	rtmsg_ifinfo(RTM_NEWLINK, slave->dev, IFF_SLAVE, GFP_KERNEL);
 }
 
 static struct slave *bond_alloc_slave(struct bonding *bond)
@@ -1328,7 +1324,8 @@ void bond_lower_state_changed(struct slave *slave)
 }
 
 /* enslave device <slave> to bond device <master> */
-int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
+int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
+		 struct netlink_ext_ack *extack)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
@@ -1346,12 +1343,14 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 
 	/* already in-use? */
 	if (netdev_is_rx_handler_busy(slave_dev)) {
+		NL_SET_ERR_MSG(extack, "Device is in use and cannot be enslaved");
 		netdev_err(bond_dev,
 			   "Error: Device is in use and cannot be enslaved\n");
 		return -EBUSY;
 	}
 
 	if (bond_dev == slave_dev) {
+		NL_SET_ERR_MSG(extack, "Cannot enslave bond to itself.");
 		netdev_err(bond_dev, "cannot enslave bond to itself.\n");
 		return -EPERM;
 	}
@@ -1362,6 +1361,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		netdev_dbg(bond_dev, "%s is NETIF_F_VLAN_CHALLENGED\n",
 			   slave_dev->name);
 		if (vlan_uses_dev(bond_dev)) {
+			NL_SET_ERR_MSG(extack, "Can not enslave VLAN challenged device to VLAN enabled bond");
 			netdev_err(bond_dev, "Error: cannot enslave VLAN challenged slave %s on VLAN enabled bond %s\n",
 				   slave_dev->name, bond_dev->name);
 			return -EPERM;
@@ -1381,6 +1381,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	 * enslaving it; the old ifenslave will not.
 	 */
 	if (slave_dev->flags & IFF_UP) {
+		NL_SET_ERR_MSG(extack, "Device can not be enslaved while up");
 		netdev_err(bond_dev, "%s is up - this may be due to an out of date ifenslave\n",
 			   slave_dev->name);
 		return -EPERM;
@@ -1421,6 +1422,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 						 bond_dev);
 		}
 	} else if (bond_dev->type != slave_dev->type) {
+		NL_SET_ERR_MSG(extack, "Device type is different from other slaves");
 		netdev_err(bond_dev, "%s ether type (%d) is different from other slaves (%d), can not enslave it\n",
 			   slave_dev->name, slave_dev->type, bond_dev->type);
 		return -EINVAL;
@@ -1428,6 +1430,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 
 	if (slave_dev->type == ARPHRD_INFINIBAND &&
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
+		NL_SET_ERR_MSG(extack, "Only active-backup mode is supported for infiniband slaves");
 		netdev_warn(bond_dev, "Type (%d) supports only active-backup mode\n",
 			    slave_dev->type);
 		res = -EOPNOTSUPP;
@@ -1443,6 +1446,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 				bond->params.fail_over_mac = BOND_FOM_ACTIVE;
 				netdev_warn(bond_dev, "Setting fail_over_mac to active for active-backup mode\n");
 			} else {
+				NL_SET_ERR_MSG(extack, "Slave device does not support setting the MAC address, but fail_over_mac is not set to active");
 				netdev_err(bond_dev, "The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active\n");
 				res = -EOPNOTSUPP;
 				goto err_undo_flags;
@@ -1709,7 +1713,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		goto err_detach;
 	}
 
-	res = bond_master_upper_dev_link(bond, new_slave);
+	res = bond_master_upper_dev_link(bond, new_slave, extack);
 	if (res) {
 		netdev_dbg(bond_dev, "Error %d calling bond_master_upper_dev_link\n", res);
 		goto err_unregister;
@@ -2491,7 +2495,8 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 	struct slave *curr_active_slave, *curr_arp_slave;
 	unsigned char *arp_ptr;
 	__be32 sip, tip;
-	int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
+	int is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
+	unsigned int alen;
 
 	if (!slave_do_arp_validate(bond, slave)) {
 		if ((slave_do_arp_validate_only(bond) && is_arp) ||
@@ -3072,7 +3077,16 @@ static int bond_slave_netdev_event(unsigned long event,
 		break;
 	case NETDEV_UP:
 	case NETDEV_CHANGE:
-		bond_update_speed_duplex(slave);
+		/* For 802.3ad mode only:
+		 * Getting invalid Speed/Duplex values here will put slave
+		 * in weird state. So mark it as link-down for the time
+		 * being and let link-monitoring (miimon) set it right when
+		 * correct speeds/duplex are available.
+		 */
+		if (bond_update_speed_duplex(slave) &&
+		    BOND_MODE(bond) == BOND_MODE_8023AD)
+			slave->link = BOND_LINK_DOWN;
+
 		if (BOND_MODE(bond) == BOND_MODE_8023AD)
 			bond_3ad_adapter_speed_duplex_changed(slave);
 		/* Fallthrough */
@@ -3482,7 +3496,7 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 	switch (cmd) {
 	case BOND_ENSLAVE_OLD:
 	case SIOCBONDENSLAVE:
-		res = bond_enslave(bond_dev, slave_dev);
+		res = bond_enslave(bond_dev, slave_dev, NULL);
 		break;
 	case BOND_RELEASE_OLD:
 	case SIOCBONDRELEASE:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 5931aa2fe997..8a9b085c2a98 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1383,7 +1383,7 @@ static int bond_option_slaves_set(struct bonding *bond,
 	switch (command[0]) {
 	case '+':
 		netdev_dbg(bond->dev, "Adding slave %s\n", dev->name);
-		ret = bond_enslave(bond->dev, dev);
+		ret = bond_enslave(bond->dev, dev, NULL);
 		break;
 
 	case '-':
diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c
index 438966bf51c2..fed75e75207a 100644
--- a/drivers/net/caif/caif_hsi.c
+++ b/drivers/net/caif/caif_hsi.c
@@ -1211,17 +1211,14 @@ static int cfhsi_open(struct net_device *ndev)
 	init_waitqueue_head(&cfhsi->flush_fifo_wait);
 
 	/* Setup the inactivity timer. */
-	init_timer(&cfhsi->inactivity_timer);
-	cfhsi->inactivity_timer.data = (unsigned long)cfhsi;
-	cfhsi->inactivity_timer.function = cfhsi_inactivity_tout;
+	setup_timer(&cfhsi->inactivity_timer, cfhsi_inactivity_tout,
+		    (unsigned long)cfhsi);
 	/* Setup the slowpath RX timer. */
-	init_timer(&cfhsi->rx_slowpath_timer);
-	cfhsi->rx_slowpath_timer.data = (unsigned long)cfhsi;
-	cfhsi->rx_slowpath_timer.function = cfhsi_rx_slowpath;
+	setup_timer(&cfhsi->rx_slowpath_timer, cfhsi_rx_slowpath,
+		    (unsigned long)cfhsi);
 	/* Setup the aggregation timer. */
-	init_timer(&cfhsi->aggregation_timer);
-	cfhsi->aggregation_timer.data = (unsigned long)cfhsi;
-	cfhsi->aggregation_timer.function = cfhsi_aggregation_tout;
+	setup_timer(&cfhsi->aggregation_timer, cfhsi_aggregation_tout,
+		    (unsigned long)cfhsi);
 
 	/* Activate HSI interface. */
 	res = cfhsi->ops->cfhsi_up(cfhsi->ops);
diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c
index a7be12d9a139..897c6b113d3f 100644
--- a/drivers/net/can/grcan.c
+++ b/drivers/net/can/grcan.c
@@ -807,10 +807,10 @@ static irqreturn_t grcan_interrupt(int irq, void *dev_id)
  * is not ONGOING (TX might be stuck in ONGOING due to a harwrware bug
  * for single shot)
  */
-static void grcan_running_reset(unsigned long data)
+static void grcan_running_reset(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct grcan_priv *priv = netdev_priv(dev);
+	struct grcan_priv *priv = from_timer(priv, t, rr_timer);
+	struct net_device *dev = priv->dev;
 	struct grcan_registers __iomem *regs = priv->regs;
 	unsigned long flags;
 
@@ -898,10 +898,10 @@ static inline void grcan_reset_timer(struct timer_list *timer, __u32 bitrate)
 }
 
 /* Disable channels and schedule a running reset */
-static void grcan_initiate_running_reset(unsigned long data)
+static void grcan_initiate_running_reset(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct grcan_priv *priv = netdev_priv(dev);
+	struct grcan_priv *priv = from_timer(priv, t, hang_timer);
+	struct net_device *dev = priv->dev;
 	struct grcan_registers __iomem *regs = priv->regs;
 	unsigned long flags;
 
@@ -1626,13 +1626,8 @@ static int grcan_setup_netdev(struct platform_device *ofdev,
 	spin_lock_init(&priv->lock);
 
 	if (priv->need_txbug_workaround) {
-		init_timer(&priv->rr_timer);
-		priv->rr_timer.function = grcan_running_reset;
-		priv->rr_timer.data = (unsigned long)dev;
-
-		init_timer(&priv->hang_timer);
-		priv->hang_timer.function = grcan_initiate_running_reset;
-		priv->hang_timer.data = (unsigned long)dev;
+		timer_setup(&priv->rr_timer, grcan_running_reset, 0);
+		timer_setup(&priv->hang_timer, grcan_initiate_running_reset, 0);
 	}
 
 	netif_napi_add(dev, &priv->napi, grcan_poll, GRCAN_NAPI_WEIGHT);
diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c
index dd56133cc461..485b19c9ae47 100644
--- a/drivers/net/can/sja1000/peak_pcmcia.c
+++ b/drivers/net/can/sja1000/peak_pcmcia.c
@@ -381,9 +381,9 @@ static inline void pcan_set_can_power(struct pcan_pccard *card, int onoff)
 /*
  * set leds state according to channel activity
  */
-static void pcan_led_timer(unsigned long arg)
+static void pcan_led_timer(struct timer_list *t)
 {
-	struct pcan_pccard *card = (struct pcan_pccard *)arg;
+	struct pcan_pccard *card = from_timer(card, t, led_timer);
 	struct net_device *netdev;
 	int i, up_count = 0;
 	u8 ccr;
@@ -692,9 +692,7 @@ static int pcan_probe(struct pcmcia_device *pdev)
 	}
 
 	/* init the timer which controls the leds */
-	init_timer(&card->led_timer);
-	card->led_timer.function = pcan_led_timer;
-	card->led_timer.data = (unsigned long)card;
+	timer_setup(&card->led_timer, pcan_led_timer, 0);
 
 	/* request the given irq */
 	err = request_irq(pdev->irq, &pcan_isr, IRQF_SHARED, PCC_NAME, card);
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 838545ce468d..25a9b79cc42d 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -259,10 +259,13 @@ static int pcan_usb_write_mode(struct peak_usb_device *dev, u8 onoff)
 /*
  * handle end of waiting for the device to reset
  */
-static void pcan_usb_restart(unsigned long arg)
+static void pcan_usb_restart(struct timer_list *t)
 {
+	struct pcan_usb *pdev = from_timer(pdev, t, restart_timer);
+	struct peak_usb_device *dev = &pdev->dev;
+
 	/* notify candev and netdev */
-	peak_usb_restart_complete((struct peak_usb_device *)arg);
+	peak_usb_restart_complete(dev);
 }
 
 /*
@@ -798,9 +801,7 @@ static int pcan_usb_init(struct peak_usb_device *dev)
 	int err;
 
 	/* initialize a timer needed to wait for hardware restart */
-	init_timer(&pdev->restart_timer);
-	pdev->restart_timer.function = pcan_usb_restart;
-	pdev->restart_timer.data = (unsigned long)dev;
+	timer_setup(&pdev->restart_timer, pcan_usb_restart, 0);
 
 	/*
 	 * explicit use of dev_xxx() instead of netdev_xxx() here:
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 274f3679f33d..a7ca62ba27b7 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -484,7 +484,7 @@ static int b53_fast_age_vlan(struct b53_device *dev, u16 vid)
 	return b53_flush_arl(dev, FAST_AGE_VLAN);
 }
 
-static void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
+void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
 {
 	struct b53_device *dev = ds->priv;
 	unsigned int i;
@@ -500,9 +500,9 @@ static void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
 		b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), pvlan);
 	}
 }
+EXPORT_SYMBOL(b53_imp_vlan_setup);
 
-static int b53_enable_port(struct dsa_switch *ds, int port,
-			   struct phy_device *phy)
+int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 {
 	struct b53_device *dev = ds->priv;
 	unsigned int cpu_port = dev->cpu_port;
@@ -523,11 +523,15 @@ static int b53_enable_port(struct dsa_switch *ds, int port,
 
 	b53_imp_vlan_setup(ds, cpu_port);
 
+	/* If EEE was enabled, restore it */
+	if (dev->ports[port].eee.eee_enabled)
+		b53_eee_enable_set(ds, port, true);
+
 	return 0;
 }
+EXPORT_SYMBOL(b53_enable_port);
 
-static void b53_disable_port(struct dsa_switch *ds, int port,
-			     struct phy_device *phy)
+void b53_disable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 {
 	struct b53_device *dev = ds->priv;
 	u8 reg;
@@ -537,20 +541,77 @@ static void b53_disable_port(struct dsa_switch *ds, int port,
 	reg |= PORT_CTRL_RX_DISABLE | PORT_CTRL_TX_DISABLE;
 	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), reg);
 }
+EXPORT_SYMBOL(b53_disable_port);
 
-static void b53_enable_cpu_port(struct b53_device *dev)
+void b53_brcm_hdr_setup(struct dsa_switch *ds, int port)
+{
+	bool tag_en = !!(ds->ops->get_tag_protocol(ds) == DSA_TAG_PROTO_BRCM);
+	struct b53_device *dev = ds->priv;
+	u8 hdr_ctl, val;
+	u16 reg;
+
+	/* Resolve which bit controls the Broadcom tag */
+	switch (port) {
+	case 8:
+		val = BRCM_HDR_P8_EN;
+		break;
+	case 7:
+		val = BRCM_HDR_P7_EN;
+		break;
+	case 5:
+		val = BRCM_HDR_P5_EN;
+		break;
+	default:
+		val = 0;
+		break;
+	}
+
+	/* Enable Broadcom tags for IMP port */
+	b53_read8(dev, B53_MGMT_PAGE, B53_BRCM_HDR, &hdr_ctl);
+	if (tag_en)
+		hdr_ctl |= val;
+	else
+		hdr_ctl &= ~val;
+	b53_write8(dev, B53_MGMT_PAGE, B53_BRCM_HDR, hdr_ctl);
+
+	/* Registers below are only accessible on newer devices */
+	if (!is58xx(dev))
+		return;
+
+	/* Enable reception Broadcom tag for CPU TX (switch RX) to
+	 * allow us to tag outgoing frames
+	 */
+	b53_read16(dev, B53_MGMT_PAGE, B53_BRCM_HDR_RX_DIS, &reg);
+	if (tag_en)
+		reg &= ~BIT(port);
+	else
+		reg |= BIT(port);
+	b53_write16(dev, B53_MGMT_PAGE, B53_BRCM_HDR_RX_DIS, reg);
+
+	/* Enable transmission of Broadcom tags from the switch (CPU RX) to
+	 * allow delivering frames to the per-port net_devices
+	 */
+	b53_read16(dev, B53_MGMT_PAGE, B53_BRCM_HDR_TX_DIS, &reg);
+	if (tag_en)
+		reg &= ~BIT(port);
+	else
+		reg |= BIT(port);
+	b53_write16(dev, B53_MGMT_PAGE, B53_BRCM_HDR_TX_DIS, reg);
+}
+EXPORT_SYMBOL(b53_brcm_hdr_setup);
+
+static void b53_enable_cpu_port(struct b53_device *dev, int port)
 {
-	unsigned int cpu_port = dev->cpu_port;
 	u8 port_ctrl;
 
 	/* BCM5325 CPU port is at 8 */
-	if ((is5325(dev) || is5365(dev)) && cpu_port == B53_CPU_PORT_25)
-		cpu_port = B53_CPU_PORT;
+	if ((is5325(dev) || is5365(dev)) && port == B53_CPU_PORT_25)
+		port = B53_CPU_PORT;
 
 	port_ctrl = PORT_CTRL_RX_BCST_EN |
 		    PORT_CTRL_RX_MCST_EN |
 		    PORT_CTRL_RX_UCST_EN;
-	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(cpu_port), port_ctrl);
+	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), port_ctrl);
 }
 
 static void b53_enable_mib(struct b53_device *dev)
@@ -562,8 +623,9 @@ static void b53_enable_mib(struct b53_device *dev)
 	b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc);
 }
 
-static int b53_configure_vlan(struct b53_device *dev)
+int b53_configure_vlan(struct dsa_switch *ds)
 {
+	struct b53_device *dev = ds->priv;
 	struct b53_vlan vl = { 0 };
 	int i;
 
@@ -586,6 +648,7 @@ static int b53_configure_vlan(struct b53_device *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL(b53_configure_vlan);
 
 static void b53_switch_reset_gpio(struct b53_device *dev)
 {
@@ -700,7 +763,7 @@ static int b53_apply_config(struct b53_device *priv)
 	/* disable switching */
 	b53_set_forwarding(priv, 0);
 
-	b53_configure_vlan(priv);
+	b53_configure_vlan(priv->ds);
 
 	/* enable switching */
 	b53_set_forwarding(priv, 1);
@@ -816,12 +879,13 @@ static int b53_setup(struct dsa_switch *ds)
 	if (ret)
 		dev_err(ds->dev, "failed to apply configuration\n");
 
+	/* Configure IMP/CPU port, disable unused ports. Enabled
+	 * ports will be configured with .port_enable
+	 */
 	for (port = 0; port < dev->num_ports; port++) {
-		if (BIT(port) & ds->enabled_port_mask)
-			b53_enable_port(ds, port, NULL);
-		else if (dsa_is_cpu_port(ds, port))
-			b53_enable_cpu_port(dev);
-		else
+		if (dsa_is_cpu_port(ds, port))
+			b53_enable_cpu_port(dev, port);
+		else if (dsa_is_unused_port(ds, port))
 			b53_disable_port(ds, port, NULL);
 	}
 
@@ -832,6 +896,7 @@ static void b53_adjust_link(struct dsa_switch *ds, int port,
 			    struct phy_device *phydev)
 {
 	struct b53_device *dev = ds->priv;
+	struct ethtool_eee *p = &dev->ports[port].eee;
 	u8 rgmii_ctrl = 0, reg = 0, off;
 
 	if (!phy_is_pseudo_fixed_link(phydev))
@@ -953,6 +1018,9 @@ static void b53_adjust_link(struct dsa_switch *ds, int port,
 			b53_write8(dev, B53_CTRL_PAGE, po_reg, gmii_po);
 		}
 	}
+
+	/* Re-negotiate EEE if it was enabled already */
+	p->eee_enabled = b53_eee_init(ds, port, phydev);
 }
 
 int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
@@ -1280,7 +1348,7 @@ EXPORT_SYMBOL(b53_fdb_dump);
 int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br)
 {
 	struct b53_device *dev = ds->priv;
-	s8 cpu_port = ds->dst->cpu_dp->index;
+	s8 cpu_port = ds->ports[port].cpu_dp->index;
 	u16 pvlan, reg;
 	unsigned int i;
 
@@ -1298,7 +1366,7 @@ int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br)
 	b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan);
 
 	b53_for_each_port(dev, i) {
-		if (ds->ports[i].bridge_dev != br)
+		if (dsa_to_port(ds, i)->bridge_dev != br)
 			continue;
 
 		/* Add this local port to the remote port VLAN control
@@ -1326,7 +1394,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br)
 {
 	struct b53_device *dev = ds->priv;
 	struct b53_vlan *vl = &dev->vlans[0];
-	s8 cpu_port = ds->dst->cpu_dp->index;
+	s8 cpu_port = ds->ports[port].cpu_dp->index;
 	unsigned int i;
 	u16 pvlan, reg, pvid;
 
@@ -1334,7 +1402,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br)
 
 	b53_for_each_port(dev, i) {
 		/* Don't touch the remaining ports */
-		if (ds->ports[i].bridge_dev != br)
+		if (dsa_to_port(ds, i)->bridge_dev != br)
 			continue;
 
 		b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), &reg);
@@ -1484,6 +1552,69 @@ void b53_mirror_del(struct dsa_switch *ds, int port,
 }
 EXPORT_SYMBOL(b53_mirror_del);
 
+void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable)
+{
+	struct b53_device *dev = ds->priv;
+	u16 reg;
+
+	b53_read16(dev, B53_EEE_PAGE, B53_EEE_EN_CTRL, &reg);
+	if (enable)
+		reg |= BIT(port);
+	else
+		reg &= ~BIT(port);
+	b53_write16(dev, B53_EEE_PAGE, B53_EEE_EN_CTRL, reg);
+}
+EXPORT_SYMBOL(b53_eee_enable_set);
+
+
+/* Returns 0 if EEE was not enabled, or 1 otherwise
+ */
+int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy)
+{
+	int ret;
+
+	ret = phy_init_eee(phy, 0);
+	if (ret)
+		return 0;
+
+	b53_eee_enable_set(ds, port, true);
+
+	return 1;
+}
+EXPORT_SYMBOL(b53_eee_init);
+
+int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e)
+{
+	struct b53_device *dev = ds->priv;
+	struct ethtool_eee *p = &dev->ports[port].eee;
+	u16 reg;
+
+	if (is5325(dev) || is5365(dev))
+		return -EOPNOTSUPP;
+
+	b53_read16(dev, B53_EEE_PAGE, B53_EEE_LPI_INDICATE, &reg);
+	e->eee_enabled = p->eee_enabled;
+	e->eee_active = !!(reg & BIT(port));
+
+	return 0;
+}
+EXPORT_SYMBOL(b53_get_mac_eee);
+
+int b53_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e)
+{
+	struct b53_device *dev = ds->priv;
+	struct ethtool_eee *p = &dev->ports[port].eee;
+
+	if (is5325(dev) || is5365(dev))
+		return -EOPNOTSUPP;
+
+	p->eee_enabled = e->eee_enabled;
+	b53_eee_enable_set(ds, port, e->eee_enabled);
+
+	return 0;
+}
+EXPORT_SYMBOL(b53_set_mac_eee);
+
 static const struct dsa_switch_ops b53_switch_ops = {
 	.get_tag_protocol	= b53_get_tag_protocol,
 	.setup			= b53_setup,
@@ -1495,6 +1626,8 @@ static const struct dsa_switch_ops b53_switch_ops = {
 	.adjust_link		= b53_adjust_link,
 	.port_enable		= b53_enable_port,
 	.port_disable		= b53_disable_port,
+	.get_mac_eee		= b53_get_mac_eee,
+	.set_mac_eee		= b53_set_mac_eee,
 	.port_bridge_join	= b53_br_join,
 	.port_bridge_leave	= b53_br_leave,
 	.port_stp_state_set	= b53_br_set_stp_state,
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 01bd8cbe9a3f..daaaa1ecb996 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -70,6 +70,7 @@ enum {
 
 struct b53_port {
 	u16		vlan_ctl_mask;
+	struct ethtool_eee eee;
 };
 
 struct b53_vlan {
@@ -186,11 +187,6 @@ static inline int is58xx(struct b53_device *dev)
 #define B53_CPU_PORT_25	5
 #define B53_CPU_PORT	8
 
-static inline int is_cpu_port(struct b53_device *dev, int port)
-{
-	return dev->cpu_port;
-}
-
 struct b53_device *b53_switch_alloc(struct device *base,
 				    const struct b53_io_ops *ops,
 				    void *priv);
@@ -204,119 +200,30 @@ static inline void b53_switch_remove(struct b53_device *dev)
 	dsa_unregister_switch(dev->ds);
 }
 
-static inline int b53_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->read8(dev, page, reg, val);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
+#define b53_build_op(type_op_size, val_type)				\
+static inline int b53_##type_op_size(struct b53_device *dev, u8 page,	\
+				     u8 reg, val_type val)		\
+{									\
+	int ret;							\
+									\
+	mutex_lock(&dev->reg_mutex);					\
+	ret = dev->ops->type_op_size(dev, page, reg, val);		\
+	mutex_unlock(&dev->reg_mutex);					\
+									\
+	return ret;							\
 }
 
-static inline int b53_read16(struct b53_device *dev, u8 page, u8 reg, u16 *val)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->read16(dev, page, reg, val);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int b53_read32(struct b53_device *dev, u8 page, u8 reg, u32 *val)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->read32(dev, page, reg, val);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int b53_read48(struct b53_device *dev, u8 page, u8 reg, u64 *val)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->read48(dev, page, reg, val);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int b53_read64(struct b53_device *dev, u8 page, u8 reg, u64 *val)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->read64(dev, page, reg, val);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
+b53_build_op(read8, u8 *);
+b53_build_op(read16, u16 *);
+b53_build_op(read32, u32 *);
+b53_build_op(read48, u64 *);
+b53_build_op(read64, u64 *);
 
-static inline int b53_write8(struct b53_device *dev, u8 page, u8 reg, u8 value)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->write8(dev, page, reg, value);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int b53_write16(struct b53_device *dev, u8 page, u8 reg,
-			      u16 value)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->write16(dev, page, reg, value);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int b53_write32(struct b53_device *dev, u8 page, u8 reg,
-			      u32 value)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->write32(dev, page, reg, value);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int b53_write48(struct b53_device *dev, u8 page, u8 reg,
-			      u64 value)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->write48(dev, page, reg, value);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
-
-static inline int b53_write64(struct b53_device *dev, u8 page, u8 reg,
-			       u64 value)
-{
-	int ret;
-
-	mutex_lock(&dev->reg_mutex);
-	ret = dev->ops->write64(dev, page, reg, value);
-	mutex_unlock(&dev->reg_mutex);
-
-	return ret;
-}
+b53_build_op(write8, u8);
+b53_build_op(write16, u16);
+b53_build_op(write32, u32);
+b53_build_op(write48, u64);
+b53_build_op(write64, u64);
 
 struct b53_arl_entry {
 	u8 port;
@@ -377,6 +284,8 @@ static inline int b53_switch_get_reset_gpio(struct b53_device *dev)
 #endif
 
 /* Exported functions towards other drivers */
+void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port);
+int b53_configure_vlan(struct dsa_switch *ds);
 void b53_get_strings(struct dsa_switch *ds, int port, uint8_t *data);
 void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data);
 int b53_get_sset_count(struct dsa_switch *ds);
@@ -403,5 +312,12 @@ int b53_mirror_add(struct dsa_switch *ds, int port,
 		   struct dsa_mall_mirror_tc_entry *mirror, bool ingress);
 void b53_mirror_del(struct dsa_switch *ds, int port,
 		    struct dsa_mall_mirror_tc_entry *mirror);
+int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy);
+void b53_disable_port(struct dsa_switch *ds, int port, struct phy_device *phy);
+void b53_brcm_hdr_setup(struct dsa_switch *ds, int port);
+void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable);
+int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy);
+int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e);
+int b53_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e);
 
 #endif
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index e5c86d44667a..2a9f421680aa 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -50,6 +50,9 @@
 /* Jumbo Frame Registers */
 #define B53_JUMBO_PAGE			0x40
 
+/* EEE Control Registers Page */
+#define B53_EEE_PAGE			0x92
+
 /* CFP Configuration Registers Page */
 #define B53_CFP_PAGE			0xa1
 
@@ -210,6 +213,7 @@
 #define B53_BRCM_HDR			0x03
 #define   BRCM_HDR_P8_EN		BIT(0) /* Enable tagging on port 8 */
 #define   BRCM_HDR_P5_EN		BIT(1) /* Enable tagging on port 5 */
+#define   BRCM_HDR_P7_EN		BIT(2) /* Enable tagging on port 7 */
 
 /* Mirror capture control register (16 bit) */
 #define B53_MIR_CAP_CTL			0x10
@@ -249,6 +253,12 @@
 /* Revision ID register (8 bit) */
 #define B53_REV_ID			0x40
 
+/* Broadcom header RX control (16 bit) */
+#define B53_BRCM_HDR_RX_DIS		0x60
+
+/* Broadcom header TX control (16 bit)	*/
+#define B53_BRCM_HDR_TX_DIS		0x62
+
 /*************************************************************************
  * ARL Access Page Registers
  *************************************************************************/
@@ -465,6 +475,44 @@
 #define   JMS_MAX_SIZE			9724
 
 /*************************************************************************
+ * EEE Configuration Page Registers
+ *************************************************************************/
+
+/* EEE Enable control register (16 bit) */
+#define B53_EEE_EN_CTRL			0x00
+
+/* EEE LPI assert status register (16 bit) */
+#define B53_EEE_LPI_ASSERT_STS		0x02
+
+/* EEE LPI indicate status register (16 bit) */
+#define B53_EEE_LPI_INDICATE		0x4
+
+/* EEE Receiving idle symbols status register (16 bit) */
+#define B53_EEE_RX_IDLE_SYM_STS		0x6
+
+/* EEE Pipeline timer register (32 bit) */
+#define B53_EEE_PIP_TIMER		0xC
+
+/* EEE Sleep timer Gig register (32 bit) */
+#define B53_EEE_SLEEP_TIMER_GIG(i)	(0x10 + 4 * (i))
+
+/* EEE Sleep timer FE register (32 bit) */
+#define B53_EEE_SLEEP_TIMER_FE(i)	(0x34 + 4 * (i))
+
+/* EEE Minimum LP timer Gig register (32 bit) */
+#define B53_EEE_MIN_LP_TIMER_GIG(i)	(0x58 + 4 * (i))
+
+/* EEE Minimum LP timer FE register (32 bit) */
+#define B53_EEE_MIN_LP_TIMER_FE(i)	(0x7c + 4 * (i))
+
+/* EEE Wake timer Gig register (16 bit) */
+#define B53_EEE_WAKE_TIMER_GIG(i)	(0xa0 + 2 * (i))
+
+/* EEE Wake timer FE register (16 bit) */
+#define B53_EEE_WAKE_TIMER_FE(i)	(0xb2 + 2 * (i))
+
+
+/*************************************************************************
  * CFP Configuration Page Registers
  *************************************************************************/
 
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index d7b53d53c116..2d6867f4008c 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -40,66 +40,6 @@ static enum dsa_tag_protocol bcm_sf2_sw_get_tag_protocol(struct dsa_switch *ds)
 	return DSA_TAG_PROTO_BRCM;
 }
 
-static void bcm_sf2_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
-{
-	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
-	unsigned int i;
-	u32 reg;
-
-	/* Enable the IMP Port to be in the same VLAN as the other ports
-	 * on a per-port basis such that we only have Port i and IMP in
-	 * the same VLAN.
-	 */
-	for (i = 0; i < priv->hw_params.num_ports; i++) {
-		if (!((1 << i) & ds->enabled_port_mask))
-			continue;
-
-		reg = core_readl(priv, CORE_PORT_VLAN_CTL_PORT(i));
-		reg |= (1 << cpu_port);
-		core_writel(priv, reg, CORE_PORT_VLAN_CTL_PORT(i));
-	}
-}
-
-static void bcm_sf2_brcm_hdr_setup(struct bcm_sf2_priv *priv, int port)
-{
-	u32 reg, val;
-
-	/* Resolve which bit controls the Broadcom tag */
-	switch (port) {
-	case 8:
-		val = BRCM_HDR_EN_P8;
-		break;
-	case 7:
-		val = BRCM_HDR_EN_P7;
-		break;
-	case 5:
-		val = BRCM_HDR_EN_P5;
-		break;
-	default:
-		val = 0;
-		break;
-	}
-
-	/* Enable Broadcom tags for IMP port */
-	reg = core_readl(priv, CORE_BRCM_HDR_CTRL);
-	reg |= val;
-	core_writel(priv, reg, CORE_BRCM_HDR_CTRL);
-
-	/* Enable reception Broadcom tag for CPU TX (switch RX) to
-	 * allow us to tag outgoing frames
-	 */
-	reg = core_readl(priv, CORE_BRCM_HDR_RX_DIS);
-	reg &= ~(1 << port);
-	core_writel(priv, reg, CORE_BRCM_HDR_RX_DIS);
-
-	/* Enable transmission of Broadcom tags from the switch (CPU RX) to
-	 * allow delivering frames to the per-port net_devices
-	 */
-	reg = core_readl(priv, CORE_BRCM_HDR_TX_DIS);
-	reg &= ~(1 << port);
-	core_writel(priv, reg, CORE_BRCM_HDR_TX_DIS);
-}
-
 static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
@@ -138,7 +78,7 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 		reg |= i << (PRT_TO_QID_SHIFT * i);
 	core_writel(priv, reg, CORE_PORT_TC2_QOS_MAP_PORT(port));
 
-	bcm_sf2_brcm_hdr_setup(priv, port);
+	b53_brcm_hdr_setup(ds, port);
 
 	/* Force link status for IMP port */
 	reg = core_readl(priv, offset);
@@ -146,19 +86,6 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 	core_writel(priv, reg, offset);
 }
 
-static void bcm_sf2_eee_enable_set(struct dsa_switch *ds, int port, bool enable)
-{
-	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
-	u32 reg;
-
-	reg = core_readl(priv, CORE_EEE_EN_CTRL);
-	if (enable)
-		reg |= 1 << port;
-	else
-		reg &= ~(1 << port);
-	core_writel(priv, reg, CORE_EEE_EN_CTRL);
-}
-
 static void bcm_sf2_gphy_enable_set(struct dsa_switch *ds, bool enable)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
@@ -236,7 +163,6 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
 			      struct phy_device *phy)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
-	s8 cpu_port = ds->dst->cpu_dp->index;
 	unsigned int i;
 	u32 reg;
 
@@ -247,7 +173,7 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
 
 	/* Enable Broadcom tags for that port if requested */
 	if (priv->brcm_tag_mask & BIT(port))
-		bcm_sf2_brcm_hdr_setup(priv, port);
+		b53_brcm_hdr_setup(ds, port);
 
 	/* Configure Traffic Class to QoS mapping, allow each priority to map
 	 * to a different queue number
@@ -257,9 +183,6 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
 		reg |= i << (PRT_TO_QID_SHIFT * i);
 	core_writel(priv, reg, CORE_PORT_TC2_QOS_MAP_PORT(port));
 
-	/* Clear the Rx and Tx disable bits and set to no spanning tree */
-	core_writel(priv, 0, CORE_G_PCTL_PORT(port));
-
 	/* Re-enable the GPHY and re-apply workarounds */
 	if (priv->int_phy_mask & 1 << port && priv->hw_params.num_gphy == 1) {
 		bcm_sf2_gphy_enable_set(ds, true);
@@ -282,23 +205,20 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
 	if (port == priv->moca_port)
 		bcm_sf2_port_intr_enable(priv, port);
 
-	/* Set this port, and only this one to be in the default VLAN,
-	 * if member of a bridge, restore its membership prior to
-	 * bringing down this port.
-	 */
-	reg = core_readl(priv, CORE_PORT_VLAN_CTL_PORT(port));
-	reg &= ~PORT_VLAN_CTRL_MASK;
-	reg |= (1 << port);
-	reg |= priv->dev->ports[port].vlan_ctl_mask;
-	core_writel(priv, reg, CORE_PORT_VLAN_CTL_PORT(port));
-
-	bcm_sf2_imp_vlan_setup(ds, cpu_port);
-
-	/* If EEE was enabled, restore it */
-	if (priv->port_sts[port].eee.eee_enabled)
-		bcm_sf2_eee_enable_set(ds, port, true);
+	/* Set per-queue pause threshold to 32 */
+	core_writel(priv, 32, CORE_TXQ_THD_PAUSE_QN_PORT(port));
+
+	/* Set ACB threshold to 24 */
+	for (i = 0; i < SF2_NUM_EGRESS_QUEUES; i++) {
+		reg = acb_readl(priv, ACB_QUEUE_CFG(port *
+						    SF2_NUM_EGRESS_QUEUES + i));
+		reg &= ~XOFF_THRESHOLD_MASK;
+		reg |= 24;
+		acb_writel(priv, reg, ACB_QUEUE_CFG(port *
+						    SF2_NUM_EGRESS_QUEUES + i));
+	}
 
-	return 0;
+	return b53_enable_port(ds, port, phy);
 }
 
 static void bcm_sf2_port_disable(struct dsa_switch *ds, int port,
@@ -321,9 +241,7 @@ static void bcm_sf2_port_disable(struct dsa_switch *ds, int port,
 	else
 		off = CORE_G_PCTL_PORT(port);
 
-	reg = core_readl(priv, off);
-	reg |= RX_DIS | TX_DIS;
-	core_writel(priv, reg, off);
+	b53_disable_port(ds, port, phy);
 
 	/* Power down the port memory */
 	reg = core_readl(priv, CORE_MEM_PSM_VDD_CTRL);
@@ -331,47 +249,6 @@ static void bcm_sf2_port_disable(struct dsa_switch *ds, int port,
 	core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL);
 }
 
-/* Returns 0 if EEE was not enabled, or 1 otherwise
- */
-static int bcm_sf2_eee_init(struct dsa_switch *ds, int port,
-			    struct phy_device *phy)
-{
-	int ret;
-
-	ret = phy_init_eee(phy, 0);
-	if (ret)
-		return 0;
-
-	bcm_sf2_eee_enable_set(ds, port, true);
-
-	return 1;
-}
-
-static int bcm_sf2_sw_get_mac_eee(struct dsa_switch *ds, int port,
-				  struct ethtool_eee *e)
-{
-	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
-	struct ethtool_eee *p = &priv->port_sts[port].eee;
-	u32 reg;
-
-	reg = core_readl(priv, CORE_EEE_LPI_INDICATE);
-	e->eee_enabled = p->eee_enabled;
-	e->eee_active = !!(reg & (1 << port));
-
-	return 0;
-}
-
-static int bcm_sf2_sw_set_mac_eee(struct dsa_switch *ds, int port,
-				  struct ethtool_eee *e)
-{
-	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
-	struct ethtool_eee *p = &priv->port_sts[port].eee;
-
-	p->eee_enabled = e->eee_enabled;
-	bcm_sf2_eee_enable_set(ds, port, e->eee_enabled);
-
-	return 0;
-}
 
 static int bcm_sf2_sw_indir_rw(struct bcm_sf2_priv *priv, int op, int addr,
 			       int regnum, u16 val)
@@ -606,7 +483,7 @@ static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port,
 				   struct phy_device *phydev)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
-	struct ethtool_eee *p = &priv->port_sts[port].eee;
+	struct ethtool_eee *p = &priv->dev->ports[port].eee;
 	u32 id_mode_dis = 0, port_mode;
 	const char *str = NULL;
 	u32 reg, offset;
@@ -688,7 +565,7 @@ force_link:
 	core_writel(priv, reg, offset);
 
 	if (!phydev->is_pseudo_fixed_link)
-		p->eee_enabled = bcm_sf2_eee_init(ds, port, phydev);
+		p->eee_enabled = b53_eee_init(ds, port, phydev);
 }
 
 static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
@@ -724,7 +601,7 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
 		 * state machine and make it go in PHY_FORCING state instead.
 		 */
 		if (!status->link)
-			netif_carrier_off(ds->ports[port].netdev);
+			netif_carrier_off(ds->ports[port].slave);
 		status->duplex = 1;
 	} else {
 		status->link = 1;
@@ -749,6 +626,20 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
 		status->pause = 1;
 }
 
+static void bcm_sf2_enable_acb(struct dsa_switch *ds)
+{
+	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+	u32 reg;
+
+	/* Enable ACB globally */
+	reg = acb_readl(priv, ACB_CONTROL);
+	reg |= (ACB_FLUSH_MASK << ACB_FLUSH_SHIFT);
+	acb_writel(priv, reg, ACB_CONTROL);
+	reg &= ~(ACB_FLUSH_MASK << ACB_FLUSH_SHIFT);
+	reg |= ACB_EN | ACB_ALGORITHM;
+	acb_writel(priv, reg, ACB_CONTROL);
+}
+
 static int bcm_sf2_sw_suspend(struct dsa_switch *ds)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
@@ -761,8 +652,7 @@ static int bcm_sf2_sw_suspend(struct dsa_switch *ds)
 	 * bcm_sf2_sw_setup
 	 */
 	for (port = 0; port < DSA_MAX_PORTS; port++) {
-		if ((1 << port) & ds->enabled_port_mask ||
-		    dsa_is_cpu_port(ds, port))
+		if (dsa_is_user_port(ds, port) || dsa_is_cpu_port(ds, port))
 			bcm_sf2_port_disable(ds, port, NULL);
 	}
 
@@ -785,19 +675,21 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds)
 		bcm_sf2_gphy_enable_set(ds, true);
 
 	for (port = 0; port < DSA_MAX_PORTS; port++) {
-		if ((1 << port) & ds->enabled_port_mask)
+		if (dsa_is_user_port(ds, port))
 			bcm_sf2_port_setup(ds, port, NULL);
 		else if (dsa_is_cpu_port(ds, port))
 			bcm_sf2_imp_setup(ds, port);
 	}
 
+	bcm_sf2_enable_acb(ds);
+
 	return 0;
 }
 
 static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port,
 			       struct ethtool_wolinfo *wol)
 {
-	struct net_device *p = ds->dst->cpu_dp->netdev;
+	struct net_device *p = ds->ports[port].cpu_dp->master;
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
 	struct ethtool_wolinfo pwol;
 
@@ -820,9 +712,9 @@ static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port,
 static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port,
 			      struct ethtool_wolinfo *wol)
 {
-	struct net_device *p = ds->dst->cpu_dp->netdev;
+	struct net_device *p = ds->ports[port].cpu_dp->master;
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
-	s8 cpu_port = ds->dst->cpu_dp->index;
+	s8 cpu_port = ds->ports[port].cpu_dp->index;
 	struct ethtool_wolinfo pwol;
 
 	p->ethtool_ops->get_wol(p, &pwol);
@@ -846,45 +738,6 @@ static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port,
 	return p->ethtool_ops->set_wol(p, wol);
 }
 
-static int bcm_sf2_vlan_op_wait(struct bcm_sf2_priv *priv)
-{
-	unsigned int timeout = 10;
-	u32 reg;
-
-	do {
-		reg = core_readl(priv, CORE_ARLA_VTBL_RWCTRL);
-		if (!(reg & ARLA_VTBL_STDN))
-			return 0;
-
-		usleep_range(1000, 2000);
-	} while (timeout--);
-
-	return -ETIMEDOUT;
-}
-
-static int bcm_sf2_vlan_op(struct bcm_sf2_priv *priv, u8 op)
-{
-	core_writel(priv, ARLA_VTBL_STDN | op, CORE_ARLA_VTBL_RWCTRL);
-
-	return bcm_sf2_vlan_op_wait(priv);
-}
-
-static void bcm_sf2_sw_configure_vlan(struct dsa_switch *ds)
-{
-	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
-	unsigned int port;
-
-	/* Clear all VLANs */
-	bcm_sf2_vlan_op(priv, ARLA_VTBL_CMD_CLEAR);
-
-	for (port = 0; port < priv->hw_params.num_ports; port++) {
-		if (!((1 << port) & ds->enabled_port_mask))
-			continue;
-
-		core_writel(priv, 1, CORE_DEFAULT_1Q_TAG_P(port));
-	}
-}
-
 static int bcm_sf2_sw_setup(struct dsa_switch *ds)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
@@ -893,7 +746,7 @@ static int bcm_sf2_sw_setup(struct dsa_switch *ds)
 	/* Enable all valid ports and disable those unused */
 	for (port = 0; port < priv->hw_params.num_ports; port++) {
 		/* IMP port receives special treatment */
-		if ((1 << port) & ds->enabled_port_mask)
+		if (dsa_is_user_port(ds, port))
 			bcm_sf2_port_setup(ds, port, NULL);
 		else if (dsa_is_cpu_port(ds, port))
 			bcm_sf2_imp_setup(ds, port);
@@ -901,7 +754,8 @@ static int bcm_sf2_sw_setup(struct dsa_switch *ds)
 			bcm_sf2_port_disable(ds, port, NULL);
 	}
 
-	bcm_sf2_sw_configure_vlan(ds);
+	b53_configure_vlan(ds);
+	bcm_sf2_enable_acb(ds);
 
 	return 0;
 }
@@ -1020,8 +874,8 @@ static const struct dsa_switch_ops bcm_sf2_ops = {
 	.set_wol		= bcm_sf2_sw_set_wol,
 	.port_enable		= bcm_sf2_port_setup,
 	.port_disable		= bcm_sf2_port_disable,
-	.get_mac_eee		= bcm_sf2_sw_get_mac_eee,
-	.set_mac_eee		= bcm_sf2_sw_set_mac_eee,
+	.get_mac_eee		= b53_get_mac_eee,
+	.set_mac_eee		= b53_set_mac_eee,
 	.port_bridge_join	= b53_br_join,
 	.port_bridge_leave	= b53_br_leave,
 	.port_stp_state_set	= b53_br_set_stp_state,
@@ -1173,6 +1027,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	 * permanently used
 	 */
 	set_bit(0, priv->cfp.used);
+	set_bit(0, priv->cfp.unique);
 
 	bcm_sf2_identify_ports(priv, dn->child);
 
diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 02c499f9c56b..cc31e986e6e3 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -48,14 +48,13 @@ struct bcm_sf2_hw_params {
 
 struct bcm_sf2_port_status {
 	unsigned int link;
-
-	struct ethtool_eee eee;
 };
 
 struct bcm_sf2_cfp_priv {
 	/* Mutex protecting concurrent accesses to the CFP registers */
 	struct mutex lock;
 	DECLARE_BITMAP(used, CFP_NUM_RULES);
+	DECLARE_BITMAP(unique, CFP_NUM_RULES);
 	unsigned int rules_cnt;
 };
 
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 8a1da7e67707..b721a2009b50 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -20,37 +20,102 @@
 #include "bcm_sf2.h"
 #include "bcm_sf2_regs.h"
 
-struct cfp_udf_layout {
-	u8 slices[UDF_NUM_SLICES];
+struct cfp_udf_slice_layout {
+	u8 slices[UDFS_PER_SLICE];
 	u32 mask_value;
+	u32 base_offset;
+};
 
+struct cfp_udf_layout {
+	struct cfp_udf_slice_layout udfs[UDF_NUM_SLICES];
 };
 
+static const u8 zero_slice[UDFS_PER_SLICE] = { };
+
 /* UDF slices layout for a TCPv4/UDPv4 specification */
 static const struct cfp_udf_layout udf_tcpip4_layout = {
-	.slices = {
-		/* End of L2, byte offset 12, src IP[0:15] */
-		CFG_UDF_EOL2 | 6,
-		/* End of L2, byte offset 14, src IP[16:31] */
-		CFG_UDF_EOL2 | 7,
-		/* End of L2, byte offset 16, dst IP[0:15] */
-		CFG_UDF_EOL2 | 8,
-		/* End of L2, byte offset 18, dst IP[16:31] */
-		CFG_UDF_EOL2 | 9,
-		/* End of L3, byte offset 0, src port */
-		CFG_UDF_EOL3 | 0,
-		/* End of L3, byte offset 2, dst port */
-		CFG_UDF_EOL3 | 1,
-		0, 0, 0
+	.udfs = {
+		[1] = {
+			.slices = {
+				/* End of L2, byte offset 12, src IP[0:15] */
+				CFG_UDF_EOL2 | 6,
+				/* End of L2, byte offset 14, src IP[16:31] */
+				CFG_UDF_EOL2 | 7,
+				/* End of L2, byte offset 16, dst IP[0:15] */
+				CFG_UDF_EOL2 | 8,
+				/* End of L2, byte offset 18, dst IP[16:31] */
+				CFG_UDF_EOL2 | 9,
+				/* End of L3, byte offset 0, src port */
+				CFG_UDF_EOL3 | 0,
+				/* End of L3, byte offset 2, dst port */
+				CFG_UDF_EOL3 | 1,
+				0, 0, 0
+			},
+			.mask_value = L3_FRAMING_MASK | IPPROTO_MASK | IP_FRAG,
+			.base_offset = CORE_UDF_0_A_0_8_PORT_0 + UDF_SLICE_OFFSET,
+		},
+	},
+};
+
+/* UDF slices layout for a TCPv6/UDPv6 specification */
+static const struct cfp_udf_layout udf_tcpip6_layout = {
+	.udfs = {
+		[0] = {
+			.slices = {
+				/* End of L2, byte offset 8, src IP[0:15] */
+				CFG_UDF_EOL2 | 4,
+				/* End of L2, byte offset 10, src IP[16:31] */
+				CFG_UDF_EOL2 | 5,
+				/* End of L2, byte offset 12, src IP[32:47] */
+				CFG_UDF_EOL2 | 6,
+				/* End of L2, byte offset 14, src IP[48:63] */
+				CFG_UDF_EOL2 | 7,
+				/* End of L2, byte offset 16, src IP[64:79] */
+				CFG_UDF_EOL2 | 8,
+				/* End of L2, byte offset 18, src IP[80:95] */
+				CFG_UDF_EOL2 | 9,
+				/* End of L2, byte offset 20, src IP[96:111] */
+				CFG_UDF_EOL2 | 10,
+				/* End of L2, byte offset 22, src IP[112:127] */
+				CFG_UDF_EOL2 | 11,
+				/* End of L3, byte offset 0, src port */
+				CFG_UDF_EOL3 | 0,
+			},
+			.mask_value = L3_FRAMING_MASK | IPPROTO_MASK | IP_FRAG,
+			.base_offset = CORE_UDF_0_B_0_8_PORT_0,
+		},
+		[3] = {
+			.slices = {
+				/* End of L2, byte offset 24, dst IP[0:15] */
+				CFG_UDF_EOL2 | 12,
+				/* End of L2, byte offset 26, dst IP[16:31] */
+				CFG_UDF_EOL2 | 13,
+				/* End of L2, byte offset 28, dst IP[32:47] */
+				CFG_UDF_EOL2 | 14,
+				/* End of L2, byte offset 30, dst IP[48:63] */
+				CFG_UDF_EOL2 | 15,
+				/* End of L2, byte offset 32, dst IP[64:79] */
+				CFG_UDF_EOL2 | 16,
+				/* End of L2, byte offset 34, dst IP[80:95] */
+				CFG_UDF_EOL2 | 17,
+				/* End of L2, byte offset 36, dst IP[96:111] */
+				CFG_UDF_EOL2 | 18,
+				/* End of L2, byte offset 38, dst IP[112:127] */
+				CFG_UDF_EOL2 | 19,
+				/* End of L3, byte offset 2, dst port */
+				CFG_UDF_EOL3 | 1,
+			},
+			.mask_value = L3_FRAMING_MASK | IPPROTO_MASK | IP_FRAG,
+			.base_offset = CORE_UDF_0_D_0_11_PORT_0,
+		},
 	},
-	.mask_value = L3_FRAMING_MASK | IPPROTO_MASK | IP_FRAG,
 };
 
 static inline unsigned int bcm_sf2_get_num_udf_slices(const u8 *layout)
 {
 	unsigned int i, count = 0;
 
-	for (i = 0; i < UDF_NUM_SLICES; i++) {
+	for (i = 0; i < UDFS_PER_SLICE; i++) {
 		if (layout[i] != 0)
 			count++;
 	}
@@ -58,15 +123,42 @@ static inline unsigned int bcm_sf2_get_num_udf_slices(const u8 *layout)
 	return count;
 }
 
+static inline u32 udf_upper_bits(unsigned int num_udf)
+{
+	return GENMASK(num_udf - 1, 0) >> (UDFS_PER_SLICE - 1);
+}
+
+static inline u32 udf_lower_bits(unsigned int num_udf)
+{
+	return (u8)GENMASK(num_udf - 1, 0);
+}
+
+static unsigned int bcm_sf2_get_slice_number(const struct cfp_udf_layout *l,
+					     unsigned int start)
+{
+	const struct cfp_udf_slice_layout *slice_layout;
+	unsigned int slice_idx;
+
+	for (slice_idx = start; slice_idx < UDF_NUM_SLICES; slice_idx++) {
+		slice_layout = &l->udfs[slice_idx];
+		if (memcmp(slice_layout->slices, zero_slice,
+			   sizeof(zero_slice)))
+			break;
+	}
+
+	return slice_idx;
+}
+
 static void bcm_sf2_cfp_udf_set(struct bcm_sf2_priv *priv,
-				unsigned int slice_num,
-				const u8 *layout)
+				const struct cfp_udf_layout *layout,
+				unsigned int slice_num)
 {
-	u32 offset = CORE_UDF_0_A_0_8_PORT_0 + slice_num * UDF_SLICE_OFFSET;
+	u32 offset = layout->udfs[slice_num].base_offset;
 	unsigned int i;
 
-	for (i = 0; i < UDF_NUM_SLICES; i++)
-		core_writel(priv, layout[i], offset + i * 4);
+	for (i = 0; i < UDFS_PER_SLICE; i++)
+		core_writel(priv, layout->udfs[slice_num].slices[i],
+			    offset + i * 4);
 }
 
 static int bcm_sf2_cfp_op(struct bcm_sf2_priv *priv, unsigned int op)
@@ -112,69 +204,177 @@ static inline unsigned int bcm_sf2_cfp_rule_size(struct bcm_sf2_priv *priv)
 	return priv->num_cfp_rules - 1;
 }
 
-static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
-				struct ethtool_rx_flow_spec *fs)
+static int bcm_sf2_cfp_act_pol_set(struct bcm_sf2_priv *priv,
+				   unsigned int rule_index,
+				   unsigned int port_num,
+				   unsigned int queue_num,
+				   bool fwd_map_change)
 {
-	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
-	struct ethtool_tcpip4_spec *v4_spec;
-	const struct cfp_udf_layout *layout;
-	unsigned int slice_num, rule_index;
-	unsigned int queue_num, port_num;
-	u8 ip_proto, ip_frag;
-	u8 num_udf;
-	u32 reg;
 	int ret;
+	u32 reg;
 
-	/* Check for unsupported extensions */
-	if ((fs->flow_type & FLOW_EXT) &&
-	    (fs->m_ext.vlan_etype || fs->m_ext.data[1]))
-		return -EINVAL;
+	/* Replace ARL derived destination with DST_MAP derived, define
+	 * which port and queue this should be forwarded to.
+	 */
+	if (fwd_map_change)
+		reg = CHANGE_FWRD_MAP_IB_REP_ARL |
+		      BIT(port_num + DST_MAP_IB_SHIFT) |
+		      CHANGE_TC | queue_num << NEW_TC_SHIFT;
+	else
+		reg = 0;
 
-	if (fs->location != RX_CLS_LOC_ANY &&
-	    test_bit(fs->location, priv->cfp.used))
-		return -EBUSY;
+	core_writel(priv, reg, CORE_ACT_POL_DATA0);
 
-	if (fs->location != RX_CLS_LOC_ANY &&
-	    fs->location > bcm_sf2_cfp_rule_size(priv))
-		return -EINVAL;
+	/* Set classification ID that needs to be put in Broadcom tag */
+	core_writel(priv, rule_index << CHAIN_ID_SHIFT, CORE_ACT_POL_DATA1);
 
-	ip_frag = be32_to_cpu(fs->m_ext.data[0]);
+	core_writel(priv, 0, CORE_ACT_POL_DATA2);
 
-	/* We do not support discarding packets, check that the
-	 * destination port is enabled and that we are within the
-	 * number of ports supported by the switch
+	/* Configure policer RAM now */
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | ACT_POL_RAM);
+	if (ret) {
+		pr_err("Policer entry at %d failed\n", rule_index);
+		return ret;
+	}
+
+	/* Disable the policer */
+	core_writel(priv, POLICER_MODE_DISABLE, CORE_RATE_METER0);
+
+	/* Now the rate meter */
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | RATE_METER_RAM);
+	if (ret) {
+		pr_err("Meter entry at %d failed\n", rule_index);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void bcm_sf2_cfp_slice_ipv4(struct bcm_sf2_priv *priv,
+				   struct ethtool_tcpip4_spec *v4_spec,
+				   unsigned int slice_num,
+				   bool mask)
+{
+	u32 reg, offset;
+
+	/* C-Tag		[31:24]
+	 * UDF_n_A8		[23:8]
+	 * UDF_n_A7		[7:0]
 	 */
-	port_num = fs->ring_cookie / 8;
+	reg = 0;
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(4);
+	else
+		offset = CORE_CFP_DATA_PORT(4);
+	core_writel(priv, reg, offset);
 
-	if (fs->ring_cookie == RX_CLS_FLOW_DISC ||
-	    !(BIT(port_num) & ds->enabled_port_mask) ||
-	    port_num >= priv->hw_params.num_ports)
-		return -EINVAL;
+	/* UDF_n_A7		[31:24]
+	 * UDF_n_A6		[23:8]
+	 * UDF_n_A5		[7:0]
+	 */
+	reg = be16_to_cpu(v4_spec->pdst) >> 8;
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(3);
+	else
+		offset = CORE_CFP_DATA_PORT(3);
+	core_writel(priv, reg, offset);
+
+	/* UDF_n_A5		[31:24]
+	 * UDF_n_A4		[23:8]
+	 * UDF_n_A3		[7:0]
+	 */
+	reg = (be16_to_cpu(v4_spec->pdst) & 0xff) << 24 |
+	      (u32)be16_to_cpu(v4_spec->psrc) << 8 |
+	      (be32_to_cpu(v4_spec->ip4dst) & 0x0000ff00) >> 8;
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(2);
+	else
+		offset = CORE_CFP_DATA_PORT(2);
+	core_writel(priv, reg, offset);
+
+	/* UDF_n_A3		[31:24]
+	 * UDF_n_A2		[23:8]
+	 * UDF_n_A1		[7:0]
+	 */
+	reg = (u32)(be32_to_cpu(v4_spec->ip4dst) & 0xff) << 24 |
+	      (u32)(be32_to_cpu(v4_spec->ip4dst) >> 16) << 8 |
+	      (be32_to_cpu(v4_spec->ip4src) & 0x0000ff00) >> 8;
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(1);
+	else
+		offset = CORE_CFP_DATA_PORT(1);
+	core_writel(priv, reg, offset);
+
+	/* UDF_n_A1		[31:24]
+	 * UDF_n_A0		[23:8]
+	 * Reserved		[7:4]
+	 * Slice ID		[3:2]
+	 * Slice valid		[1:0]
+	 */
+	reg = (u32)(be32_to_cpu(v4_spec->ip4src) & 0xff) << 24 |
+	      (u32)(be32_to_cpu(v4_spec->ip4src) >> 16) << 8 |
+	      SLICE_NUM(slice_num) | SLICE_VALID;
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(0);
+	else
+		offset = CORE_CFP_DATA_PORT(0);
+	core_writel(priv, reg, offset);
+}
+
+static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port,
+				     unsigned int port_num,
+				     unsigned int queue_num,
+				     struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *v4_spec, *v4_m_spec;
+	const struct cfp_udf_layout *layout;
+	unsigned int slice_num, rule_index;
+	u8 ip_proto, ip_frag;
+	u8 num_udf;
+	u32 reg;
+	int ret;
 
 	switch (fs->flow_type & ~FLOW_EXT) {
 	case TCP_V4_FLOW:
 		ip_proto = IPPROTO_TCP;
 		v4_spec = &fs->h_u.tcp_ip4_spec;
+		v4_m_spec = &fs->m_u.tcp_ip4_spec;
 		break;
 	case UDP_V4_FLOW:
 		ip_proto = IPPROTO_UDP;
 		v4_spec = &fs->h_u.udp_ip4_spec;
+		v4_m_spec = &fs->m_u.udp_ip4_spec;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	/* We only use one UDF slice for now */
-	slice_num = 1;
+	ip_frag = be32_to_cpu(fs->m_ext.data[0]);
+
+	/* Locate the first rule available */
+	if (fs->location == RX_CLS_LOC_ANY)
+		rule_index = find_first_zero_bit(priv->cfp.used,
+						 bcm_sf2_cfp_rule_size(priv));
+	else
+		rule_index = fs->location;
+
 	layout = &udf_tcpip4_layout;
-	num_udf = bcm_sf2_get_num_udf_slices(layout->slices);
+	/* We only use one UDF slice for now */
+	slice_num = bcm_sf2_get_slice_number(layout, 0);
+	if (slice_num == UDF_NUM_SLICES)
+		return -EINVAL;
+
+	num_udf = bcm_sf2_get_num_udf_slices(layout->udfs[slice_num].slices);
 
 	/* Apply the UDF layout for this filter */
-	bcm_sf2_cfp_udf_set(priv, slice_num, layout->slices);
+	bcm_sf2_cfp_udf_set(priv, layout, slice_num);
 
 	/* Apply to all packets received through this port */
 	core_writel(priv, BIT(port), CORE_CFP_DATA_PORT(7));
 
+	/* Source port map match */
+	core_writel(priv, 0xff, CORE_CFP_MASK_PORT(7));
+
 	/* S-Tag status		[31:30]
 	 * C-Tag status		[29:28]
 	 * L2 framing		[27:26]
@@ -189,143 +389,398 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	 * Reserved		[1]
 	 * UDF_Valid[8]		[0]
 	 */
-	core_writel(priv, v4_spec->tos << 16 | ip_proto << 8 | ip_frag << 7,
+	core_writel(priv, v4_spec->tos << IPTOS_SHIFT |
+		    ip_proto << IPPROTO_SHIFT | ip_frag << IP_FRAG_SHIFT |
+		    udf_upper_bits(num_udf),
 		    CORE_CFP_DATA_PORT(6));
 
+	/* Mask with the specific layout for IPv4 packets */
+	core_writel(priv, layout->udfs[slice_num].mask_value |
+		    udf_upper_bits(num_udf), CORE_CFP_MASK_PORT(6));
+
 	/* UDF_Valid[7:0]	[31:24]
 	 * S-Tag		[23:8]
 	 * C-Tag		[7:0]
 	 */
-	core_writel(priv, GENMASK(num_udf - 1, 0) << 24, CORE_CFP_DATA_PORT(5));
+	core_writel(priv, udf_lower_bits(num_udf) << 24, CORE_CFP_DATA_PORT(5));
+
+	/* Mask all but valid UDFs */
+	core_writel(priv, udf_lower_bits(num_udf) << 24, CORE_CFP_MASK_PORT(5));
+
+	/* Program the match and the mask */
+	bcm_sf2_cfp_slice_ipv4(priv, v4_spec, slice_num, false);
+	bcm_sf2_cfp_slice_ipv4(priv, v4_m_spec, SLICE_NUM_MASK, true);
+
+	/* Insert into TCAM now */
+	bcm_sf2_cfp_rule_addr_set(priv, rule_index);
+
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | TCAM_SEL);
+	if (ret) {
+		pr_err("TCAM entry at addr %d failed\n", rule_index);
+		return ret;
+	}
+
+	/* Insert into Action and policer RAMs now */
+	ret = bcm_sf2_cfp_act_pol_set(priv, rule_index, port_num,
+				      queue_num, true);
+	if (ret)
+		return ret;
+
+	/* Turn on CFP for this rule now */
+	reg = core_readl(priv, CORE_CFP_CTL_REG);
+	reg |= BIT(port);
+	core_writel(priv, reg, CORE_CFP_CTL_REG);
+
+	/* Flag the rule as being used and return it */
+	set_bit(rule_index, priv->cfp.used);
+	set_bit(rule_index, priv->cfp.unique);
+	fs->location = rule_index;
+
+	return 0;
+}
+
+static void bcm_sf2_cfp_slice_ipv6(struct bcm_sf2_priv *priv,
+				   const __be32 *ip6_addr, const __be16 port,
+				   unsigned int slice_num,
+				   bool mask)
+{
+	u32 reg, tmp, val, offset;
 
 	/* C-Tag		[31:24]
-	 * UDF_n_A8		[23:8]
-	 * UDF_n_A7		[7:0]
+	 * UDF_n_B8		[23:8]	(port)
+	 * UDF_n_B7 (upper)	[7:0]	(addr[15:8])
 	 */
-	core_writel(priv, 0, CORE_CFP_DATA_PORT(4));
+	reg = be32_to_cpu(ip6_addr[3]);
+	val = (u32)be16_to_cpu(port) << 8 | ((reg >> 8) & 0xff);
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(4);
+	else
+		offset = CORE_CFP_DATA_PORT(4);
+	core_writel(priv, val, offset);
 
-	/* UDF_n_A7		[31:24]
-	 * UDF_n_A6		[23:8]
-	 * UDF_n_A5		[7:0]
+	/* UDF_n_B7 (lower)	[31:24]	(addr[7:0])
+	 * UDF_n_B6		[23:8] (addr[31:16])
+	 * UDF_n_B5 (upper)	[7:0] (addr[47:40])
 	 */
-	core_writel(priv, be16_to_cpu(v4_spec->pdst) >> 8,
-		    CORE_CFP_DATA_PORT(3));
+	tmp = be32_to_cpu(ip6_addr[2]);
+	val = (u32)(reg & 0xff) << 24 | (u32)(reg >> 16) << 8 |
+	      ((tmp >> 8) & 0xff);
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(3);
+	else
+		offset = CORE_CFP_DATA_PORT(3);
+	core_writel(priv, val, offset);
 
-	/* UDF_n_A5		[31:24]
-	 * UDF_n_A4		[23:8]
-	 * UDF_n_A3		[7:0]
+	/* UDF_n_B5 (lower)	[31:24] (addr[39:32])
+	 * UDF_n_B4		[23:8] (addr[63:48])
+	 * UDF_n_B3 (upper)	[7:0] (addr[79:72])
 	 */
-	reg = (be16_to_cpu(v4_spec->pdst) & 0xff) << 24 |
-	      (u32)be16_to_cpu(v4_spec->psrc) << 8 |
-	      (be32_to_cpu(v4_spec->ip4dst) & 0x0000ff00) >> 8;
-	core_writel(priv, reg, CORE_CFP_DATA_PORT(2));
+	reg = be32_to_cpu(ip6_addr[1]);
+	val = (u32)(tmp & 0xff) << 24 | (u32)(tmp >> 16) << 8 |
+	      ((reg >> 8) & 0xff);
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(2);
+	else
+		offset = CORE_CFP_DATA_PORT(2);
+	core_writel(priv, val, offset);
 
-	/* UDF_n_A3		[31:24]
-	 * UDF_n_A2		[23:8]
-	 * UDF_n_A1		[7:0]
+	/* UDF_n_B3 (lower)	[31:24] (addr[71:64])
+	 * UDF_n_B2		[23:8] (addr[95:80])
+	 * UDF_n_B1 (upper)	[7:0] (addr[111:104])
 	 */
-	reg = (u32)(be32_to_cpu(v4_spec->ip4dst) & 0xff) << 24 |
-	      (u32)(be32_to_cpu(v4_spec->ip4dst) >> 16) << 8 |
-	      (be32_to_cpu(v4_spec->ip4src) & 0x0000ff00) >> 8;
-	core_writel(priv, reg, CORE_CFP_DATA_PORT(1));
+	tmp = be32_to_cpu(ip6_addr[0]);
+	val = (u32)(reg & 0xff) << 24 | (u32)(reg >> 16) << 8 |
+	      ((tmp >> 8) & 0xff);
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(1);
+	else
+		offset = CORE_CFP_DATA_PORT(1);
+	core_writel(priv, val, offset);
 
-	/* UDF_n_A1		[31:24]
-	 * UDF_n_A0		[23:8]
+	/* UDF_n_B1 (lower)	[31:24] (addr[103:96])
+	 * UDF_n_B0		[23:8] (addr[127:112])
 	 * Reserved		[7:4]
 	 * Slice ID		[3:2]
 	 * Slice valid		[1:0]
 	 */
-	reg = (u32)(be32_to_cpu(v4_spec->ip4src) & 0xff) << 24 |
-	      (u32)(be32_to_cpu(v4_spec->ip4src) >> 16) << 8 |
-	      SLICE_NUM(slice_num) | SLICE_VALID;
-	core_writel(priv, reg, CORE_CFP_DATA_PORT(0));
+	reg = (u32)(tmp & 0xff) << 24 | (u32)(tmp >> 16) << 8 |
+	       SLICE_NUM(slice_num) | SLICE_VALID;
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(0);
+	else
+		offset = CORE_CFP_DATA_PORT(0);
+	core_writel(priv, reg, offset);
+}
 
-	/* Source port map match */
-	core_writel(priv, 0xff, CORE_CFP_MASK_PORT(7));
+static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
+				     unsigned int port_num,
+				     unsigned int queue_num,
+				     struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip6_spec *v6_spec, *v6_m_spec;
+	unsigned int slice_num, rule_index[2];
+	const struct cfp_udf_layout *layout;
+	u8 ip_proto, ip_frag;
+	int ret = 0;
+	u8 num_udf;
+	u32 reg;
 
-	/* Mask with the specific layout for IPv4 packets */
-	core_writel(priv, layout->mask_value, CORE_CFP_MASK_PORT(6));
+	switch (fs->flow_type & ~FLOW_EXT) {
+	case TCP_V6_FLOW:
+		ip_proto = IPPROTO_TCP;
+		v6_spec = &fs->h_u.tcp_ip6_spec;
+		v6_m_spec = &fs->m_u.tcp_ip6_spec;
+		break;
+	case UDP_V6_FLOW:
+		ip_proto = IPPROTO_UDP;
+		v6_spec = &fs->h_u.udp_ip6_spec;
+		v6_m_spec = &fs->m_u.udp_ip6_spec;
+		break;
+	default:
+		return -EINVAL;
+	}
 
-	/* Mask all but valid UDFs */
-	core_writel(priv, GENMASK(num_udf - 1, 0) << 24, CORE_CFP_MASK_PORT(5));
+	ip_frag = be32_to_cpu(fs->m_ext.data[0]);
 
-	/* Mask all */
-	core_writel(priv, 0, CORE_CFP_MASK_PORT(4));
+	layout = &udf_tcpip6_layout;
+	slice_num = bcm_sf2_get_slice_number(layout, 0);
+	if (slice_num == UDF_NUM_SLICES)
+		return -EINVAL;
 
-	/* All other UDFs should be matched with the filter */
-	core_writel(priv, 0xff, CORE_CFP_MASK_PORT(3));
-	core_writel(priv, 0xffffffff, CORE_CFP_MASK_PORT(2));
-	core_writel(priv, 0xffffffff, CORE_CFP_MASK_PORT(1));
-	core_writel(priv, 0xffffff0f, CORE_CFP_MASK_PORT(0));
+	num_udf = bcm_sf2_get_num_udf_slices(layout->udfs[slice_num].slices);
 
-	/* Locate the first rule available */
+	/* Negotiate two indexes, one for the second half which we are chained
+	 * from, which is what we will return to user-space, and a second one
+	 * which is used to store its first half. That first half does not
+	 * allow any choice of placement, so it just needs to find the next
+	 * available bit. We return the second half as fs->location because
+	 * that helps with the rule lookup later on since the second half is
+	 * chained from its first half, we can easily identify IPv6 CFP rules
+	 * by looking whether they carry a CHAIN_ID.
+	 *
+	 * We also want the second half to have a lower rule_index than its
+	 * first half because the HW search is by incrementing addresses.
+	 */
 	if (fs->location == RX_CLS_LOC_ANY)
-		rule_index = find_first_zero_bit(priv->cfp.used,
-						 bcm_sf2_cfp_rule_size(priv));
+		rule_index[0] = find_first_zero_bit(priv->cfp.used,
+						    bcm_sf2_cfp_rule_size(priv));
 	else
-		rule_index = fs->location;
+		rule_index[0] = fs->location;
 
-	/* Insert into TCAM now */
-	bcm_sf2_cfp_rule_addr_set(priv, rule_index);
+	/* Flag it as used (cleared on error path) such that we can immediately
+	 * obtain a second one to chain from.
+	 */
+	set_bit(rule_index[0], priv->cfp.used);
 
-	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | TCAM_SEL);
-	if (ret) {
-		pr_err("TCAM entry at addr %d failed\n", rule_index);
-		return ret;
+	rule_index[1] = find_first_zero_bit(priv->cfp.used,
+					    bcm_sf2_cfp_rule_size(priv));
+	if (rule_index[1] > bcm_sf2_cfp_rule_size(priv)) {
+		ret = -ENOSPC;
+		goto out_err;
 	}
 
-	/* Replace ARL derived destination with DST_MAP derived, define
-	 * which port and queue this should be forwarded to.
-	 *
-	 * We have a small oddity where Port 6 just does not have a
-	 * valid bit here (so we subtract by one).
+	/* Apply the UDF layout for this filter */
+	bcm_sf2_cfp_udf_set(priv, layout, slice_num);
+
+	/* Apply to all packets received through this port */
+	core_writel(priv, BIT(port), CORE_CFP_DATA_PORT(7));
+
+	/* Source port map match */
+	core_writel(priv, 0xff, CORE_CFP_MASK_PORT(7));
+
+	/* S-Tag status		[31:30]
+	 * C-Tag status		[29:28]
+	 * L2 framing		[27:26]
+	 * L3 framing		[25:24]
+	 * IP ToS		[23:16]
+	 * IP proto		[15:08]
+	 * IP Fragm		[7]
+	 * Non 1st frag		[6]
+	 * IP Authen		[5]
+	 * TTL range		[4:3]
+	 * PPPoE session	[2]
+	 * Reserved		[1]
+	 * UDF_Valid[8]		[0]
 	 */
-	queue_num = fs->ring_cookie % 8;
-	if (port_num >= 7)
-		port_num -= 1;
+	reg = 1 << L3_FRAMING_SHIFT | ip_proto << IPPROTO_SHIFT |
+		ip_frag << IP_FRAG_SHIFT | udf_upper_bits(num_udf);
+	core_writel(priv, reg, CORE_CFP_DATA_PORT(6));
 
-	reg = CHANGE_FWRD_MAP_IB_REP_ARL | BIT(port_num + DST_MAP_IB_SHIFT) |
-		CHANGE_TC | queue_num << NEW_TC_SHIFT;
+	/* Mask with the specific layout for IPv6 packets including
+	 * UDF_Valid[8]
+	 */
+	reg = layout->udfs[slice_num].mask_value | udf_upper_bits(num_udf);
+	core_writel(priv, reg, CORE_CFP_MASK_PORT(6));
 
-	core_writel(priv, reg, CORE_ACT_POL_DATA0);
+	/* UDF_Valid[7:0]	[31:24]
+	 * S-Tag		[23:8]
+	 * C-Tag		[7:0]
+	 */
+	core_writel(priv, udf_lower_bits(num_udf) << 24, CORE_CFP_DATA_PORT(5));
 
-	/* Set classification ID that needs to be put in Broadcom tag */
-	core_writel(priv, rule_index << CHAIN_ID_SHIFT,
-		    CORE_ACT_POL_DATA1);
+	/* Mask all but valid UDFs */
+	core_writel(priv, udf_lower_bits(num_udf) << 24, CORE_CFP_MASK_PORT(5));
 
-	core_writel(priv, 0, CORE_ACT_POL_DATA2);
+	/* Slice the IPv6 source address and port */
+	bcm_sf2_cfp_slice_ipv6(priv, v6_spec->ip6src, v6_spec->psrc,
+				slice_num, false);
+	bcm_sf2_cfp_slice_ipv6(priv, v6_m_spec->ip6src, v6_m_spec->psrc,
+				slice_num, true);
 
-	/* Configure policer RAM now */
-	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | ACT_POL_RAM);
+	/* Insert into TCAM now because we need to insert a second rule */
+	bcm_sf2_cfp_rule_addr_set(priv, rule_index[0]);
+
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | TCAM_SEL);
 	if (ret) {
-		pr_err("Policer entry at %d failed\n", rule_index);
-		return ret;
+		pr_err("TCAM entry at addr %d failed\n", rule_index[0]);
+		goto out_err;
 	}
 
-	/* Disable the policer */
-	core_writel(priv, POLICER_MODE_DISABLE, CORE_RATE_METER0);
+	/* Insert into Action and policer RAMs now */
+	ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[0], port_num,
+				      queue_num, false);
+	if (ret)
+		goto out_err;
 
-	/* Now the rate meter */
-	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | RATE_METER_RAM);
+	/* Now deal with the second slice to chain this rule */
+	slice_num = bcm_sf2_get_slice_number(layout, slice_num + 1);
+	if (slice_num == UDF_NUM_SLICES) {
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	num_udf = bcm_sf2_get_num_udf_slices(layout->udfs[slice_num].slices);
+
+	/* Apply the UDF layout for this filter */
+	bcm_sf2_cfp_udf_set(priv, layout, slice_num);
+
+	/* Chained rule, source port match is coming from the rule we are
+	 * chained from.
+	 */
+	core_writel(priv, 0, CORE_CFP_DATA_PORT(7));
+	core_writel(priv, 0, CORE_CFP_MASK_PORT(7));
+
+	/*
+	 * CHAIN ID		[31:24] chain to previous slice
+	 * Reserved		[23:20]
+	 * UDF_Valid[11:8]	[19:16]
+	 * UDF_Valid[7:0]	[15:8]
+	 * UDF_n_D11		[7:0]
+	 */
+	reg = rule_index[0] << 24 | udf_upper_bits(num_udf) << 16 |
+		udf_lower_bits(num_udf) << 8;
+	core_writel(priv, reg, CORE_CFP_DATA_PORT(6));
+
+	/* Mask all except chain ID, UDF Valid[8] and UDF Valid[7:0] */
+	reg = XCESS_ADDR_MASK << 24 | udf_upper_bits(num_udf) << 16 |
+		udf_lower_bits(num_udf) << 8;
+	core_writel(priv, reg, CORE_CFP_MASK_PORT(6));
+
+	/* Don't care */
+	core_writel(priv, 0, CORE_CFP_DATA_PORT(5));
+
+	/* Mask all */
+	core_writel(priv, 0, CORE_CFP_MASK_PORT(5));
+
+	bcm_sf2_cfp_slice_ipv6(priv, v6_spec->ip6dst, v6_spec->pdst, slice_num,
+			       false);
+	bcm_sf2_cfp_slice_ipv6(priv, v6_m_spec->ip6dst, v6_m_spec->pdst,
+			       SLICE_NUM_MASK, true);
+
+	/* Insert into TCAM now */
+	bcm_sf2_cfp_rule_addr_set(priv, rule_index[1]);
+
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | TCAM_SEL);
 	if (ret) {
-		pr_err("Meter entry at %d failed\n", rule_index);
-		return ret;
+		pr_err("TCAM entry at addr %d failed\n", rule_index[1]);
+		goto out_err;
 	}
 
+	/* Insert into Action and policer RAMs now, set chain ID to
+	 * the one we are chained to
+	 */
+	ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[0], port_num,
+				      queue_num, true);
+	if (ret)
+		goto out_err;
+
 	/* Turn on CFP for this rule now */
 	reg = core_readl(priv, CORE_CFP_CTL_REG);
 	reg |= BIT(port);
 	core_writel(priv, reg, CORE_CFP_CTL_REG);
 
-	/* Flag the rule as being used and return it */
-	set_bit(rule_index, priv->cfp.used);
-	fs->location = rule_index;
+	/* Flag the second half rule as being used now, return it as the
+	 * location, and flag it as unique while dumping rules
+	 */
+	set_bit(rule_index[1], priv->cfp.used);
+	set_bit(rule_index[1], priv->cfp.unique);
+	fs->location = rule_index[1];
 
-	return 0;
+	return ret;
+
+out_err:
+	clear_bit(rule_index[0], priv->cfp.used);
+	return ret;
 }
 
-static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
-				u32 loc)
+static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
+				struct ethtool_rx_flow_spec *fs)
+{
+	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+	unsigned int queue_num, port_num;
+	int ret = -EINVAL;
+
+	/* Check for unsupported extensions */
+	if ((fs->flow_type & FLOW_EXT) && (fs->m_ext.vlan_etype ||
+	     fs->m_ext.data[1]))
+		return -EINVAL;
+
+	if (fs->location != RX_CLS_LOC_ANY &&
+	    test_bit(fs->location, priv->cfp.used))
+		return -EBUSY;
+
+	if (fs->location != RX_CLS_LOC_ANY &&
+	    fs->location > bcm_sf2_cfp_rule_size(priv))
+		return -EINVAL;
+
+	/* We do not support discarding packets, check that the
+	 * destination port is enabled and that we are within the
+	 * number of ports supported by the switch
+	 */
+	port_num = fs->ring_cookie / SF2_NUM_EGRESS_QUEUES;
+
+	if (fs->ring_cookie == RX_CLS_FLOW_DISC ||
+	    !dsa_is_user_port(ds, port_num) ||
+	    port_num >= priv->hw_params.num_ports)
+		return -EINVAL;
+	/*
+	 * We have a small oddity where Port 6 just does not have a
+	 * valid bit here (so we substract by one).
+	 */
+	queue_num = fs->ring_cookie % SF2_NUM_EGRESS_QUEUES;
+	if (port_num >= 7)
+		port_num -= 1;
+
+	switch (fs->flow_type & ~FLOW_EXT) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+		ret = bcm_sf2_cfp_ipv4_rule_set(priv, port, port_num,
+						queue_num, fs);
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+		ret = bcm_sf2_cfp_ipv6_rule_set(priv, port, port_num,
+						queue_num, fs);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int bcm_sf2_cfp_rule_del_one(struct bcm_sf2_priv *priv, int port,
+				    u32 loc, u32 *next_loc)
 {
 	int ret;
 	u32 reg;
@@ -341,6 +796,14 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 	if (ret)
 		return ret;
 
+	/* Check if this is possibly an IPv6 rule that would
+	 * indicate we need to delete its companion rule
+	 * as well
+	 */
+	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
+	if (next_loc)
+		*next_loc = (reg >> 24) & CHAIN_ID_MASK;
+
 	/* Clear its valid bits */
 	reg = core_readl(priv, CORE_CFP_DATA_PORT(0));
 	reg &= ~SLICE_VALID;
@@ -352,10 +815,28 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 		return ret;
 
 	clear_bit(loc, priv->cfp.used);
+	clear_bit(loc, priv->cfp.unique);
 
 	return 0;
 }
 
+static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
+				u32 loc)
+{
+	u32 next_loc = 0;
+	int ret;
+
+	ret = bcm_sf2_cfp_rule_del_one(priv, port, loc, &next_loc);
+	if (ret)
+		return ret;
+
+	/* If this was an IPv6 rule, delete is companion rule too */
+	if (next_loc)
+		ret = bcm_sf2_cfp_rule_del_one(priv, port, next_loc, NULL);
+
+	return ret;
+}
+
 static void bcm_sf2_invert_masks(struct ethtool_rx_flow_spec *flow)
 {
 	unsigned int i;
@@ -369,93 +850,63 @@ static void bcm_sf2_invert_masks(struct ethtool_rx_flow_spec *flow)
 	flow->m_ext.data[1] ^= cpu_to_be32(~0);
 }
 
-static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
-				struct ethtool_rxnfc *nfc, bool search)
+static int bcm_sf2_cfp_unslice_ipv4(struct bcm_sf2_priv *priv,
+				    struct ethtool_tcpip4_spec *v4_spec,
+				    bool mask)
 {
-	struct ethtool_tcpip4_spec *v4_spec;
-	unsigned int queue_num;
+	u32 reg, offset, ipv4;
 	u16 src_dst_port;
-	u32 reg, ipv4;
-	int ret;
-
-	if (!search) {
-		bcm_sf2_cfp_rule_addr_set(priv, nfc->fs.location);
-
-		ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | ACT_POL_RAM);
-		if (ret)
-			return ret;
-
-		reg = core_readl(priv, CORE_ACT_POL_DATA0);
 
-		ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | TCAM_SEL);
-		if (ret)
-			return ret;
-	} else {
-		reg = core_readl(priv, CORE_ACT_POL_DATA0);
-	}
-
-	/* Extract the destination port */
-	nfc->fs.ring_cookie = fls((reg >> DST_MAP_IB_SHIFT) &
-				  DST_MAP_IB_MASK) - 1;
-
-	/* There is no Port 6, so we compensate for that here */
-	if (nfc->fs.ring_cookie >= 6)
-		nfc->fs.ring_cookie++;
-	nfc->fs.ring_cookie *= 8;
-
-	/* Extract the destination queue */
-	queue_num = (reg >> NEW_TC_SHIFT) & NEW_TC_MASK;
-	nfc->fs.ring_cookie += queue_num;
-
-	/* Extract the IP protocol */
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
-	switch ((reg & IPPROTO_MASK) >> IPPROTO_SHIFT) {
-	case IPPROTO_TCP:
-		nfc->fs.flow_type = TCP_V4_FLOW;
-		v4_spec = &nfc->fs.h_u.tcp_ip4_spec;
-		break;
-	case IPPROTO_UDP:
-		nfc->fs.flow_type = UDP_V4_FLOW;
-		v4_spec = &nfc->fs.h_u.udp_ip4_spec;
-		break;
-	default:
-		/* Clear to exit the search process */
-		if (search)
-			core_readl(priv, CORE_CFP_DATA_PORT(7));
-		return -EINVAL;
-	}
-
-	v4_spec->tos = (reg >> 16) & IPPROTO_MASK;
-	nfc->fs.m_ext.data[0] = cpu_to_be32((reg >> 7) & 1);
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(3);
+	else
+		offset = CORE_CFP_DATA_PORT(3);
 
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(3));
+	reg = core_readl(priv, offset);
 	/* src port [15:8] */
 	src_dst_port = reg << 8;
 
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(2));
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(2);
+	else
+		offset = CORE_CFP_DATA_PORT(2);
+
+	reg = core_readl(priv, offset);
 	/* src port [7:0] */
 	src_dst_port |= (reg >> 24);
 
 	v4_spec->pdst = cpu_to_be16(src_dst_port);
-	nfc->fs.m_u.tcp_ip4_spec.pdst = cpu_to_be16(~0);
 	v4_spec->psrc = cpu_to_be16((u16)(reg >> 8));
-	nfc->fs.m_u.tcp_ip4_spec.psrc = cpu_to_be16(~0);
 
 	/* IPv4 dst [15:8] */
 	ipv4 = (reg & 0xff) << 8;
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(1));
+
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(1);
+	else
+		offset = CORE_CFP_DATA_PORT(1);
+
+	reg = core_readl(priv, offset);
 	/* IPv4 dst [31:16] */
 	ipv4 |= ((reg >> 8) & 0xffff) << 16;
 	/* IPv4 dst [7:0] */
 	ipv4 |= (reg >> 24) & 0xff;
 	v4_spec->ip4dst = cpu_to_be32(ipv4);
-	nfc->fs.m_u.tcp_ip4_spec.ip4dst = cpu_to_be32(~0);
 
 	/* IPv4 src [15:8] */
 	ipv4 = (reg & 0xff) << 8;
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(0));
 
-	if (!(reg & SLICE_VALID))
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(0);
+	else
+		offset = CORE_CFP_DATA_PORT(0);
+	reg = core_readl(priv, offset);
+
+	/* Once the TCAM is programmed, the mask reflects the slice number
+	 * being matched, don't bother checking it when reading back the
+	 * mask spec
+	 */
+	if (!mask && !(reg & SLICE_VALID))
 		return -EINVAL;
 
 	/* IPv4 src [7:0] */
@@ -463,7 +914,233 @@ static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
 	/* IPv4 src [31:16] */
 	ipv4 |= ((reg >> 8) & 0xffff) << 16;
 	v4_spec->ip4src = cpu_to_be32(ipv4);
-	nfc->fs.m_u.tcp_ip4_spec.ip4src = cpu_to_be32(~0);
+
+	return 0;
+}
+
+static int bcm_sf2_cfp_ipv4_rule_get(struct bcm_sf2_priv *priv, int port,
+				     struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *v4_spec = NULL, *v4_m_spec = NULL;
+	u32 reg;
+	int ret;
+
+	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
+
+	switch ((reg & IPPROTO_MASK) >> IPPROTO_SHIFT) {
+	case IPPROTO_TCP:
+		fs->flow_type = TCP_V4_FLOW;
+		v4_spec = &fs->h_u.tcp_ip4_spec;
+		v4_m_spec = &fs->m_u.tcp_ip4_spec;
+		break;
+	case IPPROTO_UDP:
+		fs->flow_type = UDP_V4_FLOW;
+		v4_spec = &fs->h_u.udp_ip4_spec;
+		v4_m_spec = &fs->m_u.udp_ip4_spec;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	fs->m_ext.data[0] = cpu_to_be32((reg >> IP_FRAG_SHIFT) & 1);
+	v4_spec->tos = (reg >> IPTOS_SHIFT) & IPTOS_MASK;
+
+	ret = bcm_sf2_cfp_unslice_ipv4(priv, v4_spec, false);
+	if (ret)
+		return ret;
+
+	return bcm_sf2_cfp_unslice_ipv4(priv, v4_m_spec, true);
+}
+
+static int bcm_sf2_cfp_unslice_ipv6(struct bcm_sf2_priv *priv,
+				     __be32 *ip6_addr, __be16 *port,
+				     bool mask)
+{
+	u32 reg, tmp, offset;
+
+	/* C-Tag		[31:24]
+	 * UDF_n_B8		[23:8] (port)
+	 * UDF_n_B7 (upper)	[7:0] (addr[15:8])
+	 */
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(4);
+	else
+		offset = CORE_CFP_DATA_PORT(4);
+	reg = core_readl(priv, offset);
+	*port = cpu_to_be32(reg) >> 8;
+	tmp = (u32)(reg & 0xff) << 8;
+
+	/* UDF_n_B7 (lower)	[31:24] (addr[7:0])
+	 * UDF_n_B6		[23:8] (addr[31:16])
+	 * UDF_n_B5 (upper)	[7:0] (addr[47:40])
+	 */
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(3);
+	else
+		offset = CORE_CFP_DATA_PORT(3);
+	reg = core_readl(priv, offset);
+	tmp |= (reg >> 24) & 0xff;
+	tmp |= (u32)((reg >> 8) << 16);
+	ip6_addr[3] = cpu_to_be32(tmp);
+	tmp = (u32)(reg & 0xff) << 8;
+
+	/* UDF_n_B5 (lower)	[31:24] (addr[39:32])
+	 * UDF_n_B4		[23:8] (addr[63:48])
+	 * UDF_n_B3 (upper)	[7:0] (addr[79:72])
+	 */
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(2);
+	else
+		offset = CORE_CFP_DATA_PORT(2);
+	reg = core_readl(priv, offset);
+	tmp |= (reg >> 24) & 0xff;
+	tmp |= (u32)((reg >> 8) << 16);
+	ip6_addr[2] = cpu_to_be32(tmp);
+	tmp = (u32)(reg & 0xff) << 8;
+
+	/* UDF_n_B3 (lower)	[31:24] (addr[71:64])
+	 * UDF_n_B2		[23:8] (addr[95:80])
+	 * UDF_n_B1 (upper)	[7:0] (addr[111:104])
+	 */
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(1);
+	else
+		offset = CORE_CFP_DATA_PORT(1);
+	reg = core_readl(priv, offset);
+	tmp |= (reg >> 24) & 0xff;
+	tmp |= (u32)((reg >> 8) << 16);
+	ip6_addr[1] = cpu_to_be32(tmp);
+	tmp = (u32)(reg & 0xff) << 8;
+
+	/* UDF_n_B1 (lower)	[31:24] (addr[103:96])
+	 * UDF_n_B0		[23:8] (addr[127:112])
+	 * Reserved		[7:4]
+	 * Slice ID		[3:2]
+	 * Slice valid		[1:0]
+	 */
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(0);
+	else
+		offset = CORE_CFP_DATA_PORT(0);
+	reg = core_readl(priv, offset);
+	tmp |= (reg >> 24) & 0xff;
+	tmp |= (u32)((reg >> 8) << 16);
+	ip6_addr[0] = cpu_to_be32(tmp);
+
+	if (!mask && !(reg & SLICE_VALID))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int bcm_sf2_cfp_ipv6_rule_get(struct bcm_sf2_priv *priv, int port,
+				     struct ethtool_rx_flow_spec *fs,
+				     u32 next_loc)
+{
+	struct ethtool_tcpip6_spec *v6_spec = NULL, *v6_m_spec = NULL;
+	u32 reg;
+	int ret;
+
+	/* UDPv6 and TCPv6 both use ethtool_tcpip6_spec so we are fine
+	 * assuming tcp_ip6_spec here being an union.
+	 */
+	v6_spec = &fs->h_u.tcp_ip6_spec;
+	v6_m_spec = &fs->m_u.tcp_ip6_spec;
+
+	/* Read the second half first */
+	ret = bcm_sf2_cfp_unslice_ipv6(priv, v6_spec->ip6dst, &v6_spec->pdst,
+				       false);
+	if (ret)
+		return ret;
+
+	ret = bcm_sf2_cfp_unslice_ipv6(priv, v6_m_spec->ip6dst,
+				       &v6_m_spec->pdst, true);
+	if (ret)
+		return ret;
+
+	/* Read last to avoid next entry clobbering the results during search
+	 * operations. We would not have the port enabled for this rule, so
+	 * don't bother checking it.
+	 */
+	(void)core_readl(priv, CORE_CFP_DATA_PORT(7));
+
+	/* The slice number is valid, so read the rule we are chained from now
+	 * which is our first half.
+	 */
+	bcm_sf2_cfp_rule_addr_set(priv, next_loc);
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | TCAM_SEL);
+	if (ret)
+		return ret;
+
+	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
+
+	switch ((reg & IPPROTO_MASK) >> IPPROTO_SHIFT) {
+	case IPPROTO_TCP:
+		fs->flow_type = TCP_V6_FLOW;
+		break;
+	case IPPROTO_UDP:
+		fs->flow_type = UDP_V6_FLOW;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = bcm_sf2_cfp_unslice_ipv6(priv, v6_spec->ip6src, &v6_spec->psrc,
+				       false);
+	if (ret)
+		return ret;
+
+	return bcm_sf2_cfp_unslice_ipv6(priv, v6_m_spec->ip6src,
+					&v6_m_spec->psrc, true);
+}
+
+static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
+				struct ethtool_rxnfc *nfc)
+{
+	u32 reg, ipv4_or_chain_id;
+	unsigned int queue_num;
+	int ret;
+
+	bcm_sf2_cfp_rule_addr_set(priv, nfc->fs.location);
+
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | ACT_POL_RAM);
+	if (ret)
+		return ret;
+
+	reg = core_readl(priv, CORE_ACT_POL_DATA0);
+
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | TCAM_SEL);
+	if (ret)
+		return ret;
+
+	/* Extract the destination port */
+	nfc->fs.ring_cookie = fls((reg >> DST_MAP_IB_SHIFT) &
+				  DST_MAP_IB_MASK) - 1;
+
+	/* There is no Port 6, so we compensate for that here */
+	if (nfc->fs.ring_cookie >= 6)
+		nfc->fs.ring_cookie++;
+	nfc->fs.ring_cookie *= SF2_NUM_EGRESS_QUEUES;
+
+	/* Extract the destination queue */
+	queue_num = (reg >> NEW_TC_SHIFT) & NEW_TC_MASK;
+	nfc->fs.ring_cookie += queue_num;
+
+	/* Extract the L3_FRAMING or CHAIN_ID */
+	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
+
+	/* With IPv6 rules this would contain a non-zero chain ID since
+	 * we reserve entry 0 and it cannot be used. So if we read 0 here
+	 * this means an IPv4 rule.
+	 */
+	ipv4_or_chain_id = (reg >> L3_FRAMING_SHIFT) & 0xff;
+	if (ipv4_or_chain_id == 0)
+		ret = bcm_sf2_cfp_ipv4_rule_get(priv, port, &nfc->fs);
+	else
+		ret = bcm_sf2_cfp_ipv6_rule_get(priv, port, &nfc->fs,
+						ipv4_or_chain_id);
+	if (ret)
+		return ret;
 
 	/* Read last to avoid next entry clobbering the results during search
 	 * operations
@@ -486,44 +1163,11 @@ static int bcm_sf2_cfp_rule_get_all(struct bcm_sf2_priv *priv,
 				    u32 *rule_locs)
 {
 	unsigned int index = 1, rules_cnt = 0;
-	int ret;
-	u32 reg;
 
-	/* Do not poll on OP_STR_DONE to be self-clearing for search
-	 * operations, we cannot use bcm_sf2_cfp_op here because it completes
-	 * on clearing OP_STR_DONE which won't clear until the entire search
-	 * operation is over.
-	 */
-	reg = core_readl(priv, CORE_CFP_ACC);
-	reg &= ~(XCESS_ADDR_MASK << XCESS_ADDR_SHIFT);
-	reg |= index << XCESS_ADDR_SHIFT;
-	reg &= ~(OP_SEL_MASK | RAM_SEL_MASK);
-	reg |= OP_SEL_SEARCH | TCAM_SEL | OP_STR_DONE;
-	core_writel(priv, reg, CORE_CFP_ACC);
-
-	do {
-		/* Wait for results to be ready */
-		reg = core_readl(priv, CORE_CFP_ACC);
-
-		/* Extract the address we are searching */
-		index = reg >> XCESS_ADDR_SHIFT;
-		index &= XCESS_ADDR_MASK;
-
-		/* We have a valid search result, so flag it accordingly */
-		if (reg & SEARCH_STS) {
-			ret = bcm_sf2_cfp_rule_get(priv, port, nfc, true);
-			if (ret)
-				continue;
-
-			rule_locs[rules_cnt] = index;
-			rules_cnt++;
-		}
-
-		/* Search is over break out */
-		if (!(reg & OP_STR_DONE))
-			break;
-
-	} while (index < priv->num_cfp_rules);
+	for_each_set_bit_from(index, priv->cfp.unique, priv->num_cfp_rules) {
+		rule_locs[rules_cnt] = index;
+		rules_cnt++;
+	}
 
 	/* Put the TCAM size here */
 	nfc->data = bcm_sf2_cfp_rule_size(priv);
@@ -543,13 +1187,13 @@ int bcm_sf2_get_rxnfc(struct dsa_switch *ds, int port,
 	switch (nfc->cmd) {
 	case ETHTOOL_GRXCLSRLCNT:
 		/* Subtract the default, unusable rule */
-		nfc->rule_cnt = bitmap_weight(priv->cfp.used,
+		nfc->rule_cnt = bitmap_weight(priv->cfp.unique,
 					      priv->num_cfp_rules) - 1;
 		/* We support specifying rule locations */
 		nfc->data |= RX_CLS_LOC_SPECIAL;
 		break;
 	case ETHTOOL_GRXCLSRULE:
-		ret = bcm_sf2_cfp_rule_get(priv, port, nfc, false);
+		ret = bcm_sf2_cfp_rule_get(priv, port, nfc);
 		break;
 	case ETHTOOL_GRXCLSRLALL:
 		ret = bcm_sf2_cfp_rule_get_all(priv, port, nfc, rule_locs);
diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h
index 49695fcc2ea8..3ccd5a865dcb 100644
--- a/drivers/net/dsa/bcm_sf2_regs.h
+++ b/drivers/net/dsa/bcm_sf2_regs.h
@@ -115,6 +115,24 @@ enum bcm_sf2_reg_offs {
 #define P7_IRQ_OFF			0
 #define P_IRQ_OFF(x)			((6 - (x)) * P_NUM_IRQ)
 
+/* Register set relative to 'ACB' */
+#define ACB_CONTROL			0x00
+#define  ACB_EN				(1 << 0)
+#define  ACB_ALGORITHM			(1 << 1)
+#define  ACB_FLUSH_SHIFT		2
+#define  ACB_FLUSH_MASK			0x3
+
+#define ACB_QUEUE_0_CFG			0x08
+#define  XOFF_THRESHOLD_MASK		0x7ff
+#define  XON_EN				(1 << 11)
+#define  TOTAL_XOFF_THRESHOLD_SHIFT	12
+#define  TOTAL_XOFF_THRESHOLD_MASK	0x7ff
+#define  TOTAL_XOFF_EN			(1 << 23)
+#define  TOTAL_XON_EN			(1 << 24)
+#define  PKTLEN_SHIFT			25
+#define  PKTLEN_MASK			0x3f
+#define ACB_QUEUE_CFG(x)		(ACB_QUEUE_0_CFG + ((x) * 0x4))
+
 /* Register set relative to 'CORE' */
 #define CORE_G_PCTL_PORT0		0x00000
 #define CORE_G_PCTL_PORT(x)		(CORE_G_PCTL_PORT0 + (x * 0x4))
@@ -205,16 +223,8 @@ enum bcm_sf2_reg_offs {
 
 #define CORE_IMP0_PRT_ID		0x0804
 
-#define CORE_BRCM_HDR_CTRL		0x0080c
-#define  BRCM_HDR_EN_P8			(1 << 0)
-#define  BRCM_HDR_EN_P5			(1 << 1)
-#define  BRCM_HDR_EN_P7			(1 << 2)
-
 #define CORE_RST_MIB_CNT_EN		0x0950
 
-#define CORE_BRCM_HDR_RX_DIS		0x0980
-#define CORE_BRCM_HDR_TX_DIS		0x0988
-
 #define CORE_ARLA_VTBL_RWCTRL		0x1600
 #define  ARLA_VTBL_CMD_WRITE		0
 #define  ARLA_VTBL_CMD_READ		1
@@ -245,6 +255,11 @@ enum bcm_sf2_reg_offs {
 #define CORE_PORT_VLAN_CTL_PORT(x)	(0xc400 + ((x) * 0x8))
 #define  PORT_VLAN_CTRL_MASK		0x1ff
 
+#define CORE_TXQ_THD_PAUSE_QN_PORT_0	0x2c80
+#define  TXQ_PAUSE_THD_MASK		0x7ff
+#define CORE_TXQ_THD_PAUSE_QN_PORT(x)	(CORE_TXQ_THD_PAUSE_QN_PORT_0 + \
+					(x) * 0x8)
+
 #define CORE_DEFAULT_1Q_TAG_P(x)	(0xd040 + ((x) * 8))
 #define  CFI_SHIFT			12
 #define  PRI_SHIFT			13
@@ -252,9 +267,6 @@ enum bcm_sf2_reg_offs {
 
 #define CORE_JOIN_ALL_VLAN_EN		0xd140
 
-#define CORE_EEE_EN_CTRL		0x24800
-#define CORE_EEE_LPI_INDICATE		0x24810
-
 #define CORE_CFP_ACC			0x28000
 #define  OP_STR_DONE			(1 << 0)
 #define  OP_SEL_SHIFT			1
@@ -290,14 +302,18 @@ enum bcm_sf2_reg_offs {
 /* UDF_DATA7 */
 #define L3_FRAMING_SHIFT		24
 #define L3_FRAMING_MASK			(0x3 << L3_FRAMING_SHIFT)
+#define IPTOS_SHIFT			16
+#define IPTOS_MASK			0xff
 #define IPPROTO_SHIFT			8
 #define IPPROTO_MASK			(0xff << IPPROTO_SHIFT)
-#define IP_FRAG				(1 << 7)
+#define IP_FRAG_SHIFT			7
+#define IP_FRAG				(1 << IP_FRAG_SHIFT)
 
 /* UDF_DATA0 */
 #define  SLICE_VALID			3
 #define  SLICE_NUM_SHIFT		2
 #define  SLICE_NUM(x)			((x) << SLICE_NUM_SHIFT)
+#define  SLICE_NUM_MASK			0x3
 
 #define CORE_CFP_MASK_PORT_0		0x280c0
 
@@ -393,8 +409,15 @@ enum bcm_sf2_reg_offs {
 #define  CFG_UDF_EOL2			(2 << CFG_UDF_OFFSET_BASE_SHIFT)
 #define  CFG_UDF_EOL3			(3 << CFG_UDF_OFFSET_BASE_SHIFT)
 
+/* IPv6 slices */
+#define CORE_UDF_0_B_0_8_PORT_0		0x28500
+
+/* IPv6 chained slices */
+#define CORE_UDF_0_D_0_11_PORT_0	0x28680
+
 /* Number of slices for IPv4, IPv6 and non-IP */
-#define UDF_NUM_SLICES			9
+#define UDF_NUM_SLICES			4
+#define UDFS_PER_SLICE			9
 
 /* Spacing between different slices */
 #define UDF_SLICE_OFFSET		0x40
diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index d55051abf4ed..3a3f4f7ba364 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -110,13 +110,6 @@ static void dsa_loop_get_ethtool_stats(struct dsa_switch *ds, int port,
 		data[i] = ps->ports[port].mib[i].val;
 }
 
-static int dsa_loop_set_addr(struct dsa_switch *ds, u8 *addr)
-{
-	dev_dbg(ds->dev, "%s\n", __func__);
-
-	return 0;
-}
-
 static int dsa_loop_phy_read(struct dsa_switch *ds, int port, int regnum)
 {
 	struct dsa_loop_priv *ps = ds->priv;
@@ -263,7 +256,6 @@ static const struct dsa_switch_ops dsa_loop_driver = {
 	.get_strings		= dsa_loop_get_strings,
 	.get_ethtool_stats	= dsa_loop_get_ethtool_stats,
 	.get_sset_count		= dsa_loop_get_sset_count,
-	.set_addr		= dsa_loop_set_addr,
 	.phy_read		= dsa_loop_phy_read,
 	.phy_write		= dsa_loop_phy_write,
 	.port_bridge_join	= dsa_loop_port_bridge_join,
diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c
index b471413d3df9..c4afc8f1a66d 100644
--- a/drivers/net/dsa/lan9303-core.c
+++ b/drivers/net/dsa/lan9303-core.c
@@ -17,6 +17,9 @@
 #include <linux/regmap.h>
 #include <linux/mutex.h>
 #include <linux/mii.h>
+#include <linux/phy.h>
+#include <linux/if_bridge.h>
+#include <linux/etherdevice.h>
 
 #include "lan9303.h"
 
@@ -57,6 +60,7 @@
 #define LAN9303_SWITCH_CSR_CMD_LANES (BIT(19) | BIT(18) | BIT(17) | BIT(16))
 #define LAN9303_VIRT_PHY_BASE 0x70
 #define LAN9303_VIRT_SPECIAL_CTRL 0x77
+#define  LAN9303_VIRT_SPECIAL_TURBO BIT(10) /*Turbo MII Enable*/
 
 /*13.4 Switch Fabric Control and Status Registers
  * Accessed indirectly via SWITCH_CSR_CMD, SWITCH_CSR_DATA.
@@ -121,6 +125,21 @@
 #define LAN9303_MAC_RX_CFG_2 0x0c01
 #define LAN9303_MAC_TX_CFG_2 0x0c40
 #define LAN9303_SWE_ALR_CMD 0x1800
+# define LAN9303_ALR_CMD_MAKE_ENTRY    BIT(2)
+# define LAN9303_ALR_CMD_GET_FIRST     BIT(1)
+# define LAN9303_ALR_CMD_GET_NEXT      BIT(0)
+#define LAN9303_SWE_ALR_WR_DAT_0 0x1801
+#define LAN9303_SWE_ALR_WR_DAT_1 0x1802
+# define LAN9303_ALR_DAT1_VALID        BIT(26)
+# define LAN9303_ALR_DAT1_END_OF_TABL  BIT(25)
+# define LAN9303_ALR_DAT1_AGE_OVERRID  BIT(25)
+# define LAN9303_ALR_DAT1_STATIC       BIT(24)
+# define LAN9303_ALR_DAT1_PORT_BITOFFS  16
+# define LAN9303_ALR_DAT1_PORT_MASK    (7 << LAN9303_ALR_DAT1_PORT_BITOFFS)
+#define LAN9303_SWE_ALR_RD_DAT_0 0x1805
+#define LAN9303_SWE_ALR_RD_DAT_1 0x1806
+#define LAN9303_SWE_ALR_CMD_STS 0x1808
+# define ALR_STS_MAKE_PEND     BIT(0)
 #define LAN9303_SWE_VLAN_CMD 0x180b
 # define LAN9303_SWE_VLAN_CMD_RNW BIT(5)
 # define LAN9303_SWE_VLAN_CMD_PVIDNVLAN BIT(4)
@@ -144,6 +163,7 @@
 # define LAN9303_SWE_PORT_STATE_FORWARDING_PORT0 (0)
 # define LAN9303_SWE_PORT_STATE_LEARNING_PORT0 BIT(1)
 # define LAN9303_SWE_PORT_STATE_BLOCKING_PORT0 BIT(0)
+# define LAN9303_SWE_PORT_STATE_DISABLED_PORT0 (3)
 #define LAN9303_SWE_PORT_MIRROR 0x1846
 # define LAN9303_SWE_PORT_MIRROR_SNIFF_ALL BIT(8)
 # define LAN9303_SWE_PORT_MIRROR_SNIFFER_PORT2 BIT(7)
@@ -154,7 +174,9 @@
 # define LAN9303_SWE_PORT_MIRROR_MIRRORED_PORT0 BIT(2)
 # define LAN9303_SWE_PORT_MIRROR_ENABLE_RX_MIRRORING BIT(1)
 # define LAN9303_SWE_PORT_MIRROR_ENABLE_TX_MIRRORING BIT(0)
+# define LAN9303_SWE_PORT_MIRROR_DISABLED 0
 #define LAN9303_SWE_INGRESS_PORT_TYPE 0x1847
+#define  LAN9303_SWE_INGRESS_PORT_TYPE_VLAN 3
 #define LAN9303_BM_CFG 0x1c00
 #define LAN9303_BM_EGRSS_PORT_TYPE 0x1c0c
 # define LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT2 (BIT(17) | BIT(16))
@@ -472,6 +494,220 @@ static int lan9303_detect_phy_setup(struct lan9303 *chip)
 	return 0;
 }
 
+/* Map ALR-port bits to port bitmap, and back */
+static const int alrport_2_portmap[] = {1, 2, 4, 0, 3, 5, 6, 7 };
+static const int portmap_2_alrport[] = {3, 0, 1, 4, 2, 5, 6, 7 };
+
+/* Return pointer to first free ALR cache entry, return NULL if none */
+static struct lan9303_alr_cache_entry *
+lan9303_alr_cache_find_free(struct lan9303 *chip)
+{
+	int i;
+	struct lan9303_alr_cache_entry *entr = chip->alr_cache;
+
+	for (i = 0; i < LAN9303_NUM_ALR_RECORDS; i++, entr++)
+		if (entr->port_map == 0)
+			return entr;
+
+	return NULL;
+}
+
+/* Return pointer to ALR cache entry matching MAC address */
+static struct lan9303_alr_cache_entry *
+lan9303_alr_cache_find_mac(struct lan9303 *chip, const u8 *mac_addr)
+{
+	int i;
+	struct lan9303_alr_cache_entry *entr = chip->alr_cache;
+
+	BUILD_BUG_ON_MSG(sizeof(struct lan9303_alr_cache_entry) & 1,
+			 "ether_addr_equal require u16 alignment");
+
+	for (i = 0; i < LAN9303_NUM_ALR_RECORDS; i++, entr++)
+		if (ether_addr_equal(entr->mac_addr, mac_addr))
+			return entr;
+
+	return NULL;
+}
+
+/* Wait a while until mask & reg == value. Otherwise return timeout. */
+static int lan9303_csr_reg_wait(struct lan9303 *chip, int regno,
+				int mask, char value)
+{
+	int i;
+
+	for (i = 0; i < 0x1000; i++) {
+		u32 reg;
+
+		lan9303_read_switch_reg(chip, regno, &reg);
+		if ((reg & mask) == value)
+			return 0;
+		usleep_range(1000, 2000);
+	}
+	return -ETIMEDOUT;
+}
+
+static int lan9303_alr_make_entry_raw(struct lan9303 *chip, u32 dat0, u32 dat1)
+{
+	lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_WR_DAT_0, dat0);
+	lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_WR_DAT_1, dat1);
+	lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_CMD,
+				 LAN9303_ALR_CMD_MAKE_ENTRY);
+	lan9303_csr_reg_wait(chip, LAN9303_SWE_ALR_CMD_STS, ALR_STS_MAKE_PEND,
+			     0);
+	lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_CMD, 0);
+
+	return 0;
+}
+
+typedef void alr_loop_cb_t(struct lan9303 *chip, u32 dat0, u32 dat1,
+			   int portmap, void *ctx);
+
+static void lan9303_alr_loop(struct lan9303 *chip, alr_loop_cb_t *cb, void *ctx)
+{
+	int i;
+
+	lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_CMD,
+				 LAN9303_ALR_CMD_GET_FIRST);
+	lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_CMD, 0);
+
+	for (i = 1; i < LAN9303_NUM_ALR_RECORDS; i++) {
+		u32 dat0, dat1;
+		int alrport, portmap;
+
+		lan9303_read_switch_reg(chip, LAN9303_SWE_ALR_RD_DAT_0, &dat0);
+		lan9303_read_switch_reg(chip, LAN9303_SWE_ALR_RD_DAT_1, &dat1);
+		if (dat1 & LAN9303_ALR_DAT1_END_OF_TABL)
+			break;
+
+		alrport = (dat1 & LAN9303_ALR_DAT1_PORT_MASK) >>
+						LAN9303_ALR_DAT1_PORT_BITOFFS;
+		portmap = alrport_2_portmap[alrport];
+
+		cb(chip, dat0, dat1, portmap, ctx);
+
+		lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_CMD,
+					 LAN9303_ALR_CMD_GET_NEXT);
+		lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_CMD, 0);
+	}
+}
+
+static void alr_reg_to_mac(u32 dat0, u32 dat1, u8 mac[6])
+{
+	mac[0] = (dat0 >>  0) & 0xff;
+	mac[1] = (dat0 >>  8) & 0xff;
+	mac[2] = (dat0 >> 16) & 0xff;
+	mac[3] = (dat0 >> 24) & 0xff;
+	mac[4] = (dat1 >>  0) & 0xff;
+	mac[5] = (dat1 >>  8) & 0xff;
+}
+
+struct del_port_learned_ctx {
+	int port;
+};
+
+/* Clear learned (non-static) entry on given port */
+static void alr_loop_cb_del_port_learned(struct lan9303 *chip, u32 dat0,
+					 u32 dat1, int portmap, void *ctx)
+{
+	struct del_port_learned_ctx *del_ctx = ctx;
+	int port = del_ctx->port;
+
+	if (((BIT(port) & portmap) == 0) || (dat1 & LAN9303_ALR_DAT1_STATIC))
+		return;
+
+	/* learned entries has only one port, we can just delete */
+	dat1 &= ~LAN9303_ALR_DAT1_VALID; /* delete entry */
+	lan9303_alr_make_entry_raw(chip, dat0, dat1);
+}
+
+struct port_fdb_dump_ctx {
+	int port;
+	void *data;
+	dsa_fdb_dump_cb_t *cb;
+};
+
+static void alr_loop_cb_fdb_port_dump(struct lan9303 *chip, u32 dat0,
+				      u32 dat1, int portmap, void *ctx)
+{
+	struct port_fdb_dump_ctx *dump_ctx = ctx;
+	u8 mac[ETH_ALEN];
+	bool is_static;
+
+	if ((BIT(dump_ctx->port) & portmap) == 0)
+		return;
+
+	alr_reg_to_mac(dat0, dat1, mac);
+	is_static = !!(dat1 & LAN9303_ALR_DAT1_STATIC);
+	dump_ctx->cb(mac, 0, is_static, dump_ctx->data);
+}
+
+/* Set a static ALR entry. Delete entry if port_map is zero */
+static void lan9303_alr_set_entry(struct lan9303 *chip, const u8 *mac,
+				  u8 port_map, bool stp_override)
+{
+	u32 dat0, dat1, alr_port;
+
+	dev_dbg(chip->dev, "%s(%pM, %d)\n", __func__, mac, port_map);
+	dat1 = LAN9303_ALR_DAT1_STATIC;
+	if (port_map)
+		dat1 |= LAN9303_ALR_DAT1_VALID;
+	/* otherwise no ports: delete entry */
+	if (stp_override)
+		dat1 |= LAN9303_ALR_DAT1_AGE_OVERRID;
+
+	alr_port = portmap_2_alrport[port_map & 7];
+	dat1 &= ~LAN9303_ALR_DAT1_PORT_MASK;
+	dat1 |= alr_port << LAN9303_ALR_DAT1_PORT_BITOFFS;
+
+	dat0 = 0;
+	dat0 |= (mac[0] << 0);
+	dat0 |= (mac[1] << 8);
+	dat0 |= (mac[2] << 16);
+	dat0 |= (mac[3] << 24);
+
+	dat1 |= (mac[4] << 0);
+	dat1 |= (mac[5] << 8);
+
+	lan9303_alr_make_entry_raw(chip, dat0, dat1);
+}
+
+/* Add port to static ALR entry, create new static entry if needed */
+static int lan9303_alr_add_port(struct lan9303 *chip, const u8 *mac, int port,
+				bool stp_override)
+{
+	struct lan9303_alr_cache_entry *entr;
+
+	entr = lan9303_alr_cache_find_mac(chip, mac);
+	if (!entr) { /*New entry */
+		entr = lan9303_alr_cache_find_free(chip);
+		if (!entr)
+			return -ENOSPC;
+		ether_addr_copy(entr->mac_addr, mac);
+	}
+	entr->port_map |= BIT(port);
+	entr->stp_override = stp_override;
+	lan9303_alr_set_entry(chip, mac, entr->port_map, stp_override);
+
+	return 0;
+}
+
+/* Delete static port from ALR entry, delete entry if last port */
+static int lan9303_alr_del_port(struct lan9303 *chip, const u8 *mac, int port)
+{
+	struct lan9303_alr_cache_entry *entr;
+
+	entr = lan9303_alr_cache_find_mac(chip, mac);
+	if (!entr)
+		return 0;  /* no static entry found */
+
+	entr->port_map &= ~BIT(port);
+	if (entr->port_map == 0) /* zero means its free again */
+		eth_zero_addr(&entr->port_map);
+	lan9303_alr_set_entry(chip, mac, entr->port_map, entr->stp_override);
+
+	return 0;
+}
+
 static int lan9303_disable_processing_port(struct lan9303 *chip,
 					   unsigned int port)
 {
@@ -508,16 +744,36 @@ static int lan9303_enable_processing_port(struct lan9303 *chip,
 				LAN9303_MAC_TX_CFG_X_TX_ENABLE);
 }
 
+/* forward special tagged packets from port 0 to port 1 *or* port 2 */
+static int lan9303_setup_tagging(struct lan9303 *chip)
+{
+	int ret;
+	u32 val;
+	/* enable defining the destination port via special VLAN tagging
+	 * for port 0
+	 */
+	ret = lan9303_write_switch_reg(chip, LAN9303_SWE_INGRESS_PORT_TYPE,
+				       LAN9303_SWE_INGRESS_PORT_TYPE_VLAN);
+	if (ret)
+		return ret;
+
+	/* tag incoming packets at port 1 and 2 on their way to port 0 to be
+	 * able to discover their source port
+	 */
+	val = LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT0;
+	return lan9303_write_switch_reg(chip, LAN9303_BM_EGRSS_PORT_TYPE, val);
+}
+
 /* We want a special working switch:
  * - do not forward packets between port 1 and 2
  * - forward everything from port 1 to port 0
  * - forward everything from port 2 to port 0
- * - forward special tagged packets from port 0 to port 1 *or* port 2
  */
 static int lan9303_separate_ports(struct lan9303 *chip)
 {
 	int ret;
 
+	lan9303_alr_del_port(chip, eth_stp_addr, 0);
 	ret = lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_MIRROR,
 				LAN9303_SWE_PORT_MIRROR_SNIFFER_PORT0 |
 				LAN9303_SWE_PORT_MIRROR_MIRRORED_PORT1 |
@@ -527,22 +783,6 @@ static int lan9303_separate_ports(struct lan9303 *chip)
 	if (ret)
 		return ret;
 
-	/* enable defining the destination port via special VLAN tagging
-	 * for port 0
-	 */
-	ret = lan9303_write_switch_reg(chip, LAN9303_SWE_INGRESS_PORT_TYPE,
-				       0x03);
-	if (ret)
-		return ret;
-
-	/* tag incoming packets at port 1 and 2 on their way to port 0 to be
-	 * able to discover their source port
-	 */
-	ret = lan9303_write_switch_reg(chip, LAN9303_BM_EGRSS_PORT_TYPE,
-			LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT0);
-	if (ret)
-		return ret;
-
 	/* prevent port 1 and 2 from forwarding packets by their own */
 	return lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_STATE,
 				LAN9303_SWE_PORT_STATE_FORWARDING_PORT0 |
@@ -550,6 +790,17 @@ static int lan9303_separate_ports(struct lan9303 *chip)
 				LAN9303_SWE_PORT_STATE_BLOCKING_PORT2);
 }
 
+static void lan9303_bridge_ports(struct lan9303 *chip)
+{
+	/* ports bridged: remove mirroring */
+	lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_MIRROR,
+				 LAN9303_SWE_PORT_MIRROR_DISABLED);
+
+	lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_STATE,
+				 chip->swe_port_state);
+	lan9303_alr_add_port(chip, eth_stp_addr, 0, true);
+}
+
 static int lan9303_handle_reset(struct lan9303 *chip)
 {
 	if (!chip->reset_gpio)
@@ -569,7 +820,7 @@ static int lan9303_disable_processing(struct lan9303 *chip)
 {
 	int p;
 
-	for (p = 0; p < LAN9303_NUM_PORTS; p++) {
+	for (p = 1; p < LAN9303_NUM_PORTS; p++) {
 		int ret = lan9303_disable_processing_port(chip, p);
 
 		if (ret)
@@ -642,6 +893,10 @@ static int lan9303_setup(struct dsa_switch *ds)
 		return -EINVAL;
 	}
 
+	ret = lan9303_setup_tagging(chip);
+	if (ret)
+		dev_err(chip->dev, "failed to setup port tagging %d\n", ret);
+
 	ret = lan9303_separate_ports(chip);
 	if (ret)
 		dev_err(chip->dev, "failed to separate ports %d\n", ret);
@@ -760,6 +1015,43 @@ static int lan9303_phy_write(struct dsa_switch *ds, int phy, int regnum,
 	return chip->ops->phy_write(chip, phy, regnum, val);
 }
 
+static void lan9303_adjust_link(struct dsa_switch *ds, int port,
+				struct phy_device *phydev)
+{
+	struct lan9303 *chip = ds->priv;
+	int ctl, res;
+
+	if (!phy_is_pseudo_fixed_link(phydev))
+		return;
+
+	ctl = lan9303_phy_read(ds, port, MII_BMCR);
+
+	ctl &= ~BMCR_ANENABLE;
+
+	if (phydev->speed == SPEED_100)
+		ctl |= BMCR_SPEED100;
+	else if (phydev->speed == SPEED_10)
+		ctl &= ~BMCR_SPEED100;
+	else
+		dev_err(ds->dev, "unsupported speed: %d\n", phydev->speed);
+
+	if (phydev->duplex == DUPLEX_FULL)
+		ctl |= BMCR_FULLDPLX;
+	else
+		ctl &= ~BMCR_FULLDPLX;
+
+	res =  lan9303_phy_write(ds, port, MII_BMCR, ctl);
+
+	if (port == chip->phy_addr_sel_strap) {
+		/* Virtual Phy: Remove Turbo 200Mbit mode */
+		lan9303_read(chip->regmap, LAN9303_VIRT_SPECIAL_CTRL, &ctl);
+
+		ctl &= ~LAN9303_VIRT_SPECIAL_TURBO;
+		res =  regmap_write(chip->regmap,
+				    LAN9303_VIRT_SPECIAL_CTRL, ctl);
+	}
+}
+
 static int lan9303_port_enable(struct dsa_switch *ds, int port,
 			       struct phy_device *phy)
 {
@@ -797,16 +1089,189 @@ static void lan9303_port_disable(struct dsa_switch *ds, int port,
 	}
 }
 
+static int lan9303_port_bridge_join(struct dsa_switch *ds, int port,
+				    struct net_device *br)
+{
+	struct lan9303 *chip = ds->priv;
+
+	dev_dbg(chip->dev, "%s(port %d)\n", __func__, port);
+	if (dsa_to_port(ds, 1)->bridge_dev == dsa_to_port(ds, 2)->bridge_dev) {
+		lan9303_bridge_ports(chip);
+		chip->is_bridged = true;  /* unleash stp_state_set() */
+	}
+
+	return 0;
+}
+
+static void lan9303_port_bridge_leave(struct dsa_switch *ds, int port,
+				      struct net_device *br)
+{
+	struct lan9303 *chip = ds->priv;
+
+	dev_dbg(chip->dev, "%s(port %d)\n", __func__, port);
+	if (chip->is_bridged) {
+		lan9303_separate_ports(chip);
+		chip->is_bridged = false;
+	}
+}
+
+static void lan9303_port_stp_state_set(struct dsa_switch *ds, int port,
+				       u8 state)
+{
+	int portmask, portstate;
+	struct lan9303 *chip = ds->priv;
+
+	dev_dbg(chip->dev, "%s(port %d, state %d)\n",
+		__func__, port, state);
+
+	switch (state) {
+	case BR_STATE_DISABLED:
+		portstate = LAN9303_SWE_PORT_STATE_DISABLED_PORT0;
+		break;
+	case BR_STATE_BLOCKING:
+	case BR_STATE_LISTENING:
+		portstate = LAN9303_SWE_PORT_STATE_BLOCKING_PORT0;
+		break;
+	case BR_STATE_LEARNING:
+		portstate = LAN9303_SWE_PORT_STATE_LEARNING_PORT0;
+		break;
+	case BR_STATE_FORWARDING:
+		portstate = LAN9303_SWE_PORT_STATE_FORWARDING_PORT0;
+		break;
+	default:
+		portstate = LAN9303_SWE_PORT_STATE_DISABLED_PORT0;
+		dev_err(chip->dev, "unknown stp state: port %d, state %d\n",
+			port, state);
+	}
+
+	portmask = 0x3 << (port * 2);
+	portstate <<= (port * 2);
+
+	chip->swe_port_state = (chip->swe_port_state & ~portmask) | portstate;
+
+	if (chip->is_bridged)
+		lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_STATE,
+					 chip->swe_port_state);
+	/* else: touching SWE_PORT_STATE would break port separation */
+}
+
+static void lan9303_port_fast_age(struct dsa_switch *ds, int port)
+{
+	struct lan9303 *chip = ds->priv;
+	struct del_port_learned_ctx del_ctx = {
+		.port = port,
+	};
+
+	dev_dbg(chip->dev, "%s(%d)\n", __func__, port);
+	lan9303_alr_loop(chip, alr_loop_cb_del_port_learned, &del_ctx);
+}
+
+static int lan9303_port_fdb_add(struct dsa_switch *ds, int port,
+				const unsigned char *addr, u16 vid)
+{
+	struct lan9303 *chip = ds->priv;
+
+	dev_dbg(chip->dev, "%s(%d, %pM, %d)\n", __func__, port, addr, vid);
+	if (vid)
+		return -EOPNOTSUPP;
+
+	return lan9303_alr_add_port(chip, addr, port, false);
+}
+
+static int lan9303_port_fdb_del(struct dsa_switch *ds, int port,
+				const unsigned char *addr, u16 vid)
+
+{
+	struct lan9303 *chip = ds->priv;
+
+	dev_dbg(chip->dev, "%s(%d, %pM, %d)\n", __func__, port, addr, vid);
+	if (vid)
+		return -EOPNOTSUPP;
+	lan9303_alr_del_port(chip, addr, port);
+
+	return 0;
+}
+
+static int lan9303_port_fdb_dump(struct dsa_switch *ds, int port,
+				 dsa_fdb_dump_cb_t *cb, void *data)
+{
+	struct lan9303 *chip = ds->priv;
+	struct port_fdb_dump_ctx dump_ctx = {
+		.port = port,
+		.data = data,
+		.cb   = cb,
+	};
+
+	dev_dbg(chip->dev, "%s(%d)\n", __func__, port);
+	lan9303_alr_loop(chip, alr_loop_cb_fdb_port_dump, &dump_ctx);
+
+	return 0;
+}
+
+static int lan9303_port_mdb_prepare(struct dsa_switch *ds, int port,
+				    const struct switchdev_obj_port_mdb *mdb,
+				    struct switchdev_trans *trans)
+{
+	struct lan9303 *chip = ds->priv;
+
+	dev_dbg(chip->dev, "%s(%d, %pM, %d)\n", __func__, port, mdb->addr,
+		mdb->vid);
+	if (mdb->vid)
+		return -EOPNOTSUPP;
+	if (lan9303_alr_cache_find_mac(chip, mdb->addr))
+		return 0;
+	if (!lan9303_alr_cache_find_free(chip))
+		return -ENOSPC;
+
+	return 0;
+}
+
+static void lan9303_port_mdb_add(struct dsa_switch *ds, int port,
+				 const struct switchdev_obj_port_mdb *mdb,
+				 struct switchdev_trans *trans)
+{
+	struct lan9303 *chip = ds->priv;
+
+	dev_dbg(chip->dev, "%s(%d, %pM, %d)\n", __func__, port, mdb->addr,
+		mdb->vid);
+	lan9303_alr_add_port(chip, mdb->addr, port, false);
+}
+
+static int lan9303_port_mdb_del(struct dsa_switch *ds, int port,
+				const struct switchdev_obj_port_mdb *mdb)
+{
+	struct lan9303 *chip = ds->priv;
+
+	dev_dbg(chip->dev, "%s(%d, %pM, %d)\n", __func__, port, mdb->addr,
+		mdb->vid);
+	if (mdb->vid)
+		return -EOPNOTSUPP;
+	lan9303_alr_del_port(chip, mdb->addr, port);
+
+	return 0;
+}
+
 static const struct dsa_switch_ops lan9303_switch_ops = {
 	.get_tag_protocol = lan9303_get_tag_protocol,
 	.setup = lan9303_setup,
 	.get_strings = lan9303_get_strings,
 	.phy_read = lan9303_phy_read,
 	.phy_write = lan9303_phy_write,
+	.adjust_link = lan9303_adjust_link,
 	.get_ethtool_stats = lan9303_get_ethtool_stats,
 	.get_sset_count = lan9303_get_sset_count,
 	.port_enable = lan9303_port_enable,
 	.port_disable = lan9303_port_disable,
+	.port_bridge_join       = lan9303_port_bridge_join,
+	.port_bridge_leave      = lan9303_port_bridge_leave,
+	.port_stp_state_set     = lan9303_port_stp_state_set,
+	.port_fast_age          = lan9303_port_fast_age,
+	.port_fdb_add           = lan9303_port_fdb_add,
+	.port_fdb_del           = lan9303_port_fdb_del,
+	.port_fdb_dump          = lan9303_port_fdb_dump,
+	.port_mdb_prepare       = lan9303_port_mdb_prepare,
+	.port_mdb_add           = lan9303_port_mdb_add,
+	.port_mdb_del           = lan9303_port_mdb_del,
 };
 
 static int lan9303_register_switch(struct lan9303 *chip)
diff --git a/drivers/net/dsa/lan9303.h b/drivers/net/dsa/lan9303.h
index 7df2ac77fc8f..11f590b64701 100644
--- a/drivers/net/dsa/lan9303.h
+++ b/drivers/net/dsa/lan9303.h
@@ -3,26 +3,7 @@
 #include <linux/device.h>
 #include <net/dsa.h>
 
-struct lan9303;
-
-struct lan9303_phy_ops {
-	/* PHY 1 and 2 access*/
-	int	(*phy_read)(struct lan9303 *chip, int port, int regnum);
-	int	(*phy_write)(struct lan9303 *chip, int port,
-			     int regnum, u16 val);
-};
-
-struct lan9303 {
-	struct device *dev;
-	struct regmap *regmap;
-	struct regmap_irq_chip_data *irq_data;
-	struct gpio_desc *reset_gpio;
-	u32 reset_duration; /* in [ms] */
-	bool phy_addr_sel_strap;
-	struct dsa_switch *ds;
-	struct mutex indirect_mutex; /* protect indexed register access */
-	const struct lan9303_phy_ops *ops;
-};
+#include <linux/dsa/lan9303.h>
 
 extern const struct regmap_access_table lan9303_register_set;
 extern const struct lan9303_phy_ops lan9303_indirect_phy_ops;
diff --git a/drivers/net/dsa/lan9303_mdio.c b/drivers/net/dsa/lan9303_mdio.c
index fc16668a487f..0bc56b9900f9 100644
--- a/drivers/net/dsa/lan9303_mdio.c
+++ b/drivers/net/dsa/lan9303_mdio.c
@@ -67,14 +67,15 @@ static int lan9303_mdio_read(void *ctx, uint32_t reg, uint32_t *val)
 	return 0;
 }
 
-int lan9303_mdio_phy_write(struct lan9303 *chip, int phy, int reg, u16 val)
+static int lan9303_mdio_phy_write(struct lan9303 *chip, int phy, int reg,
+				  u16 val)
 {
 	struct lan9303_mdio *sw_dev = dev_get_drvdata(chip->dev);
 
 	return mdiobus_write_nested(sw_dev->device->bus, phy, reg, val);
 }
 
-int lan9303_mdio_phy_read(struct lan9303 *chip, int phy,  int reg)
+static int lan9303_mdio_phy_read(struct lan9303 *chip, int phy,  int reg)
 {
 	struct lan9303_mdio *sw_dev = dev_get_drvdata(chip->dev);
 
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index c142b97add2c..627c039f12ca 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -564,7 +564,8 @@ static int mt7530_phy_read(struct dsa_switch *ds, int port, int regnum)
 	return mdiobus_read_nested(priv->bus, port, regnum);
 }
 
-int mt7530_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val)
+static int mt7530_phy_write(struct dsa_switch *ds, int port, int regnum,
+			    u16 val)
 {
 	struct mt7530_priv *priv = ds->priv;
 
@@ -687,7 +688,7 @@ mt7530_cpu_port_enable(struct mt7530_priv *priv,
 	 * the switch
 	 */
 	mt7530_write(priv, MT7530_PCR_P(port),
-		     PCR_MATRIX(priv->ds->enabled_port_mask));
+		     PCR_MATRIX(dsa_user_ports(priv->ds)));
 
 	return 0;
 }
@@ -780,8 +781,8 @@ mt7530_port_bridge_join(struct dsa_switch *ds, int port,
 		 * same bridge. If the port is disabled, port matrix is kept
 		 * and not being setup until the port becomes enabled.
 		 */
-		if (ds->enabled_port_mask & BIT(i) && i != port) {
-			if (ds->ports[i].bridge_dev != bridge)
+		if (dsa_is_user_port(ds, i) && i != port) {
+			if (dsa_to_port(ds, i)->bridge_dev != bridge)
 				continue;
 			if (priv->ports[i].enable)
 				mt7530_set(priv, MT7530_PCR_P(i),
@@ -817,8 +818,8 @@ mt7530_port_bridge_leave(struct dsa_switch *ds, int port,
 		 * in the same bridge. If the port is disabled, port matrix
 		 * is kept and not being setup until the port becomes enabled.
 		 */
-		if (ds->enabled_port_mask & BIT(i) && i != port) {
-			if (ds->ports[i].bridge_dev != bridge)
+		if (dsa_is_user_port(ds, i) && i != port) {
+			if (dsa_to_port(ds, i)->bridge_dev != bridge)
 				continue;
 			if (priv->ports[i].enable)
 				mt7530_clear(priv, MT7530_PCR_P(i),
@@ -928,11 +929,11 @@ mt7530_setup(struct dsa_switch *ds)
 	struct device_node *dn;
 	struct mt7530_dummy_poll p;
 
-	/* The parent node of cpu_dp->netdev which holds the common system
+	/* The parent node of master netdev which holds the common system
 	 * controller also is the container for two GMACs nodes representing
 	 * as two netdev instances.
 	 */
-	dn = ds->dst->cpu_dp->netdev->dev.of_node->parent;
+	dn = ds->ports[MT7530_CPU_PORT].master->dev.of_node->parent;
 	priv->ethernet = syscon_node_to_regmap(dn);
 	if (IS_ERR(priv->ethernet))
 		return PTR_ERR(priv->ethernet);
diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index f123ed57630d..45768e3c5bc5 100644
--- a/drivers/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/etherdevice.h>
 #include <linux/jiffies.h>
 #include <linux/list.h>
 #include <linux/module.h>
@@ -174,9 +175,8 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p)
 	 */
 	REG_WRITE(addr, PORT_VLAN_MAP,
 		  ((p & 0xf) << PORT_VLAN_MAP_DBNUM_SHIFT) |
-		   (dsa_is_cpu_port(ds, p) ?
-			ds->enabled_port_mask :
-			BIT(ds->dst->cpu_dp->index)));
+		   (dsa_is_cpu_port(ds, p) ? dsa_user_ports(ds) :
+		    BIT(dsa_to_port(ds, p)->cpu_dp->index)));
 
 	/* Port Association Vector: when learning source addresses
 	 * of packets, add the address to the address database using
@@ -188,6 +188,27 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p)
 	return 0;
 }
 
+static int mv88e6060_setup_addr(struct dsa_switch *ds)
+{
+	u8 addr[ETH_ALEN];
+	u16 val;
+
+	eth_random_addr(addr);
+
+	val = addr[0] << 8 | addr[1];
+
+	/* The multicast bit is always transmitted as a zero, so the switch uses
+	 * bit 8 for "DiffAddr", where 0 means all ports transmit the same SA.
+	 */
+	val &= 0xfeff;
+
+	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, val);
+	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_23, (addr[2] << 8) | addr[3]);
+	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_45, (addr[4] << 8) | addr[5]);
+
+	return 0;
+}
+
 static int mv88e6060_setup(struct dsa_switch *ds)
 {
 	int ret;
@@ -203,6 +224,10 @@ static int mv88e6060_setup(struct dsa_switch *ds)
 	if (ret < 0)
 		return ret;
 
+	ret = mv88e6060_setup_addr(ds);
+	if (ret < 0)
+		return ret;
+
 	for (i = 0; i < MV88E6060_PORTS; i++) {
 		ret = mv88e6060_setup_port(ds, i);
 		if (ret < 0)
@@ -212,22 +237,6 @@ static int mv88e6060_setup(struct dsa_switch *ds)
 	return 0;
 }
 
-static int mv88e6060_set_addr(struct dsa_switch *ds, u8 *addr)
-{
-	u16 val = addr[0] << 8 | addr[1];
-
-	/* The multicast bit is always transmitted as a zero, so the switch uses
-	 * bit 8 for "DiffAddr", where 0 means all ports transmit the same SA.
-	 */
-	val &= 0xfeff;
-
-	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, val);
-	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_23, (addr[2] << 8) | addr[3]);
-	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_45, (addr[4] << 8) | addr[5]);
-
-	return 0;
-}
-
 static int mv88e6060_port_to_phy_addr(int port)
 {
 	if (port >= 0 && port < MV88E6060_PORTS)
@@ -262,7 +271,6 @@ static const struct dsa_switch_ops mv88e6060_switch_ops = {
 	.get_tag_protocol = mv88e6060_get_tag_protocol,
 	.probe		= mv88e6060_drv_probe,
 	.setup		= mv88e6060_setup,
-	.set_addr	= mv88e6060_set_addr,
 	.phy_read	= mv88e6060_phy_read,
 	.phy_write	= mv88e6060_phy_write,
 };
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index d74c7335c512..09a66d4d9492 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -851,7 +851,7 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port)
 	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i)
 		if (dsa_is_cpu_port(chip->ds, i) ||
 		    dsa_is_dsa_port(chip->ds, i) ||
-		    (br && chip->ds->ports[i].bridge_dev == br))
+		    (br && dsa_to_port(chip->ds, i)->bridge_dev == br))
 			pvlan |= BIT(i);
 
 	return pvlan;
@@ -932,6 +932,19 @@ static int mv88e6xxx_irl_setup(struct mv88e6xxx_chip *chip)
 	return 0;
 }
 
+static int mv88e6xxx_mac_setup(struct mv88e6xxx_chip *chip)
+{
+	if (chip->info->ops->set_switch_mac) {
+		u8 addr[ETH_ALEN];
+
+		eth_random_addr(addr);
+
+		return chip->info->ops->set_switch_mac(chip, addr);
+	}
+
+	return 0;
+}
+
 static int mv88e6xxx_pvt_map(struct mv88e6xxx_chip *chip, int dev, int port)
 {
 	u16 pvlan = 0;
@@ -1124,23 +1137,23 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port,
 			if (dsa_is_dsa_port(ds, i) || dsa_is_cpu_port(ds, i))
 				continue;
 
-			if (!ds->ports[port].netdev)
+			if (!ds->ports[port].slave)
 				continue;
 
 			if (vlan.member[i] ==
 			    MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_NON_MEMBER)
 				continue;
 
-			if (ds->ports[i].bridge_dev ==
+			if (dsa_to_port(ds, i)->bridge_dev ==
 			    ds->ports[port].bridge_dev)
 				break; /* same bridge, check next VLAN */
 
-			if (!ds->ports[i].bridge_dev)
+			if (!dsa_to_port(ds, i)->bridge_dev)
 				continue;
 
 			dev_err(ds->dev, "p%d: hw VLAN %d already used by %s\n",
 				port, vlan.vid,
-				netdev_name(ds->ports[i].bridge_dev));
+				netdev_name(dsa_to_port(ds, i)->bridge_dev));
 			err = -EOPNOTSUPP;
 			goto unlock;
 		}
@@ -1663,7 +1676,7 @@ static int mv88e6xxx_setup_port_mode(struct mv88e6xxx_chip *chip, int port)
 	if (dsa_is_dsa_port(chip->ds, port))
 		return mv88e6xxx_set_port_mode_dsa(chip, port);
 
-	if (dsa_is_normal_port(chip->ds, port))
+	if (dsa_is_user_port(chip->ds, port))
 		return mv88e6xxx_set_port_mode_normal(chip, port);
 
 	/* Setup CPU port mode depending on its supported tag format */
@@ -1992,6 +2005,9 @@ static int mv88e6xxx_setup(struct dsa_switch *ds)
 
 	/* Setup Switch Port Registers */
 	for (i = 0; i < mv88e6xxx_num_ports(chip); i++) {
+		if (dsa_is_unused_port(ds, i))
+			continue;
+
 		err = mv88e6xxx_setup_port(chip, i);
 		if (err)
 			goto unlock;
@@ -2013,6 +2029,10 @@ static int mv88e6xxx_setup(struct dsa_switch *ds)
 	if (err)
 		goto unlock;
 
+	err = mv88e6xxx_mac_setup(chip);
+	if (err)
+		goto unlock;
+
 	err = mv88e6xxx_phy_setup(chip);
 	if (err)
 		goto unlock;
@@ -2043,21 +2063,6 @@ unlock:
 	return err;
 }
 
-static int mv88e6xxx_set_addr(struct dsa_switch *ds, u8 *addr)
-{
-	struct mv88e6xxx_chip *chip = ds->priv;
-	int err;
-
-	if (!chip->info->ops->set_switch_mac)
-		return -EOPNOTSUPP;
-
-	mutex_lock(&chip->reg_lock);
-	err = chip->info->ops->set_switch_mac(chip, addr);
-	mutex_unlock(&chip->reg_lock);
-
-	return err;
-}
-
 static int mv88e6xxx_mdio_read(struct mii_bus *bus, int phy, int reg)
 {
 	struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv;
@@ -3785,7 +3790,6 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = {
 	.probe			= mv88e6xxx_drv_probe,
 	.get_tag_protocol	= mv88e6xxx_get_tag_protocol,
 	.setup			= mv88e6xxx_setup,
-	.set_addr		= mv88e6xxx_set_addr,
 	.adjust_link		= mv88e6xxx_adjust_link,
 	.get_strings		= mv88e6xxx_get_strings,
 	.get_ethtool_stats	= mv88e6xxx_get_ethtool_stats,
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index 5ada7a41449c..cf72e274275f 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -506,7 +506,7 @@ qca8k_setup(struct dsa_switch *ds)
 		pr_warn("regmap initialization failed");
 
 	/* Initialize CPU port pad mode (xMII type, delays...) */
-	phy_mode = of_get_phy_mode(ds->dst->cpu_dp->dn);
+	phy_mode = of_get_phy_mode(ds->ports[QCA8K_CPU_PORT].dn);
 	if (phy_mode < 0) {
 		pr_err("Can't find phy-mode for master device\n");
 		return phy_mode;
@@ -536,7 +536,7 @@ qca8k_setup(struct dsa_switch *ds)
 
 	/* Disable MAC by default on all user ports */
 	for (i = 1; i < QCA8K_NUM_PORTS; i++)
-		if (ds->enabled_port_mask & BIT(i))
+		if (dsa_is_user_port(ds, i))
 			qca8k_port_set_status(priv, i, 0);
 
 	/* Forward all unknown frames to CPU port for Linux processing */
@@ -551,12 +551,11 @@ qca8k_setup(struct dsa_switch *ds)
 		/* 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,
-				  ds->enabled_port_mask);
+				  QCA8K_PORT_LOOKUP_MEMBER, dsa_user_ports(ds));
 		}
 
 		/* Invividual user ports get connected to CPU port only */
-		if (ds->enabled_port_mask & BIT(i)) {
+		if (dsa_is_user_port(ds, i)) {
 			int shift = 16 * (i % 2);
 
 			qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i),
@@ -700,7 +699,7 @@ qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br)
 	int i;
 
 	for (i = 1; i < QCA8K_NUM_PORTS; i++) {
-		if (ds->ports[i].bridge_dev != br)
+		if (dsa_to_port(ds, i)->bridge_dev != br)
 			continue;
 		/* Add this port to the portvlan mask of the other ports
 		 * in the bridge
@@ -725,7 +724,7 @@ qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br)
 	int i;
 
 	for (i = 1; i < QCA8K_NUM_PORTS; i++) {
-		if (ds->ports[i].bridge_dev != br)
+		if (dsa_to_port(ds, i)->bridge_dev != br)
 			continue;
 		/* Remove this port to the portvlan mask of the other ports
 		 * in the bridge
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index d0a1f9ce3168..58483af80bdb 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -353,7 +353,7 @@ static void dummy_setup(struct net_device *dev)
 	eth_hw_addr_random(dev);
 
 	dev->min_mtu = 0;
-	dev->max_mtu = ETH_MAX_MTU;
+	dev->max_mtu = 0;
 }
 
 static int dummy_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -388,7 +388,7 @@ static int __init dummy_init_one(void)
 	int err;
 
 	dev_dummy = alloc_netdev(sizeof(struct dummy_priv),
-				 "dummy%d", NET_NAME_UNKNOWN, dummy_setup);
+				 "dummy%d", NET_NAME_ENUM, dummy_setup);
 	if (!dev_dummy)
 		return -ENOMEM;
 
diff --git a/drivers/net/eql.c b/drivers/net/eql.c
index fe13bfea30ac..fccce4b47778 100644
--- a/drivers/net/eql.c
+++ b/drivers/net/eql.c
@@ -178,10 +178,8 @@ static void __init eql_setup(struct net_device *dev)
 {
 	equalizer_t *eql = netdev_priv(dev);
 
-	init_timer(&eql->timer);
-	eql->timer.data     	= (unsigned long) eql;
+	setup_timer(&eql->timer, eql_timer, (unsigned long)eql);
 	eql->timer.expires  	= jiffies + EQL_DEFAULT_RESCHED_IVAL;
-	eql->timer.function 	= eql_timer;
 
 	spin_lock_init(&eql->queue.lock);
 	INIT_LIST_HEAD(&eql->queue.all_slaves);
diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c
index c5987f518cb2..b648e3f95c01 100644
--- a/drivers/net/ethernet/3com/3c515.c
+++ b/drivers/net/ethernet/3com/3c515.c
@@ -367,7 +367,7 @@ static struct net_device *corkscrew_scan(int unit);
 static int corkscrew_setup(struct net_device *dev, int ioaddr,
 			    struct pnp_dev *idev, int card_number);
 static int corkscrew_open(struct net_device *dev);
-static void corkscrew_timer(unsigned long arg);
+static void corkscrew_timer(struct timer_list *t);
 static netdev_tx_t corkscrew_start_xmit(struct sk_buff *skb,
 					struct net_device *dev);
 static int corkscrew_rx(struct net_device *dev);
@@ -627,7 +627,7 @@ static int corkscrew_setup(struct net_device *dev, int ioaddr,
 
 	spin_lock_init(&vp->lock);
 
-	setup_timer(&vp->timer, corkscrew_timer, (unsigned long) dev);
+	timer_setup(&vp->timer, corkscrew_timer, 0);
 
 	/* Read the station address from the EEPROM. */
 	EL3WINDOW(0);
@@ -869,11 +869,11 @@ static int corkscrew_open(struct net_device *dev)
 	return 0;
 }
 
-static void corkscrew_timer(unsigned long data)
+static void corkscrew_timer(struct timer_list *t)
 {
 #ifdef AUTOMEDIA
-	struct net_device *dev = (struct net_device *) data;
-	struct corkscrew_private *vp = netdev_priv(dev);
+	struct corkscrew_private *vp = from_timer(vp, t, timer);
+	struct net_device *dev = vp->our_dev;
 	int ioaddr = dev->base_addr;
 	unsigned long flags;
 	int ok = 0;
diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c
index 47c844cc9d27..48bc7fa0258c 100644
--- a/drivers/net/ethernet/3com/3c574_cs.c
+++ b/drivers/net/ethernet/3com/3c574_cs.c
@@ -225,7 +225,7 @@ static unsigned short read_eeprom(unsigned int ioaddr, int index);
 static void tc574_wait_for_completion(struct net_device *dev, int cmd);
 
 static void tc574_reset(struct net_device *dev);
-static void media_check(unsigned long arg);
+static void media_check(struct timer_list *t);
 static int el3_open(struct net_device *dev);
 static netdev_tx_t el3_start_xmit(struct sk_buff *skb,
 					struct net_device *dev);
@@ -377,7 +377,7 @@ static int tc574_config(struct pcmcia_device *link)
 		lp->autoselect = config & Autoselect ? 1 : 0;
 	}
 
-	init_timer(&lp->media);
+	timer_setup(&lp->media, media_check, 0);
 
 	{
 		int phy;
@@ -681,8 +681,6 @@ static int el3_open(struct net_device *dev)
 	netif_start_queue(dev);
 	
 	tc574_reset(dev);
-	lp->media.function = media_check;
-	lp->media.data = (unsigned long) dev;
 	lp->media.expires = jiffies + HZ;
 	add_timer(&lp->media);
 	
@@ -859,10 +857,10 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id)
 	(and as a last resort, poll the NIC for events), and to monitor
 	the MII, reporting changes in cable status.
 */
-static void media_check(unsigned long arg)
+static void media_check(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) arg;
-	struct el3_private *lp = netdev_priv(dev);
+	struct el3_private *lp = from_timer(lp, t, media);
+	struct net_device *dev = lp->p_dev->priv;
 	unsigned int ioaddr = dev->base_addr;
 	unsigned long flags;
 	unsigned short /* cable, */ media, partner;
diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c
index e28254a00599..2b2695311bda 100644
--- a/drivers/net/ethernet/3com/3c589_cs.c
+++ b/drivers/net/ethernet/3com/3c589_cs.c
@@ -163,7 +163,7 @@ static void tc589_release(struct pcmcia_device *link);
 
 static u16 read_eeprom(unsigned int ioaddr, int index);
 static void tc589_reset(struct net_device *dev);
-static void media_check(unsigned long arg);
+static void media_check(struct timer_list *t);
 static int el3_config(struct net_device *dev, struct ifmap *map);
 static int el3_open(struct net_device *dev);
 static netdev_tx_t el3_start_xmit(struct sk_buff *skb,
@@ -517,7 +517,7 @@ static int el3_open(struct net_device *dev)
 	netif_start_queue(dev);
 
 	tc589_reset(dev);
-	setup_timer(&lp->media, media_check, (unsigned long)dev);
+	timer_setup(&lp->media, media_check, 0);
 	mod_timer(&lp->media, jiffies + HZ);
 
 	dev_dbg(&link->dev, "%s: opened, status %4.4x.\n",
@@ -676,10 +676,10 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id)
 	return IRQ_RETVAL(handled);
 }
 
-static void media_check(unsigned long arg)
+static void media_check(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)(arg);
-	struct el3_private *lp = netdev_priv(dev);
+	struct el3_private *lp = from_timer(lp, t, media);
+	struct net_device *dev = lp->p_dev->priv;
 	unsigned int ioaddr = dev->base_addr;
 	u16 media, errs;
 	unsigned long flags;
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 402d9090ad29..f4e13a7014bd 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -759,8 +759,8 @@ static int vortex_open(struct net_device *dev);
 static void mdio_sync(struct vortex_private *vp, int bits);
 static int mdio_read(struct net_device *dev, int phy_id, int location);
 static void mdio_write(struct net_device *vp, int phy_id, int location, int value);
-static void vortex_timer(unsigned long arg);
-static void rx_oom_timer(unsigned long arg);
+static void vortex_timer(struct timer_list *t);
+static void rx_oom_timer(struct timer_list *t);
 static netdev_tx_t vortex_start_xmit(struct sk_buff *skb,
 				     struct net_device *dev);
 static netdev_tx_t boomerang_start_xmit(struct sk_buff *skb,
@@ -1599,9 +1599,9 @@ vortex_up(struct net_device *dev)
 				dev->name, media_tbl[dev->if_port].name);
 	}
 
-	setup_timer(&vp->timer, vortex_timer, (unsigned long)dev);
+	timer_setup(&vp->timer, vortex_timer, 0);
 	mod_timer(&vp->timer, RUN_AT(media_tbl[dev->if_port].wait));
-	setup_timer(&vp->rx_oom_timer, rx_oom_timer, (unsigned long)dev);
+	timer_setup(&vp->rx_oom_timer, rx_oom_timer, 0);
 
 	if (vortex_debug > 1)
 		pr_debug("%s: Initial media type %s.\n",
@@ -1784,10 +1784,10 @@ out:
 }
 
 static void
-vortex_timer(unsigned long data)
+vortex_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct vortex_private *vp = netdev_priv(dev);
+	struct vortex_private *vp = from_timer(vp, t, timer);
+	struct net_device *dev = vp->mii.dev;
 	void __iomem *ioaddr = vp->ioaddr;
 	int next_tick = 60*HZ;
 	int ok = 0;
@@ -2687,10 +2687,10 @@ boomerang_rx(struct net_device *dev)
  * for some memory.  Otherwise there is no way to restart the rx process.
  */
 static void
-rx_oom_timer(unsigned long arg)
+rx_oom_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)arg;
-	struct vortex_private *vp = netdev_priv(dev);
+	struct vortex_private *vp = from_timer(vp, t, rx_oom_timer);
+	struct net_device *dev = vp->mii.dev;
 
 	spin_lock_irq(&vp->lock);
 	if ((vp->cur_rx - vp->dirty_rx) == RX_RING_SIZE)	/* This test is redundant, but makes me feel good */
diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c
index 3da1fc539ef9..7bddb8efb6d5 100644
--- a/drivers/net/ethernet/8390/axnet_cs.c
+++ b/drivers/net/ethernet/8390/axnet_cs.c
@@ -85,7 +85,7 @@ static struct net_device_stats *get_stats(struct net_device *dev);
 static void set_multicast_list(struct net_device *dev);
 static void axnet_tx_timeout(struct net_device *dev);
 static irqreturn_t ei_irq_wrapper(int irq, void *dev_id);
-static void ei_watchdog(u_long arg);
+static void ei_watchdog(struct timer_list *t);
 static void axnet_reset_8390(struct net_device *dev);
 
 static int mdio_read(unsigned int addr, int phy_id, int loc);
@@ -483,7 +483,7 @@ static int axnet_open(struct net_device *dev)
     link->open++;
 
     info->link_status = 0x00;
-    setup_timer(&info->watchdog, ei_watchdog, (u_long)dev);
+    timer_setup(&info->watchdog, ei_watchdog, 0);
     mod_timer(&info->watchdog, jiffies + HZ);
 
     return ax_open(dev);
@@ -547,10 +547,10 @@ static irqreturn_t ei_irq_wrapper(int irq, void *dev_id)
     return ax_interrupt(irq, dev_id);
 }
 
-static void ei_watchdog(u_long arg)
+static void ei_watchdog(struct timer_list *t)
 {
-    struct net_device *dev = (struct net_device *)(arg);
-    struct axnet_dev *info = PRIV(dev);
+    struct axnet_dev *info = from_timer(info, t, watchdog);
+    struct net_device *dev = info->p_dev->priv;
     unsigned int nic_base = dev->base_addr;
     unsigned int mii_addr = nic_base + AXNET_MII_EEP;
     u_short link;
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index bd0a2a14b649..eae9827035dc 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -99,7 +99,7 @@ static int pcnet_open(struct net_device *dev);
 static int pcnet_close(struct net_device *dev);
 static int ei_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
 static irqreturn_t ei_irq_wrapper(int irq, void *dev_id);
-static void ei_watchdog(u_long arg);
+static void ei_watchdog(struct timer_list *t);
 static void pcnet_reset_8390(struct net_device *dev);
 static int set_config(struct net_device *dev, struct ifmap *map);
 static int setup_shmem_window(struct pcmcia_device *link, int start_pg,
@@ -917,7 +917,7 @@ static int pcnet_open(struct net_device *dev)
 
     info->phy_id = info->eth_phy;
     info->link_status = 0x00;
-    setup_timer(&info->watchdog, ei_watchdog, (u_long)dev);
+    timer_setup(&info->watchdog, ei_watchdog, 0);
     mod_timer(&info->watchdog, jiffies + HZ);
 
     return ei_open(dev);
@@ -1006,10 +1006,10 @@ static irqreturn_t ei_irq_wrapper(int irq, void *dev_id)
     return ret;
 }
 
-static void ei_watchdog(u_long arg)
+static void ei_watchdog(struct timer_list *t)
 {
-    struct net_device *dev = (struct net_device *)arg;
-    struct pcnet_dev *info = PRIV(dev);
+    struct pcnet_dev *info = from_timer(info, t, watchdog);
+    struct net_device *dev = info->p_dev->priv;
     unsigned int nic_base = dev->base_addr;
     unsigned int mii_addr = nic_base + DLINK_GPIO;
     u_short link;
diff --git a/drivers/net/ethernet/adi/bfin_mac.c b/drivers/net/ethernet/adi/bfin_mac.c
index a251de8d9a91..0658cde1586a 100644
--- a/drivers/net/ethernet/adi/bfin_mac.c
+++ b/drivers/net/ethernet/adi/bfin_mac.c
@@ -1650,9 +1650,8 @@ static int bfin_mac_probe(struct platform_device *pdev)
 	ndev->netdev_ops = &bfin_mac_netdev_ops;
 	ndev->ethtool_ops = &bfin_mac_ethtool_ops;
 
-	init_timer(&lp->tx_reclaim_timer);
-	lp->tx_reclaim_timer.data = (unsigned long)lp;
-	lp->tx_reclaim_timer.function = tx_reclaim_skb_timeout;
+	setup_timer(&lp->tx_reclaim_timer, tx_reclaim_skb_timeout,
+		    (unsigned long)lp);
 
 	lp->flags = 0;
 	netif_napi_add(ndev, &lp->napi, bfin_mac_poll, CONFIG_BFIN_RX_DESC_NUM);
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 54eff90e2f02..658e92f79d36 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -3624,11 +3624,10 @@ static int et131x_open(struct net_device *netdev)
 	int result;
 
 	/* Start the timer to track NIC errors */
-	init_timer(&adapter->error_timer);
+	setup_timer(&adapter->error_timer, et131x_error_timer_handler,
+		    (unsigned long)adapter);
 	adapter->error_timer.expires = jiffies +
 		msecs_to_jiffies(TX_ERROR_PERIOD);
-	adapter->error_timer.function = et131x_error_timer_handler;
-	adapter->error_timer.data = (unsigned long)adapter;
 	add_timer(&adapter->error_timer);
 
 	result = request_irq(irq, et131x_isr,
diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c
index 15a8096c60df..0b60921c392f 100644
--- a/drivers/net/ethernet/alacritech/slicoss.c
+++ b/drivers/net/ethernet/alacritech/slicoss.c
@@ -355,10 +355,10 @@ static void slic_xmit_complete(struct slic_device *sdev)
 {
 	struct slic_tx_queue *txq = &sdev->txq;
 	struct net_device *dev = sdev->netdev;
-	unsigned int idx = txq->done_idx;
 	struct slic_tx_buffer *buff;
 	unsigned int frames = 0;
 	unsigned int bytes = 0;
+	unsigned int idx;
 
 	/* Limit processing to SLIC_MAX_TX_COMPLETIONS frames to avoid that new
 	 * completions during processing keeps the loop running endlessly.
diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
index 305dc1996b4e..4532e574ebcd 100644
--- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
@@ -627,6 +627,12 @@ enum ena_admin_flow_hash_proto {
 
 	ENA_ADMIN_RSS_NOT_IP	= 7,
 
+	/* TCPv6 with extension header */
+	ENA_ADMIN_RSS_TCP6_EX	= 8,
+
+	/* IPv6 with extension header */
+	ENA_ADMIN_RSS_IP6_EX	= 9,
+
 	ENA_ADMIN_RSS_PROTO_NUM	= 16,
 };
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 52beba8c7a39..bf2de5298005 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -63,6 +63,8 @@
 
 #define ENA_REGS_ADMIN_INTR_MASK 1
 
+#define ENA_POLL_MS	5
+
 /*****************************************************************************/
 /*****************************************************************************/
 /*****************************************************************************/
@@ -315,7 +317,7 @@ static struct ena_comp_ctx *ena_com_submit_admin_cmd(struct ena_com_admin_queue
 					      cmd_size_in_bytes,
 					      comp,
 					      comp_size_in_bytes);
-	if (unlikely(IS_ERR(comp_ctx)))
+	if (IS_ERR(comp_ctx))
 		admin_queue->running_state = false;
 	spin_unlock_irqrestore(&admin_queue->q_lock, flags);
 
@@ -533,7 +535,7 @@ static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_c
 			goto err;
 		}
 
-		msleep(100);
+		msleep(ENA_POLL_MS);
 	}
 
 	if (unlikely(comp_ctx->status == ENA_CMD_ABORTED)) {
@@ -746,6 +748,9 @@ static int wait_for_reset_state(struct ena_com_dev *ena_dev, u32 timeout,
 {
 	u32 val, i;
 
+	/* Convert timeout from resolution of 100ms to ENA_POLL_MS */
+	timeout = (timeout * 100) / ENA_POLL_MS;
+
 	for (i = 0; i < timeout; i++) {
 		val = ena_com_reg_bar_read32(ena_dev, ENA_REGS_DEV_STS_OFF);
 
@@ -758,8 +763,7 @@ static int wait_for_reset_state(struct ena_com_dev *ena_dev, u32 timeout,
 			exp_state)
 			return 0;
 
-		/* The resolution of the timeout is 100ms */
-		msleep(100);
+		msleep(ENA_POLL_MS);
 	}
 
 	return -ETIME;
@@ -1130,7 +1134,7 @@ int ena_com_execute_admin_command(struct ena_com_admin_queue *admin_queue,
 
 	comp_ctx = ena_com_submit_admin_cmd(admin_queue, cmd, cmd_size,
 					    comp, comp_size);
-	if (unlikely(IS_ERR(comp_ctx))) {
+	if (IS_ERR(comp_ctx)) {
 		if (comp_ctx == ERR_PTR(-ENODEV))
 			pr_debug("Failed to submit command [%ld]\n",
 				 PTR_ERR(comp_ctx));
@@ -1253,7 +1257,7 @@ void ena_com_wait_for_abort_completion(struct ena_com_dev *ena_dev)
 	spin_lock_irqsave(&admin_queue->q_lock, flags);
 	while (atomic_read(&admin_queue->outstanding_cmds) != 0) {
 		spin_unlock_irqrestore(&admin_queue->q_lock, flags);
-		msleep(20);
+		msleep(ENA_POLL_MS);
 		spin_lock_irqsave(&admin_queue->q_lock, flags);
 	}
 	spin_unlock_irqrestore(&admin_queue->q_lock, flags);
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 967020fb26ee..060cb18fa659 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -60,8 +60,8 @@ struct ena_stats {
 
 static const struct ena_stats ena_stats_global_strings[] = {
 	ENA_STAT_GLOBAL_ENTRY(tx_timeout),
-	ENA_STAT_GLOBAL_ENTRY(io_suspend),
-	ENA_STAT_GLOBAL_ENTRY(io_resume),
+	ENA_STAT_GLOBAL_ENTRY(suspend),
+	ENA_STAT_GLOBAL_ENTRY(resume),
 	ENA_STAT_GLOBAL_ENTRY(wd_expired),
 	ENA_STAT_GLOBAL_ENTRY(interface_up),
 	ENA_STAT_GLOBAL_ENTRY(interface_down),
@@ -81,6 +81,7 @@ static const struct ena_stats ena_stats_tx_strings[] = {
 	ENA_STAT_TX_ENTRY(doorbells),
 	ENA_STAT_TX_ENTRY(prepare_ctx_err),
 	ENA_STAT_TX_ENTRY(bad_req_id),
+	ENA_STAT_TX_ENTRY(missed_tx),
 };
 
 static const struct ena_stats ena_stats_rx_strings[] = {
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index c6bd5e24005d..5417e4da64ca 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2361,38 +2361,6 @@ static const struct net_device_ops ena_netdev_ops = {
 #endif /* CONFIG_NET_POLL_CONTROLLER */
 };
 
-static void ena_device_io_suspend(struct work_struct *work)
-{
-	struct ena_adapter *adapter =
-		container_of(work, struct ena_adapter, suspend_io_task);
-	struct net_device *netdev = adapter->netdev;
-
-	/* ena_napi_disable_all disables only the IO handling.
-	 * We are still subject to AENQ keep alive watchdog.
-	 */
-	u64_stats_update_begin(&adapter->syncp);
-	adapter->dev_stats.io_suspend++;
-	u64_stats_update_begin(&adapter->syncp);
-	ena_napi_disable_all(adapter);
-	netif_tx_lock(netdev);
-	netif_device_detach(netdev);
-	netif_tx_unlock(netdev);
-}
-
-static void ena_device_io_resume(struct work_struct *work)
-{
-	struct ena_adapter *adapter =
-		container_of(work, struct ena_adapter, resume_io_task);
-	struct net_device *netdev = adapter->netdev;
-
-	u64_stats_update_begin(&adapter->syncp);
-	adapter->dev_stats.io_resume++;
-	u64_stats_update_end(&adapter->syncp);
-
-	netif_device_attach(netdev);
-	ena_napi_enable_all(adapter);
-}
-
 static int ena_device_validate_params(struct ena_adapter *adapter,
 				      struct ena_com_dev_get_features_ctx *get_feat_ctx)
 {
@@ -2561,38 +2529,31 @@ err_disable_msix:
 	return rc;
 }
 
-static void ena_fw_reset_device(struct work_struct *work)
+static void ena_destroy_device(struct ena_adapter *adapter)
 {
-	struct ena_com_dev_get_features_ctx get_feat_ctx;
-	struct ena_adapter *adapter =
-		container_of(work, struct ena_adapter, reset_task);
 	struct net_device *netdev = adapter->netdev;
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
-	struct pci_dev *pdev = adapter->pdev;
-	bool dev_up, wd_state;
-	int rc;
-
-	if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
-		dev_err(&pdev->dev,
-			"device reset schedule while reset bit is off\n");
-		return;
-	}
+	bool dev_up;
 
 	netif_carrier_off(netdev);
 
 	del_timer_sync(&adapter->timer_service);
 
-	rtnl_lock();
-
 	dev_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags);
+	adapter->dev_up_before_reset = dev_up;
+
 	ena_com_set_admin_running_state(ena_dev, false);
 
-	/* After calling ena_close the tx queues and the napi
-	 * are disabled so no one can interfere or touch the
-	 * data structures
-	 */
 	ena_close(netdev);
 
+	/* Before releasing the ENA resources, a device reset is required.
+	 * (to prevent the device from accessing them).
+	 * In case the reset flag is set and the device is up, ena_close
+	 * already perform the reset, so it can be skipped.
+	 */
+	if (!(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags) && dev_up))
+		ena_com_dev_reset(adapter->ena_dev, adapter->reset_reason);
+
 	ena_free_mgmnt_irq(adapter);
 
 	ena_disable_msix(adapter);
@@ -2606,9 +2567,17 @@ static void ena_fw_reset_device(struct work_struct *work)
 	ena_com_mmio_reg_read_request_destroy(ena_dev);
 
 	adapter->reset_reason = ENA_REGS_RESET_NORMAL;
+
 	clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+}
 
-	/* Finish with the destroy part. Start the init part */
+static int ena_restore_device(struct ena_adapter *adapter)
+{
+	struct ena_com_dev_get_features_ctx get_feat_ctx;
+	struct ena_com_dev *ena_dev = adapter->ena_dev;
+	struct pci_dev *pdev = adapter->pdev;
+	bool wd_state;
+	int rc;
 
 	rc = ena_device_init(ena_dev, adapter->pdev, &get_feat_ctx, &wd_state);
 	if (rc) {
@@ -2630,7 +2599,7 @@ static void ena_fw_reset_device(struct work_struct *work)
 		goto err_device_destroy;
 	}
 	/* If the interface was up before the reset bring it up */
-	if (dev_up) {
+	if (adapter->dev_up_before_reset) {
 		rc = ena_up(adapter);
 		if (rc) {
 			dev_err(&pdev->dev, "Failed to create I/O queues\n");
@@ -2639,24 +2608,38 @@ static void ena_fw_reset_device(struct work_struct *work)
 	}
 
 	mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ));
-
-	rtnl_unlock();
-
 	dev_err(&pdev->dev, "Device reset completed successfully\n");
 
-	return;
+	return rc;
 err_disable_msix:
 	ena_free_mgmnt_irq(adapter);
 	ena_disable_msix(adapter);
 err_device_destroy:
 	ena_com_admin_destroy(ena_dev);
 err:
-	rtnl_unlock();
-
 	clear_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags);
 
 	dev_err(&pdev->dev,
 		"Reset attempt failed. Can not reset the device\n");
+
+	return rc;
+}
+
+static void ena_fw_reset_device(struct work_struct *work)
+{
+	struct ena_adapter *adapter =
+		container_of(work, struct ena_adapter, reset_task);
+	struct pci_dev *pdev = adapter->pdev;
+
+	if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
+		dev_err(&pdev->dev,
+			"device reset schedule while reset bit is off\n");
+		return;
+	}
+	rtnl_lock();
+	ena_destroy_device(adapter);
+	ena_restore_device(adapter);
+	rtnl_unlock();
 }
 
 static int check_missing_comp_in_queue(struct ena_adapter *adapter,
@@ -2665,7 +2648,7 @@ static int check_missing_comp_in_queue(struct ena_adapter *adapter,
 	struct ena_tx_buffer *tx_buf;
 	unsigned long last_jiffies;
 	u32 missed_tx = 0;
-	int i;
+	int i, rc = 0;
 
 	for (i = 0; i < tx_ring->ring_size; i++) {
 		tx_buf = &tx_ring->tx_buffer_info[i];
@@ -2679,21 +2662,25 @@ static int check_missing_comp_in_queue(struct ena_adapter *adapter,
 
 			tx_buf->print_once = 1;
 			missed_tx++;
-
-			if (unlikely(missed_tx > adapter->missing_tx_completion_threshold)) {
-				netif_err(adapter, tx_err, adapter->netdev,
-					  "The number of lost tx completions is above the threshold (%d > %d). Reset the device\n",
-					  missed_tx,
-					  adapter->missing_tx_completion_threshold);
-				adapter->reset_reason =
-					ENA_REGS_RESET_MISS_TX_CMPL;
-				set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
-				return -EIO;
-			}
 		}
 	}
 
-	return 0;
+	if (unlikely(missed_tx > adapter->missing_tx_completion_threshold)) {
+		netif_err(adapter, tx_err, adapter->netdev,
+			  "The number of lost tx completions is above the threshold (%d > %d). Reset the device\n",
+			  missed_tx,
+			  adapter->missing_tx_completion_threshold);
+		adapter->reset_reason =
+			ENA_REGS_RESET_MISS_TX_CMPL;
+		set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+		rc = -EIO;
+	}
+
+	u64_stats_update_begin(&tx_ring->syncp);
+	tx_ring->tx_stats.missed_tx = missed_tx;
+	u64_stats_update_end(&tx_ring->syncp);
+
+	return rc;
 }
 
 static void check_for_missing_tx_completions(struct ena_adapter *adapter)
@@ -3276,8 +3263,6 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_rss;
 	}
 
-	INIT_WORK(&adapter->suspend_io_task, ena_device_io_suspend);
-	INIT_WORK(&adapter->resume_io_task, ena_device_io_resume);
 	INIT_WORK(&adapter->reset_task, ena_fw_reset_device);
 
 	adapter->last_keep_alive_jiffies = jiffies;
@@ -3311,8 +3296,6 @@ err_free_msix:
 err_worker_destroy:
 	ena_com_destroy_interrupt_moderation(ena_dev);
 	del_timer(&adapter->timer_service);
-	cancel_work_sync(&adapter->suspend_io_task);
-	cancel_work_sync(&adapter->resume_io_task);
 err_netdev_destroy:
 	free_netdev(netdev);
 err_device_destroy:
@@ -3382,10 +3365,6 @@ static void ena_remove(struct pci_dev *pdev)
 
 	cancel_work_sync(&adapter->reset_task);
 
-	cancel_work_sync(&adapter->suspend_io_task);
-
-	cancel_work_sync(&adapter->resume_io_task);
-
 	/* Reset the device only if the device is running. */
 	if (test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags))
 		ena_com_dev_reset(ena_dev, adapter->reset_reason);
@@ -3419,11 +3398,59 @@ static void ena_remove(struct pci_dev *pdev)
 	vfree(ena_dev);
 }
 
+#ifdef CONFIG_PM
+/* ena_suspend - PM suspend callback
+ * @pdev: PCI device information struct
+ * @state:power state
+ */
+static int ena_suspend(struct pci_dev *pdev,  pm_message_t state)
+{
+	struct ena_adapter *adapter = pci_get_drvdata(pdev);
+
+	u64_stats_update_begin(&adapter->syncp);
+	adapter->dev_stats.suspend++;
+	u64_stats_update_end(&adapter->syncp);
+
+	rtnl_lock();
+	if (unlikely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
+		dev_err(&pdev->dev,
+			"ignoring device reset request as the device is being suspended\n");
+		clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+	}
+	ena_destroy_device(adapter);
+	rtnl_unlock();
+	return 0;
+}
+
+/* ena_resume - PM resume callback
+ * @pdev: PCI device information struct
+ *
+ */
+static int ena_resume(struct pci_dev *pdev)
+{
+	struct ena_adapter *adapter = pci_get_drvdata(pdev);
+	int rc;
+
+	u64_stats_update_begin(&adapter->syncp);
+	adapter->dev_stats.resume++;
+	u64_stats_update_end(&adapter->syncp);
+
+	rtnl_lock();
+	rc = ena_restore_device(adapter);
+	rtnl_unlock();
+	return rc;
+}
+#endif
+
 static struct pci_driver ena_pci_driver = {
 	.name		= DRV_MODULE_NAME,
 	.id_table	= ena_pci_tbl,
 	.probe		= ena_probe,
 	.remove		= ena_remove,
+#ifdef CONFIG_PM
+	.suspend    = ena_suspend,
+	.resume     = ena_resume,
+#endif
 	.sriov_configure = ena_sriov_configure,
 };
 
@@ -3504,16 +3531,6 @@ static void ena_notification(void *adapter_data,
 	     ENA_ADMIN_NOTIFICATION);
 
 	switch (aenq_e->aenq_common_desc.syndrom) {
-	case ENA_ADMIN_SUSPEND:
-		/* Suspend just the IO queues.
-		 * We deliberately don't suspend admin so the timer and
-		 * the keep_alive events should remain.
-		 */
-		queue_work(ena_wq, &adapter->suspend_io_task);
-		break;
-	case ENA_ADMIN_RESUME:
-		queue_work(ena_wq, &adapter->resume_io_task);
-		break;
 	case ENA_ADMIN_UPDATE_HINTS:
 		hints = (struct ena_admin_ena_hw_hints *)
 			(&aenq_e->inline_data_w4);
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 29bb5704260b..ed8bd0a579c4 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -44,7 +44,7 @@
 #include "ena_eth_com.h"
 
 #define DRV_MODULE_VER_MAJOR	1
-#define DRV_MODULE_VER_MINOR	2
+#define DRV_MODULE_VER_MINOR	3
 #define DRV_MODULE_VER_SUBMINOR 0
 
 #define DRV_MODULE_NAME		"ena"
@@ -52,7 +52,7 @@
 #define DRV_MODULE_VERSION \
 	__stringify(DRV_MODULE_VER_MAJOR) "."	\
 	__stringify(DRV_MODULE_VER_MINOR) "."	\
-	__stringify(DRV_MODULE_VER_SUBMINOR) "k"
+	__stringify(DRV_MODULE_VER_SUBMINOR) "K"
 #endif
 
 #define DEVICE_NAME	"Elastic Network Adapter (ENA)"
@@ -185,6 +185,7 @@ struct ena_stats_tx {
 	u64 tx_poll;
 	u64 doorbells;
 	u64 bad_req_id;
+	u64 missed_tx;
 };
 
 struct ena_stats_rx {
@@ -257,8 +258,8 @@ struct ena_ring {
 
 struct ena_stats_dev {
 	u64 tx_timeout;
-	u64 io_suspend;
-	u64 io_resume;
+	u64 suspend;
+	u64 resume;
 	u64 wd_expired;
 	u64 interface_up;
 	u64 interface_down;
@@ -326,11 +327,10 @@ struct ena_adapter {
 
 	/* timer service */
 	struct work_struct reset_task;
-	struct work_struct suspend_io_task;
-	struct work_struct resume_io_task;
 	struct timer_list timer_service;
 
 	bool wd_state;
+	bool dev_up_before_reset;
 	unsigned long last_keep_alive_jiffies;
 
 	struct u64_stats_sync syncp;
diff --git a/drivers/net/ethernet/amd/a2065.c b/drivers/net/ethernet/amd/a2065.c
index e22f976a0d18..212fe72a190b 100644
--- a/drivers/net/ethernet/amd/a2065.c
+++ b/drivers/net/ethernet/amd/a2065.c
@@ -123,6 +123,7 @@ struct lance_private {
 	int burst_sizes;	      /* ledma SBus burst sizes */
 #endif
 	struct timer_list         multicast_timer;
+	struct net_device	  *dev;
 };
 
 #define LANCE_ADDR(x) ((int)(x) & ~0xff000000)
@@ -638,6 +639,13 @@ static void lance_set_multicast(struct net_device *dev)
 	netif_wake_queue(dev);
 }
 
+static void lance_set_multicast_retry(struct timer_list *t)
+{
+	struct lance_private *lp = from_timer(lp, t, multicast_timer);
+
+	lance_set_multicast(lp->dev);
+}
+
 static int a2065_init_one(struct zorro_dev *z,
 			  const struct zorro_device_id *ent);
 static void a2065_remove_one(struct zorro_dev *z);
@@ -728,15 +736,13 @@ static int a2065_init_one(struct zorro_dev *z,
 	priv->lance_log_tx_bufs = LANCE_LOG_TX_BUFFERS;
 	priv->rx_ring_mod_mask = RX_RING_MOD_MASK;
 	priv->tx_ring_mod_mask = TX_RING_MOD_MASK;
+	priv->dev = dev;
 
 	dev->netdev_ops = &lance_netdev_ops;
 	dev->watchdog_timeo = 5*HZ;
 	dev->dma = 0;
 
-	init_timer(&priv->multicast_timer);
-	priv->multicast_timer.data = (unsigned long) dev;
-	priv->multicast_timer.function =
-		(void (*)(unsigned long))lance_set_multicast;
+	timer_setup(&priv->multicast_timer, lance_set_multicast_retry, 0);
 
 	err = register_netdev(dev);
 	if (err) {
diff --git a/drivers/net/ethernet/amd/am79c961a.c b/drivers/net/ethernet/amd/am79c961a.c
index b11e910850f7..01d132c02ff9 100644
--- a/drivers/net/ethernet/amd/am79c961a.c
+++ b/drivers/net/ethernet/amd/am79c961a.c
@@ -302,10 +302,10 @@ am79c961_init_for_open(struct net_device *dev)
 	write_rreg (dev->base_addr, CSR0, CSR0_IENA|CSR0_STRT);
 }
 
-static void am79c961_timer(unsigned long data)
+static void am79c961_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct dev_priv *priv = netdev_priv(dev);
+	struct dev_priv *priv = from_timer(priv, t, timer);
+	struct net_device *dev = priv->dev;
 	unsigned int lnkstat, carrier;
 	unsigned long flags;
 
@@ -728,9 +728,8 @@ static int am79c961_probe(struct platform_device *pdev)
 	am79c961_banner();
 
 	spin_lock_init(&priv->chip_lock);
-	init_timer(&priv->timer);
-	priv->timer.data = (unsigned long)dev;
-	priv->timer.function = am79c961_timer;
+	priv->dev = dev;
+	timer_setup(&priv->timer, am79c961_timer, 0);
 
 	if (am79c961_hw_init(dev))
 		goto release;
diff --git a/drivers/net/ethernet/amd/am79c961a.h b/drivers/net/ethernet/amd/am79c961a.h
index 9f384b79507b..fc5088c70731 100644
--- a/drivers/net/ethernet/amd/am79c961a.h
+++ b/drivers/net/ethernet/amd/am79c961a.h
@@ -140,6 +140,7 @@ struct dev_priv {
     unsigned long	txhdr;
     spinlock_t		chip_lock;
     struct timer_list	timer;
+    struct net_device   *dev;
 };
 
 #endif
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index 7b5df562f30f..358f7ab77c70 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -1669,9 +1669,9 @@ static int amd8111e_resume(struct pci_dev *pci_dev)
 	return 0;
 }
 
-static void amd8111e_config_ipg(struct net_device *dev)
+static void amd8111e_config_ipg(struct timer_list *t)
 {
-	struct amd8111e_priv *lp = netdev_priv(dev);
+	struct amd8111e_priv *lp = from_timer(lp, t, ipg_data.ipg_timer);
 	struct ipg_info *ipg_data = &lp->ipg_data;
 	void __iomem *mmio = lp->mmio;
 	unsigned int prev_col_cnt = ipg_data->col_cnt;
@@ -1883,9 +1883,7 @@ static int amd8111e_probe_one(struct pci_dev *pdev,
 
 	/* Initialize software ipg timer */
 	if(lp->options & OPTION_DYN_IPG_ENABLE){
-		init_timer(&lp->ipg_data.ipg_timer);
-		lp->ipg_data.ipg_timer.data = (unsigned long) dev;
-		lp->ipg_data.ipg_timer.function = (void *)&amd8111e_config_ipg;
+		timer_setup(&lp->ipg_data.ipg_timer, amd8111e_config_ipg, 0);
 		lp->ipg_data.ipg_timer.expires = jiffies +
 						 IPG_CONVERGE_JIFFIES;
 		lp->ipg_data.ipg = DEFAULT_IPG;
diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c
index 82cc81385033..116997a8b593 100644
--- a/drivers/net/ethernet/amd/declance.c
+++ b/drivers/net/ethernet/amd/declance.c
@@ -260,6 +260,7 @@ struct lance_private {
 	unsigned short busmaster_regval;
 
 	struct timer_list       multicast_timer;
+	struct net_device	*dev;
 
 	/* Pointers to the ring buffers as seen from the CPU */
 	char *rx_buf_ptr_cpu[RX_RING_SIZE];
@@ -1000,9 +1001,10 @@ static void lance_set_multicast(struct net_device *dev)
 	netif_wake_queue(dev);
 }
 
-static void lance_set_multicast_retry(unsigned long _opaque)
+static void lance_set_multicast_retry(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) _opaque;
+	struct lance_private *lp = from_timer(lp, t, multicast_timer);
+	struct net_device *dev = lp->dev;
 
 	lance_set_multicast(dev);
 }
@@ -1246,9 +1248,9 @@ static int dec_lance_probe(struct device *bdev, const int type)
 	 * can occur from interrupts (ex. IPv6).  So we
 	 * use a timer to try again later when necessary. -DaveM
 	 */
-	init_timer(&lp->multicast_timer);
-	lp->multicast_timer.data = (unsigned long) dev;
-	lp->multicast_timer.function = lance_set_multicast_retry;
+	lp->dev = dev;
+	timer_setup(&lp->multicast_timer, lance_set_multicast_retry, 0);
+
 
 	ret = register_netdev(dev);
 	if (ret) {
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index 7f60d17819ce..a561705f232c 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -321,7 +321,7 @@ static struct net_device_stats *pcnet32_get_stats(struct net_device *);
 static void pcnet32_load_multicast(struct net_device *dev);
 static void pcnet32_set_multicast_list(struct net_device *);
 static int pcnet32_ioctl(struct net_device *, struct ifreq *, int);
-static void pcnet32_watchdog(struct net_device *);
+static void pcnet32_watchdog(struct timer_list *);
 static int mdio_read(struct net_device *dev, int phy_id, int reg_num);
 static void mdio_write(struct net_device *dev, int phy_id, int reg_num,
 		       int val);
@@ -1970,9 +1970,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 			lp->options |= PCNET32_PORT_MII;
 	}
 
-	init_timer(&lp->watchdog_timer);
-	lp->watchdog_timer.data = (unsigned long)dev;
-	lp->watchdog_timer.function = (void *)&pcnet32_watchdog;
+	timer_setup(&lp->watchdog_timer, pcnet32_watchdog, 0);
 
 	/* The PCNET32-specific entries in the device structure. */
 	dev->netdev_ops = &pcnet32_netdev_ops;
@@ -2902,9 +2900,10 @@ static void pcnet32_check_media(struct net_device *dev, int verbose)
  * Could possibly be changed to use mii_check_media instead.
  */
 
-static void pcnet32_watchdog(struct net_device *dev)
+static void pcnet32_watchdog(struct timer_list *t)
 {
-	struct pcnet32_private *lp = netdev_priv(dev);
+	struct pcnet32_private *lp = from_timer(lp, t, watchdog_timer);
+	struct net_device *dev = lp->dev;
 	unsigned long flags;
 
 	/* Print the link status if it has changed */
diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c
index 291ca5187f12..cdd7a611479b 100644
--- a/drivers/net/ethernet/amd/sunlance.c
+++ b/drivers/net/ethernet/amd/sunlance.c
@@ -1248,9 +1248,10 @@ static void lance_set_multicast(struct net_device *dev)
 	netif_wake_queue(dev);
 }
 
-static void lance_set_multicast_retry(unsigned long _opaque)
+static void lance_set_multicast_retry(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) _opaque;
+	struct lance_private *lp = from_timer(lp, t, multicast_timer);
+	struct net_device *dev = lp->dev;
 
 	lance_set_multicast(dev);
 }
@@ -1459,9 +1460,7 @@ no_link_test:
 	 * can occur from interrupts (ex. IPv6).  So we
 	 * use a timer to try again later when necessary. -DaveM
 	 */
-	init_timer(&lp->multicast_timer);
-	lp->multicast_timer.data = (unsigned long) dev;
-	lp->multicast_timer.function = lance_set_multicast_retry;
+	timer_setup(&lp->multicast_timer, lance_set_multicast_retry, 0);
 
 	if (register_netdev(dev)) {
 		printk(KERN_ERR "SunLance: Cannot register device.\n");
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 608693d11bd7..3d53153ce751 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -642,9 +642,9 @@ static irqreturn_t xgbe_dma_isr(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static void xgbe_tx_timer(unsigned long data)
+static void xgbe_tx_timer(struct timer_list *t)
 {
-	struct xgbe_channel *channel = (struct xgbe_channel *)data;
+	struct xgbe_channel *channel = from_timer(channel, t, tx_timer);
 	struct xgbe_prv_data *pdata = channel->pdata;
 	struct napi_struct *napi;
 
@@ -680,9 +680,9 @@ static void xgbe_service(struct work_struct *work)
 	pdata->phy_if.phy_status(pdata);
 }
 
-static void xgbe_service_timer(unsigned long data)
+static void xgbe_service_timer(struct timer_list *t)
 {
-	struct xgbe_prv_data *pdata = (struct xgbe_prv_data *)data;
+	struct xgbe_prv_data *pdata = from_timer(pdata, t, service_timer);
 
 	queue_work(pdata->dev_workqueue, &pdata->service_work);
 
@@ -694,16 +694,14 @@ static void xgbe_init_timers(struct xgbe_prv_data *pdata)
 	struct xgbe_channel *channel;
 	unsigned int i;
 
-	setup_timer(&pdata->service_timer, xgbe_service_timer,
-		    (unsigned long)pdata);
+	timer_setup(&pdata->service_timer, xgbe_service_timer, 0);
 
 	for (i = 0; i < pdata->channel_count; i++) {
 		channel = pdata->channel[i];
 		if (!channel->tx_ring)
 			break;
 
-		setup_timer(&channel->tx_timer, xgbe_tx_timer,
-			    (unsigned long)channel);
+		timer_setup(&channel->tx_timer, xgbe_tx_timer, 0);
 	}
 }
 
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index eac740c476ce..5a655d289dd5 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -157,7 +157,7 @@ static irqreturn_t bmac_misc_intr(int irq, void *dev_id);
 static irqreturn_t bmac_txdma_intr(int irq, void *dev_id);
 static irqreturn_t bmac_rxdma_intr(int irq, void *dev_id);
 static void bmac_set_timeout(struct net_device *dev);
-static void bmac_tx_timeout(unsigned long data);
+static void bmac_tx_timeout(struct timer_list *t);
 static int bmac_output(struct sk_buff *skb, struct net_device *dev);
 static void bmac_start(struct net_device *dev);
 
@@ -555,8 +555,6 @@ static inline void bmac_set_timeout(struct net_device *dev)
 	if (bp->timeout_active)
 		del_timer(&bp->tx_timeout);
 	bp->tx_timeout.expires = jiffies + TX_TIMEOUT;
-	bp->tx_timeout.function = bmac_tx_timeout;
-	bp->tx_timeout.data = (unsigned long) dev;
 	add_timer(&bp->tx_timeout);
 	bp->timeout_active = 1;
 	spin_unlock_irqrestore(&bp->lock, flags);
@@ -1321,7 +1319,7 @@ static int bmac_probe(struct macio_dev *mdev, const struct of_device_id *match)
 	bp->queue = (struct sk_buff_head *)(bp->rx_cmds + N_RX_RING + 1);
 	skb_queue_head_init(bp->queue);
 
-	init_timer(&bp->tx_timeout);
+	timer_setup(&bp->tx_timeout, bmac_tx_timeout, 0);
 
 	ret = request_irq(dev->irq, bmac_misc_intr, 0, "BMAC-misc", dev);
 	if (ret) {
@@ -1471,10 +1469,10 @@ bmac_output(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-static void bmac_tx_timeout(unsigned long data)
+static void bmac_tx_timeout(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) data;
-	struct bmac_data *bp = netdev_priv(dev);
+	struct bmac_data *bp = from_timer(bp, t, tx_timeout);
+	struct net_device *dev = macio_get_drvdata(bp->mdev);
 	volatile struct dbdma_regs __iomem *td = bp->tx_dma;
 	volatile struct dbdma_regs __iomem *rd = bp->rx_dma;
 	volatile struct dbdma_cmd *cp;
diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c
index e58b157b7d7c..0b5429d76bcf 100644
--- a/drivers/net/ethernet/apple/mace.c
+++ b/drivers/net/ethernet/apple/mace.c
@@ -86,7 +86,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id);
 static irqreturn_t mace_txdma_intr(int irq, void *dev_id);
 static irqreturn_t mace_rxdma_intr(int irq, void *dev_id);
 static void mace_set_timeout(struct net_device *dev);
-static void mace_tx_timeout(unsigned long data);
+static void mace_tx_timeout(struct timer_list *t);
 static inline void dbdma_reset(volatile struct dbdma_regs __iomem *dma);
 static inline void mace_clean_rings(struct mace_data *mp);
 static void __mace_set_address(struct net_device *dev, void *addr);
@@ -196,7 +196,7 @@ static int mace_probe(struct macio_dev *mdev, const struct of_device_id *match)
 
 	memset((char *) mp->tx_cmds, 0,
 	       (NCMDS_TX*N_TX_RING + N_RX_RING + 2) * sizeof(struct dbdma_cmd));
-	init_timer(&mp->tx_timeout);
+	timer_setup(&mp->tx_timeout, mace_tx_timeout, 0);
 	spin_lock_init(&mp->lock);
 	mp->timeout_active = 0;
 
@@ -521,8 +521,6 @@ static inline void mace_set_timeout(struct net_device *dev)
     if (mp->timeout_active)
 	del_timer(&mp->tx_timeout);
     mp->tx_timeout.expires = jiffies + TX_TIMEOUT;
-    mp->tx_timeout.function = mace_tx_timeout;
-    mp->tx_timeout.data = (unsigned long) dev;
     add_timer(&mp->tx_timeout);
     mp->timeout_active = 1;
 }
@@ -801,10 +799,10 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id)
     return IRQ_HANDLED;
 }
 
-static void mace_tx_timeout(unsigned long data)
+static void mace_tx_timeout(struct timer_list *t)
 {
-    struct net_device *dev = (struct net_device *) data;
-    struct mace_data *mp = netdev_priv(dev);
+    struct mace_data *mp = from_timer(mp, t, tx_timeout);
+    struct net_device *dev = macio_get_drvdata(mp->mdev);
     volatile struct mace __iomem *mb = mp->mace;
     volatile struct dbdma_regs __iomem *td = mp->tx_dma;
     volatile struct dbdma_regs __iomem *rd = mp->rx_dma;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index d5e99b468870..70efb7467bf3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -221,8 +221,8 @@ static int aq_ethtool_get_rxnfc(struct net_device *ndev,
 	return err;
 }
 
-int aq_ethtool_get_coalesce(struct net_device *ndev,
-			    struct ethtool_coalesce *coal)
+static int aq_ethtool_get_coalesce(struct net_device *ndev,
+				   struct ethtool_coalesce *coal)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
 	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic);
@@ -242,8 +242,8 @@ int aq_ethtool_get_coalesce(struct net_device *ndev,
 	return 0;
 }
 
-int aq_ethtool_set_coalesce(struct net_device *ndev,
-			    struct ethtool_coalesce *coal)
+static int aq_ethtool_set_coalesce(struct net_device *ndev,
+				   struct ethtool_coalesce *coal)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
 	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic);
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 67134ece1107..af75156919ed 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -184,6 +184,7 @@ config BGMAC_PLATFORM
 config SYSTEMPORT
 	tristate "Broadcom SYSTEMPORT internal MAC support"
 	depends on OF
+	depends on NET_DSA || !NET_DSA
 	select MII
 	select PHYLIB
 	select FIXED_PHY
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index a1125d10c825..42e44fc03a18 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -1474,10 +1474,8 @@ static int b44_open(struct net_device *dev)
 		goto out;
 	}
 
-	init_timer(&bp->timer);
+	setup_timer(&bp->timer, b44_timer, (unsigned long)bp);
 	bp->timer.expires = jiffies + HZ;
-	bp->timer.data = (unsigned long) bp;
-	bp->timer.function = b44_timer;
 	add_timer(&bp->timer);
 
 	b44_enable_ints(bp);
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 4f3845a58126..d9346e2ac720 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -295,16 +295,13 @@ static int bcm_enet_refill_rx(struct net_device *dev)
 /*
  * timer callback to defer refill rx queue in case we're OOM
  */
-static void bcm_enet_refill_rx_timer(unsigned long data)
+static void bcm_enet_refill_rx_timer(struct timer_list *t)
 {
-	struct net_device *dev;
-	struct bcm_enet_priv *priv;
-
-	dev = (struct net_device *)data;
-	priv = netdev_priv(dev);
+	struct bcm_enet_priv *priv = from_timer(priv, t, rx_timeout);
+	struct net_device *dev = priv->net_dev;
 
 	spin_lock(&priv->rx_lock);
-	bcm_enet_refill_rx((struct net_device *)data);
+	bcm_enet_refill_rx(dev);
 	spin_unlock(&priv->rx_lock);
 }
 
@@ -1062,7 +1059,8 @@ static int bcm_enet_open(struct net_device *dev)
 	val = enet_readl(priv, ENET_CTL_REG);
 	val |= ENET_CTL_ENABLE_MASK;
 	enet_writel(priv, val, ENET_CTL_REG);
-	enet_dma_writel(priv, ENETDMA_CFG_EN_MASK, ENETDMA_CFG_REG);
+	if (priv->dma_has_sram)
+		enet_dma_writel(priv, ENETDMA_CFG_EN_MASK, ENETDMA_CFG_REG);
 	enet_dmac_writel(priv, priv->dma_chan_en_mask,
 			 ENETDMAC_CHANCFG, priv->rx_chan);
 
@@ -1721,10 +1719,8 @@ static int bcm_enet_probe(struct platform_device *pdev)
 	const char *clk_name;
 	int i, ret;
 
-	/* stop if shared driver failed, assume driver->probe will be
-	 * called in the same order we register devices (correct ?) */
 	if (!bcm_enet_shared_base[0])
-		return -ENODEV;
+		return -EPROBE_DEFER;
 
 	res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	res_irq_rx = platform_get_resource(pdev, IORESOURCE_IRQ, 1);
@@ -1768,12 +1764,14 @@ static int bcm_enet_probe(struct platform_device *pdev)
 		clk_name = "enet1";
 	}
 
-	priv->mac_clk = clk_get(&pdev->dev, clk_name);
+	priv->mac_clk = devm_clk_get(&pdev->dev, clk_name);
 	if (IS_ERR(priv->mac_clk)) {
 		ret = PTR_ERR(priv->mac_clk);
 		goto out;
 	}
-	clk_prepare_enable(priv->mac_clk);
+	ret = clk_prepare_enable(priv->mac_clk);
+	if (ret)
+		goto out;
 
 	/* initialize default and fetch platform data */
 	priv->rx_ring_size = BCMENET_DEF_RX_DESC;
@@ -1801,13 +1799,15 @@ static int bcm_enet_probe(struct platform_device *pdev)
 
 	if (priv->mac_id == 0 && priv->has_phy && !priv->use_external_mii) {
 		/* using internal PHY, enable clock */
-		priv->phy_clk = clk_get(&pdev->dev, "ephy");
+		priv->phy_clk = devm_clk_get(&pdev->dev, "ephy");
 		if (IS_ERR(priv->phy_clk)) {
 			ret = PTR_ERR(priv->phy_clk);
 			priv->phy_clk = NULL;
-			goto out_put_clk_mac;
+			goto out_disable_clk_mac;
 		}
-		clk_prepare_enable(priv->phy_clk);
+		ret = clk_prepare_enable(priv->phy_clk);
+		if (ret)
+			goto out_disable_clk_mac;
 	}
 
 	/* do minimal hardware init to be able to probe mii bus */
@@ -1857,9 +1857,7 @@ static int bcm_enet_probe(struct platform_device *pdev)
 	spin_lock_init(&priv->rx_lock);
 
 	/* init rx timeout (used for oom) */
-	init_timer(&priv->rx_timeout);
-	priv->rx_timeout.function = bcm_enet_refill_rx_timer;
-	priv->rx_timeout.data = (unsigned long)dev;
+	timer_setup(&priv->rx_timeout, bcm_enet_refill_rx_timer, 0);
 
 	/* init the mib update lock&work */
 	mutex_init(&priv->mib_update_lock);
@@ -1901,14 +1899,10 @@ out_free_mdio:
 out_uninit_hw:
 	/* turn off mdc clock */
 	enet_writel(priv, 0, ENET_MIISC_REG);
-	if (priv->phy_clk) {
-		clk_disable_unprepare(priv->phy_clk);
-		clk_put(priv->phy_clk);
-	}
+	clk_disable_unprepare(priv->phy_clk);
 
-out_put_clk_mac:
+out_disable_clk_mac:
 	clk_disable_unprepare(priv->mac_clk);
-	clk_put(priv->mac_clk);
 out:
 	free_netdev(dev);
 	return ret;
@@ -1944,12 +1938,8 @@ static int bcm_enet_remove(struct platform_device *pdev)
 	}
 
 	/* disable hw block clocks */
-	if (priv->phy_clk) {
-		clk_disable_unprepare(priv->phy_clk);
-		clk_put(priv->phy_clk);
-	}
+	clk_disable_unprepare(priv->phy_clk);
 	clk_disable_unprepare(priv->mac_clk);
-	clk_put(priv->mac_clk);
 
 	free_netdev(dev);
 	return 0;
@@ -2021,9 +2011,9 @@ static inline int bcm_enet_port_is_rgmii(int portid)
 /*
  * enet sw PHY polling
  */
-static void swphy_poll_timer(unsigned long data)
+static void swphy_poll_timer(struct timer_list *t)
 {
-	struct bcm_enet_priv *priv = (struct bcm_enet_priv *)data;
+	struct bcm_enet_priv *priv = from_timer(priv, t, swphy_poll);
 	unsigned int i;
 
 	for (i = 0; i < priv->num_ports; i++) {
@@ -2332,11 +2322,8 @@ static int bcm_enetsw_open(struct net_device *dev)
 	}
 
 	/* start phy polling timer */
-	init_timer(&priv->swphy_poll);
-	priv->swphy_poll.function = swphy_poll_timer;
-	priv->swphy_poll.data = (unsigned long)priv;
-	priv->swphy_poll.expires = jiffies;
-	add_timer(&priv->swphy_poll);
+	timer_setup(&priv->swphy_poll, swphy_poll_timer, 0);
+	mod_timer(&priv->swphy_poll, jiffies);
 	return 0;
 
 out:
@@ -2692,11 +2679,8 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
 	struct resource *res_mem;
 	int ret, irq_rx, irq_tx;
 
-	/* stop if shared driver failed, assume driver->probe will be
-	 * called in the same order we register devices (correct ?)
-	 */
 	if (!bcm_enet_shared_base[0])
-		return -ENODEV;
+		return -EPROBE_DEFER;
 
 	res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq_rx = platform_get_irq(pdev, 0);
@@ -2735,33 +2719,27 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
 	if (ret)
 		goto out;
 
-	if (!request_mem_region(res_mem->start, resource_size(res_mem),
-				"bcm63xx_enetsw")) {
-		ret = -EBUSY;
+	priv->base = devm_ioremap_resource(&pdev->dev, res_mem);
+	if (IS_ERR(priv->base)) {
+		ret = PTR_ERR(priv->base);
 		goto out;
 	}
 
-	priv->base = ioremap(res_mem->start, resource_size(res_mem));
-	if (priv->base == NULL) {
-		ret = -ENOMEM;
-		goto out_release_mem;
-	}
-
-	priv->mac_clk = clk_get(&pdev->dev, "enetsw");
+	priv->mac_clk = devm_clk_get(&pdev->dev, "enetsw");
 	if (IS_ERR(priv->mac_clk)) {
 		ret = PTR_ERR(priv->mac_clk);
-		goto out_unmap;
+		goto out;
 	}
-	clk_enable(priv->mac_clk);
+	ret = clk_prepare_enable(priv->mac_clk);
+	if (ret)
+		goto out;
 
 	priv->rx_chan = 0;
 	priv->tx_chan = 1;
 	spin_lock_init(&priv->rx_lock);
 
 	/* init rx timeout (used for oom) */
-	init_timer(&priv->rx_timeout);
-	priv->rx_timeout.function = bcm_enet_refill_rx_timer;
-	priv->rx_timeout.data = (unsigned long)dev;
+	timer_setup(&priv->rx_timeout, bcm_enet_refill_rx_timer, 0);
 
 	/* register netdevice */
 	dev->netdev_ops = &bcm_enetsw_ops;
@@ -2773,7 +2751,7 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
 
 	ret = register_netdev(dev);
 	if (ret)
-		goto out_put_clk;
+		goto out_disable_clk;
 
 	netif_carrier_off(dev);
 	platform_set_drvdata(pdev, dev);
@@ -2782,14 +2760,8 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
 
 	return 0;
 
-out_put_clk:
-	clk_put(priv->mac_clk);
-
-out_unmap:
-	iounmap(priv->base);
-
-out_release_mem:
-	release_mem_region(res_mem->start, resource_size(res_mem));
+out_disable_clk:
+	clk_disable_unprepare(priv->mac_clk);
 out:
 	free_netdev(dev);
 	return ret;
@@ -2801,17 +2773,13 @@ static int bcm_enetsw_remove(struct platform_device *pdev)
 {
 	struct bcm_enet_priv *priv;
 	struct net_device *dev;
-	struct resource *res;
 
 	/* stop netdevice */
 	dev = platform_get_drvdata(pdev);
 	priv = netdev_priv(dev);
 	unregister_netdev(dev);
 
-	/* release device resources */
-	iounmap(priv->base);
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(res->start, resource_size(res));
+	clk_disable_unprepare(priv->mac_clk);
 
 	free_netdev(dev);
 	return 0;
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.h b/drivers/net/ethernet/broadcom/bcm63xx_enet.h
index c6f6f14e87ca..5a66728d4776 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.h
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.h
@@ -9,7 +9,6 @@
 #include <linux/platform_device.h>
 
 #include <bcm63xx_regs.h>
-#include <bcm63xx_irq.h>
 #include <bcm63xx_io.h>
 #include <bcm63xx_iudma.h>
 
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index eb441e5e2cd8..087f01b4dc3a 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1416,9 +1416,24 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 	tdma_writel(priv, 0, TDMA_DESC_RING_COUNT(index));
 	tdma_writel(priv, 1, TDMA_DESC_RING_INTR_CONTROL(index));
 	tdma_writel(priv, 0, TDMA_DESC_RING_PROD_CONS_INDEX(index));
-	tdma_writel(priv, RING_IGNORE_STATUS, TDMA_DESC_RING_MAPPING(index));
+
+	/* Configure QID and port mapping */
+	reg = tdma_readl(priv, TDMA_DESC_RING_MAPPING(index));
+	reg &= ~(RING_QID_MASK | RING_PORT_ID_MASK << RING_PORT_ID_SHIFT);
+	if (ring->inspect) {
+		reg |= ring->switch_queue & RING_QID_MASK;
+		reg |= ring->switch_port << RING_PORT_ID_SHIFT;
+	} else {
+		reg |= RING_IGNORE_STATUS;
+	}
+	tdma_writel(priv, reg, TDMA_DESC_RING_MAPPING(index));
 	tdma_writel(priv, 0, TDMA_DESC_RING_PCP_DEI_VID(index));
 
+	/* Enable ACB algorithm 2 */
+	reg = tdma_readl(priv, TDMA_CONTROL);
+	reg |= tdma_control_bit(priv, ACB_ALGO);
+	tdma_writel(priv, reg, TDMA_CONTROL);
+
 	/* Do not use tdma_control_bit() here because TSB_SWAP1 collides
 	 * with the original definition of ACB_ALGO
 	 */
@@ -1447,8 +1462,9 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 	napi_enable(&ring->napi);
 
 	netif_dbg(priv, hw, priv->netdev,
-		  "TDMA cfg, size=%d, desc_cpu=%p\n",
-		  ring->size, ring->desc_cpu);
+		  "TDMA cfg, size=%d, desc_cpu=%p switch q=%d,port=%d\n",
+		  ring->size, ring->desc_cpu, ring->switch_queue,
+		  ring->switch_port);
 
 	return 0;
 }
@@ -2013,6 +2029,29 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = {
 	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
 };
 
+static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
+				    void *accel_priv,
+				    select_queue_fallback_t fallback)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	u16 queue = skb_get_queue_mapping(skb);
+	struct bcm_sysport_tx_ring *tx_ring;
+	unsigned int q, port;
+
+	if (!netdev_uses_dsa(dev))
+		return fallback(dev, skb);
+
+	/* DSA tagging layer will have configured the correct queue */
+	q = BRCM_TAG_GET_QUEUE(queue);
+	port = BRCM_TAG_GET_PORT(queue);
+	tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues];
+
+	if (unlikely(!tx_ring))
+		return fallback(dev, skb);
+
+	return tx_ring->index;
+}
+
 static const struct net_device_ops bcm_sysport_netdev_ops = {
 	.ndo_start_xmit		= bcm_sysport_xmit,
 	.ndo_tx_timeout		= bcm_sysport_tx_timeout,
@@ -2025,8 +2064,79 @@ static const struct net_device_ops bcm_sysport_netdev_ops = {
 	.ndo_poll_controller	= bcm_sysport_poll_controller,
 #endif
 	.ndo_get_stats64	= bcm_sysport_get_stats64,
+	.ndo_select_queue	= bcm_sysport_select_queue,
 };
 
+static int bcm_sysport_map_queues(struct net_device *dev,
+				  struct dsa_notifier_register_info *info)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	struct bcm_sysport_tx_ring *ring;
+	struct net_device *slave_dev;
+	unsigned int num_tx_queues;
+	unsigned int q, start, port;
+
+	/* We can't be setting up queue inspection for non directly attached
+	 * switches
+	 */
+	if (info->switch_number)
+		return 0;
+
+	if (dev->netdev_ops != &bcm_sysport_netdev_ops)
+		return 0;
+
+	port = info->port_number;
+	slave_dev = info->info.dev;
+
+	/* On SYSTEMPORT Lite we have twice as less queues, so we cannot do a
+	 * 1:1 mapping, we can only do a 2:1 mapping. By reducing the number of
+	 * per-port (slave_dev) network devices queue, we achieve just that.
+	 * This need to happen now before any slave network device is used such
+	 * it accurately reflects the number of real TX queues.
+	 */
+	if (priv->is_lite)
+		netif_set_real_num_tx_queues(slave_dev,
+					     slave_dev->num_tx_queues / 2);
+	num_tx_queues = slave_dev->real_num_tx_queues;
+
+	if (priv->per_port_num_tx_queues &&
+	    priv->per_port_num_tx_queues != num_tx_queues)
+		netdev_warn(slave_dev, "asymetric number of per-port queues\n");
+
+	priv->per_port_num_tx_queues = num_tx_queues;
+
+	start = find_first_zero_bit(&priv->queue_bitmap, dev->num_tx_queues);
+	for (q = 0; q < num_tx_queues; q++) {
+		ring = &priv->tx_rings[q + start];
+
+		/* Just remember the mapping actual programming done
+		 * during bcm_sysport_init_tx_ring
+		 */
+		ring->switch_queue = q;
+		ring->switch_port = port;
+		ring->inspect = true;
+		priv->ring_map[q + port * num_tx_queues] = ring;
+
+		/* Set all queues as being used now */
+		set_bit(q + start, &priv->queue_bitmap);
+	}
+
+	return 0;
+}
+
+static int bcm_sysport_dsa_notifier(struct notifier_block *unused,
+				    unsigned long event, void *ptr)
+{
+	struct dsa_notifier_register_info *info;
+
+	if (event != DSA_PORT_REGISTER)
+		return NOTIFY_DONE;
+
+	info = ptr;
+
+	return notifier_from_errno(bcm_sysport_map_queues(info->master, info));
+}
+
 #define REV_FMT	"v%2x.%02x"
 
 static const struct bcm_sysport_hw_params bcm_sysport_params[] = {
@@ -2174,10 +2284,18 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 
 	u64_stats_init(&priv->syncp);
 
+	priv->dsa_notifier.notifier_call = bcm_sysport_dsa_notifier;
+
+	ret = register_dsa_notifier(&priv->dsa_notifier);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register DSA notifier\n");
+		goto err_deregister_fixed_link;
+	}
+
 	ret = register_netdev(dev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register net_device\n");
-		goto err_deregister_fixed_link;
+		goto err_deregister_notifier;
 	}
 
 	priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK;
@@ -2190,6 +2308,8 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_deregister_notifier:
+	unregister_dsa_notifier(&priv->dsa_notifier);
 err_deregister_fixed_link:
 	if (of_phy_is_fixed_link(dn))
 		of_phy_deregister_fixed_link(dn);
@@ -2201,11 +2321,13 @@ err_free_netdev:
 static int bcm_sysport_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = dev_get_drvdata(&pdev->dev);
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct device_node *dn = pdev->dev.of_node;
 
 	/* Not much to do, ndo_close has been called
 	 * and we use managed allocations
 	 */
+	unregister_dsa_notifier(&priv->dsa_notifier);
 	unregister_netdev(dev);
 	if (of_phy_is_fixed_link(dn))
 		of_phy_deregister_fixed_link(dn);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index 82e401df199e..f5a984c1c986 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -404,7 +404,7 @@ struct bcm_rsb {
 #define  RING_CONS_INDEX_MASK		0xffff
 
 #define RING_MAPPING			0x14
-#define  RING_QID_MASK			0x3
+#define  RING_QID_MASK			0x7
 #define  RING_PORT_ID_SHIFT		3
 #define  RING_PORT_ID_MASK		0x7
 #define  RING_IGNORE_STATUS		(1 << 6)
@@ -712,6 +712,9 @@ struct bcm_sysport_tx_ring {
 	struct bcm_sysport_priv *priv;	/* private context backpointer */
 	unsigned long	packets;	/* packets statistics */
 	unsigned long	bytes;		/* bytes statistics */
+	unsigned int	switch_queue;	/* switch port queue number */
+	unsigned int	switch_port;	/* switch port queue number */
+	bool		inspect;	/* inspect switch port and queue */
 };
 
 /* Driver private structure */
@@ -765,5 +768,12 @@ struct bcm_sysport_priv {
 
 	/* For atomic update generic 64bit value on 32bit Machine */
 	struct u64_stats_sync	syncp;
+
+	/* map information between switch port queues and local queues */
+	struct notifier_block	dsa_notifier;
+	unsigned int		per_port_num_tx_queues;
+	unsigned long		queue_bitmap;
+	struct bcm_sysport_tx_ring *ring_map[DSA_MAX_PORTS * 8];
+
 };
 #endif /* __BCM_SYSPORT_H */
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index 6322594ab260..6fe074c1588b 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -184,13 +184,19 @@ static int bgmac_probe(struct bcma_device *core)
 
 	if (!bgmac_is_bcm4707_family(core) &&
 	    !(ci->id == BCMA_CHIP_ID_BCM53573 && core->core_unit == 1)) {
+		struct phy_device *phydev;
+
 		mii_bus = bcma_mdio_mii_register(bgmac);
 		if (IS_ERR(mii_bus)) {
 			err = PTR_ERR(mii_bus);
 			goto err;
 		}
-
 		bgmac->mii_bus = mii_bus;
+
+		phydev = mdiobus_get_phy(bgmac->mii_bus, bgmac->phyaddr);
+		if (ci->id == BCMA_CHIP_ID_BCM53573 && phydev &&
+		    (phydev->drv->phy_id & phydev->drv->phy_id_mask) == PHY_ID_BCM54210E)
+			phydev->dev_flags |= PHY_BRCM_EN_MASTER_MODE;
 	}
 
 	if (core->bus->hosttype == BCMA_HOSTTYPE_PCI) {
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index e3af1f3cb61f..b3055a76dfbf 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -8462,10 +8462,8 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev)
 	bnx2_set_default_link(bp);
 	bp->req_flow_ctrl = FLOW_CTRL_RX | FLOW_CTRL_TX;
 
-	init_timer(&bp->timer);
+	setup_timer(&bp->timer, bnx2_timer, (unsigned long)bp);
 	bp->timer.expires = RUN_AT(BNX2_TIMER_INTERVAL);
-	bp->timer.data = (unsigned long) bp;
-	bp->timer.function = bnx2_timer;
 
 #ifdef BCM_CNIC
 	if (bnx2_shmem_rd(bp, BNX2_ISCSI_INITIATOR) & BNX2_ISCSI_INITIATOR_EN)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c12b4d3e946e..54d1571384a0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12414,10 +12414,8 @@ static int bnx2x_init_bp(struct bnx2x *bp)
 
 	bp->current_interval = CHIP_REV_IS_SLOW(bp) ? 5*HZ : HZ;
 
-	init_timer(&bp->timer);
+	setup_timer(&bp->timer, bnx2x_timer, (unsigned long)bp);
 	bp->timer.expires = jiffies + bp->current_interval;
-	bp->timer.data = (unsigned long) bp;
-	bp->timer.function = bnx2x_timer;
 
 	if (SHMEM2_HAS(bp, dcbx_lldp_params_offset) &&
 	    SHMEM2_HAS(bp, dcbx_lldp_dcbx_stat_offset) &&
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 9ca994d0bab6..3591077a5f6b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1074,11 +1074,6 @@ static void bnx2x_vf_set_bars(struct bnx2x *bp, struct bnx2x_virtf *vf)
 	}
 }
 
-static int bnx2x_ari_enabled(struct pci_dev *dev)
-{
-	return dev->bus->self && dev->bus->self->ari_enabled;
-}
-
 static int
 bnx2x_get_vf_igu_cam_info(struct bnx2x *bp)
 {
@@ -1212,7 +1207,7 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param,
 
 	err = -EIO;
 	/* verify ari is enabled */
-	if (!bnx2x_ari_enabled(bp->pdev)) {
+	if (!pci_ari_enabled(bp->pdev->bus)) {
 		BNX2X_ERR("ARI not supported (check pci bridge ARI forwarding), SRIOV can not be enabled\n");
 		return 0;
 	}
diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile
index 4f0cb8e1ffc0..59c8ec9c1cad 100644
--- a/drivers/net/ethernet/broadcom/bnxt/Makefile
+++ b/drivers/net/ethernet/broadcom/bnxt/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_BNXT) += bnxt_en.o
 
-bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_tc.o
+bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_devlink.o
+bnxt_en-$(CONFIG_BNXT_FLOWER_OFFLOAD) += bnxt_tc.o
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index dc5de275352a..4e3d569bf32e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -61,6 +61,7 @@
 #include "bnxt_xdp.h"
 #include "bnxt_vfr.h"
 #include "bnxt_tc.h"
+#include "bnxt_devlink.h"
 
 #define BNXT_TX_TIMEOUT		(5 * HZ)
 
@@ -107,9 +108,11 @@ enum board_idx {
 	BCM57452,
 	BCM57454,
 	BCM58802,
+	BCM58804,
 	BCM58808,
 	NETXTREME_E_VF,
 	NETXTREME_C_VF,
+	NETXTREME_S_VF,
 };
 
 /* indexed by enum above */
@@ -145,9 +148,11 @@ static const struct {
 	[BCM57452] = { "Broadcom BCM57452 NetXtreme-E 10Gb/25Gb/40Gb/50Gb Ethernet" },
 	[BCM57454] = { "Broadcom BCM57454 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
 	[BCM58802] = { "Broadcom BCM58802 NetXtreme-S 10Gb/25Gb/40Gb/50Gb Ethernet" },
+	[BCM58804] = { "Broadcom BCM58804 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
 	[BCM58808] = { "Broadcom BCM58808 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
 	[NETXTREME_E_VF] = { "Broadcom NetXtreme-E Ethernet Virtual Function" },
 	[NETXTREME_C_VF] = { "Broadcom NetXtreme-C Ethernet Virtual Function" },
+	[NETXTREME_S_VF] = { "Broadcom NetXtreme-S Ethernet Virtual Function" },
 };
 
 static const struct pci_device_id bnxt_pci_tbl[] = {
@@ -185,6 +190,7 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x16f0), .driver_data = BCM58808 },
 	{ PCI_VDEVICE(BROADCOM, 0x16f1), .driver_data = BCM57452 },
 	{ PCI_VDEVICE(BROADCOM, 0xd802), .driver_data = BCM58802 },
+	{ PCI_VDEVICE(BROADCOM, 0xd804), .driver_data = BCM58804 },
 #ifdef CONFIG_BNXT_SRIOV
 	{ PCI_VDEVICE(BROADCOM, 0x1606), .driver_data = NETXTREME_E_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x1609), .driver_data = NETXTREME_E_VF },
@@ -194,6 +200,7 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x16dc), .driver_data = NETXTREME_E_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16e1), .driver_data = NETXTREME_C_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16e5), .driver_data = NETXTREME_C_VF },
+	{ PCI_VDEVICE(BROADCOM, 0xd800), .driver_data = NETXTREME_S_VF },
 #endif
 	{ 0 }
 };
@@ -218,7 +225,8 @@ static struct workqueue_struct *bnxt_pf_wq;
 
 static bool bnxt_vf_pciid(enum board_idx idx)
 {
-	return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF);
+	return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF ||
+		idx == NETXTREME_S_VF);
 }
 
 #define DB_CP_REARM_FLAGS	(DB_KEY_CP | DB_IDX_VALID)
@@ -1509,7 +1517,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 				   (struct rx_tpa_end_cmp *)rxcmp,
 				   (struct rx_tpa_end_cmp_ext *)rxcmp1, event);
 
-		if (unlikely(IS_ERR(skb)))
+		if (IS_ERR(skb))
 			return -EBUSY;
 
 		rc = -ENOMEM;
@@ -2827,7 +2835,8 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 	if (page_mode) {
 		if (bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU)
 			return -EOPNOTSUPP;
-		bp->dev->max_mtu = BNXT_MAX_PAGE_MODE_MTU;
+		bp->dev->max_mtu =
+			min_t(u16, bp->max_mtu, BNXT_MAX_PAGE_MODE_MTU);
 		bp->flags &= ~BNXT_FLAG_AGG_RINGS;
 		bp->flags |= BNXT_FLAG_NO_AGG_RINGS | BNXT_FLAG_RX_PAGE_MODE;
 		bp->dev->hw_features &= ~NETIF_F_LRO;
@@ -2835,7 +2844,7 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 		bp->rx_dir = DMA_BIDIRECTIONAL;
 		bp->rx_skb_func = bnxt_rx_page_skb;
 	} else {
-		bp->dev->max_mtu = BNXT_MAX_MTU;
+		bp->dev->max_mtu = bp->max_mtu;
 		bp->flags &= ~BNXT_FLAG_RX_PAGE_MODE;
 		bp->rx_dir = DMA_FROM_DEVICE;
 		bp->rx_skb_func = bnxt_rx_skb;
@@ -4528,19 +4537,46 @@ static int bnxt_hwrm_check_tx_rings(struct bnxt *bp, int tx_rings)
 	return 0;
 }
 
-static void bnxt_hwrm_set_coal_params(struct bnxt *bp, u32 max_bufs,
-	u32 buf_tmrs, u16 flags,
+static void bnxt_hwrm_set_coal_params(struct bnxt_coal *hw_coal,
 	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req)
 {
+	u16 val, tmr, max, flags;
+
+	max = hw_coal->bufs_per_record * 128;
+	if (hw_coal->budget)
+		max = hw_coal->bufs_per_record * hw_coal->budget;
+
+	val = clamp_t(u16, hw_coal->coal_bufs, 1, max);
+	req->num_cmpl_aggr_int = cpu_to_le16(val);
+
+	/* This is a 6-bit value and must not be 0, or we'll get non stop IRQ */
+	val = min_t(u16, val, 63);
+	req->num_cmpl_dma_aggr = cpu_to_le16(val);
+
+	/* This is a 6-bit value and must not be 0, or we'll get non stop IRQ */
+	val = clamp_t(u16, hw_coal->coal_bufs_irq, 1, 63);
+	req->num_cmpl_dma_aggr_during_int = cpu_to_le16(val);
+
+	tmr = BNXT_USEC_TO_COAL_TIMER(hw_coal->coal_ticks);
+	tmr = max_t(u16, tmr, 1);
+	req->int_lat_tmr_max = cpu_to_le16(tmr);
+
+	/* min timer set to 1/2 of interrupt timer */
+	val = tmr / 2;
+	req->int_lat_tmr_min = cpu_to_le16(val);
+
+	/* buf timer set to 1/4 of interrupt timer */
+	val = max_t(u16, tmr / 4, 1);
+	req->cmpl_aggr_dma_tmr = cpu_to_le16(val);
+
+	tmr = BNXT_USEC_TO_COAL_TIMER(hw_coal->coal_ticks_irq);
+	tmr = max_t(u16, tmr, 1);
+	req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(tmr);
+
+	flags = RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET;
+	if (hw_coal->idle_thresh && hw_coal->coal_ticks < hw_coal->idle_thresh)
+		flags |= RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_RING_IDLE;
 	req->flags = cpu_to_le16(flags);
-	req->num_cmpl_dma_aggr = cpu_to_le16((u16)max_bufs);
-	req->num_cmpl_dma_aggr_during_int = cpu_to_le16(max_bufs >> 16);
-	req->cmpl_aggr_dma_tmr = cpu_to_le16((u16)buf_tmrs);
-	req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(buf_tmrs >> 16);
-	/* Minimum time between 2 interrupts set to buf_tmr x 2 */
-	req->int_lat_tmr_min = cpu_to_le16((u16)buf_tmrs * 2);
-	req->int_lat_tmr_max = cpu_to_le16((u16)buf_tmrs * 4);
-	req->num_cmpl_aggr_int = cpu_to_le16((u16)max_bufs * 4);
 }
 
 int bnxt_hwrm_set_coal(struct bnxt *bp)
@@ -4548,51 +4584,14 @@ int bnxt_hwrm_set_coal(struct bnxt *bp)
 	int i, rc = 0;
 	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input req_rx = {0},
 							   req_tx = {0}, *req;
-	u16 max_buf, max_buf_irq;
-	u16 buf_tmr, buf_tmr_irq;
-	u32 flags;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req_rx,
 			       HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS, -1, -1);
 	bnxt_hwrm_cmd_hdr_init(bp, &req_tx,
 			       HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS, -1, -1);
 
-	/* Each rx completion (2 records) should be DMAed immediately.
-	 * DMA 1/4 of the completion buffers at a time.
-	 */
-	max_buf = min_t(u16, bp->rx_coal_bufs / 4, 2);
-	/* max_buf must not be zero */
-	max_buf = clamp_t(u16, max_buf, 1, 63);
-	max_buf_irq = clamp_t(u16, bp->rx_coal_bufs_irq, 1, 63);
-	buf_tmr = BNXT_USEC_TO_COAL_TIMER(bp->rx_coal_ticks);
-	/* buf timer set to 1/4 of interrupt timer */
-	buf_tmr = max_t(u16, buf_tmr / 4, 1);
-	buf_tmr_irq = BNXT_USEC_TO_COAL_TIMER(bp->rx_coal_ticks_irq);
-	buf_tmr_irq = max_t(u16, buf_tmr_irq, 1);
-
-	flags = RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET;
-
-	/* RING_IDLE generates more IRQs for lower latency.  Enable it only
-	 * if coal_ticks is less than 25 us.
-	 */
-	if (bp->rx_coal_ticks < 25)
-		flags |= RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_RING_IDLE;
-
-	bnxt_hwrm_set_coal_params(bp, max_buf_irq << 16 | max_buf,
-				  buf_tmr_irq << 16 | buf_tmr, flags, &req_rx);
-
-	/* max_buf must not be zero */
-	max_buf = clamp_t(u16, bp->tx_coal_bufs, 1, 63);
-	max_buf_irq = clamp_t(u16, bp->tx_coal_bufs_irq, 1, 63);
-	buf_tmr = BNXT_USEC_TO_COAL_TIMER(bp->tx_coal_ticks);
-	/* buf timer set to 1/4 of interrupt timer */
-	buf_tmr = max_t(u16, buf_tmr / 4, 1);
-	buf_tmr_irq = BNXT_USEC_TO_COAL_TIMER(bp->tx_coal_ticks_irq);
-	buf_tmr_irq = max_t(u16, buf_tmr_irq, 1);
-
-	flags = RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET;
-	bnxt_hwrm_set_coal_params(bp, max_buf_irq << 16 | max_buf,
-				  buf_tmr_irq << 16 | buf_tmr, flags, &req_tx);
+	bnxt_hwrm_set_coal_params(&bp->rx_coal, &req_rx);
+	bnxt_hwrm_set_coal_params(&bp->tx_coal, &req_tx);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	for (i = 0; i < bp->cp_nr_rings; i++) {
@@ -4724,6 +4723,10 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 	else
 		bp->br_mode = BRIDGE_MODE_UNDEF;
 
+	bp->max_mtu = le16_to_cpu(resp->max_mtu_configured);
+	if (!bp->max_mtu)
+		bp->max_mtu = BNXT_MAX_MTU;
+
 func_qcfg_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -4884,9 +4887,9 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 			    resp->hwrm_intf_upd);
 		netdev_warn(bp->dev, "Please update firmware with HWRM interface 1.0.0 or newer.\n");
 	}
-	snprintf(bp->fw_ver_str, BC_HWRM_STR_LEN, "%d.%d.%d/%d.%d.%d",
+	snprintf(bp->fw_ver_str, BC_HWRM_STR_LEN, "%d.%d.%d.%d",
 		 resp->hwrm_fw_maj, resp->hwrm_fw_min, resp->hwrm_fw_bld,
-		 resp->hwrm_intf_maj, resp->hwrm_intf_min, resp->hwrm_intf_upd);
+		 resp->hwrm_fw_rsvd);
 
 	bp->hwrm_cmd_timeout = le16_to_cpu(resp->def_req_timeout);
 	if (!bp->hwrm_cmd_timeout)
@@ -6980,6 +6983,11 @@ static void bnxt_timer(unsigned long data)
 		set_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event);
 		bnxt_queue_sp_work(bp);
 	}
+
+	if (bnxt_tc_flower_enabled(bp)) {
+		set_bit(BNXT_FLOW_STATS_SP_EVENT, &bp->sp_event);
+		bnxt_queue_sp_work(bp);
+	}
 bnxt_restart_timer:
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 }
@@ -7070,6 +7078,10 @@ static void bnxt_sp_task(struct work_struct *work)
 		bnxt_get_port_module_status(bp);
 		mutex_unlock(&bp->link_lock);
 	}
+
+	if (test_and_clear_bit(BNXT_FLOW_STATS_SP_EVENT, &bp->sp_event))
+		bnxt_tc_flow_stats_work(bp);
+
 	/* These functions below will clear BNXT_STATE_IN_SP_TASK.  They
 	 * must be the last functions to be called before exiting.
 	 */
@@ -7133,6 +7145,32 @@ static void bnxt_cleanup_pci(struct bnxt *bp)
 	pci_disable_device(bp->pdev);
 }
 
+static void bnxt_init_dflt_coal(struct bnxt *bp)
+{
+	struct bnxt_coal *coal;
+
+	/* Tick values in micro seconds.
+	 * 1 coal_buf x bufs_per_record = 1 completion record.
+	 */
+	coal = &bp->rx_coal;
+	coal->coal_ticks = 14;
+	coal->coal_bufs = 30;
+	coal->coal_ticks_irq = 1;
+	coal->coal_bufs_irq = 2;
+	coal->idle_thresh = 25;
+	coal->bufs_per_record = 2;
+	coal->budget = 64;		/* NAPI budget */
+
+	coal = &bp->tx_coal;
+	coal->coal_ticks = 28;
+	coal->coal_bufs = 30;
+	coal->coal_ticks_irq = 2;
+	coal->coal_bufs_irq = 2;
+	coal->bufs_per_record = 1;
+
+	bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS;
+}
+
 static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)
 {
 	int rc;
@@ -7201,22 +7239,9 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)
 	bp->rx_ring_size = BNXT_DEFAULT_RX_RING_SIZE;
 	bp->tx_ring_size = BNXT_DEFAULT_TX_RING_SIZE;
 
-	/* tick values in micro seconds */
-	bp->rx_coal_ticks = 12;
-	bp->rx_coal_bufs = 30;
-	bp->rx_coal_ticks_irq = 1;
-	bp->rx_coal_bufs_irq = 2;
+	bnxt_init_dflt_coal(bp);
 
-	bp->tx_coal_ticks = 25;
-	bp->tx_coal_bufs = 30;
-	bp->tx_coal_ticks_irq = 2;
-	bp->tx_coal_bufs_irq = 2;
-
-	bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS;
-
-	init_timer(&bp->timer);
-	bp->timer.data = (unsigned long)bp;
-	bp->timer.function = bnxt_timer;
+	setup_timer(&bp->timer, bnxt_timer, (unsigned long)bp);
 	bp->current_interval = BNXT_TIMER_INTERVAL;
 
 	clear_bit(BNXT_STATE_OPEN, &bp->state);
@@ -7243,13 +7268,13 @@ static int bnxt_change_mac_addr(struct net_device *dev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
+	if (ether_addr_equal(addr->sa_data, dev->dev_addr))
+		return 0;
+
 	rc = bnxt_approve_mac(bp, addr->sa_data);
 	if (rc)
 		return rc;
 
-	if (ether_addr_equal(addr->sa_data, dev->dev_addr))
-		return 0;
-
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
 	if (netif_running(dev)) {
 		bnxt_close_nic(bp, false, false);
@@ -7321,23 +7346,48 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 	return 0;
 }
 
-static int bnxt_setup_flower(struct net_device *dev,
-			     struct tc_cls_flower_offload *cls_flower)
+static int bnxt_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				  void *cb_priv)
+{
+	struct bnxt *bp = cb_priv;
+
+	if (!bnxt_tc_flower_enabled(bp) || !tc_can_offload(bp->dev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return bnxt_tc_setup_flower(bp, bp->pf.fw_fid, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int bnxt_setup_tc_block(struct net_device *dev,
+			       struct tc_block_offload *f)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (BNXT_VF(bp))
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
-	return bnxt_tc_setup_flower(bp, bp->pf.fw_fid, cls_flower);
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block, bnxt_setup_tc_block_cb,
+					     bp, bp);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, bnxt_setup_tc_block_cb, bp);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			 void *type_data)
 {
 	switch (type) {
-	case TC_SETUP_CLSFLOWER:
-		return bnxt_setup_flower(dev, type_data);
+	case TC_SETUP_BLOCK:
+		return bnxt_setup_tc_block(dev, type_data);
 	case TC_SETUP_MQPRIO: {
 		struct tc_mqprio_qopt *mqprio = type_data;
 
@@ -8064,10 +8114,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->features |= dev->hw_features | NETIF_F_HIGHDMA;
 	dev->priv_flags |= IFF_UNICAST_FLT;
 
-	/* MTU range: 60 - 9500 */
-	dev->min_mtu = ETH_ZLEN;
-	dev->max_mtu = BNXT_MAX_MTU;
-
 #ifdef CONFIG_BNXT_SRIOV
 	init_waitqueue_head(&bp->sriov_cfg_wait);
 	mutex_init(&bp->sriov_lock);
@@ -8115,6 +8161,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bnxt_ethtool_init(bp);
 	bnxt_dcb_init(bp);
 
+	/* MTU range: 60 - FW defined max */
+	dev->min_mtu = ETH_ZLEN;
+	dev->max_mtu = bp->max_mtu;
+
 	rc = bnxt_probe_phy(bp);
 	if (rc)
 		goto init_err_pci_clean;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index c911e69ff25f..5359a1f0045f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -944,6 +944,22 @@ struct bnxt_test_info {
 #define BNXT_CAG_REG_LEGACY_INT_STATUS	0x4014
 #define BNXT_CAG_REG_BASE		0x300000
 
+struct bnxt_coal {
+	u16			coal_ticks;
+	u16			coal_ticks_irq;
+	u16			coal_bufs;
+	u16			coal_bufs_irq;
+			/* RING_IDLE enabled when coal ticks < idle_thresh  */
+	u16			idle_thresh;
+	u8			bufs_per_record;
+	u8			budget;
+};
+
+struct bnxt_tc_flow_stats {
+	u64		packets;
+	u64		bytes;
+};
+
 struct bnxt_tc_info {
 	bool				enabled;
 
@@ -954,12 +970,29 @@ struct bnxt_tc_info {
 	/* hash table to store L2 keys of TC flows */
 	struct rhashtable		l2_table;
 	struct rhashtable_params	l2_ht_params;
+	/* hash table to store L2 keys for TC tunnel decap */
+	struct rhashtable		decap_l2_table;
+	struct rhashtable_params	decap_l2_ht_params;
+	/* hash table to store tunnel decap entries */
+	struct rhashtable		decap_table;
+	struct rhashtable_params	decap_ht_params;
+	/* hash table to store tunnel encap entries */
+	struct rhashtable		encap_table;
+	struct rhashtable_params	encap_ht_params;
 
 	/* lock to atomically add/del an l2 node when a flow is
 	 * added or deleted.
 	 */
 	struct mutex			lock;
 
+	/* Fields used for batching stats query */
+	struct rhashtable_iter		iter;
+#define BNXT_FLOW_STATS_BATCH_MAX	10
+	struct bnxt_tc_stats_batch {
+		void			  *flow_node;
+		struct bnxt_tc_flow_stats hw_stats;
+	} stats_batch[BNXT_FLOW_STATS_BATCH_MAX];
+
 	/* Stat counter mask (width) */
 	u64				bytes_mask;
 	u64				packets_mask;
@@ -1013,6 +1046,7 @@ struct bnxt {
 #define CHIP_NUM_5745X		0xd730
 
 #define CHIP_NUM_58802		0xd802
+#define CHIP_NUM_58804		0xd804
 #define CHIP_NUM_58808		0xd808
 
 #define BNXT_CHIP_NUM_5730X(chip_num)		\
@@ -1048,6 +1082,7 @@ struct bnxt {
 
 #define BNXT_CHIP_NUM_588XX(chip_num)		\
 	((chip_num) == CHIP_NUM_58802 ||	\
+	 (chip_num) == CHIP_NUM_58804 ||        \
 	 (chip_num) == CHIP_NUM_58808)
 
 	struct net_device	*dev;
@@ -1170,6 +1205,7 @@ struct bnxt {
 	int			nr_vnics;
 	u32			rss_hash_cfg;
 
+	u16			max_mtu;
 	u8			max_tc;
 	u8			max_lltc;	/* lossless TCs */
 	struct bnxt_queue_info	q_info[BNXT_MAX_QUEUE];
@@ -1232,14 +1268,8 @@ struct bnxt {
 	u8			port_count;
 	u16			br_mode;
 
-	u16			rx_coal_ticks;
-	u16			rx_coal_ticks_irq;
-	u16			rx_coal_bufs;
-	u16			rx_coal_bufs_irq;
-	u16			tx_coal_ticks;
-	u16			tx_coal_ticks_irq;
-	u16			tx_coal_bufs;
-	u16			tx_coal_bufs_irq;
+	struct bnxt_coal	rx_coal;
+	struct bnxt_coal	tx_coal;
 
 #define BNXT_USEC_TO_COAL_TIMER(x)	((x) * 25 / 2)
 
@@ -1265,6 +1295,7 @@ struct bnxt {
 #define BNXT_GENEVE_ADD_PORT_SP_EVENT	12
 #define BNXT_GENEVE_DEL_PORT_SP_EVENT	13
 #define BNXT_LINK_SPEED_CHNG_SP_EVENT	14
+#define BNXT_FLOW_STATS_SP_EVENT	15
 
 	struct bnxt_pf_info	pf;
 #ifdef CONFIG_BNXT_SRIOV
@@ -1315,7 +1346,7 @@ struct bnxt {
 	enum devlink_eswitch_mode eswitch_mode;
 	struct bnxt_vf_rep	**vf_reps; /* array of vf-rep ptrs */
 	u16			*cfa_code_map; /* cfa_code -> vf_idx map */
-	struct bnxt_tc_info	tc_info;
+	struct bnxt_tc_info	*tc_info;
 };
 
 #define BNXT_RX_STATS_OFFSET(counter)			\
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
new file mode 100644
index 000000000000..402fa32f7a88
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -0,0 +1,65 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include "bnxt_hsi.h"
+#include "bnxt.h"
+#include "bnxt_vfr.h"
+#include "bnxt_devlink.h"
+
+static const struct devlink_ops bnxt_dl_ops = {
+#ifdef CONFIG_BNXT_SRIOV
+	.eswitch_mode_set = bnxt_dl_eswitch_mode_set,
+	.eswitch_mode_get = bnxt_dl_eswitch_mode_get,
+#endif /* CONFIG_BNXT_SRIOV */
+};
+
+int bnxt_dl_register(struct bnxt *bp)
+{
+	struct devlink *dl;
+	int rc;
+
+	if (!pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV))
+		return 0;
+
+	if (bp->hwrm_spec_code < 0x10803) {
+		netdev_warn(bp->dev, "Firmware does not support SR-IOV E-Switch SWITCHDEV mode.\n");
+		return -ENOTSUPP;
+	}
+
+	dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
+	if (!dl) {
+		netdev_warn(bp->dev, "devlink_alloc failed");
+		return -ENOMEM;
+	}
+
+	bnxt_link_bp_to_dl(bp, dl);
+	bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+	rc = devlink_register(dl, &bp->pdev->dev);
+	if (rc) {
+		bnxt_link_bp_to_dl(bp, NULL);
+		devlink_free(dl);
+		netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+void bnxt_dl_unregister(struct bnxt *bp)
+{
+	struct devlink *dl = bp->dl;
+
+	if (!dl)
+		return;
+
+	devlink_unregister(dl);
+	devlink_free(dl);
+}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
new file mode 100644
index 000000000000..e92a35d8b642
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -0,0 +1,39 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef BNXT_DEVLINK_H
+#define BNXT_DEVLINK_H
+
+/* Struct to hold housekeeping info needed by devlink interface */
+struct bnxt_dl {
+	struct bnxt *bp;	/* back ptr to the controlling dev */
+};
+
+static inline struct bnxt *bnxt_get_bp_from_dl(struct devlink *dl)
+{
+	return ((struct bnxt_dl *)devlink_priv(dl))->bp;
+}
+
+/* To clear devlink pointer from bp, pass NULL dl */
+static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
+{
+	bp->dl = dl;
+
+	/* add a back pointer in dl to bp */
+	if (dl) {
+		struct bnxt_dl *bp_dl = devlink_priv(dl);
+
+		bp_dl->bp = bp;
+	}
+}
+
+int bnxt_dl_register(struct bnxt *bp);
+void bnxt_dl_unregister(struct bnxt *bp);
+
+#endif /* BNXT_DEVLINK_H */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 3cbe771b3352..7ce1d4b7e67d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -26,8 +26,6 @@
 #define FLASH_PACKAGE_TIMEOUT	((HWRM_CMD_TIMEOUT) * 200)
 #define INSTALL_PACKAGE_TIMEOUT	((HWRM_CMD_TIMEOUT) * 200)
 
-static char *bnxt_get_pkgver(struct net_device *dev, char *buf, size_t buflen);
-
 static u32 bnxt_get_msglevel(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -46,19 +44,24 @@ static int bnxt_get_coalesce(struct net_device *dev,
 			     struct ethtool_coalesce *coal)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	struct bnxt_coal *hw_coal;
+	u16 mult;
 
 	memset(coal, 0, sizeof(*coal));
 
-	coal->rx_coalesce_usecs = bp->rx_coal_ticks;
-	/* 2 completion records per rx packet */
-	coal->rx_max_coalesced_frames = bp->rx_coal_bufs / 2;
-	coal->rx_coalesce_usecs_irq = bp->rx_coal_ticks_irq;
-	coal->rx_max_coalesced_frames_irq = bp->rx_coal_bufs_irq / 2;
+	hw_coal = &bp->rx_coal;
+	mult = hw_coal->bufs_per_record;
+	coal->rx_coalesce_usecs = hw_coal->coal_ticks;
+	coal->rx_max_coalesced_frames = hw_coal->coal_bufs / mult;
+	coal->rx_coalesce_usecs_irq = hw_coal->coal_ticks_irq;
+	coal->rx_max_coalesced_frames_irq = hw_coal->coal_bufs_irq / mult;
 
-	coal->tx_coalesce_usecs = bp->tx_coal_ticks;
-	coal->tx_max_coalesced_frames = bp->tx_coal_bufs;
-	coal->tx_coalesce_usecs_irq = bp->tx_coal_ticks_irq;
-	coal->tx_max_coalesced_frames_irq = bp->tx_coal_bufs_irq;
+	hw_coal = &bp->tx_coal;
+	mult = hw_coal->bufs_per_record;
+	coal->tx_coalesce_usecs = hw_coal->coal_ticks;
+	coal->tx_max_coalesced_frames = hw_coal->coal_bufs / mult;
+	coal->tx_coalesce_usecs_irq = hw_coal->coal_ticks_irq;
+	coal->tx_max_coalesced_frames_irq = hw_coal->coal_bufs_irq / mult;
 
 	coal->stats_block_coalesce_usecs = bp->stats_coal_ticks;
 
@@ -70,18 +73,23 @@ static int bnxt_set_coalesce(struct net_device *dev,
 {
 	struct bnxt *bp = netdev_priv(dev);
 	bool update_stats = false;
+	struct bnxt_coal *hw_coal;
 	int rc = 0;
-
-	bp->rx_coal_ticks = coal->rx_coalesce_usecs;
-	/* 2 completion records per rx packet */
-	bp->rx_coal_bufs = coal->rx_max_coalesced_frames * 2;
-	bp->rx_coal_ticks_irq = coal->rx_coalesce_usecs_irq;
-	bp->rx_coal_bufs_irq = coal->rx_max_coalesced_frames_irq * 2;
-
-	bp->tx_coal_ticks = coal->tx_coalesce_usecs;
-	bp->tx_coal_bufs = coal->tx_max_coalesced_frames;
-	bp->tx_coal_ticks_irq = coal->tx_coalesce_usecs_irq;
-	bp->tx_coal_bufs_irq = coal->tx_max_coalesced_frames_irq;
+	u16 mult;
+
+	hw_coal = &bp->rx_coal;
+	mult = hw_coal->bufs_per_record;
+	hw_coal->coal_ticks = coal->rx_coalesce_usecs;
+	hw_coal->coal_bufs = coal->rx_max_coalesced_frames * mult;
+	hw_coal->coal_ticks_irq = coal->rx_coalesce_usecs_irq;
+	hw_coal->coal_bufs_irq = coal->rx_max_coalesced_frames_irq * mult;
+
+	hw_coal = &bp->tx_coal;
+	mult = hw_coal->bufs_per_record;
+	hw_coal->coal_ticks = coal->tx_coalesce_usecs;
+	hw_coal->coal_bufs = coal->tx_max_coalesced_frames * mult;
+	hw_coal->coal_ticks_irq = coal->tx_coalesce_usecs_irq;
+	hw_coal->coal_bufs_irq = coal->tx_max_coalesced_frames_irq * mult;
 
 	if (bp->stats_coal_ticks != coal->stats_block_coalesce_usecs) {
 		u32 stats_ticks = coal->stats_block_coalesce_usecs;
@@ -822,20 +830,10 @@ static void bnxt_get_drvinfo(struct net_device *dev,
 			     struct ethtool_drvinfo *info)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	char *pkglog;
-	char *pkgver = NULL;
 
-	pkglog = kmalloc(BNX_PKG_LOG_MAX_LENGTH, GFP_KERNEL);
-	if (pkglog)
-		pkgver = bnxt_get_pkgver(dev, pkglog, BNX_PKG_LOG_MAX_LENGTH);
 	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
 	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
-	if (pkgver && *pkgver != 0 && isdigit(*pkgver))
-		snprintf(info->fw_version, sizeof(info->fw_version) - 1,
-			 "%s pkg %s", bp->fw_ver_str, pkgver);
-	else
-		strlcpy(info->fw_version, bp->fw_ver_str,
-			sizeof(info->fw_version));
+	strlcpy(info->fw_version, bp->fw_ver_str, sizeof(info->fw_version));
 	strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
 	info->n_stats = bnxt_get_num_stats(bp);
 	info->testinfo_len = bp->num_tests;
@@ -843,7 +841,6 @@ static void bnxt_get_drvinfo(struct net_device *dev,
 	info->eedump_len = 0;
 	/* TODO CHIMP FW: reg dump details */
 	info->regdump_len = 0;
-	kfree(pkglog);
 }
 
 static void bnxt_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
@@ -1350,7 +1347,6 @@ static int bnxt_firmware_reset(struct net_device *dev,
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FW_RESET, -1, -1);
 
-	/* TODO: Support ASAP ChiMP self-reset (e.g. upon PF driver unload) */
 	/* TODO: Address self-reset of APE/KONG/BONO/TANG or ungraceful reset */
 	/*       (e.g. when firmware isn't already running) */
 	switch (dir_type) {
@@ -1376,6 +1372,10 @@ static int bnxt_firmware_reset(struct net_device *dev,
 	case BNX_DIR_TYPE_BONO_PATCH:
 		req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE;
 		break;
+	case BNXT_FW_RESET_CHIP:
+		req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP;
+		req.selfrst_status = FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1773,6 +1773,9 @@ static int bnxt_get_nvram_item(struct net_device *dev, u32 index, u32 offset,
 	dma_addr_t dma_handle;
 	struct hwrm_nvm_read_input req = {0};
 
+	if (!length)
+		return -EINVAL;
+
 	buf = dma_alloc_coherent(&bp->pdev->dev, length, &dma_handle,
 				 GFP_KERNEL);
 	if (!buf) {
@@ -2495,13 +2498,59 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 	}
 }
 
+static int bnxt_reset(struct net_device *dev, u32 *flags)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	int rc = 0;
+
+	if (!BNXT_PF(bp)) {
+		netdev_err(dev, "Reset is not supported from a VF\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (pci_vfs_assigned(bp->pdev)) {
+		netdev_err(dev,
+			   "Reset not allowed when VFs are assigned to VMs\n");
+		return -EBUSY;
+	}
+
+	if (*flags == ETH_RESET_ALL) {
+		/* This feature is not supported in older firmware versions */
+		if (bp->hwrm_spec_code < 0x10803)
+			return -EOPNOTSUPP;
+
+		rc = bnxt_firmware_reset(dev, BNXT_FW_RESET_CHIP);
+		if (!rc)
+			netdev_info(dev, "Reset request successful. Reload driver to complete reset\n");
+	} else {
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
 void bnxt_ethtool_init(struct bnxt *bp)
 {
 	struct hwrm_selftest_qlist_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_selftest_qlist_input req = {0};
 	struct bnxt_test_info *test_info;
+	struct net_device *dev = bp->dev;
+	char *pkglog;
 	int i, rc;
 
+	pkglog = kzalloc(BNX_PKG_LOG_MAX_LENGTH, GFP_KERNEL);
+	if (pkglog) {
+		char *pkgver;
+		int len;
+
+		pkgver = bnxt_get_pkgver(dev, pkglog, BNX_PKG_LOG_MAX_LENGTH);
+		if (pkgver && *pkgver != 0 && isdigit(*pkgver)) {
+			len = strlen(bp->fw_ver_str);
+			snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1,
+				 "/pkg %s", pkgver);
+		}
+		kfree(pkglog);
+	}
 	if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp))
 		return;
 
@@ -2592,4 +2641,5 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 	.nway_reset		= bnxt_nway_reset,
 	.set_phys_id		= bnxt_set_phys_id,
 	.self_test		= bnxt_self_test,
+	.reset			= bnxt_reset,
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
index f1bc90b6fb5b..ff601b42fcc8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
@@ -34,6 +34,8 @@ struct bnxt_led_cfg {
 #define BNXT_LED_DFLT_ENABLES(x)			\
 	cpu_to_le32(BNXT_LED_DFLT_ENA << (BNXT_LED_DFLT_ENA_SHIFT * (x)))
 
+#define BNXT_FW_RESET_CHIP	0xffff
+
 extern const struct ethtool_ops bnxt_ethtool_ops;
 
 u32 _bnxt_fw_to_ethtool_adv_spds(u16, u8);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index cb04cc76e8ad..c99f4d0880e4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -11,21 +11,21 @@
 #ifndef BNXT_HSI_H
 #define BNXT_HSI_H
 
-/* HSI and HWRM Specification 1.8.1 */
+/* HSI and HWRM Specification 1.8.3 */
 #define HWRM_VERSION_MAJOR	1
 #define HWRM_VERSION_MINOR	8
-#define HWRM_VERSION_UPDATE	1
+#define HWRM_VERSION_UPDATE	3
 
-#define HWRM_VERSION_RSVD	4 /* non-zero means beta version */
+#define HWRM_VERSION_RSVD	1 /* non-zero means beta version */
 
-#define HWRM_VERSION_STR	"1.8.1.4"
+#define HWRM_VERSION_STR	"1.8.3.1"
 /*
  * Following is the signature for HWRM message field that indicates not
  * applicable (All F's). Need to cast it the size of the field if needed.
  */
 #define HWRM_NA_SIGNATURE	((__le32)(-1))
 #define HWRM_MAX_REQ_LEN    (128)  /* hwrm_func_buf_rgtr */
-#define HWRM_MAX_RESP_LEN    (248)  /* hwrm_selftest_qlist */
+#define HWRM_MAX_RESP_LEN    (280)  /* hwrm_selftest_qlist */
 #define HW_HASH_INDEX_SIZE      0x80    /* 7 bit indirection table index. */
 #define HW_HASH_KEY_SIZE	40
 #define HWRM_RESP_VALID_KEY      1 /* valid key for HWRM response */
@@ -111,6 +111,7 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_MAC_ADDR_CHANGE      0x31UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_VF_COMM_STATUS_CHANGE 0x32UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE	   0x33UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LLFC_PFC_CHANGE	   0x34UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR		   0xffUL
 	__le32 event_data2;
 	u8 opaque_v;
@@ -835,8 +836,7 @@ struct hwrm_func_qcfg_output {
 	u8 port_pf_cnt;
 	#define FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL		   0x0UL
 	__le16 dflt_vnic_id;
-	u8 unused_0;
-	u8 unused_1;
+	__le16 max_mtu_configured;
 	__le32 min_bw;
 	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_MASK		    0xfffffffUL
 	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_SFT		    0
@@ -873,12 +873,12 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_EVB_MODE_NO_EVB			   0x0UL
 	#define FUNC_QCFG_RESP_EVB_MODE_VEB			   0x1UL
 	#define FUNC_QCFG_RESP_EVB_MODE_VEPA			   0x2UL
-	u8 unused_2;
+	u8 unused_0;
 	__le16 alloc_vfs;
 	__le32 alloc_mcast_filters;
 	__le32 alloc_hw_ring_grps;
 	__le16 alloc_sp_tx_rings;
-	u8 unused_3;
+	u8 unused_1;
 	u8 valid;
 };
 
@@ -3407,6 +3407,7 @@ struct hwrm_vnic_cfg_input {
 	#define VNIC_CFG_REQ_FLAGS_ROCE_DUAL_VNIC_MODE		    0x8UL
 	#define VNIC_CFG_REQ_FLAGS_ROCE_ONLY_VNIC_MODE		    0x10UL
 	#define VNIC_CFG_REQ_FLAGS_RSS_DFLT_CR_MODE		    0x20UL
+	#define VNIC_CFG_REQ_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_MODE 0x40UL
 	__le32 enables;
 	#define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP		    0x1UL
 	#define VNIC_CFG_REQ_ENABLES_RSS_RULE			    0x2UL
@@ -3463,6 +3464,7 @@ struct hwrm_vnic_qcaps_output {
 	#define VNIC_QCAPS_RESP_FLAGS_ROCE_DUAL_VNIC_CAP	    0x8UL
 	#define VNIC_QCAPS_RESP_FLAGS_ROCE_ONLY_VNIC_CAP	    0x10UL
 	#define VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP		    0x20UL
+	#define VNIC_QCAPS_RESP_FLAGS_ROCE_MIRROING_CAPABLE_VNIC_CAP 0x40UL
 	__le32 unused_2;
 	u8 unused_3;
 	u8 unused_4;
@@ -3994,6 +3996,7 @@ struct hwrm_cfa_l2_filter_alloc_input {
 	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS	   0x6UL
 	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT	   0x7UL
 	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE	   0x8UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4      0x9UL
 	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL     0xffUL
 	u8 unused_7;
 	__le16 dst_id;
@@ -4122,6 +4125,14 @@ struct hwrm_cfa_l2_set_rx_mask_output {
 	u8 valid;
 };
 
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_cfa_l2_set_rx_mask_cmd_err {
+	u8 code;
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_UNKNOWN	   0x0UL
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_NTUPLE_FILTER_CONFLICT_ERR 0x1UL
+	u8 unused_0[7];
+};
+
 /* hwrm_cfa_tunnel_filter_alloc */
 /* Input (88 bytes) */
 struct hwrm_cfa_tunnel_filter_alloc_input {
@@ -4161,6 +4172,7 @@ struct hwrm_cfa_tunnel_filter_alloc_input {
 	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
 	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
 	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
 	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
 	u8 unused_0;
 	__le32 vni;
@@ -4323,6 +4335,7 @@ struct hwrm_cfa_ntuple_filter_alloc_input {
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
 	u8 pri_hint;
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER    0x0UL
@@ -4355,6 +4368,14 @@ struct hwrm_cfa_ntuple_filter_alloc_output {
 	u8 valid;
 };
 
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_cfa_ntuple_filter_alloc_cmd_err {
+	u8 code;
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_UNKNOWN      0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_RX_MASK_VLAN_CONFLICT_ERR 0x1UL
+	u8 unused_0[7];
+};
+
 /* hwrm_cfa_ntuple_filter_free */
 /* Input (24 bytes) */
 struct hwrm_cfa_ntuple_filter_free_input {
@@ -4413,6 +4434,116 @@ struct hwrm_cfa_ntuple_filter_cfg_output {
 	u8 valid;
 };
 
+/* hwrm_cfa_decap_filter_alloc */
+/* Input (104 bytes) */
+struct hwrm_cfa_decap_filter_alloc_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le32 flags;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_FLAGS_OVS_TUNNEL	    0x1UL
+	__le32 enables;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE     0x1UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_ID       0x2UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR     0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR     0x8UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_OVLAN_VID       0x10UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IVLAN_VID       0x20UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_OVLAN_VID     0x40UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_IVLAN_VID     0x80UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE       0x100UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR      0x200UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR      0x400UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE     0x800UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL     0x1000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_PORT	    0x2000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_PORT	    0x4000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_ID	    0x8000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID  0x10000UL
+	__be32 tunnel_id;
+	u8 tunnel_type;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL  0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN      0x1UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE      0x2UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE      0x3UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP       0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE     0x5UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS       0x6UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT	   0x7UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE      0x8UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4   0x9UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL  0xffUL
+	u8 unused_0;
+	__le16 unused_1;
+	u8 src_macaddr[6];
+	u8 unused_2;
+	u8 unused_3;
+	u8 dst_macaddr[6];
+	__be16 ovlan_vid;
+	__be16 ivlan_vid;
+	__be16 t_ovlan_vid;
+	__be16 t_ivlan_vid;
+	__be16 ethertype;
+	u8 ip_addr_type;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_UNKNOWN   0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4      0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6      0x6UL
+	u8 ip_protocol;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN    0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP	   0x6UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP	   0x11UL
+	u8 unused_4;
+	u8 unused_5;
+	u8 unused_6[3];
+	u8 unused_7;
+	__be32 src_ipaddr[4];
+	__be32 dst_ipaddr[4];
+	__be16 src_port;
+	__be16 dst_port;
+	__le16 dst_id;
+	__le16 l2_ctxt_ref_id;
+};
+
+/* Output (16 bytes) */
+struct hwrm_cfa_decap_filter_alloc_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le32 decap_filter_id;
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 valid;
+};
+
+/* hwrm_cfa_decap_filter_free */
+/* Input (24 bytes) */
+struct hwrm_cfa_decap_filter_free_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le32 decap_filter_id;
+	__le32 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_cfa_decap_filter_free_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
 /* hwrm_cfa_flow_alloc */
 /* Input (128 bytes) */
 struct hwrm_cfa_flow_alloc_input {
@@ -4634,6 +4765,7 @@ struct hwrm_tunnel_dst_port_query_input {
 	u8 tunnel_type;
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN       0x1UL
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE      0x5UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4    0x9UL
 	u8 unused_0[7];
 };
 
@@ -4662,9 +4794,10 @@ struct hwrm_tunnel_dst_port_alloc_input {
 	u8 tunnel_type;
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN       0x1UL
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE      0x5UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4    0x9UL
 	u8 unused_0;
 	__be16 tunnel_dst_port_val;
-	__le32 unused_1;
+	__be32 unused_1;
 };
 
 /* Output (16 bytes) */
@@ -4693,6 +4826,7 @@ struct hwrm_tunnel_dst_port_free_input {
 	u8 tunnel_type;
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN	   0x1UL
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
 	u8 unused_0;
 	__le16 tunnel_dst_port_id;
 	__le32 unused_1;
@@ -4848,6 +4982,8 @@ struct hwrm_fw_reset_input {
 	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_NETCTRL	   0x2UL
 	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE		   0x3UL
 	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST		   0x4UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP		   0x5UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP		   0x6UL
 	u8 selfrst_status;
 	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE	   0x0UL
 	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP	   0x1UL
@@ -4888,6 +5024,8 @@ struct hwrm_fw_qstatus_input {
 	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_NETCTRL	   0x2UL
 	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_ROCE		   0x3UL
 	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_HOST		   0x4UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_AP		   0x5UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_CHIP		   0x6UL
 	u8 unused_0[7];
 };
 
@@ -5324,6 +5462,32 @@ struct hwrm_wol_reason_qcfg_output {
 	u8 valid;
 };
 
+/* hwrm_dbg_read_direct */
+/* Input (32 bytes) */
+struct hwrm_dbg_read_direct_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le64 host_dest_addr;
+	__le32 read_addr;
+	__le32 read_len32;
+};
+
+/* Output (16 bytes) */
+struct hwrm_dbg_read_direct_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
 /* hwrm_nvm_read */
 /* Input (40 bytes) */
 struct hwrm_nvm_read_input {
@@ -5676,6 +5840,105 @@ struct hwrm_nvm_install_update_cmd_err {
 	u8 unused_0[7];
 };
 
+/* hwrm_nvm_get_variable */
+/* Input (40 bytes) */
+struct hwrm_nvm_get_variable_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le64 dest_data_addr;
+	__le16 data_len;
+	__le16 option_num;
+	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_0		   0x0UL
+	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF	   0xffffUL
+	__le16 dimensions;
+	__le16 index_0;
+	__le16 index_1;
+	__le16 index_2;
+	__le16 index_3;
+	u8 flags;
+	#define NVM_GET_VARIABLE_REQ_FLAGS_FACTORY_DFLT	    0x1UL
+	u8 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_nvm_get_variable_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le16 data_len;
+	__le16 option_num;
+	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_0	   0x0UL
+	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF	   0xffffUL
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 valid;
+};
+
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_nvm_get_variable_cmd_err {
+	u8 code;
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_UNKNOWN		   0x0UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST       0x1UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR	   0x2UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT       0x3UL
+	u8 unused_0[7];
+};
+
+/* hwrm_nvm_set_variable */
+/* Input (40 bytes) */
+struct hwrm_nvm_set_variable_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le64 src_data_addr;
+	__le16 data_len;
+	__le16 option_num;
+	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_0		   0x0UL
+	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF	   0xffffUL
+	__le16 dimensions;
+	__le16 index_0;
+	__le16 index_1;
+	__le16 index_2;
+	__le16 index_3;
+	u8 flags;
+	#define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH		    0x1UL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK       0xeUL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT	    1
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE      (0x0UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1 (0x1UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST    NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1
+	u8 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_nvm_set_variable_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_nvm_set_variable_cmd_err {
+	u8 code;
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_UNKNOWN		   0x0UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST       0x1UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR	   0x2UL
+	u8 unused_0[7];
+};
+
 /* hwrm_selftest_qlist */
 /* Input (16 bytes) */
 struct hwrm_selftest_qlist_input {
@@ -5686,7 +5949,7 @@ struct hwrm_selftest_qlist_input {
 	__le64 resp_addr;
 };
 
-/* Output (248 bytes) */
+/* Output (280 bytes) */
 struct hwrm_selftest_qlist_output {
 	__le16 error_code;
 	__le16 req_type;
@@ -5698,15 +5961,15 @@ struct hwrm_selftest_qlist_output {
 	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_LINK_TEST      0x2UL
 	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_REGISTER_TEST  0x4UL
 	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_MEMORY_TEST    0x8UL
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_PCIE_EYE_TEST  0x10UL
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_ETHERNET_EYE_TEST 0x20UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_PCIE_SERDES_TEST 0x10UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_ETHERNET_SERDES_TEST 0x20UL
 	u8 offline_tests;
 	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_NVM_TEST	    0x1UL
 	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_LINK_TEST	    0x2UL
 	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_REGISTER_TEST    0x4UL
 	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_MEMORY_TEST      0x8UL
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_PCIE_EYE_TEST    0x10UL
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_ETHERNET_EYE_TEST 0x20UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_PCIE_SERDES_TEST 0x10UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_ETHERNET_SERDES_TEST 0x20UL
 	u8 unused_0;
 	__le16 test_timeout;
 	u8 unused_1;
@@ -5719,6 +5982,11 @@ struct hwrm_selftest_qlist_output {
 	char test5_name[32];
 	char test6_name[32];
 	char test7_name[32];
+	__le32 unused_3;
+	u8 unused_4;
+	u8 unused_5;
+	u8 unused_6;
+	u8 valid;
 };
 
 /* hwrm_selftest_exec */
@@ -5734,8 +6002,8 @@ struct hwrm_selftest_exec_input {
 	#define SELFTEST_EXEC_REQ_FLAGS_LINK_TEST		    0x2UL
 	#define SELFTEST_EXEC_REQ_FLAGS_REGISTER_TEST		    0x4UL
 	#define SELFTEST_EXEC_REQ_FLAGS_MEMORY_TEST		    0x8UL
-	#define SELFTEST_EXEC_REQ_FLAGS_PCIE_EYE_TEST		    0x10UL
-	#define SELFTEST_EXEC_REQ_FLAGS_ETHERNET_EYE_TEST	    0x20UL
+	#define SELFTEST_EXEC_REQ_FLAGS_PCIE_SERDES_TEST	    0x10UL
+	#define SELFTEST_EXEC_REQ_FLAGS_ETHERNET_SERDES_TEST       0x20UL
 	u8 unused_0[7];
 };
 
@@ -5750,16 +6018,21 @@ struct hwrm_selftest_exec_output {
 	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_LINK_TEST       0x2UL
 	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_REGISTER_TEST   0x4UL
 	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_MEMORY_TEST     0x8UL
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_PCIE_EYE_TEST   0x10UL
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_ETHERNET_EYE_TEST 0x20UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_PCIE_SERDES_TEST 0x10UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_ETHERNET_SERDES_TEST 0x20UL
 	u8 test_success;
 	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_NVM_TEST	    0x1UL
 	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_LINK_TEST	    0x2UL
 	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_REGISTER_TEST      0x4UL
 	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_MEMORY_TEST	    0x8UL
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_PCIE_EYE_TEST      0x10UL
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_ETHERNET_EYE_TEST  0x20UL
-	__le16 unused_0[3];
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_PCIE_SERDES_TEST   0x10UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_ETHERNET_SERDES_TEST 0x20UL
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 unused_4;
+	u8 valid;
 };
 
 /* hwrm_selftest_irq */
@@ -5772,12 +6045,50 @@ struct hwrm_selftest_irq_input {
 	__le64 resp_addr;
 };
 
-/* Output (8 bytes) */
+/* Output (16 bytes) */
 struct hwrm_selftest_irq_output {
 	__le16 error_code;
 	__le16 req_type;
 	__le16 seq_id;
 	__le16 resp_len;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* hwrm_selftest_retrieve_serdes_data */
+/* Input (32 bytes) */
+struct hwrm_selftest_retrieve_serdes_data_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le64 resp_data_addr;
+	__le32 resp_data_offset;
+	__le16 data_len;
+	u8 flags;
+	#define SELFTEST_RETRIEVE_SERDES_DATA_REQ_FLAGS_UNUSED_TEST_MASK 0xfUL
+	#define SELFTEST_RETRIEVE_SERDES_DATA_REQ_FLAGS_UNUSED_TEST_SFT 0
+	#define SELFTEST_RETRIEVE_SERDES_DATA_REQ_FLAGS_PCIE_SERDES_TEST 0x10UL
+	#define SELFTEST_RETRIEVE_SERDES_DATA_REQ_FLAGS_ETHERNET_SERDES_TEST 0x20UL
+	u8 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_selftest_retrieve_serdes_data_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le16 total_data_len;
+	__le16 copied_data_len;
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 valid;
 };
 
 /* Hardware Resource Manager Specification */
@@ -5938,10 +6249,16 @@ struct cmd_nums {
 	#define HWRM_CFA_DECAP_FILTER_ALLOC			   (0x108UL)
 	#define HWRM_CFA_DECAP_FILTER_FREE			   (0x109UL)
 	#define HWRM_CFA_VLAN_ANTISPOOF_QCFG			   (0x10aUL)
+	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_ALLOC		   (0x10bUL)
+	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_FREE		   (0x10cUL)
+	#define HWRM_CFA_PAIR_ALLOC				   (0x10dUL)
+	#define HWRM_CFA_PAIR_FREE				   (0x10eUL)
+	#define HWRM_CFA_PAIR_INFO				   (0x10fUL)
+	#define HWRM_FW_IPC_MSG				   (0x110UL)
 	#define HWRM_SELFTEST_QLIST				   (0x200UL)
 	#define HWRM_SELFTEST_EXEC				   (0x201UL)
 	#define HWRM_SELFTEST_IRQ				   (0x202UL)
-	#define HWRM_SELFTEST_RETREIVE_EYE_DATA		   (0x203UL)
+	#define HWRM_SELFTEST_RETRIEVE_SERDES_DATA		   (0x203UL)
 	#define HWRM_DBG_READ_DIRECT				   (0xff10UL)
 	#define HWRM_DBG_READ_INDIRECT				   (0xff11UL)
 	#define HWRM_DBG_WRITE_DIRECT				   (0xff12UL)
@@ -5949,6 +6266,9 @@ struct cmd_nums {
 	#define HWRM_DBG_DUMP					   (0xff14UL)
 	#define HWRM_DBG_ERASE_NVM				   (0xff15UL)
 	#define HWRM_DBG_CFG					   (0xff16UL)
+	#define HWRM_DBG_COREDUMP_LIST				   (0xff17UL)
+	#define HWRM_DBG_COREDUMP_INITIATE			   (0xff18UL)
+	#define HWRM_DBG_COREDUMP_RETRIEVE			   (0xff19UL)
 	#define HWRM_NVM_FACTORY_DEFAULTS			   (0xffeeUL)
 	#define HWRM_NVM_VALIDATE_OPTION			   (0xffefUL)
 	#define HWRM_NVM_FLUSH					   (0xfff0UL)
@@ -6123,6 +6443,58 @@ struct rx_port_stats {
 	__le64 rx_stat_err;
 };
 
+/* VXLAN IPv4 encapsulation structure (16 bytes) */
+struct hwrm_vxlan_ipv4_hdr {
+	u8 ver_hlen;
+	#define VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_MASK	    0xfUL
+	#define VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_SFT	    0
+	#define VXLAN_IPV4_HDR_VER_HLEN_VERSION_MASK		    0xf0UL
+	#define VXLAN_IPV4_HDR_VER_HLEN_VERSION_SFT		    4
+	u8 tos;
+	__be16 ip_id;
+	__be16 flags_frag_offset;
+	u8 ttl;
+	u8 protocol;
+	__be32 src_ip_addr;
+	__be32 dest_ip_addr;
+};
+
+/* VXLAN IPv6 encapsulation structure (32 bytes) */
+struct hwrm_vxlan_ipv6_hdr {
+	__be32 ver_tc_flow_label;
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_VER_SFT	   0x1cUL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_VER_MASK	   0xf0000000UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_TC_SFT	   0x14UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_TC_MASK	   0xff00000UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_SFT   0x0UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_MASK  0xfffffUL
+	__be16 payload_len;
+	u8 next_hdr;
+	u8 ttl;
+	__be32 src_ip_addr[4];
+	__be32 dest_ip_addr[4];
+};
+
+/* VXLAN encapsulation structure (72 bytes) */
+struct hwrm_cfa_encap_data_vxlan {
+	u8 src_mac_addr[6];
+	__le16 unused_0;
+	u8 dst_mac_addr[6];
+	u8 num_vlan_tags;
+	u8 unused_1;
+	__be16 ovlan_tpid;
+	__be16 ovlan_tci;
+	__be16 ivlan_tpid;
+	__be16 ivlan_tci;
+	__le32 l3[10];
+	#define CFA_ENCAP_DATA_VXLAN_L3_VER_MASK		   0xfUL
+	#define CFA_ENCAP_DATA_VXLAN_L3_VER_IPV4		   0x4UL
+	#define CFA_ENCAP_DATA_VXLAN_L3_VER_IPV6		   0x6UL
+	__be16 src_port;
+	__be16 dst_port;
+	__be32 vni;
+};
+
 /* Periodic Statistics Context DMA to host (160 bytes) */
 struct ctx_hw_stats {
 	__le64 rx_ucast_pkts;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 7dd3d131043a..d5031f436f83 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -16,6 +16,7 @@
 #include <net/tc_act/tc_skbedit.h>
 #include <net/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_vlan.h>
+#include <net/tc_act/tc_tunnel_key.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -23,8 +24,6 @@
 #include "bnxt_tc.h"
 #include "bnxt_vfr.h"
 
-#ifdef CONFIG_BNXT_FLOWER_OFFLOAD
-
 #define BNXT_FID_INVALID			0xffff
 #define VLAN_TCI(vid, prio)	((vid) | ((prio) << VLAN_PRIO_SHIFT))
 
@@ -91,6 +90,23 @@ static void bnxt_tc_parse_vlan(struct bnxt *bp,
 	}
 }
 
+static int bnxt_tc_parse_tunnel_set(struct bnxt *bp,
+				    struct bnxt_tc_actions *actions,
+				    const struct tc_action *tc_act)
+{
+	struct ip_tunnel_info *tun_info = tcf_tunnel_info(tc_act);
+	struct ip_tunnel_key *tun_key = &tun_info->key;
+
+	if (ip_tunnel_info_af(tun_info) != AF_INET) {
+		netdev_info(bp->dev, "only IPv4 tunnel-encap is supported");
+		return -EOPNOTSUPP;
+	}
+
+	actions->tun_encap_key = *tun_key;
+	actions->flags |= BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP;
+	return 0;
+}
+
 static int bnxt_tc_parse_actions(struct bnxt *bp,
 				 struct bnxt_tc_actions *actions,
 				 struct tcf_exts *tc_exts)
@@ -125,9 +141,35 @@ static int bnxt_tc_parse_actions(struct bnxt *bp,
 			bnxt_tc_parse_vlan(bp, actions, tc_act);
 			continue;
 		}
+
+		/* Tunnel encap */
+		if (is_tcf_tunnel_set(tc_act)) {
+			rc = bnxt_tc_parse_tunnel_set(bp, actions, tc_act);
+			if (rc)
+				return rc;
+			continue;
+		}
+
+		/* Tunnel decap */
+		if (is_tcf_tunnel_release(tc_act)) {
+			actions->flags |= BNXT_TC_ACTION_FLAG_TUNNEL_DECAP;
+			continue;
+		}
 	}
 
-	return 0;
+	if (rc)
+		return rc;
+
+	/* Tunnel encap/decap action must be accompanied by a redirect action */
+	if ((actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP ||
+	     actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP) &&
+	    !(actions->flags & BNXT_TC_ACTION_FLAG_FWD)) {
+		netdev_info(bp->dev,
+			    "error: no redir action along with encap/decap");
+		return -EINVAL;
+	}
+
+	return rc;
 }
 
 #define GET_KEY(flow_cmd, key_type)					\
@@ -254,6 +296,54 @@ static int bnxt_tc_parse_flow(struct bnxt *bp,
 		flow->l4_mask.icmp.code = mask->code;
 	}
 
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
+		struct flow_dissector_key_control *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_CONTROL);
+
+		addr_type = key->addr_type;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+		struct flow_dissector_key_ipv4_addrs *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS);
+		struct flow_dissector_key_ipv4_addrs *mask =
+				GET_MASK(tc_flow_cmd,
+					 FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS;
+		flow->tun_key.u.ipv4.dst = key->dst;
+		flow->tun_mask.u.ipv4.dst = mask->dst;
+		flow->tun_key.u.ipv4.src = key->src;
+		flow->tun_mask.u.ipv4.src = mask->src;
+	} else if (dissector_uses_key(dissector,
+				      FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
+		return -EOPNOTSUPP;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_dissector_key_keyid *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_KEYID);
+		struct flow_dissector_key_keyid *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_KEYID);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_ID;
+		flow->tun_key.tun_id = key32_to_tunnel_id(key->keyid);
+		flow->tun_mask.tun_id = key32_to_tunnel_id(mask->keyid);
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
+		struct flow_dissector_key_ports *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_PORTS);
+		struct flow_dissector_key_ports *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_PORTS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_PORTS;
+		flow->tun_key.tp_dst = key->dst;
+		flow->tun_mask.tp_dst = mask->dst;
+		flow->tun_key.tp_src = key->src;
+		flow->tun_mask.tp_src = mask->src;
+	}
+
 	return bnxt_tc_parse_actions(bp, &flow->actions, tc_flow_cmd->exts);
 }
 
@@ -295,7 +385,8 @@ static bool is_wildcard(void *mask, int len)
 }
 
 static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
-				    __le16 ref_flow_handle, __le16 *flow_handle)
+				    __le16 ref_flow_handle,
+				    __le32 tunnel_handle, __le16 *flow_handle)
 {
 	struct hwrm_cfa_flow_alloc_output *resp = bp->hwrm_cmd_resp_addr;
 	struct bnxt_tc_actions *actions = &flow->actions;
@@ -309,6 +400,14 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 
 	req.src_fid = cpu_to_le16(flow->src_fid);
 	req.ref_flow_handle = ref_flow_handle;
+
+	if (actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP ||
+	    actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP) {
+		req.tunnel_handle = tunnel_handle;
+		flow_flags |= CFA_FLOW_ALLOC_REQ_FLAGS_TUNNEL;
+		action_flags |= CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL;
+	}
+
 	req.ethertype = flow->l2_key.ether_type;
 	req.ip_proto = flow->l4_key.ip_proto;
 
@@ -405,78 +504,153 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 	return rc;
 }
 
-/* Add val to accum while handling a possible wraparound
- * of val. Eventhough val is of type u64, its actual width
- * is denoted by mask and will wrap-around beyond that width.
- */
-static void accumulate_val(u64 *accum, u64 val, u64 mask)
+static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp,
+				       struct bnxt_tc_flow *flow,
+				       struct bnxt_tc_l2_key *l2_info,
+				       __le32 ref_decap_handle,
+				       __le32 *decap_filter_handle)
 {
-#define low_bits(x, mask)		((x) & (mask))
-#define high_bits(x, mask)		((x) & ~(mask))
-	bool wrapped = val < low_bits(*accum, mask);
+	struct hwrm_cfa_decap_filter_alloc_output *resp =
+						bp->hwrm_cmd_resp_addr;
+	struct hwrm_cfa_decap_filter_alloc_input req = { 0 };
+	struct ip_tunnel_key *tun_key = &flow->tun_key;
+	u32 enables = 0;
+	int rc;
 
-	*accum = high_bits(*accum, mask) + val;
-	if (wrapped)
-		*accum += (mask + 1);
-}
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_DECAP_FILTER_ALLOC, -1, -1);
 
-/* The HW counters' width is much less than 64bits.
- * Handle possible wrap-around while updating the stat counters
- */
-static void bnxt_flow_stats_fix_wraparound(struct bnxt_tc_info *tc_info,
-					   struct bnxt_tc_flow_stats *stats,
-					   struct bnxt_tc_flow_stats *hw_stats)
-{
-	accumulate_val(&stats->bytes, hw_stats->bytes, tc_info->bytes_mask);
-	accumulate_val(&stats->packets, hw_stats->packets,
-		       tc_info->packets_mask);
+	req.flags = cpu_to_le32(CFA_DECAP_FILTER_ALLOC_REQ_FLAGS_OVS_TUNNEL);
+	enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE |
+		   CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL;
+	req.tunnel_type = CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN;
+	req.ip_protocol = CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP;
+
+	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_ID) {
+		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_ID;
+		/* tunnel_id is wrongly defined in hsi defn. as __le32 */
+		req.tunnel_id = tunnel_id_to_key32(tun_key->tun_id);
+	}
+
+	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_ETH_ADDRS) {
+		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR |
+			   CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR;
+		ether_addr_copy(req.dst_macaddr, l2_info->dmac);
+		ether_addr_copy(req.src_macaddr, l2_info->smac);
+	}
+	if (l2_info->num_vlans) {
+		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_IVLAN_VID;
+		req.t_ivlan_vid = l2_info->inner_vlan_tci;
+	}
+
+	enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE;
+	req.ethertype = htons(ETH_P_IP);
+
+	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS) {
+		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR |
+			   CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR |
+			   CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE;
+		req.ip_addr_type = CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4;
+		req.dst_ipaddr[0] = tun_key->u.ipv4.dst;
+		req.src_ipaddr[0] = tun_key->u.ipv4.src;
+	}
+
+	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_PORTS) {
+		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_PORT;
+		req.dst_port = tun_key->tp_dst;
+	}
+
+	/* Eventhough the decap_handle returned by hwrm_cfa_decap_filter_alloc
+	 * is defined as __le32, l2_ctxt_ref_id is defined in HSI as __le16.
+	 */
+	req.l2_ctxt_ref_id = (__force __le16)ref_decap_handle;
+	req.enables = cpu_to_le32(enables);
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		*decap_filter_handle = resp->decap_filter_id;
+	else
+		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+	mutex_unlock(&bp->hwrm_cmd_lock);
+
+	return rc;
 }
 
-/* Fix possible wraparound of the stats queried from HW, calculate
- * the delta from prev_stats, and also update the prev_stats.
- * The HW flow stats are fetched under the hwrm_cmd_lock mutex.
- * This routine is best called while under the mutex so that the
- * stats processing happens atomically.
- */
-static void bnxt_flow_stats_calc(struct bnxt_tc_info *tc_info,
-				 struct bnxt_tc_flow *flow,
-				 struct bnxt_tc_flow_stats *stats)
+static int hwrm_cfa_decap_filter_free(struct bnxt *bp,
+				      __le32 decap_filter_handle)
 {
-	struct bnxt_tc_flow_stats *acc_stats, *prev_stats;
+	struct hwrm_cfa_decap_filter_free_input req = { 0 };
+	int rc;
 
-	acc_stats = &flow->stats;
-	bnxt_flow_stats_fix_wraparound(tc_info, acc_stats, stats);
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_DECAP_FILTER_FREE, -1, -1);
+	req.decap_filter_id = decap_filter_handle;
 
-	prev_stats = &flow->prev_stats;
-	stats->bytes = acc_stats->bytes - prev_stats->bytes;
-	stats->packets = acc_stats->packets - prev_stats->packets;
-	*prev_stats = *acc_stats;
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+	return rc;
 }
 
-static int bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp,
-					__le16 flow_handle,
-					struct bnxt_tc_flow *flow,
-					struct bnxt_tc_flow_stats *stats)
+static int hwrm_cfa_encap_record_alloc(struct bnxt *bp,
+				       struct ip_tunnel_key *encap_key,
+				       struct bnxt_tc_l2_key *l2_info,
+				       __le32 *encap_record_handle)
 {
-	struct hwrm_cfa_flow_stats_output *resp = bp->hwrm_cmd_resp_addr;
-	struct hwrm_cfa_flow_stats_input req = { 0 };
+	struct hwrm_cfa_encap_record_alloc_output *resp =
+						bp->hwrm_cmd_resp_addr;
+	struct hwrm_cfa_encap_record_alloc_input req = { 0 };
+	struct hwrm_cfa_encap_data_vxlan *encap =
+			(struct hwrm_cfa_encap_data_vxlan *)&req.encap_data;
+	struct hwrm_vxlan_ipv4_hdr *encap_ipv4 =
+				(struct hwrm_vxlan_ipv4_hdr *)encap->l3;
 	int rc;
 
-	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_STATS, -1, -1);
-	req.num_flows = cpu_to_le16(1);
-	req.flow_handle_0 = flow_handle;
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_ENCAP_RECORD_ALLOC, -1, -1);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc) {
-		stats->packets = le64_to_cpu(resp->packet_0);
-		stats->bytes = le64_to_cpu(resp->byte_0);
-		bnxt_flow_stats_calc(&bp->tc_info, flow, stats);
-	} else {
-		netdev_info(bp->dev, "error rc=%d", rc);
+	req.encap_type = CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN;
+
+	ether_addr_copy(encap->dst_mac_addr, l2_info->dmac);
+	ether_addr_copy(encap->src_mac_addr, l2_info->smac);
+	if (l2_info->num_vlans) {
+		encap->num_vlan_tags = l2_info->num_vlans;
+		encap->ovlan_tci = l2_info->inner_vlan_tci;
+		encap->ovlan_tpid = l2_info->inner_vlan_tpid;
 	}
 
+	encap_ipv4->ver_hlen = 4 << VXLAN_IPV4_HDR_VER_HLEN_VERSION_SFT;
+	encap_ipv4->ver_hlen |= 5 << VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_SFT;
+	encap_ipv4->ttl = encap_key->ttl;
+
+	encap_ipv4->dest_ip_addr = encap_key->u.ipv4.dst;
+	encap_ipv4->src_ip_addr = encap_key->u.ipv4.src;
+	encap_ipv4->protocol = IPPROTO_UDP;
+
+	encap->dst_port = encap_key->tp_dst;
+	encap->vni = tunnel_id_to_key32(encap_key->tun_id);
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		*encap_record_handle = resp->encap_record_id;
+	else
+		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
 	mutex_unlock(&bp->hwrm_cmd_lock);
+
+	return rc;
+}
+
+static int hwrm_cfa_encap_record_free(struct bnxt *bp,
+				      __le32 encap_record_handle)
+{
+	struct hwrm_cfa_encap_record_free_input req = { 0 };
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_ENCAP_RECORD_FREE, -1, -1);
+	req.encap_record_id = encap_record_handle;
+
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
 	return rc;
 }
 
@@ -484,7 +658,7 @@ static int bnxt_tc_put_l2_node(struct bnxt *bp,
 			       struct bnxt_tc_flow_node *flow_node)
 {
 	struct bnxt_tc_l2_node *l2_node = flow_node->l2_node;
-	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
 	int rc;
 
 	/* remove flow_node from the L2 shared flow list */
@@ -521,7 +695,7 @@ bnxt_tc_get_l2_node(struct bnxt *bp, struct rhashtable *l2_table,
 		rc = rhashtable_insert_fast(l2_table, &l2_node->node,
 					    ht_params);
 		if (rc) {
-			kfree(l2_node);
+			kfree_rcu(l2_node, rcu);
 			netdev_err(bp->dev,
 				   "Error: %s: rhashtable_insert_fast: %d",
 				   __func__, rc);
@@ -540,7 +714,7 @@ bnxt_tc_get_ref_flow_handle(struct bnxt *bp, struct bnxt_tc_flow *flow,
 			    struct bnxt_tc_flow_node *flow_node,
 			    __le16 *ref_flow_handle)
 {
-	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
 	struct bnxt_tc_flow_node *ref_flow_node;
 	struct bnxt_tc_l2_node *l2_node;
 
@@ -590,10 +764,386 @@ static bool bnxt_tc_can_offload(struct bnxt *bp, struct bnxt_tc_flow *flow)
 	return true;
 }
 
+/* Returns the final refcount of the node on success
+ * or a -ve error code on failure
+ */
+static int bnxt_tc_put_tunnel_node(struct bnxt *bp,
+				   struct rhashtable *tunnel_table,
+				   struct rhashtable_params *ht_params,
+				   struct bnxt_tc_tunnel_node *tunnel_node)
+{
+	int rc;
+
+	if (--tunnel_node->refcount == 0) {
+		rc =  rhashtable_remove_fast(tunnel_table, &tunnel_node->node,
+					     *ht_params);
+		if (rc) {
+			netdev_err(bp->dev, "rhashtable_remove_fast rc=%d", rc);
+			rc = -1;
+		}
+		kfree_rcu(tunnel_node, rcu);
+		return rc;
+	} else {
+		return tunnel_node->refcount;
+	}
+}
+
+/* Get (or add) either encap or decap tunnel node from/to the supplied
+ * hash table.
+ */
+static struct bnxt_tc_tunnel_node *
+bnxt_tc_get_tunnel_node(struct bnxt *bp, struct rhashtable *tunnel_table,
+			struct rhashtable_params *ht_params,
+			struct ip_tunnel_key *tun_key)
+{
+	struct bnxt_tc_tunnel_node *tunnel_node;
+	int rc;
+
+	tunnel_node = rhashtable_lookup_fast(tunnel_table, tun_key, *ht_params);
+	if (!tunnel_node) {
+		tunnel_node = kzalloc(sizeof(*tunnel_node), GFP_KERNEL);
+		if (!tunnel_node) {
+			rc = -ENOMEM;
+			goto err;
+		}
+
+		tunnel_node->key = *tun_key;
+		tunnel_node->tunnel_handle = INVALID_TUNNEL_HANDLE;
+		rc = rhashtable_insert_fast(tunnel_table, &tunnel_node->node,
+					    *ht_params);
+		if (rc) {
+			kfree_rcu(tunnel_node, rcu);
+			goto err;
+		}
+	}
+	tunnel_node->refcount++;
+	return tunnel_node;
+err:
+	netdev_info(bp->dev, "error rc=%d", rc);
+	return NULL;
+}
+
+static int bnxt_tc_get_ref_decap_handle(struct bnxt *bp,
+					struct bnxt_tc_flow *flow,
+					struct bnxt_tc_l2_key *l2_key,
+					struct bnxt_tc_flow_node *flow_node,
+					__le32 *ref_decap_handle)
+{
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	struct bnxt_tc_flow_node *ref_flow_node;
+	struct bnxt_tc_l2_node *decap_l2_node;
+
+	decap_l2_node = bnxt_tc_get_l2_node(bp, &tc_info->decap_l2_table,
+					    tc_info->decap_l2_ht_params,
+					    l2_key);
+	if (!decap_l2_node)
+		return -1;
+
+	/* If any other flow is using this decap_l2_node, use it's decap_handle
+	 * as the ref_decap_handle
+	 */
+	if (decap_l2_node->refcount > 0) {
+		ref_flow_node =
+			list_first_entry(&decap_l2_node->common_l2_flows,
+					 struct bnxt_tc_flow_node,
+					 decap_l2_list_node);
+		*ref_decap_handle = ref_flow_node->decap_node->tunnel_handle;
+	} else {
+		*ref_decap_handle = INVALID_TUNNEL_HANDLE;
+	}
+
+	/* Insert the l2_node into the flow_node so that subsequent flows
+	 * with a matching decap l2 key can use the decap_filter_handle of
+	 * this flow as their ref_decap_handle
+	 */
+	flow_node->decap_l2_node = decap_l2_node;
+	list_add(&flow_node->decap_l2_list_node,
+		 &decap_l2_node->common_l2_flows);
+	decap_l2_node->refcount++;
+	return 0;
+}
+
+static void bnxt_tc_put_decap_l2_node(struct bnxt *bp,
+				      struct bnxt_tc_flow_node *flow_node)
+{
+	struct bnxt_tc_l2_node *decap_l2_node = flow_node->decap_l2_node;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	int rc;
+
+	/* remove flow_node from the decap L2 sharing flow list */
+	list_del(&flow_node->decap_l2_list_node);
+	if (--decap_l2_node->refcount == 0) {
+		rc =  rhashtable_remove_fast(&tc_info->decap_l2_table,
+					     &decap_l2_node->node,
+					     tc_info->decap_l2_ht_params);
+		if (rc)
+			netdev_err(bp->dev, "rhashtable_remove_fast rc=%d", rc);
+		kfree_rcu(decap_l2_node, rcu);
+	}
+}
+
+static void bnxt_tc_put_decap_handle(struct bnxt *bp,
+				     struct bnxt_tc_flow_node *flow_node)
+{
+	__le32 decap_handle = flow_node->decap_node->tunnel_handle;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	int rc;
+
+	if (flow_node->decap_l2_node)
+		bnxt_tc_put_decap_l2_node(bp, flow_node);
+
+	rc = bnxt_tc_put_tunnel_node(bp, &tc_info->decap_table,
+				     &tc_info->decap_ht_params,
+				     flow_node->decap_node);
+	if (!rc && decap_handle != INVALID_TUNNEL_HANDLE)
+		hwrm_cfa_decap_filter_free(bp, decap_handle);
+}
+
+static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp,
+				       struct ip_tunnel_key *tun_key,
+				       struct bnxt_tc_l2_key *l2_info,
+				       struct net_device *real_dst_dev)
+{
+#ifdef CONFIG_INET
+	struct flowi4 flow = { {0} };
+	struct net_device *dst_dev;
+	struct neighbour *nbr;
+	struct rtable *rt;
+	int rc;
+
+	flow.flowi4_proto = IPPROTO_UDP;
+	flow.fl4_dport = tun_key->tp_dst;
+	flow.daddr = tun_key->u.ipv4.dst;
+
+	rt = ip_route_output_key(dev_net(real_dst_dev), &flow);
+	if (IS_ERR(rt)) {
+		netdev_info(bp->dev, "no route to %pI4b", &flow.daddr);
+		return -EOPNOTSUPP;
+	}
+
+	/* The route must either point to the real_dst_dev or a dst_dev that
+	 * uses the real_dst_dev.
+	 */
+	dst_dev = rt->dst.dev;
+	if (is_vlan_dev(dst_dev)) {
+#if IS_ENABLED(CONFIG_VLAN_8021Q)
+		struct vlan_dev_priv *vlan = vlan_dev_priv(dst_dev);
+
+		if (vlan->real_dev != real_dst_dev) {
+			netdev_info(bp->dev,
+				    "dst_dev(%s) doesn't use PF-if(%s)",
+				    netdev_name(dst_dev),
+				    netdev_name(real_dst_dev));
+			rc = -EOPNOTSUPP;
+			goto put_rt;
+		}
+		l2_info->inner_vlan_tci = htons(vlan->vlan_id);
+		l2_info->inner_vlan_tpid = vlan->vlan_proto;
+		l2_info->num_vlans = 1;
+#endif
+	} else if (dst_dev != real_dst_dev) {
+		netdev_info(bp->dev,
+			    "dst_dev(%s) for %pI4b is not PF-if(%s)",
+			    netdev_name(dst_dev), &flow.daddr,
+			    netdev_name(real_dst_dev));
+		rc = -EOPNOTSUPP;
+		goto put_rt;
+	}
+
+	nbr = dst_neigh_lookup(&rt->dst, &flow.daddr);
+	if (!nbr) {
+		netdev_info(bp->dev, "can't lookup neighbor for %pI4b",
+			    &flow.daddr);
+		rc = -EOPNOTSUPP;
+		goto put_rt;
+	}
+
+	tun_key->u.ipv4.src = flow.saddr;
+	tun_key->ttl = ip4_dst_hoplimit(&rt->dst);
+	neigh_ha_snapshot(l2_info->dmac, nbr, dst_dev);
+	ether_addr_copy(l2_info->smac, dst_dev->dev_addr);
+	neigh_release(nbr);
+	ip_rt_put(rt);
+
+	return 0;
+put_rt:
+	ip_rt_put(rt);
+	return rc;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int bnxt_tc_get_decap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow,
+				    struct bnxt_tc_flow_node *flow_node,
+				    __le32 *decap_filter_handle)
+{
+	struct ip_tunnel_key *decap_key = &flow->tun_key;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	struct bnxt_tc_l2_key l2_info = { {0} };
+	struct bnxt_tc_tunnel_node *decap_node;
+	struct ip_tunnel_key tun_key = { 0 };
+	struct bnxt_tc_l2_key *decap_l2_info;
+	__le32 ref_decap_handle;
+	int rc;
+
+	/* Check if there's another flow using the same tunnel decap.
+	 * If not, add this tunnel to the table and resolve the other
+	 * tunnel header fileds
+	 */
+	decap_node = bnxt_tc_get_tunnel_node(bp, &tc_info->decap_table,
+					     &tc_info->decap_ht_params,
+					     decap_key);
+	if (!decap_node)
+		return -ENOMEM;
+
+	flow_node->decap_node = decap_node;
+
+	if (decap_node->tunnel_handle != INVALID_TUNNEL_HANDLE)
+		goto done;
+
+	/* Resolve the L2 fields for tunnel decap
+	 * Resolve the route for remote vtep (saddr) of the decap key
+	 * Find it's next-hop mac addrs
+	 */
+	tun_key.u.ipv4.dst = flow->tun_key.u.ipv4.src;
+	tun_key.tp_dst = flow->tun_key.tp_dst;
+	rc = bnxt_tc_resolve_tunnel_hdrs(bp, &tun_key, &l2_info, bp->dev);
+	if (rc)
+		goto put_decap;
+
+	decap_key->ttl = tun_key.ttl;
+	decap_l2_info = &decap_node->l2_info;
+	ether_addr_copy(decap_l2_info->dmac, l2_info.smac);
+	ether_addr_copy(decap_l2_info->smac, l2_info.dmac);
+	if (l2_info.num_vlans) {
+		decap_l2_info->num_vlans = l2_info.num_vlans;
+		decap_l2_info->inner_vlan_tpid = l2_info.inner_vlan_tpid;
+		decap_l2_info->inner_vlan_tci = l2_info.inner_vlan_tci;
+	}
+	flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_ETH_ADDRS;
+
+	/* For getting a decap_filter_handle we first need to check if
+	 * there are any other decap flows that share the same tunnel L2
+	 * key and if so, pass that flow's decap_filter_handle as the
+	 * ref_decap_handle for this flow.
+	 */
+	rc = bnxt_tc_get_ref_decap_handle(bp, flow, decap_l2_info, flow_node,
+					  &ref_decap_handle);
+	if (rc)
+		goto put_decap;
+
+	/* Issue the hwrm cmd to allocate a decap filter handle */
+	rc = hwrm_cfa_decap_filter_alloc(bp, flow, decap_l2_info,
+					 ref_decap_handle,
+					 &decap_node->tunnel_handle);
+	if (rc)
+		goto put_decap_l2;
+
+done:
+	*decap_filter_handle = decap_node->tunnel_handle;
+	return 0;
+
+put_decap_l2:
+	bnxt_tc_put_decap_l2_node(bp, flow_node);
+put_decap:
+	bnxt_tc_put_tunnel_node(bp, &tc_info->decap_table,
+				&tc_info->decap_ht_params,
+				flow_node->decap_node);
+	return rc;
+}
+
+static void bnxt_tc_put_encap_handle(struct bnxt *bp,
+				     struct bnxt_tc_tunnel_node *encap_node)
+{
+	__le32 encap_handle = encap_node->tunnel_handle;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	int rc;
+
+	rc = bnxt_tc_put_tunnel_node(bp, &tc_info->encap_table,
+				     &tc_info->encap_ht_params, encap_node);
+	if (!rc && encap_handle != INVALID_TUNNEL_HANDLE)
+		hwrm_cfa_encap_record_free(bp, encap_handle);
+}
+
+/* Lookup the tunnel encap table and check if there's an encap_handle
+ * alloc'd already.
+ * If not, query L2 info via a route lookup and issue an encap_record_alloc
+ * cmd to FW.
+ */
+static int bnxt_tc_get_encap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow,
+				    struct bnxt_tc_flow_node *flow_node,
+				    __le32 *encap_handle)
+{
+	struct ip_tunnel_key *encap_key = &flow->actions.tun_encap_key;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	struct bnxt_tc_tunnel_node *encap_node;
+	int rc;
+
+	/* Check if there's another flow using the same tunnel encap.
+	 * If not, add this tunnel to the table and resolve the other
+	 * tunnel header fileds
+	 */
+	encap_node = bnxt_tc_get_tunnel_node(bp, &tc_info->encap_table,
+					     &tc_info->encap_ht_params,
+					     encap_key);
+	if (!encap_node)
+		return -ENOMEM;
+
+	flow_node->encap_node = encap_node;
+
+	if (encap_node->tunnel_handle != INVALID_TUNNEL_HANDLE)
+		goto done;
+
+	rc = bnxt_tc_resolve_tunnel_hdrs(bp, encap_key, &encap_node->l2_info,
+					 flow->actions.dst_dev);
+	if (rc)
+		goto put_encap;
+
+	/* Allocate a new tunnel encap record */
+	rc = hwrm_cfa_encap_record_alloc(bp, encap_key, &encap_node->l2_info,
+					 &encap_node->tunnel_handle);
+	if (rc)
+		goto put_encap;
+
+done:
+	*encap_handle = encap_node->tunnel_handle;
+	return 0;
+
+put_encap:
+	bnxt_tc_put_tunnel_node(bp, &tc_info->encap_table,
+				&tc_info->encap_ht_params, encap_node);
+	return rc;
+}
+
+static void bnxt_tc_put_tunnel_handle(struct bnxt *bp,
+				      struct bnxt_tc_flow *flow,
+				      struct bnxt_tc_flow_node *flow_node)
+{
+	if (flow->actions.flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP)
+		bnxt_tc_put_decap_handle(bp, flow_node);
+	else if (flow->actions.flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP)
+		bnxt_tc_put_encap_handle(bp, flow_node->encap_node);
+}
+
+static int bnxt_tc_get_tunnel_handle(struct bnxt *bp,
+				     struct bnxt_tc_flow *flow,
+				     struct bnxt_tc_flow_node *flow_node,
+				     __le32 *tunnel_handle)
+{
+	if (flow->actions.flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP)
+		return bnxt_tc_get_decap_handle(bp, flow, flow_node,
+						tunnel_handle);
+	else if (flow->actions.flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP)
+		return bnxt_tc_get_encap_handle(bp, flow, flow_node,
+						tunnel_handle);
+	else
+		return 0;
+}
 static int __bnxt_tc_del_flow(struct bnxt *bp,
 			      struct bnxt_tc_flow_node *flow_node)
 {
-	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
 	int rc;
 
 	/* send HWRM cmd to free the flow-id */
@@ -601,6 +1151,9 @@ static int __bnxt_tc_del_flow(struct bnxt *bp,
 
 	mutex_lock(&tc_info->lock);
 
+	/* release references to any tunnel encap/decap nodes */
+	bnxt_tc_put_tunnel_handle(bp, &flow_node->flow, flow_node);
+
 	/* release reference to l2 node */
 	bnxt_tc_put_l2_node(bp, flow_node);
 
@@ -633,8 +1186,9 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
 			    struct tc_cls_flower_offload *tc_flow_cmd)
 {
 	struct bnxt_tc_flow_node *new_node, *old_node;
-	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
 	struct bnxt_tc_flow *flow;
+	__le32 tunnel_handle = 0;
 	__le16 ref_flow_handle;
 	int rc;
 
@@ -672,12 +1226,19 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
 	if (rc)
 		goto unlock;
 
+	/* If the flow involves tunnel encap/decap, get tunnel_handle */
+	rc = bnxt_tc_get_tunnel_handle(bp, flow, new_node, &tunnel_handle);
+	if (rc)
+		goto put_l2;
+
 	/* send HWRM cmd to alloc the flow */
 	rc = bnxt_hwrm_cfa_flow_alloc(bp, flow, ref_flow_handle,
-				      &new_node->flow_handle);
+				      tunnel_handle, &new_node->flow_handle);
 	if (rc)
-		goto put_l2;
+		goto put_tunnel;
 
+	flow->lastused = jiffies;
+	spin_lock_init(&flow->stats_lock);
 	/* add new flow to flow-table */
 	rc = rhashtable_insert_fast(&tc_info->flow_table, &new_node->node,
 				    tc_info->flow_ht_params);
@@ -689,12 +1250,14 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
 
 hwrm_flow_free:
 	bnxt_hwrm_cfa_flow_free(bp, new_node->flow_handle);
+put_tunnel:
+	bnxt_tc_put_tunnel_handle(bp, flow, new_node);
 put_l2:
 	bnxt_tc_put_l2_node(bp, new_node);
 unlock:
 	mutex_unlock(&tc_info->lock);
 free_node:
-	kfree(new_node);
+	kfree_rcu(new_node, rcu);
 done:
 	netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d",
 		   __func__, tc_flow_cmd->cookie, rc);
@@ -704,7 +1267,7 @@ done:
 static int bnxt_tc_del_flow(struct bnxt *bp,
 			    struct tc_cls_flower_offload *tc_flow_cmd)
 {
-	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
 	struct bnxt_tc_flow_node *flow_node;
 
 	flow_node = rhashtable_lookup_fast(&tc_info->flow_table,
@@ -722,10 +1285,11 @@ static int bnxt_tc_del_flow(struct bnxt *bp,
 static int bnxt_tc_get_flow_stats(struct bnxt *bp,
 				  struct tc_cls_flower_offload *tc_flow_cmd)
 {
-	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_flow_stats stats, *curr_stats, *prev_stats;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
 	struct bnxt_tc_flow_node *flow_node;
-	struct bnxt_tc_flow_stats stats;
-	int rc;
+	struct bnxt_tc_flow *flow;
+	unsigned long lastused;
 
 	flow_node = rhashtable_lookup_fast(&tc_info->flow_table,
 					   &tc_flow_cmd->cookie,
@@ -736,22 +1300,189 @@ static int bnxt_tc_get_flow_stats(struct bnxt *bp,
 		return -1;
 	}
 
-	rc = bnxt_hwrm_cfa_flow_stats_get(bp, flow_node->flow_handle,
-					  &flow_node->flow, &stats);
+	flow = &flow_node->flow;
+	curr_stats = &flow->stats;
+	prev_stats = &flow->prev_stats;
+
+	spin_lock(&flow->stats_lock);
+	stats.packets = curr_stats->packets - prev_stats->packets;
+	stats.bytes = curr_stats->bytes - prev_stats->bytes;
+	*prev_stats = *curr_stats;
+	lastused = flow->lastused;
+	spin_unlock(&flow->stats_lock);
+
+	tcf_exts_stats_update(tc_flow_cmd->exts, stats.bytes, stats.packets,
+			      lastused);
+	return 0;
+}
+
+static int
+bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
+			     struct bnxt_tc_stats_batch stats_batch[])
+{
+	struct hwrm_cfa_flow_stats_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_cfa_flow_stats_input req = { 0 };
+	__le16 *req_flow_handles = &req.flow_handle_0;
+	int rc, i;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_STATS, -1, -1);
+	req.num_flows = cpu_to_le16(num_flows);
+	for (i = 0; i < num_flows; i++) {
+		struct bnxt_tc_flow_node *flow_node = stats_batch[i].flow_node;
+
+		req_flow_handles[i] = flow_node->flow_handle;
+	}
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc) {
+		__le64 *resp_packets = &resp->packet_0;
+		__le64 *resp_bytes = &resp->byte_0;
+
+		for (i = 0; i < num_flows; i++) {
+			stats_batch[i].hw_stats.packets =
+						le64_to_cpu(resp_packets[i]);
+			stats_batch[i].hw_stats.bytes =
+						le64_to_cpu(resp_bytes[i]);
+		}
+	} else {
+		netdev_info(bp->dev, "error rc=%d", rc);
+	}
+
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
+/* Add val to accum while handling a possible wraparound
+ * of val. Eventhough val is of type u64, its actual width
+ * is denoted by mask and will wrap-around beyond that width.
+ */
+static void accumulate_val(u64 *accum, u64 val, u64 mask)
+{
+#define low_bits(x, mask)		((x) & (mask))
+#define high_bits(x, mask)		((x) & ~(mask))
+	bool wrapped = val < low_bits(*accum, mask);
+
+	*accum = high_bits(*accum, mask) + val;
+	if (wrapped)
+		*accum += (mask + 1);
+}
+
+/* The HW counters' width is much less than 64bits.
+ * Handle possible wrap-around while updating the stat counters
+ */
+static void bnxt_flow_stats_accum(struct bnxt_tc_info *tc_info,
+				  struct bnxt_tc_flow_stats *acc_stats,
+				  struct bnxt_tc_flow_stats *hw_stats)
+{
+	accumulate_val(&acc_stats->bytes, hw_stats->bytes, tc_info->bytes_mask);
+	accumulate_val(&acc_stats->packets, hw_stats->packets,
+		       tc_info->packets_mask);
+}
+
+static int
+bnxt_tc_flow_stats_batch_update(struct bnxt *bp, int num_flows,
+				struct bnxt_tc_stats_batch stats_batch[])
+{
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	int rc, i;
+
+	rc = bnxt_hwrm_cfa_flow_stats_get(bp, num_flows, stats_batch);
 	if (rc)
 		return rc;
 
-	tcf_exts_stats_update(tc_flow_cmd->exts, stats.bytes, stats.packets, 0);
+	for (i = 0; i < num_flows; i++) {
+		struct bnxt_tc_flow_node *flow_node = stats_batch[i].flow_node;
+		struct bnxt_tc_flow *flow = &flow_node->flow;
+
+		spin_lock(&flow->stats_lock);
+		bnxt_flow_stats_accum(tc_info, &flow->stats,
+				      &stats_batch[i].hw_stats);
+		if (flow->stats.packets != flow->prev_stats.packets)
+			flow->lastused = jiffies;
+		spin_unlock(&flow->stats_lock);
+	}
+
 	return 0;
 }
 
+static int
+bnxt_tc_flow_stats_batch_prep(struct bnxt *bp,
+			      struct bnxt_tc_stats_batch stats_batch[],
+			      int *num_flows)
+{
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	struct rhashtable_iter *iter = &tc_info->iter;
+	void *flow_node;
+	int rc, i;
+
+	rc = rhashtable_walk_start(iter);
+	if (rc && rc != -EAGAIN) {
+		i = 0;
+		goto done;
+	}
+
+	rc = 0;
+	for (i = 0; i < BNXT_FLOW_STATS_BATCH_MAX; i++) {
+		flow_node = rhashtable_walk_next(iter);
+		if (IS_ERR(flow_node)) {
+			i = 0;
+			if (PTR_ERR(flow_node) == -EAGAIN) {
+				continue;
+			} else {
+				rc = PTR_ERR(flow_node);
+				goto done;
+			}
+		}
+
+		/* No more flows */
+		if (!flow_node)
+			goto done;
+
+		stats_batch[i].flow_node = flow_node;
+	}
+done:
+	rhashtable_walk_stop(iter);
+	*num_flows = i;
+	return rc;
+}
+
+void bnxt_tc_flow_stats_work(struct bnxt *bp)
+{
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	int num_flows, rc;
+
+	num_flows = atomic_read(&tc_info->flow_table.nelems);
+	if (!num_flows)
+		return;
+
+	rhashtable_walk_enter(&tc_info->flow_table, &tc_info->iter);
+
+	for (;;) {
+		rc = bnxt_tc_flow_stats_batch_prep(bp, tc_info->stats_batch,
+						   &num_flows);
+		if (rc) {
+			if (rc == -EAGAIN)
+				continue;
+			break;
+		}
+
+		if (!num_flows)
+			break;
+
+		bnxt_tc_flow_stats_batch_update(bp, num_flows,
+						tc_info->stats_batch);
+	}
+
+	rhashtable_walk_exit(&tc_info->iter);
+}
+
 int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
 			 struct tc_cls_flower_offload *cls_flower)
 {
 	int rc = 0;
 
-	if (!is_classid_clsact_ingress(cls_flower->common.classid) ||
-	    cls_flower->common.chain_index)
+	if (cls_flower->common.chain_index)
 		return -EOPNOTSUPP;
 
 	switch (cls_flower->command) {
@@ -784,19 +1515,37 @@ static const struct rhashtable_params bnxt_tc_l2_ht_params = {
 	.automatic_shrinking = true
 };
 
+static const struct rhashtable_params bnxt_tc_decap_l2_ht_params = {
+	.head_offset = offsetof(struct bnxt_tc_l2_node, node),
+	.key_offset = offsetof(struct bnxt_tc_l2_node, key),
+	.key_len = BNXT_TC_L2_KEY_LEN,
+	.automatic_shrinking = true
+};
+
+static const struct rhashtable_params bnxt_tc_tunnel_ht_params = {
+	.head_offset = offsetof(struct bnxt_tc_tunnel_node, node),
+	.key_offset = offsetof(struct bnxt_tc_tunnel_node, key),
+	.key_len = sizeof(struct ip_tunnel_key),
+	.automatic_shrinking = true
+};
+
 /* convert counter width in bits to a mask */
 #define mask(width)		((u64)~0 >> (64 - (width)))
 
 int bnxt_init_tc(struct bnxt *bp)
 {
-	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_info *tc_info;
 	int rc;
 
-	if (bp->hwrm_spec_code < 0x10800) {
+	if (bp->hwrm_spec_code < 0x10803) {
 		netdev_warn(bp->dev,
 			    "Firmware does not support TC flower offload.\n");
 		return -ENOTSUPP;
 	}
+
+	tc_info = kzalloc(sizeof(*tc_info), GFP_KERNEL);
+	if (!tc_info)
+		return -ENOMEM;
 	mutex_init(&tc_info->lock);
 
 	/* Counter widths are programmed by FW */
@@ -806,33 +1555,62 @@ int bnxt_init_tc(struct bnxt *bp)
 	tc_info->flow_ht_params = bnxt_tc_flow_ht_params;
 	rc = rhashtable_init(&tc_info->flow_table, &tc_info->flow_ht_params);
 	if (rc)
-		return rc;
+		goto free_tc_info;
 
 	tc_info->l2_ht_params = bnxt_tc_l2_ht_params;
 	rc = rhashtable_init(&tc_info->l2_table, &tc_info->l2_ht_params);
 	if (rc)
 		goto destroy_flow_table;
 
+	tc_info->decap_l2_ht_params = bnxt_tc_decap_l2_ht_params;
+	rc = rhashtable_init(&tc_info->decap_l2_table,
+			     &tc_info->decap_l2_ht_params);
+	if (rc)
+		goto destroy_l2_table;
+
+	tc_info->decap_ht_params = bnxt_tc_tunnel_ht_params;
+	rc = rhashtable_init(&tc_info->decap_table,
+			     &tc_info->decap_ht_params);
+	if (rc)
+		goto destroy_decap_l2_table;
+
+	tc_info->encap_ht_params = bnxt_tc_tunnel_ht_params;
+	rc = rhashtable_init(&tc_info->encap_table,
+			     &tc_info->encap_ht_params);
+	if (rc)
+		goto destroy_decap_table;
+
 	tc_info->enabled = true;
 	bp->dev->hw_features |= NETIF_F_HW_TC;
 	bp->dev->features |= NETIF_F_HW_TC;
+	bp->tc_info = tc_info;
 	return 0;
 
+destroy_decap_table:
+	rhashtable_destroy(&tc_info->decap_table);
+destroy_decap_l2_table:
+	rhashtable_destroy(&tc_info->decap_l2_table);
+destroy_l2_table:
+	rhashtable_destroy(&tc_info->l2_table);
 destroy_flow_table:
 	rhashtable_destroy(&tc_info->flow_table);
+free_tc_info:
+	kfree(tc_info);
 	return rc;
 }
 
 void bnxt_shutdown_tc(struct bnxt *bp)
 {
-	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
 
-	if (!tc_info->enabled)
+	if (!bnxt_tc_flower_enabled(bp))
 		return;
 
 	rhashtable_destroy(&tc_info->flow_table);
 	rhashtable_destroy(&tc_info->l2_table);
+	rhashtable_destroy(&tc_info->decap_l2_table);
+	rhashtable_destroy(&tc_info->decap_table);
+	rhashtable_destroy(&tc_info->encap_table);
+	kfree(tc_info);
+	bp->tc_info = NULL;
 }
-
-#else
-#endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
index 6c4c1ed279ef..97e09a880693 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
@@ -12,6 +12,8 @@
 
 #ifdef CONFIG_BNXT_FLOWER_OFFLOAD
 
+#include <net/ip_tunnels.h>
+
 /* Structs used for storing the filter/actions of the TC cmd.
  */
 struct bnxt_tc_l2_key {
@@ -50,6 +52,13 @@ struct bnxt_tc_l4_key {
 	};
 };
 
+struct bnxt_tc_tunnel_key {
+	struct bnxt_tc_l2_key	l2;
+	struct bnxt_tc_l3_key	l3;
+	struct bnxt_tc_l4_key	l4;
+	__be32			id;
+};
+
 struct bnxt_tc_actions {
 	u32				flags;
 #define BNXT_TC_ACTION_FLAG_FWD			BIT(0)
@@ -57,16 +66,16 @@ struct bnxt_tc_actions {
 #define BNXT_TC_ACTION_FLAG_PUSH_VLAN		BIT(3)
 #define BNXT_TC_ACTION_FLAG_POP_VLAN		BIT(4)
 #define BNXT_TC_ACTION_FLAG_DROP		BIT(5)
+#define BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP	BIT(6)
+#define BNXT_TC_ACTION_FLAG_TUNNEL_DECAP	BIT(7)
 
 	u16				dst_fid;
 	struct net_device		*dst_dev;
 	__be16				push_vlan_tpid;
 	__be16				push_vlan_tci;
-};
 
-struct bnxt_tc_flow_stats {
-	u64		packets;
-	u64		bytes;
+	/* tunnel encap */
+	struct ip_tunnel_key		tun_encap_key;
 };
 
 struct bnxt_tc_flow {
@@ -76,6 +85,16 @@ struct bnxt_tc_flow {
 #define BNXT_TC_FLOW_FLAGS_IPV6_ADDRS		BIT(3)
 #define BNXT_TC_FLOW_FLAGS_PORTS		BIT(4)
 #define BNXT_TC_FLOW_FLAGS_ICMP			BIT(5)
+#define BNXT_TC_FLOW_FLAGS_TUNL_ETH_ADDRS	BIT(6)
+#define BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS	BIT(7)
+#define BNXT_TC_FLOW_FLAGS_TUNL_IPV6_ADDRS	BIT(8)
+#define BNXT_TC_FLOW_FLAGS_TUNL_PORTS		BIT(9)
+#define BNXT_TC_FLOW_FLAGS_TUNL_ID		BIT(10)
+#define BNXT_TC_FLOW_FLAGS_TUNNEL	(BNXT_TC_FLOW_FLAGS_TUNL_ETH_ADDRS | \
+					 BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS | \
+					 BNXT_TC_FLOW_FLAGS_TUNL_IPV6_ADDRS |\
+					 BNXT_TC_FLOW_FLAGS_TUNL_PORTS |\
+					 BNXT_TC_FLOW_FLAGS_TUNL_ID)
 
 	/* flow applicable to pkts ingressing on this fid */
 	u16				src_fid;
@@ -85,6 +104,8 @@ struct bnxt_tc_flow {
 	struct bnxt_tc_l3_key		l3_mask;
 	struct bnxt_tc_l4_key		l4_key;
 	struct bnxt_tc_l4_key		l4_mask;
+	struct ip_tunnel_key		tun_key;
+	struct ip_tunnel_key		tun_mask;
 
 	struct bnxt_tc_actions		actions;
 
@@ -93,13 +114,39 @@ struct bnxt_tc_flow {
 	/* previous snap-shot of stats */
 	struct bnxt_tc_flow_stats	prev_stats;
 	unsigned long			lastused; /* jiffies */
+	/* for calculating delta from prev_stats and
+	 * updating prev_stats atomically.
+	 */
+	spinlock_t			stats_lock;
+};
+
+/* Tunnel encap/decap hash table
+ * This table is used to maintain a list of flows that use
+ * the same tunnel encap/decap params (ip_daddrs, vni, udp_dport)
+ * and the FW returned handle.
+ * A separate table is maintained for encap and decap
+ */
+struct bnxt_tc_tunnel_node {
+	struct ip_tunnel_key		key;
+	struct rhash_head		node;
+
+	/* tunnel l2 info */
+	struct bnxt_tc_l2_key		l2_info;
+
+#define	INVALID_TUNNEL_HANDLE		cpu_to_le32(0xffffffff)
+	/* tunnel handle returned by FW */
+	__le32				tunnel_handle;
+
+	u32				refcount;
+	struct rcu_head			rcu;
 };
 
 /* L2 hash table
- * This data-struct is used for L2-flow table.
- * The L2 part of a flow is stored in a hash table.
+ * The same data-struct is used for L2-flow table and L2-tunnel table.
+ * The L2 part of a flow or tunnel is stored in a hash table.
  * A flow that shares the same L2 key/mask with an
- * already existing flow must refer to it's flow handle.
+ * already existing flow/tunnel must refer to it's flow handle or
+ * decap_filter_id respectively.
  */
 struct bnxt_tc_l2_node {
 	/* hash key: first 16b of key */
@@ -110,7 +157,7 @@ struct bnxt_tc_l2_node {
 	/* a linked list of flows that share the same l2 key */
 	struct list_head	common_l2_flows;
 
-	/* number of flows sharing the l2 key */
+	/* number of flows/tunnels sharing the l2 key */
 	u16			refcount;
 
 	struct rcu_head		rcu;
@@ -130,6 +177,16 @@ struct bnxt_tc_flow_node {
 	/* for the shared_flows list maintained in l2_node */
 	struct list_head		l2_list_node;
 
+	/* tunnel encap related */
+	struct bnxt_tc_tunnel_node	*encap_node;
+
+	/* tunnel decap related */
+	struct bnxt_tc_tunnel_node	*decap_node;
+	/* L2 node in tunnel-l2 hashtable that shares flow's tunnel l2 key */
+	struct bnxt_tc_l2_node		*decap_l2_node;
+	/* for the shared_flows list maintained in tunnel decap l2_node */
+	struct list_head		decap_l2_list_node;
+
 	struct rcu_head			rcu;
 };
 
@@ -137,6 +194,12 @@ int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
 			 struct tc_cls_flower_offload *cls_flower);
 int bnxt_init_tc(struct bnxt *bp);
 void bnxt_shutdown_tc(struct bnxt *bp);
+void bnxt_tc_flow_stats_work(struct bnxt *bp);
+
+static inline bool bnxt_tc_flower_enabled(struct bnxt *bp)
+{
+	return bp->tc_info && bp->tc_info->enabled;
+}
 
 #else /* CONFIG_BNXT_FLOWER_OFFLOAD */
 
@@ -154,5 +217,14 @@ static inline int bnxt_init_tc(struct bnxt *bp)
 static inline void bnxt_shutdown_tc(struct bnxt *bp)
 {
 }
+
+static inline void bnxt_tc_flow_stats_work(struct bnxt *bp)
+{
+}
+
+static inline bool bnxt_tc_flower_enabled(struct bnxt *bp)
+{
+	return false;
+}
 #endif /* CONFIG_BNXT_FLOWER_OFFLOAD */
 #endif /* BNXT_TC_H */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index e75db04c6cdc..b6aa7db99705 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -16,6 +16,7 @@
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_vfr.h"
+#include "bnxt_devlink.h"
 #include "bnxt_tc.h"
 
 #ifdef CONFIG_BNXT_SRIOV
@@ -115,13 +116,17 @@ bnxt_vf_rep_get_stats64(struct net_device *dev,
 	stats->tx_bytes = vf_rep->tx_stats.bytes;
 }
 
-static int bnxt_vf_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
-				void *type_data)
+static int bnxt_vf_rep_setup_tc_block_cb(enum tc_setup_type type,
+					 void *type_data,
+					 void *cb_priv)
 {
-	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+	struct bnxt_vf_rep *vf_rep = cb_priv;
 	struct bnxt *bp = vf_rep->bp;
 	int vf_fid = bp->pf.vf[vf_rep->vf_idx].fw_fid;
 
+	if (!bnxt_tc_flower_enabled(vf_rep->bp) || !tc_can_offload(bp->dev))
+		return -EOPNOTSUPP;
+
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return bnxt_tc_setup_flower(bp, vf_fid, type_data);
@@ -130,6 +135,40 @@ static int bnxt_vf_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	}
 }
 
+static int bnxt_vf_rep_setup_tc_block(struct net_device *dev,
+				      struct tc_block_offload *f)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block,
+					     bnxt_vf_rep_setup_tc_block_cb,
+					     vf_rep, vf_rep);
+		return 0;
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block,
+					bnxt_vf_rep_setup_tc_block_cb, vf_rep);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int bnxt_vf_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
+				void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return bnxt_vf_rep_setup_tc_block(dev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code)
 {
 	u16 vf_idx;
@@ -416,7 +455,7 @@ err:
 }
 
 /* Devlink related routines */
-static int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 {
 	struct bnxt *bp = bnxt_get_bp_from_dl(devlink);
 
@@ -424,7 +463,7 @@ static int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 	return 0;
 }
 
-static int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode)
+int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode)
 {
 	struct bnxt *bp = bnxt_get_bp_from_dl(devlink);
 	int rc = 0;
@@ -462,52 +501,4 @@ done:
 	return rc;
 }
 
-static const struct devlink_ops bnxt_dl_ops = {
-	.eswitch_mode_set = bnxt_dl_eswitch_mode_set,
-	.eswitch_mode_get = bnxt_dl_eswitch_mode_get
-};
-
-int bnxt_dl_register(struct bnxt *bp)
-{
-	struct devlink *dl;
-	int rc;
-
-	if (!pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV))
-		return 0;
-
-	if (bp->hwrm_spec_code < 0x10800) {
-		netdev_warn(bp->dev, "Firmware does not support SR-IOV E-Switch SWITCHDEV mode.\n");
-		return -ENOTSUPP;
-	}
-
-	dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
-	if (!dl) {
-		netdev_warn(bp->dev, "devlink_alloc failed");
-		return -ENOMEM;
-	}
-
-	bnxt_link_bp_to_dl(bp, dl);
-	bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
-	rc = devlink_register(dl, &bp->pdev->dev);
-	if (rc) {
-		bnxt_link_bp_to_dl(bp, NULL);
-		devlink_free(dl);
-		netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc);
-		return rc;
-	}
-
-	return 0;
-}
-
-void bnxt_dl_unregister(struct bnxt *bp)
-{
-	struct devlink *dl = bp->dl;
-
-	if (!dl)
-		return;
-
-	devlink_unregister(dl);
-	devlink_free(dl);
-}
-
 #endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
index 7787cd24606a..fb06bbe70e42 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
@@ -14,31 +14,6 @@
 
 #define	MAX_CFA_CODE			65536
 
-/* Struct to hold housekeeping info needed by devlink interface */
-struct bnxt_dl {
-	struct bnxt *bp;	/* back ptr to the controlling dev */
-};
-
-static inline struct bnxt *bnxt_get_bp_from_dl(struct devlink *dl)
-{
-	return ((struct bnxt_dl *)devlink_priv(dl))->bp;
-}
-
-/* To clear devlink pointer from bp, pass NULL dl */
-static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
-{
-	bp->dl = dl;
-
-	/* add a back pointer in dl to bp */
-	if (dl) {
-		struct bnxt_dl *bp_dl = devlink_priv(dl);
-
-		bp_dl->bp = bp;
-	}
-}
-
-int bnxt_dl_register(struct bnxt *bp);
-void bnxt_dl_unregister(struct bnxt *bp);
 void bnxt_vf_reps_destroy(struct bnxt *bp);
 void bnxt_vf_reps_close(struct bnxt *bp);
 void bnxt_vf_reps_open(struct bnxt *bp);
@@ -53,16 +28,10 @@ static inline u16 bnxt_vf_rep_get_fid(struct net_device *dev)
 	return bp->pf.vf[vf_rep->vf_idx].fw_fid;
 }
 
-#else
-
-static inline int bnxt_dl_register(struct bnxt *bp)
-{
-	return 0;
-}
+int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode);
+int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode);
 
-static inline void bnxt_dl_unregister(struct bnxt *bp)
-{
-}
+#else
 
 static inline void bnxt_vf_reps_close(struct bnxt *bp)
 {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index d8f0c837b72c..06ce63c00821 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -94,6 +94,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 
 	xdp.data_hard_start = *data_ptr - offset;
 	xdp.data = *data_ptr;
+	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = *data_ptr + *len;
 	orig_data = xdp.data;
 	mapping = rx_buf->mapping - bp->rx_dma_offset;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 9cebca896913..24b4f4ceceef 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -488,15 +488,13 @@ static void bcmgenet_complete(struct net_device *dev)
 static int bcmgenet_get_link_ksettings(struct net_device *dev,
 				       struct ethtool_link_ksettings *cmd)
 {
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-
 	if (!netif_running(dev))
 		return -EINVAL;
 
-	if (!priv->phydev)
+	if (!dev->phydev)
 		return -ENODEV;
 
-	phy_ethtool_ksettings_get(priv->phydev, cmd);
+	phy_ethtool_ksettings_get(dev->phydev, cmd);
 
 	return 0;
 }
@@ -504,15 +502,13 @@ static int bcmgenet_get_link_ksettings(struct net_device *dev,
 static int bcmgenet_set_link_ksettings(struct net_device *dev,
 				       const struct ethtool_link_ksettings *cmd)
 {
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-
 	if (!netif_running(dev))
 		return -EINVAL;
 
-	if (!priv->phydev)
+	if (!dev->phydev)
 		return -ENODEV;
 
-	return phy_ethtool_ksettings_set(priv->phydev, cmd);
+	return phy_ethtool_ksettings_set(dev->phydev, cmd);
 }
 
 static int bcmgenet_set_rx_csum(struct net_device *dev,
@@ -1042,11 +1038,14 @@ static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_eee *e)
 	if (GENET_IS_V1(priv))
 		return -EOPNOTSUPP;
 
+	if (!dev->phydev)
+		return -ENODEV;
+
 	e->eee_enabled = p->eee_enabled;
 	e->eee_active = p->eee_active;
 	e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER);
 
-	return phy_ethtool_get_eee(priv->phydev, e);
+	return phy_ethtool_get_eee(dev->phydev, e);
 }
 
 static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
@@ -1058,12 +1057,15 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
 	if (GENET_IS_V1(priv))
 		return -EOPNOTSUPP;
 
+	if (!dev->phydev)
+		return -ENODEV;
+
 	p->eee_enabled = e->eee_enabled;
 
 	if (!p->eee_enabled) {
 		bcmgenet_eee_enable_set(dev, false);
 	} else {
-		ret = phy_init_eee(priv->phydev, 0);
+		ret = phy_init_eee(dev->phydev, 0);
 		if (ret) {
 			netif_err(priv, hw, dev, "EEE initialization failed\n");
 			return ret;
@@ -1073,7 +1075,7 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
 		bcmgenet_eee_enable_set(dev, true);
 	}
 
-	return phy_ethtool_set_eee(priv->phydev, e);
+	return phy_ethtool_set_eee(dev->phydev, e);
 }
 
 /* standard ethtool support functions. */
@@ -1107,7 +1109,7 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 
 	switch (mode) {
 	case GENET_POWER_CABLE_SENSE:
-		phy_detach(priv->phydev);
+		phy_detach(priv->dev->phydev);
 		break;
 
 	case GENET_POWER_WOL_MAGIC:
@@ -1172,7 +1174,6 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 		}
 		bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
 		bcmgenet_phy_power_set(priv->dev, true);
-		bcmgenet_mii_reset(priv->dev);
 		break;
 
 	case GENET_POWER_CABLE_SENSE:
@@ -1193,15 +1194,13 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 /* ioctl handle special commands that are not present in ethtool. */
 static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-
 	if (!netif_running(dev))
 		return -EINVAL;
 
-	if (!priv->phydev)
+	if (!dev->phydev)
 		return -ENODEV;
 
-	return phy_mii_ioctl(priv->phydev, rq, cmd);
+	return phy_mii_ioctl(dev->phydev, rq, cmd);
 }
 
 static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv,
@@ -1405,11 +1404,10 @@ static unsigned int bcmgenet_tx_reclaim(struct net_device *dev,
 				struct bcmgenet_tx_ring *ring)
 {
 	unsigned int released;
-	unsigned long flags;
 
-	spin_lock_irqsave(&ring->lock, flags);
+	spin_lock_bh(&ring->lock);
 	released = __bcmgenet_tx_reclaim(dev, ring);
-	spin_unlock_irqrestore(&ring->lock, flags);
+	spin_unlock_bh(&ring->lock);
 
 	return released;
 }
@@ -1420,15 +1418,14 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
 		container_of(napi, struct bcmgenet_tx_ring, napi);
 	unsigned int work_done = 0;
 	struct netdev_queue *txq;
-	unsigned long flags;
 
-	spin_lock_irqsave(&ring->lock, flags);
+	spin_lock(&ring->lock);
 	work_done = __bcmgenet_tx_reclaim(ring->priv->dev, ring);
 	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
 		txq = netdev_get_tx_queue(ring->priv->dev, ring->queue);
 		netif_tx_wake_queue(txq);
 	}
-	spin_unlock_irqrestore(&ring->lock, flags);
+	spin_unlock(&ring->lock);
 
 	if (work_done == 0) {
 		napi_complete(napi);
@@ -1523,7 +1520,6 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct bcmgenet_tx_ring *ring = NULL;
 	struct enet_cb *tx_cb_ptr;
 	struct netdev_queue *txq;
-	unsigned long flags = 0;
 	int nr_frags, index;
 	dma_addr_t mapping;
 	unsigned int size;
@@ -1550,7 +1546,7 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 
-	spin_lock_irqsave(&ring->lock, flags);
+	spin_lock(&ring->lock);
 	if (ring->free_bds <= (nr_frags + 1)) {
 		if (!netif_tx_queue_stopped(txq)) {
 			netif_tx_stop_queue(txq);
@@ -1584,8 +1580,7 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 	for (i = 0; i <= nr_frags; i++) {
 		tx_cb_ptr = bcmgenet_get_txcb(priv, ring);
 
-		if (unlikely(!tx_cb_ptr))
-			BUG();
+		BUG_ON(!tx_cb_ptr);
 
 		if (!i) {
 			/* Transmit single SKB or head of fragment list */
@@ -1645,7 +1640,7 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 		bcmgenet_tdma_ring_writel(priv, ring->index,
 					  ring->prod_index, TDMA_PROD_INDEX);
 out:
-	spin_unlock_irqrestore(&ring->lock, flags);
+	spin_unlock(&ring->lock);
 
 	return ret;
 
@@ -1935,12 +1930,8 @@ static void umac_enable_set(struct bcmgenet_priv *priv, u32 mask, bool enable)
 		usleep_range(1000, 2000);
 }
 
-static int reset_umac(struct bcmgenet_priv *priv)
+static void reset_umac(struct bcmgenet_priv *priv)
 {
-	struct device *kdev = &priv->pdev->dev;
-	unsigned int timeout = 0;
-	u32 reg;
-
 	/* 7358a0/7552a0: bad default in RBUF_FLUSH_CTRL.umac_sw_rst */
 	bcmgenet_rbuf_ctrl_set(priv, 0);
 	udelay(10);
@@ -1948,23 +1939,10 @@ static int reset_umac(struct bcmgenet_priv *priv)
 	/* disable MAC while updating its registers */
 	bcmgenet_umac_writel(priv, 0, UMAC_CMD);
 
-	/* issue soft reset, wait for it to complete */
-	bcmgenet_umac_writel(priv, CMD_SW_RESET, UMAC_CMD);
-	while (timeout++ < 1000) {
-		reg = bcmgenet_umac_readl(priv, UMAC_CMD);
-		if (!(reg & CMD_SW_RESET))
-			return 0;
-
-		udelay(1);
-	}
-
-	if (timeout == 1000) {
-		dev_err(kdev,
-			"timeout waiting for MAC to come out of reset\n");
-		return -ETIMEDOUT;
-	}
-
-	return 0;
+	/* issue soft reset with (rg)mii loopback to ensure a stable rxclk */
+	bcmgenet_umac_writel(priv, CMD_SW_RESET | CMD_LCL_LOOP_EN, UMAC_CMD);
+	udelay(2);
+	bcmgenet_umac_writel(priv, 0, UMAC_CMD);
 }
 
 static void bcmgenet_intr_disable(struct bcmgenet_priv *priv)
@@ -1994,20 +1972,16 @@ static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
 }
 
-static int init_umac(struct bcmgenet_priv *priv)
+static void init_umac(struct bcmgenet_priv *priv)
 {
 	struct device *kdev = &priv->pdev->dev;
-	int ret;
 	u32 reg;
 	u32 int0_enable = 0;
 
 	dev_dbg(&priv->pdev->dev, "bcmgenet: init_umac\n");
 
-	ret = reset_umac(priv);
-	if (ret)
-		return ret;
+	reset_umac(priv);
 
-	bcmgenet_umac_writel(priv, 0, UMAC_CMD);
 	/* clear tx/rx counter */
 	bcmgenet_umac_writel(priv,
 			     MIB_RESET_RX | MIB_RESET_TX | MIB_RESET_RUNT,
@@ -2046,8 +2020,6 @@ static int init_umac(struct bcmgenet_priv *priv)
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
 
 	dev_dbg(kdev, "done init umac\n");
-
-	return 0;
 }
 
 /* Initialize a Tx ring along with corresponding hardware registers */
@@ -2104,6 +2076,10 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 				  TDMA_WRITE_PTR);
 	bcmgenet_tdma_ring_writel(priv, index, end_ptr * words_per_bd - 1,
 				  DMA_END_ADDR);
+
+	/* Initialize Tx NAPI */
+	netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
+		       NAPI_POLL_WEIGHT);
 }
 
 /* Initialize a RDMA ring */
@@ -2135,6 +2111,10 @@ static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
 	if (ret)
 		return ret;
 
+	/* Initialize Rx NAPI */
+	netif_napi_add(priv->dev, &ring->napi, bcmgenet_rx_poll,
+		       NAPI_POLL_WEIGHT);
+
 	bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_PROD_INDEX);
 	bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_CONS_INDEX);
 	bcmgenet_rdma_ring_writel(priv, index, 1, DMA_MBUF_DONE_THRESH);
@@ -2159,50 +2139,27 @@ static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
 	return ret;
 }
 
-static void bcmgenet_init_tx_napi(struct bcmgenet_priv *priv)
-{
-	unsigned int i;
-	struct bcmgenet_tx_ring *ring;
-
-	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
-		ring = &priv->tx_rings[i];
-		netif_tx_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll, 64);
-	}
-
-	ring = &priv->tx_rings[DESC_INDEX];
-	netif_tx_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll, 64);
-}
-
 static void bcmgenet_enable_tx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
-	u32 int0_enable = UMAC_IRQ_TXDMA_DONE;
-	u32 int1_enable = 0;
 	struct bcmgenet_tx_ring *ring;
 
 	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_enable(&ring->napi);
-		int1_enable |= (1 << i);
+		ring->int_enable(ring);
 	}
 
 	ring = &priv->tx_rings[DESC_INDEX];
 	napi_enable(&ring->napi);
-
-	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
-	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
+	ring->int_enable(ring);
 }
 
 static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
-	u32 int0_disable = UMAC_IRQ_TXDMA_DONE;
-	u32 int1_disable = 0xffff;
 	struct bcmgenet_tx_ring *ring;
 
-	bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET);
-	bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET);
-
 	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_disable(&ring->napi);
@@ -2286,9 +2243,6 @@ static void bcmgenet_init_tx_queues(struct net_device *dev)
 	bcmgenet_tdma_writel(priv, dma_priority[1], DMA_PRIORITY_1);
 	bcmgenet_tdma_writel(priv, dma_priority[2], DMA_PRIORITY_2);
 
-	/* Initialize Tx NAPI */
-	bcmgenet_init_tx_napi(priv);
-
 	/* Enable Tx queues */
 	bcmgenet_tdma_writel(priv, ring_cfg, DMA_RING_CFG);
 
@@ -2298,50 +2252,27 @@ static void bcmgenet_init_tx_queues(struct net_device *dev)
 	bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL);
 }
 
-static void bcmgenet_init_rx_napi(struct bcmgenet_priv *priv)
-{
-	unsigned int i;
-	struct bcmgenet_rx_ring *ring;
-
-	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
-		ring = &priv->rx_rings[i];
-		netif_napi_add(priv->dev, &ring->napi, bcmgenet_rx_poll, 64);
-	}
-
-	ring = &priv->rx_rings[DESC_INDEX];
-	netif_napi_add(priv->dev, &ring->napi, bcmgenet_rx_poll, 64);
-}
-
 static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
-	u32 int0_enable = UMAC_IRQ_RXDMA_DONE;
-	u32 int1_enable = 0;
 	struct bcmgenet_rx_ring *ring;
 
 	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_enable(&ring->napi);
-		int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i));
+		ring->int_enable(ring);
 	}
 
 	ring = &priv->rx_rings[DESC_INDEX];
 	napi_enable(&ring->napi);
-
-	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
-	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
+	ring->int_enable(ring);
 }
 
 static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
-	u32 int0_disable = UMAC_IRQ_RXDMA_DONE;
-	u32 int1_disable = 0xffff << UMAC_IRQ1_RX_INTR_SHIFT;
 	struct bcmgenet_rx_ring *ring;
 
-	bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET);
-	bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET);
-
 	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_disable(&ring->napi);
@@ -2414,9 +2345,6 @@ static int bcmgenet_init_rx_queues(struct net_device *dev)
 	ring_cfg |= (1 << DESC_INDEX);
 	dma_ctrl |= (1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT));
 
-	/* Initialize Rx NAPI */
-	bcmgenet_init_rx_napi(priv);
-
 	/* Enable rings */
 	bcmgenet_rdma_writel(priv, ring_cfg, DMA_RING_CFG);
 
@@ -2505,9 +2433,6 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
 	bcmgenet_fini_rx_napi(priv);
 	bcmgenet_fini_tx_napi(priv);
 
-	/* disable DMA */
-	bcmgenet_dma_teardown(priv);
-
 	for (i = 0; i < priv->num_tx_bds; i++) {
 		cb = priv->tx_cbs + i;
 		skb = bcmgenet_free_tx_cb(&priv->pdev->dev, cb);
@@ -2590,27 +2515,20 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
 /* Interrupt bottom half */
 static void bcmgenet_irq_task(struct work_struct *work)
 {
-	unsigned long flags;
 	unsigned int status;
 	struct bcmgenet_priv *priv = container_of(
 			work, struct bcmgenet_priv, bcmgenet_irq_work);
 
 	netif_dbg(priv, intr, priv->dev, "%s\n", __func__);
 
-	spin_lock_irqsave(&priv->lock, flags);
+	spin_lock_irq(&priv->lock);
 	status = priv->irq0_stat;
 	priv->irq0_stat = 0;
-	spin_unlock_irqrestore(&priv->lock, flags);
-
-	if (status & UMAC_IRQ_MPD_R) {
-		netif_dbg(priv, wol, priv->dev,
-			  "magic packet detected, waking up\n");
-		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
-	}
+	spin_unlock_irq(&priv->lock);
 
 	/* Link UP/DOWN event */
 	if (status & UMAC_IRQ_LINK_EVENT)
-		phy_mac_interrupt(priv->phydev,
+		phy_mac_interrupt(priv->dev->phydev,
 				  !!(status & UMAC_IRQ_LINK_UP));
 }
 
@@ -2698,23 +2616,13 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 		}
 	}
 
-	if (priv->irq0_stat & (UMAC_IRQ_PHY_DET_R |
-				UMAC_IRQ_PHY_DET_F |
-				UMAC_IRQ_LINK_EVENT |
-				UMAC_IRQ_HFB_SM |
-				UMAC_IRQ_HFB_MM)) {
-		/* all other interested interrupts handled in bottom half */
-		schedule_work(&priv->bcmgenet_irq_work);
-	}
-
 	if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
 		status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
 		wake_up(&priv->wq);
 	}
 
 	/* all other interested interrupts handled in bottom half */
-	status &= (UMAC_IRQ_LINK_EVENT |
-		   UMAC_IRQ_MPD_R);
+	status &= UMAC_IRQ_LINK_EVENT;
 	if (status) {
 		/* Save irq status for bottom-half processing. */
 		spin_lock_irqsave(&priv->lock, flags);
@@ -2849,16 +2757,16 @@ static void bcmgenet_netif_start(struct net_device *dev)
 
 	/* Start the network engine */
 	bcmgenet_enable_rx_napi(priv);
-	bcmgenet_enable_tx_napi(priv);
 
 	umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true);
 
 	netif_tx_start_all_queues(dev);
+	bcmgenet_enable_tx_napi(priv);
 
 	/* Monitor link interrupts now */
 	bcmgenet_link_intr_enable(priv);
 
-	phy_start(priv->phydev);
+	phy_start(dev->phydev);
 }
 
 static int bcmgenet_open(struct net_device *dev)
@@ -2882,12 +2790,7 @@ static int bcmgenet_open(struct net_device *dev)
 	/* take MAC out of reset */
 	bcmgenet_umac_reset(priv);
 
-	ret = init_umac(priv);
-	if (ret)
-		goto err_clk_disable;
-
-	/* disable ethernet MAC while updating its registers */
-	umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, false);
+	init_umac(priv);
 
 	/* Make sure we reflect the value of CRC_CMD_FWD */
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
@@ -2946,6 +2849,7 @@ err_irq1:
 err_irq0:
 	free_irq(priv->irq0, priv);
 err_fini_dma:
+	bcmgenet_dma_teardown(priv);
 	bcmgenet_fini_dma(priv);
 err_clk_disable:
 	if (priv->internal_phy)
@@ -2958,11 +2862,20 @@ static void bcmgenet_netif_stop(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
+	bcmgenet_disable_tx_napi(priv);
 	netif_tx_stop_all_queues(dev);
-	phy_stop(priv->phydev);
-	bcmgenet_intr_disable(priv);
+
+	/* Disable MAC receive */
+	umac_enable_set(priv, CMD_RX_EN, false);
+
+	bcmgenet_dma_teardown(priv);
+
+	/* Disable MAC transmit. TX DMA disabled must be done before this */
+	umac_enable_set(priv, CMD_TX_EN, false);
+
+	phy_stop(dev->phydev);
 	bcmgenet_disable_rx_napi(priv);
-	bcmgenet_disable_tx_napi(priv);
+	bcmgenet_intr_disable(priv);
 
 	/* Wait for pending work items to complete. Since interrupts are
 	 * disabled no new work will be scheduled.
@@ -2973,33 +2886,23 @@ static void bcmgenet_netif_stop(struct net_device *dev)
 	priv->old_speed = -1;
 	priv->old_duplex = -1;
 	priv->old_pause = -1;
+
+	/* tx reclaim */
+	bcmgenet_tx_reclaim_all(dev);
+	bcmgenet_fini_dma(priv);
 }
 
 static int bcmgenet_close(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	int ret;
+	int ret = 0;
 
 	netif_dbg(priv, ifdown, dev, "bcmgenet_close\n");
 
 	bcmgenet_netif_stop(dev);
 
 	/* Really kill the PHY state machine and disconnect from it */
-	phy_disconnect(priv->phydev);
-
-	/* Disable MAC receive */
-	umac_enable_set(priv, CMD_RX_EN, false);
-
-	ret = bcmgenet_dma_teardown(priv);
-	if (ret)
-		return ret;
-
-	/* Disable MAC transmit. TX DMA disabled must be done before this */
-	umac_enable_set(priv, CMD_TX_EN, false);
-
-	/* tx reclaim */
-	bcmgenet_tx_reclaim_all(dev);
-	bcmgenet_fini_dma(priv);
+	phy_disconnect(dev->phydev);
 
 	free_irq(priv->irq0, priv);
 	free_irq(priv->irq1, priv);
@@ -3018,7 +2921,6 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 	u32 p_index, c_index, intsts, intmsk;
 	struct netdev_queue *txq;
 	unsigned int free_bds;
-	unsigned long flags;
 	bool txq_stopped;
 
 	if (!netif_msg_tx_err(priv))
@@ -3026,7 +2928,7 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 
 	txq = netdev_get_tx_queue(priv->dev, ring->queue);
 
-	spin_lock_irqsave(&ring->lock, flags);
+	spin_lock(&ring->lock);
 	if (ring->index == DESC_INDEX) {
 		intsts = ~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
 		intmsk = UMAC_IRQ_TXDMA_DONE | UMAC_IRQ_TXDMA_MBDONE;
@@ -3038,7 +2940,7 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 	p_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_PROD_INDEX);
 	txq_stopped = netif_tx_queue_stopped(txq);
 	free_bds = ring->free_bds;
-	spin_unlock_irqrestore(&ring->lock, flags);
+	spin_unlock(&ring->lock);
 
 	netif_err(priv, tx_err, priv->dev, "Ring %d queue %d status summary\n"
 		  "TX queue status: %s, interrupts: %s\n"
@@ -3564,9 +3466,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	    !strcasecmp(phy_mode_str, "internal"))
 		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
 
-	err = reset_umac(priv);
-	if (err)
-		goto err_clk_disable;
+	reset_umac(priv);
 
 	err = bcmgenet_mii_init(dev);
 	if (err)
@@ -3614,7 +3514,7 @@ static int bcmgenet_suspend(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	int ret;
+	int ret = 0;
 
 	if (!netif_running(dev))
 		return 0;
@@ -3622,24 +3522,10 @@ static int bcmgenet_suspend(struct device *d)
 	bcmgenet_netif_stop(dev);
 
 	if (!device_may_wakeup(d))
-		phy_suspend(priv->phydev);
+		phy_suspend(dev->phydev);
 
 	netif_device_detach(dev);
 
-	/* Disable MAC receive */
-	umac_enable_set(priv, CMD_RX_EN, false);
-
-	ret = bcmgenet_dma_teardown(priv);
-	if (ret)
-		return ret;
-
-	/* Disable MAC transmit. TX DMA disabled must be done before this */
-	umac_enable_set(priv, CMD_TX_EN, false);
-
-	/* tx reclaim */
-	bcmgenet_tx_reclaim_all(dev);
-	bcmgenet_fini_dma(priv);
-
 	/* Prepare the device for Wake-on-LAN and switch to the slow clock */
 	if (device_may_wakeup(d) && priv->wolopts) {
 		ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC);
@@ -3678,21 +3564,17 @@ static int bcmgenet_resume(struct device *d)
 
 	bcmgenet_umac_reset(priv);
 
-	ret = init_umac(priv);
-	if (ret)
-		goto out_clk_disable;
+	init_umac(priv);
 
 	/* From WOL-enabled suspend, switch to regular clock */
 	if (priv->wolopts)
 		clk_disable_unprepare(priv->clk_wol);
 
-	phy_init_hw(priv->phydev);
+	phy_init_hw(dev->phydev);
+
 	/* Speed settings must be restored */
 	bcmgenet_mii_config(priv->dev, false);
 
-	/* disable ethernet MAC while updating its registers */
-	umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, false);
-
 	bcmgenet_set_hw_addr(priv, dev->dev_addr);
 
 	if (priv->internal_phy) {
@@ -3720,7 +3602,7 @@ static int bcmgenet_resume(struct device *d)
 	netif_device_attach(dev);
 
 	if (!device_may_wakeup(d))
-		phy_resume(priv->phydev);
+		phy_resume(dev->phydev);
 
 	if (priv->eee.eee_enabled)
 		bcmgenet_eee_enable_set(dev, true);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 4c49d0b97748..3c50431ccd2a 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -617,7 +617,6 @@ struct bcmgenet_priv {
 
 	/* MDIO bus variables */
 	wait_queue_head_t wq;
-	struct phy_device *phydev;
 	bool internal_phy;
 	struct device_node *phy_dn;
 	struct device_node *mdio_dn;
@@ -711,7 +710,6 @@ int bcmgenet_mii_init(struct net_device *dev);
 int bcmgenet_mii_config(struct net_device *dev, bool init);
 int bcmgenet_mii_probe(struct net_device *dev);
 void bcmgenet_mii_exit(struct net_device *dev);
-void bcmgenet_mii_reset(struct net_device *dev);
 void bcmgenet_phy_power_set(struct net_device *dev, bool enable);
 void bcmgenet_mii_setup(struct net_device *dev);
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 18f5723be2c9..5333274a283c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -34,7 +34,7 @@
 void bcmgenet_mii_setup(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	u32 reg, cmd_bits = 0;
 	bool status_changed = false;
 
@@ -121,22 +121,6 @@ static int bcmgenet_fixed_phy_link_update(struct net_device *dev,
 	return 0;
 }
 
-/* Perform a voluntary PHY software reset, since the EPHY is very finicky about
- * not doing it and will start corrupting packets
- */
-void bcmgenet_mii_reset(struct net_device *dev)
-{
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-
-	if (GENET_IS_V4(priv))
-		return;
-
-	if (priv->phydev) {
-		phy_init_hw(priv->phydev);
-		phy_start_aneg(priv->phydev);
-	}
-}
-
 void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
@@ -182,14 +166,14 @@ static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 	}
 
 	if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
-		fixed_phy_set_link_update(priv->phydev,
+		fixed_phy_set_link_update(priv->dev->phydev,
 					  bcmgenet_fixed_phy_link_update);
 }
 
 int bcmgenet_mii_config(struct net_device *dev, bool init)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	struct device *kdev = &priv->pdev->dev;
 	const char *phy_name = NULL;
 	u32 id_mode_dis = 0;
@@ -236,7 +220,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 		 * capabilities, use that knowledge to also configure the
 		 * Reverse MII interface correctly.
 		 */
-		if ((priv->phydev->supported & PHY_BASIC_FEATURES) ==
+		if ((dev->phydev->supported & PHY_BASIC_FEATURES) ==
 				PHY_BASIC_FEATURES)
 			port_ctrl = PORT_MODE_EXT_RVMII_25;
 		else
@@ -306,7 +290,7 @@ int bcmgenet_mii_probe(struct net_device *dev)
 			return -ENODEV;
 		}
 	} else {
-		phydev = priv->phydev;
+		phydev = dev->phydev;
 		phydev->dev_flags = phy_flags;
 
 		ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup,
@@ -317,8 +301,6 @@ int bcmgenet_mii_probe(struct net_device *dev)
 		}
 	}
 
-	priv->phydev = phydev;
-
 	/* Configure port multiplexer based on what the probed PHY device since
 	 * reading the 'max-speed' property determines the maximum supported
 	 * PHY speed which is needed for bcmgenet_mii_config() to configure
@@ -326,7 +308,7 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	 */
 	ret = bcmgenet_mii_config(dev, true);
 	if (ret) {
-		phy_disconnect(priv->phydev);
+		phy_disconnect(dev->phydev);
 		return ret;
 	}
 
@@ -336,7 +318,7 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	 * Ethernet MAC ISRs
 	 */
 	if (priv->internal_phy)
-		priv->phydev->irq = PHY_IGNORE_INTERRUPT;
+		dev->phydev->irq = PHY_IGNORE_INTERRUPT;
 
 	return 0;
 }
@@ -545,7 +527,6 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
 
 	}
 
-	priv->phydev = phydev;
 	priv->phy_interface = pd->phy_interface;
 
 	return 0;
@@ -590,5 +571,4 @@ void bcmgenet_mii_exit(struct net_device *dev)
 		of_phy_deregister_fixed_link(dn);
 	of_node_put(priv->phy_dn);
 	platform_device_unregister(priv->mii_pdev);
-	platform_device_put(priv->mii_pdev);
 }
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 656e6af70f0a..d8d5f207c759 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -11087,9 +11087,7 @@ static void tg3_timer_init(struct tg3 *tp)
 	tp->asf_multiplier = (HZ / tp->timer_offset) *
 			     TG3_FW_UPDATE_FREQ_SEC;
 
-	init_timer(&tp->timer);
-	tp->timer.data = (unsigned long) tp;
-	tp->timer.function = tg3_timer;
+	setup_timer(&tp->timer, tg3_timer, (unsigned long)tp);
 }
 
 static void tg3_timer_start(struct tg3 *tp)
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 6e13c937d715..a843076597ec 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -1693,9 +1693,9 @@ err_return:
 /* Timer callbacks */
 /* a) IOC timer */
 static void
-bnad_ioc_timeout(unsigned long data)
+bnad_ioc_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = (struct bnad *)data;
+	struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.ioc_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
@@ -1704,9 +1704,9 @@ bnad_ioc_timeout(unsigned long data)
 }
 
 static void
-bnad_ioc_hb_check(unsigned long data)
+bnad_ioc_hb_check(struct timer_list *t)
 {
-	struct bnad *bnad = (struct bnad *)data;
+	struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.hb_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
@@ -1715,9 +1715,9 @@ bnad_ioc_hb_check(unsigned long data)
 }
 
 static void
-bnad_iocpf_timeout(unsigned long data)
+bnad_iocpf_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = (struct bnad *)data;
+	struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.iocpf_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
@@ -1726,9 +1726,9 @@ bnad_iocpf_timeout(unsigned long data)
 }
 
 static void
-bnad_iocpf_sem_timeout(unsigned long data)
+bnad_iocpf_sem_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = (struct bnad *)data;
+	struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.sem_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
@@ -1748,9 +1748,9 @@ bnad_iocpf_sem_timeout(unsigned long data)
 
 /* b) Dynamic Interrupt Moderation Timer */
 static void
-bnad_dim_timeout(unsigned long data)
+bnad_dim_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = (struct bnad *)data;
+	struct bnad *bnad = from_timer(bnad, t, dim_timer);
 	struct bnad_rx_info *rx_info;
 	struct bnad_rx_ctrl *rx_ctrl;
 	int i, j;
@@ -1781,9 +1781,9 @@ bnad_dim_timeout(unsigned long data)
 
 /* c)  Statistics Timer */
 static void
-bnad_stats_timeout(unsigned long data)
+bnad_stats_timeout(struct timer_list *t)
 {
-	struct bnad *bnad = (struct bnad *)data;
+	struct bnad *bnad = from_timer(bnad, t, stats_timer);
 	unsigned long flags;
 
 	if (!netif_running(bnad->netdev) ||
@@ -1804,8 +1804,7 @@ bnad_dim_timer_start(struct bnad *bnad)
 {
 	if (bnad->cfg_flags & BNAD_CF_DIM_ENABLED &&
 	    !test_bit(BNAD_RF_DIM_TIMER_RUNNING, &bnad->run_flags)) {
-		setup_timer(&bnad->dim_timer, bnad_dim_timeout,
-			    (unsigned long)bnad);
+		timer_setup(&bnad->dim_timer, bnad_dim_timeout, 0);
 		set_bit(BNAD_RF_DIM_TIMER_RUNNING, &bnad->run_flags);
 		mod_timer(&bnad->dim_timer,
 			  jiffies + msecs_to_jiffies(BNAD_DIM_TIMER_FREQ));
@@ -1823,8 +1822,7 @@ bnad_stats_timer_start(struct bnad *bnad)
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
 	if (!test_and_set_bit(BNAD_RF_STATS_TIMER_RUNNING, &bnad->run_flags)) {
-		setup_timer(&bnad->stats_timer, bnad_stats_timeout,
-			    (unsigned long)bnad);
+		timer_setup(&bnad->stats_timer, bnad_stats_timeout, 0);
 		mod_timer(&bnad->stats_timer,
 			  jiffies + msecs_to_jiffies(BNAD_STATS_TIMER_FREQ));
 	}
@@ -3692,14 +3690,11 @@ bnad_pci_probe(struct pci_dev *pdev,
 		goto res_free;
 
 	/* Set up timers */
-	setup_timer(&bnad->bna.ioceth.ioc.ioc_timer, bnad_ioc_timeout,
-		    (unsigned long)bnad);
-	setup_timer(&bnad->bna.ioceth.ioc.hb_timer, bnad_ioc_hb_check,
-		    (unsigned long)bnad);
-	setup_timer(&bnad->bna.ioceth.ioc.iocpf_timer, bnad_iocpf_timeout,
-		    (unsigned long)bnad);
-	setup_timer(&bnad->bna.ioceth.ioc.sem_timer, bnad_iocpf_sem_timeout,
-		    (unsigned long)bnad);
+	timer_setup(&bnad->bna.ioceth.ioc.ioc_timer, bnad_ioc_timeout, 0);
+	timer_setup(&bnad->bna.ioceth.ioc.hb_timer, bnad_ioc_hb_check, 0);
+	timer_setup(&bnad->bna.ioceth.ioc.iocpf_timer, bnad_iocpf_timeout, 0);
+	timer_setup(&bnad->bna.ioceth.ioc.sem_timer, bnad_iocpf_sem_timeout,
+		    0);
 
 	/*
 	 * Start the chip
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 6df2cad61647..5dafcde67e45 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1218,8 +1218,6 @@ static int macb_poll(struct napi_struct *napi, int budget)
 	status = macb_readl(bp, RSR);
 	macb_writel(bp, RSR, status);
 
-	work_done = 0;
-
 	netdev_vdbg(bp->dev, "poll: status = %08lx, budget = %d\n",
 		    (unsigned long)status, budget);
 
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index dcbce6cac63e..63be75eb34d2 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -53,6 +53,7 @@ config	THUNDER_NIC_RGX
 config LIQUIDIO
 	tristate "Cavium LiquidIO support"
 	depends on 64BIT
+	depends on MAY_USE_DEVLINK
 	imply PTP_1588_CLOCK
 	select FW_LOADER
 	select LIBCRC32C
diff --git a/drivers/net/ethernet/cavium/liquidio/Makefile b/drivers/net/ethernet/cavium/liquidio/Makefile
index b802896bb2e0..e3fc4645cd8a 100644
--- a/drivers/net/ethernet/cavium/liquidio/Makefile
+++ b/drivers/net/ethernet/cavium/liquidio/Makefile
@@ -18,7 +18,7 @@ liquidio-$(CONFIG_LIQUIDIO) += lio_ethtool.o \
 			octeon_droq.o      \
 			octeon_nic.o
 
-liquidio-objs := lio_main.o octeon_console.o $(liquidio-y)
+liquidio-objs := lio_main.o octeon_console.o lio_vf_rep.o $(liquidio-y)
 
 obj-$(CONFIG_LIQUIDIO_VF) += liquidio_vf.o
 
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index 23f6b60030c5..89b7820d59ce 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -91,7 +91,7 @@ void octeon_update_tx_completion_counters(void *buf, int reqtype,
 	*bytes_compl += skb->len;
 }
 
-void octeon_report_sent_bytes_to_bql(void *buf, int reqtype)
+int octeon_report_sent_bytes_to_bql(void *buf, int reqtype)
 {
 	struct octnet_buf_free_info *finfo;
 	struct sk_buff *skb;
@@ -112,11 +112,13 @@ void octeon_report_sent_bytes_to_bql(void *buf, int reqtype)
 		break;
 
 	default:
-		return;
+		return 0;
 	}
 
 	txq = netdev_get_tx_queue(skb->dev, skb_get_queue_mapping(skb));
 	netdev_tx_sent_queue(txq, skb->len);
+
+	return netif_xmit_stopped(txq);
 }
 
 void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
@@ -141,6 +143,7 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
 	switch (nctrl->ncmd.s.cmd) {
 	case OCTNET_CMD_CHANGE_DEVFLAGS:
 	case OCTNET_CMD_SET_MULTI_LIST:
+	case OCTNET_CMD_SET_UC_LIST:
 		break;
 
 	case OCTNET_CMD_CHANGE_MACADDR:
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 5b19826a7e16..f05045a69dcc 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -21,6 +21,7 @@
 #include <linux/firmware.h>
 #include <net/vxlan.h>
 #include <linux/kthread.h>
+#include <net/switchdev.h>
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
@@ -34,6 +35,7 @@
 #include "cn68xx_device.h"
 #include "cn23xx_pf_device.h"
 #include "liquidio_image.h"
+#include "lio_vf_rep.h"
 
 MODULE_AUTHOR("Cavium Networks, <support@cavium.com>");
 MODULE_DESCRIPTION("Cavium LiquidIO Intelligent Server Adapter Driver");
@@ -59,9 +61,9 @@ static int debug = -1;
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "NETIF_MSG debug bits");
 
-static char fw_type[LIO_MAX_FW_TYPE_LEN] = LIO_FW_NAME_TYPE_NIC;
+static char fw_type[LIO_MAX_FW_TYPE_LEN] = LIO_FW_NAME_TYPE_AUTO;
 module_param_string(fw_type, fw_type, sizeof(fw_type), 0444);
-MODULE_PARM_DESC(fw_type, "Type of firmware to be loaded. Default \"nic\".  Use \"none\" to load firmware from flash.");
+MODULE_PARM_DESC(fw_type, "Type of firmware to be loaded (default is \"auto\"), which uses firmware in flash, if present, else loads \"nic\".");
 
 static u32 console_bitmask;
 module_param(console_bitmask, int, 0644);
@@ -83,6 +85,11 @@ static int octeon_console_debug_enabled(u32 console)
 
 /* runtime link query interval */
 #define LIQUIDIO_LINK_QUERY_INTERVAL_MS         1000
+/* update localtime to octeon firmware every 60 seconds.
+ * make firmware to use same time reference, so that it will be easy to
+ * correlate firmware logged events/errors with host events, for debugging.
+ */
+#define LIO_SYNC_OCTEON_TIME_INTERVAL_MS 60000
 
 struct liquidio_if_cfg_context {
 	int octeon_id;
@@ -901,6 +908,121 @@ static inline void update_link_status(struct net_device *netdev,
 	}
 }
 
+/**
+ * lio_sync_octeon_time_cb - callback that is invoked when soft command
+ * sent by lio_sync_octeon_time() has completed successfully or failed
+ *
+ * @oct - octeon device structure
+ * @status - indicates success or failure
+ * @buf - pointer to the command that was sent to firmware
+ **/
+static void lio_sync_octeon_time_cb(struct octeon_device *oct,
+				    u32 status, void *buf)
+{
+	struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
+
+	if (status)
+		dev_err(&oct->pci_dev->dev,
+			"Failed to sync time to octeon; error=%d\n", status);
+
+	octeon_free_soft_command(oct, sc);
+}
+
+/**
+ * lio_sync_octeon_time - send latest localtime to octeon firmware so that
+ * firmware will correct it's time, in case there is a time skew
+ *
+ * @work: work scheduled to send time update to octeon firmware
+ **/
+static void lio_sync_octeon_time(struct work_struct *work)
+{
+	struct cavium_wk *wk = (struct cavium_wk *)work;
+	struct lio *lio = (struct lio *)wk->ctxptr;
+	struct octeon_device *oct = lio->oct_dev;
+	struct octeon_soft_command *sc;
+	struct timespec64 ts;
+	struct lio_time *lt;
+	int ret;
+
+	sc = octeon_alloc_soft_command(oct, sizeof(struct lio_time), 0, 0);
+	if (!sc) {
+		dev_err(&oct->pci_dev->dev,
+			"Failed to sync time to octeon: soft command allocation failed\n");
+		return;
+	}
+
+	lt = (struct lio_time *)sc->virtdptr;
+
+	/* Get time of the day */
+	getnstimeofday64(&ts);
+	lt->sec = ts.tv_sec;
+	lt->nsec = ts.tv_nsec;
+	octeon_swap_8B_data((u64 *)lt, (sizeof(struct lio_time)) / 8);
+
+	sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+	octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
+				    OPCODE_NIC_SYNC_OCTEON_TIME, 0, 0, 0);
+
+	sc->callback = lio_sync_octeon_time_cb;
+	sc->callback_arg = sc;
+	sc->wait_time = 1000;
+
+	ret = octeon_send_soft_command(oct, sc);
+	if (ret == IQ_SEND_FAILED) {
+		dev_err(&oct->pci_dev->dev,
+			"Failed to sync time to octeon: failed to send soft command\n");
+		octeon_free_soft_command(oct, sc);
+	}
+
+	queue_delayed_work(lio->sync_octeon_time_wq.wq,
+			   &lio->sync_octeon_time_wq.wk.work,
+			   msecs_to_jiffies(LIO_SYNC_OCTEON_TIME_INTERVAL_MS));
+}
+
+/**
+ * setup_sync_octeon_time_wq - Sets up the work to periodically update
+ * local time to octeon firmware
+ *
+ * @netdev - network device which should send time update to firmware
+ **/
+static inline int setup_sync_octeon_time_wq(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+
+	lio->sync_octeon_time_wq.wq =
+		alloc_workqueue("update-octeon-time", WQ_MEM_RECLAIM, 0);
+	if (!lio->sync_octeon_time_wq.wq) {
+		dev_err(&oct->pci_dev->dev, "Unable to create wq to update octeon time\n");
+		return -1;
+	}
+	INIT_DELAYED_WORK(&lio->sync_octeon_time_wq.wk.work,
+			  lio_sync_octeon_time);
+	lio->sync_octeon_time_wq.wk.ctxptr = lio;
+	queue_delayed_work(lio->sync_octeon_time_wq.wq,
+			   &lio->sync_octeon_time_wq.wk.work,
+			   msecs_to_jiffies(LIO_SYNC_OCTEON_TIME_INTERVAL_MS));
+
+	return 0;
+}
+
+/**
+ * cleanup_sync_octeon_time_wq - stop scheduling and destroy the work created
+ * to periodically update local time to octeon firmware
+ *
+ * @netdev - network device which should send time update to firmware
+ **/
+static inline void cleanup_sync_octeon_time_wq(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct cavium_wq *time_wq = &lio->sync_octeon_time_wq;
+
+	if (time_wq->wq) {
+		cancel_delayed_work_sync(&time_wq->wk.work);
+		destroy_workqueue(time_wq->wq);
+	}
+}
+
 static struct octeon_device *get_other_octeon_device(struct octeon_device *oct)
 {
 	struct octeon_device *other_oct;
@@ -1076,19 +1198,13 @@ liquidio_probe(struct pci_dev *pdev,
 	}
 
 	if (OCTEON_CN23XX_PF(oct_dev)) {
-		u64 scratch1;
 		u8 bus, device, function;
 
-		scratch1 = octeon_read_csr64(oct_dev, CN23XX_SLI_SCRATCH1);
-		if (!(scratch1 & 4ULL)) {
-			/* Bit 2 of SLI_SCRATCH_1 is a flag that indicates that
-			 * the lio watchdog kernel thread is running for this
-			 * NIC.  Each NIC gets one watchdog kernel thread.
+		if (atomic_read(oct_dev->adapter_refcount) == 1) {
+			/* Each NIC gets one watchdog kernel thread.  The first
+			 * PF (of each NIC) that gets pci_driver->probe()'d
+			 * creates that thread.
 			 */
-			scratch1 |= 4ULL;
-			octeon_write_csr64(oct_dev, CN23XX_SLI_SCRATCH1,
-					   scratch1);
-
 			bus = pdev->bus->number;
 			device = PCI_SLOT(pdev->devfn);
 			function = PCI_FUNC(pdev->devfn);
@@ -1115,10 +1231,10 @@ liquidio_probe(struct pci_dev *pdev,
 	return 0;
 }
 
-static bool fw_type_is_none(void)
+static bool fw_type_is_auto(void)
 {
-	return strncmp(fw_type, LIO_FW_NAME_TYPE_NONE,
-		       sizeof(LIO_FW_NAME_TYPE_NONE)) == 0;
+	return strncmp(fw_type, LIO_FW_NAME_TYPE_AUTO,
+		       sizeof(LIO_FW_NAME_TYPE_AUTO)) == 0;
 }
 
 /**
@@ -1302,7 +1418,7 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 		 * Implementation note: only soft-reset the device
 		 * if it is a CN6XXX OR the LAST CN23XX device.
 		 */
-		if (fw_type_is_none())
+		if (atomic_read(oct->adapter_fw_state) == FW_IS_PRELOADED)
 			octeon_pci_flr(oct);
 		else if (OCTEON_CN6XXX(oct) || !refcount)
 			oct->fn_list.soft_reset(oct);
@@ -1455,6 +1571,7 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED)
 		unregister_netdev(netdev);
 
+	cleanup_sync_octeon_time_wq(netdev);
 	cleanup_link_status_change_wq(netdev);
 
 	cleanup_rx_oom_poll_fn(netdev);
@@ -1487,6 +1604,8 @@ static int liquidio_stop_nic_module(struct octeon_device *oct)
 	oct->cmd_resp_state = OCT_DRV_OFFLINE;
 	spin_unlock_bh(&oct->cmd_resp_wqlock);
 
+	lio_vf_rep_destroy(oct);
+
 	for (i = 0; i < oct->ifcount; i++) {
 		lio = GET_LIO(oct->props[i].netdev);
 		for (j = 0; j < oct->num_oqs; j++)
@@ -1497,6 +1616,12 @@ static int liquidio_stop_nic_module(struct octeon_device *oct)
 	for (i = 0; i < oct->ifcount; i++)
 		liquidio_destroy_nic_device(oct, i);
 
+	if (oct->devlink) {
+		devlink_unregister(oct->devlink);
+		devlink_free(oct->devlink);
+		oct->devlink = NULL;
+	}
+
 	dev_dbg(&oct->pci_dev->dev, "Network interfaces stopped\n");
 	return 0;
 }
@@ -1514,6 +1639,10 @@ static void liquidio_remove(struct pci_dev *pdev)
 	if (oct_dev->watchdog_task)
 		kthread_stop(oct_dev->watchdog_task);
 
+	if (!oct_dev->octeon_id &&
+	    oct_dev->fw_info.app_cap_flags & LIQUIDIO_SWITCHDEV_CAP)
+		lio_vf_rep_modexit();
+
 	if (oct_dev->app_mode && (oct_dev->app_mode == CVM_DRV_NIC_APP))
 		liquidio_stop_nic_module(oct_dev);
 
@@ -1934,10 +2063,12 @@ static int load_firmware(struct octeon_device *oct)
 	char fw_name[LIO_MAX_FW_FILENAME_LEN];
 	char *tmp_fw_type;
 
-	if (fw_type[0] == '\0')
+	if (fw_type_is_auto()) {
 		tmp_fw_type = LIO_FW_NAME_TYPE_NIC;
-	else
+		strncpy(fw_type, tmp_fw_type, sizeof(fw_type));
+	} else {
 		tmp_fw_type = fw_type;
+	}
 
 	sprintf(fw_name, "%s%s%s_%s%s", LIO_FW_DIR, LIO_FW_BASE_NAME,
 		octeon_get_conf(oct)->card_name, tmp_fw_type,
@@ -2477,7 +2608,8 @@ static void handle_timestamp(struct octeon_device *oct,
  */
 static inline int send_nic_timestamp_pkt(struct octeon_device *oct,
 					 struct octnic_data_pkt *ndata,
-					 struct octnet_buf_free_info *finfo)
+					 struct octnet_buf_free_info *finfo,
+					 int xmit_more)
 {
 	int retval;
 	struct octeon_soft_command *sc;
@@ -2512,7 +2644,7 @@ static inline int send_nic_timestamp_pkt(struct octeon_device *oct,
 		len = (u32)((struct octeon_instr_ih2 *)
 			    (&sc->cmd.cmd2.ih2))->dlengsz;
 
-	ring_doorbell = 1;
+	ring_doorbell = !xmit_more;
 
 	retval = octeon_send_command(oct, sc->iq_no, ring_doorbell, &sc->cmd,
 				     sc, len, ndata->reqtype);
@@ -2546,7 +2678,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 	union tx_info *tx_info;
 	int status = 0;
 	int q_idx = 0, iq_no = 0;
-	int j;
+	int j, xmit_more = 0;
 	u64 dptr = 0;
 	u32 tag = 0;
 
@@ -2751,17 +2883,19 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 		irh->vlan = skb_vlan_tag_get(skb) & 0xfff;
 	}
 
+	xmit_more = skb->xmit_more;
+
 	if (unlikely(cmdsetup.s.timestamp))
-		status = send_nic_timestamp_pkt(oct, &ndata, finfo);
+		status = send_nic_timestamp_pkt(oct, &ndata, finfo, xmit_more);
 	else
-		status = octnet_send_nic_data_pkt(oct, &ndata);
+		status = octnet_send_nic_data_pkt(oct, &ndata, xmit_more);
 	if (status == IQ_SEND_FAILED)
 		goto lio_xmit_failed;
 
 	netif_info(lio, tx_queued, lio->netdev, "Transmit queued successfully\n");
 
 	if (status == IQ_SEND_STOP)
-		stop_q(lio->netdev, q_idx);
+		stop_q(netdev, q_idx);
 
 	netif_trans_update(netdev);
 
@@ -2780,6 +2914,9 @@ lio_xmit_failed:
 	if (dptr)
 		dma_unmap_single(&oct->pci_dev->dev, dptr,
 				 ndata.datasize, DMA_TO_DEVICE);
+
+	octeon_ring_doorbell_locked(oct, iq_no);
+
 	tx_buffer_free(skb);
 	return NETDEV_TX_OK;
 }
@@ -3186,6 +3323,86 @@ static int liquidio_set_vf_link_state(struct net_device *netdev, int vfidx,
 	return 0;
 }
 
+static int
+liquidio_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+	struct lio_devlink_priv *priv;
+	struct octeon_device *oct;
+
+	priv = devlink_priv(devlink);
+	oct = priv->oct;
+
+	*mode = oct->eswitch_mode;
+
+	return 0;
+}
+
+static int
+liquidio_eswitch_mode_set(struct devlink *devlink, u16 mode)
+{
+	struct lio_devlink_priv *priv;
+	struct octeon_device *oct;
+	int ret = 0;
+
+	priv = devlink_priv(devlink);
+	oct = priv->oct;
+
+	if (!(oct->fw_info.app_cap_flags & LIQUIDIO_SWITCHDEV_CAP))
+		return -EINVAL;
+
+	if (oct->eswitch_mode == mode)
+		return 0;
+
+	switch (mode) {
+	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+		oct->eswitch_mode = mode;
+		ret = lio_vf_rep_create(oct);
+		break;
+
+	case DEVLINK_ESWITCH_MODE_LEGACY:
+		lio_vf_rep_destroy(oct);
+		oct->eswitch_mode = mode;
+		break;
+
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static const struct devlink_ops liquidio_devlink_ops = {
+	.eswitch_mode_get = liquidio_eswitch_mode_get,
+	.eswitch_mode_set = liquidio_eswitch_mode_set,
+};
+
+static int
+lio_pf_switchdev_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+{
+	struct lio *lio = GET_LIO(dev);
+	struct octeon_device *oct = lio->oct_dev;
+
+	if (oct->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV)
+		return -EOPNOTSUPP;
+
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
+		attr->u.ppid.id_len = ETH_ALEN;
+		ether_addr_copy(attr->u.ppid.id,
+				(void *)&lio->linfo.hw_addr + 2);
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static const struct switchdev_ops lio_pf_switchdev_ops = {
+	.switchdev_port_attr_get = lio_pf_switchdev_attr_get,
+};
+
 static const struct net_device_ops lionetdevops = {
 	.ndo_open		= liquidio_open,
 	.ndo_stop		= liquidio_stop,
@@ -3303,7 +3520,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 {
 	struct lio *lio = NULL;
 	struct net_device *netdev;
-	u8 mac[6], i, j;
+	u8 mac[6], i, j, *fw_ver;
 	struct octeon_soft_command *sc;
 	struct liquidio_if_cfg_context *ctx;
 	struct liquidio_if_cfg_resp *resp;
@@ -3315,6 +3532,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 	u32 resp_size, ctx_size, data_size;
 	u32 ifidx_or_pfnum;
 	struct lio_version *vdata;
+	struct devlink *devlink;
+	struct lio_devlink_priv *lio_devlink;
 
 	/* This is to handle link status changes */
 	octeon_register_dispatch_fn(octeon_dev, OPCODE_NIC,
@@ -3414,6 +3633,22 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 			goto setup_nic_dev_fail;
 		}
 
+		/* Verify f/w version (in case of 'auto' loading from flash) */
+		fw_ver = octeon_dev->fw_info.liquidio_firmware_version;
+		if (memcmp(LIQUIDIO_BASE_VERSION,
+			   fw_ver,
+			   strlen(LIQUIDIO_BASE_VERSION))) {
+			dev_err(&octeon_dev->pci_dev->dev,
+				"Unmatched firmware version. Expected %s.x, got %s.\n",
+				LIQUIDIO_BASE_VERSION, fw_ver);
+			goto setup_nic_dev_fail;
+		} else if (atomic_read(octeon_dev->adapter_fw_state) ==
+			   FW_IS_PRELOADED) {
+			dev_info(&octeon_dev->pci_dev->dev,
+				 "Using auto-loaded firmware version %s.\n",
+				 fw_ver);
+		}
+
 		octeon_swap_8B_data((u64 *)(&resp->cfg_info),
 				    (sizeof(struct liquidio_if_cfg_info)) >> 3);
 
@@ -3444,6 +3679,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		 * netdev tasks.
 		 */
 		netdev->netdev_ops = &lionetdevops;
+		SWITCHDEV_SET_OPS(netdev, &lio_pf_switchdev_ops);
 
 		lio = GET_LIO(netdev);
 
@@ -3593,6 +3829,11 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		if (setup_link_status_change_wq(netdev))
 			goto setup_nic_dev_fail;
 
+		if ((octeon_dev->fw_info.app_cap_flags &
+		     LIQUIDIO_TIME_SYNC_CAP) &&
+		    setup_sync_octeon_time_wq(netdev))
+			goto setup_nic_dev_fail;
+
 		if (setup_rx_oom_poll_fn(netdev))
 			goto setup_nic_dev_fail;
 
@@ -3625,6 +3866,26 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		octeon_free_soft_command(octeon_dev, sc);
 	}
 
+	devlink = devlink_alloc(&liquidio_devlink_ops,
+				sizeof(struct lio_devlink_priv));
+	if (!devlink) {
+		dev_err(&octeon_dev->pci_dev->dev, "devlink alloc failed\n");
+		goto setup_nic_wait_intr;
+	}
+
+	lio_devlink = devlink_priv(devlink);
+	lio_devlink->oct = octeon_dev;
+
+	if (devlink_register(devlink, &octeon_dev->pci_dev->dev)) {
+		devlink_free(devlink);
+		dev_err(&octeon_dev->pci_dev->dev,
+			"devlink registration failed\n");
+		goto setup_nic_wait_intr;
+	}
+
+	octeon_dev->devlink = devlink;
+	octeon_dev->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+
 	return 0;
 
 setup_nic_dev_fail:
@@ -3719,6 +3980,7 @@ static int liquidio_enable_sriov(struct pci_dev *dev, int num_vfs)
 	}
 
 	if (!num_vfs) {
+		lio_vf_rep_destroy(oct);
 		ret = lio_pci_sriov_disable(oct);
 	} else if (num_vfs > oct->sriov_info.max_vfs) {
 		dev_err(&oct->pci_dev->dev,
@@ -3730,6 +3992,10 @@ static int liquidio_enable_sriov(struct pci_dev *dev, int num_vfs)
 		ret = octeon_enable_sriov(oct);
 		dev_info(&oct->pci_dev->dev, "oct->pf_num:%d num_vfs:%d\n",
 			 oct->pf_num, num_vfs);
+		ret = lio_vf_rep_create(oct);
+		if (ret)
+			dev_info(&oct->pci_dev->dev,
+				 "vf representor create failed");
 	}
 
 	return ret;
@@ -3767,6 +4033,17 @@ static int liquidio_init_nic_module(struct octeon_device *oct)
 		goto octnet_init_failure;
 	}
 
+	/* Call vf_rep_modinit if the firmware is switchdev capable
+	 * and do it from the first liquidio function probed.
+	 */
+	if (!oct->octeon_id &&
+	    oct->fw_info.app_cap_flags & LIQUIDIO_SWITCHDEV_CAP) {
+		if (lio_vf_rep_modinit()) {
+			liquidio_stop_nic_module(oct);
+			goto octnet_init_failure;
+		}
+	}
+
 	liquidio_ptp_init(oct);
 
 	dev_dbg(&oct->pci_dev->dev, "Network interfaces ready\n");
@@ -3882,9 +4159,9 @@ octeon_recv_vf_drv_notice(struct octeon_recv_info *recv_info, void *buf)
 static int octeon_device_init(struct octeon_device *octeon_dev)
 {
 	int j, ret;
-	int fw_loaded = 0;
 	char bootcmd[] = "\n";
 	char *dbg_enb = NULL;
+	enum lio_fw_state fw_state;
 	struct octeon_device_priv *oct_priv =
 		(struct octeon_device_priv *)octeon_dev->priv;
 	atomic_set(&octeon_dev->status, OCT_DEV_BEGIN_STATE);
@@ -3916,24 +4193,40 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
 
 	octeon_dev->app_mode = CVM_DRV_INVALID_APP;
 
-	if (OCTEON_CN23XX_PF(octeon_dev)) {
-		if (!cn23xx_fw_loaded(octeon_dev) && !fw_type_is_none()) {
-			fw_loaded = 0;
-			/* Do a soft reset of the Octeon device. */
-			if (octeon_dev->fn_list.soft_reset(octeon_dev))
-				return 1;
-			/* things might have changed */
-			if (!cn23xx_fw_loaded(octeon_dev))
-				fw_loaded = 0;
-			else
-				fw_loaded = 1;
-		} else {
-			fw_loaded = 1;
-		}
-	} else if (octeon_dev->fn_list.soft_reset(octeon_dev)) {
-		return 1;
+	/* CN23XX supports preloaded firmware if the following is true:
+	 *
+	 * The adapter indicates that firmware is currently running AND
+	 * 'fw_type' is 'auto'.
+	 *
+	 * (default state is NEEDS_TO_BE_LOADED, override it if appropriate).
+	 */
+	if (OCTEON_CN23XX_PF(octeon_dev) &&
+	    cn23xx_fw_loaded(octeon_dev) && fw_type_is_auto()) {
+		atomic_cmpxchg(octeon_dev->adapter_fw_state,
+			       FW_NEEDS_TO_BE_LOADED, FW_IS_PRELOADED);
 	}
 
+	/* If loading firmware, only first device of adapter needs to do so. */
+	fw_state = atomic_cmpxchg(octeon_dev->adapter_fw_state,
+				  FW_NEEDS_TO_BE_LOADED,
+				  FW_IS_BEING_LOADED);
+
+	/* Here, [local variable] 'fw_state' is set to one of:
+	 *
+	 *   FW_IS_PRELOADED:       No firmware is to be loaded (see above)
+	 *   FW_NEEDS_TO_BE_LOADED: The driver's first instance will load
+	 *                          firmware to the adapter.
+	 *   FW_IS_BEING_LOADED:    The driver's second instance will not load
+	 *                          firmware to the adapter.
+	 */
+
+	/* Prior to f/w load, perform a soft reset of the Octeon device;
+	 * if error resetting, return w/error.
+	 */
+	if (fw_state == FW_NEEDS_TO_BE_LOADED)
+		if (octeon_dev->fn_list.soft_reset(octeon_dev))
+			return 1;
+
 	/* Initialize the dispatch mechanism used to push packets arriving on
 	 * Octeon Output queues.
 	 */
@@ -4063,7 +4356,7 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
 
 	atomic_set(&octeon_dev->status, OCT_DEV_IO_QUEUES_DONE);
 
-	if ((!OCTEON_CN23XX_PF(octeon_dev)) || !fw_loaded) {
+	if (fw_state == FW_NEEDS_TO_BE_LOADED) {
 		dev_dbg(&octeon_dev->pci_dev->dev, "Waiting for DDR initialization...\n");
 		if (!ddr_timeout) {
 			dev_info(&octeon_dev->pci_dev->dev,
@@ -4125,6 +4418,8 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
 			dev_err(&octeon_dev->pci_dev->dev, "Could not load firmware to board\n");
 			return 1;
 		}
+
+		atomic_set(octeon_dev->adapter_fw_state, FW_HAS_BEEN_LOADED);
 	}
 
 	handshake[octeon_dev->octeon_id].init_ok = 1;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 2e993ce43b66..fd70a4844e2d 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -435,8 +435,7 @@ static void delete_glists(struct lio *lio)
 		do {
 			g = (struct octnic_gather *)
 			    list_delete_head(&lio->glist[i]);
-			if (g)
-				kfree(g);
+			kfree(g);
 		} while (g);
 
 		if (lio->glists_virt_base && lio->glists_virt_base[i] &&
@@ -748,7 +747,7 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 
 		if (lio_wait_for_oq_pkts(oct))
 			dev_err(&oct->pci_dev->dev, "OQ had pending packets\n");
-
+		/* fall through */
 	case OCT_DEV_INTR_SET_DONE:
 		/* Disable interrupts  */
 		oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR);
@@ -1289,6 +1288,9 @@ static int liquidio_stop(struct net_device *netdev)
 	struct octeon_device *oct = lio->oct_dev;
 	struct napi_struct *napi, *n;
 
+	/* tell Octeon to stop forwarding packets to host */
+	send_rx_ctrl_cmd(lio, 0);
+
 	if (oct->props[lio->ifidx].napi_enabled) {
 		list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
 			napi_disable(napi);
@@ -1306,9 +1308,6 @@ static int liquidio_stop(struct net_device *netdev)
 	netif_carrier_off(netdev);
 	lio->link_changes++;
 
-	/* tell Octeon to stop forwarding packets to host */
-	send_rx_ctrl_cmd(lio, 0);
-
 	ifstate_reset(lio, LIO_IFSTATE_RUNNING);
 
 	txqs_stop(netdev);
@@ -1691,7 +1690,8 @@ static void handle_timestamp(struct octeon_device *oct, u32 status, void *buf)
  */
 static int send_nic_timestamp_pkt(struct octeon_device *oct,
 				  struct octnic_data_pkt *ndata,
-				  struct octnet_buf_free_info *finfo)
+				  struct octnet_buf_free_info *finfo,
+				  int xmit_more)
 {
 	struct octeon_soft_command *sc;
 	int ring_doorbell;
@@ -1721,7 +1721,7 @@ static int send_nic_timestamp_pkt(struct octeon_device *oct,
 
 	len = (u32)((struct octeon_instr_ih3 *)(&sc->cmd.cmd3.ih3))->dlengsz;
 
-	ring_doorbell = 1;
+	ring_doorbell = !xmit_more;
 
 	retval = octeon_send_command(oct, sc->iq_no, ring_doorbell, &sc->cmd,
 				     sc, len, ndata->reqtype);
@@ -1753,6 +1753,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 	struct octeon_device *oct;
 	int q_idx = 0, iq_no = 0;
 	union tx_info *tx_info;
+	int xmit_more = 0;
 	struct lio *lio;
 	int status = 0;
 	u64 dptr = 0;
@@ -1941,10 +1942,12 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 		irh->vlan = skb_vlan_tag_get(skb) & VLAN_VID_MASK;
 	}
 
+	xmit_more = skb->xmit_more;
+
 	if (unlikely(cmdsetup.s.timestamp))
-		status = send_nic_timestamp_pkt(oct, &ndata, finfo);
+		status = send_nic_timestamp_pkt(oct, &ndata, finfo, xmit_more);
 	else
-		status = octnet_send_nic_data_pkt(oct, &ndata);
+		status = octnet_send_nic_data_pkt(oct, &ndata, xmit_more);
 	if (status == IQ_SEND_FAILED)
 		goto lio_xmit_failed;
 
@@ -1953,7 +1956,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 	if (status == IQ_SEND_STOP) {
 		dev_err(&oct->pci_dev->dev, "Rcvd IQ_SEND_STOP signal; stopping IQ-%d\n",
 			iq_no);
-		stop_q(lio->netdev, q_idx);
+		stop_q(netdev, q_idx);
 	}
 
 	netif_trans_update(netdev);
@@ -1973,6 +1976,9 @@ lio_xmit_failed:
 	if (dptr)
 		dma_unmap_single(&oct->pci_dev->dev, dptr,
 				 ndata.datasize, DMA_TO_DEVICE);
+
+	octeon_ring_doorbell_locked(oct, iq_no);
+
 	tx_buffer_free(skb);
 	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
new file mode 100644
index 000000000000..2adafa366d3f
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
@@ -0,0 +1,695 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more details.
+ ***********************************************************************/
+#include <linux/pci.h>
+#include <linux/if_vlan.h>
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_nic.h"
+#include "octeon_main.h"
+#include "octeon_network.h"
+#include <net/switchdev.h>
+#include "lio_vf_rep.h"
+#include "octeon_network.h"
+
+static int lio_vf_rep_open(struct net_device *ndev);
+static int lio_vf_rep_stop(struct net_device *ndev);
+static int lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev);
+static void lio_vf_rep_tx_timeout(struct net_device *netdev);
+static int lio_vf_rep_phys_port_name(struct net_device *dev,
+				     char *buf, size_t len);
+static void lio_vf_rep_get_stats64(struct net_device *dev,
+				   struct rtnl_link_stats64 *stats64);
+static int lio_vf_rep_change_mtu(struct net_device *ndev, int new_mtu);
+
+static const struct net_device_ops lio_vf_rep_ndev_ops = {
+	.ndo_open = lio_vf_rep_open,
+	.ndo_stop = lio_vf_rep_stop,
+	.ndo_start_xmit = lio_vf_rep_pkt_xmit,
+	.ndo_tx_timeout = lio_vf_rep_tx_timeout,
+	.ndo_get_phys_port_name = lio_vf_rep_phys_port_name,
+	.ndo_get_stats64 = lio_vf_rep_get_stats64,
+	.ndo_change_mtu = lio_vf_rep_change_mtu,
+};
+
+static void
+lio_vf_rep_send_sc_complete(struct octeon_device *oct,
+			    u32 status, void *ptr)
+{
+	struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr;
+	struct lio_vf_rep_sc_ctx *ctx =
+		(struct lio_vf_rep_sc_ctx *)sc->ctxptr;
+	struct lio_vf_rep_resp *resp =
+		(struct lio_vf_rep_resp *)sc->virtrptr;
+
+	if (status != OCTEON_REQUEST_TIMEOUT && READ_ONCE(resp->status))
+		WRITE_ONCE(resp->status, 0);
+
+	complete(&ctx->complete);
+}
+
+static int
+lio_vf_rep_send_soft_command(struct octeon_device *oct,
+			     void *req, int req_size,
+			     void *resp, int resp_size)
+{
+	int tot_resp_size = sizeof(struct lio_vf_rep_resp) + resp_size;
+	int ctx_size = sizeof(struct lio_vf_rep_sc_ctx);
+	struct octeon_soft_command *sc = NULL;
+	struct lio_vf_rep_resp *rep_resp;
+	struct lio_vf_rep_sc_ctx *ctx;
+	void *sc_req;
+	int err;
+
+	sc = (struct octeon_soft_command *)
+		octeon_alloc_soft_command(oct, req_size,
+					  tot_resp_size, ctx_size);
+	if (!sc)
+		return -ENOMEM;
+
+	ctx = (struct lio_vf_rep_sc_ctx *)sc->ctxptr;
+	memset(ctx, 0, ctx_size);
+	init_completion(&ctx->complete);
+
+	sc_req = (struct lio_vf_rep_req *)sc->virtdptr;
+	memcpy(sc_req, req, req_size);
+
+	rep_resp = (struct lio_vf_rep_resp *)sc->virtrptr;
+	memset(rep_resp, 0, tot_resp_size);
+	WRITE_ONCE(rep_resp->status, 1);
+
+	sc->iq_no = 0;
+	octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
+				    OPCODE_NIC_VF_REP_CMD, 0, 0, 0);
+	sc->callback = lio_vf_rep_send_sc_complete;
+	sc->callback_arg = sc;
+	sc->wait_time = LIO_VF_REP_REQ_TMO_MS;
+
+	err = octeon_send_soft_command(oct, sc);
+	if (err == IQ_SEND_FAILED)
+		goto free_buff;
+
+	wait_for_completion_timeout(&ctx->complete,
+				    msecs_to_jiffies
+				    (2 * LIO_VF_REP_REQ_TMO_MS));
+	err = READ_ONCE(rep_resp->status) ? -EBUSY : 0;
+	if (err)
+		dev_err(&oct->pci_dev->dev, "VF rep send config failed\n");
+
+	if (resp)
+		memcpy(resp, (rep_resp + 1), resp_size);
+free_buff:
+	octeon_free_soft_command(oct, sc);
+
+	return err;
+}
+
+static int
+lio_vf_rep_open(struct net_device *ndev)
+{
+	struct lio_vf_rep_desc *vf_rep = netdev_priv(ndev);
+	struct lio_vf_rep_req rep_cfg;
+	struct octeon_device *oct;
+	int ret;
+
+	oct = vf_rep->oct;
+
+	memset(&rep_cfg, 0, sizeof(rep_cfg));
+	rep_cfg.req_type = LIO_VF_REP_REQ_STATE;
+	rep_cfg.ifidx = vf_rep->ifidx;
+	rep_cfg.rep_state.state = LIO_VF_REP_STATE_UP;
+
+	ret = lio_vf_rep_send_soft_command(oct, &rep_cfg,
+					   sizeof(rep_cfg), NULL, 0);
+
+	if (ret) {
+		dev_err(&oct->pci_dev->dev,
+			"VF_REP open failed with err %d\n", ret);
+		return -EIO;
+	}
+
+	atomic_set(&vf_rep->ifstate, (atomic_read(&vf_rep->ifstate) |
+				      LIO_IFSTATE_RUNNING));
+
+	netif_carrier_on(ndev);
+	netif_start_queue(ndev);
+
+	return 0;
+}
+
+static int
+lio_vf_rep_stop(struct net_device *ndev)
+{
+	struct lio_vf_rep_desc *vf_rep = netdev_priv(ndev);
+	struct lio_vf_rep_req rep_cfg;
+	struct octeon_device *oct;
+	int ret;
+
+	oct = vf_rep->oct;
+
+	memset(&rep_cfg, 0, sizeof(rep_cfg));
+	rep_cfg.req_type = LIO_VF_REP_REQ_STATE;
+	rep_cfg.ifidx = vf_rep->ifidx;
+	rep_cfg.rep_state.state = LIO_VF_REP_STATE_DOWN;
+
+	ret = lio_vf_rep_send_soft_command(oct, &rep_cfg,
+					   sizeof(rep_cfg), NULL, 0);
+
+	if (ret) {
+		dev_err(&oct->pci_dev->dev,
+			"VF_REP dev stop failed with err %d\n", ret);
+		return -EIO;
+	}
+
+	atomic_set(&vf_rep->ifstate, (atomic_read(&vf_rep->ifstate) &
+				      ~LIO_IFSTATE_RUNNING));
+
+	netif_tx_disable(ndev);
+	netif_carrier_off(ndev);
+
+	return 0;
+}
+
+static void
+lio_vf_rep_tx_timeout(struct net_device *ndev)
+{
+	netif_trans_update(ndev);
+
+	netif_wake_queue(ndev);
+}
+
+static void
+lio_vf_rep_get_stats64(struct net_device *dev,
+		       struct rtnl_link_stats64 *stats64)
+{
+	struct lio_vf_rep_desc *vf_rep = netdev_priv(dev);
+
+	stats64->tx_packets = vf_rep->stats.tx_packets;
+	stats64->tx_bytes   = vf_rep->stats.tx_bytes;
+	stats64->tx_dropped = vf_rep->stats.tx_dropped;
+
+	stats64->rx_packets = vf_rep->stats.rx_packets;
+	stats64->rx_bytes   = vf_rep->stats.rx_bytes;
+	stats64->rx_dropped = vf_rep->stats.rx_dropped;
+}
+
+static int
+lio_vf_rep_change_mtu(struct net_device *ndev, int new_mtu)
+{
+	struct lio_vf_rep_desc *vf_rep = netdev_priv(ndev);
+	struct lio_vf_rep_req rep_cfg;
+	struct octeon_device *oct;
+	int ret;
+
+	oct = vf_rep->oct;
+
+	memset(&rep_cfg, 0, sizeof(rep_cfg));
+	rep_cfg.req_type = LIO_VF_REP_REQ_MTU;
+	rep_cfg.ifidx = vf_rep->ifidx;
+	rep_cfg.rep_mtu.mtu = cpu_to_be32(new_mtu);
+
+	ret = lio_vf_rep_send_soft_command(oct, &rep_cfg,
+					   sizeof(rep_cfg), NULL, 0);
+	if (ret) {
+		dev_err(&oct->pci_dev->dev,
+			"Change MTU failed with err %d\n", ret);
+		return -EIO;
+	}
+
+	ndev->mtu = new_mtu;
+
+	return 0;
+}
+
+static int
+lio_vf_rep_phys_port_name(struct net_device *dev,
+			  char *buf, size_t len)
+{
+	struct lio_vf_rep_desc *vf_rep = netdev_priv(dev);
+	struct octeon_device *oct = vf_rep->oct;
+	int ret;
+
+	ret = snprintf(buf, len, "pf%dvf%d", oct->pf_num,
+		       vf_rep->ifidx - oct->pf_num * 64 - 1);
+	if (ret >= len)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static struct net_device *
+lio_vf_rep_get_ndev(struct octeon_device *oct, int ifidx)
+{
+	int vf_id, max_vfs = CN23XX_MAX_VFS_PER_PF + 1;
+	int vfid_mask = max_vfs - 1;
+
+	if (ifidx <= oct->pf_num * max_vfs ||
+	    ifidx >= oct->pf_num * max_vfs + max_vfs)
+		return NULL;
+
+	/* ifidx 1-63 for PF0 VFs
+	 * ifidx 65-127 for PF1 VFs
+	 */
+	vf_id = (ifidx & vfid_mask) - 1;
+
+	return oct->vf_rep_list.ndev[vf_id];
+}
+
+static void
+lio_vf_rep_copy_packet(struct octeon_device *oct,
+		       struct sk_buff *skb,
+		       int len)
+{
+	if (likely(len > MIN_SKB_SIZE)) {
+		struct octeon_skb_page_info *pg_info;
+		unsigned char *va;
+
+		pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+		if (pg_info->page) {
+			va = page_address(pg_info->page) +
+				pg_info->page_offset;
+			memcpy(skb->data, va, MIN_SKB_SIZE);
+			skb_put(skb, MIN_SKB_SIZE);
+		}
+
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				pg_info->page,
+				pg_info->page_offset + MIN_SKB_SIZE,
+				len - MIN_SKB_SIZE,
+				LIO_RXBUFFER_SZ);
+	} else {
+		struct octeon_skb_page_info *pg_info =
+			((struct octeon_skb_page_info *)(skb->cb));
+
+		skb_copy_to_linear_data(skb, page_address(pg_info->page) +
+					pg_info->page_offset, len);
+		skb_put(skb, len);
+		put_page(pg_info->page);
+	}
+}
+
+static int
+lio_vf_rep_pkt_recv(struct octeon_recv_info *recv_info, void *buf)
+{
+	struct octeon_recv_pkt *recv_pkt = recv_info->recv_pkt;
+	struct lio_vf_rep_desc *vf_rep;
+	struct net_device *vf_ndev;
+	struct octeon_device *oct;
+	union octeon_rh *rh;
+	struct sk_buff *skb;
+	int i, ifidx;
+
+	oct = lio_get_device(recv_pkt->octeon_id);
+	if (!oct)
+		goto free_buffers;
+
+	skb = recv_pkt->buffer_ptr[0];
+	rh = &recv_pkt->rh;
+	ifidx = rh->r.ossp;
+
+	vf_ndev = lio_vf_rep_get_ndev(oct, ifidx);
+	if (!vf_ndev)
+		goto free_buffers;
+
+	vf_rep = netdev_priv(vf_ndev);
+	if (!(atomic_read(&vf_rep->ifstate) & LIO_IFSTATE_RUNNING) ||
+	    recv_pkt->buffer_count > 1)
+		goto free_buffers;
+
+	skb->dev = vf_ndev;
+
+	/* Multiple buffers are not used for vf_rep packets.
+	 * So just buffer_size[0] is valid.
+	 */
+	lio_vf_rep_copy_packet(oct, skb, recv_pkt->buffer_size[0]);
+
+	skb_pull(skb, rh->r_dh.len * BYTES_PER_DHLEN_UNIT);
+	skb->protocol = eth_type_trans(skb, skb->dev);
+	skb->ip_summed = CHECKSUM_NONE;
+
+	netif_rx(skb);
+
+	octeon_free_recv_info(recv_info);
+
+	return 0;
+
+free_buffers:
+	for (i = 0; i < recv_pkt->buffer_count; i++)
+		recv_buffer_free(recv_pkt->buffer_ptr[i]);
+
+	octeon_free_recv_info(recv_info);
+
+	return 0;
+}
+
+static void
+lio_vf_rep_packet_sent_callback(struct octeon_device *oct,
+				u32 status, void *buf)
+{
+	struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
+	struct sk_buff *skb = sc->ctxptr;
+	struct net_device *ndev = skb->dev;
+
+	dma_unmap_single(&oct->pci_dev->dev, sc->dmadptr,
+			 sc->datasize, DMA_TO_DEVICE);
+	dev_kfree_skb_any(skb);
+	octeon_free_soft_command(oct, sc);
+
+	if (octnet_iq_is_full(oct, sc->iq_no))
+		return;
+
+	if (netif_queue_stopped(ndev))
+		netif_wake_queue(ndev);
+}
+
+static int
+lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct lio_vf_rep_desc *vf_rep = netdev_priv(ndev);
+	struct net_device *parent_ndev = vf_rep->parent_ndev;
+	struct octeon_device *oct = vf_rep->oct;
+	struct octeon_instr_pki_ih3 *pki_ih3;
+	struct octeon_soft_command *sc;
+	struct lio *parent_lio;
+	int status;
+
+	parent_lio = GET_LIO(parent_ndev);
+
+	if (!(atomic_read(&vf_rep->ifstate) & LIO_IFSTATE_RUNNING) ||
+	    skb->len <= 0)
+		goto xmit_failed;
+
+	if (octnet_iq_is_full(vf_rep->oct, parent_lio->txq)) {
+		dev_err(&oct->pci_dev->dev, "VF rep: Device IQ full\n");
+		netif_stop_queue(ndev);
+		return NETDEV_TX_BUSY;
+	}
+
+	sc = (struct octeon_soft_command *)
+		octeon_alloc_soft_command(oct, 0, 0, 0);
+	if (!sc) {
+		dev_err(&oct->pci_dev->dev, "VF rep: Soft command alloc failed\n");
+		goto xmit_failed;
+	}
+
+	/* Multiple buffers are not used for vf_rep packets. */
+	if (skb_shinfo(skb)->nr_frags != 0) {
+		dev_err(&oct->pci_dev->dev, "VF rep: nr_frags != 0. Dropping packet\n");
+		goto xmit_failed;
+	}
+
+	sc->dmadptr = dma_map_single(&oct->pci_dev->dev,
+				     skb->data, skb->len, DMA_TO_DEVICE);
+	if (dma_mapping_error(&oct->pci_dev->dev, sc->dmadptr)) {
+		dev_err(&oct->pci_dev->dev, "VF rep: DMA mapping failed\n");
+		goto xmit_failed;
+	}
+
+	sc->virtdptr = skb->data;
+	sc->datasize = skb->len;
+	sc->ctxptr = skb;
+	sc->iq_no = parent_lio->txq;
+
+	octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_VF_REP_PKT,
+				    vf_rep->ifidx, 0, 0);
+	pki_ih3 = (struct octeon_instr_pki_ih3 *)&sc->cmd.cmd3.pki_ih3;
+	pki_ih3->tagtype = ORDERED_TAG;
+
+	sc->callback = lio_vf_rep_packet_sent_callback;
+	sc->callback_arg = sc;
+
+	status = octeon_send_soft_command(oct, sc);
+	if (status == IQ_SEND_FAILED) {
+		dma_unmap_single(&oct->pci_dev->dev, sc->dmadptr,
+				 sc->datasize, DMA_TO_DEVICE);
+		goto xmit_failed;
+	}
+
+	if (status == IQ_SEND_STOP)
+		netif_stop_queue(ndev);
+
+	netif_trans_update(ndev);
+
+	return NETDEV_TX_OK;
+
+xmit_failed:
+	dev_kfree_skb_any(skb);
+
+	return NETDEV_TX_OK;
+}
+
+static int
+lio_vf_rep_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+{
+	struct lio_vf_rep_desc *vf_rep = netdev_priv(dev);
+	struct net_device *parent_ndev = vf_rep->parent_ndev;
+	struct lio *lio = GET_LIO(parent_ndev);
+
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
+		attr->u.ppid.id_len = ETH_ALEN;
+		ether_addr_copy(attr->u.ppid.id,
+				(void *)&lio->linfo.hw_addr + 2);
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static const struct switchdev_ops lio_vf_rep_switchdev_ops = {
+	.switchdev_port_attr_get        = lio_vf_rep_attr_get,
+};
+
+static void
+lio_vf_rep_fetch_stats(struct work_struct *work)
+{
+	struct cavium_wk *wk = (struct cavium_wk *)work;
+	struct lio_vf_rep_desc *vf_rep = wk->ctxptr;
+	struct lio_vf_rep_stats stats;
+	struct lio_vf_rep_req rep_cfg;
+	struct octeon_device *oct;
+	int ret;
+
+	oct = vf_rep->oct;
+
+	memset(&rep_cfg, 0, sizeof(rep_cfg));
+	rep_cfg.req_type = LIO_VF_REP_REQ_STATS;
+	rep_cfg.ifidx = vf_rep->ifidx;
+
+	ret = lio_vf_rep_send_soft_command(oct, &rep_cfg, sizeof(rep_cfg),
+					   &stats, sizeof(stats));
+
+	if (!ret) {
+		octeon_swap_8B_data((u64 *)&stats, (sizeof(stats) >> 3));
+		memcpy(&vf_rep->stats, &stats, sizeof(stats));
+	}
+
+	schedule_delayed_work(&vf_rep->stats_wk.work,
+			      msecs_to_jiffies(LIO_VF_REP_STATS_POLL_TIME_MS));
+}
+
+int
+lio_vf_rep_create(struct octeon_device *oct)
+{
+	struct lio_vf_rep_desc *vf_rep;
+	struct net_device *ndev;
+	int i, num_vfs;
+
+	if (oct->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV)
+		return 0;
+
+	if (!oct->sriov_info.sriov_enabled)
+		return 0;
+
+	num_vfs = oct->sriov_info.num_vfs_alloced;
+
+	oct->vf_rep_list.num_vfs = 0;
+	for (i = 0; i < num_vfs; i++) {
+		ndev = alloc_etherdev(sizeof(struct lio_vf_rep_desc));
+
+		if (!ndev) {
+			dev_err(&oct->pci_dev->dev,
+				"VF rep device %d creation failed\n", i);
+			goto cleanup;
+		}
+
+		ndev->min_mtu = LIO_MIN_MTU_SIZE;
+		ndev->max_mtu = LIO_MAX_MTU_SIZE;
+		ndev->netdev_ops = &lio_vf_rep_ndev_ops;
+		SWITCHDEV_SET_OPS(ndev, &lio_vf_rep_switchdev_ops);
+
+		vf_rep = netdev_priv(ndev);
+		memset(vf_rep, 0, sizeof(*vf_rep));
+
+		vf_rep->ndev = ndev;
+		vf_rep->oct = oct;
+		vf_rep->parent_ndev = oct->props[0].netdev;
+		vf_rep->ifidx = (oct->pf_num * 64) + i + 1;
+
+		eth_hw_addr_random(ndev);
+
+		if (register_netdev(ndev)) {
+			dev_err(&oct->pci_dev->dev, "VF rep nerdev registration failed\n");
+
+			free_netdev(ndev);
+			goto cleanup;
+		}
+
+		netif_carrier_off(ndev);
+
+		INIT_DELAYED_WORK(&vf_rep->stats_wk.work,
+				  lio_vf_rep_fetch_stats);
+		vf_rep->stats_wk.ctxptr = (void *)vf_rep;
+		schedule_delayed_work(&vf_rep->stats_wk.work,
+				      msecs_to_jiffies
+				      (LIO_VF_REP_STATS_POLL_TIME_MS));
+		oct->vf_rep_list.num_vfs++;
+		oct->vf_rep_list.ndev[i] = ndev;
+	}
+
+	if (octeon_register_dispatch_fn(oct, OPCODE_NIC,
+					OPCODE_NIC_VF_REP_PKT,
+					lio_vf_rep_pkt_recv, oct)) {
+		dev_err(&oct->pci_dev->dev, "VF rep Dispatch func registration failed\n");
+
+		goto cleanup;
+	}
+
+	return 0;
+
+cleanup:
+	for (i = 0; i < oct->vf_rep_list.num_vfs; i++) {
+		ndev = oct->vf_rep_list.ndev[i];
+		oct->vf_rep_list.ndev[i] = NULL;
+		if (ndev) {
+			vf_rep = netdev_priv(ndev);
+			cancel_delayed_work_sync
+				(&vf_rep->stats_wk.work);
+			unregister_netdev(ndev);
+			free_netdev(ndev);
+		}
+	}
+
+	oct->vf_rep_list.num_vfs = 0;
+
+	return -1;
+}
+
+void
+lio_vf_rep_destroy(struct octeon_device *oct)
+{
+	struct lio_vf_rep_desc *vf_rep;
+	struct net_device *ndev;
+	int i;
+
+	if (oct->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV)
+		return;
+
+	if (!oct->sriov_info.sriov_enabled)
+		return;
+
+	for (i = 0; i < oct->vf_rep_list.num_vfs; i++) {
+		ndev = oct->vf_rep_list.ndev[i];
+		oct->vf_rep_list.ndev[i] = NULL;
+		if (ndev) {
+			vf_rep = netdev_priv(ndev);
+			cancel_delayed_work_sync
+				(&vf_rep->stats_wk.work);
+			netif_tx_disable(ndev);
+			netif_carrier_off(ndev);
+
+			unregister_netdev(ndev);
+			free_netdev(ndev);
+		}
+	}
+
+	oct->vf_rep_list.num_vfs = 0;
+}
+
+static int
+lio_vf_rep_netdev_event(struct notifier_block *nb,
+			unsigned long event, void *ptr)
+{
+	struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
+	struct lio_vf_rep_desc *vf_rep;
+	struct lio_vf_rep_req rep_cfg;
+	struct octeon_device *oct;
+	int ret;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+	case NETDEV_CHANGENAME:
+		break;
+
+	default:
+		return NOTIFY_DONE;
+	}
+
+	if (ndev->netdev_ops != &lio_vf_rep_ndev_ops)
+		return NOTIFY_DONE;
+
+	vf_rep = netdev_priv(ndev);
+	oct = vf_rep->oct;
+
+	if (strlen(ndev->name) > LIO_IF_NAME_SIZE) {
+		dev_err(&oct->pci_dev->dev,
+			"Device name change sync failed as the size is > %d\n",
+			LIO_IF_NAME_SIZE);
+		return NOTIFY_DONE;
+	}
+
+	memset(&rep_cfg, 0, sizeof(rep_cfg));
+	rep_cfg.req_type = LIO_VF_REP_REQ_DEVNAME;
+	rep_cfg.ifidx = vf_rep->ifidx;
+	strncpy(rep_cfg.rep_name.name, ndev->name, LIO_IF_NAME_SIZE);
+
+	ret = lio_vf_rep_send_soft_command(oct, &rep_cfg,
+					   sizeof(rep_cfg), NULL, 0);
+	if (ret)
+		dev_err(&oct->pci_dev->dev,
+			"vf_rep netdev name change failed with err %d\n", ret);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block lio_vf_rep_netdev_notifier = {
+	.notifier_call = lio_vf_rep_netdev_event,
+};
+
+int
+lio_vf_rep_modinit(void)
+{
+	if (register_netdevice_notifier(&lio_vf_rep_netdev_notifier)) {
+		pr_err("netdev notifier registration failed\n");
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+void
+lio_vf_rep_modexit(void)
+{
+	if (unregister_netdevice_notifier(&lio_vf_rep_netdev_notifier))
+		pr_err("netdev notifier unregister failed\n");
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.h b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.h
new file mode 100644
index 000000000000..bb3cedc63c63
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.h
@@ -0,0 +1,49 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium, Inc. for more information
+ **********************************************************************/
+
+/*! \file octeon_vf_main.h
+ *  \brief Host Driver: This file defines vf_rep related macros and structures
+ */
+#ifndef __LIO_VF_REP_H__
+#define __LIO_VF_REP_H__
+#define LIO_VF_REP_REQ_TMO_MS 5000
+#define LIO_VF_REP_STATS_POLL_TIME_MS 200
+
+struct lio_vf_rep_desc {
+	struct net_device *parent_ndev;
+	struct net_device *ndev;
+	struct octeon_device *oct;
+	struct lio_vf_rep_stats stats;
+	struct cavium_wk stats_wk;
+	atomic_t ifstate;
+	int ifidx;
+};
+
+struct lio_vf_rep_sc_ctx {
+	struct completion complete;
+};
+
+int lio_vf_rep_create(struct octeon_device *oct);
+void lio_vf_rep_destroy(struct octeon_device *oct);
+int lio_vf_rep_modinit(void);
+void lio_vf_rep_modexit(void);
+#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
index 3788c8cd082a..522dcc4dcff7 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
@@ -27,8 +27,8 @@
 
 #define LIQUIDIO_PACKAGE ""
 #define LIQUIDIO_BASE_MAJOR_VERSION 1
-#define LIQUIDIO_BASE_MINOR_VERSION 6
-#define LIQUIDIO_BASE_MICRO_VERSION 1
+#define LIQUIDIO_BASE_MINOR_VERSION 7
+#define LIQUIDIO_BASE_MICRO_VERSION 0
 #define LIQUIDIO_BASE_VERSION   __stringify(LIQUIDIO_BASE_MAJOR_VERSION) "." \
 				__stringify(LIQUIDIO_BASE_MINOR_VERSION)
 #define LIQUIDIO_MICRO_VERSION  "." __stringify(LIQUIDIO_BASE_MICRO_VERSION)
@@ -84,10 +84,14 @@ enum octeon_tag_type {
 #define OPCODE_NIC_IF_CFG              0x09
 #define OPCODE_NIC_VF_DRV_NOTICE       0x0A
 #define OPCODE_NIC_INTRMOD_PARAMS      0x0B
+#define OPCODE_NIC_SYNC_OCTEON_TIME	0x14
 #define VF_DRV_LOADED                  1
 #define VF_DRV_REMOVED                -1
 #define VF_DRV_MACADDR_CHANGED         2
 
+#define OPCODE_NIC_VF_REP_PKT          0x15
+#define OPCODE_NIC_VF_REP_CMD          0x16
+
 #define CORE_DRV_TEST_SCATTER_OP    0xFFF5
 
 /* Application codes advertised by the core driver initialization packet. */
@@ -108,6 +112,10 @@ enum octeon_tag_type {
 
 #define SCR2_BIT_FW_LOADED	    63
 
+/* App specific capabilities from firmware to pf driver */
+#define LIQUIDIO_TIME_SYNC_CAP 0x1
+#define LIQUIDIO_SWITCHDEV_CAP 0x2
+
 static inline u32 incr_index(u32 index, u32 count, u32 max)
 {
 	if ((index + count) >= max)
@@ -901,4 +909,60 @@ union oct_nic_if_cfg {
 	} s;
 };
 
+struct lio_time {
+	s64 sec;   /* seconds */
+	s64 nsec;  /* nanoseconds */
+};
+
+struct lio_vf_rep_stats {
+	u64 tx_packets;
+	u64 tx_bytes;
+	u64 tx_dropped;
+
+	u64 rx_packets;
+	u64 rx_bytes;
+	u64 rx_dropped;
+};
+
+enum lio_vf_rep_req_type {
+	LIO_VF_REP_REQ_NONE,
+	LIO_VF_REP_REQ_STATE,
+	LIO_VF_REP_REQ_MTU,
+	LIO_VF_REP_REQ_STATS,
+	LIO_VF_REP_REQ_DEVNAME
+};
+
+enum {
+	LIO_VF_REP_STATE_DOWN,
+	LIO_VF_REP_STATE_UP
+};
+
+#define LIO_IF_NAME_SIZE 16
+struct lio_vf_rep_req {
+	u8 req_type;
+	u8 ifidx;
+	u8 rsvd[6];
+
+	union {
+		struct lio_vf_rep_name {
+			char name[LIO_IF_NAME_SIZE];
+		} rep_name;
+
+		struct lio_vf_rep_mtu {
+			u32 mtu;
+			u32 rsvd;
+		} rep_mtu;
+
+		struct lio_vf_rep_state {
+			u8 state;
+			u8 rsvd[7];
+		} rep_state;
+	};
+};
+
+struct lio_vf_rep_resp {
+	u64 rh;
+	u8  status;
+	u8  rsvd[7];
+};
 #endif
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_image.h b/drivers/net/ethernet/cavium/liquidio/liquidio_image.h
index 78a3685f6fe0..5bf5e8791dfb 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_image.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_image.h
@@ -24,6 +24,7 @@
 #define LIO_FW_BASE_NAME        "lio_"
 #define LIO_FW_NAME_SUFFIX      ".bin"
 #define LIO_FW_NAME_TYPE_NIC    "nic"
+#define LIO_FW_NAME_TYPE_AUTO   "auto"
 #define LIO_FW_NAME_TYPE_NONE   "none"
 #define LIO_MAX_FIRMWARE_VERSION_LEN 16
 
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_config.h b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
index 63bd9c94e547..ceac74388e09 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_config.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
@@ -37,6 +37,8 @@
 #define   MAX_OCTEON_LINKS	       MAX_OCTEON_NICIF
 #define   MAX_OCTEON_MULTICAST_ADDR    32
 
+#define   MAX_OCTEON_FILL_COUNT        8
+
 /* CN6xxx IQ configuration macros */
 #define   CN6XXX_MAX_INPUT_QUEUES      32
 #define   CN6XXX_MAX_IQ_DESCRIPTORS    2048
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
index ec3dd69cd6b2..7f97ae48efed 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_console.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
@@ -803,15 +803,18 @@ static int octeon_console_read(struct octeon_device *oct, u32 console_num,
 }
 
 #define FBUF_SIZE	(4 * 1024 * 1024)
+#define MAX_BOOTTIME_SIZE    80
 
 int octeon_download_firmware(struct octeon_device *oct, const u8 *data,
 			     size_t size)
 {
-	int ret = 0;
+	struct octeon_firmware_file_header *h;
+	char boottime[MAX_BOOTTIME_SIZE];
+	struct timespec64 ts;
 	u32 crc32_result;
 	u64 load_addr;
 	u32 image_len;
-	struct octeon_firmware_file_header *h;
+	int ret = 0;
 	u32 i, rem;
 
 	if (size < sizeof(struct octeon_firmware_file_header)) {
@@ -890,11 +893,34 @@ int octeon_download_firmware(struct octeon_device *oct, const u8 *data,
 			load_addr += size;
 		}
 	}
+
+	/* Pass date and time information to NIC at the time of loading
+	 * firmware and periodically update the host time to NIC firmware.
+	 * This is to make NIC firmware use the same time reference as Host,
+	 * so that it is easy to correlate logs from firmware and host for
+	 * debugging.
+	 *
+	 * Octeon always uses UTC time. so timezone information is not sent.
+	 */
+	getnstimeofday64(&ts);
+	ret = snprintf(boottime, MAX_BOOTTIME_SIZE,
+		       " time_sec=%lld time_nsec=%ld",
+		       (s64)ts.tv_sec, ts.tv_nsec);
+	if ((sizeof(h->bootcmd) - strnlen(h->bootcmd, sizeof(h->bootcmd))) <
+		ret) {
+		dev_err(&oct->pci_dev->dev, "Boot command buffer too small\n");
+		return -EINVAL;
+	}
+	strncat(h->bootcmd, boottime,
+		sizeof(h->bootcmd) - strnlen(h->bootcmd, sizeof(h->bootcmd)));
+
 	dev_info(&oct->pci_dev->dev, "Writing boot command: %s\n",
 		 h->bootcmd);
 
 	/* Invoke the bootcmd */
 	ret = octeon_console_send_cmd(oct, h->bootcmd, 50);
+	if (ret)
+		dev_info(&oct->pci_dev->dev, "Boot command send failed\n");
 
-	return 0;
+	return ret;
 }
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 29d53b1763a7..2c615ab09e64 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -541,6 +541,7 @@ static char oct_dev_app_str[CVM_DRV_APP_COUNT + 1][32] = {
 
 static struct octeon_device *octeon_device[MAX_OCTEON_DEVICES];
 static atomic_t adapter_refcounts[MAX_OCTEON_DEVICES];
+static atomic_t adapter_fw_states[MAX_OCTEON_DEVICES];
 
 static u32 octeon_device_count;
 /* locks device array (i.e. octeon_device[]) */
@@ -770,6 +771,10 @@ int octeon_register_device(struct octeon_device *oct,
 	oct->adapter_refcount = &adapter_refcounts[oct->octeon_id];
 	atomic_set(oct->adapter_refcount, 0);
 
+	/* Like the reference count, the f/w state is shared 'per-adapter' */
+	oct->adapter_fw_state = &adapter_fw_states[oct->octeon_id];
+	atomic_set(oct->adapter_fw_state, FW_NEEDS_TO_BE_LOADED);
+
 	spin_lock(&octeon_devices_lock);
 	for (idx = (int)oct->octeon_id - 1; idx >= 0; idx--) {
 		if (!octeon_device[idx]) {
@@ -780,11 +785,15 @@ int octeon_register_device(struct octeon_device *oct,
 			atomic_inc(oct->adapter_refcount);
 			return 1; /* here, refcount is guaranteed to be 1 */
 		}
-		/* if another device is at same bus/dev, use its refcounter */
+		/* If another device is at same bus/dev, use its refcounter
+		 * (and f/w state variable).
+		 */
 		if ((octeon_device[idx]->loc.bus == bus) &&
 		    (octeon_device[idx]->loc.dev == dev)) {
 			oct->adapter_refcount =
 				octeon_device[idx]->adapter_refcount;
+			oct->adapter_fw_state =
+				octeon_device[idx]->adapter_fw_state;
 			break;
 		}
 	}
@@ -1171,6 +1180,10 @@ octeon_register_dispatch_fn(struct octeon_device *oct,
 		spin_unlock_bh(&oct->dispatch.lock);
 
 	} else {
+		if (pfn == fn &&
+		    octeon_get_dispatch_arg(oct, opcode, subcode) == fn_arg)
+			return 0;
+
 		dev_err(&oct->pci_dev->dev,
 			"Found previously registered dispatch fn for opcode/subcode: %x/%x\n",
 			opcode, subcode);
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index 894af199ddef..63b0c758a0a6 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -23,6 +23,7 @@
 #define  _OCTEON_DEVICE_H_
 
 #include <linux/interrupt.h>
+#include <net/devlink.h>
 
 /** PCI VendorId Device Id */
 #define  OCTEON_CN68XX_PCIID          0x91177d
@@ -50,6 +51,13 @@ enum octeon_pci_swap_mode {
 	OCTEON_PCI_32BIT_LW_SWAP = 3
 };
 
+enum lio_fw_state {
+	FW_IS_PRELOADED = 0,
+	FW_NEEDS_TO_BE_LOADED = 1,
+	FW_IS_BEING_LOADED = 2,
+	FW_HAS_BEEN_LOADED = 3,
+};
+
 enum {
 	OCTEON_CONFIG_TYPE_DEFAULT = 0,
 	NUM_OCTEON_CONFS,
@@ -384,6 +392,15 @@ struct octeon_ioq_vector {
 	u32			ioq_num;
 };
 
+struct lio_vf_rep_list {
+	int num_vfs;
+	struct net_device *ndev[CN23XX_MAX_VFS_PER_PF];
+};
+
+struct lio_devlink_priv {
+	struct octeon_device *oct;
+};
+
 /** The Octeon device.
  *  Each Octeon device has this structure to represent all its
  *  components.
@@ -557,7 +574,14 @@ struct octeon_device {
 	} loc;
 
 	atomic_t *adapter_refcount; /* reference count of adapter */
+
+	atomic_t *adapter_fw_state; /* per-adapter, lio_fw_state */
+
 	bool ptp_enable;
+
+	struct lio_vf_rep_list vf_rep_list;
+	struct devlink *devlink;
+	enum devlink_eswitch_mode eswitch_mode;
 };
 
 #define  OCT_DRV_ONLINE 1
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index 9372d4ce9954..3461d65ff4eb 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -52,8 +52,8 @@ struct __dispatch {
  *  @return  Failure: NULL
  *
  */
-static inline void *octeon_get_dispatch_arg(struct octeon_device *octeon_dev,
-					    u16 opcode, u16 subcode)
+void *octeon_get_dispatch_arg(struct octeon_device *octeon_dev,
+			      u16 opcode, u16 subcode)
 {
 	int idx;
 	struct list_head *dispatch;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
index f91bc84d1719..815a9f56fd59 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
@@ -400,6 +400,9 @@ int octeon_register_dispatch_fn(struct octeon_device *oct,
 				u16 subcode,
 				octeon_dispatch_fn_t fn, void *fn_arg);
 
+void *octeon_get_dispatch_arg(struct octeon_device *oct,
+			      u16 opcode, u16 subcode);
+
 void octeon_droq_print_stats(void);
 
 u32 octeon_droq_check_hw_for_pkts(struct octeon_droq *droq);
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
index 5c3c8da976f7..81c987682941 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -343,6 +343,9 @@ int octeon_delete_instr_queue(struct octeon_device *octeon_dev, u32 iq_no);
 
 int lio_wait_for_instr_fetch(struct octeon_device *oct);
 
+void
+octeon_ring_doorbell_locked(struct octeon_device *oct, u32 iq_no);
+
 int
 octeon_register_reqtype_free_fn(struct octeon_device *oct, int reqtype,
 				void (*fn)(void *));
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
index 32ef3a7d88d8..c846eec11a45 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
@@ -63,7 +63,7 @@ struct octnet_buf_free_info {
 };
 
 /* BQL-related functions */
-void octeon_report_sent_bytes_to_bql(void *buf, int reqtype);
+int octeon_report_sent_bytes_to_bql(void *buf, int reqtype);
 void octeon_update_tx_completion_counters(void *buf, int reqtype,
 					  unsigned int *pkts_compl,
 					  unsigned int *bytes_compl);
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
index 9e36319cead6..433f3619de8f 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
@@ -136,6 +136,9 @@ struct lio {
 	/* work queue for  link status */
 	struct cavium_wq	link_status_wq;
 
+	/* work queue to regularly send local time to octeon firmware */
+	struct cavium_wq	sync_octeon_time_wq;
+
 	int netdev_uc_count;
 };
 
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
index b457cf23fce6..150609bd8849 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
@@ -82,9 +82,10 @@ octeon_alloc_soft_command_resp(struct octeon_device    *oct,
 }
 
 int octnet_send_nic_data_pkt(struct octeon_device *oct,
-			     struct octnic_data_pkt *ndata)
+			     struct octnic_data_pkt *ndata,
+			     int xmit_more)
 {
-	int ring_doorbell = 1;
+	int ring_doorbell = !xmit_more;
 
 	return octeon_send_command(oct, ndata->q_no, ring_doorbell, &ndata->cmd,
 				   ndata->buf, ndata->datasize,
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
index 6480ef863441..de4130d26a98 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
@@ -279,7 +279,8 @@ octeon_alloc_soft_command_resp(struct octeon_device    *oct,
  * queue should be stopped, and IQ_SEND_OK if it sent okay.
  */
 int octnet_send_nic_data_pkt(struct octeon_device *oct,
-			     struct octnic_data_pkt *ndata);
+			     struct octnic_data_pkt *ndata,
+			     int xmit_more);
 
 /** Send a NIC control packet to the device
  * @param oct - octeon device pointer
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index 1e0fbce86d60..e07d2093b971 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -278,6 +278,18 @@ ring_doorbell(struct octeon_device *oct, struct octeon_instr_queue *iq)
 	}
 }
 
+void
+octeon_ring_doorbell_locked(struct octeon_device *oct, u32 iq_no)
+{
+	struct octeon_instr_queue *iq;
+
+	iq = oct->instr_queue[iq_no];
+	spin_lock(&iq->post_lock);
+	if (iq->fill_cnt)
+		ring_doorbell(oct, iq);
+	spin_unlock(&iq->post_lock);
+}
+
 static inline void __copy_cmd_into_iq(struct octeon_instr_queue *iq,
 				      u8 *cmd)
 {
@@ -477,8 +489,6 @@ octeon_flush_iq(struct octeon_device *oct, struct octeon_instr_queue *iq,
 		}
 
 		tot_inst_processed += inst_processed;
-		inst_processed = 0;
-
 	} while (tot_inst_processed < napi_budget);
 
 	if (napi_budget && (tot_inst_processed >= napi_budget))
@@ -543,6 +553,7 @@ octeon_send_command(struct octeon_device *oct, u32 iq_no,
 		    u32 force_db, void *cmd, void *buf,
 		    u32 datasize, u32 reqtype)
 {
+	int xmit_stopped;
 	struct iq_post_status st;
 	struct octeon_instr_queue *iq = oct->instr_queue[iq_no];
 
@@ -554,12 +565,13 @@ octeon_send_command(struct octeon_device *oct, u32 iq_no,
 	st = __post_command2(iq, cmd);
 
 	if (st.status != IQ_SEND_FAILED) {
-		octeon_report_sent_bytes_to_bql(buf, reqtype);
+		xmit_stopped = octeon_report_sent_bytes_to_bql(buf, reqtype);
 		__add_to_request_list(iq, st.index, buf, reqtype);
 		INCR_INSTRQUEUE_PKT_COUNT(oct, iq_no, bytes_sent, datasize);
 		INCR_INSTRQUEUE_PKT_COUNT(oct, iq_no, instr_posted, 1);
 
-		if (force_db)
+		if (iq->fill_cnt >= MAX_OCTEON_FILL_COUNT || force_db ||
+		    xmit_stopped || st.status == IQ_SEND_STOP)
 			ring_doorbell(oct, iq);
 	} else {
 		INCR_INSTRQUEUE_PKT_COUNT(oct, iq_no, instr_dropped, 1);
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 2887bcaf6af5..3f6afb54a5eb 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -705,14 +705,15 @@ static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev,
 			u64 clock_comp = (NSEC_PER_SEC << 32) /	octeon_get_io_clock_rate();
 			if (!ptp.s.ptp_en)
 				cvmx_write_csr(CVMX_MIO_PTP_CLOCK_COMP, clock_comp);
-			pr_info("PTP Clock: Using sclk reference at %lld Hz\n",
-				(NSEC_PER_SEC << 32) / clock_comp);
+			netdev_info(netdev,
+				    "PTP Clock using sclk reference @ %lldHz\n",
+				    (NSEC_PER_SEC << 32) / clock_comp);
 		} else {
 			/* The clock is already programmed to use a GPIO */
 			u64 clock_comp = cvmx_read_csr(CVMX_MIO_PTP_CLOCK_COMP);
-			pr_info("PTP Clock: Using GPIO %d at %lld Hz\n",
-				ptp.s.ext_clk_in,
-				(NSEC_PER_SEC << 32) / clock_comp);
+			netdev_info(netdev,
+				    "PTP Clock using GPIO%d @ %lld Hz\n",
+				    ptp.s.ext_clk_in, (NSEC_PER_SEC << 32) / clock_comp);
 		}
 
 		/* Enable the clock if it wasn't done already */
@@ -926,14 +927,11 @@ static void octeon_mgmt_adjust_link(struct net_device *netdev)
 	spin_unlock_irqrestore(&p->lock, flags);
 
 	if (link_changed != 0) {
-		if (link_changed > 0) {
-			pr_info("%s: Link is up - %d/%s\n", netdev->name,
-				phydev->speed,
-				phydev->duplex == DUPLEX_FULL ?
-				"Full" : "Half");
-		} else {
-			pr_info("%s: Link is down\n", netdev->name);
-		}
+		if (link_changed > 0)
+			netdev_info(netdev, "Link is up - %d/%s\n",
+				    phydev->speed, phydev->duplex == DUPLEX_FULL ? "Full" : "Half");
+		else
+			netdev_info(netdev, "Link is down\n");
 	}
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index fb770b0182d3..988c06a28e5e 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -584,9 +584,6 @@ static void nic_config_cpi(struct nicpf *nic, struct cpi_cfg_msg *cfg)
 static void nic_send_rss_size(struct nicpf *nic, int vf)
 {
 	union nic_mbx mbx = {};
-	u64  *msg;
-
-	msg = (u64 *)&mbx;
 
 	mbx.rss_size.msg = NIC_MBOX_MSG_RSS_SIZE;
 	mbx.rss_size.ind_tbl_size = nic->hw->rss_ind_tbl_size;
@@ -608,7 +605,6 @@ static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg)
 	rssi_base = nic->rssi_base[cfg->vf_id] + cfg->tbl_offset;
 
 	rssi = rssi_base;
-	qset = cfg->vf_id;
 
 	for (; rssi < (rssi_base + cfg->tbl_len); rssi++) {
 		u8 svf = cfg->ind_tbl[idx] >> 3;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 805ab45e9b5a..71989e180289 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -523,6 +523,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 
 	xdp.data_hard_start = page_address(page);
 	xdp.data = (void *)cpu_addr;
+	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = xdp.data + len;
 	orig_data = xdp.data;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
index 0f13a7f7c1d3..30de26ef3da4 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -1882,10 +1882,10 @@ send:
 /*
  * Callback for the Tx buffer reclaim timer.  Runs with softirqs disabled.
  */
-static void sge_tx_reclaim_cb(unsigned long data)
+static void sge_tx_reclaim_cb(struct timer_list *t)
 {
 	int i;
-	struct sge *sge = (struct sge *)data;
+	struct sge *sge = from_timer(sge, t, tx_reclaim_timer);
 
 	for (i = 0; i < SGE_CMDQ_N; ++i) {
 		struct cmdQ *q = &sge->cmdQ[i];
@@ -1978,10 +1978,10 @@ void t1_sge_start(struct sge *sge)
 /*
  * Callback for the T2 ESPI 'stuck packet feature' workaorund
  */
-static void espibug_workaround_t204(unsigned long data)
+static void espibug_workaround_t204(struct timer_list *t)
 {
-	struct adapter *adapter = (struct adapter *)data;
-	struct sge *sge = adapter->sge;
+	struct sge *sge = from_timer(sge, t, espibug_timer);
+	struct adapter *adapter = sge->adapter;
 	unsigned int nports = adapter->params.nports;
 	u32 seop[MAX_NPORTS];
 
@@ -2021,10 +2021,10 @@ static void espibug_workaround_t204(unsigned long data)
 	mod_timer(&sge->espibug_timer, jiffies + sge->espibug_timeout);
 }
 
-static void espibug_workaround(unsigned long data)
+static void espibug_workaround(struct timer_list *t)
 {
-	struct adapter *adapter = (struct adapter *)data;
-	struct sge *sge = adapter->sge;
+	struct sge *sge = from_timer(sge, t, espibug_timer);
+	struct adapter *adapter = sge->adapter;
 
 	if (netif_running(adapter->port[0].dev)) {
 	        struct sk_buff *skb = sge->espibug_skb[0];
@@ -2075,19 +2075,15 @@ struct sge *t1_sge_create(struct adapter *adapter, struct sge_params *p)
 			goto nomem_port;
 	}
 
-	init_timer(&sge->tx_reclaim_timer);
-	sge->tx_reclaim_timer.data = (unsigned long)sge;
-	sge->tx_reclaim_timer.function = sge_tx_reclaim_cb;
+	timer_setup(&sge->tx_reclaim_timer, sge_tx_reclaim_cb, 0);
 
 	if (is_T2(sge->adapter)) {
-		init_timer(&sge->espibug_timer);
+		timer_setup(&sge->espibug_timer,
+			    adapter->params.nports > 1 ? espibug_workaround_t204 : espibug_workaround,
+			    0);
 
-		if (adapter->params.nports > 1) {
+		if (adapter->params.nports > 1)
 			tx_sched_init(sge);
-			sge->espibug_timer.function = espibug_workaround_t204;
-		} else
-			sge->espibug_timer.function = espibug_workaround;
-		sge->espibug_timer.data = (unsigned long)sge->adapter;
 
 		sge->espibug_timeout = 1;
 		/* for T204, every 10ms */
diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index e2d342647b19..e988caa797cb 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -455,6 +455,11 @@ static int alloc_pg_chunk(struct adapter *adapter, struct sge_fl *q,
 		q->pg_chunk.offset = 0;
 		mapping = pci_map_page(adapter->pdev, q->pg_chunk.page,
 				       0, q->alloc_size, PCI_DMA_FROMDEVICE);
+		if (unlikely(pci_dma_mapping_error(adapter->pdev, mapping))) {
+			__free_pages(q->pg_chunk.page, order);
+			q->pg_chunk.page = NULL;
+			return -EIO;
+		}
 		q->pg_chunk.mapping = mapping;
 	}
 	sd->pg_chunk = q->pg_chunk;
@@ -949,40 +954,78 @@ static inline unsigned int calc_tx_descs(const struct sk_buff *skb)
 	return flits_to_desc(flits);
 }
 
+/*	map_skb - map a packet main body and its page fragments
+ *	@pdev: the PCI device
+ *	@skb: the packet
+ *	@addr: placeholder to save the mapped addresses
+ *
+ *	map the main body of an sk_buff and its page fragments, if any.
+ */
+static int map_skb(struct pci_dev *pdev, const struct sk_buff *skb,
+		   dma_addr_t *addr)
+{
+	const skb_frag_t *fp, *end;
+	const struct skb_shared_info *si;
+
+	if (skb_headlen(skb)) {
+		*addr = pci_map_single(pdev, skb->data, skb_headlen(skb),
+				       PCI_DMA_TODEVICE);
+		if (pci_dma_mapping_error(pdev, *addr))
+			goto out_err;
+		addr++;
+	}
+
+	si = skb_shinfo(skb);
+	end = &si->frags[si->nr_frags];
+
+	for (fp = si->frags; fp < end; fp++) {
+		*addr = skb_frag_dma_map(&pdev->dev, fp, 0, skb_frag_size(fp),
+					 DMA_TO_DEVICE);
+		if (pci_dma_mapping_error(pdev, *addr))
+			goto unwind;
+		addr++;
+	}
+	return 0;
+
+unwind:
+	while (fp-- > si->frags)
+		dma_unmap_page(&pdev->dev, *--addr, skb_frag_size(fp),
+			       DMA_TO_DEVICE);
+
+	pci_unmap_single(pdev, addr[-1], skb_headlen(skb), PCI_DMA_TODEVICE);
+out_err:
+	return -ENOMEM;
+}
+
 /**
- *	make_sgl - populate a scatter/gather list for a packet
+ *	write_sgl - populate a scatter/gather list for a packet
  *	@skb: the packet
  *	@sgp: the SGL to populate
  *	@start: start address of skb main body data to include in the SGL
  *	@len: length of skb main body data to include in the SGL
- *	@pdev: the PCI device
+ *	@addr: the list of the mapped addresses
  *
- *	Generates a scatter/gather list for the buffers that make up a packet
+ *	Copies the scatter/gather list for the buffers that make up a packet
  *	and returns the SGL size in 8-byte words.  The caller must size the SGL
  *	appropriately.
  */
-static inline unsigned int make_sgl(const struct sk_buff *skb,
-				    struct sg_ent *sgp, unsigned char *start,
-				    unsigned int len, struct pci_dev *pdev)
+static inline unsigned int write_sgl(const struct sk_buff *skb,
+				     struct sg_ent *sgp, unsigned char *start,
+				     unsigned int len, const dma_addr_t *addr)
 {
-	dma_addr_t mapping;
-	unsigned int i, j = 0, nfrags;
+	unsigned int i, j = 0, k = 0, nfrags;
 
 	if (len) {
-		mapping = pci_map_single(pdev, start, len, PCI_DMA_TODEVICE);
 		sgp->len[0] = cpu_to_be32(len);
-		sgp->addr[0] = cpu_to_be64(mapping);
-		j = 1;
+		sgp->addr[j++] = cpu_to_be64(addr[k++]);
 	}
 
 	nfrags = skb_shinfo(skb)->nr_frags;
 	for (i = 0; i < nfrags; i++) {
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
-		mapping = skb_frag_dma_map(&pdev->dev, frag, 0, skb_frag_size(frag),
-					   DMA_TO_DEVICE);
 		sgp->len[j] = cpu_to_be32(skb_frag_size(frag));
-		sgp->addr[j] = cpu_to_be64(mapping);
+		sgp->addr[j] = cpu_to_be64(addr[k++]);
 		j ^= 1;
 		if (j == 0)
 			++sgp;
@@ -1138,7 +1181,7 @@ static void write_tx_pkt_wr(struct adapter *adap, struct sk_buff *skb,
 			    const struct port_info *pi,
 			    unsigned int pidx, unsigned int gen,
 			    struct sge_txq *q, unsigned int ndesc,
-			    unsigned int compl)
+			    unsigned int compl, const dma_addr_t *addr)
 {
 	unsigned int flits, sgl_flits, cntrl, tso_info;
 	struct sg_ent *sgp, sgl[MAX_SKB_FRAGS / 2 + 1];
@@ -1196,7 +1239,7 @@ static void write_tx_pkt_wr(struct adapter *adap, struct sk_buff *skb,
 	}
 
 	sgp = ndesc == 1 ? (struct sg_ent *)&d->flit[flits] : sgl;
-	sgl_flits = make_sgl(skb, sgp, skb->data, skb_headlen(skb), adap->pdev);
+	sgl_flits = write_sgl(skb, sgp, skb->data, skb_headlen(skb), addr);
 
 	write_wr_hdr_sgl(ndesc, skb, d, pidx, q, sgl, flits, sgl_flits, gen,
 			 htonl(V_WR_OP(FW_WROPCODE_TUNNEL_TX_PKT) | compl),
@@ -1227,6 +1270,7 @@ netdev_tx_t t3_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct netdev_queue *txq;
 	struct sge_qset *qs;
 	struct sge_txq *q;
+	dma_addr_t addr[MAX_SKB_FRAGS + 1];
 
 	/*
 	 * The chip min packet length is 9 octets but play safe and reject
@@ -1255,6 +1299,14 @@ netdev_tx_t t3_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_BUSY;
 	}
 
+	/* Check if ethernet packet can't be sent as immediate data */
+	if (skb->len > (WR_LEN - sizeof(struct cpl_tx_pkt))) {
+		if (unlikely(map_skb(adap->pdev, skb, addr) < 0)) {
+			dev_kfree_skb(skb);
+			return NETDEV_TX_OK;
+		}
+	}
+
 	q->in_use += ndesc;
 	if (unlikely(credits - ndesc < q->stop_thres)) {
 		t3_stop_tx_queue(txq, qs, q);
@@ -1312,7 +1364,7 @@ netdev_tx_t t3_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (likely(!skb_shared(skb)))
 		skb_orphan(skb);
 
-	write_tx_pkt_wr(adap, skb, pi, pidx, gen, q, ndesc, compl);
+	write_tx_pkt_wr(adap, skb, pi, pidx, gen, q, ndesc, compl, addr);
 	check_ring_tx_db(adap, q);
 	return NETDEV_TX_OK;
 }
@@ -1577,7 +1629,8 @@ static void setup_deferred_unmapping(struct sk_buff *skb, struct pci_dev *pdev,
  */
 static void write_ofld_wr(struct adapter *adap, struct sk_buff *skb,
 			  struct sge_txq *q, unsigned int pidx,
-			  unsigned int gen, unsigned int ndesc)
+			  unsigned int gen, unsigned int ndesc,
+			  const dma_addr_t *addr)
 {
 	unsigned int sgl_flits, flits;
 	struct work_request_hdr *from;
@@ -1598,10 +1651,9 @@ static void write_ofld_wr(struct adapter *adap, struct sk_buff *skb,
 
 	flits = skb_transport_offset(skb) / 8;
 	sgp = ndesc == 1 ? (struct sg_ent *)&d->flit[flits] : sgl;
-	sgl_flits = make_sgl(skb, sgp, skb_transport_header(skb),
-			     skb_tail_pointer(skb) -
-			     skb_transport_header(skb),
-			     adap->pdev);
+	sgl_flits = write_sgl(skb, sgp, skb_transport_header(skb),
+			      skb_tail_pointer(skb) - skb_transport_header(skb),
+			      addr);
 	if (need_skb_unmap()) {
 		setup_deferred_unmapping(skb, adap->pdev, sgp, sgl_flits);
 		skb->destructor = deferred_unmap_destructor;
@@ -1659,6 +1711,12 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 		goto again;
 	}
 
+	if (!immediate(skb) &&
+	    map_skb(adap->pdev, skb, (dma_addr_t *)skb->head)) {
+		spin_unlock(&q->lock);
+		return NET_XMIT_SUCCESS;
+	}
+
 	gen = q->gen;
 	q->in_use += ndesc;
 	pidx = q->pidx;
@@ -1669,7 +1727,7 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 	}
 	spin_unlock(&q->lock);
 
-	write_ofld_wr(adap, skb, q, pidx, gen, ndesc);
+	write_ofld_wr(adap, skb, q, pidx, gen, ndesc, (dma_addr_t *)skb->head);
 	check_ring_tx_db(adap, q);
 	return NET_XMIT_SUCCESS;
 }
@@ -1687,6 +1745,7 @@ static void restart_offloadq(unsigned long data)
 	struct sge_txq *q = &qs->txq[TXQ_OFLD];
 	const struct port_info *pi = netdev_priv(qs->netdev);
 	struct adapter *adap = pi->adapter;
+	unsigned int written = 0;
 
 	spin_lock(&q->lock);
 again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
@@ -1706,10 +1765,15 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 			break;
 		}
 
+		if (!immediate(skb) &&
+		    map_skb(adap->pdev, skb, (dma_addr_t *)skb->head))
+			break;
+
 		gen = q->gen;
 		q->in_use += ndesc;
 		pidx = q->pidx;
 		q->pidx += ndesc;
+		written += ndesc;
 		if (q->pidx >= q->size) {
 			q->pidx -= q->size;
 			q->gen ^= 1;
@@ -1717,7 +1781,8 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 		__skb_unlink(skb, &q->sendq);
 		spin_unlock(&q->lock);
 
-		write_ofld_wr(adap, skb, q, pidx, gen, ndesc);
+		write_ofld_wr(adap, skb, q, pidx, gen, ndesc,
+			      (dma_addr_t *)skb->head);
 		spin_lock(&q->lock);
 	}
 	spin_unlock(&q->lock);
@@ -1727,8 +1792,9 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 	set_bit(TXQ_LAST_PKT_DB, &q->flags);
 #endif
 	wmb();
-	t3_write_reg(adap, A_SG_KDOORBELL,
-		     F_SELEGRCNTX | V_EGRCNTX(q->cntxt_id));
+	if (likely(written))
+		t3_write_reg(adap, A_SG_KDOORBELL,
+			     F_SELEGRCNTX | V_EGRCNTX(q->cntxt_id));
 }
 
 /**
@@ -2853,9 +2919,9 @@ void t3_sge_err_intr_handler(struct adapter *adapter)
  *	bother cleaning them up here.
  *
  */
-static void sge_timer_tx(unsigned long data)
+static void sge_timer_tx(struct timer_list *t)
 {
-	struct sge_qset *qs = (struct sge_qset *)data;
+	struct sge_qset *qs = from_timer(qs, t, tx_reclaim_timer);
 	struct port_info *pi = netdev_priv(qs->netdev);
 	struct adapter *adap = pi->adapter;
 	unsigned int tbd[SGE_TXQ_PER_SET] = {0, 0};
@@ -2893,10 +2959,10 @@ static void sge_timer_tx(unsigned long data)
  *	starved.
  *
  */
-static void sge_timer_rx(unsigned long data)
+static void sge_timer_rx(struct timer_list *t)
 {
 	spinlock_t *lock;
-	struct sge_qset *qs = (struct sge_qset *)data;
+	struct sge_qset *qs = from_timer(qs, t, rx_reclaim_timer);
 	struct port_info *pi = netdev_priv(qs->netdev);
 	struct adapter *adap = pi->adapter;
 	u32 status;
@@ -2976,8 +3042,8 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
 	struct sge_qset *q = &adapter->sge.qs[id];
 
 	init_qset_cntxt(q, id);
-	setup_timer(&q->tx_reclaim_timer, sge_timer_tx, (unsigned long)q);
-	setup_timer(&q->rx_reclaim_timer, sge_timer_rx, (unsigned long)q);
+	timer_setup(&q->tx_reclaim_timer, sge_timer_tx, 0);
+	timer_setup(&q->rx_reclaim_timer, sge_timer_rx, 0);
 
 	q->fl[0].desc = alloc_ring(adapter->pdev, p->fl_size,
 				   sizeof(struct rx_desc),
diff --git a/drivers/net/ethernet/chelsio/cxgb4/Makefile b/drivers/net/ethernet/chelsio/cxgb4/Makefile
index 24143c8abfdb..8c9c6b0d2e5d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/Makefile
+++ b/drivers/net/ethernet/chelsio/cxgb4/Makefile
@@ -5,7 +5,10 @@
 
 obj-$(CONFIG_CHELSIO_T4) += cxgb4.o
 
-cxgb4-objs := cxgb4_main.o l2t.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o cxgb4_uld.o sched.o cxgb4_filter.o cxgb4_tc_u32.o cxgb4_ptp.o
+cxgb4-objs := cxgb4_main.o l2t.o smt.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o \
+	      cxgb4_uld.o sched.o cxgb4_filter.o cxgb4_tc_u32.o \
+	      cxgb4_ptp.o cxgb4_tc_flower.o cxgb4_cudbg.o \
+	      cudbg_common.o cudbg_lib.o
 cxgb4-$(CONFIG_CHELSIO_T4_DCB) +=  cxgb4_dcb.o
 cxgb4-$(CONFIG_CHELSIO_T4_FCOE) +=  cxgb4_fcoe.o
 cxgb4-$(CONFIG_DEBUG_FS) += cxgb4_debugfs.o
diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
index 3103ef9b561d..290039026ece 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
@@ -96,7 +96,8 @@ int cxgb4_clip_get(const struct net_device *dev, const u32 *lip, u8 v6)
 		if (!ret) {
 			ce = cte;
 			read_unlock_bh(&ctbl->lock);
-			goto found;
+			refcount_inc(&ce->refcnt);
+			return 0;
 		}
 	}
 	read_unlock_bh(&ctbl->lock);
@@ -108,7 +109,7 @@ int cxgb4_clip_get(const struct net_device *dev, const u32 *lip, u8 v6)
 		list_del(&ce->list);
 		INIT_LIST_HEAD(&ce->list);
 		spin_lock_init(&ce->lock);
-		atomic_set(&ce->refcnt, 0);
+		refcount_set(&ce->refcnt, 0);
 		atomic_dec(&ctbl->nfree);
 		list_add_tail(&ce->list, &ctbl->hash_list[hash]);
 		if (v6) {
@@ -138,9 +139,7 @@ int cxgb4_clip_get(const struct net_device *dev, const u32 *lip, u8 v6)
 		return -ENOMEM;
 	}
 	write_unlock_bh(&ctbl->lock);
-found:
-	atomic_inc(&ce->refcnt);
-
+	refcount_set(&ce->refcnt, 1);
 	return 0;
 }
 EXPORT_SYMBOL(cxgb4_clip_get);
@@ -179,7 +178,7 @@ void cxgb4_clip_release(const struct net_device *dev, const u32 *lip, u8 v6)
 found:
 	write_lock_bh(&ctbl->lock);
 	spin_lock_bh(&ce->lock);
-	if (atomic_dec_and_test(&ce->refcnt)) {
+	if (refcount_dec_and_test(&ce->refcnt)) {
 		list_del(&ce->list);
 		INIT_LIST_HEAD(&ce->list);
 		list_add_tail(&ce->list, &ctbl->ce_free_head);
@@ -266,7 +265,7 @@ int clip_tbl_show(struct seq_file *seq, void *v)
 			ip[0] = '\0';
 			sprintf(ip, "%pISc", &ce->addr);
 			seq_printf(seq, "%-25s   %u\n", ip,
-				   atomic_read(&ce->refcnt));
+				   refcount_read(&ce->refcnt));
 		}
 	}
 	seq_printf(seq, "Free clip entries : %d\n", atomic_read(&ctbl->nfree));
diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h
index 35eb43c6bcbb..a0e0ae19649f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h
@@ -10,9 +10,11 @@
  *  release for licensing terms and conditions.
  */
 
+#include <linux/refcount.h>
+
 struct clip_entry {
 	spinlock_t lock;	/* Hold while modifying clip reference */
-	atomic_t refcnt;
+	refcount_t refcnt;
 	struct list_head list;
 	union {
 		struct sockaddr_in addr;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c
new file mode 100644
index 000000000000..f78ba1743b5a
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c
@@ -0,0 +1,54 @@
+/*
+ *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms and conditions of the GNU General Public License,
+ *  version 2, as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope it will be useful, but WITHOUT
+ *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *  more details.
+ *
+ *  The full GNU General Public License is included in this distribution in
+ *  the file called "COPYING".
+ *
+ */
+
+#include "cxgb4.h"
+#include "cudbg_if.h"
+#include "cudbg_lib_common.h"
+
+int cudbg_get_buff(struct cudbg_buffer *pdbg_buff, u32 size,
+		   struct cudbg_buffer *pin_buff)
+{
+	u32 offset;
+
+	offset = pdbg_buff->offset;
+	if (offset + size > pdbg_buff->size)
+		return CUDBG_STATUS_NO_MEM;
+
+	pin_buff->data = (char *)pdbg_buff->data + offset;
+	pin_buff->offset = offset;
+	pin_buff->size = size;
+	pdbg_buff->size -= size;
+	return 0;
+}
+
+void cudbg_put_buff(struct cudbg_buffer *pin_buff,
+		    struct cudbg_buffer *pdbg_buff)
+{
+	pdbg_buff->size += pin_buff->size;
+	pin_buff->data = NULL;
+	pin_buff->offset = 0;
+	pin_buff->size = 0;
+}
+
+void cudbg_update_buff(struct cudbg_buffer *pin_buff,
+		       struct cudbg_buffer *pout_buff)
+{
+	/* We already write to buffer provided by ethool, so just
+	 * increment offset to next free space.
+	 */
+	pout_buff->offset += pin_buff->size;
+}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
new file mode 100644
index 000000000000..239c43084e77
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
@@ -0,0 +1,340 @@
+/*
+ *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms and conditions of the GNU General Public License,
+ *  version 2, as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope it will be useful, but WITHOUT
+ *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *  more details.
+ *
+ *  The full GNU General Public License is included in this distribution in
+ *  the file called "COPYING".
+ *
+ */
+
+#ifndef __CUDBG_ENTITY_H__
+#define __CUDBG_ENTITY_H__
+
+#define EDC0_FLAG 3
+#define EDC1_FLAG 4
+
+#define CUDBG_ENTITY_SIGNATURE 0xCCEDB001
+
+struct card_mem {
+	u16 size_edc0;
+	u16 size_edc1;
+	u16 mem_flag;
+};
+
+struct cudbg_mbox_log {
+	struct mbox_cmd entry;
+	u32 hi[MBOX_LEN / 8];
+	u32 lo[MBOX_LEN / 8];
+};
+
+struct cudbg_cim_qcfg {
+	u8 chip;
+	u16 base[CIM_NUM_IBQ + CIM_NUM_OBQ_T5];
+	u16 size[CIM_NUM_IBQ + CIM_NUM_OBQ_T5];
+	u16 thres[CIM_NUM_IBQ];
+	u32 obq_wr[2 * CIM_NUM_OBQ_T5];
+	u32 stat[4 * (CIM_NUM_IBQ + CIM_NUM_OBQ_T5)];
+};
+
+struct cudbg_rss_vf_conf {
+	u32 rss_vf_vfl;
+	u32 rss_vf_vfh;
+};
+
+struct cudbg_pm_stats {
+	u32 tx_cnt[T6_PM_NSTATS];
+	u32 rx_cnt[T6_PM_NSTATS];
+	u64 tx_cyc[T6_PM_NSTATS];
+	u64 rx_cyc[T6_PM_NSTATS];
+};
+
+struct cudbg_hw_sched {
+	u32 kbps[NTX_SCHED];
+	u32 ipg[NTX_SCHED];
+	u32 pace_tab[NTX_SCHED];
+	u32 mode;
+	u32 map;
+};
+
+struct ireg_field {
+	u32 ireg_addr;
+	u32 ireg_data;
+	u32 ireg_local_offset;
+	u32 ireg_offset_range;
+};
+
+struct ireg_buf {
+	struct ireg_field tp_pio;
+	u32 outbuf[32];
+};
+
+struct cudbg_ulprx_la {
+	u32 data[ULPRX_LA_SIZE * 8];
+	u32 size;
+};
+
+struct cudbg_tp_la {
+	u32 size;
+	u32 mode;
+	u8 data[0];
+};
+
+struct cudbg_cim_pif_la {
+	int size;
+	u8 data[0];
+};
+
+struct cudbg_clk_info {
+	u64 retransmit_min;
+	u64 retransmit_max;
+	u64 persist_timer_min;
+	u64 persist_timer_max;
+	u64 keepalive_idle_timer;
+	u64 keepalive_interval;
+	u64 initial_srtt;
+	u64 finwait2_timer;
+	u32 dack_timer;
+	u32 res;
+	u32 cclk_ps;
+	u32 tre;
+	u32 dack_re;
+};
+
+struct cudbg_tid_info_region {
+	u32 ntids;
+	u32 nstids;
+	u32 stid_base;
+	u32 hash_base;
+
+	u32 natids;
+	u32 nftids;
+	u32 ftid_base;
+	u32 aftid_base;
+	u32 aftid_end;
+
+	u32 sftid_base;
+	u32 nsftids;
+
+	u32 uotid_base;
+	u32 nuotids;
+
+	u32 sb;
+	u32 flags;
+	u32 le_db_conf;
+	u32 ip_users;
+	u32 ipv6_users;
+
+	u32 hpftid_base;
+	u32 nhpftids;
+};
+
+#define CUDBG_TID_INFO_REV 1
+
+struct cudbg_tid_info_region_rev1 {
+	struct cudbg_ver_hdr ver_hdr;
+	struct cudbg_tid_info_region tid;
+	u32 tid_start;
+	u32 reserved[16];
+};
+
+#define CUDBG_MAX_RPLC_SIZE 128
+
+struct cudbg_mps_tcam {
+	u64 mask;
+	u32 rplc[8];
+	u32 idx;
+	u32 cls_lo;
+	u32 cls_hi;
+	u32 rplc_size;
+	u32 vniy;
+	u32 vnix;
+	u32 dip_hit;
+	u32 vlan_vld;
+	u32 repli;
+	u16 ivlan;
+	u8 addr[ETH_ALEN];
+	u8 lookup_type;
+	u8 port_num;
+	u8 reserved[2];
+};
+
+struct cudbg_vpd_data {
+	u8 sn[SERNUM_LEN + 1];
+	u8 bn[PN_LEN + 1];
+	u8 na[MACADDR_LEN + 1];
+	u8 mn[ID_LEN + 1];
+	u16 fw_major;
+	u16 fw_minor;
+	u16 fw_micro;
+	u16 fw_build;
+	u32 scfg_vers;
+	u32 vpd_vers;
+};
+
+#define CUDBG_NUM_ULPTX 11
+#define CUDBG_NUM_ULPTX_READ 512
+
+struct cudbg_ulptx_la {
+	u32 rdptr[CUDBG_NUM_ULPTX];
+	u32 wrptr[CUDBG_NUM_ULPTX];
+	u32 rddata[CUDBG_NUM_ULPTX];
+	u32 rd_data[CUDBG_NUM_ULPTX][CUDBG_NUM_ULPTX_READ];
+};
+
+#define CUDBG_CHAC_PBT_ADDR 0x2800
+#define CUDBG_CHAC_PBT_LRF  0x3000
+#define CUDBG_CHAC_PBT_DATA 0x3800
+#define CUDBG_PBT_DYNAMIC_ENTRIES 8
+#define CUDBG_PBT_STATIC_ENTRIES 16
+#define CUDBG_LRF_ENTRIES 8
+#define CUDBG_PBT_DATA_ENTRIES 512
+
+struct cudbg_pbt_tables {
+	u32 pbt_dynamic[CUDBG_PBT_DYNAMIC_ENTRIES];
+	u32 pbt_static[CUDBG_PBT_STATIC_ENTRIES];
+	u32 lrf_table[CUDBG_LRF_ENTRIES];
+	u32 pbt_data[CUDBG_PBT_DATA_ENTRIES];
+};
+
+#define IREG_NUM_ELEM 4
+
+static const u32 t6_tp_pio_array[][IREG_NUM_ELEM] = {
+	{0x7e40, 0x7e44, 0x020, 28}, /* t6_tp_pio_regs_20_to_3b */
+	{0x7e40, 0x7e44, 0x040, 10}, /* t6_tp_pio_regs_40_to_49 */
+	{0x7e40, 0x7e44, 0x050, 10}, /* t6_tp_pio_regs_50_to_59 */
+	{0x7e40, 0x7e44, 0x060, 14}, /* t6_tp_pio_regs_60_to_6d */
+	{0x7e40, 0x7e44, 0x06F, 1}, /* t6_tp_pio_regs_6f */
+	{0x7e40, 0x7e44, 0x070, 6}, /* t6_tp_pio_regs_70_to_75 */
+	{0x7e40, 0x7e44, 0x130, 18}, /* t6_tp_pio_regs_130_to_141 */
+	{0x7e40, 0x7e44, 0x145, 19}, /* t6_tp_pio_regs_145_to_157 */
+	{0x7e40, 0x7e44, 0x160, 1}, /* t6_tp_pio_regs_160 */
+	{0x7e40, 0x7e44, 0x230, 25}, /* t6_tp_pio_regs_230_to_248 */
+	{0x7e40, 0x7e44, 0x24a, 3}, /* t6_tp_pio_regs_24c */
+	{0x7e40, 0x7e44, 0x8C0, 1} /* t6_tp_pio_regs_8c0 */
+};
+
+static const u32 t5_tp_pio_array[][IREG_NUM_ELEM] = {
+	{0x7e40, 0x7e44, 0x020, 28}, /* t5_tp_pio_regs_20_to_3b */
+	{0x7e40, 0x7e44, 0x040, 19}, /* t5_tp_pio_regs_40_to_52 */
+	{0x7e40, 0x7e44, 0x054, 2}, /* t5_tp_pio_regs_54_to_55 */
+	{0x7e40, 0x7e44, 0x060, 13}, /* t5_tp_pio_regs_60_to_6c */
+	{0x7e40, 0x7e44, 0x06F, 1}, /* t5_tp_pio_regs_6f */
+	{0x7e40, 0x7e44, 0x120, 4}, /* t5_tp_pio_regs_120_to_123 */
+	{0x7e40, 0x7e44, 0x12b, 2}, /* t5_tp_pio_regs_12b_to_12c */
+	{0x7e40, 0x7e44, 0x12f, 21}, /* t5_tp_pio_regs_12f_to_143 */
+	{0x7e40, 0x7e44, 0x145, 19}, /* t5_tp_pio_regs_145_to_157 */
+	{0x7e40, 0x7e44, 0x230, 25}, /* t5_tp_pio_regs_230_to_248 */
+	{0x7e40, 0x7e44, 0x8C0, 1} /* t5_tp_pio_regs_8c0 */
+};
+
+static const u32 t6_tp_tm_pio_array[][IREG_NUM_ELEM] = {
+	{0x7e18, 0x7e1c, 0x0, 12}
+};
+
+static const u32 t5_tp_tm_pio_array[][IREG_NUM_ELEM] = {
+	{0x7e18, 0x7e1c, 0x0, 12}
+};
+
+static const u32 t6_tp_mib_index_array[6][IREG_NUM_ELEM] = {
+	{0x7e50, 0x7e54, 0x0, 13},
+	{0x7e50, 0x7e54, 0x10, 6},
+	{0x7e50, 0x7e54, 0x18, 21},
+	{0x7e50, 0x7e54, 0x30, 32},
+	{0x7e50, 0x7e54, 0x50, 22},
+	{0x7e50, 0x7e54, 0x68, 12}
+};
+
+static const u32 t5_tp_mib_index_array[9][IREG_NUM_ELEM] = {
+	{0x7e50, 0x7e54, 0x0, 13},
+	{0x7e50, 0x7e54, 0x10, 6},
+	{0x7e50, 0x7e54, 0x18, 8},
+	{0x7e50, 0x7e54, 0x20, 13},
+	{0x7e50, 0x7e54, 0x30, 16},
+	{0x7e50, 0x7e54, 0x40, 16},
+	{0x7e50, 0x7e54, 0x50, 16},
+	{0x7e50, 0x7e54, 0x60, 6},
+	{0x7e50, 0x7e54, 0x68, 4}
+};
+
+static const u32 t5_sge_dbg_index_array[2][IREG_NUM_ELEM] = {
+	{0x10cc, 0x10d0, 0x0, 16},
+	{0x10cc, 0x10d4, 0x0, 16},
+};
+
+static const u32 t5_pcie_pdbg_array[][IREG_NUM_ELEM] = {
+	{0x5a04, 0x5a0c, 0x00, 0x20}, /* t5_pcie_pdbg_regs_00_to_20 */
+	{0x5a04, 0x5a0c, 0x21, 0x20}, /* t5_pcie_pdbg_regs_21_to_40 */
+	{0x5a04, 0x5a0c, 0x41, 0x10}, /* t5_pcie_pdbg_regs_41_to_50 */
+};
+
+static const u32 t5_pcie_cdbg_array[][IREG_NUM_ELEM] = {
+	{0x5a10, 0x5a18, 0x00, 0x20}, /* t5_pcie_cdbg_regs_00_to_20 */
+	{0x5a10, 0x5a18, 0x21, 0x18}, /* t5_pcie_cdbg_regs_21_to_37 */
+};
+
+static const u32 t5_pm_rx_array[][IREG_NUM_ELEM] = {
+	{0x8FD0, 0x8FD4, 0x10000, 0x20}, /* t5_pm_rx_regs_10000_to_10020 */
+	{0x8FD0, 0x8FD4, 0x10021, 0x0D}, /* t5_pm_rx_regs_10021_to_1002c */
+};
+
+static const u32 t5_pm_tx_array[][IREG_NUM_ELEM] = {
+	{0x8FF0, 0x8FF4, 0x10000, 0x20}, /* t5_pm_tx_regs_10000_to_10020 */
+	{0x8FF0, 0x8FF4, 0x10021, 0x1D}, /* t5_pm_tx_regs_10021_to_1003c */
+};
+
+static const u32 t6_ma_ireg_array[][IREG_NUM_ELEM] = {
+	{0x78f8, 0x78fc, 0xa000, 23}, /* t6_ma_regs_a000_to_a016 */
+	{0x78f8, 0x78fc, 0xa400, 30}, /* t6_ma_regs_a400_to_a41e */
+	{0x78f8, 0x78fc, 0xa800, 20} /* t6_ma_regs_a800_to_a813 */
+};
+
+static const u32 t6_ma_ireg_array2[][IREG_NUM_ELEM] = {
+	{0x78f8, 0x78fc, 0xe400, 17}, /* t6_ma_regs_e400_to_e600 */
+	{0x78f8, 0x78fc, 0xe640, 13} /* t6_ma_regs_e640_to_e7c0 */
+};
+
+static const u32 t6_up_cim_reg_array[][IREG_NUM_ELEM] = {
+	{0x7b50, 0x7b54, 0x2000, 0x20}, /* up_cim_2000_to_207c */
+	{0x7b50, 0x7b54, 0x2080, 0x1d}, /* up_cim_2080_to_20fc */
+	{0x7b50, 0x7b54, 0x00, 0x20}, /* up_cim_00_to_7c */
+	{0x7b50, 0x7b54, 0x80, 0x20}, /* up_cim_80_to_fc */
+	{0x7b50, 0x7b54, 0x100, 0x11}, /* up_cim_100_to_14c */
+	{0x7b50, 0x7b54, 0x200, 0x10}, /* up_cim_200_to_23c */
+	{0x7b50, 0x7b54, 0x240, 0x2}, /* up_cim_240_to_244 */
+	{0x7b50, 0x7b54, 0x250, 0x2}, /* up_cim_250_to_254 */
+	{0x7b50, 0x7b54, 0x260, 0x2}, /* up_cim_260_to_264 */
+	{0x7b50, 0x7b54, 0x270, 0x2}, /* up_cim_270_to_274 */
+	{0x7b50, 0x7b54, 0x280, 0x20}, /* up_cim_280_to_2fc */
+	{0x7b50, 0x7b54, 0x300, 0x20}, /* up_cim_300_to_37c */
+	{0x7b50, 0x7b54, 0x380, 0x14}, /* up_cim_380_to_3cc */
+
+};
+
+static const u32 t5_up_cim_reg_array[][IREG_NUM_ELEM] = {
+	{0x7b50, 0x7b54, 0x2000, 0x20}, /* up_cim_2000_to_207c */
+	{0x7b50, 0x7b54, 0x2080, 0x19}, /* up_cim_2080_to_20ec */
+	{0x7b50, 0x7b54, 0x00, 0x20}, /* up_cim_00_to_7c */
+	{0x7b50, 0x7b54, 0x80, 0x20}, /* up_cim_80_to_fc */
+	{0x7b50, 0x7b54, 0x100, 0x11}, /* up_cim_100_to_14c */
+	{0x7b50, 0x7b54, 0x200, 0x10}, /* up_cim_200_to_23c */
+	{0x7b50, 0x7b54, 0x240, 0x2}, /* up_cim_240_to_244 */
+	{0x7b50, 0x7b54, 0x250, 0x2}, /* up_cim_250_to_254 */
+	{0x7b50, 0x7b54, 0x260, 0x2}, /* up_cim_260_to_264 */
+	{0x7b50, 0x7b54, 0x270, 0x2}, /* up_cim_270_to_274 */
+	{0x7b50, 0x7b54, 0x280, 0x20}, /* up_cim_280_to_2fc */
+	{0x7b50, 0x7b54, 0x300, 0x20}, /* up_cim_300_to_37c */
+	{0x7b50, 0x7b54, 0x380, 0x14}, /* up_cim_380_to_3cc */
+};
+
+static const u32 t6_hma_ireg_array[][IREG_NUM_ELEM] = {
+	{0x51320, 0x51324, 0xa000, 32} /* t6_hma_regs_a000_to_a01f */
+};
+#endif /* __CUDBG_ENTITY_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h
new file mode 100644
index 000000000000..e484c514e9ae
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h
@@ -0,0 +1,88 @@
+/*
+ *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms and conditions of the GNU General Public License,
+ *  version 2, as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope it will be useful, but WITHOUT
+ *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *  more details.
+ *
+ *  The full GNU General Public License is included in this distribution in
+ *  the file called "COPYING".
+ *
+ */
+
+#ifndef __CUDBG_IF_H__
+#define __CUDBG_IF_H__
+
+/* Error codes */
+#define CUDBG_STATUS_NO_MEM -19
+#define CUDBG_STATUS_ENTITY_NOT_FOUND -24
+#define CUDBG_SYSTEM_ERROR -29
+#define CUDBG_STATUS_CCLK_NOT_DEFINED -32
+
+#define CUDBG_MAJOR_VERSION 1
+#define CUDBG_MINOR_VERSION 14
+
+enum cudbg_dbg_entity_type {
+	CUDBG_REG_DUMP = 1,
+	CUDBG_DEV_LOG = 2,
+	CUDBG_CIM_LA = 3,
+	CUDBG_CIM_MA_LA = 4,
+	CUDBG_CIM_QCFG = 5,
+	CUDBG_CIM_IBQ_TP0 = 6,
+	CUDBG_CIM_IBQ_TP1 = 7,
+	CUDBG_CIM_IBQ_ULP = 8,
+	CUDBG_CIM_IBQ_SGE0 = 9,
+	CUDBG_CIM_IBQ_SGE1 = 10,
+	CUDBG_CIM_IBQ_NCSI = 11,
+	CUDBG_CIM_OBQ_ULP0 = 12,
+	CUDBG_CIM_OBQ_ULP1 = 13,
+	CUDBG_CIM_OBQ_ULP2 = 14,
+	CUDBG_CIM_OBQ_ULP3 = 15,
+	CUDBG_CIM_OBQ_SGE = 16,
+	CUDBG_CIM_OBQ_NCSI = 17,
+	CUDBG_EDC0 = 18,
+	CUDBG_EDC1 = 19,
+	CUDBG_RSS = 22,
+	CUDBG_RSS_VF_CONF = 25,
+	CUDBG_PATH_MTU = 27,
+	CUDBG_PM_STATS = 30,
+	CUDBG_HW_SCHED = 31,
+	CUDBG_TP_INDIRECT = 36,
+	CUDBG_SGE_INDIRECT = 37,
+	CUDBG_ULPRX_LA = 41,
+	CUDBG_TP_LA = 43,
+	CUDBG_CIM_PIF_LA = 45,
+	CUDBG_CLK = 46,
+	CUDBG_CIM_OBQ_RXQ0 = 47,
+	CUDBG_CIM_OBQ_RXQ1 = 48,
+	CUDBG_PCIE_INDIRECT = 50,
+	CUDBG_PM_INDIRECT = 51,
+	CUDBG_TID_INFO = 54,
+	CUDBG_MPS_TCAM = 57,
+	CUDBG_VPD_DATA = 58,
+	CUDBG_CCTRL = 60,
+	CUDBG_MA_INDIRECT = 61,
+	CUDBG_ULPTX_LA = 62,
+	CUDBG_UP_CIM_INDIRECT = 64,
+	CUDBG_PBT_TABLE = 65,
+	CUDBG_MBOX_LOG = 66,
+	CUDBG_HMA_INDIRECT = 67,
+	CUDBG_MAX_ENTITY = 70,
+};
+
+struct cudbg_init {
+	struct adapter *adap; /* Pointer to adapter structure */
+	void *outbuf; /* Output buffer */
+	u32 outbuf_size;  /* Output buffer size */
+};
+
+static inline unsigned int cudbg_mbytes_to_bytes(unsigned int size)
+{
+	return size * 1024 * 1024;
+}
+#endif /* __CUDBG_IF_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
new file mode 100644
index 000000000000..fe3a9ef0ec3f
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -0,0 +1,1621 @@
+/*
+ *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms and conditions of the GNU General Public License,
+ *  version 2, as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope it will be useful, but WITHOUT
+ *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *  more details.
+ *
+ *  The full GNU General Public License is included in this distribution in
+ *  the file called "COPYING".
+ *
+ */
+
+#include "t4_regs.h"
+#include "cxgb4.h"
+#include "cudbg_if.h"
+#include "cudbg_lib_common.h"
+#include "cudbg_lib.h"
+#include "cudbg_entity.h"
+
+static void cudbg_write_and_release_buff(struct cudbg_buffer *pin_buff,
+					 struct cudbg_buffer *dbg_buff)
+{
+	cudbg_update_buff(pin_buff, dbg_buff);
+	cudbg_put_buff(pin_buff, dbg_buff);
+}
+
+static int is_fw_attached(struct cudbg_init *pdbg_init)
+{
+	struct adapter *padap = pdbg_init->adap;
+
+	if (!(padap->flags & FW_OK) || padap->use_bd)
+		return 0;
+
+	return 1;
+}
+
+/* This function will add additional padding bytes into debug_buffer to make it
+ * 4 byte aligned.
+ */
+void cudbg_align_debug_buffer(struct cudbg_buffer *dbg_buff,
+			      struct cudbg_entity_hdr *entity_hdr)
+{
+	u8 zero_buf[4] = {0};
+	u8 padding, remain;
+
+	remain = (dbg_buff->offset - entity_hdr->start_offset) % 4;
+	padding = 4 - remain;
+	if (remain) {
+		memcpy(((u8 *)dbg_buff->data) + dbg_buff->offset, &zero_buf,
+		       padding);
+		dbg_buff->offset += padding;
+		entity_hdr->num_pad = padding;
+	}
+	entity_hdr->size = dbg_buff->offset - entity_hdr->start_offset;
+}
+
+struct cudbg_entity_hdr *cudbg_get_entity_hdr(void *outbuf, int i)
+{
+	struct cudbg_hdr *cudbg_hdr = (struct cudbg_hdr *)outbuf;
+
+	return (struct cudbg_entity_hdr *)
+	       ((char *)outbuf + cudbg_hdr->hdr_len +
+		(sizeof(struct cudbg_entity_hdr) * (i - 1)));
+}
+
+int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	u32 buf_size = 0;
+	int rc = 0;
+
+	if (is_t4(padap->params.chip))
+		buf_size = T4_REGMAP_SIZE;
+	else if (is_t5(padap->params.chip) || is_t6(padap->params.chip))
+		buf_size = T5_REGMAP_SIZE;
+
+	rc = cudbg_get_buff(dbg_buff, buf_size, &temp_buff);
+	if (rc)
+		return rc;
+	t4_get_regs(padap, (void *)temp_buff.data, temp_buff.size);
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_fw_devlog(struct cudbg_init *pdbg_init,
+			    struct cudbg_buffer *dbg_buff,
+			    struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct devlog_params *dparams;
+	int rc = 0;
+
+	rc = t4_init_devlog_params(padap);
+	if (rc < 0) {
+		cudbg_err->sys_err = rc;
+		return rc;
+	}
+
+	dparams = &padap->params.devlog;
+	rc = cudbg_get_buff(dbg_buff, dparams->size, &temp_buff);
+	if (rc)
+		return rc;
+
+	/* Collect FW devlog */
+	if (dparams->start != 0) {
+		spin_lock(&padap->win0_lock);
+		rc = t4_memory_rw(padap, padap->params.drv_memwin,
+				  dparams->memtype, dparams->start,
+				  dparams->size,
+				  (__be32 *)(char *)temp_buff.data,
+				  1);
+		spin_unlock(&padap->win0_lock);
+		if (rc) {
+			cudbg_err->sys_err = rc;
+			cudbg_put_buff(&temp_buff, dbg_buff);
+			return rc;
+		}
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_cim_la(struct cudbg_init *pdbg_init,
+			 struct cudbg_buffer *dbg_buff,
+			 struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	int size, rc;
+	u32 cfg = 0;
+
+	if (is_t6(padap->params.chip)) {
+		size = padap->params.cim_la_size / 10 + 1;
+		size *= 11 * sizeof(u32);
+	} else {
+		size = padap->params.cim_la_size / 8;
+		size *= 8 * sizeof(u32);
+	}
+
+	size += sizeof(cfg);
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	rc = t4_cim_read(padap, UP_UP_DBG_LA_CFG_A, 1, &cfg);
+	if (rc) {
+		cudbg_err->sys_err = rc;
+		cudbg_put_buff(&temp_buff, dbg_buff);
+		return rc;
+	}
+
+	memcpy((char *)temp_buff.data, &cfg, sizeof(cfg));
+	rc = t4_cim_read_la(padap,
+			    (u32 *)((char *)temp_buff.data + sizeof(cfg)),
+			    NULL);
+	if (rc < 0) {
+		cudbg_err->sys_err = rc;
+		cudbg_put_buff(&temp_buff, dbg_buff);
+		return rc;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_cim_ma_la(struct cudbg_init *pdbg_init,
+			    struct cudbg_buffer *dbg_buff,
+			    struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	int size, rc;
+
+	size = 2 * CIM_MALA_SIZE * 5 * sizeof(u32);
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	t4_cim_read_ma_la(padap,
+			  (u32 *)temp_buff.data,
+			  (u32 *)((char *)temp_buff.data +
+				  5 * CIM_MALA_SIZE));
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_cim_qcfg(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_cim_qcfg *cim_qcfg_data;
+	int rc;
+
+	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_cim_qcfg),
+			    &temp_buff);
+	if (rc)
+		return rc;
+
+	cim_qcfg_data = (struct cudbg_cim_qcfg *)temp_buff.data;
+	cim_qcfg_data->chip = padap->params.chip;
+	rc = t4_cim_read(padap, UP_IBQ_0_RDADDR_A,
+			 ARRAY_SIZE(cim_qcfg_data->stat), cim_qcfg_data->stat);
+	if (rc) {
+		cudbg_err->sys_err = rc;
+		cudbg_put_buff(&temp_buff, dbg_buff);
+		return rc;
+	}
+
+	rc = t4_cim_read(padap, UP_OBQ_0_REALADDR_A,
+			 ARRAY_SIZE(cim_qcfg_data->obq_wr),
+			 cim_qcfg_data->obq_wr);
+	if (rc) {
+		cudbg_err->sys_err = rc;
+		cudbg_put_buff(&temp_buff, dbg_buff);
+		return rc;
+	}
+
+	t4_read_cimq_cfg(padap, cim_qcfg_data->base, cim_qcfg_data->size,
+			 cim_qcfg_data->thres);
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+static int cudbg_read_cim_ibq(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err, int qid)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	int no_of_read_words, rc = 0;
+	u32 qsize;
+
+	/* collect CIM IBQ */
+	qsize = CIM_IBQ_SIZE * 4 * sizeof(u32);
+	rc = cudbg_get_buff(dbg_buff, qsize, &temp_buff);
+	if (rc)
+		return rc;
+
+	/* t4_read_cim_ibq will return no. of read words or error */
+	no_of_read_words = t4_read_cim_ibq(padap, qid,
+					   (u32 *)temp_buff.data, qsize);
+	/* no_of_read_words is less than or equal to 0 means error */
+	if (no_of_read_words <= 0) {
+		if (!no_of_read_words)
+			rc = CUDBG_SYSTEM_ERROR;
+		else
+			rc = no_of_read_words;
+		cudbg_err->sys_err = rc;
+		cudbg_put_buff(&temp_buff, dbg_buff);
+		return rc;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_cim_ibq_tp0(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 0);
+}
+
+int cudbg_collect_cim_ibq_tp1(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 1);
+}
+
+int cudbg_collect_cim_ibq_ulp(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 2);
+}
+
+int cudbg_collect_cim_ibq_sge0(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 3);
+}
+
+int cudbg_collect_cim_ibq_sge1(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 4);
+}
+
+int cudbg_collect_cim_ibq_ncsi(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 5);
+}
+
+u32 cudbg_cim_obq_size(struct adapter *padap, int qid)
+{
+	u32 value;
+
+	t4_write_reg(padap, CIM_QUEUE_CONFIG_REF_A, OBQSELECT_F |
+		     QUENUMSELECT_V(qid));
+	value = t4_read_reg(padap, CIM_QUEUE_CONFIG_CTRL_A);
+	value = CIMQSIZE_G(value) * 64; /* size in number of words */
+	return value * sizeof(u32);
+}
+
+static int cudbg_read_cim_obq(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err, int qid)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	int no_of_read_words, rc = 0;
+	u32 qsize;
+
+	/* collect CIM OBQ */
+	qsize =  cudbg_cim_obq_size(padap, qid);
+	rc = cudbg_get_buff(dbg_buff, qsize, &temp_buff);
+	if (rc)
+		return rc;
+
+	/* t4_read_cim_obq will return no. of read words or error */
+	no_of_read_words = t4_read_cim_obq(padap, qid,
+					   (u32 *)temp_buff.data, qsize);
+	/* no_of_read_words is less than or equal to 0 means error */
+	if (no_of_read_words <= 0) {
+		if (!no_of_read_words)
+			rc = CUDBG_SYSTEM_ERROR;
+		else
+			rc = no_of_read_words;
+		cudbg_err->sys_err = rc;
+		cudbg_put_buff(&temp_buff, dbg_buff);
+		return rc;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_cim_obq_ulp0(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 0);
+}
+
+int cudbg_collect_cim_obq_ulp1(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 1);
+}
+
+int cudbg_collect_cim_obq_ulp2(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 2);
+}
+
+int cudbg_collect_cim_obq_ulp3(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 3);
+}
+
+int cudbg_collect_cim_obq_sge(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 4);
+}
+
+int cudbg_collect_cim_obq_ncsi(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 5);
+}
+
+int cudbg_collect_obq_sge_rx_q0(struct cudbg_init *pdbg_init,
+				struct cudbg_buffer *dbg_buff,
+				struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 6);
+}
+
+int cudbg_collect_obq_sge_rx_q1(struct cudbg_init *pdbg_init,
+				struct cudbg_buffer *dbg_buff,
+				struct cudbg_error *cudbg_err)
+{
+	return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 7);
+}
+
+static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init,
+			     struct cudbg_buffer *dbg_buff, u8 mem_type,
+			     unsigned long tot_len,
+			     struct cudbg_error *cudbg_err)
+{
+	unsigned long bytes, bytes_left, bytes_read = 0;
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	int rc = 0;
+
+	bytes_left = tot_len;
+	while (bytes_left > 0) {
+		bytes = min_t(unsigned long, bytes_left,
+			      (unsigned long)CUDBG_CHUNK_SIZE);
+		rc = cudbg_get_buff(dbg_buff, bytes, &temp_buff);
+		if (rc)
+			return rc;
+		spin_lock(&padap->win0_lock);
+		rc = t4_memory_rw(padap, MEMWIN_NIC, mem_type,
+				  bytes_read, bytes,
+				  (__be32 *)temp_buff.data,
+				  1);
+		spin_unlock(&padap->win0_lock);
+		if (rc) {
+			cudbg_err->sys_err = rc;
+			cudbg_put_buff(&temp_buff, dbg_buff);
+			return rc;
+		}
+		bytes_left -= bytes;
+		bytes_read += bytes;
+		cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	}
+	return rc;
+}
+
+static void cudbg_collect_mem_info(struct cudbg_init *pdbg_init,
+				   struct card_mem *mem_info)
+{
+	struct adapter *padap = pdbg_init->adap;
+	u32 value;
+
+	value = t4_read_reg(padap, MA_EDRAM0_BAR_A);
+	value = EDRAM0_SIZE_G(value);
+	mem_info->size_edc0 = (u16)value;
+
+	value = t4_read_reg(padap, MA_EDRAM1_BAR_A);
+	value = EDRAM1_SIZE_G(value);
+	mem_info->size_edc1 = (u16)value;
+
+	value = t4_read_reg(padap, MA_TARGET_MEM_ENABLE_A);
+	if (value & EDRAM0_ENABLE_F)
+		mem_info->mem_flag |= (1 << EDC0_FLAG);
+	if (value & EDRAM1_ENABLE_F)
+		mem_info->mem_flag |= (1 << EDC1_FLAG);
+}
+
+static void cudbg_t4_fwcache(struct cudbg_init *pdbg_init,
+			     struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	int rc;
+
+	if (is_fw_attached(pdbg_init)) {
+		/* Flush uP dcache before reading edcX/mcX  */
+		rc = t4_fwcache(padap, FW_PARAM_DEV_FWCACHE_FLUSH);
+		if (rc)
+			cudbg_err->sys_warn = rc;
+	}
+}
+
+static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
+				    struct cudbg_buffer *dbg_buff,
+				    struct cudbg_error *cudbg_err,
+				    u8 mem_type)
+{
+	struct card_mem mem_info = {0};
+	unsigned long flag, size;
+	int rc;
+
+	cudbg_t4_fwcache(pdbg_init, cudbg_err);
+	cudbg_collect_mem_info(pdbg_init, &mem_info);
+	switch (mem_type) {
+	case MEM_EDC0:
+		flag = (1 << EDC0_FLAG);
+		size = cudbg_mbytes_to_bytes(mem_info.size_edc0);
+		break;
+	case MEM_EDC1:
+		flag = (1 << EDC1_FLAG);
+		size = cudbg_mbytes_to_bytes(mem_info.size_edc1);
+		break;
+	default:
+		rc = CUDBG_STATUS_ENTITY_NOT_FOUND;
+		goto err;
+	}
+
+	if (mem_info.mem_flag & flag) {
+		rc = cudbg_read_fw_mem(pdbg_init, dbg_buff, mem_type,
+				       size, cudbg_err);
+		if (rc)
+			goto err;
+	} else {
+		rc = CUDBG_STATUS_ENTITY_NOT_FOUND;
+		goto err;
+	}
+err:
+	return rc;
+}
+
+int cudbg_collect_edc0_meminfo(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err)
+{
+	return cudbg_collect_mem_region(pdbg_init, dbg_buff, cudbg_err,
+					MEM_EDC0);
+}
+
+int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err)
+{
+	return cudbg_collect_mem_region(pdbg_init, dbg_buff, cudbg_err,
+					MEM_EDC1);
+}
+
+int cudbg_collect_rss(struct cudbg_init *pdbg_init,
+		      struct cudbg_buffer *dbg_buff,
+		      struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	int rc;
+
+	rc = cudbg_get_buff(dbg_buff, RSS_NENTRIES * sizeof(u16), &temp_buff);
+	if (rc)
+		return rc;
+
+	rc = t4_read_rss(padap, (u16 *)temp_buff.data);
+	if (rc) {
+		cudbg_err->sys_err = rc;
+		cudbg_put_buff(&temp_buff, dbg_buff);
+		return rc;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_rss_vf_config(struct cudbg_init *pdbg_init,
+				struct cudbg_buffer *dbg_buff,
+				struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_rss_vf_conf *vfconf;
+	int vf, rc, vf_count;
+
+	vf_count = padap->params.arch.vfcount;
+	rc = cudbg_get_buff(dbg_buff,
+			    vf_count * sizeof(struct cudbg_rss_vf_conf),
+			    &temp_buff);
+	if (rc)
+		return rc;
+
+	vfconf = (struct cudbg_rss_vf_conf *)temp_buff.data;
+	for (vf = 0; vf < vf_count; vf++)
+		t4_read_rss_vf_config(padap, vf, &vfconf[vf].rss_vf_vfl,
+				      &vfconf[vf].rss_vf_vfh, true);
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_path_mtu(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	int rc;
+
+	rc = cudbg_get_buff(dbg_buff, NMTUS * sizeof(u16), &temp_buff);
+	if (rc)
+		return rc;
+
+	t4_read_mtu_tbl(padap, (u16 *)temp_buff.data, NULL);
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_pm_stats(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_pm_stats *pm_stats_buff;
+	int rc;
+
+	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_pm_stats),
+			    &temp_buff);
+	if (rc)
+		return rc;
+
+	pm_stats_buff = (struct cudbg_pm_stats *)temp_buff.data;
+	t4_pmtx_get_stats(padap, pm_stats_buff->tx_cnt, pm_stats_buff->tx_cyc);
+	t4_pmrx_get_stats(padap, pm_stats_buff->rx_cnt, pm_stats_buff->rx_cyc);
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_hw_sched(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_hw_sched *hw_sched_buff;
+	int i, rc = 0;
+
+	if (!padap->params.vpd.cclk)
+		return CUDBG_STATUS_CCLK_NOT_DEFINED;
+
+	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_hw_sched),
+			    &temp_buff);
+	hw_sched_buff = (struct cudbg_hw_sched *)temp_buff.data;
+	hw_sched_buff->map = t4_read_reg(padap, TP_TX_MOD_QUEUE_REQ_MAP_A);
+	hw_sched_buff->mode = TIMERMODE_G(t4_read_reg(padap, TP_MOD_CONFIG_A));
+	t4_read_pace_tbl(padap, hw_sched_buff->pace_tab);
+	for (i = 0; i < NTX_SCHED; ++i)
+		t4_get_tx_sched(padap, i, &hw_sched_buff->kbps[i],
+				&hw_sched_buff->ipg[i], true);
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_tp_indirect(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct ireg_buf *ch_tp_pio;
+	int i, rc, n = 0;
+	u32 size;
+
+	if (is_t5(padap->params.chip))
+		n = sizeof(t5_tp_pio_array) +
+		    sizeof(t5_tp_tm_pio_array) +
+		    sizeof(t5_tp_mib_index_array);
+	else
+		n = sizeof(t6_tp_pio_array) +
+		    sizeof(t6_tp_tm_pio_array) +
+		    sizeof(t6_tp_mib_index_array);
+
+	n = n / (IREG_NUM_ELEM * sizeof(u32));
+	size = sizeof(struct ireg_buf) * n;
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	ch_tp_pio = (struct ireg_buf *)temp_buff.data;
+
+	/* TP_PIO */
+	if (is_t5(padap->params.chip))
+		n = sizeof(t5_tp_pio_array) / (IREG_NUM_ELEM * sizeof(u32));
+	else if (is_t6(padap->params.chip))
+		n = sizeof(t6_tp_pio_array) / (IREG_NUM_ELEM * sizeof(u32));
+
+	for (i = 0; i < n; i++) {
+		struct ireg_field *tp_pio = &ch_tp_pio->tp_pio;
+		u32 *buff = ch_tp_pio->outbuf;
+
+		if (is_t5(padap->params.chip)) {
+			tp_pio->ireg_addr = t5_tp_pio_array[i][0];
+			tp_pio->ireg_data = t5_tp_pio_array[i][1];
+			tp_pio->ireg_local_offset = t5_tp_pio_array[i][2];
+			tp_pio->ireg_offset_range = t5_tp_pio_array[i][3];
+		} else if (is_t6(padap->params.chip)) {
+			tp_pio->ireg_addr = t6_tp_pio_array[i][0];
+			tp_pio->ireg_data = t6_tp_pio_array[i][1];
+			tp_pio->ireg_local_offset = t6_tp_pio_array[i][2];
+			tp_pio->ireg_offset_range = t6_tp_pio_array[i][3];
+		}
+		t4_tp_pio_read(padap, buff, tp_pio->ireg_offset_range,
+			       tp_pio->ireg_local_offset, true);
+		ch_tp_pio++;
+	}
+
+	/* TP_TM_PIO */
+	if (is_t5(padap->params.chip))
+		n = sizeof(t5_tp_tm_pio_array) / (IREG_NUM_ELEM * sizeof(u32));
+	else if (is_t6(padap->params.chip))
+		n = sizeof(t6_tp_tm_pio_array) / (IREG_NUM_ELEM * sizeof(u32));
+
+	for (i = 0; i < n; i++) {
+		struct ireg_field *tp_pio = &ch_tp_pio->tp_pio;
+		u32 *buff = ch_tp_pio->outbuf;
+
+		if (is_t5(padap->params.chip)) {
+			tp_pio->ireg_addr = t5_tp_tm_pio_array[i][0];
+			tp_pio->ireg_data = t5_tp_tm_pio_array[i][1];
+			tp_pio->ireg_local_offset = t5_tp_tm_pio_array[i][2];
+			tp_pio->ireg_offset_range = t5_tp_tm_pio_array[i][3];
+		} else if (is_t6(padap->params.chip)) {
+			tp_pio->ireg_addr = t6_tp_tm_pio_array[i][0];
+			tp_pio->ireg_data = t6_tp_tm_pio_array[i][1];
+			tp_pio->ireg_local_offset = t6_tp_tm_pio_array[i][2];
+			tp_pio->ireg_offset_range = t6_tp_tm_pio_array[i][3];
+		}
+		t4_tp_tm_pio_read(padap, buff, tp_pio->ireg_offset_range,
+				  tp_pio->ireg_local_offset, true);
+		ch_tp_pio++;
+	}
+
+	/* TP_MIB_INDEX */
+	if (is_t5(padap->params.chip))
+		n = sizeof(t5_tp_mib_index_array) /
+		    (IREG_NUM_ELEM * sizeof(u32));
+	else if (is_t6(padap->params.chip))
+		n = sizeof(t6_tp_mib_index_array) /
+		    (IREG_NUM_ELEM * sizeof(u32));
+
+	for (i = 0; i < n ; i++) {
+		struct ireg_field *tp_pio = &ch_tp_pio->tp_pio;
+		u32 *buff = ch_tp_pio->outbuf;
+
+		if (is_t5(padap->params.chip)) {
+			tp_pio->ireg_addr = t5_tp_mib_index_array[i][0];
+			tp_pio->ireg_data = t5_tp_mib_index_array[i][1];
+			tp_pio->ireg_local_offset =
+				t5_tp_mib_index_array[i][2];
+			tp_pio->ireg_offset_range =
+				t5_tp_mib_index_array[i][3];
+		} else if (is_t6(padap->params.chip)) {
+			tp_pio->ireg_addr = t6_tp_mib_index_array[i][0];
+			tp_pio->ireg_data = t6_tp_mib_index_array[i][1];
+			tp_pio->ireg_local_offset =
+				t6_tp_mib_index_array[i][2];
+			tp_pio->ireg_offset_range =
+				t6_tp_mib_index_array[i][3];
+		}
+		t4_tp_mib_read(padap, buff, tp_pio->ireg_offset_range,
+			       tp_pio->ireg_local_offset, true);
+		ch_tp_pio++;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct ireg_buf *ch_sge_dbg;
+	int i, rc;
+
+	rc = cudbg_get_buff(dbg_buff, sizeof(*ch_sge_dbg) * 2, &temp_buff);
+	if (rc)
+		return rc;
+
+	ch_sge_dbg = (struct ireg_buf *)temp_buff.data;
+	for (i = 0; i < 2; i++) {
+		struct ireg_field *sge_pio = &ch_sge_dbg->tp_pio;
+		u32 *buff = ch_sge_dbg->outbuf;
+
+		sge_pio->ireg_addr = t5_sge_dbg_index_array[i][0];
+		sge_pio->ireg_data = t5_sge_dbg_index_array[i][1];
+		sge_pio->ireg_local_offset = t5_sge_dbg_index_array[i][2];
+		sge_pio->ireg_offset_range = t5_sge_dbg_index_array[i][3];
+		t4_read_indirect(padap,
+				 sge_pio->ireg_addr,
+				 sge_pio->ireg_data,
+				 buff,
+				 sge_pio->ireg_offset_range,
+				 sge_pio->ireg_local_offset);
+		ch_sge_dbg++;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_ulprx_la(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_ulprx_la *ulprx_la_buff;
+	int rc;
+
+	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_ulprx_la),
+			    &temp_buff);
+	if (rc)
+		return rc;
+
+	ulprx_la_buff = (struct cudbg_ulprx_la *)temp_buff.data;
+	t4_ulprx_read_la(padap, (u32 *)ulprx_la_buff->data);
+	ulprx_la_buff->size = ULPRX_LA_SIZE;
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_tp_la(struct cudbg_init *pdbg_init,
+			struct cudbg_buffer *dbg_buff,
+			struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_tp_la *tp_la_buff;
+	int size, rc;
+
+	size = sizeof(struct cudbg_tp_la) + TPLA_SIZE *  sizeof(u64);
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	tp_la_buff = (struct cudbg_tp_la *)temp_buff.data;
+	tp_la_buff->mode = DBGLAMODE_G(t4_read_reg(padap, TP_DBG_LA_CONFIG_A));
+	t4_tp_read_la(padap, (u64 *)tp_la_buff->data, NULL);
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_cim_pif_la(struct cudbg_init *pdbg_init,
+			     struct cudbg_buffer *dbg_buff,
+			     struct cudbg_error *cudbg_err)
+{
+	struct cudbg_cim_pif_la *cim_pif_la_buff;
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	int size, rc;
+
+	size = sizeof(struct cudbg_cim_pif_la) +
+	       2 * CIM_PIFLA_SIZE * 6 * sizeof(u32);
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	cim_pif_la_buff = (struct cudbg_cim_pif_la *)temp_buff.data;
+	cim_pif_la_buff->size = CIM_PIFLA_SIZE;
+	t4_cim_read_pif_la(padap, (u32 *)cim_pif_la_buff->data,
+			   (u32 *)cim_pif_la_buff->data + 6 * CIM_PIFLA_SIZE,
+			   NULL, NULL);
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_clk_info(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_clk_info *clk_info_buff;
+	u64 tp_tick_us;
+	int rc;
+
+	if (!padap->params.vpd.cclk)
+		return CUDBG_STATUS_CCLK_NOT_DEFINED;
+
+	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_clk_info),
+			    &temp_buff);
+	if (rc)
+		return rc;
+
+	clk_info_buff = (struct cudbg_clk_info *)temp_buff.data;
+	clk_info_buff->cclk_ps = 1000000000 / padap->params.vpd.cclk; /* psec */
+	clk_info_buff->res = t4_read_reg(padap, TP_TIMER_RESOLUTION_A);
+	clk_info_buff->tre = TIMERRESOLUTION_G(clk_info_buff->res);
+	clk_info_buff->dack_re = DELAYEDACKRESOLUTION_G(clk_info_buff->res);
+	tp_tick_us = (clk_info_buff->cclk_ps << clk_info_buff->tre) / 1000000;
+
+	clk_info_buff->dack_timer =
+		(clk_info_buff->cclk_ps << clk_info_buff->dack_re) / 1000000 *
+		t4_read_reg(padap, TP_DACK_TIMER_A);
+	clk_info_buff->retransmit_min =
+		tp_tick_us * t4_read_reg(padap, TP_RXT_MIN_A);
+	clk_info_buff->retransmit_max =
+		tp_tick_us * t4_read_reg(padap, TP_RXT_MAX_A);
+	clk_info_buff->persist_timer_min =
+		tp_tick_us * t4_read_reg(padap, TP_PERS_MIN_A);
+	clk_info_buff->persist_timer_max =
+		tp_tick_us * t4_read_reg(padap, TP_PERS_MAX_A);
+	clk_info_buff->keepalive_idle_timer =
+		tp_tick_us * t4_read_reg(padap, TP_KEEP_IDLE_A);
+	clk_info_buff->keepalive_interval =
+		tp_tick_us * t4_read_reg(padap, TP_KEEP_INTVL_A);
+	clk_info_buff->initial_srtt =
+		tp_tick_us * INITSRTT_G(t4_read_reg(padap, TP_INIT_SRTT_A));
+	clk_info_buff->finwait2_timer =
+		tp_tick_us * t4_read_reg(padap, TP_FINWAIT2_TIMER_A);
+
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_pcie_indirect(struct cudbg_init *pdbg_init,
+				struct cudbg_buffer *dbg_buff,
+				struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct ireg_buf *ch_pcie;
+	int i, rc, n;
+	u32 size;
+
+	n = sizeof(t5_pcie_pdbg_array) / (IREG_NUM_ELEM * sizeof(u32));
+	size = sizeof(struct ireg_buf) * n * 2;
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	ch_pcie = (struct ireg_buf *)temp_buff.data;
+	/* PCIE_PDBG */
+	for (i = 0; i < n; i++) {
+		struct ireg_field *pcie_pio = &ch_pcie->tp_pio;
+		u32 *buff = ch_pcie->outbuf;
+
+		pcie_pio->ireg_addr = t5_pcie_pdbg_array[i][0];
+		pcie_pio->ireg_data = t5_pcie_pdbg_array[i][1];
+		pcie_pio->ireg_local_offset = t5_pcie_pdbg_array[i][2];
+		pcie_pio->ireg_offset_range = t5_pcie_pdbg_array[i][3];
+		t4_read_indirect(padap,
+				 pcie_pio->ireg_addr,
+				 pcie_pio->ireg_data,
+				 buff,
+				 pcie_pio->ireg_offset_range,
+				 pcie_pio->ireg_local_offset);
+		ch_pcie++;
+	}
+
+	/* PCIE_CDBG */
+	n = sizeof(t5_pcie_cdbg_array) / (IREG_NUM_ELEM * sizeof(u32));
+	for (i = 0; i < n; i++) {
+		struct ireg_field *pcie_pio = &ch_pcie->tp_pio;
+		u32 *buff = ch_pcie->outbuf;
+
+		pcie_pio->ireg_addr = t5_pcie_cdbg_array[i][0];
+		pcie_pio->ireg_data = t5_pcie_cdbg_array[i][1];
+		pcie_pio->ireg_local_offset = t5_pcie_cdbg_array[i][2];
+		pcie_pio->ireg_offset_range = t5_pcie_cdbg_array[i][3];
+		t4_read_indirect(padap,
+				 pcie_pio->ireg_addr,
+				 pcie_pio->ireg_data,
+				 buff,
+				 pcie_pio->ireg_offset_range,
+				 pcie_pio->ireg_local_offset);
+		ch_pcie++;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_pm_indirect(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct ireg_buf *ch_pm;
+	int i, rc, n;
+	u32 size;
+
+	n = sizeof(t5_pm_rx_array) / (IREG_NUM_ELEM * sizeof(u32));
+	size = sizeof(struct ireg_buf) * n * 2;
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	ch_pm = (struct ireg_buf *)temp_buff.data;
+	/* PM_RX */
+	for (i = 0; i < n; i++) {
+		struct ireg_field *pm_pio = &ch_pm->tp_pio;
+		u32 *buff = ch_pm->outbuf;
+
+		pm_pio->ireg_addr = t5_pm_rx_array[i][0];
+		pm_pio->ireg_data = t5_pm_rx_array[i][1];
+		pm_pio->ireg_local_offset = t5_pm_rx_array[i][2];
+		pm_pio->ireg_offset_range = t5_pm_rx_array[i][3];
+		t4_read_indirect(padap,
+				 pm_pio->ireg_addr,
+				 pm_pio->ireg_data,
+				 buff,
+				 pm_pio->ireg_offset_range,
+				 pm_pio->ireg_local_offset);
+		ch_pm++;
+	}
+
+	/* PM_TX */
+	n = sizeof(t5_pm_tx_array) / (IREG_NUM_ELEM * sizeof(u32));
+	for (i = 0; i < n; i++) {
+		struct ireg_field *pm_pio = &ch_pm->tp_pio;
+		u32 *buff = ch_pm->outbuf;
+
+		pm_pio->ireg_addr = t5_pm_tx_array[i][0];
+		pm_pio->ireg_data = t5_pm_tx_array[i][1];
+		pm_pio->ireg_local_offset = t5_pm_tx_array[i][2];
+		pm_pio->ireg_offset_range = t5_pm_tx_array[i][3];
+		t4_read_indirect(padap,
+				 pm_pio->ireg_addr,
+				 pm_pio->ireg_data,
+				 buff,
+				 pm_pio->ireg_offset_range,
+				 pm_pio->ireg_local_offset);
+		ch_pm++;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_tid(struct cudbg_init *pdbg_init,
+		      struct cudbg_buffer *dbg_buff,
+		      struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_tid_info_region_rev1 *tid1;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_tid_info_region *tid;
+	u32 para[2], val[2];
+	int rc;
+
+	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_tid_info_region_rev1),
+			    &temp_buff);
+	if (rc)
+		return rc;
+
+	tid1 = (struct cudbg_tid_info_region_rev1 *)temp_buff.data;
+	tid = &tid1->tid;
+	tid1->ver_hdr.signature = CUDBG_ENTITY_SIGNATURE;
+	tid1->ver_hdr.revision = CUDBG_TID_INFO_REV;
+	tid1->ver_hdr.size = sizeof(struct cudbg_tid_info_region_rev1) -
+			     sizeof(struct cudbg_ver_hdr);
+
+#define FW_PARAM_PFVF_A(param) \
+	(FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) | \
+	 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_##param) | \
+	 FW_PARAMS_PARAM_Y_V(0) | \
+	 FW_PARAMS_PARAM_Z_V(0))
+
+	para[0] = FW_PARAM_PFVF_A(ETHOFLD_START);
+	para[1] = FW_PARAM_PFVF_A(ETHOFLD_END);
+	rc = t4_query_params(padap, padap->mbox, padap->pf, 0, 2, para, val);
+	if (rc <  0) {
+		cudbg_err->sys_err = rc;
+		cudbg_put_buff(&temp_buff, dbg_buff);
+		return rc;
+	}
+	tid->uotid_base = val[0];
+	tid->nuotids = val[1] - val[0] + 1;
+
+	if (is_t5(padap->params.chip)) {
+		tid->sb = t4_read_reg(padap, LE_DB_SERVER_INDEX_A) / 4;
+	} else if (is_t6(padap->params.chip)) {
+		tid1->tid_start =
+			t4_read_reg(padap, LE_DB_ACTIVE_TABLE_START_INDEX_A);
+		tid->sb = t4_read_reg(padap, LE_DB_SRVR_START_INDEX_A);
+
+		para[0] = FW_PARAM_PFVF_A(HPFILTER_START);
+		para[1] = FW_PARAM_PFVF_A(HPFILTER_END);
+		rc = t4_query_params(padap, padap->mbox, padap->pf, 0, 2,
+				     para, val);
+		if (rc < 0) {
+			cudbg_err->sys_err = rc;
+			cudbg_put_buff(&temp_buff, dbg_buff);
+			return rc;
+		}
+		tid->hpftid_base = val[0];
+		tid->nhpftids = val[1] - val[0] + 1;
+	}
+
+	tid->ntids = padap->tids.ntids;
+	tid->nstids = padap->tids.nstids;
+	tid->stid_base = padap->tids.stid_base;
+	tid->hash_base = padap->tids.hash_base;
+
+	tid->natids = padap->tids.natids;
+	tid->nftids = padap->tids.nftids;
+	tid->ftid_base = padap->tids.ftid_base;
+	tid->aftid_base = padap->tids.aftid_base;
+	tid->aftid_end = padap->tids.aftid_end;
+
+	tid->sftid_base = padap->tids.sftid_base;
+	tid->nsftids = padap->tids.nsftids;
+
+	tid->flags = padap->flags;
+	tid->le_db_conf = t4_read_reg(padap, LE_DB_CONFIG_A);
+	tid->ip_users = t4_read_reg(padap, LE_DB_ACT_CNT_IPV4_A);
+	tid->ipv6_users = t4_read_reg(padap, LE_DB_ACT_CNT_IPV6_A);
+
+#undef FW_PARAM_PFVF_A
+
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+static inline void cudbg_tcamxy2valmask(u64 x, u64 y, u8 *addr, u64 *mask)
+{
+	*mask = x | y;
+	y = (__force u64)cpu_to_be64(y);
+	memcpy(addr, (char *)&y + 2, ETH_ALEN);
+}
+
+static void cudbg_mps_rpl_backdoor(struct adapter *padap,
+				   struct fw_ldst_mps_rplc *mps_rplc)
+{
+	if (is_t5(padap->params.chip)) {
+		mps_rplc->rplc255_224 = htonl(t4_read_reg(padap,
+							  MPS_VF_RPLCT_MAP3_A));
+		mps_rplc->rplc223_192 = htonl(t4_read_reg(padap,
+							  MPS_VF_RPLCT_MAP2_A));
+		mps_rplc->rplc191_160 = htonl(t4_read_reg(padap,
+							  MPS_VF_RPLCT_MAP1_A));
+		mps_rplc->rplc159_128 = htonl(t4_read_reg(padap,
+							  MPS_VF_RPLCT_MAP0_A));
+	} else {
+		mps_rplc->rplc255_224 = htonl(t4_read_reg(padap,
+							  MPS_VF_RPLCT_MAP7_A));
+		mps_rplc->rplc223_192 = htonl(t4_read_reg(padap,
+							  MPS_VF_RPLCT_MAP6_A));
+		mps_rplc->rplc191_160 = htonl(t4_read_reg(padap,
+							  MPS_VF_RPLCT_MAP5_A));
+		mps_rplc->rplc159_128 = htonl(t4_read_reg(padap,
+							  MPS_VF_RPLCT_MAP4_A));
+	}
+	mps_rplc->rplc127_96 = htonl(t4_read_reg(padap, MPS_VF_RPLCT_MAP3_A));
+	mps_rplc->rplc95_64 = htonl(t4_read_reg(padap, MPS_VF_RPLCT_MAP2_A));
+	mps_rplc->rplc63_32 = htonl(t4_read_reg(padap, MPS_VF_RPLCT_MAP1_A));
+	mps_rplc->rplc31_0 = htonl(t4_read_reg(padap, MPS_VF_RPLCT_MAP0_A));
+}
+
+static int cudbg_collect_tcam_index(struct adapter *padap,
+				    struct cudbg_mps_tcam *tcam, u32 idx)
+{
+	u64 tcamy, tcamx, val;
+	u32 ctl, data2;
+	int rc = 0;
+
+	if (CHELSIO_CHIP_VERSION(padap->params.chip) >= CHELSIO_T6) {
+		/* CtlReqID   - 1: use Host Driver Requester ID
+		 * CtlCmdType - 0: Read, 1: Write
+		 * CtlTcamSel - 0: TCAM0, 1: TCAM1
+		 * CtlXYBitSel- 0: Y bit, 1: X bit
+		 */
+
+		/* Read tcamy */
+		ctl = CTLREQID_V(1) | CTLCMDTYPE_V(0) | CTLXYBITSEL_V(0);
+		if (idx < 256)
+			ctl |= CTLTCAMINDEX_V(idx) | CTLTCAMSEL_V(0);
+		else
+			ctl |= CTLTCAMINDEX_V(idx - 256) | CTLTCAMSEL_V(1);
+
+		t4_write_reg(padap, MPS_CLS_TCAM_DATA2_CTL_A, ctl);
+		val = t4_read_reg(padap, MPS_CLS_TCAM_RDATA1_REQ_ID1_A);
+		tcamy = DMACH_G(val) << 32;
+		tcamy |= t4_read_reg(padap, MPS_CLS_TCAM_RDATA0_REQ_ID1_A);
+		data2 = t4_read_reg(padap, MPS_CLS_TCAM_RDATA2_REQ_ID1_A);
+		tcam->lookup_type = DATALKPTYPE_G(data2);
+
+		/* 0 - Outer header, 1 - Inner header
+		 * [71:48] bit locations are overloaded for
+		 * outer vs. inner lookup types.
+		 */
+		if (tcam->lookup_type && tcam->lookup_type != DATALKPTYPE_M) {
+			/* Inner header VNI */
+			tcam->vniy = (data2 & DATAVIDH2_F) | DATAVIDH1_G(data2);
+			tcam->vniy = (tcam->vniy << 16) | VIDL_G(val);
+			tcam->dip_hit = data2 & DATADIPHIT_F;
+		} else {
+			tcam->vlan_vld = data2 & DATAVIDH2_F;
+			tcam->ivlan = VIDL_G(val);
+		}
+
+		tcam->port_num = DATAPORTNUM_G(data2);
+
+		/* Read tcamx. Change the control param */
+		ctl |= CTLXYBITSEL_V(1);
+		t4_write_reg(padap, MPS_CLS_TCAM_DATA2_CTL_A, ctl);
+		val = t4_read_reg(padap, MPS_CLS_TCAM_RDATA1_REQ_ID1_A);
+		tcamx = DMACH_G(val) << 32;
+		tcamx |= t4_read_reg(padap, MPS_CLS_TCAM_RDATA0_REQ_ID1_A);
+		data2 = t4_read_reg(padap, MPS_CLS_TCAM_RDATA2_REQ_ID1_A);
+		if (tcam->lookup_type && tcam->lookup_type != DATALKPTYPE_M) {
+			/* Inner header VNI mask */
+			tcam->vnix = (data2 & DATAVIDH2_F) | DATAVIDH1_G(data2);
+			tcam->vnix = (tcam->vnix << 16) | VIDL_G(val);
+		}
+	} else {
+		tcamy = t4_read_reg64(padap, MPS_CLS_TCAM_Y_L(idx));
+		tcamx = t4_read_reg64(padap, MPS_CLS_TCAM_X_L(idx));
+	}
+
+	/* If no entry, return */
+	if (tcamx & tcamy)
+		return rc;
+
+	tcam->cls_lo = t4_read_reg(padap, MPS_CLS_SRAM_L(idx));
+	tcam->cls_hi = t4_read_reg(padap, MPS_CLS_SRAM_H(idx));
+
+	if (is_t5(padap->params.chip))
+		tcam->repli = (tcam->cls_lo & REPLICATE_F);
+	else if (is_t6(padap->params.chip))
+		tcam->repli = (tcam->cls_lo & T6_REPLICATE_F);
+
+	if (tcam->repli) {
+		struct fw_ldst_cmd ldst_cmd;
+		struct fw_ldst_mps_rplc mps_rplc;
+
+		memset(&ldst_cmd, 0, sizeof(ldst_cmd));
+		ldst_cmd.op_to_addrspace =
+			htonl(FW_CMD_OP_V(FW_LDST_CMD) |
+			      FW_CMD_REQUEST_F | FW_CMD_READ_F |
+			      FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_MPS));
+		ldst_cmd.cycles_to_len16 = htonl(FW_LEN16(ldst_cmd));
+		ldst_cmd.u.mps.rplc.fid_idx =
+			htons(FW_LDST_CMD_FID_V(FW_LDST_MPS_RPLC) |
+			      FW_LDST_CMD_IDX_V(idx));
+
+		rc = t4_wr_mbox(padap, padap->mbox, &ldst_cmd, sizeof(ldst_cmd),
+				&ldst_cmd);
+		if (rc)
+			cudbg_mps_rpl_backdoor(padap, &mps_rplc);
+		else
+			mps_rplc = ldst_cmd.u.mps.rplc;
+
+		tcam->rplc[0] = ntohl(mps_rplc.rplc31_0);
+		tcam->rplc[1] = ntohl(mps_rplc.rplc63_32);
+		tcam->rplc[2] = ntohl(mps_rplc.rplc95_64);
+		tcam->rplc[3] = ntohl(mps_rplc.rplc127_96);
+		if (padap->params.arch.mps_rplc_size > CUDBG_MAX_RPLC_SIZE) {
+			tcam->rplc[4] = ntohl(mps_rplc.rplc159_128);
+			tcam->rplc[5] = ntohl(mps_rplc.rplc191_160);
+			tcam->rplc[6] = ntohl(mps_rplc.rplc223_192);
+			tcam->rplc[7] = ntohl(mps_rplc.rplc255_224);
+		}
+	}
+	cudbg_tcamxy2valmask(tcamx, tcamy, tcam->addr, &tcam->mask);
+	tcam->idx = idx;
+	tcam->rplc_size = padap->params.arch.mps_rplc_size;
+	return rc;
+}
+
+int cudbg_collect_mps_tcam(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	u32 size = 0, i, n, total_size = 0;
+	struct cudbg_mps_tcam *tcam;
+	int rc;
+
+	n = padap->params.arch.mps_tcam_size;
+	size = sizeof(struct cudbg_mps_tcam) * n;
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	tcam = (struct cudbg_mps_tcam *)temp_buff.data;
+	for (i = 0; i < n; i++) {
+		rc = cudbg_collect_tcam_index(padap, tcam, i);
+		if (rc) {
+			cudbg_err->sys_err = rc;
+			cudbg_put_buff(&temp_buff, dbg_buff);
+			return rc;
+		}
+		total_size += sizeof(struct cudbg_mps_tcam);
+		tcam++;
+	}
+
+	if (!total_size) {
+		rc = CUDBG_SYSTEM_ERROR;
+		cudbg_err->sys_err = rc;
+		cudbg_put_buff(&temp_buff, dbg_buff);
+		return rc;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_vpd_data(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_vpd_data *vpd_data;
+	int rc;
+
+	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_vpd_data),
+			    &temp_buff);
+	if (rc)
+		return rc;
+
+	vpd_data = (struct cudbg_vpd_data *)temp_buff.data;
+	memcpy(vpd_data->sn, padap->params.vpd.sn, SERNUM_LEN + 1);
+	memcpy(vpd_data->bn, padap->params.vpd.pn, PN_LEN + 1);
+	memcpy(vpd_data->na, padap->params.vpd.na, MACADDR_LEN + 1);
+	memcpy(vpd_data->mn, padap->params.vpd.id, ID_LEN + 1);
+	vpd_data->scfg_vers = padap->params.scfg_vers;
+	vpd_data->vpd_vers = padap->params.vpd_vers;
+	vpd_data->fw_major = FW_HDR_FW_VER_MAJOR_G(padap->params.fw_vers);
+	vpd_data->fw_minor = FW_HDR_FW_VER_MINOR_G(padap->params.fw_vers);
+	vpd_data->fw_micro = FW_HDR_FW_VER_MICRO_G(padap->params.fw_vers);
+	vpd_data->fw_build = FW_HDR_FW_VER_BUILD_G(padap->params.fw_vers);
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_cctrl(struct cudbg_init *pdbg_init,
+			struct cudbg_buffer *dbg_buff,
+			struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	u32 size;
+	int rc;
+
+	size = sizeof(u16) * NMTUS * NCCTRL_WIN;
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	t4_read_cong_tbl(padap, (void *)temp_buff.data);
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_ma_indirect(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct ireg_buf *ma_indr;
+	int i, rc, n;
+	u32 size, j;
+
+	if (CHELSIO_CHIP_VERSION(padap->params.chip) < CHELSIO_T6)
+		return CUDBG_STATUS_ENTITY_NOT_FOUND;
+
+	n = sizeof(t6_ma_ireg_array) / (IREG_NUM_ELEM * sizeof(u32));
+	size = sizeof(struct ireg_buf) * n * 2;
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	ma_indr = (struct ireg_buf *)temp_buff.data;
+	for (i = 0; i < n; i++) {
+		struct ireg_field *ma_fli = &ma_indr->tp_pio;
+		u32 *buff = ma_indr->outbuf;
+
+		ma_fli->ireg_addr = t6_ma_ireg_array[i][0];
+		ma_fli->ireg_data = t6_ma_ireg_array[i][1];
+		ma_fli->ireg_local_offset = t6_ma_ireg_array[i][2];
+		ma_fli->ireg_offset_range = t6_ma_ireg_array[i][3];
+		t4_read_indirect(padap, ma_fli->ireg_addr, ma_fli->ireg_data,
+				 buff, ma_fli->ireg_offset_range,
+				 ma_fli->ireg_local_offset);
+		ma_indr++;
+	}
+
+	n = sizeof(t6_ma_ireg_array2) / (IREG_NUM_ELEM * sizeof(u32));
+	for (i = 0; i < n; i++) {
+		struct ireg_field *ma_fli = &ma_indr->tp_pio;
+		u32 *buff = ma_indr->outbuf;
+
+		ma_fli->ireg_addr = t6_ma_ireg_array2[i][0];
+		ma_fli->ireg_data = t6_ma_ireg_array2[i][1];
+		ma_fli->ireg_local_offset = t6_ma_ireg_array2[i][2];
+		for (j = 0; j < t6_ma_ireg_array2[i][3]; j++) {
+			t4_read_indirect(padap, ma_fli->ireg_addr,
+					 ma_fli->ireg_data, buff, 1,
+					 ma_fli->ireg_local_offset);
+			buff++;
+			ma_fli->ireg_local_offset += 0x20;
+		}
+		ma_indr++;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_ulptx_la(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_ulptx_la *ulptx_la_buff;
+	u32 i, j;
+	int rc;
+
+	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_ulptx_la),
+			    &temp_buff);
+	if (rc)
+		return rc;
+
+	ulptx_la_buff = (struct cudbg_ulptx_la *)temp_buff.data;
+	for (i = 0; i < CUDBG_NUM_ULPTX; i++) {
+		ulptx_la_buff->rdptr[i] = t4_read_reg(padap,
+						      ULP_TX_LA_RDPTR_0_A +
+						      0x10 * i);
+		ulptx_la_buff->wrptr[i] = t4_read_reg(padap,
+						      ULP_TX_LA_WRPTR_0_A +
+						      0x10 * i);
+		ulptx_la_buff->rddata[i] = t4_read_reg(padap,
+						       ULP_TX_LA_RDDATA_0_A +
+						       0x10 * i);
+		for (j = 0; j < CUDBG_NUM_ULPTX_READ; j++)
+			ulptx_la_buff->rd_data[i][j] =
+				t4_read_reg(padap,
+					    ULP_TX_LA_RDDATA_0_A + 0x10 * i);
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_up_cim_indirect(struct cudbg_init *pdbg_init,
+				  struct cudbg_buffer *dbg_buff,
+				  struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct ireg_buf *up_cim;
+	int i, rc, n;
+	u32 size;
+
+	n = sizeof(t5_up_cim_reg_array) / (IREG_NUM_ELEM * sizeof(u32));
+	size = sizeof(struct ireg_buf) * n;
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	up_cim = (struct ireg_buf *)temp_buff.data;
+	for (i = 0; i < n; i++) {
+		struct ireg_field *up_cim_reg = &up_cim->tp_pio;
+		u32 *buff = up_cim->outbuf;
+
+		if (is_t5(padap->params.chip)) {
+			up_cim_reg->ireg_addr = t5_up_cim_reg_array[i][0];
+			up_cim_reg->ireg_data = t5_up_cim_reg_array[i][1];
+			up_cim_reg->ireg_local_offset =
+						t5_up_cim_reg_array[i][2];
+			up_cim_reg->ireg_offset_range =
+						t5_up_cim_reg_array[i][3];
+		} else if (is_t6(padap->params.chip)) {
+			up_cim_reg->ireg_addr = t6_up_cim_reg_array[i][0];
+			up_cim_reg->ireg_data = t6_up_cim_reg_array[i][1];
+			up_cim_reg->ireg_local_offset =
+						t6_up_cim_reg_array[i][2];
+			up_cim_reg->ireg_offset_range =
+						t6_up_cim_reg_array[i][3];
+		}
+
+		rc = t4_cim_read(padap, up_cim_reg->ireg_local_offset,
+				 up_cim_reg->ireg_offset_range, buff);
+		if (rc) {
+			cudbg_put_buff(&temp_buff, dbg_buff);
+			return rc;
+		}
+		up_cim++;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_pbt_tables(struct cudbg_init *pdbg_init,
+			     struct cudbg_buffer *dbg_buff,
+			     struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct cudbg_pbt_tables *pbt;
+	int i, rc;
+	u32 addr;
+
+	rc = cudbg_get_buff(dbg_buff, sizeof(struct cudbg_pbt_tables),
+			    &temp_buff);
+	if (rc)
+		return rc;
+
+	pbt = (struct cudbg_pbt_tables *)temp_buff.data;
+	/* PBT dynamic entries */
+	addr = CUDBG_CHAC_PBT_ADDR;
+	for (i = 0; i < CUDBG_PBT_DYNAMIC_ENTRIES; i++) {
+		rc = t4_cim_read(padap, addr + (i * 4), 1,
+				 &pbt->pbt_dynamic[i]);
+		if (rc) {
+			cudbg_err->sys_err = rc;
+			cudbg_put_buff(&temp_buff, dbg_buff);
+			return rc;
+		}
+	}
+
+	/* PBT static entries */
+	/* static entries start when bit 6 is set */
+	addr = CUDBG_CHAC_PBT_ADDR + (1 << 6);
+	for (i = 0; i < CUDBG_PBT_STATIC_ENTRIES; i++) {
+		rc = t4_cim_read(padap, addr + (i * 4), 1,
+				 &pbt->pbt_static[i]);
+		if (rc) {
+			cudbg_err->sys_err = rc;
+			cudbg_put_buff(&temp_buff, dbg_buff);
+			return rc;
+		}
+	}
+
+	/* LRF entries */
+	addr = CUDBG_CHAC_PBT_LRF;
+	for (i = 0; i < CUDBG_LRF_ENTRIES; i++) {
+		rc = t4_cim_read(padap, addr + (i * 4), 1,
+				 &pbt->lrf_table[i]);
+		if (rc) {
+			cudbg_err->sys_err = rc;
+			cudbg_put_buff(&temp_buff, dbg_buff);
+			return rc;
+		}
+	}
+
+	/* PBT data entries */
+	addr = CUDBG_CHAC_PBT_DATA;
+	for (i = 0; i < CUDBG_PBT_DATA_ENTRIES; i++) {
+		rc = t4_cim_read(padap, addr + (i * 4), 1,
+				 &pbt->pbt_data[i]);
+		if (rc) {
+			cudbg_err->sys_err = rc;
+			cudbg_put_buff(&temp_buff, dbg_buff);
+			return rc;
+		}
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_mbox_log *mboxlog = NULL;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct mbox_cmd_log *log = NULL;
+	struct mbox_cmd *entry;
+	unsigned int entry_idx;
+	u16 mbox_cmds;
+	int i, k, rc;
+	u64 flit;
+	u32 size;
+
+	log = padap->mbox_log;
+	mbox_cmds = padap->mbox_log->size;
+	size = sizeof(struct cudbg_mbox_log) * mbox_cmds;
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	mboxlog = (struct cudbg_mbox_log *)temp_buff.data;
+	for (k = 0; k < mbox_cmds; k++) {
+		entry_idx = log->cursor + k;
+		if (entry_idx >= log->size)
+			entry_idx -= log->size;
+
+		entry = mbox_cmd_log_entry(log, entry_idx);
+		/* skip over unused entries */
+		if (entry->timestamp == 0)
+			continue;
+
+		memcpy(&mboxlog->entry, entry, sizeof(struct mbox_cmd));
+		for (i = 0; i < MBOX_LEN / 8; i++) {
+			flit = entry->cmd[i];
+			mboxlog->hi[i] = (u32)(flit >> 32);
+			mboxlog->lo[i] = (u32)flit;
+		}
+		mboxlog++;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
+
+int cudbg_collect_hma_indirect(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err)
+{
+	struct adapter *padap = pdbg_init->adap;
+	struct cudbg_buffer temp_buff = { 0 };
+	struct ireg_buf *hma_indr;
+	int i, rc, n;
+	u32 size;
+
+	if (CHELSIO_CHIP_VERSION(padap->params.chip) < CHELSIO_T6)
+		return CUDBG_STATUS_ENTITY_NOT_FOUND;
+
+	n = sizeof(t6_hma_ireg_array) / (IREG_NUM_ELEM * sizeof(u32));
+	size = sizeof(struct ireg_buf) * n;
+	rc = cudbg_get_buff(dbg_buff, size, &temp_buff);
+	if (rc)
+		return rc;
+
+	hma_indr = (struct ireg_buf *)temp_buff.data;
+	for (i = 0; i < n; i++) {
+		struct ireg_field *hma_fli = &hma_indr->tp_pio;
+		u32 *buff = hma_indr->outbuf;
+
+		hma_fli->ireg_addr = t6_hma_ireg_array[i][0];
+		hma_fli->ireg_data = t6_hma_ireg_array[i][1];
+		hma_fli->ireg_local_offset = t6_hma_ireg_array[i][2];
+		hma_fli->ireg_offset_range = t6_hma_ireg_array[i][3];
+		t4_read_indirect(padap, hma_fli->ireg_addr, hma_fli->ireg_data,
+				 buff, hma_fli->ireg_offset_range,
+				 hma_fli->ireg_local_offset);
+		hma_indr++;
+	}
+	cudbg_write_and_release_buff(&temp_buff, dbg_buff);
+	return rc;
+}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h
new file mode 100644
index 000000000000..230ba88a6a81
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h
@@ -0,0 +1,158 @@
+/*
+ *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms and conditions of the GNU General Public License,
+ *  version 2, as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope it will be useful, but WITHOUT
+ *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *  more details.
+ *
+ *  The full GNU General Public License is included in this distribution in
+ *  the file called "COPYING".
+ *
+ */
+
+#ifndef __CUDBG_LIB_H__
+#define __CUDBG_LIB_H__
+
+int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err);
+int cudbg_collect_fw_devlog(struct cudbg_init *pdbg_init,
+			    struct cudbg_buffer *dbg_buff,
+			    struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_la(struct cudbg_init *pdbg_init,
+			 struct cudbg_buffer *dbg_buff,
+			 struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_ma_la(struct cudbg_init *pdbg_init,
+			    struct cudbg_buffer *dbg_buff,
+			    struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_qcfg(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_ibq_tp0(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_ibq_tp1(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_ibq_ulp(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_ibq_sge0(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_ibq_sge1(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_ibq_ncsi(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_obq_ulp0(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_obq_ulp1(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_obq_ulp2(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_obq_ulp3(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_obq_sge(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_obq_ncsi(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err);
+int cudbg_collect_edc0_meminfo(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err);
+int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err);
+int cudbg_collect_rss(struct cudbg_init *pdbg_init,
+		      struct cudbg_buffer *dbg_buff,
+		      struct cudbg_error *cudbg_err);
+int cudbg_collect_rss_vf_config(struct cudbg_init *pdbg_init,
+				struct cudbg_buffer *dbg_buff,
+				struct cudbg_error *cudbg_err);
+int cudbg_collect_tp_indirect(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err);
+int cudbg_collect_path_mtu(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err);
+int cudbg_collect_pm_stats(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err);
+int cudbg_collect_hw_sched(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err);
+int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err);
+int cudbg_collect_ulprx_la(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err);
+int cudbg_collect_tp_la(struct cudbg_init *pdbg_init,
+			struct cudbg_buffer *dbg_buff,
+			struct cudbg_error *cudbg_err);
+int cudbg_collect_cim_pif_la(struct cudbg_init *pdbg_init,
+			     struct cudbg_buffer *dbg_buff,
+			     struct cudbg_error *cudbg_err);
+int cudbg_collect_clk_info(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err);
+int cudbg_collect_obq_sge_rx_q0(struct cudbg_init *pdbg_init,
+				struct cudbg_buffer *dbg_buff,
+				struct cudbg_error *cudbg_err);
+int cudbg_collect_obq_sge_rx_q1(struct cudbg_init *pdbg_init,
+				struct cudbg_buffer *dbg_buff,
+				struct cudbg_error *cudbg_err);
+int cudbg_collect_pcie_indirect(struct cudbg_init *pdbg_init,
+				struct cudbg_buffer *dbg_buff,
+				struct cudbg_error *cudbg_err);
+int cudbg_collect_pm_indirect(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err);
+int cudbg_collect_tid(struct cudbg_init *pdbg_init,
+		      struct cudbg_buffer *dbg_buff,
+		      struct cudbg_error *cudbg_err);
+int cudbg_collect_mps_tcam(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err);
+int cudbg_collect_vpd_data(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err);
+int cudbg_collect_cctrl(struct cudbg_init *pdbg_init,
+			struct cudbg_buffer *dbg_buff,
+			struct cudbg_error *cudbg_err);
+int cudbg_collect_ma_indirect(struct cudbg_init *pdbg_init,
+			      struct cudbg_buffer *dbg_buff,
+			      struct cudbg_error *cudbg_err);
+int cudbg_collect_ulptx_la(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err);
+int cudbg_collect_up_cim_indirect(struct cudbg_init *pdbg_init,
+				  struct cudbg_buffer *dbg_buff,
+				  struct cudbg_error *cudbg_err);
+int cudbg_collect_pbt_tables(struct cudbg_init *pdbg_init,
+			     struct cudbg_buffer *dbg_buff,
+			     struct cudbg_error *cudbg_err);
+int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init,
+			   struct cudbg_buffer *dbg_buff,
+			   struct cudbg_error *cudbg_err);
+int cudbg_collect_hma_indirect(struct cudbg_init *pdbg_init,
+			       struct cudbg_buffer *dbg_buff,
+			       struct cudbg_error *cudbg_err);
+
+struct cudbg_entity_hdr *cudbg_get_entity_hdr(void *outbuf, int i);
+void cudbg_align_debug_buffer(struct cudbg_buffer *dbg_buff,
+			      struct cudbg_entity_hdr *entity_hdr);
+u32 cudbg_cim_obq_size(struct adapter *padap, int qid);
+#endif /* __CUDBG_LIB_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h
new file mode 100644
index 000000000000..24b33f28e548
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h
@@ -0,0 +1,87 @@
+/*
+ *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms and conditions of the GNU General Public License,
+ *  version 2, as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope it will be useful, but WITHOUT
+ *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *  more details.
+ *
+ *  The full GNU General Public License is included in this distribution in
+ *  the file called "COPYING".
+ *
+ */
+
+#ifndef __CUDBG_LIB_COMMON_H__
+#define __CUDBG_LIB_COMMON_H__
+
+#define CUDBG_SIGNATURE 67856866 /* CUDB in ascii */
+
+enum cudbg_dump_type {
+	CUDBG_DUMP_TYPE_MINI = 1,
+};
+
+enum cudbg_compression_type {
+	CUDBG_COMPRESSION_NONE = 1,
+};
+
+struct cudbg_hdr {
+	u32 signature;
+	u32 hdr_len;
+	u16 major_ver;
+	u16 minor_ver;
+	u32 data_len;
+	u32 hdr_flags;
+	u16 max_entities;
+	u8 chip_ver;
+	u8 dump_type:3;
+	u8 reserved1:1;
+	u8 compress_type:4;
+	u32 reserved[8];
+};
+
+struct cudbg_entity_hdr {
+	u32 entity_type;
+	u32 start_offset;
+	u32 size;
+	int hdr_flags;
+	u32 sys_warn;
+	u32 sys_err;
+	u8 num_pad;
+	u8 flag;             /* bit 0 is used to indicate ext data */
+	u8 reserved1[2];
+	u32 next_ext_offset; /* pointer to next extended entity meta data */
+	u32 reserved[5];
+};
+
+struct cudbg_ver_hdr {
+	u32 signature;
+	u16 revision;
+	u16 size;
+};
+
+struct cudbg_buffer {
+	u32 size;
+	u32 offset;
+	char *data;
+};
+
+struct cudbg_error {
+	int sys_err;
+	int sys_warn;
+	int app_err;
+};
+
+#define CDUMP_MAX_COMP_BUF_SIZE ((64 * 1024) - 1)
+#define CUDBG_CHUNK_SIZE ((CDUMP_MAX_COMP_BUF_SIZE / 1024) * 1024)
+
+int cudbg_get_buff(struct cudbg_buffer *pdbg_buff, u32 size,
+		   struct cudbg_buffer *pin_buff);
+void cudbg_put_buff(struct cudbg_buffer *pin_buff,
+		    struct cudbg_buffer *pdbg_buff);
+void cudbg_update_buff(struct cudbg_buffer *pin_buff,
+		       struct cudbg_buffer *pout_buff);
+#endif /* __CUDBG_LIB_COMMON_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index ea72d2d2e1b4..0c83ceb5a1a6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -287,10 +287,18 @@ struct tp_params {
 	 * places we store their offsets here, or a -1 if the field isn't
 	 * present.
 	 */
-	int vlan_shift;
-	int vnic_shift;
+	int fcoe_shift;
 	int port_shift;
+	int vnic_shift;
+	int vlan_shift;
+	int tos_shift;
 	int protocol_shift;
+	int ethertype_shift;
+	int macmatch_shift;
+	int matchtype_shift;
+	int frag_shift;
+
+	u64 hash_filter_mask;
 };
 
 struct vpd_params {
@@ -358,6 +366,7 @@ struct adapter_params {
 	unsigned char crypto;		/* HW capability for crypto */
 
 	unsigned char bypass;
+	unsigned char hash_filter;
 
 	unsigned int ofldq_wr_cred;
 	bool ulptx_memwrite_dsgl;          /* use of T5 DSGL allowed */
@@ -367,6 +376,7 @@ struct adapter_params {
 	unsigned int max_ird_adapter;     /* Max read depth per adapter */
 	bool fr_nsmr_tpte_wr_support;	  /* FW support for FR_NSMR_TPTE_WR */
 	u8 fw_caps_support;		/* 32-bit Port Capabilities */
+	bool filter2_wr_support;	/* FW support for FILTER2_WR */
 
 	/* MPS Buffer Group Map[per Port].  Bit i is set if buffer group i is
 	 * used by the Port
@@ -549,6 +559,7 @@ enum {                                 /* adapter flags */
 	MASTER_PF          = (1 << 7),
 	FW_OFLD_CONN       = (1 << 9),
 	ROOT_NO_RELAXED_ORDERING = (1 << 10),
+	SHUTTING_DOWN	   = (1 << 11),
 };
 
 enum {
@@ -857,6 +868,7 @@ struct adapter {
 	unsigned int clipt_start;
 	unsigned int clipt_end;
 	struct clip_tbl *clipt;
+	struct smt_data *smt;
 	struct cxgb4_uld_info *uld;
 	void *uld_handle[CXGB4_ULD_MAX];
 	unsigned int num_uld;
@@ -904,6 +916,15 @@ struct adapter {
 	/* TC u32 offload */
 	struct cxgb4_tc_u32_table *tc_u32;
 	struct chcr_stats_debug chcr_stats;
+
+	/* TC flower offload */
+	struct rhashtable flower_tbl;
+	struct rhashtable_params flower_ht_params;
+	struct timer_list flower_stats_timer;
+	struct work_struct flower_stats_work;
+
+	/* Ethtool Dump */
+	struct ethtool_dump eth_dump;
 };
 
 /* Support for "sched-class" command to allow a TX Scheduling Class to be
@@ -1031,6 +1052,7 @@ struct ch_filter_specification {
 	 * matching that doesn't exist as a (value, mask) tuple.
 	 */
 	uint32_t type:1;        /* 0 => IPv4, 1 => IPv6 */
+	u32 hash:1;		/* 0 => wild-card, 1 => exact-match */
 
 	/* Packet dispatch information.  Ingress packets which match the
 	 * filter rules will be dropped, passed to the host or switched back
@@ -1055,10 +1077,19 @@ struct ch_filter_specification {
 	uint32_t newdmac:1;     /* rewrite destination MAC address */
 	uint32_t newsmac:1;     /* rewrite source MAC address */
 	uint32_t newvlan:2;     /* rewrite VLAN Tag */
+	uint32_t nat_mode:3;    /* specify NAT operation mode */
 	uint8_t dmac[ETH_ALEN]; /* new destination MAC address */
 	uint8_t smac[ETH_ALEN]; /* new source MAC address */
 	uint16_t vlan;          /* VLAN Tag to insert */
 
+	u8 nat_lip[16];		/* local IP to use after NAT'ing */
+	u8 nat_fip[16];		/* foreign IP to use after NAT'ing */
+	u16 nat_lport;		/* local port to use after NAT'ing */
+	u16 nat_fport;		/* foreign port to use after NAT'ing */
+
+	/* reservation for future additions */
+	u8 rsvd[24];
+
 	/* Filter rule value/mask pairs.
 	 */
 	struct ch_filter_tuple val;
@@ -1078,6 +1109,17 @@ enum {
 	VLAN_REWRITE
 };
 
+enum {
+	NAT_MODE_NONE = 0,	/* No NAT performed */
+	NAT_MODE_DIP,		/* NAT on Dst IP */
+	NAT_MODE_DIP_DP,	/* NAT on Dst IP, Dst Port */
+	NAT_MODE_DIP_DP_SIP,	/* NAT on Dst IP, Dst Port and Src IP */
+	NAT_MODE_DIP_DP_SP,	/* NAT on Dst IP, Dst Port and Src Port */
+	NAT_MODE_SIP_SP,	/* NAT on Src IP and Src Port */
+	NAT_MODE_DIP_SIP_SP,	/* NAT on Dst IP, Src IP and Src Port */
+	NAT_MODE_ALL		/* NAT on entire 4-tuple */
+};
+
 /* Host shadow copy of ingress filter entry.  This is in host native format
  * and doesn't match the ordering or bit order, etc. of the hardware of the
  * firmware command.  The use of bit-field structure elements is purely to
@@ -1090,9 +1132,9 @@ struct filter_entry {
 	u32 locked:1;           /* filter is administratively locked */
 
 	u32 pending:1;          /* filter action is pending firmware reply */
-	u32 smtidx:8;           /* Source MAC Table index for smac */
 	struct filter_ctx *ctx; /* Caller's completion hook */
 	struct l2t_entry *l2t;  /* Layer Two Table entry for dmac */
+	struct smt_entry *smt;  /* Source Mac Table entry for smac */
 	struct net_device *dev; /* Associated net device */
 	u32 tid;                /* This will store the actual tid */
 
@@ -1109,6 +1151,11 @@ static inline int is_offload(const struct adapter *adap)
 	return adap->params.offload;
 }
 
+static inline int is_hashfilter(const struct adapter *adap)
+{
+	return adap->params.hash_filter;
+}
+
 static inline int is_pci_uld(const struct adapter *adap)
 {
 	return adap->params.crypto;
@@ -1312,6 +1359,12 @@ static inline unsigned int core_ticks_to_us(const struct adapter *adapter,
 		adapter->params.vpd.cclk);
 }
 
+static inline unsigned int dack_ticks_to_usec(const struct adapter *adap,
+					      unsigned int ticks)
+{
+	return (ticks << adap->params.tp.dack_re) / core_ticks_per_usec(adap);
+}
+
 void t4_set_reg_field(struct adapter *adap, unsigned int addr, u32 mask,
 		      u32 val);
 
@@ -1451,7 +1504,7 @@ unsigned int qtimer_val(const struct adapter *adap,
 
 int t4_init_devlog_params(struct adapter *adapter);
 int t4_init_sge_params(struct adapter *adapter);
-int t4_init_tp_params(struct adapter *adap);
+int t4_init_tp_params(struct adapter *adap, bool sleep_ok);
 int t4_filter_field_shift(const struct adapter *adap, int filter_sel);
 int t4_init_rss_mode(struct adapter *adap, int mbox);
 int t4_init_portinfo(struct port_info *pi, int mbox,
@@ -1465,14 +1518,15 @@ int t4_config_glbl_rss(struct adapter *adapter, int mbox, unsigned int mode,
 int t4_config_vi_rss(struct adapter *adapter, int mbox, unsigned int viid,
 		     unsigned int flags, unsigned int defq);
 int t4_read_rss(struct adapter *adapter, u16 *entries);
-void t4_read_rss_key(struct adapter *adapter, u32 *key);
-void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx);
+void t4_read_rss_key(struct adapter *adapter, u32 *key, bool sleep_ok);
+void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx,
+		      bool sleep_ok);
 void t4_read_rss_pf_config(struct adapter *adapter, unsigned int index,
-			   u32 *valp);
+			   u32 *valp, bool sleep_ok);
 void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index,
-			   u32 *vfl, u32 *vfh);
-u32 t4_read_rss_pf_map(struct adapter *adapter);
-u32 t4_read_rss_pf_mask(struct adapter *adapter);
+			   u32 *vfl, u32 *vfh, bool sleep_ok);
+u32 t4_read_rss_pf_map(struct adapter *adapter, bool sleep_ok);
+u32 t4_read_rss_pf_mask(struct adapter *adapter, bool sleep_ok);
 
 unsigned int t4_get_mps_bg_map(struct adapter *adapter, int pidx);
 unsigned int t4_get_tp_ch_map(struct adapter *adapter, int pidx);
@@ -1503,14 +1557,18 @@ void t4_read_cong_tbl(struct adapter *adap, u16 incr[NMTUS][NCCTRL_WIN]);
 void t4_tp_wr_bits_indirect(struct adapter *adap, unsigned int addr,
 			    unsigned int mask, unsigned int val);
 void t4_tp_read_la(struct adapter *adap, u64 *la_buf, unsigned int *wrptr);
-void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st);
-void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st);
-void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st);
-void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st);
+void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st,
+			 bool sleep_ok);
+void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st,
+			 bool sleep_ok);
+void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st,
+			  bool sleep_ok);
+void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st,
+		      bool sleep_ok);
 void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4,
-			 struct tp_tcp_stats *v6);
+			 struct tp_tcp_stats *v6, bool sleep_ok);
 void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx,
-		       struct tp_fcoe_stats *st);
+		       struct tp_fcoe_stats *st, bool sleep_ok);
 void t4_load_mtus(struct adapter *adap, const unsigned short *mtus,
 		  const unsigned short *alpha, const unsigned short *beta);
 
@@ -1608,6 +1666,9 @@ void t4_get_trace_filter(struct adapter *adapter, struct trace_params *tp,
 			 int filter_index, int *enabled);
 int t4_fwaddrspace_write(struct adapter *adap, unsigned int mbox,
 			 u32 addr, u32 val);
+void t4_read_pace_tbl(struct adapter *adap, unsigned int pace_vals[NTX_SCHED]);
+void t4_get_tx_sched(struct adapter *adap, unsigned int sched,
+		     unsigned int *kbps, unsigned int *ipg, bool sleep_ok);
 int t4_sched_params(struct adapter *adapter, int type, int level, int mode,
 		    int rateunit, int ratemode, int channel, int class,
 		    int minrate, int maxrate, int weight, int pktsize);
@@ -1619,6 +1680,13 @@ void t4_idma_monitor(struct adapter *adapter,
 		     int hz, int ticks);
 int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf,
 		      unsigned int naddr, u8 *addr);
+void t4_tp_pio_read(struct adapter *adap, u32 *buff, u32 nregs,
+		    u32 start_index, bool sleep_ok);
+void t4_tp_tm_pio_read(struct adapter *adap, u32 *buff, u32 nregs,
+		       u32 start_index, bool sleep_ok);
+void t4_tp_mib_read(struct adapter *adap, u32 *buff, u32 nregs,
+		    u32 start_index, bool sleep_ok);
+
 void t4_uld_mem_free(struct adapter *adap);
 int t4_uld_mem_alloc(struct adapter *adap);
 void t4_uld_clean_up(struct adapter *adap);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
new file mode 100644
index 000000000000..7373617da635
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
@@ -0,0 +1,392 @@
+/*
+ *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms and conditions of the GNU General Public License,
+ *  version 2, as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope it will be useful, but WITHOUT
+ *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *  more details.
+ *
+ *  The full GNU General Public License is included in this distribution in
+ *  the file called "COPYING".
+ *
+ */
+
+#include "t4_regs.h"
+#include "cxgb4.h"
+#include "cxgb4_cudbg.h"
+#include "cudbg_entity.h"
+
+static const struct cxgb4_collect_entity cxgb4_collect_mem_dump[] = {
+	{ CUDBG_EDC0, cudbg_collect_edc0_meminfo },
+	{ CUDBG_EDC1, cudbg_collect_edc1_meminfo },
+};
+
+static const struct cxgb4_collect_entity cxgb4_collect_hw_dump[] = {
+	{ CUDBG_MBOX_LOG, cudbg_collect_mbox_log },
+	{ CUDBG_DEV_LOG, cudbg_collect_fw_devlog },
+	{ CUDBG_REG_DUMP, cudbg_collect_reg_dump },
+	{ CUDBG_CIM_LA, cudbg_collect_cim_la },
+	{ CUDBG_CIM_MA_LA, cudbg_collect_cim_ma_la },
+	{ CUDBG_CIM_QCFG, cudbg_collect_cim_qcfg },
+	{ CUDBG_CIM_IBQ_TP0, cudbg_collect_cim_ibq_tp0 },
+	{ CUDBG_CIM_IBQ_TP1, cudbg_collect_cim_ibq_tp1 },
+	{ CUDBG_CIM_IBQ_ULP, cudbg_collect_cim_ibq_ulp },
+	{ CUDBG_CIM_IBQ_SGE0, cudbg_collect_cim_ibq_sge0 },
+	{ CUDBG_CIM_IBQ_SGE1, cudbg_collect_cim_ibq_sge1 },
+	{ CUDBG_CIM_IBQ_NCSI, cudbg_collect_cim_ibq_ncsi },
+	{ CUDBG_CIM_OBQ_ULP0, cudbg_collect_cim_obq_ulp0 },
+	{ CUDBG_CIM_OBQ_ULP1, cudbg_collect_cim_obq_ulp1 },
+	{ CUDBG_CIM_OBQ_ULP2, cudbg_collect_cim_obq_ulp2 },
+	{ CUDBG_CIM_OBQ_ULP3, cudbg_collect_cim_obq_ulp3 },
+	{ CUDBG_CIM_OBQ_SGE, cudbg_collect_cim_obq_sge },
+	{ CUDBG_CIM_OBQ_NCSI, cudbg_collect_cim_obq_ncsi },
+	{ CUDBG_RSS, cudbg_collect_rss },
+	{ CUDBG_RSS_VF_CONF, cudbg_collect_rss_vf_config },
+	{ CUDBG_PATH_MTU, cudbg_collect_path_mtu },
+	{ CUDBG_PM_STATS, cudbg_collect_pm_stats },
+	{ CUDBG_HW_SCHED, cudbg_collect_hw_sched },
+	{ CUDBG_TP_INDIRECT, cudbg_collect_tp_indirect },
+	{ CUDBG_SGE_INDIRECT, cudbg_collect_sge_indirect },
+	{ CUDBG_ULPRX_LA, cudbg_collect_ulprx_la },
+	{ CUDBG_TP_LA, cudbg_collect_tp_la },
+	{ CUDBG_CIM_PIF_LA, cudbg_collect_cim_pif_la },
+	{ CUDBG_CLK, cudbg_collect_clk_info },
+	{ CUDBG_CIM_OBQ_RXQ0, cudbg_collect_obq_sge_rx_q0 },
+	{ CUDBG_CIM_OBQ_RXQ1, cudbg_collect_obq_sge_rx_q1 },
+	{ CUDBG_PCIE_INDIRECT, cudbg_collect_pcie_indirect },
+	{ CUDBG_PM_INDIRECT, cudbg_collect_pm_indirect },
+	{ CUDBG_TID_INFO, cudbg_collect_tid },
+	{ CUDBG_MPS_TCAM, cudbg_collect_mps_tcam },
+	{ CUDBG_VPD_DATA, cudbg_collect_vpd_data },
+	{ CUDBG_CCTRL, cudbg_collect_cctrl },
+	{ CUDBG_MA_INDIRECT, cudbg_collect_ma_indirect },
+	{ CUDBG_ULPTX_LA, cudbg_collect_ulptx_la },
+	{ CUDBG_UP_CIM_INDIRECT, cudbg_collect_up_cim_indirect },
+	{ CUDBG_PBT_TABLE, cudbg_collect_pbt_tables },
+	{ CUDBG_HMA_INDIRECT, cudbg_collect_hma_indirect },
+};
+
+static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity)
+{
+	u32 value, n = 0, len = 0;
+
+	switch (entity) {
+	case CUDBG_REG_DUMP:
+		switch (CHELSIO_CHIP_VERSION(adap->params.chip)) {
+		case CHELSIO_T4:
+			len = T4_REGMAP_SIZE;
+			break;
+		case CHELSIO_T5:
+		case CHELSIO_T6:
+			len = T5_REGMAP_SIZE;
+			break;
+		default:
+			break;
+		}
+		break;
+	case CUDBG_DEV_LOG:
+		len = adap->params.devlog.size;
+		break;
+	case CUDBG_CIM_LA:
+		if (is_t6(adap->params.chip)) {
+			len = adap->params.cim_la_size / 10 + 1;
+			len *= 11 * sizeof(u32);
+		} else {
+			len = adap->params.cim_la_size / 8;
+			len *= 8 * sizeof(u32);
+		}
+		len += sizeof(u32); /* for reading CIM LA configuration */
+		break;
+	case CUDBG_CIM_MA_LA:
+		len = 2 * CIM_MALA_SIZE * 5 * sizeof(u32);
+		break;
+	case CUDBG_CIM_QCFG:
+		len = sizeof(struct cudbg_cim_qcfg);
+		break;
+	case CUDBG_CIM_IBQ_TP0:
+	case CUDBG_CIM_IBQ_TP1:
+	case CUDBG_CIM_IBQ_ULP:
+	case CUDBG_CIM_IBQ_SGE0:
+	case CUDBG_CIM_IBQ_SGE1:
+	case CUDBG_CIM_IBQ_NCSI:
+		len = CIM_IBQ_SIZE * 4 * sizeof(u32);
+		break;
+	case CUDBG_CIM_OBQ_ULP0:
+		len = cudbg_cim_obq_size(adap, 0);
+		break;
+	case CUDBG_CIM_OBQ_ULP1:
+		len = cudbg_cim_obq_size(adap, 1);
+		break;
+	case CUDBG_CIM_OBQ_ULP2:
+		len = cudbg_cim_obq_size(adap, 2);
+		break;
+	case CUDBG_CIM_OBQ_ULP3:
+		len = cudbg_cim_obq_size(adap, 3);
+		break;
+	case CUDBG_CIM_OBQ_SGE:
+		len = cudbg_cim_obq_size(adap, 4);
+		break;
+	case CUDBG_CIM_OBQ_NCSI:
+		len = cudbg_cim_obq_size(adap, 5);
+		break;
+	case CUDBG_CIM_OBQ_RXQ0:
+		len = cudbg_cim_obq_size(adap, 6);
+		break;
+	case CUDBG_CIM_OBQ_RXQ1:
+		len = cudbg_cim_obq_size(adap, 7);
+		break;
+	case CUDBG_EDC0:
+		value = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A);
+		if (value & EDRAM0_ENABLE_F) {
+			value = t4_read_reg(adap, MA_EDRAM0_BAR_A);
+			len = EDRAM0_SIZE_G(value);
+		}
+		len = cudbg_mbytes_to_bytes(len);
+		break;
+	case CUDBG_EDC1:
+		value = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A);
+		if (value & EDRAM1_ENABLE_F) {
+			value = t4_read_reg(adap, MA_EDRAM1_BAR_A);
+			len = EDRAM1_SIZE_G(value);
+		}
+		len = cudbg_mbytes_to_bytes(len);
+		break;
+	case CUDBG_RSS:
+		len = RSS_NENTRIES * sizeof(u16);
+		break;
+	case CUDBG_RSS_VF_CONF:
+		len = adap->params.arch.vfcount *
+		      sizeof(struct cudbg_rss_vf_conf);
+		break;
+	case CUDBG_PATH_MTU:
+		len = NMTUS * sizeof(u16);
+		break;
+	case CUDBG_PM_STATS:
+		len = sizeof(struct cudbg_pm_stats);
+		break;
+	case CUDBG_HW_SCHED:
+		len = sizeof(struct cudbg_hw_sched);
+		break;
+	case CUDBG_TP_INDIRECT:
+		switch (CHELSIO_CHIP_VERSION(adap->params.chip)) {
+		case CHELSIO_T5:
+			n = sizeof(t5_tp_pio_array) +
+			    sizeof(t5_tp_tm_pio_array) +
+			    sizeof(t5_tp_mib_index_array);
+			break;
+		case CHELSIO_T6:
+			n = sizeof(t6_tp_pio_array) +
+			    sizeof(t6_tp_tm_pio_array) +
+			    sizeof(t6_tp_mib_index_array);
+			break;
+		default:
+			break;
+		}
+		n = n / (IREG_NUM_ELEM * sizeof(u32));
+		len = sizeof(struct ireg_buf) * n;
+		break;
+	case CUDBG_SGE_INDIRECT:
+		len = sizeof(struct ireg_buf) * 2;
+		break;
+	case CUDBG_ULPRX_LA:
+		len = sizeof(struct cudbg_ulprx_la);
+		break;
+	case CUDBG_TP_LA:
+		len = sizeof(struct cudbg_tp_la) + TPLA_SIZE * sizeof(u64);
+		break;
+	case CUDBG_CIM_PIF_LA:
+		len = sizeof(struct cudbg_cim_pif_la);
+		len += 2 * CIM_PIFLA_SIZE * 6 * sizeof(u32);
+		break;
+	case CUDBG_CLK:
+		len = sizeof(struct cudbg_clk_info);
+		break;
+	case CUDBG_PCIE_INDIRECT:
+		n = sizeof(t5_pcie_pdbg_array) / (IREG_NUM_ELEM * sizeof(u32));
+		len = sizeof(struct ireg_buf) * n * 2;
+		break;
+	case CUDBG_PM_INDIRECT:
+		n = sizeof(t5_pm_rx_array) / (IREG_NUM_ELEM * sizeof(u32));
+		len = sizeof(struct ireg_buf) * n * 2;
+		break;
+	case CUDBG_TID_INFO:
+		len = sizeof(struct cudbg_tid_info_region_rev1);
+		break;
+	case CUDBG_MPS_TCAM:
+		len = sizeof(struct cudbg_mps_tcam) *
+		      adap->params.arch.mps_tcam_size;
+		break;
+	case CUDBG_VPD_DATA:
+		len = sizeof(struct cudbg_vpd_data);
+		break;
+	case CUDBG_CCTRL:
+		len = sizeof(u16) * NMTUS * NCCTRL_WIN;
+		break;
+	case CUDBG_MA_INDIRECT:
+		if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) {
+			n = sizeof(t6_ma_ireg_array) /
+			    (IREG_NUM_ELEM * sizeof(u32));
+			len = sizeof(struct ireg_buf) * n * 2;
+		}
+		break;
+	case CUDBG_ULPTX_LA:
+		len = sizeof(struct cudbg_ulptx_la);
+		break;
+	case CUDBG_UP_CIM_INDIRECT:
+		n = sizeof(t5_up_cim_reg_array) / (IREG_NUM_ELEM * sizeof(u32));
+		len = sizeof(struct ireg_buf) * n;
+		break;
+	case CUDBG_PBT_TABLE:
+		len = sizeof(struct cudbg_pbt_tables);
+		break;
+	case CUDBG_MBOX_LOG:
+		len = sizeof(struct cudbg_mbox_log) * adap->mbox_log->size;
+		break;
+	case CUDBG_HMA_INDIRECT:
+		if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) {
+			n = sizeof(t6_hma_ireg_array) /
+			    (IREG_NUM_ELEM * sizeof(u32));
+			len = sizeof(struct ireg_buf) * n;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return len;
+}
+
+u32 cxgb4_get_dump_length(struct adapter *adap, u32 flag)
+{
+	u32 i, entity;
+	u32 len = 0;
+
+	if (flag & CXGB4_ETH_DUMP_HW) {
+		for (i = 0; i < ARRAY_SIZE(cxgb4_collect_hw_dump); i++) {
+			entity = cxgb4_collect_hw_dump[i].entity;
+			len += cxgb4_get_entity_length(adap, entity);
+		}
+	}
+
+	if (flag & CXGB4_ETH_DUMP_MEM) {
+		for (i = 0; i < ARRAY_SIZE(cxgb4_collect_mem_dump); i++) {
+			entity = cxgb4_collect_mem_dump[i].entity;
+			len += cxgb4_get_entity_length(adap, entity);
+		}
+	}
+
+	return len;
+}
+
+static void cxgb4_cudbg_collect_entity(struct cudbg_init *pdbg_init,
+				       struct cudbg_buffer *dbg_buff,
+				       const struct cxgb4_collect_entity *e_arr,
+				       u32 arr_size, void *buf, u32 *tot_size)
+{
+	struct adapter *adap = pdbg_init->adap;
+	struct cudbg_error cudbg_err = { 0 };
+	struct cudbg_entity_hdr *entity_hdr;
+	u32 entity_size, i;
+	u32 total_size = 0;
+	int ret;
+
+	for (i = 0; i < arr_size; i++) {
+		const struct cxgb4_collect_entity *e = &e_arr[i];
+
+		/* Skip entities that won't fit in output buffer */
+		entity_size = cxgb4_get_entity_length(adap, e->entity);
+		if (entity_size >
+		    pdbg_init->outbuf_size - *tot_size - total_size)
+			continue;
+
+		entity_hdr = cudbg_get_entity_hdr(buf, e->entity);
+		entity_hdr->entity_type = e->entity;
+		entity_hdr->start_offset = dbg_buff->offset;
+		memset(&cudbg_err, 0, sizeof(struct cudbg_error));
+		ret = e->collect_cb(pdbg_init, dbg_buff, &cudbg_err);
+		if (ret) {
+			entity_hdr->size = 0;
+			dbg_buff->offset = entity_hdr->start_offset;
+		} else {
+			cudbg_align_debug_buffer(dbg_buff, entity_hdr);
+		}
+
+		/* Log error and continue with next entity */
+		if (cudbg_err.sys_err)
+			ret = CUDBG_SYSTEM_ERROR;
+
+		entity_hdr->hdr_flags = ret;
+		entity_hdr->sys_err = cudbg_err.sys_err;
+		entity_hdr->sys_warn = cudbg_err.sys_warn;
+		total_size += entity_hdr->size;
+	}
+
+	*tot_size += total_size;
+}
+
+int cxgb4_cudbg_collect(struct adapter *adap, void *buf, u32 *buf_size,
+			u32 flag)
+{
+	struct cudbg_init cudbg_init = { 0 };
+	struct cudbg_buffer dbg_buff = { 0 };
+	u32 size, min_size, total_size = 0;
+	struct cudbg_hdr *cudbg_hdr;
+
+	size = *buf_size;
+
+	cudbg_init.adap = adap;
+	cudbg_init.outbuf = buf;
+	cudbg_init.outbuf_size = size;
+
+	dbg_buff.data = buf;
+	dbg_buff.size = size;
+	dbg_buff.offset = 0;
+
+	cudbg_hdr = (struct cudbg_hdr *)buf;
+	cudbg_hdr->signature = CUDBG_SIGNATURE;
+	cudbg_hdr->hdr_len = sizeof(struct cudbg_hdr);
+	cudbg_hdr->major_ver = CUDBG_MAJOR_VERSION;
+	cudbg_hdr->minor_ver = CUDBG_MINOR_VERSION;
+	cudbg_hdr->max_entities = CUDBG_MAX_ENTITY;
+	cudbg_hdr->chip_ver = adap->params.chip;
+	cudbg_hdr->dump_type = CUDBG_DUMP_TYPE_MINI;
+	cudbg_hdr->compress_type = CUDBG_COMPRESSION_NONE;
+
+	min_size = sizeof(struct cudbg_hdr) +
+		   sizeof(struct cudbg_entity_hdr) *
+		   cudbg_hdr->max_entities;
+	if (size < min_size)
+		return -ENOMEM;
+
+	dbg_buff.offset += min_size;
+	total_size = dbg_buff.offset;
+
+	if (flag & CXGB4_ETH_DUMP_HW)
+		cxgb4_cudbg_collect_entity(&cudbg_init, &dbg_buff,
+					   cxgb4_collect_hw_dump,
+					   ARRAY_SIZE(cxgb4_collect_hw_dump),
+					   buf,
+					   &total_size);
+
+	if (flag & CXGB4_ETH_DUMP_MEM)
+		cxgb4_cudbg_collect_entity(&cudbg_init, &dbg_buff,
+					   cxgb4_collect_mem_dump,
+					   ARRAY_SIZE(cxgb4_collect_mem_dump),
+					   buf,
+					   &total_size);
+
+	cudbg_hdr->data_len = total_size;
+	*buf_size = total_size;
+	return 0;
+}
+
+void cxgb4_init_ethtool_dump(struct adapter *adapter)
+{
+	adapter->eth_dump.flag = CXGB4_ETH_DUMP_NONE;
+	adapter->eth_dump.version = adapter->params.fw_vers;
+	adapter->eth_dump.len = 0;
+}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h
new file mode 100644
index 000000000000..c099b5aa2214
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h
@@ -0,0 +1,44 @@
+/*
+ *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms and conditions of the GNU General Public License,
+ *  version 2, as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope it will be useful, but WITHOUT
+ *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *  more details.
+ *
+ *  The full GNU General Public License is included in this distribution in
+ *  the file called "COPYING".
+ *
+ */
+
+#ifndef __CXGB4_CUDBG_H__
+#define __CXGB4_CUDBG_H__
+
+#include "cudbg_if.h"
+#include "cudbg_lib_common.h"
+#include "cudbg_lib.h"
+
+typedef int (*cudbg_collect_callback_t)(struct cudbg_init *pdbg_init,
+					struct cudbg_buffer *dbg_buff,
+					struct cudbg_error *cudbg_err);
+
+struct cxgb4_collect_entity {
+	enum cudbg_dbg_entity_type entity;
+	cudbg_collect_callback_t collect_cb;
+};
+
+enum CXGB4_ETHTOOL_DUMP_FLAGS {
+	CXGB4_ETH_DUMP_NONE = ETH_FW_DUMP_DISABLE,
+	CXGB4_ETH_DUMP_MEM = (1 << 0), /* On-Chip Memory Dumps */
+	CXGB4_ETH_DUMP_HW = (1 << 1), /* various FW and HW dumps */
+};
+
+u32 cxgb4_get_dump_length(struct adapter *adap, u32 flag);
+int cxgb4_cudbg_collect(struct adapter *adap, void *buf, u32 *buf_size,
+			u32 flag);
+void cxgb4_init_ethtool_dump(struct adapter *adapter);
+#endif /* __CXGB4_CUDBG_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
index 6ee2ed30626b..4e7f72b17e82 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
@@ -40,8 +40,7 @@ static inline bool cxgb4_dcb_state_synced(enum cxgb4_dcb_state state)
 		return false;
 }
 
-/* Initialize a port's Data Center Bridging state.  Typically used after a
- * Link Down event.
+/* Initialize a port's Data Center Bridging state.
  */
 void cxgb4_dcb_state_init(struct net_device *dev)
 {
@@ -106,6 +105,15 @@ static void cxgb4_dcb_cleanup_apps(struct net_device *dev)
 	}
 }
 
+/* Reset a port's Data Center Bridging state.  Typically used after a
+ * Link Down event.
+ */
+void cxgb4_dcb_reset(struct net_device *dev)
+{
+	cxgb4_dcb_cleanup_apps(dev);
+	cxgb4_dcb_state_init(dev);
+}
+
 /* Finite State machine for Data Center Bridging.
  */
 void cxgb4_dcb_state_fsm(struct net_device *dev,
@@ -194,8 +202,7 @@ void cxgb4_dcb_state_fsm(struct net_device *dev,
 			 * state.  We need to reset back to a ground state
 			 * of incomplete.
 			 */
-			cxgb4_dcb_cleanup_apps(dev);
-			cxgb4_dcb_state_init(dev);
+			cxgb4_dcb_reset(dev);
 			dcb->state = CXGB4_DCB_STATE_FW_INCOMPLETE;
 			dcb->supported = CXGB4_DCBX_FW_SUPPORT;
 			linkwatch_fire_event(dev);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
index ccf24d3dc982..02040b99c78a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
@@ -131,6 +131,7 @@ struct port_dcb_info {
 
 void cxgb4_dcb_state_init(struct net_device *);
 void cxgb4_dcb_version_init(struct net_device *);
+void cxgb4_dcb_reset(struct net_device *dev);
 void cxgb4_dcb_state_fsm(struct net_device *, enum cxgb4_dcb_state_input);
 void cxgb4_dcb_handle_fw_update(struct adapter *, const struct fw_port_cmd *);
 void cxgb4_dcb_set_caps(struct adapter *, const struct fw_port_cmd *);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 76540b0e082d..917663b35603 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2211,7 +2211,7 @@ static int rss_key_show(struct seq_file *seq, void *v)
 {
 	u32 key[10];
 
-	t4_read_rss_key(seq->private, key);
+	t4_read_rss_key(seq->private, key, true);
 	seq_printf(seq, "%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x\n",
 		   key[9], key[8], key[7], key[6], key[5], key[4], key[3],
 		   key[2], key[1], key[0]);
@@ -2248,7 +2248,7 @@ static ssize_t rss_key_write(struct file *file, const char __user *buf,
 		}
 	}
 
-	t4_write_rss_key(adap, key, -1);
+	t4_write_rss_key(adap, key, -1, true);
 	return count;
 }
 
@@ -2325,12 +2325,13 @@ static int rss_pf_config_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 
 	pfconf = (struct rss_pf_conf *)p->data;
-	rss_pf_map = t4_read_rss_pf_map(adapter);
-	rss_pf_mask = t4_read_rss_pf_mask(adapter);
+	rss_pf_map = t4_read_rss_pf_map(adapter, true);
+	rss_pf_mask = t4_read_rss_pf_mask(adapter, true);
 	for (pf = 0; pf < 8; pf++) {
 		pfconf[pf].rss_pf_map = rss_pf_map;
 		pfconf[pf].rss_pf_mask = rss_pf_mask;
-		t4_read_rss_pf_config(adapter, pf, &pfconf[pf].rss_pf_config);
+		t4_read_rss_pf_config(adapter, pf, &pfconf[pf].rss_pf_config,
+				      true);
 	}
 	return 0;
 }
@@ -2393,7 +2394,7 @@ static int rss_vf_config_open(struct inode *inode, struct file *file)
 	vfconf = (struct rss_vf_conf *)p->data;
 	for (vf = 0; vf < vfcount; vf++) {
 		t4_read_rss_vf_config(adapter, vf, &vfconf[vf].rss_vf_vfl,
-				      &vfconf[vf].rss_vf_vfh);
+				      &vfconf[vf].rss_vf_vfh, true);
 	}
 	return 0;
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index a71af1e587e2..1b7f6b9ccc8b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -21,6 +21,7 @@
 #include "cxgb4.h"
 #include "t4_regs.h"
 #include "t4fw_api.h"
+#include "cxgb4_cudbg.h"
 
 #define EEPROM_MAGIC 0x38E2F10C
 
@@ -335,10 +336,10 @@ static void collect_adapter_stats(struct adapter *adap, struct adapter_stats *s)
 	memset(s, 0, sizeof(*s));
 
 	spin_lock(&adap->stats_lock);
-	t4_tp_get_tcp_stats(adap, &v4, &v6);
-	t4_tp_get_rdma_stats(adap, &rdma_stats);
-	t4_get_usm_stats(adap, &usm_stats);
-	t4_tp_get_err_stats(adap, &err_stats);
+	t4_tp_get_tcp_stats(adap, &v4, &v6, false);
+	t4_tp_get_rdma_stats(adap, &rdma_stats, false);
+	t4_get_usm_stats(adap, &usm_stats, false);
+	t4_tp_get_err_stats(adap, &err_stats, false);
 	spin_unlock(&adap->stats_lock);
 
 	s->db_drop = adap->db_stats.db_drop;
@@ -388,9 +389,9 @@ static void collect_channel_stats(struct adapter *adap, struct channel_stats *s,
 	memset(s, 0, sizeof(*s));
 
 	spin_lock(&adap->stats_lock);
-	t4_tp_get_cpl_stats(adap, &cpl_stats);
-	t4_tp_get_err_stats(adap, &err_stats);
-	t4_get_fcoe_stats(adap, i, &fcoe_stats);
+	t4_tp_get_cpl_stats(adap, &cpl_stats, false);
+	t4_tp_get_err_stats(adap, &err_stats, false);
+	t4_get_fcoe_stats(adap, i, &fcoe_stats, false);
 	spin_unlock(&adap->stats_lock);
 
 	s->cpl_req = cpl_stats.req[i];
@@ -1374,6 +1375,56 @@ static int get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
 	return -EOPNOTSUPP;
 }
 
+static int set_dump(struct net_device *dev, struct ethtool_dump *eth_dump)
+{
+	struct adapter *adapter = netdev2adap(dev);
+	u32 len = 0;
+
+	len = sizeof(struct cudbg_hdr) +
+	      sizeof(struct cudbg_entity_hdr) * CUDBG_MAX_ENTITY;
+	len += cxgb4_get_dump_length(adapter, eth_dump->flag);
+
+	adapter->eth_dump.flag = eth_dump->flag;
+	adapter->eth_dump.len = len;
+	return 0;
+}
+
+static int get_dump_flag(struct net_device *dev, struct ethtool_dump *eth_dump)
+{
+	struct adapter *adapter = netdev2adap(dev);
+
+	eth_dump->flag = adapter->eth_dump.flag;
+	eth_dump->len = adapter->eth_dump.len;
+	eth_dump->version = adapter->eth_dump.version;
+	return 0;
+}
+
+static int get_dump_data(struct net_device *dev, struct ethtool_dump *eth_dump,
+			 void *buf)
+{
+	struct adapter *adapter = netdev2adap(dev);
+	u32 len = 0;
+	int ret = 0;
+
+	if (adapter->eth_dump.flag == CXGB4_ETH_DUMP_NONE)
+		return -ENOENT;
+
+	len = sizeof(struct cudbg_hdr) +
+	      sizeof(struct cudbg_entity_hdr) * CUDBG_MAX_ENTITY;
+	len += cxgb4_get_dump_length(adapter, adapter->eth_dump.flag);
+	if (eth_dump->len < len)
+		return -ENOMEM;
+
+	ret = cxgb4_cudbg_collect(adapter, buf, &len, adapter->eth_dump.flag);
+	if (ret)
+		return ret;
+
+	eth_dump->flag = adapter->eth_dump.flag;
+	eth_dump->len = len;
+	eth_dump->version = adapter->eth_dump.version;
+	return 0;
+}
+
 static const struct ethtool_ops cxgb_ethtool_ops = {
 	.get_link_ksettings = get_link_ksettings,
 	.set_link_ksettings = set_link_ksettings,
@@ -1404,7 +1455,10 @@ static const struct ethtool_ops cxgb_ethtool_ops = {
 	.get_rxfh	   = get_rss_table,
 	.set_rxfh	   = set_rss_table,
 	.flash_device      = set_flash,
-	.get_ts_info       = get_ts_info
+	.get_ts_info       = get_ts_info,
+	.set_dump          = set_dump,
+	.get_dump_flag     = get_dump_flag,
+	.get_dump_data     = get_dump_data,
 };
 
 void cxgb4_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 45b5853ca2f1..5980f308a253 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -31,10 +31,15 @@
  * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
+#include <net/ipv6.h>
 
 #include "cxgb4.h"
 #include "t4_regs.h"
+#include "t4_tcb.h"
+#include "t4_values.h"
+#include "clip_tbl.h"
 #include "l2t.h"
+#include "smt.h"
 #include "t4fw_api.h"
 #include "cxgb4_filter.h"
 
@@ -48,6 +53,194 @@ static inline bool unsupported(u32 conf, u32 conf_mask, u32 val, u32 mask)
 	return !(conf & conf_mask) && is_field_set(val, mask);
 }
 
+static int set_tcb_field(struct adapter *adap, struct filter_entry *f,
+			 unsigned int ftid,  u16 word, u64 mask, u64 val,
+			 int no_reply)
+{
+	struct cpl_set_tcb_field *req;
+	struct sk_buff *skb;
+
+	skb = alloc_skb(sizeof(struct cpl_set_tcb_field), GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	req = (struct cpl_set_tcb_field *)__skb_put(skb, sizeof(*req));
+	memset(req, 0, sizeof(*req));
+	INIT_TP_WR_CPL(req, CPL_SET_TCB_FIELD, ftid);
+	req->reply_ctrl = htons(REPLY_CHAN_V(0) |
+				QUEUENO_V(adap->sge.fw_evtq.abs_id) |
+				NO_REPLY_V(no_reply));
+	req->word_cookie = htons(TCB_WORD_V(word) | TCB_COOKIE_V(ftid));
+	req->mask = cpu_to_be64(mask);
+	req->val = cpu_to_be64(val);
+	set_wr_txq(skb, CPL_PRIORITY_CONTROL, f->fs.val.iport & 0x3);
+	t4_ofld_send(adap, skb);
+	return 0;
+}
+
+/* Set one of the t_flags bits in the TCB.
+ */
+static int set_tcb_tflag(struct adapter *adap, struct filter_entry *f,
+			 unsigned int ftid, unsigned int bit_pos,
+			 unsigned int val, int no_reply)
+{
+	return set_tcb_field(adap, f, ftid,  TCB_T_FLAGS_W, 1ULL << bit_pos,
+			     (unsigned long long)val << bit_pos, no_reply);
+}
+
+static void mk_abort_req_ulp(struct cpl_abort_req *abort_req, unsigned int tid)
+{
+	struct ulp_txpkt *txpkt = (struct ulp_txpkt *)abort_req;
+	struct ulptx_idata *sc = (struct ulptx_idata *)(txpkt + 1);
+
+	txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0));
+	txpkt->len = htonl(DIV_ROUND_UP(sizeof(*abort_req), 16));
+	sc->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_IMM));
+	sc->len = htonl(sizeof(*abort_req) - sizeof(struct work_request_hdr));
+	OPCODE_TID(abort_req) = htonl(MK_OPCODE_TID(CPL_ABORT_REQ, tid));
+	abort_req->rsvd0 = htonl(0);
+	abort_req->rsvd1 = 0;
+	abort_req->cmd = CPL_ABORT_NO_RST;
+}
+
+static void mk_abort_rpl_ulp(struct cpl_abort_rpl *abort_rpl, unsigned int tid)
+{
+	struct ulp_txpkt *txpkt = (struct ulp_txpkt *)abort_rpl;
+	struct ulptx_idata *sc = (struct ulptx_idata *)(txpkt + 1);
+
+	txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0));
+	txpkt->len = htonl(DIV_ROUND_UP(sizeof(*abort_rpl), 16));
+	sc->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_IMM));
+	sc->len = htonl(sizeof(*abort_rpl) - sizeof(struct work_request_hdr));
+	OPCODE_TID(abort_rpl) = htonl(MK_OPCODE_TID(CPL_ABORT_RPL, tid));
+	abort_rpl->rsvd0 = htonl(0);
+	abort_rpl->rsvd1 = 0;
+	abort_rpl->cmd = CPL_ABORT_NO_RST;
+}
+
+static void mk_set_tcb_ulp(struct filter_entry *f,
+			   struct cpl_set_tcb_field *req,
+			   unsigned int word, u64 mask, u64 val,
+			   u8 cookie, int no_reply)
+{
+	struct ulp_txpkt *txpkt = (struct ulp_txpkt *)req;
+	struct ulptx_idata *sc = (struct ulptx_idata *)(txpkt + 1);
+
+	txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0));
+	txpkt->len = htonl(DIV_ROUND_UP(sizeof(*req), 16));
+	sc->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_IMM));
+	sc->len = htonl(sizeof(*req) - sizeof(struct work_request_hdr));
+	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, f->tid));
+	req->reply_ctrl = htons(NO_REPLY_V(no_reply) | REPLY_CHAN_V(0) |
+				QUEUENO_V(0));
+	req->word_cookie = htons(TCB_WORD_V(word) | TCB_COOKIE_V(cookie));
+	req->mask = cpu_to_be64(mask);
+	req->val = cpu_to_be64(val);
+	sc = (struct ulptx_idata *)(req + 1);
+	sc->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_NOOP));
+	sc->len = htonl(0);
+}
+
+static int configure_filter_smac(struct adapter *adap, struct filter_entry *f)
+{
+	int err;
+
+	/* do a set-tcb for smac-sel and CWR bit.. */
+	err = set_tcb_tflag(adap, f, f->tid, TF_CCTRL_CWR_S, 1, 1);
+	if (err)
+		goto smac_err;
+
+	err = set_tcb_field(adap, f, f->tid, TCB_SMAC_SEL_W,
+			    TCB_SMAC_SEL_V(TCB_SMAC_SEL_M),
+			    TCB_SMAC_SEL_V(f->smt->idx), 1);
+	if (!err)
+		return 0;
+
+smac_err:
+	dev_err(adap->pdev_dev, "filter %u smac config failed with error %u\n",
+		f->tid, err);
+	return err;
+}
+
+static void set_nat_params(struct adapter *adap, struct filter_entry *f,
+			   unsigned int tid, bool dip, bool sip, bool dp,
+			   bool sp)
+{
+	if (dip) {
+		if (f->fs.type) {
+			set_tcb_field(adap, f, tid, TCB_SND_UNA_RAW_W,
+				      WORD_MASK, f->fs.nat_lip[15] |
+				      f->fs.nat_lip[14] << 8 |
+				      f->fs.nat_lip[13] << 16 |
+				      f->fs.nat_lip[12] << 24, 1);
+
+			set_tcb_field(adap, f, tid, TCB_SND_UNA_RAW_W + 1,
+				      WORD_MASK, f->fs.nat_lip[11] |
+				      f->fs.nat_lip[10] << 8 |
+				      f->fs.nat_lip[9] << 16 |
+				      f->fs.nat_lip[8] << 24, 1);
+
+			set_tcb_field(adap, f, tid, TCB_SND_UNA_RAW_W + 2,
+				      WORD_MASK, f->fs.nat_lip[7] |
+				      f->fs.nat_lip[6] << 8 |
+				      f->fs.nat_lip[5] << 16 |
+				      f->fs.nat_lip[4] << 24, 1);
+
+			set_tcb_field(adap, f, tid, TCB_SND_UNA_RAW_W + 3,
+				      WORD_MASK, f->fs.nat_lip[3] |
+				      f->fs.nat_lip[2] << 8 |
+				      f->fs.nat_lip[1] << 16 |
+				      f->fs.nat_lip[0] << 24, 1);
+		} else {
+			set_tcb_field(adap, f, tid, TCB_RX_FRAG3_LEN_RAW_W,
+				      WORD_MASK, f->fs.nat_lip[3] |
+				      f->fs.nat_lip[2] << 8 |
+				      f->fs.nat_lip[1] << 16 |
+				      f->fs.nat_lip[0] << 24, 1);
+		}
+	}
+
+	if (sip) {
+		if (f->fs.type) {
+			set_tcb_field(adap, f, tid, TCB_RX_FRAG2_PTR_RAW_W,
+				      WORD_MASK, f->fs.nat_fip[15] |
+				      f->fs.nat_fip[14] << 8 |
+				      f->fs.nat_fip[13] << 16 |
+				      f->fs.nat_fip[12] << 24, 1);
+
+			set_tcb_field(adap, f, tid, TCB_RX_FRAG2_PTR_RAW_W + 1,
+				      WORD_MASK, f->fs.nat_fip[11] |
+				      f->fs.nat_fip[10] << 8 |
+				      f->fs.nat_fip[9] << 16 |
+				      f->fs.nat_fip[8] << 24, 1);
+
+			set_tcb_field(adap, f, tid, TCB_RX_FRAG2_PTR_RAW_W + 2,
+				      WORD_MASK, f->fs.nat_fip[7] |
+				      f->fs.nat_fip[6] << 8 |
+				      f->fs.nat_fip[5] << 16 |
+				      f->fs.nat_fip[4] << 24, 1);
+
+			set_tcb_field(adap, f, tid, TCB_RX_FRAG2_PTR_RAW_W + 3,
+				      WORD_MASK, f->fs.nat_fip[3] |
+				      f->fs.nat_fip[2] << 8 |
+				      f->fs.nat_fip[1] << 16 |
+				      f->fs.nat_fip[0] << 24, 1);
+
+		} else {
+			set_tcb_field(adap, f, tid,
+				      TCB_RX_FRAG3_START_IDX_OFFSET_RAW_W,
+				      WORD_MASK, f->fs.nat_fip[3] |
+				      f->fs.nat_fip[2] << 8 |
+				      f->fs.nat_fip[1] << 16 |
+				      f->fs.nat_fip[0] << 24, 1);
+		}
+	}
+
+	set_tcb_field(adap, f, tid, TCB_PDU_HDR_LEN_W, WORD_MASK,
+		      (dp ? f->fs.nat_lport : 0) |
+		      (sp ? f->fs.nat_fport << 16 : 0), 1);
+}
+
 /* Validate filter spec against configuration done on the card. */
 static int validate_filter(struct net_device *dev,
 			   struct ch_filter_specification *fs)
@@ -148,6 +341,116 @@ static int get_filter_steerq(struct net_device *dev,
 	return iq;
 }
 
+static int get_filter_count(struct adapter *adapter, unsigned int fidx,
+			    u64 *pkts, u64 *bytes, bool hash)
+{
+	unsigned int tcb_base, tcbaddr;
+	unsigned int word_offset;
+	struct filter_entry *f;
+	__be64 be64_byte_count;
+	int ret;
+
+	tcb_base = t4_read_reg(adapter, TP_CMM_TCB_BASE_A);
+	if (is_hashfilter(adapter) && hash) {
+		if (fidx < adapter->tids.ntids) {
+			f = adapter->tids.tid_tab[fidx];
+			if (!f)
+				return -EINVAL;
+		} else {
+			return -E2BIG;
+		}
+	} else {
+		if ((fidx != (adapter->tids.nftids +
+			      adapter->tids.nsftids - 1)) &&
+		    fidx >= adapter->tids.nftids)
+			return -E2BIG;
+
+		f = &adapter->tids.ftid_tab[fidx];
+		if (!f->valid)
+			return -EINVAL;
+	}
+	tcbaddr = tcb_base + f->tid * TCB_SIZE;
+
+	spin_lock(&adapter->win0_lock);
+	if (is_t4(adapter->params.chip)) {
+		__be64 be64_count;
+
+		/* T4 doesn't maintain byte counts in hw */
+		*bytes = 0;
+
+		/* Get pkts */
+		word_offset = 4;
+		ret = t4_memory_rw(adapter, MEMWIN_NIC, MEM_EDC0,
+				   tcbaddr + (word_offset * sizeof(__be32)),
+				   sizeof(be64_count),
+				   (__be32 *)&be64_count,
+				   T4_MEMORY_READ);
+		if (ret < 0)
+			goto out;
+		*pkts = be64_to_cpu(be64_count);
+	} else {
+		__be32 be32_count;
+
+		/* Get bytes */
+		word_offset = 4;
+		ret = t4_memory_rw(adapter, MEMWIN_NIC, MEM_EDC0,
+				   tcbaddr + (word_offset * sizeof(__be32)),
+				   sizeof(be64_byte_count),
+				   &be64_byte_count,
+				   T4_MEMORY_READ);
+		if (ret < 0)
+			goto out;
+		*bytes = be64_to_cpu(be64_byte_count);
+
+		/* Get pkts */
+		word_offset = 6;
+		ret = t4_memory_rw(adapter, MEMWIN_NIC, MEM_EDC0,
+				   tcbaddr + (word_offset * sizeof(__be32)),
+				   sizeof(be32_count),
+				   &be32_count,
+				   T4_MEMORY_READ);
+		if (ret < 0)
+			goto out;
+		*pkts = (u64)be32_to_cpu(be32_count);
+	}
+
+out:
+	spin_unlock(&adapter->win0_lock);
+	return ret;
+}
+
+int cxgb4_get_filter_counters(struct net_device *dev, unsigned int fidx,
+			      u64 *hitcnt, u64 *bytecnt, bool hash)
+{
+	struct adapter *adapter = netdev2adap(dev);
+
+	return get_filter_count(adapter, fidx, hitcnt, bytecnt, hash);
+}
+
+int cxgb4_get_free_ftid(struct net_device *dev, int family)
+{
+	struct adapter *adap = netdev2adap(dev);
+	struct tid_info *t = &adap->tids;
+	int ftid;
+
+	spin_lock_bh(&t->ftid_lock);
+	if (family == PF_INET) {
+		ftid = find_first_zero_bit(t->ftid_bmap, t->nftids);
+		if (ftid >= t->nftids)
+			ftid = -1;
+	} else {
+		ftid = bitmap_find_free_region(t->ftid_bmap, t->nftids, 2);
+		if (ftid < 0)
+			goto out_unlock;
+
+		/* this is only a lookup, keep the found region unallocated */
+		bitmap_release_region(t->ftid_bmap, ftid, 2);
+	}
+out_unlock:
+	spin_unlock_bh(&t->ftid_lock);
+	return ftid;
+}
+
 static int cxgb4_set_ftid(struct tid_info *t, int fidx, int family)
 {
 	spin_lock_bh(&t->ftid_lock);
@@ -191,7 +494,8 @@ static int del_filter_wr(struct adapter *adapter, int fidx)
 		return -ENOMEM;
 
 	fwr = __skb_put(skb, len);
-	t4_mk_filtdelwr(f->tid, fwr, adapter->sge.fw_evtq.abs_id);
+	t4_mk_filtdelwr(f->tid, fwr, (adapter->flags & SHUTTING_DOWN) ? -1
+			: adapter->sge.fw_evtq.abs_id);
 
 	/* Mark the filter as "pending" and ship off the Filter Work Request.
 	 * When we get the Work Request Reply we'll clear the pending status.
@@ -210,7 +514,7 @@ static int del_filter_wr(struct adapter *adapter, int fidx)
 int set_filter_wr(struct adapter *adapter, int fidx)
 {
 	struct filter_entry *f = &adapter->tids.ftid_tab[fidx];
-	struct fw_filter_wr *fwr;
+	struct fw_filter2_wr *fwr;
 	struct sk_buff *skb;
 
 	skb = alloc_skb(sizeof(*fwr), GFP_KERNEL);
@@ -231,6 +535,21 @@ int set_filter_wr(struct adapter *adapter, int fidx)
 		}
 	}
 
+	/* If the new filter requires loopback Source MAC rewriting then
+	 * we need to allocate a SMT entry for the filter.
+	 */
+	if (f->fs.newsmac) {
+		f->smt = cxgb4_smt_alloc_switching(f->dev, f->fs.smac);
+		if (!f->smt) {
+			if (f->l2t) {
+				cxgb4_l2t_release(f->l2t);
+				f->l2t = NULL;
+			}
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+	}
+
 	fwr = __skb_put_zero(skb, sizeof(*fwr));
 
 	/* It would be nice to put most of the following in t4_hw.c but most
@@ -241,7 +560,10 @@ int set_filter_wr(struct adapter *adapter, int fidx)
 	 * filter specification structure but for now it's easiest to simply
 	 * put this fairly direct code in line ...
 	 */
-	fwr->op_pkd = htonl(FW_WR_OP_V(FW_FILTER_WR));
+	if (adapter->params.filter2_wr_support)
+		fwr->op_pkd = htonl(FW_WR_OP_V(FW_FILTER2_WR));
+	else
+		fwr->op_pkd = htonl(FW_WR_OP_V(FW_FILTER_WR));
 	fwr->len16_pkd = htonl(FW_WR_LEN16_V(sizeof(*fwr) / 16));
 	fwr->tid_to_iq =
 		htonl(FW_FILTER_WR_TID_V(f->tid) |
@@ -256,7 +578,6 @@ int set_filter_wr(struct adapter *adapter, int fidx)
 		      FW_FILTER_WR_DIRSTEERHASH_V(f->fs.dirsteerhash) |
 		      FW_FILTER_WR_LPBK_V(f->fs.action == FILTER_SWITCH) |
 		      FW_FILTER_WR_DMAC_V(f->fs.newdmac) |
-		      FW_FILTER_WR_SMAC_V(f->fs.newsmac) |
 		      FW_FILTER_WR_INSVLAN_V(f->fs.newvlan == VLAN_INSERT ||
 					     f->fs.newvlan == VLAN_REWRITE) |
 		      FW_FILTER_WR_RMVLAN_V(f->fs.newvlan == VLAN_REMOVE ||
@@ -303,8 +624,18 @@ int set_filter_wr(struct adapter *adapter, int fidx)
 	fwr->lpm = htons(f->fs.mask.lport);
 	fwr->fp = htons(f->fs.val.fport);
 	fwr->fpm = htons(f->fs.mask.fport);
-	if (f->fs.newsmac)
-		memcpy(fwr->sma, f->fs.smac, sizeof(fwr->sma));
+
+	if (adapter->params.filter2_wr_support) {
+		fwr->natmode_to_ulp_type =
+			FW_FILTER2_WR_ULP_TYPE_V(f->fs.nat_mode ?
+						 ULP_MODE_TCPDDP :
+						 ULP_MODE_NONE) |
+			FW_FILTER2_WR_NATMODE_V(f->fs.nat_mode);
+		memcpy(fwr->newlip, f->fs.nat_lip, sizeof(fwr->newlip));
+		memcpy(fwr->newfip, f->fs.nat_fip, sizeof(fwr->newfip));
+		fwr->newlport = htons(f->fs.nat_lport);
+		fwr->newfport = htons(f->fs.nat_fport);
+	}
 
 	/* Mark the filter as "pending" and ship off the Filter Work Request.
 	 * When we get the Work Request Reply we'll clear the pending status.
@@ -354,14 +685,18 @@ int delete_filter(struct adapter *adapter, unsigned int fidx)
 void clear_filter(struct adapter *adap, struct filter_entry *f)
 {
 	/* If the new or old filter have loopback rewriteing rules then we'll
-	 * need to free any existing Layer Two Table (L2T) entries of the old
-	 * filter rule.  The firmware will handle freeing up any Source MAC
-	 * Table (SMT) entries used for rewriting Source MAC Addresses in
-	 * loopback rules.
+	 * need to free any existing L2T, SMT, CLIP entries of filter
+	 * rule.
 	 */
 	if (f->l2t)
 		cxgb4_l2t_release(f->l2t);
 
+	if (f->smt)
+		cxgb4_smt_release(f->smt);
+
+	if (f->fs.hash && f->fs.type)
+		cxgb4_clip_release(f->dev, (const u32 *)&f->fs.val.lip, 1);
+
 	/* The zeroing of the filter rule below clears the filter valid,
 	 * pending, locked flags, l2t pointer, etc. so it's all we need for
 	 * this operation.
@@ -431,6 +766,418 @@ static void fill_default_mask(struct ch_filter_specification *fs)
 		fs->mask.fport = ~0;
 }
 
+static bool is_addr_all_mask(u8 *ipmask, int family)
+{
+	if (family == AF_INET) {
+		struct in_addr *addr;
+
+		addr = (struct in_addr *)ipmask;
+		if (addr->s_addr == 0xffffffff)
+			return true;
+	} else if (family == AF_INET6) {
+		struct in6_addr *addr6;
+
+		addr6 = (struct in6_addr *)ipmask;
+		if (addr6->s6_addr32[0] == 0xffffffff &&
+		    addr6->s6_addr32[1] == 0xffffffff &&
+		    addr6->s6_addr32[2] == 0xffffffff &&
+		    addr6->s6_addr32[3] == 0xffffffff)
+			return true;
+	}
+	return false;
+}
+
+static bool is_inaddr_any(u8 *ip, int family)
+{
+	int addr_type;
+
+	if (family == AF_INET) {
+		struct in_addr *addr;
+
+		addr = (struct in_addr *)ip;
+		if (addr->s_addr == htonl(INADDR_ANY))
+			return true;
+	} else if (family == AF_INET6) {
+		struct in6_addr *addr6;
+
+		addr6 = (struct in6_addr *)ip;
+		addr_type = ipv6_addr_type((const struct in6_addr *)
+					   &addr6);
+		if (addr_type == IPV6_ADDR_ANY)
+			return true;
+	}
+	return false;
+}
+
+bool is_filter_exact_match(struct adapter *adap,
+			   struct ch_filter_specification *fs)
+{
+	struct tp_params *tp = &adap->params.tp;
+	u64 hash_filter_mask = tp->hash_filter_mask;
+	u32 mask;
+
+	if (!is_hashfilter(adap))
+		return false;
+
+	if (fs->type) {
+		if (is_inaddr_any(fs->val.fip, AF_INET6) ||
+		    !is_addr_all_mask(fs->mask.fip, AF_INET6))
+			return false;
+
+		if (is_inaddr_any(fs->val.lip, AF_INET6) ||
+		    !is_addr_all_mask(fs->mask.lip, AF_INET6))
+			return false;
+	} else {
+		if (is_inaddr_any(fs->val.fip, AF_INET) ||
+		    !is_addr_all_mask(fs->mask.fip, AF_INET))
+			return false;
+
+		if (is_inaddr_any(fs->val.lip, AF_INET) ||
+		    !is_addr_all_mask(fs->mask.lip, AF_INET))
+			return false;
+	}
+
+	if (!fs->val.lport || fs->mask.lport != 0xffff)
+		return false;
+
+	if (!fs->val.fport || fs->mask.fport != 0xffff)
+		return false;
+
+	if (tp->fcoe_shift >= 0) {
+		mask = (hash_filter_mask >> tp->fcoe_shift) & FT_FCOE_W;
+		if (mask && !fs->mask.fcoe)
+			return false;
+	}
+
+	if (tp->port_shift >= 0) {
+		mask = (hash_filter_mask >> tp->port_shift) & FT_PORT_W;
+		if (mask && !fs->mask.iport)
+			return false;
+	}
+
+	if (tp->vnic_shift >= 0) {
+		mask = (hash_filter_mask >> tp->vnic_shift) & FT_VNIC_ID_W;
+
+		if ((adap->params.tp.ingress_config & VNIC_F)) {
+			if (mask && !fs->mask.pfvf_vld)
+				return false;
+		} else {
+			if (mask && !fs->mask.ovlan_vld)
+				return false;
+		}
+	}
+
+	if (tp->vlan_shift >= 0) {
+		mask = (hash_filter_mask >> tp->vlan_shift) & FT_VLAN_W;
+		if (mask && !fs->mask.ivlan)
+			return false;
+	}
+
+	if (tp->tos_shift >= 0) {
+		mask = (hash_filter_mask >> tp->tos_shift) & FT_TOS_W;
+		if (mask && !fs->mask.tos)
+			return false;
+	}
+
+	if (tp->protocol_shift >= 0) {
+		mask = (hash_filter_mask >> tp->protocol_shift) & FT_PROTOCOL_W;
+		if (mask && !fs->mask.proto)
+			return false;
+	}
+
+	if (tp->ethertype_shift >= 0) {
+		mask = (hash_filter_mask >> tp->ethertype_shift) &
+			FT_ETHERTYPE_W;
+		if (mask && !fs->mask.ethtype)
+			return false;
+	}
+
+	if (tp->macmatch_shift >= 0) {
+		mask = (hash_filter_mask >> tp->macmatch_shift) & FT_MACMATCH_W;
+		if (mask && !fs->mask.macidx)
+			return false;
+	}
+
+	if (tp->matchtype_shift >= 0) {
+		mask = (hash_filter_mask >> tp->matchtype_shift) &
+			FT_MPSHITTYPE_W;
+		if (mask && !fs->mask.matchtype)
+			return false;
+	}
+	if (tp->frag_shift >= 0) {
+		mask = (hash_filter_mask >> tp->frag_shift) &
+			FT_FRAGMENTATION_W;
+		if (mask && !fs->mask.frag)
+			return false;
+	}
+	return true;
+}
+
+static u64 hash_filter_ntuple(struct ch_filter_specification *fs,
+			      struct net_device *dev)
+{
+	struct adapter *adap = netdev2adap(dev);
+	struct tp_params *tp = &adap->params.tp;
+	u64 ntuple = 0;
+
+	/* Initialize each of the fields which we care about which are present
+	 * in the Compressed Filter Tuple.
+	 */
+	if (tp->vlan_shift >= 0 && fs->mask.ivlan)
+		ntuple |= (FT_VLAN_VLD_F | fs->val.ivlan) << tp->vlan_shift;
+
+	if (tp->port_shift >= 0 && fs->mask.iport)
+		ntuple |= (u64)fs->val.iport << tp->port_shift;
+
+	if (tp->protocol_shift >= 0) {
+		if (!fs->val.proto)
+			ntuple |= (u64)IPPROTO_TCP << tp->protocol_shift;
+		else
+			ntuple |= (u64)fs->val.proto << tp->protocol_shift;
+	}
+
+	if (tp->tos_shift >= 0 && fs->mask.tos)
+		ntuple |= (u64)(fs->val.tos) << tp->tos_shift;
+
+	if (tp->vnic_shift >= 0) {
+		if ((adap->params.tp.ingress_config & VNIC_F) &&
+		    fs->mask.pfvf_vld)
+			ntuple |= (u64)((fs->val.pfvf_vld << 16) |
+					(fs->val.pf << 13) |
+					(fs->val.vf)) << tp->vnic_shift;
+		else
+			ntuple |= (u64)((fs->val.ovlan_vld << 16) |
+					(fs->val.ovlan)) << tp->vnic_shift;
+	}
+
+	if (tp->macmatch_shift >= 0 && fs->mask.macidx)
+		ntuple |= (u64)(fs->val.macidx) << tp->macmatch_shift;
+
+	if (tp->ethertype_shift >= 0 && fs->mask.ethtype)
+		ntuple |= (u64)(fs->val.ethtype) << tp->ethertype_shift;
+
+	if (tp->matchtype_shift >= 0 && fs->mask.matchtype)
+		ntuple |= (u64)(fs->val.matchtype) << tp->matchtype_shift;
+
+	if (tp->frag_shift >= 0 && fs->mask.frag)
+		ntuple |= (u64)(fs->val.frag) << tp->frag_shift;
+
+	if (tp->fcoe_shift >= 0 && fs->mask.fcoe)
+		ntuple |= (u64)(fs->val.fcoe) << tp->fcoe_shift;
+	return ntuple;
+}
+
+static void mk_act_open_req6(struct filter_entry *f, struct sk_buff *skb,
+			     unsigned int qid_filterid, struct adapter *adap)
+{
+	struct cpl_t6_act_open_req6 *t6req = NULL;
+	struct cpl_act_open_req6 *req = NULL;
+
+	t6req = (struct cpl_t6_act_open_req6 *)__skb_put(skb, sizeof(*t6req));
+	INIT_TP_WR(t6req, 0);
+	req = (struct cpl_act_open_req6 *)t6req;
+	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ACT_OPEN_REQ6, qid_filterid));
+	req->local_port = cpu_to_be16(f->fs.val.lport);
+	req->peer_port = cpu_to_be16(f->fs.val.fport);
+	req->local_ip_hi = *(__be64 *)(&f->fs.val.lip);
+	req->local_ip_lo = *(((__be64 *)&f->fs.val.lip) + 1);
+	req->peer_ip_hi = *(__be64 *)(&f->fs.val.fip);
+	req->peer_ip_lo = *(((__be64 *)&f->fs.val.fip) + 1);
+	req->opt0 = cpu_to_be64(NAGLE_V(f->fs.newvlan == VLAN_REMOVE ||
+					f->fs.newvlan == VLAN_REWRITE) |
+				DELACK_V(f->fs.hitcnts) |
+				L2T_IDX_V(f->l2t ? f->l2t->idx : 0) |
+				SMAC_SEL_V((cxgb4_port_viid(f->dev) &
+					    0x7F) << 1) |
+				TX_CHAN_V(f->fs.eport) |
+				NO_CONG_V(f->fs.rpttid) |
+				ULP_MODE_V(f->fs.nat_mode ?
+					   ULP_MODE_TCPDDP : ULP_MODE_NONE) |
+				TCAM_BYPASS_F | NON_OFFLOAD_F);
+	t6req->params = cpu_to_be64(FILTER_TUPLE_V(hash_filter_ntuple(&f->fs,
+								      f->dev)));
+	t6req->opt2 = htonl(RSS_QUEUE_VALID_F |
+			    RSS_QUEUE_V(f->fs.iq) |
+			    TX_QUEUE_V(f->fs.nat_mode) |
+			    T5_OPT_2_VALID_F |
+			    RX_CHANNEL_F |
+			    CONG_CNTRL_V((f->fs.action == FILTER_DROP) |
+					 (f->fs.dirsteer << 1)) |
+			    PACE_V((f->fs.maskhash) |
+				   ((f->fs.dirsteerhash) << 1)) |
+			    CCTRL_ECN_V(f->fs.action == FILTER_SWITCH));
+}
+
+static void mk_act_open_req(struct filter_entry *f, struct sk_buff *skb,
+			    unsigned int qid_filterid, struct adapter *adap)
+{
+	struct cpl_t6_act_open_req *t6req = NULL;
+	struct cpl_act_open_req *req = NULL;
+
+	t6req = (struct cpl_t6_act_open_req *)__skb_put(skb, sizeof(*t6req));
+	INIT_TP_WR(t6req, 0);
+	req = (struct cpl_act_open_req *)t6req;
+	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ACT_OPEN_REQ, qid_filterid));
+	req->local_port = cpu_to_be16(f->fs.val.lport);
+	req->peer_port = cpu_to_be16(f->fs.val.fport);
+	req->local_ip = f->fs.val.lip[0] | f->fs.val.lip[1] << 8 |
+		f->fs.val.lip[2] << 16 | f->fs.val.lip[3] << 24;
+	req->peer_ip = f->fs.val.fip[0] | f->fs.val.fip[1] << 8 |
+		f->fs.val.fip[2] << 16 | f->fs.val.fip[3] << 24;
+	req->opt0 = cpu_to_be64(NAGLE_V(f->fs.newvlan == VLAN_REMOVE ||
+					f->fs.newvlan == VLAN_REWRITE) |
+				DELACK_V(f->fs.hitcnts) |
+				L2T_IDX_V(f->l2t ? f->l2t->idx : 0) |
+				SMAC_SEL_V((cxgb4_port_viid(f->dev) &
+					    0x7F) << 1) |
+				TX_CHAN_V(f->fs.eport) |
+				NO_CONG_V(f->fs.rpttid) |
+				ULP_MODE_V(f->fs.nat_mode ?
+					   ULP_MODE_TCPDDP : ULP_MODE_NONE) |
+				TCAM_BYPASS_F | NON_OFFLOAD_F);
+
+	t6req->params = cpu_to_be64(FILTER_TUPLE_V(hash_filter_ntuple(&f->fs,
+								      f->dev)));
+	t6req->opt2 = htonl(RSS_QUEUE_VALID_F |
+			    RSS_QUEUE_V(f->fs.iq) |
+			    TX_QUEUE_V(f->fs.nat_mode) |
+			    T5_OPT_2_VALID_F |
+			    RX_CHANNEL_F |
+			    CONG_CNTRL_V((f->fs.action == FILTER_DROP) |
+					 (f->fs.dirsteer << 1)) |
+			    PACE_V((f->fs.maskhash) |
+				   ((f->fs.dirsteerhash) << 1)) |
+			    CCTRL_ECN_V(f->fs.action == FILTER_SWITCH));
+}
+
+static int cxgb4_set_hash_filter(struct net_device *dev,
+				 struct ch_filter_specification *fs,
+				 struct filter_ctx *ctx)
+{
+	struct adapter *adapter = netdev2adap(dev);
+	struct tid_info *t = &adapter->tids;
+	struct filter_entry *f;
+	struct sk_buff *skb;
+	int iq, atid, size;
+	int ret = 0;
+	u32 iconf;
+
+	fill_default_mask(fs);
+	ret = validate_filter(dev, fs);
+	if (ret)
+		return ret;
+
+	iq = get_filter_steerq(dev, fs);
+	if (iq < 0)
+		return iq;
+
+	f = kzalloc(sizeof(*f), GFP_KERNEL);
+	if (!f)
+		return -ENOMEM;
+
+	f->fs = *fs;
+	f->ctx = ctx;
+	f->dev = dev;
+	f->fs.iq = iq;
+
+	/* If the new filter requires loopback Destination MAC and/or VLAN
+	 * rewriting then we need to allocate a Layer 2 Table (L2T) entry for
+	 * the filter.
+	 */
+	if (f->fs.newdmac || f->fs.newvlan) {
+		/* allocate L2T entry for new filter */
+		f->l2t = t4_l2t_alloc_switching(adapter, f->fs.vlan,
+						f->fs.eport, f->fs.dmac);
+		if (!f->l2t) {
+			ret = -ENOMEM;
+			goto out_err;
+		}
+	}
+
+	/* If the new filter requires loopback Source MAC rewriting then
+	 * we need to allocate a SMT entry for the filter.
+	 */
+	if (f->fs.newsmac) {
+		f->smt = cxgb4_smt_alloc_switching(f->dev, f->fs.smac);
+		if (!f->smt) {
+			if (f->l2t) {
+				cxgb4_l2t_release(f->l2t);
+				f->l2t = NULL;
+			}
+			ret = -ENOMEM;
+			goto free_l2t;
+		}
+	}
+
+	atid = cxgb4_alloc_atid(t, f);
+	if (atid < 0) {
+		ret = atid;
+		goto free_smt;
+	}
+
+	iconf = adapter->params.tp.ingress_config;
+	if (iconf & VNIC_F) {
+		f->fs.val.ovlan = (fs->val.pf << 13) | fs->val.vf;
+		f->fs.mask.ovlan = (fs->mask.pf << 13) | fs->mask.vf;
+		f->fs.val.ovlan_vld = fs->val.pfvf_vld;
+		f->fs.mask.ovlan_vld = fs->mask.pfvf_vld;
+	}
+
+	size = sizeof(struct cpl_t6_act_open_req);
+	if (f->fs.type) {
+		ret = cxgb4_clip_get(f->dev, (const u32 *)&f->fs.val.lip, 1);
+		if (ret)
+			goto free_atid;
+
+		skb = alloc_skb(size, GFP_KERNEL);
+		if (!skb) {
+			ret = -ENOMEM;
+			goto free_clip;
+		}
+
+		mk_act_open_req6(f, skb,
+				 ((adapter->sge.fw_evtq.abs_id << 14) | atid),
+				 adapter);
+	} else {
+		skb = alloc_skb(size, GFP_KERNEL);
+		if (!skb) {
+			ret = -ENOMEM;
+			goto free_atid;
+		}
+
+		mk_act_open_req(f, skb,
+				((adapter->sge.fw_evtq.abs_id << 14) | atid),
+				adapter);
+	}
+
+	f->pending = 1;
+	set_wr_txq(skb, CPL_PRIORITY_SETUP, f->fs.val.iport & 0x3);
+	t4_ofld_send(adapter, skb);
+	return 0;
+
+free_clip:
+	cxgb4_clip_release(f->dev, (const u32 *)&f->fs.val.lip, 1);
+
+free_atid:
+	cxgb4_free_atid(t, atid);
+
+free_smt:
+	if (f->smt) {
+		cxgb4_smt_release(f->smt);
+		f->smt = NULL;
+	}
+
+free_l2t:
+	if (f->l2t) {
+		cxgb4_l2t_release(f->l2t);
+		f->l2t = NULL;
+	}
+
+out_err:
+	kfree(f);
+	return ret;
+}
+
 /* Check a Chelsio Filter Request for validity, convert it into our internal
  * format and send it to the hardware.  Return 0 on success, an error number
  * otherwise.  We attach any provided filter operation context to the internal
@@ -447,6 +1194,14 @@ int __cxgb4_set_filter(struct net_device *dev, int filter_id,
 	u32 iconf;
 	int iq, ret;
 
+	if (fs->hash) {
+		if (is_hashfilter(adapter))
+			return cxgb4_set_hash_filter(dev, fs, ctx);
+		netdev_err(dev, "%s: Exact-match filters only supported with Hash Filter configuration\n",
+			   __func__);
+		return -EINVAL;
+	}
+
 	max_fidx = adapter->tids.nftids;
 	if (filter_id != (max_fidx + adapter->tids.nsftids - 1) &&
 	    filter_id >= max_fidx)
@@ -568,12 +1323,74 @@ int __cxgb4_set_filter(struct net_device *dev, int filter_id,
 	return ret;
 }
 
+static int cxgb4_del_hash_filter(struct net_device *dev, int filter_id,
+				 struct filter_ctx *ctx)
+{
+	struct adapter *adapter = netdev2adap(dev);
+	struct tid_info *t = &adapter->tids;
+	struct cpl_abort_req *abort_req;
+	struct cpl_abort_rpl *abort_rpl;
+	struct cpl_set_tcb_field *req;
+	struct ulptx_idata *aligner;
+	struct work_request_hdr *wr;
+	struct filter_entry *f;
+	struct sk_buff *skb;
+	unsigned int wrlen;
+	int ret;
+
+	netdev_dbg(dev, "%s: filter_id = %d ; nftids = %d\n",
+		   __func__, filter_id, adapter->tids.nftids);
+
+	if (filter_id > adapter->tids.ntids)
+		return -E2BIG;
+
+	f = lookup_tid(t, filter_id);
+	if (!f) {
+		netdev_err(dev, "%s: no filter entry for filter_id = %d",
+			   __func__, filter_id);
+		return -EINVAL;
+	}
+
+	ret = writable_filter(f);
+	if (ret)
+		return ret;
+
+	if (!f->valid)
+		return -EINVAL;
+
+	f->ctx = ctx;
+	f->pending = 1;
+	wrlen = roundup(sizeof(*wr) + (sizeof(*req) + sizeof(*aligner))
+			+ sizeof(*abort_req) + sizeof(*abort_rpl), 16);
+	skb = alloc_skb(wrlen, GFP_KERNEL);
+	if (!skb) {
+		netdev_err(dev, "%s: could not allocate skb ..\n", __func__);
+		return -ENOMEM;
+	}
+	set_wr_txq(skb, CPL_PRIORITY_CONTROL, f->fs.val.iport & 0x3);
+	req = (struct cpl_set_tcb_field *)__skb_put(skb, wrlen);
+	INIT_ULPTX_WR(req, wrlen, 0, 0);
+	wr = (struct work_request_hdr *)req;
+	wr++;
+	req = (struct cpl_set_tcb_field *)wr;
+	mk_set_tcb_ulp(f, req, TCB_RSS_INFO_W, TCB_RSS_INFO_V(TCB_RSS_INFO_M),
+		       TCB_RSS_INFO_V(adapter->sge.fw_evtq.abs_id), 0, 1);
+	aligner = (struct ulptx_idata *)(req + 1);
+	abort_req = (struct cpl_abort_req *)(aligner + 1);
+	mk_abort_req_ulp(abort_req, f->tid);
+	abort_rpl = (struct cpl_abort_rpl *)(abort_req + 1);
+	mk_abort_rpl_ulp(abort_rpl, f->tid);
+	t4_ofld_send(adapter, skb);
+	return 0;
+}
+
 /* Check a delete filter request for validity and send it to the hardware.
  * Return 0 on success, an error number otherwise.  We attach any provided
  * filter operation context to the internal filter specification in order to
  * facilitate signaling completion of the operation.
  */
 int __cxgb4_del_filter(struct net_device *dev, int filter_id,
+		       struct ch_filter_specification *fs,
 		       struct filter_ctx *ctx)
 {
 	struct adapter *adapter = netdev2adap(dev);
@@ -581,6 +1398,14 @@ int __cxgb4_del_filter(struct net_device *dev, int filter_id,
 	unsigned int max_fidx;
 	int ret;
 
+	if (fs && fs->hash) {
+		if (is_hashfilter(adapter))
+			return cxgb4_del_hash_filter(dev, filter_id, ctx);
+		netdev_err(dev, "%s: Exact-match filters only supported with Hash Filter configuration\n",
+			   __func__);
+		return -EINVAL;
+	}
+
 	max_fidx = adapter->tids.nftids;
 	if (filter_id != (max_fidx + adapter->tids.nsftids - 1) &&
 	    filter_id >= max_fidx)
@@ -631,14 +1456,19 @@ out:
 	return ret;
 }
 
-int cxgb4_del_filter(struct net_device *dev, int filter_id)
+int cxgb4_del_filter(struct net_device *dev, int filter_id,
+		     struct ch_filter_specification *fs)
 {
 	struct filter_ctx ctx;
 	int ret;
 
+	/* If we are shutting down the adapter do not wait for completion */
+	if (netdev2adap(dev)->flags & SHUTTING_DOWN)
+		return __cxgb4_del_filter(dev, filter_id, fs, NULL);
+
 	init_completion(&ctx.completion);
 
-	ret = __cxgb4_del_filter(dev, filter_id, &ctx);
+	ret = __cxgb4_del_filter(dev, filter_id, fs, &ctx);
 	if (ret)
 		goto out;
 
@@ -652,6 +1482,157 @@ out:
 	return ret;
 }
 
+static int configure_filter_tcb(struct adapter *adap, unsigned int tid,
+				struct filter_entry *f)
+{
+	if (f->fs.hitcnts)
+		set_tcb_field(adap, f, tid, TCB_TIMESTAMP_W,
+			      TCB_TIMESTAMP_V(TCB_TIMESTAMP_M) |
+			      TCB_RTT_TS_RECENT_AGE_V(TCB_RTT_TS_RECENT_AGE_M),
+			      TCB_TIMESTAMP_V(0ULL) |
+			      TCB_RTT_TS_RECENT_AGE_V(0ULL),
+			      1);
+
+	if (f->fs.newdmac)
+		set_tcb_tflag(adap, f, tid, TF_CCTRL_ECE_S, 1,
+			      1);
+
+	if (f->fs.newvlan == VLAN_INSERT ||
+	    f->fs.newvlan == VLAN_REWRITE)
+		set_tcb_tflag(adap, f, tid, TF_CCTRL_RFR_S, 1,
+			      1);
+	if (f->fs.newsmac)
+		configure_filter_smac(adap, f);
+
+	if (f->fs.nat_mode) {
+		switch (f->fs.nat_mode) {
+		case NAT_MODE_DIP:
+			set_nat_params(adap, f, tid, true, false, false, false);
+			break;
+
+		case NAT_MODE_DIP_DP:
+			set_nat_params(adap, f, tid, true, false, true, false);
+			break;
+
+		case NAT_MODE_DIP_DP_SIP:
+			set_nat_params(adap, f, tid, true, true, true, false);
+			break;
+		case NAT_MODE_DIP_DP_SP:
+			set_nat_params(adap, f, tid, true, false, true, true);
+			break;
+
+		case NAT_MODE_SIP_SP:
+			set_nat_params(adap, f, tid, false, true, false, true);
+			break;
+
+		case NAT_MODE_DIP_SIP_SP:
+			set_nat_params(adap, f, tid, true, true, false, true);
+			break;
+
+		case NAT_MODE_ALL:
+			set_nat_params(adap, f, tid, true, true, true, true);
+			break;
+
+		default:
+			pr_err("%s: Invalid NAT mode: %d\n",
+			       __func__, f->fs.nat_mode);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+void hash_del_filter_rpl(struct adapter *adap,
+			 const struct cpl_abort_rpl_rss *rpl)
+{
+	unsigned int status = rpl->status;
+	struct tid_info *t = &adap->tids;
+	unsigned int tid = GET_TID(rpl);
+	struct filter_ctx *ctx = NULL;
+	struct filter_entry *f;
+
+	dev_dbg(adap->pdev_dev, "%s: status = %u; tid = %u\n",
+		__func__, status, tid);
+
+	f = lookup_tid(t, tid);
+	if (!f) {
+		dev_err(adap->pdev_dev, "%s:could not find filter entry",
+			__func__);
+		return;
+	}
+	ctx = f->ctx;
+	f->ctx = NULL;
+	clear_filter(adap, f);
+	cxgb4_remove_tid(t, 0, tid, 0);
+	kfree(f);
+	if (ctx) {
+		ctx->result = 0;
+		complete(&ctx->completion);
+	}
+}
+
+void hash_filter_rpl(struct adapter *adap, const struct cpl_act_open_rpl *rpl)
+{
+	unsigned int ftid = TID_TID_G(AOPEN_ATID_G(ntohl(rpl->atid_status)));
+	unsigned int status  = AOPEN_STATUS_G(ntohl(rpl->atid_status));
+	struct tid_info *t = &adap->tids;
+	unsigned int tid = GET_TID(rpl);
+	struct filter_ctx *ctx = NULL;
+	struct filter_entry *f;
+
+	dev_dbg(adap->pdev_dev, "%s: tid = %u; atid = %u; status = %u\n",
+		__func__, tid, ftid, status);
+
+	f = lookup_atid(t, ftid);
+	if (!f) {
+		dev_err(adap->pdev_dev, "%s:could not find filter entry",
+			__func__);
+		return;
+	}
+	ctx = f->ctx;
+	f->ctx = NULL;
+
+	switch (status) {
+	case CPL_ERR_NONE:
+		f->tid = tid;
+		f->pending = 0;
+		f->valid = 1;
+		cxgb4_insert_tid(t, f, f->tid, 0);
+		cxgb4_free_atid(t, ftid);
+		if (ctx) {
+			ctx->tid = f->tid;
+			ctx->result = 0;
+		}
+		if (configure_filter_tcb(adap, tid, f)) {
+			clear_filter(adap, f);
+			cxgb4_remove_tid(t, 0, tid, 0);
+			kfree(f);
+			if (ctx) {
+				ctx->result = -EINVAL;
+				complete(&ctx->completion);
+			}
+			return;
+		}
+		break;
+
+	default:
+		dev_err(adap->pdev_dev, "%s: filter creation PROBLEM; status = %u\n",
+			__func__, status);
+
+		if (ctx) {
+			if (status == CPL_ERR_TCAM_FULL)
+				ctx->result = -EAGAIN;
+			else
+				ctx->result = -EINVAL;
+		}
+		clear_filter(adap, f);
+		cxgb4_free_atid(t, ftid);
+		kfree(f);
+	}
+	if (ctx)
+		complete(&ctx->completion);
+}
+
 /* Handle a filter write/deletion reply. */
 void filter_rpl(struct adapter *adap, const struct cpl_set_tcb_rpl *rpl)
 {
@@ -690,19 +1671,23 @@ void filter_rpl(struct adapter *adap, const struct cpl_set_tcb_rpl *rpl)
 			clear_filter(adap, f);
 			if (ctx)
 				ctx->result = 0;
-		} else if (ret == FW_FILTER_WR_SMT_TBL_FULL) {
-			dev_err(adap->pdev_dev, "filter %u setup failed due to full SMT\n",
-				idx);
-			clear_filter(adap, f);
-			if (ctx)
-				ctx->result = -ENOMEM;
 		} else if (ret == FW_FILTER_WR_FLT_ADDED) {
-			f->smtidx = (be64_to_cpu(rpl->oldval) >> 24) & 0xff;
-			f->pending = 0;  /* asynchronous setup completed */
-			f->valid = 1;
-			if (ctx) {
-				ctx->result = 0;
-				ctx->tid = idx;
+			int err = 0;
+
+			if (f->fs.newsmac)
+				err = configure_filter_smac(adap, f);
+
+			if (!err) {
+				f->pending = 0;  /* async setup completed */
+				f->valid = 1;
+				if (ctx) {
+					ctx->result = 0;
+					ctx->tid = idx;
+				}
+			} else {
+				clear_filter(adap, f);
+				if (ctx)
+					ctx->result = err;
 			}
 		} else {
 			/* Something went wrong.  Issue a warning about the
@@ -718,3 +1703,25 @@ void filter_rpl(struct adapter *adap, const struct cpl_set_tcb_rpl *rpl)
 			complete(&ctx->completion);
 	}
 }
+
+int init_hash_filter(struct adapter *adap)
+{
+	/* On T6, verify the necessary register configs and warn the user in
+	 * case of improper config
+	 */
+	if (is_t6(adap->params.chip)) {
+		if (TCAM_ACTV_HIT_G(t4_read_reg(adap, LE_DB_RSP_CODE_0_A)) != 4)
+			goto err;
+
+		if (HASH_ACTV_HIT_G(t4_read_reg(adap, LE_DB_RSP_CODE_1_A)) != 4)
+			goto err;
+	} else {
+		dev_err(adap->pdev_dev, "Hash filter supported only on T6\n");
+		return -EINVAL;
+	}
+	adap->params.hash_filter = 1;
+	return 0;
+err:
+	dev_warn(adap->pdev_dev, "Invalid hash filter config!\n");
+	return -EINVAL;
+}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.h
index 23742cb1c69f..8db5fca6dcc9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.h
@@ -37,7 +37,12 @@
 
 #include "t4_msg.h"
 
+#define WORD_MASK	0xffffffff
+
 void filter_rpl(struct adapter *adap, const struct cpl_set_tcb_rpl *rpl);
+void hash_filter_rpl(struct adapter *adap, const struct cpl_act_open_rpl *rpl);
+void hash_del_filter_rpl(struct adapter *adap,
+			 const struct cpl_abort_rpl_rss *rpl);
 void clear_filter(struct adapter *adap, struct filter_entry *f);
 
 int set_filter_wr(struct adapter *adapter, int fidx);
@@ -45,4 +50,7 @@ int delete_filter(struct adapter *adapter, unsigned int fidx);
 
 int writable_filter(struct filter_entry *f);
 void clear_all_filters(struct adapter *adapter);
+int init_hash_filter(struct adapter *adap);
+bool is_filter_exact_match(struct adapter *adap,
+			   struct ch_filter_specification *fs);
 #endif /* __CXGB4_FILTER_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 92d9d795d874..6f900ffe25cc 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -77,9 +77,12 @@
 #include "cxgb4_debugfs.h"
 #include "clip_tbl.h"
 #include "l2t.h"
+#include "smt.h"
 #include "sched.h"
 #include "cxgb4_tc_u32.h"
+#include "cxgb4_tc_flower.h"
 #include "cxgb4_ptp.h"
+#include "cxgb4_cudbg.h"
 
 char cxgb4_driver_name[] = KBUILD_MODNAME;
 
@@ -280,7 +283,7 @@ void t4_os_link_changed(struct adapter *adapter, int port_id, int link_stat)
 		else {
 #ifdef CONFIG_CHELSIO_T4_DCB
 			if (cxgb4_dcb_enabled(dev)) {
-				cxgb4_dcb_state_init(dev);
+				cxgb4_dcb_reset(dev);
 				dcb_tx_queue_prio_enable(dev, false);
 			}
 #endif /* CONFIG_CHELSIO_T4_DCB */
@@ -561,10 +564,22 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
 		const struct cpl_l2t_write_rpl *p = (void *)rsp;
 
 		do_l2t_write_rpl(q->adap, p);
+	} else if (opcode == CPL_SMT_WRITE_RPL) {
+		const struct cpl_smt_write_rpl *p = (void *)rsp;
+
+		do_smt_write_rpl(q->adap, p);
 	} else if (opcode == CPL_SET_TCB_RPL) {
 		const struct cpl_set_tcb_rpl *p = (void *)rsp;
 
 		filter_rpl(q->adap, p);
+	} else if (opcode == CPL_ACT_OPEN_RPL) {
+		const struct cpl_act_open_rpl *p = (void *)rsp;
+
+		hash_filter_rpl(q->adap, p);
+	} else if (opcode == CPL_ABORT_RPL_RSS) {
+		const struct cpl_abort_rpl_rss *p = (void *)rsp;
+
+		hash_del_filter_rpl(q->adap, p);
 	} else
 		dev_err(q->adap->pdev_dev,
 			"unexpected CPL %#x on FW event queue\n", opcode);
@@ -1637,7 +1652,7 @@ void cxgb4_get_tcp_stats(struct pci_dev *pdev, struct tp_tcp_stats *v4,
 	struct adapter *adap = pci_get_drvdata(pdev);
 
 	spin_lock(&adap->stats_lock);
-	t4_tp_get_tcp_stats(adap, v4, v6);
+	t4_tp_get_tcp_stats(adap, v4, v6, false);
 	spin_unlock(&adap->stats_lock);
 }
 EXPORT_SYMBOL(cxgb4_get_tcp_stats);
@@ -2303,10 +2318,16 @@ static int cxgb_close(struct net_device *dev)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
+	int ret;
 
 	netif_tx_stop_all_queues(dev);
 	netif_carrier_off(dev);
-	return t4_enable_vi(adapter, adapter->pf, pi->viid, false, false);
+	ret = t4_enable_vi(adapter, adapter->pf, pi->viid, false, false);
+#ifdef CONFIG_CHELSIO_T4_DCB
+	cxgb4_dcb_reset(dev);
+	dcb_tx_queue_prio_enable(dev, false);
+#endif
+	return ret;
 }
 
 int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
@@ -2873,11 +2894,28 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 	return err;
 }
 
+static int cxgb_setup_tc_flower(struct net_device *dev,
+				struct tc_cls_flower_offload *cls_flower)
+{
+	if (cls_flower->common.chain_index)
+		return -EOPNOTSUPP;
+
+	switch (cls_flower->command) {
+	case TC_CLSFLOWER_REPLACE:
+		return cxgb4_tc_flower_replace(dev, cls_flower);
+	case TC_CLSFLOWER_DESTROY:
+		return cxgb4_tc_flower_destroy(dev, cls_flower);
+	case TC_CLSFLOWER_STATS:
+		return cxgb4_tc_flower_stats(dev, cls_flower);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int cxgb_setup_tc_cls_u32(struct net_device *dev,
 				 struct tc_cls_u32_offload *cls_u32)
 {
-	if (!is_classid_clsact_ingress(cls_u32->common.classid) ||
-	    cls_u32->common.chain_index)
+	if (cls_u32->common.chain_index)
 		return -EOPNOTSUPP;
 
 	switch (cls_u32->command) {
@@ -2891,9 +2929,10 @@ static int cxgb_setup_tc_cls_u32(struct net_device *dev,
 	}
 }
 
-static int cxgb_setup_tc(struct net_device *dev, enum tc_setup_type type,
-			 void *type_data)
+static int cxgb_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				  void *cb_priv)
 {
+	struct net_device *dev = cb_priv;
 	struct port_info *pi = netdev2pinfo(dev);
 	struct adapter *adap = netdev2adap(dev);
 
@@ -2904,9 +2943,45 @@ static int cxgb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 		return -EINVAL;
 	}
 
+	if (!tc_can_offload(dev))
+		return -EOPNOTSUPP;
+
 	switch (type) {
 	case TC_SETUP_CLSU32:
 		return cxgb_setup_tc_cls_u32(dev, type_data);
+	case TC_SETUP_CLSFLOWER:
+		return cxgb_setup_tc_flower(dev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int cxgb_setup_tc_block(struct net_device *dev,
+			       struct tc_block_offload *f)
+{
+	struct port_info *pi = netdev2pinfo(dev);
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block, cxgb_setup_tc_block_cb,
+					     pi, dev);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, cxgb_setup_tc_block_cb, pi);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int cxgb_setup_tc(struct net_device *dev, enum tc_setup_type type,
+			 void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return cxgb_setup_tc_block(dev, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -3876,6 +3951,16 @@ static int adap_init0(struct adapter *adap)
 			      1, params, val);
 	adap->params.fr_nsmr_tpte_wr_support = (ret == 0 && val[0] != 0);
 
+	/* See if FW supports FW_FILTER2 work request */
+	if (is_t4(adap->params.chip)) {
+		adap->params.filter2_wr_support = 0;
+	} else {
+		params[0] = FW_PARAM_DEV(FILTER2_WR);
+		ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
+				      1, params, val);
+		adap->params.filter2_wr_support = (ret == 0 && val[0] != 0);
+	}
+
 	/*
 	 * Get device capabilities so we can determine what resources we need
 	 * to manage.
@@ -3889,7 +3974,8 @@ static int adap_init0(struct adapter *adap)
 	if (ret < 0)
 		goto bye;
 
-	if (caps_cmd.ofldcaps) {
+	if (caps_cmd.ofldcaps ||
+	    (caps_cmd.niccaps & htons(FW_CAPS_CONFIG_NIC_HASHFILTER))) {
 		/* query offload-related parameters */
 		params[0] = FW_PARAM_DEV(NTID);
 		params[1] = FW_PARAM_PFVF(SERVER_START);
@@ -3926,8 +4012,13 @@ static int adap_init0(struct adapter *adap)
 		adap->vres.ddp.size = val[4] - val[3] + 1;
 		adap->params.ofldq_wr_cred = val[5];
 
-		adap->params.offload = 1;
-		adap->num_ofld_uld += 1;
+		if (caps_cmd.niccaps & htons(FW_CAPS_CONFIG_NIC_HASHFILTER)) {
+			if (init_hash_filter(adap) < 0)
+				goto bye;
+		} else {
+			adap->params.offload = 1;
+			adap->num_ofld_uld += 1;
+		}
 	}
 	if (caps_cmd.rdmacaps) {
 		params[0] = FW_PARAM_PFVF(STAG_START);
@@ -4048,7 +4139,7 @@ static int adap_init0(struct adapter *adap)
 	}
 	t4_init_sge_params(adap);
 	adap->flags |= FW_OK;
-	t4_init_tp_params(adap);
+	t4_init_tp_params(adap, true);
 	return 0;
 
 	/*
@@ -4612,9 +4703,11 @@ static void free_some_resources(struct adapter *adapter)
 {
 	unsigned int i;
 
+	kvfree(adapter->smt);
 	kvfree(adapter->l2t);
 	t4_cleanup_sched(adapter);
 	kvfree(adapter->tids.tid_tab);
+	cxgb4_cleanup_tc_flower(adapter);
 	cxgb4_cleanup_tc_u32(adapter);
 	kfree(adapter->sge.egr_map);
 	kfree(adapter->sge.ingr_map);
@@ -4995,7 +5088,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		netdev->priv_flags |= IFF_UNICAST_FLT;
 
 		/* MTU range: 81 - 9600 */
-		netdev->min_mtu = 81;
+		netdev->min_mtu = 81;              /* accommodate SACK */
 		netdev->max_mtu = MAX_MTU;
 
 		netdev->netdev_ops = &cxgb4_netdev_ops;
@@ -5006,6 +5099,8 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		cxgb4_set_ethtool_ops(netdev);
 	}
 
+	cxgb4_init_ethtool_dump(adapter);
+
 	pci_set_drvdata(pdev, adapter);
 
 	if (adapter->flags & FW_OK) {
@@ -5035,6 +5130,12 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 */
 	cfg_queues(adapter);
 
+	adapter->smt = t4_init_smt();
+	if (!adapter->smt) {
+		/* We tolerate a lack of SMT, giving up some functionality */
+		dev_warn(&pdev->dev, "could not allocate SMT, continuing\n");
+	}
+
 	adapter->l2t = t4_init_l2t(adapter->l2t_start, adapter->l2t_end);
 	if (!adapter->l2t) {
 		/* We tolerate a lack of L2T, giving up some functionality */
@@ -5083,9 +5184,13 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		if (!adapter->tc_u32)
 			dev_warn(&pdev->dev,
 				 "could not offload tc u32, continuing\n");
+
+		if (cxgb4_init_tc_flower(adapter))
+			dev_warn(&pdev->dev,
+				 "could not offload tc flower, continuing\n");
 	}
 
-	if (is_offload(adapter)) {
+	if (is_offload(adapter) || is_hashfilter(adapter)) {
 		if (t4_read_reg(adapter, LE_DB_CONFIG_A) & HASHEN_F) {
 			u32 hash_base, hash_reg;
 
@@ -5254,6 +5359,8 @@ static void remove_one(struct pci_dev *pdev)
 		return;
 	}
 
+	adapter->flags |= SHUTTING_DOWN;
+
 	if (adapter->pf == 4) {
 		int i;
 
@@ -5339,6 +5446,8 @@ static void shutdown_one(struct pci_dev *pdev)
 		return;
 	}
 
+	adapter->flags |= SHUTTING_DOWN;
+
 	if (adapter->pf == 4) {
 		int i;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
new file mode 100644
index 000000000000..d4a548a6a55c
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -0,0 +1,876 @@
+/*
+ * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux.
+ *
+ * Copyright (c) 2017 Chelsio Communications, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <net/tc_act/tc_mirred.h>
+#include <net/tc_act/tc_pedit.h>
+#include <net/tc_act/tc_gact.h>
+#include <net/tc_act/tc_vlan.h>
+
+#include "cxgb4.h"
+#include "cxgb4_filter.h"
+#include "cxgb4_tc_flower.h"
+
+#define STATS_CHECK_PERIOD (HZ / 2)
+
+struct ch_tc_pedit_fields pedits[] = {
+	PEDIT_FIELDS(ETH_, DMAC_31_0, 4, dmac, 0),
+	PEDIT_FIELDS(ETH_, DMAC_47_32, 2, dmac, 4),
+	PEDIT_FIELDS(ETH_, SMAC_15_0, 2, smac, 0),
+	PEDIT_FIELDS(ETH_, SMAC_47_16, 4, smac, 2),
+	PEDIT_FIELDS(IP4_, SRC, 4, nat_fip, 0),
+	PEDIT_FIELDS(IP4_, DST, 4, nat_lip, 0),
+	PEDIT_FIELDS(IP6_, SRC_31_0, 4, nat_fip, 0),
+	PEDIT_FIELDS(IP6_, SRC_63_32, 4, nat_fip, 4),
+	PEDIT_FIELDS(IP6_, SRC_95_64, 4, nat_fip, 8),
+	PEDIT_FIELDS(IP6_, SRC_127_96, 4, nat_fip, 12),
+	PEDIT_FIELDS(IP6_, DST_31_0, 4, nat_lip, 0),
+	PEDIT_FIELDS(IP6_, DST_63_32, 4, nat_lip, 4),
+	PEDIT_FIELDS(IP6_, DST_95_64, 4, nat_lip, 8),
+	PEDIT_FIELDS(IP6_, DST_127_96, 4, nat_lip, 12),
+	PEDIT_FIELDS(TCP_, SPORT, 2, nat_fport, 0),
+	PEDIT_FIELDS(TCP_, DPORT, 2, nat_lport, 0),
+	PEDIT_FIELDS(UDP_, SPORT, 2, nat_fport, 0),
+	PEDIT_FIELDS(UDP_, DPORT, 2, nat_lport, 0),
+};
+
+static struct ch_tc_flower_entry *allocate_flower_entry(void)
+{
+	struct ch_tc_flower_entry *new = kzalloc(sizeof(*new), GFP_KERNEL);
+	spin_lock_init(&new->lock);
+	return new;
+}
+
+/* Must be called with either RTNL or rcu_read_lock */
+static struct ch_tc_flower_entry *ch_flower_lookup(struct adapter *adap,
+						   unsigned long flower_cookie)
+{
+	return rhashtable_lookup_fast(&adap->flower_tbl, &flower_cookie,
+				      adap->flower_ht_params);
+}
+
+static void cxgb4_process_flow_match(struct net_device *dev,
+				     struct tc_cls_flower_offload *cls,
+				     struct ch_filter_specification *fs)
+{
+	u16 addr_type = 0;
+
+	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_dissector_key_control *key =
+			skb_flow_dissector_target(cls->dissector,
+						  FLOW_DISSECTOR_KEY_CONTROL,
+						  cls->key);
+
+		addr_type = key->addr_type;
+	}
+
+	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_dissector_key_basic *key =
+			skb_flow_dissector_target(cls->dissector,
+						  FLOW_DISSECTOR_KEY_BASIC,
+						  cls->key);
+		struct flow_dissector_key_basic *mask =
+			skb_flow_dissector_target(cls->dissector,
+						  FLOW_DISSECTOR_KEY_BASIC,
+						  cls->mask);
+		u16 ethtype_key = ntohs(key->n_proto);
+		u16 ethtype_mask = ntohs(mask->n_proto);
+
+		if (ethtype_key == ETH_P_ALL) {
+			ethtype_key = 0;
+			ethtype_mask = 0;
+		}
+
+		fs->val.ethtype = ethtype_key;
+		fs->mask.ethtype = ethtype_mask;
+		fs->val.proto = key->ip_proto;
+		fs->mask.proto = mask->ip_proto;
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		struct flow_dissector_key_ipv4_addrs *key =
+			skb_flow_dissector_target(cls->dissector,
+						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+						  cls->key);
+		struct flow_dissector_key_ipv4_addrs *mask =
+			skb_flow_dissector_target(cls->dissector,
+						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+						  cls->mask);
+		fs->type = 0;
+		memcpy(&fs->val.lip[0], &key->dst, sizeof(key->dst));
+		memcpy(&fs->val.fip[0], &key->src, sizeof(key->src));
+		memcpy(&fs->mask.lip[0], &mask->dst, sizeof(mask->dst));
+		memcpy(&fs->mask.fip[0], &mask->src, sizeof(mask->src));
+
+		/* also initialize nat_lip/fip to same values */
+		memcpy(&fs->nat_lip[0], &key->dst, sizeof(key->dst));
+		memcpy(&fs->nat_fip[0], &key->src, sizeof(key->src));
+
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+		struct flow_dissector_key_ipv6_addrs *key =
+			skb_flow_dissector_target(cls->dissector,
+						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+						  cls->key);
+		struct flow_dissector_key_ipv6_addrs *mask =
+			skb_flow_dissector_target(cls->dissector,
+						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+						  cls->mask);
+
+		fs->type = 1;
+		memcpy(&fs->val.lip[0], key->dst.s6_addr, sizeof(key->dst));
+		memcpy(&fs->val.fip[0], key->src.s6_addr, sizeof(key->src));
+		memcpy(&fs->mask.lip[0], mask->dst.s6_addr, sizeof(mask->dst));
+		memcpy(&fs->mask.fip[0], mask->src.s6_addr, sizeof(mask->src));
+
+		/* also initialize nat_lip/fip to same values */
+		memcpy(&fs->nat_lip[0], key->dst.s6_addr, sizeof(key->dst));
+		memcpy(&fs->nat_fip[0], key->src.s6_addr, sizeof(key->src));
+	}
+
+	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_dissector_key_ports *key, *mask;
+
+		key = skb_flow_dissector_target(cls->dissector,
+						FLOW_DISSECTOR_KEY_PORTS,
+						cls->key);
+		mask = skb_flow_dissector_target(cls->dissector,
+						 FLOW_DISSECTOR_KEY_PORTS,
+						 cls->mask);
+		fs->val.lport = cpu_to_be16(key->dst);
+		fs->mask.lport = cpu_to_be16(mask->dst);
+		fs->val.fport = cpu_to_be16(key->src);
+		fs->mask.fport = cpu_to_be16(mask->src);
+
+		/* also initialize nat_lport/fport to same values */
+		fs->nat_lport = cpu_to_be16(key->dst);
+		fs->nat_fport = cpu_to_be16(key->src);
+	}
+
+	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) {
+		struct flow_dissector_key_ip *key, *mask;
+
+		key = skb_flow_dissector_target(cls->dissector,
+						FLOW_DISSECTOR_KEY_IP,
+						cls->key);
+		mask = skb_flow_dissector_target(cls->dissector,
+						 FLOW_DISSECTOR_KEY_IP,
+						 cls->mask);
+		fs->val.tos = key->tos;
+		fs->mask.tos = mask->tos;
+	}
+
+	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_dissector_key_vlan *key, *mask;
+		u16 vlan_tci, vlan_tci_mask;
+
+		key = skb_flow_dissector_target(cls->dissector,
+						FLOW_DISSECTOR_KEY_VLAN,
+						cls->key);
+		mask = skb_flow_dissector_target(cls->dissector,
+						 FLOW_DISSECTOR_KEY_VLAN,
+						 cls->mask);
+		vlan_tci = key->vlan_id | (key->vlan_priority <<
+					   VLAN_PRIO_SHIFT);
+		vlan_tci_mask = mask->vlan_id | (mask->vlan_priority <<
+						 VLAN_PRIO_SHIFT);
+		fs->val.ivlan = cpu_to_be16(vlan_tci);
+		fs->mask.ivlan = cpu_to_be16(vlan_tci_mask);
+
+		/* Chelsio adapters use ivlan_vld bit to match vlan packets
+		 * as 802.1Q. Also, when vlan tag is present in packets,
+		 * ethtype match is used then to match on ethtype of inner
+		 * header ie. the header following the vlan header.
+		 * So, set the ivlan_vld based on ethtype info supplied by
+		 * TC for vlan packets if its 802.1Q. And then reset the
+		 * ethtype value else, hw will try to match the supplied
+		 * ethtype value with ethtype of inner header.
+		 */
+		if (fs->val.ethtype == ETH_P_8021Q) {
+			fs->val.ivlan_vld = 1;
+			fs->mask.ivlan_vld = 1;
+			fs->val.ethtype = 0;
+			fs->mask.ethtype = 0;
+		}
+	}
+
+	/* Match only packets coming from the ingress port where this
+	 * filter will be created.
+	 */
+	fs->val.iport = netdev2pinfo(dev)->port_id;
+	fs->mask.iport = ~0;
+}
+
+static int cxgb4_validate_flow_match(struct net_device *dev,
+				     struct tc_cls_flower_offload *cls)
+{
+	u16 ethtype_mask = 0;
+	u16 ethtype_key = 0;
+
+	if (cls->dissector->used_keys &
+	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT(FLOW_DISSECTOR_KEY_IP))) {
+		netdev_warn(dev, "Unsupported key used: 0x%x\n",
+			    cls->dissector->used_keys);
+		return -EOPNOTSUPP;
+	}
+
+	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_dissector_key_basic *key =
+			skb_flow_dissector_target(cls->dissector,
+						  FLOW_DISSECTOR_KEY_BASIC,
+						  cls->key);
+		struct flow_dissector_key_basic *mask =
+			skb_flow_dissector_target(cls->dissector,
+						  FLOW_DISSECTOR_KEY_BASIC,
+						  cls->mask);
+		ethtype_key = ntohs(key->n_proto);
+		ethtype_mask = ntohs(mask->n_proto);
+	}
+
+	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) {
+		u16 eth_ip_type = ethtype_key & ethtype_mask;
+		struct flow_dissector_key_ip *mask;
+
+		if (eth_ip_type != ETH_P_IP && eth_ip_type != ETH_P_IPV6) {
+			netdev_err(dev, "IP Key supported only with IPv4/v6");
+			return -EINVAL;
+		}
+
+		mask = skb_flow_dissector_target(cls->dissector,
+						 FLOW_DISSECTOR_KEY_IP,
+						 cls->mask);
+		if (mask->ttl) {
+			netdev_warn(dev, "ttl match unsupported for offload");
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static void offload_pedit(struct ch_filter_specification *fs, u32 val, u32 mask,
+			  u8 field)
+{
+	u32 set_val = val & ~mask;
+	u32 offset = 0;
+	u8 size = 1;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(pedits); i++) {
+		if (pedits[i].field == field) {
+			offset = pedits[i].offset;
+			size = pedits[i].size;
+			break;
+		}
+	}
+	memcpy((u8 *)fs + offset, &set_val, size);
+}
+
+static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
+				u32 mask, u32 offset, u8 htype)
+{
+	switch (htype) {
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
+		switch (offset) {
+		case PEDIT_ETH_DMAC_31_0:
+			fs->newdmac = 1;
+			offload_pedit(fs, val, mask, ETH_DMAC_31_0);
+			break;
+		case PEDIT_ETH_DMAC_47_32_SMAC_15_0:
+			if (~mask & PEDIT_ETH_DMAC_MASK)
+				offload_pedit(fs, val, mask, ETH_DMAC_47_32);
+			else
+				offload_pedit(fs, val >> 16, mask >> 16,
+					      ETH_SMAC_15_0);
+			break;
+		case PEDIT_ETH_SMAC_47_16:
+			fs->newsmac = 1;
+			offload_pedit(fs, val, mask, ETH_SMAC_47_16);
+		}
+		break;
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
+		switch (offset) {
+		case PEDIT_IP4_SRC:
+			offload_pedit(fs, val, mask, IP4_SRC);
+			break;
+		case PEDIT_IP4_DST:
+			offload_pedit(fs, val, mask, IP4_DST);
+		}
+		fs->nat_mode = NAT_MODE_ALL;
+		break;
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
+		switch (offset) {
+		case PEDIT_IP6_SRC_31_0:
+			offload_pedit(fs, val, mask, IP6_SRC_31_0);
+			break;
+		case PEDIT_IP6_SRC_63_32:
+			offload_pedit(fs, val, mask, IP6_SRC_63_32);
+			break;
+		case PEDIT_IP6_SRC_95_64:
+			offload_pedit(fs, val, mask, IP6_SRC_95_64);
+			break;
+		case PEDIT_IP6_SRC_127_96:
+			offload_pedit(fs, val, mask, IP6_SRC_127_96);
+			break;
+		case PEDIT_IP6_DST_31_0:
+			offload_pedit(fs, val, mask, IP6_DST_31_0);
+			break;
+		case PEDIT_IP6_DST_63_32:
+			offload_pedit(fs, val, mask, IP6_DST_63_32);
+			break;
+		case PEDIT_IP6_DST_95_64:
+			offload_pedit(fs, val, mask, IP6_DST_95_64);
+			break;
+		case PEDIT_IP6_DST_127_96:
+			offload_pedit(fs, val, mask, IP6_DST_127_96);
+		}
+		fs->nat_mode = NAT_MODE_ALL;
+		break;
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
+		switch (offset) {
+		case PEDIT_TCP_SPORT_DPORT:
+			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
+				offload_pedit(fs, cpu_to_be32(val) >> 16,
+					      cpu_to_be32(mask) >> 16,
+					      TCP_SPORT);
+			else
+				offload_pedit(fs, cpu_to_be32(val),
+					      cpu_to_be32(mask), TCP_DPORT);
+		}
+		fs->nat_mode = NAT_MODE_ALL;
+		break;
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
+		switch (offset) {
+		case PEDIT_UDP_SPORT_DPORT:
+			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
+				offload_pedit(fs, cpu_to_be32(val) >> 16,
+					      cpu_to_be32(mask) >> 16,
+					      UDP_SPORT);
+			else
+				offload_pedit(fs, cpu_to_be32(val),
+					      cpu_to_be32(mask), UDP_DPORT);
+		}
+		fs->nat_mode = NAT_MODE_ALL;
+	}
+}
+
+static void cxgb4_process_flow_actions(struct net_device *in,
+				       struct tc_cls_flower_offload *cls,
+				       struct ch_filter_specification *fs)
+{
+	const struct tc_action *a;
+	LIST_HEAD(actions);
+
+	tcf_exts_to_list(cls->exts, &actions);
+	list_for_each_entry(a, &actions, list) {
+		if (is_tcf_gact_ok(a)) {
+			fs->action = FILTER_PASS;
+		} else if (is_tcf_gact_shot(a)) {
+			fs->action = FILTER_DROP;
+		} else if (is_tcf_mirred_egress_redirect(a)) {
+			int ifindex = tcf_mirred_ifindex(a);
+			struct net_device *out = __dev_get_by_index(dev_net(in),
+								    ifindex);
+			struct port_info *pi = netdev_priv(out);
+
+			fs->action = FILTER_SWITCH;
+			fs->eport = pi->port_id;
+		} else if (is_tcf_vlan(a)) {
+			u32 vlan_action = tcf_vlan_action(a);
+			u8 prio = tcf_vlan_push_prio(a);
+			u16 vid = tcf_vlan_push_vid(a);
+			u16 vlan_tci = (prio << VLAN_PRIO_SHIFT) | vid;
+
+			switch (vlan_action) {
+			case TCA_VLAN_ACT_POP:
+				fs->newvlan |= VLAN_REMOVE;
+				break;
+			case TCA_VLAN_ACT_PUSH:
+				fs->newvlan |= VLAN_INSERT;
+				fs->vlan = vlan_tci;
+				break;
+			case TCA_VLAN_ACT_MODIFY:
+				fs->newvlan |= VLAN_REWRITE;
+				fs->vlan = vlan_tci;
+				break;
+			default:
+				break;
+			}
+		} else if (is_tcf_pedit(a)) {
+			u32 mask, val, offset;
+			int nkeys, i;
+			u8 htype;
+
+			nkeys = tcf_pedit_nkeys(a);
+			for (i = 0; i < nkeys; i++) {
+				htype = tcf_pedit_htype(a, i);
+				mask = tcf_pedit_mask(a, i);
+				val = tcf_pedit_val(a, i);
+				offset = tcf_pedit_offset(a, i);
+
+				process_pedit_field(fs, val, mask, offset,
+						    htype);
+			}
+		}
+	}
+}
+
+static bool valid_l4_mask(u32 mask)
+{
+	u16 hi, lo;
+
+	/* Either the upper 16-bits (SPORT) OR the lower
+	 * 16-bits (DPORT) can be set, but NOT BOTH.
+	 */
+	hi = (mask >> 16) & 0xFFFF;
+	lo = mask & 0xFFFF;
+
+	return hi && lo ? false : true;
+}
+
+static bool valid_pedit_action(struct net_device *dev,
+			       const struct tc_action *a)
+{
+	u32 mask, offset;
+	u8 cmd, htype;
+	int nkeys, i;
+
+	nkeys = tcf_pedit_nkeys(a);
+	for (i = 0; i < nkeys; i++) {
+		htype = tcf_pedit_htype(a, i);
+		cmd = tcf_pedit_cmd(a, i);
+		mask = tcf_pedit_mask(a, i);
+		offset = tcf_pedit_offset(a, i);
+
+		if (cmd != TCA_PEDIT_KEY_EX_CMD_SET) {
+			netdev_err(dev, "%s: Unsupported pedit cmd\n",
+				   __func__);
+			return false;
+		}
+
+		switch (htype) {
+		case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
+			switch (offset) {
+			case PEDIT_ETH_DMAC_31_0:
+			case PEDIT_ETH_DMAC_47_32_SMAC_15_0:
+			case PEDIT_ETH_SMAC_47_16:
+				break;
+			default:
+				netdev_err(dev, "%s: Unsupported pedit field\n",
+					   __func__);
+				return false;
+			}
+			break;
+		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
+			switch (offset) {
+			case PEDIT_IP4_SRC:
+			case PEDIT_IP4_DST:
+				break;
+			default:
+				netdev_err(dev, "%s: Unsupported pedit field\n",
+					   __func__);
+				return false;
+			}
+			break;
+		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
+			switch (offset) {
+			case PEDIT_IP6_SRC_31_0:
+			case PEDIT_IP6_SRC_63_32:
+			case PEDIT_IP6_SRC_95_64:
+			case PEDIT_IP6_SRC_127_96:
+			case PEDIT_IP6_DST_31_0:
+			case PEDIT_IP6_DST_63_32:
+			case PEDIT_IP6_DST_95_64:
+			case PEDIT_IP6_DST_127_96:
+				break;
+			default:
+				netdev_err(dev, "%s: Unsupported pedit field\n",
+					   __func__);
+				return false;
+			}
+			break;
+		case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
+			switch (offset) {
+			case PEDIT_TCP_SPORT_DPORT:
+				if (!valid_l4_mask(~mask)) {
+					netdev_err(dev, "%s: Unsupported mask for TCP L4 ports\n",
+						   __func__);
+					return false;
+				}
+				break;
+			default:
+				netdev_err(dev, "%s: Unsupported pedit field\n",
+					   __func__);
+				return false;
+			}
+			break;
+		case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
+			switch (offset) {
+			case PEDIT_UDP_SPORT_DPORT:
+				if (!valid_l4_mask(~mask)) {
+					netdev_err(dev, "%s: Unsupported mask for UDP L4 ports\n",
+						   __func__);
+					return false;
+				}
+				break;
+			default:
+				netdev_err(dev, "%s: Unsupported pedit field\n",
+					   __func__);
+				return false;
+			}
+			break;
+		default:
+			netdev_err(dev, "%s: Unsupported pedit type\n",
+				   __func__);
+			return false;
+		}
+	}
+	return true;
+}
+
+static int cxgb4_validate_flow_actions(struct net_device *dev,
+				       struct tc_cls_flower_offload *cls)
+{
+	const struct tc_action *a;
+	bool act_redir = false;
+	bool act_pedit = false;
+	bool act_vlan = false;
+	LIST_HEAD(actions);
+
+	tcf_exts_to_list(cls->exts, &actions);
+	list_for_each_entry(a, &actions, list) {
+		if (is_tcf_gact_ok(a)) {
+			/* Do nothing */
+		} else if (is_tcf_gact_shot(a)) {
+			/* Do nothing */
+		} else if (is_tcf_mirred_egress_redirect(a)) {
+			struct adapter *adap = netdev2adap(dev);
+			struct net_device *n_dev;
+			unsigned int i, ifindex;
+			bool found = false;
+
+			ifindex = tcf_mirred_ifindex(a);
+			for_each_port(adap, i) {
+				n_dev = adap->port[i];
+				if (ifindex == n_dev->ifindex) {
+					found = true;
+					break;
+				}
+			}
+
+			/* If interface doesn't belong to our hw, then
+			 * the provided output port is not valid
+			 */
+			if (!found) {
+				netdev_err(dev, "%s: Out port invalid\n",
+					   __func__);
+				return -EINVAL;
+			}
+			act_redir = true;
+		} else if (is_tcf_vlan(a)) {
+			u16 proto = be16_to_cpu(tcf_vlan_push_proto(a));
+			u32 vlan_action = tcf_vlan_action(a);
+
+			switch (vlan_action) {
+			case TCA_VLAN_ACT_POP:
+				break;
+			case TCA_VLAN_ACT_PUSH:
+			case TCA_VLAN_ACT_MODIFY:
+				if (proto != ETH_P_8021Q) {
+					netdev_err(dev, "%s: Unsupported vlan proto\n",
+						   __func__);
+					return -EOPNOTSUPP;
+				}
+				break;
+			default:
+				netdev_err(dev, "%s: Unsupported vlan action\n",
+					   __func__);
+				return -EOPNOTSUPP;
+			}
+			act_vlan = true;
+		} else if (is_tcf_pedit(a)) {
+			bool pedit_valid = valid_pedit_action(dev, a);
+
+			if (!pedit_valid)
+				return -EOPNOTSUPP;
+			act_pedit = true;
+		} else {
+			netdev_err(dev, "%s: Unsupported action\n", __func__);
+			return -EOPNOTSUPP;
+		}
+	}
+
+	if ((act_pedit || act_vlan) && !act_redir) {
+		netdev_err(dev, "%s: pedit/vlan rewrite invalid without egress redirect\n",
+			   __func__);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int cxgb4_tc_flower_replace(struct net_device *dev,
+			    struct tc_cls_flower_offload *cls)
+{
+	struct adapter *adap = netdev2adap(dev);
+	struct ch_tc_flower_entry *ch_flower;
+	struct ch_filter_specification *fs;
+	struct filter_ctx ctx;
+	int fidx;
+	int ret;
+
+	if (cxgb4_validate_flow_actions(dev, cls))
+		return -EOPNOTSUPP;
+
+	if (cxgb4_validate_flow_match(dev, cls))
+		return -EOPNOTSUPP;
+
+	ch_flower = allocate_flower_entry();
+	if (!ch_flower) {
+		netdev_err(dev, "%s: ch_flower alloc failed.\n", __func__);
+		return -ENOMEM;
+	}
+
+	fs = &ch_flower->fs;
+	fs->hitcnts = 1;
+	cxgb4_process_flow_match(dev, cls, fs);
+	cxgb4_process_flow_actions(dev, cls, fs);
+
+	fs->hash = is_filter_exact_match(adap, fs);
+	if (fs->hash) {
+		fidx = 0;
+	} else {
+		fidx = cxgb4_get_free_ftid(dev, fs->type ? PF_INET6 : PF_INET);
+		if (fidx < 0) {
+			netdev_err(dev, "%s: No fidx for offload.\n", __func__);
+			ret = -ENOMEM;
+			goto free_entry;
+		}
+	}
+
+	init_completion(&ctx.completion);
+	ret = __cxgb4_set_filter(dev, fidx, fs, &ctx);
+	if (ret) {
+		netdev_err(dev, "%s: filter creation err %d\n",
+			   __func__, ret);
+		goto free_entry;
+	}
+
+	/* Wait for reply */
+	ret = wait_for_completion_timeout(&ctx.completion, 10 * HZ);
+	if (!ret) {
+		ret = -ETIMEDOUT;
+		goto free_entry;
+	}
+
+	ret = ctx.result;
+	/* Check if hw returned error for filter creation */
+	if (ret) {
+		netdev_err(dev, "%s: filter creation err %d\n",
+			   __func__, ret);
+		goto free_entry;
+	}
+
+	ch_flower->tc_flower_cookie = cls->cookie;
+	ch_flower->filter_id = ctx.tid;
+	ret = rhashtable_insert_fast(&adap->flower_tbl, &ch_flower->node,
+				     adap->flower_ht_params);
+	if (ret)
+		goto del_filter;
+
+	return 0;
+
+del_filter:
+	cxgb4_del_filter(dev, ch_flower->filter_id, &ch_flower->fs);
+
+free_entry:
+	kfree(ch_flower);
+	return ret;
+}
+
+int cxgb4_tc_flower_destroy(struct net_device *dev,
+			    struct tc_cls_flower_offload *cls)
+{
+	struct adapter *adap = netdev2adap(dev);
+	struct ch_tc_flower_entry *ch_flower;
+	int ret;
+
+	ch_flower = ch_flower_lookup(adap, cls->cookie);
+	if (!ch_flower)
+		return -ENOENT;
+
+	ret = cxgb4_del_filter(dev, ch_flower->filter_id, &ch_flower->fs);
+	if (ret)
+		goto err;
+
+	ret = rhashtable_remove_fast(&adap->flower_tbl, &ch_flower->node,
+				     adap->flower_ht_params);
+	if (ret) {
+		netdev_err(dev, "Flow remove from rhashtable failed");
+		goto err;
+	}
+	kfree_rcu(ch_flower, rcu);
+
+err:
+	return ret;
+}
+
+static void ch_flower_stats_handler(struct work_struct *work)
+{
+	struct adapter *adap = container_of(work, struct adapter,
+					    flower_stats_work);
+	struct ch_tc_flower_entry *flower_entry;
+	struct ch_tc_flower_stats *ofld_stats;
+	struct rhashtable_iter iter;
+	u64 packets;
+	u64 bytes;
+	int ret;
+
+	rhashtable_walk_enter(&adap->flower_tbl, &iter);
+	do {
+		flower_entry = ERR_PTR(rhashtable_walk_start(&iter));
+		if (IS_ERR(flower_entry))
+			goto walk_stop;
+
+		while ((flower_entry = rhashtable_walk_next(&iter)) &&
+		       !IS_ERR(flower_entry)) {
+			ret = cxgb4_get_filter_counters(adap->port[0],
+							flower_entry->filter_id,
+							&packets, &bytes,
+							flower_entry->fs.hash);
+			if (!ret) {
+				spin_lock(&flower_entry->lock);
+				ofld_stats = &flower_entry->stats;
+
+				if (ofld_stats->prev_packet_count != packets) {
+					ofld_stats->prev_packet_count = packets;
+					ofld_stats->last_used = jiffies;
+				}
+				spin_unlock(&flower_entry->lock);
+			}
+		}
+walk_stop:
+		rhashtable_walk_stop(&iter);
+	} while (flower_entry == ERR_PTR(-EAGAIN));
+	rhashtable_walk_exit(&iter);
+	mod_timer(&adap->flower_stats_timer, jiffies + STATS_CHECK_PERIOD);
+}
+
+static void ch_flower_stats_cb(struct timer_list *t)
+{
+	struct adapter *adap = from_timer(adap, t, flower_stats_timer);
+
+	schedule_work(&adap->flower_stats_work);
+}
+
+int cxgb4_tc_flower_stats(struct net_device *dev,
+			  struct tc_cls_flower_offload *cls)
+{
+	struct adapter *adap = netdev2adap(dev);
+	struct ch_tc_flower_stats *ofld_stats;
+	struct ch_tc_flower_entry *ch_flower;
+	u64 packets;
+	u64 bytes;
+	int ret;
+
+	ch_flower = ch_flower_lookup(adap, cls->cookie);
+	if (!ch_flower) {
+		ret = -ENOENT;
+		goto err;
+	}
+
+	ret = cxgb4_get_filter_counters(dev, ch_flower->filter_id,
+					&packets, &bytes,
+					ch_flower->fs.hash);
+	if (ret < 0)
+		goto err;
+
+	spin_lock_bh(&ch_flower->lock);
+	ofld_stats = &ch_flower->stats;
+	if (ofld_stats->packet_count != packets) {
+		if (ofld_stats->prev_packet_count != packets)
+			ofld_stats->last_used = jiffies;
+		tcf_exts_stats_update(cls->exts, bytes - ofld_stats->byte_count,
+				      packets - ofld_stats->packet_count,
+				      ofld_stats->last_used);
+
+		ofld_stats->packet_count = packets;
+		ofld_stats->byte_count = bytes;
+		ofld_stats->prev_packet_count = packets;
+	}
+	spin_unlock_bh(&ch_flower->lock);
+	return 0;
+
+err:
+	return ret;
+}
+
+static const struct rhashtable_params cxgb4_tc_flower_ht_params = {
+	.nelem_hint = 384,
+	.head_offset = offsetof(struct ch_tc_flower_entry, node),
+	.key_offset = offsetof(struct ch_tc_flower_entry, tc_flower_cookie),
+	.key_len = sizeof(((struct ch_tc_flower_entry *)0)->tc_flower_cookie),
+	.max_size = 524288,
+	.min_size = 512,
+	.automatic_shrinking = true
+};
+
+int cxgb4_init_tc_flower(struct adapter *adap)
+{
+	int ret;
+
+	adap->flower_ht_params = cxgb4_tc_flower_ht_params;
+	ret = rhashtable_init(&adap->flower_tbl, &adap->flower_ht_params);
+	if (ret)
+		return ret;
+
+	INIT_WORK(&adap->flower_stats_work, ch_flower_stats_handler);
+	timer_setup(&adap->flower_stats_timer, ch_flower_stats_cb, 0);
+	mod_timer(&adap->flower_stats_timer, jiffies + STATS_CHECK_PERIOD);
+	return 0;
+}
+
+void cxgb4_cleanup_tc_flower(struct adapter *adap)
+{
+	if (adap->flower_stats_timer.function)
+		del_timer_sync(&adap->flower_stats_timer);
+	cancel_work_sync(&adap->flower_stats_work);
+	rhashtable_destroy(&adap->flower_tbl);
+}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h
new file mode 100644
index 000000000000..050c8a50ae41
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h
@@ -0,0 +1,120 @@
+/*
+ * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux.
+ *
+ * Copyright (c) 2017 Chelsio Communications, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __CXGB4_TC_FLOWER_H
+#define __CXGB4_TC_FLOWER_H
+
+#include <net/pkt_cls.h>
+
+struct ch_tc_flower_stats {
+	u64 prev_packet_count;
+	u64 packet_count;
+	u64 byte_count;
+	u64 last_used;
+};
+
+struct ch_tc_flower_entry {
+	struct ch_filter_specification fs;
+	struct ch_tc_flower_stats stats;
+	unsigned long tc_flower_cookie;
+	struct rhash_head node;
+	struct rcu_head rcu;
+	spinlock_t lock; /* lock for stats */
+	u32 filter_id;
+};
+
+enum {
+	ETH_DMAC_31_0,	/* dmac bits 0.. 31 */
+	ETH_DMAC_47_32,	/* dmac bits 32..47 */
+	ETH_SMAC_15_0,	/* smac bits 0.. 15 */
+	ETH_SMAC_47_16,	/* smac bits 16..47 */
+
+	IP4_SRC,	/* 32-bit IPv4 src  */
+	IP4_DST,	/* 32-bit IPv4 dst  */
+
+	IP6_SRC_31_0,	/* src bits 0..  31 */
+	IP6_SRC_63_32,	/* src bits 63.. 32 */
+	IP6_SRC_95_64,	/* src bits 95.. 64 */
+	IP6_SRC_127_96,	/* src bits 127..96 */
+
+	IP6_DST_31_0,	/* dst bits 0..  31 */
+	IP6_DST_63_32,	/* dst bits 63.. 32 */
+	IP6_DST_95_64,	/* dst bits 95.. 64 */
+	IP6_DST_127_96,	/* dst bits 127..96 */
+
+	TCP_SPORT,	/* 16-bit TCP sport */
+	TCP_DPORT,	/* 16-bit TCP dport */
+
+	UDP_SPORT,	/* 16-bit UDP sport */
+	UDP_DPORT,	/* 16-bit UDP dport */
+};
+
+struct ch_tc_pedit_fields {
+	u8 field;
+	u8 size;
+	u32 offset;
+};
+
+#define PEDIT_FIELDS(type, field, size, fs_field, offset) \
+	{ type## field, size, \
+		offsetof(struct ch_filter_specification, fs_field) + (offset) }
+
+#define PEDIT_ETH_DMAC_MASK		0xffff
+#define PEDIT_TCP_UDP_SPORT_MASK	0xffff
+#define PEDIT_ETH_DMAC_31_0		0x0
+#define PEDIT_ETH_DMAC_47_32_SMAC_15_0	0x4
+#define PEDIT_ETH_SMAC_47_16		0x8
+#define PEDIT_IP4_SRC			0xC
+#define PEDIT_IP4_DST			0x10
+#define PEDIT_IP6_SRC_31_0		0x8
+#define PEDIT_IP6_SRC_63_32		0xC
+#define PEDIT_IP6_SRC_95_64		0x10
+#define PEDIT_IP6_SRC_127_96		0x14
+#define PEDIT_IP6_DST_31_0		0x18
+#define PEDIT_IP6_DST_63_32		0x1C
+#define PEDIT_IP6_DST_95_64		0x20
+#define PEDIT_IP6_DST_127_96		0x24
+#define PEDIT_TCP_SPORT_DPORT		0x0
+#define PEDIT_UDP_SPORT_DPORT		0x0
+
+int cxgb4_tc_flower_replace(struct net_device *dev,
+			    struct tc_cls_flower_offload *cls);
+int cxgb4_tc_flower_destroy(struct net_device *dev,
+			    struct tc_cls_flower_offload *cls);
+int cxgb4_tc_flower_stats(struct net_device *dev,
+			  struct tc_cls_flower_offload *cls);
+
+int cxgb4_init_tc_flower(struct adapter *adap);
+void cxgb4_cleanup_tc_flower(struct adapter *adap);
+#endif /* __CXGB4_TC_FLOWER_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
index 48970ba08bdc..cd0cd13a964d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
@@ -380,7 +380,7 @@ int cxgb4_delete_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 			return -EINVAL;
 	}
 
-	ret = cxgb4_del_filter(dev, filter_id);
+	ret = cxgb4_del_filter(dev, filter_id, NULL);
 	if (ret)
 		goto out;
 
@@ -399,7 +399,7 @@ int cxgb4_delete_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 				if (!test_bit(j, link->tid_map))
 					continue;
 
-				ret = __cxgb4_del_filter(dev, j, NULL);
+				ret = __cxgb4_del_filter(dev, j, NULL, NULL);
 				if (ret)
 					goto out;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 84541fce94c5..08e709ab6dd4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -212,14 +212,19 @@ struct filter_ctx {
 
 struct ch_filter_specification;
 
+int cxgb4_get_free_ftid(struct net_device *dev, int family);
 int __cxgb4_set_filter(struct net_device *dev, int filter_id,
 		       struct ch_filter_specification *fs,
 		       struct filter_ctx *ctx);
 int __cxgb4_del_filter(struct net_device *dev, int filter_id,
+		       struct ch_filter_specification *fs,
 		       struct filter_ctx *ctx);
 int cxgb4_set_filter(struct net_device *dev, int filter_id,
 		     struct ch_filter_specification *fs);
-int cxgb4_del_filter(struct net_device *dev, int filter_id);
+int cxgb4_del_filter(struct net_device *dev, int filter_id,
+		     struct ch_filter_specification *fs);
+int cxgb4_get_filter_counters(struct net_device *dev, unsigned int fidx,
+			      u64 *hitcnt, u64 *bytecnt, bool hash);
 
 static inline void set_wr_txq(struct sk_buff *skb, int prio, int queue)
 {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index f7ef8871dd0b..1817a0307d26 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -422,7 +422,7 @@ struct l2t_entry *cxgb4_l2t_get(struct l2t_data *d, struct neighbour *neigh,
 	u8 lport;
 	u16 vlan;
 	struct l2t_entry *e;
-	int addr_len = neigh->tbl->key_len;
+	unsigned int addr_len = neigh->tbl->key_len;
 	u32 *addr = (u32 *)neigh->primary_key;
 	int ifidx = neigh->dev->ifindex;
 	int hash = addr_hash(d, addr, addr_len, ifidx);
@@ -536,7 +536,7 @@ void t4_l2t_update(struct adapter *adap, struct neighbour *neigh)
 	struct l2t_entry *e;
 	struct sk_buff_head *arpq = NULL;
 	struct l2t_data *d = adap->l2t;
-	int addr_len = neigh->tbl->key_len;
+	unsigned int addr_len = neigh->tbl->key_len;
 	u32 *addr = (u32 *) neigh->primary_key;
 	int ifidx = neigh->dev->ifindex;
 	int hash = addr_hash(d, addr, addr_len, ifidx);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 4ef68f69b58c..486b01fe23bd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2583,11 +2583,11 @@ irq_handler_t t4_intr_handler(struct adapter *adap)
 	return t4_intr_intx;
 }
 
-static void sge_rx_timer_cb(unsigned long data)
+static void sge_rx_timer_cb(struct timer_list *t)
 {
 	unsigned long m;
 	unsigned int i;
-	struct adapter *adap = (struct adapter *)data;
+	struct adapter *adap = from_timer(adap, t, sge.rx_timer);
 	struct sge *s = &adap->sge;
 
 	for (i = 0; i < BITS_TO_LONGS(s->egr_sz); i++)
@@ -2620,11 +2620,11 @@ done:
 	mod_timer(&s->rx_timer, jiffies + RX_QCHECK_PERIOD);
 }
 
-static void sge_tx_timer_cb(unsigned long data)
+static void sge_tx_timer_cb(struct timer_list *t)
 {
 	unsigned long m;
 	unsigned int i, budget;
-	struct adapter *adap = (struct adapter *)data;
+	struct adapter *adap = from_timer(adap, t, sge.tx_timer);
 	struct sge *s = &adap->sge;
 
 	for (i = 0; i < BITS_TO_LONGS(s->egr_sz); i++)
@@ -3458,8 +3458,8 @@ int t4_sge_init(struct adapter *adap)
 	/* Set up timers used for recuring callbacks to process RX and TX
 	 * administrative tasks.
 	 */
-	setup_timer(&s->rx_timer, sge_rx_timer_cb, (unsigned long)adap);
-	setup_timer(&s->tx_timer, sge_tx_timer_cb, (unsigned long)adap);
+	timer_setup(&s->rx_timer, sge_rx_timer_cb, 0);
+	timer_setup(&s->tx_timer, sge_tx_timer_cb, 0);
 
 	spin_lock_init(&s->intrq_lock);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.c b/drivers/net/ethernet/chelsio/cxgb4/smt.c
new file mode 100644
index 000000000000..7b2207a2a130
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/smt.c
@@ -0,0 +1,247 @@
+/*
+ * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux.
+ *
+ * Copyright (c) 2017 Chelsio Communications, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "cxgb4.h"
+#include "smt.h"
+#include "t4_msg.h"
+#include "t4fw_api.h"
+#include "t4_regs.h"
+#include "t4_values.h"
+
+struct smt_data *t4_init_smt(void)
+{
+	unsigned int smt_size;
+	struct smt_data *s;
+	int i;
+
+	smt_size = SMT_SIZE;
+
+	s = kvzalloc(sizeof(*s) + smt_size * sizeof(struct smt_entry),
+		     GFP_KERNEL);
+	if (!s)
+		return NULL;
+	s->smt_size = smt_size;
+	rwlock_init(&s->lock);
+	for (i = 0; i < s->smt_size; ++i) {
+		s->smtab[i].idx = i;
+		s->smtab[i].state = SMT_STATE_UNUSED;
+		memset(&s->smtab[i].src_mac, 0, ETH_ALEN);
+		spin_lock_init(&s->smtab[i].lock);
+		atomic_set(&s->smtab[i].refcnt, 0);
+	}
+	return s;
+}
+
+static struct smt_entry *find_or_alloc_smte(struct smt_data *s, u8 *smac)
+{
+	struct smt_entry *first_free = NULL;
+	struct smt_entry *e, *end;
+
+	for (e = &s->smtab[0], end = &s->smtab[s->smt_size]; e != end; ++e) {
+		if (atomic_read(&e->refcnt) == 0) {
+			if (!first_free)
+				first_free = e;
+		} else {
+			if (e->state == SMT_STATE_SWITCHING) {
+				/* This entry is actually in use. See if we can
+				 * re-use it ?
+				 */
+				if (memcmp(e->src_mac, smac, ETH_ALEN) == 0)
+					goto found_reuse;
+			}
+		}
+	}
+
+	if (first_free) {
+		e = first_free;
+		goto found;
+	}
+	return NULL;
+
+found:
+	e->state = SMT_STATE_UNUSED;
+
+found_reuse:
+	return e;
+}
+
+static void t4_smte_free(struct smt_entry *e)
+{
+	spin_lock_bh(&e->lock);
+	if (atomic_read(&e->refcnt) == 0) {  /* hasn't been recycled */
+		e->state = SMT_STATE_UNUSED;
+	}
+	spin_unlock_bh(&e->lock);
+}
+
+/**
+ * @e: smt entry to release
+ *
+ * Releases ref count and frees up an smt entry from SMT table
+ */
+void cxgb4_smt_release(struct smt_entry *e)
+{
+	if (atomic_dec_and_test(&e->refcnt))
+		t4_smte_free(e);
+}
+EXPORT_SYMBOL(cxgb4_smt_release);
+
+void do_smt_write_rpl(struct adapter *adap, const struct cpl_smt_write_rpl *rpl)
+{
+	unsigned int smtidx = TID_TID_G(GET_TID(rpl));
+	struct smt_data *s = adap->smt;
+
+	if (unlikely(rpl->status != CPL_ERR_NONE)) {
+		struct smt_entry *e = &s->smtab[smtidx];
+
+		dev_err(adap->pdev_dev,
+			"Unexpected SMT_WRITE_RPL status %u for entry %u\n",
+			rpl->status, smtidx);
+		spin_lock(&e->lock);
+		e->state = SMT_STATE_ERROR;
+		spin_unlock(&e->lock);
+		return;
+	}
+}
+
+static int write_smt_entry(struct adapter *adapter, struct smt_entry *e)
+{
+	struct cpl_t6_smt_write_req *t6req;
+	struct smt_data *s = adapter->smt;
+	struct cpl_smt_write_req *req;
+	struct sk_buff *skb;
+	int size;
+	u8 row;
+
+	if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) {
+		size = sizeof(*req);
+		skb = alloc_skb(size, GFP_ATOMIC);
+		if (!skb)
+			return -ENOMEM;
+		/* Source MAC Table (SMT) contains 256 SMAC entries
+		 * organized in 128 rows of 2 entries each.
+		 */
+		req = (struct cpl_smt_write_req *)__skb_put(skb, size);
+		INIT_TP_WR(req, 0);
+
+		/* Each row contains an SMAC pair.
+		 * LSB selects the SMAC entry within a row
+		 */
+		row = (e->idx >> 1);
+		if (e->idx & 1) {
+			req->pfvf1 = 0x0;
+			memcpy(req->src_mac1, e->src_mac, ETH_ALEN);
+
+			/* fill pfvf0/src_mac0 with entry
+			 * at prev index from smt-tab.
+			 */
+			req->pfvf0 = 0x0;
+			memcpy(req->src_mac0, s->smtab[e->idx - 1].src_mac,
+			       ETH_ALEN);
+		} else {
+			req->pfvf0 = 0x0;
+			memcpy(req->src_mac0, e->src_mac, ETH_ALEN);
+
+			/* fill pfvf1/src_mac1 with entry
+			 * at next index from smt-tab
+			 */
+			req->pfvf1 = 0x0;
+			memcpy(req->src_mac1, s->smtab[e->idx + 1].src_mac,
+			       ETH_ALEN);
+		}
+	} else {
+		size = sizeof(*t6req);
+		skb = alloc_skb(size, GFP_ATOMIC);
+		if (!skb)
+			return -ENOMEM;
+		/* Source MAC Table (SMT) contains 256 SMAC entries */
+		t6req = (struct cpl_t6_smt_write_req *)__skb_put(skb, size);
+		INIT_TP_WR(t6req, 0);
+		req = (struct cpl_smt_write_req *)t6req;
+
+		/* fill pfvf0/src_mac0 from smt-tab */
+		req->pfvf0 = 0x0;
+		memcpy(req->src_mac0, s->smtab[e->idx].src_mac, ETH_ALEN);
+		row = e->idx;
+	}
+
+	OPCODE_TID(req) =
+		htonl(MK_OPCODE_TID(CPL_SMT_WRITE_REQ, e->idx |
+				    TID_QID_V(adapter->sge.fw_evtq.abs_id)));
+	req->params = htonl(SMTW_NORPL_V(0) |
+			    SMTW_IDX_V(row) |
+			    SMTW_OVLAN_IDX_V(0));
+	t4_mgmt_tx(adapter, skb);
+	return 0;
+}
+
+static struct smt_entry *t4_smt_alloc_switching(struct adapter *adap, u16 pfvf,
+						u8 *smac)
+{
+	struct smt_data *s = adap->smt;
+	struct smt_entry *e;
+
+	write_lock_bh(&s->lock);
+	e = find_or_alloc_smte(s, smac);
+	if (e) {
+		spin_lock(&e->lock);
+		if (!atomic_read(&e->refcnt)) {
+			atomic_set(&e->refcnt, 1);
+			e->state = SMT_STATE_SWITCHING;
+			e->pfvf = pfvf;
+			memcpy(e->src_mac, smac, ETH_ALEN);
+			write_smt_entry(adap, e);
+		} else {
+			atomic_inc(&e->refcnt);
+		}
+		spin_unlock(&e->lock);
+	}
+	write_unlock_bh(&s->lock);
+	return e;
+}
+
+/**
+ * @dev: net_device pointer
+ * @smac: MAC address to add to SMT
+ * Returns pointer to the SMT entry created
+ *
+ * Allocates an SMT entry to be used by switching rule of a filter.
+ */
+struct smt_entry *cxgb4_smt_alloc_switching(struct net_device *dev, u8 *smac)
+{
+	struct adapter *adap = netdev2adap(dev);
+
+	return t4_smt_alloc_switching(adap, 0x0, smac);
+}
+EXPORT_SYMBOL(cxgb4_smt_alloc_switching);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.h b/drivers/net/ethernet/chelsio/cxgb4/smt.h
new file mode 100644
index 000000000000..d6c2cc271398
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/smt.h
@@ -0,0 +1,76 @@
+/*
+ * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux.
+ *
+ * Copyright (c) 2017 Chelsio Communications, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __CXGB4_SMT_H
+#define __CXGB4_SMT_H
+
+#include <linux/spinlock.h>
+#include <linux/if_ether.h>
+#include <linux/atomic.h>
+
+struct adapter;
+struct cpl_smt_write_rpl;
+
+/* SMT related handling. Heavily adapted based on l2t ops in l2t.h/l2t.c
+ */
+enum {
+	SMT_STATE_SWITCHING,
+	SMT_STATE_UNUSED,
+	SMT_STATE_ERROR
+};
+
+enum {
+	SMT_SIZE = 256
+};
+
+struct smt_entry {
+	u16 state;
+	u16 idx;
+	u16 pfvf;
+	u8 src_mac[ETH_ALEN];
+	atomic_t refcnt;
+	spinlock_t lock;	/* protect smt entry add,removal */
+};
+
+struct smt_data {
+	unsigned int smt_size;
+	rwlock_t lock;
+	struct smt_entry smtab[0];
+};
+
+struct smt_data *t4_init_smt(void);
+struct smt_entry *cxgb4_smt_alloc_switching(struct net_device *dev, u8 *smac);
+void cxgb4_smt_release(struct smt_entry *e);
+void do_smt_write_rpl(struct adapter *p, const struct cpl_smt_write_rpl *rpl);
+#endif /* __CXGB4_SMT_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index b65ce26ff72f..efe9d3a20135 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -5052,23 +5052,26 @@ static unsigned int t4_use_ldst(struct adapter *adap)
 }
 
 /**
- *	t4_fw_tp_pio_rw - Access TP PIO through LDST
- *	@adap: the adapter
- *	@vals: where the indirect register values are stored/written
- *	@nregs: how many indirect registers to read/write
- *	@start_idx: index of first indirect register to read/write
- *	@rw: Read (1) or Write (0)
+ * t4_tp_fw_ldst_rw - Access TP indirect register through LDST
+ * @adap: the adapter
+ * @cmd: TP fw ldst address space type
+ * @vals: where the indirect register values are stored/written
+ * @nregs: how many indirect registers to read/write
+ * @start_idx: index of first indirect register to read/write
+ * @rw: Read (1) or Write (0)
+ * @sleep_ok: if true we may sleep while awaiting command completion
  *
- *	Access TP PIO registers through LDST
+ * Access TP indirect registers through LDST
  */
-static void t4_fw_tp_pio_rw(struct adapter *adap, u32 *vals, unsigned int nregs,
-			    unsigned int start_index, unsigned int rw)
+static int t4_tp_fw_ldst_rw(struct adapter *adap, int cmd, u32 *vals,
+			    unsigned int nregs, unsigned int start_index,
+			    unsigned int rw, bool sleep_ok)
 {
-	int ret, i;
-	int cmd = FW_LDST_ADDRSPC_TP_PIO;
+	int ret = 0;
+	unsigned int i;
 	struct fw_ldst_cmd c;
 
-	for (i = 0 ; i < nregs; i++) {
+	for (i = 0; i < nregs; i++) {
 		memset(&c, 0, sizeof(c));
 		c.op_to_addrspace = cpu_to_be32(FW_CMD_OP_V(FW_LDST_CMD) |
 						FW_CMD_REQUEST_F |
@@ -5079,26 +5082,147 @@ static void t4_fw_tp_pio_rw(struct adapter *adap, u32 *vals, unsigned int nregs,
 
 		c.u.addrval.addr = cpu_to_be32(start_index + i);
 		c.u.addrval.val  = rw ? 0 : cpu_to_be32(vals[i]);
-		ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c);
-		if (!ret && rw)
+		ret = t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c,
+				      sleep_ok);
+		if (ret)
+			return ret;
+
+		if (rw)
 			vals[i] = be32_to_cpu(c.u.addrval.val);
 	}
+	return 0;
+}
+
+/**
+ * t4_tp_indirect_rw - Read/Write TP indirect register through LDST or backdoor
+ * @adap: the adapter
+ * @reg_addr: Address Register
+ * @reg_data: Data register
+ * @buff: where the indirect register values are stored/written
+ * @nregs: how many indirect registers to read/write
+ * @start_index: index of first indirect register to read/write
+ * @rw: READ(1) or WRITE(0)
+ * @sleep_ok: if true we may sleep while awaiting command completion
+ *
+ * Read/Write TP indirect registers through LDST if possible.
+ * Else, use backdoor access
+ **/
+static void t4_tp_indirect_rw(struct adapter *adap, u32 reg_addr, u32 reg_data,
+			      u32 *buff, u32 nregs, u32 start_index, int rw,
+			      bool sleep_ok)
+{
+	int rc = -EINVAL;
+	int cmd;
+
+	switch (reg_addr) {
+	case TP_PIO_ADDR_A:
+		cmd = FW_LDST_ADDRSPC_TP_PIO;
+		break;
+	case TP_TM_PIO_ADDR_A:
+		cmd = FW_LDST_ADDRSPC_TP_TM_PIO;
+		break;
+	case TP_MIB_INDEX_A:
+		cmd = FW_LDST_ADDRSPC_TP_MIB;
+		break;
+	default:
+		goto indirect_access;
+	}
+
+	if (t4_use_ldst(adap))
+		rc = t4_tp_fw_ldst_rw(adap, cmd, buff, nregs, start_index, rw,
+				      sleep_ok);
+
+indirect_access:
+
+	if (rc) {
+		if (rw)
+			t4_read_indirect(adap, reg_addr, reg_data, buff, nregs,
+					 start_index);
+		else
+			t4_write_indirect(adap, reg_addr, reg_data, buff, nregs,
+					  start_index);
+	}
+}
+
+/**
+ * t4_tp_pio_read - Read TP PIO registers
+ * @adap: the adapter
+ * @buff: where the indirect register values are written
+ * @nregs: how many indirect registers to read
+ * @start_index: index of first indirect register to read
+ * @sleep_ok: if true we may sleep while awaiting command completion
+ *
+ * Read TP PIO Registers
+ **/
+void t4_tp_pio_read(struct adapter *adap, u32 *buff, u32 nregs,
+		    u32 start_index, bool sleep_ok)
+{
+	t4_tp_indirect_rw(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, buff, nregs,
+			  start_index, 1, sleep_ok);
+}
+
+/**
+ * t4_tp_pio_write - Write TP PIO registers
+ * @adap: the adapter
+ * @buff: where the indirect register values are stored
+ * @nregs: how many indirect registers to write
+ * @start_index: index of first indirect register to write
+ * @sleep_ok: if true we may sleep while awaiting command completion
+ *
+ * Write TP PIO Registers
+ **/
+static void t4_tp_pio_write(struct adapter *adap, u32 *buff, u32 nregs,
+			    u32 start_index, bool sleep_ok)
+{
+	t4_tp_indirect_rw(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, buff, nregs,
+			  start_index, 0, sleep_ok);
+}
+
+/**
+ * t4_tp_tm_pio_read - Read TP TM PIO registers
+ * @adap: the adapter
+ * @buff: where the indirect register values are written
+ * @nregs: how many indirect registers to read
+ * @start_index: index of first indirect register to read
+ * @sleep_ok: if true we may sleep while awaiting command completion
+ *
+ * Read TP TM PIO Registers
+ **/
+void t4_tp_tm_pio_read(struct adapter *adap, u32 *buff, u32 nregs,
+		       u32 start_index, bool sleep_ok)
+{
+	t4_tp_indirect_rw(adap, TP_TM_PIO_ADDR_A, TP_TM_PIO_DATA_A, buff,
+			  nregs, start_index, 1, sleep_ok);
+}
+
+/**
+ * t4_tp_mib_read - Read TP MIB registers
+ * @adap: the adapter
+ * @buff: where the indirect register values are written
+ * @nregs: how many indirect registers to read
+ * @start_index: index of first indirect register to read
+ * @sleep_ok: if true we may sleep while awaiting command completion
+ *
+ * Read TP MIB Registers
+ **/
+void t4_tp_mib_read(struct adapter *adap, u32 *buff, u32 nregs, u32 start_index,
+		    bool sleep_ok)
+{
+	t4_tp_indirect_rw(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, buff, nregs,
+			  start_index, 1, sleep_ok);
 }
 
 /**
  *	t4_read_rss_key - read the global RSS key
  *	@adap: the adapter
  *	@key: 10-entry array holding the 320-bit RSS key
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *	Reads the global 320-bit RSS key.
  */
-void t4_read_rss_key(struct adapter *adap, u32 *key)
+void t4_read_rss_key(struct adapter *adap, u32 *key, bool sleep_ok)
 {
-	if (t4_use_ldst(adap))
-		t4_fw_tp_pio_rw(adap, key, 10, TP_RSS_SECRET_KEY0_A, 1);
-	else
-		t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10,
-				 TP_RSS_SECRET_KEY0_A);
+	t4_tp_pio_read(adap, key, 10, TP_RSS_SECRET_KEY0_A, sleep_ok);
 }
 
 /**
@@ -5106,12 +5230,14 @@ void t4_read_rss_key(struct adapter *adap, u32 *key)
  *	@adap: the adapter
  *	@key: 10-entry array holding the 320-bit RSS key
  *	@idx: which RSS key to write
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *	Writes one of the RSS keys with the given 320-bit value.  If @idx is
  *	0..15 the corresponding entry in the RSS key table is written,
  *	otherwise the global RSS key is written.
  */
-void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx)
+void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx,
+		      bool sleep_ok)
 {
 	u8 rss_key_addr_cnt = 16;
 	u32 vrt = t4_read_reg(adap, TP_RSS_CONFIG_VRT_A);
@@ -5124,11 +5250,7 @@ void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx)
 	    (vrt & KEYEXTEND_F) && (KEYMODE_G(vrt) == 3))
 		rss_key_addr_cnt = 32;
 
-	if (t4_use_ldst(adap))
-		t4_fw_tp_pio_rw(adap, (void *)key, 10, TP_RSS_SECRET_KEY0_A, 0);
-	else
-		t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10,
-				  TP_RSS_SECRET_KEY0_A);
+	t4_tp_pio_write(adap, (void *)key, 10, TP_RSS_SECRET_KEY0_A, sleep_ok);
 
 	if (idx >= 0 && idx < rss_key_addr_cnt) {
 		if (rss_key_addr_cnt > 16)
@@ -5146,19 +5268,15 @@ void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx)
  *	@adapter: the adapter
  *	@index: the entry in the PF RSS table to read
  *	@valp: where to store the returned value
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *	Reads the PF RSS Configuration Table at the specified index and returns
  *	the value found there.
  */
 void t4_read_rss_pf_config(struct adapter *adapter, unsigned int index,
-			   u32 *valp)
+			   u32 *valp, bool sleep_ok)
 {
-	if (t4_use_ldst(adapter))
-		t4_fw_tp_pio_rw(adapter, valp, 1,
-				TP_RSS_PF0_CONFIG_A + index, 1);
-	else
-		t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-				 valp, 1, TP_RSS_PF0_CONFIG_A + index);
+	t4_tp_pio_read(adapter, valp, 1, TP_RSS_PF0_CONFIG_A + index, sleep_ok);
 }
 
 /**
@@ -5167,12 +5285,13 @@ void t4_read_rss_pf_config(struct adapter *adapter, unsigned int index,
  *	@index: the entry in the VF RSS table to read
  *	@vfl: where to store the returned VFL
  *	@vfh: where to store the returned VFH
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *	Reads the VF RSS Configuration Table at the specified index and returns
  *	the (VFL, VFH) values found there.
  */
 void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index,
-			   u32 *vfl, u32 *vfh)
+			   u32 *vfl, u32 *vfh, bool sleep_ok)
 {
 	u32 vrt, mask, data;
 
@@ -5193,50 +5312,37 @@ void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index,
 
 	/* Grab the VFL/VFH values ...
 	 */
-	if (t4_use_ldst(adapter)) {
-		t4_fw_tp_pio_rw(adapter, vfl, 1, TP_RSS_VFL_CONFIG_A, 1);
-		t4_fw_tp_pio_rw(adapter, vfh, 1, TP_RSS_VFH_CONFIG_A, 1);
-	} else {
-		t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-				 vfl, 1, TP_RSS_VFL_CONFIG_A);
-		t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-				 vfh, 1, TP_RSS_VFH_CONFIG_A);
-	}
+	t4_tp_pio_read(adapter, vfl, 1, TP_RSS_VFL_CONFIG_A, sleep_ok);
+	t4_tp_pio_read(adapter, vfh, 1, TP_RSS_VFH_CONFIG_A, sleep_ok);
 }
 
 /**
  *	t4_read_rss_pf_map - read PF RSS Map
  *	@adapter: the adapter
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *	Reads the PF RSS Map register and returns its value.
  */
-u32 t4_read_rss_pf_map(struct adapter *adapter)
+u32 t4_read_rss_pf_map(struct adapter *adapter, bool sleep_ok)
 {
 	u32 pfmap;
 
-	if (t4_use_ldst(adapter))
-		t4_fw_tp_pio_rw(adapter, &pfmap, 1, TP_RSS_PF_MAP_A, 1);
-	else
-		t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-				 &pfmap, 1, TP_RSS_PF_MAP_A);
+	t4_tp_pio_read(adapter, &pfmap, 1, TP_RSS_PF_MAP_A, sleep_ok);
 	return pfmap;
 }
 
 /**
  *	t4_read_rss_pf_mask - read PF RSS Mask
  *	@adapter: the adapter
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *	Reads the PF RSS Mask register and returns its value.
  */
-u32 t4_read_rss_pf_mask(struct adapter *adapter)
+u32 t4_read_rss_pf_mask(struct adapter *adapter, bool sleep_ok)
 {
 	u32 pfmask;
 
-	if (t4_use_ldst(adapter))
-		t4_fw_tp_pio_rw(adapter, &pfmask, 1, TP_RSS_PF_MSK_A, 1);
-	else
-		t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-				 &pfmask, 1, TP_RSS_PF_MSK_A);
+	t4_tp_pio_read(adapter, &pfmask, 1, TP_RSS_PF_MSK_A, sleep_ok);
 	return pfmask;
 }
 
@@ -5245,12 +5351,13 @@ u32 t4_read_rss_pf_mask(struct adapter *adapter)
  *	@adap: the adapter
  *	@v4: holds the TCP/IP counter values
  *	@v6: holds the TCP/IPv6 counter values
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *	Returns the values of TP's TCP/IP and TCP/IPv6 MIB counters.
  *	Either @v4 or @v6 may be %NULL to skip the corresponding stats.
  */
 void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4,
-			 struct tp_tcp_stats *v6)
+			 struct tp_tcp_stats *v6, bool sleep_ok)
 {
 	u32 val[TP_MIB_TCP_RXT_SEG_LO_A - TP_MIB_TCP_OUT_RST_A + 1];
 
@@ -5259,16 +5366,16 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4,
 #define STAT64(x)   (((u64)STAT(x##_HI) << 32) | STAT(x##_LO))
 
 	if (v4) {
-		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val,
-				 ARRAY_SIZE(val), TP_MIB_TCP_OUT_RST_A);
+		t4_tp_mib_read(adap, val, ARRAY_SIZE(val),
+			       TP_MIB_TCP_OUT_RST_A, sleep_ok);
 		v4->tcp_out_rsts = STAT(OUT_RST);
 		v4->tcp_in_segs  = STAT64(IN_SEG);
 		v4->tcp_out_segs = STAT64(OUT_SEG);
 		v4->tcp_retrans_segs = STAT64(RXT_SEG);
 	}
 	if (v6) {
-		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val,
-				 ARRAY_SIZE(val), TP_MIB_TCP_V6OUT_RST_A);
+		t4_tp_mib_read(adap, val, ARRAY_SIZE(val),
+			       TP_MIB_TCP_V6OUT_RST_A, sleep_ok);
 		v6->tcp_out_rsts = STAT(OUT_RST);
 		v6->tcp_in_segs  = STAT64(IN_SEG);
 		v6->tcp_out_segs = STAT64(OUT_SEG);
@@ -5283,63 +5390,66 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4,
  *	t4_tp_get_err_stats - read TP's error MIB counters
  *	@adap: the adapter
  *	@st: holds the counter values
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *	Returns the values of TP's error counters.
  */
-void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st)
+void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st,
+			 bool sleep_ok)
 {
 	int nchan = adap->params.arch.nchan;
 
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
-			 st->mac_in_errs, nchan, TP_MIB_MAC_IN_ERR_0_A);
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
-			 st->hdr_in_errs, nchan, TP_MIB_HDR_IN_ERR_0_A);
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
-			 st->tcp_in_errs, nchan, TP_MIB_TCP_IN_ERR_0_A);
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
-			 st->tnl_cong_drops, nchan, TP_MIB_TNL_CNG_DROP_0_A);
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
-			 st->ofld_chan_drops, nchan, TP_MIB_OFD_CHN_DROP_0_A);
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
-			 st->tnl_tx_drops, nchan, TP_MIB_TNL_DROP_0_A);
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
-			 st->ofld_vlan_drops, nchan, TP_MIB_OFD_VLN_DROP_0_A);
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
-			 st->tcp6_in_errs, nchan, TP_MIB_TCP_V6IN_ERR_0_A);
-
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
-			 &st->ofld_no_neigh, 2, TP_MIB_OFD_ARP_DROP_A);
+	t4_tp_mib_read(adap, st->mac_in_errs, nchan, TP_MIB_MAC_IN_ERR_0_A,
+		       sleep_ok);
+	t4_tp_mib_read(adap, st->hdr_in_errs, nchan, TP_MIB_HDR_IN_ERR_0_A,
+		       sleep_ok);
+	t4_tp_mib_read(adap, st->tcp_in_errs, nchan, TP_MIB_TCP_IN_ERR_0_A,
+		       sleep_ok);
+	t4_tp_mib_read(adap, st->tnl_cong_drops, nchan,
+		       TP_MIB_TNL_CNG_DROP_0_A, sleep_ok);
+	t4_tp_mib_read(adap, st->ofld_chan_drops, nchan,
+		       TP_MIB_OFD_CHN_DROP_0_A, sleep_ok);
+	t4_tp_mib_read(adap, st->tnl_tx_drops, nchan, TP_MIB_TNL_DROP_0_A,
+		       sleep_ok);
+	t4_tp_mib_read(adap, st->ofld_vlan_drops, nchan,
+		       TP_MIB_OFD_VLN_DROP_0_A, sleep_ok);
+	t4_tp_mib_read(adap, st->tcp6_in_errs, nchan,
+		       TP_MIB_TCP_V6IN_ERR_0_A, sleep_ok);
+	t4_tp_mib_read(adap, &st->ofld_no_neigh, 2, TP_MIB_OFD_ARP_DROP_A,
+		       sleep_ok);
 }
 
 /**
  *	t4_tp_get_cpl_stats - read TP's CPL MIB counters
  *	@adap: the adapter
  *	@st: holds the counter values
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *	Returns the values of TP's CPL counters.
  */
-void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st)
+void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st,
+			 bool sleep_ok)
 {
 	int nchan = adap->params.arch.nchan;
 
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->req,
-			 nchan, TP_MIB_CPL_IN_REQ_0_A);
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->rsp,
-			 nchan, TP_MIB_CPL_OUT_RSP_0_A);
+	t4_tp_mib_read(adap, st->req, nchan, TP_MIB_CPL_IN_REQ_0_A, sleep_ok);
 
+	t4_tp_mib_read(adap, st->rsp, nchan, TP_MIB_CPL_OUT_RSP_0_A, sleep_ok);
 }
 
 /**
  *	t4_tp_get_rdma_stats - read TP's RDMA MIB counters
  *	@adap: the adapter
  *	@st: holds the counter values
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *	Returns the values of TP's RDMA counters.
  */
-void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st)
+void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st,
+			  bool sleep_ok)
 {
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->rqe_dfr_pkt,
-			 2, TP_MIB_RQE_DFR_PKT_A);
+	t4_tp_mib_read(adap, &st->rqe_dfr_pkt, 2, TP_MIB_RQE_DFR_PKT_A,
+		       sleep_ok);
 }
 
 /**
@@ -5347,20 +5457,24 @@ void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st)
  *	@adap: the adapter
  *	@idx: the port index
  *	@st: holds the counter values
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *	Returns the values of TP's FCoE counters for the selected port.
  */
 void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx,
-		       struct tp_fcoe_stats *st)
+		       struct tp_fcoe_stats *st, bool sleep_ok)
 {
 	u32 val[2];
 
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->frames_ddp,
-			 1, TP_MIB_FCOE_DDP_0_A + idx);
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->frames_drop,
-			 1, TP_MIB_FCOE_DROP_0_A + idx);
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val,
-			 2, TP_MIB_FCOE_BYTE_0_HI_A + 2 * idx);
+	t4_tp_mib_read(adap, &st->frames_ddp, 1, TP_MIB_FCOE_DDP_0_A + idx,
+		       sleep_ok);
+
+	t4_tp_mib_read(adap, &st->frames_drop, 1,
+		       TP_MIB_FCOE_DROP_0_A + idx, sleep_ok);
+
+	t4_tp_mib_read(adap, val, 2, TP_MIB_FCOE_BYTE_0_HI_A + 2 * idx,
+		       sleep_ok);
+
 	st->octets_ddp = ((u64)val[0] << 32) | val[1];
 }
 
@@ -5368,15 +5482,16 @@ void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx,
  *	t4_get_usm_stats - read TP's non-TCP DDP MIB counters
  *	@adap: the adapter
  *	@st: holds the counter values
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *	Returns the values of TP's counters for non-TCP directly-placed packets.
  */
-void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st)
+void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st,
+		      bool sleep_ok)
 {
 	u32 val[4];
 
-	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, 4,
-			 TP_MIB_USM_PKTS_A);
+	t4_tp_mib_read(adap, val, 4, TP_MIB_USM_PKTS_A, sleep_ok);
 	st->frames = val[0];
 	st->drops = val[1];
 	st->octets = ((u64)val[2] << 32) | val[3];
@@ -8205,7 +8320,7 @@ struct flash_desc {
 	u32 size_mb;
 };
 
-static int get_flash_params(struct adapter *adap)
+static int t4_get_flash_params(struct adapter *adap)
 {
 	/* Table for non-Numonix supported flash parts.  Numonix parts are left
 	 * to the preexisting code.  All flash parts have 64KB sectors.
@@ -8214,40 +8329,137 @@ static int get_flash_params(struct adapter *adap)
 		{ 0x150201, 4 << 20 },       /* Spansion 4MB S25FL032P */
 	};
 
+	unsigned int part, manufacturer;
+	unsigned int density, size;
+	u32 flashid = 0;
 	int ret;
-	u32 info;
+
+	/* Issue a Read ID Command to the Flash part.  We decode supported
+	 * Flash parts and their sizes from this.  There's a newer Query
+	 * Command which can retrieve detailed geometry information but many
+	 * Flash parts don't support it.
+	 */
 
 	ret = sf1_write(adap, 1, 1, 0, SF_RD_ID);
 	if (!ret)
-		ret = sf1_read(adap, 3, 0, 1, &info);
+		ret = sf1_read(adap, 3, 0, 1, &flashid);
 	t4_write_reg(adap, SF_OP_A, 0);                    /* unlock SF */
 	if (ret)
 		return ret;
 
-	for (ret = 0; ret < ARRAY_SIZE(supported_flash); ++ret)
-		if (supported_flash[ret].vendor_and_model_id == info) {
-			adap->params.sf_size = supported_flash[ret].size_mb;
+	/* Check to see if it's one of our non-standard supported Flash parts.
+	 */
+	for (part = 0; part < ARRAY_SIZE(supported_flash); part++)
+		if (supported_flash[part].vendor_and_model_id == flashid) {
+			adap->params.sf_size = supported_flash[part].size_mb;
 			adap->params.sf_nsec =
 				adap->params.sf_size / SF_SEC_SIZE;
-			return 0;
+			goto found;
 		}
 
-	if ((info & 0xff) != 0x20)             /* not a Numonix flash */
-		return -EINVAL;
-	info >>= 16;                           /* log2 of size */
-	if (info >= 0x14 && info < 0x18)
-		adap->params.sf_nsec = 1 << (info - 16);
-	else if (info == 0x18)
-		adap->params.sf_nsec = 64;
-	else
+	/* Decode Flash part size.  The code below looks repetative with
+	 * common encodings, but that's not guaranteed in the JEDEC
+	 * specification for the Read JADEC ID command.  The only thing that
+	 * we're guaranteed by the JADEC specification is where the
+	 * Manufacturer ID is in the returned result.  After that each
+	 * Manufacturer ~could~ encode things completely differently.
+	 * Note, all Flash parts must have 64KB sectors.
+	 */
+	manufacturer = flashid & 0xff;
+	switch (manufacturer) {
+	case 0x20: { /* Micron/Numonix */
+		/* This Density -> Size decoding table is taken from Micron
+		 * Data Sheets.
+		 */
+		density = (flashid >> 16) & 0xff;
+		switch (density) {
+		case 0x14: /* 1MB */
+			size = 1 << 20;
+			break;
+		case 0x15: /* 2MB */
+			size = 1 << 21;
+			break;
+		case 0x16: /* 4MB */
+			size = 1 << 22;
+			break;
+		case 0x17: /* 8MB */
+			size = 1 << 23;
+			break;
+		case 0x18: /* 16MB */
+			size = 1 << 24;
+			break;
+		case 0x19: /* 32MB */
+			size = 1 << 25;
+			break;
+		case 0x20: /* 64MB */
+			size = 1 << 26;
+			break;
+		case 0x21: /* 128MB */
+			size = 1 << 27;
+			break;
+		case 0x22: /* 256MB */
+			size = 1 << 28;
+			break;
+
+		default:
+			dev_err(adap->pdev_dev, "Micron Flash Part has bad size, ID = %#x, Density code = %#x\n",
+				flashid, density);
+			return -EINVAL;
+		}
+		break;
+	}
+	case 0xc2: { /* Macronix */
+		/* This Density -> Size decoding table is taken from Macronix
+		 * Data Sheets.
+		 */
+		density = (flashid >> 16) & 0xff;
+		switch (density) {
+		case 0x17: /* 8MB */
+			size = 1 << 23;
+			break;
+		case 0x18: /* 16MB */
+			size = 1 << 24;
+			break;
+		default:
+			dev_err(adap->pdev_dev, "Macronix Flash Part has bad size, ID = %#x, Density code = %#x\n",
+				flashid, density);
+			return -EINVAL;
+		}
+		break;
+	}
+	case 0xef: { /* Winbond */
+		/* This Density -> Size decoding table is taken from Winbond
+		 * Data Sheets.
+		 */
+		density = (flashid >> 16) & 0xff;
+		switch (density) {
+		case 0x17: /* 8MB */
+			size = 1 << 23;
+			break;
+		case 0x18: /* 16MB */
+			size = 1 << 24;
+			break;
+		default:
+			dev_err(adap->pdev_dev, "Winbond Flash Part has bad size, ID = %#x, Density code = %#x\n",
+				flashid, density);
+			return -EINVAL;
+		}
+		break;
+	}
+	default:
+		dev_err(adap->pdev_dev, "Unsupported Flash Part, ID = %#x\n",
+			flashid);
 		return -EINVAL;
-	adap->params.sf_size = 1 << info;
-	adap->params.sf_fw_start =
-		t4_read_reg(adap, CIM_BOOT_CFG_A) & BOOTADDR_M;
+	}
+
+	/* Store decoded Flash size and fall through into vetting code. */
+	adap->params.sf_size = size;
+	adap->params.sf_nsec = size / SF_SEC_SIZE;
 
+found:
 	if (adap->params.sf_size < FLASH_MIN_SIZE)
-		dev_warn(adap->pdev_dev, "WARNING!!! FLASH size %#x < %#x!!!\n",
-			 adap->params.sf_size, FLASH_MIN_SIZE);
+		dev_warn(adap->pdev_dev, "WARNING: Flash Part ID %#x, size %#x < %#x\n",
+			 flashid, adap->params.sf_size, FLASH_MIN_SIZE);
 	return 0;
 }
 
@@ -8285,7 +8497,7 @@ int t4_prep_adapter(struct adapter *adapter)
 	get_pci_mode(adapter, &adapter->params.pci);
 	pl_rev = REV_G(t4_read_reg(adapter, PL_REV_A));
 
-	ret = get_flash_params(adapter);
+	ret = t4_get_flash_params(adapter);
 	if (ret < 0) {
 		dev_err(adapter->pdev_dev, "error %d identifying flash\n", ret);
 		return ret;
@@ -8567,10 +8779,11 @@ int t4_init_sge_params(struct adapter *adapter)
 /**
  *      t4_init_tp_params - initialize adap->params.tp
  *      @adap: the adapter
+ *      @sleep_ok: if true we may sleep while awaiting command completion
  *
  *      Initialize various fields of the adapter's TP Parameters structure.
  */
-int t4_init_tp_params(struct adapter *adap)
+int t4_init_tp_params(struct adapter *adap, bool sleep_ok)
 {
 	int chan;
 	u32 v;
@@ -8586,19 +8799,11 @@ int t4_init_tp_params(struct adapter *adap)
 	/* Cache the adapter's Compressed Filter Mode and global Incress
 	 * Configuration.
 	 */
-	if (t4_use_ldst(adap)) {
-		t4_fw_tp_pio_rw(adap, &adap->params.tp.vlan_pri_map, 1,
-				TP_VLAN_PRI_MAP_A, 1);
-		t4_fw_tp_pio_rw(adap, &adap->params.tp.ingress_config, 1,
-				TP_INGRESS_CONFIG_A, 1);
-	} else {
-		t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-				 &adap->params.tp.vlan_pri_map, 1,
-				 TP_VLAN_PRI_MAP_A);
-		t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-				 &adap->params.tp.ingress_config, 1,
-				 TP_INGRESS_CONFIG_A);
-	}
+	t4_tp_pio_read(adap, &adap->params.tp.vlan_pri_map, 1,
+		       TP_VLAN_PRI_MAP_A, sleep_ok);
+	t4_tp_pio_read(adap, &adap->params.tp.ingress_config, 1,
+		       TP_INGRESS_CONFIG_A, sleep_ok);
+
 	/* For T6, cache the adapter's compressed error vector
 	 * and passing outer header info for encapsulated packets.
 	 */
@@ -8611,11 +8816,21 @@ int t4_init_tp_params(struct adapter *adap)
 	 * shift positions of several elements of the Compressed Filter Tuple
 	 * for this adapter which we need frequently ...
 	 */
-	adap->params.tp.vlan_shift = t4_filter_field_shift(adap, VLAN_F);
-	adap->params.tp.vnic_shift = t4_filter_field_shift(adap, VNIC_ID_F);
+	adap->params.tp.fcoe_shift = t4_filter_field_shift(adap, FCOE_F);
 	adap->params.tp.port_shift = t4_filter_field_shift(adap, PORT_F);
+	adap->params.tp.vnic_shift = t4_filter_field_shift(adap, VNIC_ID_F);
+	adap->params.tp.vlan_shift = t4_filter_field_shift(adap, VLAN_F);
+	adap->params.tp.tos_shift = t4_filter_field_shift(adap, TOS_F);
 	adap->params.tp.protocol_shift = t4_filter_field_shift(adap,
 							       PROTOCOL_F);
+	adap->params.tp.ethertype_shift = t4_filter_field_shift(adap,
+								ETHERTYPE_F);
+	adap->params.tp.macmatch_shift = t4_filter_field_shift(adap,
+							       MACMATCH_F);
+	adap->params.tp.matchtype_shift = t4_filter_field_shift(adap,
+								MPSHITTYPE_F);
+	adap->params.tp.frag_shift = t4_filter_field_shift(adap,
+							   FRAGMENTATION_F);
 
 	/* If TP_INGRESS_CONFIG.VNID == 0, then TP_VLAN_PRI_MAP.VNIC_ID
 	 * represents the presence of an Outer VLAN instead of a VNIC ID.
@@ -8623,6 +8838,10 @@ int t4_init_tp_params(struct adapter *adap)
 	if ((adap->params.tp.ingress_config & VNIC_F) == 0)
 		adap->params.tp.vnic_shift = -1;
 
+	v = t4_read_reg(adap, LE_3_DB_HASH_MASK_GEN_IPV4_T6_A);
+	adap->params.tp.hash_filter_mask = v;
+	v = t4_read_reg(adap, LE_4_DB_HASH_MASK_GEN_IPV4_T6_A);
+	adap->params.tp.hash_filter_mask |= ((u64)v << 32);
 	return 0;
 }
 
@@ -9342,6 +9561,63 @@ int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf,
 	return t4_wr_mbox(adapter, adapter->mbox, &cmd, sizeof(cmd), &cmd);
 }
 
+/**
+ * t4_read_pace_tbl - read the pace table
+ * @adap: the adapter
+ * @pace_vals: holds the returned values
+ *
+ * Returns the values of TP's pace table in microseconds.
+ */
+void t4_read_pace_tbl(struct adapter *adap, unsigned int pace_vals[NTX_SCHED])
+{
+	unsigned int i, v;
+
+	for (i = 0; i < NTX_SCHED; i++) {
+		t4_write_reg(adap, TP_PACE_TABLE_A, 0xffff0000 + i);
+		v = t4_read_reg(adap, TP_PACE_TABLE_A);
+		pace_vals[i] = dack_ticks_to_usec(adap, v);
+	}
+}
+
+/**
+ * t4_get_tx_sched - get the configuration of a Tx HW traffic scheduler
+ * @adap: the adapter
+ * @sched: the scheduler index
+ * @kbps: the byte rate in Kbps
+ * @ipg: the interpacket delay in tenths of nanoseconds
+ * @sleep_ok: if true we may sleep while awaiting command completion
+ *
+ * Return the current configuration of a HW Tx scheduler.
+ */
+void t4_get_tx_sched(struct adapter *adap, unsigned int sched,
+		     unsigned int *kbps, unsigned int *ipg, bool sleep_ok)
+{
+	unsigned int v, addr, bpt, cpt;
+
+	if (kbps) {
+		addr = TP_TX_MOD_Q1_Q0_RATE_LIMIT_A - sched / 2;
+		t4_tp_tm_pio_read(adap, &v, 1, addr, sleep_ok);
+		if (sched & 1)
+			v >>= 16;
+		bpt = (v >> 8) & 0xff;
+		cpt = v & 0xff;
+		if (!cpt) {
+			*kbps = 0;	/* scheduler disabled */
+		} else {
+			v = (adap->params.vpd.cclk * 1000) / cpt; /* ticks/s */
+			*kbps = (v * bpt) / 125;
+		}
+	}
+	if (ipg) {
+		addr = TP_TX_MOD_Q1_Q0_TIMER_SEPARATOR_A - sched / 2;
+		t4_tp_tm_pio_read(adap, &v, 1, addr, sleep_ok);
+		if (sched & 1)
+			v >>= 16;
+		v &= 0xffff;
+		*ipg = (10000 * v) / core_ticks_per_usec(adap);
+	}
+}
+
 int t4_sched_params(struct adapter *adapter, int type, int level, int mode,
 		    int rateunit, int ratemode, int channel, int class,
 		    int minrate, int maxrate, int weight, int pktsize)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
index 7f59ca458431..7c6af14905c2 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
@@ -47,6 +47,7 @@ enum {
 	TCB_SIZE       = 128,   /* TCB size */
 	NMTUS          = 16,    /* size of MTU table */
 	NCCTRL_WIN     = 32,    /* # of congestion control windows */
+	NTX_SCHED      = 8,     /* # of HW Tx scheduling queues */
 	PM_NSTATS      = 5,     /* # of PM stats */
 	T6_PM_NSTATS   = 7,     /* # of PM stats in T6 */
 	MBOX_LEN       = 64,    /* mailbox size in bytes */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index b0ff78da8aa2..7e12f241145b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -50,6 +50,7 @@ enum {
 	CPL_RX_DATA_ACK       = 0xD,
 	CPL_TX_PKT            = 0xE,
 	CPL_L2T_WRITE_REQ     = 0x12,
+	CPL_SMT_WRITE_REQ     = 0x14,
 	CPL_TID_RELEASE       = 0x1A,
 	CPL_TX_DATA_ISO	      = 0x1F,
 
@@ -60,6 +61,7 @@ enum {
 	CPL_PEER_CLOSE        = 0x26,
 	CPL_ABORT_REQ_RSS     = 0x2B,
 	CPL_ABORT_RPL_RSS     = 0x2D,
+	CPL_SMT_WRITE_RPL     = 0x2E,
 
 	CPL_RX_PHYS_ADDR      = 0x30,
 	CPL_CLOSE_CON_RPL     = 0x32,
@@ -284,6 +286,7 @@ struct work_request_hdr {
 
 #define RX_CHANNEL_S    26
 #define RX_CHANNEL_V(x) ((x) << RX_CHANNEL_S)
+#define RX_CHANNEL_F	RX_CHANNEL_V(1U)
 
 #define WND_SCALE_EN_S    28
 #define WND_SCALE_EN_V(x) ((x) << WND_SCALE_EN_S)
@@ -313,6 +316,10 @@ struct cpl_pass_open_req {
 #define DELACK_V(x) ((x) << DELACK_S)
 #define DELACK_F    DELACK_V(1U)
 
+#define NON_OFFLOAD_S		7
+#define NON_OFFLOAD_V(x)	((x) << NON_OFFLOAD_S)
+#define NON_OFFLOAD_F		NON_OFFLOAD_V(1U)
+
 #define DSCP_S    22
 #define DSCP_M    0x3F
 #define DSCP_V(x) ((x) << DSCP_S)
@@ -681,8 +688,8 @@ struct cpl_set_tcb_field {
 };
 
 /* cpl_set_tcb_field.word_cookie fields */
-#define TCB_WORD_S    0
-#define TCB_WORD(x)   ((x) << TCB_WORD_S)
+#define TCB_WORD_S	0
+#define TCB_WORD_V(x)	((x) << TCB_WORD_S)
 
 #define TCB_COOKIE_S    5
 #define TCB_COOKIE_M    0x7
@@ -1266,6 +1273,44 @@ struct cpl_l2t_write_rpl {
 	u8 rsvd[3];
 };
 
+struct cpl_smt_write_req {
+	WR_HDR;
+	union opcode_tid ot;
+	__be32 params;
+	__be16 pfvf1;
+	u8 src_mac1[6];
+	__be16 pfvf0;
+	u8 src_mac0[6];
+};
+
+struct cpl_t6_smt_write_req {
+	WR_HDR;
+	union opcode_tid ot;
+	__be32 params;
+	__be64 tag;
+	__be16 pfvf0;
+	u8 src_mac0[6];
+	__be32 local_ip;
+	__be32 rsvd;
+};
+
+struct cpl_smt_write_rpl {
+	union opcode_tid ot;
+	u8 status;
+	u8 rsvd[3];
+};
+
+/* cpl_smt_{read,write}_req.params fields */
+#define SMTW_OVLAN_IDX_S	16
+#define SMTW_OVLAN_IDX_V(x)	((x) << SMTW_OVLAN_IDX_S)
+
+#define SMTW_IDX_S	20
+#define SMTW_IDX_V(x)	((x) << SMTW_IDX_S)
+
+#define SMTW_NORPL_S	31
+#define SMTW_NORPL_V(x)	((x) << SMTW_NORPL_S)
+#define SMTW_NORPL_F	SMTW_NORPL_V(1U)
+
 struct cpl_rdma_terminate {
 	union opcode_tid ot;
 	__be16 rsvd;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index aa28299aef5f..60cf9e02de5d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -176,6 +176,13 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x50a2), /* Custom T540-KR4 */
 	CH_PCI_ID_TABLE_FENTRY(0x50a3), /* Custom T580-KR4 */
 	CH_PCI_ID_TABLE_FENTRY(0x50a4), /* Custom 2x T540-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x50a5), /* Custom T522-BT */
+	CH_PCI_ID_TABLE_FENTRY(0x50a6), /* Custom T522-BT-SO */
+	CH_PCI_ID_TABLE_FENTRY(0x50a7), /* Custom T580-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x50a8), /* Custom T580-KR */
+	CH_PCI_ID_TABLE_FENTRY(0x50a9), /* Custom T580-KR */
+	CH_PCI_ID_TABLE_FENTRY(0x50aa), /* Custom T580-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x50ab), /* Custom T520-CR */
 
 	/* T6 adapters:
 	 */
@@ -197,6 +204,8 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x6082), /* Custom T6225-CR SFP28 */
 	CH_PCI_ID_TABLE_FENTRY(0x6083), /* Custom T62100-CR QSFP28 */
 	CH_PCI_ID_TABLE_FENTRY(0x6084), /* Custom T64100-CR QSFP28 */
+	CH_PCI_ID_TABLE_FENTRY(0x6085), /* Custom T6240-SO */
+	CH_PCI_ID_TABLE_FENTRY(0x6086), /* Custom T6225-SO-CR */
 CH_PCI_DEVICE_ID_TABLE_DEFINE_END;
 
 #endif /* __T4_PCI_ID_TBL_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index dac90837842b..623f453bd327 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1415,6 +1415,7 @@
 #define ROWINDEX_V(x) ((x) << ROWINDEX_S)
 
 #define TP_CCTRL_TABLE_A	0x7ddc
+#define TP_PACE_TABLE_A 0x7dd8
 #define TP_MTU_TABLE_A		0x7de4
 
 #define MTUINDEX_S    24
@@ -1447,6 +1448,17 @@
 #define LKPTBLQUEUE0_M    0x3ffU
 #define LKPTBLQUEUE0_G(x) (((x) >> LKPTBLQUEUE0_S) & LKPTBLQUEUE0_M)
 
+#define TP_TM_PIO_ADDR_A 0x7e18
+#define TP_TM_PIO_DATA_A 0x7e1c
+#define TP_MOD_CONFIG_A 0x7e24
+
+#define TIMERMODE_S    8
+#define TIMERMODE_M    0xffU
+#define TIMERMODE_G(x) (((x) >> TIMERMODE_S) & TIMERMODE_M)
+
+#define TP_TX_MOD_Q1_Q0_TIMER_SEPARATOR_A 0x3
+#define TP_TX_MOD_Q1_Q0_RATE_LIMIT_A 0x8
+
 #define TP_PIO_ADDR_A	0x7e40
 #define TP_PIO_DATA_A	0x7e44
 #define TP_MIB_INDEX_A	0x7e50
@@ -1627,6 +1639,10 @@
 #define IESPI_PAR_ERROR_V(x) ((x) << IESPI_PAR_ERROR_S)
 #define IESPI_PAR_ERROR_F    IESPI_PAR_ERROR_V(1U)
 
+#define ULP_TX_LA_RDPTR_0_A 0x8ec0
+#define ULP_TX_LA_RDDATA_0_A 0x8ec4
+#define ULP_TX_LA_WRPTR_0_A 0x8ec8
+
 #define PMRX_E_PCMD_PAR_ERROR_S    0
 #define PMRX_E_PCMD_PAR_ERROR_V(x) ((x) << PMRX_E_PCMD_PAR_ERROR_S)
 #define PMRX_E_PCMD_PAR_ERROR_F    PMRX_E_PCMD_PAR_ERROR_V(1U)
@@ -2433,6 +2449,18 @@
 #define MPS_CLS_TCAM_DATA0_A 0xf000
 #define MPS_CLS_TCAM_DATA1_A 0xf004
 
+#define CTLREQID_S    30
+#define CTLREQID_V(x) ((x) << CTLREQID_S)
+
+#define MPS_VF_RPLCT_MAP0_A 0x1111c
+#define MPS_VF_RPLCT_MAP1_A 0x11120
+#define MPS_VF_RPLCT_MAP2_A 0x11124
+#define MPS_VF_RPLCT_MAP3_A 0x11128
+#define MPS_VF_RPLCT_MAP4_A 0x11300
+#define MPS_VF_RPLCT_MAP5_A 0x11304
+#define MPS_VF_RPLCT_MAP6_A 0x11308
+#define MPS_VF_RPLCT_MAP7_A 0x1130c
+
 #define VIDL_S    16
 #define VIDL_M    0xffffU
 #define VIDL_G(x) (((x) >> VIDL_S) & VIDL_M)
@@ -2457,6 +2485,10 @@
 #define DATAVIDH1_M    0x7fU
 #define DATAVIDH1_G(x) (((x) >> DATAVIDH1_S) & DATAVIDH1_M)
 
+#define MPS_CLS_TCAM_RDATA0_REQ_ID1_A 0xf020
+#define MPS_CLS_TCAM_RDATA1_REQ_ID1_A 0xf024
+#define MPS_CLS_TCAM_RDATA2_REQ_ID1_A 0xf028
+
 #define USED_S    16
 #define USED_M    0x7ffU
 #define USED_G(x) (((x) >> USED_S) & USED_M)
@@ -2850,6 +2882,7 @@
 #define T6_LIPMISS_F    T6_LIPMISS_V(1U)
 
 #define LE_DB_CONFIG_A 0x19c04
+#define LE_DB_ACTIVE_TABLE_START_INDEX_A 0x19c10
 #define LE_DB_SERVER_INDEX_A 0x19c18
 #define LE_DB_SRVR_START_INDEX_A 0x19c18
 #define LE_DB_ACT_CNT_IPV4_A 0x19c20
@@ -2900,6 +2933,23 @@
 #define SSRAMINTPERR_V(x) ((x) << SSRAMINTPERR_S)
 #define SSRAMINTPERR_F    SSRAMINTPERR_V(1U)
 
+#define LE_DB_RSP_CODE_0_A	0x19c74
+
+#define TCAM_ACTV_HIT_S		0
+#define TCAM_ACTV_HIT_M		0x1fU
+#define TCAM_ACTV_HIT_V(x)	((x) << TCAM_ACTV_HIT_S)
+#define TCAM_ACTV_HIT_G(x)	(((x) >> TCAM_ACTV_HIT_S) & TCAM_ACTV_HIT_M)
+
+#define LE_DB_RSP_CODE_1_A     0x19c78
+
+#define HASH_ACTV_HIT_S		25
+#define HASH_ACTV_HIT_M		0x1fU
+#define HASH_ACTV_HIT_V(x)	((x) << HASH_ACTV_HIT_S)
+#define HASH_ACTV_HIT_G(x)	(((x) >> HASH_ACTV_HIT_S) & HASH_ACTV_HIT_M)
+
+#define LE_3_DB_HASH_MASK_GEN_IPV4_T6_A	0x19eac
+#define LE_4_DB_HASH_MASK_GEN_IPV4_T6_A	0x19eb0
+
 #define NCSI_INT_CAUSE_A 0x1a0d8
 
 #define CIM_DM_PRTY_ERR_S    8
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
new file mode 100644
index 000000000000..3297ce025e8b
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
@@ -0,0 +1,69 @@
+/*
+ * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux.
+ *
+ * Copyright (c) 2017 Chelsio Communications, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __T4_TCB_H
+#define __T4_TCB_H
+
+#define TCB_SMAC_SEL_W		0
+#define TCB_SMAC_SEL_S		24
+#define TCB_SMAC_SEL_M		0xffULL
+#define TCB_SMAC_SEL_V(x)	((x) << TCB_SMAC_SEL_S)
+
+#define TCB_T_FLAGS_W		1
+
+#define TF_CCTRL_ECE_S		60
+#define TF_CCTRL_CWR_S		61
+#define TF_CCTRL_RFR_S		62
+
+#define TCB_RSS_INFO_W		3
+#define TCB_RSS_INFO_S		0
+#define TCB_RSS_INFO_M		0x3ffULL
+#define TCB_RSS_INFO_V(x)	((x) << TCB_RSS_INFO_S)
+
+#define TCB_TIMESTAMP_W		5
+#define TCB_TIMESTAMP_S		0
+#define TCB_TIMESTAMP_M		0xffffffffULL
+#define TCB_TIMESTAMP_V(x)	((x) << TCB_TIMESTAMP_S)
+
+#define TCB_RTT_TS_RECENT_AGE_W		6
+#define TCB_RTT_TS_RECENT_AGE_S		0
+#define TCB_RTT_TS_RECENT_AGE_M		0xffffffffULL
+#define TCB_RTT_TS_RECENT_AGE_V(x)	((x) << TCB_RTT_TS_RECENT_AGE_S)
+
+#define TCB_SND_UNA_RAW_W	10
+#define TCB_RX_FRAG2_PTR_RAW_W	27
+#define TCB_RX_FRAG3_LEN_RAW_W	29
+#define TCB_RX_FRAG3_START_IDX_OFFSET_RAW_W	30
+#define TCB_PDU_HDR_LEN_W	31
+#endif /* __T4_TCB_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index ca2756dcefc5..57eb4ad3485d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -105,7 +105,8 @@ enum fw_wr_opcodes {
 	FW_ISCSI_TX_DATA_WR	       = 0x45,
 	FW_PTP_TX_PKT_WR               = 0x46,
 	FW_CRYPTO_LOOKASIDE_WR         = 0X6d,
-	FW_LASTC2E_WR                  = 0x70
+	FW_LASTC2E_WR                  = 0x70,
+	FW_FILTER2_WR		       = 0x77
 };
 
 struct fw_wr_hdr {
@@ -201,6 +202,51 @@ struct fw_filter_wr {
 	__u8   sma[6];
 };
 
+struct fw_filter2_wr {
+	__be32 op_pkd;
+	__be32 len16_pkd;
+	__be64 r3;
+	__be32 tid_to_iq;
+	__be32 del_filter_to_l2tix;
+	__be16 ethtype;
+	__be16 ethtypem;
+	__u8   frag_to_ovlan_vldm;
+	__u8   smac_sel;
+	__be16 rx_chan_rx_rpl_iq;
+	__be32 maci_to_matchtypem;
+	__u8   ptcl;
+	__u8   ptclm;
+	__u8   ttyp;
+	__u8   ttypm;
+	__be16 ivlan;
+	__be16 ivlanm;
+	__be16 ovlan;
+	__be16 ovlanm;
+	__u8   lip[16];
+	__u8   lipm[16];
+	__u8   fip[16];
+	__u8   fipm[16];
+	__be16 lp;
+	__be16 lpm;
+	__be16 fp;
+	__be16 fpm;
+	__be16 r7;
+	__u8   sma[6];
+	__be16 r8;
+	__u8   filter_type_swapmac;
+	__u8   natmode_to_ulp_type;
+	__be16 newlport;
+	__be16 newfport;
+	__u8   newlip[16];
+	__u8   newfip[16];
+	__be32 natseqcheck;
+	__be32 r9;
+	__be64 r10;
+	__be64 r11;
+	__be64 r12;
+	__be64 r13;
+};
+
 #define FW_FILTER_WR_TID_S      12
 #define FW_FILTER_WR_TID_M      0xfffff
 #define FW_FILTER_WR_TID_V(x)   ((x) << FW_FILTER_WR_TID_S)
@@ -385,6 +431,32 @@ struct fw_filter_wr {
 #define FW_FILTER_WR_RX_RPL_IQ_G(x)     \
 	(((x) >> FW_FILTER_WR_RX_RPL_IQ_S) & FW_FILTER_WR_RX_RPL_IQ_M)
 
+#define FW_FILTER2_WR_FILTER_TYPE_S	1
+#define FW_FILTER2_WR_FILTER_TYPE_M	0x1
+#define FW_FILTER2_WR_FILTER_TYPE_V(x)	((x) << FW_FILTER2_WR_FILTER_TYPE_S)
+#define FW_FILTER2_WR_FILTER_TYPE_G(x)  \
+	(((x) >> FW_FILTER2_WR_FILTER_TYPE_S) & FW_FILTER2_WR_FILTER_TYPE_M)
+#define FW_FILTER2_WR_FILTER_TYPE_F	FW_FILTER2_WR_FILTER_TYPE_V(1U)
+
+#define FW_FILTER2_WR_NATMODE_S		5
+#define FW_FILTER2_WR_NATMODE_M		0x7
+#define FW_FILTER2_WR_NATMODE_V(x)	((x) << FW_FILTER2_WR_NATMODE_S)
+#define FW_FILTER2_WR_NATMODE_G(x)      \
+	(((x) >> FW_FILTER2_WR_NATMODE_S) & FW_FILTER2_WR_NATMODE_M)
+
+#define FW_FILTER2_WR_NATFLAGCHECK_S	4
+#define FW_FILTER2_WR_NATFLAGCHECK_M	0x1
+#define FW_FILTER2_WR_NATFLAGCHECK_V(x)	((x) << FW_FILTER2_WR_NATFLAGCHECK_S)
+#define FW_FILTER2_WR_NATFLAGCHECK_G(x) \
+	(((x) >> FW_FILTER2_WR_NATFLAGCHECK_S) & FW_FILTER2_WR_NATFLAGCHECK_M)
+#define FW_FILTER2_WR_NATFLAGCHECK_F	FW_FILTER2_WR_NATFLAGCHECK_V(1U)
+
+#define FW_FILTER2_WR_ULP_TYPE_S	0
+#define FW_FILTER2_WR_ULP_TYPE_M	0xf
+#define FW_FILTER2_WR_ULP_TYPE_V(x)	((x) << FW_FILTER2_WR_ULP_TYPE_S)
+#define FW_FILTER2_WR_ULP_TYPE_G(x)     \
+	(((x) >> FW_FILTER2_WR_ULP_TYPE_S) & FW_FILTER2_WR_ULP_TYPE_M)
+
 #define FW_FILTER_WR_MACI_S     23
 #define FW_FILTER_WR_MACI_M     0x1ff
 #define FW_FILTER_WR_MACI_V(x)  ((x) << FW_FILTER_WR_MACI_S)
@@ -1020,6 +1092,7 @@ enum fw_caps_config_switch {
 enum fw_caps_config_nic {
 	FW_CAPS_CONFIG_NIC		= 0x00000001,
 	FW_CAPS_CONFIG_NIC_VM		= 0x00000002,
+	FW_CAPS_CONFIG_NIC_HASHFILTER	= 0x00000020,
 };
 
 enum fw_caps_config_ofld {
@@ -1127,6 +1200,7 @@ enum fw_params_param_dev {
 	FW_PARAMS_PARAM_DEV_SCFGREV = 0x1A,
 	FW_PARAMS_PARAM_DEV_VPDREV = 0x1B,
 	FW_PARAMS_PARAM_DEV_RI_FR_NSMR_TPTE_WR	= 0x1C,
+	FW_PARAMS_PARAM_DEV_FILTER2_WR  = 0x1D,
 	FW_PARAMS_PARAM_DEV_MPSBGMAP	= 0x1E,
 };
 
@@ -1171,9 +1245,12 @@ enum fw_params_param_pfvf {
 	FW_PARAMS_PARAM_PFVF_EQ_END	= 0x2C,
 	FW_PARAMS_PARAM_PFVF_ACTIVE_FILTER_START = 0x2D,
 	FW_PARAMS_PARAM_PFVF_ACTIVE_FILTER_END = 0x2E,
+	FW_PARAMS_PARAM_PFVF_ETHOFLD_START = 0x2F,
 	FW_PARAMS_PARAM_PFVF_ETHOFLD_END = 0x30,
 	FW_PARAMS_PARAM_PFVF_CPLFW4MSG_ENCAP = 0x31,
-	FW_PARAMS_PARAM_PFVF_NCRYPTO_LOOKASIDE = 0x32,
+	FW_PARAMS_PARAM_PFVF_HPFILTER_START = 0x32,
+	FW_PARAMS_PARAM_PFVF_HPFILTER_END = 0x33,
+	FW_PARAMS_PARAM_PFVF_NCRYPTO_LOOKASIDE = 0x39,
 	FW_PARAMS_PARAM_PFVF_PORT_CAPS32 = 0x3A,
 };
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 8996ebbd222e..b48361cfdc78 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -1401,6 +1401,63 @@ static int cxgb4vf_get_link_ksettings(struct net_device *dev,
 	return 0;
 }
 
+/* Translate the Firmware FEC value into the ethtool value. */
+static inline unsigned int fwcap_to_eth_fec(unsigned int fw_fec)
+{
+	unsigned int eth_fec = 0;
+
+	if (fw_fec & FW_PORT_CAP32_FEC_RS)
+		eth_fec |= ETHTOOL_FEC_RS;
+	if (fw_fec & FW_PORT_CAP32_FEC_BASER_RS)
+		eth_fec |= ETHTOOL_FEC_BASER;
+
+	/* if nothing is set, then FEC is off */
+	if (!eth_fec)
+		eth_fec = ETHTOOL_FEC_OFF;
+
+	return eth_fec;
+}
+
+/* Translate Common Code FEC value into ethtool value. */
+static inline unsigned int cc_to_eth_fec(unsigned int cc_fec)
+{
+	unsigned int eth_fec = 0;
+
+	if (cc_fec & FEC_AUTO)
+		eth_fec |= ETHTOOL_FEC_AUTO;
+	if (cc_fec & FEC_RS)
+		eth_fec |= ETHTOOL_FEC_RS;
+	if (cc_fec & FEC_BASER_RS)
+		eth_fec |= ETHTOOL_FEC_BASER;
+
+	/* if nothing is set, then FEC is off */
+	if (!eth_fec)
+		eth_fec = ETHTOOL_FEC_OFF;
+
+	return eth_fec;
+}
+
+static int cxgb4vf_get_fecparam(struct net_device *dev,
+				struct ethtool_fecparam *fec)
+{
+	const struct port_info *pi = netdev_priv(dev);
+	const struct link_config *lc = &pi->link_cfg;
+
+	/* Translate the Firmware FEC Support into the ethtool value.  We
+	 * always support IEEE 802.3 "automatic" selection of Link FEC type if
+	 * any FEC is supported.
+	 */
+	fec->fec = fwcap_to_eth_fec(lc->pcaps);
+	if (fec->fec != ETHTOOL_FEC_OFF)
+		fec->fec |= ETHTOOL_FEC_AUTO;
+
+	/* Translate the current internal FEC parameters into the
+	 * ethtool values.
+	 */
+	fec->active_fec = cc_to_eth_fec(lc->fec);
+	return 0;
+}
+
 /*
  * Return our driver information.
  */
@@ -1774,6 +1831,7 @@ static void cxgb4vf_get_wol(struct net_device *dev,
 
 static const struct ethtool_ops cxgb4vf_ethtool_ops = {
 	.get_link_ksettings	= cxgb4vf_get_link_ksettings,
+	.get_fecparam		= cxgb4vf_get_fecparam,
 	.get_drvinfo		= cxgb4vf_get_drvinfo,
 	.get_msglevel		= cxgb4vf_get_msglevel,
 	.set_msglevel		= cxgb4vf_set_msglevel,
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 05498e7f2840..14d7e673c656 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -2058,9 +2058,9 @@ irq_handler_t t4vf_intr_handler(struct adapter *adapter)
  *	when out of memory a queue can become empty.  We schedule NAPI to do
  *	the actual refill.
  */
-static void sge_rx_timer_cb(unsigned long data)
+static void sge_rx_timer_cb(struct timer_list *t)
 {
-	struct adapter *adapter = (struct adapter *)data;
+	struct adapter *adapter = from_timer(adapter, t, sge.rx_timer);
 	struct sge *s = &adapter->sge;
 	unsigned int i;
 
@@ -2117,9 +2117,9 @@ static void sge_rx_timer_cb(unsigned long data)
  *	when no new packets are being submitted.  This is essential for pktgen,
  *	at least.
  */
-static void sge_tx_timer_cb(unsigned long data)
+static void sge_tx_timer_cb(struct timer_list *t)
 {
-	struct adapter *adapter = (struct adapter *)data;
+	struct adapter *adapter = from_timer(adapter, t, sge.tx_timer);
 	struct sge *s = &adapter->sge;
 	unsigned int i, budget;
 
@@ -2676,8 +2676,8 @@ int t4vf_sge_init(struct adapter *adapter)
 	/*
 	 * Set up tasklet timers.
 	 */
-	setup_timer(&s->rx_timer, sge_rx_timer_cb, (unsigned long)adapter);
-	setup_timer(&s->tx_timer, sge_tx_timer_cb, (unsigned long)adapter);
+	timer_setup(&s->rx_timer, sge_rx_timer_cb, 0);
+	timer_setup(&s->tx_timer, sge_tx_timer_cb, 0);
 
 	/*
 	 * Initialize Forwarded Interrupt Queue lock.
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
index a8d94963b4d0..67aec59a14e6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
@@ -1812,7 +1812,7 @@ int t4vf_eth_eq_free(struct adapter *adapter, unsigned int eqid)
  *
  *	Returns a string representation of the Link Down Reason Code.
  */
-const char *t4vf_link_down_rc_str(unsigned char link_down_rc)
+static const char *t4vf_link_down_rc_str(unsigned char link_down_rc)
 {
 	static const char * const reason[] = {
 		"Link Down",
@@ -1838,8 +1838,8 @@ const char *t4vf_link_down_rc_str(unsigned char link_down_rc)
  *
  *	Processes a GET_PORT_INFO FW reply message.
  */
-void t4vf_handle_get_port_info(struct port_info *pi,
-			       const struct fw_port_cmd *cmd)
+static void t4vf_handle_get_port_info(struct port_info *pi,
+				      const struct fw_port_cmd *cmd)
 {
 	int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16));
 	struct adapter *adapter = pi->adapter;
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index ba032ac9ae86..6a9527004cb1 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -33,7 +33,7 @@
 
 #define DRV_NAME		"enic"
 #define DRV_DESCRIPTION		"Cisco VIC Ethernet NIC Driver"
-#define DRV_VERSION		"2.3.0.42"
+#define DRV_VERSION		"2.3.0.45"
 #define DRV_COPYRIGHT		"Copyright 2008-2013 Cisco Systems, Inc"
 
 #define ENIC_BARS_MAX		6
diff --git a/drivers/net/ethernet/cisco/enic/enic_clsf.h b/drivers/net/ethernet/cisco/enic/enic_clsf.h
index d3c4a1cb0610..0ae83e091a62 100644
--- a/drivers/net/ethernet/cisco/enic/enic_clsf.h
+++ b/drivers/net/ethernet/cisco/enic/enic_clsf.h
@@ -20,9 +20,8 @@ void enic_flow_may_expire(unsigned long data);
 
 static inline void enic_rfs_timer_start(struct enic *enic)
 {
-	init_timer(&enic->rfs_h.rfs_may_expire);
-	enic->rfs_h.rfs_may_expire.function = enic_flow_may_expire;
-	enic->rfs_h.rfs_may_expire.data = (unsigned long)enic;
+	setup_timer(&enic->rfs_h.rfs_may_expire, enic_flow_may_expire,
+		    (unsigned long)enic);
 	mod_timer(&enic->rfs_h.rfs_may_expire, jiffies + HZ/4);
 }
 
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index fd3980cc1e34..462d0ce51240 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -176,6 +176,81 @@ static void enic_get_strings(struct net_device *netdev, u32 stringset,
 	}
 }
 
+static void enic_get_ringparam(struct net_device *netdev,
+			       struct ethtool_ringparam *ring)
+{
+	struct enic *enic = netdev_priv(netdev);
+	struct vnic_enet_config *c = &enic->config;
+
+	ring->rx_max_pending = ENIC_MAX_RQ_DESCS;
+	ring->rx_pending = c->rq_desc_count;
+	ring->tx_max_pending = ENIC_MAX_WQ_DESCS;
+	ring->tx_pending = c->wq_desc_count;
+}
+
+static int enic_set_ringparam(struct net_device *netdev,
+			      struct ethtool_ringparam *ring)
+{
+	struct enic *enic = netdev_priv(netdev);
+	struct vnic_enet_config *c = &enic->config;
+	int running = netif_running(netdev);
+	unsigned int rx_pending;
+	unsigned int tx_pending;
+	int err = 0;
+
+	if (ring->rx_mini_max_pending || ring->rx_mini_pending) {
+		netdev_info(netdev,
+			    "modifying mini ring params is not supported");
+		return -EINVAL;
+	}
+	if (ring->rx_jumbo_max_pending || ring->rx_jumbo_pending) {
+		netdev_info(netdev,
+			    "modifying jumbo ring params is not supported");
+		return -EINVAL;
+	}
+	rx_pending = c->rq_desc_count;
+	tx_pending = c->wq_desc_count;
+	if (ring->rx_pending > ENIC_MAX_RQ_DESCS ||
+	    ring->rx_pending < ENIC_MIN_RQ_DESCS) {
+		netdev_info(netdev, "rx pending (%u) not in range [%u,%u]",
+			    ring->rx_pending, ENIC_MIN_RQ_DESCS,
+			    ENIC_MAX_RQ_DESCS);
+		return -EINVAL;
+	}
+	if (ring->tx_pending > ENIC_MAX_WQ_DESCS ||
+	    ring->tx_pending < ENIC_MIN_WQ_DESCS) {
+		netdev_info(netdev, "tx pending (%u) not in range [%u,%u]",
+			    ring->tx_pending, ENIC_MIN_WQ_DESCS,
+			    ENIC_MAX_WQ_DESCS);
+		return -EINVAL;
+	}
+	if (running)
+		dev_close(netdev);
+	c->rq_desc_count =
+		ring->rx_pending & 0xffffffe0; /* must be aligned to groups of 32 */
+	c->wq_desc_count =
+		ring->tx_pending & 0xffffffe0; /* must be aligned to groups of 32 */
+	enic_free_vnic_resources(enic);
+	err = enic_alloc_vnic_resources(enic);
+	if (err) {
+		netdev_err(netdev,
+			   "Failed to alloc vNIC resources, aborting\n");
+		enic_free_vnic_resources(enic);
+		goto err_out;
+	}
+	enic_init_vnic_resources(enic);
+	if (running) {
+		err = dev_open(netdev);
+		if (err)
+			goto err_out;
+	}
+	return 0;
+err_out:
+	c->rq_desc_count = rx_pending;
+	c->wq_desc_count = tx_pending;
+	return err;
+}
+
 static int enic_get_sset_count(struct net_device *netdev, int sset)
 {
 	switch (sset) {
@@ -509,6 +584,8 @@ static const struct ethtool_ops enic_ethtool_ops = {
 	.set_msglevel = enic_set_msglevel,
 	.get_link = ethtool_op_get_link,
 	.get_strings = enic_get_strings,
+	.get_ringparam = enic_get_ringparam,
+	.set_ringparam = enic_set_ringparam,
 	.get_sset_count = enic_get_sset_count,
 	.get_ethtool_stats = enic_get_ethtool_stats,
 	.get_coalesce = enic_get_coalesce,
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index d24ee1ad3be1..4a11baffe02d 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2846,9 +2846,8 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Setup notification timer, HW reset task, and wq locks
 	 */
 
-	init_timer(&enic->notify_timer);
-	enic->notify_timer.function = enic_notify_timer;
-	enic->notify_timer.data = (unsigned long)enic;
+	setup_timer(&enic->notify_timer, enic_notify_timer,
+		    (unsigned long)enic);
 
 	enic_set_rx_coal_setting(enic);
 	INIT_WORK(&enic->reset, enic_reset);
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.c b/drivers/net/ethernet/cisco/enic/vnic_rq.c
index 36bc2c71fba9..f8aa326d1d58 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.c
@@ -139,20 +139,8 @@ void vnic_rq_init(struct vnic_rq *rq, unsigned int cq_index,
 	unsigned int error_interrupt_enable,
 	unsigned int error_interrupt_offset)
 {
-	u32 fetch_index = 0;
-
-	/* Use current fetch_index as the ring starting point */
-	fetch_index = ioread32(&rq->ctrl->fetch_index);
-
-	if (fetch_index == 0xFFFFFFFF) { /* check for hardware gone  */
-		/* Hardware surprise removal: reset fetch_index */
-		fetch_index = 0;
-	}
-
-	vnic_rq_init_start(rq, cq_index,
-		fetch_index, fetch_index,
-		error_interrupt_enable,
-		error_interrupt_offset);
+	vnic_rq_init_start(rq, cq_index, 0, 0, error_interrupt_enable,
+			   error_interrupt_offset);
 }
 
 unsigned int vnic_rq_error_status(struct vnic_rq *rq)
diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c
index c87b8cc42963..13430f75496c 100644
--- a/drivers/net/ethernet/dec/tulip/de2104x.c
+++ b/drivers/net/ethernet/dec/tulip/de2104x.c
@@ -333,8 +333,8 @@ static void de_set_rx_mode (struct net_device *dev);
 static void de_tx (struct de_private *de);
 static void de_clean_rings (struct de_private *de);
 static void de_media_interrupt (struct de_private *de, u32 status);
-static void de21040_media_timer (unsigned long data);
-static void de21041_media_timer (unsigned long data);
+static void de21040_media_timer (struct timer_list *t);
+static void de21041_media_timer (struct timer_list *t);
 static unsigned int de_ok_to_advertise (struct de_private *de, u32 new_media);
 
 
@@ -959,9 +959,9 @@ static void de_next_media (struct de_private *de, const u32 *media,
 	}
 }
 
-static void de21040_media_timer (unsigned long data)
+static void de21040_media_timer (struct timer_list *t)
 {
-	struct de_private *de = (struct de_private *) data;
+	struct de_private *de = from_timer(de, t, media_timer);
 	struct net_device *dev = de->dev;
 	u32 status = dr32(SIAStatus);
 	unsigned int carrier;
@@ -1040,9 +1040,9 @@ static unsigned int de_ok_to_advertise (struct de_private *de, u32 new_media)
 	return 1;
 }
 
-static void de21041_media_timer (unsigned long data)
+static void de21041_media_timer (struct timer_list *t)
 {
-	struct de_private *de = (struct de_private *) data;
+	struct de_private *de = from_timer(de, t, media_timer);
 	struct net_device *dev = de->dev;
 	u32 status = dr32(SIAStatus);
 	unsigned int carrier;
@@ -1999,12 +1999,9 @@ static int de_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	de->msg_enable = (debug < 0 ? DE_DEF_MSG_ENABLE : debug);
 	de->board_idx = board_idx;
 	spin_lock_init (&de->lock);
-	init_timer(&de->media_timer);
-	if (de->de21040)
-		de->media_timer.function = de21040_media_timer;
-	else
-		de->media_timer.function = de21041_media_timer;
-	de->media_timer.data = (unsigned long) de;
+	timer_setup(&de->media_timer,
+		    de->de21040 ? de21040_media_timer : de21041_media_timer,
+		    0);
 
 	netif_carrier_off(dev);
 
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index 0affee9c8aa2..a31b4df3e7ff 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -912,7 +912,7 @@ static int     de4x5_init(struct net_device *dev);
 static int     de4x5_sw_reset(struct net_device *dev);
 static int     de4x5_rx(struct net_device *dev);
 static int     de4x5_tx(struct net_device *dev);
-static void    de4x5_ast(struct net_device *dev);
+static void    de4x5_ast(struct timer_list *t);
 static int     de4x5_txur(struct net_device *dev);
 static int     de4x5_rx_ovfc(struct net_device *dev);
 
@@ -1147,9 +1147,7 @@ de4x5_hw_init(struct net_device *dev, u_long iobase, struct device *gendev)
 	lp->timeout = -1;
 	lp->gendev = gendev;
 	spin_lock_init(&lp->lock);
-	init_timer(&lp->timer);
-	lp->timer.function = (void (*)(unsigned long))de4x5_ast;
-	lp->timer.data = (unsigned long)dev;
+	timer_setup(&lp->timer, de4x5_ast, 0);
 	de4x5_parse_params(dev);
 
 	/*
@@ -1742,9 +1740,10 @@ de4x5_tx(struct net_device *dev)
 }
 
 static void
-de4x5_ast(struct net_device *dev)
+de4x5_ast(struct timer_list *t)
 {
-	struct de4x5_private *lp = netdev_priv(dev);
+	struct de4x5_private *lp = from_timer(lp, t, timer);
+	struct net_device *dev = dev_get_drvdata(lp->gendev);
 	int next_tick = DE4X5_AUTOSENSE_MS;
 	int dt;
 
@@ -2370,7 +2369,7 @@ autoconf_media(struct net_device *dev)
 	lp->media = INIT;
 	lp->tcount = 0;
 
-	de4x5_ast(dev);
+	de4x5_ast(&lp->timer);
 
 	return lp->media;
 }
diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c
index 07e10a45beaa..17ef7a28873d 100644
--- a/drivers/net/ethernet/dec/tulip/dmfe.c
+++ b/drivers/net/ethernet/dec/tulip/dmfe.c
@@ -331,7 +331,7 @@ static void dmfe_phy_write_1bit(void __iomem *, u32);
 static u16 dmfe_phy_read_1bit(void __iomem *);
 static u8 dmfe_sense_speed(struct dmfe_board_info *);
 static void dmfe_process_mode(struct dmfe_board_info *);
-static void dmfe_timer(unsigned long);
+static void dmfe_timer(struct timer_list *);
 static inline u32 cal_CRC(unsigned char *, unsigned int, u8);
 static void dmfe_rx_packet(struct net_device *, struct dmfe_board_info *);
 static void dmfe_free_tx_pkt(struct net_device *, struct dmfe_board_info *);
@@ -596,10 +596,8 @@ static int dmfe_open(struct net_device *dev)
 	netif_wake_queue(dev);
 
 	/* set and active a timer process */
-	init_timer(&db->timer);
+	timer_setup(&db->timer, dmfe_timer, 0);
 	db->timer.expires = DMFE_TIMER_WUT + HZ * 2;
-	db->timer.data = (unsigned long)dev;
-	db->timer.function = dmfe_timer;
 	add_timer(&db->timer);
 
 	return 0;
@@ -1130,10 +1128,10 @@ static const struct ethtool_ops netdev_ethtool_ops = {
  *	Dynamic media sense, allocate Rx buffer...
  */
 
-static void dmfe_timer(unsigned long data)
+static void dmfe_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct dmfe_board_info *db = netdev_priv(dev);
+	struct dmfe_board_info *db = from_timer(db, t, timer);
+	struct net_device *dev = pci_get_drvdata(db->pdev);
 	void __iomem *ioaddr = db->ioaddr;
 	u32 tmp_cr8;
 	unsigned char tmp_cr12;
diff --git a/drivers/net/ethernet/dec/tulip/interrupt.c b/drivers/net/ethernet/dec/tulip/interrupt.c
index 8df80880ecaa..c1ca0765d56d 100644
--- a/drivers/net/ethernet/dec/tulip/interrupt.c
+++ b/drivers/net/ethernet/dec/tulip/interrupt.c
@@ -102,10 +102,10 @@ int tulip_refill_rx(struct net_device *dev)
 
 #ifdef CONFIG_TULIP_NAPI
 
-void oom_timer(unsigned long data)
+void oom_timer(struct timer_list *t)
 {
-        struct net_device *dev = (struct net_device *)data;
-	struct tulip_private *tp = netdev_priv(dev);
+	struct tulip_private *tp = from_timer(tp, t, oom_timer);
+
 	napi_schedule(&tp->napi);
 }
 
diff --git a/drivers/net/ethernet/dec/tulip/pnic.c b/drivers/net/ethernet/dec/tulip/pnic.c
index 7bcccf5cac7a..3fb39e32e1b4 100644
--- a/drivers/net/ethernet/dec/tulip/pnic.c
+++ b/drivers/net/ethernet/dec/tulip/pnic.c
@@ -84,10 +84,10 @@ void pnic_lnk_change(struct net_device *dev, int csr5)
 	}
 }
 
-void pnic_timer(unsigned long data)
+void pnic_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct tulip_private *tp = netdev_priv(dev);
+	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct net_device *dev = tp->dev;
 	void __iomem *ioaddr = tp->base_addr;
 	int next_tick = 60*HZ;
 
diff --git a/drivers/net/ethernet/dec/tulip/pnic2.c b/drivers/net/ethernet/dec/tulip/pnic2.c
index 5895fc43f6e0..412adaa7fdf8 100644
--- a/drivers/net/ethernet/dec/tulip/pnic2.c
+++ b/drivers/net/ethernet/dec/tulip/pnic2.c
@@ -76,10 +76,10 @@
 #include <linux/delay.h>
 
 
-void pnic2_timer(unsigned long data)
+void pnic2_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct tulip_private *tp = netdev_priv(dev);
+	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct net_device *dev = tp->dev;
 	void __iomem *ioaddr = tp->base_addr;
 	int next_tick = 60*HZ;
 
diff --git a/drivers/net/ethernet/dec/tulip/timer.c b/drivers/net/ethernet/dec/tulip/timer.c
index 523d9dde50a2..642e9dfc5451 100644
--- a/drivers/net/ethernet/dec/tulip/timer.c
+++ b/drivers/net/ethernet/dec/tulip/timer.c
@@ -137,10 +137,10 @@ void tulip_media_task(struct work_struct *work)
 }
 
 
-void mxic_timer(unsigned long data)
+void mxic_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct tulip_private *tp = netdev_priv(dev);
+	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct net_device *dev = tp->dev;
 	void __iomem *ioaddr = tp->base_addr;
 	int next_tick = 60*HZ;
 
@@ -154,10 +154,10 @@ void mxic_timer(unsigned long data)
 }
 
 
-void comet_timer(unsigned long data)
+void comet_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct tulip_private *tp = netdev_priv(dev);
+	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct net_device *dev = tp->dev;
 	int next_tick = 2*HZ;
 
 	if (tulip_debug > 1)
diff --git a/drivers/net/ethernet/dec/tulip/tulip.h b/drivers/net/ethernet/dec/tulip/tulip.h
index 06660dbc44b7..b458140aeaef 100644
--- a/drivers/net/ethernet/dec/tulip/tulip.h
+++ b/drivers/net/ethernet/dec/tulip/tulip.h
@@ -43,7 +43,7 @@ struct tulip_chip_table {
 	int io_size;
 	int valid_intrs;	/* CSR7 interrupt enable settings */
 	int flags;
-	void (*media_timer) (unsigned long);
+	void (*media_timer) (struct timer_list *);
 	work_func_t media_task;
 };
 
@@ -476,7 +476,7 @@ void t21142_lnk_change(struct net_device *dev, int csr5);
 
 /* PNIC2.c */
 void pnic2_lnk_change(struct net_device *dev, int csr5);
-void pnic2_timer(unsigned long data);
+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);
 
@@ -504,19 +504,19 @@ void tulip_find_mii (struct net_device *dev, int board_idx);
 /* pnic.c */
 void pnic_do_nway(struct net_device *dev);
 void pnic_lnk_change(struct net_device *dev, int csr5);
-void pnic_timer(unsigned long data);
+void pnic_timer(struct timer_list *t);
 
 /* timer.c */
 void tulip_media_task(struct work_struct *work);
-void mxic_timer(unsigned long data);
-void comet_timer(unsigned long data);
+void mxic_timer(struct timer_list *t);
+void comet_timer(struct timer_list *t);
 
 /* tulip_core.c */
 extern int tulip_debug;
 extern const char * const medianame[];
 extern const char tulip_media_cap[];
 extern const struct tulip_chip_table tulip_tbl[];
-void oom_timer(unsigned long data);
+void oom_timer(struct timer_list *t);
 extern u8 t21040_csr13[];
 
 static inline void tulip_start_rxtx(struct tulip_private *tp)
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 851b6d1f5a42..00d02a0967d0 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -123,10 +123,10 @@ int tulip_debug = TULIP_DEBUG;
 int tulip_debug = 1;
 #endif
 
-static void tulip_timer(unsigned long data)
+static void tulip_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct tulip_private *tp = netdev_priv(dev);
+	struct tulip_private *tp = from_timer(tp, t, timer);
+	struct net_device *dev = tp->dev;
 
 	if (netif_running(dev))
 		schedule_work(&tp->media_work);
@@ -505,7 +505,7 @@ media_picked:
 	tp->timer.expires = RUN_AT(next_tick);
 	add_timer(&tp->timer);
 #ifdef CONFIG_TULIP_NAPI
-	setup_timer(&tp->oom_timer, oom_timer, (unsigned long)dev);
+	timer_setup(&tp->oom_timer, oom_timer, 0);
 #endif
 }
 
@@ -780,8 +780,7 @@ static void tulip_down (struct net_device *dev)
 
 	spin_unlock_irqrestore (&tp->lock, flags);
 
-	setup_timer(&tp->timer, tulip_tbl[tp->chip_id].media_timer,
-		    (unsigned long)dev);
+	timer_setup(&tp->timer, tulip_tbl[tp->chip_id].media_timer, 0);
 
 	dev->if_port = tp->saved_if_port;
 
@@ -1470,8 +1469,7 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp->csr0 = csr0;
 	spin_lock_init(&tp->lock);
 	spin_lock_init(&tp->mii_lock);
-	setup_timer(&tp->timer, tulip_tbl[tp->chip_id].media_timer,
-		    (unsigned long)dev);
+	timer_setup(&tp->timer, tulip_tbl[tp->chip_id].media_timer, 0);
 
 	INIT_WORK(&tp->media_work, tulip_tbl[tp->chip_id].media_task);
 
diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c
index 7fc248efc4ba..488a744084c9 100644
--- a/drivers/net/ethernet/dec/tulip/uli526x.c
+++ b/drivers/net/ethernet/dec/tulip/uli526x.c
@@ -241,7 +241,7 @@ static void phy_write_1bit(struct uli526x_board_info *db, u32);
 static u16 phy_read_1bit(struct uli526x_board_info *db);
 static u8 uli526x_sense_speed(struct uli526x_board_info *);
 static void uli526x_process_mode(struct uli526x_board_info *);
-static void uli526x_timer(unsigned long);
+static void uli526x_timer(struct timer_list *t);
 static void uli526x_rx_packet(struct net_device *, struct uli526x_board_info *);
 static void uli526x_free_tx_pkt(struct net_device *, struct uli526x_board_info *);
 static void uli526x_reuse_skb(struct uli526x_board_info *, struct sk_buff *);
@@ -491,10 +491,8 @@ static int uli526x_open(struct net_device *dev)
 	netif_wake_queue(dev);
 
 	/* set and active a timer process */
-	init_timer(&db->timer);
+	timer_setup(&db->timer, uli526x_timer, 0);
 	db->timer.expires = ULI526X_TIMER_WUT + HZ * 2;
-	db->timer.data = (unsigned long)dev;
-	db->timer.function = uli526x_timer;
 	add_timer(&db->timer);
 
 	return 0;
@@ -1023,10 +1021,10 @@ static const struct ethtool_ops netdev_ethtool_ops = {
  *	Dynamic media sense, allocate Rx buffer...
  */
 
-static void uli526x_timer(unsigned long data)
+static void uli526x_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) data;
-	struct uli526x_board_info *db = netdev_priv(dev);
+	struct uli526x_board_info *db = from_timer(db, t, timer);
+	struct net_device *dev = pci_get_drvdata(db->pdev);
 	struct uli_phy_ops *phy = &db->phy;
 	void __iomem *ioaddr = db->ioaddr;
  	unsigned long flags;
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index 32d7229544fa..70cb2d689c2c 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -327,7 +327,7 @@ static int  mdio_read(struct net_device *dev, int phy_id, int location);
 static void mdio_write(struct net_device *dev, int phy_id, int location, int value);
 static int  netdev_open(struct net_device *dev);
 static int  update_link(struct net_device *dev);
-static void netdev_timer(unsigned long data);
+static void netdev_timer(struct timer_list *t);
 static void init_rxtx_rings(struct net_device *dev);
 static void free_rxtx_rings(struct netdev_private *np);
 static void init_registers(struct net_device *dev);
@@ -655,10 +655,8 @@ static int netdev_open(struct net_device *dev)
 		netdev_dbg(dev, "Done netdev_open()\n");
 
 	/* Set the timer to check for link beat. */
-	init_timer(&np->timer);
+	timer_setup(&np->timer, netdev_timer, 0);
 	np->timer.expires = jiffies + 1*HZ;
-	np->timer.data = (unsigned long)dev;
-	np->timer.function = netdev_timer;				/* timer handler */
 	add_timer(&np->timer);
 	return 0;
 out_err:
@@ -774,10 +772,10 @@ static inline void update_csr6(struct net_device *dev, int new)
 		np->mii_if.full_duplex = 1;
 }
 
-static void netdev_timer(unsigned long data)
+static void netdev_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct netdev_private *np = netdev_priv(dev);
+	struct netdev_private *np = from_timer(np, t, timer);
+	struct net_device *dev = pci_get_drvdata(np->pci_dev);
 	void __iomem *ioaddr = np->base_addr;
 
 	if (debug > 2)
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index 778f974e2928..f0536b16b3c3 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -68,7 +68,7 @@ static const int max_intrloop = 50;
 static const int multicast_filter_limit = 0x40;
 
 static int rio_open (struct net_device *dev);
-static void rio_timer (unsigned long data);
+static void rio_timer (struct timer_list *t);
 static void rio_tx_timeout (struct net_device *dev);
 static netdev_tx_t start_xmit (struct sk_buff *skb, struct net_device *dev);
 static irqreturn_t rio_interrupt (int irq, void *dev_instance);
@@ -313,7 +313,7 @@ find_miiphy (struct net_device *dev)
 {
 	struct netdev_private *np = netdev_priv(dev);
 	int i, phy_found = 0;
-	np = netdev_priv(dev);
+
 	np->phy_addr = 1;
 
 	for (i = 31; i >= 0; i--) {
@@ -644,7 +644,7 @@ static int rio_open(struct net_device *dev)
 		return i;
 	}
 
-	setup_timer(&np->timer, rio_timer, (unsigned long)dev);
+	timer_setup(&np->timer, rio_timer, 0);
 	np->timer.expires = jiffies + 1 * HZ;
 	add_timer(&np->timer);
 
@@ -655,10 +655,10 @@ static int rio_open(struct net_device *dev)
 }
 
 static void
-rio_timer (unsigned long data)
+rio_timer (struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct netdev_private *np = netdev_priv(dev);
+	struct netdev_private *np = from_timer(np, t, timer);
+	struct net_device *dev = pci_get_drvdata(np->pdev);
 	unsigned int entry;
 	int next_tick = 1*HZ;
 	unsigned long flags;
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index 2704bcf023be..1a27176381fb 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -431,7 +431,7 @@ static void mdio_write(struct net_device *dev, int phy_id, int location, int val
 static int  mdio_wait_link(struct net_device *dev, int wait);
 static int  netdev_open(struct net_device *dev);
 static void check_duplex(struct net_device *dev);
-static void netdev_timer(unsigned long data);
+static void netdev_timer(struct timer_list *t);
 static void tx_timeout(struct net_device *dev);
 static void init_ring(struct net_device *dev);
 static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev);
@@ -913,10 +913,8 @@ static int netdev_open(struct net_device *dev)
 			   ioread16(ioaddr + MACCtrl1), ioread16(ioaddr + MACCtrl0));
 
 	/* Set the timer to check for link beat. */
-	init_timer(&np->timer);
+	timer_setup(&np->timer, netdev_timer, 0);
 	np->timer.expires = jiffies + 3*HZ;
-	np->timer.data = (unsigned long)dev;
-	np->timer.function = netdev_timer;				/* timer handler */
 	add_timer(&np->timer);
 
 	/* Enable interrupts by setting the interrupt mask. */
@@ -953,10 +951,10 @@ static void check_duplex(struct net_device *dev)
 	}
 }
 
-static void netdev_timer(unsigned long data)
+static void netdev_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct netdev_private *np = netdev_priv(dev);
+	struct netdev_private *np = from_timer(np, t, timer);
+	struct net_device *dev = np->mii_if.dev;
 	void __iomem *ioaddr = np->base;
 	int next_tick = 10*HZ;
 
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 9ed8e4b81530..78db8e62a83f 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -21,6 +21,7 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <linux/clk.h>
 #include <linux/dma-mapping.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
@@ -59,6 +60,9 @@
 /* Min number of tx ring entries before stopping queue */
 #define TX_THRESHOLD		(MAX_SKB_FRAGS + 1)
 
+#define FTGMAC_100MHZ		100000000
+#define FTGMAC_25MHZ		25000000
+
 struct ftgmac100 {
 	/* Registers */
 	struct resource *res;
@@ -96,6 +100,7 @@ struct ftgmac100 {
 	struct napi_struct napi;
 	struct work_struct reset_task;
 	struct mii_bus *mii_bus;
+	struct clk *clk;
 
 	/* Link management */
 	int cur_speed;
@@ -1734,6 +1739,22 @@ static void ftgmac100_ncsi_handler(struct ncsi_dev *nd)
 		    nd->link_up ? "up" : "down");
 }
 
+static void ftgmac100_setup_clk(struct ftgmac100 *priv)
+{
+	priv->clk = devm_clk_get(priv->dev, NULL);
+	if (IS_ERR(priv->clk))
+		return;
+
+	clk_prepare_enable(priv->clk);
+
+	/* Aspeed specifies a 100MHz clock is required for up to
+	 * 1000Mbit link speeds. As NCSI is limited to 100Mbit, 25MHz
+	 * is sufficient
+	 */
+	clk_set_rate(priv->clk, priv->use_ncsi ? FTGMAC_25MHZ :
+			FTGMAC_100MHZ);
+}
+
 static int ftgmac100_probe(struct platform_device *pdev)
 {
 	struct resource *res;
@@ -1830,6 +1851,9 @@ static int ftgmac100_probe(struct platform_device *pdev)
 			goto err_setup_mdio;
 	}
 
+	if (priv->is_aspeed)
+		ftgmac100_setup_clk(priv);
+
 	/* Default ring sizes */
 	priv->rx_q_entries = priv->new_rx_q_entries = DEF_RX_QUEUE_ENTRIES;
 	priv->tx_q_entries = priv->new_tx_q_entries = DEF_TX_QUEUE_ENTRIES;
@@ -1883,6 +1907,8 @@ static int ftgmac100_remove(struct platform_device *pdev)
 
 	unregister_netdev(netdev);
 
+	clk_disable_unprepare(priv->clk);
+
 	/* There's a small chance the reset task will have been re-queued,
 	 * during stop, make sure it's gone before we free the structure.
 	 */
diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c
index 66928a922824..aecc76504b69 100644
--- a/drivers/net/ethernet/faraday/ftmac100.c
+++ b/drivers/net/ethernet/faraday/ftmac100.c
@@ -402,6 +402,7 @@ static bool ftmac100_rx_packet(struct ftmac100 *priv, int *processed)
 	struct page *page;
 	dma_addr_t map;
 	int length;
+	bool ret;
 
 	rxdes = ftmac100_rx_locate_first_segment(priv);
 	if (!rxdes)
@@ -416,8 +417,8 @@ static bool ftmac100_rx_packet(struct ftmac100 *priv, int *processed)
 	 * It is impossible to get multi-segment packets
 	 * because we always provide big enough receive buffers.
 	 */
-	if (unlikely(!ftmac100_rxdes_last_segment(rxdes)))
-		BUG();
+	ret = ftmac100_rxdes_last_segment(rxdes);
+	BUG_ON(!ret);
 
 	/* start processing */
 	skb = netdev_alloc_skb_ip_align(netdev, 128);
diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index e92859dab7ae..23053919ebf5 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -426,8 +426,8 @@ static void mdio_write(struct net_device *dev, int phy_id, int location, int val
 static int netdev_open(struct net_device *dev);
 static void getlinktype(struct net_device *dev);
 static void getlinkstatus(struct net_device *dev);
-static void netdev_timer(unsigned long data);
-static void reset_timer(unsigned long data);
+static void netdev_timer(struct timer_list *t);
+static void reset_timer(struct timer_list *t);
 static void fealnx_tx_timeout(struct net_device *dev);
 static void init_ring(struct net_device *dev);
 static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev);
@@ -909,17 +909,13 @@ static int netdev_open(struct net_device *dev)
 		printk(KERN_DEBUG "%s: Done netdev_open().\n", dev->name);
 
 	/* Set the timer to check for link beat. */
-	init_timer(&np->timer);
+	timer_setup(&np->timer, netdev_timer, 0);
 	np->timer.expires = RUN_AT(3 * HZ);
-	np->timer.data = (unsigned long) dev;
-	np->timer.function = netdev_timer;
 
 	/* timer handler */
 	add_timer(&np->timer);
 
-	init_timer(&np->reset_timer);
-	np->reset_timer.data = (unsigned long) dev;
-	np->reset_timer.function = reset_timer;
+	timer_setup(&np->reset_timer, reset_timer, 0);
 	np->reset_timer_armed = 0;
 	return rc;
 }
@@ -1082,10 +1078,10 @@ static void allocate_rx_buffers(struct net_device *dev)
 }
 
 
-static void netdev_timer(unsigned long data)
+static void netdev_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) data;
-	struct netdev_private *np = netdev_priv(dev);
+	struct netdev_private *np = from_timer(np, t, timer);
+	struct net_device *dev = np->mii.dev;
 	void __iomem *ioaddr = np->mem;
 	int old_crvalue = np->crvalue;
 	unsigned int old_linkok = np->linkok;
@@ -1171,10 +1167,10 @@ static void enable_rxtx(struct net_device *dev)
 }
 
 
-static void reset_timer(unsigned long data)
+static void reset_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) data;
-	struct netdev_private *np = netdev_priv(dev);
+	struct netdev_private *np = from_timer(np, t, reset_timer);
+	struct net_device *dev = np->mii.dev;
 	unsigned long flags;
 
 	printk(KERN_WARNING "%s: resetting tx and rx machinery\n", dev->name);
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 42258060f142..969f6b12952e 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -385,34 +385,19 @@ out:
 
 static struct mac_device *dpaa_mac_dev_get(struct platform_device *pdev)
 {
-	struct platform_device *of_dev;
 	struct dpaa_eth_data *eth_data;
-	struct device *dpaa_dev, *dev;
-	struct device_node *mac_node;
+	struct device *dpaa_dev;
 	struct mac_device *mac_dev;
 
 	dpaa_dev = &pdev->dev;
 	eth_data = dpaa_dev->platform_data;
-	if (!eth_data)
+	if (!eth_data) {
+		dev_err(dpaa_dev, "eth_data missing\n");
 		return ERR_PTR(-ENODEV);
-
-	mac_node = eth_data->mac_node;
-
-	of_dev = of_find_device_by_node(mac_node);
-	if (!of_dev) {
-		dev_err(dpaa_dev, "of_find_device_by_node(%pOF) failed\n",
-			mac_node);
-		of_node_put(mac_node);
-		return ERR_PTR(-EINVAL);
 	}
-	of_node_put(mac_node);
-
-	dev = &of_dev->dev;
-
-	mac_dev = dev_get_drvdata(dev);
+	mac_dev = eth_data->mac_dev;
 	if (!mac_dev) {
-		dev_err(dpaa_dev, "dev_get_drvdata(%s) failed\n",
-			dev_name(dev));
+		dev_err(dpaa_dev, "mac_dev missing\n");
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -2435,6 +2420,44 @@ static void dpaa_eth_napi_disable(struct dpaa_priv *priv)
 	}
 }
 
+static void dpaa_adjust_link(struct net_device *net_dev)
+{
+	struct mac_device *mac_dev;
+	struct dpaa_priv *priv;
+
+	priv = netdev_priv(net_dev);
+	mac_dev = priv->mac_dev;
+	mac_dev->adjust_link(mac_dev);
+}
+
+static int dpaa_phy_init(struct net_device *net_dev)
+{
+	struct mac_device *mac_dev;
+	struct phy_device *phy_dev;
+	struct dpaa_priv *priv;
+
+	priv = netdev_priv(net_dev);
+	mac_dev = priv->mac_dev;
+
+	phy_dev = of_phy_connect(net_dev, mac_dev->phy_node,
+				 &dpaa_adjust_link, 0,
+				 mac_dev->phy_if);
+	if (!phy_dev) {
+		netif_err(priv, ifup, net_dev, "init_phy() failed\n");
+		return -ENODEV;
+	}
+
+	/* Remove any features not supported by the controller */
+	phy_dev->supported &= mac_dev->if_support;
+	phy_dev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause);
+	phy_dev->advertising = phy_dev->supported;
+
+	mac_dev->phy_dev = phy_dev;
+	net_dev->phydev = phy_dev;
+
+	return 0;
+}
+
 static int dpaa_open(struct net_device *net_dev)
 {
 	struct mac_device *mac_dev;
@@ -2445,12 +2468,9 @@ static int dpaa_open(struct net_device *net_dev)
 	mac_dev = priv->mac_dev;
 	dpaa_eth_napi_enable(priv);
 
-	net_dev->phydev = mac_dev->init_phy(net_dev, priv->mac_dev);
-	if (!net_dev->phydev) {
-		netif_err(priv, ifup, net_dev, "init_phy() failed\n");
-		err = -ENODEV;
+	err = dpaa_phy_init(net_dev);
+	if (err)
 		goto phy_init_failed;
-	}
 
 	for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) {
 		err = fman_port_enable(mac_dev->port[i]);
@@ -2649,7 +2669,6 @@ static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl)
 static int dpaa_eth_probe(struct platform_device *pdev)
 {
 	struct dpaa_bp *dpaa_bps[DPAA_BPS_NUM] = {NULL};
-	struct dpaa_percpu_priv *percpu_priv;
 	struct net_device *net_dev = NULL;
 	struct dpaa_fq *dpaa_fq, *tmp;
 	struct dpaa_priv *priv = NULL;
@@ -2658,7 +2677,13 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	int err = 0, i, channel;
 	struct device *dev;
 
-	dev = &pdev->dev;
+	/* device used for DMA mapping */
+	dev = pdev->dev.parent;
+	err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(40));
+	if (err) {
+		dev_err(dev, "dma_coerce_mask_and_coherent() failed\n");
+		return err;
+	}
 
 	/* Allocate this early, so we can store relevant information in
 	 * the private area
@@ -2666,7 +2691,7 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	net_dev = alloc_etherdev_mq(sizeof(*priv), DPAA_ETH_TXQ_NUM);
 	if (!net_dev) {
 		dev_err(dev, "alloc_etherdev_mq() failed\n");
-		goto alloc_etherdev_mq_failed;
+		return -ENOMEM;
 	}
 
 	/* Do this here, so we can be verbose early */
@@ -2682,7 +2707,7 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	if (IS_ERR(mac_dev)) {
 		dev_err(dev, "dpaa_mac_dev_get() failed\n");
 		err = PTR_ERR(mac_dev);
-		goto mac_probe_failed;
+		goto free_netdev;
 	}
 
 	/* If fsl_fm_max_frm is set to a higher value than the all-common 1500,
@@ -2700,21 +2725,13 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	priv->buf_layout[RX].priv_data_size = DPAA_RX_PRIV_DATA_SIZE; /* Rx */
 	priv->buf_layout[TX].priv_data_size = DPAA_TX_PRIV_DATA_SIZE; /* Tx */
 
-	/* device used for DMA mapping */
-	set_dma_ops(dev, get_dma_ops(&pdev->dev));
-	err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(40));
-	if (err) {
-		dev_err(dev, "dma_coerce_mask_and_coherent() failed\n");
-		goto dev_mask_failed;
-	}
-
 	/* bp init */
 	for (i = 0; i < DPAA_BPS_NUM; i++) {
 		int err;
 
 		dpaa_bps[i] = dpaa_bp_alloc(dev);
 		if (IS_ERR(dpaa_bps[i]))
-			return PTR_ERR(dpaa_bps[i]);
+			goto free_dpaa_bps;
 		/* the raw size of the buffers used for reception */
 		dpaa_bps[i]->raw_size = bpool_buffer_raw_size(i, DPAA_BPS_NUM);
 		/* avoid runtime computations by keeping the usable size here */
@@ -2722,11 +2739,8 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 		dpaa_bps[i]->dev = dev;
 
 		err = dpaa_bp_alloc_pool(dpaa_bps[i]);
-		if (err < 0) {
-			dpaa_bps_free(priv);
-			priv->dpaa_bps[i] = NULL;
-			goto bp_create_failed;
-		}
+		if (err < 0)
+			goto free_dpaa_bps;
 		priv->dpaa_bps[i] = dpaa_bps[i];
 	}
 
@@ -2737,7 +2751,7 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	err = dpaa_alloc_all_fqs(dev, &priv->dpaa_fq_list, &port_fqs);
 	if (err < 0) {
 		dev_err(dev, "dpaa_alloc_all_fqs() failed\n");
-		goto fq_probe_failed;
+		goto free_dpaa_bps;
 	}
 
 	priv->mac_dev = mac_dev;
@@ -2746,7 +2760,7 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	if (channel < 0) {
 		dev_err(dev, "dpaa_get_channel() failed\n");
 		err = channel;
-		goto get_channel_failed;
+		goto free_dpaa_bps;
 	}
 
 	priv->channel = (u16)channel;
@@ -2766,20 +2780,20 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	err = dpaa_eth_cgr_init(priv);
 	if (err < 0) {
 		dev_err(dev, "Error initializing CGR\n");
-		goto tx_cgr_init_failed;
+		goto free_dpaa_bps;
 	}
 
 	err = dpaa_ingress_cgr_init(priv);
 	if (err < 0) {
 		dev_err(dev, "Error initializing ingress CGR\n");
-		goto rx_cgr_init_failed;
+		goto delete_egress_cgr;
 	}
 
 	/* Add the FQs to the interface, and make them active */
 	list_for_each_entry_safe(dpaa_fq, tmp, &priv->dpaa_fq_list, list) {
 		err = dpaa_fq_init(dpaa_fq, false);
 		if (err < 0)
-			goto fq_alloc_failed;
+			goto free_dpaa_fqs;
 	}
 
 	priv->tx_headroom = dpaa_get_headroom(&priv->buf_layout[TX]);
@@ -2789,7 +2803,7 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	err = dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs,
 				  &priv->buf_layout[0], dev);
 	if (err)
-		goto init_ports_failed;
+		goto free_dpaa_fqs;
 
 	/* Rx traffic distribution based on keygen hashing defaults to on */
 	priv->keygen_in_use = true;
@@ -2798,11 +2812,7 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	if (!priv->percpu_priv) {
 		dev_err(dev, "devm_alloc_percpu() failed\n");
 		err = -ENOMEM;
-		goto alloc_percpu_failed;
-	}
-	for_each_possible_cpu(i) {
-		percpu_priv = per_cpu_ptr(priv->percpu_priv, i);
-		memset(percpu_priv, 0, sizeof(*percpu_priv));
+		goto free_dpaa_fqs;
 	}
 
 	priv->num_tc = 1;
@@ -2811,11 +2821,11 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	/* Initialize NAPI */
 	err = dpaa_napi_add(net_dev);
 	if (err < 0)
-		goto napi_add_failed;
+		goto delete_dpaa_napi;
 
 	err = dpaa_netdev_init(net_dev, &dpaa_ops, tx_timeout);
 	if (err < 0)
-		goto netdev_init_failed;
+		goto delete_dpaa_napi;
 
 	dpaa_eth_sysfs_init(&net_dev->dev);
 
@@ -2824,32 +2834,21 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 
 	return 0;
 
-netdev_init_failed:
-napi_add_failed:
+delete_dpaa_napi:
 	dpaa_napi_del(net_dev);
-alloc_percpu_failed:
-init_ports_failed:
+free_dpaa_fqs:
 	dpaa_fq_free(dev, &priv->dpaa_fq_list);
-fq_alloc_failed:
 	qman_delete_cgr_safe(&priv->ingress_cgr);
 	qman_release_cgrid(priv->ingress_cgr.cgrid);
-rx_cgr_init_failed:
+delete_egress_cgr:
 	qman_delete_cgr_safe(&priv->cgr_data.cgr);
 	qman_release_cgrid(priv->cgr_data.cgr.cgrid);
-tx_cgr_init_failed:
-get_channel_failed:
+free_dpaa_bps:
 	dpaa_bps_free(priv);
-bp_create_failed:
-fq_probe_failed:
-dev_mask_failed:
-mac_probe_failed:
+free_netdev:
 	dev_set_drvdata(dev, NULL);
 	free_netdev(net_dev);
-alloc_etherdev_mq_failed:
-	for (i = 0; i < DPAA_BPS_NUM && dpaa_bps[i]; i++) {
-		if (atomic_read(&dpaa_bps[i]->refs) == 0)
-			devm_kfree(dev, dpaa_bps[i]);
-	}
+
 	return err;
 }
 
diff --git a/drivers/net/ethernet/freescale/fman/Makefile b/drivers/net/ethernet/freescale/fman/Makefile
index f83a3653b63b..b618091db091 100644
--- a/drivers/net/ethernet/freescale/fman/Makefile
+++ b/drivers/net/ethernet/freescale/fman/Makefile
@@ -1,10 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 subdir-ccflags-y +=  -I$(srctree)/drivers/net/ethernet/freescale/fman
 
-obj-$(CONFIG_FSL_FMAN) += fsl_fman.o
-obj-$(CONFIG_FSL_FMAN) += fsl_fman_port.o
-obj-$(CONFIG_FSL_FMAN) += fsl_mac.o
+obj-$(CONFIG_FSL_FMAN) += fsl_dpaa_fman.o
+obj-$(CONFIG_FSL_FMAN) += fsl_dpaa_fman_port.o
+obj-$(CONFIG_FSL_FMAN) += fsl_dpaa_mac.o
 
-fsl_fman-objs	:= fman_muram.o fman.o fman_sp.o fman_keygen.o
-fsl_fman_port-objs := fman_port.o
-fsl_mac-objs:= mac.o fman_dtsec.o fman_memac.o fman_tgec.o
+fsl_dpaa_fman-objs	:= fman_muram.o fman.o fman_sp.o fman_keygen.o
+fsl_dpaa_fman_port-objs := fman_port.o
+fsl_dpaa_mac-objs:= mac.o fman_dtsec.o fman_memac.o fman_tgec.o
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index 387eb4a88b72..1d6da1ea7bfb 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -57,9 +57,7 @@ struct mac_priv_s {
 	struct device			*dev;
 	void __iomem			*vaddr;
 	u8				cell_index;
-	phy_interface_t			phy_if;
 	struct fman			*fman;
-	struct device_node		*phy_node;
 	struct device_node		*internal_phy_node;
 	/* List of multicast addresses */
 	struct list_head		mc_addr_list;
@@ -106,7 +104,7 @@ static void set_fman_mac_params(struct mac_device *mac_dev,
 			     resource_size(mac_dev->res));
 	memcpy(&params->addr, mac_dev->addr, sizeof(mac_dev->addr));
 	params->max_speed	= priv->max_speed;
-	params->phy_if		= priv->phy_if;
+	params->phy_if		= mac_dev->phy_if;
 	params->basex_if	= false;
 	params->mac_id		= priv->cell_index;
 	params->fm		= (void *)priv->fman;
@@ -419,15 +417,12 @@ void fman_get_pause_cfg(struct mac_device *mac_dev, bool *rx_pause,
 }
 EXPORT_SYMBOL(fman_get_pause_cfg);
 
-static void adjust_link_void(struct net_device *net_dev)
+static void adjust_link_void(struct mac_device *mac_dev)
 {
 }
 
-static void adjust_link_dtsec(struct net_device *net_dev)
+static void adjust_link_dtsec(struct mac_device *mac_dev)
 {
-	struct device *dev = net_dev->dev.parent;
-	struct dpaa_eth_data *eth_data = dev->platform_data;
-	struct mac_device *mac_dev = eth_data->mac_dev;
 	struct phy_device *phy_dev = mac_dev->phy_dev;
 	struct fman_mac *fman_mac;
 	bool rx_pause, tx_pause;
@@ -444,14 +439,12 @@ static void adjust_link_dtsec(struct net_device *net_dev)
 	fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause);
 	err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause);
 	if (err < 0)
-		netdev_err(net_dev, "fman_set_mac_active_pause() = %d\n", err);
+		dev_err(mac_dev->priv->dev, "fman_set_mac_active_pause() = %d\n",
+			err);
 }
 
-static void adjust_link_memac(struct net_device *net_dev)
+static void adjust_link_memac(struct mac_device *mac_dev)
 {
-	struct device *dev = net_dev->dev.parent;
-	struct dpaa_eth_data *eth_data = dev->platform_data;
-	struct mac_device *mac_dev = eth_data->mac_dev;
 	struct phy_device *phy_dev = mac_dev->phy_dev;
 	struct fman_mac *fman_mac;
 	bool rx_pause, tx_pause;
@@ -463,60 +456,12 @@ static void adjust_link_memac(struct net_device *net_dev)
 	fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause);
 	err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause);
 	if (err < 0)
-		netdev_err(net_dev, "fman_set_mac_active_pause() = %d\n", err);
-}
-
-/* Initializes driver's PHY state, and attaches to the PHY.
- * Returns 0 on success.
- */
-static struct phy_device *init_phy(struct net_device *net_dev,
-				   struct mac_device *mac_dev,
-				   void (*adj_lnk)(struct net_device *))
-{
-	struct phy_device	*phy_dev;
-	struct mac_priv_s	*priv = mac_dev->priv;
-
-	phy_dev = of_phy_connect(net_dev, priv->phy_node, adj_lnk, 0,
-				 priv->phy_if);
-	if (!phy_dev) {
-		netdev_err(net_dev, "Could not connect to PHY\n");
-		return NULL;
-	}
-
-	/* Remove any features not supported by the controller */
-	phy_dev->supported &= mac_dev->if_support;
-	/* Enable the symmetric and asymmetric PAUSE frame advertisements,
-	 * as most of the PHY drivers do not enable them by default.
-	 */
-	phy_dev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause);
-	phy_dev->advertising = phy_dev->supported;
-
-	mac_dev->phy_dev = phy_dev;
-
-	return phy_dev;
-}
-
-static struct phy_device *dtsec_init_phy(struct net_device *net_dev,
-					 struct mac_device *mac_dev)
-{
-	return init_phy(net_dev, mac_dev, &adjust_link_dtsec);
-}
-
-static struct phy_device *tgec_init_phy(struct net_device *net_dev,
-					struct mac_device *mac_dev)
-{
-	return init_phy(net_dev, mac_dev, adjust_link_void);
-}
-
-static struct phy_device *memac_init_phy(struct net_device *net_dev,
-					 struct mac_device *mac_dev)
-{
-	return init_phy(net_dev, mac_dev, &adjust_link_memac);
+		dev_err(mac_dev->priv->dev, "fman_set_mac_active_pause() = %d\n",
+			err);
 }
 
 static void setup_dtsec(struct mac_device *mac_dev)
 {
-	mac_dev->init_phy		= dtsec_init_phy;
 	mac_dev->init			= dtsec_initialization;
 	mac_dev->set_promisc		= dtsec_set_promiscuous;
 	mac_dev->change_addr		= dtsec_modify_mac_address;
@@ -528,14 +473,13 @@ static void setup_dtsec(struct mac_device *mac_dev)
 	mac_dev->set_multi		= set_multi;
 	mac_dev->start			= start;
 	mac_dev->stop			= stop;
-
+	mac_dev->adjust_link            = adjust_link_dtsec;
 	mac_dev->priv->enable		= dtsec_enable;
 	mac_dev->priv->disable		= dtsec_disable;
 }
 
 static void setup_tgec(struct mac_device *mac_dev)
 {
-	mac_dev->init_phy		= tgec_init_phy;
 	mac_dev->init			= tgec_initialization;
 	mac_dev->set_promisc		= tgec_set_promiscuous;
 	mac_dev->change_addr		= tgec_modify_mac_address;
@@ -547,14 +491,13 @@ static void setup_tgec(struct mac_device *mac_dev)
 	mac_dev->set_multi		= set_multi;
 	mac_dev->start			= start;
 	mac_dev->stop			= stop;
-
+	mac_dev->adjust_link            = adjust_link_void;
 	mac_dev->priv->enable		= tgec_enable;
 	mac_dev->priv->disable		= tgec_disable;
 }
 
 static void setup_memac(struct mac_device *mac_dev)
 {
-	mac_dev->init_phy		= memac_init_phy;
 	mac_dev->init			= memac_initialization;
 	mac_dev->set_promisc		= memac_set_promiscuous;
 	mac_dev->change_addr		= memac_modify_mac_address;
@@ -566,7 +509,7 @@ static void setup_memac(struct mac_device *mac_dev)
 	mac_dev->set_multi		= set_multi;
 	mac_dev->start			= start;
 	mac_dev->stop			= stop;
-
+	mac_dev->adjust_link            = adjust_link_memac;
 	mac_dev->priv->enable		= memac_enable;
 	mac_dev->priv->disable		= memac_disable;
 }
@@ -599,8 +542,7 @@ static const u16 phy2speed[] = {
 };
 
 static struct platform_device *dpaa_eth_add_device(int fman_id,
-						   struct mac_device *mac_dev,
-						   struct device_node *node)
+						   struct mac_device *mac_dev)
 {
 	struct platform_device *pdev;
 	struct dpaa_eth_data data;
@@ -613,17 +555,14 @@ static struct platform_device *dpaa_eth_add_device(int fman_id,
 	data.mac_dev = mac_dev;
 	data.mac_hw_id = priv->cell_index;
 	data.fman_hw_id = fman_id;
-	data.mac_node = node;
 
 	mutex_lock(&eth_lock);
-
 	pdev = platform_device_alloc("dpaa-ethernet", dpaa_eth_dev_cnt);
 	if (!pdev) {
 		ret = -ENOMEM;
 		goto no_mem;
 	}
 
-	pdev->dev.of_node = node;
 	pdev->dev.parent = priv->dev;
 	set_dma_ops(&pdev->dev, get_dma_ops(priv->dev));
 
@@ -706,9 +645,6 @@ static int mac_probe(struct platform_device *_of_dev)
 		goto _return;
 	}
 
-	/* Register mac_dev */
-	dev_set_drvdata(dev, mac_dev);
-
 	INIT_LIST_HEAD(&priv->mc_addr_list);
 
 	/* Get the FM node */
@@ -717,7 +653,7 @@ static int mac_probe(struct platform_device *_of_dev)
 		dev_err(dev, "of_get_parent(%pOF) failed\n",
 			mac_node);
 		err = -EINVAL;
-		goto _return_dev_set_drvdata;
+		goto _return_of_get_parent;
 	}
 
 	of_dev = of_find_device_by_node(dev_node);
@@ -751,7 +687,7 @@ static int mac_probe(struct platform_device *_of_dev)
 	if (err < 0) {
 		dev_err(dev, "of_address_to_resource(%pOF) = %d\n",
 			mac_node, err);
-		goto _return_dev_set_drvdata;
+		goto _return_of_get_parent;
 	}
 
 	mac_dev->res = __devm_request_region(dev,
@@ -761,7 +697,7 @@ static int mac_probe(struct platform_device *_of_dev)
 	if (!mac_dev->res) {
 		dev_err(dev, "__devm_request_mem_region(mac) failed\n");
 		err = -EBUSY;
-		goto _return_dev_set_drvdata;
+		goto _return_of_get_parent;
 	}
 
 	priv->vaddr = devm_ioremap(dev, mac_dev->res->start,
@@ -769,7 +705,7 @@ static int mac_probe(struct platform_device *_of_dev)
 	if (!priv->vaddr) {
 		dev_err(dev, "devm_ioremap() failed\n");
 		err = -EIO;
-		goto _return_dev_set_drvdata;
+		goto _return_of_get_parent;
 	}
 
 	if (!of_device_is_available(mac_node)) {
@@ -786,7 +722,7 @@ static int mac_probe(struct platform_device *_of_dev)
 	if (err) {
 		dev_err(dev, "failed to read cell-index for %pOF\n", mac_node);
 		err = -EINVAL;
-		goto _return_dev_set_drvdata;
+		goto _return_of_get_parent;
 	}
 	priv->cell_index = (u8)val;
 
@@ -795,7 +731,7 @@ static int mac_probe(struct platform_device *_of_dev)
 	if (!mac_addr) {
 		dev_err(dev, "of_get_mac_address(%pOF) failed\n", mac_node);
 		err = -EINVAL;
-		goto _return_dev_set_drvdata;
+		goto _return_of_get_parent;
 	}
 	memcpy(mac_dev->addr, mac_addr, sizeof(mac_dev->addr));
 
@@ -805,14 +741,14 @@ static int mac_probe(struct platform_device *_of_dev)
 		dev_err(dev, "of_count_phandle_with_args(%pOF, fsl,fman-ports) failed\n",
 			mac_node);
 		err = nph;
-		goto _return_dev_set_drvdata;
+		goto _return_of_get_parent;
 	}
 
 	if (nph != ARRAY_SIZE(mac_dev->port)) {
 		dev_err(dev, "Not supported number of fman-ports handles of mac node %pOF from device tree\n",
 			mac_node);
 		err = -EINVAL;
-		goto _return_dev_set_drvdata;
+		goto _return_of_get_parent;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) {
@@ -851,13 +787,13 @@ static int mac_probe(struct platform_device *_of_dev)
 			 mac_node);
 		phy_if = PHY_INTERFACE_MODE_SGMII;
 	}
-	priv->phy_if = phy_if;
+	mac_dev->phy_if = phy_if;
 
-	priv->speed		= phy2speed[priv->phy_if];
+	priv->speed		= phy2speed[mac_dev->phy_if];
 	priv->max_speed		= priv->speed;
 	mac_dev->if_support	= DTSEC_SUPPORTED;
 	/* We don't support half-duplex in SGMII mode */
-	if (priv->phy_if == PHY_INTERFACE_MODE_SGMII)
+	if (mac_dev->phy_if == PHY_INTERFACE_MODE_SGMII)
 		mac_dev->if_support &= ~(SUPPORTED_10baseT_Half |
 					SUPPORTED_100baseT_Half);
 
@@ -866,30 +802,30 @@ static int mac_probe(struct platform_device *_of_dev)
 		mac_dev->if_support |= SUPPORTED_1000baseT_Full;
 
 	/* The 10G interface only supports one mode */
-	if (priv->phy_if == PHY_INTERFACE_MODE_XGMII)
+	if (mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII)
 		mac_dev->if_support = SUPPORTED_10000baseT_Full;
 
 	/* Get the rest of the PHY information */
-	priv->phy_node = of_parse_phandle(mac_node, "phy-handle", 0);
-	if (!priv->phy_node && of_phy_is_fixed_link(mac_node)) {
+	mac_dev->phy_node = of_parse_phandle(mac_node, "phy-handle", 0);
+	if (!mac_dev->phy_node && of_phy_is_fixed_link(mac_node)) {
 		struct phy_device *phy;
 
 		err = of_phy_register_fixed_link(mac_node);
 		if (err)
-			goto _return_dev_set_drvdata;
+			goto _return_of_get_parent;
 
 		priv->fixed_link = kzalloc(sizeof(*priv->fixed_link),
 					   GFP_KERNEL);
 		if (!priv->fixed_link) {
 			err = -ENOMEM;
-			goto _return_dev_set_drvdata;
+			goto _return_of_get_parent;
 		}
 
-		priv->phy_node = of_node_get(mac_node);
-		phy = of_phy_find_device(priv->phy_node);
+		mac_dev->phy_node = of_node_get(mac_node);
+		phy = of_phy_find_device(mac_dev->phy_node);
 		if (!phy) {
 			err = -EINVAL;
-			goto _return_dev_set_drvdata;
+			goto _return_of_get_parent;
 		}
 
 		priv->fixed_link->link = phy->link;
@@ -904,8 +840,8 @@ static int mac_probe(struct platform_device *_of_dev)
 	err = mac_dev->init(mac_dev);
 	if (err < 0) {
 		dev_err(dev, "mac_dev->init() = %d\n", err);
-		of_node_put(priv->phy_node);
-		goto _return_dev_set_drvdata;
+		of_node_put(mac_dev->phy_node);
+		goto _return_of_get_parent;
 	}
 
 	/* pause frame autonegotiation enabled */
@@ -926,7 +862,7 @@ static int mac_probe(struct platform_device *_of_dev)
 		 mac_dev->addr[0], mac_dev->addr[1], mac_dev->addr[2],
 		 mac_dev->addr[3], mac_dev->addr[4], mac_dev->addr[5]);
 
-	priv->eth_dev = dpaa_eth_add_device(fman_id, mac_dev, mac_node);
+	priv->eth_dev = dpaa_eth_add_device(fman_id, mac_dev);
 	if (IS_ERR(priv->eth_dev)) {
 		dev_err(dev, "failed to add Ethernet platform device for MAC %d\n",
 			priv->cell_index);
@@ -937,9 +873,8 @@ static int mac_probe(struct platform_device *_of_dev)
 
 _return_of_node_put:
 	of_node_put(dev_node);
-_return_dev_set_drvdata:
+_return_of_get_parent:
 	kfree(priv->fixed_link);
-	dev_set_drvdata(dev, NULL);
 _return:
 	return err;
 }
diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h
index d7313f0c5135..eefb3357e304 100644
--- a/drivers/net/ethernet/freescale/fman/mac.h
+++ b/drivers/net/ethernet/freescale/fman/mac.h
@@ -50,6 +50,8 @@ struct mac_device {
 	struct fman_port	*port[2];
 	u32			 if_support;
 	struct phy_device	*phy_dev;
+	phy_interface_t		phy_if;
+	struct device_node	*phy_node;
 
 	bool autoneg_pause;
 	bool rx_pause_req;
@@ -58,11 +60,10 @@ struct mac_device {
 	bool tx_pause_active;
 	bool promisc;
 
-	struct phy_device *(*init_phy)(struct net_device *net_dev,
-				       struct mac_device *mac_dev);
 	int (*init)(struct mac_device *mac_dev);
 	int (*start)(struct mac_device *mac_dev);
 	int (*stop)(struct mac_device *mac_dev);
+	void (*adjust_link)(struct mac_device *mac_dev);
 	int (*set_promisc)(struct fman_mac *mac_dev, bool enable);
 	int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr);
 	int (*set_multi)(struct net_device *net_dev,
@@ -82,7 +83,6 @@ struct mac_device {
 };
 
 struct dpaa_eth_data {
-	struct device_node *mac_node;
 	struct mac_device *mac_dev;
 	int mac_hw_id;
 	int fman_hw_id;
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 753259091b22..7892f2f0c6b5 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -1023,8 +1023,6 @@ static int fs_enet_probe(struct platform_device *ofdev)
 
 	ndev->ethtool_ops = &fs_ethtool_ops;
 
-	init_timer(&fep->phy_timer_list);
-
 	netif_carrier_off(ndev);
 
 	ndev->features |= NETIF_F_SG;
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
index 168e10ea487f..92e06b37a199 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
@@ -138,7 +138,6 @@ struct fs_enet_private {
 	cbd_t __iomem *cur_rx;
 	cbd_t __iomem *cur_tx;
 	int tx_free;
-	struct timer_list phy_timer_list;
 	const struct phy_info *phy;
 	u32 msg_enable;
 	struct mii_if_info mii_if;
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index f77ba9fa257b..a96b838cffce 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -3857,8 +3857,9 @@ static int ucc_geth_probe(struct platform_device* ofdev)
 	}
 
 	if (netif_msg_probe(&debug))
-		pr_info("UCC%1d at 0x%8x (irq = %d)\n",
-			ug_info->uf_info.ucc_num + 1, ug_info->uf_info.regs,
+		pr_info("UCC%1d at 0x%8llx (irq = %d)\n",
+			ug_info->uf_info.ucc_num + 1,
+			(u64)ug_info->uf_info.regs,
 			ug_info->uf_info.irq);
 
 	/* Create an ethernet device instance */
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 91c7bdb9b43c..30000b6aa7b8 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -78,7 +78,7 @@ config HNS_ENET
 
 config HNS3
 	tristate "Hisilicon Network Subsystem Support HNS3 (Framework)"
-    depends on PCI
+	depends on PCI
 	---help---
 	  This selects the framework support for Hisilicon Network Subsystem 3.
 	  This layer facilitates clients like ENET, RoCE and user-space ethernet
@@ -87,7 +87,7 @@ config HNS3
 
 config HNS3_HCLGE
 	tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support"
-    depends on PCI_MSI
+	depends on PCI_MSI
 	depends on HNS3
 	---help---
 	  This selects the HNS3_HCLGE network acceleration engine & its hardware
@@ -96,11 +96,20 @@ config HNS3_HCLGE
 
 config HNS3_ENET
 	tristate "Hisilicon HNS3 Ethernet Device Support"
-    depends on 64BIT && PCI
+	depends on 64BIT && PCI
 	depends on HNS3 && HNS3_HCLGE
 	---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
 	  devices and their associated operations.
 
+config HNS3_DCB
+	bool "Hisilicon HNS3 Data Center Bridge Support"
+	default n
+	depends on HNS3 && HNS3_HCLGE && DCB
+	---help---
+	  Say Y here if you want to use Data Center Bridging (DCB) in the HNS3 driver.
+
+	  If unsure, say N.
+
 endif # NET_VENDOR_HISILICON
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index e77192683dba..1ccb6443d2ed 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -2159,9 +2159,9 @@ static void hns_nic_task_schedule(struct hns_nic_priv *priv)
 		(void)schedule_work(&priv->service_task);
 }
 
-static void hns_nic_service_timer(unsigned long data)
+static void hns_nic_service_timer(struct timer_list *t)
 {
-	struct hns_nic_priv *priv = (struct hns_nic_priv *)data;
+	struct hns_nic_priv *priv = from_timer(priv, t, service_timer);
 
 	(void)mod_timer(&priv->service_timer, jiffies + SERVICE_TIMER_HZ);
 
@@ -2451,8 +2451,7 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 	/* carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(ndev);
 
-	setup_timer(&priv->service_timer, hns_nic_service_timer,
-		    (unsigned long)priv);
+	timer_setup(&priv->service_timer, hns_nic_service_timer, 0);
 	INIT_WORK(&priv->service_task, hns_nic_service_task);
 
 	set_bit(NIC_STATE_SERVICE_INITED, &priv->state);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 1a01cadfe5f3..67c59e1039f2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -28,6 +28,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/dcbnl.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/module.h>
@@ -109,6 +110,21 @@ enum hnae3_media_type {
 	HNAE3_MEDIA_TYPE_BACKPLANE,
 };
 
+enum hnae3_reset_notify_type {
+	HNAE3_UP_CLIENT,
+	HNAE3_DOWN_CLIENT,
+	HNAE3_INIT_CLIENT,
+	HNAE3_UNINIT_CLIENT,
+};
+
+enum hnae3_reset_type {
+	HNAE3_FUNC_RESET,
+	HNAE3_CORE_RESET,
+	HNAE3_GLOBAL_RESET,
+	HNAE3_IMP_RESET,
+	HNAE3_NONE_RESET,
+};
+
 struct hnae3_vector_info {
 	u8 __iomem *io_addr;
 	int vector;
@@ -131,6 +147,9 @@ struct hnae3_client_ops {
 	int (*init_instance)(struct hnae3_handle *handle);
 	void (*uninit_instance)(struct hnae3_handle *handle, bool reset);
 	void (*link_status_change)(struct hnae3_handle *handle, bool state);
+	int (*setup_tc)(struct hnae3_handle *handle, u8 tc);
+	int (*reset_notify)(struct hnae3_handle *handle,
+			    enum hnae3_reset_notify_type type);
 };
 
 #define HNAE3_CLIENT_NAME_LENGTH 16
@@ -337,6 +356,10 @@ struct hnae3_ae_ops {
 		       u8 *hfunc);
 	int (*set_rss)(struct hnae3_handle *handle, const u32 *indir,
 		       const u8 *key, const u8 hfunc);
+	int (*set_rss_tuple)(struct hnae3_handle *handle,
+			     struct ethtool_rxnfc *cmd);
+	int (*get_rss_tuple)(struct hnae3_handle *handle,
+			     struct ethtool_rxnfc *cmd);
 
 	int (*get_tc_size)(struct hnae3_handle *handle);
 
@@ -361,6 +384,23 @@ struct hnae3_ae_ops {
 			       u16 vlan_id, bool is_kill);
 	int (*set_vf_vlan_filter)(struct hnae3_handle *handle, int vfid,
 				  u16 vlan, u8 qos, __be16 proto);
+	void (*reset_event)(struct hnae3_handle *handle,
+			    enum hnae3_reset_type reset);
+};
+
+struct hnae3_dcb_ops {
+	/* IEEE 802.1Qaz std */
+	int (*ieee_getets)(struct hnae3_handle *, struct ieee_ets *);
+	int (*ieee_setets)(struct hnae3_handle *, struct ieee_ets *);
+	int (*ieee_getpfc)(struct hnae3_handle *, struct ieee_pfc *);
+	int (*ieee_setpfc)(struct hnae3_handle *, struct ieee_pfc *);
+
+	/* DCBX configuration */
+	u8   (*getdcbx)(struct hnae3_handle *);
+	u8   (*setdcbx)(struct hnae3_handle *, u8);
+
+	int (*map_update)(struct hnae3_handle *);
+	int (*setup_tc)(struct hnae3_handle *, u8, u8 *);
 };
 
 struct hnae3_ae_algo {
@@ -394,6 +434,7 @@ struct hnae3_knic_private_info {
 
 	u16 num_tqps;		  /* total number of TQPs in this handle */
 	struct hnae3_queue **tqp;  /* array base of all TQPs in this instance */
+	const struct hnae3_dcb_ops *dcb_ops;
 };
 
 struct hnae3_roce_private_info {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
index 162e8a42acd0..d2b20d01a58c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
@@ -7,5 +7,9 @@ ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3
 obj-$(CONFIG_HNS3_HCLGE) += hclge.o
 hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o
 
+hclge-$(CONFIG_HNS3_DCB) += hclge_dcb.o
+
 obj-$(CONFIG_HNS3_ENET) += hns3.o
 hns3-objs = hns3_enet.o hns3_ethtool.o
+
+hns3-$(CONFIG_HNS3_DCB) += hns3_dcbnl.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 8b511e6e0ce9..ff13d1876d9e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -62,7 +62,7 @@ static void hclge_free_cmd_desc(struct hclge_cmq_ring *ring)
 	ring->desc = NULL;
 }
 
-static int hclge_init_cmd_queue(struct hclge_dev *hdev, int ring_type)
+static int hclge_alloc_cmd_queue(struct hclge_dev *hdev, int ring_type)
 {
 	struct hclge_hw *hw = &hdev->hw;
 	struct hclge_cmq_ring *ring =
@@ -79,12 +79,18 @@ static int hclge_init_cmd_queue(struct hclge_dev *hdev, int ring_type)
 		return ret;
 	}
 
-	ring->next_to_clean = 0;
-	ring->next_to_use = 0;
-
 	return 0;
 }
 
+void hclge_cmd_reuse_desc(struct hclge_desc *desc, bool is_read)
+{
+	desc->flag = cpu_to_le16(HCLGE_CMD_FLAG_NO_INTR | HCLGE_CMD_FLAG_IN);
+	if (is_read)
+		desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_WR);
+	else
+		desc->flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR);
+}
+
 void hclge_cmd_setup_basic_desc(struct hclge_desc *desc,
 				enum hclge_opcode_type opcode, bool is_read)
 {
@@ -208,7 +214,7 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	 * which will be use for hardware to write back
 	 */
 	ntc = hw->cmq.csq.next_to_use;
-	opcode = desc[0].opcode;
+	opcode = le16_to_cpu(desc[0].opcode);
 	while (handle < num) {
 		desc_to_use = &hw->cmq.csq.desc[hw->cmq.csq.next_to_use];
 		*desc_to_use = desc[handle];
@@ -225,7 +231,7 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	 * If the command is sync, wait for the firmware to write back,
 	 * if multi descriptors to be sent, use the first one to check
 	 */
-	if (HCLGE_SEND_SYNC(desc->flag)) {
+	if (HCLGE_SEND_SYNC(le16_to_cpu(desc->flag))) {
 		do {
 			if (hclge_cmd_csq_done(hw))
 				break;
@@ -244,9 +250,9 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 			pr_debug("Get cmd desc:\n");
 
 			if (likely(!hclge_is_special_opcode(opcode)))
-				desc_ret = desc[handle].retval;
+				desc_ret = le16_to_cpu(desc[handle].retval);
 			else
-				desc_ret = desc[0].retval;
+				desc_ret = le16_to_cpu(desc[0].retval);
 
 			if ((enum hclge_cmd_return_status)desc_ret ==
 			    HCLGE_CMD_EXEC_SUCCESS)
@@ -276,15 +282,15 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	return retval;
 }
 
-enum hclge_cmd_status hclge_cmd_query_firmware_version(struct hclge_hw *hw,
-						       u32 *version)
+static enum hclge_cmd_status hclge_cmd_query_firmware_version(
+		struct hclge_hw *hw, u32 *version)
 {
-	struct hclge_query_version *resp;
+	struct hclge_query_version_cmd *resp;
 	struct hclge_desc desc;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_FW_VER, 1);
-	resp = (struct hclge_query_version *)desc.data;
+	resp = (struct hclge_query_version_cmd *)desc.data;
 
 	ret = hclge_cmd_send(hw, &desc, 1);
 	if (!ret)
@@ -293,37 +299,52 @@ enum hclge_cmd_status hclge_cmd_query_firmware_version(struct hclge_hw *hw,
 	return ret;
 }
 
-int hclge_cmd_init(struct hclge_dev *hdev)
+int hclge_cmd_queue_init(struct hclge_dev *hdev)
 {
-	u32 version;
 	int ret;
 
 	/* Setup the queue entries for use cmd queue */
 	hdev->hw.cmq.csq.desc_num = HCLGE_NIC_CMQ_DESC_NUM;
 	hdev->hw.cmq.crq.desc_num = HCLGE_NIC_CMQ_DESC_NUM;
 
-	/* Setup the lock for command queue */
-	spin_lock_init(&hdev->hw.cmq.csq.lock);
-	spin_lock_init(&hdev->hw.cmq.crq.lock);
-
 	/* Setup Tx write back timeout */
 	hdev->hw.cmq.tx_timeout = HCLGE_CMDQ_TX_TIMEOUT;
 
 	/* Setup queue rings */
-	ret = hclge_init_cmd_queue(hdev, HCLGE_TYPE_CSQ);
+	ret = hclge_alloc_cmd_queue(hdev, HCLGE_TYPE_CSQ);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"CSQ ring setup error %d\n", ret);
 		return ret;
 	}
 
-	ret = hclge_init_cmd_queue(hdev, HCLGE_TYPE_CRQ);
+	ret = hclge_alloc_cmd_queue(hdev, HCLGE_TYPE_CRQ);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"CRQ ring setup error %d\n", ret);
 		goto err_csq;
 	}
 
+	return 0;
+err_csq:
+	hclge_free_cmd_desc(&hdev->hw.cmq.csq);
+	return ret;
+}
+
+int hclge_cmd_init(struct hclge_dev *hdev)
+{
+	u32 version;
+	int ret;
+
+	hdev->hw.cmq.csq.next_to_clean = 0;
+	hdev->hw.cmq.csq.next_to_use = 0;
+	hdev->hw.cmq.crq.next_to_clean = 0;
+	hdev->hw.cmq.crq.next_to_use = 0;
+
+	/* Setup the lock for command queue */
+	spin_lock_init(&hdev->hw.cmq.csq.lock);
+	spin_lock_init(&hdev->hw.cmq.crq.lock);
+
 	hclge_cmd_init_regs(&hdev->hw);
 
 	ret = hclge_cmd_query_firmware_version(&hdev->hw, &version);
@@ -337,9 +358,6 @@ int hclge_cmd_init(struct hclge_dev *hdev)
 	dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version);
 
 	return 0;
-err_csq:
-	hclge_free_cmd_desc(&hdev->hw.cmq.csq);
-	return ret;
 }
 
 static void hclge_destroy_queue(struct hclge_cmq_ring *ring)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 758cf3948131..844c83ea549e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -63,6 +63,11 @@ enum hclge_cmd_status {
 	HCLGE_ERR_CSQ_ERROR	= -3,
 };
 
+struct hclge_misc_vector {
+	u8 __iomem *addr;
+	int vector_irq;
+};
+
 struct hclge_cmq {
 	struct hclge_cmq_ring csq;
 	struct hclge_cmq_ring crq;
@@ -221,12 +226,12 @@ enum hclge_opcode_type {
 #define HCLGE_RCB_INIT_QUERY_TIMEOUT	10
 #define HCLGE_RCB_INIT_FLAG_EN_B	0
 #define HCLGE_RCB_INIT_FLAG_FINI_B	8
-struct hclge_config_rcb_init {
+struct hclge_config_rcb_init_cmd {
 	__le16 rcb_init_flag;
 	u8 rsv[22];
 };
 
-struct hclge_tqp_map {
+struct hclge_tqp_map_cmd {
 	__le16 tqp_id;	/* Absolute tqp id for in this pf */
 	u8 tqp_vf;	/* VF id */
 #define HCLGE_TQP_MAP_TYPE_PF		0
@@ -246,15 +251,15 @@ enum hclge_int_type {
 	HCLGE_INT_EVENT,
 };
 
-struct hclge_ctrl_vector_chain {
+struct hclge_ctrl_vector_chain_cmd {
 	u8 int_vector_id;
 	u8 int_cause_num;
 #define HCLGE_INT_TYPE_S	0
-#define HCLGE_INT_TYPE_M	0x3
+#define HCLGE_INT_TYPE_M	GENMASK(1, 0)
 #define HCLGE_TQP_ID_S		2
-#define HCLGE_TQP_ID_M		(0x7ff << HCLGE_TQP_ID_S)
+#define HCLGE_TQP_ID_M		GENMASK(12, 2)
 #define HCLGE_INT_GL_IDX_S	13
-#define HCLGE_INT_GL_IDX_M	(0x3 << HCLGE_INT_GL_IDX_S)
+#define HCLGE_INT_GL_IDX_M	GENMASK(14, 13)
 	__le16 tqp_type_and_id[HCLGE_VECTOR_ELEMENTS_PER_CMD];
 	u8 vfid;
 	u8 rsv;
@@ -263,18 +268,18 @@ struct hclge_ctrl_vector_chain {
 #define HCLGE_TC_NUM		8
 #define HCLGE_TC0_PRI_BUF_EN_B	15 /* Bit 15 indicate enable or not */
 #define HCLGE_BUF_UNIT_S	7  /* Buf size is united by 128 bytes */
-struct hclge_tx_buff_alloc {
+struct hclge_tx_buff_alloc_cmd {
 	__le16 tx_pkt_buff[HCLGE_TC_NUM];
 	u8 tx_buff_rsv[8];
 };
 
-struct hclge_rx_priv_buff {
+struct hclge_rx_priv_buff_cmd {
 	__le16 buf_num[HCLGE_TC_NUM];
 	__le16 shared_buf;
 	u8 rsv[6];
 };
 
-struct hclge_query_version {
+struct hclge_query_version_cmd {
 	__le32 firmware;
 	__le32 firmware_rsv[5];
 };
@@ -311,6 +316,7 @@ struct hclge_tc_thrd {
 struct hclge_priv_buf {
 	struct hclge_waterline wl;	/* Waterline for low and high*/
 	u32 buf_size;	/* TC private buffer size */
+	u32 tx_buf_size;
 	u32 enable;	/* Enable TC private buffer or not */
 };
 
@@ -321,15 +327,20 @@ struct hclge_shared_buf {
 	u32 buf_size;
 };
 
+struct hclge_pkt_buf_alloc {
+	struct hclge_priv_buf priv_buf[HCLGE_MAX_TC_NUM];
+	struct hclge_shared_buf s_buf;
+};
+
 #define HCLGE_RX_COM_WL_EN_B	15
-struct hclge_rx_com_wl_buf {
+struct hclge_rx_com_wl_buf_cmd {
 	__le16 high_wl;
 	__le16 low_wl;
 	u8 rsv[20];
 };
 
 #define HCLGE_RX_PKT_EN_B	15
-struct hclge_rx_pkt_buf {
+struct hclge_rx_pkt_buf_cmd {
 	__le16 high_pkt;
 	__le16 low_pkt;
 	u8 rsv[20];
@@ -342,7 +353,7 @@ struct hclge_rx_pkt_buf {
 #define HCLGE_PF_MAC_NUM_MASK	0x3
 #define HCLGE_PF_STATE_MAIN	BIT(HCLGE_PF_STATE_MAIN_B)
 #define HCLGE_PF_STATE_DONE	BIT(HCLGE_PF_STATE_DONE_B)
-struct hclge_func_status {
+struct hclge_func_status_cmd {
 	__le32  vf_rst_state[4];
 	u8 pf_state;
 	u8 mac_id;
@@ -353,7 +364,7 @@ struct hclge_func_status {
 	u8 rsv[2];
 };
 
-struct hclge_pf_res {
+struct hclge_pf_res_cmd {
 	__le16 tqp_num;
 	__le16 buf_size;
 	__le16 msixcap_localid_ba_nic;
@@ -366,30 +377,30 @@ struct hclge_pf_res {
 };
 
 #define HCLGE_CFG_OFFSET_S	0
-#define HCLGE_CFG_OFFSET_M	0xfffff /* Byte (8-10.3) */
+#define HCLGE_CFG_OFFSET_M	GENMASK(19, 0)
 #define HCLGE_CFG_RD_LEN_S	24
-#define HCLGE_CFG_RD_LEN_M	(0xf << HCLGE_CFG_RD_LEN_S)
+#define HCLGE_CFG_RD_LEN_M	GENMASK(27, 24)
 #define HCLGE_CFG_RD_LEN_BYTES	16
 #define HCLGE_CFG_RD_LEN_UNIT	4
 
 #define HCLGE_CFG_VMDQ_S	0
-#define HCLGE_CFG_VMDQ_M	(0xff << HCLGE_CFG_VMDQ_S)
+#define HCLGE_CFG_VMDQ_M	GENMASK(7, 0)
 #define HCLGE_CFG_TC_NUM_S	8
-#define HCLGE_CFG_TC_NUM_M	(0xff << HCLGE_CFG_TC_NUM_S)
+#define HCLGE_CFG_TC_NUM_M	GENMASK(15, 8)
 #define HCLGE_CFG_TQP_DESC_N_S	16
-#define HCLGE_CFG_TQP_DESC_N_M	(0xffff << HCLGE_CFG_TQP_DESC_N_S)
+#define HCLGE_CFG_TQP_DESC_N_M	GENMASK(31, 16)
 #define HCLGE_CFG_PHY_ADDR_S	0
-#define HCLGE_CFG_PHY_ADDR_M	(0x1f << HCLGE_CFG_PHY_ADDR_S)
+#define HCLGE_CFG_PHY_ADDR_M	GENMASK(4, 0)
 #define HCLGE_CFG_MEDIA_TP_S	8
-#define HCLGE_CFG_MEDIA_TP_M	(0xff << HCLGE_CFG_MEDIA_TP_S)
+#define HCLGE_CFG_MEDIA_TP_M	GENMASK(15, 8)
 #define HCLGE_CFG_RX_BUF_LEN_S	16
-#define HCLGE_CFG_RX_BUF_LEN_M	(0xffff << HCLGE_CFG_RX_BUF_LEN_S)
+#define HCLGE_CFG_RX_BUF_LEN_M	GENMASK(31, 16)
 #define HCLGE_CFG_MAC_ADDR_H_S	0
-#define HCLGE_CFG_MAC_ADDR_H_M	(0xffff << HCLGE_CFG_MAC_ADDR_H_S)
+#define HCLGE_CFG_MAC_ADDR_H_M	GENMASK(15, 0)
 #define HCLGE_CFG_DEFAULT_SPEED_S	16
-#define HCLGE_CFG_DEFAULT_SPEED_M	(0xff << HCLGE_CFG_DEFAULT_SPEED_S)
+#define HCLGE_CFG_DEFAULT_SPEED_M	GENMASK(23, 16)
 
-struct hclge_cfg_param {
+struct hclge_cfg_param_cmd {
 	__le32 offset;
 	__le32 rsv;
 	__le32 param[4];
@@ -399,7 +410,7 @@ struct hclge_cfg_param {
 #define HCLGE_DESC_NUM		0x40
 
 #define HCLGE_ALLOC_VALID_B	0
-struct hclge_vf_num {
+struct hclge_vf_num_cmd {
 	u8 alloc_valid;
 	u8 rsv[23];
 };
@@ -407,13 +418,13 @@ struct hclge_vf_num {
 #define HCLGE_RSS_DEFAULT_OUTPORT_B	4
 #define HCLGE_RSS_HASH_KEY_OFFSET_B	4
 #define HCLGE_RSS_HASH_KEY_NUM		16
-struct hclge_rss_config {
+struct hclge_rss_config_cmd {
 	u8 hash_config;
 	u8 rsv[7];
 	u8 hash_key[HCLGE_RSS_HASH_KEY_NUM];
 };
 
-struct hclge_rss_input_tuple {
+struct hclge_rss_input_tuple_cmd {
 	u8 ipv4_tcp_en;
 	u8 ipv4_udp_en;
 	u8 ipv4_sctp_en;
@@ -427,26 +438,26 @@ struct hclge_rss_input_tuple {
 
 #define HCLGE_RSS_CFG_TBL_SIZE	16
 
-struct hclge_rss_indirection_table {
-	u16 start_table_index;
-	u16 rss_set_bitmap;
+struct hclge_rss_indirection_table_cmd {
+	__le16 start_table_index;
+	__le16 rss_set_bitmap;
 	u8 rsv[4];
 	u8 rss_result[HCLGE_RSS_CFG_TBL_SIZE];
 };
 
 #define HCLGE_RSS_TC_OFFSET_S		0
-#define HCLGE_RSS_TC_OFFSET_M		(0x3ff << HCLGE_RSS_TC_OFFSET_S)
+#define HCLGE_RSS_TC_OFFSET_M		GENMASK(9, 0)
 #define HCLGE_RSS_TC_SIZE_S		12
-#define HCLGE_RSS_TC_SIZE_M		(0x7 << HCLGE_RSS_TC_SIZE_S)
+#define HCLGE_RSS_TC_SIZE_M		GENMASK(14, 12)
 #define HCLGE_RSS_TC_VALID_B		15
-struct hclge_rss_tc_mode {
-	u16 rss_tc_mode[HCLGE_MAX_TC_NUM];
+struct hclge_rss_tc_mode_cmd {
+	__le16 rss_tc_mode[HCLGE_MAX_TC_NUM];
 	u8 rsv[8];
 };
 
 #define HCLGE_LINK_STS_B	0
 #define HCLGE_LINK_STATUS	BIT(HCLGE_LINK_STS_B)
-struct hclge_link_status {
+struct hclge_link_status_cmd {
 	u8 status;
 	u8 rsv[23];
 };
@@ -461,7 +472,7 @@ struct hclge_promisc_param {
 #define HCLGE_PROMISC_EN_UC	0x1
 #define HCLGE_PROMISC_EN_MC	0x2
 #define HCLGE_PROMISC_EN_BC	0x4
-struct hclge_promisc_cfg {
+struct hclge_promisc_cfg_cmd {
 	u8 flag;
 	u8 vf_id;
 	__le16 rsv0;
@@ -489,18 +500,18 @@ enum hclge_promisc_type {
 #define HCLGE_MAC_TX_UNDER_MIN_ERR_B		21
 #define HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B	22
 
-struct hclge_config_mac_mode {
+struct hclge_config_mac_mode_cmd {
 	__le32 txrx_pad_fcs_loop_en;
 	u8 rsv[20];
 };
 
 #define HCLGE_CFG_SPEED_S		0
-#define HCLGE_CFG_SPEED_M		(0x3f << HCLGE_CFG_SPEED_S)
+#define HCLGE_CFG_SPEED_M		GENMASK(5, 0)
 
 #define HCLGE_CFG_DUPLEX_B		7
 #define HCLGE_CFG_DUPLEX_M		BIT(HCLGE_CFG_DUPLEX_B)
 
-struct hclge_config_mac_speed_dup {
+struct hclge_config_mac_speed_dup_cmd {
 	u8 speed_dup;
 
 #define HCLGE_CFG_MAC_SPEED_CHANGE_EN_B	0
@@ -512,17 +523,17 @@ struct hclge_config_mac_speed_dup {
 #define HCLGE_QUERY_AN_B		0
 #define HCLGE_QUERY_DUPLEX_B		2
 
-#define HCLGE_QUERY_SPEED_M		(0x1f << HCLGE_QUERY_SPEED_S)
+#define HCLGE_QUERY_SPEED_M		GENMASK(4, 0)
 #define HCLGE_QUERY_AN_M		BIT(HCLGE_QUERY_AN_B)
 #define HCLGE_QUERY_DUPLEX_M		BIT(HCLGE_QUERY_DUPLEX_B)
 
-struct hclge_query_an_speed_dup {
+struct hclge_query_an_speed_dup_cmd {
 	u8 an_syn_dup_speed;
 	u8 pause;
 	u8 rsv[23];
 };
 
-#define HCLGE_RING_ID_MASK		0x3ff
+#define HCLGE_RING_ID_MASK		GENMASK(9, 0)
 #define HCLGE_TQP_ENABLE_B		0
 
 #define HCLGE_MAC_CFG_AN_EN_B		0
@@ -533,7 +544,7 @@ struct hclge_query_an_speed_dup {
 
 #define HCLGE_MAC_CFG_AN_EN	BIT(HCLGE_MAC_CFG_AN_EN_B)
 
-struct hclge_config_auto_neg {
+struct hclge_config_auto_neg_cmd {
 	__le32  cfg_an_cmd_flag;
 	u8      rsv[20];
 };
@@ -542,7 +553,7 @@ struct hclge_config_auto_neg {
 #define HCLGE_MAC_MAX_MTU		9728
 #define HCLGE_MAC_UPLINK_PORT		0x100
 
-struct hclge_config_max_frm_size {
+struct hclge_config_max_frm_size_cmd {
 	__le16  max_frm_size;
 	u8      rsv[22];
 };
@@ -559,10 +570,10 @@ enum hclge_mac_vlan_tbl_opcode {
 #define HCLGE_MAC_EPORT_SW_EN_B		0xc
 #define HCLGE_MAC_EPORT_TYPE_B		0xb
 #define HCLGE_MAC_EPORT_VFID_S		0x3
-#define HCLGE_MAC_EPORT_VFID_M		(0xff << HCLGE_MAC_EPORT_VFID_S)
+#define HCLGE_MAC_EPORT_VFID_M		GENMASK(10, 3)
 #define HCLGE_MAC_EPORT_PFID_S		0x0
-#define HCLGE_MAC_EPORT_PFID_M		(0x7 << HCLGE_MAC_EPORT_PFID_S)
-struct hclge_mac_vlan_tbl_entry {
+#define HCLGE_MAC_EPORT_PFID_M		GENMASK(2, 0)
+struct hclge_mac_vlan_tbl_entry_cmd {
 	u8	flags;
 	u8      resp_code;
 	__le16  vlan_tag;
@@ -577,15 +588,15 @@ struct hclge_mac_vlan_tbl_entry {
 };
 
 #define HCLGE_CFG_MTA_MAC_SEL_S		0x0
-#define HCLGE_CFG_MTA_MAC_SEL_M		(0x3 << HCLGE_CFG_MTA_MAC_SEL_S)
+#define HCLGE_CFG_MTA_MAC_SEL_M		GENMASK(1, 0)
 #define HCLGE_CFG_MTA_MAC_EN_B		0x7
-struct hclge_mta_filter_mode {
+struct hclge_mta_filter_mode_cmd {
 	u8	dmac_sel_en; /* Use lowest 2 bit as sel_mode, bit 7 as enable */
 	u8      rsv[23];
 };
 
 #define HCLGE_CFG_FUNC_MTA_ACCEPT_B	0x0
-struct hclge_cfg_func_mta_filter {
+struct hclge_cfg_func_mta_filter_cmd {
 	u8	accept; /* Only used lowest 1 bit */
 	u8      function_id;
 	u8      rsv[22];
@@ -593,14 +604,14 @@ struct hclge_cfg_func_mta_filter {
 
 #define HCLGE_CFG_MTA_ITEM_ACCEPT_B	0x0
 #define HCLGE_CFG_MTA_ITEM_IDX_S	0x0
-#define HCLGE_CFG_MTA_ITEM_IDX_M	(0xfff << HCLGE_CFG_MTA_ITEM_IDX_S)
-struct hclge_cfg_func_mta_item {
-	u16	item_idx; /* Only used lowest 12 bit */
+#define HCLGE_CFG_MTA_ITEM_IDX_M	GENMASK(11, 0)
+struct hclge_cfg_func_mta_item_cmd {
+	__le16	item_idx; /* Only used lowest 12 bit */
 	u8      accept;   /* Only used lowest 1 bit */
 	u8      rsv[21];
 };
 
-struct hclge_mac_vlan_add {
+struct hclge_mac_vlan_add_cmd {
 	__le16  flags;
 	__le16  mac_addr_hi16;
 	__le32  mac_addr_lo32;
@@ -613,7 +624,7 @@ struct hclge_mac_vlan_add {
 };
 
 #define HNS3_MAC_VLAN_CFG_FLAG_BIT 0
-struct hclge_mac_vlan_remove {
+struct hclge_mac_vlan_remove_cmd {
 	__le16  flags;
 	__le16  mac_addr_hi16;
 	__le32  mac_addr_lo32;
@@ -625,21 +636,21 @@ struct hclge_mac_vlan_remove {
 	u8      rsv[4];
 };
 
-struct hclge_vlan_filter_ctrl {
+struct hclge_vlan_filter_ctrl_cmd {
 	u8 vlan_type;
 	u8 vlan_fe;
 	u8 rsv[22];
 };
 
-struct hclge_vlan_filter_pf_cfg {
+struct hclge_vlan_filter_pf_cfg_cmd {
 	u8 vlan_offset;
 	u8 vlan_cfg;
 	u8 rsv[2];
 	u8 vlan_offset_bitmap[20];
 };
 
-struct hclge_vlan_filter_vf_cfg {
-	u16 vlan_id;
+struct hclge_vlan_filter_vf_cfg_cmd {
+	__le16 vlan_id;
 	u8  resp_code;
 	u8  rsv;
 	u8  vlan_cfg;
@@ -647,14 +658,14 @@ struct hclge_vlan_filter_vf_cfg {
 	u8  vf_bitmap[16];
 };
 
-struct hclge_cfg_com_tqp_queue {
+struct hclge_cfg_com_tqp_queue_cmd {
 	__le16 tqp_id;
 	__le16 stream_id;
 	u8 enable;
 	u8 rsv[19];
 };
 
-struct hclge_cfg_tx_queue_pointer {
+struct hclge_cfg_tx_queue_pointer_cmd {
 	__le16 tqp_id;
 	__le16 tx_tail;
 	__le16 tx_head;
@@ -664,12 +675,12 @@ struct hclge_cfg_tx_queue_pointer {
 };
 
 #define HCLGE_TSO_MSS_MIN_S	0
-#define HCLGE_TSO_MSS_MIN_M	(0x3FFF << HCLGE_TSO_MSS_MIN_S)
+#define HCLGE_TSO_MSS_MIN_M	GENMASK(13, 0)
 
 #define HCLGE_TSO_MSS_MAX_S	16
-#define HCLGE_TSO_MSS_MAX_M	(0x3FFF << HCLGE_TSO_MSS_MAX_S)
+#define HCLGE_TSO_MSS_MAX_M	GENMASK(29, 16)
 
-struct hclge_cfg_tso_status {
+struct hclge_cfg_tso_status_cmd {
 	__le16 tso_mss_min;
 	__le16 tso_mss_max;
 	u8 rsv[20];
@@ -679,13 +690,20 @@ struct hclge_cfg_tso_status {
 #define HCLGE_TSO_MSS_MAX	9668
 
 #define HCLGE_TQP_RESET_B	0
-struct hclge_reset_tqp_queue {
+struct hclge_reset_tqp_queue_cmd {
 	__le16 tqp_id;
 	u8 reset_req;
 	u8 ready_to_reset;
 	u8 rsv[20];
 };
 
+#define HCLGE_CFG_RESET_MAC_B		3
+#define HCLGE_CFG_RESET_FUNC_B		7
+struct hclge_reset_cmd {
+	u8 mac_func_reset;
+	u8 fun_reset_vfid;
+	u8 rsv[22];
+};
 #define HCLGE_DEFAULT_TX_BUF		0x4000	 /* 16k  bytes */
 #define HCLGE_TOTAL_PKT_BUF		0x108000 /* 1.03125M bytes */
 #define HCLGE_DEFAULT_DV		0xA000	 /* 40k byte */
@@ -733,6 +751,7 @@ struct hclge_hw;
 int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num);
 void hclge_cmd_setup_basic_desc(struct hclge_desc *desc,
 				enum hclge_opcode_type opcode, bool is_read);
+void hclge_cmd_reuse_desc(struct hclge_desc *desc, bool is_read);
 
 int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev,
 			       struct hclge_promisc_param *param);
@@ -743,4 +762,5 @@ enum hclge_cmd_status hclge_cmd_mdio_read(struct hclge_hw *hw,
 					  struct hclge_desc *desc);
 
 void hclge_destroy_cmd_queue(struct hclge_hw *hw);
+int hclge_cmd_queue_init(struct hclge_dev *hdev);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
new file mode 100644
index 000000000000..5018d6633133
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -0,0 +1,347 @@
+/*
+ * Copyright (c) 2016-2017 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "hclge_main.h"
+#include "hclge_tm.h"
+#include "hnae3.h"
+
+#define BW_PERCENT	100
+
+static int hclge_ieee_ets_to_tm_info(struct hclge_dev *hdev,
+				     struct ieee_ets *ets)
+{
+	u8 i;
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		switch (ets->tc_tsa[i]) {
+		case IEEE_8021QAZ_TSA_STRICT:
+			hdev->tm_info.tc_info[i].tc_sch_mode =
+				HCLGE_SCH_MODE_SP;
+			hdev->tm_info.pg_info[0].tc_dwrr[i] = 0;
+			break;
+		case IEEE_8021QAZ_TSA_ETS:
+			hdev->tm_info.tc_info[i].tc_sch_mode =
+				HCLGE_SCH_MODE_DWRR;
+			hdev->tm_info.pg_info[0].tc_dwrr[i] =
+				ets->tc_tx_bw[i];
+			break;
+		default:
+			/* Hardware only supports SP (strict priority)
+			 * or ETS (enhanced transmission selection)
+			 * algorithms, if we receive some other value
+			 * from dcbnl, then throw an error.
+			 */
+			return -EINVAL;
+		}
+	}
+
+	return hclge_tm_prio_tc_info_update(hdev, ets->prio_tc);
+}
+
+static void hclge_tm_info_to_ieee_ets(struct hclge_dev *hdev,
+				      struct ieee_ets *ets)
+{
+	u32 i;
+
+	memset(ets, 0, sizeof(*ets));
+	ets->willing = 1;
+	ets->ets_cap = hdev->tc_max;
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		ets->prio_tc[i] = hdev->tm_info.prio_tc[i];
+		ets->tc_tx_bw[i] = hdev->tm_info.pg_info[0].tc_dwrr[i];
+
+		if (hdev->tm_info.tc_info[i].tc_sch_mode ==
+		    HCLGE_SCH_MODE_SP)
+			ets->tc_tsa[i] = IEEE_8021QAZ_TSA_STRICT;
+		else
+			ets->tc_tsa[i] = IEEE_8021QAZ_TSA_ETS;
+	}
+}
+
+/* IEEE std */
+static int hclge_ieee_getets(struct hnae3_handle *h, struct ieee_ets *ets)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+
+	hclge_tm_info_to_ieee_ets(hdev, ets);
+
+	return 0;
+}
+
+static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
+			      u8 *tc, bool *changed)
+{
+	u32 total_ets_bw = 0;
+	u8 max_tc = 0;
+	u8 i;
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		if (ets->prio_tc[i] >= hdev->tc_max ||
+		    i >= hdev->tc_max)
+			return -EINVAL;
+
+		if (ets->prio_tc[i] != hdev->tm_info.prio_tc[i])
+			*changed = true;
+
+		if (ets->prio_tc[i] > max_tc)
+			max_tc = ets->prio_tc[i];
+
+		switch (ets->tc_tsa[i]) {
+		case IEEE_8021QAZ_TSA_STRICT:
+			if (hdev->tm_info.tc_info[i].tc_sch_mode !=
+				HCLGE_SCH_MODE_SP)
+				*changed = true;
+			break;
+		case IEEE_8021QAZ_TSA_ETS:
+			if (hdev->tm_info.tc_info[i].tc_sch_mode !=
+				HCLGE_SCH_MODE_DWRR)
+				*changed = true;
+
+			total_ets_bw += ets->tc_tx_bw[i];
+		break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	if (total_ets_bw != BW_PERCENT)
+		return -EINVAL;
+
+	*tc = max_tc + 1;
+	if (*tc != hdev->tm_info.num_tc)
+		*changed = true;
+
+	return 0;
+}
+
+static int hclge_map_update(struct hnae3_handle *h)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+	int ret;
+
+	ret = hclge_tm_map_cfg(hdev);
+	if (ret)
+		return ret;
+
+	ret = hclge_tm_schd_mode_hw(hdev);
+	if (ret)
+		return ret;
+
+	ret = hclge_pause_setup_hw(hdev);
+	if (ret)
+		return ret;
+
+	ret = hclge_buffer_alloc(hdev);
+	if (ret)
+		return ret;
+
+	return hclge_rss_init_hw(hdev);
+}
+
+static int hclge_client_setup_tc(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport = hdev->vport;
+	struct hnae3_client *client;
+	struct hnae3_handle *handle;
+	int ret;
+	u32 i;
+
+	for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
+		handle = &vport[i].nic;
+		client = handle->client;
+
+		if (!client || !client->ops || !client->ops->setup_tc)
+			continue;
+
+		ret = client->ops->setup_tc(handle, hdev->tm_info.num_tc);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+	bool map_changed = false;
+	u8 num_tc = 0;
+	int ret;
+
+	if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) ||
+	    hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
+		return -EINVAL;
+
+	ret = hclge_ets_validate(hdev, ets, &num_tc, &map_changed);
+	if (ret)
+		return ret;
+
+	hclge_tm_schd_info_update(hdev, num_tc);
+
+	ret = hclge_ieee_ets_to_tm_info(hdev, ets);
+	if (ret)
+		return ret;
+
+	if (map_changed) {
+		ret = hclge_client_setup_tc(hdev);
+		if (ret)
+			return ret;
+	}
+
+	return hclge_tm_dwrr_cfg(hdev);
+}
+
+static int hclge_ieee_getpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+	u8 i, j, pfc_map, *prio_tc;
+
+	memset(pfc, 0, sizeof(*pfc));
+	pfc->pfc_cap = hdev->pfc_max;
+	prio_tc = hdev->tm_info.prio_tc;
+	pfc_map = hdev->tm_info.hw_pfc_map;
+
+	/* Pfc setting is based on TC */
+	for (i = 0; i < hdev->tm_info.num_tc; i++) {
+		for (j = 0; j < HNAE3_MAX_USER_PRIO; j++) {
+			if ((prio_tc[j] == i) && (pfc_map & BIT(i)))
+				pfc->pfc_en |= BIT(j);
+		}
+	}
+
+	return 0;
+}
+
+static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+	u8 i, j, pfc_map, *prio_tc;
+
+	if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) ||
+	    hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
+		return -EINVAL;
+
+	prio_tc = hdev->tm_info.prio_tc;
+	pfc_map = 0;
+
+	for (i = 0; i < hdev->tm_info.num_tc; i++) {
+		for (j = 0; j < HNAE3_MAX_USER_PRIO; j++) {
+			if ((prio_tc[j] == i) && (pfc->pfc_en & BIT(j))) {
+				pfc_map |= BIT(i);
+				break;
+			}
+		}
+	}
+
+	if (pfc_map == hdev->tm_info.hw_pfc_map)
+		return 0;
+
+	hdev->tm_info.hw_pfc_map = pfc_map;
+
+	return hclge_pause_setup_hw(hdev);
+}
+
+/* DCBX configuration */
+static u8 hclge_getdcbx(struct hnae3_handle *h)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+
+	if (hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
+		return 0;
+
+	return hdev->dcbx_cap;
+}
+
+static u8 hclge_setdcbx(struct hnae3_handle *h, u8 mode)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+
+	/* No support for LLD_MANAGED modes or CEE */
+	if ((mode & DCB_CAP_DCBX_LLD_MANAGED) ||
+	    (mode & DCB_CAP_DCBX_VER_CEE) ||
+	    !(mode & DCB_CAP_DCBX_HOST))
+		return 1;
+
+	hdev->dcbx_cap = mode;
+
+	return 0;
+}
+
+/* Set up TC for hardware offloaded mqprio in channel mode */
+static int hclge_setup_tc(struct hnae3_handle *h, u8 tc, u8 *prio_tc)
+{
+	struct hclge_vport *vport = hclge_get_vport(h);
+	struct hclge_dev *hdev = vport->back;
+	int ret;
+
+	if (hdev->flag & HCLGE_FLAG_DCB_ENABLE)
+		return -EINVAL;
+
+	if (tc > hdev->tc_max) {
+		dev_err(&hdev->pdev->dev,
+			"setup tc failed, tc(%u) > tc_max(%u)\n",
+			tc, hdev->tc_max);
+		return -EINVAL;
+	}
+
+	hclge_tm_schd_info_update(hdev, tc);
+
+	ret = hclge_tm_prio_tc_info_update(hdev, prio_tc);
+	if (ret)
+		return ret;
+
+	ret = hclge_tm_init_hw(hdev);
+	if (ret)
+		return ret;
+
+	hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
+
+	if (tc > 1)
+		hdev->flag |= HCLGE_FLAG_MQPRIO_ENABLE;
+	else
+		hdev->flag &= ~HCLGE_FLAG_MQPRIO_ENABLE;
+
+	return 0;
+}
+
+static const struct hnae3_dcb_ops hns3_dcb_ops = {
+	.ieee_getets	= hclge_ieee_getets,
+	.ieee_setets	= hclge_ieee_setets,
+	.ieee_getpfc	= hclge_ieee_getpfc,
+	.ieee_setpfc	= hclge_ieee_setpfc,
+	.getdcbx	= hclge_getdcbx,
+	.setdcbx	= hclge_setdcbx,
+	.map_update	= hclge_map_update,
+	.setup_tc	= hclge_setup_tc,
+};
+
+void hclge_dcb_ops_set(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport = hdev->vport;
+	struct hnae3_knic_private_info *kinfo;
+
+	/* Hdev does not support DCB or vport is
+	 * not a pf, then dcb_ops is not set.
+	 */
+	if (!hnae3_dev_dcb_supported(hdev) ||
+	    vport->vport_id != 0)
+		return;
+
+	kinfo = &vport->nic.kinfo;
+	kinfo->dcb_ops = &hns3_dcb_ops;
+	hdev->dcbx_cap = DCB_CAP_DCBX_VER_IEEE | DCB_CAP_DCBX_HOST;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
new file mode 100644
index 000000000000..7d808ee96694
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
@@ -0,0 +1,21 @@
+/*
+ * Copyright (c) 2016~2017 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __HCLGE_DCB_H__
+#define __HCLGE_DCB_H__
+
+#include "hclge_main.h"
+
+#ifdef CONFIG_HNS3_DCB
+void hclge_dcb_ops_set(struct hclge_dev *hdev);
+#else
+static inline void hclge_dcb_ops_set(struct hclge_dev *hdev) {}
+#endif
+
+#endif /* __HCLGE_DCB_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index c1cdbfd83bdb..c6ba89089ef3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -19,6 +19,7 @@
 #include <linux/platform_device.h>
 
 #include "hclge_cmd.h"
+#include "hclge_dcb.h"
 #include "hclge_main.h"
 #include "hclge_mdio.h"
 #include "hclge_tm.h"
@@ -30,11 +31,11 @@
 #define HCLGE_64BIT_STATS_FIELD_OFF(f) (offsetof(struct hclge_64_bit_stats, f))
 #define HCLGE_32BIT_STATS_FIELD_OFF(f) (offsetof(struct hclge_32_bit_stats, f))
 
-static int hclge_rss_init_hw(struct hclge_dev *hdev);
 static int hclge_set_mta_filter_mode(struct hclge_dev *hdev,
 				     enum hclge_mta_dmac_sel_type mta_mac_sel,
 				     bool enable);
 static int hclge_init_vlan_config(struct hclge_dev *hdev);
+static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev);
 
 static struct hnae3_ae_algo ae_algo;
 
@@ -362,7 +363,7 @@ static int hclge_64_bit_update_stats(struct hclge_dev *hdev)
 #define HCLGE_64_BIT_RTN_DATANUM 4
 	u64 *data = (u64 *)(&hdev->hw_stats.all_64_bit_stats);
 	struct hclge_desc desc[HCLGE_64_BIT_CMD_NUM];
-	u64 *desc_data;
+	__le64 *desc_data;
 	int i, k, n;
 	int ret;
 
@@ -376,14 +377,14 @@ static int hclge_64_bit_update_stats(struct hclge_dev *hdev)
 
 	for (i = 0; i < HCLGE_64_BIT_CMD_NUM; i++) {
 		if (unlikely(i == 0)) {
-			desc_data = (u64 *)(&desc[i].data[0]);
+			desc_data = (__le64 *)(&desc[i].data[0]);
 			n = HCLGE_64_BIT_RTN_DATANUM - 1;
 		} else {
-			desc_data = (u64 *)(&desc[i]);
+			desc_data = (__le64 *)(&desc[i]);
 			n = HCLGE_64_BIT_RTN_DATANUM;
 		}
 		for (k = 0; k < n; k++) {
-			*data++ += cpu_to_le64(*desc_data);
+			*data++ += le64_to_cpu(*desc_data);
 			desc_data++;
 		}
 	}
@@ -411,7 +412,7 @@ static int hclge_32_bit_update_stats(struct hclge_dev *hdev)
 
 	struct hclge_desc desc[HCLGE_32_BIT_CMD_NUM];
 	struct hclge_32_bit_stats *all_32_bit_stats;
-	u32 *desc_data;
+	__le32 *desc_data;
 	int i, k, n;
 	u64 *data;
 	int ret;
@@ -431,21 +432,27 @@ static int hclge_32_bit_update_stats(struct hclge_dev *hdev)
 	hclge_reset_partial_32bit_counter(all_32_bit_stats);
 	for (i = 0; i < HCLGE_32_BIT_CMD_NUM; i++) {
 		if (unlikely(i == 0)) {
+			__le16 *desc_data_16bit;
+
 			all_32_bit_stats->igu_rx_err_pkt +=
-				cpu_to_le32(desc[i].data[0]);
+				le32_to_cpu(desc[i].data[0]);
+
+			desc_data_16bit = (__le16 *)&desc[i].data[1];
 			all_32_bit_stats->igu_rx_no_eof_pkt +=
-				cpu_to_le32(desc[i].data[1] & 0xffff);
+				le16_to_cpu(*desc_data_16bit);
+
+			desc_data_16bit++;
 			all_32_bit_stats->igu_rx_no_sof_pkt +=
-				cpu_to_le32((desc[i].data[1] >> 16) & 0xffff);
+				le16_to_cpu(*desc_data_16bit);
 
-			desc_data = (u32 *)(&desc[i].data[2]);
+			desc_data = &desc[i].data[2];
 			n = HCLGE_32_BIT_RTN_DATANUM - 4;
 		} else {
-			desc_data = (u32 *)(&desc[i]);
+			desc_data = (__le32 *)&desc[i];
 			n = HCLGE_32_BIT_RTN_DATANUM;
 		}
 		for (k = 0; k < n; k++) {
-			*data++ += cpu_to_le32(*desc_data);
+			*data++ += le32_to_cpu(*desc_data);
 			desc_data++;
 		}
 	}
@@ -460,7 +467,7 @@ static int hclge_mac_update_stats(struct hclge_dev *hdev)
 
 	u64 *data = (u64 *)(&hdev->hw_stats.mac_stats);
 	struct hclge_desc desc[HCLGE_MAC_CMD_NUM];
-	u64 *desc_data;
+	__le64 *desc_data;
 	int i, k, n;
 	int ret;
 
@@ -475,14 +482,14 @@ static int hclge_mac_update_stats(struct hclge_dev *hdev)
 
 	for (i = 0; i < HCLGE_MAC_CMD_NUM; i++) {
 		if (unlikely(i == 0)) {
-			desc_data = (u64 *)(&desc[i].data[0]);
+			desc_data = (__le64 *)(&desc[i].data[0]);
 			n = HCLGE_RTN_DATA_NUM - 2;
 		} else {
-			desc_data = (u64 *)(&desc[i]);
+			desc_data = (__le64 *)(&desc[i]);
 			n = HCLGE_RTN_DATA_NUM;
 		}
 		for (k = 0; k < n; k++) {
-			*data++ += cpu_to_le64(*desc_data);
+			*data++ += le64_to_cpu(*desc_data);
 			desc_data++;
 		}
 	}
@@ -508,7 +515,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle)
 					   HCLGE_OPC_QUERY_RX_STATUS,
 					   true);
 
-		desc[0].data[0] = (tqp->index & 0x1ff);
+		desc[0].data[0] = cpu_to_le32((tqp->index & 0x1ff));
 		ret = hclge_cmd_send(&hdev->hw, desc, 1);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
@@ -517,7 +524,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle)
 			return ret;
 		}
 		tqp->tqp_stats.rcb_rx_ring_pktnum_rcd +=
-			cpu_to_le32(desc[0].data[4]);
+			le32_to_cpu(desc[0].data[4]);
 	}
 
 	for (i = 0; i < kinfo->num_tqps; i++) {
@@ -528,7 +535,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle)
 					   HCLGE_OPC_QUERY_TX_STATUS,
 					   true);
 
-		desc[0].data[0] = (tqp->index & 0x1ff);
+		desc[0].data[0] = cpu_to_le32((tqp->index & 0x1ff));
 		ret = hclge_cmd_send(&hdev->hw, desc, 1);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
@@ -537,7 +544,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle)
 			return ret;
 		}
 		tqp->tqp_stats.rcb_tx_ring_pktnum_rcd +=
-			cpu_to_le32(desc[0].data[4]);
+			le32_to_cpu(desc[0].data[4]);
 	}
 
 	return 0;
@@ -552,12 +559,12 @@ static u64 *hclge_tqps_get_stats(struct hnae3_handle *handle, u64 *data)
 
 	for (i = 0; i < kinfo->num_tqps; i++) {
 		tqp = container_of(kinfo->tqp[i], struct hclge_tqp, q);
-		*buff++ = cpu_to_le64(tqp->tqp_stats.rcb_tx_ring_pktnum_rcd);
+		*buff++ = tqp->tqp_stats.rcb_tx_ring_pktnum_rcd;
 	}
 
 	for (i = 0; i < kinfo->num_tqps; i++) {
 		tqp = container_of(kinfo->tqp[i], struct hclge_tqp, q);
-		*buff++ = cpu_to_le64(tqp->tqp_stats.rcb_rx_ring_pktnum_rcd);
+		*buff++ = tqp->tqp_stats.rcb_rx_ring_pktnum_rcd;
 	}
 
 	return buff;
@@ -820,7 +827,7 @@ static void hclge_get_stats(struct hnae3_handle *handle, u64 *data)
 }
 
 static int hclge_parse_func_status(struct hclge_dev *hdev,
-				   struct hclge_func_status *status)
+				   struct hclge_func_status_cmd *status)
 {
 	if (!(status->pf_state & HCLGE_PF_STATE_DONE))
 		return -EINVAL;
@@ -831,19 +838,18 @@ static int hclge_parse_func_status(struct hclge_dev *hdev,
 	else
 		hdev->flag &= ~HCLGE_FLAG_MAIN;
 
-	hdev->num_req_vfs = status->vf_num / status->pf_num;
 	return 0;
 }
 
 static int hclge_query_function_status(struct hclge_dev *hdev)
 {
-	struct hclge_func_status *req;
+	struct hclge_func_status_cmd *req;
 	struct hclge_desc desc;
 	int timeout = 0;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_FUNC_STATUS, true);
-	req = (struct hclge_func_status *)desc.data;
+	req = (struct hclge_func_status_cmd *)desc.data;
 
 	do {
 		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -868,7 +874,7 @@ static int hclge_query_function_status(struct hclge_dev *hdev)
 
 static int hclge_query_pf_resource(struct hclge_dev *hdev)
 {
-	struct hclge_pf_res *req;
+	struct hclge_pf_res_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 
@@ -880,7 +886,7 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 		return ret;
 	}
 
-	req = (struct hclge_pf_res *)desc.data;
+	req = (struct hclge_pf_res_cmd *)desc.data;
 	hdev->num_tqps = __le16_to_cpu(req->tqp_num);
 	hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S;
 
@@ -938,12 +944,12 @@ static int hclge_parse_speed(int speed_cmd, int *speed)
 
 static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 {
-	struct hclge_cfg_param *req;
+	struct hclge_cfg_param_cmd *req;
 	u64 mac_addr_tmp_high;
 	u64 mac_addr_tmp;
 	int i;
 
-	req = (struct hclge_cfg_param *)desc[0].data;
+	req = (struct hclge_cfg_param_cmd *)desc[0].data;
 
 	/* get the configuration */
 	cfg->vmdq_vport_num = hnae_get_field(__le32_to_cpu(req->param[0]),
@@ -978,7 +984,7 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 	for (i = 0; i < ETH_ALEN; i++)
 		cfg->mac_addr[i] = (mac_addr_tmp >> (8 * i)) & 0xff;
 
-	req = (struct hclge_cfg_param *)desc[1].data;
+	req = (struct hclge_cfg_param_cmd *)desc[1].data;
 	cfg->numa_node_map = __le32_to_cpu(req->param[0]);
 }
 
@@ -989,20 +995,21 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 static int hclge_get_cfg(struct hclge_dev *hdev, struct hclge_cfg *hcfg)
 {
 	struct hclge_desc desc[HCLGE_PF_CFG_DESC_NUM];
-	struct hclge_cfg_param *req;
+	struct hclge_cfg_param_cmd *req;
 	int i, ret;
 
 	for (i = 0; i < HCLGE_PF_CFG_DESC_NUM; i++) {
-		req = (struct hclge_cfg_param *)desc[i].data;
+		u32 offset = 0;
+
+		req = (struct hclge_cfg_param_cmd *)desc[i].data;
 		hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_GET_CFG_PARAM,
 					   true);
-		hnae_set_field(req->offset, HCLGE_CFG_OFFSET_M,
+		hnae_set_field(offset, HCLGE_CFG_OFFSET_M,
 			       HCLGE_CFG_OFFSET_S, i * HCLGE_CFG_RD_LEN_BYTES);
 		/* Len should be united by 4 bytes when send to hardware */
-		hnae_set_field(req->offset, HCLGE_CFG_RD_LEN_M,
-			       HCLGE_CFG_RD_LEN_S,
+		hnae_set_field(offset, HCLGE_CFG_RD_LEN_M, HCLGE_CFG_RD_LEN_S,
 			       HCLGE_CFG_RD_LEN_BYTES / HCLGE_CFG_RD_LEN_UNIT);
-		req->offset = cpu_to_le32(req->offset);
+		req->offset = cpu_to_le32(offset);
 	}
 
 	ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_PF_CFG_DESC_NUM);
@@ -1058,7 +1065,7 @@ static int hclge_configure(struct hclge_dev *hdev)
 	hdev->hw.mac.phy_addr = cfg.phy_addr;
 	hdev->num_desc = cfg.tqp_desc_num;
 	hdev->tm_info.num_pg = 1;
-	hdev->tm_info.num_tc = cfg.tc_num;
+	hdev->tc_max = cfg.tc_num;
 	hdev->tm_info.hw_pfc_map = 0;
 
 	ret = hclge_parse_speed(cfg.default_speed, &hdev->hw.mac.speed);
@@ -1067,15 +1074,25 @@ static int hclge_configure(struct hclge_dev *hdev)
 		return ret;
 	}
 
-	if ((hdev->tm_info.num_tc > HNAE3_MAX_TC) ||
-	    (hdev->tm_info.num_tc < 1)) {
+	if ((hdev->tc_max > HNAE3_MAX_TC) ||
+	    (hdev->tc_max < 1)) {
 		dev_warn(&hdev->pdev->dev, "TC num = %d.\n",
-			 hdev->tm_info.num_tc);
-		hdev->tm_info.num_tc = 1;
+			 hdev->tc_max);
+		hdev->tc_max = 1;
+	}
+
+	/* Dev does not support DCB */
+	if (!hnae3_dev_dcb_supported(hdev)) {
+		hdev->tc_max = 1;
+		hdev->pfc_max = 0;
+	} else {
+		hdev->pfc_max = hdev->tc_max;
 	}
 
+	hdev->tm_info.num_tc = hdev->tc_max;
+
 	/* Currently not support uncontiuous tc */
-	for (i = 0; i < cfg.tc_num; i++)
+	for (i = 0; i < hdev->tm_info.num_tc; i++)
 		hnae_set_bit(hdev->hw_tc_map, i, 1);
 
 	if (!hdev->num_vmdq_vport && !hdev->num_req_vfs)
@@ -1089,16 +1106,23 @@ static int hclge_configure(struct hclge_dev *hdev)
 static int hclge_config_tso(struct hclge_dev *hdev, int tso_mss_min,
 			    int tso_mss_max)
 {
-	struct hclge_cfg_tso_status *req;
+	struct hclge_cfg_tso_status_cmd *req;
 	struct hclge_desc desc;
+	u16 tso_mss;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TSO_GENERIC_CONFIG, false);
 
-	req = (struct hclge_cfg_tso_status *)desc.data;
-	hnae_set_field(req->tso_mss_min, HCLGE_TSO_MSS_MIN_M,
+	req = (struct hclge_cfg_tso_status_cmd *)desc.data;
+
+	tso_mss = 0;
+	hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
 		       HCLGE_TSO_MSS_MIN_S, tso_mss_min);
-	hnae_set_field(req->tso_mss_max, HCLGE_TSO_MSS_MIN_M,
+	req->tso_mss_min = cpu_to_le16(tso_mss);
+
+	tso_mss = 0;
+	hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
 		       HCLGE_TSO_MSS_MIN_S, tso_mss_max);
+	req->tso_mss_max = cpu_to_le16(tso_mss);
 
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
@@ -1134,15 +1158,15 @@ static int hclge_alloc_tqps(struct hclge_dev *hdev)
 static int hclge_map_tqps_to_func(struct hclge_dev *hdev, u16 func_id,
 				  u16 tqp_pid, u16 tqp_vid, bool is_pf)
 {
-	struct hclge_tqp_map *req;
+	struct hclge_tqp_map_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SET_TQP_MAP, false);
 
-	req = (struct hclge_tqp_map *)desc.data;
+	req = (struct hclge_tqp_map_cmd *)desc.data;
 	req->tqp_id = cpu_to_le16(tqp_pid);
-	req->tqp_vf = cpu_to_le16(func_id);
+	req->tqp_vf = func_id;
 	req->tqp_flag = !is_pf << HCLGE_TQP_MAP_TYPE_B |
 			1 << HCLGE_TQP_MAP_EN_B;
 	req->tqp_vid = cpu_to_le16(tqp_vid);
@@ -1161,11 +1185,7 @@ static int  hclge_assign_tqp(struct hclge_vport *vport,
 			     struct hnae3_queue **tqp, u16 num_tqps)
 {
 	struct hclge_dev *hdev = vport->back;
-	int i, alloced, func_id, ret;
-	bool is_pf;
-
-	func_id = vport->vport_id;
-	is_pf = (vport->vport_id == 0) ? true : false;
+	int i, alloced;
 
 	for (i = 0, alloced = 0; i < hdev->num_tqps &&
 	     alloced < num_tqps; i++) {
@@ -1174,12 +1194,6 @@ static int  hclge_assign_tqp(struct hclge_vport *vport,
 			hdev->htqp[i].q.tqp_index = alloced;
 			tqp[alloced] = &hdev->htqp[i].q;
 			hdev->htqp[i].alloced = true;
-			ret = hclge_map_tqps_to_func(hdev, func_id,
-						     hdev->htqp[i].index,
-						     alloced, is_pf);
-			if (ret)
-				return ret;
-
 			alloced++;
 		}
 	}
@@ -1231,6 +1245,49 @@ static int hclge_knic_setup(struct hclge_vport *vport, u16 num_tqps)
 	return 0;
 }
 
+static int hclge_map_tqp_to_vport(struct hclge_dev *hdev,
+				  struct hclge_vport *vport)
+{
+	struct hnae3_handle *nic = &vport->nic;
+	struct hnae3_knic_private_info *kinfo;
+	u16 i;
+
+	kinfo = &nic->kinfo;
+	for (i = 0; i < kinfo->num_tqps; i++) {
+		struct hclge_tqp *q =
+			container_of(kinfo->tqp[i], struct hclge_tqp, q);
+		bool is_pf;
+		int ret;
+
+		is_pf = !(vport->vport_id);
+		ret = hclge_map_tqps_to_func(hdev, vport->vport_id, q->index,
+					     i, is_pf);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int hclge_map_tqp(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport = hdev->vport;
+	u16 i, num_vport;
+
+	num_vport = hdev->num_vmdq_vport + hdev->num_req_vfs + 1;
+	for (i = 0; i < num_vport; i++)	{
+		int ret;
+
+		ret = hclge_map_tqp_to_vport(hdev, vport);
+		if (ret)
+			return ret;
+
+		vport++;
+	}
+
+	return 0;
+}
+
 static void hclge_unic_setup(struct hclge_vport *vport, u16 num_tqps)
 {
 	/* this would be initialized later */
@@ -1324,23 +1381,27 @@ static int hclge_alloc_vport(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size)
+static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev,
+				    struct hclge_pkt_buf_alloc *buf_alloc)
 {
 /* TX buffer size is unit by 128 byte */
 #define HCLGE_BUF_SIZE_UNIT_SHIFT	7
 #define HCLGE_BUF_SIZE_UPDATE_EN_MSK	BIT(15)
-	struct hclge_tx_buff_alloc *req;
+	struct hclge_tx_buff_alloc_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 	u8 i;
 
-	req = (struct hclge_tx_buff_alloc *)desc.data;
+	req = (struct hclge_tx_buff_alloc_cmd *)desc.data;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0);
-	for (i = 0; i < HCLGE_TC_NUM; i++)
+	for (i = 0; i < HCLGE_TC_NUM; i++) {
+		u32 buf_size = buf_alloc->priv_buf[i].tx_buf_size;
+
 		req->tx_pkt_buff[i] =
 			cpu_to_le16((buf_size >> HCLGE_BUF_SIZE_UNIT_SHIFT) |
 				     HCLGE_BUF_SIZE_UPDATE_EN_MSK);
+	}
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
@@ -1352,9 +1413,10 @@ static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size)
 	return 0;
 }
 
-static int hclge_tx_buffer_alloc(struct hclge_dev *hdev, u32 buf_size)
+static int hclge_tx_buffer_alloc(struct hclge_dev *hdev,
+				 struct hclge_pkt_buf_alloc *buf_alloc)
 {
-	int ret = hclge_cmd_alloc_tx_buff(hdev, buf_size);
+	int ret = hclge_cmd_alloc_tx_buff(hdev, buf_alloc);
 
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
@@ -1387,13 +1449,14 @@ static int hclge_get_pfc_enalbe_num(struct hclge_dev *hdev)
 }
 
 /* Get the number of pfc enabled TCs, which have private buffer */
-static int hclge_get_pfc_priv_num(struct hclge_dev *hdev)
+static int hclge_get_pfc_priv_num(struct hclge_dev *hdev,
+				  struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_priv_buf *priv;
 	int i, cnt = 0;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 		if ((hdev->tm_info.hw_pfc_map & BIT(i)) &&
 		    priv->enable)
 			cnt++;
@@ -1403,13 +1466,14 @@ static int hclge_get_pfc_priv_num(struct hclge_dev *hdev)
 }
 
 /* Get the number of pfc disabled TCs, which have private buffer */
-static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev)
+static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev,
+				     struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_priv_buf *priv;
 	int i, cnt = 0;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 		if (hdev->hw_tc_map & BIT(i) &&
 		    !(hdev->tm_info.hw_pfc_map & BIT(i)) &&
 		    priv->enable)
@@ -1419,21 +1483,33 @@ static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev)
 	return cnt;
 }
 
-static u32 hclge_get_rx_priv_buff_alloced(struct hclge_dev *hdev)
+static u32 hclge_get_rx_priv_buff_alloced(struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_priv_buf *priv;
 	u32 rx_priv = 0;
 	int i;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 		if (priv->enable)
 			rx_priv += priv->buf_size;
 	}
 	return rx_priv;
 }
 
-static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all)
+static u32 hclge_get_tx_buff_alloced(struct hclge_pkt_buf_alloc *buf_alloc)
+{
+	u32 i, total_tx_size = 0;
+
+	for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
+		total_tx_size += buf_alloc->priv_buf[i].tx_buf_size;
+
+	return total_tx_size;
+}
+
+static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev,
+				struct hclge_pkt_buf_alloc *buf_alloc,
+				u32 rx_all)
 {
 	u32 shared_buf_min, shared_buf_tc, shared_std;
 	int tc_num, pfc_enable_num;
@@ -1454,46 +1530,74 @@ static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all)
 			hdev->mps;
 	shared_std = max_t(u32, shared_buf_min, shared_buf_tc);
 
-	rx_priv = hclge_get_rx_priv_buff_alloced(hdev);
+	rx_priv = hclge_get_rx_priv_buff_alloced(buf_alloc);
 	if (rx_all <= rx_priv + shared_std)
 		return false;
 
 	shared_buf = rx_all - rx_priv;
-	hdev->s_buf.buf_size = shared_buf;
-	hdev->s_buf.self.high = shared_buf;
-	hdev->s_buf.self.low =  2 * hdev->mps;
+	buf_alloc->s_buf.buf_size = shared_buf;
+	buf_alloc->s_buf.self.high = shared_buf;
+	buf_alloc->s_buf.self.low =  2 * hdev->mps;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		if ((hdev->hw_tc_map & BIT(i)) &&
 		    (hdev->tm_info.hw_pfc_map & BIT(i))) {
-			hdev->s_buf.tc_thrd[i].low = hdev->mps;
-			hdev->s_buf.tc_thrd[i].high = 2 * hdev->mps;
+			buf_alloc->s_buf.tc_thrd[i].low = hdev->mps;
+			buf_alloc->s_buf.tc_thrd[i].high = 2 * hdev->mps;
 		} else {
-			hdev->s_buf.tc_thrd[i].low = 0;
-			hdev->s_buf.tc_thrd[i].high = hdev->mps;
+			buf_alloc->s_buf.tc_thrd[i].low = 0;
+			buf_alloc->s_buf.tc_thrd[i].high = hdev->mps;
 		}
 	}
 
 	return true;
 }
 
+static int hclge_tx_buffer_calc(struct hclge_dev *hdev,
+				struct hclge_pkt_buf_alloc *buf_alloc)
+{
+	u32 i, total_size;
+
+	total_size = hdev->pkt_buf_size;
+
+	/* alloc tx buffer for all enabled tc */
+	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
+		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
+
+		if (total_size < HCLGE_DEFAULT_TX_BUF)
+			return -ENOMEM;
+
+		if (hdev->hw_tc_map & BIT(i))
+			priv->tx_buf_size = HCLGE_DEFAULT_TX_BUF;
+		else
+			priv->tx_buf_size = 0;
+
+		total_size -= priv->tx_buf_size;
+	}
+
+	return 0;
+}
+
 /* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs
  * @hdev: pointer to struct hclge_dev
- * @tx_size: the allocated tx buffer for all TCs
+ * @buf_alloc: pointer to buffer calculation data
  * @return: 0: calculate sucessful, negative: fail
  */
-int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
+static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
+				struct hclge_pkt_buf_alloc *buf_alloc)
 {
-	u32 rx_all = hdev->pkt_buf_size - tx_size;
+	u32 rx_all = hdev->pkt_buf_size;
 	int no_pfc_priv_num, pfc_priv_num;
 	struct hclge_priv_buf *priv;
 	int i;
 
+	rx_all -= hclge_get_tx_buff_alloced(buf_alloc);
+
 	/* When DCB is not supported, rx private
 	 * buffer is not allocated.
 	 */
 	if (!hnae3_dev_dcb_supported(hdev)) {
-		if (!hclge_is_rx_buf_ok(hdev, rx_all))
+		if (!hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
 			return -ENOMEM;
 
 		return 0;
@@ -1501,7 +1605,7 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
 
 	/* step 1, try to alloc private buffer for all enabled tc */
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 		if (hdev->hw_tc_map & BIT(i)) {
 			priv->enable = 1;
 			if (hdev->tm_info.hw_pfc_map & BIT(i)) {
@@ -1522,14 +1626,14 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
 		}
 	}
 
-	if (hclge_is_rx_buf_ok(hdev, rx_all))
+	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
 		return 0;
 
 	/* step 2, try to decrease the buffer size of
 	 * no pfc TC's private buffer
 	 */
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 
 		priv->enable = 0;
 		priv->wl.low = 0;
@@ -1552,18 +1656,18 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
 		}
 	}
 
-	if (hclge_is_rx_buf_ok(hdev, rx_all))
+	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
 		return 0;
 
 	/* step 3, try to reduce the number of pfc disabled TCs,
 	 * which have private buffer
 	 */
 	/* get the total no pfc enable TC number, which have private buffer */
-	no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev);
+	no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev, buf_alloc);
 
 	/* let the last to be cleared first */
 	for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 
 		if (hdev->hw_tc_map & BIT(i) &&
 		    !(hdev->tm_info.hw_pfc_map & BIT(i))) {
@@ -1575,22 +1679,22 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
 			no_pfc_priv_num--;
 		}
 
-		if (hclge_is_rx_buf_ok(hdev, rx_all) ||
+		if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all) ||
 		    no_pfc_priv_num == 0)
 			break;
 	}
 
-	if (hclge_is_rx_buf_ok(hdev, rx_all))
+	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
 		return 0;
 
 	/* step 4, try to reduce the number of pfc enabled TCs
 	 * which have private buffer.
 	 */
-	pfc_priv_num = hclge_get_pfc_priv_num(hdev);
+	pfc_priv_num = hclge_get_pfc_priv_num(hdev, buf_alloc);
 
 	/* let the last to be cleared first */
 	for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) {
-		priv = &hdev->priv_buf[i];
+		priv = &buf_alloc->priv_buf[i];
 
 		if (hdev->hw_tc_map & BIT(i) &&
 		    hdev->tm_info.hw_pfc_map & BIT(i)) {
@@ -1602,38 +1706,39 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
 			pfc_priv_num--;
 		}
 
-		if (hclge_is_rx_buf_ok(hdev, rx_all) ||
+		if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all) ||
 		    pfc_priv_num == 0)
 			break;
 	}
-	if (hclge_is_rx_buf_ok(hdev, rx_all))
+	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
 		return 0;
 
 	return -ENOMEM;
 }
 
-static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev)
+static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev,
+				   struct hclge_pkt_buf_alloc *buf_alloc)
 {
-	struct hclge_rx_priv_buff *req;
+	struct hclge_rx_priv_buff_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 	int i;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_PRIV_BUFF_ALLOC, false);
-	req = (struct hclge_rx_priv_buff *)desc.data;
+	req = (struct hclge_rx_priv_buff_cmd *)desc.data;
 
 	/* Alloc private buffer TCs */
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		struct hclge_priv_buf *priv = &hdev->priv_buf[i];
+		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
 
 		req->buf_num[i] =
 			cpu_to_le16(priv->buf_size >> HCLGE_BUF_UNIT_S);
 		req->buf_num[i] |=
-			cpu_to_le16(true << HCLGE_TC0_PRI_BUF_EN_B);
+			cpu_to_le16(1 << HCLGE_TC0_PRI_BUF_EN_B);
 	}
 
 	req->shared_buf =
-		cpu_to_le16((hdev->s_buf.buf_size >> HCLGE_BUF_UNIT_S) |
+		cpu_to_le16((buf_alloc->s_buf.buf_size >> HCLGE_BUF_UNIT_S) |
 			    (1 << HCLGE_TC0_PRI_BUF_EN_B));
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -1648,7 +1753,8 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev)
 
 #define HCLGE_PRIV_ENABLE(a) ((a) > 0 ? 1 : 0)
 
-static int hclge_rx_priv_wl_config(struct hclge_dev *hdev)
+static int hclge_rx_priv_wl_config(struct hclge_dev *hdev,
+				   struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_rx_priv_wl_buf *req;
 	struct hclge_priv_buf *priv;
@@ -1668,7 +1774,9 @@ static int hclge_rx_priv_wl_config(struct hclge_dev *hdev)
 			desc[i].flag &= ~cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
 
 		for (j = 0; j < HCLGE_TC_NUM_ONE_DESC; j++) {
-			priv = &hdev->priv_buf[i * HCLGE_TC_NUM_ONE_DESC + j];
+			u32 idx = i * HCLGE_TC_NUM_ONE_DESC + j;
+
+			priv = &buf_alloc->priv_buf[idx];
 			req->tc_wl[j].high =
 				cpu_to_le16(priv->wl.high >> HCLGE_BUF_UNIT_S);
 			req->tc_wl[j].high |=
@@ -1693,9 +1801,10 @@ static int hclge_rx_priv_wl_config(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int hclge_common_thrd_config(struct hclge_dev *hdev)
+static int hclge_common_thrd_config(struct hclge_dev *hdev,
+				    struct hclge_pkt_buf_alloc *buf_alloc)
 {
-	struct hclge_shared_buf *s_buf = &hdev->s_buf;
+	struct hclge_shared_buf *s_buf = &buf_alloc->s_buf;
 	struct hclge_rx_com_thrd *req;
 	struct hclge_desc desc[2];
 	struct hclge_tc_thrd *tc;
@@ -1739,9 +1848,10 @@ static int hclge_common_thrd_config(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int hclge_common_wl_config(struct hclge_dev *hdev)
+static int hclge_common_wl_config(struct hclge_dev *hdev,
+				  struct hclge_pkt_buf_alloc *buf_alloc)
 {
-	struct hclge_shared_buf *buf = &hdev->s_buf;
+	struct hclge_shared_buf *buf = &buf_alloc->s_buf;
 	struct hclge_rx_com_wl *req;
 	struct hclge_desc desc;
 	int ret;
@@ -1771,63 +1881,68 @@ static int hclge_common_wl_config(struct hclge_dev *hdev)
 
 int hclge_buffer_alloc(struct hclge_dev *hdev)
 {
-	u32 tx_buf_size = HCLGE_DEFAULT_TX_BUF;
+	struct hclge_pkt_buf_alloc *pkt_buf;
 	int ret;
 
-	hdev->priv_buf = devm_kmalloc_array(&hdev->pdev->dev, HCLGE_MAX_TC_NUM,
-					    sizeof(struct hclge_priv_buf),
-					    GFP_KERNEL | __GFP_ZERO);
-	if (!hdev->priv_buf)
+	pkt_buf = kzalloc(sizeof(*pkt_buf), GFP_KERNEL);
+	if (!pkt_buf)
 		return -ENOMEM;
 
-	ret = hclge_tx_buffer_alloc(hdev, tx_buf_size);
+	ret = hclge_tx_buffer_calc(hdev, pkt_buf);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"could not calc tx buffer size for all TCs %d\n", ret);
+		goto out;
+	}
+
+	ret = hclge_tx_buffer_alloc(hdev, pkt_buf);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"could not alloc tx buffers %d\n", ret);
-		return ret;
+		goto out;
 	}
 
-	ret = hclge_rx_buffer_calc(hdev, tx_buf_size);
+	ret = hclge_rx_buffer_calc(hdev, pkt_buf);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"could not calc rx priv buffer size for all TCs %d\n",
 			ret);
-		return ret;
+		goto out;
 	}
 
-	ret = hclge_rx_priv_buf_alloc(hdev);
+	ret = hclge_rx_priv_buf_alloc(hdev, pkt_buf);
 	if (ret) {
 		dev_err(&hdev->pdev->dev, "could not alloc rx priv buffer %d\n",
 			ret);
-		return ret;
+		goto out;
 	}
 
 	if (hnae3_dev_dcb_supported(hdev)) {
-		ret = hclge_rx_priv_wl_config(hdev);
+		ret = hclge_rx_priv_wl_config(hdev, pkt_buf);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
 				"could not configure rx private waterline %d\n",
 				ret);
-			return ret;
+			goto out;
 		}
 
-		ret = hclge_common_thrd_config(hdev);
+		ret = hclge_common_thrd_config(hdev, pkt_buf);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
 				"could not configure common threshold %d\n",
 				ret);
-			return ret;
+			goto out;
 		}
 	}
 
-	ret = hclge_common_wl_config(hdev);
-	if (ret) {
+	ret = hclge_common_wl_config(hdev, pkt_buf);
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"could not configure common waterline %d\n", ret);
-		return ret;
-	}
 
-	return 0;
+out:
+	kfree(pkt_buf);
+	return ret;
 }
 
 static int hclge_init_roce_base_info(struct hclge_vport *vport)
@@ -1932,11 +2047,11 @@ static void hclge_check_speed_dup(struct hclge_dev *hdev, int duplex, int speed)
 
 int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex)
 {
-	struct hclge_config_mac_speed_dup *req;
+	struct hclge_config_mac_speed_dup_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 
-	req = (struct hclge_config_mac_speed_dup *)desc.data;
+	req = (struct hclge_config_mac_speed_dup_cmd *)desc.data;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_SPEED_DUP, false);
 
@@ -2007,12 +2122,12 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed,
 static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed,
 					u8 *duplex)
 {
-	struct hclge_query_an_speed_dup *req;
+	struct hclge_query_an_speed_dup_cmd *req;
 	struct hclge_desc desc;
 	int speed_tmp;
 	int ret;
 
-	req = (struct hclge_query_an_speed_dup *)desc.data;
+	req = (struct hclge_query_an_speed_dup_cmd *)desc.data;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_AN_RESULT, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2040,11 +2155,11 @@ static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed,
 static int hclge_query_autoneg_result(struct hclge_dev *hdev)
 {
 	struct hclge_mac *mac = &hdev->hw.mac;
-	struct hclge_query_an_speed_dup *req;
+	struct hclge_query_an_speed_dup_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 
-	req = (struct hclge_query_an_speed_dup *)desc.data;
+	req = (struct hclge_query_an_speed_dup_cmd *)desc.data;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_AN_RESULT, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2061,14 +2176,16 @@ static int hclge_query_autoneg_result(struct hclge_dev *hdev)
 
 static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable)
 {
-	struct hclge_config_auto_neg *req;
+	struct hclge_config_auto_neg_cmd *req;
 	struct hclge_desc desc;
+	u32 flag = 0;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_AN_MODE, false);
 
-	req = (struct hclge_config_auto_neg *)desc.data;
-	hnae_set_bit(req->cfg_an_cmd_flag, HCLGE_MAC_CFG_AN_EN_B, !!enable);
+	req = (struct hclge_config_auto_neg_cmd *)desc.data;
+	hnae_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, !!enable);
+	req->cfg_an_cmd_flag = cpu_to_le32(flag);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
@@ -2112,13 +2229,6 @@ static int hclge_mac_init(struct hclge_dev *hdev)
 
 	mac->link = 0;
 
-	ret = hclge_mac_mdio_config(hdev);
-	if (ret) {
-		dev_warn(&hdev->pdev->dev,
-			 "mdio config fail ret=%d\n", ret);
-		return ret;
-	}
-
 	/* Initialize the MTA table work mode */
 	hdev->accept_mta_mc	= true;
 	hdev->enable_mta	= true;
@@ -2146,7 +2256,7 @@ static void hclge_task_schedule(struct hclge_dev *hdev)
 
 static int hclge_get_mac_link_status(struct hclge_dev *hdev)
 {
-	struct hclge_link_status *req;
+	struct hclge_link_status_cmd *req;
 	struct hclge_desc desc;
 	int link_status;
 	int ret;
@@ -2159,7 +2269,7 @@ static int hclge_get_mac_link_status(struct hclge_dev *hdev)
 		return ret;
 	}
 
-	req = (struct hclge_link_status *)desc.data;
+	req = (struct hclge_link_status_cmd *)desc.data;
 	link_status = req->status & HCLGE_LINK_STATUS;
 
 	return !!link_status;
@@ -2266,11 +2376,11 @@ static int hclge_get_status(struct hnae3_handle *handle)
 	return hdev->hw.mac.link;
 }
 
-static void hclge_service_timer(unsigned long data)
+static void hclge_service_timer(struct timer_list *t)
 {
-	struct hclge_dev *hdev = (struct hclge_dev *)data;
-	(void)mod_timer(&hdev->service_timer, jiffies + HZ);
+	struct hclge_dev *hdev = from_timer(hdev, t, service_timer);
 
+	mod_timer(&hdev->service_timer, jiffies + HZ);
 	hclge_task_schedule(hdev);
 }
 
@@ -2283,11 +2393,275 @@ static void hclge_service_complete(struct hclge_dev *hdev)
 	clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state);
 }
 
+static void hclge_enable_vector(struct hclge_misc_vector *vector, bool enable)
+{
+	writel(enable ? 1 : 0, vector->addr);
+}
+
+static irqreturn_t hclge_misc_irq_handle(int irq, void *data)
+{
+	struct hclge_dev *hdev = data;
+
+	hclge_enable_vector(&hdev->misc_vector, false);
+	if (!test_and_set_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state))
+		schedule_work(&hdev->service_task);
+
+	return IRQ_HANDLED;
+}
+
+static void hclge_free_vector(struct hclge_dev *hdev, int vector_id)
+{
+	hdev->vector_status[vector_id] = HCLGE_INVALID_VPORT;
+	hdev->num_msi_left += 1;
+	hdev->num_msi_used -= 1;
+}
+
+static void hclge_get_misc_vector(struct hclge_dev *hdev)
+{
+	struct hclge_misc_vector *vector = &hdev->misc_vector;
+
+	vector->vector_irq = pci_irq_vector(hdev->pdev, 0);
+
+	vector->addr = hdev->hw.io_base + HCLGE_MISC_VECTOR_REG_BASE;
+	hdev->vector_status[0] = 0;
+
+	hdev->num_msi_left -= 1;
+	hdev->num_msi_used += 1;
+}
+
+static int hclge_misc_irq_init(struct hclge_dev *hdev)
+{
+	int ret;
+
+	hclge_get_misc_vector(hdev);
+
+	ret = devm_request_irq(&hdev->pdev->dev,
+			       hdev->misc_vector.vector_irq,
+			       hclge_misc_irq_handle, 0, "hclge_misc", hdev);
+	if (ret) {
+		hclge_free_vector(hdev, 0);
+		dev_err(&hdev->pdev->dev, "request misc irq(%d) fail\n",
+			hdev->misc_vector.vector_irq);
+	}
+
+	return ret;
+}
+
+static int hclge_notify_client(struct hclge_dev *hdev,
+			       enum hnae3_reset_notify_type type)
+{
+	struct hnae3_client *client = hdev->nic_client;
+	u16 i;
+
+	if (!client->ops->reset_notify)
+		return -EOPNOTSUPP;
+
+	for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
+		struct hnae3_handle *handle = &hdev->vport[i].nic;
+		int ret;
+
+		ret = client->ops->reset_notify(handle, type);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int hclge_reset_wait(struct hclge_dev *hdev)
+{
+#define HCLGE_RESET_WATI_MS	100
+#define HCLGE_RESET_WAIT_CNT	5
+	u32 val, reg, reg_bit;
+	u32 cnt = 0;
+
+	switch (hdev->reset_type) {
+	case HNAE3_GLOBAL_RESET:
+		reg = HCLGE_GLOBAL_RESET_REG;
+		reg_bit = HCLGE_GLOBAL_RESET_BIT;
+		break;
+	case HNAE3_CORE_RESET:
+		reg = HCLGE_GLOBAL_RESET_REG;
+		reg_bit = HCLGE_CORE_RESET_BIT;
+		break;
+	case HNAE3_FUNC_RESET:
+		reg = HCLGE_FUN_RST_ING;
+		reg_bit = HCLGE_FUN_RST_ING_B;
+		break;
+	default:
+		dev_err(&hdev->pdev->dev,
+			"Wait for unsupported reset type: %d\n",
+			hdev->reset_type);
+		return -EINVAL;
+	}
+
+	val = hclge_read_dev(&hdev->hw, reg);
+	while (hnae_get_bit(val, reg_bit) && cnt < HCLGE_RESET_WAIT_CNT) {
+		msleep(HCLGE_RESET_WATI_MS);
+		val = hclge_read_dev(&hdev->hw, reg);
+		cnt++;
+	}
+
+	/* must clear reset status register to
+	 * prevent driver detect reset interrupt again
+	 */
+	reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG);
+	hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG, reg);
+
+	if (cnt >= HCLGE_RESET_WAIT_CNT) {
+		dev_warn(&hdev->pdev->dev,
+			 "Wait for reset timeout: %d\n", hdev->reset_type);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id)
+{
+	struct hclge_desc desc;
+	struct hclge_reset_cmd *req = (struct hclge_reset_cmd *)desc.data;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_RST_TRIGGER, false);
+	hnae_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_MAC_B, 0);
+	hnae_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_FUNC_B, 1);
+	req->fun_reset_vfid = func_id;
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"send function reset cmd fail, status =%d\n", ret);
+
+	return ret;
+}
+
+static void hclge_do_reset(struct hclge_dev *hdev, enum hnae3_reset_type type)
+{
+	struct pci_dev *pdev = hdev->pdev;
+	u32 val;
+
+	switch (type) {
+	case HNAE3_GLOBAL_RESET:
+		val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG);
+		hnae_set_bit(val, HCLGE_GLOBAL_RESET_BIT, 1);
+		hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val);
+		dev_info(&pdev->dev, "Global Reset requested\n");
+		break;
+	case HNAE3_CORE_RESET:
+		val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG);
+		hnae_set_bit(val, HCLGE_CORE_RESET_BIT, 1);
+		hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val);
+		dev_info(&pdev->dev, "Core Reset requested\n");
+		break;
+	case HNAE3_FUNC_RESET:
+		dev_info(&pdev->dev, "PF Reset requested\n");
+		hclge_func_reset_cmd(hdev, 0);
+		break;
+	default:
+		dev_warn(&pdev->dev,
+			 "Unsupported reset type: %d\n", type);
+		break;
+	}
+}
+
+static enum hnae3_reset_type hclge_detected_reset_event(struct hclge_dev *hdev)
+{
+	enum hnae3_reset_type rst_level = HNAE3_NONE_RESET;
+	u32 rst_reg_val;
+
+	rst_reg_val = hclge_read_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG);
+	if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & rst_reg_val)
+		rst_level = HNAE3_GLOBAL_RESET;
+	else if (BIT(HCLGE_VECTOR0_CORERESET_INT_B) & rst_reg_val)
+		rst_level = HNAE3_CORE_RESET;
+	else if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & rst_reg_val)
+		rst_level = HNAE3_IMP_RESET;
+
+	return rst_level;
+}
+
+static void hclge_reset_event(struct hnae3_handle *handle,
+			      enum hnae3_reset_type reset)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	dev_info(&hdev->pdev->dev,
+		 "Receive reset event , reset_type is %d", reset);
+
+	switch (reset) {
+	case HNAE3_FUNC_RESET:
+	case HNAE3_CORE_RESET:
+	case HNAE3_GLOBAL_RESET:
+		if (test_bit(HCLGE_STATE_RESET_INT, &hdev->state)) {
+			dev_err(&hdev->pdev->dev, "Already in reset state");
+			return;
+		}
+		hdev->reset_type = reset;
+		set_bit(HCLGE_STATE_RESET_INT, &hdev->state);
+		set_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state);
+		schedule_work(&hdev->service_task);
+		break;
+	default:
+		dev_warn(&hdev->pdev->dev, "Unsupported reset event:%d", reset);
+		break;
+	}
+}
+
+static void hclge_reset_subtask(struct hclge_dev *hdev)
+{
+	bool do_reset;
+
+	do_reset = hdev->reset_type != HNAE3_NONE_RESET;
+
+	/* Reset is detected by interrupt */
+	if (hdev->reset_type == HNAE3_NONE_RESET)
+		hdev->reset_type = hclge_detected_reset_event(hdev);
+
+	if (hdev->reset_type == HNAE3_NONE_RESET)
+		return;
+
+	switch (hdev->reset_type) {
+	case HNAE3_FUNC_RESET:
+	case HNAE3_CORE_RESET:
+	case HNAE3_GLOBAL_RESET:
+	case HNAE3_IMP_RESET:
+		hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+
+		if (do_reset)
+			hclge_do_reset(hdev, hdev->reset_type);
+		else
+			set_bit(HCLGE_STATE_RESET_INT, &hdev->state);
+
+		if (!hclge_reset_wait(hdev)) {
+			hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
+			hclge_reset_ae_dev(hdev->ae_dev);
+			hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+			clear_bit(HCLGE_STATE_RESET_INT, &hdev->state);
+		}
+		hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+		break;
+	default:
+		dev_err(&hdev->pdev->dev, "Unsupported reset type:%d\n",
+			hdev->reset_type);
+		break;
+	}
+	hdev->reset_type = HNAE3_NONE_RESET;
+}
+
+static void hclge_misc_irq_service_task(struct hclge_dev *hdev)
+{
+	hclge_reset_subtask(hdev);
+	hclge_enable_vector(&hdev->misc_vector, true);
+}
+
 static void hclge_service_task(struct work_struct *work)
 {
 	struct hclge_dev *hdev =
 		container_of(work, struct hclge_dev, service_task);
 
+	hclge_misc_irq_service_task(hdev);
 	hclge_update_speed_duplex(hdev);
 	hclge_update_link_status(hdev);
 	hclge_update_stats_for_all(hdev);
@@ -2383,7 +2757,7 @@ static u32 hclge_get_rss_indir_size(struct hnae3_handle *handle)
 
 static int hclge_get_rss_algo(struct hclge_dev *hdev)
 {
-	struct hclge_rss_config *req;
+	struct hclge_rss_config_cmd *req;
 	struct hclge_desc desc;
 	int rss_hash_algo;
 	int ret;
@@ -2397,7 +2771,7 @@ static int hclge_get_rss_algo(struct hclge_dev *hdev)
 		return ret;
 	}
 
-	req = (struct hclge_rss_config *)desc.data;
+	req = (struct hclge_rss_config_cmd *)desc.data;
 	rss_hash_algo = (req->hash_config & HCLGE_RSS_HASH_ALGO_MASK);
 
 	if (rss_hash_algo == HCLGE_RSS_HASH_ALGO_TOEPLITZ)
@@ -2409,13 +2783,13 @@ static int hclge_get_rss_algo(struct hclge_dev *hdev)
 static int hclge_set_rss_algo_key(struct hclge_dev *hdev,
 				  const u8 hfunc, const u8 *key)
 {
-	struct hclge_rss_config *req;
+	struct hclge_rss_config_cmd *req;
 	struct hclge_desc desc;
 	int key_offset;
 	int key_size;
 	int ret;
 
-	req = (struct hclge_rss_config *)desc.data;
+	req = (struct hclge_rss_config_cmd *)desc.data;
 
 	for (key_offset = 0; key_offset < 3; key_offset++) {
 		hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_GENERIC_CONFIG,
@@ -2446,19 +2820,20 @@ static int hclge_set_rss_algo_key(struct hclge_dev *hdev,
 
 static int hclge_set_rss_indir_table(struct hclge_dev *hdev, const u32 *indir)
 {
-	struct hclge_rss_indirection_table *req;
+	struct hclge_rss_indirection_table_cmd *req;
 	struct hclge_desc desc;
 	int i, j;
 	int ret;
 
-	req = (struct hclge_rss_indirection_table *)desc.data;
+	req = (struct hclge_rss_indirection_table_cmd *)desc.data;
 
 	for (i = 0; i < HCLGE_RSS_CFG_TBL_NUM; i++) {
 		hclge_cmd_setup_basic_desc
 			(&desc, HCLGE_OPC_RSS_INDIR_TABLE, false);
 
-		req->start_table_index = i * HCLGE_RSS_CFG_TBL_SIZE;
-		req->rss_set_bitmap = HCLGE_RSS_SET_BITMAP_MSK;
+		req->start_table_index =
+			cpu_to_le16(i * HCLGE_RSS_CFG_TBL_SIZE);
+		req->rss_set_bitmap = cpu_to_le16(HCLGE_RSS_SET_BITMAP_MSK);
 
 		for (j = 0; j < HCLGE_RSS_CFG_TBL_SIZE; j++)
 			req->rss_result[j] =
@@ -2478,21 +2853,24 @@ static int hclge_set_rss_indir_table(struct hclge_dev *hdev, const u32 *indir)
 static int hclge_set_rss_tc_mode(struct hclge_dev *hdev, u16 *tc_valid,
 				 u16 *tc_size, u16 *tc_offset)
 {
-	struct hclge_rss_tc_mode *req;
+	struct hclge_rss_tc_mode_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 	int i;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_TC_MODE, false);
-	req = (struct hclge_rss_tc_mode *)desc.data;
+	req = (struct hclge_rss_tc_mode_cmd *)desc.data;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		hnae_set_bit(req->rss_tc_mode[i], HCLGE_RSS_TC_VALID_B,
-			     (tc_valid[i] & 0x1));
-		hnae_set_field(req->rss_tc_mode[i], HCLGE_RSS_TC_SIZE_M,
+		u16 mode = 0;
+
+		hnae_set_bit(mode, HCLGE_RSS_TC_VALID_B, (tc_valid[i] & 0x1));
+		hnae_set_field(mode, HCLGE_RSS_TC_SIZE_M,
 			       HCLGE_RSS_TC_SIZE_S, tc_size[i]);
-		hnae_set_field(req->rss_tc_mode[i], HCLGE_RSS_TC_OFFSET_M,
+		hnae_set_field(mode, HCLGE_RSS_TC_OFFSET_M,
 			       HCLGE_RSS_TC_OFFSET_S, tc_offset[i]);
+
+		req->rss_tc_mode[i] = cpu_to_le16(mode);
 	}
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2507,15 +2885,13 @@ static int hclge_set_rss_tc_mode(struct hclge_dev *hdev, u16 *tc_valid,
 
 static int hclge_set_rss_input_tuple(struct hclge_dev *hdev)
 {
-#define HCLGE_RSS_INPUT_TUPLE_OTHER		0xf
-#define HCLGE_RSS_INPUT_TUPLE_SCTP		0x1f
-	struct hclge_rss_input_tuple *req;
+	struct hclge_rss_input_tuple_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_INPUT_TUPLE, false);
 
-	req = (struct hclge_rss_input_tuple *)desc.data;
+	req = (struct hclge_rss_input_tuple_cmd *)desc.data;
 	req->ipv4_tcp_en = HCLGE_RSS_INPUT_TUPLE_OTHER;
 	req->ipv4_udp_en = HCLGE_RSS_INPUT_TUPLE_OTHER;
 	req->ipv4_sctp_en = HCLGE_RSS_INPUT_TUPLE_SCTP;
@@ -2589,6 +2965,161 @@ static int hclge_set_rss(struct hnae3_handle *handle, const u32 *indir,
 	return ret;
 }
 
+static u8 hclge_get_rss_hash_bits(struct ethtool_rxnfc *nfc)
+{
+	u8 hash_sets = nfc->data & RXH_L4_B_0_1 ? HCLGE_S_PORT_BIT : 0;
+
+	if (nfc->data & RXH_L4_B_2_3)
+		hash_sets |= HCLGE_D_PORT_BIT;
+	else
+		hash_sets &= ~HCLGE_D_PORT_BIT;
+
+	if (nfc->data & RXH_IP_SRC)
+		hash_sets |= HCLGE_S_IP_BIT;
+	else
+		hash_sets &= ~HCLGE_S_IP_BIT;
+
+	if (nfc->data & RXH_IP_DST)
+		hash_sets |= HCLGE_D_IP_BIT;
+	else
+		hash_sets &= ~HCLGE_D_IP_BIT;
+
+	if (nfc->flow_type == SCTP_V4_FLOW || nfc->flow_type == SCTP_V6_FLOW)
+		hash_sets |= HCLGE_V_TAG_BIT;
+
+	return hash_sets;
+}
+
+static int hclge_set_rss_tuple(struct hnae3_handle *handle,
+			       struct ethtool_rxnfc *nfc)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	struct hclge_rss_input_tuple_cmd *req;
+	struct hclge_desc desc;
+	u8 tuple_sets;
+	int ret;
+
+	if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST |
+			  RXH_L4_B_0_1 | RXH_L4_B_2_3))
+		return -EINVAL;
+
+	req = (struct hclge_rss_input_tuple_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_INPUT_TUPLE, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Read rss tuple fail, status = %d\n", ret);
+		return ret;
+	}
+
+	hclge_cmd_reuse_desc(&desc, false);
+
+	tuple_sets = hclge_get_rss_hash_bits(nfc);
+	switch (nfc->flow_type) {
+	case TCP_V4_FLOW:
+		req->ipv4_tcp_en = tuple_sets;
+		break;
+	case TCP_V6_FLOW:
+		req->ipv6_tcp_en = tuple_sets;
+		break;
+	case UDP_V4_FLOW:
+		req->ipv4_udp_en = tuple_sets;
+		break;
+	case UDP_V6_FLOW:
+		req->ipv6_udp_en = tuple_sets;
+		break;
+	case SCTP_V4_FLOW:
+		req->ipv4_sctp_en = tuple_sets;
+		break;
+	case SCTP_V6_FLOW:
+		if ((nfc->data & RXH_L4_B_0_1) ||
+		    (nfc->data & RXH_L4_B_2_3))
+			return -EINVAL;
+
+		req->ipv6_sctp_en = tuple_sets;
+		break;
+	case IPV4_FLOW:
+		req->ipv4_fragment_en = HCLGE_RSS_INPUT_TUPLE_OTHER;
+		break;
+	case IPV6_FLOW:
+		req->ipv6_fragment_en = HCLGE_RSS_INPUT_TUPLE_OTHER;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"Set rss tuple fail, status = %d\n", ret);
+
+	return ret;
+}
+
+static int hclge_get_rss_tuple(struct hnae3_handle *handle,
+			       struct ethtool_rxnfc *nfc)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	struct hclge_rss_input_tuple_cmd *req;
+	struct hclge_desc desc;
+	u8 tuple_sets;
+	int ret;
+
+	nfc->data = 0;
+
+	req = (struct hclge_rss_input_tuple_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_INPUT_TUPLE, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Read rss tuple fail, status = %d\n", ret);
+		return ret;
+	}
+
+	switch (nfc->flow_type) {
+	case TCP_V4_FLOW:
+		tuple_sets = req->ipv4_tcp_en;
+		break;
+	case UDP_V4_FLOW:
+		tuple_sets = req->ipv4_udp_en;
+		break;
+	case TCP_V6_FLOW:
+		tuple_sets = req->ipv6_tcp_en;
+		break;
+	case UDP_V6_FLOW:
+		tuple_sets = req->ipv6_udp_en;
+		break;
+	case SCTP_V4_FLOW:
+		tuple_sets = req->ipv4_sctp_en;
+		break;
+	case SCTP_V6_FLOW:
+		tuple_sets = req->ipv6_sctp_en;
+		break;
+	case IPV4_FLOW:
+	case IPV6_FLOW:
+		tuple_sets = HCLGE_S_IP_BIT | HCLGE_D_IP_BIT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (!tuple_sets)
+		return 0;
+
+	if (tuple_sets & HCLGE_D_PORT_BIT)
+		nfc->data |= RXH_L4_B_2_3;
+	if (tuple_sets & HCLGE_S_PORT_BIT)
+		nfc->data |= RXH_L4_B_0_1;
+	if (tuple_sets & HCLGE_D_IP_BIT)
+		nfc->data |= RXH_IP_DST;
+	if (tuple_sets & HCLGE_S_IP_BIT)
+		nfc->data |= RXH_IP_SRC;
+
+	return 0;
+}
+
 static int hclge_get_tc_size(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
@@ -2597,7 +3128,7 @@ static int hclge_get_tc_size(struct hnae3_handle *handle)
 	return hdev->rss_size_max;
 }
 
-static int hclge_rss_init_hw(struct hclge_dev *hdev)
+int hclge_rss_init_hw(struct hclge_dev *hdev)
 {
 	const  u8 hfunc = HCLGE_RSS_HASH_ALGO_TOEPLITZ;
 	struct hclge_vport *vport = hdev->vport;
@@ -2682,7 +3213,7 @@ int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector_id,
 				   struct hnae3_ring_chain_node *ring_chain)
 {
 	struct hclge_dev *hdev = vport->back;
-	struct hclge_ctrl_vector_chain *req;
+	struct hclge_ctrl_vector_chain_cmd *req;
 	struct hnae3_ring_chain_node *node;
 	struct hclge_desc desc;
 	int ret;
@@ -2690,20 +3221,21 @@ int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector_id,
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ADD_RING_TO_VECTOR, false);
 
-	req = (struct hclge_ctrl_vector_chain *)desc.data;
+	req = (struct hclge_ctrl_vector_chain_cmd *)desc.data;
 	req->int_vector_id = vector_id;
 
 	i = 0;
 	for (node = ring_chain; node; node = node->next) {
-		hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_TYPE_M,
-			       HCLGE_INT_TYPE_S,
+		u16 type_and_id = 0;
+
+		hnae_set_field(type_and_id, HCLGE_INT_TYPE_M, HCLGE_INT_TYPE_S,
 			       hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
-		hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M,
-			       HCLGE_TQP_ID_S,	node->tqp_index);
-		hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M,
+		hnae_set_field(type_and_id, HCLGE_TQP_ID_M, HCLGE_TQP_ID_S,
+			       node->tqp_index);
+		hnae_set_field(type_and_id, HCLGE_INT_GL_IDX_M,
 			       HCLGE_INT_GL_IDX_S,
 			       hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
-		req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]);
+		req->tqp_type_and_id[i] = cpu_to_le16(type_and_id);
 		req->vfid = vport->vport_id;
 
 		if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) {
@@ -2739,9 +3271,9 @@ int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector_id,
 	return 0;
 }
 
-int hclge_map_handle_ring_to_vector(struct hnae3_handle *handle,
-				    int vector,
-				    struct hnae3_ring_chain_node *ring_chain)
+static int hclge_map_handle_ring_to_vector(
+		struct hnae3_handle *handle, int vector,
+		struct hnae3_ring_chain_node *ring_chain)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
@@ -2763,7 +3295,7 @@ static int hclge_unmap_ring_from_vector(
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	struct hclge_ctrl_vector_chain *req;
+	struct hclge_ctrl_vector_chain_cmd *req;
 	struct hnae3_ring_chain_node *node;
 	struct hclge_desc desc;
 	int i, vector_id;
@@ -2778,21 +3310,22 @@ static int hclge_unmap_ring_from_vector(
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_DEL_RING_TO_VECTOR, false);
 
-	req = (struct hclge_ctrl_vector_chain *)desc.data;
+	req = (struct hclge_ctrl_vector_chain_cmd *)desc.data;
 	req->int_vector_id = vector_id;
 
 	i = 0;
 	for (node = ring_chain; node; node = node->next) {
-		hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_TYPE_M,
-			       HCLGE_INT_TYPE_S,
+		u16 type_and_id = 0;
+
+		hnae_set_field(type_and_id, HCLGE_INT_TYPE_M, HCLGE_INT_TYPE_S,
 			       hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
-		hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M,
-			       HCLGE_TQP_ID_S,	node->tqp_index);
-		hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M,
+		hnae_set_field(type_and_id, HCLGE_TQP_ID_M, HCLGE_TQP_ID_S,
+			       node->tqp_index);
+		hnae_set_field(type_and_id, HCLGE_INT_GL_IDX_M,
 			       HCLGE_INT_GL_IDX_S,
 			       hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
 
-		req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]);
+		req->tqp_type_and_id[i] = cpu_to_le16(type_and_id);
 		req->vfid = vport->vport_id;
 
 		if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) {
@@ -2830,13 +3363,13 @@ static int hclge_unmap_ring_from_vector(
 int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev,
 			       struct hclge_promisc_param *param)
 {
-	struct hclge_promisc_cfg *req;
+	struct hclge_promisc_cfg_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_PROMISC_MODE, false);
 
-	req = (struct hclge_promisc_cfg *)desc.data;
+	req = (struct hclge_promisc_cfg_cmd *)desc.data;
 	req->vf_id = param->vf_id;
 	req->flag = (param->enable << HCLGE_PROMISC_EN_B);
 
@@ -2878,29 +3411,27 @@ static void hclge_set_promisc_mode(struct hnae3_handle *handle, u32 en)
 static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable)
 {
 	struct hclge_desc desc;
-	struct hclge_config_mac_mode *req =
-		(struct hclge_config_mac_mode *)desc.data;
+	struct hclge_config_mac_mode_cmd *req =
+		(struct hclge_config_mac_mode_cmd *)desc.data;
+	u32 loop_en = 0;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, false);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_TX_EN_B, enable);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_RX_EN_B, enable);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_PAD_TX_B, enable);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_PAD_RX_B, enable);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_1588_TX_B, 0);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_1588_RX_B, 0);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_APP_LP_B, 0);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_LINE_LP_B, 0);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_FCS_TX_B, enable);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_RX_FCS_B, enable);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en,
-		     HCLGE_MAC_RX_FCS_STRIP_B, enable);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en,
-		     HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en,
-		     HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable);
-	hnae_set_bit(req->txrx_pad_fcs_loop_en,
-		     HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable);
+	hnae_set_bit(loop_en, HCLGE_MAC_TX_EN_B, enable);
+	hnae_set_bit(loop_en, HCLGE_MAC_RX_EN_B, enable);
+	hnae_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, enable);
+	hnae_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, enable);
+	hnae_set_bit(loop_en, HCLGE_MAC_1588_TX_B, 0);
+	hnae_set_bit(loop_en, HCLGE_MAC_1588_RX_B, 0);
+	hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0);
+	hnae_set_bit(loop_en, HCLGE_MAC_LINE_LP_B, 0);
+	hnae_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, enable);
+	hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, enable);
+	hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, enable);
+	hnae_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable);
+	hnae_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable);
+	hnae_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable);
+	req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
@@ -2908,12 +3439,65 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable)
 			"mac enable fail, ret =%d.\n", ret);
 }
 
+static int hclge_set_loopback(struct hnae3_handle *handle,
+			      enum hnae3_loop loop_mode, bool en)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_config_mac_mode_cmd *req;
+	struct hclge_dev *hdev = vport->back;
+	struct hclge_desc desc;
+	u32 loop_en;
+	int ret;
+
+	switch (loop_mode) {
+	case HNAE3_MAC_INTER_LOOP_MAC:
+		req = (struct hclge_config_mac_mode_cmd *)&desc.data[0];
+		/* 1 Read out the MAC mode config at first */
+		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,
+				"mac loopback get fail, ret =%d.\n",
+				ret);
+			return ret;
+		}
+
+		/* 2 Then setup the loopback flag */
+		loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en);
+		if (en)
+			hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 1);
+		else
+			hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0);
+
+		req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
+
+		/* 3 Config mac work mode with loopback flag
+		 * and its original configure parameters
+		 */
+		hclge_cmd_reuse_desc(&desc, false);
+		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+		if (ret)
+			dev_err(&hdev->pdev->dev,
+				"mac loopback set fail, ret =%d.\n", ret);
+		break;
+	default:
+		ret = -ENOTSUPP;
+		dev_err(&hdev->pdev->dev,
+			"loop_mode %d is not supported\n", loop_mode);
+		break;
+	}
+
+	return ret;
+}
+
 static int hclge_tqp_enable(struct hclge_dev *hdev, int tqp_id,
 			    int stream_id, bool enable)
 {
 	struct hclge_desc desc;
-	struct hclge_cfg_com_tqp_queue *req =
-		(struct hclge_cfg_com_tqp_queue *)desc.data;
+	struct hclge_cfg_com_tqp_queue_cmd *req =
+		(struct hclge_cfg_com_tqp_queue_cmd *)desc.data;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_COM_TQP_QUEUE, false);
@@ -2963,7 +3547,7 @@ static int hclge_ae_start(struct hnae3_handle *handle)
 	/* mac enable */
 	hclge_cfg_mac_mode(hdev, true);
 	clear_bit(HCLGE_STATE_DOWN, &hdev->state);
-	(void)mod_timer(&hdev->service_timer, jiffies + HZ);
+	mod_timer(&hdev->service_timer, jiffies + HZ);
 
 	ret = hclge_mac_start_phy(hdev);
 	if (ret)
@@ -3077,16 +3661,16 @@ static int hclge_update_desc_vfid(struct hclge_desc *desc, int vfid, bool clr)
 		word_num = vfid / 32;
 		bit_num  = vfid % 32;
 		if (clr)
-			desc[1].data[word_num] &= ~(1 << bit_num);
+			desc[1].data[word_num] &= cpu_to_le32(~(1 << bit_num));
 		else
-			desc[1].data[word_num] |= (1 << bit_num);
+			desc[1].data[word_num] |= cpu_to_le32(1 << bit_num);
 	} else {
 		word_num = (vfid - 192) / 32;
 		bit_num  = vfid % 32;
 		if (clr)
-			desc[2].data[word_num] &= ~(1 << bit_num);
+			desc[2].data[word_num] &= cpu_to_le32(~(1 << bit_num));
 		else
-			desc[2].data[word_num] |= (1 << bit_num);
+			desc[2].data[word_num] |= cpu_to_le32(1 << bit_num);
 	}
 
 	return 0;
@@ -3106,7 +3690,7 @@ static bool hclge_is_all_function_id_zero(struct hclge_desc *desc)
 	return true;
 }
 
-static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry *new_req,
+static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry_cmd *new_req,
 				   const u8 *addr)
 {
 	const unsigned char *mac_addr = addr;
@@ -3118,8 +3702,8 @@ static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry *new_req,
 	new_req->mac_addr_lo16 = cpu_to_le16(low_val & 0xffff);
 }
 
-u16 hclge_get_mac_addr_to_mta_index(struct hclge_vport *vport,
-				    const u8 *addr)
+static u16 hclge_get_mac_addr_to_mta_index(struct hclge_vport *vport,
+					   const u8 *addr)
 {
 	u16 high_val = addr[1] | (addr[0] << 8);
 	struct hclge_dev *hdev = vport->back;
@@ -3133,11 +3717,11 @@ static int hclge_set_mta_filter_mode(struct hclge_dev *hdev,
 				     enum hclge_mta_dmac_sel_type mta_mac_sel,
 				     bool enable)
 {
-	struct hclge_mta_filter_mode *req;
+	struct hclge_mta_filter_mode_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 
-	req = (struct hclge_mta_filter_mode *)desc.data;
+	req = (struct hclge_mta_filter_mode_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_MODE_CFG, false);
 
 	hnae_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B,
@@ -3160,11 +3744,11 @@ int hclge_cfg_func_mta_filter(struct hclge_dev *hdev,
 			      u8 func_id,
 			      bool enable)
 {
-	struct hclge_cfg_func_mta_filter *req;
+	struct hclge_cfg_func_mta_filter_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 
-	req = (struct hclge_cfg_func_mta_filter *)desc.data;
+	req = (struct hclge_cfg_func_mta_filter_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_FUNC_CFG, false);
 
 	hnae_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B,
@@ -3187,17 +3771,18 @@ static int hclge_set_mta_table_item(struct hclge_vport *vport,
 				    bool enable)
 {
 	struct hclge_dev *hdev = vport->back;
-	struct hclge_cfg_func_mta_item *req;
+	struct hclge_cfg_func_mta_item_cmd *req;
 	struct hclge_desc desc;
+	u16 item_idx = 0;
 	int ret;
 
-	req = (struct hclge_cfg_func_mta_item *)desc.data;
+	req = (struct hclge_cfg_func_mta_item_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_TBL_ITEM_CFG, false);
 	hnae_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable);
 
-	hnae_set_field(req->item_idx, HCLGE_CFG_MTA_ITEM_IDX_M,
+	hnae_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M,
 		       HCLGE_CFG_MTA_ITEM_IDX_S, idx);
-	req->item_idx = cpu_to_le16(req->item_idx);
+	req->item_idx = cpu_to_le16(item_idx);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
@@ -3211,16 +3796,17 @@ static int hclge_set_mta_table_item(struct hclge_vport *vport,
 }
 
 static int hclge_remove_mac_vlan_tbl(struct hclge_vport *vport,
-				     struct hclge_mac_vlan_tbl_entry *req)
+				     struct hclge_mac_vlan_tbl_entry_cmd *req)
 {
 	struct hclge_dev *hdev = vport->back;
 	struct hclge_desc desc;
 	u8 resp_code;
+	u16 retval;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_REMOVE, false);
 
-	memcpy(desc.data, req, sizeof(struct hclge_mac_vlan_tbl_entry));
+	memcpy(desc.data, req, sizeof(struct hclge_mac_vlan_tbl_entry_cmd));
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
@@ -3229,19 +3815,21 @@ static int hclge_remove_mac_vlan_tbl(struct hclge_vport *vport,
 			ret);
 		return ret;
 	}
-	resp_code = (desc.data[0] >> 8) & 0xff;
+	resp_code = (le32_to_cpu(desc.data[0]) >> 8) & 0xff;
+	retval = le16_to_cpu(desc.retval);
 
-	return hclge_get_mac_vlan_cmd_status(vport, desc.retval, resp_code,
+	return hclge_get_mac_vlan_cmd_status(vport, retval, resp_code,
 					     HCLGE_MAC_VLAN_REMOVE);
 }
 
 static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport,
-				     struct hclge_mac_vlan_tbl_entry *req,
+				     struct hclge_mac_vlan_tbl_entry_cmd *req,
 				     struct hclge_desc *desc,
 				     bool is_mc)
 {
 	struct hclge_dev *hdev = vport->back;
 	u8 resp_code;
+	u16 retval;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_MAC_VLAN_ADD, true);
@@ -3249,7 +3837,7 @@ static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport,
 		desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
 		memcpy(desc[0].data,
 		       req,
-		       sizeof(struct hclge_mac_vlan_tbl_entry));
+		       sizeof(struct hclge_mac_vlan_tbl_entry_cmd));
 		hclge_cmd_setup_basic_desc(&desc[1],
 					   HCLGE_OPC_MAC_VLAN_ADD,
 					   true);
@@ -3261,7 +3849,7 @@ static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport,
 	} else {
 		memcpy(desc[0].data,
 		       req,
-		       sizeof(struct hclge_mac_vlan_tbl_entry));
+		       sizeof(struct hclge_mac_vlan_tbl_entry_cmd));
 		ret = hclge_cmd_send(&hdev->hw, desc, 1);
 	}
 	if (ret) {
@@ -3270,19 +3858,21 @@ static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport,
 			ret);
 		return ret;
 	}
-	resp_code = (desc[0].data[0] >> 8) & 0xff;
+	resp_code = (le32_to_cpu(desc[0].data[0]) >> 8) & 0xff;
+	retval = le16_to_cpu(desc[0].retval);
 
-	return hclge_get_mac_vlan_cmd_status(vport, desc[0].retval, resp_code,
+	return hclge_get_mac_vlan_cmd_status(vport, retval, resp_code,
 					     HCLGE_MAC_VLAN_LKUP);
 }
 
 static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport,
-				  struct hclge_mac_vlan_tbl_entry *req,
+				  struct hclge_mac_vlan_tbl_entry_cmd *req,
 				  struct hclge_desc *mc_desc)
 {
 	struct hclge_dev *hdev = vport->back;
 	int cfg_status;
 	u8 resp_code;
+	u16 retval;
 	int ret;
 
 	if (!mc_desc) {
@@ -3291,25 +3881,29 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport,
 		hclge_cmd_setup_basic_desc(&desc,
 					   HCLGE_OPC_MAC_VLAN_ADD,
 					   false);
-		memcpy(desc.data, req, sizeof(struct hclge_mac_vlan_tbl_entry));
+		memcpy(desc.data, req,
+		       sizeof(struct hclge_mac_vlan_tbl_entry_cmd));
 		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-		resp_code = (desc.data[0] >> 8) & 0xff;
-		cfg_status = hclge_get_mac_vlan_cmd_status(vport, desc.retval,
+		resp_code = (le32_to_cpu(desc.data[0]) >> 8) & 0xff;
+		retval = le16_to_cpu(desc.retval);
+
+		cfg_status = hclge_get_mac_vlan_cmd_status(vport, retval,
 							   resp_code,
 							   HCLGE_MAC_VLAN_ADD);
 	} else {
-		mc_desc[0].flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR);
+		hclge_cmd_reuse_desc(&mc_desc[0], false);
 		mc_desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-		mc_desc[1].flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR);
+		hclge_cmd_reuse_desc(&mc_desc[1], false);
 		mc_desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-		mc_desc[2].flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR);
+		hclge_cmd_reuse_desc(&mc_desc[2], false);
 		mc_desc[2].flag &= cpu_to_le16(~HCLGE_CMD_FLAG_NEXT);
 		memcpy(mc_desc[0].data, req,
-		       sizeof(struct hclge_mac_vlan_tbl_entry));
+		       sizeof(struct hclge_mac_vlan_tbl_entry_cmd));
 		ret = hclge_cmd_send(&hdev->hw, mc_desc, 3);
-		resp_code = (mc_desc[0].data[0] >> 8) & 0xff;
-		cfg_status = hclge_get_mac_vlan_cmd_status(vport,
-							   mc_desc[0].retval,
+		resp_code = (le32_to_cpu(mc_desc[0].data[0]) >> 8) & 0xff;
+		retval = le16_to_cpu(mc_desc[0].retval);
+
+		cfg_status = hclge_get_mac_vlan_cmd_status(vport, retval,
 							   resp_code,
 							   HCLGE_MAC_VLAN_ADD);
 	}
@@ -3336,8 +3930,9 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport,
 			     const unsigned char *addr)
 {
 	struct hclge_dev *hdev = vport->back;
-	struct hclge_mac_vlan_tbl_entry req;
+	struct hclge_mac_vlan_tbl_entry_cmd req;
 	enum hclge_cmd_status status;
+	u16 egress_port = 0;
 
 	/* mac addr check */
 	if (is_zero_ether_addr(addr) ||
@@ -3357,15 +3952,15 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport,
 	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
 	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 0);
 	hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hnae_set_bit(req.egress_port,
-		     HCLGE_MAC_EPORT_SW_EN_B, 0);
-	hnae_set_bit(req.egress_port,
-		     HCLGE_MAC_EPORT_TYPE_B, 0);
-	hnae_set_field(req.egress_port, HCLGE_MAC_EPORT_VFID_M,
+
+	hnae_set_bit(egress_port, HCLGE_MAC_EPORT_SW_EN_B, 0);
+	hnae_set_bit(egress_port, HCLGE_MAC_EPORT_TYPE_B, 0);
+	hnae_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M,
 		       HCLGE_MAC_EPORT_VFID_S, vport->vport_id);
-	hnae_set_field(req.egress_port, HCLGE_MAC_EPORT_PFID_M,
+	hnae_set_field(egress_port, HCLGE_MAC_EPORT_PFID_M,
 		       HCLGE_MAC_EPORT_PFID_S, 0);
-	req.egress_port = cpu_to_le16(req.egress_port);
+
+	req.egress_port = cpu_to_le16(egress_port);
 
 	hclge_prepare_mac_addr(&req, addr);
 
@@ -3386,7 +3981,7 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport,
 			    const unsigned char *addr)
 {
 	struct hclge_dev *hdev = vport->back;
-	struct hclge_mac_vlan_tbl_entry req;
+	struct hclge_mac_vlan_tbl_entry_cmd req;
 	enum hclge_cmd_status status;
 
 	/* mac addr check */
@@ -3420,7 +4015,7 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport,
 			     const unsigned char *addr)
 {
 	struct hclge_dev *hdev = vport->back;
-	struct hclge_mac_vlan_tbl_entry req;
+	struct hclge_mac_vlan_tbl_entry_cmd req;
 	struct hclge_desc desc[3];
 	u16 tbl_idx;
 	int status;
@@ -3471,7 +4066,7 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport,
 			    const unsigned char *addr)
 {
 	struct hclge_dev *hdev = vport->back;
-	struct hclge_mac_vlan_tbl_entry req;
+	struct hclge_mac_vlan_tbl_entry_cmd req;
 	enum hclge_cmd_status status;
 	struct hclge_desc desc[3];
 	u16 tbl_idx;
@@ -3554,13 +4149,13 @@ static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p)
 static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type,
 				      bool filter_en)
 {
-	struct hclge_vlan_filter_ctrl *req;
+	struct hclge_vlan_filter_ctrl_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_FILTER_CTRL, false);
 
-	req = (struct hclge_vlan_filter_ctrl *)desc.data;
+	req = (struct hclge_vlan_filter_ctrl_cmd *)desc.data;
 	req->vlan_type = vlan_type;
 	req->vlan_fe = filter_en;
 
@@ -3578,8 +4173,8 @@ int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid,
 			     bool is_kill, u16 vlan, u8 qos, __be16 proto)
 {
 #define HCLGE_MAX_VF_BYTES  16
-	struct hclge_vlan_filter_vf_cfg *req0;
-	struct hclge_vlan_filter_vf_cfg *req1;
+	struct hclge_vlan_filter_vf_cfg_cmd *req0;
+	struct hclge_vlan_filter_vf_cfg_cmd *req1;
 	struct hclge_desc desc[2];
 	u8 vf_byte_val;
 	u8 vf_byte_off;
@@ -3595,10 +4190,10 @@ int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid,
 	vf_byte_off = vfid / 8;
 	vf_byte_val = 1 << (vfid % 8);
 
-	req0 = (struct hclge_vlan_filter_vf_cfg *)desc[0].data;
-	req1 = (struct hclge_vlan_filter_vf_cfg *)desc[1].data;
+	req0 = (struct hclge_vlan_filter_vf_cfg_cmd *)desc[0].data;
+	req1 = (struct hclge_vlan_filter_vf_cfg_cmd *)desc[1].data;
 
-	req0->vlan_id  = vlan;
+	req0->vlan_id  = cpu_to_le16(vlan);
 	req0->vlan_cfg = is_kill;
 
 	if (vf_byte_off < HCLGE_MAX_VF_BYTES)
@@ -3639,7 +4234,7 @@ static int hclge_set_port_vlan_filter(struct hnae3_handle *handle,
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	struct hclge_vlan_filter_pf_cfg *req;
+	struct hclge_vlan_filter_pf_cfg_cmd *req;
 	struct hclge_desc desc;
 	u8 vlan_offset_byte_val;
 	u8 vlan_offset_byte;
@@ -3652,7 +4247,7 @@ static int hclge_set_port_vlan_filter(struct hnae3_handle *handle,
 	vlan_offset_byte = (vlan_id % 160) / 8;
 	vlan_offset_byte_val = 1 << (vlan_id % 8);
 
-	req = (struct hclge_vlan_filter_pf_cfg *)desc.data;
+	req = (struct hclge_vlan_filter_pf_cfg_cmd *)desc.data;
 	req->vlan_offset = vlan_offset_160;
 	req->vlan_cfg = is_kill;
 	req->vlan_offset_bitmap[vlan_offset_byte] = vlan_offset_byte_val;
@@ -3714,7 +4309,7 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev)
 static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
-	struct hclge_config_max_frm_size *req;
+	struct hclge_config_max_frm_size_cmd *req;
 	struct hclge_dev *hdev = vport->back;
 	struct hclge_desc desc;
 	int ret;
@@ -3725,7 +4320,7 @@ static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu)
 	hdev->mps = new_mtu;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAX_FRM_SIZE, false);
 
-	req = (struct hclge_config_max_frm_size *)desc.data;
+	req = (struct hclge_config_max_frm_size_cmd *)desc.data;
 	req->max_frm_size = cpu_to_le16(new_mtu);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -3740,13 +4335,13 @@ static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu)
 static int hclge_send_reset_tqp_cmd(struct hclge_dev *hdev, u16 queue_id,
 				    bool enable)
 {
-	struct hclge_reset_tqp_queue *req;
+	struct hclge_reset_tqp_queue_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RESET_TQP_QUEUE, false);
 
-	req = (struct hclge_reset_tqp_queue *)desc.data;
+	req = (struct hclge_reset_tqp_queue_cmd *)desc.data;
 	req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK);
 	hnae_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable);
 
@@ -3762,13 +4357,13 @@ static int hclge_send_reset_tqp_cmd(struct hclge_dev *hdev, u16 queue_id,
 
 static int hclge_get_reset_status(struct hclge_dev *hdev, u16 queue_id)
 {
-	struct hclge_reset_tqp_queue *req;
+	struct hclge_reset_tqp_queue_cmd *req;
 	struct hclge_desc desc;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RESET_TQP_QUEUE, true);
 
-	req = (struct hclge_reset_tqp_queue *)desc.data;
+	req = (struct hclge_reset_tqp_queue_cmd *)desc.data;
 	req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -3981,7 +4576,7 @@ static int hclge_init_client_instance(struct hnae3_client *client,
 				vport->roce.client = client;
 			}
 
-			if (hdev->roce_client) {
+			if (hdev->roce_client && hdev->nic_client) {
 				ret = hclge_init_roce_base_info(vport);
 				if (ret)
 					goto err;
@@ -4007,13 +4602,19 @@ static void hclge_uninit_client_instance(struct hnae3_client *client,
 
 	for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
 		vport = &hdev->vport[i];
-		if (hdev->roce_client)
+		if (hdev->roce_client) {
 			hdev->roce_client->ops->uninit_instance(&vport->roce,
 								0);
+			hdev->roce_client = NULL;
+			vport->roce.client = NULL;
+		}
 		if (client->type == HNAE3_CLIENT_ROCE)
 			return;
-		if (client->ops->uninit_instance)
+		if (client->ops->uninit_instance) {
 			client->ops->uninit_instance(&vport->nic, 0);
+			hdev->nic_client = NULL;
+			vport->nic.client = NULL;
+		}
 	}
 }
 
@@ -4056,6 +4657,8 @@ static int hclge_pci_init(struct hclge_dev *hdev)
 		goto err_clr_master;
 	}
 
+	hdev->num_req_vfs = pci_sriov_get_totalvfs(pdev);
+
 	return 0;
 err_clr_master:
 	pci_clear_master(pdev);
@@ -4100,6 +4703,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hdev->flag |= HCLGE_FLAG_USE_MSIX;
 	hdev->pdev = pdev;
 	hdev->ae_dev = ae_dev;
+	hdev->reset_type = HNAE3_NONE_RESET;
 	ae_dev->priv = hdev;
 
 	ret = hclge_pci_init(hdev);
@@ -4108,7 +4712,14 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		goto err_pci_init;
 	}
 
-	/* Command queue initialize */
+	/* Firmware command queue initialize */
+	ret = hclge_cmd_queue_init(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Cmd queue init failed, ret = %d.\n", ret);
+		return ret;
+	}
+
+	/* Firmware command initialize */
 	ret = hclge_cmd_init(hdev);
 	if (ret)
 		goto err_cmd_init;
@@ -4135,6 +4746,14 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
+	ret = hclge_misc_irq_init(hdev);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"Misc IRQ(vector0) init error, ret = %d.\n",
+			ret);
+		return ret;
+	}
+
 	ret = hclge_alloc_tqps(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "Allocate TQPs error, ret = %d.\n", ret);
@@ -4147,6 +4766,19 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
+	ret = hclge_map_tqp(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Map tqp error, ret = %d.\n", ret);
+		return ret;
+	}
+
+	ret = hclge_mac_mdio_config(hdev);
+	if (ret) {
+		dev_warn(&hdev->pdev->dev,
+			 "mdio config fail ret=%d\n", ret);
+		return ret;
+	}
+
 	ret = hclge_mac_init(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "Mac init error, ret = %d\n", ret);
@@ -4182,10 +4814,14 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
-	setup_timer(&hdev->service_timer, hclge_service_timer,
-		    (unsigned long)hdev);
+	hclge_dcb_ops_set(hdev);
+
+	timer_setup(&hdev->service_timer, hclge_service_timer, 0);
 	INIT_WORK(&hdev->service_task, hclge_service_task);
 
+	/* Enable MISC vector(vector0) */
+	hclge_enable_vector(&hdev->misc_vector, true);
+
 	set_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state);
 	set_bit(HCLGE_STATE_DOWN, &hdev->state);
 
@@ -4200,6 +4836,91 @@ err_hclge_dev:
 	return ret;
 }
 
+static void hclge_stats_clear(struct hclge_dev *hdev)
+{
+	memset(&hdev->hw_stats, 0, sizeof(hdev->hw_stats));
+}
+
+static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
+{
+	struct hclge_dev *hdev = ae_dev->priv;
+	struct pci_dev *pdev = ae_dev->pdev;
+	int ret;
+
+	set_bit(HCLGE_STATE_DOWN, &hdev->state);
+
+	hclge_stats_clear(hdev);
+
+	ret = hclge_cmd_init(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Cmd queue init failed\n");
+		return ret;
+	}
+
+	ret = hclge_get_cap(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "get hw capability error, ret = %d.\n",
+			ret);
+		return ret;
+	}
+
+	ret = hclge_configure(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Configure dev error, ret = %d.\n", ret);
+		return ret;
+	}
+
+	ret = hclge_map_tqp(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Map tqp error, ret = %d.\n", ret);
+		return ret;
+	}
+
+	ret = hclge_mac_init(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Mac init error, ret = %d\n", ret);
+		return ret;
+	}
+
+	ret = hclge_buffer_alloc(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Buffer allocate fail, ret =%d\n", ret);
+		return ret;
+	}
+
+	ret = hclge_config_tso(hdev, HCLGE_TSO_MSS_MIN, HCLGE_TSO_MSS_MAX);
+	if (ret) {
+		dev_err(&pdev->dev, "Enable tso fail, ret =%d\n", ret);
+		return ret;
+	}
+
+	ret = hclge_init_vlan_config(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "VLAN init fail, ret =%d\n", ret);
+		return ret;
+	}
+
+	ret = hclge_tm_schd_init(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "tm schd init fail, ret =%d\n", ret);
+		return ret;
+	}
+
+	ret = hclge_rss_init_hw(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Rss init fail, ret =%d\n", ret);
+		return ret;
+	}
+
+	/* Enable MISC vector(vector0) */
+	hclge_enable_vector(&hdev->misc_vector, true);
+
+	dev_info(&pdev->dev, "Reset done, %s driver initialization finished.\n",
+		 HCLGE_DRIVER_NAME);
+
+	return 0;
+}
+
 static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	struct hclge_dev *hdev = ae_dev->priv;
@@ -4210,7 +4931,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	if (IS_ENABLED(CONFIG_PCI_IOV))
 		hclge_disable_sriov(hdev);
 
-	if (hdev->service_timer.data)
+	if (hdev->service_timer.function)
 		del_timer_sync(&hdev->service_timer);
 	if (hdev->service_task.func)
 		cancel_work_sync(&hdev->service_task);
@@ -4218,6 +4939,9 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	if (mac->phydev)
 		mdiobus_unregister(mac->mdio_bus);
 
+	/* Disable MISC vector(vector0) */
+	hclge_enable_vector(&hdev->misc_vector, false);
+	hclge_free_vector(hdev, 0);
 	hclge_destroy_cmd_queue(&hdev->hw);
 	hclge_pci_uninit(hdev);
 	ae_dev->priv = NULL;
@@ -4232,6 +4956,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.unmap_ring_from_vector = hclge_unmap_ring_from_vector,
 	.get_vector = hclge_get_vector,
 	.set_promisc_mode = hclge_set_promisc_mode,
+	.set_loopback = hclge_set_loopback,
 	.start = hclge_ae_start,
 	.stop = hclge_ae_stop,
 	.get_status = hclge_get_status,
@@ -4243,6 +4968,8 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.get_rss_indir_size = hclge_get_rss_indir_size,
 	.get_rss = hclge_get_rss,
 	.set_rss = hclge_set_rss,
+	.set_rss_tuple = hclge_set_rss_tuple,
+	.get_rss_tuple = hclge_get_rss_tuple,
 	.get_tc_size = hclge_get_tc_size,
 	.get_mac_addr = hclge_get_mac_addr,
 	.set_mac_addr = hclge_set_mac_addr,
@@ -4263,6 +4990,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.get_mdix_mode = hclge_get_mdix_mode,
 	.set_vlan_filter = hclge_set_port_vlan_filter,
 	.set_vf_vlan_filter = hclge_set_vf_vlan_filter,
+	.reset_event = hclge_reset_event,
 };
 
 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 9fcfd9395424..742e6ee9efaf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -27,12 +27,13 @@
 	(HCLGE_PF_CFG_BLOCK_SIZE / HCLGE_CFG_RD_LEN_BYTES)
 
 #define HCLGE_VECTOR_REG_BASE		0x20000
+#define HCLGE_MISC_VECTOR_REG_BASE	0x20400
 
 #define HCLGE_VECTOR_REG_OFFSET		0x4
 #define HCLGE_VECTOR_VF_OFFSET		0x100000
 
 #define HCLGE_RSS_IND_TBL_SIZE		512
-#define HCLGE_RSS_SET_BITMAP_MSK	0xffff
+#define HCLGE_RSS_SET_BITMAP_MSK	GENMASK(15, 0)
 #define HCLGE_RSS_KEY_SIZE		40
 #define HCLGE_RSS_HASH_ALGO_TOEPLITZ	0
 #define HCLGE_RSS_HASH_ALGO_SIMPLE	1
@@ -41,6 +42,14 @@
 #define HCLGE_RSS_CFG_TBL_NUM \
 	(HCLGE_RSS_IND_TBL_SIZE / HCLGE_RSS_CFG_TBL_SIZE)
 
+#define HCLGE_RSS_INPUT_TUPLE_OTHER	GENMASK(3, 0)
+#define HCLGE_RSS_INPUT_TUPLE_SCTP	GENMASK(4, 0)
+#define HCLGE_D_PORT_BIT		BIT(0)
+#define HCLGE_S_PORT_BIT		BIT(1)
+#define HCLGE_D_IP_BIT			BIT(2)
+#define HCLGE_S_IP_BIT			BIT(3)
+#define HCLGE_V_TAG_BIT			BIT(4)
+
 #define HCLGE_RSS_TC_SIZE_0		1
 #define HCLGE_RSS_TC_SIZE_1		2
 #define HCLGE_RSS_TC_SIZE_2		4
@@ -65,11 +74,24 @@
 #define HCLGE_PHY_CSS_REG		17
 
 #define HCLGE_PHY_MDIX_CTRL_S		(5)
-#define HCLGE_PHY_MDIX_CTRL_M		(3 << HCLGE_PHY_MDIX_CTRL_S)
+#define HCLGE_PHY_MDIX_CTRL_M		GENMASK(6, 5)
 
 #define HCLGE_PHY_MDIX_STATUS_B	(6)
 #define HCLGE_PHY_SPEED_DUP_RESOLVE_B	(11)
 
+/* Reset related Registers */
+#define HCLGE_MISC_RESET_STS_REG	0x20700
+#define HCLGE_GLOBAL_RESET_REG		0x20A00
+#define HCLGE_GLOBAL_RESET_BIT		0x0
+#define HCLGE_CORE_RESET_BIT		0x1
+#define HCLGE_FUN_RST_ING		0x20C00
+#define HCLGE_FUN_RST_ING_B		0
+
+/* Vector0 register bits define */
+#define HCLGE_VECTOR0_GLOBALRESET_INT_B	5
+#define HCLGE_VECTOR0_CORERESET_INT_B	6
+#define HCLGE_VECTOR0_IMPRESET_INT_B	7
+
 enum HCLGE_DEV_STATE {
 	HCLGE_STATE_REINITING,
 	HCLGE_STATE_DOWN,
@@ -79,6 +101,7 @@ enum HCLGE_DEV_STATE {
 	HCLGE_STATE_SERVICE_SCHED,
 	HCLGE_STATE_MBX_HANDLING,
 	HCLGE_STATE_MBX_IRQ,
+	HCLGE_STATE_RESET_INT,
 	HCLGE_STATE_MAX
 };
 
@@ -392,9 +415,11 @@ struct hclge_dev {
 	struct pci_dev *pdev;
 	struct hnae3_ae_dev *ae_dev;
 	struct hclge_hw hw;
+	struct hclge_misc_vector misc_vector;
 	struct hclge_hw_stats hw_stats;
 	unsigned long state;
 
+	enum hnae3_reset_type reset_type;
 	u32 fw_version;
 	u16 num_vmdq_vport;		/* Num vmdq vport this PF has set up */
 	u16 num_tqps;			/* Num task queue pairs of this PF */
@@ -421,8 +446,11 @@ struct hclge_dev {
 #define HCLGE_FLAG_TC_BASE_SCH_MODE		1
 #define HCLGE_FLAG_VNET_BASE_SCH_MODE		2
 	u8 tx_sch_mode;
+	u8 tc_max;
+	u8 pfc_max;
 
 	u8 default_up;
+	u8 dcbx_cap;
 	struct hclge_tm_info tm_info;
 
 	u16 num_msi;
@@ -459,12 +487,11 @@ struct hclge_dev {
 #define HCLGE_FLAG_MAIN		0x00000004
 #define HCLGE_FLAG_DCB_CAPABLE	0x00000008
 #define HCLGE_FLAG_DCB_ENABLE	0x00000010
+#define HCLGE_FLAG_MQPRIO_ENABLE	0x00000020
 	u32 flag;
 
 	u32 pkt_buf_size; /* Total pf buf size for tx/rx */
 	u32 mps; /* Max packet size */
-	struct hclge_priv_buf *priv_buf;
-	struct hclge_shared_buf s_buf;
 
 	enum hclge_mta_dmac_sel_type mta_mac_sel_type;
 	bool enable_mta; /* Mutilcast filter enable */
@@ -517,4 +544,7 @@ static inline int hclge_get_queue_id(struct hnae3_queue *queue)
 int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex);
 int hclge_set_vf_vlan_common(struct hclge_dev *vport, int vfid,
 			     bool is_kill, u16 vlan, u8 qos, __be16 proto);
+
+int hclge_buffer_alloc(struct hclge_dev *hdev);
+int hclge_rss_init_hw(struct hclge_dev *hdev);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index f32d719c4f77..7069e9408d7d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -14,6 +14,13 @@
 #include "hclge_main.h"
 #include "hclge_mdio.h"
 
+#define HCLGE_PHY_SUPPORTED_FEATURES	(SUPPORTED_Autoneg | \
+					 SUPPORTED_TP | \
+					 SUPPORTED_Pause | \
+					 PHY_10BT_FEATURES | \
+					 PHY_100BT_FEATURES | \
+					 PHY_1000BT_FEATURES)
+
 enum hclge_mdio_c22_op_seq {
 	HCLGE_MDIO_C22_WRITE = 1,
 	HCLGE_MDIO_C22_READ = 2
@@ -195,6 +202,9 @@ int hclge_mac_start_phy(struct hclge_dev *hdev)
 		return ret;
 	}
 
+	phydev->supported &= HCLGE_PHY_SUPPORTED_FEATURES;
+	phydev->advertising = phydev->supported;
+
 	phy_start(phydev);
 
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 73a75d7cc551..7bfa2e5497cb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -124,6 +124,20 @@ static int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx)
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
 
+static int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap,
+				  u8 pfc_bitmap)
+{
+	struct hclge_desc desc;
+	struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)&desc.data;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_PFC_PAUSE_EN, false);
+
+	pfc->tx_rx_en_bitmap = tx_rx_bitmap;
+	pfc->pri_en_bitmap = pfc_bitmap;
+
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
 static int hclge_fill_pri_array(struct hclge_dev *hdev, u8 *pri, u8 pri_id)
 {
 	u8 tc;
@@ -269,6 +283,7 @@ static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev,
 	struct hclge_pg_shapping_cmd *shap_cfg_cmd;
 	enum hclge_opcode_type opcode;
 	struct hclge_desc desc;
+	u32 shapping_para = 0;
 
 	opcode = bucket ? HCLGE_OPC_TM_PG_P_SHAPPING :
 		HCLGE_OPC_TM_PG_C_SHAPPING;
@@ -278,11 +293,41 @@ static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev,
 
 	shap_cfg_cmd->pg_id = pg_id;
 
-	hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_B, ir_b);
-	hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_U, ir_u);
-	hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_S, ir_s);
-	hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_B, bs_b);
-	hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_S, bs_s);
+	hclge_tm_set_field(shapping_para, IR_B, ir_b);
+	hclge_tm_set_field(shapping_para, IR_U, ir_u);
+	hclge_tm_set_field(shapping_para, IR_S, ir_s);
+	hclge_tm_set_field(shapping_para, BS_B, bs_b);
+	hclge_tm_set_field(shapping_para, BS_S, bs_s);
+
+	shap_cfg_cmd->pg_shapping_para = cpu_to_le32(shapping_para);
+
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
+static int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev)
+{
+	struct hclge_port_shapping_cmd *shap_cfg_cmd;
+	struct hclge_desc desc;
+	u32 shapping_para = 0;
+	u8 ir_u, ir_b, ir_s;
+	int ret;
+
+	ret = hclge_shaper_para_calc(HCLGE_ETHER_MAX_RATE,
+				     HCLGE_SHAPER_LVL_PORT,
+				     &ir_b, &ir_u, &ir_s);
+	if (ret)
+		return ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PORT_SHAPPING, false);
+	shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data;
+
+	hclge_tm_set_field(shapping_para, IR_B, ir_b);
+	hclge_tm_set_field(shapping_para, IR_U, ir_u);
+	hclge_tm_set_field(shapping_para, IR_S, ir_s);
+	hclge_tm_set_field(shapping_para, BS_B, HCLGE_SHAPER_BS_U_DEF);
+	hclge_tm_set_field(shapping_para, BS_S, HCLGE_SHAPER_BS_S_DEF);
+
+	shap_cfg_cmd->port_shapping_para = cpu_to_le32(shapping_para);
 
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
@@ -295,6 +340,7 @@ static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev,
 	struct hclge_pri_shapping_cmd *shap_cfg_cmd;
 	enum hclge_opcode_type opcode;
 	struct hclge_desc desc;
+	u32 shapping_para = 0;
 
 	opcode = bucket ? HCLGE_OPC_TM_PRI_P_SHAPPING :
 		HCLGE_OPC_TM_PRI_C_SHAPPING;
@@ -305,11 +351,13 @@ static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev,
 
 	shap_cfg_cmd->pri_id = pri_id;
 
-	hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_B, ir_b);
-	hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_U, ir_u);
-	hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_S, ir_s);
-	hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_B, bs_b);
-	hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_S, bs_s);
+	hclge_tm_set_field(shapping_para, IR_B, ir_b);
+	hclge_tm_set_field(shapping_para, IR_U, ir_u);
+	hclge_tm_set_field(shapping_para, IR_S, ir_s);
+	hclge_tm_set_field(shapping_para, BS_B, bs_b);
+	hclge_tm_set_field(shapping_para, BS_S, bs_s);
+
+	shap_cfg_cmd->pri_shapping_para = cpu_to_le32(shapping_para);
 
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
@@ -346,13 +394,13 @@ static int hclge_tm_pri_schd_mode_cfg(struct hclge_dev *hdev, u8 pri_id)
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
 
-static int hclge_tm_qs_schd_mode_cfg(struct hclge_dev *hdev, u16 qs_id)
+static int hclge_tm_qs_schd_mode_cfg(struct hclge_dev *hdev, u16 qs_id, u8 mode)
 {
 	struct hclge_desc desc;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_QS_SCH_MODE_CFG, false);
 
-	if (hdev->tm_info.tc_info[qs_id].tc_sch_mode == HCLGE_SCH_MODE_DWRR)
+	if (mode == HCLGE_SCH_MODE_DWRR)
 		desc.data[1] = cpu_to_le32(HCLGE_TM_TX_SCHD_DWRR_MSK);
 	else
 		desc.data[1] = 0;
@@ -386,7 +434,6 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport)
 	struct hclge_dev *hdev = vport->back;
 	u8 i;
 
-	kinfo = &vport->nic.kinfo;
 	vport->bw_limit = hdev->tm_info.pg_info[0].bw_limit;
 	kinfo->num_tc =
 		min_t(u16, kinfo->num_tqps, hdev->tm_info.num_tc);
@@ -444,7 +491,11 @@ static void hclge_tm_tc_info_init(struct hclge_dev *hdev)
 		hdev->tm_info.prio_tc[i] =
 			(i >= hdev->tm_info.num_tc) ? 0 : i;
 
-	hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
+	/* DCB is enabled if we have more than 1 TC */
+	if (hdev->tm_info.num_tc > 1)
+		hdev->flag |= HCLGE_FLAG_DCB_ENABLE;
+	else
+		hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
 }
 
 static void hclge_tm_pg_info_init(struct hclge_dev *hdev)
@@ -470,6 +521,24 @@ static void hclge_tm_pg_info_init(struct hclge_dev *hdev)
 	}
 }
 
+static void hclge_pfc_info_init(struct hclge_dev *hdev)
+{
+	if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE)) {
+		if (hdev->fc_mode_last_time == HCLGE_FC_PFC)
+			dev_warn(&hdev->pdev->dev,
+				 "DCB is disable, but last mode is FC_PFC\n");
+
+		hdev->tm_info.fc_mode = hdev->fc_mode_last_time;
+	} else if (hdev->tm_info.fc_mode != HCLGE_FC_PFC) {
+		/* fc_mode_last_time record the last fc_mode when
+		 * DCB is enabled, so that fc_mode can be set to
+		 * the correct value when DCB is disabled.
+		 */
+		hdev->fc_mode_last_time = hdev->tm_info.fc_mode;
+		hdev->tm_info.fc_mode = HCLGE_FC_PFC;
+	}
+}
+
 static int hclge_tm_schd_info_init(struct hclge_dev *hdev)
 {
 	if ((hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE) &&
@@ -482,8 +551,7 @@ static int hclge_tm_schd_info_init(struct hclge_dev *hdev)
 
 	hclge_tm_vport_info_update(hdev);
 
-	hdev->tm_info.fc_mode = HCLGE_FC_NONE;
-	hdev->fc_mode_last_time = hdev->tm_info.fc_mode;
+	hclge_pfc_info_init(hdev);
 
 	return 0;
 }
@@ -596,17 +664,18 @@ static int hclge_tm_pri_q_qs_cfg(struct hclge_dev *hdev)
 {
 	struct hclge_vport *vport = hdev->vport;
 	int ret;
-	u32 i;
+	u32 i, k;
 
 	if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) {
 		/* Cfg qs -> pri mapping, one by one mapping */
-		for (i = 0; i < hdev->tm_info.num_tc; i++) {
-			ret = hclge_tm_qs_to_pri_map_cfg(hdev, i, i);
-			if (ret)
-				return ret;
-		}
+		for (k = 0; k < hdev->num_alloc_vport; k++)
+			for (i = 0; i < hdev->tm_info.num_tc; i++) {
+				ret = hclge_tm_qs_to_pri_map_cfg(
+					hdev, vport[k].qs_offset + i, i);
+				if (ret)
+					return ret;
+			}
 	} else if (hdev->tx_sch_mode == HCLGE_FLAG_VNET_BASE_SCH_MODE) {
-		int k;
 		/* Cfg qs -> pri mapping,  qs = tc, pri = vf, 8 qs -> 1 pri */
 		for (k = 0; k < hdev->num_alloc_vport; k++)
 			for (i = 0; i < HNAE3_MAX_TC; i++) {
@@ -696,13 +765,11 @@ static int hclge_tm_pri_vnet_base_shaper_qs_cfg(struct hclge_vport *vport)
 {
 	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
 	struct hclge_dev *hdev = vport->back;
-	struct hnae3_tc_info *v_tc_info;
 	u8 ir_u, ir_b, ir_s;
 	u32 i;
 	int ret;
 
 	for (i = 0; i < kinfo->num_tc; i++) {
-		v_tc_info = &kinfo->tc_info[i];
 		ret = hclge_shaper_para_calc(
 					hdev->tm_info.tc_info[i].bw_limit,
 					HCLGE_SHAPER_LVL_QSET,
@@ -755,10 +822,11 @@ static int hclge_tm_pri_shaper_cfg(struct hclge_dev *hdev)
 
 static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev)
 {
+	struct hclge_vport *vport = hdev->vport;
 	struct hclge_pg_info *pg_info;
 	u8 dwrr;
 	int ret;
-	u32 i;
+	u32 i, k;
 
 	for (i = 0; i < hdev->tm_info.num_tc; i++) {
 		pg_info =
@@ -769,9 +837,13 @@ static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev)
 		if (ret)
 			return ret;
 
-		ret = hclge_tm_qs_weight_cfg(hdev, i, dwrr);
-		if (ret)
-			return ret;
+		for (k = 0; k < hdev->num_alloc_vport; k++) {
+			ret = hclge_tm_qs_weight_cfg(
+				hdev, vport[k].qs_offset + i,
+				vport[k].dwrr);
+			if (ret)
+				return ret;
+		}
 	}
 
 	return 0;
@@ -835,10 +907,14 @@ static int hclge_tm_pri_dwrr_cfg(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int hclge_tm_map_cfg(struct hclge_dev *hdev)
+int hclge_tm_map_cfg(struct hclge_dev *hdev)
 {
 	int ret;
 
+	ret = hclge_up_to_tc_map(hdev);
+	if (ret)
+		return ret;
+
 	ret = hclge_tm_pg_to_pri_map(hdev);
 	if (ret)
 		return ret;
@@ -850,6 +926,10 @@ static int hclge_tm_shaper_cfg(struct hclge_dev *hdev)
 {
 	int ret;
 
+	ret = hclge_tm_port_shaper_cfg(hdev);
+	if (ret)
+		return ret;
+
 	ret = hclge_tm_pg_shaper_cfg(hdev);
 	if (ret)
 		return ret;
@@ -898,7 +978,10 @@ static int hclge_tm_schd_mode_vnet_base_cfg(struct hclge_vport *vport)
 		return ret;
 
 	for (i = 0; i < kinfo->num_tc; i++) {
-		ret = hclge_tm_qs_schd_mode_cfg(hdev, vport->qs_offset + i);
+		u8 sch_mode = hdev->tm_info.tc_info[i].tc_sch_mode;
+
+		ret = hclge_tm_qs_schd_mode_cfg(hdev, vport->qs_offset + i,
+						sch_mode);
 		if (ret)
 			return ret;
 	}
@@ -910,7 +993,7 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev)
 {
 	struct hclge_vport *vport = hdev->vport;
 	int ret;
-	u8 i;
+	u8 i, k;
 
 	if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) {
 		for (i = 0; i < hdev->tm_info.num_tc; i++) {
@@ -918,9 +1001,13 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev)
 			if (ret)
 				return ret;
 
-			ret = hclge_tm_qs_schd_mode_cfg(hdev, i);
-			if (ret)
-				return ret;
+			for (k = 0; k < hdev->num_alloc_vport; k++) {
+				ret = hclge_tm_qs_schd_mode_cfg(
+					hdev, vport[k].qs_offset + i,
+					HCLGE_SCH_MODE_DWRR);
+				if (ret)
+					return ret;
+			}
 		}
 	} else {
 		for (i = 0; i < hdev->num_alloc_vport; i++) {
@@ -935,7 +1022,7 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int hclge_tm_schd_mode_hw(struct hclge_dev *hdev)
+int hclge_tm_schd_mode_hw(struct hclge_dev *hdev)
 {
 	int ret;
 
@@ -969,27 +1056,109 @@ static int hclge_tm_schd_setup_hw(struct hclge_dev *hdev)
 	return hclge_tm_schd_mode_hw(hdev);
 }
 
+static int hclge_pfc_setup_hw(struct hclge_dev *hdev)
+{
+	u8 enable_bitmap = 0;
+
+	if (hdev->tm_info.fc_mode == HCLGE_FC_PFC)
+		enable_bitmap = HCLGE_TX_MAC_PAUSE_EN_MSK |
+				HCLGE_RX_MAC_PAUSE_EN_MSK;
+
+	return hclge_pfc_pause_en_cfg(hdev, enable_bitmap,
+				      hdev->tm_info.hw_pfc_map);
+}
+
+static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev)
+{
+	bool tx_en, rx_en;
+
+	switch (hdev->tm_info.fc_mode) {
+	case HCLGE_FC_NONE:
+		tx_en = false;
+		rx_en = false;
+		break;
+	case HCLGE_FC_RX_PAUSE:
+		tx_en = false;
+		rx_en = true;
+		break;
+	case HCLGE_FC_TX_PAUSE:
+		tx_en = true;
+		rx_en = false;
+		break;
+	case HCLGE_FC_FULL:
+		tx_en = true;
+		rx_en = true;
+		break;
+	default:
+		tx_en = true;
+		rx_en = true;
+	}
+
+	return hclge_mac_pause_en_cfg(hdev, tx_en, rx_en);
+}
+
 int hclge_pause_setup_hw(struct hclge_dev *hdev)
 {
-	bool en = hdev->tm_info.fc_mode != HCLGE_FC_PFC;
 	int ret;
 	u8 i;
 
-	ret = hclge_mac_pause_en_cfg(hdev, en, en);
-	if (ret)
-		return ret;
+	if (hdev->tm_info.fc_mode != HCLGE_FC_PFC)
+		return hclge_mac_pause_setup_hw(hdev);
 
-	/* Only DCB-supported dev supports qset back pressure setting */
+	/* Only DCB-supported dev supports qset back pressure and pfc cmd */
 	if (!hnae3_dev_dcb_supported(hdev))
 		return 0;
 
+	/* When MAC is GE Mode, hdev does not support pfc setting */
+	ret = hclge_pfc_setup_hw(hdev);
+	if (ret)
+		dev_warn(&hdev->pdev->dev, "set pfc pause failed:%d\n", ret);
+
 	for (i = 0; i < hdev->tm_info.num_tc; i++) {
 		ret = hclge_tm_qs_bp_cfg(hdev, i);
 		if (ret)
 			return ret;
 	}
 
-	return hclge_up_to_tc_map(hdev);
+	return 0;
+}
+
+int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc)
+{
+	struct hclge_vport *vport = hdev->vport;
+	struct hnae3_knic_private_info *kinfo;
+	u32 i, k;
+
+	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
+		if (prio_tc[i] >= hdev->tm_info.num_tc)
+			return -EINVAL;
+		hdev->tm_info.prio_tc[i] = prio_tc[i];
+
+		for (k = 0;  k < hdev->num_alloc_vport; k++) {
+			kinfo = &vport[k].nic.kinfo;
+			kinfo->prio_tc[i] = prio_tc[i];
+		}
+	}
+	return 0;
+}
+
+void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc)
+{
+	u8 i, bit_map = 0;
+
+	hdev->tm_info.num_tc = num_tc;
+
+	for (i = 0; i < hdev->tm_info.num_tc; i++)
+		bit_map |= BIT(i);
+
+	if (!bit_map) {
+		bit_map = 1;
+		hdev->tm_info.num_tc = 1;
+	}
+
+	hdev->hw_tc_map = bit_map;
+
+	hclge_tm_schd_info_init(hdev);
 }
 
 int hclge_tm_init_hw(struct hclge_dev *hdev)
@@ -1013,8 +1182,13 @@ int hclge_tm_init_hw(struct hclge_dev *hdev)
 
 int hclge_tm_schd_init(struct hclge_dev *hdev)
 {
-	int ret = hclge_tm_schd_info_init(hdev);
+	int ret;
+
+	/* fc_mode is HCLGE_FC_FULL on reset */
+	hdev->tm_info.fc_mode = HCLGE_FC_FULL;
+	hdev->fc_mode_last_time = hdev->tm_info.fc_mode;
 
+	ret = hclge_tm_schd_info_init(hdev);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 85158b0d73fe..bf59961918ab 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -94,6 +94,15 @@ struct hclge_bp_to_qs_map_cmd {
 	u32 rsvd1;
 };
 
+struct hclge_pfc_en_cmd {
+	u8 tx_rx_en_bitmap;
+	u8 pri_en_bitmap;
+};
+
+struct hclge_port_shapping_cmd {
+	__le32 port_shapping_para;
+};
+
 #define hclge_tm_set_field(dest, string, val) \
 			hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \
 				       (HCLGE_TM_SHAP_##string##_LSH), val)
@@ -103,4 +112,10 @@ struct hclge_bp_to_qs_map_cmd {
 
 int hclge_tm_schd_init(struct hclge_dev *hdev);
 int hclge_pause_setup_hw(struct hclge_dev *hdev);
+int hclge_tm_schd_mode_hw(struct hclge_dev *hdev);
+int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc);
+void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc);
+int hclge_tm_dwrr_cfg(struct hclge_dev *hdev);
+int hclge_tm_map_cfg(struct hclge_dev *hdev);
+int hclge_tm_init_hw(struct hclge_dev *hdev);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c
new file mode 100644
index 000000000000..925619a7c50a
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c
@@ -0,0 +1,100 @@
+/*
+ * Copyright (c) 2016-2017 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "hnae3.h"
+#include "hns3_enet.h"
+
+static
+int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets)
+{
+	struct hnae3_handle *h = hns3_get_handle(ndev);
+
+	if (h->kinfo.dcb_ops->ieee_getets)
+		return h->kinfo.dcb_ops->ieee_getets(h, ets);
+
+	return -EOPNOTSUPP;
+}
+
+static
+int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets)
+{
+	struct hnae3_handle *h = hns3_get_handle(ndev);
+
+	if (h->kinfo.dcb_ops->ieee_setets)
+		return h->kinfo.dcb_ops->ieee_setets(h, ets);
+
+	return -EOPNOTSUPP;
+}
+
+static
+int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc)
+{
+	struct hnae3_handle *h = hns3_get_handle(ndev);
+
+	if (h->kinfo.dcb_ops->ieee_getpfc)
+		return h->kinfo.dcb_ops->ieee_getpfc(h, pfc);
+
+	return -EOPNOTSUPP;
+}
+
+static
+int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc)
+{
+	struct hnae3_handle *h = hns3_get_handle(ndev);
+
+	if (h->kinfo.dcb_ops->ieee_setpfc)
+		return h->kinfo.dcb_ops->ieee_setpfc(h, pfc);
+
+	return -EOPNOTSUPP;
+}
+
+/* DCBX configuration */
+static u8 hns3_dcbnl_getdcbx(struct net_device *ndev)
+{
+	struct hnae3_handle *h = hns3_get_handle(ndev);
+
+	if (h->kinfo.dcb_ops->getdcbx)
+		return h->kinfo.dcb_ops->getdcbx(h);
+
+	return 0;
+}
+
+/* return 0 if successful, otherwise fail */
+static u8 hns3_dcbnl_setdcbx(struct net_device *ndev, u8 mode)
+{
+	struct hnae3_handle *h = hns3_get_handle(ndev);
+
+	if (h->kinfo.dcb_ops->setdcbx)
+		return h->kinfo.dcb_ops->setdcbx(h, mode);
+
+	return 1;
+}
+
+static const struct dcbnl_rtnl_ops hns3_dcbnl_ops = {
+	.ieee_getets	= hns3_dcbnl_ieee_getets,
+	.ieee_setets	= hns3_dcbnl_ieee_setets,
+	.ieee_getpfc	= hns3_dcbnl_ieee_getpfc,
+	.ieee_setpfc	= hns3_dcbnl_ieee_setpfc,
+	.getdcbx	= hns3_dcbnl_getdcbx,
+	.setdcbx	= hns3_dcbnl_setdcbx,
+};
+
+/* hclge_dcbnl_setup - DCBNL setup
+ * @handle: the corresponding vport handle
+ * Set up DCBNL
+ */
+void hns3_dcbnl_setup(struct hnae3_handle *handle)
+{
+	struct net_device *dev = handle->kinfo.netdev;
+
+	if (!handle->kinfo.dcb_ops)
+		return;
+
+	dev->dcbnl_ops = &hns3_dcbnl_ops;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
index 35369e1c8036..2a0af11c9b59 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
@@ -19,12 +19,13 @@
 #include <linux/sctp.h>
 #include <linux/vermagic.h>
 #include <net/gre.h>
+#include <net/pkt_cls.h>
 #include <net/vxlan.h>
 
 #include "hnae3.h"
 #include "hns3_enet.h"
 
-const char hns3_driver_name[] = "hns3";
+static const char hns3_driver_name[] = "hns3";
 const char hns3_driver_version[] = VERMAGIC_STRING;
 static const char hns3_driver_string[] =
 			"Hisilicon Ethernet Network Driver for Hip08 Family";
@@ -196,6 +197,31 @@ static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector)
 	tqp_vector->tx_group.flow_level = HNS3_FLOW_LOW;
 }
 
+static int hns3_nic_set_real_num_queue(struct net_device *netdev)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+	struct hnae3_knic_private_info *kinfo = &h->kinfo;
+	unsigned int queue_size = kinfo->rss_size * kinfo->num_tc;
+	int ret;
+
+	ret = netif_set_real_num_tx_queues(netdev, queue_size);
+	if (ret) {
+		netdev_err(netdev,
+			   "netif_set_real_num_tx_queues fail, ret=%d!\n",
+			   ret);
+		return ret;
+	}
+
+	ret = netif_set_real_num_rx_queues(netdev, queue_size);
+	if (ret) {
+		netdev_err(netdev,
+			   "netif_set_real_num_rx_queues fail, ret=%d!\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int hns3_nic_net_up(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -233,25 +259,13 @@ out_start_err:
 static int hns3_nic_net_open(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
 	int ret;
 
 	netif_carrier_off(netdev);
 
-	ret = netif_set_real_num_tx_queues(netdev, h->kinfo.num_tqps);
-	if (ret) {
-		netdev_err(netdev,
-			   "netif_set_real_num_tx_queues fail, ret=%d!\n",
-			   ret);
+	ret = hns3_nic_set_real_num_queue(netdev);
+	if (ret)
 		return ret;
-	}
-
-	ret = netif_set_real_num_rx_queues(netdev, h->kinfo.num_tqps);
-	if (ret) {
-		netdev_err(netdev,
-			   "netif_set_real_num_rx_queues fail, ret=%d!\n", ret);
-		return ret;
-	}
 
 	ret = hns3_nic_net_up(netdev);
 	if (ret) {
@@ -260,6 +274,7 @@ static int hns3_nic_net_open(struct net_device *netdev)
 		return ret;
 	}
 
+	priv->last_reset_time = jiffies;
 	return 0;
 }
 
@@ -292,24 +307,10 @@ static int hns3_nic_net_stop(struct net_device *netdev)
 	return 0;
 }
 
-void hns3_set_multicast_list(struct net_device *netdev)
-{
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
-	struct netdev_hw_addr *ha = NULL;
-
-	if (h->ae_algo->ops->set_mc_addr) {
-		netdev_for_each_mc_addr(ha, netdev)
-			if (h->ae_algo->ops->set_mc_addr(h, ha->addr))
-				netdev_err(netdev, "set multicast fail\n");
-	}
-}
-
 static int hns3_nic_uc_sync(struct net_device *netdev,
 			    const unsigned char *addr)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (h->ae_algo->ops->add_uc_addr)
 		return h->ae_algo->ops->add_uc_addr(h, addr);
@@ -320,8 +321,7 @@ static int hns3_nic_uc_sync(struct net_device *netdev,
 static int hns3_nic_uc_unsync(struct net_device *netdev,
 			      const unsigned char *addr)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (h->ae_algo->ops->rm_uc_addr)
 		return h->ae_algo->ops->rm_uc_addr(h, addr);
@@ -332,8 +332,7 @@ static int hns3_nic_uc_unsync(struct net_device *netdev,
 static int hns3_nic_mc_sync(struct net_device *netdev,
 			    const unsigned char *addr)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (h->ae_algo->ops->add_mc_addr)
 		return h->ae_algo->ops->add_mc_addr(h, addr);
@@ -344,8 +343,7 @@ static int hns3_nic_mc_sync(struct net_device *netdev,
 static int hns3_nic_mc_unsync(struct net_device *netdev,
 			      const unsigned char *addr)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (h->ae_algo->ops->rm_mc_addr)
 		return h->ae_algo->ops->rm_mc_addr(h, addr);
@@ -353,10 +351,9 @@ static int hns3_nic_mc_unsync(struct net_device *netdev,
 	return 0;
 }
 
-void hns3_nic_set_rx_mode(struct net_device *netdev)
+static void hns3_nic_set_rx_mode(struct net_device *netdev)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (h->ae_algo->ops->set_promisc_mode) {
 		if (netdev->flags & IFF_PROMISC)
@@ -721,7 +718,7 @@ static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end)
 		       HNS3_TXD_BDTYPE_M, 0);
 	hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end);
 	hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1);
-	hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 1);
+	hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 0);
 }
 
 static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
@@ -755,7 +752,7 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 
 	if (type == DESC_TYPE_SKB) {
 		skb = (struct sk_buff *)priv;
-		paylen = cpu_to_le16(skb->len);
+		paylen = skb->len;
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
 			skb_reset_mac_len(skb);
@@ -789,7 +786,7 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 			cpu_to_le32(ol_type_vlan_len_msec);
 		desc->tx.type_cs_vlan_tso_len =
 			cpu_to_le32(type_cs_vlan_tso);
-		desc->tx.paylen = cpu_to_le16(paylen);
+		desc->tx.paylen = cpu_to_le32(paylen);
 		desc->tx.mss = cpu_to_le16(mss);
 	}
 
@@ -905,8 +902,7 @@ static void hns_nic_dma_unmap(struct hns3_enet_ring *ring, int next_to_use_orig)
 	}
 }
 
-static netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb,
-				     struct net_device *netdev)
+netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hns3_nic_ring_data *ring_data =
@@ -1012,8 +1008,7 @@ out_net_tx_busy:
 
 static int hns3_nic_net_set_mac_address(struct net_device *netdev, void *p)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 	struct sockaddr *mac_addr = p;
 	int ret;
 
@@ -1193,61 +1188,80 @@ static void hns3_nic_udp_tunnel_del(struct net_device *netdev,
 	}
 }
 
-static int hns3_setup_tc(struct net_device *netdev, u8 tc)
+static int hns3_setup_tc(struct net_device *netdev, void *type_data)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct tc_mqprio_qopt_offload *mqprio_qopt = type_data;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 	struct hnae3_knic_private_info *kinfo = &h->kinfo;
+	u8 *prio_tc = mqprio_qopt->qopt.prio_tc_map;
+	u8 tc = mqprio_qopt->qopt.num_tc;
+	u16 mode = mqprio_qopt->mode;
+	u8 hw = mqprio_qopt->qopt.hw;
+	bool if_running;
 	unsigned int i;
 	int ret;
 
+	if (!((hw == TC_MQPRIO_HW_OFFLOAD_TCS &&
+	       mode == TC_MQPRIO_MODE_CHANNEL) || (!hw && tc == 0)))
+		return -EOPNOTSUPP;
+
 	if (tc > HNAE3_MAX_TC)
 		return -EINVAL;
 
-	if (kinfo->num_tc == tc)
-		return 0;
-
 	if (!netdev)
 		return -EINVAL;
 
-	if (!tc) {
-		netdev_reset_tc(netdev);
-		return 0;
+	if_running = netif_running(netdev);
+	if (if_running) {
+		hns3_nic_net_stop(netdev);
+		msleep(100);
 	}
 
-	/* Set num_tc for netdev */
-	ret = netdev_set_num_tc(netdev, tc);
+	ret = (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ?
+		kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP;
 	if (ret)
-		return ret;
+		goto out;
+
+	if (tc <= 1) {
+		netdev_reset_tc(netdev);
+	} else {
+		ret = netdev_set_num_tc(netdev, tc);
+		if (ret)
+			goto out;
+
+		for (i = 0; i < HNAE3_MAX_TC; i++) {
+			if (!kinfo->tc_info[i].enable)
+				continue;
 
-	/* Set per TC queues for the VSI */
-	for (i = 0; i < HNAE3_MAX_TC; i++) {
-		if (kinfo->tc_info[i].enable)
 			netdev_set_tc_queue(netdev,
 					    kinfo->tc_info[i].tc,
 					    kinfo->tc_info[i].tqp_count,
 					    kinfo->tc_info[i].tqp_offset);
+		}
 	}
 
-	return 0;
+	ret = hns3_nic_set_real_num_queue(netdev);
+
+out:
+	if (if_running)
+		hns3_nic_net_open(netdev);
+
+	return ret;
 }
 
 static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			     void *type_data)
 {
-	struct tc_mqprio_qopt *mqprio = type_data;
-
 	if (type != TC_SETUP_MQPRIO)
 		return -EOPNOTSUPP;
 
-	return hns3_setup_tc(dev, mqprio->num_tc);
+	return hns3_setup_tc(dev, type_data);
 }
 
 static int hns3_vlan_rx_add_vid(struct net_device *netdev,
 				__be16 proto, u16 vid)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 	int ret = -EIO;
 
 	if (h->ae_algo->ops->set_vlan_filter)
@@ -1259,8 +1273,7 @@ static int hns3_vlan_rx_add_vid(struct net_device *netdev,
 static int hns3_vlan_rx_kill_vid(struct net_device *netdev,
 				 __be16 proto, u16 vid)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 	int ret = -EIO;
 
 	if (h->ae_algo->ops->set_vlan_filter)
@@ -1272,8 +1285,7 @@ static int hns3_vlan_rx_kill_vid(struct net_device *netdev,
 static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan,
 				u8 qos, __be16 vlan_proto)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 	int ret = -EIO;
 
 	if (h->ae_algo->ops->set_vf_vlan_filter)
@@ -1285,8 +1297,7 @@ static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan,
 
 static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 	bool if_running = netif_running(netdev);
 	int ret;
 
@@ -1313,10 +1324,91 @@ static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu)
 	return ret;
 }
 
+static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct hns3_enet_ring *tx_ring = NULL;
+	int timeout_queue = 0;
+	int hw_head, hw_tail;
+	int i;
+
+	/* Find the stopped queue the same way the stack does */
+	for (i = 0; i < ndev->real_num_tx_queues; i++) {
+		struct netdev_queue *q;
+		unsigned long trans_start;
+
+		q = netdev_get_tx_queue(ndev, i);
+		trans_start = q->trans_start;
+		if (netif_xmit_stopped(q) &&
+		    time_after(jiffies,
+			       (trans_start + ndev->watchdog_timeo))) {
+			timeout_queue = i;
+			break;
+		}
+	}
+
+	if (i == ndev->num_tx_queues) {
+		netdev_info(ndev,
+			    "no netdev TX timeout queue found, timeout count: %llu\n",
+			    priv->tx_timeout_count);
+		return false;
+	}
+
+	tx_ring = priv->ring_data[timeout_queue].ring;
+
+	hw_head = readl_relaxed(tx_ring->tqp->io_base +
+				HNS3_RING_TX_RING_HEAD_REG);
+	hw_tail = readl_relaxed(tx_ring->tqp->io_base +
+				HNS3_RING_TX_RING_TAIL_REG);
+	netdev_info(ndev,
+		    "tx_timeout count: %llu, queue id: %d, SW_NTU: 0x%x, SW_NTC: 0x%x, HW_HEAD: 0x%x, HW_TAIL: 0x%x, INT: 0x%x\n",
+		    priv->tx_timeout_count,
+		    timeout_queue,
+		    tx_ring->next_to_use,
+		    tx_ring->next_to_clean,
+		    hw_head,
+		    hw_tail,
+		    readl(tx_ring->tqp_vector->mask_addr));
+
+	return true;
+}
+
+static void hns3_nic_net_timeout(struct net_device *ndev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	unsigned long last_reset_time = priv->last_reset_time;
+	struct hnae3_handle *h = priv->ae_handle;
+
+	if (!hns3_get_tx_timeo_queue_info(ndev))
+		return;
+
+	priv->tx_timeout_count++;
+
+	/* This timeout is far away enough from last timeout,
+	 * if timeout again,set the reset type to PF reset
+	 */
+	if (time_after(jiffies, (last_reset_time + 20 * HZ)))
+		priv->reset_level = HNAE3_FUNC_RESET;
+
+	/* Don't do any new action before the next timeout */
+	else if (time_before(jiffies, (last_reset_time + ndev->watchdog_timeo)))
+		return;
+
+	priv->last_reset_time = jiffies;
+
+	if (h->ae_algo->ops->reset_event)
+		h->ae_algo->ops->reset_event(h, priv->reset_level);
+
+	priv->reset_level++;
+	if (priv->reset_level > HNAE3_GLOBAL_RESET)
+		priv->reset_level = HNAE3_GLOBAL_RESET;
+}
+
 static const struct net_device_ops hns3_nic_netdev_ops = {
 	.ndo_open		= hns3_nic_net_open,
 	.ndo_stop		= hns3_nic_net_stop,
 	.ndo_start_xmit		= hns3_nic_net_xmit,
+	.ndo_tx_timeout		= hns3_nic_net_timeout,
 	.ndo_set_mac_address	= hns3_nic_net_set_mac_address,
 	.ndo_change_mtu		= hns3_nic_change_mtu,
 	.ndo_set_features	= hns3_nic_set_features,
@@ -1435,8 +1527,6 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
 	cb->length = hnae_page_size(ring);
 	cb->type = DESC_TYPE_PAGE;
 
-	memset(cb->buf, 0, cb->length);
-
 	return 0;
 }
 
@@ -1546,7 +1636,7 @@ static int hns3_reserve_buffer_map(struct hns3_enet_ring *ring,
 	return 0;
 
 out_with_buf:
-	hns3_free_buffers(ring);
+	hns3_free_buffer(ring, cb);
 out:
 	return ret;
 }
@@ -1586,7 +1676,7 @@ out_buffer_fail:
 static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i,
 				struct hns3_desc_cb *res_cb)
 {
-	hns3_map_buffer(ring, &ring->desc_cb[i]);
+	hns3_unmap_buffer(ring, &ring->desc_cb[i]);
 	ring->desc_cb[i] = *res_cb;
 	ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma);
 }
@@ -1622,7 +1712,7 @@ static int is_valid_clean_head(struct hns3_enet_ring *ring, int h)
 	return u > c ? (h > c && h <= u) : (h > c || h <= u);
 }
 
-int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget)
+bool hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget)
 {
 	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
 	struct netdev_queue *dev_queue;
@@ -1633,7 +1723,7 @@ int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget)
 	rmb(); /* Make sure head is ready before touch any data */
 
 	if (is_ring_empty(ring) || head == ring->next_to_clean)
-		return 0; /* no data to poll */
+		return true; /* no data to poll */
 
 	if (!is_valid_clean_head(ring, head)) {
 		netdev_err(netdev, "wrong head (%d, %d-%d)\n", head,
@@ -1642,7 +1732,7 @@ int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget)
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.io_err_cnt++;
 		u64_stats_update_end(&ring->syncp);
-		return -EIO;
+		return true;
 	}
 
 	bytes = 0;
@@ -1933,6 +2023,11 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 	}
 }
 
+static void hns3_rx_skb(struct hns3_enet_ring *ring, struct sk_buff *skb)
+{
+	napi_gro_receive(&ring->tqp_vector->napi, skb);
+}
+
 static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 			     struct sk_buff **out_skb, int *out_bnum)
 {
@@ -2067,7 +2162,9 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	return 0;
 }
 
-static int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget)
+int hns3_clean_rx_ring(
+		struct hns3_enet_ring *ring, int budget,
+		void (*rx_fn)(struct hns3_enet_ring *, struct sk_buff *))
 {
 #define RCB_NOF_ALLOC_RX_BUFF_ONCE 16
 	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
@@ -2105,7 +2202,7 @@ static int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget)
 
 		/* Do update ip stack process */
 		skb->protocol = eth_type_trans(skb, netdev);
-		(void)napi_gro_receive(&ring->tqp_vector->napi, skb);
+		rx_fn(ring, skb);
 
 		recv_pkts++;
 	}
@@ -2248,7 +2345,8 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 	rx_budget = max(budget / tqp_vector->num_tqps, 1);
 
 	hns3_for_each_ring(ring, tqp_vector->rx_group) {
-		int rx_cleaned = hns3_clean_rx_ring(ring, rx_budget);
+		int rx_cleaned = hns3_clean_rx_ring(ring, rx_budget,
+						    hns3_rx_skb);
 
 		if (rx_cleaned >= rx_budget)
 			clean_complete = false;
@@ -2460,9 +2558,8 @@ static int hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv)
 			(void)irq_set_affinity_hint(
 				priv->tqp_vector[i].vector_irq,
 						    NULL);
-			devm_free_irq(&pdev->dev,
-				      priv->tqp_vector[i].vector_irq,
-				      &priv->tqp_vector[i]);
+			free_irq(priv->tqp_vector[i].vector_irq,
+				 &priv->tqp_vector[i]);
 		}
 
 		priv->ring_data[i].ring->irq_init_flag = HNS3_VECTOR_NOT_INITED;
@@ -2489,16 +2586,16 @@ static int hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 
 	if (ring_type == HNAE3_RING_TYPE_TX) {
 		ring_data[q->tqp_index].ring = ring;
+		ring_data[q->tqp_index].queue_index = q->tqp_index;
 		ring->io_base = (u8 __iomem *)q->io_base + HNS3_TX_REG_OFFSET;
 	} else {
 		ring_data[q->tqp_index + queue_num].ring = ring;
+		ring_data[q->tqp_index + queue_num].queue_index = q->tqp_index;
 		ring->io_base = q->io_base;
 	}
 
 	hnae_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type);
 
-	ring_data[q->tqp_index].queue_index = q->tqp_index;
-
 	ring->tqp = q;
 	ring->desc = NULL;
 	ring->desc_cb = NULL;
@@ -2596,7 +2693,7 @@ static void hns3_fini_ring(struct hns3_enet_ring *ring)
 	ring->next_to_use = 0;
 }
 
-int hns3_buf_size2type(u32 buf_size)
+static int hns3_buf_size2type(u32 buf_size)
 {
 	int bd_size_type;
 
@@ -2649,7 +2746,7 @@ static void hns3_init_ring_hw(struct hns3_enet_ring *ring)
 	}
 }
 
-static int hns3_init_all_ring(struct hns3_nic_priv *priv)
+int hns3_init_all_ring(struct hns3_nic_priv *priv)
 {
 	struct hnae3_handle *h = priv->ae_handle;
 	int ring_num = h->kinfo.num_tqps * 2;
@@ -2673,12 +2770,12 @@ static int hns3_init_all_ring(struct hns3_nic_priv *priv)
 
 out_when_alloc_ring_memory:
 	for (j = i - 1; j >= 0; j--)
-		hns3_fini_ring(priv->ring_data[i].ring);
+		hns3_fini_ring(priv->ring_data[j].ring);
 
 	return -ENOMEM;
 }
 
-static int hns3_uninit_all_ring(struct hns3_nic_priv *priv)
+int hns3_uninit_all_ring(struct hns3_nic_priv *priv)
 {
 	struct hnae3_handle *h = priv->ae_handle;
 	int i;
@@ -2748,6 +2845,9 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	priv->dev = &pdev->dev;
 	priv->netdev = netdev;
 	priv->ae_handle = handle;
+	priv->last_reset_time = jiffies;
+	priv->reset_level = HNAE3_FUNC_RESET;
+	priv->tx_timeout_count = 0;
 
 	handle->kinfo.netdev = netdev;
 	handle->priv = (void *)priv;
@@ -2790,6 +2890,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
 		goto out_reg_netdev_fail;
 	}
 
+	hns3_dcbnl_setup(handle);
+
 	/* MTU range: (ETH_MIN_MTU(kernel default) - 9706) */
 	netdev->max_mtu = HNS3_MAX_MTU - (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN);
 
@@ -2846,10 +2948,224 @@ static void hns3_link_status_change(struct hnae3_handle *handle, bool linkup)
 	}
 }
 
-const struct hnae3_client_ops client_ops = {
+static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
+{
+	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+	struct net_device *ndev = kinfo->netdev;
+	bool if_running;
+	int ret;
+	u8 i;
+
+	if (tc > HNAE3_MAX_TC)
+		return -EINVAL;
+
+	if (!ndev)
+		return -ENODEV;
+
+	if_running = netif_running(ndev);
+
+	ret = netdev_set_num_tc(ndev, tc);
+	if (ret)
+		return ret;
+
+	if (if_running) {
+		(void)hns3_nic_net_stop(ndev);
+		msleep(100);
+	}
+
+	ret = (kinfo->dcb_ops && kinfo->dcb_ops->map_update) ?
+		kinfo->dcb_ops->map_update(handle) : -EOPNOTSUPP;
+	if (ret)
+		goto err_out;
+
+	if (tc <= 1) {
+		netdev_reset_tc(ndev);
+		goto out;
+	}
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		struct hnae3_tc_info *tc_info = &kinfo->tc_info[i];
+
+		if (tc_info->enable)
+			netdev_set_tc_queue(ndev,
+					    tc_info->tc,
+					    tc_info->tqp_count,
+					    tc_info->tqp_offset);
+	}
+
+	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
+		netdev_set_prio_tc_map(ndev, i,
+				       kinfo->prio_tc[i]);
+	}
+
+out:
+	ret = hns3_nic_set_real_num_queue(ndev);
+
+err_out:
+	if (if_running)
+		(void)hns3_nic_net_open(ndev);
+
+	return ret;
+}
+
+static void hns3_recover_hw_addr(struct net_device *ndev)
+{
+	struct netdev_hw_addr_list *list;
+	struct netdev_hw_addr *ha, *tmp;
+
+	/* go through and sync uc_addr entries to the device */
+	list = &ndev->uc;
+	list_for_each_entry_safe(ha, tmp, &list->list, list)
+		hns3_nic_uc_sync(ndev, ha->addr);
+
+	/* go through and sync mc_addr entries to the device */
+	list = &ndev->mc;
+	list_for_each_entry_safe(ha, tmp, &list->list, list)
+		hns3_nic_mc_sync(ndev, ha->addr);
+}
+
+static void hns3_drop_skb_data(struct hns3_enet_ring *ring, struct sk_buff *skb)
+{
+	dev_kfree_skb_any(skb);
+}
+
+static void hns3_clear_all_ring(struct hnae3_handle *h)
+{
+	struct net_device *ndev = h->kinfo.netdev;
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	u32 i;
+
+	for (i = 0; i < h->kinfo.num_tqps; i++) {
+		struct netdev_queue *dev_queue;
+		struct hns3_enet_ring *ring;
+
+		ring = priv->ring_data[i].ring;
+		hns3_clean_tx_ring(ring, ring->desc_num);
+		dev_queue = netdev_get_tx_queue(ndev,
+						priv->ring_data[i].queue_index);
+		netdev_tx_reset_queue(dev_queue);
+
+		ring = priv->ring_data[i + h->kinfo.num_tqps].ring;
+		hns3_clean_rx_ring(ring, ring->desc_num, hns3_drop_skb_data);
+	}
+}
+
+static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
+{
+	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+	struct net_device *ndev = kinfo->netdev;
+
+	if (!netif_running(ndev))
+		return -EIO;
+
+	return hns3_nic_net_stop(ndev);
+}
+
+static int hns3_reset_notify_up_enet(struct hnae3_handle *handle)
+{
+	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+	struct hns3_nic_priv *priv = netdev_priv(kinfo->netdev);
+	int ret = 0;
+
+	if (netif_running(kinfo->netdev)) {
+		ret = hns3_nic_net_up(kinfo->netdev);
+		if (ret) {
+			netdev_err(kinfo->netdev,
+				   "hns net up fail, ret=%d!\n", ret);
+			return ret;
+		}
+
+		priv->last_reset_time = jiffies;
+	}
+
+	return ret;
+}
+
+static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
+{
+	struct net_device *netdev = handle->kinfo.netdev;
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	int ret;
+
+	priv->reset_level = 1;
+	hns3_init_mac_addr(netdev);
+	hns3_nic_set_rx_mode(netdev);
+	hns3_recover_hw_addr(netdev);
+
+	/* Carrier off reporting is important to ethtool even BEFORE open */
+	netif_carrier_off(netdev);
+
+	ret = hns3_get_ring_config(priv);
+	if (ret)
+		return ret;
+
+	ret = hns3_nic_init_vector_data(priv);
+	if (ret)
+		return ret;
+
+	ret = hns3_init_all_ring(priv);
+	if (ret) {
+		hns3_nic_uninit_vector_data(priv);
+		priv->ring_data = NULL;
+	}
+
+	return ret;
+}
+
+static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
+{
+	struct net_device *netdev = handle->kinfo.netdev;
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	int ret;
+
+	hns3_clear_all_ring(handle);
+
+	ret = hns3_nic_uninit_vector_data(priv);
+	if (ret) {
+		netdev_err(netdev, "uninit vector error\n");
+		return ret;
+	}
+
+	ret = hns3_uninit_all_ring(priv);
+	if (ret)
+		netdev_err(netdev, "uninit ring error\n");
+
+	priv->ring_data = NULL;
+
+	return ret;
+}
+
+static int hns3_reset_notify(struct hnae3_handle *handle,
+			     enum hnae3_reset_notify_type type)
+{
+	int ret = 0;
+
+	switch (type) {
+	case HNAE3_UP_CLIENT:
+                ret = hns3_reset_notify_up_enet(handle);
+                break;
+	case HNAE3_DOWN_CLIENT:
+		ret = hns3_reset_notify_down_enet(handle);
+		break;
+	case HNAE3_INIT_CLIENT:
+		ret = hns3_reset_notify_init_enet(handle);
+		break;
+	case HNAE3_UNINIT_CLIENT:
+		ret = hns3_reset_notify_uninit_enet(handle);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static const struct hnae3_client_ops client_ops = {
 	.init_instance = hns3_client_init,
 	.uninit_instance = hns3_client_uninit,
 	.link_status_change = hns3_link_status_change,
+	.setup_tc = hns3_client_setup_tc,
+	.reset_notify = hns3_reset_notify,
 };
 
 /* hns3_init_module - Driver registration routine
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h
index 7e8746189747..8a9de759957b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h
@@ -76,6 +76,8 @@ enum hns3_nic_state {
 #define HNS3_RING_NAME_LEN			16
 #define HNS3_BUFFER_SIZE_2048			2048
 #define HNS3_RING_MAX_PENDING			32768
+#define HNS3_RING_MIN_PENDING			8
+#define HNS3_RING_BD_MULTIPLE			8
 #define HNS3_MAX_MTU				9728
 
 #define HNS3_BD_SIZE_512_TYPE			0
@@ -516,6 +518,8 @@ struct hns3_nic_priv {
 	/* The most recently read link state */
 	int link;
 	u64 tx_timeout_count;
+	enum hnae3_reset_type reset_level;
+	unsigned long last_reset_time;
 
 	unsigned long state;
 
@@ -587,7 +591,23 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 #define hns3_for_each_ring(pos, head) \
 	for (pos = (head).ring; pos; pos = pos->next)
 
+#define hns3_get_handle(ndev) \
+	(((struct hns3_nic_priv *)netdev_priv(ndev))->ae_handle)
+
 void hns3_ethtool_set_ops(struct net_device *netdev);
 
-int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget);
+bool hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget);
+int hns3_init_all_ring(struct hns3_nic_priv *priv);
+int hns3_uninit_all_ring(struct hns3_nic_priv *priv);
+netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev);
+int hns3_clean_rx_ring(
+		struct hns3_enet_ring *ring, int budget,
+		void (*rx_fn)(struct hns3_enet_ring *, struct sk_buff *));
+
+#ifdef CONFIG_HNS3_DCB
+void hns3_dcbnl_setup(struct hnae3_handle *handle);
+#else
+static inline void hns3_dcbnl_setup(struct hnae3_handle *handle) {}
+#endif
+
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c
index d636399232fb..a21470c72da3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c
@@ -9,6 +9,7 @@
 
 #include <linux/etherdevice.h>
 #include <linux/string.h>
+#include <linux/phy.h>
 
 #include "hns3_enet.h"
 
@@ -59,6 +60,16 @@ static const struct hns3_stats hns3_rxq_stats[] = {
 
 #define HNS3_TQP_STATS_COUNT (HNS3_TXQ_STATS_COUNT + HNS3_RXQ_STATS_COUNT)
 
+#define HNS3_SELF_TEST_TPYE_NUM		1
+#define HNS3_NIC_LB_TEST_PKT_NUM	1
+#define HNS3_NIC_LB_TEST_RING_ID	0
+#define HNS3_NIC_LB_TEST_PACKET_SIZE	128
+
+/* Nic loopback test err  */
+#define HNS3_NIC_LB_TEST_NO_MEM_ERR	1
+#define HNS3_NIC_LB_TEST_TX_CNT_ERR	2
+#define HNS3_NIC_LB_TEST_RX_CNT_ERR	3
+
 struct hns3_link_mode_mapping {
 	u32 hns3_link_mode;
 	u32 ethtool_link_mode;
@@ -77,6 +88,268 @@ static const struct hns3_link_mode_mapping hns3_lm_map[] = {
 	{HNS3_LM_1000BASET_FULL_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT},
 };
 
+static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop)
+{
+	struct hnae3_handle *h = hns3_get_handle(ndev);
+	int ret;
+
+	if (!h->ae_algo->ops->set_loopback ||
+	    !h->ae_algo->ops->set_promisc_mode)
+		return -EOPNOTSUPP;
+
+	switch (loop) {
+	case HNAE3_MAC_INTER_LOOP_MAC:
+		ret = h->ae_algo->ops->set_loopback(h, loop, true);
+		break;
+	case HNAE3_MAC_LOOP_NONE:
+		ret = h->ae_algo->ops->set_loopback(h,
+			HNAE3_MAC_INTER_LOOP_MAC, false);
+		break;
+	default:
+		ret = -ENOTSUPP;
+		break;
+	}
+
+	if (ret)
+		return ret;
+
+	if (loop == HNAE3_MAC_LOOP_NONE)
+		h->ae_algo->ops->set_promisc_mode(h, ndev->flags & IFF_PROMISC);
+	else
+		h->ae_algo->ops->set_promisc_mode(h, 1);
+
+	return ret;
+}
+
+static int hns3_lp_up(struct net_device *ndev, enum hnae3_loop loop_mode)
+{
+	struct hnae3_handle *h = hns3_get_handle(ndev);
+	int ret;
+
+	if (!h->ae_algo->ops->start)
+		return -EOPNOTSUPP;
+
+	ret = h->ae_algo->ops->start(h);
+	if (ret) {
+		netdev_err(ndev,
+			   "hns3_lb_up ae start return error: %d\n", ret);
+		return ret;
+	}
+
+	ret = hns3_lp_setup(ndev, loop_mode);
+	usleep_range(10000, 20000);
+
+	return ret;
+}
+
+static int hns3_lp_down(struct net_device *ndev)
+{
+	struct hnae3_handle *h = hns3_get_handle(ndev);
+	int ret;
+
+	if (!h->ae_algo->ops->stop)
+		return -EOPNOTSUPP;
+
+	ret = hns3_lp_setup(ndev, HNAE3_MAC_LOOP_NONE);
+	if (ret) {
+		netdev_err(ndev, "lb_setup return error: %d\n", ret);
+		return ret;
+	}
+
+	h->ae_algo->ops->stop(h);
+	usleep_range(10000, 20000);
+
+	return 0;
+}
+
+static void hns3_lp_setup_skb(struct sk_buff *skb)
+{
+	struct net_device *ndev = skb->dev;
+	unsigned char *packet;
+	struct ethhdr *ethh;
+	unsigned int i;
+
+	skb_reserve(skb, NET_IP_ALIGN);
+	ethh = skb_put(skb, sizeof(struct ethhdr));
+	packet = skb_put(skb, HNS3_NIC_LB_TEST_PACKET_SIZE);
+
+	memcpy(ethh->h_dest, ndev->dev_addr, ETH_ALEN);
+	eth_zero_addr(ethh->h_source);
+	ethh->h_proto = htons(ETH_P_ARP);
+	skb_reset_mac_header(skb);
+
+	for (i = 0; i < HNS3_NIC_LB_TEST_PACKET_SIZE; i++)
+		packet[i] = (unsigned char)(i & 0xff);
+}
+
+static void hns3_lb_check_skb_data(struct hns3_enet_ring *ring,
+				   struct sk_buff *skb)
+{
+	struct hns3_enet_tqp_vector *tqp_vector = ring->tqp_vector;
+	unsigned char *packet = skb->data;
+	u32 i;
+
+	for (i = 0; i < skb->len; i++)
+		if (packet[i] != (unsigned char)(i & 0xff))
+			break;
+
+	/* The packet is correctly received */
+	if (i == skb->len)
+		tqp_vector->rx_group.total_packets++;
+	else
+		print_hex_dump(KERN_ERR, "selftest:", DUMP_PREFIX_OFFSET, 16, 1,
+			       skb->data, skb->len, true);
+
+	dev_kfree_skb_any(skb);
+}
+
+static u32 hns3_lb_check_rx_ring(struct hns3_nic_priv *priv, u32 budget)
+{
+	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_knic_private_info *kinfo;
+	u32 i, rcv_good_pkt_total = 0;
+
+	kinfo = &h->kinfo;
+	for (i = kinfo->num_tqps; i < kinfo->num_tqps * 2; i++) {
+		struct hns3_enet_ring *ring = priv->ring_data[i].ring;
+		struct hns3_enet_ring_group *rx_group;
+		u64 pre_rx_pkt;
+
+		rx_group = &ring->tqp_vector->rx_group;
+		pre_rx_pkt = rx_group->total_packets;
+
+		hns3_clean_rx_ring(ring, budget, hns3_lb_check_skb_data);
+
+		rcv_good_pkt_total += (rx_group->total_packets - pre_rx_pkt);
+		rx_group->total_packets = pre_rx_pkt;
+	}
+	return rcv_good_pkt_total;
+}
+
+static void hns3_lb_clear_tx_ring(struct hns3_nic_priv *priv, u32 start_ringid,
+				  u32 end_ringid, u32 budget)
+{
+	u32 i;
+
+	for (i = start_ringid; i <= end_ringid; i++) {
+		struct hns3_enet_ring *ring = priv->ring_data[i].ring;
+
+		hns3_clean_tx_ring(ring, budget);
+	}
+}
+
+/**
+ * hns3_lp_run_test -  run loopback test
+ * @ndev: net device
+ * @mode: loopback type
+ */
+static int hns3_lp_run_test(struct net_device *ndev, enum hnae3_loop mode)
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct sk_buff *skb;
+	u32 i, good_cnt;
+	int ret_val = 0;
+
+	skb = alloc_skb(HNS3_NIC_LB_TEST_PACKET_SIZE + ETH_HLEN + NET_IP_ALIGN,
+			GFP_KERNEL);
+	if (!skb)
+		return HNS3_NIC_LB_TEST_NO_MEM_ERR;
+
+	skb->dev = ndev;
+	hns3_lp_setup_skb(skb);
+	skb->queue_mapping = HNS3_NIC_LB_TEST_RING_ID;
+
+	good_cnt = 0;
+	for (i = 0; i < HNS3_NIC_LB_TEST_PKT_NUM; i++) {
+		netdev_tx_t tx_ret;
+
+		skb_get(skb);
+		tx_ret = hns3_nic_net_xmit(skb, ndev);
+		if (tx_ret == NETDEV_TX_OK)
+			good_cnt++;
+		else
+			netdev_err(ndev, "hns3_lb_run_test xmit failed: %d\n",
+				   tx_ret);
+	}
+	if (good_cnt != HNS3_NIC_LB_TEST_PKT_NUM) {
+		ret_val = HNS3_NIC_LB_TEST_TX_CNT_ERR;
+		netdev_err(ndev, "mode %d sent fail, cnt=0x%x, budget=0x%x\n",
+			   mode, good_cnt, HNS3_NIC_LB_TEST_PKT_NUM);
+		goto out;
+	}
+
+	/* Allow 200 milliseconds for packets to go from Tx to Rx */
+	msleep(200);
+
+	good_cnt = hns3_lb_check_rx_ring(priv, HNS3_NIC_LB_TEST_PKT_NUM);
+	if (good_cnt != HNS3_NIC_LB_TEST_PKT_NUM) {
+		ret_val = HNS3_NIC_LB_TEST_RX_CNT_ERR;
+		netdev_err(ndev, "mode %d recv fail, cnt=0x%x, budget=0x%x\n",
+			   mode, good_cnt, HNS3_NIC_LB_TEST_PKT_NUM);
+	}
+
+out:
+	hns3_lb_clear_tx_ring(priv, HNS3_NIC_LB_TEST_RING_ID,
+			      HNS3_NIC_LB_TEST_RING_ID,
+			      HNS3_NIC_LB_TEST_PKT_NUM);
+
+	kfree_skb(skb);
+	return ret_val;
+}
+
+/**
+ * hns3_nic_self_test - self test
+ * @ndev: net device
+ * @eth_test: test cmd
+ * @data: test result
+ */
+static void hns3_self_test(struct net_device *ndev,
+			   struct ethtool_test *eth_test, u64 *data)
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct hnae3_handle *h = priv->ae_handle;
+	int st_param[HNS3_SELF_TEST_TPYE_NUM][2];
+	bool if_running = netif_running(ndev);
+	int test_index = 0;
+	u32 i;
+
+	/* Only do offline selftest, or pass by default */
+	if (eth_test->flags != ETH_TEST_FL_OFFLINE)
+		return;
+
+	st_param[HNAE3_MAC_INTER_LOOP_MAC][0] = HNAE3_MAC_INTER_LOOP_MAC;
+	st_param[HNAE3_MAC_INTER_LOOP_MAC][1] =
+			h->flags & HNAE3_SUPPORT_MAC_LOOPBACK;
+
+	if (if_running)
+		dev_close(ndev);
+
+	set_bit(HNS3_NIC_STATE_TESTING, &priv->state);
+
+	for (i = 0; i < HNS3_SELF_TEST_TPYE_NUM; i++) {
+		enum hnae3_loop loop_type = (enum hnae3_loop)st_param[i][0];
+
+		if (!st_param[i][1])
+			continue;
+
+		data[test_index] = hns3_lp_up(ndev, loop_type);
+		if (!data[test_index]) {
+			data[test_index] = hns3_lp_run_test(ndev, loop_type);
+			hns3_lp_down(ndev);
+		}
+
+		if (data[test_index])
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+
+		test_index++;
+	}
+
+	clear_bit(HNS3_NIC_STATE_TESTING, &priv->state);
+
+	if (if_running)
+		dev_open(ndev);
+}
+
 static void hns3_driv_to_eth_caps(u32 caps, struct ethtool_link_ksettings *cmd,
 				  bool is_advertised)
 {
@@ -86,24 +359,18 @@ static void hns3_driv_to_eth_caps(u32 caps, struct ethtool_link_ksettings *cmd,
 		if (!(caps & hns3_lm_map[i].hns3_link_mode))
 			continue;
 
-		if (is_advertised) {
-			ethtool_link_ksettings_zero_link_mode(cmd,
-							      advertising);
+		if (is_advertised)
 			__set_bit(hns3_lm_map[i].ethtool_link_mode,
 				  cmd->link_modes.advertising);
-		} else {
-			ethtool_link_ksettings_zero_link_mode(cmd,
-							      supported);
+		else
 			__set_bit(hns3_lm_map[i].ethtool_link_mode,
 				  cmd->link_modes.supported);
-		}
 	}
 }
 
 static int hns3_get_sset_count(struct net_device *netdev, int stringset)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 	const struct hnae3_ae_ops *ops = h->ae_algo->ops;
 
 	if (!ops->get_sset_count)
@@ -164,8 +431,7 @@ static u8 *hns3_get_strings_tqps(struct hnae3_handle *handle, u8 *data)
 
 static void hns3_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 	const struct hnae3_ae_ops *ops = h->ae_algo->ops;
 	char *buff = (char *)data;
 
@@ -217,11 +483,10 @@ static u64 *hns3_get_stats_tqps(struct hnae3_handle *handle, u64 *data)
  * @stats: statistics info.
  * @data: statistics data.
  */
-void hns3_get_stats(struct net_device *netdev, struct ethtool_stats *stats,
-		    u64 *data)
+static void hns3_get_stats(struct net_device *netdev,
+			   struct ethtool_stats *stats, u64 *data)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 	u64 *p = data;
 
 	if (!h->ae_algo->ops->get_stats || !h->ae_algo->ops->update_stats) {
@@ -262,10 +527,7 @@ static void hns3_get_drvinfo(struct net_device *netdev,
 
 static u32 hns3_get_link(struct net_device *netdev)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h;
-
-	h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (h->ae_algo && h->ae_algo->ops && h->ae_algo->ops->get_status)
 		return h->ae_algo->ops->get_status(h);
@@ -277,7 +539,8 @@ static void hns3_get_ringparam(struct net_device *netdev,
 			       struct ethtool_ringparam *param)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	int queue_num = priv->ae_handle->kinfo.num_tqps;
+	struct hnae3_handle *h = priv->ae_handle;
+	int queue_num = h->kinfo.num_tqps;
 
 	param->tx_max_pending = HNS3_RING_MAX_PENDING;
 	param->rx_max_pending = HNS3_RING_MAX_PENDING;
@@ -289,8 +552,7 @@ static void hns3_get_ringparam(struct net_device *netdev,
 static void hns3_get_pauseparam(struct net_device *netdev,
 				struct ethtool_pauseparam *param)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (h->ae_algo && h->ae_algo->ops && h->ae_algo->ops->get_pauseparam)
 		h->ae_algo->ops->get_pauseparam(h, &param->autoneg,
@@ -300,32 +562,30 @@ static void hns3_get_pauseparam(struct net_device *netdev,
 static int hns3_get_link_ksettings(struct net_device *netdev,
 				   struct ethtool_link_ksettings *cmd)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 	u32 supported_caps;
 	u32 advertised_caps;
 	u8 media_type = HNAE3_MEDIA_TYPE_UNKNOWN;
 	u8 link_stat;
-	u8 auto_neg;
-	u8 duplex;
-	u32 speed;
 
 	if (!h->ae_algo || !h->ae_algo->ops)
 		return -EOPNOTSUPP;
 
 	/* 1.auto_neg & speed & duplex from cmd */
-	if (h->ae_algo->ops->get_ksettings_an_result) {
-		h->ae_algo->ops->get_ksettings_an_result(h, &auto_neg,
-							 &speed, &duplex);
-		cmd->base.autoneg = auto_neg;
-		cmd->base.speed = speed;
-		cmd->base.duplex = duplex;
-
-		link_stat = hns3_get_link(netdev);
-		if (!link_stat) {
-			cmd->base.speed = (u32)SPEED_UNKNOWN;
-			cmd->base.duplex = DUPLEX_UNKNOWN;
-		}
+	if (netdev->phydev)
+		phy_ethtool_ksettings_get(netdev->phydev, cmd);
+	else if (h->ae_algo->ops->get_ksettings_an_result)
+		h->ae_algo->ops->get_ksettings_an_result(h,
+							 &cmd->base.autoneg,
+							 &cmd->base.speed,
+							 &cmd->base.duplex);
+	else
+		return -EOPNOTSUPP;
+
+	link_stat = hns3_get_link(netdev);
+	if (!link_stat) {
+		cmd->base.speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 
 	/* 2.media_type get from bios parameter block */
@@ -375,6 +635,9 @@ static int hns3_get_link_ksettings(struct net_device *netdev,
 			break;
 		}
 
+		if (!cmd->base.autoneg)
+			advertised_caps &= ~HNS3_LM_AUTONEG_BIT;
+
 		/* now, map driver link modes to ethtool link modes */
 		hns3_driv_to_eth_caps(supported_caps, cmd, false);
 		hns3_driv_to_eth_caps(advertised_caps, cmd, true);
@@ -390,10 +653,19 @@ static int hns3_get_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
+static int hns3_set_link_ksettings(struct net_device *netdev,
+				   const struct ethtool_link_ksettings *cmd)
+{
+	/* Only support ksettings_set for netdev with phy attached for now */
+	if (netdev->phydev)
+		return phy_ethtool_ksettings_set(netdev->phydev, cmd);
+
+	return -EOPNOTSUPP;
+}
+
 static u32 hns3_get_rss_key_size(struct net_device *netdev)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (!h->ae_algo || !h->ae_algo->ops ||
 	    !h->ae_algo->ops->get_rss_key_size)
@@ -404,8 +676,7 @@ static u32 hns3_get_rss_key_size(struct net_device *netdev)
 
 static u32 hns3_get_rss_indir_size(struct net_device *netdev)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (!h->ae_algo || !h->ae_algo->ops ||
 	    !h->ae_algo->ops->get_rss_indir_size)
@@ -417,8 +688,7 @@ static u32 hns3_get_rss_indir_size(struct net_device *netdev)
 static int hns3_get_rss(struct net_device *netdev, u32 *indir, u8 *key,
 			u8 *hfunc)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_rss)
 		return -EOPNOTSUPP;
@@ -429,8 +699,7 @@ static int hns3_get_rss(struct net_device *netdev, u32 *indir, u8 *key,
 static int hns3_set_rss(struct net_device *netdev, const u32 *indir,
 			const u8 *key, const u8 hfunc)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->set_rss)
 		return -EOPNOTSUPP;
@@ -454,16 +723,17 @@ static int hns3_get_rxnfc(struct net_device *netdev,
 			  struct ethtool_rxnfc *cmd,
 			  u32 *rule_locs)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 
-	if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_tc_size)
+	if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_rss_tuple)
 		return -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
 	case ETHTOOL_GRXRINGS:
-		cmd->data = h->ae_algo->ops->get_tc_size(h);
+		cmd->data = h->kinfo.num_tc * h->kinfo.rss_size;
 		break;
+	case ETHTOOL_GRXFH:
+		return h->ae_algo->ops->get_rss_tuple(h, cmd);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -471,20 +741,133 @@ static int hns3_get_rxnfc(struct net_device *netdev,
 	return 0;
 }
 
+static int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv,
+				       u32 new_desc_num)
+{
+	struct hnae3_handle *h = priv->ae_handle;
+	int i;
+
+	h->kinfo.num_desc = new_desc_num;
+
+	for (i = 0; i < h->kinfo.num_tqps * 2; i++)
+		priv->ring_data[i].ring->desc_num = new_desc_num;
+
+	return hns3_init_all_ring(priv);
+}
+
+static int hns3_set_ringparam(struct net_device *ndev,
+			      struct ethtool_ringparam *param)
+{
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct hnae3_handle *h = priv->ae_handle;
+	bool if_running = netif_running(ndev);
+	u32 old_desc_num, new_desc_num;
+	int ret;
+
+	if (param->rx_mini_pending || param->rx_jumbo_pending)
+		return -EINVAL;
+
+	if (param->tx_pending != param->rx_pending) {
+		netdev_err(ndev,
+			   "Descriptors of tx and rx must be equal");
+		return -EINVAL;
+	}
+
+	if (param->tx_pending > HNS3_RING_MAX_PENDING ||
+	    param->tx_pending < HNS3_RING_MIN_PENDING) {
+		netdev_err(ndev,
+			   "Descriptors requested (Tx/Rx: %d) out of range [%d-%d]\n",
+			   param->tx_pending, HNS3_RING_MIN_PENDING,
+			   HNS3_RING_MAX_PENDING);
+		return -EINVAL;
+	}
+
+	new_desc_num = param->tx_pending;
+
+	/* Hardware requires that its descriptors must be multiple of eight */
+	new_desc_num = ALIGN(new_desc_num, HNS3_RING_BD_MULTIPLE);
+	old_desc_num = h->kinfo.num_desc;
+	if (old_desc_num == new_desc_num)
+		return 0;
+
+	netdev_info(ndev,
+		    "Changing descriptor count from %d to %d.\n",
+		    old_desc_num, new_desc_num);
+
+	if (if_running)
+		dev_close(ndev);
+
+	ret = hns3_uninit_all_ring(priv);
+	if (ret)
+		return ret;
+
+	ret = hns3_change_all_ring_bd_num(priv, new_desc_num);
+	if (ret) {
+		ret = hns3_change_all_ring_bd_num(priv, old_desc_num);
+		if (ret) {
+			netdev_err(ndev,
+				   "Revert to old bd num fail, ret=%d.\n", ret);
+			return ret;
+		}
+	}
+
+	if (if_running)
+		ret = dev_open(ndev);
+
+	return ret;
+}
+
+static int hns3_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+
+	if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->set_rss_tuple)
+		return -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXFH:
+		return h->ae_algo->ops->set_rss_tuple(h, cmd);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int hns3_nway_reset(struct net_device *netdev)
+{
+	struct phy_device *phy = netdev->phydev;
+
+	if (!netif_running(netdev))
+		return 0;
+
+	/* Only support nway_reset for netdev with phy attached for now */
+	if (!phy)
+		return -EOPNOTSUPP;
+
+	if (phy->autoneg != AUTONEG_ENABLE)
+		return -EINVAL;
+
+	return genphy_restart_aneg(phy);
+}
+
 static const struct ethtool_ops hns3_ethtool_ops = {
+	.self_test = hns3_self_test,
 	.get_drvinfo = hns3_get_drvinfo,
 	.get_link = hns3_get_link,
 	.get_ringparam = hns3_get_ringparam,
+	.set_ringparam = hns3_set_ringparam,
 	.get_pauseparam = hns3_get_pauseparam,
 	.get_strings = hns3_get_strings,
 	.get_ethtool_stats = hns3_get_stats,
 	.get_sset_count = hns3_get_sset_count,
 	.get_rxnfc = hns3_get_rxnfc,
+	.set_rxnfc = hns3_set_rxnfc,
 	.get_rxfh_key_size = hns3_get_rss_key_size,
 	.get_rxfh_indir_size = hns3_get_rss_indir_size,
 	.get_rxfh = hns3_get_rss,
 	.set_rxfh = hns3_set_rss,
 	.get_link_ksettings = hns3_get_link_ksettings,
+	.set_link_ksettings = hns3_set_link_ksettings,
+	.nway_reset = hns3_nway_reset,
 };
 
 void hns3_ethtool_set_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index 1d4f712b15a8..e2e5cdc7119c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -26,6 +26,7 @@
 #include <linux/skbuff.h>
 #include <linux/dma-mapping.h>
 #include <linux/prefetch.h>
+#include <linux/cpumask.h>
 #include <asm/barrier.h>
 
 #include "hinic_common.h"
@@ -171,11 +172,10 @@ static int rx_alloc_pkts(struct hinic_rxq *rxq)
 	struct hinic_sge sge;
 	dma_addr_t dma_addr;
 	struct sk_buff *skb;
-	int i, alloc_more;
 	u16 prod_idx;
+	int i;
 
 	free_wqebbs = hinic_get_rq_free_wqebbs(rxq->rq);
-	alloc_more = 0;
 
 	/* Limit the allocation chunks */
 	if (free_wqebbs > nic_dev->rx_weight)
@@ -185,7 +185,6 @@ static int rx_alloc_pkts(struct hinic_rxq *rxq)
 		skb = rx_alloc_skb(rxq, &dma_addr);
 		if (!skb) {
 			netdev_err(rxq->netdev, "Failed to alloc Rx skb\n");
-			alloc_more = 1;
 			goto skb_out;
 		}
 
@@ -195,7 +194,6 @@ static int rx_alloc_pkts(struct hinic_rxq *rxq)
 					  &prod_idx);
 		if (!rq_wqe) {
 			rx_free_skb(rxq, skb, dma_addr);
-			alloc_more = 1;
 			goto skb_out;
 		}
 
@@ -211,9 +209,7 @@ skb_out:
 		hinic_rq_update(rxq->rq, prod_idx);
 	}
 
-	if (alloc_more)
-		tasklet_schedule(&rxq->rx_task);
-
+	tasklet_schedule(&rxq->rx_task);
 	return i;
 }
 
@@ -357,7 +353,7 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 	}
 
 	if (pkts)
-		tasklet_schedule(&rxq->rx_task); /* hinic_rx_alloc_pkts */
+		tasklet_schedule(&rxq->rx_task); /* rx_alloc_pkts */
 
 	u64_stats_update_begin(&rxq->rxq_stats.syncp);
 	rxq->rxq_stats.pkts += pkts;
@@ -417,6 +413,8 @@ static int rx_request_irq(struct hinic_rxq *rxq)
 	struct hinic_dev *nic_dev = netdev_priv(rxq->netdev);
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 	struct hinic_rq *rq = rxq->rq;
+	struct hinic_qp *qp;
+	struct cpumask mask;
 	int err;
 
 	rx_add_napi(rxq);
@@ -432,7 +430,9 @@ static int rx_request_irq(struct hinic_rxq *rxq)
 		return err;
 	}
 
-	return 0;
+	qp = container_of(rq, struct hinic_qp, rq);
+	cpumask_set_cpu(qp->q_id % num_online_cpus(), &mask);
+	return irq_set_affinity_hint(rq->irq, &mask);
 }
 
 static void rx_free_irq(struct hinic_rxq *rxq)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index abe3e38cd342..9128858479c4 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -212,10 +212,19 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 
 	sq_wqe = hinic_sq_get_wqe(txq->sq, wqe_size, &prod_idx);
 	if (!sq_wqe) {
-		tx_unmap_skb(nic_dev, skb, txq->sges);
-
 		netif_stop_subqueue(netdev, qp->q_id);
 
+		/* Check for the case free_tx_poll is called in another cpu
+		 * and we stopped the subqueue after free_tx_poll check.
+		 */
+		sq_wqe = hinic_sq_get_wqe(txq->sq, wqe_size, &prod_idx);
+		if (sq_wqe) {
+			netif_wake_subqueue(nic_dev->netdev, qp->q_id);
+			goto process_sq_wqe;
+		}
+
+		tx_unmap_skb(nic_dev, skb, txq->sges);
+
 		u64_stats_update_begin(&txq->txq_stats.syncp);
 		txq->txq_stats.tx_busy++;
 		u64_stats_update_end(&txq->txq_stats.syncp);
@@ -223,6 +232,7 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 		goto flush_skbs;
 	}
 
+process_sq_wqe:
 	hinic_sq_prepare_wqe(txq->sq, prod_idx, sq_wqe, txq->sges, nr_sges);
 
 	hinic_sq_write_wqe(txq->sq, prod_idx, sq_wqe, skb, wqe_size);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index c66abd476023..d0cff2807d0b 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -115,6 +115,7 @@ static int init_sub_crqs(struct ibmvnic_adapter *);
 static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter);
 static int ibmvnic_init(struct ibmvnic_adapter *);
 static void release_crq_queue(struct ibmvnic_adapter *);
+static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p);
 
 struct ibmvnic_stat {
 	char name[ETH_GSTRING_LEN];
@@ -553,6 +554,10 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter)
 		if (rc)
 			return rc;
 
+		rc = reset_long_term_buff(adapter, &tx_pool->tso_ltb);
+		if (rc)
+			return rc;
+
 		memset(tx_pool->tx_buff, 0,
 		       adapter->req_tx_entries_per_subcrq *
 		       sizeof(struct ibmvnic_tx_buff));
@@ -562,6 +567,7 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter)
 
 		tx_pool->consumer_index = 0;
 		tx_pool->producer_index = 0;
+		tx_pool->tso_index = 0;
 	}
 
 	return 0;
@@ -581,6 +587,7 @@ static void release_tx_pools(struct ibmvnic_adapter *adapter)
 		tx_pool = &adapter->tx_pool[i];
 		kfree(tx_pool->tx_buff);
 		free_long_term_buff(adapter, &tx_pool->long_term_buff);
+		free_long_term_buff(adapter, &tx_pool->tso_ltb);
 		kfree(tx_pool->free_map);
 	}
 
@@ -625,6 +632,16 @@ static int init_tx_pools(struct net_device *netdev)
 			return -1;
 		}
 
+		/* alloc TSO ltb */
+		if (alloc_long_term_buff(adapter, &tx_pool->tso_ltb,
+					 IBMVNIC_TSO_BUFS *
+					 IBMVNIC_TSO_BUF_SZ)) {
+			release_tx_pools(adapter);
+			return -1;
+		}
+
+		tx_pool->tso_index = 0;
+
 		tx_pool->free_map = kcalloc(adapter->req_tx_entries_per_subcrq,
 					    sizeof(int), GFP_KERNEL);
 		if (!tx_pool->free_map) {
@@ -910,6 +927,11 @@ static int ibmvnic_open(struct net_device *netdev)
 
 	mutex_lock(&adapter->reset_lock);
 
+	if (adapter->mac_change_pending) {
+		__ibmvnic_set_mac(netdev, &adapter->desired.mac);
+		adapter->mac_change_pending = false;
+	}
+
 	if (adapter->state != VNIC_CLOSED) {
 		rc = ibmvnic_login(netdev);
 		if (rc) {
@@ -927,6 +949,7 @@ static int ibmvnic_open(struct net_device *netdev)
 	}
 
 	rc = __ibmvnic_open(netdev);
+	netif_carrier_on(netdev);
 	mutex_unlock(&adapter->reset_lock);
 
 	return rc;
@@ -1200,11 +1223,41 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		be32_to_cpu(adapter->login_rsp_buf->off_txsubm_subcrqs));
 
 	index = tx_pool->free_map[tx_pool->consumer_index];
-	offset = index * adapter->req_mtu;
-	dst = tx_pool->long_term_buff.buff + offset;
-	memset(dst, 0, adapter->req_mtu);
-	skb_copy_from_linear_data(skb, dst, skb->len);
-	data_dma_addr = tx_pool->long_term_buff.addr + offset;
+
+	if (skb_is_gso(skb)) {
+		offset = tx_pool->tso_index * IBMVNIC_TSO_BUF_SZ;
+		dst = tx_pool->tso_ltb.buff + offset;
+		memset(dst, 0, IBMVNIC_TSO_BUF_SZ);
+		data_dma_addr = tx_pool->tso_ltb.addr + offset;
+		tx_pool->tso_index++;
+		if (tx_pool->tso_index == IBMVNIC_TSO_BUFS)
+			tx_pool->tso_index = 0;
+	} else {
+		offset = index * adapter->req_mtu;
+		dst = tx_pool->long_term_buff.buff + offset;
+		memset(dst, 0, adapter->req_mtu);
+		data_dma_addr = tx_pool->long_term_buff.addr + offset;
+	}
+
+	if (skb_shinfo(skb)->nr_frags) {
+		int cur, i;
+
+		/* Copy the head */
+		skb_copy_from_linear_data(skb, dst, skb_headlen(skb));
+		cur = skb_headlen(skb);
+
+		/* Copy the frags */
+		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+			const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+			memcpy(dst + cur,
+			       page_address(skb_frag_page(frag)) +
+			       frag->page_offset, skb_frag_size(frag));
+			cur += skb_frag_size(frag);
+		}
+	} else {
+		skb_copy_from_linear_data(skb, dst, skb->len);
+	}
 
 	tx_pool->consumer_index =
 	    (tx_pool->consumer_index + 1) %
@@ -1225,7 +1278,10 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	tx_crq.v1.n_sge = 1;
 	tx_crq.v1.flags1 = IBMVNIC_TX_COMP_NEEDED;
 	tx_crq.v1.correlator = cpu_to_be32(index);
-	tx_crq.v1.dma_reg = cpu_to_be16(tx_pool->long_term_buff.map_id);
+	if (skb_is_gso(skb))
+		tx_crq.v1.dma_reg = cpu_to_be16(tx_pool->tso_ltb.map_id);
+	else
+		tx_crq.v1.dma_reg = cpu_to_be16(tx_pool->long_term_buff.map_id);
 	tx_crq.v1.sge_len = cpu_to_be32(skb->len);
 	tx_crq.v1.ioba = cpu_to_be64(data_dma_addr);
 
@@ -1250,6 +1306,11 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		tx_crq.v1.flags1 |= IBMVNIC_TX_CHKSUM_OFFLOAD;
 		hdrs += 2;
 	}
+	if (skb_is_gso(skb)) {
+		tx_crq.v1.flags1 |= IBMVNIC_TX_LSO;
+		tx_crq.v1.mss = cpu_to_be16(skb_shinfo(skb)->gso_size);
+		hdrs += 2;
+	}
 	/* determine if l2/3/4 headers are sent to firmware */
 	if ((*hdrs >> 7) & 1 &&
 	    (skb->protocol == htons(ETH_P_IP) ||
@@ -1371,7 +1432,7 @@ static void ibmvnic_set_multi(struct net_device *netdev)
 	}
 }
 
-static int ibmvnic_set_mac(struct net_device *netdev, void *p)
+static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 	struct sockaddr *addr = p;
@@ -1389,6 +1450,22 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p)
 	return 0;
 }
 
+static int ibmvnic_set_mac(struct net_device *netdev, void *p)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	struct sockaddr *addr = p;
+
+	if (adapter->state != VNIC_OPEN) {
+		memcpy(&adapter->desired.mac, addr, sizeof(struct sockaddr));
+		adapter->mac_change_pending = true;
+		return 0;
+	}
+
+	__ibmvnic_set_mac(netdev, addr);
+
+	return 0;
+}
+
 /**
  * do_reset returns zero if we are able to keep processing reset events, or
  * non-zero if we hit a fatal error and must halt.
@@ -1415,6 +1492,13 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 	if (rc)
 		return rc;
 
+	if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM ||
+	    adapter->wait_for_reset) {
+		release_resources(adapter);
+		release_sub_crqs(adapter);
+		release_crq_queue(adapter);
+	}
+
 	if (adapter->reset_reason != VNIC_RESET_NON_FATAL) {
 		/* remove the closed state so when we call open it appears
 		 * we are coming from the probed state.
@@ -1423,7 +1507,7 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 
 		rc = ibmvnic_init(adapter);
 		if (rc)
-			return 0;
+			return IBMVNIC_INIT_FAILED;
 
 		/* If the adapter was in PROBE state prior to the reset,
 		 * exit here.
@@ -1437,16 +1521,23 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 			return 0;
 		}
 
-		rc = reset_tx_pools(adapter);
-		if (rc)
-			return rc;
+		if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM ||
+		    adapter->wait_for_reset) {
+			rc = init_resources(adapter);
+			if (rc)
+				return rc;
+		} else {
+			rc = reset_tx_pools(adapter);
+			if (rc)
+				return rc;
 
-		rc = reset_rx_pools(adapter);
-		if (rc)
-			return rc;
+			rc = reset_rx_pools(adapter);
+			if (rc)
+				return rc;
 
-		if (reset_state == VNIC_CLOSED)
-			return 0;
+			if (reset_state == VNIC_CLOSED)
+				return 0;
+		}
 	}
 
 	rc = __ibmvnic_open(netdev);
@@ -1506,7 +1597,7 @@ static void __ibmvnic_reset(struct work_struct *work)
 	struct ibmvnic_adapter *adapter;
 	struct net_device *netdev;
 	u32 reset_state;
-	int rc;
+	int rc = 0;
 
 	adapter = container_of(work, struct ibmvnic_adapter, ibmvnic_reset);
 	netdev = adapter->netdev;
@@ -1519,12 +1610,18 @@ static void __ibmvnic_reset(struct work_struct *work)
 	while (rwi) {
 		rc = do_reset(adapter, rwi, reset_state);
 		kfree(rwi);
-		if (rc)
+		if (rc && rc != IBMVNIC_INIT_FAILED)
 			break;
 
 		rwi = get_next_rwi(adapter);
 	}
 
+	if (adapter->wait_for_reset) {
+		adapter->wait_for_reset = false;
+		adapter->reset_done_rc = rc;
+		complete(&adapter->reset_done);
+	}
+
 	if (rc) {
 		netdev_dbg(adapter->netdev, "Reset failed\n");
 		free_all_rwi(adapter);
@@ -1704,9 +1801,42 @@ static void ibmvnic_netpoll_controller(struct net_device *dev)
 }
 #endif
 
+static int wait_for_reset(struct ibmvnic_adapter *adapter)
+{
+	adapter->fallback.mtu = adapter->req_mtu;
+	adapter->fallback.rx_queues = adapter->req_rx_queues;
+	adapter->fallback.tx_queues = adapter->req_tx_queues;
+	adapter->fallback.rx_entries = adapter->req_rx_add_entries_per_subcrq;
+	adapter->fallback.tx_entries = adapter->req_tx_entries_per_subcrq;
+
+	init_completion(&adapter->reset_done);
+	ibmvnic_reset(adapter, VNIC_RESET_CHANGE_PARAM);
+	adapter->wait_for_reset = true;
+	wait_for_completion(&adapter->reset_done);
+
+	if (adapter->reset_done_rc) {
+		adapter->desired.mtu = adapter->fallback.mtu;
+		adapter->desired.rx_queues = adapter->fallback.rx_queues;
+		adapter->desired.tx_queues = adapter->fallback.tx_queues;
+		adapter->desired.rx_entries = adapter->fallback.rx_entries;
+		adapter->desired.tx_entries = adapter->fallback.tx_entries;
+
+		init_completion(&adapter->reset_done);
+		ibmvnic_reset(adapter, VNIC_RESET_CHANGE_PARAM);
+		wait_for_completion(&adapter->reset_done);
+	}
+	adapter->wait_for_reset = false;
+
+	return adapter->reset_done_rc;
+}
+
 static int ibmvnic_change_mtu(struct net_device *netdev, int new_mtu)
 {
-	return -EOPNOTSUPP;
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+
+	adapter->desired.mtu = new_mtu + ETH_HLEN;
+
+	return wait_for_reset(adapter);
 }
 
 static const struct net_device_ops ibmvnic_netdev_ops = {
@@ -1794,6 +1924,27 @@ static void ibmvnic_get_ringparam(struct net_device *netdev,
 	ring->rx_jumbo_pending = 0;
 }
 
+static int ibmvnic_set_ringparam(struct net_device *netdev,
+				 struct ethtool_ringparam *ring)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+
+	if (ring->rx_pending > adapter->max_rx_add_entries_per_subcrq  ||
+	    ring->tx_pending > adapter->max_tx_entries_per_subcrq) {
+		netdev_err(netdev, "Invalid request.\n");
+		netdev_err(netdev, "Max tx buffers = %llu\n",
+			   adapter->max_rx_add_entries_per_subcrq);
+		netdev_err(netdev, "Max rx buffers = %llu\n",
+			   adapter->max_tx_entries_per_subcrq);
+		return -EINVAL;
+	}
+
+	adapter->desired.rx_entries = ring->rx_pending;
+	adapter->desired.tx_entries = ring->tx_pending;
+
+	return wait_for_reset(adapter);
+}
+
 static void ibmvnic_get_channels(struct net_device *netdev,
 				 struct ethtool_channels *channels)
 {
@@ -1809,6 +1960,17 @@ static void ibmvnic_get_channels(struct net_device *netdev,
 	channels->combined_count = 0;
 }
 
+static int ibmvnic_set_channels(struct net_device *netdev,
+				struct ethtool_channels *channels)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+
+	adapter->desired.rx_queues = channels->rx_count;
+	adapter->desired.tx_queues = channels->tx_count;
+
+	return wait_for_reset(adapter);
+}
+
 static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(dev);
@@ -1905,7 +2067,9 @@ static const struct ethtool_ops ibmvnic_ethtool_ops = {
 	.set_msglevel		= ibmvnic_set_msglevel,
 	.get_link		= ibmvnic_get_link,
 	.get_ringparam		= ibmvnic_get_ringparam,
+	.set_ringparam		= ibmvnic_set_ringparam,
 	.get_channels		= ibmvnic_get_channels,
+	.set_channels		= ibmvnic_set_channels,
 	.get_strings            = ibmvnic_get_strings,
 	.get_sset_count         = ibmvnic_get_sset_count,
 	.get_ethtool_stats	= ibmvnic_get_ethtool_stats,
@@ -2371,6 +2535,7 @@ static void ibmvnic_send_req_caps(struct ibmvnic_adapter *adapter, int retry)
 {
 	struct device *dev = &adapter->vdev->dev;
 	union ibmvnic_crq crq;
+	int max_entries;
 
 	if (!retry) {
 		/* Sub-CRQ entries are 32 byte long */
@@ -2382,21 +2547,60 @@ static void ibmvnic_send_req_caps(struct ibmvnic_adapter *adapter, int retry)
 			return;
 		}
 
-		/* Get the minimum between the queried max and the entries
-		 * that fit in our PAGE_SIZE
-		 */
-		adapter->req_tx_entries_per_subcrq =
-		    adapter->max_tx_entries_per_subcrq > entries_page ?
-		    entries_page : adapter->max_tx_entries_per_subcrq;
-		adapter->req_rx_add_entries_per_subcrq =
-		    adapter->max_rx_add_entries_per_subcrq > entries_page ?
-		    entries_page : adapter->max_rx_add_entries_per_subcrq;
-
-		adapter->req_tx_queues = adapter->opt_tx_comp_sub_queues;
-		adapter->req_rx_queues = adapter->opt_rx_comp_queues;
-		adapter->req_rx_add_queues = adapter->max_rx_add_queues;
+		if (adapter->desired.mtu)
+			adapter->req_mtu = adapter->desired.mtu;
+		else
+			adapter->req_mtu = adapter->netdev->mtu + ETH_HLEN;
 
-		adapter->req_mtu = adapter->netdev->mtu + ETH_HLEN;
+		if (!adapter->desired.tx_entries)
+			adapter->desired.tx_entries =
+					adapter->max_tx_entries_per_subcrq;
+		if (!adapter->desired.rx_entries)
+			adapter->desired.rx_entries =
+					adapter->max_rx_add_entries_per_subcrq;
+
+		max_entries = IBMVNIC_MAX_LTB_SIZE /
+			      (adapter->req_mtu + IBMVNIC_BUFFER_HLEN);
+
+		if ((adapter->req_mtu + IBMVNIC_BUFFER_HLEN) *
+			adapter->desired.tx_entries > IBMVNIC_MAX_LTB_SIZE) {
+			adapter->desired.tx_entries = max_entries;
+		}
+
+		if ((adapter->req_mtu + IBMVNIC_BUFFER_HLEN) *
+			adapter->desired.rx_entries > IBMVNIC_MAX_LTB_SIZE) {
+			adapter->desired.rx_entries = max_entries;
+		}
+
+		if (adapter->desired.tx_entries)
+			adapter->req_tx_entries_per_subcrq =
+					adapter->desired.tx_entries;
+		else
+			adapter->req_tx_entries_per_subcrq =
+					adapter->max_tx_entries_per_subcrq;
+
+		if (adapter->desired.rx_entries)
+			adapter->req_rx_add_entries_per_subcrq =
+					adapter->desired.rx_entries;
+		else
+			adapter->req_rx_add_entries_per_subcrq =
+					adapter->max_rx_add_entries_per_subcrq;
+
+		if (adapter->desired.tx_queues)
+			adapter->req_tx_queues =
+					adapter->desired.tx_queues;
+		else
+			adapter->req_tx_queues =
+					adapter->opt_tx_comp_sub_queues;
+
+		if (adapter->desired.rx_queues)
+			adapter->req_rx_queues =
+					adapter->desired.rx_queues;
+		else
+			adapter->req_rx_queues =
+					adapter->opt_rx_comp_queues;
+
+		adapter->req_rx_add_queues = adapter->max_rx_add_queues;
 	}
 
 	memset(&crq, 0, sizeof(crq));
@@ -2940,14 +3144,14 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 	adapter->ip_offload_ctrl.udp_ipv4_chksum = buf->udp_ipv4_chksum;
 	adapter->ip_offload_ctrl.tcp_ipv6_chksum = buf->tcp_ipv6_chksum;
 	adapter->ip_offload_ctrl.udp_ipv6_chksum = buf->udp_ipv6_chksum;
+	adapter->ip_offload_ctrl.large_tx_ipv4 = buf->large_tx_ipv4;
+	adapter->ip_offload_ctrl.large_tx_ipv6 = buf->large_tx_ipv6;
 
-	/* large_tx/rx disabled for now, additional features needed */
-	adapter->ip_offload_ctrl.large_tx_ipv4 = 0;
-	adapter->ip_offload_ctrl.large_tx_ipv6 = 0;
+	/* large_rx disabled for now, additional features needed */
 	adapter->ip_offload_ctrl.large_rx_ipv4 = 0;
 	adapter->ip_offload_ctrl.large_rx_ipv6 = 0;
 
-	adapter->netdev->features = NETIF_F_GSO;
+	adapter->netdev->features = NETIF_F_SG | NETIF_F_GSO;
 
 	if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum)
 		adapter->netdev->features |= NETIF_F_IP_CSUM;
@@ -2959,6 +3163,13 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 	    (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)))
 		adapter->netdev->features |= NETIF_F_RXCSUM;
 
+	if (buf->large_tx_ipv4)
+		adapter->netdev->features |= NETIF_F_TSO;
+	if (buf->large_tx_ipv6)
+		adapter->netdev->features |= NETIF_F_TSO6;
+
+	adapter->netdev->hw_features |= adapter->netdev->features;
+
 	memset(&crq, 0, sizeof(crq));
 	crq.control_ip_offload.first = IBMVNIC_CRQ_CMD;
 	crq.control_ip_offload.cmd = CONTROL_IP_OFFLOAD;
@@ -3210,6 +3421,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 			    struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
+	struct net_device *netdev = adapter->netdev;
 	struct ibmvnic_login_rsp_buffer *login_rsp = adapter->login_rsp_buf;
 	struct ibmvnic_login_buffer *login = adapter->login_buf;
 	int i;
@@ -3229,6 +3441,8 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 		return 0;
 	}
 
+	netdev->mtu = adapter->req_mtu - ETH_HLEN;
+
 	netdev_dbg(adapter->netdev, "Login Response Buffer:\n");
 	for (i = 0; i < (adapter->login_rsp_buf_sz - 1) / 8 + 1; i++) {
 		netdev_dbg(adapter->netdev, "%016lx\n",
@@ -3784,7 +3998,7 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 	unsigned long timeout = msecs_to_jiffies(30000);
 	int rc;
 
-	if (adapter->resetting) {
+	if (adapter->resetting && !adapter->wait_for_reset) {
 		rc = ibmvnic_reset_crq(adapter);
 		if (!rc)
 			rc = vio_enable_interrupts(adapter->vdev);
@@ -3818,7 +4032,7 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 		return -1;
 	}
 
-	if (adapter->resetting)
+	if (adapter->resetting && !adapter->wait_for_reset)
 		rc = reset_sub_crq_queues(adapter);
 	else
 		rc = init_sub_crqs(adapter);
@@ -3887,6 +4101,8 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	mutex_init(&adapter->rwi_lock);
 	adapter->resetting = false;
 
+	adapter->mac_change_pending = false;
+
 	do {
 		rc = ibmvnic_init(adapter);
 		if (rc && rc != EAGAIN)
@@ -3894,11 +4110,14 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	} while (rc == EAGAIN);
 
 	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_init_fail;
 
+	netif_carrier_off(netdev);
 	rc = register_netdev(netdev);
 	if (rc) {
 		dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc);
@@ -3907,6 +4126,9 @@ 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;
+
+	adapter->wait_for_reset = false;
+
 	return 0;
 
 ibmvnic_register_fail:
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index d02257ccc377..4670af80d612 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -30,6 +30,8 @@
 #define IBMVNIC_DRIVER_VERSION	"1.0.1"
 #define IBMVNIC_INVALID_MAP	-1
 #define IBMVNIC_STATS_TIMEOUT	1
+#define IBMVNIC_INIT_FAILED	2
+
 /* basic structures plus 100 2k buffers */
 #define IBMVNIC_IO_ENTITLEMENT_DEFAULT	610305
 
@@ -39,6 +41,12 @@
 #define IBMVNIC_BUFFS_PER_POOL	100
 #define IBMVNIC_MAX_TX_QUEUES	5
 
+#define IBMVNIC_TSO_BUF_SZ	65536
+#define IBMVNIC_TSO_BUFS	64
+
+#define IBMVNIC_MAX_LTB_SIZE ((1 << (MAX_ORDER - 1)) * PAGE_SIZE)
+#define IBMVNIC_BUFFER_HLEN 500
+
 struct ibmvnic_login_buffer {
 	__be32 len;
 	__be32 version;
@@ -896,6 +904,8 @@ struct ibmvnic_tx_pool {
 	wait_queue_head_t ibmvnic_tx_comp_q;
 	struct task_struct *work_thread;
 	struct ibmvnic_long_term_buff long_term_buff;
+	struct ibmvnic_long_term_buff tso_ltb;
+	int tso_index;
 };
 
 struct ibmvnic_rx_buff {
@@ -940,13 +950,23 @@ enum ibmvnic_reset_reason {VNIC_RESET_FAILOVER = 1,
 			   VNIC_RESET_MOBILITY,
 			   VNIC_RESET_FATAL,
 			   VNIC_RESET_NON_FATAL,
-			   VNIC_RESET_TIMEOUT};
+			   VNIC_RESET_TIMEOUT,
+			   VNIC_RESET_CHANGE_PARAM};
 
 struct ibmvnic_rwi {
 	enum ibmvnic_reset_reason reset_reason;
 	struct list_head list;
 };
 
+struct ibmvnic_tunables {
+	u64 rx_queues;
+	u64 tx_queues;
+	u64 rx_entries;
+	u64 tx_entries;
+	u64 mtu;
+	struct sockaddr mac;
+};
+
 struct ibmvnic_adapter {
 	struct vio_dev *vdev;
 	struct net_device *netdev;
@@ -1007,6 +1027,10 @@ struct ibmvnic_adapter {
 	struct completion fw_done;
 	int fw_done_rc;
 
+	struct completion reset_done;
+	int reset_done_rc;
+	bool wait_for_reset;
+
 	/* partner capabilities */
 	u64 min_tx_queues;
 	u64 min_rx_queues;
@@ -1051,4 +1075,9 @@ struct ibmvnic_adapter {
 	struct work_struct ibmvnic_reset;
 	bool resetting;
 	bool napi_enabled, from_passive_init;
+
+	bool mac_change_pending;
+
+	struct ibmvnic_tunables desired;
+	struct ibmvnic_tunables fallback;
 };
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 4d10270ddf8f..44b3937f7e81 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -1710,9 +1710,9 @@ static void e100_adjust_adaptive_ifs(struct nic *nic, int speed, int duplex)
 	}
 }
 
-static void e100_watchdog(unsigned long data)
+static void e100_watchdog(struct timer_list *t)
 {
-	struct nic *nic = (struct nic *)data;
+	struct nic *nic = from_timer(nic, t, watchdog);
 	struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET };
 	u32 speed;
 
@@ -1910,11 +1910,10 @@ static int e100_alloc_cbs(struct nic *nic)
 	nic->cb_to_use = nic->cb_to_send = nic->cb_to_clean = NULL;
 	nic->cbs_avail = 0;
 
-	nic->cbs = pci_pool_alloc(nic->cbs_pool, GFP_KERNEL,
-				  &nic->cbs_dma_addr);
+	nic->cbs = pci_pool_zalloc(nic->cbs_pool, GFP_KERNEL,
+				   &nic->cbs_dma_addr);
 	if (!nic->cbs)
 		return -ENOMEM;
-	memset(nic->cbs, 0, count * sizeof(struct cb));
 
 	for (cb = nic->cbs, i = 0; i < count; cb++, i++) {
 		cb->next = (i + 1 < count) ? cb + 1 : nic->cbs;
@@ -2921,7 +2920,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_master(pdev);
 
-	setup_timer(&nic->watchdog, e100_watchdog, (unsigned long)nic);
+	timer_setup(&nic->watchdog, e100_watchdog, 0);
 
 	INIT_WORK(&nic->tx_timeout_task, e100_tx_timeout_task);
 
diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index 0641c0098738..afb7ebe20b24 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -398,6 +398,7 @@
 #define E1000_ICR_LSC           0x00000004 /* Link Status Change */
 #define E1000_ICR_RXSEQ         0x00000008 /* Rx sequence error */
 #define E1000_ICR_RXDMT0        0x00000010 /* Rx desc min. threshold (0) */
+#define E1000_ICR_RXO           0x00000040 /* Receiver Overrun */
 #define E1000_ICR_RXT0          0x00000080 /* Rx timer intr (ring 0) */
 #define E1000_ICR_ECCER         0x00400000 /* Uncorrectable ECC Error */
 /* If this bit asserted, the driver should claim the interrupt */
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 98e68888abb1..2311b31bdcac 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -94,10 +94,6 @@ struct e1000_info;
  */
 #define E1000_CHECK_RESET_COUNT		25
 
-#define DEFAULT_RDTR			0
-#define DEFAULT_RADV			8
-#define BURST_RDTR			0x20
-#define BURST_RADV			0x20
 #define PCICFG_DESC_RING_STATUS		0xe4
 #define FLUSH_DESC_REQUIRED		0x100
 
diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c
index b322011ec282..f457c5703d0c 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.c
+++ b/drivers/net/ethernet/intel/e1000e/mac.c
@@ -410,6 +410,9 @@ void e1000e_clear_hw_cntrs_base(struct e1000_hw *hw)
  *  Checks to see of the link status of the hardware has changed.  If a
  *  change in link status has been detected, then we read the PHY registers
  *  to get the current speed/duplex if link exists.
+ *
+ *  Returns a negative error code (-E1000_ERR_*) or 0 (link down) or 1 (link
+ *  up).
  **/
 s32 e1000e_check_for_copper_link(struct e1000_hw *hw)
 {
@@ -423,7 +426,7 @@ s32 e1000e_check_for_copper_link(struct e1000_hw *hw)
 	 * Change or Rx Sequence Error interrupt.
 	 */
 	if (!mac->get_link_status)
-		return 0;
+		return 1;
 
 	/* First we want to see if the MII Status Register reports
 	 * link.  If so, then we want to get the current speed/duplex
@@ -461,10 +464,12 @@ s32 e1000e_check_for_copper_link(struct e1000_hw *hw)
 	 * different link partner.
 	 */
 	ret_val = e1000e_config_fc_after_link_up(hw);
-	if (ret_val)
+	if (ret_val) {
 		e_dbg("Error configuring flow control\n");
+		return ret_val;
+	}
 
-	return ret_val;
+	return 1;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 327dfe5bedc0..f2f49239b015 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1071,7 +1071,8 @@ next_desc:
 }
 
 static void e1000_put_txbuf(struct e1000_ring *tx_ring,
-			    struct e1000_buffer *buffer_info)
+			    struct e1000_buffer *buffer_info,
+			    bool drop)
 {
 	struct e1000_adapter *adapter = tx_ring->adapter;
 
@@ -1085,7 +1086,10 @@ static void e1000_put_txbuf(struct e1000_ring *tx_ring,
 		buffer_info->dma = 0;
 	}
 	if (buffer_info->skb) {
-		dev_kfree_skb_any(buffer_info->skb);
+		if (drop)
+			dev_kfree_skb_any(buffer_info->skb);
+		else
+			dev_consume_skb_any(buffer_info->skb);
 		buffer_info->skb = NULL;
 	}
 	buffer_info->time_stamp = 0;
@@ -1199,7 +1203,7 @@ static void e1000e_tx_hwtstamp_work(struct work_struct *work)
 		wmb(); /* force write prior to skb_tstamp_tx */
 
 		skb_tstamp_tx(skb, &shhwtstamps);
-		dev_kfree_skb_any(skb);
+		dev_consume_skb_any(skb);
 	} else if (time_after(jiffies, adapter->tx_hwtstamp_start
 			      + adapter->tx_timeout_factor * HZ)) {
 		dev_kfree_skb_any(adapter->tx_hwtstamp_skb);
@@ -1254,7 +1258,7 @@ static bool e1000_clean_tx_irq(struct e1000_ring *tx_ring)
 				}
 			}
 
-			e1000_put_txbuf(tx_ring, buffer_info);
+			e1000_put_txbuf(tx_ring, buffer_info, false);
 			tx_desc->upper.data = 0;
 
 			i++;
@@ -1910,14 +1914,30 @@ static irqreturn_t e1000_msix_other(int __always_unused irq, void *data)
 	struct net_device *netdev = data;
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	u32 icr;
+	bool enable = true;
+
+	icr = er32(ICR);
+	if (icr & E1000_ICR_RXO) {
+		ew32(ICR, E1000_ICR_RXO);
+		enable = false;
+		/* napi poll will re-enable Other, make sure it runs */
+		if (napi_schedule_prep(&adapter->napi)) {
+			adapter->total_rx_bytes = 0;
+			adapter->total_rx_packets = 0;
+			__napi_schedule(&adapter->napi);
+		}
+	}
+	if (icr & E1000_ICR_LSC) {
+		ew32(ICR, E1000_ICR_LSC);
+		hw->mac.get_link_status = true;
+		/* guard against interrupt when we're going down */
+		if (!test_bit(__E1000_DOWN, &adapter->state))
+			mod_timer(&adapter->watchdog_timer, jiffies + 1);
+	}
 
-	hw->mac.get_link_status = true;
-
-	/* guard against interrupt when we're going down */
-	if (!test_bit(__E1000_DOWN, &adapter->state)) {
-		mod_timer(&adapter->watchdog_timer, jiffies + 1);
+	if (enable && !test_bit(__E1000_DOWN, &adapter->state))
 		ew32(IMS, E1000_IMS_OTHER);
-	}
 
 	return IRQ_HANDLED;
 }
@@ -2421,7 +2441,7 @@ static void e1000_clean_tx_ring(struct e1000_ring *tx_ring)
 
 	for (i = 0; i < tx_ring->count; i++) {
 		buffer_info = &tx_ring->buffer_info[i];
-		e1000_put_txbuf(tx_ring, buffer_info);
+		e1000_put_txbuf(tx_ring, buffer_info, false);
 	}
 
 	netdev_reset_queue(adapter->netdev);
@@ -2687,7 +2707,8 @@ static int e1000e_poll(struct napi_struct *napi, int weight)
 		napi_complete_done(napi, work_done);
 		if (!test_bit(__E1000_DOWN, &adapter->state)) {
 			if (adapter->msix_entries)
-				ew32(IMS, adapter->rx_ring->ims_val);
+				ew32(IMS, adapter->rx_ring->ims_val |
+				     E1000_IMS_OTHER);
 			else
 				e1000_irq_enable(adapter);
 		}
@@ -3004,8 +3025,8 @@ static void e1000_configure_tx(struct e1000_adapter *adapter)
 
 	hw->mac.ops.config_collision_dist(hw);
 
-	/* SPT and CNP Si errata workaround to avoid data corruption */
-	if (hw->mac.type >= e1000_pch_spt) {
+	/* SPT and KBL Si errata workaround to avoid data corruption */
+	if (hw->mac.type == e1000_pch_spt) {
 		u32 reg_val;
 
 		reg_val = er32(IOSFPC);
@@ -3013,7 +3034,9 @@ static void e1000_configure_tx(struct e1000_adapter *adapter)
 		ew32(IOSFPC, reg_val);
 
 		reg_val = er32(TARC(0));
-		reg_val |= E1000_TARC0_CB_MULTIQ_3_REQ;
+		/* SPT and KBL Si errata workaround to avoid Tx hang */
+		reg_val &= ~BIT(28);
+		reg_val |= BIT(29);
 		ew32(TARC(0), reg_val);
 	}
 }
@@ -3223,14 +3246,6 @@ static void e1000_configure_rx(struct e1000_adapter *adapter)
 		 */
 		ew32(RXDCTL(0), E1000_RXDCTL_DMA_BURST_ENABLE);
 		ew32(RXDCTL(1), E1000_RXDCTL_DMA_BURST_ENABLE);
-
-		/* override the delay timers for enabling bursting, only if
-		 * the value was not set by the user via module options
-		 */
-		if (adapter->rx_int_delay == DEFAULT_RDTR)
-			adapter->rx_int_delay = BURST_RDTR;
-		if (adapter->rx_abs_int_delay == DEFAULT_RADV)
-			adapter->rx_abs_int_delay = BURST_RADV;
 	}
 
 	/* set the Receive Delay Timer Register */
@@ -4204,7 +4219,7 @@ static void e1000e_trigger_lsc(struct e1000_adapter *adapter)
 	struct e1000_hw *hw = &adapter->hw;
 
 	if (adapter->msix_entries)
-		ew32(ICS, E1000_ICS_OTHER);
+		ew32(ICS, E1000_ICS_LSC | E1000_ICS_OTHER);
 	else
 		ew32(ICS, E1000_ICS_LSC);
 }
@@ -4808,9 +4823,9 @@ static void e1000e_update_phy_task(struct work_struct *work)
  * Need to wait a few seconds after link up to get diagnostic information from
  * the phy
  **/
-static void e1000_update_phy_info(unsigned long data)
+static void e1000_update_phy_info(struct timer_list *t)
 {
-	struct e1000_adapter *adapter = (struct e1000_adapter *)data;
+	struct e1000_adapter *adapter = from_timer(adapter, t, phy_info_timer);
 
 	if (test_bit(__E1000_DOWN, &adapter->state))
 		return;
@@ -5074,14 +5089,14 @@ static bool e1000e_has_link(struct e1000_adapter *adapter)
 
 	/* get_link_status is set on LSC (link status) interrupt or
 	 * Rx sequence error interrupt.  get_link_status will stay
-	 * false until the check_for_link establishes link
+	 * true until the check_for_link establishes link
 	 * for copper adapters ONLY
 	 */
 	switch (hw->phy.media_type) {
 	case e1000_media_type_copper:
 		if (hw->mac.get_link_status) {
 			ret_val = hw->mac.ops.check_for_link(hw);
-			link_active = !hw->mac.get_link_status;
+			link_active = ret_val > 0;
 		} else {
 			link_active = true;
 		}
@@ -5092,14 +5107,14 @@ static bool e1000e_has_link(struct e1000_adapter *adapter)
 		break;
 	case e1000_media_type_internal_serdes:
 		ret_val = hw->mac.ops.check_for_link(hw);
-		link_active = adapter->hw.mac.serdes_has_link;
+		link_active = hw->mac.serdes_has_link;
 		break;
 	default:
 	case e1000_media_type_unknown:
 		break;
 	}
 
-	if ((ret_val == E1000_ERR_PHY) && (hw->phy.type == e1000_phy_igp_3) &&
+	if ((ret_val == -E1000_ERR_PHY) && (hw->phy.type == e1000_phy_igp_3) &&
 	    (er32(CTRL) & E1000_PHY_CTRL_GBE_DISABLE)) {
 		/* See e1000_kmrn_lock_loss_workaround_ich8lan() */
 		e_info("Gigabit has been disabled, downgrading speed\n");
@@ -5144,9 +5159,9 @@ static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter)
  * e1000_watchdog - Timer Call-back
  * @data: pointer to adapter cast into an unsigned long
  **/
-static void e1000_watchdog(unsigned long data)
+static void e1000_watchdog(struct timer_list *t)
 {
-	struct e1000_adapter *adapter = (struct e1000_adapter *)data;
+	struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer);
 
 	/* Do the rest outside of interrupt context */
 	schedule_work(&adapter->watchdog_task);
@@ -5614,7 +5629,7 @@ dma_error:
 			i += tx_ring->count;
 		i--;
 		buffer_info = &tx_ring->buffer_info[i];
-		e1000_put_txbuf(tx_ring, buffer_info);
+		e1000_put_txbuf(tx_ring, buffer_info, true);
 	}
 
 	return 0;
@@ -7252,13 +7267,8 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_eeprom;
 	}
 
-	init_timer(&adapter->watchdog_timer);
-	adapter->watchdog_timer.function = e1000_watchdog;
-	adapter->watchdog_timer.data = (unsigned long)adapter;
-
-	init_timer(&adapter->phy_info_timer);
-	adapter->phy_info_timer.function = e1000_update_phy_info;
-	adapter->phy_info_timer.data = (unsigned long)adapter;
+	timer_setup(&adapter->watchdog_timer, e1000_watchdog, 0);
+	timer_setup(&adapter->phy_info_timer, e1000_update_phy_info, 0);
 
 	INIT_WORK(&adapter->reset_task, e1000_reset_task);
 	INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task);
@@ -7411,7 +7421,7 @@ static void e1000_remove(struct pci_dev *pdev)
 	if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) {
 		cancel_work_sync(&adapter->tx_hwtstamp_work);
 		if (adapter->tx_hwtstamp_skb) {
-			dev_kfree_skb_any(adapter->tx_hwtstamp_skb);
+			dev_consume_skb_any(adapter->tx_hwtstamp_skb);
 			adapter->tx_hwtstamp_skb = NULL;
 		}
 	}
diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c
index 6d8c39abee16..47da51864543 100644
--- a/drivers/net/ethernet/intel/e1000e/param.c
+++ b/drivers/net/ethernet/intel/e1000e/param.c
@@ -73,17 +73,25 @@ E1000_PARAM(TxAbsIntDelay, "Transmit Absolute Interrupt Delay");
 /* Receive Interrupt Delay in units of 1.024 microseconds
  * hardware will likely hang if you set this to anything but zero.
  *
+ * Burst variant is used as default if device has FLAG2_DMA_BURST.
+ *
  * Valid Range: 0-65535
  */
 E1000_PARAM(RxIntDelay, "Receive Interrupt Delay");
+#define DEFAULT_RDTR	0
+#define BURST_RDTR	0x20
 #define MAX_RXDELAY 0xFFFF
 #define MIN_RXDELAY 0
 
 /* Receive Absolute Interrupt Delay in units of 1.024 microseconds
  *
+ * Burst variant is used as default if device has FLAG2_DMA_BURST.
+ *
  * Valid Range: 0-65535
  */
 E1000_PARAM(RxAbsIntDelay, "Receive Absolute Interrupt Delay");
+#define DEFAULT_RADV	8
+#define BURST_RADV	0x20
 #define MAX_RXABSDELAY 0xFFFF
 #define MIN_RXABSDELAY 0
 
@@ -297,6 +305,9 @@ void e1000e_check_options(struct e1000_adapter *adapter)
 					 .max = MAX_RXDELAY } }
 		};
 
+		if (adapter->flags2 & FLAG2_DMA_BURST)
+			opt.def = BURST_RDTR;
+
 		if (num_RxIntDelay > bd) {
 			adapter->rx_int_delay = RxIntDelay[bd];
 			e1000_validate_option(&adapter->rx_int_delay, &opt,
@@ -307,7 +318,7 @@ void e1000e_check_options(struct e1000_adapter *adapter)
 	}
 	/* Receive Absolute Interrupt Delay */
 	{
-		static const struct e1000_option opt = {
+		static struct e1000_option opt = {
 			.type = range_option,
 			.name = "Receive Absolute Interrupt Delay",
 			.err  = "using default of "
@@ -317,6 +328,9 @@ void e1000e_check_options(struct e1000_adapter *adapter)
 					 .max = MAX_RXABSDELAY } }
 		};
 
+		if (adapter->flags2 & FLAG2_DMA_BURST)
+			opt.def = BURST_RADV;
+
 		if (num_RxAbsIntDelay > bd) {
 			adapter->rx_abs_int_delay = RxAbsIntDelay[bd];
 			e1000_validate_option(&adapter->rx_abs_int_delay, &opt,
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index d78d47b41a71..86ff0969efb6 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -1744,6 +1744,7 @@ s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations,
 	s32 ret_val = 0;
 	u16 i, phy_status;
 
+	*success = false;
 	for (i = 0; i < iterations; i++) {
 		/* Some PHYs require the MII_BMSR register to be read
 		 * twice due to the link bit being sticky.  No harm doing
@@ -1763,16 +1764,16 @@ s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations,
 		ret_val = e1e_rphy(hw, MII_BMSR, &phy_status);
 		if (ret_val)
 			break;
-		if (phy_status & BMSR_LSTATUS)
+		if (phy_status & BMSR_LSTATUS) {
+			*success = true;
 			break;
+		}
 		if (usec_interval >= 1000)
 			msleep(usec_interval / 1000);
 		else
 			udelay(usec_interval);
 	}
 
-	*success = (i < iterations);
-
 	return ret_val;
 }
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
index 689c413b7782..46973fb234c5 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -248,6 +248,29 @@ struct fm10k_udp_port {
 	__be16			port;
 };
 
+enum fm10k_macvlan_request_type {
+	FM10K_UC_MAC_REQUEST,
+	FM10K_MC_MAC_REQUEST,
+	FM10K_VLAN_REQUEST
+};
+
+struct fm10k_macvlan_request {
+	enum fm10k_macvlan_request_type type;
+	struct list_head list;
+	union {
+		struct fm10k_mac_request {
+			u8 addr[ETH_ALEN];
+			u16 glort;
+			u16 vid;
+		} mac;
+		struct fm10k_vlan_request {
+			u32 vid;
+			u8 vsi;
+		} vlan;
+	};
+	bool set;
+};
+
 /* one work queue for entire driver */
 extern struct workqueue_struct *fm10k_workqueue;
 
@@ -270,11 +293,15 @@ enum fm10k_flags_t {
 
 enum fm10k_state_t {
 	__FM10K_RESETTING,
+	__FM10K_RESET_DETACHED,
+	__FM10K_RESET_SUSPENDED,
 	__FM10K_DOWN,
 	__FM10K_SERVICE_SCHED,
 	__FM10K_SERVICE_REQUEST,
 	__FM10K_SERVICE_DISABLE,
-	__FM10K_MBX_LOCK,
+	__FM10K_MACVLAN_SCHED,
+	__FM10K_MACVLAN_REQUEST,
+	__FM10K_MACVLAN_DISABLE,
 	__FM10K_LINK_DOWN,
 	__FM10K_UPDATING_STATS,
 	/* This value must be last and determines the BITMAP size */
@@ -344,6 +371,8 @@ struct fm10k_intfc {
 
 	struct fm10k_hw_stats stats;
 	struct fm10k_hw hw;
+	/* Mailbox lock */
+	spinlock_t mbx_lock;
 	u32 __iomem *uc_addr;
 	u32 __iomem *sw_addr;
 	u16 msg_enable;
@@ -365,6 +394,12 @@ struct fm10k_intfc {
 	struct list_head vxlan_port;
 	struct list_head geneve_port;
 
+	/* MAC/VLAN update queue */
+	struct list_head macvlan_requests;
+	struct delayed_work macvlan_task;
+	/* MAC/VLAN update queue lock */
+	spinlock_t macvlan_lock;
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dbg_intfc;
 #endif /* CONFIG_DEBUG_FS */
@@ -384,23 +419,17 @@ struct fm10k_intfc {
 
 static inline void fm10k_mbx_lock(struct fm10k_intfc *interface)
 {
-	/* busy loop if we cannot obtain the lock as some calls
-	 * such as ndo_set_rx_mode may be made in atomic context
-	 */
-	while (test_and_set_bit(__FM10K_MBX_LOCK, interface->state))
-		udelay(20);
+	spin_lock(&interface->mbx_lock);
 }
 
 static inline void fm10k_mbx_unlock(struct fm10k_intfc *interface)
 {
-	/* flush memory to make sure state is correct */
-	smp_mb__before_atomic();
-	clear_bit(__FM10K_MBX_LOCK, interface->state);
+	spin_unlock(&interface->mbx_lock);
 }
 
 static inline int fm10k_mbx_trylock(struct fm10k_intfc *interface)
 {
-	return !test_and_set_bit(__FM10K_MBX_LOCK, interface->state);
+	return spin_trylock(&interface->mbx_lock);
 }
 
 /* fm10k_test_staterr - test bits in Rx descriptor status and error fields */
@@ -490,6 +519,7 @@ void fm10k_up(struct fm10k_intfc *interface);
 void fm10k_down(struct fm10k_intfc *interface);
 void fm10k_update_stats(struct fm10k_intfc *interface);
 void fm10k_service_event_schedule(struct fm10k_intfc *interface);
+void fm10k_macvlan_schedule(struct fm10k_intfc *interface);
 void fm10k_update_rx_drop_en(struct fm10k_intfc *interface);
 #ifdef CONFIG_NET_POLL_CONTROLLER
 void fm10k_netpoll(struct net_device *netdev);
@@ -510,6 +540,12 @@ void fm10k_reset_rx_state(struct fm10k_intfc *);
 int fm10k_setup_tc(struct net_device *dev, u8 tc);
 int fm10k_open(struct net_device *netdev);
 int fm10k_close(struct net_device *netdev);
+int fm10k_queue_vlan_request(struct fm10k_intfc *interface, u32 vid,
+			     u8 vsi, bool set);
+int fm10k_queue_mac_request(struct fm10k_intfc *interface, u16 glort,
+			    const unsigned char *addr, u16 vid, bool set);
+void fm10k_clear_macvlan_queue(struct fm10k_intfc *interface,
+			       u16 glort, bool vlans);
 
 /* Ethtool */
 void fm10k_set_ethtool_ops(struct net_device *dev);
@@ -526,8 +562,8 @@ s32 fm10k_iov_update_pvid(struct fm10k_intfc *interface, u16 glort, u16 pvid);
 int fm10k_ndo_set_vf_mac(struct net_device *netdev, int vf_idx, u8 *mac);
 int fm10k_ndo_set_vf_vlan(struct net_device *netdev,
 			  int vf_idx, u16 vid, u8 qos, __be16 vlan_proto);
-int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx, int rate,
-			int unused);
+int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx,
+			int __always_unused min_rate, int max_rate);
 int fm10k_ndo_get_vf_config(struct net_device *netdev,
 			    int vf_idx, struct ifla_vf_info *ivi);
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.c b/drivers/net/ethernet/intel/fm10k/fm10k_common.c
index 62a6ad9b3eed..736a9f087bc9 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_common.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.c
@@ -1,5 +1,5 @@
 /* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -517,8 +517,8 @@ s32 fm10k_get_host_state_generic(struct fm10k_hw *hw, bool *host_ready)
 		goto out;
 	}
 
-	/* verify Mailbox is still valid */
-	if (!mbx->ops.tx_ready(mbx, FM10K_VFMBX_MSG_MTU))
+	/* verify Mailbox is still open */
+	if (mbx->state != FM10K_STATE_OPEN)
 		goto out;
 
 	/* interface cannot receive traffic without logical ports */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c
index 5116fd043630..14df09e2d964 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c
@@ -52,9 +52,9 @@ static void fm10k_dbg_desc_seq_stop(struct seq_file __always_unused *s,
 static void fm10k_dbg_desc_break(struct seq_file *s, int i)
 {
 	while (i--)
-		seq_puts(s, "-");
+		seq_putc(s, '-');
 
-	seq_puts(s, "\n");
+	seq_putc(s, '\n');
 }
 
 static int fm10k_dbg_tx_desc_seq_show(struct seq_file *s, void *v)
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
index 5f4dac0d36ef..ea3ab24265ee 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
@@ -1,5 +1,5 @@
 /* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -35,10 +35,133 @@ static s32 fm10k_iov_msg_error(struct fm10k_hw *hw, u32 **results,
 	return fm10k_tlv_msg_error(hw, results, mbx);
 }
 
+/**
+ *  fm10k_iov_msg_queue_mac_vlan - Message handler for MAC/VLAN request from VF
+ *  @hw: Pointer to hardware structure
+ *  @results: Pointer array to message, results[0] is pointer to message
+ *  @mbx: Pointer to mailbox information structure
+ *
+ *  This function is a custom handler for MAC/VLAN requests from the VF. The
+ *  assumption is that it is acceptable to directly hand off the message from
+ *  the VF to the PF's switch manager. However, we use a MAC/VLAN message
+ *  queue to avoid overloading the mailbox when a large number of requests
+ *  come in.
+ **/
+static s32 fm10k_iov_msg_queue_mac_vlan(struct fm10k_hw *hw, u32 **results,
+					struct fm10k_mbx_info *mbx)
+{
+	struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx;
+	struct fm10k_intfc *interface = hw->back;
+	u8 mac[ETH_ALEN];
+	u32 *result;
+	int err = 0;
+	bool set;
+	u16 vlan;
+	u32 vid;
+
+	/* we shouldn't be updating rules on a disabled interface */
+	if (!FM10K_VF_FLAG_ENABLED(vf_info))
+		err = FM10K_ERR_PARAM;
+
+	if (!err && !!results[FM10K_MAC_VLAN_MSG_VLAN]) {
+		result = results[FM10K_MAC_VLAN_MSG_VLAN];
+
+		/* record VLAN id requested */
+		err = fm10k_tlv_attr_get_u32(result, &vid);
+		if (err)
+			return err;
+
+		set = !(vid & FM10K_VLAN_CLEAR);
+		vid &= ~FM10K_VLAN_CLEAR;
+
+		/* if the length field has been set, this is a multi-bit
+		 * update request. For multi-bit requests, simply disallow
+		 * them when the pf_vid has been set. In this case, the PF
+		 * should have already cleared the VLAN_TABLE, and if we
+		 * allowed them, it could allow a rogue VF to receive traffic
+		 * on a VLAN it was not assigned. In the single-bit case, we
+		 * need to modify requests for VLAN 0 to use the default PF or
+		 * SW vid when assigned.
+		 */
+
+		if (vid >> 16) {
+			/* prevent multi-bit requests when PF has
+			 * administratively set the VLAN for this VF
+			 */
+			if (vf_info->pf_vid)
+				return FM10K_ERR_PARAM;
+		} else {
+			err = fm10k_iov_select_vid(vf_info, (u16)vid);
+			if (err < 0)
+				return err;
+
+			vid = err;
+		}
+
+		/* update VSI info for VF in regards to VLAN table */
+		err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set);
+	}
+
+	if (!err && !!results[FM10K_MAC_VLAN_MSG_MAC]) {
+		result = results[FM10K_MAC_VLAN_MSG_MAC];
+
+		/* record unicast MAC address requested */
+		err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
+		if (err)
+			return err;
+
+		/* block attempts to set MAC for a locked device */
+		if (is_valid_ether_addr(vf_info->mac) &&
+		    !ether_addr_equal(mac, vf_info->mac))
+			return FM10K_ERR_PARAM;
+
+		set = !(vlan & FM10K_VLAN_CLEAR);
+		vlan &= ~FM10K_VLAN_CLEAR;
+
+		err = fm10k_iov_select_vid(vf_info, vlan);
+		if (err < 0)
+			return err;
+
+		vlan = (u16)err;
+
+		/* Add this request to the MAC/VLAN queue */
+		err = fm10k_queue_mac_request(interface, vf_info->glort,
+					      mac, vlan, set);
+	}
+
+	if (!err && !!results[FM10K_MAC_VLAN_MSG_MULTICAST]) {
+		result = results[FM10K_MAC_VLAN_MSG_MULTICAST];
+
+		/* record multicast MAC address requested */
+		err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
+		if (err)
+			return err;
+
+		/* verify that the VF is allowed to request multicast */
+		if (!(vf_info->vf_flags & FM10K_VF_FLAG_MULTI_ENABLED))
+			return FM10K_ERR_PARAM;
+
+		set = !(vlan & FM10K_VLAN_CLEAR);
+		vlan &= ~FM10K_VLAN_CLEAR;
+
+		err = fm10k_iov_select_vid(vf_info, vlan);
+		if (err < 0)
+			return err;
+
+		vlan = (u16)err;
+
+		/* Add this request to the MAC/VLAN queue */
+		err = fm10k_queue_mac_request(interface, vf_info->glort,
+					      mac, vlan, set);
+	}
+
+	return err;
+}
+
 static const struct fm10k_msg_data iov_mbx_data[] = {
 	FM10K_TLV_MSG_TEST_HANDLER(fm10k_tlv_msg_test),
 	FM10K_VF_MSG_MSIX_HANDLER(fm10k_iov_msg_msix_pf),
-	FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_iov_msg_mac_vlan_pf),
+	FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_iov_msg_queue_mac_vlan),
 	FM10K_VF_MSG_LPORT_STATE_HANDLER(fm10k_iov_msg_lport_state_pf),
 	FM10K_TLV_MSG_ERROR_HANDLER(fm10k_iov_msg_error),
 };
@@ -66,25 +189,21 @@ s32 fm10k_iov_event(struct fm10k_intfc *interface)
 		goto read_unlock;
 
 	/* read VFLRE to determine if any VFs have been reset */
-	do {
-		vflre = fm10k_read_reg(hw, FM10K_PFVFLRE(0));
-		vflre <<= 32;
-		vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(1));
-		vflre = (vflre << 32) | (vflre >> 32);
-		vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(0));
+	vflre = fm10k_read_reg(hw, FM10K_PFVFLRE(1));
+	vflre <<= 32;
+	vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(0));
 
-		i = iov_data->num_vfs;
+	i = iov_data->num_vfs;
 
-		for (vflre <<= 64 - i; vflre && i--; vflre += vflre) {
-			struct fm10k_vf_info *vf_info = &iov_data->vf_info[i];
+	for (vflre <<= 64 - i; vflre && i--; vflre += vflre) {
+		struct fm10k_vf_info *vf_info = &iov_data->vf_info[i];
 
-			if (vflre >= 0)
-				continue;
+		if (vflre >= 0)
+			continue;
 
-			hw->iov.ops.reset_resources(hw, vf_info);
-			vf_info->mbx.ops.connect(hw, &vf_info->mbx);
-		}
-	} while (i != iov_data->num_vfs);
+		hw->iov.ops.reset_resources(hw, vf_info);
+		vf_info->mbx.ops.connect(hw, &vf_info->mbx);
+	}
 
 read_unlock:
 	rcu_read_unlock();
@@ -126,9 +245,14 @@ process_mbx:
 		struct fm10k_mbx_info *mbx = &vf_info->mbx;
 		u16 glort = vf_info->glort;
 
+		/* process the SM mailbox first to drain outgoing messages */
+		hw->mbx.ops.process(hw, &hw->mbx);
+
 		/* verify port mapping is valid, if not reset port */
-		if (vf_info->vf_flags && !fm10k_glort_valid_pf(hw, glort))
+		if (vf_info->vf_flags && !fm10k_glort_valid_pf(hw, glort)) {
 			hw->iov.ops.reset_lport(hw, vf_info);
+			fm10k_clear_macvlan_queue(interface, glort, false);
+		}
 
 		/* reset VFs that have mailbox timed out */
 		if (!mbx->timeout) {
@@ -140,6 +264,10 @@ process_mbx:
 		if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU)) {
 			/* keep track of how many times this occurs */
 			interface->hw_sm_mbx_full++;
+
+			/* make sure we try again momentarily */
+			fm10k_service_event_schedule(interface);
+
 			break;
 		}
 
@@ -187,6 +315,7 @@ void fm10k_iov_suspend(struct pci_dev *pdev)
 
 		hw->iov.ops.reset_resources(hw, vf_info);
 		hw->iov.ops.reset_lport(hw, vf_info);
+		fm10k_clear_macvlan_queue(interface, vf_info->glort, false);
 	}
 }
 
@@ -411,6 +540,8 @@ static inline void fm10k_reset_vf_info(struct fm10k_intfc *interface,
 	/* disable LPORT for this VF which clears switch rules */
 	hw->iov.ops.reset_lport(hw, vf_info);
 
+	fm10k_clear_macvlan_queue(interface, vf_info->glort, false);
+
 	/* assign new MAC+VLAN for this VF */
 	hw->iov.ops.assign_default_mac_vlan(hw, vf_info);
 
@@ -482,7 +613,7 @@ int fm10k_ndo_set_vf_vlan(struct net_device *netdev, int vf_idx, u16 vid,
 }
 
 int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx,
-			int __always_unused unused, int rate)
+			int __always_unused min_rate, int max_rate)
 {
 	struct fm10k_intfc *interface = netdev_priv(netdev);
 	struct fm10k_iov_data *iov_data = interface->iov_data;
@@ -493,14 +624,15 @@ int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx,
 		return -EINVAL;
 
 	/* rate limit cannot be less than 10Mbs or greater than link speed */
-	if (rate && ((rate < FM10K_VF_TC_MIN) || rate > FM10K_VF_TC_MAX))
+	if (max_rate &&
+	    (max_rate < FM10K_VF_TC_MIN || max_rate > FM10K_VF_TC_MAX))
 		return -EINVAL;
 
 	/* store values */
-	iov_data->vf_info[vf_idx].rate = rate;
+	iov_data->vf_info[vf_idx].rate = max_rate;
 
 	/* update hardware configuration */
-	hw->iov.ops.configure_tc(hw, vf_idx, rate);
+	hw->iov.ops.configure_tc(hw, vf_idx, max_rate);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 9dffaba85ae6..dbd69310f263 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -28,7 +28,7 @@
 
 #include "fm10k.h"
 
-#define DRV_VERSION	"0.21.7-k"
+#define DRV_VERSION	"0.22.1-k"
 #define DRV_SUMMARY	"Intel(R) Ethernet Switch Host Interface Driver"
 const char fm10k_driver_version[] = DRV_VERSION;
 char fm10k_driver_name[] = "fm10k";
@@ -806,9 +806,10 @@ static int fm10k_tso(struct fm10k_ring *tx_ring,
 	tx_desc->mss = cpu_to_le16(skb_shinfo(skb)->gso_size);
 
 	return 1;
+
 err_vxlan:
 	tx_ring->netdev->features &= ~NETIF_F_GSO_UDP_TUNNEL;
-	if (!net_ratelimit())
+	if (net_ratelimit())
 		netdev_err(tx_ring->netdev,
 			   "TSO requested for unsupported tunnel, disabling offload\n");
 	return -1;
@@ -876,6 +877,7 @@ static void fm10k_tx_csum(struct fm10k_ring *tx_ring,
 	case IPPROTO_GRE:
 		if (skb->encapsulation)
 			break;
+		/* fall through */
 	default:
 		if (unlikely(net_ratelimit())) {
 			dev_warn(tx_ring->dev,
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
index 334088a101c3..244d3ad58ca7 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
@@ -1,5 +1,5 @@
 /* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -1586,7 +1586,7 @@ s32 fm10k_pfvf_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx,
 			mbx->mbmem_reg = FM10K_MBMEM_VF(id, 0);
 			break;
 		}
-		/* fallthough */
+		/* fall through */
 	default:
 		return FM10K_MBX_ERR_NO_MBX;
 	}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index e69d49d91d67..81e4425f0529 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -643,9 +643,13 @@ int fm10k_close(struct net_device *netdev)
 static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 {
 	struct fm10k_intfc *interface = netdev_priv(dev);
+	int num_tx_queues = READ_ONCE(interface->num_tx_queues);
 	unsigned int r_idx = skb->queue_mapping;
 	int err;
 
+	if (!num_tx_queues)
+		return NETDEV_TX_BUSY;
+
 	if ((skb->protocol == htons(ETH_P_8021Q)) &&
 	    !skb_vlan_tag_present(skb)) {
 		/* FM10K only supports hardware tagging, any tags in frame
@@ -698,8 +702,8 @@ static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 		__skb_put(skb, pad_len);
 	}
 
-	if (r_idx >= interface->num_tx_queues)
-		r_idx %= interface->num_tx_queues;
+	if (r_idx >= num_tx_queues)
+		r_idx %= num_tx_queues;
 
 	err = fm10k_xmit_frame_ring(skb, interface->tx_ring[r_idx]);
 
@@ -754,11 +758,132 @@ static bool fm10k_host_mbx_ready(struct fm10k_intfc *interface)
 	return (hw->mac.type == fm10k_mac_vf || interface->host_ready);
 }
 
+/**
+ * fm10k_queue_vlan_request - Queue a VLAN update request
+ * @interface: the fm10k interface structure
+ * @vid: the VLAN vid
+ * @vsi: VSI index number
+ * @set: whether to set or clear
+ *
+ * This function queues up a VLAN update. For VFs, this must be sent to the
+ * managing PF over the mailbox. For PFs, we'll use the same handling so that
+ * it's similar to the VF. This avoids storming the PF<->VF mailbox with too
+ * many VLAN updates during reset.
+ */
+int fm10k_queue_vlan_request(struct fm10k_intfc *interface,
+			     u32 vid, u8 vsi, bool set)
+{
+	struct fm10k_macvlan_request *request;
+	unsigned long flags;
+
+	/* This must be atomic since we may be called while the netdev
+	 * addr_list_lock is held
+	 */
+	request = kzalloc(sizeof(*request), GFP_ATOMIC);
+	if (!request)
+		return -ENOMEM;
+
+	request->type = FM10K_VLAN_REQUEST;
+	request->vlan.vid = vid;
+	request->vlan.vsi = vsi;
+	request->set = set;
+
+	spin_lock_irqsave(&interface->macvlan_lock, flags);
+	list_add_tail(&request->list, &interface->macvlan_requests);
+	spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+
+	fm10k_macvlan_schedule(interface);
+
+	return 0;
+}
+
+/**
+ * fm10k_queue_mac_request - Queue a MAC update request
+ * @interface: the fm10k interface structure
+ * @glort: the target glort for this update
+ * @addr: the address to update
+ * @vid: the vid to update
+ * @sync: whether to add or remove
+ *
+ * This function queues up a MAC request for sending to the switch manager.
+ * A separate thread monitors the queue and sends updates to the switch
+ * manager. Return 0 on success, and negative error code on failure.
+ **/
+int fm10k_queue_mac_request(struct fm10k_intfc *interface, u16 glort,
+			    const unsigned char *addr, u16 vid, bool set)
+{
+	struct fm10k_macvlan_request *request;
+	unsigned long flags;
+
+	/* This must be atomic since we may be called while the netdev
+	 * addr_list_lock is held
+	 */
+	request = kzalloc(sizeof(*request), GFP_ATOMIC);
+	if (!request)
+		return -ENOMEM;
+
+	if (is_multicast_ether_addr(addr))
+		request->type = FM10K_MC_MAC_REQUEST;
+	else
+		request->type = FM10K_UC_MAC_REQUEST;
+
+	ether_addr_copy(request->mac.addr, addr);
+	request->mac.glort = glort;
+	request->mac.vid = vid;
+	request->set = set;
+
+	spin_lock_irqsave(&interface->macvlan_lock, flags);
+	list_add_tail(&request->list, &interface->macvlan_requests);
+	spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+
+	fm10k_macvlan_schedule(interface);
+
+	return 0;
+}
+
+/**
+ * fm10k_clear_macvlan_queue - Cancel pending updates for a given glort
+ * @interface: the fm10k interface structure
+ * @glort: the target glort to clear
+ * @vlans: true to clear VLAN messages, false to ignore them
+ *
+ * Cancel any outstanding MAC/VLAN requests for a given glort. This is
+ * expected to be called when a logical port goes down.
+ **/
+void fm10k_clear_macvlan_queue(struct fm10k_intfc *interface,
+			       u16 glort, bool vlans)
+
+{
+	struct fm10k_macvlan_request *r, *tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&interface->macvlan_lock, flags);
+
+	/* Free any outstanding MAC/VLAN requests for this interface */
+	list_for_each_entry_safe(r, tmp, &interface->macvlan_requests, list) {
+		switch (r->type) {
+		case FM10K_MC_MAC_REQUEST:
+		case FM10K_UC_MAC_REQUEST:
+			/* Don't free requests for other interfaces */
+			if (r->mac.glort != glort)
+				break;
+			/* fall through */
+		case FM10K_VLAN_REQUEST:
+			if (vlans) {
+				list_del(&r->list);
+				kfree(r);
+			}
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+}
+
 static int fm10k_uc_vlan_unsync(struct net_device *netdev,
 				const unsigned char *uc_addr)
 {
 	struct fm10k_intfc *interface = netdev_priv(netdev);
-	struct fm10k_hw *hw = &interface->hw;
 	u16 glort = interface->glort;
 	u16 vid = interface->vid;
 	bool set = !!(vid / VLAN_N_VID);
@@ -767,10 +892,7 @@ static int fm10k_uc_vlan_unsync(struct net_device *netdev,
 	/* drop any leading bits on the VLAN ID */
 	vid &= VLAN_N_VID - 1;
 
-	if (fm10k_host_mbx_ready(interface))
-		err = hw->mac.ops.update_uc_addr(hw, glort, uc_addr,
-						 vid, set, 0);
-
+	err = fm10k_queue_mac_request(interface, glort, uc_addr, vid, set);
 	if (err)
 		return err;
 
@@ -782,7 +904,6 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev,
 				const unsigned char *mc_addr)
 {
 	struct fm10k_intfc *interface = netdev_priv(netdev);
-	struct fm10k_hw *hw = &interface->hw;
 	u16 glort = interface->glort;
 	u16 vid = interface->vid;
 	bool set = !!(vid / VLAN_N_VID);
@@ -791,9 +912,7 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev,
 	/* drop any leading bits on the VLAN ID */
 	vid &= VLAN_N_VID - 1;
 
-	if (fm10k_host_mbx_ready(interface))
-		err = hw->mac.ops.update_mc_addr(hw, glort, mc_addr, vid, set);
-
+	err = fm10k_queue_mac_request(interface, glort, mc_addr, vid, set);
 	if (err)
 		return err;
 
@@ -851,18 +970,14 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set)
 
 	/* only need to update the VLAN if not in promiscuous mode */
 	if (!(netdev->flags & IFF_PROMISC)) {
-		err = hw->mac.ops.update_vlan(hw, vid, 0, set);
+		err = fm10k_queue_vlan_request(interface, vid, 0, set);
 		if (err)
 			goto err_out;
 	}
 
-	/* update our base MAC address if host's mailbox is ready */
-	if (fm10k_host_mbx_ready(interface))
-		err = hw->mac.ops.update_uc_addr(hw, interface->glort,
-						 hw->mac.addr, vid, set, 0);
-	else
-		err = -EHOSTDOWN;
-
+	/* Update our base MAC address */
+	err = fm10k_queue_mac_request(interface, interface->glort,
+				      hw->mac.addr, vid, set);
 	if (err)
 		goto err_out;
 
@@ -906,7 +1021,6 @@ static u16 fm10k_find_next_vlan(struct fm10k_intfc *interface, u16 vid)
 
 static void fm10k_clear_unused_vlans(struct fm10k_intfc *interface)
 {
-	struct fm10k_hw *hw = &interface->hw;
 	u32 vid, prev_vid;
 
 	/* loop through and find any gaps in the table */
@@ -918,7 +1032,7 @@ static void fm10k_clear_unused_vlans(struct fm10k_intfc *interface)
 
 		/* send request to clear multiple bits at a time */
 		prev_vid += (vid - prev_vid - 1) << FM10K_VLAN_LENGTH_SHIFT;
-		hw->mac.ops.update_vlan(hw, prev_vid, 0, false);
+		fm10k_queue_vlan_request(interface, prev_vid, 0, false);
 	}
 }
 
@@ -933,15 +1047,11 @@ static int __fm10k_uc_sync(struct net_device *dev,
 	if (!is_valid_ether_addr(addr))
 		return -EADDRNOTAVAIL;
 
-	/* update table with current entries if host's mailbox is ready */
-	if (!fm10k_host_mbx_ready(interface))
-		return -EHOSTDOWN;
-
 	for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1;
 	     vid < VLAN_N_VID;
 	     vid = fm10k_find_next_vlan(interface, vid)) {
-		err = hw->mac.ops.update_uc_addr(hw, glort, addr,
-						 vid, sync, 0);
+		err = fm10k_queue_mac_request(interface, glort,
+					      addr, vid, sync);
 		if (err)
 			return err;
 	}
@@ -998,15 +1108,18 @@ static int __fm10k_mc_sync(struct net_device *dev,
 	struct fm10k_intfc *interface = netdev_priv(dev);
 	struct fm10k_hw *hw = &interface->hw;
 	u16 vid, glort = interface->glort;
+	s32 err;
 
-	/* update table with current entries if host's mailbox is ready */
-	if (!fm10k_host_mbx_ready(interface))
-		return 0;
+	if (!is_multicast_ether_addr(addr))
+		return -EADDRNOTAVAIL;
 
 	for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1;
 	     vid < VLAN_N_VID;
 	     vid = fm10k_find_next_vlan(interface, vid)) {
-		hw->mac.ops.update_mc_addr(hw, glort, addr, vid, sync);
+		err = fm10k_queue_mac_request(interface, glort,
+					      addr, vid, sync);
+		if (err)
+			return err;
 	}
 
 	return 0;
@@ -1046,7 +1159,8 @@ static void fm10k_set_rx_mode(struct net_device *dev)
 	if (interface->xcast_mode != xcast_mode) {
 		/* update VLAN table */
 		if (xcast_mode == FM10K_XCAST_MODE_PROMISC)
-			hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, 0, true);
+			fm10k_queue_vlan_request(interface, FM10K_VLAN_ALL,
+						 0, true);
 		if (interface->xcast_mode == FM10K_XCAST_MODE_PROMISC)
 			fm10k_clear_unused_vlans(interface);
 
@@ -1094,22 +1208,20 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface)
 					       interface->glort_count, true);
 
 	/* update VLAN table */
-	hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, 0,
-				xcast_mode == FM10K_XCAST_MODE_PROMISC);
+	fm10k_queue_vlan_request(interface, FM10K_VLAN_ALL, 0,
+				 xcast_mode == FM10K_XCAST_MODE_PROMISC);
 
 	/* Add filter for VLAN 0 */
-	hw->mac.ops.update_vlan(hw, 0, 0, true);
+	fm10k_queue_vlan_request(interface, 0, 0, true);
 
 	/* update table with current entries */
 	for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1;
 	     vid < VLAN_N_VID;
 	     vid = fm10k_find_next_vlan(interface, vid)) {
-		hw->mac.ops.update_vlan(hw, vid, 0, true);
+		fm10k_queue_vlan_request(interface, vid, 0, true);
 
-		/* Update unicast entries if host's mailbox is ready */
-		if (fm10k_host_mbx_ready(interface))
-			hw->mac.ops.update_uc_addr(hw, glort, hw->mac.addr,
-						   vid, true, 0);
+		fm10k_queue_mac_request(interface, glort,
+					hw->mac.addr, vid, true);
 	}
 
 	/* update xcast mode before synchronizing addresses if host's mailbox
@@ -1136,6 +1248,13 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface)
 	struct net_device *netdev = interface->netdev;
 	struct fm10k_hw *hw = &interface->hw;
 
+	/* Wait for MAC/VLAN work to finish */
+	while (test_bit(__FM10K_MACVLAN_SCHED, interface->state))
+		usleep_range(1000, 2000);
+
+	/* Cancel pending MAC/VLAN requests */
+	fm10k_clear_macvlan_queue(interface, interface->glort, true);
+
 	fm10k_mbx_lock(interface);
 
 	/* clear the logical port state on lower device if host's mailbox is
@@ -1370,8 +1489,8 @@ static void *fm10k_dfwd_add_station(struct net_device *dev,
 	if (fm10k_host_mbx_ready(interface)) {
 		hw->mac.ops.update_xcast_mode(hw, glort,
 					      FM10K_XCAST_MODE_MULTI);
-		hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr,
-					   0, true, 0);
+		fm10k_queue_mac_request(interface, glort, sdev->dev_addr,
+					0, true);
 	}
 
 	fm10k_mbx_unlock(interface);
@@ -1410,8 +1529,8 @@ static void fm10k_dfwd_del_station(struct net_device *dev, void *priv)
 	if (fm10k_host_mbx_ready(interface)) {
 		hw->mac.ops.update_xcast_mode(hw, glort,
 					      FM10K_XCAST_MODE_NONE);
-		hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr,
-					   0, false, 0);
+		fm10k_queue_mac_request(interface, glort, sdev->dev_addr,
+					0, false);
 	}
 
 	fm10k_mbx_unlock(interface);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index 63784576ae8b..7f605221a686 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -91,6 +91,76 @@ static int fm10k_hw_ready(struct fm10k_intfc *interface)
 	return FM10K_REMOVED(hw->hw_addr) ? -ENODEV : 0;
 }
 
+/**
+ * fm10k_macvlan_schedule - Schedule MAC/VLAN queue task
+ * @interface: fm10k private interface structure
+ *
+ * Schedule the MAC/VLAN queue monitor task. If the MAC/VLAN task cannot be
+ * started immediately, request that it be restarted when possible.
+ */
+void fm10k_macvlan_schedule(struct fm10k_intfc *interface)
+{
+	/* Avoid processing the MAC/VLAN queue when the service task is
+	 * disabled, or when we're resetting the device.
+	 */
+	if (!test_bit(__FM10K_MACVLAN_DISABLE, interface->state) &&
+	    !test_and_set_bit(__FM10K_MACVLAN_SCHED, interface->state)) {
+		clear_bit(__FM10K_MACVLAN_REQUEST, interface->state);
+		/* We delay the actual start of execution in order to allow
+		 * multiple MAC/VLAN updates to accumulate before handling
+		 * them, and to allow some time to let the mailbox drain
+		 * between runs.
+		 */
+		queue_delayed_work(fm10k_workqueue,
+				   &interface->macvlan_task, 10);
+	} else {
+		set_bit(__FM10K_MACVLAN_REQUEST, interface->state);
+	}
+}
+
+/**
+ * fm10k_stop_macvlan_task - Stop the MAC/VLAN queue monitor
+ * @interface: fm10k private interface structure
+ *
+ * Wait until the MAC/VLAN queue task has stopped, and cancel any future
+ * requests.
+ */
+static void fm10k_stop_macvlan_task(struct fm10k_intfc *interface)
+{
+	/* Disable the MAC/VLAN work item */
+	set_bit(__FM10K_MACVLAN_DISABLE, interface->state);
+
+	/* Make sure we waited until any current invocations have stopped */
+	cancel_delayed_work_sync(&interface->macvlan_task);
+
+	/* We set the __FM10K_MACVLAN_SCHED bit when we schedule the task.
+	 * However, it may not be unset of the MAC/VLAN task never actually
+	 * got a chance to run. Since we've canceled the task here, and it
+	 * cannot be rescheuled right now, we need to ensure the scheduled bit
+	 * gets unset.
+	 */
+	clear_bit(__FM10K_MACVLAN_SCHED, interface->state);
+}
+
+/**
+ * fm10k_resume_macvlan_task - Restart the MAC/VLAN queue monitor
+ * @interface: fm10k private interface structure
+ *
+ * Clear the __FM10K_MACVLAN_DISABLE bit and, if a request occurred, schedule
+ * the MAC/VLAN work monitor.
+ */
+static void fm10k_resume_macvlan_task(struct fm10k_intfc *interface)
+{
+	/* Re-enable the MAC/VLAN work item */
+	clear_bit(__FM10K_MACVLAN_DISABLE, interface->state);
+
+	/* We might have received a MAC/VLAN request while disabled. If so,
+	 * kick off the queue now.
+	 */
+	if (test_bit(__FM10K_MACVLAN_REQUEST, interface->state))
+		fm10k_macvlan_schedule(interface);
+}
+
 void fm10k_service_event_schedule(struct fm10k_intfc *interface)
 {
 	if (!test_bit(__FM10K_SERVICE_DISABLE, interface->state) &&
@@ -118,13 +188,35 @@ static void fm10k_service_event_complete(struct fm10k_intfc *interface)
 		fm10k_service_event_schedule(interface);
 }
 
+static void fm10k_stop_service_event(struct fm10k_intfc *interface)
+{
+	set_bit(__FM10K_SERVICE_DISABLE, interface->state);
+	cancel_work_sync(&interface->service_task);
+
+	/* It's possible that cancel_work_sync stopped the service task from
+	 * running before it could actually start. In this case the
+	 * __FM10K_SERVICE_SCHED bit will never be cleared. Since we know that
+	 * the service task cannot be running at this point, we need to clear
+	 * the scheduled bit, as otherwise the service task may never be
+	 * restarted.
+	 */
+	clear_bit(__FM10K_SERVICE_SCHED, interface->state);
+}
+
+static void fm10k_start_service_event(struct fm10k_intfc *interface)
+{
+	clear_bit(__FM10K_SERVICE_DISABLE, interface->state);
+	fm10k_service_event_schedule(interface);
+}
+
 /**
  * fm10k_service_timer - Timer Call-back
  * @data: pointer to interface cast into an unsigned long
  **/
-static void fm10k_service_timer(unsigned long data)
+static void fm10k_service_timer(struct timer_list *t)
 {
-	struct fm10k_intfc *interface = (struct fm10k_intfc *)data;
+	struct fm10k_intfc *interface = from_timer(interface, t,
+						   service_timer);
 
 	/* Reset the timer */
 	mod_timer(&interface->service_timer, (HZ * 2) + jiffies);
@@ -132,36 +224,15 @@ static void fm10k_service_timer(unsigned long data)
 	fm10k_service_event_schedule(interface);
 }
 
-static void fm10k_detach_subtask(struct fm10k_intfc *interface)
-{
-	struct net_device *netdev = interface->netdev;
-	u32 __iomem *hw_addr;
-	u32 value;
-
-	/* do nothing if device is still present or hw_addr is set */
-	if (netif_device_present(netdev) || interface->hw.hw_addr)
-		return;
-
-	/* check the real address space to see if we've recovered */
-	hw_addr = READ_ONCE(interface->uc_addr);
-	value = readl(hw_addr);
-	if (~value) {
-		interface->hw.hw_addr = interface->uc_addr;
-		netif_device_attach(netdev);
-		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
-		netdev_warn(netdev, "PCIe link restored, device now attached\n");
-		return;
-	}
-
-	rtnl_lock();
-
-	if (netif_running(netdev))
-		dev_close(netdev);
-
-	rtnl_unlock();
-}
-
-static void fm10k_prepare_for_reset(struct fm10k_intfc *interface)
+/**
+ * fm10k_prepare_for_reset - Prepare the driver and device for a pending reset
+ * @interface: fm10k private data structure
+ *
+ * This function prepares for a device reset by shutting as much down as we
+ * can. It does nothing and returns false if __FM10K_RESETTING was already set
+ * prior to calling this function. It returns true if it actually did work.
+ */
+static bool fm10k_prepare_for_reset(struct fm10k_intfc *interface)
 {
 	struct net_device *netdev = interface->netdev;
 
@@ -170,8 +241,15 @@ static void fm10k_prepare_for_reset(struct fm10k_intfc *interface)
 	/* put off any impending NetWatchDogTimeout */
 	netif_trans_update(netdev);
 
-	while (test_and_set_bit(__FM10K_RESETTING, interface->state))
-		usleep_range(1000, 2000);
+	/* Nothing to do if a reset is already in progress */
+	if (test_and_set_bit(__FM10K_RESETTING, interface->state))
+		return false;
+
+	/* As the MAC/VLAN task will be accessing registers it must not be
+	 * running while we reset. Although the task will not be scheduled
+	 * once we start resetting it may already be running
+	 */
+	fm10k_stop_macvlan_task(interface);
 
 	rtnl_lock();
 
@@ -189,6 +267,8 @@ static void fm10k_prepare_for_reset(struct fm10k_intfc *interface)
 	interface->last_reset = jiffies + (10 * HZ);
 
 	rtnl_unlock();
+
+	return true;
 }
 
 static int fm10k_handle_reset(struct fm10k_intfc *interface)
@@ -197,6 +277,8 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface)
 	struct fm10k_hw *hw = &interface->hw;
 	int err;
 
+	WARN_ON(!test_bit(__FM10K_RESETTING, interface->state));
+
 	rtnl_lock();
 
 	pci_set_master(interface->pdev);
@@ -253,6 +335,8 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface)
 
 	rtnl_unlock();
 
+	fm10k_resume_macvlan_task(interface);
+
 	clear_bit(__FM10K_RESETTING, interface->state);
 
 	return err;
@@ -270,27 +354,80 @@ reinit_err:
 	return err;
 }
 
-static void fm10k_reinit(struct fm10k_intfc *interface)
+static void fm10k_detach_subtask(struct fm10k_intfc *interface)
 {
+	struct net_device *netdev = interface->netdev;
+	u32 __iomem *hw_addr;
+	u32 value;
 	int err;
 
-	fm10k_prepare_for_reset(interface);
+	/* do nothing if netdev is still present or hw_addr is set */
+	if (netif_device_present(netdev) || interface->hw.hw_addr)
+		return;
 
-	err = fm10k_handle_reset(interface);
-	if (err)
-		dev_err(&interface->pdev->dev,
-			"fm10k_handle_reset failed: %d\n", err);
+	/* We've lost the PCIe register space, and can no longer access the
+	 * device. Shut everything except the detach subtask down and prepare
+	 * to reset the device in case we recover. If we actually prepare for
+	 * reset, indicate that we're detached.
+	 */
+	if (fm10k_prepare_for_reset(interface))
+		set_bit(__FM10K_RESET_DETACHED, interface->state);
+
+	/* check the real address space to see if we've recovered */
+	hw_addr = READ_ONCE(interface->uc_addr);
+	value = readl(hw_addr);
+	if (~value) {
+		/* Make sure the reset was initiated because we detached,
+		 * otherwise we might race with a different reset flow.
+		 */
+		if (!test_and_clear_bit(__FM10K_RESET_DETACHED,
+					interface->state))
+			return;
+
+		/* Restore the hardware address */
+		interface->hw.hw_addr = interface->uc_addr;
+
+		/* PCIe link has been restored, and the device is active
+		 * again. Restore everything and reset the device.
+		 */
+		err = fm10k_handle_reset(interface);
+		if (err) {
+			netdev_err(netdev, "Unable to reset device: %d\n", err);
+			interface->hw.hw_addr = NULL;
+			return;
+		}
+
+		/* Re-attach the netdev */
+		netif_device_attach(netdev);
+		netdev_warn(netdev, "PCIe link restored, device now attached\n");
+		return;
+	}
 }
 
 static void fm10k_reset_subtask(struct fm10k_intfc *interface)
 {
+	int err;
+
 	if (!test_and_clear_bit(FM10K_FLAG_RESET_REQUESTED,
 				interface->flags))
 		return;
 
+	/* If another thread has already prepared to reset the device, we
+	 * should not attempt to handle a reset here, since we'd race with
+	 * that thread. This may happen if we suspend the device or if the
+	 * PCIe link is lost. In this case, we'll just ignore the RESET
+	 * request, as it will (eventually) be taken care of when the thread
+	 * which actually started the reset is finished.
+	 */
+	if (!fm10k_prepare_for_reset(interface))
+		return;
+
 	netdev_err(interface->netdev, "Reset interface\n");
 
-	fm10k_reinit(interface);
+	err = fm10k_handle_reset(interface);
+	if (err)
+		dev_err(&interface->pdev->dev,
+			"fm10k_handle_reset failed: %d\n", err);
 }
 
 /**
@@ -360,6 +497,10 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface)
  **/
 static void fm10k_mbx_subtask(struct fm10k_intfc *interface)
 {
+	/* If we're resetting, bail out */
+	if (test_bit(__FM10K_RESETTING, interface->state))
+		return;
+
 	/* process upstream mailbox and update device state */
 	fm10k_watchdog_update_host_state(interface);
 
@@ -609,9 +750,11 @@ static void fm10k_service_task(struct work_struct *work)
 
 	interface = container_of(work, struct fm10k_intfc, service_task);
 
+	/* Check whether we're detached first */
+	fm10k_detach_subtask(interface);
+
 	/* tasks run even when interface is down */
 	fm10k_mbx_subtask(interface);
-	fm10k_detach_subtask(interface);
 	fm10k_reset_subtask(interface);
 
 	/* tasks only run when interface is up */
@@ -623,6 +766,112 @@ static void fm10k_service_task(struct work_struct *work)
 }
 
 /**
+ * fm10k_macvlan_task - send queued MAC/VLAN requests to switch manager
+ * @work: pointer to work_struct containing our data
+ *
+ * This work item handles sending MAC/VLAN updates to the switch manager. When
+ * the interface is up, it will attempt to queue mailbox messages to the
+ * switch manager requesting updates for MAC/VLAN pairs. If the Tx fifo of the
+ * mailbox is full, it will reschedule itself to try again in a short while.
+ * This ensures that the driver does not overload the switch mailbox with too
+ * many simultaneous requests, causing an unnecessary reset.
+ **/
+static void fm10k_macvlan_task(struct work_struct *work)
+{
+	struct fm10k_macvlan_request *item;
+	struct fm10k_intfc *interface;
+	struct delayed_work *dwork;
+	struct list_head *requests;
+	struct fm10k_hw *hw;
+	unsigned long flags;
+
+	dwork = to_delayed_work(work);
+	interface = container_of(dwork, struct fm10k_intfc, macvlan_task);
+	hw = &interface->hw;
+	requests = &interface->macvlan_requests;
+
+	do {
+		/* Pop the first item off the list */
+		spin_lock_irqsave(&interface->macvlan_lock, flags);
+		item = list_first_entry_or_null(requests,
+						struct fm10k_macvlan_request,
+						list);
+		if (item)
+			list_del_init(&item->list);
+
+		spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+
+		/* We have no more items to process */
+		if (!item)
+			goto done;
+
+		fm10k_mbx_lock(interface);
+
+		/* Check that we have plenty of space to send the message. We
+		 * want to ensure that the mailbox stays low enough to avoid a
+		 * change in the host state, otherwise we may see spurious
+		 * link up / link down notifications.
+		 */
+		if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU + 5)) {
+			hw->mbx.ops.process(hw, &hw->mbx);
+			set_bit(__FM10K_MACVLAN_REQUEST, interface->state);
+			fm10k_mbx_unlock(interface);
+
+			/* Put the request back on the list */
+			spin_lock_irqsave(&interface->macvlan_lock, flags);
+			list_add(&item->list, requests);
+			spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+			break;
+		}
+
+		switch (item->type) {
+		case FM10K_MC_MAC_REQUEST:
+			hw->mac.ops.update_mc_addr(hw,
+						   item->mac.glort,
+						   item->mac.addr,
+						   item->mac.vid,
+						   item->set);
+			break;
+		case FM10K_UC_MAC_REQUEST:
+			hw->mac.ops.update_uc_addr(hw,
+						   item->mac.glort,
+						   item->mac.addr,
+						   item->mac.vid,
+						   item->set,
+						   0);
+			break;
+		case FM10K_VLAN_REQUEST:
+			hw->mac.ops.update_vlan(hw,
+						item->vlan.vid,
+						item->vlan.vsi,
+						item->set);
+			break;
+		default:
+			break;
+		}
+
+		fm10k_mbx_unlock(interface);
+
+		/* Free the item now that we've sent the update */
+		kfree(item);
+	} while (true);
+
+done:
+	WARN_ON(!test_bit(__FM10K_MACVLAN_SCHED, interface->state));
+
+	/* flush memory to make sure state is correct */
+	smp_mb__before_atomic();
+	clear_bit(__FM10K_MACVLAN_SCHED, interface->state);
+
+	/* If a MAC/VLAN request was scheduled since we started, we should
+	 * re-schedule. However, there is no reason to re-schedule if there is
+	 * no work to do.
+	 */
+	if (test_bit(__FM10K_MACVLAN_REQUEST, interface->state))
+		fm10k_macvlan_schedule(interface);
+}
+
+/**
  * fm10k_configure_tx_ring - Configure Tx ring after Reset
  * @interface: board private structure
  * @ring: structure containing ring specific data
@@ -1544,7 +1793,7 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface)
 	struct net_device *dev = interface->netdev;
 	struct fm10k_hw *hw = &interface->hw;
 	struct msix_entry *entry;
-	int ri = 0, ti = 0;
+	unsigned int ri = 0, ti = 0;
 	int vector, err;
 
 	entry = &interface->msix_entries[NON_Q_VECTORS(hw)];
@@ -1554,15 +1803,15 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface)
 
 		/* name the vector */
 		if (q_vector->tx.count && q_vector->rx.count) {
-			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
-				 "%s-TxRx-%d", dev->name, ri++);
+			snprintf(q_vector->name, sizeof(q_vector->name),
+				 "%s-TxRx-%u", dev->name, ri++);
 			ti++;
 		} else if (q_vector->rx.count) {
-			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
-				 "%s-rx-%d", dev->name, ri++);
+			snprintf(q_vector->name, sizeof(q_vector->name),
+				 "%s-rx-%u", dev->name, ri++);
 		} else if (q_vector->tx.count) {
-			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
-				 "%s-tx-%d", dev->name, ti++);
+			snprintf(q_vector->name, sizeof(q_vector->name),
+				 "%s-tx-%u", dev->name, ti++);
 		} else {
 			/* skip this unused q_vector */
 			continue;
@@ -1800,9 +2049,6 @@ static int fm10k_sw_init(struct fm10k_intfc *interface,
 		netdev->vlan_features |= NETIF_F_HIGHDMA;
 	}
 
-	/* delay any future reset requests */
-	interface->last_reset = jiffies + (10 * HZ);
-
 	/* reset and initialize the hardware so it is in a known state */
 	err = hw->mac.ops.reset_hw(hw);
 	if (err) {
@@ -1857,9 +2103,16 @@ static int fm10k_sw_init(struct fm10k_intfc *interface,
 	INIT_LIST_HEAD(&interface->vxlan_port);
 	INIT_LIST_HEAD(&interface->geneve_port);
 
+	/* Initialize the MAC/VLAN queue */
+	INIT_LIST_HEAD(&interface->macvlan_requests);
+
 	netdev_rss_key_fill(rss_key, sizeof(rss_key));
 	memcpy(interface->rssrk, rss_key, sizeof(rss_key));
 
+	/* Initialize the mailbox lock */
+	spin_lock_init(&interface->mbx_lock);
+	spin_lock_init(&interface->macvlan_lock);
+
 	/* Start off interface as being down */
 	set_bit(__FM10K_DOWN, interface->state);
 	set_bit(__FM10K_UPDATING_STATS, interface->state);
@@ -2063,10 +2316,12 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Initialize service timer and service task late in order to avoid
 	 * cleanup issues.
 	 */
-	setup_timer(&interface->service_timer, &fm10k_service_timer,
-		    (unsigned long)interface);
+	timer_setup(&interface->service_timer, fm10k_service_timer, 0);
 	INIT_WORK(&interface->service_task, fm10k_service_task);
 
+	/* Setup the MAC/VLAN queue */
+	INIT_DELAYED_WORK(&interface->macvlan_task, fm10k_macvlan_task);
+
 	/* kick off service timer now, even when interface is down */
 	mod_timer(&interface->service_timer, (HZ * 2) + jiffies);
 
@@ -2079,8 +2334,9 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* enable SR-IOV after registering netdev to enforce PF/VF ordering */
 	fm10k_iov_configure(pdev, 0);
 
-	/* clear the service task disable bit to allow service task to start */
+	/* clear the service task disable bit and kick off service task */
 	clear_bit(__FM10K_SERVICE_DISABLE, interface->state);
+	fm10k_service_event_schedule(interface);
 
 	return 0;
 
@@ -2118,8 +2374,11 @@ static void fm10k_remove(struct pci_dev *pdev)
 
 	del_timer_sync(&interface->service_timer);
 
-	set_bit(__FM10K_SERVICE_DISABLE, interface->state);
-	cancel_work_sync(&interface->service_task);
+	fm10k_stop_service_event(interface);
+	fm10k_stop_macvlan_task(interface);
+
+	/* Remove all pending MAC/VLAN requests */
+	fm10k_clear_macvlan_queue(interface, interface->glort, true);
 
 	/* free netdev, this may bounce the interrupts due to setup_tc */
 	if (netdev->reg_state == NETREG_REGISTERED)
@@ -2156,11 +2415,14 @@ static void fm10k_prepare_suspend(struct fm10k_intfc *interface)
 	 * a surprise remove if the PCIe device is disabled while we're
 	 * stopped. We stop the watchdog task until after we resume software
 	 * activity.
+	 *
+	 * Note that the MAC/VLAN task will be stopped as part of preparing
+	 * for reset so we don't need to handle it here.
 	 */
-	set_bit(__FM10K_SERVICE_DISABLE, interface->state);
-	cancel_work_sync(&interface->service_task);
+	fm10k_stop_service_event(interface);
 
-	fm10k_prepare_for_reset(interface);
+	if (fm10k_prepare_for_reset(interface))
+		set_bit(__FM10K_RESET_SUSPENDED, interface->state);
 }
 
 static int fm10k_handle_resume(struct fm10k_intfc *interface)
@@ -2168,6 +2430,13 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface)
 	struct fm10k_hw *hw = &interface->hw;
 	int err;
 
+	/* Even if we didn't properly prepare for reset in
+	 * fm10k_prepare_suspend, we'll attempt to resume anyways.
+	 */
+	if (!test_and_clear_bit(__FM10K_RESET_SUSPENDED, interface->state))
+		dev_warn(&interface->pdev->dev,
+			 "Device was shut down as part of suspend... Attempting to recover\n");
+
 	/* reset statistics starting values */
 	hw->mac.ops.rebind_hw_stats(hw, &interface->stats);
 
@@ -2185,45 +2454,30 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface)
 	interface->link_down_event = jiffies + (HZ);
 	set_bit(__FM10K_LINK_DOWN, interface->state);
 
-	/* clear the service task disable bit to allow service task to start */
-	clear_bit(__FM10K_SERVICE_DISABLE, interface->state);
-	fm10k_service_event_schedule(interface);
+	/* restart the service task */
+	fm10k_start_service_event(interface);
+
+	/* Restart the MAC/VLAN request queue in-case of outstanding events */
+	fm10k_macvlan_schedule(interface);
 
 	return err;
 }
 
 #ifdef CONFIG_PM
 /**
- * fm10k_resume - Restore device to pre-sleep state
- * @pdev: PCI device information struct
+ * fm10k_resume - Generic PM resume hook
+ * @dev: generic device structure
  *
- * fm10k_resume is called after the system has powered back up from a sleep
- * state and is ready to resume operation.  This function is meant to restore
- * the device back to its pre-sleep state.
+ * Generic PM hook used when waking the device from a low power state after
+ * suspend or hibernation. This function does not need to handle lower PCIe
+ * device state as the stack takes care of that for us.
  **/
-static int fm10k_resume(struct pci_dev *pdev)
+static int fm10k_resume(struct device *dev)
 {
-	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
+	struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev));
 	struct net_device *netdev = interface->netdev;
 	struct fm10k_hw *hw = &interface->hw;
-	u32 err;
-
-	pci_set_power_state(pdev, PCI_D0);
-	pci_restore_state(pdev);
-
-	/* pci_restore_state clears dev->state_saved so call
-	 * pci_save_state to restore it.
-	 */
-	pci_save_state(pdev);
-
-	err = pci_enable_device_mem(pdev);
-	if (err) {
-		dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n");
-		return err;
-	}
-	pci_set_master(pdev);
-
-	pci_wake_from_d3(pdev, false);
+	int err;
 
 	/* refresh hw_addr in case it was dropped */
 	hw->hw_addr = interface->uc_addr;
@@ -2238,36 +2492,27 @@ static int fm10k_resume(struct pci_dev *pdev)
 }
 
 /**
- * fm10k_suspend - Prepare the device for a system sleep state
- * @pdev: PCI device information struct
+ * fm10k_suspend - Generic PM suspend hook
+ * @dev: generic device structure
  *
- * fm10k_suspend is meant to shutdown the device prior to the system entering
- * a sleep state.  The fm10k hardware does not support wake on lan so the
- * driver simply needs to shut down the device so it is in a low power state.
+ * Generic PM hook used when setting the device into a low power state for
+ * system suspend or hibernation. This function does not need to handle lower
+ * PCIe device state as the stack takes care of that for us.
  **/
-static int fm10k_suspend(struct pci_dev *pdev,
-			 pm_message_t __always_unused state)
+static int fm10k_suspend(struct device *dev)
 {
-	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
+	struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev));
 	struct net_device *netdev = interface->netdev;
-	int err = 0;
 
 	netif_device_detach(netdev);
 
 	fm10k_prepare_suspend(interface);
 
-	err = pci_save_state(pdev);
-	if (err)
-		return err;
-
-	pci_disable_device(pdev);
-	pci_wake_from_d3(pdev, false);
-	pci_set_power_state(pdev, PCI_D3hot);
-
 	return 0;
 }
 
 #endif /* CONFIG_PM */
+
 /**
  * fm10k_io_error_detected - called when PCI error is detected
  * @pdev: Pointer to PCI device
@@ -2343,11 +2588,18 @@ static void fm10k_io_resume(struct pci_dev *pdev)
 
 	if (err)
 		dev_warn(&pdev->dev,
-			 "fm10k_io_resume failed: %d\n", err);
+			 "%s failed: %d\n", __func__, err);
 	else
 		netif_device_attach(netdev);
 }
 
+/**
+ * fm10k_io_reset_prepare - called when PCI function is about to be reset
+ * @pdev: Pointer to PCI device
+ *
+ * This callback is called when the PCI function is about to be reset,
+ * allowing the device driver to prepare for it.
+ */
 static void fm10k_io_reset_prepare(struct pci_dev *pdev)
 {
 	/* warn incase we have any active VF devices */
@@ -2357,6 +2609,13 @@ static void fm10k_io_reset_prepare(struct pci_dev *pdev)
 	fm10k_prepare_suspend(pci_get_drvdata(pdev));
 }
 
+/**
+ * fm10k_io_reset_done - called when PCI function has finished resetting
+ * @pdev: Pointer to PCI device
+ *
+ * This callback is called just after the PCI function is reset, such as via
+ * /sys/class/net/<enpX>/device/reset or similar.
+ */
 static void fm10k_io_reset_done(struct pci_dev *pdev)
 {
 	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
@@ -2364,7 +2623,7 @@ static void fm10k_io_reset_done(struct pci_dev *pdev)
 
 	if (err) {
 		dev_warn(&pdev->dev,
-			 "fm10k_io_reset_notify failed: %d\n", err);
+			 "%s failed: %d\n", __func__, err);
 		netif_device_detach(interface->netdev);
 	}
 }
@@ -2377,15 +2636,18 @@ static const struct pci_error_handlers fm10k_err_handler = {
 	.reset_done = fm10k_io_reset_done,
 };
 
+static SIMPLE_DEV_PM_OPS(fm10k_pm_ops, fm10k_suspend, fm10k_resume);
+
 static struct pci_driver fm10k_driver = {
 	.name			= fm10k_driver_name,
 	.id_table		= fm10k_pci_tbl,
 	.probe			= fm10k_probe,
 	.remove			= fm10k_remove,
 #ifdef CONFIG_PM
-	.suspend		= fm10k_suspend,
-	.resume			= fm10k_resume,
-#endif
+	.driver = {
+		.pm		= &fm10k_pm_ops,
+	},
+#endif /* CONFIG_PM */
 	.sriov_configure	= fm10k_iov_configure,
 	.err_handler		= &fm10k_err_handler
 };
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
index 40ee0242a80a..425d814aed4d 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
@@ -1,5 +1,5 @@
 /* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -1186,7 +1186,7 @@ s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 **results,
  * Will report an error if the VLAN ID is out of range. For VID = 0, it will
  * return either the pf_vid or sw_vid depending on which one is set.
  */
-static s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid)
+s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid)
 {
 	if (!vid)
 		return vf_info->pf_vid ? vf_info->pf_vid : vf_info->sw_vid;
@@ -1334,19 +1334,19 @@ static u8 fm10k_iov_supported_xcast_mode_pf(struct fm10k_vf_info *vf_info,
 	case FM10K_XCAST_MODE_PROMISC:
 		if (vf_flags & FM10K_VF_FLAG_PROMISC_CAPABLE)
 			return FM10K_XCAST_MODE_PROMISC;
-		/* fallthough */
+		/* fall through */
 	case FM10K_XCAST_MODE_ALLMULTI:
 		if (vf_flags & FM10K_VF_FLAG_ALLMULTI_CAPABLE)
 			return FM10K_XCAST_MODE_ALLMULTI;
-		/* fallthough */
+		/* fall through */
 	case FM10K_XCAST_MODE_MULTI:
 		if (vf_flags & FM10K_VF_FLAG_MULTI_CAPABLE)
 			return FM10K_XCAST_MODE_MULTI;
-		/* fallthough */
+		/* fall through */
 	case FM10K_XCAST_MODE_NONE:
 		if (vf_flags & FM10K_VF_FLAG_NONE_CAPABLE)
 			return FM10K_XCAST_MODE_NONE;
-		/* fallthough */
+		/* fall through */
 	default:
 		break;
 	}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
index 3336d3c10760..e04d41f1a532 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
@@ -1,5 +1,5 @@
 /* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -114,6 +114,7 @@ extern const struct fm10k_tlv_attr fm10k_err_msg_attr[];
 #define FM10K_PF_MSG_ERR_HANDLER(msg, func) \
 	FM10K_MSG_HANDLER(FM10K_PF_MSG_ID_##msg, fm10k_err_msg_attr, func)
 
+s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid);
 s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *);
 s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *, u32 **,
 			      struct fm10k_mbx_info *);
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index d0c1bf5441d8..5829715fa342 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -54,6 +54,9 @@
 #include <linux/clocksource.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_gact.h>
+#include <net/tc_act/tc_mirred.h>
 #include "i40e_type.h"
 #include "i40e_prototype.h"
 #include "i40e_client.h"
@@ -77,6 +80,7 @@
 #define i40e_default_queues_per_vmdq(pf) \
 		(((pf)->hw_features & I40E_HW_RSS_AQ_CAPABLE) ? 4 : 1)
 #define I40E_DEFAULT_QUEUES_PER_VF	4
+#define I40E_MAX_VF_QUEUES		16
 #define I40E_DEFAULT_QUEUES_PER_TC	1 /* should be a power of 2 */
 #define i40e_pf_get_max_q_per_tc(pf) \
 		(((pf)->hw_features & I40E_HW_128_QP_RSS_CAPABLE) ? 128 : 64)
@@ -86,6 +90,7 @@
 #define I40E_AQ_LEN			256
 #define I40E_AQ_WORK_LIMIT		66 /* max number of VFs + a little */
 #define I40E_MAX_USER_PRIORITY		8
+#define I40E_MAX_QUEUES_PER_CH		64
 #define I40E_DEFAULT_TRAFFIC_CLASS	BIT(0)
 #define I40E_DEFAULT_MSG_ENABLE		4
 #define I40E_QUEUE_WAIT_RETRY_LIMIT	10
@@ -125,6 +130,11 @@
 /* default to trying for four seconds */
 #define I40E_TRY_LINK_TIMEOUT	(4 * HZ)
 
+/* BW rate limiting */
+#define I40E_BW_CREDIT_DIVISOR		50 /* 50Mbps per BW credit */
+#define I40E_BW_MBPS_DIVISOR		125000 /* rate / (1000000 / 8) Mbps */
+#define I40E_MAX_BW_INACTIVE_ACCUM	4 /* accumulate 4 credits max */
+
 /* driver state flags */
 enum i40e_state_t {
 	__I40E_TESTING,
@@ -136,6 +146,7 @@ enum i40e_state_t {
 	__I40E_MDD_EVENT_PENDING,
 	__I40E_VFLR_EVENT_PENDING,
 	__I40E_RESET_RECOVERY_PENDING,
+	__I40E_MISC_IRQ_REQUESTED,
 	__I40E_RESET_INTR_RECEIVED,
 	__I40E_REINIT_REQUESTED,
 	__I40E_PF_RESET_REQUESTED,
@@ -155,6 +166,8 @@ enum i40e_state_t {
 	__I40E_STATE_SIZE__,
 };
 
+#define I40E_PF_RESET_FLAG	BIT_ULL(__I40E_PF_RESET_REQUESTED)
+
 /* VSI state flags */
 enum i40e_vsi_state_t {
 	__I40E_VSI_DOWN,
@@ -242,6 +255,58 @@ struct i40e_fdir_filter {
 	u32 fd_id;
 };
 
+#define I40E_CLOUD_FIELD_OMAC	0x01
+#define I40E_CLOUD_FIELD_IMAC	0x02
+#define I40E_CLOUD_FIELD_IVLAN	0x04
+#define I40E_CLOUD_FIELD_TEN_ID	0x08
+#define I40E_CLOUD_FIELD_IIP	0x10
+
+#define I40E_CLOUD_FILTER_FLAGS_OMAC	I40E_CLOUD_FIELD_OMAC
+#define I40E_CLOUD_FILTER_FLAGS_IMAC	I40E_CLOUD_FIELD_IMAC
+#define I40E_CLOUD_FILTER_FLAGS_IMAC_IVLAN	(I40E_CLOUD_FIELD_IMAC | \
+						 I40E_CLOUD_FIELD_IVLAN)
+#define I40E_CLOUD_FILTER_FLAGS_IMAC_TEN_ID	(I40E_CLOUD_FIELD_IMAC | \
+						 I40E_CLOUD_FIELD_TEN_ID)
+#define I40E_CLOUD_FILTER_FLAGS_OMAC_TEN_ID_IMAC (I40E_CLOUD_FIELD_OMAC | \
+						  I40E_CLOUD_FIELD_IMAC | \
+						  I40E_CLOUD_FIELD_TEN_ID)
+#define I40E_CLOUD_FILTER_FLAGS_IMAC_IVLAN_TEN_ID (I40E_CLOUD_FIELD_IMAC | \
+						   I40E_CLOUD_FIELD_IVLAN | \
+						   I40E_CLOUD_FIELD_TEN_ID)
+#define I40E_CLOUD_FILTER_FLAGS_IIP	I40E_CLOUD_FIELD_IIP
+
+struct i40e_cloud_filter {
+	struct hlist_node cloud_node;
+	unsigned long cookie;
+	/* cloud filter input set follows */
+	u8 dst_mac[ETH_ALEN];
+	u8 src_mac[ETH_ALEN];
+	__be16 vlan_id;
+	u16 seid;       /* filter control */
+	__be16 dst_port;
+	__be16 src_port;
+	u32 tenant_id;
+	union {
+		struct {
+			struct in_addr dst_ip;
+			struct in_addr src_ip;
+		} v4;
+		struct {
+			struct in6_addr dst_ip6;
+			struct in6_addr src_ip6;
+		} v6;
+	} ip;
+#define dst_ipv6	ip.v6.dst_ip6.s6_addr32
+#define src_ipv6	ip.v6.src_ip6.s6_addr32
+#define dst_ipv4	ip.v4.dst_ip.s_addr
+#define src_ipv4	ip.v4.src_ip.s_addr
+	u16 n_proto;    /* Ethernet Protocol */
+	u8 ip_proto;    /* IPPROTO value */
+	u8 flags;
+#define I40E_CLOUD_TNL_TYPE_NONE        0xff
+	u8 tunnel_type;
+};
+
 #define I40E_ETH_P_LLDP			0x88cc
 
 #define I40E_DCB_PRIO_TYPE_STRICT	0
@@ -336,6 +401,25 @@ struct i40e_flex_pit {
 	u8 pit_index;
 };
 
+struct i40e_channel {
+	struct list_head list;
+	bool initialized;
+	u8 type;
+	u16 vsi_number; /* Assigned VSI number from AQ 'Add VSI' response */
+	u16 stat_counter_idx;
+	u16 base_queue;
+	u16 num_queue_pairs; /* Requested by user */
+	u16 seid;
+
+	u8 enabled_tc;
+	struct i40e_aqc_vsi_properties_data info;
+
+	u64 max_tx_rate;
+
+	/* track this channel belongs to which VSI */
+	struct i40e_vsi *parent_vsi;
+};
+
 /* struct that defines the Ethernet device */
 struct i40e_pf {
 	struct pci_dev *pdev;
@@ -348,7 +432,7 @@ struct i40e_pf {
 	u16 num_vmdq_vsis;         /* num vmdq vsis this PF has set up */
 	u16 num_vmdq_qps;          /* num queue pairs per vmdq pool */
 	u16 num_vmdq_msix;         /* num queue vectors per vmdq pool */
-	u16 num_req_vfs;           /* num VFs requested for this VF */
+	u16 num_req_vfs;           /* num VFs requested for this PF */
 	u16 num_vf_qps;            /* num queue pairs per VF */
 	u16 num_lan_qps;           /* num lan queues this PF has set up */
 	u16 num_lan_msix;          /* num queue vectors for the base PF vsi */
@@ -390,6 +474,9 @@ struct i40e_pf {
 	struct i40e_udp_port_config udp_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS];
 	u16 pending_udp_bitmap;
 
+	struct hlist_head cloud_filter_list;
+	u16 num_cloud_filters;
+
 	enum i40e_interrupt_policy int_policy;
 	u16 rx_itr_default;
 	u16 tx_itr_default;
@@ -401,55 +488,60 @@ struct i40e_pf {
 	struct timer_list service_timer;
 	struct work_struct service_task;
 
-	u64 hw_features;
-#define I40E_HW_RSS_AQ_CAPABLE			BIT_ULL(0)
-#define I40E_HW_128_QP_RSS_CAPABLE		BIT_ULL(1)
-#define I40E_HW_ATR_EVICT_CAPABLE		BIT_ULL(2)
-#define I40E_HW_WB_ON_ITR_CAPABLE		BIT_ULL(3)
-#define I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE	BIT_ULL(4)
-#define I40E_HW_NO_PCI_LINK_CHECK		BIT_ULL(5)
-#define I40E_HW_100M_SGMII_CAPABLE		BIT_ULL(6)
-#define I40E_HW_NO_DCB_SUPPORT			BIT_ULL(7)
-#define I40E_HW_USE_SET_LLDP_MIB		BIT_ULL(8)
-#define I40E_HW_GENEVE_OFFLOAD_CAPABLE		BIT_ULL(9)
-#define I40E_HW_PTP_L4_CAPABLE			BIT_ULL(10)
-#define I40E_HW_WOL_MC_MAGIC_PKT_WAKE		BIT_ULL(11)
-#define I40E_HW_MPLS_HDR_OFFLOAD_CAPABLE	BIT_ULL(12)
-#define I40E_HW_HAVE_CRT_RETIMER		BIT_ULL(13)
-#define I40E_HW_OUTER_UDP_CSUM_CAPABLE		BIT_ULL(14)
-#define I40E_HW_PHY_CONTROLS_LEDS		BIT_ULL(15)
-#define I40E_HW_STOP_FW_LLDP			BIT_ULL(16)
-#define I40E_HW_PORT_ID_VALID			BIT_ULL(17)
-#define I40E_HW_RESTART_AUTONEG			BIT_ULL(18)
-
-	u64 flags;
-#define I40E_FLAG_RX_CSUM_ENABLED		BIT_ULL(1)
-#define I40E_FLAG_MSI_ENABLED			BIT_ULL(2)
-#define I40E_FLAG_MSIX_ENABLED			BIT_ULL(3)
-#define I40E_FLAG_HW_ATR_EVICT_ENABLED		BIT_ULL(4)
-#define I40E_FLAG_RSS_ENABLED			BIT_ULL(6)
-#define I40E_FLAG_VMDQ_ENABLED			BIT_ULL(7)
-#define I40E_FLAG_IWARP_ENABLED			BIT_ULL(10)
-#define I40E_FLAG_FILTER_SYNC			BIT_ULL(15)
-#define I40E_FLAG_SERVICE_CLIENT_REQUESTED	BIT_ULL(16)
-#define I40E_FLAG_SRIOV_ENABLED			BIT_ULL(19)
-#define I40E_FLAG_DCB_ENABLED			BIT_ULL(20)
-#define I40E_FLAG_FD_SB_ENABLED			BIT_ULL(21)
-#define I40E_FLAG_FD_ATR_ENABLED		BIT_ULL(22)
-#define I40E_FLAG_FD_SB_AUTO_DISABLED		BIT_ULL(23)
-#define I40E_FLAG_FD_ATR_AUTO_DISABLED		BIT_ULL(24)
-#define I40E_FLAG_PTP				BIT_ULL(25)
-#define I40E_FLAG_MFP_ENABLED			BIT_ULL(26)
-#define I40E_FLAG_UDP_FILTER_SYNC		BIT_ULL(27)
-#define I40E_FLAG_DCB_CAPABLE			BIT_ULL(29)
-#define I40E_FLAG_VEB_STATS_ENABLED		BIT_ULL(37)
-#define I40E_FLAG_LINK_POLLING_ENABLED		BIT_ULL(39)
-#define I40E_FLAG_VEB_MODE_ENABLED		BIT_ULL(40)
-#define I40E_FLAG_TRUE_PROMISC_SUPPORT		BIT_ULL(51)
-#define I40E_FLAG_CLIENT_RESET			BIT_ULL(54)
-#define I40E_FLAG_TEMP_LINK_POLLING		BIT_ULL(55)
-#define I40E_FLAG_CLIENT_L2_CHANGE		BIT_ULL(56)
-#define I40E_FLAG_LEGACY_RX			BIT_ULL(58)
+	u32 hw_features;
+#define I40E_HW_RSS_AQ_CAPABLE			BIT(0)
+#define I40E_HW_128_QP_RSS_CAPABLE		BIT(1)
+#define I40E_HW_ATR_EVICT_CAPABLE		BIT(2)
+#define I40E_HW_WB_ON_ITR_CAPABLE		BIT(3)
+#define I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE	BIT(4)
+#define I40E_HW_NO_PCI_LINK_CHECK		BIT(5)
+#define I40E_HW_100M_SGMII_CAPABLE		BIT(6)
+#define I40E_HW_NO_DCB_SUPPORT			BIT(7)
+#define I40E_HW_USE_SET_LLDP_MIB		BIT(8)
+#define I40E_HW_GENEVE_OFFLOAD_CAPABLE		BIT(9)
+#define I40E_HW_PTP_L4_CAPABLE			BIT(10)
+#define I40E_HW_WOL_MC_MAGIC_PKT_WAKE		BIT(11)
+#define I40E_HW_MPLS_HDR_OFFLOAD_CAPABLE	BIT(12)
+#define I40E_HW_HAVE_CRT_RETIMER		BIT(13)
+#define I40E_HW_OUTER_UDP_CSUM_CAPABLE		BIT(14)
+#define I40E_HW_PHY_CONTROLS_LEDS		BIT(15)
+#define I40E_HW_STOP_FW_LLDP			BIT(16)
+#define I40E_HW_PORT_ID_VALID			BIT(17)
+#define I40E_HW_RESTART_AUTONEG			BIT(18)
+
+	u32 flags;
+#define I40E_FLAG_RX_CSUM_ENABLED		BIT(0)
+#define I40E_FLAG_MSI_ENABLED			BIT(1)
+#define I40E_FLAG_MSIX_ENABLED			BIT(2)
+#define I40E_FLAG_RSS_ENABLED			BIT(3)
+#define I40E_FLAG_VMDQ_ENABLED			BIT(4)
+#define I40E_FLAG_FILTER_SYNC			BIT(5)
+#define I40E_FLAG_SRIOV_ENABLED			BIT(6)
+#define I40E_FLAG_DCB_CAPABLE			BIT(7)
+#define I40E_FLAG_DCB_ENABLED			BIT(8)
+#define I40E_FLAG_FD_SB_ENABLED			BIT(9)
+#define I40E_FLAG_FD_ATR_ENABLED		BIT(10)
+#define I40E_FLAG_FD_SB_AUTO_DISABLED		BIT(11)
+#define I40E_FLAG_FD_ATR_AUTO_DISABLED		BIT(12)
+#define I40E_FLAG_MFP_ENABLED			BIT(13)
+#define I40E_FLAG_UDP_FILTER_SYNC		BIT(14)
+#define I40E_FLAG_HW_ATR_EVICT_ENABLED		BIT(15)
+#define I40E_FLAG_VEB_MODE_ENABLED		BIT(16)
+#define I40E_FLAG_VEB_STATS_ENABLED		BIT(17)
+#define I40E_FLAG_LINK_POLLING_ENABLED		BIT(18)
+#define I40E_FLAG_TRUE_PROMISC_SUPPORT		BIT(19)
+#define I40E_FLAG_TEMP_LINK_POLLING		BIT(20)
+#define I40E_FLAG_LEGACY_RX			BIT(21)
+#define I40E_FLAG_PTP				BIT(22)
+#define I40E_FLAG_IWARP_ENABLED			BIT(23)
+#define I40E_FLAG_SERVICE_CLIENT_REQUESTED	BIT(24)
+#define I40E_FLAG_CLIENT_L2_CHANGE		BIT(25)
+#define I40E_FLAG_CLIENT_RESET			BIT(26)
+#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED	BIT(27)
+#define I40E_FLAG_SOURCE_PRUNING_DISABLED	BIT(28)
+#define I40E_FLAG_TC_MQPRIO			BIT(29)
+#define I40E_FLAG_FD_SB_INACTIVE		BIT(30)
+#define I40E_FLAG_FD_SB_TO_CLOUD_FILTER		BIT(31)
 
 	struct i40e_client_instance *cinst;
 	bool stat_offsets_loaded;
@@ -530,6 +622,10 @@ struct i40e_pf {
 	u32 ioremap_len;
 	u32 fd_inv;
 	u16 phy_led_val;
+
+	u16 override_q_count;
+	u16 last_sw_conf_flags;
+	u16 last_sw_conf_valid_flags;
 };
 
 /**
@@ -673,6 +769,7 @@ struct i40e_vsi {
 	enum i40e_vsi_type type;  /* VSI type, e.g., LAN, FCoE, etc */
 	s16 vf_id;		/* Virtual function ID for SRIOV VSIs */
 
+	struct tc_mqprio_qopt_offload mqprio_qopt; /* queue parameters */
 	struct i40e_tc_configuration tc_config;
 	struct i40e_aqc_vsi_properties_data info;
 
@@ -694,6 +791,17 @@ struct i40e_vsi {
 	bool current_isup;	/* Sync 'link up' logging */
 	enum i40e_aq_link_speed current_speed;	/* Sync link speed logging */
 
+	/* channel specific fields */
+	u16 cnt_q_avail;	/* num of queues available for channel usage */
+	u16 orig_rss_size;
+	u16 current_rss_size;
+	bool reconfig_rss;
+
+	u16 next_base_queue;	/* next queue to be used for channel setup */
+
+	struct list_head ch_list;
+	u16 tc_seid_map[I40E_MAX_TRAFFIC_CLASS];
+
 	void *priv;	/* client driver data reference. */
 
 	/* VSI specific handlers */
@@ -945,9 +1053,6 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector)
 	struct i40e_hw *hw = &pf->hw;
 	u32 val;
 
-	/* definitely clear the PBA here, as this function is meant to
-	 * clean out all previous interrupts AND enable the interrupt
-	 */
 	val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
 	      I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
 	      (I40E_ITR_NONE << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT);
@@ -956,7 +1061,7 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector)
 }
 
 void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf);
-void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba);
+void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf);
 int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
 int i40e_open(struct net_device *netdev);
 int i40e_close(struct net_device *netdev);
@@ -1001,4 +1106,7 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi)
 {
 	return !!vsi->xdp_prog;
 }
+
+int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch);
+int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate);
 #endif /* _I40E_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index ba04988e0598..9dcb2a961197 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -607,6 +607,18 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw)
 			   &oem_lo);
 	hw->nvm.oem_ver = ((u32)oem_hi << 16) | oem_lo;
 
+	if (hw->mac.type == I40E_MAC_XL710 &&
+	    hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
+	    hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) {
+		hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE;
+	}
+
+	/* The ability to RX (not drop) 802.1ad frames was added in API 1.7 */
+	if (hw->aq.api_maj_ver > 1 ||
+	    (hw->aq.api_maj_ver == 1 &&
+	     hw->aq.api_min_ver >= 7))
+		hw->flags |= I40E_HW_FLAG_802_1AD_CAPABLE;
+
 	if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) {
 		ret_code = I40E_ERR_FIRMWARE_API_VERSION;
 		goto init_adminq_free_arq;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 5d5f422cbae5..b0188b8f91ba 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -34,7 +34,15 @@
  */
 
 #define I40E_FW_API_VERSION_MAJOR	0x0001
-#define I40E_FW_API_VERSION_MINOR	0x0005
+#define I40E_FW_API_VERSION_MINOR_X722	0x0005
+#define I40E_FW_API_VERSION_MINOR_X710	0x0007
+
+#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \
+					I40E_FW_API_VERSION_MINOR_X710 : \
+					I40E_FW_API_VERSION_MINOR_X722)
+
+/* API version 1.7 implements additional link and PHY-specific APIs  */
+#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007
 
 struct i40e_aq_desc {
 	__le16 flags;
@@ -236,6 +244,8 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_set_phy_debug		= 0x0622,
 	i40e_aqc_opc_upload_ext_phy_fm		= 0x0625,
 	i40e_aqc_opc_run_phy_activity		= 0x0626,
+	i40e_aqc_opc_set_phy_register		= 0x0628,
+	i40e_aqc_opc_get_phy_register		= 0x0629,
 
 	/* NVM commands */
 	i40e_aqc_opc_nvm_read			= 0x0701,
@@ -765,7 +775,50 @@ struct i40e_aqc_set_switch_config {
 #define I40E_AQ_SET_SWITCH_CFG_PROMISC		0x0001
 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER	0x0002
 	__le16	valid_flags;
-	u8	reserved[12];
+	/* The ethertype in switch_tag is dropped on ingress and used
+	 * internally by the switch. Set this to zero for the default
+	 * of 0x88a8 (802.1ad). Should be zero for firmware API
+	 * versions lower than 1.7.
+	 */
+	__le16	switch_tag;
+	/* The ethertypes in first_tag and second_tag are used to
+	 * match the outer and inner VLAN tags (respectively) when HW
+	 * double VLAN tagging is enabled via the set port parameters
+	 * AQ command. Otherwise these are both ignored. Set them to
+	 * zero for their defaults of 0x8100 (802.1Q). Should be zero
+	 * for firmware API versions lower than 1.7.
+	 */
+	__le16	first_tag;
+	__le16	second_tag;
+	/* Next byte is split into following:
+	 * Bit 7    : 0 : No action, 1: Switch to mode defined by bits 6:0
+	 * Bit 6    : 0 : Destination Port, 1: source port
+	 * Bit 5..4 : L4 type
+	 * 0: rsvd
+	 * 1: TCP
+	 * 2: UDP
+	 * 3: Both TCP and UDP
+	 * Bits 3:0 Mode
+	 * 0: default mode
+	 * 1: L4 port only mode
+	 * 2: non-tunneled mode
+	 * 3: tunneled mode
+	 */
+#define I40E_AQ_SET_SWITCH_BIT7_VALID		0x80
+
+#define I40E_AQ_SET_SWITCH_L4_SRC_PORT		0x40
+
+#define I40E_AQ_SET_SWITCH_L4_TYPE_RSVD		0x00
+#define I40E_AQ_SET_SWITCH_L4_TYPE_TCP		0x10
+#define I40E_AQ_SET_SWITCH_L4_TYPE_UDP		0x20
+#define I40E_AQ_SET_SWITCH_L4_TYPE_BOTH		0x30
+
+#define I40E_AQ_SET_SWITCH_MODE_DEFAULT		0x00
+#define I40E_AQ_SET_SWITCH_MODE_L4_PORT		0x01
+#define I40E_AQ_SET_SWITCH_MODE_NON_TUNNEL	0x02
+#define I40E_AQ_SET_SWITCH_MODE_TUNNEL		0x03
+	u8	mode;
+	u8	rsvd5[5];
 };
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config);
@@ -1318,14 +1371,16 @@ struct i40e_aqc_add_remove_cloud_filters {
 #define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT	0
 #define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_MASK	(0x3FF << \
 					I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT)
-	u8	reserved2[4];
+	u8	big_buffer_flag;
+#define I40E_AQC_ADD_CLOUD_CMD_BB	1
+	u8	reserved2[3];
 	__le32	addr_high;
 	__le32	addr_low;
 };
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_cloud_filters);
 
-struct i40e_aqc_add_remove_cloud_filters_element_data {
+struct i40e_aqc_cloud_filters_element_data {
 	u8	outer_mac[6];
 	u8	inner_mac[6];
 	__le16	inner_vlan;
@@ -1337,6 +1392,9 @@ struct i40e_aqc_add_remove_cloud_filters_element_data {
 		struct {
 			u8 data[16];
 		} v6;
+		struct {
+			__le16 data[8];
+		} raw_v6;
 	} ipaddr;
 	__le16	flags;
 #define I40E_AQC_ADD_CLOUD_FILTER_SHIFT			0
@@ -1355,6 +1413,10 @@ struct i40e_aqc_add_remove_cloud_filters_element_data {
 #define I40E_AQC_ADD_CLOUD_FILTER_IMAC			0x000A
 #define I40E_AQC_ADD_CLOUD_FILTER_OMAC_TEN_ID_IMAC	0x000B
 #define I40E_AQC_ADD_CLOUD_FILTER_IIP			0x000C
+/* 0x0010 to 0x0017 is for custom filters */
+#define I40E_AQC_ADD_CLOUD_FILTER_IP_PORT		0x0010 /* Dest IP + L4 Port */
+#define I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT		0x0011 /* Dest MAC + L4 Port */
+#define I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT		0x0012 /* Dest MAC + VLAN + L4 Port */
 
 #define I40E_AQC_ADD_CLOUD_FLAGS_TO_QUEUE		0x0080
 #define I40E_AQC_ADD_CLOUD_VNK_SHIFT			6
@@ -1389,6 +1451,49 @@ struct i40e_aqc_add_remove_cloud_filters_element_data {
 	u8	response_reserved[7];
 };
 
+I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_cloud_filters_element_data);
+
+/* i40e_aqc_cloud_filters_element_bb is used when
+ * I40E_AQC_CLOUD_CMD_BB flag is set.
+ */
+struct i40e_aqc_cloud_filters_element_bb {
+	struct i40e_aqc_cloud_filters_element_data element;
+	u16     general_fields[32];
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD0	0
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD1	1
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD2	2
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD0	3
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD1	4
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD2	5
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD0	6
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD1	7
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD2	8
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD0	9
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD1	10
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD2	11
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD0	12
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD1	13
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD2	14
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD0	15
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD1	16
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD2	17
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD3	18
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD4	19
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD5	20
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD6	21
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD7	22
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD0	23
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD1	24
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD2	25
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD3	26
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD4	27
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD5	28
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD6	29
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD7	30
+};
+
+I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_cloud_filters_element_bb);
+
 struct i40e_aqc_remove_cloud_filters_completion {
 	__le16 perfect_ovlan_used;
 	__le16 perfect_ovlan_free;
@@ -1400,6 +1505,60 @@ struct i40e_aqc_remove_cloud_filters_completion {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_cloud_filters_completion);
 
+/* Replace filter Command 0x025F
+ * uses the i40e_aqc_replace_cloud_filters,
+ * and the generic indirect completion structure
+ */
+struct i40e_filter_data {
+	u8 filter_type;
+	u8 input[3];
+};
+
+I40E_CHECK_STRUCT_LEN(4, i40e_filter_data);
+
+struct i40e_aqc_replace_cloud_filters_cmd {
+	u8      valid_flags;
+#define I40E_AQC_REPLACE_L1_FILTER		0x0
+#define I40E_AQC_REPLACE_CLOUD_FILTER		0x1
+#define I40E_AQC_GET_CLOUD_FILTERS		0x2
+#define I40E_AQC_MIRROR_CLOUD_FILTER		0x4
+#define I40E_AQC_HIGH_PRIORITY_CLOUD_FILTER	0x8
+	u8      old_filter_type;
+	u8      new_filter_type;
+	u8      tr_bit;
+	u8      reserved[4];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_replace_cloud_filters_cmd);
+
+struct i40e_aqc_replace_cloud_filters_cmd_buf {
+	u8      data[32];
+/* Filter type INPUT codes*/
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_ENTRIES_MAX	3
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_VALIDATED	BIT(7)
+
+/* Field Vector offsets */
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_MAC_DA	0
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_ETH	6
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG	7
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_VLAN	8
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_OVLAN	9
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_IVLAN	10
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_TUNNLE_KEY	11
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IMAC	12
+/* big FLU */
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IP_DA	14
+/* big FLU */
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_OIP_DA	15
+
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_INNER_VLAN	37
+	struct i40e_filter_data filters[8];
+};
+
+I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_replace_cloud_filters_cmd_buf);
+
 /* Add Mirror Rule (indirect or direct 0x0260)
  * Delete Mirror Rule (indirect or direct 0x0261)
  * note: some rule types (4,5) do not use an external buffer.
@@ -1726,6 +1885,8 @@ enum i40e_aq_phy_type {
 	I40E_PHY_TYPE_10GBASE_CR1_CU		= 0xB,
 	I40E_PHY_TYPE_10GBASE_AOC		= 0xC,
 	I40E_PHY_TYPE_40GBASE_AOC		= 0xD,
+	I40E_PHY_TYPE_UNRECOGNIZED		= 0xE,
+	I40E_PHY_TYPE_UNSUPPORTED		= 0xF,
 	I40E_PHY_TYPE_100BASE_TX		= 0x11,
 	I40E_PHY_TYPE_1000BASE_T		= 0x12,
 	I40E_PHY_TYPE_10GBASE_T			= 0x13,
@@ -1744,7 +1905,12 @@ enum i40e_aq_phy_type {
 	I40E_PHY_TYPE_25GBASE_CR		= 0x20,
 	I40E_PHY_TYPE_25GBASE_SR		= 0x21,
 	I40E_PHY_TYPE_25GBASE_LR		= 0x22,
-	I40E_PHY_TYPE_MAX
+	I40E_PHY_TYPE_25GBASE_AOC		= 0x23,
+	I40E_PHY_TYPE_25GBASE_ACC		= 0x24,
+	I40E_PHY_TYPE_MAX,
+	I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP	= 0xFD,
+	I40E_PHY_TYPE_EMPTY			= 0xFE,
+	I40E_PHY_TYPE_DEFAULT			= 0xFF,
 };
 
 #define I40E_LINK_SPEED_100MB_SHIFT	0x1
@@ -1801,6 +1967,8 @@ struct i40e_aq_get_phy_abilities_resp {
 #define I40E_AQ_PHY_TYPE_EXT_25G_CR	0X02
 #define I40E_AQ_PHY_TYPE_EXT_25G_SR	0x04
 #define I40E_AQ_PHY_TYPE_EXT_25G_LR	0x08
+#define I40E_AQ_PHY_TYPE_EXT_25G_AOC	0x10
+#define I40E_AQ_PHY_TYPE_EXT_25G_ACC	0x20
 	u8	fec_cfg_curr_mod_ext_info;
 #define I40E_AQ_ENABLE_FEC_KR		0x01
 #define I40E_AQ_ENABLE_FEC_RS		0x02
@@ -1934,19 +2102,31 @@ struct i40e_aqc_get_link_status {
 #define I40E_AQ_25G_SERDES_UCODE_ERR	0X04
 #define I40E_AQ_25G_NIMB_UCODE_ERR	0X05
 	u8	loopback; /* use defines from i40e_aqc_set_lb_mode */
+/* Since firmware API 1.7 loopback field keeps power class info as well */
+#define I40E_AQ_LOOPBACK_MASK		0x07
+#define I40E_AQ_PWR_CLASS_SHIFT_LB	6
+#define I40E_AQ_PWR_CLASS_MASK_LB	(0x03 << I40E_AQ_PWR_CLASS_SHIFT_LB)
 	__le16	max_frame_size;
 	u8	config;
 #define I40E_AQ_CONFIG_FEC_KR_ENA	0x01
 #define I40E_AQ_CONFIG_FEC_RS_ENA	0x02
 #define I40E_AQ_CONFIG_CRC_ENA		0x04
 #define I40E_AQ_CONFIG_PACING_MASK	0x78
-	u8	power_desc;
+	union {
+		struct {
+			u8	power_desc;
 #define I40E_AQ_LINK_POWER_CLASS_1	0x00
 #define I40E_AQ_LINK_POWER_CLASS_2	0x01
 #define I40E_AQ_LINK_POWER_CLASS_3	0x02
 #define I40E_AQ_LINK_POWER_CLASS_4	0x03
 #define I40E_AQ_PWR_CLASS_MASK		0x03
-	u8	reserved[4];
+			u8	reserved[4];
+		};
+		struct {
+			u8	link_type[4];
+			u8	link_type_ext;
+		};
+	};
 };
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status);
@@ -2029,6 +2209,22 @@ struct i40e_aqc_run_phy_activity {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity);
 
+/* Set PHY Register command (0x0628) */
+/* Get PHY Register command (0x0629) */
+struct i40e_aqc_phy_register_access {
+	u8	phy_interface;
+#define I40E_AQ_PHY_REG_ACCESS_INTERNAL	0
+#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL	1
+#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE	2
+	u8	dev_address;
+	u8	reserved1[2];
+	__le32	reg_address;
+	__le32	reg_value;
+	u8	reserved2[4];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access);
+
 /* NVM Read command (indirect 0x0701)
  * NVM Erase commands (direct 0x0702)
  * NVM Update commands (indirect 0x0703)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 111426ba5fbc..0203665cb53c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1180,6 +1180,8 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw)
 	case I40E_PHY_TYPE_40GBASE_AOC:
 	case I40E_PHY_TYPE_10GBASE_AOC:
 	case I40E_PHY_TYPE_25GBASE_CR:
+	case I40E_PHY_TYPE_25GBASE_AOC:
+	case I40E_PHY_TYPE_25GBASE_ACC:
 		media = I40E_MEDIA_TYPE_DA;
 		break;
 	case I40E_PHY_TYPE_1000BASE_KX:
@@ -1567,34 +1569,57 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw,
 	struct i40e_aq_desc desc;
 	i40e_status status;
 	u16 abilities_size = sizeof(struct i40e_aq_get_phy_abilities_resp);
+	u16 max_delay = I40E_MAX_PHY_TIMEOUT, total_delay = 0;
 
 	if (!abilities)
 		return I40E_ERR_PARAM;
 
-	i40e_fill_default_direct_cmd_desc(&desc,
-					  i40e_aqc_opc_get_phy_abilities);
+	do {
+		i40e_fill_default_direct_cmd_desc(&desc,
+					       i40e_aqc_opc_get_phy_abilities);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
-	if (abilities_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+		if (abilities_size > I40E_AQ_LARGE_BUF)
+			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
 
-	if (qualified_modules)
-		desc.params.external.param0 |=
+		if (qualified_modules)
+			desc.params.external.param0 |=
 			cpu_to_le32(I40E_AQ_PHY_REPORT_QUALIFIED_MODULES);
 
-	if (report_init)
-		desc.params.external.param0 |=
+		if (report_init)
+			desc.params.external.param0 |=
 			cpu_to_le32(I40E_AQ_PHY_REPORT_INITIAL_VALUES);
 
-	status = i40e_asq_send_command(hw, &desc, abilities, abilities_size,
-				       cmd_details);
+		status = i40e_asq_send_command(hw, &desc, abilities,
+					       abilities_size, cmd_details);
 
-	if (hw->aq.asq_last_status == I40E_AQ_RC_EIO)
-		status = I40E_ERR_UNKNOWN_PHY;
+		if (status)
+			break;
+
+		if (hw->aq.asq_last_status == I40E_AQ_RC_EIO) {
+			status = I40E_ERR_UNKNOWN_PHY;
+			break;
+		} else if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN) {
+			usleep_range(1000, 2000);
+			total_delay++;
+			status = I40E_ERR_TIMEOUT;
+		}
+	} while ((hw->aq.asq_last_status != I40E_AQ_RC_OK) &&
+		 (total_delay < max_delay));
+
+	if (status)
+		return status;
 
 	if (report_init) {
-		hw->phy.phy_types = le32_to_cpu(abilities->phy_type);
-		hw->phy.phy_types |= ((u64)abilities->phy_type_ext << 32);
+		if (hw->mac.type ==  I40E_MAC_XL710 &&
+		    hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
+		    hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) {
+			status = i40e_aq_get_link_info(hw, true, NULL, NULL);
+		} else {
+			hw->phy.phy_types = le32_to_cpu(abilities->phy_type);
+			hw->phy.phy_types |=
+					((u64)abilities->phy_type_ext << 32);
+		}
 	}
 
 	return status;
@@ -1819,7 +1844,7 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw,
 	hw_link_info->fec_info = resp->config & (I40E_AQ_CONFIG_FEC_KR_ENA |
 						 I40E_AQ_CONFIG_FEC_RS_ENA);
 	hw_link_info->ext_info = resp->ext_info;
-	hw_link_info->loopback = resp->loopback;
+	hw_link_info->loopback = resp->loopback & I40E_AQ_LOOPBACK_MASK;
 	hw_link_info->max_frame_size = le16_to_cpu(resp->max_frame_size);
 	hw_link_info->pacing = resp->config & I40E_AQ_CONFIG_PACING_MASK;
 
@@ -1850,6 +1875,15 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw,
 	     hw->aq.fw_min_ver < 40)) && hw_link_info->phy_type == 0xE)
 		hw_link_info->phy_type = I40E_PHY_TYPE_10GBASE_SFPP_CU;
 
+	if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
+	    hw->aq.api_min_ver >= 7) {
+		__le32 tmp;
+
+		memcpy(&tmp, resp->link_type, sizeof(tmp));
+		hw->phy.phy_types = le32_to_cpu(tmp);
+		hw->phy.phy_types |= ((u64)resp->link_type_ext << 32);
+	}
+
 	/* save link status information */
 	if (link)
 		*link = *hw_link_info;
@@ -2373,13 +2407,14 @@ i40e_status i40e_aq_get_switch_config(struct i40e_hw *hw,
  * @hw: pointer to the hardware structure
  * @flags: bit flag values to set
  * @valid_flags: which bit flags to set
+ * @mode: cloud filter mode
  * @cmd_details: pointer to command details structure or NULL
  *
  * Set switch configuration bits
  **/
 enum i40e_status_code i40e_aq_set_switch_config(struct i40e_hw *hw,
 						u16 flags,
-						u16 valid_flags,
+						u16 valid_flags, u8 mode,
 				struct i40e_asq_cmd_details *cmd_details)
 {
 	struct i40e_aq_desc desc;
@@ -2391,7 +2426,12 @@ enum i40e_status_code i40e_aq_set_switch_config(struct i40e_hw *hw,
 					  i40e_aqc_opc_set_switch_config);
 	scfg->flags = cpu_to_le16(flags);
 	scfg->valid_flags = cpu_to_le16(valid_flags);
-
+	scfg->mode = mode;
+	if (hw->flags & I40E_HW_FLAG_802_1AD_CAPABLE) {
+		scfg->switch_tag = cpu_to_le16(hw->switch_tag);
+		scfg->first_tag = cpu_to_le16(hw->first_tag);
+		scfg->second_tag = cpu_to_le16(hw->second_tag);
+	}
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
 
 	return status;
@@ -4826,6 +4866,74 @@ phy_blinking_end:
 }
 
 /**
+ * i40e_led_get_reg - read LED register
+ * @hw: pointer to the HW structure
+ * @led_addr: LED register address
+ * @reg_val: read register value
+ **/
+static enum i40e_status_code i40e_led_get_reg(struct i40e_hw *hw, u16 led_addr,
+					      u32 *reg_val)
+{
+	enum i40e_status_code status;
+	u8 phy_addr = 0;
+	u8 port_num;
+	u32 i;
+
+	*reg_val = 0;
+	if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) {
+		status =
+		       i40e_aq_get_phy_register(hw,
+						I40E_AQ_PHY_REG_ACCESS_EXTERNAL,
+						I40E_PHY_COM_REG_PAGE,
+						I40E_PHY_LED_PROV_REG_1,
+						reg_val, NULL);
+	} else {
+		i = rd32(hw, I40E_PFGEN_PORTNUM);
+		port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
+		phy_addr = i40e_get_phy_address(hw, port_num);
+		status = i40e_read_phy_register_clause45(hw,
+							 I40E_PHY_COM_REG_PAGE,
+							 led_addr, phy_addr,
+							 (u16 *)reg_val);
+	}
+	return status;
+}
+
+/**
+ * i40e_led_set_reg - write LED register
+ * @hw: pointer to the HW structure
+ * @led_addr: LED register address
+ * @reg_val: register value to write
+ **/
+static enum i40e_status_code i40e_led_set_reg(struct i40e_hw *hw, u16 led_addr,
+					      u32 reg_val)
+{
+	enum i40e_status_code status;
+	u8 phy_addr = 0;
+	u8 port_num;
+	u32 i;
+
+	if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) {
+		status =
+		       i40e_aq_set_phy_register(hw,
+						I40E_AQ_PHY_REG_ACCESS_EXTERNAL,
+						I40E_PHY_COM_REG_PAGE,
+						I40E_PHY_LED_PROV_REG_1,
+						reg_val, NULL);
+	} else {
+		i = rd32(hw, I40E_PFGEN_PORTNUM);
+		port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
+		phy_addr = i40e_get_phy_address(hw, port_num);
+		status = i40e_write_phy_register_clause45(hw,
+							  I40E_PHY_COM_REG_PAGE,
+							  led_addr, phy_addr,
+							  (u16)reg_val);
+	}
+
+	return status;
+}
+
+/**
  * i40e_led_get_phy - return current on/off mode
  * @hw: pointer to the hw struct
  * @led_addr: address of led register to use
@@ -4842,7 +4950,19 @@ i40e_status i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr,
 	u16 temp_addr;
 	u8 port_num;
 	u32 i;
-
+	u32 reg_val_aq;
+
+	if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) {
+		status =
+		      i40e_aq_get_phy_register(hw,
+					       I40E_AQ_PHY_REG_ACCESS_EXTERNAL,
+					       I40E_PHY_COM_REG_PAGE,
+					       I40E_PHY_LED_PROV_REG_1,
+					       &reg_val_aq, NULL);
+		if (status == I40E_SUCCESS)
+			*val = (u16)reg_val_aq;
+		return status;
+	}
 	temp_addr = I40E_PHY_LED_PROV_REG_1;
 	i = rd32(hw, I40E_PFGEN_PORTNUM);
 	port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
@@ -4877,51 +4997,38 @@ i40e_status i40e_led_set_phy(struct i40e_hw *hw, bool on,
 			     u16 led_addr, u32 mode)
 {
 	i40e_status status = 0;
-	u16 led_ctl = 0;
-	u16 led_reg = 0;
-	u8 phy_addr = 0;
-	u8 port_num;
-	u32 i;
+	u32 led_ctl = 0;
+	u32 led_reg = 0;
 
-	i = rd32(hw, I40E_PFGEN_PORTNUM);
-	port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
-	phy_addr = i40e_get_phy_address(hw, port_num);
-	status = i40e_read_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE,
-						 led_addr, phy_addr, &led_reg);
+	status = i40e_led_get_reg(hw, led_addr, &led_reg);
 	if (status)
 		return status;
 	led_ctl = led_reg;
 	if (led_reg & I40E_PHY_LED_LINK_MODE_MASK) {
 		led_reg = 0;
-		status = i40e_write_phy_register_clause45(hw,
-							  I40E_PHY_COM_REG_PAGE,
-							  led_addr, phy_addr,
-							  led_reg);
+		status = i40e_led_set_reg(hw, led_addr, led_reg);
 		if (status)
 			return status;
 	}
-	status = i40e_read_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE,
-						 led_addr, phy_addr, &led_reg);
+	status = i40e_led_get_reg(hw, led_addr, &led_reg);
 	if (status)
 		goto restore_config;
 	if (on)
 		led_reg = I40E_PHY_LED_MANUAL_ON;
 	else
 		led_reg = 0;
-	status = i40e_write_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE,
-						  led_addr, phy_addr, led_reg);
+
+	status = i40e_led_set_reg(hw, led_addr, led_reg);
 	if (status)
 		goto restore_config;
 	if (mode & I40E_PHY_LED_MODE_ORIG) {
 		led_ctl = (mode & I40E_PHY_LED_MODE_MASK);
-		status = i40e_write_phy_register_clause45(hw,
-						 I40E_PHY_COM_REG_PAGE,
-						 led_addr, phy_addr, led_ctl);
+		status = i40e_led_set_reg(hw, led_addr, led_ctl);
 	}
 	return status;
+
 restore_config:
-	status = i40e_write_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE,
-						  led_addr, phy_addr, led_ctl);
+	status = i40e_led_set_reg(hw, led_addr, led_ctl);
 	return status;
 }
 
@@ -5052,6 +5159,75 @@ do_retry:
 }
 
 /**
+ * i40e_aq_set_phy_register
+ * @hw: pointer to the hw struct
+ * @phy_select: select which phy should be accessed
+ * @dev_addr: PHY device address
+ * @reg_addr: PHY register address
+ * @reg_val: new register value
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Write the external PHY register.
+ **/
+i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw,
+				     u8 phy_select, u8 dev_addr,
+				     u32 reg_addr, u32 reg_val,
+				     struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_phy_register_access *cmd =
+		(struct i40e_aqc_phy_register_access *)&desc.params.raw;
+	i40e_status status;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_set_phy_register);
+
+	cmd->phy_interface = phy_select;
+	cmd->dev_address = dev_addr;
+	cmd->reg_address = cpu_to_le32(reg_addr);
+	cmd->reg_value = cpu_to_le32(reg_val);
+
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+	return status;
+}
+
+/**
+ * i40e_aq_get_phy_register
+ * @hw: pointer to the hw struct
+ * @phy_select: select which phy should be accessed
+ * @dev_addr: PHY device address
+ * @reg_addr: PHY register address
+ * @reg_val: read register value
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Read the external PHY register.
+ **/
+i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw,
+				     u8 phy_select, u8 dev_addr,
+				     u32 reg_addr, u32 *reg_val,
+				     struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_phy_register_access *cmd =
+		(struct i40e_aqc_phy_register_access *)&desc.params.raw;
+	i40e_status status;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_get_phy_register);
+
+	cmd->phy_interface = phy_select;
+	cmd->dev_address = dev_addr;
+	cmd->reg_address = cpu_to_le32(reg_addr);
+
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+	if (!status)
+		*reg_val = le32_to_cpu(cmd->reg_value);
+
+	return status;
+}
+
+/**
  * i40e_aq_write_ppp - Write pipeline personalization profile (ppp)
  * @hw: pointer to the hw struct
  * @buff: command buffer (size in bytes = buff_size)
@@ -5260,5 +5436,194 @@ i40e_add_pinfo_to_list(struct i40e_hw *hw,
 
 	status = i40e_aq_write_ppp(hw, (void *)sec, sec->data_end,
 				   track_id, &offset, &info, NULL);
+
+	return status;
+}
+
+/**
+ * i40e_aq_add_cloud_filters
+ * @hw: pointer to the hardware structure
+ * @seid: VSI seid to add cloud filters from
+ * @filters: Buffer which contains the filters to be added
+ * @filter_count: number of filters contained in the buffer
+ *
+ * Set the cloud filters for a given VSI.  The contents of the
+ * i40e_aqc_cloud_filters_element_data are filled in by the caller
+ * of the function.
+ *
+ **/
+enum i40e_status_code
+i40e_aq_add_cloud_filters(struct i40e_hw *hw, u16 seid,
+			  struct i40e_aqc_cloud_filters_element_data *filters,
+			  u8 filter_count)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_add_remove_cloud_filters *cmd =
+	(struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+	enum i40e_status_code status;
+	u16 buff_len;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_add_cloud_filters);
+
+	buff_len = filter_count * sizeof(*filters);
+	desc.datalen = cpu_to_le16(buff_len);
+	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	cmd->num_filters = filter_count;
+	cmd->seid = cpu_to_le16(seid);
+
+	status = i40e_asq_send_command(hw, &desc, filters, buff_len, NULL);
+
+	return status;
+}
+
+/**
+ * i40e_aq_add_cloud_filters_bb
+ * @hw: pointer to the hardware structure
+ * @seid: VSI seid to add cloud filters from
+ * @filters: Buffer which contains the filters in big buffer to be added
+ * @filter_count: number of filters contained in the buffer
+ *
+ * Set the big buffer cloud filters for a given VSI.  The contents of the
+ * i40e_aqc_cloud_filters_element_bb are filled in by the caller of the
+ * function.
+ *
+ **/
+i40e_status
+i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
+			     struct i40e_aqc_cloud_filters_element_bb *filters,
+			     u8 filter_count)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_add_remove_cloud_filters *cmd =
+	(struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+	i40e_status status;
+	u16 buff_len;
+	int i;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_add_cloud_filters);
+
+	buff_len = filter_count * sizeof(*filters);
+	desc.datalen = cpu_to_le16(buff_len);
+	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	cmd->num_filters = filter_count;
+	cmd->seid = cpu_to_le16(seid);
+	cmd->big_buffer_flag = I40E_AQC_ADD_CLOUD_CMD_BB;
+
+	for (i = 0; i < filter_count; i++) {
+		u16 tnl_type;
+		u32 ti;
+
+		tnl_type = (le16_to_cpu(filters[i].element.flags) &
+			   I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK) >>
+			   I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT;
+
+		/* Due to hardware eccentricities, the VNI for Geneve is shifted
+		 * one more byte further than normally used for Tenant ID in
+		 * other tunnel types.
+		 */
+		if (tnl_type == I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE) {
+			ti = le32_to_cpu(filters[i].element.tenant_id);
+			filters[i].element.tenant_id = cpu_to_le32(ti << 8);
+		}
+	}
+
+	status = i40e_asq_send_command(hw, &desc, filters, buff_len, NULL);
+
+	return status;
+}
+
+/**
+ * i40e_aq_rem_cloud_filters
+ * @hw: pointer to the hardware structure
+ * @seid: VSI seid to remove cloud filters from
+ * @filters: Buffer which contains the filters to be removed
+ * @filter_count: number of filters contained in the buffer
+ *
+ * Remove the cloud filters for a given VSI.  The contents of the
+ * i40e_aqc_cloud_filters_element_data are filled in by the caller
+ * of the function.
+ *
+ **/
+enum i40e_status_code
+i40e_aq_rem_cloud_filters(struct i40e_hw *hw, u16 seid,
+			  struct i40e_aqc_cloud_filters_element_data *filters,
+			  u8 filter_count)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_add_remove_cloud_filters *cmd =
+	(struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+	enum i40e_status_code status;
+	u16 buff_len;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_remove_cloud_filters);
+
+	buff_len = filter_count * sizeof(*filters);
+	desc.datalen = cpu_to_le16(buff_len);
+	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	cmd->num_filters = filter_count;
+	cmd->seid = cpu_to_le16(seid);
+
+	status = i40e_asq_send_command(hw, &desc, filters, buff_len, NULL);
+
+	return status;
+}
+
+/**
+ * i40e_aq_rem_cloud_filters_bb
+ * @hw: pointer to the hardware structure
+ * @seid: VSI seid to remove cloud filters from
+ * @filters: Buffer which contains the filters in big buffer to be removed
+ * @filter_count: number of filters contained in the buffer
+ *
+ * Remove the big buffer cloud filters for a given VSI.  The contents of the
+ * i40e_aqc_cloud_filters_element_bb are filled in by the caller of the
+ * function.
+ *
+ **/
+i40e_status
+i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
+			     struct i40e_aqc_cloud_filters_element_bb *filters,
+			     u8 filter_count)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_add_remove_cloud_filters *cmd =
+	(struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+	i40e_status status;
+	u16 buff_len;
+	int i;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_remove_cloud_filters);
+
+	buff_len = filter_count * sizeof(*filters);
+	desc.datalen = cpu_to_le16(buff_len);
+	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	cmd->num_filters = filter_count;
+	cmd->seid = cpu_to_le16(seid);
+	cmd->big_buffer_flag = I40E_AQC_ADD_CLOUD_CMD_BB;
+
+	for (i = 0; i < filter_count; i++) {
+		u16 tnl_type;
+		u32 ti;
+
+		tnl_type = (le16_to_cpu(filters[i].element.flags) &
+			   I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK) >>
+			   I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT;
+
+		/* Due to hardware eccentricities, the VNI for Geneve is shifted
+		 * one more byte further than normally used for Tenant ID in
+		 * other tunnel types.
+		 */
+		if (tnl_type == I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE) {
+			ti = le32_to_cpu(filters[i].element.tenant_id);
+			filters[i].element.tenant_id = cpu_to_le32(ti << 8);
+		}
+	}
+
+	status = i40e_asq_send_command(hw, &desc, filters, buff_len, NULL);
+
 	return status;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 8f326f87a815..2b8bbc84e34f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -278,8 +278,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 			 rx_ring->netdev,
 			 rx_ring->rx_bi);
 		dev_info(&pf->pdev->dev,
-			 "    rx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n",
-			 i, rx_ring->state,
+			 "    rx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n",
+			 i, *rx_ring->state,
 			 rx_ring->queue_index,
 			 rx_ring->reg_idx);
 		dev_info(&pf->pdev->dev,
@@ -334,8 +334,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 			 tx_ring->netdev,
 			 tx_ring->tx_bi);
 		dev_info(&pf->pdev->dev,
-			 "    tx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n",
-			 i, tx_ring->state,
+			 "    tx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n",
+			 i, *tx_ring->state,
 			 tx_ring->queue_index,
 			 tx_ring->reg_idx);
 		dev_info(&pf->pdev->dev,
@@ -798,8 +798,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 		 */
 		if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
 			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
-			i40e_do_reset_safe(pf,
-					   BIT_ULL(__I40E_PF_RESET_REQUESTED));
+			i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
 		}
 
 		vsi = i40e_vsi_setup(pf, I40E_VSI_VMDQ2, vsi_seid, 0);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.c b/drivers/net/ethernet/intel/i40e/i40e_diag.c
index f141e78d409e..76ed56641864 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_diag.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_diag.c
@@ -36,7 +36,9 @@
 static i40e_status i40e_diag_reg_pattern_test(struct i40e_hw *hw,
 							u32 reg, u32 mask)
 {
-	const u32 patterns[] = {0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF};
+	static const u32 patterns[] = {
+		0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF
+	};
 	u32 pat, val, orig_val;
 	int i;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 05e89864f781..dc9b8dcf4a1e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -227,6 +227,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = {
 	I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENABLED, 0),
 	I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_ENABLED, 0),
 	I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0),
+	I40E_PRIV_FLAG("disable-source-pruning",
+		       I40E_FLAG_SOURCE_PRUNING_DISABLED, 0),
 };
 
 #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags)
@@ -251,428 +253,557 @@ static void i40e_partition_setting_complaint(struct i40e_pf *pf)
 
 /**
  * i40e_phy_type_to_ethtool - convert the phy_types to ethtool link modes
- * @phy_types: PHY types to convert
- * @supported: pointer to the ethtool supported variable to fill in
- * @advertising: pointer to the ethtool advertising variable to fill in
+ * @pf: PF struct with phy_types
+ * @ks: ethtool link ksettings struct to fill out
  *
  **/
-static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
-				     u32 *advertising)
+static void i40e_phy_type_to_ethtool(struct i40e_pf *pf,
+				     struct ethtool_link_ksettings *ks)
 {
 	struct i40e_link_status *hw_link_info = &pf->hw.phy.link_info;
 	u64 phy_types = pf->hw.phy.phy_types;
 
-	*supported = 0x0;
-	*advertising = 0x0;
+	ethtool_link_ksettings_zero_link_mode(ks, supported);
+	ethtool_link_ksettings_zero_link_mode(ks, advertising);
 
 	if (phy_types & I40E_CAP_PHY_TYPE_SGMII) {
-		*supported |= SUPPORTED_Autoneg |
-			      SUPPORTED_1000baseT_Full;
-		*advertising |= ADVERTISED_Autoneg;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     1000baseT_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
-			*advertising |= ADVERTISED_1000baseT_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     1000baseT_Full);
 		if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) {
-			*supported |= SUPPORTED_100baseT_Full;
-			*advertising |= ADVERTISED_100baseT_Full;
+			ethtool_link_ksettings_add_link_mode(ks, supported,
+							     100baseT_Full);
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     100baseT_Full);
 		}
 	}
 	if (phy_types & I40E_CAP_PHY_TYPE_XAUI ||
 	    phy_types & I40E_CAP_PHY_TYPE_XFI ||
 	    phy_types & I40E_CAP_PHY_TYPE_SFI ||
 	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU ||
-	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_AOC)
-		*supported |= SUPPORTED_10000baseT_Full;
-	if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU ||
-	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 ||
-	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_T ||
-	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR ||
-	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR) {
-		*supported |= SUPPORTED_Autoneg |
-			      SUPPORTED_10000baseT_Full;
-		*advertising |= ADVERTISED_Autoneg;
+	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_AOC) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseT_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     10000baseT_Full);
+	}
+	if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_T) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseT_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
-			*advertising |= ADVERTISED_10000baseT_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     10000baseT_Full);
 	}
 	if (phy_types & I40E_CAP_PHY_TYPE_XLAUI ||
 	    phy_types & I40E_CAP_PHY_TYPE_XLPPI ||
 	    phy_types & I40E_CAP_PHY_TYPE_40GBASE_AOC)
-		*supported |= SUPPORTED_40000baseCR4_Full;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     40000baseCR4_Full);
 	if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4_CU ||
 	    phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4) {
-		*supported |= SUPPORTED_Autoneg |
-			      SUPPORTED_40000baseCR4_Full;
-		*advertising |= ADVERTISED_Autoneg;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     40000baseCR4_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_40GB)
-			*advertising |= ADVERTISED_40000baseCR4_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     40000baseCR4_Full);
 	}
 	if (phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) {
-		*supported |= SUPPORTED_Autoneg |
-			      SUPPORTED_100baseT_Full;
-		*advertising |= ADVERTISED_Autoneg;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100baseT_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB)
-			*advertising |= ADVERTISED_100baseT_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     100baseT_Full);
 	}
-	if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_T ||
-	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX ||
-	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX ||
-	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL) {
-		*supported |= SUPPORTED_Autoneg |
-			      SUPPORTED_1000baseT_Full;
-		*advertising |= ADVERTISED_Autoneg;
+	if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_T) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     1000baseT_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
-			*advertising |= ADVERTISED_1000baseT_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     1000baseT_Full);
 	}
 	if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_SR4)
-		*supported |= SUPPORTED_40000baseSR4_Full;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     40000baseSR4_Full);
 	if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_LR4)
-		*supported |= SUPPORTED_40000baseLR4_Full;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     40000baseLR4_Full);
 	if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4) {
-		*supported |= SUPPORTED_40000baseKR4_Full |
-			      SUPPORTED_Autoneg;
-		*advertising |= ADVERTISED_40000baseKR4_Full |
-				ADVERTISED_Autoneg;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     40000baseLR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     40000baseLR4_Full);
 	}
 	if (phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2) {
-		*supported |= SUPPORTED_20000baseKR2_Full |
-			      SUPPORTED_Autoneg;
-		*advertising |= ADVERTISED_Autoneg;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     20000baseKR2_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_20GB)
-			*advertising |= ADVERTISED_20000baseKR2_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     20000baseKR2_Full);
 	}
-	if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR) {
-		if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER))
-			*supported |= SUPPORTED_10000baseKR_Full |
-				      SUPPORTED_Autoneg;
-		*advertising |= ADVERTISED_Autoneg;
+	if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseKX4_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
-			if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER))
-				*advertising |= ADVERTISED_10000baseKR_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     10000baseKX4_Full);
 	}
-	if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4) {
-		*supported |= SUPPORTED_10000baseKX4_Full |
-			      SUPPORTED_Autoneg;
-		*advertising |= ADVERTISED_Autoneg;
+	if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR &&
+	    !(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseKR_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
-			*advertising |= ADVERTISED_10000baseKX4_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     10000baseKR_Full);
 	}
-	if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX) {
-		if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER))
-			*supported |= SUPPORTED_1000baseKX_Full |
-				      SUPPORTED_Autoneg;
-		*advertising |= ADVERTISED_Autoneg;
+	if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX &&
+	    !(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     1000baseKX_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
-			if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER))
-				*advertising |= ADVERTISED_1000baseKX_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     1000baseKX_Full);
 	}
-	if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR ||
-	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR ||
-	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR ||
+	/* need to add 25G PHY types */
+	if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     25000baseKR_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     25000baseKR_Full);
+	}
+	if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     25000baseCR_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     25000baseCR_Full);
+	}
+	if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR ||
 	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR) {
-		*supported |= SUPPORTED_Autoneg;
-		*advertising |= ADVERTISED_Autoneg;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     25000baseSR_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     25000baseSR_Full);
+	}
+	if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_AOC ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_ACC) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     25000baseCR_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     25000baseCR_Full);
+	}
+	/* need to add new 10G PHY types */
+	if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 ||
+	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseCR_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     10000baseCR_Full);
+	}
+	if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseSR_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     10000baseSR_Full);
+	}
+	if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseLR_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     10000baseLR_Full);
+	}
+	if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX ||
+	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX ||
+	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     1000baseX_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     1000baseX_Full);
+	}
+	/* Autoneg PHY types */
+	if (phy_types & I40E_CAP_PHY_TYPE_SGMII ||
+	    phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4 ||
+	    phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4_CU ||
+	    phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4 ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR ||
+	    phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2 ||
+	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_T ||
+	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR ||
+	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR ||
+	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4 ||
+	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR ||
+	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU ||
+	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 ||
+	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL ||
+	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_T ||
+	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX ||
+	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX ||
+	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX ||
+	    phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     Autoneg);
 	}
 }
 
 /**
  * i40e_get_settings_link_up - Get the Link settings for when link is up
  * @hw: hw structure
- * @ecmd: ethtool command to fill in
+ * @ks: ethtool ksettings to fill in
  * @netdev: network interface device structure
- *
+ * @pf: pointer to physical function struct
  **/
 static void i40e_get_settings_link_up(struct i40e_hw *hw,
-				      struct ethtool_link_ksettings *cmd,
+				      struct ethtool_link_ksettings *ks,
 				      struct net_device *netdev,
 				      struct i40e_pf *pf)
 {
 	struct i40e_link_status *hw_link_info = &hw->phy.link_info;
+	struct ethtool_link_ksettings cap_ksettings;
 	u32 link_speed = hw_link_info->link_speed;
-	u32 e_advertising = 0x0;
-	u32 e_supported = 0x0;
-	u32 supported, advertising;
-
-	ethtool_convert_link_mode_to_legacy_u32(&supported,
-						cmd->link_modes.supported);
-	ethtool_convert_link_mode_to_legacy_u32(&advertising,
-						cmd->link_modes.advertising);
 
 	/* Initialize supported and advertised settings based on phy settings */
 	switch (hw_link_info->phy_type) {
 	case I40E_PHY_TYPE_40GBASE_CR4:
 	case I40E_PHY_TYPE_40GBASE_CR4_CU:
-		supported = SUPPORTED_Autoneg |
-			    SUPPORTED_40000baseCR4_Full;
-		advertising = ADVERTISED_Autoneg |
-			      ADVERTISED_40000baseCR4_Full;
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     40000baseCR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     40000baseCR4_Full);
 		break;
 	case I40E_PHY_TYPE_XLAUI:
 	case I40E_PHY_TYPE_XLPPI:
 	case I40E_PHY_TYPE_40GBASE_AOC:
-		supported = SUPPORTED_40000baseCR4_Full;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     40000baseCR4_Full);
 		break;
 	case I40E_PHY_TYPE_40GBASE_SR4:
-		supported = SUPPORTED_40000baseSR4_Full;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     40000baseSR4_Full);
 		break;
 	case I40E_PHY_TYPE_40GBASE_LR4:
-		supported = SUPPORTED_40000baseLR4_Full;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     40000baseLR4_Full);
 		break;
+	case I40E_PHY_TYPE_25GBASE_SR:
+	case I40E_PHY_TYPE_25GBASE_LR:
 	case I40E_PHY_TYPE_10GBASE_SR:
 	case I40E_PHY_TYPE_10GBASE_LR:
 	case I40E_PHY_TYPE_1000BASE_SX:
 	case I40E_PHY_TYPE_1000BASE_LX:
-		supported = SUPPORTED_10000baseT_Full;
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     25000baseSR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     25000baseSR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseSR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     10000baseSR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseLR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     10000baseLR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     1000baseX_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     1000baseX_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseT_Full);
 		if (hw_link_info->module_type[2] &
 		    I40E_MODULE_TYPE_1000BASE_SX ||
 		    hw_link_info->module_type[2] &
 		    I40E_MODULE_TYPE_1000BASE_LX) {
-			supported |= SUPPORTED_1000baseT_Full;
+			ethtool_link_ksettings_add_link_mode(ks, supported,
+							     1000baseT_Full);
 			if (hw_link_info->requested_speeds &
 			    I40E_LINK_SPEED_1GB)
-				advertising |= ADVERTISED_1000baseT_Full;
+				ethtool_link_ksettings_add_link_mode(
+				     ks, advertising, 1000baseT_Full);
 		}
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
-			advertising |= ADVERTISED_10000baseT_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     10000baseT_Full);
 		break;
 	case I40E_PHY_TYPE_10GBASE_T:
 	case I40E_PHY_TYPE_1000BASE_T:
 	case I40E_PHY_TYPE_100BASE_TX:
-		supported = SUPPORTED_Autoneg |
-			    SUPPORTED_10000baseT_Full |
-			    SUPPORTED_1000baseT_Full |
-			    SUPPORTED_100baseT_Full;
-		advertising = ADVERTISED_Autoneg;
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseT_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     1000baseT_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100baseT_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
-			advertising |= ADVERTISED_10000baseT_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     10000baseT_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
-			advertising |= ADVERTISED_1000baseT_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     1000baseT_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB)
-			advertising |= ADVERTISED_100baseT_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     100baseT_Full);
 		break;
 	case I40E_PHY_TYPE_1000BASE_T_OPTICAL:
-		supported = SUPPORTED_Autoneg |
-			    SUPPORTED_1000baseT_Full;
-		advertising = ADVERTISED_Autoneg |
-			      ADVERTISED_1000baseT_Full;
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     1000baseT_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     1000baseT_Full);
 		break;
 	case I40E_PHY_TYPE_10GBASE_CR1_CU:
 	case I40E_PHY_TYPE_10GBASE_CR1:
-		supported = SUPPORTED_Autoneg |
-			    SUPPORTED_10000baseT_Full;
-		advertising = ADVERTISED_Autoneg |
-			      ADVERTISED_10000baseT_Full;
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseT_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     10000baseT_Full);
 		break;
 	case I40E_PHY_TYPE_XAUI:
 	case I40E_PHY_TYPE_XFI:
 	case I40E_PHY_TYPE_SFI:
 	case I40E_PHY_TYPE_10GBASE_SFPP_CU:
 	case I40E_PHY_TYPE_10GBASE_AOC:
-		supported = SUPPORTED_10000baseT_Full;
-		advertising = SUPPORTED_10000baseT_Full;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseT_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     10000baseT_Full);
 		break;
 	case I40E_PHY_TYPE_SGMII:
-		supported = SUPPORTED_Autoneg |
-			    SUPPORTED_1000baseT_Full;
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     1000baseT_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
-			advertising |= ADVERTISED_1000baseT_Full;
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     1000baseT_Full);
 		if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) {
-			supported |= SUPPORTED_100baseT_Full;
+			ethtool_link_ksettings_add_link_mode(ks, supported,
+							     100baseT_Full);
 			if (hw_link_info->requested_speeds &
 			    I40E_LINK_SPEED_100MB)
-				advertising |= ADVERTISED_100baseT_Full;
+				ethtool_link_ksettings_add_link_mode(
+				      ks, advertising, 100baseT_Full);
 		}
 		break;
 	case I40E_PHY_TYPE_40GBASE_KR4:
+	case I40E_PHY_TYPE_25GBASE_KR:
 	case I40E_PHY_TYPE_20GBASE_KR2:
 	case I40E_PHY_TYPE_10GBASE_KR:
 	case I40E_PHY_TYPE_10GBASE_KX4:
 	case I40E_PHY_TYPE_1000BASE_KX:
-		supported |= SUPPORTED_40000baseKR4_Full |
-			     SUPPORTED_20000baseKR2_Full |
-			     SUPPORTED_10000baseKR_Full |
-			     SUPPORTED_10000baseKX4_Full |
-			     SUPPORTED_1000baseKX_Full |
-			     SUPPORTED_Autoneg;
-		advertising |= ADVERTISED_40000baseKR4_Full |
-			       ADVERTISED_20000baseKR2_Full |
-			       ADVERTISED_10000baseKR_Full |
-			       ADVERTISED_10000baseKX4_Full |
-			       ADVERTISED_1000baseKX_Full |
-			       ADVERTISED_Autoneg;
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     40000baseKR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     25000baseKR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     20000baseKR2_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseKR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseKX4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     1000baseKX_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     40000baseKR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     25000baseKR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     20000baseKR2_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     10000baseKR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     10000baseKX4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     1000baseKX_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
 		break;
-	case I40E_PHY_TYPE_25GBASE_KR:
 	case I40E_PHY_TYPE_25GBASE_CR:
-	case I40E_PHY_TYPE_25GBASE_SR:
-	case I40E_PHY_TYPE_25GBASE_LR:
-		supported = SUPPORTED_Autoneg;
-		advertising = ADVERTISED_Autoneg;
-		/* TODO: add speeds when ethtool is ready to support*/
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     25000baseCR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     25000baseCR_Full);
+		break;
+	case I40E_PHY_TYPE_25GBASE_AOC:
+	case I40E_PHY_TYPE_25GBASE_ACC:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     25000baseCR_Full);
+
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     25000baseCR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     10000baseCR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     10000baseCR_Full);
 		break;
 	default:
 		/* if we got here and link is up something bad is afoot */
-		netdev_info(netdev, "WARNING: Link is up but PHY type 0x%x is not recognized.\n",
+		netdev_info(netdev,
+			    "WARNING: Link is up but PHY type 0x%x is not recognized.\n",
 			    hw_link_info->phy_type);
 	}
 
 	/* Now that we've worked out everything that could be supported by the
-	 * current PHY type, get what is supported by the NVM and them to
-	 * get what is truly supported
+	 * current PHY type, get what is supported by the NVM and intersect
+	 * them to get what is truly supported
 	 */
-	i40e_phy_type_to_ethtool(pf, &e_supported,
-				 &e_advertising);
-
-	supported = supported & e_supported;
-	advertising = advertising & e_advertising;
+	memset(&cap_ksettings, 0, sizeof(struct ethtool_link_ksettings));
+	i40e_phy_type_to_ethtool(pf, &cap_ksettings);
+	ethtool_intersect_link_masks(ks, &cap_ksettings);
 
 	/* Set speed and duplex */
 	switch (link_speed) {
 	case I40E_LINK_SPEED_40GB:
-		cmd->base.speed = SPEED_40000;
+		ks->base.speed = SPEED_40000;
 		break;
 	case I40E_LINK_SPEED_25GB:
-#ifdef SPEED_25000
-		cmd->base.speed = SPEED_25000;
-#else
-		netdev_info(netdev,
-			    "Speed is 25G, display not supported by this version of ethtool.\n");
-#endif
+		ks->base.speed = SPEED_25000;
 		break;
 	case I40E_LINK_SPEED_20GB:
-		cmd->base.speed = SPEED_20000;
+		ks->base.speed = SPEED_20000;
 		break;
 	case I40E_LINK_SPEED_10GB:
-		cmd->base.speed = SPEED_10000;
+		ks->base.speed = SPEED_10000;
 		break;
 	case I40E_LINK_SPEED_1GB:
-		cmd->base.speed = SPEED_1000;
+		ks->base.speed = SPEED_1000;
 		break;
 	case I40E_LINK_SPEED_100MB:
-		cmd->base.speed = SPEED_100;
+		ks->base.speed = SPEED_100;
 		break;
 	default:
 		break;
 	}
-	cmd->base.duplex = DUPLEX_FULL;
-
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
-						supported);
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
-						advertising);
+	ks->base.duplex = DUPLEX_FULL;
 }
 
 /**
  * i40e_get_settings_link_down - Get the Link settings for when link is down
  * @hw: hw structure
- * @ecmd: ethtool command to fill in
+ * @ks: ethtool ksettings to fill in
+ * @pf: pointer to physical function struct
  *
  * Reports link settings that can be determined when link is down
  **/
 static void i40e_get_settings_link_down(struct i40e_hw *hw,
-					struct ethtool_link_ksettings *cmd,
+					struct ethtool_link_ksettings *ks,
 					struct i40e_pf *pf)
 {
-	u32 supported, advertising;
-
 	/* link is down and the driver needs to fall back on
 	 * supported phy types to figure out what info to display
 	 */
-	i40e_phy_type_to_ethtool(pf, &supported, &advertising);
-
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
-						supported);
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
-						advertising);
+	i40e_phy_type_to_ethtool(pf, ks);
 
 	/* With no link speed and duplex are unknown */
-	cmd->base.speed = SPEED_UNKNOWN;
-	cmd->base.duplex = DUPLEX_UNKNOWN;
+	ks->base.speed = SPEED_UNKNOWN;
+	ks->base.duplex = DUPLEX_UNKNOWN;
 }
 
 /**
- * i40e_get_settings - Get Link Speed and Duplex settings
+ * i40e_get_link_ksettings - Get Link Speed and Duplex settings
  * @netdev: network interface device structure
- * @ecmd: ethtool command
+ * @ks: ethtool ksettings
  *
  * Reports speed/duplex settings based on media_type
  **/
 static int i40e_get_link_ksettings(struct net_device *netdev,
-				   struct ethtool_link_ksettings *cmd)
+				   struct ethtool_link_ksettings *ks)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_hw *hw = &pf->hw;
 	struct i40e_link_status *hw_link_info = &hw->phy.link_info;
 	bool link_up = hw_link_info->link_info & I40E_AQ_LINK_UP;
-	u32 advertising;
+
+	ethtool_link_ksettings_zero_link_mode(ks, supported);
+	ethtool_link_ksettings_zero_link_mode(ks, advertising);
 
 	if (link_up)
-		i40e_get_settings_link_up(hw, cmd, netdev, pf);
+		i40e_get_settings_link_up(hw, ks, netdev, pf);
 	else
-		i40e_get_settings_link_down(hw, cmd, pf);
+		i40e_get_settings_link_down(hw, ks, pf);
 
 	/* Now set the settings that don't rely on link being up/down */
 	/* Set autoneg settings */
-	cmd->base.autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
-			  AUTONEG_ENABLE : AUTONEG_DISABLE);
+	ks->base.autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
+			    AUTONEG_ENABLE : AUTONEG_DISABLE);
 
+	/* Set media type settings */
 	switch (hw->phy.media_type) {
 	case I40E_MEDIA_TYPE_BACKPLANE:
-		ethtool_link_ksettings_add_link_mode(cmd, supported,
-						     Autoneg);
-		ethtool_link_ksettings_add_link_mode(cmd, supported,
-						     Backplane);
-		ethtool_link_ksettings_add_link_mode(cmd, advertising,
-						     Autoneg);
-		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported, Backplane);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     Backplane);
-		cmd->base.port = PORT_NONE;
+		ks->base.port = PORT_NONE;
 		break;
 	case I40E_MEDIA_TYPE_BASET:
-		ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
-		ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
-		cmd->base.port = PORT_TP;
+		ethtool_link_ksettings_add_link_mode(ks, supported, TP);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, TP);
+		ks->base.port = PORT_TP;
 		break;
 	case I40E_MEDIA_TYPE_DA:
 	case I40E_MEDIA_TYPE_CX4:
-		ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
-		ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
-		cmd->base.port = PORT_DA;
+		ethtool_link_ksettings_add_link_mode(ks, supported, FIBRE);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FIBRE);
+		ks->base.port = PORT_DA;
 		break;
 	case I40E_MEDIA_TYPE_FIBER:
-		ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
-		cmd->base.port = PORT_FIBRE;
+		ethtool_link_ksettings_add_link_mode(ks, supported, FIBRE);
+		ks->base.port = PORT_FIBRE;
 		break;
 	case I40E_MEDIA_TYPE_UNKNOWN:
 	default:
-		cmd->base.port = PORT_OTHER;
+		ks->base.port = PORT_OTHER;
 		break;
 	}
 
 	/* Set flow control settings */
-	ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
+	ethtool_link_ksettings_add_link_mode(ks, supported, Pause);
 
 	switch (hw->fc.requested_mode) {
 	case I40E_FC_FULL:
-		ethtool_link_ksettings_add_link_mode(cmd, advertising,
-						     Pause);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Pause);
 		break;
 	case I40E_FC_TX_PAUSE:
-		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     Asym_Pause);
 		break;
 	case I40E_FC_RX_PAUSE:
-		ethtool_link_ksettings_add_link_mode(cmd, advertising,
-						     Pause);
-		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Pause);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     Asym_Pause);
 		break;
 	default:
-		ethtool_convert_link_mode_to_legacy_u32(
-			&advertising, cmd->link_modes.advertising);
-
-		advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause);
-
-		ethtool_convert_legacy_u32_to_link_mode(
-			cmd->link_modes.advertising, advertising);
+		ethtool_link_ksettings_del_link_mode(ks, advertising, Pause);
+		ethtool_link_ksettings_del_link_mode(ks, advertising,
+						     Asym_Pause);
 		break;
 	}
 
@@ -680,30 +811,28 @@ static int i40e_get_link_ksettings(struct net_device *netdev,
 }
 
 /**
- * i40e_set_settings - Set Speed and Duplex
+ * i40e_set_link_ksettings - Set Speed and Duplex
  * @netdev: network interface device structure
- * @ecmd: ethtool command
+ * @ks: ethtool ksettings
  *
  * Set speed/duplex per media_types advertised/forced
  **/
 static int i40e_set_link_ksettings(struct net_device *netdev,
-				   const struct ethtool_link_ksettings *cmd)
+				   const struct ethtool_link_ksettings *ks)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_aq_get_phy_abilities_resp abilities;
+	struct ethtool_link_ksettings safe_ks;
+	struct ethtool_link_ksettings copy_ks;
 	struct i40e_aq_set_phy_config config;
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_hw *hw = &pf->hw;
-	struct ethtool_link_ksettings safe_cmd;
-	struct ethtool_link_ksettings copy_cmd;
+	bool autoneg_changed = false;
 	i40e_status status = 0;
-	bool change = false;
 	int timeout = 50;
 	int err = 0;
-	u32 autoneg;
-	u32 advertise;
-	u32 tmp;
+	u8 autoneg;
 
 	/* Changing port settings is not supported if this isn't the
 	 * port's controlling PF
@@ -712,17 +841,14 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 		i40e_partition_setting_complaint(pf);
 		return -EOPNOTSUPP;
 	}
-
 	if (vsi != pf->vsi[pf->lan_vsi])
 		return -EOPNOTSUPP;
-
 	if (hw->phy.media_type != I40E_MEDIA_TYPE_BASET &&
 	    hw->phy.media_type != I40E_MEDIA_TYPE_FIBER &&
 	    hw->phy.media_type != I40E_MEDIA_TYPE_BACKPLANE &&
 	    hw->phy.media_type != I40E_MEDIA_TYPE_DA &&
 	    hw->phy.link_info.link_info & I40E_AQ_LINK_UP)
 		return -EOPNOTSUPP;
-
 	if (hw->device_id == I40E_DEV_ID_KX_B ||
 	    hw->device_id == I40E_DEV_ID_KX_C ||
 	    hw->device_id == I40E_DEV_ID_20G_KR2 ||
@@ -731,31 +857,37 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 		return -EOPNOTSUPP;
 	}
 
-	/* copy the cmd to copy_cmd to avoid modifying the origin */
-	memcpy(&copy_cmd, cmd, sizeof(struct ethtool_link_ksettings));
+	/* copy the ksettings to copy_ks to avoid modifying the origin */
+	memcpy(&copy_ks, ks, sizeof(struct ethtool_link_ksettings));
 
-	/* get our own copy of the bits to check against */
-	memset(&safe_cmd, 0, sizeof(struct ethtool_link_ksettings));
-	i40e_get_link_ksettings(netdev, &safe_cmd);
+	/* save autoneg out of ksettings */
+	autoneg = copy_ks.base.autoneg;
 
-	/* save autoneg and speed out of cmd */
-	autoneg = cmd->base.autoneg;
-	ethtool_convert_link_mode_to_legacy_u32(&advertise,
-						cmd->link_modes.advertising);
+	memset(&safe_ks, 0, sizeof(safe_ks));
+	/* Get link modes supported by hardware and check against modes
+	 * requested by the user.  Return an error if unsupported mode was set.
+	 */
+	i40e_phy_type_to_ethtool(pf, &safe_ks);
+	if (!bitmap_subset(copy_ks.link_modes.advertising,
+			   safe_ks.link_modes.supported,
+			   __ETHTOOL_LINK_MODE_MASK_NBITS))
+		return -EINVAL;
 
-	/* set autoneg and speed back to what they currently are */
-	copy_cmd.base.autoneg = safe_cmd.base.autoneg;
-	ethtool_convert_link_mode_to_legacy_u32(
-		&tmp, safe_cmd.link_modes.advertising);
-	ethtool_convert_legacy_u32_to_link_mode(
-		copy_cmd.link_modes.advertising, tmp);
+	/* get our own copy of the bits to check against */
+	memset(&safe_ks, 0, sizeof(struct ethtool_link_ksettings));
+	safe_ks.base.cmd = copy_ks.base.cmd;
+	safe_ks.base.link_mode_masks_nwords =
+		copy_ks.base.link_mode_masks_nwords;
+	i40e_get_link_ksettings(netdev, &safe_ks);
 
-	copy_cmd.base.cmd = safe_cmd.base.cmd;
+	/* set autoneg back to what it currently is */
+	copy_ks.base.autoneg = safe_ks.base.autoneg;
 
-	/* If copy_cmd and safe_cmd are not the same now, then they are
-	 * trying to set something that we do not support
+	/* If copy_ks.base and safe_ks.base are not the same now, then they are
+	 * trying to set something that we do not support.
 	 */
-	if (memcmp(&copy_cmd, &safe_cmd, sizeof(struct ethtool_link_ksettings)))
+	if (memcmp(&copy_ks.base, &safe_ks.base,
+		   sizeof(struct ethtool_link_settings)))
 		return -EOPNOTSUPP;
 
 	while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) {
@@ -784,8 +916,9 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 		/* If autoneg was not already enabled */
 		if (!(hw->phy.link_info.an_info & I40E_AQ_AN_COMPLETED)) {
 			/* If autoneg is not supported, return error */
-			if (!ethtool_link_ksettings_test_link_mode(
-				    &safe_cmd, supported, Autoneg)) {
+			if (!ethtool_link_ksettings_test_link_mode(&safe_ks,
+								   supported,
+								   Autoneg)) {
 				netdev_info(netdev, "Autoneg not supported on this phy\n");
 				err = -EINVAL;
 				goto done;
@@ -793,7 +926,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 			/* Autoneg is allowed to change */
 			config.abilities = abilities.abilities |
 					   I40E_AQ_PHY_ENABLE_AN;
-			change = true;
+			autoneg_changed = true;
 		}
 	} else {
 		/* If autoneg is currently enabled */
@@ -801,8 +934,9 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 			/* If autoneg is supported 10GBASE_T is the only PHY
 			 * that can disable it, so otherwise return error
 			 */
-			if (ethtool_link_ksettings_test_link_mode(
-				    &safe_cmd, supported, Autoneg) &&
+			if (ethtool_link_ksettings_test_link_mode(&safe_ks,
+								  supported,
+								  Autoneg) &&
 			    hw->phy.link_info.phy_type !=
 			    I40E_PHY_TYPE_10GBASE_T) {
 				netdev_info(netdev, "Autoneg cannot be disabled on this phy\n");
@@ -812,32 +946,49 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 			/* Autoneg is allowed to change */
 			config.abilities = abilities.abilities &
 					   ~I40E_AQ_PHY_ENABLE_AN;
-			change = true;
+			autoneg_changed = true;
 		}
 	}
 
-	ethtool_convert_link_mode_to_legacy_u32(&tmp,
-						safe_cmd.link_modes.supported);
-	if (advertise & ~tmp) {
-		err = -EINVAL;
-		goto done;
-	}
-
-	if (advertise & ADVERTISED_100baseT_Full)
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  100baseT_Full))
 		config.link_speed |= I40E_LINK_SPEED_100MB;
-	if (advertise & ADVERTISED_1000baseT_Full ||
-	    advertise & ADVERTISED_1000baseKX_Full)
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  1000baseT_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  1000baseX_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  1000baseKX_Full))
 		config.link_speed |= I40E_LINK_SPEED_1GB;
-	if (advertise & ADVERTISED_10000baseT_Full ||
-	    advertise & ADVERTISED_10000baseKX4_Full ||
-	    advertise & ADVERTISED_10000baseKR_Full)
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  10000baseT_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  10000baseKX4_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  10000baseKR_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  10000baseCR_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  10000baseSR_Full))
 		config.link_speed |= I40E_LINK_SPEED_10GB;
-	if (advertise & ADVERTISED_20000baseKR2_Full)
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  20000baseKR2_Full))
 		config.link_speed |= I40E_LINK_SPEED_20GB;
-	if (advertise & ADVERTISED_40000baseKR4_Full ||
-	    advertise & ADVERTISED_40000baseCR4_Full ||
-	    advertise & ADVERTISED_40000baseSR4_Full ||
-	    advertise & ADVERTISED_40000baseLR4_Full)
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  25000baseCR_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  25000baseKR_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  25000baseSR_Full))
+		config.link_speed |= I40E_LINK_SPEED_25GB;
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  40000baseKR4_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  40000baseCR4_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  40000baseSR4_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  40000baseLR4_Full))
 		config.link_speed |= I40E_LINK_SPEED_40GB;
 
 	/* If speed didn't get set, set it to what it currently is.
@@ -846,8 +997,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 	 */
 	if (!config.link_speed)
 		config.link_speed = abilities.link_speed;
-
-	if (change || (abilities.link_speed != config.link_speed)) {
+	if (autoneg_changed || abilities.link_speed != config.link_speed) {
 		/* copy over the rest of the abilities */
 		config.phy_type = abilities.phy_type;
 		config.phy_type_ext = abilities.phy_type_ext;
@@ -874,7 +1024,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 		/* make the aq call */
 		status = i40e_aq_set_phy_config(hw, &config, NULL);
 		if (status) {
-			netdev_info(netdev, "Set phy config failed, err %s aq_err %s\n",
+			netdev_info(netdev,
+				    "Set phy config failed, err %s aq_err %s\n",
 				    i40e_stat_str(hw, status),
 				    i40e_aq_str(hw, hw->aq.asq_last_status));
 			err = -EAGAIN;
@@ -883,7 +1034,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 
 		status = i40e_update_link_info(hw);
 		if (status)
-			netdev_dbg(netdev, "Updating link info failed with err %s aq_err %s\n",
+			netdev_dbg(netdev,
+				   "Updating link info failed with err %s aq_err %s\n",
 				   i40e_stat_str(hw, status),
 				   i40e_aq_str(hw, hw->aq.asq_last_status));
 
@@ -2008,7 +2160,9 @@ static int i40e_set_phys_id(struct net_device *netdev,
 		if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS)) {
 			pf->led_status = i40e_led_get(hw);
 		} else {
-			i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL, NULL);
+			if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE))
+				i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL,
+						      NULL);
 			ret = i40e_led_get_phy(hw, &temp_status,
 					       &pf->phy_led_val);
 			pf->led_status = temp_status;
@@ -2033,7 +2187,8 @@ static int i40e_set_phys_id(struct net_device *netdev,
 			ret = i40e_led_set_phy(hw, false, pf->led_status,
 					       (pf->phy_led_val |
 					       I40E_PHY_LED_MODE_ORIG));
-			i40e_aq_set_phy_debug(hw, 0, NULL);
+			if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE))
+				i40e_aq_set_phy_debug(hw, 0, NULL);
 		}
 		break;
 	default:
@@ -2071,14 +2226,13 @@ static int __i40e_get_coalesce(struct net_device *netdev,
 	ec->tx_max_coalesced_frames_irq = vsi->work_limit;
 	ec->rx_max_coalesced_frames_irq = vsi->work_limit;
 
-	/* rx and tx usecs has per queue value. If user doesn't specify the queue,
-	 * return queue 0's value to represent.
+	/* rx and tx usecs has per queue value. If user doesn't specify the
+	 * queue, return queue 0's value to represent.
 	 */
-	if (queue < 0) {
+	if (queue < 0)
 		queue = 0;
-	} else if (queue >= vsi->num_queue_pairs) {
+	else if (queue >= vsi->num_queue_pairs)
 		return -EINVAL;
-	}
 
 	rx_ring = vsi->rx_rings[queue];
 	tx_ring = vsi->tx_rings[queue];
@@ -2092,7 +2246,6 @@ static int __i40e_get_coalesce(struct net_device *netdev,
 	ec->rx_coalesce_usecs = rx_ring->rx_itr_setting & ~I40E_ITR_DYNAMIC;
 	ec->tx_coalesce_usecs = tx_ring->tx_itr_setting & ~I40E_ITR_DYNAMIC;
 
-
 	/* we use the _usecs_high to store/set the interrupt rate limit
 	 * that the hardware supports, that almost but not quite
 	 * fits the original intent of the ethtool variable,
@@ -2142,7 +2295,6 @@ static int i40e_get_per_queue_coalesce(struct net_device *netdev, u32 queue,
  *
  * Change the ITR settings for a specific queue.
  **/
-
 static void i40e_set_itr_per_queue(struct i40e_vsi *vsi,
 				   struct ethtool_coalesce *ec,
 				   int queue)
@@ -2264,8 +2416,8 @@ static int __i40e_set_coalesce(struct net_device *netdev,
 			   vsi->int_rate_limit);
 	}
 
-	/* rx and tx usecs has per queue value. If user doesn't specify the queue,
-	 * apply to all queues.
+	/* rx and tx usecs has per queue value. If user doesn't specify the
+	 * queue, apply to all queues.
 	 */
 	if (queue < 0) {
 		for (i = 0; i < vsi->num_queue_pairs; i++)
@@ -2647,7 +2799,7 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 
 	switch (cmd->cmd) {
 	case ETHTOOL_GRXRINGS:
-		cmd->data = vsi->num_queue_pairs;
+		cmd->data = vsi->rss_size;
 		ret = 0;
 		break;
 	case ETHTOOL_GRXFH:
@@ -3892,6 +4044,12 @@ static int i40e_set_channels(struct net_device *dev,
 	if (vsi->type != I40E_VSI_MAIN)
 		return -EINVAL;
 
+	/* We do not support setting channels via ethtool when TCs are
+	 * configured through mqprio
+	 */
+	if (pf->flags & I40E_FLAG_TC_MQPRIO)
+		return -EINVAL;
+
 	/* verify they are not requesting separate vectors */
 	if (!count || ch->rx_count || ch->tx_count)
 		return -EINVAL;
@@ -3959,6 +4117,16 @@ static u32 i40e_get_rxfh_indir_size(struct net_device *netdev)
 	return I40E_HLUT_ARRAY_SIZE;
 }
 
+/**
+ * i40e_get_rxfh - get the rx flow hash indirection table
+ * @netdev: network interface device structure
+ * @indir: indirection table
+ * @key: hash key
+ * @hfunc: hash function
+ *
+ * Reads the indirection table directly from the hardware. Returns 0 on
+ * success.
+ **/
 static int i40e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 			 u8 *hfunc)
 {
@@ -4090,7 +4258,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	u64 orig_flags, new_flags, changed_flags;
+	u32 orig_flags, new_flags, changed_flags;
 	u32 i, j;
 
 	orig_flags = READ_ONCE(pf->flags);
@@ -4142,12 +4310,12 @@ flags_complete:
 		return -EOPNOTSUPP;
 
 	/* Compare and exchange the new flags into place. If we failed, that
-	 * is if cmpxchg64 returns anything but the old value, this means that
+	 * is if cmpxchg returns anything but the old value, this means that
 	 * something else has modified the flags variable since we copied it
 	 * originally. We'll just punt with an error and log something in the
 	 * message buffer.
 	 */
-	if (cmpxchg64(&pf->flags, orig_flags, new_flags) != orig_flags) {
+	if (cmpxchg(&pf->flags, orig_flags, new_flags) != orig_flags) {
 		dev_warn(&pf->pdev->dev,
 			 "Unable to update pf->flags as it was modified by another thread...\n");
 		return -EAGAIN;
@@ -4175,7 +4343,7 @@ flags_complete:
 			sw_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		ret = i40e_aq_set_switch_config(&pf->hw, sw_flags, valid_flags,
-						NULL);
+						0, NULL);
 		if (ret && pf->hw.aq.asq_last_status != I40E_AQ_RC_ESRCH) {
 			dev_info(&pf->pdev->dev,
 				 "couldn't set switch config bits, err %s aq_err %s\n",
@@ -4189,13 +4357,166 @@ flags_complete:
 	/* Issue reset to cause things to take effect, as additional bits
 	 * are added we will need to create a mask of bits requiring reset
 	 */
-	if ((changed_flags & I40E_FLAG_VEB_STATS_ENABLED) ||
-	    ((changed_flags & I40E_FLAG_LEGACY_RX) && netif_running(dev)))
+	if (changed_flags & (I40E_FLAG_VEB_STATS_ENABLED |
+			     I40E_FLAG_LEGACY_RX |
+			     I40E_FLAG_SOURCE_PRUNING_DISABLED))
 		i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true);
 
 	return 0;
 }
 
+/**
+ * i40e_get_module_info - get (Q)SFP+ module type info
+ * @netdev: network interface device structure
+ * @modinfo: module EEPROM size and layout information structure
+ **/
+static int i40e_get_module_info(struct net_device *netdev,
+				struct ethtool_modinfo *modinfo)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	u32 sff8472_comp = 0;
+	u32 sff8472_swap = 0;
+	u32 sff8636_rev = 0;
+	i40e_status status;
+	u32 type = 0;
+
+	/* Check if firmware supports reading module EEPROM. */
+	if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE)) {
+		netdev_err(vsi->netdev, "Module EEPROM memory read not supported. Please update the NVM image.\n");
+		return -EINVAL;
+	}
+
+	status = i40e_update_link_info(hw);
+	if (status)
+		return -EIO;
+
+	if (hw->phy.link_info.phy_type == I40E_PHY_TYPE_EMPTY) {
+		netdev_err(vsi->netdev, "Cannot read module EEPROM memory. No module connected.\n");
+		return -EINVAL;
+	}
+
+	type = hw->phy.link_info.module_type[0];
+
+	switch (type) {
+	case I40E_MODULE_TYPE_SFP:
+		status = i40e_aq_get_phy_register(hw,
+				I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE,
+				I40E_I2C_EEPROM_DEV_ADDR,
+				I40E_MODULE_SFF_8472_COMP,
+				&sff8472_comp, NULL);
+		if (status)
+			return -EIO;
+
+		status = i40e_aq_get_phy_register(hw,
+				I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE,
+				I40E_I2C_EEPROM_DEV_ADDR,
+				I40E_MODULE_SFF_8472_SWAP,
+				&sff8472_swap, NULL);
+		if (status)
+			return -EIO;
+
+		/* Check if the module requires address swap to access
+		 * the other EEPROM memory page.
+		 */
+		if (sff8472_swap & I40E_MODULE_SFF_ADDR_MODE) {
+			netdev_warn(vsi->netdev, "Module address swap to access page 0xA2 is not supported.\n");
+			modinfo->type = ETH_MODULE_SFF_8079;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
+		} else if (sff8472_comp == 0x00) {
+			/* Module is not SFF-8472 compliant */
+			modinfo->type = ETH_MODULE_SFF_8079;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
+		} else {
+			modinfo->type = ETH_MODULE_SFF_8472;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		}
+		break;
+	case I40E_MODULE_TYPE_QSFP_PLUS:
+		/* Read from memory page 0. */
+		status = i40e_aq_get_phy_register(hw,
+				I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE,
+				0,
+				I40E_MODULE_REVISION_ADDR,
+				&sff8636_rev, NULL);
+		if (status)
+			return -EIO;
+		/* Determine revision compliance byte */
+		if (sff8636_rev > 0x02) {
+			/* Module is SFF-8636 compliant */
+			modinfo->type = ETH_MODULE_SFF_8636;
+			modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN;
+		} else {
+			modinfo->type = ETH_MODULE_SFF_8436;
+			modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN;
+		}
+		break;
+	case I40E_MODULE_TYPE_QSFP28:
+		modinfo->type = ETH_MODULE_SFF_8636;
+		modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN;
+		break;
+	default:
+		netdev_err(vsi->netdev, "Module type unrecognized\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * i40e_get_module_eeprom - fills buffer with (Q)SFP+ module memory contents
+ * @netdev: network interface device structure
+ * @ee: EEPROM dump request structure
+ * @data: buffer to be filled with EEPROM contents
+ **/
+static int i40e_get_module_eeprom(struct net_device *netdev,
+				  struct ethtool_eeprom *ee,
+				  u8 *data)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	bool is_sfp = false;
+	i40e_status status;
+	u32 value = 0;
+	int i;
+
+	if (!ee || !ee->len || !data)
+		return -EINVAL;
+
+	if (hw->phy.link_info.module_type[0] == I40E_MODULE_TYPE_SFP)
+		is_sfp = true;
+
+	for (i = 0; i < ee->len; i++) {
+		u32 offset = i + ee->offset;
+		u32 addr = is_sfp ? I40E_I2C_EEPROM_DEV_ADDR : 0;
+
+		/* Check if we need to access the other memory page */
+		if (is_sfp) {
+			if (offset >= ETH_MODULE_SFF_8079_LEN) {
+				offset -= ETH_MODULE_SFF_8079_LEN;
+				addr = I40E_I2C_EEPROM_DEV_ADDR2;
+			}
+		} else {
+			while (offset >= ETH_MODULE_SFF_8436_LEN) {
+				/* Compute memory page number and offset. */
+				offset -= ETH_MODULE_SFF_8436_LEN / 2;
+				addr++;
+			}
+		}
+
+		status = i40e_aq_get_phy_register(hw,
+				I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE,
+				addr, offset, &value, NULL);
+		if (status)
+			return -EIO;
+		data[i] = value;
+	}
+	return 0;
+}
+
 static const struct ethtool_ops i40e_ethtool_ops = {
 	.get_drvinfo		= i40e_get_drvinfo,
 	.get_regs_len		= i40e_get_regs_len,
@@ -4228,6 +4549,8 @@ static const struct ethtool_ops i40e_ethtool_ops = {
 	.set_rxfh		= i40e_set_rxfh,
 	.get_channels		= i40e_get_channels,
 	.set_channels		= i40e_set_channels,
+	.get_module_info	= i40e_get_module_info,
+	.get_module_eeprom	= i40e_get_module_eeprom,
 	.get_ts_info		= i40e_get_ts_info,
 	.get_priv_flags		= i40e_get_priv_flags,
 	.set_priv_flags		= i40e_set_priv_flags,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 6498da8806cb..dfecaeda0654 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -69,6 +69,15 @@ static int i40e_reset(struct i40e_pf *pf);
 static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired);
 static void i40e_fdir_sb_setup(struct i40e_pf *pf);
 static int i40e_veb_get_bw_info(struct i40e_veb *veb);
+static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi,
+				     struct i40e_cloud_filter *filter,
+				     bool add);
+static int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi,
+					     struct i40e_cloud_filter *filter,
+					     bool add);
+static int i40e_get_capabilities(struct i40e_pf *pf,
+				 enum i40e_admin_queue_opc list_type);
+
 
 /* i40e_pci_tbl - PCI Device ID Table
  *
@@ -600,6 +609,20 @@ static void i40e_stat_update32(struct i40e_hw *hw, u32 reg,
 }
 
 /**
+ * i40e_stat_update_and_clear32 - read and clear hw reg, update a 32 bit stat
+ * @hw: ptr to the hardware info
+ * @reg: the hw reg to read and clear
+ * @stat: ptr to the stat
+ **/
+static void i40e_stat_update_and_clear32(struct i40e_hw *hw, u32 reg, u64 *stat)
+{
+	u32 new_data = rd32(hw, reg);
+
+	wr32(hw, reg, 1); /* must write a nonzero value to clear register */
+	*stat += new_data;
+}
+
+/**
  * i40e_update_eth_stats - Update VSI-specific ethernet statistics counters.
  * @vsi: the VSI to be updated
  **/
@@ -1040,18 +1063,15 @@ static void i40e_update_pf_stats(struct i40e_pf *pf)
 			   &osd->rx_jabber, &nsd->rx_jabber);
 
 	/* FDIR stats */
-	i40e_stat_update32(hw,
-			   I40E_GLQF_PCNT(I40E_FD_ATR_STAT_IDX(pf->hw.pf_id)),
-			   pf->stat_offsets_loaded,
-			   &osd->fd_atr_match, &nsd->fd_atr_match);
-	i40e_stat_update32(hw,
-			   I40E_GLQF_PCNT(I40E_FD_SB_STAT_IDX(pf->hw.pf_id)),
-			   pf->stat_offsets_loaded,
-			   &osd->fd_sb_match, &nsd->fd_sb_match);
-	i40e_stat_update32(hw,
-		      I40E_GLQF_PCNT(I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id)),
-		      pf->stat_offsets_loaded,
-		      &osd->fd_atr_tunnel_match, &nsd->fd_atr_tunnel_match);
+	i40e_stat_update_and_clear32(hw,
+			I40E_GLQF_PCNT(I40E_FD_ATR_STAT_IDX(hw->pf_id)),
+			&nsd->fd_atr_match);
+	i40e_stat_update_and_clear32(hw,
+			I40E_GLQF_PCNT(I40E_FD_SB_STAT_IDX(hw->pf_id)),
+			&nsd->fd_sb_match);
+	i40e_stat_update_and_clear32(hw,
+			I40E_GLQF_PCNT(I40E_FD_ATR_TUNNEL_STAT_IDX(hw->pf_id)),
+			&nsd->fd_atr_tunnel_match);
 
 	val = rd32(hw, I40E_PRTPM_EEE_STAT);
 	nsd->tx_lpi_status =
@@ -1578,6 +1598,170 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
 }
 
 /**
+ * i40e_config_rss_aq - Prepare for RSS using AQ commands
+ * @vsi: vsi structure
+ * @seed: RSS hash seed
+ **/
+static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
+			      u8 *lut, u16 lut_size)
+{
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	int ret = 0;
+
+	if (seed) {
+		struct i40e_aqc_get_set_rss_key_data *seed_dw =
+			(struct i40e_aqc_get_set_rss_key_data *)seed;
+		ret = i40e_aq_set_rss_key(hw, vsi->id, seed_dw);
+		if (ret) {
+			dev_info(&pf->pdev->dev,
+				 "Cannot set RSS key, err %s aq_err %s\n",
+				 i40e_stat_str(hw, ret),
+				 i40e_aq_str(hw, hw->aq.asq_last_status));
+			return ret;
+		}
+	}
+	if (lut) {
+		bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false;
+
+		ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size);
+		if (ret) {
+			dev_info(&pf->pdev->dev,
+				 "Cannot set RSS lut, err %s aq_err %s\n",
+				 i40e_stat_str(hw, ret),
+				 i40e_aq_str(hw, hw->aq.asq_last_status));
+			return ret;
+		}
+	}
+	return ret;
+}
+
+/**
+ * i40e_vsi_config_rss - Prepare for VSI(VMDq) RSS if used
+ * @vsi: VSI structure
+ **/
+static int i40e_vsi_config_rss(struct i40e_vsi *vsi)
+{
+	struct i40e_pf *pf = vsi->back;
+	u8 seed[I40E_HKEY_ARRAY_SIZE];
+	u8 *lut;
+	int ret;
+
+	if (!(pf->hw_features & I40E_HW_RSS_AQ_CAPABLE))
+		return 0;
+	if (!vsi->rss_size)
+		vsi->rss_size = min_t(int, pf->alloc_rss_size,
+				      vsi->num_queue_pairs);
+	if (!vsi->rss_size)
+		return -EINVAL;
+	lut = kzalloc(vsi->rss_table_size, GFP_KERNEL);
+	if (!lut)
+		return -ENOMEM;
+
+	/* Use the user configured hash keys and lookup table if there is one,
+	 * otherwise use default
+	 */
+	if (vsi->rss_lut_user)
+		memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size);
+	else
+		i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, vsi->rss_size);
+	if (vsi->rss_hkey_user)
+		memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE);
+	else
+		netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE);
+	ret = i40e_config_rss_aq(vsi, seed, lut, vsi->rss_table_size);
+	kfree(lut);
+	return ret;
+}
+
+/**
+ * i40e_vsi_setup_queue_map_mqprio - Prepares mqprio based tc_config
+ * @vsi: the VSI being configured,
+ * @ctxt: VSI context structure
+ * @enabled_tc: number of traffic classes to enable
+ *
+ * Prepares VSI tc_config to have queue configurations based on MQPRIO options.
+ **/
+static int i40e_vsi_setup_queue_map_mqprio(struct i40e_vsi *vsi,
+					   struct i40e_vsi_context *ctxt,
+					   u8 enabled_tc)
+{
+	u16 qcount = 0, max_qcount, qmap, sections = 0;
+	int i, override_q, pow, num_qps, ret;
+	u8 netdev_tc = 0, offset = 0;
+
+	if (vsi->type != I40E_VSI_MAIN)
+		return -EINVAL;
+	sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID;
+	sections |= I40E_AQ_VSI_PROP_SCHED_VALID;
+	vsi->tc_config.numtc = vsi->mqprio_qopt.qopt.num_tc;
+	vsi->tc_config.enabled_tc = enabled_tc ? enabled_tc : 1;
+	num_qps = vsi->mqprio_qopt.qopt.count[0];
+
+	/* find the next higher power-of-2 of num queue pairs */
+	pow = ilog2(num_qps);
+	if (!is_power_of_2(num_qps))
+		pow++;
+	qmap = (offset << I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) |
+		(pow << I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT);
+
+	/* Setup queue offset/count for all TCs for given VSI */
+	max_qcount = vsi->mqprio_qopt.qopt.count[0];
+	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+		/* See if the given TC is enabled for the given VSI */
+		if (vsi->tc_config.enabled_tc & BIT(i)) {
+			offset = vsi->mqprio_qopt.qopt.offset[i];
+			qcount = vsi->mqprio_qopt.qopt.count[i];
+			if (qcount > max_qcount)
+				max_qcount = qcount;
+			vsi->tc_config.tc_info[i].qoffset = offset;
+			vsi->tc_config.tc_info[i].qcount = qcount;
+			vsi->tc_config.tc_info[i].netdev_tc = netdev_tc++;
+		} else {
+			/* TC is not enabled so set the offset to
+			 * default queue and allocate one queue
+			 * for the given TC.
+			 */
+			vsi->tc_config.tc_info[i].qoffset = 0;
+			vsi->tc_config.tc_info[i].qcount = 1;
+			vsi->tc_config.tc_info[i].netdev_tc = 0;
+		}
+	}
+
+	/* Set actual Tx/Rx queue pairs */
+	vsi->num_queue_pairs = offset + qcount;
+
+	/* Setup queue TC[0].qmap for given VSI context */
+	ctxt->info.tc_mapping[0] = cpu_to_le16(qmap);
+	ctxt->info.mapping_flags |= cpu_to_le16(I40E_AQ_VSI_QUE_MAP_CONTIG);
+	ctxt->info.queue_mapping[0] = cpu_to_le16(vsi->base_queue);
+	ctxt->info.valid_sections |= cpu_to_le16(sections);
+
+	/* Reconfigure RSS for main VSI with max queue count */
+	vsi->rss_size = max_qcount;
+	ret = i40e_vsi_config_rss(vsi);
+	if (ret) {
+		dev_info(&vsi->back->pdev->dev,
+			 "Failed to reconfig rss for num_queues (%u)\n",
+			 max_qcount);
+		return ret;
+	}
+	vsi->reconfig_rss = true;
+	dev_dbg(&vsi->back->pdev->dev,
+		"Reconfigured rss with num_queues (%u)\n", max_qcount);
+
+	/* Find queue count available for channel VSIs and starting offset
+	 * for channel VSIs
+	 */
+	override_q = vsi->mqprio_qopt.qopt.count[0];
+	if (override_q && override_q < vsi->num_queue_pairs) {
+		vsi->cnt_q_avail = vsi->num_queue_pairs - override_q;
+		vsi->next_base_queue = override_q;
+	}
+	return 0;
+}
+
+/**
  * i40e_vsi_setup_queue_map - Setup a VSI queue map based on enabled_tc
  * @vsi: the VSI being setup
  * @ctxt: VSI context structure
@@ -1615,7 +1799,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 			numtc = 1;
 		}
 	} else {
-		/* At least TC0 is enabled in case of non-DCB case */
+		/* At least TC0 is enabled in non-DCB, non-MQPRIO case */
 		numtc = 1;
 	}
 
@@ -1765,11 +1949,6 @@ static void i40e_set_rx_mode(struct net_device *netdev)
 		vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
 		vsi->back->flags |= I40E_FLAG_FILTER_SYNC;
 	}
-
-	/* schedule our worker thread which will take care of
-	 * applying the new filter changes
-	 */
-	i40e_service_event_schedule(vsi->back);
 }
 
 /**
@@ -2873,22 +3052,18 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi)
  **/
 static void i40e_config_xps_tx_ring(struct i40e_ring *ring)
 {
-	struct i40e_vsi *vsi = ring->vsi;
+	int cpu;
 
-	if (!ring->q_vector || !ring->netdev)
+	if (!ring->q_vector || !ring->netdev || ring->ch)
 		return;
 
-	if ((vsi->tc_config.numtc <= 1) &&
-	    !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, &ring->state)) {
-		netif_set_xps_queue(ring->netdev,
-				    get_cpu_mask(ring->q_vector->v_idx),
-				    ring->queue_index);
-	}
+	/* We only initialize XPS once, so as not to overwrite user settings */
+	if (test_and_set_bit(__I40E_TX_XPS_INIT_DONE, ring->state))
+		return;
 
-	/* schedule our worker thread which will take care of
-	 * applying the new filter changes
-	 */
-	i40e_service_event_schedule(vsi->back);
+	cpu = cpumask_local_spread(ring->q_vector->v_idx, -1);
+	netif_set_xps_queue(ring->netdev, get_cpu_mask(cpu),
+			    ring->queue_index);
 }
 
 /**
@@ -2942,7 +3117,14 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
 	 * initialization. This has to be done regardless of
 	 * DCB as by default everything is mapped to TC0.
 	 */
-	tx_ctx.rdylist = le16_to_cpu(vsi->info.qs_handle[ring->dcb_tc]);
+
+	if (ring->ch)
+		tx_ctx.rdylist =
+			le16_to_cpu(ring->ch->info.qs_handle[ring->dcb_tc]);
+
+	else
+		tx_ctx.rdylist = le16_to_cpu(vsi->info.qs_handle[ring->dcb_tc]);
+
 	tx_ctx.rdylist_act = 0;
 
 	/* clear the context in the HMC */
@@ -2964,12 +3146,23 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
 	}
 
 	/* Now associate this queue with this PCI function */
-	if (vsi->type == I40E_VSI_VMDQ2) {
-		qtx_ctl = I40E_QTX_CTL_VM_QUEUE;
-		qtx_ctl |= ((vsi->id) << I40E_QTX_CTL_VFVM_INDX_SHIFT) &
-			   I40E_QTX_CTL_VFVM_INDX_MASK;
+	if (ring->ch) {
+		if (ring->ch->type == I40E_VSI_VMDQ2)
+			qtx_ctl = I40E_QTX_CTL_VM_QUEUE;
+		else
+			return -EINVAL;
+
+		qtx_ctl |= (ring->ch->vsi_number <<
+			    I40E_QTX_CTL_VFVM_INDX_SHIFT) &
+			    I40E_QTX_CTL_VFVM_INDX_MASK;
 	} else {
-		qtx_ctl = I40E_QTX_CTL_PF_QUEUE;
+		if (vsi->type == I40E_VSI_VMDQ2) {
+			qtx_ctl = I40E_QTX_CTL_VM_QUEUE;
+			qtx_ctl |= ((vsi->id) << I40E_QTX_CTL_VFVM_INDX_SHIFT) &
+				    I40E_QTX_CTL_VFVM_INDX_MASK;
+		} else {
+			qtx_ctl = I40E_QTX_CTL_PF_QUEUE;
+		}
 	}
 
 	qtx_ctl |= ((hw->pf_id << I40E_QTX_CTL_PF_INDX_SHIFT) &
@@ -2998,7 +3191,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	struct i40e_hmc_obj_rxq rx_ctx;
 	i40e_status err = 0;
 
-	ring->state = 0;
+	bitmap_zero(ring->state, __I40E_RING_STATE_NBITS);
 
 	/* clear the context structure first */
 	memset(&rx_ctx, 0, sizeof(rx_ctx));
@@ -3023,7 +3216,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	if (hw->revision_id == 0)
 		rx_ctx.lrxqthresh = 0;
 	else
-		rx_ctx.lrxqthresh = 2;
+		rx_ctx.lrxqthresh = 1;
 	rx_ctx.crcstrip = 1;
 	rx_ctx.l2tsel = 1;
 	/* this controls whether VLAN is stripped from inner headers */
@@ -3138,6 +3331,7 @@ static void i40e_vsi_config_dcb_rings(struct i40e_vsi *vsi)
 			rx_ring->dcb_tc = 0;
 			tx_ring->dcb_tc = 0;
 		}
+		return;
 	}
 
 	for (n = 0; n < I40E_MAX_TRAFFIC_CLASS; n++) {
@@ -3396,15 +3590,14 @@ void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf)
 /**
  * i40e_irq_dynamic_enable_icr0 - Enable default interrupt generation for icr0
  * @pf: board private structure
- * @clearpba: true when all pending interrupt events should be cleared
  **/
-void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba)
+void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
 	u32 val;
 
 	val = I40E_PFINT_DYN_CTL0_INTENA_MASK   |
-	      (clearpba ? I40E_PFINT_DYN_CTL0_CLEARPBA_MASK : 0) |
+	      I40E_PFINT_DYN_CTL0_CLEARPBA_MASK |
 	      (I40E_ITR_NONE << I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT);
 
 	wr32(hw, I40E_PFINT_DYN_CTL0, val);
@@ -3471,6 +3664,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 	int tx_int_idx = 0;
 	int vector, err;
 	int irq_num;
+	int cpu;
 
 	for (vector = 0; vector < q_vectors; vector++) {
 		struct i40e_q_vector *q_vector = vsi->q_vectors[vector];
@@ -3506,10 +3700,14 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 		q_vector->affinity_notify.notify = i40e_irq_affinity_notify;
 		q_vector->affinity_notify.release = i40e_irq_affinity_release;
 		irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
-		/* get_cpu_mask returns a static constant mask with
-		 * a permanent lifetime so it's ok to use here.
+		/* Spread affinity hints out across online CPUs.
+		 *
+		 * get_cpu_mask returns a static constant mask with
+		 * a permanent lifetime so it's ok to pass to
+		 * irq_set_affinity_hint without making a copy.
 		 */
-		irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx));
+		cpu = cpumask_local_spread(q_vector->v_idx, -1);
+		irq_set_affinity_hint(irq_num, get_cpu_mask(cpu));
 	}
 
 	vsi->irqs_ready = true;
@@ -3585,7 +3783,7 @@ static int i40e_vsi_enable_irq(struct i40e_vsi *vsi)
 		for (i = 0; i < vsi->num_q_vectors; i++)
 			i40e_irq_dynamic_enable(vsi, i);
 	} else {
-		i40e_irq_dynamic_enable_icr0(pf, true);
+		i40e_irq_dynamic_enable_icr0(pf);
 	}
 
 	i40e_flush(&pf->hw);
@@ -3593,14 +3791,20 @@ static int i40e_vsi_enable_irq(struct i40e_vsi *vsi)
 }
 
 /**
- * i40e_stop_misc_vector - Stop the vector that handles non-queue events
+ * i40e_free_misc_vector - Free the vector that handles non-queue events
  * @pf: board private structure
  **/
-static void i40e_stop_misc_vector(struct i40e_pf *pf)
+static void i40e_free_misc_vector(struct i40e_pf *pf)
 {
 	/* Disable ICR 0 */
 	wr32(&pf->hw, I40E_PFINT_ICR0_ENA, 0);
 	i40e_flush(&pf->hw);
+
+	if (pf->flags & I40E_FLAG_MSIX_ENABLED && pf->msix_entries) {
+		synchronize_irq(pf->msix_entries[0].vector);
+		free_irq(pf->msix_entries[0].vector, pf);
+		clear_bit(__I40E_MISC_IRQ_REQUESTED, pf->state);
+	}
 }
 
 /**
@@ -3728,7 +3932,7 @@ enable_intr:
 	wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask);
 	if (!test_bit(__I40E_DOWN, pf->state)) {
 		i40e_service_event_schedule(pf);
-		i40e_irq_dynamic_enable_icr0(pf, false);
+		i40e_irq_dynamic_enable_icr0(pf);
 	}
 
 	return ret;
@@ -4455,11 +4659,7 @@ static void i40e_clear_interrupt_scheme(struct i40e_pf *pf)
 {
 	int i;
 
-	i40e_stop_misc_vector(pf);
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED && pf->msix_entries) {
-		synchronize_irq(pf->msix_entries[0].vector);
-		free_irq(pf->msix_entries[0].vector, pf);
-	}
+	i40e_free_misc_vector(pf);
 
 	i40e_put_lump(pf->irq_pile, pf->iwarp_base_vector,
 		      I40E_IWARP_IRQ_PILE_ID);
@@ -4848,6 +5048,24 @@ static u8 i40e_dcb_get_enabled_tc(struct i40e_dcbx_config *dcbcfg)
 }
 
 /**
+ * i40e_mqprio_get_enabled_tc - Get enabled traffic classes
+ * @pf: PF being queried
+ *
+ * Query the current MQPRIO configuration and return the number of
+ * traffic classes enabled.
+ **/
+static u8 i40e_mqprio_get_enabled_tc(struct i40e_pf *pf)
+{
+	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	u8 num_tc = vsi->mqprio_qopt.qopt.num_tc;
+	u8 enabled_tc = 1, i;
+
+	for (i = 1; i < num_tc; i++)
+		enabled_tc |= BIT(i);
+	return enabled_tc;
+}
+
+/**
  * i40e_pf_get_num_tc - Get enabled traffic classes for PF
  * @pf: PF being queried
  *
@@ -4860,7 +5078,10 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf)
 	u8 num_tc = 0;
 	struct i40e_dcbx_config *dcbcfg = &hw->local_dcbx_config;
 
-	/* If DCB is not enabled then always in single TC */
+	if (pf->flags & I40E_FLAG_TC_MQPRIO)
+		return pf->vsi[pf->lan_vsi]->mqprio_qopt.qopt.num_tc;
+
+	/* If neither MQPRIO nor DCB is enabled, then always use single TC */
 	if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
 		return 1;
 
@@ -4889,7 +5110,12 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf)
  **/
 static u8 i40e_pf_get_tc_map(struct i40e_pf *pf)
 {
-	/* If DCB is not enabled for this PF then just return default TC */
+	if (pf->flags & I40E_FLAG_TC_MQPRIO)
+		return i40e_mqprio_get_enabled_tc(pf);
+
+	/* If neither MQPRIO nor DCB is enabled for this PF then just return
+	 * default TC
+	 */
 	if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
 		return I40E_DEFAULT_TRAFFIC_CLASS;
 
@@ -4979,6 +5205,16 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc,
 	i40e_status ret;
 	int i;
 
+	if (vsi->back->flags & I40E_FLAG_TC_MQPRIO)
+		return 0;
+	if (!vsi->mqprio_qopt.qopt.hw) {
+		ret = i40e_set_bw_limit(vsi, vsi->seid, 0);
+		if (ret)
+			dev_info(&vsi->back->pdev->dev,
+				 "Failed to reset tx rate for vsi->seid %u\n",
+				 vsi->seid);
+		return ret;
+	}
 	bw_data.tc_valid_bits = enabled_tc;
 	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)
 		bw_data.tc_bw_credits[i] = bw_share[i];
@@ -5041,6 +5277,9 @@ static void i40e_vsi_config_netdev_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 					vsi->tc_config.tc_info[i].qoffset);
 	}
 
+	if (pf->flags & I40E_FLAG_TC_MQPRIO)
+		return;
+
 	/* Assign UP2TC map for the VSI */
 	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
 		/* Get the actual TC# for the UP */
@@ -5091,7 +5330,8 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 	int i;
 
 	/* Check if enabled_tc is same as existing or new TCs */
-	if (vsi->tc_config.enabled_tc == enabled_tc)
+	if (vsi->tc_config.enabled_tc == enabled_tc &&
+	    vsi->mqprio_qopt.mode != TC_MQPRIO_MODE_CHANNEL)
 		return ret;
 
 	/* Enable ETS TCs with equal BW Share for now across all VSIs */
@@ -5114,15 +5354,37 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 	ctxt.vf_num = 0;
 	ctxt.uplink_seid = vsi->uplink_seid;
 	ctxt.info = vsi->info;
-	i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, false);
+	if (vsi->back->flags & I40E_FLAG_TC_MQPRIO) {
+		ret = i40e_vsi_setup_queue_map_mqprio(vsi, &ctxt, enabled_tc);
+		if (ret)
+			goto out;
+	} else {
+		i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, false);
+	}
 
+	/* On destroying the qdisc, reset vsi->rss_size, as number of enabled
+	 * queues changed.
+	 */
+	if (!vsi->mqprio_qopt.qopt.hw && vsi->reconfig_rss) {
+		vsi->rss_size = min_t(int, vsi->back->alloc_rss_size,
+				      vsi->num_queue_pairs);
+		ret = i40e_vsi_config_rss(vsi);
+		if (ret) {
+			dev_info(&vsi->back->pdev->dev,
+				 "Failed to reconfig rss for num_queues\n");
+			return ret;
+		}
+		vsi->reconfig_rss = false;
+	}
 	if (vsi->back->flags & I40E_FLAG_IWARP_ENABLED) {
 		ctxt.info.valid_sections |=
 				cpu_to_le16(I40E_AQ_VSI_PROP_QUEUE_OPT_VALID);
 		ctxt.info.queueing_opt_flags |= I40E_AQ_VSI_QUE_OPT_TCP_ENA;
 	}
 
-	/* Update the VSI after updating the VSI queue-mapping information */
+	/* Update the VSI after updating the VSI queue-mapping
+	 * information
+	 */
 	ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL);
 	if (ret) {
 		dev_info(&vsi->back->pdev->dev,
@@ -5154,6 +5416,825 @@ out:
 }
 
 /**
+ * i40e_get_link_speed - Returns link speed for the interface
+ * @vsi: VSI to be configured
+ *
+ **/
+int i40e_get_link_speed(struct i40e_vsi *vsi)
+{
+	struct i40e_pf *pf = vsi->back;
+
+	switch (pf->hw.phy.link_info.link_speed) {
+	case I40E_LINK_SPEED_40GB:
+		return 40000;
+	case I40E_LINK_SPEED_25GB:
+		return 25000;
+	case I40E_LINK_SPEED_20GB:
+		return 20000;
+	case I40E_LINK_SPEED_10GB:
+		return 10000;
+	case I40E_LINK_SPEED_1GB:
+		return 1000;
+	default:
+		return -EINVAL;
+	}
+}
+
+/**
+ * i40e_set_bw_limit - setup BW limit for Tx traffic based on max_tx_rate
+ * @vsi: VSI to be configured
+ * @seid: seid of the channel/VSI
+ * @max_tx_rate: max TX rate to be configured as BW limit
+ *
+ * Helper function to set BW limit for a given VSI
+ **/
+int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate)
+{
+	struct i40e_pf *pf = vsi->back;
+	u64 credits = 0;
+	int speed = 0;
+	int ret = 0;
+
+	speed = i40e_get_link_speed(vsi);
+	if (max_tx_rate > speed) {
+		dev_err(&pf->pdev->dev,
+			"Invalid max tx rate %llu specified for VSI seid %d.",
+			max_tx_rate, seid);
+		return -EINVAL;
+	}
+	if (max_tx_rate && max_tx_rate < 50) {
+		dev_warn(&pf->pdev->dev,
+			 "Setting max tx rate to minimum usable value of 50Mbps.\n");
+		max_tx_rate = 50;
+	}
+
+	/* Tx rate credits are in values of 50Mbps, 0 is disabled */
+	credits = max_tx_rate;
+	do_div(credits, I40E_BW_CREDIT_DIVISOR);
+	ret = i40e_aq_config_vsi_bw_limit(&pf->hw, seid, credits,
+					  I40E_MAX_BW_INACTIVE_ACCUM, NULL);
+	if (ret)
+		dev_err(&pf->pdev->dev,
+			"Failed set tx rate (%llu Mbps) for vsi->seid %u, err %s aq_err %s\n",
+			max_tx_rate, seid, i40e_stat_str(&pf->hw, ret),
+			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+	return ret;
+}
+
+/**
+ * i40e_remove_queue_channels - Remove queue channels for the TCs
+ * @vsi: VSI to be configured
+ *
+ * Remove queue channels for the TCs
+ **/
+static void i40e_remove_queue_channels(struct i40e_vsi *vsi)
+{
+	enum i40e_admin_queue_err last_aq_status;
+	struct i40e_cloud_filter *cfilter;
+	struct i40e_channel *ch, *ch_tmp;
+	struct i40e_pf *pf = vsi->back;
+	struct hlist_node *node;
+	int ret, i;
+
+	/* Reset rss size that was stored when reconfiguring rss for
+	 * channel VSIs with non-power-of-2 queue count.
+	 */
+	vsi->current_rss_size = 0;
+
+	/* perform cleanup for channels if they exist */
+	if (list_empty(&vsi->ch_list))
+		return;
+
+	list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) {
+		struct i40e_vsi *p_vsi;
+
+		list_del(&ch->list);
+		p_vsi = ch->parent_vsi;
+		if (!p_vsi || !ch->initialized) {
+			kfree(ch);
+			continue;
+		}
+		/* Reset queue contexts */
+		for (i = 0; i < ch->num_queue_pairs; i++) {
+			struct i40e_ring *tx_ring, *rx_ring;
+			u16 pf_q;
+
+			pf_q = ch->base_queue + i;
+			tx_ring = vsi->tx_rings[pf_q];
+			tx_ring->ch = NULL;
+
+			rx_ring = vsi->rx_rings[pf_q];
+			rx_ring->ch = NULL;
+		}
+
+		/* Reset BW configured for this VSI via mqprio */
+		ret = i40e_set_bw_limit(vsi, ch->seid, 0);
+		if (ret)
+			dev_info(&vsi->back->pdev->dev,
+				 "Failed to reset tx rate for ch->seid %u\n",
+				 ch->seid);
+
+		/* delete cloud filters associated with this channel */
+		hlist_for_each_entry_safe(cfilter, node,
+					  &pf->cloud_filter_list, cloud_node) {
+			if (cfilter->seid != ch->seid)
+				continue;
+
+			hash_del(&cfilter->cloud_node);
+			if (cfilter->dst_port)
+				ret = i40e_add_del_cloud_filter_big_buf(vsi,
+									cfilter,
+									false);
+			else
+				ret = i40e_add_del_cloud_filter(vsi, cfilter,
+								false);
+			last_aq_status = pf->hw.aq.asq_last_status;
+			if (ret)
+				dev_info(&pf->pdev->dev,
+					 "Failed to delete cloud filter, err %s aq_err %s\n",
+					 i40e_stat_str(&pf->hw, ret),
+					 i40e_aq_str(&pf->hw, last_aq_status));
+			kfree(cfilter);
+		}
+
+		/* delete VSI from FW */
+		ret = i40e_aq_delete_element(&vsi->back->hw, ch->seid,
+					     NULL);
+		if (ret)
+			dev_err(&vsi->back->pdev->dev,
+				"unable to remove channel (%d) for parent VSI(%d)\n",
+				ch->seid, p_vsi->seid);
+		kfree(ch);
+	}
+	INIT_LIST_HEAD(&vsi->ch_list);
+}
+
+/**
+ * i40e_is_any_channel - channel exist or not
+ * @vsi: ptr to VSI to which channels are associated with
+ *
+ * Returns true or false if channel(s) exist for associated VSI or not
+ **/
+static bool i40e_is_any_channel(struct i40e_vsi *vsi)
+{
+	struct i40e_channel *ch, *ch_tmp;
+
+	list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) {
+		if (ch->initialized)
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * i40e_get_max_queues_for_channel
+ * @vsi: ptr to VSI to which channels are associated with
+ *
+ * Helper function which returns max value among the queue counts set on the
+ * channels/TCs created.
+ **/
+static int i40e_get_max_queues_for_channel(struct i40e_vsi *vsi)
+{
+	struct i40e_channel *ch, *ch_tmp;
+	int max = 0;
+
+	list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) {
+		if (!ch->initialized)
+			continue;
+		if (ch->num_queue_pairs > max)
+			max = ch->num_queue_pairs;
+	}
+
+	return max;
+}
+
+/**
+ * i40e_validate_num_queues - validate num_queues w.r.t channel
+ * @pf: ptr to PF device
+ * @num_queues: number of queues
+ * @vsi: the parent VSI
+ * @reconfig_rss: indicates should the RSS be reconfigured or not
+ *
+ * This function validates number of queues in the context of new channel
+ * which is being established and determines if RSS should be reconfigured
+ * or not for parent VSI.
+ **/
+static int i40e_validate_num_queues(struct i40e_pf *pf, int num_queues,
+				    struct i40e_vsi *vsi, bool *reconfig_rss)
+{
+	int max_ch_queues;
+
+	if (!reconfig_rss)
+		return -EINVAL;
+
+	*reconfig_rss = false;
+
+	if (num_queues > I40E_MAX_QUEUES_PER_CH) {
+		dev_err(&pf->pdev->dev,
+			"Failed to create VMDq VSI. User requested num_queues (%d) > I40E_MAX_QUEUES_PER_VSI (%u)\n",
+			num_queues, I40E_MAX_QUEUES_PER_CH);
+		return -EINVAL;
+	}
+
+	if (vsi->current_rss_size) {
+		if (num_queues > vsi->current_rss_size) {
+			dev_dbg(&pf->pdev->dev,
+				"Error: num_queues (%d) > vsi's current_size(%d)\n",
+				num_queues, vsi->current_rss_size);
+			return -EINVAL;
+		} else if ((num_queues < vsi->current_rss_size) &&
+			   (!is_power_of_2(num_queues))) {
+			dev_dbg(&pf->pdev->dev,
+				"Error: num_queues (%d) < vsi's current_size(%d), but not power of 2\n",
+				num_queues, vsi->current_rss_size);
+			return -EINVAL;
+		}
+	}
+
+	if (!is_power_of_2(num_queues)) {
+		/* Find the max num_queues configured for channel if channel
+		 * exist.
+		 * if channel exist, then enforce 'num_queues' to be more than
+		 * max ever queues configured for channel.
+		 */
+		max_ch_queues = i40e_get_max_queues_for_channel(vsi);
+		if (num_queues < max_ch_queues) {
+			dev_dbg(&pf->pdev->dev,
+				"Error: num_queues (%d) < max queues configured for channel(%d)\n",
+				num_queues, max_ch_queues);
+			return -EINVAL;
+		}
+		*reconfig_rss = true;
+	}
+
+	return 0;
+}
+
+/**
+ * i40e_vsi_reconfig_rss - reconfig RSS based on specified rss_size
+ * @vsi: the VSI being setup
+ * @rss_size: size of RSS, accordingly LUT gets reprogrammed
+ *
+ * This function reconfigures RSS by reprogramming LUTs using 'rss_size'
+ **/
+static int i40e_vsi_reconfig_rss(struct i40e_vsi *vsi, u16 rss_size)
+{
+	struct i40e_pf *pf = vsi->back;
+	u8 seed[I40E_HKEY_ARRAY_SIZE];
+	struct i40e_hw *hw = &pf->hw;
+	int local_rss_size;
+	u8 *lut;
+	int ret;
+
+	if (!vsi->rss_size)
+		return -EINVAL;
+
+	if (rss_size > vsi->rss_size)
+		return -EINVAL;
+
+	local_rss_size = min_t(int, vsi->rss_size, rss_size);
+	lut = kzalloc(vsi->rss_table_size, GFP_KERNEL);
+	if (!lut)
+		return -ENOMEM;
+
+	/* Ignoring user configured lut if there is one */
+	i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, local_rss_size);
+
+	/* Use user configured hash key if there is one, otherwise
+	 * use default.
+	 */
+	if (vsi->rss_hkey_user)
+		memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE);
+	else
+		netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE);
+
+	ret = i40e_config_rss(vsi, seed, lut, vsi->rss_table_size);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "Cannot set RSS lut, err %s aq_err %s\n",
+			 i40e_stat_str(hw, ret),
+			 i40e_aq_str(hw, hw->aq.asq_last_status));
+		kfree(lut);
+		return ret;
+	}
+	kfree(lut);
+
+	/* Do the update w.r.t. storing rss_size */
+	if (!vsi->orig_rss_size)
+		vsi->orig_rss_size = vsi->rss_size;
+	vsi->current_rss_size = local_rss_size;
+
+	return ret;
+}
+
+/**
+ * i40e_channel_setup_queue_map - Setup a channel queue map
+ * @pf: ptr to PF device
+ * @vsi: the VSI being setup
+ * @ctxt: VSI context structure
+ * @ch: ptr to channel structure
+ *
+ * Setup queue map for a specific channel
+ **/
+static void i40e_channel_setup_queue_map(struct i40e_pf *pf,
+					 struct i40e_vsi_context *ctxt,
+					 struct i40e_channel *ch)
+{
+	u16 qcount, qmap, sections = 0;
+	u8 offset = 0;
+	int pow;
+
+	sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID;
+	sections |= I40E_AQ_VSI_PROP_SCHED_VALID;
+
+	qcount = min_t(int, ch->num_queue_pairs, pf->num_lan_msix);
+	ch->num_queue_pairs = qcount;
+
+	/* find the next higher power-of-2 of num queue pairs */
+	pow = ilog2(qcount);
+	if (!is_power_of_2(qcount))
+		pow++;
+
+	qmap = (offset << I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) |
+		(pow << I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT);
+
+	/* Setup queue TC[0].qmap for given VSI context */
+	ctxt->info.tc_mapping[0] = cpu_to_le16(qmap);
+
+	ctxt->info.up_enable_bits = 0x1; /* TC0 enabled */
+	ctxt->info.mapping_flags |= cpu_to_le16(I40E_AQ_VSI_QUE_MAP_CONTIG);
+	ctxt->info.queue_mapping[0] = cpu_to_le16(ch->base_queue);
+	ctxt->info.valid_sections |= cpu_to_le16(sections);
+}
+
+/**
+ * i40e_add_channel - add a channel by adding VSI
+ * @pf: ptr to PF device
+ * @uplink_seid: underlying HW switching element (VEB) ID
+ * @ch: ptr to channel structure
+ *
+ * Add a channel (VSI) using add_vsi and queue_map
+ **/
+static int i40e_add_channel(struct i40e_pf *pf, u16 uplink_seid,
+			    struct i40e_channel *ch)
+{
+	struct i40e_hw *hw = &pf->hw;
+	struct i40e_vsi_context ctxt;
+	u8 enabled_tc = 0x1; /* TC0 enabled */
+	int ret;
+
+	if (ch->type != I40E_VSI_VMDQ2) {
+		dev_info(&pf->pdev->dev,
+			 "add new vsi failed, ch->type %d\n", ch->type);
+		return -EINVAL;
+	}
+
+	memset(&ctxt, 0, sizeof(ctxt));
+	ctxt.pf_num = hw->pf_id;
+	ctxt.vf_num = 0;
+	ctxt.uplink_seid = uplink_seid;
+	ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL;
+	if (ch->type == I40E_VSI_VMDQ2)
+		ctxt.flags = I40E_AQ_VSI_TYPE_VMDQ2;
+
+	if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED) {
+		ctxt.info.valid_sections |=
+		     cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID);
+		ctxt.info.switch_id =
+		   cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB);
+	}
+
+	/* Set queue map for a given VSI context */
+	i40e_channel_setup_queue_map(pf, &ctxt, ch);
+
+	/* Now time to create VSI */
+	ret = i40e_aq_add_vsi(hw, &ctxt, NULL);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "add new vsi failed, err %s aq_err %s\n",
+			 i40e_stat_str(&pf->hw, ret),
+			 i40e_aq_str(&pf->hw,
+				     pf->hw.aq.asq_last_status));
+		return -ENOENT;
+	}
+
+	/* Success, update channel */
+	ch->enabled_tc = enabled_tc;
+	ch->seid = ctxt.seid;
+	ch->vsi_number = ctxt.vsi_number;
+	ch->stat_counter_idx = cpu_to_le16(ctxt.info.stat_counter_idx);
+
+	/* copy just the sections touched not the entire info
+	 * since not all sections are valid as returned by
+	 * update vsi params
+	 */
+	ch->info.mapping_flags = ctxt.info.mapping_flags;
+	memcpy(&ch->info.queue_mapping,
+	       &ctxt.info.queue_mapping, sizeof(ctxt.info.queue_mapping));
+	memcpy(&ch->info.tc_mapping, ctxt.info.tc_mapping,
+	       sizeof(ctxt.info.tc_mapping));
+
+	return 0;
+}
+
+static int i40e_channel_config_bw(struct i40e_vsi *vsi, struct i40e_channel *ch,
+				  u8 *bw_share)
+{
+	struct i40e_aqc_configure_vsi_tc_bw_data bw_data;
+	i40e_status ret;
+	int i;
+
+	bw_data.tc_valid_bits = ch->enabled_tc;
+	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)
+		bw_data.tc_bw_credits[i] = bw_share[i];
+
+	ret = i40e_aq_config_vsi_tc_bw(&vsi->back->hw, ch->seid,
+				       &bw_data, NULL);
+	if (ret) {
+		dev_info(&vsi->back->pdev->dev,
+			 "Config VSI BW allocation per TC failed, aq_err: %d for new_vsi->seid %u\n",
+			 vsi->back->hw.aq.asq_last_status, ch->seid);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)
+		ch->info.qs_handle[i] = bw_data.qs_handles[i];
+
+	return 0;
+}
+
+/**
+ * i40e_channel_config_tx_ring - config TX ring associated with new channel
+ * @pf: ptr to PF device
+ * @vsi: the VSI being setup
+ * @ch: ptr to channel structure
+ *
+ * Configure TX rings associated with channel (VSI) since queues are being
+ * from parent VSI.
+ **/
+static int i40e_channel_config_tx_ring(struct i40e_pf *pf,
+				       struct i40e_vsi *vsi,
+				       struct i40e_channel *ch)
+{
+	i40e_status ret;
+	int i;
+	u8 bw_share[I40E_MAX_TRAFFIC_CLASS] = {0};
+
+	/* Enable ETS TCs with equal BW Share for now across all VSIs */
+	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+		if (ch->enabled_tc & BIT(i))
+			bw_share[i] = 1;
+	}
+
+	/* configure BW for new VSI */
+	ret = i40e_channel_config_bw(vsi, ch, bw_share);
+	if (ret) {
+		dev_info(&vsi->back->pdev->dev,
+			 "Failed configuring TC map %d for channel (seid %u)\n",
+			 ch->enabled_tc, ch->seid);
+		return ret;
+	}
+
+	for (i = 0; i < ch->num_queue_pairs; i++) {
+		struct i40e_ring *tx_ring, *rx_ring;
+		u16 pf_q;
+
+		pf_q = ch->base_queue + i;
+
+		/* Get to TX ring ptr of main VSI, for re-setup TX queue
+		 * context
+		 */
+		tx_ring = vsi->tx_rings[pf_q];
+		tx_ring->ch = ch;
+
+		/* Get the RX ring ptr */
+		rx_ring = vsi->rx_rings[pf_q];
+		rx_ring->ch = ch;
+	}
+
+	return 0;
+}
+
+/**
+ * i40e_setup_hw_channel - setup new channel
+ * @pf: ptr to PF device
+ * @vsi: the VSI being setup
+ * @ch: ptr to channel structure
+ * @uplink_seid: underlying HW switching element (VEB) ID
+ * @type: type of channel to be created (VMDq2/VF)
+ *
+ * Setup new channel (VSI) based on specified type (VMDq2/VF)
+ * and configures TX rings accordingly
+ **/
+static inline int i40e_setup_hw_channel(struct i40e_pf *pf,
+					struct i40e_vsi *vsi,
+					struct i40e_channel *ch,
+					u16 uplink_seid, u8 type)
+{
+	int ret;
+
+	ch->initialized = false;
+	ch->base_queue = vsi->next_base_queue;
+	ch->type = type;
+
+	/* Proceed with creation of channel (VMDq2) VSI */
+	ret = i40e_add_channel(pf, uplink_seid, ch);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "failed to add_channel using uplink_seid %u\n",
+			 uplink_seid);
+		return ret;
+	}
+
+	/* Mark the successful creation of channel */
+	ch->initialized = true;
+
+	/* Reconfigure TX queues using QTX_CTL register */
+	ret = i40e_channel_config_tx_ring(pf, vsi, ch);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "failed to configure TX rings for channel %u\n",
+			 ch->seid);
+		return ret;
+	}
+
+	/* update 'next_base_queue' */
+	vsi->next_base_queue = vsi->next_base_queue + ch->num_queue_pairs;
+	dev_dbg(&pf->pdev->dev,
+		"Added channel: vsi_seid %u, vsi_number %u, stat_counter_idx %u, num_queue_pairs %u, pf->next_base_queue %d\n",
+		ch->seid, ch->vsi_number, ch->stat_counter_idx,
+		ch->num_queue_pairs,
+		vsi->next_base_queue);
+	return ret;
+}
+
+/**
+ * i40e_setup_channel - setup new channel using uplink element
+ * @pf: ptr to PF device
+ * @type: type of channel to be created (VMDq2/VF)
+ * @uplink_seid: underlying HW switching element (VEB) ID
+ * @ch: ptr to channel structure
+ *
+ * Setup new channel (VSI) based on specified type (VMDq2/VF)
+ * and uplink switching element (uplink_seid)
+ **/
+static bool i40e_setup_channel(struct i40e_pf *pf, struct i40e_vsi *vsi,
+			       struct i40e_channel *ch)
+{
+	u8 vsi_type;
+	u16 seid;
+	int ret;
+
+	if (vsi->type == I40E_VSI_MAIN) {
+		vsi_type = I40E_VSI_VMDQ2;
+	} else {
+		dev_err(&pf->pdev->dev, "unsupported parent vsi type(%d)\n",
+			vsi->type);
+		return false;
+	}
+
+	/* underlying switching element */
+	seid = pf->vsi[pf->lan_vsi]->uplink_seid;
+
+	/* create channel (VSI), configure TX rings */
+	ret = i40e_setup_hw_channel(pf, vsi, ch, seid, vsi_type);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "failed to setup hw_channel\n");
+		return false;
+	}
+
+	return ch->initialized ? true : false;
+}
+
+/**
+ * i40e_validate_and_set_switch_mode - sets up switch mode correctly
+ * @vsi: ptr to VSI which has PF backing
+ *
+ * Sets up switch mode correctly if it needs to be changed and perform
+ * what are allowed modes.
+ **/
+static int i40e_validate_and_set_switch_mode(struct i40e_vsi *vsi)
+{
+	u8 mode;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	int ret;
+
+	ret = i40e_get_capabilities(pf, i40e_aqc_opc_list_dev_capabilities);
+	if (ret)
+		return -EINVAL;
+
+	if (hw->dev_caps.switch_mode) {
+		/* if switch mode is set, support mode2 (non-tunneled for
+		 * cloud filter) for now
+		 */
+		u32 switch_mode = hw->dev_caps.switch_mode &
+				  I40E_SWITCH_MODE_MASK;
+		if (switch_mode >= I40E_CLOUD_FILTER_MODE1) {
+			if (switch_mode == I40E_CLOUD_FILTER_MODE2)
+				return 0;
+			dev_err(&pf->pdev->dev,
+				"Invalid switch_mode (%d), only non-tunneled mode for cloud filter is supported\n",
+				hw->dev_caps.switch_mode);
+			return -EINVAL;
+		}
+	}
+
+	/* Set Bit 7 to be valid */
+	mode = I40E_AQ_SET_SWITCH_BIT7_VALID;
+
+	/* Set L4type to both TCP and UDP support */
+	mode |= I40E_AQ_SET_SWITCH_L4_TYPE_BOTH;
+
+	/* Set cloud filter mode */
+	mode |= I40E_AQ_SET_SWITCH_MODE_NON_TUNNEL;
+
+	/* Prep mode field for set_switch_config */
+	ret = i40e_aq_set_switch_config(hw, pf->last_sw_conf_flags,
+					pf->last_sw_conf_valid_flags,
+					mode, NULL);
+	if (ret && hw->aq.asq_last_status != I40E_AQ_RC_ESRCH)
+		dev_err(&pf->pdev->dev,
+			"couldn't set switch config bits, err %s aq_err %s\n",
+			i40e_stat_str(hw, ret),
+			i40e_aq_str(hw,
+				    hw->aq.asq_last_status));
+
+	return ret;
+}
+
+/**
+ * i40e_create_queue_channel - function to create channel
+ * @vsi: VSI to be configured
+ * @ch: ptr to channel (it contains channel specific params)
+ *
+ * This function creates channel (VSI) using num_queues specified by user,
+ * reconfigs RSS if needed.
+ **/
+int i40e_create_queue_channel(struct i40e_vsi *vsi,
+			      struct i40e_channel *ch)
+{
+	struct i40e_pf *pf = vsi->back;
+	bool reconfig_rss;
+	int err;
+
+	if (!ch)
+		return -EINVAL;
+
+	if (!ch->num_queue_pairs) {
+		dev_err(&pf->pdev->dev, "Invalid num_queues requested: %d\n",
+			ch->num_queue_pairs);
+		return -EINVAL;
+	}
+
+	/* validate user requested num_queues for channel */
+	err = i40e_validate_num_queues(pf, ch->num_queue_pairs, vsi,
+				       &reconfig_rss);
+	if (err) {
+		dev_info(&pf->pdev->dev, "Failed to validate num_queues (%d)\n",
+			 ch->num_queue_pairs);
+		return -EINVAL;
+	}
+
+	/* By default we are in VEPA mode, if this is the first VF/VMDq
+	 * VSI to be added switch to VEB mode.
+	 */
+	if ((!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) ||
+	    (!i40e_is_any_channel(vsi))) {
+		if (!is_power_of_2(vsi->tc_config.tc_info[0].qcount)) {
+			dev_dbg(&pf->pdev->dev,
+				"Failed to create channel. Override queues (%u) not power of 2\n",
+				vsi->tc_config.tc_info[0].qcount);
+			return -EINVAL;
+		}
+
+		if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
+			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+
+			if (vsi->type == I40E_VSI_MAIN) {
+				if (pf->flags & I40E_FLAG_TC_MQPRIO)
+					i40e_do_reset(pf, I40E_PF_RESET_FLAG,
+						      true);
+				else
+					i40e_do_reset_safe(pf,
+							   I40E_PF_RESET_FLAG);
+			}
+		}
+		/* now onwards for main VSI, number of queues will be value
+		 * of TC0's queue count
+		 */
+	}
+
+	/* By this time, vsi->cnt_q_avail shall be set to non-zero and
+	 * it should be more than num_queues
+	 */
+	if (!vsi->cnt_q_avail || vsi->cnt_q_avail < ch->num_queue_pairs) {
+		dev_dbg(&pf->pdev->dev,
+			"Error: cnt_q_avail (%u) less than num_queues %d\n",
+			vsi->cnt_q_avail, ch->num_queue_pairs);
+		return -EINVAL;
+	}
+
+	/* reconfig_rss only if vsi type is MAIN_VSI */
+	if (reconfig_rss && (vsi->type == I40E_VSI_MAIN)) {
+		err = i40e_vsi_reconfig_rss(vsi, ch->num_queue_pairs);
+		if (err) {
+			dev_info(&pf->pdev->dev,
+				 "Error: unable to reconfig rss for num_queues (%u)\n",
+				 ch->num_queue_pairs);
+			return -EINVAL;
+		}
+	}
+
+	if (!i40e_setup_channel(pf, vsi, ch)) {
+		dev_info(&pf->pdev->dev, "Failed to setup channel\n");
+		return -EINVAL;
+	}
+
+	dev_info(&pf->pdev->dev,
+		 "Setup channel (id:%u) utilizing num_queues %d\n",
+		 ch->seid, ch->num_queue_pairs);
+
+	/* configure VSI for BW limit */
+	if (ch->max_tx_rate) {
+		u64 credits = ch->max_tx_rate;
+
+		if (i40e_set_bw_limit(vsi, ch->seid, ch->max_tx_rate))
+			return -EINVAL;
+
+		do_div(credits, I40E_BW_CREDIT_DIVISOR);
+		dev_dbg(&pf->pdev->dev,
+			"Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n",
+			ch->max_tx_rate,
+			credits,
+			ch->seid);
+	}
+
+	/* in case of VF, this will be main SRIOV VSI */
+	ch->parent_vsi = vsi;
+
+	/* and update main_vsi's count for queue_available to use */
+	vsi->cnt_q_avail -= ch->num_queue_pairs;
+
+	return 0;
+}
+
+/**
+ * i40e_configure_queue_channels - Add queue channel for the given TCs
+ * @vsi: VSI to be configured
+ *
+ * Configures queue channel mapping to the given TCs
+ **/
+static int i40e_configure_queue_channels(struct i40e_vsi *vsi)
+{
+	struct i40e_channel *ch;
+	u64 max_rate = 0;
+	int ret = 0, i;
+
+	/* Create app vsi with the TCs. Main VSI with TC0 is already set up */
+	vsi->tc_seid_map[0] = vsi->seid;
+	for (i = 1; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+		if (vsi->tc_config.enabled_tc & BIT(i)) {
+			ch = kzalloc(sizeof(*ch), GFP_KERNEL);
+			if (!ch) {
+				ret = -ENOMEM;
+				goto err_free;
+			}
+
+			INIT_LIST_HEAD(&ch->list);
+			ch->num_queue_pairs =
+				vsi->tc_config.tc_info[i].qcount;
+			ch->base_queue =
+				vsi->tc_config.tc_info[i].qoffset;
+
+			/* Bandwidth limit through tc interface is in bytes/s,
+			 * change to Mbit/s
+			 */
+			max_rate = vsi->mqprio_qopt.max_rate[i];
+			do_div(max_rate, I40E_BW_MBPS_DIVISOR);
+			ch->max_tx_rate = max_rate;
+
+			list_add_tail(&ch->list, &vsi->ch_list);
+
+			ret = i40e_create_queue_channel(vsi, ch);
+			if (ret) {
+				dev_err(&vsi->back->pdev->dev,
+					"Failed creating queue channel with TC%d: queues %d\n",
+					i, ch->num_queue_pairs);
+				goto err_free;
+			}
+			vsi->tc_seid_map[i] = ch->seid;
+		}
+	}
+	return ret;
+
+err_free:
+	i40e_remove_queue_channels(vsi);
+	return ret;
+}
+
+/**
  * i40e_veb_config_tc - Configure TCs for given VEB
  * @veb: given VEB
  * @enabled_tc: TC bitmap
@@ -5346,13 +6427,14 @@ out:
 void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
 {
 	enum i40e_aq_link_speed new_speed;
+	struct i40e_pf *pf = vsi->back;
 	char *speed = "Unknown";
 	char *fc = "Unknown";
 	char *fec = "";
 	char *req_fec = "";
 	char *an = "";
 
-	new_speed = vsi->back->hw.phy.link_info.link_speed;
+	new_speed = pf->hw.phy.link_info.link_speed;
 
 	if ((vsi->current_isup == isup) && (vsi->current_speed == new_speed))
 		return;
@@ -5366,13 +6448,13 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
 	/* Warn user if link speed on NPAR enabled partition is not at
 	 * least 10GB
 	 */
-	if (vsi->back->hw.func_caps.npar_enable &&
-	    (vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_1GB ||
-	     vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_100MB))
+	if (pf->hw.func_caps.npar_enable &&
+	    (pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_1GB ||
+	     pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_100MB))
 		netdev_warn(vsi->netdev,
 			    "The partition detected link speed that is less than 10Gbps\n");
 
-	switch (vsi->back->hw.phy.link_info.link_speed) {
+	switch (pf->hw.phy.link_info.link_speed) {
 	case I40E_LINK_SPEED_40GB:
 		speed = "40 G";
 		break;
@@ -5395,7 +6477,7 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
 		break;
 	}
 
-	switch (vsi->back->hw.fc.current_mode) {
+	switch (pf->hw.fc.current_mode) {
 	case I40E_FC_FULL:
 		fc = "RX/TX";
 		break;
@@ -5410,18 +6492,18 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
 		break;
 	}
 
-	if (vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) {
+	if (pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) {
 		req_fec = ", Requested FEC: None";
 		fec = ", FEC: None";
 		an = ", Autoneg: False";
 
-		if (vsi->back->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED)
+		if (pf->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED)
 			an = ", Autoneg: True";
 
-		if (vsi->back->hw.phy.link_info.fec_info &
+		if (pf->hw.phy.link_info.fec_info &
 		    I40E_AQ_CONFIG_FEC_KR_ENA)
 			fec = ", FEC: CL74 FC-FEC/BASE-R";
-		else if (vsi->back->hw.phy.link_info.fec_info &
+		else if (pf->hw.phy.link_info.fec_info &
 			 I40E_AQ_CONFIG_FEC_RS_ENA)
 			fec = ", FEC: CL108 RS-FEC";
 
@@ -5470,15 +6552,6 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
 		i40e_print_link_message(vsi, true);
 		netif_tx_start_all_queues(vsi->netdev);
 		netif_carrier_on(vsi->netdev);
-	} else if (vsi->netdev) {
-		i40e_print_link_message(vsi, false);
-		/* need to check for qualified module here*/
-		if ((pf->hw.phy.link_info.link_info &
-			I40E_AQ_MEDIA_AVAILABLE) &&
-		    (!(pf->hw.phy.link_info.an_info &
-			I40E_AQ_QUALIFIED_MODULE)))
-			netdev_err(vsi->netdev,
-				   "the driver failed to link because an unqualified module was detected.");
 	}
 
 	/* replay FDIR SB filters */
@@ -5562,74 +6635,928 @@ void i40e_down(struct i40e_vsi *vsi)
 }
 
 /**
+ * i40e_validate_mqprio_qopt- validate queue mapping info
+ * @vsi: the VSI being configured
+ * @mqprio_qopt: queue parametrs
+ **/
+static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi,
+				     struct tc_mqprio_qopt_offload *mqprio_qopt)
+{
+	u64 sum_max_rate = 0;
+	u64 max_rate = 0;
+	int i;
+
+	if (mqprio_qopt->qopt.offset[0] != 0 ||
+	    mqprio_qopt->qopt.num_tc < 1 ||
+	    mqprio_qopt->qopt.num_tc > I40E_MAX_TRAFFIC_CLASS)
+		return -EINVAL;
+	for (i = 0; ; i++) {
+		if (!mqprio_qopt->qopt.count[i])
+			return -EINVAL;
+		if (mqprio_qopt->min_rate[i]) {
+			dev_err(&vsi->back->pdev->dev,
+				"Invalid min tx rate (greater than 0) specified\n");
+			return -EINVAL;
+		}
+		max_rate = mqprio_qopt->max_rate[i];
+		do_div(max_rate, I40E_BW_MBPS_DIVISOR);
+		sum_max_rate += max_rate;
+
+		if (i >= mqprio_qopt->qopt.num_tc - 1)
+			break;
+		if (mqprio_qopt->qopt.offset[i + 1] !=
+		    (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i]))
+			return -EINVAL;
+	}
+	if (vsi->num_queue_pairs <
+	    (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) {
+		return -EINVAL;
+	}
+	if (sum_max_rate > i40e_get_link_speed(vsi)) {
+		dev_err(&vsi->back->pdev->dev,
+			"Invalid max tx rate specified\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * i40e_vsi_set_default_tc_config - set default values for tc configuration
+ * @vsi: the VSI being configured
+ **/
+static void i40e_vsi_set_default_tc_config(struct i40e_vsi *vsi)
+{
+	u16 qcount;
+	int i;
+
+	/* Only TC0 is enabled */
+	vsi->tc_config.numtc = 1;
+	vsi->tc_config.enabled_tc = 1;
+	qcount = min_t(int, vsi->alloc_queue_pairs,
+		       i40e_pf_get_max_q_per_tc(vsi->back));
+	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+		/* For the TC that is not enabled set the offset to to default
+		 * queue and allocate one queue for the given TC.
+		 */
+		vsi->tc_config.tc_info[i].qoffset = 0;
+		if (i == 0)
+			vsi->tc_config.tc_info[i].qcount = qcount;
+		else
+			vsi->tc_config.tc_info[i].qcount = 1;
+		vsi->tc_config.tc_info[i].netdev_tc = 0;
+	}
+}
+
+/**
  * i40e_setup_tc - configure multiple traffic classes
  * @netdev: net device to configure
- * @tc: number of traffic classes to enable
+ * @type_data: tc offload data
  **/
-static int i40e_setup_tc(struct net_device *netdev, u8 tc)
+static int i40e_setup_tc(struct net_device *netdev, void *type_data)
 {
+	struct tc_mqprio_qopt_offload *mqprio_qopt = type_data;
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	u8 enabled_tc = 0;
+	u8 enabled_tc = 0, num_tc, hw;
+	bool need_reset = false;
 	int ret = -EINVAL;
+	u16 mode;
 	int i;
 
-	/* Check if DCB enabled to continue */
-	if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) {
-		netdev_info(netdev, "DCB is not enabled for adapter\n");
-		goto exit;
+	num_tc = mqprio_qopt->qopt.num_tc;
+	hw = mqprio_qopt->qopt.hw;
+	mode = mqprio_qopt->mode;
+	if (!hw) {
+		pf->flags &= ~I40E_FLAG_TC_MQPRIO;
+		memcpy(&vsi->mqprio_qopt, mqprio_qopt, sizeof(*mqprio_qopt));
+		goto config_tc;
 	}
 
 	/* Check if MFP enabled */
 	if (pf->flags & I40E_FLAG_MFP_ENABLED) {
-		netdev_info(netdev, "Configuring TC not supported in MFP mode\n");
-		goto exit;
+		netdev_info(netdev,
+			    "Configuring TC not supported in MFP mode\n");
+		return ret;
 	}
+	switch (mode) {
+	case TC_MQPRIO_MODE_DCB:
+		pf->flags &= ~I40E_FLAG_TC_MQPRIO;
 
-	/* Check whether tc count is within enabled limit */
-	if (tc > i40e_pf_get_num_tc(pf)) {
-		netdev_info(netdev, "TC count greater than enabled on link for adapter\n");
-		goto exit;
+		/* Check if DCB enabled to continue */
+		if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) {
+			netdev_info(netdev,
+				    "DCB is not enabled for adapter\n");
+			return ret;
+		}
+
+		/* Check whether tc count is within enabled limit */
+		if (num_tc > i40e_pf_get_num_tc(pf)) {
+			netdev_info(netdev,
+				    "TC count greater than enabled on link for adapter\n");
+			return ret;
+		}
+		break;
+	case TC_MQPRIO_MODE_CHANNEL:
+		if (pf->flags & I40E_FLAG_DCB_ENABLED) {
+			netdev_info(netdev,
+				    "Full offload of TC Mqprio options is not supported when DCB is enabled\n");
+			return ret;
+		}
+		if (!(pf->flags & I40E_FLAG_MSIX_ENABLED))
+			return ret;
+		ret = i40e_validate_mqprio_qopt(vsi, mqprio_qopt);
+		if (ret)
+			return ret;
+		memcpy(&vsi->mqprio_qopt, mqprio_qopt,
+		       sizeof(*mqprio_qopt));
+		pf->flags |= I40E_FLAG_TC_MQPRIO;
+		pf->flags &= ~I40E_FLAG_DCB_ENABLED;
+		break;
+	default:
+		return -EINVAL;
 	}
 
+config_tc:
 	/* Generate TC map for number of tc requested */
-	for (i = 0; i < tc; i++)
+	for (i = 0; i < num_tc; i++)
 		enabled_tc |= BIT(i);
 
 	/* Requesting same TC configuration as already enabled */
-	if (enabled_tc == vsi->tc_config.enabled_tc)
+	if (enabled_tc == vsi->tc_config.enabled_tc &&
+	    mode != TC_MQPRIO_MODE_CHANNEL)
 		return 0;
 
 	/* Quiesce VSI queues */
 	i40e_quiesce_vsi(vsi);
 
+	if (!hw && !(pf->flags & I40E_FLAG_TC_MQPRIO))
+		i40e_remove_queue_channels(vsi);
+
 	/* Configure VSI for enabled TCs */
 	ret = i40e_vsi_config_tc(vsi, enabled_tc);
 	if (ret) {
 		netdev_info(netdev, "Failed configuring TC for VSI seid=%d\n",
 			    vsi->seid);
+		need_reset = true;
 		goto exit;
 	}
 
+	if (pf->flags & I40E_FLAG_TC_MQPRIO) {
+		if (vsi->mqprio_qopt.max_rate[0]) {
+			u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0];
+
+			do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR);
+			ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate);
+			if (!ret) {
+				u64 credits = max_tx_rate;
+
+				do_div(credits, I40E_BW_CREDIT_DIVISOR);
+				dev_dbg(&vsi->back->pdev->dev,
+					"Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n",
+					max_tx_rate,
+					credits,
+					vsi->seid);
+			} else {
+				need_reset = true;
+				goto exit;
+			}
+		}
+		ret = i40e_configure_queue_channels(vsi);
+		if (ret) {
+			netdev_info(netdev,
+				    "Failed configuring queue channels\n");
+			need_reset = true;
+			goto exit;
+		}
+	}
+
+exit:
+	/* Reset the configuration data to defaults, only TC0 is enabled */
+	if (need_reset) {
+		i40e_vsi_set_default_tc_config(vsi);
+		need_reset = false;
+	}
+
 	/* Unquiesce VSI */
 	i40e_unquiesce_vsi(vsi);
+	return ret;
+}
 
-exit:
+/**
+ * i40e_set_cld_element - sets cloud filter element data
+ * @filter: cloud filter rule
+ * @cld: ptr to cloud filter element data
+ *
+ * This is helper function to copy data into cloud filter element
+ **/
+static inline void
+i40e_set_cld_element(struct i40e_cloud_filter *filter,
+		     struct i40e_aqc_cloud_filters_element_data *cld)
+{
+	int i, j;
+	u32 ipa;
+
+	memset(cld, 0, sizeof(*cld));
+	ether_addr_copy(cld->outer_mac, filter->dst_mac);
+	ether_addr_copy(cld->inner_mac, filter->src_mac);
+
+	if (filter->n_proto != ETH_P_IP && filter->n_proto != ETH_P_IPV6)
+		return;
+
+	if (filter->n_proto == ETH_P_IPV6) {
+#define IPV6_MAX_INDEX	(ARRAY_SIZE(filter->dst_ipv6) - 1)
+		for (i = 0, j = 0; i < ARRAY_SIZE(filter->dst_ipv6);
+		     i++, j += 2) {
+			ipa = be32_to_cpu(filter->dst_ipv6[IPV6_MAX_INDEX - i]);
+			ipa = cpu_to_le32(ipa);
+			memcpy(&cld->ipaddr.raw_v6.data[j], &ipa, sizeof(ipa));
+		}
+	} else {
+		ipa = be32_to_cpu(filter->dst_ipv4);
+		memcpy(&cld->ipaddr.v4.data, &ipa, sizeof(ipa));
+	}
+
+	cld->inner_vlan = cpu_to_le16(ntohs(filter->vlan_id));
+
+	/* tenant_id is not supported by FW now, once the support is enabled
+	 * fill the cld->tenant_id with cpu_to_le32(filter->tenant_id)
+	 */
+	if (filter->tenant_id)
+		return;
+}
+
+/**
+ * i40e_add_del_cloud_filter - Add/del cloud filter
+ * @vsi: pointer to VSI
+ * @filter: cloud filter rule
+ * @add: if true, add, if false, delete
+ *
+ * Add or delete a cloud filter for a specific flow spec.
+ * Returns 0 if the filter were successfully added.
+ **/
+static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi,
+				     struct i40e_cloud_filter *filter, bool add)
+{
+	struct i40e_aqc_cloud_filters_element_data cld_filter;
+	struct i40e_pf *pf = vsi->back;
+	int ret;
+	static const u16 flag_table[128] = {
+		[I40E_CLOUD_FILTER_FLAGS_OMAC]  =
+			I40E_AQC_ADD_CLOUD_FILTER_OMAC,
+		[I40E_CLOUD_FILTER_FLAGS_IMAC]  =
+			I40E_AQC_ADD_CLOUD_FILTER_IMAC,
+		[I40E_CLOUD_FILTER_FLAGS_IMAC_IVLAN]  =
+			I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN,
+		[I40E_CLOUD_FILTER_FLAGS_IMAC_TEN_ID] =
+			I40E_AQC_ADD_CLOUD_FILTER_IMAC_TEN_ID,
+		[I40E_CLOUD_FILTER_FLAGS_OMAC_TEN_ID_IMAC] =
+			I40E_AQC_ADD_CLOUD_FILTER_OMAC_TEN_ID_IMAC,
+		[I40E_CLOUD_FILTER_FLAGS_IMAC_IVLAN_TEN_ID] =
+			I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN_TEN_ID,
+		[I40E_CLOUD_FILTER_FLAGS_IIP] =
+			I40E_AQC_ADD_CLOUD_FILTER_IIP,
+	};
+
+	if (filter->flags >= ARRAY_SIZE(flag_table))
+		return I40E_ERR_CONFIG;
+
+	/* copy element needed to add cloud filter from filter */
+	i40e_set_cld_element(filter, &cld_filter);
+
+	if (filter->tunnel_type != I40E_CLOUD_TNL_TYPE_NONE)
+		cld_filter.flags = cpu_to_le16(filter->tunnel_type <<
+					     I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT);
+
+	if (filter->n_proto == ETH_P_IPV6)
+		cld_filter.flags |= cpu_to_le16(flag_table[filter->flags] |
+						I40E_AQC_ADD_CLOUD_FLAGS_IPV6);
+	else
+		cld_filter.flags |= cpu_to_le16(flag_table[filter->flags] |
+						I40E_AQC_ADD_CLOUD_FLAGS_IPV4);
+
+	if (add)
+		ret = i40e_aq_add_cloud_filters(&pf->hw, filter->seid,
+						&cld_filter, 1);
+	else
+		ret = i40e_aq_rem_cloud_filters(&pf->hw, filter->seid,
+						&cld_filter, 1);
+	if (ret)
+		dev_dbg(&pf->pdev->dev,
+			"Failed to %s cloud filter using l4 port %u, err %d aq_err %d\n",
+			add ? "add" : "delete", filter->dst_port, ret,
+			pf->hw.aq.asq_last_status);
+	else
+		dev_info(&pf->pdev->dev,
+			 "%s cloud filter for VSI: %d\n",
+			 add ? "Added" : "Deleted", filter->seid);
 	return ret;
 }
 
-static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type,
-			   void *type_data)
+/**
+ * i40e_add_del_cloud_filter_big_buf - Add/del cloud filter using big_buf
+ * @vsi: pointer to VSI
+ * @filter: cloud filter rule
+ * @add: if true, add, if false, delete
+ *
+ * Add or delete a cloud filter for a specific flow spec using big buffer.
+ * Returns 0 if the filter were successfully added.
+ **/
+static int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi,
+					     struct i40e_cloud_filter *filter,
+					     bool add)
 {
-	struct tc_mqprio_qopt *mqprio = type_data;
+	struct i40e_aqc_cloud_filters_element_bb cld_filter;
+	struct i40e_pf *pf = vsi->back;
+	int ret;
+
+	/* Both (src/dst) valid mac_addr are not supported */
+	if ((is_valid_ether_addr(filter->dst_mac) &&
+	     is_valid_ether_addr(filter->src_mac)) ||
+	    (is_multicast_ether_addr(filter->dst_mac) &&
+	     is_multicast_ether_addr(filter->src_mac)))
+		return -EINVAL;
+
+	/* Make sure port is specified, otherwise bail out, for channel
+	 * specific cloud filter needs 'L4 port' to be non-zero
+	 */
+	if (!filter->dst_port)
+		return -EINVAL;
+
+	/* adding filter using src_port/src_ip is not supported at this stage */
+	if (filter->src_port || filter->src_ipv4 ||
+	    !ipv6_addr_any(&filter->ip.v6.src_ip6))
+		return -EINVAL;
+
+	/* copy element needed to add cloud filter from filter */
+	i40e_set_cld_element(filter, &cld_filter.element);
+
+	if (is_valid_ether_addr(filter->dst_mac) ||
+	    is_valid_ether_addr(filter->src_mac) ||
+	    is_multicast_ether_addr(filter->dst_mac) ||
+	    is_multicast_ether_addr(filter->src_mac)) {
+		/* MAC + IP : unsupported mode */
+		if (filter->dst_ipv4)
+			return -EINVAL;
+
+		/* since we validated that L4 port must be valid before
+		 * we get here, start with respective "flags" value
+		 * and update if vlan is present or not
+		 */
+		cld_filter.element.flags =
+			cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT);
+
+		if (filter->vlan_id) {
+			cld_filter.element.flags =
+			cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT);
+		}
+
+	} else if (filter->dst_ipv4 ||
+		   !ipv6_addr_any(&filter->ip.v6.dst_ip6)) {
+		cld_filter.element.flags =
+				cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_IP_PORT);
+		if (filter->n_proto == ETH_P_IPV6)
+			cld_filter.element.flags |=
+				cpu_to_le16(I40E_AQC_ADD_CLOUD_FLAGS_IPV6);
+		else
+			cld_filter.element.flags |=
+				cpu_to_le16(I40E_AQC_ADD_CLOUD_FLAGS_IPV4);
+	} else {
+		dev_err(&pf->pdev->dev,
+			"either mac or ip has to be valid for cloud filter\n");
+		return -EINVAL;
+	}
+
+	/* Now copy L4 port in Byte 6..7 in general fields */
+	cld_filter.general_fields[I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD0] =
+						be16_to_cpu(filter->dst_port);
+
+	if (add) {
+		/* Validate current device switch mode, change if necessary */
+		ret = i40e_validate_and_set_switch_mode(vsi);
+		if (ret) {
+			dev_err(&pf->pdev->dev,
+				"failed to set switch mode, ret %d\n",
+				ret);
+			return ret;
+		}
 
-	if (type != TC_SETUP_MQPRIO)
+		ret = i40e_aq_add_cloud_filters_bb(&pf->hw, filter->seid,
+						   &cld_filter, 1);
+	} else {
+		ret = i40e_aq_rem_cloud_filters_bb(&pf->hw, filter->seid,
+						   &cld_filter, 1);
+	}
+
+	if (ret)
+		dev_dbg(&pf->pdev->dev,
+			"Failed to %s cloud filter(big buffer) err %d aq_err %d\n",
+			add ? "add" : "delete", ret, pf->hw.aq.asq_last_status);
+	else
+		dev_info(&pf->pdev->dev,
+			 "%s cloud filter for VSI: %d, L4 port: %d\n",
+			 add ? "add" : "delete", filter->seid,
+			 ntohs(filter->dst_port));
+	return ret;
+}
+
+/**
+ * i40e_parse_cls_flower - Parse tc flower filters provided by kernel
+ * @vsi: Pointer to VSI
+ * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @filter: Pointer to cloud filter structure
+ *
+ **/
+static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
+				 struct tc_cls_flower_offload *f,
+				 struct i40e_cloud_filter *filter)
+{
+	u16 n_proto_mask = 0, n_proto_key = 0, addr_type = 0;
+	struct i40e_pf *pf = vsi->back;
+	u8 field_flags = 0;
+
+	if (f->dissector->used_keys &
+	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
+		dev_err(&pf->pdev->dev, "Unsupported key used: 0x%x\n",
+			f->dissector->used_keys);
 		return -EOPNOTSUPP;
+	}
+
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_dissector_key_keyid *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_KEYID,
+						  f->key);
+
+		struct flow_dissector_key_keyid *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_KEYID,
+						  f->mask);
+
+		if (mask->keyid != 0)
+			field_flags |= I40E_CLOUD_FIELD_TEN_ID;
+
+		filter->tenant_id = be32_to_cpu(key->keyid);
+	}
 
-	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_dissector_key_basic *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_BASIC,
+						  f->key);
 
-	return i40e_setup_tc(netdev, mqprio->num_tc);
+		struct flow_dissector_key_basic *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_BASIC,
+						  f->mask);
+
+		n_proto_key = ntohs(key->n_proto);
+		n_proto_mask = ntohs(mask->n_proto);
+
+		if (n_proto_key == ETH_P_ALL) {
+			n_proto_key = 0;
+			n_proto_mask = 0;
+		}
+		filter->n_proto = n_proto_key & n_proto_mask;
+		filter->ip_proto = key->ip_proto;
+	}
+
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_dissector_key_eth_addrs *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
+						  f->key);
+
+		struct flow_dissector_key_eth_addrs *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
+						  f->mask);
+
+		/* use is_broadcast and is_zero to check for all 0xf or 0 */
+		if (!is_zero_ether_addr(mask->dst)) {
+			if (is_broadcast_ether_addr(mask->dst)) {
+				field_flags |= I40E_CLOUD_FIELD_OMAC;
+			} else {
+				dev_err(&pf->pdev->dev, "Bad ether dest mask %pM\n",
+					mask->dst);
+				return I40E_ERR_CONFIG;
+			}
+		}
+
+		if (!is_zero_ether_addr(mask->src)) {
+			if (is_broadcast_ether_addr(mask->src)) {
+				field_flags |= I40E_CLOUD_FIELD_IMAC;
+			} else {
+				dev_err(&pf->pdev->dev, "Bad ether src mask %pM\n",
+					mask->src);
+				return I40E_ERR_CONFIG;
+			}
+		}
+		ether_addr_copy(filter->dst_mac, key->dst);
+		ether_addr_copy(filter->src_mac, key->src);
+	}
+
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_dissector_key_vlan *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_VLAN,
+						  f->key);
+		struct flow_dissector_key_vlan *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_VLAN,
+						  f->mask);
+
+		if (mask->vlan_id) {
+			if (mask->vlan_id == VLAN_VID_MASK) {
+				field_flags |= I40E_CLOUD_FIELD_IVLAN;
+
+			} else {
+				dev_err(&pf->pdev->dev, "Bad vlan mask 0x%04x\n",
+					mask->vlan_id);
+				return I40E_ERR_CONFIG;
+			}
+		}
+
+		filter->vlan_id = cpu_to_be16(key->vlan_id);
+	}
+
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_dissector_key_control *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_CONTROL,
+						  f->key);
+
+		addr_type = key->addr_type;
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		struct flow_dissector_key_ipv4_addrs *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+						  f->key);
+		struct flow_dissector_key_ipv4_addrs *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+						  f->mask);
+
+		if (mask->dst) {
+			if (mask->dst == cpu_to_be32(0xffffffff)) {
+				field_flags |= I40E_CLOUD_FIELD_IIP;
+			} else {
+				mask->dst = be32_to_cpu(mask->dst);
+				dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4\n",
+					&mask->dst);
+				return I40E_ERR_CONFIG;
+			}
+		}
+
+		if (mask->src) {
+			if (mask->src == cpu_to_be32(0xffffffff)) {
+				field_flags |= I40E_CLOUD_FIELD_IIP;
+			} else {
+				mask->src = be32_to_cpu(mask->src);
+				dev_err(&pf->pdev->dev, "Bad ip src mask %pI4\n",
+					&mask->src);
+				return I40E_ERR_CONFIG;
+			}
+		}
+
+		if (field_flags & I40E_CLOUD_FIELD_TEN_ID) {
+			dev_err(&pf->pdev->dev, "Tenant id not allowed for ip filter\n");
+			return I40E_ERR_CONFIG;
+		}
+		filter->dst_ipv4 = key->dst;
+		filter->src_ipv4 = key->src;
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+		struct flow_dissector_key_ipv6_addrs *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+						  f->key);
+		struct flow_dissector_key_ipv6_addrs *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+						  f->mask);
+
+		/* src and dest IPV6 address should not be LOOPBACK
+		 * (0:0:0:0:0:0:0:1), which can be represented as ::1
+		 */
+		if (ipv6_addr_loopback(&key->dst) ||
+		    ipv6_addr_loopback(&key->src)) {
+			dev_err(&pf->pdev->dev,
+				"Bad ipv6, addr is LOOPBACK\n");
+			return I40E_ERR_CONFIG;
+		}
+		if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src))
+			field_flags |= I40E_CLOUD_FIELD_IIP;
+
+		memcpy(&filter->src_ipv6, &key->src.s6_addr32,
+		       sizeof(filter->src_ipv6));
+		memcpy(&filter->dst_ipv6, &key->dst.s6_addr32,
+		       sizeof(filter->dst_ipv6));
+	}
+
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_dissector_key_ports *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_PORTS,
+						  f->key);
+		struct flow_dissector_key_ports *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_PORTS,
+						  f->mask);
+
+		if (mask->src) {
+			if (mask->src == cpu_to_be16(0xffff)) {
+				field_flags |= I40E_CLOUD_FIELD_IIP;
+			} else {
+				dev_err(&pf->pdev->dev, "Bad src port mask 0x%04x\n",
+					be16_to_cpu(mask->src));
+				return I40E_ERR_CONFIG;
+			}
+		}
+
+		if (mask->dst) {
+			if (mask->dst == cpu_to_be16(0xffff)) {
+				field_flags |= I40E_CLOUD_FIELD_IIP;
+			} else {
+				dev_err(&pf->pdev->dev, "Bad dst port mask 0x%04x\n",
+					be16_to_cpu(mask->dst));
+				return I40E_ERR_CONFIG;
+			}
+		}
+
+		filter->dst_port = key->dst;
+		filter->src_port = key->src;
+
+		switch (filter->ip_proto) {
+		case IPPROTO_TCP:
+		case IPPROTO_UDP:
+			break;
+		default:
+			dev_err(&pf->pdev->dev,
+				"Only UDP and TCP transport are supported\n");
+			return -EINVAL;
+		}
+	}
+	filter->flags = field_flags;
+	return 0;
+}
+
+/**
+ * i40e_handle_tclass: Forward to a traffic class on the device
+ * @vsi: Pointer to VSI
+ * @tc: traffic class index on the device
+ * @filter: Pointer to cloud filter structure
+ *
+ **/
+static int i40e_handle_tclass(struct i40e_vsi *vsi, u32 tc,
+			      struct i40e_cloud_filter *filter)
+{
+	struct i40e_channel *ch, *ch_tmp;
+
+	/* direct to a traffic class on the same device */
+	if (tc == 0) {
+		filter->seid = vsi->seid;
+		return 0;
+	} else if (vsi->tc_config.enabled_tc & BIT(tc)) {
+		if (!filter->dst_port) {
+			dev_err(&vsi->back->pdev->dev,
+				"Specify destination port to direct to traffic class that is not default\n");
+			return -EINVAL;
+		}
+		if (list_empty(&vsi->ch_list))
+			return -EINVAL;
+		list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list,
+					 list) {
+			if (ch->seid == vsi->tc_seid_map[tc])
+				filter->seid = ch->seid;
+		}
+		return 0;
+	}
+	dev_err(&vsi->back->pdev->dev, "TC is not enabled\n");
+	return -EINVAL;
+}
+
+/**
+ * i40e_configure_clsflower - Configure tc flower filters
+ * @vsi: Pointer to VSI
+ * @cls_flower: Pointer to struct tc_cls_flower_offload
+ *
+ **/
+static int i40e_configure_clsflower(struct i40e_vsi *vsi,
+				    struct tc_cls_flower_offload *cls_flower)
+{
+	int tc = tc_classid_to_hwtc(vsi->netdev, cls_flower->classid);
+	struct i40e_cloud_filter *filter = NULL;
+	struct i40e_pf *pf = vsi->back;
+	int err = 0;
+
+	if (tc < 0) {
+		dev_err(&vsi->back->pdev->dev, "Invalid traffic class\n");
+		return -EINVAL;
+	}
+
+	if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
+	    test_bit(__I40E_RESET_INTR_RECEIVED, pf->state))
+		return -EBUSY;
+
+	if (pf->fdir_pf_active_filters ||
+	    (!hlist_empty(&pf->fdir_filter_list))) {
+		dev_err(&vsi->back->pdev->dev,
+			"Flow Director Sideband filters exists, turn ntuple off to configure cloud filters\n");
+		return -EINVAL;
+	}
+
+	if (vsi->back->flags & I40E_FLAG_FD_SB_ENABLED) {
+		dev_err(&vsi->back->pdev->dev,
+			"Disable Flow Director Sideband, configuring Cloud filters via tc-flower\n");
+		vsi->back->flags &= ~I40E_FLAG_FD_SB_ENABLED;
+		vsi->back->flags |= I40E_FLAG_FD_SB_TO_CLOUD_FILTER;
+	}
+
+	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+	if (!filter)
+		return -ENOMEM;
+
+	filter->cookie = cls_flower->cookie;
+
+	err = i40e_parse_cls_flower(vsi, cls_flower, filter);
+	if (err < 0)
+		goto err;
+
+	err = i40e_handle_tclass(vsi, tc, filter);
+	if (err < 0)
+		goto err;
+
+	/* Add cloud filter */
+	if (filter->dst_port)
+		err = i40e_add_del_cloud_filter_big_buf(vsi, filter, true);
+	else
+		err = i40e_add_del_cloud_filter(vsi, filter, true);
+
+	if (err) {
+		dev_err(&pf->pdev->dev,
+			"Failed to add cloud filter, err %s\n",
+			i40e_stat_str(&pf->hw, err));
+		err = i40e_aq_rc_to_posix(err, pf->hw.aq.asq_last_status);
+		goto err;
+	}
+
+	/* add filter to the ordered list */
+	INIT_HLIST_NODE(&filter->cloud_node);
+
+	hlist_add_head(&filter->cloud_node, &pf->cloud_filter_list);
+
+	pf->num_cloud_filters++;
+
+	return err;
+err:
+	kfree(filter);
+	return err;
+}
+
+/**
+ * i40e_find_cloud_filter - Find the could filter in the list
+ * @vsi: Pointer to VSI
+ * @cookie: filter specific cookie
+ *
+ **/
+static struct i40e_cloud_filter *i40e_find_cloud_filter(struct i40e_vsi *vsi,
+							unsigned long *cookie)
+{
+	struct i40e_cloud_filter *filter = NULL;
+	struct hlist_node *node2;
+
+	hlist_for_each_entry_safe(filter, node2,
+				  &vsi->back->cloud_filter_list, cloud_node)
+		if (!memcmp(cookie, &filter->cookie, sizeof(filter->cookie)))
+			return filter;
+	return NULL;
+}
+
+/**
+ * i40e_delete_clsflower - Remove tc flower filters
+ * @vsi: Pointer to VSI
+ * @cls_flower: Pointer to struct tc_cls_flower_offload
+ *
+ **/
+static int i40e_delete_clsflower(struct i40e_vsi *vsi,
+				 struct tc_cls_flower_offload *cls_flower)
+{
+	struct i40e_cloud_filter *filter = NULL;
+	struct i40e_pf *pf = vsi->back;
+	int err = 0;
+
+	filter = i40e_find_cloud_filter(vsi, &cls_flower->cookie);
+
+	if (!filter)
+		return -EINVAL;
+
+	hash_del(&filter->cloud_node);
+
+	if (filter->dst_port)
+		err = i40e_add_del_cloud_filter_big_buf(vsi, filter, false);
+	else
+		err = i40e_add_del_cloud_filter(vsi, filter, false);
+
+	kfree(filter);
+	if (err) {
+		dev_err(&pf->pdev->dev,
+			"Failed to delete cloud filter, err %s\n",
+			i40e_stat_str(&pf->hw, err));
+		return i40e_aq_rc_to_posix(err, pf->hw.aq.asq_last_status);
+	}
+
+	pf->num_cloud_filters--;
+	if (!pf->num_cloud_filters)
+		if ((pf->flags & I40E_FLAG_FD_SB_TO_CLOUD_FILTER) &&
+		    !(pf->flags & I40E_FLAG_FD_SB_INACTIVE)) {
+			pf->flags |= I40E_FLAG_FD_SB_ENABLED;
+			pf->flags &= ~I40E_FLAG_FD_SB_TO_CLOUD_FILTER;
+			pf->flags &= ~I40E_FLAG_FD_SB_INACTIVE;
+		}
+	return 0;
+}
+
+/**
+ * i40e_setup_tc_cls_flower - flower classifier offloads
+ * @netdev: net device to configure
+ * @type_data: offload data
+ **/
+static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np,
+				    struct tc_cls_flower_offload *cls_flower)
+{
+	struct i40e_vsi *vsi = np->vsi;
+
+	if (cls_flower->common.chain_index)
+		return -EOPNOTSUPP;
+
+	switch (cls_flower->command) {
+	case TC_CLSFLOWER_REPLACE:
+		return i40e_configure_clsflower(vsi, cls_flower);
+	case TC_CLSFLOWER_DESTROY:
+		return i40e_delete_clsflower(vsi, cls_flower);
+	case TC_CLSFLOWER_STATS:
+		return -EOPNOTSUPP;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int i40e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				  void *cb_priv)
+{
+	struct i40e_netdev_priv *np = cb_priv;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return i40e_setup_tc_cls_flower(np, type_data);
+
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int i40e_setup_tc_block(struct net_device *dev,
+			       struct tc_block_offload *f)
+{
+	struct i40e_netdev_priv *np = netdev_priv(dev);
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block, i40e_setup_tc_block_cb,
+					     np, np);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, i40e_setup_tc_block_cb, np);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type,
+			   void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_MQPRIO:
+		return i40e_setup_tc(netdev, type_data);
+	case TC_SETUP_BLOCK:
+		return i40e_setup_tc_block(netdev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 /**
@@ -5747,7 +7674,7 @@ err_setup_rx:
 err_setup_tx:
 	i40e_vsi_free_tx_resources(vsi);
 	if (vsi == pf->vsi[pf->lan_vsi])
-		i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true);
+		i40e_do_reset(pf, I40E_PF_RESET_FLAG, true);
 
 	return err;
 }
@@ -5810,6 +7737,33 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf)
 }
 
 /**
+ * i40e_cloud_filter_exit - Cleans up the cloud filters
+ * @pf: Pointer to PF
+ *
+ * This function destroys the hlist where all the cloud filters
+ * were saved.
+ **/
+static void i40e_cloud_filter_exit(struct i40e_pf *pf)
+{
+	struct i40e_cloud_filter *cfilter;
+	struct hlist_node *node;
+
+	hlist_for_each_entry_safe(cfilter, node,
+				  &pf->cloud_filter_list, cloud_node) {
+		hlist_del(&cfilter->cloud_node);
+		kfree(cfilter);
+	}
+	pf->num_cloud_filters = 0;
+
+	if ((pf->flags & I40E_FLAG_FD_SB_TO_CLOUD_FILTER) &&
+	    !(pf->flags & I40E_FLAG_FD_SB_INACTIVE)) {
+		pf->flags |= I40E_FLAG_FD_SB_ENABLED;
+		pf->flags &= ~I40E_FLAG_FD_SB_TO_CLOUD_FILTER;
+		pf->flags &= ~I40E_FLAG_FD_SB_INACTIVE;
+	}
+}
+
+/**
  * i40e_close - Disables a network interface
  * @netdev: network interface device structure
  *
@@ -5875,7 +7829,7 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired)
 		wr32(&pf->hw, I40E_GLGEN_RTRIG, val);
 		i40e_flush(&pf->hw);
 
-	} else if (reset_flags & BIT_ULL(__I40E_PF_RESET_REQUESTED)) {
+	} else if (reset_flags & I40E_PF_RESET_FLAG) {
 
 		/* Request a PF Reset
 		 *
@@ -6226,6 +8180,7 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
 				hlist_del(&filter->fdir_node);
 				kfree(filter);
 				pf->fdir_pf_active_filters--;
+				pf->fd_inv = 0;
 			}
 		}
 	}
@@ -6429,8 +8384,7 @@ static void i40e_link_event(struct i40e_pf *pf)
 	     new_link == netif_carrier_ok(vsi->netdev)))
 		return;
 
-	if (!test_bit(__I40E_VSI_DOWN, vsi->state))
-		i40e_print_link_message(vsi, new_link);
+	i40e_print_link_message(vsi, new_link);
 
 	/* Notify the base of the switch tree connected to
 	 * the link.  Floating VEBs are not notified.
@@ -6553,12 +8507,26 @@ static void i40e_handle_link_event(struct i40e_pf *pf,
 	 */
 	i40e_link_event(pf);
 
-	/* check for unqualified module, if link is down */
-	if ((status->link_info & I40E_AQ_MEDIA_AVAILABLE) &&
-	    (!(status->an_info & I40E_AQ_QUALIFIED_MODULE)) &&
-	    (!(status->link_info & I40E_AQ_LINK_UP)))
+	/* Check if module meets thermal requirements */
+	if (status->phy_type == I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP) {
+		dev_err(&pf->pdev->dev,
+			"Rx/Tx is disabled on this device because the module does not meet thermal requirements.\n");
 		dev_err(&pf->pdev->dev,
-			"The driver failed to link because an unqualified module was detected.\n");
+			"Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n");
+	} else {
+		/* check for unqualified module, if link is down, suppress
+		 * the message if link was forced to be down.
+		 */
+		if ((status->link_info & I40E_AQ_MEDIA_AVAILABLE) &&
+		    (!(status->an_info & I40E_AQ_QUALIFIED_MODULE)) &&
+		    (!(status->link_info & I40E_AQ_LINK_UP)) &&
+		    (!(pf->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED))) {
+			dev_err(&pf->pdev->dev,
+				"Rx/Tx is disabled on this device because an unsupported SFP module type was detected.\n");
+			dev_err(&pf->pdev->dev,
+				"Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n");
+		}
+	}
 }
 
 /**
@@ -6900,7 +8868,8 @@ end_reconstitute:
  * i40e_get_capabilities - get info about the HW
  * @pf: the PF struct
  **/
-static int i40e_get_capabilities(struct i40e_pf *pf)
+static int i40e_get_capabilities(struct i40e_pf *pf,
+				 enum i40e_admin_queue_opc list_type)
 {
 	struct i40e_aqc_list_capabilities_element_resp *cap_buf;
 	u16 data_size;
@@ -6915,9 +8884,8 @@ static int i40e_get_capabilities(struct i40e_pf *pf)
 
 		/* this loads the data into the hw struct for us */
 		err = i40e_aq_discover_capabilities(&pf->hw, cap_buf, buf_len,
-					    &data_size,
-					    i40e_aqc_opc_list_func_capabilities,
-					    NULL);
+						    &data_size, list_type,
+						    NULL);
 		/* data loaded, buffer no longer needed */
 		kfree(cap_buf);
 
@@ -6934,26 +8902,44 @@ static int i40e_get_capabilities(struct i40e_pf *pf)
 		}
 	} while (err);
 
-	if (pf->hw.debug_mask & I40E_DEBUG_USER)
-		dev_info(&pf->pdev->dev,
-			 "pf=%d, num_vfs=%d, msix_pf=%d, msix_vf=%d, fd_g=%d, fd_b=%d, pf_max_q=%d num_vsi=%d\n",
-			 pf->hw.pf_id, pf->hw.func_caps.num_vfs,
-			 pf->hw.func_caps.num_msix_vectors,
-			 pf->hw.func_caps.num_msix_vectors_vf,
-			 pf->hw.func_caps.fd_filters_guaranteed,
-			 pf->hw.func_caps.fd_filters_best_effort,
-			 pf->hw.func_caps.num_tx_qp,
-			 pf->hw.func_caps.num_vsis);
-
+	if (pf->hw.debug_mask & I40E_DEBUG_USER) {
+		if (list_type == i40e_aqc_opc_list_func_capabilities) {
+			dev_info(&pf->pdev->dev,
+				 "pf=%d, num_vfs=%d, msix_pf=%d, msix_vf=%d, fd_g=%d, fd_b=%d, pf_max_q=%d num_vsi=%d\n",
+				 pf->hw.pf_id, pf->hw.func_caps.num_vfs,
+				 pf->hw.func_caps.num_msix_vectors,
+				 pf->hw.func_caps.num_msix_vectors_vf,
+				 pf->hw.func_caps.fd_filters_guaranteed,
+				 pf->hw.func_caps.fd_filters_best_effort,
+				 pf->hw.func_caps.num_tx_qp,
+				 pf->hw.func_caps.num_vsis);
+		} else if (list_type == i40e_aqc_opc_list_dev_capabilities) {
+			dev_info(&pf->pdev->dev,
+				 "switch_mode=0x%04x, function_valid=0x%08x\n",
+				 pf->hw.dev_caps.switch_mode,
+				 pf->hw.dev_caps.valid_functions);
+			dev_info(&pf->pdev->dev,
+				 "SR-IOV=%d, num_vfs for all function=%u\n",
+				 pf->hw.dev_caps.sr_iov_1_1,
+				 pf->hw.dev_caps.num_vfs);
+			dev_info(&pf->pdev->dev,
+				 "num_vsis=%u, num_rx:%u, num_tx=%u\n",
+				 pf->hw.dev_caps.num_vsis,
+				 pf->hw.dev_caps.num_rx_qp,
+				 pf->hw.dev_caps.num_tx_qp);
+		}
+	}
+	if (list_type == i40e_aqc_opc_list_func_capabilities) {
 #define DEF_NUM_VSI (1 + (pf->hw.func_caps.fcoe ? 1 : 0) \
 		       + pf->hw.func_caps.num_vfs)
-	if (pf->hw.revision_id == 0 && (DEF_NUM_VSI > pf->hw.func_caps.num_vsis)) {
-		dev_info(&pf->pdev->dev,
-			 "got num_vsis %d, setting num_vsis to %d\n",
-			 pf->hw.func_caps.num_vsis, DEF_NUM_VSI);
-		pf->hw.func_caps.num_vsis = DEF_NUM_VSI;
+		if (pf->hw.revision_id == 0 &&
+		    pf->hw.func_caps.num_vsis < DEF_NUM_VSI) {
+			dev_info(&pf->pdev->dev,
+				 "got num_vsis %d, setting num_vsis to %d\n",
+				 pf->hw.func_caps.num_vsis, DEF_NUM_VSI);
+			pf->hw.func_caps.num_vsis = DEF_NUM_VSI;
+		}
 	}
-
 	return 0;
 }
 
@@ -6995,6 +8981,7 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf)
 		if (!vsi) {
 			dev_info(&pf->pdev->dev, "Couldn't create FDir VSI\n");
 			pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
+			pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
 			return;
 		}
 	}
@@ -7017,6 +9004,95 @@ static void i40e_fdir_teardown(struct i40e_pf *pf)
 }
 
 /**
+ * i40e_rebuild_cloud_filters - Rebuilds cloud filters for VSIs
+ * @vsi: PF main vsi
+ * @seid: seid of main or channel VSIs
+ *
+ * Rebuilds cloud filters associated with main VSI and channel VSIs if they
+ * existed before reset
+ **/
+static int i40e_rebuild_cloud_filters(struct i40e_vsi *vsi, u16 seid)
+{
+	struct i40e_cloud_filter *cfilter;
+	struct i40e_pf *pf = vsi->back;
+	struct hlist_node *node;
+	i40e_status ret;
+
+	/* Add cloud filters back if they exist */
+	hlist_for_each_entry_safe(cfilter, node, &pf->cloud_filter_list,
+				  cloud_node) {
+		if (cfilter->seid != seid)
+			continue;
+
+		if (cfilter->dst_port)
+			ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter,
+								true);
+		else
+			ret = i40e_add_del_cloud_filter(vsi, cfilter, true);
+
+		if (ret) {
+			dev_dbg(&pf->pdev->dev,
+				"Failed to rebuild cloud filter, err %s aq_err %s\n",
+				i40e_stat_str(&pf->hw, ret),
+				i40e_aq_str(&pf->hw,
+					    pf->hw.aq.asq_last_status));
+			return ret;
+		}
+	}
+	return 0;
+}
+
+/**
+ * i40e_rebuild_channels - Rebuilds channel VSIs if they existed before reset
+ * @vsi: PF main vsi
+ *
+ * Rebuilds channel VSIs if they existed before reset
+ **/
+static int i40e_rebuild_channels(struct i40e_vsi *vsi)
+{
+	struct i40e_channel *ch, *ch_tmp;
+	i40e_status ret;
+
+	if (list_empty(&vsi->ch_list))
+		return 0;
+
+	list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) {
+		if (!ch->initialized)
+			break;
+		/* Proceed with creation of channel (VMDq2) VSI */
+		ret = i40e_add_channel(vsi->back, vsi->uplink_seid, ch);
+		if (ret) {
+			dev_info(&vsi->back->pdev->dev,
+				 "failed to rebuild channels using uplink_seid %u\n",
+				 vsi->uplink_seid);
+			return ret;
+		}
+		if (ch->max_tx_rate) {
+			u64 credits = ch->max_tx_rate;
+
+			if (i40e_set_bw_limit(vsi, ch->seid,
+					      ch->max_tx_rate))
+				return -EINVAL;
+
+			do_div(credits, I40E_BW_CREDIT_DIVISOR);
+			dev_dbg(&vsi->back->pdev->dev,
+				"Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n",
+				ch->max_tx_rate,
+				credits,
+				ch->seid);
+		}
+		ret = i40e_rebuild_cloud_filters(vsi, ch->seid);
+		if (ret) {
+			dev_dbg(&vsi->back->pdev->dev,
+				"Failed to rebuild cloud filters for channel VSI %u\n",
+				ch->seid);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+/**
  * i40e_prep_for_reset - prep for the core to reset
  * @pf: board private structure
  * @lock_acquired: indicates whether or not the lock has been acquired
@@ -7152,6 +9228,7 @@ static int i40e_reset(struct i40e_pf *pf)
  **/
 static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 {
+	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 	struct i40e_hw *hw = &pf->hw;
 	u8 set_fc_aq_fail = 0;
 	i40e_status ret;
@@ -7177,7 +9254,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 		i40e_verify_eeprom(pf);
 
 	i40e_clear_pxe_mode(hw);
-	ret = i40e_get_capabilities(pf);
+	ret = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities);
 	if (ret)
 		goto end_core_reset;
 
@@ -7234,7 +9311,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 	 * If there were VEBs but the reconstitution failed, we'll try
 	 * try to recover minimal use by getting the basic PF VSI working.
 	 */
-	if (pf->vsi[pf->lan_vsi]->uplink_seid != pf->mac_seid) {
+	if (vsi->uplink_seid != pf->mac_seid) {
 		dev_dbg(&pf->pdev->dev, "attempting to rebuild switch\n");
 		/* find the one VEB connected to the MAC, and find orphans */
 		for (v = 0; v < I40E_MAX_VEB; v++) {
@@ -7258,8 +9335,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 					dev_info(&pf->pdev->dev,
 						 "rebuild of switch failed: %d, will try to set up simple PF connection\n",
 						 ret);
-					pf->vsi[pf->lan_vsi]->uplink_seid
-								= pf->mac_seid;
+					vsi->uplink_seid = pf->mac_seid;
 					break;
 				} else if (pf->veb[v]->uplink_seid == 0) {
 					dev_info(&pf->pdev->dev,
@@ -7270,10 +9346,10 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 		}
 	}
 
-	if (pf->vsi[pf->lan_vsi]->uplink_seid == pf->mac_seid) {
+	if (vsi->uplink_seid == pf->mac_seid) {
 		dev_dbg(&pf->pdev->dev, "attempting to rebuild PF VSI\n");
 		/* no VEB, so rebuild only the Main VSI */
-		ret = i40e_add_vsi(pf->vsi[pf->lan_vsi]);
+		ret = i40e_add_vsi(vsi);
 		if (ret) {
 			dev_info(&pf->pdev->dev,
 				 "rebuild of Main VSI failed: %d\n", ret);
@@ -7281,6 +9357,35 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 		}
 	}
 
+	if (vsi->mqprio_qopt.max_rate[0]) {
+		u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0];
+		u64 credits = 0;
+
+		do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR);
+		ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate);
+		if (ret)
+			goto end_unlock;
+
+		credits = max_tx_rate;
+		do_div(credits, I40E_BW_CREDIT_DIVISOR);
+		dev_dbg(&vsi->back->pdev->dev,
+			"Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n",
+			max_tx_rate,
+			credits,
+			vsi->seid);
+	}
+
+	ret = i40e_rebuild_cloud_filters(vsi, vsi->seid);
+	if (ret)
+		goto end_unlock;
+
+	/* PF Main VSI is rebuild by now, go ahead and rebuild channel VSIs
+	 * for this main VSI if they exist
+	 */
+	ret = i40e_rebuild_channels(vsi);
+	if (ret)
+		goto end_unlock;
+
 	/* Reconfigure hardware for allowing smaller MSS in the case
 	 * of TSO, so that we avoid the MDD being fired and causing
 	 * a reset in the case of small MSS+TSO.
@@ -7615,9 +9720,9 @@ static void i40e_service_task(struct work_struct *work)
  * i40e_service_timer - timer callback
  * @data: pointer to PF struct
  **/
-static void i40e_service_timer(unsigned long data)
+static void i40e_service_timer(struct timer_list *t)
 {
-	struct i40e_pf *pf = (struct i40e_pf *)data;
+	struct i40e_pf *pf = from_timer(pf, t, service_timer);
 
 	mod_timer(&pf->service_timer,
 		  round_jiffies(jiffies + pf->service_timer_period));
@@ -7674,7 +9779,7 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi)
 
 /**
  * i40e_vsi_alloc_arrays - Allocate queue and vector pointer arrays for the vsi
- * @type: VSI pointer
+ * @vsi: VSI pointer
  * @alloc_qvectors: a bool to specify if q_vectors need to be allocated.
  *
  * On error: returns error code (negative)
@@ -8139,7 +10244,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		pf->num_lan_qps = 1;
 		pf->num_lan_msix = 1;
 
-	} else if (!vectors_left) {
+	} else if (v_actual != v_budget) {
 		/* If we have limited resources, we will start with no vectors
 		 * for the special features and then allocate vectors to some
 		 * of these features based on the policy and at the end disable
@@ -8148,7 +10253,8 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		int vec;
 
 		dev_info(&pf->pdev->dev,
-			 "MSI-X vector limit reached, attempting to redistribute vectors\n");
+			 "MSI-X vector limit reached with %d, wanted %d, attempting to redistribute vectors\n",
+			 v_actual, v_budget);
 		/* reserve the misc vector */
 		vec = v_actual - 1;
 
@@ -8196,6 +10302,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
 	    (pf->num_fdsb_msix == 0)) {
 		dev_info(&pf->pdev->dev, "Sideband Flowdir disabled, not enough MSI-X vectors\n");
 		pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
+		pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
 	}
 	if ((pf->flags & I40E_FLAG_VMDQ_ENABLED) &&
 	    (pf->num_vmdq_msix == 0)) {
@@ -8313,6 +10420,7 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf)
 				       I40E_FLAG_FD_SB_ENABLED	|
 				       I40E_FLAG_FD_ATR_ENABLED	|
 				       I40E_FLAG_VMDQ_ENABLED);
+			pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
 
 			/* rework the queue expectations without MSIX */
 			i40e_determine_queue_usage(pf);
@@ -8351,6 +10459,55 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf)
 }
 
 /**
+ * i40e_restore_interrupt_scheme - Restore the interrupt scheme
+ * @pf: private board data structure
+ *
+ * Restore the interrupt scheme that was cleared when we suspended the
+ * device. This should be called during resume to re-allocate the q_vectors
+ * and reacquire IRQs.
+ */
+static int i40e_restore_interrupt_scheme(struct i40e_pf *pf)
+{
+	int err, i;
+
+	/* We cleared the MSI and MSI-X flags when disabling the old interrupt
+	 * scheme. We need to re-enabled them here in order to attempt to
+	 * re-acquire the MSI or MSI-X vectors
+	 */
+	pf->flags |= (I40E_FLAG_MSIX_ENABLED | I40E_FLAG_MSI_ENABLED);
+
+	err = i40e_init_interrupt_scheme(pf);
+	if (err)
+		return err;
+
+	/* Now that we've re-acquired IRQs, we need to remap the vectors and
+	 * rings together again.
+	 */
+	for (i = 0; i < pf->num_alloc_vsi; i++) {
+		if (pf->vsi[i]) {
+			err = i40e_vsi_alloc_q_vectors(pf->vsi[i]);
+			if (err)
+				goto err_unwind;
+			i40e_vsi_map_rings_to_vectors(pf->vsi[i]);
+		}
+	}
+
+	err = i40e_setup_misc_vector(pf);
+	if (err)
+		goto err_unwind;
+
+	return 0;
+
+err_unwind:
+	while (i--) {
+		if (pf->vsi[i])
+			i40e_vsi_free_q_vectors(pf->vsi[i]);
+	}
+
+	return err;
+}
+
+/**
  * i40e_setup_misc_vector - Setup the misc vector to handle non queue events
  * @pf: board private structure
  *
@@ -8363,13 +10520,12 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf)
 	struct i40e_hw *hw = &pf->hw;
 	int err = 0;
 
-	/* Only request the irq if this is the first time through, and
-	 * not when we're rebuilding after a Reset
-	 */
-	if (!test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) {
+	/* Only request the IRQ once, the first time through. */
+	if (!test_and_set_bit(__I40E_MISC_IRQ_REQUESTED, pf->state)) {
 		err = request_irq(pf->msix_entries[0].vector,
 				  i40e_intr, 0, pf->int_name, pf);
 		if (err) {
+			clear_bit(__I40E_MISC_IRQ_REQUESTED, pf->state);
 			dev_info(&pf->pdev->dev,
 				 "request_irq for %s failed: %d\n",
 				 pf->int_name, err);
@@ -8385,51 +10541,12 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf)
 
 	i40e_flush(hw);
 
-	i40e_irq_dynamic_enable_icr0(pf, true);
+	i40e_irq_dynamic_enable_icr0(pf);
 
 	return err;
 }
 
 /**
- * i40e_config_rss_aq - Prepare for RSS using AQ commands
- * @vsi: vsi structure
- * @seed: RSS hash seed
- **/
-static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
-			      u8 *lut, u16 lut_size)
-{
-	struct i40e_pf *pf = vsi->back;
-	struct i40e_hw *hw = &pf->hw;
-	int ret = 0;
-
-	if (seed) {
-		struct i40e_aqc_get_set_rss_key_data *seed_dw =
-			(struct i40e_aqc_get_set_rss_key_data *)seed;
-		ret = i40e_aq_set_rss_key(hw, vsi->id, seed_dw);
-		if (ret) {
-			dev_info(&pf->pdev->dev,
-				 "Cannot set RSS key, err %s aq_err %s\n",
-				 i40e_stat_str(hw, ret),
-				 i40e_aq_str(hw, hw->aq.asq_last_status));
-			return ret;
-		}
-	}
-	if (lut) {
-		bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false;
-
-		ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size);
-		if (ret) {
-			dev_info(&pf->pdev->dev,
-				 "Cannot set RSS lut, err %s aq_err %s\n",
-				 i40e_stat_str(hw, ret),
-				 i40e_aq_str(hw, hw->aq.asq_last_status));
-			return ret;
-		}
-	}
-	return ret;
-}
-
-/**
  * i40e_get_rss_aq - Get RSS keys and lut by using AQ commands
  * @vsi: Pointer to vsi structure
  * @seed: Buffter to store the hash keys
@@ -8476,46 +10593,6 @@ static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
 }
 
 /**
- * i40e_vsi_config_rss - Prepare for VSI(VMDq) RSS if used
- * @vsi: VSI structure
- **/
-static int i40e_vsi_config_rss(struct i40e_vsi *vsi)
-{
-	u8 seed[I40E_HKEY_ARRAY_SIZE];
-	struct i40e_pf *pf = vsi->back;
-	u8 *lut;
-	int ret;
-
-	if (!(pf->hw_features & I40E_HW_RSS_AQ_CAPABLE))
-		return 0;
-
-	if (!vsi->rss_size)
-		vsi->rss_size = min_t(int, pf->alloc_rss_size,
-				      vsi->num_queue_pairs);
-	if (!vsi->rss_size)
-		return -EINVAL;
-
-	lut = kzalloc(vsi->rss_table_size, GFP_KERNEL);
-	if (!lut)
-		return -ENOMEM;
-	/* Use the user configured hash keys and lookup table if there is one,
-	 * otherwise use default
-	 */
-	if (vsi->rss_lut_user)
-		memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size);
-	else
-		i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, vsi->rss_size);
-	if (vsi->rss_hkey_user)
-		memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE);
-	else
-		netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE);
-	ret = i40e_config_rss_aq(vsi, seed, lut, vsi->rss_table_size);
-	kfree(lut);
-
-	return ret;
-}
-
-/**
  * i40e_config_rss_reg - Configure RSS keys and lut by writing registers
  * @vsi: Pointer to vsi structure
  * @seed: RSS hash seed
@@ -8913,8 +10990,8 @@ static int i40e_sw_init(struct i40e_pf *pf)
 		    I40E_FLAG_MSIX_ENABLED;
 
 	/* Set default ITR */
-	pf->rx_itr_default = I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF;
-	pf->tx_itr_default = I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF;
+	pf->rx_itr_default = I40E_ITR_RX_DEF;
+	pf->tx_itr_default = I40E_ITR_TX_DEF;
 
 	/* Depending on PF configurations, it is possible that the RSS
 	 * maximum might end up larger than the available queues
@@ -9014,6 +11091,11 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	    (pf->hw.aq.fw_maj_ver >= 5)))
 		pf->hw_features |= I40E_HW_USE_SET_LLDP_MIB;
 
+	/* Enable PTP L4 if FW > v6.0 */
+	if (pf->hw.mac.type == I40E_MAC_XL710 &&
+	    pf->hw.aq.fw_maj_ver >= 6)
+		pf->hw_features |= I40E_HW_PTP_L4_CAPABLE;
+
 	if (pf->hw.func_caps.vmdq) {
 		pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI;
 		pf->flags |= I40E_FLAG_VMDQ_ENABLED;
@@ -9079,9 +11161,13 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
 		/* Enable filters and mark for reset */
 		if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
 			need_reset = true;
-		/* enable FD_SB only if there is MSI-X vector */
-		if (pf->num_fdsb_msix > 0)
+		/* enable FD_SB only if there is MSI-X vector and no cloud
+		 * filters exist
+		 */
+		if (pf->num_fdsb_msix > 0 && !pf->num_cloud_filters) {
 			pf->flags |= I40E_FLAG_FD_SB_ENABLED;
+			pf->flags &= ~I40E_FLAG_FD_SB_INACTIVE;
+		}
 	} else {
 		/* turn off filters, mark for reset and clear SW filter list */
 		if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
@@ -9090,6 +11176,8 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
 		}
 		pf->flags &= ~(I40E_FLAG_FD_SB_ENABLED |
 			       I40E_FLAG_FD_SB_AUTO_DISABLED);
+		pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
+
 		/* reset fd counters */
 		pf->fd_add_err = 0;
 		pf->fd_atr_cnt = 0;
@@ -9151,10 +11239,16 @@ static int i40e_set_features(struct net_device *netdev,
 	else
 		i40e_vlan_stripping_disable(vsi);
 
+	if (!(features & NETIF_F_HW_TC) && pf->num_cloud_filters) {
+		dev_err(&pf->pdev->dev,
+			"Offloaded tc filters active, can't turn hw_tc_offload off");
+		return -EINVAL;
+	}
+
 	need_reset = i40e_set_ntuple(pf, features);
 
 	if (need_reset)
-		i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true);
+		i40e_do_reset(pf, I40E_PF_RESET_FLAG, true);
 
 	return 0;
 }
@@ -9406,8 +11500,7 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev,
 				pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
 			else
 				pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
-			i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED),
-				      true);
+			i40e_do_reset(pf, I40E_PF_RESET_FLAG, true);
 			break;
 		}
 	}
@@ -9671,7 +11764,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID;
 
 	if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
-		netdev->hw_features |= NETIF_F_NTUPLE;
+		netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC;
+
 	hw_features = hw_enc_features		|
 		      NETIF_F_HW_VLAN_CTAG_TX	|
 		      NETIF_F_HW_VLAN_CTAG_RX;
@@ -9849,6 +11943,31 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 
 		enabled_tc = i40e_pf_get_tc_map(pf);
 
+		/* Source pruning is enabled by default, so the flag is
+		 * negative logic - if it's set, we need to fiddle with
+		 * the VSI to disable source pruning.
+		 */
+		if (pf->flags & I40E_FLAG_SOURCE_PRUNING_DISABLED) {
+			memset(&ctxt, 0, sizeof(ctxt));
+			ctxt.seid = pf->main_vsi_seid;
+			ctxt.pf_num = pf->hw.pf_id;
+			ctxt.vf_num = 0;
+			ctxt.info.valid_sections |=
+				     cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID);
+			ctxt.info.switch_id =
+				   cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB);
+			ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL);
+			if (ret) {
+				dev_info(&pf->pdev->dev,
+					 "update vsi failed, err %s aq_err %s\n",
+					 i40e_stat_str(&pf->hw, ret),
+					 i40e_aq_str(&pf->hw,
+						     pf->hw.aq.asq_last_status));
+				ret = -ENOENT;
+				goto err;
+			}
+		}
+
 		/* MFP mode setup queue map and update VSI */
 		if ((pf->flags & I40E_FLAG_MFP_ENABLED) &&
 		    !(pf->hw.func_caps.iscsi)) { /* NIC type PF */
@@ -10951,14 +13070,16 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
 	*/
 
 	if ((pf->hw.pf_id == 0) &&
-	    !(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT))
+	    !(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) {
 		flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
+		pf->last_sw_conf_flags = flags;
+	}
 
 	if (pf->hw.pf_id == 0) {
 		u16 valid_flags;
 
 		valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
-		ret = i40e_aq_set_switch_config(&pf->hw, flags, valid_flags,
+		ret = i40e_aq_set_switch_config(&pf->hw, flags, valid_flags, 0,
 						NULL);
 		if (ret && pf->hw.aq.asq_last_status != I40E_AQ_RC_ESRCH) {
 			dev_info(&pf->pdev->dev,
@@ -10968,6 +13089,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
 					     pf->hw.aq.asq_last_status));
 			/* not a fatal problem, just keep going */
 		}
+		pf->last_sw_conf_valid_flags = valid_flags;
 	}
 
 	/* first time setup */
@@ -10988,6 +13110,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
 			vsi = i40e_vsi_reinit_setup(pf->vsi[pf->lan_vsi]);
 		if (!vsi) {
 			dev_info(&pf->pdev->dev, "setup of MAIN VSI failed\n");
+			i40e_cloud_filter_exit(pf);
 			i40e_fdir_teardown(pf);
 			return -EAGAIN;
 		}
@@ -11039,6 +13162,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
 static void i40e_determine_queue_usage(struct i40e_pf *pf)
 {
 	int queues_left;
+	int q_max;
 
 	pf->num_lan_qps = 0;
 
@@ -11063,6 +13187,7 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 			       I40E_FLAG_DCB_ENABLED	|
 			       I40E_FLAG_SRIOV_ENABLED	|
 			       I40E_FLAG_VMDQ_ENABLED);
+		pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
 	} else if (!(pf->flags & (I40E_FLAG_RSS_ENABLED |
 				  I40E_FLAG_FD_SB_ENABLED |
 				  I40E_FLAG_FD_ATR_ENABLED |
@@ -11077,6 +13202,7 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 			       I40E_FLAG_FD_ATR_ENABLED	|
 			       I40E_FLAG_DCB_ENABLED	|
 			       I40E_FLAG_VMDQ_ENABLED);
+		pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
 	} else {
 		/* Not enough queues for all TCs */
 		if ((pf->flags & I40E_FLAG_DCB_CAPABLE) &&
@@ -11085,10 +13211,12 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 					I40E_FLAG_DCB_ENABLED);
 			dev_info(&pf->pdev->dev, "not enough queues for DCB. DCB is disabled.\n");
 		}
-		pf->num_lan_qps = max_t(int, pf->rss_size_max,
-					num_online_cpus());
-		pf->num_lan_qps = min_t(int, pf->num_lan_qps,
-					pf->hw.func_caps.num_tx_qp);
+
+		/* limit lan qps to the smaller of qps, cpus or msix */
+		q_max = max_t(int, pf->rss_size_max, num_online_cpus());
+		q_max = min_t(int, q_max, pf->hw.func_caps.num_tx_qp);
+		q_max = min_t(int, q_max, pf->hw.func_caps.num_msix_vectors);
+		pf->num_lan_qps = q_max;
 
 		queues_left -= pf->num_lan_qps;
 	}
@@ -11098,6 +13226,7 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 			queues_left -= 1; /* save 1 queue for FD */
 		} else {
 			pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
+			pf->flags |= I40E_FLAG_FD_SB_INACTIVE;
 			dev_info(&pf->pdev->dev, "not enough queues for Flow Director. Flow Director feature is disabled\n");
 		}
 	}
@@ -11304,6 +13433,13 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hw->bus.bus_id = pdev->bus->number;
 	pf->instance = pfs_found;
 
+	/* Select something other than the 802.1ad ethertype for the
+	 * switch to use internally and drop on ingress.
+	 */
+	hw->switch_tag = 0xffff;
+	hw->first_tag = ETH_P_8021AD;
+	hw->second_tag = ETH_P_8021Q;
+
 	INIT_LIST_HEAD(&pf->l3_flex_pit_list);
 	INIT_LIST_HEAD(&pf->l4_flex_pit_list);
 
@@ -11380,11 +13516,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		 i40e_nvm_version_str(hw));
 
 	if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
-	    hw->aq.api_min_ver > I40E_FW_API_VERSION_MINOR)
+	    hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw))
 		dev_info(&pdev->dev,
 			 "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n");
-	else if (hw->aq.api_maj_ver < I40E_FW_API_VERSION_MAJOR ||
-		 hw->aq.api_min_ver < (I40E_FW_API_VERSION_MINOR - 1))
+	else if (hw->aq.api_maj_ver == 1 && hw->aq.api_min_ver < 4)
 		dev_info(&pdev->dev,
 			 "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n");
 
@@ -11395,7 +13530,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_warn(&pdev->dev, "This device is a pre-production adapter/LOM. Please be aware there may be issues with your hardware. If you are experiencing problems please contact your Intel or hardware representative who provided you with this hardware.\n");
 
 	i40e_clear_pxe_mode(hw);
-	err = i40e_get_capabilities(pf);
+	err = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities);
 	if (err)
 		goto err_adminq_setup;
 
@@ -11454,7 +13589,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 #endif /* CONFIG_I40E_DCB */
 
 	/* set up periodic task facility */
-	setup_timer(&pf->service_timer, i40e_service_timer, (unsigned long)pf);
+	timer_setup(&pf->service_timer, i40e_service_timer, 0);
 	pf->service_timer_period = HZ;
 
 	INIT_WORK(&pf->service_task, i40e_service_task);
@@ -11506,6 +13641,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err);
 		goto err_vsis;
 	}
+	INIT_LIST_HEAD(&pf->vsi[pf->lan_vsi]->ch_list);
 
 	/* Make sure flow control is set according to current settings */
 	err = i40e_set_fc(hw, &set_fc_aq_fail, true);
@@ -11777,7 +13913,7 @@ static void i40e_remove(struct pci_dev *pdev)
 	/* no more scheduling of any task */
 	set_bit(__I40E_SUSPENDED, pf->state);
 	set_bit(__I40E_DOWN, pf->state);
-	if (pf->service_timer.data)
+	if (pf->service_timer.function)
 		del_timer_sync(&pf->service_timer);
 	if (pf->service_task.func)
 		cancel_work_sync(&pf->service_task);
@@ -11812,6 +13948,8 @@ static void i40e_remove(struct pci_dev *pdev)
 	if (pf->vsi[pf->lan_vsi])
 		i40e_vsi_release(pf->vsi[pf->lan_vsi]);
 
+	i40e_cloud_filter_exit(pf);
+
 	/* remove attached clients */
 	if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
 		ret_code = i40e_lan_del_device(pf);
@@ -11937,6 +14075,28 @@ static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev)
 }
 
 /**
+ * i40e_pci_error_reset_prepare - prepare device driver for pci reset
+ * @pdev: PCI device information struct
+ */
+static void i40e_pci_error_reset_prepare(struct pci_dev *pdev)
+{
+	struct i40e_pf *pf = pci_get_drvdata(pdev);
+
+	i40e_prep_for_reset(pf, false);
+}
+
+/**
+ * i40e_pci_error_reset_done - pci reset done, device driver reset can begin
+ * @pdev: PCI device information struct
+ */
+static void i40e_pci_error_reset_done(struct pci_dev *pdev)
+{
+	struct i40e_pf *pf = pci_get_drvdata(pdev);
+
+	i40e_reset_and_rebuild(pf, false, false);
+}
+
+/**
  * i40e_pci_error_resume - restart operations after PCI error recovery
  * @pdev: PCI device information struct
  *
@@ -12021,6 +14181,7 @@ static void i40e_shutdown(struct pci_dev *pdev)
 
 	del_timer_sync(&pf->service_timer);
 	cancel_work_sync(&pf->service_task);
+	i40e_cloud_filter_exit(pf);
 	i40e_fdir_teardown(pf);
 
 	/* Client close must be called explicitly here because the timer
@@ -12046,20 +14207,26 @@ static void i40e_shutdown(struct pci_dev *pdev)
 	}
 }
 
-#ifdef CONFIG_PM
 /**
- * i40e_suspend - PCI callback for moving to D3
- * @pdev: PCI device information struct
+ * i40e_suspend - PM callback for moving to D3
+ * @dev: generic device information structure
  **/
-static int i40e_suspend(struct pci_dev *pdev, pm_message_t state)
+static int __maybe_unused i40e_suspend(struct device *dev)
 {
+	struct pci_dev *pdev = to_pci_dev(dev);
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
 	struct i40e_hw *hw = &pf->hw;
-	int retval = 0;
 
-	set_bit(__I40E_SUSPENDED, pf->state);
+	/* If we're already suspended, then there is nothing to do */
+	if (test_and_set_bit(__I40E_SUSPENDED, pf->state))
+		return 0;
+
 	set_bit(__I40E_DOWN, pf->state);
 
+	/* Ensure service task will not be running */
+	del_timer_sync(&pf->service_timer);
+	cancel_work_sync(&pf->service_task);
+
 	if (pf->wol_en && (pf->hw_features & I40E_HW_WOL_MC_MAGIC_PKT_WAKE))
 		i40e_enable_mc_magic_wake(pf);
 
@@ -12068,81 +14235,70 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state)
 	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
 	wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
 
-	i40e_stop_misc_vector(pf);
-	if (pf->msix_entries) {
-		synchronize_irq(pf->msix_entries[0].vector);
-		free_irq(pf->msix_entries[0].vector, pf);
-	}
-	retval = pci_save_state(pdev);
-	if (retval)
-		return retval;
-
-	pci_wake_from_d3(pdev, pf->wol_en);
-	pci_set_power_state(pdev, PCI_D3hot);
+	/* Clear the interrupt scheme and release our IRQs so that the system
+	 * can safely hibernate even when there are a large number of CPUs.
+	 * Otherwise hibernation might fail when mapping all the vectors back
+	 * to CPU0.
+	 */
+	i40e_clear_interrupt_scheme(pf);
 
-	return retval;
+	return 0;
 }
 
 /**
- * i40e_resume - PCI callback for waking up from D3
- * @pdev: PCI device information struct
+ * i40e_resume - PM callback for waking up from D3
+ * @dev: generic device information structure
  **/
-static int i40e_resume(struct pci_dev *pdev)
+static int __maybe_unused i40e_resume(struct device *dev)
 {
+	struct pci_dev *pdev = to_pci_dev(dev);
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
-	u32 err;
+	int err;
 
-	pci_set_power_state(pdev, PCI_D0);
-	pci_restore_state(pdev);
-	/* pci_restore_state() clears dev->state_saves, so
-	 * call pci_save_state() again to restore it.
-	 */
-	pci_save_state(pdev);
+	/* If we're not suspended, then there is nothing to do */
+	if (!test_bit(__I40E_SUSPENDED, pf->state))
+		return 0;
 
-	err = pci_enable_device_mem(pdev);
+	/* We cleared the interrupt scheme when we suspended, so we need to
+	 * restore it now to resume device functionality.
+	 */
+	err = i40e_restore_interrupt_scheme(pf);
 	if (err) {
-		dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n");
-		return err;
+		dev_err(&pdev->dev, "Cannot restore interrupt scheme: %d\n",
+			err);
 	}
-	pci_set_master(pdev);
 
-	/* no wakeup events while running */
-	pci_wake_from_d3(pdev, false);
-
-	/* handling the reset will rebuild the device state */
-	if (test_and_clear_bit(__I40E_SUSPENDED, pf->state)) {
-		clear_bit(__I40E_DOWN, pf->state);
-		if (pf->msix_entries) {
-			err = request_irq(pf->msix_entries[0].vector,
-					  i40e_intr, 0, pf->int_name, pf);
-			if (err) {
-				dev_err(&pf->pdev->dev,
-					"request_irq for %s failed: %d\n",
-					pf->int_name, err);
-			}
-		}
-		i40e_reset_and_rebuild(pf, false, false);
-	}
+	clear_bit(__I40E_DOWN, pf->state);
+	i40e_reset_and_rebuild(pf, false, false);
+
+	/* Clear suspended state last after everything is recovered */
+	clear_bit(__I40E_SUSPENDED, pf->state);
+
+	/* Restart the service task */
+	mod_timer(&pf->service_timer,
+		  round_jiffies(jiffies + pf->service_timer_period));
 
 	return 0;
 }
 
-#endif
 static const struct pci_error_handlers i40e_err_handler = {
 	.error_detected = i40e_pci_error_detected,
 	.slot_reset = i40e_pci_error_slot_reset,
+	.reset_prepare = i40e_pci_error_reset_prepare,
+	.reset_done = i40e_pci_error_reset_done,
 	.resume = i40e_pci_error_resume,
 };
 
+static SIMPLE_DEV_PM_OPS(i40e_pm_ops, i40e_suspend, i40e_resume);
+
 static struct pci_driver i40e_driver = {
 	.name     = i40e_driver_name,
 	.id_table = i40e_pci_tbl,
 	.probe    = i40e_probe,
 	.remove   = i40e_remove,
-#ifdef CONFIG_PM
-	.suspend  = i40e_suspend,
-	.resume   = i40e_resume,
-#endif
+	.driver   = {
+		.pm = &i40e_pm_ops,
+	},
 	.shutdown = i40e_shutdown,
 	.err_handler = &i40e_err_handler,
 	.sriov_configure = i40e_pci_sriov_configure,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index d591b3e6bd7c..0ccab0a5d717 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -311,13 +311,10 @@ static i40e_status i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset,
 static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw,
 					u16 offset, u16 *data)
 {
-	i40e_status ret_code = 0;
-
 	if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE)
-		ret_code = i40e_read_nvm_word_aq(hw, offset, data);
-	else
-		ret_code = i40e_read_nvm_word_srctl(hw, offset, data);
-	return ret_code;
+		return i40e_read_nvm_word_aq(hw, offset, data);
+
+	return i40e_read_nvm_word_srctl(hw, offset, data);
 }
 
 /**
@@ -331,7 +328,7 @@ static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw,
 i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
 			       u16 *data)
 {
-	i40e_status ret_code = 0;
+	i40e_status ret_code;
 
 	ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
 	if (ret_code)
@@ -446,13 +443,10 @@ static i40e_status __i40e_read_nvm_buffer(struct i40e_hw *hw,
 					  u16 offset, u16 *words,
 					  u16 *data)
 {
-	i40e_status ret_code = 0;
-
 	if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE)
-		ret_code = i40e_read_nvm_buffer_aq(hw, offset, words, data);
-	else
-		ret_code = i40e_read_nvm_buffer_srctl(hw, offset, words, data);
-	return ret_code;
+		return i40e_read_nvm_buffer_aq(hw, offset, words, data);
+
+	return i40e_read_nvm_buffer_srctl(hw, offset, words, data);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index a39b13197891..3bb6659db822 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -190,7 +190,7 @@ i40e_status i40e_aq_get_switch_config(struct i40e_hw *hw,
 				struct i40e_asq_cmd_details *cmd_details);
 enum i40e_status_code i40e_aq_set_switch_config(struct i40e_hw *hw,
 						u16 flags,
-						u16 valid_flags,
+						u16 valid_flags, u8 mode,
 				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_request_resource(struct i40e_hw *hw,
 				enum i40e_aq_resources_ids resource,
@@ -283,6 +283,22 @@ i40e_status i40e_aq_query_switch_comp_bw_config(struct i40e_hw *hw,
 		struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_resume_port_tx(struct i40e_hw *hw,
 				   struct i40e_asq_cmd_details *cmd_details);
+i40e_status
+i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
+			     struct i40e_aqc_cloud_filters_element_bb *filters,
+			     u8 filter_count);
+enum i40e_status_code
+i40e_aq_add_cloud_filters(struct i40e_hw *hw, u16 vsi,
+			  struct i40e_aqc_cloud_filters_element_data *filters,
+			  u8 filter_count);
+enum i40e_status_code
+i40e_aq_rem_cloud_filters(struct i40e_hw *hw, u16 vsi,
+			  struct i40e_aqc_cloud_filters_element_data *filters,
+			  u8 filter_count);
+i40e_status
+i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
+			     struct i40e_aqc_cloud_filters_element_bb *filters,
+			     u8 filter_count);
 i40e_status i40e_read_lldp_cfg(struct i40e_hw *hw,
 			       struct i40e_lldp_variables *lldp_cfg);
 /* i40e_common */
@@ -360,6 +376,15 @@ i40e_status i40e_aq_rx_ctl_write_register(struct i40e_hw *hw,
 				u32 reg_addr, u32 reg_val,
 				struct i40e_asq_cmd_details *cmd_details);
 void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val);
+i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw,
+				     u8 phy_select, u8 dev_addr,
+				     u32 reg_addr, u32 reg_val,
+				     struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw,
+				     u8 phy_select, u8 dev_addr,
+				     u32 reg_addr, u32 *reg_val,
+				     struct i40e_asq_cmd_details *cmd_details);
+
 i40e_status i40e_read_phy_register_clause22(struct i40e_hw *hw,
 					    u16 reg, u8 phy_addr, u16 *value);
 i40e_status i40e_write_phy_register_clause22(struct i40e_hw *hw,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index 86ca27f72f02..c234758dad15 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -2794,7 +2794,7 @@
 #define I40E_GLV_RUPP_MAX_INDEX 383
 #define I40E_GLV_RUPP_RUPP_SHIFT 0
 #define I40E_GLV_RUPP_RUPP_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_RUPP_RUPP_SHIFT)
-#define I40E_GLV_TEPC(_VSI) (0x00344000 + ((_VSI) * 4)) /* _i=0...383 */ /* Reset: CORER */
+#define I40E_GLV_TEPC(_i) (0x00344000 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
 #define I40E_GLV_TEPC_MAX_INDEX 383
 #define I40E_GLV_TEPC_TEPC_SHIFT 0
 #define I40E_GLV_TEPC_TEPC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_TEPC_TEPC_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 120c68f78951..d6d352a6e6ea 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -960,14 +960,14 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 {
 	enum i40e_latency_range new_latency_range = rc->latency_range;
 	u32 new_itr = rc->itr;
-	int bytes_per_int;
+	int bytes_per_usec;
 	unsigned int usecs, estimated_usecs;
 
 	if (rc->total_packets == 0 || !rc->itr)
 		return false;
 
 	usecs = (rc->itr << 1) * ITR_COUNTDOWN_START;
-	bytes_per_int = rc->total_bytes / usecs;
+	bytes_per_usec = rc->total_bytes / usecs;
 
 	/* The calculations in this algorithm depend on interrupts actually
 	 * firing at the ITR rate. This may not happen if the packet rate is
@@ -993,18 +993,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 	 */
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
-		if (bytes_per_int > 10)
+		if (bytes_per_usec > 10)
 			new_latency_range = I40E_LOW_LATENCY;
 		break;
 	case I40E_LOW_LATENCY:
-		if (bytes_per_int > 20)
+		if (bytes_per_usec > 20)
 			new_latency_range = I40E_BULK_LATENCY;
-		else if (bytes_per_int <= 10)
+		else if (bytes_per_usec <= 10)
 			new_latency_range = I40E_LOWEST_LATENCY;
 		break;
 	case I40E_BULK_LATENCY:
 	default:
-		if (bytes_per_int <= 20)
+		if (bytes_per_usec <= 20)
 			new_latency_range = I40E_LOW_LATENCY;
 		break;
 	}
@@ -2117,6 +2117,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		if (!skb) {
 			xdp.data = page_address(rx_buffer->page) +
 				   rx_buffer->page_offset;
+			xdp_set_data_meta_invalid(&xdp);
 			xdp.data_hard_start = xdp.data -
 					      i40e_rx_offset(rx_ring);
 			xdp.data_end = xdp.data + size;
@@ -2211,9 +2212,7 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr)
 	u32 val;
 
 	val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
-	      /* Don't clear PBA because that can cause lost interrupts that
-	       * came in while we were cleaning/polling
-	       */
+	      I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
 	      (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) |
 	      (itr << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT);
 
@@ -2250,7 +2249,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 
 	/* If we don't have MSIX, then we only need to re-enable icr0 */
 	if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) {
-		i40e_irq_dynamic_enable_icr0(vsi->back, false);
+		i40e_irq_dynamic_enable_icr0(vsi->back);
 		return;
 	}
 
@@ -3176,38 +3175,12 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	/* write last descriptor with EOP bit */
 	td_cmd |= I40E_TX_DESC_CMD_EOP;
 
-	/* We can OR these values together as they both are checked against
-	 * 4 below and at this point desc_count will be used as a boolean value
-	 * after this if/else block.
+	/* We OR these values together to check both against 4 (WB_STRIDE)
+	 * below. This is safe since we don't re-use desc_count afterwards.
 	 */
 	desc_count |= ++tx_ring->packet_stride;
 
-	/* Algorithm to optimize tail and RS bit setting:
-	 * if queue is stopped
-	 *	mark RS bit
-	 *	reset packet counter
-	 * else if xmit_more is supported and is true
-	 *	advance packet counter to 4
-	 *	reset desc_count to 0
-	 *
-	 * if desc_count >= 4
-	 *	mark RS bit
-	 *	reset packet counter
-	 * if desc_count > 0
-	 *	update tail
-	 *
-	 * Note: If there are less than 4 descriptors
-	 * pending and interrupts were disabled the service task will
-	 * trigger a force WB.
-	 */
-	if (netif_xmit_stopped(txring_txq(tx_ring))) {
-		goto do_rs;
-	} else if (skb->xmit_more) {
-		/* set stride to arm on next packet and reset desc_count */
-		tx_ring->packet_stride = WB_STRIDE;
-		desc_count = 0;
-	} else if (desc_count >= WB_STRIDE) {
-do_rs:
+	if (desc_count >= WB_STRIDE) {
 		/* write last descriptor with RS bit set */
 		td_cmd |= I40E_TX_DESC_CMD_RS;
 		tx_ring->packet_stride = 0;
@@ -3228,7 +3201,7 @@ do_rs:
 	first->next_to_watch = tx_desc;
 
 	/* notify HW of packet */
-	if (desc_count) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 2f848bc5e391..fbae1182e2ea 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -38,8 +38,10 @@
 #define I40E_ITR_8K                0x003E
 #define I40E_ITR_4K                0x007A
 #define I40E_MAX_INTRL             0x3B    /* reg uses 4 usec resolution */
-#define I40E_ITR_RX_DEF            I40E_ITR_20K
-#define I40E_ITR_TX_DEF            I40E_ITR_20K
+#define I40E_ITR_RX_DEF            (ITR_REG_TO_USEC(I40E_ITR_20K) | \
+				    I40E_ITR_DYNAMIC)
+#define I40E_ITR_TX_DEF            (ITR_REG_TO_USEC(I40E_ITR_20K) | \
+				    I40E_ITR_DYNAMIC)
 #define I40E_ITR_DYNAMIC           0x8000  /* use top bit as a flag */
 #define I40E_MIN_INT_RATE          250     /* ~= 1000000 / (I40E_MAX_ITR * 2) */
 #define I40E_MAX_INT_RATE          500000  /* == 1000000 / (I40E_MIN_ITR * 2) */
@@ -206,7 +208,7 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc,
 }
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
-#define I40E_RX_BUFFER_WRITE	16	/* Must be power of 2 */
+#define I40E_RX_BUFFER_WRITE	32	/* Must be power of 2 */
 #define I40E_RX_INCREMENT(r, i) \
 	do {					\
 		(i)++;				\
@@ -342,6 +344,7 @@ struct i40e_rx_queue_stats {
 enum i40e_ring_state_t {
 	__I40E_TX_FDIR_INIT_DONE,
 	__I40E_TX_XPS_INIT_DONE,
+	__I40E_RING_STATE_NBITS /* must be last */
 };
 
 /* some useful defines for virtchannel interface, which
@@ -366,7 +369,7 @@ struct i40e_ring {
 		struct i40e_tx_buffer *tx_bi;
 		struct i40e_rx_buffer *rx_bi;
 	};
-	unsigned long state;
+	DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS);
 	u16 queue_index;		/* Queue number of ring */
 	u8 dcb_tc;			/* Traffic class of ring */
 	u8 __iomem *tail;
@@ -423,6 +426,8 @@ struct i40e_ring {
 					 * i40e_clean_rx_ring_irq() is called
 					 * for this ring.
 					 */
+
+	struct i40e_channel *ch;
 } ____cacheline_internodealigned_in_smp;
 
 static inline bool ring_uses_build_skb(struct i40e_ring *ring)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index fd4bbdd88b57..00d4833e9925 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -46,6 +46,9 @@
 /* Max default timeout in ms, */
 #define I40E_MAX_NVM_TIMEOUT		18000
 
+/* Max timeout in ms for the phy to respond */
+#define I40E_MAX_PHY_TIMEOUT		500
+
 /* Switch from ms to the 1usec global time (this is the GTIME resolution) */
 #define I40E_MS_TO_GTIME(time)		((time) * 1000)
 
@@ -268,6 +271,10 @@ struct i40e_phy_info {
 					     I40E_PHY_TYPE_OFFSET)
 #define I40E_CAP_PHY_TYPE_25GBASE_LR BIT_ULL(I40E_PHY_TYPE_25GBASE_LR + \
 					     I40E_PHY_TYPE_OFFSET)
+#define I40E_CAP_PHY_TYPE_25GBASE_AOC BIT_ULL(I40E_PHY_TYPE_25GBASE_AOC + \
+					     I40E_PHY_TYPE_OFFSET)
+#define I40E_CAP_PHY_TYPE_25GBASE_ACC BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC + \
+					     I40E_PHY_TYPE_OFFSET)
 #define I40E_HW_CAP_MAX_GPIO			30
 /* Capabilities of a PF or a VF or the whole device */
 struct i40e_hw_capabilities {
@@ -276,6 +283,16 @@ struct i40e_hw_capabilities {
 #define I40E_NVM_IMAGE_TYPE_CLOUD	0x2
 #define I40E_NVM_IMAGE_TYPE_UDP_CLOUD	0x3
 
+	/* Cloud filter modes:
+	 * Mode1: Filter on L4 port only
+	 * Mode2: Filter for non-tunneled traffic
+	 * Mode3: Filter for tunnel traffic
+	 */
+#define I40E_CLOUD_FILTER_MODE1	0x6
+#define I40E_CLOUD_FILTER_MODE2	0x7
+#define I40E_CLOUD_FILTER_MODE3	0x8
+#define I40E_SWITCH_MODE_MASK	0xF
+
 	u32  management_mode;
 	u32  mng_protocols_over_mctp;
 #define I40E_MNG_PROTOCOL_PLDM		0x2
@@ -428,6 +445,18 @@ struct i40e_nvm_access {
 	u8 data[1];
 };
 
+/* (Q)SFP module access definitions */
+#define I40E_I2C_EEPROM_DEV_ADDR	0xA0
+#define I40E_I2C_EEPROM_DEV_ADDR2	0xA2
+#define I40E_MODULE_TYPE_ADDR		0x00
+#define I40E_MODULE_REVISION_ADDR	0x01
+#define I40E_MODULE_SFF_8472_COMP	0x5E
+#define I40E_MODULE_SFF_8472_SWAP	0x5C
+#define I40E_MODULE_SFF_ADDR_MODE	0x04
+#define I40E_MODULE_TYPE_QSFP_PLUS	0x0D
+#define I40E_MODULE_TYPE_QSFP28		0x11
+#define I40E_MODULE_QSFP_MAX_LEN	640
+
 /* PCI bus types */
 enum i40e_bus_type {
 	i40e_bus_type_unknown = 0,
@@ -598,8 +627,15 @@ struct i40e_hw {
 	struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */
 
 #define I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE BIT_ULL(0)
+#define I40E_HW_FLAG_802_1AD_CAPABLE        BIT_ULL(1)
+#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE  BIT_ULL(2)
 	u64 flags;
 
+	/* Used in set switch config AQ command */
+	u16 switch_tag;
+	u16 first_tag;
+	u16 second_tag;
+
 	/* debug mask */
 	u32 debug_mask;
 	char err_str[16];
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 4d1e670f490e..f8a794b72462 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -154,15 +154,30 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf)
 
 /**
  * i40e_vc_disable_vf
- * @pf: pointer to the PF info
  * @vf: pointer to the VF info
  *
- * Disable the VF through a SW reset
+ * Disable the VF through a SW reset.
  **/
-static inline void i40e_vc_disable_vf(struct i40e_pf *pf, struct i40e_vf *vf)
+static inline void i40e_vc_disable_vf(struct i40e_vf *vf)
 {
+	int i;
+
 	i40e_vc_notify_vf_reset(vf);
-	i40e_reset_vf(vf, false);
+
+	/* We want to ensure that an actual reset occurs initiated after this
+	 * function was called. However, we do not want to wait forever, so
+	 * we'll give a reasonable time and print a message if we failed to
+	 * ensure a reset.
+	 */
+	for (i = 0; i < 20; i++) {
+		if (i40e_reset_vf(vf, false))
+			return;
+		usleep_range(10000, 20000);
+	}
+
+	dev_warn(&vf->pf->pdev->dev,
+		 "Failed to initiate reset for VF %d after 200 milliseconds\n",
+		 vf->vf_id);
 }
 
 /**
@@ -258,7 +273,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id,
 	struct i40e_hw *hw = &pf->hw;
 	u16 vsi_queue_id, pf_queue_id;
 	enum i40e_queue_type qtype;
-	u16 next_q, vector_id;
+	u16 next_q, vector_id, size;
 	u32 reg, reg_idx;
 	u16 itr_idx = 0;
 
@@ -288,9 +303,11 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id,
 				     vsi_queue_id + 1));
 	}
 
-	next_q = find_first_bit(&linklistmap,
-				(I40E_MAX_VSI_QP *
-				 I40E_VIRTCHNL_SUPPORTED_QTYPES));
+	size = I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES;
+	next_q = find_first_bit(&linklistmap, size);
+	if (unlikely(next_q == size))
+		goto irq_list_done;
+
 	vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES;
 	qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES;
 	pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id);
@@ -298,7 +315,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id,
 
 	wr32(hw, reg_idx, reg);
 
-	while (next_q < (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)) {
+	while (next_q < size) {
 		switch (qtype) {
 		case I40E_QUEUE_TYPE_RX:
 			reg_idx = I40E_QINT_RQCTL(pf_queue_id);
@@ -312,12 +329,8 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id,
 			break;
 		}
 
-		next_q = find_next_bit(&linklistmap,
-				       (I40E_MAX_VSI_QP *
-					I40E_VIRTCHNL_SUPPORTED_QTYPES),
-				       next_q + 1);
-		if (next_q <
-		    (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)) {
+		next_q = find_next_bit(&linklistmap, size, next_q + 1);
+		if (next_q < size) {
 			vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES;
 			qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES;
 			pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id,
@@ -423,6 +436,9 @@ static int i40e_config_iwarp_qvlist(struct i40e_vf *vf,
 	       (sizeof(struct virtchnl_iwarp_qv_info) *
 						(qvlist_info->num_vectors - 1));
 	vf->qvlist_info = kzalloc(size, GFP_KERNEL);
+	if (!vf->qvlist_info)
+		return -ENOMEM;
+
 	vf->qvlist_info->num_vectors = qvlist_info->num_vectors;
 
 	msix_vf = pf->hw.func_caps.num_msix_vectors_vf;
@@ -621,7 +637,7 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id,
 	rx_ctx.dsize = 1;
 
 	/* default values */
-	rx_ctx.lrxqthresh = 2;
+	rx_ctx.lrxqthresh = 1;
 	rx_ctx.crcstrip = 1;
 	rx_ctx.prefena = 1;
 	rx_ctx.l2tsel = 1;
@@ -815,6 +831,14 @@ static void i40e_free_vf_res(struct i40e_vf *vf)
 	 */
 	clear_bit(I40E_VF_STATE_INIT, &vf->vf_states);
 
+	/* It's possible the VF had requeuested more queues than the default so
+	 * do the accounting here when we're about to free them.
+	 */
+	if (vf->num_queue_pairs > I40E_DEFAULT_QUEUES_PER_VF) {
+		pf->queues_left += vf->num_queue_pairs -
+				   I40E_DEFAULT_QUEUES_PER_VF;
+	}
+
 	/* free vsi & disconnect it from the parent uplink */
 	if (vf->lan_vsi_idx) {
 		i40e_vsi_release(pf->vsi[vf->lan_vsi_idx]);
@@ -853,7 +877,8 @@ static void i40e_free_vf_res(struct i40e_vf *vf)
 	}
 	/* reset some of the state variables keeping track of the resources */
 	vf->num_queue_pairs = 0;
-	vf->vf_states = 0;
+	clear_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states);
+	clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states);
 }
 
 /**
@@ -868,12 +893,27 @@ static int i40e_alloc_vf_res(struct i40e_vf *vf)
 	int total_queue_pairs = 0;
 	int ret;
 
+	if (vf->num_req_queues &&
+	    vf->num_req_queues <= pf->queues_left + I40E_DEFAULT_QUEUES_PER_VF)
+		pf->num_vf_qps = vf->num_req_queues;
+	else
+		pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF;
+
 	/* allocate hw vsi context & associated resources */
 	ret = i40e_alloc_vsi_res(vf, I40E_VSI_SRIOV);
 	if (ret)
 		goto error_alloc;
 	total_queue_pairs += pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs;
 
+	/* We account for each VF to get a default number of queue pairs.  If
+	 * the VF has now requested more, we need to account for that to make
+	 * certain we never request more queues than we actually have left in
+	 * HW.
+	 */
+	if (total_queue_pairs > I40E_DEFAULT_QUEUES_PER_VF)
+		pf->queues_left -=
+			total_queue_pairs - I40E_DEFAULT_QUEUES_PER_VF;
+
 	if (vf->trusted)
 		set_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
 	else
@@ -1008,8 +1048,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf)
 		set_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states);
 		clear_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
 		/* Do not notify the client during VF init */
-		if (test_and_clear_bit(I40E_VF_STATE_PRE_ENABLE,
-				       &vf->vf_states))
+		if (!test_and_clear_bit(I40E_VF_STATE_PRE_ENABLE,
+					&vf->vf_states))
 			i40e_notify_client_of_vf_reset(pf, abs_vf_id);
 		vf->num_vlan = 0;
 	}
@@ -1026,9 +1066,9 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf)
  * @vf: pointer to the VF structure
  * @flr: VFLR was issued or not
  *
- * reset the VF
+ * Returns true if the VF is reset, false otherwise.
  **/
-void i40e_reset_vf(struct i40e_vf *vf, bool flr)
+bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 {
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_hw *hw = &pf->hw;
@@ -1036,9 +1076,11 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
 	u32 reg;
 	int i;
 
-	/* If VFs have been disabled, there is no need to reset */
+	/* If the VFs have been disabled, this means something else is
+	 * resetting the VF, so we shouldn't continue.
+	 */
 	if (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
-		return;
+		return false;
 
 	i40e_trigger_vf_reset(vf, flr);
 
@@ -1075,6 +1117,8 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
 
 	i40e_flush(hw);
 	clear_bit(__I40E_VF_DISABLE, pf->state);
+
+	return true;
 }
 
 /**
@@ -1086,8 +1130,10 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
  * VF, then do all the waiting in one chunk, and finally finish restoring each
  * VF after the wait. This is useful during PF routines which need to reset
  * all VFs, as otherwise it must perform these resets in a serialized fashion.
+ *
+ * Returns true if any VFs were reset, and false otherwise.
  **/
-void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
+bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 {
 	struct i40e_hw *hw = &pf->hw;
 	struct i40e_vf *vf;
@@ -1096,11 +1142,11 @@ void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 
 	/* If we don't have any VFs, then there is nothing to reset */
 	if (!pf->num_alloc_vfs)
-		return;
+		return false;
 
 	/* If VFs have been disabled, there is no need to reset */
 	if (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
-		return;
+		return false;
 
 	/* Begin reset on all VFs at once */
 	for (v = 0; v < pf->num_alloc_vfs; v++)
@@ -1175,6 +1221,8 @@ void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 
 	i40e_flush(hw);
 	clear_bit(__I40E_VF_DISABLE, pf->state);
+
+	return true;
 }
 
 /**
@@ -1308,7 +1356,7 @@ err_alloc:
 		i40e_free_vfs(pf);
 err_iov:
 	/* Re-enable interrupt 0. */
-	i40e_irq_dynamic_enable_icr0(pf, false);
+	i40e_irq_dynamic_enable_icr0(pf);
 	return ret;
 }
 
@@ -1377,8 +1425,7 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	if (num_vfs) {
 		if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
 			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
-			i40e_do_reset_safe(pf,
-					   BIT_ULL(__I40E_PF_RESET_REQUESTED));
+			i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
 		}
 		return i40e_pci_sriov_enable(pdev, num_vfs);
 	}
@@ -1386,7 +1433,7 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	if (!pci_vfs_assigned(pf->pdev)) {
 		i40e_free_vfs(pf);
 		pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
-		i40e_do_reset_safe(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
+		i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
 	} else {
 		dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n");
 		return -EINVAL;
@@ -1537,6 +1584,8 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	    (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_IWARP)) {
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_IWARP;
 		set_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states);
+	} else {
+		clear_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states);
 	}
 
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
@@ -1579,6 +1628,9 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 					VIRTCHNL_VF_OFFLOAD_WB_ON_ITR;
 	}
 
+	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)
+		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES;
+
 	vfres->num_vsis = num_vsis;
 	vfres->num_queue_pairs = vf->num_queue_pairs;
 	vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf;
@@ -1987,6 +2039,57 @@ error_param:
 }
 
 /**
+ * i40e_vc_request_queues_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * VFs get a default number of queues but can use this message to request a
+ * different number.  If the request is successful, PF will reset the VF and
+ * return 0.  If unsuccessful, PF will send message informing VF of number of
+ * available queues and return result of sending VF a message.
+ **/
+static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen)
+{
+	struct virtchnl_vf_res_request *vfres =
+		(struct virtchnl_vf_res_request *)msg;
+	int req_pairs = vfres->num_queue_pairs;
+	int cur_pairs = vf->num_queue_pairs;
+	struct i40e_pf *pf = vf->pf;
+
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states))
+		return -EINVAL;
+
+	if (req_pairs <= 0) {
+		dev_err(&pf->pdev->dev,
+			"VF %d tried to request %d queues.  Ignoring.\n",
+			vf->vf_id, req_pairs);
+	} else if (req_pairs > I40E_MAX_VF_QUEUES) {
+		dev_err(&pf->pdev->dev,
+			"VF %d tried to request more than %d queues.\n",
+			vf->vf_id,
+			I40E_MAX_VF_QUEUES);
+		vfres->num_queue_pairs = I40E_MAX_VF_QUEUES;
+	} else if (req_pairs - cur_pairs > pf->queues_left) {
+		dev_warn(&pf->pdev->dev,
+			 "VF %d requested %d more queues, but only %d left.\n",
+			 vf->vf_id,
+			 req_pairs - cur_pairs,
+			 pf->queues_left);
+		vfres->num_queue_pairs = pf->queues_left + cur_pairs;
+	} else {
+		/* successful request */
+		vf->num_req_queues = req_pairs;
+		i40e_vc_notify_vf_reset(vf);
+		i40e_reset_vf(vf, false);
+		return 0;
+	}
+
+	return i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES, 0,
+				      (u8 *)vfres, sizeof(vfres));
+}
+
+/**
  * i40e_vc_get_stats_msg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
@@ -2708,6 +2811,9 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 	case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING:
 		ret = i40e_vc_disable_vlan_stripping(vf, msg, msglen);
 		break;
+	case VIRTCHNL_OP_REQUEST_QUEUES:
+		ret = i40e_vc_request_queues_msg(vf, msg, msglen);
+		break;
 
 	case VIRTCHNL_OP_UNKNOWN:
 	default:
@@ -2779,6 +2885,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	struct i40e_mac_filter *f;
 	struct i40e_vf *vf;
 	int ret = 0;
+	struct hlist_node *h;
 	int bkt;
 
 	/* validate the request */
@@ -2817,7 +2924,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	/* Delete all the filters for this VSI - we're going to kill it
 	 * anyway.
 	 */
-	hash_for_each(vsi->mac_filter_hash, bkt, f, hlist)
+	hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist)
 		__i40e_del_filter(vsi, f);
 
 	spin_unlock_bh(&vsi->mac_filter_hash_lock);
@@ -2840,7 +2947,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	}
 
 	/* Force the VF driver stop so it has to reload with new MAC address */
-	i40e_vc_disable_vf(pf, vf);
+	i40e_vc_disable_vf(vf);
 	dev_info(&pf->pdev->dev, "Reload the VF driver to make this change effective.\n");
 
 error_param:
@@ -2848,6 +2955,34 @@ error_param:
 }
 
 /**
+ * i40e_vsi_has_vlans - True if VSI has configured VLANs
+ * @vsi: pointer to the vsi
+ *
+ * Check if a VSI has configured any VLANs. False if we have a port VLAN or if
+ * we have no configured VLANs. Do not call while holding the
+ * mac_filter_hash_lock.
+ */
+static bool i40e_vsi_has_vlans(struct i40e_vsi *vsi)
+{
+	bool have_vlans;
+
+	/* If we have a port VLAN, then the VSI cannot have any VLANs
+	 * configured, as all MAC/VLAN filters will be assigned to the PVID.
+	 */
+	if (vsi->info.pvid)
+		return false;
+
+	/* Since we don't have a PVID, we know that if the device is in VLAN
+	 * mode it must be because of a VLAN filter configured on this VSI.
+	 */
+	spin_lock_bh(&vsi->mac_filter_hash_lock);
+	have_vlans = i40e_is_vsi_in_vlan(vsi);
+	spin_unlock_bh(&vsi->mac_filter_hash_lock);
+
+	return have_vlans;
+}
+
+/**
  * i40e_ndo_set_vf_port_vlan
  * @netdev: network interface device structure
  * @vf_id: VF identifier
@@ -2899,10 +3034,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 		/* duplicate request, so just return success */
 		goto error_pvid;
 
-	/* Locked once because multiple functions below iterate list */
-	spin_lock_bh(&vsi->mac_filter_hash_lock);
-
-	if (le16_to_cpu(vsi->info.pvid) == 0 && i40e_is_vsi_in_vlan(vsi)) {
+	if (i40e_vsi_has_vlans(vsi)) {
 		dev_err(&pf->pdev->dev,
 			"VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n",
 			vf_id);
@@ -2910,11 +3042,14 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 		 * the right thing by reconfiguring his network correctly
 		 * and then reloading the VF driver.
 		 */
-		i40e_vc_disable_vf(pf, vf);
+		i40e_vc_disable_vf(vf);
 		/* During reset the VF got a new VSI, so refresh the pointer. */
 		vsi = pf->vsi[vf->lan_vsi_idx];
 	}
 
+	/* Locked once because multiple functions below iterate list */
+	spin_lock_bh(&vsi->mac_filter_hash_lock);
+
 	/* Check for condition where there was already a port VLAN ID
 	 * filter set and now it is being deleted by setting it to zero.
 	 * Additionally check for the condition where there was a port
@@ -2987,8 +3122,6 @@ error_pvid:
 	return ret;
 }
 
-#define I40E_BW_CREDIT_DIVISOR 50     /* 50Mbps per BW credit */
-#define I40E_MAX_BW_INACTIVE_ACCUM 4  /* device can accumulate 4 credits max */
 /**
  * i40e_ndo_set_vf_bw
  * @netdev: network interface device structure
@@ -3004,7 +3137,6 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_vsi *vsi;
 	struct i40e_vf *vf;
-	int speed = 0;
 	int ret = 0;
 
 	/* validate the request */
@@ -3029,48 +3161,10 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
 		goto error;
 	}
 
-	switch (pf->hw.phy.link_info.link_speed) {
-	case I40E_LINK_SPEED_40GB:
-		speed = 40000;
-		break;
-	case I40E_LINK_SPEED_25GB:
-		speed = 25000;
-		break;
-	case I40E_LINK_SPEED_20GB:
-		speed = 20000;
-		break;
-	case I40E_LINK_SPEED_10GB:
-		speed = 10000;
-		break;
-	case I40E_LINK_SPEED_1GB:
-		speed = 1000;
-		break;
-	default:
-		break;
-	}
-
-	if (max_tx_rate > speed) {
-		dev_err(&pf->pdev->dev, "Invalid max tx rate %d specified for VF %d.\n",
-			max_tx_rate, vf->vf_id);
-		ret = -EINVAL;
+	ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate);
+	if (ret)
 		goto error;
-	}
-
-	if ((max_tx_rate < 50) && (max_tx_rate > 0)) {
-		dev_warn(&pf->pdev->dev, "Setting max Tx rate to minimum usable value of 50Mbps.\n");
-		max_tx_rate = 50;
-	}
 
-	/* Tx rate credits are in values of 50Mbps, 0 is disabled*/
-	ret = i40e_aq_config_vsi_bw_limit(&pf->hw, vsi->seid,
-					  max_tx_rate / I40E_BW_CREDIT_DIVISOR,
-					  I40E_MAX_BW_INACTIVE_ACCUM, NULL);
-	if (ret) {
-		dev_err(&pf->pdev->dev, "Unable to set max tx rate, error code %d.\n",
-			ret);
-		ret = -EIO;
-		goto error;
-	}
 	vf->tx_rate = max_tx_rate;
 error:
 	return ret;
@@ -3279,14 +3373,11 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting)
 
 	vf = &pf->vf[vf_id];
 
-	if (!vf)
-		return -EINVAL;
 	if (setting == vf->trusted)
 		goto out;
 
 	vf->trusted = setting;
-	i40e_vc_notify_vf_reset(vf);
-	i40e_reset_vf(vf, false);
+	i40e_vc_disable_vf(vf);
 	dev_info(&pf->pdev->dev, "VF %u is now %strusted\n",
 		 vf_id, setting ? "" : "un");
 out:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 1f4b0c504368..5efc4f92bb37 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -56,7 +56,6 @@ enum i40e_vf_states {
 	I40E_VF_STATE_INIT = 0,
 	I40E_VF_STATE_ACTIVE,
 	I40E_VF_STATE_IWARPENA,
-	I40E_VF_STATE_FCOEENA,
 	I40E_VF_STATE_DISABLED,
 	I40E_VF_STATE_MC_PROMISC,
 	I40E_VF_STATE_UC_PROMISC,
@@ -97,6 +96,7 @@ struct i40e_vf {
 	u16 lan_vsi_id;		/* ID as used by firmware */
 
 	u8 num_queue_pairs;	/* num of qps assigned to VF vsis */
+	u8 num_req_queues;	/* num of requested qps */
 	u64 num_mdd_events;	/* num of mdd events detected */
 	/* num of continuous malformed or invalid msgs detected */
 	u64 num_invalid_msgs;
@@ -121,8 +121,8 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs);
 int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 			   u32 v_retval, u8 *msg, u16 msglen);
 int i40e_vc_process_vflr_event(struct i40e_pf *pf);
-void i40e_reset_vf(struct i40e_vf *vf, bool flr);
-void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr);
+bool i40e_reset_vf(struct i40e_vf *vf, bool flr);
+bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr);
 void i40e_vc_notify_vf_reset(struct i40e_vf *vf);
 
 /* VF configuration related iplink handlers */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index 83e63e55c4b4..06b04572c518 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -34,7 +34,15 @@
  */
 
 #define I40E_FW_API_VERSION_MAJOR	0x0001
-#define I40E_FW_API_VERSION_MINOR	0x0005
+#define I40E_FW_API_VERSION_MINOR_X722	0x0005
+#define I40E_FW_API_VERSION_MINOR_X710	0x0007
+
+#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \
+					I40E_FW_API_VERSION_MINOR_X710 : \
+					I40E_FW_API_VERSION_MINOR_X722)
+
+/* API version 1.7 implements additional link and PHY-specific APIs  */
+#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007
 
 struct i40e_aq_desc {
 	__le16 flags;
@@ -236,6 +244,8 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_set_phy_debug		= 0x0622,
 	i40e_aqc_opc_upload_ext_phy_fm		= 0x0625,
 	i40e_aqc_opc_run_phy_activity		= 0x0626,
+	i40e_aqc_opc_set_phy_register		= 0x0628,
+	i40e_aqc_opc_get_phy_register		= 0x0629,
 
 	/* NVM commands */
 	i40e_aqc_opc_nvm_read			= 0x0701,
@@ -761,7 +771,22 @@ struct i40e_aqc_set_switch_config {
 #define I40E_AQ_SET_SWITCH_CFG_PROMISC		0x0001
 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER	0x0002
 	__le16	valid_flags;
-	u8	reserved[12];
+	/* The ethertype in switch_tag is dropped on ingress and used
+	 * internally by the switch. Set this to zero for the default
+	 * of 0x88a8 (802.1ad). Should be zero for firmware API
+	 * versions lower than 1.7.
+	 */
+	__le16	switch_tag;
+	/* The ethertypes in first_tag and second_tag are used to
+	 * match the outer and inner VLAN tags (respectively) when HW
+	 * double VLAN tagging is enabled via the set port parameters
+	 * AQ command. Otherwise these are both ignored. Set them to
+	 * zero for their defaults of 0x8100 (802.1Q). Should be zero
+	 * for firmware API versions lower than 1.7.
+	 */
+	__le16	first_tag;
+	__le16	second_tag;
+	u8	reserved[6];
 };
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config);
@@ -1314,14 +1339,16 @@ struct i40e_aqc_add_remove_cloud_filters {
 #define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT	0
 #define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_MASK	(0x3FF << \
 					I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT)
-	u8	reserved2[4];
+	u8	big_buffer_flag;
+#define I40E_AQC_ADD_CLOUD_CMD_BB	1
+	u8	reserved2[3];
 	__le32	addr_high;
 	__le32	addr_low;
 };
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_cloud_filters);
 
-struct i40e_aqc_add_remove_cloud_filters_element_data {
+struct i40e_aqc_cloud_filters_element_data {
 	u8	outer_mac[6];
 	u8	inner_mac[6];
 	__le16	inner_vlan;
@@ -1333,6 +1360,9 @@ struct i40e_aqc_add_remove_cloud_filters_element_data {
 		struct {
 			u8 data[16];
 		} v6;
+		struct {
+			__le16 data[8];
+		} raw_v6;
 	} ipaddr;
 	__le16	flags;
 #define I40E_AQC_ADD_CLOUD_FILTER_SHIFT			0
@@ -1351,6 +1381,10 @@ struct i40e_aqc_add_remove_cloud_filters_element_data {
 #define I40E_AQC_ADD_CLOUD_FILTER_IMAC			0x000A
 #define I40E_AQC_ADD_CLOUD_FILTER_OMAC_TEN_ID_IMAC	0x000B
 #define I40E_AQC_ADD_CLOUD_FILTER_IIP			0x000C
+/* 0x0010 to 0x0017 is for custom filters */
+#define I40E_AQC_ADD_CLOUD_FILTER_IP_PORT		0x0010 /* Dest IP + L4 Port */
+#define I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT		0x0011 /* Dest MAC + L4 Port */
+#define I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT		0x0012 /* Dest MAC + VLAN + L4 Port */
 
 #define I40E_AQC_ADD_CLOUD_FLAGS_TO_QUEUE		0x0080
 #define I40E_AQC_ADD_CLOUD_VNK_SHIFT			6
@@ -1385,6 +1419,49 @@ struct i40e_aqc_add_remove_cloud_filters_element_data {
 	u8	response_reserved[7];
 };
 
+I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_cloud_filters_element_data);
+
+/* i40e_aqc_cloud_filters_element_bb is used when
+ * I40E_AQC_ADD_CLOUD_CMD_BB flag is set.
+ */
+struct i40e_aqc_cloud_filters_element_bb {
+	struct i40e_aqc_cloud_filters_element_data element;
+	u16     general_fields[32];
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD0	0
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD1	1
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD2	2
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD0	3
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD1	4
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD2	5
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD0	6
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD1	7
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD2	8
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD0	9
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD1	10
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD2	11
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD0	12
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD1	13
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD2	14
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD0	15
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD1	16
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD2	17
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD3	18
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD4	19
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD5	20
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD6	21
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD7	22
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD0	23
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD1	24
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD2	25
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD3	26
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD4	27
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD5	28
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD6	29
+#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD7	30
+};
+
+I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_cloud_filters_element_bb);
+
 struct i40e_aqc_remove_cloud_filters_completion {
 	__le16 perfect_ovlan_used;
 	__le16 perfect_ovlan_free;
@@ -1396,6 +1473,60 @@ struct i40e_aqc_remove_cloud_filters_completion {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_cloud_filters_completion);
 
+/* Replace filter Command 0x025F
+ * uses the i40e_aqc_replace_cloud_filters,
+ * and the generic indirect completion structure
+ */
+struct i40e_filter_data {
+	u8 filter_type;
+	u8 input[3];
+};
+
+I40E_CHECK_STRUCT_LEN(4, i40e_filter_data);
+
+struct i40e_aqc_replace_cloud_filters_cmd {
+	u8      valid_flags;
+#define I40E_AQC_REPLACE_L1_FILTER		0x0
+#define I40E_AQC_REPLACE_CLOUD_FILTER		0x1
+#define I40E_AQC_GET_CLOUD_FILTERS		0x2
+#define I40E_AQC_MIRROR_CLOUD_FILTER		0x4
+#define I40E_AQC_HIGH_PRIORITY_CLOUD_FILTER	0x8
+	u8      old_filter_type;
+	u8      new_filter_type;
+	u8      tr_bit;
+	u8      reserved[4];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_replace_cloud_filters_cmd);
+
+struct i40e_aqc_replace_cloud_filters_cmd_buf {
+	u8      data[32];
+/* Filter type INPUT codes*/
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_ENTRIES_MAX	3
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_VALIDATED	BIT(7)
+
+/* Field Vector offsets */
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_MAC_DA	0
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_ETH	6
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG	7
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_VLAN	8
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_OVLAN	9
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_IVLAN	10
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_TUNNLE_KEY	11
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IMAC	12
+/* big FLU */
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IP_DA	14
+/* big FLU */
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_OIP_DA	15
+
+#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_INNER_VLAN	37
+	struct i40e_filter_data filters[8];
+};
+
+I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_replace_cloud_filters_cmd_buf);
+
 /* Add Mirror Rule (indirect or direct 0x0260)
  * Delete Mirror Rule (indirect or direct 0x0261)
  * note: some rule types (4,5) do not use an external buffer.
@@ -1722,6 +1853,8 @@ enum i40e_aq_phy_type {
 	I40E_PHY_TYPE_10GBASE_CR1_CU		= 0xB,
 	I40E_PHY_TYPE_10GBASE_AOC		= 0xC,
 	I40E_PHY_TYPE_40GBASE_AOC		= 0xD,
+	I40E_PHY_TYPE_UNRECOGNIZED		= 0xE,
+	I40E_PHY_TYPE_UNSUPPORTED		= 0xF,
 	I40E_PHY_TYPE_100BASE_TX		= 0x11,
 	I40E_PHY_TYPE_1000BASE_T		= 0x12,
 	I40E_PHY_TYPE_10GBASE_T			= 0x13,
@@ -1740,7 +1873,12 @@ enum i40e_aq_phy_type {
 	I40E_PHY_TYPE_25GBASE_CR		= 0x20,
 	I40E_PHY_TYPE_25GBASE_SR		= 0x21,
 	I40E_PHY_TYPE_25GBASE_LR		= 0x22,
-	I40E_PHY_TYPE_MAX
+	I40E_PHY_TYPE_25GBASE_AOC		= 0x23,
+	I40E_PHY_TYPE_25GBASE_ACC		= 0x24,
+	I40E_PHY_TYPE_MAX,
+	I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP	= 0xFD,
+	I40E_PHY_TYPE_EMPTY			= 0xFE,
+	I40E_PHY_TYPE_DEFAULT			= 0xFF,
 };
 
 #define I40E_LINK_SPEED_100MB_SHIFT	0x1
@@ -1797,6 +1935,8 @@ struct i40e_aq_get_phy_abilities_resp {
 #define I40E_AQ_PHY_TYPE_EXT_25G_CR	0X02
 #define I40E_AQ_PHY_TYPE_EXT_25G_SR	0x04
 #define I40E_AQ_PHY_TYPE_EXT_25G_LR	0x08
+#define I40E_AQ_PHY_TYPE_EXT_25G_AOC	0x10
+#define I40E_AQ_PHY_TYPE_EXT_25G_ACC	0x20
 	u8	fec_cfg_curr_mod_ext_info;
 #define I40E_AQ_ENABLE_FEC_KR		0x01
 #define I40E_AQ_ENABLE_FEC_RS		0x02
@@ -1930,19 +2070,31 @@ struct i40e_aqc_get_link_status {
 #define I40E_AQ_25G_SERDES_UCODE_ERR	0X04
 #define I40E_AQ_25G_NIMB_UCODE_ERR	0X05
 	u8	loopback; /* use defines from i40e_aqc_set_lb_mode */
+/* Since firmware API 1.7 loopback field keeps power class info as well */
+#define I40E_AQ_LOOPBACK_MASK		0x07
+#define I40E_AQ_PWR_CLASS_SHIFT_LB	6
+#define I40E_AQ_PWR_CLASS_MASK_LB	(0x03 << I40E_AQ_PWR_CLASS_SHIFT_LB)
 	__le16	max_frame_size;
 	u8	config;
 #define I40E_AQ_CONFIG_FEC_KR_ENA	0x01
 #define I40E_AQ_CONFIG_FEC_RS_ENA	0x02
 #define I40E_AQ_CONFIG_CRC_ENA		0x04
 #define I40E_AQ_CONFIG_PACING_MASK	0x78
-	u8	power_desc;
+	union {
+		struct {
+			u8	power_desc;
 #define I40E_AQ_LINK_POWER_CLASS_1	0x00
 #define I40E_AQ_LINK_POWER_CLASS_2	0x01
 #define I40E_AQ_LINK_POWER_CLASS_3	0x02
 #define I40E_AQ_LINK_POWER_CLASS_4	0x03
 #define I40E_AQ_PWR_CLASS_MASK		0x03
-	u8	reserved[4];
+			u8	reserved[4];
+		};
+		struct {
+			u8	link_type[4];
+			u8	link_type_ext;
+		};
+	};
 };
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status);
@@ -2022,6 +2174,22 @@ struct i40e_aqc_run_phy_activity {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity);
 
+/* Set PHY Register command (0x0628) */
+/* Get PHY Register command (0x0629) */
+struct i40e_aqc_phy_register_access {
+	u8	phy_interface;
+#define I40E_AQ_PHY_REG_ACCESS_INTERNAL	0
+#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL	1
+#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE	2
+	u8	dev_address;
+	u8	reserved1[2];
+	__le32	reg_address;
+	__le32	reg_value;
+	u8	reserved2[4];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access);
+
 /* NVM Read command (indirect 0x0701)
  * NVM Erase commands (direct 0x0702)
  * NVM Update commands (indirect 0x0703)
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index 8d3a2bfe186a..7d70bf69b249 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -1042,6 +1042,75 @@ do_retry:
 }
 
 /**
+ * i40evf_aq_set_phy_register
+ * @hw: pointer to the hw struct
+ * @phy_select: select which phy should be accessed
+ * @dev_addr: PHY device address
+ * @reg_addr: PHY register address
+ * @reg_val: new register value
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Reset the external PHY.
+ **/
+i40e_status i40evf_aq_set_phy_register(struct i40e_hw *hw,
+				       u8 phy_select, u8 dev_addr,
+				       u32 reg_addr, u32 reg_val,
+				       struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_phy_register_access *cmd =
+		(struct i40e_aqc_phy_register_access *)&desc.params.raw;
+	i40e_status status;
+
+	i40evf_fill_default_direct_cmd_desc(&desc,
+					    i40e_aqc_opc_set_phy_register);
+
+	cmd->phy_interface = phy_select;
+	cmd->dev_address = dev_addr;
+	cmd->reg_address = cpu_to_le32(reg_addr);
+	cmd->reg_value = cpu_to_le32(reg_val);
+
+	status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+	return status;
+}
+
+/**
+ * i40evf_aq_get_phy_register
+ * @hw: pointer to the hw struct
+ * @phy_select: select which phy should be accessed
+ * @dev_addr: PHY device address
+ * @reg_addr: PHY register address
+ * @reg_val: read register value
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Reset the external PHY.
+ **/
+i40e_status i40evf_aq_get_phy_register(struct i40e_hw *hw,
+				       u8 phy_select, u8 dev_addr,
+				       u32 reg_addr, u32 *reg_val,
+				       struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_phy_register_access *cmd =
+		(struct i40e_aqc_phy_register_access *)&desc.params.raw;
+	i40e_status status;
+
+	i40evf_fill_default_direct_cmd_desc(&desc,
+					    i40e_aqc_opc_get_phy_register);
+
+	cmd->phy_interface = phy_select;
+	cmd->dev_address = dev_addr;
+	cmd->reg_address = cpu_to_le32(reg_addr);
+
+	status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+	if (!status)
+		*reg_val = le32_to_cpu(cmd->reg_value);
+
+	return status;
+}
+
+/**
  * i40e_aq_send_msg_to_pf
  * @hw: pointer to the hardware structure
  * @v_opcode: opcodes for VF-PF communication
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
index c9836bba487d..b624b5994075 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
@@ -111,6 +111,15 @@ i40e_status i40evf_aq_rx_ctl_write_register(struct i40e_hw *hw,
 				u32 reg_addr, u32 reg_val,
 				struct i40e_asq_cmd_details *cmd_details);
 void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val);
+i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw,
+				     u8 phy_select, u8 dev_addr,
+				     u32 reg_addr, u32 reg_val,
+				     struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw,
+				     u8 phy_select, u8 dev_addr,
+				     u32 reg_addr, u32 *reg_val,
+				     struct i40e_asq_cmd_details *cmd_details);
+
 i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page,
 				   u16 reg, u8 phy_addr, u16 *value);
 i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page,
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index c32c62462c84..fe817e2b6fef 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -358,14 +358,14 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 {
 	enum i40e_latency_range new_latency_range = rc->latency_range;
 	u32 new_itr = rc->itr;
-	int bytes_per_int;
+	int bytes_per_usec;
 	unsigned int usecs, estimated_usecs;
 
 	if (rc->total_packets == 0 || !rc->itr)
 		return false;
 
 	usecs = (rc->itr << 1) * ITR_COUNTDOWN_START;
-	bytes_per_int = rc->total_bytes / usecs;
+	bytes_per_usec = rc->total_bytes / usecs;
 
 	/* The calculations in this algorithm depend on interrupts actually
 	 * firing at the ITR rate. This may not happen if the packet rate is
@@ -391,18 +391,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 	 */
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
-		if (bytes_per_int > 10)
+		if (bytes_per_usec > 10)
 			new_latency_range = I40E_LOW_LATENCY;
 		break;
 	case I40E_LOW_LATENCY:
-		if (bytes_per_int > 20)
+		if (bytes_per_usec > 20)
 			new_latency_range = I40E_BULK_LATENCY;
-		else if (bytes_per_int <= 10)
+		else if (bytes_per_usec <= 10)
 			new_latency_range = I40E_LOWEST_LATENCY;
 		break;
 	case I40E_BULK_LATENCY:
 	default:
-		if (bytes_per_int <= 20)
+		if (bytes_per_usec <= 20)
 			new_latency_range = I40E_LOW_LATENCY;
 		break;
 	}
@@ -1409,9 +1409,7 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr)
 	u32 val;
 
 	val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
-	      /* Don't clear PBA because that can cause lost interrupts that
-	       * came in while we were cleaning/polling
-	       */
+	      I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
 	      (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) |
 	      (itr << I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT);
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 0d9f98bc07bd..8d26c85d12e1 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -38,8 +38,10 @@
 #define I40E_ITR_8K                0x003E
 #define I40E_ITR_4K                0x007A
 #define I40E_MAX_INTRL             0x3B    /* reg uses 4 usec resolution */
-#define I40E_ITR_RX_DEF            I40E_ITR_20K
-#define I40E_ITR_TX_DEF            I40E_ITR_20K
+#define I40E_ITR_RX_DEF            (ITR_REG_TO_USEC(I40E_ITR_20K) | \
+				    I40E_ITR_DYNAMIC)
+#define I40E_ITR_TX_DEF            (ITR_REG_TO_USEC(I40E_ITR_20K) | \
+				    I40E_ITR_DYNAMIC)
 #define I40E_ITR_DYNAMIC           0x8000  /* use top bit as a flag */
 #define I40E_MIN_INT_RATE          250     /* ~= 1000000 / (I40E_MAX_ITR * 2) */
 #define I40E_MAX_INT_RATE          500000  /* == 1000000 / (I40E_MIN_ITR * 2) */
@@ -189,7 +191,7 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc,
 }
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
-#define I40E_RX_BUFFER_WRITE	16	/* Must be power of 2 */
+#define I40E_RX_BUFFER_WRITE	32	/* Must be power of 2 */
 #define I40E_RX_INCREMENT(r, i) \
 	do {					\
 		(i)++;				\
@@ -325,6 +327,7 @@ struct i40e_rx_queue_stats {
 enum i40e_ring_state_t {
 	__I40E_TX_FDIR_INIT_DONE,
 	__I40E_TX_XPS_INIT_DONE,
+	__I40E_RING_STATE_NBITS /* must be last */
 };
 
 /* some useful defines for virtchannel interface, which
@@ -348,7 +351,7 @@ struct i40e_ring {
 		struct i40e_tx_buffer *tx_bi;
 		struct i40e_rx_buffer *rx_bi;
 	};
-	unsigned long state;
+	DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS);
 	u16 queue_index;		/* Queue number of ring */
 	u8 dcb_tc;			/* Traffic class of ring */
 	u8 __iomem *tail;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index 2ea919d9cdcf..213b773dfad6 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -46,6 +46,9 @@
 /* Max default timeout in ms, */
 #define I40E_MAX_NVM_TIMEOUT		18000
 
+/* Max timeout in ms for the phy to respond */
+#define I40E_MAX_PHY_TIMEOUT		500
+
 /* Switch from ms to the 1usec global time (this is the GTIME resolution) */
 #define I40E_MS_TO_GTIME(time)		((time) * 1000)
 
@@ -401,6 +404,18 @@ struct i40e_nvm_access {
 	u8 data[1];
 };
 
+/* (Q)SFP module access definitions */
+#define I40E_I2C_EEPROM_DEV_ADDR	0xA0
+#define I40E_I2C_EEPROM_DEV_ADDR2	0xA2
+#define I40E_MODULE_TYPE_ADDR		0x00
+#define I40E_MODULE_REVISION_ADDR	0x01
+#define I40E_MODULE_SFF_8472_COMP	0x5E
+#define I40E_MODULE_SFF_8472_SWAP	0x5C
+#define I40E_MODULE_SFF_ADDR_MODE	0x04
+#define I40E_MODULE_TYPE_QSFP_PLUS	0x0D
+#define I40E_MODULE_TYPE_QSFP28		0x11
+#define I40E_MODULE_QSFP_MAX_LEN	640
+
 /* PCI bus types */
 enum i40e_bus_type {
 	i40e_bus_type_unknown = 0,
@@ -556,11 +571,19 @@ struct i40e_hw {
 	/* LLDP/DCBX Status */
 	u16 dcbx_status;
 
+#define I40E_HW_FLAG_802_1AD_CAPABLE        BIT_ULL(1)
+#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE  BIT_ULL(2)
+
 	/* DCBX info */
 	struct i40e_dcbx_config local_dcbx_config; /* Oper/Local Cfg */
 	struct i40e_dcbx_config remote_dcbx_config; /* Peer Cfg */
 	struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */
 
+	/* Used in set switch config AQ command */
+	u16 switch_tag;
+	u16 first_tag;
+	u16 second_tag;
+
 	/* debug mask */
 	u32 debug_mask;
 	char err_str[16];
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index 82f69031e5cd..de0af521d602 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -102,6 +102,7 @@ struct i40e_vsi {
 #define I40E_TX_CTXTDESC(R, i) \
 	(&(((struct i40e_tx_context_desc *)((R)->desc))[i]))
 #define MAX_QUEUES 16
+#define I40EVF_MAX_REQ_QUEUES 4
 
 #define I40EVF_HKEY_ARRAY_SIZE ((I40E_VFQF_HKEY_MAX_INDEX + 1) * 4)
 #define I40EVF_HLUT_ARRAY_SIZE ((I40E_VFQF_HLUT_MAX_INDEX + 1) * 4)
@@ -200,6 +201,7 @@ struct i40evf_adapter {
 	struct list_head vlan_filter_list;
 	char misc_vector_name[IFNAMSIZ + 9];
 	int num_active_queues;
+	int num_req_queues;
 
 	/* TX */
 	struct i40e_ring *tx_rings;
@@ -220,21 +222,22 @@ struct i40evf_adapter {
 
 	u32 flags;
 #define I40EVF_FLAG_RX_CSUM_ENABLED		BIT(0)
-#define I40EVF_FLAG_IMIR_ENABLED		BIT(5)
-#define I40EVF_FLAG_MQ_CAPABLE			BIT(6)
-#define I40EVF_FLAG_PF_COMMS_FAILED		BIT(8)
-#define I40EVF_FLAG_RESET_PENDING		BIT(9)
-#define I40EVF_FLAG_RESET_NEEDED		BIT(10)
-#define I40EVF_FLAG_WB_ON_ITR_CAPABLE		BIT(11)
-#define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE	BIT(12)
-#define I40EVF_FLAG_ADDR_SET_BY_PF		BIT(13)
-#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED	BIT(14)
-#define I40EVF_FLAG_CLIENT_NEEDS_OPEN		BIT(15)
-#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE		BIT(16)
-#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS	BIT(17)
-#define I40EVF_FLAG_PROMISC_ON			BIT(18)
-#define I40EVF_FLAG_ALLMULTI_ON			BIT(19)
-#define I40EVF_FLAG_LEGACY_RX			BIT(20)
+#define I40EVF_FLAG_IMIR_ENABLED		BIT(1)
+#define I40EVF_FLAG_MQ_CAPABLE			BIT(2)
+#define I40EVF_FLAG_PF_COMMS_FAILED		BIT(3)
+#define I40EVF_FLAG_RESET_PENDING		BIT(4)
+#define I40EVF_FLAG_RESET_NEEDED		BIT(5)
+#define I40EVF_FLAG_WB_ON_ITR_CAPABLE		BIT(6)
+#define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE	BIT(7)
+#define I40EVF_FLAG_ADDR_SET_BY_PF		BIT(8)
+#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED	BIT(9)
+#define I40EVF_FLAG_CLIENT_NEEDS_OPEN		BIT(10)
+#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE		BIT(11)
+#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS	BIT(12)
+#define I40EVF_FLAG_PROMISC_ON			BIT(13)
+#define I40EVF_FLAG_ALLMULTI_ON			BIT(14)
+#define I40EVF_FLAG_LEGACY_RX			BIT(15)
+#define I40EVF_FLAG_REINIT_ITR_NEEDED		BIT(16)
 /* duplicates for common code */
 #define I40E_FLAG_DCB_ENABLED			0
 #define I40E_FLAG_RX_CSUM_ENABLED		I40EVF_FLAG_RX_CSUM_ENABLED
@@ -349,6 +352,7 @@ void i40evf_deconfigure_queues(struct i40evf_adapter *adapter);
 void i40evf_enable_queues(struct i40evf_adapter *adapter);
 void i40evf_disable_queues(struct i40evf_adapter *adapter);
 void i40evf_map_queues(struct i40evf_adapter *adapter);
+int i40evf_request_queues(struct i40evf_adapter *adapter, int num);
 void i40evf_add_ether_addrs(struct i40evf_adapter *adapter);
 void i40evf_del_ether_addrs(struct i40evf_adapter *adapter);
 void i40evf_add_vlans(struct i40evf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index 65874d6b3ab9..da006fa3fec1 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -669,7 +669,7 @@ static void i40evf_get_channels(struct net_device *netdev,
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
 	/* Report maximum channels */
-	ch->max_combined = adapter->num_active_queues;
+	ch->max_combined = I40EVF_MAX_REQ_QUEUES;
 
 	ch->max_other = NONQ_VECS;
 	ch->other_count = NONQ_VECS;
@@ -678,6 +678,41 @@ static void i40evf_get_channels(struct net_device *netdev,
 }
 
 /**
+ * i40evf_set_channels: set the new channel count
+ * @netdev: network interface device structure
+ * @ch: channel information structure
+ *
+ * Negotiate a new number of channels with the PF then do a reset.  During
+ * reset we'll realloc queues and fix the RSS table.  Returns 0 on success,
+ * negative on failure.
+ **/
+static int i40evf_set_channels(struct net_device *netdev,
+			       struct ethtool_channels *ch)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+	int num_req = ch->combined_count;
+
+	if (num_req != adapter->num_active_queues &&
+	    !(adapter->vf_res->vf_cap_flags &
+	      VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)) {
+		dev_info(&adapter->pdev->dev, "PF is not capable of queue negotiation.\n");
+		return -EINVAL;
+	}
+
+	/* All of these should have already been checked by ethtool before this
+	 * even gets to us, but just to be sure.
+	 */
+	if (num_req <= 0 || num_req > I40EVF_MAX_REQ_QUEUES)
+		return -EINVAL;
+
+	if (ch->rx_count || ch->tx_count || ch->other_count != NONQ_VECS)
+		return -EINVAL;
+
+	adapter->num_req_queues = num_req;
+	return i40evf_request_queues(adapter, num_req);
+}
+
+/**
  * i40evf_get_rxfh_key_size - get the RSS hash key size
  * @netdev: network interface device structure
  *
@@ -785,6 +820,7 @@ static const struct ethtool_ops i40evf_ethtool_ops = {
 	.get_rxfh		= i40evf_get_rxfh,
 	.set_rxfh		= i40evf_set_rxfh,
 	.get_channels		= i40evf_get_channels,
+	.set_channels		= i40evf_set_channels,
 	.get_rxfh_key_size	= i40evf_get_rxfh_key_size,
 	.get_link_ksettings	= i40evf_get_link_ksettings,
 };
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 1825d956bb00..ca2ebdbd24d7 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -46,7 +46,7 @@ static const char i40evf_driver_string[] =
 
 #define DRV_VERSION_MAJOR 3
 #define DRV_VERSION_MINOR 0
-#define DRV_VERSION_BUILD 0
+#define DRV_VERSION_BUILD 1
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD) \
@@ -430,57 +430,26 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx)
  * group the rings as "efficiently" as possible.  You would add new
  * mapping configurations in here.
  **/
-static int i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter)
+static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter)
 {
+	int rings_remaining = adapter->num_active_queues;
+	int ridx = 0, vidx = 0;
 	int q_vectors;
-	int v_start = 0;
-	int rxr_idx = 0, txr_idx = 0;
-	int rxr_remaining = adapter->num_active_queues;
-	int txr_remaining = adapter->num_active_queues;
-	int i, j;
-	int rqpv, tqpv;
-	int err = 0;
 
 	q_vectors = adapter->num_msix_vectors - NONQ_VECS;
 
-	/* The ideal configuration...
-	 * We have enough vectors to map one per queue.
-	 */
-	if (q_vectors >= (rxr_remaining * 2)) {
-		for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++)
-			i40evf_map_vector_to_rxq(adapter, v_start, rxr_idx);
-
-		for (; txr_idx < txr_remaining; v_start++, txr_idx++)
-			i40evf_map_vector_to_txq(adapter, v_start, txr_idx);
-		goto out;
-	}
+	for (; ridx < rings_remaining; ridx++) {
+		i40evf_map_vector_to_rxq(adapter, vidx, ridx);
+		i40evf_map_vector_to_txq(adapter, vidx, ridx);
 
-	/* If we don't have enough vectors for a 1-to-1
-	 * mapping, we'll have to group them so there are
-	 * multiple queues per vector.
-	 * Re-adjusting *qpv takes care of the remainder.
-	 */
-	for (i = v_start; i < q_vectors; i++) {
-		rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - i);
-		for (j = 0; j < rqpv; j++) {
-			i40evf_map_vector_to_rxq(adapter, i, rxr_idx);
-			rxr_idx++;
-			rxr_remaining--;
-		}
-	}
-	for (i = v_start; i < q_vectors; i++) {
-		tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - i);
-		for (j = 0; j < tqpv; j++) {
-			i40evf_map_vector_to_txq(adapter, i, txr_idx);
-			txr_idx++;
-			txr_remaining--;
-		}
+		/* In the case where we have more queues than vectors, continue
+		 * round-robin on vectors until all queues are mapped.
+		 */
+		if (++vidx >= q_vectors)
+			vidx = 0;
 	}
 
-out:
 	adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS;
-
-	return err;
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -546,6 +515,7 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 	unsigned int vector, q_vectors;
 	unsigned int rx_int_idx = 0, tx_int_idx = 0;
 	int irq_num, err;
+	int cpu;
 
 	i40evf_irq_disable(adapter);
 	/* Decrement for Other and TCP Timer vectors */
@@ -584,10 +554,12 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 		q_vector->affinity_notify.release =
 						   i40evf_irq_affinity_release;
 		irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
-		/* get_cpu_mask returns a static constant mask with
-		 * a permanent lifetime so it's ok to use here.
+		/* Spread the IRQ affinity hints across online CPUs. Note that
+		 * get_cpu_mask returns a mask with a permanent lifetime so
+		 * it's safe to use as a hint for irq_set_affinity_hint.
 		 */
-		irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx));
+		cpu = cpumask_local_spread(q_vector->v_idx, -1);
+		irq_set_affinity_hint(irq_num, get_cpu_mask(cpu));
 	}
 
 	return 0;
@@ -908,6 +880,8 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter,
 		list_add_tail(&f->list, &adapter->mac_filter_list);
 		f->add = true;
 		adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER;
+	} else {
+		f->remove = false;
 	}
 
 	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
@@ -1217,9 +1191,18 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 {
 	int i, num_active_queues;
 
-	num_active_queues = min_t(int,
-				  adapter->vsi_res->num_queue_pairs,
-				  (int)(num_online_cpus()));
+	/* If we're in reset reallocating queues we don't actually know yet for
+	 * certain the PF gave us the number of queues we asked for but we'll
+	 * assume it did.  Once basic reset is finished we'll confirm once we
+	 * start negotiating config with PF.
+	 */
+	if (adapter->num_req_queues)
+		num_active_queues = adapter->num_req_queues;
+	else
+		num_active_queues = min_t(int,
+					  adapter->vsi_res->num_queue_pairs,
+					  (int)(num_online_cpus()));
+
 
 	adapter->tx_rings = kcalloc(num_active_queues,
 				    sizeof(struct i40e_ring), GFP_KERNEL);
@@ -1240,7 +1223,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 		tx_ring->netdev = adapter->netdev;
 		tx_ring->dev = &adapter->pdev->dev;
 		tx_ring->count = adapter->tx_desc_count;
-		tx_ring->tx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF);
+		tx_ring->tx_itr_setting = I40E_ITR_TX_DEF;
 		if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE)
 			tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR;
 
@@ -1249,7 +1232,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 		rx_ring->netdev = adapter->netdev;
 		rx_ring->dev = &adapter->pdev->dev;
 		rx_ring->count = adapter->rx_desc_count;
-		rx_ring->rx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF);
+		rx_ring->rx_itr_setting = I40E_ITR_RX_DEF;
 	}
 
 	adapter->num_active_queues = num_active_queues;
@@ -1568,12 +1551,53 @@ static void i40evf_free_rss(struct i40evf_adapter *adapter)
 }
 
 /**
+ * i40evf_reinit_interrupt_scheme - Reallocate queues and vectors
+ * @adapter: board private structure
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40evf_reinit_interrupt_scheme(struct i40evf_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	int err;
+
+	if (netif_running(netdev))
+		i40evf_free_traffic_irqs(adapter);
+	i40evf_free_misc_irq(adapter);
+	i40evf_reset_interrupt_capability(adapter);
+	i40evf_free_q_vectors(adapter);
+	i40evf_free_queues(adapter);
+
+	err =  i40evf_init_interrupt_scheme(adapter);
+	if (err)
+		goto err;
+
+	netif_tx_stop_all_queues(netdev);
+
+	err = i40evf_request_misc_irq(adapter);
+	if (err)
+		goto err;
+
+	set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
+
+	i40evf_map_rings_to_vectors(adapter);
+
+	if (RSS_AQ(adapter))
+		adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_RSS;
+	else
+		err = i40evf_init_rss(adapter);
+err:
+	return err;
+}
+
+/**
  * i40evf_watchdog_timer - Periodic call-back timer
  * @data: pointer to adapter disguised as unsigned long
  **/
-static void i40evf_watchdog_timer(unsigned long data)
+static void i40evf_watchdog_timer(struct timer_list *t)
 {
-	struct i40evf_adapter *adapter = (struct i40evf_adapter *)data;
+	struct i40evf_adapter *adapter = from_timer(adapter, t,
+						    watchdog_timer);
 
 	schedule_work(&adapter->watchdog_task);
 	/* timer will be rescheduled in watchdog task */
@@ -1913,8 +1937,15 @@ continue_reset:
 	if (err)
 		dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n",
 			 err);
+	adapter->aq_required = 0;
 
-	adapter->aq_required = I40EVF_FLAG_AQ_GET_CONFIG;
+	if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) {
+		err = i40evf_reinit_interrupt_scheme(adapter);
+		if (err)
+			goto reset_err;
+	}
+
+	adapter->aq_required |= I40EVF_FLAG_AQ_GET_CONFIG;
 	adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS;
 
 	/* re-add all MAC filters */
@@ -1944,6 +1975,15 @@ continue_reset:
 		if (err)
 			goto reset_err;
 
+		if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) {
+			err = i40evf_request_traffic_irqs(adapter,
+							  netdev->name);
+			if (err)
+				goto reset_err;
+
+			adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED;
+		}
+
 		i40evf_configure(adapter);
 
 		i40evf_up_complete(adapter);
@@ -2386,10 +2426,6 @@ out_err:
 	return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
 }
 
-#define I40EVF_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_TX |\
-			      NETIF_F_HW_VLAN_CTAG_RX |\
-			      NETIF_F_HW_VLAN_CTAG_FILTER)
-
 /**
  * i40evf_fix_features - fix up the netdev feature bits
  * @netdev: our net device
@@ -2402,9 +2438,11 @@ static netdev_features_t i40evf_fix_features(struct net_device *netdev,
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
-	features &= ~I40EVF_VLAN_FEATURES;
-	if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
-		features |= I40EVF_VLAN_FEATURES;
+	if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN))
+		features &= ~(NETIF_F_HW_VLAN_CTAG_TX |
+			      NETIF_F_HW_VLAN_CTAG_RX |
+			      NETIF_F_HW_VLAN_CTAG_FILTER);
+
 	return features;
 }
 
@@ -2459,9 +2497,9 @@ static int i40evf_check_reset_complete(struct i40e_hw *hw)
 int i40evf_process_config(struct i40evf_adapter *adapter)
 {
 	struct virtchnl_vf_resource *vfres = adapter->vf_res;
+	int i, num_req_queues = adapter->num_req_queues;
 	struct net_device *netdev = adapter->netdev;
 	struct i40e_vsi *vsi = &adapter->vsi;
-	int i;
 	netdev_features_t hw_enc_features;
 	netdev_features_t hw_features;
 
@@ -2475,6 +2513,23 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 		return -ENODEV;
 	}
 
+	if (num_req_queues &&
+	    num_req_queues != adapter->vsi_res->num_queue_pairs) {
+		/* Problem.  The PF gave us fewer queues than what we had
+		 * negotiated in our request.  Need a reset to see if we can't
+		 * get back to a working state.
+		 */
+		dev_err(&adapter->pdev->dev,
+			"Requested %d queues, but PF only gave us %d.\n",
+			num_req_queues,
+			adapter->vsi_res->num_queue_pairs);
+		adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED;
+		adapter->num_req_queues = adapter->vsi_res->num_queue_pairs;
+		i40evf_schedule_reset(adapter);
+		return -ENODEV;
+	}
+	adapter->num_req_queues = 0;
+
 	hw_enc_features = NETIF_F_SG			|
 			  NETIF_F_IP_CSUM		|
 			  NETIF_F_IPV6_CSUM		|
@@ -2518,9 +2573,17 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 	 */
 	hw_features = hw_enc_features;
 
+	/* Enable VLAN features if supported */
+	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
+		hw_features |= (NETIF_F_HW_VLAN_CTAG_TX |
+				NETIF_F_HW_VLAN_CTAG_RX);
+
 	netdev->hw_features |= hw_features;
 
-	netdev->features |= hw_features | I40EVF_VLAN_FEATURES;
+	netdev->features |= hw_features;
+
+	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
+		netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	adapter->vsi.id = adapter->vsi_res->vsi_id;
 
@@ -2686,9 +2749,7 @@ static void i40evf_init_task(struct work_struct *work)
 		ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr);
 	}
 
-	init_timer(&adapter->watchdog_timer);
-	adapter->watchdog_timer.function = &i40evf_watchdog_timer;
-	adapter->watchdog_timer.data = (unsigned long)adapter;
+	timer_setup(&adapter->watchdog_timer, i40evf_watchdog_timer, 0);
 	mod_timer(&adapter->watchdog_timer, jiffies + 1);
 
 	adapter->tx_desc_count = I40EVF_DEFAULT_TXD;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index 85876f4fb1fb..46c8b8a3907c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -52,7 +52,7 @@ static int i40evf_send_pf_msg(struct i40evf_adapter *adapter,
 
 	err = i40e_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL);
 	if (err)
-		dev_err(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n",
+		dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n",
 			op, i40evf_stat_str(hw, err),
 			i40evf_aq_str(hw, hw->aq.asq_last_status));
 	return err;
@@ -160,7 +160,8 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter)
 	       VIRTCHNL_VF_OFFLOAD_WB_ON_ITR |
 	       VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 |
 	       VIRTCHNL_VF_OFFLOAD_ENCAP |
-	       VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM;
+	       VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM |
+	       VIRTCHNL_VF_OFFLOAD_REQ_QUEUES;
 
 	adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES;
 	adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG;
@@ -385,6 +386,33 @@ void i40evf_map_queues(struct i40evf_adapter *adapter)
 }
 
 /**
+ * i40evf_request_queues
+ * @adapter: adapter structure
+ * @num: number of requested queues
+ *
+ * We get a default number of queues from the PF.  This enables us to request a
+ * different number.  Returns 0 on success, negative on failure
+ **/
+int i40evf_request_queues(struct i40evf_adapter *adapter, int num)
+{
+	struct virtchnl_vf_res_request vfres;
+
+	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+		/* bail because we already have a command pending */
+		dev_err(&adapter->pdev->dev, "Cannot request queues, command %d pending\n",
+			adapter->current_op);
+		return -EBUSY;
+	}
+
+	vfres.num_queue_pairs = num;
+
+	adapter->current_op = VIRTCHNL_OP_REQUEST_QUEUES;
+	adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED;
+	return i40evf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES,
+				  (u8 *)&vfres, sizeof(vfres));
+}
+
+/**
  * i40evf_add_ether_addrs
  * @adapter: adapter structure
  * @addrs: the MAC address filters to add (contiguous)
@@ -1068,6 +1096,19 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 				 "Invalid message %d from PF\n", v_opcode);
 		}
 		break;
+	case VIRTCHNL_OP_REQUEST_QUEUES: {
+		struct virtchnl_vf_res_request *vfres =
+			(struct virtchnl_vf_res_request *)msg;
+		if (vfres->num_queue_pairs != adapter->num_req_queues) {
+			dev_info(&adapter->pdev->dev,
+				 "Requested %d queues, PF can support %d\n",
+				 adapter->num_req_queues,
+				 vfres->num_queue_pairs);
+			adapter->num_req_queues = 0;
+			adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED;
+		}
+		}
+		break;
 	default:
 		if (adapter->current_op && (v_opcode != adapter->current_op))
 			dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n",
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 1de82f247312..83cabff1e0ab 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -353,7 +353,18 @@
 #define E1000_RXPBS_CFG_TS_EN           0x80000000
 
 #define I210_RXPBSIZE_DEFAULT		0x000000A2 /* RXPBSIZE default */
+#define I210_RXPBSIZE_MASK		0x0000003F
+#define I210_RXPBSIZE_PB_32KB		0x00000020
 #define I210_TXPBSIZE_DEFAULT		0x04000014 /* TXPBSIZE default */
+#define I210_TXPBSIZE_MASK		0xC0FFFFFF
+#define I210_TXPBSIZE_PB0_8KB		(8 << 0)
+#define I210_TXPBSIZE_PB1_8KB		(8 << 6)
+#define I210_TXPBSIZE_PB2_4KB		(4 << 12)
+#define I210_TXPBSIZE_PB3_4KB		(4 << 18)
+
+#define I210_DTXMXPKTSZ_DEFAULT		0x00000098
+
+#define I210_SR_QUEUES_NUM		2
 
 /* SerDes Control */
 #define E1000_SCTL_DISABLE_SERDES_LOOPBACK 0x0400
@@ -1051,4 +1062,16 @@
 #define E1000_VLAPQF_P_VALID(_n)	(0x1 << (3 + (_n) * 4))
 #define E1000_VLAPQF_QUEUE_MASK	0x03
 
+/* TX Qav Control fields */
+#define E1000_TQAVCTRL_XMIT_MODE	BIT(0)
+#define E1000_TQAVCTRL_DATAFETCHARB	BIT(4)
+#define E1000_TQAVCTRL_DATATRANARB	BIT(8)
+
+/* TX Qav Credit Control fields */
+#define E1000_TQAVCC_IDLESLOPE_MASK	0xFFFF
+#define E1000_TQAVCC_QUEUEMODE		BIT(31)
+
+/* Transmit Descriptor Control fields */
+#define E1000_TXDCTL_PRIORITY		BIT(27)
+
 #endif
diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h
index 58adbf234e07..8eee081d395f 100644
--- a/drivers/net/ethernet/intel/igb/e1000_regs.h
+++ b/drivers/net/ethernet/intel/igb/e1000_regs.h
@@ -421,6 +421,14 @@ do { \
 
 #define E1000_I210_FLA		0x1201C
 
+#define E1000_I210_DTXMXPKTSZ	0x355C
+
+#define E1000_I210_TXDCTL(_n)	(0x0E028 + ((_n) * 0x40))
+
+#define E1000_I210_TQAVCTRL	0x3570
+#define E1000_I210_TQAVCC(_n)	(0x3004 + ((_n) * 0x40))
+#define E1000_I210_TQAVHC(_n)	(0x300C + ((_n) * 0x40))
+
 #define E1000_INVM_DATA_REG(_n)	(0x12120 + 4*(_n))
 #define E1000_INVM_SIZE		64 /* Number of INVM Data Registers */
 
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 06ffb2bc713e..92845692087a 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -281,6 +281,11 @@ struct igb_ring {
 	u16 count;			/* number of desc. in the ring */
 	u8 queue_index;			/* logical index of the ring*/
 	u8 reg_idx;			/* physical index of the ring */
+	bool cbs_enable;		/* indicates if CBS is enabled */
+	s32 idleslope;			/* idleSlope in kbps */
+	s32 sendslope;			/* sendSlope in kbps */
+	s32 hicredit;			/* hiCredit in bytes */
+	s32 locredit;			/* loCredit in bytes */
 
 	/* everything past this point are written often */
 	u16 next_to_clean;
@@ -621,6 +626,7 @@ struct igb_adapter {
 #define IGB_FLAG_EEE			BIT(14)
 #define IGB_FLAG_VLAN_PROMISC		BIT(15)
 #define IGB_FLAG_RX_LEGACY		BIT(16)
+#define IGB_FLAG_FQTSS			BIT(17)
 
 /* Media Auto Sense */
 #define IGB_MAS_ENABLE_0		0X0001
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index ea69af267d63..e22bce7cdacd 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
+#include <net/pkt_sched.h>
 #include <linux/net_tstamp.h>
 #include <linux/mii.h>
 #include <linux/ethtool.h>
@@ -62,6 +63,17 @@
 #define BUILD 0
 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \
 __stringify(BUILD) "-k"
+
+enum queue_mode {
+	QUEUE_MODE_STRICT_PRIORITY,
+	QUEUE_MODE_STREAM_RESERVATION,
+};
+
+enum tx_queue_prio {
+	TX_QUEUE_PRIO_HIGH,
+	TX_QUEUE_PRIO_LOW,
+};
+
 char igb_driver_name[] = "igb";
 char igb_driver_version[] = DRV_VERSION;
 static const char igb_driver_string[] =
@@ -133,8 +145,8 @@ static void igb_clean_all_rx_rings(struct igb_adapter *);
 static void igb_clean_tx_ring(struct igb_ring *);
 static void igb_clean_rx_ring(struct igb_ring *);
 static void igb_set_rx_mode(struct net_device *);
-static void igb_update_phy_info(unsigned long);
-static void igb_watchdog(unsigned long);
+static void igb_update_phy_info(struct timer_list *);
+static void igb_watchdog(struct timer_list *);
 static void igb_watchdog_task(struct work_struct *);
 static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, struct net_device *);
 static void igb_get_stats64(struct net_device *dev,
@@ -1271,6 +1283,12 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 		ring->count = adapter->tx_ring_count;
 		ring->queue_index = txr_idx;
 
+		ring->cbs_enable = false;
+		ring->idleslope = 0;
+		ring->sendslope = 0;
+		ring->hicredit = 0;
+		ring->locredit = 0;
+
 		u64_stats_init(&ring->tx_syncp);
 		u64_stats_init(&ring->tx_syncp2);
 
@@ -1598,6 +1616,284 @@ static void igb_get_hw_control(struct igb_adapter *adapter)
 			ctrl_ext | E1000_CTRL_EXT_DRV_LOAD);
 }
 
+static void enable_fqtss(struct igb_adapter *adapter, bool enable)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct e1000_hw *hw = &adapter->hw;
+
+	WARN_ON(hw->mac.type != e1000_i210);
+
+	if (enable)
+		adapter->flags |= IGB_FLAG_FQTSS;
+	else
+		adapter->flags &= ~IGB_FLAG_FQTSS;
+
+	if (netif_running(netdev))
+		schedule_work(&adapter->reset_task);
+}
+
+static bool is_fqtss_enabled(struct igb_adapter *adapter)
+{
+	return (adapter->flags & IGB_FLAG_FQTSS) ? true : false;
+}
+
+static void set_tx_desc_fetch_prio(struct e1000_hw *hw, int queue,
+				   enum tx_queue_prio prio)
+{
+	u32 val;
+
+	WARN_ON(hw->mac.type != e1000_i210);
+	WARN_ON(queue < 0 || queue > 4);
+
+	val = rd32(E1000_I210_TXDCTL(queue));
+
+	if (prio == TX_QUEUE_PRIO_HIGH)
+		val |= E1000_TXDCTL_PRIORITY;
+	else
+		val &= ~E1000_TXDCTL_PRIORITY;
+
+	wr32(E1000_I210_TXDCTL(queue), val);
+}
+
+static void set_queue_mode(struct e1000_hw *hw, int queue, enum queue_mode mode)
+{
+	u32 val;
+
+	WARN_ON(hw->mac.type != e1000_i210);
+	WARN_ON(queue < 0 || queue > 1);
+
+	val = rd32(E1000_I210_TQAVCC(queue));
+
+	if (mode == QUEUE_MODE_STREAM_RESERVATION)
+		val |= E1000_TQAVCC_QUEUEMODE;
+	else
+		val &= ~E1000_TQAVCC_QUEUEMODE;
+
+	wr32(E1000_I210_TQAVCC(queue), val);
+}
+
+/**
+ *  igb_configure_cbs - Configure Credit-Based Shaper (CBS)
+ *  @adapter: pointer to adapter struct
+ *  @queue: queue number
+ *  @enable: true = enable CBS, false = disable CBS
+ *  @idleslope: idleSlope in kbps
+ *  @sendslope: sendSlope in kbps
+ *  @hicredit: hiCredit in bytes
+ *  @locredit: loCredit in bytes
+ *
+ *  Configure CBS for a given hardware queue. When disabling, idleslope,
+ *  sendslope, hicredit, locredit arguments are ignored. Returns 0 if
+ *  success. Negative otherwise.
+ **/
+static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
+			      bool enable, int idleslope, int sendslope,
+			      int hicredit, int locredit)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct e1000_hw *hw = &adapter->hw;
+	u32 tqavcc;
+	u16 value;
+
+	WARN_ON(hw->mac.type != e1000_i210);
+	WARN_ON(queue < 0 || queue > 1);
+
+	if (enable) {
+		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
+		set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
+
+		/* According to i210 datasheet section 7.2.7.7, we should set
+		 * the 'idleSlope' field from TQAVCC register following the
+		 * equation:
+		 *
+		 * For 100 Mbps link speed:
+		 *
+		 *     value = BW * 0x7735 * 0.2                          (E1)
+		 *
+		 * For 1000Mbps link speed:
+		 *
+		 *     value = BW * 0x7735 * 2                            (E2)
+		 *
+		 * E1 and E2 can be merged into one equation as shown below.
+		 * Note that 'link-speed' is in Mbps.
+		 *
+		 *     value = BW * 0x7735 * 2 * link-speed
+		 *                           --------------               (E3)
+		 *                                1000
+		 *
+		 * 'BW' is the percentage bandwidth out of full link speed
+		 * which can be found with the following equation. Note that
+		 * idleSlope here is the parameter from this function which
+		 * is in kbps.
+		 *
+		 *     BW =     idleSlope
+		 *          -----------------                             (E4)
+		 *          link-speed * 1000
+		 *
+		 * That said, we can come up with a generic equation to
+		 * calculate the value we should set it TQAVCC register by
+		 * replacing 'BW' in E3 by E4. The resulting equation is:
+		 *
+		 * value =     idleSlope     * 0x7735 * 2 * link-speed
+		 *         -----------------            --------------    (E5)
+		 *         link-speed * 1000                 1000
+		 *
+		 * 'link-speed' is present in both sides of the fraction so
+		 * it is canceled out. The final equation is the following:
+		 *
+		 *     value = idleSlope * 61034
+		 *             -----------------                          (E6)
+		 *                  1000000
+		 */
+		value = DIV_ROUND_UP_ULL(idleslope * 61034ULL, 1000000);
+
+		tqavcc = rd32(E1000_I210_TQAVCC(queue));
+		tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK;
+		tqavcc |= value;
+		wr32(E1000_I210_TQAVCC(queue), tqavcc);
+
+		wr32(E1000_I210_TQAVHC(queue), 0x80000000 + hicredit * 0x7735);
+	} else {
+		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
+		set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
+
+		/* Set idleSlope to zero. */
+		tqavcc = rd32(E1000_I210_TQAVCC(queue));
+		tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK;
+		wr32(E1000_I210_TQAVCC(queue), tqavcc);
+
+		/* Set hiCredit to zero. */
+		wr32(E1000_I210_TQAVHC(queue), 0);
+	}
+
+	/* XXX: In i210 controller the sendSlope and loCredit parameters from
+	 * CBS are not configurable by software so we don't do any 'controller
+	 * configuration' in respect to these parameters.
+	 */
+
+	netdev_dbg(netdev, "CBS %s: queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n",
+		   (enable) ? "enabled" : "disabled", queue,
+		   idleslope, sendslope, hicredit, locredit);
+}
+
+static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
+			       bool enable, int idleslope, int sendslope,
+			       int hicredit, int locredit)
+{
+	struct igb_ring *ring;
+
+	if (queue < 0 || queue > adapter->num_tx_queues)
+		return -EINVAL;
+
+	ring = adapter->tx_ring[queue];
+
+	ring->cbs_enable = enable;
+	ring->idleslope = idleslope;
+	ring->sendslope = sendslope;
+	ring->hicredit = hicredit;
+	ring->locredit = locredit;
+
+	return 0;
+}
+
+static bool is_any_cbs_enabled(struct igb_adapter *adapter)
+{
+	struct igb_ring *ring;
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		ring = adapter->tx_ring[i];
+
+		if (ring->cbs_enable)
+			return true;
+	}
+
+	return false;
+}
+
+static void igb_setup_tx_mode(struct igb_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct e1000_hw *hw = &adapter->hw;
+	u32 val;
+
+	/* Only i210 controller supports changing the transmission mode. */
+	if (hw->mac.type != e1000_i210)
+		return;
+
+	if (is_fqtss_enabled(adapter)) {
+		int i, max_queue;
+
+		/* Configure TQAVCTRL register: set transmit mode to 'Qav',
+		 * set data fetch arbitration to 'round robin' and set data
+		 * transfer arbitration to 'credit shaper algorithm.
+		 */
+		val = rd32(E1000_I210_TQAVCTRL);
+		val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_DATATRANARB;
+		val &= ~E1000_TQAVCTRL_DATAFETCHARB;
+		wr32(E1000_I210_TQAVCTRL, val);
+
+		/* Configure Tx and Rx packet buffers sizes as described in
+		 * i210 datasheet section 7.2.7.7.
+		 */
+		val = rd32(E1000_TXPBS);
+		val &= ~I210_TXPBSIZE_MASK;
+		val |= I210_TXPBSIZE_PB0_8KB | I210_TXPBSIZE_PB1_8KB |
+			I210_TXPBSIZE_PB2_4KB | I210_TXPBSIZE_PB3_4KB;
+		wr32(E1000_TXPBS, val);
+
+		val = rd32(E1000_RXPBS);
+		val &= ~I210_RXPBSIZE_MASK;
+		val |= I210_RXPBSIZE_PB_32KB;
+		wr32(E1000_RXPBS, val);
+
+		/* Section 8.12.9 states that MAX_TPKT_SIZE from DTXMXPKTSZ
+		 * register should not exceed the buffer size programmed in
+		 * TXPBS. The smallest buffer size programmed in TXPBS is 4kB
+		 * so according to the datasheet we should set MAX_TPKT_SIZE to
+		 * 4kB / 64.
+		 *
+		 * However, when we do so, no frame from queue 2 and 3 are
+		 * transmitted.  It seems the MAX_TPKT_SIZE should not be great
+		 * or _equal_ to the buffer size programmed in TXPBS. For this
+		 * reason, we set set MAX_ TPKT_SIZE to (4kB - 1) / 64.
+		 */
+		val = (4096 - 1) / 64;
+		wr32(E1000_I210_DTXMXPKTSZ, val);
+
+		/* Since FQTSS mode is enabled, apply any CBS configuration
+		 * previously set. If no previous CBS configuration has been
+		 * done, then the initial configuration is applied, which means
+		 * CBS is disabled.
+		 */
+		max_queue = (adapter->num_tx_queues < I210_SR_QUEUES_NUM) ?
+			    adapter->num_tx_queues : I210_SR_QUEUES_NUM;
+
+		for (i = 0; i < max_queue; i++) {
+			struct igb_ring *ring = adapter->tx_ring[i];
+
+			igb_configure_cbs(adapter, i, ring->cbs_enable,
+					  ring->idleslope, ring->sendslope,
+					  ring->hicredit, ring->locredit);
+		}
+	} else {
+		wr32(E1000_RXPBS, I210_RXPBSIZE_DEFAULT);
+		wr32(E1000_TXPBS, I210_TXPBSIZE_DEFAULT);
+		wr32(E1000_I210_DTXMXPKTSZ, I210_DTXMXPKTSZ_DEFAULT);
+
+		val = rd32(E1000_I210_TQAVCTRL);
+		/* According to Section 8.12.21, the other flags we've set when
+		 * enabling FQTSS are not relevant when disabling FQTSS so we
+		 * don't set they here.
+		 */
+		val &= ~E1000_TQAVCTRL_XMIT_MODE;
+		wr32(E1000_I210_TQAVCTRL, val);
+	}
+
+	netdev_dbg(netdev, "FQTSS %s\n", (is_fqtss_enabled(adapter)) ?
+		   "enabled" : "disabled");
+}
+
 /**
  *  igb_configure - configure the hardware for RX and TX
  *  @adapter: private board structure
@@ -1609,6 +1905,7 @@ static void igb_configure(struct igb_adapter *adapter)
 
 	igb_get_hw_control(adapter);
 	igb_set_rx_mode(netdev);
+	igb_setup_tx_mode(adapter);
 
 	igb_restore_vlan(adapter);
 
@@ -2150,6 +2447,55 @@ igb_features_check(struct sk_buff *skb, struct net_device *dev,
 	return features;
 }
 
+static int igb_offload_cbs(struct igb_adapter *adapter,
+			   struct tc_cbs_qopt_offload *qopt)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	int err;
+
+	/* CBS offloading is only supported by i210 controller. */
+	if (hw->mac.type != e1000_i210)
+		return -EOPNOTSUPP;
+
+	/* CBS offloading is only supported by queue 0 and queue 1. */
+	if (qopt->queue < 0 || qopt->queue > 1)
+		return -EINVAL;
+
+	err = igb_save_cbs_params(adapter, qopt->queue, qopt->enable,
+				  qopt->idleslope, qopt->sendslope,
+				  qopt->hicredit, qopt->locredit);
+	if (err)
+		return err;
+
+	if (is_fqtss_enabled(adapter)) {
+		igb_configure_cbs(adapter, qopt->queue, qopt->enable,
+				  qopt->idleslope, qopt->sendslope,
+				  qopt->hicredit, qopt->locredit);
+
+		if (!is_any_cbs_enabled(adapter))
+			enable_fqtss(adapter, false);
+
+	} else {
+		enable_fqtss(adapter, true);
+	}
+
+	return 0;
+}
+
+static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
+			void *type_data)
+{
+	struct igb_adapter *adapter = netdev_priv(dev);
+
+	switch (type) {
+	case TC_SETUP_CBS:
+		return igb_offload_cbs(adapter, type_data);
+
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops igb_netdev_ops = {
 	.ndo_open		= igb_open,
 	.ndo_stop		= igb_close,
@@ -2175,6 +2521,7 @@ static const struct net_device_ops igb_netdev_ops = {
 	.ndo_set_features	= igb_set_features,
 	.ndo_fdb_add		= igb_ndo_fdb_add,
 	.ndo_features_check	= igb_features_check,
+	.ndo_setup_tc		= igb_setup_tc,
 };
 
 /**
@@ -2538,10 +2885,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		wr32(E1000_TXPBS, I210_TXPBSIZE_DEFAULT);
 	}
 
-	setup_timer(&adapter->watchdog_timer, igb_watchdog,
-		    (unsigned long) adapter);
-	setup_timer(&adapter->phy_info_timer, igb_update_phy_info,
-		    (unsigned long) adapter);
+	timer_setup(&adapter->watchdog_timer, igb_watchdog, 0);
+	timer_setup(&adapter->phy_info_timer, igb_update_phy_info, 0);
 
 	INIT_WORK(&adapter->reset_task, igb_reset_task);
 	INIT_WORK(&adapter->watchdog_task, igb_watchdog_task);
@@ -3162,6 +3507,8 @@ static int igb_sw_init(struct igb_adapter *adapter)
 	/* Setup and initialize a copy of the hw vlan table array */
 	adapter->shadow_vfta = kcalloc(E1000_VLAN_FILTER_TBL_SIZE, sizeof(u32),
 				       GFP_ATOMIC);
+	if (!adapter->shadow_vfta)
+		return -ENOMEM;
 
 	/* This call may decrease the number of queues */
 	if (igb_init_interrupt_scheme(adapter, true)) {
@@ -4423,9 +4770,9 @@ static void igb_spoof_check(struct igb_adapter *adapter)
 /* Need to wait a few seconds after link up to get diagnostic information from
  * the phy
  */
-static void igb_update_phy_info(unsigned long data)
+static void igb_update_phy_info(struct timer_list *t)
 {
-	struct igb_adapter *adapter = (struct igb_adapter *) data;
+	struct igb_adapter *adapter = from_timer(adapter, t, phy_info_timer);
 	igb_get_phy_info(&adapter->hw);
 }
 
@@ -4512,9 +4859,9 @@ static void igb_check_lvmmc(struct igb_adapter *adapter)
  *  igb_watchdog - Timer Call-back
  *  @data: pointer to adapter cast into an unsigned long
  **/
-static void igb_watchdog(unsigned long data)
+static void igb_watchdog(struct timer_list *t)
 {
-	struct igb_adapter *adapter = (struct igb_adapter *)data;
+	struct igb_adapter *adapter = from_timer(adapter, t, watchdog_timer);
 	/* Do the rest outside of interrupt context */
 	schedule_work(&adapter->watchdog_task);
 }
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 1ed556911b14..713e8df23744 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -1915,9 +1915,9 @@ static bool igbvf_has_link(struct igbvf_adapter *adapter)
  * igbvf_watchdog - Timer Call-back
  * @data: pointer to adapter cast into an unsigned long
  **/
-static void igbvf_watchdog(unsigned long data)
+static void igbvf_watchdog(struct timer_list *t)
 {
-	struct igbvf_adapter *adapter = (struct igbvf_adapter *)data;
+	struct igbvf_adapter *adapter = from_timer(adapter, t, watchdog_timer);
 
 	/* Do the rest outside of interrupt context */
 	schedule_work(&adapter->watchdog_task);
@@ -2878,8 +2878,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		       netdev->addr_len);
 	}
 
-	setup_timer(&adapter->watchdog_timer, &igbvf_watchdog,
-		    (unsigned long)adapter);
+	timer_setup(&adapter->watchdog_timer, igbvf_watchdog, 0);
 
 	INIT_WORK(&adapter->reset_task, igbvf_reset_task);
 	INIT_WORK(&adapter->watchdog_task, igbvf_watchdog_task);
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index 5a713199653c..2353c383f0a7 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -83,7 +83,7 @@ static void ixgb_setup_rctl(struct ixgb_adapter *adapter);
 static void ixgb_clean_tx_ring(struct ixgb_adapter *adapter);
 static void ixgb_clean_rx_ring(struct ixgb_adapter *adapter);
 static void ixgb_set_multi(struct net_device *netdev);
-static void ixgb_watchdog(unsigned long data);
+static void ixgb_watchdog(struct timer_list *t);
 static netdev_tx_t ixgb_xmit_frame(struct sk_buff *skb,
 				   struct net_device *netdev);
 static int ixgb_change_mtu(struct net_device *netdev, int new_mtu);
@@ -508,9 +508,7 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	adapter->part_num = ixgb_get_ee_pba_number(&adapter->hw);
 
-	init_timer(&adapter->watchdog_timer);
-	adapter->watchdog_timer.function = ixgb_watchdog;
-	adapter->watchdog_timer.data = (unsigned long)adapter;
+	timer_setup(&adapter->watchdog_timer, ixgb_watchdog, 0);
 
 	INIT_WORK(&adapter->tx_timeout_task, ixgb_tx_timeout_task);
 
@@ -1152,9 +1150,9 @@ alloc_failed:
  **/
 
 static void
-ixgb_watchdog(unsigned long data)
+ixgb_watchdog(struct timer_list *t)
 {
-	struct ixgb_adapter *adapter = (struct ixgb_adapter *)data;
+	struct ixgb_adapter *adapter = from_timer(adapter, t, watchdog_timer);
 	struct net_device *netdev = adapter->netdev;
 	struct ixgb_desc_ring *txdr = &adapter->tx_ring;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index dd5578756ae0..468c3555a629 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -275,6 +275,7 @@ struct ixgbe_rx_queue_stats {
 	u64 rsc_count;
 	u64 rsc_flush;
 	u64 non_eop_descs;
+	u64 alloc_rx_page;
 	u64 alloc_rx_page_failed;
 	u64 alloc_rx_buff_failed;
 	u64 csum_err;
@@ -434,8 +435,15 @@ static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring)
 }
 #define ixgbe_rx_pg_size(_ring) (PAGE_SIZE << ixgbe_rx_pg_order(_ring))
 
+#define IXGBE_ITR_ADAPTIVE_MIN_INC	2
+#define IXGBE_ITR_ADAPTIVE_MIN_USECS	10
+#define IXGBE_ITR_ADAPTIVE_MAX_USECS	126
+#define IXGBE_ITR_ADAPTIVE_LATENCY	0x80
+#define IXGBE_ITR_ADAPTIVE_BULK		0x00
+
 struct ixgbe_ring_container {
 	struct ixgbe_ring *ring;	/* pointer to linked list of rings */
+	unsigned long next_update;	/* jiffies value of last update */
 	unsigned int total_bytes;	/* total bytes processed this int */
 	unsigned int total_packets;	/* total packets processed this int */
 	u16 work_limit;			/* total work allowed per interrupt */
@@ -655,6 +663,7 @@ struct ixgbe_adapter {
 	u64 rsc_total_count;
 	u64 rsc_total_flush;
 	u64 non_eop_descs;
+	u32 alloc_rx_page;
 	u32 alloc_rx_page_failed;
 	u32 alloc_rx_buff_failed;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 6e6ab6f6875e..9bef255f6a18 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -3781,10 +3781,10 @@ s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min,
 	fw_cmd.ver_build = build;
 	fw_cmd.ver_sub = sub;
 	fw_cmd.hdr.checksum = 0;
-	fw_cmd.hdr.checksum = ixgbe_calculate_checksum((u8 *)&fw_cmd,
-				(FW_CEM_HDR_LEN + fw_cmd.hdr.buf_len));
 	fw_cmd.pad = 0;
 	fw_cmd.pad2 = 0;
+	fw_cmd.hdr.checksum = ixgbe_calculate_checksum((u8 *)&fw_cmd,
+				(FW_CEM_HDR_LEN + fw_cmd.hdr.buf_len));
 
 	for (i = 0; i <= FW_CEM_MAX_RETRIES; i++) {
 		ret_val = ixgbe_host_interface_command(hw, &fw_cmd,
@@ -4081,8 +4081,8 @@ bool ixgbe_mng_present(struct ixgbe_hw *hw)
 		return false;
 
 	fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
-	fwsm &= IXGBE_FWSM_MODE_MASK;
-	return fwsm == IXGBE_FWSM_FW_MODE_PT;
+
+	return !!(fwsm & IXGBE_FWSM_FW_MODE_PT);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index c3e7a8191128..0aad1c2a3667 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -104,6 +104,7 @@ static const struct ixgbe_stats ixgbe_gstrings_stats[] = {
 	{"tx_flow_control_xoff", IXGBE_STAT(stats.lxofftxc)},
 	{"rx_flow_control_xoff", IXGBE_STAT(stats.lxoffrxc)},
 	{"rx_csum_offload_errors", IXGBE_STAT(hw_csum_rx_error)},
+	{"alloc_rx_page", IXGBE_STAT(alloc_rx_page)},
 	{"alloc_rx_page_failed", IXGBE_STAT(alloc_rx_page_failed)},
 	{"alloc_rx_buff_failed", IXGBE_STAT(alloc_rx_buff_failed)},
 	{"rx_no_dma_resources", IXGBE_STAT(hw_rx_no_dma_resources)},
@@ -1916,8 +1917,6 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring,
 				  unsigned int size)
 {
 	union ixgbe_adv_rx_desc *rx_desc;
-	struct ixgbe_rx_buffer *rx_buffer;
-	struct ixgbe_tx_buffer *tx_buffer;
 	u16 rx_ntc, tx_ntc, count = 0;
 
 	/* initialize next to clean and descriptor values */
@@ -1925,7 +1924,38 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring,
 	tx_ntc = tx_ring->next_to_clean;
 	rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc);
 
+	while (tx_ntc != tx_ring->next_to_use) {
+		union ixgbe_adv_tx_desc *tx_desc;
+		struct ixgbe_tx_buffer *tx_buffer;
+
+		tx_desc = IXGBE_TX_DESC(tx_ring, tx_ntc);
+
+		/* if DD is not set transmit has not completed */
+		if (!(tx_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))
+			return count;
+
+		/* unmap buffer on Tx side */
+		tx_buffer = &tx_ring->tx_buffer_info[tx_ntc];
+
+		/* Free all the Tx ring sk_buffs */
+		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);
+		dma_unmap_len_set(tx_buffer, len, 0);
+
+		/* increment Tx next to clean counter */
+		tx_ntc++;
+		if (tx_ntc == tx_ring->count)
+			tx_ntc = 0;
+	}
+
 	while (rx_desc->wb.upper.length) {
+		struct ixgbe_rx_buffer *rx_buffer;
+
 		/* check Rx buffer */
 		rx_buffer = &rx_ring->rx_buffer_info[rx_ntc];
 
@@ -1938,6 +1968,8 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring,
 		/* verify contents of skb */
 		if (ixgbe_check_lbtest_frame(rx_buffer, size))
 			count++;
+		else
+			break;
 
 		/* sync Rx buffer for device write */
 		dma_sync_single_for_device(rx_ring->dev,
@@ -1945,26 +1977,10 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring,
 					   ixgbe_rx_bufsz(rx_ring),
 					   DMA_FROM_DEVICE);
 
-		/* unmap buffer on Tx side */
-		tx_buffer = &tx_ring->tx_buffer_info[tx_ntc];
-
-		/* Free all the Tx ring sk_buffs */
-		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);
-		dma_unmap_len_set(tx_buffer, len, 0);
-
-		/* increment Rx/Tx next to clean counters */
+		/* increment Rx next to clean counter */
 		rx_ntc++;
 		if (rx_ntc == rx_ring->count)
 			rx_ntc = 0;
-		tx_ntc++;
-		if (tx_ntc == tx_ring->count)
-			tx_ntc = 0;
 
 		/* fetch next descriptor */
 		rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index f1bfae0c41d0..8e2a957aca18 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -806,6 +806,7 @@ static void ixgbe_add_ring(struct ixgbe_ring *ring,
 	ring->next = head->ring;
 	head->ring = ring;
 	head->count++;
+	head->next_update = jiffies + 1;
 }
 
 /**
@@ -879,8 +880,11 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 	/* initialize work limits */
 	q_vector->tx.work_limit = adapter->tx_work_limit;
 
-	/* initialize pointer to rings */
-	ring = q_vector->ring;
+	/* Initialize setting for adaptive ITR */
+	q_vector->tx.itr = IXGBE_ITR_ADAPTIVE_MAX_USECS |
+			   IXGBE_ITR_ADAPTIVE_LATENCY;
+	q_vector->rx.itr = IXGBE_ITR_ADAPTIVE_MAX_USECS |
+			   IXGBE_ITR_ADAPTIVE_LATENCY;
 
 	/* intialize ITR */
 	if (txr_count && !rxr_count) {
@@ -897,6 +901,9 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 			q_vector->itr = adapter->rx_itr_setting;
 	}
 
+	/* initialize pointer to rings */
+	ring = q_vector->ring;
+
 	while (txr_count) {
 		/* assign generic ring traits */
 		ring->dev = &adapter->pdev->dev;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 6d5f31e94358..507977994a03 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1620,6 +1620,7 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
 	bi->page = page;
 	bi->page_offset = ixgbe_rx_offset(rx_ring);
 	bi->pagecnt_bias = 1;
+	rx_ring->rx_stats.alloc_rx_page++;
 
 	return true;
 }
@@ -2133,6 +2134,21 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
 #if L1_CACHE_BYTES < 128
 	prefetch(xdp->data + L1_CACHE_BYTES);
 #endif
+	/* Note, we get here by enabling legacy-rx via:
+	 *
+	 *    ethtool --set-priv-flags <dev> legacy-rx on
+	 *
+	 * In this mode, we currently get 0 extra XDP headroom as
+	 * opposed to having legacy-rx off, where we process XDP
+	 * packets going to stack via ixgbe_build_skb(). The latter
+	 * provides us currently with 192 bytes of headroom.
+	 *
+	 * For ixgbe_construct_skb() mode it means that the
+	 * xdp->data_meta will always point to xdp->data, since
+	 * the helper cannot expand the head. Should this ever
+	 * change in future for legacy-rx mode on, then lets also
+	 * add xdp->data_meta handling here.
+	 */
 
 	/* allocate a skb to store the frags */
 	skb = napi_alloc_skb(&rx_ring->q_vector->napi, IXGBE_RX_HDR_SIZE);
@@ -2165,6 +2181,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 				       struct xdp_buff *xdp,
 				       union ixgbe_adv_rx_desc *rx_desc)
 {
+	unsigned int metasize = xdp->data - xdp->data_meta;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
 #else
@@ -2174,10 +2191,14 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 #endif
 	struct sk_buff *skb;
 
-	/* prefetch first cache line of first page */
-	prefetch(xdp->data);
+	/* Prefetch first cache line of first page. If xdp->data_meta
+	 * is unused, this points extactly as xdp->data, otherwise we
+	 * likely have a consumer accessing first few bytes of meta
+	 * data, and then actual data.
+	 */
+	prefetch(xdp->data_meta);
 #if L1_CACHE_BYTES < 128
-	prefetch(xdp->data + L1_CACHE_BYTES);
+	prefetch(xdp->data_meta + L1_CACHE_BYTES);
 #endif
 
 	/* build an skb to around the page buffer */
@@ -2188,6 +2209,8 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 	/* update pointers within the skb to store the data */
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	__skb_put(skb, xdp->data_end - xdp->data);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 
 	/* record DMA address if this is the start of a chain of buffers */
 	if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
@@ -2326,6 +2349,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		if (!skb) {
 			xdp.data = page_address(rx_buffer->page) +
 				   rx_buffer->page_offset;
+			xdp.data_meta = xdp.data;
 			xdp.data_hard_start = xdp.data -
 					      ixgbe_rx_offset(rx_ring);
 			xdp.data_end = xdp.data + size;
@@ -2516,50 +2540,174 @@ enum latency_range {
 static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector,
 			     struct ixgbe_ring_container *ring_container)
 {
-	int bytes = ring_container->total_bytes;
-	int packets = ring_container->total_packets;
-	u32 timepassed_us;
-	u64 bytes_perint;
-	u8 itr_setting = ring_container->itr;
+	unsigned int itr = IXGBE_ITR_ADAPTIVE_MIN_USECS |
+			   IXGBE_ITR_ADAPTIVE_LATENCY;
+	unsigned int avg_wire_size, packets, bytes;
+	unsigned long next_update = jiffies;
 
-	if (packets == 0)
+	/* If we don't have any rings just leave ourselves set for maximum
+	 * possible latency so we take ourselves out of the equation.
+	 */
+	if (!ring_container->ring)
 		return;
 
-	/* simple throttlerate management
-	 *   0-10MB/s   lowest (100000 ints/s)
-	 *  10-20MB/s   low    (20000 ints/s)
-	 *  20-1249MB/s bulk   (12000 ints/s)
+	/* If we didn't update within up to 1 - 2 jiffies we can assume
+	 * that either packets are coming in so slow there hasn't been
+	 * any work, or that there is so much work that NAPI is dealing
+	 * with interrupt moderation and we don't need to do anything.
 	 */
-	/* what was last interrupt timeslice? */
-	timepassed_us = q_vector->itr >> 2;
-	if (timepassed_us == 0)
-		return;
+	if (time_after(next_update, ring_container->next_update))
+		goto clear_counts;
 
-	bytes_perint = bytes / timepassed_us; /* bytes/usec */
+	packets = ring_container->total_packets;
 
-	switch (itr_setting) {
-	case lowest_latency:
-		if (bytes_perint > 10)
-			itr_setting = low_latency;
-		break;
-	case low_latency:
-		if (bytes_perint > 20)
-			itr_setting = bulk_latency;
-		else if (bytes_perint <= 10)
-			itr_setting = lowest_latency;
+	/* We have no packets to actually measure against. This means
+	 * either one of the other queues on this vector is active or
+	 * we are a Tx queue doing TSO with too high of an interrupt rate.
+	 *
+	 * When this occurs just tick up our delay by the minimum value
+	 * and hope that this extra delay will prevent us from being called
+	 * without any work on our queue.
+	 */
+	if (!packets) {
+		itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC;
+		if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS)
+			itr = IXGBE_ITR_ADAPTIVE_MAX_USECS;
+		itr += ring_container->itr & IXGBE_ITR_ADAPTIVE_LATENCY;
+		goto clear_counts;
+	}
+
+	bytes = ring_container->total_bytes;
+
+	/* If packets are less than 4 or bytes are less than 9000 assume
+	 * insufficient data to use bulk rate limiting approach. We are
+	 * likely latency driven.
+	 */
+	if (packets < 4 && bytes < 9000) {
+		itr = IXGBE_ITR_ADAPTIVE_LATENCY;
+		goto adjust_by_size;
+	}
+
+	/* Between 4 and 48 we can assume that our current interrupt delay
+	 * is only slightly too low. As such we should increase it by a small
+	 * fixed amount.
+	 */
+	if (packets < 48) {
+		itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC;
+		if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS)
+			itr = IXGBE_ITR_ADAPTIVE_MAX_USECS;
+		goto clear_counts;
+	}
+
+	/* Between 48 and 96 is our "goldilocks" zone where we are working
+	 * out "just right". Just report that our current ITR is good for us.
+	 */
+	if (packets < 96) {
+		itr = q_vector->itr >> 2;
+		goto clear_counts;
+	}
+
+	/* If packet count is 96 or greater we are likely looking at a slight
+	 * overrun of the delay we want. Try halving our delay to see if that
+	 * will cut the number of packets in half per interrupt.
+	 */
+	if (packets < 256) {
+		itr = q_vector->itr >> 3;
+		if (itr < IXGBE_ITR_ADAPTIVE_MIN_USECS)
+			itr = IXGBE_ITR_ADAPTIVE_MIN_USECS;
+		goto clear_counts;
+	}
+
+	/* The paths below assume we are dealing with a bulk ITR since number
+	 * of packets is 256 or greater. We are just going to have to compute
+	 * a value and try to bring the count under control, though for smaller
+	 * packet sizes there isn't much we can do as NAPI polling will likely
+	 * be kicking in sooner rather than later.
+	 */
+	itr = IXGBE_ITR_ADAPTIVE_BULK;
+
+adjust_by_size:
+	/* If packet counts are 256 or greater we can assume we have a gross
+	 * overestimation of what the rate should be. Instead of trying to fine
+	 * tune it just use the formula below to try and dial in an exact value
+	 * give the current packet size of the frame.
+	 */
+	avg_wire_size = bytes / packets;
+
+	/* The following is a crude approximation of:
+	 *  wmem_default / (size + overhead) = desired_pkts_per_int
+	 *  rate / bits_per_byte / (size + ethernet overhead) = pkt_rate
+	 *  (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value
+	 *
+	 * Assuming wmem_default is 212992 and overhead is 640 bytes per
+	 * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the
+	 * formula down to
+	 *
+	 *  (170 * (size + 24)) / (size + 640) = ITR
+	 *
+	 * We first do some math on the packet size and then finally bitshift
+	 * by 8 after rounding up. We also have to account for PCIe link speed
+	 * difference as ITR scales based on this.
+	 */
+	if (avg_wire_size <= 60) {
+		/* Start at 50k ints/sec */
+		avg_wire_size = 5120;
+	} else if (avg_wire_size <= 316) {
+		/* 50K ints/sec to 16K ints/sec */
+		avg_wire_size *= 40;
+		avg_wire_size += 2720;
+	} else if (avg_wire_size <= 1084) {
+		/* 16K ints/sec to 9.2K ints/sec */
+		avg_wire_size *= 15;
+		avg_wire_size += 11452;
+	} else if (avg_wire_size <= 1980) {
+		/* 9.2K ints/sec to 8K ints/sec */
+		avg_wire_size *= 5;
+		avg_wire_size += 22420;
+	} else {
+		/* plateau at a limit of 8K ints/sec */
+		avg_wire_size = 32256;
+	}
+
+	/* If we are in low latency mode half our delay which doubles the rate
+	 * to somewhere between 100K to 16K ints/sec
+	 */
+	if (itr & IXGBE_ITR_ADAPTIVE_LATENCY)
+		avg_wire_size >>= 1;
+
+	/* Resultant value is 256 times larger than it needs to be. This
+	 * gives us room to adjust the value as needed to either increase
+	 * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc.
+	 *
+	 * Use addition as we have already recorded the new latency flag
+	 * for the ITR value.
+	 */
+	switch (q_vector->adapter->link_speed) {
+	case IXGBE_LINK_SPEED_10GB_FULL:
+	case IXGBE_LINK_SPEED_100_FULL:
+	default:
+		itr += DIV_ROUND_UP(avg_wire_size,
+				    IXGBE_ITR_ADAPTIVE_MIN_INC * 256) *
+		       IXGBE_ITR_ADAPTIVE_MIN_INC;
 		break;
-	case bulk_latency:
-		if (bytes_perint <= 20)
-			itr_setting = low_latency;
+	case IXGBE_LINK_SPEED_2_5GB_FULL:
+	case IXGBE_LINK_SPEED_1GB_FULL:
+	case IXGBE_LINK_SPEED_10_FULL:
+		itr += DIV_ROUND_UP(avg_wire_size,
+				    IXGBE_ITR_ADAPTIVE_MIN_INC * 64) *
+		       IXGBE_ITR_ADAPTIVE_MIN_INC;
 		break;
 	}
 
-	/* clear work counters since we have the values we need */
+clear_counts:
+	/* write back value */
+	ring_container->itr = itr;
+
+	/* next update should occur within next jiffy */
+	ring_container->next_update = next_update + 1;
+
 	ring_container->total_bytes = 0;
 	ring_container->total_packets = 0;
-
-	/* write updated itr to ring container */
-	ring_container->itr = itr_setting;
 }
 
 /**
@@ -2601,34 +2749,19 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector)
 
 static void ixgbe_set_itr(struct ixgbe_q_vector *q_vector)
 {
-	u32 new_itr = q_vector->itr;
-	u8 current_itr;
+	u32 new_itr;
 
 	ixgbe_update_itr(q_vector, &q_vector->tx);
 	ixgbe_update_itr(q_vector, &q_vector->rx);
 
-	current_itr = max(q_vector->rx.itr, q_vector->tx.itr);
+	/* use the smallest value of new ITR delay calculations */
+	new_itr = min(q_vector->rx.itr, q_vector->tx.itr);
 
-	switch (current_itr) {
-	/* counts and packets in update_itr are dependent on these numbers */
-	case lowest_latency:
-		new_itr = IXGBE_100K_ITR;
-		break;
-	case low_latency:
-		new_itr = IXGBE_20K_ITR;
-		break;
-	case bulk_latency:
-		new_itr = IXGBE_12K_ITR;
-		break;
-	default:
-		break;
-	}
+	/* Clear latency flag if set, shift into correct position */
+	new_itr &= ~IXGBE_ITR_ADAPTIVE_LATENCY;
+	new_itr <<= 2;
 
 	if (new_itr != q_vector->itr) {
-		/* do an exponential smoothing */
-		new_itr = (10 * new_itr * q_vector->itr) /
-			  ((9 * new_itr) + q_vector->itr);
-
 		/* save the algorithm value here */
 		q_vector->itr = new_itr;
 
@@ -6771,6 +6904,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	u32 i, missed_rx = 0, mpc, bprc, lxon, lxoff, xon_off_tot;
 	u64 non_eop_descs = 0, restart_queue = 0, tx_busy = 0;
 	u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0;
+	u64 alloc_rx_page = 0;
 	u64 bytes = 0, packets = 0, hw_csum_rx_error = 0;
 
 	if (test_bit(__IXGBE_DOWN, &adapter->state) ||
@@ -6791,6 +6925,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		struct ixgbe_ring *rx_ring = adapter->rx_ring[i];
 		non_eop_descs += rx_ring->rx_stats.non_eop_descs;
+		alloc_rx_page += rx_ring->rx_stats.alloc_rx_page;
 		alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed;
 		alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed;
 		hw_csum_rx_error += rx_ring->rx_stats.csum_err;
@@ -6798,6 +6933,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 		packets += rx_ring->stats.packets;
 	}
 	adapter->non_eop_descs = non_eop_descs;
+	adapter->alloc_rx_page = alloc_rx_page;
 	adapter->alloc_rx_page_failed = alloc_rx_page_failed;
 	adapter->alloc_rx_buff_failed = alloc_rx_buff_failed;
 	adapter->hw_csum_rx_error = hw_csum_rx_error;
@@ -7554,9 +7690,9 @@ static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter)
  * ixgbe_service_timer - Timer Call-back
  * @data: pointer to adapter cast into an unsigned long
  **/
-static void ixgbe_service_timer(unsigned long data)
+static void ixgbe_service_timer(struct timer_list *t)
 {
-	struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)data;
+	struct ixgbe_adapter *adapter = from_timer(adapter, t, service_timer);
 	unsigned long next_event_offset;
 
 	/* poll faster when waiting for link */
@@ -9223,13 +9359,10 @@ free_jump:
 	return err;
 }
 
-static int ixgbe_setup_tc_cls_u32(struct net_device *dev,
+static int ixgbe_setup_tc_cls_u32(struct ixgbe_adapter *adapter,
 				  struct tc_cls_u32_offload *cls_u32)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
-
-	if (!is_classid_clsact_ingress(cls_u32->common.classid) ||
-	    cls_u32->common.chain_index)
+	if (cls_u32->common.chain_index)
 		return -EOPNOTSUPP;
 
 	switch (cls_u32->command) {
@@ -9248,6 +9381,43 @@ static int ixgbe_setup_tc_cls_u32(struct net_device *dev,
 	}
 }
 
+static int ixgbe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				   void *cb_priv)
+{
+	struct ixgbe_adapter *adapter = cb_priv;
+
+	if (!tc_can_offload(adapter->netdev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSU32:
+		return ixgbe_setup_tc_cls_u32(adapter, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int ixgbe_setup_tc_block(struct net_device *dev,
+				struct tc_block_offload *f)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb,
+					     adapter, adapter);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb,
+					adapter);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int ixgbe_setup_tc_mqprio(struct net_device *dev,
 				 struct tc_mqprio_qopt *mqprio)
 {
@@ -9259,8 +9429,8 @@ static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			    void *type_data)
 {
 	switch (type) {
-	case TC_SETUP_CLSU32:
-		return ixgbe_setup_tc_cls_u32(dev, type_data);
+	case TC_SETUP_BLOCK:
+		return ixgbe_setup_tc_block(dev, type_data);
 	case TC_SETUP_MQPRIO:
 		return ixgbe_setup_tc_mqprio(dev, type_data);
 	default:
@@ -9733,6 +9903,17 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 	limit = find_last_bit(&adapter->fwd_bitmask, 32);
 	adapter->ring_feature[RING_F_VMDQ].limit = limit + 1;
 	ixgbe_fwd_ring_down(fwd_adapter->netdev, fwd_adapter);
+
+	/* go back to full RSS if we're done with our VMQs */
+	if (adapter->ring_feature[RING_F_VMDQ].limit == 1) {
+		int rss = min_t(int, ixgbe_max_rss_indices(adapter),
+				num_online_cpus());
+
+		adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED;
+		adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
+		adapter->ring_feature[RING_F_RSS].limit = rss;
+	}
+
 	ixgbe_setup_tc(pdev, netdev_get_num_tc(pdev));
 	netdev_dbg(pdev, "pool %i:%i queues %i:%i VSI bitmask %lx\n",
 		   fwd_adapter->pool, adapter->num_rx_pools,
@@ -10355,8 +10536,7 @@ skip_sriov:
 	ether_addr_copy(hw->mac.addr, hw->mac.perm_addr);
 	ixgbe_mac_set_default_filter(adapter);
 
-	setup_timer(&adapter->service_timer, &ixgbe_service_timer,
-		    (unsigned long) adapter);
+	timer_setup(&adapter->service_timer, ixgbe_service_timer, 0);
 
 	if (ixgbe_removed(hw->hw_addr)) {
 		err = -EIO;
@@ -10712,6 +10892,9 @@ skip_bad_vf_detection:
 	if (!test_bit(__IXGBE_SERVICE_INITED, &adapter->state))
 		return PCI_ERS_RESULT_DISCONNECT;
 
+	if (!netif_device_present(netdev))
+		return PCI_ERS_RESULT_DISCONNECT;
+
 	rtnl_lock();
 	netif_device_detach(netdev);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
index 6ea0d6a5fb90..b8c5fd2a2115 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
@@ -619,12 +619,6 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask)
 		usleep_range(5000, 10000);
 	}
 
-	/* Failed to get SW only semaphore */
-	if (swmask == IXGBE_GSSR_SW_MNG_SM) {
-		hw_dbg(hw, "Failed to get SW only semaphore\n");
-		return IXGBE_ERR_SWFW_SYNC;
-	}
-
 	/* If the resource is not released by the FW/HW the SW can assume that
 	 * the FW/HW malfunctions. In that case the SW should set the SW bit(s)
 	 * of the requested resource(s) while ignoring the corresponding FW/HW
@@ -647,7 +641,8 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask)
 	 */
 	if (swfw_sync & swmask) {
 		u32 rmask = IXGBE_GSSR_EEP_SM | IXGBE_GSSR_PHY0_SM |
-			    IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM;
+			    IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM |
+			    IXGBE_GSSR_SW_MNG_SM;
 
 		if (swi2c_mask)
 			rmask |= IXGBE_GSSR_I2C_MASK;
@@ -763,6 +758,8 @@ static void ixgbe_release_swfw_sync_semaphore(struct ixgbe_hw *hw)
  **/
 void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw)
 {
+	u32 rmask;
+
 	/* First try to grab the semaphore but we don't need to bother
 	 * looking to see whether we got the lock or not since we do
 	 * the same thing regardless of whether we got the lock or not.
@@ -771,6 +768,14 @@ void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw)
 	 */
 	ixgbe_get_swfw_sync_semaphore(hw);
 	ixgbe_release_swfw_sync_semaphore(hw);
+
+	/* Acquire and release all software resources. */
+	rmask = IXGBE_GSSR_EEP_SM | IXGBE_GSSR_PHY0_SM |
+		IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM |
+		IXGBE_GSSR_SW_MNG_SM | IXGBE_GSSR_I2C_MASK;
+
+	ixgbe_acquire_swfw_sync_X540(hw, rmask);
+	ixgbe_release_swfw_sync_X540(hw, rmask);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 19fbb2f28ea4..cb7da5f9c4da 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -900,6 +900,8 @@ static s32 ixgbe_read_ee_hostif_buffer_X550(struct ixgbe_hw *hw,
 		/* convert offset from words to bytes */
 		buffer.address = cpu_to_be32((offset + current_word) * 2);
 		buffer.length = cpu_to_be16(words_to_read * 2);
+		buffer.pad2 = 0;
+		buffer.pad3 = 0;
 
 		status = ixgbe_hic_unlocked(hw, (u32 *)&buffer, sizeof(buffer),
 					    IXGBE_HI_COMMAND_TIMEOUT);
@@ -3192,6 +3194,9 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw)
 
 	/* Identify the PHY or SFP module */
 	ret_val = phy->ops.identify(hw);
+	if (ret_val == IXGBE_ERR_SFP_NOT_SUPPORTED ||
+	    ret_val == IXGBE_ERR_PHY_ADDR_INVALID)
+		return ret_val;
 
 	/* Setup function pointers based on detected hardware */
 	ixgbe_init_mac_link_ops_X550em(hw);
@@ -3394,9 +3399,10 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw)
 	ixgbe_clear_tx_pending(hw);
 
 	/* PHY ops must be identified and initialized prior to reset */
-
-	/* Identify PHY and related function pointers */
 	status = hw->phy.ops.init(hw);
+	if (status == IXGBE_ERR_SFP_NOT_SUPPORTED ||
+	    status == IXGBE_ERR_PHY_ADDR_INVALID)
+		return status;
 
 	/* start the external PHY */
 	if (hw->phy.type == ixgbe_phy_x550em_ext_t) {
@@ -3884,7 +3890,7 @@ static const struct ixgbe_mac_operations mac_ops_X550EM_x_fw = {
 	.write_iosf_sb_reg	= ixgbe_write_iosf_sb_reg_x550,
 };
 
-static struct ixgbe_mac_operations mac_ops_x550em_a = {
+static const struct ixgbe_mac_operations mac_ops_x550em_a = {
 	X550_COMMON_MAC
 	.led_on			= ixgbe_led_on_t_x550em,
 	.led_off		= ixgbe_led_off_t_x550em,
@@ -3905,7 +3911,7 @@ static struct ixgbe_mac_operations mac_ops_x550em_a = {
 	.write_iosf_sb_reg	= ixgbe_write_iosf_sb_reg_x550a,
 };
 
-static struct ixgbe_mac_operations mac_ops_x550em_a_fw = {
+static const struct ixgbe_mac_operations mac_ops_x550em_a_fw = {
 	X550_COMMON_MAC
 	.led_on			= ixgbe_led_on_generic,
 	.led_off		= ixgbe_led_off_generic,
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 032f8ac06357..12d3601b1d57 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -2747,9 +2747,10 @@ void ixgbevf_update_stats(struct ixgbevf_adapter *adapter)
  * ixgbevf_service_timer - Timer Call-back
  * @data: pointer to adapter cast into an unsigned long
  **/
-static void ixgbevf_service_timer(unsigned long data)
+static void ixgbevf_service_timer(struct timer_list *t)
 {
-	struct ixgbevf_adapter *adapter = (struct ixgbevf_adapter *)data;
+	struct ixgbevf_adapter *adapter = from_timer(adapter, t,
+						     service_timer);
 
 	/* Reset the timer */
 	mod_timer(&adapter->service_timer, (HZ * 2) + jiffies);
@@ -4120,8 +4121,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_sw_init;
 	}
 
-	setup_timer(&adapter->service_timer, &ixgbevf_service_timer,
-		    (unsigned long)adapter);
+	timer_setup(&adapter->service_timer, ixgbevf_service_timer, 0);
 
 	INIT_WORK(&adapter->service_task, ixgbevf_service_task);
 	set_bit(__IXGBEVF_SERVICE_INITED, &adapter->state);
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index 3c0a6451273d..ae195f8adff5 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -4,6 +4,7 @@
  *  Copyright 2004 IDT Inc. (rischelp@idt.com)
  *  Copyright 2006 Felix Fietkau <nbd@openwrt.org>
  *  Copyright 2008 Florian Fainelli <florian@openwrt.org>
+ *  Copyright 2017 Roman Yeryomin <roman@advem.lv>
  *
  *  This program is free software; you can redistribute  it and/or modify it
  *  under  the terms of  the GNU General  Public License as published by the
@@ -64,9 +65,9 @@
 #include <asm/mach-rc32434/eth.h>
 #include <asm/mach-rc32434/dma_v.h>
 
-#define DRV_NAME        "korina"
-#define DRV_VERSION     "0.10"
-#define DRV_RELDATE     "04Mar2008"
+#define DRV_NAME	"korina"
+#define DRV_VERSION	"0.20"
+#define DRV_RELDATE	"15Sep2017"
 
 #define STATION_ADDRESS_HIGH(dev) (((dev)->dev_addr[0] << 8) | \
 				   ((dev)->dev_addr[1]))
@@ -75,7 +76,7 @@
 				   ((dev)->dev_addr[4] << 8)  | \
 				   ((dev)->dev_addr[5]))
 
-#define MII_CLOCK 1250000 	/* no more than 2.5MHz */
+#define MII_CLOCK	1250000 /* no more than 2.5MHz */
 
 /* the following must be powers of two */
 #define KORINA_NUM_RDS	64  /* number of receive descriptors */
@@ -87,15 +88,19 @@
 #define KORINA_RBSIZE	1536 /* size of one resource buffer = Ether MTU */
 #define KORINA_RDS_MASK	(KORINA_NUM_RDS - 1)
 #define KORINA_TDS_MASK	(KORINA_NUM_TDS - 1)
-#define RD_RING_SIZE 	(KORINA_NUM_RDS * sizeof(struct dma_desc))
+#define RD_RING_SIZE	(KORINA_NUM_RDS * sizeof(struct dma_desc))
 #define TD_RING_SIZE	(KORINA_NUM_TDS * sizeof(struct dma_desc))
 
-#define TX_TIMEOUT 	(6000 * HZ / 1000)
+#define TX_TIMEOUT	(6000 * HZ / 1000)
 
-enum chain_status { desc_filled, desc_empty };
-#define IS_DMA_FINISHED(X)   (((X) & (DMA_DESC_FINI)) != 0)
-#define IS_DMA_DONE(X)   (((X) & (DMA_DESC_DONE)) != 0)
-#define RCVPKT_LENGTH(X)     (((X) & ETH_RX_LEN) >> ETH_RX_LEN_BIT)
+enum chain_status {
+	desc_filled,
+	desc_empty
+};
+
+#define IS_DMA_FINISHED(X)	(((X) & (DMA_DESC_FINI)) != 0)
+#define IS_DMA_DONE(X)		(((X) & (DMA_DESC_DONE)) != 0)
+#define RCVPKT_LENGTH(X)	(((X) & ETH_RX_LEN) >> ETH_RX_LEN_BIT)
 
 /* Information that need to be kept for each board. */
 struct korina_private {
@@ -122,10 +127,8 @@ struct korina_private {
 
 	int rx_irq;
 	int tx_irq;
-	int ovr_irq;
-	int und_irq;
 
-	spinlock_t lock;        /* NIC xmit lock */
+	spinlock_t lock;	/* NIC xmit lock */
 
 	int dma_halt_cnt;
 	int dma_run_cnt;
@@ -148,17 +151,17 @@ static inline void korina_start_dma(struct dma_reg *ch, u32 dma_addr)
 static inline void korina_abort_dma(struct net_device *dev,
 					struct dma_reg *ch)
 {
-       if (readl(&ch->dmac) & DMA_CHAN_RUN_BIT) {
-	       writel(0x10, &ch->dmac);
+	if (readl(&ch->dmac) & DMA_CHAN_RUN_BIT) {
+		writel(0x10, &ch->dmac);
 
-	       while (!(readl(&ch->dmas) & DMA_STAT_HALT))
-		       netif_trans_update(dev);
+		while (!(readl(&ch->dmas) & DMA_STAT_HALT))
+			netif_trans_update(dev);
 
-	       writel(0, &ch->dmas);
-       }
+		writel(0, &ch->dmas);
+	}
 
-       writel(0, &ch->dmadptr);
-       writel(0, &ch->dmandptr);
+	writel(0, &ch->dmadptr);
+	writel(0, &ch->dmandptr);
 }
 
 static inline void korina_chain_dma(struct dma_reg *ch, u32 dma_addr)
@@ -365,59 +368,60 @@ static int korina_rx(struct net_device *dev, int limit)
 		if ((KORINA_RBSIZE - (u32)DMA_COUNT(rd->control)) == 0)
 			break;
 
-		/* Update statistics counters */
-		if (devcs & ETH_RX_CRC)
-			dev->stats.rx_crc_errors++;
-		if (devcs & ETH_RX_LOR)
-			dev->stats.rx_length_errors++;
-		if (devcs & ETH_RX_LE)
-			dev->stats.rx_length_errors++;
-		if (devcs & ETH_RX_OVR)
-			dev->stats.rx_fifo_errors++;
-		if (devcs & ETH_RX_CV)
-			dev->stats.rx_frame_errors++;
-		if (devcs & ETH_RX_CES)
-			dev->stats.rx_length_errors++;
-		if (devcs & ETH_RX_MP)
-			dev->stats.multicast++;
+		/* check that this is a whole packet
+		 * WARNING: DMA_FD bit incorrectly set
+		 * in Rc32434 (errata ref #077) */
+		if (!(devcs & ETH_RX_LD))
+			goto next;
 
-		if ((devcs & ETH_RX_LD) != ETH_RX_LD) {
-			/* check that this is a whole packet
-			 * WARNING: DMA_FD bit incorrectly set
-			 * in Rc32434 (errata ref #077) */
+		if (!(devcs & ETH_RX_ROK)) {
+			/* Update statistics counters */
 			dev->stats.rx_errors++;
 			dev->stats.rx_dropped++;
-		} else if ((devcs & ETH_RX_ROK)) {
-			pkt_len = RCVPKT_LENGTH(devcs);
+			if (devcs & ETH_RX_CRC)
+				dev->stats.rx_crc_errors++;
+			if (devcs & ETH_RX_LE)
+				dev->stats.rx_length_errors++;
+			if (devcs & ETH_RX_OVR)
+				dev->stats.rx_fifo_errors++;
+			if (devcs & ETH_RX_CV)
+				dev->stats.rx_frame_errors++;
+			if (devcs & ETH_RX_CES)
+				dev->stats.rx_frame_errors++;
+
+			goto next;
+		}
 
-			/* must be the (first and) last
-			 * descriptor then */
-			pkt_buf = (u8 *)lp->rx_skb[lp->rx_next_done]->data;
+		pkt_len = RCVPKT_LENGTH(devcs);
 
-			/* invalidate the cache */
-			dma_cache_inv((unsigned long)pkt_buf, pkt_len - 4);
+		/* must be the (first and) last
+		 * descriptor then */
+		pkt_buf = (u8 *)lp->rx_skb[lp->rx_next_done]->data;
 
-			/* Malloc up new buffer. */
-			skb_new = netdev_alloc_skb_ip_align(dev, KORINA_RBSIZE);
+		/* invalidate the cache */
+		dma_cache_inv((unsigned long)pkt_buf, pkt_len - 4);
 
-			if (!skb_new)
-				break;
-			/* Do not count the CRC */
-			skb_put(skb, pkt_len - 4);
-			skb->protocol = eth_type_trans(skb, dev);
+		/* Malloc up new buffer. */
+		skb_new = netdev_alloc_skb_ip_align(dev, KORINA_RBSIZE);
 
-			/* Pass the packet to upper layers */
-			netif_receive_skb(skb);
-			dev->stats.rx_packets++;
-			dev->stats.rx_bytes += pkt_len;
+		if (!skb_new)
+			break;
+		/* Do not count the CRC */
+		skb_put(skb, pkt_len - 4);
+		skb->protocol = eth_type_trans(skb, dev);
 
-			/* Update the mcast stats */
-			if (devcs & ETH_RX_MP)
-				dev->stats.multicast++;
+		/* Pass the packet to upper layers */
+		napi_gro_receive(&lp->napi, skb);
+		dev->stats.rx_packets++;
+		dev->stats.rx_bytes += pkt_len;
 
-			lp->rx_skb[lp->rx_next_done] = skb_new;
-		}
+		/* Update the mcast stats */
+		if (devcs & ETH_RX_MP)
+			dev->stats.multicast++;
+
+		lp->rx_skb[lp->rx_next_done] = skb_new;
 
+next:
 		rd->devcs = 0;
 
 		/* Restore descriptor's curr_addr */
@@ -649,10 +653,10 @@ static void korina_check_media(struct net_device *dev, unsigned int init_media)
 						&lp->eth_regs->ethmac2);
 }
 
-static void korina_poll_media(unsigned long data)
+static void korina_poll_media(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) data;
-	struct korina_private *lp = netdev_priv(dev);
+	struct korina_private *lp = from_timer(lp, t, media_check_timer);
+	struct net_device *dev = lp->dev;
 
 	korina_check_media(dev, 0);
 	mod_timer(&lp->media_check_timer, jiffies + HZ);
@@ -686,7 +690,7 @@ static int korina_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 
 /* ethtool helpers */
 static void netdev_get_drvinfo(struct net_device *dev,
-			struct ethtool_drvinfo *info)
+				struct ethtool_drvinfo *info)
 {
 	struct korina_private *lp = netdev_priv(dev);
 
@@ -729,10 +733,10 @@ static u32 netdev_get_link(struct net_device *dev)
 }
 
 static const struct ethtool_ops netdev_ethtool_ops = {
-	.get_drvinfo            = netdev_get_drvinfo,
-	.get_link               = netdev_get_link,
-	.get_link_ksettings     = netdev_get_link_ksettings,
-	.set_link_ksettings     = netdev_set_link_ksettings,
+	.get_drvinfo		= netdev_get_drvinfo,
+	.get_link		= netdev_get_link,
+	.get_link_ksettings	= netdev_get_link_ksettings,
+	.set_link_ksettings	= netdev_set_link_ksettings,
 };
 
 static int korina_alloc_ring(struct net_device *dev)
@@ -864,7 +868,7 @@ static int korina_init(struct net_device *dev)
 	/* Management Clock Prescaler Divisor
 	 * Clock independent setting */
 	writel(((idt_cpu_freq) / MII_CLOCK + 1) & ~1,
-		       &lp->eth_regs->ethmcp);
+			&lp->eth_regs->ethmcp);
 
 	/* don't transmit until fifo contains 48b */
 	writel(48, &lp->eth_regs->ethfifott);
@@ -891,8 +895,6 @@ static void korina_restart_task(struct work_struct *work)
 	 */
 	disable_irq(lp->rx_irq);
 	disable_irq(lp->tx_irq);
-	disable_irq(lp->ovr_irq);
-	disable_irq(lp->und_irq);
 
 	writel(readl(&lp->tx_dma_regs->dmasm) |
 				DMA_STAT_FINI | DMA_STAT_ERR,
@@ -911,40 +913,10 @@ static void korina_restart_task(struct work_struct *work)
 	}
 	korina_multicast_list(dev);
 
-	enable_irq(lp->und_irq);
-	enable_irq(lp->ovr_irq);
 	enable_irq(lp->tx_irq);
 	enable_irq(lp->rx_irq);
 }
 
-static void korina_clear_and_restart(struct net_device *dev, u32 value)
-{
-	struct korina_private *lp = netdev_priv(dev);
-
-	netif_stop_queue(dev);
-	writel(value, &lp->eth_regs->ethintfc);
-	schedule_work(&lp->restart_task);
-}
-
-/* Ethernet Tx Underflow interrupt */
-static irqreturn_t korina_und_interrupt(int irq, void *dev_id)
-{
-	struct net_device *dev = dev_id;
-	struct korina_private *lp = netdev_priv(dev);
-	unsigned int und;
-
-	spin_lock(&lp->lock);
-
-	und = readl(&lp->eth_regs->ethintfc);
-
-	if (und & ETH_INT_FC_UND)
-		korina_clear_and_restart(dev, und & ~ETH_INT_FC_UND);
-
-	spin_unlock(&lp->lock);
-
-	return IRQ_HANDLED;
-}
-
 static void korina_tx_timeout(struct net_device *dev)
 {
 	struct korina_private *lp = netdev_priv(dev);
@@ -952,25 +924,6 @@ static void korina_tx_timeout(struct net_device *dev)
 	schedule_work(&lp->restart_task);
 }
 
-/* Ethernet Rx Overflow interrupt */
-static irqreturn_t
-korina_ovr_interrupt(int irq, void *dev_id)
-{
-	struct net_device *dev = dev_id;
-	struct korina_private *lp = netdev_priv(dev);
-	unsigned int ovr;
-
-	spin_lock(&lp->lock);
-	ovr = readl(&lp->eth_regs->ethintfc);
-
-	if (ovr & ETH_INT_FC_OVR)
-		korina_clear_and_restart(dev, ovr & ~ETH_INT_FC_OVR);
-
-	spin_unlock(&lp->lock);
-
-	return IRQ_HANDLED;
-}
-
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void korina_poll_controller(struct net_device *dev)
 {
@@ -993,48 +946,26 @@ static int korina_open(struct net_device *dev)
 	}
 
 	/* Install the interrupt handler
-	 * that handles the Done Finished
-	 * Ovr and Und Events */
+	 * that handles the Done Finished */
 	ret = request_irq(lp->rx_irq, korina_rx_dma_interrupt,
 			0, "Korina ethernet Rx", dev);
 	if (ret < 0) {
 		printk(KERN_ERR "%s: unable to get Rx DMA IRQ %d\n",
-		    dev->name, lp->rx_irq);
+			dev->name, lp->rx_irq);
 		goto err_release;
 	}
 	ret = request_irq(lp->tx_irq, korina_tx_dma_interrupt,
 			0, "Korina ethernet Tx", dev);
 	if (ret < 0) {
 		printk(KERN_ERR "%s: unable to get Tx DMA IRQ %d\n",
-		    dev->name, lp->tx_irq);
+			dev->name, lp->tx_irq);
 		goto err_free_rx_irq;
 	}
 
-	/* Install handler for overrun error. */
-	ret = request_irq(lp->ovr_irq, korina_ovr_interrupt,
-			0, "Ethernet Overflow", dev);
-	if (ret < 0) {
-		printk(KERN_ERR "%s: unable to get OVR IRQ %d\n",
-		    dev->name, lp->ovr_irq);
-		goto err_free_tx_irq;
-	}
-
-	/* Install handler for underflow error. */
-	ret = request_irq(lp->und_irq, korina_und_interrupt,
-			0, "Ethernet Underflow", dev);
-	if (ret < 0) {
-		printk(KERN_ERR "%s: unable to get UND IRQ %d\n",
-		    dev->name, lp->und_irq);
-		goto err_free_ovr_irq;
-	}
 	mod_timer(&lp->media_check_timer, jiffies + 1);
 out:
 	return ret;
 
-err_free_ovr_irq:
-	free_irq(lp->ovr_irq, dev);
-err_free_tx_irq:
-	free_irq(lp->tx_irq, dev);
 err_free_rx_irq:
 	free_irq(lp->rx_irq, dev);
 err_release:
@@ -1052,8 +983,6 @@ static int korina_close(struct net_device *dev)
 	/* Disable interrupts */
 	disable_irq(lp->rx_irq);
 	disable_irq(lp->tx_irq);
-	disable_irq(lp->ovr_irq);
-	disable_irq(lp->und_irq);
 
 	korina_abort_tx(dev);
 	tmp = readl(&lp->tx_dma_regs->dmasm);
@@ -1073,8 +1002,6 @@ static int korina_close(struct net_device *dev)
 
 	free_irq(lp->rx_irq, dev);
 	free_irq(lp->tx_irq, dev);
-	free_irq(lp->ovr_irq, dev);
-	free_irq(lp->und_irq, dev);
 
 	return 0;
 }
@@ -1113,8 +1040,6 @@ static int korina_probe(struct platform_device *pdev)
 
 	lp->rx_irq = platform_get_irq_byname(pdev, "korina_rx");
 	lp->tx_irq = platform_get_irq_byname(pdev, "korina_tx");
-	lp->ovr_irq = platform_get_irq_byname(pdev, "korina_ovr");
-	lp->und_irq = platform_get_irq_byname(pdev, "korina_und");
 
 	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "korina_regs");
 	dev->base_addr = r->start;
@@ -1162,7 +1087,7 @@ static int korina_probe(struct platform_device *pdev)
 	dev->netdev_ops = &korina_netdev_ops;
 	dev->ethtool_ops = &netdev_ethtool_ops;
 	dev->watchdog_timeo = TX_TIMEOUT;
-	netif_napi_add(dev, &lp->napi, korina_poll, 64);
+	netif_napi_add(dev, &lp->napi, korina_poll, NAPI_POLL_WEIGHT);
 
 	lp->phy_addr = (((lp->rx_irq == 0x2c? 1:0) << 8) | 0x05);
 	lp->mii_if.dev = dev;
@@ -1178,7 +1103,7 @@ static int korina_probe(struct platform_device *pdev)
 			": cannot register net device: %d\n", rc);
 		goto probe_err_register;
 	}
-	setup_timer(&lp->media_check_timer, korina_poll_media, (unsigned long) dev);
+	timer_setup(&lp->media_check_timer, korina_poll_media, 0);
 
 	INIT_WORK(&lp->restart_task, korina_restart_task);
 
@@ -1226,5 +1151,6 @@ module_platform_driver(korina_driver);
 MODULE_AUTHOR("Philip Rischel <rischelp@idt.com>");
 MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>");
 MODULE_AUTHOR("Florian Fainelli <florian@openwrt.org>");
+MODULE_AUTHOR("Roman Yeryomin <roman@advem.lv>");
 MODULE_DESCRIPTION("IDT RC32434 (Korina) Ethernet driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index a37af5813f33..965b6a829a5d 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -38,11 +38,12 @@
 #include <net/ipv6.h>
 #include <net/tso.h>
 
-/* RX Fifo Registers */
+/* Fifo Registers */
 #define MVPP2_RX_DATA_FIFO_SIZE_REG(port)	(0x00 + 4 * (port))
 #define MVPP2_RX_ATTR_FIFO_SIZE_REG(port)	(0x20 + 4 * (port))
 #define MVPP2_RX_MIN_PKT_SIZE_REG		0x60
 #define MVPP2_RX_FIFO_INIT_REG			0x64
+#define MVPP22_TX_FIFO_SIZE_REG(port)		(0x8860 + 4 * (port))
 
 /* RX DMA Top Registers */
 #define MVPP2_RX_CTRL_REG(port)			(0x140 + 4 * (port))
@@ -82,6 +83,16 @@
 #define MVPP2_PRS_TCAM_CTRL_REG			0x1230
 #define     MVPP2_PRS_TCAM_EN_MASK		BIT(0)
 
+/* RSS Registers */
+#define MVPP22_RSS_INDEX			0x1500
+#define     MVPP22_RSS_INDEX_TABLE_ENTRY(idx)	((idx) << 8)
+#define     MVPP22_RSS_INDEX_TABLE(idx)		((idx) << 8)
+#define     MVPP22_RSS_INDEX_QUEUE(idx)		((idx) << 16)
+#define MVPP22_RSS_TABLE_ENTRY			0x1508
+#define MVPP22_RSS_TABLE			0x1510
+#define     MVPP22_RSS_TABLE_POINTER(p)		(p)
+#define MVPP22_RSS_WIDTH			0x150c
+
 /* Classifier Registers */
 #define MVPP2_CLS_MODE_REG			0x1800
 #define     MVPP2_CLS_MODE_ACTIVE_MASK		BIT(0)
@@ -482,6 +493,13 @@
 /* Maximum number of TXQs used by single port */
 #define MVPP2_MAX_TXQ			8
 
+/* MVPP2_MAX_TSO_SEGS is the maximum number of fragments to allow in the GSO
+ * skb. As we need a maxium of two descriptors per fragments (1 header, 1 data),
+ * multiply this value by two to count the maximum number of skb descs needed.
+ */
+#define MVPP2_MAX_TSO_SEGS		300
+#define MVPP2_MAX_SKB_DESCS		(MVPP2_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
+
 /* Dfault number of RXQs in use */
 #define MVPP2_DEFAULT_RXQ		4
 
@@ -504,9 +522,17 @@
 #define MVPP2_TX_DESC_ALIGN		(MVPP2_DESC_ALIGNED_SIZE - 1)
 
 /* RX FIFO constants */
-#define MVPP2_RX_FIFO_PORT_DATA_SIZE	0x2000
-#define MVPP2_RX_FIFO_PORT_ATTR_SIZE	0x80
-#define MVPP2_RX_FIFO_PORT_MIN_PKT	0x80
+#define MVPP2_RX_FIFO_PORT_DATA_SIZE_32KB	0x8000
+#define MVPP2_RX_FIFO_PORT_DATA_SIZE_8KB	0x2000
+#define MVPP2_RX_FIFO_PORT_DATA_SIZE_4KB	0x1000
+#define MVPP2_RX_FIFO_PORT_ATTR_SIZE_32KB	0x200
+#define MVPP2_RX_FIFO_PORT_ATTR_SIZE_8KB	0x80
+#define MVPP2_RX_FIFO_PORT_ATTR_SIZE_4KB	0x40
+#define MVPP2_RX_FIFO_PORT_MIN_PKT		0x80
+
+/* TX FIFO constants */
+#define MVPP22_TX_FIFO_DATA_SIZE_10KB		0xa
+#define MVPP22_TX_FIFO_DATA_SIZE_3KB		0x3
 
 /* RX buffer constants */
 #define MVPP2_SKB_SHINFO_SIZE \
@@ -737,6 +763,10 @@ enum mvpp2_prs_l3_cast {
 #define MVPP2_CLS_FLOWS_TBL_SIZE	512
 #define MVPP2_CLS_FLOWS_TBL_DATA_WORDS	3
 #define MVPP2_CLS_LKP_TBL_SIZE		64
+#define MVPP2_CLS_RX_QUEUES		256
+
+/* RSS constants */
+#define MVPP22_RSS_TABLE_ENTRIES	32
 
 /* BM constants */
 #define MVPP2_BM_POOLS_NUM		8
@@ -1022,6 +1052,9 @@ struct mvpp2_txq_pcpu {
 	 */
 	int count;
 
+	int wake_threshold;
+	int stop_threshold;
+
 	/* Number of Tx DMA descriptors reserved for each CPU */
 	int reserved_num;
 
@@ -1257,13 +1290,20 @@ static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
 				      struct mvpp2_tx_desc *tx_desc,
 				      dma_addr_t dma_addr)
 {
+	dma_addr_t addr, offset;
+
+	addr = dma_addr & ~MVPP2_TX_DESC_ALIGN;
+	offset = dma_addr & MVPP2_TX_DESC_ALIGN;
+
 	if (port->priv->hw_version == MVPP21) {
-		tx_desc->pp21.buf_dma_addr = dma_addr;
+		tx_desc->pp21.buf_dma_addr = addr;
+		tx_desc->pp21.packet_offset = offset;
 	} else {
-		u64 val = (u64)dma_addr;
+		u64 val = (u64)addr;
 
 		tx_desc->pp22.buf_dma_addr_ptp &= ~GENMASK_ULL(40, 0);
 		tx_desc->pp22.buf_dma_addr_ptp |= val;
+		tx_desc->pp22.packet_offset = offset;
 	}
 }
 
@@ -1306,16 +1346,6 @@ static void mvpp2_txdesc_cmd_set(struct mvpp2_port *port,
 		tx_desc->pp22.command = command;
 }
 
-static void mvpp2_txdesc_offset_set(struct mvpp2_port *port,
-				    struct mvpp2_tx_desc *tx_desc,
-				    unsigned int offset)
-{
-	if (port->priv->hw_version == MVPP21)
-		tx_desc->pp21.packet_offset = offset;
-	else
-		tx_desc->pp22.packet_offset = offset;
-}
-
 static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port,
 					    struct mvpp2_tx_desc *tx_desc)
 {
@@ -5022,7 +5052,7 @@ static void mvpp2_aggr_txq_pend_desc_add(struct mvpp2_port *port, int pending)
 static int mvpp2_aggr_desc_num_check(struct mvpp2 *priv,
 				     struct mvpp2_tx_queue *aggr_txq, int num)
 {
-	if ((aggr_txq->count + num) > aggr_txq->size) {
+	if ((aggr_txq->count + num) > MVPP2_AGGR_TXQ_SIZE) {
 		/* Update number of occupied aggregated Tx descriptors */
 		int cpu = smp_processor_id();
 		u32 val = mvpp2_read(priv, MVPP2_AGGR_TXQ_STATUS_REG(cpu));
@@ -5030,7 +5060,7 @@ static int mvpp2_aggr_desc_num_check(struct mvpp2 *priv,
 		aggr_txq->count = val & MVPP2_AGGR_TXQ_PENDING_MASK;
 	}
 
-	if ((aggr_txq->count + num) > aggr_txq->size)
+	if ((aggr_txq->count + num) > MVPP2_AGGR_TXQ_SIZE)
 		return -ENOMEM;
 
 	return 0;
@@ -5370,7 +5400,7 @@ static void mvpp2_txq_done(struct mvpp2_port *port, struct mvpp2_tx_queue *txq,
 	txq_pcpu->count -= tx_done;
 
 	if (netif_tx_queue_stopped(nq))
-		if (txq_pcpu->size - txq_pcpu->count >= MAX_SKB_FRAGS + 1)
+		if (txq_pcpu->count <= txq_pcpu->wake_threshold)
 			netif_tx_wake_queue(nq);
 }
 
@@ -5414,7 +5444,7 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev,
 	if (!aggr_txq->descs)
 		return -ENOMEM;
 
-	aggr_txq->last_desc = aggr_txq->size - 1;
+	aggr_txq->last_desc = MVPP2_AGGR_TXQ_SIZE - 1;
 
 	/* Aggr TXQ no reset WA */
 	aggr_txq->next_desc_to_proc = mvpp2_read(priv,
@@ -5613,6 +5643,9 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
 		txq_pcpu->txq_put_index = 0;
 		txq_pcpu->txq_get_index = 0;
 
+		txq_pcpu->stop_threshold = txq->size - MVPP2_MAX_SKB_DESCS;
+		txq_pcpu->wake_threshold = txq_pcpu->stop_threshold / 2;
+
 		txq_pcpu->tso_headers =
 			dma_alloc_coherent(port->dev->dev.parent,
 					   txq_pcpu->size * TSO_HEADER_SIZE,
@@ -6256,10 +6289,7 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb,
 			goto cleanup;
 		}
 
-		mvpp2_txdesc_offset_set(port, tx_desc,
-					buf_dma_addr & MVPP2_TX_DESC_ALIGN);
-		mvpp2_txdesc_dma_addr_set(port, tx_desc,
-					  buf_dma_addr & ~MVPP2_TX_DESC_ALIGN);
+		mvpp2_txdesc_dma_addr_set(port, tx_desc, buf_dma_addr);
 
 		if (i == (skb_shinfo(skb)->nr_frags - 1)) {
 			/* Last descriptor */
@@ -6302,8 +6332,7 @@ static inline void mvpp2_tso_put_hdr(struct sk_buff *skb,
 
 	addr = txq_pcpu->tso_headers_dma +
 	       txq_pcpu->txq_put_index * TSO_HEADER_SIZE;
-	mvpp2_txdesc_offset_set(port, tx_desc, addr & MVPP2_TX_DESC_ALIGN);
-	mvpp2_txdesc_dma_addr_set(port, tx_desc, addr & ~MVPP2_TX_DESC_ALIGN);
+	mvpp2_txdesc_dma_addr_set(port, tx_desc, addr);
 
 	mvpp2_txdesc_cmd_set(port, tx_desc, mvpp2_skb_tx_csum(port, skb) |
 					    MVPP2_TXD_F_DESC |
@@ -6332,10 +6361,7 @@ static inline int mvpp2_tso_put_data(struct sk_buff *skb,
 		return -ENOMEM;
 	}
 
-	mvpp2_txdesc_offset_set(port, tx_desc,
-				buf_dma_addr & MVPP2_TX_DESC_ALIGN);
-	mvpp2_txdesc_dma_addr_set(port, tx_desc,
-				  buf_dma_addr & ~MVPP2_TX_DESC_ALIGN);
+	mvpp2_txdesc_dma_addr_set(port, tx_desc, buf_dma_addr);
 
 	if (!left) {
 		mvpp2_txdesc_cmd_set(port, tx_desc, MVPP2_TXD_L_DESC);
@@ -6447,10 +6473,7 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev)
 		goto out;
 	}
 
-	mvpp2_txdesc_offset_set(port, tx_desc,
-				buf_dma_addr & MVPP2_TX_DESC_ALIGN);
-	mvpp2_txdesc_dma_addr_set(port, tx_desc,
-				  buf_dma_addr & ~MVPP2_TX_DESC_ALIGN);
+	mvpp2_txdesc_dma_addr_set(port, tx_desc, buf_dma_addr);
 
 	tx_cmd = mvpp2_skb_tx_csum(port, skb);
 
@@ -6469,7 +6492,6 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev)
 		if (mvpp2_tx_frag_process(port, skb, aggr_txq, txq)) {
 			tx_desc_unmap_put(port, txq, tx_desc);
 			frags = 0;
-			goto out;
 		}
 	}
 
@@ -6486,7 +6508,7 @@ out:
 		wmb();
 		mvpp2_aggr_txq_pend_desc_add(port, frags);
 
-		if (txq_pcpu->size - txq_pcpu->count < MAX_SKB_FRAGS + 1)
+		if (txq_pcpu->count >= txq_pcpu->stop_threshold)
 			netif_tx_stop_queue(nq);
 
 		u64_stats_update_begin(&stats->syncp);
@@ -6780,6 +6802,39 @@ static void mvpp2_irqs_deinit(struct mvpp2_port *port)
 	}
 }
 
+static void mvpp22_init_rss(struct mvpp2_port *port)
+{
+	struct mvpp2 *priv = port->priv;
+	int i;
+
+	/* Set the table width: replace the whole classifier Rx queue number
+	 * with the ones configured in RSS table entries.
+	 */
+	mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_TABLE(0));
+	mvpp2_write(priv, MVPP22_RSS_WIDTH, 8);
+
+	/* Loop through the classifier Rx Queues and map them to a RSS table.
+	 * Map them all to the first table (0) by default.
+	 */
+	for (i = 0; i < MVPP2_CLS_RX_QUEUES; i++) {
+		mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_QUEUE(i));
+		mvpp2_write(priv, MVPP22_RSS_TABLE,
+			    MVPP22_RSS_TABLE_POINTER(0));
+	}
+
+	/* Configure the first table to evenly distribute the packets across
+	 * real Rx Queues. The table entries map a hash to an port Rx Queue.
+	 */
+	for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++) {
+		u32 sel = MVPP22_RSS_INDEX_TABLE(0) |
+			  MVPP22_RSS_INDEX_TABLE_ENTRY(i);
+		mvpp2_write(priv, MVPP22_RSS_INDEX, sel);
+
+		mvpp2_write(priv, MVPP22_RSS_TABLE_ENTRY, i % port->nrxqs);
+	}
+
+}
+
 static int mvpp2_open(struct net_device *dev)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
@@ -6854,6 +6909,9 @@ static int mvpp2_open(struct net_device *dev)
 
 	mvpp2_start_dev(port);
 
+	if (priv->hw_version == MVPP22)
+		mvpp22_init_rss(port);
+
 	return 0;
 
 err_free_link_irq:
@@ -7674,6 +7732,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	dev->features = features | NETIF_F_RXCSUM;
 	dev->hw_features |= features | NETIF_F_RXCSUM | NETIF_F_GRO;
 	dev->vlan_features |= features;
+	dev->gso_max_segs = MVPP2_MAX_TSO_SEGS;
 
 	/* MTU range: 68 - 9676 */
 	dev->min_mtu = ETH_MIN_MTU;
@@ -7765,9 +7824,9 @@ static void mvpp2_rx_fifo_init(struct mvpp2 *priv)
 
 	for (port = 0; port < MVPP2_MAX_PORTS; port++) {
 		mvpp2_write(priv, MVPP2_RX_DATA_FIFO_SIZE_REG(port),
-			    MVPP2_RX_FIFO_PORT_DATA_SIZE);
+			    MVPP2_RX_FIFO_PORT_DATA_SIZE_4KB);
 		mvpp2_write(priv, MVPP2_RX_ATTR_FIFO_SIZE_REG(port),
-			    MVPP2_RX_FIFO_PORT_ATTR_SIZE);
+			    MVPP2_RX_FIFO_PORT_ATTR_SIZE_4KB);
 	}
 
 	mvpp2_write(priv, MVPP2_RX_MIN_PKT_SIZE_REG,
@@ -7775,6 +7834,49 @@ static void mvpp2_rx_fifo_init(struct mvpp2 *priv)
 	mvpp2_write(priv, MVPP2_RX_FIFO_INIT_REG, 0x1);
 }
 
+static void mvpp22_rx_fifo_init(struct mvpp2 *priv)
+{
+	int port;
+
+	/* The FIFO size parameters are set depending on the maximum speed a
+	 * given port can handle:
+	 * - Port 0: 10Gbps
+	 * - Port 1: 2.5Gbps
+	 * - Ports 2 and 3: 1Gbps
+	 */
+
+	mvpp2_write(priv, MVPP2_RX_DATA_FIFO_SIZE_REG(0),
+		    MVPP2_RX_FIFO_PORT_DATA_SIZE_32KB);
+	mvpp2_write(priv, MVPP2_RX_ATTR_FIFO_SIZE_REG(0),
+		    MVPP2_RX_FIFO_PORT_ATTR_SIZE_32KB);
+
+	mvpp2_write(priv, MVPP2_RX_DATA_FIFO_SIZE_REG(1),
+		    MVPP2_RX_FIFO_PORT_DATA_SIZE_8KB);
+	mvpp2_write(priv, MVPP2_RX_ATTR_FIFO_SIZE_REG(1),
+		    MVPP2_RX_FIFO_PORT_ATTR_SIZE_8KB);
+
+	for (port = 2; port < MVPP2_MAX_PORTS; port++) {
+		mvpp2_write(priv, MVPP2_RX_DATA_FIFO_SIZE_REG(port),
+			    MVPP2_RX_FIFO_PORT_DATA_SIZE_4KB);
+		mvpp2_write(priv, MVPP2_RX_ATTR_FIFO_SIZE_REG(port),
+			    MVPP2_RX_FIFO_PORT_ATTR_SIZE_4KB);
+	}
+
+	mvpp2_write(priv, MVPP2_RX_MIN_PKT_SIZE_REG,
+		    MVPP2_RX_FIFO_PORT_MIN_PKT);
+	mvpp2_write(priv, MVPP2_RX_FIFO_INIT_REG, 0x1);
+}
+
+/* Initialize Tx FIFO's */
+static void mvpp22_tx_fifo_init(struct mvpp2 *priv)
+{
+	int port;
+
+	for (port = 0; port < MVPP2_MAX_PORTS; port++)
+		mvpp2_write(priv, MVPP22_TX_FIFO_SIZE_REG(port),
+			    MVPP22_TX_FIFO_DATA_SIZE_3KB);
+}
+
 static void mvpp2_axi_init(struct mvpp2 *priv)
 {
 	u32 val, rdval, wrval;
@@ -7870,8 +7972,13 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
 			return err;
 	}
 
-	/* Rx Fifo Init */
-	mvpp2_rx_fifo_init(priv);
+	/* Fifo Init */
+	if (priv->hw_version == MVPP21) {
+		mvpp2_rx_fifo_init(priv);
+	} else {
+		mvpp22_rx_fifo_init(priv);
+		mvpp22_tx_fifo_init(priv);
+	}
 
 	if (priv->hw_version == MVPP21)
 		writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT,
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index 993724959a7c..91b1c154fd29 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1496,9 +1496,8 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 	netif_napi_add(dev, &pep->napi, pxa168_rx_poll, pep->rx_ring_size);
 
 	memset(&pep->timeout, 0, sizeof(struct timer_list));
-	init_timer(&pep->timeout);
-	pep->timeout.function = rxq_refill_timer_wrapper;
-	pep->timeout.data = (unsigned long)pep;
+	setup_timer(&pep->timeout, rxq_refill_timer_wrapper,
+		    (unsigned long)pep);
 
 	pep->smi_bus = mdiobus_alloc();
 	if (!pep->smi_bus) {
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 5e81a7263654..54adfd967858 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1817,7 +1817,7 @@ static int mtk_open(struct net_device *dev)
 	struct mtk_eth *eth = mac->hw;
 
 	/* we run 2 netdevs on the same dma ring so we only bring it up once */
-	if (!atomic_read(&eth->dma_refcnt)) {
+	if (!refcount_read(&eth->dma_refcnt)) {
 		int err = mtk_start_dma(eth);
 
 		if (err)
@@ -1827,8 +1827,10 @@ static int mtk_open(struct net_device *dev)
 		napi_enable(&eth->rx_napi);
 		mtk_tx_irq_enable(eth, MTK_TX_DONE_INT);
 		mtk_rx_irq_enable(eth, MTK_RX_DONE_INT);
+		refcount_set(&eth->dma_refcnt, 1);
 	}
-	atomic_inc(&eth->dma_refcnt);
+	else
+		refcount_inc(&eth->dma_refcnt);
 
 	phy_start(dev->phydev);
 	netif_start_queue(dev);
@@ -1868,7 +1870,7 @@ static int mtk_stop(struct net_device *dev)
 	phy_stop(dev->phydev);
 
 	/* only shutdown DMA if this is the last user */
-	if (!atomic_dec_and_test(&eth->dma_refcnt))
+	if (!refcount_dec_and_test(&eth->dma_refcnt))
 		return 0;
 
 	mtk_tx_irq_disable(eth, MTK_TX_DONE_INT);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 3d3c24a28112..a3af4660de81 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -15,6 +15,8 @@
 #ifndef MTK_ETH_H
 #define MTK_ETH_H
 
+#include <linux/refcount.h>
+
 #define MTK_QDMA_PAGE_SIZE	2048
 #define	MTK_MAX_RX_LENGTH	1536
 #define MTK_TX_DMA_BUF_LEN	0x3fff
@@ -632,7 +634,7 @@ struct mtk_eth {
 	struct regmap			*pctl;
 	u32				chip_id;
 	bool				hwlro;
-	atomic_t			dma_refcnt;
+	refcount_t			dma_refcnt;
 	struct mtk_tx_ring		tx_ring;
 	struct mtk_rx_ring		rx_ring[MTK_MAX_RX_RING_NUM];
 	struct mtk_rx_ring		rx_ring_qdma;
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 53daa6ca5d83..de0f9e5e42ec 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -277,7 +277,7 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev)
 	phys_addr_t addr;
 
 	INIT_LIST_HEAD(&priv->catas_err.list);
-	init_timer(&priv->catas_err.timer);
+	setup_timer(&priv->catas_err.timer, poll_catas, (unsigned long)dev);
 	priv->catas_err.map = NULL;
 
 	if (!mlx4_is_slave(dev)) {
@@ -293,8 +293,6 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev)
 		}
 	}
 
-	priv->catas_err.timer.data     = (unsigned long) dev;
-	priv->catas_err.timer.function = poll_catas;
 	priv->catas_err.timer.expires  =
 		round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL);
 	add_timer(&priv->catas_err.timer);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 72eb50cd5ecd..d8e9a323122e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -69,7 +69,7 @@ void mlx4_cq_tasklet_cb(unsigned long data)
 	list_for_each_entry_safe(mcq, temp, &ctx->process_list, tasklet_ctx.list) {
 		list_del_init(&mcq->tasklet_ctx.list);
 		mcq->tasklet_ctx.comp(mcq);
-		if (atomic_dec_and_test(&mcq->refcount))
+		if (refcount_dec_and_test(&mcq->refcount))
 			complete(&mcq->free);
 		if (time_after(jiffies, end))
 			break;
@@ -92,7 +92,7 @@ static void mlx4_add_cq_to_tasklet(struct mlx4_cq *cq)
 	 * still arrive.
 	 */
 	if (list_empty_careful(&cq->tasklet_ctx.list)) {
-		atomic_inc(&cq->refcount);
+		refcount_inc(&cq->refcount);
 		kick = list_empty(&tasklet_ctx->list);
 		list_add_tail(&cq->tasklet_ctx.list, &tasklet_ctx->list);
 		if (kick)
@@ -344,7 +344,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	cq->cons_index = 0;
 	cq->arm_sn     = 1;
 	cq->uar        = uar;
-	atomic_set(&cq->refcount, 1);
+	refcount_set(&cq->refcount, 1);
 	init_completion(&cq->free);
 	cq->comp = mlx4_add_cq_to_tasklet;
 	cq->tasklet_ctx.priv =
@@ -386,7 +386,7 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq)
 	    priv->eq_table.eq[MLX4_EQ_ASYNC].irq)
 		synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
 
-	if (atomic_dec_and_test(&cq->refcount))
+	if (refcount_dec_and_test(&cq->refcount))
 		complete(&cq->free);
 	wait_for_completion(&cq->free);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 3d4e4a5d00d1..bf1f04164885 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1742,13 +1742,18 @@ static int mlx4_en_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	return err;
 }
 
+static int mlx4_en_get_max_num_rx_rings(struct net_device *dev)
+{
+	return min_t(int, num_online_cpus(), MAX_RX_RINGS);
+}
+
 static void mlx4_en_get_channels(struct net_device *dev,
 				 struct ethtool_channels *channel)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
-	channel->max_rx = MAX_RX_RINGS;
-	channel->max_tx = MLX4_EN_MAX_TX_RING_P_UP;
+	channel->max_rx = mlx4_en_get_max_num_rx_rings(dev);
+	channel->max_tx = priv->mdev->profile.max_num_tx_rings_p_up;
 
 	channel->rx_count = priv->rx_ring_num;
 	channel->tx_count = priv->tx_ring_num[TX] /
@@ -1777,7 +1782,7 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	mutex_lock(&mdev->state_lock);
 	xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0;
 	if (channel->tx_count * priv->prof->num_up + xdp_count >
-	    MAX_TX_RINGS) {
+	    priv->mdev->profile.max_num_tx_rings_p_up * priv->prof->num_up) {
 		err = -EINVAL;
 		en_err(priv,
 		       "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n",
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 686e18de9a97..2c2965497ed3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -153,7 +153,7 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 	int i;
 
 	params->udp_rss = udp_rss;
-	params->num_tx_rings_p_up = mlx4_low_memory_profile() ?
+	params->max_num_tx_rings_p_up = mlx4_low_memory_profile() ?
 		MLX4_EN_MIN_TX_RING_P_UP :
 		min_t(int, num_online_cpus(), MLX4_EN_MAX_TX_RING_P_UP);
 
@@ -170,8 +170,8 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 		params->prof[i].tx_ring_size = MLX4_EN_DEF_TX_RING_SIZE;
 		params->prof[i].rx_ring_size = MLX4_EN_DEF_RX_RING_SIZE;
 		params->prof[i].num_up = MLX4_EN_NUM_UP_LOW;
-		params->prof[i].num_tx_rings_p_up = params->num_tx_rings_p_up;
-		params->prof[i].tx_ring_num[TX] = params->num_tx_rings_p_up *
+		params->prof[i].num_tx_rings_p_up = params->max_num_tx_rings_p_up;
+		params->prof[i].tx_ring_num[TX] = params->max_num_tx_rings_p_up *
 			params->prof[i].num_up;
 		params->prof[i].rss_rings = 0;
 		params->prof[i].inline_thold = inline_thold;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 9c218f1cfc6c..d611df2f274d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1752,6 +1752,7 @@ int mlx4_en_start_port(struct net_device *dev)
 				mlx4_en_arm_cq(priv, cq);
 
 			} else {
+				mlx4_en_init_tx_xdp_ring_descs(priv, tx_ring);
 				mlx4_en_init_recycle_ring(priv, i);
 				/* XDP TX CQ should never be armed */
 			}
@@ -3305,7 +3306,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->pflags = MLX4_EN_PRIV_FLAGS_BLUEFLAME;
 	priv->ctrl_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE |
 			MLX4_WQE_CTRL_SOLICITED);
-	priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up;
+	priv->num_tx_rings_p_up = mdev->profile.max_num_tx_rings_p_up;
 	priv->tx_work_limit = MLX4_EN_DEFAULT_TX_WORK;
 	netdev_rss_key_fill(priv->rss_key, sizeof(priv->rss_key));
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
index 5a47f9669621..6883ac75d37f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
@@ -53,7 +53,7 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
 	if (is_tx) {
 		context->sq_size_stride = ilog2(size) << 3 | (ilog2(stride) - 4);
 		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP)
-			context->params2 |= MLX4_QP_BIT_FPP;
+			context->params2 |= cpu_to_be32(MLX4_QP_BIT_FPP);
 
 	} else {
 		context->sq_size_stride = ilog2(TXBB_SIZE) - 4;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index b97a55c827eb..92aec17f4b4d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -254,8 +254,7 @@ void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev)
 					 DEF_RX_RINGS));
 
 		num_rx_rings = mlx4_low_memory_profile() ? MIN_RX_RINGS :
-			min_t(int, num_of_eqs,
-			      netif_get_num_default_rss_queues());
+			min_t(int, num_of_eqs, num_online_cpus());
 		mdev->profile.prof[i].rx_ring_num =
 			rounddown_pow_of_two(num_rx_rings);
 	}
@@ -762,6 +761,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 
 			xdp.data_hard_start = va - frags[0].page_offset;
 			xdp.data = va;
+			xdp_set_data_meta_invalid(&xdp);
 			xdp.data_end = xdp.data + length;
 			orig_data = xdp.data;
 
@@ -778,7 +778,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			case XDP_PASS:
 				break;
 			case XDP_TX:
-				if (likely(!mlx4_en_xmit_frame(ring, frags, dev,
+				if (likely(!mlx4_en_xmit_frame(ring, frags, priv,
 							length, cq_ring,
 							&doorbell_pending))) {
 					frags[0].page = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 8a32a8f7f9c0..596445a4a241 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -718,7 +718,7 @@ void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring)
 #else
 	iowrite32be(
 #endif
-		  ring->doorbell_qpn,
+		  (__force u32)ring->doorbell_qpn,
 		  ring->bf.uar->map + MLX4_SEND_DOORBELL);
 }
 
@@ -1085,13 +1085,35 @@ tx_drop:
 #define MLX4_EN_XDP_TX_REAL_SZ (((CTRL_SIZE + MLX4_EN_XDP_TX_NRTXBB * DS_SIZE) \
 				 / 16) & 0x3f)
 
+void mlx4_en_init_tx_xdp_ring_descs(struct mlx4_en_priv *priv,
+				    struct mlx4_en_tx_ring *ring)
+{
+	int i;
+
+	for (i = 0; i < ring->size; i++) {
+		struct mlx4_en_tx_info *tx_info = &ring->tx_info[i];
+		struct mlx4_en_tx_desc *tx_desc = ring->buf +
+			(i << LOG_TXBB_SIZE);
+
+		tx_info->map0_byte_count = PAGE_SIZE;
+		tx_info->nr_txbb = MLX4_EN_XDP_TX_NRTXBB;
+		tx_info->data_offset = offsetof(struct mlx4_en_tx_desc, data);
+		tx_info->ts_requested = 0;
+		tx_info->nr_maps = 1;
+		tx_info->linear = 1;
+		tx_info->inl = 0;
+
+		tx_desc->data.lkey = ring->mr_key;
+		tx_desc->ctrl.qpn_vlan.fence_size = MLX4_EN_XDP_TX_REAL_SZ;
+		tx_desc->ctrl.srcrb_flags = priv->ctrl_flags;
+	}
+}
+
 netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_rx_alloc *frame,
-			       struct net_device *dev, unsigned int length,
+			       struct mlx4_en_priv *priv, unsigned int length,
 			       int tx_ind, bool *doorbell_pending)
 {
-	struct mlx4_en_priv *priv = netdev_priv(dev);
-	union mlx4_wqe_qpn_vlan	qpn_vlan = {};
 	struct mlx4_en_tx_desc *tx_desc;
 	struct mlx4_en_tx_info *tx_info;
 	struct mlx4_wqe_data_seg *data;
@@ -1123,25 +1145,16 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 	tx_info->page = frame->page;
 	frame->page = NULL;
 	tx_info->map0_dma = dma;
-	tx_info->map0_byte_count = PAGE_SIZE;
-	tx_info->nr_txbb = MLX4_EN_XDP_TX_NRTXBB;
 	tx_info->nr_bytes = max_t(unsigned int, length, ETH_ZLEN);
-	tx_info->data_offset = offsetof(struct mlx4_en_tx_desc, data);
-	tx_info->ts_requested = 0;
-	tx_info->nr_maps = 1;
-	tx_info->linear = 1;
-	tx_info->inl = 0;
 
 	dma_sync_single_range_for_device(priv->ddev, dma, frame->page_offset,
 					 length, PCI_DMA_TODEVICE);
 
 	data->addr = cpu_to_be64(dma + frame->page_offset);
-	data->lkey = ring->mr_key;
 	dma_wmb();
 	data->byte_count = cpu_to_be32(length);
 
 	/* tx completion can avoid cache line miss for common cases */
-	tx_desc->ctrl.srcrb_flags = priv->ctrl_flags;
 
 	op_own = cpu_to_be32(MLX4_OPCODE_SEND) |
 		((ring->prod & ring->size) ?
@@ -1152,10 +1165,13 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 
 	ring->prod += MLX4_EN_XDP_TX_NRTXBB;
 
-	qpn_vlan.fence_size = MLX4_EN_XDP_TX_REAL_SZ;
+	/* Ensure new descriptor hits memory
+	 * before setting ownership of this descriptor to HW
+	 */
+	dma_wmb();
+	tx_desc->ctrl.owner_opcode = op_own;
+	ring->xmit_more++;
 
-	mlx4_en_tx_write_desc(ring, tx_desc, qpn_vlan, TXBB_SIZE, 0,
-			      op_own, false, false);
 	*doorbell_pending = true;
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 16c09949afd5..634f603f941c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -57,12 +57,12 @@ MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: off)");
 #define MLX4_GET(dest, source, offset)				      \
 	do {							      \
 		void *__p = (char *) (source) + (offset);	      \
-		u64 val;                                              \
-		switch (sizeof(dest)) {			      \
+		__be64 val;                                           \
+		switch (sizeof(dest)) {				      \
 		case 1: (dest) = *(u8 *) __p;	    break;	      \
 		case 2: (dest) = be16_to_cpup(__p); break;	      \
 		case 4: (dest) = be32_to_cpup(__p); break;	      \
-		case 8: val = get_unaligned((u64 *)__p);              \
+		case 8: val = get_unaligned((__be64 *)__p);           \
 			(dest) = be64_to_cpu(val);  break;            \
 		default: __buggy_use_of_MLX4_GET();		      \
 		}						      \
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index fdb3ad0cbe54..1856e279a7e0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -399,7 +399,7 @@ struct mlx4_en_profile {
 	u32 active_ports;
 	u32 small_pkt_int;
 	u8 no_reset;
-	u8 num_tx_rings_p_up;
+	u8 max_num_tx_rings_p_up;
 	struct mlx4_en_port_profile prof[MLX4_MAX_PORTS + 1];
 };
 
@@ -693,7 +693,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_rx_alloc *frame,
-			       struct net_device *dev, unsigned int length,
+			       struct mlx4_en_priv *priv, unsigned int length,
 			       int tx_ind, bool *doorbell_pending);
 void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring);
 bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
@@ -705,6 +705,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   int node, int queue_index);
 void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_tx_ring **pring);
+void mlx4_en_init_tx_xdp_ring_descs(struct mlx4_en_priv *priv,
+				    struct mlx4_en_tx_ring *ring);
 int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_tx_ring *ring,
 			     int cq, int user_prio);
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 728a2fb1f5c0..769598f7b6c8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -55,7 +55,7 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
 
 	qp = __mlx4_qp_lookup(dev, qpn);
 	if (qp)
-		atomic_inc(&qp->refcount);
+		refcount_inc(&qp->refcount);
 
 	spin_unlock(&qp_table->lock);
 
@@ -66,7 +66,7 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
 
 	qp->event(qp, event_type);
 
-	if (atomic_dec_and_test(&qp->refcount))
+	if (refcount_dec_and_test(&qp->refcount))
 		complete(&qp->free);
 }
 
@@ -420,7 +420,7 @@ int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp)
 	if (err)
 		goto err_icm;
 
-	atomic_set(&qp->refcount, 1);
+	refcount_set(&qp->refcount, 1);
 	init_completion(&qp->free);
 
 	return 0;
@@ -520,7 +520,7 @@ EXPORT_SYMBOL_GPL(mlx4_qp_remove);
 
 void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp)
 {
-	if (atomic_dec_and_test(&qp->refcount))
+	if (refcount_dec_and_test(&qp->refcount))
 		complete(&qp->free);
 	wait_for_completion(&qp->free);
 
@@ -925,7 +925,7 @@ int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		context->flags &= cpu_to_be32(~(0xf << 28));
 		context->flags |= cpu_to_be32(states[i + 1] << 28);
 		if (states[i + 1] != MLX4_QP_STATE_RTR)
-			context->params2 &= ~MLX4_QP_BIT_FPP;
+			context->params2 &= ~cpu_to_be32(MLX4_QP_BIT_FPP);
 		err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1],
 				     context, 0, 0, qp);
 		if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index fabb53379727..04304dd894c6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -3185,7 +3185,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 	optpar	= be32_to_cpu(*(__be32 *) inbox->buf);
 
 	if (slave != mlx4_master_func_num(dev)) {
-		qp_ctx->params2 &= ~MLX4_QP_BIT_FPP;
+		qp_ctx->params2 &= ~cpu_to_be32(MLX4_QP_BIT_FPP);
 		/* setting QP rate-limit is disallowed for VFs */
 		if (qp_ctx->rate_limit_params)
 			return -EPERM;
diff --git a/drivers/net/ethernet/mellanox/mlx4/srq.c b/drivers/net/ethernet/mellanox/mlx4/srq.c
index bedf52126824..cbe4d9746ddf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/srq.c
@@ -49,7 +49,7 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type)
 	srq = radix_tree_lookup(&srq_table->tree, srqn & (dev->caps.num_srqs - 1));
 	rcu_read_unlock();
 	if (srq)
-		atomic_inc(&srq->refcount);
+		refcount_inc(&srq->refcount);
 	else {
 		mlx4_warn(dev, "Async event for bogus SRQ %08x\n", srqn);
 		return;
@@ -57,7 +57,7 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type)
 
 	srq->event(srq, event_type);
 
-	if (atomic_dec_and_test(&srq->refcount))
+	if (refcount_dec_and_test(&srq->refcount))
 		complete(&srq->free);
 }
 
@@ -203,7 +203,7 @@ int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcd,
 	if (err)
 		goto err_radix;
 
-	atomic_set(&srq->refcount, 1);
+	refcount_set(&srq->refcount, 1);
 	init_completion(&srq->free);
 
 	return 0;
@@ -232,7 +232,7 @@ void mlx4_srq_free(struct mlx4_dev *dev, struct mlx4_srq *srq)
 	radix_tree_delete(&srq_table->tree, srq->srqn);
 	spin_unlock_irq(&srq_table->lock);
 
-	if (atomic_dec_and_test(&srq->refcount))
+	if (refcount_dec_and_test(&srq->refcount))
 		complete(&srq->free);
 	wait_for_completion(&srq->free);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index fdaef00465d7..25deaa5a534c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -6,6 +6,7 @@ config MLX5_CORE
 	tristate "Mellanox Technologies ConnectX-4 and Connect-IB core driver"
 	depends on MAY_USE_DEVLINK
 	depends on PCI
+	imply PTP_1588_CLOCK
 	default n
 	---help---
 	  Core driver for low level functionality of the ConnectX-4 and
@@ -29,7 +30,6 @@ config MLX5_CORE_EN
 	bool "Mellanox Technologies ConnectX-4 Ethernet support"
 	depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE
 	depends on IPV6=y || IPV6=n || MLX5_CORE=m
-	imply PTP_1588_CLOCK
 	default n
 	---help---
 	  Ethernet support in Mellanox Technologies ConnectX-4 NIC.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 714dd0dc5eef..19b21b40ab07 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -5,7 +5,7 @@ subdir-ccflags-y += -I$(src)
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
 		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
-		fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o \
+		fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o lib/clock.o \
 		diag/fs_tracepoint.o
 
 mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o
@@ -14,7 +14,7 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
 		fpga/ipsec.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
-		en_tx.o en_rx.o en_rx_am.o en_txrx.o en_clock.o vxlan.o \
+		en_tx.o en_rx.o en_rx_am.o en_txrx.o en_stats.o vxlan.o \
 		en_arfs.o en_fs_ethtool.o en_selftest.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
@@ -23,7 +23,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc.
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) +=  en_dcbnl.o
 
-mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o
+mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o
 
 mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
 		en_accel/ipsec_stats.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 336d4738b807..1016e05c7ec7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -58,7 +58,7 @@ void mlx5_cq_tasklet_cb(unsigned long data)
 				 tasklet_ctx.list) {
 		list_del_init(&mcq->tasklet_ctx.list);
 		mcq->tasklet_ctx.comp(mcq);
-		if (atomic_dec_and_test(&mcq->refcount))
+		if (refcount_dec_and_test(&mcq->refcount))
 			complete(&mcq->free);
 		if (time_after(jiffies, end))
 			break;
@@ -80,7 +80,7 @@ static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq)
 	 * still arrive.
 	 */
 	if (list_empty_careful(&cq->tasklet_ctx.list)) {
-		atomic_inc(&cq->refcount);
+		refcount_inc(&cq->refcount);
 		list_add_tail(&cq->tasklet_ctx.list, &tasklet_ctx->list);
 	}
 	spin_unlock_irqrestore(&tasklet_ctx->lock, flags);
@@ -94,7 +94,7 @@ void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn)
 	spin_lock(&table->lock);
 	cq = radix_tree_lookup(&table->tree, cqn);
 	if (likely(cq))
-		atomic_inc(&cq->refcount);
+		refcount_inc(&cq->refcount);
 	spin_unlock(&table->lock);
 
 	if (!cq) {
@@ -106,7 +106,7 @@ void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn)
 
 	cq->comp(cq);
 
-	if (atomic_dec_and_test(&cq->refcount))
+	if (refcount_dec_and_test(&cq->refcount))
 		complete(&cq->free);
 }
 
@@ -119,7 +119,7 @@ void mlx5_cq_event(struct mlx5_core_dev *dev, u32 cqn, int event_type)
 
 	cq = radix_tree_lookup(&table->tree, cqn);
 	if (cq)
-		atomic_inc(&cq->refcount);
+		refcount_inc(&cq->refcount);
 
 	spin_unlock(&table->lock);
 
@@ -130,7 +130,7 @@ void mlx5_cq_event(struct mlx5_core_dev *dev, u32 cqn, int event_type)
 
 	cq->event(cq, event_type);
 
-	if (atomic_dec_and_test(&cq->refcount))
+	if (refcount_dec_and_test(&cq->refcount))
 		complete(&cq->free);
 }
 
@@ -159,7 +159,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	cq->cqn = MLX5_GET(create_cq_out, out, cqn);
 	cq->cons_index = 0;
 	cq->arm_sn     = 0;
-	atomic_set(&cq->refcount, 1);
+	refcount_set(&cq->refcount, 1);
 	init_completion(&cq->free);
 	if (!cq->comp)
 		cq->comp = mlx5_add_cq_to_tasklet;
@@ -222,7 +222,7 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 	synchronize_irq(cq->irqn);
 
 	mlx5_debug_cq_remove(dev, cq);
-	if (atomic_dec_and_test(&cq->refcount))
+	if (refcount_dec_and_test(&cq->refcount))
 		complete(&cq->free);
 	wait_for_completion(&cq->free);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index cc13d3dbd366..e613ce02216d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -267,28 +267,6 @@ struct mlx5e_dcbx {
 };
 #endif
 
-#define MAX_PIN_NUM	8
-struct mlx5e_pps {
-	u8                         pin_caps[MAX_PIN_NUM];
-	struct work_struct         out_work;
-	u64                        start[MAX_PIN_NUM];
-	u8                         enabled;
-};
-
-struct mlx5e_tstamp {
-	rwlock_t                   lock;
-	struct cyclecounter        cycles;
-	struct timecounter         clock;
-	struct hwtstamp_config     hwtstamp_config;
-	u32                        nominal_c_mult;
-	unsigned long              overflow_period;
-	struct delayed_work        overflow_work;
-	struct mlx5_core_dev      *mdev;
-	struct ptp_clock          *ptp;
-	struct ptp_clock_info      ptp_info;
-	struct mlx5e_pps           pps_info;
-};
-
 enum {
 	MLX5E_RQ_STATE_ENABLED,
 	MLX5E_RQ_STATE_AM,
@@ -375,9 +353,10 @@ struct mlx5e_txqsq {
 	u8                         min_inline_mode;
 	u16                        edge;
 	struct device             *pdev;
-	struct mlx5e_tstamp       *tstamp;
 	__be32                     mkey_be;
 	unsigned long              state;
+	struct hwtstamp_config    *tstamp;
+	struct mlx5_clock         *clock;
 
 	/* control path */
 	struct mlx5_wq_ctrl        wq_ctrl;
@@ -543,10 +522,11 @@ struct mlx5e_rq {
 	struct mlx5e_channel  *channel;
 	struct device         *pdev;
 	struct net_device     *netdev;
-	struct mlx5e_tstamp   *tstamp;
 	struct mlx5e_rq_stats  stats;
 	struct mlx5e_cq        cq;
 	struct mlx5e_page_cache page_cache;
+	struct hwtstamp_config *tstamp;
+	struct mlx5_clock      *clock;
 
 	mlx5e_fp_handle_rx_cqe handle_rx_cqe;
 	mlx5e_fp_post_rx_wqes  post_wqes;
@@ -588,7 +568,7 @@ struct mlx5e_channel {
 	/* control */
 	struct mlx5e_priv         *priv;
 	struct mlx5_core_dev      *mdev;
-	struct mlx5e_tstamp       *tstamp;
+	struct hwtstamp_config    *tstamp;
 	int                        ix;
 };
 
@@ -789,7 +769,7 @@ struct mlx5e_priv {
 	struct mlx5_core_dev      *mdev;
 	struct net_device         *netdev;
 	struct mlx5e_stats         stats;
-	struct mlx5e_tstamp        tstamp;
+	struct hwtstamp_config     tstamp;
 	u16 q_counter;
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	struct mlx5e_dcbx          dcbx;
@@ -873,12 +853,6 @@ void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv);
 void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv);
 void mlx5e_set_rx_mode_work(struct work_struct *work);
 
-void mlx5e_fill_hwstamp(struct mlx5e_tstamp *clock, u64 timestamp,
-			struct skb_shared_hwtstamps *hwts);
-void mlx5e_timestamp_init(struct mlx5e_priv *priv);
-void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv);
-void mlx5e_pps_event_handler(struct mlx5e_priv *priv,
-			     struct ptp_clock_event *event);
 int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr);
 int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr);
 int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val);
@@ -889,6 +863,7 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
 			   u16 vid);
 void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv);
 void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv);
+void mlx5e_timestamp_set(struct mlx5e_priv *priv);
 
 struct mlx5e_redirect_rqt_param {
 	bool is_rss;
@@ -1081,6 +1056,9 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
 			       struct ethtool_flash *flash);
 
+int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+			    void *cb_priv);
+
 /* mlx5e generic netdev management API */
 struct net_device*
 mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 4614ddfa91eb..6a7c8b04447e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -256,7 +256,7 @@ struct sk_buff *mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
 			goto drop;
 		}
 	mdata = mlx5e_ipsec_add_metadata(skb);
-	if (unlikely(IS_ERR(mdata))) {
+	if (IS_ERR(mdata)) {
 		atomic64_inc(&priv->ipsec->sw_stats.ipsec_tx_drop_metadata);
 		goto drop;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
deleted file mode 100644
index 84dd63e74041..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ /dev/null
@@ -1,619 +0,0 @@
-/*
- * Copyright (c) 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.
- */
-
-#include <linux/clocksource.h>
-#include "en.h"
-
-enum {
-	MLX5E_CYCLES_SHIFT	= 23
-};
-
-enum {
-	MLX5E_PIN_MODE_IN		= 0x0,
-	MLX5E_PIN_MODE_OUT		= 0x1,
-};
-
-enum {
-	MLX5E_OUT_PATTERN_PULSE		= 0x0,
-	MLX5E_OUT_PATTERN_PERIODIC	= 0x1,
-};
-
-enum {
-	MLX5E_EVENT_MODE_DISABLE	= 0x0,
-	MLX5E_EVENT_MODE_REPETETIVE	= 0x1,
-	MLX5E_EVENT_MODE_ONCE_TILL_ARM	= 0x2,
-};
-
-enum {
-	MLX5E_MTPPS_FS_ENABLE			= BIT(0x0),
-	MLX5E_MTPPS_FS_PATTERN			= BIT(0x2),
-	MLX5E_MTPPS_FS_PIN_MODE			= BIT(0x3),
-	MLX5E_MTPPS_FS_TIME_STAMP		= BIT(0x4),
-	MLX5E_MTPPS_FS_OUT_PULSE_DURATION	= BIT(0x5),
-	MLX5E_MTPPS_FS_ENH_OUT_PER_ADJ		= BIT(0x7),
-};
-
-void mlx5e_fill_hwstamp(struct mlx5e_tstamp *tstamp, u64 timestamp,
-			struct skb_shared_hwtstamps *hwts)
-{
-	u64 nsec;
-
-	read_lock(&tstamp->lock);
-	nsec = timecounter_cyc2time(&tstamp->clock, timestamp);
-	read_unlock(&tstamp->lock);
-
-	hwts->hwtstamp = ns_to_ktime(nsec);
-}
-
-static u64 mlx5e_read_internal_timer(const struct cyclecounter *cc)
-{
-	struct mlx5e_tstamp *tstamp = container_of(cc, struct mlx5e_tstamp,
-						   cycles);
-
-	return mlx5_read_internal_timer(tstamp->mdev) & cc->mask;
-}
-
-static void mlx5e_pps_out(struct work_struct *work)
-{
-	struct mlx5e_pps *pps_info = container_of(work, struct mlx5e_pps,
-						  out_work);
-	struct mlx5e_tstamp *tstamp = container_of(pps_info, struct mlx5e_tstamp,
-						   pps_info);
-	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
-	unsigned long flags;
-	int i;
-
-	for (i = 0; i < tstamp->ptp_info.n_pins; i++) {
-		u64 tstart;
-
-		write_lock_irqsave(&tstamp->lock, flags);
-		tstart = tstamp->pps_info.start[i];
-		tstamp->pps_info.start[i] = 0;
-		write_unlock_irqrestore(&tstamp->lock, flags);
-		if (!tstart)
-			continue;
-
-		MLX5_SET(mtpps_reg, in, pin, i);
-		MLX5_SET64(mtpps_reg, in, time_stamp, tstart);
-		MLX5_SET(mtpps_reg, in, field_select, MLX5E_MTPPS_FS_TIME_STAMP);
-		mlx5_set_mtpps(tstamp->mdev, in, sizeof(in));
-	}
-}
-
-static void mlx5e_timestamp_overflow(struct work_struct *work)
-{
-	struct delayed_work *dwork = to_delayed_work(work);
-	struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp,
-						   overflow_work);
-	struct mlx5e_priv *priv = container_of(tstamp, struct mlx5e_priv, tstamp);
-	unsigned long flags;
-
-	write_lock_irqsave(&tstamp->lock, flags);
-	timecounter_read(&tstamp->clock);
-	write_unlock_irqrestore(&tstamp->lock, flags);
-	queue_delayed_work(priv->wq, &tstamp->overflow_work,
-			   msecs_to_jiffies(tstamp->overflow_period * 1000));
-}
-
-int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
-{
-	struct hwtstamp_config config;
-	int err;
-
-	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
-		return -EOPNOTSUPP;
-
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	/* TX HW timestamp */
-	switch (config.tx_type) {
-	case HWTSTAMP_TX_OFF:
-	case HWTSTAMP_TX_ON:
-		break;
-	default:
-		return -ERANGE;
-	}
-
-	mutex_lock(&priv->state_lock);
-	/* RX HW timestamp */
-	switch (config.rx_filter) {
-	case HWTSTAMP_FILTER_NONE:
-		/* Reset CQE compression to Admin default */
-		mlx5e_modify_rx_cqe_compression_locked(priv, priv->channels.params.rx_cqe_compress_def);
-		break;
-	case HWTSTAMP_FILTER_ALL:
-	case HWTSTAMP_FILTER_SOME:
-	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_L4_EVENT:
-	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
-	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:
-	case HWTSTAMP_FILTER_PTP_V2_EVENT:
-	case HWTSTAMP_FILTER_PTP_V2_SYNC:
-	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-	case HWTSTAMP_FILTER_NTP_ALL:
-		/* Disable CQE compression */
-		netdev_warn(priv->netdev, "Disabling cqe compression");
-		err = mlx5e_modify_rx_cqe_compression_locked(priv, false);
-		if (err) {
-			netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err);
-			mutex_unlock(&priv->state_lock);
-			return err;
-		}
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
-		break;
-	default:
-		mutex_unlock(&priv->state_lock);
-		return -ERANGE;
-	}
-
-	memcpy(&priv->tstamp.hwtstamp_config, &config, sizeof(config));
-	mutex_unlock(&priv->state_lock);
-
-	return copy_to_user(ifr->ifr_data, &config,
-			    sizeof(config)) ? -EFAULT : 0;
-}
-
-int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr)
-{
-	struct hwtstamp_config *cfg = &priv->tstamp.hwtstamp_config;
-
-	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
-		return -EOPNOTSUPP;
-
-	return copy_to_user(ifr->ifr_data, cfg, sizeof(*cfg)) ? -EFAULT : 0;
-}
-
-static int mlx5e_ptp_settime(struct ptp_clock_info *ptp,
-			     const struct timespec64 *ts)
-{
-	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
-						   ptp_info);
-	u64 ns = timespec64_to_ns(ts);
-	unsigned long flags;
-
-	write_lock_irqsave(&tstamp->lock, flags);
-	timecounter_init(&tstamp->clock, &tstamp->cycles, ns);
-	write_unlock_irqrestore(&tstamp->lock, flags);
-
-	return 0;
-}
-
-static int mlx5e_ptp_gettime(struct ptp_clock_info *ptp,
-			     struct timespec64 *ts)
-{
-	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
-						   ptp_info);
-	u64 ns;
-	unsigned long flags;
-
-	write_lock_irqsave(&tstamp->lock, flags);
-	ns = timecounter_read(&tstamp->clock);
-	write_unlock_irqrestore(&tstamp->lock, flags);
-
-	*ts = ns_to_timespec64(ns);
-
-	return 0;
-}
-
-static int mlx5e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
-{
-	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
-						   ptp_info);
-	unsigned long flags;
-
-	write_lock_irqsave(&tstamp->lock, flags);
-	timecounter_adjtime(&tstamp->clock, delta);
-	write_unlock_irqrestore(&tstamp->lock, flags);
-
-	return 0;
-}
-
-static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
-{
-	u64 adj;
-	u32 diff;
-	unsigned long flags;
-	int neg_adj = 0;
-	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
-						  ptp_info);
-
-	if (delta < 0) {
-		neg_adj = 1;
-		delta = -delta;
-	}
-
-	adj = tstamp->nominal_c_mult;
-	adj *= delta;
-	diff = div_u64(adj, 1000000000ULL);
-
-	write_lock_irqsave(&tstamp->lock, flags);
-	timecounter_read(&tstamp->clock);
-	tstamp->cycles.mult = neg_adj ? tstamp->nominal_c_mult - diff :
-					tstamp->nominal_c_mult + diff;
-	write_unlock_irqrestore(&tstamp->lock, flags);
-
-	return 0;
-}
-
-static int mlx5e_extts_configure(struct ptp_clock_info *ptp,
-				 struct ptp_clock_request *rq,
-				 int on)
-{
-	struct mlx5e_tstamp *tstamp =
-		container_of(ptp, struct mlx5e_tstamp, ptp_info);
-	struct mlx5e_priv *priv =
-		container_of(tstamp, struct mlx5e_priv, tstamp);
-	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
-	u32 field_select = 0;
-	u8 pin_mode = 0;
-	u8 pattern = 0;
-	int pin = -1;
-	int err = 0;
-
-	if (!MLX5_PPS_CAP(priv->mdev))
-		return -EOPNOTSUPP;
-
-	if (rq->extts.index >= tstamp->ptp_info.n_pins)
-		return -EINVAL;
-
-	if (on) {
-		pin = ptp_find_pin(tstamp->ptp, PTP_PF_EXTTS, rq->extts.index);
-		if (pin < 0)
-			return -EBUSY;
-		pin_mode = MLX5E_PIN_MODE_IN;
-		pattern = !!(rq->extts.flags & PTP_FALLING_EDGE);
-		field_select = MLX5E_MTPPS_FS_PIN_MODE |
-			       MLX5E_MTPPS_FS_PATTERN |
-			       MLX5E_MTPPS_FS_ENABLE;
-	} else {
-		pin = rq->extts.index;
-		field_select = MLX5E_MTPPS_FS_ENABLE;
-	}
-
-	MLX5_SET(mtpps_reg, in, pin, pin);
-	MLX5_SET(mtpps_reg, in, pin_mode, pin_mode);
-	MLX5_SET(mtpps_reg, in, pattern, pattern);
-	MLX5_SET(mtpps_reg, in, enable, on);
-	MLX5_SET(mtpps_reg, in, field_select, field_select);
-
-	err = mlx5_set_mtpps(priv->mdev, in, sizeof(in));
-	if (err)
-		return err;
-
-	return mlx5_set_mtppse(priv->mdev, pin, 0,
-			       MLX5E_EVENT_MODE_REPETETIVE & on);
-}
-
-static int mlx5e_perout_configure(struct ptp_clock_info *ptp,
-				  struct ptp_clock_request *rq,
-				  int on)
-{
-	struct mlx5e_tstamp *tstamp =
-		container_of(ptp, struct mlx5e_tstamp, ptp_info);
-	struct mlx5e_priv *priv =
-		container_of(tstamp, struct mlx5e_priv, tstamp);
-	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
-	u64 nsec_now, nsec_delta, time_stamp = 0;
-	u64 cycles_now, cycles_delta;
-	struct timespec64 ts;
-	unsigned long flags;
-	u32 field_select = 0;
-	u8 pin_mode = 0;
-	u8 pattern = 0;
-	int pin = -1;
-	int err = 0;
-	s64 ns;
-
-	if (!MLX5_PPS_CAP(priv->mdev))
-		return -EOPNOTSUPP;
-
-	if (rq->perout.index >= tstamp->ptp_info.n_pins)
-		return -EINVAL;
-
-	if (on) {
-		pin = ptp_find_pin(tstamp->ptp, PTP_PF_PEROUT,
-				   rq->perout.index);
-		if (pin < 0)
-			return -EBUSY;
-
-		pin_mode = MLX5E_PIN_MODE_OUT;
-		pattern = MLX5E_OUT_PATTERN_PERIODIC;
-		ts.tv_sec = rq->perout.period.sec;
-		ts.tv_nsec = rq->perout.period.nsec;
-		ns = timespec64_to_ns(&ts);
-
-		if ((ns >> 1) != 500000000LL)
-			return -EINVAL;
-
-		ts.tv_sec = rq->perout.start.sec;
-		ts.tv_nsec = rq->perout.start.nsec;
-		ns = timespec64_to_ns(&ts);
-		cycles_now = mlx5_read_internal_timer(tstamp->mdev);
-		write_lock_irqsave(&tstamp->lock, flags);
-		nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now);
-		nsec_delta = ns - nsec_now;
-		cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift,
-					 tstamp->cycles.mult);
-		write_unlock_irqrestore(&tstamp->lock, flags);
-		time_stamp = cycles_now + cycles_delta;
-		field_select = MLX5E_MTPPS_FS_PIN_MODE |
-			       MLX5E_MTPPS_FS_PATTERN |
-			       MLX5E_MTPPS_FS_ENABLE |
-			       MLX5E_MTPPS_FS_TIME_STAMP;
-	} else {
-		pin = rq->perout.index;
-		field_select = MLX5E_MTPPS_FS_ENABLE;
-	}
-
-	MLX5_SET(mtpps_reg, in, pin, pin);
-	MLX5_SET(mtpps_reg, in, pin_mode, pin_mode);
-	MLX5_SET(mtpps_reg, in, pattern, pattern);
-	MLX5_SET(mtpps_reg, in, enable, on);
-	MLX5_SET64(mtpps_reg, in, time_stamp, time_stamp);
-	MLX5_SET(mtpps_reg, in, field_select, field_select);
-
-	err = mlx5_set_mtpps(priv->mdev, in, sizeof(in));
-	if (err)
-		return err;
-
-	return mlx5_set_mtppse(priv->mdev, pin, 0,
-			       MLX5E_EVENT_MODE_REPETETIVE & on);
-}
-
-static int mlx5e_pps_configure(struct ptp_clock_info *ptp,
-			       struct ptp_clock_request *rq,
-			       int on)
-{
-	struct mlx5e_tstamp *tstamp =
-		container_of(ptp, struct mlx5e_tstamp, ptp_info);
-
-	tstamp->pps_info.enabled = !!on;
-	return 0;
-}
-
-static int mlx5e_ptp_enable(struct ptp_clock_info *ptp,
-			    struct ptp_clock_request *rq,
-			    int on)
-{
-	switch (rq->type) {
-	case PTP_CLK_REQ_EXTTS:
-		return mlx5e_extts_configure(ptp, rq, on);
-	case PTP_CLK_REQ_PEROUT:
-		return mlx5e_perout_configure(ptp, rq, on);
-	case PTP_CLK_REQ_PPS:
-		return mlx5e_pps_configure(ptp, rq, on);
-	default:
-		return -EOPNOTSUPP;
-	}
-	return 0;
-}
-
-static int mlx5e_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
-			    enum ptp_pin_function func, unsigned int chan)
-{
-	return (func == PTP_PF_PHYSYNC) ? -EOPNOTSUPP : 0;
-}
-
-static const struct ptp_clock_info mlx5e_ptp_clock_info = {
-	.owner		= THIS_MODULE,
-	.max_adj	= 100000000,
-	.n_alarm	= 0,
-	.n_ext_ts	= 0,
-	.n_per_out	= 0,
-	.n_pins		= 0,
-	.pps		= 0,
-	.adjfreq	= mlx5e_ptp_adjfreq,
-	.adjtime	= mlx5e_ptp_adjtime,
-	.gettime64	= mlx5e_ptp_gettime,
-	.settime64	= mlx5e_ptp_settime,
-	.enable		= NULL,
-	.verify		= NULL,
-};
-
-static void mlx5e_timestamp_init_config(struct mlx5e_tstamp *tstamp)
-{
-	tstamp->hwtstamp_config.tx_type = HWTSTAMP_TX_OFF;
-	tstamp->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
-}
-
-static int mlx5e_init_pin_config(struct mlx5e_tstamp *tstamp)
-{
-	int i;
-
-	tstamp->ptp_info.pin_config =
-		kzalloc(sizeof(*tstamp->ptp_info.pin_config) *
-			       tstamp->ptp_info.n_pins, GFP_KERNEL);
-	if (!tstamp->ptp_info.pin_config)
-		return -ENOMEM;
-	tstamp->ptp_info.enable = mlx5e_ptp_enable;
-	tstamp->ptp_info.verify = mlx5e_ptp_verify;
-	tstamp->ptp_info.pps = 1;
-
-	for (i = 0; i < tstamp->ptp_info.n_pins; i++) {
-		snprintf(tstamp->ptp_info.pin_config[i].name,
-			 sizeof(tstamp->ptp_info.pin_config[i].name),
-			 "mlx5_pps%d", i);
-		tstamp->ptp_info.pin_config[i].index = i;
-		tstamp->ptp_info.pin_config[i].func = PTP_PF_NONE;
-		tstamp->ptp_info.pin_config[i].chan = i;
-	}
-
-	return 0;
-}
-
-static void mlx5e_get_pps_caps(struct mlx5e_priv *priv,
-			       struct mlx5e_tstamp *tstamp)
-{
-	u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
-
-	mlx5_query_mtpps(priv->mdev, out, sizeof(out));
-
-	tstamp->ptp_info.n_pins = MLX5_GET(mtpps_reg, out,
-					   cap_number_of_pps_pins);
-	tstamp->ptp_info.n_ext_ts = MLX5_GET(mtpps_reg, out,
-					     cap_max_num_of_pps_in_pins);
-	tstamp->ptp_info.n_per_out = MLX5_GET(mtpps_reg, out,
-					      cap_max_num_of_pps_out_pins);
-
-	tstamp->pps_info.pin_caps[0] = MLX5_GET(mtpps_reg, out, cap_pin_0_mode);
-	tstamp->pps_info.pin_caps[1] = MLX5_GET(mtpps_reg, out, cap_pin_1_mode);
-	tstamp->pps_info.pin_caps[2] = MLX5_GET(mtpps_reg, out, cap_pin_2_mode);
-	tstamp->pps_info.pin_caps[3] = MLX5_GET(mtpps_reg, out, cap_pin_3_mode);
-	tstamp->pps_info.pin_caps[4] = MLX5_GET(mtpps_reg, out, cap_pin_4_mode);
-	tstamp->pps_info.pin_caps[5] = MLX5_GET(mtpps_reg, out, cap_pin_5_mode);
-	tstamp->pps_info.pin_caps[6] = MLX5_GET(mtpps_reg, out, cap_pin_6_mode);
-	tstamp->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode);
-}
-
-void mlx5e_pps_event_handler(struct mlx5e_priv *priv,
-			     struct ptp_clock_event *event)
-{
-	struct net_device *netdev = priv->netdev;
-	struct mlx5e_tstamp *tstamp = &priv->tstamp;
-	struct timespec64 ts;
-	u64 nsec_now, nsec_delta;
-	u64 cycles_now, cycles_delta;
-	int pin = event->index;
-	s64 ns;
-	unsigned long flags;
-
-	switch (tstamp->ptp_info.pin_config[pin].func) {
-	case PTP_PF_EXTTS:
-		if (tstamp->pps_info.enabled) {
-			event->type = PTP_CLOCK_PPSUSR;
-			event->pps_times.ts_real = ns_to_timespec64(event->timestamp);
-		} else {
-			event->type = PTP_CLOCK_EXTTS;
-		}
-		ptp_clock_event(tstamp->ptp, event);
-		break;
-	case PTP_PF_PEROUT:
-		mlx5e_ptp_gettime(&tstamp->ptp_info, &ts);
-		cycles_now = mlx5_read_internal_timer(tstamp->mdev);
-		ts.tv_sec += 1;
-		ts.tv_nsec = 0;
-		ns = timespec64_to_ns(&ts);
-		write_lock_irqsave(&tstamp->lock, flags);
-		nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now);
-		nsec_delta = ns - nsec_now;
-		cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift,
-					 tstamp->cycles.mult);
-		tstamp->pps_info.start[pin] = cycles_now + cycles_delta;
-		queue_work(priv->wq, &tstamp->pps_info.out_work);
-		write_unlock_irqrestore(&tstamp->lock, flags);
-		break;
-	default:
-		netdev_err(netdev, "%s: Unhandled event\n", __func__);
-	}
-}
-
-void mlx5e_timestamp_init(struct mlx5e_priv *priv)
-{
-	struct mlx5e_tstamp *tstamp = &priv->tstamp;
-	u64 ns;
-	u64 frac = 0;
-	u32 dev_freq;
-
-	mlx5e_timestamp_init_config(tstamp);
-	dev_freq = MLX5_CAP_GEN(priv->mdev, device_frequency_khz);
-	if (!dev_freq) {
-		mlx5_core_warn(priv->mdev, "invalid device_frequency_khz, aborting HW clock init\n");
-		return;
-	}
-	rwlock_init(&tstamp->lock);
-	tstamp->cycles.read = mlx5e_read_internal_timer;
-	tstamp->cycles.shift = MLX5E_CYCLES_SHIFT;
-	tstamp->cycles.mult = clocksource_khz2mult(dev_freq,
-						   tstamp->cycles.shift);
-	tstamp->nominal_c_mult = tstamp->cycles.mult;
-	tstamp->cycles.mask = CLOCKSOURCE_MASK(41);
-	tstamp->mdev = priv->mdev;
-
-	timecounter_init(&tstamp->clock, &tstamp->cycles,
-			 ktime_to_ns(ktime_get_real()));
-
-	/* Calculate period in seconds to call the overflow watchdog - to make
-	 * sure counter is checked at least once every wrap around.
-	 */
-	ns = cyclecounter_cyc2ns(&tstamp->cycles, tstamp->cycles.mask,
-				 frac, &frac);
-	do_div(ns, NSEC_PER_SEC / 2 / HZ);
-	tstamp->overflow_period = ns;
-
-	INIT_WORK(&tstamp->pps_info.out_work, mlx5e_pps_out);
-	INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow);
-	if (tstamp->overflow_period)
-		queue_delayed_work(priv->wq, &tstamp->overflow_work, 0);
-	else
-		mlx5_core_warn(priv->mdev, "invalid overflow period, overflow_work is not scheduled\n");
-
-	/* Configure the PHC */
-	tstamp->ptp_info = mlx5e_ptp_clock_info;
-	snprintf(tstamp->ptp_info.name, 16, "mlx5 ptp");
-
-	/* Initialize 1PPS data structures */
-	if (MLX5_PPS_CAP(priv->mdev))
-		mlx5e_get_pps_caps(priv, tstamp);
-	if (tstamp->ptp_info.n_pins)
-		mlx5e_init_pin_config(tstamp);
-
-	tstamp->ptp = ptp_clock_register(&tstamp->ptp_info,
-					 &priv->mdev->pdev->dev);
-	if (IS_ERR(tstamp->ptp)) {
-		mlx5_core_warn(priv->mdev, "ptp_clock_register failed %ld\n",
-			       PTR_ERR(tstamp->ptp));
-		tstamp->ptp = NULL;
-	}
-}
-
-void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv)
-{
-	struct mlx5e_tstamp *tstamp = &priv->tstamp;
-
-	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
-		return;
-
-	if (priv->tstamp.ptp) {
-		ptp_clock_unregister(priv->tstamp.ptp);
-		priv->tstamp.ptp = NULL;
-	}
-
-	cancel_work_sync(&tstamp->pps_info.out_work);
-	cancel_delayed_work_sync(&tstamp->overflow_work);
-	kfree(tstamp->ptp_info.pin_config);
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index ece3fb147e3e..157d02917237 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -134,6 +134,7 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 	mlx5_core_destroy_mkey(mdev, &res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
 	mlx5_core_dealloc_pd(mdev, res->pdn);
+	memset(res, 0, sizeof(*res));
 }
 
 int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index d12e9fc0d76b..b34aa8efb036 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -31,7 +31,6 @@
  */
 
 #include "en.h"
-#include "en_accel/ipsec.h"
 
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo)
@@ -136,59 +135,15 @@ void mlx5e_build_ptys2ethtool_map(void)
 				       ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT);
 }
 
-static unsigned long mlx5e_query_pfc_combined(struct mlx5e_priv *priv)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	u8 pfc_en_tx;
-	u8 pfc_en_rx;
-	int err;
-
-	if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
-		return 0;
-
-	err = mlx5_query_port_pfc(mdev, &pfc_en_tx, &pfc_en_rx);
-
-	return err ? 0 : pfc_en_tx | pfc_en_rx;
-}
-
-static bool mlx5e_query_global_pause_combined(struct mlx5e_priv *priv)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	u32 rx_pause;
-	u32 tx_pause;
-	int err;
-
-	if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
-		return false;
-
-	err = mlx5_query_port_pause(mdev, &rx_pause, &tx_pause);
-
-	return err ? false : rx_pause | tx_pause;
-}
-
-#define MLX5E_NUM_Q_CNTRS(priv) (NUM_Q_COUNTERS * (!!priv->q_counter))
-#define MLX5E_NUM_RQ_STATS(priv) (NUM_RQ_STATS * (priv)->channels.num)
-#define MLX5E_NUM_SQ_STATS(priv) \
-	(NUM_SQ_STATS * (priv)->channels.num * (priv)->channels.params.num_tc)
-#define MLX5E_NUM_PFC_COUNTERS(priv) \
-	((mlx5e_query_global_pause_combined(priv) + hweight8(mlx5e_query_pfc_combined(priv))) * \
-	  NUM_PPORT_PER_PRIO_PFC_COUNTERS)
-
 int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset)
 {
+	int i, num_stats = 0;
+
 	switch (sset) {
 	case ETH_SS_STATS:
-		return NUM_SW_COUNTERS +
-		       MLX5E_NUM_Q_CNTRS(priv) +
-		       NUM_VPORT_COUNTERS + NUM_PPORT_COUNTERS(priv) +
-		       NUM_PCIE_COUNTERS(priv) +
-		       MLX5E_NUM_RQ_STATS(priv) +
-		       MLX5E_NUM_SQ_STATS(priv) +
-		       MLX5E_NUM_PFC_COUNTERS(priv) +
-		       ARRAY_SIZE(mlx5e_pme_status_desc) +
-		       ARRAY_SIZE(mlx5e_pme_error_desc) +
-		       mlx5e_ipsec_get_count(priv);
-
+		for (i = 0; i < mlx5e_num_stats_grps; i++)
+			num_stats += mlx5e_stats_grps[i].get_num_stats(priv);
+		return num_stats;
 	case ETH_SS_PRIV_FLAGS:
 		return ARRAY_SIZE(mlx5e_priv_flags);
 	case ETH_SS_TEST:
@@ -208,104 +163,10 @@ static int mlx5e_get_sset_count(struct net_device *dev, int sset)
 
 static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, u8 *data)
 {
-	int i, j, tc, prio, idx = 0;
-	unsigned long pfc_combined;
-
-	/* SW counters */
-	for (i = 0; i < NUM_SW_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, sw_stats_desc[i].format);
-
-	/* Q counters */
-	for (i = 0; i < MLX5E_NUM_Q_CNTRS(priv); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].format);
-
-	/* VPORT counters */
-	for (i = 0; i < NUM_VPORT_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       vport_stats_desc[i].format);
-
-	/* PPORT counters */
-	for (i = 0; i < NUM_PPORT_802_3_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_802_3_stats_desc[i].format);
-
-	for (i = 0; i < NUM_PPORT_2863_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_2863_stats_desc[i].format);
-
-	for (i = 0; i < NUM_PPORT_2819_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_2819_stats_desc[i].format);
-
-	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS(priv); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_phy_statistical_stats_desc[i].format);
-
-	for (i = 0; i < NUM_PPORT_ETH_EXT_COUNTERS(priv); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_eth_ext_stats_desc[i].format);
-
-	for (i = 0; i < NUM_PCIE_PERF_COUNTERS(priv); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pcie_perf_stats_desc[i].format);
-
-	for (i = 0; i < NUM_PCIE_PERF_COUNTERS64(priv); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pcie_perf_stats_desc64[i].format);
-
-	for (i = 0; i < NUM_PCIE_PERF_STALL_COUNTERS(priv); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pcie_perf_stall_stats_desc[i].format);
-
-	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
-		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				pport_per_prio_traffic_stats_desc[i].format, prio);
-	}
-
-	pfc_combined = mlx5e_query_pfc_combined(priv);
-	for_each_set_bit(prio, &pfc_combined, NUM_PPORT_PRIO) {
-		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
-			char pfc_string[ETH_GSTRING_LEN];
-
-			snprintf(pfc_string, sizeof(pfc_string), "prio%d", prio);
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				pport_per_prio_pfc_stats_desc[i].format, pfc_string);
-		}
-	}
-
-	if (mlx5e_query_global_pause_combined(priv)) {
-		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				pport_per_prio_pfc_stats_desc[i].format, "global");
-		}
-	}
-
-	/* port module event counters */
-	for (i = 0; i < ARRAY_SIZE(mlx5e_pme_status_desc); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, mlx5e_pme_status_desc[i].format);
-
-	for (i = 0; i < ARRAY_SIZE(mlx5e_pme_error_desc); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, mlx5e_pme_error_desc[i].format);
-
-	/* IPSec counters */
-	idx += mlx5e_ipsec_get_strings(priv, data + idx * ETH_GSTRING_LEN);
-
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		return;
+	int i, idx = 0;
 
-	/* per channel counters */
-	for (i = 0; i < priv->channels.num; i++)
-		for (j = 0; j < NUM_RQ_STATS; j++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				rq_stats_desc[j].format, i);
-
-	for (tc = 0; tc < priv->channels.params.num_tc; tc++)
-		for (i = 0; i < priv->channels.num; i++)
-			for (j = 0; j < NUM_SQ_STATS; j++)
-				sprintf(data + (idx++) * ETH_GSTRING_LEN,
-					sq_stats_desc[j].format,
-					priv->channel_tc2txq[i][tc]);
+	for (i = 0; i < mlx5e_num_stats_grps; i++)
+		idx = mlx5e_stats_grps[i].fill_strings(priv, data, idx);
 }
 
 void mlx5e_ethtool_get_strings(struct mlx5e_priv *priv, u32 stringset, u8 *data)
@@ -340,10 +201,7 @@ static void mlx5e_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 void mlx5e_ethtool_get_ethtool_stats(struct mlx5e_priv *priv,
 				     struct ethtool_stats *stats, u64 *data)
 {
-	struct mlx5e_channels *channels;
-	struct mlx5_priv *mlx5_priv;
-	int i, j, tc, prio, idx = 0;
-	unsigned long pfc_combined;
+	int i, idx = 0;
 
 	if (!data)
 		return;
@@ -351,102 +209,10 @@ void mlx5e_ethtool_get_ethtool_stats(struct mlx5e_priv *priv,
 	mutex_lock(&priv->state_lock);
 	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
 		mlx5e_update_stats(priv, true);
-	channels = &priv->channels;
 	mutex_unlock(&priv->state_lock);
 
-	for (i = 0; i < NUM_SW_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.sw,
-						   sw_stats_desc, i);
-
-	for (i = 0; i < MLX5E_NUM_Q_CNTRS(priv); i++)
-		data[idx++] = MLX5E_READ_CTR32_CPU(&priv->stats.qcnt,
-						   q_stats_desc, i);
-
-	for (i = 0; i < NUM_VPORT_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(priv->stats.vport.query_vport_out,
-						  vport_stats_desc, i);
-
-	for (i = 0; i < NUM_PPORT_802_3_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.IEEE_802_3_counters,
-						  pport_802_3_stats_desc, i);
-
-	for (i = 0; i < NUM_PPORT_2863_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.RFC_2863_counters,
-						  pport_2863_stats_desc, i);
-
-	for (i = 0; i < NUM_PPORT_2819_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.RFC_2819_counters,
-						  pport_2819_stats_desc, i);
-
-	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS(priv); i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.phy_statistical_counters,
-						  pport_phy_statistical_stats_desc, i);
-
-	for (i = 0; i < NUM_PPORT_ETH_EXT_COUNTERS(priv); i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.eth_ext_counters,
-						  pport_eth_ext_stats_desc, i);
-
-	for (i = 0; i < NUM_PCIE_PERF_COUNTERS(priv); i++)
-		data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters,
-						  pcie_perf_stats_desc, i);
-
-	for (i = 0; i < NUM_PCIE_PERF_COUNTERS64(priv); i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pcie.pcie_perf_counters,
-						  pcie_perf_stats_desc64, i);
-
-	for (i = 0; i < NUM_PCIE_PERF_STALL_COUNTERS(priv); i++)
-		data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters,
-						  pcie_perf_stall_stats_desc, i);
-
-	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
-		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
-			data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio],
-						 pport_per_prio_traffic_stats_desc, i);
-	}
-
-	pfc_combined = mlx5e_query_pfc_combined(priv);
-	for_each_set_bit(prio, &pfc_combined, NUM_PPORT_PRIO) {
-		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
-			data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio],
-							  pport_per_prio_pfc_stats_desc, i);
-		}
-	}
-
-	if (mlx5e_query_global_pause_combined(priv)) {
-		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
-			data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[0],
-							  pport_per_prio_pfc_stats_desc, i);
-		}
-	}
-
-	/* port module event counters */
-	mlx5_priv =  &priv->mdev->priv;
-	for (i = 0; i < ARRAY_SIZE(mlx5e_pme_status_desc); i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.status_counters,
-						   mlx5e_pme_status_desc, i);
-
-	for (i = 0; i < ARRAY_SIZE(mlx5e_pme_error_desc); i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.error_counters,
-						   mlx5e_pme_error_desc, i);
-
-	/* IPSec counters */
-	idx += mlx5e_ipsec_get_stats(priv, data + idx);
-
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		return;
-
-	/* per channel counters */
-	for (i = 0; i < channels->num; i++)
-		for (j = 0; j < NUM_RQ_STATS; j++)
-			data[idx++] =
-			       MLX5E_READ_CTR64_CPU(&channels->c[i]->rq.stats,
-						    rq_stats_desc, j);
-
-	for (tc = 0; tc < priv->channels.params.num_tc; tc++)
-		for (i = 0; i < channels->num; i++)
-			for (j = 0; j < NUM_SQ_STATS; j++)
-				data[idx++] = MLX5E_READ_CTR64_CPU(&channels->c[i]->sq[tc].stats,
-								   sq_stats_desc, j);
+	for (i = 0; i < mlx5e_num_stats_grps; i++)
+		idx = mlx5e_stats_grps[i].fill_stats(priv, data, idx);
 }
 
 static void mlx5e_get_ethtool_stats(struct net_device *dev,
@@ -1417,14 +1183,15 @@ static int mlx5e_set_pauseparam(struct net_device *netdev,
 int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 			      struct ethtool_ts_info *info)
 {
+	struct mlx5_core_dev *mdev = priv->mdev;
 	int ret;
 
 	ret = ethtool_op_get_ts_info(priv->netdev, info);
 	if (ret)
 		return ret;
 
-	info->phc_index = priv->tstamp.ptp ?
-			  ptp_clock_index(priv->tstamp.ptp) : -1;
+	info->phc_index = mdev->clock.ptp ?
+			  ptp_clock_index(mdev->clock.ptp) : -1;
 
 	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
 		return 0;
@@ -1754,7 +1521,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev,
 	if (!MLX5_CAP_GEN(mdev, cqe_compression))
 		return -EOPNOTSUPP;
 
-	if (enable && priv->tstamp.hwtstamp_config.rx_filter != HWTSTAMP_FILTER_NONE) {
+	if (enable && priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE) {
 		netdev_err(netdev, "Can't enable cqe compression while timestamping is enabled.\n");
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cc11bbbd0309..28ae00b3eb88 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -373,8 +373,6 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
 			      enum mlx5_dev_event event, unsigned long param)
 {
 	struct mlx5e_priv *priv = vpriv;
-	struct ptp_clock_event ptp_event;
-	struct mlx5_eqe *eqe = NULL;
 
 	if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state))
 		return;
@@ -384,14 +382,6 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
 	case MLX5_DEV_EVENT_PORT_DOWN:
 		queue_work(priv->wq, &priv->update_carrier_work);
 		break;
-	case MLX5_DEV_EVENT_PPS:
-		eqe = (struct mlx5_eqe *)param;
-		ptp_event.index = eqe->data.pps.pin;
-		ptp_event.timestamp =
-			timecounter_cyc2time(&priv->tstamp.clock,
-					     be64_to_cpu(eqe->data.pps.time_stamp));
-		mlx5e_pps_event_handler(vpriv, &ptp_event);
-		break;
 	default:
 		break;
 	}
@@ -585,6 +575,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	rq->pdev    = c->pdev;
 	rq->netdev  = c->netdev;
 	rq->tstamp  = c->tstamp;
+	rq->clock   = &mdev->clock;
 	rq->channel = c;
 	rq->ix      = c->ix;
 	rq->mdev    = mdev;
@@ -1123,6 +1114,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 
 	sq->pdev      = c->pdev;
 	sq->tstamp    = c->tstamp;
+	sq->clock     = &mdev->clock;
 	sq->mkey_be   = c->mkey_be;
 	sq->channel   = c;
 	sq->txq_ix    = txq_ix;
@@ -2678,6 +2670,12 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
 		netif_carrier_on(netdev);
 }
 
+void mlx5e_timestamp_set(struct mlx5e_priv *priv)
+{
+	priv->tstamp.tx_type   = HWTSTAMP_TX_OFF;
+	priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE;
+}
+
 int mlx5e_open_locked(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -2693,7 +2691,7 @@ int mlx5e_open_locked(struct net_device *netdev)
 	mlx5e_activate_priv_channels(priv);
 	if (priv->profile->update_carrier)
 		priv->profile->update_carrier(priv);
-	mlx5e_timestamp_init(priv);
+	mlx5e_timestamp_set(priv);
 
 	if (priv->profile->update_stats)
 		queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
@@ -2731,7 +2729,6 @@ int mlx5e_close_locked(struct net_device *netdev)
 
 	clear_bit(MLX5E_STATE_OPENED, &priv->state);
 
-	mlx5e_timestamp_cleanup(priv);
 	netif_carrier_off(priv->netdev);
 	mlx5e_deactivate_priv_channels(priv);
 	mlx5e_close_channels(&priv->channels);
@@ -3086,13 +3083,10 @@ out:
 }
 
 #ifdef CONFIG_MLX5_ESWITCH
-static int mlx5e_setup_tc_cls_flower(struct net_device *dev,
+static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv,
 				     struct tc_cls_flower_offload *cls_flower)
 {
-	struct mlx5e_priv *priv = netdev_priv(dev);
-
-	if (!is_classid_clsact_ingress(cls_flower->common.classid) ||
-	    cls_flower->common.chain_index)
+	if (cls_flower->common.chain_index)
 		return -EOPNOTSUPP;
 
 	switch (cls_flower->command) {
@@ -3106,15 +3100,52 @@ static int mlx5e_setup_tc_cls_flower(struct net_device *dev,
 		return -EOPNOTSUPP;
 	}
 }
+
+int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+			    void *cb_priv)
+{
+	struct mlx5e_priv *priv = cb_priv;
+
+	if (!tc_can_offload(priv->netdev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return mlx5e_setup_tc_cls_flower(priv, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlx5e_setup_tc_block(struct net_device *dev,
+				struct tc_block_offload *f)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block, mlx5e_setup_tc_block_cb,
+					     priv, priv);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, mlx5e_setup_tc_block_cb,
+					priv);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
 #endif
 
-static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
-			  void *type_data)
+int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		   void *type_data)
 {
 	switch (type) {
 #ifdef CONFIG_MLX5_ESWITCH
-	case TC_SETUP_CLSFLOWER:
-		return mlx5e_setup_tc_cls_flower(dev, type_data);
+	case TC_SETUP_BLOCK:
+		return mlx5e_setup_tc_block(dev, type_data);
 #endif
 	case TC_SETUP_MQPRIO:
 		return mlx5e_setup_tc_mqprio(dev, type_data);
@@ -3403,6 +3434,80 @@ out:
 	return err;
 }
 
+int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
+{
+	struct hwtstamp_config config;
+	int err;
+
+	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	/* TX HW timestamp */
+	switch (config.tx_type) {
+	case HWTSTAMP_TX_OFF:
+	case HWTSTAMP_TX_ON:
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	mutex_lock(&priv->state_lock);
+	/* RX HW timestamp */
+	switch (config.rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		/* Reset CQE compression to Admin default */
+		mlx5e_modify_rx_cqe_compression_locked(priv, priv->channels.params.rx_cqe_compress_def);
+		break;
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_SOME:
+	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_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	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:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
+		/* Disable CQE compression */
+		netdev_warn(priv->netdev, "Disabling cqe compression");
+		err = mlx5e_modify_rx_cqe_compression_locked(priv, false);
+		if (err) {
+			netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err);
+			mutex_unlock(&priv->state_lock);
+			return err;
+		}
+		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		break;
+	default:
+		mutex_unlock(&priv->state_lock);
+		return -ERANGE;
+	}
+
+	memcpy(&priv->tstamp, &config, sizeof(config));
+	mutex_unlock(&priv->state_lock);
+
+	return copy_to_user(ifr->ifr_data, &config,
+			    sizeof(config)) ? -EFAULT : 0;
+}
+
+int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr)
+{
+	struct hwtstamp_config *cfg = &priv->tstamp;
+
+	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
+		return -EOPNOTSUPP;
+
+	return copy_to_user(ifr->ifr_data, cfg, sizeof(*cfg)) ? -EFAULT : 0;
+}
+
 static int mlx5e_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 45e03c427faf..2c43606c26b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -34,6 +34,7 @@
 #include <linux/mlx5/fs.h>
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
+#include <net/act_api.h>
 #include <net/netevent.h>
 #include <net/arp.h>
 
@@ -658,23 +659,12 @@ static int mlx5e_rep_get_phys_port_name(struct net_device *dev,
 }
 
 static int
-mlx5e_rep_setup_tc_cls_flower(struct net_device *dev,
+mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
 			      struct tc_cls_flower_offload *cls_flower)
 {
-	struct mlx5e_priv *priv = netdev_priv(dev);
-
-	if (!is_classid_clsact_ingress(cls_flower->common.classid) ||
-	    cls_flower->common.chain_index)
+	if (cls_flower->common.chain_index)
 		return -EOPNOTSUPP;
 
-	if (cls_flower->egress_dev) {
-		struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-
-		dev = mlx5_eswitch_get_uplink_netdev(esw);
-		return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER,
-						     cls_flower);
-	}
-
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
 		return mlx5e_configure_flower(priv, cls_flower);
@@ -687,12 +677,48 @@ mlx5e_rep_setup_tc_cls_flower(struct net_device *dev,
 	}
 }
 
+static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
+				 void *cb_priv)
+{
+	struct mlx5e_priv *priv = cb_priv;
+
+	if (!tc_can_offload(priv->netdev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return mlx5e_rep_setup_tc_cls_flower(priv, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlx5e_rep_setup_tc_block(struct net_device *dev,
+				    struct tc_block_offload *f)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block, mlx5e_rep_setup_tc_cb,
+					     priv, priv);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, mlx5e_rep_setup_tc_cb, priv);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			      void *type_data)
 {
 	switch (type) {
-	case TC_SETUP_CLSFLOWER:
-		return mlx5e_rep_setup_tc_cls_flower(dev, type_data);
+	case TC_SETUP_BLOCK:
+		return mlx5e_rep_setup_tc_block(dev, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -986,6 +1012,7 @@ mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
 {
 	struct mlx5e_rep_priv *rpriv;
 	struct net_device *netdev;
+	struct mlx5e_priv *upriv;
 	int err;
 
 	rpriv = kzalloc(sizeof(*rpriv), GFP_KERNEL);
@@ -1017,15 +1044,25 @@ mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
 		goto err_detach_netdev;
 	}
 
+	upriv = netdev_priv(mlx5_eswitch_get_uplink_netdev(esw));
+	err = tc_setup_cb_egdev_register(netdev, mlx5e_setup_tc_block_cb,
+					 upriv);
+	if (err)
+		goto err_neigh_cleanup;
+
 	err = register_netdev(netdev);
 	if (err) {
 		pr_warn("Failed to register representor netdev for vport %d\n",
 			rep->vport);
-		goto err_neigh_cleanup;
+		goto err_egdev_cleanup;
 	}
 
 	return 0;
 
+err_egdev_cleanup:
+	tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb,
+				     upriv);
+
 err_neigh_cleanup:
 	mlx5e_rep_neigh_cleanup(rpriv);
 
@@ -1045,9 +1082,12 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	void *ppriv = priv->ppriv;
+	struct mlx5e_priv *upriv;
 
 	unregister_netdev(rep->netdev);
-
+	upriv = netdev_priv(mlx5_eswitch_get_uplink_netdev(esw));
+	tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb,
+				     upriv);
 	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_detach_netdev(priv);
 	mlx5e_destroy_netdev(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 15a1687483cc..6d7df4750e0f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -42,10 +42,11 @@
 #include "en_rep.h"
 #include "ipoib/ipoib.h"
 #include "en_accel/ipsec_rxtx.h"
+#include "lib/clock.h"
 
-static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp)
+static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
 {
-	return tstamp->hwtstamp_config.rx_filter == HWTSTAMP_FILTER_ALL;
+	return config->rx_filter == HWTSTAMP_FILTER_ALL;
 }
 
 static inline void mlx5e_read_cqe_slot(struct mlx5e_cq *cq, u32 cqcc,
@@ -661,7 +662,6 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 				      struct sk_buff *skb)
 {
 	struct net_device *netdev = rq->netdev;
-	struct mlx5e_tstamp *tstamp = rq->tstamp;
 	int lro_num_seg;
 
 	lro_num_seg = be32_to_cpu(cqe->srqn) >> 24;
@@ -676,8 +676,9 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 		rq->stats.lro_bytes += cqe_bcnt;
 	}
 
-	if (unlikely(mlx5e_rx_hw_stamp(tstamp)))
-		mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb));
+	if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp)))
+		skb_hwtstamps(skb)->hwtstamp =
+				mlx5_timecounter_cyc2time(rq->clock, get_cqe_ts(cqe));
 
 	skb_record_rx_queue(skb, rq->ix);
 
@@ -797,6 +798,7 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq,
 		return false;
 
 	xdp.data = va + *rx_headroom;
+	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = xdp.data + *len;
 	xdp.data_hard_start = va;
 
@@ -1162,12 +1164,25 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 					 u32 cqe_bcnt,
 					 struct sk_buff *skb)
 {
-	struct net_device *netdev = rq->netdev;
-	struct mlx5e_tstamp *tstamp = rq->tstamp;
+	struct net_device *netdev;
 	char *pseudo_header;
+	u32 qpn;
 	u8 *dgid;
 	u8 g;
 
+	qpn = be32_to_cpu(cqe->sop_drop_qpn) & 0xffffff;
+	netdev = mlx5i_pkey_get_netdev(rq->netdev, qpn);
+
+	/* No mapping present, cannot process SKB. This might happen if a child
+	 * interface is going down while having unprocessed CQEs on parent RQ
+	 */
+	if (unlikely(!netdev)) {
+		/* TODO: add drop counters support */
+		skb->dev = NULL;
+		pr_warn_once("Unable to map QPN %u to dev - dropping skb\n", qpn);
+		return;
+	}
+
 	g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3;
 	dgid = skb->data + MLX5_IB_GRH_DGID_OFFSET;
 	if ((!g) || dgid[0] != 0xff)
@@ -1188,8 +1203,9 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 	skb->ip_summed = CHECKSUM_COMPLETE;
 	skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
 
-	if (unlikely(mlx5e_rx_hw_stamp(tstamp)))
-		mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb));
+	if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp)))
+		skb_hwtstamps(skb)->hwtstamp =
+				mlx5_timecounter_cyc2time(rq->clock, get_cqe_ts(cqe));
 
 	skb_record_rx_queue(skb, rq->ix);
 
@@ -1229,6 +1245,10 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 		goto wq_free_wqe;
 
 	mlx5i_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	if (unlikely(!skb->dev)) {
+		dev_kfree_skb_any(skb);
+		goto wq_free_wqe;
+	}
 	napi_gro_receive(rq->cq.napi, skb);
 
 wq_free_wqe:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
new file mode 100644
index 000000000000..8bc30484ecc1
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -0,0 +1,895 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies, Ltd.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "en.h"
+#include "en_accel/ipsec.h"
+
+static const struct counter_desc sw_stats_desc[] = {
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_page_reuse) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_reuse) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_full) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events_phy) },
+};
+
+#define NUM_SW_COUNTERS			ARRAY_SIZE(sw_stats_desc)
+
+static int mlx5e_grp_sw_get_num_stats(struct mlx5e_priv *priv)
+{
+	return NUM_SW_COUNTERS;
+}
+
+static int mlx5e_grp_sw_fill_strings(struct mlx5e_priv *priv, u8 *data, int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_SW_COUNTERS; i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, sw_stats_desc[i].format);
+	return idx;
+}
+
+static int mlx5e_grp_sw_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_SW_COUNTERS; i++)
+		data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.sw, sw_stats_desc, i);
+	return idx;
+}
+
+static const struct counter_desc q_stats_desc[] = {
+	{ MLX5E_DECLARE_STAT(struct mlx5e_qcounter_stats, rx_out_of_buffer) },
+};
+
+#define NUM_Q_COUNTERS			ARRAY_SIZE(q_stats_desc)
+
+static int mlx5e_grp_q_get_num_stats(struct mlx5e_priv *priv)
+{
+	return priv->q_counter ? NUM_Q_COUNTERS : 0;
+}
+
+static int mlx5e_grp_q_fill_strings(struct mlx5e_priv *priv, u8 *data, int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].format);
+	return idx;
+}
+
+static int mlx5e_grp_q_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++)
+		data[idx++] = MLX5E_READ_CTR32_CPU(&priv->stats.qcnt, q_stats_desc, i);
+	return idx;
+}
+
+#define VPORT_COUNTER_OFF(c) MLX5_BYTE_OFF(query_vport_counter_out, c)
+static const struct counter_desc vport_stats_desc[] = {
+	{ "rx_vport_unicast_packets",
+		VPORT_COUNTER_OFF(received_eth_unicast.packets) },
+	{ "rx_vport_unicast_bytes",
+		VPORT_COUNTER_OFF(received_eth_unicast.octets) },
+	{ "tx_vport_unicast_packets",
+		VPORT_COUNTER_OFF(transmitted_eth_unicast.packets) },
+	{ "tx_vport_unicast_bytes",
+		VPORT_COUNTER_OFF(transmitted_eth_unicast.octets) },
+	{ "rx_vport_multicast_packets",
+		VPORT_COUNTER_OFF(received_eth_multicast.packets) },
+	{ "rx_vport_multicast_bytes",
+		VPORT_COUNTER_OFF(received_eth_multicast.octets) },
+	{ "tx_vport_multicast_packets",
+		VPORT_COUNTER_OFF(transmitted_eth_multicast.packets) },
+	{ "tx_vport_multicast_bytes",
+		VPORT_COUNTER_OFF(transmitted_eth_multicast.octets) },
+	{ "rx_vport_broadcast_packets",
+		VPORT_COUNTER_OFF(received_eth_broadcast.packets) },
+	{ "rx_vport_broadcast_bytes",
+		VPORT_COUNTER_OFF(received_eth_broadcast.octets) },
+	{ "tx_vport_broadcast_packets",
+		VPORT_COUNTER_OFF(transmitted_eth_broadcast.packets) },
+	{ "tx_vport_broadcast_bytes",
+		VPORT_COUNTER_OFF(transmitted_eth_broadcast.octets) },
+	{ "rx_vport_rdma_unicast_packets",
+		VPORT_COUNTER_OFF(received_ib_unicast.packets) },
+	{ "rx_vport_rdma_unicast_bytes",
+		VPORT_COUNTER_OFF(received_ib_unicast.octets) },
+	{ "tx_vport_rdma_unicast_packets",
+		VPORT_COUNTER_OFF(transmitted_ib_unicast.packets) },
+	{ "tx_vport_rdma_unicast_bytes",
+		VPORT_COUNTER_OFF(transmitted_ib_unicast.octets) },
+	{ "rx_vport_rdma_multicast_packets",
+		VPORT_COUNTER_OFF(received_ib_multicast.packets) },
+	{ "rx_vport_rdma_multicast_bytes",
+		VPORT_COUNTER_OFF(received_ib_multicast.octets) },
+	{ "tx_vport_rdma_multicast_packets",
+		VPORT_COUNTER_OFF(transmitted_ib_multicast.packets) },
+	{ "tx_vport_rdma_multicast_bytes",
+		VPORT_COUNTER_OFF(transmitted_ib_multicast.octets) },
+};
+
+#define NUM_VPORT_COUNTERS		ARRAY_SIZE(vport_stats_desc)
+
+static int mlx5e_grp_vport_get_num_stats(struct mlx5e_priv *priv)
+{
+	return NUM_VPORT_COUNTERS;
+}
+
+static int mlx5e_grp_vport_fill_strings(struct mlx5e_priv *priv, u8 *data,
+					int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_VPORT_COUNTERS; i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, vport_stats_desc[i].format);
+	return idx;
+}
+
+static int mlx5e_grp_vport_fill_stats(struct mlx5e_priv *priv, u64 *data,
+				      int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_VPORT_COUNTERS; i++)
+		data[idx++] = MLX5E_READ_CTR64_BE(priv->stats.vport.query_vport_out,
+						  vport_stats_desc, i);
+	return idx;
+}
+
+#define PPORT_802_3_OFF(c) \
+	MLX5_BYTE_OFF(ppcnt_reg, \
+		      counter_set.eth_802_3_cntrs_grp_data_layout.c##_high)
+static const struct counter_desc pport_802_3_stats_desc[] = {
+	{ "tx_packets_phy", PPORT_802_3_OFF(a_frames_transmitted_ok) },
+	{ "rx_packets_phy", PPORT_802_3_OFF(a_frames_received_ok) },
+	{ "rx_crc_errors_phy", PPORT_802_3_OFF(a_frame_check_sequence_errors) },
+	{ "tx_bytes_phy", PPORT_802_3_OFF(a_octets_transmitted_ok) },
+	{ "rx_bytes_phy", PPORT_802_3_OFF(a_octets_received_ok) },
+	{ "tx_multicast_phy", PPORT_802_3_OFF(a_multicast_frames_xmitted_ok) },
+	{ "tx_broadcast_phy", PPORT_802_3_OFF(a_broadcast_frames_xmitted_ok) },
+	{ "rx_multicast_phy", PPORT_802_3_OFF(a_multicast_frames_received_ok) },
+	{ "rx_broadcast_phy", PPORT_802_3_OFF(a_broadcast_frames_received_ok) },
+	{ "rx_in_range_len_errors_phy", PPORT_802_3_OFF(a_in_range_length_errors) },
+	{ "rx_out_of_range_len_phy", PPORT_802_3_OFF(a_out_of_range_length_field) },
+	{ "rx_oversize_pkts_phy", PPORT_802_3_OFF(a_frame_too_long_errors) },
+	{ "rx_symbol_err_phy", PPORT_802_3_OFF(a_symbol_error_during_carrier) },
+	{ "tx_mac_control_phy", PPORT_802_3_OFF(a_mac_control_frames_transmitted) },
+	{ "rx_mac_control_phy", PPORT_802_3_OFF(a_mac_control_frames_received) },
+	{ "rx_unsupported_op_phy", PPORT_802_3_OFF(a_unsupported_opcodes_received) },
+	{ "rx_pause_ctrl_phy", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_received) },
+	{ "tx_pause_ctrl_phy", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_transmitted) },
+};
+
+#define NUM_PPORT_802_3_COUNTERS	ARRAY_SIZE(pport_802_3_stats_desc)
+
+static int mlx5e_grp_802_3_get_num_stats(struct mlx5e_priv *priv)
+{
+	return NUM_PPORT_802_3_COUNTERS;
+}
+
+static int mlx5e_grp_802_3_fill_strings(struct mlx5e_priv *priv, u8 *data,
+					int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_PPORT_802_3_COUNTERS; i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, pport_802_3_stats_desc[i].format);
+	return idx;
+}
+
+static int mlx5e_grp_802_3_fill_stats(struct mlx5e_priv *priv, u64 *data,
+				      int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_PPORT_802_3_COUNTERS; i++)
+		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.IEEE_802_3_counters,
+						  pport_802_3_stats_desc, i);
+	return idx;
+}
+
+#define PPORT_2863_OFF(c) \
+	MLX5_BYTE_OFF(ppcnt_reg, \
+		      counter_set.eth_2863_cntrs_grp_data_layout.c##_high)
+static const struct counter_desc pport_2863_stats_desc[] = {
+	{ "rx_discards_phy", PPORT_2863_OFF(if_in_discards) },
+	{ "tx_discards_phy", PPORT_2863_OFF(if_out_discards) },
+	{ "tx_errors_phy", PPORT_2863_OFF(if_out_errors) },
+};
+
+#define NUM_PPORT_2863_COUNTERS		ARRAY_SIZE(pport_2863_stats_desc)
+
+static int mlx5e_grp_2863_get_num_stats(struct mlx5e_priv *priv)
+{
+	return NUM_PPORT_2863_COUNTERS;
+}
+
+static int mlx5e_grp_2863_fill_strings(struct mlx5e_priv *priv, u8 *data,
+				       int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_PPORT_2863_COUNTERS; i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, pport_2863_stats_desc[i].format);
+	return idx;
+}
+
+static int mlx5e_grp_2863_fill_stats(struct mlx5e_priv *priv, u64 *data,
+				     int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_PPORT_2863_COUNTERS; i++)
+		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.RFC_2863_counters,
+						  pport_2863_stats_desc, i);
+	return idx;
+}
+
+#define PPORT_2819_OFF(c) \
+	MLX5_BYTE_OFF(ppcnt_reg, \
+		      counter_set.eth_2819_cntrs_grp_data_layout.c##_high)
+static const struct counter_desc pport_2819_stats_desc[] = {
+	{ "rx_undersize_pkts_phy", PPORT_2819_OFF(ether_stats_undersize_pkts) },
+	{ "rx_fragments_phy", PPORT_2819_OFF(ether_stats_fragments) },
+	{ "rx_jabbers_phy", PPORT_2819_OFF(ether_stats_jabbers) },
+	{ "rx_64_bytes_phy", PPORT_2819_OFF(ether_stats_pkts64octets) },
+	{ "rx_65_to_127_bytes_phy", PPORT_2819_OFF(ether_stats_pkts65to127octets) },
+	{ "rx_128_to_255_bytes_phy", PPORT_2819_OFF(ether_stats_pkts128to255octets) },
+	{ "rx_256_to_511_bytes_phy", PPORT_2819_OFF(ether_stats_pkts256to511octets) },
+	{ "rx_512_to_1023_bytes_phy", PPORT_2819_OFF(ether_stats_pkts512to1023octets) },
+	{ "rx_1024_to_1518_bytes_phy", PPORT_2819_OFF(ether_stats_pkts1024to1518octets) },
+	{ "rx_1519_to_2047_bytes_phy", PPORT_2819_OFF(ether_stats_pkts1519to2047octets) },
+	{ "rx_2048_to_4095_bytes_phy", PPORT_2819_OFF(ether_stats_pkts2048to4095octets) },
+	{ "rx_4096_to_8191_bytes_phy", PPORT_2819_OFF(ether_stats_pkts4096to8191octets) },
+	{ "rx_8192_to_10239_bytes_phy", PPORT_2819_OFF(ether_stats_pkts8192to10239octets) },
+};
+
+#define NUM_PPORT_2819_COUNTERS		ARRAY_SIZE(pport_2819_stats_desc)
+
+static int mlx5e_grp_2819_get_num_stats(struct mlx5e_priv *priv)
+{
+	return NUM_PPORT_2819_COUNTERS;
+}
+
+static int mlx5e_grp_2819_fill_strings(struct mlx5e_priv *priv, u8 *data,
+				       int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_PPORT_2819_COUNTERS; i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, pport_2819_stats_desc[i].format);
+	return idx;
+}
+
+static int mlx5e_grp_2819_fill_stats(struct mlx5e_priv *priv, u64 *data,
+				     int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_PPORT_2819_COUNTERS; i++)
+		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.RFC_2819_counters,
+						  pport_2819_stats_desc, i);
+	return idx;
+}
+
+#define PPORT_PHY_STATISTICAL_OFF(c) \
+	MLX5_BYTE_OFF(ppcnt_reg, \
+		      counter_set.phys_layer_statistical_cntrs.c##_high)
+static const struct counter_desc pport_phy_statistical_stats_desc[] = {
+	{ "rx_pcs_symbol_err_phy", PPORT_PHY_STATISTICAL_OFF(phy_symbol_errors) },
+	{ "rx_corrected_bits_phy", PPORT_PHY_STATISTICAL_OFF(phy_corrected_bits) },
+};
+
+#define NUM_PPORT_PHY_COUNTERS		ARRAY_SIZE(pport_phy_statistical_stats_desc)
+
+static int mlx5e_grp_phy_get_num_stats(struct mlx5e_priv *priv)
+{
+	return MLX5_CAP_PCAM_FEATURE((priv)->mdev, ppcnt_statistical_group) ?
+		NUM_PPORT_PHY_COUNTERS : 0;
+}
+
+static int mlx5e_grp_phy_fill_strings(struct mlx5e_priv *priv, u8 *data,
+				      int idx)
+{
+	int i;
+
+	if (MLX5_CAP_PCAM_FEATURE((priv)->mdev, ppcnt_statistical_group))
+		for (i = 0; i < NUM_PPORT_PHY_COUNTERS; i++)
+			strcpy(data + (idx++) * ETH_GSTRING_LEN,
+			       pport_phy_statistical_stats_desc[i].format);
+	return idx;
+}
+
+static int mlx5e_grp_phy_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
+{
+	int i;
+
+	if (MLX5_CAP_PCAM_FEATURE((priv)->mdev, ppcnt_statistical_group))
+		for (i = 0; i < NUM_PPORT_PHY_COUNTERS; i++)
+			data[idx++] =
+				MLX5E_READ_CTR64_BE(&priv->stats.pport.phy_statistical_counters,
+						    pport_phy_statistical_stats_desc, i);
+	return idx;
+}
+
+#define PPORT_ETH_EXT_OFF(c) \
+	MLX5_BYTE_OFF(ppcnt_reg, \
+		      counter_set.eth_extended_cntrs_grp_data_layout.c##_high)
+static const struct counter_desc pport_eth_ext_stats_desc[] = {
+	{ "rx_buffer_passed_thres_phy", PPORT_ETH_EXT_OFF(rx_buffer_almost_full) },
+};
+
+#define NUM_PPORT_ETH_EXT_COUNTERS	ARRAY_SIZE(pport_eth_ext_stats_desc)
+
+static int mlx5e_grp_eth_ext_get_num_stats(struct mlx5e_priv *priv)
+{
+	if (MLX5_CAP_PCAM_FEATURE((priv)->mdev, rx_buffer_fullness_counters))
+		return NUM_PPORT_ETH_EXT_COUNTERS;
+
+	return 0;
+}
+
+static int mlx5e_grp_eth_ext_fill_strings(struct mlx5e_priv *priv, u8 *data,
+					  int idx)
+{
+	int i;
+
+	if (MLX5_CAP_PCAM_FEATURE((priv)->mdev, rx_buffer_fullness_counters))
+		for (i = 0; i < NUM_PPORT_ETH_EXT_COUNTERS; i++)
+			strcpy(data + (idx++) * ETH_GSTRING_LEN,
+			       pport_eth_ext_stats_desc[i].format);
+	return idx;
+}
+
+static int mlx5e_grp_eth_ext_fill_stats(struct mlx5e_priv *priv, u64 *data,
+					int idx)
+{
+	int i;
+
+	if (MLX5_CAP_PCAM_FEATURE((priv)->mdev, rx_buffer_fullness_counters))
+		for (i = 0; i < NUM_PPORT_ETH_EXT_COUNTERS; i++)
+			data[idx++] =
+				MLX5E_READ_CTR64_BE(&priv->stats.pport.eth_ext_counters,
+						    pport_eth_ext_stats_desc, i);
+	return idx;
+}
+
+#define PCIE_PERF_OFF(c) \
+	MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_perf_cntrs_grp_data_layout.c)
+static const struct counter_desc pcie_perf_stats_desc[] = {
+	{ "rx_pci_signal_integrity", PCIE_PERF_OFF(rx_errors) },
+	{ "tx_pci_signal_integrity", PCIE_PERF_OFF(tx_errors) },
+};
+
+#define PCIE_PERF_OFF64(c) \
+	MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_perf_cntrs_grp_data_layout.c##_high)
+static const struct counter_desc pcie_perf_stats_desc64[] = {
+	{ "outbound_pci_buffer_overflow", PCIE_PERF_OFF64(tx_overflow_buffer_pkt) },
+};
+
+static const struct counter_desc pcie_perf_stall_stats_desc[] = {
+	{ "outbound_pci_stalled_rd", PCIE_PERF_OFF(outbound_stalled_reads) },
+	{ "outbound_pci_stalled_wr", PCIE_PERF_OFF(outbound_stalled_writes) },
+	{ "outbound_pci_stalled_rd_events", PCIE_PERF_OFF(outbound_stalled_reads_events) },
+	{ "outbound_pci_stalled_wr_events", PCIE_PERF_OFF(outbound_stalled_writes_events) },
+};
+
+#define NUM_PCIE_PERF_COUNTERS		ARRAY_SIZE(pcie_perf_stats_desc)
+#define NUM_PCIE_PERF_COUNTERS64	ARRAY_SIZE(pcie_perf_stats_desc64)
+#define NUM_PCIE_PERF_STALL_COUNTERS	ARRAY_SIZE(pcie_perf_stall_stats_desc)
+
+static int mlx5e_grp_pcie_get_num_stats(struct mlx5e_priv *priv)
+{
+	int num_stats = 0;
+
+	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_performance_group))
+		num_stats += NUM_PCIE_PERF_COUNTERS;
+
+	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, tx_overflow_buffer_pkt))
+		num_stats += NUM_PCIE_PERF_COUNTERS64;
+
+	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_outbound_stalled))
+		num_stats += NUM_PCIE_PERF_STALL_COUNTERS;
+
+	return num_stats;
+}
+
+static int mlx5e_grp_pcie_fill_strings(struct mlx5e_priv *priv, u8 *data,
+				       int idx)
+{
+	int i;
+
+	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_performance_group))
+		for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++)
+			strcpy(data + (idx++) * ETH_GSTRING_LEN,
+			       pcie_perf_stats_desc[i].format);
+
+	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, tx_overflow_buffer_pkt))
+		for (i = 0; i < NUM_PCIE_PERF_COUNTERS64; i++)
+			strcpy(data + (idx++) * ETH_GSTRING_LEN,
+			       pcie_perf_stats_desc64[i].format);
+
+	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_outbound_stalled))
+		for (i = 0; i < NUM_PCIE_PERF_STALL_COUNTERS; i++)
+			strcpy(data + (idx++) * ETH_GSTRING_LEN,
+			       pcie_perf_stall_stats_desc[i].format);
+	return idx;
+}
+
+static int mlx5e_grp_pcie_fill_stats(struct mlx5e_priv *priv, u64 *data,
+				     int idx)
+{
+	int i;
+
+	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_performance_group))
+		for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++)
+			data[idx++] =
+				MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters,
+						    pcie_perf_stats_desc, i);
+
+	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, tx_overflow_buffer_pkt))
+		for (i = 0; i < NUM_PCIE_PERF_COUNTERS64; i++)
+			data[idx++] =
+				MLX5E_READ_CTR64_BE(&priv->stats.pcie.pcie_perf_counters,
+						    pcie_perf_stats_desc64, i);
+
+	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_outbound_stalled))
+		for (i = 0; i < NUM_PCIE_PERF_STALL_COUNTERS; i++)
+			data[idx++] =
+				MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters,
+						    pcie_perf_stall_stats_desc, i);
+	return idx;
+}
+
+#define PPORT_PER_PRIO_OFF(c) \
+	MLX5_BYTE_OFF(ppcnt_reg, \
+		      counter_set.eth_per_prio_grp_data_layout.c##_high)
+static const struct counter_desc pport_per_prio_traffic_stats_desc[] = {
+	{ "rx_prio%d_bytes", PPORT_PER_PRIO_OFF(rx_octets) },
+	{ "rx_prio%d_packets", PPORT_PER_PRIO_OFF(rx_frames) },
+	{ "tx_prio%d_bytes", PPORT_PER_PRIO_OFF(tx_octets) },
+	{ "tx_prio%d_packets", PPORT_PER_PRIO_OFF(tx_frames) },
+};
+
+#define NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS	ARRAY_SIZE(pport_per_prio_traffic_stats_desc)
+
+static int mlx5e_grp_per_prio_traffic_get_num_stats(struct mlx5e_priv *priv)
+{
+	return NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS * NUM_PPORT_PRIO;
+}
+
+static int mlx5e_grp_per_prio_traffic_fill_strings(struct mlx5e_priv *priv,
+						   u8 *data,
+						   int idx)
+{
+	int i, prio;
+
+	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
+		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				pport_per_prio_traffic_stats_desc[i].format, prio);
+	}
+
+	return idx;
+}
+
+static int mlx5e_grp_per_prio_traffic_fill_stats(struct mlx5e_priv *priv,
+						 u64 *data,
+						 int idx)
+{
+	int i, prio;
+
+	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
+		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
+			data[idx++] =
+				MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio],
+						    pport_per_prio_traffic_stats_desc, i);
+	}
+
+	return idx;
+}
+
+static const struct counter_desc pport_per_prio_pfc_stats_desc[] = {
+	/* %s is "global" or "prio{i}" */
+	{ "rx_%s_pause", PPORT_PER_PRIO_OFF(rx_pause) },
+	{ "rx_%s_pause_duration", PPORT_PER_PRIO_OFF(rx_pause_duration) },
+	{ "tx_%s_pause", PPORT_PER_PRIO_OFF(tx_pause) },
+	{ "tx_%s_pause_duration", PPORT_PER_PRIO_OFF(tx_pause_duration) },
+	{ "rx_%s_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
+};
+
+#define NUM_PPORT_PER_PRIO_PFC_COUNTERS		ARRAY_SIZE(pport_per_prio_pfc_stats_desc)
+
+static unsigned long mlx5e_query_pfc_combined(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u8 pfc_en_tx;
+	u8 pfc_en_rx;
+	int err;
+
+	if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
+		return 0;
+
+	err = mlx5_query_port_pfc(mdev, &pfc_en_tx, &pfc_en_rx);
+
+	return err ? 0 : pfc_en_tx | pfc_en_rx;
+}
+
+static bool mlx5e_query_global_pause_combined(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 rx_pause;
+	u32 tx_pause;
+	int err;
+
+	if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
+		return false;
+
+	err = mlx5_query_port_pause(mdev, &rx_pause, &tx_pause);
+
+	return err ? false : rx_pause | tx_pause;
+}
+
+static int mlx5e_grp_per_prio_pfc_get_num_stats(struct mlx5e_priv *priv)
+{
+	return (mlx5e_query_global_pause_combined(priv) +
+		hweight8(mlx5e_query_pfc_combined(priv))) *
+		NUM_PPORT_PER_PRIO_PFC_COUNTERS;
+}
+
+static int mlx5e_grp_per_prio_pfc_fill_strings(struct mlx5e_priv *priv,
+					       u8 *data,
+					       int idx)
+{
+	unsigned long pfc_combined;
+	int i, prio;
+
+	pfc_combined = mlx5e_query_pfc_combined(priv);
+	for_each_set_bit(prio, &pfc_combined, NUM_PPORT_PRIO) {
+		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
+			char pfc_string[ETH_GSTRING_LEN];
+
+			snprintf(pfc_string, sizeof(pfc_string), "prio%d", prio);
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				pport_per_prio_pfc_stats_desc[i].format, pfc_string);
+		}
+	}
+
+	if (mlx5e_query_global_pause_combined(priv)) {
+		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				pport_per_prio_pfc_stats_desc[i].format, "global");
+		}
+	}
+
+	return idx;
+}
+
+static int mlx5e_grp_per_prio_pfc_fill_stats(struct mlx5e_priv *priv,
+					     u64 *data,
+					     int idx)
+{
+	unsigned long pfc_combined;
+	int i, prio;
+
+	pfc_combined = mlx5e_query_pfc_combined(priv);
+	for_each_set_bit(prio, &pfc_combined, NUM_PPORT_PRIO) {
+		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
+			data[idx++] =
+				MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio],
+						    pport_per_prio_pfc_stats_desc, i);
+		}
+	}
+
+	if (mlx5e_query_global_pause_combined(priv)) {
+		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
+			data[idx++] =
+				MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[0],
+						    pport_per_prio_pfc_stats_desc, i);
+		}
+	}
+
+	return idx;
+}
+
+static const struct counter_desc mlx5e_pme_status_desc[] = {
+	{ "module_unplug", 8 },
+};
+
+static const struct counter_desc mlx5e_pme_error_desc[] = {
+	{ "module_bus_stuck", 16 },       /* bus stuck (I2C or data shorted) */
+	{ "module_high_temp", 48 },       /* high temperature */
+	{ "module_bad_shorted", 56 },    /* bad or shorted cable/module */
+};
+
+#define NUM_PME_STATUS_STATS		ARRAY_SIZE(mlx5e_pme_status_desc)
+#define NUM_PME_ERR_STATS		ARRAY_SIZE(mlx5e_pme_error_desc)
+
+static int mlx5e_grp_pme_get_num_stats(struct mlx5e_priv *priv)
+{
+	return NUM_PME_STATUS_STATS + NUM_PME_ERR_STATS;
+}
+
+static int mlx5e_grp_pme_fill_strings(struct mlx5e_priv *priv, u8 *data,
+				      int idx)
+{
+	int i;
+
+	for (i = 0; i < NUM_PME_STATUS_STATS; i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, mlx5e_pme_status_desc[i].format);
+
+	for (i = 0; i < NUM_PME_ERR_STATS; i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, mlx5e_pme_error_desc[i].format);
+
+	return idx;
+}
+
+static int mlx5e_grp_pme_fill_stats(struct mlx5e_priv *priv, u64 *data,
+				    int idx)
+{
+	struct mlx5_priv *mlx5_priv = &priv->mdev->priv;
+	int i;
+
+	for (i = 0; i < NUM_PME_STATUS_STATS; i++)
+		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.status_counters,
+						   mlx5e_pme_status_desc, i);
+
+	for (i = 0; i < NUM_PME_ERR_STATS; i++)
+		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.error_counters,
+						   mlx5e_pme_error_desc, i);
+
+	return idx;
+}
+
+static int mlx5e_grp_ipsec_get_num_stats(struct mlx5e_priv *priv)
+{
+	return mlx5e_ipsec_get_count(priv);
+}
+
+static int mlx5e_grp_ipsec_fill_strings(struct mlx5e_priv *priv, u8 *data,
+					int idx)
+{
+	return idx + mlx5e_ipsec_get_strings(priv,
+					     data + idx * ETH_GSTRING_LEN);
+}
+
+static int mlx5e_grp_ipsec_fill_stats(struct mlx5e_priv *priv, u64 *data,
+				      int idx)
+{
+	return idx + mlx5e_ipsec_get_stats(priv, data + idx);
+}
+
+static const struct counter_desc rq_stats_desc[] = {
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_full) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, page_reuse) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_reuse) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_full) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) },
+};
+
+static const struct counter_desc sq_stats_desc[] = {
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, packets) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_packets) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_packets) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) },
+};
+
+#define NUM_RQ_STATS			ARRAY_SIZE(rq_stats_desc)
+#define NUM_SQ_STATS			ARRAY_SIZE(sq_stats_desc)
+
+static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
+{
+	return (NUM_RQ_STATS * priv->channels.num) +
+		(NUM_SQ_STATS * priv->channels.num * priv->channels.params.num_tc);
+}
+
+static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
+					   int idx)
+{
+	int i, j, tc;
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		return idx;
+
+	for (i = 0; i < priv->channels.num; i++)
+		for (j = 0; j < NUM_RQ_STATS; j++)
+			sprintf(data + (idx++) * ETH_GSTRING_LEN, rq_stats_desc[j].format, i);
+
+	for (tc = 0; tc < priv->channels.params.num_tc; tc++)
+		for (i = 0; i < priv->channels.num; i++)
+			for (j = 0; j < NUM_SQ_STATS; j++)
+				sprintf(data + (idx++) * ETH_GSTRING_LEN,
+					sq_stats_desc[j].format,
+					priv->channel_tc2txq[i][tc]);
+
+	return idx;
+}
+
+static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
+					 int idx)
+{
+	struct mlx5e_channels *channels = &priv->channels;
+	int i, j, tc;
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		return idx;
+
+	for (i = 0; i < channels->num; i++)
+		for (j = 0; j < NUM_RQ_STATS; j++)
+			data[idx++] =
+				MLX5E_READ_CTR64_CPU(&channels->c[i]->rq.stats,
+						     rq_stats_desc, j);
+
+	for (tc = 0; tc < priv->channels.params.num_tc; tc++)
+		for (i = 0; i < channels->num; i++)
+			for (j = 0; j < NUM_SQ_STATS; j++)
+				data[idx++] =
+					MLX5E_READ_CTR64_CPU(&channels->c[i]->sq[tc].stats,
+							     sq_stats_desc, j);
+
+	return idx;
+}
+
+const struct mlx5e_stats_grp mlx5e_stats_grps[] = {
+	{
+		.get_num_stats = mlx5e_grp_sw_get_num_stats,
+		.fill_strings = mlx5e_grp_sw_fill_strings,
+		.fill_stats = mlx5e_grp_sw_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_q_get_num_stats,
+		.fill_strings = mlx5e_grp_q_fill_strings,
+		.fill_stats = mlx5e_grp_q_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_vport_get_num_stats,
+		.fill_strings = mlx5e_grp_vport_fill_strings,
+		.fill_stats = mlx5e_grp_vport_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_802_3_get_num_stats,
+		.fill_strings = mlx5e_grp_802_3_fill_strings,
+		.fill_stats = mlx5e_grp_802_3_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_2863_get_num_stats,
+		.fill_strings = mlx5e_grp_2863_fill_strings,
+		.fill_stats = mlx5e_grp_2863_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_2819_get_num_stats,
+		.fill_strings = mlx5e_grp_2819_fill_strings,
+		.fill_stats = mlx5e_grp_2819_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_phy_get_num_stats,
+		.fill_strings = mlx5e_grp_phy_fill_strings,
+		.fill_stats = mlx5e_grp_phy_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_eth_ext_get_num_stats,
+		.fill_strings = mlx5e_grp_eth_ext_fill_strings,
+		.fill_stats = mlx5e_grp_eth_ext_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_pcie_get_num_stats,
+		.fill_strings = mlx5e_grp_pcie_fill_strings,
+		.fill_stats = mlx5e_grp_pcie_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_per_prio_traffic_get_num_stats,
+		.fill_strings = mlx5e_grp_per_prio_traffic_fill_strings,
+		.fill_stats = mlx5e_grp_per_prio_traffic_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_per_prio_pfc_get_num_stats,
+		.fill_strings = mlx5e_grp_per_prio_pfc_fill_strings,
+		.fill_stats = mlx5e_grp_per_prio_pfc_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_pme_get_num_stats,
+		.fill_strings = mlx5e_grp_pme_fill_strings,
+		.fill_stats = mlx5e_grp_pme_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_ipsec_get_num_stats,
+		.fill_strings = mlx5e_grp_ipsec_fill_strings,
+		.fill_stats = mlx5e_grp_ipsec_fill_stats,
+	},
+	{
+		.get_num_stats = mlx5e_grp_channels_get_num_stats,
+		.fill_strings = mlx5e_grp_channels_fill_strings,
+		.fill_stats = mlx5e_grp_channels_fill_stats,
+	}
+};
+
+const int mlx5e_num_stats_grps = ARRAY_SIZE(mlx5e_stats_grps);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index f8637213afc0..d094663edd9b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -91,54 +91,10 @@ struct mlx5e_sw_stats {
 	u64 link_down_events_phy;
 };
 
-static const struct counter_desc sw_stats_desc[] = {
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_page_reuse) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_reuse) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_full) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events_phy) },
-};
-
 struct mlx5e_qcounter_stats {
 	u32 rx_out_of_buffer;
 };
 
-static const struct counter_desc q_stats_desc[] = {
-	{ MLX5E_DECLARE_STAT(struct mlx5e_qcounter_stats, rx_out_of_buffer) },
-};
-
-#define VPORT_COUNTER_OFF(c) MLX5_BYTE_OFF(query_vport_counter_out, c)
 #define VPORT_COUNTER_GET(vstats, c) MLX5_GET64(query_vport_counter_out, \
 						vstats->query_vport_out, c)
 
@@ -146,83 +102,22 @@ struct mlx5e_vport_stats {
 	__be64 query_vport_out[MLX5_ST_SZ_QW(query_vport_counter_out)];
 };
 
-static const struct counter_desc vport_stats_desc[] = {
-	{ "rx_vport_unicast_packets",
-		VPORT_COUNTER_OFF(received_eth_unicast.packets) },
-	{ "rx_vport_unicast_bytes",
-		VPORT_COUNTER_OFF(received_eth_unicast.octets) },
-	{ "tx_vport_unicast_packets",
-		VPORT_COUNTER_OFF(transmitted_eth_unicast.packets) },
-	{ "tx_vport_unicast_bytes",
-		VPORT_COUNTER_OFF(transmitted_eth_unicast.octets) },
-	{ "rx_vport_multicast_packets",
-		VPORT_COUNTER_OFF(received_eth_multicast.packets) },
-	{ "rx_vport_multicast_bytes",
-		VPORT_COUNTER_OFF(received_eth_multicast.octets) },
-	{ "tx_vport_multicast_packets",
-		VPORT_COUNTER_OFF(transmitted_eth_multicast.packets) },
-	{ "tx_vport_multicast_bytes",
-		VPORT_COUNTER_OFF(transmitted_eth_multicast.octets) },
-	{ "rx_vport_broadcast_packets",
-		VPORT_COUNTER_OFF(received_eth_broadcast.packets) },
-	{ "rx_vport_broadcast_bytes",
-		VPORT_COUNTER_OFF(received_eth_broadcast.octets) },
-	{ "tx_vport_broadcast_packets",
-		VPORT_COUNTER_OFF(transmitted_eth_broadcast.packets) },
-	{ "tx_vport_broadcast_bytes",
-		VPORT_COUNTER_OFF(transmitted_eth_broadcast.octets) },
-	{ "rx_vport_rdma_unicast_packets",
-		VPORT_COUNTER_OFF(received_ib_unicast.packets) },
-	{ "rx_vport_rdma_unicast_bytes",
-		VPORT_COUNTER_OFF(received_ib_unicast.octets) },
-	{ "tx_vport_rdma_unicast_packets",
-		VPORT_COUNTER_OFF(transmitted_ib_unicast.packets) },
-	{ "tx_vport_rdma_unicast_bytes",
-		VPORT_COUNTER_OFF(transmitted_ib_unicast.octets) },
-	{ "rx_vport_rdma_multicast_packets",
-		VPORT_COUNTER_OFF(received_ib_multicast.packets) },
-	{ "rx_vport_rdma_multicast_bytes",
-		VPORT_COUNTER_OFF(received_ib_multicast.octets) },
-	{ "tx_vport_rdma_multicast_packets",
-		VPORT_COUNTER_OFF(transmitted_ib_multicast.packets) },
-	{ "tx_vport_rdma_multicast_bytes",
-		VPORT_COUNTER_OFF(transmitted_ib_multicast.octets) },
-};
-
-#define PPORT_802_3_OFF(c) \
-	MLX5_BYTE_OFF(ppcnt_reg, \
-		      counter_set.eth_802_3_cntrs_grp_data_layout.c##_high)
 #define PPORT_802_3_GET(pstats, c) \
 	MLX5_GET64(ppcnt_reg, pstats->IEEE_802_3_counters, \
 		   counter_set.eth_802_3_cntrs_grp_data_layout.c##_high)
-#define PPORT_2863_OFF(c) \
-	MLX5_BYTE_OFF(ppcnt_reg, \
-		      counter_set.eth_2863_cntrs_grp_data_layout.c##_high)
 #define PPORT_2863_GET(pstats, c) \
 	MLX5_GET64(ppcnt_reg, pstats->RFC_2863_counters, \
 		   counter_set.eth_2863_cntrs_grp_data_layout.c##_high)
-#define PPORT_2819_OFF(c) \
-	MLX5_BYTE_OFF(ppcnt_reg, \
-		      counter_set.eth_2819_cntrs_grp_data_layout.c##_high)
 #define PPORT_2819_GET(pstats, c) \
 	MLX5_GET64(ppcnt_reg, pstats->RFC_2819_counters, \
 		   counter_set.eth_2819_cntrs_grp_data_layout.c##_high)
-#define PPORT_PHY_STATISTICAL_OFF(c) \
-	MLX5_BYTE_OFF(ppcnt_reg, \
-		      counter_set.phys_layer_statistical_cntrs.c##_high)
 #define PPORT_PHY_STATISTICAL_GET(pstats, c) \
 	MLX5_GET64(ppcnt_reg, (pstats)->phy_statistical_counters, \
 		   counter_set.phys_layer_statistical_cntrs.c##_high)
-#define PPORT_PER_PRIO_OFF(c) \
-	MLX5_BYTE_OFF(ppcnt_reg, \
-		      counter_set.eth_per_prio_grp_data_layout.c##_high)
 #define PPORT_PER_PRIO_GET(pstats, prio, c) \
 	MLX5_GET64(ppcnt_reg, pstats->per_prio_counters[prio], \
 		   counter_set.eth_per_prio_grp_data_layout.c##_high)
 #define NUM_PPORT_PRIO				8
-#define PPORT_ETH_EXT_OFF(c) \
-	MLX5_BYTE_OFF(ppcnt_reg, \
-		      counter_set.eth_extended_cntrs_grp_data_layout.c##_high)
 #define PPORT_ETH_EXT_GET(pstats, c) \
 	MLX5_GET64(ppcnt_reg, (pstats)->eth_ext_counters, \
 		   counter_set.eth_extended_cntrs_grp_data_layout.c##_high)
@@ -237,82 +132,10 @@ struct mlx5e_pport_stats {
 	__be64 eth_ext_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
 };
 
-static const struct counter_desc pport_802_3_stats_desc[] = {
-	{ "tx_packets_phy", PPORT_802_3_OFF(a_frames_transmitted_ok) },
-	{ "rx_packets_phy", PPORT_802_3_OFF(a_frames_received_ok) },
-	{ "rx_crc_errors_phy", PPORT_802_3_OFF(a_frame_check_sequence_errors) },
-	{ "tx_bytes_phy", PPORT_802_3_OFF(a_octets_transmitted_ok) },
-	{ "rx_bytes_phy", PPORT_802_3_OFF(a_octets_received_ok) },
-	{ "tx_multicast_phy", PPORT_802_3_OFF(a_multicast_frames_xmitted_ok) },
-	{ "tx_broadcast_phy", PPORT_802_3_OFF(a_broadcast_frames_xmitted_ok) },
-	{ "rx_multicast_phy", PPORT_802_3_OFF(a_multicast_frames_received_ok) },
-	{ "rx_broadcast_phy", PPORT_802_3_OFF(a_broadcast_frames_received_ok) },
-	{ "rx_in_range_len_errors_phy", PPORT_802_3_OFF(a_in_range_length_errors) },
-	{ "rx_out_of_range_len_phy", PPORT_802_3_OFF(a_out_of_range_length_field) },
-	{ "rx_oversize_pkts_phy", PPORT_802_3_OFF(a_frame_too_long_errors) },
-	{ "rx_symbol_err_phy", PPORT_802_3_OFF(a_symbol_error_during_carrier) },
-	{ "tx_mac_control_phy", PPORT_802_3_OFF(a_mac_control_frames_transmitted) },
-	{ "rx_mac_control_phy", PPORT_802_3_OFF(a_mac_control_frames_received) },
-	{ "rx_unsupported_op_phy", PPORT_802_3_OFF(a_unsupported_opcodes_received) },
-	{ "rx_pause_ctrl_phy", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_received) },
-	{ "tx_pause_ctrl_phy", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_transmitted) },
-};
-
-static const struct counter_desc pport_2863_stats_desc[] = {
-	{ "rx_discards_phy", PPORT_2863_OFF(if_in_discards) },
-	{ "tx_discards_phy", PPORT_2863_OFF(if_out_discards) },
-	{ "tx_errors_phy", PPORT_2863_OFF(if_out_errors) },
-};
-
-static const struct counter_desc pport_2819_stats_desc[] = {
-	{ "rx_undersize_pkts_phy", PPORT_2819_OFF(ether_stats_undersize_pkts) },
-	{ "rx_fragments_phy", PPORT_2819_OFF(ether_stats_fragments) },
-	{ "rx_jabbers_phy", PPORT_2819_OFF(ether_stats_jabbers) },
-	{ "rx_64_bytes_phy", PPORT_2819_OFF(ether_stats_pkts64octets) },
-	{ "rx_65_to_127_bytes_phy", PPORT_2819_OFF(ether_stats_pkts65to127octets) },
-	{ "rx_128_to_255_bytes_phy", PPORT_2819_OFF(ether_stats_pkts128to255octets) },
-	{ "rx_256_to_511_bytes_phy", PPORT_2819_OFF(ether_stats_pkts256to511octets) },
-	{ "rx_512_to_1023_bytes_phy", PPORT_2819_OFF(ether_stats_pkts512to1023octets) },
-	{ "rx_1024_to_1518_bytes_phy", PPORT_2819_OFF(ether_stats_pkts1024to1518octets) },
-	{ "rx_1519_to_2047_bytes_phy", PPORT_2819_OFF(ether_stats_pkts1519to2047octets) },
-	{ "rx_2048_to_4095_bytes_phy", PPORT_2819_OFF(ether_stats_pkts2048to4095octets) },
-	{ "rx_4096_to_8191_bytes_phy", PPORT_2819_OFF(ether_stats_pkts4096to8191octets) },
-	{ "rx_8192_to_10239_bytes_phy", PPORT_2819_OFF(ether_stats_pkts8192to10239octets) },
-};
-
-static const struct counter_desc pport_phy_statistical_stats_desc[] = {
-	{ "rx_pcs_symbol_err_phy", PPORT_PHY_STATISTICAL_OFF(phy_symbol_errors) },
-	{ "rx_corrected_bits_phy", PPORT_PHY_STATISTICAL_OFF(phy_corrected_bits) },
-};
-
-static const struct counter_desc pport_per_prio_traffic_stats_desc[] = {
-	{ "rx_prio%d_bytes", PPORT_PER_PRIO_OFF(rx_octets) },
-	{ "rx_prio%d_packets", PPORT_PER_PRIO_OFF(rx_frames) },
-	{ "tx_prio%d_bytes", PPORT_PER_PRIO_OFF(tx_octets) },
-	{ "tx_prio%d_packets", PPORT_PER_PRIO_OFF(tx_frames) },
-};
-
-static const struct counter_desc pport_per_prio_pfc_stats_desc[] = {
-	/* %s is "global" or "prio{i}" */
-	{ "rx_%s_pause", PPORT_PER_PRIO_OFF(rx_pause) },
-	{ "rx_%s_pause_duration", PPORT_PER_PRIO_OFF(rx_pause_duration) },
-	{ "tx_%s_pause", PPORT_PER_PRIO_OFF(tx_pause) },
-	{ "tx_%s_pause_duration", PPORT_PER_PRIO_OFF(tx_pause_duration) },
-	{ "rx_%s_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
-};
-
-static const struct counter_desc pport_eth_ext_stats_desc[] = {
-	{ "rx_buffer_passed_thres_phy", PPORT_ETH_EXT_OFF(rx_buffer_almost_full) },
-};
-
-#define PCIE_PERF_OFF(c) \
-	MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_perf_cntrs_grp_data_layout.c)
 #define PCIE_PERF_GET(pcie_stats, c) \
 	MLX5_GET(mpcnt_reg, (pcie_stats)->pcie_perf_counters, \
 		 counter_set.pcie_perf_cntrs_grp_data_layout.c)
 
-#define PCIE_PERF_OFF64(c) \
-	MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_perf_cntrs_grp_data_layout.c##_high)
 #define PCIE_PERF_GET64(pcie_stats, c) \
 	MLX5_GET64(mpcnt_reg, (pcie_stats)->pcie_perf_counters, \
 		   counter_set.pcie_perf_cntrs_grp_data_layout.c##_high)
@@ -321,22 +144,6 @@ struct mlx5e_pcie_stats {
 	__be64 pcie_perf_counters[MLX5_ST_SZ_QW(mpcnt_reg)];
 };
 
-static const struct counter_desc pcie_perf_stats_desc[] = {
-	{ "rx_pci_signal_integrity", PCIE_PERF_OFF(rx_errors) },
-	{ "tx_pci_signal_integrity", PCIE_PERF_OFF(tx_errors) },
-};
-
-static const struct counter_desc pcie_perf_stats_desc64[] = {
-	{ "outbound_pci_buffer_overflow", PCIE_PERF_OFF64(tx_overflow_buffer_pkt) },
-};
-
-static const struct counter_desc pcie_perf_stall_stats_desc[] = {
-	{ "outbound_pci_stalled_rd", PCIE_PERF_OFF(outbound_stalled_reads) },
-	{ "outbound_pci_stalled_wr", PCIE_PERF_OFF(outbound_stalled_writes) },
-	{ "outbound_pci_stalled_rd_events", PCIE_PERF_OFF(outbound_stalled_reads_events) },
-	{ "outbound_pci_stalled_wr_events", PCIE_PERF_OFF(outbound_stalled_writes_events) },
-};
-
 struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
@@ -362,31 +169,6 @@ struct mlx5e_rq_stats {
 	u64 cache_waive;
 };
 
-static const struct counter_desc rq_stats_desc[] = {
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_full) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, page_reuse) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_reuse) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_full) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) },
-};
-
 struct mlx5e_sq_stats {
 	/* commonly accessed in data path */
 	u64 packets;
@@ -406,61 +188,6 @@ struct mlx5e_sq_stats {
 	u64 dropped;
 };
 
-static const struct counter_desc sq_stats_desc[] = {
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, packets) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, bytes) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_packets) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_bytes) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_packets) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_bytes) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) },
-};
-
-#define NUM_SW_COUNTERS			ARRAY_SIZE(sw_stats_desc)
-#define NUM_Q_COUNTERS			ARRAY_SIZE(q_stats_desc)
-#define NUM_VPORT_COUNTERS		ARRAY_SIZE(vport_stats_desc)
-#define NUM_PPORT_802_3_COUNTERS	ARRAY_SIZE(pport_802_3_stats_desc)
-#define NUM_PPORT_2863_COUNTERS		ARRAY_SIZE(pport_2863_stats_desc)
-#define NUM_PPORT_2819_COUNTERS		ARRAY_SIZE(pport_2819_stats_desc)
-#define NUM_PPORT_PHY_STATISTICAL_COUNTERS(priv) \
-	(ARRAY_SIZE(pport_phy_statistical_stats_desc) * \
-	 MLX5_CAP_PCAM_FEATURE((priv)->mdev, ppcnt_statistical_group))
-#define NUM_PCIE_PERF_COUNTERS(priv) \
-	(ARRAY_SIZE(pcie_perf_stats_desc) * \
-	 MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_performance_group))
-#define NUM_PCIE_PERF_COUNTERS64(priv) \
-	(ARRAY_SIZE(pcie_perf_stats_desc64) * \
-	 MLX5_CAP_MCAM_FEATURE((priv)->mdev, tx_overflow_buffer_pkt))
-#define NUM_PCIE_PERF_STALL_COUNTERS(priv) \
-	(ARRAY_SIZE(pcie_perf_stall_stats_desc) * \
-	 MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_outbound_stalled))
-#define NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS \
-	ARRAY_SIZE(pport_per_prio_traffic_stats_desc)
-#define NUM_PPORT_PER_PRIO_PFC_COUNTERS \
-	ARRAY_SIZE(pport_per_prio_pfc_stats_desc)
-#define NUM_PPORT_ETH_EXT_COUNTERS(priv) \
-	(ARRAY_SIZE(pport_eth_ext_stats_desc) * \
-	 MLX5_CAP_PCAM_FEATURE((priv)->mdev, rx_buffer_fullness_counters))
-#define NUM_PPORT_COUNTERS(priv)	(NUM_PPORT_802_3_COUNTERS + \
-					 NUM_PPORT_2863_COUNTERS  + \
-					 NUM_PPORT_2819_COUNTERS  + \
-					 NUM_PPORT_PHY_STATISTICAL_COUNTERS(priv) + \
-					 NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS * \
-					 NUM_PPORT_PRIO + \
-					 NUM_PPORT_ETH_EXT_COUNTERS(priv))
-#define NUM_PCIE_COUNTERS(priv)		(NUM_PCIE_PERF_COUNTERS(priv) + \
-					 NUM_PCIE_PERF_COUNTERS64(priv) +\
-					 NUM_PCIE_PERF_STALL_COUNTERS(priv))
-#define NUM_RQ_STATS			ARRAY_SIZE(rq_stats_desc)
-#define NUM_SQ_STATS			ARRAY_SIZE(sq_stats_desc)
-
 struct mlx5e_stats {
 	struct mlx5e_sw_stats sw;
 	struct mlx5e_qcounter_stats qcnt;
@@ -470,14 +197,14 @@ struct mlx5e_stats {
 	struct mlx5e_pcie_stats pcie;
 };
 
-static const struct counter_desc mlx5e_pme_status_desc[] = {
-	{ "module_unplug", 8 },
+struct mlx5e_priv;
+struct mlx5e_stats_grp {
+	int (*get_num_stats)(struct mlx5e_priv *priv);
+	int (*fill_strings)(struct mlx5e_priv *priv, u8 *data, int idx);
+	int (*fill_stats)(struct mlx5e_priv *priv, u64 *data, int idx);
 };
 
-static const struct counter_desc mlx5e_pme_error_desc[] = {
-	{ "module_bus_stuck", 16 },       /* bus stuck (I2C or data shorted) */
-	{ "module_high_temp", 48 },       /* high temperature */
-	{ "module_bad_shorted", 56 },    /* bad or shorted cable/module */
-};
+extern const struct mlx5e_stats_grp mlx5e_stats_grps[];
+extern const int mlx5e_num_stats_grps;
 
 #endif /* __MLX5_EN_STATS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 1d6925d4369a..a7c208a1ad83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -35,6 +35,7 @@
 #include "en.h"
 #include "ipoib/ipoib.h"
 #include "en_accel/ipsec_rxtx.h"
+#include "lib/clock.h"
 
 #define MLX5E_SQ_NOPS_ROOM  MLX5_SEND_WQE_MAX_WQEBBS
 #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
@@ -452,8 +453,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 				     SKBTX_HW_TSTAMP)) {
 				struct skb_shared_hwtstamps hwts = {};
 
-				mlx5e_fill_hwstamp(sq->tstamp,
-						   get_cqe_ts(cqe), &hwts);
+				hwts.hwtstamp =
+					mlx5_timecounter_cyc2time(sq->clock,
+								  get_cqe_ts(cqe));
 				skb_tstamp_tx(skb, &hwts);
 			}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index fc606bfd1d6e..60771865c99c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -491,8 +491,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 			break;
 
 		case MLX5_EVENT_TYPE_PPS_EVENT:
-			if (dev->event)
-				dev->event(dev, MLX5_DEV_EVENT_PPS, (unsigned long)eqe);
+			mlx5_pps_event(dev, eqe);
 			break;
 
 		case MLX5_EVENT_TYPE_FPGA_ERROR:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 36ecc2b2e187..881e2e55840c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -40,7 +40,8 @@
 #include "eswitch.h"
 
 int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
-			    struct mlx5_flow_table *ft, u32 underlay_qpn)
+			    struct mlx5_flow_table *ft, u32 underlay_qpn,
+			    bool disconnect)
 {
 	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)]   = {0};
 	u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {0};
@@ -52,7 +53,15 @@ int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
 	MLX5_SET(set_flow_table_root_in, in, opcode,
 		 MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
 	MLX5_SET(set_flow_table_root_in, in, table_type, ft->type);
-	MLX5_SET(set_flow_table_root_in, in, table_id, ft->id);
+
+	if (disconnect) {
+		MLX5_SET(set_flow_table_root_in, in, op_mod, 1);
+		MLX5_SET(set_flow_table_root_in, in, table_id, 0);
+	} else {
+		MLX5_SET(set_flow_table_root_in, in, op_mod, 0);
+		MLX5_SET(set_flow_table_root_in, in, table_id, ft->id);
+	}
+
 	MLX5_SET(set_flow_table_root_in, in, underlay_qpn, underlay_qpn);
 	if (ft->vport) {
 		MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
index c6d7bdf255b6..71e2d0f37ad9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
@@ -71,8 +71,8 @@ int mlx5_cmd_delete_fte(struct mlx5_core_dev *dev,
 			unsigned int index);
 
 int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
-			    struct mlx5_flow_table *ft,
-			    u32 underlay_qpn);
+			    struct mlx5_flow_table *ft, u32 underlay_qpn,
+			    bool disconnect);
 
 int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id);
 int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 5a7bea688ec8..c7fa1389bace 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -145,10 +145,10 @@ static struct init_tree_node {
 	}
 };
 
-enum fs_i_mutex_lock_class {
-	FS_MUTEX_GRANDPARENT,
-	FS_MUTEX_PARENT,
-	FS_MUTEX_CHILD
+enum fs_i_lock_class {
+	FS_LOCK_GRANDPARENT,
+	FS_LOCK_PARENT,
+	FS_LOCK_CHILD
 };
 
 static const struct rhashtable_params rhash_fte = {
@@ -168,10 +168,16 @@ static const struct rhashtable_params rhash_fg = {
 
 };
 
-static void del_rule(struct fs_node *node);
-static void del_flow_table(struct fs_node *node);
-static void del_flow_group(struct fs_node *node);
-static void del_fte(struct fs_node *node);
+static void del_hw_flow_table(struct fs_node *node);
+static void del_hw_flow_group(struct fs_node *node);
+static void del_hw_fte(struct fs_node *node);
+static void del_sw_flow_table(struct fs_node *node);
+static void del_sw_flow_group(struct fs_node *node);
+static void del_sw_fte(struct fs_node *node);
+/* Delete rule (destination) is special case that 
+ * requires to lock the FTE for all the deletion process.
+ */
+static void del_sw_hw_rule(struct fs_node *node);
 static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
 				struct mlx5_flow_destination *d2);
 static struct mlx5_flow_rule *
@@ -179,20 +185,22 @@ find_flow_rule(struct fs_fte *fte,
 	       struct mlx5_flow_destination *dest);
 
 static void tree_init_node(struct fs_node *node,
-			   unsigned int refcount,
-			   void (*remove_func)(struct fs_node *))
+			   void (*del_hw_func)(struct fs_node *),
+			   void (*del_sw_func)(struct fs_node *))
 {
-	atomic_set(&node->refcount, refcount);
+	refcount_set(&node->refcount, 1);
 	INIT_LIST_HEAD(&node->list);
 	INIT_LIST_HEAD(&node->children);
-	mutex_init(&node->lock);
-	node->remove_func = remove_func;
+	init_rwsem(&node->lock);
+	node->del_hw_func = del_hw_func;
+	node->del_sw_func = del_sw_func;
+	node->active = false;
 }
 
 static void tree_add_node(struct fs_node *node, struct fs_node *parent)
 {
 	if (parent)
-		atomic_inc(&parent->refcount);
+		refcount_inc(&parent->refcount);
 	node->parent = parent;
 
 	/* Parent is the root */
@@ -202,58 +210,78 @@ static void tree_add_node(struct fs_node *node, struct fs_node *parent)
 		node->root = parent->root;
 }
 
-static void tree_get_node(struct fs_node *node)
+static int tree_get_node(struct fs_node *node)
 {
-	atomic_inc(&node->refcount);
+	return refcount_inc_not_zero(&node->refcount);
 }
 
-static void nested_lock_ref_node(struct fs_node *node,
-				 enum fs_i_mutex_lock_class class)
+static void nested_down_read_ref_node(struct fs_node *node,
+				      enum fs_i_lock_class class)
 {
 	if (node) {
-		mutex_lock_nested(&node->lock, class);
-		atomic_inc(&node->refcount);
+		down_read_nested(&node->lock, class);
+		refcount_inc(&node->refcount);
 	}
 }
 
-static void lock_ref_node(struct fs_node *node)
+static void nested_down_write_ref_node(struct fs_node *node,
+				       enum fs_i_lock_class class)
 {
 	if (node) {
-		mutex_lock(&node->lock);
-		atomic_inc(&node->refcount);
+		down_write_nested(&node->lock, class);
+		refcount_inc(&node->refcount);
 	}
 }
 
-static void unlock_ref_node(struct fs_node *node)
+static void down_write_ref_node(struct fs_node *node)
 {
 	if (node) {
-		atomic_dec(&node->refcount);
-		mutex_unlock(&node->lock);
+		down_write(&node->lock);
+		refcount_inc(&node->refcount);
 	}
 }
 
+static void up_read_ref_node(struct fs_node *node)
+{
+	refcount_dec(&node->refcount);
+	up_read(&node->lock);
+}
+
+static void up_write_ref_node(struct fs_node *node)
+{
+	refcount_dec(&node->refcount);
+	up_write(&node->lock);
+}
+
 static void tree_put_node(struct fs_node *node)
 {
 	struct fs_node *parent_node = node->parent;
 
-	lock_ref_node(parent_node);
-	if (atomic_dec_and_test(&node->refcount)) {
-		if (parent_node)
+	if (refcount_dec_and_test(&node->refcount)) {
+		if (node->del_hw_func)
+			node->del_hw_func(node);
+		if (parent_node) {
+			/* Only root namespace doesn't have parent and we just
+			 * need to free its node.
+			 */
+			down_write_ref_node(parent_node);
 			list_del_init(&node->list);
-		if (node->remove_func)
-			node->remove_func(node);
-		kfree(node);
+			if (node->del_sw_func)
+				node->del_sw_func(node);
+			up_write_ref_node(parent_node);
+		} else {
+			kfree(node);
+		}
 		node = NULL;
 	}
-	unlock_ref_node(parent_node);
 	if (!node && parent_node)
 		tree_put_node(parent_node);
 }
 
 static int tree_remove_node(struct fs_node *node)
 {
-	if (atomic_read(&node->refcount) > 1) {
-		atomic_dec(&node->refcount);
+	if (refcount_read(&node->refcount) > 1) {
+		refcount_dec(&node->refcount);
 		return -EEXIST;
 	}
 	tree_put_node(node);
@@ -362,6 +390,15 @@ static struct mlx5_flow_root_namespace *find_root(struct fs_node *node)
 	return container_of(ns, struct mlx5_flow_root_namespace, ns);
 }
 
+static inline struct mlx5_flow_steering *get_steering(struct fs_node *node)
+{
+	struct mlx5_flow_root_namespace *root = find_root(node);
+
+	if (root)
+		return root->dev->priv.steering;
+	return NULL;
+}
+
 static inline struct mlx5_core_dev *get_dev(struct fs_node *node)
 {
 	struct mlx5_flow_root_namespace *root = find_root(node);
@@ -371,26 +408,36 @@ static inline struct mlx5_core_dev *get_dev(struct fs_node *node)
 	return NULL;
 }
 
-static void del_flow_table(struct fs_node *node)
+static void del_hw_flow_table(struct fs_node *node)
 {
 	struct mlx5_flow_table *ft;
 	struct mlx5_core_dev *dev;
-	struct fs_prio *prio;
 	int err;
 
 	fs_get_obj(ft, node);
 	dev = get_dev(&ft->node);
 
-	err = mlx5_cmd_destroy_flow_table(dev, ft);
-	if (err)
-		mlx5_core_warn(dev, "flow steering can't destroy ft\n");
-	ida_destroy(&ft->fte_allocator);
+	if (node->active) {
+		err = mlx5_cmd_destroy_flow_table(dev, ft);
+		if (err)
+			mlx5_core_warn(dev, "flow steering can't destroy ft\n");
+	}
+}
+
+static void del_sw_flow_table(struct fs_node *node)
+{
+	struct mlx5_flow_table *ft;
+	struct fs_prio *prio;
+
+	fs_get_obj(ft, node);
+
 	rhltable_destroy(&ft->fgs_hash);
 	fs_get_obj(prio, ft->node.parent);
 	prio->num_ft--;
+	kfree(ft);
 }
 
-static void del_rule(struct fs_node *node)
+static void del_sw_hw_rule(struct fs_node *node)
 {
 	struct mlx5_flow_rule *rule;
 	struct mlx5_flow_table *ft;
@@ -406,7 +453,6 @@ static void del_rule(struct fs_node *node)
 	fs_get_obj(fg, fte->node.parent);
 	fs_get_obj(ft, fg->node.parent);
 	trace_mlx5_fs_del_rule(rule);
-	list_del(&rule->node.list);
 	if (rule->sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		mutex_lock(&rule->dest_attr.ft->lock);
 		list_del(&rule->next_ft);
@@ -434,117 +480,203 @@ out:
 				       "%s can't del rule fg id=%d fte_index=%d\n",
 				       __func__, fg->id, fte->index);
 	}
+	kfree(rule);
 }
 
-static void destroy_fte(struct fs_fte *fte, struct mlx5_flow_group *fg)
+static void del_hw_fte(struct fs_node *node)
 {
 	struct mlx5_flow_table *ft;
-	int ret;
+	struct mlx5_flow_group *fg;
+	struct mlx5_core_dev *dev;
+	struct fs_fte *fte;
+	int err;
 
-	ret = rhashtable_remove_fast(&fg->ftes_hash, &fte->hash, rhash_fte);
-	WARN_ON(ret);
-	fte->status = 0;
+	fs_get_obj(fte, node);
+	fs_get_obj(fg, fte->node.parent);
 	fs_get_obj(ft, fg->node.parent);
-	ida_simple_remove(&ft->fte_allocator, fte->index);
+
+	trace_mlx5_fs_del_fte(fte);
+	dev = get_dev(&ft->node);
+	if (node->active) {
+		err = mlx5_cmd_delete_fte(dev, ft,
+					  fte->index);
+		if (err)
+			mlx5_core_warn(dev,
+				       "flow steering can't delete fte in index %d of flow group id %d\n",
+				       fte->index, fg->id);
+	}
 }
 
-static void del_fte(struct fs_node *node)
+static void del_sw_fte(struct fs_node *node)
 {
-	struct mlx5_flow_table *ft;
+	struct mlx5_flow_steering *steering = get_steering(node);
 	struct mlx5_flow_group *fg;
-	struct mlx5_core_dev *dev;
 	struct fs_fte *fte;
 	int err;
 
 	fs_get_obj(fte, node);
 	fs_get_obj(fg, fte->node.parent);
-	fs_get_obj(ft, fg->node.parent);
-	trace_mlx5_fs_del_fte(fte);
 
-	dev = get_dev(&ft->node);
-	err = mlx5_cmd_delete_fte(dev, ft,
-				  fte->index);
-	if (err)
-		mlx5_core_warn(dev,
-			       "flow steering can't delete fte in index %d of flow group id %d\n",
-			       fte->index, fg->id);
-
-	destroy_fte(fte, fg);
+	err = rhashtable_remove_fast(&fg->ftes_hash,
+				     &fte->hash,
+				     rhash_fte);
+	WARN_ON(err);
+	ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index);
+	kmem_cache_free(steering->ftes_cache, fte);
 }
 
-static void del_flow_group(struct fs_node *node)
+static void del_hw_flow_group(struct fs_node *node)
 {
 	struct mlx5_flow_group *fg;
 	struct mlx5_flow_table *ft;
 	struct mlx5_core_dev *dev;
-	int err;
 
 	fs_get_obj(fg, node);
 	fs_get_obj(ft, fg->node.parent);
 	dev = get_dev(&ft->node);
 	trace_mlx5_fs_del_fg(fg);
 
-	if (ft->autogroup.active)
-		ft->autogroup.num_groups--;
+	if (fg->node.active && mlx5_cmd_destroy_flow_group(dev, ft, fg->id))
+		mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n",
+			       fg->id, ft->id);
+}
+
+static void del_sw_flow_group(struct fs_node *node)
+{
+	struct mlx5_flow_steering *steering = get_steering(node);
+	struct mlx5_flow_group *fg;
+	struct mlx5_flow_table *ft;
+	int err;
+
+	fs_get_obj(fg, node);
+	fs_get_obj(ft, fg->node.parent);
 
 	rhashtable_destroy(&fg->ftes_hash);
+	ida_destroy(&fg->fte_allocator);
+	if (ft->autogroup.active)
+		ft->autogroup.num_groups--;
 	err = rhltable_remove(&ft->fgs_hash,
 			      &fg->hash,
 			      rhash_fg);
 	WARN_ON(err);
-	if (mlx5_cmd_destroy_flow_group(dev, ft, fg->id))
-		mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n",
-			       fg->id, ft->id);
+	kmem_cache_free(steering->fgs_cache, fg);
+}
+
+static int insert_fte(struct mlx5_flow_group *fg, struct fs_fte *fte)
+{
+	int index;
+	int ret;
+
+	index = ida_simple_get(&fg->fte_allocator, 0, fg->max_ftes, GFP_KERNEL);
+	if (index < 0)
+		return index;
+
+	fte->index = index + fg->start_index;
+	ret = rhashtable_insert_fast(&fg->ftes_hash,
+				     &fte->hash,
+				     rhash_fte);
+	if (ret)
+		goto err_ida_remove;
+
+	tree_add_node(&fte->node, &fg->node);
+	list_add_tail(&fte->node.list, &fg->node.children);
+	return 0;
+
+err_ida_remove:
+	ida_simple_remove(&fg->fte_allocator, index);
+	return ret;
 }
 
-static struct fs_fte *alloc_fte(struct mlx5_flow_act *flow_act,
+static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
 				u32 *match_value,
-				unsigned int index)
+				struct mlx5_flow_act *flow_act)
 {
+	struct mlx5_flow_steering *steering = get_steering(&ft->node);
 	struct fs_fte *fte;
 
-	fte = kzalloc(sizeof(*fte), GFP_KERNEL);
+	fte = kmem_cache_zalloc(steering->ftes_cache, GFP_KERNEL);
 	if (!fte)
 		return ERR_PTR(-ENOMEM);
 
 	memcpy(fte->val, match_value, sizeof(fte->val));
 	fte->node.type =  FS_TYPE_FLOW_ENTRY;
 	fte->flow_tag = flow_act->flow_tag;
-	fte->index = index;
 	fte->action = flow_act->action;
 	fte->encap_id = flow_act->encap_id;
 	fte->modify_id = flow_act->modify_id;
 
+	tree_init_node(&fte->node, del_hw_fte, del_sw_fte);
+
 	return fte;
 }
 
-static struct mlx5_flow_group *alloc_flow_group(u32 *create_fg_in)
+static void dealloc_flow_group(struct mlx5_flow_steering *steering,
+			       struct mlx5_flow_group *fg)
+{
+	rhashtable_destroy(&fg->ftes_hash);
+	kmem_cache_free(steering->fgs_cache, fg);
+}
+
+static struct mlx5_flow_group *alloc_flow_group(struct mlx5_flow_steering *steering,
+						u8 match_criteria_enable,
+						void *match_criteria,
+						int start_index,
+						int end_index)
 {
 	struct mlx5_flow_group *fg;
-	void *match_criteria = MLX5_ADDR_OF(create_flow_group_in,
-					    create_fg_in, match_criteria);
-	u8 match_criteria_enable = MLX5_GET(create_flow_group_in,
-					    create_fg_in,
-					    match_criteria_enable);
 	int ret;
 
-	fg = kzalloc(sizeof(*fg), GFP_KERNEL);
+	fg = kmem_cache_zalloc(steering->fgs_cache, GFP_KERNEL);
 	if (!fg)
 		return ERR_PTR(-ENOMEM);
 
 	ret = rhashtable_init(&fg->ftes_hash, &rhash_fte);
 	if (ret) {
-		kfree(fg);
+		kmem_cache_free(steering->fgs_cache, fg);
 		return ERR_PTR(ret);
-	}
+}
+	ida_init(&fg->fte_allocator);
 	fg->mask.match_criteria_enable = match_criteria_enable;
 	memcpy(&fg->mask.match_criteria, match_criteria,
 	       sizeof(fg->mask.match_criteria));
 	fg->node.type =  FS_TYPE_FLOW_GROUP;
-	fg->start_index = MLX5_GET(create_flow_group_in, create_fg_in,
-				   start_flow_index);
-	fg->max_ftes = MLX5_GET(create_flow_group_in, create_fg_in,
-				end_flow_index) - fg->start_index + 1;
+	fg->start_index = start_index;
+	fg->max_ftes = end_index - start_index + 1;
+
+	return fg;
+}
+
+static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *ft,
+						       u8 match_criteria_enable,
+						       void *match_criteria,
+						       int start_index,
+						       int end_index,
+						       struct list_head *prev)
+{
+	struct mlx5_flow_steering *steering = get_steering(&ft->node);
+	struct mlx5_flow_group *fg;
+	int ret;
+
+	fg = alloc_flow_group(steering, match_criteria_enable, match_criteria,
+			      start_index, end_index);
+	if (IS_ERR(fg))
+		return fg;
+
+	/* initialize refcnt, add to parent list */
+	ret = rhltable_insert(&ft->fgs_hash,
+			      &fg->hash,
+			      rhash_fg);
+	if (ret) {
+		dealloc_flow_group(steering, fg);
+		return ERR_PTR(ret);
+	}
+
+	tree_init_node(&fg->node, del_hw_flow_group, del_sw_flow_group);
+	tree_add_node(&fg->node, &ft->node);
+	/* Add node to group list */
+	list_add(&fg->node.list, prev);
+	atomic_inc(&ft->node.version);
+
 	return fg;
 }
 
@@ -575,7 +707,6 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_ft
 	ft->flags = flags;
 	INIT_LIST_HEAD(&ft->fwd_rules);
 	mutex_init(&ft->lock);
-	ida_init(&ft->fte_allocator);
 
 	return ft;
 }
@@ -693,8 +824,10 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio
 				 *prio)
 {
 	struct mlx5_flow_root_namespace *root = find_root(&prio->node);
+	struct mlx5_ft_underlay_qp *uqp;
 	int min_level = INT_MAX;
 	int err;
+	u32 qpn;
 
 	if (root->root_ft)
 		min_level = root->root_ft->level;
@@ -702,10 +835,24 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio
 	if (ft->level >= min_level)
 		return 0;
 
-	err = mlx5_cmd_update_root_ft(root->dev, ft, root->underlay_qpn);
+	if (list_empty(&root->underlay_qpns)) {
+		/* Don't set any QPN (zero) in case QPN list is empty */
+		qpn = 0;
+		err = mlx5_cmd_update_root_ft(root->dev, ft, qpn, false);
+	} else {
+		list_for_each_entry(uqp, &root->underlay_qpns, list) {
+			qpn = uqp->qpn;
+			err = mlx5_cmd_update_root_ft(root->dev, ft, qpn,
+						      false);
+			if (err)
+				break;
+		}
+	}
+
 	if (err)
-		mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n",
-			       ft->id);
+		mlx5_core_warn(root->dev,
+			       "Update root flow table of id(%u) qpn(%d) failed\n",
+			       ft->id, qpn);
 	else
 		root->root_ft = ft;
 
@@ -724,7 +871,7 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
 	fs_get_obj(fte, rule->node.parent);
 	if (!(fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
 		return -EINVAL;
-	lock_ref_node(&fte->node);
+	down_write_ref_node(&fte->node);
 	fs_get_obj(fg, fte->node.parent);
 	fs_get_obj(ft, fg->node.parent);
 
@@ -733,7 +880,7 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
 				  ft, fg->id,
 				  modify_mask,
 				  fte);
-	unlock_ref_node(&fte->node);
+	up_write_ref_node(&fte->node);
 
 	return err;
 }
@@ -870,7 +1017,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 		goto unlock_root;
 	}
 
-	tree_init_node(&ft->node, 1, del_flow_table);
+	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 = find_next_chained_ft(fs_prio);
 	err = mlx5_cmd_create_flow_table(root->dev, ft->vport, ft->op_mod, ft->type,
@@ -882,17 +1029,17 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 	err = connect_flow_table(root->dev, ft, fs_prio);
 	if (err)
 		goto destroy_ft;
-	lock_ref_node(&fs_prio->node);
+	ft->node.active = true;
+	down_write_ref_node(&fs_prio->node);
 	tree_add_node(&ft->node, &fs_prio->node);
 	list_add_flow_table(ft, fs_prio);
 	fs_prio->num_ft++;
-	unlock_ref_node(&fs_prio->node);
+	up_write_ref_node(&fs_prio->node);
 	mutex_unlock(&root->chain_lock);
 	return ft;
 destroy_ft:
 	mlx5_cmd_destroy_flow_table(root->dev, ft);
 free_ft:
-	ida_destroy(&ft->fte_allocator);
 	kfree(ft);
 unlock_root:
 	mutex_unlock(&root->chain_lock);
@@ -960,54 +1107,6 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
 }
 EXPORT_SYMBOL(mlx5_create_auto_grouped_flow_table);
 
-/* Flow table should be locked */
-static struct mlx5_flow_group *create_flow_group_common(struct mlx5_flow_table *ft,
-							u32 *fg_in,
-							struct list_head
-							*prev_fg,
-							bool is_auto_fg)
-{
-	struct mlx5_flow_group *fg;
-	struct mlx5_core_dev *dev = get_dev(&ft->node);
-	int err;
-
-	if (!dev)
-		return ERR_PTR(-ENODEV);
-
-	fg = alloc_flow_group(fg_in);
-	if (IS_ERR(fg))
-		return fg;
-
-	err = rhltable_insert(&ft->fgs_hash, &fg->hash, rhash_fg);
-	if (err)
-		goto err_free_fg;
-
-	err = mlx5_cmd_create_flow_group(dev, ft, fg_in, &fg->id);
-	if (err)
-		goto err_remove_fg;
-
-	if (ft->autogroup.active)
-		ft->autogroup.num_groups++;
-	/* Add node to tree */
-	tree_init_node(&fg->node, !is_auto_fg, del_flow_group);
-	tree_add_node(&fg->node, &ft->node);
-	/* Add node to group list */
-	list_add(&fg->node.list, prev_fg);
-
-	trace_mlx5_fs_add_fg(fg);
-	return fg;
-
-err_remove_fg:
-	WARN_ON(rhltable_remove(&ft->fgs_hash,
-				&fg->hash,
-				rhash_fg));
-err_free_fg:
-	rhashtable_destroy(&fg->ftes_hash);
-	kfree(fg);
-
-	return ERR_PTR(err);
-}
-
 struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft,
 					       u32 *fg_in)
 {
@@ -1016,7 +1115,13 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft,
 	u8 match_criteria_enable = MLX5_GET(create_flow_group_in,
 					    fg_in,
 					    match_criteria_enable);
+	int start_index = MLX5_GET(create_flow_group_in, fg_in,
+				   start_flow_index);
+	int end_index = MLX5_GET(create_flow_group_in, fg_in,
+				 end_flow_index);
+	struct mlx5_core_dev *dev = get_dev(&ft->node);
 	struct mlx5_flow_group *fg;
+	int err;
 
 	if (!check_valid_mask(match_criteria_enable, match_criteria))
 		return ERR_PTR(-EINVAL);
@@ -1024,9 +1129,21 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft,
 	if (ft->autogroup.active)
 		return ERR_PTR(-EPERM);
 
-	lock_ref_node(&ft->node);
-	fg = create_flow_group_common(ft, fg_in, ft->node.children.prev, false);
-	unlock_ref_node(&ft->node);
+	down_write_ref_node(&ft->node);
+	fg = alloc_insert_flow_group(ft, match_criteria_enable, match_criteria,
+				     start_index, end_index,
+				     ft->node.children.prev);
+	up_write_ref_node(&ft->node);
+	if (IS_ERR(fg))
+		return fg;
+
+	err = mlx5_cmd_create_flow_group(dev, ft, fg_in, &fg->id);
+	if (err) {
+		tree_put_node(&fg->node);
+		return ERR_PTR(err);
+	}
+	trace_mlx5_fs_add_fg(fg);
+	fg->node.active = true;
 
 	return fg;
 }
@@ -1067,7 +1184,7 @@ static void destroy_flow_handle(struct fs_fte *fte,
 				int i)
 {
 	for (; --i >= 0;) {
-		if (atomic_dec_and_test(&handle->rule[i]->node.refcount)) {
+		if (refcount_dec_and_test(&handle->rule[i]->node.refcount)) {
 			fte->dests_size--;
 			list_del(&handle->rule[i]->node.list);
 			kfree(handle->rule[i]);
@@ -1098,7 +1215,7 @@ create_flow_handle(struct fs_fte *fte,
 		if (dest) {
 			rule = find_flow_rule(fte, dest + i);
 			if (rule) {
-				atomic_inc(&rule->node.refcount);
+				refcount_inc(&rule->node.refcount);
 				goto rule_found;
 			}
 		}
@@ -1111,7 +1228,7 @@ create_flow_handle(struct fs_fte *fte,
 		/* Add dest to dests list- we need flow tables to be in the
 		 * end of the list for forward to next prio rules.
 		 */
-		tree_init_node(&rule->node, 1, del_rule);
+		tree_init_node(&rule->node, NULL, del_sw_hw_rule);
 		if (dest &&
 		    dest[i].type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
 			list_add(&rule->node.list, &fte->node.children);
@@ -1167,7 +1284,9 @@ add_rule_fte(struct fs_fte *fte,
 	if (err)
 		goto free_handle;
 
+	fte->node.active = true;
 	fte->status |= FS_FTE_STATUS_EXISTING;
+	atomic_inc(&fte->node.version);
 
 out:
 	return handle;
@@ -1177,59 +1296,17 @@ free_handle:
 	return ERR_PTR(err);
 }
 
-static struct fs_fte *create_fte(struct mlx5_flow_group *fg,
-				 u32 *match_value,
-				 struct mlx5_flow_act *flow_act)
-{
-	struct mlx5_flow_table *ft;
-	struct fs_fte *fte;
-	int index;
-	int ret;
-
-	fs_get_obj(ft, fg->node.parent);
-	index = ida_simple_get(&ft->fte_allocator, fg->start_index,
-			       fg->start_index + fg->max_ftes,
-			       GFP_KERNEL);
-	if (index < 0)
-		return ERR_PTR(index);
-
-	fte = alloc_fte(flow_act, match_value, index);
-	if (IS_ERR(fte)) {
-		ret = PTR_ERR(fte);
-		goto err_alloc;
-	}
-	ret = rhashtable_insert_fast(&fg->ftes_hash, &fte->hash, rhash_fte);
-	if (ret)
-		goto err_hash;
-
-	return fte;
-
-err_hash:
-	kfree(fte);
-err_alloc:
-	ida_simple_remove(&ft->fte_allocator, index);
-	return ERR_PTR(ret);
-}
-
-static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft,
-						u8 match_criteria_enable,
-						u32 *match_criteria)
+static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table  *ft,
+						     struct mlx5_flow_spec *spec)
 {
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct list_head *prev = &ft->node.children;
-	unsigned int candidate_index = 0;
 	struct mlx5_flow_group *fg;
-	void *match_criteria_addr;
+	unsigned int candidate_index = 0;
 	unsigned int group_size = 0;
-	u32 *in;
 
 	if (!ft->autogroup.active)
 		return ERR_PTR(-ENOENT);
 
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
-		return ERR_PTR(-ENOMEM);
-
 	if (ft->autogroup.num_groups < ft->autogroup.required_groups)
 		/* We save place for flow groups in addition to max types */
 		group_size = ft->max_fte / (ft->autogroup.required_groups + 1);
@@ -1247,25 +1324,55 @@ static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft,
 		prev = &fg->node.list;
 	}
 
-	if (candidate_index + group_size > ft->max_fte) {
-		fg = ERR_PTR(-ENOSPC);
+	if (candidate_index + group_size > ft->max_fte)
+		return ERR_PTR(-ENOSPC);
+
+	fg = alloc_insert_flow_group(ft,
+				     spec->match_criteria_enable,
+				     spec->match_criteria,
+				     candidate_index,
+				     candidate_index + group_size - 1,
+				     prev);
+	if (IS_ERR(fg))
 		goto out;
-	}
+
+	ft->autogroup.num_groups++;
+
+out:
+	return fg;
+}
+
+static int create_auto_flow_group(struct mlx5_flow_table *ft,
+				  struct mlx5_flow_group *fg)
+{
+	struct mlx5_core_dev *dev = get_dev(&ft->node);
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	void *match_criteria_addr;
+	int err;
+	u32 *in;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
 
 	MLX5_SET(create_flow_group_in, in, match_criteria_enable,
-		 match_criteria_enable);
-	MLX5_SET(create_flow_group_in, in, start_flow_index, candidate_index);
-	MLX5_SET(create_flow_group_in, in, end_flow_index,   candidate_index +
-		 group_size - 1);
+		 fg->mask.match_criteria_enable);
+	MLX5_SET(create_flow_group_in, in, start_flow_index, fg->start_index);
+	MLX5_SET(create_flow_group_in, in, end_flow_index,   fg->start_index +
+		 fg->max_ftes - 1);
 	match_criteria_addr = MLX5_ADDR_OF(create_flow_group_in,
 					   in, match_criteria);
-	memcpy(match_criteria_addr, match_criteria,
-	       MLX5_ST_SZ_BYTES(fte_match_param));
+	memcpy(match_criteria_addr, fg->mask.match_criteria,
+	       sizeof(fg->mask.match_criteria));
+
+	err = mlx5_cmd_create_flow_group(dev, ft, in, &fg->id);
+	if (!err) {
+		fg->node.active = true;
+		trace_mlx5_fs_add_fg(fg);
+	}
 
-	fg = create_flow_group_common(ft, in, prev, true);
-out:
 	kvfree(in);
-	return fg;
+	return err;
 }
 
 static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
@@ -1340,60 +1447,30 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg,
 					    struct fs_fte *fte)
 {
 	struct mlx5_flow_handle *handle;
-	struct mlx5_flow_table *ft;
+	int old_action;
 	int i;
+	int ret;
 
-	if (fte) {
-		int old_action;
-		int ret;
-
-		nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD);
-		ret = check_conflicting_ftes(fte, flow_act);
-		if (ret) {
-			handle = ERR_PTR(ret);
-			goto unlock_fte;
-		}
-
-		old_action = fte->action;
-		fte->action |= flow_act->action;
-		handle = add_rule_fte(fte, fg, dest, dest_num,
-				      old_action != flow_act->action);
-		if (IS_ERR(handle)) {
-			fte->action = old_action;
-			goto unlock_fte;
-		} else {
-			trace_mlx5_fs_set_fte(fte, false);
-			goto add_rules;
-		}
-	}
-	fs_get_obj(ft, fg->node.parent);
+	ret = check_conflicting_ftes(fte, flow_act);
+	if (ret)
+		return ERR_PTR(ret);
 
-	fte = create_fte(fg, match_value, flow_act);
-	if (IS_ERR(fte))
-		return (void *)fte;
-	tree_init_node(&fte->node, 0, del_fte);
-	nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD);
-	handle = add_rule_fte(fte, fg, dest, dest_num, false);
+	old_action = fte->action;
+	fte->action |= flow_act->action;
+	handle = add_rule_fte(fte, fg, dest, dest_num,
+			      old_action != flow_act->action);
 	if (IS_ERR(handle)) {
-		unlock_ref_node(&fte->node);
-		destroy_fte(fte, fg);
-		kfree(fte);
+		fte->action = old_action;
 		return handle;
 	}
+	trace_mlx5_fs_set_fte(fte, false);
 
-	tree_add_node(&fte->node, &fg->node);
-	/* fte list isn't sorted */
-	list_add_tail(&fte->node.list, &fg->node.children);
-	trace_mlx5_fs_set_fte(fte, true);
-add_rules:
 	for (i = 0; i < handle->num_rules; i++) {
-		if (atomic_read(&handle->rule[i]->node.refcount) == 1) {
+		if (refcount_read(&handle->rule[i]->node.refcount) == 1) {
 			tree_add_node(&handle->rule[i]->node, &fte->node);
 			trace_mlx5_fs_add_rule(handle->rule[i]);
 		}
 	}
-unlock_fte:
-	unlock_ref_node(&fte->node);
 	return handle;
 }
 
@@ -1441,93 +1518,197 @@ static bool dest_is_valid(struct mlx5_flow_destination *dest,
 	return true;
 }
 
-static struct mlx5_flow_handle *
-try_add_to_existing_fg(struct mlx5_flow_table *ft,
-		       struct mlx5_flow_spec *spec,
-		       struct mlx5_flow_act *flow_act,
-		       struct mlx5_flow_destination *dest,
-		       int dest_num)
-{
+struct match_list {
+	struct list_head	list;
 	struct mlx5_flow_group *g;
-	struct mlx5_flow_handle *rule = ERR_PTR(-ENOENT);
+};
+
+struct match_list_head {
+	struct list_head  list;
+	struct match_list first;
+};
+
+static void free_match_list(struct match_list_head *head)
+{
+	if (!list_empty(&head->list)) {
+		struct match_list *iter, *match_tmp;
+
+		list_del(&head->first.list);
+		tree_put_node(&head->first.g->node);
+		list_for_each_entry_safe(iter, match_tmp, &head->list,
+					 list) {
+			tree_put_node(&iter->g->node);
+			list_del(&iter->list);
+			kfree(iter);
+		}
+	}
+}
+
+static int build_match_list(struct match_list_head *match_head,
+			    struct mlx5_flow_table *ft,
+			    struct mlx5_flow_spec *spec)
+{
 	struct rhlist_head *tmp, *list;
-	struct match_list {
-		struct list_head	list;
-		struct mlx5_flow_group *g;
-	} match_list, *iter;
-	LIST_HEAD(match_head);
+	struct mlx5_flow_group *g;
+	int err = 0;
 
 	rcu_read_lock();
+	INIT_LIST_HEAD(&match_head->list);
 	/* Collect all fgs which has a matching match_criteria */
 	list = rhltable_lookup(&ft->fgs_hash, spec, rhash_fg);
+	/* RCU is atomic, we can't execute FW commands here */
 	rhl_for_each_entry_rcu(g, tmp, list, hash) {
 		struct match_list *curr_match;
 
-		if (likely(list_empty(&match_head))) {
-			match_list.g = g;
-			list_add_tail(&match_list.list, &match_head);
+		if (likely(list_empty(&match_head->list))) {
+			if (!tree_get_node(&g->node))
+				continue;
+			match_head->first.g = g;
+			list_add_tail(&match_head->first.list,
+				      &match_head->list);
 			continue;
 		}
-		curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC);
 
+		curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC);
 		if (!curr_match) {
-			rcu_read_unlock();
-			rule = ERR_PTR(-ENOMEM);
-			goto free_list;
+			free_match_list(match_head);
+			err = -ENOMEM;
+			goto out;
+		}
+		if (!tree_get_node(&g->node)) {
+			kfree(curr_match);
+			continue;
 		}
 		curr_match->g = g;
-		list_add_tail(&curr_match->list, &match_head);
+		list_add_tail(&curr_match->list, &match_head->list);
 	}
+out:
 	rcu_read_unlock();
+	return err;
+}
+
+static u64 matched_fgs_get_version(struct list_head *match_head)
+{
+	struct match_list *iter;
+	u64 version = 0;
+
+	list_for_each_entry(iter, match_head, list)
+		version += (u64)atomic_read(&iter->g->node.version);
+	return version;
+}
 
+static struct mlx5_flow_handle *
+try_add_to_existing_fg(struct mlx5_flow_table *ft,
+		       struct list_head *match_head,
+		       struct mlx5_flow_spec *spec,
+		       struct mlx5_flow_act *flow_act,
+		       struct mlx5_flow_destination *dest,
+		       int dest_num,
+		       int ft_version)
+{
+	struct mlx5_flow_steering *steering = get_steering(&ft->node);
+	struct mlx5_flow_group *g;
+	struct mlx5_flow_handle *rule;
+	struct match_list *iter;
+	bool take_write = false;
+	struct fs_fte *fte;
+	u64  version;
+	int err;
+
+	fte = alloc_fte(ft, spec->match_value, flow_act);
+	if (IS_ERR(fte))
+		return  ERR_PTR(-ENOMEM);
+
+	list_for_each_entry(iter, match_head, list) {
+		nested_down_read_ref_node(&iter->g->node, FS_LOCK_PARENT);
+		ida_pre_get(&iter->g->fte_allocator, GFP_KERNEL);
+	}
+
+search_again_locked:
+	version = matched_fgs_get_version(match_head);
 	/* Try to find a fg that already contains a matching fte */
-	list_for_each_entry(iter, &match_head, list) {
-		struct fs_fte *fte;
+	list_for_each_entry(iter, match_head, list) {
+		struct fs_fte *fte_tmp;
 
 		g = iter->g;
-		nested_lock_ref_node(&g->node, FS_MUTEX_PARENT);
-		fte = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value,
-					     rhash_fte);
-		if (fte) {
-			rule = add_rule_fg(g, spec->match_value,
-					   flow_act, dest, dest_num, fte);
-			unlock_ref_node(&g->node);
-			goto free_list;
+		fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value,
+						 rhash_fte);
+		if (!fte_tmp || !tree_get_node(&fte_tmp->node))
+			continue;
+
+		nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
+		if (!take_write) {
+			list_for_each_entry(iter, match_head, list)
+				up_read_ref_node(&iter->g->node);
+		} else {
+			list_for_each_entry(iter, match_head, list)
+				up_write_ref_node(&iter->g->node);
 		}
-		unlock_ref_node(&g->node);
+
+		rule = add_rule_fg(g, spec->match_value,
+				   flow_act, dest, dest_num, fte_tmp);
+		up_write_ref_node(&fte_tmp->node);
+		tree_put_node(&fte_tmp->node);
+		kmem_cache_free(steering->ftes_cache, fte);
+		return rule;
 	}
 
 	/* No group with matching fte found. Try to add a new fte to any
 	 * matching fg.
 	 */
-	list_for_each_entry(iter, &match_head, list) {
-		g = iter->g;
 
-		nested_lock_ref_node(&g->node, FS_MUTEX_PARENT);
-		rule = add_rule_fg(g, spec->match_value,
-				   flow_act, dest, dest_num, NULL);
-		if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOSPC) {
-			unlock_ref_node(&g->node);
-			goto free_list;
-		}
-		unlock_ref_node(&g->node);
+	if (!take_write) {
+		list_for_each_entry(iter, match_head, list)
+			up_read_ref_node(&iter->g->node);
+		list_for_each_entry(iter, match_head, list)
+			nested_down_write_ref_node(&iter->g->node,
+						   FS_LOCK_PARENT);
+		take_write = true;
 	}
 
-free_list:
-	if (!list_empty(&match_head)) {
-		struct match_list *match_tmp;
+	/* Check the ft version, for case that new flow group
+	 * was added while the fgs weren't locked
+	 */
+	if (atomic_read(&ft->node.version) != ft_version) {
+		rule = ERR_PTR(-EAGAIN);
+		goto out;
+	}
 
-		/* The most common case is having one FG. Since we want to
-		 * optimize this case, we save the first on the stack.
-		 * Therefore, no need to free it.
-		 */
-		list_del(&list_first_entry(&match_head, typeof(*iter), list)->list);
-		list_for_each_entry_safe(iter, match_tmp, &match_head, list) {
-			list_del(&iter->list);
-			kfree(iter);
+	/* Check the fgs version, for case the new FTE with the
+	 * same values was added while the fgs weren't locked
+	 */
+	if (version != matched_fgs_get_version(match_head))
+		goto search_again_locked;
+
+	list_for_each_entry(iter, match_head, list) {
+		g = iter->g;
+
+		if (!g->node.active)
+			continue;
+		err = insert_fte(g, fte);
+		if (err) {
+			if (err == -ENOSPC)
+				continue;
+			list_for_each_entry(iter, match_head, list)
+				up_write_ref_node(&iter->g->node);
+			kmem_cache_free(steering->ftes_cache, fte);
+			return ERR_PTR(err);
 		}
-	}
 
+		nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
+		list_for_each_entry(iter, match_head, list)
+			up_write_ref_node(&iter->g->node);
+		rule = add_rule_fg(g, spec->match_value,
+				   flow_act, dest, dest_num, fte);
+		up_write_ref_node(&fte->node);
+		tree_put_node(&fte->node);
+		return rule;
+	}
+	rule = ERR_PTR(-ENOENT);
+out:
+	list_for_each_entry(iter, match_head, list)
+		up_write_ref_node(&iter->g->node);
+	kmem_cache_free(steering->ftes_cache, fte);
 	return rule;
 }
 
@@ -1539,8 +1720,14 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 		     int dest_num)
 
 {
+	struct mlx5_flow_steering *steering = get_steering(&ft->node);
 	struct mlx5_flow_group *g;
 	struct mlx5_flow_handle *rule;
+	struct match_list_head match_head;
+	bool take_write = false;
+	struct fs_fte *fte;
+	int version;
+	int err;
 	int i;
 
 	if (!check_valid_spec(spec))
@@ -1550,33 +1737,73 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 		if (!dest_is_valid(&dest[i], flow_act->action, ft))
 			return ERR_PTR(-EINVAL);
 	}
+	nested_down_read_ref_node(&ft->node, FS_LOCK_GRANDPARENT);
+search_again_locked:
+	version = atomic_read(&ft->node.version);
+
+	/* Collect all fgs which has a matching match_criteria */
+	err = build_match_list(&match_head, ft, spec);
+	if (err)
+		return ERR_PTR(err);
 
-	nested_lock_ref_node(&ft->node, FS_MUTEX_GRANDPARENT);
-	rule = try_add_to_existing_fg(ft, spec, flow_act, dest, dest_num);
-	if (!IS_ERR(rule))
-		goto unlock;
+	if (!take_write)
+		up_read_ref_node(&ft->node);
 
-	g = create_autogroup(ft, spec->match_criteria_enable,
-			     spec->match_criteria);
+	rule = try_add_to_existing_fg(ft, &match_head.list, spec, flow_act, dest,
+				      dest_num, version);
+	free_match_list(&match_head);
+	if (!IS_ERR(rule) ||
+	    (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN))
+		return rule;
+
+	if (!take_write) {
+		nested_down_write_ref_node(&ft->node, FS_LOCK_GRANDPARENT);
+		take_write = true;
+	}
+
+	if (PTR_ERR(rule) == -EAGAIN ||
+	    version != atomic_read(&ft->node.version))
+		goto search_again_locked;
+
+	g = alloc_auto_flow_group(ft, spec);
 	if (IS_ERR(g)) {
 		rule = (void *)g;
-		goto unlock;
+		up_write_ref_node(&ft->node);
+		return rule;
 	}
 
-	rule = add_rule_fg(g, spec->match_value, flow_act, dest,
-			   dest_num, NULL);
-	if (IS_ERR(rule)) {
-		/* Remove assumes refcount > 0 and autogroup creates a group
-		 * with a refcount = 0.
-		 */
-		unlock_ref_node(&ft->node);
-		tree_get_node(&g->node);
-		tree_remove_node(&g->node);
-		return rule;
+	nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
+	up_write_ref_node(&ft->node);
+
+	err = create_auto_flow_group(ft, g);
+	if (err)
+		goto err_release_fg;
+
+	fte = alloc_fte(ft, spec->match_value, flow_act);
+	if (IS_ERR(fte)) {
+		err = PTR_ERR(fte);
+		goto err_release_fg;
 	}
-unlock:
-	unlock_ref_node(&ft->node);
+
+	err = insert_fte(g, fte);
+	if (err) {
+		kmem_cache_free(steering->ftes_cache, fte);
+		goto err_release_fg;
+	}
+
+	nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
+	up_write_ref_node(&g->node);
+	rule = add_rule_fg(g, spec->match_value, flow_act, dest,
+			   dest_num, fte);
+	up_write_ref_node(&fte->node);
+	tree_put_node(&fte->node);
+	tree_put_node(&g->node);
 	return rule;
+
+err_release_fg:
+	up_write_ref_node(&g->node);
+	tree_put_node(&g->node);
+	return ERR_PTR(err);
 }
 
 static bool fwd_next_prio_supported(struct mlx5_flow_table *ft)
@@ -1661,23 +1888,43 @@ static struct mlx5_flow_table *find_next_ft(struct mlx5_flow_table *ft)
 static int update_root_ft_destroy(struct mlx5_flow_table *ft)
 {
 	struct mlx5_flow_root_namespace *root = find_root(&ft->node);
+	struct mlx5_ft_underlay_qp *uqp;
 	struct mlx5_flow_table *new_root_ft = NULL;
+	int err = 0;
+	u32 qpn;
 
 	if (root->root_ft != ft)
 		return 0;
 
 	new_root_ft = find_next_ft(ft);
-	if (new_root_ft) {
-		int err = mlx5_cmd_update_root_ft(root->dev, new_root_ft,
-						  root->underlay_qpn);
 
-		if (err) {
-			mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n",
-				       ft->id);
-			return err;
+	if (!new_root_ft) {
+		root->root_ft = NULL;
+		return 0;
+	}
+
+	if (list_empty(&root->underlay_qpns)) {
+		/* Don't set any QPN (zero) in case QPN list is empty */
+		qpn = 0;
+		err = mlx5_cmd_update_root_ft(root->dev, new_root_ft, qpn,
+					      false);
+	} else {
+		list_for_each_entry(uqp, &root->underlay_qpns, list) {
+			qpn = uqp->qpn;
+			err = mlx5_cmd_update_root_ft(root->dev, new_root_ft,
+						      qpn, false);
+			if (err)
+				break;
 		}
 	}
-	root->root_ft = new_root_ft;
+
+	if (err)
+		mlx5_core_warn(root->dev,
+			       "Update root flow table of id(%u) qpn(%d) failed\n",
+			       ft->id, qpn);
+	else
+		root->root_ft = new_root_ft;
+
 	return 0;
 }
 
@@ -1817,7 +2064,7 @@ static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns,
 		return ERR_PTR(-ENOMEM);
 
 	fs_prio->node.type = FS_TYPE_PRIO;
-	tree_init_node(&fs_prio->node, 1, NULL);
+	tree_init_node(&fs_prio->node, NULL, NULL);
 	tree_add_node(&fs_prio->node, &ns->node);
 	fs_prio->num_levels = num_levels;
 	fs_prio->prio = prio;
@@ -1843,7 +2090,7 @@ static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio)
 		return ERR_PTR(-ENOMEM);
 
 	fs_init_namespace(ns);
-	tree_init_node(&ns->node, 1, NULL);
+	tree_init_node(&ns->node, NULL, NULL);
 	tree_add_node(&ns->node, &prio->node);
 	list_add_tail(&ns->node.list, &prio->node.children);
 
@@ -1965,10 +2212,12 @@ static struct mlx5_flow_root_namespace *create_root_ns(struct mlx5_flow_steering
 	root_ns->dev = steering->dev;
 	root_ns->table_type = table_type;
 
+	INIT_LIST_HEAD(&root_ns->underlay_qpns);
+
 	ns = &root_ns->ns;
 	fs_init_namespace(ns);
 	mutex_init(&root_ns->chain_lock);
-	tree_init_node(&ns->node, 1, NULL);
+	tree_init_node(&ns->node, NULL, NULL);
 	tree_add_node(&ns->node, NULL);
 
 	return root_ns;
@@ -2066,8 +2315,10 @@ static void clean_tree(struct fs_node *node)
 		struct fs_node *iter;
 		struct fs_node *temp;
 
+		tree_get_node(node);
 		list_for_each_entry_safe(iter, temp, &node->children, list)
 			clean_tree(iter);
+		tree_put_node(node);
 		tree_remove_node(node);
 	}
 }
@@ -2091,6 +2342,8 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
 	cleanup_root_ns(steering->sniffer_rx_root_ns);
 	cleanup_root_ns(steering->sniffer_tx_root_ns);
 	mlx5_cleanup_fc_stats(dev);
+	kmem_cache_destroy(steering->ftes_cache);
+	kmem_cache_destroy(steering->fgs_cache);
 	kfree(steering);
 }
 
@@ -2196,6 +2449,16 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 	steering->dev = dev;
 	dev->priv.steering = steering;
 
+	steering->fgs_cache = kmem_cache_create("mlx5_fs_fgs",
+						sizeof(struct mlx5_flow_group), 0,
+						0, NULL);
+	steering->ftes_cache = kmem_cache_create("mlx5_fs_ftes", sizeof(struct fs_fte), 0,
+						 0, NULL);
+	if (!steering->ftes_cache || !steering->fgs_cache) {
+		err = -ENOMEM;
+		goto err;
+	}
+
 	if ((((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) &&
 	      (MLX5_CAP_GEN(dev, nic_flow_table))) ||
 	     ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
@@ -2245,17 +2508,76 @@ err:
 int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn)
 {
 	struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns;
+	struct mlx5_ft_underlay_qp *new_uqp;
+	int err = 0;
+
+	new_uqp = kzalloc(sizeof(*new_uqp), GFP_KERNEL);
+	if (!new_uqp)
+		return -ENOMEM;
+
+	mutex_lock(&root->chain_lock);
+
+	if (!root->root_ft) {
+		err = -EINVAL;
+		goto update_ft_fail;
+	}
+
+	err = mlx5_cmd_update_root_ft(dev, root->root_ft, underlay_qpn, false);
+	if (err) {
+		mlx5_core_warn(dev, "Failed adding underlay QPN (%u) to root FT err(%d)\n",
+			       underlay_qpn, err);
+		goto update_ft_fail;
+	}
+
+	new_uqp->qpn = underlay_qpn;
+	list_add_tail(&new_uqp->list, &root->underlay_qpns);
+
+	mutex_unlock(&root->chain_lock);
 
-	root->underlay_qpn = underlay_qpn;
 	return 0;
+
+update_ft_fail:
+	mutex_unlock(&root->chain_lock);
+	kfree(new_uqp);
+	return err;
 }
 EXPORT_SYMBOL(mlx5_fs_add_rx_underlay_qpn);
 
 int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn)
 {
 	struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns;
+	struct mlx5_ft_underlay_qp *uqp;
+	bool found = false;
+	int err = 0;
+
+	mutex_lock(&root->chain_lock);
+	list_for_each_entry(uqp, &root->underlay_qpns, list) {
+		if (uqp->qpn == underlay_qpn) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		mlx5_core_warn(dev, "Failed finding underlay qp (%u) in qpn list\n",
+			       underlay_qpn);
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = mlx5_cmd_update_root_ft(dev, root->root_ft, underlay_qpn, true);
+	if (err)
+		mlx5_core_warn(dev, "Failed removing underlay QPN (%u) from root FT err(%d)\n",
+			       underlay_qpn, err);
+
+	list_del(&uqp->list);
+	mutex_unlock(&root->chain_lock);
+	kfree(uqp);
 
-	root->underlay_qpn = 0;
 	return 0;
+
+out:
+	mutex_unlock(&root->chain_lock);
+	return err;
 }
 EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 48dd78975062..397d24a621a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -33,6 +33,7 @@
 #ifndef _MLX5_FS_CORE_
 #define _MLX5_FS_CORE_
 
+#include <linux/refcount.h>
 #include <linux/mlx5/fs.h>
 #include <linux/rhashtable.h>
 
@@ -66,6 +67,8 @@ enum fs_fte_status {
 
 struct mlx5_flow_steering {
 	struct mlx5_core_dev *dev;
+	struct kmem_cache               *fgs_cache;
+	struct kmem_cache               *ftes_cache;
 	struct mlx5_flow_root_namespace *root_ns;
 	struct mlx5_flow_root_namespace *fdb_root_ns;
 	struct mlx5_flow_root_namespace *esw_egress_root_ns;
@@ -81,9 +84,12 @@ struct fs_node {
 	struct fs_node		*parent;
 	struct fs_node		*root;
 	/* lock the node for writing and traversing */
-	struct mutex		lock;
-	atomic_t		refcount;
-	void			(*remove_func)(struct fs_node *);
+	struct rw_semaphore	lock;
+	refcount_t		refcount;
+	bool			active;
+	void			(*del_hw_func)(struct fs_node *);
+	void			(*del_sw_func)(struct fs_node *);
+	atomic_t		version;
 };
 
 struct mlx5_flow_rule {
@@ -120,7 +126,6 @@ struct mlx5_flow_table {
 	/* FWD rules that point on this flow table */
 	struct list_head		fwd_rules;
 	u32				flags;
-	struct ida			fte_allocator;
 	struct rhltable			fgs_hash;
 };
 
@@ -147,6 +152,11 @@ struct mlx5_fc {
 	struct mlx5_fc_cache cache ____cacheline_aligned_in_smp;
 };
 
+struct mlx5_ft_underlay_qp {
+	struct list_head list;
+	u32 qpn;
+};
+
 #define MLX5_FTE_MATCH_PARAM_RESERVED	reserved_at_600
 /* Calculate the fte_match_param length and without the reserved length.
  * Make sure the reserved field is the last.
@@ -200,6 +210,7 @@ struct mlx5_flow_group {
 	struct mlx5_flow_group_mask	mask;
 	u32				start_index;
 	u32				max_ftes;
+	struct ida			fte_allocator;
 	u32				id;
 	struct rhashtable		ftes_hash;
 	struct rhlist_head		hash;
@@ -212,7 +223,7 @@ struct mlx5_flow_root_namespace {
 	struct mlx5_flow_table		*root_ft;
 	/* Should be held when chaining flow tables */
 	struct mutex			chain_lock;
-	u32				underlay_qpn;
+	struct list_head		underlay_qpns;
 };
 
 int mlx5_init_fc_stats(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index db86e1506c8b..1a0e797ad001 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -285,9 +285,9 @@ void mlx5_trigger_health_work(struct mlx5_core_dev *dev)
 	spin_unlock_irqrestore(&health->wq_lock, flags);
 }
 
-static void poll_health(unsigned long data)
+static void poll_health(struct timer_list *t)
 {
-	struct mlx5_core_dev *dev = (struct mlx5_core_dev *)data;
+	struct mlx5_core_dev *dev = from_timer(dev, t, priv.health.timer);
 	struct mlx5_core_health *health = &dev->priv.health;
 	u32 count;
 
@@ -320,15 +320,13 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 
-	init_timer(&health->timer);
+	timer_setup(&health->timer, poll_health, 0);
 	health->sick = 0;
 	clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
 	clear_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
 	health->health = &dev->iseg->health;
 	health->health_counter = &dev->iseg->health_counter;
 
-	health->timer.data = (unsigned long)dev;
-	health->timer.function = poll_health;
 	health->timer.expires = round_jiffies(jiffies + MLX5_HEALTH_POLL_INTERVAL);
 	add_timer(&health->timer);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index 43c126c63955..6f338a9219c8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -250,3 +250,8 @@ const struct ethtool_ops mlx5i_ethtool_ops = {
 	.get_link_ksettings = mlx5i_get_link_ksettings,
 	.get_link           = ethtool_op_get_link,
 };
+
+const struct ethtool_ops mlx5i_pkey_ethtool_ops = {
+	.get_drvinfo        = mlx5i_get_drvinfo,
+	.get_link           = ethtool_op_get_link,
+};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 145e392ab849..abf270d7f556 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -40,8 +40,6 @@
 
 static int mlx5i_open(struct net_device *netdev);
 static int mlx5i_close(struct net_device *netdev);
-static int  mlx5i_dev_init(struct net_device *dev);
-static void mlx5i_dev_cleanup(struct net_device *dev);
 static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu);
 static int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
 
@@ -70,10 +68,10 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev,
 }
 
 /* Called directly after IPoIB netdevice was created to initialize SW structs */
-static void mlx5i_init(struct mlx5_core_dev *mdev,
-		       struct net_device *netdev,
-		       const struct mlx5e_profile *profile,
-		       void *ppriv)
+void mlx5i_init(struct mlx5_core_dev *mdev,
+		struct net_device *netdev,
+		const struct mlx5e_profile *profile,
+		void *ppriv)
 {
 	struct mlx5e_priv *priv  = mlx5i_epriv(netdev);
 
@@ -108,11 +106,69 @@ static void mlx5i_cleanup(struct mlx5e_priv *priv)
 	/* Do nothing .. */
 }
 
+int mlx5i_init_underlay_qp(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5i_priv *ipriv = priv->ppriv;
+	struct mlx5_core_qp *qp = &ipriv->qp;
+	struct mlx5_qp_context *context;
+	int ret;
+
+	/* QP states */
+	context = kzalloc(sizeof(*context), GFP_KERNEL);
+	if (!context)
+		return -ENOMEM;
+
+	context->flags = cpu_to_be32(MLX5_QP_PM_MIGRATED << 11);
+	context->pri_path.port = 1;
+	context->pri_path.pkey_index = cpu_to_be16(ipriv->pkey_index);
+	context->qkey = cpu_to_be32(IB_DEFAULT_Q_KEY);
+
+	ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, context, qp);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to modify qp RST2INIT, err: %d\n", ret);
+		goto err_qp_modify_to_err;
+	}
+	memset(context, 0, sizeof(*context));
+
+	ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, context, qp);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to modify qp INIT2RTR, err: %d\n", ret);
+		goto err_qp_modify_to_err;
+	}
+
+	ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, context, qp);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to modify qp RTR2RTS, err: %d\n", ret);
+		goto err_qp_modify_to_err;
+	}
+
+	kfree(context);
+	return 0;
+
+err_qp_modify_to_err:
+	mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2ERR_QP, 0, &context, qp);
+	kfree(context);
+	return ret;
+}
+
+void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv)
+{
+	struct mlx5i_priv *ipriv = priv->ppriv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_qp_context context;
+	int err;
+
+	err = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2RST_QP, 0, &context,
+				  &ipriv->qp);
+	if (err)
+		mlx5_core_err(mdev, "Failed to modify qp 2RST, err: %d\n", err);
+}
+
 #define MLX5_QP_ENHANCED_ULP_STATELESS_MODE 2
 
-static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
+int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
 {
-	struct mlx5_qp_context *context = NULL;
 	u32 *in = NULL;
 	void *addr_path;
 	int ret = 0;
@@ -140,43 +196,12 @@ static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core
 		goto out;
 	}
 
-	/* QP states */
-	context = kzalloc(sizeof(*context), GFP_KERNEL);
-	if (!context) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	context->flags = cpu_to_be32(MLX5_QP_PM_MIGRATED << 11);
-	context->pri_path.port = 1;
-	context->qkey = cpu_to_be32(IB_DEFAULT_Q_KEY);
-
-	ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, context, qp);
-	if (ret) {
-		mlx5_core_err(mdev, "Failed to modify qp RST2INIT, err: %d\n", ret);
-		goto out;
-	}
-	memset(context, 0, sizeof(*context));
-
-	ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, context, qp);
-	if (ret) {
-		mlx5_core_err(mdev, "Failed to modify qp INIT2RTR, err: %d\n", ret);
-		goto out;
-	}
-
-	ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, context, qp);
-	if (ret) {
-		mlx5_core_err(mdev, "Failed to modify qp RTR2RTS, err: %d\n", ret);
-		goto out;
-	}
-
 out:
-	kfree(context);
 	kvfree(in);
 	return ret;
 }
 
-static void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
+void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
 {
 	mlx5_core_destroy_qp(mdev, qp);
 }
@@ -195,10 +220,14 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv)
 	err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]);
 	if (err) {
 		mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err);
-		return err;
+		goto err_destroy_underlay_qp;
 	}
 
 	return 0;
+
+err_destroy_underlay_qp:
+	mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp);
+	return err;
 }
 
 static void mlx5i_cleanup_tx(struct mlx5e_priv *priv)
@@ -249,7 +278,6 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv)
 
 static int mlx5i_init_rx(struct mlx5e_priv *priv)
 {
-	struct mlx5i_priv *ipriv  = priv->ppriv;
 	int err;
 
 	err = mlx5e_create_indirect_rqt(priv);
@@ -268,18 +296,12 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 	if (err)
 		goto err_destroy_indirect_tirs;
 
-	err = mlx5_fs_add_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
-	if (err)
-		goto err_destroy_direct_tirs;
-
 	err = mlx5i_create_flow_steering(priv);
 	if (err)
-		goto err_remove_rx_underlay_qpn;
+		goto err_destroy_direct_tirs;
 
 	return 0;
 
-err_remove_rx_underlay_qpn:
-	mlx5_fs_remove_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv);
 err_destroy_indirect_tirs:
@@ -293,9 +315,6 @@ err_destroy_indirect_rqts:
 
 static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
 {
-	struct mlx5i_priv *ipriv  = priv->ppriv;
-
-	mlx5_fs_remove_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
 	mlx5i_destroy_flow_steering(priv);
 	mlx5e_destroy_direct_tirs(priv);
 	mlx5e_destroy_indirect_tirs(priv);
@@ -351,7 +370,7 @@ out:
 	return err;
 }
 
-static int mlx5i_dev_init(struct net_device *dev)
+int mlx5i_dev_init(struct net_device *dev)
 {
 	struct mlx5e_priv    *priv   = mlx5i_epriv(dev);
 	struct mlx5i_priv    *ipriv  = priv->ppriv;
@@ -361,6 +380,9 @@ static int mlx5i_dev_init(struct net_device *dev)
 	dev->dev_addr[2] = (ipriv->qp.qpn >>  8) & 0xff;
 	dev->dev_addr[3] = (ipriv->qp.qpn) & 0xff;
 
+	/* Add QPN to net-device mapping to HT */
+	mlx5i_pkey_add_qpn(dev ,ipriv->qp.qpn);
+
 	return 0;
 }
 
@@ -378,63 +400,84 @@ static int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	}
 }
 
-static void mlx5i_dev_cleanup(struct net_device *dev)
+void mlx5i_dev_cleanup(struct net_device *dev)
 {
 	struct mlx5e_priv    *priv   = mlx5i_epriv(dev);
-	struct mlx5_core_dev *mdev   = priv->mdev;
-	struct mlx5i_priv    *ipriv  = priv->ppriv;
-	struct mlx5_qp_context context;
+	struct mlx5i_priv    *ipriv = priv->ppriv;
+
+	mlx5i_uninit_underlay_qp(priv);
 
-	/* detach qp from flow-steering by reset it */
-	mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2RST_QP, 0, &context, &ipriv->qp);
+	/* Delete QPN to net-device mapping from HT */
+	mlx5i_pkey_del_qpn(dev, ipriv->qp.qpn);
 }
 
 static int mlx5i_open(struct net_device *netdev)
 {
-	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+	struct mlx5e_priv *epriv = mlx5i_epriv(netdev);
+	struct mlx5i_priv *ipriv = epriv->ppriv;
+	struct mlx5_core_dev *mdev = epriv->mdev;
 	int err;
 
-	mutex_lock(&priv->state_lock);
+	mutex_lock(&epriv->state_lock);
 
-	set_bit(MLX5E_STATE_OPENED, &priv->state);
+	set_bit(MLX5E_STATE_OPENED, &epriv->state);
 
-	err = mlx5e_open_channels(priv, &priv->channels);
-	if (err)
+	err = mlx5i_init_underlay_qp(epriv);
+	if (err) {
+		mlx5_core_warn(mdev, "prepare underlay qp state failed, %d\n", err);
 		goto err_clear_state_opened_flag;
+	}
 
-	mlx5e_refresh_tirs(priv, false);
-	mlx5e_activate_priv_channels(priv);
-	mlx5e_timestamp_init(priv);
+	err = mlx5_fs_add_rx_underlay_qpn(mdev, ipriv->qp.qpn);
+	if (err) {
+		mlx5_core_warn(mdev, "attach underlay qp to ft failed, %d\n", err);
+		goto err_reset_qp;
+	}
 
-	mutex_unlock(&priv->state_lock);
+	err = mlx5e_open_channels(epriv, &epriv->channels);
+	if (err)
+		goto err_remove_fs_underlay_qp;
+
+	mlx5e_refresh_tirs(epriv, false);
+	mlx5e_activate_priv_channels(epriv);
+	mlx5e_timestamp_set(epriv);
+
+	mutex_unlock(&epriv->state_lock);
 	return 0;
 
+err_remove_fs_underlay_qp:
+	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn);
+err_reset_qp:
+	mlx5i_uninit_underlay_qp(epriv);
 err_clear_state_opened_flag:
-	clear_bit(MLX5E_STATE_OPENED, &priv->state);
-	mutex_unlock(&priv->state_lock);
+	clear_bit(MLX5E_STATE_OPENED, &epriv->state);
+	mutex_unlock(&epriv->state_lock);
 	return err;
 }
 
 static int mlx5i_close(struct net_device *netdev)
 {
-	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+	struct mlx5e_priv *epriv = mlx5i_epriv(netdev);
+	struct mlx5i_priv *ipriv = epriv->ppriv;
+	struct mlx5_core_dev *mdev = epriv->mdev;
 
 	/* May already be CLOSED in case a previous configuration operation
 	 * (e.g RX/TX queue size change) that involves close&open failed.
 	 */
-	mutex_lock(&priv->state_lock);
+	mutex_lock(&epriv->state_lock);
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+	if (!test_bit(MLX5E_STATE_OPENED, &epriv->state))
 		goto unlock;
 
-	clear_bit(MLX5E_STATE_OPENED, &priv->state);
+	clear_bit(MLX5E_STATE_OPENED, &epriv->state);
 
-	mlx5e_timestamp_cleanup(priv);
-	netif_carrier_off(priv->netdev);
-	mlx5e_deactivate_priv_channels(priv);
-	mlx5e_close_channels(&priv->channels);
+	netif_carrier_off(epriv->netdev);
+	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn);
+	mlx5i_uninit_underlay_qp(epriv);
+	mlx5e_deactivate_priv_channels(epriv);
+	mlx5e_close_channels(&epriv->channels);;
 unlock:
-	mutex_unlock(&priv->state_lock);
+	mutex_unlock(&epriv->state_lock);
 	return 0;
 }
 
@@ -492,6 +535,13 @@ static int mlx5i_xmit(struct net_device *dev, struct sk_buff *skb,
 	return mlx5i_sq_xmit(sq, skb, &mah->av, dqpn, ipriv->qkey);
 }
 
+static void mlx5i_set_pkey_index(struct net_device *netdev, int id)
+{
+	struct mlx5i_priv *ipriv = netdev_priv(netdev);
+
+	ipriv->pkey_index = (u16)id;
+}
+
 static int mlx5i_check_required_hca_cap(struct mlx5_core_dev *mdev)
 {
 	if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_IB)
@@ -510,12 +560,13 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 					  const char *name,
 					  void (*setup)(struct net_device *))
 {
-	const struct mlx5e_profile *profile = &mlx5i_nic_profile;
-	int nch = profile->max_nch(mdev);
+	const struct mlx5e_profile *profile;
 	struct net_device *netdev;
 	struct mlx5i_priv *ipriv;
 	struct mlx5e_priv *epriv;
 	struct rdma_netdev *rn;
+	bool sub_interface;
+	int nch;
 	int err;
 
 	if (mlx5i_check_required_hca_cap(mdev)) {
@@ -523,10 +574,15 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 		return ERR_PTR(-EOPNOTSUPP);
 	}
 
-	/* This function should only be called once per mdev */
-	err = mlx5e_create_mdev_resources(mdev);
-	if (err)
-		return NULL;
+	/* TODO: Need to find a better way to check if child device*/
+	sub_interface = (mdev->mlx5e_res.pdn != 0);
+
+	if (sub_interface)
+		profile = mlx5i_pkey_get_profile();
+	else
+		profile = &mlx5i_nic_profile;
+
+	nch = profile->max_nch(mdev);
 
 	netdev = alloc_netdev_mqs(sizeof(struct mlx5i_priv) + sizeof(struct mlx5e_priv),
 				  name, NET_NAME_UNKNOWN,
@@ -535,7 +591,7 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 				  nch);
 	if (!netdev) {
 		mlx5_core_warn(mdev, "alloc_netdev_mqs failed\n");
-		goto free_mdev_resources;
+		return NULL;
 	}
 
 	ipriv = netdev_priv(netdev);
@@ -545,6 +601,20 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 	if (!epriv->wq)
 		goto err_free_netdev;
 
+	ipriv->sub_interface = sub_interface;
+	if (!ipriv->sub_interface) {
+		err = mlx5i_pkey_qpn_ht_init(netdev);
+		if (err) {
+			mlx5_core_warn(mdev, "allocate qpn_to_netdev ht failed\n");
+			goto destroy_wq;
+		}
+
+		/* This should only be called once per mdev */
+		err = mlx5e_create_mdev_resources(mdev);
+		if (err)
+			goto destroy_ht;
+	}
+
 	profile->init(mdev, netdev, profile, ipriv);
 
 	mlx5e_attach_netdev(epriv);
@@ -556,13 +626,16 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 	rn->send = mlx5i_xmit;
 	rn->attach_mcast = mlx5i_attach_mcast;
 	rn->detach_mcast = mlx5i_detach_mcast;
+	rn->set_id = mlx5i_set_pkey_index;
 
 	return netdev;
 
+destroy_ht:
+	mlx5i_pkey_qpn_ht_cleanup(netdev);
+destroy_wq:
+	destroy_workqueue(epriv->wq);
 err_free_netdev:
 	free_netdev(netdev);
-free_mdev_resources:
-	mlx5e_destroy_mdev_resources(mdev);
 
 	return NULL;
 }
@@ -570,15 +643,18 @@ EXPORT_SYMBOL(mlx5_rdma_netdev_alloc);
 
 void mlx5_rdma_netdev_free(struct net_device *netdev)
 {
-	struct mlx5e_priv          *priv    = mlx5i_epriv(netdev);
+	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+	struct mlx5i_priv *ipriv = priv->ppriv;
 	const struct mlx5e_profile *profile = priv->profile;
-	struct mlx5_core_dev       *mdev    = priv->mdev;
 
 	mlx5e_detach_netdev(priv);
 	profile->cleanup(priv);
 	destroy_workqueue(priv->wq);
-	free_netdev(netdev);
 
-	mlx5e_destroy_mdev_resources(mdev);
+	if (!ipriv->sub_interface) {
+		mlx5i_pkey_qpn_ht_cleanup(netdev);
+		mlx5e_destroy_mdev_resources(priv->mdev);
+	}
+	free_netdev(netdev);
 }
 EXPORT_SYMBOL(mlx5_rdma_netdev_free);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
index a0f405f520f7..49008022c306 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
@@ -39,6 +39,7 @@
 #define MLX5I_MAX_NUM_TC 1
 
 extern const struct ethtool_ops mlx5i_ethtool_ops;
+extern const struct ethtool_ops mlx5i_pkey_ethtool_ops;
 
 #define MLX5_IB_GRH_BYTES       40
 #define MLX5_IPOIB_ENCAP_LEN    4
@@ -49,10 +50,45 @@ extern const struct ethtool_ops mlx5i_ethtool_ops;
 struct mlx5i_priv {
 	struct rdma_netdev rn; /* keep this first */
 	struct mlx5_core_qp qp;
+	bool   sub_interface;
 	u32    qkey;
+	u16    pkey_index;
+	struct mlx5i_pkey_qpn_ht *qpn_htbl;
 	char  *mlx5e_priv[0];
 };
 
+/* Underlay QP create/destroy functions */
+int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp);
+void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp);
+
+/* Underlay QP state modification init/uninit functions */
+int mlx5i_init_underlay_qp(struct mlx5e_priv *priv);
+void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv);
+
+/* Allocate/Free underlay QPN to net-device hash table */
+int mlx5i_pkey_qpn_ht_init(struct net_device *netdev);
+void mlx5i_pkey_qpn_ht_cleanup(struct net_device *netdev);
+
+/* Add/Remove an underlay QPN to net-device mapping to/from the hash table */
+int mlx5i_pkey_add_qpn(struct net_device *netdev, u32 qpn);
+int mlx5i_pkey_del_qpn(struct net_device *netdev, u32 qpn);
+
+/* Get the net-device corresponding to the given underlay QPN */
+struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn);
+
+/* Shared ndo functionts */
+int mlx5i_dev_init(struct net_device *dev);
+void mlx5i_dev_cleanup(struct net_device *dev);
+
+/* Parent profile functions */
+void mlx5i_init(struct mlx5_core_dev *mdev,
+		struct net_device *netdev,
+		const struct mlx5e_profile *profile,
+		void *ppriv);
+
+/* Get child interface nic profile */
+const struct mlx5e_profile *mlx5i_pkey_get_profile(void);
+
 /* Extract mlx5e_priv from IPoIB netdev */
 #define mlx5i_epriv(netdev) ((void *)(((struct mlx5i_priv *)netdev_priv(netdev))->mlx5e_priv))
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
new file mode 100644
index 000000000000..531b02cc979b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -0,0 +1,350 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/hash.h>
+#include "ipoib.h"
+
+#define MLX5I_MAX_LOG_PKEY_SUP 7
+
+struct qpn_to_netdev {
+	struct net_device *netdev;
+	struct hlist_node hlist;
+	u32 underlay_qpn;
+};
+
+struct mlx5i_pkey_qpn_ht {
+	struct hlist_head buckets[1 << MLX5I_MAX_LOG_PKEY_SUP];
+	spinlock_t ht_lock; /* Synchronise with NAPI */
+};
+
+int mlx5i_pkey_qpn_ht_init(struct net_device *netdev)
+{
+	struct mlx5i_priv *ipriv = netdev_priv(netdev);
+	struct mlx5i_pkey_qpn_ht *qpn_htbl;
+
+	qpn_htbl = kzalloc(sizeof(*qpn_htbl), GFP_KERNEL);
+	if (!qpn_htbl)
+		return -ENOMEM;
+
+	ipriv->qpn_htbl = qpn_htbl;
+	spin_lock_init(&qpn_htbl->ht_lock);
+
+	return 0;
+}
+
+void mlx5i_pkey_qpn_ht_cleanup(struct net_device *netdev)
+{
+	struct mlx5i_priv *ipriv = netdev_priv(netdev);
+
+	kfree(ipriv->qpn_htbl);
+}
+
+static struct qpn_to_netdev *mlx5i_find_qpn_to_netdev_node(struct hlist_head *buckets,
+							   u32 qpn)
+{
+	struct hlist_head *h = &buckets[hash_32(qpn, MLX5I_MAX_LOG_PKEY_SUP)];
+	struct qpn_to_netdev *node;
+
+	hlist_for_each_entry(node, h, hlist) {
+		if (node->underlay_qpn == qpn)
+			return node;
+	}
+
+	return NULL;
+}
+
+int mlx5i_pkey_add_qpn(struct net_device *netdev, u32 qpn)
+{
+	struct mlx5i_priv *ipriv = netdev_priv(netdev);
+	struct mlx5i_pkey_qpn_ht *ht = ipriv->qpn_htbl;
+	u8 key = hash_32(qpn, MLX5I_MAX_LOG_PKEY_SUP);
+	struct qpn_to_netdev *new_node;
+
+	new_node = kzalloc(sizeof(*new_node), GFP_KERNEL);
+	if (!new_node)
+		return -ENOMEM;
+
+	new_node->netdev = netdev;
+	new_node->underlay_qpn = qpn;
+	spin_lock_bh(&ht->ht_lock);
+	hlist_add_head(&new_node->hlist, &ht->buckets[key]);
+	spin_unlock_bh(&ht->ht_lock);
+
+	return 0;
+}
+
+int mlx5i_pkey_del_qpn(struct net_device *netdev, u32 qpn)
+{
+	struct mlx5e_priv *epriv = mlx5i_epriv(netdev);
+	struct mlx5i_priv *ipriv = epriv->ppriv;
+	struct mlx5i_pkey_qpn_ht *ht = ipriv->qpn_htbl;
+	struct qpn_to_netdev *node;
+
+	node = mlx5i_find_qpn_to_netdev_node(ht->buckets, qpn);
+	if (!node) {
+		mlx5_core_warn(epriv->mdev, "QPN to netdev delete from HT failed\n");
+		return -EINVAL;
+	}
+
+	spin_lock_bh(&ht->ht_lock);
+	hlist_del_init(&node->hlist);
+	spin_unlock_bh(&ht->ht_lock);
+	kfree(node);
+
+	return 0;
+}
+
+struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn)
+{
+	struct mlx5i_priv *ipriv = netdev_priv(netdev);
+	struct qpn_to_netdev *node;
+
+	node = mlx5i_find_qpn_to_netdev_node(ipriv->qpn_htbl->buckets, qpn);
+	if (!node)
+		return NULL;
+
+	return node->netdev;
+}
+
+static int mlx5i_pkey_open(struct net_device *netdev);
+static int mlx5i_pkey_close(struct net_device *netdev);
+static int mlx5i_pkey_dev_init(struct net_device *dev);
+static void mlx5i_pkey_dev_cleanup(struct net_device *netdev);
+static int mlx5i_pkey_change_mtu(struct net_device *netdev, int new_mtu);
+
+static const struct net_device_ops mlx5i_pkey_netdev_ops = {
+	.ndo_open                = mlx5i_pkey_open,
+	.ndo_stop                = mlx5i_pkey_close,
+	.ndo_init                = mlx5i_pkey_dev_init,
+	.ndo_uninit              = mlx5i_pkey_dev_cleanup,
+	.ndo_change_mtu          = mlx5i_pkey_change_mtu,
+};
+
+/* Child NDOs */
+static int mlx5i_pkey_dev_init(struct net_device *dev)
+{
+	struct mlx5e_priv *priv = mlx5i_epriv(dev);
+	struct mlx5i_priv *ipriv, *parent_ipriv;
+	struct net_device *parent_dev;
+	int parent_ifindex;
+
+	ipriv = priv->ppriv;
+
+	/* Get QPN to netdevice hash table from parent */
+	parent_ifindex = dev->netdev_ops->ndo_get_iflink(dev);
+	parent_dev = dev_get_by_index(dev_net(dev), parent_ifindex);
+	if (!parent_dev) {
+		mlx5_core_warn(priv->mdev, "failed to get parent device\n");
+		return -EINVAL;
+	}
+
+	parent_ipriv = netdev_priv(parent_dev);
+	ipriv->qpn_htbl = parent_ipriv->qpn_htbl;
+	dev_put(parent_dev);
+
+	return mlx5i_dev_init(dev);
+}
+
+static void mlx5i_pkey_dev_cleanup(struct net_device *netdev)
+{
+	return mlx5i_dev_cleanup(netdev);
+}
+
+static int mlx5i_pkey_open(struct net_device *netdev)
+{
+	struct mlx5e_priv *epriv = mlx5i_epriv(netdev);
+	struct mlx5i_priv *ipriv = epriv->ppriv;
+	struct mlx5_core_dev *mdev = epriv->mdev;
+	int err;
+
+	mutex_lock(&epriv->state_lock);
+
+	set_bit(MLX5E_STATE_OPENED, &epriv->state);
+
+	err = mlx5i_init_underlay_qp(epriv);
+	if (err) {
+		mlx5_core_warn(mdev, "prepare child underlay qp state failed, %d\n", err);
+		goto err_release_lock;
+	}
+
+	err = mlx5_fs_add_rx_underlay_qpn(mdev, ipriv->qp.qpn);
+	if (err) {
+		mlx5_core_warn(mdev, "attach child underlay qp to ft failed, %d\n", err);
+		goto err_unint_underlay_qp;
+	}
+
+	err = mlx5e_create_tis(mdev, 0 /* tc */, ipriv->qp.qpn, &epriv->tisn[0]);
+	if (err) {
+		mlx5_core_warn(mdev, "create child tis failed, %d\n", err);
+		goto err_remove_rx_uderlay_qp;
+	}
+
+	err = mlx5e_open_channels(epriv, &epriv->channels);
+	if (err) {
+		mlx5_core_warn(mdev, "opening child channels failed, %d\n", err);
+		goto err_clear_state_opened_flag;
+	}
+	mlx5e_refresh_tirs(epriv, false);
+	mlx5e_activate_priv_channels(epriv);
+	mutex_unlock(&epriv->state_lock);
+
+	return 0;
+
+err_clear_state_opened_flag:
+	mlx5e_destroy_tis(mdev, epriv->tisn[0]);
+err_remove_rx_uderlay_qp:
+	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn);
+err_unint_underlay_qp:
+	mlx5i_uninit_underlay_qp(epriv);
+err_release_lock:
+	clear_bit(MLX5E_STATE_OPENED, &epriv->state);
+	mutex_unlock(&epriv->state_lock);
+	return err;
+}
+
+static int mlx5i_pkey_close(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+	struct mlx5i_priv *ipriv = priv->ppriv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+
+	clear_bit(MLX5E_STATE_OPENED, &priv->state);
+
+	netif_carrier_off(priv->netdev);
+	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn);
+	mlx5i_uninit_underlay_qp(priv);
+	mlx5e_deactivate_priv_channels(priv);
+	mlx5e_close_channels(&priv->channels);
+	mlx5e_destroy_tis(mdev, priv->tisn[0]);
+unlock:
+	mutex_unlock(&priv->state_lock);
+	return 0;
+}
+
+static int mlx5i_pkey_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+
+	mutex_lock(&priv->state_lock);
+	netdev->mtu = new_mtu;
+	mutex_unlock(&priv->state_lock);
+
+	return 0;
+}
+
+/* Called directly after IPoIB netdevice was created to initialize SW structs */
+static void mlx5i_pkey_init(struct mlx5_core_dev *mdev,
+			     struct net_device *netdev,
+			     const struct mlx5e_profile *profile,
+			     void *ppriv)
+{
+	struct mlx5e_priv *priv  = mlx5i_epriv(netdev);
+
+	mlx5i_init(mdev, netdev, profile, ppriv);
+
+	/* Override parent ndo */
+	netdev->netdev_ops = &mlx5i_pkey_netdev_ops;
+
+	/* Set child limited ethtool support */
+	netdev->ethtool_ops = &mlx5i_pkey_ethtool_ops;
+
+	/* Use dummy rqs */
+	priv->channels.params.log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
+}
+
+/* Called directly before IPoIB netdevice is destroyed to cleanup SW structs */
+static void mlx5i_pkey_cleanup(struct mlx5e_priv *priv)
+{
+	/* Do nothing .. */
+}
+
+static int mlx5i_pkey_init_tx(struct mlx5e_priv *priv)
+{
+	struct mlx5i_priv *ipriv = priv->ppriv;
+	int err;
+
+	err = mlx5i_create_underlay_qp(priv->mdev, &ipriv->qp);
+	if (err) {
+		mlx5_core_warn(priv->mdev, "create child underlay QP failed, %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void mlx5i_pkey_cleanup_tx(struct mlx5e_priv *priv)
+{
+	struct mlx5i_priv *ipriv = priv->ppriv;
+
+	mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp);
+}
+
+static int mlx5i_pkey_init_rx(struct mlx5e_priv *priv)
+{
+	/* Since the rx resources are shared between child and parent, the
+	 * parent interface is taking care of rx resource allocation and init
+	 */
+	return 0;
+}
+
+static void mlx5i_pkey_cleanup_rx(struct mlx5e_priv *priv)
+{
+	/* Since the rx resources are shared between child and parent, the
+	 * parent interface is taking care of rx resource free and de-init
+	 */
+}
+
+static const struct mlx5e_profile mlx5i_pkey_nic_profile = {
+	.init		   = mlx5i_pkey_init,
+	.cleanup	   = mlx5i_pkey_cleanup,
+	.init_tx	   = mlx5i_pkey_init_tx,
+	.cleanup_tx	   = mlx5i_pkey_cleanup_tx,
+	.init_rx	   = mlx5i_pkey_init_rx,
+	.cleanup_rx	   = mlx5i_pkey_cleanup_rx,
+	.enable		   = NULL,
+	.disable	   = NULL,
+	.update_stats	   = NULL,
+	.max_nch	   = mlx5e_get_max_num_channels,
+	.rx_handlers.handle_rx_cqe       = mlx5i_handle_rx_cqe,
+	.rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */
+	.max_tc		   = MLX5I_MAX_NUM_TC,
+};
+
+const struct mlx5e_profile *mlx5i_pkey_get_profile(void)
+{
+	return &mlx5i_pkey_nic_profile;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
new file mode 100644
index 000000000000..fa8aed62b231
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -0,0 +1,525 @@
+/*
+ * Copyright (c) 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.
+ */
+
+#include <linux/clocksource.h>
+#include "en.h"
+
+enum {
+	MLX5_CYCLES_SHIFT	= 23
+};
+
+enum {
+	MLX5_PIN_MODE_IN		= 0x0,
+	MLX5_PIN_MODE_OUT		= 0x1,
+};
+
+enum {
+	MLX5_OUT_PATTERN_PULSE		= 0x0,
+	MLX5_OUT_PATTERN_PERIODIC	= 0x1,
+};
+
+enum {
+	MLX5_EVENT_MODE_DISABLE	= 0x0,
+	MLX5_EVENT_MODE_REPETETIVE	= 0x1,
+	MLX5_EVENT_MODE_ONCE_TILL_ARM	= 0x2,
+};
+
+enum {
+	MLX5_MTPPS_FS_ENABLE			= BIT(0x0),
+	MLX5_MTPPS_FS_PATTERN			= BIT(0x2),
+	MLX5_MTPPS_FS_PIN_MODE			= BIT(0x3),
+	MLX5_MTPPS_FS_TIME_STAMP		= BIT(0x4),
+	MLX5_MTPPS_FS_OUT_PULSE_DURATION	= BIT(0x5),
+	MLX5_MTPPS_FS_ENH_OUT_PER_ADJ		= BIT(0x7),
+};
+
+static u64 read_internal_timer(const struct cyclecounter *cc)
+{
+	struct mlx5_clock *clock = container_of(cc, struct mlx5_clock, cycles);
+	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
+						  clock);
+
+	return mlx5_read_internal_timer(mdev) & cc->mask;
+}
+
+static void mlx5_pps_out(struct work_struct *work)
+{
+	struct mlx5_pps *pps_info = container_of(work, struct mlx5_pps,
+						 out_work);
+	struct mlx5_clock *clock = container_of(pps_info, struct mlx5_clock,
+						pps_info);
+	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
+						  clock);
+	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < clock->ptp_info.n_pins; i++) {
+		u64 tstart;
+
+		write_lock_irqsave(&clock->lock, flags);
+		tstart = clock->pps_info.start[i];
+		clock->pps_info.start[i] = 0;
+		write_unlock_irqrestore(&clock->lock, flags);
+		if (!tstart)
+			continue;
+
+		MLX5_SET(mtpps_reg, in, pin, i);
+		MLX5_SET64(mtpps_reg, in, time_stamp, tstart);
+		MLX5_SET(mtpps_reg, in, field_select, MLX5_MTPPS_FS_TIME_STAMP);
+		mlx5_set_mtpps(mdev, in, sizeof(in));
+	}
+}
+
+static void mlx5_timestamp_overflow(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct mlx5_clock *clock = container_of(dwork, struct mlx5_clock,
+						overflow_work);
+	unsigned long flags;
+
+	write_lock_irqsave(&clock->lock, flags);
+	timecounter_read(&clock->tc);
+	write_unlock_irqrestore(&clock->lock, flags);
+	schedule_delayed_work(&clock->overflow_work, clock->overflow_period);
+}
+
+static int mlx5_ptp_settime(struct ptp_clock_info *ptp,
+			    const struct timespec64 *ts)
+{
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
+						 ptp_info);
+	u64 ns = timespec64_to_ns(ts);
+	unsigned long flags;
+
+	write_lock_irqsave(&clock->lock, flags);
+	timecounter_init(&clock->tc, &clock->cycles, ns);
+	write_unlock_irqrestore(&clock->lock, flags);
+
+	return 0;
+}
+
+static int mlx5_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+{
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
+						ptp_info);
+	u64 ns;
+	unsigned long flags;
+
+	write_lock_irqsave(&clock->lock, flags);
+	ns = timecounter_read(&clock->tc);
+	write_unlock_irqrestore(&clock->lock, flags);
+
+	*ts = ns_to_timespec64(ns);
+
+	return 0;
+}
+
+static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
+						ptp_info);
+	unsigned long flags;
+
+	write_lock_irqsave(&clock->lock, flags);
+	timecounter_adjtime(&clock->tc, delta);
+	write_unlock_irqrestore(&clock->lock, flags);
+
+	return 0;
+}
+
+static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
+{
+	u64 adj;
+	u32 diff;
+	unsigned long flags;
+	int neg_adj = 0;
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
+						ptp_info);
+
+	if (delta < 0) {
+		neg_adj = 1;
+		delta = -delta;
+	}
+
+	adj = clock->nominal_c_mult;
+	adj *= delta;
+	diff = div_u64(adj, 1000000000ULL);
+
+	write_lock_irqsave(&clock->lock, flags);
+	timecounter_read(&clock->tc);
+	clock->cycles.mult = neg_adj ? clock->nominal_c_mult - diff :
+				       clock->nominal_c_mult + diff;
+	write_unlock_irqrestore(&clock->lock, flags);
+
+	return 0;
+}
+
+static int mlx5_extts_configure(struct ptp_clock_info *ptp,
+				struct ptp_clock_request *rq,
+				int on)
+{
+	struct mlx5_clock *clock =
+			container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev =
+			container_of(clock, struct mlx5_core_dev, clock);
+	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	u32 field_select = 0;
+	u8 pin_mode = 0;
+	u8 pattern = 0;
+	int pin = -1;
+	int err = 0;
+
+	if (!MLX5_PPS_CAP(mdev))
+		return -EOPNOTSUPP;
+
+	if (rq->extts.index >= clock->ptp_info.n_pins)
+		return -EINVAL;
+
+	if (on) {
+		pin = ptp_find_pin(clock->ptp, PTP_PF_EXTTS, rq->extts.index);
+		if (pin < 0)
+			return -EBUSY;
+		pin_mode = MLX5_PIN_MODE_IN;
+		pattern = !!(rq->extts.flags & PTP_FALLING_EDGE);
+		field_select = MLX5_MTPPS_FS_PIN_MODE |
+			       MLX5_MTPPS_FS_PATTERN |
+			       MLX5_MTPPS_FS_ENABLE;
+	} else {
+		pin = rq->extts.index;
+		field_select = MLX5_MTPPS_FS_ENABLE;
+	}
+
+	MLX5_SET(mtpps_reg, in, pin, pin);
+	MLX5_SET(mtpps_reg, in, pin_mode, pin_mode);
+	MLX5_SET(mtpps_reg, in, pattern, pattern);
+	MLX5_SET(mtpps_reg, in, enable, on);
+	MLX5_SET(mtpps_reg, in, field_select, field_select);
+
+	err = mlx5_set_mtpps(mdev, in, sizeof(in));
+	if (err)
+		return err;
+
+	return mlx5_set_mtppse(mdev, pin, 0,
+			       MLX5_EVENT_MODE_REPETETIVE & on);
+}
+
+static int mlx5_perout_configure(struct ptp_clock_info *ptp,
+				 struct ptp_clock_request *rq,
+				 int on)
+{
+	struct mlx5_clock *clock =
+			container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev =
+			container_of(clock, struct mlx5_core_dev, clock);
+	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	u64 nsec_now, nsec_delta, time_stamp = 0;
+	u64 cycles_now, cycles_delta;
+	struct timespec64 ts;
+	unsigned long flags;
+	u32 field_select = 0;
+	u8 pin_mode = 0;
+	u8 pattern = 0;
+	int pin = -1;
+	int err = 0;
+	s64 ns;
+
+	if (!MLX5_PPS_CAP(mdev))
+		return -EOPNOTSUPP;
+
+	if (rq->perout.index >= clock->ptp_info.n_pins)
+		return -EINVAL;
+
+	if (on) {
+		pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT,
+				   rq->perout.index);
+		if (pin < 0)
+			return -EBUSY;
+
+		pin_mode = MLX5_PIN_MODE_OUT;
+		pattern = MLX5_OUT_PATTERN_PERIODIC;
+		ts.tv_sec = rq->perout.period.sec;
+		ts.tv_nsec = rq->perout.period.nsec;
+		ns = timespec64_to_ns(&ts);
+
+		if ((ns >> 1) != 500000000LL)
+			return -EINVAL;
+
+		ts.tv_sec = rq->perout.start.sec;
+		ts.tv_nsec = rq->perout.start.nsec;
+		ns = timespec64_to_ns(&ts);
+		cycles_now = mlx5_read_internal_timer(mdev);
+		write_lock_irqsave(&clock->lock, flags);
+		nsec_now = timecounter_cyc2time(&clock->tc, cycles_now);
+		nsec_delta = ns - nsec_now;
+		cycles_delta = div64_u64(nsec_delta << clock->cycles.shift,
+					 clock->cycles.mult);
+		write_unlock_irqrestore(&clock->lock, flags);
+		time_stamp = cycles_now + cycles_delta;
+		field_select = MLX5_MTPPS_FS_PIN_MODE |
+			       MLX5_MTPPS_FS_PATTERN |
+			       MLX5_MTPPS_FS_ENABLE |
+			       MLX5_MTPPS_FS_TIME_STAMP;
+	} else {
+		pin = rq->perout.index;
+		field_select = MLX5_MTPPS_FS_ENABLE;
+	}
+
+	MLX5_SET(mtpps_reg, in, pin, pin);
+	MLX5_SET(mtpps_reg, in, pin_mode, pin_mode);
+	MLX5_SET(mtpps_reg, in, pattern, pattern);
+	MLX5_SET(mtpps_reg, in, enable, on);
+	MLX5_SET64(mtpps_reg, in, time_stamp, time_stamp);
+	MLX5_SET(mtpps_reg, in, field_select, field_select);
+
+	err = mlx5_set_mtpps(mdev, in, sizeof(in));
+	if (err)
+		return err;
+
+	return mlx5_set_mtppse(mdev, pin, 0,
+			       MLX5_EVENT_MODE_REPETETIVE & on);
+}
+
+static int mlx5_pps_configure(struct ptp_clock_info *ptp,
+			      struct ptp_clock_request *rq,
+			      int on)
+{
+	struct mlx5_clock *clock =
+			container_of(ptp, struct mlx5_clock, ptp_info);
+
+	clock->pps_info.enabled = !!on;
+	return 0;
+}
+
+static int mlx5_ptp_enable(struct ptp_clock_info *ptp,
+			   struct ptp_clock_request *rq,
+			   int on)
+{
+	switch (rq->type) {
+	case PTP_CLK_REQ_EXTTS:
+		return mlx5_extts_configure(ptp, rq, on);
+	case PTP_CLK_REQ_PEROUT:
+		return mlx5_perout_configure(ptp, rq, on);
+	case PTP_CLK_REQ_PPS:
+		return mlx5_pps_configure(ptp, rq, on);
+	default:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
+			   enum ptp_pin_function func, unsigned int chan)
+{
+	return (func == PTP_PF_PHYSYNC) ? -EOPNOTSUPP : 0;
+}
+
+static const struct ptp_clock_info mlx5_ptp_clock_info = {
+	.owner		= THIS_MODULE,
+	.name		= "mlx5_p2p",
+	.max_adj	= 100000000,
+	.n_alarm	= 0,
+	.n_ext_ts	= 0,
+	.n_per_out	= 0,
+	.n_pins		= 0,
+	.pps		= 0,
+	.adjfreq	= mlx5_ptp_adjfreq,
+	.adjtime	= mlx5_ptp_adjtime,
+	.gettime64	= mlx5_ptp_gettime,
+	.settime64	= mlx5_ptp_settime,
+	.enable		= NULL,
+	.verify		= NULL,
+};
+
+static int mlx5_init_pin_config(struct mlx5_clock *clock)
+{
+	int i;
+
+	clock->ptp_info.pin_config =
+			kzalloc(sizeof(*clock->ptp_info.pin_config) *
+				clock->ptp_info.n_pins, GFP_KERNEL);
+	if (!clock->ptp_info.pin_config)
+		return -ENOMEM;
+	clock->ptp_info.enable = mlx5_ptp_enable;
+	clock->ptp_info.verify = mlx5_ptp_verify;
+	clock->ptp_info.pps = 1;
+
+	for (i = 0; i < clock->ptp_info.n_pins; i++) {
+		snprintf(clock->ptp_info.pin_config[i].name,
+			 sizeof(clock->ptp_info.pin_config[i].name),
+			 "mlx5_pps%d", i);
+		clock->ptp_info.pin_config[i].index = i;
+		clock->ptp_info.pin_config[i].func = PTP_PF_NONE;
+		clock->ptp_info.pin_config[i].chan = i;
+	}
+
+	return 0;
+}
+
+static void mlx5_get_pps_caps(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock *clock = &mdev->clock;
+	u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+
+	mlx5_query_mtpps(mdev, out, sizeof(out));
+
+	clock->ptp_info.n_pins = MLX5_GET(mtpps_reg, out,
+					  cap_number_of_pps_pins);
+	clock->ptp_info.n_ext_ts = MLX5_GET(mtpps_reg, out,
+					    cap_max_num_of_pps_in_pins);
+	clock->ptp_info.n_per_out = MLX5_GET(mtpps_reg, out,
+					     cap_max_num_of_pps_out_pins);
+
+	clock->pps_info.pin_caps[0] = MLX5_GET(mtpps_reg, out, cap_pin_0_mode);
+	clock->pps_info.pin_caps[1] = MLX5_GET(mtpps_reg, out, cap_pin_1_mode);
+	clock->pps_info.pin_caps[2] = MLX5_GET(mtpps_reg, out, cap_pin_2_mode);
+	clock->pps_info.pin_caps[3] = MLX5_GET(mtpps_reg, out, cap_pin_3_mode);
+	clock->pps_info.pin_caps[4] = MLX5_GET(mtpps_reg, out, cap_pin_4_mode);
+	clock->pps_info.pin_caps[5] = MLX5_GET(mtpps_reg, out, cap_pin_5_mode);
+	clock->pps_info.pin_caps[6] = MLX5_GET(mtpps_reg, out, cap_pin_6_mode);
+	clock->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode);
+}
+
+void mlx5_pps_event(struct mlx5_core_dev *mdev,
+		    struct mlx5_eqe *eqe)
+{
+	struct mlx5_clock *clock = &mdev->clock;
+	struct ptp_clock_event ptp_event;
+	struct timespec64 ts;
+	u64 nsec_now, nsec_delta;
+	u64 cycles_now, cycles_delta;
+	int pin = eqe->data.pps.pin;
+	s64 ns;
+	unsigned long flags;
+
+	switch (clock->ptp_info.pin_config[pin].func) {
+	case PTP_PF_EXTTS:
+		if (clock->pps_info.enabled) {
+			ptp_event.type = PTP_CLOCK_PPSUSR;
+			ptp_event.pps_times.ts_real = ns_to_timespec64(eqe->data.pps.time_stamp);
+		} else {
+			ptp_event.type = PTP_CLOCK_EXTTS;
+		}
+		ptp_clock_event(clock->ptp, &ptp_event);
+		break;
+	case PTP_PF_PEROUT:
+		mlx5_ptp_gettime(&clock->ptp_info, &ts);
+		cycles_now = mlx5_read_internal_timer(mdev);
+		ts.tv_sec += 1;
+		ts.tv_nsec = 0;
+		ns = timespec64_to_ns(&ts);
+		write_lock_irqsave(&clock->lock, flags);
+		nsec_now = timecounter_cyc2time(&clock->tc, cycles_now);
+		nsec_delta = ns - nsec_now;
+		cycles_delta = div64_u64(nsec_delta << clock->cycles.shift,
+					 clock->cycles.mult);
+		clock->pps_info.start[pin] = cycles_now + cycles_delta;
+		schedule_work(&clock->pps_info.out_work);
+		write_unlock_irqrestore(&clock->lock, flags);
+		break;
+	default:
+		mlx5_core_err(mdev, " Unhandled event\n");
+	}
+}
+
+void mlx5_init_clock(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock *clock = &mdev->clock;
+	u64 ns;
+	u64 frac = 0;
+	u32 dev_freq;
+
+	dev_freq = MLX5_CAP_GEN(mdev, device_frequency_khz);
+	if (!dev_freq) {
+		mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n");
+		return;
+	}
+	rwlock_init(&clock->lock);
+	clock->cycles.read = read_internal_timer;
+	clock->cycles.shift = MLX5_CYCLES_SHIFT;
+	clock->cycles.mult = clocksource_khz2mult(dev_freq,
+						  clock->cycles.shift);
+	clock->nominal_c_mult = clock->cycles.mult;
+	clock->cycles.mask = CLOCKSOURCE_MASK(41);
+
+	timecounter_init(&clock->tc, &clock->cycles,
+			 ktime_to_ns(ktime_get_real()));
+
+	/* Calculate period in seconds to call the overflow watchdog - to make
+	 * sure counter is checked at least once every wrap around.
+	 */
+	ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask,
+				 frac, &frac);
+	do_div(ns, NSEC_PER_SEC / 2 / HZ);
+	clock->overflow_period = ns;
+
+	INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out);
+	INIT_DELAYED_WORK(&clock->overflow_work, mlx5_timestamp_overflow);
+	if (clock->overflow_period)
+		schedule_delayed_work(&clock->overflow_work, 0);
+	else
+		mlx5_core_warn(mdev, "invalid overflow period, overflow_work is not scheduled\n");
+
+	/* Configure the PHC */
+	clock->ptp_info = mlx5_ptp_clock_info;
+
+	/* Initialize 1PPS data structures */
+	if (MLX5_PPS_CAP(mdev))
+		mlx5_get_pps_caps(mdev);
+	if (clock->ptp_info.n_pins)
+		mlx5_init_pin_config(clock);
+
+	clock->ptp = ptp_clock_register(&clock->ptp_info,
+					&mdev->pdev->dev);
+	if (IS_ERR(clock->ptp)) {
+		mlx5_core_warn(mdev, "ptp_clock_register failed %ld\n",
+			       PTR_ERR(clock->ptp));
+		clock->ptp = NULL;
+	}
+}
+
+void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock *clock = &mdev->clock;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	if (clock->ptp) {
+		ptp_clock_unregister(clock->ptp);
+		clock->ptp = NULL;
+	}
+
+	cancel_work_sync(&clock->pps_info.out_work);
+	cancel_delayed_work_sync(&clock->overflow_work);
+	kfree(clock->ptp_info.pin_config);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
new file mode 100644
index 000000000000..a8eecedd46c2
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -0,0 +1,51 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies, Ltd.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __LIB_CLOCK_H__
+#define __LIB_CLOCK_H__
+
+void mlx5_init_clock(struct mlx5_core_dev *mdev);
+void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
+
+static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
+						u64 timestamp)
+{
+	u64 nsec;
+
+	read_lock(&clock->lock);
+	nsec = timecounter_cyc2time(&clock->tc, timestamp);
+	read_unlock(&clock->lock);
+
+	return ns_to_ktime(nsec);
+}
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 0d2c8dcd6eae..ecbe9fad22d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -59,6 +59,7 @@
 #include "lib/mlx5.h"
 #include "fpga/core.h"
 #include "accel/ipsec.h"
+#include "lib/clock.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox Connect-IB, ConnectX-4 core driver");
@@ -889,6 +890,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 
 	mlx5_init_reserved_gids(dev);
 
+	mlx5_init_clock(dev);
+
 	err = mlx5_init_rl_table(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to init rate limiting\n");
@@ -949,6 +952,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
 	mlx5_mpfs_cleanup(dev);
 	mlx5_cleanup_rl_table(dev);
+	mlx5_cleanup_clock(dev);
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cleanup_mkey_table(dev);
 	mlx5_cleanup_srq_table(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index b7c2900b75f9..8f00de2fe283 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -93,6 +93,7 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
 		     unsigned long param);
 void mlx5_core_page_fault(struct mlx5_core_dev *dev,
 			  struct mlx5_pagefault *pfault);
+void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 9a5a1cc877b6..80f4efd3e82f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -18,7 +18,8 @@ mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_kvdl.o spectrum_acl_tcam.o \
 				   spectrum_acl.o spectrum_flower.o \
 				   spectrum_cnt.o spectrum_fid.o \
-				   spectrum_ipip.o
+				   spectrum_ipip.o spectrum_acl_flex_actions.o \
+				   spectrum_mr.o spectrum_mr_tcam.o
 mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB)	+= spectrum_dcb.o
 mlxsw_spectrum-$(CONFIG_NET_DEVLINK) += spectrum_dpipe.o
 obj-$(CONFIG_MLXSW_MINIMAL)	+= mlxsw_minimal.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 5ae110172c22..6a979a09ab72 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -399,23 +399,25 @@ u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block)
 }
 EXPORT_SYMBOL(mlxsw_afa_block_first_set_kvdl_index);
 
-void mlxsw_afa_block_continue(struct mlxsw_afa_block *block)
+int mlxsw_afa_block_continue(struct mlxsw_afa_block *block)
 {
-	if (WARN_ON(block->finished))
-		return;
+	if (block->finished)
+		return -EINVAL;
 	mlxsw_afa_set_goto_set(block->cur_set,
 			       MLXSW_AFA_SET_GOTO_BINDING_CMD_NONE, 0);
 	block->finished = true;
+	return 0;
 }
 EXPORT_SYMBOL(mlxsw_afa_block_continue);
 
-void mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id)
+int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id)
 {
-	if (WARN_ON(block->finished))
-		return;
+	if (block->finished)
+		return -EINVAL;
 	mlxsw_afa_set_goto_set(block->cur_set,
 			       MLXSW_AFA_SET_GOTO_BINDING_CMD_JUMP, group_id);
 	block->finished = true;
+	return 0;
 }
 EXPORT_SYMBOL(mlxsw_afa_block_jump);
 
@@ -674,6 +676,7 @@ enum mlxsw_afa_trapdisc_trap_action {
 MLXSW_ITEM32(afa, trapdisc, trap_action, 0x00, 24, 4);
 
 enum mlxsw_afa_trapdisc_forward_action {
+	MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD = 1,
 	MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD = 3,
 };
 
@@ -712,7 +715,7 @@ int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block)
 }
 EXPORT_SYMBOL(mlxsw_afa_block_append_drop);
 
-int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block)
+int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id)
 {
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_TRAPDISC_CODE,
@@ -722,11 +725,27 @@ int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block)
 		return -ENOBUFS;
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD,
-				MLXSW_TRAP_ID_ACL0);
+				trap_id);
 	return 0;
 }
 EXPORT_SYMBOL(mlxsw_afa_block_append_trap);
 
+int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block,
+					    u16 trap_id)
+{
+	char *act = mlxsw_afa_block_append_action(block,
+						  MLXSW_AFA_TRAPDISC_CODE,
+						  MLXSW_AFA_TRAPDISC_SIZE);
+
+	if (!act)
+		return -ENOBUFS;
+	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP,
+				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD,
+				trap_id);
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_append_trap_and_forward);
+
 /* Forwarding Action
  * -----------------
  * Forwarding Action can be used to implement Policy Based Switching (PBS)
@@ -891,3 +910,74 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid)
 	return 0;
 }
 EXPORT_SYMBOL(mlxsw_afa_block_append_fid_set);
+
+/* MC Routing Action
+ * -----------------
+ * The Multicast router action. Can be used by RMFT_V2 - Router Multicast
+ * Forwarding Table Version 2 Register.
+ */
+
+#define MLXSW_AFA_MCROUTER_CODE 0x10
+#define MLXSW_AFA_MCROUTER_SIZE 2
+
+enum mlxsw_afa_mcrouter_rpf_action {
+	MLXSW_AFA_MCROUTER_RPF_ACTION_NOP,
+	MLXSW_AFA_MCROUTER_RPF_ACTION_TRAP,
+	MLXSW_AFA_MCROUTER_RPF_ACTION_DISCARD_ERROR,
+};
+
+/* afa_mcrouter_rpf_action */
+MLXSW_ITEM32(afa, mcrouter, rpf_action, 0x00, 28, 3);
+
+/* afa_mcrouter_expected_irif */
+MLXSW_ITEM32(afa, mcrouter, expected_irif, 0x00, 0, 16);
+
+/* afa_mcrouter_min_mtu */
+MLXSW_ITEM32(afa, mcrouter, min_mtu, 0x08, 0, 16);
+
+enum mlxsw_afa_mrouter_vrmid {
+	MLXSW_AFA_MCROUTER_VRMID_INVALID,
+	MLXSW_AFA_MCROUTER_VRMID_VALID
+};
+
+/* afa_mcrouter_vrmid
+ * Valid RMID: rigr_rmid_index is used as RMID
+ */
+MLXSW_ITEM32(afa, mcrouter, vrmid, 0x0C, 31, 1);
+
+/* afa_mcrouter_rigr_rmid_index
+ * When the vrmid field is set to invalid, the field is used as pointer to
+ * Router Interface Group (RIGR) Table in the KVD linear.
+ * When the vrmid is set to valid, the field is used as RMID index, ranged
+ * from 0 to max_mid - 1. The index is to the Port Group Table.
+ */
+MLXSW_ITEM32(afa, mcrouter, rigr_rmid_index, 0x0C, 0, 24);
+
+static inline void
+mlxsw_afa_mcrouter_pack(char *payload,
+			enum mlxsw_afa_mcrouter_rpf_action rpf_action,
+			u16 expected_irif, u16 min_mtu,
+			enum mlxsw_afa_mrouter_vrmid vrmid, u32 rigr_rmid_index)
+
+{
+	mlxsw_afa_mcrouter_rpf_action_set(payload, rpf_action);
+	mlxsw_afa_mcrouter_expected_irif_set(payload, expected_irif);
+	mlxsw_afa_mcrouter_min_mtu_set(payload, min_mtu);
+	mlxsw_afa_mcrouter_vrmid_set(payload, vrmid);
+	mlxsw_afa_mcrouter_rigr_rmid_index_set(payload, rigr_rmid_index);
+}
+
+int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block,
+				    u16 expected_irif, u16 min_mtu,
+				    bool rmid_valid, u32 kvdl_index)
+{
+	char *act = mlxsw_afa_block_append_action(block,
+						  MLXSW_AFA_MCROUTER_CODE,
+						  MLXSW_AFA_MCROUTER_SIZE);
+	if (!act)
+		return -ENOBUFS;
+	mlxsw_afa_mcrouter_pack(act, MLXSW_AFA_MCROUTER_RPF_ACTION_TRAP,
+				expected_irif, min_mtu, rmid_valid, kvdl_index);
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_append_mcrouter);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index f99c341b2497..a8d3314c3a24 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -57,10 +57,12 @@ void mlxsw_afa_block_destroy(struct mlxsw_afa_block *block);
 int mlxsw_afa_block_commit(struct mlxsw_afa_block *block);
 char *mlxsw_afa_block_first_set(struct mlxsw_afa_block *block);
 u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block);
-void mlxsw_afa_block_continue(struct mlxsw_afa_block *block);
-void mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id);
+int mlxsw_afa_block_continue(struct mlxsw_afa_block *block);
+int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id);
 int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block);
-int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block);
+int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id);
+int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block,
+					    u16 trap_id);
 int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
 			       u8 local_port, bool in_port);
 int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
@@ -68,5 +70,8 @@ int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
 int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
 				   u32 counter_index);
 int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid);
+int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block,
+				    u16 expected_irif, u16 min_mtu,
+				    bool rmid_valid, u32 kvdl_index);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 5acfbe5b8b9d..5066553dd0b6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2142,15 +2142,14 @@ MLXSW_REG_DEFINE(pefa, MLXSW_REG_PEFA_ID, MLXSW_REG_PEFA_LEN);
  */
 MLXSW_ITEM32(reg, pefa, index, 0x00, 0, 24);
 
-#define MLXSW_REG_PXXX_FLEX_ACTION_SET_LEN 0xA8
+#define MLXSW_REG_FLEX_ACTION_SET_LEN 0xA8
 
 /* reg_pefa_flex_action_set
  * Action-set to perform when rule is matched.
  * Must be zero padded if action set is shorter.
  * Access: RW
  */
-MLXSW_ITEM_BUF(reg, pefa, flex_action_set, 0x08,
-	       MLXSW_REG_PXXX_FLEX_ACTION_SET_LEN);
+MLXSW_ITEM_BUF(reg, pefa, flex_action_set, 0x08, MLXSW_REG_FLEX_ACTION_SET_LEN);
 
 static inline void mlxsw_reg_pefa_pack(char *payload, u32 index,
 				       const char *flex_action_set)
@@ -2243,7 +2242,7 @@ MLXSW_ITEM_BUF(reg, ptce2, mask, 0x80,
  * Access: RW
  */
 MLXSW_ITEM_BUF(reg, ptce2, flex_action_set, 0xE0,
-	       MLXSW_REG_PXXX_FLEX_ACTION_SET_LEN);
+	       MLXSW_REG_FLEX_ACTION_SET_LEN);
 
 static inline void mlxsw_reg_ptce2_pack(char *payload, bool valid,
 					enum mlxsw_reg_ptce2_op op,
@@ -3124,6 +3123,7 @@ static inline void mlxsw_reg_pfcc_pack(char *payload, u8 local_port)
  */
 #define MLXSW_REG_PPCNT_ID 0x5008
 #define MLXSW_REG_PPCNT_LEN 0x100
+#define MLXSW_REG_PPCNT_COUNTERS_OFFSET 0x08
 
 MLXSW_REG_DEFINE(ppcnt, MLXSW_REG_PPCNT_ID, MLXSW_REG_PPCNT_LEN);
 
@@ -3201,162 +3201,171 @@ MLXSW_ITEM32(reg, ppcnt, prio_tc, 0x04, 0, 5);
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_frames_transmitted_ok,
-	     0x08 + 0x00, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x00, 0, 64);
 
 /* reg_ppcnt_a_frames_received_ok
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_frames_received_ok,
-	     0x08 + 0x08, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x08, 0, 64);
 
 /* reg_ppcnt_a_frame_check_sequence_errors
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_frame_check_sequence_errors,
-	     0x08 + 0x10, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x10, 0, 64);
 
 /* reg_ppcnt_a_alignment_errors
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_alignment_errors,
-	     0x08 + 0x18, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x18, 0, 64);
 
 /* reg_ppcnt_a_octets_transmitted_ok
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_octets_transmitted_ok,
-	     0x08 + 0x20, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x20, 0, 64);
 
 /* reg_ppcnt_a_octets_received_ok
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_octets_received_ok,
-	     0x08 + 0x28, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x28, 0, 64);
 
 /* reg_ppcnt_a_multicast_frames_xmitted_ok
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_multicast_frames_xmitted_ok,
-	     0x08 + 0x30, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x30, 0, 64);
 
 /* reg_ppcnt_a_broadcast_frames_xmitted_ok
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_broadcast_frames_xmitted_ok,
-	     0x08 + 0x38, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x38, 0, 64);
 
 /* reg_ppcnt_a_multicast_frames_received_ok
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_multicast_frames_received_ok,
-	     0x08 + 0x40, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x40, 0, 64);
 
 /* reg_ppcnt_a_broadcast_frames_received_ok
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_broadcast_frames_received_ok,
-	     0x08 + 0x48, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x48, 0, 64);
 
 /* reg_ppcnt_a_in_range_length_errors
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_in_range_length_errors,
-	     0x08 + 0x50, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x50, 0, 64);
 
 /* reg_ppcnt_a_out_of_range_length_field
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_out_of_range_length_field,
-	     0x08 + 0x58, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x58, 0, 64);
 
 /* reg_ppcnt_a_frame_too_long_errors
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_frame_too_long_errors,
-	     0x08 + 0x60, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x60, 0, 64);
 
 /* reg_ppcnt_a_symbol_error_during_carrier
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_symbol_error_during_carrier,
-	     0x08 + 0x68, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x68, 0, 64);
 
 /* reg_ppcnt_a_mac_control_frames_transmitted
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_mac_control_frames_transmitted,
-	     0x08 + 0x70, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x70, 0, 64);
 
 /* reg_ppcnt_a_mac_control_frames_received
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_mac_control_frames_received,
-	     0x08 + 0x78, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x78, 0, 64);
 
 /* reg_ppcnt_a_unsupported_opcodes_received
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_unsupported_opcodes_received,
-	     0x08 + 0x80, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x80, 0, 64);
 
 /* reg_ppcnt_a_pause_mac_ctrl_frames_received
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_received,
-	     0x08 + 0x88, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x88, 0, 64);
 
 /* reg_ppcnt_a_pause_mac_ctrl_frames_transmitted
  * Access: RO
  */
 MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_transmitted,
-	     0x08 + 0x90, 0, 64);
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x90, 0, 64);
 
 /* Ethernet Per Priority Group Counters */
 
 /* reg_ppcnt_rx_octets
  * Access: RO
  */
-MLXSW_ITEM64(reg, ppcnt, rx_octets, 0x08 + 0x00, 0, 64);
+MLXSW_ITEM64(reg, ppcnt, rx_octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x00, 0, 64);
 
 /* reg_ppcnt_rx_frames
  * Access: RO
  */
-MLXSW_ITEM64(reg, ppcnt, rx_frames, 0x08 + 0x20, 0, 64);
+MLXSW_ITEM64(reg, ppcnt, rx_frames,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x20, 0, 64);
 
 /* reg_ppcnt_tx_octets
  * Access: RO
  */
-MLXSW_ITEM64(reg, ppcnt, tx_octets, 0x08 + 0x28, 0, 64);
+MLXSW_ITEM64(reg, ppcnt, tx_octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x28, 0, 64);
 
 /* reg_ppcnt_tx_frames
  * Access: RO
  */
-MLXSW_ITEM64(reg, ppcnt, tx_frames, 0x08 + 0x48, 0, 64);
+MLXSW_ITEM64(reg, ppcnt, tx_frames,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x48, 0, 64);
 
 /* reg_ppcnt_rx_pause
  * Access: RO
  */
-MLXSW_ITEM64(reg, ppcnt, rx_pause, 0x08 + 0x50, 0, 64);
+MLXSW_ITEM64(reg, ppcnt, rx_pause,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x50, 0, 64);
 
 /* reg_ppcnt_rx_pause_duration
  * Access: RO
  */
-MLXSW_ITEM64(reg, ppcnt, rx_pause_duration, 0x08 + 0x58, 0, 64);
+MLXSW_ITEM64(reg, ppcnt, rx_pause_duration,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x58, 0, 64);
 
 /* reg_ppcnt_tx_pause
  * Access: RO
  */
-MLXSW_ITEM64(reg, ppcnt, tx_pause, 0x08 + 0x60, 0, 64);
+MLXSW_ITEM64(reg, ppcnt, tx_pause,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x60, 0, 64);
 
 /* reg_ppcnt_tx_pause_duration
  * Access: RO
  */
-MLXSW_ITEM64(reg, ppcnt, tx_pause_duration, 0x08 + 0x68, 0, 64);
+MLXSW_ITEM64(reg, ppcnt, tx_pause_duration,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x68, 0, 64);
 
 /* reg_ppcnt_rx_pause_transition
  * Access: RO
  */
-MLXSW_ITEM64(reg, ppcnt, tx_pause_transition, 0x08 + 0x70, 0, 64);
+MLXSW_ITEM64(reg, ppcnt, tx_pause_transition,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x70, 0, 64);
 
 /* Ethernet Per Traffic Group Counters */
 
@@ -3366,14 +3375,16 @@ MLXSW_ITEM64(reg, ppcnt, tx_pause_transition, 0x08 + 0x70, 0, 64);
  * The field cannot be cleared.
  * Access: RO
  */
-MLXSW_ITEM64(reg, ppcnt, tc_transmit_queue, 0x08 + 0x00, 0, 64);
+MLXSW_ITEM64(reg, ppcnt, tc_transmit_queue,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x00, 0, 64);
 
 /* reg_ppcnt_tc_no_buffer_discard_uc
  * The number of unicast packets dropped due to lack of shared
  * buffer resources.
  * Access: RO
  */
-MLXSW_ITEM64(reg, ppcnt, tc_no_buffer_discard_uc, 0x08 + 0x08, 0, 64);
+MLXSW_ITEM64(reg, ppcnt, tc_no_buffer_discard_uc,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x08, 0, 64);
 
 static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port,
 					enum mlxsw_reg_ppcnt_grp grp,
@@ -3682,12 +3693,15 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IGMP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_HOST_MISS,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_RPF,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND,
@@ -3992,6 +4006,12 @@ MLXSW_ITEM32(reg, ritr, ipv4, 0x00, 29, 1);
  */
 MLXSW_ITEM32(reg, ritr, ipv6, 0x00, 28, 1);
 
+/* reg_ritr_ipv4_mc
+ * IPv4 multicast routing enable.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ipv4_mc, 0x00, 27, 1);
+
 enum mlxsw_reg_ritr_if_type {
 	/* VLAN interface. */
 	MLXSW_REG_RITR_VLAN_IF,
@@ -4049,6 +4069,14 @@ MLXSW_ITEM32(reg, ritr, ipv4_fe, 0x04, 29, 1);
  */
 MLXSW_ITEM32(reg, ritr, ipv6_fe, 0x04, 28, 1);
 
+/* reg_ritr_ipv4_mc_fe
+ * IPv4 Multicast Forwarding Enable.
+ * When disabled, forwarding is blocked but local traffic (traps and IP to me)
+ * will be enabled.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ipv4_mc_fe, 0x04, 27, 1);
+
 /* reg_ritr_lb_en
  * Loop-back filter enable for unicast packets.
  * If the flag is set then loop-back filter for unicast packets is
@@ -4271,11 +4299,13 @@ static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
 	mlxsw_reg_ritr_enable_set(payload, enable);
 	mlxsw_reg_ritr_ipv4_set(payload, 1);
 	mlxsw_reg_ritr_ipv6_set(payload, 1);
+	mlxsw_reg_ritr_ipv4_mc_set(payload, 1);
 	mlxsw_reg_ritr_type_set(payload, type);
 	mlxsw_reg_ritr_op_set(payload, op);
 	mlxsw_reg_ritr_rif_set(payload, rif);
 	mlxsw_reg_ritr_ipv4_fe_set(payload, 1);
 	mlxsw_reg_ritr_ipv6_fe_set(payload, 1);
+	mlxsw_reg_ritr_ipv4_mc_fe_set(payload, 1);
 	mlxsw_reg_ritr_lb_en_set(payload, 1);
 	mlxsw_reg_ritr_virtual_router_set(payload, vr_id);
 	mlxsw_reg_ritr_mtu_set(payload, mtu);
@@ -4311,6 +4341,57 @@ mlxsw_reg_ritr_loopback_ipip4_pack(char *payload,
 	mlxsw_reg_ritr_loopback_ipip_usip4_set(payload, usip);
 }
 
+/* RTAR - Router TCAM Allocation Register
+ * --------------------------------------
+ * This register is used for allocation of regions in the TCAM table.
+ */
+#define MLXSW_REG_RTAR_ID 0x8004
+#define MLXSW_REG_RTAR_LEN 0x20
+
+MLXSW_REG_DEFINE(rtar, MLXSW_REG_RTAR_ID, MLXSW_REG_RTAR_LEN);
+
+enum mlxsw_reg_rtar_op {
+	MLXSW_REG_RTAR_OP_ALLOCATE,
+	MLXSW_REG_RTAR_OP_RESIZE,
+	MLXSW_REG_RTAR_OP_DEALLOCATE,
+};
+
+/* reg_rtar_op
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, rtar, op, 0x00, 28, 4);
+
+enum mlxsw_reg_rtar_key_type {
+	MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST = 1,
+	MLXSW_REG_RTAR_KEY_TYPE_IPV6_MULTICAST = 3
+};
+
+/* reg_rtar_key_type
+ * TCAM key type for the region.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, rtar, key_type, 0x00, 0, 8);
+
+/* reg_rtar_region_size
+ * TCAM region size. When allocating/resizing this is the requested
+ * size, the response is the actual size.
+ * Note: Actual size may be larger than requested.
+ * Reserved for op = Deallocate
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, rtar, region_size, 0x04, 0, 16);
+
+static inline void mlxsw_reg_rtar_pack(char *payload,
+				       enum mlxsw_reg_rtar_op op,
+				       enum mlxsw_reg_rtar_key_type key_type,
+				       u16 region_size)
+{
+	MLXSW_REG_ZERO(rtar, payload);
+	mlxsw_reg_rtar_op_set(payload, op);
+	mlxsw_reg_rtar_key_type_set(payload, key_type);
+	mlxsw_reg_rtar_region_size_set(payload, region_size);
+}
+
 /* RATR - Router Adjacency Table Register
  * --------------------------------------
  * The RATR register is used to configure the Router Adjacency (next-hop)
@@ -4480,6 +4561,27 @@ MLXSW_ITEM32(reg, ratr, ipip_ipv4_udip, 0x18, 0, 32);
  */
 MLXSW_ITEM32(reg, ratr, ipip_ipv6_ptr, 0x1C, 0, 24);
 
+enum mlxsw_reg_flow_counter_set_type {
+	/* No count */
+	MLXSW_REG_FLOW_COUNTER_SET_TYPE_NO_COUNT = 0x00,
+	/* Count packets and bytes */
+	MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03,
+	/* Count only packets */
+	MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS = 0x05,
+};
+
+/* reg_ratr_counter_set_type
+ * Counter set type for flow counters
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ratr, counter_set_type, 0x28, 24, 8);
+
+/* reg_ratr_counter_index
+ * Counter index for flow counters
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ratr, counter_index, 0x28, 0, 24);
+
 static inline void
 mlxsw_reg_ratr_pack(char *payload,
 		    enum mlxsw_reg_ratr_op op, bool valid,
@@ -4507,6 +4609,20 @@ static inline void mlxsw_reg_ratr_ipip4_entry_pack(char *payload, u32 ipv4_udip)
 	mlxsw_reg_ratr_ipip_ipv4_udip_set(payload, ipv4_udip);
 }
 
+static inline void mlxsw_reg_ratr_counter_pack(char *payload, u64 counter_index,
+					       bool counter_enable)
+{
+	enum mlxsw_reg_flow_counter_set_type set_type;
+
+	if (counter_enable)
+		set_type = MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES;
+	else
+		set_type = MLXSW_REG_FLOW_COUNTER_SET_TYPE_NO_COUNT;
+
+	mlxsw_reg_ratr_counter_index_set(payload, counter_index);
+	mlxsw_reg_ratr_counter_set_type_set(payload, set_type);
+}
+
 /* RICNT - Router Interface Counter Register
  * -----------------------------------------
  * The RICNT register retrieves per port performance counters
@@ -4630,6 +4746,65 @@ static inline void mlxsw_reg_ricnt_pack(char *payload, u32 index,
 					     MLXSW_REG_RICNT_COUNTER_SET_TYPE_BASIC);
 }
 
+/* RRCR - Router Rules Copy Register Layout
+ * ----------------------------------------
+ * This register is used for moving and copying route entry rules.
+ */
+#define MLXSW_REG_RRCR_ID 0x800F
+#define MLXSW_REG_RRCR_LEN 0x24
+
+MLXSW_REG_DEFINE(rrcr, MLXSW_REG_RRCR_ID, MLXSW_REG_RRCR_LEN);
+
+enum mlxsw_reg_rrcr_op {
+	/* Move rules */
+	MLXSW_REG_RRCR_OP_MOVE,
+	/* Copy rules */
+	MLXSW_REG_RRCR_OP_COPY,
+};
+
+/* reg_rrcr_op
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, rrcr, op, 0x00, 28, 4);
+
+/* reg_rrcr_offset
+ * Offset within the region from which to copy/move.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rrcr, offset, 0x00, 0, 16);
+
+/* reg_rrcr_size
+ * The number of rules to copy/move.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, rrcr, size, 0x04, 0, 16);
+
+/* reg_rrcr_table_id
+ * Identifier of the table on which to perform the operation. Encoding is the
+ * same as in RTAR.key_type
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rrcr, table_id, 0x10, 0, 4);
+
+/* reg_rrcr_dest_offset
+ * Offset within the region to which to copy/move
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rrcr, dest_offset, 0x20, 0, 16);
+
+static inline void mlxsw_reg_rrcr_pack(char *payload, enum mlxsw_reg_rrcr_op op,
+				       u16 offset, u16 size,
+				       enum mlxsw_reg_rtar_key_type table_id,
+				       u16 dest_offset)
+{
+	MLXSW_REG_ZERO(rrcr, payload);
+	mlxsw_reg_rrcr_op_set(payload, op);
+	mlxsw_reg_rrcr_offset_set(payload, offset);
+	mlxsw_reg_rrcr_size_set(payload, size);
+	mlxsw_reg_rrcr_table_id_set(payload, table_id);
+	mlxsw_reg_rrcr_dest_offset_set(payload, dest_offset);
+}
+
 /* RALTA - Router Algorithmic LPM Tree Allocation Register
  * -------------------------------------------------------
  * RALTA is used to allocate the LPM trees of the SHSPM method.
@@ -5169,15 +5344,6 @@ enum mlxsw_reg_rauht_trap_id {
  */
 MLXSW_ITEM32(reg, rauht, trap_id, 0x60, 0, 9);
 
-enum mlxsw_reg_flow_counter_set_type {
-	/* No count */
-	MLXSW_REG_FLOW_COUNTER_SET_TYPE_NO_COUNT = 0x00,
-	/* Count packets and bytes */
-	MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03,
-	/* Count only packets */
-	MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS = 0x05,
-};
-
 /* reg_rauht_counter_set_type
  * Counter set type for flow counters
  * Access: RW
@@ -5596,6 +5762,360 @@ mlxsw_reg_rtdp_ipip4_pack(char *payload, u16 irif,
 	mlxsw_reg_rtdp_ipip_expected_gre_key_set(payload, expected_gre_key);
 }
 
+/* RIGR-V2 - Router Interface Group Register Version 2
+ * ---------------------------------------------------
+ * The RIGR_V2 register is used to add, remove and query egress interface list
+ * of a multicast forwarding entry.
+ */
+#define MLXSW_REG_RIGR2_ID 0x8023
+#define MLXSW_REG_RIGR2_LEN 0xB0
+
+#define MLXSW_REG_RIGR2_MAX_ERIFS 32
+
+MLXSW_REG_DEFINE(rigr2, MLXSW_REG_RIGR2_ID, MLXSW_REG_RIGR2_LEN);
+
+/* reg_rigr2_rigr_index
+ * KVD Linear index.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rigr2, rigr_index, 0x04, 0, 24);
+
+/* reg_rigr2_vnext
+ * Next RIGR Index is valid.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rigr2, vnext, 0x08, 31, 1);
+
+/* reg_rigr2_next_rigr_index
+ * Next RIGR Index. The index is to the KVD linear.
+ * Reserved when vnxet = '0'.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rigr2, next_rigr_index, 0x08, 0, 24);
+
+/* reg_rigr2_vrmid
+ * RMID Index is valid.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rigr2, vrmid, 0x20, 31, 1);
+
+/* reg_rigr2_rmid_index
+ * RMID Index.
+ * Range 0 .. max_mid - 1
+ * Reserved when vrmid = '0'.
+ * The index is to the Port Group Table (PGT)
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rigr2, rmid_index, 0x20, 0, 16);
+
+/* reg_rigr2_erif_entry_v
+ * Egress Router Interface is valid.
+ * Note that low-entries must be set if high-entries are set. For
+ * example: if erif_entry[2].v is set then erif_entry[1].v and
+ * erif_entry[0].v must be set.
+ * Index can be from 0 to cap_mc_erif_list_entries-1
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, rigr2, erif_entry_v, 0x24, 31, 1, 4, 0, false);
+
+/* reg_rigr2_erif_entry_erif
+ * Egress Router Interface.
+ * Valid range is from 0 to cap_max_router_interfaces - 1
+ * Index can be from 0 to MLXSW_REG_RIGR2_MAX_ERIFS - 1
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, rigr2, erif_entry_erif, 0x24, 0, 16, 4, 0, false);
+
+static inline void mlxsw_reg_rigr2_pack(char *payload, u32 rigr_index,
+					bool vnext, u32 next_rigr_index)
+{
+	MLXSW_REG_ZERO(rigr2, payload);
+	mlxsw_reg_rigr2_rigr_index_set(payload, rigr_index);
+	mlxsw_reg_rigr2_vnext_set(payload, vnext);
+	mlxsw_reg_rigr2_next_rigr_index_set(payload, next_rigr_index);
+	mlxsw_reg_rigr2_vrmid_set(payload, 0);
+	mlxsw_reg_rigr2_rmid_index_set(payload, 0);
+}
+
+static inline void mlxsw_reg_rigr2_erif_entry_pack(char *payload, int index,
+						   bool v, u16 erif)
+{
+	mlxsw_reg_rigr2_erif_entry_v_set(payload, index, v);
+	mlxsw_reg_rigr2_erif_entry_erif_set(payload, index, erif);
+}
+
+/* RECR-V2 - Router ECMP Configuration Version 2 Register
+ * ------------------------------------------------------
+ */
+#define MLXSW_REG_RECR2_ID 0x8025
+#define MLXSW_REG_RECR2_LEN 0x38
+
+MLXSW_REG_DEFINE(recr2, MLXSW_REG_RECR2_ID, MLXSW_REG_RECR2_LEN);
+
+/* reg_recr2_pp
+ * Per-port configuration
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, recr2, pp, 0x00, 24, 1);
+
+/* reg_recr2_sh
+ * Symmetric hash
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, recr2, sh, 0x00, 8, 1);
+
+/* reg_recr2_seed
+ * Seed
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, recr2, seed, 0x08, 0, 32);
+
+enum {
+	/* Enable IPv4 fields if packet is not TCP and not UDP */
+	MLXSW_REG_RECR2_IPV4_EN_NOT_TCP_NOT_UDP	= 3,
+	/* Enable IPv4 fields if packet is TCP or UDP */
+	MLXSW_REG_RECR2_IPV4_EN_TCP_UDP		= 4,
+	/* Enable IPv6 fields if packet is not TCP and not UDP */
+	MLXSW_REG_RECR2_IPV6_EN_NOT_TCP_NOT_UDP	= 5,
+	/* Enable IPv6 fields if packet is TCP or UDP */
+	MLXSW_REG_RECR2_IPV6_EN_TCP_UDP		= 6,
+	/* Enable TCP/UDP header fields if packet is IPv4 */
+	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,
+};
+
+/* reg_recr2_outer_header_enables
+ * Bit mask where each bit enables a specific layer to be included in
+ * the hash calculation.
+ * Access: RW
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, recr2, outer_header_enables, 0x10, 0x04, 1);
+
+enum {
+	/* IPv4 Source IP */
+	MLXSW_REG_RECR2_IPV4_SIP0			= 9,
+	MLXSW_REG_RECR2_IPV4_SIP3			= 12,
+	/* IPv4 Destination IP */
+	MLXSW_REG_RECR2_IPV4_DIP0			= 13,
+	MLXSW_REG_RECR2_IPV4_DIP3			= 16,
+	/* IP Protocol */
+	MLXSW_REG_RECR2_IPV4_PROTOCOL			= 17,
+	/* IPv6 Source IP */
+	MLXSW_REG_RECR2_IPV6_SIP0_7			= 21,
+	MLXSW_REG_RECR2_IPV6_SIP8			= 29,
+	MLXSW_REG_RECR2_IPV6_SIP15			= 36,
+	/* IPv6 Destination IP */
+	MLXSW_REG_RECR2_IPV6_DIP0_7			= 37,
+	MLXSW_REG_RECR2_IPV6_DIP8			= 45,
+	MLXSW_REG_RECR2_IPV6_DIP15			= 52,
+	/* IPv6 Next Header */
+	MLXSW_REG_RECR2_IPV6_NEXT_HEADER		= 53,
+	/* IPv6 Flow Label */
+	MLXSW_REG_RECR2_IPV6_FLOW_LABEL			= 57,
+	/* TCP/UDP Source Port */
+	MLXSW_REG_RECR2_TCP_UDP_SPORT			= 74,
+	/* TCP/UDP Destination Port */
+	MLXSW_REG_RECR2_TCP_UDP_DPORT			= 75,
+};
+
+/* reg_recr2_outer_header_fields_enable
+ * Packet fields to enable for ECMP hash subject to outer_header_enable.
+ * Access: RW
+ */
+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);
+
+	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);
+}
+
+static inline void mlxsw_reg_recr2_pack(char *payload, u32 seed)
+{
+	MLXSW_REG_ZERO(recr2, payload);
+	mlxsw_reg_recr2_pp_set(payload, false);
+	mlxsw_reg_recr2_sh_set(payload, true);
+	mlxsw_reg_recr2_seed_set(payload, seed);
+}
+
+/* RMFT-V2 - Router Multicast Forwarding Table Version 2 Register
+ * --------------------------------------------------------------
+ * The RMFT_V2 register is used to configure and query the multicast table.
+ */
+#define MLXSW_REG_RMFT2_ID 0x8027
+#define MLXSW_REG_RMFT2_LEN 0x174
+
+MLXSW_REG_DEFINE(rmft2, MLXSW_REG_RMFT2_ID, MLXSW_REG_RMFT2_LEN);
+
+/* reg_rmft2_v
+ * Valid
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, v, 0x00, 31, 1);
+
+enum mlxsw_reg_rmft2_type {
+	MLXSW_REG_RMFT2_TYPE_IPV4,
+	MLXSW_REG_RMFT2_TYPE_IPV6
+};
+
+/* reg_rmft2_type
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rmft2, type, 0x00, 28, 2);
+
+enum mlxsw_sp_reg_rmft2_op {
+	/* For Write:
+	 * Write operation. Used to write a new entry to the table. All RW
+	 * fields are relevant for new entry. Activity bit is set for new
+	 * entries - Note write with v (Valid) 0 will delete the entry.
+	 * For Query:
+	 * Read operation
+	 */
+	MLXSW_REG_RMFT2_OP_READ_WRITE,
+};
+
+/* reg_rmft2_op
+ * Operation.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, rmft2, op, 0x00, 20, 2);
+
+/* reg_rmft2_a
+ * Activity. Set for new entries. Set if a packet lookup has hit on the specific
+ * entry.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, rmft2, a, 0x00, 16, 1);
+
+/* reg_rmft2_offset
+ * Offset within the multicast forwarding table to write to.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rmft2, offset, 0x00, 0, 16);
+
+/* reg_rmft2_virtual_router
+ * Virtual Router ID. Range from 0..cap_max_virtual_routers-1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, virtual_router, 0x04, 0, 16);
+
+enum mlxsw_reg_rmft2_irif_mask {
+	MLXSW_REG_RMFT2_IRIF_MASK_IGNORE,
+	MLXSW_REG_RMFT2_IRIF_MASK_COMPARE
+};
+
+/* reg_rmft2_irif_mask
+ * Ingress RIF mask.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, irif_mask, 0x08, 24, 1);
+
+/* reg_rmft2_irif
+ * Ingress RIF index.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, irif, 0x08, 0, 16);
+
+/* reg_rmft2_dip4
+ * Destination IPv4 address
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, dip4, 0x1C, 0, 32);
+
+/* reg_rmft2_dip4_mask
+ * A bit that is set directs the TCAM to compare the corresponding bit in key. A
+ * bit that is clear directs the TCAM to ignore the corresponding bit in key.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, dip4_mask, 0x2C, 0, 32);
+
+/* reg_rmft2_sip4
+ * Source IPv4 address
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, sip4, 0x3C, 0, 32);
+
+/* reg_rmft2_sip4_mask
+ * A bit that is set directs the TCAM to compare the corresponding bit in key. A
+ * bit that is clear directs the TCAM to ignore the corresponding bit in key.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, sip4_mask, 0x4C, 0, 32);
+
+/* reg_rmft2_flexible_action_set
+ * ACL action set. The only supported action types in this field and in any
+ * action-set pointed from here are as follows:
+ * 00h: ACTION_NULL
+ * 01h: ACTION_MAC_TTL, only TTL configuration is supported.
+ * 03h: ACTION_TRAP
+ * 06h: ACTION_QOS
+ * 08h: ACTION_POLICING_MONITORING
+ * 10h: ACTION_ROUTER_MC
+ * Access: RW
+ */
+MLXSW_ITEM_BUF(reg, rmft2, flexible_action_set, 0x80,
+	       MLXSW_REG_FLEX_ACTION_SET_LEN);
+
+static inline void
+mlxsw_reg_rmft2_ipv4_pack(char *payload, bool v, u16 offset, u16 virtual_router,
+			  enum mlxsw_reg_rmft2_irif_mask irif_mask, u16 irif,
+			  u32 dip4, u32 dip4_mask, u32 sip4, u32 sip4_mask,
+			  const char *flexible_action_set)
+{
+	MLXSW_REG_ZERO(rmft2, payload);
+	mlxsw_reg_rmft2_v_set(payload, v);
+	mlxsw_reg_rmft2_type_set(payload, MLXSW_REG_RMFT2_TYPE_IPV4);
+	mlxsw_reg_rmft2_op_set(payload, MLXSW_REG_RMFT2_OP_READ_WRITE);
+	mlxsw_reg_rmft2_offset_set(payload, offset);
+	mlxsw_reg_rmft2_virtual_router_set(payload, virtual_router);
+	mlxsw_reg_rmft2_irif_mask_set(payload, irif_mask);
+	mlxsw_reg_rmft2_irif_set(payload, irif);
+	mlxsw_reg_rmft2_dip4_set(payload, dip4);
+	mlxsw_reg_rmft2_dip4_mask_set(payload, dip4_mask);
+	mlxsw_reg_rmft2_sip4_set(payload, sip4);
+	mlxsw_reg_rmft2_sip4_mask_set(payload, sip4_mask);
+	if (flexible_action_set)
+		mlxsw_reg_rmft2_flexible_action_set_memcpy_to(payload,
+							      flexible_action_set);
+}
+
 /* MFCR - Management Fan Control Register
  * --------------------------------------
  * This register controls the settings of the Fan Speed PWM mechanism.
@@ -6911,9 +7431,11 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(hpkt),
 	MLXSW_REG(rgcr),
 	MLXSW_REG(ritr),
+	MLXSW_REG(rtar),
 	MLXSW_REG(ratr),
 	MLXSW_REG(rtdp),
 	MLXSW_REG(ricnt),
+	MLXSW_REG(rrcr),
 	MLXSW_REG(ralta),
 	MLXSW_REG(ralst),
 	MLXSW_REG(raltb),
@@ -6921,6 +7443,9 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(rauht),
 	MLXSW_REG(raleu),
 	MLXSW_REG(rauhtd),
+	MLXSW_REG(rigr2),
+	MLXSW_REG(recr2),
+	MLXSW_REG(rmft2),
 	MLXSW_REG(mfcr),
 	MLXSW_REG(mfsc),
 	MLXSW_REG(mfsm),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index 9556d934714b..087aad52c195 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -63,6 +63,7 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_MAX_CPU_POLICERS,
 	MLXSW_RES_ID_MAX_VRS,
 	MLXSW_RES_ID_MAX_RIFS,
+	MLXSW_RES_ID_MC_ERIF_LIST_ENTRIES,
 	MLXSW_RES_ID_MAX_LPM_TREES,
 
 	/* Internal resources.
@@ -100,6 +101,7 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_MAX_CPU_POLICERS] = 0x2A13,
 	[MLXSW_RES_ID_MAX_VRS] = 0x2C01,
 	[MLXSW_RES_ID_MAX_RIFS] = 0x2C02,
+	[MLXSW_RES_ID_MC_ERIF_LIST_ENTRIES] = 0x2C10,
 	[MLXSW_RES_ID_MAX_LPM_TREES] = 0x2C30,
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 696b99e65a5a..63e50877796b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -53,6 +53,7 @@
 #include <linux/notifier.h>
 #include <linux/dcbnl.h>
 #include <linux/inetdevice.h>
+#include <linux/netlink.h>
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_mirred.h>
@@ -69,6 +70,7 @@
 #include "txheader.h"
 #include "spectrum_cnt.h"
 #include "spectrum_dpipe.h"
+#include "spectrum_acl_flex_actions.h"
 #include "../mlxfw/mlxfw.h"
 
 #define MLXSW_FWREV_MAJOR 13
@@ -1326,16 +1328,16 @@ static void update_stats_cache(struct work_struct *work)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port =
 		container_of(work, struct mlxsw_sp_port,
-			     hw_stats.update_dw.work);
+			     periodic_hw_stats.update_dw.work);
 
 	if (!netif_carrier_ok(mlxsw_sp_port->dev))
 		goto out;
 
 	mlxsw_sp_port_get_hw_stats(mlxsw_sp_port->dev,
-				   mlxsw_sp_port->hw_stats.cache);
+				   &mlxsw_sp_port->periodic_hw_stats.stats);
 
 out:
-	mlxsw_core_schedule_dw(&mlxsw_sp_port->hw_stats.update_dw,
+	mlxsw_core_schedule_dw(&mlxsw_sp_port->periodic_hw_stats.update_dw,
 			       MLXSW_HW_STATS_UPDATE_TIME);
 }
 
@@ -1348,7 +1350,7 @@ mlxsw_sp_port_get_stats64(struct net_device *dev,
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 
-	memcpy(stats, mlxsw_sp_port->hw_stats.cache, sizeof(*stats));
+	memcpy(stats, &mlxsw_sp_port->periodic_hw_stats.stats, sizeof(*stats));
 }
 
 static int __mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -1695,17 +1697,9 @@ static void mlxsw_sp_port_del_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 }
 
 static int mlxsw_sp_setup_tc_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
-					  struct tc_cls_matchall_offload *f)
+					  struct tc_cls_matchall_offload *f,
+					  bool ingress)
 {
-	bool ingress;
-
-	if (is_classid_clsact_ingress(f->common.classid))
-		ingress = true;
-	else if (is_classid_clsact_egress(f->common.classid))
-		ingress = false;
-	else
-		return -EOPNOTSUPP;
-
 	if (f->common.chain_index)
 		return -EOPNOTSUPP;
 
@@ -1723,17 +1717,9 @@ static int mlxsw_sp_setup_tc_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 
 static int
 mlxsw_sp_setup_tc_cls_flower(struct mlxsw_sp_port *mlxsw_sp_port,
-			     struct tc_cls_flower_offload *f)
+			     struct tc_cls_flower_offload *f,
+			     bool ingress)
 {
-	bool ingress;
-
-	if (is_classid_clsact_ingress(f->common.classid))
-		ingress = true;
-	else if (is_classid_clsact_egress(f->common.classid))
-		ingress = false;
-	else
-		return -EOPNOTSUPP;
-
 	switch (f->command) {
 	case TC_CLSFLOWER_REPLACE:
 		return mlxsw_sp_flower_replace(mlxsw_sp_port, ingress, f);
@@ -1747,16 +1733,70 @@ mlxsw_sp_setup_tc_cls_flower(struct mlxsw_sp_port *mlxsw_sp_port,
 	}
 }
 
+static int mlxsw_sp_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				      void *cb_priv, bool ingress)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = cb_priv;
+
+	if (!tc_can_offload(mlxsw_sp_port->dev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSMATCHALL:
+		return mlxsw_sp_setup_tc_cls_matchall(mlxsw_sp_port, type_data,
+						      ingress);
+	case TC_SETUP_CLSFLOWER:
+		return mlxsw_sp_setup_tc_cls_flower(mlxsw_sp_port, type_data,
+						    ingress);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlxsw_sp_setup_tc_block_cb_ig(enum tc_setup_type type,
+					 void *type_data, void *cb_priv)
+{
+	return mlxsw_sp_setup_tc_block_cb(type, type_data, cb_priv, true);
+}
+
+static int mlxsw_sp_setup_tc_block_cb_eg(enum tc_setup_type type,
+					 void *type_data, void *cb_priv)
+{
+	return mlxsw_sp_setup_tc_block_cb(type, type_data, cb_priv, false);
+}
+
+static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct tc_block_offload *f)
+{
+	tc_setup_cb_t *cb;
+
+	if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		cb = mlxsw_sp_setup_tc_block_cb_ig;
+	else if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
+		cb = mlxsw_sp_setup_tc_block_cb_eg;
+	else
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block, cb, mlxsw_sp_port,
+					     mlxsw_sp_port);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, cb, mlxsw_sp_port);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int mlxsw_sp_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			     void *type_data)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 
 	switch (type) {
-	case TC_SETUP_CLSMATCHALL:
-		return mlxsw_sp_setup_tc_cls_matchall(mlxsw_sp_port, type_data);
-	case TC_SETUP_CLSFLOWER:
-		return mlxsw_sp_setup_tc_cls_flower(mlxsw_sp_port, type_data);
+	case TC_SETUP_BLOCK:
+		return mlxsw_sp_setup_tc_block(mlxsw_sp_port, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -2868,14 +2908,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		goto err_alloc_sample;
 	}
 
-	mlxsw_sp_port->hw_stats.cache =
-		kzalloc(sizeof(*mlxsw_sp_port->hw_stats.cache), GFP_KERNEL);
-
-	if (!mlxsw_sp_port->hw_stats.cache) {
-		err = -ENOMEM;
-		goto err_alloc_hw_stats;
-	}
-	INIT_DELAYED_WORK(&mlxsw_sp_port->hw_stats.update_dw,
+	INIT_DELAYED_WORK(&mlxsw_sp_port->periodic_hw_stats.update_dw,
 			  &update_stats_cache);
 
 	dev->netdev_ops = &mlxsw_sp_port_netdev_ops;
@@ -2989,7 +3022,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	mlxsw_core_port_eth_set(mlxsw_sp->core, mlxsw_sp_port->local_port,
 				mlxsw_sp_port, dev, mlxsw_sp_port->split,
 				module);
-	mlxsw_core_schedule_dw(&mlxsw_sp_port->hw_stats.update_dw, 0);
+	mlxsw_core_schedule_dw(&mlxsw_sp_port->periodic_hw_stats.update_dw, 0);
 	return 0;
 
 err_register_netdev:
@@ -3012,8 +3045,6 @@ err_dev_addr_init:
 err_port_swid_set:
 	mlxsw_sp_port_module_unmap(mlxsw_sp_port);
 err_port_module_map:
-	kfree(mlxsw_sp_port->hw_stats.cache);
-err_alloc_hw_stats:
 	kfree(mlxsw_sp_port->sample);
 err_alloc_sample:
 	free_percpu(mlxsw_sp_port->pcpu_stats);
@@ -3028,7 +3059,7 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port];
 
-	cancel_delayed_work_sync(&mlxsw_sp_port->hw_stats.update_dw);
+	cancel_delayed_work_sync(&mlxsw_sp_port->periodic_hw_stats.update_dw);
 	mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp);
 	unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
 	mlxsw_sp->ports[local_port] = NULL;
@@ -3038,7 +3069,6 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 	mlxsw_sp_port_dcb_fini(mlxsw_sp_port);
 	mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT);
 	mlxsw_sp_port_module_unmap(mlxsw_sp_port);
-	kfree(mlxsw_sp_port->hw_stats.cache);
 	kfree(mlxsw_sp_port->sample);
 	free_percpu(mlxsw_sp_port->pcpu_stats);
 	WARN_ON_ONCE(!list_empty(&mlxsw_sp_port->vlans_list));
@@ -3311,6 +3341,14 @@ static void mlxsw_sp_rx_listener_mark_func(struct sk_buff *skb, u8 local_port,
 	return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv);
 }
 
+static void mlxsw_sp_rx_listener_mr_mark_func(struct sk_buff *skb,
+					      u8 local_port, void *priv)
+{
+	skb->offload_mr_fwd_mark = 1;
+	skb->offload_fwd_mark = 1;
+	return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv);
+}
+
 static void mlxsw_sp_rx_listener_sample_func(struct sk_buff *skb, u8 local_port,
 					     void *priv)
 {
@@ -3354,6 +3392,10 @@ out:
 	MLXSW_RXL(mlxsw_sp_rx_listener_mark_func, _trap_id, _action,	\
 		_is_ctrl, SP_##_trap_group, DISCARD)
 
+#define MLXSW_SP_RXL_MR_MARK(_trap_id, _action, _trap_group, _is_ctrl)	\
+	MLXSW_RXL(mlxsw_sp_rx_listener_mr_mark_func, _trap_id, _action,	\
+		_is_ctrl, SP_##_trap_group, DISCARD)
+
 #define MLXSW_SP_EVENTL(_func, _trap_id)		\
 	MLXSW_EVENTL(_func, _trap_id, SP_EVENT)
 
@@ -3420,6 +3462,11 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 		  false, SP_IP2ME, DISCARD),
 	/* ACL trap */
 	MLXSW_SP_RXL_NO_MARK(ACL0, TRAP_TO_CPU, IP2ME, false),
+	/* Multicast Router Traps */
+	MLXSW_SP_RXL_MARK(IPV4_PIM, TRAP_TO_CPU, PIM, false),
+	MLXSW_SP_RXL_MARK(RPF, TRAP_TO_CPU, RPF, false),
+	MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),
+	MLXSW_SP_RXL_MR_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
 };
 
 static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
@@ -3445,6 +3492,8 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_RPF:
 			rate = 128;
 			burst_size = 7;
 			break;
@@ -3460,6 +3509,7 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
 			rate = 1024;
 			burst_size = 7;
 			break;
@@ -3505,6 +3555,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
 			priority = 5;
 			tc = 5;
 			break;
@@ -3521,12 +3572,14 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_RPF:
 			priority = 2;
 			tc = 2;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_HOST_MISS:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
 			priority = 1;
 			tc = 1;
 			break;
@@ -3642,6 +3695,9 @@ static int mlxsw_sp_basic_trap_groups_set(struct mlxsw_core *mlxsw_core)
 	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
 }
 
+static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
+				    unsigned long event, void *ptr);
+
 static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 			 const struct mlxsw_bus_info *mlxsw_bus_info)
 {
@@ -3663,10 +3719,16 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		return err;
 	}
 
+	err = mlxsw_sp_kvdl_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize KVDL\n");
+		return err;
+	}
+
 	err = mlxsw_sp_fids_init(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize FIDs\n");
-		return err;
+		goto err_fids_init;
 	}
 
 	err = mlxsw_sp_traps_init(mlxsw_sp);
@@ -3693,12 +3755,34 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		goto err_switchdev_init;
 	}
 
+	err = mlxsw_sp_counter_pool_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to init counter pool\n");
+		goto err_counter_pool_init;
+	}
+
+	err = mlxsw_sp_afa_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize ACL actions\n");
+		goto err_afa_init;
+	}
+
 	err = mlxsw_sp_router_init(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize router\n");
 		goto err_router_init;
 	}
 
+	/* Initialize netdevice notifier after router is initialized, so that
+	 * the event handler can use router structures.
+	 */
+	mlxsw_sp->netdevice_nb.notifier_call = mlxsw_sp_netdevice_event;
+	err = register_netdevice_notifier(&mlxsw_sp->netdevice_nb);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to register netdev notifier\n");
+		goto err_netdev_notifier;
+	}
+
 	err = mlxsw_sp_span_init(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n");
@@ -3711,12 +3795,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		goto err_acl_init;
 	}
 
-	err = mlxsw_sp_counter_pool_init(mlxsw_sp);
-	if (err) {
-		dev_err(mlxsw_sp->bus_info->dev, "Failed to init counter pool\n");
-		goto err_counter_pool_init;
-	}
-
 	err = mlxsw_sp_dpipe_init(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to init pipeline debug\n");
@@ -3734,14 +3812,18 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 err_ports_create:
 	mlxsw_sp_dpipe_fini(mlxsw_sp);
 err_dpipe_init:
-	mlxsw_sp_counter_pool_fini(mlxsw_sp);
-err_counter_pool_init:
 	mlxsw_sp_acl_fini(mlxsw_sp);
 err_acl_init:
 	mlxsw_sp_span_fini(mlxsw_sp);
 err_span_init:
+	unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb);
+err_netdev_notifier:
 	mlxsw_sp_router_fini(mlxsw_sp);
 err_router_init:
+	mlxsw_sp_afa_fini(mlxsw_sp);
+err_afa_init:
+	mlxsw_sp_counter_pool_fini(mlxsw_sp);
+err_counter_pool_init:
 	mlxsw_sp_switchdev_fini(mlxsw_sp);
 err_switchdev_init:
 	mlxsw_sp_lag_fini(mlxsw_sp);
@@ -3751,6 +3833,8 @@ err_buffers_init:
 	mlxsw_sp_traps_fini(mlxsw_sp);
 err_traps_init:
 	mlxsw_sp_fids_fini(mlxsw_sp);
+err_fids_init:
+	mlxsw_sp_kvdl_fini(mlxsw_sp);
 	return err;
 }
 
@@ -3760,15 +3844,18 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 
 	mlxsw_sp_ports_remove(mlxsw_sp);
 	mlxsw_sp_dpipe_fini(mlxsw_sp);
-	mlxsw_sp_counter_pool_fini(mlxsw_sp);
 	mlxsw_sp_acl_fini(mlxsw_sp);
 	mlxsw_sp_span_fini(mlxsw_sp);
+	unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb);
 	mlxsw_sp_router_fini(mlxsw_sp);
+	mlxsw_sp_afa_fini(mlxsw_sp);
+	mlxsw_sp_counter_pool_fini(mlxsw_sp);
 	mlxsw_sp_switchdev_fini(mlxsw_sp);
 	mlxsw_sp_lag_fini(mlxsw_sp);
 	mlxsw_sp_buffers_fini(mlxsw_sp);
 	mlxsw_sp_traps_fini(mlxsw_sp);
 	mlxsw_sp_fids_fini(mlxsw_sp);
+	mlxsw_sp_kvdl_fini(mlxsw_sp);
 }
 
 static const struct mlxsw_config_profile mlxsw_sp_config_profile = {
@@ -3791,8 +3878,8 @@ static const struct mlxsw_config_profile mlxsw_sp_config_profile = {
 	.max_pkey			= 0,
 	.used_kvd_split_data		= 1,
 	.kvd_hash_granularity		= MLXSW_SP_KVD_GRANULARITY,
-	.kvd_hash_single_parts		= 2,
-	.kvd_hash_double_parts		= 1,
+	.kvd_hash_single_parts		= 59,
+	.kvd_hash_double_parts		= 41,
 	.kvd_linear_size		= MLXSW_SP_KVD_LINEAR_SIZE,
 	.swid_config			= {
 		{
@@ -3986,14 +4073,21 @@ static int mlxsw_sp_lag_index_get(struct mlxsw_sp *mlxsw_sp,
 static bool
 mlxsw_sp_master_lag_check(struct mlxsw_sp *mlxsw_sp,
 			  struct net_device *lag_dev,
-			  struct netdev_lag_upper_info *lag_upper_info)
+			  struct netdev_lag_upper_info *lag_upper_info,
+			  struct netlink_ext_ack *extack)
 {
 	u16 lag_id;
 
-	if (mlxsw_sp_lag_index_get(mlxsw_sp, lag_dev, &lag_id) != 0)
+	if (mlxsw_sp_lag_index_get(mlxsw_sp, lag_dev, &lag_id) != 0) {
+		NL_SET_ERR_MSG(extack,
+			       "spectrum: Exceeded number of supported LAG devices");
 		return false;
-	if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH)
+	}
+	if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
+		NL_SET_ERR_MSG(extack,
+			       "spectrum: LAG device using unsupported Tx type");
 		return false;
+	}
 	return true;
 }
 
@@ -4198,6 +4292,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 {
 	struct netdev_notifier_changeupper_info *info;
 	struct mlxsw_sp_port *mlxsw_sp_port;
+	struct netlink_ext_ack *extack;
 	struct net_device *upper_dev;
 	struct mlxsw_sp *mlxsw_sp;
 	int err = 0;
@@ -4205,6 +4300,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 	mlxsw_sp_port = netdev_priv(dev);
 	mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	info = ptr;
+	extack = netdev_notifier_info_to_extack(&info->info);
 
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
@@ -4212,25 +4308,43 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 		if (!is_vlan_dev(upper_dev) &&
 		    !netif_is_lag_master(upper_dev) &&
 		    !netif_is_bridge_master(upper_dev) &&
-		    !netif_is_ovs_master(upper_dev))
+		    !netif_is_ovs_master(upper_dev)) {
+			NL_SET_ERR_MSG(extack,
+				       "spectrum: Unknown upper device type");
 			return -EINVAL;
+		}
 		if (!info->linking)
 			break;
-		if (netdev_has_any_upper_dev(upper_dev))
+		if (netdev_has_any_upper_dev(upper_dev)) {
+			NL_SET_ERR_MSG(extack,
+				       "spectrum: Enslaving a port to a device that already has an upper device is not supported");
 			return -EINVAL;
+		}
 		if (netif_is_lag_master(upper_dev) &&
 		    !mlxsw_sp_master_lag_check(mlxsw_sp, upper_dev,
-					       info->upper_info))
+					       info->upper_info, extack))
 			return -EINVAL;
-		if (netif_is_lag_master(upper_dev) && vlan_uses_dev(dev))
+		if (netif_is_lag_master(upper_dev) && vlan_uses_dev(dev)) {
+			NL_SET_ERR_MSG(extack,
+				       "spectrum: Master device is a LAG master and this device has a VLAN");
 			return -EINVAL;
+		}
 		if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) &&
-		    !netif_is_lag_master(vlan_dev_real_dev(upper_dev)))
+		    !netif_is_lag_master(vlan_dev_real_dev(upper_dev))) {
+			NL_SET_ERR_MSG(extack,
+				       "spectrum: Can not put a VLAN on a LAG port");
 			return -EINVAL;
-		if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev))
+		}
+		if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev)) {
+			NL_SET_ERR_MSG(extack,
+				       "spectrum: Master device is an OVS master and this device has a VLAN");
 			return -EINVAL;
-		if (netif_is_ovs_port(dev) && is_vlan_dev(upper_dev))
+		}
+		if (netif_is_ovs_port(dev) && is_vlan_dev(upper_dev)) {
+			NL_SET_ERR_MSG(extack,
+				       "spectrum: Can not put a VLAN on an OVS port");
 			return -EINVAL;
+		}
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
@@ -4238,7 +4352,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 			if (info->linking)
 				err = mlxsw_sp_port_bridge_join(mlxsw_sp_port,
 								lower_dev,
-								upper_dev);
+								upper_dev,
+								extack);
 			else
 				mlxsw_sp_port_bridge_leave(mlxsw_sp_port,
 							   lower_dev,
@@ -4329,18 +4444,25 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct netdev_notifier_changeupper_info *info = ptr;
+	struct netlink_ext_ack *extack;
 	struct net_device *upper_dev;
 	int err = 0;
 
+	extack = netdev_notifier_info_to_extack(&info->info);
+
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (!netif_is_bridge_master(upper_dev))
+		if (!netif_is_bridge_master(upper_dev)) {
+			NL_SET_ERR_MSG(extack, "spectrum: VLAN devices only support bridge and VRF uppers");
 			return -EINVAL;
+		}
 		if (!info->linking)
 			break;
-		if (netdev_has_any_upper_dev(upper_dev))
+		if (netdev_has_any_upper_dev(upper_dev)) {
+			NL_SET_ERR_MSG(extack, "spectrum: Enslaving a port to a device that already has an upper device is not supported");
 			return -EINVAL;
+		}
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
@@ -4348,7 +4470,8 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 			if (info->linking)
 				err = mlxsw_sp_port_bridge_join(mlxsw_sp_port,
 								vlan_dev,
-								upper_dev);
+								upper_dev,
+								extack);
 			else
 				mlxsw_sp_port_bridge_leave(mlxsw_sp_port,
 							   vlan_dev,
@@ -4411,13 +4534,21 @@ static bool mlxsw_sp_is_vrf_event(unsigned long event, void *ptr)
 	return netif_is_l3_master(info->upper_dev);
 }
 
-static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
+static int mlxsw_sp_netdevice_event(struct notifier_block *nb,
 				    unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct mlxsw_sp *mlxsw_sp;
 	int err = 0;
 
-	if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU)
+	mlxsw_sp = container_of(nb, struct mlxsw_sp, netdevice_nb);
+	if (mlxsw_sp_netdev_is_ipip_ol(mlxsw_sp, dev))
+		err = mlxsw_sp_netdevice_ipip_ol_event(mlxsw_sp, dev,
+						       event, ptr);
+	else if (mlxsw_sp_netdev_is_ipip_ul(mlxsw_sp, dev))
+		err = mlxsw_sp_netdevice_ipip_ul_event(mlxsw_sp, dev,
+						       event, ptr);
+	else if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU)
 		err = mlxsw_sp_netdevice_router_port_event(dev);
 	else if (mlxsw_sp_is_vrf_event(event, ptr))
 		err = mlxsw_sp_netdevice_vrf_event(dev, event, ptr);
@@ -4431,21 +4562,20 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
 	return notifier_from_errno(err);
 }
 
-static struct notifier_block mlxsw_sp_netdevice_nb __read_mostly = {
-	.notifier_call = mlxsw_sp_netdevice_event,
+static struct notifier_block mlxsw_sp_inetaddr_valid_nb __read_mostly = {
+	.notifier_call = mlxsw_sp_inetaddr_valid_event,
 };
 
 static struct notifier_block mlxsw_sp_inetaddr_nb __read_mostly = {
 	.notifier_call = mlxsw_sp_inetaddr_event,
-	.priority = 10,	/* Must be called before FIB notifier block */
 };
 
-static struct notifier_block mlxsw_sp_inet6addr_nb __read_mostly = {
-	.notifier_call = mlxsw_sp_inet6addr_event,
+static struct notifier_block mlxsw_sp_inet6addr_valid_nb __read_mostly = {
+	.notifier_call = mlxsw_sp_inet6addr_valid_event,
 };
 
-static struct notifier_block mlxsw_sp_router_netevent_nb __read_mostly = {
-	.notifier_call = mlxsw_sp_router_netevent_event,
+static struct notifier_block mlxsw_sp_inet6addr_nb __read_mostly = {
+	.notifier_call = mlxsw_sp_inet6addr_event,
 };
 
 static const struct pci_device_id mlxsw_sp_pci_id_table[] = {
@@ -4462,10 +4592,10 @@ static int __init mlxsw_sp_module_init(void)
 {
 	int err;
 
-	register_netdevice_notifier(&mlxsw_sp_netdevice_nb);
+	register_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb);
 	register_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
+	register_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
 	register_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
-	register_netevent_notifier(&mlxsw_sp_router_netevent_nb);
 
 	err = mlxsw_core_driver_register(&mlxsw_sp_driver);
 	if (err)
@@ -4480,10 +4610,10 @@ static int __init mlxsw_sp_module_init(void)
 err_pci_driver_register:
 	mlxsw_core_driver_unregister(&mlxsw_sp_driver);
 err_core_driver_register:
-	unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb);
 	unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
+	unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
 	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
-	unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb);
+	unregister_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb);
 	return err;
 }
 
@@ -4491,10 +4621,10 @@ static void __exit mlxsw_sp_module_exit(void)
 {
 	mlxsw_pci_driver_unregister(&mlxsw_sp_pci_driver);
 	mlxsw_core_driver_unregister(&mlxsw_sp_driver);
-	unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb);
 	unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
+	unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
 	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
-	unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb);
+	unregister_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb);
 }
 
 module_init(mlxsw_sp_module_init);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 84ce83acdc19..47dd7e06fd29 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -62,7 +62,7 @@
 
 #define MLXSW_SP_PORT_BASE_SPEED 25000	/* Mb/s */
 
-#define MLXSW_SP_KVD_LINEAR_SIZE 65536 /* entries */
+#define MLXSW_SP_KVD_LINEAR_SIZE 98304 /* entries */
 #define MLXSW_SP_KVD_GRANULARITY 128
 
 struct mlxsw_sp_port;
@@ -94,7 +94,8 @@ struct mlxsw_sp_mid {
 	unsigned char addr[ETH_ALEN];
 	u16 fid;
 	u16 mid;
-	unsigned int ref_count;
+	bool in_hw;
+	unsigned long *ports_in_mid; /* bits array */
 };
 
 enum mlxsw_sp_span_type {
@@ -138,9 +139,11 @@ struct mlxsw_sp_port_mall_tc_entry {
 struct mlxsw_sp_sb;
 struct mlxsw_sp_bridge;
 struct mlxsw_sp_router;
+struct mlxsw_sp_mr;
 struct mlxsw_sp_acl;
 struct mlxsw_sp_counter_pool;
 struct mlxsw_sp_fid_core;
+struct mlxsw_sp_kvdl;
 
 struct mlxsw_sp {
 	struct mlxsw_sp_port **ports;
@@ -152,11 +155,12 @@ struct mlxsw_sp {
 	struct mlxsw_sp_sb *sb;
 	struct mlxsw_sp_bridge *bridge;
 	struct mlxsw_sp_router *router;
+	struct mlxsw_sp_mr *mr;
+	struct mlxsw_afa *afa;
 	struct mlxsw_sp_acl *acl;
 	struct mlxsw_sp_fid_core *fid_core;
-	struct {
-		DECLARE_BITMAP(usage, MLXSW_SP_KVD_LINEAR_SIZE);
-	} kvdl;
+	struct mlxsw_sp_kvdl *kvdl;
+	struct notifier_block netdevice_nb;
 
 	struct mlxsw_sp_counter_pool *counter_pool;
 	struct {
@@ -227,9 +231,9 @@ struct mlxsw_sp_port {
 	struct list_head mall_tc_list;
 	struct {
 		#define MLXSW_HW_STATS_UPDATE_TIME HZ
-		struct rtnl_link_stats64 *cache;
+		struct rtnl_link_stats64 stats;
 		struct delayed_work update_dw;
-	} hw_stats;
+	} periodic_hw_stats;
 	struct mlxsw_sp_port_sample *sample;
 	struct list_head vlans_list;
 };
@@ -322,7 +326,8 @@ void
 mlxsw_sp_port_vlan_bridge_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port,
 			      struct net_device *brport_dev,
-			      struct net_device *br_dev);
+			      struct net_device *br_dev,
+			      struct netlink_ext_ack *extack);
 void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 				struct net_device *brport_dev,
 				struct net_device *br_dev);
@@ -380,23 +385,43 @@ static inline void mlxsw_sp_port_dcb_fini(struct mlxsw_sp_port *mlxsw_sp_port)
 /* spectrum_router.c */
 int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp);
-int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
-				   unsigned long event, void *ptr);
 int mlxsw_sp_netdevice_router_port_event(struct net_device *dev);
 int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
 			    unsigned long event, void *ptr);
+int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
+				  unsigned long event, void *ptr);
 int mlxsw_sp_inet6addr_event(struct notifier_block *unused,
 			     unsigned long event, void *ptr);
+int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused,
+				   unsigned long event, void *ptr);
 int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
 				 struct netdev_notifier_changeupper_info *info);
+bool mlxsw_sp_netdev_is_ipip_ol(const struct mlxsw_sp *mlxsw_sp,
+				const struct net_device *dev);
+bool mlxsw_sp_netdev_is_ipip_ul(const struct mlxsw_sp *mlxsw_sp,
+				const struct net_device *dev);
+int mlxsw_sp_netdevice_ipip_ol_event(struct mlxsw_sp *mlxsw_sp,
+				     struct net_device *l3_dev,
+				     unsigned long event,
+				     struct netdev_notifier_info *info);
+int
+mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp,
+				 struct net_device *l3_dev,
+				 unsigned long event,
+				 struct netdev_notifier_info *info);
 void
 mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
 
 /* spectrum_kvdl.c */
+int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
 			u32 *p_entry_index);
 void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index);
+int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
+				   unsigned int entry_count,
+				   unsigned int *p_alloc_size);
 
 struct mlxsw_sp_acl_rule_info {
 	unsigned int priority;
@@ -466,9 +491,9 @@ void mlxsw_sp_acl_rulei_keymask_buf(struct mlxsw_sp_acl_rule_info *rulei,
 				    enum mlxsw_afk_element element,
 				    const char *key_value,
 				    const char *mask_value, unsigned int len);
-void mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei);
-void mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei,
-				 u16 group_id);
+int mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei);
+int mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei,
+				u16 group_id);
 int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 4b2455e3e079..93dcd315f7d6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -52,7 +52,6 @@
 struct mlxsw_sp_acl {
 	struct mlxsw_sp *mlxsw_sp;
 	struct mlxsw_afk *afk;
-	struct mlxsw_afa *afa;
 	struct mlxsw_sp_fid *dummy_fid;
 	const struct mlxsw_sp_acl_ops *ops;
 	struct rhashtable ruleset_ht;
@@ -333,7 +332,7 @@ mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl)
 	rulei = kzalloc(sizeof(*rulei), GFP_KERNEL);
 	if (!rulei)
 		return NULL;
-	rulei->act_block = mlxsw_afa_block_create(acl->afa);
+	rulei->act_block = mlxsw_afa_block_create(acl->mlxsw_sp->afa);
 	if (IS_ERR(rulei->act_block)) {
 		err = PTR_ERR(rulei->act_block);
 		goto err_afa_block_create;
@@ -379,15 +378,15 @@ void mlxsw_sp_acl_rulei_keymask_buf(struct mlxsw_sp_acl_rule_info *rulei,
 				 key_value, mask_value, len);
 }
 
-void mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei)
+int mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei)
 {
-	mlxsw_afa_block_continue(rulei->act_block);
+	return mlxsw_afa_block_continue(rulei->act_block);
 }
 
-void mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei,
-				 u16 group_id)
+int mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei,
+				u16 group_id)
 {
-	mlxsw_afa_block_jump(rulei->act_block, group_id);
+	return mlxsw_afa_block_jump(rulei->act_block, group_id);
 }
 
 int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei)
@@ -397,7 +396,8 @@ int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei)
 
 int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei)
 {
-	return mlxsw_afa_block_append_trap(rulei->act_block);
+	return mlxsw_afa_block_append_trap(rulei->act_block,
+					   MLXSW_TRAP_ID_ACL0);
 }
 
 int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
@@ -653,85 +653,6 @@ int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
-#define MLXSW_SP_KDVL_ACT_EXT_SIZE 1
-
-static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
-				     char *enc_actions, bool is_first)
-{
-	struct mlxsw_sp *mlxsw_sp = priv;
-	char pefa_pl[MLXSW_REG_PEFA_LEN];
-	u32 kvdl_index;
-	int err;
-
-	/* The first action set of a TCAM entry is stored directly in TCAM,
-	 * not KVD linear area.
-	 */
-	if (is_first)
-		return 0;
-
-	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KDVL_ACT_EXT_SIZE,
-				  &kvdl_index);
-	if (err)
-		return err;
-	mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, enc_actions);
-	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
-	if (err)
-		goto err_pefa_write;
-	*p_kvdl_index = kvdl_index;
-	return 0;
-
-err_pefa_write:
-	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
-	return err;
-}
-
-static void mlxsw_sp_act_kvdl_set_del(void *priv, u32 kvdl_index,
-				      bool is_first)
-{
-	struct mlxsw_sp *mlxsw_sp = priv;
-
-	if (is_first)
-		return;
-	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
-}
-
-static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
-					   u8 local_port)
-{
-	struct mlxsw_sp *mlxsw_sp = priv;
-	char ppbs_pl[MLXSW_REG_PPBS_LEN];
-	u32 kvdl_index;
-	int err;
-
-	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &kvdl_index);
-	if (err)
-		return err;
-	mlxsw_reg_ppbs_pack(ppbs_pl, kvdl_index, local_port);
-	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ppbs), ppbs_pl);
-	if (err)
-		goto err_ppbs_write;
-	*p_kvdl_index = kvdl_index;
-	return 0;
-
-err_ppbs_write:
-	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
-	return err;
-}
-
-static void mlxsw_sp_act_kvdl_fwd_entry_del(void *priv, u32 kvdl_index)
-{
-	struct mlxsw_sp *mlxsw_sp = priv;
-
-	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
-}
-
-static const struct mlxsw_afa_ops mlxsw_sp_act_afa_ops = {
-	.kvdl_set_add		= mlxsw_sp_act_kvdl_set_add,
-	.kvdl_set_del		= mlxsw_sp_act_kvdl_set_del,
-	.kvdl_fwd_entry_add	= mlxsw_sp_act_kvdl_fwd_entry_add,
-	.kvdl_fwd_entry_del	= mlxsw_sp_act_kvdl_fwd_entry_del,
-};
-
 int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 {
 	const struct mlxsw_sp_acl_ops *acl_ops = &mlxsw_sp_acl_tcam_ops;
@@ -753,14 +674,6 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 		goto err_afk_create;
 	}
 
-	acl->afa = mlxsw_afa_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
-						       ACL_ACTIONS_PER_SET),
-				    &mlxsw_sp_act_afa_ops, mlxsw_sp);
-	if (IS_ERR(acl->afa)) {
-		err = PTR_ERR(acl->afa);
-		goto err_afa_create;
-	}
-
 	err = rhashtable_init(&acl->ruleset_ht,
 			      &mlxsw_sp_acl_ruleset_ht_params);
 	if (err)
@@ -792,8 +705,6 @@ err_acl_ops_init:
 err_fid_get:
 	rhashtable_destroy(&acl->ruleset_ht);
 err_rhashtable_init:
-	mlxsw_afa_destroy(acl->afa);
-err_afa_create:
 	mlxsw_afk_destroy(acl->afk);
 err_afk_create:
 	kfree(acl);
@@ -810,7 +721,6 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
 	WARN_ON(!list_empty(&acl->rules));
 	mlxsw_sp_fid_put(acl->dummy_fid);
 	rhashtable_destroy(&acl->ruleset_ht);
-	mlxsw_afa_destroy(acl->afa);
 	mlxsw_afk_destroy(acl->afk);
 	kfree(acl);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
new file mode 100644
index 000000000000..4d3340ed0291
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
@@ -0,0 +1,129 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "spectrum_acl_flex_actions.h"
+#include "core_acl_flex_actions.h"
+
+#define MLXSW_SP_KVDL_ACT_EXT_SIZE 1
+
+static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
+				     char *enc_actions, bool is_first)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+	char pefa_pl[MLXSW_REG_PEFA_LEN];
+	u32 kvdl_index;
+	int err;
+
+	/* The first action set of a TCAM entry is stored directly in TCAM,
+	 * not KVD linear area.
+	 */
+	if (is_first)
+		return 0;
+
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ACT_EXT_SIZE,
+				  &kvdl_index);
+	if (err)
+		return err;
+	mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, enc_actions);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
+	if (err)
+		goto err_pefa_write;
+	*p_kvdl_index = kvdl_index;
+	return 0;
+
+err_pefa_write:
+	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+	return err;
+}
+
+static void mlxsw_sp_act_kvdl_set_del(void *priv, u32 kvdl_index,
+				      bool is_first)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+
+	if (is_first)
+		return;
+	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+}
+
+static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
+					   u8 local_port)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+	char ppbs_pl[MLXSW_REG_PPBS_LEN];
+	u32 kvdl_index;
+	int err;
+
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &kvdl_index);
+	if (err)
+		return err;
+	mlxsw_reg_ppbs_pack(ppbs_pl, kvdl_index, local_port);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ppbs), ppbs_pl);
+	if (err)
+		goto err_ppbs_write;
+	*p_kvdl_index = kvdl_index;
+	return 0;
+
+err_ppbs_write:
+	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+	return err;
+}
+
+static void mlxsw_sp_act_kvdl_fwd_entry_del(void *priv, u32 kvdl_index)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+
+	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+}
+
+static const struct mlxsw_afa_ops mlxsw_sp_act_afa_ops = {
+	.kvdl_set_add		= mlxsw_sp_act_kvdl_set_add,
+	.kvdl_set_del		= mlxsw_sp_act_kvdl_set_del,
+	.kvdl_fwd_entry_add	= mlxsw_sp_act_kvdl_fwd_entry_add,
+	.kvdl_fwd_entry_del	= mlxsw_sp_act_kvdl_fwd_entry_del,
+};
+
+int mlxsw_sp_afa_init(struct mlxsw_sp *mlxsw_sp)
+{
+	mlxsw_sp->afa = mlxsw_afa_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
+							    ACL_ACTIONS_PER_SET),
+					 &mlxsw_sp_act_afa_ops, mlxsw_sp);
+	return PTR_ERR_OR_ZERO(mlxsw_sp->afa);
+}
+
+void mlxsw_sp_afa_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	mlxsw_afa_destroy(mlxsw_sp->afa);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
new file mode 100644
index 000000000000..2726192836ad
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
@@ -0,0 +1,44 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_SPECTRUM_ACL_FLEX_KEYS_H
+#define _MLXSW_SPECTRUM_ACL_FLEX_KEYS_H
+
+#include "spectrum.h"
+
+int mlxsw_sp_afa_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_afa_fini(struct mlxsw_sp *mlxsw_sp);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 50b40de1fb91..7e8284b46968 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -608,7 +608,10 @@ mlxsw_sp_acl_tcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
 		goto err_rulei_create;
 	}
 
-	mlxsw_sp_acl_rulei_act_continue(rulei);
+	err = mlxsw_sp_acl_rulei_act_continue(rulei);
+	if (WARN_ON(err))
+		goto err_rulei_act_continue;
+
 	err = mlxsw_sp_acl_rulei_commit(rulei);
 	if (err)
 		goto err_rulei_commit;
@@ -623,6 +626,7 @@ mlxsw_sp_acl_tcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
 
 err_rule_insert:
 err_rulei_commit:
+err_rulei_act_continue:
 	mlxsw_sp_acl_rulei_destroy(rulei);
 err_rulei_create:
 	parman_item_remove(region->parman, parman_prio, parman_item);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
index 51e6846da72b..96fdba78acab 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
@@ -43,21 +43,42 @@ enum mlxsw_sp_field_metadata_id {
 	MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT,
 	MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
 	MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
+	MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX,
+	MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_SIZE,
+	MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX,
 };
 
 static struct devlink_dpipe_field mlxsw_sp_dpipe_fields_metadata[] = {
-	{ .name = "erif_port",
-	  .id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT,
-	  .bitwidth = 32,
-	  .mapping_type = DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX,
+	{
+		.name = "erif_port",
+		.id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT,
+		.bitwidth = 32,
+		.mapping_type = DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX,
 	},
-	{ .name = "l3_forward",
-	  .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
-	  .bitwidth = 1,
+	{
+		.name = "l3_forward",
+		.id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
+		.bitwidth = 1,
 	},
-	{ .name = "l3_drop",
-	  .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
-	  .bitwidth = 1,
+	{
+		.name = "l3_drop",
+		.id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
+		.bitwidth = 1,
+	},
+	{
+		.name = "adj_index",
+		.id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX,
+		.bitwidth = 32,
+	},
+	{
+		.name = "adj_size",
+		.id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_SIZE,
+		.bitwidth = 32,
+	},
+	{
+		.name = "adj_hash_index",
+		.id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX,
+		.bitwidth = 32,
 	},
 };
 
@@ -826,6 +847,390 @@ static void mlxsw_sp_dpipe_host6_table_fini(struct mlxsw_sp *mlxsw_sp)
 				       MLXSW_SP_DPIPE_TABLE_NAME_HOST6);
 }
 
+static int mlxsw_sp_dpipe_table_adj_matches_dump(void *priv,
+						 struct sk_buff *skb)
+{
+	struct devlink_dpipe_match match = {0};
+	int err;
+
+	match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+	match.header = &mlxsw_sp_dpipe_header_metadata;
+	match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX;
+
+	err = devlink_dpipe_match_put(skb, &match);
+	if (err)
+		return err;
+
+	match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+	match.header = &mlxsw_sp_dpipe_header_metadata;
+	match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_SIZE;
+
+	err = devlink_dpipe_match_put(skb, &match);
+	if (err)
+		return err;
+
+	match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+	match.header = &mlxsw_sp_dpipe_header_metadata;
+	match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX;
+
+	return devlink_dpipe_match_put(skb, &match);
+}
+
+static int mlxsw_sp_dpipe_table_adj_actions_dump(void *priv,
+						 struct sk_buff *skb)
+{
+	struct devlink_dpipe_action action = {0};
+	int err;
+
+	action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+	action.header = &devlink_dpipe_header_ethernet;
+	action.field_id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC;
+
+	err = devlink_dpipe_action_put(skb, &action);
+	if (err)
+		return err;
+
+	action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+	action.header = &mlxsw_sp_dpipe_header_metadata;
+	action.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT;
+
+	return devlink_dpipe_action_put(skb, &action);
+}
+
+static u64 mlxsw_sp_dpipe_table_adj_size(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_nexthop *nh;
+	u64 size = 0;
+
+	mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router)
+		if (mlxsw_sp_nexthop_offload(nh) &&
+		    !mlxsw_sp_nexthop_group_has_ipip(nh))
+			size++;
+	return size;
+}
+
+enum mlxsw_sp_dpipe_table_adj_match {
+	MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX,
+	MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_SIZE,
+	MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX,
+	MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT,
+};
+
+enum mlxsw_sp_dpipe_table_adj_action {
+	MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC,
+	MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT,
+	MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT,
+};
+
+static void
+mlxsw_sp_dpipe_table_adj_match_action_prepare(struct devlink_dpipe_match *matches,
+					      struct devlink_dpipe_action *actions)
+{
+	struct devlink_dpipe_action *action;
+	struct devlink_dpipe_match *match;
+
+	match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX];
+	match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+	match->header = &mlxsw_sp_dpipe_header_metadata;
+	match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX;
+
+	match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_SIZE];
+	match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+	match->header = &mlxsw_sp_dpipe_header_metadata;
+	match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_SIZE;
+
+	match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX];
+	match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+	match->header = &mlxsw_sp_dpipe_header_metadata;
+	match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX;
+
+	action = &actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC];
+	action->type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+	action->header = &devlink_dpipe_header_ethernet;
+	action->field_id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC;
+
+	action = &actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT];
+	action->type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+	action->header = &mlxsw_sp_dpipe_header_metadata;
+	action->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT;
+}
+
+static int
+mlxsw_sp_dpipe_table_adj_entry_prepare(struct devlink_dpipe_entry *entry,
+				       struct devlink_dpipe_value *match_values,
+				       struct devlink_dpipe_match *matches,
+				       struct devlink_dpipe_value *action_values,
+				       struct devlink_dpipe_action *actions)
+{	struct devlink_dpipe_value *action_value;
+	struct devlink_dpipe_value *match_value;
+	struct devlink_dpipe_action *action;
+	struct devlink_dpipe_match *match;
+
+	entry->match_values = match_values;
+	entry->match_values_count = MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT;
+
+	entry->action_values = action_values;
+	entry->action_values_count = MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT;
+
+	match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX];
+	match_value = &match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX];
+
+	match_value->match = match;
+	match_value->value_size = sizeof(u32);
+	match_value->value = kmalloc(match_value->value_size, GFP_KERNEL);
+	if (!match_value->value)
+		return -ENOMEM;
+
+	match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_SIZE];
+	match_value = &match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_SIZE];
+
+	match_value->match = match;
+	match_value->value_size = sizeof(u32);
+	match_value->value = kmalloc(match_value->value_size, GFP_KERNEL);
+	if (!match_value->value)
+		return -ENOMEM;
+
+	match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX];
+	match_value = &match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX];
+
+	match_value->match = match;
+	match_value->value_size = sizeof(u32);
+	match_value->value = kmalloc(match_value->value_size, GFP_KERNEL);
+	if (!match_value->value)
+		return -ENOMEM;
+
+	action = &actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC];
+	action_value = &action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC];
+
+	action_value->action = action;
+	action_value->value_size = sizeof(u64);
+	action_value->value = kmalloc(action_value->value_size, GFP_KERNEL);
+	if (!action_value->value)
+		return -ENOMEM;
+
+	action = &actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT];
+	action_value = &action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT];
+
+	action_value->action = action;
+	action_value->value_size = sizeof(u32);
+	action_value->value = kmalloc(action_value->value_size, GFP_KERNEL);
+	if (!action_value->value)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void
+__mlxsw_sp_dpipe_table_adj_entry_fill(struct devlink_dpipe_entry *entry,
+				      u32 adj_index, u32 adj_size,
+				      u32 adj_hash_index, unsigned char *ha,
+				      struct mlxsw_sp_rif *rif)
+{
+	struct devlink_dpipe_value *value;
+	u32 *p_rif_value;
+	u32 *p_index;
+
+	value = &entry->match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX];
+	p_index = value->value;
+	*p_index = adj_index;
+
+	value = &entry->match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_SIZE];
+	p_index = value->value;
+	*p_index = adj_size;
+
+	value = &entry->match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX];
+	p_index = value->value;
+	*p_index = adj_hash_index;
+
+	value = &entry->action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC];
+	ether_addr_copy(value->value, ha);
+
+	value = &entry->action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT];
+	p_rif_value = value->value;
+	*p_rif_value = mlxsw_sp_rif_index(rif);
+	value->mapping_value = mlxsw_sp_rif_dev_ifindex(rif);
+	value->mapping_valid = true;
+}
+
+static void mlxsw_sp_dpipe_table_adj_entry_fill(struct mlxsw_sp *mlxsw_sp,
+						struct mlxsw_sp_nexthop *nh,
+						struct devlink_dpipe_entry *entry)
+{
+	struct mlxsw_sp_rif *rif = mlxsw_sp_nexthop_rif(nh);
+	unsigned char *ha = mlxsw_sp_nexthop_ha(nh);
+	u32 adj_hash_index = 0;
+	u32 adj_index = 0;
+	u32 adj_size = 0;
+	int err;
+
+	mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_size, &adj_hash_index);
+	__mlxsw_sp_dpipe_table_adj_entry_fill(entry, adj_index, adj_size,
+					      adj_hash_index, ha, rif);
+	err = mlxsw_sp_nexthop_counter_get(mlxsw_sp, nh, &entry->counter);
+	if (!err)
+		entry->counter_valid = true;
+}
+
+static int
+mlxsw_sp_dpipe_table_adj_entries_get(struct mlxsw_sp *mlxsw_sp,
+				     struct devlink_dpipe_entry *entry,
+				     bool counters_enabled,
+				     struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	struct mlxsw_sp_nexthop *nh;
+	int entry_index = 0;
+	int nh_count_max;
+	int nh_count = 0;
+	int nh_skip;
+	int j;
+	int err;
+
+	rtnl_lock();
+	nh_count_max = mlxsw_sp_dpipe_table_adj_size(mlxsw_sp);
+start_again:
+	err = devlink_dpipe_entry_ctx_prepare(dump_ctx);
+	if (err)
+		goto err_ctx_prepare;
+	j = 0;
+	nh_skip = nh_count;
+	nh_count = 0;
+	mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) {
+		if (!mlxsw_sp_nexthop_offload(nh) ||
+		    mlxsw_sp_nexthop_group_has_ipip(nh))
+			continue;
+
+		if (nh_count < nh_skip)
+			goto skip;
+
+		mlxsw_sp_dpipe_table_adj_entry_fill(mlxsw_sp, nh, entry);
+		entry->index = entry_index;
+		err = devlink_dpipe_entry_ctx_append(dump_ctx, entry);
+		if (err) {
+			if (err == -EMSGSIZE) {
+				if (!j)
+					goto err_entry_append;
+				break;
+			}
+			goto err_entry_append;
+		}
+		entry_index++;
+		j++;
+skip:
+		nh_count++;
+	}
+
+	devlink_dpipe_entry_ctx_close(dump_ctx);
+	if (nh_count != nh_count_max)
+		goto start_again;
+	rtnl_unlock();
+
+	return 0;
+
+err_ctx_prepare:
+err_entry_append:
+	rtnl_unlock();
+	return err;
+}
+
+static int
+mlxsw_sp_dpipe_table_adj_entries_dump(void *priv, bool counters_enabled,
+				      struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	struct devlink_dpipe_value action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT];
+	struct devlink_dpipe_value match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT];
+	struct devlink_dpipe_action actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT];
+	struct devlink_dpipe_match matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT];
+	struct devlink_dpipe_entry entry = {0};
+	struct mlxsw_sp *mlxsw_sp = priv;
+	int err;
+
+	memset(matches, 0, MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT *
+			   sizeof(matches[0]));
+	memset(match_values, 0, MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT *
+				sizeof(match_values[0]));
+	memset(actions, 0, MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT *
+			   sizeof(actions[0]));
+	memset(action_values, 0, MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT *
+				 sizeof(action_values[0]));
+
+	mlxsw_sp_dpipe_table_adj_match_action_prepare(matches, actions);
+	err = mlxsw_sp_dpipe_table_adj_entry_prepare(&entry,
+						     match_values, matches,
+						     action_values, actions);
+	if (err)
+		goto out;
+
+	err = mlxsw_sp_dpipe_table_adj_entries_get(mlxsw_sp, &entry,
+						   counters_enabled, dump_ctx);
+out:
+	devlink_dpipe_entry_clear(&entry);
+	return err;
+}
+
+static int mlxsw_sp_dpipe_table_adj_counters_update(void *priv, bool enable)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+	struct mlxsw_sp_nexthop *nh;
+	u32 adj_hash_index = 0;
+	u32 adj_index = 0;
+	u32 adj_size = 0;
+
+	mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) {
+		if (!mlxsw_sp_nexthop_offload(nh) ||
+		    mlxsw_sp_nexthop_group_has_ipip(nh))
+			continue;
+
+		mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_size,
+					 &adj_hash_index);
+		if (enable)
+			mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
+		else
+			mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
+		mlxsw_sp_nexthop_update(mlxsw_sp,
+					adj_index + adj_hash_index, nh);
+	}
+	return 0;
+}
+
+static u64
+mlxsw_sp_dpipe_table_adj_size_get(void *priv)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+	u64 size;
+
+	rtnl_lock();
+	size = mlxsw_sp_dpipe_table_adj_size(mlxsw_sp);
+	rtnl_unlock();
+
+	return size;
+}
+
+static struct devlink_dpipe_table_ops mlxsw_sp_dpipe_table_adj_ops = {
+	.matches_dump = mlxsw_sp_dpipe_table_adj_matches_dump,
+	.actions_dump = mlxsw_sp_dpipe_table_adj_actions_dump,
+	.entries_dump = mlxsw_sp_dpipe_table_adj_entries_dump,
+	.counters_set_update = mlxsw_sp_dpipe_table_adj_counters_update,
+	.size_get = mlxsw_sp_dpipe_table_adj_size_get,
+};
+
+static int mlxsw_sp_dpipe_adj_table_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+
+	return devlink_dpipe_table_register(devlink,
+					    MLXSW_SP_DPIPE_TABLE_NAME_ADJ,
+					    &mlxsw_sp_dpipe_table_adj_ops,
+					    mlxsw_sp, false);
+}
+
+static void mlxsw_sp_dpipe_adj_table_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+
+	devlink_dpipe_table_unregister(devlink,
+				       MLXSW_SP_DPIPE_TABLE_NAME_ADJ);
+}
+
 int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp)
 {
 	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
@@ -846,8 +1251,14 @@ int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp)
 	err = mlxsw_sp_dpipe_host6_table_init(mlxsw_sp);
 	if (err)
 		goto err_host6_table_init;
-	return 0;
 
+	err = mlxsw_sp_dpipe_adj_table_init(mlxsw_sp);
+	if (err)
+		goto err_adj_table_init;
+
+	return 0;
+err_adj_table_init:
+	mlxsw_sp_dpipe_host6_table_fini(mlxsw_sp);
 err_host6_table_init:
 	mlxsw_sp_dpipe_host4_table_fini(mlxsw_sp);
 err_host4_table_init:
@@ -861,6 +1272,7 @@ void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
 
+	mlxsw_sp_dpipe_adj_table_fini(mlxsw_sp);
 	mlxsw_sp_dpipe_host6_table_fini(mlxsw_sp);
 	mlxsw_sp_dpipe_host4_table_fini(mlxsw_sp);
 	mlxsw_sp_dpipe_erif_table_fini(mlxsw_sp);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
index 283fde4e6783..815d543cf114 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
@@ -56,5 +56,6 @@ static inline void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp)
 #define MLXSW_SP_DPIPE_TABLE_NAME_ERIF "mlxsw_erif"
 #define MLXSW_SP_DPIPE_TABLE_NAME_HOST4 "mlxsw_host4"
 #define MLXSW_SP_DPIPE_TABLE_NAME_HOST6 "mlxsw_host6"
+#define MLXSW_SP_DPIPE_TABLE_NAME_ADJ "mlxsw_adj"
 
 #endif /* _MLXSW_PIPELINE_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 8aace9a06a5d..2f0e57857ea4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -63,7 +63,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 
 	tcf_exts_to_list(exts, &actions);
 	list_for_each_entry(a, &actions, list) {
-		if (is_tcf_gact_shot(a)) {
+		if (is_tcf_gact_ok(a)) {
+			err = mlxsw_sp_acl_rulei_act_continue(rulei);
+			if (err)
+				return err;
+		} else if (is_tcf_gact_shot(a)) {
 			err = mlxsw_sp_acl_rulei_act_drop(rulei);
 			if (err)
 				return err;
@@ -84,7 +88,9 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 				return PTR_ERR(ruleset);
 
 			group_id = mlxsw_sp_acl_ruleset_group_id(ruleset);
-			mlxsw_sp_acl_rulei_act_jump(rulei, group_id);
+			err = mlxsw_sp_acl_rulei_act_jump(rulei, group_id);
+			if (err)
+				return err;
 		} else if (is_tcf_mirred_egress_redirect(a)) {
 			int ifindex = tcf_mirred_ifindex(a);
 			struct net_device *out_dev;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
index 702fe945227c..7502e53447bd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
@@ -36,36 +36,123 @@
 
 #include "spectrum_ipip.h"
 
-static bool
-mlxsw_sp_ipip_netdev_has_ikey(const struct net_device *ol_dev)
+struct ip_tunnel_parm
+mlxsw_sp_ipip_netdev_parms(const struct net_device *ol_dev)
 {
 	struct ip_tunnel *tun = netdev_priv(ol_dev);
 
-	return !!(tun->parms.i_flags & TUNNEL_KEY);
+	return tun->parms;
 }
 
-static bool
-mlxsw_sp_ipip_netdev_has_okey(const struct net_device *ol_dev)
+static bool mlxsw_sp_ipip_parms_has_ikey(struct ip_tunnel_parm parms)
 {
-	struct ip_tunnel *tun = netdev_priv(ol_dev);
+	return !!(parms.i_flags & TUNNEL_KEY);
+}
 
-	return !!(tun->parms.o_flags & TUNNEL_KEY);
+static bool mlxsw_sp_ipip_parms_has_okey(struct ip_tunnel_parm parms)
+{
+	return !!(parms.o_flags & TUNNEL_KEY);
 }
 
-static u32 mlxsw_sp_ipip_netdev_ikey(const struct net_device *ol_dev)
+static u32 mlxsw_sp_ipip_parms_ikey(struct ip_tunnel_parm parms)
 {
-	struct ip_tunnel *tun = netdev_priv(ol_dev);
+	return mlxsw_sp_ipip_parms_has_ikey(parms) ?
+		be32_to_cpu(parms.i_key) : 0;
+}
+
+static u32 mlxsw_sp_ipip_parms_okey(struct ip_tunnel_parm parms)
+{
+	return mlxsw_sp_ipip_parms_has_okey(parms) ?
+		be32_to_cpu(parms.o_key) : 0;
+}
 
-	return mlxsw_sp_ipip_netdev_has_ikey(ol_dev) ?
-		be32_to_cpu(tun->parms.i_key) : 0;
+static __be32 mlxsw_sp_ipip_parms_saddr4(struct ip_tunnel_parm parms)
+{
+	return parms.iph.saddr;
+}
+
+static union mlxsw_sp_l3addr
+mlxsw_sp_ipip_parms_saddr(enum mlxsw_sp_l3proto proto,
+			  struct ip_tunnel_parm parms)
+{
+	switch (proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		return (union mlxsw_sp_l3addr) {
+			.addr4 = mlxsw_sp_ipip_parms_saddr4(parms),
+		};
+	case MLXSW_SP_L3_PROTO_IPV6:
+		break;
+	}
+
+	WARN_ON(1);
+	return (union mlxsw_sp_l3addr) {
+		.addr4 = 0,
+	};
+}
+
+static __be32 mlxsw_sp_ipip_parms_daddr4(struct ip_tunnel_parm parms)
+{
+	return parms.iph.daddr;
+}
+
+static union mlxsw_sp_l3addr
+mlxsw_sp_ipip_parms_daddr(enum mlxsw_sp_l3proto proto,
+			  struct ip_tunnel_parm parms)
+{
+	switch (proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		return (union mlxsw_sp_l3addr) {
+			.addr4 = mlxsw_sp_ipip_parms_daddr4(parms),
+		};
+	case MLXSW_SP_L3_PROTO_IPV6:
+		break;
+	}
+
+	WARN_ON(1);
+	return (union mlxsw_sp_l3addr) {
+		.addr4 = 0,
+	};
+}
+
+static bool mlxsw_sp_ipip_netdev_has_ikey(const struct net_device *ol_dev)
+{
+	return mlxsw_sp_ipip_parms_has_ikey(mlxsw_sp_ipip_netdev_parms(ol_dev));
+}
+
+static bool mlxsw_sp_ipip_netdev_has_okey(const struct net_device *ol_dev)
+{
+	return mlxsw_sp_ipip_parms_has_okey(mlxsw_sp_ipip_netdev_parms(ol_dev));
+}
+
+static u32 mlxsw_sp_ipip_netdev_ikey(const struct net_device *ol_dev)
+{
+	return mlxsw_sp_ipip_parms_ikey(mlxsw_sp_ipip_netdev_parms(ol_dev));
 }
 
 static u32 mlxsw_sp_ipip_netdev_okey(const struct net_device *ol_dev)
 {
-	struct ip_tunnel *tun = netdev_priv(ol_dev);
+	return mlxsw_sp_ipip_parms_okey(mlxsw_sp_ipip_netdev_parms(ol_dev));
+}
+
+union mlxsw_sp_l3addr
+mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto,
+			   const struct net_device *ol_dev)
+{
+	return mlxsw_sp_ipip_parms_saddr(proto,
+					 mlxsw_sp_ipip_netdev_parms(ol_dev));
+}
+
+static __be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev)
+{
+	return mlxsw_sp_ipip_parms_daddr4(mlxsw_sp_ipip_netdev_parms(ol_dev));
+}
 
-	return mlxsw_sp_ipip_netdev_has_okey(ol_dev) ?
-		be32_to_cpu(tun->parms.o_key) : 0;
+static union mlxsw_sp_l3addr
+mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto,
+			   const struct net_device *ol_dev)
+{
+	return mlxsw_sp_ipip_parms_daddr(proto,
+					 mlxsw_sp_ipip_netdev_parms(ol_dev));
 }
 
 static int
@@ -200,6 +287,73 @@ mlxsw_sp_ipip_ol_loopback_config_gre4(struct mlxsw_sp *mlxsw_sp,
 	};
 }
 
+static int
+mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_ipip_entry *ipip_entry,
+				    struct netlink_ext_ack *extack)
+{
+	union mlxsw_sp_l3addr old_saddr, new_saddr;
+	union mlxsw_sp_l3addr old_daddr, new_daddr;
+	struct ip_tunnel_parm new_parms;
+	bool update_tunnel = false;
+	bool update_decap = false;
+	bool update_nhs = false;
+	int err = 0;
+
+	new_parms = mlxsw_sp_ipip_netdev_parms(ipip_entry->ol_dev);
+
+	new_saddr = mlxsw_sp_ipip_parms_saddr(MLXSW_SP_L3_PROTO_IPV4,
+					      new_parms);
+	old_saddr = mlxsw_sp_ipip_parms_saddr(MLXSW_SP_L3_PROTO_IPV4,
+					      ipip_entry->parms);
+	new_daddr = mlxsw_sp_ipip_parms_daddr(MLXSW_SP_L3_PROTO_IPV4,
+					      new_parms);
+	old_daddr = mlxsw_sp_ipip_parms_daddr(MLXSW_SP_L3_PROTO_IPV4,
+					      ipip_entry->parms);
+
+	if (!mlxsw_sp_l3addr_eq(&new_saddr, &old_saddr)) {
+		u16 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ipip_entry->ol_dev);
+
+		/* Since the local address has changed, if there is another
+		 * tunnel with a matching saddr, both need to be demoted.
+		 */
+		if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp,
+							 MLXSW_SP_L3_PROTO_IPV4,
+							 new_saddr, ul_tb_id,
+							 ipip_entry)) {
+			mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry);
+			return 0;
+		}
+
+		update_tunnel = true;
+	} else if ((mlxsw_sp_ipip_parms_okey(ipip_entry->parms) !=
+		    mlxsw_sp_ipip_parms_okey(new_parms)) ||
+		   ipip_entry->parms.link != new_parms.link) {
+		update_tunnel = true;
+	} else if (!mlxsw_sp_l3addr_eq(&new_daddr, &old_daddr)) {
+		update_nhs = true;
+	} else if (mlxsw_sp_ipip_parms_ikey(ipip_entry->parms) !=
+		   mlxsw_sp_ipip_parms_ikey(new_parms)) {
+		update_decap = true;
+	}
+
+	if (update_tunnel)
+		err = __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry,
+							  true, true, true,
+							  extack);
+	else if (update_nhs)
+		err = __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry,
+							  false, false, true,
+							  extack);
+	else if (update_decap)
+		err = __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry,
+							  false, false, false,
+							  extack);
+
+	ipip_entry->parms = new_parms;
+	return err;
+}
+
 static const struct mlxsw_sp_ipip_ops mlxsw_sp_ipip_gre4_ops = {
 	.dev_type = ARPHRD_IPGRE,
 	.ul_proto = MLXSW_SP_L3_PROTO_IPV4,
@@ -207,6 +361,7 @@ static const struct mlxsw_sp_ipip_ops mlxsw_sp_ipip_gre4_ops = {
 	.fib_entry_op = mlxsw_sp_ipip_fib_entry_op_gre4,
 	.can_offload = mlxsw_sp_ipip_can_offload_gre4,
 	.ol_loopback_config = mlxsw_sp_ipip_ol_loopback_config_gre4,
+	.ol_netdev_change = mlxsw_sp_ipip_ol_netdev_change_gre4,
 };
 
 const struct mlxsw_sp_ipip_ops *mlxsw_sp_ipip_ops_arr[] = {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
index 1c2db831d83b..04b08d9d76e9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
@@ -38,6 +38,13 @@
 #include "spectrum_router.h"
 #include <net/ip_fib.h>
 
+struct ip_tunnel_parm
+mlxsw_sp_ipip_netdev_parms(const struct net_device *ol_dev);
+
+union mlxsw_sp_l3addr
+mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto,
+			   const struct net_device *ol_dev);
+
 enum mlxsw_sp_ipip_type {
 	MLXSW_SP_IPIP_TYPE_GRE4,
 	MLXSW_SP_IPIP_TYPE_MAX,
@@ -47,9 +54,9 @@ struct mlxsw_sp_ipip_entry {
 	enum mlxsw_sp_ipip_type ipipt;
 	struct net_device *ol_dev; /* Overlay. */
 	struct mlxsw_sp_rif_ipip_lb *ol_lb;
-	unsigned int ref_count; /* Number of next hops using the tunnel. */
 	struct mlxsw_sp_fib_entry *decap_fib_entry;
 	struct list_head ipip_list_node;
+	struct ip_tunnel_parm parms;
 };
 
 struct mlxsw_sp_ipip_ops {
@@ -72,6 +79,10 @@ struct mlxsw_sp_ipip_ops {
 			    struct mlxsw_sp_ipip_entry *ipip_entry,
 			    enum mlxsw_reg_ralue_op op,
 			    u32 tunnel_index);
+
+	int (*ol_netdev_change)(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_ipip_entry *ipip_entry,
+				struct netlink_ext_ack *extack);
 };
 
 extern const struct mlxsw_sp_ipip_ops *mlxsw_sp_ipip_ops_arr[];
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
index 26c26cd30c3d..310c38247b5c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -39,55 +39,276 @@
 
 #define MLXSW_SP_KVDL_SINGLE_BASE 0
 #define MLXSW_SP_KVDL_SINGLE_SIZE 16384
+#define MLXSW_SP_KVDL_SINGLE_END \
+	(MLXSW_SP_KVDL_SINGLE_SIZE + MLXSW_SP_KVDL_SINGLE_BASE - 1)
+
 #define MLXSW_SP_KVDL_CHUNKS_BASE \
 	(MLXSW_SP_KVDL_SINGLE_BASE + MLXSW_SP_KVDL_SINGLE_SIZE)
-#define MLXSW_SP_KVDL_CHUNKS_SIZE \
-	(MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP_KVDL_CHUNKS_BASE)
+#define MLXSW_SP_KVDL_CHUNKS_SIZE 49152
+#define MLXSW_SP_KVDL_CHUNKS_END \
+	(MLXSW_SP_KVDL_CHUNKS_SIZE + MLXSW_SP_KVDL_CHUNKS_BASE - 1)
+
+#define MLXSW_SP_KVDL_LARGE_CHUNKS_BASE \
+	(MLXSW_SP_KVDL_CHUNKS_BASE + MLXSW_SP_KVDL_CHUNKS_SIZE)
+#define MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE \
+	(MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP_KVDL_LARGE_CHUNKS_BASE)
+#define MLXSW_SP_KVDL_LARGE_CHUNKS_END \
+	(MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE + MLXSW_SP_KVDL_LARGE_CHUNKS_BASE - 1)
+
 #define MLXSW_SP_CHUNK_MAX 32
+#define MLXSW_SP_LARGE_CHUNK_MAX 512
+
+struct mlxsw_sp_kvdl_part_info {
+	unsigned int part_index;
+	unsigned int start_index;
+	unsigned int end_index;
+	unsigned int alloc_size;
+};
+
+struct mlxsw_sp_kvdl_part {
+	struct list_head list;
+	const struct mlxsw_sp_kvdl_part_info *info;
+	unsigned long usage[0];	/* Entries */
+};
+
+struct mlxsw_sp_kvdl {
+	struct list_head parts_list;
+};
+
+static struct mlxsw_sp_kvdl_part *
+mlxsw_sp_kvdl_alloc_size_part(struct mlxsw_sp_kvdl *kvdl,
+			      unsigned int alloc_size)
+{
+	struct mlxsw_sp_kvdl_part *part, *min_part = NULL;
+
+	list_for_each_entry(part, &kvdl->parts_list, list) {
+		if (alloc_size <= part->info->alloc_size &&
+		    (!min_part ||
+		     part->info->alloc_size <= min_part->info->alloc_size))
+			min_part = part;
+	}
+
+	return min_part ?: ERR_PTR(-ENOBUFS);
+}
+
+static struct mlxsw_sp_kvdl_part *
+mlxsw_sp_kvdl_index_part(struct mlxsw_sp_kvdl *kvdl, u32 kvdl_index)
+{
+	struct mlxsw_sp_kvdl_part *part;
+
+	list_for_each_entry(part, &kvdl->parts_list, list) {
+		if (kvdl_index >= part->info->start_index &&
+		    kvdl_index <= part->info->end_index)
+			return part;
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static u32
+mlxsw_sp_entry_index_kvdl_index(const struct mlxsw_sp_kvdl_part_info *info,
+				unsigned int entry_index)
+{
+	return info->start_index + entry_index * info->alloc_size;
+}
+
+static unsigned int
+mlxsw_sp_kvdl_index_entry_index(const struct mlxsw_sp_kvdl_part_info *info,
+				u32 kvdl_index)
+{
+	return (kvdl_index - info->start_index) / info->alloc_size;
+}
+
+static int mlxsw_sp_kvdl_part_alloc(struct mlxsw_sp_kvdl_part *part,
+				    u32 *p_kvdl_index)
+{
+	const struct mlxsw_sp_kvdl_part_info *info = part->info;
+	unsigned int entry_index, nr_entries;
+
+	nr_entries = (info->end_index - info->start_index + 1) /
+		     info->alloc_size;
+	entry_index = find_first_zero_bit(part->usage, nr_entries);
+	if (entry_index == nr_entries)
+		return -ENOBUFS;
+	__set_bit(entry_index, part->usage);
+
+	*p_kvdl_index = mlxsw_sp_entry_index_kvdl_index(part->info,
+							entry_index);
+
+	return 0;
+}
+
+static void mlxsw_sp_kvdl_part_free(struct mlxsw_sp_kvdl_part *part,
+				    u32 kvdl_index)
+{
+	unsigned int entry_index;
+
+	entry_index = mlxsw_sp_kvdl_index_entry_index(part->info,
+						      kvdl_index);
+	__clear_bit(entry_index, part->usage);
+}
 
 int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
 			u32 *p_entry_index)
 {
-	int entry_index;
-	int size;
-	int type_base;
-	int type_size;
-	int type_entries;
-
-	if (entry_count == 0 || entry_count > MLXSW_SP_CHUNK_MAX) {
-		return -EINVAL;
-	} else if (entry_count == 1) {
-		type_base = MLXSW_SP_KVDL_SINGLE_BASE;
-		type_size = MLXSW_SP_KVDL_SINGLE_SIZE;
-		type_entries = 1;
-	} else {
-		type_base = MLXSW_SP_KVDL_CHUNKS_BASE;
-		type_size = MLXSW_SP_KVDL_CHUNKS_SIZE;
-		type_entries = MLXSW_SP_CHUNK_MAX;
+	struct mlxsw_sp_kvdl_part *part;
+
+	/* Find partition with smallest allocation size satisfying the
+	 * requested size.
+	 */
+	part = mlxsw_sp_kvdl_alloc_size_part(mlxsw_sp->kvdl, entry_count);
+	if (IS_ERR(part))
+		return PTR_ERR(part);
+
+	return mlxsw_sp_kvdl_part_alloc(part, p_entry_index);
+}
+
+void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index)
+{
+	struct mlxsw_sp_kvdl_part *part;
+
+	part = mlxsw_sp_kvdl_index_part(mlxsw_sp->kvdl, entry_index);
+	if (IS_ERR(part))
+		return;
+	mlxsw_sp_kvdl_part_free(part, entry_index);
+}
+
+int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
+				   unsigned int entry_count,
+				   unsigned int *p_alloc_size)
+{
+	struct mlxsw_sp_kvdl_part *part;
+
+	part = mlxsw_sp_kvdl_alloc_size_part(mlxsw_sp->kvdl, entry_count);
+	if (IS_ERR(part))
+		return PTR_ERR(part);
+
+	*p_alloc_size = part->info->alloc_size;
+
+	return 0;
+}
+
+static const struct mlxsw_sp_kvdl_part_info kvdl_parts_info[] = {
+	{
+		.part_index	= 0,
+		.start_index	= MLXSW_SP_KVDL_SINGLE_BASE,
+		.end_index	= MLXSW_SP_KVDL_SINGLE_END,
+		.alloc_size	= 1,
+	},
+	{
+		.part_index	= 1,
+		.start_index	= MLXSW_SP_KVDL_CHUNKS_BASE,
+		.end_index	= MLXSW_SP_KVDL_CHUNKS_END,
+		.alloc_size	= MLXSW_SP_CHUNK_MAX,
+	},
+	{
+		.part_index	= 2,
+		.start_index	= MLXSW_SP_KVDL_LARGE_CHUNKS_BASE,
+		.end_index	= MLXSW_SP_KVDL_LARGE_CHUNKS_END,
+		.alloc_size	= MLXSW_SP_LARGE_CHUNK_MAX,
+	},
+};
+
+static struct mlxsw_sp_kvdl_part *
+mlxsw_sp_kvdl_part_find(struct mlxsw_sp *mlxsw_sp, unsigned int part_index)
+{
+	struct mlxsw_sp_kvdl_part *part;
+
+	list_for_each_entry(part, &mlxsw_sp->kvdl->parts_list, list) {
+		if (part->info->part_index == part_index)
+			return part;
 	}
 
-	entry_index = type_base;
-	size = type_base + type_size;
-	for_each_clear_bit_from(entry_index, mlxsw_sp->kvdl.usage, size) {
-		int i;
+	return NULL;
+}
+
+static int mlxsw_sp_kvdl_part_init(struct mlxsw_sp *mlxsw_sp,
+				   unsigned int part_index)
+{
+	const struct mlxsw_sp_kvdl_part_info *info;
+	struct mlxsw_sp_kvdl_part *part;
+	unsigned int nr_entries;
+	size_t usage_size;
+
+	info = &kvdl_parts_info[part_index];
+
+	nr_entries = (info->end_index - info->start_index + 1) /
+		     info->alloc_size;
+	usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long);
+	part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL);
+	if (!part)
+		return -ENOMEM;
+
+	part->info = info;
+	list_add(&part->list, &mlxsw_sp->kvdl->parts_list);
+
+	return 0;
+}
+
+static void mlxsw_sp_kvdl_part_fini(struct mlxsw_sp *mlxsw_sp,
+				    unsigned int part_index)
+{
+	struct mlxsw_sp_kvdl_part *part;
+
+	part = mlxsw_sp_kvdl_part_find(mlxsw_sp, part_index);
+	if (!part)
+		return;
+
+	list_del(&part->list);
+	kfree(part);
+}
+
+static int mlxsw_sp_kvdl_parts_init(struct mlxsw_sp *mlxsw_sp)
+{
+	int err, i;
+
+	INIT_LIST_HEAD(&mlxsw_sp->kvdl->parts_list);
 
-		for (i = 0; i < type_entries; i++)
-			set_bit(entry_index + i, mlxsw_sp->kvdl.usage);
-		*p_entry_index = entry_index;
-		return 0;
+	for (i = 0; i < ARRAY_SIZE(kvdl_parts_info); i++) {
+		err = mlxsw_sp_kvdl_part_init(mlxsw_sp, i);
+		if (err)
+			goto err_kvdl_part_init;
 	}
-	return -ENOBUFS;
+
+	return 0;
+
+err_kvdl_part_init:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_kvdl_part_fini(mlxsw_sp, i);
+	return err;
 }
 
-void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index)
+static void mlxsw_sp_kvdl_parts_fini(struct mlxsw_sp *mlxsw_sp)
 {
-	int type_entries;
 	int i;
 
-	if (entry_index < MLXSW_SP_KVDL_CHUNKS_BASE)
-		type_entries = 1;
-	else
-		type_entries = MLXSW_SP_CHUNK_MAX;
-	for (i = 0; i < type_entries; i++)
-		clear_bit(entry_index + i, mlxsw_sp->kvdl.usage);
+	for (i = ARRAY_SIZE(kvdl_parts_info) - 1; i >= 0; i--)
+		mlxsw_sp_kvdl_part_fini(mlxsw_sp, i);
+}
+
+int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_kvdl *kvdl;
+	int err;
+
+	kvdl = kzalloc(sizeof(*mlxsw_sp->kvdl), GFP_KERNEL);
+	if (!kvdl)
+		return -ENOMEM;
+	mlxsw_sp->kvdl = kvdl;
+
+	err = mlxsw_sp_kvdl_parts_init(mlxsw_sp);
+	if (err)
+		goto err_kvdl_parts_init;
+
+	return 0;
+
+err_kvdl_parts_init:
+	kfree(mlxsw_sp->kvdl);
+	return err;
+}
+
+void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	mlxsw_sp_kvdl_parts_fini(mlxsw_sp);
+	kfree(mlxsw_sp->kvdl);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
new file mode 100644
index 000000000000..d20b143de3b4
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
@@ -0,0 +1,1012 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/rhashtable.h>
+
+#include "spectrum_mr.h"
+#include "spectrum_router.h"
+
+struct mlxsw_sp_mr {
+	const struct mlxsw_sp_mr_ops *mr_ops;
+	void *catchall_route_priv;
+	struct delayed_work stats_update_dw;
+	struct list_head table_list;
+#define MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL 5000 /* ms */
+	unsigned long priv[0];
+	/* priv has to be always the last item */
+};
+
+struct mlxsw_sp_mr_vif {
+	struct net_device *dev;
+	const struct mlxsw_sp_rif *rif;
+	unsigned long vif_flags;
+
+	/* A list of route_vif_entry structs that point to routes that the VIF
+	 * instance is used as one of the egress VIFs
+	 */
+	struct list_head route_evif_list;
+
+	/* A list of route_vif_entry structs that point to routes that the VIF
+	 * instance is used as an ingress VIF
+	 */
+	struct list_head route_ivif_list;
+};
+
+struct mlxsw_sp_mr_route_vif_entry {
+	struct list_head vif_node;
+	struct list_head route_node;
+	struct mlxsw_sp_mr_vif *mr_vif;
+	struct mlxsw_sp_mr_route *mr_route;
+};
+
+struct mlxsw_sp_mr_table {
+	struct list_head node;
+	enum mlxsw_sp_l3proto proto;
+	struct mlxsw_sp *mlxsw_sp;
+	u32 vr_id;
+	struct mlxsw_sp_mr_vif vifs[MAXVIFS];
+	struct list_head route_list;
+	struct rhashtable route_ht;
+	char catchall_route_priv[0];
+	/* catchall_route_priv has to be always the last item */
+};
+
+struct mlxsw_sp_mr_route {
+	struct list_head node;
+	struct rhash_head ht_node;
+	struct mlxsw_sp_mr_route_key key;
+	enum mlxsw_sp_mr_route_action route_action;
+	u16 min_mtu;
+	struct mfc_cache *mfc4;
+	void *route_priv;
+	const struct mlxsw_sp_mr_table *mr_table;
+	/* A list of route_vif_entry structs that point to the egress VIFs */
+	struct list_head evif_list;
+	/* A route_vif_entry struct that point to the ingress VIF */
+	struct mlxsw_sp_mr_route_vif_entry ivif;
+};
+
+static const struct rhashtable_params mlxsw_sp_mr_route_ht_params = {
+	.key_len = sizeof(struct mlxsw_sp_mr_route_key),
+	.key_offset = offsetof(struct mlxsw_sp_mr_route, key),
+	.head_offset = offsetof(struct mlxsw_sp_mr_route, ht_node),
+	.automatic_shrinking = true,
+};
+
+static bool mlxsw_sp_mr_vif_regular(const struct mlxsw_sp_mr_vif *vif)
+{
+	return !(vif->vif_flags & (VIFF_TUNNEL | VIFF_REGISTER));
+}
+
+static bool mlxsw_sp_mr_vif_valid(const struct mlxsw_sp_mr_vif *vif)
+{
+	return mlxsw_sp_mr_vif_regular(vif) && vif->dev && vif->rif;
+}
+
+static bool mlxsw_sp_mr_vif_exists(const struct mlxsw_sp_mr_vif *vif)
+{
+	return vif->dev;
+}
+
+static bool
+mlxsw_sp_mr_route_ivif_in_evifs(const struct mlxsw_sp_mr_route *mr_route)
+{
+	vifi_t ivif;
+
+	switch (mr_route->mr_table->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		ivif = mr_route->mfc4->mfc_parent;
+		return mr_route->mfc4->mfc_un.res.ttls[ivif] != 255;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		/* fall through */
+	default:
+		WARN_ON_ONCE(1);
+	}
+	return false;
+}
+
+static int
+mlxsw_sp_mr_route_valid_evifs_num(const struct mlxsw_sp_mr_route *mr_route)
+{
+	struct mlxsw_sp_mr_route_vif_entry *rve;
+	int valid_evifs;
+
+	valid_evifs = 0;
+	list_for_each_entry(rve, &mr_route->evif_list, route_node)
+		if (mlxsw_sp_mr_vif_valid(rve->mr_vif))
+			valid_evifs++;
+	return valid_evifs;
+}
+
+static bool mlxsw_sp_mr_route_starg(const struct mlxsw_sp_mr_route *mr_route)
+{
+	switch (mr_route->mr_table->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		return mr_route->key.source_mask.addr4 == htonl(INADDR_ANY);
+	case MLXSW_SP_L3_PROTO_IPV6:
+		/* fall through */
+	default:
+		WARN_ON_ONCE(1);
+	}
+	return false;
+}
+
+static enum mlxsw_sp_mr_route_action
+mlxsw_sp_mr_route_action(const struct mlxsw_sp_mr_route *mr_route)
+{
+	struct mlxsw_sp_mr_route_vif_entry *rve;
+
+	/* If the ingress port is not regular and resolved, trap the route */
+	if (!mlxsw_sp_mr_vif_valid(mr_route->ivif.mr_vif))
+		return MLXSW_SP_MR_ROUTE_ACTION_TRAP;
+
+	/* The kernel does not match a (*,G) route that the ingress interface is
+	 * not one of the egress interfaces, so trap these kind of routes.
+	 */
+	if (mlxsw_sp_mr_route_starg(mr_route) &&
+	    !mlxsw_sp_mr_route_ivif_in_evifs(mr_route))
+		return MLXSW_SP_MR_ROUTE_ACTION_TRAP;
+
+	/* If the route has no valid eVIFs, trap it. */
+	if (!mlxsw_sp_mr_route_valid_evifs_num(mr_route))
+		return MLXSW_SP_MR_ROUTE_ACTION_TRAP;
+
+	/* If one of the eVIFs has no RIF, trap-and-forward the route as there
+	 * is some more routing to do in software too.
+	 */
+	list_for_each_entry(rve, &mr_route->evif_list, route_node)
+		if (mlxsw_sp_mr_vif_exists(rve->mr_vif) && !rve->mr_vif->rif)
+			return MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD;
+
+	return MLXSW_SP_MR_ROUTE_ACTION_FORWARD;
+}
+
+static enum mlxsw_sp_mr_route_prio
+mlxsw_sp_mr_route_prio(const struct mlxsw_sp_mr_route *mr_route)
+{
+	return mlxsw_sp_mr_route_starg(mr_route) ?
+		MLXSW_SP_MR_ROUTE_PRIO_STARG : MLXSW_SP_MR_ROUTE_PRIO_SG;
+}
+
+static void mlxsw_sp_mr_route4_key(struct mlxsw_sp_mr_table *mr_table,
+				   struct mlxsw_sp_mr_route_key *key,
+				   const struct mfc_cache *mfc)
+{
+	bool starg = (mfc->mfc_origin == htonl(INADDR_ANY));
+
+	memset(key, 0, sizeof(*key));
+	key->vrid = mr_table->vr_id;
+	key->proto = mr_table->proto;
+	key->group.addr4 = mfc->mfc_mcastgrp;
+	key->group_mask.addr4 = htonl(0xffffffff);
+	key->source.addr4 = mfc->mfc_origin;
+	key->source_mask.addr4 = htonl(starg ? 0 : 0xffffffff);
+}
+
+static int mlxsw_sp_mr_route_evif_link(struct mlxsw_sp_mr_route *mr_route,
+				       struct mlxsw_sp_mr_vif *mr_vif)
+{
+	struct mlxsw_sp_mr_route_vif_entry *rve;
+
+	rve = kzalloc(sizeof(*rve), GFP_KERNEL);
+	if (!rve)
+		return -ENOMEM;
+	rve->mr_route = mr_route;
+	rve->mr_vif = mr_vif;
+	list_add_tail(&rve->route_node, &mr_route->evif_list);
+	list_add_tail(&rve->vif_node, &mr_vif->route_evif_list);
+	return 0;
+}
+
+static void
+mlxsw_sp_mr_route_evif_unlink(struct mlxsw_sp_mr_route_vif_entry *rve)
+{
+	list_del(&rve->route_node);
+	list_del(&rve->vif_node);
+	kfree(rve);
+}
+
+static void mlxsw_sp_mr_route_ivif_link(struct mlxsw_sp_mr_route *mr_route,
+					struct mlxsw_sp_mr_vif *mr_vif)
+{
+	mr_route->ivif.mr_route = mr_route;
+	mr_route->ivif.mr_vif = mr_vif;
+	list_add_tail(&mr_route->ivif.vif_node, &mr_vif->route_ivif_list);
+}
+
+static void mlxsw_sp_mr_route_ivif_unlink(struct mlxsw_sp_mr_route *mr_route)
+{
+	list_del(&mr_route->ivif.vif_node);
+}
+
+static int
+mlxsw_sp_mr_route_info_create(struct mlxsw_sp_mr_table *mr_table,
+			      struct mlxsw_sp_mr_route *mr_route,
+			      struct mlxsw_sp_mr_route_info *route_info)
+{
+	struct mlxsw_sp_mr_route_vif_entry *rve;
+	u16 *erif_indices;
+	u16 irif_index;
+	u16 erif = 0;
+
+	erif_indices = kmalloc_array(MAXVIFS, sizeof(*erif_indices),
+				     GFP_KERNEL);
+	if (!erif_indices)
+		return -ENOMEM;
+
+	list_for_each_entry(rve, &mr_route->evif_list, route_node) {
+		if (mlxsw_sp_mr_vif_valid(rve->mr_vif)) {
+			u16 rifi = mlxsw_sp_rif_index(rve->mr_vif->rif);
+
+			erif_indices[erif++] = rifi;
+		}
+	}
+
+	if (mlxsw_sp_mr_vif_valid(mr_route->ivif.mr_vif))
+		irif_index = mlxsw_sp_rif_index(mr_route->ivif.mr_vif->rif);
+	else
+		irif_index = 0;
+
+	route_info->irif_index = irif_index;
+	route_info->erif_indices = erif_indices;
+	route_info->min_mtu = mr_route->min_mtu;
+	route_info->route_action = mr_route->route_action;
+	route_info->erif_num = erif;
+	return 0;
+}
+
+static void
+mlxsw_sp_mr_route_info_destroy(struct mlxsw_sp_mr_route_info *route_info)
+{
+	kfree(route_info->erif_indices);
+}
+
+static int mlxsw_sp_mr_route_write(struct mlxsw_sp_mr_table *mr_table,
+				   struct mlxsw_sp_mr_route *mr_route,
+				   bool replace)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+	struct mlxsw_sp_mr_route_info route_info;
+	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+	int err;
+
+	err = mlxsw_sp_mr_route_info_create(mr_table, mr_route, &route_info);
+	if (err)
+		return err;
+
+	if (!replace) {
+		struct mlxsw_sp_mr_route_params route_params;
+
+		mr_route->route_priv = kzalloc(mr->mr_ops->route_priv_size,
+					       GFP_KERNEL);
+		if (!mr_route->route_priv) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		route_params.key = mr_route->key;
+		route_params.value = route_info;
+		route_params.prio = mlxsw_sp_mr_route_prio(mr_route);
+		err = mr->mr_ops->route_create(mlxsw_sp, mr->priv,
+					       mr_route->route_priv,
+					       &route_params);
+		if (err)
+			kfree(mr_route->route_priv);
+	} else {
+		err = mr->mr_ops->route_update(mlxsw_sp, mr_route->route_priv,
+					       &route_info);
+	}
+out:
+	mlxsw_sp_mr_route_info_destroy(&route_info);
+	return err;
+}
+
+static void mlxsw_sp_mr_route_erase(struct mlxsw_sp_mr_table *mr_table,
+				    struct mlxsw_sp_mr_route *mr_route)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+
+	mr->mr_ops->route_destroy(mlxsw_sp, mr->priv, mr_route->route_priv);
+	kfree(mr_route->route_priv);
+}
+
+static struct mlxsw_sp_mr_route *
+mlxsw_sp_mr_route4_create(struct mlxsw_sp_mr_table *mr_table,
+			  struct mfc_cache *mfc)
+{
+	struct mlxsw_sp_mr_route_vif_entry *rve, *tmp;
+	struct mlxsw_sp_mr_route *mr_route;
+	int err = 0;
+	int i;
+
+	/* Allocate and init a new route and fill it with parameters */
+	mr_route = kzalloc(sizeof(*mr_route), GFP_KERNEL);
+	if (!mr_route)
+		return ERR_PTR(-ENOMEM);
+	INIT_LIST_HEAD(&mr_route->evif_list);
+	mlxsw_sp_mr_route4_key(mr_table, &mr_route->key, mfc);
+
+	/* Find min_mtu and link iVIF and eVIFs */
+	mr_route->min_mtu = ETH_MAX_MTU;
+	ipmr_cache_hold(mfc);
+	mr_route->mfc4 = mfc;
+	mr_route->mr_table = mr_table;
+	for (i = 0; i < MAXVIFS; i++) {
+		if (mfc->mfc_un.res.ttls[i] != 255) {
+			err = mlxsw_sp_mr_route_evif_link(mr_route,
+							  &mr_table->vifs[i]);
+			if (err)
+				goto err;
+			if (mr_table->vifs[i].dev &&
+			    mr_table->vifs[i].dev->mtu < mr_route->min_mtu)
+				mr_route->min_mtu = mr_table->vifs[i].dev->mtu;
+		}
+	}
+	mlxsw_sp_mr_route_ivif_link(mr_route, &mr_table->vifs[mfc->mfc_parent]);
+
+	mr_route->route_action = mlxsw_sp_mr_route_action(mr_route);
+	return mr_route;
+err:
+	ipmr_cache_put(mfc);
+	list_for_each_entry_safe(rve, tmp, &mr_route->evif_list, route_node)
+		mlxsw_sp_mr_route_evif_unlink(rve);
+	kfree(mr_route);
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_mr_route4_destroy(struct mlxsw_sp_mr_table *mr_table,
+				       struct mlxsw_sp_mr_route *mr_route)
+{
+	struct mlxsw_sp_mr_route_vif_entry *rve, *tmp;
+
+	mlxsw_sp_mr_route_ivif_unlink(mr_route);
+	ipmr_cache_put(mr_route->mfc4);
+	list_for_each_entry_safe(rve, tmp, &mr_route->evif_list, route_node)
+		mlxsw_sp_mr_route_evif_unlink(rve);
+	kfree(mr_route);
+}
+
+static void mlxsw_sp_mr_route_destroy(struct mlxsw_sp_mr_table *mr_table,
+				      struct mlxsw_sp_mr_route *mr_route)
+{
+	switch (mr_table->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		mlxsw_sp_mr_route4_destroy(mr_table, mr_route);
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		/* fall through */
+	default:
+		WARN_ON_ONCE(1);
+	}
+}
+
+static void mlxsw_sp_mr_mfc_offload_set(struct mlxsw_sp_mr_route *mr_route,
+					bool offload)
+{
+	switch (mr_route->mr_table->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		if (offload)
+			mr_route->mfc4->mfc_flags |= MFC_OFFLOAD;
+		else
+			mr_route->mfc4->mfc_flags &= ~MFC_OFFLOAD;
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		/* fall through */
+	default:
+		WARN_ON_ONCE(1);
+	}
+}
+
+static void mlxsw_sp_mr_mfc_offload_update(struct mlxsw_sp_mr_route *mr_route)
+{
+	bool offload;
+
+	offload = mr_route->route_action != MLXSW_SP_MR_ROUTE_ACTION_TRAP;
+	mlxsw_sp_mr_mfc_offload_set(mr_route, offload);
+}
+
+static void __mlxsw_sp_mr_route_del(struct mlxsw_sp_mr_table *mr_table,
+				    struct mlxsw_sp_mr_route *mr_route)
+{
+	mlxsw_sp_mr_mfc_offload_set(mr_route, false);
+	mlxsw_sp_mr_route_erase(mr_table, mr_route);
+	rhashtable_remove_fast(&mr_table->route_ht, &mr_route->ht_node,
+			       mlxsw_sp_mr_route_ht_params);
+	list_del(&mr_route->node);
+	mlxsw_sp_mr_route_destroy(mr_table, mr_route);
+}
+
+int mlxsw_sp_mr_route4_add(struct mlxsw_sp_mr_table *mr_table,
+			   struct mfc_cache *mfc, bool replace)
+{
+	struct mlxsw_sp_mr_route *mr_orig_route = NULL;
+	struct mlxsw_sp_mr_route *mr_route;
+	int err;
+
+	/* If the route is a (*,*) route, abort, as these kind of routes are
+	 * used for proxy routes.
+	 */
+	if (mfc->mfc_origin == htonl(INADDR_ANY) &&
+	    mfc->mfc_mcastgrp == htonl(INADDR_ANY)) {
+		dev_warn(mr_table->mlxsw_sp->bus_info->dev,
+			 "Offloading proxy routes is not supported.\n");
+		return -EINVAL;
+	}
+
+	/* Create a new route */
+	mr_route = mlxsw_sp_mr_route4_create(mr_table, mfc);
+	if (IS_ERR(mr_route))
+		return PTR_ERR(mr_route);
+
+	/* Find any route with a matching key */
+	mr_orig_route = rhashtable_lookup_fast(&mr_table->route_ht,
+					       &mr_route->key,
+					       mlxsw_sp_mr_route_ht_params);
+	if (replace) {
+		/* On replace case, make the route point to the new route_priv.
+		 */
+		if (WARN_ON(!mr_orig_route)) {
+			err = -ENOENT;
+			goto err_no_orig_route;
+		}
+		mr_route->route_priv = mr_orig_route->route_priv;
+	} else if (mr_orig_route) {
+		/* On non replace case, if another route with the same key was
+		 * found, abort, as duplicate routes are used for proxy routes.
+		 */
+		dev_warn(mr_table->mlxsw_sp->bus_info->dev,
+			 "Offloading proxy routes is not supported.\n");
+		err = -EINVAL;
+		goto err_duplicate_route;
+	}
+
+	/* Put it in the table data-structures */
+	list_add_tail(&mr_route->node, &mr_table->route_list);
+	err = rhashtable_insert_fast(&mr_table->route_ht,
+				     &mr_route->ht_node,
+				     mlxsw_sp_mr_route_ht_params);
+	if (err)
+		goto err_rhashtable_insert;
+
+	/* Write the route to the hardware */
+	err = mlxsw_sp_mr_route_write(mr_table, mr_route, replace);
+	if (err)
+		goto err_mr_route_write;
+
+	/* Destroy the original route */
+	if (replace) {
+		rhashtable_remove_fast(&mr_table->route_ht,
+				       &mr_orig_route->ht_node,
+				       mlxsw_sp_mr_route_ht_params);
+		list_del(&mr_orig_route->node);
+		mlxsw_sp_mr_route4_destroy(mr_table, mr_orig_route);
+	}
+
+	mlxsw_sp_mr_mfc_offload_update(mr_route);
+	return 0;
+
+err_mr_route_write:
+	rhashtable_remove_fast(&mr_table->route_ht, &mr_route->ht_node,
+			       mlxsw_sp_mr_route_ht_params);
+err_rhashtable_insert:
+	list_del(&mr_route->node);
+err_no_orig_route:
+err_duplicate_route:
+	mlxsw_sp_mr_route4_destroy(mr_table, mr_route);
+	return err;
+}
+
+void mlxsw_sp_mr_route4_del(struct mlxsw_sp_mr_table *mr_table,
+			    struct mfc_cache *mfc)
+{
+	struct mlxsw_sp_mr_route *mr_route;
+	struct mlxsw_sp_mr_route_key key;
+
+	mlxsw_sp_mr_route4_key(mr_table, &key, mfc);
+	mr_route = rhashtable_lookup_fast(&mr_table->route_ht, &key,
+					  mlxsw_sp_mr_route_ht_params);
+	if (mr_route)
+		__mlxsw_sp_mr_route_del(mr_table, mr_route);
+}
+
+/* Should be called after the VIF struct is updated */
+static int
+mlxsw_sp_mr_route_ivif_resolve(struct mlxsw_sp_mr_table *mr_table,
+			       struct mlxsw_sp_mr_route_vif_entry *rve)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+	enum mlxsw_sp_mr_route_action route_action;
+	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+	u16 irif_index;
+	int err;
+
+	route_action = mlxsw_sp_mr_route_action(rve->mr_route);
+	if (route_action == MLXSW_SP_MR_ROUTE_ACTION_TRAP)
+		return 0;
+
+	/* rve->mr_vif->rif is guaranteed to be valid at this stage */
+	irif_index = mlxsw_sp_rif_index(rve->mr_vif->rif);
+	err = mr->mr_ops->route_irif_update(mlxsw_sp, rve->mr_route->route_priv,
+					    irif_index);
+	if (err)
+		return err;
+
+	err = mr->mr_ops->route_action_update(mlxsw_sp,
+					      rve->mr_route->route_priv,
+					      route_action);
+	if (err)
+		/* No need to rollback here because the iRIF change only takes
+		 * place after the action has been updated.
+		 */
+		return err;
+
+	rve->mr_route->route_action = route_action;
+	mlxsw_sp_mr_mfc_offload_update(rve->mr_route);
+	return 0;
+}
+
+static void
+mlxsw_sp_mr_route_ivif_unresolve(struct mlxsw_sp_mr_table *mr_table,
+				 struct mlxsw_sp_mr_route_vif_entry *rve)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+
+	mr->mr_ops->route_action_update(mlxsw_sp, rve->mr_route->route_priv,
+					MLXSW_SP_MR_ROUTE_ACTION_TRAP);
+	rve->mr_route->route_action = MLXSW_SP_MR_ROUTE_ACTION_TRAP;
+	mlxsw_sp_mr_mfc_offload_update(rve->mr_route);
+}
+
+/* Should be called after the RIF struct is updated */
+static int
+mlxsw_sp_mr_route_evif_resolve(struct mlxsw_sp_mr_table *mr_table,
+			       struct mlxsw_sp_mr_route_vif_entry *rve)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+	enum mlxsw_sp_mr_route_action route_action;
+	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+	u16 erif_index = 0;
+	int err;
+
+	/* Update the route action, as the new eVIF can be a tunnel or a pimreg
+	 * device which will require updating the action.
+	 */
+	route_action = mlxsw_sp_mr_route_action(rve->mr_route);
+	if (route_action != rve->mr_route->route_action) {
+		err = mr->mr_ops->route_action_update(mlxsw_sp,
+						      rve->mr_route->route_priv,
+						      route_action);
+		if (err)
+			return err;
+	}
+
+	/* Add the eRIF */
+	if (mlxsw_sp_mr_vif_valid(rve->mr_vif)) {
+		erif_index = mlxsw_sp_rif_index(rve->mr_vif->rif);
+		err = mr->mr_ops->route_erif_add(mlxsw_sp,
+						 rve->mr_route->route_priv,
+						 erif_index);
+		if (err)
+			goto err_route_erif_add;
+	}
+
+	/* Update the minimum MTU */
+	if (rve->mr_vif->dev->mtu < rve->mr_route->min_mtu) {
+		rve->mr_route->min_mtu = rve->mr_vif->dev->mtu;
+		err = mr->mr_ops->route_min_mtu_update(mlxsw_sp,
+						       rve->mr_route->route_priv,
+						       rve->mr_route->min_mtu);
+		if (err)
+			goto err_route_min_mtu_update;
+	}
+
+	rve->mr_route->route_action = route_action;
+	mlxsw_sp_mr_mfc_offload_update(rve->mr_route);
+	return 0;
+
+err_route_min_mtu_update:
+	if (mlxsw_sp_mr_vif_valid(rve->mr_vif))
+		mr->mr_ops->route_erif_del(mlxsw_sp, rve->mr_route->route_priv,
+					   erif_index);
+err_route_erif_add:
+	if (route_action != rve->mr_route->route_action)
+		mr->mr_ops->route_action_update(mlxsw_sp,
+						rve->mr_route->route_priv,
+						rve->mr_route->route_action);
+	return err;
+}
+
+/* Should be called before the RIF struct is updated */
+static void
+mlxsw_sp_mr_route_evif_unresolve(struct mlxsw_sp_mr_table *mr_table,
+				 struct mlxsw_sp_mr_route_vif_entry *rve)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+	enum mlxsw_sp_mr_route_action route_action;
+	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+	u16 rifi;
+
+	/* If the unresolved RIF was not valid, no need to delete it */
+	if (!mlxsw_sp_mr_vif_valid(rve->mr_vif))
+		return;
+
+	/* Update the route action: if there is only one valid eVIF in the
+	 * route, set the action to trap as the VIF deletion will lead to zero
+	 * valid eVIFs. On any other case, use the mlxsw_sp_mr_route_action to
+	 * determine the route action.
+	 */
+	if (mlxsw_sp_mr_route_valid_evifs_num(rve->mr_route) == 1)
+		route_action = MLXSW_SP_MR_ROUTE_ACTION_TRAP;
+	else
+		route_action = mlxsw_sp_mr_route_action(rve->mr_route);
+	if (route_action != rve->mr_route->route_action)
+		mr->mr_ops->route_action_update(mlxsw_sp,
+						rve->mr_route->route_priv,
+						route_action);
+
+	/* Delete the erif from the route */
+	rifi = mlxsw_sp_rif_index(rve->mr_vif->rif);
+	mr->mr_ops->route_erif_del(mlxsw_sp, rve->mr_route->route_priv, rifi);
+	rve->mr_route->route_action = route_action;
+	mlxsw_sp_mr_mfc_offload_update(rve->mr_route);
+}
+
+static int mlxsw_sp_mr_vif_resolve(struct mlxsw_sp_mr_table *mr_table,
+				   struct net_device *dev,
+				   struct mlxsw_sp_mr_vif *mr_vif,
+				   unsigned long vif_flags,
+				   const struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_mr_route_vif_entry *irve, *erve;
+	int err;
+
+	/* Update the VIF */
+	mr_vif->dev = dev;
+	mr_vif->rif = rif;
+	mr_vif->vif_flags = vif_flags;
+
+	/* Update all routes where this VIF is used as an unresolved iRIF */
+	list_for_each_entry(irve, &mr_vif->route_ivif_list, vif_node) {
+		err = mlxsw_sp_mr_route_ivif_resolve(mr_table, irve);
+		if (err)
+			goto err_irif_unresolve;
+	}
+
+	/* Update all routes where this VIF is used as an unresolved eRIF */
+	list_for_each_entry(erve, &mr_vif->route_evif_list, vif_node) {
+		err = mlxsw_sp_mr_route_evif_resolve(mr_table, erve);
+		if (err)
+			goto err_erif_unresolve;
+	}
+	return 0;
+
+err_erif_unresolve:
+	list_for_each_entry_from_reverse(erve, &mr_vif->route_evif_list,
+					 vif_node)
+		mlxsw_sp_mr_route_evif_unresolve(mr_table, erve);
+err_irif_unresolve:
+	list_for_each_entry_from_reverse(irve, &mr_vif->route_ivif_list,
+					 vif_node)
+		mlxsw_sp_mr_route_ivif_unresolve(mr_table, irve);
+	mr_vif->rif = NULL;
+	return err;
+}
+
+static void mlxsw_sp_mr_vif_unresolve(struct mlxsw_sp_mr_table *mr_table,
+				      struct net_device *dev,
+				      struct mlxsw_sp_mr_vif *mr_vif)
+{
+	struct mlxsw_sp_mr_route_vif_entry *rve;
+
+	/* Update all routes where this VIF is used as an unresolved eRIF */
+	list_for_each_entry(rve, &mr_vif->route_evif_list, vif_node)
+		mlxsw_sp_mr_route_evif_unresolve(mr_table, rve);
+
+	/* Update all routes where this VIF is used as an unresolved iRIF */
+	list_for_each_entry(rve, &mr_vif->route_ivif_list, vif_node)
+		mlxsw_sp_mr_route_ivif_unresolve(mr_table, rve);
+
+	/* Update the VIF */
+	mr_vif->dev = dev;
+	mr_vif->rif = NULL;
+}
+
+int mlxsw_sp_mr_vif_add(struct mlxsw_sp_mr_table *mr_table,
+			struct net_device *dev, vifi_t vif_index,
+			unsigned long vif_flags, const struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_mr_vif *mr_vif = &mr_table->vifs[vif_index];
+
+	if (WARN_ON(vif_index >= MAXVIFS))
+		return -EINVAL;
+	if (mr_vif->dev)
+		return -EEXIST;
+	return mlxsw_sp_mr_vif_resolve(mr_table, dev, mr_vif, vif_flags, rif);
+}
+
+void mlxsw_sp_mr_vif_del(struct mlxsw_sp_mr_table *mr_table, vifi_t vif_index)
+{
+	struct mlxsw_sp_mr_vif *mr_vif = &mr_table->vifs[vif_index];
+
+	if (WARN_ON(vif_index >= MAXVIFS))
+		return;
+	if (WARN_ON(!mr_vif->dev))
+		return;
+	mlxsw_sp_mr_vif_unresolve(mr_table, NULL, mr_vif);
+}
+
+static struct mlxsw_sp_mr_vif *
+mlxsw_sp_mr_dev_vif_lookup(struct mlxsw_sp_mr_table *mr_table,
+			   const struct net_device *dev)
+{
+	vifi_t vif_index;
+
+	for (vif_index = 0; vif_index < MAXVIFS; vif_index++)
+		if (mr_table->vifs[vif_index].dev == dev)
+			return &mr_table->vifs[vif_index];
+	return NULL;
+}
+
+int mlxsw_sp_mr_rif_add(struct mlxsw_sp_mr_table *mr_table,
+			const struct mlxsw_sp_rif *rif)
+{
+	const struct net_device *rif_dev = mlxsw_sp_rif_dev(rif);
+	struct mlxsw_sp_mr_vif *mr_vif;
+
+	if (!rif_dev)
+		return 0;
+
+	mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif_dev);
+	if (!mr_vif)
+		return 0;
+	return mlxsw_sp_mr_vif_resolve(mr_table, mr_vif->dev, mr_vif,
+				       mr_vif->vif_flags, rif);
+}
+
+void mlxsw_sp_mr_rif_del(struct mlxsw_sp_mr_table *mr_table,
+			 const struct mlxsw_sp_rif *rif)
+{
+	const struct net_device *rif_dev = mlxsw_sp_rif_dev(rif);
+	struct mlxsw_sp_mr_vif *mr_vif;
+
+	if (!rif_dev)
+		return;
+
+	mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif_dev);
+	if (!mr_vif)
+		return;
+	mlxsw_sp_mr_vif_unresolve(mr_table, mr_vif->dev, mr_vif);
+}
+
+void mlxsw_sp_mr_rif_mtu_update(struct mlxsw_sp_mr_table *mr_table,
+				const struct mlxsw_sp_rif *rif, int mtu)
+{
+	const struct net_device *rif_dev = mlxsw_sp_rif_dev(rif);
+	struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+	struct mlxsw_sp_mr_route_vif_entry *rve;
+	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+	struct mlxsw_sp_mr_vif *mr_vif;
+
+	if (!rif_dev)
+		return;
+
+	/* Search for a VIF that use that RIF */
+	mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif_dev);
+	if (!mr_vif)
+		return;
+
+	/* Update all the routes that uses that VIF as eVIF */
+	list_for_each_entry(rve, &mr_vif->route_evif_list, vif_node) {
+		if (mtu < rve->mr_route->min_mtu) {
+			rve->mr_route->min_mtu = mtu;
+			mr->mr_ops->route_min_mtu_update(mlxsw_sp,
+							 rve->mr_route->route_priv,
+							 mtu);
+		}
+	}
+}
+
+struct mlxsw_sp_mr_table *mlxsw_sp_mr_table_create(struct mlxsw_sp *mlxsw_sp,
+						   u32 vr_id,
+						   enum mlxsw_sp_l3proto proto)
+{
+	struct mlxsw_sp_mr_route_params catchall_route_params = {
+		.prio = MLXSW_SP_MR_ROUTE_PRIO_CATCHALL,
+		.key = {
+			.vrid = vr_id,
+		},
+		.value = {
+			.route_action = MLXSW_SP_MR_ROUTE_ACTION_TRAP,
+		}
+	};
+	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+	struct mlxsw_sp_mr_table *mr_table;
+	int err;
+	int i;
+
+	mr_table = kzalloc(sizeof(*mr_table) + mr->mr_ops->route_priv_size,
+			   GFP_KERNEL);
+	if (!mr_table)
+		return ERR_PTR(-ENOMEM);
+
+	mr_table->vr_id = vr_id;
+	mr_table->mlxsw_sp = mlxsw_sp;
+	mr_table->proto = proto;
+	INIT_LIST_HEAD(&mr_table->route_list);
+
+	err = rhashtable_init(&mr_table->route_ht,
+			      &mlxsw_sp_mr_route_ht_params);
+	if (err)
+		goto err_route_rhashtable_init;
+
+	for (i = 0; i < MAXVIFS; i++) {
+		INIT_LIST_HEAD(&mr_table->vifs[i].route_evif_list);
+		INIT_LIST_HEAD(&mr_table->vifs[i].route_ivif_list);
+	}
+
+	err = mr->mr_ops->route_create(mlxsw_sp, mr->priv,
+				       mr_table->catchall_route_priv,
+				       &catchall_route_params);
+	if (err)
+		goto err_ops_route_create;
+	list_add_tail(&mr_table->node, &mr->table_list);
+	return mr_table;
+
+err_ops_route_create:
+	rhashtable_destroy(&mr_table->route_ht);
+err_route_rhashtable_init:
+	kfree(mr_table);
+	return ERR_PTR(err);
+}
+
+void mlxsw_sp_mr_table_destroy(struct mlxsw_sp_mr_table *mr_table)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+
+	WARN_ON(!mlxsw_sp_mr_table_empty(mr_table));
+	list_del(&mr_table->node);
+	mr->mr_ops->route_destroy(mlxsw_sp, mr->priv,
+				  &mr_table->catchall_route_priv);
+	rhashtable_destroy(&mr_table->route_ht);
+	kfree(mr_table);
+}
+
+void mlxsw_sp_mr_table_flush(struct mlxsw_sp_mr_table *mr_table)
+{
+	struct mlxsw_sp_mr_route *mr_route, *tmp;
+	int i;
+
+	list_for_each_entry_safe(mr_route, tmp, &mr_table->route_list, node)
+		__mlxsw_sp_mr_route_del(mr_table, mr_route);
+
+	for (i = 0; i < MAXVIFS; i++) {
+		mr_table->vifs[i].dev = NULL;
+		mr_table->vifs[i].rif = NULL;
+	}
+}
+
+bool mlxsw_sp_mr_table_empty(const struct mlxsw_sp_mr_table *mr_table)
+{
+	int i;
+
+	for (i = 0; i < MAXVIFS; i++)
+		if (mr_table->vifs[i].dev)
+			return false;
+	return list_empty(&mr_table->route_list);
+}
+
+static void mlxsw_sp_mr_route_stats_update(struct mlxsw_sp *mlxsw_sp,
+					   struct mlxsw_sp_mr_route *mr_route)
+{
+	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+	u64 packets, bytes;
+
+	if (mr_route->route_action == MLXSW_SP_MR_ROUTE_ACTION_TRAP)
+		return;
+
+	mr->mr_ops->route_stats(mlxsw_sp, mr_route->route_priv, &packets,
+				&bytes);
+
+	switch (mr_route->mr_table->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		if (mr_route->mfc4->mfc_un.res.pkt != packets)
+			mr_route->mfc4->mfc_un.res.lastuse = jiffies;
+		mr_route->mfc4->mfc_un.res.pkt = packets;
+		mr_route->mfc4->mfc_un.res.bytes = bytes;
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		/* fall through */
+	default:
+		WARN_ON_ONCE(1);
+	}
+}
+
+static void mlxsw_sp_mr_stats_update(struct work_struct *work)
+{
+	struct mlxsw_sp_mr *mr = container_of(work, struct mlxsw_sp_mr,
+					      stats_update_dw.work);
+	struct mlxsw_sp_mr_table *mr_table;
+	struct mlxsw_sp_mr_route *mr_route;
+	unsigned long interval;
+
+	rtnl_lock();
+	list_for_each_entry(mr_table, &mr->table_list, node)
+		list_for_each_entry(mr_route, &mr_table->route_list, node)
+			mlxsw_sp_mr_route_stats_update(mr_table->mlxsw_sp,
+						       mr_route);
+	rtnl_unlock();
+
+	interval = msecs_to_jiffies(MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL);
+	mlxsw_core_schedule_dw(&mr->stats_update_dw, interval);
+}
+
+int mlxsw_sp_mr_init(struct mlxsw_sp *mlxsw_sp,
+		     const struct mlxsw_sp_mr_ops *mr_ops)
+{
+	struct mlxsw_sp_mr *mr;
+	unsigned long interval;
+	int err;
+
+	mr = kzalloc(sizeof(*mr) + mr_ops->priv_size, GFP_KERNEL);
+	if (!mr)
+		return -ENOMEM;
+	mr->mr_ops = mr_ops;
+	mlxsw_sp->mr = mr;
+	INIT_LIST_HEAD(&mr->table_list);
+
+	err = mr_ops->init(mlxsw_sp, mr->priv);
+	if (err)
+		goto err;
+
+	/* Create the delayed work for counter updates */
+	INIT_DELAYED_WORK(&mr->stats_update_dw, mlxsw_sp_mr_stats_update);
+	interval = msecs_to_jiffies(MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL);
+	mlxsw_core_schedule_dw(&mr->stats_update_dw, interval);
+	return 0;
+err:
+	kfree(mr);
+	return err;
+}
+
+void mlxsw_sp_mr_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+
+	cancel_delayed_work_sync(&mr->stats_update_dw);
+	mr->mr_ops->fini(mr->priv);
+	kfree(mr);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
new file mode 100644
index 000000000000..5d26a122af49
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
@@ -0,0 +1,134 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_SPECTRUM_MCROUTER_H
+#define _MLXSW_SPECTRUM_MCROUTER_H
+
+#include <linux/mroute.h>
+#include "spectrum_router.h"
+#include "spectrum.h"
+
+enum mlxsw_sp_mr_route_action {
+	MLXSW_SP_MR_ROUTE_ACTION_FORWARD,
+	MLXSW_SP_MR_ROUTE_ACTION_TRAP,
+	MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD,
+};
+
+enum mlxsw_sp_mr_route_prio {
+	MLXSW_SP_MR_ROUTE_PRIO_SG,
+	MLXSW_SP_MR_ROUTE_PRIO_STARG,
+	MLXSW_SP_MR_ROUTE_PRIO_CATCHALL,
+	__MLXSW_SP_MR_ROUTE_PRIO_MAX
+};
+
+#define MLXSW_SP_MR_ROUTE_PRIO_MAX (__MLXSW_SP_MR_ROUTE_PRIO_MAX - 1)
+
+struct mlxsw_sp_mr_route_key {
+	int vrid;
+	enum mlxsw_sp_l3proto proto;
+	union mlxsw_sp_l3addr group;
+	union mlxsw_sp_l3addr group_mask;
+	union mlxsw_sp_l3addr source;
+	union mlxsw_sp_l3addr source_mask;
+};
+
+struct mlxsw_sp_mr_route_info {
+	enum mlxsw_sp_mr_route_action route_action;
+	u16 irif_index;
+	u16 *erif_indices;
+	size_t erif_num;
+	u16 min_mtu;
+};
+
+struct mlxsw_sp_mr_route_params {
+	struct mlxsw_sp_mr_route_key key;
+	struct mlxsw_sp_mr_route_info value;
+	enum mlxsw_sp_mr_route_prio prio;
+};
+
+struct mlxsw_sp_mr_ops {
+	int priv_size;
+	int route_priv_size;
+	int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv);
+	int (*route_create)(struct mlxsw_sp *mlxsw_sp, void *priv,
+			    void *route_priv,
+			    struct mlxsw_sp_mr_route_params *route_params);
+	int (*route_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+			    struct mlxsw_sp_mr_route_info *route_info);
+	int (*route_stats)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+			   u64 *packets, u64 *bytes);
+	int (*route_action_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+				   enum mlxsw_sp_mr_route_action route_action);
+	int (*route_min_mtu_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+				    u16 min_mtu);
+	int (*route_irif_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+				 u16 irif_index);
+	int (*route_erif_add)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+			      u16 erif_index);
+	int (*route_erif_del)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+			      u16 erif_index);
+	void (*route_destroy)(struct mlxsw_sp *mlxsw_sp, void *priv,
+			      void *route_priv);
+	void (*fini)(void *priv);
+};
+
+struct mlxsw_sp_mr;
+struct mlxsw_sp_mr_table;
+
+int mlxsw_sp_mr_init(struct mlxsw_sp *mlxsw_sp,
+		     const struct mlxsw_sp_mr_ops *mr_ops);
+void mlxsw_sp_mr_fini(struct mlxsw_sp *mlxsw_sp);
+int mlxsw_sp_mr_route4_add(struct mlxsw_sp_mr_table *mr_table,
+			   struct mfc_cache *mfc, bool replace);
+void mlxsw_sp_mr_route4_del(struct mlxsw_sp_mr_table *mr_table,
+			    struct mfc_cache *mfc);
+int mlxsw_sp_mr_vif_add(struct mlxsw_sp_mr_table *mr_table,
+			struct net_device *dev, vifi_t vif_index,
+			unsigned long vif_flags,
+			const struct mlxsw_sp_rif *rif);
+void mlxsw_sp_mr_vif_del(struct mlxsw_sp_mr_table *mr_table, vifi_t vif_index);
+int mlxsw_sp_mr_rif_add(struct mlxsw_sp_mr_table *mr_table,
+			const struct mlxsw_sp_rif *rif);
+void mlxsw_sp_mr_rif_del(struct mlxsw_sp_mr_table *mr_table,
+			 const struct mlxsw_sp_rif *rif);
+void mlxsw_sp_mr_rif_mtu_update(struct mlxsw_sp_mr_table *mr_table,
+				const struct mlxsw_sp_rif *rif, int mtu);
+struct mlxsw_sp_mr_table *mlxsw_sp_mr_table_create(struct mlxsw_sp *mlxsw_sp,
+						   u32 tb_id,
+						   enum mlxsw_sp_l3proto proto);
+void mlxsw_sp_mr_table_destroy(struct mlxsw_sp_mr_table *mr_table);
+void mlxsw_sp_mr_table_flush(struct mlxsw_sp_mr_table *mr_table);
+bool mlxsw_sp_mr_table_empty(const struct mlxsw_sp_mr_table *mr_table);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
new file mode 100644
index 000000000000..34a0b632e5dd
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
@@ -0,0 +1,839 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/parman.h>
+
+#include "spectrum_mr_tcam.h"
+#include "reg.h"
+#include "spectrum.h"
+#include "core_acl_flex_actions.h"
+#include "spectrum_mr.h"
+
+struct mlxsw_sp_mr_tcam_region {
+	struct mlxsw_sp *mlxsw_sp;
+	enum mlxsw_reg_rtar_key_type rtar_key_type;
+	struct parman *parman;
+	struct parman_prio *parman_prios;
+};
+
+struct mlxsw_sp_mr_tcam {
+	struct mlxsw_sp_mr_tcam_region ipv4_tcam_region;
+};
+
+/* This struct maps to one RIGR2 register entry */
+struct mlxsw_sp_mr_erif_sublist {
+	struct list_head list;
+	u32 rigr2_kvdl_index;
+	int num_erifs;
+	u16 erif_indices[MLXSW_REG_RIGR2_MAX_ERIFS];
+	bool synced;
+};
+
+struct mlxsw_sp_mr_tcam_erif_list {
+	struct list_head erif_sublists;
+	u32 kvdl_index;
+};
+
+static bool
+mlxsw_sp_mr_erif_sublist_full(struct mlxsw_sp *mlxsw_sp,
+			      struct mlxsw_sp_mr_erif_sublist *erif_sublist)
+{
+	int erif_list_entries = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+						   MC_ERIF_LIST_ENTRIES);
+
+	return erif_sublist->num_erifs == erif_list_entries;
+}
+
+static void
+mlxsw_sp_mr_erif_list_init(struct mlxsw_sp_mr_tcam_erif_list *erif_list)
+{
+	INIT_LIST_HEAD(&erif_list->erif_sublists);
+}
+
+#define MLXSW_SP_KVDL_RIGR2_SIZE 1
+
+static struct mlxsw_sp_mr_erif_sublist *
+mlxsw_sp_mr_erif_sublist_create(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_mr_tcam_erif_list *erif_list)
+{
+	struct mlxsw_sp_mr_erif_sublist *erif_sublist;
+	int err;
+
+	erif_sublist = kzalloc(sizeof(*erif_sublist), GFP_KERNEL);
+	if (!erif_sublist)
+		return ERR_PTR(-ENOMEM);
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_RIGR2_SIZE,
+				  &erif_sublist->rigr2_kvdl_index);
+	if (err) {
+		kfree(erif_sublist);
+		return ERR_PTR(err);
+	}
+
+	list_add_tail(&erif_sublist->list, &erif_list->erif_sublists);
+	return erif_sublist;
+}
+
+static void
+mlxsw_sp_mr_erif_sublist_destroy(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_mr_erif_sublist *erif_sublist)
+{
+	list_del(&erif_sublist->list);
+	mlxsw_sp_kvdl_free(mlxsw_sp, erif_sublist->rigr2_kvdl_index);
+	kfree(erif_sublist);
+}
+
+static int
+mlxsw_sp_mr_erif_list_add(struct mlxsw_sp *mlxsw_sp,
+			  struct mlxsw_sp_mr_tcam_erif_list *erif_list,
+			  u16 erif_index)
+{
+	struct mlxsw_sp_mr_erif_sublist *sublist;
+
+	/* If either there is no erif_entry or the last one is full, allocate a
+	 * new one.
+	 */
+	if (list_empty(&erif_list->erif_sublists)) {
+		sublist = mlxsw_sp_mr_erif_sublist_create(mlxsw_sp, erif_list);
+		if (IS_ERR(sublist))
+			return PTR_ERR(sublist);
+		erif_list->kvdl_index = sublist->rigr2_kvdl_index;
+	} else {
+		sublist = list_last_entry(&erif_list->erif_sublists,
+					  struct mlxsw_sp_mr_erif_sublist,
+					  list);
+		sublist->synced = false;
+		if (mlxsw_sp_mr_erif_sublist_full(mlxsw_sp, sublist)) {
+			sublist = mlxsw_sp_mr_erif_sublist_create(mlxsw_sp,
+								  erif_list);
+			if (IS_ERR(sublist))
+				return PTR_ERR(sublist);
+		}
+	}
+
+	/* Add the eRIF to the last entry's last index */
+	sublist->erif_indices[sublist->num_erifs++] = erif_index;
+	return 0;
+}
+
+static void
+mlxsw_sp_mr_erif_list_flush(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_mr_tcam_erif_list *erif_list)
+{
+	struct mlxsw_sp_mr_erif_sublist *erif_sublist, *tmp;
+
+	list_for_each_entry_safe(erif_sublist, tmp, &erif_list->erif_sublists,
+				 list)
+		mlxsw_sp_mr_erif_sublist_destroy(mlxsw_sp, erif_sublist);
+}
+
+static int
+mlxsw_sp_mr_erif_list_commit(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_mr_tcam_erif_list *erif_list)
+{
+	struct mlxsw_sp_mr_erif_sublist *curr_sublist;
+	char rigr2_pl[MLXSW_REG_RIGR2_LEN];
+	int err;
+	int i;
+
+	list_for_each_entry(curr_sublist, &erif_list->erif_sublists, list) {
+		if (curr_sublist->synced)
+			continue;
+
+		/* If the sublist is not the last one, pack the next index */
+		if (list_is_last(&curr_sublist->list,
+				 &erif_list->erif_sublists)) {
+			mlxsw_reg_rigr2_pack(rigr2_pl,
+					     curr_sublist->rigr2_kvdl_index,
+					     false, 0);
+		} else {
+			struct mlxsw_sp_mr_erif_sublist *next_sublist;
+
+			next_sublist = list_next_entry(curr_sublist, list);
+			mlxsw_reg_rigr2_pack(rigr2_pl,
+					     curr_sublist->rigr2_kvdl_index,
+					     true,
+					     next_sublist->rigr2_kvdl_index);
+		}
+
+		/* Pack all the erifs */
+		for (i = 0; i < curr_sublist->num_erifs; i++) {
+			u16 erif_index = curr_sublist->erif_indices[i];
+
+			mlxsw_reg_rigr2_erif_entry_pack(rigr2_pl, i, true,
+							erif_index);
+		}
+
+		/* Write the entry */
+		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rigr2),
+				      rigr2_pl);
+		if (err)
+			/* No need of a rollback here because this
+			 * hardware entry should not be pointed yet.
+			 */
+			return err;
+		curr_sublist->synced = true;
+	}
+	return 0;
+}
+
+static void mlxsw_sp_mr_erif_list_move(struct mlxsw_sp_mr_tcam_erif_list *to,
+				       struct mlxsw_sp_mr_tcam_erif_list *from)
+{
+	list_splice(&from->erif_sublists, &to->erif_sublists);
+	to->kvdl_index = from->kvdl_index;
+}
+
+struct mlxsw_sp_mr_tcam_route {
+	struct mlxsw_sp_mr_tcam_erif_list erif_list;
+	struct mlxsw_afa_block *afa_block;
+	u32 counter_index;
+	struct parman_item parman_item;
+	struct parman_prio *parman_prio;
+	enum mlxsw_sp_mr_route_action action;
+	struct mlxsw_sp_mr_route_key key;
+	u16 irif_index;
+	u16 min_mtu;
+};
+
+static struct mlxsw_afa_block *
+mlxsw_sp_mr_tcam_afa_block_create(struct mlxsw_sp *mlxsw_sp,
+				  enum mlxsw_sp_mr_route_action route_action,
+				  u16 irif_index, u32 counter_index,
+				  u16 min_mtu,
+				  struct mlxsw_sp_mr_tcam_erif_list *erif_list)
+{
+	struct mlxsw_afa_block *afa_block;
+	int err;
+
+	afa_block = mlxsw_afa_block_create(mlxsw_sp->afa);
+	if (!afa_block)
+		return ERR_PTR(-ENOMEM);
+
+	err = mlxsw_afa_block_append_counter(afa_block, counter_index);
+	if (err)
+		goto err;
+
+	switch (route_action) {
+	case MLXSW_SP_MR_ROUTE_ACTION_TRAP:
+		err = mlxsw_afa_block_append_trap(afa_block,
+						  MLXSW_TRAP_ID_ACL1);
+		if (err)
+			goto err;
+		break;
+	case MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD:
+	case MLXSW_SP_MR_ROUTE_ACTION_FORWARD:
+		/* If we are about to append a multicast router action, commit
+		 * the erif_list.
+		 */
+		err = mlxsw_sp_mr_erif_list_commit(mlxsw_sp, erif_list);
+		if (err)
+			goto err;
+
+		err = mlxsw_afa_block_append_mcrouter(afa_block, irif_index,
+						      min_mtu, false,
+						      erif_list->kvdl_index);
+		if (err)
+			goto err;
+
+		if (route_action == MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD) {
+			err = mlxsw_afa_block_append_trap_and_forward(afa_block,
+								      MLXSW_TRAP_ID_ACL2);
+			if (err)
+				goto err;
+		}
+		break;
+	default:
+		err = -EINVAL;
+		goto err;
+	}
+
+	err = mlxsw_afa_block_commit(afa_block);
+	if (err)
+		goto err;
+	return afa_block;
+err:
+	mlxsw_afa_block_destroy(afa_block);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_mr_tcam_afa_block_destroy(struct mlxsw_afa_block *afa_block)
+{
+	mlxsw_afa_block_destroy(afa_block);
+}
+
+static int mlxsw_sp_mr_tcam_route_replace(struct mlxsw_sp *mlxsw_sp,
+					  struct parman_item *parman_item,
+					  struct mlxsw_sp_mr_route_key *key,
+					  struct mlxsw_afa_block *afa_block)
+{
+	char rmft2_pl[MLXSW_REG_RMFT2_LEN];
+
+	switch (key->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, true, parman_item->index,
+					  key->vrid,
+					  MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
+					  ntohl(key->group.addr4),
+					  ntohl(key->group_mask.addr4),
+					  ntohl(key->source.addr4),
+					  ntohl(key->source_mask.addr4),
+					  mlxsw_afa_block_first_set(afa_block));
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+	default:
+		WARN_ON_ONCE(1);
+	}
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
+}
+
+static int mlxsw_sp_mr_tcam_route_remove(struct mlxsw_sp *mlxsw_sp, int vrid,
+					 struct parman_item *parman_item)
+{
+	char rmft2_pl[MLXSW_REG_RMFT2_LEN];
+
+	mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, false, parman_item->index, vrid,
+				  0, 0, 0, 0, 0, 0, NULL);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
+}
+
+static int
+mlxsw_sp_mr_tcam_erif_populate(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_mr_tcam_erif_list *erif_list,
+			       struct mlxsw_sp_mr_route_info *route_info)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < route_info->erif_num; i++) {
+		u16 erif_index = route_info->erif_indices[i];
+
+		err = mlxsw_sp_mr_erif_list_add(mlxsw_sp, erif_list,
+						erif_index);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int
+mlxsw_sp_mr_tcam_route_parman_item_add(struct mlxsw_sp_mr_tcam *mr_tcam,
+				       struct mlxsw_sp_mr_tcam_route *route,
+				       enum mlxsw_sp_mr_route_prio prio)
+{
+	struct parman_prio *parman_prio = NULL;
+	int err;
+
+	switch (route->key.proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		parman_prio = &mr_tcam->ipv4_tcam_region.parman_prios[prio];
+		err = parman_item_add(mr_tcam->ipv4_tcam_region.parman,
+				      parman_prio, &route->parman_item);
+		if (err)
+			return err;
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+	default:
+		WARN_ON_ONCE(1);
+	}
+	route->parman_prio = parman_prio;
+	return 0;
+}
+
+static void
+mlxsw_sp_mr_tcam_route_parman_item_remove(struct mlxsw_sp_mr_tcam *mr_tcam,
+					  struct mlxsw_sp_mr_tcam_route *route)
+{
+	switch (route->key.proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		parman_item_remove(mr_tcam->ipv4_tcam_region.parman,
+				   route->parman_prio, &route->parman_item);
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+	default:
+		WARN_ON_ONCE(1);
+	}
+}
+
+static int
+mlxsw_sp_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
+			      void *route_priv,
+			      struct mlxsw_sp_mr_route_params *route_params)
+{
+	struct mlxsw_sp_mr_tcam_route *route = route_priv;
+	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
+	int err;
+
+	route->key = route_params->key;
+	route->irif_index = route_params->value.irif_index;
+	route->min_mtu = route_params->value.min_mtu;
+	route->action = route_params->value.route_action;
+
+	/* Create the egress RIFs list */
+	mlxsw_sp_mr_erif_list_init(&route->erif_list);
+	err = mlxsw_sp_mr_tcam_erif_populate(mlxsw_sp, &route->erif_list,
+					     &route_params->value);
+	if (err)
+		goto err_erif_populate;
+
+	/* Create the flow counter */
+	err = mlxsw_sp_flow_counter_alloc(mlxsw_sp, &route->counter_index);
+	if (err)
+		goto err_counter_alloc;
+
+	/* Create the flexible action block */
+	route->afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp,
+							     route->action,
+							     route->irif_index,
+							     route->counter_index,
+							     route->min_mtu,
+							     &route->erif_list);
+	if (IS_ERR(route->afa_block)) {
+		err = PTR_ERR(route->afa_block);
+		goto err_afa_block_create;
+	}
+
+	/* Allocate place in the TCAM */
+	err = mlxsw_sp_mr_tcam_route_parman_item_add(mr_tcam, route,
+						     route_params->prio);
+	if (err)
+		goto err_parman_item_add;
+
+	/* Write the route to the TCAM */
+	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+					     &route->key, route->afa_block);
+	if (err)
+		goto err_route_replace;
+	return 0;
+
+err_route_replace:
+	mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route);
+err_parman_item_add:
+	mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
+err_afa_block_create:
+	mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index);
+err_erif_populate:
+err_counter_alloc:
+	mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list);
+	return err;
+}
+
+static void mlxsw_sp_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp,
+					   void *priv, void *route_priv)
+{
+	struct mlxsw_sp_mr_tcam_route *route = route_priv;
+	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
+
+	mlxsw_sp_mr_tcam_route_remove(mlxsw_sp, route->key.vrid,
+				      &route->parman_item);
+	mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route);
+	mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
+	mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index);
+	mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list);
+}
+
+static int mlxsw_sp_mr_tcam_route_stats(struct mlxsw_sp *mlxsw_sp,
+					void *route_priv, u64 *packets,
+					u64 *bytes)
+{
+	struct mlxsw_sp_mr_tcam_route *route = route_priv;
+
+	return mlxsw_sp_flow_counter_get(mlxsw_sp, route->counter_index,
+					 packets, bytes);
+}
+
+static int
+mlxsw_sp_mr_tcam_route_action_update(struct mlxsw_sp *mlxsw_sp,
+				     void *route_priv,
+				     enum mlxsw_sp_mr_route_action route_action)
+{
+	struct mlxsw_sp_mr_tcam_route *route = route_priv;
+	struct mlxsw_afa_block *afa_block;
+	int err;
+
+	/* Create a new flexible action block */
+	afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp, route_action,
+						      route->irif_index,
+						      route->counter_index,
+						      route->min_mtu,
+						      &route->erif_list);
+	if (IS_ERR(afa_block))
+		return PTR_ERR(afa_block);
+
+	/* Update the TCAM route entry */
+	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+					     &route->key, afa_block);
+	if (err)
+		goto err;
+
+	/* Delete the old one */
+	mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
+	route->afa_block = afa_block;
+	route->action = route_action;
+	return 0;
+err:
+	mlxsw_sp_mr_tcam_afa_block_destroy(afa_block);
+	return err;
+}
+
+static int mlxsw_sp_mr_tcam_route_min_mtu_update(struct mlxsw_sp *mlxsw_sp,
+						 void *route_priv, u16 min_mtu)
+{
+	struct mlxsw_sp_mr_tcam_route *route = route_priv;
+	struct mlxsw_afa_block *afa_block;
+	int err;
+
+	/* Create a new flexible action block */
+	afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp,
+						      route->action,
+						      route->irif_index,
+						      route->counter_index,
+						      min_mtu,
+						      &route->erif_list);
+	if (IS_ERR(afa_block))
+		return PTR_ERR(afa_block);
+
+	/* Update the TCAM route entry */
+	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+					     &route->key, afa_block);
+	if (err)
+		goto err;
+
+	/* Delete the old one */
+	mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
+	route->afa_block = afa_block;
+	route->min_mtu = min_mtu;
+	return 0;
+err:
+	mlxsw_sp_mr_tcam_afa_block_destroy(afa_block);
+	return err;
+}
+
+static int mlxsw_sp_mr_tcam_route_irif_update(struct mlxsw_sp *mlxsw_sp,
+					      void *route_priv, u16 irif_index)
+{
+	struct mlxsw_sp_mr_tcam_route *route = route_priv;
+
+	if (route->action != MLXSW_SP_MR_ROUTE_ACTION_TRAP)
+		return -EINVAL;
+	route->irif_index = irif_index;
+	return 0;
+}
+
+static int mlxsw_sp_mr_tcam_route_erif_add(struct mlxsw_sp *mlxsw_sp,
+					   void *route_priv, u16 erif_index)
+{
+	struct mlxsw_sp_mr_tcam_route *route = route_priv;
+	int err;
+
+	err = mlxsw_sp_mr_erif_list_add(mlxsw_sp, &route->erif_list,
+					erif_index);
+	if (err)
+		return err;
+
+	/* Commit the action only if the route action is not TRAP */
+	if (route->action != MLXSW_SP_MR_ROUTE_ACTION_TRAP)
+		return mlxsw_sp_mr_erif_list_commit(mlxsw_sp,
+						    &route->erif_list);
+	return 0;
+}
+
+static int mlxsw_sp_mr_tcam_route_erif_del(struct mlxsw_sp *mlxsw_sp,
+					   void *route_priv, u16 erif_index)
+{
+	struct mlxsw_sp_mr_tcam_route *route = route_priv;
+	struct mlxsw_sp_mr_erif_sublist *erif_sublist;
+	struct mlxsw_sp_mr_tcam_erif_list erif_list;
+	struct mlxsw_afa_block *afa_block;
+	int err;
+	int i;
+
+	/* Create a copy of the original erif_list without the deleted entry */
+	mlxsw_sp_mr_erif_list_init(&erif_list);
+	list_for_each_entry(erif_sublist, &route->erif_list.erif_sublists, list) {
+		for (i = 0; i < erif_sublist->num_erifs; i++) {
+			u16 curr_erif = erif_sublist->erif_indices[i];
+
+			if (curr_erif == erif_index)
+				continue;
+			err = mlxsw_sp_mr_erif_list_add(mlxsw_sp, &erif_list,
+							curr_erif);
+			if (err)
+				goto err_erif_list_add;
+		}
+	}
+
+	/* Create the flexible action block pointing to the new erif_list */
+	afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp, route->action,
+						      route->irif_index,
+						      route->counter_index,
+						      route->min_mtu,
+						      &erif_list);
+	if (IS_ERR(afa_block)) {
+		err = PTR_ERR(afa_block);
+		goto err_afa_block_create;
+	}
+
+	/* Update the TCAM route entry */
+	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+					     &route->key, afa_block);
+	if (err)
+		goto err_route_write;
+
+	mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
+	mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list);
+	route->afa_block = afa_block;
+	mlxsw_sp_mr_erif_list_move(&route->erif_list, &erif_list);
+	return 0;
+
+err_route_write:
+	mlxsw_sp_mr_tcam_afa_block_destroy(afa_block);
+err_afa_block_create:
+err_erif_list_add:
+	mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &erif_list);
+	return err;
+}
+
+static int
+mlxsw_sp_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+			      struct mlxsw_sp_mr_route_info *route_info)
+{
+	struct mlxsw_sp_mr_tcam_route *route = route_priv;
+	struct mlxsw_sp_mr_tcam_erif_list erif_list;
+	struct mlxsw_afa_block *afa_block;
+	int err;
+
+	/* Create a new erif_list */
+	mlxsw_sp_mr_erif_list_init(&erif_list);
+	err = mlxsw_sp_mr_tcam_erif_populate(mlxsw_sp, &erif_list, route_info);
+	if (err)
+		goto err_erif_populate;
+
+	/* Create the flexible action block pointing to the new erif_list */
+	afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp,
+						      route_info->route_action,
+						      route_info->irif_index,
+						      route->counter_index,
+						      route_info->min_mtu,
+						      &erif_list);
+	if (IS_ERR(afa_block)) {
+		err = PTR_ERR(afa_block);
+		goto err_afa_block_create;
+	}
+
+	/* Update the TCAM route entry */
+	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+					     &route->key, afa_block);
+	if (err)
+		goto err_route_write;
+
+	mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
+	mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list);
+	route->afa_block = afa_block;
+	mlxsw_sp_mr_erif_list_move(&route->erif_list, &erif_list);
+	route->action = route_info->route_action;
+	route->irif_index = route_info->irif_index;
+	route->min_mtu = route_info->min_mtu;
+	return 0;
+
+err_route_write:
+	mlxsw_sp_mr_tcam_afa_block_destroy(afa_block);
+err_afa_block_create:
+err_erif_populate:
+	mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &erif_list);
+	return err;
+}
+
+#define MLXSW_SP_MR_TCAM_REGION_BASE_COUNT 16
+#define MLXSW_SP_MR_TCAM_REGION_RESIZE_STEP 16
+
+static int
+mlxsw_sp_mr_tcam_region_alloc(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+	char rtar_pl[MLXSW_REG_RTAR_LEN];
+
+	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_ALLOCATE,
+			    mr_tcam_region->rtar_key_type,
+			    MLXSW_SP_MR_TCAM_REGION_BASE_COUNT);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static void
+mlxsw_sp_mr_tcam_region_free(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+	char rtar_pl[MLXSW_REG_RTAR_LEN];
+
+	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_DEALLOCATE,
+			    mr_tcam_region->rtar_key_type, 0);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static int mlxsw_sp_mr_tcam_region_parman_resize(void *priv,
+						 unsigned long new_count)
+{
+	struct mlxsw_sp_mr_tcam_region *mr_tcam_region = priv;
+	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+	char rtar_pl[MLXSW_REG_RTAR_LEN];
+	u64 max_tcam_rules;
+
+	max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
+	if (new_count > max_tcam_rules)
+		return -EINVAL;
+	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_RESIZE,
+			    mr_tcam_region->rtar_key_type, new_count);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static void mlxsw_sp_mr_tcam_region_parman_move(void *priv,
+						unsigned long from_index,
+						unsigned long to_index,
+						unsigned long count)
+{
+	struct mlxsw_sp_mr_tcam_region *mr_tcam_region = priv;
+	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+	char rrcr_pl[MLXSW_REG_RRCR_LEN];
+
+	mlxsw_reg_rrcr_pack(rrcr_pl, MLXSW_REG_RRCR_OP_MOVE,
+			    from_index, count,
+			    mr_tcam_region->rtar_key_type, to_index);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rrcr), rrcr_pl);
+}
+
+static const struct parman_ops mlxsw_sp_mr_tcam_region_parman_ops = {
+	.base_count	= MLXSW_SP_MR_TCAM_REGION_BASE_COUNT,
+	.resize_step	= MLXSW_SP_MR_TCAM_REGION_RESIZE_STEP,
+	.resize		= mlxsw_sp_mr_tcam_region_parman_resize,
+	.move		= mlxsw_sp_mr_tcam_region_parman_move,
+	.algo		= PARMAN_ALGO_TYPE_LSORT,
+};
+
+static int
+mlxsw_sp_mr_tcam_region_init(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_mr_tcam_region *mr_tcam_region,
+			     enum mlxsw_reg_rtar_key_type rtar_key_type)
+{
+	struct parman_prio *parman_prios;
+	struct parman *parman;
+	int err;
+	int i;
+
+	mr_tcam_region->rtar_key_type = rtar_key_type;
+	mr_tcam_region->mlxsw_sp = mlxsw_sp;
+
+	err = mlxsw_sp_mr_tcam_region_alloc(mr_tcam_region);
+	if (err)
+		return err;
+
+	parman = parman_create(&mlxsw_sp_mr_tcam_region_parman_ops,
+			       mr_tcam_region);
+	if (!parman) {
+		err = -ENOMEM;
+		goto err_parman_create;
+	}
+	mr_tcam_region->parman = parman;
+
+	parman_prios = kmalloc_array(MLXSW_SP_MR_ROUTE_PRIO_MAX + 1,
+				     sizeof(*parman_prios), GFP_KERNEL);
+	if (!parman_prios) {
+		err = -ENOMEM;
+		goto err_parman_prios_alloc;
+	}
+	mr_tcam_region->parman_prios = parman_prios;
+
+	for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
+		parman_prio_init(mr_tcam_region->parman,
+				 &mr_tcam_region->parman_prios[i], i);
+	return 0;
+
+err_parman_prios_alloc:
+	parman_destroy(parman);
+err_parman_create:
+	mlxsw_sp_mr_tcam_region_free(mr_tcam_region);
+	return err;
+}
+
+static void
+mlxsw_sp_mr_tcam_region_fini(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
+		parman_prio_fini(&mr_tcam_region->parman_prios[i]);
+	kfree(mr_tcam_region->parman_prios);
+	parman_destroy(mr_tcam_region->parman);
+	mlxsw_sp_mr_tcam_region_free(mr_tcam_region);
+}
+
+static int mlxsw_sp_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MC_ERIF_LIST_ENTRIES) ||
+	    !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_TCAM_RULES))
+		return -EIO;
+
+	return mlxsw_sp_mr_tcam_region_init(mlxsw_sp,
+					    &mr_tcam->ipv4_tcam_region,
+					    MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST);
+}
+
+static void mlxsw_sp_mr_tcam_fini(void *priv)
+{
+	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
+
+	mlxsw_sp_mr_tcam_region_fini(&mr_tcam->ipv4_tcam_region);
+}
+
+const struct mlxsw_sp_mr_ops mlxsw_sp_mr_tcam_ops = {
+	.priv_size = sizeof(struct mlxsw_sp_mr_tcam),
+	.route_priv_size = sizeof(struct mlxsw_sp_mr_tcam_route),
+	.init = mlxsw_sp_mr_tcam_init,
+	.route_create = mlxsw_sp_mr_tcam_route_create,
+	.route_update = mlxsw_sp_mr_tcam_route_update,
+	.route_stats = mlxsw_sp_mr_tcam_route_stats,
+	.route_action_update = mlxsw_sp_mr_tcam_route_action_update,
+	.route_min_mtu_update = mlxsw_sp_mr_tcam_route_min_mtu_update,
+	.route_irif_update = mlxsw_sp_mr_tcam_route_irif_update,
+	.route_erif_add = mlxsw_sp_mr_tcam_route_erif_add,
+	.route_erif_del = mlxsw_sp_mr_tcam_route_erif_del,
+	.route_destroy = mlxsw_sp_mr_tcam_route_destroy,
+	.fini = mlxsw_sp_mr_tcam_fini,
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
new file mode 100644
index 000000000000..f9b59ee25406
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
@@ -0,0 +1,43 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_SPECTRUM_MCROUTER_TCAM_H
+#define _MLXSW_SPECTRUM_MCROUTER_TCAM_H
+
+#include "spectrum.h"
+#include "spectrum_mr.h"
+
+extern const struct mlxsw_sp_mr_ops mlxsw_sp_mr_tcam_ops;
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 5189022a1c8c..e9187841d82a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -46,6 +46,8 @@
 #include <linux/if_bridge.h>
 #include <linux/socket.h>
 #include <linux/route.h>
+#include <linux/gcd.h>
+#include <linux/random.h>
 #include <net/netevent.h>
 #include <net/neighbour.h>
 #include <net/arp.h>
@@ -65,6 +67,8 @@
 #include "spectrum_cnt.h"
 #include "spectrum_dpipe.h"
 #include "spectrum_ipip.h"
+#include "spectrum_mr.h"
+#include "spectrum_mr_tcam.h"
 #include "spectrum_router.h"
 
 struct mlxsw_sp_vr;
@@ -78,6 +82,7 @@ struct mlxsw_sp_router {
 	struct rhashtable neigh_ht;
 	struct rhashtable nexthop_group_ht;
 	struct rhashtable nexthop_ht;
+	struct list_head nexthop_list;
 	struct {
 		struct mlxsw_sp_lpm_tree *trees;
 		unsigned int tree_count;
@@ -92,6 +97,7 @@ struct mlxsw_sp_router {
 	struct list_head ipip_list;
 	bool aborted;
 	struct notifier_block fib_nb;
+	struct notifier_block netevent_nb;
 	const struct mlxsw_sp_rif_ops **rif_ops_arr;
 	const struct mlxsw_sp_ipip_ops **ipip_ops_arr;
 };
@@ -458,6 +464,7 @@ struct mlxsw_sp_vr {
 	unsigned int rif_count;
 	struct mlxsw_sp_fib *fib4;
 	struct mlxsw_sp_fib *fib6;
+	struct mlxsw_sp_mr_table *mr4_table;
 };
 
 static const struct rhashtable_params mlxsw_sp_fib_ht_params;
@@ -652,7 +659,7 @@ static void mlxsw_sp_lpm_fini(struct mlxsw_sp *mlxsw_sp)
 
 static bool mlxsw_sp_vr_is_used(const struct mlxsw_sp_vr *vr)
 {
-	return !!vr->fib4 || !!vr->fib6;
+	return !!vr->fib4 || !!vr->fib6 || !!vr->mr4_table;
 }
 
 static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp)
@@ -692,8 +699,8 @@ static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp,
 
 static u32 mlxsw_sp_fix_tb_id(u32 tb_id)
 {
-	/* For our purpose, squash main and local table into one */
-	if (tb_id == RT_TABLE_LOCAL)
+	/* For our purpose, squash main, default and local tables into one */
+	if (tb_id == RT_TABLE_LOCAL || tb_id == RT_TABLE_DEFAULT)
 		tb_id = RT_TABLE_MAIN;
 	return tb_id;
 }
@@ -727,14 +734,17 @@ static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr,
 }
 
 static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
-					      u32 tb_id)
+					      u32 tb_id,
+					      struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_vr *vr;
 	int err;
 
 	vr = mlxsw_sp_vr_find_unused(mlxsw_sp);
-	if (!vr)
+	if (!vr) {
+		NL_SET_ERR_MSG(extack, "spectrum: Exceeded number of supported virtual routers");
 		return ERR_PTR(-EBUSY);
+	}
 	vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4);
 	if (IS_ERR(vr->fib4))
 		return ERR_CAST(vr->fib4);
@@ -743,9 +753,18 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
 		err = PTR_ERR(vr->fib6);
 		goto err_fib6_create;
 	}
+	vr->mr4_table = mlxsw_sp_mr_table_create(mlxsw_sp, vr->id,
+						 MLXSW_SP_L3_PROTO_IPV4);
+	if (IS_ERR(vr->mr4_table)) {
+		err = PTR_ERR(vr->mr4_table);
+		goto err_mr_table_create;
+	}
 	vr->tb_id = tb_id;
 	return vr;
 
+err_mr_table_create:
+	mlxsw_sp_fib_destroy(vr->fib6);
+	vr->fib6 = NULL;
 err_fib6_create:
 	mlxsw_sp_fib_destroy(vr->fib4);
 	vr->fib4 = NULL;
@@ -754,27 +773,31 @@ err_fib6_create:
 
 static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr)
 {
+	mlxsw_sp_mr_table_destroy(vr->mr4_table);
+	vr->mr4_table = NULL;
 	mlxsw_sp_fib_destroy(vr->fib6);
 	vr->fib6 = NULL;
 	mlxsw_sp_fib_destroy(vr->fib4);
 	vr->fib4 = NULL;
 }
 
-static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id)
+static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id,
+					   struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_vr *vr;
 
 	tb_id = mlxsw_sp_fix_tb_id(tb_id);
 	vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id);
 	if (!vr)
-		vr = mlxsw_sp_vr_create(mlxsw_sp, tb_id);
+		vr = mlxsw_sp_vr_create(mlxsw_sp, tb_id, extack);
 	return vr;
 }
 
 static void mlxsw_sp_vr_put(struct mlxsw_sp_vr *vr)
 {
 	if (!vr->rif_count && list_empty(&vr->fib4->node_list) &&
-	    list_empty(&vr->fib6->node_list))
+	    list_empty(&vr->fib6->node_list) &&
+	    mlxsw_sp_mr_table_empty(vr->mr4_table))
 		mlxsw_sp_vr_destroy(vr);
 }
 
@@ -920,7 +943,7 @@ __mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev)
 	return __dev_get_by_index(net, tun->parms.link);
 }
 
-static u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev)
+u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev)
 {
 	struct net_device *d = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev);
 
@@ -932,12 +955,14 @@ static u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev)
 
 static struct mlxsw_sp_rif *
 mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
-		    const struct mlxsw_sp_rif_params *params);
+		    const struct mlxsw_sp_rif_params *params,
+		    struct netlink_ext_ack *extack);
 
 static struct mlxsw_sp_rif_ipip_lb *
 mlxsw_sp_ipip_ol_ipip_lb_create(struct mlxsw_sp *mlxsw_sp,
 				enum mlxsw_sp_ipip_type ipipt,
-				struct net_device *ol_dev)
+				struct net_device *ol_dev,
+				struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_rif_params_ipip_lb lb_params;
 	const struct mlxsw_sp_ipip_ops *ipip_ops;
@@ -950,7 +975,7 @@ mlxsw_sp_ipip_ol_ipip_lb_create(struct mlxsw_sp *mlxsw_sp,
 		.lb_config = ipip_ops->ol_loopback_config(mlxsw_sp, ol_dev),
 	};
 
-	rif = mlxsw_sp_rif_create(mlxsw_sp, &lb_params.common);
+	rif = mlxsw_sp_rif_create(mlxsw_sp, &lb_params.common, extack);
 	if (IS_ERR(rif))
 		return ERR_CAST(rif);
 	return container_of(rif, struct mlxsw_sp_rif_ipip_lb, common);
@@ -969,7 +994,7 @@ mlxsw_sp_ipip_entry_alloc(struct mlxsw_sp *mlxsw_sp,
 		return ERR_PTR(-ENOMEM);
 
 	ipip_entry->ol_lb = mlxsw_sp_ipip_ol_ipip_lb_create(mlxsw_sp, ipipt,
-							    ol_dev);
+							    ol_dev, NULL);
 	if (IS_ERR(ipip_entry->ol_lb)) {
 		ret = ERR_CAST(ipip_entry->ol_lb);
 		goto err_ol_ipip_lb_create;
@@ -977,6 +1002,7 @@ mlxsw_sp_ipip_entry_alloc(struct mlxsw_sp *mlxsw_sp,
 
 	ipip_entry->ipipt = ipipt;
 	ipip_entry->ol_dev = ol_dev;
+	ipip_entry->parms = mlxsw_sp_ipip_netdev_parms(ol_dev);
 
 	return ipip_entry;
 
@@ -986,72 +1012,12 @@ err_ol_ipip_lb_create:
 }
 
 static void
-mlxsw_sp_ipip_entry_destroy(struct mlxsw_sp_ipip_entry *ipip_entry)
+mlxsw_sp_ipip_entry_dealloc(struct mlxsw_sp_ipip_entry *ipip_entry)
 {
-	WARN_ON(ipip_entry->ref_count > 0);
 	mlxsw_sp_rif_destroy(&ipip_entry->ol_lb->common);
 	kfree(ipip_entry);
 }
 
-static __be32
-mlxsw_sp_ipip_netdev_saddr4(const struct net_device *ol_dev)
-{
-	struct ip_tunnel *tun = netdev_priv(ol_dev);
-
-	return tun->parms.iph.saddr;
-}
-
-union mlxsw_sp_l3addr
-mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto,
-			   const struct net_device *ol_dev)
-{
-	switch (proto) {
-	case MLXSW_SP_L3_PROTO_IPV4:
-		return (union mlxsw_sp_l3addr) {
-			.addr4 = mlxsw_sp_ipip_netdev_saddr4(ol_dev),
-		};
-	case MLXSW_SP_L3_PROTO_IPV6:
-		break;
-	};
-
-	WARN_ON(1);
-	return (union mlxsw_sp_l3addr) {
-		.addr4 = 0,
-	};
-}
-
-__be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev)
-{
-	struct ip_tunnel *tun = netdev_priv(ol_dev);
-
-	return tun->parms.iph.daddr;
-}
-
-union mlxsw_sp_l3addr
-mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto,
-			   const struct net_device *ol_dev)
-{
-	switch (proto) {
-	case MLXSW_SP_L3_PROTO_IPV4:
-		return (union mlxsw_sp_l3addr) {
-			.addr4 = mlxsw_sp_ipip_netdev_daddr4(ol_dev),
-		};
-	case MLXSW_SP_L3_PROTO_IPV6:
-		break;
-	};
-
-	WARN_ON(1);
-	return (union mlxsw_sp_l3addr) {
-		.addr4 = 0,
-	};
-}
-
-static bool mlxsw_sp_l3addr_eq(const union mlxsw_sp_l3addr *addr1,
-			       const union mlxsw_sp_l3addr *addr2)
-{
-	return !memcmp(addr1, addr2, sizeof(*addr1));
-}
-
 static bool
 mlxsw_sp_ipip_entry_saddr_matches(struct mlxsw_sp *mlxsw_sp,
 				  const enum mlxsw_sp_l3proto ul_proto,
@@ -1184,60 +1150,28 @@ mlxsw_sp_ipip_entry_find_decap(struct mlxsw_sp *mlxsw_sp,
 }
 
 static struct mlxsw_sp_ipip_entry *
-mlxsw_sp_ipip_entry_get(struct mlxsw_sp *mlxsw_sp,
-			enum mlxsw_sp_ipip_type ipipt,
-			struct net_device *ol_dev)
+mlxsw_sp_ipip_entry_create(struct mlxsw_sp *mlxsw_sp,
+			   enum mlxsw_sp_ipip_type ipipt,
+			   struct net_device *ol_dev)
 {
-	u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev);
-	struct mlxsw_sp_router *router = mlxsw_sp->router;
-	struct mlxsw_sp_fib_entry *decap_fib_entry;
 	struct mlxsw_sp_ipip_entry *ipip_entry;
-	enum mlxsw_sp_l3proto ul_proto;
-	union mlxsw_sp_l3addr saddr;
-
-	list_for_each_entry(ipip_entry, &mlxsw_sp->router->ipip_list,
-			    ipip_list_node) {
-		if (ipip_entry->ol_dev == ol_dev)
-			goto inc_ref_count;
-
-		/* The configuration where several tunnels have the same local
-		 * address in the same underlay table needs special treatment in
-		 * the HW. That is currently not implemented in the driver.
-		 */
-		ul_proto = router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto;
-		saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev);
-		if (mlxsw_sp_ipip_entry_saddr_matches(mlxsw_sp, ul_proto, saddr,
-						      ul_tb_id, ipip_entry))
-			return ERR_PTR(-EEXIST);
-	}
 
 	ipip_entry = mlxsw_sp_ipip_entry_alloc(mlxsw_sp, ipipt, ol_dev);
 	if (IS_ERR(ipip_entry))
 		return ipip_entry;
 
-	decap_fib_entry = mlxsw_sp_ipip_entry_find_decap(mlxsw_sp, ipip_entry);
-	if (decap_fib_entry)
-		mlxsw_sp_ipip_entry_promote_decap(mlxsw_sp, ipip_entry,
-						  decap_fib_entry);
-
 	list_add_tail(&ipip_entry->ipip_list_node,
 		      &mlxsw_sp->router->ipip_list);
 
-inc_ref_count:
-	++ipip_entry->ref_count;
 	return ipip_entry;
 }
 
 static void
-mlxsw_sp_ipip_entry_put(struct mlxsw_sp *mlxsw_sp,
-			struct mlxsw_sp_ipip_entry *ipip_entry)
+mlxsw_sp_ipip_entry_destroy(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_ipip_entry *ipip_entry)
 {
-	if (--ipip_entry->ref_count == 0) {
-		list_del(&ipip_entry->ipip_list_node);
-		if (ipip_entry->decap_fib_entry)
-			mlxsw_sp_ipip_entry_demote_decap(mlxsw_sp, ipip_entry);
-		mlxsw_sp_ipip_entry_destroy(ipip_entry);
-	}
+	list_del(&ipip_entry->ipip_list_node);
+	mlxsw_sp_ipip_entry_dealloc(ipip_entry);
 }
 
 static bool
@@ -1279,6 +1213,455 @@ mlxsw_sp_ipip_entry_find_by_decap(struct mlxsw_sp *mlxsw_sp,
 	return NULL;
 }
 
+static bool mlxsw_sp_netdev_ipip_type(const struct mlxsw_sp *mlxsw_sp,
+				      const struct net_device *dev,
+				      enum mlxsw_sp_ipip_type *p_type)
+{
+	struct mlxsw_sp_router *router = mlxsw_sp->router;
+	const struct mlxsw_sp_ipip_ops *ipip_ops;
+	enum mlxsw_sp_ipip_type ipipt;
+
+	for (ipipt = 0; ipipt < MLXSW_SP_IPIP_TYPE_MAX; ++ipipt) {
+		ipip_ops = router->ipip_ops_arr[ipipt];
+		if (dev->type == ipip_ops->dev_type) {
+			if (p_type)
+				*p_type = ipipt;
+			return true;
+		}
+	}
+	return false;
+}
+
+bool mlxsw_sp_netdev_is_ipip_ol(const struct mlxsw_sp *mlxsw_sp,
+				const struct net_device *dev)
+{
+	return mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, NULL);
+}
+
+static struct mlxsw_sp_ipip_entry *
+mlxsw_sp_ipip_entry_find_by_ol_dev(struct mlxsw_sp *mlxsw_sp,
+				   const struct net_device *ol_dev)
+{
+	struct mlxsw_sp_ipip_entry *ipip_entry;
+
+	list_for_each_entry(ipip_entry, &mlxsw_sp->router->ipip_list,
+			    ipip_list_node)
+		if (ipip_entry->ol_dev == ol_dev)
+			return ipip_entry;
+
+	return NULL;
+}
+
+static struct mlxsw_sp_ipip_entry *
+mlxsw_sp_ipip_entry_find_by_ul_dev(const struct mlxsw_sp *mlxsw_sp,
+				   const struct net_device *ul_dev,
+				   struct mlxsw_sp_ipip_entry *start)
+{
+	struct mlxsw_sp_ipip_entry *ipip_entry;
+
+	ipip_entry = list_prepare_entry(start, &mlxsw_sp->router->ipip_list,
+					ipip_list_node);
+	list_for_each_entry_continue(ipip_entry, &mlxsw_sp->router->ipip_list,
+				     ipip_list_node) {
+		struct net_device *ipip_ul_dev =
+			__mlxsw_sp_ipip_netdev_ul_dev_get(ipip_entry->ol_dev);
+
+		if (ipip_ul_dev == ul_dev)
+			return ipip_entry;
+	}
+
+	return NULL;
+}
+
+bool mlxsw_sp_netdev_is_ipip_ul(const struct mlxsw_sp *mlxsw_sp,
+				const struct net_device *dev)
+{
+	return mlxsw_sp_ipip_entry_find_by_ul_dev(mlxsw_sp, dev, NULL);
+}
+
+static bool mlxsw_sp_netdevice_ipip_can_offload(struct mlxsw_sp *mlxsw_sp,
+						const struct net_device *ol_dev,
+						enum mlxsw_sp_ipip_type ipipt)
+{
+	const struct mlxsw_sp_ipip_ops *ops
+		= mlxsw_sp->router->ipip_ops_arr[ipipt];
+
+	/* For deciding whether decap should be offloaded, we don't care about
+	 * overlay protocol, so ask whether either one is supported.
+	 */
+	return ops->can_offload(mlxsw_sp, ol_dev, MLXSW_SP_L3_PROTO_IPV4) ||
+	       ops->can_offload(mlxsw_sp, ol_dev, MLXSW_SP_L3_PROTO_IPV6);
+}
+
+static int mlxsw_sp_netdevice_ipip_ol_reg_event(struct mlxsw_sp *mlxsw_sp,
+						struct net_device *ol_dev)
+{
+	struct mlxsw_sp_ipip_entry *ipip_entry;
+	enum mlxsw_sp_l3proto ul_proto;
+	enum mlxsw_sp_ipip_type ipipt;
+	union mlxsw_sp_l3addr saddr;
+	u32 ul_tb_id;
+
+	mlxsw_sp_netdev_ipip_type(mlxsw_sp, ol_dev, &ipipt);
+	if (mlxsw_sp_netdevice_ipip_can_offload(mlxsw_sp, ol_dev, ipipt)) {
+		ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev);
+		ul_proto = mlxsw_sp->router->ipip_ops_arr[ipipt]->ul_proto;
+		saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev);
+		if (!mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, ul_proto,
+							  saddr, ul_tb_id,
+							  NULL)) {
+			ipip_entry = mlxsw_sp_ipip_entry_create(mlxsw_sp, ipipt,
+								ol_dev);
+			if (IS_ERR(ipip_entry))
+				return PTR_ERR(ipip_entry);
+		}
+	}
+
+	return 0;
+}
+
+static void mlxsw_sp_netdevice_ipip_ol_unreg_event(struct mlxsw_sp *mlxsw_sp,
+						   struct net_device *ol_dev)
+{
+	struct mlxsw_sp_ipip_entry *ipip_entry;
+
+	ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
+	if (ipip_entry)
+		mlxsw_sp_ipip_entry_destroy(mlxsw_sp, ipip_entry);
+}
+
+static void
+mlxsw_sp_ipip_entry_ol_up_event(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_ipip_entry *ipip_entry)
+{
+	struct mlxsw_sp_fib_entry *decap_fib_entry;
+
+	decap_fib_entry = mlxsw_sp_ipip_entry_find_decap(mlxsw_sp, ipip_entry);
+	if (decap_fib_entry)
+		mlxsw_sp_ipip_entry_promote_decap(mlxsw_sp, ipip_entry,
+						  decap_fib_entry);
+}
+
+static void mlxsw_sp_netdevice_ipip_ol_up_event(struct mlxsw_sp *mlxsw_sp,
+						struct net_device *ol_dev)
+{
+	struct mlxsw_sp_ipip_entry *ipip_entry;
+
+	ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
+	if (ipip_entry)
+		mlxsw_sp_ipip_entry_ol_up_event(mlxsw_sp, ipip_entry);
+}
+
+static void
+mlxsw_sp_ipip_entry_ol_down_event(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_ipip_entry *ipip_entry)
+{
+	if (ipip_entry->decap_fib_entry)
+		mlxsw_sp_ipip_entry_demote_decap(mlxsw_sp, ipip_entry);
+}
+
+static void mlxsw_sp_netdevice_ipip_ol_down_event(struct mlxsw_sp *mlxsw_sp,
+						  struct net_device *ol_dev)
+{
+	struct mlxsw_sp_ipip_entry *ipip_entry;
+
+	ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
+	if (ipip_entry)
+		mlxsw_sp_ipip_entry_ol_down_event(mlxsw_sp, ipip_entry);
+}
+
+static void mlxsw_sp_nexthop_rif_update(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_rif *rif);
+static int
+mlxsw_sp_ipip_entry_ol_lb_update(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_ipip_entry *ipip_entry,
+				 bool keep_encap,
+				 struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_rif_ipip_lb *old_lb_rif = ipip_entry->ol_lb;
+	struct mlxsw_sp_rif_ipip_lb *new_lb_rif;
+
+	new_lb_rif = mlxsw_sp_ipip_ol_ipip_lb_create(mlxsw_sp,
+						     ipip_entry->ipipt,
+						     ipip_entry->ol_dev,
+						     extack);
+	if (IS_ERR(new_lb_rif))
+		return PTR_ERR(new_lb_rif);
+	ipip_entry->ol_lb = new_lb_rif;
+
+	if (keep_encap) {
+		list_splice_init(&old_lb_rif->common.nexthop_list,
+				 &new_lb_rif->common.nexthop_list);
+		mlxsw_sp_nexthop_rif_update(mlxsw_sp, &new_lb_rif->common);
+	}
+
+	mlxsw_sp_rif_destroy(&old_lb_rif->common);
+
+	return 0;
+}
+
+/**
+ * Update the offload related to an IPIP entry. This always updates decap, and
+ * in addition to that it also:
+ * @recreate_loopback: recreates the associated loopback RIF
+ * @keep_encap: updates next hops that use the tunnel netdevice. This is only
+ *              relevant when recreate_loopback is true.
+ * @update_nexthops: updates next hops, keeping the current loopback RIF. This
+ *                   is only relevant when recreate_loopback is false.
+ */
+int __mlxsw_sp_ipip_entry_update_tunnel(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_ipip_entry *ipip_entry,
+					bool recreate_loopback,
+					bool keep_encap,
+					bool update_nexthops,
+					struct netlink_ext_ack *extack)
+{
+	int err;
+
+	/* RIFs can't be edited, so to update loopback, we need to destroy and
+	 * recreate it. That creates a window of opportunity where RALUE and
+	 * RATR registers end up referencing a RIF that's already gone. RATRs
+	 * are handled in mlxsw_sp_ipip_entry_ol_lb_update(), and to take care
+	 * of RALUE, demote the decap route back.
+	 */
+	if (ipip_entry->decap_fib_entry)
+		mlxsw_sp_ipip_entry_demote_decap(mlxsw_sp, ipip_entry);
+
+	if (recreate_loopback) {
+		err = mlxsw_sp_ipip_entry_ol_lb_update(mlxsw_sp, ipip_entry,
+						       keep_encap, extack);
+		if (err)
+			return err;
+	} else if (update_nexthops) {
+		mlxsw_sp_nexthop_rif_update(mlxsw_sp,
+					    &ipip_entry->ol_lb->common);
+	}
+
+	if (ipip_entry->ol_dev->flags & IFF_UP)
+		mlxsw_sp_ipip_entry_ol_up_event(mlxsw_sp, ipip_entry);
+
+	return 0;
+}
+
+static int mlxsw_sp_netdevice_ipip_ol_vrf_event(struct mlxsw_sp *mlxsw_sp,
+						struct net_device *ol_dev,
+						struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_ipip_entry *ipip_entry =
+		mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
+
+	if (!ipip_entry)
+		return 0;
+	return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry,
+						   true, false, false, extack);
+}
+
+static int
+mlxsw_sp_netdevice_ipip_ul_vrf_event(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_ipip_entry *ipip_entry,
+				     struct net_device *ul_dev,
+				     struct netlink_ext_ack *extack)
+{
+	return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry,
+						   true, true, false, extack);
+}
+
+static int
+mlxsw_sp_netdevice_ipip_ul_up_event(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_ipip_entry *ipip_entry,
+				    struct net_device *ul_dev)
+{
+	return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry,
+						   false, false, true, NULL);
+}
+
+static int
+mlxsw_sp_netdevice_ipip_ul_down_event(struct mlxsw_sp *mlxsw_sp,
+				      struct mlxsw_sp_ipip_entry *ipip_entry,
+				      struct net_device *ul_dev)
+{
+	/* A down underlay device causes encapsulated packets to not be
+	 * forwarded, but decap still works. So refresh next hops without
+	 * touching anything else.
+	 */
+	return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry,
+						   false, false, true, NULL);
+}
+
+static int
+mlxsw_sp_netdevice_ipip_ol_change_event(struct mlxsw_sp *mlxsw_sp,
+					struct net_device *ol_dev,
+					struct netlink_ext_ack *extack)
+{
+	const struct mlxsw_sp_ipip_ops *ipip_ops;
+	struct mlxsw_sp_ipip_entry *ipip_entry;
+	int err;
+
+	ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
+	if (!ipip_entry)
+		/* A change might make a tunnel eligible for offloading, but
+		 * that is currently not implemented. What falls to slow path
+		 * stays there.
+		 */
+		return 0;
+
+	/* A change might make a tunnel not eligible for offloading. */
+	if (!mlxsw_sp_netdevice_ipip_can_offload(mlxsw_sp, ol_dev,
+						 ipip_entry->ipipt)) {
+		mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry);
+		return 0;
+	}
+
+	ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt];
+	err = ipip_ops->ol_netdev_change(mlxsw_sp, ipip_entry, extack);
+	return err;
+}
+
+void mlxsw_sp_ipip_entry_demote_tunnel(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_ipip_entry *ipip_entry)
+{
+	struct net_device *ol_dev = ipip_entry->ol_dev;
+
+	if (ol_dev->flags & IFF_UP)
+		mlxsw_sp_ipip_entry_ol_down_event(mlxsw_sp, ipip_entry);
+	mlxsw_sp_ipip_entry_destroy(mlxsw_sp, ipip_entry);
+}
+
+/* The configuration where several tunnels have the same local address in the
+ * same underlay table needs special treatment in the HW. That is currently not
+ * implemented in the driver. This function finds and demotes the first tunnel
+ * with a given source address, except the one passed in in the argument
+ * `except'.
+ */
+bool
+mlxsw_sp_ipip_demote_tunnel_by_saddr(struct mlxsw_sp *mlxsw_sp,
+				     enum mlxsw_sp_l3proto ul_proto,
+				     union mlxsw_sp_l3addr saddr,
+				     u32 ul_tb_id,
+				     const struct mlxsw_sp_ipip_entry *except)
+{
+	struct mlxsw_sp_ipip_entry *ipip_entry, *tmp;
+
+	list_for_each_entry_safe(ipip_entry, tmp, &mlxsw_sp->router->ipip_list,
+				 ipip_list_node) {
+		if (ipip_entry != except &&
+		    mlxsw_sp_ipip_entry_saddr_matches(mlxsw_sp, ul_proto, saddr,
+						      ul_tb_id, ipip_entry)) {
+			mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry);
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static void mlxsw_sp_ipip_demote_tunnel_by_ul_netdev(struct mlxsw_sp *mlxsw_sp,
+						     struct net_device *ul_dev)
+{
+	struct mlxsw_sp_ipip_entry *ipip_entry, *tmp;
+
+	list_for_each_entry_safe(ipip_entry, tmp, &mlxsw_sp->router->ipip_list,
+				 ipip_list_node) {
+		struct net_device *ipip_ul_dev =
+			__mlxsw_sp_ipip_netdev_ul_dev_get(ipip_entry->ol_dev);
+
+		if (ipip_ul_dev == ul_dev)
+			mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry);
+	}
+}
+
+int mlxsw_sp_netdevice_ipip_ol_event(struct mlxsw_sp *mlxsw_sp,
+				     struct net_device *ol_dev,
+				     unsigned long event,
+				     struct netdev_notifier_info *info)
+{
+	struct netdev_notifier_changeupper_info *chup;
+	struct netlink_ext_ack *extack;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		return mlxsw_sp_netdevice_ipip_ol_reg_event(mlxsw_sp, ol_dev);
+	case NETDEV_UNREGISTER:
+		mlxsw_sp_netdevice_ipip_ol_unreg_event(mlxsw_sp, ol_dev);
+		return 0;
+	case NETDEV_UP:
+		mlxsw_sp_netdevice_ipip_ol_up_event(mlxsw_sp, ol_dev);
+		return 0;
+	case NETDEV_DOWN:
+		mlxsw_sp_netdevice_ipip_ol_down_event(mlxsw_sp, ol_dev);
+		return 0;
+	case NETDEV_CHANGEUPPER:
+		chup = container_of(info, typeof(*chup), info);
+		extack = info->extack;
+		if (netif_is_l3_master(chup->upper_dev))
+			return mlxsw_sp_netdevice_ipip_ol_vrf_event(mlxsw_sp,
+								    ol_dev,
+								    extack);
+		return 0;
+	case NETDEV_CHANGE:
+		extack = info->extack;
+		return mlxsw_sp_netdevice_ipip_ol_change_event(mlxsw_sp,
+							       ol_dev, extack);
+	}
+	return 0;
+}
+
+static int
+__mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_ipip_entry *ipip_entry,
+				   struct net_device *ul_dev,
+				   unsigned long event,
+				   struct netdev_notifier_info *info)
+{
+	struct netdev_notifier_changeupper_info *chup;
+	struct netlink_ext_ack *extack;
+
+	switch (event) {
+	case NETDEV_CHANGEUPPER:
+		chup = container_of(info, typeof(*chup), info);
+		extack = info->extack;
+		if (netif_is_l3_master(chup->upper_dev))
+			return mlxsw_sp_netdevice_ipip_ul_vrf_event(mlxsw_sp,
+								    ipip_entry,
+								    ul_dev,
+								    extack);
+		break;
+
+	case NETDEV_UP:
+		return mlxsw_sp_netdevice_ipip_ul_up_event(mlxsw_sp, ipip_entry,
+							   ul_dev);
+	case NETDEV_DOWN:
+		return mlxsw_sp_netdevice_ipip_ul_down_event(mlxsw_sp,
+							     ipip_entry,
+							     ul_dev);
+	}
+	return 0;
+}
+
+int
+mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp,
+				 struct net_device *ul_dev,
+				 unsigned long event,
+				 struct netdev_notifier_info *info)
+{
+	struct mlxsw_sp_ipip_entry *ipip_entry = NULL;
+	int err;
+
+	while ((ipip_entry = mlxsw_sp_ipip_entry_find_by_ul_dev(mlxsw_sp,
+								ul_dev,
+								ipip_entry))) {
+		err = __mlxsw_sp_netdevice_ipip_ul_event(mlxsw_sp, ipip_entry,
+							 ul_dev, event, info);
+		if (err) {
+			mlxsw_sp_ipip_demote_tunnel_by_ul_netdev(mlxsw_sp,
+								 ul_dev);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
 struct mlxsw_sp_neigh_key {
 	struct neighbour *n;
 };
@@ -1316,7 +1699,7 @@ mlxsw_sp_rif_neigh_next(struct mlxsw_sp_rif *rif,
 						typeof(*neigh_entry),
 						rif_list_node);
 	}
-	if (neigh_entry->rif_list_node.next == &rif->neigh_list)
+	if (list_is_last(&neigh_entry->rif_list_node, &rif->neigh_list))
 		return NULL;
 	return list_next_entry(neigh_entry, rif_list_node);
 }
@@ -1664,7 +2047,7 @@ __mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp,
 		err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(rauhtd),
 				      rauhtd_pl);
 		if (err) {
-			dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to dump neighbour talbe\n");
+			dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to dump neighbour table\n");
 			break;
 		}
 		num_rec = mlxsw_reg_rauhtd_num_rec_get(rauhtd_pl);
@@ -1857,7 +2240,7 @@ mlxsw_sp_neigh_entry_counter_update(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_neigh_entry_update(mlxsw_sp, neigh_entry, true);
 }
 
-struct mlxsw_sp_neigh_event_work {
+struct mlxsw_sp_netevent_work {
 	struct work_struct work;
 	struct mlxsw_sp *mlxsw_sp;
 	struct neighbour *n;
@@ -1865,11 +2248,11 @@ struct mlxsw_sp_neigh_event_work {
 
 static void mlxsw_sp_router_neigh_event_work(struct work_struct *work)
 {
-	struct mlxsw_sp_neigh_event_work *neigh_work =
-		container_of(work, struct mlxsw_sp_neigh_event_work, work);
-	struct mlxsw_sp *mlxsw_sp = neigh_work->mlxsw_sp;
+	struct mlxsw_sp_netevent_work *net_work =
+		container_of(work, struct mlxsw_sp_netevent_work, work);
+	struct mlxsw_sp *mlxsw_sp = net_work->mlxsw_sp;
 	struct mlxsw_sp_neigh_entry *neigh_entry;
-	struct neighbour *n = neigh_work->n;
+	struct neighbour *n = net_work->n;
 	unsigned char ha[ETH_ALEN];
 	bool entry_connected;
 	u8 nud_state, dead;
@@ -1905,18 +2288,32 @@ static void mlxsw_sp_router_neigh_event_work(struct work_struct *work)
 out:
 	rtnl_unlock();
 	neigh_release(n);
-	kfree(neigh_work);
+	kfree(net_work);
 }
 
-int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
-				   unsigned long event, void *ptr)
+static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp);
+
+static void mlxsw_sp_router_mp_hash_event_work(struct work_struct *work)
+{
+	struct mlxsw_sp_netevent_work *net_work =
+		container_of(work, struct mlxsw_sp_netevent_work, work);
+	struct mlxsw_sp *mlxsw_sp = net_work->mlxsw_sp;
+
+	mlxsw_sp_mp_hash_init(mlxsw_sp);
+	kfree(net_work);
+}
+
+static int mlxsw_sp_router_netevent_event(struct notifier_block *nb,
+					  unsigned long event, void *ptr)
 {
-	struct mlxsw_sp_neigh_event_work *neigh_work;
+	struct mlxsw_sp_netevent_work *net_work;
 	struct mlxsw_sp_port *mlxsw_sp_port;
+	struct mlxsw_sp_router *router;
 	struct mlxsw_sp *mlxsw_sp;
 	unsigned long interval;
 	struct neigh_parms *p;
 	struct neighbour *n;
+	struct net *net;
 
 	switch (event) {
 	case NETEVENT_DELAY_PROBE_TIME_UPDATE:
@@ -1950,24 +2347,39 @@ int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
 		if (!mlxsw_sp_port)
 			return NOTIFY_DONE;
 
-		neigh_work = kzalloc(sizeof(*neigh_work), GFP_ATOMIC);
-		if (!neigh_work) {
+		net_work = kzalloc(sizeof(*net_work), GFP_ATOMIC);
+		if (!net_work) {
 			mlxsw_sp_port_dev_put(mlxsw_sp_port);
 			return NOTIFY_BAD;
 		}
 
-		INIT_WORK(&neigh_work->work, mlxsw_sp_router_neigh_event_work);
-		neigh_work->mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-		neigh_work->n = n;
+		INIT_WORK(&net_work->work, mlxsw_sp_router_neigh_event_work);
+		net_work->mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+		net_work->n = n;
 
 		/* Take a reference to ensure the neighbour won't be
 		 * destructed until we drop the reference in delayed
 		 * work.
 		 */
 		neigh_clone(n);
-		mlxsw_core_schedule_work(&neigh_work->work);
+		mlxsw_core_schedule_work(&net_work->work);
 		mlxsw_sp_port_dev_put(mlxsw_sp_port);
 		break;
+	case NETEVENT_MULTIPATH_HASH_UPDATE:
+		net = ptr;
+
+		if (!net_eq(net, &init_net))
+			return NOTIFY_DONE;
+
+		net_work = kzalloc(sizeof(*net_work), GFP_ATOMIC);
+		if (!net_work)
+			return NOTIFY_BAD;
+
+		router = container_of(nb, struct mlxsw_sp_router, netevent_nb);
+		INIT_WORK(&net_work->work, mlxsw_sp_router_mp_hash_event_work);
+		net_work->mlxsw_sp = router->mlxsw_sp;
+		mlxsw_core_schedule_work(&net_work->work);
+		break;
 	}
 
 	return NOTIFY_DONE;
@@ -2028,6 +2440,7 @@ struct mlxsw_sp_nexthop_key {
 struct mlxsw_sp_nexthop {
 	struct list_head neigh_list_node; /* member of neigh entry list */
 	struct list_head rif_list_node;
+	struct list_head router_list_node;
 	struct mlxsw_sp_nexthop_group *nh_grp; /* pointer back to the group
 						* this belongs to
 						*/
@@ -2035,6 +2448,9 @@ struct mlxsw_sp_nexthop {
 	struct mlxsw_sp_nexthop_key key;
 	unsigned char gw_addr[sizeof(struct in6_addr)];
 	int ifindex;
+	int nh_weight;
+	int norm_nh_weight;
+	int num_adj_entries;
 	struct mlxsw_sp_rif *rif;
 	u8 should_offload:1, /* set indicates this neigh is connected and
 			      * should be put to KVD linear area of this group.
@@ -2050,6 +2466,8 @@ struct mlxsw_sp_nexthop {
 		struct mlxsw_sp_neigh_entry *neigh_entry;
 		struct mlxsw_sp_ipip_entry *ipip_entry;
 	};
+	unsigned int counter_index;
+	bool counter_valid;
 };
 
 struct mlxsw_sp_nexthop_group {
@@ -2062,10 +2480,118 @@ struct mlxsw_sp_nexthop_group {
 	u32 adj_index;
 	u16 ecmp_size;
 	u16 count;
+	int sum_norm_weight;
 	struct mlxsw_sp_nexthop nexthops[0];
 #define nh_rif	nexthops[0].rif
 };
 
+void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_nexthop *nh)
+{
+	struct devlink *devlink;
+
+	devlink = priv_to_devlink(mlxsw_sp->core);
+	if (!devlink_dpipe_table_counter_enabled(devlink,
+						 MLXSW_SP_DPIPE_TABLE_NAME_ADJ))
+		return;
+
+	if (mlxsw_sp_flow_counter_alloc(mlxsw_sp, &nh->counter_index))
+		return;
+
+	nh->counter_valid = true;
+}
+
+void mlxsw_sp_nexthop_counter_free(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_nexthop *nh)
+{
+	if (!nh->counter_valid)
+		return;
+	mlxsw_sp_flow_counter_free(mlxsw_sp, nh->counter_index);
+	nh->counter_valid = false;
+}
+
+int mlxsw_sp_nexthop_counter_get(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_nexthop *nh, u64 *p_counter)
+{
+	if (!nh->counter_valid)
+		return -EINVAL;
+
+	return mlxsw_sp_flow_counter_get(mlxsw_sp, nh->counter_index,
+					 p_counter, NULL);
+}
+
+struct mlxsw_sp_nexthop *mlxsw_sp_nexthop_next(struct mlxsw_sp_router *router,
+					       struct mlxsw_sp_nexthop *nh)
+{
+	if (!nh) {
+		if (list_empty(&router->nexthop_list))
+			return NULL;
+		else
+			return list_first_entry(&router->nexthop_list,
+						typeof(*nh), router_list_node);
+	}
+	if (list_is_last(&nh->router_list_node, &router->nexthop_list))
+		return NULL;
+	return list_next_entry(nh, router_list_node);
+}
+
+bool mlxsw_sp_nexthop_offload(struct mlxsw_sp_nexthop *nh)
+{
+	return nh->offloaded;
+}
+
+unsigned char *mlxsw_sp_nexthop_ha(struct mlxsw_sp_nexthop *nh)
+{
+	if (!nh->offloaded)
+		return NULL;
+	return nh->neigh_entry->ha;
+}
+
+int mlxsw_sp_nexthop_indexes(struct mlxsw_sp_nexthop *nh, u32 *p_adj_index,
+			     u32 *p_adj_size, u32 *p_adj_hash_index)
+{
+	struct mlxsw_sp_nexthop_group *nh_grp = nh->nh_grp;
+	u32 adj_hash_index = 0;
+	int i;
+
+	if (!nh->offloaded || !nh_grp->adj_index_valid)
+		return -EINVAL;
+
+	*p_adj_index = nh_grp->adj_index;
+	*p_adj_size = nh_grp->ecmp_size;
+
+	for (i = 0; i < nh_grp->count; i++) {
+		struct mlxsw_sp_nexthop *nh_iter = &nh_grp->nexthops[i];
+
+		if (nh_iter == nh)
+			break;
+		if (nh_iter->offloaded)
+			adj_hash_index += nh_iter->num_adj_entries;
+	}
+
+	*p_adj_hash_index = adj_hash_index;
+	return 0;
+}
+
+struct mlxsw_sp_rif *mlxsw_sp_nexthop_rif(struct mlxsw_sp_nexthop *nh)
+{
+	return nh->rif;
+}
+
+bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh)
+{
+	struct mlxsw_sp_nexthop_group *nh_grp = nh->nh_grp;
+	int i;
+
+	for (i = 0; i < nh_grp->count; i++) {
+		struct mlxsw_sp_nexthop *nh_iter = &nh_grp->nexthops[i];
+
+		if (nh_iter->type == MLXSW_SP_NEXTHOP_TYPE_IPIP)
+			return true;
+	}
+	return false;
+}
+
 static struct fib_info *
 mlxsw_sp_nexthop4_group_fi(const struct mlxsw_sp_nexthop_group *nh_grp)
 {
@@ -2323,8 +2849,8 @@ static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
-static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
-				       struct mlxsw_sp_nexthop *nh)
+static int __mlxsw_sp_nexthop_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
+				     struct mlxsw_sp_nexthop *nh)
 {
 	struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry;
 	char ratr_pl[MLXSW_REG_RATR_LEN];
@@ -2333,12 +2859,33 @@ static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
 			    true, MLXSW_REG_RATR_TYPE_ETHERNET,
 			    adj_index, neigh_entry->rif);
 	mlxsw_reg_ratr_eth_entry_pack(ratr_pl, neigh_entry->ha);
+	if (nh->counter_valid)
+		mlxsw_reg_ratr_counter_pack(ratr_pl, nh->counter_index, true);
+	else
+		mlxsw_reg_ratr_counter_pack(ratr_pl, 0, false);
+
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl);
 }
 
-static int mlxsw_sp_nexthop_ipip_update(struct mlxsw_sp *mlxsw_sp,
-					u32 adj_index,
-					struct mlxsw_sp_nexthop *nh)
+int mlxsw_sp_nexthop_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
+			    struct mlxsw_sp_nexthop *nh)
+{
+	int i;
+
+	for (i = 0; i < nh->num_adj_entries; i++) {
+		int err;
+
+		err = __mlxsw_sp_nexthop_update(mlxsw_sp, adj_index + i, nh);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int __mlxsw_sp_nexthop_ipip_update(struct mlxsw_sp *mlxsw_sp,
+					  u32 adj_index,
+					  struct mlxsw_sp_nexthop *nh)
 {
 	const struct mlxsw_sp_ipip_ops *ipip_ops;
 
@@ -2346,6 +2893,24 @@ static int mlxsw_sp_nexthop_ipip_update(struct mlxsw_sp *mlxsw_sp,
 	return ipip_ops->nexthop_update(mlxsw_sp, adj_index, nh->ipip_entry);
 }
 
+static int mlxsw_sp_nexthop_ipip_update(struct mlxsw_sp *mlxsw_sp,
+					u32 adj_index,
+					struct mlxsw_sp_nexthop *nh)
+{
+	int i;
+
+	for (i = 0; i < nh->num_adj_entries; i++) {
+		int err;
+
+		err = __mlxsw_sp_nexthop_ipip_update(mlxsw_sp, adj_index + i,
+						     nh);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int
 mlxsw_sp_nexthop_group_update(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_nexthop_group *nh_grp,
@@ -2367,7 +2932,7 @@ mlxsw_sp_nexthop_group_update(struct mlxsw_sp *mlxsw_sp,
 		if (nh->update || reallocate) {
 			switch (nh->type) {
 			case MLXSW_SP_NEXTHOP_TYPE_ETH:
-				err = mlxsw_sp_nexthop_mac_update
+				err = mlxsw_sp_nexthop_update
 					    (mlxsw_sp, adj_index, nh);
 				break;
 			case MLXSW_SP_NEXTHOP_TYPE_IPIP:
@@ -2380,7 +2945,7 @@ mlxsw_sp_nexthop_group_update(struct mlxsw_sp *mlxsw_sp,
 			nh->update = 0;
 			nh->offloaded = 1;
 		}
-		adj_index++;
+		adj_index += nh->num_adj_entries;
 	}
 	return 0;
 }
@@ -2425,17 +2990,118 @@ mlxsw_sp_nexthop_fib_entries_refresh(struct mlxsw_sp_nexthop_group *nh_grp)
 	}
 }
 
+static void mlxsw_sp_adj_grp_size_round_up(u16 *p_adj_grp_size)
+{
+	/* Valid sizes for an adjacency group are:
+	 * 1-64, 512, 1024, 2048 and 4096.
+	 */
+	if (*p_adj_grp_size <= 64)
+		return;
+	else if (*p_adj_grp_size <= 512)
+		*p_adj_grp_size = 512;
+	else if (*p_adj_grp_size <= 1024)
+		*p_adj_grp_size = 1024;
+	else if (*p_adj_grp_size <= 2048)
+		*p_adj_grp_size = 2048;
+	else
+		*p_adj_grp_size = 4096;
+}
+
+static void mlxsw_sp_adj_grp_size_round_down(u16 *p_adj_grp_size,
+					     unsigned int alloc_size)
+{
+	if (alloc_size >= 4096)
+		*p_adj_grp_size = 4096;
+	else if (alloc_size >= 2048)
+		*p_adj_grp_size = 2048;
+	else if (alloc_size >= 1024)
+		*p_adj_grp_size = 1024;
+	else if (alloc_size >= 512)
+		*p_adj_grp_size = 512;
+}
+
+static int mlxsw_sp_fix_adj_grp_size(struct mlxsw_sp *mlxsw_sp,
+				     u16 *p_adj_grp_size)
+{
+	unsigned int alloc_size;
+	int err;
+
+	/* Round up the requested group size to the next size supported
+	 * by the device and make sure the request can be satisfied.
+	 */
+	mlxsw_sp_adj_grp_size_round_up(p_adj_grp_size);
+	err = mlxsw_sp_kvdl_alloc_size_query(mlxsw_sp, *p_adj_grp_size,
+					     &alloc_size);
+	if (err)
+		return err;
+	/* It is possible the allocation results in more allocated
+	 * entries than requested. Try to use as much of them as
+	 * possible.
+	 */
+	mlxsw_sp_adj_grp_size_round_down(p_adj_grp_size, alloc_size);
+
+	return 0;
+}
+
+static void
+mlxsw_sp_nexthop_group_normalize(struct mlxsw_sp_nexthop_group *nh_grp)
+{
+	int i, g = 0, sum_norm_weight = 0;
+	struct mlxsw_sp_nexthop *nh;
+
+	for (i = 0; i < nh_grp->count; i++) {
+		nh = &nh_grp->nexthops[i];
+
+		if (!nh->should_offload)
+			continue;
+		if (g > 0)
+			g = gcd(nh->nh_weight, g);
+		else
+			g = nh->nh_weight;
+	}
+
+	for (i = 0; i < nh_grp->count; i++) {
+		nh = &nh_grp->nexthops[i];
+
+		if (!nh->should_offload)
+			continue;
+		nh->norm_nh_weight = nh->nh_weight / g;
+		sum_norm_weight += nh->norm_nh_weight;
+	}
+
+	nh_grp->sum_norm_weight = sum_norm_weight;
+}
+
+static void
+mlxsw_sp_nexthop_group_rebalance(struct mlxsw_sp_nexthop_group *nh_grp)
+{
+	int total = nh_grp->sum_norm_weight;
+	u16 ecmp_size = nh_grp->ecmp_size;
+	int i, weight = 0, lower_bound = 0;
+
+	for (i = 0; i < nh_grp->count; i++) {
+		struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
+		int upper_bound;
+
+		if (!nh->should_offload)
+			continue;
+		weight += nh->norm_nh_weight;
+		upper_bound = DIV_ROUND_CLOSEST(ecmp_size * weight, total);
+		nh->num_adj_entries = upper_bound - lower_bound;
+		lower_bound = upper_bound;
+	}
+}
+
 static void
 mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_nexthop_group *nh_grp)
 {
+	u16 ecmp_size, old_ecmp_size;
 	struct mlxsw_sp_nexthop *nh;
 	bool offload_change = false;
 	u32 adj_index;
-	u16 ecmp_size = 0;
 	bool old_adj_index_valid;
 	u32 old_adj_index;
-	u16 old_ecmp_size;
 	int i;
 	int err;
 
@@ -2452,8 +3118,6 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 			if (nh->should_offload)
 				nh->update = 1;
 		}
-		if (nh->should_offload)
-			ecmp_size++;
 	}
 	if (!offload_change) {
 		/* Nothing was added or removed, so no need to reallocate. Just
@@ -2466,12 +3130,19 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 		}
 		return;
 	}
-	if (!ecmp_size)
+	mlxsw_sp_nexthop_group_normalize(nh_grp);
+	if (!nh_grp->sum_norm_weight)
 		/* No neigh of this group is connected so we just set
 		 * the trap and let everthing flow through kernel.
 		 */
 		goto set_trap;
 
+	ecmp_size = nh_grp->sum_norm_weight;
+	err = mlxsw_sp_fix_adj_grp_size(mlxsw_sp, &ecmp_size);
+	if (err)
+		/* No valid allocation size available. */
+		goto set_trap;
+
 	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size, &adj_index);
 	if (err) {
 		/* We ran out of KVD linear space, just set the
@@ -2486,6 +3157,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 	nh_grp->adj_index_valid = 1;
 	nh_grp->adj_index = adj_index;
 	nh_grp->ecmp_size = ecmp_size;
+	mlxsw_sp_nexthop_group_rebalance(nh_grp);
 	err = mlxsw_sp_nexthop_group_update(mlxsw_sp, nh_grp, true);
 	if (err) {
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
@@ -2655,38 +3327,28 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp,
 	neigh_release(n);
 }
 
-static bool mlxsw_sp_netdev_ipip_type(const struct mlxsw_sp *mlxsw_sp,
-				      const struct net_device *dev,
-				      enum mlxsw_sp_ipip_type *p_type)
+static bool mlxsw_sp_ipip_netdev_ul_up(struct net_device *ol_dev)
 {
-	struct mlxsw_sp_router *router = mlxsw_sp->router;
-	const struct mlxsw_sp_ipip_ops *ipip_ops;
-	enum mlxsw_sp_ipip_type ipipt;
+	struct net_device *ul_dev = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev);
 
-	for (ipipt = 0; ipipt < MLXSW_SP_IPIP_TYPE_MAX; ++ipipt) {
-		ipip_ops = router->ipip_ops_arr[ipipt];
-		if (dev->type == ipip_ops->dev_type) {
-			if (p_type)
-				*p_type = ipipt;
-			return true;
-		}
-	}
-	return false;
+	return ul_dev ? (ul_dev->flags & IFF_UP) : true;
 }
 
 static int mlxsw_sp_nexthop_ipip_init(struct mlxsw_sp *mlxsw_sp,
-				      enum mlxsw_sp_ipip_type ipipt,
 				      struct mlxsw_sp_nexthop *nh,
 				      struct net_device *ol_dev)
 {
+	bool removing;
+
 	if (!nh->nh_grp->gateway || nh->ipip_entry)
 		return 0;
 
-	nh->ipip_entry = mlxsw_sp_ipip_entry_get(mlxsw_sp, ipipt, ol_dev);
-	if (IS_ERR(nh->ipip_entry))
-		return PTR_ERR(nh->ipip_entry);
+	nh->ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
+	if (!nh->ipip_entry)
+		return -ENOENT;
 
-	__mlxsw_sp_nexthop_neigh_update(nh, false);
+	removing = !mlxsw_sp_ipip_netdev_ul_up(ol_dev);
+	__mlxsw_sp_nexthop_neigh_update(nh, removing);
 	return 0;
 }
 
@@ -2699,7 +3361,6 @@ static void mlxsw_sp_nexthop_ipip_fini(struct mlxsw_sp *mlxsw_sp,
 		return;
 
 	__mlxsw_sp_nexthop_neigh_update(nh, true);
-	mlxsw_sp_ipip_entry_put(mlxsw_sp, ipip_entry);
 	nh->ipip_entry = NULL;
 }
 
@@ -2743,7 +3404,7 @@ static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp,
 	    router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev,
 						     MLXSW_SP_L3_PROTO_IPV4)) {
 		nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP;
-		err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev);
+		err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, dev);
 		if (err)
 			return err;
 		mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common);
@@ -2784,11 +3445,19 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
 
 	nh->nh_grp = nh_grp;
 	nh->key.fib_nh = fib_nh;
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+	nh->nh_weight = fib_nh->nh_weight;
+#else
+	nh->nh_weight = 1;
+#endif
 	memcpy(&nh->gw_addr, &fib_nh->nh_gw, sizeof(fib_nh->nh_gw));
 	err = mlxsw_sp_nexthop_insert(mlxsw_sp, nh);
 	if (err)
 		return err;
 
+	mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
+	list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list);
+
 	if (!dev)
 		return 0;
 
@@ -2812,6 +3481,8 @@ static void mlxsw_sp_nexthop4_fini(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_nexthop *nh)
 {
 	mlxsw_sp_nexthop4_type_fini(mlxsw_sp, nh);
+	list_del(&nh->router_list_node);
+	mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
 	mlxsw_sp_nexthop_remove(mlxsw_sp, nh);
 }
 
@@ -2841,6 +3512,30 @@ static void mlxsw_sp_nexthop4_event(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
 }
 
+static void mlxsw_sp_nexthop_rif_update(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_nexthop *nh;
+	bool removing;
+
+	list_for_each_entry(nh, &rif->nexthop_list, rif_list_node) {
+		switch (nh->type) {
+		case MLXSW_SP_NEXTHOP_TYPE_ETH:
+			removing = false;
+			break;
+		case MLXSW_SP_NEXTHOP_TYPE_IPIP:
+			removing = !mlxsw_sp_ipip_netdev_ul_up(rif->dev);
+			break;
+		default:
+			WARN_ON(1);
+			continue;
+		}
+
+		__mlxsw_sp_nexthop_neigh_update(nh, removing);
+		mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
+	}
+}
+
 static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
 					   struct mlxsw_sp_rif *rif)
 {
@@ -3121,7 +3816,7 @@ mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry,
 			return;
 		if (mlxsw_sp_fib_entry_should_offload(fib_entry))
 			mlxsw_sp_fib_entry_offload_set(fib_entry);
-		else if (!mlxsw_sp_fib_entry_should_offload(fib_entry))
+		else
 			mlxsw_sp_fib_entry_offload_unset(fib_entry);
 		return;
 	default:
@@ -3576,7 +4271,7 @@ mlxsw_sp_fib_node_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id, const void *addr,
 	struct mlxsw_sp_vr *vr;
 	int err;
 
-	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id);
+	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id, NULL);
 	if (IS_ERR(vr))
 		return ERR_CAST(vr);
 	fib = mlxsw_sp_vr_fib(vr, proto);
@@ -4000,7 +4695,7 @@ static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp,
 	    router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev,
 						     MLXSW_SP_L3_PROTO_IPV6)) {
 		nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP;
-		err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev);
+		err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, dev);
 		if (err)
 			return err;
 		mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common);
@@ -4038,7 +4733,11 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
 	struct net_device *dev = rt->dst.dev;
 
 	nh->nh_grp = nh_grp;
+	nh->nh_weight = 1;
 	memcpy(&nh->gw_addr, &rt->rt6i_gateway, sizeof(nh->gw_addr));
+	mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
+
+	list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list);
 
 	if (!dev)
 		return 0;
@@ -4051,6 +4750,8 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_nexthop *nh)
 {
 	mlxsw_sp_nexthop6_type_fini(mlxsw_sp, nh);
+	list_del(&nh->router_list_node);
+	mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
 }
 
 static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp,
@@ -4601,6 +5302,75 @@ static int __mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
+static int mlxsw_sp_router_fibmr_add(struct mlxsw_sp *mlxsw_sp,
+				     struct mfc_entry_notifier_info *men_info,
+				     bool replace)
+{
+	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);
+
+	return mlxsw_sp_mr_route4_add(vr->mr4_table, men_info->mfc, replace);
+}
+
+static void mlxsw_sp_router_fibmr_del(struct mlxsw_sp *mlxsw_sp,
+				      struct mfc_entry_notifier_info *men_info)
+{
+	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;
+
+	mlxsw_sp_mr_route4_del(vr->mr4_table, men_info->mfc);
+	mlxsw_sp_vr_put(vr);
+}
+
+static int
+mlxsw_sp_router_fibmr_vif_add(struct mlxsw_sp *mlxsw_sp,
+			      struct vif_entry_notifier_info *ven_info)
+{
+	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);
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, ven_info->dev);
+	return mlxsw_sp_mr_vif_add(vr->mr4_table, ven_info->dev,
+				   ven_info->vif_index,
+				   ven_info->vif_flags, rif);
+}
+
+static void
+mlxsw_sp_router_fibmr_vif_del(struct mlxsw_sp *mlxsw_sp,
+			      struct vif_entry_notifier_info *ven_info)
+{
+	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;
+
+	mlxsw_sp_mr_vif_del(vr->mr4_table, ven_info->vif_index);
+	mlxsw_sp_vr_put(vr);
+}
+
 static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
 {
 	enum mlxsw_reg_ralxx_protocol proto = MLXSW_REG_RALXX_PROTOCOL_IPV4;
@@ -4611,6 +5381,10 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
 	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_REG_RALXX_PROTOCOL_IPV6;
 	return __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto,
 						MLXSW_SP_LPM_TREE_MIN + 1);
@@ -4692,6 +5466,8 @@ static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp)
 
 		if (!mlxsw_sp_vr_is_used(vr))
 			continue;
+
+		mlxsw_sp_mr_table_flush(vr->mr4_table);
 		mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4);
 
 		/* If virtual router was only used for IPv4, then it's no
@@ -4724,6 +5500,8 @@ struct mlxsw_sp_fib_event_work {
 		struct fib_entry_notifier_info fen_info;
 		struct fib_rule_notifier_info fr_info;
 		struct fib_nh_notifier_info fnh_info;
+		struct mfc_entry_notifier_info men_info;
+		struct vif_entry_notifier_info ven_info;
 	};
 	struct mlxsw_sp *mlxsw_sp;
 	unsigned long event;
@@ -4734,7 +5512,6 @@ static void mlxsw_sp_router_fib4_event_work(struct work_struct *work)
 	struct mlxsw_sp_fib_event_work *fib_work =
 		container_of(work, struct mlxsw_sp_fib_event_work, work);
 	struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp;
-	struct fib_rule *rule;
 	bool replace, append;
 	int err;
 
@@ -4756,12 +5533,11 @@ static void mlxsw_sp_router_fib4_event_work(struct work_struct *work)
 		mlxsw_sp_router_fib4_del(mlxsw_sp, &fib_work->fen_info);
 		fib_info_put(fib_work->fen_info.fi);
 		break;
-	case FIB_EVENT_RULE_ADD: /* fall through */
-	case FIB_EVENT_RULE_DEL:
-		rule = fib_work->fr_info.rule;
-		if (!fib4_rule_default(rule) && !rule->l3mdev)
-			mlxsw_sp_router_fib_abort(mlxsw_sp);
-		fib_rule_put(rule);
+	case FIB_EVENT_RULE_ADD:
+		/* if we get here, a rule was added that we do not support.
+		 * just do the fib_abort
+		 */
+		mlxsw_sp_router_fib_abort(mlxsw_sp);
 		break;
 	case FIB_EVENT_NH_ADD: /* fall through */
 	case FIB_EVENT_NH_DEL:
@@ -4779,7 +5555,6 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work)
 	struct mlxsw_sp_fib_event_work *fib_work =
 		container_of(work, struct mlxsw_sp_fib_event_work, work);
 	struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp;
-	struct fib_rule *rule;
 	bool replace;
 	int err;
 
@@ -4798,12 +5573,58 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work)
 		mlxsw_sp_router_fib6_del(mlxsw_sp, fib_work->fen6_info.rt);
 		mlxsw_sp_rt6_release(fib_work->fen6_info.rt);
 		break;
-	case FIB_EVENT_RULE_ADD: /* fall through */
-	case FIB_EVENT_RULE_DEL:
-		rule = fib_work->fr_info.rule;
-		if (!fib6_rule_default(rule) && !rule->l3mdev)
+	case FIB_EVENT_RULE_ADD:
+		/* if we get here, a rule was added that we do not support.
+		 * just do the fib_abort
+		 */
+		mlxsw_sp_router_fib_abort(mlxsw_sp);
+		break;
+	}
+	rtnl_unlock();
+	kfree(fib_work);
+}
+
+static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work)
+{
+	struct mlxsw_sp_fib_event_work *fib_work =
+		container_of(work, struct mlxsw_sp_fib_event_work, work);
+	struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp;
+	bool replace;
+	int err;
+
+	rtnl_lock();
+	switch (fib_work->event) {
+	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_ADD:
+		replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE;
+
+		err = mlxsw_sp_router_fibmr_add(mlxsw_sp, &fib_work->men_info,
+						replace);
+		if (err)
 			mlxsw_sp_router_fib_abort(mlxsw_sp);
-		fib_rule_put(rule);
+		ipmr_cache_put(fib_work->men_info.mfc);
+		break;
+	case FIB_EVENT_ENTRY_DEL:
+		mlxsw_sp_router_fibmr_del(mlxsw_sp, &fib_work->men_info);
+		ipmr_cache_put(fib_work->men_info.mfc);
+		break;
+	case FIB_EVENT_VIF_ADD:
+		err = mlxsw_sp_router_fibmr_vif_add(mlxsw_sp,
+						    &fib_work->ven_info);
+		if (err)
+			mlxsw_sp_router_fib_abort(mlxsw_sp);
+		dev_put(fib_work->ven_info.dev);
+		break;
+	case FIB_EVENT_VIF_DEL:
+		mlxsw_sp_router_fibmr_vif_del(mlxsw_sp,
+					      &fib_work->ven_info);
+		dev_put(fib_work->ven_info.dev);
+		break;
+	case FIB_EVENT_RULE_ADD:
+		/* if we get here, a rule was added that we do not support.
+		 * just do the fib_abort
+		 */
+		mlxsw_sp_router_fib_abort(mlxsw_sp);
 		break;
 	}
 	rtnl_unlock();
@@ -4813,25 +5634,27 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work)
 static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work,
 				       struct fib_notifier_info *info)
 {
+	struct fib_entry_notifier_info *fen_info;
+	struct fib_nh_notifier_info *fnh_info;
+
 	switch (fib_work->event) {
 	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
 	case FIB_EVENT_ENTRY_APPEND: /* fall through */
 	case FIB_EVENT_ENTRY_ADD: /* fall through */
 	case FIB_EVENT_ENTRY_DEL:
-		memcpy(&fib_work->fen_info, info, sizeof(fib_work->fen_info));
-		/* Take referece on fib_info to prevent it from being
+		fen_info = container_of(info, struct fib_entry_notifier_info,
+					info);
+		fib_work->fen_info = *fen_info;
+		/* Take reference on fib_info to prevent it from being
 		 * freed while work is queued. Release it afterwards.
 		 */
 		fib_info_hold(fib_work->fen_info.fi);
 		break;
-	case FIB_EVENT_RULE_ADD: /* fall through */
-	case FIB_EVENT_RULE_DEL:
-		memcpy(&fib_work->fr_info, info, sizeof(fib_work->fr_info));
-		fib_rule_get(fib_work->fr_info.rule);
-		break;
 	case FIB_EVENT_NH_ADD: /* fall through */
 	case FIB_EVENT_NH_DEL:
-		memcpy(&fib_work->fnh_info, info, sizeof(fib_work->fnh_info));
+		fnh_info = container_of(info, struct fib_nh_notifier_info,
+					info);
+		fib_work->fnh_info = *fnh_info;
 		fib_info_hold(fib_work->fnh_info.fib_nh->nh_parent);
 		break;
 	}
@@ -4840,21 +5663,79 @@ static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work,
 static void mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work,
 				       struct fib_notifier_info *info)
 {
+	struct fib6_entry_notifier_info *fen6_info;
+
 	switch (fib_work->event) {
 	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
 	case FIB_EVENT_ENTRY_ADD: /* fall through */
 	case FIB_EVENT_ENTRY_DEL:
-		memcpy(&fib_work->fen6_info, info, sizeof(fib_work->fen6_info));
+		fen6_info = container_of(info, struct fib6_entry_notifier_info,
+					 info);
+		fib_work->fen6_info = *fen6_info;
 		rt6_hold(fib_work->fen6_info.rt);
 		break;
-	case FIB_EVENT_RULE_ADD: /* fall through */
-	case FIB_EVENT_RULE_DEL:
-		memcpy(&fib_work->fr_info, info, sizeof(fib_work->fr_info));
-		fib_rule_get(fib_work->fr_info.rule);
+	}
+}
+
+static void
+mlxsw_sp_router_fibmr_event(struct mlxsw_sp_fib_event_work *fib_work,
+			    struct fib_notifier_info *info)
+{
+	switch (fib_work->event) {
+	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_ADD: /* fall through */
+	case FIB_EVENT_ENTRY_DEL:
+		memcpy(&fib_work->men_info, info, sizeof(fib_work->men_info));
+		ipmr_cache_hold(fib_work->men_info.mfc);
+		break;
+	case FIB_EVENT_VIF_ADD: /* fall through */
+	case FIB_EVENT_VIF_DEL:
+		memcpy(&fib_work->ven_info, info, sizeof(fib_work->ven_info));
+		dev_hold(fib_work->ven_info.dev);
 		break;
 	}
 }
 
+static int mlxsw_sp_router_fib_rule_event(unsigned long event,
+					  struct fib_notifier_info *info,
+					  struct mlxsw_sp *mlxsw_sp)
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct fib_rule_notifier_info *fr_info;
+	struct fib_rule *rule;
+	int err = 0;
+
+	/* nothing to do at the moment */
+	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;
+
+	switch (info->family) {
+	case AF_INET:
+		if (!fib4_rule_default(rule) && !rule->l3mdev)
+			err = -1;
+		break;
+	case AF_INET6:
+		if (!fib6_rule_default(rule) && !rule->l3mdev)
+			err = -1;
+		break;
+	case RTNL_FAMILY_IPMR:
+		if (!ipmr_rule_default(rule) && !rule->l3mdev)
+			err = -1;
+		break;
+	}
+
+	if (err < 0)
+		NL_SET_ERR_MSG(extack, "spectrum: FIB rules not supported. Aborting offload");
+
+	return err;
+}
+
 /* Called with rcu_read_lock() */
 static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 				     unsigned long event, void *ptr)
@@ -4862,16 +5743,28 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	struct mlxsw_sp_fib_event_work *fib_work;
 	struct fib_notifier_info *info = ptr;
 	struct mlxsw_sp_router *router;
+	int err;
 
 	if (!net_eq(info->net, &init_net) ||
-	    (info->family != AF_INET && info->family != AF_INET6))
+	    (info->family != AF_INET && info->family != AF_INET6 &&
+	     info->family != RTNL_FAMILY_IPMR))
 		return NOTIFY_DONE;
 
+	router = container_of(nb, struct mlxsw_sp_router, fib_nb);
+
+	switch (event) {
+	case FIB_EVENT_RULE_ADD: /* fall through */
+	case FIB_EVENT_RULE_DEL:
+		err = mlxsw_sp_router_fib_rule_event(event, info,
+						     router->mlxsw_sp);
+		if (!err)
+			return NOTIFY_DONE;
+	}
+
 	fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
 	if (WARN_ON(!fib_work))
 		return NOTIFY_BAD;
 
-	router = container_of(nb, struct mlxsw_sp_router, fib_nb);
 	fib_work->mlxsw_sp = router->mlxsw_sp;
 	fib_work->event = event;
 
@@ -4884,6 +5777,10 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 		INIT_WORK(&fib_work->work, mlxsw_sp_router_fib6_event_work);
 		mlxsw_sp_router_fib6_event(fib_work, info);
 		break;
+	case RTNL_FAMILY_IPMR:
+		INIT_WORK(&fib_work->work, mlxsw_sp_router_fibmr_event_work);
+		mlxsw_sp_router_fibmr_event(fib_work, info);
+		break;
 	}
 
 	mlxsw_core_schedule_work(&fib_work->work);
@@ -5044,9 +5941,15 @@ int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif)
 	return rif->dev->ifindex;
 }
 
+const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif)
+{
+	return rif->dev;
+}
+
 static struct mlxsw_sp_rif *
 mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
-		    const struct mlxsw_sp_rif_params *params)
+		    const struct mlxsw_sp_rif_params *params,
+		    struct netlink_ext_ack *extack)
 {
 	u32 tb_id = l3mdev_fib_table(params->dev);
 	const struct mlxsw_sp_rif_ops *ops;
@@ -5060,14 +5963,16 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	type = mlxsw_sp_dev_rif_type(mlxsw_sp, params->dev);
 	ops = mlxsw_sp->router->rif_ops_arr[type];
 
-	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN);
+	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN, extack);
 	if (IS_ERR(vr))
 		return ERR_CAST(vr);
 	vr->rif_count++;
 
 	err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index);
-	if (err)
+	if (err) {
+		NL_SET_ERR_MSG(extack, "spectrum: Exceeded number of supported router interfaces");
 		goto err_rif_index_alloc;
+	}
 
 	rif = mlxsw_sp_rif_alloc(ops->rif_size, rif_index, vr->id, params->dev);
 	if (!rif) {
@@ -5093,11 +5998,17 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_configure;
 
+	err = mlxsw_sp_mr_rif_add(vr->mr4_table, rif);
+	if (err)
+		goto err_mr_rif_add;
+
 	mlxsw_sp_rif_counters_alloc(rif);
 	mlxsw_sp->router->rifs[rif_index] = rif;
 
 	return rif;
 
+err_mr_rif_add:
+	ops->deconfigure(rif);
 err_configure:
 	if (fid)
 		mlxsw_sp_fid_put(fid);
@@ -5122,6 +6033,7 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 
 	mlxsw_sp->router->rifs[rif->rif_index] = NULL;
 	mlxsw_sp_rif_counters_free(rif);
+	mlxsw_sp_mr_rif_del(vr->mr4_table, rif);
 	ops->deconfigure(rif);
 	if (fid)
 		/* Loopback RIFs are not associated with a FID. */
@@ -5147,7 +6059,8 @@ mlxsw_sp_rif_subport_params_init(struct mlxsw_sp_rif_params *params,
 
 static int
 mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
-			       struct net_device *l3_dev)
+			       struct net_device *l3_dev,
+			       struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
@@ -5163,7 +6076,7 @@ mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 		};
 
 		mlxsw_sp_rif_subport_params_init(&params, mlxsw_sp_port_vlan);
-		rif = mlxsw_sp_rif_create(mlxsw_sp, &params);
+		rif = mlxsw_sp_rif_create(mlxsw_sp, &params, extack);
 		if (IS_ERR(rif))
 			return PTR_ERR(rif);
 	}
@@ -5218,7 +6131,8 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 
 static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev,
 					     struct net_device *port_dev,
-					     unsigned long event, u16 vid)
+					     unsigned long event, u16 vid,
+					     struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev);
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
@@ -5230,7 +6144,7 @@ static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev,
 	switch (event) {
 	case NETDEV_UP:
 		return mlxsw_sp_port_vlan_router_join(mlxsw_sp_port_vlan,
-						      l3_dev);
+						      l3_dev, extack);
 	case NETDEV_DOWN:
 		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
 		break;
@@ -5240,19 +6154,22 @@ static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev,
 }
 
 static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev,
-					unsigned long event)
+					unsigned long event,
+					struct netlink_ext_ack *extack)
 {
 	if (netif_is_bridge_port(port_dev) ||
 	    netif_is_lag_port(port_dev) ||
 	    netif_is_ovs_port(port_dev))
 		return 0;
 
-	return mlxsw_sp_inetaddr_port_vlan_event(port_dev, port_dev, event, 1);
+	return mlxsw_sp_inetaddr_port_vlan_event(port_dev, port_dev, event, 1,
+						 extack);
 }
 
 static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
 					 struct net_device *lag_dev,
-					 unsigned long event, u16 vid)
+					 unsigned long event, u16 vid,
+					 struct netlink_ext_ack *extack)
 {
 	struct net_device *port_dev;
 	struct list_head *iter;
@@ -5262,7 +6179,8 @@ static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
 		if (mlxsw_sp_port_dev_check(port_dev)) {
 			err = mlxsw_sp_inetaddr_port_vlan_event(l3_dev,
 								port_dev,
-								event, vid);
+								event, vid,
+								extack);
 			if (err)
 				return err;
 		}
@@ -5272,16 +6190,19 @@ static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
 }
 
 static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
-				       unsigned long event)
+				       unsigned long event,
+				       struct netlink_ext_ack *extack)
 {
 	if (netif_is_bridge_port(lag_dev))
 		return 0;
 
-	return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1);
+	return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1,
+					     extack);
 }
 
 static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
-					  unsigned long event)
+					  unsigned long event,
+					  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
 	struct mlxsw_sp_rif_params params = {
@@ -5291,7 +6212,7 @@ static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
 
 	switch (event) {
 	case NETDEV_UP:
-		rif = mlxsw_sp_rif_create(mlxsw_sp, &params);
+		rif = mlxsw_sp_rif_create(mlxsw_sp, &params, extack);
 		if (IS_ERR(rif))
 			return PTR_ERR(rif);
 		break;
@@ -5305,7 +6226,8 @@ static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
 }
 
 static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
-					unsigned long event)
+					unsigned long event,
+					struct netlink_ext_ack *extack)
 {
 	struct net_device *real_dev = vlan_dev_real_dev(vlan_dev);
 	u16 vid = vlan_dev_vlan_id(vlan_dev);
@@ -5315,27 +6237,28 @@ static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
 
 	if (mlxsw_sp_port_dev_check(real_dev))
 		return mlxsw_sp_inetaddr_port_vlan_event(vlan_dev, real_dev,
-							 event, vid);
+							 event, vid, extack);
 	else if (netif_is_lag_master(real_dev))
 		return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event,
-						     vid);
+						     vid, extack);
 	else if (netif_is_bridge_master(real_dev) && br_vlan_enabled(real_dev))
-		return mlxsw_sp_inetaddr_bridge_event(vlan_dev, event);
+		return mlxsw_sp_inetaddr_bridge_event(vlan_dev, event, extack);
 
 	return 0;
 }
 
 static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
-				     unsigned long event)
+				     unsigned long event,
+				     struct netlink_ext_ack *extack)
 {
 	if (mlxsw_sp_port_dev_check(dev))
-		return mlxsw_sp_inetaddr_port_event(dev, event);
+		return mlxsw_sp_inetaddr_port_event(dev, event, extack);
 	else if (netif_is_lag_master(dev))
-		return mlxsw_sp_inetaddr_lag_event(dev, event);
+		return mlxsw_sp_inetaddr_lag_event(dev, event, extack);
 	else if (netif_is_bridge_master(dev))
-		return mlxsw_sp_inetaddr_bridge_event(dev, event);
+		return mlxsw_sp_inetaddr_bridge_event(dev, event, extack);
 	else if (is_vlan_dev(dev))
-		return mlxsw_sp_inetaddr_vlan_event(dev, event);
+		return mlxsw_sp_inetaddr_vlan_event(dev, event, extack);
 	else
 		return 0;
 }
@@ -5349,6 +6272,10 @@ int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
 	struct mlxsw_sp_rif *rif;
 	int err = 0;
 
+	/* NETDEV_UP event is handled by mlxsw_sp_inetaddr_valid_event */
+	if (event == NETDEV_UP)
+		goto out;
+
 	mlxsw_sp = mlxsw_sp_lower_get(dev);
 	if (!mlxsw_sp)
 		goto out;
@@ -5357,7 +6284,29 @@ int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(dev, event);
+	err = __mlxsw_sp_inetaddr_event(dev, event, NULL);
+out:
+	return notifier_from_errno(err);
+}
+
+int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
+				  unsigned long event, void *ptr)
+{
+	struct in_validator_info *ivi = (struct in_validator_info *) ptr;
+	struct net_device *dev = ivi->ivi_dev->dev;
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_rif *rif;
+	int err = 0;
+
+	mlxsw_sp = mlxsw_sp_lower_get(dev);
+	if (!mlxsw_sp)
+		goto out;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!mlxsw_sp_rif_should_config(rif, dev, event))
+		goto out;
+
+	err = __mlxsw_sp_inetaddr_event(dev, event, ivi->extack);
 out:
 	return notifier_from_errno(err);
 }
@@ -5386,7 +6335,7 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work)
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	__mlxsw_sp_inetaddr_event(dev, event);
+	__mlxsw_sp_inetaddr_event(dev, event, NULL);
 out:
 	rtnl_unlock();
 	dev_put(dev);
@@ -5401,6 +6350,10 @@ int mlxsw_sp_inet6addr_event(struct notifier_block *unused,
 	struct mlxsw_sp_inet6addr_event_work *inet6addr_work;
 	struct net_device *dev = if6->idev->dev;
 
+	/* NETDEV_UP event is handled by mlxsw_sp_inet6addr_valid_event */
+	if (event == NETDEV_UP)
+		return NOTIFY_DONE;
+
 	if (!mlxsw_sp_port_dev_lower_find_rcu(dev))
 		return NOTIFY_DONE;
 
@@ -5417,6 +6370,28 @@ int mlxsw_sp_inet6addr_event(struct notifier_block *unused,
 	return NOTIFY_DONE;
 }
 
+int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused,
+				   unsigned long event, void *ptr)
+{
+	struct in6_validator_info *i6vi = (struct in6_validator_info *) ptr;
+	struct net_device *dev = i6vi->i6vi_dev->dev;
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_rif *rif;
+	int err = 0;
+
+	mlxsw_sp = mlxsw_sp_lower_get(dev);
+	if (!mlxsw_sp)
+		goto out;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!mlxsw_sp_rif_should_config(rif, dev, event))
+		goto out;
+
+	err = __mlxsw_sp_inetaddr_event(dev, event, i6vi->extack);
+out:
+	return notifier_from_errno(err);
+}
+
 static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index,
 			     const char *mac, int mtu)
 {
@@ -5463,6 +6438,17 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev)
 	if (err)
 		goto err_rif_fdb_op;
 
+	if (rif->mtu != dev->mtu) {
+		struct mlxsw_sp_vr *vr;
+
+		/* The RIF is relevant only to its mr_table instance, as unlike
+		 * unicast routing, in multicast routing a RIF cannot be shared
+		 * between several multicast routing tables.
+		 */
+		vr = &mlxsw_sp->router->vrs[rif->vr_id];
+		mlxsw_sp_mr_rif_mtu_update(vr->mr4_table, rif, dev->mtu);
+	}
+
 	ether_addr_copy(rif->addr, dev->dev_addr);
 	rif->mtu = dev->mtu;
 
@@ -5478,7 +6464,8 @@ err_rif_edit:
 }
 
 static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp,
-				  struct net_device *l3_dev)
+				  struct net_device *l3_dev,
+				  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_rif *rif;
 
@@ -5487,9 +6474,9 @@ static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp,
 	 */
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
 	if (rif)
-		__mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN);
+		__mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN, extack);
 
-	return __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_UP);
+	return __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_UP, extack);
 }
 
 static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp,
@@ -5500,7 +6487,7 @@ static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp,
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
 	if (!rif)
 		return;
-	__mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN);
+	__mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN, NULL);
 }
 
 int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
@@ -5516,10 +6503,14 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
 	case NETDEV_PRECHANGEUPPER:
 		return 0;
 	case NETDEV_CHANGEUPPER:
-		if (info->linking)
-			err = mlxsw_sp_port_vrf_join(mlxsw_sp, l3_dev);
-		else
+		if (info->linking) {
+			struct netlink_ext_ack *extack;
+
+			extack = netdev_notifier_info_to_extack(&info->info);
+			err = mlxsw_sp_port_vrf_join(mlxsw_sp, l3_dev, extack);
+		} else {
 			mlxsw_sp_port_vrf_leave(mlxsw_sp, l3_dev);
+		}
 		break;
 	}
 
@@ -5625,7 +6616,7 @@ static int mlxsw_sp_rif_vlan_fid_op(struct mlxsw_sp_rif *rif,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
 }
 
-static u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp)
+u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp)
 {
 	return mlxsw_core_max_ports(mlxsw_sp->core) + 1;
 }
@@ -5826,7 +6817,7 @@ mlxsw_sp_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif)
 	struct mlxsw_sp_vr *ul_vr;
 	int err;
 
-	ul_vr = mlxsw_sp_vr_get(mlxsw_sp, ul_tb_id);
+	ul_vr = mlxsw_sp_vr_get(mlxsw_sp, ul_tb_id, NULL);
 	if (IS_ERR(ul_vr))
 		return PTR_ERR(ul_vr);
 
@@ -5930,6 +6921,64 @@ static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb)
 	mlxsw_sp_router_fib_flush(router->mlxsw_sp);
 }
 
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+static void mlxsw_sp_mp_hash_header_set(char *recr2_pl, int header)
+{
+	mlxsw_reg_recr2_outer_header_enables_set(recr2_pl, header, true);
+}
+
+static void mlxsw_sp_mp_hash_field_set(char *recr2_pl, int field)
+{
+	mlxsw_reg_recr2_outer_header_fields_enable_set(recr2_pl, field, true);
+}
+
+static void mlxsw_sp_mp4_hash_init(char *recr2_pl)
+{
+	bool only_l3 = !init_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);
+}
+
+static void mlxsw_sp_mp6_hash_init(char *recr2_pl)
+{
+	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_FLOW_LABEL);
+	mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_IPV6_NEXT_HEADER);
+}
+
+static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp)
+{
+	char recr2_pl[MLXSW_REG_RECR2_LEN];
+	u32 seed;
+
+	get_random_bytes(&seed, sizeof(seed));
+	mlxsw_reg_recr2_pack(recr2_pl, seed);
+	mlxsw_sp_mp4_hash_init(recr2_pl);
+	mlxsw_sp_mp6_hash_init(recr2_pl);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(recr2), recr2_pl);
+}
+#else
+static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp)
+{
+	return 0;
+}
+#endif
+
 static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 {
 	char rgcr_pl[MLXSW_REG_RGCR_LEN];
@@ -5990,10 +7039,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 	if (err)
 		goto err_nexthop_group_ht_init;
 
+	INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_list);
 	err = mlxsw_sp_lpm_init(mlxsw_sp);
 	if (err)
 		goto err_lpm_init;
 
+	err = mlxsw_sp_mr_init(mlxsw_sp, &mlxsw_sp_mr_tcam_ops);
+	if (err)
+		goto err_mr_init;
+
 	err = mlxsw_sp_vrs_init(mlxsw_sp);
 	if (err)
 		goto err_vrs_init;
@@ -6002,6 +7056,16 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 	if (err)
 		goto err_neigh_init;
 
+	mlxsw_sp->router->netevent_nb.notifier_call =
+		mlxsw_sp_router_netevent_event;
+	err = register_netevent_notifier(&mlxsw_sp->router->netevent_nb);
+	if (err)
+		goto err_register_netevent_notifier;
+
+	err = mlxsw_sp_mp_hash_init(mlxsw_sp);
+	if (err)
+		goto err_mp_hash_init;
+
 	mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event;
 	err = register_fib_notifier(&mlxsw_sp->router->fib_nb,
 				    mlxsw_sp_router_fib_dump_flush);
@@ -6011,10 +7075,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 	return 0;
 
 err_register_fib_notifier:
+err_mp_hash_init:
+	unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb);
+err_register_netevent_notifier:
 	mlxsw_sp_neigh_fini(mlxsw_sp);
 err_neigh_init:
 	mlxsw_sp_vrs_fini(mlxsw_sp);
 err_vrs_init:
+	mlxsw_sp_mr_fini(mlxsw_sp);
+err_mr_init:
 	mlxsw_sp_lpm_fini(mlxsw_sp);
 err_lpm_init:
 	rhashtable_destroy(&mlxsw_sp->router->nexthop_group_ht);
@@ -6034,8 +7103,10 @@ err_router_init:
 void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	unregister_fib_notifier(&mlxsw_sp->router->fib_nb);
+	unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb);
 	mlxsw_sp_neigh_fini(mlxsw_sp);
 	mlxsw_sp_vrs_fini(mlxsw_sp);
+	mlxsw_sp_mr_fini(mlxsw_sp);
 	mlxsw_sp_lpm_fini(mlxsw_sp);
 	rhashtable_destroy(&mlxsw_sp->router->nexthop_group_ht);
 	rhashtable_destroy(&mlxsw_sp->router->nexthop_ht);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 345fcc4f38e9..1fb82246ce96 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -62,13 +62,18 @@ enum mlxsw_sp_rif_counter_dir {
 };
 
 struct mlxsw_sp_neigh_entry;
+struct mlxsw_sp_nexthop;
+struct mlxsw_sp_ipip_entry;
 
 struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp,
 					   u16 rif_index);
 u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif);
 u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *rif);
 u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *rif);
+u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev);
 int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
+u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp);
+const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif);
 int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_rif *rif,
 				   enum mlxsw_sp_rif_counter_dir dir,
@@ -100,12 +105,44 @@ mlxsw_sp_neigh_entry_counter_update(struct mlxsw_sp *mlxsw_sp,
 				    struct mlxsw_sp_neigh_entry *neigh_entry,
 				    bool adding);
 bool mlxsw_sp_neigh_ipv6_ignore(struct mlxsw_sp_neigh_entry *neigh_entry);
-union mlxsw_sp_l3addr
-mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto,
-			   const struct net_device *ol_dev);
-union mlxsw_sp_l3addr
-mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto,
-			   const struct net_device *ol_dev);
-__be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev);
+int __mlxsw_sp_ipip_entry_update_tunnel(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_ipip_entry *ipip_entry,
+					bool recreate_loopback,
+					bool keep_encap,
+					bool update_nexthops,
+					struct netlink_ext_ack *extack);
+void mlxsw_sp_ipip_entry_demote_tunnel(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_ipip_entry *ipip_entry);
+bool
+mlxsw_sp_ipip_demote_tunnel_by_saddr(struct mlxsw_sp *mlxsw_sp,
+				     enum mlxsw_sp_l3proto ul_proto,
+				     union mlxsw_sp_l3addr saddr,
+				     u32 ul_tb_id,
+				     const struct mlxsw_sp_ipip_entry *except);
+struct mlxsw_sp_nexthop *mlxsw_sp_nexthop_next(struct mlxsw_sp_router *router,
+					       struct mlxsw_sp_nexthop *nh);
+bool mlxsw_sp_nexthop_offload(struct mlxsw_sp_nexthop *nh);
+unsigned char *mlxsw_sp_nexthop_ha(struct mlxsw_sp_nexthop *nh);
+int mlxsw_sp_nexthop_indexes(struct mlxsw_sp_nexthop *nh, u32 *p_adj_index,
+			     u32 *p_adj_size, u32 *p_adj_hash_index);
+struct mlxsw_sp_rif *mlxsw_sp_nexthop_rif(struct mlxsw_sp_nexthop *nh);
+bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh);
+#define mlxsw_sp_nexthop_for_each(nh, router)				\
+	for (nh = mlxsw_sp_nexthop_next(router, NULL); nh;		\
+	     nh = mlxsw_sp_nexthop_next(router, nh))
+int mlxsw_sp_nexthop_counter_get(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_nexthop *nh, u64 *p_counter);
+int mlxsw_sp_nexthop_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
+			    struct mlxsw_sp_nexthop *nh);
+void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_nexthop *nh);
+void mlxsw_sp_nexthop_counter_free(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_nexthop *nh);
+
+static inline bool mlxsw_sp_l3addr_eq(const union mlxsw_sp_l3addr *addr1,
+				      const union mlxsw_sp_l3addr *addr2)
+{
+	return !memcmp(addr1, addr2, sizeof(*addr1));
+}
 
 #endif /* _MLXSW_ROUTER_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index d39ffbfcc436..7b8548e25ae7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -46,8 +46,10 @@
 #include <linux/workqueue.h>
 #include <linux/jiffies.h>
 #include <linux/rtnetlink.h>
+#include <linux/netlink.h>
 #include <net/switchdev.h>
 
+#include "spectrum_router.h"
 #include "spectrum.h"
 #include "core.h"
 #include "reg.h"
@@ -67,7 +69,6 @@ struct mlxsw_sp_bridge {
 	u32 ageing_time;
 	bool vlan_enabled_exists;
 	struct list_head bridges_list;
-	struct list_head mids_list;
 	DECLARE_BITMAP(mids_bitmap, MLXSW_SP_MID_MAX);
 	const struct mlxsw_sp_bridge_ops *bridge_8021q_ops;
 	const struct mlxsw_sp_bridge_ops *bridge_8021d_ops;
@@ -77,8 +78,10 @@ struct mlxsw_sp_bridge_device {
 	struct net_device *dev;
 	struct list_head list;
 	struct list_head ports_list;
+	struct list_head mids_list;
 	u8 vlan_enabled:1,
-	   multicast_enabled:1;
+	   multicast_enabled:1,
+	   mrouter:1;
 	const struct mlxsw_sp_bridge_ops *ops;
 };
 
@@ -107,7 +110,8 @@ struct mlxsw_sp_bridge_vlan {
 struct mlxsw_sp_bridge_ops {
 	int (*port_join)(struct mlxsw_sp_bridge_device *bridge_device,
 			 struct mlxsw_sp_bridge_port *bridge_port,
-			 struct mlxsw_sp_port *mlxsw_sp_port);
+			 struct mlxsw_sp_port *mlxsw_sp_port,
+			 struct netlink_ext_ack *extack);
 	void (*port_leave)(struct mlxsw_sp_bridge_device *bridge_device,
 			   struct mlxsw_sp_bridge_port *bridge_port,
 			   struct mlxsw_sp_port *mlxsw_sp_port);
@@ -121,6 +125,20 @@ mlxsw_sp_bridge_port_fdb_flush(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_bridge_port *bridge_port,
 			       u16 fid_index);
 
+static void
+mlxsw_sp_bridge_port_mdb_flush(struct mlxsw_sp_port *mlxsw_sp_port,
+			       struct mlxsw_sp_bridge_port *bridge_port);
+
+static void
+mlxsw_sp_bridge_mdb_mc_enable_sync(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct mlxsw_sp_bridge_device
+				   *bridge_device);
+
+static void
+mlxsw_sp_port_mrouter_update_mdb(struct mlxsw_sp_port *mlxsw_sp_port,
+				 struct mlxsw_sp_bridge_port *bridge_port,
+				 bool add);
+
 static struct mlxsw_sp_bridge_device *
 mlxsw_sp_bridge_device_find(const struct mlxsw_sp_bridge *bridge,
 			    const struct net_device *br_dev)
@@ -154,6 +172,7 @@ mlxsw_sp_bridge_device_create(struct mlxsw_sp_bridge *bridge,
 	bridge_device->dev = br_dev;
 	bridge_device->vlan_enabled = vlan_enabled;
 	bridge_device->multicast_enabled = br_multicast_enabled(br_dev);
+	bridge_device->mrouter = br_multicast_router(br_dev);
 	INIT_LIST_HEAD(&bridge_device->ports_list);
 	if (vlan_enabled) {
 		bridge->vlan_enabled_exists = true;
@@ -161,6 +180,7 @@ mlxsw_sp_bridge_device_create(struct mlxsw_sp_bridge *bridge,
 	} else {
 		bridge_device->ops = bridge->bridge_8021d_ops;
 	}
+	INIT_LIST_HEAD(&bridge_device->mids_list);
 	list_add(&bridge_device->list, &bridge->bridges_list);
 
 	return bridge_device;
@@ -174,6 +194,7 @@ mlxsw_sp_bridge_device_destroy(struct mlxsw_sp_bridge *bridge,
 	if (bridge_device->vlan_enabled)
 		bridge->vlan_enabled_exists = false;
 	WARN_ON(!list_empty(&bridge_device->ports_list));
+	WARN_ON(!list_empty(&bridge_device->mids_list));
 	kfree(bridge_device);
 }
 
@@ -249,7 +270,8 @@ mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device,
 	bridge_port->dev = brport_dev;
 	bridge_port->bridge_device = bridge_device;
 	bridge_port->stp_state = BR_STATE_DISABLED;
-	bridge_port->flags = BR_LEARNING | BR_FLOOD | BR_LEARNING_SYNC;
+	bridge_port->flags = BR_LEARNING | BR_FLOOD | BR_LEARNING_SYNC |
+			     BR_MCAST_FLOOD;
 	INIT_LIST_HEAD(&bridge_port->vlans_list);
 	list_add(&bridge_port->list, &bridge_device->ports_list);
 	bridge_port->ref_count = 1;
@@ -455,7 +477,8 @@ static int mlxsw_sp_port_attr_get(struct net_device *dev,
 					       &attr->u.brport_flags);
 		break;
 	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT:
-		attr->u.brport_flags_support = BR_LEARNING | BR_FLOOD;
+		attr->u.brport_flags_support = BR_LEARNING | BR_FLOOD |
+					       BR_MCAST_FLOOD;
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -640,8 +663,18 @@ static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (err)
 		return err;
 
-	memcpy(&bridge_port->flags, &brport_flags, sizeof(brport_flags));
+	if (bridge_port->bridge_device->multicast_enabled)
+		goto out;
 
+	err = mlxsw_sp_bridge_port_flood_table_set(mlxsw_sp_port, bridge_port,
+						   MLXSW_SP_FLOOD_TYPE_MC,
+						   brport_flags &
+						   BR_MCAST_FLOOD);
+	if (err)
+		return err;
+
+out:
+	memcpy(&bridge_port->flags, &brport_flags, sizeof(brport_flags));
 	return 0;
 }
 
@@ -699,10 +732,10 @@ static int mlxsw_sp_port_attr_br_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	return -EINVAL;
 }
 
-static int mlxsw_sp_port_attr_mc_router_set(struct mlxsw_sp_port *mlxsw_sp_port,
-					    struct switchdev_trans *trans,
-					    struct net_device *orig_dev,
-					    bool is_port_mc_router)
+static int mlxsw_sp_port_attr_mrouter_set(struct mlxsw_sp_port *mlxsw_sp_port,
+					  struct switchdev_trans *trans,
+					  struct net_device *orig_dev,
+					  bool is_port_mrouter)
 {
 	struct mlxsw_sp_bridge_port *bridge_port;
 	int err;
@@ -720,15 +753,26 @@ static int mlxsw_sp_port_attr_mc_router_set(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	err = mlxsw_sp_bridge_port_flood_table_set(mlxsw_sp_port, bridge_port,
 						   MLXSW_SP_FLOOD_TYPE_MC,
-						   is_port_mc_router);
+						   is_port_mrouter);
 	if (err)
 		return err;
 
+	mlxsw_sp_port_mrouter_update_mdb(mlxsw_sp_port, bridge_port,
+					 is_port_mrouter);
 out:
-	bridge_port->mrouter = is_port_mc_router;
+	bridge_port->mrouter = is_port_mrouter;
 	return 0;
 }
 
+static bool mlxsw_sp_mc_flood(const struct mlxsw_sp_bridge_port *bridge_port)
+{
+	const struct mlxsw_sp_bridge_device *bridge_device;
+
+	bridge_device = bridge_port->bridge_device;
+	return bridge_device->multicast_enabled ? bridge_port->mrouter :
+					bridge_port->flags & BR_MCAST_FLOOD;
+}
+
 static int mlxsw_sp_port_mc_disabled_set(struct mlxsw_sp_port *mlxsw_sp_port,
 					 struct switchdev_trans *trans,
 					 struct net_device *orig_dev,
@@ -749,9 +793,15 @@ static int mlxsw_sp_port_mc_disabled_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (!bridge_device)
 		return 0;
 
+	if (bridge_device->multicast_enabled != !mc_disabled) {
+		bridge_device->multicast_enabled = !mc_disabled;
+		mlxsw_sp_bridge_mdb_mc_enable_sync(mlxsw_sp_port,
+						   bridge_device);
+	}
+
 	list_for_each_entry(bridge_port, &bridge_device->ports_list, list) {
 		enum mlxsw_sp_flood_type packet_type = MLXSW_SP_FLOOD_TYPE_MC;
-		bool member = mc_disabled ? true : bridge_port->mrouter;
+		bool member = mlxsw_sp_mc_flood(bridge_port);
 
 		err = mlxsw_sp_bridge_port_flood_table_set(mlxsw_sp_port,
 							   bridge_port,
@@ -765,6 +815,60 @@ static int mlxsw_sp_port_mc_disabled_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	return 0;
 }
 
+static int mlxsw_sp_smid_router_port_set(struct mlxsw_sp *mlxsw_sp,
+					 u16 mid_idx, bool add)
+{
+	char *smid_pl;
+	int err;
+
+	smid_pl = kmalloc(MLXSW_REG_SMID_LEN, GFP_KERNEL);
+	if (!smid_pl)
+		return -ENOMEM;
+
+	mlxsw_reg_smid_pack(smid_pl, mid_idx,
+			    mlxsw_sp_router_port(mlxsw_sp), add);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(smid), smid_pl);
+	kfree(smid_pl);
+	return err;
+}
+
+static void
+mlxsw_sp_bridge_mrouter_update_mdb(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_bridge_device *bridge_device,
+				   bool add)
+{
+	struct mlxsw_sp_mid *mid;
+
+	list_for_each_entry(mid, &bridge_device->mids_list, list)
+		mlxsw_sp_smid_router_port_set(mlxsw_sp, mid->mid, add);
+}
+
+static int
+mlxsw_sp_port_attr_br_mrouter_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				  struct switchdev_trans *trans,
+				  struct net_device *orig_dev,
+				  bool is_mrouter)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_bridge_device *bridge_device;
+
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
+	/* It's possible we failed to enslave the port, yet this
+	 * operation is executed due to it being deferred.
+	 */
+	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, orig_dev);
+	if (!bridge_device)
+		return 0;
+
+	if (bridge_device->mrouter != is_mrouter)
+		mlxsw_sp_bridge_mrouter_update_mdb(mlxsw_sp, bridge_device,
+						   is_mrouter);
+	bridge_device->mrouter = is_mrouter;
+	return 0;
+}
+
 static int mlxsw_sp_port_attr_set(struct net_device *dev,
 				  const struct switchdev_attr *attr,
 				  struct switchdev_trans *trans)
@@ -793,15 +897,20 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev,
 						     attr->u.vlan_filtering);
 		break;
 	case SWITCHDEV_ATTR_ID_PORT_MROUTER:
-		err = mlxsw_sp_port_attr_mc_router_set(mlxsw_sp_port, trans,
-						       attr->orig_dev,
-						       attr->u.mrouter);
+		err = mlxsw_sp_port_attr_mrouter_set(mlxsw_sp_port, trans,
+						     attr->orig_dev,
+						     attr->u.mrouter);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED:
 		err = mlxsw_sp_port_mc_disabled_set(mlxsw_sp_port, trans,
 						    attr->orig_dev,
 						    attr->u.mc_disabled);
 		break;
+	case SWITCHDEV_ATTR_ID_BRIDGE_MROUTER:
+		err = mlxsw_sp_port_attr_br_mrouter_set(mlxsw_sp_port, trans,
+							attr->orig_dev,
+							attr->u.mrouter);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
@@ -810,14 +919,6 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev,
 	return err;
 }
 
-static bool mlxsw_sp_mc_flood(const struct mlxsw_sp_bridge_port *bridge_port)
-{
-	const struct mlxsw_sp_bridge_device *bridge_device;
-
-	bridge_device = bridge_port->bridge_device;
-	return !bridge_device->multicast_enabled ? true : bridge_port->mrouter;
-}
-
 static int
 mlxsw_sp_port_vlan_fid_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 			    struct mlxsw_sp_bridge_port *bridge_port)
@@ -955,24 +1056,28 @@ mlxsw_sp_port_vlan_bridge_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 	struct mlxsw_sp_bridge_vlan *bridge_vlan;
 	struct mlxsw_sp_bridge_port *bridge_port;
 	u16 vid = mlxsw_sp_port_vlan->vid;
-	bool last;
+	bool last_port, last_vlan;
 
 	if (WARN_ON(mlxsw_sp_fid_type(fid) != MLXSW_SP_FID_TYPE_8021Q &&
 		    mlxsw_sp_fid_type(fid) != MLXSW_SP_FID_TYPE_8021D))
 		return;
 
 	bridge_port = mlxsw_sp_port_vlan->bridge_port;
+	last_vlan = list_is_singular(&bridge_port->vlans_list);
 	bridge_vlan = mlxsw_sp_bridge_vlan_find(bridge_port, vid);
-	last = list_is_singular(&bridge_vlan->port_vlan_list);
+	last_port = list_is_singular(&bridge_vlan->port_vlan_list);
 
 	list_del(&mlxsw_sp_port_vlan->bridge_vlan_node);
 	mlxsw_sp_bridge_vlan_put(bridge_vlan);
 	mlxsw_sp_port_vid_stp_set(mlxsw_sp_port, vid, BR_STATE_DISABLED);
 	mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, false);
-	if (last)
+	if (last_port)
 		mlxsw_sp_bridge_port_fdb_flush(mlxsw_sp_port->mlxsw_sp,
 					       bridge_port,
 					       mlxsw_sp_fid_index(fid));
+	if (last_vlan)
+		mlxsw_sp_bridge_port_mdb_flush(mlxsw_sp_port, bridge_port);
+
 	mlxsw_sp_port_vlan_fid_leave(mlxsw_sp_port_vlan);
 
 	mlxsw_sp_bridge_port_put(mlxsw_sp_port->mlxsw_sp->bridge, bridge_port);
@@ -1182,7 +1287,7 @@ mlxsw_sp_port_fdb_set(struct mlxsw_sp_port *mlxsw_sp_port,
 }
 
 static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr,
-				u16 fid, u16 mid, bool adding)
+				u16 fid, u16 mid_idx, bool adding)
 {
 	char *sfd_pl;
 	int err;
@@ -1193,16 +1298,16 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr,
 
 	mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
 	mlxsw_reg_sfd_mc_pack(sfd_pl, 0, addr, fid,
-			      MLXSW_REG_SFD_REC_ACTION_NOP, mid);
+			      MLXSW_REG_SFD_REC_ACTION_NOP, mid_idx);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
 	kfree(sfd_pl);
 	return err;
 }
 
-static int mlxsw_sp_port_smid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mid,
-				  bool add, bool clear_all_ports)
+static int mlxsw_sp_port_smid_full_entry(struct mlxsw_sp *mlxsw_sp, u16 mid_idx,
+					 long *ports_bitmap,
+					 bool set_router_port)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char *smid_pl;
 	int err, i;
 
@@ -1210,66 +1315,208 @@ static int mlxsw_sp_port_smid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mid,
 	if (!smid_pl)
 		return -ENOMEM;
 
-	mlxsw_reg_smid_pack(smid_pl, mid, mlxsw_sp_port->local_port, add);
-	if (clear_all_ports) {
-		for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++)
-			if (mlxsw_sp->ports[i])
-				mlxsw_reg_smid_port_mask_set(smid_pl, i, 1);
+	mlxsw_reg_smid_pack(smid_pl, mid_idx, 0, false);
+	for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++) {
+		if (mlxsw_sp->ports[i])
+			mlxsw_reg_smid_port_mask_set(smid_pl, i, 1);
 	}
+
+	mlxsw_reg_smid_port_mask_set(smid_pl,
+				     mlxsw_sp_router_port(mlxsw_sp), 1);
+
+	for_each_set_bit(i, ports_bitmap, mlxsw_core_max_ports(mlxsw_sp->core))
+		mlxsw_reg_smid_port_set(smid_pl, i, 1);
+
+	mlxsw_reg_smid_port_set(smid_pl, mlxsw_sp_router_port(mlxsw_sp),
+				set_router_port);
+
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(smid), smid_pl);
+	kfree(smid_pl);
+	return err;
+}
+
+static int mlxsw_sp_port_smid_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				  u16 mid_idx, bool add)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char *smid_pl;
+	int err;
+
+	smid_pl = kmalloc(MLXSW_REG_SMID_LEN, GFP_KERNEL);
+	if (!smid_pl)
+		return -ENOMEM;
+
+	mlxsw_reg_smid_pack(smid_pl, mid_idx, mlxsw_sp_port->local_port, add);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(smid), smid_pl);
 	kfree(smid_pl);
 	return err;
 }
 
-static struct mlxsw_sp_mid *__mlxsw_sp_mc_get(struct mlxsw_sp *mlxsw_sp,
-					      const unsigned char *addr,
-					      u16 fid)
+static struct
+mlxsw_sp_mid *__mlxsw_sp_mc_get(struct mlxsw_sp_bridge_device *bridge_device,
+				const unsigned char *addr,
+				u16 fid)
 {
 	struct mlxsw_sp_mid *mid;
 
-	list_for_each_entry(mid, &mlxsw_sp->bridge->mids_list, list) {
+	list_for_each_entry(mid, &bridge_device->mids_list, list) {
 		if (ether_addr_equal(mid->addr, addr) && mid->fid == fid)
 			return mid;
 	}
 	return NULL;
 }
 
-static struct mlxsw_sp_mid *__mlxsw_sp_mc_alloc(struct mlxsw_sp *mlxsw_sp,
-						const unsigned char *addr,
-						u16 fid)
+static void
+mlxsw_sp_bridge_port_get_ports_bitmap(struct mlxsw_sp *mlxsw_sp,
+				      struct mlxsw_sp_bridge_port *bridge_port,
+				      unsigned long *ports_bitmap)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	u64 max_lag_members, i;
+	int lag_id;
+
+	if (!bridge_port->lagged) {
+		set_bit(bridge_port->system_port, ports_bitmap);
+	} else {
+		max_lag_members = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+						     MAX_LAG_MEMBERS);
+		lag_id = bridge_port->lag_id;
+		for (i = 0; i < max_lag_members; i++) {
+			mlxsw_sp_port = mlxsw_sp_port_lagged_get(mlxsw_sp,
+								 lag_id, i);
+			if (mlxsw_sp_port)
+				set_bit(mlxsw_sp_port->local_port,
+					ports_bitmap);
+		}
+	}
+}
+
+static void
+mlxsw_sp_mc_get_mrouters_bitmap(unsigned long *flood_bitmap,
+				struct mlxsw_sp_bridge_device *bridge_device,
+				struct mlxsw_sp *mlxsw_sp)
 {
-	struct mlxsw_sp_mid *mid;
+	struct mlxsw_sp_bridge_port *bridge_port;
+
+	list_for_each_entry(bridge_port, &bridge_device->ports_list, list) {
+		if (bridge_port->mrouter) {
+			mlxsw_sp_bridge_port_get_ports_bitmap(mlxsw_sp,
+							      bridge_port,
+							      flood_bitmap);
+		}
+	}
+}
+
+static bool
+mlxsw_sp_mc_write_mdb_entry(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_mid *mid,
+			    struct mlxsw_sp_bridge_device *bridge_device)
+{
+	long *flood_bitmap;
+	int num_of_ports;
+	int alloc_size;
 	u16 mid_idx;
+	int err;
 
 	mid_idx = find_first_zero_bit(mlxsw_sp->bridge->mids_bitmap,
 				      MLXSW_SP_MID_MAX);
 	if (mid_idx == MLXSW_SP_MID_MAX)
-		return NULL;
+		return false;
+
+	num_of_ports = mlxsw_core_max_ports(mlxsw_sp->core);
+	alloc_size = sizeof(long) * BITS_TO_LONGS(num_of_ports);
+	flood_bitmap = kzalloc(alloc_size, GFP_KERNEL);
+	if (!flood_bitmap)
+		return false;
+
+	bitmap_copy(flood_bitmap,  mid->ports_in_mid, num_of_ports);
+	mlxsw_sp_mc_get_mrouters_bitmap(flood_bitmap, bridge_device, mlxsw_sp);
+
+	mid->mid = mid_idx;
+	err = mlxsw_sp_port_smid_full_entry(mlxsw_sp, mid_idx, flood_bitmap,
+					    bridge_device->mrouter);
+	kfree(flood_bitmap);
+	if (err)
+		return false;
+
+	err = mlxsw_sp_port_mdb_op(mlxsw_sp, mid->addr, mid->fid, mid_idx,
+				   true);
+	if (err)
+		return false;
+
+	set_bit(mid_idx, mlxsw_sp->bridge->mids_bitmap);
+	mid->in_hw = true;
+	return true;
+}
+
+static int mlxsw_sp_mc_remove_mdb_entry(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_mid *mid)
+{
+	if (!mid->in_hw)
+		return 0;
+
+	clear_bit(mid->mid, mlxsw_sp->bridge->mids_bitmap);
+	mid->in_hw = false;
+	return mlxsw_sp_port_mdb_op(mlxsw_sp, mid->addr, mid->fid, mid->mid,
+				    false);
+}
+
+static struct
+mlxsw_sp_mid *__mlxsw_sp_mc_alloc(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_bridge_device *bridge_device,
+				  const unsigned char *addr,
+				  u16 fid)
+{
+	struct mlxsw_sp_mid *mid;
+	size_t alloc_size;
 
 	mid = kzalloc(sizeof(*mid), GFP_KERNEL);
 	if (!mid)
 		return NULL;
 
-	set_bit(mid_idx, mlxsw_sp->bridge->mids_bitmap);
+	alloc_size = sizeof(unsigned long) *
+		     BITS_TO_LONGS(mlxsw_core_max_ports(mlxsw_sp->core));
+
+	mid->ports_in_mid = kzalloc(alloc_size, GFP_KERNEL);
+	if (!mid->ports_in_mid)
+		goto err_ports_in_mid_alloc;
+
 	ether_addr_copy(mid->addr, addr);
 	mid->fid = fid;
-	mid->mid = mid_idx;
-	mid->ref_count = 0;
-	list_add_tail(&mid->list, &mlxsw_sp->bridge->mids_list);
+	mid->in_hw = false;
+
+	if (!bridge_device->multicast_enabled)
+		goto out;
 
+	if (!mlxsw_sp_mc_write_mdb_entry(mlxsw_sp, mid, bridge_device))
+		goto err_write_mdb_entry;
+
+out:
+	list_add_tail(&mid->list, &bridge_device->mids_list);
 	return mid;
+
+err_write_mdb_entry:
+	kfree(mid->ports_in_mid);
+err_ports_in_mid_alloc:
+	kfree(mid);
+	return NULL;
 }
 
-static int __mlxsw_sp_mc_dec_ref(struct mlxsw_sp *mlxsw_sp,
-				 struct mlxsw_sp_mid *mid)
+static int mlxsw_sp_port_remove_from_mid(struct mlxsw_sp_port *mlxsw_sp_port,
+					 struct mlxsw_sp_mid *mid)
 {
-	if (--mid->ref_count == 0) {
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	int err = 0;
+
+	clear_bit(mlxsw_sp_port->local_port, mid->ports_in_mid);
+	if (bitmap_empty(mid->ports_in_mid,
+			 mlxsw_core_max_ports(mlxsw_sp->core))) {
+		err = mlxsw_sp_mc_remove_mdb_entry(mlxsw_sp, mid);
 		list_del(&mid->list);
-		clear_bit(mid->mid, mlxsw_sp->bridge->mids_bitmap);
+		kfree(mid->ports_in_mid);
 		kfree(mid);
-		return 1;
 	}
-	return 0;
+	return err;
 }
 
 static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -1302,39 +1549,72 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	fid_index = mlxsw_sp_fid_index(mlxsw_sp_port_vlan->fid);
 
-	mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, fid_index);
+	mid = __mlxsw_sp_mc_get(bridge_device, mdb->addr, fid_index);
 	if (!mid) {
-		mid = __mlxsw_sp_mc_alloc(mlxsw_sp, mdb->addr, fid_index);
+		mid = __mlxsw_sp_mc_alloc(mlxsw_sp, bridge_device, mdb->addr,
+					  fid_index);
 		if (!mid) {
 			netdev_err(dev, "Unable to allocate MC group\n");
 			return -ENOMEM;
 		}
 	}
-	mid->ref_count++;
+	set_bit(mlxsw_sp_port->local_port, mid->ports_in_mid);
+
+	if (!bridge_device->multicast_enabled)
+		return 0;
 
-	err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, true,
-				     mid->ref_count == 1);
+	if (bridge_port->mrouter)
+		return 0;
+
+	err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, true);
 	if (err) {
 		netdev_err(dev, "Unable to set SMID\n");
 		goto err_out;
 	}
 
-	if (mid->ref_count == 1) {
-		err = mlxsw_sp_port_mdb_op(mlxsw_sp, mdb->addr, fid_index,
-					   mid->mid, true);
-		if (err) {
-			netdev_err(dev, "Unable to set MC SFD\n");
-			goto err_out;
-		}
-	}
-
 	return 0;
 
 err_out:
-	__mlxsw_sp_mc_dec_ref(mlxsw_sp, mid);
+	mlxsw_sp_port_remove_from_mid(mlxsw_sp_port, mid);
 	return err;
 }
 
+static void
+mlxsw_sp_bridge_mdb_mc_enable_sync(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct mlxsw_sp_bridge_device
+				   *bridge_device)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_mid *mid;
+	bool mc_enabled;
+
+	mc_enabled = bridge_device->multicast_enabled;
+
+	list_for_each_entry(mid, &bridge_device->mids_list, list) {
+		if (mc_enabled)
+			mlxsw_sp_mc_write_mdb_entry(mlxsw_sp, mid,
+						    bridge_device);
+		else
+			mlxsw_sp_mc_remove_mdb_entry(mlxsw_sp, mid);
+	}
+}
+
+static void
+mlxsw_sp_port_mrouter_update_mdb(struct mlxsw_sp_port *mlxsw_sp_port,
+				 struct mlxsw_sp_bridge_port *bridge_port,
+				 bool add)
+{
+	struct mlxsw_sp_bridge_device *bridge_device;
+	struct mlxsw_sp_mid *mid;
+
+	bridge_device = bridge_port->bridge_device;
+
+	list_for_each_entry(mid, &bridge_device->mids_list, list) {
+		if (!test_bit(mlxsw_sp_port->local_port, mid->ports_in_mid))
+			mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, add);
+	}
+}
+
 static int mlxsw_sp_port_obj_add(struct net_device *dev,
 				 const struct switchdev_obj *obj,
 				 struct switchdev_trans *trans)
@@ -1399,6 +1679,30 @@ static int mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
 	return 0;
 }
 
+static int
+__mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
+			struct mlxsw_sp_bridge_port *bridge_port,
+			struct mlxsw_sp_mid *mid)
+{
+	struct net_device *dev = mlxsw_sp_port->dev;
+	int err;
+
+	if (bridge_port->bridge_device->multicast_enabled) {
+		if (bridge_port->bridge_device->multicast_enabled) {
+			err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid,
+						     false);
+			if (err)
+				netdev_err(dev, "Unable to remove port from SMID\n");
+		}
+	}
+
+	err = mlxsw_sp_port_remove_from_mid(mlxsw_sp_port, mid);
+	if (err)
+		netdev_err(dev, "Unable to remove MC SFD\n");
+
+	return err;
+}
+
 static int mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
 				 const struct switchdev_obj_port_mdb *mdb)
 {
@@ -1410,8 +1714,6 @@ static int mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct mlxsw_sp_bridge_port *bridge_port;
 	struct mlxsw_sp_mid *mid;
 	u16 fid_index;
-	u16 mid_idx;
-	int err = 0;
 
 	bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
 	if (!bridge_port)
@@ -1426,25 +1728,33 @@ static int mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	fid_index = mlxsw_sp_fid_index(mlxsw_sp_port_vlan->fid);
 
-	mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, fid_index);
+	mid = __mlxsw_sp_mc_get(bridge_device, mdb->addr, fid_index);
 	if (!mid) {
 		netdev_err(dev, "Unable to remove port from MC DB\n");
 		return -EINVAL;
 	}
 
-	err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, false, false);
-	if (err)
-		netdev_err(dev, "Unable to remove port from SMID\n");
+	return __mlxsw_sp_port_mdb_del(mlxsw_sp_port, bridge_port, mid);
+}
 
-	mid_idx = mid->mid;
-	if (__mlxsw_sp_mc_dec_ref(mlxsw_sp, mid)) {
-		err = mlxsw_sp_port_mdb_op(mlxsw_sp, mdb->addr, fid_index,
-					   mid_idx, false);
-		if (err)
-			netdev_err(dev, "Unable to remove MC SFD\n");
-	}
+static void
+mlxsw_sp_bridge_port_mdb_flush(struct mlxsw_sp_port *mlxsw_sp_port,
+			       struct mlxsw_sp_bridge_port *bridge_port)
+{
+	struct mlxsw_sp_bridge_device *bridge_device;
+	struct mlxsw_sp_mid *mid, *tmp;
 
-	return err;
+	bridge_device = bridge_port->bridge_device;
+
+	list_for_each_entry_safe(mid, tmp, &bridge_device->mids_list, list) {
+		if (test_bit(mlxsw_sp_port->local_port, mid->ports_in_mid)) {
+			__mlxsw_sp_port_mdb_del(mlxsw_sp_port, bridge_port,
+						mid);
+		} else if (bridge_device->multicast_enabled &&
+			   bridge_port->mrouter) {
+			mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, false);
+		}
+	}
 }
 
 static int mlxsw_sp_port_obj_del(struct net_device *dev,
@@ -1497,12 +1807,15 @@ static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = {
 static int
 mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 				struct mlxsw_sp_bridge_port *bridge_port,
-				struct mlxsw_sp_port *mlxsw_sp_port)
+				struct mlxsw_sp_port *mlxsw_sp_port,
+				struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 
-	if (is_vlan_dev(bridge_port->dev))
+	if (is_vlan_dev(bridge_port->dev)) {
+		NL_SET_ERR_MSG(extack, "spectrum: Can not enslave a VLAN device to a VLAN-aware bridge");
 		return -EINVAL;
+	}
 
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, 1);
 	if (WARN_ON(!mlxsw_sp_port_vlan))
@@ -1559,13 +1872,16 @@ mlxsw_sp_port_is_br_member(const struct mlxsw_sp_port *mlxsw_sp_port,
 static int
 mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 				struct mlxsw_sp_bridge_port *bridge_port,
-				struct mlxsw_sp_port *mlxsw_sp_port)
+				struct mlxsw_sp_port *mlxsw_sp_port,
+				struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 	u16 vid;
 
-	if (!is_vlan_dev(bridge_port->dev))
+	if (!is_vlan_dev(bridge_port->dev)) {
+		NL_SET_ERR_MSG(extack, "spectrum: Only VLAN devices can be enslaved to a VLAN-unaware bridge");
 		return -EINVAL;
+	}
 	vid = vlan_dev_vlan_id(bridge_port->dev);
 
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
@@ -1573,7 +1889,7 @@ mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 		return -EINVAL;
 
 	if (mlxsw_sp_port_is_br_member(mlxsw_sp_port, bridge_device->dev)) {
-		netdev_err(mlxsw_sp_port->dev, "Can't bridge VLAN uppers of the same port\n");
+		NL_SET_ERR_MSG(extack, "spectrum: Can not bridge VLAN uppers of the same port");
 		return -EINVAL;
 	}
 
@@ -1616,7 +1932,8 @@ static const struct mlxsw_sp_bridge_ops mlxsw_sp_bridge_8021d_ops = {
 
 int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port,
 			      struct net_device *brport_dev,
-			      struct net_device *br_dev)
+			      struct net_device *br_dev,
+			      struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_bridge_device *bridge_device;
@@ -1629,7 +1946,7 @@ int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	bridge_device = bridge_port->bridge_device;
 
 	err = bridge_device->ops->port_join(bridge_device, bridge_port,
-					    mlxsw_sp_port);
+					    mlxsw_sp_port, extack);
 	if (err)
 		goto err_port_join;
 
@@ -1981,17 +2298,6 @@ static void mlxsw_sp_fdb_fini(struct mlxsw_sp *mlxsw_sp)
 
 }
 
-static void mlxsw_sp_mids_fini(struct mlxsw_sp *mlxsw_sp)
-{
-	struct mlxsw_sp_mid *mid, *tmp;
-
-	list_for_each_entry_safe(mid, tmp, &mlxsw_sp->bridge->mids_list, list) {
-		list_del(&mid->list);
-		clear_bit(mid->mid, mlxsw_sp->bridge->mids_bitmap);
-		kfree(mid);
-	}
-}
-
 int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_bridge *bridge;
@@ -2003,7 +2309,6 @@ int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
 	bridge->mlxsw_sp = mlxsw_sp;
 
 	INIT_LIST_HEAD(&mlxsw_sp->bridge->bridges_list);
-	INIT_LIST_HEAD(&mlxsw_sp->bridge->mids_list);
 
 	bridge->bridge_8021q_ops = &mlxsw_sp_bridge_8021q_ops;
 	bridge->bridge_8021d_ops = &mlxsw_sp_bridge_8021d_ops;
@@ -2014,7 +2319,6 @@ int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
 void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	mlxsw_sp_fdb_fini(mlxsw_sp);
-	mlxsw_sp_mids_fini(mlxsw_sp);
 	WARN_ON(!list_empty(&mlxsw_sp->bridge->bridges_list));
 	kfree(mlxsw_sp->bridge);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index f396a1fef633..ec6cef8267ae 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -62,6 +62,8 @@ enum {
 	MLXSW_TRAP_ID_TTLERROR = 0x53,
 	MLXSW_TRAP_ID_LBERROR = 0x54,
 	MLXSW_TRAP_ID_IPV4_OSPF = 0x55,
+	MLXSW_TRAP_ID_IPV4_PIM = 0x58,
+	MLXSW_TRAP_ID_RPF = 0x5C,
 	MLXSW_TRAP_ID_IP2ME = 0x5F,
 	MLXSW_TRAP_ID_IPV6_UNSPECIFIED_ADDRESS = 0x60,
 	MLXSW_TRAP_ID_IPV6_LINK_LOCAL_DEST = 0x61,
@@ -89,6 +91,10 @@ enum {
 	MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6,
 	MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7,
 	MLXSW_TRAP_ID_ACL0 = 0x1C0,
+	/* Multicast trap used for routes with trap action */
+	MLXSW_TRAP_ID_ACL1 = 0x1C1,
+	/* Multicast trap used for routes with trap-and-forward action */
+	MLXSW_TRAP_ID_ACL2 = 0x1C2,
 
 	MLXSW_TRAP_ID_MAX = 0x1FF
 };
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index e798fbe08600..52207508744c 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -4338,11 +4338,11 @@ static void ksz_stop_timer(struct ksz_timer_info *info)
 }
 
 static void ksz_init_timer(struct ksz_timer_info *info, int period,
-	void (*function)(unsigned long), void *data)
+	void (*function)(struct timer_list *))
 {
 	info->max = 0;
 	info->period = period;
-	setup_timer(&info->timer, function, (unsigned long)data);
+	timer_setup(&info->timer, function, 0);
 }
 
 static void ksz_update_timer(struct ksz_timer_info *info)
@@ -6689,9 +6689,9 @@ static void mib_read_work(struct work_struct *work)
 	}
 }
 
-static void mib_monitor(unsigned long ptr)
+static void mib_monitor(struct timer_list *t)
 {
-	struct dev_info *hw_priv = (struct dev_info *) ptr;
+	struct dev_info *hw_priv = from_timer(hw_priv, t, mib_timer_info.timer);
 
 	mib_read_work(&hw_priv->mib_read);
 
@@ -6716,10 +6716,10 @@ static void mib_monitor(unsigned long ptr)
  *
  * This routine is run in a kernel timer to monitor the network device.
  */
-static void dev_monitor(unsigned long ptr)
+static void dev_monitor(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) ptr;
-	struct dev_priv *priv = netdev_priv(dev);
+	struct dev_priv *priv = from_timer(priv, t, monitor_timer_info.timer);
+	struct net_device *dev = priv->mii_if.dev;
 	struct dev_info *hw_priv = priv->adapter;
 	struct ksz_hw *hw = &hw_priv->hw;
 	struct ksz_port *port = &priv->port;
@@ -6789,7 +6789,7 @@ static int __init netdev_init(struct net_device *dev)
 
 	/* 500 ms timeout */
 	ksz_init_timer(&priv->monitor_timer_info, 500 * HZ / 1000,
-		dev_monitor, dev);
+		dev_monitor);
 
 	/* 500 ms timeout */
 	dev->watchdog_timeo = HZ / 2;
@@ -7065,7 +7065,7 @@ static int pcidev_init(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	/* 500 ms timeout */
 	ksz_init_timer(&hw_priv->mib_timer_info, 500 * HZ / 1000,
-		mib_monitor, hw_priv);
+		mib_monitor);
 
 	for (i = 0; i < hw->dev_count; i++) {
 		dev = alloc_etherdev(sizeof(struct dev_priv));
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index 18af2a23a933..b9a1a9f999ea 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -610,7 +610,7 @@ static int netdev_open(struct net_device *dev);
 static void do_cable_magic(struct net_device *dev);
 static void undo_cable_magic(struct net_device *dev);
 static void check_link(struct net_device *dev);
-static void netdev_timer(unsigned long data);
+static void netdev_timer(struct timer_list *t);
 static void dump_ring(struct net_device *dev);
 static void ns_tx_timeout(struct net_device *dev);
 static int alloc_ring(struct net_device *dev);
@@ -1571,10 +1571,8 @@ static int netdev_open(struct net_device *dev)
 			dev->name, (int)readl(ioaddr + ChipCmd));
 
 	/* Set the timer to check for link beat. */
-	init_timer(&np->timer);
+	timer_setup(&np->timer, netdev_timer, 0);
 	np->timer.expires = round_jiffies(jiffies + NATSEMI_TIMER_FREQ);
-	np->timer.data = (unsigned long)dev;
-	np->timer.function = netdev_timer; /* timer handler */
 	add_timer(&np->timer);
 
 	return 0;
@@ -1789,10 +1787,10 @@ static void init_registers(struct net_device *dev)
  *    this check via dspcfg_workaround sysfs option.
  * 3) check of death of the RX path due to OOM
  */
-static void netdev_timer(unsigned long data)
+static void netdev_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct netdev_private *np = netdev_priv(dev);
+	struct netdev_private *np = from_timer(np, t, timer);
+	struct net_device *dev = np->dev;
 	void __iomem * ioaddr = ns_ioaddr(dev);
 	int next_tick = NATSEMI_TIMER_FREQ;
 	const int irq = np->pci_dev->irq;
diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c
index 729095db3e08..958fced4dacf 100644
--- a/drivers/net/ethernet/natsemi/ns83820.c
+++ b/drivers/net/ethernet/natsemi/ns83820.c
@@ -1600,10 +1600,10 @@ static void ns83820_tx_timeout(struct net_device *ndev)
 	spin_unlock_irqrestore(&dev->tx_lock, flags);
 }
 
-static void ns83820_tx_watch(unsigned long data)
+static void ns83820_tx_watch(struct timer_list *t)
 {
-	struct net_device *ndev = (void *)data;
-	struct ns83820 *dev = PRIV(ndev);
+	struct ns83820 *dev = from_timer(dev, t, tx_watchdog);
+	struct net_device *ndev = dev->ndev;
 
 #if defined(DEBUG)
 	printk("ns83820_tx_watch: %u %u %d\n",
@@ -1652,9 +1652,7 @@ static int ns83820_open(struct net_device *ndev)
 	writel(0, dev->base + TXDP_HI);
 	writel(desc, dev->base + TXDP);
 
-	init_timer(&dev->tx_watchdog);
-	dev->tx_watchdog.data = (unsigned long)ndev;
-	dev->tx_watchdog.function = ns83820_tx_watch;
+	timer_setup(&dev->tx_watchdog, ns83820_tx_watch, 0);
 	mod_timer(&dev->tx_watchdog, jiffies + 2*HZ);
 
 	netif_start_queue(ndev);	/* FIXME: wait for phy to come up */
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 462eda926b1c..b8983e73265a 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -337,12 +337,6 @@ static const char ethtool_driver_stats_keys[][ETH_GSTRING_LEN] = {
 #define S2IO_TEST_LEN	ARRAY_SIZE(s2io_gstrings)
 #define S2IO_STRINGS_LEN	(S2IO_TEST_LEN * ETH_GSTRING_LEN)
 
-#define S2IO_TIMER_CONF(timer, handle, arg, exp)	\
-	init_timer(&timer);				\
-	timer.function = handle;			\
-	timer.data = (unsigned long)arg;		\
-	mod_timer(&timer, (jiffies + exp))		\
-
 /* copy mac addr to def_mac_addr array */
 static void do_s2io_copy_mac_addr(struct s2io_nic *sp, int offset, u64 mac_addr)
 {
@@ -4193,9 +4187,9 @@ pci_map_failed:
 }
 
 static void
-s2io_alarm_handle(unsigned long data)
+s2io_alarm_handle(struct timer_list *t)
 {
-	struct s2io_nic *sp = (struct s2io_nic *)data;
+	struct s2io_nic *sp = from_timer(sp, t, alarm_timer);
 	struct net_device *dev = sp->dev;
 
 	s2io_handle_errors(dev);
@@ -7186,7 +7180,8 @@ static int s2io_card_up(struct s2io_nic *sp)
 		return -ENODEV;
 	}
 
-	S2IO_TIMER_CONF(sp->alarm_timer, s2io_alarm_handle, sp, (HZ/2));
+	timer_setup(&sp->alarm_timer, s2io_alarm_handle, 0);
+	mod_timer(&sp->alarm_timer, jiffies + HZ / 2);
 
 	set_bit(__S2IO_STATE_CARD_UP, &sp->state);
 
diff --git a/drivers/net/ethernet/neterion/s2io.h b/drivers/net/ethernet/neterion/s2io.h
index 6c5997dc8afc..1a24a7218794 100644
--- a/drivers/net/ethernet/neterion/s2io.h
+++ b/drivers/net/ethernet/neterion/s2io.h
@@ -1094,7 +1094,7 @@ static int s2io_poll_msix(struct napi_struct *napi, int budget);
 static int s2io_poll_inta(struct napi_struct *napi, int budget);
 static void s2io_init_pci(struct s2io_nic * sp);
 static int do_s2io_prog_unicast(struct net_device *dev, u8 *addr);
-static void s2io_alarm_handle(unsigned long data);
+static void s2io_alarm_handle(struct timer_list *t);
 static irqreturn_t
 s2io_msix_ring_handle(int irq, void *dev_id);
 static irqreturn_t
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index 50ea69d88480..5d5b9855e24e 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -2597,9 +2597,9 @@ INTA_MODE:
 	return VXGE_HW_OK;
 }
 
-static void vxge_poll_vp_reset(unsigned long data)
+static void vxge_poll_vp_reset(struct timer_list *t)
 {
-	struct vxgedev *vdev = (struct vxgedev *)data;
+	struct vxgedev *vdev = from_timer(vdev, t, vp_reset_timer);
 	int i, j = 0;
 
 	for (i = 0; i < vdev->no_of_vpath; i++) {
@@ -2616,9 +2616,9 @@ static void vxge_poll_vp_reset(unsigned long data)
 	mod_timer(&vdev->vp_reset_timer, jiffies + HZ / 2);
 }
 
-static void vxge_poll_vp_lockup(unsigned long data)
+static void vxge_poll_vp_lockup(struct timer_list *t)
 {
-	struct vxgedev *vdev = (struct vxgedev *)data;
+	struct vxgedev *vdev = from_timer(vdev, t, vp_lockup_timer);
 	enum vxge_hw_status status = VXGE_HW_OK;
 	struct vxge_vpath *vpath;
 	struct vxge_ring *ring;
@@ -2858,12 +2858,12 @@ static int vxge_open(struct net_device *dev)
 		vdev->config.rx_pause_enable);
 
 	if (vdev->vp_reset_timer.function == NULL)
-		vxge_os_timer(&vdev->vp_reset_timer, vxge_poll_vp_reset, vdev,
+		vxge_os_timer(&vdev->vp_reset_timer, vxge_poll_vp_reset,
 			      HZ / 2);
 
 	/* There is no need to check for RxD leak and RxD lookup on Titan1A */
 	if (vdev->titan1 && vdev->vp_lockup_timer.function == NULL)
-		vxge_os_timer(&vdev->vp_lockup_timer, vxge_poll_vp_lockup, vdev,
+		vxge_os_timer(&vdev->vp_lockup_timer, vxge_poll_vp_lockup,
 			      HZ / 2);
 
 	set_bit(__VXGE_STATE_CARD_UP, &vdev->state);
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.h b/drivers/net/ethernet/neterion/vxge/vxge-main.h
index 3a79d93b8445..59a57ff5e96a 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.h
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.h
@@ -417,12 +417,10 @@ struct vxge_tx_priv {
 	module_param(p, int, 0)
 
 static inline
-void vxge_os_timer(struct timer_list *timer, void (*func)(unsigned long data),
-		   struct vxgedev *vdev, unsigned long timeout)
+void vxge_os_timer(struct timer_list *timer, void (*func)(struct timer_list *),
+		   unsigned long timeout)
 {
-	init_timer(timer);
-	timer->function = func;
-	timer->data = (unsigned long)vdev;
+	timer_setup(timer, func, 0);
 	mod_timer(timer, jiffies + timeout);
 }
 
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
index 5f630a24e491..0c3b5dea2858 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
@@ -1209,9 +1209,6 @@ void vxge_hw_ring_rxd_pre_post(struct __vxge_hw_ring *ring, void *rxdh)
 void vxge_hw_ring_rxd_post_post(struct __vxge_hw_ring *ring, void *rxdh)
 {
 	struct vxge_hw_ring_rxd_1 *rxdp = (struct vxge_hw_ring_rxd_1 *)rxdh;
-	struct __vxge_hw_channel *channel;
-
-	channel = &ring->channel;
 
 	rxdp->control_0	= VXGE_HW_RING_RXD_LIST_OWN_ADAPTER;
 
@@ -1359,11 +1356,8 @@ exit:
 enum vxge_hw_status vxge_hw_ring_handle_tcode(
 	struct __vxge_hw_ring *ring, void *rxdh, u8 t_code)
 {
-	struct __vxge_hw_channel *channel;
 	enum vxge_hw_status status = VXGE_HW_OK;
 
-	channel = &ring->channel;
-
 	/* If the t_code is not supported and if the
 	 * t_code is other than 0x5 (unparseable packet
 	 * such as unknown UPV6 header), Drop it !!!
@@ -1399,10 +1393,6 @@ exit:
 static void __vxge_hw_non_offload_db_post(struct __vxge_hw_fifo *fifo,
 	u64 txdl_ptr, u32 num_txds, u32 no_snoop)
 {
-	struct __vxge_hw_channel *channel;
-
-	channel = &fifo->channel;
-
 	writeq(VXGE_HW_NODBW_TYPE(VXGE_HW_NODBW_TYPE_NODBW) |
 		VXGE_HW_NODBW_LAST_TXD_NUMBER(num_txds) |
 		VXGE_HW_NODBW_GET_NO_SNOOP(no_snoop),
@@ -1506,9 +1496,6 @@ void vxge_hw_fifo_txdl_buffer_set(struct __vxge_hw_fifo *fifo,
 {
 	struct __vxge_hw_fifo_txdl_priv *txdl_priv;
 	struct vxge_hw_fifo_txd *txdp, *txdp_last;
-	struct __vxge_hw_channel *channel;
-
-	channel = &fifo->channel;
 
 	txdl_priv = __vxge_hw_fifo_txdl_priv(fifo, txdlh);
 	txdp = (struct vxge_hw_fifo_txd *)txdlh  +  txdl_priv->frags;
@@ -1554,9 +1541,6 @@ void vxge_hw_fifo_txdl_post(struct __vxge_hw_fifo *fifo, void *txdlh)
 	struct __vxge_hw_fifo_txdl_priv *txdl_priv;
 	struct vxge_hw_fifo_txd *txdp_last;
 	struct vxge_hw_fifo_txd *txdp_first;
-	struct __vxge_hw_channel *channel;
-
-	channel = &fifo->channel;
 
 	txdl_priv = __vxge_hw_fifo_txdl_priv(fifo, txdlh);
 	txdp_first = txdlh;
@@ -1672,10 +1656,7 @@ enum vxge_hw_status vxge_hw_fifo_handle_tcode(struct __vxge_hw_fifo *fifo,
 					      void *txdlh,
 					      enum vxge_hw_fifo_tcode t_code)
 {
-	struct __vxge_hw_channel *channel;
-
 	enum vxge_hw_status status = VXGE_HW_OK;
-	channel = &fifo->channel;
 
 	if (((t_code & 0x7) < 0) || ((t_code & 0x7) > 0x4)) {
 		status = VXGE_HW_ERR_INVALID_TCODE;
diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile
index 3cafa3d15082..24c4408b5734 100644
--- a/drivers/net/ethernet/netronome/nfp/Makefile
+++ b/drivers/net/ethernet/netronome/nfp/Makefile
@@ -15,6 +15,7 @@ nfp-objs := \
 	    nfpcore/nfp_resource.o \
 	    nfpcore/nfp_rtsym.o \
 	    nfpcore/nfp_target.o \
+	    nfp_asm.o \
 	    nfp_app.o \
 	    nfp_app_nic.o \
 	    nfp_devlink.o \
@@ -27,8 +28,6 @@ nfp-objs := \
 	    nfp_net_sriov.o \
 	    nfp_netvf_main.o \
 	    nfp_port.o \
-	    bpf/main.o \
-	    bpf/offload.o \
 	    nic/main.o
 
 ifeq ($(CONFIG_NFP_APP_FLOWER),y)
@@ -38,11 +37,14 @@ nfp-objs += \
 	    flower/main.o \
 	    flower/match.o \
 	    flower/metadata.o \
-	    flower/offload.o
+	    flower/offload.o \
+	    flower/tunnel_conf.o
 endif
 
 ifeq ($(CONFIG_BPF_SYSCALL),y)
 nfp-objs += \
+	    bpf/main.o \
+	    bpf/offload.o \
 	    bpf/verifier.o \
 	    bpf/jit.o
 endif
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 239dfbe8a0a1..2609a2487100 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -110,150 +110,7 @@ nfp_prog_offset_to_index(struct nfp_prog *nfp_prog, unsigned int offset)
 	return offset - nfp_prog->start_off;
 }
 
-/* --- SW reg --- */
-struct nfp_insn_ur_regs {
-	enum alu_dst_ab dst_ab;
-	u16 dst;
-	u16 areg, breg;
-	bool swap;
-	bool wr_both;
-};
-
-struct nfp_insn_re_regs {
-	enum alu_dst_ab dst_ab;
-	u8 dst;
-	u8 areg, breg;
-	bool swap;
-	bool wr_both;
-	bool i8;
-};
-
-static u16 nfp_swreg_to_unreg(u32 swreg, bool is_dst)
-{
-	u16 val = FIELD_GET(NN_REG_VAL, swreg);
-
-	switch (FIELD_GET(NN_REG_TYPE, swreg)) {
-	case NN_REG_GPR_A:
-	case NN_REG_GPR_B:
-	case NN_REG_GPR_BOTH:
-		return val;
-	case NN_REG_NNR:
-		return UR_REG_NN | val;
-	case NN_REG_XFER:
-		return UR_REG_XFR | val;
-	case NN_REG_IMM:
-		if (val & ~0xff) {
-			pr_err("immediate too large\n");
-			return 0;
-		}
-		return UR_REG_IMM_encode(val);
-	case NN_REG_NONE:
-		return is_dst ? UR_REG_NO_DST : REG_NONE;
-	default:
-		pr_err("unrecognized reg encoding %08x\n", swreg);
-		return 0;
-	}
-}
-
-static int
-swreg_to_unrestricted(u32 dst, u32 lreg, u32 rreg, struct nfp_insn_ur_regs *reg)
-{
-	memset(reg, 0, sizeof(*reg));
-
-	/* Decode destination */
-	if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_IMM)
-		return -EFAULT;
-
-	if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_GPR_B)
-		reg->dst_ab = ALU_DST_B;
-	if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_GPR_BOTH)
-		reg->wr_both = true;
-	reg->dst = nfp_swreg_to_unreg(dst, true);
-
-	/* Decode source operands */
-	if (FIELD_GET(NN_REG_TYPE, lreg) == FIELD_GET(NN_REG_TYPE, rreg))
-		return -EFAULT;
-
-	if (FIELD_GET(NN_REG_TYPE, lreg) == NN_REG_GPR_B ||
-	    FIELD_GET(NN_REG_TYPE, rreg) == NN_REG_GPR_A) {
-		reg->areg = nfp_swreg_to_unreg(rreg, false);
-		reg->breg = nfp_swreg_to_unreg(lreg, false);
-		reg->swap = true;
-	} else {
-		reg->areg = nfp_swreg_to_unreg(lreg, false);
-		reg->breg = nfp_swreg_to_unreg(rreg, false);
-	}
-
-	return 0;
-}
-
-static u16 nfp_swreg_to_rereg(u32 swreg, bool is_dst, bool has_imm8, bool *i8)
-{
-	u16 val = FIELD_GET(NN_REG_VAL, swreg);
-
-	switch (FIELD_GET(NN_REG_TYPE, swreg)) {
-	case NN_REG_GPR_A:
-	case NN_REG_GPR_B:
-	case NN_REG_GPR_BOTH:
-		return val;
-	case NN_REG_XFER:
-		return RE_REG_XFR | val;
-	case NN_REG_IMM:
-		if (val & ~(0x7f | has_imm8 << 7)) {
-			pr_err("immediate too large\n");
-			return 0;
-		}
-		*i8 = val & 0x80;
-		return RE_REG_IMM_encode(val & 0x7f);
-	case NN_REG_NONE:
-		return is_dst ? RE_REG_NO_DST : REG_NONE;
-	default:
-		pr_err("unrecognized reg encoding\n");
-		return 0;
-	}
-}
-
-static int
-swreg_to_restricted(u32 dst, u32 lreg, u32 rreg, struct nfp_insn_re_regs *reg,
-		    bool has_imm8)
-{
-	memset(reg, 0, sizeof(*reg));
-
-	/* Decode destination */
-	if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_IMM)
-		return -EFAULT;
-
-	if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_GPR_B)
-		reg->dst_ab = ALU_DST_B;
-	if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_GPR_BOTH)
-		reg->wr_both = true;
-	reg->dst = nfp_swreg_to_rereg(dst, true, false, NULL);
-
-	/* Decode source operands */
-	if (FIELD_GET(NN_REG_TYPE, lreg) == FIELD_GET(NN_REG_TYPE, rreg))
-		return -EFAULT;
-
-	if (FIELD_GET(NN_REG_TYPE, lreg) == NN_REG_GPR_B ||
-	    FIELD_GET(NN_REG_TYPE, rreg) == NN_REG_GPR_A) {
-		reg->areg = nfp_swreg_to_rereg(rreg, false, has_imm8, &reg->i8);
-		reg->breg = nfp_swreg_to_rereg(lreg, false, has_imm8, &reg->i8);
-		reg->swap = true;
-	} else {
-		reg->areg = nfp_swreg_to_rereg(lreg, false, has_imm8, &reg->i8);
-		reg->breg = nfp_swreg_to_rereg(rreg, false, has_imm8, &reg->i8);
-	}
-
-	return 0;
-}
-
 /* --- Emitters --- */
-static const struct cmd_tgt_act cmd_tgt_act[__CMD_TGT_MAP_SIZE] = {
-	[CMD_TGT_WRITE8] =		{ 0x00, 0x42 },
-	[CMD_TGT_READ8] =		{ 0x01, 0x43 },
-	[CMD_TGT_READ_LE] =		{ 0x01, 0x40 },
-	[CMD_TGT_READ_SWAP_LE] =	{ 0x03, 0x40 },
-};
-
 static void
 __emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op,
 	   u8 mode, u8 xfer, u8 areg, u8 breg, u8 size, bool sync)
@@ -281,7 +138,7 @@ __emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op,
 
 static void
 emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op,
-	 u8 mode, u8 xfer, u32 lreg, u32 rreg, u8 size, bool sync)
+	 u8 mode, u8 xfer, swreg lreg, swreg rreg, u8 size, bool sync)
 {
 	struct nfp_insn_re_regs reg;
 	int err;
@@ -296,6 +153,11 @@ emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op,
 		nfp_prog->error = -EFAULT;
 		return;
 	}
+	if (reg.dst_lmextn || reg.src_lmextn) {
+		pr_err("cmd can't use LMextn\n");
+		nfp_prog->error = -EFAULT;
+		return;
+	}
 
 	__emit_cmd(nfp_prog, op, mode, xfer, reg.areg, reg.breg, size, sync);
 }
@@ -341,7 +203,7 @@ emit_br(struct nfp_prog *nfp_prog, enum br_mask mask, u16 addr, u8 defer)
 
 static void
 __emit_br_byte(struct nfp_prog *nfp_prog, u8 areg, u8 breg, bool imm8,
-	       u8 byte, bool equal, u16 addr, u8 defer)
+	       u8 byte, bool equal, u16 addr, u8 defer, bool src_lmextn)
 {
 	u16 addr_lo, addr_hi;
 	u64 insn;
@@ -357,32 +219,34 @@ __emit_br_byte(struct nfp_prog *nfp_prog, u8 areg, u8 breg, bool imm8,
 		FIELD_PREP(OP_BB_EQ, equal) |
 		FIELD_PREP(OP_BB_DEFBR, defer) |
 		FIELD_PREP(OP_BB_ADDR_LO, addr_lo) |
-		FIELD_PREP(OP_BB_ADDR_HI, addr_hi);
+		FIELD_PREP(OP_BB_ADDR_HI, addr_hi) |
+		FIELD_PREP(OP_BB_SRC_LMEXTN, src_lmextn);
 
 	nfp_prog_push(nfp_prog, insn);
 }
 
 static void
 emit_br_byte_neq(struct nfp_prog *nfp_prog,
-		 u32 dst, u8 imm, u8 byte, u16 addr, u8 defer)
+		 swreg src, u8 imm, u8 byte, u16 addr, u8 defer)
 {
 	struct nfp_insn_re_regs reg;
 	int err;
 
-	err = swreg_to_restricted(reg_none(), dst, reg_imm(imm), &reg, true);
+	err = swreg_to_restricted(reg_none(), src, reg_imm(imm), &reg, true);
 	if (err) {
 		nfp_prog->error = err;
 		return;
 	}
 
 	__emit_br_byte(nfp_prog, reg.areg, reg.breg, reg.i8, byte, false, addr,
-		       defer);
+		       defer, reg.src_lmextn);
 }
 
 static void
 __emit_immed(struct nfp_prog *nfp_prog, u16 areg, u16 breg, u16 imm_hi,
 	     enum immed_width width, bool invert,
-	     enum immed_shift shift, bool wr_both)
+	     enum immed_shift shift, bool wr_both,
+	     bool dst_lmextn, bool src_lmextn)
 {
 	u64 insn;
 
@@ -393,19 +257,21 @@ __emit_immed(struct nfp_prog *nfp_prog, u16 areg, u16 breg, u16 imm_hi,
 		FIELD_PREP(OP_IMMED_WIDTH, width) |
 		FIELD_PREP(OP_IMMED_INV, invert) |
 		FIELD_PREP(OP_IMMED_SHIFT, shift) |
-		FIELD_PREP(OP_IMMED_WR_AB, wr_both);
+		FIELD_PREP(OP_IMMED_WR_AB, wr_both) |
+		FIELD_PREP(OP_IMMED_SRC_LMEXTN, src_lmextn) |
+		FIELD_PREP(OP_IMMED_DST_LMEXTN, dst_lmextn);
 
 	nfp_prog_push(nfp_prog, insn);
 }
 
 static void
-emit_immed(struct nfp_prog *nfp_prog, u32 dst, u16 imm,
+emit_immed(struct nfp_prog *nfp_prog, swreg dst, u16 imm,
 	   enum immed_width width, bool invert, enum immed_shift shift)
 {
 	struct nfp_insn_ur_regs reg;
 	int err;
 
-	if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_IMM) {
+	if (swreg_type(dst) == NN_REG_IMM) {
 		nfp_prog->error = -EFAULT;
 		return;
 	}
@@ -417,13 +283,15 @@ emit_immed(struct nfp_prog *nfp_prog, u32 dst, u16 imm,
 	}
 
 	__emit_immed(nfp_prog, reg.areg, reg.breg, imm >> 8, width,
-		     invert, shift, reg.wr_both);
+		     invert, shift, reg.wr_both,
+		     reg.dst_lmextn, reg.src_lmextn);
 }
 
 static void
 __emit_shf(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab,
 	   enum shf_sc sc, u8 shift,
-	   u16 areg, enum shf_op op, u16 breg, bool i8, bool sw, bool wr_both)
+	   u16 areg, enum shf_op op, u16 breg, bool i8, bool sw, bool wr_both,
+	   bool dst_lmextn, bool src_lmextn)
 {
 	u64 insn;
 
@@ -445,14 +313,16 @@ __emit_shf(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab,
 		FIELD_PREP(OP_SHF_SHIFT, shift) |
 		FIELD_PREP(OP_SHF_OP, op) |
 		FIELD_PREP(OP_SHF_DST_AB, dst_ab) |
-		FIELD_PREP(OP_SHF_WR_AB, wr_both);
+		FIELD_PREP(OP_SHF_WR_AB, wr_both) |
+		FIELD_PREP(OP_SHF_SRC_LMEXTN, src_lmextn) |
+		FIELD_PREP(OP_SHF_DST_LMEXTN, dst_lmextn);
 
 	nfp_prog_push(nfp_prog, insn);
 }
 
 static void
-emit_shf(struct nfp_prog *nfp_prog, u32 dst, u32 lreg, enum shf_op op, u32 rreg,
-	 enum shf_sc sc, u8 shift)
+emit_shf(struct nfp_prog *nfp_prog, swreg dst,
+	 swreg lreg, enum shf_op op, swreg rreg, enum shf_sc sc, u8 shift)
 {
 	struct nfp_insn_re_regs reg;
 	int err;
@@ -464,12 +334,14 @@ emit_shf(struct nfp_prog *nfp_prog, u32 dst, u32 lreg, enum shf_op op, u32 rreg,
 	}
 
 	__emit_shf(nfp_prog, reg.dst, reg.dst_ab, sc, shift,
-		   reg.areg, op, reg.breg, reg.i8, reg.swap, reg.wr_both);
+		   reg.areg, op, reg.breg, reg.i8, reg.swap, reg.wr_both,
+		   reg.dst_lmextn, reg.src_lmextn);
 }
 
 static void
 __emit_alu(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab,
-	   u16 areg, enum alu_op op, u16 breg, bool swap, bool wr_both)
+	   u16 areg, enum alu_op op, u16 breg, bool swap, bool wr_both,
+	   bool dst_lmextn, bool src_lmextn)
 {
 	u64 insn;
 
@@ -480,13 +352,16 @@ __emit_alu(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab,
 		FIELD_PREP(OP_ALU_SW, swap) |
 		FIELD_PREP(OP_ALU_OP, op) |
 		FIELD_PREP(OP_ALU_DST_AB, dst_ab) |
-		FIELD_PREP(OP_ALU_WR_AB, wr_both);
+		FIELD_PREP(OP_ALU_WR_AB, wr_both) |
+		FIELD_PREP(OP_ALU_SRC_LMEXTN, src_lmextn) |
+		FIELD_PREP(OP_ALU_DST_LMEXTN, dst_lmextn);
 
 	nfp_prog_push(nfp_prog, insn);
 }
 
 static void
-emit_alu(struct nfp_prog *nfp_prog, u32 dst, u32 lreg, enum alu_op op, u32 rreg)
+emit_alu(struct nfp_prog *nfp_prog, swreg dst,
+	 swreg lreg, enum alu_op op, swreg rreg)
 {
 	struct nfp_insn_ur_regs reg;
 	int err;
@@ -498,13 +373,15 @@ emit_alu(struct nfp_prog *nfp_prog, u32 dst, u32 lreg, enum alu_op op, u32 rreg)
 	}
 
 	__emit_alu(nfp_prog, reg.dst, reg.dst_ab,
-		   reg.areg, op, reg.breg, reg.swap, reg.wr_both);
+		   reg.areg, op, reg.breg, reg.swap, reg.wr_both,
+		   reg.dst_lmextn, reg.src_lmextn);
 }
 
 static void
 __emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc,
 		u8 areg, u8 bmask, u8 breg, u8 shift, bool imm8,
-		bool zero, bool swap, bool wr_both)
+		bool zero, bool swap, bool wr_both,
+		bool dst_lmextn, bool src_lmextn)
 {
 	u64 insn;
 
@@ -517,33 +394,84 @@ __emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc,
 		FIELD_PREP(OP_LDF_ZF, zero) |
 		FIELD_PREP(OP_LDF_BMASK, bmask) |
 		FIELD_PREP(OP_LDF_SHF, shift) |
-		FIELD_PREP(OP_LDF_WR_AB, wr_both);
+		FIELD_PREP(OP_LDF_WR_AB, wr_both) |
+		FIELD_PREP(OP_LDF_SRC_LMEXTN, src_lmextn) |
+		FIELD_PREP(OP_LDF_DST_LMEXTN, dst_lmextn);
 
 	nfp_prog_push(nfp_prog, insn);
 }
 
 static void
-emit_ld_field_any(struct nfp_prog *nfp_prog, enum shf_sc sc, u8 shift,
-		  u32 dst, u8 bmask, u32 src, bool zero)
+emit_ld_field_any(struct nfp_prog *nfp_prog, swreg dst, u8 bmask, swreg src,
+		  enum shf_sc sc, u8 shift, bool zero)
 {
 	struct nfp_insn_re_regs reg;
 	int err;
 
-	err = swreg_to_restricted(reg_none(), dst, src, &reg, true);
+	/* Note: ld_field is special as it uses one of the src regs as dst */
+	err = swreg_to_restricted(dst, dst, src, &reg, true);
 	if (err) {
 		nfp_prog->error = err;
 		return;
 	}
 
 	__emit_ld_field(nfp_prog, sc, reg.areg, bmask, reg.breg, shift,
-			reg.i8, zero, reg.swap, reg.wr_both);
+			reg.i8, zero, reg.swap, reg.wr_both,
+			reg.dst_lmextn, reg.src_lmextn);
 }
 
 static void
-emit_ld_field(struct nfp_prog *nfp_prog, u32 dst, u8 bmask, u32 src,
+emit_ld_field(struct nfp_prog *nfp_prog, swreg dst, u8 bmask, swreg src,
 	      enum shf_sc sc, u8 shift)
 {
-	emit_ld_field_any(nfp_prog, sc, shift, dst, bmask, src, false);
+	emit_ld_field_any(nfp_prog, dst, bmask, src, sc, shift, false);
+}
+
+static void
+__emit_lcsr(struct nfp_prog *nfp_prog, u16 areg, u16 breg, bool wr, u16 addr,
+	    bool dst_lmextn, bool src_lmextn)
+{
+	u64 insn;
+
+	insn = OP_LCSR_BASE |
+		FIELD_PREP(OP_LCSR_A_SRC, areg) |
+		FIELD_PREP(OP_LCSR_B_SRC, breg) |
+		FIELD_PREP(OP_LCSR_WRITE, wr) |
+		FIELD_PREP(OP_LCSR_ADDR, addr) |
+		FIELD_PREP(OP_LCSR_SRC_LMEXTN, src_lmextn) |
+		FIELD_PREP(OP_LCSR_DST_LMEXTN, dst_lmextn);
+
+	nfp_prog_push(nfp_prog, insn);
+}
+
+static void emit_csr_wr(struct nfp_prog *nfp_prog, swreg src, u16 addr)
+{
+	struct nfp_insn_ur_regs reg;
+	int err;
+
+	/* This instruction takes immeds instead of reg_none() for the ignored
+	 * operand, but we can't encode 2 immeds in one instr with our normal
+	 * swreg infra so if param is an immed, we encode as reg_none() and
+	 * copy the immed to both operands.
+	 */
+	if (swreg_type(src) == NN_REG_IMM) {
+		err = swreg_to_unrestricted(reg_none(), src, reg_none(), &reg);
+		reg.breg = reg.areg;
+	} else {
+		err = swreg_to_unrestricted(reg_none(), src, reg_imm(0), &reg);
+	}
+	if (err) {
+		nfp_prog->error = err;
+		return;
+	}
+
+	__emit_lcsr(nfp_prog, reg.areg, reg.breg, true, addr / 4,
+		    false, reg.src_lmextn);
+}
+
+static void emit_nop(struct nfp_prog *nfp_prog)
+{
+	__emit_immed(nfp_prog, UR_REG_IMM, UR_REG_IMM, 0, 0, 0, 0, 0, 0, 0);
 }
 
 /* --- Wrappers --- */
@@ -565,7 +493,7 @@ static bool pack_immed(u32 imm, u16 *val, enum immed_shift *shift)
 	return true;
 }
 
-static void wrp_immed(struct nfp_prog *nfp_prog, u32 dst, u32 imm)
+static void wrp_immed(struct nfp_prog *nfp_prog, swreg dst, u32 imm)
 {
 	enum immed_shift shift;
 	u16 val;
@@ -586,7 +514,7 @@ static void wrp_immed(struct nfp_prog *nfp_prog, u32 dst, u32 imm)
  * If the @imm is small enough encode it directly in operand and return
  * otherwise load @imm to a spare register and return its encoding.
  */
-static u32 ur_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, u32 tmp_reg)
+static swreg ur_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, swreg tmp_reg)
 {
 	if (FIELD_FIT(UR_REG_IMM_MAX, imm))
 		return reg_imm(imm);
@@ -599,7 +527,7 @@ static u32 ur_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, u32 tmp_reg)
  * If the @imm is small enough encode it directly in operand and return
  * otherwise load @imm to a spare register and return its encoding.
  */
-static u32 re_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, u32 tmp_reg)
+static swreg re_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, swreg tmp_reg)
 {
 	if (FIELD_FIT(RE_REG_IMM_MAX, imm))
 		return reg_imm(imm);
@@ -608,6 +536,12 @@ static u32 re_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, u32 tmp_reg)
 	return tmp_reg;
 }
 
+static void wrp_nops(struct nfp_prog *nfp_prog, unsigned int count)
+{
+	while (count--)
+		emit_nop(nfp_prog);
+}
+
 static void
 wrp_br_special(struct nfp_prog *nfp_prog, enum br_mask mask,
 	       enum br_special special)
@@ -618,78 +552,374 @@ wrp_br_special(struct nfp_prog *nfp_prog, enum br_mask mask,
 		FIELD_PREP(OP_BR_SPECIAL, special);
 }
 
+static void wrp_mov(struct nfp_prog *nfp_prog, swreg dst, swreg src)
+{
+	emit_alu(nfp_prog, dst, reg_none(), ALU_OP_NONE, src);
+}
+
 static void wrp_reg_mov(struct nfp_prog *nfp_prog, u16 dst, u16 src)
 {
-	emit_alu(nfp_prog, reg_both(dst), reg_none(), ALU_OP_NONE, reg_b(src));
+	wrp_mov(nfp_prog, reg_both(dst), reg_b(src));
 }
 
 static int
-construct_data_ind_ld(struct nfp_prog *nfp_prog, u16 offset,
-		      u16 src, bool src_valid, u8 size)
+data_ld(struct nfp_prog *nfp_prog, swreg offset, u8 dst_gpr, int size)
 {
 	unsigned int i;
 	u16 shift, sz;
-	u32 tmp_reg;
 
 	/* We load the value from the address indicated in @offset and then
 	 * shift out the data we don't need.  Note: this is big endian!
 	 */
-	sz = size < 4 ? 4 : size;
+	sz = max(size, 4);
 	shift = size < 4 ? 4 - size : 0;
 
-	if (src_valid) {
-		/* Calculate the true offset (src_reg + imm) */
-		tmp_reg = ur_load_imm_any(nfp_prog, offset, imm_b(nfp_prog));
-		emit_alu(nfp_prog, imm_both(nfp_prog),
-			 reg_a(src), ALU_OP_ADD, tmp_reg);
-		/* Check packet length (size guaranteed to fit b/c it's u8) */
-		emit_alu(nfp_prog, imm_a(nfp_prog),
-			 imm_a(nfp_prog), ALU_OP_ADD, reg_imm(size));
-		emit_alu(nfp_prog, reg_none(),
-			 NFP_BPF_ABI_LEN, ALU_OP_SUB, imm_a(nfp_prog));
-		wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT);
-		/* Load data */
-		emit_cmd(nfp_prog, CMD_TGT_READ8, CMD_MODE_32b, 0,
-			 pkt_reg(nfp_prog), imm_b(nfp_prog), sz - 1, true);
-	} else {
-		/* Check packet length */
-		tmp_reg = ur_load_imm_any(nfp_prog, offset + size,
-					  imm_a(nfp_prog));
-		emit_alu(nfp_prog, reg_none(),
-			 NFP_BPF_ABI_LEN, ALU_OP_SUB, tmp_reg);
-		wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT);
-		/* Load data */
-		tmp_reg = re_load_imm_any(nfp_prog, offset, imm_b(nfp_prog));
-		emit_cmd(nfp_prog, CMD_TGT_READ8, CMD_MODE_32b, 0,
-			 pkt_reg(nfp_prog), tmp_reg, sz - 1, true);
-	}
+	emit_cmd(nfp_prog, CMD_TGT_READ8, CMD_MODE_32b, 0,
+		 pptr_reg(nfp_prog), offset, sz - 1, true);
 
 	i = 0;
 	if (shift)
-		emit_shf(nfp_prog, reg_both(0), reg_none(), SHF_OP_NONE,
+		emit_shf(nfp_prog, reg_both(dst_gpr), reg_none(), SHF_OP_NONE,
 			 reg_xfer(0), SHF_SC_R_SHF, shift * 8);
 	else
 		for (; i * 4 < size; i++)
-			emit_alu(nfp_prog, reg_both(i),
-				 reg_none(), ALU_OP_NONE, reg_xfer(i));
+			wrp_mov(nfp_prog, reg_both(dst_gpr + i), reg_xfer(i));
+
+	if (i < 2)
+		wrp_immed(nfp_prog, reg_both(dst_gpr + 1), 0);
+
+	return 0;
+}
+
+static int
+data_ld_host_order(struct nfp_prog *nfp_prog, u8 src_gpr, swreg offset,
+		   u8 dst_gpr, int size)
+{
+	unsigned int i;
+	u8 mask, sz;
+
+	/* We load the value from the address indicated in @offset and then
+	 * mask out the data we don't need.  Note: this is little endian!
+	 */
+	sz = max(size, 4);
+	mask = size < 4 ? GENMASK(size - 1, 0) : 0;
+
+	emit_cmd(nfp_prog, CMD_TGT_READ32_SWAP, CMD_MODE_32b, 0,
+		 reg_a(src_gpr), offset, sz / 4 - 1, true);
+
+	i = 0;
+	if (mask)
+		emit_ld_field_any(nfp_prog, reg_both(dst_gpr), mask,
+				  reg_xfer(0), SHF_SC_NONE, 0, true);
+	else
+		for (; i * 4 < size; i++)
+			wrp_mov(nfp_prog, reg_both(dst_gpr + i), reg_xfer(i));
 
 	if (i < 2)
-		wrp_immed(nfp_prog, reg_both(1), 0);
+		wrp_immed(nfp_prog, reg_both(dst_gpr + 1), 0);
 
 	return 0;
 }
 
+static int
+construct_data_ind_ld(struct nfp_prog *nfp_prog, u16 offset, u16 src, u8 size)
+{
+	swreg tmp_reg;
+
+	/* Calculate the true offset (src_reg + imm) */
+	tmp_reg = ur_load_imm_any(nfp_prog, offset, imm_b(nfp_prog));
+	emit_alu(nfp_prog, imm_both(nfp_prog), reg_a(src), ALU_OP_ADD, tmp_reg);
+
+	/* Check packet length (size guaranteed to fit b/c it's u8) */
+	emit_alu(nfp_prog, imm_a(nfp_prog),
+		 imm_a(nfp_prog), ALU_OP_ADD, reg_imm(size));
+	emit_alu(nfp_prog, reg_none(),
+		 plen_reg(nfp_prog), ALU_OP_SUB, imm_a(nfp_prog));
+	wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT);
+
+	/* Load data */
+	return data_ld(nfp_prog, imm_b(nfp_prog), 0, size);
+}
+
 static int construct_data_ld(struct nfp_prog *nfp_prog, u16 offset, u8 size)
 {
-	return construct_data_ind_ld(nfp_prog, offset, 0, false, size);
+	swreg tmp_reg;
+
+	/* Check packet length */
+	tmp_reg = ur_load_imm_any(nfp_prog, offset + size, imm_a(nfp_prog));
+	emit_alu(nfp_prog, reg_none(), plen_reg(nfp_prog), ALU_OP_SUB, tmp_reg);
+	wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT);
+
+	/* Load data */
+	tmp_reg = re_load_imm_any(nfp_prog, offset, imm_b(nfp_prog));
+	return data_ld(nfp_prog, tmp_reg, 0, size);
 }
 
-static int wrp_set_mark(struct nfp_prog *nfp_prog, u8 src)
+static int
+data_stx_host_order(struct nfp_prog *nfp_prog, u8 dst_gpr, swreg offset,
+		    u8 src_gpr, u8 size)
 {
-	emit_alu(nfp_prog, NFP_BPF_ABI_MARK,
-		 reg_none(), ALU_OP_NONE, reg_b(src));
-	emit_alu(nfp_prog, NFP_BPF_ABI_FLAGS,
-		 NFP_BPF_ABI_FLAGS, ALU_OP_OR, reg_imm(NFP_BPF_ABI_FLAG_MARK));
+	unsigned int i;
+
+	for (i = 0; i * 4 < size; i++)
+		wrp_mov(nfp_prog, reg_xfer(i), reg_a(src_gpr + i));
+
+	emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 0,
+		 reg_a(dst_gpr), offset, size - 1, true);
+
+	return 0;
+}
+
+static int
+data_st_host_order(struct nfp_prog *nfp_prog, u8 dst_gpr, swreg offset,
+		   u64 imm, u8 size)
+{
+	wrp_immed(nfp_prog, reg_xfer(0), imm);
+	if (size == 8)
+		wrp_immed(nfp_prog, reg_xfer(1), imm >> 32);
+
+	emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 0,
+		 reg_a(dst_gpr), offset, size - 1, true);
+
+	return 0;
+}
+
+typedef int
+(*lmem_step)(struct nfp_prog *nfp_prog, u8 gpr, u8 gpr_byte, s32 off,
+	     unsigned int size, bool first, bool new_gpr, bool last, bool lm3,
+	     bool needs_inc);
+
+static int
+wrp_lmem_load(struct nfp_prog *nfp_prog, u8 dst, u8 dst_byte, s32 off,
+	      unsigned int size, bool first, bool new_gpr, bool last, bool lm3,
+	      bool needs_inc)
+{
+	bool should_inc = needs_inc && new_gpr && !last;
+	u32 idx, src_byte;
+	enum shf_sc sc;
+	swreg reg;
+	int shf;
+	u8 mask;
+
+	if (WARN_ON_ONCE(dst_byte + size > 4 || off % 4 + size > 4))
+		return -EOPNOTSUPP;
+
+	idx = off / 4;
+
+	/* Move the entire word */
+	if (size == 4) {
+		wrp_mov(nfp_prog, reg_both(dst),
+			should_inc ? reg_lm_inc(3) : reg_lm(lm3 ? 3 : 0, idx));
+		return 0;
+	}
+
+	if (WARN_ON_ONCE(lm3 && idx > RE_REG_LM_IDX_MAX))
+		return -EOPNOTSUPP;
+
+	src_byte = off % 4;
+
+	mask = (1 << size) - 1;
+	mask <<= dst_byte;
+
+	if (WARN_ON_ONCE(mask > 0xf))
+		return -EOPNOTSUPP;
+
+	shf = abs(src_byte - dst_byte) * 8;
+	if (src_byte == dst_byte) {
+		sc = SHF_SC_NONE;
+	} else if (src_byte < dst_byte) {
+		shf = 32 - shf;
+		sc = SHF_SC_L_SHF;
+	} else {
+		sc = SHF_SC_R_SHF;
+	}
+
+	/* ld_field can address fewer indexes, if offset too large do RMW.
+	 * Because we RMV twice we waste 2 cycles on unaligned 8 byte writes.
+	 */
+	if (idx <= RE_REG_LM_IDX_MAX) {
+		reg = reg_lm(lm3 ? 3 : 0, idx);
+	} else {
+		reg = imm_a(nfp_prog);
+		/* If it's not the first part of the load and we start a new GPR
+		 * that means we are loading a second part of the LMEM word into
+		 * a new GPR.  IOW we've already looked that LMEM word and
+		 * therefore it has been loaded into imm_a().
+		 */
+		if (first || !new_gpr)
+			wrp_mov(nfp_prog, reg, reg_lm(0, idx));
+	}
+
+	emit_ld_field_any(nfp_prog, reg_both(dst), mask, reg, sc, shf, new_gpr);
+
+	if (should_inc)
+		wrp_mov(nfp_prog, reg_none(), reg_lm_inc(3));
+
+	return 0;
+}
+
+static int
+wrp_lmem_store(struct nfp_prog *nfp_prog, u8 src, u8 src_byte, s32 off,
+	       unsigned int size, bool first, bool new_gpr, bool last, bool lm3,
+	       bool needs_inc)
+{
+	bool should_inc = needs_inc && new_gpr && !last;
+	u32 idx, dst_byte;
+	enum shf_sc sc;
+	swreg reg;
+	int shf;
+	u8 mask;
+
+	if (WARN_ON_ONCE(src_byte + size > 4 || off % 4 + size > 4))
+		return -EOPNOTSUPP;
+
+	idx = off / 4;
+
+	/* Move the entire word */
+	if (size == 4) {
+		wrp_mov(nfp_prog,
+			should_inc ? reg_lm_inc(3) : reg_lm(lm3 ? 3 : 0, idx),
+			reg_b(src));
+		return 0;
+	}
+
+	if (WARN_ON_ONCE(lm3 && idx > RE_REG_LM_IDX_MAX))
+		return -EOPNOTSUPP;
+
+	dst_byte = off % 4;
+
+	mask = (1 << size) - 1;
+	mask <<= dst_byte;
+
+	if (WARN_ON_ONCE(mask > 0xf))
+		return -EOPNOTSUPP;
+
+	shf = abs(src_byte - dst_byte) * 8;
+	if (src_byte == dst_byte) {
+		sc = SHF_SC_NONE;
+	} else if (src_byte < dst_byte) {
+		shf = 32 - shf;
+		sc = SHF_SC_L_SHF;
+	} else {
+		sc = SHF_SC_R_SHF;
+	}
+
+	/* ld_field can address fewer indexes, if offset too large do RMW.
+	 * Because we RMV twice we waste 2 cycles on unaligned 8 byte writes.
+	 */
+	if (idx <= RE_REG_LM_IDX_MAX) {
+		reg = reg_lm(lm3 ? 3 : 0, idx);
+	} else {
+		reg = imm_a(nfp_prog);
+		/* Only first and last LMEM locations are going to need RMW,
+		 * the middle location will be overwritten fully.
+		 */
+		if (first || last)
+			wrp_mov(nfp_prog, reg, reg_lm(0, idx));
+	}
+
+	emit_ld_field(nfp_prog, reg, mask, reg_b(src), sc, shf);
+
+	if (new_gpr || last) {
+		if (idx > RE_REG_LM_IDX_MAX)
+			wrp_mov(nfp_prog, reg_lm(0, idx), reg);
+		if (should_inc)
+			wrp_mov(nfp_prog, reg_none(), reg_lm_inc(3));
+	}
+
+	return 0;
+}
+
+static int
+mem_op_stack(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+	     unsigned int size, unsigned int ptr_off, u8 gpr, u8 ptr_gpr,
+	     bool clr_gpr, lmem_step step)
+{
+	s32 off = nfp_prog->stack_depth + meta->insn.off + ptr_off;
+	bool first = true, last;
+	bool needs_inc = false;
+	swreg stack_off_reg;
+	u8 prev_gpr = 255;
+	u32 gpr_byte = 0;
+	bool lm3 = true;
+	int ret;
+
+	if (meta->ptr_not_const) {
+		/* Use of the last encountered ptr_off is OK, they all have
+		 * the same alignment.  Depend on low bits of value being
+		 * discarded when written to LMaddr register.
+		 */
+		stack_off_reg = ur_load_imm_any(nfp_prog, meta->insn.off,
+						stack_imm(nfp_prog));
+
+		emit_alu(nfp_prog, imm_b(nfp_prog),
+			 reg_a(ptr_gpr), ALU_OP_ADD, stack_off_reg);
+
+		needs_inc = true;
+	} else if (off + size <= 64) {
+		/* We can reach bottom 64B with LMaddr0 */
+		lm3 = false;
+	} else if (round_down(off, 32) == round_down(off + size - 1, 32)) {
+		/* We have to set up a new pointer.  If we know the offset
+		 * and the entire access falls into a single 32 byte aligned
+		 * window we won't have to increment the LM pointer.
+		 * The 32 byte alignment is imporant because offset is ORed in
+		 * not added when doing *l$indexN[off].
+		 */
+		stack_off_reg = ur_load_imm_any(nfp_prog, round_down(off, 32),
+						stack_imm(nfp_prog));
+		emit_alu(nfp_prog, imm_b(nfp_prog),
+			 stack_reg(nfp_prog), ALU_OP_ADD, stack_off_reg);
+
+		off %= 32;
+	} else {
+		stack_off_reg = ur_load_imm_any(nfp_prog, round_down(off, 4),
+						stack_imm(nfp_prog));
+
+		emit_alu(nfp_prog, imm_b(nfp_prog),
+			 stack_reg(nfp_prog), ALU_OP_ADD, stack_off_reg);
+
+		needs_inc = true;
+	}
+	if (lm3) {
+		emit_csr_wr(nfp_prog, imm_b(nfp_prog), NFP_CSR_ACT_LM_ADDR3);
+		/* For size < 4 one slot will be filled by zeroing of upper. */
+		wrp_nops(nfp_prog, clr_gpr && size < 8 ? 2 : 3);
+	}
+
+	if (clr_gpr && size < 8)
+		wrp_immed(nfp_prog, reg_both(gpr + 1), 0);
+
+	while (size) {
+		u32 slice_end;
+		u8 slice_size;
+
+		slice_size = min(size, 4 - gpr_byte);
+		slice_end = min(off + slice_size, round_up(off + 1, 4));
+		slice_size = slice_end - off;
+
+		last = slice_size == size;
+
+		if (needs_inc)
+			off %= 4;
+
+		ret = step(nfp_prog, gpr, gpr_byte, off, slice_size,
+			   first, gpr != prev_gpr, last, lm3, needs_inc);
+		if (ret)
+			return ret;
+
+		prev_gpr = gpr;
+		first = false;
+
+		gpr_byte += slice_size;
+		if (gpr_byte >= 4) {
+			gpr_byte -= 4;
+			gpr++;
+		}
+
+		size -= slice_size;
+		off += slice_size;
+	}
 
 	return 0;
 }
@@ -697,7 +927,7 @@ static int wrp_set_mark(struct nfp_prog *nfp_prog, u8 src)
 static void
 wrp_alu_imm(struct nfp_prog *nfp_prog, u8 dst, enum alu_op alu_op, u32 imm)
 {
-	u32 tmp_reg;
+	swreg tmp_reg;
 
 	if (alu_op == ALU_OP_AND) {
 		if (!imm)
@@ -714,7 +944,7 @@ wrp_alu_imm(struct nfp_prog *nfp_prog, u8 dst, enum alu_op alu_op, u32 imm)
 	if (alu_op == ALU_OP_XOR) {
 		if (!~imm)
 			emit_alu(nfp_prog, reg_both(dst), reg_none(),
-				 ALU_OP_NEG, reg_b(dst));
+				 ALU_OP_NOT, reg_b(dst));
 		if (!imm || !~imm)
 			return;
 	}
@@ -815,7 +1045,7 @@ wrp_cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	const struct bpf_insn *insn = &meta->insn;
 	u64 imm = insn->imm; /* sign extend */
 	u8 reg = insn->dst_reg * 2;
-	u32 tmp_reg;
+	swreg tmp_reg;
 
 	if (insn->off < 0) /* TODO */
 		return -EOPNOTSUPP;
@@ -844,7 +1074,10 @@ wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	    enum br_mask br_mask, bool swap)
 {
 	const struct bpf_insn *insn = &meta->insn;
-	u8 areg = insn->src_reg * 2, breg = insn->dst_reg * 2;
+	u8 areg, breg;
+
+	areg = insn->dst_reg * 2;
+	breg = insn->src_reg * 2;
 
 	if (insn->off < 0) /* TODO */
 		return -EOPNOTSUPP;
@@ -863,13 +1096,34 @@ wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	return 0;
 }
 
+static void wrp_end32(struct nfp_prog *nfp_prog, swreg reg_in, u8 gpr_out)
+{
+	emit_ld_field(nfp_prog, reg_both(gpr_out), 0xf, reg_in,
+		      SHF_SC_R_ROT, 8);
+	emit_ld_field(nfp_prog, reg_both(gpr_out), 0x5, reg_a(gpr_out),
+		      SHF_SC_R_ROT, 16);
+}
+
 /* --- Callbacks --- */
 static int mov_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
-
-	wrp_reg_mov(nfp_prog, insn->dst_reg * 2, insn->src_reg * 2);
-	wrp_reg_mov(nfp_prog, insn->dst_reg * 2 + 1, insn->src_reg * 2 + 1);
+	u8 dst = insn->dst_reg * 2;
+	u8 src = insn->src_reg * 2;
+
+	if (insn->src_reg == BPF_REG_10) {
+		swreg stack_depth_reg;
+
+		stack_depth_reg = ur_load_imm_any(nfp_prog,
+						  nfp_prog->stack_depth,
+						  stack_imm(nfp_prog));
+		emit_alu(nfp_prog, reg_both(dst),
+			 stack_reg(nfp_prog), ALU_OP_ADD, stack_depth_reg);
+		wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+	} else {
+		wrp_reg_mov(nfp_prog, dst, src);
+		wrp_reg_mov(nfp_prog, dst + 1, src + 1);
+	}
 
 	return 0;
 }
@@ -964,28 +1218,64 @@ static int sub_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
-static int shl_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+static int neg_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
 
-	if (insn->imm != 32)
-		return 1; /* TODO */
-
-	wrp_reg_mov(nfp_prog, insn->dst_reg * 2 + 1, insn->dst_reg * 2);
-	wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2), 0);
+	emit_alu(nfp_prog, reg_both(insn->dst_reg * 2), reg_imm(0),
+		 ALU_OP_SUB, reg_b(insn->dst_reg * 2));
+	emit_alu(nfp_prog, reg_both(insn->dst_reg * 2 + 1), reg_imm(0),
+		 ALU_OP_SUB_C, reg_b(insn->dst_reg * 2 + 1));
 
 	return 0;
 }
 
-static int shr_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+static int shl_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
+	u8 dst = insn->dst_reg * 2;
+
+	if (insn->imm < 32) {
+		emit_shf(nfp_prog, reg_both(dst + 1),
+			 reg_a(dst + 1), SHF_OP_NONE, reg_b(dst),
+			 SHF_SC_R_DSHF, 32 - insn->imm);
+		emit_shf(nfp_prog, reg_both(dst),
+			 reg_none(), SHF_OP_NONE, reg_b(dst),
+			 SHF_SC_L_SHF, insn->imm);
+	} else if (insn->imm == 32) {
+		wrp_reg_mov(nfp_prog, dst + 1, dst);
+		wrp_immed(nfp_prog, reg_both(dst), 0);
+	} else if (insn->imm > 32) {
+		emit_shf(nfp_prog, reg_both(dst + 1),
+			 reg_none(), SHF_OP_NONE, reg_b(dst),
+			 SHF_SC_L_SHF, insn->imm - 32);
+		wrp_immed(nfp_prog, reg_both(dst), 0);
+	}
 
-	if (insn->imm != 32)
-		return 1; /* TODO */
+	return 0;
+}
 
-	wrp_reg_mov(nfp_prog, insn->dst_reg * 2, insn->dst_reg * 2 + 1);
-	wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2 + 1), 0);
+static int shr_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u8 dst = insn->dst_reg * 2;
+
+	if (insn->imm < 32) {
+		emit_shf(nfp_prog, reg_both(dst),
+			 reg_a(dst + 1), SHF_OP_NONE, reg_b(dst),
+			 SHF_SC_R_DSHF, insn->imm);
+		emit_shf(nfp_prog, reg_both(dst + 1),
+			 reg_none(), SHF_OP_NONE, reg_b(dst + 1),
+			 SHF_SC_R_SHF, insn->imm);
+	} else if (insn->imm == 32) {
+		wrp_reg_mov(nfp_prog, dst, dst + 1);
+		wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+	} else if (insn->imm > 32) {
+		emit_shf(nfp_prog, reg_both(dst),
+			 reg_none(), SHF_OP_NONE, reg_b(dst + 1),
+			 SHF_SC_R_SHF, insn->imm - 32);
+		wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+	}
 
 	return 0;
 }
@@ -1060,6 +1350,16 @@ static int sub_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB, !meta->insn.imm);
 }
 
+static int neg_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	u8 dst = meta->insn.dst_reg * 2;
+
+	emit_alu(nfp_prog, reg_both(dst), reg_imm(0), ALU_OP_SUB, reg_b(dst));
+	wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0);
+
+	return 0;
+}
+
 static int shl_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
@@ -1075,21 +1375,59 @@ static int shl_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int end_reg32(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u8 gpr = insn->dst_reg * 2;
+
+	switch (insn->imm) {
+	case 16:
+		emit_ld_field(nfp_prog, reg_both(gpr), 0x9, reg_b(gpr),
+			      SHF_SC_R_ROT, 8);
+		emit_ld_field(nfp_prog, reg_both(gpr), 0xe, reg_a(gpr),
+			      SHF_SC_R_SHF, 16);
+
+		wrp_immed(nfp_prog, reg_both(gpr + 1), 0);
+		break;
+	case 32:
+		wrp_end32(nfp_prog, reg_a(gpr), gpr);
+		wrp_immed(nfp_prog, reg_both(gpr + 1), 0);
+		break;
+	case 64:
+		wrp_mov(nfp_prog, imm_a(nfp_prog), reg_b(gpr + 1));
+
+		wrp_end32(nfp_prog, reg_a(gpr), gpr + 1);
+		wrp_end32(nfp_prog, imm_a(nfp_prog), gpr);
+		break;
+	}
+
+	return 0;
+}
+
 static int imm_ld8_part2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	wrp_immed(nfp_prog, reg_both(nfp_meta_prev(meta)->insn.dst_reg * 2 + 1),
-		  meta->insn.imm);
+	struct nfp_insn_meta *prev = nfp_meta_prev(meta);
+	u32 imm_lo, imm_hi;
+	u8 dst;
+
+	dst = prev->insn.dst_reg * 2;
+	imm_lo = prev->insn.imm;
+	imm_hi = meta->insn.imm;
+
+	wrp_immed(nfp_prog, reg_both(dst), imm_lo);
+
+	/* mov is always 1 insn, load imm may be two, so try to use mov */
+	if (imm_hi == imm_lo)
+		wrp_mov(nfp_prog, reg_both(dst + 1), reg_a(dst));
+	else
+		wrp_immed(nfp_prog, reg_both(dst + 1), imm_hi);
 
 	return 0;
 }
 
 static int imm_ld8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	const struct bpf_insn *insn = &meta->insn;
-
 	meta->double_cb = imm_ld8_part2;
-	wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2), insn->imm);
-
 	return 0;
 }
 
@@ -1111,82 +1449,235 @@ static int data_ld4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 static int data_ind_ld1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	return construct_data_ind_ld(nfp_prog, meta->insn.imm,
-				     meta->insn.src_reg * 2, true, 1);
+				     meta->insn.src_reg * 2, 1);
 }
 
 static int data_ind_ld2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	return construct_data_ind_ld(nfp_prog, meta->insn.imm,
-				     meta->insn.src_reg * 2, true, 2);
+				     meta->insn.src_reg * 2, 2);
 }
 
 static int data_ind_ld4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	return construct_data_ind_ld(nfp_prog, meta->insn.imm,
-				     meta->insn.src_reg * 2, true, 4);
+				     meta->insn.src_reg * 2, 4);
 }
 
-static int mem_ldx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+static int
+mem_ldx_stack(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+	      unsigned int size, unsigned int ptr_off)
 {
-	if (meta->insn.off == offsetof(struct sk_buff, len))
-		emit_alu(nfp_prog, reg_both(meta->insn.dst_reg * 2),
-			 reg_none(), ALU_OP_NONE, NFP_BPF_ABI_LEN);
-	else
+	return mem_op_stack(nfp_prog, meta, size, ptr_off,
+			    meta->insn.dst_reg * 2, meta->insn.src_reg * 2,
+			    true, wrp_lmem_load);
+}
+
+static int mem_ldx_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+		       u8 size)
+{
+	swreg dst = reg_both(meta->insn.dst_reg * 2);
+
+	switch (meta->insn.off) {
+	case offsetof(struct sk_buff, len):
+		if (size != FIELD_SIZEOF(struct sk_buff, len))
+			return -EOPNOTSUPP;
+		wrp_mov(nfp_prog, dst, plen_reg(nfp_prog));
+		break;
+	case offsetof(struct sk_buff, data):
+		if (size != sizeof(void *))
+			return -EOPNOTSUPP;
+		wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog));
+		break;
+	case offsetof(struct sk_buff, cb) +
+	     offsetof(struct bpf_skb_data_end, data_end):
+		if (size != sizeof(void *))
+			return -EOPNOTSUPP;
+		emit_alu(nfp_prog, dst,
+			 plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog));
+		break;
+	default:
 		return -EOPNOTSUPP;
+	}
+
+	wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0);
 
 	return 0;
 }
 
-static int mem_ldx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+static int mem_ldx_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+		       u8 size)
 {
-	u32 dst = reg_both(meta->insn.dst_reg * 2);
+	swreg dst = reg_both(meta->insn.dst_reg * 2);
+
+	if (size != sizeof(void *))
+		return -EINVAL;
 
-	if (meta->insn.off != offsetof(struct xdp_md, data) &&
-	    meta->insn.off != offsetof(struct xdp_md, data_end))
+	switch (meta->insn.off) {
+	case offsetof(struct xdp_buff, data):
+		wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog));
+		break;
+	case offsetof(struct xdp_buff, data_end):
+		emit_alu(nfp_prog, dst,
+			 plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog));
+		break;
+	default:
 		return -EOPNOTSUPP;
+	}
 
-	emit_alu(nfp_prog, dst, reg_none(), ALU_OP_NONE, NFP_BPF_ABI_PKT);
+	wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0);
 
-	if (meta->insn.off == offsetof(struct xdp_md, data))
-		return 0;
+	return 0;
+}
 
-	emit_alu(nfp_prog, dst,	dst, ALU_OP_ADD, NFP_BPF_ABI_LEN);
+static int
+mem_ldx_data(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+	     unsigned int size)
+{
+	swreg tmp_reg;
 
-	return 0;
+	tmp_reg = re_load_imm_any(nfp_prog, meta->insn.off, imm_b(nfp_prog));
+
+	return data_ld_host_order(nfp_prog, meta->insn.src_reg * 2, tmp_reg,
+				  meta->insn.dst_reg * 2, size);
+}
+
+static int
+mem_ldx(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+	unsigned int size)
+{
+	if (meta->ptr.type == PTR_TO_CTX) {
+		if (nfp_prog->act == NN_ACT_XDP)
+			return mem_ldx_xdp(nfp_prog, meta, size);
+		else
+			return mem_ldx_skb(nfp_prog, meta, size);
+	}
+
+	if (meta->ptr.type == PTR_TO_PACKET)
+		return mem_ldx_data(nfp_prog, meta, size);
+
+	if (meta->ptr.type == PTR_TO_STACK)
+		return mem_ldx_stack(nfp_prog, meta, size,
+				     meta->ptr.off + meta->ptr.var_off.value);
+
+	return -EOPNOTSUPP;
+}
+
+static int mem_ldx1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return mem_ldx(nfp_prog, meta, 1);
+}
+
+static int mem_ldx2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return mem_ldx(nfp_prog, meta, 2);
 }
 
 static int mem_ldx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	int ret;
+	return mem_ldx(nfp_prog, meta, 4);
+}
 
-	if (nfp_prog->act == NN_ACT_XDP)
-		ret = mem_ldx4_xdp(nfp_prog, meta);
-	else
-		ret = mem_ldx4_skb(nfp_prog, meta);
+static int mem_ldx8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return mem_ldx(nfp_prog, meta, 8);
+}
 
-	wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0);
+static int
+mem_st_data(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+	    unsigned int size)
+{
+	u64 imm = meta->insn.imm; /* sign extend */
+	swreg off_reg;
 
-	return ret;
+	off_reg = re_load_imm_any(nfp_prog, meta->insn.off, imm_b(nfp_prog));
+
+	return data_st_host_order(nfp_prog, meta->insn.dst_reg * 2, off_reg,
+				  imm, size);
 }
 
-static int mem_stx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+static int mem_st(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+		  unsigned int size)
 {
-	if (meta->insn.off == offsetof(struct sk_buff, mark))
-		return wrp_set_mark(nfp_prog, meta->insn.src_reg * 2);
+	if (meta->ptr.type == PTR_TO_PACKET)
+		return mem_st_data(nfp_prog, meta, size);
 
 	return -EOPNOTSUPP;
 }
 
-static int mem_stx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+static int mem_st1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return mem_st(nfp_prog, meta, 1);
+}
+
+static int mem_st2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return mem_st(nfp_prog, meta, 2);
+}
+
+static int mem_st4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return mem_st(nfp_prog, meta, 4);
+}
+
+static int mem_st8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
+	return mem_st(nfp_prog, meta, 8);
+}
+
+static int
+mem_stx_data(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+	     unsigned int size)
+{
+	swreg off_reg;
+
+	off_reg = re_load_imm_any(nfp_prog, meta->insn.off, imm_b(nfp_prog));
+
+	return data_stx_host_order(nfp_prog, meta->insn.dst_reg * 2, off_reg,
+				   meta->insn.src_reg * 2, size);
+}
+
+static int
+mem_stx_stack(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+	      unsigned int size, unsigned int ptr_off)
+{
+	return mem_op_stack(nfp_prog, meta, size, ptr_off,
+			    meta->insn.src_reg * 2, meta->insn.dst_reg * 2,
+			    false, wrp_lmem_store);
+}
+
+static int
+mem_stx(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+	unsigned int size)
+{
+	if (meta->ptr.type == PTR_TO_PACKET)
+		return mem_stx_data(nfp_prog, meta, size);
+
+	if (meta->ptr.type == PTR_TO_STACK)
+		return mem_stx_stack(nfp_prog, meta, size,
+				     meta->ptr.off + meta->ptr.var_off.value);
+
 	return -EOPNOTSUPP;
 }
 
+static int mem_stx1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return mem_stx(nfp_prog, meta, 1);
+}
+
+static int mem_stx2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return mem_stx(nfp_prog, meta, 2);
+}
+
 static int mem_stx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	if (nfp_prog->act == NN_ACT_XDP)
-		return mem_stx4_xdp(nfp_prog, meta);
-	return mem_stx4_skb(nfp_prog, meta);
+	return mem_stx(nfp_prog, meta, 4);
+}
+
+static int mem_stx8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return mem_stx(nfp_prog, meta, 8);
 }
 
 static int jump(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -1202,8 +1693,10 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
 	u64 imm = insn->imm; /* sign extend */
-	u32 or1 = reg_a(insn->dst_reg * 2), or2 = reg_b(insn->dst_reg * 2 + 1);
-	u32 tmp_reg;
+	swreg or1, or2, tmp_reg;
+
+	or1 = reg_a(insn->dst_reg * 2);
+	or2 = reg_b(insn->dst_reg * 2 + 1);
 
 	if (insn->off < 0) /* TODO */
 		return -EOPNOTSUPP;
@@ -1230,29 +1723,29 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int jgt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_cmp_imm(nfp_prog, meta, BR_BLO, false);
+	return wrp_cmp_imm(nfp_prog, meta, BR_BLO, true);
 }
 
 static int jge_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_cmp_imm(nfp_prog, meta, BR_BHS, true);
+	return wrp_cmp_imm(nfp_prog, meta, BR_BHS, false);
 }
 
 static int jlt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_cmp_imm(nfp_prog, meta, BR_BHS, false);
+	return wrp_cmp_imm(nfp_prog, meta, BR_BLO, false);
 }
 
 static int jle_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_cmp_imm(nfp_prog, meta, BR_BLO, true);
+	return wrp_cmp_imm(nfp_prog, meta, BR_BHS, true);
 }
 
 static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
 	u64 imm = insn->imm; /* sign extend */
-	u32 tmp_reg;
+	swreg tmp_reg;
 
 	if (insn->off < 0) /* TODO */
 		return -EOPNOTSUPP;
@@ -1283,7 +1776,7 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
 	u64 imm = insn->imm; /* sign extend */
-	u32 tmp_reg;
+	swreg tmp_reg;
 
 	if (insn->off < 0) /* TODO */
 		return -EOPNOTSUPP;
@@ -1292,6 +1785,7 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 		emit_alu(nfp_prog, reg_none(), reg_a(insn->dst_reg * 2),
 			 ALU_OP_OR, reg_b(insn->dst_reg * 2 + 1));
 		emit_br(nfp_prog, BR_BNE, insn->off, 0);
+		return 0;
 	}
 
 	tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
@@ -1327,22 +1821,22 @@ static int jeq_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int jgt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_cmp_reg(nfp_prog, meta, BR_BLO, false);
+	return wrp_cmp_reg(nfp_prog, meta, BR_BLO, true);
 }
 
 static int jge_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_cmp_reg(nfp_prog, meta, BR_BHS, true);
+	return wrp_cmp_reg(nfp_prog, meta, BR_BHS, false);
 }
 
 static int jlt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_cmp_reg(nfp_prog, meta, BR_BHS, false);
+	return wrp_cmp_reg(nfp_prog, meta, BR_BLO, false);
 }
 
 static int jle_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_cmp_reg(nfp_prog, meta, BR_BLO, true);
+	return wrp_cmp_reg(nfp_prog, meta, BR_BHS, true);
 }
 
 static int jset_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -1375,6 +1869,7 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU64 | BPF_ADD | BPF_K] =	add_imm64,
 	[BPF_ALU64 | BPF_SUB | BPF_X] =	sub_reg64,
 	[BPF_ALU64 | BPF_SUB | BPF_K] =	sub_imm64,
+	[BPF_ALU64 | BPF_NEG] =		neg_reg64,
 	[BPF_ALU64 | BPF_LSH | BPF_K] =	shl_imm64,
 	[BPF_ALU64 | BPF_RSH | BPF_K] =	shr_imm64,
 	[BPF_ALU | BPF_MOV | BPF_X] =	mov_reg,
@@ -1389,7 +1884,9 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU | BPF_ADD | BPF_K] =	add_imm,
 	[BPF_ALU | BPF_SUB | BPF_X] =	sub_reg,
 	[BPF_ALU | BPF_SUB | BPF_K] =	sub_imm,
+	[BPF_ALU | BPF_NEG] =		neg_reg,
 	[BPF_ALU | BPF_LSH | BPF_K] =	shl_imm,
+	[BPF_ALU | BPF_END | BPF_X] =	end_reg32,
 	[BPF_LD | BPF_IMM | BPF_DW] =	imm_ld8,
 	[BPF_LD | BPF_ABS | BPF_B] =	data_ld1,
 	[BPF_LD | BPF_ABS | BPF_H] =	data_ld2,
@@ -1397,8 +1894,18 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_LD | BPF_IND | BPF_B] =	data_ind_ld1,
 	[BPF_LD | BPF_IND | BPF_H] =	data_ind_ld2,
 	[BPF_LD | BPF_IND | BPF_W] =	data_ind_ld4,
+	[BPF_LDX | BPF_MEM | BPF_B] =	mem_ldx1,
+	[BPF_LDX | BPF_MEM | BPF_H] =	mem_ldx2,
 	[BPF_LDX | BPF_MEM | BPF_W] =	mem_ldx4,
+	[BPF_LDX | BPF_MEM | BPF_DW] =	mem_ldx8,
+	[BPF_STX | BPF_MEM | BPF_B] =	mem_stx1,
+	[BPF_STX | BPF_MEM | BPF_H] =	mem_stx2,
 	[BPF_STX | BPF_MEM | BPF_W] =	mem_stx4,
+	[BPF_STX | BPF_MEM | BPF_DW] =	mem_stx8,
+	[BPF_ST | BPF_MEM | BPF_B] =	mem_st1,
+	[BPF_ST | BPF_MEM | BPF_H] =	mem_st2,
+	[BPF_ST | BPF_MEM | BPF_W] =	mem_st4,
+	[BPF_ST | BPF_MEM | BPF_DW] =	mem_st8,
 	[BPF_JMP | BPF_JA | BPF_K] =	jump,
 	[BPF_JMP | BPF_JEQ | BPF_K] =	jeq_imm,
 	[BPF_JMP | BPF_JGT | BPF_K] =	jgt_imm,
@@ -1510,8 +2017,9 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 
 static void nfp_intro(struct nfp_prog *nfp_prog)
 {
-	emit_alu(nfp_prog, pkt_reg(nfp_prog),
-		 reg_none(), ALU_OP_NONE, NFP_BPF_ABI_PKT);
+	wrp_immed(nfp_prog, plen_reg(nfp_prog), GENMASK(13, 0));
+	emit_alu(nfp_prog, plen_reg(nfp_prog),
+		 plen_reg(nfp_prog), ALU_OP_AND, pv_len(nfp_prog));
 }
 
 static void nfp_outro_tc_legacy(struct nfp_prog *nfp_prog)
@@ -1534,8 +2042,7 @@ static void nfp_outro_tc_legacy(struct nfp_prog *nfp_prog)
 	 *  ife + tx  0x24 -> redir, count as stat1
 	 */
 	emit_br_byte_neq(nfp_prog, reg_b(0), 0xff, 0, nfp_prog->tgt_done, 2);
-	emit_alu(nfp_prog, reg_a(0),
-		 reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS);
+	wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS);
 	emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_imm(0x11), SHF_SC_L_SHF, 16);
 
 	emit_br(nfp_prog, BR_UNC, nfp_prog->tgt_done, 1);
@@ -1562,8 +2069,7 @@ static void nfp_outro_tc_da(struct nfp_prog *nfp_prog)
 
 	emit_br_def(nfp_prog, nfp_prog->tgt_done, 2);
 
-	emit_alu(nfp_prog, reg_a(0),
-		 reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS);
+	wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS);
 	emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_imm(0x11), SHF_SC_L_SHF, 16);
 
 	/* Target for normal exits */
@@ -1572,8 +2078,7 @@ static void nfp_outro_tc_da(struct nfp_prog *nfp_prog)
 	/* if R0 > 7 jump to abort */
 	emit_alu(nfp_prog, reg_none(), reg_imm(7), ALU_OP_SUB, reg_b(0));
 	emit_br(nfp_prog, BR_BLO, nfp_prog->tgt_abort, 0);
-	emit_alu(nfp_prog, reg_a(0),
-		 reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS);
+	wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS);
 
 	wrp_immed(nfp_prog, reg_b(2), 0x41221211);
 	wrp_immed(nfp_prog, reg_b(3), 0x41001211);
@@ -1610,8 +2115,7 @@ static void nfp_outro_xdp(struct nfp_prog *nfp_prog)
 
 	emit_br_def(nfp_prog, nfp_prog->tgt_done, 2);
 
-	emit_alu(nfp_prog, reg_a(0),
-		 reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS);
+	wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS);
 	emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_imm(0x82), SHF_SC_L_SHF, 16);
 
 	/* Target for normal exits */
@@ -1632,8 +2136,7 @@ static void nfp_outro_xdp(struct nfp_prog *nfp_prog)
 
 	emit_br_def(nfp_prog, nfp_prog->tgt_done, 2);
 
-	emit_alu(nfp_prog, reg_a(0),
-		 reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS);
+	wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS);
 	emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_b(2), SHF_SC_L_SHF, 16);
 }
 
@@ -1688,6 +2191,10 @@ static int nfp_translate(struct nfp_prog *nfp_prog)
 	if (nfp_prog->error)
 		return nfp_prog->error;
 
+	wrp_nops(nfp_prog, NFP_USTORE_PREFETCH_WINDOW);
+	if (nfp_prog->error)
+		return nfp_prog->error;
+
 	return nfp_fixup_branches(nfp_prog);
 }
 
@@ -1737,38 +2244,6 @@ static void nfp_bpf_opt_reg_init(struct nfp_prog *nfp_prog)
 	}
 }
 
-/* Try to rename registers so that program uses only low ones */
-static int nfp_bpf_opt_reg_rename(struct nfp_prog *nfp_prog)
-{
-	bool reg_used[MAX_BPF_REG] = {};
-	u8 tgt_reg[MAX_BPF_REG] = {};
-	struct nfp_insn_meta *meta;
-	unsigned int i, j;
-
-	list_for_each_entry(meta, &nfp_prog->insns, l) {
-		if (meta->skip)
-			continue;
-
-		reg_used[meta->insn.src_reg] = true;
-		reg_used[meta->insn.dst_reg] = true;
-	}
-
-	for (i = 0, j = 0; i < ARRAY_SIZE(tgt_reg); i++) {
-		if (!reg_used[i])
-			continue;
-
-		tgt_reg[i] = j++;
-	}
-	nfp_prog->num_regs = j;
-
-	list_for_each_entry(meta, &nfp_prog->insns, l) {
-		meta->insn.src_reg = tgt_reg[meta->insn.src_reg];
-		meta->insn.dst_reg = tgt_reg[meta->insn.dst_reg];
-	}
-
-	return 0;
-}
-
 /* Remove masking after load since our load guarantees this is not needed */
 static void nfp_bpf_opt_ld_mask(struct nfp_prog *nfp_prog)
 {
@@ -1845,20 +2320,33 @@ static void nfp_bpf_opt_ld_shift(struct nfp_prog *nfp_prog)
 
 static int nfp_bpf_optimize(struct nfp_prog *nfp_prog)
 {
-	int ret;
-
 	nfp_bpf_opt_reg_init(nfp_prog);
 
-	ret = nfp_bpf_opt_reg_rename(nfp_prog);
-	if (ret)
-		return ret;
-
 	nfp_bpf_opt_ld_mask(nfp_prog);
 	nfp_bpf_opt_ld_shift(nfp_prog);
 
 	return 0;
 }
 
+static int nfp_bpf_ustore_calc(struct nfp_prog *nfp_prog, __le64 *ustore)
+{
+	int i;
+
+	for (i = 0; i < nfp_prog->prog_len; i++) {
+		int err;
+
+		err = nfp_ustore_check_valid_no_ecc(nfp_prog->prog[i]);
+		if (err)
+			return err;
+
+		nfp_prog->prog[i] = nfp_ustore_calc_ecc_insn(nfp_prog->prog[i]);
+
+		ustore[i] = cpu_to_le64(nfp_prog->prog[i]);
+	}
+
+	return 0;
+}
+
 /**
  * nfp_bpf_jit() - translate BPF code into NFP assembly
  * @filter:	kernel BPF filter struct
@@ -1899,10 +2387,8 @@ nfp_bpf_jit(struct bpf_prog *filter, void *prog_mem,
 	if (ret)
 		goto out;
 
-	if (nfp_prog->num_regs <= 7)
-		nfp_prog->regs_per_thread = 16;
-	else
-		nfp_prog->regs_per_thread = 32;
+	nfp_prog->num_regs = MAX_BPF_REG;
+	nfp_prog->regs_per_thread = 32;
 
 	nfp_prog->prog = prog_mem;
 	nfp_prog->__prog_alloc_len = prog_sz;
@@ -1912,10 +2398,13 @@ nfp_bpf_jit(struct bpf_prog *filter, void *prog_mem,
 		pr_err("Translation failed with error %d (translated: %u)\n",
 		       ret, nfp_prog->n_translated);
 		ret = -EINVAL;
+		goto out;
 	}
 
+	ret = nfp_bpf_ustore_calc(nfp_prog, (__force __le64 *)prog_mem);
+
 	res->n_instr = nfp_prog->prog_len;
-	res->dense_mode = nfp_prog->num_regs <= 7;
+	res->dense_mode = false;
 out:
 	nfp_prog_free(nfp_prog);
 
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index be2cf10a2cd7..8e3e89cace8d 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -42,9 +42,11 @@
 
 static bool nfp_net_ebpf_capable(struct nfp_net *nn)
 {
+#ifdef __LITTLE_ENDIAN
 	if (nn->cap & NFP_NET_CFG_CTRL_BPF &&
 	    nn_readb(nn, NFP_NET_CFG_BPF_ABI) == NFP_NET_BPF_ABI)
 		return true;
+#endif
 	return false;
 }
 
@@ -89,22 +91,15 @@ nfp_bpf_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 	struct nfp_net_bpf_priv *priv;
 	int ret;
 
-	/* Limit to single port, otherwise it's just a NIC */
-	if (id > 0) {
-		nfp_warn(app->cpp,
-			 "BPF NIC doesn't support more than one port right now\n");
-		nn->port = nfp_port_alloc(app, NFP_PORT_INVALID, nn->dp.netdev);
-		return PTR_ERR_OR_ZERO(nn->port);
-	}
-
 	priv = kmalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
 	nn->app_priv = priv;
 	spin_lock_init(&priv->rx_filter_lock);
-	setup_timer(&priv->rx_filter_stats_timer,
-		    nfp_net_filter_stats_timer, (unsigned long)nn);
+	priv->nn = nn;
+	timer_setup(&priv->rx_filter_stats_timer,
+		    nfp_net_filter_stats_timer, 0);
 
 	ret = nfp_app_nic_vnic_alloc(app, nn, id);
 	if (ret)
@@ -120,22 +115,62 @@ static void nfp_bpf_vnic_free(struct nfp_app *app, struct nfp_net *nn)
 	kfree(nn->app_priv);
 }
 
-static int nfp_bpf_setup_tc(struct nfp_app *app, struct net_device *netdev,
-			    enum tc_setup_type type, void *type_data)
+static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type,
+				     void *type_data, void *cb_priv)
 {
 	struct tc_cls_bpf_offload *cls_bpf = type_data;
+	struct nfp_net *nn = cb_priv;
+
+	if (!tc_can_offload(nn->dp.netdev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSBPF:
+		if (!nfp_net_ebpf_capable(nn) ||
+		    cls_bpf->common.protocol != htons(ETH_P_ALL) ||
+		    cls_bpf->common.chain_index)
+			return -EOPNOTSUPP;
+		if (nn->dp.bpf_offload_xdp)
+			return -EBUSY;
+
+		return nfp_net_bpf_offload(nn, cls_bpf);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int nfp_bpf_setup_tc_block(struct net_device *netdev,
+				  struct tc_block_offload *f)
+{
 	struct nfp_net *nn = netdev_priv(netdev);
 
-	if (type != TC_SETUP_CLSBPF || !nfp_net_ebpf_capable(nn) ||
-	    !is_classid_clsact_ingress(cls_bpf->common.classid) ||
-	    cls_bpf->common.protocol != htons(ETH_P_ALL) ||
-	    cls_bpf->common.chain_index)
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
-	if (nn->dp.bpf_offload_xdp)
-		return -EBUSY;
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block,
+					     nfp_bpf_setup_tc_block_cb,
+					     nn, nn);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block,
+					nfp_bpf_setup_tc_block_cb,
+					nn);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
 
-	return nfp_net_bpf_offload(nn, cls_bpf);
+static int nfp_bpf_setup_tc(struct nfp_app *app, struct net_device *netdev,
+			    enum tc_setup_type type, void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return nfp_bpf_setup_tc_block(netdev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static bool nfp_bpf_tc_busy(struct nfp_app *app, struct nfp_net *nn)
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 4051e943f363..bc604030ff6c 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -36,9 +36,11 @@
 
 #include <linux/bitfield.h>
 #include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
 #include <linux/list.h>
 #include <linux/types.h>
 
+#include "../nfp_asm.h"
 #include "../nfp_net.h"
 
 /* For branch fixup logic use up-most byte of branch instruction as scratch
@@ -53,9 +55,14 @@ enum br_special {
 };
 
 enum static_regs {
-	STATIC_REG_PKT		= 1,
-#define REG_PKT_BANK	ALU_DST_A
-	STATIC_REG_IMM		= 2, /* Bank AB */
+	STATIC_REG_IMM		= 21, /* Bank AB */
+	STATIC_REG_STACK	= 22, /* Bank A */
+	STATIC_REG_PKT_LEN	= 22, /* Bank B */
+};
+
+enum pkt_vec {
+	PKT_VEC_PKT_LEN		= 0,
+	PKT_VEC_PKT_PTR		= 2,
 };
 
 enum nfp_bpf_action_type {
@@ -65,39 +72,19 @@ enum nfp_bpf_action_type {
 	NN_ACT_XDP,
 };
 
-/* Software register representation, hardware encoding in asm.h */
-#define NN_REG_TYPE	GENMASK(31, 24)
-#define NN_REG_VAL	GENMASK(7, 0)
-
-enum nfp_bpf_reg_type {
-	NN_REG_GPR_A =	BIT(0),
-	NN_REG_GPR_B =	BIT(1),
-	NN_REG_NNR =	BIT(2),
-	NN_REG_XFER =	BIT(3),
-	NN_REG_IMM =	BIT(4),
-	NN_REG_NONE =	BIT(5),
-};
-
-#define NN_REG_GPR_BOTH	(NN_REG_GPR_A | NN_REG_GPR_B)
-
-#define reg_both(x)	((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_GPR_BOTH))
-#define reg_a(x)	((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_GPR_A))
-#define reg_b(x)	((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_GPR_B))
-#define reg_nnr(x)	((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_NNR))
-#define reg_xfer(x)	((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_XFER))
-#define reg_imm(x)	((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_IMM))
-#define reg_none()	(FIELD_PREP(NN_REG_TYPE, NN_REG_NONE))
+#define pv_len(np)	reg_lm(1, PKT_VEC_PKT_LEN)
+#define pv_ctm_ptr(np)	reg_lm(1, PKT_VEC_PKT_PTR)
 
-#define pkt_reg(np)	reg_a((np)->regs_per_thread - STATIC_REG_PKT)
-#define imm_a(np)	reg_a((np)->regs_per_thread - STATIC_REG_IMM)
-#define imm_b(np)	reg_b((np)->regs_per_thread - STATIC_REG_IMM)
-#define imm_both(np)	reg_both((np)->regs_per_thread - STATIC_REG_IMM)
+#define stack_reg(np)	reg_a(STATIC_REG_STACK)
+#define stack_imm(np)	imm_b(np)
+#define plen_reg(np)	reg_b(STATIC_REG_PKT_LEN)
+#define pptr_reg(np)	pv_ctm_ptr(np)
+#define imm_a(np)	reg_a(STATIC_REG_IMM)
+#define imm_b(np)	reg_b(STATIC_REG_IMM)
+#define imm_both(np)	reg_both(STATIC_REG_IMM)
 
-#define NFP_BPF_ABI_FLAGS	reg_nnr(0)
+#define NFP_BPF_ABI_FLAGS	reg_imm(0)
 #define   NFP_BPF_ABI_FLAG_MARK	1
-#define NFP_BPF_ABI_MARK	reg_nnr(1)
-#define NFP_BPF_ABI_PKT		reg_nnr(2)
-#define NFP_BPF_ABI_LEN		reg_nnr(3)
 
 struct nfp_prog;
 struct nfp_insn_meta;
@@ -113,6 +100,8 @@ typedef int (*instr_cb_t)(struct nfp_prog *, struct nfp_insn_meta *);
 /**
  * struct nfp_insn_meta - BPF instruction wrapper
  * @insn: BPF instruction
+ * @ptr: pointer type for memory operations
+ * @ptr_not_const: pointer is not always constant
  * @off: index of first generated machine instruction (in nfp_prog.prog)
  * @n: eBPF instruction number
  * @skip: skip this instruction (optimized out)
@@ -121,6 +110,8 @@ typedef int (*instr_cb_t)(struct nfp_prog *, struct nfp_insn_meta *);
  */
 struct nfp_insn_meta {
 	struct bpf_insn insn;
+	struct bpf_reg_state ptr;
+	bool ptr_not_const;
 	unsigned int off;
 	unsigned short n;
 	bool skip;
@@ -165,6 +156,7 @@ static inline u8 mbpf_mode(const struct nfp_insn_meta *meta)
  * @tgt_done: jump target to get the next packet
  * @n_translated: number of successfully translated instructions (for errors)
  * @error: error code if something went wrong
+ * @stack_depth: max stack depth from the verifier
  * @insns: list of BPF instruction wrappers (struct nfp_insn_meta)
  */
 struct nfp_prog {
@@ -185,6 +177,8 @@ struct nfp_prog {
 	unsigned int n_translated;
 	int error;
 
+	unsigned int stack_depth;
+
 	struct list_head insns;
 };
 
@@ -215,10 +209,11 @@ struct nfp_net_bpf_priv {
 	struct nfp_stat_pair rx_filter, rx_filter_prev;
 	unsigned long rx_filter_change;
 	struct timer_list rx_filter_stats_timer;
+	struct nfp_net *nn;
 	spinlock_t rx_filter_lock;
 };
 
 int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf);
-void nfp_net_filter_stats_timer(unsigned long data);
+void nfp_net_filter_stats_timer(struct timer_list *t);
 
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index a88bb5bc0082..6d576f631392 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -51,14 +51,13 @@
 #include "../nfp_net_ctrl.h"
 #include "../nfp_net.h"
 
-void nfp_net_filter_stats_timer(unsigned long data)
+void nfp_net_filter_stats_timer(struct timer_list *t)
 {
-	struct nfp_net *nn = (void *)data;
-	struct nfp_net_bpf_priv *priv;
+	struct nfp_net_bpf_priv *priv = from_timer(priv, t,
+						   rx_filter_stats_timer);
+	struct nfp_net *nn = priv->nn;
 	struct nfp_stat_pair latest;
 
-	priv = nn->app_priv;
-
 	spin_lock_bh(&priv->rx_filter_lock);
 
 	if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF)
@@ -146,13 +145,11 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn,
 {
 	unsigned int code_sz = max_instr * sizeof(u64);
 	enum nfp_bpf_action_type act;
+	unsigned int stack_size;
 	u16 start_off, done_off;
 	unsigned int max_mtu;
 	int ret;
 
-	if (!IS_ENABLED(CONFIG_BPF_SYSCALL))
-		return -EOPNOTSUPP;
-
 	ret = nfp_net_bpf_get_act(nn, cls_bpf);
 	if (ret < 0)
 		return ret;
@@ -167,6 +164,13 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn,
 	start_off = nn_readw(nn, NFP_NET_CFG_BPF_START);
 	done_off = nn_readw(nn, NFP_NET_CFG_BPF_DONE);
 
+	stack_size = nn_readb(nn, NFP_NET_CFG_BPF_STACK_SZ) * 64;
+	if (cls_bpf->prog->aux->stack_depth > stack_size) {
+		nn_info(nn, "stack too large: program %dB > FW stack %dB\n",
+			cls_bpf->prog->aux->stack_depth, stack_size);
+		return -EOPNOTSUPP;
+	}
+
 	*code = dma_zalloc_coherent(nn->dp.dev, code_sz, dma_addr, GFP_KERNEL);
 	if (!*code)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index 5b783a91b115..a8c7615546a9 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -76,9 +76,9 @@ nfp_bpf_goto_meta(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 
 static int
 nfp_bpf_check_exit(struct nfp_prog *nfp_prog,
-		   const struct bpf_verifier_env *env)
+		   struct bpf_verifier_env *env)
 {
-	const struct bpf_reg_state *reg0 = &env->cur_state.regs[0];
+	const struct bpf_reg_state *reg0 = cur_regs(env) + BPF_REG_0;
 	u64 imm;
 
 	if (nfp_prog->act == NN_ACT_XDP)
@@ -112,11 +112,63 @@ nfp_bpf_check_exit(struct nfp_prog *nfp_prog,
 }
 
 static int
-nfp_bpf_check_ctx_ptr(struct nfp_prog *nfp_prog,
-		      const struct bpf_verifier_env *env, u8 reg)
+nfp_bpf_check_stack_access(struct nfp_prog *nfp_prog,
+			   struct nfp_insn_meta *meta,
+			   const struct bpf_reg_state *reg)
 {
-	if (env->cur_state.regs[reg].type != PTR_TO_CTX)
+	s32 old_off, new_off;
+
+	if (!tnum_is_const(reg->var_off)) {
+		pr_info("variable ptr stack access\n");
 		return -EINVAL;
+	}
+
+	if (meta->ptr.type == NOT_INIT)
+		return 0;
+
+	old_off = meta->ptr.off + meta->ptr.var_off.value;
+	new_off = reg->off + reg->var_off.value;
+
+	meta->ptr_not_const |= old_off != new_off;
+
+	if (!meta->ptr_not_const)
+		return 0;
+
+	if (old_off % 4 == new_off % 4)
+		return 0;
+
+	pr_info("stack access changed location was:%d is:%d\n",
+		old_off, new_off);
+	return -EINVAL;
+}
+
+static int
+nfp_bpf_check_ptr(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+		  struct bpf_verifier_env *env, u8 reg_no)
+{
+	const struct bpf_reg_state *reg = cur_regs(env) + reg_no;
+	int err;
+
+	if (reg->type != PTR_TO_CTX &&
+	    reg->type != PTR_TO_STACK &&
+	    reg->type != PTR_TO_PACKET) {
+		pr_info("unsupported ptr type: %d\n", reg->type);
+		return -EINVAL;
+	}
+
+	if (reg->type == PTR_TO_STACK) {
+		err = nfp_bpf_check_stack_access(nfp_prog, meta, reg);
+		if (err)
+			return err;
+	}
+
+	if (meta->ptr.type != NOT_INIT && meta->ptr.type != reg->type) {
+		pr_info("ptr type changed for instruction %d -> %d\n",
+			meta->ptr.type, reg->type);
+		return -EINVAL;
+	}
+
+	meta->ptr = *reg;
 
 	return 0;
 }
@@ -130,11 +182,6 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 	meta = nfp_bpf_goto_meta(priv->prog, meta, insn_idx, env->prog->len);
 	priv->meta = meta;
 
-	if (meta->insn.src_reg == BPF_REG_10 ||
-	    meta->insn.dst_reg == BPF_REG_10) {
-		pr_err("stack not yet supported\n");
-		return -EINVAL;
-	}
 	if (meta->insn.src_reg >= MAX_BPF_REG ||
 	    meta->insn.dst_reg >= MAX_BPF_REG) {
 		pr_err("program uses extended registers - jit hardening?\n");
@@ -145,11 +192,11 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 		return nfp_bpf_check_exit(priv->prog, env);
 
 	if ((meta->insn.code & ~BPF_SIZE_MASK) == (BPF_LDX | BPF_MEM))
-		return nfp_bpf_check_ctx_ptr(priv->prog, env,
-					     meta->insn.src_reg);
+		return nfp_bpf_check_ptr(priv->prog, meta, env,
+					 meta->insn.src_reg);
 	if ((meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_MEM))
-		return nfp_bpf_check_ctx_ptr(priv->prog, env,
-					     meta->insn.dst_reg);
+		return nfp_bpf_check_ptr(priv->prog, meta, env,
+					 meta->insn.dst_reg);
 
 	return 0;
 }
@@ -163,6 +210,8 @@ int nfp_prog_verify(struct nfp_prog *nfp_prog, struct bpf_prog *prog)
 	struct nfp_bpf_analyzer_priv *priv;
 	int ret;
 
+	nfp_prog->stack_depth = prog->aux->stack_depth;
+
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 8ea9320014ee..de64cedf8b26 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -36,7 +36,9 @@
 #include <net/switchdev.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
+#include <net/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_vlan.h>
+#include <net/tc_act/tc_tunnel_key.h>
 
 #include "cmsg.h"
 #include "main.h"
@@ -45,13 +47,9 @@
 static void nfp_fl_pop_vlan(struct nfp_fl_pop_vlan *pop_vlan)
 {
 	size_t act_size = sizeof(struct nfp_fl_pop_vlan);
-	u16 tmp_pop_vlan_op;
 
-	tmp_pop_vlan_op =
-		FIELD_PREP(NFP_FL_ACT_LEN_LW, act_size >> NFP_FL_LW_SIZ) |
-		FIELD_PREP(NFP_FL_ACT_JMP_ID, NFP_FL_ACTION_OPCODE_POP_VLAN);
-
-	pop_vlan->a_op = cpu_to_be16(tmp_pop_vlan_op);
+	pop_vlan->head.jump_id = NFP_FL_ACTION_OPCODE_POP_VLAN;
+	pop_vlan->head.len_lw = act_size >> NFP_FL_LW_SIZ;
 	pop_vlan->reserved = 0;
 }
 
@@ -62,14 +60,9 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan,
 	size_t act_size = sizeof(struct nfp_fl_push_vlan);
 	struct tcf_vlan *vlan = to_vlan(action);
 	u16 tmp_push_vlan_tci;
-	u16 tmp_push_vlan_op;
-
-	tmp_push_vlan_op =
-		FIELD_PREP(NFP_FL_ACT_LEN_LW, act_size >> NFP_FL_LW_SIZ) |
-		FIELD_PREP(NFP_FL_ACT_JMP_ID, NFP_FL_ACTION_OPCODE_PUSH_VLAN);
 
-	push_vlan->a_op = cpu_to_be16(tmp_push_vlan_op);
-	/* Set action push vlan parameters. */
+	push_vlan->head.jump_id = NFP_FL_ACTION_OPCODE_PUSH_VLAN;
+	push_vlan->head.len_lw = act_size >> NFP_FL_LW_SIZ;
 	push_vlan->reserved = 0;
 	push_vlan->vlan_tpid = tcf_vlan_push_proto(action);
 
@@ -80,44 +73,359 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan,
 	push_vlan->vlan_tci = cpu_to_be16(tmp_push_vlan_tci);
 }
 
+static bool nfp_fl_netdev_is_tunnel_type(struct net_device *out_dev,
+					 enum nfp_flower_tun_type tun_type)
+{
+	if (!out_dev->rtnl_link_ops)
+		return false;
+
+	if (!strcmp(out_dev->rtnl_link_ops->kind, "vxlan"))
+		return tun_type == NFP_FL_TUNNEL_VXLAN;
+
+	return false;
+}
+
 static int
 nfp_fl_output(struct nfp_fl_output *output, const struct tc_action *action,
 	      struct nfp_fl_payload *nfp_flow, bool last,
-	      struct net_device *in_dev)
+	      struct net_device *in_dev, enum nfp_flower_tun_type tun_type,
+	      int *tun_out_cnt)
 {
 	size_t act_size = sizeof(struct nfp_fl_output);
 	struct net_device *out_dev;
-	u16 tmp_output_op;
+	u16 tmp_flags;
 	int ifindex;
 
-	/* Set action opcode to output action. */
-	tmp_output_op =
-		FIELD_PREP(NFP_FL_ACT_LEN_LW, act_size >> NFP_FL_LW_SIZ) |
-		FIELD_PREP(NFP_FL_ACT_JMP_ID, NFP_FL_ACTION_OPCODE_OUTPUT);
-
-	output->a_op = cpu_to_be16(tmp_output_op);
-
-	/* Set action output parameters. */
-	output->flags = cpu_to_be16(last ? NFP_FL_OUT_FLAGS_LAST : 0);
+	output->head.jump_id = NFP_FL_ACTION_OPCODE_OUTPUT;
+	output->head.len_lw = act_size >> NFP_FL_LW_SIZ;
 
 	ifindex = tcf_mirred_ifindex(action);
 	out_dev = __dev_get_by_index(dev_net(in_dev), ifindex);
 	if (!out_dev)
 		return -EOPNOTSUPP;
 
-	/* Only offload egress ports are on the same device as the ingress
-	 * port.
+	tmp_flags = last ? NFP_FL_OUT_FLAGS_LAST : 0;
+
+	if (tun_type) {
+		/* Verify the egress netdev matches the tunnel type. */
+		if (!nfp_fl_netdev_is_tunnel_type(out_dev, tun_type))
+			return -EOPNOTSUPP;
+
+		if (*tun_out_cnt)
+			return -EOPNOTSUPP;
+		(*tun_out_cnt)++;
+
+		output->flags = cpu_to_be16(tmp_flags |
+					    NFP_FL_OUT_FLAGS_USE_TUN);
+		output->port = cpu_to_be32(NFP_FL_PORT_TYPE_TUN | tun_type);
+	} else {
+		/* Set action output parameters. */
+		output->flags = cpu_to_be16(tmp_flags);
+
+		/* Only offload if egress ports are on the same device as the
+		 * ingress port.
+		 */
+		if (!switchdev_port_same_parent_id(in_dev, out_dev))
+			return -EOPNOTSUPP;
+		if (!nfp_netdev_is_nfp_repr(out_dev))
+			return -EOPNOTSUPP;
+
+		output->port = cpu_to_be32(nfp_repr_get_port_id(out_dev));
+		if (!output->port)
+			return -EOPNOTSUPP;
+	}
+	nfp_flow->meta.shortcut = output->port;
+
+	return 0;
+}
+
+static bool nfp_fl_supported_tun_port(const struct tc_action *action)
+{
+	struct ip_tunnel_info *tun = tcf_tunnel_info(action);
+
+	return tun->key.tp_dst == htons(NFP_FL_VXLAN_PORT);
+}
+
+static struct nfp_fl_pre_tunnel *nfp_fl_pre_tunnel(char *act_data, int act_len)
+{
+	size_t act_size = sizeof(struct nfp_fl_pre_tunnel);
+	struct nfp_fl_pre_tunnel *pre_tun_act;
+
+	/* Pre_tunnel action must be first on action list.
+	 * If other actions already exist they need pushed forward.
 	 */
-	if (!switchdev_port_same_parent_id(in_dev, out_dev))
+	if (act_len)
+		memmove(act_data + act_size, act_data, act_len);
+
+	pre_tun_act = (struct nfp_fl_pre_tunnel *)act_data;
+
+	memset(pre_tun_act, 0, act_size);
+
+	pre_tun_act->head.jump_id = NFP_FL_ACTION_OPCODE_PRE_TUNNEL;
+	pre_tun_act->head.len_lw = act_size >> NFP_FL_LW_SIZ;
+
+	return pre_tun_act;
+}
+
+static int
+nfp_fl_set_vxlan(struct nfp_fl_set_vxlan *set_vxlan,
+		 const struct tc_action *action,
+		 struct nfp_fl_pre_tunnel *pre_tun)
+{
+	struct ip_tunnel_info *vxlan = tcf_tunnel_info(action);
+	size_t act_size = sizeof(struct nfp_fl_set_vxlan);
+	u32 tmp_set_vxlan_type_index = 0;
+	/* Currently support one pre-tunnel so index is always 0. */
+	int pretun_idx = 0;
+
+	if (vxlan->options_len) {
+		/* Do not support options e.g. vxlan gpe. */
 		return -EOPNOTSUPP;
-	if (!nfp_netdev_is_nfp_repr(out_dev))
+	}
+
+	set_vxlan->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL;
+	set_vxlan->head.len_lw = act_size >> NFP_FL_LW_SIZ;
+
+	/* Set tunnel type and pre-tunnel index. */
+	tmp_set_vxlan_type_index |=
+		FIELD_PREP(NFP_FL_IPV4_TUNNEL_TYPE, NFP_FL_TUNNEL_VXLAN) |
+		FIELD_PREP(NFP_FL_IPV4_PRE_TUN_INDEX, pretun_idx);
+
+	set_vxlan->tun_type_index = cpu_to_be32(tmp_set_vxlan_type_index);
+
+	set_vxlan->tun_id = vxlan->key.tun_id;
+	set_vxlan->tun_flags = vxlan->key.tun_flags;
+	set_vxlan->ipv4_ttl = vxlan->key.ttl;
+	set_vxlan->ipv4_tos = vxlan->key.tos;
+
+	/* Complete pre_tunnel action. */
+	pre_tun->ipv4_dst = vxlan->key.u.ipv4.dst;
+
+	return 0;
+}
+
+static void nfp_fl_set_helper32(u32 value, u32 mask, u8 *p_exact, u8 *p_mask)
+{
+	u32 oldvalue = get_unaligned((u32 *)p_exact);
+	u32 oldmask = get_unaligned((u32 *)p_mask);
+
+	value &= mask;
+	value |= oldvalue & ~mask;
+
+	put_unaligned(oldmask | mask, (u32 *)p_mask);
+	put_unaligned(value, (u32 *)p_exact);
+}
+
+static int
+nfp_fl_set_eth(const struct tc_action *action, int idx, u32 off,
+	       struct nfp_fl_set_eth *set_eth)
+{
+	u32 exact, mask;
+
+	if (off + 4 > ETH_ALEN * 2)
 		return -EOPNOTSUPP;
 
-	output->port = cpu_to_be32(nfp_repr_get_port_id(out_dev));
-	if (!output->port)
+	mask = ~tcf_pedit_mask(action, idx);
+	exact = tcf_pedit_val(action, idx);
+
+	if (exact & ~mask)
 		return -EOPNOTSUPP;
 
-	nfp_flow->meta.shortcut = output->port;
+	nfp_fl_set_helper32(exact, mask, &set_eth->eth_addr_val[off],
+			    &set_eth->eth_addr_mask[off]);
+
+	set_eth->reserved = cpu_to_be16(0);
+	set_eth->head.jump_id = NFP_FL_ACTION_OPCODE_SET_ETHERNET;
+	set_eth->head.len_lw = sizeof(*set_eth) >> NFP_FL_LW_SIZ;
+
+	return 0;
+}
+
+static int
+nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off,
+	       struct nfp_fl_set_ip4_addrs *set_ip_addr)
+{
+	__be32 exact, mask;
+
+	/* We are expecting tcf_pedit to return a big endian value */
+	mask = (__force __be32)~tcf_pedit_mask(action, idx);
+	exact = (__force __be32)tcf_pedit_val(action, idx);
+
+	if (exact & ~mask)
+		return -EOPNOTSUPP;
+
+	switch (off) {
+	case offsetof(struct iphdr, daddr):
+		set_ip_addr->ipv4_dst_mask = mask;
+		set_ip_addr->ipv4_dst = exact;
+		break;
+	case offsetof(struct iphdr, saddr):
+		set_ip_addr->ipv4_src_mask = mask;
+		set_ip_addr->ipv4_src = exact;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	set_ip_addr->reserved = cpu_to_be16(0);
+	set_ip_addr->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS;
+	set_ip_addr->head.len_lw = sizeof(*set_ip_addr) >> NFP_FL_LW_SIZ;
+
+	return 0;
+}
+
+static void
+nfp_fl_set_ip6_helper(int opcode_tag, int idx, __be32 exact, __be32 mask,
+		      struct nfp_fl_set_ipv6_addr *ip6)
+{
+	ip6->ipv6[idx % 4].mask = mask;
+	ip6->ipv6[idx % 4].exact = exact;
+
+	ip6->reserved = cpu_to_be16(0);
+	ip6->head.jump_id = opcode_tag;
+	ip6->head.len_lw = sizeof(*ip6) >> NFP_FL_LW_SIZ;
+}
+
+static int
+nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off,
+	       struct nfp_fl_set_ipv6_addr *ip_dst,
+	       struct nfp_fl_set_ipv6_addr *ip_src)
+{
+	__be32 exact, mask;
+
+	/* We are expecting tcf_pedit to return a big endian value */
+	mask = (__force __be32)~tcf_pedit_mask(action, idx);
+	exact = (__force __be32)tcf_pedit_val(action, idx);
+
+	if (exact & ~mask)
+		return -EOPNOTSUPP;
+
+	if (off < offsetof(struct ipv6hdr, saddr))
+		return -EOPNOTSUPP;
+	else if (off < offsetof(struct ipv6hdr, daddr))
+		nfp_fl_set_ip6_helper(NFP_FL_ACTION_OPCODE_SET_IPV6_SRC, idx,
+				      exact, mask, ip_src);
+	else if (off < offsetof(struct ipv6hdr, daddr) +
+		       sizeof(struct in6_addr))
+		nfp_fl_set_ip6_helper(NFP_FL_ACTION_OPCODE_SET_IPV6_DST, idx,
+				      exact, mask, ip_dst);
+	else
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static int
+nfp_fl_set_tport(const struct tc_action *action, int idx, u32 off,
+		 struct nfp_fl_set_tport *set_tport, int opcode)
+{
+	u32 exact, mask;
+
+	if (off)
+		return -EOPNOTSUPP;
+
+	mask = ~tcf_pedit_mask(action, idx);
+	exact = tcf_pedit_val(action, idx);
+
+	if (exact & ~mask)
+		return -EOPNOTSUPP;
+
+	nfp_fl_set_helper32(exact, mask, set_tport->tp_port_val,
+			    set_tport->tp_port_mask);
+
+	set_tport->reserved = cpu_to_be16(0);
+	set_tport->head.jump_id = opcode;
+	set_tport->head.len_lw = sizeof(*set_tport) >> NFP_FL_LW_SIZ;
+
+	return 0;
+}
+
+static int
+nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len)
+{
+	struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src;
+	struct nfp_fl_set_ip4_addrs set_ip_addr;
+	struct nfp_fl_set_tport set_tport;
+	struct nfp_fl_set_eth set_eth;
+	enum pedit_header_type htype;
+	int idx, nkeys, err;
+	size_t act_size;
+	u32 offset, cmd;
+
+	memset(&set_ip6_dst, 0, sizeof(set_ip6_dst));
+	memset(&set_ip6_src, 0, sizeof(set_ip6_src));
+	memset(&set_ip_addr, 0, sizeof(set_ip_addr));
+	memset(&set_tport, 0, sizeof(set_tport));
+	memset(&set_eth, 0, sizeof(set_eth));
+	nkeys = tcf_pedit_nkeys(action);
+
+	for (idx = 0; idx < nkeys; idx++) {
+		cmd = tcf_pedit_cmd(action, idx);
+		htype = tcf_pedit_htype(action, idx);
+		offset = tcf_pedit_offset(action, idx);
+
+		if (cmd != TCA_PEDIT_KEY_EX_CMD_SET)
+			return -EOPNOTSUPP;
+
+		switch (htype) {
+		case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
+			err = nfp_fl_set_eth(action, idx, offset, &set_eth);
+			break;
+		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
+			err = nfp_fl_set_ip4(action, idx, offset, &set_ip_addr);
+			break;
+		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
+			err = nfp_fl_set_ip6(action, idx, offset, &set_ip6_dst,
+					     &set_ip6_src);
+			break;
+		case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
+			err = nfp_fl_set_tport(action, idx, offset, &set_tport,
+					       NFP_FL_ACTION_OPCODE_SET_TCP);
+			break;
+		case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
+			err = nfp_fl_set_tport(action, idx, offset, &set_tport,
+					       NFP_FL_ACTION_OPCODE_SET_UDP);
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+		if (err)
+			return err;
+	}
+
+	if (set_eth.head.len_lw) {
+		act_size = sizeof(set_eth);
+		memcpy(nfp_action, &set_eth, act_size);
+		*a_len += act_size;
+	} else if (set_ip_addr.head.len_lw) {
+		act_size = sizeof(set_ip_addr);
+		memcpy(nfp_action, &set_ip_addr, act_size);
+		*a_len += act_size;
+	} else if (set_ip6_dst.head.len_lw && set_ip6_src.head.len_lw) {
+		/* TC compiles set src and dst IPv6 address as a single action,
+		 * the hardware requires this to be 2 separate actions.
+		 */
+		act_size = sizeof(set_ip6_src);
+		memcpy(nfp_action, &set_ip6_src, act_size);
+		*a_len += act_size;
+
+		act_size = sizeof(set_ip6_dst);
+		memcpy(&nfp_action[sizeof(set_ip6_src)], &set_ip6_dst,
+		       act_size);
+		*a_len += act_size;
+	} else if (set_ip6_dst.head.len_lw) {
+		act_size = sizeof(set_ip6_dst);
+		memcpy(nfp_action, &set_ip6_dst, act_size);
+		*a_len += act_size;
+	} else if (set_ip6_src.head.len_lw) {
+		act_size = sizeof(set_ip6_src);
+		memcpy(nfp_action, &set_ip6_src, act_size);
+		*a_len += act_size;
+	} else if (set_tport.head.len_lw) {
+		act_size = sizeof(set_tport);
+		memcpy(nfp_action, &set_tport, act_size);
+		*a_len += act_size;
+	}
 
 	return 0;
 }
@@ -125,8 +433,11 @@ nfp_fl_output(struct nfp_fl_output *output, const struct tc_action *action,
 static int
 nfp_flower_loop_action(const struct tc_action *a,
 		       struct nfp_fl_payload *nfp_fl, int *a_len,
-		       struct net_device *netdev)
+		       struct net_device *netdev,
+		       enum nfp_flower_tun_type *tun_type, int *tun_out_cnt)
 {
+	struct nfp_fl_pre_tunnel *pre_tun;
+	struct nfp_fl_set_vxlan *s_vxl;
 	struct nfp_fl_push_vlan *psh_v;
 	struct nfp_fl_pop_vlan *pop_v;
 	struct nfp_fl_output *output;
@@ -139,7 +450,8 @@ nfp_flower_loop_action(const struct tc_action *a,
 			return -EOPNOTSUPP;
 
 		output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len];
-		err = nfp_fl_output(output, a, nfp_fl, true, netdev);
+		err = nfp_fl_output(output, a, nfp_fl, true, netdev, *tun_type,
+				    tun_out_cnt);
 		if (err)
 			return err;
 
@@ -149,7 +461,8 @@ nfp_flower_loop_action(const struct tc_action *a,
 			return -EOPNOTSUPP;
 
 		output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len];
-		err = nfp_fl_output(output, a, nfp_fl, false, netdev);
+		err = nfp_fl_output(output, a, nfp_fl, false, netdev, *tun_type,
+				    tun_out_cnt);
 		if (err)
 			return err;
 
@@ -172,6 +485,32 @@ nfp_flower_loop_action(const struct tc_action *a,
 
 		nfp_fl_push_vlan(psh_v, a);
 		*a_len += sizeof(struct nfp_fl_push_vlan);
+	} else if (is_tcf_tunnel_set(a) && nfp_fl_supported_tun_port(a)) {
+		/* Pre-tunnel action is required for tunnel encap.
+		 * This checks for next hop entries on NFP.
+		 * If none, the packet falls back before applying other actions.
+		 */
+		if (*a_len + sizeof(struct nfp_fl_pre_tunnel) +
+		    sizeof(struct nfp_fl_set_vxlan) > NFP_FL_MAX_A_SIZ)
+			return -EOPNOTSUPP;
+
+		*tun_type = NFP_FL_TUNNEL_VXLAN;
+		pre_tun = nfp_fl_pre_tunnel(nfp_fl->action_data, *a_len);
+		nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL);
+		*a_len += sizeof(struct nfp_fl_pre_tunnel);
+
+		s_vxl = (struct nfp_fl_set_vxlan *)&nfp_fl->action_data[*a_len];
+		err = nfp_fl_set_vxlan(s_vxl, a, pre_tun);
+		if (err)
+			return err;
+
+		*a_len += sizeof(struct nfp_fl_set_vxlan);
+	} else if (is_tcf_tunnel_release(a)) {
+		/* Tunnel decap is handled by default so accept action. */
+		return 0;
+	} else if (is_tcf_pedit(a)) {
+		if (nfp_fl_pedit(a, &nfp_fl->action_data[*a_len], a_len))
+			return -EOPNOTSUPP;
 	} else {
 		/* Currently we do not handle any other actions. */
 		return -EOPNOTSUPP;
@@ -184,18 +523,22 @@ int nfp_flower_compile_action(struct tc_cls_flower_offload *flow,
 			      struct net_device *netdev,
 			      struct nfp_fl_payload *nfp_flow)
 {
-	int act_len, act_cnt, err;
+	int act_len, act_cnt, err, tun_out_cnt;
+	enum nfp_flower_tun_type tun_type;
 	const struct tc_action *a;
 	LIST_HEAD(actions);
 
 	memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ);
 	nfp_flow->meta.act_len = 0;
+	tun_type = NFP_FL_TUNNEL_NONE;
 	act_len = 0;
 	act_cnt = 0;
+	tun_out_cnt = 0;
 
 	tcf_exts_to_list(flow->exts, &actions);
 	list_for_each_entry(a, &actions, list) {
-		err = nfp_flower_loop_action(a, nfp_flow, &act_len, netdev);
+		err = nfp_flower_loop_action(a, nfp_flow, &act_len, netdev,
+					     &tun_type, &tun_out_cnt);
 		if (err)
 			return err;
 		act_cnt++;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
index c3ca05d10fe1..e98bb9cdb6a3 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
@@ -38,17 +38,10 @@
 #include <net/dst_metadata.h>
 
 #include "main.h"
-#include "../nfpcore/nfp_cpp.h"
 #include "../nfp_net.h"
 #include "../nfp_net_repr.h"
 #include "./cmsg.h"
 
-#define nfp_flower_cmsg_warn(app, fmt, args...)				\
-	do {								\
-		if (net_ratelimit())					\
-			nfp_warn((app)->cpp, fmt, ## args);		\
-	} while (0)
-
 static struct nfp_flower_cmsg_hdr *
 nfp_flower_cmsg_get_hdr(struct sk_buff *skb)
 {
@@ -57,14 +50,14 @@ nfp_flower_cmsg_get_hdr(struct sk_buff *skb)
 
 struct sk_buff *
 nfp_flower_cmsg_alloc(struct nfp_app *app, unsigned int size,
-		      enum nfp_flower_cmsg_type_port type)
+		      enum nfp_flower_cmsg_type_port type, gfp_t flag)
 {
 	struct nfp_flower_cmsg_hdr *ch;
 	struct sk_buff *skb;
 
 	size += NFP_FLOWER_CMSG_HLEN;
 
-	skb = nfp_app_ctrl_msg_alloc(app, size, GFP_KERNEL);
+	skb = nfp_app_ctrl_msg_alloc(app, size, flag);
 	if (!skb)
 		return NULL;
 
@@ -85,7 +78,8 @@ nfp_flower_cmsg_mac_repr_start(struct nfp_app *app, unsigned int num_ports)
 	unsigned int size;
 
 	size = sizeof(*msg) + num_ports * sizeof(msg->ports[0]);
-	skb = nfp_flower_cmsg_alloc(app, size, NFP_FLOWER_CMSG_TYPE_MAC_REPR);
+	skb = nfp_flower_cmsg_alloc(app, size, NFP_FLOWER_CMSG_TYPE_MAC_REPR,
+				    GFP_KERNEL);
 	if (!skb)
 		return NULL;
 
@@ -116,7 +110,7 @@ int nfp_flower_cmsg_portmod(struct nfp_repr *repr, bool carrier_ok)
 	struct sk_buff *skb;
 
 	skb = nfp_flower_cmsg_alloc(repr->app, sizeof(*msg),
-				    NFP_FLOWER_CMSG_TYPE_PORT_MOD);
+				    NFP_FLOWER_CMSG_TYPE_PORT_MOD, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
@@ -188,6 +182,15 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb)
 	case NFP_FLOWER_CMSG_TYPE_FLOW_STATS:
 		nfp_flower_rx_flow_stats(app, skb);
 		break;
+	case NFP_FLOWER_CMSG_TYPE_NO_NEIGH:
+		nfp_tunnel_request_route(app, skb);
+		break;
+	case NFP_FLOWER_CMSG_TYPE_ACTIVE_TUNS:
+		nfp_tunnel_keep_alive(app, skb);
+		break;
+	case NFP_FLOWER_CMSG_TYPE_TUN_NEIGH:
+		/* Acks from the NFP that the route is added - ignore. */
+		break;
 	default:
 		nfp_flower_cmsg_warn(app, "Cannot handle invalid repr control type %u\n",
 				     type);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index a2ec60344236..66070741d55f 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -39,6 +39,7 @@
 #include <linux/types.h>
 
 #include "../nfp_app.h"
+#include "../nfpcore/nfp_cpp.h"
 
 #define NFP_FLOWER_LAYER_META		BIT(0)
 #define NFP_FLOWER_LAYER_PORT		BIT(1)
@@ -56,6 +57,11 @@
 #define NFP_FLOWER_MASK_VLAN_CFI	BIT(12)
 #define NFP_FLOWER_MASK_VLAN_VID	GENMASK(11, 0)
 
+#define NFP_FLOWER_MASK_MPLS_LB		GENMASK(31, 12)
+#define NFP_FLOWER_MASK_MPLS_TC		GENMASK(11, 9)
+#define NFP_FLOWER_MASK_MPLS_BOS	BIT(8)
+#define NFP_FLOWER_MASK_MPLS_Q		BIT(0)
+
 #define NFP_FL_SC_ACT_DROP		0x80000000
 #define NFP_FL_SC_ACT_USER		0x7D000000
 #define NFP_FL_SC_ACT_POPV		0x6A000000
@@ -67,13 +73,18 @@
 #define NFP_FL_LW_SIZ			2
 
 /* Action opcodes */
-#define NFP_FL_ACTION_OPCODE_OUTPUT	0
-#define NFP_FL_ACTION_OPCODE_PUSH_VLAN	1
-#define NFP_FL_ACTION_OPCODE_POP_VLAN	2
-#define NFP_FL_ACTION_OPCODE_NUM	32
-
-#define NFP_FL_ACT_JMP_ID		GENMASK(15, 8)
-#define NFP_FL_ACT_LEN_LW		GENMASK(7, 0)
+#define NFP_FL_ACTION_OPCODE_OUTPUT		0
+#define NFP_FL_ACTION_OPCODE_PUSH_VLAN		1
+#define NFP_FL_ACTION_OPCODE_POP_VLAN		2
+#define NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL	6
+#define NFP_FL_ACTION_OPCODE_SET_ETHERNET	7
+#define NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS	9
+#define NFP_FL_ACTION_OPCODE_SET_IPV6_SRC	11
+#define NFP_FL_ACTION_OPCODE_SET_IPV6_DST	12
+#define NFP_FL_ACTION_OPCODE_SET_UDP		14
+#define NFP_FL_ACTION_OPCODE_SET_TCP		15
+#define NFP_FL_ACTION_OPCODE_PRE_TUNNEL		17
+#define NFP_FL_ACTION_OPCODE_NUM		32
 
 #define NFP_FL_OUT_FLAGS_LAST		BIT(15)
 #define NFP_FL_OUT_FLAGS_USE_TUN	BIT(4)
@@ -83,21 +94,74 @@
 #define NFP_FL_PUSH_VLAN_CFI		BIT(12)
 #define NFP_FL_PUSH_VLAN_VID		GENMASK(11, 0)
 
+/* Tunnel ports */
+#define NFP_FL_PORT_TYPE_TUN		0x50000000
+#define NFP_FL_IPV4_TUNNEL_TYPE		GENMASK(7, 4)
+#define NFP_FL_IPV4_PRE_TUN_INDEX	GENMASK(2, 0)
+
+#define nfp_flower_cmsg_warn(app, fmt, args...)                         \
+	do {                                                            \
+		if (net_ratelimit())                                    \
+			nfp_warn((app)->cpp, fmt, ## args);             \
+	} while (0)
+
+enum nfp_flower_tun_type {
+	NFP_FL_TUNNEL_NONE =	0,
+	NFP_FL_TUNNEL_VXLAN =	2,
+};
+
+struct nfp_fl_act_head {
+	u8 jump_id;
+	u8 len_lw;
+};
+
+struct nfp_fl_set_eth {
+	struct nfp_fl_act_head head;
+	__be16 reserved;
+	u8 eth_addr_mask[ETH_ALEN * 2];
+	u8 eth_addr_val[ETH_ALEN * 2];
+};
+
+struct nfp_fl_set_ip4_addrs {
+	struct nfp_fl_act_head head;
+	__be16 reserved;
+	__be32 ipv4_src_mask;
+	__be32 ipv4_src;
+	__be32 ipv4_dst_mask;
+	__be32 ipv4_dst;
+};
+
+struct nfp_fl_set_ipv6_addr {
+	struct nfp_fl_act_head head;
+	__be16 reserved;
+	struct {
+		__be32 mask;
+		__be32 exact;
+	} ipv6[4];
+};
+
+struct nfp_fl_set_tport {
+	struct nfp_fl_act_head head;
+	__be16 reserved;
+	u8 tp_port_mask[4];
+	u8 tp_port_val[4];
+};
+
 struct nfp_fl_output {
-	__be16 a_op;
+	struct nfp_fl_act_head head;
 	__be16 flags;
 	__be32 port;
 };
 
 struct nfp_fl_push_vlan {
-	__be16 a_op;
+	struct nfp_fl_act_head head;
 	__be16 reserved;
 	__be16 vlan_tpid;
 	__be16 vlan_tci;
 };
 
 struct nfp_fl_pop_vlan {
-	__be16 a_op;
+	struct nfp_fl_act_head head;
 	__be16 reserved;
 };
 
@@ -115,6 +179,25 @@ struct nfp_flower_meta_one {
 	u16 reserved;
 };
 
+struct nfp_fl_pre_tunnel {
+	struct nfp_fl_act_head head;
+	__be16 reserved;
+	__be32 ipv4_dst;
+	/* reserved for use with IPv6 addresses */
+	__be32 extra[3];
+};
+
+struct nfp_fl_set_vxlan {
+	struct nfp_fl_act_head head;
+	__be16 reserved;
+	__be64 tun_id;
+	__be32 tun_type_index;
+	__be16 tun_flags;
+	u8 ipv4_ttl;
+	u8 ipv4_tos;
+	__be32 extra[2];
+} __packed;
+
 /* Metadata with L2 (1W/4B)
  * ----------------------------------------------------------------
  *    3                   2                   1
@@ -230,6 +313,36 @@ struct nfp_flower_ipv6 {
 	struct in6_addr ipv6_dst;
 };
 
+/* Flow Frame VXLAN --> Tunnel details (4W/16B)
+ * -----------------------------------------------------------------
+ *    3                   2                   1
+ *  1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                         ipv4_addr_src                         |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                         ipv4_addr_dst                         |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |           tun_flags           |       tos     |       ttl     |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |   gpe_flags   |            Reserved           | Next Protocol |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                     VNI                       |   Reserved    |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ */
+struct nfp_flower_vxlan {
+	__be32 ip_src;
+	__be32 ip_dst;
+	__be16 tun_flags;
+	u8 tos;
+	u8 ttl;
+	u8 gpe_flags;
+	u8 reserved[2];
+	u8 nxt_proto;
+	__be32 tun_id;
+};
+
+#define NFP_FL_TUN_VNI_OFFSET 8
+
 /* The base header for a control message packet.
  * Defines an 8-bit version, and an 8-bit type, padded
  * to a 32-bit word. Rest of the packet is type-specific.
@@ -249,6 +362,11 @@ enum nfp_flower_cmsg_type_port {
 	NFP_FLOWER_CMSG_TYPE_FLOW_DEL =		2,
 	NFP_FLOWER_CMSG_TYPE_MAC_REPR =		7,
 	NFP_FLOWER_CMSG_TYPE_PORT_MOD =		8,
+	NFP_FLOWER_CMSG_TYPE_NO_NEIGH =		10,
+	NFP_FLOWER_CMSG_TYPE_TUN_MAC =		11,
+	NFP_FLOWER_CMSG_TYPE_ACTIVE_TUNS =	12,
+	NFP_FLOWER_CMSG_TYPE_TUN_NEIGH =	13,
+	NFP_FLOWER_CMSG_TYPE_TUN_IPS =		14,
 	NFP_FLOWER_CMSG_TYPE_FLOW_STATS =	15,
 	NFP_FLOWER_CMSG_TYPE_PORT_ECHO =	16,
 	NFP_FLOWER_CMSG_TYPE_MAX =		32,
@@ -282,6 +400,7 @@ enum nfp_flower_cmsg_port_type {
 	NFP_FLOWER_CMSG_PORT_TYPE_UNSPEC =	0x0,
 	NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT =	0x1,
 	NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT =	0x2,
+	NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT =  0x3,
 };
 
 enum nfp_flower_cmsg_port_vnic_type {
@@ -323,6 +442,11 @@ static inline void *nfp_flower_cmsg_get_data(struct sk_buff *skb)
 	return (unsigned char *)skb->data + NFP_FLOWER_CMSG_HLEN;
 }
 
+static inline int nfp_flower_cmsg_get_data_len(struct sk_buff *skb)
+{
+	return skb->len - NFP_FLOWER_CMSG_HLEN;
+}
+
 struct sk_buff *
 nfp_flower_cmsg_mac_repr_start(struct nfp_app *app, unsigned int num_ports);
 void
@@ -334,6 +458,6 @@ void nfp_flower_cmsg_process_rx(struct work_struct *work);
 void nfp_flower_cmsg_rx(struct nfp_app *app, struct sk_buff *skb);
 struct sk_buff *
 nfp_flower_cmsg_alloc(struct nfp_app *app, unsigned int size,
-		      enum nfp_flower_cmsg_type_port type);
+		      enum nfp_flower_cmsg_type_port type, gfp_t flag);
 
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 91fe03617106..e46e7c60d491 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -436,6 +436,16 @@ static void nfp_flower_clean(struct nfp_app *app)
 	app->priv = NULL;
 }
 
+static int nfp_flower_start(struct nfp_app *app)
+{
+	return nfp_tunnel_config_start(app);
+}
+
+static void nfp_flower_stop(struct nfp_app *app)
+{
+	nfp_tunnel_config_stop(app);
+}
+
 const struct nfp_app_type app_flower = {
 	.id		= NFP_APP_FLOWER_NIC,
 	.name		= "flower",
@@ -453,6 +463,9 @@ const struct nfp_app_type app_flower = {
 	.repr_open	= nfp_flower_repr_netdev_open,
 	.repr_stop	= nfp_flower_repr_netdev_stop,
 
+	.start		= nfp_flower_start,
+	.stop		= nfp_flower_stop,
+
 	.ctrl_msg_rx	= nfp_flower_cmsg_rx,
 
 	.sriov_enable	= nfp_flower_sriov_enable,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index c20dd00a1cae..c90e72b7ff5a 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -58,6 +58,8 @@ struct nfp_app;
 #define NFP_FL_MASK_REUSE_TIME_NS	40000
 #define NFP_FL_MASK_ID_LOCATION		1
 
+#define NFP_FL_VXLAN_PORT		4789
+
 struct nfp_fl_mask_id {
 	struct circ_buf mask_id_free_list;
 	struct timespec64 *last_used;
@@ -82,6 +84,18 @@ struct nfp_fl_stats_id {
  * @flow_table:		Hash table used to store flower rules
  * @cmsg_work:		Workqueue for control messages processing
  * @cmsg_skbs:		List of skbs for control message processing
+ * @nfp_mac_off_list:	List of MAC addresses to offload
+ * @nfp_mac_index_list:	List of unique 8-bit indexes for non NFP netdevs
+ * @nfp_ipv4_off_list:	List of IPv4 addresses to offload
+ * @nfp_neigh_off_list:	List of neighbour offloads
+ * @nfp_mac_off_lock:	Lock for the MAC address list
+ * @nfp_mac_index_lock:	Lock for the MAC index list
+ * @nfp_ipv4_off_lock:	Lock for the IPv4 address list
+ * @nfp_neigh_off_lock:	Lock for the neighbour address list
+ * @nfp_mac_off_ids:	IDA to manage id assignment for offloaded macs
+ * @nfp_mac_off_count:	Number of MACs in address list
+ * @nfp_tun_mac_nb:	Notifier to monitor link state
+ * @nfp_tun_neigh_nb:	Notifier to monitor neighbour state
  */
 struct nfp_flower_priv {
 	struct nfp_app *app;
@@ -94,6 +108,18 @@ struct nfp_flower_priv {
 	DECLARE_HASHTABLE(flow_table, NFP_FLOWER_HASH_BITS);
 	struct work_struct cmsg_work;
 	struct sk_buff_head cmsg_skbs;
+	struct list_head nfp_mac_off_list;
+	struct list_head nfp_mac_index_list;
+	struct list_head nfp_ipv4_off_list;
+	struct list_head nfp_neigh_off_list;
+	struct mutex nfp_mac_off_lock;
+	struct mutex nfp_mac_index_lock;
+	struct mutex nfp_ipv4_off_lock;
+	spinlock_t nfp_neigh_off_lock;
+	struct ida nfp_mac_off_ids;
+	int nfp_mac_off_count;
+	struct notifier_block nfp_tun_mac_nb;
+	struct notifier_block nfp_tun_neigh_nb;
 };
 
 struct nfp_fl_key_ls {
@@ -126,6 +152,7 @@ struct nfp_fl_payload {
 	struct rcu_head rcu;
 	spinlock_t lock; /* lock stats */
 	struct nfp_fl_stats stats;
+	__be32 nfp_tun_ipv4_addr;
 	char *unmasked_data;
 	char *mask_data;
 	char *action_data;
@@ -163,4 +190,12 @@ nfp_flower_remove_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie);
 
 void nfp_flower_rx_flow_stats(struct nfp_app *app, struct sk_buff *skb);
 
+int nfp_tunnel_config_start(struct nfp_app *app);
+void nfp_tunnel_config_stop(struct nfp_app *app);
+void nfp_tunnel_write_macs(struct nfp_app *app);
+void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4);
+void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4);
+void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb);
+void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb);
+
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index d25b5038c3a2..60614d4f0e22 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -77,14 +77,17 @@ nfp_flower_compile_meta(struct nfp_flower_meta_one *frame, u8 key_type)
 
 static int
 nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port,
-			bool mask_version)
+			bool mask_version, enum nfp_flower_tun_type tun_type)
 {
 	if (mask_version) {
 		frame->in_port = cpu_to_be32(~0);
 		return 0;
 	}
 
-	frame->in_port = cpu_to_be32(cmsg_port);
+	if (tun_type)
+		frame->in_port = cpu_to_be32(NFP_FL_PORT_TYPE_TUN | tun_type);
+	else
+		frame->in_port = cpu_to_be32(cmsg_port);
 
 	return 0;
 }
@@ -108,8 +111,21 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame,
 		ether_addr_copy(frame->mac_src, &addr->src[0]);
 	}
 
-	if (mask_version)
-		frame->mpls_lse = cpu_to_be32(~0);
+	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_MPLS)) {
+		struct flow_dissector_key_mpls *mpls;
+		u32 t_mpls;
+
+		mpls = skb_flow_dissector_target(flow->dissector,
+						 FLOW_DISSECTOR_KEY_MPLS,
+						 target);
+
+		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, mpls->mpls_label) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, mpls->mpls_tc) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, mpls->mpls_bos) |
+			 NFP_FLOWER_MASK_MPLS_Q;
+
+		frame->mpls_lse = cpu_to_be32(t_mpls);
+	}
 }
 
 static void
@@ -140,7 +156,6 @@ nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *frame,
 	struct flow_dissector_key_ipv4_addrs *addr;
 	struct flow_dissector_key_basic *basic;
 
-	/* Wildcard TOS/TTL for now. */
 	memset(frame, 0, sizeof(struct nfp_flower_ipv4));
 
 	if (dissector_uses_key(flow->dissector,
@@ -158,6 +173,16 @@ nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *frame,
 						  target);
 		frame->proto = basic->ip_proto;
 	}
+
+	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_IP)) {
+		struct flow_dissector_key_ip *flow_ip;
+
+		flow_ip = skb_flow_dissector_target(flow->dissector,
+						    FLOW_DISSECTOR_KEY_IP,
+						    target);
+		frame->tos = flow_ip->tos;
+		frame->ttl = flow_ip->ttl;
+	}
 }
 
 static void
@@ -169,7 +194,6 @@ nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame,
 	struct flow_dissector_key_ipv6_addrs *addr;
 	struct flow_dissector_key_basic *basic;
 
-	/* Wildcard LABEL/TOS/TTL for now. */
 	memset(frame, 0, sizeof(struct nfp_flower_ipv6));
 
 	if (dissector_uses_key(flow->dissector,
@@ -187,6 +211,51 @@ nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame,
 						  target);
 		frame->proto = basic->ip_proto;
 	}
+
+	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_IP)) {
+		struct flow_dissector_key_ip *flow_ip;
+
+		flow_ip = skb_flow_dissector_target(flow->dissector,
+						    FLOW_DISSECTOR_KEY_IP,
+						    target);
+		frame->tos = flow_ip->tos;
+		frame->ttl = flow_ip->ttl;
+	}
+}
+
+static void
+nfp_flower_compile_vxlan(struct nfp_flower_vxlan *frame,
+			 struct tc_cls_flower_offload *flow,
+			 bool mask_version, __be32 *tun_dst)
+{
+	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
+	struct flow_dissector_key_ipv4_addrs *vxlan_ips;
+	struct flow_dissector_key_keyid *vni;
+
+	/* Wildcard TOS/TTL/GPE_FLAGS/NXT_PROTO for now. */
+	memset(frame, 0, sizeof(struct nfp_flower_vxlan));
+
+	if (dissector_uses_key(flow->dissector,
+			       FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		u32 temp_vni;
+
+		vni = skb_flow_dissector_target(flow->dissector,
+						FLOW_DISSECTOR_KEY_ENC_KEYID,
+						target);
+		temp_vni = be32_to_cpu(vni->keyid) << NFP_FL_TUN_VNI_OFFSET;
+		frame->tun_id = cpu_to_be32(temp_vni);
+	}
+
+	if (dissector_uses_key(flow->dissector,
+			       FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+		vxlan_ips =
+		   skb_flow_dissector_target(flow->dissector,
+					     FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
+					     target);
+		frame->ip_src = vxlan_ips->src;
+		frame->ip_dst = vxlan_ips->dst;
+		*tun_dst = vxlan_ips->dst;
+	}
 }
 
 int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
@@ -194,10 +263,16 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
 				  struct net_device *netdev,
 				  struct nfp_fl_payload *nfp_flow)
 {
+	enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE;
+	__be32 tun_dst, tun_dst_mask = 0;
+	struct nfp_repr *netdev_repr;
 	int err;
 	u8 *ext;
 	u8 *msk;
 
+	if (key_ls->key_layer & NFP_FLOWER_LAYER_VXLAN)
+		tun_type = NFP_FL_TUNNEL_VXLAN;
+
 	memset(nfp_flow->unmasked_data, 0, key_ls->key_size);
 	memset(nfp_flow->mask_data, 0, key_ls->key_size);
 
@@ -216,14 +291,14 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
 		/* Populate Exact Port data. */
 		err = nfp_flower_compile_port((struct nfp_flower_in_port *)ext,
 					      nfp_repr_get_port_id(netdev),
-					      false);
+					      false, tun_type);
 		if (err)
 			return err;
 
 		/* Populate Mask Port Data. */
 		err = nfp_flower_compile_port((struct nfp_flower_in_port *)msk,
 					      nfp_repr_get_port_id(netdev),
-					      true);
+					      true, tun_type);
 		if (err)
 			return err;
 
@@ -291,5 +366,28 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
 		msk += sizeof(struct nfp_flower_ipv6);
 	}
 
+	if (key_ls->key_layer & NFP_FLOWER_LAYER_VXLAN) {
+		/* Populate Exact VXLAN Data. */
+		nfp_flower_compile_vxlan((struct nfp_flower_vxlan *)ext,
+					 flow, false, &tun_dst);
+		/* Populate Mask VXLAN Data. */
+		nfp_flower_compile_vxlan((struct nfp_flower_vxlan *)msk,
+					 flow, true, &tun_dst_mask);
+		ext += sizeof(struct nfp_flower_vxlan);
+		msk += sizeof(struct nfp_flower_vxlan);
+
+		/* Configure tunnel end point MAC. */
+		if (nfp_netdev_is_nfp_repr(netdev)) {
+			netdev_repr = netdev_priv(netdev);
+			nfp_tunnel_write_macs(netdev_repr->app);
+
+			/* Store the tunnel destination in the rule data.
+			 * This must be present and be an exact match.
+			 */
+			nfp_flow->nfp_tun_ipv4_addr = tun_dst;
+			nfp_tunnel_add_ipv4_off(netdev_repr->app, tun_dst);
+		}
+	}
+
 	return 0;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index 3226ddc55f99..193520ef23f0 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -140,7 +140,7 @@ exit_rcu_unlock:
 
 void nfp_flower_rx_flow_stats(struct nfp_app *app, struct sk_buff *skb)
 {
-	unsigned int msg_len = skb->len - NFP_FLOWER_CMSG_HLEN;
+	unsigned int msg_len = nfp_flower_cmsg_get_data_len(skb);
 	struct nfp_fl_stats_frame *stats_frame;
 	unsigned char *msg;
 	int i;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index a18b4d2b1d3e..cdbb5464b790 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -52,8 +52,26 @@
 	 BIT(FLOW_DISSECTOR_KEY_PORTS) | \
 	 BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \
 	 BIT(FLOW_DISSECTOR_KEY_VLAN) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \
+	 BIT(FLOW_DISSECTOR_KEY_MPLS) | \
 	 BIT(FLOW_DISSECTOR_KEY_IP))
 
+#define NFP_FLOWER_WHITELIST_TUN_DISSECTOR \
+	(BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))
+
+#define NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R \
+	(BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))
+
 static int
 nfp_flower_xmit_flow(struct net_device *netdev,
 		     struct nfp_fl_payload *nfp_flow, u8 mtype)
@@ -77,7 +95,7 @@ nfp_flower_xmit_flow(struct net_device *netdev,
 	nfp_flow->meta.mask_len >>= NFP_FL_LW_SIZ;
 	nfp_flow->meta.act_len >>= NFP_FL_LW_SIZ;
 
-	skb = nfp_flower_cmsg_alloc(priv->app, tot_len, mtype);
+	skb = nfp_flower_cmsg_alloc(priv->app, tot_len, mtype, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
@@ -117,7 +135,6 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls,
 {
 	struct flow_dissector_key_basic *mask_basic = NULL;
 	struct flow_dissector_key_basic *key_basic = NULL;
-	struct flow_dissector_key_ip *mask_ip = NULL;
 	u32 key_layer_two;
 	u8 key_layer;
 	int key_size;
@@ -125,15 +142,58 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls,
 	if (flow->dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR)
 		return -EOPNOTSUPP;
 
+	/* If any tun dissector is used then the required set must be used. */
+	if (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR &&
+	    (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R)
+	    != NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R)
+		return -EOPNOTSUPP;
+
+	key_layer_two = 0;
+	key_layer = NFP_FLOWER_LAYER_PORT | NFP_FLOWER_LAYER_MAC;
+	key_size = sizeof(struct nfp_flower_meta_one) +
+		   sizeof(struct nfp_flower_in_port) +
+		   sizeof(struct nfp_flower_mac_mpls);
+
 	if (dissector_uses_key(flow->dissector,
 			       FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
+		struct flow_dissector_key_ipv4_addrs *mask_ipv4 = NULL;
+		struct flow_dissector_key_ports *mask_enc_ports = NULL;
+		struct flow_dissector_key_ports *enc_ports = NULL;
 		struct flow_dissector_key_control *mask_enc_ctl =
 			skb_flow_dissector_target(flow->dissector,
 						  FLOW_DISSECTOR_KEY_ENC_CONTROL,
 						  flow->mask);
-		/* We are expecting a tunnel. For now we ignore offloading. */
-		if (mask_enc_ctl->addr_type)
+		struct flow_dissector_key_control *enc_ctl =
+			skb_flow_dissector_target(flow->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_CONTROL,
+						  flow->key);
+		if (mask_enc_ctl->addr_type != 0xffff ||
+		    enc_ctl->addr_type != FLOW_DISSECTOR_KEY_IPV4_ADDRS)
 			return -EOPNOTSUPP;
+
+		/* These fields are already verified as used. */
+		mask_ipv4 =
+			skb_flow_dissector_target(flow->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
+						  flow->mask);
+		if (mask_ipv4->dst != cpu_to_be32(~0))
+			return -EOPNOTSUPP;
+
+		mask_enc_ports =
+			skb_flow_dissector_target(flow->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_PORTS,
+						  flow->mask);
+		enc_ports =
+			skb_flow_dissector_target(flow->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_PORTS,
+						  flow->key);
+
+		if (mask_enc_ports->dst != cpu_to_be16(~0) ||
+		    enc_ports->dst != htons(NFP_FL_VXLAN_PORT))
+			return -EOPNOTSUPP;
+
+		key_layer |= NFP_FLOWER_LAYER_VXLAN;
+		key_size += sizeof(struct nfp_flower_vxlan);
 	}
 
 	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
@@ -146,34 +206,15 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls,
 						      flow->key);
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_IP))
-		mask_ip = skb_flow_dissector_target(flow->dissector,
-						    FLOW_DISSECTOR_KEY_IP,
-						    flow->mask);
-
-	key_layer_two = 0;
-	key_layer = NFP_FLOWER_LAYER_PORT | NFP_FLOWER_LAYER_MAC;
-	key_size = sizeof(struct nfp_flower_meta_one) +
-		   sizeof(struct nfp_flower_in_port) +
-		   sizeof(struct nfp_flower_mac_mpls);
-
 	if (mask_basic && mask_basic->n_proto) {
 		/* Ethernet type is present in the key. */
 		switch (key_basic->n_proto) {
 		case cpu_to_be16(ETH_P_IP):
-			if (mask_ip && mask_ip->tos)
-				return -EOPNOTSUPP;
-			if (mask_ip && mask_ip->ttl)
-				return -EOPNOTSUPP;
 			key_layer |= NFP_FLOWER_LAYER_IPV4;
 			key_size += sizeof(struct nfp_flower_ipv4);
 			break;
 
 		case cpu_to_be16(ETH_P_IPV6):
-			if (mask_ip && mask_ip->tos)
-				return -EOPNOTSUPP;
-			if (mask_ip && mask_ip->ttl)
-				return -EOPNOTSUPP;
 			key_layer |= NFP_FLOWER_LAYER_IPV6;
 			key_size += sizeof(struct nfp_flower_ipv6);
 			break;
@@ -184,11 +225,6 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls,
 		case cpu_to_be16(ETH_P_ARP):
 			return -EOPNOTSUPP;
 
-		/* Currently we do not offload MPLS. */
-		case cpu_to_be16(ETH_P_MPLS_UC):
-		case cpu_to_be16(ETH_P_MPLS_MC):
-			return -EOPNOTSUPP;
-
 		/* Will be included in layer 2. */
 		case cpu_to_be16(ETH_P_8021Q):
 			break;
@@ -252,6 +288,7 @@ nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer)
 	if (!flow_pay->action_data)
 		goto err_free_mask;
 
+	flow_pay->nfp_tun_ipv4_addr = 0;
 	flow_pay->meta.flags = 0;
 	spin_lock_init(&flow_pay->lock);
 
@@ -361,6 +398,9 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
 	if (err)
 		goto err_free_flow;
 
+	if (nfp_flow->nfp_tun_ipv4_addr)
+		nfp_tunnel_del_ipv4_off(app, nfp_flow->nfp_tun_ipv4_addr);
+
 	err = nfp_flower_xmit_flow(netdev, nfp_flow,
 				   NFP_FLOWER_CMSG_TYPE_FLOW_DEL);
 	if (err)
@@ -409,6 +449,10 @@ static int
 nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev,
 			struct tc_cls_flower_offload *flower)
 {
+	if (!eth_proto_is_802_3(flower->common.protocol) ||
+	    flower->common.chain_index)
+		return -EOPNOTSUPP;
+
 	switch (flower->command) {
 	case TC_CLSFLOWER_REPLACE:
 		return nfp_flower_add_offload(app, netdev, flower);
@@ -421,16 +465,53 @@ nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev,
 	return -EOPNOTSUPP;
 }
 
-int nfp_flower_setup_tc(struct nfp_app *app, struct net_device *netdev,
-			enum tc_setup_type type, void *type_data)
+static int nfp_flower_setup_tc_block_cb(enum tc_setup_type type,
+					void *type_data, void *cb_priv)
 {
-	struct tc_cls_flower_offload *cls_flower = type_data;
+	struct nfp_repr *repr = cb_priv;
 
-	if (type != TC_SETUP_CLSFLOWER ||
-	    !is_classid_clsact_ingress(cls_flower->common.classid) ||
-	    !eth_proto_is_802_3(cls_flower->common.protocol) ||
-	    cls_flower->common.chain_index)
+	if (!tc_can_offload(repr->netdev))
 		return -EOPNOTSUPP;
 
-	return nfp_flower_repr_offload(app, netdev, cls_flower);
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return nfp_flower_repr_offload(repr->app, repr->netdev,
+					       type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int nfp_flower_setup_tc_block(struct net_device *netdev,
+				     struct tc_block_offload *f)
+{
+	struct nfp_repr *repr = netdev_priv(netdev);
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block,
+					     nfp_flower_setup_tc_block_cb,
+					     repr, repr);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block,
+					nfp_flower_setup_tc_block_cb,
+					repr);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+int nfp_flower_setup_tc(struct nfp_app *app, struct net_device *netdev,
+			enum tc_setup_type type, void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return nfp_flower_setup_tc_block(netdev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
new file mode 100644
index 000000000000..b03f22f29612
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -0,0 +1,804 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/inetdevice.h>
+#include <net/netevent.h>
+#include <linux/idr.h>
+#include <net/dst_metadata.h>
+#include <net/arp.h>
+
+#include "cmsg.h"
+#include "main.h"
+#include "../nfp_net_repr.h"
+#include "../nfp_net.h"
+
+#define NFP_FL_MAX_ROUTES               32
+
+/**
+ * struct nfp_tun_active_tuns - periodic message of active tunnels
+ * @seq:		sequence number of the message
+ * @count:		number of tunnels report in message
+ * @flags:		options part of the request
+ * @ipv4:		dest IPv4 address of active route
+ * @egress_port:	port the encapsulated packet egressed
+ * @extra:		reserved for future use
+ * @tun_info:		tunnels that have sent traffic in reported period
+ */
+struct nfp_tun_active_tuns {
+	__be32 seq;
+	__be32 count;
+	__be32 flags;
+	struct route_ip_info {
+		__be32 ipv4;
+		__be32 egress_port;
+		__be32 extra[2];
+	} tun_info[];
+};
+
+/**
+ * struct nfp_tun_neigh - neighbour/route entry on the NFP
+ * @dst_ipv4:	destination IPv4 address
+ * @src_ipv4:	source IPv4 address
+ * @dst_addr:	destination MAC address
+ * @src_addr:	source MAC address
+ * @port_id:	NFP port to output packet on - associated with source IPv4
+ */
+struct nfp_tun_neigh {
+	__be32 dst_ipv4;
+	__be32 src_ipv4;
+	u8 dst_addr[ETH_ALEN];
+	u8 src_addr[ETH_ALEN];
+	__be32 port_id;
+};
+
+/**
+ * struct nfp_tun_req_route_ipv4 - NFP requests a route/neighbour lookup
+ * @ingress_port:	ingress port of packet that signalled request
+ * @ipv4_addr:		destination ipv4 address for route
+ * @reserved:		reserved for future use
+ */
+struct nfp_tun_req_route_ipv4 {
+	__be32 ingress_port;
+	__be32 ipv4_addr;
+	__be32 reserved[2];
+};
+
+/**
+ * struct nfp_ipv4_route_entry - routes that are offloaded to the NFP
+ * @ipv4_addr:	destination of route
+ * @list:	list pointer
+ */
+struct nfp_ipv4_route_entry {
+	__be32 ipv4_addr;
+	struct list_head list;
+};
+
+#define NFP_FL_IPV4_ADDRS_MAX        32
+
+/**
+ * struct nfp_tun_ipv4_addr - set the IP address list on the NFP
+ * @count:	number of IPs populated in the array
+ * @ipv4_addr:	array of IPV4_ADDRS_MAX 32 bit IPv4 addresses
+ */
+struct nfp_tun_ipv4_addr {
+	__be32 count;
+	__be32 ipv4_addr[NFP_FL_IPV4_ADDRS_MAX];
+};
+
+/**
+ * struct nfp_ipv4_addr_entry - cached IPv4 addresses
+ * @ipv4_addr:	IP address
+ * @ref_count:	number of rules currently using this IP
+ * @list:	list pointer
+ */
+struct nfp_ipv4_addr_entry {
+	__be32 ipv4_addr;
+	int ref_count;
+	struct list_head list;
+};
+
+/**
+ * struct nfp_tun_mac_addr - configure MAC address of tunnel EP on NFP
+ * @reserved:	reserved for future use
+ * @count:	number of MAC addresses in the message
+ * @index:	index of MAC address in the lookup table
+ * @addr:	interface MAC address
+ * @addresses:	series of MACs to offload
+ */
+struct nfp_tun_mac_addr {
+	__be16 reserved;
+	__be16 count;
+	struct index_mac_addr {
+		__be16 index;
+		u8 addr[ETH_ALEN];
+	} addresses[];
+};
+
+/**
+ * struct nfp_tun_mac_offload_entry - list of MACs to offload
+ * @index:	index of MAC address for offloading
+ * @addr:	interface MAC address
+ * @list:	list pointer
+ */
+struct nfp_tun_mac_offload_entry {
+	__be16 index;
+	u8 addr[ETH_ALEN];
+	struct list_head list;
+};
+
+#define NFP_MAX_MAC_INDEX       0xff
+
+/**
+ * struct nfp_tun_mac_non_nfp_idx - converts non NFP netdev ifindex to 8-bit id
+ * @ifindex:	netdev ifindex of the device
+ * @index:	index of netdevs mac on NFP
+ * @list:	list pointer
+ */
+struct nfp_tun_mac_non_nfp_idx {
+	int ifindex;
+	u8 index;
+	struct list_head list;
+};
+
+void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb)
+{
+	struct nfp_tun_active_tuns *payload;
+	struct net_device *netdev;
+	int count, i, pay_len;
+	struct neighbour *n;
+	__be32 ipv4_addr;
+	u32 port;
+
+	payload = nfp_flower_cmsg_get_data(skb);
+	count = be32_to_cpu(payload->count);
+	if (count > NFP_FL_MAX_ROUTES) {
+		nfp_flower_cmsg_warn(app, "Tunnel keep-alive request exceeds max routes.\n");
+		return;
+	}
+
+	pay_len = nfp_flower_cmsg_get_data_len(skb);
+	if (pay_len != sizeof(struct nfp_tun_active_tuns) +
+	    sizeof(struct route_ip_info) * count) {
+		nfp_flower_cmsg_warn(app, "Corruption in tunnel keep-alive message.\n");
+		return;
+	}
+
+	for (i = 0; i < count; i++) {
+		ipv4_addr = payload->tun_info[i].ipv4;
+		port = be32_to_cpu(payload->tun_info[i].egress_port);
+		netdev = nfp_app_repr_get(app, port);
+		if (!netdev)
+			continue;
+
+		n = neigh_lookup(&arp_tbl, &ipv4_addr, netdev);
+		if (!n)
+			continue;
+
+		/* Update the used timestamp of neighbour */
+		neigh_event_send(n, NULL);
+		neigh_release(n);
+	}
+}
+
+static bool nfp_tun_is_netdev_to_offload(struct net_device *netdev)
+{
+	if (!netdev->rtnl_link_ops)
+		return false;
+	if (!strcmp(netdev->rtnl_link_ops->kind, "openvswitch"))
+		return true;
+	if (!strcmp(netdev->rtnl_link_ops->kind, "vxlan"))
+		return true;
+
+	return false;
+}
+
+static int
+nfp_flower_xmit_tun_conf(struct nfp_app *app, u8 mtype, u16 plen, void *pdata,
+			 gfp_t flag)
+{
+	struct sk_buff *skb;
+	unsigned char *msg;
+
+	skb = nfp_flower_cmsg_alloc(app, plen, mtype, flag);
+	if (!skb)
+		return -ENOMEM;
+
+	msg = nfp_flower_cmsg_get_data(skb);
+	memcpy(msg, pdata, nfp_flower_cmsg_get_data_len(skb));
+
+	nfp_ctrl_tx(app->ctrl, skb);
+	return 0;
+}
+
+static bool nfp_tun_has_route(struct nfp_app *app, __be32 ipv4_addr)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_ipv4_route_entry *entry;
+	struct list_head *ptr, *storage;
+
+	spin_lock_bh(&priv->nfp_neigh_off_lock);
+	list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+		entry = list_entry(ptr, struct nfp_ipv4_route_entry, list);
+		if (entry->ipv4_addr == ipv4_addr) {
+			spin_unlock_bh(&priv->nfp_neigh_off_lock);
+			return true;
+		}
+	}
+	spin_unlock_bh(&priv->nfp_neigh_off_lock);
+	return false;
+}
+
+static void nfp_tun_add_route_to_cache(struct nfp_app *app, __be32 ipv4_addr)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_ipv4_route_entry *entry;
+	struct list_head *ptr, *storage;
+
+	spin_lock_bh(&priv->nfp_neigh_off_lock);
+	list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+		entry = list_entry(ptr, struct nfp_ipv4_route_entry, list);
+		if (entry->ipv4_addr == ipv4_addr) {
+			spin_unlock_bh(&priv->nfp_neigh_off_lock);
+			return;
+		}
+	}
+	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+	if (!entry) {
+		spin_unlock_bh(&priv->nfp_neigh_off_lock);
+		nfp_flower_cmsg_warn(app, "Mem error when storing new route.\n");
+		return;
+	}
+
+	entry->ipv4_addr = ipv4_addr;
+	list_add_tail(&entry->list, &priv->nfp_neigh_off_list);
+	spin_unlock_bh(&priv->nfp_neigh_off_lock);
+}
+
+static void nfp_tun_del_route_from_cache(struct nfp_app *app, __be32 ipv4_addr)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_ipv4_route_entry *entry;
+	struct list_head *ptr, *storage;
+
+	spin_lock_bh(&priv->nfp_neigh_off_lock);
+	list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+		entry = list_entry(ptr, struct nfp_ipv4_route_entry, list);
+		if (entry->ipv4_addr == ipv4_addr) {
+			list_del(&entry->list);
+			kfree(entry);
+			break;
+		}
+	}
+	spin_unlock_bh(&priv->nfp_neigh_off_lock);
+}
+
+static void
+nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app,
+		    struct flowi4 *flow, struct neighbour *neigh, gfp_t flag)
+{
+	struct nfp_tun_neigh payload;
+
+	/* Only offload representor IPv4s for now. */
+	if (!nfp_netdev_is_nfp_repr(netdev))
+		return;
+
+	memset(&payload, 0, sizeof(struct nfp_tun_neigh));
+	payload.dst_ipv4 = flow->daddr;
+
+	/* If entry has expired send dst IP with all other fields 0. */
+	if (!(neigh->nud_state & NUD_VALID)) {
+		nfp_tun_del_route_from_cache(app, payload.dst_ipv4);
+		/* Trigger ARP to verify invalid neighbour state. */
+		neigh_event_send(neigh, NULL);
+		goto send_msg;
+	}
+
+	/* Have a valid neighbour so populate rest of entry. */
+	payload.src_ipv4 = flow->saddr;
+	ether_addr_copy(payload.src_addr, netdev->dev_addr);
+	neigh_ha_snapshot(payload.dst_addr, neigh, netdev);
+	payload.port_id = cpu_to_be32(nfp_repr_get_port_id(netdev));
+	/* Add destination of new route to NFP cache. */
+	nfp_tun_add_route_to_cache(app, payload.dst_ipv4);
+
+send_msg:
+	nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_NEIGH,
+				 sizeof(struct nfp_tun_neigh),
+				 (unsigned char *)&payload, flag);
+}
+
+static int
+nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
+			    void *ptr)
+{
+	struct nfp_flower_priv *app_priv;
+	struct netevent_redirect *redir;
+	struct flowi4 flow = {};
+	struct neighbour *n;
+	struct nfp_app *app;
+	struct rtable *rt;
+	int err;
+
+	switch (event) {
+	case NETEVENT_REDIRECT:
+		redir = (struct netevent_redirect *)ptr;
+		n = redir->neigh;
+		break;
+	case NETEVENT_NEIGH_UPDATE:
+		n = (struct neighbour *)ptr;
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	flow.daddr = *(__be32 *)n->primary_key;
+
+	/* Only concerned with route changes for representors. */
+	if (!nfp_netdev_is_nfp_repr(n->dev))
+		return NOTIFY_DONE;
+
+	app_priv = container_of(nb, struct nfp_flower_priv, nfp_tun_neigh_nb);
+	app = app_priv->app;
+
+	/* Only concerned with changes to routes already added to NFP. */
+	if (!nfp_tun_has_route(app, flow.daddr))
+		return NOTIFY_DONE;
+
+#if IS_ENABLED(CONFIG_INET)
+	/* Do a route lookup to populate flow data. */
+	rt = ip_route_output_key(dev_net(n->dev), &flow);
+	err = PTR_ERR_OR_ZERO(rt);
+	if (err)
+		return NOTIFY_DONE;
+#else
+	return NOTIFY_DONE;
+#endif
+
+	flow.flowi4_proto = IPPROTO_UDP;
+	nfp_tun_write_neigh(n->dev, app, &flow, n, GFP_ATOMIC);
+
+	return NOTIFY_OK;
+}
+
+void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb)
+{
+	struct nfp_tun_req_route_ipv4 *payload;
+	struct net_device *netdev;
+	struct flowi4 flow = {};
+	struct neighbour *n;
+	struct rtable *rt;
+	int err;
+
+	payload = nfp_flower_cmsg_get_data(skb);
+
+	netdev = nfp_app_repr_get(app, be32_to_cpu(payload->ingress_port));
+	if (!netdev)
+		goto route_fail_warning;
+
+	flow.daddr = payload->ipv4_addr;
+	flow.flowi4_proto = IPPROTO_UDP;
+
+#if IS_ENABLED(CONFIG_INET)
+	/* Do a route lookup on same namespace as ingress port. */
+	rt = ip_route_output_key(dev_net(netdev), &flow);
+	err = PTR_ERR_OR_ZERO(rt);
+	if (err)
+		goto route_fail_warning;
+#else
+	goto route_fail_warning;
+#endif
+
+	/* Get the neighbour entry for the lookup */
+	n = dst_neigh_lookup(&rt->dst, &flow.daddr);
+	ip_rt_put(rt);
+	if (!n)
+		goto route_fail_warning;
+	nfp_tun_write_neigh(n->dev, app, &flow, n, GFP_KERNEL);
+	neigh_release(n);
+	return;
+
+route_fail_warning:
+	nfp_flower_cmsg_warn(app, "Requested route not found.\n");
+}
+
+static void nfp_tun_write_ipv4_list(struct nfp_app *app)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_ipv4_addr_entry *entry;
+	struct nfp_tun_ipv4_addr payload;
+	struct list_head *ptr, *storage;
+	int count;
+
+	memset(&payload, 0, sizeof(struct nfp_tun_ipv4_addr));
+	mutex_lock(&priv->nfp_ipv4_off_lock);
+	count = 0;
+	list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+		if (count >= NFP_FL_IPV4_ADDRS_MAX) {
+			mutex_unlock(&priv->nfp_ipv4_off_lock);
+			nfp_flower_cmsg_warn(app, "IPv4 offload exceeds limit.\n");
+			return;
+		}
+		entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
+		payload.ipv4_addr[count++] = entry->ipv4_addr;
+	}
+	payload.count = cpu_to_be32(count);
+	mutex_unlock(&priv->nfp_ipv4_off_lock);
+
+	nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_IPS,
+				 sizeof(struct nfp_tun_ipv4_addr),
+				 &payload, GFP_KERNEL);
+}
+
+void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_ipv4_addr_entry *entry;
+	struct list_head *ptr, *storage;
+
+	mutex_lock(&priv->nfp_ipv4_off_lock);
+	list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+		entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
+		if (entry->ipv4_addr == ipv4) {
+			entry->ref_count++;
+			mutex_unlock(&priv->nfp_ipv4_off_lock);
+			return;
+		}
+	}
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry) {
+		mutex_unlock(&priv->nfp_ipv4_off_lock);
+		nfp_flower_cmsg_warn(app, "Mem error when offloading IP address.\n");
+		return;
+	}
+	entry->ipv4_addr = ipv4;
+	entry->ref_count = 1;
+	list_add_tail(&entry->list, &priv->nfp_ipv4_off_list);
+	mutex_unlock(&priv->nfp_ipv4_off_lock);
+
+	nfp_tun_write_ipv4_list(app);
+}
+
+void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_ipv4_addr_entry *entry;
+	struct list_head *ptr, *storage;
+
+	mutex_lock(&priv->nfp_ipv4_off_lock);
+	list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+		entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
+		if (entry->ipv4_addr == ipv4) {
+			entry->ref_count--;
+			if (!entry->ref_count) {
+				list_del(&entry->list);
+				kfree(entry);
+			}
+			break;
+		}
+	}
+	mutex_unlock(&priv->nfp_ipv4_off_lock);
+
+	nfp_tun_write_ipv4_list(app);
+}
+
+void nfp_tunnel_write_macs(struct nfp_app *app)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_tun_mac_offload_entry *entry;
+	struct nfp_tun_mac_addr *payload;
+	struct list_head *ptr, *storage;
+	int mac_count, err, pay_size;
+
+	mutex_lock(&priv->nfp_mac_off_lock);
+	if (!priv->nfp_mac_off_count) {
+		mutex_unlock(&priv->nfp_mac_off_lock);
+		return;
+	}
+
+	pay_size = sizeof(struct nfp_tun_mac_addr) +
+		   sizeof(struct index_mac_addr) * priv->nfp_mac_off_count;
+
+	payload = kzalloc(pay_size, GFP_KERNEL);
+	if (!payload) {
+		mutex_unlock(&priv->nfp_mac_off_lock);
+		return;
+	}
+
+	payload->count = cpu_to_be16(priv->nfp_mac_off_count);
+
+	mac_count = 0;
+	list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) {
+		entry = list_entry(ptr, struct nfp_tun_mac_offload_entry,
+				   list);
+		payload->addresses[mac_count].index = entry->index;
+		ether_addr_copy(payload->addresses[mac_count].addr,
+				entry->addr);
+		mac_count++;
+	}
+
+	err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_MAC,
+				       pay_size, payload, GFP_KERNEL);
+
+	kfree(payload);
+
+	if (err) {
+		mutex_unlock(&priv->nfp_mac_off_lock);
+		/* Write failed so retain list for future retry. */
+		return;
+	}
+
+	/* If list was successfully offloaded, flush it. */
+	list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) {
+		entry = list_entry(ptr, struct nfp_tun_mac_offload_entry,
+				   list);
+		list_del(&entry->list);
+		kfree(entry);
+	}
+
+	priv->nfp_mac_off_count = 0;
+	mutex_unlock(&priv->nfp_mac_off_lock);
+}
+
+static int nfp_tun_get_mac_idx(struct nfp_app *app, int ifindex)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_tun_mac_non_nfp_idx *entry;
+	struct list_head *ptr, *storage;
+	int idx;
+
+	mutex_lock(&priv->nfp_mac_index_lock);
+	list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) {
+		entry = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx, list);
+		if (entry->ifindex == ifindex) {
+			idx = entry->index;
+			mutex_unlock(&priv->nfp_mac_index_lock);
+			return idx;
+		}
+	}
+
+	idx = ida_simple_get(&priv->nfp_mac_off_ids, 0,
+			     NFP_MAX_MAC_INDEX, GFP_KERNEL);
+	if (idx < 0) {
+		mutex_unlock(&priv->nfp_mac_index_lock);
+		return idx;
+	}
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry) {
+		mutex_unlock(&priv->nfp_mac_index_lock);
+		return -ENOMEM;
+	}
+	entry->ifindex = ifindex;
+	entry->index = idx;
+	list_add_tail(&entry->list, &priv->nfp_mac_index_list);
+	mutex_unlock(&priv->nfp_mac_index_lock);
+
+	return idx;
+}
+
+static void nfp_tun_del_mac_idx(struct nfp_app *app, int ifindex)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_tun_mac_non_nfp_idx *entry;
+	struct list_head *ptr, *storage;
+
+	mutex_lock(&priv->nfp_mac_index_lock);
+	list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) {
+		entry = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx, list);
+		if (entry->ifindex == ifindex) {
+			ida_simple_remove(&priv->nfp_mac_off_ids,
+					  entry->index);
+			list_del(&entry->list);
+			kfree(entry);
+			break;
+		}
+	}
+	mutex_unlock(&priv->nfp_mac_index_lock);
+}
+
+static void nfp_tun_add_to_mac_offload_list(struct net_device *netdev,
+					    struct nfp_app *app)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_tun_mac_offload_entry *entry;
+	u16 nfp_mac_idx;
+	int port = 0;
+
+	/* Check if MAC should be offloaded. */
+	if (!is_valid_ether_addr(netdev->dev_addr))
+		return;
+
+	if (nfp_netdev_is_nfp_repr(netdev))
+		port = nfp_repr_get_port_id(netdev);
+	else if (!nfp_tun_is_netdev_to_offload(netdev))
+		return;
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry) {
+		nfp_flower_cmsg_warn(app, "Mem fail when offloading MAC.\n");
+		return;
+	}
+
+	if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port) ==
+	    NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT) {
+		nfp_mac_idx = port << 8 | NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT;
+	} else if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port) ==
+		   NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT) {
+		port = FIELD_GET(NFP_FLOWER_CMSG_PORT_VNIC, port);
+		nfp_mac_idx = port << 8 | NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT;
+	} else {
+		/* Must assign our own unique 8-bit index. */
+		int idx = nfp_tun_get_mac_idx(app, netdev->ifindex);
+
+		if (idx < 0) {
+			nfp_flower_cmsg_warn(app, "Can't assign non-repr MAC index.\n");
+			kfree(entry);
+			return;
+		}
+		nfp_mac_idx = idx << 8 | NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT;
+	}
+
+	entry->index = cpu_to_be16(nfp_mac_idx);
+	ether_addr_copy(entry->addr, netdev->dev_addr);
+
+	mutex_lock(&priv->nfp_mac_off_lock);
+	priv->nfp_mac_off_count++;
+	list_add_tail(&entry->list, &priv->nfp_mac_off_list);
+	mutex_unlock(&priv->nfp_mac_off_lock);
+}
+
+static int nfp_tun_mac_event_handler(struct notifier_block *nb,
+				     unsigned long event, void *ptr)
+{
+	struct nfp_flower_priv *app_priv;
+	struct net_device *netdev;
+	struct nfp_app *app;
+
+	if (event == NETDEV_DOWN || event == NETDEV_UNREGISTER) {
+		app_priv = container_of(nb, struct nfp_flower_priv,
+					nfp_tun_mac_nb);
+		app = app_priv->app;
+		netdev = netdev_notifier_info_to_dev(ptr);
+
+		/* If non-nfp netdev then free its offload index. */
+		if (nfp_tun_is_netdev_to_offload(netdev))
+			nfp_tun_del_mac_idx(app, netdev->ifindex);
+	} else if (event == NETDEV_UP || event == NETDEV_CHANGEADDR ||
+		   event == NETDEV_REGISTER) {
+		app_priv = container_of(nb, struct nfp_flower_priv,
+					nfp_tun_mac_nb);
+		app = app_priv->app;
+		netdev = netdev_notifier_info_to_dev(ptr);
+
+		nfp_tun_add_to_mac_offload_list(netdev, app);
+
+		/* Force a list write to keep NFP up to date. */
+		nfp_tunnel_write_macs(app);
+	}
+	return NOTIFY_OK;
+}
+
+int nfp_tunnel_config_start(struct nfp_app *app)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct net_device *netdev;
+	int err;
+
+	/* Initialise priv data for MAC offloading. */
+	priv->nfp_mac_off_count = 0;
+	mutex_init(&priv->nfp_mac_off_lock);
+	INIT_LIST_HEAD(&priv->nfp_mac_off_list);
+	priv->nfp_tun_mac_nb.notifier_call = nfp_tun_mac_event_handler;
+	mutex_init(&priv->nfp_mac_index_lock);
+	INIT_LIST_HEAD(&priv->nfp_mac_index_list);
+	ida_init(&priv->nfp_mac_off_ids);
+
+	/* Initialise priv data for IPv4 offloading. */
+	mutex_init(&priv->nfp_ipv4_off_lock);
+	INIT_LIST_HEAD(&priv->nfp_ipv4_off_list);
+
+	/* Initialise priv data for neighbour offloading. */
+	spin_lock_init(&priv->nfp_neigh_off_lock);
+	INIT_LIST_HEAD(&priv->nfp_neigh_off_list);
+	priv->nfp_tun_neigh_nb.notifier_call = nfp_tun_neigh_event_handler;
+
+	err = register_netdevice_notifier(&priv->nfp_tun_mac_nb);
+	if (err)
+		goto err_free_mac_ida;
+
+	err = register_netevent_notifier(&priv->nfp_tun_neigh_nb);
+	if (err)
+		goto err_unreg_mac_nb;
+
+	/* Parse netdevs already registered for MACs that need offloaded. */
+	rtnl_lock();
+	for_each_netdev(&init_net, netdev)
+		nfp_tun_add_to_mac_offload_list(netdev, app);
+	rtnl_unlock();
+
+	return 0;
+
+err_unreg_mac_nb:
+	unregister_netdevice_notifier(&priv->nfp_tun_mac_nb);
+err_free_mac_ida:
+	ida_destroy(&priv->nfp_mac_off_ids);
+	return err;
+}
+
+void nfp_tunnel_config_stop(struct nfp_app *app)
+{
+	struct nfp_tun_mac_offload_entry *mac_entry;
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_ipv4_route_entry *route_entry;
+	struct nfp_tun_mac_non_nfp_idx *mac_idx;
+	struct nfp_ipv4_addr_entry *ip_entry;
+	struct list_head *ptr, *storage;
+
+	unregister_netdevice_notifier(&priv->nfp_tun_mac_nb);
+	unregister_netevent_notifier(&priv->nfp_tun_neigh_nb);
+
+	/* Free any memory that may be occupied by MAC list. */
+	list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) {
+		mac_entry = list_entry(ptr, struct nfp_tun_mac_offload_entry,
+				       list);
+		list_del(&mac_entry->list);
+		kfree(mac_entry);
+	}
+
+	/* Free any memory that may be occupied by MAC index list. */
+	list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) {
+		mac_idx = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx,
+				     list);
+		list_del(&mac_idx->list);
+		kfree(mac_idx);
+	}
+
+	ida_destroy(&priv->nfp_mac_off_ids);
+
+	/* Free any memory that may be occupied by ipv4 list. */
+	list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+		ip_entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
+		list_del(&ip_entry->list);
+		kfree(ip_entry);
+	}
+
+	/* Free any memory that may be occupied by the route list. */
+	list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+		route_entry = list_entry(ptr, struct nfp_ipv4_route_entry,
+					 list);
+		list_del(&route_entry->list);
+		kfree(route_entry);
+	}
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c
index 82c290763529..3644d74fe304 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c
@@ -31,6 +31,7 @@
  * SOFTWARE.
  */
 
+#include <linux/bug.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 
@@ -42,10 +43,14 @@
 #include "nfp_net_repr.h"
 
 static const struct nfp_app_type *apps[] = {
-	&app_nic,
-	&app_bpf,
+	[NFP_APP_CORE_NIC]	= &app_nic,
+#ifdef CONFIG_BPF_SYSCALL
+	[NFP_APP_BPF_NIC]	= &app_bpf,
+#else
+	[NFP_APP_BPF_NIC]	= &app_nic,
+#endif
 #ifdef CONFIG_NFP_APP_FLOWER
-	&app_flower,
+	[NFP_APP_FLOWER_NIC]	= &app_flower,
 #endif
 };
 
@@ -115,17 +120,13 @@ exit_unlock:
 struct nfp_app *nfp_app_alloc(struct nfp_pf *pf, enum nfp_app_id id)
 {
 	struct nfp_app *app;
-	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(apps); i++)
-		if (apps[i]->id == id)
-			break;
-	if (i == ARRAY_SIZE(apps)) {
+	if (id >= ARRAY_SIZE(apps) || !apps[id]) {
 		nfp_err(pf->cpp, "failed to find app with ID 0x%02hhx\n", id);
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (WARN_ON(!apps[i]->name || !apps[i]->vnic_alloc))
+	if (WARN_ON(!apps[id]->name || !apps[id]->vnic_alloc))
 		return ERR_PTR(-EINVAL);
 
 	app = kzalloc(sizeof(*app), GFP_KERNEL);
@@ -135,7 +136,7 @@ struct nfp_app *nfp_app_alloc(struct nfp_pf *pf, enum nfp_app_id id)
 	app->pf = pf;
 	app->cpp = pf->cpp;
 	app->pdev = pf->pdev;
-	app->type = apps[i];
+	app->type = apps[id];
 
 	return app;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h
index af640b5c2108..857bb33020ba 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h
@@ -36,6 +36,8 @@
 
 #include <net/devlink.h>
 
+#include <trace/events/devlink.h>
+
 #include "nfp_net_repr.h"
 
 struct bpf_prog;
@@ -271,11 +273,17 @@ static inline int nfp_app_xdp_offload(struct nfp_app *app, struct nfp_net *nn,
 
 static inline bool nfp_app_ctrl_tx(struct nfp_app *app, struct sk_buff *skb)
 {
+	trace_devlink_hwmsg(priv_to_devlink(app->pf), false, 0,
+			    skb->data, skb->len);
+
 	return nfp_ctrl_tx(app->ctrl, skb);
 }
 
 static inline void nfp_app_ctrl_rx(struct nfp_app *app, struct sk_buff *skb)
 {
+	trace_devlink_hwmsg(priv_to_devlink(app->pf), true, 0,
+			    skb->data, skb->len);
+
 	app->type->ctrl_msg_rx(app, skb);
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c
new file mode 100644
index 000000000000..830f6de25f47
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c
@@ -0,0 +1,257 @@
+/*
+ * Copyright (C) 2016-2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "nfp_asm.h"
+
+const struct cmd_tgt_act cmd_tgt_act[__CMD_TGT_MAP_SIZE] = {
+	[CMD_TGT_WRITE8_SWAP] =		{ 0x02, 0x42 },
+	[CMD_TGT_READ8] =		{ 0x01, 0x43 },
+	[CMD_TGT_READ32] =		{ 0x00, 0x5c },
+	[CMD_TGT_READ32_LE] =		{ 0x01, 0x5c },
+	[CMD_TGT_READ32_SWAP] =		{ 0x02, 0x5c },
+	[CMD_TGT_READ_LE] =		{ 0x01, 0x40 },
+	[CMD_TGT_READ_SWAP_LE] =	{ 0x03, 0x40 },
+};
+
+static u16 nfp_swreg_to_unreg(swreg reg, bool is_dst)
+{
+	bool lm_id, lm_dec = false;
+	u16 val = swreg_value(reg);
+
+	switch (swreg_type(reg)) {
+	case NN_REG_GPR_A:
+	case NN_REG_GPR_B:
+	case NN_REG_GPR_BOTH:
+		return val;
+	case NN_REG_NNR:
+		return UR_REG_NN | val;
+	case NN_REG_XFER:
+		return UR_REG_XFR | val;
+	case NN_REG_LMEM:
+		lm_id = swreg_lm_idx(reg);
+
+		switch (swreg_lm_mode(reg)) {
+		case NN_LM_MOD_NONE:
+			if (val & ~UR_REG_LM_IDX_MAX) {
+				pr_err("LM offset too large\n");
+				return 0;
+			}
+			return UR_REG_LM | FIELD_PREP(UR_REG_LM_IDX, lm_id) |
+				val;
+		case NN_LM_MOD_DEC:
+			lm_dec = true;
+			/* fall through */
+		case NN_LM_MOD_INC:
+			if (val) {
+				pr_err("LM offset in inc/dev mode\n");
+				return 0;
+			}
+			return UR_REG_LM | UR_REG_LM_POST_MOD |
+				FIELD_PREP(UR_REG_LM_IDX, lm_id) |
+				FIELD_PREP(UR_REG_LM_POST_MOD_DEC, lm_dec);
+		default:
+			pr_err("bad LM mode for unrestricted operands %d\n",
+			       swreg_lm_mode(reg));
+			return 0;
+		}
+	case NN_REG_IMM:
+		if (val & ~0xff) {
+			pr_err("immediate too large\n");
+			return 0;
+		}
+		return UR_REG_IMM_encode(val);
+	case NN_REG_NONE:
+		return is_dst ? UR_REG_NO_DST : REG_NONE;
+	}
+
+	pr_err("unrecognized reg encoding %08x\n", reg);
+	return 0;
+}
+
+int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg,
+			  struct nfp_insn_ur_regs *reg)
+{
+	memset(reg, 0, sizeof(*reg));
+
+	/* Decode destination */
+	if (swreg_type(dst) == NN_REG_IMM)
+		return -EFAULT;
+
+	if (swreg_type(dst) == NN_REG_GPR_B)
+		reg->dst_ab = ALU_DST_B;
+	if (swreg_type(dst) == NN_REG_GPR_BOTH)
+		reg->wr_both = true;
+	reg->dst = nfp_swreg_to_unreg(dst, true);
+
+	/* Decode source operands */
+	if (swreg_type(lreg) == swreg_type(rreg))
+		return -EFAULT;
+
+	if (swreg_type(lreg) == NN_REG_GPR_B ||
+	    swreg_type(rreg) == NN_REG_GPR_A) {
+		reg->areg = nfp_swreg_to_unreg(rreg, false);
+		reg->breg = nfp_swreg_to_unreg(lreg, false);
+		reg->swap = true;
+	} else {
+		reg->areg = nfp_swreg_to_unreg(lreg, false);
+		reg->breg = nfp_swreg_to_unreg(rreg, false);
+	}
+
+	reg->dst_lmextn = swreg_lmextn(dst);
+	reg->src_lmextn = swreg_lmextn(lreg) | swreg_lmextn(rreg);
+
+	return 0;
+}
+
+static u16 nfp_swreg_to_rereg(swreg reg, bool is_dst, bool has_imm8, bool *i8)
+{
+	u16 val = swreg_value(reg);
+	bool lm_id;
+
+	switch (swreg_type(reg)) {
+	case NN_REG_GPR_A:
+	case NN_REG_GPR_B:
+	case NN_REG_GPR_BOTH:
+		return val;
+	case NN_REG_XFER:
+		return RE_REG_XFR | val;
+	case NN_REG_LMEM:
+		lm_id = swreg_lm_idx(reg);
+
+		if (swreg_lm_mode(reg) != NN_LM_MOD_NONE) {
+			pr_err("bad LM mode for restricted operands %d\n",
+			       swreg_lm_mode(reg));
+			return 0;
+		}
+
+		if (val & ~RE_REG_LM_IDX_MAX) {
+			pr_err("LM offset too large\n");
+			return 0;
+		}
+
+		return RE_REG_LM | FIELD_PREP(RE_REG_LM_IDX, lm_id) | val;
+	case NN_REG_IMM:
+		if (val & ~(0x7f | has_imm8 << 7)) {
+			pr_err("immediate too large\n");
+			return 0;
+		}
+		*i8 = val & 0x80;
+		return RE_REG_IMM_encode(val & 0x7f);
+	case NN_REG_NONE:
+		return is_dst ? RE_REG_NO_DST : REG_NONE;
+	case NN_REG_NNR:
+		pr_err("NNRs used with restricted encoding\n");
+		return 0;
+	}
+
+	pr_err("unrecognized reg encoding\n");
+	return 0;
+}
+
+int swreg_to_restricted(swreg dst, swreg lreg, swreg rreg,
+			struct nfp_insn_re_regs *reg, bool has_imm8)
+{
+	memset(reg, 0, sizeof(*reg));
+
+	/* Decode destination */
+	if (swreg_type(dst) == NN_REG_IMM)
+		return -EFAULT;
+
+	if (swreg_type(dst) == NN_REG_GPR_B)
+		reg->dst_ab = ALU_DST_B;
+	if (swreg_type(dst) == NN_REG_GPR_BOTH)
+		reg->wr_both = true;
+	reg->dst = nfp_swreg_to_rereg(dst, true, false, NULL);
+
+	/* Decode source operands */
+	if (swreg_type(lreg) == swreg_type(rreg))
+		return -EFAULT;
+
+	if (swreg_type(lreg) == NN_REG_GPR_B ||
+	    swreg_type(rreg) == NN_REG_GPR_A) {
+		reg->areg = nfp_swreg_to_rereg(rreg, false, has_imm8, &reg->i8);
+		reg->breg = nfp_swreg_to_rereg(lreg, false, has_imm8, &reg->i8);
+		reg->swap = true;
+	} else {
+		reg->areg = nfp_swreg_to_rereg(lreg, false, has_imm8, &reg->i8);
+		reg->breg = nfp_swreg_to_rereg(rreg, false, has_imm8, &reg->i8);
+	}
+
+	reg->dst_lmextn = swreg_lmextn(dst);
+	reg->src_lmextn = swreg_lmextn(lreg) | swreg_lmextn(rreg);
+
+	return 0;
+}
+
+#define NFP_USTORE_ECC_POLY_WORDS		7
+#define NFP_USTORE_OP_BITS			45
+
+static const u64 nfp_ustore_ecc_polynomials[NFP_USTORE_ECC_POLY_WORDS] = {
+	0x0ff800007fffULL,
+	0x11f801ff801fULL,
+	0x1e387e0781e1ULL,
+	0x17cb8e388e22ULL,
+	0x1af5b2c93244ULL,
+	0x1f56d5525488ULL,
+	0x0daf69a46910ULL,
+};
+
+static bool parity(u64 value)
+{
+	return hweight64(value) & 1;
+}
+
+int nfp_ustore_check_valid_no_ecc(u64 insn)
+{
+	if (insn & ~GENMASK_ULL(NFP_USTORE_OP_BITS, 0))
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 nfp_ustore_calc_ecc_insn(u64 insn)
+{
+	u8 ecc = 0;
+	int i;
+
+	for (i = 0; i < NFP_USTORE_ECC_POLY_WORDS; i++)
+		ecc |= parity(nfp_ustore_ecc_polynomials[i] & insn) << i;
+
+	return insn | (u64)ecc << NFP_USTORE_OP_BITS;
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
index d2b535739d2b..74d0c11ab2f9 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
@@ -34,6 +34,8 @@
 #ifndef __NFP_ASM_H__
 #define __NFP_ASM_H__ 1
 
+#include <linux/bitfield.h>
+#include <linux/bug.h>
 #include <linux/types.h>
 
 #define REG_NONE	0
@@ -43,23 +45,31 @@
 #define RE_REG_IMM_encode(x)					\
 	(RE_REG_IMM | ((x) & 0x1f) | (((x) & 0x60) << 1))
 #define RE_REG_IMM_MAX	 0x07fULL
+#define RE_REG_LM	0x050
+#define RE_REG_LM_IDX	0x008
+#define RE_REG_LM_IDX_MAX	0x7
 #define RE_REG_XFR	0x080
 
 #define UR_REG_XFR	0x180
+#define UR_REG_LM	0x200
+#define UR_REG_LM_IDX	0x020
+#define UR_REG_LM_POST_MOD	0x010
+#define UR_REG_LM_POST_MOD_DEC	0x001
+#define UR_REG_LM_IDX_MAX	0xf
 #define UR_REG_NN	0x280
 #define UR_REG_NO_DST	0x300
 #define UR_REG_IMM	UR_REG_NO_DST
 #define UR_REG_IMM_encode(x) (UR_REG_IMM | (x))
 #define UR_REG_IMM_MAX	 0x0ffULL
 
-#define OP_BR_BASE	0x0d800000020ULL
-#define OP_BR_BASE_MASK	0x0f8000c3ce0ULL
-#define OP_BR_MASK	0x0000000001fULL
-#define OP_BR_EV_PIP	0x00000000300ULL
-#define OP_BR_CSS	0x0000003c000ULL
-#define OP_BR_DEFBR	0x00000300000ULL
-#define OP_BR_ADDR_LO	0x007ffc00000ULL
-#define OP_BR_ADDR_HI	0x10000000000ULL
+#define OP_BR_BASE		0x0d800000020ULL
+#define OP_BR_BASE_MASK		0x0f8000c3ce0ULL
+#define OP_BR_MASK		0x0000000001fULL
+#define OP_BR_EV_PIP		0x00000000300ULL
+#define OP_BR_CSS		0x0000003c000ULL
+#define OP_BR_DEFBR		0x00000300000ULL
+#define OP_BR_ADDR_LO		0x007ffc00000ULL
+#define OP_BR_ADDR_HI		0x10000000000ULL
 
 #define nfp_is_br(_insn)				\
 	(((_insn) & OP_BR_BASE_MASK) == OP_BR_BASE)
@@ -82,30 +92,33 @@ enum br_ctx_signal_state {
 	BR_CSS_NONE = 2,
 };
 
-#define OP_BBYTE_BASE	0x0c800000000ULL
-#define OP_BB_A_SRC	0x000000000ffULL
-#define OP_BB_BYTE	0x00000000300ULL
-#define OP_BB_B_SRC	0x0000003fc00ULL
-#define OP_BB_I8	0x00000040000ULL
-#define OP_BB_EQ	0x00000080000ULL
-#define OP_BB_DEFBR	0x00000300000ULL
-#define OP_BB_ADDR_LO	0x007ffc00000ULL
-#define OP_BB_ADDR_HI	0x10000000000ULL
-
-#define OP_BALU_BASE	0x0e800000000ULL
-#define OP_BA_A_SRC	0x000000003ffULL
-#define OP_BA_B_SRC	0x000000ffc00ULL
-#define OP_BA_DEFBR	0x00000300000ULL
-#define OP_BA_ADDR_HI	0x0007fc00000ULL
-
-#define OP_IMMED_A_SRC	0x000000003ffULL
-#define OP_IMMED_B_SRC	0x000000ffc00ULL
-#define OP_IMMED_IMM	0x0000ff00000ULL
-#define OP_IMMED_WIDTH	0x00060000000ULL
-#define OP_IMMED_INV	0x00080000000ULL
-#define OP_IMMED_SHIFT	0x00600000000ULL
-#define OP_IMMED_BASE	0x0f000000000ULL
-#define OP_IMMED_WR_AB	0x20000000000ULL
+#define OP_BBYTE_BASE		0x0c800000000ULL
+#define OP_BB_A_SRC		0x000000000ffULL
+#define OP_BB_BYTE		0x00000000300ULL
+#define OP_BB_B_SRC		0x0000003fc00ULL
+#define OP_BB_I8		0x00000040000ULL
+#define OP_BB_EQ		0x00000080000ULL
+#define OP_BB_DEFBR		0x00000300000ULL
+#define OP_BB_ADDR_LO		0x007ffc00000ULL
+#define OP_BB_ADDR_HI		0x10000000000ULL
+#define OP_BB_SRC_LMEXTN	0x40000000000ULL
+
+#define OP_BALU_BASE		0x0e800000000ULL
+#define OP_BA_A_SRC		0x000000003ffULL
+#define OP_BA_B_SRC		0x000000ffc00ULL
+#define OP_BA_DEFBR		0x00000300000ULL
+#define OP_BA_ADDR_HI		0x0007fc00000ULL
+
+#define OP_IMMED_A_SRC		0x000000003ffULL
+#define OP_IMMED_B_SRC		0x000000ffc00ULL
+#define OP_IMMED_IMM		0x0000ff00000ULL
+#define OP_IMMED_WIDTH		0x00060000000ULL
+#define OP_IMMED_INV		0x00080000000ULL
+#define OP_IMMED_SHIFT		0x00600000000ULL
+#define OP_IMMED_BASE		0x0f000000000ULL
+#define OP_IMMED_WR_AB		0x20000000000ULL
+#define OP_IMMED_SRC_LMEXTN	0x40000000000ULL
+#define OP_IMMED_DST_LMEXTN	0x80000000000ULL
 
 enum immed_width {
 	IMMED_WIDTH_ALL = 0,
@@ -119,17 +132,19 @@ enum immed_shift {
 	IMMED_SHIFT_2B = 2,
 };
 
-#define OP_SHF_BASE	0x08000000000ULL
-#define OP_SHF_A_SRC	0x000000000ffULL
-#define OP_SHF_SC	0x00000000300ULL
-#define OP_SHF_B_SRC	0x0000003fc00ULL
-#define OP_SHF_I8	0x00000040000ULL
-#define OP_SHF_SW	0x00000080000ULL
-#define OP_SHF_DST	0x0000ff00000ULL
-#define OP_SHF_SHIFT	0x001f0000000ULL
-#define OP_SHF_OP	0x00e00000000ULL
-#define OP_SHF_DST_AB	0x01000000000ULL
-#define OP_SHF_WR_AB	0x20000000000ULL
+#define OP_SHF_BASE		0x08000000000ULL
+#define OP_SHF_A_SRC		0x000000000ffULL
+#define OP_SHF_SC		0x00000000300ULL
+#define OP_SHF_B_SRC		0x0000003fc00ULL
+#define OP_SHF_I8		0x00000040000ULL
+#define OP_SHF_SW		0x00000080000ULL
+#define OP_SHF_DST		0x0000ff00000ULL
+#define OP_SHF_SHIFT		0x001f0000000ULL
+#define OP_SHF_OP		0x00e00000000ULL
+#define OP_SHF_DST_AB		0x01000000000ULL
+#define OP_SHF_WR_AB		0x20000000000ULL
+#define OP_SHF_SRC_LMEXTN	0x40000000000ULL
+#define OP_SHF_DST_LMEXTN	0x80000000000ULL
 
 enum shf_op {
 	SHF_OP_NONE = 0,
@@ -139,24 +154,27 @@ enum shf_op {
 
 enum shf_sc {
 	SHF_SC_R_ROT = 0,
+	SHF_SC_NONE = SHF_SC_R_ROT,
 	SHF_SC_R_SHF = 1,
 	SHF_SC_L_SHF = 2,
 	SHF_SC_R_DSHF = 3,
 };
 
-#define OP_ALU_A_SRC	0x000000003ffULL
-#define OP_ALU_B_SRC	0x000000ffc00ULL
-#define OP_ALU_DST	0x0003ff00000ULL
-#define OP_ALU_SW	0x00040000000ULL
-#define OP_ALU_OP	0x00f80000000ULL
-#define OP_ALU_DST_AB	0x01000000000ULL
-#define OP_ALU_BASE	0x0a000000000ULL
-#define OP_ALU_WR_AB	0x20000000000ULL
+#define OP_ALU_A_SRC		0x000000003ffULL
+#define OP_ALU_B_SRC		0x000000ffc00ULL
+#define OP_ALU_DST		0x0003ff00000ULL
+#define OP_ALU_SW		0x00040000000ULL
+#define OP_ALU_OP		0x00f80000000ULL
+#define OP_ALU_DST_AB		0x01000000000ULL
+#define OP_ALU_BASE		0x0a000000000ULL
+#define OP_ALU_WR_AB		0x20000000000ULL
+#define OP_ALU_SRC_LMEXTN	0x40000000000ULL
+#define OP_ALU_DST_LMEXTN	0x80000000000ULL
 
 enum alu_op {
 	ALU_OP_NONE	= 0x00,
 	ALU_OP_ADD	= 0x01,
-	ALU_OP_NEG	= 0x04,
+	ALU_OP_NOT	= 0x04,
 	ALU_OP_AND	= 0x08,
 	ALU_OP_SUB_C	= 0x0d,
 	ALU_OP_ADD_C	= 0x11,
@@ -170,26 +188,28 @@ enum alu_dst_ab {
 	ALU_DST_B = 1,
 };
 
-#define OP_LDF_BASE	0x0c000000000ULL
-#define OP_LDF_A_SRC	0x000000000ffULL
-#define OP_LDF_SC	0x00000000300ULL
-#define OP_LDF_B_SRC	0x0000003fc00ULL
-#define OP_LDF_I8	0x00000040000ULL
-#define OP_LDF_SW	0x00000080000ULL
-#define OP_LDF_ZF	0x00000100000ULL
-#define OP_LDF_BMASK	0x0000f000000ULL
-#define OP_LDF_SHF	0x001f0000000ULL
-#define OP_LDF_WR_AB	0x20000000000ULL
-
-#define OP_CMD_A_SRC	 0x000000000ffULL
-#define OP_CMD_CTX	 0x00000000300ULL
-#define OP_CMD_B_SRC	 0x0000003fc00ULL
-#define OP_CMD_TOKEN	 0x000000c0000ULL
-#define OP_CMD_XFER	 0x00001f00000ULL
-#define OP_CMD_CNT	 0x0000e000000ULL
-#define OP_CMD_SIG	 0x000f0000000ULL
-#define OP_CMD_TGT_CMD	 0x07f00000000ULL
-#define OP_CMD_MODE	0x1c0000000000ULL
+#define OP_LDF_BASE		0x0c000000000ULL
+#define OP_LDF_A_SRC		0x000000000ffULL
+#define OP_LDF_SC		0x00000000300ULL
+#define OP_LDF_B_SRC		0x0000003fc00ULL
+#define OP_LDF_I8		0x00000040000ULL
+#define OP_LDF_SW		0x00000080000ULL
+#define OP_LDF_ZF		0x00000100000ULL
+#define OP_LDF_BMASK		0x0000f000000ULL
+#define OP_LDF_SHF		0x001f0000000ULL
+#define OP_LDF_WR_AB		0x20000000000ULL
+#define OP_LDF_SRC_LMEXTN	0x40000000000ULL
+#define OP_LDF_DST_LMEXTN	0x80000000000ULL
+
+#define OP_CMD_A_SRC		0x000000000ffULL
+#define OP_CMD_CTX		0x00000000300ULL
+#define OP_CMD_B_SRC		0x0000003fc00ULL
+#define OP_CMD_TOKEN		0x000000c0000ULL
+#define OP_CMD_XFER		0x00001f00000ULL
+#define OP_CMD_CNT		0x0000e000000ULL
+#define OP_CMD_SIG		0x000f0000000ULL
+#define OP_CMD_TGT_CMD		0x07f00000000ULL
+#define OP_CMD_MODE	       0x1c0000000000ULL
 
 struct cmd_tgt_act {
 	u8 token;
@@ -198,12 +218,17 @@ struct cmd_tgt_act {
 
 enum cmd_tgt_map {
 	CMD_TGT_READ8,
-	CMD_TGT_WRITE8,
+	CMD_TGT_WRITE8_SWAP,
+	CMD_TGT_READ32,
+	CMD_TGT_READ32_LE,
+	CMD_TGT_READ32_SWAP,
 	CMD_TGT_READ_LE,
 	CMD_TGT_READ_SWAP_LE,
 	__CMD_TGT_MAP_SIZE,
 };
 
+extern const struct cmd_tgt_act cmd_tgt_act[__CMD_TGT_MAP_SIZE];
+
 enum cmd_mode {
 	CMD_MODE_40b_AB	= 0,
 	CMD_MODE_40b_BA	= 1,
@@ -215,11 +240,13 @@ enum cmd_ctx_swap {
 	CMD_CTX_NO_SWAP = 3,
 };
 
-#define OP_LCSR_BASE	0x0fc00000000ULL
-#define OP_LCSR_A_SRC	0x000000003ffULL
-#define OP_LCSR_B_SRC	0x000000ffc00ULL
-#define OP_LCSR_WRITE	0x00000200000ULL
-#define OP_LCSR_ADDR	0x001ffc00000ULL
+#define OP_LCSR_BASE		0x0fc00000000ULL
+#define OP_LCSR_A_SRC		0x000000003ffULL
+#define OP_LCSR_B_SRC		0x000000ffc00ULL
+#define OP_LCSR_WRITE		0x00000200000ULL
+#define OP_LCSR_ADDR		0x001ffc00000ULL
+#define OP_LCSR_SRC_LMEXTN	0x40000000000ULL
+#define OP_LCSR_DST_LMEXTN	0x80000000000ULL
 
 enum lcsr_wr_src {
 	LCSR_WR_AREG,
@@ -227,7 +254,127 @@ enum lcsr_wr_src {
 	LCSR_WR_IMM,
 };
 
-#define OP_CARB_BASE	0x0e000000000ULL
-#define OP_CARB_OR	0x00000010000ULL
+#define OP_CARB_BASE		0x0e000000000ULL
+#define OP_CARB_OR		0x00000010000ULL
+
+#define NFP_CSR_ACT_LM_ADDR0	0x64
+#define NFP_CSR_ACT_LM_ADDR1	0x6c
+#define NFP_CSR_ACT_LM_ADDR2	0x94
+#define NFP_CSR_ACT_LM_ADDR3	0x9c
+
+/* Software register representation, independent of operand type */
+#define NN_REG_TYPE	GENMASK(31, 24)
+#define NN_REG_LM_IDX	GENMASK(23, 22)
+#define NN_REG_LM_IDX_HI	BIT(23)
+#define NN_REG_LM_IDX_LO	BIT(22)
+#define NN_REG_LM_MOD	GENMASK(21, 20)
+#define NN_REG_VAL	GENMASK(7, 0)
+
+enum nfp_bpf_reg_type {
+	NN_REG_GPR_A =	BIT(0),
+	NN_REG_GPR_B =	BIT(1),
+	NN_REG_GPR_BOTH = NN_REG_GPR_A | NN_REG_GPR_B,
+	NN_REG_NNR =	BIT(2),
+	NN_REG_XFER =	BIT(3),
+	NN_REG_IMM =	BIT(4),
+	NN_REG_NONE =	BIT(5),
+	NN_REG_LMEM =	BIT(6),
+};
+
+enum nfp_bpf_lm_mode {
+	NN_LM_MOD_NONE = 0,
+	NN_LM_MOD_INC,
+	NN_LM_MOD_DEC,
+};
+
+#define reg_both(x)	__enc_swreg((x), NN_REG_GPR_BOTH)
+#define reg_a(x)	__enc_swreg((x), NN_REG_GPR_A)
+#define reg_b(x)	__enc_swreg((x), NN_REG_GPR_B)
+#define reg_nnr(x)	__enc_swreg((x), NN_REG_NNR)
+#define reg_xfer(x)	__enc_swreg((x), NN_REG_XFER)
+#define reg_imm(x)	__enc_swreg((x), NN_REG_IMM)
+#define reg_none()	__enc_swreg(0, NN_REG_NONE)
+#define reg_lm(x, off)	__enc_swreg_lm((x), NN_LM_MOD_NONE, (off))
+#define reg_lm_inc(x)	__enc_swreg_lm((x), NN_LM_MOD_INC, 0)
+#define reg_lm_dec(x)	__enc_swreg_lm((x), NN_LM_MOD_DEC, 0)
+#define __reg_lm(x, mod, off)	__enc_swreg_lm((x), (mod), (off))
+
+typedef __u32 __bitwise swreg;
+
+static inline swreg __enc_swreg(u16 id, u8 type)
+{
+	return (__force swreg)(id | FIELD_PREP(NN_REG_TYPE, type));
+}
+
+static inline swreg __enc_swreg_lm(u8 id, enum nfp_bpf_lm_mode mode, u8 off)
+{
+	WARN_ON(id > 3 || (off && mode != NN_LM_MOD_NONE));
+
+	return (__force swreg)(FIELD_PREP(NN_REG_TYPE, NN_REG_LMEM) |
+			       FIELD_PREP(NN_REG_LM_IDX, id) |
+			       FIELD_PREP(NN_REG_LM_MOD, mode) |
+			       off);
+}
+
+static inline u32 swreg_raw(swreg reg)
+{
+	return (__force u32)reg;
+}
+
+static inline enum nfp_bpf_reg_type swreg_type(swreg reg)
+{
+	return FIELD_GET(NN_REG_TYPE, swreg_raw(reg));
+}
+
+static inline u16 swreg_value(swreg reg)
+{
+	return FIELD_GET(NN_REG_VAL, swreg_raw(reg));
+}
+
+static inline bool swreg_lm_idx(swreg reg)
+{
+	return FIELD_GET(NN_REG_LM_IDX_LO, swreg_raw(reg));
+}
+
+static inline bool swreg_lmextn(swreg reg)
+{
+	return FIELD_GET(NN_REG_LM_IDX_HI, swreg_raw(reg));
+}
+
+static inline enum nfp_bpf_lm_mode swreg_lm_mode(swreg reg)
+{
+	return FIELD_GET(NN_REG_LM_MOD, swreg_raw(reg));
+}
+
+struct nfp_insn_ur_regs {
+	enum alu_dst_ab dst_ab;
+	u16 dst;
+	u16 areg, breg;
+	bool swap;
+	bool wr_both;
+	bool dst_lmextn;
+	bool src_lmextn;
+};
+
+struct nfp_insn_re_regs {
+	enum alu_dst_ab dst_ab;
+	u8 dst;
+	u8 areg, breg;
+	bool swap;
+	bool wr_both;
+	bool i8;
+	bool dst_lmextn;
+	bool src_lmextn;
+};
+
+int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg,
+			  struct nfp_insn_ur_regs *reg);
+int swreg_to_restricted(swreg dst, swreg lreg, swreg rreg,
+			struct nfp_insn_re_regs *reg, bool has_imm8);
+
+#define NFP_USTORE_PREFETCH_WINDOW	8
+
+int nfp_ustore_check_valid_no_ecc(u64 insn);
+u64 nfp_ustore_calc_ecc_insn(u64 insn);
 
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index d51d8237b984..3d411f0d15b6 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -394,6 +394,7 @@ struct nfp_net_rx_ring {
  * @tx_lso:	    Counter of LSO packets sent
  * @tx_errors:	    How many TX errors were encountered
  * @tx_busy:        How often was TX busy (no space)?
+ * @rx_replace_buf_alloc_fail:	Counter of RX buffer allocation failures
  * @irq_vector:     Interrupt vector number (use for talking to the OS)
  * @handler:        Interrupt handler for this ring vector
  * @name:           Name of the interrupt vector
@@ -437,6 +438,8 @@ struct nfp_net_r_vector {
 	u64 hw_csum_tx_inner;
 	u64 tx_gather;
 	u64 tx_lso;
+
+	u64 rx_replace_buf_alloc_fail;
 	u64 tx_errors;
 	u64 tx_busy;
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index e118b5f23996..185a3dd35a3f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -177,9 +177,9 @@ static int nfp_net_reconfig_wait(struct nfp_net *nn, unsigned long deadline)
 	return timed_out ? -EIO : 0;
 }
 
-static void nfp_net_reconfig_timer(unsigned long data)
+static void nfp_net_reconfig_timer(struct timer_list *t)
 {
-	struct nfp_net *nn = (void *)data;
+	struct nfp_net *nn = from_timer(nn, t, reconfig_timer);
 
 	spin_lock_bh(&nn->reconfig_lock);
 
@@ -1209,15 +1209,15 @@ static void *nfp_net_napi_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr)
 
 	if (!dp->xdp_prog) {
 		frag = napi_alloc_frag(dp->fl_bufsz);
+		if (unlikely(!frag))
+			return NULL;
 	} else {
 		struct page *page;
 
-		page = alloc_page(GFP_ATOMIC | __GFP_COLD);
-		frag = page ? page_address(page) : NULL;
-	}
-	if (!frag) {
-		nn_dp_warn(dp, "Failed to alloc receive page frag\n");
-		return NULL;
+		page = dev_alloc_page();
+		if (unlikely(!page))
+			return NULL;
+		frag = page_address(page);
 	}
 
 	*dma_addr = nfp_net_dma_map_rx(dp, frag);
@@ -1514,6 +1514,11 @@ nfp_net_rx_drop(const struct nfp_net_dp *dp, struct nfp_net_r_vector *r_vec,
 {
 	u64_stats_update_begin(&r_vec->rx_sync);
 	r_vec->rx_drops++;
+	/* If we have both skb and rxbuf the replacement buffer allocation
+	 * must have failed, count this as an alloc failure.
+	 */
+	if (skb && rxbuf)
+		r_vec->rx_replace_buf_alloc_fail++;
 	u64_stats_update_end(&r_vec->rx_sync);
 
 	/* skb is build based on the frag, free_skb() would free the frag
@@ -1582,26 +1587,6 @@ nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring,
 	return true;
 }
 
-static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start,
-			   unsigned int *off, unsigned int *len)
-{
-	struct xdp_buff xdp;
-	void *orig_data;
-	int ret;
-
-	xdp.data_hard_start = hard_start;
-	xdp.data = data + *off;
-	xdp.data_end = data + *off + *len;
-
-	orig_data = xdp.data;
-	ret = bpf_prog_run_xdp(prog, &xdp);
-
-	*len -= xdp.data - orig_data;
-	*off += xdp.data - orig_data;
-
-	return ret;
-}
-
 /**
  * nfp_net_rx() - receive up to @budget packets on @rx_ring
  * @rx_ring:   RX ring to receive from
@@ -1637,6 +1622,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 		struct nfp_meta_parsed meta;
 		struct net_device *netdev;
 		dma_addr_t new_dma_addr;
+		u32 meta_len_xdp = 0;
 		void *new_frag;
 
 		idx = D_IDX(rx_ring, rx_ring->rd_p);
@@ -1715,16 +1701,24 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 
 		if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF &&
 				  dp->bpf_offload_xdp) && !meta.portid) {
+			void *orig_data = rxbuf->frag + pkt_off;
 			unsigned int dma_off;
-			void *hard_start;
+			struct xdp_buff xdp;
 			int act;
 
-			hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM;
+			xdp.data_hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM;
+			xdp.data = orig_data;
+			xdp.data_meta = orig_data;
+			xdp.data_end = orig_data + pkt_len;
+
+			act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+			pkt_len -= xdp.data - orig_data;
+			pkt_off += xdp.data - orig_data;
 
-			act = nfp_net_run_xdp(xdp_prog, rxbuf->frag, hard_start,
-					      &pkt_off, &pkt_len);
 			switch (act) {
 			case XDP_PASS:
+				meta_len_xdp = xdp.data - xdp.data_meta;
 				break;
 			case XDP_TX:
 				dma_off = pkt_off - NFP_NET_RX_BUF_HEADROOM;
@@ -1792,6 +1786,8 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 		if (rxd->rxd.flags & PCIE_DESC_RX_VLAN)
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
 					       le16_to_cpu(rxd->rxd.vlan));
+		if (meta_len_xdp)
+			skb_metadata_set(skb, meta_len_xdp);
 
 		napi_gro_receive(&rx_ring->r_vec->napi, skb);
 	}
@@ -3546,8 +3542,7 @@ struct nfp_net *nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev,
 	spin_lock_init(&nn->reconfig_lock);
 	spin_lock_init(&nn->link_status_lock);
 
-	setup_timer(&nn->reconfig_timer,
-		    nfp_net_reconfig_timer, (unsigned long)nn);
+	timer_setup(&nn->reconfig_timer, nfp_net_reconfig_timer, 0);
 
 	return nn;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index b0a452ba9039..782d452e0fc2 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -255,7 +255,7 @@
  * @NFP_NET_CFG_BPF_ADDR:	DMA address of the buffer with JITed BPF code
  */
 #define NFP_NET_CFG_BPF_ABI		0x0080
-#define   NFP_NET_BPF_ABI		1
+#define   NFP_NET_BPF_ABI		2
 #define NFP_NET_CFG_BPF_CAP		0x0081
 #define   NFP_NET_BPF_CAP_RELO		(1 << 0) /* seamless reload */
 #define NFP_NET_CFG_BPF_MAX_LEN		0x0082
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index dc016dfec64d..c67b90c8d8b7 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -181,7 +181,8 @@ static const struct nfp_et_stat nfp_mac_et_stats[] = {
 
 #define NN_ET_GLOBAL_STATS_LEN ARRAY_SIZE(nfp_net_et_stats)
 #define NN_ET_SWITCH_STATS_LEN 9
-#define NN_ET_RVEC_GATHER_STATS 7
+#define NN_RVEC_GATHER_STATS	8
+#define NN_RVEC_PER_Q_STATS	3
 
 static void nfp_net_get_nspinfo(struct nfp_app *app, char *version)
 {
@@ -427,7 +428,7 @@ static unsigned int nfp_vnic_get_sw_stats_count(struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 
-	return NN_ET_RVEC_GATHER_STATS + nn->dp.num_r_vecs * 3;
+	return NN_RVEC_GATHER_STATS + nn->dp.num_r_vecs * NN_RVEC_PER_Q_STATS;
 }
 
 static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data)
@@ -444,6 +445,7 @@ static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data)
 	data = nfp_pr_et(data, "hw_rx_csum_ok");
 	data = nfp_pr_et(data, "hw_rx_csum_inner_ok");
 	data = nfp_pr_et(data, "hw_rx_csum_err");
+	data = nfp_pr_et(data, "rx_replace_buf_alloc_fail");
 	data = nfp_pr_et(data, "hw_tx_csum");
 	data = nfp_pr_et(data, "hw_tx_inner_csum");
 	data = nfp_pr_et(data, "tx_gather");
@@ -454,9 +456,9 @@ static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data)
 
 static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 {
-	u64 gathered_stats[NN_ET_RVEC_GATHER_STATS] = {};
+	u64 gathered_stats[NN_RVEC_GATHER_STATS] = {};
 	struct nfp_net *nn = netdev_priv(netdev);
-	u64 tmp[NN_ET_RVEC_GATHER_STATS];
+	u64 tmp[NN_RVEC_GATHER_STATS];
 	unsigned int i, j;
 
 	for (i = 0; i < nn->dp.num_r_vecs; i++) {
@@ -468,25 +470,26 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 			tmp[0] = nn->r_vecs[i].hw_csum_rx_ok;
 			tmp[1] = nn->r_vecs[i].hw_csum_rx_inner_ok;
 			tmp[2] = nn->r_vecs[i].hw_csum_rx_error;
+			tmp[3] = nn->r_vecs[i].rx_replace_buf_alloc_fail;
 		} while (u64_stats_fetch_retry(&nn->r_vecs[i].rx_sync, start));
 
 		do {
 			start = u64_stats_fetch_begin(&nn->r_vecs[i].tx_sync);
 			data[1] = nn->r_vecs[i].tx_pkts;
 			data[2] = nn->r_vecs[i].tx_busy;
-			tmp[3] = nn->r_vecs[i].hw_csum_tx;
-			tmp[4] = nn->r_vecs[i].hw_csum_tx_inner;
-			tmp[5] = nn->r_vecs[i].tx_gather;
-			tmp[6] = nn->r_vecs[i].tx_lso;
+			tmp[4] = nn->r_vecs[i].hw_csum_tx;
+			tmp[5] = nn->r_vecs[i].hw_csum_tx_inner;
+			tmp[6] = nn->r_vecs[i].tx_gather;
+			tmp[7] = nn->r_vecs[i].tx_lso;
 		} while (u64_stats_fetch_retry(&nn->r_vecs[i].tx_sync, start));
 
-		data += 3;
+		data += NN_RVEC_PER_Q_STATS;
 
-		for (j = 0; j < NN_ET_RVEC_GATHER_STATS; j++)
+		for (j = 0; j < NN_RVEC_GATHER_STATS; j++)
 			gathered_stats[j] += tmp[j];
 	}
 
-	for (j = 0; j < NN_ET_RVEC_GATHER_STATS; j++)
+	for (j = 0; j < NN_RVEC_GATHER_STATS; j++)
 		*data++ = gathered_stats[j];
 
 	return data;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.c b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.c
index e6d2e06b050c..8b1b962cf1d1 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.c
@@ -112,7 +112,13 @@ int nfp_app_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 	writew(get_unaligned_be16(mac + 4),
 	       app->pf->vfcfg_tbl2 + vf_offset + NFP_NET_VF_CFG_MAC_LO);
 
-	return nfp_net_sriov_update(app, vf, NFP_NET_VF_CFG_MB_UPD_MAC, "MAC");
+	err = nfp_net_sriov_update(app, vf, NFP_NET_VF_CFG_MB_UPD_MAC, "MAC");
+	if (!err)
+		nfp_info(app->pf->cpp,
+			 "MAC %pM set on VF %d, reload the VF driver to make this change effective.\n",
+			 mac, vf);
+
+	return err;
 }
 
 int nfp_app_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos,
diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c
index 4a67c55aa9f1..052b3d2c07a1 100644
--- a/drivers/net/ethernet/nuvoton/w90p910_ether.c
+++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c
@@ -253,10 +253,10 @@ static void update_linkspeed(struct net_device *dev)
 	netif_carrier_on(dev);
 }
 
-static void w90p910_check_link(unsigned long dev_id)
+static void w90p910_check_link(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) dev_id;
-	struct w90p910_ether *ether = netdev_priv(dev);
+	struct w90p910_ether *ether = from_timer(ether, t, check_timer);
+	struct net_device *dev = ether->mii.dev;
 
 	update_linkspeed(dev);
 	mod_timer(&ether->check_timer, jiffies + msecs_to_jiffies(1000));
@@ -957,8 +957,7 @@ static int w90p910_ether_setup(struct net_device *dev)
 	ether->mii.mdio_read = w90p910_mdio_read;
 	ether->mii.mdio_write = w90p910_mdio_write;
 
-	setup_timer(&ether->check_timer, w90p910_check_link,
-						(unsigned long)dev);
+	timer_setup(&ether->check_timer, w90p910_check_link, 0);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 994a83a1f0a5..31a943860f32 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -1024,12 +1024,18 @@ static void free_rings(struct net_device *dev)
 
 	if (!nv_optimized(np)) {
 		if (np->rx_ring.orig)
-			pci_free_consistent(np->pci_dev, sizeof(struct ring_desc) * (np->rx_ring_size + np->tx_ring_size),
-					    np->rx_ring.orig, np->ring_addr);
+			dma_free_coherent(&np->pci_dev->dev,
+					  sizeof(struct ring_desc) *
+					  (np->rx_ring_size +
+					  np->tx_ring_size),
+					  np->rx_ring.orig, np->ring_addr);
 	} else {
 		if (np->rx_ring.ex)
-			pci_free_consistent(np->pci_dev, sizeof(struct ring_desc_ex) * (np->rx_ring_size + np->tx_ring_size),
-					    np->rx_ring.ex, np->ring_addr);
+			dma_free_coherent(&np->pci_dev->dev,
+					  sizeof(struct ring_desc_ex) *
+					  (np->rx_ring_size +
+					  np->tx_ring_size),
+					  np->rx_ring.ex, np->ring_addr);
 	}
 	kfree(np->rx_skb);
 	kfree(np->tx_skb);
@@ -1813,12 +1819,12 @@ static int nv_alloc_rx(struct net_device *dev)
 		struct sk_buff *skb = netdev_alloc_skb(dev, np->rx_buf_sz + NV_RX_ALLOC_PAD);
 		if (skb) {
 			np->put_rx_ctx->skb = skb;
-			np->put_rx_ctx->dma = pci_map_single(np->pci_dev,
+			np->put_rx_ctx->dma = dma_map_single(&np->pci_dev->dev,
 							     skb->data,
 							     skb_tailroom(skb),
-							     PCI_DMA_FROMDEVICE);
-			if (pci_dma_mapping_error(np->pci_dev,
-						  np->put_rx_ctx->dma)) {
+							     DMA_FROM_DEVICE);
+			if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+						       np->put_rx_ctx->dma))) {
 				kfree_skb(skb);
 				goto packet_dropped;
 			}
@@ -1854,12 +1860,12 @@ static int nv_alloc_rx_optimized(struct net_device *dev)
 		struct sk_buff *skb = netdev_alloc_skb(dev, np->rx_buf_sz + NV_RX_ALLOC_PAD);
 		if (skb) {
 			np->put_rx_ctx->skb = skb;
-			np->put_rx_ctx->dma = pci_map_single(np->pci_dev,
+			np->put_rx_ctx->dma = dma_map_single(&np->pci_dev->dev,
 							     skb->data,
 							     skb_tailroom(skb),
-							     PCI_DMA_FROMDEVICE);
-			if (pci_dma_mapping_error(np->pci_dev,
-						  np->put_rx_ctx->dma)) {
+							     DMA_FROM_DEVICE);
+			if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+						       np->put_rx_ctx->dma))) {
 				kfree_skb(skb);
 				goto packet_dropped;
 			}
@@ -1884,10 +1890,9 @@ packet_dropped:
 }
 
 /* If rx bufs are exhausted called after 50ms to attempt to refresh */
-static void nv_do_rx_refill(unsigned long data)
+static void nv_do_rx_refill(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) data;
-	struct fe_priv *np = netdev_priv(dev);
+	struct fe_priv *np = from_timer(np, t, oom_kick);
 
 	/* Just reschedule NAPI rx processing */
 	napi_schedule(&np->napi);
@@ -1977,9 +1982,9 @@ static void nv_unmap_txskb(struct fe_priv *np, struct nv_skb_map *tx_skb)
 {
 	if (tx_skb->dma) {
 		if (tx_skb->dma_single)
-			pci_unmap_single(np->pci_dev, tx_skb->dma,
+			dma_unmap_single(&np->pci_dev->dev, tx_skb->dma,
 					 tx_skb->dma_len,
-					 PCI_DMA_TODEVICE);
+					 DMA_TO_DEVICE);
 		else
 			pci_unmap_page(np->pci_dev, tx_skb->dma,
 				       tx_skb->dma_len,
@@ -2047,10 +2052,10 @@ static void nv_drain_rx(struct net_device *dev)
 		}
 		wmb();
 		if (np->rx_skb[i].skb) {
-			pci_unmap_single(np->pci_dev, np->rx_skb[i].dma,
+			dma_unmap_single(&np->pci_dev->dev, np->rx_skb[i].dma,
 					 (skb_end_pointer(np->rx_skb[i].skb) -
-					  np->rx_skb[i].skb->data),
-					 PCI_DMA_FROMDEVICE);
+					 np->rx_skb[i].skb->data),
+					 DMA_FROM_DEVICE);
 			dev_kfree_skb(np->rx_skb[i].skb);
 			np->rx_skb[i].skb = NULL;
 		}
@@ -2224,10 +2229,11 @@ static netdev_tx_t nv_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		prev_tx = put_tx;
 		prev_tx_ctx = np->put_tx_ctx;
 		bcnt = (size > NV_TX2_TSO_MAX_SIZE) ? NV_TX2_TSO_MAX_SIZE : size;
-		np->put_tx_ctx->dma = pci_map_single(np->pci_dev, skb->data + offset, bcnt,
-						PCI_DMA_TODEVICE);
-		if (pci_dma_mapping_error(np->pci_dev,
-					  np->put_tx_ctx->dma)) {
+		np->put_tx_ctx->dma = dma_map_single(&np->pci_dev->dev,
+						     skb->data + offset, bcnt,
+						     DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+					       np->put_tx_ctx->dma))) {
 			/* on DMA mapping error - drop the packet */
 			dev_kfree_skb_any(skb);
 			u64_stats_update_begin(&np->swstats_tx_syncp);
@@ -2267,7 +2273,8 @@ static netdev_tx_t nv_start_xmit(struct sk_buff *skb, struct net_device *dev)
 							frag, offset,
 							bcnt,
 							DMA_TO_DEVICE);
-			if (dma_mapping_error(&np->pci_dev->dev, np->put_tx_ctx->dma)) {
+			if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+						       np->put_tx_ctx->dma))) {
 
 				/* Unwind the mapped fragments */
 				do {
@@ -2373,10 +2380,11 @@ static netdev_tx_t nv_start_xmit_optimized(struct sk_buff *skb,
 		prev_tx = put_tx;
 		prev_tx_ctx = np->put_tx_ctx;
 		bcnt = (size > NV_TX2_TSO_MAX_SIZE) ? NV_TX2_TSO_MAX_SIZE : size;
-		np->put_tx_ctx->dma = pci_map_single(np->pci_dev, skb->data + offset, bcnt,
-						PCI_DMA_TODEVICE);
-		if (pci_dma_mapping_error(np->pci_dev,
-					  np->put_tx_ctx->dma)) {
+		np->put_tx_ctx->dma = dma_map_single(&np->pci_dev->dev,
+						     skb->data + offset, bcnt,
+						     DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+					       np->put_tx_ctx->dma))) {
 			/* on DMA mapping error - drop the packet */
 			dev_kfree_skb_any(skb);
 			u64_stats_update_begin(&np->swstats_tx_syncp);
@@ -2417,7 +2425,8 @@ static netdev_tx_t nv_start_xmit_optimized(struct sk_buff *skb,
 							bcnt,
 							DMA_TO_DEVICE);
 
-			if (dma_mapping_error(&np->pci_dev->dev, np->put_tx_ctx->dma)) {
+			if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+						       np->put_tx_ctx->dma))) {
 
 				/* Unwind the mapped fragments */
 				do {
@@ -2810,9 +2819,9 @@ static int nv_rx_process(struct net_device *dev, int limit)
 		 * TODO: check if a prefetch of the first cacheline improves
 		 * the performance.
 		 */
-		pci_unmap_single(np->pci_dev, np->get_rx_ctx->dma,
-				np->get_rx_ctx->dma_len,
-				PCI_DMA_FROMDEVICE);
+		dma_unmap_single(&np->pci_dev->dev, np->get_rx_ctx->dma,
+				 np->get_rx_ctx->dma_len,
+				 DMA_FROM_DEVICE);
 		skb = np->get_rx_ctx->skb;
 		np->get_rx_ctx->skb = NULL;
 
@@ -2916,9 +2925,9 @@ static int nv_rx_process_optimized(struct net_device *dev, int limit)
 		 * TODO: check if a prefetch of the first cacheline improves
 		 * the performance.
 		 */
-		pci_unmap_single(np->pci_dev, np->get_rx_ctx->dma,
-				np->get_rx_ctx->dma_len,
-				PCI_DMA_FROMDEVICE);
+		dma_unmap_single(&np->pci_dev->dev, np->get_rx_ctx->dma,
+				 np->get_rx_ctx->dma_len,
+				 DMA_FROM_DEVICE);
 		skb = np->get_rx_ctx->skb;
 		np->get_rx_ctx->skb = NULL;
 
@@ -4061,10 +4070,10 @@ static void nv_free_irq(struct net_device *dev)
 	}
 }
 
-static void nv_do_nic_poll(unsigned long data)
+static void nv_do_nic_poll(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) data;
-	struct fe_priv *np = netdev_priv(dev);
+	struct fe_priv *np = from_timer(np, t, nic_poll);
+	struct net_device *dev = np->dev;
 	u8 __iomem *base = get_hwbase(dev);
 	u32 mask = 0;
 	unsigned long flags;
@@ -4172,16 +4181,18 @@ static void nv_do_nic_poll(unsigned long data)
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void nv_poll_controller(struct net_device *dev)
 {
-	nv_do_nic_poll((unsigned long) dev);
+	struct fe_priv *np = netdev_priv(dev);
+
+	nv_do_nic_poll(&np->nic_poll);
 }
 #endif
 
-static void nv_do_stats_poll(unsigned long data)
+static void nv_do_stats_poll(struct timer_list *t)
 	__acquires(&netdev_priv(dev)->hwstats_lock)
 	__releases(&netdev_priv(dev)->hwstats_lock)
 {
-	struct net_device *dev = (struct net_device *) data;
-	struct fe_priv *np = netdev_priv(dev);
+	struct fe_priv *np = from_timer(np, t, stats_poll);
+	struct net_device *dev = np->dev;
 
 	/* If lock is currently taken, the stats are being refreshed
 	 * and hence fresh enough */
@@ -4591,13 +4602,17 @@ static int nv_set_ringparam(struct net_device *dev, struct ethtool_ringparam* ri
 
 	/* allocate new rings */
 	if (!nv_optimized(np)) {
-		rxtx_ring = pci_alloc_consistent(np->pci_dev,
-					    sizeof(struct ring_desc) * (ring->rx_pending + ring->tx_pending),
-					    &ring_addr);
+		rxtx_ring = dma_alloc_coherent(&np->pci_dev->dev,
+					       sizeof(struct ring_desc) *
+					       (ring->rx_pending +
+					       ring->tx_pending),
+					       &ring_addr, GFP_ATOMIC);
 	} else {
-		rxtx_ring = pci_alloc_consistent(np->pci_dev,
-					    sizeof(struct ring_desc_ex) * (ring->rx_pending + ring->tx_pending),
-					    &ring_addr);
+		rxtx_ring = dma_alloc_coherent(&np->pci_dev->dev,
+					       sizeof(struct ring_desc_ex) *
+					       (ring->rx_pending +
+					       ring->tx_pending),
+					       &ring_addr, GFP_ATOMIC);
 	}
 	rx_skbuff = kmalloc(sizeof(struct nv_skb_map) * ring->rx_pending, GFP_KERNEL);
 	tx_skbuff = kmalloc(sizeof(struct nv_skb_map) * ring->tx_pending, GFP_KERNEL);
@@ -4605,12 +4620,18 @@ static int nv_set_ringparam(struct net_device *dev, struct ethtool_ringparam* ri
 		/* fall back to old rings */
 		if (!nv_optimized(np)) {
 			if (rxtx_ring)
-				pci_free_consistent(np->pci_dev, sizeof(struct ring_desc) * (ring->rx_pending + ring->tx_pending),
-						    rxtx_ring, ring_addr);
+				dma_free_coherent(&np->pci_dev->dev,
+						  sizeof(struct ring_desc) *
+						  (ring->rx_pending +
+						  ring->tx_pending),
+						  rxtx_ring, ring_addr);
 		} else {
 			if (rxtx_ring)
-				pci_free_consistent(np->pci_dev, sizeof(struct ring_desc_ex) * (ring->rx_pending + ring->tx_pending),
-						    rxtx_ring, ring_addr);
+				dma_free_coherent(&np->pci_dev->dev,
+						  sizeof(struct ring_desc_ex) *
+						  (ring->rx_pending +
+						  ring->tx_pending),
+						  rxtx_ring, ring_addr);
 		}
 
 		kfree(rx_skbuff);
@@ -5070,11 +5091,11 @@ static int nv_loopback_test(struct net_device *dev)
 		ret = 0;
 		goto out;
 	}
-	test_dma_addr = pci_map_single(np->pci_dev, tx_skb->data,
+	test_dma_addr = dma_map_single(&np->pci_dev->dev, tx_skb->data,
 				       skb_tailroom(tx_skb),
-				       PCI_DMA_FROMDEVICE);
-	if (pci_dma_mapping_error(np->pci_dev,
-				  test_dma_addr)) {
+				       DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+				       test_dma_addr))) {
 		dev_kfree_skb_any(tx_skb);
 		goto out;
 	}
@@ -5129,9 +5150,9 @@ static int nv_loopback_test(struct net_device *dev)
 		}
 	}
 
-	pci_unmap_single(np->pci_dev, test_dma_addr,
-		       (skb_end_pointer(tx_skb) - tx_skb->data),
-		       PCI_DMA_TODEVICE);
+	dma_unmap_single(&np->pci_dev->dev, test_dma_addr,
+			 (skb_end_pointer(tx_skb) - tx_skb->data),
+			 DMA_TO_DEVICE);
 	dev_kfree_skb_any(tx_skb);
  out:
 	/* stop engines */
@@ -5627,10 +5648,9 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 	u64_stats_init(&np->swstats_rx_syncp);
 	u64_stats_init(&np->swstats_tx_syncp);
 
-	setup_timer(&np->oom_kick, nv_do_rx_refill, (unsigned long)dev);
-	setup_timer(&np->nic_poll, nv_do_nic_poll, (unsigned long)dev);
-	setup_deferrable_timer(&np->stats_poll, nv_do_stats_poll,
-			       (unsigned long)dev);
+	timer_setup(&np->oom_kick, nv_do_rx_refill, 0);
+	timer_setup(&np->nic_poll, nv_do_nic_poll, 0);
+	timer_setup(&np->stats_poll, nv_do_stats_poll, TIMER_DEFERRABLE);
 
 	err = pci_enable_device(pci_dev);
 	if (err)
@@ -5736,16 +5756,21 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 	np->tx_ring_size = TX_RING_DEFAULT;
 
 	if (!nv_optimized(np)) {
-		np->rx_ring.orig = pci_alloc_consistent(pci_dev,
-					sizeof(struct ring_desc) * (np->rx_ring_size + np->tx_ring_size),
-					&np->ring_addr);
+		np->rx_ring.orig = dma_alloc_coherent(&pci_dev->dev,
+						      sizeof(struct ring_desc) *
+						      (np->rx_ring_size +
+						      np->tx_ring_size),
+						      &np->ring_addr,
+						      GFP_ATOMIC);
 		if (!np->rx_ring.orig)
 			goto out_unmap;
 		np->tx_ring.orig = &np->rx_ring.orig[np->rx_ring_size];
 	} else {
-		np->rx_ring.ex = pci_alloc_consistent(pci_dev,
-					sizeof(struct ring_desc_ex) * (np->rx_ring_size + np->tx_ring_size),
-					&np->ring_addr);
+		np->rx_ring.ex = dma_alloc_coherent(&pci_dev->dev,
+						    sizeof(struct ring_desc_ex) *
+						    (np->rx_ring_size +
+						    np->tx_ring_size),
+						    &np->ring_addr, GFP_ATOMIC);
 		if (!np->rx_ring.ex)
 			goto out_unmap;
 		np->tx_ring.ex = &np->rx_ring.ex[np->rx_ring_size];
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 8d710a3b4db0..697e29dd4bd3 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
@@ -613,7 +613,6 @@ struct pch_gbe_privdata {
  * @rx_ring:		Pointer of Rx descriptor ring structure
  * @rx_buffer_len:	Receive buffer length
  * @tx_queue_len:	Transmit queue length
- * @have_msi:		PCI MSI mode flag
  * @pch_gbe_privdata:	PCI Device ID driver_data
  */
 
@@ -623,6 +622,7 @@ struct pch_gbe_adapter {
 	atomic_t irq_sem;
 	struct net_device *netdev;
 	struct pci_dev *pdev;
+	int irq;
 	struct net_device *polling_netdev;
 	struct napi_struct napi;
 	struct pch_gbe_hw hw;
@@ -637,7 +637,6 @@ struct pch_gbe_adapter {
 	struct pch_gbe_rx_ring *rx_ring;
 	unsigned long rx_buffer_len;
 	unsigned long tx_queue_len;
-	bool have_msi;
 	bool rx_stop_flag;
 	int hwts_tx_en;
 	int hwts_rx_en;
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 5ae9681a2da7..457ee80307ea 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
@@ -781,11 +781,8 @@ static void pch_gbe_free_irq(struct pch_gbe_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 
-	free_irq(adapter->pdev->irq, netdev);
-	if (adapter->have_msi) {
-		pci_disable_msi(adapter->pdev);
-		netdev_dbg(netdev, "call pci_disable_msi\n");
-	}
+	free_irq(adapter->irq, netdev);
+	pci_free_irq_vectors(adapter->pdev);
 }
 
 /**
@@ -799,7 +796,7 @@ static void pch_gbe_irq_disable(struct pch_gbe_adapter *adapter)
 	atomic_inc(&adapter->irq_sem);
 	iowrite32(0, &hw->reg->INT_EN);
 	ioread32(&hw->reg->INT_ST);
-	synchronize_irq(adapter->pdev->irq);
+	synchronize_irq(adapter->irq);
 
 	netdev_dbg(adapter->netdev, "INT_EN reg : 0x%08x\n",
 		   ioread32(&hw->reg->INT_EN));
@@ -1903,30 +1900,23 @@ static int pch_gbe_request_irq(struct pch_gbe_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	int err;
-	int flags;
 
-	flags = IRQF_SHARED;
-	adapter->have_msi = false;
-	err = pci_enable_msi(adapter->pdev);
-	netdev_dbg(netdev, "call pci_enable_msi\n");
-	if (err) {
-		netdev_dbg(netdev, "call pci_enable_msi - Error: %d\n", err);
-	} else {
-		flags = 0;
-		adapter->have_msi = true;
-	}
-	err = request_irq(adapter->pdev->irq, &pch_gbe_intr,
-			  flags, netdev->name, netdev);
+	err = pci_alloc_irq_vectors(adapter->pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+	if (err < 0)
+		return err;
+
+	adapter->irq = pci_irq_vector(adapter->pdev, 0);
+
+	err = request_irq(adapter->irq, &pch_gbe_intr, IRQF_SHARED,
+			  netdev->name, netdev);
 	if (err)
 		netdev_err(netdev, "Unable to allocate interrupt Error: %d\n",
 			   err);
-	netdev_dbg(netdev,
-		   "adapter->have_msi : %d  flags : 0x%04x  return : 0x%04x\n",
-		   adapter->have_msi, flags, err);
+	netdev_dbg(netdev, "have_msi : %d  return : 0x%04x\n",
+		   pci_dev_msi_enabled(adapter->pdev), err);
 	return err;
 }
 
-
 /**
  * pch_gbe_up - Up GbE network device
  * @adapter:  Board private structure
@@ -2399,9 +2389,9 @@ static void pch_gbe_netpoll(struct net_device *netdev)
 {
 	struct pch_gbe_adapter *adapter = netdev_priv(netdev);
 
-	disable_irq(adapter->pdev->irq);
-	pch_gbe_intr(adapter->pdev->irq, netdev);
-	enable_irq(adapter->pdev->irq);
+	disable_irq(adapter->irq);
+	pch_gbe_intr(adapter->irq, netdev);
+	enable_irq(adapter->irq);
 }
 #endif
 
diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c
index 482b85e4d665..c9529c29a0a7 100644
--- a/drivers/net/ethernet/packetengines/hamachi.c
+++ b/drivers/net/ethernet/packetengines/hamachi.c
@@ -413,13 +413,13 @@ that case.
 
 /* The rest of these values should never change. */
 
-static void hamachi_timer(unsigned long data);
+static void hamachi_timer(struct timer_list *t);
 
 enum capability_flags {CanHaveMII=1, };
 static const struct chip_info {
 	u16	vendor_id, device_id, device_id_mask, pad;
 	const char *name;
-	void (*media_timer)(unsigned long data);
+	void (*media_timer)(struct timer_list *t);
 	int flags;
 } chip_tbl[] = {
 	{0x1318, 0x0911, 0xffff, 0, "Hamachi GNIC-II", hamachi_timer, 0},
@@ -547,7 +547,7 @@ static int mdio_read(struct net_device *dev, int phy_id, int location);
 static void mdio_write(struct net_device *dev, int phy_id, int location, int value);
 static int hamachi_open(struct net_device *dev);
 static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
-static void hamachi_timer(unsigned long data);
+static void hamachi_timer(struct timer_list *t);
 static void hamachi_tx_timeout(struct net_device *dev);
 static void hamachi_init_ring(struct net_device *dev);
 static netdev_tx_t hamachi_start_xmit(struct sk_buff *skb,
@@ -979,10 +979,8 @@ static int hamachi_open(struct net_device *dev)
 			   dev->name, readw(ioaddr + RxStatus), readw(ioaddr + TxStatus));
 	}
 	/* Set the timer to check for link beat. */
-	init_timer(&hmp->timer);
+	timer_setup(&hmp->timer, hamachi_timer, 0);
 	hmp->timer.expires = RUN_AT((24*HZ)/10);			/* 2.4 sec. */
-	hmp->timer.data = (unsigned long)dev;
-	hmp->timer.function = hamachi_timer;				/* timer handler */
 	add_timer(&hmp->timer);
 
 	return 0;
@@ -1019,10 +1017,10 @@ static inline int hamachi_tx(struct net_device *dev)
 	return 0;
 }
 
-static void hamachi_timer(unsigned long data)
+static void hamachi_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct hamachi_private *hmp = netdev_priv(dev);
+	struct hamachi_private *hmp = from_timer(hmp, t, timer);
+	struct net_device *dev = hmp->mii_if.dev;
 	void __iomem *ioaddr = hmp->base;
 	int next_tick = 10*HZ;
 
diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c
index fa7770da6ef8..54224d1822e3 100644
--- a/drivers/net/ethernet/packetengines/yellowfin.c
+++ b/drivers/net/ethernet/packetengines/yellowfin.c
@@ -343,7 +343,7 @@ static int mdio_read(void __iomem *ioaddr, int phy_id, int location);
 static void mdio_write(void __iomem *ioaddr, int phy_id, int location, int value);
 static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
 static int yellowfin_open(struct net_device *dev);
-static void yellowfin_timer(unsigned long data);
+static void yellowfin_timer(struct timer_list *t);
 static void yellowfin_tx_timeout(struct net_device *dev);
 static int yellowfin_init_ring(struct net_device *dev);
 static netdev_tx_t yellowfin_start_xmit(struct sk_buff *skb,
@@ -632,10 +632,8 @@ static int yellowfin_open(struct net_device *dev)
 	}
 
 	/* Set the timer to check for link beat. */
-	init_timer(&yp->timer);
+	timer_setup(&yp->timer, yellowfin_timer, 0);
 	yp->timer.expires = jiffies + 3*HZ;
-	yp->timer.data = (unsigned long)dev;
-	yp->timer.function = yellowfin_timer;				/* timer handler */
 	add_timer(&yp->timer);
 out:
 	return rc;
@@ -645,10 +643,10 @@ err_free_irq:
 	goto out;
 }
 
-static void yellowfin_timer(unsigned long data)
+static void yellowfin_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct yellowfin_private *yp = netdev_priv(dev);
+	struct yellowfin_private *yp = from_timer(yp, t, timer);
+	struct net_device *dev = pci_get_drvdata(yp->pci_dev);
 	void __iomem *ioaddr = yp->base;
 	int next_tick = 60*HZ;
 
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index c2e24afbaeb2..26ddf092e3ec 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -117,4 +117,7 @@ config QED_ISCSI
 config QED_FCOE
 	bool
 
+config QED_OOO
+	bool
+
 endif # NET_VENDOR_QLOGIC
diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile
index 82a0b90185df..c70cf2ad81c0 100644
--- a/drivers/net/ethernet/qlogic/qed/Makefile
+++ b/drivers/net/ethernet/qlogic/qed/Makefile
@@ -7,5 +7,6 @@ qed-y := qed_cxt.o qed_dev.o qed_hw.o qed_init_fw_funcs.o qed_init_ops.o \
 qed-$(CONFIG_QED_SRIOV) += qed_sriov.o qed_vf.o
 qed-$(CONFIG_QED_LL2) += qed_ll2.o
 qed-$(CONFIG_QED_RDMA) += qed_roce.o qed_rdma.o qed_iwarp.o
-qed-$(CONFIG_QED_ISCSI) += qed_iscsi.o qed_ooo.o
+qed-$(CONFIG_QED_ISCSI) += qed_iscsi.o
 qed-$(CONFIG_QED_FCOE) += qed_fcoe.o
+qed-$(CONFIG_QED_OOO) += qed_ooo.o
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index af106be8cc08..afd07ad91631 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -2069,6 +2069,12 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
 
 	num_srqs = min_t(u32, 32 * 1024, p_params->num_srqs);
 
+	if (p_hwfn->mcp_info->func_info.protocol == QED_PCI_ETH_RDMA) {
+		DP_NOTICE(p_hwfn,
+			  "Current day drivers don't support RoCE & iWARP simultaneously on the same PF. Default to RoCE-only\n");
+		p_hwfn->hw_info.personality = QED_PCI_ETH_ROCE;
+	}
+
 	switch (p_hwfn->hw_info.personality) {
 	case QED_PCI_ETH_IWARP:
 		/* Each QP requires one connection */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 8f6ccc0c39e5..6e15d3c10ebf 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -2308,7 +2308,7 @@ static int qed_dcbnl_ieee_setapp(struct qed_dev *cdev, struct dcb_app *app)
 
 	DP_VERBOSE(hwfn, QED_MSG_DCB, "selector = %d protocol = %d pri = %d\n",
 		   app->selector, app->protocol, app->priority);
-	if (app->priority < 0 || app->priority >= QED_MAX_PFC_PRIORITIES) {
+	if (app->priority >= QED_MAX_PFC_PRIORITIES) {
 		DP_INFO(hwfn, "Invalid priority %d\n", app->priority);
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index 9d989c96278c..409041eab189 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -41,6 +41,7 @@
 #include "qed_rdma.h"
 #include "qed_reg_addr.h"
 #include "qed_sp.h"
+#include "qed_ooo.h"
 
 #define QED_IWARP_ORD_DEFAULT		32
 #define QED_IWARP_IRD_DEFAULT		32
@@ -119,6 +120,13 @@ static void qed_iwarp_cid_cleaned(struct qed_hwfn *p_hwfn, u32 cid)
 	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
 }
 
+void qed_iwarp_init_fw_ramrod(struct qed_hwfn *p_hwfn,
+			      struct iwarp_init_func_params *p_ramrod)
+{
+	p_ramrod->ll2_ooo_q_index = RESC_START(p_hwfn, QED_LL2_QUEUE) +
+				    p_hwfn->p_rdma_info->iwarp.ll2_ooo_handle;
+}
+
 static int qed_iwarp_alloc_cid(struct qed_hwfn *p_hwfn, u32 *cid)
 {
 	int rc;
@@ -1402,12 +1410,22 @@ int qed_iwarp_alloc(struct qed_hwfn *p_hwfn)
 	INIT_LIST_HEAD(&p_hwfn->p_rdma_info->iwarp.ep_free_list);
 	spin_lock_init(&p_hwfn->p_rdma_info->iwarp.iw_lock);
 
-	return qed_iwarp_prealloc_ep(p_hwfn, true);
+	rc = qed_iwarp_prealloc_ep(p_hwfn, true);
+	if (rc)
+		return rc;
+
+	return qed_ooo_alloc(p_hwfn);
 }
 
 void qed_iwarp_resc_free(struct qed_hwfn *p_hwfn)
 {
+	struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp;
+
+	qed_ooo_free(p_hwfn);
 	qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->tcp_cid_map, 1);
+	kfree(iwarp_info->mpa_bufs);
+	kfree(iwarp_info->partial_fpdus);
+	kfree(iwarp_info->mpa_intermediate_buf);
 }
 
 int qed_iwarp_accept(void *rdma_cxt, struct qed_iwarp_accept_in *iparams)
@@ -1705,6 +1723,569 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+static struct qed_iwarp_fpdu *qed_iwarp_get_curr_fpdu(struct qed_hwfn *p_hwfn,
+						      u16 cid)
+{
+	struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp;
+	struct qed_iwarp_fpdu *partial_fpdu;
+	u32 idx;
+
+	idx = cid - qed_cxt_get_proto_cid_start(p_hwfn, PROTOCOLID_IWARP);
+	if (idx >= iwarp_info->max_num_partial_fpdus) {
+		DP_ERR(p_hwfn, "Invalid cid %x max_num_partial_fpdus=%x\n", cid,
+		       iwarp_info->max_num_partial_fpdus);
+		return NULL;
+	}
+
+	partial_fpdu = &iwarp_info->partial_fpdus[idx];
+
+	return partial_fpdu;
+}
+
+enum qed_iwarp_mpa_pkt_type {
+	QED_IWARP_MPA_PKT_PACKED,
+	QED_IWARP_MPA_PKT_PARTIAL,
+	QED_IWARP_MPA_PKT_UNALIGNED
+};
+
+#define QED_IWARP_INVALID_FPDU_LENGTH 0xffff
+#define QED_IWARP_MPA_FPDU_LENGTH_SIZE (2)
+#define QED_IWARP_MPA_CRC32_DIGEST_SIZE (4)
+
+/* Pad to multiple of 4 */
+#define QED_IWARP_PDU_DATA_LEN_WITH_PAD(data_len) ALIGN(data_len, 4)
+#define QED_IWARP_FPDU_LEN_WITH_PAD(_mpa_len)				   \
+	(QED_IWARP_PDU_DATA_LEN_WITH_PAD((_mpa_len) +			   \
+					 QED_IWARP_MPA_FPDU_LENGTH_SIZE) + \
+					 QED_IWARP_MPA_CRC32_DIGEST_SIZE)
+
+/* fpdu can be fragmented over maximum 3 bds: header, partial mpa, unaligned */
+#define QED_IWARP_MAX_BDS_PER_FPDU 3
+
+char *pkt_type_str[] = {
+	"QED_IWARP_MPA_PKT_PACKED",
+	"QED_IWARP_MPA_PKT_PARTIAL",
+	"QED_IWARP_MPA_PKT_UNALIGNED"
+};
+
+static int
+qed_iwarp_recycle_pkt(struct qed_hwfn *p_hwfn,
+		      struct qed_iwarp_fpdu *fpdu,
+		      struct qed_iwarp_ll2_buff *buf);
+
+static enum qed_iwarp_mpa_pkt_type
+qed_iwarp_mpa_classify(struct qed_hwfn *p_hwfn,
+		       struct qed_iwarp_fpdu *fpdu,
+		       u16 tcp_payload_len, u8 *mpa_data)
+{
+	enum qed_iwarp_mpa_pkt_type pkt_type;
+	u16 mpa_len;
+
+	if (fpdu->incomplete_bytes) {
+		pkt_type = QED_IWARP_MPA_PKT_UNALIGNED;
+		goto out;
+	}
+
+	/* special case of one byte remaining...
+	 * lower byte will be read next packet
+	 */
+	if (tcp_payload_len == 1) {
+		fpdu->fpdu_length = *mpa_data << BITS_PER_BYTE;
+		pkt_type = QED_IWARP_MPA_PKT_PARTIAL;
+		goto out;
+	}
+
+	mpa_len = ntohs(*((u16 *)(mpa_data)));
+	fpdu->fpdu_length = QED_IWARP_FPDU_LEN_WITH_PAD(mpa_len);
+
+	if (fpdu->fpdu_length <= tcp_payload_len)
+		pkt_type = QED_IWARP_MPA_PKT_PACKED;
+	else
+		pkt_type = QED_IWARP_MPA_PKT_PARTIAL;
+
+out:
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+		   "MPA_ALIGN: %s: fpdu_length=0x%x tcp_payload_len:0x%x\n",
+		   pkt_type_str[pkt_type], fpdu->fpdu_length, tcp_payload_len);
+
+	return pkt_type;
+}
+
+static void
+qed_iwarp_init_fpdu(struct qed_iwarp_ll2_buff *buf,
+		    struct qed_iwarp_fpdu *fpdu,
+		    struct unaligned_opaque_data *pkt_data,
+		    u16 tcp_payload_size, u8 placement_offset)
+{
+	fpdu->mpa_buf = buf;
+	fpdu->pkt_hdr = buf->data_phys_addr + placement_offset;
+	fpdu->pkt_hdr_size = pkt_data->tcp_payload_offset;
+	fpdu->mpa_frag = buf->data_phys_addr + pkt_data->first_mpa_offset;
+	fpdu->mpa_frag_virt = (u8 *)(buf->data) + pkt_data->first_mpa_offset;
+
+	if (tcp_payload_size == 1)
+		fpdu->incomplete_bytes = QED_IWARP_INVALID_FPDU_LENGTH;
+	else if (tcp_payload_size < fpdu->fpdu_length)
+		fpdu->incomplete_bytes = fpdu->fpdu_length - tcp_payload_size;
+	else
+		fpdu->incomplete_bytes = 0;	/* complete fpdu */
+
+	fpdu->mpa_frag_len = fpdu->fpdu_length - fpdu->incomplete_bytes;
+}
+
+static int
+qed_iwarp_cp_pkt(struct qed_hwfn *p_hwfn,
+		 struct qed_iwarp_fpdu *fpdu,
+		 struct unaligned_opaque_data *pkt_data,
+		 struct qed_iwarp_ll2_buff *buf, u16 tcp_payload_size)
+{
+	u8 *tmp_buf = p_hwfn->p_rdma_info->iwarp.mpa_intermediate_buf;
+	int rc;
+
+	/* need to copy the data from the partial packet stored in fpdu
+	 * to the new buf, for this we also need to move the data currently
+	 * placed on the buf. The assumption is that the buffer is big enough
+	 * since fpdu_length <= mss, we use an intermediate buffer since
+	 * we may need to copy the new data to an overlapping location
+	 */
+	if ((fpdu->mpa_frag_len + tcp_payload_size) > (u16)buf->buff_size) {
+		DP_ERR(p_hwfn,
+		       "MPA ALIGN: Unexpected: buffer is not large enough for split fpdu buff_size = %d mpa_frag_len = %d, tcp_payload_size = %d, incomplete_bytes = %d\n",
+		       buf->buff_size, fpdu->mpa_frag_len,
+		       tcp_payload_size, fpdu->incomplete_bytes);
+		return -EINVAL;
+	}
+
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+		   "MPA ALIGN Copying fpdu: [%p, %d] [%p, %d]\n",
+		   fpdu->mpa_frag_virt, fpdu->mpa_frag_len,
+		   (u8 *)(buf->data) + pkt_data->first_mpa_offset,
+		   tcp_payload_size);
+
+	memcpy(tmp_buf, fpdu->mpa_frag_virt, fpdu->mpa_frag_len);
+	memcpy(tmp_buf + fpdu->mpa_frag_len,
+	       (u8 *)(buf->data) + pkt_data->first_mpa_offset,
+	       tcp_payload_size);
+
+	rc = qed_iwarp_recycle_pkt(p_hwfn, fpdu, fpdu->mpa_buf);
+	if (rc)
+		return rc;
+
+	/* If we managed to post the buffer copy the data to the new buffer
+	 * o/w this will occur in the next round...
+	 */
+	memcpy((u8 *)(buf->data), tmp_buf,
+	       fpdu->mpa_frag_len + tcp_payload_size);
+
+	fpdu->mpa_buf = buf;
+	/* fpdu->pkt_hdr remains as is */
+	/* fpdu->mpa_frag is overridden with new buf */
+	fpdu->mpa_frag = buf->data_phys_addr;
+	fpdu->mpa_frag_virt = buf->data;
+	fpdu->mpa_frag_len += tcp_payload_size;
+
+	fpdu->incomplete_bytes -= tcp_payload_size;
+
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_RDMA,
+		   "MPA ALIGN: split fpdu buff_size = %d mpa_frag_len = %d, tcp_payload_size = %d, incomplete_bytes = %d\n",
+		   buf->buff_size, fpdu->mpa_frag_len, tcp_payload_size,
+		   fpdu->incomplete_bytes);
+
+	return 0;
+}
+
+static void
+qed_iwarp_update_fpdu_length(struct qed_hwfn *p_hwfn,
+			     struct qed_iwarp_fpdu *fpdu, u8 *mpa_data)
+{
+	u16 mpa_len;
+
+	/* Update incomplete packets if needed */
+	if (fpdu->incomplete_bytes == QED_IWARP_INVALID_FPDU_LENGTH) {
+		/* Missing lower byte is now available */
+		mpa_len = fpdu->fpdu_length | *mpa_data;
+		fpdu->fpdu_length = QED_IWARP_FPDU_LEN_WITH_PAD(mpa_len);
+		fpdu->mpa_frag_len = fpdu->fpdu_length;
+		/* one byte of hdr */
+		fpdu->incomplete_bytes = fpdu->fpdu_length - 1;
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_RDMA,
+			   "MPA_ALIGN: Partial header mpa_len=%x fpdu_length=%x incomplete_bytes=%x\n",
+			   mpa_len, fpdu->fpdu_length, fpdu->incomplete_bytes);
+	}
+}
+
+#define QED_IWARP_IS_RIGHT_EDGE(_curr_pkt) \
+	(GET_FIELD((_curr_pkt)->flags,	   \
+		   UNALIGNED_OPAQUE_DATA_PKT_REACHED_WIN_RIGHT_EDGE))
+
+/* This function is used to recycle a buffer using the ll2 drop option. It
+ * uses the mechanism to ensure that all buffers posted to tx before this one
+ * were completed. The buffer sent here will be sent as a cookie in the tx
+ * completion function and can then be reposted to rx chain when done. The flow
+ * that requires this is the flow where a FPDU splits over more than 3 tcp
+ * segments. In this case the driver needs to re-post a rx buffer instead of
+ * the one received, but driver can't simply repost a buffer it copied from
+ * as there is a case where the buffer was originally a packed FPDU, and is
+ * partially posted to FW. Driver needs to ensure FW is done with it.
+ */
+static int
+qed_iwarp_recycle_pkt(struct qed_hwfn *p_hwfn,
+		      struct qed_iwarp_fpdu *fpdu,
+		      struct qed_iwarp_ll2_buff *buf)
+{
+	struct qed_ll2_tx_pkt_info tx_pkt;
+	u8 ll2_handle;
+	int rc;
+
+	memset(&tx_pkt, 0, sizeof(tx_pkt));
+	tx_pkt.num_of_bds = 1;
+	tx_pkt.tx_dest = QED_LL2_TX_DEST_DROP;
+	tx_pkt.l4_hdr_offset_w = fpdu->pkt_hdr_size >> 2;
+	tx_pkt.first_frag = fpdu->pkt_hdr;
+	tx_pkt.first_frag_len = fpdu->pkt_hdr_size;
+	buf->piggy_buf = NULL;
+	tx_pkt.cookie = buf;
+
+	ll2_handle = p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle;
+
+	rc = qed_ll2_prepare_tx_packet(p_hwfn, ll2_handle, &tx_pkt, true);
+	if (rc)
+		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+			   "Can't drop packet rc=%d\n", rc);
+
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_RDMA,
+		   "MPA_ALIGN: send drop tx packet [%lx, 0x%x], buf=%p, rc=%d\n",
+		   (unsigned long int)tx_pkt.first_frag,
+		   tx_pkt.first_frag_len, buf, rc);
+
+	return rc;
+}
+
+static int
+qed_iwarp_win_right_edge(struct qed_hwfn *p_hwfn, struct qed_iwarp_fpdu *fpdu)
+{
+	struct qed_ll2_tx_pkt_info tx_pkt;
+	u8 ll2_handle;
+	int rc;
+
+	memset(&tx_pkt, 0, sizeof(tx_pkt));
+	tx_pkt.num_of_bds = 1;
+	tx_pkt.tx_dest = QED_LL2_TX_DEST_LB;
+	tx_pkt.l4_hdr_offset_w = fpdu->pkt_hdr_size >> 2;
+
+	tx_pkt.first_frag = fpdu->pkt_hdr;
+	tx_pkt.first_frag_len = fpdu->pkt_hdr_size;
+	tx_pkt.enable_ip_cksum = true;
+	tx_pkt.enable_l4_cksum = true;
+	tx_pkt.calc_ip_len = true;
+	/* vlan overload with enum iwarp_ll2_tx_queues */
+	tx_pkt.vlan = IWARP_LL2_ALIGNED_RIGHT_TRIMMED_TX_QUEUE;
+
+	ll2_handle = p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle;
+
+	rc = qed_ll2_prepare_tx_packet(p_hwfn, ll2_handle, &tx_pkt, true);
+	if (rc)
+		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+			   "Can't send right edge rc=%d\n", rc);
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_RDMA,
+		   "MPA_ALIGN: Sent right edge FPDU num_bds=%d [%lx, 0x%x], rc=%d\n",
+		   tx_pkt.num_of_bds,
+		   (unsigned long int)tx_pkt.first_frag,
+		   tx_pkt.first_frag_len, rc);
+
+	return rc;
+}
+
+static int
+qed_iwarp_send_fpdu(struct qed_hwfn *p_hwfn,
+		    struct qed_iwarp_fpdu *fpdu,
+		    struct unaligned_opaque_data *curr_pkt,
+		    struct qed_iwarp_ll2_buff *buf,
+		    u16 tcp_payload_size, enum qed_iwarp_mpa_pkt_type pkt_type)
+{
+	struct qed_ll2_tx_pkt_info tx_pkt;
+	u8 ll2_handle;
+	int rc;
+
+	memset(&tx_pkt, 0, sizeof(tx_pkt));
+
+	/* An unaligned packet means it's split over two tcp segments. So the
+	 * complete packet requires 3 bds, one for the header, one for the
+	 * part of the fpdu of the first tcp segment, and the last fragment
+	 * will point to the remainder of the fpdu. A packed pdu, requires only
+	 * two bds, one for the header and one for the data.
+	 */
+	tx_pkt.num_of_bds = (pkt_type == QED_IWARP_MPA_PKT_UNALIGNED) ? 3 : 2;
+	tx_pkt.tx_dest = QED_LL2_TX_DEST_LB;
+	tx_pkt.l4_hdr_offset_w = fpdu->pkt_hdr_size >> 2; /* offset in words */
+
+	/* Send the mpa_buf only with the last fpdu (in case of packed) */
+	if (pkt_type == QED_IWARP_MPA_PKT_UNALIGNED ||
+	    tcp_payload_size <= fpdu->fpdu_length)
+		tx_pkt.cookie = fpdu->mpa_buf;
+
+	tx_pkt.first_frag = fpdu->pkt_hdr;
+	tx_pkt.first_frag_len = fpdu->pkt_hdr_size;
+	tx_pkt.enable_ip_cksum = true;
+	tx_pkt.enable_l4_cksum = true;
+	tx_pkt.calc_ip_len = true;
+	/* vlan overload with enum iwarp_ll2_tx_queues */
+	tx_pkt.vlan = IWARP_LL2_ALIGNED_TX_QUEUE;
+
+	/* special case of unaligned packet and not packed, need to send
+	 * both buffers as cookie to release.
+	 */
+	if (tcp_payload_size == fpdu->incomplete_bytes)
+		fpdu->mpa_buf->piggy_buf = buf;
+
+	ll2_handle = p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle;
+
+	/* Set first fragment to header */
+	rc = qed_ll2_prepare_tx_packet(p_hwfn, ll2_handle, &tx_pkt, true);
+	if (rc)
+		goto out;
+
+	/* Set second fragment to first part of packet */
+	rc = qed_ll2_set_fragment_of_tx_packet(p_hwfn, ll2_handle,
+					       fpdu->mpa_frag,
+					       fpdu->mpa_frag_len);
+	if (rc)
+		goto out;
+
+	if (!fpdu->incomplete_bytes)
+		goto out;
+
+	/* Set third fragment to second part of the packet */
+	rc = qed_ll2_set_fragment_of_tx_packet(p_hwfn,
+					       ll2_handle,
+					       buf->data_phys_addr +
+					       curr_pkt->first_mpa_offset,
+					       fpdu->incomplete_bytes);
+out:
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_RDMA,
+		   "MPA_ALIGN: Sent FPDU num_bds=%d first_frag_len=%x, mpa_frag_len=0x%x, incomplete_bytes:0x%x rc=%d\n",
+		   tx_pkt.num_of_bds,
+		   tx_pkt.first_frag_len,
+		   fpdu->mpa_frag_len,
+		   fpdu->incomplete_bytes, rc);
+
+	return rc;
+}
+
+static void
+qed_iwarp_mpa_get_data(struct qed_hwfn *p_hwfn,
+		       struct unaligned_opaque_data *curr_pkt,
+		       u32 opaque_data0, u32 opaque_data1)
+{
+	u64 opaque_data;
+
+	opaque_data = HILO_64(opaque_data1, opaque_data0);
+	*curr_pkt = *((struct unaligned_opaque_data *)&opaque_data);
+
+	curr_pkt->first_mpa_offset = curr_pkt->tcp_payload_offset +
+				     le16_to_cpu(curr_pkt->first_mpa_offset);
+	curr_pkt->cid = le32_to_cpu(curr_pkt->cid);
+}
+
+/* This function is called when an unaligned or incomplete MPA packet arrives
+ * driver needs to align the packet, perhaps using previous data and send
+ * it down to FW once it is aligned.
+ */
+static int
+qed_iwarp_process_mpa_pkt(struct qed_hwfn *p_hwfn,
+			  struct qed_iwarp_ll2_mpa_buf *mpa_buf)
+{
+	struct unaligned_opaque_data *curr_pkt = &mpa_buf->data;
+	struct qed_iwarp_ll2_buff *buf = mpa_buf->ll2_buf;
+	enum qed_iwarp_mpa_pkt_type pkt_type;
+	struct qed_iwarp_fpdu *fpdu;
+	int rc = -EINVAL;
+	u8 *mpa_data;
+
+	fpdu = qed_iwarp_get_curr_fpdu(p_hwfn, curr_pkt->cid & 0xffff);
+	if (!fpdu) { /* something corrupt with cid, post rx back */
+		DP_ERR(p_hwfn, "Invalid cid, drop and post back to rx cid=%x\n",
+		       curr_pkt->cid);
+		goto err;
+	}
+
+	do {
+		mpa_data = ((u8 *)(buf->data) + curr_pkt->first_mpa_offset);
+
+		pkt_type = qed_iwarp_mpa_classify(p_hwfn, fpdu,
+						  mpa_buf->tcp_payload_len,
+						  mpa_data);
+
+		switch (pkt_type) {
+		case QED_IWARP_MPA_PKT_PARTIAL:
+			qed_iwarp_init_fpdu(buf, fpdu,
+					    curr_pkt,
+					    mpa_buf->tcp_payload_len,
+					    mpa_buf->placement_offset);
+
+			if (!QED_IWARP_IS_RIGHT_EDGE(curr_pkt)) {
+				mpa_buf->tcp_payload_len = 0;
+				break;
+			}
+
+			rc = qed_iwarp_win_right_edge(p_hwfn, fpdu);
+
+			if (rc) {
+				DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+					   "Can't send FPDU:reset rc=%d\n", rc);
+				memset(fpdu, 0, sizeof(*fpdu));
+				break;
+			}
+
+			mpa_buf->tcp_payload_len = 0;
+			break;
+		case QED_IWARP_MPA_PKT_PACKED:
+			qed_iwarp_init_fpdu(buf, fpdu,
+					    curr_pkt,
+					    mpa_buf->tcp_payload_len,
+					    mpa_buf->placement_offset);
+
+			rc = qed_iwarp_send_fpdu(p_hwfn, fpdu, curr_pkt, buf,
+						 mpa_buf->tcp_payload_len,
+						 pkt_type);
+			if (rc) {
+				DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+					   "Can't send FPDU:reset rc=%d\n", rc);
+				memset(fpdu, 0, sizeof(*fpdu));
+				break;
+			}
+
+			mpa_buf->tcp_payload_len -= fpdu->fpdu_length;
+			curr_pkt->first_mpa_offset += fpdu->fpdu_length;
+			break;
+		case QED_IWARP_MPA_PKT_UNALIGNED:
+			qed_iwarp_update_fpdu_length(p_hwfn, fpdu, mpa_data);
+			if (mpa_buf->tcp_payload_len < fpdu->incomplete_bytes) {
+				/* special handling of fpdu split over more
+				 * than 2 segments
+				 */
+				if (QED_IWARP_IS_RIGHT_EDGE(curr_pkt)) {
+					rc = qed_iwarp_win_right_edge(p_hwfn,
+								      fpdu);
+					/* packet will be re-processed later */
+					if (rc)
+						return rc;
+				}
+
+				rc = qed_iwarp_cp_pkt(p_hwfn, fpdu, curr_pkt,
+						      buf,
+						      mpa_buf->tcp_payload_len);
+				if (rc) /* packet will be re-processed later */
+					return rc;
+
+				mpa_buf->tcp_payload_len = 0;
+				break;
+			}
+
+			rc = qed_iwarp_send_fpdu(p_hwfn, fpdu, curr_pkt, buf,
+						 mpa_buf->tcp_payload_len,
+						 pkt_type);
+			if (rc) {
+				DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+					   "Can't send FPDU:delay rc=%d\n", rc);
+				/* don't reset fpdu -> we need it for next
+				 * classify
+				 */
+				break;
+			}
+
+			mpa_buf->tcp_payload_len -= fpdu->incomplete_bytes;
+			curr_pkt->first_mpa_offset += fpdu->incomplete_bytes;
+			/* The framed PDU was sent - no more incomplete bytes */
+			fpdu->incomplete_bytes = 0;
+			break;
+		}
+	} while (mpa_buf->tcp_payload_len && !rc);
+
+	return rc;
+
+err:
+	qed_iwarp_ll2_post_rx(p_hwfn,
+			      buf,
+			      p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle);
+	return rc;
+}
+
+static void qed_iwarp_process_pending_pkts(struct qed_hwfn *p_hwfn)
+{
+	struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp;
+	struct qed_iwarp_ll2_mpa_buf *mpa_buf = NULL;
+	int rc;
+
+	while (!list_empty(&iwarp_info->mpa_buf_pending_list)) {
+		mpa_buf = list_first_entry(&iwarp_info->mpa_buf_pending_list,
+					   struct qed_iwarp_ll2_mpa_buf,
+					   list_entry);
+
+		rc = qed_iwarp_process_mpa_pkt(p_hwfn, mpa_buf);
+
+		/* busy means break and continue processing later, don't
+		 * remove the buf from the pending list.
+		 */
+		if (rc == -EBUSY)
+			break;
+
+		list_del(&mpa_buf->list_entry);
+		list_add_tail(&mpa_buf->list_entry, &iwarp_info->mpa_buf_list);
+
+		if (rc) {	/* different error, don't continue */
+			DP_NOTICE(p_hwfn, "process pkts failed rc=%d\n", rc);
+			break;
+		}
+	}
+}
+
+static void
+qed_iwarp_ll2_comp_mpa_pkt(void *cxt, struct qed_ll2_comp_rx_data *data)
+{
+	struct qed_iwarp_ll2_mpa_buf *mpa_buf;
+	struct qed_iwarp_info *iwarp_info;
+	struct qed_hwfn *p_hwfn = cxt;
+
+	iwarp_info = &p_hwfn->p_rdma_info->iwarp;
+	mpa_buf = list_first_entry(&iwarp_info->mpa_buf_list,
+				   struct qed_iwarp_ll2_mpa_buf, list_entry);
+	if (!mpa_buf) {
+		DP_ERR(p_hwfn, "No free mpa buf\n");
+		goto err;
+	}
+
+	list_del(&mpa_buf->list_entry);
+	qed_iwarp_mpa_get_data(p_hwfn, &mpa_buf->data,
+			       data->opaque_data_0, data->opaque_data_1);
+
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_RDMA,
+		   "LL2 MPA CompRx payload_len:0x%x\tfirst_mpa_offset:0x%x\ttcp_payload_offset:0x%x\tflags:0x%x\tcid:0x%x\n",
+		   data->length.packet_length, mpa_buf->data.first_mpa_offset,
+		   mpa_buf->data.tcp_payload_offset, mpa_buf->data.flags,
+		   mpa_buf->data.cid);
+
+	mpa_buf->ll2_buf = data->cookie;
+	mpa_buf->tcp_payload_len = data->length.packet_length -
+				   mpa_buf->data.first_mpa_offset;
+	mpa_buf->data.first_mpa_offset += data->u.placement_offset;
+	mpa_buf->placement_offset = data->u.placement_offset;
+
+	list_add_tail(&mpa_buf->list_entry, &iwarp_info->mpa_buf_pending_list);
+
+	qed_iwarp_process_pending_pkts(p_hwfn);
+	return;
+err:
+	qed_iwarp_ll2_post_rx(p_hwfn, data->cookie,
+			      iwarp_info->ll2_mpa_handle);
+}
+
 static void
 qed_iwarp_ll2_comp_syn_pkt(void *cxt, struct qed_ll2_comp_rx_data *data)
 {
@@ -1725,6 +2306,14 @@ qed_iwarp_ll2_comp_syn_pkt(void *cxt, struct qed_ll2_comp_rx_data *data)
 
 	memset(&cm_info, 0, sizeof(cm_info));
 	ll2_syn_handle = p_hwfn->p_rdma_info->iwarp.ll2_syn_handle;
+
+	/* Check if packet was received with errors... */
+	if (data->err_flags) {
+		DP_NOTICE(p_hwfn, "Error received on SYN packet: 0x%x\n",
+			  data->err_flags);
+		goto err;
+	}
+
 	if (GET_FIELD(data->parse_flags,
 		      PARSING_AND_ERR_FLAGS_L4CHKSMWASCALCULATED) &&
 	    GET_FIELD(data->parse_flags, PARSING_AND_ERR_FLAGS_L4CHKSMERROR)) {
@@ -1839,10 +2428,25 @@ static void qed_iwarp_ll2_comp_tx_pkt(void *cxt, u8 connection_handle,
 				      bool b_last_fragment, bool b_last_packet)
 {
 	struct qed_iwarp_ll2_buff *buffer = cookie;
+	struct qed_iwarp_ll2_buff *piggy;
 	struct qed_hwfn *p_hwfn = cxt;
 
+	if (!buffer)		/* can happen in packed mpa unaligned... */
+		return;
+
 	/* this was originally an rx packet, post it back */
+	piggy = buffer->piggy_buf;
+	if (piggy) {
+		buffer->piggy_buf = NULL;
+		qed_iwarp_ll2_post_rx(p_hwfn, piggy, connection_handle);
+	}
+
 	qed_iwarp_ll2_post_rx(p_hwfn, buffer, connection_handle);
+
+	if (connection_handle == p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle)
+		qed_iwarp_process_pending_pkts(p_hwfn);
+
+	return;
 }
 
 static void qed_iwarp_ll2_rel_tx_pkt(void *cxt, u8 connection_handle,
@@ -1855,12 +2459,44 @@ static void qed_iwarp_ll2_rel_tx_pkt(void *cxt, u8 connection_handle,
 	if (!buffer)
 		return;
 
+	if (buffer->piggy_buf) {
+		dma_free_coherent(&p_hwfn->cdev->pdev->dev,
+				  buffer->piggy_buf->buff_size,
+				  buffer->piggy_buf->data,
+				  buffer->piggy_buf->data_phys_addr);
+
+		kfree(buffer->piggy_buf);
+	}
+
 	dma_free_coherent(&p_hwfn->cdev->pdev->dev, buffer->buff_size,
 			  buffer->data, buffer->data_phys_addr);
 
 	kfree(buffer);
 }
 
+/* The only slowpath for iwarp ll2 is unalign flush. When this completion
+ * is received, need to reset the FPDU.
+ */
+void
+qed_iwarp_ll2_slowpath(void *cxt,
+		       u8 connection_handle,
+		       u32 opaque_data_0, u32 opaque_data_1)
+{
+	struct unaligned_opaque_data unalign_data;
+	struct qed_hwfn *p_hwfn = cxt;
+	struct qed_iwarp_fpdu *fpdu;
+
+	qed_iwarp_mpa_get_data(p_hwfn, &unalign_data,
+			       opaque_data_0, opaque_data_1);
+
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "(0x%x) Flush fpdu\n",
+		   unalign_data.cid);
+
+	fpdu = qed_iwarp_get_curr_fpdu(p_hwfn, (u16)unalign_data.cid);
+	if (fpdu)
+		memset(fpdu, 0, sizeof(*fpdu));
+}
+
 static int qed_iwarp_ll2_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp;
@@ -1876,6 +2512,26 @@ static int qed_iwarp_ll2_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		iwarp_info->ll2_syn_handle = QED_IWARP_HANDLE_INVAL;
 	}
 
+	if (iwarp_info->ll2_ooo_handle != QED_IWARP_HANDLE_INVAL) {
+		rc = qed_ll2_terminate_connection(p_hwfn,
+						  iwarp_info->ll2_ooo_handle);
+		if (rc)
+			DP_INFO(p_hwfn, "Failed to terminate ooo connection\n");
+
+		qed_ll2_release_connection(p_hwfn, iwarp_info->ll2_ooo_handle);
+		iwarp_info->ll2_ooo_handle = QED_IWARP_HANDLE_INVAL;
+	}
+
+	if (iwarp_info->ll2_mpa_handle != QED_IWARP_HANDLE_INVAL) {
+		rc = qed_ll2_terminate_connection(p_hwfn,
+						  iwarp_info->ll2_mpa_handle);
+		if (rc)
+			DP_INFO(p_hwfn, "Failed to terminate mpa connection\n");
+
+		qed_ll2_release_connection(p_hwfn, iwarp_info->ll2_mpa_handle);
+		iwarp_info->ll2_mpa_handle = QED_IWARP_HANDLE_INVAL;
+	}
+
 	qed_llh_remove_mac_filter(p_hwfn,
 				  p_ptt, p_hwfn->p_rdma_info->iwarp.mac_addr);
 	return rc;
@@ -1927,10 +2583,15 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 	struct qed_iwarp_info *iwarp_info;
 	struct qed_ll2_acquire_data data;
 	struct qed_ll2_cbs cbs;
+	u32 mpa_buff_size;
+	u16 n_ooo_bufs;
 	int rc = 0;
+	int i;
 
 	iwarp_info = &p_hwfn->p_rdma_info->iwarp;
 	iwarp_info->ll2_syn_handle = QED_IWARP_HANDLE_INVAL;
+	iwarp_info->ll2_ooo_handle = QED_IWARP_HANDLE_INVAL;
+	iwarp_info->ll2_mpa_handle = QED_IWARP_HANDLE_INVAL;
 
 	iwarp_info->max_mtu = params->max_mtu;
 
@@ -1978,6 +2639,91 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 	if (rc)
 		goto err;
 
+	/* Start OOO connection */
+	data.input.conn_type = QED_LL2_TYPE_OOO;
+	data.input.mtu = params->max_mtu;
+
+	n_ooo_bufs = (QED_IWARP_MAX_OOO * QED_IWARP_RCV_WND_SIZE_DEF) /
+		     iwarp_info->max_mtu;
+	n_ooo_bufs = min_t(u32, n_ooo_bufs, QED_IWARP_LL2_OOO_MAX_RX_SIZE);
+
+	data.input.rx_num_desc = n_ooo_bufs;
+	data.input.rx_num_ooo_buffers = n_ooo_bufs;
+
+	data.input.tx_max_bds_per_packet = 1;	/* will never be fragmented */
+	data.input.tx_num_desc = QED_IWARP_LL2_OOO_DEF_TX_SIZE;
+	data.p_connection_handle = &iwarp_info->ll2_ooo_handle;
+
+	rc = qed_ll2_acquire_connection(p_hwfn, &data);
+	if (rc)
+		goto err;
+
+	rc = qed_ll2_establish_connection(p_hwfn, iwarp_info->ll2_ooo_handle);
+	if (rc)
+		goto err;
+
+	/* Start Unaligned MPA connection */
+	cbs.rx_comp_cb = qed_iwarp_ll2_comp_mpa_pkt;
+	cbs.slowpath_cb = qed_iwarp_ll2_slowpath;
+
+	memset(&data, 0, sizeof(data));
+	data.input.conn_type = QED_LL2_TYPE_IWARP;
+	data.input.mtu = params->max_mtu;
+	/* FW requires that once a packet arrives OOO, it must have at
+	 * least 2 rx buffers available on the unaligned connection
+	 * for handling the case that it is a partial fpdu.
+	 */
+	data.input.rx_num_desc = n_ooo_bufs * 2;
+	data.input.tx_num_desc = data.input.rx_num_desc;
+	data.input.tx_max_bds_per_packet = QED_IWARP_MAX_BDS_PER_FPDU;
+	data.p_connection_handle = &iwarp_info->ll2_mpa_handle;
+	data.input.secondary_queue = true;
+	data.cbs = &cbs;
+
+	rc = qed_ll2_acquire_connection(p_hwfn, &data);
+	if (rc)
+		goto err;
+
+	rc = qed_ll2_establish_connection(p_hwfn, iwarp_info->ll2_mpa_handle);
+	if (rc)
+		goto err;
+
+	mpa_buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu);
+	rc = qed_iwarp_ll2_alloc_buffers(p_hwfn,
+					 data.input.rx_num_desc,
+					 mpa_buff_size,
+					 iwarp_info->ll2_mpa_handle);
+	if (rc)
+		goto err;
+
+	iwarp_info->partial_fpdus = kcalloc((u16)p_hwfn->p_rdma_info->num_qps,
+					    sizeof(*iwarp_info->partial_fpdus),
+					    GFP_KERNEL);
+	if (!iwarp_info->partial_fpdus)
+		goto err;
+
+	iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps;
+
+	iwarp_info->mpa_intermediate_buf = kzalloc(mpa_buff_size, GFP_KERNEL);
+	if (!iwarp_info->mpa_intermediate_buf)
+		goto err;
+
+	/* The mpa_bufs array serves for pending RX packets received on the
+	 * mpa ll2 that don't have place on the tx ring and require later
+	 * processing. We can't fail on allocation of such a struct therefore
+	 * we allocate enough to take care of all rx packets
+	 */
+	iwarp_info->mpa_bufs = kcalloc(data.input.rx_num_desc,
+				       sizeof(*iwarp_info->mpa_bufs),
+				       GFP_KERNEL);
+	if (!iwarp_info->mpa_bufs)
+		goto err;
+
+	INIT_LIST_HEAD(&iwarp_info->mpa_buf_pending_list);
+	INIT_LIST_HEAD(&iwarp_info->mpa_buf_list);
+	for (i = 0; i < data.input.rx_num_desc; i++)
+		list_add_tail(&iwarp_info->mpa_bufs[i].list_entry,
+			      &iwarp_info->mpa_buf_list);
 	return rc;
 err:
 	qed_iwarp_ll2_stop(p_hwfn, p_ptt);
@@ -2014,6 +2760,7 @@ int qed_iwarp_setup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 
 	qed_spq_register_async_cb(p_hwfn, PROTOCOLID_IWARP,
 				  qed_iwarp_async_event);
+	qed_ooo_setup(p_hwfn);
 
 	return qed_iwarp_ll2_start(p_hwfn, params, p_ptt);
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
index 148ef3c33a5d..c1ecd743305f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
@@ -47,18 +47,51 @@ enum qed_iwarp_qp_state qed_roce2iwarp_state(enum qed_roce_qp_state state);
 #define QED_IWARP_LL2_SYN_TX_SIZE       (128)
 #define QED_IWARP_LL2_SYN_RX_SIZE       (256)
 #define QED_IWARP_MAX_SYN_PKT_SIZE      (128)
-#define QED_IWARP_HANDLE_INVAL			(0xff)
+
+#define QED_IWARP_LL2_OOO_DEF_TX_SIZE   (256)
+#define QED_IWARP_MAX_OOO		(16)
+#define QED_IWARP_LL2_OOO_MAX_RX_SIZE   (16384)
+
+#define QED_IWARP_HANDLE_INVAL		(0xff)
 
 struct qed_iwarp_ll2_buff {
+	struct qed_iwarp_ll2_buff *piggy_buf;
 	void *data;
 	dma_addr_t data_phys_addr;
 	u32 buff_size;
 };
 
+struct qed_iwarp_ll2_mpa_buf {
+	struct list_head list_entry;
+	struct qed_iwarp_ll2_buff *ll2_buf;
+	struct unaligned_opaque_data data;
+	u16 tcp_payload_len;
+	u8 placement_offset;
+};
+
+/* In some cases a fpdu will arrive with only one byte of the header, in this
+ * case the fpdu_length will be partial (contain only higher byte and
+ * incomplete bytes will contain the invalid value
+ */
+#define QED_IWARP_INVALID_INCOMPLETE_BYTES 0xffff
+
+struct qed_iwarp_fpdu {
+	struct qed_iwarp_ll2_buff *mpa_buf;
+	void *mpa_frag_virt;
+	dma_addr_t mpa_frag;
+	dma_addr_t pkt_hdr;
+	u16 mpa_frag_len;
+	u16 fpdu_length;
+	u16 incomplete_bytes;
+	u8 pkt_hdr_size;
+};
+
 struct qed_iwarp_info {
 	struct list_head listen_list;	/* qed_iwarp_listener */
 	struct list_head ep_list;	/* qed_iwarp_ep */
 	struct list_head ep_free_list;	/* pre-allocated ep's */
+	struct list_head mpa_buf_list;	/* list of mpa_bufs */
+	struct list_head mpa_buf_pending_list;
 	spinlock_t iw_lock;	/* for iwarp resources */
 	spinlock_t qp_lock;	/* for teardown races */
 	u32 rcv_wnd_scale;
@@ -67,9 +100,15 @@ struct qed_iwarp_info {
 	u8 crc_needed;
 	u8 tcp_flags;
 	u8 ll2_syn_handle;
+	u8 ll2_ooo_handle;
+	u8 ll2_mpa_handle;
 	u8 peer2peer;
 	enum mpa_negotiation_mode mpa_rev;
 	enum mpa_rtr_type rtr_type;
+	struct qed_iwarp_fpdu *partial_fpdus;
+	struct qed_iwarp_ll2_mpa_buf *mpa_bufs;
+	u8 *mpa_intermediate_buf;
+	u16 max_num_partial_fpdus;
 };
 
 enum qed_iwarp_ep_state {
@@ -147,6 +186,9 @@ int qed_iwarp_alloc(struct qed_hwfn *p_hwfn);
 int qed_iwarp_setup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 		    struct qed_rdma_start_in_params *params);
 
+void qed_iwarp_init_fw_ramrod(struct qed_hwfn *p_hwfn,
+			      struct iwarp_init_func_params *p_ramrod);
+
 int qed_iwarp_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 
 void qed_iwarp_resc_free(struct qed_hwfn *p_hwfn);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index c06ad4f0758e..047f556ca62e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -413,6 +413,7 @@ static void qed_ll2_rxq_parse_reg(struct qed_hwfn *p_hwfn,
 				  struct qed_ll2_comp_rx_data *data)
 {
 	data->parse_flags = le16_to_cpu(p_cqe->rx_cqe_fp.parse_flags.flags);
+	data->err_flags = le16_to_cpu(p_cqe->rx_cqe_fp.err_flags.flags);
 	data->length.packet_length =
 	    le16_to_cpu(p_cqe->rx_cqe_fp.packet_length);
 	data->vlan = le16_to_cpu(p_cqe->rx_cqe_fp.vlan);
@@ -422,6 +423,41 @@ static void qed_ll2_rxq_parse_reg(struct qed_hwfn *p_hwfn,
 }
 
 static int
+qed_ll2_handle_slowpath(struct qed_hwfn *p_hwfn,
+			struct qed_ll2_info *p_ll2_conn,
+			union core_rx_cqe_union *p_cqe,
+			unsigned long *p_lock_flags)
+{
+	struct qed_ll2_rx_queue *p_rx = &p_ll2_conn->rx_queue;
+	struct core_rx_slow_path_cqe *sp_cqe;
+
+	sp_cqe = &p_cqe->rx_cqe_sp;
+	if (sp_cqe->ramrod_cmd_id != CORE_RAMROD_RX_QUEUE_FLUSH) {
+		DP_NOTICE(p_hwfn,
+			  "LL2 - unexpected Rx CQE slowpath ramrod_cmd_id:%d\n",
+			  sp_cqe->ramrod_cmd_id);
+		return -EINVAL;
+	}
+
+	if (!p_ll2_conn->cbs.slowpath_cb) {
+		DP_NOTICE(p_hwfn,
+			  "LL2 - received RX_QUEUE_FLUSH but no callback was provided\n");
+		return -EINVAL;
+	}
+
+	spin_unlock_irqrestore(&p_rx->lock, *p_lock_flags);
+
+	p_ll2_conn->cbs.slowpath_cb(p_ll2_conn->cbs.cookie,
+				    p_ll2_conn->my_id,
+				    le32_to_cpu(sp_cqe->opaque_data.data[0]),
+				    le32_to_cpu(sp_cqe->opaque_data.data[1]));
+
+	spin_lock_irqsave(&p_rx->lock, *p_lock_flags);
+
+	return 0;
+}
+
+static int
 qed_ll2_rxq_handle_completion(struct qed_hwfn *p_hwfn,
 			      struct qed_ll2_info *p_ll2_conn,
 			      union core_rx_cqe_union *p_cqe,
@@ -494,8 +530,8 @@ static int qed_ll2_rxq_completion(struct qed_hwfn *p_hwfn, void *cookie)
 
 		switch (cqe->rx_cqe_sp.type) {
 		case CORE_RX_CQE_TYPE_SLOW_PATH:
-			DP_NOTICE(p_hwfn, "LL2 - unexpected Rx CQE slowpath\n");
-			rc = -EINVAL;
+			rc = qed_ll2_handle_slowpath(p_hwfn, p_ll2_conn,
+						     cqe, &flags);
 			break;
 		case CORE_RX_CQE_TYPE_GSI_OFFLOAD:
 		case CORE_RX_CQE_TYPE_REGULAR:
@@ -893,7 +929,7 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn,
 	p_ramrod->drop_ttl0_flg = p_ll2_conn->input.rx_drop_ttl0_flg;
 	p_ramrod->inner_vlan_removal_en = p_ll2_conn->input.rx_vlan_removal_en;
 	p_ramrod->queue_id = p_ll2_conn->queue_id;
-	p_ramrod->main_func_queue = (conn_type == QED_LL2_TYPE_OOO) ? 0 : 1;
+	p_ramrod->main_func_queue = p_ll2_conn->main_func_queue ? 1 : 0;
 
 	if ((IS_MF_DEFAULT(p_hwfn) || IS_MF_SI(p_hwfn)) &&
 	    p_ramrod->main_func_queue && (conn_type != QED_LL2_TYPE_ROCE) &&
@@ -1104,6 +1140,7 @@ static int qed_ll2_acquire_connection_tx(struct qed_hwfn *p_hwfn,
 					 struct qed_ll2_info *p_ll2_info)
 {
 	struct qed_ll2_tx_packet *p_descq;
+	u32 desc_size;
 	u32 capacity;
 	int rc = 0;
 
@@ -1121,13 +1158,17 @@ static int qed_ll2_acquire_connection_tx(struct qed_hwfn *p_hwfn,
 		goto out;
 
 	capacity = qed_chain_get_capacity(&p_ll2_info->tx_queue.txq_chain);
-	p_descq = kcalloc(capacity, sizeof(struct qed_ll2_tx_packet),
-			  GFP_KERNEL);
+	/* First element is part of the packet, rest are flexibly added */
+	desc_size = (sizeof(*p_descq) +
+		     (p_ll2_info->input.tx_max_bds_per_packet - 1) *
+		     sizeof(p_descq->bds_set));
+
+	p_descq = kcalloc(capacity, desc_size, GFP_KERNEL);
 	if (!p_descq) {
 		rc = -ENOMEM;
 		goto out;
 	}
-	p_ll2_info->tx_queue.descq_array = p_descq;
+	p_ll2_info->tx_queue.descq_mem = p_descq;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_LL2,
 		   "Allocated LL2 Txq [Type %08x] with 0x%08x buffers\n",
@@ -1208,6 +1249,7 @@ qed_ll2_set_cbs(struct qed_ll2_info *p_ll2_info, const struct qed_ll2_cbs *cbs)
 	p_ll2_info->cbs.rx_release_cb = cbs->rx_release_cb;
 	p_ll2_info->cbs.tx_comp_cb = cbs->tx_comp_cb;
 	p_ll2_info->cbs.tx_release_cb = cbs->tx_release_cb;
+	p_ll2_info->cbs.slowpath_cb = cbs->slowpath_cb;
 	p_ll2_info->cbs.cookie = cbs->cookie;
 
 	return 0;
@@ -1259,6 +1301,11 @@ int qed_ll2_acquire_connection(void *cxt, struct qed_ll2_acquire_data *data)
 
 	p_ll2_info->tx_dest = (data->input.tx_dest == QED_LL2_TX_DEST_NW) ?
 			      CORE_TX_DEST_NW : CORE_TX_DEST_LB;
+	if (data->input.conn_type == QED_LL2_TYPE_OOO ||
+	    data->input.secondary_queue)
+		p_ll2_info->main_func_queue = false;
+	else
+		p_ll2_info->main_func_queue = true;
 
 	/* Correct maximum number of Tx BDs */
 	p_tx_max = &p_ll2_info->input.tx_max_bds_per_packet;
@@ -1358,11 +1405,13 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle)
 {
 	struct qed_hwfn *p_hwfn = cxt;
 	struct qed_ll2_info *p_ll2_conn;
+	struct qed_ll2_tx_packet *p_pkt;
 	struct qed_ll2_rx_queue *p_rx;
 	struct qed_ll2_tx_queue *p_tx;
 	struct qed_ptt *p_ptt;
 	int rc = -EINVAL;
 	u32 i, capacity;
+	u32 desc_size;
 	u8 qid;
 
 	p_ptt = qed_ptt_acquire(p_hwfn);
@@ -1396,9 +1445,15 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle)
 	INIT_LIST_HEAD(&p_tx->sending_descq);
 	spin_lock_init(&p_tx->lock);
 	capacity = qed_chain_get_capacity(&p_tx->txq_chain);
-	for (i = 0; i < capacity; i++)
-		list_add_tail(&p_tx->descq_array[i].list_entry,
-			      &p_tx->free_descq);
+	/* First element is part of the packet, rest are flexibly added */
+	desc_size = (sizeof(*p_pkt) +
+		     (p_ll2_conn->input.tx_max_bds_per_packet - 1) *
+		     sizeof(p_pkt->bds_set));
+
+	for (i = 0; i < capacity; i++) {
+		p_pkt = p_tx->descq_mem + desc_size * i;
+		list_add_tail(&p_pkt->list_entry, &p_tx->free_descq);
+	}
 	p_tx->cur_completing_bd_idx = 0;
 	p_tx->bds_idx = 0;
 	p_tx->b_completing_packet = false;
@@ -1578,11 +1633,28 @@ qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
 	roce_flavor = (pkt->qed_roce_flavor == QED_LL2_ROCE) ? CORE_ROCE
 							     : CORE_RROCE;
 
-	tx_dest = (pkt->tx_dest == QED_LL2_TX_DEST_NW) ? CORE_TX_DEST_NW
-						       : CORE_TX_DEST_LB;
+	switch (pkt->tx_dest) {
+	case QED_LL2_TX_DEST_NW:
+		tx_dest = CORE_TX_DEST_NW;
+		break;
+	case QED_LL2_TX_DEST_LB:
+		tx_dest = CORE_TX_DEST_LB;
+		break;
+	case QED_LL2_TX_DEST_DROP:
+		tx_dest = CORE_TX_DEST_DROP;
+		break;
+	default:
+		tx_dest = CORE_TX_DEST_LB;
+		break;
+	}
 
 	start_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain);
-	start_bd->nw_vlan_or_lb_echo = cpu_to_le16(pkt->vlan);
+	if (QED_IS_IWARP_PERSONALITY(p_hwfn) &&
+	    p_ll2->input.conn_type == QED_LL2_TYPE_OOO)
+		start_bd->nw_vlan_or_lb_echo =
+		    cpu_to_le16(IWARP_LL2_IN_ORDER_TX_QUEUE);
+	else
+		start_bd->nw_vlan_or_lb_echo = cpu_to_le16(pkt->vlan);
 	SET_FIELD(start_bd->bitfield1, CORE_TX_BD_L4_HDR_OFFSET_W,
 		  cpu_to_le16(pkt->l4_hdr_offset_w));
 	SET_FIELD(start_bd->bitfield1, CORE_TX_BD_TX_DST, tx_dest);
@@ -1590,6 +1662,9 @@ qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
 	SET_FIELD(bd_data, CORE_TX_BD_DATA_START_BD, 0x1);
 	SET_FIELD(bd_data, CORE_TX_BD_DATA_NBDS, pkt->num_of_bds);
 	SET_FIELD(bd_data, CORE_TX_BD_DATA_ROCE_FLAV, roce_flavor);
+	SET_FIELD(bd_data, CORE_TX_BD_DATA_IP_CSUM, !!(pkt->enable_ip_cksum));
+	SET_FIELD(bd_data, CORE_TX_BD_DATA_L4_CSUM, !!(pkt->enable_l4_cksum));
+	SET_FIELD(bd_data, CORE_TX_BD_DATA_IP_LEN, !!(pkt->calc_ip_len));
 	start_bd->bd_data.as_bitfield = cpu_to_le16(bd_data);
 	DMA_REGPAIR_LE(start_bd->addr, pkt->first_frag);
 	start_bd->nbytes = cpu_to_le16(pkt->first_frag_len);
@@ -1697,7 +1772,7 @@ int qed_ll2_prepare_tx_packet(void *cxt,
 	p_tx = &p_ll2_conn->tx_queue;
 	p_tx_chain = &p_tx->txq_chain;
 
-	if (pkt->num_of_bds > CORE_LL2_TX_MAX_BDS_PER_PACKET)
+	if (pkt->num_of_bds > p_ll2_conn->input.tx_max_bds_per_packet)
 		return -EIO;
 
 	spin_lock_irqsave(&p_tx->lock, flags);
@@ -1857,7 +1932,7 @@ void qed_ll2_release_connection(void *cxt, u8 connection_handle)
 		qed_int_unregister_cb(p_hwfn, p_ll2_conn->tx_queue.tx_sb_index);
 	}
 
-	kfree(p_ll2_conn->tx_queue.descq_array);
+	kfree(p_ll2_conn->tx_queue.descq_mem);
 	qed_chain_free(p_hwfn->cdev, &p_ll2_conn->tx_queue.txq_chain);
 
 	kfree(p_ll2_conn->rx_queue.descq_array);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
index a822528e9c63..f65817012e97 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
@@ -63,17 +63,14 @@ struct qed_ll2_rx_packet {
 struct qed_ll2_tx_packet {
 	struct list_head list_entry;
 	u16 bd_used;
-	u16 vlan;
-	u16 l4_hdr_offset_w;
-	u8 bd_flags;
 	bool notify_fw;
 	void *cookie;
-
+	/* Flexible Array of bds_set determined by max_bds_per_packet */
 	struct {
 		struct core_tx_bd *txq_bd;
 		dma_addr_t tx_frag;
 		u16 frag_len;
-	} bds_set[ETH_TX_MAX_BDS_PER_NON_LSO_PACKET];
+	} bds_set[1];
 };
 
 struct qed_ll2_rx_queue {
@@ -101,7 +98,7 @@ struct qed_ll2_tx_queue {
 	struct list_head active_descq;
 	struct list_head free_descq;
 	struct list_head sending_descq;
-	struct qed_ll2_tx_packet *descq_array;
+	void *descq_mem; /* memory for variable sized qed_ll2_tx_packet*/
 	struct qed_ll2_tx_packet *cur_send_packet;
 	struct qed_ll2_tx_packet cur_completing_packet;
 	u16 cur_completing_bd_idx;
@@ -124,6 +121,7 @@ struct qed_ll2_info {
 	bool b_active;
 	enum core_tx_dest tx_dest;
 	u8 tx_stats_en;
+	bool main_func_queue;
 	struct qed_ll2_rx_queue rx_queue;
 	struct qed_ll2_tx_queue tx_queue;
 	struct qed_ll2_cbs cbs;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 376485d99357..8b99c7d26f34 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1691,12 +1691,12 @@ qed_mcp_get_shmem_proto_mfw(struct qed_hwfn *p_hwfn,
 	case FW_MB_PARAM_GET_PF_RDMA_ROCE:
 		*p_proto = QED_PCI_ETH_ROCE;
 		break;
+	case FW_MB_PARAM_GET_PF_RDMA_IWARP:
+		*p_proto = QED_PCI_ETH_IWARP;
+		break;
 	case FW_MB_PARAM_GET_PF_RDMA_BOTH:
-		DP_NOTICE(p_hwfn,
-			  "Current day drivers don't support RoCE & iWARP. Default to RoCE-only\n");
-		*p_proto = QED_PCI_ETH_ROCE;
+		*p_proto = QED_PCI_ETH_RDMA;
 		break;
-	case FW_MB_PARAM_GET_PF_RDMA_IWARP:
 	default:
 		DP_NOTICE(p_hwfn,
 			  "MFW answers GET_PF_RDMA_PROTOCOL but param is %08x\n",
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
index 000636530111..6172354b451c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
@@ -103,18 +103,28 @@ int qed_ooo_alloc(struct qed_hwfn *p_hwfn)
 {
 	u16 max_num_archipelagos = 0, cid_base;
 	struct qed_ooo_info *p_ooo_info;
+	enum protocol_type proto;
 	u16 max_num_isles = 0;
 	u32 i;
 
-	if (p_hwfn->hw_info.personality != QED_PCI_ISCSI) {
+	switch (p_hwfn->hw_info.personality) {
+	case QED_PCI_ISCSI:
+		proto = PROTOCOLID_ISCSI;
+		break;
+	case QED_PCI_ETH_RDMA:
+	case QED_PCI_ETH_IWARP:
+		proto = PROTOCOLID_IWARP;
+		break;
+	default:
 		DP_NOTICE(p_hwfn,
 			  "Failed to allocate qed_ooo_info: unknown personality\n");
 		return -EINVAL;
 	}
 
-	max_num_archipelagos = p_hwfn->pf_params.iscsi_pf_params.num_cons;
+	max_num_archipelagos = (u16)qed_cxt_get_proto_cid_count(p_hwfn, proto,
+								NULL);
 	max_num_isles = QED_MAX_NUM_ISLES + max_num_archipelagos;
-	cid_base = (u16)qed_cxt_get_proto_cid_start(p_hwfn, PROTOCOLID_ISCSI);
+	cid_base = (u16)qed_cxt_get_proto_cid_start(p_hwfn, proto);
 
 	if (!max_num_archipelagos) {
 		DP_NOTICE(p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.h b/drivers/net/ethernet/qlogic/qed/qed_ooo.h
index e8ed40b848f5..49c4e75b15b1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.h
@@ -83,7 +83,7 @@ struct qed_ooo_info {
 	u16 cid_base;
 };
 
-#if IS_ENABLED(CONFIG_QED_ISCSI)
+#if IS_ENABLED(CONFIG_QED_OOO)
 void qed_ooo_save_history_entry(struct qed_hwfn *p_hwfn,
 				struct qed_ooo_info *p_ooo_info,
 				struct ooo_opaque *p_cqe);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 6fb99518a61f..c8c4b3940564 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -156,7 +156,10 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 		return rc;
 
 	p_hwfn->p_rdma_info = p_rdma_info;
-	p_rdma_info->proto = PROTOCOLID_ROCE;
+	if (QED_IS_IWARP_PERSONALITY(p_hwfn))
+		p_rdma_info->proto = PROTOCOLID_IWARP;
+	else
+		p_rdma_info->proto = PROTOCOLID_ROCE;
 
 	num_cons = qed_cxt_get_proto_cid_count(p_hwfn, p_rdma_info->proto,
 					       NULL);
@@ -206,11 +209,11 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 		goto free_pd_map;
 	}
 
-	/* Allocate bitmap for cq's. The maximum number of CQs is bounded to
-	 * twice the number of QPs.
+	/* Allocate bitmap for cq's. The maximum number of CQs is bound to
+	 * the number of connections we support. (num_qps in iWARP or
+	 * num_qps/2 in RoCE).
 	 */
-	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->cq_map,
-				 p_rdma_info->num_qps * 2, "CQ");
+	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->cq_map, num_cons, "CQ");
 	if (rc) {
 		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
 			   "Failed to allocate cq bitmap, rc = %d\n", rc);
@@ -219,10 +222,10 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 
 	/* Allocate bitmap for toggle bit for cq icids
 	 * We toggle the bit every time we create or resize cq for a given icid.
-	 * The maximum number of CQs is bounded to  twice the number of QPs.
+	 * Size needs to equal the size of the cq bmap.
 	 */
 	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->toggle_bits,
-				 p_rdma_info->num_qps * 2, "Toggle");
+				 num_cons, "Toggle");
 	if (rc) {
 		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
 			   "Failed to allocate toogle bits, rc = %d\n", rc);
@@ -548,10 +551,13 @@ static int qed_rdma_start_fw(struct qed_hwfn *p_hwfn,
 	if (rc)
 		return rc;
 
-	if (QED_IS_IWARP_PERSONALITY(p_hwfn))
+	if (QED_IS_IWARP_PERSONALITY(p_hwfn)) {
+		qed_iwarp_init_fw_ramrod(p_hwfn,
+					 &p_ent->ramrod.iwarp_init_func.iwarp);
 		p_ramrod = &p_ent->ramrod.iwarp_init_func.rdma;
-	else
+	} else {
 		p_ramrod = &p_ent->ramrod.roce_init_func.rdma;
+	}
 
 	p_params_header = &p_ramrod->params_header;
 	p_params_header->cnq_start_offset = (u8)RESC_START(p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
index 46d0c3cb83a5..a1d33f35aad3 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
@@ -377,6 +377,7 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn,
 		p_ramrod->personality = PERSONALITY_ISCSI;
 		break;
 	case QED_PCI_ETH_ROCE:
+	case QED_PCI_ETH_IWARP:
 		p_ramrod->personality = PERSONALITY_RDMA_AND_ETH;
 		break;
 	default:
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 6fc854b120b0..48ec4c56cddf 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1004,6 +1004,7 @@ static bool qede_rx_xdp(struct qede_dev *edev,
 
 	xdp.data_hard_start = page_address(bd->data);
 	xdp.data = xdp.data_hard_start + *data_offset;
+	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = xdp.data + *len;
 
 	/* Queues always have a full reset currently, so for the time
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 2991179c2fd0..05479d435469 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -3891,10 +3891,8 @@ static int ql3xxx_probe(struct pci_dev *pdev,
 	INIT_DELAYED_WORK(&qdev->tx_timeout_work, ql_tx_timeout_work);
 	INIT_DELAYED_WORK(&qdev->link_state_work, ql_link_state_machine_work);
 
-	init_timer(&qdev->adapter_timer);
-	qdev->adapter_timer.function = ql3xxx_timer;
+	setup_timer(&qdev->adapter_timer, ql3xxx_timer, (unsigned long)qdev);
 	qdev->adapter_timer.expires = jiffies + HZ * 2;	/* two second delay */
-	qdev->adapter_timer.data = (unsigned long)qdev;
 
 	if (!cards_found) {
 		pr_alert("%s\n", DRV_STRING);
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index 3ed9033e56db..9cbb27263742 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -309,22 +309,12 @@ void emac_mac_mode_config(struct emac_adapter *adpt)
 /* Config descriptor rings */
 static void emac_mac_dma_rings_config(struct emac_adapter *adpt)
 {
-	static const unsigned short tpd_q_offset[] = {
-		EMAC_DESC_CTRL_8,        EMAC_H1TPD_BASE_ADDR_LO,
-		EMAC_H2TPD_BASE_ADDR_LO, EMAC_H3TPD_BASE_ADDR_LO};
-	static const unsigned short rfd_q_offset[] = {
-		EMAC_DESC_CTRL_2,        EMAC_DESC_CTRL_10,
-		EMAC_DESC_CTRL_12,       EMAC_DESC_CTRL_13};
-	static const unsigned short rrd_q_offset[] = {
-		EMAC_DESC_CTRL_5,        EMAC_DESC_CTRL_14,
-		EMAC_DESC_CTRL_15,       EMAC_DESC_CTRL_16};
-
 	/* TPD (Transmit Packet Descriptor) */
 	writel(upper_32_bits(adpt->tx_q.tpd.dma_addr),
 	       adpt->base + EMAC_DESC_CTRL_1);
 
 	writel(lower_32_bits(adpt->tx_q.tpd.dma_addr),
-	       adpt->base + tpd_q_offset[0]);
+	       adpt->base + EMAC_DESC_CTRL_8);
 
 	writel(adpt->tx_q.tpd.count & TPD_RING_SIZE_BMSK,
 	       adpt->base + EMAC_DESC_CTRL_9);
@@ -334,9 +324,9 @@ static void emac_mac_dma_rings_config(struct emac_adapter *adpt)
 	       adpt->base + EMAC_DESC_CTRL_0);
 
 	writel(lower_32_bits(adpt->rx_q.rfd.dma_addr),
-	       adpt->base + rfd_q_offset[0]);
+	       adpt->base + EMAC_DESC_CTRL_2);
 	writel(lower_32_bits(adpt->rx_q.rrd.dma_addr),
-	       adpt->base + rrd_q_offset[0]);
+	       adpt->base + EMAC_DESC_CTRL_5);
 
 	writel(adpt->rx_q.rfd.count & RFD_RING_SIZE_BMSK,
 	       adpt->base + EMAC_DESC_CTRL_3);
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
index 29ba37a08372..e8ab512ee7e3 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
@@ -68,10 +68,10 @@ static void emac_sgmii_link_init(struct emac_adapter *adpt)
 	writel(val, phy->base + EMAC_SGMII_PHY_AUTONEG_CFG2);
 }
 
-static int emac_sgmii_irq_clear(struct emac_adapter *adpt, u32 irq_bits)
+static int emac_sgmii_irq_clear(struct emac_adapter *adpt, u8 irq_bits)
 {
 	struct emac_sgmii *phy = &adpt->phy;
-	u32 status;
+	u8 status;
 
 	writel_relaxed(irq_bits, phy->base + EMAC_SGMII_PHY_INTERRUPT_CLEAR);
 	writel_relaxed(IRQ_GLOBAL_CLEAR, phy->base + EMAC_SGMII_PHY_IRQ_CMD);
@@ -86,9 +86,8 @@ static int emac_sgmii_irq_clear(struct emac_adapter *adpt, u32 irq_bits)
 				      EMAC_SGMII_PHY_INTERRUPT_STATUS,
 				      status, !(status & irq_bits), 1,
 				      SGMII_PHY_IRQ_CLR_WAIT_TIME)) {
-		netdev_err(adpt->netdev,
-			   "error: failed clear SGMII irq: status:0x%x bits:0x%x\n",
-			   status, irq_bits);
+		net_err_ratelimited("%s: failed to clear SGMII irq: status:0x%x bits:0x%x\n",
+				    adpt->netdev->name, status, irq_bits);
 		return -EIO;
 	}
 
@@ -109,7 +108,7 @@ static irqreturn_t emac_sgmii_interrupt(int irq, void *data)
 {
 	struct emac_adapter *adpt = data;
 	struct emac_sgmii *phy = &adpt->phy;
-	u32 status;
+	u8 status;
 
 	status = readl(phy->base + EMAC_SGMII_PHY_INTERRUPT_STATUS);
 	status &= SGMII_ISR_MASK;
@@ -139,10 +138,8 @@ static irqreturn_t emac_sgmii_interrupt(int irq, void *data)
 		atomic_set(&phy->decode_error_count, 0);
 	}
 
-	if (emac_sgmii_irq_clear(adpt, status)) {
-		netdev_warn(adpt->netdev, "failed to clear SGMII interrupt\n");
+	if (emac_sgmii_irq_clear(adpt, status))
 		schedule_work(&adpt->work_thread);
-	}
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index 759543512117..70c92b649b29 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -130,7 +130,7 @@ static int emac_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	return emac_mac_tx_buf_send(adpt, &adpt->tx_q, skb);
 }
 
-irqreturn_t emac_isr(int _irq, void *data)
+static irqreturn_t emac_isr(int _irq, void *data)
 {
 	struct emac_irq *irq = data;
 	struct emac_adapter *adpt =
@@ -148,9 +148,8 @@ irqreturn_t emac_isr(int _irq, void *data)
 		goto exit;
 
 	if (status & ISR_ERROR) {
-		netif_warn(adpt,  intr, adpt->netdev,
-			   "warning: error irq status 0x%lx\n",
-			   status & ISR_ERROR);
+		net_err_ratelimited("%s: error interrupt 0x%lx\n",
+				    adpt->netdev->name, status & ISR_ERROR);
 		/* reset MAC */
 		schedule_work(&adpt->work_thread);
 	}
@@ -169,7 +168,8 @@ irqreturn_t emac_isr(int _irq, void *data)
 		emac_mac_tx_process(adpt, &adpt->tx_q);
 
 	if (status & ISR_OVER)
-		net_warn_ratelimited("warning: TX/RX overflow\n");
+		net_warn_ratelimited("%s: TX/RX overflow interrupt\n",
+				     adpt->netdev->name);
 
 exit:
 	/* enable the interrupt */
@@ -615,20 +615,11 @@ static int emac_probe(struct platform_device *pdev)
 	u32 reg;
 	int ret;
 
-	/* The EMAC itself is capable of 64-bit DMA, so try that first. */
-	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	/* The TPD buffer address is limited to 45 bits. */
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(45));
 	if (ret) {
-		/* Some platforms may restrict the EMAC's address bus to less
-		 * then the size of DDR. In this case, we need to try a
-		 * smaller mask.  We could try every possible smaller mask,
-		 * but that's overkill.  Instead, just fall to 32-bit, which
-		 * should always work.
-		 */
-		ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
-		if (ret) {
-			dev_err(&pdev->dev, "could not set DMA mask\n");
-			return ret;
-		}
+		dev_err(&pdev->dev, "could not set DMA mask\n");
+		return ret;
 	}
 
 	netdev = alloc_etherdev(sizeof(struct emac_adapter));
diff --git a/drivers/net/ethernet/qualcomm/rmnet/Kconfig b/drivers/net/ethernet/qualcomm/rmnet/Kconfig
index 6e2587af47a4..9bb06d284644 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/Kconfig
+++ b/drivers/net/ethernet/qualcomm/rmnet/Kconfig
@@ -5,6 +5,7 @@
 menuconfig RMNET
 	tristate "RmNet MAP driver"
 	default n
+	select GRO_CELLS
 	---help---
 	  If you select this, you will enable the RMNET module which is used
 	  for handling data in the multiplexing and aggregation protocol (MAP)
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 1e33aea59f50..71bee1af71ef 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -61,23 +61,6 @@ rmnet_get_port_rtnl(const struct net_device *real_dev)
 	return rtnl_dereference(real_dev->rx_handler_data);
 }
 
-static struct rmnet_endpoint*
-rmnet_get_endpoint(struct net_device *dev, int config_id)
-{
-	struct rmnet_endpoint *ep;
-	struct rmnet_port *port;
-
-	if (!rmnet_is_real_dev_registered(dev)) {
-		ep = rmnet_vnd_get_endpoint(dev);
-	} else {
-		port = rmnet_get_port_rtnl(dev);
-
-		ep = &port->muxed_ep[config_id];
-	}
-
-	return ep;
-}
-
 static int rmnet_unregister_real_device(struct net_device *real_dev,
 					struct rmnet_port *port)
 {
@@ -98,7 +81,7 @@ static int rmnet_unregister_real_device(struct net_device *real_dev,
 static int rmnet_register_real_device(struct net_device *real_dev)
 {
 	struct rmnet_port *port;
-	int rc;
+	int rc, entry;
 
 	ASSERT_RTNL();
 
@@ -119,27 +102,41 @@ static int rmnet_register_real_device(struct net_device *real_dev)
 	/* hold on to real dev for MAP data */
 	dev_hold(real_dev);
 
+	for (entry = 0; entry < RMNET_MAX_LOGICAL_EP; entry++)
+		INIT_HLIST_HEAD(&port->muxed_ep[entry]);
+
 	netdev_dbg(real_dev, "registered with rmnet\n");
 	return 0;
 }
 
-static void rmnet_set_endpoint_config(struct net_device *dev,
-				      u8 mux_id, u8 rmnet_mode,
-				      struct net_device *egress_dev)
+static void rmnet_unregister_bridge(struct net_device *dev,
+				    struct rmnet_port *port)
 {
-	struct rmnet_endpoint *ep;
+	struct net_device *rmnet_dev, *bridge_dev;
+	struct rmnet_port *bridge_port;
+
+	if (port->rmnet_mode != RMNET_EPMODE_BRIDGE)
+		return;
 
-	netdev_dbg(dev, "id %d mode %d dev %s\n",
-		   mux_id, rmnet_mode, egress_dev->name);
+	/* bridge slave handling */
+	if (!port->nr_rmnet_devs) {
+		rmnet_dev = netdev_master_upper_dev_get_rcu(dev);
+		netdev_upper_dev_unlink(dev, rmnet_dev);
 
-	ep = rmnet_get_endpoint(dev, mux_id);
-	/* This config is cleared on every set, so its ok to not
-	 * clear it on a device delete.
-	 */
-	memset(ep, 0, sizeof(struct rmnet_endpoint));
-	ep->rmnet_mode = rmnet_mode;
-	ep->egress_dev = egress_dev;
-	ep->mux_id = mux_id;
+		bridge_dev = port->bridge_ep;
+
+		bridge_port = rmnet_get_port_rtnl(bridge_dev);
+		bridge_port->bridge_ep = NULL;
+		bridge_port->rmnet_mode = RMNET_EPMODE_VND;
+	} else {
+		bridge_dev = port->bridge_ep;
+
+		bridge_port = rmnet_get_port_rtnl(bridge_dev);
+		rmnet_dev = netdev_master_upper_dev_get_rcu(bridge_dev);
+		netdev_upper_dev_unlink(bridge_dev, rmnet_dev);
+
+		rmnet_unregister_real_device(bridge_dev, bridge_port);
+	}
 }
 
 static int rmnet_newlink(struct net *src_net, struct net_device *dev,
@@ -153,6 +150,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev,
 			    RMNET_EGRESS_FORMAT_MAP;
 	struct net_device *real_dev;
 	int mode = RMNET_EPMODE_VND;
+	struct rmnet_endpoint *ep;
 	struct rmnet_port *port;
 	int err = 0;
 	u16 mux_id;
@@ -164,6 +162,10 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev,
 	if (!data[IFLA_VLAN_ID])
 		return -EINVAL;
 
+	ep = kzalloc(sizeof(*ep), GFP_ATOMIC);
+	if (!ep)
+		return -ENOMEM;
+
 	mux_id = nla_get_u16(data[IFLA_VLAN_ID]);
 
 	err = rmnet_register_real_device(real_dev);
@@ -171,11 +173,11 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev,
 		goto err0;
 
 	port = rmnet_get_port_rtnl(real_dev);
-	err = rmnet_vnd_newlink(mux_id, dev, port, real_dev);
+	err = rmnet_vnd_newlink(mux_id, dev, port, real_dev, ep);
 	if (err)
 		goto err1;
 
-	err = netdev_master_upper_dev_link(dev, real_dev, NULL, NULL);
+	err = netdev_master_upper_dev_link(dev, real_dev, NULL, NULL, extack);
 	if (err)
 		goto err2;
 
@@ -183,13 +185,13 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev,
 		   ingress_format, egress_format);
 	port->egress_data_format = egress_format;
 	port->ingress_data_format = ingress_format;
+	port->rmnet_mode = mode;
 
-	rmnet_set_endpoint_config(real_dev, mux_id, mode, dev);
-	rmnet_set_endpoint_config(dev, mux_id, mode, real_dev);
+	hlist_add_head_rcu(&ep->hlnode, &port->muxed_ep[mux_id]);
 	return 0;
 
 err2:
-	rmnet_vnd_dellink(mux_id, port);
+	rmnet_vnd_dellink(mux_id, port, ep);
 err1:
 	rmnet_unregister_real_device(real_dev, port);
 err0:
@@ -199,6 +201,7 @@ err0:
 static void rmnet_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct net_device *real_dev;
+	struct rmnet_endpoint *ep;
 	struct rmnet_port *port;
 	u8 mux_id;
 
@@ -212,8 +215,15 @@ static void rmnet_dellink(struct net_device *dev, struct list_head *head)
 	port = rmnet_get_port_rtnl(real_dev);
 
 	mux_id = rmnet_vnd_get_mux(dev);
-	rmnet_vnd_dellink(mux_id, port);
 	netdev_upper_dev_unlink(dev, real_dev);
+
+	ep = rmnet_get_endpoint(port, mux_id);
+	if (ep) {
+		hlist_del_init_rcu(&ep->hlnode);
+		rmnet_unregister_bridge(dev, port);
+		rmnet_vnd_dellink(mux_id, port, ep);
+		kfree(ep);
+	}
 	rmnet_unregister_real_device(real_dev, port);
 
 	unregister_netdevice_queue(dev, head);
@@ -222,11 +232,16 @@ static void rmnet_dellink(struct net_device *dev, struct list_head *head)
 static int rmnet_dev_walk_unreg(struct net_device *rmnet_dev, void *data)
 {
 	struct rmnet_walk_data *d = data;
+	struct rmnet_endpoint *ep;
 	u8 mux_id;
 
 	mux_id = rmnet_vnd_get_mux(rmnet_dev);
-
-	rmnet_vnd_dellink(mux_id, d->port);
+	ep = rmnet_get_endpoint(d->port, mux_id);
+	if (ep) {
+		hlist_del_init_rcu(&ep->hlnode);
+		rmnet_vnd_dellink(mux_id, d->port, ep);
+		kfree(ep);
+	}
 	netdev_upper_dev_unlink(rmnet_dev, d->real_dev);
 	unregister_netdevice_queue(rmnet_dev, d->head);
 
@@ -252,6 +267,8 @@ static void rmnet_force_unassociate_device(struct net_device *dev)
 	d.port = port;
 
 	rcu_read_lock();
+	rmnet_unregister_bridge(dev, port);
+
 	netdev_walk_all_lower_dev_rcu(real_dev, rmnet_dev_walk_unreg, &d);
 	rcu_read_unlock();
 	unregister_netdevice_many(&list);
@@ -324,6 +341,77 @@ struct rmnet_port *rmnet_get_port(struct net_device *real_dev)
 		return NULL;
 }
 
+struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id)
+{
+	struct rmnet_endpoint *ep;
+
+	hlist_for_each_entry_rcu(ep, &port->muxed_ep[mux_id], hlnode) {
+		if (ep->mux_id == mux_id)
+			return ep;
+	}
+
+	return NULL;
+}
+
+int rmnet_add_bridge(struct net_device *rmnet_dev,
+		     struct net_device *slave_dev,
+		     struct netlink_ext_ack *extack)
+{
+	struct rmnet_priv *priv = netdev_priv(rmnet_dev);
+	struct net_device *real_dev = priv->real_dev;
+	struct rmnet_port *port, *slave_port;
+	int err;
+
+	port = rmnet_get_port(real_dev);
+
+	/* If there is more than one rmnet dev attached, its probably being
+	 * used for muxing. Skip the briding in that case
+	 */
+	if (port->nr_rmnet_devs > 1)
+		return -EINVAL;
+
+	if (rmnet_is_real_dev_registered(slave_dev))
+		return -EBUSY;
+
+	err = rmnet_register_real_device(slave_dev);
+	if (err)
+		return -EBUSY;
+
+	err = netdev_master_upper_dev_link(slave_dev, rmnet_dev, NULL, NULL,
+					   extack);
+	if (err)
+		return -EINVAL;
+
+	slave_port = rmnet_get_port(slave_dev);
+	slave_port->rmnet_mode = RMNET_EPMODE_BRIDGE;
+	slave_port->bridge_ep = real_dev;
+
+	port->rmnet_mode = RMNET_EPMODE_BRIDGE;
+	port->bridge_ep = slave_dev;
+
+	netdev_dbg(slave_dev, "registered with rmnet as slave\n");
+	return 0;
+}
+
+int rmnet_del_bridge(struct net_device *rmnet_dev,
+		     struct net_device *slave_dev)
+{
+	struct rmnet_priv *priv = netdev_priv(rmnet_dev);
+	struct net_device *real_dev = priv->real_dev;
+	struct rmnet_port *port, *slave_port;
+
+	port = rmnet_get_port(real_dev);
+	port->rmnet_mode = RMNET_EPMODE_VND;
+	port->bridge_ep = NULL;
+
+	netdev_upper_dev_unlink(slave_dev, rmnet_dev);
+	slave_port = rmnet_get_port(slave_dev);
+	rmnet_unregister_real_device(slave_dev, slave_port);
+
+	netdev_dbg(slave_dev, "removed from rmnet as slave\n");
+	return 0;
+}
+
 /* Startup/Shutdown */
 
 static int __init rmnet_init(void)
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
index dde4e9f14f4a..c19259eea99e 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
@@ -14,19 +14,17 @@
  */
 
 #include <linux/skbuff.h>
+#include <net/gro_cells.h>
 
 #ifndef _RMNET_CONFIG_H_
 #define _RMNET_CONFIG_H_
 
 #define RMNET_MAX_LOGICAL_EP 255
 
-/* Information about the next device to deliver the packet to.
- * Exact usage of this parameter depends on the rmnet_mode.
- */
 struct rmnet_endpoint {
-	u8 rmnet_mode;
 	u8 mux_id;
 	struct net_device *egress_dev;
+	struct hlist_node hlnode;
 };
 
 /* One instance of this structure is instantiated for each real_dev associated
@@ -34,22 +32,41 @@ struct rmnet_endpoint {
  */
 struct rmnet_port {
 	struct net_device *dev;
-	struct rmnet_endpoint local_ep;
-	struct rmnet_endpoint muxed_ep[RMNET_MAX_LOGICAL_EP];
 	u32 ingress_data_format;
 	u32 egress_data_format;
-	struct net_device *rmnet_devices[RMNET_MAX_LOGICAL_EP];
 	u8 nr_rmnet_devs;
+	u8 rmnet_mode;
+	struct hlist_head muxed_ep[RMNET_MAX_LOGICAL_EP];
+	struct net_device *bridge_ep;
 };
 
 extern struct rtnl_link_ops rmnet_link_ops;
 
+struct rmnet_vnd_stats {
+	u64 rx_pkts;
+	u64 rx_bytes;
+	u64 tx_pkts;
+	u64 tx_bytes;
+	u32 tx_drops;
+};
+
+struct rmnet_pcpu_stats {
+	struct rmnet_vnd_stats stats;
+	struct u64_stats_sync syncp;
+};
+
 struct rmnet_priv {
-	struct rmnet_endpoint local_ep;
 	u8 mux_id;
 	struct net_device *real_dev;
+	struct rmnet_pcpu_stats __percpu *pcpu_stats;
+	struct gro_cells gro_cells;
 };
 
 struct rmnet_port *rmnet_get_port(struct net_device *real_dev);
-
+struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id);
+int rmnet_add_bridge(struct net_device *rmnet_dev,
+		     struct net_device *slave_dev,
+		     struct netlink_ext_ack *extack);
+int rmnet_del_bridge(struct net_device *rmnet_dev,
+		     struct net_device *slave_dev);
 #endif /* _RMNET_CONFIG_H_ */
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
index 540c7622dcb1..29842ccc91a9 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
@@ -43,60 +43,23 @@ static void rmnet_set_skb_proto(struct sk_buff *skb)
 
 /* Generic handler */
 
-static rx_handler_result_t
-rmnet_bridge_handler(struct sk_buff *skb, struct rmnet_endpoint *ep)
+static void
+rmnet_deliver_skb(struct sk_buff *skb)
 {
-	if (!ep->egress_dev)
-		kfree_skb(skb);
-	else
-		rmnet_egress_handler(skb, ep);
-
-	return RX_HANDLER_CONSUMED;
-}
-
-static rx_handler_result_t
-rmnet_deliver_skb(struct sk_buff *skb, struct rmnet_endpoint *ep)
-{
-	switch (ep->rmnet_mode) {
-	case RMNET_EPMODE_NONE:
-		return RX_HANDLER_PASS;
-
-	case RMNET_EPMODE_BRIDGE:
-		return rmnet_bridge_handler(skb, ep);
-
-	case RMNET_EPMODE_VND:
-		skb_reset_transport_header(skb);
-		skb_reset_network_header(skb);
-		rmnet_vnd_rx_fixup(skb, skb->dev);
-
-		skb->pkt_type = PACKET_HOST;
-		skb_set_mac_header(skb, 0);
-		netif_receive_skb(skb);
-		return RX_HANDLER_CONSUMED;
-
-	default:
-		kfree_skb(skb);
-		return RX_HANDLER_CONSUMED;
-	}
-}
-
-static rx_handler_result_t
-rmnet_ingress_deliver_packet(struct sk_buff *skb,
-			     struct rmnet_port *port)
-{
-	if (!port) {
-		kfree_skb(skb);
-		return RX_HANDLER_CONSUMED;
-	}
+	struct rmnet_priv *priv = netdev_priv(skb->dev);
 
-	skb->dev = port->local_ep.egress_dev;
+	skb_reset_transport_header(skb);
+	skb_reset_network_header(skb);
+	rmnet_vnd_rx_fixup(skb, skb->dev);
 
-	return rmnet_deliver_skb(skb, &port->local_ep);
+	skb->pkt_type = PACKET_HOST;
+	skb_set_mac_header(skb, 0);
+	gro_cells_receive(&priv->gro_cells, skb);
 }
 
 /* MAP handler */
 
-static rx_handler_result_t
+static void
 __rmnet_map_ingress_handler(struct sk_buff *skb,
 			    struct rmnet_port *port)
 {
@@ -109,53 +72,50 @@ __rmnet_map_ingress_handler(struct sk_buff *skb,
 		    & RMNET_INGRESS_FORMAT_MAP_COMMANDS)
 			return rmnet_map_command(skb, port);
 
-		kfree_skb(skb);
-		return RX_HANDLER_CONSUMED;
+		goto free_skb;
 	}
 
 	mux_id = RMNET_MAP_GET_MUX_ID(skb);
 	len = RMNET_MAP_GET_LENGTH(skb) - RMNET_MAP_GET_PAD(skb);
 
-	if (mux_id >= RMNET_MAX_LOGICAL_EP) {
-		kfree_skb(skb);
-		return RX_HANDLER_CONSUMED;
-	}
+	if (mux_id >= RMNET_MAX_LOGICAL_EP)
+		goto free_skb;
 
-	ep = &port->muxed_ep[mux_id];
+	ep = rmnet_get_endpoint(port, mux_id);
+	if (!ep)
+		goto free_skb;
 
-	if (port->ingress_data_format & RMNET_INGRESS_FORMAT_DEMUXING)
-		skb->dev = ep->egress_dev;
+	skb->dev = ep->egress_dev;
 
 	/* Subtract MAP header */
 	skb_pull(skb, sizeof(struct rmnet_map_header));
 	skb_trim(skb, len);
 	rmnet_set_skb_proto(skb);
-	return rmnet_deliver_skb(skb, ep);
+	rmnet_deliver_skb(skb);
+	return;
+
+free_skb:
+	kfree_skb(skb);
 }
 
-static rx_handler_result_t
+static void
 rmnet_map_ingress_handler(struct sk_buff *skb,
 			  struct rmnet_port *port)
 {
 	struct sk_buff *skbn;
-	int rc;
 
 	if (port->ingress_data_format & RMNET_INGRESS_FORMAT_DEAGGREGATION) {
 		while ((skbn = rmnet_map_deaggregate(skb)) != NULL)
 			__rmnet_map_ingress_handler(skbn, port);
 
 		consume_skb(skb);
-		rc = RX_HANDLER_CONSUMED;
 	} else {
-		rc = __rmnet_map_ingress_handler(skb, port);
+		__rmnet_map_ingress_handler(skb, port);
 	}
-
-	return rc;
 }
 
 static int rmnet_map_egress_handler(struct sk_buff *skb,
-				    struct rmnet_port *port,
-				    struct rmnet_endpoint *ep,
+				    struct rmnet_port *port, u8 mux_id,
 				    struct net_device *orig_dev)
 {
 	int required_headroom, additional_header_len;
@@ -174,10 +134,10 @@ static int rmnet_map_egress_handler(struct sk_buff *skb,
 		return RMNET_MAP_CONSUMED;
 
 	if (port->egress_data_format & RMNET_EGRESS_FORMAT_MUXING) {
-		if (ep->mux_id == 0xff)
+		if (mux_id == 0xff)
 			map_header->mux_id = 0;
 		else
-			map_header->mux_id = ep->mux_id;
+			map_header->mux_id = mux_id;
 	}
 
 	skb->protocol = htons(ETH_P_MAP);
@@ -185,6 +145,15 @@ static int rmnet_map_egress_handler(struct sk_buff *skb,
 	return RMNET_MAP_SUCCESS;
 }
 
+static void
+rmnet_bridge_handler(struct sk_buff *skb, struct net_device *bridge_dev)
+{
+	if (bridge_dev) {
+		skb->dev = bridge_dev;
+		dev_queue_xmit(skb);
+	}
+}
+
 /* Ingress / Egress Entry Points */
 
 /* Processes packet as per ingress data format for receiving device. Logical
@@ -193,56 +162,45 @@ static int rmnet_map_egress_handler(struct sk_buff *skb,
  */
 rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb)
 {
-	struct rmnet_port *port;
 	struct sk_buff *skb = *pskb;
+	struct rmnet_port *port;
 	struct net_device *dev;
-	int rc;
 
 	if (!skb)
-		return RX_HANDLER_CONSUMED;
+		goto done;
 
 	dev = skb->dev;
 	port = rmnet_get_port(dev);
 
-	if (port->ingress_data_format & RMNET_INGRESS_FORMAT_MAP) {
-		rc = rmnet_map_ingress_handler(skb, port);
-	} else {
-		switch (ntohs(skb->protocol)) {
-		case ETH_P_MAP:
-			if (port->local_ep.rmnet_mode ==
-				RMNET_EPMODE_BRIDGE) {
-				rc = rmnet_ingress_deliver_packet(skb, port);
-			} else {
-				kfree_skb(skb);
-				rc = RX_HANDLER_CONSUMED;
-			}
-			break;
-
-		case ETH_P_IP:
-		case ETH_P_IPV6:
-			rc = rmnet_ingress_deliver_packet(skb, port);
-			break;
-
-		default:
-			rc = RX_HANDLER_PASS;
-		}
+	switch (port->rmnet_mode) {
+	case RMNET_EPMODE_VND:
+		if (port->ingress_data_format & RMNET_INGRESS_FORMAT_MAP)
+			rmnet_map_ingress_handler(skb, port);
+		break;
+	case RMNET_EPMODE_BRIDGE:
+		rmnet_bridge_handler(skb, port->bridge_ep);
+		break;
 	}
 
-	return rc;
+done:
+	return RX_HANDLER_CONSUMED;
 }
 
 /* Modifies packet as per logical endpoint configuration and egress data format
  * for egress device configured in logical endpoint. Packet is then transmitted
  * on the egress device.
  */
-void rmnet_egress_handler(struct sk_buff *skb,
-			  struct rmnet_endpoint *ep)
+void rmnet_egress_handler(struct sk_buff *skb)
 {
 	struct net_device *orig_dev;
 	struct rmnet_port *port;
+	struct rmnet_priv *priv;
+	u8 mux_id;
 
 	orig_dev = skb->dev;
-	skb->dev = ep->egress_dev;
+	priv = netdev_priv(orig_dev);
+	skb->dev = priv->real_dev;
+	mux_id = priv->mux_id;
 
 	port = rmnet_get_port(skb->dev);
 	if (!port) {
@@ -251,7 +209,7 @@ void rmnet_egress_handler(struct sk_buff *skb,
 	}
 
 	if (port->egress_data_format & RMNET_EGRESS_FORMAT_MAP) {
-		switch (rmnet_map_egress_handler(skb, port, ep, orig_dev)) {
+		switch (rmnet_map_egress_handler(skb, port, mux_id, orig_dev)) {
 		case RMNET_MAP_CONSUMED:
 			return;
 
@@ -264,8 +222,7 @@ void rmnet_egress_handler(struct sk_buff *skb,
 		}
 	}
 
-	if (ep->rmnet_mode == RMNET_EPMODE_VND)
-		rmnet_vnd_tx_fixup(skb, orig_dev);
+	rmnet_vnd_tx_fixup(skb, orig_dev);
 
 	dev_queue_xmit(skb);
 }
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h
index f2638cf5693c..3537e4ceedb3 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h
@@ -18,8 +18,7 @@
 
 #include "rmnet_config.h"
 
-void rmnet_egress_handler(struct sk_buff *skb,
-			  struct rmnet_endpoint *ep);
+void rmnet_egress_handler(struct sk_buff *skb);
 
 rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb);
 
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
index ce2302c25b12..3af3fe7b5457 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
@@ -80,7 +80,6 @@ u8 rmnet_map_demultiplex(struct sk_buff *skb);
 struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb);
 struct rmnet_map_header *rmnet_map_add_map_header(struct sk_buff *skb,
 						  int hdrlen, int pad);
-rx_handler_result_t rmnet_map_command(struct sk_buff *skb,
-				      struct rmnet_port *port);
+void rmnet_map_command(struct sk_buff *skb, struct rmnet_port *port);
 
 #endif /* _RMNET_MAP_H_ */
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
index d1ea5e21b982..51e604923ac1 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
@@ -17,7 +17,7 @@
 #include "rmnet_vnd.h"
 
 static u8 rmnet_map_do_flow_control(struct sk_buff *skb,
-				    struct rmnet_port *rdinfo,
+				    struct rmnet_port *port,
 				    int enable)
 {
 	struct rmnet_map_control_command *cmd;
@@ -37,7 +37,7 @@ static u8 rmnet_map_do_flow_control(struct sk_buff *skb,
 		return RX_HANDLER_CONSUMED;
 	}
 
-	ep = &rdinfo->muxed_ep[mux_id];
+	ep = rmnet_get_endpoint(port, mux_id);
 	vnd = ep->egress_dev;
 
 	ip_family = cmd->flow_control.ip_family;
@@ -76,8 +76,7 @@ static void rmnet_map_send_ack(struct sk_buff *skb,
 /* Process MAP command frame and send N/ACK message as appropriate. Message cmd
  * name is decoded here and appropriate handler is called.
  */
-rx_handler_result_t rmnet_map_command(struct sk_buff *skb,
-				      struct rmnet_port *port)
+void rmnet_map_command(struct sk_buff *skb, struct rmnet_port *port)
 {
 	struct rmnet_map_control_command *cmd;
 	unsigned char command_name;
@@ -102,5 +101,4 @@ rx_handler_result_t rmnet_map_command(struct sk_buff *skb,
 	}
 	if (rc == RMNET_MAP_COMMAND_ACK)
 		rmnet_map_send_ack(skb, rc);
-	return RX_HANDLER_CONSUMED;
 }
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h
index 7967198fdd90..49102f922b31 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h
@@ -19,23 +19,15 @@
 #define RMNET_TX_QUEUE_LEN         1000
 
 /* Constants */
-#define RMNET_EGRESS_FORMAT__RESERVED__         BIT(0)
 #define RMNET_EGRESS_FORMAT_MAP                 BIT(1)
 #define RMNET_EGRESS_FORMAT_AGGREGATION         BIT(2)
 #define RMNET_EGRESS_FORMAT_MUXING              BIT(3)
-#define RMNET_EGRESS_FORMAT_MAP_CKSUMV3         BIT(4)
-#define RMNET_EGRESS_FORMAT_MAP_CKSUMV4         BIT(5)
 
-#define RMNET_INGRESS_FIX_ETHERNET              BIT(0)
 #define RMNET_INGRESS_FORMAT_MAP                BIT(1)
 #define RMNET_INGRESS_FORMAT_DEAGGREGATION      BIT(2)
 #define RMNET_INGRESS_FORMAT_DEMUXING           BIT(3)
 #define RMNET_INGRESS_FORMAT_MAP_COMMANDS       BIT(4)
-#define RMNET_INGRESS_FORMAT_MAP_CKSUMV3        BIT(5)
-#define RMNET_INGRESS_FORMAT_MAP_CKSUMV4        BIT(6)
 
-/* Pass the frame up the stack with no modifications to skb->dev */
-#define RMNET_EPMODE_NONE (0)
 /* Replace skb->dev to a virtual rmnet device and pass up the stack */
 #define RMNET_EPMODE_VND (1)
 /* Pass the frame directly to another device with dev_queue_xmit() */
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index 7f90d5587653..9caa5e387450 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -27,14 +27,28 @@
 
 void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev)
 {
-	dev->stats.rx_packets++;
-	dev->stats.rx_bytes += skb->len;
+	struct rmnet_priv *priv = netdev_priv(dev);
+	struct rmnet_pcpu_stats *pcpu_ptr;
+
+	pcpu_ptr = this_cpu_ptr(priv->pcpu_stats);
+
+	u64_stats_update_begin(&pcpu_ptr->syncp);
+	pcpu_ptr->stats.rx_pkts++;
+	pcpu_ptr->stats.rx_bytes += skb->len;
+	u64_stats_update_end(&pcpu_ptr->syncp);
 }
 
 void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev)
 {
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
+	struct rmnet_priv *priv = netdev_priv(dev);
+	struct rmnet_pcpu_stats *pcpu_ptr;
+
+	pcpu_ptr = this_cpu_ptr(priv->pcpu_stats);
+
+	u64_stats_update_begin(&pcpu_ptr->syncp);
+	pcpu_ptr->stats.tx_pkts++;
+	pcpu_ptr->stats.tx_bytes += skb->len;
+	u64_stats_update_end(&pcpu_ptr->syncp);
 }
 
 /* Network Device Operations */
@@ -45,10 +59,10 @@ static netdev_tx_t rmnet_vnd_start_xmit(struct sk_buff *skb,
 	struct rmnet_priv *priv;
 
 	priv = netdev_priv(dev);
-	if (priv->local_ep.egress_dev) {
-		rmnet_egress_handler(skb, &priv->local_ep);
+	if (priv->real_dev) {
+		rmnet_egress_handler(skb);
 	} else {
-		dev->stats.tx_dropped++;
+		this_cpu_inc(priv->pcpu_stats->stats.tx_drops);
 		kfree_skb(skb);
 	}
 	return NETDEV_TX_OK;
@@ -70,10 +84,72 @@ static int rmnet_vnd_get_iflink(const struct net_device *dev)
 	return priv->real_dev->ifindex;
 }
 
+static int rmnet_vnd_init(struct net_device *dev)
+{
+	struct rmnet_priv *priv = netdev_priv(dev);
+	int err;
+
+	priv->pcpu_stats = alloc_percpu(struct rmnet_pcpu_stats);
+	if (!priv->pcpu_stats)
+		return -ENOMEM;
+
+	err = gro_cells_init(&priv->gro_cells, dev);
+	if (err) {
+		free_percpu(priv->pcpu_stats);
+		return err;
+	}
+
+	return 0;
+}
+
+static void rmnet_vnd_uninit(struct net_device *dev)
+{
+	struct rmnet_priv *priv = netdev_priv(dev);
+
+	gro_cells_destroy(&priv->gro_cells);
+	free_percpu(priv->pcpu_stats);
+}
+
+static void rmnet_get_stats64(struct net_device *dev,
+			      struct rtnl_link_stats64 *s)
+{
+	struct rmnet_priv *priv = netdev_priv(dev);
+	struct rmnet_vnd_stats total_stats;
+	struct rmnet_pcpu_stats *pcpu_ptr;
+	unsigned int cpu, start;
+
+	memset(&total_stats, 0, sizeof(struct rmnet_vnd_stats));
+
+	for_each_possible_cpu(cpu) {
+		pcpu_ptr = this_cpu_ptr(priv->pcpu_stats);
+
+		do {
+			start = u64_stats_fetch_begin_irq(&pcpu_ptr->syncp);
+			total_stats.rx_pkts += pcpu_ptr->stats.rx_pkts;
+			total_stats.rx_bytes += pcpu_ptr->stats.rx_bytes;
+			total_stats.tx_pkts += pcpu_ptr->stats.tx_pkts;
+			total_stats.tx_bytes += pcpu_ptr->stats.tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&pcpu_ptr->syncp, start));
+
+		total_stats.tx_drops += pcpu_ptr->stats.tx_drops;
+	}
+
+	s->rx_packets = total_stats.rx_pkts;
+	s->rx_bytes = total_stats.rx_bytes;
+	s->tx_packets = total_stats.tx_pkts;
+	s->tx_bytes = total_stats.tx_bytes;
+	s->tx_dropped = total_stats.tx_drops;
+}
+
 static const struct net_device_ops rmnet_vnd_ops = {
 	.ndo_start_xmit = rmnet_vnd_start_xmit,
 	.ndo_change_mtu = rmnet_vnd_change_mtu,
 	.ndo_get_iflink = rmnet_vnd_get_iflink,
+	.ndo_add_slave  = rmnet_add_bridge,
+	.ndo_del_slave  = rmnet_del_bridge,
+	.ndo_init       = rmnet_vnd_init,
+	.ndo_uninit     = rmnet_vnd_uninit,
+	.ndo_get_stats64 = rmnet_get_stats64,
 };
 
 /* Called by kernel whenever a new rmnet<n> device is created. Sets MTU,
@@ -100,17 +176,19 @@ void rmnet_vnd_setup(struct net_device *rmnet_dev)
 
 int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev,
 		      struct rmnet_port *port,
-		      struct net_device *real_dev)
+		      struct net_device *real_dev,
+		      struct rmnet_endpoint *ep)
 {
 	struct rmnet_priv *priv;
 	int rc;
 
-	if (port->rmnet_devices[id])
+	if (ep->egress_dev)
 		return -EINVAL;
 
 	rc = register_netdevice(rmnet_dev);
 	if (!rc) {
-		port->rmnet_devices[id] = rmnet_dev;
+		ep->egress_dev = rmnet_dev;
+		ep->mux_id = id;
 		port->nr_rmnet_devs++;
 
 		rmnet_dev->rtnl_link_ops = &rmnet_link_ops;
@@ -125,12 +203,13 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev,
 	return rc;
 }
 
-int rmnet_vnd_dellink(u8 id, struct rmnet_port *port)
+int rmnet_vnd_dellink(u8 id, struct rmnet_port *port,
+		      struct rmnet_endpoint *ep)
 {
-	if (id >= RMNET_MAX_LOGICAL_EP || !port->rmnet_devices[id])
+	if (id >= RMNET_MAX_LOGICAL_EP || !ep->egress_dev)
 		return -EINVAL;
 
-	port->rmnet_devices[id] = NULL;
+	ep->egress_dev = NULL;
 	port->nr_rmnet_devs--;
 	return 0;
 }
@@ -143,21 +222,6 @@ u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev)
 	return priv->mux_id;
 }
 
-/* Gets the logical endpoint configuration for a RmNet virtual network device
- * node. Caller should confirm that devices is a RmNet VND before calling.
- */
-struct rmnet_endpoint *rmnet_vnd_get_endpoint(struct net_device *rmnet_dev)
-{
-	struct rmnet_priv *priv;
-
-	if (!rmnet_dev)
-		return NULL;
-
-	priv = netdev_priv(rmnet_dev);
-
-	return &priv->local_ep;
-}
-
 int rmnet_vnd_do_flow_control(struct net_device *rmnet_dev, int enable)
 {
 	netdev_dbg(rmnet_dev, "Setting VND TX queue state to %d\n", enable);
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h
index 8a4042f0f6bf..71e4c3286951 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h
@@ -17,11 +17,12 @@
 #define _RMNET_VND_H_
 
 int rmnet_vnd_do_flow_control(struct net_device *dev, int enable);
-struct rmnet_endpoint *rmnet_vnd_get_endpoint(struct net_device *dev);
 int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev,
 		      struct rmnet_port *port,
-		      struct net_device *real_dev);
-int rmnet_vnd_dellink(u8 id, struct rmnet_port *port);
+		      struct net_device *real_dev,
+		      struct rmnet_endpoint *ep);
+int rmnet_vnd_dellink(u8 id, struct rmnet_port *port,
+		      struct rmnet_endpoint *ep);
 void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev);
 void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev);
 u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev);
diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c
index bed34684994f..7e011c1c1e6e 100644
--- a/drivers/net/ethernet/realtek/atp.c
+++ b/drivers/net/ethernet/realtek/atp.c
@@ -170,6 +170,7 @@ struct net_local {
     spinlock_t lock;
     struct net_device *next_module;
     struct timer_list timer;	/* Media selection timer. */
+    struct net_device *dev;	/* Timer dev. */
     unsigned long last_rx_time;	/* Last Rx, in jiffies, to handle Rx hang. */
     int saved_tx_size;
     unsigned int tx_unit_busy:1;
@@ -184,7 +185,7 @@ struct net_local {
 #define TIMED_CHECKER (HZ/4)
 #ifdef TIMED_CHECKER
 #include <linux/timer.h>
-static void atp_timed_checker(unsigned long ignored);
+static void atp_timed_checker(struct timer_list *t);
 #endif
 
 /* Index to functions, as function prototypes. */
@@ -438,10 +439,9 @@ static int net_open(struct net_device *dev)
 
 	hardware_init(dev);
 
-	init_timer(&lp->timer);
+	lp->dev = dev;
+	timer_setup(&lp->timer, atp_timed_checker, 0);
 	lp->timer.expires = jiffies + TIMED_CHECKER;
-	lp->timer.data = (unsigned long)dev;
-	lp->timer.function = atp_timed_checker;    /* timer handler */
 	add_timer(&lp->timer);
 
 	netif_start_queue(dev);
@@ -710,11 +710,11 @@ static irqreturn_t atp_interrupt(int irq, void *dev_instance)
 #ifdef TIMED_CHECKER
 /* This following code fixes a rare (and very difficult to track down)
    problem where the adapter forgets its ethernet address. */
-static void atp_timed_checker(unsigned long data)
+static void atp_timed_checker(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
+	struct net_local *lp = from_timer(lp, t, timer);
+	struct net_device *dev = lp->dev;
 	long ioaddr = dev->base_addr;
-	struct net_local *lp = netdev_priv(dev);
 	int tickssofar = jiffies - lp->last_rx_time;
 	int i;
 
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index a3c949ea7d1a..fd218fd9ef3c 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -399,6 +399,12 @@ enum rtl_registers {
 	RxMaxSize	= 0xda,
 	CPlusCmd	= 0xe0,
 	IntrMitigate	= 0xe2,
+
+#define RTL_COALESCE_MASK	0x0f
+#define RTL_COALESCE_SHIFT	4
+#define RTL_COALESCE_T_MAX	(RTL_COALESCE_MASK)
+#define RTL_COALESCE_FRAME_MAX	(RTL_COALESCE_MASK << 2)
+
 	RxDescAddrLow	= 0xe4,
 	RxDescAddrHigh	= 0xe8,
 	EarlyTxThres	= 0xec,	/* 8169. Unit of 32 bytes. */
@@ -795,6 +801,7 @@ struct rtl8169_private {
 	u16 cp_cmd;
 
 	u16 event_slow;
+	const struct rtl_coalesce_info *coalesce_info;
 
 	struct mdio_ops {
 		void (*write)(struct rtl8169_private *, int, int);
@@ -2363,10 +2370,229 @@ static int rtl8169_nway_reset(struct net_device *dev)
 	return mii_nway_restart(&tp->mii);
 }
 
+/*
+ * Interrupt coalescing
+ *
+ * > 1 - the availability of the IntrMitigate (0xe2) register through the
+ * >     8169, 8168 and 810x line of chipsets
+ *
+ * 8169, 8168, and 8136(810x) serial chipsets support it.
+ *
+ * > 2 - the Tx timer unit at gigabit speed
+ *
+ * The unit of the timer depends on both the speed and the setting of CPlusCmd
+ * (0xe0) bit 1 and bit 0.
+ *
+ * For 8169
+ * bit[1:0] \ speed        1000M           100M            10M
+ * 0 0                     320ns           2.56us          40.96us
+ * 0 1                     2.56us          20.48us         327.7us
+ * 1 0                     5.12us          40.96us         655.4us
+ * 1 1                     10.24us         81.92us         1.31ms
+ *
+ * For the other
+ * bit[1:0] \ speed        1000M           100M            10M
+ * 0 0                     5us             2.56us          40.96us
+ * 0 1                     40us            20.48us         327.7us
+ * 1 0                     80us            40.96us         655.4us
+ * 1 1                     160us           81.92us         1.31ms
+ */
+
+/* rx/tx scale factors for one particular CPlusCmd[0:1] value */
+struct rtl_coalesce_scale {
+	/* Rx / Tx */
+	u32 nsecs[2];
+};
+
+/* rx/tx scale factors for all CPlusCmd[0:1] cases */
+struct rtl_coalesce_info {
+	u32 speed;
+	struct rtl_coalesce_scale scalev[4];	/* each CPlusCmd[0:1] case */
+};
+
+/* produce (r,t) pairs with each being in series of *1, *8, *8*2, *8*2*2 */
+#define rxtx_x1822(r, t) {		\
+	{{(r),		(t)}},		\
+	{{(r)*8,	(t)*8}},	\
+	{{(r)*8*2,	(t)*8*2}},	\
+	{{(r)*8*2*2,	(t)*8*2*2}},	\
+}
+static const struct rtl_coalesce_info rtl_coalesce_info_8169[] = {
+	/* speed	delays:     rx00   tx00	*/
+	{ SPEED_10,	rxtx_x1822(40960, 40960)	},
+	{ SPEED_100,	rxtx_x1822( 2560,  2560)	},
+	{ SPEED_1000,	rxtx_x1822(  320,   320)	},
+	{ 0 },
+};
+
+static const struct rtl_coalesce_info rtl_coalesce_info_8168_8136[] = {
+	/* speed	delays:     rx00   tx00	*/
+	{ SPEED_10,	rxtx_x1822(40960, 40960)	},
+	{ SPEED_100,	rxtx_x1822( 2560,  2560)	},
+	{ SPEED_1000,	rxtx_x1822( 5000,  5000)	},
+	{ 0 },
+};
+#undef rxtx_x1822
+
+/* get rx/tx scale vector corresponding to current speed */
+static const struct rtl_coalesce_info *rtl_coalesce_info(struct net_device *dev)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	struct ethtool_link_ksettings ecmd;
+	const struct rtl_coalesce_info *ci;
+	int rc;
+
+	rc = rtl8169_get_link_ksettings(dev, &ecmd);
+	if (rc < 0)
+		return ERR_PTR(rc);
+
+	for (ci = tp->coalesce_info; ci->speed != 0; ci++) {
+		if (ecmd.base.speed == ci->speed) {
+			return ci;
+		}
+	}
+
+	return ERR_PTR(-ELNRNG);
+}
+
+static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	void __iomem *ioaddr = tp->mmio_addr;
+	const struct rtl_coalesce_info *ci;
+	const struct rtl_coalesce_scale *scale;
+	struct {
+		u32 *max_frames;
+		u32 *usecs;
+	} coal_settings [] = {
+		{ &ec->rx_max_coalesced_frames, &ec->rx_coalesce_usecs },
+		{ &ec->tx_max_coalesced_frames, &ec->tx_coalesce_usecs }
+	}, *p = coal_settings;
+	int i;
+	u16 w;
+
+	memset(ec, 0, sizeof(*ec));
+
+	/* get rx/tx scale corresponding to current speed and CPlusCmd[0:1] */
+	ci = rtl_coalesce_info(dev);
+	if (IS_ERR(ci))
+		return PTR_ERR(ci);
+
+	scale = &ci->scalev[RTL_R16(CPlusCmd) & 3];
+
+	/* read IntrMitigate and adjust according to scale */
+	for (w = RTL_R16(IntrMitigate); w; w >>= RTL_COALESCE_SHIFT, p++) {
+		*p->max_frames = (w & RTL_COALESCE_MASK) << 2;
+		w >>= RTL_COALESCE_SHIFT;
+		*p->usecs = w & RTL_COALESCE_MASK;
+	}
+
+	for (i = 0; i < 2; i++) {
+		p = coal_settings + i;
+		*p->usecs = (*p->usecs * scale->nsecs[i]) / 1000;
+
+		/*
+		 * ethtool_coalesce says it is illegal to set both usecs and
+		 * max_frames to 0.
+		 */
+		if (!*p->usecs && !*p->max_frames)
+			*p->max_frames = 1;
+	}
+
+	return 0;
+}
+
+/* choose appropriate scale factor and CPlusCmd[0:1] for (speed, nsec) */
+static const struct rtl_coalesce_scale *rtl_coalesce_choose_scale(
+			struct net_device *dev, u32 nsec, u16 *cp01)
+{
+	const struct rtl_coalesce_info *ci;
+	u16 i;
+
+	ci = rtl_coalesce_info(dev);
+	if (IS_ERR(ci))
+		return ERR_CAST(ci);
+
+	for (i = 0; i < 4; i++) {
+		u32 rxtx_maxscale = max(ci->scalev[i].nsecs[0],
+					ci->scalev[i].nsecs[1]);
+		if (nsec <= rxtx_maxscale * RTL_COALESCE_T_MAX) {
+			*cp01 = i;
+			return &ci->scalev[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	void __iomem *ioaddr = tp->mmio_addr;
+	const struct rtl_coalesce_scale *scale;
+	struct {
+		u32 frames;
+		u32 usecs;
+	} coal_settings [] = {
+		{ ec->rx_max_coalesced_frames, ec->rx_coalesce_usecs },
+		{ ec->tx_max_coalesced_frames, ec->tx_coalesce_usecs }
+	}, *p = coal_settings;
+	u16 w = 0, cp01;
+	int i;
+
+	scale = rtl_coalesce_choose_scale(dev,
+			max(p[0].usecs, p[1].usecs) * 1000, &cp01);
+	if (IS_ERR(scale))
+		return PTR_ERR(scale);
+
+	for (i = 0; i < 2; i++, p++) {
+		u32 units;
+
+		/*
+		 * accept max_frames=1 we returned in rtl_get_coalesce.
+		 * accept it not only when usecs=0 because of e.g. the following scenario:
+		 *
+		 * - both rx_usecs=0 & rx_frames=0 in hardware (no delay on RX)
+		 * - rtl_get_coalesce returns rx_usecs=0, rx_frames=1
+		 * - then user does `ethtool -C eth0 rx-usecs 100`
+		 *
+		 * since ethtool sends to kernel whole ethtool_coalesce
+		 * settings, if we do not handle rx_usecs=!0, rx_frames=1
+		 * we'll reject it below in `frames % 4 != 0`.
+		 */
+		if (p->frames == 1) {
+			p->frames = 0;
+		}
+
+		units = p->usecs * 1000 / scale->nsecs[i];
+		if (p->frames > RTL_COALESCE_FRAME_MAX || p->frames % 4)
+			return -EINVAL;
+
+		w <<= RTL_COALESCE_SHIFT;
+		w |= units;
+		w <<= RTL_COALESCE_SHIFT;
+		w |= p->frames >> 2;
+	}
+
+	rtl_lock_work(tp);
+
+	RTL_W16(IntrMitigate, swab16(w));
+
+	tp->cp_cmd = (tp->cp_cmd & ~3) | cp01;
+	RTL_W16(CPlusCmd, tp->cp_cmd);
+	RTL_R16(CPlusCmd);
+
+	rtl_unlock_work(tp);
+
+	return 0;
+}
+
 static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_drvinfo		= rtl8169_get_drvinfo,
 	.get_regs_len		= rtl8169_get_regs_len,
 	.get_link		= ethtool_op_get_link,
+	.get_coalesce		= rtl_get_coalesce,
+	.set_coalesce		= rtl_set_coalesce,
 	.set_settings		= rtl8169_set_settings,
 	.get_msglevel		= rtl8169_get_msglevel,
 	.set_msglevel		= rtl8169_set_msglevel,
@@ -4401,10 +4627,9 @@ static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag)
 		schedule_work(&tp->wk.work);
 }
 
-static void rtl8169_phy_timer(unsigned long __opaque)
+static void rtl8169_phy_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)__opaque;
-	struct rtl8169_private *tp = netdev_priv(dev);
+	struct rtl8169_private *tp = from_timer(tp, t, timer);
 
 	rtl_schedule_task(tp, RTL_FLAG_TASK_PHY_PENDING);
 }
@@ -8062,6 +8287,7 @@ static const struct rtl_cfg_info {
 	unsigned int align;
 	u16 event_slow;
 	unsigned features;
+	const struct rtl_coalesce_info *coalesce_info;
 	u8 default_ver;
 } rtl_cfg_infos [] = {
 	[RTL_CFG_0] = {
@@ -8070,6 +8296,7 @@ static const struct rtl_cfg_info {
 		.align		= 0,
 		.event_slow	= SYSErr | LinkChg | RxOverflow | RxFIFOOver,
 		.features	= RTL_FEATURE_GMII,
+		.coalesce_info	= rtl_coalesce_info_8169,
 		.default_ver	= RTL_GIGA_MAC_VER_01,
 	},
 	[RTL_CFG_1] = {
@@ -8078,6 +8305,7 @@ static const struct rtl_cfg_info {
 		.align		= 8,
 		.event_slow	= SYSErr | LinkChg | RxOverflow,
 		.features	= RTL_FEATURE_GMII | RTL_FEATURE_MSI,
+		.coalesce_info	= rtl_coalesce_info_8168_8136,
 		.default_ver	= RTL_GIGA_MAC_VER_11,
 	},
 	[RTL_CFG_2] = {
@@ -8087,6 +8315,7 @@ static const struct rtl_cfg_info {
 		.event_slow	= SYSErr | LinkChg | RxOverflow | RxFIFOOver |
 				  PCSTimeout,
 		.features	= RTL_FEATURE_MSI,
+		.coalesce_info	= rtl_coalesce_info_8168_8136,
 		.default_ver	= RTL_GIGA_MAC_VER_13,
 	}
 };
@@ -8450,11 +8679,12 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	tp->hw_start = cfg->hw_start;
 	tp->event_slow = cfg->event_slow;
+	tp->coalesce_info = cfg->coalesce_info;
 
 	tp->opts1_mask = (tp->mac_version != RTL_GIGA_MAC_VER_01) ?
 		~(RxBOVF | RxFOVF) : ~0;
 
-	setup_timer(&tp->timer, rtl8169_phy_timer, (unsigned long)dev);
+	timer_setup(&tp->timer, rtl8169_phy_timer, 0);
 
 	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index fdf30bfa403b..2b962d349f5f 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -403,8 +403,9 @@ static void ravb_emac_init(struct net_device *ndev)
 	/* Receive frame limit set register */
 	ravb_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN, RFLR);
 
-	/* PAUSE prohibition */
+	/* EMAC Mode: PAUSE prohibition; Duplex; RX Checksum; TX; RX */
 	ravb_write(ndev, ECMR_ZPF | (priv->duplex ? ECMR_DM : 0) |
+		   (ndev->features & NETIF_F_RXCSUM ? ECMR_RCSC : 0) |
 		   ECMR_TE | ECMR_RE, ECMR);
 
 	ravb_set_rate(ndev);
@@ -520,6 +521,19 @@ static void ravb_get_tx_tstamp(struct net_device *ndev)
 	}
 }
 
+static void ravb_rx_csum(struct sk_buff *skb)
+{
+	u8 *hw_csum;
+
+	/* The hardware checksum is 2 bytes appended to packet data */
+	if (unlikely(skb->len < 2))
+		return;
+	hw_csum = skb_tail_pointer(skb) - 2;
+	skb->csum = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum));
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	skb_trim(skb, skb->len - 2);
+}
+
 /* Packet receive function for Ethernet AVB */
 static bool ravb_rx(struct net_device *ndev, int *quota, int q)
 {
@@ -587,8 +601,11 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q)
 				ts.tv_nsec = le32_to_cpu(desc->ts_n);
 				shhwtstamps->hwtstamp = timespec64_to_ktime(ts);
 			}
+
 			skb_put(skb, pkt_len);
 			skb->protocol = eth_type_trans(skb, ndev);
+			if (ndev->features & NETIF_F_RXCSUM)
+				ravb_rx_csum(skb);
 			napi_gro_receive(&priv->napi[q], skb);
 			stats->rx_packets++;
 			stats->rx_bytes += pkt_len;
@@ -1337,20 +1354,15 @@ static void ravb_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 
-	wol->supported = 0;
-	wol->wolopts = 0;
-
-	if (priv->clk) {
-		wol->supported = WAKE_MAGIC;
-		wol->wolopts = priv->wol_enabled ? WAKE_MAGIC : 0;
-	}
+	wol->supported = WAKE_MAGIC;
+	wol->wolopts = priv->wol_enabled ? WAKE_MAGIC : 0;
 }
 
 static int ravb_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 
-	if (!priv->clk || wol->wolopts & ~WAKE_MAGIC)
+	if (wol->wolopts & ~WAKE_MAGIC)
 		return -EOPNOTSUPP;
 
 	priv->wol_enabled = !!(wol->wolopts & WAKE_MAGIC);
@@ -1842,6 +1854,38 @@ static int ravb_do_ioctl(struct net_device *ndev, struct ifreq *req, int cmd)
 	return phy_mii_ioctl(phydev, req, cmd);
 }
 
+static void ravb_set_rx_csum(struct net_device *ndev, bool enable)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	/* Disable TX and RX */
+	ravb_rcv_snd_disable(ndev);
+
+	/* Modify RX Checksum setting */
+	ravb_modify(ndev, ECMR, ECMR_RCSC, enable ? ECMR_RCSC : 0);
+
+	/* Enable TX and RX */
+	ravb_rcv_snd_enable(ndev);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static int ravb_set_features(struct net_device *ndev,
+			     netdev_features_t features)
+{
+	netdev_features_t changed = ndev->features ^ features;
+
+	if (changed & NETIF_F_RXCSUM)
+		ravb_set_rx_csum(ndev, features & NETIF_F_RXCSUM);
+
+	ndev->features = features;
+
+	return 0;
+}
+
 static const struct net_device_ops ravb_netdev_ops = {
 	.ndo_open		= ravb_open,
 	.ndo_stop		= ravb_close,
@@ -1853,6 +1897,7 @@ static const struct net_device_ops ravb_netdev_ops = {
 	.ndo_do_ioctl		= ravb_do_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_set_features	= ravb_set_features,
 };
 
 /* MDIO bus init function */
@@ -1912,22 +1957,12 @@ MODULE_DEVICE_TABLE(of, ravb_match_table);
 
 static int ravb_set_gti(struct net_device *ndev)
 {
-
+	struct ravb_private *priv = netdev_priv(ndev);
 	struct device *dev = ndev->dev.parent;
-	struct device_node *np = dev->of_node;
 	unsigned long rate;
-	struct clk *clk;
 	uint64_t inc;
 
-	clk = of_clk_get(np, 0);
-	if (IS_ERR(clk)) {
-		dev_err(dev, "could not get clock\n");
-		return PTR_ERR(clk);
-	}
-
-	rate = clk_get_rate(clk);
-	clk_put(clk);
-
+	rate = clk_get_rate(priv->clk);
 	if (!rate)
 		return -EINVAL;
 
@@ -2004,6 +2039,9 @@ static int ravb_probe(struct platform_device *pdev)
 	if (!ndev)
 		return -ENOMEM;
 
+	ndev->features = NETIF_F_RXCSUM;
+	ndev->hw_features = NETIF_F_RXCSUM;
+
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_get_sync(&pdev->dev);
 
@@ -2073,10 +2111,11 @@ static int ravb_probe(struct platform_device *pdev)
 
 	priv->chip_id = chip_id;
 
-	/* Get clock, if not found that's OK but Wake-On-Lan is unavailable */
 	priv->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(priv->clk))
-		priv->clk = NULL;
+	if (IS_ERR(priv->clk)) {
+		error = PTR_ERR(priv->clk);
+		goto out_release;
+	}
 
 	/* Set function */
 	ndev->netdev_ops = &ravb_netdev_ops;
@@ -2144,8 +2183,7 @@ static int ravb_probe(struct platform_device *pdev)
 	if (error)
 		goto out_napi_del;
 
-	if (priv->clk)
-		device_set_wakeup_capable(&pdev->dev, 1);
+	device_set_wakeup_capable(&pdev->dev, 1);
 
 	/* Print device information */
 	netdev_info(ndev, "Base address at %#x, %pM, IRQ %d.\n",
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index d2e88a30f57b..7e060aa9fbed 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -594,7 +594,7 @@ static struct sh_eth_cpu_data r8a7740_data = {
 };
 
 /* There is CPU dependent code */
-static void sh_eth_set_rate_r8a777x(struct net_device *ndev)
+static void sh_eth_set_rate_rcar(struct net_device *ndev)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
 
@@ -608,10 +608,10 @@ static void sh_eth_set_rate_r8a777x(struct net_device *ndev)
 	}
 }
 
-/* R8A7778/9 */
-static struct sh_eth_cpu_data r8a777x_data = {
+/* R-Car Gen1 */
+static struct sh_eth_cpu_data rcar_gen1_data = {
 	.set_duplex	= sh_eth_set_duplex,
-	.set_rate	= sh_eth_set_rate_r8a777x,
+	.set_rate	= sh_eth_set_rate_rcar,
 
 	.register_type	= SH_ETH_REG_FAST_RCAR,
 
@@ -635,10 +635,10 @@ static struct sh_eth_cpu_data r8a777x_data = {
 	.hw_swap	= 1,
 };
 
-/* R8A7790/1 */
-static struct sh_eth_cpu_data r8a779x_data = {
+/* R-Car Gen2 and RZ/G1 */
+static struct sh_eth_cpu_data rcar_gen2_data = {
 	.set_duplex	= sh_eth_set_duplex,
-	.set_rate	= sh_eth_set_rate_r8a777x,
+	.set_rate	= sh_eth_set_rate_rcar,
 
 	.register_type	= SH_ETH_REG_FAST_RCAR,
 
@@ -3086,15 +3086,17 @@ static struct sh_eth_plat_data *sh_eth_parse_dt(struct device *dev)
 
 static const struct of_device_id sh_eth_match_table[] = {
 	{ .compatible = "renesas,gether-r8a7740", .data = &r8a7740_data },
-	{ .compatible = "renesas,ether-r8a7743", .data = &r8a779x_data },
-	{ .compatible = "renesas,ether-r8a7745", .data = &r8a779x_data },
-	{ .compatible = "renesas,ether-r8a7778", .data = &r8a777x_data },
-	{ .compatible = "renesas,ether-r8a7779", .data = &r8a777x_data },
-	{ .compatible = "renesas,ether-r8a7790", .data = &r8a779x_data },
-	{ .compatible = "renesas,ether-r8a7791", .data = &r8a779x_data },
-	{ .compatible = "renesas,ether-r8a7793", .data = &r8a779x_data },
-	{ .compatible = "renesas,ether-r8a7794", .data = &r8a779x_data },
+	{ .compatible = "renesas,ether-r8a7743", .data = &rcar_gen2_data },
+	{ .compatible = "renesas,ether-r8a7745", .data = &rcar_gen2_data },
+	{ .compatible = "renesas,ether-r8a7778", .data = &rcar_gen1_data },
+	{ .compatible = "renesas,ether-r8a7779", .data = &rcar_gen1_data },
+	{ .compatible = "renesas,ether-r8a7790", .data = &rcar_gen2_data },
+	{ .compatible = "renesas,ether-r8a7791", .data = &rcar_gen2_data },
+	{ .compatible = "renesas,ether-r8a7793", .data = &rcar_gen2_data },
+	{ .compatible = "renesas,ether-r8a7794", .data = &rcar_gen2_data },
 	{ .compatible = "renesas,ether-r7s72100", .data = &r7s72100_data },
+	{ .compatible = "renesas,rcar-gen1-ether", .data = &rcar_gen1_data },
+	{ .compatible = "renesas,rcar-gen2-ether", .data = &rcar_gen2_data },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, sh_eth_match_table);
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index 89831adb8eb7..fd35d8004a78 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -105,9 +105,9 @@ void sxgbe_disable_eee_mode(struct sxgbe_priv_data * const priv)
  *  If there is no data transfer and if we are not in LPI state,
  *  then MAC Transmitter can be moved to LPI state.
  */
-static void sxgbe_eee_ctrl_timer(unsigned long arg)
+static void sxgbe_eee_ctrl_timer(struct timer_list *t)
 {
-	struct sxgbe_priv_data *priv = (struct sxgbe_priv_data *)arg;
+	struct sxgbe_priv_data *priv = from_timer(priv, t, eee_ctrl_timer);
 
 	sxgbe_enable_eee_mode(priv);
 	mod_timer(&priv->eee_ctrl_timer, SXGBE_LPI_TIMER(eee_timer));
@@ -134,8 +134,7 @@ bool sxgbe_eee_init(struct sxgbe_priv_data * const priv)
 			return false;
 
 		priv->eee_active = 1;
-		setup_timer(&priv->eee_ctrl_timer, sxgbe_eee_ctrl_timer,
-			    (unsigned long)priv);
+		timer_setup(&priv->eee_ctrl_timer, sxgbe_eee_ctrl_timer, 0);
 		priv->eee_ctrl_timer.expires = SXGBE_LPI_TIMER(eee_timer);
 		add_timer(&priv->eee_ctrl_timer);
 
@@ -1002,13 +1001,13 @@ static void sxgbe_disable_mtl_engine(struct sxgbe_priv_data *priv)
 
 /**
  * sxgbe_tx_timer: mitigation sw timer for tx.
- * @data: data pointer
+ * @t: timer pointer
  * Description:
  * This is the timer handler to directly invoke the sxgbe_tx_clean.
  */
-static void sxgbe_tx_timer(unsigned long data)
+static void sxgbe_tx_timer(struct timer_list *t)
 {
-	struct sxgbe_tx_queue *p = (struct sxgbe_tx_queue *)data;
+	struct sxgbe_tx_queue *p = from_timer(p, t, txtimer);
 	sxgbe_tx_queue_clean(p);
 }
 
@@ -1028,8 +1027,7 @@ static void sxgbe_tx_init_coalesce(struct sxgbe_priv_data *priv)
 		struct sxgbe_tx_queue *p = priv->txq[queue_num];
 		p->tx_coal_frames =  SXGBE_TX_FRAMES;
 		p->tx_coal_timer = SXGBE_COAL_TX_TIMER;
-		setup_timer(&p->txtimer, sxgbe_tx_timer,
-			    (unsigned long)&priv->txq[queue_num]);
+		timer_setup(&p->txtimer, sxgbe_tx_timer, 0);
 		p->txtimer.expires = SXGBE_COAL_TIMER(p->tx_coal_timer);
 		add_timer(&p->txtimer);
 	}
diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c
index 244c1e171017..c5bc124b41a9 100644
--- a/drivers/net/ethernet/seeq/ether3.c
+++ b/drivers/net/ethernet/seeq/ether3.c
@@ -170,9 +170,11 @@ ether3_setbuffer(struct net_device *dev, buffer_rw_t read, int start)
 /*
  * Switch LED off...
  */
-static void ether3_ledoff(unsigned long data)
+static void ether3_ledoff(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
+	struct dev_priv *private = from_timer(private, t, timer);
+	struct net_device *dev = private->dev;
+
 	ether3_outw(priv(dev)->regs.config2 |= CFG2_CTRLO, REG_CONFIG2);
 }
 
@@ -183,8 +185,6 @@ static inline void ether3_ledon(struct net_device *dev)
 {
 	del_timer(&priv(dev)->timer);
 	priv(dev)->timer.expires = jiffies + HZ / 50; /* leave on for 1/50th second */
-	priv(dev)->timer.data = (unsigned long)dev;
-	priv(dev)->timer.function = ether3_ledoff;
 	add_timer(&priv(dev)->timer);
 	if (priv(dev)->regs.config2 & CFG2_CTRLO)
 		ether3_outw(priv(dev)->regs.config2 &= ~CFG2_CTRLO, REG_CONFIG2);
@@ -783,7 +783,8 @@ ether3_probe(struct expansion_card *ec, const struct ecard_id *id)
 
 	ether3_addr(dev->dev_addr, ec);
 
-	init_timer(&priv(dev)->timer);
+	priv(dev)->dev = dev;
+	timer_setup(&priv(dev)->timer, ether3_ledoff, 0);
 
 	/* Reset card...
 	 */
diff --git a/drivers/net/ethernet/seeq/ether3.h b/drivers/net/ethernet/seeq/ether3.h
index 2db63b08bdf3..be19e5fa5cf2 100644
--- a/drivers/net/ethernet/seeq/ether3.h
+++ b/drivers/net/ethernet/seeq/ether3.h
@@ -165,6 +165,7 @@ struct dev_priv {
     unsigned char tx_tail;		/* buffer nr of transmitting packet	 */
     unsigned int rx_head;		/* address to fetch next packet from	 */
     struct timer_list timer;
+    struct net_device *dev;
     int broken;				/* 0 = ok, 1 = something went wrong	 */
 };
 
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 13f72f5b18d2..19a91881fbf9 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -674,6 +674,10 @@ static int efx_ef10_probe(struct efx_nic *efx)
 	efx->rx_packet_len_offset =
 		ES_DZ_RX_PREFIX_PKTLEN_OFST - ES_DZ_RX_PREFIX_SIZE;
 
+	if (nic_data->datapath_caps &
+	    (1 << MC_CMD_GET_CAPABILITIES_OUT_RX_INCLUDE_FCS_LBN))
+		efx->net_dev->hw_features |= NETIF_F_RXFCS;
+
 	rc = efx_mcdi_port_get_number(efx);
 	if (rc < 0)
 		goto fail5;
@@ -3199,11 +3203,15 @@ static u16 efx_ef10_handle_rx_event_errors(struct efx_channel *channel,
 					   const efx_qword_t *event)
 {
 	struct efx_nic *efx = channel->efx;
+	bool handled = false;
 
 	if (EFX_QWORD_FIELD(*event, ESF_DZ_RX_ECRC_ERR)) {
-		if (!efx->loopback_selftest)
-			channel->n_rx_eth_crc_err += n_packets;
-		return EFX_RX_PKT_DISCARD;
+		if (!(efx->net_dev->features & NETIF_F_RXALL)) {
+			if (!efx->loopback_selftest)
+				channel->n_rx_eth_crc_err += n_packets;
+			return EFX_RX_PKT_DISCARD;
+		}
+		handled = true;
 	}
 	if (EFX_QWORD_FIELD(*event, ESF_DZ_RX_IPCKSUM_ERR)) {
 		if (unlikely(rx_encap_hdr != ESE_EZ_ENCAP_HDR_VXLAN &&
@@ -3274,7 +3282,7 @@ static u16 efx_ef10_handle_rx_event_errors(struct efx_channel *channel,
 		return 0;
 	}
 
-	WARN_ON(1); /* No error bits were recognised */
+	WARN_ON(!handled); /* No error bits were recognised */
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index b9cb697b2818..6668e371405c 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -471,8 +471,7 @@ efx_alloc_channel(struct efx_nic *efx, int i, struct efx_channel *old_channel)
 
 	rx_queue = &channel->rx_queue;
 	rx_queue->efx = efx;
-	setup_timer(&rx_queue->slow_fill, efx_rx_slow_fill,
-		    (unsigned long)rx_queue);
+	timer_setup(&rx_queue->slow_fill, efx_rx_slow_fill, 0);
 
 	return channel;
 }
@@ -511,8 +510,7 @@ efx_copy_channel(const struct efx_channel *old_channel)
 	rx_queue = &channel->rx_queue;
 	rx_queue->buffer = NULL;
 	memset(&rx_queue->rxd, 0, sizeof(rx_queue->rxd));
-	setup_timer(&rx_queue->slow_fill, efx_rx_slow_fill,
-		    (unsigned long)rx_queue);
+	timer_setup(&rx_queue->slow_fill, efx_rx_slow_fill, 0);
 
 	return channel;
 }
@@ -2317,8 +2315,11 @@ static int efx_set_features(struct net_device *net_dev, netdev_features_t data)
 			return rc;
 	}
 
-	/* If Rx VLAN filter is changed, update filters via mac_reconfigure */
-	if ((net_dev->features ^ data) & NETIF_F_HW_VLAN_CTAG_FILTER) {
+	/* If Rx VLAN filter is changed, update filters via mac_reconfigure.
+	 * If rx-fcs is changed, mac_reconfigure updates that too.
+	 */
+	if ((net_dev->features ^ data) & (NETIF_F_HW_VLAN_CTAG_FILTER |
+					  NETIF_F_RXFCS)) {
 		/* efx_set_rx_mode() will schedule MAC work to update filters
 		 * when a new features are finally set in net_dev.
 		 */
@@ -3244,7 +3245,7 @@ static int efx_pci_probe_post_io(struct efx_nic *efx)
 
 	/* Determine netdevice features */
 	net_dev->features |= (efx->type->offload_features | NETIF_F_SG |
-			      NETIF_F_TSO | NETIF_F_RXCSUM);
+			      NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_RXALL);
 	if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
 		net_dev->features |= NETIF_F_TSO6;
 	/* Check whether device supports TSO */
@@ -3255,7 +3256,10 @@ static int efx_pci_probe_post_io(struct efx_nic *efx)
 				   NETIF_F_HIGHDMA | NETIF_F_ALL_TSO |
 				   NETIF_F_RXCSUM);
 
-	net_dev->hw_features = net_dev->features & ~efx->fixed_features;
+	net_dev->hw_features |= net_dev->features & ~efx->fixed_features;
+
+	/* Disable receiving frames with bad FCS, by default. */
+	net_dev->features &= ~NETIF_F_RXALL;
 
 	/* Disable VLAN filtering by default.  It may be enforced if
 	 * the feature is fixed (i.e. VLAN filters are required to
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index d407adf59610..52c84b782901 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -46,7 +46,7 @@ void efx_remove_rx_queue(struct efx_rx_queue *rx_queue);
 void efx_init_rx_queue(struct efx_rx_queue *rx_queue);
 void efx_fini_rx_queue(struct efx_rx_queue *rx_queue);
 void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic);
-void efx_rx_slow_fill(unsigned long context);
+void efx_rx_slow_fill(struct timer_list *t);
 void __efx_rx_packet(struct efx_channel *channel);
 void efx_rx_packet(struct efx_rx_queue *rx_queue, unsigned int index,
 		   unsigned int n_frags, unsigned int len, u16 flags);
diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c
index 29614da91cbf..6685a66ee1a3 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.c
+++ b/drivers/net/ethernet/sfc/falcon/efx.c
@@ -449,8 +449,7 @@ ef4_alloc_channel(struct ef4_nic *efx, int i, struct ef4_channel *old_channel)
 
 	rx_queue = &channel->rx_queue;
 	rx_queue->efx = efx;
-	setup_timer(&rx_queue->slow_fill, ef4_rx_slow_fill,
-		    (unsigned long)rx_queue);
+	timer_setup(&rx_queue->slow_fill, ef4_rx_slow_fill, 0);
 
 	return channel;
 }
@@ -489,8 +488,7 @@ ef4_copy_channel(const struct ef4_channel *old_channel)
 	rx_queue = &channel->rx_queue;
 	rx_queue->buffer = NULL;
 	memset(&rx_queue->rxd, 0, sizeof(rx_queue->rxd));
-	setup_timer(&rx_queue->slow_fill, ef4_rx_slow_fill,
-		    (unsigned long)rx_queue);
+	timer_setup(&rx_queue->slow_fill, ef4_rx_slow_fill, 0);
 
 	return channel;
 }
diff --git a/drivers/net/ethernet/sfc/falcon/efx.h b/drivers/net/ethernet/sfc/falcon/efx.h
index 4f3bb30661ea..a4e4d8ea4078 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.h
+++ b/drivers/net/ethernet/sfc/falcon/efx.h
@@ -45,7 +45,7 @@ void ef4_remove_rx_queue(struct ef4_rx_queue *rx_queue);
 void ef4_init_rx_queue(struct ef4_rx_queue *rx_queue);
 void ef4_fini_rx_queue(struct ef4_rx_queue *rx_queue);
 void ef4_fast_push_rx_descriptors(struct ef4_rx_queue *rx_queue, bool atomic);
-void ef4_rx_slow_fill(unsigned long context);
+void ef4_rx_slow_fill(struct timer_list *t);
 void __ef4_rx_packet(struct ef4_channel *channel);
 void ef4_rx_packet(struct ef4_rx_queue *rx_queue, unsigned int index,
 		   unsigned int n_frags, unsigned int len, u16 flags);
diff --git a/drivers/net/ethernet/sfc/falcon/falcon.c b/drivers/net/ethernet/sfc/falcon/falcon.c
index 93c713c1f627..ccda017b6794 100644
--- a/drivers/net/ethernet/sfc/falcon/falcon.c
+++ b/drivers/net/ethernet/sfc/falcon/falcon.c
@@ -1454,10 +1454,11 @@ static void falcon_stats_complete(struct ef4_nic *efx)
 	}
 }
 
-static void falcon_stats_timer_func(unsigned long context)
+static void falcon_stats_timer_func(struct timer_list *t)
 {
-	struct ef4_nic *efx = (struct ef4_nic *)context;
-	struct falcon_nic_data *nic_data = efx->nic_data;
+	struct falcon_nic_data *nic_data = from_timer(nic_data, t,
+						      stats_timer);
+	struct ef4_nic *efx = nic_data->efx;
 
 	spin_lock(&efx->stats_lock);
 
@@ -2295,6 +2296,7 @@ static int falcon_probe_nic(struct ef4_nic *efx)
 	if (!nic_data)
 		return -ENOMEM;
 	efx->nic_data = nic_data;
+	nic_data->efx = efx;
 
 	rc = -ENODEV;
 
@@ -2402,8 +2404,7 @@ static int falcon_probe_nic(struct ef4_nic *efx)
 	}
 
 	nic_data->stats_disable_count = 1;
-	setup_timer(&nic_data->stats_timer, &falcon_stats_timer_func,
-		    (unsigned long)efx);
+	timer_setup(&nic_data->stats_timer, falcon_stats_timer_func, 0);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/sfc/falcon/nic.h b/drivers/net/ethernet/sfc/falcon/nic.h
index a4c4592f6023..e2e3c008d073 100644
--- a/drivers/net/ethernet/sfc/falcon/nic.h
+++ b/drivers/net/ethernet/sfc/falcon/nic.h
@@ -267,6 +267,7 @@ enum {
 /**
  * struct falcon_nic_data - Falcon NIC state
  * @pci_dev2: Secondary function of Falcon A
+ * @efx: ef4_nic pointer
  * @board: Board state and functions
  * @stats: Hardware statistics
  * @stats_disable_count: Nest count for disabling statistics fetches
@@ -280,6 +281,7 @@ enum {
  */
 struct falcon_nic_data {
 	struct pci_dev *pci_dev2;
+	struct ef4_nic *efx;
 	struct falcon_board board;
 	u64 stats[FALCON_STAT_COUNT];
 	unsigned int stats_disable_count;
diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c
index 6a8406dc0c2b..382019b302db 100644
--- a/drivers/net/ethernet/sfc/falcon/rx.c
+++ b/drivers/net/ethernet/sfc/falcon/rx.c
@@ -376,9 +376,9 @@ void ef4_fast_push_rx_descriptors(struct ef4_rx_queue *rx_queue, bool atomic)
 		ef4_nic_notify_rx_desc(rx_queue);
 }
 
-void ef4_rx_slow_fill(unsigned long context)
+void ef4_rx_slow_fill(struct timer_list *t)
 {
-	struct ef4_rx_queue *rx_queue = (struct ef4_rx_queue *)context;
+	struct ef4_rx_queue *rx_queue = from_timer(rx_queue, t, slow_fill);
 
 	/* Post an event to cause NAPI to run and refill the queue */
 	ef4_nic_generate_fill_event(rx_queue);
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index ba45150f53c7..6608dfe455b1 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -927,6 +927,10 @@ static u16 efx_farch_handle_rx_not_ok(struct efx_rx_queue *rx_queue,
 	}
 #endif
 
+	if (efx->net_dev->features & NETIF_F_RXALL)
+		/* don't discard frame for CRC error */
+		rx_ev_eth_crc_err = false;
+
 	/* The frame must be discarded if any of these are true. */
 	return (rx_ev_eth_crc_err | rx_ev_frm_trunc |
 		rx_ev_tobe_disc | rx_ev_pause_frm) ?
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index 3df872f56289..9c2567b0d93e 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -48,7 +48,7 @@ struct efx_mcdi_async_param {
 	/* followed by request/response buffer */
 };
 
-static void efx_mcdi_timeout_async(unsigned long context);
+static void efx_mcdi_timeout_async(struct timer_list *t);
 static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
 			       bool *was_attached_out);
 static bool efx_mcdi_poll_once(struct efx_nic *efx);
@@ -87,8 +87,7 @@ int efx_mcdi_init(struct efx_nic *efx)
 	mcdi->mode = MCDI_MODE_POLL;
 	spin_lock_init(&mcdi->async_lock);
 	INIT_LIST_HEAD(&mcdi->async_list);
-	setup_timer(&mcdi->async_timer, efx_mcdi_timeout_async,
-		    (unsigned long)mcdi);
+	timer_setup(&mcdi->async_timer, efx_mcdi_timeout_async, 0);
 
 	(void) efx_mcdi_poll_reboot(efx);
 	mcdi->new_epoch = true;
@@ -608,9 +607,9 @@ static void efx_mcdi_ev_cpl(struct efx_nic *efx, unsigned int seqno,
 	}
 }
 
-static void efx_mcdi_timeout_async(unsigned long context)
+static void efx_mcdi_timeout_async(struct timer_list *t)
 {
-	struct efx_mcdi_iface *mcdi = (struct efx_mcdi_iface *)context;
+	struct efx_mcdi_iface *mcdi = from_timer(mcdi, t, async_timer);
 
 	efx_mcdi_complete_async(mcdi, true);
 }
diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c
index c7407d129c7d..6e1f282b2976 100644
--- a/drivers/net/ethernet/sfc/mcdi_port.c
+++ b/drivers/net/ethernet/sfc/mcdi_port.c
@@ -1029,6 +1029,10 @@ int efx_mcdi_set_mac(struct efx_nic *efx)
 	MCDI_POPULATE_DWORD_1(cmdbytes, SET_MAC_IN_REJECT,
 			      SET_MAC_IN_REJECT_UNCST, efx->unicast_filter);
 
+	MCDI_POPULATE_DWORD_1(cmdbytes, SET_MAC_IN_FLAGS,
+			      SET_MAC_IN_FLAG_INCLUDE_FCS,
+			      !!(efx->net_dev->features & NETIF_F_RXFCS));
+
 	switch (efx->wanted_fc) {
 	case EFX_FC_RX | EFX_FC_TX:
 		fcntl = MC_CMD_FCNTL_BIDIR;
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 42443f434569..8cb60513dca2 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -376,9 +376,9 @@ void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic)
 		efx_nic_notify_rx_desc(rx_queue);
 }
 
-void efx_rx_slow_fill(unsigned long context)
+void efx_rx_slow_fill(struct timer_list *t)
 {
-	struct efx_rx_queue *rx_queue = (struct efx_rx_queue *)context;
+	struct efx_rx_queue *rx_queue = from_timer(rx_queue, t, slow_fill);
 
 	/* Post an event to cause NAPI to run and refill the queue */
 	efx_nic_generate_fill_event(rx_queue);
diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 9c0488e0f08e..18d533fdf14c 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -764,9 +764,9 @@ static inline void ioc3_setup_duplex(struct ioc3_private *ip)
 	ioc3_w_emcr(ip->emcr);
 }
 
-static void ioc3_timer(unsigned long data)
+static void ioc3_timer(struct timer_list *t)
 {
-	struct ioc3_private *ip = (struct ioc3_private *) data;
+	struct ioc3_private *ip = from_timer(ip, t, ioc3_timer);
 
 	/* Print the link status if it has changed */
 	mii_check_media(&ip->mii, 1, 0);
@@ -818,8 +818,6 @@ out:
 static void ioc3_mii_start(struct ioc3_private *ip)
 {
 	ip->ioc3_timer.expires = jiffies + (12 * HZ)/10;  /* 1.2 sec. */
-	ip->ioc3_timer.data = (unsigned long) ip;
-	ip->ioc3_timer.function = ioc3_timer;
 	add_timer(&ip->ioc3_timer);
 }
 
@@ -1291,7 +1289,7 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 #endif
 
 	spin_lock_init(&ip->ioc3_lock);
-	init_timer(&ip->ioc3_timer);
+	timer_setup(&ip->ioc3_timer, ioc3_timer, 0);
 
 	ioc3_stop(ip);
 	ioc3_init(dev);
diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c
index 445109bd6910..c2c50522b96d 100644
--- a/drivers/net/ethernet/sis/sis190.c
+++ b/drivers/net/ethernet/sis/sis190.c
@@ -1018,10 +1018,10 @@ out_unlock:
 	rtnl_unlock();
 }
 
-static void sis190_phy_timer(unsigned long __opaque)
+static void sis190_phy_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)__opaque;
-	struct sis190_private *tp = netdev_priv(dev);
+	struct sis190_private *tp = from_timer(tp, t, timer);
+	struct net_device *dev = tp->dev;
 
 	if (likely(netif_running(dev)))
 		schedule_work(&tp->phy_task);
@@ -1039,10 +1039,8 @@ static inline void sis190_request_timer(struct net_device *dev)
 	struct sis190_private *tp = netdev_priv(dev);
 	struct timer_list *timer = &tp->timer;
 
-	init_timer(timer);
+	timer_setup(timer, sis190_phy_timer, 0);
 	timer->expires = jiffies + SIS190_PHY_TIMEOUT;
-	timer->data = (unsigned long)dev;
-	timer->function = sis190_phy_timer;
 	add_timer(timer);
 }
 
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 40bd88362e3d..4bb89f74742c 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -218,7 +218,7 @@ static void sis900_init_rxfilter (struct net_device * net_dev);
 static u16 read_eeprom(void __iomem *ioaddr, int location);
 static int mdio_read(struct net_device *net_dev, int phy_id, int location);
 static void mdio_write(struct net_device *net_dev, int phy_id, int location, int val);
-static void sis900_timer(unsigned long data);
+static void sis900_timer(struct timer_list *t);
 static void sis900_check_mode (struct net_device *net_dev, struct mii_phy *mii_phy);
 static void sis900_tx_timeout(struct net_device *net_dev);
 static void sis900_init_tx_ring(struct net_device *net_dev);
@@ -1065,10 +1065,8 @@ sis900_open(struct net_device *net_dev)
 
 	/* Set the timer to switch to check for link beat and perhaps switch
 	   to an alternate media type. */
-	init_timer(&sis_priv->timer);
+	timer_setup(&sis_priv->timer, sis900_timer, 0);
 	sis_priv->timer.expires = jiffies + HZ;
-	sis_priv->timer.data = (unsigned long)net_dev;
-	sis_priv->timer.function = sis900_timer;
 	add_timer(&sis_priv->timer);
 
 	return 0;
@@ -1302,10 +1300,10 @@ static void sis630_set_eq(struct net_device *net_dev, u8 revision)
  *	link status (ON/OFF) and link mode (10/100/Full/Half)
  */
 
-static void sis900_timer(unsigned long data)
+static void sis900_timer(struct timer_list *t)
 {
-	struct net_device *net_dev = (struct net_device *)data;
-	struct sis900_private *sis_priv = netdev_priv(net_dev);
+	struct sis900_private *sis_priv = from_timer(sis_priv, t, timer);
+	struct net_device *net_dev = sis_priv->mii_info.dev;
 	struct mii_phy *mii_phy = sis_priv->mii;
 	static const int next_tick = 5*HZ;
 	int speed = 0, duplex = 0;
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 6a0e1d4b597c..949aaef390b6 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -290,7 +290,7 @@ static int read_eeprom(struct epic_private *, int);
 static int mdio_read(struct net_device *dev, int phy_id, int location);
 static void mdio_write(struct net_device *dev, int phy_id, int loc, int val);
 static void epic_restart(struct net_device *dev);
-static void epic_timer(unsigned long data);
+static void epic_timer(struct timer_list *t);
 static void epic_tx_timeout(struct net_device *dev);
 static void epic_init_ring(struct net_device *dev);
 static netdev_tx_t epic_start_xmit(struct sk_buff *skb,
@@ -739,10 +739,8 @@ static int epic_open(struct net_device *dev)
 
 	/* Set the timer to switch to check for link beat and perhaps switch
 	   to an alternate media type. */
-	init_timer(&ep->timer);
+	timer_setup(&ep->timer, epic_timer, 0);
 	ep->timer.expires = jiffies + 3*HZ;
-	ep->timer.data = (unsigned long)dev;
-	ep->timer.function = epic_timer;				/* timer handler */
 	add_timer(&ep->timer);
 
 	return rc;
@@ -845,10 +843,10 @@ static void check_media(struct net_device *dev)
 	}
 }
 
-static void epic_timer(unsigned long data)
+static void epic_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct epic_private *ep = netdev_priv(dev);
+	struct epic_private *ep = from_timer(ep, t, timer);
+	struct net_device *dev = ep->mii.dev;
 	void __iomem *ioaddr = ep->ioaddr;
 	int next_tick = 5*HZ;
 
diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c
index 92c927aec66d..a55f430f6a7b 100644
--- a/drivers/net/ethernet/smsc/smc91c92_cs.c
+++ b/drivers/net/ethernet/smsc/smc91c92_cs.c
@@ -280,7 +280,7 @@ static void set_rx_mode(struct net_device *dev);
 static int s9k_config(struct net_device *dev, struct ifmap *map);
 static void smc_set_xcvr(struct net_device *dev, int if_port);
 static void smc_reset(struct net_device *dev);
-static void media_check(u_long arg);
+static void media_check(struct timer_list *t);
 static void mdio_sync(unsigned int addr);
 static int mdio_read(struct net_device *dev, int phy_id, int loc);
 static void mdio_write(struct net_device *dev, int phy_id, int loc, int value);
@@ -1070,7 +1070,7 @@ static int smc_open(struct net_device *dev)
     smc->packets_waiting = 0;
 
     smc_reset(dev);
-    setup_timer(&smc->media, media_check, (u_long)dev);
+    timer_setup(&smc->media, media_check, 0);
     mod_timer(&smc->media, jiffies + HZ);
 
     return 0;
@@ -1708,10 +1708,10 @@ static void smc_reset(struct net_device *dev)
 
 ======================================================================*/
 
-static void media_check(u_long arg)
+static void media_check(struct timer_list *t)
 {
-    struct net_device *dev = (struct net_device *) arg;
-    struct smc_private *smc = netdev_priv(dev);
+    struct smc_private *smc = from_timer(smc, t, media);
+    struct net_device *dev = smc->mii_if.dev;
     unsigned int ioaddr = dev->base_addr;
     u_short i, media, saved_bank;
     u_short link;
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 97035766c291..e28c0d2c58e9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -159,6 +159,7 @@ config DWMAC_SUN8I
 	tristate "Allwinner sun8i GMAC support"
 	default ARCH_SUNXI
 	depends on OF && (ARCH_SUNXI || COMPILE_TEST)
+	select MDIO_BUS_MUX
 	---help---
 	  Support for Allwinner H3 A83T A64 EMAC ethernet controllers.
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
index 6a9c954492f2..8b50afcdb52d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
@@ -118,10 +118,9 @@ int tse_pcs_init(void __iomem *base, struct tse_pcs *pcs)
 	return ret;
 }
 
-static void pcs_link_timer_callback(unsigned long data)
+static void pcs_link_timer_callback(struct tse_pcs *pcs)
 {
 	u16 val = 0;
-	struct tse_pcs *pcs = (struct tse_pcs *)data;
 	void __iomem *tse_pcs_base = pcs->tse_pcs_base;
 	void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base;
 
@@ -138,12 +137,11 @@ static void pcs_link_timer_callback(unsigned long data)
 	}
 }
 
-static void auto_nego_timer_callback(unsigned long data)
+static void auto_nego_timer_callback(struct tse_pcs *pcs)
 {
 	u16 val = 0;
 	u16 speed = 0;
 	u16 duplex = 0;
-	struct tse_pcs *pcs = (struct tse_pcs *)data;
 	void __iomem *tse_pcs_base = pcs->tse_pcs_base;
 	void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base;
 
@@ -201,14 +199,14 @@ static void auto_nego_timer_callback(unsigned long data)
 	}
 }
 
-static void aneg_link_timer_callback(unsigned long data)
+static void aneg_link_timer_callback(struct timer_list *t)
 {
-	struct tse_pcs *pcs = (struct tse_pcs *)data;
+	struct tse_pcs *pcs = from_timer(pcs, t, aneg_link_timer);
 
 	if (pcs->autoneg == AUTONEG_ENABLE)
-		auto_nego_timer_callback(data);
+		auto_nego_timer_callback(pcs);
 	else if (pcs->autoneg == AUTONEG_DISABLE)
-		pcs_link_timer_callback(data);
+		pcs_link_timer_callback(pcs);
 }
 
 void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev,
@@ -237,8 +235,8 @@ void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev,
 
 		tse_pcs_reset(tse_pcs_base, pcs);
 
-		setup_timer(&pcs->aneg_link_timer,
-			    aneg_link_timer_callback, (unsigned long)pcs);
+		timer_setup(&pcs->aneg_link_timer, aneg_link_timer_callback,
+			    0);
 		mod_timer(&pcs->aneg_link_timer, jiffies +
 			  msecs_to_jiffies(AUTONEGO_LINK_TIMER));
 	} else if (phy_dev->autoneg == AUTONEG_DISABLE) {
@@ -270,8 +268,8 @@ void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev,
 
 		tse_pcs_reset(tse_pcs_base, pcs);
 
-		setup_timer(&pcs->aneg_link_timer,
-			    aneg_link_timer_callback, (unsigned long)pcs);
+		timer_setup(&pcs->aneg_link_timer, aneg_link_timer_callback,
+			    0);
 		mod_timer(&pcs->aneg_link_timer, jiffies +
 			  msecs_to_jiffies(AUTONEGO_LINK_TIMER));
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index e82b4b70b7be..e1e5ac053760 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -442,8 +442,9 @@ struct stmmac_dma_ops {
 	void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode,
 			 int rxfifosz);
 	void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel,
-			    int fifosz);
-	void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel);
+			    int fifosz, u8 qmode);
+	void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel,
+			    int fifosz, u8 qmode);
 	/* To track extra statistic (if supported) */
 	void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x,
 				   void __iomem *ioaddr);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 866444b6c82f..2c6d7c69c8f7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -51,15 +51,11 @@
 #define NSS_COMMON_CLK_SRC_CTRL_RGMII(x)	1
 #define NSS_COMMON_CLK_SRC_CTRL_SGMII(x)	((x >= 2) ? 1 : 0)
 
-#define NSS_COMMON_MACSEC_CTL			0x28
-#define NSS_COMMON_MACSEC_CTL_EXT_BYPASS_EN(x)	(1 << x)
-
 #define NSS_COMMON_GMAC_CTL(x)			(0x30 + (x * 4))
 #define NSS_COMMON_GMAC_CTL_CSYS_REQ		BIT(19)
 #define NSS_COMMON_GMAC_CTL_PHY_IFACE_SEL	BIT(16)
 #define NSS_COMMON_GMAC_CTL_IFG_LIMIT_OFFSET	8
 #define NSS_COMMON_GMAC_CTL_IFG_OFFSET		0
-#define NSS_COMMON_GMAC_CTL_IFG_MASK		0x3f
 
 #define NSS_COMMON_CLK_DIV_RGMII_1000		1
 #define NSS_COMMON_CLK_DIV_RGMII_100		9
@@ -68,9 +64,6 @@
 #define NSS_COMMON_CLK_DIV_SGMII_100		4
 #define NSS_COMMON_CLK_DIV_SGMII_10		49
 
-#define QSGMII_PCS_MODE_CTL			0x68
-#define QSGMII_PCS_MODE_CTL_AUTONEG_EN(x)	BIT((x * 8) + 7)
-
 #define QSGMII_PCS_CAL_LCKDT_CTL		0x120
 #define QSGMII_PCS_CAL_LCKDT_CTL_RST		BIT(19)
 
@@ -83,15 +76,10 @@
 #define QSGMII_PHY_TX_DRIVER_EN			BIT(3)
 #define QSGMII_PHY_QSGMII_EN			BIT(7)
 #define QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET	12
-#define QSGMII_PHY_PHASE_LOOP_GAIN_MASK		0x7
 #define QSGMII_PHY_RX_DC_BIAS_OFFSET		18
-#define QSGMII_PHY_RX_DC_BIAS_MASK		0x3
 #define QSGMII_PHY_RX_INPUT_EQU_OFFSET		20
-#define QSGMII_PHY_RX_INPUT_EQU_MASK		0x3
 #define QSGMII_PHY_CDR_PI_SLEW_OFFSET		22
-#define QSGMII_PHY_CDR_PI_SLEW_MASK		0x3
 #define QSGMII_PHY_TX_DRV_AMP_OFFSET		28
-#define QSGMII_PHY_TX_DRV_AMP_MASK		0xf
 
 struct ipq806x_gmac {
 	struct platform_device *pdev;
@@ -217,7 +205,7 @@ static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac)
 	 * code and keep it consistent with the Linux convention, we'll number
 	 * them from 0 to 3 here.
 	 */
-	if (gmac->id < 0 || gmac->id > 3) {
+	if (gmac->id > 3) {
 		dev_err(dev, "invalid gmac id\n");
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 39c2122a4f26..e5ff734d4f9b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -17,6 +17,7 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
+#include <linux/mdio-mux.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
@@ -41,14 +42,14 @@
  *				This value is used for disabling properly EMAC
  *				and used as a good starting value in case of the
  *				boot process(uboot) leave some stuff.
- * @internal_phy:		Does the MAC embed an internal PHY
+ * @soc_has_internal_phy:	Does the MAC embed an internal PHY
  * @support_mii:		Does the MAC handle MII
  * @support_rmii:		Does the MAC handle RMII
  * @support_rgmii:		Does the MAC handle RGMII
  */
 struct emac_variant {
 	u32 default_syscon_value;
-	int internal_phy;
+	bool soc_has_internal_phy;
 	bool support_mii;
 	bool support_rmii;
 	bool support_rgmii;
@@ -61,7 +62,8 @@ struct emac_variant {
  * @rst_ephy:	reference to the optional EPHY reset for the internal PHY
  * @variant:	reference to the current board variant
  * @regmap:	regmap for using the syscon
- * @use_internal_phy: Does the current PHY choice imply using the internal PHY
+ * @internal_phy_powered: Does the internal PHY is enabled
+ * @mux_handle:	Internal pointer used by mdio-mux lib
  */
 struct sunxi_priv_data {
 	struct clk *tx_clk;
@@ -70,12 +72,13 @@ struct sunxi_priv_data {
 	struct reset_control *rst_ephy;
 	const struct emac_variant *variant;
 	struct regmap *regmap;
-	bool use_internal_phy;
+	bool internal_phy_powered;
+	void *mux_handle;
 };
 
 static const struct emac_variant emac_variant_h3 = {
 	.default_syscon_value = 0x58000,
-	.internal_phy = PHY_INTERFACE_MODE_MII,
+	.soc_has_internal_phy = true,
 	.support_mii = true,
 	.support_rmii = true,
 	.support_rgmii = true
@@ -83,20 +86,20 @@ static const struct emac_variant emac_variant_h3 = {
 
 static const struct emac_variant emac_variant_v3s = {
 	.default_syscon_value = 0x38000,
-	.internal_phy = PHY_INTERFACE_MODE_MII,
+	.soc_has_internal_phy = true,
 	.support_mii = true
 };
 
 static const struct emac_variant emac_variant_a83t = {
 	.default_syscon_value = 0,
-	.internal_phy = 0,
+	.soc_has_internal_phy = false,
 	.support_mii = true,
 	.support_rgmii = true
 };
 
 static const struct emac_variant emac_variant_a64 = {
 	.default_syscon_value = 0,
-	.internal_phy = 0,
+	.soc_has_internal_phy = false,
 	.support_mii = true,
 	.support_rmii = true,
 	.support_rgmii = true
@@ -195,6 +198,9 @@ static const struct emac_variant emac_variant_a64 = {
 #define H3_EPHY_LED_POL		BIT(17) /* 1: active low, 0: active high */
 #define H3_EPHY_SHUTDOWN	BIT(16) /* 1: shutdown, 0: power up */
 #define H3_EPHY_SELECT		BIT(15) /* 1: internal PHY, 0: external PHY */
+#define H3_EPHY_MUX_MASK	(H3_EPHY_SHUTDOWN | H3_EPHY_SELECT)
+#define DWMAC_SUN8I_MDIO_MUX_INTERNAL_ID	1
+#define DWMAC_SUN8I_MDIO_MUX_EXTERNAL_ID	2
 
 /* H3/A64 specific bits */
 #define SYSCON_RMII_EN		BIT(13) /* 1: enable RMII (overrides EPIT) */
@@ -634,6 +640,159 @@ static int sun8i_dwmac_reset(struct stmmac_priv *priv)
 	return 0;
 }
 
+/* Search in mdio-mux node for internal PHY node and get its clk/reset */
+static int get_ephy_nodes(struct stmmac_priv *priv)
+{
+	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
+	struct device_node *mdio_mux, *iphynode;
+	struct device_node *mdio_internal;
+	int ret;
+
+	mdio_mux = of_get_child_by_name(priv->device->of_node, "mdio-mux");
+	if (!mdio_mux) {
+		dev_err(priv->device, "Cannot get mdio-mux node\n");
+		return -ENODEV;
+	}
+
+	mdio_internal = of_find_compatible_node(mdio_mux, NULL,
+						"allwinner,sun8i-h3-mdio-internal");
+	if (!mdio_internal) {
+		dev_err(priv->device, "Cannot get internal_mdio node\n");
+		return -ENODEV;
+	}
+
+	/* Seek for internal PHY */
+	for_each_child_of_node(mdio_internal, iphynode) {
+		gmac->ephy_clk = of_clk_get(iphynode, 0);
+		if (IS_ERR(gmac->ephy_clk))
+			continue;
+		gmac->rst_ephy = of_reset_control_get_exclusive(iphynode, NULL);
+		if (IS_ERR(gmac->rst_ephy)) {
+			ret = PTR_ERR(gmac->rst_ephy);
+			if (ret == -EPROBE_DEFER)
+				return ret;
+			continue;
+		}
+		dev_info(priv->device, "Found internal PHY node\n");
+		return 0;
+	}
+	return -ENODEV;
+}
+
+static int sun8i_dwmac_power_internal_phy(struct stmmac_priv *priv)
+{
+	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
+	int ret;
+
+	if (gmac->internal_phy_powered) {
+		dev_warn(priv->device, "Internal PHY already powered\n");
+		return 0;
+	}
+
+	dev_info(priv->device, "Powering internal PHY\n");
+	ret = clk_prepare_enable(gmac->ephy_clk);
+	if (ret) {
+		dev_err(priv->device, "Cannot enable internal PHY\n");
+		return ret;
+	}
+
+	/* Make sure the EPHY is properly reseted, as U-Boot may leave
+	 * it at deasserted state, and thus it may fail to reset EMAC.
+	 */
+	reset_control_assert(gmac->rst_ephy);
+
+	ret = reset_control_deassert(gmac->rst_ephy);
+	if (ret) {
+		dev_err(priv->device, "Cannot deassert internal phy\n");
+		clk_disable_unprepare(gmac->ephy_clk);
+		return ret;
+	}
+
+	gmac->internal_phy_powered = true;
+
+	return 0;
+}
+
+static int sun8i_dwmac_unpower_internal_phy(struct sunxi_priv_data *gmac)
+{
+	if (!gmac->internal_phy_powered)
+		return 0;
+
+	clk_disable_unprepare(gmac->ephy_clk);
+	reset_control_assert(gmac->rst_ephy);
+	gmac->internal_phy_powered = false;
+	return 0;
+}
+
+/* MDIO multiplexing switch function
+ * This function is called by the mdio-mux layer when it thinks the mdio bus
+ * multiplexer needs to switch.
+ * 'current_child' is the current value of the mux register
+ * 'desired_child' is the value of the 'reg' property of the target child MDIO
+ * node.
+ * The first time this function is called, current_child == -1.
+ * If current_child == desired_child, then the mux is already set to the
+ * correct bus.
+ */
+static int mdio_mux_syscon_switch_fn(int current_child, int desired_child,
+				     void *data)
+{
+	struct stmmac_priv *priv = data;
+	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
+	u32 reg, val;
+	int ret = 0;
+	bool need_power_ephy = false;
+
+	if (current_child ^ desired_child) {
+		regmap_read(gmac->regmap, SYSCON_EMAC_REG, &reg);
+		switch (desired_child) {
+		case DWMAC_SUN8I_MDIO_MUX_INTERNAL_ID:
+			dev_info(priv->device, "Switch mux to internal PHY");
+			val = (reg & ~H3_EPHY_MUX_MASK) | H3_EPHY_SELECT;
+
+			need_power_ephy = true;
+			break;
+		case DWMAC_SUN8I_MDIO_MUX_EXTERNAL_ID:
+			dev_info(priv->device, "Switch mux to external PHY");
+			val = (reg & ~H3_EPHY_MUX_MASK) | H3_EPHY_SHUTDOWN;
+			need_power_ephy = false;
+			break;
+		default:
+			dev_err(priv->device, "Invalid child ID %x\n",
+				desired_child);
+			return -EINVAL;
+		}
+		regmap_write(gmac->regmap, SYSCON_EMAC_REG, val);
+		if (need_power_ephy) {
+			ret = sun8i_dwmac_power_internal_phy(priv);
+			if (ret)
+				return ret;
+		} else {
+			sun8i_dwmac_unpower_internal_phy(gmac);
+		}
+		/* After changing syscon value, the MAC need reset or it will
+		 * use the last value (and so the last PHY set).
+		 */
+		ret = sun8i_dwmac_reset(priv);
+	}
+	return ret;
+}
+
+static int sun8i_dwmac_register_mdio_mux(struct stmmac_priv *priv)
+{
+	int ret;
+	struct device_node *mdio_mux;
+	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
+
+	mdio_mux = of_get_child_by_name(priv->device->of_node, "mdio-mux");
+	if (!mdio_mux)
+		return -ENODEV;
+
+	ret = mdio_mux_init(priv->device, mdio_mux, mdio_mux_syscon_switch_fn,
+			    &gmac->mux_handle, priv, priv->mii);
+	return ret;
+}
+
 static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
 {
 	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
@@ -648,35 +807,25 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
 			 "Current syscon value is not the default %x (expect %x)\n",
 			 val, reg);
 
-	if (gmac->variant->internal_phy) {
-		if (!gmac->use_internal_phy) {
-			/* switch to external PHY interface */
-			reg &= ~H3_EPHY_SELECT;
-		} else {
-			reg |= H3_EPHY_SELECT;
-			reg &= ~H3_EPHY_SHUTDOWN;
-			dev_dbg(priv->device, "Select internal_phy %x\n", reg);
-
-			if (of_property_read_bool(priv->plat->phy_node,
-						  "allwinner,leds-active-low"))
-				reg |= H3_EPHY_LED_POL;
-			else
-				reg &= ~H3_EPHY_LED_POL;
-
-			/* Force EPHY xtal frequency to 24MHz. */
-			reg |= H3_EPHY_CLK_SEL;
-
-			ret = of_mdio_parse_addr(priv->device,
-						 priv->plat->phy_node);
-			if (ret < 0) {
-				dev_err(priv->device, "Could not parse MDIO addr\n");
-				return ret;
-			}
-			/* of_mdio_parse_addr returns a valid (0 ~ 31) PHY
-			 * address. No need to mask it again.
-			 */
-			reg |= ret << H3_EPHY_ADDR_SHIFT;
+	if (gmac->variant->soc_has_internal_phy) {
+		if (of_property_read_bool(priv->plat->phy_node,
+					  "allwinner,leds-active-low"))
+			reg |= H3_EPHY_LED_POL;
+		else
+			reg &= ~H3_EPHY_LED_POL;
+
+		/* Force EPHY xtal frequency to 24MHz. */
+		reg |= H3_EPHY_CLK_SEL;
+
+		ret = of_mdio_parse_addr(priv->device, priv->plat->phy_node);
+		if (ret < 0) {
+			dev_err(priv->device, "Could not parse MDIO addr\n");
+			return ret;
 		}
+		/* of_mdio_parse_addr returns a valid (0 ~ 31) PHY
+		 * address. No need to mask it again.
+		 */
+		reg |= 1 << H3_EPHY_ADDR_SHIFT;
 	}
 
 	if (!of_property_read_u32(node, "allwinner,tx-delay-ps", &val)) {
@@ -746,81 +895,21 @@ static void sun8i_dwmac_unset_syscon(struct sunxi_priv_data *gmac)
 	regmap_write(gmac->regmap, SYSCON_EMAC_REG, reg);
 }
 
-static int sun8i_dwmac_power_internal_phy(struct stmmac_priv *priv)
+static void sun8i_dwmac_exit(struct platform_device *pdev, void *priv)
 {
-	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
-	int ret;
-
-	if (!gmac->use_internal_phy)
-		return 0;
-
-	ret = clk_prepare_enable(gmac->ephy_clk);
-	if (ret) {
-		dev_err(priv->device, "Cannot enable ephy\n");
-		return ret;
-	}
-
-	/* Make sure the EPHY is properly reseted, as U-Boot may leave
-	 * it at deasserted state, and thus it may fail to reset EMAC.
-	 */
-	reset_control_assert(gmac->rst_ephy);
+	struct sunxi_priv_data *gmac = priv;
 
-	ret = reset_control_deassert(gmac->rst_ephy);
-	if (ret) {
-		dev_err(priv->device, "Cannot deassert ephy\n");
-		clk_disable_unprepare(gmac->ephy_clk);
-		return ret;
+	if (gmac->variant->soc_has_internal_phy) {
+		/* sun8i_dwmac_exit could be called with mdiomux uninit */
+		if (gmac->mux_handle)
+			mdio_mux_uninit(gmac->mux_handle);
+		if (gmac->internal_phy_powered)
+			sun8i_dwmac_unpower_internal_phy(gmac);
 	}
 
-	return 0;
-}
-
-static int sun8i_dwmac_unpower_internal_phy(struct sunxi_priv_data *gmac)
-{
-	if (!gmac->use_internal_phy)
-		return 0;
-
-	clk_disable_unprepare(gmac->ephy_clk);
-	reset_control_assert(gmac->rst_ephy);
-	return 0;
-}
-
-/* sun8i_power_phy() - Activate the PHY:
- * In case of error, no need to call sun8i_unpower_phy(),
- * it will be called anyway by sun8i_dwmac_exit()
- */
-static int sun8i_power_phy(struct stmmac_priv *priv)
-{
-	int ret;
-
-	ret = sun8i_dwmac_power_internal_phy(priv);
-	if (ret)
-		return ret;
-
-	ret = sun8i_dwmac_set_syscon(priv);
-	if (ret)
-		return ret;
-
-	/* After changing syscon value, the MAC need reset or it will use
-	 * the last value (and so the last PHY set.
-	 */
-	ret = sun8i_dwmac_reset(priv);
-	if (ret)
-		return ret;
-	return 0;
-}
-
-static void sun8i_unpower_phy(struct sunxi_priv_data *gmac)
-{
 	sun8i_dwmac_unset_syscon(gmac);
-	sun8i_dwmac_unpower_internal_phy(gmac);
-}
-
-static void sun8i_dwmac_exit(struct platform_device *pdev, void *priv)
-{
-	struct sunxi_priv_data *gmac = priv;
 
-	sun8i_unpower_phy(gmac);
+	reset_control_put(gmac->rst_ephy);
 
 	clk_disable_unprepare(gmac->tx_clk);
 
@@ -849,7 +938,7 @@ static struct mac_device_info *sun8i_dwmac_setup(void *ppriv)
 	if (!mac)
 		return NULL;
 
-	ret = sun8i_power_phy(priv);
+	ret = sun8i_dwmac_set_syscon(priv);
 	if (ret)
 		return NULL;
 
@@ -889,6 +978,8 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	struct sunxi_priv_data *gmac;
 	struct device *dev = &pdev->dev;
 	int ret;
+	struct stmmac_priv *priv;
+	struct net_device *ndev;
 
 	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
 	if (ret)
@@ -932,29 +1023,6 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	}
 
 	plat_dat->interface = of_get_phy_mode(dev->of_node);
-	if (plat_dat->interface == gmac->variant->internal_phy) {
-		dev_info(&pdev->dev, "Will use internal PHY\n");
-		gmac->use_internal_phy = true;
-		gmac->ephy_clk = of_clk_get(plat_dat->phy_node, 0);
-		if (IS_ERR(gmac->ephy_clk)) {
-			ret = PTR_ERR(gmac->ephy_clk);
-			dev_err(&pdev->dev, "Cannot get EPHY clock: %d\n", ret);
-			return -EINVAL;
-		}
-
-		gmac->rst_ephy = of_reset_control_get(plat_dat->phy_node, NULL);
-		if (IS_ERR(gmac->rst_ephy)) {
-			ret = PTR_ERR(gmac->rst_ephy);
-			if (ret == -EPROBE_DEFER)
-				return ret;
-			dev_err(&pdev->dev, "No EPHY reset control found %d\n",
-				ret);
-			return -EINVAL;
-		}
-	} else {
-		dev_info(&pdev->dev, "Will use external PHY\n");
-		gmac->use_internal_phy = false;
-	}
 
 	/* platform data specifying hardware features and callbacks.
 	 * hardware features were copied from Allwinner drivers.
@@ -973,12 +1041,45 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
-		sun8i_dwmac_exit(pdev, plat_dat->bsp_priv);
+		goto dwmac_exit;
+
+	ndev = dev_get_drvdata(&pdev->dev);
+	priv = netdev_priv(ndev);
+	/* The mux must be registered after parent MDIO
+	 * so after stmmac_dvr_probe()
+	 */
+	if (gmac->variant->soc_has_internal_phy) {
+		ret = get_ephy_nodes(priv);
+		if (ret)
+			goto dwmac_exit;
+		ret = sun8i_dwmac_register_mdio_mux(priv);
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to register mux\n");
+			goto dwmac_mux;
+		}
+	} else {
+		ret = sun8i_dwmac_reset(priv);
+		if (ret)
+			goto dwmac_exit;
+	}
 
 	return ret;
+dwmac_mux:
+	sun8i_dwmac_unset_syscon(gmac);
+dwmac_exit:
+	sun8i_dwmac_exit(pdev, plat_dat->bsp_priv);
+return ret;
 }
 
 static const struct of_device_id sun8i_dwmac_match[] = {
+	{ .compatible = "allwinner,sun8i-h3-emac",
+		.data = &emac_variant_h3 },
+	{ .compatible = "allwinner,sun8i-v3s-emac",
+		.data = &emac_variant_v3s },
+	{ .compatible = "allwinner,sun8i-a83t-emac",
+		.data = &emac_variant_a83t },
+	{ .compatible = "allwinner,sun50i-a64-emac",
+		.data = &emac_variant_a64 },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, sun8i_dwmac_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index d74cedf2a397..aeda3ab2d761 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -225,6 +225,8 @@ enum power_event {
 #define MTL_CHAN_RX_DEBUG(x)		(MTL_CHANX_BASE_ADDR(x) + 0x38)
 
 #define MTL_OP_MODE_RSF			BIT(5)
+#define MTL_OP_MODE_TXQEN_MASK		GENMASK(3, 2)
+#define MTL_OP_MODE_TXQEN_AV		BIT(2)
 #define MTL_OP_MODE_TXQEN		BIT(3)
 #define MTL_OP_MODE_TSF			BIT(1)
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index e84831e1b63b..c110f6850ffa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -191,7 +191,7 @@ static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 number_chan)
 }
 
 static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode,
-				       u32 channel, int fifosz)
+				       u32 channel, int fifosz, u8 qmode)
 {
 	unsigned int rqs = fifosz / 256 - 1;
 	u32 mtl_rx_op, mtl_rx_int;
@@ -218,8 +218,10 @@ static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode,
 	mtl_rx_op &= ~MTL_OP_MODE_RQS_MASK;
 	mtl_rx_op |= rqs << MTL_OP_MODE_RQS_SHIFT;
 
-	/* enable flow control only if each channel gets 4 KiB or more FIFO */
-	if (fifosz >= 4096) {
+	/* Enable flow control only if each channel gets 4 KiB or more FIFO and
+	 * only if channel is not an AVB channel.
+	 */
+	if ((fifosz >= 4096) && (qmode != MTL_QUEUE_AVB)) {
 		unsigned int rfd, rfa;
 
 		mtl_rx_op |= MTL_OP_MODE_EHFC;
@@ -271,9 +273,10 @@ static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode,
 }
 
 static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode,
-				       u32 channel)
+				       u32 channel, int fifosz, u8 qmode)
 {
 	u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+	unsigned int tqs = fifosz / 256 - 1;
 
 	if (mode == SF_DMA_MODE) {
 		pr_debug("GMAC: enable TX store and forward mode\n");
@@ -306,12 +309,18 @@ static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode,
 	 * For an IP with DWC_EQOS_NUM_TXQ > 1, the fields TXQEN and TQS are R/W
 	 * with reset values: TXQEN off, TQS 256 bytes.
 	 *
-	 * Write the bits in both cases, since it will have no effect when RO.
-	 * For DWC_EQOS_NUM_TXQ > 1, the top bits in MTL_OP_MODE_TQS_MASK might
-	 * be RO, however, writing the whole TQS field will result in a value
-	 * equal to DWC_EQOS_TXFIFO_SIZE, just like for DWC_EQOS_NUM_TXQ == 1.
+	 * TXQEN must be written for multi-channel operation and TQS must
+	 * reflect the available fifo size per queue (total fifo size / number
+	 * of enabled queues).
 	 */
-	mtl_tx_op |= MTL_OP_MODE_TXQEN | MTL_OP_MODE_TQS_MASK;
+	mtl_tx_op &= ~MTL_OP_MODE_TXQEN_MASK;
+	if (qmode != MTL_QUEUE_AVB)
+		mtl_tx_op |= MTL_OP_MODE_TXQEN;
+	else
+		mtl_tx_op |= MTL_OP_MODE_TXQEN_AV;
+	mtl_tx_op &= ~MTL_OP_MODE_TQS_MASK;
+	mtl_tx_op |= tqs << MTL_OP_MODE_TQS_SHIFT;
+
 	writel(mtl_tx_op, ioaddr +  MTL_CHAN_TX_OP_MODE(channel));
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 16bd50929084..ff4fb5eae1af 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1749,12 +1749,20 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 	u32 rx_channels_count = priv->plat->rx_queues_to_use;
 	u32 tx_channels_count = priv->plat->tx_queues_to_use;
 	int rxfifosz = priv->plat->rx_fifo_size;
+	int txfifosz = priv->plat->tx_fifo_size;
 	u32 txmode = 0;
 	u32 rxmode = 0;
 	u32 chan = 0;
+	u8 qmode = 0;
 
 	if (rxfifosz == 0)
 		rxfifosz = priv->dma_cap.rx_fifo_size;
+	if (txfifosz == 0)
+		txfifosz = priv->dma_cap.tx_fifo_size;
+
+	/* Adjust for real per queue fifo size */
+	rxfifosz /= rx_channels_count;
+	txfifosz /= tx_channels_count;
 
 	if (priv->plat->force_thresh_dma_mode) {
 		txmode = tc;
@@ -1777,12 +1785,19 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 
 	/* configure all channels */
 	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
-		for (chan = 0; chan < rx_channels_count; chan++)
+		for (chan = 0; chan < rx_channels_count; chan++) {
+			qmode = priv->plat->rx_queues_cfg[chan].mode_to_use;
+
 			priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan,
-						   rxfifosz);
+						   rxfifosz, qmode);
+		}
 
-		for (chan = 0; chan < tx_channels_count; chan++)
-			priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan);
+		for (chan = 0; chan < tx_channels_count; chan++) {
+			qmode = priv->plat->tx_queues_cfg[chan].mode_to_use;
+
+			priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan,
+						   txfifosz, qmode);
+		}
 	} else {
 		priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode,
 					rxfifosz);
@@ -1946,15 +1961,27 @@ static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan)
 static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
 					  u32 rxmode, u32 chan)
 {
+	u8 rxqmode = priv->plat->rx_queues_cfg[chan].mode_to_use;
+	u8 txqmode = priv->plat->tx_queues_cfg[chan].mode_to_use;
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
 	int rxfifosz = priv->plat->rx_fifo_size;
+	int txfifosz = priv->plat->tx_fifo_size;
 
 	if (rxfifosz == 0)
 		rxfifosz = priv->dma_cap.rx_fifo_size;
+	if (txfifosz == 0)
+		txfifosz = priv->dma_cap.tx_fifo_size;
+
+	/* Adjust for real per queue fifo size */
+	rxfifosz /= rx_channels_count;
+	txfifosz /= tx_channels_count;
 
 	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
 		priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan,
-					   rxfifosz);
-		priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan);
+					   rxfifosz, rxqmode);
+		priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan,
+					   txfifosz, txqmode);
 	} else {
 		priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode,
 					rxfifosz);
@@ -2217,10 +2244,8 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
 {
 	priv->tx_coal_frames = STMMAC_TX_FRAMES;
 	priv->tx_coal_timer = STMMAC_COAL_TX_TIMER;
-	init_timer(&priv->txtimer);
+	setup_timer(&priv->txtimer, stmmac_tx_timer, (unsigned long)priv);
 	priv->txtimer.expires = STMMAC_COAL_TIMER(priv->tx_coal_timer);
-	priv->txtimer.data = (unsigned long)priv;
-	priv->txtimer.function = stmmac_tx_timer;
 	add_timer(&priv->txtimer);
 }
 
@@ -3724,6 +3749,20 @@ static int stmmac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	return ret;
 }
 
+static int stmmac_set_mac_address(struct net_device *ndev, void *addr)
+{
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	int ret = 0;
+
+	ret = eth_mac_addr(ndev, addr);
+	if (ret)
+		return ret;
+
+	priv->hw->mac->set_umac_addr(priv->hw, ndev->dev_addr, 0);
+
+	return ret;
+}
+
 #ifdef CONFIG_DEBUG_FS
 static struct dentry *stmmac_fs_dir;
 
@@ -3951,7 +3990,7 @@ static const struct net_device_ops stmmac_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = stmmac_poll_controller,
 #endif
-	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_set_mac_address = stmmac_set_mac_address,
 };
 
 /**
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 195eb7e71473..05f122b8424a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -318,10 +318,6 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat,
 	bool mdio = true;
 	static const struct of_device_id need_mdio_ids[] = {
 		{ .compatible = "snps,dwc-qos-ethernet-4.10" },
-		{ .compatible = "allwinner,sun8i-a83t-emac" },
-		{ .compatible = "allwinner,sun8i-h3-emac" },
-		{ .compatible = "allwinner,sun8i-v3s-emac" },
-		{ .compatible = "allwinner,sun50i-a64-emac" },
 		{},
 	};
 
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 382993c1561c..113bd57e2ea0 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -4079,9 +4079,9 @@ done:
 #endif
 }
 
-static void cas_link_timer(unsigned long data)
+static void cas_link_timer(struct timer_list *t)
 {
-	struct cas *cp = (struct cas *) data;
+	struct cas *cp = from_timer(cp, t, link_timer);
 	int mask, pending = 0, reset = 0;
 	unsigned long flags;
 
@@ -5039,9 +5039,7 @@ static int cas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	spin_lock_init(&cp->stat_lock[N_TX_RINGS]);
 	mutex_init(&cp->pm_mutex);
 
-	init_timer(&cp->link_timer);
-	cp->link_timer.function = cas_link_timer;
-	cp->link_timer.data = (unsigned long) cp;
+	timer_setup(&cp->link_timer, cas_link_timer, 0);
 
 #if 1
 	/* Just in case the implementation of atomic operations
diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
index 5b56c24b6ed2..5ea037672e6f 100644
--- a/drivers/net/ethernet/sun/ldmvsw.c
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -307,7 +307,7 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 
 	/* Get (or create) the vnet associated with this port */
 	vp = vsw_get_vnet(hp, vdev->mp, &handle);
-	if (unlikely(IS_ERR(vp))) {
+	if (IS_ERR(vp)) {
 		err = PTR_ERR(vp);
 		pr_err("Failed to get vnet for vsw-port\n");
 		mdesc_release(hp);
@@ -363,8 +363,7 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	list_add_rcu(&port->list, &vp->port_list);
 	spin_unlock_irqrestore(&vp->lock, flags);
 
-	setup_timer(&port->clean_timer, sunvnet_clean_timer_expire_common,
-		    (unsigned long)port);
+	timer_setup(&port->clean_timer, sunvnet_clean_timer_expire_common, 0);
 
 	err = register_netdev(dev);
 	if (err) {
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 6a4e8e1bbd90..ab502ee35fb2 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -2221,9 +2221,9 @@ static int niu_link_status(struct niu *np, int *link_up_p)
 	return err;
 }
 
-static void niu_timer(unsigned long __opaque)
+static void niu_timer(struct timer_list *t)
 {
-	struct niu *np = (struct niu *) __opaque;
+	struct niu *np = from_timer(np, t, timer);
 	unsigned long off;
 	int err, link_up;
 
@@ -6123,10 +6123,8 @@ static int niu_open(struct net_device *dev)
 
 	err = niu_init_hw(np);
 	if (!err) {
-		init_timer(&np->timer);
+		timer_setup(&np->timer, niu_timer, 0);
 		np->timer.expires = jiffies + HZ;
-		np->timer.data = (unsigned long) np;
-		np->timer.function = niu_timer;
 
 		err = niu_enable_interrupts(np, 1);
 		if (err)
@@ -6775,10 +6773,8 @@ static int niu_change_mtu(struct net_device *dev, int new_mtu)
 
 	err = niu_init_hw(np);
 	if (!err) {
-		init_timer(&np->timer);
+		timer_setup(&np->timer, niu_timer, 0);
 		np->timer.expires = jiffies + HZ;
-		np->timer.data = (unsigned long) np;
-		np->timer.function = niu_timer;
 
 		err = niu_enable_interrupts(np, 1);
 		if (err)
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index 3189722110c2..0b1f41f6bceb 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -523,9 +523,9 @@ static int try_next_permutation(struct bigmac *bp, void __iomem *tregs)
 	return -1;
 }
 
-static void bigmac_timer(unsigned long data)
+static void bigmac_timer(struct timer_list *t)
 {
-	struct bigmac *bp = (struct bigmac *) data;
+	struct bigmac *bp = from_timer(bp, t, bigmac_timer);
 	void __iomem *tregs = bp->tregs;
 	int restart_timer = 0;
 
@@ -613,8 +613,6 @@ static void bigmac_begin_auto_negotiation(struct bigmac *bp)
 	bp->timer_state = ltrywait;
 	bp->timer_ticks = 0;
 	bp->bigmac_timer.expires = jiffies + (12 * HZ) / 10;
-	bp->bigmac_timer.data = (unsigned long) bp;
-	bp->bigmac_timer.function = bigmac_timer;
 	add_timer(&bp->bigmac_timer);
 }
 
@@ -921,7 +919,7 @@ static int bigmac_open(struct net_device *dev)
 		printk(KERN_ERR "BIGMAC: Can't order irq %d to go.\n", dev->irq);
 		return ret;
 	}
-	init_timer(&bp->bigmac_timer);
+	timer_setup(&bp->bigmac_timer, bigmac_timer, 0);
 	ret = bigmac_init_hw(bp, 0);
 	if (ret)
 		free_irq(dev->irq, bp);
@@ -1172,7 +1170,7 @@ static int bigmac_ether_init(struct platform_device *op,
 					      "board-version", 1);
 
 	/* Init auto-negotiation timer state. */
-	init_timer(&bp->bigmac_timer);
+	timer_setup(&bp->bigmac_timer, bigmac_timer, 0);
 	bp->timer_state = asleep;
 	bp->timer_ticks = 0;
 
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index fa607d062cb3..a7afcee3c5ae 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -1496,9 +1496,9 @@ static int gem_mdio_link_not_up(struct gem *gp)
 	}
 }
 
-static void gem_link_timer(unsigned long data)
+static void gem_link_timer(struct timer_list *t)
 {
-	struct gem *gp = (struct gem *) data;
+	struct gem *gp = from_timer(gp, t, link_timer);
 	struct net_device *dev = gp->dev;
 	int restart_aneg = 0;
 
@@ -2910,9 +2910,7 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	gp->msg_enable = DEFAULT_MSG;
 
-	init_timer(&gp->link_timer);
-	gp->link_timer.function = gem_link_timer;
-	gp->link_timer.data = (unsigned long) gp;
+	timer_setup(&gp->link_timer, gem_link_timer, 0);
 
 	INIT_WORK(&gp->reset_task, gem_reset_task);
 
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index 9e983e1d8249..0431f1e5f511 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -685,9 +685,9 @@ static int is_lucent_phy(struct happy_meal *hp)
 	return ret;
 }
 
-static void happy_meal_timer(unsigned long data)
+static void happy_meal_timer(struct timer_list *t)
 {
-	struct happy_meal *hp = (struct happy_meal *) data;
+	struct happy_meal *hp = from_timer(hp, t, happy_timer);
 	void __iomem *tregs = hp->tcvregs;
 	int restart_timer = 0;
 
@@ -1413,8 +1413,6 @@ force_link:
 
 	hp->timer_ticks = 0;
 	hp->happy_timer.expires = jiffies + (12 * HZ)/10;  /* 1.2 sec. */
-	hp->happy_timer.data = (unsigned long) hp;
-	hp->happy_timer.function = happy_meal_timer;
 	add_timer(&hp->happy_timer);
 }
 
@@ -2819,7 +2817,7 @@ static int happy_meal_sbus_probe_one(struct platform_device *op, int is_qfe)
 	hp->timer_state = asleep;
 	hp->timer_ticks = 0;
 
-	init_timer(&hp->happy_timer);
+	timer_setup(&hp->happy_timer, happy_meal_timer, 0);
 
 	hp->dev = dev;
 	dev->netdev_ops = &hme_netdev_ops;
@@ -3133,7 +3131,7 @@ static int happy_meal_pci_probe(struct pci_dev *pdev,
 	hp->timer_state = asleep;
 	hp->timer_ticks = 0;
 
-	init_timer(&hp->happy_timer);
+	timer_setup(&hp->happy_timer, happy_meal_timer, 0);
 
 	hp->irq = pdev->irq;
 	hp->dev = dev;
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 0b95105f7060..27fb22638885 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -492,8 +492,7 @@ static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	pr_info("%s: PORT ( remote-mac %pM%s )\n",
 		vp->dev->name, port->raddr, switch_port ? " switch-port" : "");
 
-	setup_timer(&port->clean_timer, sunvnet_clean_timer_expire_common,
-		    (unsigned long)port);
+	timer_setup(&port->clean_timer, sunvnet_clean_timer_expire_common, 0);
 
 	napi_enable(&port->napi);
 	vio_port_up(&port->vio);
diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c
index ecf456c7b6d1..8aa3ce46bb81 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.c
+++ b/drivers/net/ethernet/sun/sunvnet_common.c
@@ -1040,9 +1040,9 @@ static inline void vnet_free_skbs(struct sk_buff *skb)
 	}
 }
 
-void sunvnet_clean_timer_expire_common(unsigned long port0)
+void sunvnet_clean_timer_expire_common(struct timer_list *t)
 {
-	struct vnet_port *port = (struct vnet_port *)port0;
+	struct vnet_port *port = from_timer(port, t, clean_timer);
 	struct sk_buff *freeskbs;
 	unsigned pending;
 
diff --git a/drivers/net/ethernet/sun/sunvnet_common.h b/drivers/net/ethernet/sun/sunvnet_common.h
index 6a4dd1fb19bf..1ea0b016580a 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.h
+++ b/drivers/net/ethernet/sun/sunvnet_common.h
@@ -130,7 +130,7 @@ struct vnet {
 	((__port)->vsw ? (__port)->dev : (__port)->vp->dev)
 
 /* Common funcs */
-void sunvnet_clean_timer_expire_common(unsigned long port0);
+void sunvnet_clean_timer_expire_common(struct timer_list *t);
 int sunvnet_open_common(struct net_device *dev);
 int sunvnet_close_common(struct net_device *dev);
 void sunvnet_set_rx_mode_common(struct net_device *dev, struct vnet *vp);
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index ddd43e09111e..cd1185e66133 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -859,9 +859,7 @@ void cpsw_ale_start(struct cpsw_ale *ale)
 	cpsw_ale_control_set(ale, 0, ALE_ENABLE, 1);
 	cpsw_ale_control_set(ale, 0, ALE_CLEAR, 1);
 
-	init_timer(&ale->timer);
-	ale->timer.data	    = (unsigned long)ale;
-	ale->timer.function = cpsw_ale_timer;
+	setup_timer(&ale->timer, cpsw_ale_timer, (unsigned long)ale);
 	if (ale->ageout) {
 		ale->timer.expires = jiffies + ale->ageout;
 		add_timer(&ale->timer);
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 28cb38af1a34..4ad821655e51 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -3616,9 +3616,8 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 	}
 	spin_unlock_bh(&gbe_dev->hw_stats_lock);
 
-	init_timer(&gbe_dev->timer);
-	gbe_dev->timer.data	 = (unsigned long)gbe_dev;
-	gbe_dev->timer.function = netcp_ethss_timer;
+	setup_timer(&gbe_dev->timer, netcp_ethss_timer,
+		    (unsigned long)gbe_dev);
 	gbe_dev->timer.expires	 = jiffies + GBE_TIMER_INTERVAL;
 	add_timer(&gbe_dev->timer);
 	*inst_priv = gbe_dev;
diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c
index c8d53d8c83ee..8f53d762fbc4 100644
--- a/drivers/net/ethernet/ti/tlan.c
+++ b/drivers/net/ethernet/ti/tlan.c
@@ -172,7 +172,8 @@ static u32	tlan_handle_tx_eoc(struct net_device *, u16);
 static u32	tlan_handle_status_check(struct net_device *, u16);
 static u32	tlan_handle_rx_eoc(struct net_device *, u16);
 
-static void	tlan_timer(unsigned long);
+static void	tlan_timer(struct timer_list *t);
+static void	tlan_phy_monitor(struct timer_list *t);
 
 static void	tlan_reset_lists(struct net_device *);
 static void	tlan_free_lists(struct net_device *);
@@ -190,7 +191,6 @@ static void	tlan_phy_power_up(struct net_device *);
 static void	tlan_phy_reset(struct net_device *);
 static void	tlan_phy_start_link(struct net_device *);
 static void	tlan_phy_finish_auto_neg(struct net_device *);
-static void     tlan_phy_monitor(unsigned long);
 
 /*
   static int	tlan_phy_nop(struct net_device *);
@@ -254,11 +254,10 @@ tlan_set_timer(struct net_device *dev, u32 ticks, u32 type)
 			spin_unlock_irqrestore(&priv->lock, flags);
 		return;
 	}
-	priv->timer.function = tlan_timer;
+	priv->timer.function = (TIMER_FUNC_TYPE)tlan_timer;
 	if (!in_irq())
 		spin_unlock_irqrestore(&priv->lock, flags);
 
-	priv->timer.data = (unsigned long) dev;
 	priv->timer_set_at = jiffies;
 	priv->timer_type = type;
 	mod_timer(&priv->timer, jiffies + ticks);
@@ -926,8 +925,8 @@ static int tlan_open(struct net_device *dev)
 		return err;
 	}
 
-	init_timer(&priv->timer);
-	init_timer(&priv->media_timer);
+	timer_setup(&priv->timer, NULL, 0);
+	timer_setup(&priv->media_timer, tlan_phy_monitor, 0);
 
 	tlan_start(dev);
 
@@ -1426,8 +1425,7 @@ static u32 tlan_handle_tx_eof(struct net_device *dev, u16 host_int)
 		tlan_dio_write8(dev->base_addr,
 				TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT);
 		if (priv->timer.function == NULL) {
-			priv->timer.function = tlan_timer;
-			priv->timer.data = (unsigned long) dev;
+			priv->timer.function = (TIMER_FUNC_TYPE)tlan_timer;
 			priv->timer.expires = jiffies + TLAN_TIMER_ACT_DELAY;
 			priv->timer_set_at = jiffies;
 			priv->timer_type = TLAN_TIMER_ACTIVITY;
@@ -1578,8 +1576,7 @@ drop_and_reuse:
 		tlan_dio_write8(dev->base_addr,
 				TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT);
 		if (priv->timer.function == NULL)  {
-			priv->timer.function = tlan_timer;
-			priv->timer.data = (unsigned long) dev;
+			priv->timer.function = (TIMER_FUNC_TYPE)tlan_timer;
 			priv->timer.expires = jiffies + TLAN_TIMER_ACT_DELAY;
 			priv->timer_set_at = jiffies;
 			priv->timer_type = TLAN_TIMER_ACTIVITY;
@@ -1836,10 +1833,10 @@ ThunderLAN driver timer function
  *
  **************************************************************/
 
-static void tlan_timer(unsigned long data)
+static void tlan_timer(struct timer_list *t)
 {
-	struct net_device	*dev = (struct net_device *) data;
-	struct tlan_priv	*priv = netdev_priv(dev);
+	struct tlan_priv	*priv = from_timer(priv, t, timer);
+	struct net_device	*dev = priv->dev;
 	u32		elapsed;
 	unsigned long	flags = 0;
 
@@ -1872,7 +1869,6 @@ static void tlan_timer(unsigned long data)
 				tlan_dio_write8(dev->base_addr,
 						TLAN_LED_REG, TLAN_LED_LINK);
 			} else  {
-				priv->timer.function = tlan_timer;
 				priv->timer.expires = priv->timer_set_at
 					+ TLAN_TIMER_ACT_DELAY;
 				spin_unlock_irqrestore(&priv->lock, flags);
@@ -2317,8 +2313,6 @@ tlan_finish_reset(struct net_device *dev)
 			} else
 				netdev_info(dev, "Link active\n");
 			/* Enabling link beat monitoring */
-			priv->media_timer.function = tlan_phy_monitor;
-			priv->media_timer.data = (unsigned long) dev;
 			priv->media_timer.expires = jiffies + HZ;
 			add_timer(&priv->media_timer);
 		}
@@ -2763,10 +2757,10 @@ static void tlan_phy_finish_auto_neg(struct net_device *dev)
  *
  *******************************************************************/
 
-static void tlan_phy_monitor(unsigned long data)
+static void tlan_phy_monitor(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *) data;
-	struct tlan_priv *priv = netdev_priv(dev);
+	struct tlan_priv *priv = from_timer(priv, t, media_timer);
+	struct net_device *dev = priv->dev;
 	u16     phy;
 	u16     phy_status;
 
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
index cec9e70ab995..a913538d3213 100644
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ b/drivers/net/ethernet/toshiba/spider_net.c
@@ -2256,16 +2256,14 @@ spider_net_setup_netdev(struct spider_net_card *card)
 
 	pci_set_drvdata(card->pdev, netdev);
 
-	init_timer(&card->tx_timer);
-	card->tx_timer.function =
-		(void (*)(unsigned long)) spider_net_cleanup_tx_ring;
-	card->tx_timer.data = (unsigned long) card;
+	setup_timer(&card->tx_timer,
+		    (void(*)(unsigned long))spider_net_cleanup_tx_ring,
+		    (unsigned long)card);
 	netdev->irq = card->pdev->irq;
 
 	card->aneg_count = 0;
-	init_timer(&card->aneg_timer);
-	card->aneg_timer.function = spider_net_link_phy;
-	card->aneg_timer.data = (unsigned long) card;
+	setup_timer(&card->aneg_timer, spider_net_link_phy,
+		    (unsigned long)card);
 
 	netif_napi_add(netdev, &card->napi,
 		       spider_net_poll, SPIDER_NET_NAPI_WEIGHT);
diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c
index c2d15d9c0c33..0624b71ab5d4 100644
--- a/drivers/net/ethernet/tundra/tsi108_eth.c
+++ b/drivers/net/ethernet/tundra/tsi108_eth.c
@@ -164,7 +164,7 @@ static struct platform_driver tsi_eth_driver = {
 	},
 };
 
-static void tsi108_timed_checker(unsigned long dev_ptr);
+static void tsi108_timed_checker(struct timer_list *t);
 
 #ifdef DEBUG
 static void dump_eth_one(struct net_device *dev)
@@ -1370,7 +1370,7 @@ static int tsi108_open(struct net_device *dev)
 
 	napi_enable(&data->napi);
 
-	setup_timer(&data->timer, tsi108_timed_checker, (unsigned long)dev);
+	timer_setup(&data->timer, tsi108_timed_checker, 0);
 	mod_timer(&data->timer, jiffies + 1);
 
 	tsi108_restart_rx(data, dev);
@@ -1666,10 +1666,10 @@ regs_fail:
  * Thus, we have to do it using a timer.
  */
 
-static void tsi108_timed_checker(unsigned long dev_ptr)
+static void tsi108_timed_checker(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)dev_ptr;
-	struct tsi108_prv_data *data = netdev_priv(dev);
+	struct tsi108_prv_data *data = from_timer(data, t, timer);
+	struct net_device *dev = data->dev;
 
 	tsi108_check_phy(dev);
 	tsi108_check_rxring(dev);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index ed51018a813e..5ec39f113127 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1134,24 +1134,11 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn,
 	return t;
 }
 
-static bool is_all_zero(const u8 *fp, size_t size)
-{
-	int i;
-
-	for (i = 0; i < size; i++)
-		if (fp[i])
-			return false;
-	return true;
-}
-
 static bool is_tnl_info_zero(const struct ip_tunnel_info *info)
 {
-	if (info->key.tun_id || info->key.tun_flags || info->key.tos ||
-	    info->key.ttl || info->key.label || info->key.tp_src ||
-	    !is_all_zero((const u8 *)&info->key.u, sizeof(info->key.u)))
-		return false;
-	else
-		return true;
+	return !(info->key.tun_id || info->key.tun_flags || info->key.tos ||
+		 info->key.ttl || info->key.label || info->key.tp_src ||
+		 memchr_inv(&info->key.u, 0, sizeof(info->key.u)));
 }
 
 static bool geneve_dst_addr_equal(struct ip_tunnel_info *a,
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 021a8ec411ab..32f49c4ce457 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -35,7 +35,7 @@
 #include <linux/tcp.h>
 #include <linux/semaphore.h>
 #include <linux/compat.h>
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 
 #define SIXPACK_VERSION    "Revision: 0.3.0"
 
@@ -120,7 +120,7 @@ struct sixpack {
 
 	struct timer_list	tx_t;
 	struct timer_list	resync_t;
-	atomic_t		refcnt;
+	refcount_t		refcnt;
 	struct semaphore	dead_sem;
 	spinlock_t		lock;
 };
@@ -136,9 +136,9 @@ static int encode_sixpack(unsigned char *, unsigned char *, int, unsigned char);
  * Note that in case of DAMA operation, the data is not sent here.
  */
 
-static void sp_xmit_on_air(unsigned long channel)
+static void sp_xmit_on_air(struct timer_list *t)
 {
-	struct sixpack *sp = (struct sixpack *) channel;
+	struct sixpack *sp = from_timer(sp, t, tx_t);
 	int actual, when = sp->slottime;
 	static unsigned char random;
 
@@ -229,7 +229,7 @@ static void sp_encaps(struct sixpack *sp, unsigned char *icp, int len)
 		sp->xleft = count;
 		sp->xhead = sp->xbuff;
 		sp->status2 = count;
-		sp_xmit_on_air((unsigned long)sp);
+		sp_xmit_on_air(&sp->tx_t);
 	}
 
 	return;
@@ -381,7 +381,7 @@ static struct sixpack *sp_get(struct tty_struct *tty)
 	read_lock(&disc_data_lock);
 	sp = tty->disc_data;
 	if (sp)
-		atomic_inc(&sp->refcnt);
+		refcount_inc(&sp->refcnt);
 	read_unlock(&disc_data_lock);
 
 	return sp;
@@ -389,7 +389,7 @@ static struct sixpack *sp_get(struct tty_struct *tty)
 
 static void sp_put(struct sixpack *sp)
 {
-	if (atomic_dec_and_test(&sp->refcnt))
+	if (refcount_dec_and_test(&sp->refcnt))
 		up(&sp->dead_sem);
 }
 
@@ -500,9 +500,9 @@ static inline void tnc_set_sync_state(struct sixpack *sp, int new_tnc_state)
 		__tnc_set_sync_state(sp, new_tnc_state);
 }
 
-static void resync_tnc(unsigned long channel)
+static void resync_tnc(struct timer_list *t)
 {
-	struct sixpack *sp = (struct sixpack *) channel;
+	struct sixpack *sp = from_timer(sp, t, resync_t);
 	static char resync_cmd = 0xe8;
 
 	/* clear any data that might have been received */
@@ -526,8 +526,6 @@ static void resync_tnc(unsigned long channel)
 	/* Start resync timer again -- the TNC might be still absent */
 
 	del_timer(&sp->resync_t);
-	sp->resync_t.data	= (unsigned long) sp;
-	sp->resync_t.function	= resync_tnc;
 	sp->resync_t.expires	= jiffies + SIXP_RESYNC_TIMEOUT;
 	add_timer(&sp->resync_t);
 }
@@ -541,8 +539,6 @@ static inline int tnc_init(struct sixpack *sp)
 	sp->tty->ops->write(sp->tty, &inbyte, 1);
 
 	del_timer(&sp->resync_t);
-	sp->resync_t.data = (unsigned long) sp;
-	sp->resync_t.function = resync_tnc;
 	sp->resync_t.expires = jiffies + SIXP_RESYNC_TIMEOUT;
 	add_timer(&sp->resync_t);
 
@@ -580,7 +576,7 @@ static int sixpack_open(struct tty_struct *tty)
 	sp->dev = dev;
 
 	spin_lock_init(&sp->lock);
-	atomic_set(&sp->refcnt, 1);
+	refcount_set(&sp->refcnt, 1);
 	sema_init(&sp->dead_sem, 0);
 
 	/* !!! length of the buffers. MTU is IP MTU, not PACLEN!  */
@@ -623,11 +619,9 @@ static int sixpack_open(struct tty_struct *tty)
 
 	netif_start_queue(dev);
 
-	init_timer(&sp->tx_t);
-	sp->tx_t.function = sp_xmit_on_air;
-	sp->tx_t.data = (unsigned long) sp;
+	timer_setup(&sp->tx_t, sp_xmit_on_air, 0);
 
-	init_timer(&sp->resync_t);
+	timer_setup(&sp->resync_t, resync_tnc, 0);
 
 	spin_unlock_bh(&sp->lock);
 
@@ -676,7 +670,7 @@ static void sixpack_close(struct tty_struct *tty)
 	 * We have now ensured that nobody can start using ap from now on, but
 	 * we have to wait for all existing users to finish.
 	 */
-	if (!atomic_dec_and_test(&sp->refcnt))
+	if (!refcount_dec_and_test(&sp->refcnt))
 		down(&sp->dead_sem);
 
 	/* We must stop the queue to avoid potentially scribbling
@@ -928,8 +922,6 @@ static void decode_prio_command(struct sixpack *sp, unsigned char cmd)
 
 	if (sp->tnc_state == TNC_IN_SYNC) {
 		del_timer(&sp->resync_t);
-		sp->resync_t.data	= (unsigned long) sp;
-		sp->resync_t.function	= resync_tnc;
 		sp->resync_t.expires	= jiffies + SIXP_INIT_RESYNC_TIMEOUT;
 		add_timer(&sp->resync_t);
 	}
diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c
index 1503f10122f7..1e62d00732f2 100644
--- a/drivers/net/hamradio/baycom_epp.c
+++ b/drivers/net/hamradio/baycom_epp.c
@@ -840,6 +840,7 @@ static int epp_open(struct net_device *dev)
 	unsigned char tmp[128];
 	unsigned char stat;
 	unsigned long tstart;
+	struct pardev_cb par_cb;
 	
         if (!pp) {
                 printk(KERN_ERR "%s: parport at 0x%lx unknown\n", bc_drvname, dev->base_addr);
@@ -859,8 +860,21 @@ static int epp_open(struct net_device *dev)
                 return -EIO;
 	}
 	memset(&bc->modem, 0, sizeof(bc->modem));
-        bc->pdev = parport_register_device(pp, dev->name, NULL, epp_wakeup, 
-					   NULL, PARPORT_DEV_EXCL, dev);
+	memset(&par_cb, 0, sizeof(par_cb));
+	par_cb.wakeup = epp_wakeup;
+	par_cb.private = (void *)dev;
+	par_cb.flags = PARPORT_DEV_EXCL;
+	for (i = 0; i < NR_PORTS; i++)
+		if (baycom_device[i] == dev)
+			break;
+
+	if (i == NR_PORTS) {
+		pr_err("%s: no device found\n", bc_drvname);
+		parport_put_port(pp);
+		return -ENODEV;
+	}
+
+	bc->pdev = parport_register_dev_model(pp, dev->name, &par_cb, i);
 	parport_put_port(pp);
         if (!bc->pdev) {
                 printk(KERN_ERR "%s: cannot register parport at 0x%lx\n", bc_drvname, pp->base);
@@ -1185,6 +1199,23 @@ MODULE_LICENSE("GPL");
 
 /* --------------------------------------------------------------------- */
 
+static int baycom_epp_par_probe(struct pardevice *par_dev)
+{
+	struct device_driver *drv = par_dev->dev.driver;
+	int len = strlen(drv->name);
+
+	if (strncmp(par_dev->name, drv->name, len))
+		return -ENODEV;
+
+	return 0;
+}
+
+static struct parport_driver baycom_epp_par_driver = {
+	.name = "bce",
+	.probe = baycom_epp_par_probe,
+	.devmodel = true,
+};
+
 static void __init baycom_epp_dev_setup(struct net_device *dev)
 {
 	struct baycom_state *bc = netdev_priv(dev);
@@ -1204,10 +1235,15 @@ static void __init baycom_epp_dev_setup(struct net_device *dev)
 
 static int __init init_baycomepp(void)
 {
-	int i, found = 0;
+	int i, found = 0, ret;
 	char set_hw = 1;
 
 	printk(bc_drvinfo);
+
+	ret = parport_register_driver(&baycom_epp_par_driver);
+	if (ret)
+		return ret;
+
 	/*
 	 * register net devices
 	 */
@@ -1241,7 +1277,12 @@ static int __init init_baycomepp(void)
 		found++;
 	}
 
-	return found ? 0 : -ENXIO;
+	if (found == 0) {
+		parport_unregister_driver(&baycom_epp_par_driver);
+		return -ENXIO;
+	}
+
+	return 0;
 }
 
 static void __exit cleanup_baycomepp(void)
@@ -1260,6 +1301,7 @@ static void __exit cleanup_baycomepp(void)
 				printk(paranoia_str, "cleanup_module");
 		}
 	}
+	parport_unregister_driver(&baycom_epp_par_driver);
 }
 
 module_init(init_baycomepp);
diff --git a/drivers/net/hamradio/baycom_par.c b/drivers/net/hamradio/baycom_par.c
index e1783832d304..1f7ceafd61ff 100644
--- a/drivers/net/hamradio/baycom_par.c
+++ b/drivers/net/hamradio/baycom_par.c
@@ -311,7 +311,9 @@ static void par96_wakeup(void *handle)
 static int par96_open(struct net_device *dev)
 {
 	struct baycom_state *bc = netdev_priv(dev);
+	struct pardev_cb par_cb;
 	struct parport *pp;
+	int i;
 
 	if (!dev || !bc)
 		return -ENXIO;
@@ -332,8 +334,21 @@ static int par96_open(struct net_device *dev)
 	}
 	memset(&bc->modem, 0, sizeof(bc->modem));
 	bc->hdrv.par.bitrate = 9600;
-	bc->pdev = parport_register_device(pp, dev->name, NULL, par96_wakeup, 
-				 par96_interrupt, PARPORT_DEV_EXCL, dev);
+	memset(&par_cb, 0, sizeof(par_cb));
+	par_cb.wakeup = par96_wakeup;
+	par_cb.irq_func = par96_interrupt;
+	par_cb.private = (void *)dev;
+	par_cb.flags = PARPORT_DEV_EXCL;
+	for (i = 0; i < NR_PORTS; i++)
+		if (baycom_device[i] == dev)
+			break;
+
+	if (i == NR_PORTS) {
+		pr_err("%s: no device found\n", bc_drvname);
+		parport_put_port(pp);
+		return -ENODEV;
+	}
+	bc->pdev = parport_register_dev_model(pp, dev->name, &par_cb, i);
 	parport_put_port(pp);
 	if (!bc->pdev) {
 		printk(KERN_ERR "baycom_par: cannot register parport at 0x%lx\n", dev->base_addr);
@@ -490,12 +505,34 @@ MODULE_LICENSE("GPL");
 
 /* --------------------------------------------------------------------- */
 
+static int baycom_par_probe(struct pardevice *par_dev)
+{
+	struct device_driver *drv = par_dev->dev.driver;
+	int len = strlen(drv->name);
+
+	if (strncmp(par_dev->name, drv->name, len))
+		return -ENODEV;
+
+	return 0;
+}
+
+static struct parport_driver baycom_par_driver = {
+	.name = "bcp",
+	.probe = baycom_par_probe,
+	.devmodel = true,
+};
+
 static int __init init_baycompar(void)
 {
-	int i, found = 0;
+	int i, found = 0, ret;
 	char set_hw = 1;
 
 	printk(bc_drvinfo);
+
+	ret = parport_register_driver(&baycom_par_driver);
+	if (ret)
+		return ret;
+
 	/*
 	 * register net devices
 	 */
@@ -524,8 +561,10 @@ static int __init init_baycompar(void)
 		baycom_device[i] = dev;
 	}
 
-	if (!found)
+	if (!found) {
+		parport_unregister_driver(&baycom_par_driver);
 		return -ENXIO;
+	}
 	return 0;
 }
 
@@ -539,6 +578,7 @@ static void __exit cleanup_baycompar(void)
 		if (dev)
 			hdlcdrv_unregister(dev);
 	}
+	parport_unregister_driver(&baycom_par_driver);
 }
 
 module_init(init_baycompar);
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index aec6c26563cf..c180b480f8ef 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -440,7 +440,6 @@ static void ax_encaps(struct net_device *dev, unsigned char *icp, int len)
 		ax_changedmtu(ax);
 
 	if (len > ax->mtu) {		/* Sigh, shouldn't occur BUT ... */
-		len = ax->mtu;
 		printk(KERN_ERR "mkiss: %s: truncating oversized transmit packet!\n", ax->dev->name);
 		dev->stats.tx_dropped++;
 		netif_start_queue(dev);
@@ -477,7 +476,8 @@ static void ax_encaps(struct net_device *dev, unsigned char *icp, int len)
 				  cmd = 0;
 				}
 				ax->crcauto = (cmd ? 0 : 1);
-				printk(KERN_INFO "mkiss: %s: crc mode %s %d\n", ax->dev->name, (len) ? "set to" : "is", cmd);
+				printk(KERN_INFO "mkiss: %s: crc mode set to %d\n",
+				       ax->dev->name, cmd);
 			}
 			spin_unlock_bh(&ax->buflock);
 			netif_start_queue(dev);
diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c
index 295f267b73ea..c9f7215c5dc2 100644
--- a/drivers/net/hamradio/scc.c
+++ b/drivers/net/hamradio/scc.c
@@ -185,14 +185,15 @@
 static const char banner[] __initconst = KERN_INFO \
 	"AX.25: Z8530 SCC driver version "VERSION".dl1bke\n";
 
-static void t_dwait(unsigned long);
-static void t_txdelay(unsigned long);
-static void t_tail(unsigned long);
-static void t_busy(unsigned long);
-static void t_maxkeyup(unsigned long);
-static void t_idle(unsigned long);
+static void t_dwait(struct timer_list *t);
+static void t_txdelay(struct timer_list *t);
+static void t_tail(struct timer_list *t);
+static void t_busy(struct timer_list *);
+static void t_maxkeyup(struct timer_list *);
+static void t_idle(struct timer_list *t);
 static void scc_tx_done(struct scc_channel *);
-static void scc_start_tx_timer(struct scc_channel *, void (*)(unsigned long), unsigned long);
+static void scc_start_tx_timer(struct scc_channel *,
+			       void (*)(struct timer_list *), unsigned long);
 static void scc_start_maxkeyup(struct scc_channel *);
 static void scc_start_defer(struct scc_channel *);
 
@@ -992,24 +993,27 @@ static void scc_key_trx(struct scc_channel *scc, char tx)
 
 /* ----> SCC timer interrupt handler and friends. <---- */
 
-static void __scc_start_tx_timer(struct scc_channel *scc, void (*handler)(unsigned long), unsigned long when)
+static void __scc_start_tx_timer(struct scc_channel *scc,
+				 void (*handler)(struct timer_list *t),
+				 unsigned long when)
 {
 	del_timer(&scc->tx_t);
 
 	if (when == 0)
 	{
-		handler((unsigned long) scc);
+		handler(&scc->tx_t);
 	} else 
 	if (when != TIMER_OFF)
 	{
-		scc->tx_t.data = (unsigned long) scc;
-		scc->tx_t.function = handler;
+		scc->tx_t.function = (TIMER_FUNC_TYPE)handler;
 		scc->tx_t.expires = jiffies + (when*HZ)/100;
 		add_timer(&scc->tx_t);
 	}
 }
 
-static void scc_start_tx_timer(struct scc_channel *scc, void (*handler)(unsigned long), unsigned long when)
+static void scc_start_tx_timer(struct scc_channel *scc,
+			       void (*handler)(struct timer_list *t),
+			       unsigned long when)
 {
 	unsigned long flags;
 	
@@ -1027,8 +1031,7 @@ static void scc_start_defer(struct scc_channel *scc)
 	
 	if (scc->kiss.maxdefer != 0 && scc->kiss.maxdefer != TIMER_OFF)
 	{
-		scc->tx_wdog.data = (unsigned long) scc;
-		scc->tx_wdog.function = t_busy;
+		scc->tx_wdog.function = (TIMER_FUNC_TYPE)t_busy;
 		scc->tx_wdog.expires = jiffies + HZ*scc->kiss.maxdefer;
 		add_timer(&scc->tx_wdog);
 	}
@@ -1044,8 +1047,7 @@ static void scc_start_maxkeyup(struct scc_channel *scc)
 	
 	if (scc->kiss.maxkeyup != 0 && scc->kiss.maxkeyup != TIMER_OFF)
 	{
-		scc->tx_wdog.data = (unsigned long) scc;
-		scc->tx_wdog.function = t_maxkeyup;
+		scc->tx_wdog.function = (TIMER_FUNC_TYPE)t_maxkeyup;
 		scc->tx_wdog.expires = jiffies + HZ*scc->kiss.maxkeyup;
 		add_timer(&scc->tx_wdog);
 	}
@@ -1121,9 +1123,9 @@ static inline int is_grouped(struct scc_channel *scc)
  * fulldup == 2:  mintime expired, reset status or key trx and start txdelay
  */
 
-static void t_dwait(unsigned long channel)
+static void t_dwait(struct timer_list *t)
 {
-	struct scc_channel *scc = (struct scc_channel *) channel;
+	struct scc_channel *scc = from_timer(scc, t, tx_t);
 	
 	if (scc->stat.tx_state == TXS_WAIT)	/* maxkeyup or idle timeout */
 	{
@@ -1163,9 +1165,9 @@ static void t_dwait(unsigned long channel)
  * kick transmission by a fake scc_txint(scc), start 'maxkeyup' watchdog.
  */
 
-static void t_txdelay(unsigned long channel)
+static void t_txdelay(struct timer_list *t)
 {
-	struct scc_channel *scc = (struct scc_channel *) channel;
+	struct scc_channel *scc = from_timer(scc, t, tx_t);
 
 	scc_start_maxkeyup(scc);
 
@@ -1184,9 +1186,9 @@ static void t_txdelay(unsigned long channel)
  * transmission after 'mintime' seconds
  */
 
-static void t_tail(unsigned long channel)
+static void t_tail(struct timer_list *t)
 {
-	struct scc_channel *scc = (struct scc_channel *) channel;
+	struct scc_channel *scc = from_timer(scc, t, tx_t);
 	unsigned long flags;
 	
 	spin_lock_irqsave(&scc->lock, flags); 
@@ -1211,9 +1213,9 @@ static void t_tail(unsigned long channel)
  * throw away send buffers if DCD remains active too long.
  */
 
-static void t_busy(unsigned long channel)
+static void t_busy(struct timer_list *t)
 {
-	struct scc_channel *scc = (struct scc_channel *) channel;
+	struct scc_channel *scc = from_timer(scc, t, tx_wdog);
 
 	del_timer(&scc->tx_t);
 	netif_stop_queue(scc->dev);	/* don't pile on the wabbit! */
@@ -1230,9 +1232,9 @@ static void t_busy(unsigned long channel)
  * this is our watchdog.
  */
 
-static void t_maxkeyup(unsigned long channel)
+static void t_maxkeyup(struct timer_list *t)
 {
-	struct scc_channel *scc = (struct scc_channel *) channel;
+	struct scc_channel *scc = from_timer(scc, t, tx_wdog);
 	unsigned long flags;
 
 	spin_lock_irqsave(&scc->lock, flags);
@@ -1264,9 +1266,9 @@ static void t_maxkeyup(unsigned long channel)
  * expires.
  */
 
-static void t_idle(unsigned long channel)
+static void t_idle(struct timer_list *t)
 {
-	struct scc_channel *scc = (struct scc_channel *) channel;
+	struct scc_channel *scc = from_timer(scc, t, tx_t);
 	
 	del_timer(&scc->tx_wdog);
 
@@ -1397,9 +1399,9 @@ static unsigned long scc_get_param(struct scc_channel *scc, unsigned int cmd)
 /* *			Send calibration pattern		     * */
 /* ******************************************************************* */
 
-static void scc_stop_calibrate(unsigned long channel)
+static void scc_stop_calibrate(struct timer_list *t)
 {
-	struct scc_channel *scc = (struct scc_channel *) channel;
+	struct scc_channel *scc = from_timer(scc, t, tx_wdog);
 	unsigned long flags;
 	
 	spin_lock_irqsave(&scc->lock, flags);
@@ -1426,8 +1428,7 @@ scc_start_calibrate(struct scc_channel *scc, int duration, unsigned char pattern
 
 	del_timer(&scc->tx_wdog);
 
-	scc->tx_wdog.data = (unsigned long) scc;
-	scc->tx_wdog.function = scc_stop_calibrate;
+	scc->tx_wdog.function = (TIMER_FUNC_TYPE)scc_stop_calibrate;
 	scc->tx_wdog.expires = jiffies + HZ*duration;
 	add_timer(&scc->tx_wdog);
 
@@ -1522,8 +1523,8 @@ static int scc_net_alloc(const char *name, struct scc_channel *scc)
 	dev->ml_priv = scc;
 	scc->dev = dev;
 	spin_lock_init(&scc->lock);
-	init_timer(&scc->tx_t);
-	init_timer(&scc->tx_wdog);
+	timer_setup(&scc->tx_t, NULL, 0);
+	timer_setup(&scc->tx_wdog, NULL, 0);
 
 	err = register_netdevice(dev);
 	if (err) {
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 7a7c5224a336..b88c5cc00a63 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -647,7 +647,7 @@ static void yam_arbitrate(struct net_device *dev)
 	yam_start_tx(dev, yp);
 }
 
-static void yam_dotimer(unsigned long dummy)
+static void yam_dotimer(struct timer_list *unused)
 {
 	int i;
 
@@ -1164,7 +1164,7 @@ static int __init yam_init_driver(void)
 
 	}
 
-	yam_timer.function = yam_dotimer;
+	timer_setup(&yam_timer, yam_dotimer, 0);
 	yam_timer.expires = jiffies + HZ / 100;
 	add_timer(&yam_timer);
 
diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c
index 71ddadbf2368..8483f03d5a41 100644
--- a/drivers/net/hippi/rrunner.c
+++ b/drivers/net/hippi/rrunner.c
@@ -1146,10 +1146,10 @@ static inline void rr_raz_rx(struct rr_private *rrpriv,
 	}
 }
 
-static void rr_timer(unsigned long data)
+static void rr_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct rr_private *rrpriv = netdev_priv(dev);
+	struct rr_private *rrpriv = from_timer(rrpriv, t, timer);
+	struct net_device *dev = pci_get_drvdata(rrpriv->pci_dev);
 	struct rr_regs __iomem *regs = rrpriv->regs;
 	unsigned long flags;
 
@@ -1229,10 +1229,8 @@ static int rr_open(struct net_device *dev)
 
 	/* Set the timer to switch to check for link beat and perhaps switch
 	   to an alternate media type. */
-	init_timer(&rrpriv->timer);
+	timer_setup(&rrpriv->timer, rr_timer, 0);
 	rrpriv->timer.expires = RUN_AT(5*HZ);           /* 5 sec. watchdog */
-	rrpriv->timer.data = (unsigned long)dev;
-	rrpriv->timer.function = rr_timer;               /* timer handler */
 	add_timer(&rrpriv->timer);
 
 	netif_start_queue(dev);
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 5176be76ca7d..4958bb6b7376 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -179,7 +179,7 @@ struct rndis_device {
 
 	u8 hw_mac_adr[ETH_ALEN];
 	u8 rss_key[NETVSC_HASH_KEYLEN];
-	u16 ind_table[ITAB_NUM];
+	u16 rx_table[ITAB_NUM];
 };
 
 
@@ -686,6 +686,8 @@ struct netvsc_ethtool_stats {
 	unsigned long tx_busy;
 	unsigned long tx_send_full;
 	unsigned long rx_comp_busy;
+	unsigned long stop_queue;
+	unsigned long wake_queue;
 };
 
 struct netvsc_vf_pcpu_stats {
@@ -702,6 +704,14 @@ struct netvsc_reconfig {
 	u32 event;
 };
 
+/* L4 hash bits for different protocols */
+#define HV_TCP4_L4HASH 1
+#define HV_TCP6_L4HASH 2
+#define HV_UDP4_L4HASH 4
+#define HV_UDP6_L4HASH 8
+#define HV_DEFAULT_L4HASH (HV_TCP4_L4HASH | HV_TCP6_L4HASH | HV_UDP4_L4HASH | \
+			   HV_UDP6_L4HASH)
+
 /* The context of the netvsc device  */
 struct net_device_context {
 	/* point back to our device context */
@@ -721,13 +731,12 @@ struct net_device_context {
 
 	u32 tx_checksum_mask;
 
-	u32 tx_send_table[VRSS_SEND_TAB_SIZE];
+	u32 tx_table[VRSS_SEND_TAB_SIZE];
 
 	/* Ethtool settings */
-	bool udp4_l4_hash;
-	bool udp6_l4_hash;
 	u8 duplex;
 	u32 speed;
+	u32 l4_hash; /* L4 hash settings */
 	struct netvsc_ethtool_stats eth_stats;
 
 	/* State to manage the associated VF interface. */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 8d5077fb0492..5bb6a20072dd 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -484,7 +484,7 @@ static int netvsc_connect_vsp(struct hv_device *device,
 			      struct netvsc_device *net_device,
 			      const struct netvsc_device_info *device_info)
 {
-	const u32 ver_list[] = {
+	static const u32 ver_list[] = {
 		NVSP_PROTOCOL_VERSION_1, NVSP_PROTOCOL_VERSION_2,
 		NVSP_PROTOCOL_VERSION_4, NVSP_PROTOCOL_VERSION_5
 	};
@@ -609,6 +609,7 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 {
 	struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id;
 	struct net_device *ndev = hv_get_drvdata(device);
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
 	struct vmbus_channel *channel = device->channel;
 	u16 q_idx = 0;
 	int queue_sends;
@@ -643,8 +644,10 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 
 	if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) &&
 	    (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER ||
-	     queue_sends < 1))
+	     queue_sends < 1)) {
 		netif_tx_wake_queue(netdev_get_tx_queue(ndev, q_idx));
+		ndev_ctx->eth_stats.wake_queue++;
+	}
 }
 
 static void netvsc_send_completion(struct netvsc_device *net_device,
@@ -749,6 +752,7 @@ static inline int netvsc_send_pkt(
 		&net_device->chan_table[packet->q_idx];
 	struct vmbus_channel *out_channel = nvchan->channel;
 	struct net_device *ndev = hv_get_drvdata(device);
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
 	struct netdev_queue *txq = netdev_get_tx_queue(ndev, packet->q_idx);
 	u64 req_id;
 	int ret;
@@ -789,12 +793,16 @@ static inline int netvsc_send_pkt(
 	if (ret == 0) {
 		atomic_inc_return(&nvchan->queue_sends);
 
-		if (ring_avail < RING_AVAIL_PERCENT_LOWATER)
+		if (ring_avail < RING_AVAIL_PERCENT_LOWATER) {
 			netif_tx_stop_queue(txq);
+			ndev_ctx->eth_stats.stop_queue++;
+		}
 	} else if (ret == -EAGAIN) {
 		netif_tx_stop_queue(txq);
+		ndev_ctx->eth_stats.stop_queue++;
 		if (atomic_read(&nvchan->queue_sends) < 1) {
 			netif_tx_wake_queue(txq);
+			ndev_ctx->eth_stats.wake_queue++;
 			ret = -ENOSPC;
 		}
 	} else {
@@ -1102,7 +1110,7 @@ static void netvsc_send_table(struct hv_device *hdev,
 		      nvmsg->msg.v5_msg.send_table.offset);
 
 	for (i = 0; i < count; i++)
-		net_device_ctx->tx_send_table[i] = tab[i];
+		net_device_ctx->tx_table[i] = tab[i];
 }
 
 static void netvsc_send_vf(struct net_device_context *net_device_ctx,
@@ -1247,6 +1255,9 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 	if (!net_device)
 		return ERR_PTR(-ENOMEM);
 
+	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
+		net_device_ctx->tx_table[i] = 0;
+
 	net_device->ring_size = ring_size;
 
 	/* Because the device uses NAPI, all the interrupt batching and
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index a32ae02e1b6c..da216ca4f2b2 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -203,7 +203,7 @@ static inline u32 netvsc_get_hash(
 	const struct net_device_context *ndc)
 {
 	struct flow_keys flow;
-	u32 hash;
+	u32 hash, pkt_proto = 0;
 	static u32 hashrnd __read_mostly;
 
 	net_get_random_once(&hashrnd, sizeof(hashrnd));
@@ -211,11 +211,25 @@ static inline u32 netvsc_get_hash(
 	if (!skb_flow_dissect_flow_keys(skb, &flow, 0))
 		return 0;
 
-	if (flow.basic.ip_proto == IPPROTO_TCP ||
-	    (flow.basic.ip_proto == IPPROTO_UDP &&
-	     ((flow.basic.n_proto == htons(ETH_P_IP) && ndc->udp4_l4_hash) ||
-	      (flow.basic.n_proto == htons(ETH_P_IPV6) &&
-	       ndc->udp6_l4_hash)))) {
+	switch (flow.basic.ip_proto) {
+	case IPPROTO_TCP:
+		if (flow.basic.n_proto == htons(ETH_P_IP))
+			pkt_proto = HV_TCP4_L4HASH;
+		else if (flow.basic.n_proto == htons(ETH_P_IPV6))
+			pkt_proto = HV_TCP6_L4HASH;
+
+		break;
+
+	case IPPROTO_UDP:
+		if (flow.basic.n_proto == htons(ETH_P_IP))
+			pkt_proto = HV_UDP4_L4HASH;
+		else if (flow.basic.n_proto == htons(ETH_P_IPV6))
+			pkt_proto = HV_UDP6_L4HASH;
+
+		break;
+	}
+
+	if (pkt_proto & ndc->l4_hash) {
 		return skb_get_hash(skb);
 	} else {
 		if (flow.basic.n_proto == htons(ETH_P_IP))
@@ -238,8 +252,8 @@ static inline int netvsc_get_tx_queue(struct net_device *ndev,
 	struct sock *sk = skb->sk;
 	int q_idx;
 
-	q_idx = ndc->tx_send_table[netvsc_get_hash(skb, ndc) &
-				   (VRSS_SEND_TAB_SIZE - 1)];
+	q_idx = ndc->tx_table[netvsc_get_hash(skb, ndc) &
+			      (VRSS_SEND_TAB_SIZE - 1)];
 
 	/* If queue index changed record the new value */
 	if (q_idx != old_idx &&
@@ -898,8 +912,7 @@ static void netvsc_init_settings(struct net_device *dev)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
 
-	ndc->udp4_l4_hash = true;
-	ndc->udp6_l4_hash = true;
+	ndc->l4_hash = HV_DEFAULT_L4HASH;
 
 	ndc->speed = SPEED_UNKNOWN;
 	ndc->duplex = DUPLEX_FULL;
@@ -1126,6 +1139,8 @@ static const struct {
 	{ "tx_busy",	  offsetof(struct netvsc_ethtool_stats, tx_busy) },
 	{ "tx_send_full", offsetof(struct netvsc_ethtool_stats, tx_send_full) },
 	{ "rx_comp_busy", offsetof(struct netvsc_ethtool_stats, rx_comp_busy) },
+	{ "stop_queue", offsetof(struct netvsc_ethtool_stats, stop_queue) },
+	{ "wake_queue", offsetof(struct netvsc_ethtool_stats, wake_queue) },
 }, vf_stats[] = {
 	{ "vf_rx_packets", offsetof(struct netvsc_vf_pcpu_stats, rx_packets) },
 	{ "vf_rx_bytes",   offsetof(struct netvsc_vf_pcpu_stats, rx_bytes) },
@@ -1243,23 +1258,32 @@ static int
 netvsc_get_rss_hash_opts(struct net_device_context *ndc,
 			 struct ethtool_rxnfc *info)
 {
+	const u32 l4_flag = RXH_L4_B_0_1 | RXH_L4_B_2_3;
+
 	info->data = RXH_IP_SRC | RXH_IP_DST;
 
 	switch (info->flow_type) {
 	case TCP_V4_FLOW:
+		if (ndc->l4_hash & HV_TCP4_L4HASH)
+			info->data |= l4_flag;
+
+		break;
+
 	case TCP_V6_FLOW:
-		info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		if (ndc->l4_hash & HV_TCP6_L4HASH)
+			info->data |= l4_flag;
+
 		break;
 
 	case UDP_V4_FLOW:
-		if (ndc->udp4_l4_hash)
-			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		if (ndc->l4_hash & HV_UDP4_L4HASH)
+			info->data |= l4_flag;
 
 		break;
 
 	case UDP_V6_FLOW:
-		if (ndc->udp6_l4_hash)
-			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		if (ndc->l4_hash & HV_UDP6_L4HASH)
+			info->data |= l4_flag;
 
 		break;
 
@@ -1300,23 +1324,51 @@ static int netvsc_set_rss_hash_opts(struct net_device_context *ndc,
 {
 	if (info->data == (RXH_IP_SRC | RXH_IP_DST |
 			   RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
-		if (info->flow_type == UDP_V4_FLOW)
-			ndc->udp4_l4_hash = true;
-		else if (info->flow_type == UDP_V6_FLOW)
-			ndc->udp6_l4_hash = true;
-		else
+		switch (info->flow_type) {
+		case TCP_V4_FLOW:
+			ndc->l4_hash |= HV_TCP4_L4HASH;
+			break;
+
+		case TCP_V6_FLOW:
+			ndc->l4_hash |= HV_TCP6_L4HASH;
+			break;
+
+		case UDP_V4_FLOW:
+			ndc->l4_hash |= HV_UDP4_L4HASH;
+			break;
+
+		case UDP_V6_FLOW:
+			ndc->l4_hash |= HV_UDP6_L4HASH;
+			break;
+
+		default:
 			return -EOPNOTSUPP;
+		}
 
 		return 0;
 	}
 
 	if (info->data == (RXH_IP_SRC | RXH_IP_DST)) {
-		if (info->flow_type == UDP_V4_FLOW)
-			ndc->udp4_l4_hash = false;
-		else if (info->flow_type == UDP_V6_FLOW)
-			ndc->udp6_l4_hash = false;
-		else
+		switch (info->flow_type) {
+		case TCP_V4_FLOW:
+			ndc->l4_hash &= ~HV_TCP4_L4HASH;
+			break;
+
+		case TCP_V6_FLOW:
+			ndc->l4_hash &= ~HV_TCP6_L4HASH;
+			break;
+
+		case UDP_V4_FLOW:
+			ndc->l4_hash &= ~HV_UDP4_L4HASH;
+			break;
+
+		case UDP_V6_FLOW:
+			ndc->l4_hash &= ~HV_UDP6_L4HASH;
+			break;
+
+		default:
 			return -EOPNOTSUPP;
+		}
 
 		return 0;
 	}
@@ -1382,7 +1434,7 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 	rndis_dev = ndev->extension;
 	if (indir) {
 		for (i = 0; i < ITAB_NUM; i++)
-			indir[i] = rndis_dev->ind_table[i];
+			indir[i] = rndis_dev->rx_table[i];
 	}
 
 	if (key)
@@ -1412,7 +1464,7 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir,
 				return -EINVAL;
 
 		for (i = 0; i < ITAB_NUM; i++)
-			rndis_dev->ind_table[i] = indir[i];
+			rndis_dev->rx_table[i] = indir[i];
 	}
 
 	if (!key) {
@@ -1746,7 +1798,7 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto rx_handler_failed;
 	}
 
-	ret = netdev_upper_dev_link(vf_netdev, ndev);
+	ret = netdev_upper_dev_link(vf_netdev, ndev, NULL);
 	if (ret != 0) {
 		netdev_err(vf_netdev,
 			   "can not set master device %s (err = %d)\n",
@@ -1935,6 +1987,12 @@ static int netvsc_probe(struct hv_device *dev,
 	/* We always need headroom for rndis header */
 	net->needed_headroom = RNDIS_AND_PPI_SIZE;
 
+	/* Initialize the number of queues to be 1, we may change it if more
+	 * channels are offered later.
+	 */
+	netif_set_real_num_tx_queues(net, 1);
+	netif_set_real_num_rx_queues(net, 1);
+
 	/* Notify the netvsc driver of the new device */
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.ring_size = ring_size;
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 065b204d8e17..0648eebda829 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -759,7 +759,7 @@ int rndis_filter_set_rss_param(struct rndis_device *rdev,
 	/* Set indirection table entries */
 	itab = (u32 *)(rssp + 1);
 	for (i = 0; i < ITAB_NUM; i++)
-		itab[i] = rdev->ind_table[i];
+		itab[i] = rdev->rx_table[i];
 
 	/* Set hask key values */
 	keyp = (u8 *)((unsigned long)rssp + rssp->kashkey_offset);
@@ -1114,6 +1114,9 @@ void rndis_set_subchannel(struct work_struct *w)
 	netif_set_real_num_tx_queues(ndev, nvdev->num_chn);
 	netif_set_real_num_rx_queues(ndev, nvdev->num_chn);
 
+	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
+		ndev_ctx->tx_table[i] = i % nvdev->num_chn;
+
 	rtnl_unlock();
 	return;
 
@@ -1284,8 +1287,8 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 	net_device->num_chn = min(net_device->max_chn, device_info->num_chn);
 
 	for (i = 0; i < ITAB_NUM; i++)
-		rndis_device->ind_table[i] = ethtool_rxfh_indir_default(i,
-							net_device->num_chn);
+		rndis_device->rx_table[i] = ethtool_rxfh_indir_default(
+						i, net_device->num_chn);
 
 	atomic_set(&net_device->open_chn, 1);
 	vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open);
diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c
index ef688518ad77..d5584063049f 100644
--- a/drivers/net/ieee802154/atusb.c
+++ b/drivers/net/ieee802154/atusb.c
@@ -21,6 +21,9 @@
  *
  * USB initialization is
  * Copyright (c) 2013 Alexander Aring <alex.aring@gmail.com>
+ *
+ * Busware HUL support is
+ * Copyright (c) 2017 Josef Filzmaier <j.filzmaier@gmx.at>
  */
 
 #include <linux/kernel.h>
@@ -45,6 +48,7 @@
 struct atusb {
 	struct ieee802154_hw *hw;
 	struct usb_device *usb_dev;
+	struct atusb_chip_data *data;
 	int shutdown;			/* non-zero if shutting down */
 	int err;			/* set by first error */
 
@@ -65,6 +69,14 @@ struct atusb {
 	unsigned char fw_hw_type;	/* Firmware hardware type */
 };
 
+struct atusb_chip_data {
+	u16 t_channel_switch;
+	int rssi_base_val;
+
+	int (*set_channel)(struct ieee802154_hw*, u8, u8);
+	int (*set_txpower)(struct ieee802154_hw*, s32);
+};
+
 /* ----- USB commands without data ----------------------------------------- */
 
 /* To reduce the number of error checks in the code, we record the first error
@@ -163,6 +175,18 @@ static int atusb_write_subreg(struct atusb *atusb, uint8_t reg, uint8_t mask,
 	return ret;
 }
 
+static int atusb_read_subreg(struct atusb *lp,
+			     unsigned int addr, unsigned int mask,
+			     unsigned int shift)
+{
+	int rc;
+
+	rc = atusb_read_reg(lp, addr);
+	rc = (rc & mask) >> shift;
+
+	return rc;
+}
+
 static int atusb_get_and_clear_error(struct atusb *atusb)
 {
 	int err = atusb->err;
@@ -379,18 +403,6 @@ static int atusb_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
 	return ret;
 }
 
-static int atusb_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
-{
-	struct atusb *atusb = hw->priv;
-	int ret;
-
-	ret = atusb_write_subreg(atusb, SR_CHANNEL, channel);
-	if (ret < 0)
-		return ret;
-	msleep(1);	/* @@@ ugly synchronization */
-	return 0;
-}
-
 static int atusb_ed(struct ieee802154_hw *hw, u8 *level)
 {
 	BUG_ON(!level);
@@ -475,6 +487,17 @@ static const s32 atusb_powers[ATUSB_MAX_TX_POWERS + 1] = {
 };
 
 static int
+atusb_txpower(struct ieee802154_hw *hw, s32 mbm)
+{
+	struct atusb *atusb = hw->priv;
+
+	if (atusb->data)
+		return atusb->data->set_txpower(hw, mbm);
+	else
+		return -ENOTSUPP;
+}
+
+static int
 atusb_set_txpower(struct ieee802154_hw *hw, s32 mbm)
 {
 	struct atusb *atusb = hw->priv;
@@ -488,12 +511,43 @@ atusb_set_txpower(struct ieee802154_hw *hw, s32 mbm)
 	return -EINVAL;
 }
 
+static int
+hulusb_set_txpower(struct ieee802154_hw *hw, s32 mbm)
+{
+	u32 i;
+
+	for (i = 0; i < hw->phy->supported.tx_powers_size; i++) {
+		if (hw->phy->supported.tx_powers[i] == mbm)
+			return atusb_write_subreg(hw->priv, SR_TX_PWR_212, i);
+	}
+
+	return -EINVAL;
+}
+
 #define ATUSB_MAX_ED_LEVELS 0xF
 static const s32 atusb_ed_levels[ATUSB_MAX_ED_LEVELS + 1] = {
 	-9100, -8900, -8700, -8500, -8300, -8100, -7900, -7700, -7500, -7300,
 	-7100, -6900, -6700, -6500, -6300, -6100,
 };
 
+#define AT86RF212_MAX_TX_POWERS 0x1F
+static const s32 at86rf212_powers[AT86RF212_MAX_TX_POWERS + 1] = {
+	500, 400, 300, 200, 100, 0, -100, -200, -300, -400, -500, -600, -700,
+	-800, -900, -1000, -1100, -1200, -1300, -1400, -1500, -1600, -1700,
+	-1800, -1900, -2000, -2100, -2200, -2300, -2400, -2500, -2600,
+};
+
+#define AT86RF2XX_MAX_ED_LEVELS 0xF
+static const s32 at86rf212_ed_levels_100[AT86RF2XX_MAX_ED_LEVELS + 1] = {
+	-10000, -9800, -9600, -9400, -9200, -9000, -8800, -8600, -8400, -8200,
+	-8000, -7800, -7600, -7400, -7200, -7000,
+};
+
+static const s32 at86rf212_ed_levels_98[AT86RF2XX_MAX_ED_LEVELS + 1] = {
+	-9800, -9600, -9400, -9200, -9000, -8800, -8600, -8400, -8200, -8000,
+	-7800, -7600, -7400, -7200, -7000, -6800,
+};
+
 static int
 atusb_set_cca_mode(struct ieee802154_hw *hw, const struct wpan_phy_cca *cca)
 {
@@ -527,6 +581,30 @@ atusb_set_cca_mode(struct ieee802154_hw *hw, const struct wpan_phy_cca *cca)
 	return atusb_write_subreg(atusb, SR_CCA_MODE, val);
 }
 
+static int hulusb_set_cca_ed_level(struct atusb *lp, int rssi_base_val)
+{
+	unsigned int cca_ed_thres;
+
+	cca_ed_thres = atusb_read_subreg(lp, SR_CCA_ED_THRES);
+
+	switch (rssi_base_val) {
+	case -98:
+		lp->hw->phy->supported.cca_ed_levels = at86rf212_ed_levels_98;
+		lp->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf212_ed_levels_98);
+		lp->hw->phy->cca_ed_level = at86rf212_ed_levels_98[cca_ed_thres];
+		break;
+	case -100:
+		lp->hw->phy->supported.cca_ed_levels = at86rf212_ed_levels_100;
+		lp->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf212_ed_levels_100);
+		lp->hw->phy->cca_ed_level = at86rf212_ed_levels_100[cca_ed_thres];
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	return 0;
+}
+
 static int
 atusb_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm)
 {
@@ -541,6 +619,92 @@ atusb_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm)
 	return -EINVAL;
 }
 
+static int atusb_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
+{
+	struct atusb *atusb = hw->priv;
+	int ret = -ENOTSUPP;
+
+	if (atusb->data) {
+		ret = atusb->data->set_channel(hw, page, channel);
+		/* @@@ ugly synchronization */
+		msleep(atusb->data->t_channel_switch);
+	}
+
+	return ret;
+}
+
+static int atusb_set_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
+{
+	struct atusb *atusb = hw->priv;
+	int ret;
+
+	ret = atusb_write_subreg(atusb, SR_CHANNEL, channel);
+	if (ret < 0)
+		return ret;
+	return 0;
+}
+
+static int hulusb_set_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
+{
+	int rc;
+	int rssi_base_val;
+
+	struct atusb *lp = hw->priv;
+
+	if (channel == 0)
+		rc = atusb_write_subreg(lp, SR_SUB_MODE, 0);
+	else
+		rc = atusb_write_subreg(lp, SR_SUB_MODE, 1);
+	if (rc < 0)
+		return rc;
+
+	if (page == 0) {
+		rc = atusb_write_subreg(lp, SR_BPSK_QPSK, 0);
+		rssi_base_val = -100;
+	} else {
+		rc = atusb_write_subreg(lp, SR_BPSK_QPSK, 1);
+		rssi_base_val = -98;
+	}
+	if (rc < 0)
+		return rc;
+
+	rc = hulusb_set_cca_ed_level(lp, rssi_base_val);
+	if (rc < 0)
+		return rc;
+
+	/* This sets the symbol_duration according frequency on the 212.
+	 * TODO move this handling while set channel and page in cfg802154.
+	 * We can do that, this timings are according 802.15.4 standard.
+	 * If we do that in cfg802154, this is a more generic calculation.
+	 *
+	 * This should also protected from ifs_timer. Means cancel timer and
+	 * init with a new value. For now, this is okay.
+	 */
+	if (channel == 0) {
+		if (page == 0) {
+			/* SUB:0 and BPSK:0 -> BPSK-20 */
+			lp->hw->phy->symbol_duration = 50;
+		} else {
+			/* SUB:1 and BPSK:0 -> BPSK-40 */
+			lp->hw->phy->symbol_duration = 25;
+		}
+	} else {
+		if (page == 0)
+			/* SUB:0 and BPSK:1 -> OQPSK-100/200/400 */
+			lp->hw->phy->symbol_duration = 40;
+		else
+			/* SUB:1 and BPSK:1 -> OQPSK-250/500/1000 */
+			lp->hw->phy->symbol_duration = 16;
+	}
+
+	lp->hw->phy->lifs_period = IEEE802154_LIFS_PERIOD *
+				   lp->hw->phy->symbol_duration;
+	lp->hw->phy->sifs_period = IEEE802154_SIFS_PERIOD *
+				   lp->hw->phy->symbol_duration;
+
+	return atusb_write_subreg(lp, SR_CHANNEL, channel);
+}
+
 static int
 atusb_set_csma_params(struct ieee802154_hw *hw, u8 min_be, u8 max_be, u8 retries)
 {
@@ -559,6 +723,14 @@ atusb_set_csma_params(struct ieee802154_hw *hw, u8 min_be, u8 max_be, u8 retries
 }
 
 static int
+hulusb_set_lbt(struct ieee802154_hw *hw, bool on)
+{
+	struct atusb *atusb = hw->priv;
+
+	return atusb_write_subreg(atusb, SR_CSMA_LBT_MODE, on);
+}
+
+static int
 atusb_set_frame_retries(struct ieee802154_hw *hw, s8 retries)
 {
 	struct atusb *atusb = hw->priv;
@@ -593,6 +765,20 @@ atusb_set_promiscuous_mode(struct ieee802154_hw *hw, const bool on)
 	return 0;
 }
 
+static struct atusb_chip_data atusb_chip_data = {
+	.t_channel_switch = 1,
+	.rssi_base_val = -91,
+	.set_txpower = atusb_set_txpower,
+	.set_channel = atusb_set_channel,
+};
+
+static struct atusb_chip_data hulusb_chip_data = {
+	.t_channel_switch = 11,
+	.rssi_base_val = -100,
+	.set_txpower = hulusb_set_txpower,
+	.set_channel = hulusb_set_channel,
+};
+
 static const struct ieee802154_ops atusb_ops = {
 	.owner			= THIS_MODULE,
 	.xmit_async		= atusb_xmit,
@@ -601,7 +787,8 @@ static const struct ieee802154_ops atusb_ops = {
 	.start			= atusb_start,
 	.stop			= atusb_stop,
 	.set_hw_addr_filt	= atusb_set_hw_addr_filt,
-	.set_txpower		= atusb_set_txpower,
+	.set_txpower		= atusb_txpower,
+	.set_lbt		= hulusb_set_lbt,
 	.set_cca_mode		= atusb_set_cca_mode,
 	.set_cca_ed_level	= atusb_set_cca_ed_level,
 	.set_csma_params	= atusb_set_csma_params,
@@ -614,6 +801,7 @@ static const struct ieee802154_ops atusb_ops = {
 static int atusb_get_and_show_revision(struct atusb *atusb)
 {
 	struct usb_device *usb_dev = atusb->usb_dev;
+	char *hw_name;
 	unsigned char *buffer;
 	int ret;
 
@@ -630,9 +818,31 @@ static int atusb_get_and_show_revision(struct atusb *atusb)
 		atusb->fw_ver_min = buffer[1];
 		atusb->fw_hw_type = buffer[2];
 
+		switch (atusb->fw_hw_type) {
+		case ATUSB_HW_TYPE_100813:
+		case ATUSB_HW_TYPE_101216:
+		case ATUSB_HW_TYPE_110131:
+			hw_name = "ATUSB";
+			atusb->data = &atusb_chip_data;
+			break;
+		case ATUSB_HW_TYPE_RZUSB:
+			hw_name = "RZUSB";
+			atusb->data = &atusb_chip_data;
+			break;
+		case ATUSB_HW_TYPE_HULUSB:
+			hw_name = "HULUSB";
+			atusb->data = &hulusb_chip_data;
+			break;
+		default:
+			hw_name = "UNKNOWN";
+			atusb->err = -ENOTSUPP;
+			ret = -ENOTSUPP;
+			break;
+		}
+
 		dev_info(&usb_dev->dev,
-			 "Firmware: major: %u, minor: %u, hardware type: %u\n",
-			 atusb->fw_ver_maj, atusb->fw_ver_min, atusb->fw_hw_type);
+			 "Firmware: major: %u, minor: %u, hardware type: %s (%d)\n",
+			 atusb->fw_ver_maj, atusb->fw_ver_min, hw_name, atusb->fw_hw_type);
 	}
 	if (atusb->fw_ver_maj == 0 && atusb->fw_ver_min < 2) {
 		dev_info(&usb_dev->dev,
@@ -667,11 +877,12 @@ static int atusb_get_and_show_build(struct atusb *atusb)
 	return ret;
 }
 
-static int atusb_get_and_show_chip(struct atusb *atusb)
+static int atusb_get_and_conf_chip(struct atusb *atusb)
 {
 	struct usb_device *usb_dev = atusb->usb_dev;
 	uint8_t man_id_0, man_id_1, part_num, version_num;
 	const char *chip;
+	struct ieee802154_hw *hw = atusb->hw;
 
 	man_id_0 = atusb_read_reg(atusb, RG_MAN_ID_0);
 	man_id_1 = atusb_read_reg(atusb, RG_MAN_ID_1);
@@ -681,6 +892,22 @@ static int atusb_get_and_show_chip(struct atusb *atusb)
 	if (atusb->err)
 		return atusb->err;
 
+	hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AFILT |
+		    IEEE802154_HW_PROMISCUOUS | IEEE802154_HW_CSMA_PARAMS;
+
+	hw->phy->flags = WPAN_PHY_FLAG_TXPOWER | WPAN_PHY_FLAG_CCA_ED_LEVEL |
+			 WPAN_PHY_FLAG_CCA_MODE;
+
+	hw->phy->supported.cca_modes = BIT(NL802154_CCA_ENERGY) |
+				       BIT(NL802154_CCA_CARRIER) |
+				       BIT(NL802154_CCA_ENERGY_CARRIER);
+	hw->phy->supported.cca_opts = BIT(NL802154_CCA_OPT_ENERGY_CARRIER_AND) |
+				      BIT(NL802154_CCA_OPT_ENERGY_CARRIER_OR);
+
+	hw->phy->cca.mode = NL802154_CCA_ENERGY;
+
+	hw->phy->current_page = 0;
+
 	if ((man_id_1 << 8 | man_id_0) != ATUSB_JEDEC_ATMEL) {
 		dev_err(&usb_dev->dev,
 			"non-Atmel transceiver xxxx%02x%02x\n",
@@ -691,9 +918,36 @@ static int atusb_get_and_show_chip(struct atusb *atusb)
 	switch (part_num) {
 	case 2:
 		chip = "AT86RF230";
+		atusb->hw->phy->supported.channels[0] = 0x7FFF800;
+		atusb->hw->phy->current_channel = 11;	/* reset default */
+		atusb->hw->phy->symbol_duration = 16;
+		atusb->hw->phy->supported.tx_powers = atusb_powers;
+		atusb->hw->phy->supported.tx_powers_size = ARRAY_SIZE(atusb_powers);
+		hw->phy->supported.cca_ed_levels = atusb_ed_levels;
+		hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(atusb_ed_levels);
 		break;
 	case 3:
 		chip = "AT86RF231";
+		atusb->hw->phy->supported.channels[0] = 0x7FFF800;
+		atusb->hw->phy->current_channel = 11;	/* reset default */
+		atusb->hw->phy->symbol_duration = 16;
+		atusb->hw->phy->supported.tx_powers = atusb_powers;
+		atusb->hw->phy->supported.tx_powers_size = ARRAY_SIZE(atusb_powers);
+		hw->phy->supported.cca_ed_levels = atusb_ed_levels;
+		hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(atusb_ed_levels);
+		break;
+	case 7:
+		chip = "AT86RF212";
+		atusb->hw->flags |= IEEE802154_HW_LBT;
+		atusb->hw->phy->supported.channels[0] = 0x00007FF;
+		atusb->hw->phy->supported.channels[2] = 0x00007FF;
+		atusb->hw->phy->current_channel = 5;
+		atusb->hw->phy->symbol_duration = 25;
+		atusb->hw->phy->supported.lbt = NL802154_SUPPORTED_BOOL_BOTH;
+		atusb->hw->phy->supported.tx_powers = at86rf212_powers;
+		atusb->hw->phy->supported.tx_powers_size = ARRAY_SIZE(at86rf212_powers);
+		atusb->hw->phy->supported.cca_ed_levels = at86rf212_ed_levels_100;
+		atusb->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf212_ed_levels_100);
 		break;
 	default:
 		dev_err(&usb_dev->dev,
@@ -702,6 +956,9 @@ static int atusb_get_and_show_chip(struct atusb *atusb)
 		goto fail;
 	}
 
+	hw->phy->transmit_power = hw->phy->supported.tx_powers[0];
+	hw->phy->cca_ed_level = hw->phy->supported.cca_ed_levels[7];
+
 	dev_info(&usb_dev->dev, "ATUSB: %s version %d\n", chip, version_num);
 
 	return 0;
@@ -794,37 +1051,14 @@ static int atusb_probe(struct usb_interface *interface,
 		goto fail;
 
 	hw->parent = &usb_dev->dev;
-	hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AFILT |
-		    IEEE802154_HW_PROMISCUOUS | IEEE802154_HW_CSMA_PARAMS;
-
-	hw->phy->flags = WPAN_PHY_FLAG_TXPOWER | WPAN_PHY_FLAG_CCA_ED_LEVEL |
-			 WPAN_PHY_FLAG_CCA_MODE;
-
-	hw->phy->supported.cca_modes = BIT(NL802154_CCA_ENERGY) |
-		BIT(NL802154_CCA_CARRIER) | BIT(NL802154_CCA_ENERGY_CARRIER);
-	hw->phy->supported.cca_opts = BIT(NL802154_CCA_OPT_ENERGY_CARRIER_AND) |
-		BIT(NL802154_CCA_OPT_ENERGY_CARRIER_OR);
-
-	hw->phy->supported.cca_ed_levels = atusb_ed_levels;
-	hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(atusb_ed_levels);
-
-	hw->phy->cca.mode = NL802154_CCA_ENERGY;
-
-	hw->phy->current_page = 0;
-	hw->phy->current_channel = 11;	/* reset default */
-	hw->phy->supported.channels[0] = 0x7FFF800;
-	hw->phy->supported.tx_powers = atusb_powers;
-	hw->phy->supported.tx_powers_size = ARRAY_SIZE(atusb_powers);
-	hw->phy->transmit_power = hw->phy->supported.tx_powers[0];
-	hw->phy->cca_ed_level = hw->phy->supported.cca_ed_levels[7];
 
 	atusb_command(atusb, ATUSB_RF_RESET, 0);
-	atusb_get_and_show_chip(atusb);
+	atusb_get_and_conf_chip(atusb);
 	atusb_get_and_show_revision(atusb);
 	atusb_get_and_show_build(atusb);
 	atusb_set_extended_addr(atusb);
 
-	if (atusb->fw_ver_maj >= 0 && atusb->fw_ver_min >= 3)
+	if ((atusb->fw_ver_maj == 0 && atusb->fw_ver_min >= 3) || atusb->fw_ver_maj > 0)
 		hw->flags |= IEEE802154_HW_FRAME_RETRIES;
 
 	ret = atusb_get_and_clear_error(atusb);
@@ -941,5 +1175,6 @@ MODULE_AUTHOR("Alexander Aring <alex.aring@gmail.com>");
 MODULE_AUTHOR("Richard Sharpe <realrichardsharpe@gmail.com>");
 MODULE_AUTHOR("Stefan Schmidt <stefan@datenfreihafen.org>");
 MODULE_AUTHOR("Werner Almesberger <werner@almesberger.net>");
+MODULE_AUTHOR("Josef Filzmaier <j.filzmaier@gmx.at>");
 MODULE_DESCRIPTION("ATUSB IEEE 802.15.4 Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ieee802154/atusb.h b/drivers/net/ieee802154/atusb.h
index b22bbaa77590..555d14bf14a3 100644
--- a/drivers/net/ieee802154/atusb.h
+++ b/drivers/net/ieee802154/atusb.h
@@ -50,6 +50,14 @@ enum atusb_requests {
 	ATUSB_EUI64_READ,
 };
 
+enum {
+	ATUSB_HW_TYPE_100813,	/* 2010-08-13 */
+	ATUSB_HW_TYPE_101216,	/* 2010-12-16 */
+	ATUSB_HW_TYPE_110131,	/* 2011-01-31, ATmega32U2-based */
+	ATUSB_HW_TYPE_RZUSB,	/* Atmel Raven USB dongle with at86rf230 */
+	ATUSB_HW_TYPE_HULUSB,	/* Busware HUL USB dongle with at86rf212 */
+};
+
 /*
  * Direction	bRequest		wValue		wIndex	wLength
  *
diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
index 24a1eabbbc9d..e6b8ce81a6c3 100644
--- a/drivers/net/ieee802154/ca8210.c
+++ b/drivers/net/ieee802154/ca8210.c
@@ -1944,7 +1944,7 @@ static int ca8210_skb_tx(
 )
 {
 	int status;
-	struct ieee802154_hdr header = { 0 };
+	struct ieee802154_hdr header = { };
 	struct secspec secspec;
 	unsigned int mac_len;
 
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index 8870bd2a2e8a..0008da7e9d4c 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -231,6 +231,9 @@ static void ifb_setup(struct net_device *dev)
 	eth_hw_addr_random(dev);
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = ifb_dev_free;
+
+	dev->min_mtu = 0;
+	dev->max_mtu = 0;
 }
 
 static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev)
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index ba8173a0b62e..5166575a164d 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -96,6 +96,7 @@ struct ipvl_port {
 	struct hlist_head	hlhead[IPVLAN_HASH_SIZE];
 	struct list_head	ipvlans;
 	u16			mode;
+	u16			flags;
 	u16			dev_id_start;
 	struct work_struct	wq;
 	struct sk_buff_head	backlog;
@@ -123,6 +124,36 @@ static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d)
 	return rtnl_dereference(d->rx_handler_data);
 }
 
+static inline bool ipvlan_is_private(const struct ipvl_port *port)
+{
+	return !!(port->flags & IPVLAN_F_PRIVATE);
+}
+
+static inline void ipvlan_mark_private(struct ipvl_port *port)
+{
+	port->flags |= IPVLAN_F_PRIVATE;
+}
+
+static inline void ipvlan_clear_private(struct ipvl_port *port)
+{
+	port->flags &= ~IPVLAN_F_PRIVATE;
+}
+
+static inline bool ipvlan_is_vepa(const struct ipvl_port *port)
+{
+	return !!(port->flags & IPVLAN_F_VEPA);
+}
+
+static inline void ipvlan_mark_vepa(struct ipvl_port *port)
+{
+	port->flags |= IPVLAN_F_VEPA;
+}
+
+static inline void ipvlan_clear_vepa(struct ipvl_port *port)
+{
+	port->flags &= ~IPVLAN_F_VEPA;
+}
+
 void ipvlan_init_secret(void);
 unsigned int ipvlan_mac_hash(const unsigned char *addr);
 rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb);
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 1f3295e274d0..034ae4c57196 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -514,10 +514,16 @@ static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev)
 	if (!lyr3h)
 		goto out;
 
-	addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true);
-	if (addr)
-		return ipvlan_rcv_frame(addr, &skb, true);
-
+	if (!ipvlan_is_vepa(ipvlan->port)) {
+		addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true);
+		if (addr) {
+			if (ipvlan_is_private(ipvlan->port)) {
+				consume_skb(skb);
+				return NET_XMIT_DROP;
+			}
+			return ipvlan_rcv_frame(addr, &skb, true);
+		}
+	}
 out:
 	ipvlan_skb_crossing_ns(skb, ipvlan->phy_dev);
 	return ipvlan_process_outbound(skb);
@@ -531,12 +537,18 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
 	void *lyr3h;
 	int addr_type;
 
-	if (ether_addr_equal(eth->h_dest, eth->h_source)) {
+	if (!ipvlan_is_vepa(ipvlan->port) &&
+	    ether_addr_equal(eth->h_dest, eth->h_source)) {
 		lyr3h = ipvlan_get_L3_hdr(skb, &addr_type);
 		if (lyr3h) {
 			addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true);
-			if (addr)
+			if (addr) {
+				if (ipvlan_is_private(ipvlan->port)) {
+					consume_skb(skb);
+					return NET_XMIT_DROP;
+				}
 				return ipvlan_rcv_frame(addr, &skb, true);
+			}
 		}
 		skb = skb_share_check(skb, GFP_ATOMIC);
 		if (!skb)
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index c74893c1e620..a266aa435d4d 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -407,7 +407,7 @@ static int ipvlan_hard_header(struct sk_buff *skb, struct net_device *dev,
 	 * while the packets use the mac-addr on the physical device.
 	 */
 	return dev_hard_header(skb, phy_dev, type, daddr,
-			       saddr ? : dev->dev_addr, len);
+			       saddr ? : phy_dev->dev_addr, len);
 }
 
 static const struct header_ops ipvlan_header_ops = {
@@ -462,11 +462,29 @@ static int ipvlan_nl_changelink(struct net_device *dev,
 	struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev);
 	int err = 0;
 
-	if (data && data[IFLA_IPVLAN_MODE]) {
+	if (!data)
+		return 0;
+
+	if (data[IFLA_IPVLAN_MODE]) {
 		u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
 
 		err = ipvlan_set_port_mode(port, nmode);
 	}
+
+	if (!err && data[IFLA_IPVLAN_FLAGS]) {
+		u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]);
+
+		if (flags & IPVLAN_F_PRIVATE)
+			ipvlan_mark_private(port);
+		else
+			ipvlan_clear_private(port);
+
+		if (flags & IPVLAN_F_VEPA)
+			ipvlan_mark_vepa(port);
+		else
+			ipvlan_clear_vepa(port);
+	}
+
 	return err;
 }
 
@@ -474,18 +492,34 @@ static size_t ipvlan_nl_getsize(const struct net_device *dev)
 {
 	return (0
 		+ nla_total_size(2) /* IFLA_IPVLAN_MODE */
+		+ nla_total_size(2) /* IFLA_IPVLAN_FLAGS */
 		);
 }
 
 static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[],
 			      struct netlink_ext_ack *extack)
 {
-	if (data && data[IFLA_IPVLAN_MODE]) {
+	if (!data)
+		return 0;
+
+	if (data[IFLA_IPVLAN_MODE]) {
 		u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
 
 		if (mode < IPVLAN_MODE_L2 || mode >= IPVLAN_MODE_MAX)
 			return -EINVAL;
 	}
+	if (data[IFLA_IPVLAN_FLAGS]) {
+		u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]);
+
+		/* Only two bits are used at this moment. */
+		if (flags & ~(IPVLAN_F_PRIVATE | IPVLAN_F_VEPA))
+			return -EINVAL;
+		/* Also both flags can't be active at the same time. */
+		if ((flags & (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) ==
+		    (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA))
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -502,6 +536,8 @@ static int ipvlan_nl_fillinfo(struct sk_buff *skb,
 	ret = -EMSGSIZE;
 	if (nla_put_u16(skb, IFLA_IPVLAN_MODE, port->mode))
 		goto err;
+	if (nla_put_u16(skb, IFLA_IPVLAN_FLAGS, port->flags))
+		goto err;
 
 	return 0;
 
@@ -549,6 +585,12 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	ipvlan_adjust_mtu(ipvlan, phy_dev);
 	INIT_LIST_HEAD(&ipvlan->addrs);
 
+	/* Flags are per port and latest update overrides. User has
+	 * to be consistent in setting it just like the mode attribute.
+	 */
+	if (data && data[IFLA_IPVLAN_FLAGS])
+		ipvlan->port->flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]);
+
 	/* If the port-id base is at the MAX value, then wrap it around and
 	 * begin from 0x1 again. This may be due to a busy system where lots
 	 * of slaves are getting created and deleted.
@@ -584,7 +626,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		goto remove_ida;
 
-	err = netdev_upper_dev_link(phy_dev, dev);
+	err = netdev_upper_dev_link(phy_dev, dev, extack);
 	if (err) {
 		goto unregister_netdev;
 	}
@@ -644,6 +686,7 @@ EXPORT_SYMBOL_GPL(ipvlan_link_setup);
 static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] =
 {
 	[IFLA_IPVLAN_MODE] = { .type = NLA_U16 },
+	[IFLA_IPVLAN_FLAGS] = { .type = NLA_U16 },
 };
 
 static struct rtnl_link_ops ipvlan_link_ops = {
@@ -730,6 +773,11 @@ static int ipvlan_device_event(struct notifier_block *unused,
 			ipvlan_adjust_mtu(ipvlan, dev);
 		break;
 
+	case NETDEV_CHANGEADDR:
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode)
+			ether_addr_copy(ipvlan->dev->dev_addr, dev->dev_addr);
+		break;
+
 	case NETDEV_PRE_TYPE_CHANGE:
 		/* Forbid underlying device to change its type. */
 		return NOTIFY_BAD;
@@ -803,10 +851,6 @@ static int ipvlan_addr6_event(struct notifier_block *unused,
 	struct net_device *dev = (struct net_device *)if6->idev->dev;
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 
-	/* FIXME IPv6 autoconf calls us from bh without RTNL */
-	if (in_softirq())
-		return NOTIFY_DONE;
-
 	if (!netif_is_ipvlan(dev))
 		return NOTIFY_DONE;
 
@@ -846,8 +890,11 @@ static int ipvlan_addr6_validator_event(struct notifier_block *unused,
 
 	switch (event) {
 	case NETDEV_UP:
-		if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true))
+		if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) {
+			NL_SET_ERR_MSG(i6vi->extack,
+				       "Address already assigned to an ipvlan device");
 			return notifier_from_errno(-EADDRINUSE);
+		}
 		break;
 	}
 
@@ -916,8 +963,11 @@ static int ipvlan_addr4_validator_event(struct notifier_block *unused,
 
 	switch (event) {
 	case NETDEV_UP:
-		if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false))
+		if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) {
+			NL_SET_ERR_MSG(ivi->extack,
+				       "Address already assigned to an ipvlan device");
 			return notifier_from_errno(-EADDRINUSE);
+		}
 		break;
 	}
 
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 5ab1b8849c30..2c98152d1e1b 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -16,6 +16,7 @@
 #include <crypto/aead.h>
 #include <linux/etherdevice.h>
 #include <linux/rtnetlink.h>
+#include <linux/refcount.h>
 #include <net/genetlink.h>
 #include <net/sock.h>
 #include <net/gro_cells.h>
@@ -146,7 +147,7 @@ struct macsec_rx_sa {
 	struct macsec_key key;
 	spinlock_t lock;
 	u32 next_pn;
-	atomic_t refcnt;
+	refcount_t refcnt;
 	bool active;
 	struct macsec_rx_sa_stats __percpu *stats;
 	struct macsec_rx_sc *sc;
@@ -171,7 +172,7 @@ struct macsec_rx_sc {
 	bool active;
 	struct macsec_rx_sa __rcu *sa[MACSEC_NUM_AN];
 	struct pcpu_rx_sc_stats __percpu *stats;
-	atomic_t refcnt;
+	refcount_t refcnt;
 	struct rcu_head rcu_head;
 };
 
@@ -187,7 +188,7 @@ struct macsec_tx_sa {
 	struct macsec_key key;
 	spinlock_t lock;
 	u32 next_pn;
-	atomic_t refcnt;
+	refcount_t refcnt;
 	bool active;
 	struct macsec_tx_sa_stats __percpu *stats;
 	struct rcu_head rcu;
@@ -314,7 +315,7 @@ static struct macsec_rx_sa *macsec_rxsa_get(struct macsec_rx_sa __rcu *ptr)
 	if (!sa || !sa->active)
 		return NULL;
 
-	if (!atomic_inc_not_zero(&sa->refcnt))
+	if (!refcount_inc_not_zero(&sa->refcnt))
 		return NULL;
 
 	return sa;
@@ -330,12 +331,12 @@ static void free_rx_sc_rcu(struct rcu_head *head)
 
 static struct macsec_rx_sc *macsec_rxsc_get(struct macsec_rx_sc *sc)
 {
-	return atomic_inc_not_zero(&sc->refcnt) ? sc : NULL;
+	return refcount_inc_not_zero(&sc->refcnt) ? sc : NULL;
 }
 
 static void macsec_rxsc_put(struct macsec_rx_sc *sc)
 {
-	if (atomic_dec_and_test(&sc->refcnt))
+	if (refcount_dec_and_test(&sc->refcnt))
 		call_rcu(&sc->rcu_head, free_rx_sc_rcu);
 }
 
@@ -350,7 +351,7 @@ static void free_rxsa(struct rcu_head *head)
 
 static void macsec_rxsa_put(struct macsec_rx_sa *sa)
 {
-	if (atomic_dec_and_test(&sa->refcnt))
+	if (refcount_dec_and_test(&sa->refcnt))
 		call_rcu(&sa->rcu, free_rxsa);
 }
 
@@ -361,7 +362,7 @@ static struct macsec_tx_sa *macsec_txsa_get(struct macsec_tx_sa __rcu *ptr)
 	if (!sa || !sa->active)
 		return NULL;
 
-	if (!atomic_inc_not_zero(&sa->refcnt))
+	if (!refcount_inc_not_zero(&sa->refcnt))
 		return NULL;
 
 	return sa;
@@ -378,7 +379,7 @@ static void free_txsa(struct rcu_head *head)
 
 static void macsec_txsa_put(struct macsec_tx_sa *sa)
 {
-	if (atomic_dec_and_test(&sa->refcnt))
+	if (refcount_dec_and_test(&sa->refcnt))
 		call_rcu(&sa->rcu, free_txsa);
 }
 
@@ -1341,7 +1342,7 @@ static int init_rx_sa(struct macsec_rx_sa *rx_sa, char *sak, int key_len,
 
 	rx_sa->active = false;
 	rx_sa->next_pn = 1;
-	atomic_set(&rx_sa->refcnt, 1);
+	refcount_set(&rx_sa->refcnt, 1);
 	spin_lock_init(&rx_sa->lock);
 
 	return 0;
@@ -1412,7 +1413,7 @@ static struct macsec_rx_sc *create_rx_sc(struct net_device *dev, sci_t sci)
 
 	rx_sc->sci = sci;
 	rx_sc->active = true;
-	atomic_set(&rx_sc->refcnt, 1);
+	refcount_set(&rx_sc->refcnt, 1);
 
 	secy = &macsec_priv(dev)->secy;
 	rcu_assign_pointer(rx_sc->next, secy->rx_sc);
@@ -1438,7 +1439,7 @@ static int init_tx_sa(struct macsec_tx_sa *tx_sa, char *sak, int key_len,
 	}
 
 	tx_sa->active = false;
-	atomic_set(&tx_sa->refcnt, 1);
+	refcount_set(&tx_sa->refcnt, 1);
 	spin_lock_init(&tx_sa->lock);
 
 	return 0;
@@ -3246,7 +3247,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 				       &macsec_netdev_addr_lock_key,
 				       macsec_get_nest_level(dev));
 
-	err = netdev_upper_dev_link(real_dev, dev);
+	err = netdev_upper_dev_link(real_dev, dev, extack);
 	if (err < 0)
 		goto unregister;
 
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index d2aea961e0f4..a178c5efd33e 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -413,7 +413,9 @@ static void macvlan_forward_source_one(struct sk_buff *skb,
 
 	len = nskb->len + ETH_HLEN;
 	nskb->dev = dev;
-	nskb->pkt_type = PACKET_HOST;
+
+	if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, dev->dev_addr))
+		nskb->pkt_type = PACKET_HOST;
 
 	ret = netif_rx(nskb);
 	macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false);
@@ -480,7 +482,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 					      struct macvlan_dev, list);
 	else
 		vlan = macvlan_hash_lookup(port, eth->h_dest);
-	if (vlan == NULL)
+	if (!vlan || vlan->mode == MACVLAN_MODE_SOURCE)
 		return RX_HANDLER_PASS;
 
 	dev = vlan->dev;
@@ -596,8 +598,6 @@ static const struct header_ops macvlan_hard_header_ops = {
 	.cache_update	= eth_header_cache_update,
 };
 
-static struct rtnl_link_ops macvlan_link_ops;
-
 static int macvlan_open(struct net_device *dev)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
@@ -613,8 +613,7 @@ static int macvlan_open(struct net_device *dev)
 		goto hash_add;
 	}
 
-	if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD &&
-	    dev->rtnl_link_ops == &macvlan_link_ops) {
+	if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) {
 		vlan->fwd_priv =
 		      lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev);
 
@@ -1231,11 +1230,14 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[],
 			return -EADDRNOTAVAIL;
 	}
 
-	if (data && data[IFLA_MACVLAN_FLAGS] &&
+	if (!data)
+		return 0;
+
+	if (data[IFLA_MACVLAN_FLAGS] &&
 	    nla_get_u16(data[IFLA_MACVLAN_FLAGS]) & ~MACVLAN_FLAG_NOPROMISC)
 		return -EINVAL;
 
-	if (data && data[IFLA_MACVLAN_MODE]) {
+	if (data[IFLA_MACVLAN_MODE]) {
 		switch (nla_get_u32(data[IFLA_MACVLAN_MODE])) {
 		case MACVLAN_MODE_PRIVATE:
 		case MACVLAN_MODE_VEPA:
@@ -1248,7 +1250,7 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		}
 	}
 
-	if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
+	if (data[IFLA_MACVLAN_MACADDR_MODE]) {
 		switch (nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE])) {
 		case MACVLAN_MACADDR_ADD:
 		case MACVLAN_MACADDR_DEL:
@@ -1260,7 +1262,7 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		}
 	}
 
-	if (data && data[IFLA_MACVLAN_MACADDR]) {
+	if (data[IFLA_MACVLAN_MACADDR]) {
 		if (nla_len(data[IFLA_MACVLAN_MACADDR]) != ETH_ALEN)
 			return -EINVAL;
 
@@ -1268,7 +1270,7 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[],
 			return -EADDRNOTAVAIL;
 	}
 
-	if (data && data[IFLA_MACVLAN_MACADDR_COUNT])
+	if (data[IFLA_MACVLAN_MACADDR_COUNT])
 		return -EINVAL;
 
 	return 0;
@@ -1341,7 +1343,8 @@ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode,
 }
 
 int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
-			   struct nlattr *tb[], struct nlattr *data[])
+			   struct nlattr *tb[], struct nlattr *data[],
+			   struct netlink_ext_ack *extack)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	struct macvlan_port *port;
@@ -1430,7 +1433,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 		goto destroy_macvlan_port;
 
 	dev->priv_flags |= IFF_MACVLAN;
-	err = netdev_upper_dev_link(lowerdev, dev);
+	err = netdev_upper_dev_link(lowerdev, dev, extack);
 	if (err)
 		goto unregister_netdev;
 
@@ -1453,7 +1456,7 @@ static int macvlan_newlink(struct net *src_net, struct net_device *dev,
 			   struct nlattr *tb[], struct nlattr *data[],
 			   struct netlink_ext_ack *extack)
 {
-	return macvlan_common_newlink(src_net, dev, tb, data);
+	return macvlan_common_newlink(src_net, dev, tb, data, extack);
 }
 
 void macvlan_dellink(struct net_device *dev, struct list_head *head)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index cba5cb3b849a..9a10029caf83 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -105,7 +105,7 @@ static int macvtap_newlink(struct net *src_net, struct net_device *dev,
 	/* Don't put anything that may fail after macvlan_common_newlink
 	 * because we can't undo what it does.
 	 */
-	err = macvlan_common_newlink(src_net, dev, tb, data);
+	err = macvlan_common_newlink(src_net, dev, tb, data, extack);
 	if (err) {
 		netdev_rx_handler_unregister(dev);
 		return err;
diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 0250aa9ae2cb..9f6f7ccd44f7 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -230,10 +230,10 @@ err:
 	return NETDEV_TX_BUSY;
 }
 
-static void ntb_netdev_tx_timer(unsigned long data)
+static void ntb_netdev_tx_timer(struct timer_list *t)
 {
-	struct net_device *ndev = (struct net_device *)data;
-	struct ntb_netdev *dev = netdev_priv(ndev);
+	struct ntb_netdev *dev = from_timer(dev, t, tx_timer);
+	struct net_device *ndev = dev->ndev;
 
 	if (ntb_transport_tx_free_entry(dev->qp) < tx_stop) {
 		mod_timer(&dev->tx_timer, jiffies + msecs_to_jiffies(tx_time));
@@ -269,7 +269,7 @@ static int ntb_netdev_open(struct net_device *ndev)
 		}
 	}
 
-	setup_timer(&dev->tx_timer, ntb_netdev_tx_timer, (unsigned long)ndev);
+	timer_setup(&dev->tx_timer, ntb_netdev_tx_timer, 0);
 
 	netif_carrier_off(ndev);
 	ntb_transport_link_up(dev->qp);
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index cd931cf9dcc2..8125412c8814 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -277,6 +277,11 @@ config DAVICOM_PHY
 	---help---
 	  Currently supports dm9161e and dm9131
 
+config DP83822_PHY
+	tristate "Texas Instruments DP83822 PHY"
+	---help---
+	  Supports the DP83822 PHY.
+
 config DP83848_PHY
 	tristate "Texas Instruments DP83848 PHY"
 	---help---
@@ -366,6 +371,11 @@ config REALTEK_PHY
 	---help---
 	  Supports the Realtek 821x PHY.
 
+config RENESAS_PHY
+	tristate "Driver for Renesas PHYs"
+	---help---
+	  Supports the Renesas PHYs uPD60620 and uPD60620A.
+
 config ROCKCHIP_PHY
         tristate "Driver for Rockchip Ethernet PHYs"
         ---help---
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 00f097e18c68..01acbcb2c798 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_CICADA_PHY)	+= cicada.o
 obj-$(CONFIG_CORTINA_PHY)	+= cortina.o
 obj-$(CONFIG_DAVICOM_PHY)	+= davicom.o
 obj-$(CONFIG_DP83640_PHY)	+= dp83640.o
+obj-$(CONFIG_DP83822_PHY)	+= dp83822.o
 obj-$(CONFIG_DP83848_PHY)	+= dp83848.o
 obj-$(CONFIG_DP83867_PHY)	+= dp83867.o
 obj-$(CONFIG_FIXED_PHY)		+= fixed_phy.o
@@ -73,6 +74,7 @@ obj-$(CONFIG_MICROSEMI_PHY)	+= mscc.o
 obj-$(CONFIG_NATIONAL_PHY)	+= national.o
 obj-$(CONFIG_QSEMI_PHY)		+= qsemi.o
 obj-$(CONFIG_REALTEK_PHY)	+= realtek.o
+obj-$(CONFIG_RENESAS_PHY)	+= uPD60620.o
 obj-$(CONFIG_ROCKCHIP_PHY)	+= rockchip.o
 obj-$(CONFIG_SMSC_PHY)		+= smsc.o
 obj-$(CONFIG_STE10XP)		+= ste10Xp.o
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index c1e52b9dc58d..5f93e6add563 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -167,7 +167,7 @@ static int at803x_set_wol(struct phy_device *phydev,
 		mac = (const u8 *) ndev->dev_addr;
 
 		if (!is_valid_ether_addr(mac))
-			return -EFAULT;
+			return -EINVAL;
 
 		for (i = 0; i < 3; i++) {
 			phy_write(phydev, AT803X_MMD_ACCESS_CONTROL,
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 1e9ad30a35c8..d7ed69deabfb 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -43,6 +43,12 @@ static int bcm54210e_config_init(struct phy_device *phydev)
 	val &= ~BCM54810_SHD_CLK_CTL_GTXCLK_EN;
 	bcm_phy_write_shadow(phydev, BCM54810_SHD_CLK_CTL, val);
 
+	if (phydev->dev_flags & PHY_BRCM_EN_MASTER_MODE) {
+		val = phy_read(phydev, MII_CTRL1000);
+		val |= CTL1000_AS_MASTER | CTL1000_ENABLE_MASTER;
+		phy_write(phydev, MII_CTRL1000, val);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
new file mode 100644
index 000000000000..14335d14e9e4
--- /dev/null
+++ b/drivers/net/phy/dp83822.c
@@ -0,0 +1,344 @@
+/*
+ * Driver for the Texas Instruments DP83822 PHY
+ *
+ * Copyright (C) 2017 Texas Instruments Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/ethtool.h>
+#include <linux/etherdevice.h>
+#include <linux/kernel.h>
+#include <linux/mii.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/phy.h>
+#include <linux/netdevice.h>
+
+#define DP83822_PHY_ID	        0x2000a240
+#define DP83822_DEVADDR		0x1f
+
+#define MII_DP83822_PHYSCR	0x11
+#define MII_DP83822_MISR1	0x12
+#define MII_DP83822_MISR2	0x13
+#define MII_DP83822_RESET_CTRL	0x1f
+
+#define DP83822_HW_RESET	BIT(15)
+#define DP83822_SW_RESET	BIT(14)
+
+/* PHYSCR Register Fields */
+#define DP83822_PHYSCR_INT_OE		BIT(0) /* Interrupt Output Enable */
+#define DP83822_PHYSCR_INTEN		BIT(1) /* Interrupt Enable */
+
+/* MISR1 bits */
+#define DP83822_RX_ERR_HF_INT_EN	BIT(0)
+#define DP83822_FALSE_CARRIER_HF_INT_EN	BIT(1)
+#define DP83822_ANEG_COMPLETE_INT_EN	BIT(2)
+#define DP83822_DUP_MODE_CHANGE_INT_EN	BIT(3)
+#define DP83822_SPEED_CHANGED_INT_EN	BIT(4)
+#define DP83822_LINK_STAT_INT_EN	BIT(5)
+#define DP83822_ENERGY_DET_INT_EN	BIT(6)
+#define DP83822_LINK_QUAL_INT_EN	BIT(7)
+
+/* MISR2 bits */
+#define DP83822_JABBER_DET_INT_EN	BIT(0)
+#define DP83822_WOL_PKT_INT_EN		BIT(1)
+#define DP83822_SLEEP_MODE_INT_EN	BIT(2)
+#define DP83822_MDI_XOVER_INT_EN	BIT(3)
+#define DP83822_LB_FIFO_INT_EN		BIT(4)
+#define DP83822_PAGE_RX_INT_EN		BIT(5)
+#define DP83822_ANEG_ERR_INT_EN		BIT(6)
+#define DP83822_EEE_ERROR_CHANGE_INT_EN	BIT(7)
+
+/* INT_STAT1 bits */
+#define DP83822_WOL_INT_EN	BIT(4)
+#define DP83822_WOL_INT_STAT	BIT(12)
+
+#define MII_DP83822_RXSOP1	0x04a5
+#define	MII_DP83822_RXSOP2	0x04a6
+#define	MII_DP83822_RXSOP3	0x04a7
+
+/* WoL Registers */
+#define	MII_DP83822_WOL_CFG	0x04a0
+#define	MII_DP83822_WOL_STAT	0x04a1
+#define	MII_DP83822_WOL_DA1	0x04a2
+#define	MII_DP83822_WOL_DA2	0x04a3
+#define	MII_DP83822_WOL_DA3	0x04a4
+
+/* WoL bits */
+#define DP83822_WOL_MAGIC_EN	BIT(0)
+#define DP83822_WOL_SECURE_ON	BIT(5)
+#define DP83822_WOL_EN		BIT(7)
+#define DP83822_WOL_INDICATION_SEL BIT(8)
+#define DP83822_WOL_CLR_INDICATION BIT(11)
+
+static int dp83822_ack_interrupt(struct phy_device *phydev)
+{
+	int err;
+
+	err = phy_read(phydev, MII_DP83822_MISR1);
+	if (err < 0)
+		return err;
+
+	err = phy_read(phydev, MII_DP83822_MISR2);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int dp83822_set_wol(struct phy_device *phydev,
+			   struct ethtool_wolinfo *wol)
+{
+	struct net_device *ndev = phydev->attached_dev;
+	u16 value;
+	const u8 *mac;
+
+	if (wol->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) {
+		mac = (const u8 *)ndev->dev_addr;
+
+		if (!is_valid_ether_addr(mac))
+			return -EINVAL;
+
+		/* MAC addresses start with byte 5, but stored in mac[0].
+		 * 822 PHYs store bytes 4|5, 2|3, 0|1
+		 */
+		phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_DA1,
+			      (mac[1] << 8) | mac[0]);
+		phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_DA2,
+			      (mac[3] << 8) | mac[2]);
+		phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_DA3,
+			      (mac[5] << 8) | mac[4]);
+
+		value = phy_read_mmd(phydev, DP83822_DEVADDR,
+				     MII_DP83822_WOL_CFG);
+		if (wol->wolopts & WAKE_MAGIC)
+			value |= DP83822_WOL_MAGIC_EN;
+		else
+			value &= ~DP83822_WOL_MAGIC_EN;
+
+		if (wol->wolopts & WAKE_MAGICSECURE) {
+			phy_write_mmd(phydev, DP83822_DEVADDR,
+				      MII_DP83822_RXSOP1,
+				      (wol->sopass[1] << 8) | wol->sopass[0]);
+			phy_write_mmd(phydev, DP83822_DEVADDR,
+				      MII_DP83822_RXSOP2,
+				      (wol->sopass[3] << 8) | wol->sopass[2]);
+			phy_write_mmd(phydev, DP83822_DEVADDR,
+				      MII_DP83822_RXSOP3,
+				      (wol->sopass[5] << 8) | wol->sopass[4]);
+			value |= DP83822_WOL_SECURE_ON;
+		} else {
+			value &= ~DP83822_WOL_SECURE_ON;
+		}
+
+		value |= (DP83822_WOL_EN | DP83822_WOL_INDICATION_SEL |
+			  DP83822_WOL_CLR_INDICATION);
+		phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG,
+			      value);
+	} else {
+		value = phy_read_mmd(phydev, DP83822_DEVADDR,
+				     MII_DP83822_WOL_CFG);
+		value &= ~DP83822_WOL_EN;
+		phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG,
+			      value);
+	}
+
+	return 0;
+}
+
+static void dp83822_get_wol(struct phy_device *phydev,
+			    struct ethtool_wolinfo *wol)
+{
+	int value;
+	u16 sopass_val;
+
+	wol->supported = (WAKE_MAGIC | WAKE_MAGICSECURE);
+	wol->wolopts = 0;
+
+	value = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG);
+
+	if (value & DP83822_WOL_MAGIC_EN)
+		wol->wolopts |= WAKE_MAGIC;
+
+	if (value & DP83822_WOL_SECURE_ON) {
+		sopass_val = phy_read_mmd(phydev, DP83822_DEVADDR,
+					  MII_DP83822_RXSOP1);
+		wol->sopass[0] = (sopass_val & 0xff);
+		wol->sopass[1] = (sopass_val >> 8);
+
+		sopass_val = phy_read_mmd(phydev, DP83822_DEVADDR,
+					  MII_DP83822_RXSOP2);
+		wol->sopass[2] = (sopass_val & 0xff);
+		wol->sopass[3] = (sopass_val >> 8);
+
+		sopass_val = phy_read_mmd(phydev, DP83822_DEVADDR,
+					  MII_DP83822_RXSOP3);
+		wol->sopass[4] = (sopass_val & 0xff);
+		wol->sopass[5] = (sopass_val >> 8);
+
+		wol->wolopts |= WAKE_MAGICSECURE;
+	}
+
+	/* WoL is not enabled so set wolopts to 0 */
+	if (!(value & DP83822_WOL_EN))
+		wol->wolopts = 0;
+}
+
+static int dp83822_config_intr(struct phy_device *phydev)
+{
+	int misr_status;
+	int physcr_status;
+	int err;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+		misr_status = phy_read(phydev, MII_DP83822_MISR1);
+		if (misr_status < 0)
+			return misr_status;
+
+		misr_status |= (DP83822_RX_ERR_HF_INT_EN |
+				DP83822_FALSE_CARRIER_HF_INT_EN |
+				DP83822_ANEG_COMPLETE_INT_EN |
+				DP83822_DUP_MODE_CHANGE_INT_EN |
+				DP83822_SPEED_CHANGED_INT_EN |
+				DP83822_LINK_STAT_INT_EN |
+				DP83822_ENERGY_DET_INT_EN |
+				DP83822_LINK_QUAL_INT_EN);
+
+		err = phy_write(phydev, MII_DP83822_MISR1, misr_status);
+		if (err < 0)
+			return err;
+
+		misr_status = phy_read(phydev, MII_DP83822_MISR2);
+		if (misr_status < 0)
+			return misr_status;
+
+		misr_status |= (DP83822_JABBER_DET_INT_EN |
+				DP83822_WOL_PKT_INT_EN |
+				DP83822_SLEEP_MODE_INT_EN |
+				DP83822_MDI_XOVER_INT_EN |
+				DP83822_LB_FIFO_INT_EN |
+				DP83822_PAGE_RX_INT_EN |
+				DP83822_ANEG_ERR_INT_EN |
+				DP83822_EEE_ERROR_CHANGE_INT_EN);
+
+		err = phy_write(phydev, MII_DP83822_MISR2, misr_status);
+		if (err < 0)
+			return err;
+
+		physcr_status = phy_read(phydev, MII_DP83822_PHYSCR);
+		if (physcr_status < 0)
+			return physcr_status;
+
+		physcr_status |= DP83822_PHYSCR_INT_OE | DP83822_PHYSCR_INTEN;
+
+	} else {
+		err = phy_write(phydev, MII_DP83822_MISR1, 0);
+		if (err < 0)
+			return err;
+
+		err = phy_write(phydev, MII_DP83822_MISR1, 0);
+		if (err < 0)
+			return err;
+
+		physcr_status = phy_read(phydev, MII_DP83822_PHYSCR);
+		if (physcr_status < 0)
+			return physcr_status;
+
+		physcr_status &= ~DP83822_PHYSCR_INTEN;
+	}
+
+	return phy_write(phydev, MII_DP83822_PHYSCR, physcr_status);
+}
+
+static int dp83822_config_init(struct phy_device *phydev)
+{
+	int err;
+	int value;
+
+	err = genphy_config_init(phydev);
+	if (err < 0)
+		return err;
+
+	value = DP83822_WOL_MAGIC_EN | DP83822_WOL_SECURE_ON | DP83822_WOL_EN;
+
+	return phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG,
+	      value);
+}
+
+static int dp83822_phy_reset(struct phy_device *phydev)
+{
+	int err;
+
+	err = phy_write(phydev, MII_DP83822_RESET_CTRL, DP83822_HW_RESET);
+	if (err < 0)
+		return err;
+
+	dp83822_config_init(phydev);
+
+	return 0;
+}
+
+static int dp83822_suspend(struct phy_device *phydev)
+{
+	int value;
+
+	value = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG);
+
+	if (!(value & DP83822_WOL_EN))
+		genphy_suspend(phydev);
+
+	return 0;
+}
+
+static int dp83822_resume(struct phy_device *phydev)
+{
+	int value;
+
+	genphy_resume(phydev);
+
+	value = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG);
+
+	phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, value |
+		      DP83822_WOL_CLR_INDICATION);
+
+	return 0;
+}
+
+static struct phy_driver dp83822_driver[] = {
+	{
+		.phy_id = DP83822_PHY_ID,
+		.phy_id_mask = 0xfffffff0,
+		.name = "TI DP83822",
+		.features = PHY_BASIC_FEATURES,
+		.flags = PHY_HAS_INTERRUPT,
+		.config_init = dp83822_config_init,
+		.soft_reset = dp83822_phy_reset,
+		.get_wol = dp83822_get_wol,
+		.set_wol = dp83822_set_wol,
+		.ack_interrupt = dp83822_ack_interrupt,
+		.config_intr = dp83822_config_intr,
+		.config_aneg = genphy_config_aneg,
+		.read_status = genphy_read_status,
+		.suspend = dp83822_suspend,
+		.resume = dp83822_resume,
+	 },
+};
+module_phy_driver(dp83822_driver);
+
+static struct mdio_device_id __maybe_unused dp83822_tbl[] = {
+	{ DP83822_PHY_ID, 0xfffffff0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(mdio, dp83822_tbl);
+
+MODULE_DESCRIPTION("Texas Instruments DP83822 PHY driver");
+MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c
index 3de4fe4dda77..3966d43c5146 100644
--- a/drivers/net/phy/dp83848.c
+++ b/drivers/net/phy/dp83848.c
@@ -20,7 +20,6 @@
 #define TI_DP83620_PHY_ID		0x20005ce0
 #define NS_DP83848C_PHY_ID		0x20005c90
 #define TLK10X_PHY_ID			0x2000a210
-#define TI_DP83822_PHY_ID		0x2000a240
 
 /* Registers */
 #define DP83848_MICR			0x11 /* MII Interrupt Control Register */
@@ -80,7 +79,6 @@ static struct mdio_device_id __maybe_unused dp83848_tbl[] = {
 	{ NS_DP83848C_PHY_ID, 0xfffffff0 },
 	{ TI_DP83620_PHY_ID, 0xfffffff0 },
 	{ TLK10X_PHY_ID, 0xfffffff0 },
-	{ TI_DP83822_PHY_ID, 0xfffffff0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
@@ -110,7 +108,6 @@ static struct phy_driver dp83848_driver[] = {
 	DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY"),
 	DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY"),
 	DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY"),
-	DP83848_PHY_DRIVER(TI_DP83822_PHY_ID, "TI DP83822 10/100 Mbps PHY"),
 };
 module_phy_driver(dp83848_driver);
 
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index bcb4755bcd95..05c8f1c10e36 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -357,7 +357,7 @@ static void phylink_get_fixed_state(struct phylink *pl, struct phylink_link_stat
  *    1     1       0     1     TX
  */
 static void phylink_resolve_flow(struct phylink *pl,
-	struct phylink_link_state *state)
+				 struct phylink_link_state *state)
 {
 	int new_pause = 0;
 
@@ -506,7 +506,8 @@ static int phylink_register_sfp(struct phylink *pl, struct device_node *np)
 }
 
 struct phylink *phylink_create(struct net_device *ndev, struct device_node *np,
-	phy_interface_t iface, const struct phylink_mac_ops *ops)
+			       phy_interface_t iface,
+			       const struct phylink_mac_ops *ops)
 {
 	struct phylink *pl;
 	int ret;
@@ -585,7 +586,7 @@ void phylink_phy_change(struct phy_device *phydev, bool up, bool do_carrier)
 	phylink_run_resolve(pl);
 
 	netdev_dbg(pl->netdev, "phy link %s %s/%s/%s\n", up ? "up" : "down",
-	           phy_modes(phydev->interface),
+		   phy_modes(phydev->interface),
 		   phy_speed_to_str(phydev->speed),
 		   phy_duplex_to_str(phydev->duplex));
 }
@@ -823,7 +824,7 @@ static void phylink_get_ksettings(const struct phylink_link_state *state,
 }
 
 int phylink_ethtool_ksettings_get(struct phylink *pl,
-	struct ethtool_link_ksettings *kset)
+				  struct ethtool_link_ksettings *kset)
 {
 	struct phylink_link_state link_state;
 
@@ -870,7 +871,7 @@ int phylink_ethtool_ksettings_get(struct phylink *pl,
 EXPORT_SYMBOL_GPL(phylink_ethtool_ksettings_get);
 
 int phylink_ethtool_ksettings_set(struct phylink *pl,
-	const struct ethtool_link_ksettings *kset)
+				  const struct ethtool_link_ksettings *kset)
 {
 	struct ethtool_link_ksettings our_kset;
 	struct phylink_link_state config;
@@ -1337,8 +1338,6 @@ int phylink_mii_ioctl(struct phylink *pl, struct ifreq *ifr, int cmd)
 }
 EXPORT_SYMBOL_GPL(phylink_mii_ioctl);
 
-
-
 static int phylink_sfp_module_insert(void *upstream,
 				     const struct sfp_eeprom_id *id)
 {
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 9cbe645e3d89..d4670ecdb1ba 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -22,17 +22,29 @@
 #define RTL821x_INER		0x12
 #define RTL821x_INER_INIT	0x6400
 #define RTL821x_INSR		0x13
+#define RTL821x_PAGE_SELECT	0x1f
 #define RTL8211E_INER_LINK_STATUS 0x400
 
 #define RTL8211F_INER_LINK_STATUS 0x0010
 #define RTL8211F_INSR		0x1d
-#define RTL8211F_PAGE_SELECT	0x1f
 #define RTL8211F_TX_DELAY	0x100
 
+#define RTL8201F_ISR		0x1e
+#define RTL8201F_IER		0x13
+
 MODULE_DESCRIPTION("Realtek PHY driver");
 MODULE_AUTHOR("Johnson Leung");
 MODULE_LICENSE("GPL");
 
+static int rtl8201_ack_interrupt(struct phy_device *phydev)
+{
+	int err;
+
+	err = phy_read(phydev, RTL8201F_ISR);
+
+	return (err < 0) ? err : 0;
+}
+
 static int rtl821x_ack_interrupt(struct phy_device *phydev)
 {
 	int err;
@@ -46,14 +58,33 @@ static int rtl8211f_ack_interrupt(struct phy_device *phydev)
 {
 	int err;
 
-	phy_write(phydev, RTL8211F_PAGE_SELECT, 0xa43);
+	phy_write(phydev, RTL821x_PAGE_SELECT, 0xa43);
 	err = phy_read(phydev, RTL8211F_INSR);
 	/* restore to default page 0 */
-	phy_write(phydev, RTL8211F_PAGE_SELECT, 0x0);
+	phy_write(phydev, RTL821x_PAGE_SELECT, 0x0);
 
 	return (err < 0) ? err : 0;
 }
 
+static int rtl8201_config_intr(struct phy_device *phydev)
+{
+	int err;
+
+	/* switch to page 7 */
+	phy_write(phydev, RTL821x_PAGE_SELECT, 0x7);
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+		err = phy_write(phydev, RTL8201F_IER,
+				BIT(13) | BIT(12) | BIT(11));
+	else
+		err = phy_write(phydev, RTL8201F_IER, 0);
+
+	/* restore to default page 0 */
+	phy_write(phydev, RTL821x_PAGE_SELECT, 0x0);
+
+	return err;
+}
+
 static int rtl8211b_config_intr(struct phy_device *phydev)
 {
 	int err;
@@ -102,7 +133,7 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 	if (ret < 0)
 		return ret;
 
-	phy_write(phydev, RTL8211F_PAGE_SELECT, 0xd08);
+	phy_write(phydev, RTL821x_PAGE_SELECT, 0xd08);
 	reg = phy_read(phydev, 0x11);
 
 	/* enable TX-delay for rgmii-id and rgmii-txid, otherwise disable it */
@@ -114,7 +145,7 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 
 	phy_write(phydev, 0x11, reg);
 	/* restore to default page 0 */
-	phy_write(phydev, RTL8211F_PAGE_SELECT, 0x0);
+	phy_write(phydev, RTL821x_PAGE_SELECT, 0x0);
 
 	return 0;
 }
@@ -129,6 +160,18 @@ static struct phy_driver realtek_drvs[] = {
 		.config_aneg    = &genphy_config_aneg,
 		.read_status    = &genphy_read_status,
 	}, {
+		.phy_id		= 0x001cc816,
+		.name		= "RTL8201F 10/100Mbps Ethernet",
+		.phy_id_mask	= 0x001fffff,
+		.features	= PHY_BASIC_FEATURES,
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_aneg	= &genphy_config_aneg,
+		.read_status	= &genphy_read_status,
+		.ack_interrupt	= &rtl8201_ack_interrupt,
+		.config_intr	= &rtl8201_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
 		.phy_id		= 0x001cc912,
 		.name		= "RTL8211B Gigabit Ethernet",
 		.phy_id_mask	= 0x001fffff,
@@ -181,6 +224,7 @@ static struct phy_driver realtek_drvs[] = {
 module_phy_driver(realtek_drvs);
 
 static struct mdio_device_id __maybe_unused realtek_tbl[] = {
+	{ 0x001cc816, 0x001fffff },
 	{ 0x001cc912, 0x001fffff },
 	{ 0x001cc914, 0x001fffff },
 	{ 0x001cc915, 0x001fffff },
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 5cb5384697ea..8a1b1f4c1b7c 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -26,7 +26,6 @@ struct sfp_bus {
 	bool started;
 };
 
-
 int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 		   unsigned long *support)
 {
@@ -208,7 +207,6 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 }
 EXPORT_SYMBOL_GPL(sfp_parse_support);
 
-
 static LIST_HEAD(sfp_buses);
 static DEFINE_MUTEX(sfp_mutex);
 
@@ -295,7 +293,6 @@ static void sfp_unregister_bus(struct sfp_bus *bus)
 	bus->registered = false;
 }
 
-
 int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo)
 {
 	if (!bus->registered)
@@ -305,7 +302,7 @@ int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo)
 EXPORT_SYMBOL_GPL(sfp_get_module_info);
 
 int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee,
-	u8 *data)
+			  u8 *data)
 {
 	if (!bus->registered)
 		return -ENOIOCTLCMD;
@@ -330,8 +327,8 @@ void sfp_upstream_stop(struct sfp_bus *bus)
 EXPORT_SYMBOL_GPL(sfp_upstream_stop);
 
 struct sfp_bus *sfp_register_upstream(struct device_node *np,
-	struct net_device *ndev, void *upstream,
-	const struct sfp_upstream_ops *ops)
+				      struct net_device *ndev, void *upstream,
+				      const struct sfp_upstream_ops *ops)
 {
 	struct sfp_bus *bus = sfp_bus_get(np);
 	int ret = 0;
@@ -368,7 +365,6 @@ void sfp_unregister_upstream(struct sfp_bus *bus)
 }
 EXPORT_SYMBOL_GPL(sfp_unregister_upstream);
 
-
 /* Socket driver entry points */
 int sfp_add_phy(struct sfp_bus *bus, struct phy_device *phydev)
 {
@@ -395,7 +391,6 @@ void sfp_remove_phy(struct sfp_bus *bus)
 }
 EXPORT_SYMBOL_GPL(sfp_remove_phy);
 
-
 void sfp_link_up(struct sfp_bus *bus)
 {
 	const struct sfp_upstream_ops *ops = sfp_get_upstream_ops(bus);
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index baee371bf767..e381811e5f11 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -1,5 +1,5 @@
 #include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/jiffies.h>
@@ -88,15 +88,12 @@ static const enum gpiod_flags gpio_flags[] = {
 #define T_PROBE_INIT	msecs_to_jiffies(300)
 #define T_PROBE_RETRY	msecs_to_jiffies(100)
 
-/*
- * SFP modules appear to always have their PHY configured for bus address
+/* SFP modules appear to always have their PHY configured for bus address
  * 0x56 (which with mdio-i2c, translates to a PHY address of 22).
  */
 #define SFP_PHY_ADDR	22
 
-/*
- * Give this long for the PHY to reset.
- */
+/* Give this long for the PHY to reset. */
 #define T_PHY_RESET_MS	50
 
 static DEFINE_MUTEX(sfp_mutex);
@@ -150,10 +147,10 @@ static void sfp_gpio_set_state(struct sfp *sfp, unsigned int state)
 		/* If the module is present, drive the signals */
 		if (sfp->gpio[GPIO_TX_DISABLE])
 			gpiod_direction_output(sfp->gpio[GPIO_TX_DISABLE],
-						state & SFP_F_TX_DISABLE);
+					       state & SFP_F_TX_DISABLE);
 		if (state & SFP_F_RATE_SELECT)
 			gpiod_direction_output(sfp->gpio[GPIO_RATE_SELECT],
-						state & SFP_F_RATE_SELECT);
+					       state & SFP_F_RATE_SELECT);
 	} else {
 		/* Otherwise, let them float to the pull-ups */
 		if (sfp->gpio[GPIO_TX_DISABLE])
@@ -164,7 +161,7 @@ static void sfp_gpio_set_state(struct sfp *sfp, unsigned int state)
 }
 
 static int sfp__i2c_read(struct i2c_adapter *i2c, u8 bus_addr, u8 dev_addr,
-	void *buf, size_t len)
+			 void *buf, size_t len)
 {
 	struct i2c_msg msgs[2];
 	int ret;
@@ -186,7 +183,7 @@ static int sfp__i2c_read(struct i2c_adapter *i2c, u8 bus_addr, u8 dev_addr,
 }
 
 static int sfp_i2c_read(struct sfp *sfp, bool a2, u8 addr, void *buf,
-	size_t len)
+			size_t len)
 {
 	return sfp__i2c_read(sfp->i2c, a2 ? 0x51 : 0x50, addr, buf, len);
 }
@@ -220,7 +217,6 @@ static int sfp_i2c_configure(struct sfp *sfp, struct i2c_adapter *i2c)
 	return 0;
 }
 
-
 /* Interface */
 static unsigned int sfp_get_state(struct sfp *sfp)
 {
@@ -295,7 +291,8 @@ static void sfp_sm_next(struct sfp *sfp, unsigned int state,
 	sfp_sm_set_timer(sfp, timeout);
 }
 
-static void sfp_sm_ins_next(struct sfp *sfp, unsigned int state, unsigned int timeout)
+static void sfp_sm_ins_next(struct sfp *sfp, unsigned int state,
+			    unsigned int timeout)
 {
 	sfp->sm_mod_state = state;
 	sfp_sm_set_timer(sfp, timeout);
@@ -370,7 +367,8 @@ static void sfp_sm_link_check_los(struct sfp *sfp)
 static void sfp_sm_fault(struct sfp *sfp, bool warn)
 {
 	if (sfp->sm_retries && !--sfp->sm_retries) {
-		dev_err(sfp->dev, "module persistently indicates fault, disabling\n");
+		dev_err(sfp->dev,
+			"module persistently indicates fault, disabling\n");
 		sfp_sm_next(sfp, SFP_S_TX_DISABLE, 0);
 	} else {
 		if (warn)
@@ -461,7 +459,8 @@ static int sfp_sm_mod_probe(struct sfp *sfp)
 	memcpy(date, sfp->id.ext.datecode, 8);
 	date[8] = '\0';
 
-	dev_info(sfp->dev, "module %s %s rev %s sn %s dc %s\n", vendor, part, rev, sn, date);
+	dev_info(sfp->dev, "module %s %s rev %s sn %s dc %s\n",
+		 vendor, part, rev, sn, date);
 
 	/* We only support SFP modules, not the legacy GBIC modules. */
 	if (sfp->id.base.phys_id != SFP_PHYS_ID_SFP ||
@@ -651,7 +650,7 @@ static int sfp_module_info(struct sfp *sfp, struct ethtool_modinfo *modinfo)
 }
 
 static int sfp_module_eeprom(struct sfp *sfp, struct ethtool_eeprom *ee,
-	u8 *data)
+			     u8 *data)
 {
 	unsigned int first, last, len;
 	int ret;
diff --git a/drivers/net/phy/uPD60620.c b/drivers/net/phy/uPD60620.c
new file mode 100644
index 000000000000..96b33475ea5e
--- /dev/null
+++ b/drivers/net/phy/uPD60620.c
@@ -0,0 +1,109 @@
+/*
+ * Driver for the Renesas PHY uPD60620.
+ *
+ * Copyright (C) 2015 Softing Industrial Automation GmbH
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+
+#define UPD60620_PHY_ID    0xb8242824
+
+/* Extended Registers and values */
+/* PHY Special Control/Status    */
+#define PHY_PHYSCR         0x1F      /* PHY.31 */
+#define PHY_PHYSCR_10MB    0x0004    /* PHY speed = 10mb */
+#define PHY_PHYSCR_100MB   0x0008    /* PHY speed = 100mb */
+#define PHY_PHYSCR_DUPLEX  0x0010    /* PHY Duplex */
+
+/* PHY Special Modes */
+#define PHY_SPM            0x12      /* PHY.18 */
+
+/* Init PHY */
+
+static int upd60620_config_init(struct phy_device *phydev)
+{
+	/* Enable support for passive HUBs (could be a strap option) */
+	/* PHYMODE: All speeds, HD in parallel detect */
+	return phy_write(phydev, PHY_SPM, 0x0180 | phydev->mdio.addr);
+}
+
+/* Get PHY status from common registers */
+
+static int upd60620_read_status(struct phy_device *phydev)
+{
+	int phy_state;
+
+	/* Read negotiated state */
+	phy_state = phy_read(phydev, MII_BMSR);
+	if (phy_state < 0)
+		return phy_state;
+
+	phydev->link = 0;
+	phydev->lp_advertising = 0;
+	phydev->pause = 0;
+	phydev->asym_pause = 0;
+
+	if (phy_state & (BMSR_ANEGCOMPLETE | BMSR_LSTATUS)) {
+		phy_state = phy_read(phydev, PHY_PHYSCR);
+		if (phy_state < 0)
+			return phy_state;
+
+		if (phy_state & (PHY_PHYSCR_10MB | PHY_PHYSCR_100MB)) {
+			phydev->link = 1;
+			phydev->speed = SPEED_10;
+			phydev->duplex = DUPLEX_HALF;
+
+			if (phy_state & PHY_PHYSCR_100MB)
+				phydev->speed = SPEED_100;
+			if (phy_state & PHY_PHYSCR_DUPLEX)
+				phydev->duplex = DUPLEX_FULL;
+
+			phy_state = phy_read(phydev, MII_LPA);
+			if (phy_state < 0)
+				return phy_state;
+
+			phydev->lp_advertising
+				= mii_lpa_to_ethtool_lpa_t(phy_state);
+
+			if (phydev->duplex == DUPLEX_FULL) {
+				if (phy_state & LPA_PAUSE_CAP)
+					phydev->pause = 1;
+				if (phy_state & LPA_PAUSE_ASYM)
+					phydev->asym_pause = 1;
+			}
+		}
+	}
+	return 0;
+}
+
+MODULE_DESCRIPTION("Renesas uPD60620 PHY driver");
+MODULE_AUTHOR("Bernd Edlinger <bernd.edlinger@hotmail.de>");
+MODULE_LICENSE("GPL");
+
+static struct phy_driver upd60620_driver[1] = { {
+	.phy_id         = UPD60620_PHY_ID,
+	.phy_id_mask    = 0xfffffffe,
+	.name           = "Renesas uPD60620",
+	.features       = PHY_BASIC_FEATURES,
+	.flags          = 0,
+	.config_init    = upd60620_config_init,
+	.config_aneg    = genphy_config_aneg,
+	.read_status    = upd60620_read_status,
+} };
+
+module_phy_driver(upd60620_driver);
+
+static struct mdio_device_id __maybe_unused upd60620_tbl[] = {
+	{ UPD60620_PHY_ID, 0xfffffffe },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(mdio, upd60620_tbl);
diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index 814fd8fae67d..1b28e6e702f5 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -69,7 +69,7 @@ struct asyncppp {
 
 	struct tasklet_struct tsk;
 
-	atomic_t	refcnt;
+	refcount_t	refcnt;
 	struct semaphore dead_sem;
 	struct ppp_channel chan;	/* interface to generic ppp layer */
 	unsigned char	obuf[OBUFSIZE];
@@ -140,14 +140,14 @@ static struct asyncppp *ap_get(struct tty_struct *tty)
 	read_lock(&disc_data_lock);
 	ap = tty->disc_data;
 	if (ap != NULL)
-		atomic_inc(&ap->refcnt);
+		refcount_inc(&ap->refcnt);
 	read_unlock(&disc_data_lock);
 	return ap;
 }
 
 static void ap_put(struct asyncppp *ap)
 {
-	if (atomic_dec_and_test(&ap->refcnt))
+	if (refcount_dec_and_test(&ap->refcnt))
 		up(&ap->dead_sem);
 }
 
@@ -185,7 +185,7 @@ ppp_asynctty_open(struct tty_struct *tty)
 	skb_queue_head_init(&ap->rqueue);
 	tasklet_init(&ap->tsk, ppp_async_process, (unsigned long) ap);
 
-	atomic_set(&ap->refcnt, 1);
+	refcount_set(&ap->refcnt, 1);
 	sema_init(&ap->dead_sem, 0);
 
 	ap->chan.private = ap;
@@ -234,7 +234,7 @@ ppp_asynctty_close(struct tty_struct *tty)
 	 * our channel ops (i.e. ppp_async_send/ioctl) are in progress
 	 * by the time it returns.
 	 */
-	if (!atomic_dec_and_test(&ap->refcnt))
+	if (!refcount_dec_and_test(&ap->refcnt))
 		down(&ap->dead_sem);
 	tasklet_kill(&ap->tsk);
 
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index e365866600ba..44891335f9af 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -51,6 +51,7 @@
 #include <asm/unaligned.h>
 #include <net/slhc_vj.h>
 #include <linux/atomic.h>
+#include <linux/refcount.h>
 
 #include <linux/nsproxy.h>
 #include <net/net_namespace.h>
@@ -84,7 +85,7 @@ struct ppp_file {
 	struct sk_buff_head xq;		/* pppd transmit queue */
 	struct sk_buff_head rq;		/* receive queue for pppd */
 	wait_queue_head_t rwait;	/* for poll on reading /dev/ppp */
-	atomic_t	refcnt;		/* # refs (incl /dev/ppp attached) */
+	refcount_t	refcnt;		/* # refs (incl /dev/ppp attached) */
 	int		hdrlen;		/* space to leave for headers */
 	int		index;		/* interface unit / channel number */
 	int		dead;		/* unit/channel has been shut down */
@@ -389,7 +390,7 @@ static int ppp_open(struct inode *inode, struct file *file)
 	/*
 	 * This could (should?) be enforced by the permissions on /dev/ppp.
 	 */
-	if (!capable(CAP_NET_ADMIN))
+	if (!ns_capable(file->f_cred->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 	return 0;
 }
@@ -408,7 +409,7 @@ static int ppp_release(struct inode *unused, struct file *file)
 				unregister_netdevice(ppp->dev);
 			rtnl_unlock();
 		}
-		if (atomic_dec_and_test(&pf->refcnt)) {
+		if (refcount_dec_and_test(&pf->refcnt)) {
 			switch (pf->kind) {
 			case INTERFACE:
 				ppp_destroy_interface(PF_TO_PPP(pf));
@@ -881,7 +882,7 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 		mutex_lock(&pn->all_ppp_mutex);
 		ppp = ppp_find_unit(pn, unit);
 		if (ppp) {
-			atomic_inc(&ppp->file.refcnt);
+			refcount_inc(&ppp->file.refcnt);
 			file->private_data = &ppp->file;
 			err = 0;
 		}
@@ -896,7 +897,7 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 		spin_lock_bh(&pn->all_channels_lock);
 		chan = ppp_find_channel(pn, unit);
 		if (chan) {
-			atomic_inc(&chan->file.refcnt);
+			refcount_inc(&chan->file.refcnt);
 			file->private_data = &chan->file;
 			err = 0;
 		}
@@ -959,6 +960,7 @@ static __net_exit void ppp_exit_net(struct net *net)
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
 
+	mutex_destroy(&pn->all_ppp_mutex);
 	idr_destroy(&pn->units_idr);
 }
 
@@ -1348,7 +1350,7 @@ static int ppp_dev_init(struct net_device *dev)
 	 * that ppp_destroy_interface() won't run before the device gets
 	 * unregistered.
 	 */
-	atomic_inc(&ppp->file.refcnt);
+	refcount_inc(&ppp->file.refcnt);
 
 	return 0;
 }
@@ -1377,7 +1379,7 @@ static void ppp_dev_priv_destructor(struct net_device *dev)
 	struct ppp *ppp;
 
 	ppp = netdev_priv(dev);
-	if (atomic_dec_and_test(&ppp->file.refcnt))
+	if (refcount_dec_and_test(&ppp->file.refcnt))
 		ppp_destroy_interface(ppp);
 }
 
@@ -2676,7 +2678,7 @@ ppp_unregister_channel(struct ppp_channel *chan)
 
 	pch->file.dead = 1;
 	wake_up_interruptible(&pch->file.rwait);
-	if (atomic_dec_and_test(&pch->file.refcnt))
+	if (refcount_dec_and_test(&pch->file.refcnt))
 		ppp_destroy_channel(pch);
 }
 
@@ -3046,7 +3048,7 @@ init_ppp_file(struct ppp_file *pf, int kind)
 	pf->kind = kind;
 	skb_queue_head_init(&pf->xq);
 	skb_queue_head_init(&pf->rq);
-	atomic_set(&pf->refcnt, 1);
+	refcount_set(&pf->refcnt, 1);
 	init_waitqueue_head(&pf->rwait);
 }
 
@@ -3164,7 +3166,7 @@ ppp_connect_channel(struct channel *pch, int unit)
 	list_add_tail(&pch->clist, &ppp->channels);
 	++ppp->n_channels;
 	pch->ppp = ppp;
-	atomic_inc(&ppp->file.refcnt);
+	refcount_inc(&ppp->file.refcnt);
 	ppp_unlock(ppp);
 	ret = 0;
 
@@ -3195,7 +3197,7 @@ ppp_disconnect_channel(struct channel *pch)
 		if (--ppp->n_channels == 0)
 			wake_up_interruptible(&ppp->file.rwait);
 		ppp_unlock(ppp);
-		if (atomic_dec_and_test(&ppp->file.refcnt))
+		if (refcount_dec_and_test(&ppp->file.refcnt))
 			ppp_destroy_interface(ppp);
 		err = 0;
 	}
diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c
index 7868c29071d4..7196f00f0991 100644
--- a/drivers/net/ppp/ppp_synctty.c
+++ b/drivers/net/ppp/ppp_synctty.c
@@ -46,6 +46,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/refcount.h>
 #include <asm/unaligned.h>
 #include <linux/uaccess.h>
 
@@ -72,7 +73,7 @@ struct syncppp {
 
 	struct tasklet_struct tsk;
 
-	atomic_t	refcnt;
+	refcount_t	refcnt;
 	struct completion dead_cmp;
 	struct ppp_channel chan;	/* interface to generic ppp layer */
 };
@@ -141,14 +142,14 @@ static struct syncppp *sp_get(struct tty_struct *tty)
 	read_lock(&disc_data_lock);
 	ap = tty->disc_data;
 	if (ap != NULL)
-		atomic_inc(&ap->refcnt);
+		refcount_inc(&ap->refcnt);
 	read_unlock(&disc_data_lock);
 	return ap;
 }
 
 static void sp_put(struct syncppp *ap)
 {
-	if (atomic_dec_and_test(&ap->refcnt))
+	if (refcount_dec_and_test(&ap->refcnt))
 		complete(&ap->dead_cmp);
 }
 
@@ -182,7 +183,7 @@ ppp_sync_open(struct tty_struct *tty)
 	skb_queue_head_init(&ap->rqueue);
 	tasklet_init(&ap->tsk, ppp_sync_process, (unsigned long) ap);
 
-	atomic_set(&ap->refcnt, 1);
+	refcount_set(&ap->refcnt, 1);
 	init_completion(&ap->dead_cmp);
 
 	ap->chan.private = ap;
@@ -232,7 +233,7 @@ ppp_sync_close(struct tty_struct *tty)
 	 * our channel ops (i.e. ppp_sync_send/ioctl) are in progress
 	 * by the time it returns.
 	 */
-	if (!atomic_dec_and_test(&ap->refcnt))
+	if (!refcount_dec_and_test(&ap->refcnt))
 		wait_for_completion(&ap->dead_cmp);
 	tasklet_kill(&ap->tsk);
 
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 436dd78c396a..eb8a18991d8c 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -763,12 +763,8 @@ static struct slip *sl_alloc(dev_t line)
 	sl->mode        = SL_MODE_DEFAULT;
 #ifdef CONFIG_SLIP_SMART
 	/* initialize timer_list struct */
-	init_timer(&sl->keepalive_timer);
-	sl->keepalive_timer.data = (unsigned long)sl;
-	sl->keepalive_timer.function = sl_keepalive;
-	init_timer(&sl->outfill_timer);
-	sl->outfill_timer.data = (unsigned long)sl;
-	sl->outfill_timer.function = sl_outfill;
+	setup_timer(&sl->keepalive_timer, sl_keepalive, (unsigned long)sl);
+	setup_timer(&sl->outfill_timer, sl_outfill, (unsigned long)sl);
 #endif
 	slip_devs[i] = dev;
 	return sl;
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ae53e899259f..a468439969df 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1112,7 +1112,7 @@ static int team_upper_dev_link(struct team *team, struct team_port *port)
 
 	lag_upper_info.tx_type = team->mode->lag_tx_type;
 	err = netdev_master_upper_dev_link(port->dev, team->dev, NULL,
-					   &lag_upper_info);
+					   &lag_upper_info, NULL);
 	if (err)
 		return err;
 	port->dev->priv_flags |= IFF_TEAM_PORT;
@@ -1914,7 +1914,8 @@ static int team_netpoll_setup(struct net_device *dev,
 }
 #endif
 
-static int team_add_slave(struct net_device *dev, struct net_device *port_dev)
+static int team_add_slave(struct net_device *dev, struct net_device *port_dev,
+			  struct netlink_ext_ack *extack)
 {
 	struct team *team = netdev_priv(dev);
 	int err;
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index 1468ddf424cc..a5ef97010eb3 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -137,7 +137,13 @@ static struct team_port *lb_htpm_select_tx_port(struct team *team,
 						struct sk_buff *skb,
 						unsigned char hash)
 {
-	return rcu_dereference_bh(LB_HTPM_PORT_BY_HASH(lb_priv, hash));
+	struct team_port *port;
+
+	port = rcu_dereference_bh(LB_HTPM_PORT_BY_HASH(lb_priv, hash));
+	if (likely(port))
+		return port;
+	/* If no valid port in the table, fall back to simple hash */
+	return lb_hash_select_tx_port(team, lb_priv, skb, hash);
 }
 
 struct lb_select_tx_port {
diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c
new file mode 100644
index 000000000000..435854688a7a
--- /dev/null
+++ b/drivers/net/thunderbolt.c
@@ -0,0 +1,1362 @@
+/*
+ * Networking over Thunderbolt cable using Apple ThunderboltIP protocol
+ *
+ * Copyright (C) 2017, Intel Corporation
+ * Authors: Amir Levy <amir.jer.levy@intel.com>
+ *          Michael Jamet <michael.jamet@intel.com>
+ *          Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/atomic.h>
+#include <linux/highmem.h>
+#include <linux/if_vlan.h>
+#include <linux/jhash.h>
+#include <linux/module.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/sizes.h>
+#include <linux/thunderbolt.h>
+#include <linux/uuid.h>
+#include <linux/workqueue.h>
+
+#include <net/ip6_checksum.h>
+
+/* Protocol timeouts in ms */
+#define TBNET_LOGIN_DELAY	4500
+#define TBNET_LOGIN_TIMEOUT	500
+#define TBNET_LOGOUT_TIMEOUT	100
+
+#define TBNET_RING_SIZE		256
+#define TBNET_LOCAL_PATH	0xf
+#define TBNET_LOGIN_RETRIES	60
+#define TBNET_LOGOUT_RETRIES	5
+#define TBNET_MATCH_FRAGS_ID	BIT(1)
+#define TBNET_MAX_MTU		SZ_64K
+#define TBNET_FRAME_SIZE	SZ_4K
+#define TBNET_MAX_PAYLOAD_SIZE	\
+	(TBNET_FRAME_SIZE - sizeof(struct thunderbolt_ip_frame_header))
+/* Rx packets need to hold space for skb_shared_info */
+#define TBNET_RX_MAX_SIZE	\
+	(TBNET_FRAME_SIZE + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define TBNET_RX_PAGE_ORDER	get_order(TBNET_RX_MAX_SIZE)
+#define TBNET_RX_PAGE_SIZE	(PAGE_SIZE << TBNET_RX_PAGE_ORDER)
+
+#define TBNET_L0_PORT_NUM(route) ((route) & GENMASK(5, 0))
+
+/**
+ * struct thunderbolt_ip_frame_header - Header for each Thunderbolt frame
+ * @frame_size: size of the data with the frame
+ * @frame_index: running index on the frames
+ * @frame_id: ID of the frame to match frames to specific packet
+ * @frame_count: how many frames assembles a full packet
+ *
+ * Each data frame passed to the high-speed DMA ring has this header. If
+ * the XDomain network directory announces that %TBNET_MATCH_FRAGS_ID is
+ * supported then @frame_id is filled, otherwise it stays %0.
+ */
+struct thunderbolt_ip_frame_header {
+	u32 frame_size;
+	u16 frame_index;
+	u16 frame_id;
+	u32 frame_count;
+};
+
+enum thunderbolt_ip_frame_pdf {
+	TBIP_PDF_FRAME_START = 1,
+	TBIP_PDF_FRAME_END,
+};
+
+enum thunderbolt_ip_type {
+	TBIP_LOGIN,
+	TBIP_LOGIN_RESPONSE,
+	TBIP_LOGOUT,
+	TBIP_STATUS,
+};
+
+struct thunderbolt_ip_header {
+	u32 route_hi;
+	u32 route_lo;
+	u32 length_sn;
+	uuid_t uuid;
+	uuid_t initiator_uuid;
+	uuid_t target_uuid;
+	u32 type;
+	u32 command_id;
+};
+
+#define TBIP_HDR_LENGTH_MASK		GENMASK(5, 0)
+#define TBIP_HDR_SN_MASK		GENMASK(28, 27)
+#define TBIP_HDR_SN_SHIFT		27
+
+struct thunderbolt_ip_login {
+	struct thunderbolt_ip_header hdr;
+	u32 proto_version;
+	u32 transmit_path;
+	u32 reserved[4];
+};
+
+#define TBIP_LOGIN_PROTO_VERSION	1
+
+struct thunderbolt_ip_login_response {
+	struct thunderbolt_ip_header hdr;
+	u32 status;
+	u32 receiver_mac[2];
+	u32 receiver_mac_len;
+	u32 reserved[4];
+};
+
+struct thunderbolt_ip_logout {
+	struct thunderbolt_ip_header hdr;
+};
+
+struct thunderbolt_ip_status {
+	struct thunderbolt_ip_header hdr;
+	u32 status;
+};
+
+struct tbnet_stats {
+	u64 tx_packets;
+	u64 rx_packets;
+	u64 tx_bytes;
+	u64 rx_bytes;
+	u64 rx_errors;
+	u64 tx_errors;
+	u64 rx_length_errors;
+	u64 rx_over_errors;
+	u64 rx_crc_errors;
+	u64 rx_missed_errors;
+};
+
+struct tbnet_frame {
+	struct net_device *dev;
+	struct page *page;
+	struct ring_frame frame;
+};
+
+struct tbnet_ring {
+	struct tbnet_frame frames[TBNET_RING_SIZE];
+	unsigned int cons;
+	unsigned int prod;
+	struct tb_ring *ring;
+};
+
+/**
+ * struct tbnet - ThunderboltIP network driver private data
+ * @svc: XDomain service the driver is bound to
+ * @xd: XDomain the service blongs to
+ * @handler: ThunderboltIP configuration protocol handler
+ * @dev: Networking device
+ * @napi: NAPI structure for Rx polling
+ * @stats: Network statistics
+ * @skb: Network packet that is currently processed on Rx path
+ * @command_id: ID used for next configuration protocol packet
+ * @login_sent: ThunderboltIP login message successfully sent
+ * @login_received: ThunderboltIP login message received from the remote
+ *		    host
+ * @transmit_path: HopID the other end needs to use building the
+ *		   opposite side path.
+ * @connection_lock: Lock serializing access to @login_sent,
+ *		     @login_received and @transmit_path.
+ * @login_retries: Number of login retries currently done
+ * @login_work: Worker to send ThunderboltIP login packets
+ * @connected_work: Worker that finalizes the ThunderboltIP connection
+ *		    setup and enables DMA paths for high speed data
+ *		    transfers
+ * @rx_hdr: Copy of the currently processed Rx frame. Used when a
+ *	    network packet consists of multiple Thunderbolt frames.
+ *	    In host byte order.
+ * @rx_ring: Software ring holding Rx frames
+ * @frame_id: Frame ID use for next Tx packet
+ *            (if %TBNET_MATCH_FRAGS_ID is supported in both ends)
+ * @tx_ring: Software ring holding Tx frames
+ */
+struct tbnet {
+	const struct tb_service *svc;
+	struct tb_xdomain *xd;
+	struct tb_protocol_handler handler;
+	struct net_device *dev;
+	struct napi_struct napi;
+	struct tbnet_stats stats;
+	struct sk_buff *skb;
+	atomic_t command_id;
+	bool login_sent;
+	bool login_received;
+	u32 transmit_path;
+	struct mutex connection_lock;
+	int login_retries;
+	struct delayed_work login_work;
+	struct work_struct connected_work;
+	struct thunderbolt_ip_frame_header rx_hdr;
+	struct tbnet_ring rx_ring;
+	atomic_t frame_id;
+	struct tbnet_ring tx_ring;
+};
+
+/* Network property directory UUID: c66189ca-1cce-4195-bdb8-49592e5f5a4f */
+static const uuid_t tbnet_dir_uuid =
+	UUID_INIT(0xc66189ca, 0x1cce, 0x4195,
+		  0xbd, 0xb8, 0x49, 0x59, 0x2e, 0x5f, 0x5a, 0x4f);
+
+/* ThunderboltIP protocol UUID: 798f589e-3616-8a47-97c6-5664a920c8dd */
+static const uuid_t tbnet_svc_uuid =
+	UUID_INIT(0x798f589e, 0x3616, 0x8a47,
+		  0x97, 0xc6, 0x56, 0x64, 0xa9, 0x20, 0xc8, 0xdd);
+
+static struct tb_property_dir *tbnet_dir;
+
+static void tbnet_fill_header(struct thunderbolt_ip_header *hdr, u64 route,
+	u8 sequence, const uuid_t *initiator_uuid, const uuid_t *target_uuid,
+	enum thunderbolt_ip_type type, size_t size, u32 command_id)
+{
+	u32 length_sn;
+
+	/* Length does not include route_hi/lo and length_sn fields */
+	length_sn = (size - 3 * 4) / 4;
+	length_sn |= (sequence << TBIP_HDR_SN_SHIFT) & TBIP_HDR_SN_MASK;
+
+	hdr->route_hi = upper_32_bits(route);
+	hdr->route_lo = lower_32_bits(route);
+	hdr->length_sn = length_sn;
+	uuid_copy(&hdr->uuid, &tbnet_svc_uuid);
+	uuid_copy(&hdr->initiator_uuid, initiator_uuid);
+	uuid_copy(&hdr->target_uuid, target_uuid);
+	hdr->type = type;
+	hdr->command_id = command_id;
+}
+
+static int tbnet_login_response(struct tbnet *net, u64 route, u8 sequence,
+				u32 command_id)
+{
+	struct thunderbolt_ip_login_response reply;
+	struct tb_xdomain *xd = net->xd;
+
+	memset(&reply, 0, sizeof(reply));
+	tbnet_fill_header(&reply.hdr, route, sequence, xd->local_uuid,
+			  xd->remote_uuid, TBIP_LOGIN_RESPONSE, sizeof(reply),
+			  command_id);
+	memcpy(reply.receiver_mac, net->dev->dev_addr, ETH_ALEN);
+	reply.receiver_mac_len = ETH_ALEN;
+
+	return tb_xdomain_response(xd, &reply, sizeof(reply),
+				   TB_CFG_PKG_XDOMAIN_RESP);
+}
+
+static int tbnet_login_request(struct tbnet *net, u8 sequence)
+{
+	struct thunderbolt_ip_login_response reply;
+	struct thunderbolt_ip_login request;
+	struct tb_xdomain *xd = net->xd;
+
+	memset(&request, 0, sizeof(request));
+	tbnet_fill_header(&request.hdr, xd->route, sequence, xd->local_uuid,
+			  xd->remote_uuid, TBIP_LOGIN, sizeof(request),
+			  atomic_inc_return(&net->command_id));
+
+	request.proto_version = TBIP_LOGIN_PROTO_VERSION;
+	request.transmit_path = TBNET_LOCAL_PATH;
+
+	return tb_xdomain_request(xd, &request, sizeof(request),
+				  TB_CFG_PKG_XDOMAIN_RESP, &reply,
+				  sizeof(reply), TB_CFG_PKG_XDOMAIN_RESP,
+				  TBNET_LOGIN_TIMEOUT);
+}
+
+static int tbnet_logout_response(struct tbnet *net, u64 route, u8 sequence,
+				 u32 command_id)
+{
+	struct thunderbolt_ip_status reply;
+	struct tb_xdomain *xd = net->xd;
+
+	memset(&reply, 0, sizeof(reply));
+	tbnet_fill_header(&reply.hdr, route, sequence, xd->local_uuid,
+			  xd->remote_uuid, TBIP_STATUS, sizeof(reply),
+			  atomic_inc_return(&net->command_id));
+	return tb_xdomain_response(xd, &reply, sizeof(reply),
+				   TB_CFG_PKG_XDOMAIN_RESP);
+}
+
+static int tbnet_logout_request(struct tbnet *net)
+{
+	struct thunderbolt_ip_logout request;
+	struct thunderbolt_ip_status reply;
+	struct tb_xdomain *xd = net->xd;
+
+	memset(&request, 0, sizeof(request));
+	tbnet_fill_header(&request.hdr, xd->route, 0, xd->local_uuid,
+			  xd->remote_uuid, TBIP_LOGOUT, sizeof(request),
+			  atomic_inc_return(&net->command_id));
+
+	return tb_xdomain_request(xd, &request, sizeof(request),
+				  TB_CFG_PKG_XDOMAIN_RESP, &reply,
+				  sizeof(reply), TB_CFG_PKG_XDOMAIN_RESP,
+				  TBNET_LOGOUT_TIMEOUT);
+}
+
+static void start_login(struct tbnet *net)
+{
+	mutex_lock(&net->connection_lock);
+	net->login_sent = false;
+	net->login_received = false;
+	mutex_unlock(&net->connection_lock);
+
+	queue_delayed_work(system_long_wq, &net->login_work,
+			   msecs_to_jiffies(1000));
+}
+
+static void stop_login(struct tbnet *net)
+{
+	cancel_delayed_work_sync(&net->login_work);
+	cancel_work_sync(&net->connected_work);
+}
+
+static inline unsigned int tbnet_frame_size(const struct tbnet_frame *tf)
+{
+	return tf->frame.size ? : TBNET_FRAME_SIZE;
+}
+
+static void tbnet_free_buffers(struct tbnet_ring *ring)
+{
+	unsigned int i;
+
+	for (i = 0; i < TBNET_RING_SIZE; i++) {
+		struct device *dma_dev = tb_ring_dma_device(ring->ring);
+		struct tbnet_frame *tf = &ring->frames[i];
+		enum dma_data_direction dir;
+		unsigned int order;
+		size_t size;
+
+		if (!tf->page)
+			continue;
+
+		if (ring->ring->is_tx) {
+			dir = DMA_TO_DEVICE;
+			order = 0;
+			size = tbnet_frame_size(tf);
+		} else {
+			dir = DMA_FROM_DEVICE;
+			order = TBNET_RX_PAGE_ORDER;
+			size = TBNET_RX_PAGE_SIZE;
+		}
+
+		if (tf->frame.buffer_phy)
+			dma_unmap_page(dma_dev, tf->frame.buffer_phy, size,
+				       dir);
+
+		__free_pages(tf->page, order);
+		tf->page = NULL;
+	}
+
+	ring->cons = 0;
+	ring->prod = 0;
+}
+
+static void tbnet_tear_down(struct tbnet *net, bool send_logout)
+{
+	netif_carrier_off(net->dev);
+	netif_stop_queue(net->dev);
+
+	stop_login(net);
+
+	mutex_lock(&net->connection_lock);
+
+	if (net->login_sent && net->login_received) {
+		int retries = TBNET_LOGOUT_RETRIES;
+
+		while (send_logout && retries-- > 0) {
+			int ret = tbnet_logout_request(net);
+			if (ret != -ETIMEDOUT)
+				break;
+		}
+
+		tb_ring_stop(net->rx_ring.ring);
+		tb_ring_stop(net->tx_ring.ring);
+		tbnet_free_buffers(&net->rx_ring);
+		tbnet_free_buffers(&net->tx_ring);
+
+		if (tb_xdomain_disable_paths(net->xd))
+			netdev_warn(net->dev, "failed to disable DMA paths\n");
+	}
+
+	net->login_retries = 0;
+	net->login_sent = false;
+	net->login_received = false;
+
+	mutex_unlock(&net->connection_lock);
+}
+
+static int tbnet_handle_packet(const void *buf, size_t size, void *data)
+{
+	const struct thunderbolt_ip_login *pkg = buf;
+	struct tbnet *net = data;
+	u32 command_id;
+	int ret = 0;
+	u32 sequence;
+	u64 route;
+
+	/* Make sure the packet is for us */
+	if (size < sizeof(struct thunderbolt_ip_header))
+		return 0;
+	if (!uuid_equal(&pkg->hdr.initiator_uuid, net->xd->remote_uuid))
+		return 0;
+	if (!uuid_equal(&pkg->hdr.target_uuid, net->xd->local_uuid))
+		return 0;
+
+	route = ((u64)pkg->hdr.route_hi << 32) | pkg->hdr.route_lo;
+	route &= ~BIT_ULL(63);
+	if (route != net->xd->route)
+		return 0;
+
+	sequence = pkg->hdr.length_sn & TBIP_HDR_SN_MASK;
+	sequence >>= TBIP_HDR_SN_SHIFT;
+	command_id = pkg->hdr.command_id;
+
+	switch (pkg->hdr.type) {
+	case TBIP_LOGIN:
+		if (!netif_running(net->dev))
+			break;
+
+		ret = tbnet_login_response(net, route, sequence,
+					   pkg->hdr.command_id);
+		if (!ret) {
+			mutex_lock(&net->connection_lock);
+			net->login_received = true;
+			net->transmit_path = pkg->transmit_path;
+
+			/* If we reached the number of max retries or
+			 * previous logout, schedule another round of
+			 * login retries
+			 */
+			if (net->login_retries >= TBNET_LOGIN_RETRIES ||
+			    !net->login_sent) {
+				net->login_retries = 0;
+				queue_delayed_work(system_long_wq,
+						   &net->login_work, 0);
+			}
+			mutex_unlock(&net->connection_lock);
+
+			queue_work(system_long_wq, &net->connected_work);
+		}
+		break;
+
+	case TBIP_LOGOUT:
+		ret = tbnet_logout_response(net, route, sequence, command_id);
+		if (!ret)
+			tbnet_tear_down(net, false);
+		break;
+
+	default:
+		return 0;
+	}
+
+	if (ret)
+		netdev_warn(net->dev, "failed to send ThunderboltIP response\n");
+
+	return 1;
+}
+
+static unsigned int tbnet_available_buffers(const struct tbnet_ring *ring)
+{
+	return ring->prod - ring->cons;
+}
+
+static int tbnet_alloc_rx_buffers(struct tbnet *net, unsigned int nbuffers)
+{
+	struct tbnet_ring *ring = &net->rx_ring;
+	int ret;
+
+	while (nbuffers--) {
+		struct device *dma_dev = tb_ring_dma_device(ring->ring);
+		unsigned int index = ring->prod & (TBNET_RING_SIZE - 1);
+		struct tbnet_frame *tf = &ring->frames[index];
+		dma_addr_t dma_addr;
+
+		if (tf->page)
+			break;
+
+		/* Allocate page (order > 0) so that it can hold maximum
+		 * ThunderboltIP frame (4kB) and the additional room for
+		 * SKB shared info required by build_skb().
+		 */
+		tf->page = dev_alloc_pages(TBNET_RX_PAGE_ORDER);
+		if (!tf->page) {
+			ret = -ENOMEM;
+			goto err_free;
+		}
+
+		dma_addr = dma_map_page(dma_dev, tf->page, 0,
+					TBNET_RX_PAGE_SIZE, DMA_FROM_DEVICE);
+		if (dma_mapping_error(dma_dev, dma_addr)) {
+			ret = -ENOMEM;
+			goto err_free;
+		}
+
+		tf->frame.buffer_phy = dma_addr;
+		tf->dev = net->dev;
+
+		tb_ring_rx(ring->ring, &tf->frame);
+
+		ring->prod++;
+	}
+
+	return 0;
+
+err_free:
+	tbnet_free_buffers(ring);
+	return ret;
+}
+
+static struct tbnet_frame *tbnet_get_tx_buffer(struct tbnet *net)
+{
+	struct tbnet_ring *ring = &net->tx_ring;
+	struct tbnet_frame *tf;
+	unsigned int index;
+
+	if (!tbnet_available_buffers(ring))
+		return NULL;
+
+	index = ring->cons++ & (TBNET_RING_SIZE - 1);
+
+	tf = &ring->frames[index];
+	tf->frame.size = 0;
+	tf->frame.buffer_phy = 0;
+
+	return tf;
+}
+
+static void tbnet_tx_callback(struct tb_ring *ring, struct ring_frame *frame,
+			      bool canceled)
+{
+	struct tbnet_frame *tf = container_of(frame, typeof(*tf), frame);
+	struct device *dma_dev = tb_ring_dma_device(ring);
+	struct tbnet *net = netdev_priv(tf->dev);
+
+	dma_unmap_page(dma_dev, tf->frame.buffer_phy, tbnet_frame_size(tf),
+		       DMA_TO_DEVICE);
+
+	/* Return buffer to the ring */
+	net->tx_ring.prod++;
+
+	if (tbnet_available_buffers(&net->tx_ring) >= TBNET_RING_SIZE / 2)
+		netif_wake_queue(net->dev);
+}
+
+static int tbnet_alloc_tx_buffers(struct tbnet *net)
+{
+	struct tbnet_ring *ring = &net->tx_ring;
+	unsigned int i;
+
+	for (i = 0; i < TBNET_RING_SIZE; i++) {
+		struct tbnet_frame *tf = &ring->frames[i];
+
+		tf->page = alloc_page(GFP_KERNEL);
+		if (!tf->page) {
+			tbnet_free_buffers(ring);
+			return -ENOMEM;
+		}
+
+		tf->dev = net->dev;
+		tf->frame.callback = tbnet_tx_callback;
+		tf->frame.sof = TBIP_PDF_FRAME_START;
+		tf->frame.eof = TBIP_PDF_FRAME_END;
+	}
+
+	ring->cons = 0;
+	ring->prod = TBNET_RING_SIZE - 1;
+
+	return 0;
+}
+
+static void tbnet_connected_work(struct work_struct *work)
+{
+	struct tbnet *net = container_of(work, typeof(*net), connected_work);
+	bool connected;
+	int ret;
+
+	if (netif_carrier_ok(net->dev))
+		return;
+
+	mutex_lock(&net->connection_lock);
+	connected = net->login_sent && net->login_received;
+	mutex_unlock(&net->connection_lock);
+
+	if (!connected)
+		return;
+
+	/* Both logins successful so enable the high-speed DMA paths and
+	 * start the network device queue.
+	 */
+	ret = tb_xdomain_enable_paths(net->xd, TBNET_LOCAL_PATH,
+				      net->rx_ring.ring->hop,
+				      net->transmit_path,
+				      net->tx_ring.ring->hop);
+	if (ret) {
+		netdev_err(net->dev, "failed to enable DMA paths\n");
+		return;
+	}
+
+	tb_ring_start(net->tx_ring.ring);
+	tb_ring_start(net->rx_ring.ring);
+
+	ret = tbnet_alloc_rx_buffers(net, TBNET_RING_SIZE);
+	if (ret)
+		goto err_stop_rings;
+
+	ret = tbnet_alloc_tx_buffers(net);
+	if (ret)
+		goto err_free_rx_buffers;
+
+	netif_carrier_on(net->dev);
+	netif_start_queue(net->dev);
+	return;
+
+err_free_rx_buffers:
+	tbnet_free_buffers(&net->rx_ring);
+err_stop_rings:
+	tb_ring_stop(net->rx_ring.ring);
+	tb_ring_stop(net->tx_ring.ring);
+}
+
+static void tbnet_login_work(struct work_struct *work)
+{
+	struct tbnet *net = container_of(work, typeof(*net), login_work.work);
+	unsigned long delay = msecs_to_jiffies(TBNET_LOGIN_DELAY);
+	int ret;
+
+	if (netif_carrier_ok(net->dev))
+		return;
+
+	ret = tbnet_login_request(net, net->login_retries % 4);
+	if (ret) {
+		if (net->login_retries++ < TBNET_LOGIN_RETRIES) {
+			queue_delayed_work(system_long_wq, &net->login_work,
+					   delay);
+		} else {
+			netdev_info(net->dev, "ThunderboltIP login timed out\n");
+		}
+	} else {
+		net->login_retries = 0;
+
+		mutex_lock(&net->connection_lock);
+		net->login_sent = true;
+		mutex_unlock(&net->connection_lock);
+
+		queue_work(system_long_wq, &net->connected_work);
+	}
+}
+
+static bool tbnet_check_frame(struct tbnet *net, const struct tbnet_frame *tf,
+			      const struct thunderbolt_ip_frame_header *hdr)
+{
+	u32 frame_id, frame_count, frame_size, frame_index;
+	unsigned int size;
+
+	if (tf->frame.flags & RING_DESC_CRC_ERROR) {
+		net->stats.rx_crc_errors++;
+		return false;
+	} else if (tf->frame.flags & RING_DESC_BUFFER_OVERRUN) {
+		net->stats.rx_over_errors++;
+		return false;
+	}
+
+	/* Should be greater than just header i.e. contains data */
+	size = tbnet_frame_size(tf);
+	if (size <= sizeof(*hdr)) {
+		net->stats.rx_length_errors++;
+		return false;
+	}
+
+	frame_count = le32_to_cpu(hdr->frame_count);
+	frame_size = le32_to_cpu(hdr->frame_size);
+	frame_index = le16_to_cpu(hdr->frame_index);
+	frame_id = le16_to_cpu(hdr->frame_id);
+
+	if ((frame_size > size - sizeof(*hdr)) || !frame_size) {
+		net->stats.rx_length_errors++;
+		return false;
+	}
+
+	/* In case we're in the middle of packet, validate the frame
+	 * header based on first fragment of the packet.
+	 */
+	if (net->skb && net->rx_hdr.frame_count) {
+		/* Check the frame count fits the count field */
+		if (frame_count != net->rx_hdr.frame_count) {
+			net->stats.rx_length_errors++;
+			return false;
+		}
+
+		/* Check the frame identifiers are incremented correctly,
+		 * and id is matching.
+		 */
+		if (frame_index != net->rx_hdr.frame_index + 1 ||
+		    frame_id != net->rx_hdr.frame_id) {
+			net->stats.rx_missed_errors++;
+			return false;
+		}
+
+		if (net->skb->len + frame_size > TBNET_MAX_MTU) {
+			net->stats.rx_length_errors++;
+			return false;
+		}
+
+		return true;
+	}
+
+	/* Start of packet, validate the frame header */
+	if (frame_count == 0 || frame_count > TBNET_RING_SIZE / 4) {
+		net->stats.rx_length_errors++;
+		return false;
+	}
+	if (frame_index != 0) {
+		net->stats.rx_missed_errors++;
+		return false;
+	}
+
+	return true;
+}
+
+static int tbnet_poll(struct napi_struct *napi, int budget)
+{
+	struct tbnet *net = container_of(napi, struct tbnet, napi);
+	unsigned int cleaned_count = tbnet_available_buffers(&net->rx_ring);
+	struct device *dma_dev = tb_ring_dma_device(net->rx_ring.ring);
+	unsigned int rx_packets = 0;
+
+	while (rx_packets < budget) {
+		const struct thunderbolt_ip_frame_header *hdr;
+		unsigned int hdr_size = sizeof(*hdr);
+		struct sk_buff *skb = NULL;
+		struct ring_frame *frame;
+		struct tbnet_frame *tf;
+		struct page *page;
+		bool last = true;
+		u32 frame_size;
+
+		/* Return some buffers to hardware, one at a time is too
+		 * slow so allocate MAX_SKB_FRAGS buffers at the same
+		 * time.
+		 */
+		if (cleaned_count >= MAX_SKB_FRAGS) {
+			tbnet_alloc_rx_buffers(net, cleaned_count);
+			cleaned_count = 0;
+		}
+
+		frame = tb_ring_poll(net->rx_ring.ring);
+		if (!frame)
+			break;
+
+		dma_unmap_page(dma_dev, frame->buffer_phy,
+			       TBNET_RX_PAGE_SIZE, DMA_FROM_DEVICE);
+
+		tf = container_of(frame, typeof(*tf), frame);
+
+		page = tf->page;
+		tf->page = NULL;
+		net->rx_ring.cons++;
+		cleaned_count++;
+
+		hdr = page_address(page);
+		if (!tbnet_check_frame(net, tf, hdr)) {
+			__free_pages(page, TBNET_RX_PAGE_ORDER);
+			dev_kfree_skb_any(net->skb);
+			net->skb = NULL;
+			continue;
+		}
+
+		frame_size = le32_to_cpu(hdr->frame_size);
+
+		skb = net->skb;
+		if (!skb) {
+			skb = build_skb(page_address(page),
+					TBNET_RX_PAGE_SIZE);
+			if (!skb) {
+				__free_pages(page, TBNET_RX_PAGE_ORDER);
+				net->stats.rx_errors++;
+				break;
+			}
+
+			skb_reserve(skb, hdr_size);
+			skb_put(skb, frame_size);
+
+			net->skb = skb;
+		} else {
+			skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+					page, hdr_size, frame_size,
+					TBNET_RX_PAGE_SIZE - hdr_size);
+		}
+
+		net->rx_hdr.frame_size = frame_size;
+		net->rx_hdr.frame_count = le32_to_cpu(hdr->frame_count);
+		net->rx_hdr.frame_index = le16_to_cpu(hdr->frame_index);
+		net->rx_hdr.frame_id = le16_to_cpu(hdr->frame_id);
+		last = net->rx_hdr.frame_index == net->rx_hdr.frame_count - 1;
+
+		rx_packets++;
+		net->stats.rx_bytes += frame_size;
+
+		if (last) {
+			skb->protocol = eth_type_trans(skb, net->dev);
+			napi_gro_receive(&net->napi, skb);
+			net->skb = NULL;
+		}
+	}
+
+	net->stats.rx_packets += rx_packets;
+
+	if (cleaned_count)
+		tbnet_alloc_rx_buffers(net, cleaned_count);
+
+	if (rx_packets >= budget)
+		return budget;
+
+	napi_complete_done(napi, rx_packets);
+	/* Re-enable the ring interrupt */
+	tb_ring_poll_complete(net->rx_ring.ring);
+
+	return rx_packets;
+}
+
+static void tbnet_start_poll(void *data)
+{
+	struct tbnet *net = data;
+
+	napi_schedule(&net->napi);
+}
+
+static int tbnet_open(struct net_device *dev)
+{
+	struct tbnet *net = netdev_priv(dev);
+	struct tb_xdomain *xd = net->xd;
+	u16 sof_mask, eof_mask;
+	struct tb_ring *ring;
+
+	netif_carrier_off(dev);
+
+	ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE,
+				RING_FLAG_FRAME);
+	if (!ring) {
+		netdev_err(dev, "failed to allocate Tx ring\n");
+		return -ENOMEM;
+	}
+	net->tx_ring.ring = ring;
+
+	sof_mask = BIT(TBIP_PDF_FRAME_START);
+	eof_mask = BIT(TBIP_PDF_FRAME_END);
+
+	ring = tb_ring_alloc_rx(xd->tb->nhi, -1, TBNET_RING_SIZE,
+				RING_FLAG_FRAME | RING_FLAG_E2E, sof_mask,
+				eof_mask, tbnet_start_poll, net);
+	if (!ring) {
+		netdev_err(dev, "failed to allocate Rx ring\n");
+		tb_ring_free(net->tx_ring.ring);
+		net->tx_ring.ring = NULL;
+		return -ENOMEM;
+	}
+	net->rx_ring.ring = ring;
+
+	napi_enable(&net->napi);
+	start_login(net);
+
+	return 0;
+}
+
+static int tbnet_stop(struct net_device *dev)
+{
+	struct tbnet *net = netdev_priv(dev);
+
+	napi_disable(&net->napi);
+
+	tbnet_tear_down(net, true);
+
+	tb_ring_free(net->rx_ring.ring);
+	net->rx_ring.ring = NULL;
+	tb_ring_free(net->tx_ring.ring);
+	net->tx_ring.ring = NULL;
+
+	return 0;
+}
+
+static bool tbnet_xmit_map(struct device *dma_dev, struct tbnet_frame *tf)
+{
+	dma_addr_t dma_addr;
+
+	dma_addr = dma_map_page(dma_dev, tf->page, 0, tbnet_frame_size(tf),
+				DMA_TO_DEVICE);
+	if (dma_mapping_error(dma_dev, dma_addr))
+		return false;
+
+	tf->frame.buffer_phy = dma_addr;
+	return true;
+}
+
+static bool tbnet_xmit_csum_and_map(struct tbnet *net, struct sk_buff *skb,
+	struct tbnet_frame **frames, u32 frame_count)
+{
+	struct thunderbolt_ip_frame_header *hdr = page_address(frames[0]->page);
+	struct device *dma_dev = tb_ring_dma_device(net->tx_ring.ring);
+	__wsum wsum = htonl(skb->len - skb_transport_offset(skb));
+	unsigned int i, len, offset = skb_transport_offset(skb);
+	__be16 protocol = skb->protocol;
+	void *data = skb->data;
+	void *dest = hdr + 1;
+	__sum16 *tucso;
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		/* No need to calculate checksum so we just update the
+		 * total frame count and map the frames for DMA.
+		 */
+		for (i = 0; i < frame_count; i++) {
+			hdr = page_address(frames[i]->page);
+			hdr->frame_count = cpu_to_le32(frame_count);
+			if (!tbnet_xmit_map(dma_dev, frames[i]))
+				goto err_unmap;
+		}
+
+		return true;
+	}
+
+	if (protocol == htons(ETH_P_8021Q)) {
+		struct vlan_hdr *vhdr, vh;
+
+		vhdr = skb_header_pointer(skb, ETH_HLEN, sizeof(vh), &vh);
+		if (!vhdr)
+			return false;
+
+		protocol = vhdr->h_vlan_encapsulated_proto;
+	}
+
+	/* Data points on the beginning of packet.
+	 * Check is the checksum absolute place in the packet.
+	 * ipcso will update IP checksum.
+	 * tucso will update TCP/UPD checksum.
+	 */
+	if (protocol == htons(ETH_P_IP)) {
+		__sum16 *ipcso = dest + ((void *)&(ip_hdr(skb)->check) - data);
+
+		*ipcso = 0;
+		*ipcso = ip_fast_csum(dest + skb_network_offset(skb),
+				      ip_hdr(skb)->ihl);
+
+		if (ip_hdr(skb)->protocol == IPPROTO_TCP)
+			tucso = dest + ((void *)&(tcp_hdr(skb)->check) - data);
+		else if (ip_hdr(skb)->protocol == IPPROTO_UDP)
+			tucso = dest + ((void *)&(udp_hdr(skb)->check) - data);
+		else
+			return false;
+
+		*tucso = ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+					    ip_hdr(skb)->daddr, 0,
+					    ip_hdr(skb)->protocol, 0);
+	} else if (skb_is_gso_v6(skb)) {
+		tucso = dest + ((void *)&(tcp_hdr(skb)->check) - data);
+		*tucso = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+					  &ipv6_hdr(skb)->daddr, 0,
+					  IPPROTO_TCP, 0);
+		return false;
+	} else if (protocol == htons(ETH_P_IPV6)) {
+		tucso = dest + skb_checksum_start_offset(skb) + skb->csum_offset;
+		*tucso = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+					  &ipv6_hdr(skb)->daddr, 0,
+					  ipv6_hdr(skb)->nexthdr, 0);
+	} else {
+		return false;
+	}
+
+	/* First frame was headers, rest of the frames contain data.
+	 * Calculate checksum over each frame.
+	 */
+	for (i = 0; i < frame_count; i++) {
+		hdr = page_address(frames[i]->page);
+		dest = (void *)(hdr + 1) + offset;
+		len = le32_to_cpu(hdr->frame_size) - offset;
+		wsum = csum_partial(dest, len, wsum);
+		hdr->frame_count = cpu_to_le32(frame_count);
+
+		offset = 0;
+	}
+
+	*tucso = csum_fold(wsum);
+
+	/* Checksum is finally calculated and we don't touch the memory
+	 * anymore, so DMA map the frames now.
+	 */
+	for (i = 0; i < frame_count; i++) {
+		if (!tbnet_xmit_map(dma_dev, frames[i]))
+			goto err_unmap;
+	}
+
+	return true;
+
+err_unmap:
+	while (i--)
+		dma_unmap_page(dma_dev, frames[i]->frame.buffer_phy,
+			       tbnet_frame_size(frames[i]), DMA_TO_DEVICE);
+
+	return false;
+}
+
+static void *tbnet_kmap_frag(struct sk_buff *skb, unsigned int frag_num,
+			     unsigned int *len)
+{
+	const skb_frag_t *frag = &skb_shinfo(skb)->frags[frag_num];
+
+	*len = skb_frag_size(frag);
+	return kmap_atomic(skb_frag_page(frag)) + frag->page_offset;
+}
+
+static netdev_tx_t tbnet_start_xmit(struct sk_buff *skb,
+				    struct net_device *dev)
+{
+	struct tbnet *net = netdev_priv(dev);
+	struct tbnet_frame *frames[MAX_SKB_FRAGS];
+	u16 frame_id = atomic_read(&net->frame_id);
+	struct thunderbolt_ip_frame_header *hdr;
+	unsigned int len = skb_headlen(skb);
+	unsigned int data_len = skb->len;
+	unsigned int nframes, i;
+	unsigned int frag = 0;
+	void *src = skb->data;
+	u32 frame_index = 0;
+	bool unmap = false;
+	void *dest;
+
+	nframes = DIV_ROUND_UP(data_len, TBNET_MAX_PAYLOAD_SIZE);
+	if (tbnet_available_buffers(&net->tx_ring) < nframes) {
+		netif_stop_queue(net->dev);
+		return NETDEV_TX_BUSY;
+	}
+
+	frames[frame_index] = tbnet_get_tx_buffer(net);
+	if (!frames[frame_index])
+		goto err_drop;
+
+	hdr = page_address(frames[frame_index]->page);
+	dest = hdr + 1;
+
+	/* If overall packet is bigger than the frame data size */
+	while (data_len > TBNET_MAX_PAYLOAD_SIZE) {
+		unsigned int size_left = TBNET_MAX_PAYLOAD_SIZE;
+
+		hdr->frame_size = cpu_to_le32(TBNET_MAX_PAYLOAD_SIZE);
+		hdr->frame_index = cpu_to_le16(frame_index);
+		hdr->frame_id = cpu_to_le16(frame_id);
+
+		do {
+			if (len > size_left) {
+				/* Copy data onto Tx buffer data with
+				 * full frame size then break and go to
+				 * next frame
+				 */
+				memcpy(dest, src, size_left);
+				len -= size_left;
+				dest += size_left;
+				src += size_left;
+				break;
+			}
+
+			memcpy(dest, src, len);
+			size_left -= len;
+			dest += len;
+
+			if (unmap) {
+				kunmap_atomic(src);
+				unmap = false;
+			}
+
+			/* Ensure all fragments have been processed */
+			if (frag < skb_shinfo(skb)->nr_frags) {
+				/* Map and then unmap quickly */
+				src = tbnet_kmap_frag(skb, frag++, &len);
+				unmap = true;
+			} else if (unlikely(size_left > 0)) {
+				goto err_drop;
+			}
+		} while (size_left > 0);
+
+		data_len -= TBNET_MAX_PAYLOAD_SIZE;
+		frame_index++;
+
+		frames[frame_index] = tbnet_get_tx_buffer(net);
+		if (!frames[frame_index])
+			goto err_drop;
+
+		hdr = page_address(frames[frame_index]->page);
+		dest = hdr + 1;
+	}
+
+	hdr->frame_size = cpu_to_le32(data_len);
+	hdr->frame_index = cpu_to_le16(frame_index);
+	hdr->frame_id = cpu_to_le16(frame_id);
+
+	frames[frame_index]->frame.size = data_len + sizeof(*hdr);
+
+	/* In case the remaining data_len is smaller than a frame */
+	while (len < data_len) {
+		memcpy(dest, src, len);
+		data_len -= len;
+		dest += len;
+
+		if (unmap) {
+			kunmap_atomic(src);
+			unmap = false;
+		}
+
+		if (frag < skb_shinfo(skb)->nr_frags) {
+			src = tbnet_kmap_frag(skb, frag++, &len);
+			unmap = true;
+		} else if (unlikely(data_len > 0)) {
+			goto err_drop;
+		}
+	}
+
+	memcpy(dest, src, data_len);
+
+	if (unmap)
+		kunmap_atomic(src);
+
+	if (!tbnet_xmit_csum_and_map(net, skb, frames, frame_index + 1))
+		goto err_drop;
+
+	for (i = 0; i < frame_index + 1; i++)
+		tb_ring_tx(net->tx_ring.ring, &frames[i]->frame);
+
+	if (net->svc->prtcstns & TBNET_MATCH_FRAGS_ID)
+		atomic_inc(&net->frame_id);
+
+	net->stats.tx_packets++;
+	net->stats.tx_bytes += skb->len;
+
+	dev_consume_skb_any(skb);
+
+	return NETDEV_TX_OK;
+
+err_drop:
+	/* We can re-use the buffers */
+	net->tx_ring.cons -= frame_index;
+
+	dev_kfree_skb_any(skb);
+	net->stats.tx_errors++;
+
+	return NETDEV_TX_OK;
+}
+
+static void tbnet_get_stats64(struct net_device *dev,
+			      struct rtnl_link_stats64 *stats)
+{
+	struct tbnet *net = netdev_priv(dev);
+
+	stats->tx_packets = net->stats.tx_packets;
+	stats->rx_packets = net->stats.rx_packets;
+	stats->tx_bytes = net->stats.tx_bytes;
+	stats->rx_bytes = net->stats.rx_bytes;
+	stats->rx_errors = net->stats.rx_errors + net->stats.rx_length_errors +
+		net->stats.rx_over_errors + net->stats.rx_crc_errors +
+		net->stats.rx_missed_errors;
+	stats->tx_errors = net->stats.tx_errors;
+	stats->rx_length_errors = net->stats.rx_length_errors;
+	stats->rx_over_errors = net->stats.rx_over_errors;
+	stats->rx_crc_errors = net->stats.rx_crc_errors;
+	stats->rx_missed_errors = net->stats.rx_missed_errors;
+}
+
+static const struct net_device_ops tbnet_netdev_ops = {
+	.ndo_open = tbnet_open,
+	.ndo_stop = tbnet_stop,
+	.ndo_start_xmit = tbnet_start_xmit,
+	.ndo_get_stats64 = tbnet_get_stats64,
+};
+
+static void tbnet_generate_mac(struct net_device *dev)
+{
+	const struct tbnet *net = netdev_priv(dev);
+	const struct tb_xdomain *xd = net->xd;
+	u8 phy_port;
+	u32 hash;
+
+	phy_port = tb_phy_port_from_link(TBNET_L0_PORT_NUM(xd->route));
+
+	/* Unicast and locally administered MAC */
+	dev->dev_addr[0] = phy_port << 4 | 0x02;
+	hash = jhash2((u32 *)xd->local_uuid, 4, 0);
+	memcpy(dev->dev_addr + 1, &hash, sizeof(hash));
+	hash = jhash2((u32 *)xd->local_uuid, 4, hash);
+	dev->dev_addr[5] = hash & 0xff;
+}
+
+static int tbnet_probe(struct tb_service *svc, const struct tb_service_id *id)
+{
+	struct tb_xdomain *xd = tb_service_parent(svc);
+	struct net_device *dev;
+	struct tbnet *net;
+	int ret;
+
+	dev = alloc_etherdev(sizeof(*net));
+	if (!dev)
+		return -ENOMEM;
+
+	SET_NETDEV_DEV(dev, &svc->dev);
+
+	net = netdev_priv(dev);
+	INIT_DELAYED_WORK(&net->login_work, tbnet_login_work);
+	INIT_WORK(&net->connected_work, tbnet_connected_work);
+	mutex_init(&net->connection_lock);
+	atomic_set(&net->command_id, 0);
+	atomic_set(&net->frame_id, 0);
+	net->svc = svc;
+	net->dev = dev;
+	net->xd = xd;
+
+	tbnet_generate_mac(dev);
+
+	strcpy(dev->name, "thunderbolt%d");
+	dev->netdev_ops = &tbnet_netdev_ops;
+
+	/* ThunderboltIP takes advantage of TSO packets but instead of
+	 * segmenting them we just split the packet into Thunderbolt
+	 * frames (maximum payload size of each frame is 4084 bytes) and
+	 * calculate checksum over the whole packet here.
+	 *
+	 * The receiving side does the opposite if the host OS supports
+	 * LRO, otherwise it needs to split the large packet into MTU
+	 * sized smaller packets.
+	 *
+	 * In order to receive large packets from the networking stack,
+	 * we need to announce support for most of the offloading
+	 * features here.
+	 */
+	dev->hw_features = NETIF_F_SG | NETIF_F_ALL_TSO | NETIF_F_GRO |
+			   NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	dev->features = dev->hw_features | NETIF_F_HIGHDMA;
+	dev->hard_header_len += sizeof(struct thunderbolt_ip_frame_header);
+
+	netif_napi_add(dev, &net->napi, tbnet_poll, NAPI_POLL_WEIGHT);
+
+	/* MTU range: 68 - 65522 */
+	dev->min_mtu = ETH_MIN_MTU;
+	dev->max_mtu = TBNET_MAX_MTU - ETH_HLEN;
+
+	net->handler.uuid = &tbnet_svc_uuid;
+	net->handler.callback = tbnet_handle_packet,
+	net->handler.data = net;
+	tb_register_protocol_handler(&net->handler);
+
+	tb_service_set_drvdata(svc, net);
+
+	ret = register_netdev(dev);
+	if (ret) {
+		tb_unregister_protocol_handler(&net->handler);
+		free_netdev(dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void tbnet_remove(struct tb_service *svc)
+{
+	struct tbnet *net = tb_service_get_drvdata(svc);
+
+	unregister_netdev(net->dev);
+	tb_unregister_protocol_handler(&net->handler);
+	free_netdev(net->dev);
+}
+
+static void tbnet_shutdown(struct tb_service *svc)
+{
+	tbnet_tear_down(tb_service_get_drvdata(svc), true);
+}
+
+static int __maybe_unused tbnet_suspend(struct device *dev)
+{
+	struct tb_service *svc = tb_to_service(dev);
+	struct tbnet *net = tb_service_get_drvdata(svc);
+
+	stop_login(net);
+	if (netif_running(net->dev)) {
+		netif_device_detach(net->dev);
+		tb_ring_stop(net->rx_ring.ring);
+		tb_ring_stop(net->tx_ring.ring);
+		tbnet_free_buffers(&net->rx_ring);
+		tbnet_free_buffers(&net->tx_ring);
+	}
+
+	return 0;
+}
+
+static int __maybe_unused tbnet_resume(struct device *dev)
+{
+	struct tb_service *svc = tb_to_service(dev);
+	struct tbnet *net = tb_service_get_drvdata(svc);
+
+	netif_carrier_off(net->dev);
+	if (netif_running(net->dev)) {
+		netif_device_attach(net->dev);
+		start_login(net);
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops tbnet_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(tbnet_suspend, tbnet_resume)
+};
+
+static const struct tb_service_id tbnet_ids[] = {
+	{ TB_SERVICE("network", 1) },
+	{ },
+};
+MODULE_DEVICE_TABLE(tbsvc, tbnet_ids);
+
+static struct tb_service_driver tbnet_driver = {
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "thunderbolt-net",
+		.pm = &tbnet_pm_ops,
+	},
+	.probe = tbnet_probe,
+	.remove = tbnet_remove,
+	.shutdown = tbnet_shutdown,
+	.id_table = tbnet_ids,
+};
+
+static int __init tbnet_init(void)
+{
+	int ret;
+
+	tbnet_dir = tb_property_create_dir(&tbnet_dir_uuid);
+	if (!tbnet_dir)
+		return -ENOMEM;
+
+	tb_property_add_immediate(tbnet_dir, "prtcid", 1);
+	tb_property_add_immediate(tbnet_dir, "prtcvers", 1);
+	tb_property_add_immediate(tbnet_dir, "prtcrevs", 1);
+	tb_property_add_immediate(tbnet_dir, "prtcstns",
+				  TBNET_MATCH_FRAGS_ID);
+
+	ret = tb_register_property_dir("network", tbnet_dir);
+	if (ret) {
+		tb_property_free_dir(tbnet_dir);
+		return ret;
+	}
+
+	return tb_register_service_driver(&tbnet_driver);
+}
+module_init(tbnet_init);
+
+static void __exit tbnet_exit(void)
+{
+	tb_unregister_service_driver(&tbnet_driver);
+	tb_unregister_property_dir("network", tbnet_dir);
+	tb_property_free_dir(tbnet_dir);
+}
+module_exit(tbnet_exit);
+
+MODULE_AUTHOR("Amir Levy <amir.jer.levy@intel.com>");
+MODULE_AUTHOR("Michael Jamet <michael.jamet@intel.com>");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_DESCRIPTION("Thunderbolt network driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 42bb820a56c9..8125956f62a1 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -75,6 +75,7 @@
 #include <linux/skb_array.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
+#include <linux/mutex.h>
 
 #include <linux/uaccess.h>
 
@@ -121,7 +122,8 @@ do {								\
 #define TUN_VNET_BE     0x40000000
 
 #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
-		      IFF_MULTI_QUEUE)
+		      IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS)
+
 #define GOODCOPY_LEN 128
 
 #define FLT_EXACT_COUNT 8
@@ -172,6 +174,9 @@ struct tun_file {
 		u16 queue_index;
 		unsigned int ifindex;
 	};
+	struct napi_struct napi;
+	bool napi_enabled;
+	struct mutex napi_mutex;	/* Protects access to the above napi */
 	struct list_head next;
 	struct tun_struct *detached;
 	struct skb_array tx_array;
@@ -229,6 +234,75 @@ struct tun_struct {
 	struct bpf_prog __rcu *xdp_prog;
 };
 
+static int tun_napi_receive(struct napi_struct *napi, int budget)
+{
+	struct tun_file *tfile = container_of(napi, struct tun_file, napi);
+	struct sk_buff_head *queue = &tfile->sk.sk_write_queue;
+	struct sk_buff_head process_queue;
+	struct sk_buff *skb;
+	int received = 0;
+
+	__skb_queue_head_init(&process_queue);
+
+	spin_lock(&queue->lock);
+	skb_queue_splice_tail_init(queue, &process_queue);
+	spin_unlock(&queue->lock);
+
+	while (received < budget && (skb = __skb_dequeue(&process_queue))) {
+		napi_gro_receive(napi, skb);
+		++received;
+	}
+
+	if (!skb_queue_empty(&process_queue)) {
+		spin_lock(&queue->lock);
+		skb_queue_splice(&process_queue, queue);
+		spin_unlock(&queue->lock);
+	}
+
+	return received;
+}
+
+static int tun_napi_poll(struct napi_struct *napi, int budget)
+{
+	unsigned int received;
+
+	received = tun_napi_receive(napi, budget);
+
+	if (received < budget)
+		napi_complete_done(napi, received);
+
+	return received;
+}
+
+static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile,
+			  bool napi_en)
+{
+	tfile->napi_enabled = napi_en;
+	if (napi_en) {
+		netif_napi_add(tun->dev, &tfile->napi, tun_napi_poll,
+			       NAPI_POLL_WEIGHT);
+		napi_enable(&tfile->napi);
+		mutex_init(&tfile->napi_mutex);
+	}
+}
+
+static void tun_napi_disable(struct tun_struct *tun, struct tun_file *tfile)
+{
+	if (tfile->napi_enabled)
+		napi_disable(&tfile->napi);
+}
+
+static void tun_napi_del(struct tun_struct *tun, struct tun_file *tfile)
+{
+	if (tfile->napi_enabled)
+		netif_napi_del(&tfile->napi);
+}
+
+static bool tun_napi_frags_enabled(const struct tun_struct *tun)
+{
+	return READ_ONCE(tun->flags) & IFF_NAPI_FRAGS;
+}
+
 #ifdef CONFIG_TUN_VNET_CROSS_LE
 static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
 {
@@ -380,25 +454,28 @@ static void tun_flow_cleanup(unsigned long data)
 
 	tun_debug(KERN_INFO, tun, "tun_flow_cleanup\n");
 
-	spin_lock_bh(&tun->lock);
+	spin_lock(&tun->lock);
 	for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) {
 		struct tun_flow_entry *e;
 		struct hlist_node *n;
 
 		hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) {
 			unsigned long this_timer;
-			count++;
+
 			this_timer = e->updated + delay;
-			if (time_before_eq(this_timer, jiffies))
+			if (time_before_eq(this_timer, jiffies)) {
 				tun_flow_delete(tun, e);
-			else if (time_before(this_timer, next_timer))
+				continue;
+			}
+			count++;
+			if (time_before(this_timer, next_timer))
 				next_timer = this_timer;
 		}
 	}
 
 	if (count)
 		mod_timer(&tun->flow_gc_timer, round_jiffies_up(next_timer));
-	spin_unlock_bh(&tun->lock);
+	spin_unlock(&tun->lock);
 }
 
 static void tun_flow_update(struct tun_struct *tun, u32 rxhash,
@@ -541,6 +618,11 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 
 	tun = rtnl_dereference(tfile->tun);
 
+	if (tun && clean) {
+		tun_napi_disable(tun, tfile);
+		tun_napi_del(tun, tfile);
+	}
+
 	if (tun && !tfile->detached) {
 		u16 index = tfile->queue_index;
 		BUG_ON(index >= tun->numqueues);
@@ -598,6 +680,7 @@ static void tun_detach_all(struct net_device *dev)
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
 		BUG_ON(!tfile);
+		tun_napi_disable(tun, tfile);
 		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
@@ -613,6 +696,7 @@ static void tun_detach_all(struct net_device *dev)
 	synchronize_net();
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
+		tun_napi_del(tun, tfile);
 		/* Drop read queue */
 		tun_queue_purge(tfile);
 		sock_put(&tfile->sk);
@@ -631,7 +715,8 @@ static void tun_detach_all(struct net_device *dev)
 		module_put(THIS_MODULE);
 }
 
-static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter)
+static int tun_attach(struct tun_struct *tun, struct file *file,
+		      bool skip_filter, bool napi)
 {
 	struct tun_file *tfile = file->private_data;
 	struct net_device *dev = tun->dev;
@@ -677,10 +762,12 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
 	tun->numqueues++;
 
-	if (tfile->detached)
+	if (tfile->detached) {
 		tun_enable_queue(tfile);
-	else
+	} else {
 		sock_hold(&tfile->sk);
+		tun_napi_init(tun, tfile, napi);
+	}
 
 	tun_set_real_num_queues(tun);
 
@@ -692,7 +779,7 @@ out:
 	return err;
 }
 
-static struct tun_struct *__tun_get(struct tun_file *tfile)
+static struct tun_struct *tun_get(struct tun_file *tfile)
 {
 	struct tun_struct *tun;
 
@@ -705,11 +792,6 @@ static struct tun_struct *__tun_get(struct tun_file *tfile)
 	return tun;
 }
 
-static struct tun_struct *tun_get(struct file *file)
-{
-	return __tun_get(file->private_data);
-}
-
 static void tun_put(struct tun_struct *tun)
 {
 	dev_put(tun->dev);
@@ -956,13 +1038,33 @@ static void tun_poll_controller(struct net_device *dev)
 	 * Tun only receives frames when:
 	 * 1) the char device endpoint gets data from user space
 	 * 2) the tun socket gets a sendmsg call from user space
-	 * Since both of those are synchronous operations, we are guaranteed
-	 * never to have pending data when we poll for it
-	 * so there is nothing to do here but return.
+	 * If NAPI is not enabled, since both of those are synchronous
+	 * operations, we are guaranteed never to have pending data when we poll
+	 * for it so there is nothing to do here but return.
 	 * We need this though so netpoll recognizes us as an interface that
 	 * supports polling, which enables bridge devices in virt setups to
 	 * still use netconsole
+	 * If NAPI is enabled, however, we need to schedule polling for all
+	 * queues unless we are using napi_gro_frags(), which we call in
+	 * process context and not in NAPI context.
 	 */
+	struct tun_struct *tun = netdev_priv(dev);
+
+	if (tun->flags & IFF_NAPI) {
+		struct tun_file *tfile;
+		int i;
+
+		if (tun_napi_frags_enabled(tun))
+			return;
+
+		rcu_read_lock();
+		for (i = 0; i < tun->numqueues; i++) {
+			tfile = rcu_dereference(tun->tfiles[i]);
+			if (tfile->napi_enabled)
+				napi_schedule(&tfile->napi);
+		}
+		rcu_read_unlock();
+	}
 	return;
 }
 #endif
@@ -1095,8 +1197,6 @@ static void tun_flow_init(struct tun_struct *tun)
 
 	tun->ageing_time = TUN_FLOW_EXPIRE;
 	setup_timer(&tun->flow_gc_timer, tun_flow_cleanup, (unsigned long)tun);
-	mod_timer(&tun->flow_gc_timer,
-		  round_jiffies_up(jiffies + tun->ageing_time));
 }
 
 static void tun_flow_uninit(struct tun_struct *tun)
@@ -1149,7 +1249,7 @@ static void tun_net_init(struct net_device *dev)
 static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 {
 	struct tun_file *tfile = file->private_data;
-	struct tun_struct *tun = __tun_get(tfile);
+	struct tun_struct *tun = tun_get(tfile);
 	struct sock *sk;
 	unsigned int mask = 0;
 
@@ -1178,6 +1278,64 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 	return mask;
 }
 
+static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile,
+					    size_t len,
+					    const struct iov_iter *it)
+{
+	struct sk_buff *skb;
+	size_t linear;
+	int err;
+	int i;
+
+	if (it->nr_segs > MAX_SKB_FRAGS + 1)
+		return ERR_PTR(-ENOMEM);
+
+	local_bh_disable();
+	skb = napi_get_frags(&tfile->napi);
+	local_bh_enable();
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	linear = iov_iter_single_seg_count(it);
+	err = __skb_grow(skb, linear);
+	if (err)
+		goto free;
+
+	skb->len = len;
+	skb->data_len = len - linear;
+	skb->truesize += skb->data_len;
+
+	for (i = 1; i < it->nr_segs; i++) {
+		size_t fragsz = it->iov[i].iov_len;
+		unsigned long offset;
+		struct page *page;
+		void *data;
+
+		if (fragsz == 0 || fragsz > PAGE_SIZE) {
+			err = -EINVAL;
+			goto free;
+		}
+
+		local_bh_disable();
+		data = napi_alloc_frag(fragsz);
+		local_bh_enable();
+		if (!data) {
+			err = -ENOMEM;
+			goto free;
+		}
+
+		page = virt_to_head_page(data);
+		offset = data - page_address(page);
+		skb_fill_page_desc(skb, i - 1, page, offset, fragsz);
+	}
+
+	return skb;
+free:
+	/* frees skb and all frags allocated with napi_alloc_frag() */
+	napi_free_frags(&tfile->napi);
+	return ERR_PTR(err);
+}
+
 /* prepad is the amount to reserve at front.  len is length after that.
  * linear is a hint as to how much to copy (usually headers). */
 static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
@@ -1315,6 +1473,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 
 		xdp.data_hard_start = buf;
 		xdp.data = buf + pad;
+		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + len;
 		orig_data = xdp.data;
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -1391,6 +1550,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	int err;
 	u32 rxhash;
 	int skb_xdp = 1;
+	bool frags = tun_napi_frags_enabled(tun);
 
 	if (!(tun->dev->flags & IFF_UP))
 		return -EIO;
@@ -1448,7 +1608,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			zerocopy = true;
 	}
 
-	if (tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) {
+	if (!frags && tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) {
 		/* For the packet that is not easy to be processed
 		 * (e.g gso or jumbo packet), we will do it at after
 		 * skb was created with generic XDP routine.
@@ -1469,10 +1629,24 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 				linear = tun16_to_cpu(tun, gso.hdr_len);
 		}
 
-		skb = tun_alloc_skb(tfile, align, copylen, linear, noblock);
+		if (frags) {
+			mutex_lock(&tfile->napi_mutex);
+			skb = tun_napi_alloc_frags(tfile, copylen, from);
+			/* tun_napi_alloc_frags() enforces a layout for the skb.
+			 * If zerocopy is enabled, then this layout will be
+			 * overwritten by zerocopy_sg_from_iter().
+			 */
+			zerocopy = false;
+		} else {
+			skb = tun_alloc_skb(tfile, align, copylen, linear,
+					    noblock);
+		}
+
 		if (IS_ERR(skb)) {
 			if (PTR_ERR(skb) != -EAGAIN)
 				this_cpu_inc(tun->pcpu_stats->rx_dropped);
+			if (frags)
+				mutex_unlock(&tfile->napi_mutex);
 			return PTR_ERR(skb);
 		}
 
@@ -1484,6 +1658,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		if (err) {
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);
 			kfree_skb(skb);
+			if (frags) {
+				tfile->napi.skb = NULL;
+				mutex_unlock(&tfile->napi_mutex);
+			}
+
 			return -EFAULT;
 		}
 	}
@@ -1491,6 +1670,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	if (virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun))) {
 		this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
 		kfree_skb(skb);
+		if (frags) {
+			tfile->napi.skb = NULL;
+			mutex_unlock(&tfile->napi_mutex);
+		}
+
 		return -EINVAL;
 	}
 
@@ -1518,7 +1702,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		skb->dev = tun->dev;
 		break;
 	case IFF_TAP:
-		skb->protocol = eth_type_trans(skb, tun->dev);
+		if (!frags)
+			skb->protocol = eth_type_trans(skb, tun->dev);
 		break;
 	}
 
@@ -1552,11 +1737,41 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	}
 
 	rxhash = __skb_get_hash_symmetric(skb);
-#ifndef CONFIG_4KSTACKS
-	tun_rx_batched(tun, tfile, skb, more);
-#else
-	netif_rx_ni(skb);
-#endif
+
+	if (frags) {
+		/* Exercise flow dissector code path. */
+		u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb));
+
+		if (unlikely(headlen > skb_headlen(skb))) {
+			this_cpu_inc(tun->pcpu_stats->rx_dropped);
+			napi_free_frags(&tfile->napi);
+			mutex_unlock(&tfile->napi_mutex);
+			WARN_ON(1);
+			return -ENOMEM;
+		}
+
+		local_bh_disable();
+		napi_gro_frags(&tfile->napi);
+		local_bh_enable();
+		mutex_unlock(&tfile->napi_mutex);
+	} else if (tfile->napi_enabled) {
+		struct sk_buff_head *queue = &tfile->sk.sk_write_queue;
+		int queue_len;
+
+		spin_lock_bh(&queue->lock);
+		__skb_queue_tail(queue, skb);
+		queue_len = skb_queue_len(queue);
+		spin_unlock(&queue->lock);
+
+		if (!more || queue_len > NAPI_POLL_WEIGHT)
+			napi_schedule(&tfile->napi);
+
+		local_bh_enable();
+	} else if (!IS_ENABLED(CONFIG_4KSTACKS)) {
+		tun_rx_batched(tun, tfile, skb, more);
+	} else {
+		netif_rx_ni(skb);
+	}
 
 	stats = get_cpu_ptr(tun->pcpu_stats);
 	u64_stats_update_begin(&stats->syncp);
@@ -1572,8 +1787,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct tun_struct *tun = tun_get(file);
 	struct tun_file *tfile = file->private_data;
+	struct tun_struct *tun = tun_get(tfile);
 	ssize_t result;
 
 	if (!tun)
@@ -1757,7 +1972,7 @@ static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
 	struct tun_file *tfile = file->private_data;
-	struct tun_struct *tun = __tun_get(tfile);
+	struct tun_struct *tun = tun_get(tfile);
 	ssize_t len = iov_iter_count(to), ret;
 
 	if (!tun)
@@ -1834,7 +2049,7 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 {
 	int ret;
 	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
-	struct tun_struct *tun = __tun_get(tfile);
+	struct tun_struct *tun = tun_get(tfile);
 
 	if (!tun)
 		return -EBADFD;
@@ -1850,7 +2065,7 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len,
 		       int flags)
 {
 	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
-	struct tun_struct *tun = __tun_get(tfile);
+	struct tun_struct *tun = tun_get(tfile);
 	int ret;
 
 	if (!tun)
@@ -1882,7 +2097,7 @@ static int tun_peek_len(struct socket *sock)
 	struct tun_struct *tun;
 	int ret = 0;
 
-	tun = __tun_get(tfile);
+	tun = tun_get(tfile);
 	if (!tun)
 		return 0;
 
@@ -1962,6 +2177,15 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 	if (tfile->detached)
 		return -EINVAL;
 
+	if ((ifr->ifr_flags & IFF_NAPI_FRAGS)) {
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+
+		if (!(ifr->ifr_flags & IFF_NAPI) ||
+		    (ifr->ifr_flags & TUN_TYPE_MASK) != IFF_TAP)
+			return -EINVAL;
+	}
+
 	dev = __dev_get_by_name(net, ifr->ifr_name);
 	if (dev) {
 		if (ifr->ifr_flags & IFF_TUN_EXCL)
@@ -1983,7 +2207,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		if (err < 0)
 			return err;
 
-		err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER);
+		err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER,
+				 ifr->ifr_flags & IFF_NAPI);
 		if (err < 0)
 			return err;
 
@@ -2072,7 +2297,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 				       NETIF_F_HW_VLAN_STAG_TX);
 
 		INIT_LIST_HEAD(&tun->disabled);
-		err = tun_attach(tun, file, false);
+		err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI);
 		if (err < 0)
 			goto err_free_flow;
 
@@ -2222,7 +2447,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
 		ret = security_tun_dev_attach_queue(tun->security);
 		if (ret < 0)
 			goto unlock;
-		ret = tun_attach(tun, file, false);
+		ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI);
 	} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
 		tun = rtnl_dereference(tfile->tun);
 		if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached)
@@ -2271,7 +2496,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	ret = 0;
 	rtnl_lock();
 
-	tun = __tun_get(tfile);
+	tun = tun_get(tfile);
 	if (cmd == TUNSETIFF) {
 		ret = -EEXIST;
 		if (tun)
@@ -2622,15 +2847,16 @@ static int tun_chr_close(struct inode *inode, struct file *file)
 }
 
 #ifdef CONFIG_PROC_FS
-static void tun_chr_show_fdinfo(struct seq_file *m, struct file *f)
+static void tun_chr_show_fdinfo(struct seq_file *m, struct file *file)
 {
+	struct tun_file *tfile = file->private_data;
 	struct tun_struct *tun;
 	struct ifreq ifr;
 
 	memset(&ifr, 0, sizeof(ifr));
 
 	rtnl_lock();
-	tun = tun_get(f);
+	tun = tun_get(tfile);
 	if (tun)
 		tun_get_iff(current->nsproxy->net_ns, tun, &ifr);
 	rtnl_unlock();
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index 522d2900cd1d..f4d7362eb325 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -245,7 +245,7 @@ struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 	 * - We are allowed to put 4 bytes at tail if skb_cloned()
 	 *   is false (and if we have 4 bytes of tailroom)
 	 *
-	 * TCP packets for example are cloned, but skb_header_release()
+	 * TCP packets for example are cloned, but __skb_header_release()
 	 * was called in tcp stack, allowing us to use headroom for our needs.
 	 */
 	if (!skb_header_cloned(skb) &&
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index dbc90313f472..18d36dff97ea 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -611,9 +611,9 @@ static void catc_stats_done(struct catc *catc, struct ctrl_queue *q)
 	catc->stats_vals[index >> 1] = data;
 }
 
-static void catc_stats_timer(unsigned long data)
+static void catc_stats_timer(struct timer_list *t)
 {
-	struct catc *catc = (void *) data;
+	struct catc *catc = from_timer(catc, t, timer);
 	int i;
 
 	for (i = 0; i < 8; i++)
@@ -805,9 +805,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	spin_lock_init(&catc->tx_lock);
 	spin_lock_init(&catc->ctrl_lock);
 
-	init_timer(&catc->timer);
-	catc->timer.data = (long) catc;
-	catc->timer.function = catc_stats_timer;
+	timer_setup(&catc->timer, catc_stats_timer, 0);
 
 	catc->ctrl_urb = usb_alloc_urb(0, GFP_KERNEL);
 	catc->tx_urb = usb_alloc_urb(0, GFP_KERNEL);
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index d7a3379ea668..42d7edcc3106 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -2263,7 +2263,6 @@ static void hso_serial_common_free(struct hso_serial *serial)
 static int hso_serial_common_create(struct hso_serial *serial, int num_urbs,
 				    int rx_size, int tx_size)
 {
-	struct device *dev;
 	int minor;
 	int i;
 
@@ -2277,7 +2276,6 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs,
 	serial->parent->dev = tty_port_register_device_attr(&serial->port,
 			tty_drv, minor, &serial->parent->interface->dev,
 			serial->parent, hso_serial_dev_groups);
-	dev = serial->parent->dev;
 
 	/* fill in specific data for later use */
 	serial->minor = minor;
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 0161f77641fa..94c7804903c4 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -3516,11 +3516,9 @@ static const struct net_device_ops lan78xx_netdev_ops = {
 	.ndo_vlan_rx_kill_vid	= lan78xx_vlan_rx_kill_vid,
 };
 
-static void lan78xx_stat_monitor(unsigned long param)
+static void lan78xx_stat_monitor(struct timer_list *t)
 {
-	struct lan78xx_net *dev;
-
-	dev = (struct lan78xx_net *)param;
+	struct lan78xx_net *dev = from_timer(dev, t, stat_monitor);
 
 	lan78xx_defer_kevent(dev, EVENT_STAT_UPDATE);
 }
@@ -3571,10 +3569,8 @@ static int lan78xx_probe(struct usb_interface *intf,
 	netdev->watchdog_timeo = TX_TIMEOUT_JIFFIES;
 	netdev->ethtool_ops = &lan78xx_ethtool_ops;
 
-	dev->stat_monitor.function = lan78xx_stat_monitor;
-	dev->stat_monitor.data = (unsigned long)dev;
 	dev->delta = 1;
-	init_timer(&dev->stat_monitor);
+	timer_setup(&dev->stat_monitor, lan78xx_stat_monitor, 0);
 
 	mutex_init(&dev->stats.access_lock);
 
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8c3733608271..db7279d5b250 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -221,7 +221,7 @@ static int qmimux_register_device(struct net_device *real_dev, u8 mux_id)
 	/* Account for reference in struct qmimux_priv_priv */
 	dev_hold(real_dev);
 
-	err = netdev_upper_dev_link(real_dev, new_dev);
+	err = netdev_upper_dev_link(real_dev, new_dev, NULL);
 	if (err)
 		goto out_unregister_netdev;
 
diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c
index 2110ab3513f0..c43087e06696 100644
--- a/drivers/net/usb/sierra_net.c
+++ b/drivers/net/usb/sierra_net.c
@@ -189,9 +189,6 @@ struct lsi_umts_dual {
 #define SIERRA_NET_LSI_UMTS_DS_STATUS_LEN \
 	(SIERRA_NET_LSI_UMTS_DS_LEN - SIERRA_NET_LSI_COMMON_LEN)
 
-/* Forward definitions */
-static void sierra_sync_timer(unsigned long syncdata);
-
 /* Our own net device operations structure */
 static const struct net_device_ops sierra_net_device_ops = {
 	.ndo_open               = usbnet_open,
@@ -475,8 +472,6 @@ static void sierra_net_dosync(struct usbnet *dev)
 			"Send SYNC failed, status %d\n", status);
 
 	/* Now, start a timer and make sure we get the Restart Indication */
-	priv->sync_timer.function = sierra_sync_timer;
-	priv->sync_timer.data = (unsigned long) dev;
 	priv->sync_timer.expires = jiffies + SIERRA_NET_SYNCDELAY;
 	add_timer(&priv->sync_timer);
 }
@@ -593,9 +588,10 @@ static void sierra_net_defer_kevent(struct usbnet *dev, int work)
 /*
  * Sync Retransmit Timer Handler. On expiry, kick the work queue
  */
-static void sierra_sync_timer(unsigned long syncdata)
+static void sierra_sync_timer(struct timer_list *t)
 {
-	struct usbnet *dev = (struct usbnet *)syncdata;
+	struct sierra_net_data *priv = from_timer(priv, t, sync_timer);
+	struct usbnet *dev = priv->usbnet;
 
 	dev_dbg(&dev->udev->dev, "%s", __func__);
 	/* Kick the tasklet */
@@ -752,7 +748,7 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf)
 	INIT_WORK(&priv->sierra_net_kevent, sierra_net_kevent);
 
 	/* Only need to do this once */
-	init_timer(&priv->sync_timer);
+	timer_setup(&priv->sync_timer, sierra_sync_timer, 0);
 
 	/* verify fw attributes */
 	status = sierra_net_get_fw_attr(dev, &fwattr);
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 6510e5cc1817..80348b6a8646 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1509,9 +1509,9 @@ err:
 
 // tasklet (work deferred from completions, in_irq) or timer
 
-static void usbnet_bh (unsigned long param)
+static void usbnet_bh (struct timer_list *t)
 {
-	struct usbnet		*dev = (struct usbnet *) param;
+	struct usbnet		*dev = from_timer(dev, t, delay);
 	struct sk_buff		*skb;
 	struct skb_data		*entry;
 
@@ -1694,13 +1694,11 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 	skb_queue_head_init (&dev->txq);
 	skb_queue_head_init (&dev->done);
 	skb_queue_head_init(&dev->rxq_pause);
-	dev->bh.func = usbnet_bh;
-	dev->bh.data = (unsigned long) dev;
+	dev->bh.func = (void (*)(unsigned long))usbnet_bh;
+	dev->bh.data = (unsigned long)&dev->delay;
 	INIT_WORK (&dev->kevent, usbnet_deferred_kevent);
 	init_usb_anchor(&dev->deferred);
-	dev->delay.function = usbnet_bh;
-	dev->delay.data = (unsigned long) dev;
-	init_timer (&dev->delay);
+	timer_setup(&dev->delay, usbnet_bh, 0);
 	mutex_init (&dev->phy_mutex);
 	mutex_init(&dev->interrupt_mutex);
 	dev->interrupt_count = 0;
diff --git a/drivers/net/virtio_net. b/drivers/net/virtio_net.
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/drivers/net/virtio_net.
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 511f8339fa96..fc059f193e7d 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/average.h>
+#include <linux/filter.h>
 #include <net/route.h>
 
 static int napi_weight = NAPI_POLL_WEIGHT;
@@ -372,9 +373,20 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	return skb;
 }
 
-static bool virtnet_xdp_xmit(struct virtnet_info *vi,
-			     struct receive_queue *rq,
-			     struct xdp_buff *xdp)
+static void virtnet_xdp_flush(struct net_device *dev)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	struct send_queue *sq;
+	unsigned int qp;
+
+	qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
+	sq = &vi->sq[qp];
+
+	virtqueue_kick(sq->vq);
+}
+
+static bool __virtnet_xdp_xmit(struct virtnet_info *vi,
+			       struct xdp_buff *xdp)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
 	unsigned int len;
@@ -408,10 +420,19 @@ static bool virtnet_xdp_xmit(struct virtnet_info *vi,
 		return false;
 	}
 
-	virtqueue_kick(sq->vq);
 	return true;
 }
 
+static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	bool sent = __virtnet_xdp_xmit(vi, xdp);
+
+	if (!sent)
+		return -ENOSPC;
+	return 0;
+}
+
 static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
 {
 	return vi->xdp_queue_pairs ? VIRTIO_XDP_HEADROOM : 0;
@@ -484,7 +505,8 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				     struct virtnet_info *vi,
 				     struct receive_queue *rq,
 				     void *buf, void *ctx,
-				     unsigned int len)
+				     unsigned int len,
+				     bool *xdp_xmit)
 {
 	struct sk_buff *skb;
 	struct bpf_prog *xdp_prog;
@@ -494,7 +516,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	unsigned int buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) +
 			      SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	struct page *page = virt_to_head_page(buf);
-	unsigned int delta = 0;
+	unsigned int delta = 0, err;
 	struct page *xdp_page;
 	len -= vi->hdr_len;
 
@@ -532,6 +554,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 
 		xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len;
 		xdp.data = xdp.data_hard_start + xdp_headroom;
+		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + len;
 		orig_data = xdp.data;
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -542,8 +565,16 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			delta = orig_data - xdp.data;
 			break;
 		case XDP_TX:
-			if (unlikely(!virtnet_xdp_xmit(vi, rq, &xdp)))
+			if (unlikely(!__virtnet_xdp_xmit(vi, &xdp)))
 				trace_xdp_exception(vi->dev, xdp_prog, act);
+			else
+				*xdp_xmit = true;
+			rcu_read_unlock();
+			goto xdp_xmit;
+		case XDP_REDIRECT:
+			err = xdp_do_redirect(dev, &xdp, xdp_prog);
+			if (!err)
+				*xdp_xmit = true;
 			rcu_read_unlock();
 			goto xdp_xmit;
 		default:
@@ -604,7 +635,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 struct receive_queue *rq,
 					 void *buf,
 					 void *ctx,
-					 unsigned int len)
+					 unsigned int len,
+					 bool *xdp_xmit)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
 	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
@@ -614,6 +646,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	struct bpf_prog *xdp_prog;
 	unsigned int truesize;
 	unsigned int headroom = mergeable_ctx_to_headroom(ctx);
+	int err;
 
 	head_skb = NULL;
 
@@ -654,9 +687,13 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		data = page_address(xdp_page) + offset;
 		xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len;
 		xdp.data = data + vi->hdr_len;
+		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + (len - vi->hdr_len);
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
+		if (act != XDP_PASS)
+			ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
+
 		switch (act) {
 		case XDP_PASS:
 			/* recalculate offset to account for any header
@@ -672,18 +709,24 @@ 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);
-				ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
 				return head_skb;
 			}
 			break;
 		case XDP_TX:
-			if (unlikely(!virtnet_xdp_xmit(vi, rq, &xdp)))
+			if (unlikely(!__virtnet_xdp_xmit(vi, &xdp)))
 				trace_xdp_exception(vi->dev, xdp_prog, act);
-			ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
+			else
+				*xdp_xmit = true;
 			if (unlikely(xdp_page != page))
 				goto err_xdp;
 			rcu_read_unlock();
 			goto xdp_xmit;
+		case XDP_REDIRECT:
+			err = xdp_do_redirect(dev, &xdp, xdp_prog);
+			if (!err)
+				*xdp_xmit = true;
+			rcu_read_unlock();
+			goto xdp_xmit;
 		default:
 			bpf_warn_invalid_xdp_action(act);
 		case XDP_ABORTED:
@@ -691,7 +734,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		case XDP_DROP:
 			if (unlikely(xdp_page != page))
 				__free_pages(xdp_page, 0);
-			ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
 			goto err_xdp;
 		}
 	}
@@ -789,7 +831,7 @@ xdp_xmit:
 }
 
 static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
-		       void *buf, unsigned int len, void **ctx)
+		       void *buf, unsigned int len, void **ctx, bool *xdp_xmit)
 {
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
@@ -810,11 +852,11 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 	}
 
 	if (vi->mergeable_rx_bufs)
-		skb = receive_mergeable(dev, vi, rq, buf, ctx, len);
+		skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit);
 	else if (vi->big_packets)
 		skb = receive_big(dev, vi, rq, buf, len);
 	else
-		skb = receive_small(dev, vi, rq, buf, ctx, len);
+		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit);
 
 	if (unlikely(!skb))
 		return 0;
@@ -1072,7 +1114,7 @@ static void refill_work(struct work_struct *work)
 	}
 }
 
-static int virtnet_receive(struct receive_queue *rq, int budget)
+static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
 	unsigned int len, received = 0, bytes = 0;
@@ -1084,13 +1126,13 @@ static int virtnet_receive(struct receive_queue *rq, int budget)
 
 		while (received < budget &&
 		       (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
-			bytes += receive_buf(vi, rq, buf, len, ctx);
+			bytes += receive_buf(vi, rq, buf, len, ctx, xdp_xmit);
 			received++;
 		}
 	} else {
 		while (received < budget &&
 		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
-			bytes += receive_buf(vi, rq, buf, len, NULL);
+			bytes += receive_buf(vi, rq, buf, len, NULL, xdp_xmit);
 			received++;
 		}
 	}
@@ -1162,15 +1204,19 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	struct receive_queue *rq =
 		container_of(napi, struct receive_queue, napi);
 	unsigned int received;
+	bool xdp_xmit = false;
 
 	virtnet_poll_cleantx(rq);
 
-	received = virtnet_receive(rq, budget);
+	received = virtnet_receive(rq, budget, &xdp_xmit);
 
 	/* Out of packets? */
 	if (received < budget)
 		virtqueue_napi_complete(napi, rq->vq, received);
 
+	if (xdp_xmit)
+		xdp_do_flush_map();
+
 	return received;
 }
 
@@ -2070,6 +2116,8 @@ static const struct net_device_ops virtnet_netdev = {
 	.ndo_poll_controller = virtnet_netpoll,
 #endif
 	.ndo_xdp		= virtnet_xdp,
+	.ndo_xdp_xmit		= virtnet_xdp_xmit,
+	.ndo_xdp_flush		= virtnet_xdp_flush,
 	.ndo_features_check	= passthru_features_check,
 };
 
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 7dc3bcac3506..feb1b2e15c2e 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -132,7 +132,6 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev,
 	skb_orphan(skb);
 
 	skb_dst_set(skb, dst);
-	skb_dst_force(skb);
 
 	/* set pkt_type to avoid skb hitting packet taps twice -
 	 * once on Tx and again in Rx processing
@@ -765,18 +764,22 @@ static void cycle_netdev(struct net_device *dev)
 	}
 }
 
-static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
+static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev,
+			    struct netlink_ext_ack *extack)
 {
 	int ret;
 
 	/* do not allow loopback device to be enslaved to a VRF.
 	 * The vrf device acts as the loopback for the vrf.
 	 */
-	if (port_dev == dev_net(dev)->loopback_dev)
+	if (port_dev == dev_net(dev)->loopback_dev) {
+		NL_SET_ERR_MSG(extack,
+			       "Can not enslave loopback device to a VRF");
 		return -EOPNOTSUPP;
+	}
 
 	port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
-	ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL);
+	ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL, extack);
 	if (ret < 0)
 		goto err;
 
@@ -789,12 +792,19 @@ err:
 	return ret;
 }
 
-static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
+static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev,
+			 struct netlink_ext_ack *extack)
 {
-	if (netif_is_l3_master(port_dev) || netif_is_l3_slave(port_dev))
+	if (netif_is_l3_master(port_dev)) {
+		NL_SET_ERR_MSG(extack,
+			       "Can not enslave an L3 master device to a VRF");
+		return -EINVAL;
+	}
+
+	if (netif_is_l3_slave(port_dev))
 		return -EINVAL;
 
-	return do_vrf_add_slave(dev, port_dev);
+	return do_vrf_add_slave(dev, port_dev, extack);
 }
 
 /* inverse of do_vrf_add_slave */
diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c
index a043fb1367bd..c0b0f525c87c 100644
--- a/drivers/net/wan/dscc4.c
+++ b/drivers/net/wan/dscc4.c
@@ -223,8 +223,6 @@ struct dscc4_dev_priv {
 
 	u32 scc_regs[SCC_REGISTERS_MAX]; /* Cf errata DS5 p.4 */
 
-	struct timer_list timer;
-
         struct dscc4_pci_priv *pci_priv;
         spinlock_t lock;
 
@@ -369,7 +367,6 @@ static int dscc4_close(struct net_device *);
 static int dscc4_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
 static int dscc4_init_ring(struct net_device *);
 static void dscc4_release_ring(struct dscc4_dev_priv *);
-static void dscc4_timer(unsigned long);
 static void dscc4_tx_timeout(struct net_device *);
 static irqreturn_t dscc4_irq(int irq, void *dev_id);
 static int dscc4_hdlc_attach(struct net_device *, unsigned short, unsigned short);
@@ -983,19 +980,6 @@ err_out:
 	return ret;
 };
 
-/* FIXME: get rid of the unneeded code */
-static void dscc4_timer(unsigned long data)
-{
-	struct net_device *dev = (struct net_device *)data;
-	struct dscc4_dev_priv *dpriv = dscc4_priv(dev);
-//	struct dscc4_pci_priv *ppriv;
-
-	goto done;
-done:
-        dpriv->timer.expires = jiffies + TX_TIMEOUT;
-        add_timer(&dpriv->timer);
-}
-
 static void dscc4_tx_timeout(struct net_device *dev)
 {
 	/* FIXME: something is missing there */
@@ -1127,11 +1111,6 @@ static int dscc4_open(struct net_device *dev)
 done:
 	netif_start_queue(dev);
 
-        init_timer(&dpriv->timer);
-        dpriv->timer.expires = jiffies + 10*HZ;
-        dpriv->timer.data = (unsigned long)dev;
-	dpriv->timer.function = dscc4_timer;
-        add_timer(&dpriv->timer);
 	netif_carrier_on(dev);
 
 	return 0;
@@ -1199,7 +1178,6 @@ static int dscc4_close(struct net_device *dev)
 {
 	struct dscc4_dev_priv *dpriv = dscc4_priv(dev);
 
-	del_timer_sync(&dpriv->timer);
 	netif_stop_queue(dev);
 
 	scc_patchl(PowerUp | Vis, 0, dpriv, dev, CCR0);
diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c
index a408abc25512..320039d329c7 100644
--- a/drivers/net/wan/hdlc_cisco.c
+++ b/drivers/net/wan/hdlc_cisco.c
@@ -54,6 +54,7 @@ struct cisco_state {
 	cisco_proto settings;
 
 	struct timer_list timer;
+	struct net_device *dev;
 	spinlock_t lock;
 	unsigned long last_poll;
 	int up;
@@ -257,11 +258,10 @@ rx_error:
 
 
 
-static void cisco_timer(unsigned long arg)
+static void cisco_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)arg;
-	hdlc_device *hdlc = dev_to_hdlc(dev);
-	struct cisco_state *st = state(hdlc);
+	struct cisco_state *st = from_timer(st, t, timer);
+	struct net_device *dev = st->dev;
 
 	spin_lock(&st->lock);
 	if (st->up &&
@@ -276,8 +276,6 @@ static void cisco_timer(unsigned long arg)
 	spin_unlock(&st->lock);
 
 	st->timer.expires = jiffies + st->settings.interval * HZ;
-	st->timer.function = cisco_timer;
-	st->timer.data = arg;
 	add_timer(&st->timer);
 }
 
@@ -293,10 +291,9 @@ static void cisco_start(struct net_device *dev)
 	st->up = st->txseq = st->rxseq = 0;
 	spin_unlock_irqrestore(&st->lock, flags);
 
-	init_timer(&st->timer);
+	st->dev = dev;
+	timer_setup(&st->timer, cisco_timer, 0);
 	st->timer.expires = jiffies + HZ; /* First poll after 1 s */
-	st->timer.function = cisco_timer;
-	st->timer.data = (unsigned long)dev;
 	add_timer(&st->timer);
 }
 
diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index 78596e42a3f3..038236a9c60e 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -140,6 +140,7 @@ struct frad_state {
 	int dce_pvc_count;
 
 	struct timer_list timer;
+	struct net_device *dev;
 	unsigned long last_poll;
 	int reliable;
 	int dce_changed;
@@ -597,9 +598,10 @@ static void fr_set_link_state(int reliable, struct net_device *dev)
 }
 
 
-static void fr_timer(unsigned long arg)
+static void fr_timer(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)arg;
+	struct frad_state *st = from_timer(st, t, timer);
+	struct net_device *dev = st->dev;
 	hdlc_device *hdlc = dev_to_hdlc(dev);
 	int i, cnt = 0, reliable;
 	u32 list;
@@ -644,8 +646,6 @@ static void fr_timer(unsigned long arg)
 			state(hdlc)->settings.t391 * HZ;
 	}
 
-	state(hdlc)->timer.function = fr_timer;
-	state(hdlc)->timer.data = arg;
 	add_timer(&state(hdlc)->timer);
 }
 
@@ -1003,11 +1003,10 @@ static void fr_start(struct net_device *dev)
 		state(hdlc)->n391cnt = 0;
 		state(hdlc)->txseq = state(hdlc)->rxseq = 0;
 
-		init_timer(&state(hdlc)->timer);
+		state(hdlc)->dev = dev;
+		timer_setup(&state(hdlc)->timer, fr_timer, 0);
 		/* First poll after 1 s */
 		state(hdlc)->timer.expires = jiffies + HZ;
-		state(hdlc)->timer.function = fr_timer;
-		state(hdlc)->timer.data = (unsigned long)dev;
 		add_timer(&state(hdlc)->timer);
 	} else
 		fr_set_link_state(1, dev);
diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index 0d2e00ece804..c7721c729541 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -610,9 +610,7 @@ static void ppp_start(struct net_device *dev)
 	for (i = 0; i < IDX_COUNT; i++) {
 		struct proto *proto = &ppp->protos[i];
 		proto->dev = dev;
-		init_timer(&proto->timer);
-		proto->timer.function = ppp_timer;
-		proto->timer.data = (unsigned long)proto;
+		setup_timer(&proto->timer, ppp_timer, (unsigned long)proto);
 		proto->state = CLOSED;
 	}
 	ppp->protos[IDX_LCP].pid = PID_LCP;
diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c
index 4698450c77d1..37b1e0d03e31 100644
--- a/drivers/net/wan/lmc/lmc_main.c
+++ b/drivers/net/wan/lmc/lmc_main.c
@@ -99,7 +99,7 @@ static void lmc_initcsrs(lmc_softc_t * const sc, lmc_csrptr_t csr_base, size_t c
 static void lmc_softreset(lmc_softc_t * const);
 static void lmc_running_reset(struct net_device *dev);
 static int lmc_ifdown(struct net_device * const);
-static void lmc_watchdog(unsigned long data);
+static void lmc_watchdog(struct timer_list *t);
 static void lmc_reset(lmc_softc_t * const sc);
 static void lmc_dec_reset(lmc_softc_t * const sc);
 static void lmc_driver_timeout(struct net_device *dev);
@@ -636,10 +636,10 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
 
 
 /* the watchdog process that cruises around */
-static void lmc_watchdog (unsigned long data) /*fold00*/
+static void lmc_watchdog(struct timer_list *t) /*fold00*/
 {
-    struct net_device *dev = (struct net_device *)data;
-    lmc_softc_t *sc = dev_to_sc(dev);
+    lmc_softc_t *sc = from_timer(sc, t, timer);
+    struct net_device *dev = sc->lmc_device;
     int link_status;
     u32 ticks;
     unsigned long flags;
@@ -1084,10 +1084,8 @@ static int lmc_open(struct net_device *dev)
      * Setup a timer for the watchdog on probe, and start it running.
      * Since lmc_ok == 0, it will be a NOP for now.
      */
-    init_timer (&sc->timer);
+    timer_setup(&sc->timer, lmc_watchdog, 0);
     sc->timer.expires = jiffies + HZ;
-    sc->timer.data = (unsigned long) dev;
-    sc->timer.function = lmc_watchdog;
     add_timer (&sc->timer);
 
     lmc_trace(dev, "lmc_open out");
diff --git a/drivers/net/wan/sbni.c b/drivers/net/wan/sbni.c
index bde8c0339831..8e8c4c0e1b64 100644
--- a/drivers/net/wan/sbni.c
+++ b/drivers/net/wan/sbni.c
@@ -71,6 +71,7 @@
 
 struct net_local {
 	struct timer_list	watchdog;
+	struct net_device	*watchdog_dev;
 
 	spinlock_t	lock;
 	struct sk_buff  *rx_buf_p;		/* receive buffer ptr */
@@ -128,7 +129,7 @@ static void  send_frame( struct net_device * );
 static int   upload_data( struct net_device *,
 			  unsigned, unsigned, unsigned, u32 );
 static void  download_data( struct net_device *, u32 * );
-static void  sbni_watchdog( unsigned long );
+static void  sbni_watchdog(struct timer_list *);
 static void  interpret_ack( struct net_device *, unsigned );
 static int   append_frame_to_pkt( struct net_device *, unsigned, u32 );
 static void  indicate_pkt( struct net_device * );
@@ -1029,11 +1030,10 @@ indicate_pkt( struct net_device  *dev )
  */
 
 static void
-sbni_watchdog( unsigned long  arg )
+sbni_watchdog(struct timer_list *t)
 {
-	struct net_device  *dev = (struct net_device *) arg;
-	struct net_local   *nl  = netdev_priv(dev);
-	struct timer_list  *w   = &nl->watchdog; 
+	struct net_local   *nl  = from_timer(nl, t, watchdog);
+	struct net_device  *dev = nl->watchdog_dev;
 	unsigned long	   flags;
 	unsigned char	   csr0;
 
@@ -1060,11 +1060,7 @@ sbni_watchdog( unsigned long  arg )
 
 	outb( csr0 | RC_CHK, dev->base_addr + CSR0 ); 
 
-	init_timer( w );
-	w->expires	= jiffies + SBNI_TIMEOUT;
-	w->data		= arg;
-	w->function	= sbni_watchdog;
-	add_timer( w );
+	mod_timer(t, jiffies + SBNI_TIMEOUT);
 
 	spin_unlock_irqrestore( &nl->lock, flags );
 }
@@ -1195,10 +1191,9 @@ handler_attached:
 	netif_start_queue( dev );
 
 	/* set timer watchdog */
-	init_timer( w );
+	nl->watchdog_dev = dev;
+	timer_setup(w, sbni_watchdog, 0);
 	w->expires	= jiffies + SBNI_TIMEOUT;
-	w->data		= (unsigned long) dev;
-	w->function	= sbni_watchdog;
 	add_timer( w );
    
 	spin_unlock( &nl->lock );
diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c
index 236c62538036..57ed259c8208 100644
--- a/drivers/net/wan/sdla.c
+++ b/drivers/net/wan/sdla.c
@@ -927,13 +927,10 @@ static irqreturn_t sdla_isr(int dummy, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void sdla_poll(unsigned long device)
+static void sdla_poll(struct timer_list *t)
 {
-	struct net_device	  *dev;
-	struct frad_local *flp;
-
-	dev = (struct net_device *) device;
-	flp = netdev_priv(dev);
+	struct frad_local *flp = from_timer(flp, t, timer);
+	struct net_device *dev = flp->dev;
 
 	if (sdla_byte(dev, SDLA_502_RCV_BUF))
 		sdla_receive(dev);
@@ -1616,11 +1613,10 @@ static void setup_sdla(struct net_device *dev)
 	flp->assoc		= sdla_assoc;
 	flp->deassoc		= sdla_deassoc;
 	flp->dlci_conf		= sdla_dlci_conf;
+	flp->dev		= dev;
 
-	init_timer(&flp->timer);
+	timer_setup(&flp->timer, sdla_poll, 0);
 	flp->timer.expires	= 1;
-	flp->timer.data		= (unsigned long) dev;
-	flp->timer.function	= sdla_poll;
 }
 
 static struct net_device *sdla;
diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c
index 0c7317520ed3..d573a57bc301 100644
--- a/drivers/net/wan/wanxl.c
+++ b/drivers/net/wan/wanxl.c
@@ -734,7 +734,6 @@ static int wanxl_pci_init_one(struct pci_dev *pdev,
 		return -ENODEV;
 	}
 
-	stat = 0;
 	timeout = jiffies + 5 * HZ;
 	do {
 		if ((stat = readl(card->plx + PLX_MAILBOX_5)) != 0)
diff --git a/drivers/net/wireless/ath/ath6kl/txrx.c b/drivers/net/wireless/ath/ath6kl/txrx.c
index e6b2517e6334..4e5cc2b7045a 100644
--- a/drivers/net/wireless/ath/ath6kl/txrx.c
+++ b/drivers/net/wireless/ath/ath6kl/txrx.c
@@ -1753,9 +1753,7 @@ void aggr_conn_init(struct ath6kl_vif *vif, struct aggr_info *aggr_info,
 
 	aggr_conn->aggr_sz = AGGR_SZ_DEFAULT;
 	aggr_conn->dev = vif->ndev;
-	init_timer(&aggr_conn->timer);
-	aggr_conn->timer.function = aggr_timeout;
-	aggr_conn->timer.data = (unsigned long) aggr_conn;
+	setup_timer(&aggr_conn->timer, aggr_timeout, (unsigned long)aggr_conn);
 	aggr_conn->aggr_info = aggr_info;
 
 	aggr_conn->timer_scheduled = false;
diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
index b68436b23a63..e816d53c2c05 100644
--- a/drivers/net/wireless/atmel/atmel.c
+++ b/drivers/net/wireless/atmel/atmel.c
@@ -1579,11 +1579,10 @@ struct net_device *init_atmel_card(unsigned short irq, unsigned long port,
 	priv->default_beacon_period = priv->beacon_period = 100;
 	priv->listen_interval = 1;
 
-	init_timer(&priv->management_timer);
+	setup_timer(&priv->management_timer, atmel_management_timer,
+		    (unsigned long)dev);
 	spin_lock_init(&priv->irqlock);
 	spin_lock_init(&priv->timerlock);
-	priv->management_timer.function = atmel_management_timer;
-	priv->management_timer.data = (unsigned long) dev;
 
 	dev->netdev_ops = &atmel_netdev_ops;
 	dev->wireless_handlers = &atmel_handler_def;
diff --git a/drivers/net/wireless/broadcom/b43/phy_g.c b/drivers/net/wireless/broadcom/b43/phy_g.c
index 822dcaa8ace6..f59c02166462 100644
--- a/drivers/net/wireless/broadcom/b43/phy_g.c
+++ b/drivers/net/wireless/broadcom/b43/phy_g.c
@@ -2297,7 +2297,7 @@ static u8 b43_gphy_aci_detect(struct b43_wldev *dev, u8 channel)
 static u8 b43_gphy_aci_scan(struct b43_wldev *dev)
 {
 	struct b43_phy *phy = &dev->phy;
-	u8 ret[13];
+	u8 ret[13] = { 0 };
 	unsigned int channel = phy->channel;
 	unsigned int i, j, start, end;
 
diff --git a/drivers/net/wireless/broadcom/b43/phy_ht.c b/drivers/net/wireless/broadcom/b43/phy_ht.c
index 718c90e81696..c3158d085c2b 100644
--- a/drivers/net/wireless/broadcom/b43/phy_ht.c
+++ b/drivers/net/wireless/broadcom/b43/phy_ht.c
@@ -119,7 +119,7 @@ static void b43_radio_2059_rcal(struct b43_wldev *dev)
 /* Calibrate the internal RC oscillator? */
 static void b43_radio_2057_rccal(struct b43_wldev *dev)
 {
-	const u16 radio_values[3][2] = {
+	static const u16 radio_values[3][2] = {
 		{ 0x61, 0xE9 }, { 0x69, 0xD5 }, { 0x73, 0x99 },
 	};
 	int i;
@@ -154,7 +154,7 @@ static void b43_radio_2059_init_pre(struct b43_wldev *dev)
 
 static void b43_radio_2059_init(struct b43_wldev *dev)
 {
-	const u16 routing[] = { R2059_C1, R2059_C2, R2059_C3 };
+	static const u16 routing[] = { R2059_C1, R2059_C2, R2059_C3 };
 	int i;
 
 	/* Prepare (reset?) radio */
@@ -263,7 +263,7 @@ static void b43_phy_ht_reset_cca(struct b43_wldev *dev)
 static void b43_phy_ht_zero_extg(struct b43_wldev *dev)
 {
 	u8 i, j;
-	u16 base[] = { 0x40, 0x60, 0x80 };
+	static const u16 base[] = { 0x40, 0x60, 0x80 };
 
 	for (i = 0; i < ARRAY_SIZE(base); i++) {
 		for (j = 0; j < 4; j++)
diff --git a/drivers/net/wireless/broadcom/b43legacy/radio.c b/drivers/net/wireless/broadcom/b43legacy/radio.c
index 9501420340a9..eab1c9387846 100644
--- a/drivers/net/wireless/broadcom/b43legacy/radio.c
+++ b/drivers/net/wireless/broadcom/b43legacy/radio.c
@@ -280,7 +280,7 @@ u8 b43legacy_radio_aci_detect(struct b43legacy_wldev *dev, u8 channel)
 u8 b43legacy_radio_aci_scan(struct b43legacy_wldev *dev)
 {
 	struct b43legacy_phy *phy = &dev->phy;
-	u8 ret[13];
+	u8 ret[13] = { 0 };
 	unsigned int channel = phy->channel;
 	unsigned int i;
 	unsigned int j;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 4157c90ad973..4bfd43a80273 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -3261,9 +3261,8 @@ static void brcmf_init_escan(struct brcmf_cfg80211_info *cfg)
 			    brcmf_cfg80211_escan_handler);
 	cfg->escan_info.escan_state = WL_ESCAN_STATE_IDLE;
 	/* Init scan_timeout timer */
-	init_timer(&cfg->escan_timeout);
-	cfg->escan_timeout.data = (unsigned long) cfg;
-	cfg->escan_timeout.function = brcmf_escan_timeout;
+	setup_timer(&cfg->escan_timeout, brcmf_escan_timeout,
+		    (unsigned long)cfg);
 	INIT_WORK(&cfg->escan_timeout_work,
 		  brcmf_cfg80211_escan_timeout_worker);
 }
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
index ef72baf6dd96..e7eaa57d11d9 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
@@ -257,11 +257,6 @@ static void brcmf_fweh_event_worker(struct work_struct *work)
 		brcmf_dbg_hex_dump(BRCMF_EVENT_ON(), event->data,
 				   min_t(u32, emsg.datalen, 64),
 				   "event payload, len=%d\n", emsg.datalen);
-		if (emsg.datalen > event->datalen) {
-			brcmf_err("event invalid length header=%d, msg=%d\n",
-				  event->datalen, emsg.datalen);
-			goto event_free;
-		}
 
 		/* special handling of interface event */
 		if (event->code == BRCMF_E_IF) {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
index 2ce675ab40ef..1c450c0727cb 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
@@ -1853,7 +1853,6 @@ s32 brcmf_p2p_notify_rx_mgmt_p2p_probereq(struct brcmf_if *ifp,
 	struct afx_hdl *afx_hdl = &p2p->afx_hdl;
 	struct brcmf_cfg80211_vif *vif = ifp->vif;
 	struct brcmf_rx_mgmt_data *rxframe = (struct brcmf_rx_mgmt_data *)data;
-	u16 chanspec = be16_to_cpu(rxframe->chanspec);
 	struct brcmu_chan ch;
 	u8 *mgmt_frame;
 	u32 mgmt_frame_len;
@@ -1906,7 +1905,7 @@ s32 brcmf_p2p_notify_rx_mgmt_p2p_probereq(struct brcmf_if *ifp,
 	cfg80211_rx_mgmt(&vif->wdev, freq, 0, mgmt_frame, mgmt_frame_len, 0);
 
 	brcmf_dbg(INFO, "mgmt_frame_len (%d) , e->datalen (%d), chanspec (%04x), freq (%d)\n",
-		  mgmt_frame_len, e->datalen, chanspec, freq);
+		  mgmt_frame_len, e->datalen, ch.chspec, freq);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 613caca7dc02..5adce0e36fe5 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -4144,10 +4144,8 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
 	init_waitqueue_head(&bus->dcmd_resp_wait);
 
 	/* Set up the watchdog timer */
-	init_timer(&bus->timer);
-	bus->timer.data = (unsigned long)bus;
-	bus->timer.function = brcmf_sdio_watchdog;
-
+	setup_timer(&bus->timer, brcmf_sdio_watchdog,
+		    (unsigned long)bus);
 	/* Initialize watchdog thread */
 	init_completion(&bus->watchdog_wait);
 	bus->watchdog_tsk = kthread_run(brcmf_sdio_watchdog_thread,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c
index 1c4e9dd57960..3a13d176b221 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c
@@ -1916,7 +1916,7 @@ void wlc_phy_txpower_update_shm(struct brcms_phy *pi)
 				     pi->hwpwr_txcur);
 
 		for (j = TXP_FIRST_OFDM; j <= TXP_LAST_OFDM; j++) {
-			const u8 ucode_ofdm_rates[] = {
+			static const u8 ucode_ofdm_rates[] = {
 				0x0c, 0x12, 0x18, 0x24, 0x30, 0x48, 0x60, 0x6c
 			};
 			offset = wlapi_bmac_rate_shm_offset(
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index de9b6522c43f..65eba2c24292 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -1480,7 +1480,7 @@ il4965_get_ac_from_tid(u16 tid)
 static inline int
 il4965_get_fifo_from_tid(u16 tid)
 {
-	const u8 ac_to_fifo[] = {
+	static const u8 ac_to_fifo[] = {
 		IL_TX_FIFO_VO,
 		IL_TX_FIFO_VI,
 		IL_TX_FIFO_BE,
diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile
index 595b26b66bfc..ff136f299a0a 100644
--- a/drivers/net/wireless/intel/iwlwifi/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/Makefile
@@ -14,6 +14,7 @@ iwlwifi-objs		+= iwl-trans.o
 iwlwifi-objs		+= fw/notif-wait.o
 iwlwifi-$(CONFIG_IWLMVM) += fw/paging.o fw/smem.o fw/init.o fw/dbg.o
 iwlwifi-$(CONFIG_IWLMVM) += fw/common_rx.o fw/nvm.o
+iwlwifi-$(CONFIG_ACPI) += fw/acpi.o
 
 iwlwifi-objs += $(iwlwifi-m)
 
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/a000.c b/drivers/net/wireless/intel/iwlwifi/cfg/a000.c
index a440140ed8dd..c911d55fde49 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/a000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/a000.c
@@ -134,77 +134,78 @@ static const struct iwl_ht_params iwl_a000_ht_params = {
 	.rf_id = true,							\
 	.gen2 = true,							\
 	.nvm_type = IWL_NVM_EXT,					\
-	.dbgc_supported = true
+	.dbgc_supported = true,						\
+	.tx_cmd_queue_size = 32
 
 const struct iwl_cfg iwla000_2ac_cfg_hr = {
-		.name = "Intel(R) Dual Band Wireless AC a000",
-		.fw_name_pre = IWL_A000_HR_FW_PRE,
-		IWL_DEVICE_A000,
-		.ht_params = &iwl_a000_ht_params,
-		.nvm_ver = IWL_A000_NVM_VERSION,
-		.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
-		.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.name = "Intel(R) Dual Band Wireless AC a000",
+	.fw_name_pre = IWL_A000_HR_FW_PRE,
+	IWL_DEVICE_A000,
+	.ht_params = &iwl_a000_ht_params,
+	.nvm_ver = IWL_A000_NVM_VERSION,
+	.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
 const struct iwl_cfg iwla000_2ac_cfg_hr_cdb = {
-		.name = "Intel(R) Dual Band Wireless AC a000",
-		.fw_name_pre = IWL_A000_HR_CDB_FW_PRE,
-		IWL_DEVICE_A000,
-		.ht_params = &iwl_a000_ht_params,
-		.nvm_ver = IWL_A000_NVM_VERSION,
-		.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
-		.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
-		.cdb = true,
+	.name = "Intel(R) Dual Band Wireless AC a000",
+	.fw_name_pre = IWL_A000_HR_CDB_FW_PRE,
+	IWL_DEVICE_A000,
+	.ht_params = &iwl_a000_ht_params,
+	.nvm_ver = IWL_A000_NVM_VERSION,
+	.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.cdb = true,
 };
 
 const struct iwl_cfg iwla000_2ac_cfg_jf = {
-		.name = "Intel(R) Dual Band Wireless AC a000",
-		.fw_name_pre = IWL_A000_JF_FW_PRE,
-		IWL_DEVICE_A000,
-		.ht_params = &iwl_a000_ht_params,
-		.nvm_ver = IWL_A000_NVM_VERSION,
-		.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
-		.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.name = "Intel(R) Dual Band Wireless AC a000",
+	.fw_name_pre = IWL_A000_JF_FW_PRE,
+	IWL_DEVICE_A000,
+	.ht_params = &iwl_a000_ht_params,
+	.nvm_ver = IWL_A000_NVM_VERSION,
+	.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
 const struct iwl_cfg iwla000_2ax_cfg_hr = {
-		.name = "Intel(R) Dual Band Wireless AX a000",
-		.fw_name_pre = IWL_A000_HR_FW_PRE,
-		IWL_DEVICE_A000,
-		.ht_params = &iwl_a000_ht_params,
-		.nvm_ver = IWL_A000_NVM_VERSION,
-		.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
-		.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.name = "Intel(R) Dual Band Wireless AX a000",
+	.fw_name_pre = IWL_A000_HR_FW_PRE,
+	IWL_DEVICE_A000,
+	.ht_params = &iwl_a000_ht_params,
+	.nvm_ver = IWL_A000_NVM_VERSION,
+	.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
 const struct iwl_cfg iwla000_2ax_cfg_qnj_hr_f0 = {
-		.name = "Intel(R) Dual Band Wireless AX a000",
-		.fw_name_pre = IWL_A000_HR_F0_FW_PRE,
-		IWL_DEVICE_A000,
-		.ht_params = &iwl_a000_ht_params,
-		.nvm_ver = IWL_A000_NVM_VERSION,
-		.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
-		.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.name = "Intel(R) Dual Band Wireless AX a000",
+	.fw_name_pre = IWL_A000_HR_F0_FW_PRE,
+	IWL_DEVICE_A000,
+	.ht_params = &iwl_a000_ht_params,
+	.nvm_ver = IWL_A000_NVM_VERSION,
+	.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
 const struct iwl_cfg iwla000_2ax_cfg_qnj_jf_b0 = {
-		.name = "Intel(R) Dual Band Wireless AX a000",
-		.fw_name_pre = IWL_A000_JF_B0_FW_PRE,
-		IWL_DEVICE_A000,
-		.ht_params = &iwl_a000_ht_params,
-		.nvm_ver = IWL_A000_NVM_VERSION,
-		.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
-		.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.name = "Intel(R) Dual Band Wireless AX a000",
+	.fw_name_pre = IWL_A000_JF_B0_FW_PRE,
+	IWL_DEVICE_A000,
+	.ht_params = &iwl_a000_ht_params,
+	.nvm_ver = IWL_A000_NVM_VERSION,
+	.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
 const struct iwl_cfg iwla000_2ax_cfg_qnj_hr_a0 = {
-		.name = "Intel(R) Dual Band Wireless AX a000",
-		.fw_name_pre = IWL_A000_HR_A0_FW_PRE,
-		IWL_DEVICE_A000,
-		.ht_params = &iwl_a000_ht_params,
-		.nvm_ver = IWL_A000_NVM_VERSION,
-		.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
-		.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.name = "Intel(R) Dual Band Wireless AX a000",
+	.fw_name_pre = IWL_A000_HR_A0_FW_PRE,
+	IWL_DEVICE_A000,
+	.ht_params = &iwl_a000_ht_params,
+	.nvm_ver = IWL_A000_NVM_VERSION,
+	.nvm_calib_ver = IWL_A000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
 MODULE_FIRMWARE(IWL_A000_HR_MODULE_FIRMWARE(IWL_A000_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
new file mode 100644
index 000000000000..75cae54ea7de
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -0,0 +1,210 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2017        Intel Deutschland GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program;
+ *
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * Contact Information:
+ *  Intel Linux Wireless <linuxwifi@intel.com>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2017        Intel Deutschland GmbH
+ * All rights reserved.
+ *
+ * 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.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+
+#include "iwl-drv.h"
+#include "iwl-debug.h"
+#include "acpi.h"
+
+void *iwl_acpi_get_object(struct device *dev, acpi_string method)
+{
+	acpi_handle root_handle;
+	acpi_handle handle;
+	struct acpi_buffer buf = {ACPI_ALLOCATE_BUFFER, NULL};
+	acpi_status status;
+
+	root_handle = ACPI_HANDLE(dev);
+	if (!root_handle) {
+		IWL_DEBUG_DEV_RADIO(dev,
+				    "Could not retrieve root port ACPI handle\n");
+		return ERR_PTR(-ENOENT);
+	}
+
+	/* Get the method's handle */
+	status = acpi_get_handle(root_handle, method, &handle);
+	if (ACPI_FAILURE(status)) {
+		IWL_DEBUG_DEV_RADIO(dev, "%s method not found\n", method);
+		return ERR_PTR(-ENOENT);
+	}
+
+	/* Call the method with no arguments */
+	status = acpi_evaluate_object(handle, NULL, NULL, &buf);
+	if (ACPI_FAILURE(status)) {
+		IWL_DEBUG_DEV_RADIO(dev, "%s invocation failed (0x%x)\n",
+				    method, status);
+		return ERR_PTR(-ENOENT);
+	}
+
+	return buf.pointer;
+}
+IWL_EXPORT_SYMBOL(iwl_acpi_get_object);
+
+union acpi_object *iwl_acpi_get_wifi_pkg(struct device *dev,
+					 union acpi_object *data,
+					 int data_size)
+{
+	int i;
+	union acpi_object *wifi_pkg;
+
+	/*
+	 * We need at least one entry in the wifi package that
+	 * describes the domain, and one more entry, otherwise there's
+	 * no point in reading it.
+	 */
+	if (WARN_ON_ONCE(data_size < 2))
+		return ERR_PTR(-EINVAL);
+
+	/*
+	 * We need at least two packages, one for the revision and one
+	 * for the data itself.  Also check that the revision is valid
+	 * (i.e. it is an integer set to 0).
+	 */
+	if (data->type != ACPI_TYPE_PACKAGE ||
+	    data->package.count < 2 ||
+	    data->package.elements[0].type != ACPI_TYPE_INTEGER ||
+	    data->package.elements[0].integer.value != 0) {
+		IWL_DEBUG_DEV_RADIO(dev, "Unsupported packages structure\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* loop through all the packages to find the one for WiFi */
+	for (i = 1; i < data->package.count; i++) {
+		union acpi_object *domain;
+
+		wifi_pkg = &data->package.elements[i];
+
+		/* skip entries that are not a package with the right size */
+		if (wifi_pkg->type != ACPI_TYPE_PACKAGE ||
+		    wifi_pkg->package.count != data_size)
+			continue;
+
+		domain = &wifi_pkg->package.elements[0];
+		if (domain->type == ACPI_TYPE_INTEGER &&
+		    domain->integer.value == ACPI_WIFI_DOMAIN)
+			goto found;
+	}
+
+	return ERR_PTR(-ENOENT);
+
+found:
+	return wifi_pkg;
+}
+IWL_EXPORT_SYMBOL(iwl_acpi_get_wifi_pkg);
+
+int iwl_acpi_get_mcc(struct device *dev, char *mcc)
+{
+	union acpi_object *wifi_pkg, *data;
+	u32 mcc_val;
+	int ret;
+
+	data = iwl_acpi_get_object(dev, ACPI_WRDD_METHOD);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	wifi_pkg = iwl_acpi_get_wifi_pkg(dev, data, ACPI_WRDD_WIFI_DATA_SIZE);
+	if (IS_ERR(wifi_pkg)) {
+		ret = PTR_ERR(wifi_pkg);
+		goto out_free;
+	}
+
+	if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) {
+		ret = -EINVAL;
+		goto out_free;
+	}
+
+	mcc_val = wifi_pkg->package.elements[1].integer.value;
+
+	mcc[0] = (mcc_val >> 8) & 0xff;
+	mcc[1] = mcc_val & 0xff;
+	mcc[2] = '\0';
+
+	ret = 0;
+out_free:
+	kfree(data);
+	return ret;
+}
+IWL_EXPORT_SYMBOL(iwl_acpi_get_mcc);
+
+u64 iwl_acpi_get_pwr_limit(struct device *dev)
+{
+	union acpi_object *data, *wifi_pkg;
+	u64 dflt_pwr_limit;
+
+	data = iwl_acpi_get_object(dev, ACPI_SPLC_METHOD);
+	if (IS_ERR(data)) {
+		dflt_pwr_limit = 0;
+		goto out;
+	}
+
+	wifi_pkg = iwl_acpi_get_wifi_pkg(dev, data,
+					 ACPI_SPLC_WIFI_DATA_SIZE);
+	if (IS_ERR(wifi_pkg) ||
+	    wifi_pkg->package.elements[1].integer.value != ACPI_TYPE_INTEGER) {
+		dflt_pwr_limit = 0;
+		goto out_free;
+	}
+
+	dflt_pwr_limit = wifi_pkg->package.elements[1].integer.value;
+out_free:
+	kfree(data);
+out:
+	return dflt_pwr_limit;
+}
+IWL_EXPORT_SYMBOL(iwl_acpi_get_pwr_limit);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h
new file mode 100644
index 000000000000..cb5f32c1d705
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h
@@ -0,0 +1,138 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2017        Intel Deutschland GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program;
+ *
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * Contact Information:
+ *  Intel Linux Wireless <linuxwifi@intel.com>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2017        Intel Deutschland GmbH
+ * All rights reserved.
+ *
+ * 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.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+#ifndef __iwl_fw_acpi__
+#define __iwl_fw_acpi__
+
+#include <linux/acpi.h>
+
+#define ACPI_WRDS_METHOD	"WRDS"
+#define ACPI_EWRD_METHOD	"EWRD"
+#define ACPI_WGDS_METHOD	"WGDS"
+#define ACPI_WRDD_METHOD	"WRDD"
+#define ACPI_SPLC_METHOD	"SPLC"
+
+#define ACPI_WIFI_DOMAIN	(0x07)
+
+#define ACPI_SAR_TABLE_SIZE		10
+#define ACPI_SAR_PROFILE_NUM		4
+
+#define ACPI_GEO_TABLE_SIZE		6
+#define ACPI_NUM_GEO_PROFILES		3
+#define ACPI_GEO_PER_CHAIN_SIZE		3
+
+#define ACPI_SAR_NUM_CHAIN_LIMITS	2
+#define ACPI_SAR_NUM_SUB_BANDS		5
+
+#define ACPI_WRDS_WIFI_DATA_SIZE	(ACPI_SAR_TABLE_SIZE + 2)
+#define ACPI_EWRD_WIFI_DATA_SIZE	((ACPI_SAR_PROFILE_NUM - 1) * \
+					 ACPI_SAR_TABLE_SIZE + 3)
+#define ACPI_WGDS_WIFI_DATA_SIZE	18
+#define ACPI_WRDD_WIFI_DATA_SIZE	2
+#define ACPI_SPLC_WIFI_DATA_SIZE	2
+
+#define ACPI_WGDS_NUM_BANDS		2
+#define ACPI_WGDS_TABLE_SIZE		3
+
+#ifdef CONFIG_ACPI
+
+void *iwl_acpi_get_object(struct device *dev, acpi_string method);
+union acpi_object *iwl_acpi_get_wifi_pkg(struct device *dev,
+					 union acpi_object *data,
+					 int data_size);
+
+/**
+ * iwl_acpi_get_mcc - read MCC from ACPI, if available
+ *
+ * @dev: the struct device
+ * @mcc: output buffer (3 bytes) that will get the MCC
+ *
+ * This function tries to read the current MCC from ACPI if available.
+ */
+int iwl_acpi_get_mcc(struct device *dev, char *mcc);
+
+u64 iwl_acpi_get_pwr_limit(struct device *dev);
+
+#else /* CONFIG_ACPI */
+
+static inline void *iwl_acpi_get_object(struct device *dev, acpi_string method)
+{
+	return ERR_PTR(-ENOENT);
+}
+
+static inline union acpi_object *iwl_acpi_get_wifi_pkg(struct device *dev,
+						       union acpi_object *data,
+						       int data_size)
+{
+	return ERR_PTR(-ENOENT);
+}
+
+static inline int iwl_acpi_get_mcc(struct device *dev, char *mcc)
+{
+	return -ENOENT;
+}
+
+static inline u64 iwl_acpi_get_pwr_limit(struct device *dev)
+{
+	return 0;
+}
+
+#endif /* CONFIG_ACPI */
+#endif /* __iwl_fw_acpi__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/binding.h b/drivers/net/wireless/intel/iwlwifi/fw/api/binding.h
index d2717fafdf5b..570f19026c91 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/binding.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/binding.h
@@ -116,14 +116,14 @@ struct iwl_binding_cmd {
 #define IWL_MVM_MAX_QUOTA 128
 
 /**
- * struct iwl_time_quota_data - configuration of time quota per binding
+ * struct iwl_time_quota_data_v1 - configuration of time quota per binding
  * @id_and_color: ID and color of the relevant Binding,
  *	&enum iwl_ctxt_id_and_color
  * @quota: absolute time quota in TU. The scheduler will try to divide the
  *	remainig quota (after Time Events) according to this quota.
  * @max_duration: max uninterrupted context duration in TU
  */
-struct iwl_time_quota_data {
+struct iwl_time_quota_data_v1 {
 	__le32 id_and_color;
 	__le32 quota;
 	__le32 max_duration;
@@ -137,8 +137,43 @@ struct iwl_time_quota_data {
  *	essentially zero.
  *	On CDB the fourth one is a regular binding.
  */
+struct iwl_time_quota_cmd_v1 {
+	struct iwl_time_quota_data_v1 quotas[MAX_BINDINGS];
+} __packed; /* TIME_QUOTA_ALLOCATION_CMD_API_S_VER_1 */
+
+enum iwl_quota_low_latency {
+	IWL_QUOTA_LOW_LATENCY_NONE = 0,
+	IWL_QUOTA_LOW_LATENCY_TX = BIT(0),
+	IWL_QUOTA_LOW_LATENCY_RX = BIT(1),
+	IWL_QUOTA_LOW_LATENCY_TX_RX =
+		IWL_QUOTA_LOW_LATENCY_TX | IWL_QUOTA_LOW_LATENCY_RX,
+};
+
+/**
+ * struct iwl_time_quota_data - configuration of time quota per binding
+ * @id_and_color: ID and color of the relevant Binding.
+ * @quota: absolute time quota in TU. The scheduler will try to divide the
+ *	remainig quota (after Time Events) according to this quota.
+ * @max_duration: max uninterrupted context duration in TU
+ * @low_latency: low latency status, &enum iwl_quota_low_latency
+ */
+struct iwl_time_quota_data {
+	__le32 id_and_color;
+	__le32 quota;
+	__le32 max_duration;
+	__le32 low_latency;
+} __packed; /* TIME_QUOTA_DATA_API_S_VER_2 */
+
+/**
+ * struct iwl_time_quota_cmd - configuration of time quota between bindings
+ * ( TIME_QUOTA_CMD = 0x2c )
+ * Note: on non-CDB the fourth one is the auxilary mac and is essentially zero.
+ * On CDB the fourth one is a regular binding.
+ *
+ * @quotas: allocations per binding
+ */
 struct iwl_time_quota_cmd {
 	struct iwl_time_quota_data quotas[MAX_BINDINGS];
-} __packed; /* TIME_QUOTA_ALLOCATION_CMD_API_S_VER_1 */
+} __packed; /* TIME_QUOTA_ALLOCATION_CMD_API_S_VER_2 */
 
 #endif /* __iwl_fw_api_binding_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index 074868394427..7ebbf097488b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -504,6 +504,7 @@ enum iwl_legacy_cmds {
 
 	/**
 	 * @MARKER_CMD: trace marker command, uses &struct iwl_mvm_marker
+	 * with &struct iwl_mvm_marker_rsp
 	 */
 	MARKER_CMD = 0xcb,
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
index 9f88b61536bc..0a81fb1b6ed4 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
@@ -278,6 +278,15 @@ struct iwl_mvm_marker {
 	__le32 metadata[0];
 } __packed; /* MARKER_API_S_VER_1 */
 
+/**
+ * struct iwl_mvm_marker_rsp - Response to marker cmd
+ *
+ * @gp2: The gp2 clock value in the FW
+ */
+struct iwl_mvm_marker_rsp {
+	__le32 gp2;
+} __packed;
+
 /* Operation types for the debug mem access */
 enum {
 	DEBUG_MEM_OP_READ = 0,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index 39c89e85fd2f..ec42c84e5df2 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -68,78 +68,11 @@
  */
 enum iwl_mac_conf_subcmd_ids {
 	/**
-	 * @LINK_QUALITY_MEASUREMENT_CMD: &struct iwl_link_qual_msrmnt_cmd
-	 */
-	LINK_QUALITY_MEASUREMENT_CMD = 0x1,
-
-	/**
-	 * @LINK_QUALITY_MEASUREMENT_COMPLETE_NOTIF:
-	 * &struct iwl_link_qual_msrmnt_notif
-	 */
-	LINK_QUALITY_MEASUREMENT_COMPLETE_NOTIF = 0xFE,
-
-	/**
 	 * @CHANNEL_SWITCH_NOA_NOTIF: &struct iwl_channel_switch_noa_notif
 	 */
 	CHANNEL_SWITCH_NOA_NOTIF = 0xFF,
 };
 
-#define LQM_NUMBER_OF_STATIONS_IN_REPORT 16
-
-enum iwl_lqm_cmd_operatrions {
-	LQM_CMD_OPERATION_START_MEASUREMENT = 0x01,
-	LQM_CMD_OPERATION_STOP_MEASUREMENT = 0x02,
-};
-
-enum iwl_lqm_status {
-	LQM_STATUS_SUCCESS = 0,
-	LQM_STATUS_TIMEOUT = 1,
-	LQM_STATUS_ABORT = 2,
-};
-
-/**
- * struct iwl_link_qual_msrmnt_cmd - Link Quality Measurement command
- * @cmd_operation: command operation to be performed (start or stop)
- *	as defined above.
- * @mac_id: MAC ID the measurement applies to.
- * @measurement_time: time of the total measurement to be performed, in uSec.
- * @timeout: maximum time allowed until a response is sent, in uSec.
- */
-struct iwl_link_qual_msrmnt_cmd {
-	__le32 cmd_operation;
-	__le32 mac_id;
-	__le32 measurement_time;
-	__le32 timeout;
-} __packed /* LQM_CMD_API_S_VER_1 */;
-
-/**
- * struct iwl_link_qual_msrmnt_notif - Link Quality Measurement notification
- *
- * @frequent_stations_air_time: an array containing the total air time
- *	(in uSec) used by the most frequently transmitting stations.
- * @number_of_stations: the number of uniqe stations included in the array
- *	(a number between 0 to 16)
- * @total_air_time_other_stations: the total air time (uSec) used by all the
- *	stations which are not included in the above report.
- * @time_in_measurement_window: the total time in uSec in which a measurement
- *	took place.
- * @tx_frame_dropped: the number of TX frames dropped due to retry limit during
- *	measurement
- * @mac_id: MAC ID the measurement applies to.
- * @status: return status. may be one of the LQM_STATUS_* defined above.
- * @reserved: reserved.
- */
-struct iwl_link_qual_msrmnt_notif {
-	__le32 frequent_stations_air_time[LQM_NUMBER_OF_STATIONS_IN_REPORT];
-	__le32 number_of_stations;
-	__le32 total_air_time_other_stations;
-	__le32 time_in_measurement_window;
-	__le32 tx_frame_dropped;
-	__le32 mac_id;
-	__le32 status;
-	u8 reserved[12];
-} __packed; /* LQM_MEASUREMENT_COMPLETE_NTF_API_S_VER1 */
-
 /**
  * struct iwl_channel_switch_noa_notif - Channel switch NOA notification
  *
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
index a06afb5605d2..a3c77e01863b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
@@ -357,8 +357,7 @@ struct iwl_dev_tx_power_cmd {
 	u8 reserved[3];
 } __packed; /* TX_REDUCED_POWER_API_S_VER_4 */
 
-#define IWL_NUM_GEO_PROFILES	3
-#define IWL_GEO_PER_CHAIN_SIZE	3
+#define IWL_NUM_GEO_PROFILES   3
 
 /**
  * enum iwl_geo_per_chain_offset_operation - type of operation
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h
index af369eba3795..dc40cbd52f92 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h
@@ -68,9 +68,6 @@
  * @STA_FLG_REDUCED_TX_PWR_DATA: reduced TX power (data frames)
  * @STA_FLG_DISABLE_TX: set if TX should be disabled
  * @STA_FLG_PS: set if STA is in Power Save
- * @STA_FLG_INVALID: set if STA is invalid
- * @STA_FLG_DLP_EN: Direct Link Protocol is enabled
- * @STA_FLG_SET_ALL_KEYS: the current key applies to all key IDs
  * @STA_FLG_DRAIN_FLOW: drain flow
  * @STA_FLG_PAN: STA is for PAN interface
  * @STA_FLG_CLASS_AUTH: station is authenticated
@@ -100,7 +97,6 @@
  * @STA_FLG_MIMO_EN_SISO: no support for MIMO
  * @STA_FLG_MIMO_EN_MIMO2: 2 streams supported
  * @STA_FLG_MIMO_EN_MIMO3: 3 streams supported
- * @STA_FLG_MFP_EN: Management Frame Protection
  * @STA_FLG_AGG_MPDU_DENS_MSK: A-MPDU density (mask)
  * @STA_FLG_AGG_MPDU_DENS_SHIFT: A-MPDU density (bit shift)
  * @STA_FLG_AGG_MPDU_DENS_2US: A-MPDU density (2 usec gap)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index f5dd7d83cd0a..8106fd4be996 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -93,6 +93,8 @@ static void iwl_read_radio_regs(struct iwl_fw_runtime *fwrt,
 	unsigned long flags;
 	int i;
 
+	IWL_DEBUG_INFO(fwrt, "WRT radio registers dump\n");
+
 	if (!iwl_trans_grab_nic_access(fwrt->trans, &flags))
 		return;
 
@@ -233,6 +235,8 @@ static void iwl_fw_dump_fifos(struct iwl_fw_runtime *fwrt,
 	unsigned long flags;
 	int i, j;
 
+	IWL_DEBUG_INFO(fwrt, "WRT FIFO dump\n");
+
 	if (!iwl_trans_grab_nic_access(fwrt->trans, &flags))
 		return;
 
@@ -476,6 +480,8 @@ static void iwl_dump_prph(struct iwl_trans *trans,
 	unsigned long flags;
 	u32 i;
 
+	IWL_DEBUG_INFO(trans, "WRT PRPH dump\n");
+
 	if (!iwl_trans_grab_nic_access(trans, &flags))
 		return;
 
@@ -559,6 +565,8 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	bool monitor_dump_only = false;
 	int i;
 
+	IWL_DEBUG_INFO(fwrt, "WRT dump start\n");
+
 	/* there's no point in fw dump if the bus is dead */
 	if (test_bit(STATUS_TRANS_DEAD, &fwrt->trans->status)) {
 		IWL_ERR(fwrt, "Skip fw error dump since bus is dead\n");
@@ -816,6 +824,9 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 		dump_mem->type = fw_dbg_mem[i].data_type;
 		dump_mem->offset = cpu_to_le32(ofs);
 
+		IWL_DEBUG_INFO(fwrt, "WRT memory dump. Type=%u\n",
+			       dump_mem->type);
+
 		switch (dump_mem->type & cpu_to_le32(FW_DBG_MEM_TYPE_MASK)) {
 		case cpu_to_le32(FW_DBG_MEM_TYPE_REGULAR):
 			iwl_trans_read_mem_bytes(fwrt->trans, ofs,
@@ -841,6 +852,7 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	}
 
 	if (smem_len) {
+		IWL_DEBUG_INFO(fwrt, "WRT SMEM dump\n");
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM);
 		dump_data->len = cpu_to_le32(smem_len + sizeof(*dump_mem));
 		dump_mem = (void *)dump_data->data;
@@ -853,6 +865,7 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	}
 
 	if (sram2_len) {
+		IWL_DEBUG_INFO(fwrt, "WRT SRAM dump\n");
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM);
 		dump_data->len = cpu_to_le32(sram2_len + sizeof(*dump_mem));
 		dump_mem = (void *)dump_data->data;
@@ -868,6 +881,7 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	if (!fwrt->trans->cfg->gen2 &&
 	    fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size &&
 	    fwrt->fw_paging_db[0].fw_paging_block) {
+		IWL_DEBUG_INFO(fwrt, "WRT paging dump\n");
 		for (i = 1; i < fwrt->num_of_paging_blk + 1; i++) {
 			struct iwl_fw_error_dump_paging *paging;
 			struct page *pages =
@@ -930,6 +944,7 @@ out:
 	iwl_fw_free_dump_desc(fwrt);
 	fwrt->dump.trig = NULL;
 	clear_bit(IWL_FWRT_STATUS_DUMPING, &fwrt->status);
+	IWL_DEBUG_INFO(fwrt, "WRT dump done\n");
 }
 IWL_EXPORT_SYMBOL(iwl_fw_error_dump);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h
index 279248cd9cfb..efd7fb65de8b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/file.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h
@@ -248,6 +248,8 @@ typedef unsigned int __bitwise iwl_ucode_tlv_api_t;
  * @IWL_UCODE_TLV_API_NEW_RX_STATS: should new RX STATISTICS API be used
  * @IWL_UCODE_TLV_API_ATS_COEX_EXTERNAL: the coex notification is enlared to
  *	include information about ACL time sharing.
+ * @IWL_UCODE_TLV_API_QUOTA_LOW_LATENCY: Quota command includes a field
+ *	indicating low latency direction.
  *
  * @NUM_IWL_UCODE_TLV_API: number of bits used
  */
@@ -265,6 +267,7 @@ enum iwl_ucode_tlv_api {
 	IWL_UCODE_TLV_API_NEW_BEACON_TEMPLATE	= (__force iwl_ucode_tlv_api_t)34,
 	IWL_UCODE_TLV_API_NEW_RX_STATS		= (__force iwl_ucode_tlv_api_t)35,
 	IWL_UCODE_TLV_API_COEX_ATS_EXTERNAL	= (__force iwl_ucode_tlv_api_t)37,
+	IWL_UCODE_TLV_API_QUOTA_LOW_LATENCY	= (__force iwl_ucode_tlv_api_t)38,
 
 	NUM_IWL_UCODE_TLV_API
 #ifdef __CHECKER__
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index 71cb1ecde0f7..0347a03b6f1b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -333,6 +333,8 @@ struct iwl_pwr_tx_backoff {
  * @gen2: a000 and on transport operation
  * @cdb: CDB support
  * @nvm_type: see &enum iwl_nvm_type
+ * @tx_cmd_queue_size: size of the cmd queue. If zero, use the same value as
+ *	the regular queues
  *
  * We enable the driver to be backward compatible wrt. hardware features.
  * API differences in uCode shouldn't be handled here but through TLVs
@@ -383,6 +385,7 @@ struct iwl_cfg {
 	    gen2:1,
 	    cdb:1,
 	    dbgc_supported:1;
+	u16 tx_cmd_queue_size;
 	u8 valid_tx_ant;
 	u8 valid_rx_ant;
 	u8 non_shared_ant;
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-debug.h b/drivers/net/wireless/intel/iwlwifi/iwl-debug.h
index cd77c6971753..c023fcf5d452 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-debug.h
@@ -216,6 +216,7 @@ do {                                            			\
 #define IWL_DEBUG_TX_REPLY(p, f, a...)	IWL_DEBUG(p, IWL_DL_TX_REPLY, f, ## a)
 #define IWL_DEBUG_TX_QUEUES(p, f, a...)	IWL_DEBUG(p, IWL_DL_TX_QUEUES, f, ## a)
 #define IWL_DEBUG_RADIO(p, f, a...)	IWL_DEBUG(p, IWL_DL_RADIO, f, ## a)
+#define IWL_DEBUG_DEV_RADIO(p, f, a...)	IWL_DEBUG_DEV(p, IWL_DL_RADIO, f, ## a)
 #define IWL_DEBUG_POWER(p, f, a...)	IWL_DEBUG(p, IWL_DL_POWER, f, ## a)
 #define IWL_DEBUG_11H(p, f, a...)	IWL_DEBUG(p, IWL_DL_11H, f, ## a)
 #define IWL_DEBUG_RPM(p, f, a...)	IWL_DEBUG(p, IWL_DL_RPM, f, ## a)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 99676d6c4713..ccdb247d68c5 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -832,7 +832,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 			capa->standard_phy_calibration_size =
 					le32_to_cpup((__le32 *)tlv_data);
 			break;
-		 case IWL_UCODE_TLV_SEC_RT:
+		case IWL_UCODE_TLV_SEC_RT:
 			iwl_store_ucode_sec(pieces, tlv_data, IWL_UCODE_REGULAR,
 					    tlv_len);
 			drv->fw.type = IWL_FW_MVM;
@@ -864,7 +864,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 						FW_PHY_CFG_RX_CHAIN) >>
 						FW_PHY_CFG_RX_CHAIN_POS;
 			break;
-		 case IWL_UCODE_TLV_SECURE_SEC_RT:
+		case IWL_UCODE_TLV_SECURE_SEC_RT:
 			iwl_store_ucode_sec(pieces, tlv_data, IWL_UCODE_REGULAR,
 					    tlv_len);
 			drv->fw.type = IWL_FW_MVM;
@@ -1335,7 +1335,8 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 
 	/* Runtime instructions and 2 copies of data:
 	 * 1) unmodified from disk
-	 * 2) backup cache for save/restore during power-downs */
+	 * 2) backup cache for save/restore during power-downs
+	 */
 	for (i = 0; i < IWL_UCODE_TYPE_MAX; i++)
 		if (iwl_alloc_ucode(drv, pieces, i))
 			goto out_free_fw;
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index c3a5d8ccc95e..8928613e033e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -68,13 +68,14 @@
 #include <linux/export.h>
 #include <linux/etherdevice.h>
 #include <linux/pci.h>
-#include <linux/acpi.h>
+
 #include "iwl-drv.h"
 #include "iwl-modparams.h"
 #include "iwl-nvm-parse.h"
 #include "iwl-prph.h"
 #include "iwl-io.h"
 #include "iwl-csr.h"
+#include "fw/acpi.h"
 
 /* NVM offsets (in words) definitions */
 enum nvm_offsets {
@@ -937,91 +938,3 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 	return regd;
 }
 IWL_EXPORT_SYMBOL(iwl_parse_nvm_mcc_info);
-
-#ifdef CONFIG_ACPI
-#define WRDD_METHOD		"WRDD"
-#define WRDD_WIFI		(0x07)
-#define WRDD_WIGIG		(0x10)
-
-static u32 iwl_wrdd_get_mcc(struct device *dev, union acpi_object *wrdd)
-{
-	union acpi_object *mcc_pkg, *domain_type, *mcc_value;
-	u32 i;
-
-	if (wrdd->type != ACPI_TYPE_PACKAGE ||
-	    wrdd->package.count < 2 ||
-	    wrdd->package.elements[0].type != ACPI_TYPE_INTEGER ||
-	    wrdd->package.elements[0].integer.value != 0) {
-		IWL_DEBUG_EEPROM(dev, "Unsupported wrdd structure\n");
-		return 0;
-	}
-
-	for (i = 1 ; i < wrdd->package.count ; ++i) {
-		mcc_pkg = &wrdd->package.elements[i];
-
-		if (mcc_pkg->type != ACPI_TYPE_PACKAGE ||
-		    mcc_pkg->package.count < 2 ||
-		    mcc_pkg->package.elements[0].type != ACPI_TYPE_INTEGER ||
-		    mcc_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) {
-			mcc_pkg = NULL;
-			continue;
-		}
-
-		domain_type = &mcc_pkg->package.elements[0];
-		if (domain_type->integer.value == WRDD_WIFI)
-			break;
-
-		mcc_pkg = NULL;
-	}
-
-	if (mcc_pkg) {
-		mcc_value = &mcc_pkg->package.elements[1];
-		return mcc_value->integer.value;
-	}
-
-	return 0;
-}
-
-int iwl_get_bios_mcc(struct device *dev, char *mcc)
-{
-	acpi_handle root_handle;
-	acpi_handle handle;
-	struct acpi_buffer wrdd = {ACPI_ALLOCATE_BUFFER, NULL};
-	acpi_status status;
-	u32 mcc_val;
-
-	root_handle = ACPI_HANDLE(dev);
-	if (!root_handle) {
-		IWL_DEBUG_EEPROM(dev,
-				 "Could not retrieve root port ACPI handle\n");
-		return -ENOENT;
-	}
-
-	/* Get the method's handle */
-	status = acpi_get_handle(root_handle, (acpi_string)WRDD_METHOD,
-				 &handle);
-	if (ACPI_FAILURE(status)) {
-		IWL_DEBUG_EEPROM(dev, "WRD method not found\n");
-		return -ENOENT;
-	}
-
-	/* Call WRDD with no arguments */
-	status = acpi_evaluate_object(handle, NULL, NULL, &wrdd);
-	if (ACPI_FAILURE(status)) {
-		IWL_DEBUG_EEPROM(dev, "WRDC invocation failed (0x%x)\n",
-				 status);
-		return -ENOENT;
-	}
-
-	mcc_val = iwl_wrdd_get_mcc(dev, wrdd.pointer);
-	kfree(wrdd.pointer);
-	if (!mcc_val)
-		return -ENOENT;
-
-	mcc[0] = (mcc_val >> 8) & 0xff;
-	mcc[1] = mcc_val & 0xff;
-	mcc[2] = '\0';
-	return 0;
-}
-IWL_EXPORT_SYMBOL(iwl_get_bios_mcc);
-#endif
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
index 2d1a24dd8410..306736c7a042 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
@@ -109,21 +109,4 @@ struct ieee80211_regdomain *
 iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 		       int num_of_ch, __le32 *channels, u16 fw_mcc);
 
-#ifdef CONFIG_ACPI
-/**
- * iwl_get_bios_mcc - read MCC from BIOS, if available
- *
- * @dev: the struct device
- * @mcc: output buffer (3 bytes) that will get the MCC
- *
- * This function tries to read the current MCC from ACPI if available.
- */
-int iwl_get_bios_mcc(struct device *dev, char *mcc);
-#else
-static inline int iwl_get_bios_mcc(struct device *dev, char *mcc)
-{
-	return -ENOENT;
-}
-#endif
-
 #endif /* __iwl_nvm_parse_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index 784bdd0ed233..7e9c924e1220 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -6,6 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,6 +32,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -205,3 +207,17 @@ int iwl_cmd_groups_verify_sorted(const struct iwl_trans_config *trans)
 	return 0;
 }
 IWL_EXPORT_SYMBOL(iwl_cmd_groups_verify_sorted);
+
+void iwl_trans_ref(struct iwl_trans *trans)
+{
+	if (trans->ops->ref)
+		trans->ops->ref(trans);
+}
+IWL_EXPORT_SYMBOL(iwl_trans_ref);
+
+void iwl_trans_unref(struct iwl_trans *trans)
+{
+	if (trans->ops->unref)
+		trans->ops->unref(trans);
+}
+IWL_EXPORT_SYMBOL(iwl_trans_unref);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index e90abbfba718..bba4f54cbbbb 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -749,8 +749,6 @@ struct iwl_trans {
 	struct lockdep_map sync_cmd_lockdep_map;
 #endif
 
-	u64 dflt_pwr_limit;
-
 	const struct iwl_fw_dbg_dest_tlv *dbg_dest_tlv;
 	const struct iwl_fw_dbg_conf_tlv *dbg_conf_tlv[FW_DBG_CONF_MAX];
 	struct iwl_fw_dbg_trigger_tlv * const *dbg_trigger_tlv;
@@ -875,18 +873,6 @@ static inline int iwl_trans_d3_resume(struct iwl_trans *trans,
 	return trans->ops->d3_resume(trans, status, test, reset);
 }
 
-static inline void iwl_trans_ref(struct iwl_trans *trans)
-{
-	if (trans->ops->ref)
-		trans->ops->ref(trans);
-}
-
-static inline void iwl_trans_unref(struct iwl_trans *trans)
-{
-	if (trans->ops->unref)
-		trans->ops->unref(trans);
-}
-
 static inline int iwl_trans_suspend(struct iwl_trans *trans)
 {
 	if (!trans->ops->suspend)
@@ -1191,6 +1177,8 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 				  const struct iwl_cfg *cfg,
 				  const struct iwl_trans_ops *ops);
 void iwl_trans_free(struct iwl_trans *trans);
+void iwl_trans_ref(struct iwl_trans *trans);
+void iwl_trans_unref(struct iwl_trans *trans);
 
 /*****************************************************
 * driver (transport) register/unregister functions
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index b205a7bfb828..b1f73dcabd31 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -664,6 +664,7 @@ static int iwl_mvm_d3_reprogram(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	int ret, i;
 	struct iwl_binding_cmd binding_cmd = {};
 	struct iwl_time_quota_cmd quota_cmd = {};
+	struct iwl_time_quota_data *quota;
 	u32 status;
 	int size;
 
@@ -745,17 +746,20 @@ static int iwl_mvm_d3_reprogram(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		return ret;
 
 	/* and some quota */
-	quota_cmd.quotas[0].id_and_color =
+	quota = iwl_mvm_quota_cmd_get_quota(mvm, &quota_cmd, 0);
+	quota->id_and_color =
 		cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->phy_ctxt->id,
 						mvmvif->phy_ctxt->color));
-	quota_cmd.quotas[0].quota = cpu_to_le32(IWL_MVM_MAX_QUOTA);
-	quota_cmd.quotas[0].max_duration = cpu_to_le32(IWL_MVM_MAX_QUOTA);
+	quota->quota = cpu_to_le32(IWL_MVM_MAX_QUOTA);
+	quota->max_duration = cpu_to_le32(IWL_MVM_MAX_QUOTA);
 
-	for (i = 1; i < MAX_BINDINGS; i++)
-		quota_cmd.quotas[i].id_and_color = cpu_to_le32(FW_CTXT_INVALID);
+	for (i = 1; i < MAX_BINDINGS; i++) {
+		quota = iwl_mvm_quota_cmd_get_quota(mvm, &quota_cmd, i);
+		quota->id_and_color = cpu_to_le32(FW_CTXT_INVALID);
+	}
 
 	ret = iwl_mvm_send_cmd_pdu(mvm, TIME_QUOTA_CMD, 0,
-				   sizeof(quota_cmd), &quota_cmd);
+				   iwl_mvm_quota_cmd_size(mvm), &quota_cmd);
 	if (ret)
 		IWL_ERR(mvm, "Failed to send quota: %d\n", ret);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
index 71a01df96f8b..4228fac77f41 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
@@ -1455,80 +1455,6 @@ static const char * const chanwidths[] = {
 	[NL80211_CHAN_WIDTH_160] = "vht160",
 };
 
-static bool iwl_mvm_lqm_notif_wait(struct iwl_notif_wait_data *notif_wait,
-				   struct iwl_rx_packet *pkt, void *data)
-{
-	struct ieee80211_vif *vif = data;
-	struct iwl_mvm *mvm =
-		container_of(notif_wait, struct iwl_mvm, notif_wait);
-	struct iwl_link_qual_msrmnt_notif *report = (void *)pkt->data;
-	u32 num_of_stations = le32_to_cpu(report->number_of_stations);
-	int i;
-
-	IWL_INFO(mvm, "LQM report:\n");
-	IWL_INFO(mvm, "\tstatus: %d\n", report->status);
-	IWL_INFO(mvm, "\tmacID: %d\n", le32_to_cpu(report->mac_id));
-	IWL_INFO(mvm, "\ttx_frame_dropped: %d\n",
-		 le32_to_cpu(report->tx_frame_dropped));
-	IWL_INFO(mvm, "\ttime_in_measurement_window: %d us\n",
-		 le32_to_cpu(report->time_in_measurement_window));
-	IWL_INFO(mvm, "\ttotal_air_time_other_stations: %d\n",
-		 le32_to_cpu(report->total_air_time_other_stations));
-	IWL_INFO(mvm, "\tchannel_freq: %d\n",
-		 vif->bss_conf.chandef.center_freq1);
-	IWL_INFO(mvm, "\tchannel_width: %s\n",
-		 chanwidths[vif->bss_conf.chandef.width]);
-	IWL_INFO(mvm, "\tnumber_of_stations: %d\n", num_of_stations);
-	for (i = 0; i < num_of_stations; i++)
-		IWL_INFO(mvm, "\t\tsta[%d]: %d\n", i,
-			 report->frequent_stations_air_time[i]);
-
-	return true;
-}
-
-static ssize_t iwl_dbgfs_lqm_send_cmd_write(struct ieee80211_vif *vif,
-					    char *buf, size_t count,
-					    loff_t *ppos)
-{
-	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	struct iwl_mvm *mvm = mvmvif->mvm;
-	struct iwl_notification_wait wait_lqm_notif;
-	static u16 lqm_notif[] = {
-		WIDE_ID(MAC_CONF_GROUP,
-			LINK_QUALITY_MEASUREMENT_COMPLETE_NOTIF)
-	};
-	int err;
-	u32 duration;
-	u32 timeout;
-
-	if (sscanf(buf, "%d,%d", &duration, &timeout) != 2)
-		return -EINVAL;
-
-	iwl_init_notification_wait(&mvm->notif_wait, &wait_lqm_notif,
-				   lqm_notif, ARRAY_SIZE(lqm_notif),
-				   iwl_mvm_lqm_notif_wait, vif);
-	mutex_lock(&mvm->mutex);
-	err = iwl_mvm_send_lqm_cmd(vif, LQM_CMD_OPERATION_START_MEASUREMENT,
-				   duration, timeout);
-	mutex_unlock(&mvm->mutex);
-
-	if (err) {
-		IWL_ERR(mvm, "Failed to send lqm cmdf(err=%d)\n", err);
-		iwl_remove_notification(&mvm->notif_wait, &wait_lqm_notif);
-		return err;
-	}
-
-	/* wait for 2 * timeout (safety guard) and convert to jiffies*/
-	timeout = msecs_to_jiffies((timeout * 2) / 1000);
-
-	err = iwl_wait_notification(&mvm->notif_wait, &wait_lqm_notif,
-				    timeout);
-	if (err)
-		IWL_ERR(mvm, "Getting lqm notif timed out\n");
-
-	return count;
-}
-
 #define MVM_DEBUGFS_WRITE_FILE_OPS(name, bufsz) \
 	_MVM_DEBUGFS_WRITE_FILE_OPS(name, bufsz, struct ieee80211_vif)
 #define MVM_DEBUGFS_READ_WRITE_FILE_OPS(name, bufsz) \
@@ -1553,7 +1479,6 @@ MVM_DEBUGFS_READ_WRITE_FILE_OPS(tof_range_abort, 32);
 MVM_DEBUGFS_READ_FILE_OPS(tof_range_response);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(tof_responder_params, 32);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(quota_min, 32);
-MVM_DEBUGFS_WRITE_FILE_OPS(lqm_send_cmd, 64);
 MVM_DEBUGFS_READ_FILE_OPS(os_device_timediff);
 
 
@@ -1594,7 +1519,6 @@ void iwl_mvm_vif_dbgfs_register(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 				 S_IRUSR | S_IWUSR);
 	MVM_DEBUGFS_ADD_FILE_VIF(quota_min, mvmvif->dbgfs_dir,
 				 S_IRUSR | S_IWUSR);
-	MVM_DEBUGFS_ADD_FILE_VIF(lqm_send_cmd, mvmvif->dbgfs_dir, S_IWUSR);
 	MVM_DEBUGFS_ADD_FILE_VIF(os_device_timediff,
 				 mvmvif->dbgfs_dir, S_IRUSR);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index e97904c2c4d4..2ff594f11259 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -660,6 +660,36 @@ out:
 	return ret ?: count;
 }
 
+static ssize_t iwl_dbgfs_fw_ver_read(struct file *file, char __user *user_buf,
+				     size_t count, loff_t *ppos)
+{
+	struct iwl_mvm *mvm = file->private_data;
+	char *buff, *pos, *endpos;
+	static const size_t bufsz = 1024;
+	int ret;
+
+	buff = kmalloc(bufsz, GFP_KERNEL);
+	if (!buff)
+		return -ENOMEM;
+
+	pos = buff;
+	endpos = pos + bufsz;
+
+	pos += scnprintf(pos, endpos - pos, "FW prefix: %s\n",
+			 mvm->trans->cfg->fw_name_pre);
+	pos += scnprintf(pos, endpos - pos, "FW: %s\n",
+			 mvm->fwrt.fw->human_readable);
+	pos += scnprintf(pos, endpos - pos, "Device: %s\n",
+			 mvm->fwrt.trans->cfg->name);
+	pos += scnprintf(pos, endpos - pos, "Bus: %s\n",
+			 mvm->fwrt.dev->bus->name);
+
+	ret = simple_read_from_buffer(user_buf, count, ppos, buff, pos - buff);
+	kfree(buff);
+
+	return ret;
+}
+
 #define PRINT_STATS_LE32(_struct, _memb)				\
 			 pos += scnprintf(buf + pos, bufsz - pos,	\
 					  fmt_table, #_memb,		\
@@ -1662,6 +1692,7 @@ MVM_DEBUGFS_READ_FILE_OPS(bt_cmd);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(disable_power_off, 64);
 MVM_DEBUGFS_READ_FILE_OPS(fw_rx_stats);
 MVM_DEBUGFS_READ_FILE_OPS(drv_rx_stats);
+MVM_DEBUGFS_READ_FILE_OPS(fw_ver);
 MVM_DEBUGFS_WRITE_FILE_OPS(fw_restart, 10);
 MVM_DEBUGFS_WRITE_FILE_OPS(fw_nmi, 10);
 MVM_DEBUGFS_WRITE_FILE_OPS(bt_tx_prio, 10);
@@ -1843,6 +1874,7 @@ int iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir)
 	MVM_DEBUGFS_ADD_FILE(bt_cmd, dbgfs_dir, S_IRUSR);
 	MVM_DEBUGFS_ADD_FILE(disable_power_off, mvm->debugfs_dir,
 			     S_IRUSR | S_IWUSR);
+	MVM_DEBUGFS_ADD_FILE(fw_ver, mvm->debugfs_dir, S_IRUSR);
 	MVM_DEBUGFS_ADD_FILE(fw_rx_stats, mvm->debugfs_dir, S_IRUSR);
 	MVM_DEBUGFS_ADD_FILE(drv_rx_stats, mvm->debugfs_dir, S_IRUSR);
 	MVM_DEBUGFS_ADD_FILE(fw_restart, mvm->debugfs_dir, S_IWUSR);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 83485493a79a..f476882291ae 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -66,7 +66,6 @@
  *****************************************************************************/
 #include <net/mac80211.h>
 #include <linux/netdevice.h>
-#include <linux/acpi.h>
 
 #include "iwl-trans.h"
 #include "iwl-op-mode.h"
@@ -75,7 +74,7 @@
 #include "iwl-csr.h" /* for iwl_mvm_rx_card_state_notif */
 #include "iwl-io.h" /* for iwl_mvm_rx_card_state_notif */
 #include "iwl-prph.h"
-#include "iwl-eeprom-parse.h"
+#include "fw/acpi.h"
 
 #include "mvm.h"
 #include "fw/dbg.h"
@@ -579,17 +578,6 @@ static int iwl_mvm_config_ltr(struct iwl_mvm *mvm)
 }
 
 #ifdef CONFIG_ACPI
-#define ACPI_WRDS_METHOD		"WRDS"
-#define ACPI_EWRD_METHOD		"EWRD"
-#define ACPI_WGDS_METHOD		"WGDS"
-#define ACPI_WIFI_DOMAIN		(0x07)
-#define ACPI_WRDS_WIFI_DATA_SIZE	(IWL_MVM_SAR_TABLE_SIZE + 2)
-#define ACPI_EWRD_WIFI_DATA_SIZE	((IWL_MVM_SAR_PROFILE_NUM - 1) * \
-					 IWL_MVM_SAR_TABLE_SIZE + 3)
-#define ACPI_WGDS_WIFI_DATA_SIZE	18
-#define ACPI_WGDS_NUM_BANDS		2
-#define ACPI_WGDS_TABLE_SIZE		3
-
 static int iwl_mvm_sar_set_profile(struct iwl_mvm *mvm,
 				   union acpi_object *table,
 				   struct iwl_mvm_sar_profile *profile,
@@ -599,7 +587,7 @@ static int iwl_mvm_sar_set_profile(struct iwl_mvm *mvm,
 
 	profile->enabled = enabled;
 
-	for (i = 0; i < IWL_MVM_SAR_TABLE_SIZE; i++) {
+	for (i = 0; i < ACPI_SAR_TABLE_SIZE; i++) {
 		if ((table[i].type != ACPI_TYPE_INTEGER) ||
 		    (table[i].integer.value > U8_MAX))
 			return -EINVAL;
@@ -610,88 +598,18 @@ static int iwl_mvm_sar_set_profile(struct iwl_mvm *mvm,
 	return 0;
 }
 
-static union acpi_object *iwl_mvm_sar_find_wifi_pkg(struct iwl_mvm *mvm,
-						    union acpi_object *data,
-						    int data_size)
-{
-	union acpi_object *wifi_pkg = NULL;
-	int i;
-
-	/*
-	 * We need at least two packages, one for the revision and one
-	 * for the data itself.  Also check that the revision is valid
-	 * (i.e. it is an integer set to 0).
-	 */
-	if (data->type != ACPI_TYPE_PACKAGE ||
-	    data->package.count < 2 ||
-	    data->package.elements[0].type != ACPI_TYPE_INTEGER ||
-	    data->package.elements[0].integer.value != 0) {
-		IWL_DEBUG_RADIO(mvm, "Unsupported packages structure\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	/* loop through all the packages to find the one for WiFi */
-	for (i = 1; i < data->package.count; i++) {
-		union acpi_object *domain;
-
-		wifi_pkg = &data->package.elements[i];
-
-		/* Skip anything that is not a package with the right
-		 * amount of elements (i.e. domain_type,
-		 * enabled/disabled plus the actual data size.
-		 */
-		if (wifi_pkg->type != ACPI_TYPE_PACKAGE ||
-		    wifi_pkg->package.count != data_size)
-			continue;
-
-		domain = &wifi_pkg->package.elements[0];
-		if (domain->type == ACPI_TYPE_INTEGER &&
-		    domain->integer.value == ACPI_WIFI_DOMAIN)
-			break;
-
-		wifi_pkg = NULL;
-	}
-
-	if (!wifi_pkg)
-		return ERR_PTR(-ENOENT);
-
-	return wifi_pkg;
-}
-
 static int iwl_mvm_sar_get_wrds_table(struct iwl_mvm *mvm)
 {
-	union acpi_object *wifi_pkg, *table;
-	acpi_handle root_handle;
-	acpi_handle handle;
-	struct acpi_buffer wrds = {ACPI_ALLOCATE_BUFFER, NULL};
-	acpi_status status;
+	union acpi_object *wifi_pkg, *table, *data;
 	bool enabled;
 	int ret;
 
-	root_handle = ACPI_HANDLE(mvm->dev);
-	if (!root_handle) {
-		IWL_DEBUG_RADIO(mvm,
-				"Could not retrieve root port ACPI handle\n");
-		return -ENOENT;
-	}
-
-	/* Get the method's handle */
-	status = acpi_get_handle(root_handle, (acpi_string)ACPI_WRDS_METHOD,
-				 &handle);
-	if (ACPI_FAILURE(status)) {
-		IWL_DEBUG_RADIO(mvm, "WRDS method not found\n");
-		return -ENOENT;
-	}
-
-	/* Call WRDS with no arguments */
-	status = acpi_evaluate_object(handle, NULL, NULL, &wrds);
-	if (ACPI_FAILURE(status)) {
-		IWL_DEBUG_RADIO(mvm, "WRDS invocation failed (0x%x)\n", status);
-		return -ENOENT;
-	}
+	data = iwl_acpi_get_object(mvm->dev, ACPI_WRDS_METHOD);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
-	wifi_pkg = iwl_mvm_sar_find_wifi_pkg(mvm, wrds.pointer,
-					     ACPI_WRDS_WIFI_DATA_SIZE);
+	wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data,
+					 ACPI_WRDS_WIFI_DATA_SIZE);
 	if (IS_ERR(wifi_pkg)) {
 		ret = PTR_ERR(wifi_pkg);
 		goto out_free;
@@ -712,46 +630,23 @@ static int iwl_mvm_sar_get_wrds_table(struct iwl_mvm *mvm)
 	 */
 	ret = iwl_mvm_sar_set_profile(mvm, table, &mvm->sar_profiles[0],
 				      enabled);
-
 out_free:
-	kfree(wrds.pointer);
+	kfree(data);
 	return ret;
 }
 
 static int iwl_mvm_sar_get_ewrd_table(struct iwl_mvm *mvm)
 {
-	union acpi_object *wifi_pkg;
-	acpi_handle root_handle;
-	acpi_handle handle;
-	struct acpi_buffer ewrd = {ACPI_ALLOCATE_BUFFER, NULL};
-	acpi_status status;
+	union acpi_object *wifi_pkg, *data;
 	bool enabled;
 	int i, n_profiles, ret;
 
-	root_handle = ACPI_HANDLE(mvm->dev);
-	if (!root_handle) {
-		IWL_DEBUG_RADIO(mvm,
-				"Could not retrieve root port ACPI handle\n");
-		return -ENOENT;
-	}
-
-	/* Get the method's handle */
-	status = acpi_get_handle(root_handle, (acpi_string)ACPI_EWRD_METHOD,
-				 &handle);
-	if (ACPI_FAILURE(status)) {
-		IWL_DEBUG_RADIO(mvm, "EWRD method not found\n");
-		return -ENOENT;
-	}
+	data = iwl_acpi_get_object(mvm->dev, ACPI_EWRD_METHOD);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
-	/* Call EWRD with no arguments */
-	status = acpi_evaluate_object(handle, NULL, NULL, &ewrd);
-	if (ACPI_FAILURE(status)) {
-		IWL_DEBUG_RADIO(mvm, "EWRD invocation failed (0x%x)\n", status);
-		return -ENOENT;
-	}
-
-	wifi_pkg = iwl_mvm_sar_find_wifi_pkg(mvm, ewrd.pointer,
-					     ACPI_EWRD_WIFI_DATA_SIZE);
+	wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data,
+					 ACPI_EWRD_WIFI_DATA_SIZE);
 	if (IS_ERR(wifi_pkg)) {
 		ret = PTR_ERR(wifi_pkg);
 		goto out_free;
@@ -788,55 +683,33 @@ static int iwl_mvm_sar_get_ewrd_table(struct iwl_mvm *mvm)
 			break;
 
 		/* go to the next table */
-		pos += IWL_MVM_SAR_TABLE_SIZE;
+		pos += ACPI_SAR_TABLE_SIZE;
 	}
 
 out_free:
-	kfree(ewrd.pointer);
+	kfree(data);
 	return ret;
 }
 
 static int iwl_mvm_sar_get_wgds_table(struct iwl_mvm *mvm)
 {
-	union acpi_object *wifi_pkg;
-	acpi_handle root_handle;
-	acpi_handle handle;
-	struct acpi_buffer wgds = {ACPI_ALLOCATE_BUFFER, NULL};
-	acpi_status status;
+	union acpi_object *wifi_pkg, *data;
 	int i, j, ret;
 	int idx = 1;
 
-	root_handle = ACPI_HANDLE(mvm->dev);
-	if (!root_handle) {
-		IWL_DEBUG_RADIO(mvm,
-				"Could not retrieve root port ACPI handle\n");
-		return -ENOENT;
-	}
+	data = iwl_acpi_get_object(mvm->dev, ACPI_WGDS_METHOD);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
-	/* Get the method's handle */
-	status = acpi_get_handle(root_handle, (acpi_string)ACPI_WGDS_METHOD,
-				 &handle);
-	if (ACPI_FAILURE(status)) {
-		IWL_DEBUG_RADIO(mvm, "WGDS method not found\n");
-		return -ENOENT;
-	}
-
-	/* Call WGDS with no arguments */
-	status = acpi_evaluate_object(handle, NULL, NULL, &wgds);
-	if (ACPI_FAILURE(status)) {
-		IWL_DEBUG_RADIO(mvm, "WGDS invocation failed (0x%x)\n", status);
-		return -ENOENT;
-	}
-
-	wifi_pkg = iwl_mvm_sar_find_wifi_pkg(mvm, wgds.pointer,
-					     ACPI_WGDS_WIFI_DATA_SIZE);
+	wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data,
+					 ACPI_WGDS_WIFI_DATA_SIZE);
 	if (IS_ERR(wifi_pkg)) {
 		ret = PTR_ERR(wifi_pkg);
 		goto out_free;
 	}
 
-	for (i = 0; i < IWL_NUM_GEO_PROFILES; i++) {
-		for (j = 0; j < IWL_MVM_GEO_TABLE_SIZE; j++) {
+	for (i = 0; i < ACPI_NUM_GEO_PROFILES; i++) {
+		for (j = 0; j < ACPI_GEO_TABLE_SIZE; j++) {
 			union acpi_object *entry;
 
 			entry = &wifi_pkg->package.elements[idx++];
@@ -851,7 +724,7 @@ static int iwl_mvm_sar_get_wgds_table(struct iwl_mvm *mvm)
 	}
 	ret = 0;
 out_free:
-	kfree(wgds.pointer);
+	kfree(data);
 	return ret;
 }
 
@@ -861,25 +734,25 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 		.v3.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_CHAINS),
 	};
 	int i, j, idx;
-	int profs[IWL_NUM_CHAIN_LIMITS] = { prof_a, prof_b };
+	int profs[ACPI_SAR_NUM_CHAIN_LIMITS] = { prof_a, prof_b };
 	int len = sizeof(cmd);
 
-	BUILD_BUG_ON(IWL_NUM_CHAIN_LIMITS < 2);
-	BUILD_BUG_ON(IWL_NUM_CHAIN_LIMITS * IWL_NUM_SUB_BANDS !=
-		     IWL_MVM_SAR_TABLE_SIZE);
+	BUILD_BUG_ON(ACPI_SAR_NUM_CHAIN_LIMITS < 2);
+	BUILD_BUG_ON(ACPI_SAR_NUM_CHAIN_LIMITS * ACPI_SAR_NUM_SUB_BANDS !=
+		     ACPI_SAR_TABLE_SIZE);
 
 	if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_TX_POWER_ACK))
 		len = sizeof(cmd.v3);
 
-	for (i = 0; i < IWL_NUM_CHAIN_LIMITS; i++) {
+	for (i = 0; i < ACPI_SAR_NUM_CHAIN_LIMITS; i++) {
 		struct iwl_mvm_sar_profile *prof;
 
 		/* don't allow SAR to be disabled (profile 0 means disable) */
 		if (profs[i] == 0)
 			return -EPERM;
 
-		/* we are off by one, so allow up to IWL_MVM_SAR_PROFILE_NUM */
-		if (profs[i] > IWL_MVM_SAR_PROFILE_NUM)
+		/* we are off by one, so allow up to ACPI_SAR_PROFILE_NUM */
+		if (profs[i] > ACPI_SAR_PROFILE_NUM)
 			return -EINVAL;
 
 		/* profiles go from 1 to 4, so decrement to access the array */
@@ -894,8 +767,8 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 		}
 
 		IWL_DEBUG_RADIO(mvm, "  Chain[%d]:\n", i);
-		for (j = 0; j < IWL_NUM_SUB_BANDS; j++) {
-			idx = (i * IWL_NUM_SUB_BANDS) + j;
+		for (j = 0; j < ACPI_SAR_NUM_SUB_BANDS; j++) {
+			idx = (i * ACPI_SAR_NUM_SUB_BANDS) + j;
 			cmd.v3.per_chain_restriction[i][j] =
 				cpu_to_le16(prof->table[idx]);
 			IWL_DEBUG_RADIO(mvm, "    Band[%d] = %d * .125dBm\n",
@@ -931,7 +804,7 @@ int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm)
 
 	resp = (void *)cmd.resp_pkt->data;
 	ret = le32_to_cpu(resp->profile_idx);
-	if (WARN_ON(ret > IWL_NUM_GEO_PROFILES)) {
+	if (WARN_ON(ret > ACPI_NUM_GEO_PROFILES)) {
 		ret = -EIO;
 		IWL_WARN(mvm, "Invalid geographic profile idx (%d)\n", ret);
 	}
@@ -959,10 +832,12 @@ static int iwl_mvm_sar_geo_init(struct iwl_mvm *mvm)
 
 	IWL_DEBUG_RADIO(mvm, "Sending GEO_TX_POWER_LIMIT\n");
 
-	BUILD_BUG_ON(IWL_NUM_GEO_PROFILES * ACPI_WGDS_NUM_BANDS *
+	BUILD_BUG_ON(ACPI_NUM_GEO_PROFILES * ACPI_WGDS_NUM_BANDS *
 		     ACPI_WGDS_TABLE_SIZE !=  ACPI_WGDS_WIFI_DATA_SIZE);
 
-	for (i = 0; i < IWL_NUM_GEO_PROFILES; i++) {
+	BUILD_BUG_ON(ACPI_NUM_GEO_PROFILES > IWL_NUM_GEO_PROFILES);
+
+	for (i = 0; i < ACPI_NUM_GEO_PROFILES; i++) {
 		struct iwl_per_chain_offset *chain =
 			(struct iwl_per_chain_offset *)&cmd.table[i];
 
@@ -970,7 +845,7 @@ static int iwl_mvm_sar_geo_init(struct iwl_mvm *mvm)
 			u8 *value;
 
 			value = &mvm->geo_profiles[i].values[j *
-				IWL_GEO_PER_CHAIN_SIZE];
+				ACPI_GEO_PER_CHAIN_SIZE];
 			chain[j].max_tx_power = cpu_to_le16(value[0]);
 			chain[j].chain_a = value[1];
 			chain[j].chain_b = value[2];
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index a9ac872226fd..0b3d275fe177 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1899,11 +1899,6 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 	if (changes & BSS_CHANGED_ASSOC && bss_conf->assoc)
 		iwl_mvm_mac_ctxt_recalc_tsf_id(mvm, vif);
 
-	if (changes & BSS_CHANGED_ASSOC && !bss_conf->assoc &&
-	    mvmvif->lqm_active)
-		iwl_mvm_send_lqm_cmd(vif, LQM_CMD_OPERATION_STOP_MEASUREMENT,
-				     0, 0);
-
 	/*
 	 * If we're not associated yet, take the (new) BSSID before associating
 	 * so the firmware knows. If we're already associated, then use the old
@@ -3432,10 +3427,24 @@ static void iwl_mvm_change_chanctx(struct ieee80211_hw *hw,
 		return;
 
 	mutex_lock(&mvm->mutex);
+
+	/* we are only changing the min_width, may be a noop */
+	if (changed == IEEE80211_CHANCTX_CHANGE_MIN_WIDTH) {
+		if (phy_ctxt->width == ctx->min_def.width)
+			goto out_unlock;
+
+		/* we are just toggling between 20_NOHT and 20 */
+		if (phy_ctxt->width <= NL80211_CHAN_WIDTH_20 &&
+		    ctx->min_def.width <= NL80211_CHAN_WIDTH_20)
+			goto out_unlock;
+	}
+
 	iwl_mvm_bt_coex_vif_change(mvm);
 	iwl_mvm_phy_ctxt_changed(mvm, phy_ctxt, &ctx->min_def,
 				 ctx->rx_chains_static,
 				 ctx->rx_chains_dynamic);
+
+out_unlock:
 	mutex_unlock(&mvm->mutex);
 }
 
@@ -3900,11 +3909,6 @@ static int iwl_mvm_pre_channel_switch(struct ieee80211_hw *hw,
 
 		break;
 	case NL80211_IFTYPE_STATION:
-		if (mvmvif->lqm_active)
-			iwl_mvm_send_lqm_cmd(vif,
-					     LQM_CMD_OPERATION_STOP_MEASUREMENT,
-					     0, 0);
-
 		/* Schedule the time event to a bit before beacon 1,
 		 * to make sure we're in the new channel when the
 		 * GO/AP arrives. In case count <= 1 immediately schedule the
@@ -4259,31 +4263,6 @@ static void iwl_mvm_event_bar_rx_callback(struct iwl_mvm *mvm,
 				event->u.ba.ssn);
 }
 
-static void
-iwl_mvm_event_frame_timeout_callback(struct iwl_mvm *mvm,
-				     struct ieee80211_vif *vif,
-				     const struct ieee80211_event *event)
-{
-	struct iwl_fw_dbg_trigger_tlv *trig;
-	struct iwl_fw_dbg_trigger_ba *ba_trig;
-
-	if (!iwl_fw_dbg_trigger_enabled(mvm->fw, FW_DBG_TRIGGER_BA))
-		return;
-
-	trig = iwl_fw_dbg_get_trigger(mvm->fw, FW_DBG_TRIGGER_BA);
-	ba_trig = (void *)trig->data;
-	if (!iwl_fw_dbg_trigger_check_stop(&mvm->fwrt,
-					   ieee80211_vif_to_wdev(vif), trig))
-		return;
-
-	if (!(le16_to_cpu(ba_trig->frame_timeout) & BIT(event->u.ba.tid)))
-		return;
-
-	iwl_fw_dbg_collect_trig(&mvm->fwrt, trig,
-				"Frame from %pM timed out, tid %d",
-				event->u.ba.sta->addr, event->u.ba.tid);
-}
-
 static void iwl_mvm_mac_event_callback(struct ieee80211_hw *hw,
 				       struct ieee80211_vif *vif,
 				       const struct ieee80211_event *event)
@@ -4298,7 +4277,8 @@ static void iwl_mvm_mac_event_callback(struct ieee80211_hw *hw,
 		iwl_mvm_event_bar_rx_callback(mvm, vif, event);
 		break;
 	case BA_FRAME_TIMEOUT:
-		iwl_mvm_event_frame_timeout_callback(mvm, vif, event);
+		iwl_mvm_event_frame_timeout_callback(mvm, vif, event->u.ba.sta,
+						     event->u.ba.tid);
 		break;
 	default:
 		break;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 949e63418299..bf25c3ce7c95 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -89,6 +89,7 @@
 #include "tof.h"
 #include "fw/runtime.h"
 #include "fw/dbg.h"
+#include "fw/acpi.h"
 
 #define IWL_MVM_MAX_ADDRESSES		5
 /* RSSI offset for WkP */
@@ -147,6 +148,8 @@ struct iwl_mvm_phy_ctxt {
 	u16 color;
 	u32 ref;
 
+	enum nl80211_chan_width width;
+
 	/*
 	 * TODO: This should probably be removed. Currently here only for rate
 	 * scaling algorithm
@@ -436,12 +439,6 @@ struct iwl_mvm_vif {
 
 	/* TCP Checksum Offload */
 	netdev_features_t features;
-
-	/*
-	 * link quality measurement - used to check whether this interface
-	 * is in the middle of a link quality measurement
-	 */
-	bool lqm_active;
 };
 
 static inline struct iwl_mvm_vif *
@@ -592,6 +589,7 @@ enum iwl_mvm_tdls_cs_state {
  * @queue: queue of this reorder buffer
  * @last_amsdu: track last ASMDU SN for duplication detection
  * @last_sub_index: track ASMDU sub frame index for duplication detection
+ * @tid: the tid
  * @entries: list of skbs stored
  * @reorder_time: time the packet was stored in the reorder buffer
  * @reorder_timer: timer for frames are in the reorder buffer. For AMSDU
@@ -609,6 +607,7 @@ struct iwl_mvm_reorder_buffer {
 	int queue;
 	u16 last_amsdu;
 	u8 last_sub_index;
+	u8 tid;
 	struct sk_buff_head entries[IEEE80211_MAX_AMPDU_BUF];
 	unsigned long reorder_time[IEEE80211_MAX_AMPDU_BUF];
 	struct timer_list reorder_timer;
@@ -685,20 +684,14 @@ enum iwl_mvm_queue_status {
 
 #define IWL_MVM_NUM_CIPHERS             10
 
-#ifdef CONFIG_ACPI
-#define IWL_MVM_SAR_TABLE_SIZE		10
-#define IWL_MVM_SAR_PROFILE_NUM		4
-#define IWL_MVM_GEO_TABLE_SIZE		6
-
 struct iwl_mvm_sar_profile {
 	bool enabled;
-	u8 table[IWL_MVM_SAR_TABLE_SIZE];
+	u8 table[ACPI_SAR_TABLE_SIZE];
 };
 
 struct iwl_mvm_geo_profile {
-	u8 values[IWL_MVM_GEO_TABLE_SIZE];
+	u8 values[ACPI_GEO_TABLE_SIZE];
 };
-#endif
 
 struct iwl_mvm {
 	/* for logger access */
@@ -1019,8 +1012,8 @@ struct iwl_mvm {
 	/* does a monitor vif exist (only one can exist hence bool) */
 	bool monitor_on;
 #ifdef CONFIG_ACPI
-	struct iwl_mvm_sar_profile sar_profiles[IWL_MVM_SAR_PROFILE_NUM];
-	struct iwl_mvm_geo_profile geo_profiles[IWL_NUM_GEO_PROFILES];
+	struct iwl_mvm_sar_profile sar_profiles[ACPI_SAR_PROFILE_NUM];
+	struct iwl_mvm_geo_profile geo_profiles[ACPI_NUM_GEO_PROFILES];
 #endif
 };
 
@@ -1251,6 +1244,12 @@ static inline bool iwl_mvm_has_new_ats_coex_api(struct iwl_mvm *mvm)
 			  IWL_UCODE_TLV_API_COEX_ATS_EXTERNAL);
 }
 
+static inline bool iwl_mvm_has_quota_low_latency(struct iwl_mvm *mvm)
+{
+	return fw_has_api(&mvm->fw->ucode_capa,
+			  IWL_UCODE_TLV_API_QUOTA_LOW_LATENCY);
+}
+
 static inline struct agg_tx_status *
 iwl_mvm_get_agg_status(struct iwl_mvm *mvm, void *tx_resp)
 {
@@ -1489,6 +1488,27 @@ int iwl_mvm_binding_add_vif(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 int iwl_mvm_binding_remove_vif(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 
 /* Quota management */
+static inline size_t iwl_mvm_quota_cmd_size(struct iwl_mvm *mvm)
+{
+	return iwl_mvm_has_quota_low_latency(mvm) ?
+		sizeof(struct iwl_time_quota_cmd) :
+		sizeof(struct iwl_time_quota_cmd_v1);
+}
+
+static inline struct iwl_time_quota_data
+*iwl_mvm_quota_cmd_get_quota(struct iwl_mvm *mvm,
+			     struct iwl_time_quota_cmd *cmd,
+			     int i)
+{
+	struct iwl_time_quota_data_v1 *quotas;
+
+	if (iwl_mvm_has_quota_low_latency(mvm))
+		return &cmd->quotas[i];
+
+	quotas = (struct iwl_time_quota_data_v1 *)cmd->quotas;
+	return (struct iwl_time_quota_data *)&quotas[i];
+}
+
 int iwl_mvm_update_quotas(struct iwl_mvm *mvm, bool force_upload,
 			  struct ieee80211_vif *disabled_vif);
 
@@ -1821,12 +1841,10 @@ unsigned int iwl_mvm_get_wd_timeout(struct iwl_mvm *mvm,
 				    bool tdls, bool cmd_q);
 void iwl_mvm_connection_loss(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			     const char *errmsg);
-
-/* Link Quality Measurement */
-int iwl_mvm_send_lqm_cmd(struct ieee80211_vif *vif,
-			 enum iwl_lqm_cmd_operatrions operation,
-			 u32 duration, u32 timeout);
-bool iwl_mvm_lqm_active(struct iwl_mvm *mvm);
+void iwl_mvm_event_frame_timeout_callback(struct iwl_mvm *mvm,
+					  struct ieee80211_vif *vif,
+					  const struct ieee80211_sta *sta,
+					  u16 tid);
 
 int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b);
 int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
index fb25b6f29323..5bfe5306524c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
@@ -73,6 +73,7 @@
 #include "iwl-eeprom-read.h"
 #include "iwl-nvm-parse.h"
 #include "iwl-prph.h"
+#include "fw/acpi.h"
 
 /* Default NVM size to read */
 #define IWL_NVM_DEFAULT_CHUNK_SIZE (2*1024)
@@ -784,7 +785,7 @@ int iwl_mvm_init_mcc(struct iwl_mvm *mvm)
 		return -EIO;
 
 	if (iwl_mvm_is_wifi_mcc_supported(mvm) &&
-	    !iwl_get_bios_mcc(mvm->dev, mcc)) {
+	    !iwl_acpi_get_mcc(mvm->dev, mcc)) {
 		kfree(regd);
 		regd = iwl_mvm_get_regdomain(mvm->hw->wiphy, mcc,
 					     MCC_SOURCE_BIOS, NULL);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 231878969332..e82b4462722b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -86,6 +86,7 @@
 #include "time-event.h"
 #include "fw-api.h"
 #include "fw/api/scan.h"
+#include "fw/acpi.h"
 
 #define DRV_DESCRIPTION	"The new Intel(R) wireless AGN driver for Linux"
 MODULE_DESCRIPTION(DRV_DESCRIPTION);
@@ -423,8 +424,6 @@ static const struct iwl_hcmd_names iwl_mvm_system_names[] = {
  * Access is done through binary search
  */
 static const struct iwl_hcmd_names iwl_mvm_mac_conf_names[] = {
-	HCMD_NAME(LINK_QUALITY_MEASUREMENT_CMD),
-	HCMD_NAME(LINK_QUALITY_MEASUREMENT_COMPLETE_NOTIF),
 	HCMD_NAME(CHANNEL_SWITCH_NOA_NOTIF),
 };
 
@@ -490,18 +489,21 @@ static const struct iwl_hcmd_arr iwl_mvm_groups[] = {
 static void iwl_mvm_async_handlers_wk(struct work_struct *wk);
 static void iwl_mvm_d0i3_exit_work(struct work_struct *wk);
 
-static u32 calc_min_backoff(struct iwl_trans *trans, const struct iwl_cfg *cfg)
+static u32 iwl_mvm_min_backoff(struct iwl_mvm *mvm)
 {
-	const struct iwl_pwr_tx_backoff *pwr_tx_backoff = cfg->pwr_tx_backoffs;
+	const struct iwl_pwr_tx_backoff *backoff = mvm->cfg->pwr_tx_backoffs;
+	u64 dflt_pwr_limit;
 
-	if (!pwr_tx_backoff)
+	if (!backoff)
 		return 0;
 
-	while (pwr_tx_backoff->pwr) {
-		if (trans->dflt_pwr_limit >= pwr_tx_backoff->pwr)
-			return pwr_tx_backoff->backoff;
+	dflt_pwr_limit = iwl_acpi_get_pwr_limit(mvm->dev);
 
-		pwr_tx_backoff++;
+	while (backoff->pwr) {
+		if (dflt_pwr_limit >= backoff->pwr)
+			return backoff->backoff;
+
+		backoff++;
 	}
 
 	return 0;
@@ -771,7 +773,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 		goto out_free;
 	mvm->hw_registered = true;
 
-	min_backoff = calc_min_backoff(trans, cfg);
+	min_backoff = iwl_mvm_min_backoff(mvm);
 	iwl_mvm_thermal_initialize(mvm, min_backoff);
 
 	err = iwl_mvm_dbgfs_register(mvm, dbgfs_dir);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
index 7ee8e9077baf..305cd56bf746 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
@@ -272,6 +272,7 @@ int iwl_mvm_phy_ctxt_changed(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt,
 	}
 
 	ctxt->channel = chandef->chan;
+	ctxt->width = chandef->width;
 	return iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef,
 				      chains_static, chains_dynamic,
 				      action, 0);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/quota.c b/drivers/net/wireless/intel/iwlwifi/mvm/quota.c
index 2141db5bff82..b4a0264329b7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/quota.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/quota.c
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -34,7 +34,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright(c) 2016        Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -164,9 +164,12 @@ static void iwl_mvm_adjust_quota_for_noa(struct iwl_mvm *mvm,
 	beacon_int = mvm->noa_vif->bss_conf.beacon_int;
 
 	for (i = 0; i < MAX_BINDINGS; i++) {
-		u32 id_n_c = le32_to_cpu(cmd->quotas[i].id_and_color);
+		struct iwl_time_quota_data *data =
+					iwl_mvm_quota_cmd_get_quota(mvm, cmd,
+								    i);
+		u32 id_n_c = le32_to_cpu(data->id_and_color);
 		u32 id = (id_n_c & FW_CTXT_ID_MSK) >> FW_CTXT_ID_POS;
-		u32 quota = le32_to_cpu(cmd->quotas[i].quota);
+		u32 quota = le32_to_cpu(data->quota);
 
 		if (id != phy_id)
 			continue;
@@ -175,9 +178,9 @@ static void iwl_mvm_adjust_quota_for_noa(struct iwl_mvm *mvm,
 		quota /= beacon_int;
 
 		IWL_DEBUG_QUOTA(mvm, "quota: adjust for NoA from %d to %d\n",
-				le32_to_cpu(cmd->quotas[i].quota), quota);
+				le32_to_cpu(data->quota), quota);
 
-		cmd->quotas[i].quota = cpu_to_le32(quota);
+		data->quota = cpu_to_le32(quota);
 	}
 #endif
 }
@@ -194,6 +197,7 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm,
 		.disabled_vif = disabled_vif,
 	};
 	struct iwl_time_quota_cmd *last = &mvm->last_quota_cmd;
+	struct iwl_time_quota_data *qdata, *last_data;
 	bool send = false;
 
 	lockdep_assert_held(&mvm->mutex);
@@ -216,7 +220,8 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm,
 	 */
 	num_active_macs = 0;
 	for (i = 0; i < MAX_BINDINGS; i++) {
-		cmd.quotas[i].id_and_color = cpu_to_le32(FW_CTXT_INVALID);
+		qdata = iwl_mvm_quota_cmd_get_quota(mvm, &cmd, i);
+		qdata->id_and_color = cpu_to_le32(FW_CTXT_INVALID);
 		num_active_macs += data.n_interfaces[i];
 	}
 
@@ -265,14 +270,16 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm,
 		if (data.colors[i] < 0)
 			continue;
 
-		cmd.quotas[idx].id_and_color =
+		qdata = iwl_mvm_quota_cmd_get_quota(mvm, &cmd, idx);
+
+		qdata->id_and_color =
 			cpu_to_le32(FW_CMD_ID_AND_COLOR(i, data.colors[i]));
 
 		if (data.n_interfaces[i] <= 0)
-			cmd.quotas[idx].quota = cpu_to_le32(0);
+			qdata->quota = cpu_to_le32(0);
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 		else if (data.dbgfs_min[i])
-			cmd.quotas[idx].quota =
+			qdata->quota =
 				cpu_to_le32(data.dbgfs_min[i] * QUOTA_100 / 100);
 #endif
 		else if (data.n_low_latency_bindings == 1 && n_non_lowlat &&
@@ -283,24 +290,25 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm,
 			 * the minimal required quota for the low latency
 			 * binding.
 			 */
-			cmd.quotas[idx].quota = cpu_to_le32(QUOTA_LOWLAT_MIN);
+			qdata->quota = cpu_to_le32(QUOTA_LOWLAT_MIN);
 		else
-			cmd.quotas[idx].quota =
+			qdata->quota =
 				cpu_to_le32(quota * data.n_interfaces[i]);
 
-		WARN_ONCE(le32_to_cpu(cmd.quotas[idx].quota) > QUOTA_100,
+		WARN_ONCE(le32_to_cpu(qdata->quota) > QUOTA_100,
 			  "Binding=%d, quota=%u > max=%u\n",
-			  idx, le32_to_cpu(cmd.quotas[idx].quota), QUOTA_100);
+			  idx, le32_to_cpu(qdata->quota), QUOTA_100);
 
-		cmd.quotas[idx].max_duration = cpu_to_le32(0);
+		qdata->max_duration = cpu_to_le32(0);
 
 		idx++;
 	}
 
 	/* Give the remainder of the session to the first data binding */
 	for (i = 0; i < MAX_BINDINGS; i++) {
-		if (le32_to_cpu(cmd.quotas[i].quota) != 0) {
-			le32_add_cpu(&cmd.quotas[i].quota, quota_rem);
+		qdata = iwl_mvm_quota_cmd_get_quota(mvm, &cmd, i);
+		if (le32_to_cpu(qdata->quota) != 0) {
+			le32_add_cpu(&qdata->quota, quota_rem);
 			IWL_DEBUG_QUOTA(mvm,
 					"quota: giving remainder of %d to binding %d\n",
 					quota_rem, i);
@@ -312,17 +320,19 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm,
 
 	/* check that we have non-zero quota for all valid bindings */
 	for (i = 0; i < MAX_BINDINGS; i++) {
-		if (cmd.quotas[i].id_and_color != last->quotas[i].id_and_color)
+		qdata = iwl_mvm_quota_cmd_get_quota(mvm, &cmd, i);
+		last_data = iwl_mvm_quota_cmd_get_quota(mvm, last, i);
+		if (qdata->id_and_color != last_data->id_and_color)
 			send = true;
-		if (cmd.quotas[i].max_duration != last->quotas[i].max_duration)
+		if (qdata->max_duration != last_data->max_duration)
 			send = true;
-		if (abs((int)le32_to_cpu(cmd.quotas[i].quota) -
-			(int)le32_to_cpu(last->quotas[i].quota))
+		if (abs((int)le32_to_cpu(qdata->quota) -
+			(int)le32_to_cpu(last_data->quota))
 						> IWL_MVM_QUOTA_THRESHOLD)
 			send = true;
-		if (cmd.quotas[i].id_and_color == cpu_to_le32(FW_CTXT_INVALID))
+		if (qdata->id_and_color == cpu_to_le32(FW_CTXT_INVALID))
 			continue;
-		WARN_ONCE(cmd.quotas[i].quota == 0,
+		WARN_ONCE(qdata->quota == 0,
 			  "zero quota on binding %d\n", i);
 	}
 
@@ -334,7 +344,8 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm,
 		return 0;
 	}
 
-	err = iwl_mvm_send_cmd_pdu(mvm, TIME_QUOTA_CMD, 0, sizeof(cmd), &cmd);
+	err = iwl_mvm_send_cmd_pdu(mvm, TIME_QUOTA_CMD, 0,
+				   iwl_mvm_quota_cmd_size(mvm), &cmd);
 
 	if (err)
 		IWL_ERR(mvm, "Failed to send quota: %d\n", err);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
index 2d14a58cbdd7..d1a40688d5e1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
@@ -663,11 +663,10 @@ void iwl_mvm_handle_rx_statistics(struct iwl_mvm *mvm,
 		expected_size = sizeof(struct iwl_notif_statistics_cdb);
 	}
 
-	if (iwl_rx_packet_payload_len(pkt) != expected_size) {
-		IWL_ERR(mvm, "received invalid statistics size (%d)!\n",
-			iwl_rx_packet_payload_len(pkt));
+	if (WARN_ONCE(iwl_rx_packet_payload_len(pkt) != expected_size,
+		      "received invalid statistics size (%d)!\n",
+		      iwl_rx_packet_payload_len(pkt)))
 		return;
-	}
 
 	if (!iwl_mvm_has_new_rx_stats_api(mvm)) {
 		struct iwl_notif_statistics_v11 *stats = (void *)&pkt->data;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 248699c2c4bf..5e679859f948 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -494,13 +494,18 @@ void iwl_mvm_reorder_timer_expired(unsigned long data)
 
 	if (expired) {
 		struct ieee80211_sta *sta;
+		struct iwl_mvm_sta *mvmsta;
 
 		rcu_read_lock();
 		sta = rcu_dereference(buf->mvm->fw_id_to_mac_id[buf->sta_id]);
+		mvmsta = iwl_mvm_sta_from_mac80211(sta);
+
 		/* SN is set to the last expired frame + 1 */
 		IWL_DEBUG_HT(buf->mvm,
 			     "Releasing expired frames for sta %u, sn %d\n",
 			     buf->sta_id, sn);
+		iwl_mvm_event_frame_timeout_callback(buf->mvm, mvmsta->vif,
+						     sta, buf->tid);
 		iwl_mvm_release_frames(buf->mvm, sta, NULL, buf, sn);
 		rcu_read_unlock();
 	} else {
@@ -621,7 +626,8 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
 		return false;
 
 	/* no sta yet */
-	if (WARN_ON(IS_ERR_OR_NULL(sta)))
+	if (WARN_ONCE(IS_ERR_OR_NULL(sta),
+		      "Got valid BAID without a valid station assigned\n"))
 		return false;
 
 	mvm_sta = iwl_mvm_sta_from_mac80211(sta);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index c4a343534c5e..282424f40c43 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -2158,6 +2158,7 @@ static void iwl_mvm_init_reorder_buffer(struct iwl_mvm *mvm,
 		reorder_buf->mvm = mvm;
 		reorder_buf->queue = i;
 		reorder_buf->sta_id = sta_id;
+		reorder_buf->tid = data->tid;
 		reorder_buf->valid = false;
 		for (j = 0; j < reorder_buf->buf_size; j++)
 			__skb_queue_head_init(&reorder_buf->entries[j]);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index 2ea74abad73d..2da1b088ac01 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -1368,6 +1368,31 @@ void iwl_mvm_inactivity_check(struct iwl_mvm *mvm)
 	rcu_read_unlock();
 }
 
+void iwl_mvm_event_frame_timeout_callback(struct iwl_mvm *mvm,
+					  struct ieee80211_vif *vif,
+					  const struct ieee80211_sta *sta,
+					  u16 tid)
+{
+	struct iwl_fw_dbg_trigger_tlv *trig;
+	struct iwl_fw_dbg_trigger_ba *ba_trig;
+
+	if (!iwl_fw_dbg_trigger_enabled(mvm->fw, FW_DBG_TRIGGER_BA))
+		return;
+
+	trig = iwl_fw_dbg_get_trigger(mvm->fw, FW_DBG_TRIGGER_BA);
+	ba_trig = (void *)trig->data;
+	if (!iwl_fw_dbg_trigger_check_stop(&mvm->fwrt,
+					   ieee80211_vif_to_wdev(vif), trig))
+		return;
+
+	if (!(le16_to_cpu(ba_trig->frame_timeout) & BIT(tid)))
+		return;
+
+	iwl_fw_dbg_collect_trig(&mvm->fwrt, trig,
+				"Frame from %pM timed out, tid %d",
+				sta->addr, tid);
+}
+
 void iwl_mvm_get_sync_time(struct iwl_mvm *mvm, u32 *gp2, u64 *boottime)
 {
 	bool ps_disabled;
@@ -1389,74 +1414,3 @@ void iwl_mvm_get_sync_time(struct iwl_mvm *mvm, u32 *gp2, u64 *boottime)
 		iwl_mvm_power_update_device(mvm);
 	}
 }
-
-int iwl_mvm_send_lqm_cmd(struct ieee80211_vif *vif,
-			 enum iwl_lqm_cmd_operatrions operation,
-			 u32 duration, u32 timeout)
-{
-	struct iwl_mvm_vif *mvm_vif = iwl_mvm_vif_from_mac80211(vif);
-	struct iwl_link_qual_msrmnt_cmd cmd = {
-		.cmd_operation = cpu_to_le32(operation),
-		.mac_id = cpu_to_le32(mvm_vif->id),
-		.measurement_time = cpu_to_le32(duration),
-		.timeout = cpu_to_le32(timeout),
-	};
-	u32 cmdid =
-		iwl_cmd_id(LINK_QUALITY_MEASUREMENT_CMD, MAC_CONF_GROUP, 0);
-	int ret;
-
-	if (!fw_has_capa(&mvm_vif->mvm->fw->ucode_capa,
-			 IWL_UCODE_TLV_CAPA_LQM_SUPPORT))
-		return -EOPNOTSUPP;
-
-	if (vif->type != NL80211_IFTYPE_STATION || vif->p2p)
-		return -EINVAL;
-
-	switch (operation) {
-	case LQM_CMD_OPERATION_START_MEASUREMENT:
-		if (iwl_mvm_lqm_active(mvm_vif->mvm))
-			return -EBUSY;
-		if (!vif->bss_conf.assoc)
-			return -EINVAL;
-		mvm_vif->lqm_active = true;
-		break;
-	case LQM_CMD_OPERATION_STOP_MEASUREMENT:
-		if (!iwl_mvm_lqm_active(mvm_vif->mvm))
-			return -EINVAL;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	ret = iwl_mvm_send_cmd_pdu(mvm_vif->mvm, cmdid, 0, sizeof(cmd),
-				   &cmd);
-
-	/* command failed - roll back lqm_active state */
-	if (ret) {
-		mvm_vif->lqm_active =
-			operation == LQM_CMD_OPERATION_STOP_MEASUREMENT;
-	}
-
-	return ret;
-}
-
-static void iwl_mvm_lqm_active_iterator(void *_data, u8 *mac,
-					struct ieee80211_vif *vif)
-{
-	struct iwl_mvm_vif *mvm_vif = iwl_mvm_vif_from_mac80211(vif);
-	bool *lqm_active = _data;
-
-	*lqm_active = *lqm_active || mvm_vif->lqm_active;
-}
-
-bool iwl_mvm_lqm_active(struct iwl_mvm *mvm)
-{
-	bool ret = false;
-
-	lockdep_assert_held(&mvm->mutex);
-	ieee80211_iterate_active_interfaces_atomic(
-		mvm->hw, IEEE80211_IFACE_ITER_NORMAL,
-		iwl_mvm_lqm_active_iterator, &ret);
-
-	return ret;
-}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
index 3fc4343581ee..5ef216f3a60b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
@@ -244,7 +244,7 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
 	ctxt_info->hcmd_cfg.cmd_queue_addr =
 		cpu_to_le64(trans_pcie->txq[trans_pcie->cmd_queue]->dma_addr);
 	ctxt_info->hcmd_cfg.cmd_queue_size =
-		TFD_QUEUE_CB_SIZE(TFD_CMD_SLOTS);
+		TFD_QUEUE_CB_SIZE(trans_pcie->tx_cmd_queue_size);
 
 	/* allocate ucode sections in dram and set addresses */
 	ret = iwl_pcie_ctxt_info_init_fw_sec(trans, fw, ctxt_info);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 858765fed8f8..ce7254ec0514 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -73,6 +73,8 @@
 #include <linux/pci-aspm.h>
 #include <linux/acpi.h>
 
+#include "fw/acpi.h"
+
 #include "iwl-trans.h"
 #include "iwl-drv.h"
 #include "internal.h"
@@ -576,7 +578,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x2720, 0x0000, iwla000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0x34F0, 0x0070, iwla000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0x2720, 0x0078, iwla000_2ax_cfg_hr)},
-	{IWL_PCI_DEVICE(0x2720, 0x0070, iwla000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x2720, 0x0070, iwla000_2ac_cfg_hr_cdb)},
+	{IWL_PCI_DEVICE(0x2720, 0x0030, iwla000_2ac_cfg_hr_cdb)},
 	{IWL_PCI_DEVICE(0x2720, 0x1080, iwla000_2ax_cfg_hr)},
 #endif /* CONFIG_IWLMVM */
 
@@ -584,99 +587,6 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 };
 MODULE_DEVICE_TABLE(pci, iwl_hw_card_ids);
 
-#ifdef CONFIG_ACPI
-#define ACPI_SPLC_METHOD	"SPLC"
-#define ACPI_SPLC_DOMAIN_WIFI	(0x07)
-
-static u64 splc_get_pwr_limit(struct iwl_trans *trans, union acpi_object *splc)
-{
-	union acpi_object *data_pkg, *dflt_pwr_limit;
-	int i;
-
-	/* We need at least two elements, one for the revision and one
-	 * for the data itself.  Also check that the revision is
-	 * supported (currently only revision 0).
-	*/
-	if (splc->type != ACPI_TYPE_PACKAGE ||
-	    splc->package.count < 2 ||
-	    splc->package.elements[0].type != ACPI_TYPE_INTEGER ||
-	    splc->package.elements[0].integer.value != 0) {
-		IWL_DEBUG_INFO(trans,
-			       "Unsupported structure returned by the SPLC method.  Ignoring.\n");
-		return 0;
-	}
-
-	/* loop through all the packages to find the one for WiFi */
-	for (i = 1; i < splc->package.count; i++) {
-		union acpi_object *domain;
-
-		data_pkg = &splc->package.elements[i];
-
-		/* Skip anything that is not a package with the right
-		 * amount of elements (i.e. at least 2 integers).
-		 */
-		if (data_pkg->type != ACPI_TYPE_PACKAGE ||
-		    data_pkg->package.count < 2 ||
-		    data_pkg->package.elements[0].type != ACPI_TYPE_INTEGER ||
-		    data_pkg->package.elements[1].type != ACPI_TYPE_INTEGER)
-			continue;
-
-		domain = &data_pkg->package.elements[0];
-		if (domain->integer.value == ACPI_SPLC_DOMAIN_WIFI)
-			break;
-
-		data_pkg = NULL;
-	}
-
-	if (!data_pkg) {
-		IWL_DEBUG_INFO(trans,
-			       "No element for the WiFi domain returned by the SPLC method.\n");
-		return 0;
-	}
-
-	dflt_pwr_limit = &data_pkg->package.elements[1];
-	return dflt_pwr_limit->integer.value;
-}
-
-static void set_dflt_pwr_limit(struct iwl_trans *trans, struct pci_dev *pdev)
-{
-	acpi_handle pxsx_handle;
-	acpi_handle handle;
-	struct acpi_buffer splc = {ACPI_ALLOCATE_BUFFER, NULL};
-	acpi_status status;
-
-	pxsx_handle = ACPI_HANDLE(&pdev->dev);
-	if (!pxsx_handle) {
-		IWL_DEBUG_INFO(trans,
-			       "Could not retrieve root port ACPI handle\n");
-		return;
-	}
-
-	/* Get the method's handle */
-	status = acpi_get_handle(pxsx_handle, (acpi_string)ACPI_SPLC_METHOD,
-				 &handle);
-	if (ACPI_FAILURE(status)) {
-		IWL_DEBUG_INFO(trans, "SPLC method not found\n");
-		return;
-	}
-
-	/* Call SPLC with no arguments */
-	status = acpi_evaluate_object(handle, NULL, NULL, &splc);
-	if (ACPI_FAILURE(status)) {
-		IWL_ERR(trans, "SPLC invocation failed (0x%x)\n", status);
-		return;
-	}
-
-	trans->dflt_pwr_limit = splc_get_pwr_limit(trans, splc.pointer);
-	IWL_DEBUG_INFO(trans, "Default power limit set to %lld\n",
-		       trans->dflt_pwr_limit);
-	kfree(splc.pointer);
-}
-
-#else /* CONFIG_ACPI */
-static void set_dflt_pwr_limit(struct iwl_trans *trans, struct pci_dev *pdev) {}
-#endif
-
 /* PCI registers */
 #define PCI_CFG_RETRY_TIMEOUT	0x041
 
@@ -740,8 +650,6 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto out_free_trans;
 	}
 
-	set_dflt_pwr_limit(iwl_trans, pdev);
-
 	/* register transport layer debugfs here */
 	ret = iwl_trans_pcie_dbgfs_register(iwl_trans);
 	if (ret)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 4fb7647995c3..d749abeca3ae 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -383,6 +383,7 @@ struct iwl_self_init_dram {
  * @hw_init_mask: initial unmasked hw causes
  * @fh_mask: current unmasked fh causes
  * @hw_mask: current unmasked hw causes
+ * @tx_cmd_queue_size: the size of the tx command queue
  */
 struct iwl_trans_pcie {
 	struct iwl_rxq *rxq;
@@ -442,6 +443,7 @@ struct iwl_trans_pcie {
 	bool bc_table_dword;
 	bool scd_set_active;
 	bool sw_csum_tx;
+	bool pcie_dbg_dumped_once;
 	u32 rx_page_order;
 
 	/*protect hw register */
@@ -463,6 +465,7 @@ struct iwl_trans_pcie {
 	u32 fh_mask;
 	u32 hw_mask;
 	cpumask_t affinity_mask[IWL_MAX_RX_HW_QUEUES];
+	u16 tx_cmd_queue_size;
 };
 
 static inline struct iwl_trans_pcie *
@@ -534,6 +537,7 @@ void iwl_pcie_hcmd_complete(struct iwl_trans *trans,
 void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 			    struct sk_buff_head *skbs);
 void iwl_trans_pcie_tx_reset(struct iwl_trans *trans);
+void iwl_pcie_set_tx_cmd_queue_size(struct iwl_trans *trans);
 
 static inline u16 iwl_pcie_tfd_tb_get_len(struct iwl_trans *trans, void *_tfd,
 					  u8 idx)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 2e3e013ec95a..0008ea323be3 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -88,6 +88,93 @@
 #define IWL_FW_MEM_EXTENDED_START	0x40000
 #define IWL_FW_MEM_EXTENDED_END		0x57FFF
 
+static void iwl_trans_pcie_err_dump(struct iwl_trans *trans)
+{
+#define PCI_DUMP_SIZE	64
+#define PREFIX_LEN	32
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct pci_dev *pdev = trans_pcie->pci_dev;
+	u32 i, pos, alloc_size, *ptr, *buf;
+	char *prefix;
+
+	if (trans_pcie->pcie_dbg_dumped_once)
+		return;
+
+	/* Should be a multiple of 4 */
+	BUILD_BUG_ON(PCI_DUMP_SIZE > 4096 || PCI_DUMP_SIZE & 0x3);
+	/* Alloc a max size buffer */
+	if (PCI_ERR_ROOT_ERR_SRC +  4 > PCI_DUMP_SIZE)
+		alloc_size = PCI_ERR_ROOT_ERR_SRC +  4 + PREFIX_LEN;
+	else
+		alloc_size = PCI_DUMP_SIZE + PREFIX_LEN;
+	buf = kmalloc(alloc_size, GFP_ATOMIC);
+	if (!buf)
+		return;
+	prefix = (char *)buf + alloc_size - PREFIX_LEN;
+
+	IWL_ERR(trans, "iwlwifi transaction failed, dumping registers\n");
+
+	/* Print wifi device registers */
+	sprintf(prefix, "iwlwifi %s: ", pci_name(pdev));
+	IWL_ERR(trans, "iwlwifi device config registers:\n");
+	for (i = 0, ptr = buf; i < PCI_DUMP_SIZE; i += 4, ptr++)
+		if (pci_read_config_dword(pdev, i, ptr))
+			goto err_read;
+	print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32, 4, buf, i, 0);
+
+	IWL_ERR(trans, "iwlwifi device memory mapped registers:\n");
+	for (i = 0, ptr = buf; i < PCI_DUMP_SIZE; i += 4, ptr++)
+		*ptr = iwl_read32(trans, i);
+	print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32, 4, buf, i, 0);
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
+	if (pos) {
+		IWL_ERR(trans, "iwlwifi device AER capability structure:\n");
+		for (i = 0, ptr = buf; i < PCI_ERR_ROOT_COMMAND; i += 4, ptr++)
+			if (pci_read_config_dword(pdev, pos + i, ptr))
+				goto err_read;
+		print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET,
+			       32, 4, buf, i, 0);
+	}
+
+	/* Print parent device registers next */
+	if (!pdev->bus->self)
+		goto out;
+
+	pdev = pdev->bus->self;
+	sprintf(prefix, "iwlwifi %s: ", pci_name(pdev));
+
+	IWL_ERR(trans, "iwlwifi parent port (%s) config registers:\n",
+		pci_name(pdev));
+	for (i = 0, ptr = buf; i < PCI_DUMP_SIZE; i += 4, ptr++)
+		if (pci_read_config_dword(pdev, i, ptr))
+			goto err_read;
+	print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32, 4, buf, i, 0);
+
+	/* Print root port AER registers */
+	pos = 0;
+	pdev = pcie_find_root_port(pdev);
+	if (pdev)
+		pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
+	if (pos) {
+		IWL_ERR(trans, "iwlwifi root port (%s) AER cap structure:\n",
+			pci_name(pdev));
+		sprintf(prefix, "iwlwifi %s: ", pci_name(pdev));
+		for (i = 0, ptr = buf; i <= PCI_ERR_ROOT_ERR_SRC; i += 4, ptr++)
+			if (pci_read_config_dword(pdev, pos + i, ptr))
+				goto err_read;
+		print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32,
+			       4, buf, i, 0);
+	}
+
+err_read:
+	print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32, 4, buf, i, 0);
+	IWL_ERR(trans, "Read failed at 0x%X\n", i);
+out:
+	trans_pcie->pcie_dbg_dumped_once = 1;
+	kfree(buf);
+}
+
 static void iwl_pcie_free_fw_monitor(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -649,6 +736,7 @@ static int iwl_pcie_load_firmware_chunk(struct iwl_trans *trans,
 				 trans_pcie->ucode_write_complete, 5 * HZ);
 	if (!ret) {
 		IWL_ERR(trans, "Failed to load firmware chunk!\n");
+		iwl_trans_pcie_err_dump(trans);
 		return -ETIMEDOUT;
 	}
 
@@ -1868,6 +1956,7 @@ static bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans,
 			   (CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY |
 			    CSR_GP_CNTRL_REG_FLAG_GOING_TO_SLEEP), 15000);
 	if (unlikely(ret < 0)) {
+		iwl_trans_pcie_err_dump(trans);
 		iwl_write32(trans, CSR_RESET, CSR_RESET_REG_FLAG_FORCE_NMI);
 		WARN_ONCE(1,
 			  "Timeout waiting for hardware access (CSR_GP_CNTRL 0x%08x)\n",
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index d74613fcb756..79e4c73a9709 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -1160,6 +1160,8 @@ int iwl_pcie_gen2_tx_init(struct iwl_trans *trans)
 	struct iwl_txq *cmd_queue;
 	int txq_id = trans_pcie->cmd_queue, ret;
 
+	iwl_pcie_set_tx_cmd_queue_size(trans);
+
 	/* alloc and init the command queue */
 	if (!trans_pcie->txq[txq_id]) {
 		cmd_queue = kzalloc(sizeof(*cmd_queue), GFP_KERNEL);
@@ -1168,7 +1170,8 @@ int iwl_pcie_gen2_tx_init(struct iwl_trans *trans)
 			return -ENOMEM;
 		}
 		trans_pcie->txq[txq_id] = cmd_queue;
-		ret = iwl_pcie_txq_alloc(trans, cmd_queue, TFD_CMD_SLOTS, true);
+		ret = iwl_pcie_txq_alloc(trans, cmd_queue,
+					 trans_pcie->tx_cmd_queue_size, true);
 		if (ret) {
 			IWL_ERR(trans, "Tx %d queue init failed\n", txq_id);
 			goto error;
@@ -1177,7 +1180,8 @@ int iwl_pcie_gen2_tx_init(struct iwl_trans *trans)
 		cmd_queue = trans_pcie->txq[txq_id];
 	}
 
-	ret = iwl_pcie_txq_init(trans, cmd_queue, TFD_CMD_SLOTS, true);
+	ret = iwl_pcie_txq_init(trans, cmd_queue,
+				trans_pcie->tx_cmd_queue_size, true);
 	if (ret) {
 		IWL_ERR(trans, "Tx %d queue alloc failed\n", txq_id);
 		goto error;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index c645d10d3707..e93c471ef9bf 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -951,7 +951,8 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 	     txq_id++) {
 		bool cmd_queue = (txq_id == trans_pcie->cmd_queue);
 
-		slots_num = cmd_queue ? TFD_CMD_SLOTS : TFD_TX_CMD_SLOTS;
+		slots_num = cmd_queue ? trans_pcie->tx_cmd_queue_size :
+			TFD_TX_CMD_SLOTS;
 		trans_pcie->txq[txq_id] = &trans_pcie->txq_memory[txq_id];
 		ret = iwl_pcie_txq_alloc(trans, trans_pcie->txq[txq_id],
 					 slots_num, cmd_queue);
@@ -970,6 +971,21 @@ error:
 	return ret;
 }
 
+void iwl_pcie_set_tx_cmd_queue_size(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	int queue_size = TFD_CMD_SLOTS;
+
+	if (trans->cfg->tx_cmd_queue_size)
+		queue_size = trans->cfg->tx_cmd_queue_size;
+
+	if (WARN_ON(!(is_power_of_2(queue_size) &&
+		      TFD_QUEUE_CB_SIZE(queue_size) > 0)))
+		trans_pcie->tx_cmd_queue_size = TFD_CMD_SLOTS;
+	else
+		trans_pcie->tx_cmd_queue_size = queue_size;
+}
+
 int iwl_pcie_tx_init(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -977,6 +993,8 @@ int iwl_pcie_tx_init(struct iwl_trans *trans)
 	int txq_id, slots_num;
 	bool alloc = false;
 
+	iwl_pcie_set_tx_cmd_queue_size(trans);
+
 	if (!trans_pcie->txq_memory) {
 		ret = iwl_pcie_tx_alloc(trans);
 		if (ret)
@@ -1000,7 +1018,8 @@ int iwl_pcie_tx_init(struct iwl_trans *trans)
 	     txq_id++) {
 		bool cmd_queue = (txq_id == trans_pcie->cmd_queue);
 
-		slots_num = cmd_queue ? TFD_CMD_SLOTS : TFD_TX_CMD_SLOTS;
+		slots_num = cmd_queue ? trans_pcie->tx_cmd_queue_size :
+			TFD_TX_CMD_SLOTS;
 		ret = iwl_pcie_txq_init(trans, trans_pcie->txq[txq_id],
 					slots_num, cmd_queue);
 		if (ret) {
diff --git a/drivers/net/wireless/intersil/p54/main.c b/drivers/net/wireless/intersil/p54/main.c
index d5a3bf91a03e..ab6d39e12069 100644
--- a/drivers/net/wireless/intersil/p54/main.c
+++ b/drivers/net/wireless/intersil/p54/main.c
@@ -852,12 +852,11 @@ void p54_unregister_common(struct ieee80211_hw *dev)
 {
 	struct p54_common *priv = dev->priv;
 
-#ifdef CONFIG_P54_LEDS
-	p54_unregister_leds(priv);
-#endif /* CONFIG_P54_LEDS */
-
 	if (priv->registered) {
 		priv->registered = false;
+#ifdef CONFIG_P54_LEDS
+		p54_unregister_leds(priv);
+#endif /* CONFIG_P54_LEDS */
 		ieee80211_unregister_hw(dev);
 	}
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 6467ffac9811..ec2f4c31425a 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -396,7 +396,7 @@ static int mac80211_hwsim_vendor_cmd_test(struct wiphy *wiphy,
 	if (!tb[QCA_WLAN_VENDOR_ATTR_TEST])
 		return -EINVAL;
 	val = nla_get_u32(tb[QCA_WLAN_VENDOR_ATTR_TEST]);
-	wiphy_debug(wiphy, "%s: test=%u\n", __func__, val);
+	wiphy_dbg(wiphy, "%s: test=%u\n", __func__, val);
 
 	/* Send a vendor event as a test. Note that this would not normally be
 	 * done within a command handler, but rather, based on some other
@@ -643,9 +643,9 @@ static void hwsim_send_ps_poll(void *dat, u8 *mac, struct ieee80211_vif *vif)
 	if (!vp->assoc)
 		return;
 
-	wiphy_debug(data->hw->wiphy,
-		    "%s: send PS-Poll to %pM for aid %d\n",
-		    __func__, vp->bssid, vp->aid);
+	wiphy_dbg(data->hw->wiphy,
+		  "%s: send PS-Poll to %pM for aid %d\n",
+		  __func__, vp->bssid, vp->aid);
 
 	skb = dev_alloc_skb(sizeof(*pspoll));
 	if (!skb)
@@ -674,9 +674,9 @@ static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac,
 	if (!vp->assoc)
 		return;
 
-	wiphy_debug(data->hw->wiphy,
-		    "%s: send data::nullfunc to %pM ps=%d\n",
-		    __func__, vp->bssid, ps);
+	wiphy_dbg(data->hw->wiphy,
+		  "%s: send data::nullfunc to %pM ps=%d\n",
+		  __func__, vp->bssid, ps);
 
 	skb = dev_alloc_skb(sizeof(*hdr));
 	if (!skb)
@@ -1034,7 +1034,7 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw,
 	msg_head = genlmsg_put(skb, 0, 0, &hwsim_genl_family, 0,
 			       HWSIM_CMD_FRAME);
 	if (msg_head == NULL) {
-		printk(KERN_DEBUG "mac80211_hwsim: problem with msg_head\n");
+		pr_debug("mac80211_hwsim: problem with msg_head\n");
 		goto nla_put_failure;
 	}
 
@@ -1093,7 +1093,7 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw,
 nla_put_failure:
 	nlmsg_free(skb);
 err_free_txskb:
-	printk(KERN_DEBUG "mac80211_hwsim: error occurred in %s\n", __func__);
+	pr_debug("mac80211_hwsim: error occurred in %s\n", __func__);
 	ieee80211_free_txskb(hw, my_skb);
 	data->tx_failed++;
 }
@@ -1347,7 +1347,7 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw,
 	}
 
 	if (data->idle && !data->tmp_chan) {
-		wiphy_debug(hw->wiphy, "Trying to TX when idle - reject\n");
+		wiphy_dbg(hw->wiphy, "Trying to TX when idle - reject\n");
 		ieee80211_free_txskb(hw, skb);
 		return;
 	}
@@ -1408,7 +1408,7 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw,
 static int mac80211_hwsim_start(struct ieee80211_hw *hw)
 {
 	struct mac80211_hwsim_data *data = hw->priv;
-	wiphy_debug(hw->wiphy, "%s\n", __func__);
+	wiphy_dbg(hw->wiphy, "%s\n", __func__);
 	data->started = true;
 	return 0;
 }
@@ -1419,16 +1419,16 @@ static void mac80211_hwsim_stop(struct ieee80211_hw *hw)
 	struct mac80211_hwsim_data *data = hw->priv;
 	data->started = false;
 	tasklet_hrtimer_cancel(&data->beacon_timer);
-	wiphy_debug(hw->wiphy, "%s\n", __func__);
+	wiphy_dbg(hw->wiphy, "%s\n", __func__);
 }
 
 
 static int mac80211_hwsim_add_interface(struct ieee80211_hw *hw,
 					struct ieee80211_vif *vif)
 {
-	wiphy_debug(hw->wiphy, "%s (type=%d mac_addr=%pM)\n",
-		    __func__, ieee80211_vif_type_p2p(vif),
-		    vif->addr);
+	wiphy_dbg(hw->wiphy, "%s (type=%d mac_addr=%pM)\n",
+		  __func__, ieee80211_vif_type_p2p(vif),
+		  vif->addr);
 	hwsim_set_magic(vif);
 
 	vif->cab_queue = 0;
@@ -1447,9 +1447,9 @@ static int mac80211_hwsim_change_interface(struct ieee80211_hw *hw,
 					   bool newp2p)
 {
 	newtype = ieee80211_iftype_p2p(newtype, newp2p);
-	wiphy_debug(hw->wiphy,
-		    "%s (old type=%d, new type=%d, mac_addr=%pM)\n",
-		    __func__, ieee80211_vif_type_p2p(vif),
+	wiphy_dbg(hw->wiphy,
+		  "%s (old type=%d, new type=%d, mac_addr=%pM)\n",
+		  __func__, ieee80211_vif_type_p2p(vif),
 		    newtype, vif->addr);
 	hwsim_check_magic(vif);
 
@@ -1465,9 +1465,9 @@ static int mac80211_hwsim_change_interface(struct ieee80211_hw *hw,
 static void mac80211_hwsim_remove_interface(
 	struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 {
-	wiphy_debug(hw->wiphy, "%s (type=%d mac_addr=%pM)\n",
-		    __func__, ieee80211_vif_type_p2p(vif),
-		    vif->addr);
+	wiphy_dbg(hw->wiphy, "%s (type=%d mac_addr=%pM)\n",
+		  __func__, ieee80211_vif_type_p2p(vif),
+		  vif->addr);
 	hwsim_check_magic(vif);
 	hwsim_clear_magic(vif);
 }
@@ -1589,23 +1589,23 @@ static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed)
 	int idx;
 
 	if (conf->chandef.chan)
-		wiphy_debug(hw->wiphy,
-			    "%s (freq=%d(%d - %d)/%s idle=%d ps=%d smps=%s)\n",
-			    __func__,
-			    conf->chandef.chan->center_freq,
-			    conf->chandef.center_freq1,
-			    conf->chandef.center_freq2,
-			    hwsim_chanwidths[conf->chandef.width],
-			    !!(conf->flags & IEEE80211_CONF_IDLE),
-			    !!(conf->flags & IEEE80211_CONF_PS),
-			    smps_modes[conf->smps_mode]);
+		wiphy_dbg(hw->wiphy,
+			  "%s (freq=%d(%d - %d)/%s idle=%d ps=%d smps=%s)\n",
+			  __func__,
+			  conf->chandef.chan->center_freq,
+			  conf->chandef.center_freq1,
+			  conf->chandef.center_freq2,
+			  hwsim_chanwidths[conf->chandef.width],
+			  !!(conf->flags & IEEE80211_CONF_IDLE),
+			  !!(conf->flags & IEEE80211_CONF_PS),
+			  smps_modes[conf->smps_mode]);
 	else
-		wiphy_debug(hw->wiphy,
-			    "%s (freq=0 idle=%d ps=%d smps=%s)\n",
-			    __func__,
-			    !!(conf->flags & IEEE80211_CONF_IDLE),
-			    !!(conf->flags & IEEE80211_CONF_PS),
-			    smps_modes[conf->smps_mode]);
+		wiphy_dbg(hw->wiphy,
+			  "%s (freq=0 idle=%d ps=%d smps=%s)\n",
+			  __func__,
+			  !!(conf->flags & IEEE80211_CONF_IDLE),
+			  !!(conf->flags & IEEE80211_CONF_PS),
+			  smps_modes[conf->smps_mode]);
 
 	data->idle = !!(conf->flags & IEEE80211_CONF_IDLE);
 
@@ -1659,7 +1659,7 @@ static void mac80211_hwsim_configure_filter(struct ieee80211_hw *hw,
 {
 	struct mac80211_hwsim_data *data = hw->priv;
 
-	wiphy_debug(hw->wiphy, "%s\n", __func__);
+	wiphy_dbg(hw->wiphy, "%s\n", __func__);
 
 	data->rx_filter = 0;
 	if (*total_flags & FIF_ALLMULTI)
@@ -1688,25 +1688,25 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 
 	hwsim_check_magic(vif);
 
-	wiphy_debug(hw->wiphy, "%s(changed=0x%x vif->addr=%pM)\n",
-		    __func__, changed, vif->addr);
+	wiphy_dbg(hw->wiphy, "%s(changed=0x%x vif->addr=%pM)\n",
+		  __func__, changed, vif->addr);
 
 	if (changed & BSS_CHANGED_BSSID) {
-		wiphy_debug(hw->wiphy, "%s: BSSID changed: %pM\n",
-			    __func__, info->bssid);
+		wiphy_dbg(hw->wiphy, "%s: BSSID changed: %pM\n",
+			  __func__, info->bssid);
 		memcpy(vp->bssid, info->bssid, ETH_ALEN);
 	}
 
 	if (changed & BSS_CHANGED_ASSOC) {
-		wiphy_debug(hw->wiphy, "  ASSOC: assoc=%d aid=%d\n",
-			    info->assoc, info->aid);
+		wiphy_dbg(hw->wiphy, "  ASSOC: assoc=%d aid=%d\n",
+			  info->assoc, info->aid);
 		vp->assoc = info->assoc;
 		vp->aid = info->aid;
 	}
 
 	if (changed & BSS_CHANGED_BEACON_ENABLED) {
-		wiphy_debug(hw->wiphy, "  BCN EN: %d (BI=%u)\n",
-			    info->enable_beacon, info->beacon_int);
+		wiphy_dbg(hw->wiphy, "  BCN EN: %d (BI=%u)\n",
+			  info->enable_beacon, info->beacon_int);
 		vp->bcn_en = info->enable_beacon;
 		if (data->started &&
 		    !hrtimer_is_queued(&data->beacon_timer.timer) &&
@@ -1725,8 +1725,8 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 			ieee80211_iterate_active_interfaces_atomic(
 				data->hw, IEEE80211_IFACE_ITER_NORMAL,
 				mac80211_hwsim_bcn_en_iter, &count);
-			wiphy_debug(hw->wiphy, "  beaconing vifs remaining: %u",
-				    count);
+			wiphy_dbg(hw->wiphy, "  beaconing vifs remaining: %u",
+				  count);
 			if (count == 0) {
 				tasklet_hrtimer_cancel(&data->beacon_timer);
 				data->beacon_int = 0;
@@ -1735,31 +1735,31 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 	}
 
 	if (changed & BSS_CHANGED_ERP_CTS_PROT) {
-		wiphy_debug(hw->wiphy, "  ERP_CTS_PROT: %d\n",
-			    info->use_cts_prot);
+		wiphy_dbg(hw->wiphy, "  ERP_CTS_PROT: %d\n",
+			  info->use_cts_prot);
 	}
 
 	if (changed & BSS_CHANGED_ERP_PREAMBLE) {
-		wiphy_debug(hw->wiphy, "  ERP_PREAMBLE: %d\n",
-			    info->use_short_preamble);
+		wiphy_dbg(hw->wiphy, "  ERP_PREAMBLE: %d\n",
+			  info->use_short_preamble);
 	}
 
 	if (changed & BSS_CHANGED_ERP_SLOT) {
-		wiphy_debug(hw->wiphy, "  ERP_SLOT: %d\n", info->use_short_slot);
+		wiphy_dbg(hw->wiphy, "  ERP_SLOT: %d\n", info->use_short_slot);
 	}
 
 	if (changed & BSS_CHANGED_HT) {
-		wiphy_debug(hw->wiphy, "  HT: op_mode=0x%x\n",
-			    info->ht_operation_mode);
+		wiphy_dbg(hw->wiphy, "  HT: op_mode=0x%x\n",
+			  info->ht_operation_mode);
 	}
 
 	if (changed & BSS_CHANGED_BASIC_RATES) {
-		wiphy_debug(hw->wiphy, "  BASIC_RATES: 0x%llx\n",
-			    (unsigned long long) info->basic_rates);
+		wiphy_dbg(hw->wiphy, "  BASIC_RATES: 0x%llx\n",
+			  (unsigned long long) info->basic_rates);
 	}
 
 	if (changed & BSS_CHANGED_TXPOWER)
-		wiphy_debug(hw->wiphy, "  TX Power: %d dBm\n", info->txpower);
+		wiphy_dbg(hw->wiphy, "  TX Power: %d dBm\n", info->txpower);
 }
 
 static int mac80211_hwsim_sta_add(struct ieee80211_hw *hw,
@@ -1813,11 +1813,11 @@ static int mac80211_hwsim_conf_tx(
 	struct ieee80211_vif *vif, u16 queue,
 	const struct ieee80211_tx_queue_params *params)
 {
-	wiphy_debug(hw->wiphy,
-		    "%s (queue=%d txop=%d cw_min=%d cw_max=%d aifs=%d)\n",
-		    __func__, queue,
-		    params->txop, params->cw_min,
-		    params->cw_max, params->aifs);
+	wiphy_dbg(hw->wiphy,
+		  "%s (queue=%d txop=%d cw_min=%d cw_max=%d aifs=%d)\n",
+		  __func__, queue,
+		  params->txop, params->cw_min,
+		  params->cw_max, params->aifs);
 	return 0;
 }
 
@@ -1981,7 +1981,7 @@ static void hw_scan_work(struct work_struct *work)
 			.aborted = false,
 		};
 
-		wiphy_debug(hwsim->hw->wiphy, "hw scan complete\n");
+		wiphy_dbg(hwsim->hw->wiphy, "hw scan complete\n");
 		ieee80211_scan_completed(hwsim->hw, &info);
 		hwsim->hw_scan_request = NULL;
 		hwsim->hw_scan_vif = NULL;
@@ -1990,8 +1990,8 @@ static void hw_scan_work(struct work_struct *work)
 		return;
 	}
 
-	wiphy_debug(hwsim->hw->wiphy, "hw scan %d MHz\n",
-		    req->channels[hwsim->scan_chan_idx]->center_freq);
+	wiphy_dbg(hwsim->hw->wiphy, "hw scan %d MHz\n",
+		  req->channels[hwsim->scan_chan_idx]->center_freq);
 
 	hwsim->tmp_chan = req->channels[hwsim->scan_chan_idx];
 	if (hwsim->tmp_chan->flags & (IEEE80211_CHAN_NO_IR |
@@ -2060,7 +2060,7 @@ static int mac80211_hwsim_hw_scan(struct ieee80211_hw *hw,
 	memset(hwsim->survey_data, 0, sizeof(hwsim->survey_data));
 	mutex_unlock(&hwsim->mutex);
 
-	wiphy_debug(hw->wiphy, "hwsim hw_scan request\n");
+	wiphy_dbg(hw->wiphy, "hwsim hw_scan request\n");
 
 	ieee80211_queue_delayed_work(hwsim->hw, &hwsim->hw_scan, 0);
 
@@ -2075,7 +2075,7 @@ static void mac80211_hwsim_cancel_hw_scan(struct ieee80211_hw *hw,
 		.aborted = true,
 	};
 
-	wiphy_debug(hw->wiphy, "hwsim cancel_hw_scan\n");
+	wiphy_dbg(hw->wiphy, "hwsim cancel_hw_scan\n");
 
 	cancel_delayed_work_sync(&hwsim->hw_scan);
 
@@ -2096,11 +2096,11 @@ static void mac80211_hwsim_sw_scan(struct ieee80211_hw *hw,
 	mutex_lock(&hwsim->mutex);
 
 	if (hwsim->scanning) {
-		printk(KERN_DEBUG "two hwsim sw_scans detected!\n");
+		pr_debug("two hwsim sw_scans detected!\n");
 		goto out;
 	}
 
-	printk(KERN_DEBUG "hwsim sw_scan request, prepping stuff\n");
+	pr_debug("hwsim sw_scan request, prepping stuff\n");
 
 	memcpy(hwsim->scan_addr, mac_addr, ETH_ALEN);
 	hwsim->scanning = true;
@@ -2117,7 +2117,7 @@ static void mac80211_hwsim_sw_scan_complete(struct ieee80211_hw *hw,
 
 	mutex_lock(&hwsim->mutex);
 
-	printk(KERN_DEBUG "hwsim sw_scan_complete\n");
+	pr_debug("hwsim sw_scan_complete\n");
 	hwsim->scanning = false;
 	eth_zero_addr(hwsim->scan_addr);
 
@@ -2131,7 +2131,7 @@ static void hw_roc_start(struct work_struct *work)
 
 	mutex_lock(&hwsim->mutex);
 
-	wiphy_debug(hwsim->hw->wiphy, "hwsim ROC begins\n");
+	wiphy_dbg(hwsim->hw->wiphy, "hwsim ROC begins\n");
 	hwsim->tmp_chan = hwsim->roc_chan;
 	ieee80211_ready_on_channel(hwsim->hw);
 
@@ -2151,7 +2151,7 @@ static void hw_roc_done(struct work_struct *work)
 	hwsim->tmp_chan = NULL;
 	mutex_unlock(&hwsim->mutex);
 
-	wiphy_debug(hwsim->hw->wiphy, "hwsim ROC expired\n");
+	wiphy_dbg(hwsim->hw->wiphy, "hwsim ROC expired\n");
 }
 
 static int mac80211_hwsim_roc(struct ieee80211_hw *hw,
@@ -2172,8 +2172,8 @@ static int mac80211_hwsim_roc(struct ieee80211_hw *hw,
 	hwsim->roc_duration = duration;
 	mutex_unlock(&hwsim->mutex);
 
-	wiphy_debug(hw->wiphy, "hwsim ROC (%d MHz, %d ms)\n",
-		    chan->center_freq, duration);
+	wiphy_dbg(hw->wiphy, "hwsim ROC (%d MHz, %d ms)\n",
+		  chan->center_freq, duration);
 	ieee80211_queue_delayed_work(hw, &hwsim->roc_start, HZ/50);
 
 	return 0;
@@ -2190,7 +2190,7 @@ static int mac80211_hwsim_croc(struct ieee80211_hw *hw)
 	hwsim->tmp_chan = NULL;
 	mutex_unlock(&hwsim->mutex);
 
-	wiphy_debug(hw->wiphy, "hwsim ROC canceled\n");
+	wiphy_dbg(hw->wiphy, "hwsim ROC canceled\n");
 
 	return 0;
 }
@@ -2199,20 +2199,20 @@ static int mac80211_hwsim_add_chanctx(struct ieee80211_hw *hw,
 				      struct ieee80211_chanctx_conf *ctx)
 {
 	hwsim_set_chanctx_magic(ctx);
-	wiphy_debug(hw->wiphy,
-		    "add channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n",
-		    ctx->def.chan->center_freq, ctx->def.width,
-		    ctx->def.center_freq1, ctx->def.center_freq2);
+	wiphy_dbg(hw->wiphy,
+		  "add channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n",
+		  ctx->def.chan->center_freq, ctx->def.width,
+		  ctx->def.center_freq1, ctx->def.center_freq2);
 	return 0;
 }
 
 static void mac80211_hwsim_remove_chanctx(struct ieee80211_hw *hw,
 					  struct ieee80211_chanctx_conf *ctx)
 {
-	wiphy_debug(hw->wiphy,
-		    "remove channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n",
-		    ctx->def.chan->center_freq, ctx->def.width,
-		    ctx->def.center_freq1, ctx->def.center_freq2);
+	wiphy_dbg(hw->wiphy,
+		  "remove channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n",
+		  ctx->def.chan->center_freq, ctx->def.width,
+		  ctx->def.center_freq1, ctx->def.center_freq2);
 	hwsim_check_chanctx_magic(ctx);
 	hwsim_clear_chanctx_magic(ctx);
 }
@@ -2222,10 +2222,10 @@ static void mac80211_hwsim_change_chanctx(struct ieee80211_hw *hw,
 					  u32 changed)
 {
 	hwsim_check_chanctx_magic(ctx);
-	wiphy_debug(hw->wiphy,
-		    "change channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n",
-		    ctx->def.chan->center_freq, ctx->def.width,
-		    ctx->def.center_freq1, ctx->def.center_freq2);
+	wiphy_dbg(hw->wiphy,
+		  "change channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n",
+		  ctx->def.chan->center_freq, ctx->def.width,
+		  ctx->def.center_freq1, ctx->def.center_freq2);
 }
 
 static int mac80211_hwsim_assign_vif_chanctx(struct ieee80211_hw *hw,
@@ -2479,7 +2479,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 		ops = &mac80211_hwsim_mchan_ops;
 	hw = ieee80211_alloc_hw_nm(sizeof(*data), ops, param->hwname);
 	if (!hw) {
-		printk(KERN_DEBUG "mac80211_hwsim: ieee80211_alloc_hw failed\n");
+		pr_debug("mac80211_hwsim: ieee80211_alloc_hw failed\n");
 		err = -ENOMEM;
 		goto failed;
 	}
@@ -2507,7 +2507,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 	data->dev->driver = &mac80211_hwsim_driver.driver;
 	err = device_bind_driver(data->dev);
 	if (err != 0) {
-		printk(KERN_DEBUG "mac80211_hwsim: device_bind_driver failed (%d)\n",
+		pr_debug("mac80211_hwsim: device_bind_driver failed (%d)\n",
 		       err);
 		goto failed_bind;
 	}
@@ -2698,12 +2698,12 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 
 	err = ieee80211_register_hw(hw);
 	if (err < 0) {
-		printk(KERN_DEBUG "mac80211_hwsim: ieee80211_register_hw failed (%d)\n",
+		pr_debug("mac80211_hwsim: ieee80211_register_hw failed (%d)\n",
 		       err);
 		goto failed_hw;
 	}
 
-	wiphy_debug(hw->wiphy, "hwaddr %pM registered\n", hw->wiphy->perm_addr);
+	wiphy_dbg(hw->wiphy, "hwaddr %pM registered\n", hw->wiphy->perm_addr);
 
 	if (param->reg_alpha2) {
 		data->alpha2[0] = param->reg_alpha2[0];
@@ -3067,7 +3067,7 @@ static int hwsim_cloned_frame_received_nl(struct sk_buff *skb_2,
 
 	return 0;
 err:
-	printk(KERN_DEBUG "mac80211_hwsim: error occurred in %s\n", __func__);
+	pr_debug("mac80211_hwsim: error occurred in %s\n", __func__);
 out:
 	dev_kfree_skb(skb);
 	return -EINVAL;
@@ -3098,7 +3098,7 @@ static int hwsim_register_received_nl(struct sk_buff *skb_2,
 
 	hwsim_register_wmediumd(net, info->snd_portid);
 
-	printk(KERN_DEBUG "mac80211_hwsim: received a REGISTER, "
+	pr_debug("mac80211_hwsim: received a REGISTER, "
 	       "switching to wmediumd mode with pid %d\n", info->snd_portid);
 
 	return 0;
@@ -3387,7 +3387,7 @@ static int __init hwsim_init_netlink(void)
 	return 0;
 
 failure:
-	printk(KERN_DEBUG "mac80211_hwsim: error occurred in %s\n", __func__);
+	pr_debug("mac80211_hwsim: error occurred in %s\n", __func__);
 	return -EINVAL;
 }
 
@@ -3578,7 +3578,7 @@ module_init(init_mac80211_hwsim);
 
 static void __exit exit_mac80211_hwsim(void)
 {
-	printk(KERN_DEBUG "mac80211_hwsim: unregister radios\n");
+	pr_debug("mac80211_hwsim: unregister radios\n");
 
 	hwsim_exit_netlink();
 
diff --git a/drivers/net/wireless/marvell/mwifiex/11n.c b/drivers/net/wireless/marvell/mwifiex/11n.c
index 725206914911..8772e3949327 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n.c
@@ -658,12 +658,6 @@ void mwifiex_11n_delba(struct mwifiex_private *priv, int tid)
 	unsigned long flags;
 
 	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
-	if (list_empty(&priv->rx_reorder_tbl_ptr)) {
-		dev_dbg(priv->adapter->dev,
-			"mwifiex_11n_delba: rx_reorder_tbl_ptr empty\n");
-		goto exit;
-	}
-
 	list_for_each_entry(rx_reor_tbl_ptr, &priv->rx_reorder_tbl_ptr, list) {
 		if (rx_reor_tbl_ptr->tid == tid) {
 			dev_dbg(priv->adapter->dev,
@@ -854,9 +848,6 @@ mwifiex_send_delba_txbastream_tbl(struct mwifiex_private *priv, u8 tid)
 	struct mwifiex_adapter *adapter = priv->adapter;
 	struct mwifiex_tx_ba_stream_tbl *tx_ba_stream_tbl_ptr;
 
-	if (list_empty(&priv->tx_ba_stream_tbl_ptr))
-		return;
-
 	list_for_each_entry(tx_ba_stream_tbl_ptr,
 			    &priv->tx_ba_stream_tbl_ptr, list) {
 		if (tx_ba_stream_tbl_ptr->ba_status == BA_SETUP_COMPLETE) {
diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
index 274dd5a1574a..d87df2dfcfa4 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
@@ -835,12 +835,6 @@ void mwifiex_update_rxreor_flags(struct mwifiex_adapter *adapter, u8 flags)
 			continue;
 
 		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, lock_flags);
-		if (list_empty(&priv->rx_reorder_tbl_ptr)) {
-			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
-					       lock_flags);
-			continue;
-		}
-
 		list_for_each_entry(tbl, &priv->rx_reorder_tbl_ptr, list)
 			tbl->flags = flags;
 		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, lock_flags);
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 32c5074da84c..6e0d9a9c5cfb 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -142,7 +142,7 @@ mwifiex_cfg80211_del_key(struct wiphy *wiphy, struct net_device *netdev,
 			 u8 key_index, bool pairwise, const u8 *mac_addr)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(netdev);
-	const u8 bc_mac[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+	static const u8 bc_mac[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
 	const u8 *peer_mac = pairwise ? mac_addr : bc_mac;
 
 	if (mwifiex_set_encode(priv, NULL, NULL, 0, key_index, peer_mac, 1)) {
@@ -454,7 +454,7 @@ mwifiex_cfg80211_add_key(struct wiphy *wiphy, struct net_device *netdev,
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(netdev);
 	struct mwifiex_wep_key *wep_key;
-	const u8 bc_mac[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+	static const u8 bc_mac[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
 	const u8 *peer_mac = pairwise ? mac_addr : bc_mac;
 
 	if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP &&
@@ -2503,6 +2503,7 @@ mwifiex_cfg80211_scan(struct wiphy *wiphy,
 	struct ieee80211_channel *chan;
 	struct ieee_types_header *ie;
 	struct mwifiex_user_scan_cfg *user_scan_cfg;
+	u8 mac_addr[ETH_ALEN];
 
 	mwifiex_dbg(priv->adapter, CMD,
 		    "info: received scan request on %s\n", dev->name);
@@ -2529,15 +2530,10 @@ mwifiex_cfg80211_scan(struct wiphy *wiphy,
 	priv->scan_request = request;
 
 	if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
-		ether_addr_copy(priv->random_mac, request->mac_addr);
-		for (i = 0; i < ETH_ALEN; i++) {
-			priv->random_mac[i] &= request->mac_addr_mask[i];
-			priv->random_mac[i] |= get_random_int() &
-					       ~(request->mac_addr_mask[i]);
-		}
-		ether_addr_copy(user_scan_cfg->random_mac, priv->random_mac);
-	} else {
-		eth_zero_addr(priv->random_mac);
+		get_random_mask_addr(mac_addr, request->mac_addr,
+				     request->mac_addr_mask);
+		ether_addr_copy(request->mac_addr, mac_addr);
+		ether_addr_copy(user_scan_cfg->random_mac, mac_addr);
 	}
 
 	user_scan_cfg->num_ssids = request->n_ssids;
@@ -2959,18 +2955,21 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy,
 	}
 
 	mwifiex_init_priv_params(priv, dev);
-	mwifiex_set_mac_address(priv, dev);
 
 	priv->netdev = dev;
 
-	ret = mwifiex_send_cmd(priv, HostCmd_CMD_SET_BSS_MODE,
-			       HostCmd_ACT_GEN_SET, 0, NULL, true);
-	if (ret)
-		goto err_set_bss_mode;
+	if (!adapter->mfg_mode) {
+		mwifiex_set_mac_address(priv, dev);
 
-	ret = mwifiex_sta_init_cmd(priv, false, false);
-	if (ret)
-		goto err_sta_init;
+		ret = mwifiex_send_cmd(priv, HostCmd_CMD_SET_BSS_MODE,
+				       HostCmd_ACT_GEN_SET, 0, NULL, true);
+		if (ret)
+			goto err_set_bss_mode;
+
+		ret = mwifiex_sta_init_cmd(priv, false, false);
+		if (ret)
+			goto err_sta_init;
+	}
 
 	mwifiex_setup_ht_caps(&wiphy->bands[NL80211_BAND_2GHZ]->ht_cap, priv);
 	if (adapter->is_hw_11ac_capable)
@@ -3250,8 +3249,8 @@ static int mwifiex_set_wowlan_mef_entry(struct mwifiex_private *priv,
 	int i, filt_num = 0, ret = 0;
 	bool first_pat = true;
 	u8 byte_seq[MWIFIEX_MEF_MAX_BYTESEQ + 1];
-	const u8 ipv4_mc_mac[] = {0x33, 0x33};
-	const u8 ipv6_mc_mac[] = {0x01, 0x00, 0x5e};
+	static const u8 ipv4_mc_mac[] = {0x33, 0x33};
+	static const u8 ipv6_mc_mac[] = {0x01, 0x00, 0x5e};
 
 	mef_entry->mode = MEF_MODE_HOST_SLEEP;
 	mef_entry->action = MEF_ACTION_ALLOW_AND_WAKEUP_HOST;
@@ -3544,9 +3543,9 @@ static int mwifiex_set_rekey_data(struct wiphy *wiphy, struct net_device *dev,
 
 static int mwifiex_get_coalesce_pkt_type(u8 *byte_seq)
 {
-	const u8 ipv4_mc_mac[] = {0x33, 0x33};
-	const u8 ipv6_mc_mac[] = {0x01, 0x00, 0x5e};
-	const u8 bc_mac[] = {0xff, 0xff, 0xff, 0xff};
+	static const u8 ipv4_mc_mac[] = {0x33, 0x33};
+	static const u8 ipv6_mc_mac[] = {0x01, 0x00, 0x5e};
+	static const u8 bc_mac[] = {0xff, 0xff, 0xff, 0xff};
 
 	if ((byte_seq[0] & 0x01) &&
 	    (byte_seq[MWIFIEX_COALESCE_MAX_BYTESEQ] == 1))
@@ -3795,9 +3794,8 @@ mwifiex_cfg80211_tdls_chan_switch(struct wiphy *wiphy, struct net_device *dev,
 
 	spin_lock_irqsave(&priv->sta_list_spinlock, flags);
 	sta_ptr = mwifiex_get_sta_entry(priv, addr);
-	spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
-
 	if (!sta_ptr) {
+		spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
 		wiphy_err(wiphy, "%s: Invalid TDLS peer %pM\n",
 			  __func__, addr);
 		return -ENOENT;
@@ -3805,15 +3803,18 @@ mwifiex_cfg80211_tdls_chan_switch(struct wiphy *wiphy, struct net_device *dev,
 
 	if (!(sta_ptr->tdls_cap.extcap.ext_capab[3] &
 	      WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH)) {
+		spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
 		wiphy_err(wiphy, "%pM do not support tdls cs\n", addr);
 		return -ENOENT;
 	}
 
 	if (sta_ptr->tdls_status == TDLS_CHAN_SWITCHING ||
 	    sta_ptr->tdls_status == TDLS_IN_OFF_CHAN) {
+		spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
 		wiphy_err(wiphy, "channel switch is running, abort request\n");
 		return -EALREADY;
 	}
+	spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
 
 	chan = chandef->chan->hw_value;
 	second_chan_offset = mwifiex_get_sec_chan_offset(chan);
@@ -3834,18 +3835,20 @@ mwifiex_cfg80211_tdls_cancel_chan_switch(struct wiphy *wiphy,
 
 	spin_lock_irqsave(&priv->sta_list_spinlock, flags);
 	sta_ptr = mwifiex_get_sta_entry(priv, addr);
-	spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
-
 	if (!sta_ptr) {
+		spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
 		wiphy_err(wiphy, "%s: Invalid TDLS peer %pM\n",
 			  __func__, addr);
 	} else if (!(sta_ptr->tdls_status == TDLS_CHAN_SWITCHING ||
 		     sta_ptr->tdls_status == TDLS_IN_BASE_CHAN ||
 		     sta_ptr->tdls_status == TDLS_IN_OFF_CHAN)) {
+		spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
 		wiphy_err(wiphy, "tdls chan switch not initialize by %pM\n",
 			  addr);
-	} else
+	} else {
+		spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
 		mwifiex_stop_tdls_cs(priv, addr);
+	}
 }
 
 static int
@@ -4202,7 +4205,10 @@ int mwifiex_init_channel_scan_gap(struct mwifiex_adapter *adapter)
 	if (adapter->config_bands & BAND_A)
 		n_channels_a = mwifiex_band_5ghz.n_channels;
 
-	adapter->num_in_chan_stats = n_channels_bg + n_channels_a;
+	/* allocate twice the number total channels, since the driver issues an
+	 * additional active scan request for hidden SSIDs on passive channels.
+	 */
+	adapter->num_in_chan_stats = 2 * (n_channels_bg + n_channels_a);
 	adapter->chan_stats = vmalloc(sizeof(*adapter->chan_stats) *
 				      adapter->num_in_chan_stats);
 
@@ -4306,10 +4312,12 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
 	wiphy->features |= NL80211_FEATURE_HT_IBSS |
 			   NL80211_FEATURE_INACTIVITY_TIMER |
 			   NL80211_FEATURE_LOW_PRIORITY_SCAN |
-			   NL80211_FEATURE_NEED_OBSS_SCAN |
-			   NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR |
-			   NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR |
-			   NL80211_FEATURE_ND_RANDOM_MAC_ADDR;
+			   NL80211_FEATURE_NEED_OBSS_SCAN;
+
+	if (ISSUPP_RANDOM_MAC(adapter->fw_cap_info))
+		wiphy->features |= NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR |
+				   NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR |
+				   NL80211_FEATURE_ND_RANDOM_MAC_ADDR;
 
 	if (ISSUPP_TDLS_ENABLED(adapter->fw_cap_info))
 		wiphy->features |= NL80211_FEATURE_TDLS_CHANNEL_SWITCH;
diff --git a/drivers/net/wireless/marvell/mwifiex/cmdevt.c b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
index 0edc5d621304..a9a1a736e6e8 100644
--- a/drivers/net/wireless/marvell/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
@@ -17,6 +17,7 @@
  * this warranty disclaimer.
  */
 
+#include <asm/unaligned.h>
 #include "decl.h"
 #include "ioctl.h"
 #include "util.h"
@@ -183,7 +184,6 @@ static int mwifiex_dnld_cmd_to_fw(struct mwifiex_private *priv,
 	uint16_t cmd_code;
 	uint16_t cmd_size;
 	unsigned long flags;
-	__le32 tmp;
 
 	if (!adapter || !cmd_node)
 		return -1;
@@ -249,9 +249,9 @@ static int mwifiex_dnld_cmd_to_fw(struct mwifiex_private *priv,
 	mwifiex_dbg_dump(adapter, CMD_D, "cmd buffer:", host_cmd, cmd_size);
 
 	if (adapter->iface_type == MWIFIEX_USB) {
-		tmp = cpu_to_le32(MWIFIEX_USB_TYPE_CMD);
 		skb_push(cmd_node->cmd_skb, MWIFIEX_TYPE_LEN);
-		memcpy(cmd_node->cmd_skb->data, &tmp, MWIFIEX_TYPE_LEN);
+		put_unaligned_le32(MWIFIEX_USB_TYPE_CMD,
+				   cmd_node->cmd_skb->data);
 		adapter->cmd_sent = true;
 		ret = adapter->if_ops.host_to_card(adapter,
 						   MWIFIEX_USB_EP_CMD_EVENT,
@@ -317,7 +317,6 @@ static int mwifiex_dnld_sleep_confirm_cmd(struct mwifiex_adapter *adapter)
 				(struct mwifiex_opt_sleep_confirm *)
 						adapter->sleep_cfm->data;
 	struct sk_buff *sleep_cfm_tmp;
-	__le32 tmp;
 
 	priv = mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_ANY);
 
@@ -342,8 +341,7 @@ static int mwifiex_dnld_sleep_confirm_cmd(struct mwifiex_adapter *adapter)
 				      + MWIFIEX_TYPE_LEN);
 		skb_put(sleep_cfm_tmp, sizeof(struct mwifiex_opt_sleep_confirm)
 			+ MWIFIEX_TYPE_LEN);
-		tmp = cpu_to_le32(MWIFIEX_USB_TYPE_CMD);
-		memcpy(sleep_cfm_tmp->data, &tmp, MWIFIEX_TYPE_LEN);
+		put_unaligned_le32(MWIFIEX_USB_TYPE_CMD, sleep_cfm_tmp->data);
 		memcpy(sleep_cfm_tmp->data + MWIFIEX_TYPE_LEN,
 		       adapter->sleep_cfm->data,
 		       sizeof(struct mwifiex_opt_sleep_confirm));
diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h
index 9e75522d248a..6b765f3f37fd 100644
--- a/drivers/net/wireless/marvell/mwifiex/fw.h
+++ b/drivers/net/wireless/marvell/mwifiex/fw.h
@@ -238,6 +238,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER {
 #define ISSUPP_DRCS_ENABLED(FwCapInfo) (FwCapInfo & BIT(15))
 #define ISSUPP_SDIO_SPA_ENABLED(FwCapInfo) (FwCapInfo & BIT(16))
 #define ISSUPP_ADHOC_ENABLED(FwCapInfo) (FwCapInfo & BIT(25))
+#define ISSUPP_RANDOM_MAC(FwCapInfo) (FwCapInfo & BIT(27))
 
 #define MWIFIEX_DEF_HT_CAP	(IEEE80211_HT_CAP_DSSSCCK40 | \
 				 (1 << IEEE80211_HT_CAP_RX_STBC_SHIFT) | \
diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c
index e11919db7818..1176706ab094 100644
--- a/drivers/net/wireless/marvell/mwifiex/init.c
+++ b/drivers/net/wireless/marvell/mwifiex/init.c
@@ -579,10 +579,6 @@ static void mwifiex_delete_bss_prio_tbl(struct mwifiex_private *priv)
 
 		{
 			spin_lock_irqsave(lock, flags);
-			if (list_empty(head)) {
-				spin_unlock_irqrestore(lock, flags);
-				continue;
-			}
 			list_for_each_entry_safe(bssprio_node, tmp_node, head,
 						 list) {
 				if (bssprio_node->priv == priv) {
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index a76bd797e454..a34de8582e91 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -680,7 +680,6 @@ struct mwifiex_private {
 	struct mwifiex_user_scan_chan hidden_chan[MWIFIEX_USER_SCAN_CHAN_MAX];
 	u8 assoc_resp_ht_param;
 	bool ht_param_present;
-	u8 random_mac[ETH_ALEN];
 };
 
 
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index c9d41ed77fc7..d7ce7f75ae38 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -1936,8 +1936,6 @@ mwifiex_active_scan_req_for_passive_chan(struct mwifiex_private *priv)
 	if (!user_scan_cfg)
 		return -ENOMEM;
 
-	memset(user_scan_cfg, 0, sizeof(*user_scan_cfg));
-
 	for (id = 0; id < MWIFIEX_USER_SCAN_CHAN_MAX; id++) {
 		if (!priv->hidden_chan[id].chan_number)
 			break;
@@ -1948,7 +1946,8 @@ mwifiex_active_scan_req_for_passive_chan(struct mwifiex_private *priv)
 
 	adapter->active_scan_triggered = true;
 	if (priv->scan_request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)
-		ether_addr_copy(user_scan_cfg->random_mac, priv->random_mac);
+		ether_addr_copy(user_scan_cfg->random_mac,
+				priv->scan_request->mac_addr);
 	user_scan_cfg->num_ssids = priv->scan_request->n_ssids;
 	user_scan_cfg->ssid_list = priv->scan_request->ssids;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
index 0fba5b10ef2d..1bd4e13b8449 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
@@ -70,11 +70,7 @@ mwifiex_process_cmdresp_error(struct mwifiex_private *priv,
 		break;
 	case HostCmd_CMD_802_11_SCAN:
 	case HostCmd_CMD_802_11_SCAN_EXT:
-		mwifiex_cancel_pending_scan_cmd(adapter);
-
-		spin_lock_irqsave(&adapter->mwifiex_cmd_lock, flags);
-		adapter->scan_processing = false;
-		spin_unlock_irqrestore(&adapter->mwifiex_cmd_lock, flags);
+		mwifiex_cancel_scan(adapter);
 		break;
 
 	case HostCmd_CMD_MAC_CONTROL:
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_event.c b/drivers/net/wireless/marvell/mwifiex/sta_event.c
index 839df8a9634e..d8db412b76c6 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_event.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_event.c
@@ -359,13 +359,12 @@ static void mwifiex_process_uap_tx_pause(struct mwifiex_private *priv,
 	} else {
 		spin_lock_irqsave(&priv->sta_list_spinlock, flags);
 		sta_ptr = mwifiex_get_sta_entry(priv, tp->peermac);
-		spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
-
 		if (sta_ptr && sta_ptr->tx_pause != tp->tx_pause) {
 			sta_ptr->tx_pause = tp->tx_pause;
 			mwifiex_update_ralist_tx_pause(priv, tp->peermac,
 						       tp->tx_pause);
 		}
+		spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
 	}
 }
 
@@ -396,14 +395,13 @@ static void mwifiex_process_sta_tx_pause(struct mwifiex_private *priv,
 		if (mwifiex_is_tdls_link_setup(status)) {
 			spin_lock_irqsave(&priv->sta_list_spinlock, flags);
 			sta_ptr = mwifiex_get_sta_entry(priv, tp->peermac);
-			spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
-
 			if (sta_ptr && sta_ptr->tx_pause != tp->tx_pause) {
 				sta_ptr->tx_pause = tp->tx_pause;
 				mwifiex_update_ralist_tx_pause(priv,
 							       tp->peermac,
 							       tp->tx_pause);
 			}
+			spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
 		}
 	}
 }
diff --git a/drivers/net/wireless/marvell/mwifiex/tdls.c b/drivers/net/wireless/marvell/mwifiex/tdls.c
index e76af2866a19..9fe0bae957b7 100644
--- a/drivers/net/wireless/marvell/mwifiex/tdls.c
+++ b/drivers/net/wireless/marvell/mwifiex/tdls.c
@@ -1413,13 +1413,6 @@ void mwifiex_check_auto_tdls(unsigned long context)
 
 	priv->check_tdls_tx = false;
 
-	if (list_empty(&priv->auto_tdls_list)) {
-		mod_timer(&priv->auto_tdls_timer,
-			  jiffies +
-			  msecs_to_jiffies(MWIFIEX_TIMER_10S));
-		return;
-	}
-
 	spin_lock_irqsave(&priv->auto_tdls_lock, flags);
 	list_for_each_entry(tdls_peer, &priv->auto_tdls_list, list) {
 		if ((jiffies - tdls_peer->rssi_jiffies) >
diff --git a/drivers/net/wireless/marvell/mwifiex/wmm.c b/drivers/net/wireless/marvell/mwifiex/wmm.c
index 0edd26881321..936a0a841af8 100644
--- a/drivers/net/wireless/marvell/mwifiex/wmm.c
+++ b/drivers/net/wireless/marvell/mwifiex/wmm.c
@@ -359,7 +359,8 @@ static enum mwifiex_wmm_ac_e
 mwifiex_wmm_convert_tos_to_ac(struct mwifiex_adapter *adapter, u32 tos)
 {
 	/* Map of TOS UP values to WMM AC */
-	const enum mwifiex_wmm_ac_e tos_to_ac[] = { WMM_AC_BE,
+	static const enum mwifiex_wmm_ac_e tos_to_ac[] = {
+		WMM_AC_BE,
 		WMM_AC_BK,
 		WMM_AC_BK,
 		WMM_AC_BE,
diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
index a450bc6bc774..ebc3792a95bd 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
@@ -133,6 +133,7 @@ int qtnf_del_virtual_intf(struct wiphy *wiphy, struct wireless_dev *wdev)
 	vif->netdev = NULL;
 	vif->wdev.iftype = NL80211_IFTYPE_UNSPECIFIED;
 	eth_zero_addr(vif->mac_addr);
+	eth_zero_addr(vif->bssid);
 
 	return 0;
 }
@@ -201,6 +202,8 @@ err_mac:
 	qtnf_cmd_send_del_intf(vif);
 err_cmd:
 	vif->wdev.iftype = NL80211_IFTYPE_UNSPECIFIED;
+	eth_zero_addr(vif->mac_addr);
+	eth_zero_addr(vif->bssid);
 
 	return ERR_PTR(-EFAULT);
 }
@@ -256,11 +259,6 @@ static int qtnf_change_beacon(struct wiphy *wiphy, struct net_device *dev,
 {
 	struct qtnf_vif *vif = qtnf_netdev_get_priv(dev);
 
-	if (!(vif->bss_status & QTNF_STATE_AP_START)) {
-		pr_err("VIF%u.%u: not started\n", vif->mac->macid, vif->vifid);
-		return -EFAULT;
-	}
-
 	return qtnf_mgmt_set_appie(vif, info);
 }
 
@@ -268,46 +266,15 @@ static int qtnf_start_ap(struct wiphy *wiphy, struct net_device *dev,
 			 struct cfg80211_ap_settings *settings)
 {
 	struct qtnf_vif *vif = qtnf_netdev_get_priv(dev);
-	struct qtnf_wmac *mac = wiphy_priv(wiphy);
-	struct qtnf_bss_config *bss_cfg;
 	int ret;
 
-	if (!cfg80211_chandef_identical(&mac->chandef, &settings->chandef)) {
-		memcpy(&mac->chandef, &settings->chandef, sizeof(mac->chandef));
-		if (vif->vifid != 0)
-			pr_warn("%s: unexpected chan %u (%u MHz)\n", dev->name,
-				settings->chandef.chan->hw_value,
-				settings->chandef.chan->center_freq);
-	}
-
-	bss_cfg = &vif->bss_cfg;
-	memset(bss_cfg, 0, sizeof(*bss_cfg));
-
-	bss_cfg->bcn_period = settings->beacon_interval;
-	bss_cfg->dtim = settings->dtim_period;
-	bss_cfg->auth_type = settings->auth_type;
-	bss_cfg->privacy = settings->privacy;
-
-	bss_cfg->ssid_len = settings->ssid_len;
-	memcpy(&bss_cfg->ssid, settings->ssid, bss_cfg->ssid_len);
-
-	memcpy(&bss_cfg->crypto, &settings->crypto,
-	       sizeof(struct cfg80211_crypto_settings));
-
-	ret = qtnf_cmd_send_config_ap(vif);
+	ret = qtnf_cmd_send_config_ap(vif, settings);
 	if (ret) {
 		pr_err("VIF%u.%u: failed to push config to FW\n",
 		       vif->mac->macid, vif->vifid);
 		goto out;
 	}
 
-	if (!(vif->bss_status & QTNF_STATE_AP_CONFIG)) {
-		pr_err("VIF%u.%u: AP config failed in FW\n", vif->mac->macid,
-		       vif->vifid);
-		ret = -EFAULT;
-		goto out;
-	}
-
 	ret = qtnf_mgmt_set_appie(vif, &settings->beacon);
 	if (ret) {
 		pr_err("VIF%u.%u: failed to add IEs to beacon\n",
@@ -316,17 +283,9 @@ static int qtnf_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	}
 
 	ret = qtnf_cmd_send_start_ap(vif);
-	if (ret) {
+	if (ret)
 		pr_err("VIF%u.%u: failed to start AP\n", vif->mac->macid,
 		       vif->vifid);
-		goto out;
-	}
-
-	if (!(vif->bss_status & QTNF_STATE_AP_START)) {
-		pr_err("VIF%u.%u: FW failed to start AP operation\n",
-		       vif->mac->macid, vif->vifid);
-		ret = -EFAULT;
-	}
 
 out:
 	return ret;
@@ -343,8 +302,6 @@ static int qtnf_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	if (ret) {
 		pr_err("VIF%u.%u: failed to stop AP operation in FW\n",
 		       vif->mac->macid, vif->vifid);
-		vif->bss_status &= ~QTNF_STATE_AP_START;
-		vif->bss_status &= ~QTNF_STATE_AP_CONFIG;
 
 		netif_carrier_off(vif->netdev);
 	}
@@ -615,9 +572,6 @@ qtnf_connect(struct wiphy *wiphy, struct net_device *dev,
 	     struct cfg80211_connect_params *sme)
 {
 	struct qtnf_vif *vif = qtnf_netdev_get_priv(dev);
-	struct qtnf_wmac *mac = wiphy_priv(wiphy);
-	struct cfg80211_chan_def chandef;
-	struct qtnf_bss_config *bss_cfg;
 	int ret;
 
 	if (vif->wdev.iftype != NL80211_IFTYPE_STATION)
@@ -626,49 +580,10 @@ qtnf_connect(struct wiphy *wiphy, struct net_device *dev,
 	if (vif->sta_state != QTNF_STA_DISCONNECTED)
 		return -EBUSY;
 
-	bss_cfg = &vif->bss_cfg;
-	memset(bss_cfg, 0, sizeof(*bss_cfg));
-
-	if (sme->channel) {
-		/* FIXME: need to set proper nl80211_channel_type value */
-		cfg80211_chandef_create(&chandef, sme->channel,
-					NL80211_CHAN_HT20);
-		/* fall-back to minimal safe chandef description */
-		if (!cfg80211_chandef_valid(&chandef))
-			cfg80211_chandef_create(&chandef, sme->channel,
-						NL80211_CHAN_HT20);
-
-		memcpy(&mac->chandef, &chandef, sizeof(mac->chandef));
-	}
-
-	bss_cfg->ssid_len = sme->ssid_len;
-	memcpy(&bss_cfg->ssid, sme->ssid, bss_cfg->ssid_len);
-	bss_cfg->auth_type = sme->auth_type;
-	bss_cfg->privacy = sme->privacy;
-	bss_cfg->mfp = sme->mfp;
-
-	if ((sme->bg_scan_period > 0) &&
-	    (sme->bg_scan_period <= QTNF_MAX_BG_SCAN_PERIOD))
-		bss_cfg->bg_scan_period = sme->bg_scan_period;
-	else if (sme->bg_scan_period == -1)
-		bss_cfg->bg_scan_period = QTNF_DEFAULT_BG_SCAN_PERIOD;
-	else
-		bss_cfg->bg_scan_period = 0; /* disabled */
-
-	bss_cfg->connect_flags = 0;
-
-	if (sme->flags & ASSOC_REQ_DISABLE_HT)
-		bss_cfg->connect_flags |= QLINK_STA_CONNECT_DISABLE_HT;
-	if (sme->flags & ASSOC_REQ_DISABLE_VHT)
-		bss_cfg->connect_flags |= QLINK_STA_CONNECT_DISABLE_VHT;
-	if (sme->flags & ASSOC_REQ_USE_RRM)
-		bss_cfg->connect_flags |= QLINK_STA_CONNECT_USE_RRM;
-
-	memcpy(&bss_cfg->crypto, &sme->crypto, sizeof(bss_cfg->crypto));
 	if (sme->bssid)
-		ether_addr_copy(bss_cfg->bssid, sme->bssid);
+		ether_addr_copy(vif->bssid, sme->bssid);
 	else
-		eth_zero_addr(bss_cfg->bssid);
+		eth_zero_addr(vif->bssid);
 
 	ret = qtnf_cmd_send_connect(vif, sme);
 	if (ret) {
@@ -717,15 +632,15 @@ qtnf_dump_survey(struct wiphy *wiphy, struct net_device *dev,
 		 int idx, struct survey_info *survey)
 {
 	struct qtnf_wmac *mac = wiphy_priv(wiphy);
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct ieee80211_supported_band *sband;
-	struct cfg80211_chan_def *chandef;
+	const struct cfg80211_chan_def *chandef = &wdev->chandef;
 	struct ieee80211_channel *chan;
 	struct qtnf_chan_stats stats;
 	struct qtnf_vif *vif;
 	int ret;
 
 	vif = qtnf_netdev_get_priv(dev);
-	chandef = &mac->chandef;
 
 	sband = wiphy->bands[NL80211_BAND_2GHZ];
 	if (sband && idx >= sband->n_channels) {
@@ -792,46 +707,35 @@ static int
 qtnf_get_channel(struct wiphy *wiphy, struct wireless_dev *wdev,
 		 struct cfg80211_chan_def *chandef)
 {
-	struct qtnf_wmac *mac = wiphy_priv(wiphy);
 	struct net_device *ndev = wdev->netdev;
 	struct qtnf_vif *vif;
+	int ret;
 
 	if (!ndev)
 		return -ENODEV;
 
 	vif = qtnf_netdev_get_priv(wdev->netdev);
 
-	switch (vif->wdev.iftype) {
-	case NL80211_IFTYPE_STATION:
-		if (vif->sta_state == QTNF_STA_DISCONNECTED) {
-			pr_warn("%s: STA disconnected\n", ndev->name);
-			return -ENODATA;
-		}
-		break;
-	case NL80211_IFTYPE_AP:
-		if (!(vif->bss_status & QTNF_STATE_AP_START)) {
-			pr_warn("%s: AP not started\n", ndev->name);
-			return -ENODATA;
-		}
-		break;
-	default:
-		pr_err("unsupported vif type (%d)\n", vif->wdev.iftype);
-		return -ENODATA;
+	ret = qtnf_cmd_get_channel(vif, chandef);
+	if (ret) {
+		pr_err("%s: failed to get channel: %d\n", ndev->name, ret);
+		goto out;
 	}
 
-	if (!cfg80211_chandef_valid(&mac->chandef)) {
-		pr_err("invalid channel settings on %s\n", ndev->name);
-		return -ENODATA;
+	if (!cfg80211_chandef_valid(chandef)) {
+		pr_err("%s: bad chan freq1=%u freq2=%u bw=%u\n", ndev->name,
+		       chandef->center_freq1, chandef->center_freq2,
+		       chandef->width);
+		ret = -ENODATA;
 	}
 
-	memcpy(chandef, &mac->chandef, sizeof(*chandef));
-	return 0;
+out:
+	return ret;
 }
 
 static int qtnf_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 			       struct cfg80211_csa_settings *params)
 {
-	struct qtnf_wmac *mac = wiphy_priv(wiphy);
 	struct qtnf_vif *vif = qtnf_netdev_get_priv(dev);
 	int ret;
 
@@ -839,41 +743,12 @@ static int qtnf_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 		 params->chandef.chan->hw_value, params->count,
 		 params->radar_required, params->block_tx);
 
-	switch (vif->wdev.iftype) {
-	case NL80211_IFTYPE_AP:
-		if (!(vif->bss_status & QTNF_STATE_AP_START)) {
-			pr_warn("AP not started on %s\n", dev->name);
-			return -ENOTCONN;
-		}
-		break;
-	default:
-		pr_err("unsupported vif type (%d) on %s\n",
-		       vif->wdev.iftype, dev->name);
-		return -EOPNOTSUPP;
-	}
-
-	if (vif->vifid != 0) {
-		if (!(mac->status & QTNF_MAC_CSA_ACTIVE))
-			return -EOPNOTSUPP;
-
-		if (!cfg80211_chandef_identical(&params->chandef,
-						&mac->csa_chandef))
-			return -EINVAL;
-
-		return 0;
-	}
-
 	if (!cfg80211_chandef_valid(&params->chandef)) {
 		pr_err("%s: invalid channel\n", dev->name);
 		return -EINVAL;
 	}
 
-	if (cfg80211_chandef_identical(&params->chandef, &mac->chandef)) {
-		pr_err("%s: switch request to the same channel\n", dev->name);
-		return -EALREADY;
-	}
-
-	ret = qtnf_cmd_send_chan_switch(mac, params);
+	ret = qtnf_cmd_send_chan_switch(vif, params);
 	if (ret)
 		pr_warn("%s: failed to switch to channel (%u)\n",
 			dev->name, params->chandef.chan->hw_value);
@@ -1119,7 +994,7 @@ void qtnf_virtual_intf_cleanup(struct net_device *ndev)
 			break;
 		case QTNF_STA_CONNECTING:
 			cfg80211_connect_result(vif->netdev,
-						vif->bss_cfg.bssid, NULL, 0,
+						vif->bssid, NULL, 0,
 						NULL, 0,
 						WLAN_STATUS_UNSPECIFIED_FAILURE,
 						GFP_KERNEL);
@@ -1147,7 +1022,7 @@ void qtnf_cfg80211_vif_reset(struct qtnf_vif *vif)
 		switch (vif->sta_state) {
 		case QTNF_STA_CONNECTING:
 			cfg80211_connect_result(vif->netdev,
-						vif->bss_cfg.bssid, NULL, 0,
+						vif->bssid, NULL, 0,
 						NULL, 0,
 						WLAN_STATUS_UNSPECIFIED_FAILURE,
 						GFP_KERNEL);
diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c
index 4206886b110c..babdc600c193 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c
@@ -173,7 +173,6 @@ int qtnf_cmd_send_start_ap(struct qtnf_vif *vif)
 		goto out;
 	}
 
-	vif->bss_status |= QTNF_STATE_AP_START;
 	netif_carrier_on(vif->netdev);
 
 out:
@@ -181,62 +180,68 @@ out:
 	return ret;
 }
 
-int qtnf_cmd_send_config_ap(struct qtnf_vif *vif)
+int qtnf_cmd_send_config_ap(struct qtnf_vif *vif,
+			    const struct cfg80211_ap_settings *s)
 {
 	struct sk_buff *cmd_skb;
-	struct qtnf_bss_config *bss_cfg = &vif->bss_cfg;
-	struct cfg80211_chan_def *chandef = &vif->mac->chandef;
-	struct qlink_tlv_channel *qchan;
-	struct qlink_auth_encr aen;
+	struct qlink_cmd_config_ap *cmd;
+	struct qlink_auth_encr *aen;
 	u16 res_code = QLINK_CMD_RESULT_OK;
 	int ret;
 	int i;
 
 	cmd_skb = qtnf_cmd_alloc_new_cmdskb(vif->mac->macid, vif->vifid,
 					    QLINK_CMD_CONFIG_AP,
-					    sizeof(struct qlink_cmd));
+					    sizeof(*cmd));
 	if (unlikely(!cmd_skb))
 		return -ENOMEM;
 
-	qtnf_bus_lock(vif->mac->bus);
-
-	qtnf_cmd_skb_put_tlv_arr(cmd_skb, WLAN_EID_SSID, bss_cfg->ssid,
-				 bss_cfg->ssid_len);
-	qtnf_cmd_skb_put_tlv_u16(cmd_skb, QTN_TLV_ID_BCN_PERIOD,
-				 bss_cfg->bcn_period);
-	qtnf_cmd_skb_put_tlv_u8(cmd_skb, QTN_TLV_ID_DTIM, bss_cfg->dtim);
-
-	qchan = skb_put_zero(cmd_skb, sizeof(*qchan));
-	qchan->hdr.type = cpu_to_le16(QTN_TLV_ID_CHANNEL);
-	qchan->hdr.len = cpu_to_le16(sizeof(*qchan) -
-			sizeof(struct qlink_tlv_hdr));
-	qchan->hw_value = cpu_to_le16(
-		ieee80211_frequency_to_channel(chandef->chan->center_freq));
-
-	memset(&aen, 0, sizeof(aen));
-	aen.auth_type = bss_cfg->auth_type;
-	aen.privacy = !!bss_cfg->privacy;
-	aen.mfp = bss_cfg->mfp;
-	aen.wpa_versions = cpu_to_le32(bss_cfg->crypto.wpa_versions);
-	aen.cipher_group = cpu_to_le32(bss_cfg->crypto.cipher_group);
-	aen.n_ciphers_pairwise = cpu_to_le32(
-					bss_cfg->crypto.n_ciphers_pairwise);
+	cmd = (struct qlink_cmd_config_ap *)cmd_skb->data;
+	cmd->dtim_period = s->dtim_period;
+	cmd->beacon_interval = cpu_to_le16(s->beacon_interval);
+	cmd->hidden_ssid = qlink_hidden_ssid_nl2q(s->hidden_ssid);
+	cmd->inactivity_timeout = cpu_to_le16(s->inactivity_timeout);
+	cmd->smps_mode = s->smps_mode;
+	cmd->p2p_ctwindow = s->p2p_ctwindow;
+	cmd->p2p_opp_ps = s->p2p_opp_ps;
+	cmd->pbss = s->pbss;
+	cmd->ht_required = s->ht_required;
+	cmd->vht_required = s->vht_required;
+
+	aen = &cmd->aen;
+	aen->auth_type = s->auth_type;
+	aen->privacy = !!s->privacy;
+	aen->mfp = 0;
+	aen->wpa_versions = cpu_to_le32(s->crypto.wpa_versions);
+	aen->cipher_group = cpu_to_le32(s->crypto.cipher_group);
+	aen->n_ciphers_pairwise = cpu_to_le32(s->crypto.n_ciphers_pairwise);
 	for (i = 0; i < QLINK_MAX_NR_CIPHER_SUITES; i++)
-		aen.ciphers_pairwise[i] = cpu_to_le32(
-					bss_cfg->crypto.ciphers_pairwise[i]);
-	aen.n_akm_suites = cpu_to_le32(
-					bss_cfg->crypto.n_akm_suites);
+		aen->ciphers_pairwise[i] =
+				cpu_to_le32(s->crypto.ciphers_pairwise[i]);
+	aen->n_akm_suites = cpu_to_le32(s->crypto.n_akm_suites);
 	for (i = 0; i < QLINK_MAX_NR_AKM_SUITES; i++)
-		aen.akm_suites[i] = cpu_to_le32(
-					bss_cfg->crypto.akm_suites[i]);
-	aen.control_port = bss_cfg->crypto.control_port;
-	aen.control_port_no_encrypt =
-			bss_cfg->crypto.control_port_no_encrypt;
-	aen.control_port_ethertype = cpu_to_le16(be16_to_cpu(
-				bss_cfg->crypto.control_port_ethertype));
+		aen->akm_suites[i] = cpu_to_le32(s->crypto.akm_suites[i]);
+	aen->control_port = s->crypto.control_port;
+	aen->control_port_no_encrypt = s->crypto.control_port_no_encrypt;
+	aen->control_port_ethertype =
+		cpu_to_le16(be16_to_cpu(s->crypto.control_port_ethertype));
+
+	if (s->ssid && s->ssid_len > 0 && s->ssid_len <= IEEE80211_MAX_SSID_LEN)
+		qtnf_cmd_skb_put_tlv_arr(cmd_skb, WLAN_EID_SSID, s->ssid,
+					 s->ssid_len);
 
-	qtnf_cmd_skb_put_tlv_arr(cmd_skb, QTN_TLV_ID_CRYPTO, (u8 *)&aen,
-				 sizeof(aen));
+	if (cfg80211_chandef_valid(&s->chandef)) {
+		struct qlink_tlv_chandef *chtlv =
+			(struct qlink_tlv_chandef *)skb_put(cmd_skb,
+							    sizeof(*chtlv));
+
+		chtlv->hdr.type = cpu_to_le16(QTN_TLV_ID_CHANDEF);
+		chtlv->hdr.len = cpu_to_le16(sizeof(*chtlv) -
+					     sizeof(chtlv->hdr));
+		qlink_chandef_cfg2q(&s->chandef, &chtlv->chan);
+	}
+
+	qtnf_bus_lock(vif->mac->bus);
 
 	ret = qtnf_cmd_send(vif->mac->bus, cmd_skb, &res_code);
 
@@ -250,8 +255,6 @@ int qtnf_cmd_send_config_ap(struct qtnf_vif *vif)
 		goto out;
 	}
 
-	vif->bss_status |= QTNF_STATE_AP_CONFIG;
-
 out:
 	qtnf_bus_unlock(vif->mac->bus);
 	return ret;
@@ -283,9 +286,6 @@ int qtnf_cmd_send_stop_ap(struct qtnf_vif *vif)
 		goto out;
 	}
 
-	vif->bss_status &= ~QTNF_STATE_AP_START;
-	vif->bss_status &= ~QTNF_STATE_AP_CONFIG;
-
 	netif_carrier_off(vif->netdev);
 
 out:
@@ -2037,11 +2037,11 @@ int qtnf_cmd_send_connect(struct qtnf_vif *vif,
 {
 	struct sk_buff *cmd_skb;
 	struct qlink_cmd_connect *cmd;
-	struct qtnf_bss_config *bss_cfg = &vif->bss_cfg;
-	struct qlink_auth_encr aen;
+	struct qlink_auth_encr *aen;
 	u16 res_code = QLINK_CMD_RESULT_OK;
 	int ret;
 	int i;
+	u32 connect_flags = 0;
 
 	cmd_skb = qtnf_cmd_alloc_new_cmdskb(vif->mac->macid, vif->vifid,
 					    QLINK_CMD_CONNECT,
@@ -2049,52 +2049,65 @@ int qtnf_cmd_send_connect(struct qtnf_vif *vif,
 	if (unlikely(!cmd_skb))
 		return -ENOMEM;
 
-	qtnf_bus_lock(vif->mac->bus);
-
 	cmd = (struct qlink_cmd_connect *)cmd_skb->data;
 
-	ether_addr_copy(cmd->bssid, bss_cfg->bssid);
+	ether_addr_copy(cmd->bssid, vif->bssid);
+
+	if (sme->channel)
+		cmd->channel = cpu_to_le16(sme->channel->hw_value);
+	else
+		cmd->channel = 0;
+
+	if ((sme->bg_scan_period > 0) &&
+	    (sme->bg_scan_period <= QTNF_MAX_BG_SCAN_PERIOD))
+		cmd->bg_scan_period = cpu_to_le16(sme->bg_scan_period);
+	else if (sme->bg_scan_period == -1)
+		cmd->bg_scan_period = cpu_to_le16(QTNF_DEFAULT_BG_SCAN_PERIOD);
+	else
+		cmd->bg_scan_period = 0; /* disabled */
 
-	if (vif->mac->chandef.chan)
-		cmd->channel = cpu_to_le16(vif->mac->chandef.chan->hw_value);
+	if (sme->flags & ASSOC_REQ_DISABLE_HT)
+		connect_flags |= QLINK_STA_CONNECT_DISABLE_HT;
+	if (sme->flags & ASSOC_REQ_DISABLE_VHT)
+		connect_flags |= QLINK_STA_CONNECT_DISABLE_VHT;
+	if (sme->flags & ASSOC_REQ_USE_RRM)
+		connect_flags |= QLINK_STA_CONNECT_USE_RRM;
 
-	cmd->bg_scan_period = cpu_to_le16(bss_cfg->bg_scan_period);
+	cmd->flags = cpu_to_le32(connect_flags);
 
-	memset(&aen, 0, sizeof(aen));
-	aen.auth_type = bss_cfg->auth_type;
-	aen.privacy = !!bss_cfg->privacy;
-	aen.mfp = bss_cfg->mfp;
-	aen.wpa_versions = cpu_to_le32(bss_cfg->crypto.wpa_versions);
-	aen.cipher_group = cpu_to_le32(bss_cfg->crypto.cipher_group);
-	aen.n_ciphers_pairwise = cpu_to_le32(
-					bss_cfg->crypto.n_ciphers_pairwise);
+	aen = &cmd->aen;
+	aen->auth_type = sme->auth_type;
+	aen->privacy = !!sme->privacy;
+	aen->mfp = sme->mfp;
+	aen->wpa_versions = cpu_to_le32(sme->crypto.wpa_versions);
+	aen->cipher_group = cpu_to_le32(sme->crypto.cipher_group);
+	aen->n_ciphers_pairwise = cpu_to_le32(sme->crypto.n_ciphers_pairwise);
 
 	for (i = 0; i < QLINK_MAX_NR_CIPHER_SUITES; i++)
-		aen.ciphers_pairwise[i] = cpu_to_le32(
-					bss_cfg->crypto.ciphers_pairwise[i]);
+		aen->ciphers_pairwise[i] =
+			cpu_to_le32(sme->crypto.ciphers_pairwise[i]);
 
-	aen.n_akm_suites = cpu_to_le32(bss_cfg->crypto.n_akm_suites);
+	aen->n_akm_suites = cpu_to_le32(sme->crypto.n_akm_suites);
 
 	for (i = 0; i < QLINK_MAX_NR_AKM_SUITES; i++)
-		aen.akm_suites[i] = cpu_to_le32(
-					bss_cfg->crypto.akm_suites[i]);
+		aen->akm_suites[i] = cpu_to_le32(sme->crypto.akm_suites[i]);
 
-	aen.control_port = bss_cfg->crypto.control_port;
-	aen.control_port_no_encrypt =
-			bss_cfg->crypto.control_port_no_encrypt;
-	aen.control_port_ethertype = cpu_to_le16(be16_to_cpu(
-				bss_cfg->crypto.control_port_ethertype));
+	aen->control_port = sme->crypto.control_port;
+	aen->control_port_no_encrypt =
+		sme->crypto.control_port_no_encrypt;
+	aen->control_port_ethertype =
+		cpu_to_le16(be16_to_cpu(sme->crypto.control_port_ethertype));
 
-	qtnf_cmd_skb_put_tlv_arr(cmd_skb, WLAN_EID_SSID, bss_cfg->ssid,
-				 bss_cfg->ssid_len);
-	qtnf_cmd_skb_put_tlv_arr(cmd_skb, QTN_TLV_ID_CRYPTO, (u8 *)&aen,
-				 sizeof(aen));
+	qtnf_cmd_skb_put_tlv_arr(cmd_skb, WLAN_EID_SSID, sme->ssid,
+				 sme->ssid_len);
 
 	if (sme->ie_len != 0)
 		qtnf_cmd_skb_put_tlv_arr(cmd_skb, QTN_TLV_ID_IE_SET,
 					 sme->ie,
 					 sme->ie_len);
 
+	qtnf_bus_lock(vif->mac->bus);
+
 	ret = qtnf_cmd_send(vif->mac->bus, cmd_skb, &res_code);
 
 	if (unlikely(ret))
@@ -2304,15 +2317,16 @@ out:
 	return ret;
 }
 
-int qtnf_cmd_send_chan_switch(struct qtnf_wmac *mac,
+int qtnf_cmd_send_chan_switch(struct qtnf_vif *vif,
 			      struct cfg80211_csa_settings *params)
 {
+	struct qtnf_wmac *mac = vif->mac;
 	struct qlink_cmd_chan_switch *cmd;
 	struct sk_buff *cmd_skb;
 	u16 res_code = QLINK_CMD_RESULT_OK;
 	int ret;
 
-	cmd_skb = qtnf_cmd_alloc_new_cmdskb(mac->macid, 0x0,
+	cmd_skb = qtnf_cmd_alloc_new_cmdskb(mac->macid, vif->vifid,
 					    QLINK_CMD_CHAN_SWITCH,
 					    sizeof(*cmd));
 
@@ -2334,9 +2348,6 @@ int qtnf_cmd_send_chan_switch(struct qtnf_wmac *mac,
 
 	switch (res_code) {
 	case QLINK_CMD_RESULT_OK:
-		memcpy(&mac->csa_chandef, &params->chandef,
-		       sizeof(mac->csa_chandef));
-		mac->status |= QTNF_MAC_CSA_ACTIVE;
 		ret = 0;
 		break;
 	case QLINK_CMD_RESULT_ENOTFOUND:
@@ -2358,3 +2369,41 @@ out:
 	qtnf_bus_unlock(mac->bus);
 	return ret;
 }
+
+int qtnf_cmd_get_channel(struct qtnf_vif *vif, struct cfg80211_chan_def *chdef)
+{
+	struct qtnf_bus *bus = vif->mac->bus;
+	const struct qlink_resp_channel_get *resp;
+	struct sk_buff *cmd_skb;
+	struct sk_buff *resp_skb = NULL;
+	u16 res_code = QLINK_CMD_RESULT_OK;
+	int ret;
+
+	cmd_skb = qtnf_cmd_alloc_new_cmdskb(vif->mac->macid, vif->vifid,
+					    QLINK_CMD_CHAN_GET,
+					    sizeof(struct qlink_cmd));
+	if (unlikely(!cmd_skb))
+		return -ENOMEM;
+
+	qtnf_bus_lock(bus);
+
+	ret = qtnf_cmd_send_with_reply(bus, cmd_skb, &resp_skb, &res_code,
+				       sizeof(*resp), NULL);
+
+	qtnf_bus_unlock(bus);
+
+	if (unlikely(ret))
+		goto out;
+
+	if (unlikely(res_code != QLINK_CMD_RESULT_OK)) {
+		ret = -ENODATA;
+		goto out;
+	}
+
+	resp = (const struct qlink_resp_channel_get *)resp_skb->data;
+	qlink_chandef_q2cfg(priv_to_wiphy(vif->mac), &resp->chan, chdef);
+
+out:
+	consume_skb(resp_skb);
+	return ret;
+}
diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.h b/drivers/net/wireless/quantenna/qtnfmac/commands.h
index 783b20364296..e87c4a484dd4 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.h
@@ -33,7 +33,8 @@ int qtnf_cmd_send_del_intf(struct qtnf_vif *vif);
 int qtnf_cmd_get_mac_chan_info(struct qtnf_wmac *mac,
 			       struct ieee80211_supported_band *band);
 int qtnf_cmd_send_regulatory_config(struct qtnf_wmac *mac, const char *alpha2);
-int qtnf_cmd_send_config_ap(struct qtnf_vif *vif);
+int qtnf_cmd_send_config_ap(struct qtnf_vif *vif,
+			    const struct cfg80211_ap_settings *s);
 int qtnf_cmd_send_start_ap(struct qtnf_vif *vif);
 int qtnf_cmd_send_stop_ap(struct qtnf_vif *vif);
 int qtnf_cmd_send_register_mgmt(struct qtnf_vif *vif, u16 frame_type, bool reg);
@@ -73,7 +74,8 @@ int qtnf_cmd_send_updown_intf(struct qtnf_vif *vif,
 int qtnf_cmd_reg_notify(struct qtnf_bus *bus, struct regulatory_request *req);
 int qtnf_cmd_get_chan_stats(struct qtnf_wmac *mac, u16 channel,
 			    struct qtnf_chan_stats *stats);
-int qtnf_cmd_send_chan_switch(struct qtnf_wmac *mac,
+int qtnf_cmd_send_chan_switch(struct qtnf_vif *vif,
 			      struct cfg80211_csa_settings *params);
+int qtnf_cmd_get_channel(struct qtnf_vif *vif, struct cfg80211_chan_def *chdef);
 
 #endif /* QLINK_COMMANDS_H_ */
diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.h b/drivers/net/wireless/quantenna/qtnfmac/core.h
index 066fcd1095a0..44a2cbb19310 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/core.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/core.h
@@ -52,27 +52,11 @@
 #define QTNF_DEF_WDOG_TIMEOUT		5
 #define QTNF_TX_TIMEOUT_TRSHLD		100
 
-#define QTNF_STATE_AP_CONFIG		BIT(2)
-#define QTNF_STATE_AP_START		BIT(1)
-
 extern const struct net_device_ops qtnf_netdev_ops;
+
 struct qtnf_bus;
 struct qtnf_vif;
 
-struct qtnf_bss_config {
-	u8 ssid[IEEE80211_MAX_SSID_LEN];
-	u8 bssid[ETH_ALEN];
-	size_t ssid_len;
-	u8 dtim;
-	u16 bcn_period;
-	u16 auth_type;
-	bool privacy;
-	enum nl80211_mfp mfp;
-	struct cfg80211_crypto_settings crypto;
-	u16 bg_scan_period;
-	u32 connect_flags;
-};
-
 struct qtnf_sta_node {
 	struct list_head list;
 	u8 mac_addr[ETH_ALEN];
@@ -89,12 +73,10 @@ enum qtnf_sta_state {
 	QTNF_STA_CONNECTED
 };
 
-enum qtnf_mac_status {
-	QTNF_MAC_CSA_ACTIVE	= BIT(0)
-};
-
 struct qtnf_vif {
 	struct wireless_dev wdev;
+	u8 bssid[ETH_ALEN];
+	u8 mac_addr[ETH_ALEN];
 	u8 vifid;
 	u8 bss_priority;
 	u8 bss_status;
@@ -102,9 +84,8 @@ struct qtnf_vif {
 	u16 mgmt_frames_bitmask;
 	struct net_device *netdev;
 	struct qtnf_wmac *mac;
-	u8 mac_addr[ETH_ALEN];
+
 	struct work_struct reset_work;
-	struct qtnf_bss_config bss_cfg;
 	struct qtnf_sta_list sta_list;
 	unsigned long cons_tx_timeout_cnt;
 };
@@ -141,13 +122,10 @@ struct qtnf_wmac {
 	u8 macid;
 	u8 wiphy_registered;
 	u8 macaddr[ETH_ALEN];
-	u32 status;
 	struct qtnf_bus *bus;
 	struct qtnf_mac_info macinfo;
 	struct qtnf_vif iflist[QTNF_MAX_INTF];
 	struct cfg80211_scan_request *scan_req;
-	struct cfg80211_chan_def chandef;
-	struct cfg80211_chan_def csa_chandef;
 	struct mutex mac_lock;	/* lock during wmac speicific ops */
 	struct timer_list scan_timeout;
 };
diff --git a/drivers/net/wireless/quantenna/qtnfmac/event.c b/drivers/net/wireless/quantenna/qtnfmac/event.c
index 43d2e7fd6e02..4b29f9fb9c3c 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/event.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/event.c
@@ -25,6 +25,7 @@
 #include "trans.h"
 #include "util.h"
 #include "event.h"
+#include "qlink_util.h"
 
 static int
 qtnf_event_handle_sta_assoc(struct qtnf_wmac *mac, struct qtnf_vif *vif,
@@ -52,12 +53,6 @@ qtnf_event_handle_sta_assoc(struct qtnf_wmac *mac, struct qtnf_vif *vif,
 		return -EPROTO;
 	}
 
-	if (!(vif->bss_status & QTNF_STATE_AP_START)) {
-		pr_err("VIF%u.%u: STA_ASSOC event when AP is not started\n",
-		       mac->macid, vif->vifid);
-		return -EPROTO;
-	}
-
 	sta_addr = sta_assoc->sta_addr;
 	frame_control = le16_to_cpu(sta_assoc->frame_control);
 
@@ -126,12 +121,6 @@ qtnf_event_handle_sta_deauth(struct qtnf_wmac *mac, struct qtnf_vif *vif,
 		return -EPROTO;
 	}
 
-	if (!(vif->bss_status & QTNF_STATE_AP_START)) {
-		pr_err("VIF%u.%u: STA_DEAUTH event when AP is not started\n",
-		       mac->macid, vif->vifid);
-		return -EPROTO;
-	}
-
 	sta_addr = sta_deauth->sta_addr;
 	reason = le16_to_cpu(sta_deauth->reason);
 
@@ -357,40 +346,29 @@ qtnf_event_handle_freq_change(struct qtnf_wmac *mac,
 {
 	struct wiphy *wiphy = priv_to_wiphy(mac);
 	struct cfg80211_chan_def chandef;
-	struct ieee80211_channel *chan;
 	struct qtnf_vif *vif;
-	int freq;
 	int i;
 
 	if (len < sizeof(*data)) {
-		pr_err("payload is too short\n");
+		pr_err("MAC%u: payload is too short\n", mac->macid);
 		return -EINVAL;
 	}
 
-	freq = le32_to_cpu(data->freq);
-	chan = ieee80211_get_channel(wiphy, freq);
-	if (!chan) {
-		pr_err("channel at %d MHz not found\n", freq);
-		return -EINVAL;
-	}
+	if (!wiphy->registered)
+		return 0;
 
-	pr_debug("MAC%d switch to new channel %u MHz\n", mac->macid, freq);
+	qlink_chandef_q2cfg(wiphy, &data->chan, &chandef);
 
-	if (mac->status & QTNF_MAC_CSA_ACTIVE) {
-		mac->status &= ~QTNF_MAC_CSA_ACTIVE;
-		if (chan->hw_value != mac->csa_chandef.chan->hw_value)
-			pr_warn("unexpected switch to %u during CSA to %u\n",
-				chan->hw_value,
-				mac->csa_chandef.chan->hw_value);
+	if (!cfg80211_chandef_valid(&chandef)) {
+		pr_err("MAC%u: bad channel f1=%u f2=%u bw=%u\n", mac->macid,
+		       chandef.center_freq1, chandef.center_freq2,
+		       chandef.width);
+		return -EINVAL;
 	}
 
-	/* FIXME: need to figure out proper nl80211_channel_type value */
-	cfg80211_chandef_create(&chandef, chan, NL80211_CHAN_HT20);
-	/* fall-back to minimal safe chandef description */
-	if (!cfg80211_chandef_valid(&chandef))
-		cfg80211_chandef_create(&chandef, chan, NL80211_CHAN_HT20);
-
-	memcpy(&mac->chandef, &chandef, sizeof(mac->chandef));
+	pr_debug("MAC%d: new channel ieee=%u freq1=%u freq2=%u bw=%u\n",
+		 mac->macid, chandef.chan->hw_value, chandef.center_freq1,
+		 chandef.center_freq2, chandef.width);
 
 	for (i = 0; i < QTNF_MAX_INTF; i++) {
 		vif = &mac->iflist[i];
diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink.h b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
index a8242f678496..7b313d38c30b 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/qlink.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
@@ -108,16 +108,48 @@ enum qlink_sta_flags {
 };
 
 enum qlink_channel_width {
-	QLINK_CHAN_WIDTH_5		= BIT(0),
-	QLINK_CHAN_WIDTH_10		= BIT(1),
-	QLINK_CHAN_WIDTH_20_NOHT	= BIT(2),
-	QLINK_CHAN_WIDTH_20		= BIT(3),
-	QLINK_CHAN_WIDTH_40		= BIT(4),
-	QLINK_CHAN_WIDTH_80		= BIT(5),
-	QLINK_CHAN_WIDTH_80P80		= BIT(6),
-	QLINK_CHAN_WIDTH_160		= BIT(7),
+	QLINK_CHAN_WIDTH_5 = 0,
+	QLINK_CHAN_WIDTH_10,
+	QLINK_CHAN_WIDTH_20_NOHT,
+	QLINK_CHAN_WIDTH_20,
+	QLINK_CHAN_WIDTH_40,
+	QLINK_CHAN_WIDTH_80,
+	QLINK_CHAN_WIDTH_80P80,
+	QLINK_CHAN_WIDTH_160,
 };
 
+/**
+ * struct qlink_chandef - qlink channel definition
+ *
+ * @center_freq1: center frequency of first segment
+ * @center_freq2: center frequency of second segment (80+80 only)
+ * @width: channel width, one of @enum qlink_channel_width
+ */
+struct qlink_chandef {
+	__le16 center_freq1;
+	__le16 center_freq2;
+	u8 width;
+	u8 rsvd[3];
+} __packed;
+
+#define QLINK_MAX_NR_CIPHER_SUITES            5
+#define QLINK_MAX_NR_AKM_SUITES               2
+
+struct qlink_auth_encr {
+	__le32 wpa_versions;
+	__le32 cipher_group;
+	__le32 n_ciphers_pairwise;
+	__le32 ciphers_pairwise[QLINK_MAX_NR_CIPHER_SUITES];
+	__le32 n_akm_suites;
+	__le32 akm_suites[QLINK_MAX_NR_AKM_SUITES];
+	__le16 control_port_ethertype;
+	u8 auth_type;
+	u8 privacy;
+	u8 mfp;
+	u8 control_port;
+	u8 control_port_no_encrypt;
+} __packed;
+
 /* QLINK Command messages related definitions
  */
 
@@ -155,6 +187,7 @@ enum qlink_cmd_type {
 	QLINK_CMD_REG_NOTIFY		= 0x0019,
 	QLINK_CMD_CHANS_INFO_GET	= 0x001A,
 	QLINK_CMD_CHAN_SWITCH		= 0x001B,
+	QLINK_CMD_CHAN_GET		= 0x001C,
 	QLINK_CMD_CONFIG_AP		= 0x0020,
 	QLINK_CMD_START_AP		= 0x0021,
 	QLINK_CMD_STOP_AP		= 0x0022,
@@ -384,8 +417,9 @@ enum qlink_sta_connect_flags {
  * struct qlink_cmd_connect - data for QLINK_CMD_CONNECT command
  *
  * @flags: for future use.
- * @freq: center frequence of a channel which should be used to connect.
+ * @channel: channel which should be used to connect.
  * @bg_scan_period: period of background scan.
+ * @aen: authentication information.
  * @bssid: BSSID of the BSS to connect to.
  * @payload: variable portion of connection request.
  */
@@ -394,6 +428,7 @@ struct qlink_cmd_connect {
 	__le32 flags;
 	__le16 channel;
 	__le16 bg_scan_period;
+	struct qlink_auth_encr aen;
 	u8 bssid[ETH_ALEN];
 	u8 payload[0];
 } __packed;
@@ -506,6 +541,46 @@ struct qlink_cmd_chan_switch {
 	u8 beacon_count;
 } __packed;
 
+/**
+ * enum qlink_hidden_ssid - values for %NL80211_ATTR_HIDDEN_SSID
+ *
+ * Refer to &enum nl80211_hidden_ssid
+ */
+enum qlink_hidden_ssid {
+	QLINK_HIDDEN_SSID_NOT_IN_USE,
+	QLINK_HIDDEN_SSID_ZERO_LEN,
+	QLINK_HIDDEN_SSID_ZERO_CONTENTS
+};
+
+/**
+ * struct qlink_cmd_config_ap - data for QLINK_CMD_CONFIG_AP command
+ *
+ * @beacon_interval: beacon interval
+ * @inactivity_timeout: station's inactivity period in seconds
+ * @dtim_period: DTIM period
+ * @hidden_ssid: whether to hide the SSID, one of &enum qlink_hidden_ssid
+ * @smps_mode: SMPS mode
+ * @ht_required: stations must support HT
+ * @vht_required: stations must support VHT
+ * @aen: encryption info
+ * @info: variable configurations
+ */
+struct qlink_cmd_config_ap {
+	struct qlink_cmd chdr;
+	__le16 beacon_interval;
+	__le16 inactivity_timeout;
+	u8 dtim_period;
+	u8 hidden_ssid;
+	u8 smps_mode;
+	u8 p2p_ctwindow;
+	u8 p2p_opp_ps;
+	u8 pbss;
+	u8 ht_required;
+	u8 vht_required;
+	struct qlink_auth_encr aen;
+	u8 info[0];
+} __packed;
+
 /* QLINK Command Responses messages related definitions
  */
 
@@ -680,6 +755,16 @@ struct qlink_resp_get_chan_stats {
 	u8 info[0];
 } __packed;
 
+/**
+ * struct qlink_resp_channel_get - response for QLINK_CMD_CHAN_GET command
+ *
+ * @chan: definition of current operating channel.
+ */
+struct qlink_resp_channel_get {
+	struct qlink_resp rhdr;
+	struct qlink_chandef chan;
+} __packed;
+
 /* QLINK Events messages related definitions
  */
 
@@ -764,11 +849,11 @@ struct qlink_event_bss_leave {
 /**
  * struct qlink_event_freq_change - data for QLINK_EVENT_FREQ_CHANGE event
  *
- * @freq: new operating frequency in MHz
+ * @chan: new operating channel definition
  */
 struct qlink_event_freq_change {
 	struct qlink_event ehdr;
-	__le32 freq;
+	struct qlink_chandef chan;
 } __packed;
 
 enum qlink_rxmgmt_flags {
@@ -856,10 +941,9 @@ enum qlink_tlv_id {
 	QTN_TLV_ID_RTS_THRESH		= 0x0202,
 	QTN_TLV_ID_SRETRY_LIMIT		= 0x0203,
 	QTN_TLV_ID_LRETRY_LIMIT		= 0x0204,
-	QTN_TLV_ID_BCN_PERIOD		= 0x0205,
-	QTN_TLV_ID_DTIM			= 0x0206,
 	QTN_TLV_ID_REG_RULE		= 0x0207,
 	QTN_TLV_ID_CHANNEL		= 0x020F,
+	QTN_TLV_ID_CHANDEF		= 0x0210,
 	QTN_TLV_ID_COVERAGE_CLASS	= 0x0213,
 	QTN_TLV_ID_IFACE_LIMIT		= 0x0214,
 	QTN_TLV_ID_NUM_IFACE_COMB	= 0x0215,
@@ -868,7 +952,6 @@ enum qlink_tlv_id {
 	QTN_TLV_ID_STA_GENERIC_INFO	= 0x0301,
 	QTN_TLV_ID_KEY			= 0x0302,
 	QTN_TLV_ID_SEQ			= 0x0303,
-	QTN_TLV_ID_CRYPTO		= 0x0304,
 	QTN_TLV_ID_IE_SET		= 0x0305,
 };
 
@@ -1047,22 +1130,16 @@ struct qlink_tlv_channel {
 	u8 rsvd[2];
 } __packed;
 
-#define QLINK_MAX_NR_CIPHER_SUITES            5
-#define QLINK_MAX_NR_AKM_SUITES               2
-
-struct qlink_auth_encr {
-	__le32 wpa_versions;
-	__le32 cipher_group;
-	__le32 n_ciphers_pairwise;
-	__le32 ciphers_pairwise[QLINK_MAX_NR_CIPHER_SUITES];
-	__le32 n_akm_suites;
-	__le32 akm_suites[QLINK_MAX_NR_AKM_SUITES];
-	__le16 control_port_ethertype;
-	u8 auth_type;
-	u8 privacy;
-	u8 mfp;
-	u8 control_port;
-	u8 control_port_no_encrypt;
+/**
+ * struct qlink_tlv_chandef - data for QTN_TLV_ID_CHANDEF TLV
+ *
+ * Channel definition.
+ *
+ * @chan: channel definition data.
+ */
+struct qlink_tlv_chandef {
+	struct qlink_tlv_hdr hdr;
+	struct qlink_chandef chan;
 } __packed;
 
 struct qlink_chan_stats {
diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink_util.c b/drivers/net/wireless/quantenna/qtnfmac/qlink_util.c
index cf024c995fd6..61d999affb09 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/qlink_util.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/qlink_util.c
@@ -49,29 +49,126 @@ u8 qlink_chan_width_mask_to_nl(u16 qlink_mask)
 {
 	u8 result = 0;
 
-	if (qlink_mask & QLINK_CHAN_WIDTH_5)
+	if (qlink_mask & BIT(QLINK_CHAN_WIDTH_5))
 		result |= BIT(NL80211_CHAN_WIDTH_5);
 
-	if (qlink_mask & QLINK_CHAN_WIDTH_10)
+	if (qlink_mask & BIT(QLINK_CHAN_WIDTH_10))
 		result |= BIT(NL80211_CHAN_WIDTH_10);
 
-	if (qlink_mask & QLINK_CHAN_WIDTH_20_NOHT)
+	if (qlink_mask & BIT(QLINK_CHAN_WIDTH_20_NOHT))
 		result |= BIT(NL80211_CHAN_WIDTH_20_NOHT);
 
-	if (qlink_mask & QLINK_CHAN_WIDTH_20)
+	if (qlink_mask & BIT(QLINK_CHAN_WIDTH_20))
 		result |= BIT(NL80211_CHAN_WIDTH_20);
 
-	if (qlink_mask & QLINK_CHAN_WIDTH_40)
+	if (qlink_mask & BIT(QLINK_CHAN_WIDTH_40))
 		result |= BIT(NL80211_CHAN_WIDTH_40);
 
-	if (qlink_mask & QLINK_CHAN_WIDTH_80)
+	if (qlink_mask & BIT(QLINK_CHAN_WIDTH_80))
 		result |= BIT(NL80211_CHAN_WIDTH_80);
 
-	if (qlink_mask & QLINK_CHAN_WIDTH_80P80)
+	if (qlink_mask & BIT(QLINK_CHAN_WIDTH_80P80))
 		result |= BIT(NL80211_CHAN_WIDTH_80P80);
 
-	if (qlink_mask & QLINK_CHAN_WIDTH_160)
+	if (qlink_mask & BIT(QLINK_CHAN_WIDTH_160))
 		result |= BIT(NL80211_CHAN_WIDTH_160);
 
 	return result;
 }
+
+static enum nl80211_chan_width qlink_chanwidth_to_nl(u8 qlw)
+{
+	switch (qlw) {
+	case QLINK_CHAN_WIDTH_20_NOHT:
+		return NL80211_CHAN_WIDTH_20_NOHT;
+	case QLINK_CHAN_WIDTH_20:
+		return NL80211_CHAN_WIDTH_20;
+	case QLINK_CHAN_WIDTH_40:
+		return NL80211_CHAN_WIDTH_40;
+	case QLINK_CHAN_WIDTH_80:
+		return NL80211_CHAN_WIDTH_80;
+	case QLINK_CHAN_WIDTH_80P80:
+		return NL80211_CHAN_WIDTH_80P80;
+	case QLINK_CHAN_WIDTH_160:
+		return NL80211_CHAN_WIDTH_160;
+	case QLINK_CHAN_WIDTH_5:
+		return NL80211_CHAN_WIDTH_5;
+	case QLINK_CHAN_WIDTH_10:
+		return NL80211_CHAN_WIDTH_10;
+	default:
+		return -1;
+	}
+}
+
+void qlink_chandef_q2cfg(struct wiphy *wiphy,
+			 const struct qlink_chandef *qch,
+			 struct cfg80211_chan_def *chdef)
+{
+	chdef->center_freq1 = le16_to_cpu(qch->center_freq1);
+	chdef->center_freq2 = le16_to_cpu(qch->center_freq2);
+	chdef->width = qlink_chanwidth_to_nl(qch->width);
+
+	switch (chdef->width) {
+	case NL80211_CHAN_WIDTH_20_NOHT:
+	case NL80211_CHAN_WIDTH_20:
+	case NL80211_CHAN_WIDTH_5:
+	case NL80211_CHAN_WIDTH_10:
+		chdef->chan = ieee80211_get_channel(wiphy, chdef->center_freq1);
+		break;
+	case NL80211_CHAN_WIDTH_40:
+	case NL80211_CHAN_WIDTH_80:
+	case NL80211_CHAN_WIDTH_80P80:
+	case NL80211_CHAN_WIDTH_160:
+		chdef->chan = ieee80211_get_channel(wiphy,
+						    chdef->center_freq1 - 10);
+		break;
+	default:
+		chdef->chan = NULL;
+		break;
+	}
+}
+
+static u8 qlink_chanwidth_nl_to_qlink(enum nl80211_chan_width nlwidth)
+{
+	switch (nlwidth) {
+	case NL80211_CHAN_WIDTH_20_NOHT:
+		return QLINK_CHAN_WIDTH_20_NOHT;
+	case NL80211_CHAN_WIDTH_20:
+		return QLINK_CHAN_WIDTH_20;
+	case NL80211_CHAN_WIDTH_40:
+		return QLINK_CHAN_WIDTH_40;
+	case NL80211_CHAN_WIDTH_80:
+		return QLINK_CHAN_WIDTH_80;
+	case NL80211_CHAN_WIDTH_80P80:
+		return QLINK_CHAN_WIDTH_80P80;
+	case NL80211_CHAN_WIDTH_160:
+		return QLINK_CHAN_WIDTH_160;
+	case NL80211_CHAN_WIDTH_5:
+		return QLINK_CHAN_WIDTH_5;
+	case NL80211_CHAN_WIDTH_10:
+		return QLINK_CHAN_WIDTH_10;
+	default:
+		return -1;
+	}
+}
+
+void qlink_chandef_cfg2q(const struct cfg80211_chan_def *chdef,
+			 struct qlink_chandef *qch)
+{
+	qch->center_freq1 = cpu_to_le16(chdef->center_freq1);
+	qch->center_freq2 = cpu_to_le16(chdef->center_freq2);
+	qch->width = qlink_chanwidth_nl_to_qlink(chdef->width);
+}
+
+enum qlink_hidden_ssid qlink_hidden_ssid_nl2q(enum nl80211_hidden_ssid nl_val)
+{
+	switch (nl_val) {
+	case NL80211_HIDDEN_SSID_ZERO_LEN:
+		return QLINK_HIDDEN_SSID_ZERO_LEN;
+	case NL80211_HIDDEN_SSID_ZERO_CONTENTS:
+		return QLINK_HIDDEN_SSID_ZERO_CONTENTS;
+	case NL80211_HIDDEN_SSID_NOT_IN_USE:
+	default:
+		return QLINK_HIDDEN_SSID_NOT_IN_USE;
+	}
+}
diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink_util.h b/drivers/net/wireless/quantenna/qtnfmac/qlink_util.h
index de06c1e20b5b..260383d6d109 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/qlink_util.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/qlink_util.h
@@ -19,6 +19,7 @@
 
 #include <linux/types.h>
 #include <linux/skbuff.h>
+#include <net/cfg80211.h>
 
 #include "qlink.h"
 
@@ -62,5 +63,11 @@ static inline void qtnf_cmd_skb_put_tlv_u16(struct sk_buff *skb,
 
 u16 qlink_iface_type_to_nl_mask(u16 qlink_type);
 u8 qlink_chan_width_mask_to_nl(u16 qlink_mask);
+void qlink_chandef_q2cfg(struct wiphy *wiphy,
+			 const struct qlink_chandef *qch,
+			 struct cfg80211_chan_def *chdef);
+void qlink_chandef_cfg2q(const struct cfg80211_chan_def *chdef,
+			 struct qlink_chandef *qch);
+enum qlink_hidden_ssid qlink_hidden_ssid_nl2q(enum nl80211_hidden_ssid nl_val);
 
 #endif /* _QTN_FMAC_QLINK_UTIL_H_ */
diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index 170cd504e8ff..d8afcdfca1ed 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -92,7 +92,7 @@ static const struct iw_handler_def ray_handler_def;
 /***** Prototypes for raylink functions **************************************/
 static void authenticate(ray_dev_t *local);
 static int build_auth_frame(ray_dev_t *local, UCHAR *dest, int auth_type);
-static void authenticate_timeout(u_long);
+static void authenticate_timeout(struct timer_list *t);
 static int get_free_ccs(ray_dev_t *local);
 static int get_free_tx_ccs(ray_dev_t *local);
 static void init_startup_params(ray_dev_t *local);
@@ -102,7 +102,7 @@ static int ray_init(struct net_device *dev);
 static int interrupt_ecf(ray_dev_t *local, int ccs);
 static void ray_reset(struct net_device *dev);
 static void ray_update_parm(struct net_device *dev, UCHAR objid, UCHAR *value, int len);
-static void verify_dl_startup(u_long);
+static void verify_dl_startup(struct timer_list *t);
 
 /* Prototypes for interrpt time functions **********************************/
 static irqreturn_t ray_interrupt(int reg, void *dev_id);
@@ -120,9 +120,8 @@ static void associate(ray_dev_t *local);
 
 /* Card command functions */
 static int dl_startup_params(struct net_device *dev);
-static void join_net(u_long local);
-static void start_net(u_long local);
-/* void start_net(ray_dev_t *local); */
+static void join_net(struct timer_list *t);
+static void start_net(struct timer_list *t);
 
 /*===========================================================================*/
 /* Parameters that can be set with 'insmod' */
@@ -323,7 +322,7 @@ static int ray_probe(struct pcmcia_device *p_dev)
 	dev_dbg(&p_dev->dev, "ray_cs ray_attach calling ether_setup.)\n");
 	netif_stop_queue(dev);
 
-	init_timer(&local->timer);
+	timer_setup(&local->timer, NULL, 0);
 
 	this_device = p_dev;
 	return ray_config(p_dev);
@@ -570,8 +569,7 @@ static int dl_startup_params(struct net_device *dev)
 	local->card_status = CARD_DL_PARAM;
 	/* Start kernel timer to wait for dl startup to complete. */
 	local->timer.expires = jiffies + HZ / 2;
-	local->timer.data = (long)local;
-	local->timer.function = verify_dl_startup;
+	local->timer.function = (TIMER_FUNC_TYPE)verify_dl_startup;
 	add_timer(&local->timer);
 	dev_dbg(&link->dev,
 	      "ray_cs dl_startup_params started timer for verify_dl_startup\n");
@@ -641,9 +639,9 @@ static void init_startup_params(ray_dev_t *local)
 } /* init_startup_params */
 
 /*===========================================================================*/
-static void verify_dl_startup(u_long data)
+static void verify_dl_startup(struct timer_list *t)
 {
-	ray_dev_t *local = (ray_dev_t *) data;
+	ray_dev_t *local = from_timer(local, t, timer);
 	struct ccs __iomem *pccs = ccs_base(local) + local->dl_param_ccs;
 	UCHAR status;
 	struct pcmcia_device *link = local->finder;
@@ -676,16 +674,16 @@ static void verify_dl_startup(u_long data)
 		return;
 	}
 	if (local->sparm.b4.a_network_type == ADHOC)
-		start_net((u_long) local);
+		start_net(&local->timer);
 	else
-		join_net((u_long) local);
+		join_net(&local->timer);
 } /* end verify_dl_startup */
 
 /*===========================================================================*/
 /* Command card to start a network */
-static void start_net(u_long data)
+static void start_net(struct timer_list *t)
 {
-	ray_dev_t *local = (ray_dev_t *) data;
+	ray_dev_t *local = from_timer(local, t, timer);
 	struct ccs __iomem *pccs;
 	int ccsindex;
 	struct pcmcia_device *link = local->finder;
@@ -710,9 +708,9 @@ static void start_net(u_long data)
 
 /*===========================================================================*/
 /* Command card to join a network */
-static void join_net(u_long data)
+static void join_net(struct timer_list *t)
 {
-	ray_dev_t *local = (ray_dev_t *) data;
+	ray_dev_t *local = from_timer(local, t, timer);
 
 	struct ccs __iomem *pccs;
 	int ccsindex;
@@ -1639,13 +1637,13 @@ static int get_free_ccs(ray_dev_t *local)
 } /* get_free_ccs */
 
 /*===========================================================================*/
-static void authenticate_timeout(u_long data)
+static void authenticate_timeout(struct timer_list *t)
 {
-	ray_dev_t *local = (ray_dev_t *) data;
+	ray_dev_t *local = from_timer(local, t, timer);
 	del_timer(&local->timer);
 	printk(KERN_INFO "ray_cs Authentication with access point failed"
 	       " - timeout\n");
-	join_net((u_long) local);
+	join_net(&local->timer);
 }
 
 /*===========================================================================*/
@@ -1945,17 +1943,16 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id)
 
 				del_timer(&local->timer);
 				local->timer.expires = jiffies + HZ * 5;
-				local->timer.data = (long)local;
 				if (status == CCS_START_NETWORK) {
 					dev_dbg(&link->dev,
 					      "ray_cs interrupt network \"%s\" start failed\n",
 					      memtmp);
-					local->timer.function = start_net;
+					local->timer.function = (TIMER_FUNC_TYPE)start_net;
 				} else {
 					dev_dbg(&link->dev,
 					      "ray_cs interrupt network \"%s\" join failed\n",
 					      memtmp);
-					local->timer.function = join_net;
+					local->timer.function = (TIMER_FUNC_TYPE)join_net;
 				}
 				add_timer(&local->timer);
 			}
@@ -1967,7 +1964,7 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id)
 			} else {
 				dev_dbg(&link->dev, "ray_cs association failed,\n");
 				local->card_status = CARD_ASSOC_FAILED;
-				join_net((u_long) local);
+				join_net(&local->timer);
 			}
 			break;
 		case CCS_TX_REQUEST:
@@ -2420,12 +2417,11 @@ static void authenticate(ray_dev_t *local)
 
 	del_timer(&local->timer);
 	if (build_auth_frame(local, local->bss_id, OPEN_AUTH_REQUEST)) {
-		local->timer.function = join_net;
+		local->timer.function = (TIMER_FUNC_TYPE)join_net;
 	} else {
-		local->timer.function = authenticate_timeout;
+		local->timer.function = (TIMER_FUNC_TYPE)authenticate_timeout;
 	}
 	local->timer.expires = jiffies + HZ * 2;
-	local->timer.data = (long)local;
 	add_timer(&local->timer);
 	local->authentication_state = AWAITING_RESPONSE;
 } /* end authenticate */
@@ -2468,7 +2464,7 @@ static void rx_authenticate(ray_dev_t *local, struct rcs __iomem *prcs,
 				} else {
 					pr_debug("Authentication refused\n");
 					local->card_status = CARD_AUTH_REFUSED;
-					join_net((u_long) local);
+					join_net(&local->timer);
 					local->authentication_state =
 					    UNAUTHENTICATED;
 				}
@@ -2506,8 +2502,7 @@ static void associate(ray_dev_t *local)
 
 		del_timer(&local->timer);
 		local->timer.expires = jiffies + HZ * 2;
-		local->timer.data = (long)local;
-		local->timer.function = join_net;
+		local->timer.function = (TIMER_FUNC_TYPE)join_net;
 		add_timer(&local->timer);
 		local->card_status = CARD_ASSOC_FAILED;
 		return;
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
index 80fee699f58a..38b2ba1ac6f8 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
@@ -614,7 +614,10 @@ static int rtl8192eu_parse_efuse(struct rtl8xxxu_priv *priv)
 
 	dev_info(&priv->udev->dev, "Vendor: %.7s\n", efuse->vendor_name);
 	dev_info(&priv->udev->dev, "Product: %.11s\n", efuse->device_name);
-	dev_info(&priv->udev->dev, "Serial: %.11s\n", efuse->serial);
+	if (memchr_inv(efuse->serial, 0xff, 11))
+		dev_info(&priv->udev->dev, "Serial: %.11s\n", efuse->serial);
+	else
+		dev_info(&priv->udev->dev, "Serial not available.\n");
 
 	if (rtl8xxxu_debug & RTL8XXXU_DEBUG_EFUSE) {
 		unsigned char *raw = priv->efuse_wifi.raw;
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c
index ea18aa7afecb..0b34886321f1 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.c
+++ b/drivers/net/wireless/realtek/rtlwifi/base.c
@@ -249,8 +249,6 @@ static void _rtl_init_hw_vht_capab(struct ieee80211_hw *hw,
 
 		vht_cap->vht_supported = true;
 		vht_cap->cap =
-			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 |
-			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 |
 			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 |
 			IEEE80211_VHT_CAP_SHORT_GI_80 |
 			IEEE80211_VHT_CAP_TXSTBC |
@@ -283,8 +281,6 @@ static void _rtl_init_hw_vht_capab(struct ieee80211_hw *hw,
 
 		vht_cap->vht_supported = true;
 		vht_cap->cap =
-			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 |
-			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 |
 			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 |
 			IEEE80211_VHT_CAP_SHORT_GI_80 |
 			IEEE80211_VHT_CAP_TXSTBC |
@@ -835,7 +831,7 @@ static u8 _rtl_get_vht_highest_n_rate(struct ieee80211_hw *hw,
 		else if ((tx_mcs_map  & 0x000c) >> 2 ==
 			IEEE80211_VHT_MCS_SUPPORT_0_8)
 			hw_rate =
-			rtlpriv->cfg->maps[RTL_RC_VHT_RATE_2SS_MCS9];
+			rtlpriv->cfg->maps[RTL_RC_VHT_RATE_2SS_MCS8];
 		else
 			hw_rate =
 			rtlpriv->cfg->maps[RTL_RC_VHT_RATE_2SS_MCS9];
@@ -847,7 +843,7 @@ static u8 _rtl_get_vht_highest_n_rate(struct ieee80211_hw *hw,
 		else if ((tx_mcs_map  & 0x0003) ==
 			IEEE80211_VHT_MCS_SUPPORT_0_8)
 			hw_rate =
-			rtlpriv->cfg->maps[RTL_RC_VHT_RATE_1SS_MCS9];
+			rtlpriv->cfg->maps[RTL_RC_VHT_RATE_1SS_MCS8];
 		else
 			hw_rate =
 			rtlpriv->cfg->maps[RTL_RC_VHT_RATE_1SS_MCS9];
@@ -1103,6 +1099,42 @@ int rtlwifi_rate_mapping(struct ieee80211_hw *hw, bool isht, bool isvht,
 }
 EXPORT_SYMBOL(rtlwifi_rate_mapping);
 
+static u8 _rtl_get_tx_hw_rate(struct ieee80211_hw *hw,
+			      struct ieee80211_tx_info *info)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct ieee80211_tx_rate *r = &info->status.rates[0];
+	struct ieee80211_rate *txrate;
+	u8 hw_value = 0x0;
+
+	if (r->flags & IEEE80211_TX_RC_MCS) {
+		/* HT MCS0-15 */
+		hw_value = rtlpriv->cfg->maps[RTL_RC_HT_RATEMCS15] - 15 +
+			   r->idx;
+	} else if (r->flags & IEEE80211_TX_RC_VHT_MCS) {
+		/* VHT MCS0-9, NSS */
+		if (ieee80211_rate_get_vht_nss(r) == 2)
+			hw_value = rtlpriv->cfg->maps[RTL_RC_VHT_RATE_2SS_MCS9];
+		else
+			hw_value = rtlpriv->cfg->maps[RTL_RC_VHT_RATE_1SS_MCS9];
+
+		hw_value = hw_value - 9 + ieee80211_rate_get_vht_mcs(r);
+	} else {
+		/* legacy */
+		txrate = ieee80211_get_tx_rate(hw, info);
+
+		if (txrate)
+			hw_value = txrate->hw_value;
+	}
+
+	/* check 5G band */
+	if (rtlpriv->rtlhal.current_bandtype == BAND_ON_5G &&
+	    hw_value < rtlpriv->cfg->maps[RTL_RC_OFDM_RATE6M])
+		hw_value = rtlpriv->cfg->maps[RTL_RC_OFDM_RATE6M];
+
+	return hw_value;
+}
+
 void rtl_get_tcb_desc(struct ieee80211_hw *hw,
 		      struct ieee80211_tx_info *info,
 		      struct ieee80211_sta *sta,
@@ -1111,12 +1143,10 @@ void rtl_get_tcb_desc(struct ieee80211_hw *hw,
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_mac *rtlmac = rtl_mac(rtl_priv(hw));
 	struct ieee80211_hdr *hdr = rtl_get_hdr(skb);
-	struct ieee80211_rate *txrate;
+
 	__le16 fc = rtl_get_fc(skb);
 
-	txrate = ieee80211_get_tx_rate(hw, info);
-	if (txrate)
-		tcb_desc->hw_rate = txrate->hw_value;
+	tcb_desc->hw_rate = _rtl_get_tx_hw_rate(hw, info);
 
 	if (rtl_is_tx_report_skb(hw, skb))
 		tcb_desc->use_spe_rpt = 1;
@@ -1527,6 +1557,42 @@ void rtl_wait_tx_report_acked(struct ieee80211_hw *hw, u32 wait_ms)
 			 "Wait 1ms (%d/%d) to disable key.\n", i, wait_ms);
 	}
 }
+
+u32 rtl_get_hal_edca_param(struct ieee80211_hw *hw,
+			   struct ieee80211_vif *vif,
+			   enum wireless_mode wirelessmode,
+			   struct ieee80211_tx_queue_params *param)
+{
+	u32 reg = 0;
+	u8 sifstime = 10;
+	u8 slottime = 20;
+
+	/* AIFS = AIFSN * slot time + SIFS */
+	switch (wirelessmode) {
+	case WIRELESS_MODE_A:
+	case WIRELESS_MODE_N_24G:
+	case WIRELESS_MODE_N_5G:
+	case WIRELESS_MODE_AC_5G:
+	case WIRELESS_MODE_AC_24G:
+		sifstime = 16;
+		slottime = 9;
+		break;
+	case WIRELESS_MODE_G:
+		slottime = (vif->bss_conf.use_short_slot ? 9 : 20);
+		break;
+	default:
+		break;
+	}
+
+	reg |= (param->txop & 0x7FF) << 16;
+	reg |= (fls(param->cw_max) & 0xF) << 12;
+	reg |= (fls(param->cw_min) & 0xF) << 8;
+	reg |= (param->aifs & 0x0F) * slottime + sifstime;
+
+	return reg;
+}
+EXPORT_SYMBOL_GPL(rtl_get_hal_edca_param);
+
 /*********************************************************
  *
  * functions called by core.c
@@ -1932,6 +1998,22 @@ label_lps_done:
 	rtlpriv->link_info.tx_busy_traffic = tx_busy_traffic;
 	rtlpriv->link_info.higher_busyrxtraffic = higher_busyrxtraffic;
 
+	rtlpriv->stats.txbytesunicast_inperiod =
+		rtlpriv->stats.txbytesunicast -
+		rtlpriv->stats.txbytesunicast_last;
+	rtlpriv->stats.rxbytesunicast_inperiod =
+		rtlpriv->stats.rxbytesunicast -
+		rtlpriv->stats.rxbytesunicast_last;
+	rtlpriv->stats.txbytesunicast_last = rtlpriv->stats.txbytesunicast;
+	rtlpriv->stats.rxbytesunicast_last = rtlpriv->stats.rxbytesunicast;
+
+	rtlpriv->stats.txbytesunicast_inperiod_tp =
+		(u32)(rtlpriv->stats.txbytesunicast_inperiod * 8 / 2 /
+		1024 / 1024);
+	rtlpriv->stats.rxbytesunicast_inperiod_tp =
+		(u32)(rtlpriv->stats.rxbytesunicast_inperiod * 8 / 2 /
+		1024 / 1024);
+
 	/* <3> DM */
 	if (!rtlpriv->cfg->mod_params->disable_watchdog)
 		rtlpriv->cfg->ops->dm_watchdog(hw);
@@ -2204,7 +2286,7 @@ int rtl_send_smps_action(struct ieee80211_hw *hw,
 		struct rtl_sta_info *sta_entry =
 			(struct rtl_sta_info *) sta->drv_priv;
 		sta_entry->mimo_ps = smps;
-		/* rtlpriv->cfg->ops->update_rate_tbl(hw, sta, 0); */
+		/* rtlpriv->cfg->ops->update_rate_tbl(hw, sta, 0, true); */
 
 		info->control.rates[0].idx = 0;
 		info->band = hw->conf.chandef.chan->band;
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.h b/drivers/net/wireless/realtek/rtlwifi/base.h
index b56d1b7f5567..cfea9fc39a9f 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.h
+++ b/drivers/net/wireless/realtek/rtlwifi/base.h
@@ -137,6 +137,10 @@ void rtl_tx_report_handler(struct ieee80211_hw *hw, u8 *tmp_buf,
 			   u8 c2h_cmd_len);
 bool rtl_check_tx_report_acked(struct ieee80211_hw *hw);
 void rtl_wait_tx_report_acked(struct ieee80211_hw *hw, u32 wait_ms);
+u32 rtl_get_hal_edca_param(struct ieee80211_hw *hw,
+			   struct ieee80211_vif *vif,
+			   enum wireless_mode wirelessmode,
+			   struct ieee80211_tx_queue_params *param);
 
 void rtl_beacon_statistic(struct ieee80211_hw *hw, struct sk_buff *skb);
 void rtl_collect_scan_list(struct ieee80211_hw *hw, struct sk_buff *skb);
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b1ant.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b1ant.c
index c04425236ce4..5f726f6d3567 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b1ant.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b1ant.c
@@ -2260,14 +2260,11 @@ static void halbtc8723b1ant_run_coexist_mechanism(struct btc_coexist *btcoexist)
 
 		if (iot_peer != BTC_IOT_PEER_CISCO &&
 		    iot_peer != BTC_IOT_PEER_BROADCOM) {
-			if (bt_link_info->sco_exist)
-				halbtc8723b1ant_limited_rx(btcoexist,
-							   NORMAL_EXEC, false,
-							   false, 0x5);
-			else
-				halbtc8723b1ant_limited_rx(btcoexist,
-							   NORMAL_EXEC, false,
-							   false, 0x5);
+			bool sco_exist = bt_link_info->sco_exist;
+
+			halbtc8723b1ant_limited_rx(btcoexist,
+						   NORMAL_EXEC, sco_exist,
+						   false, 0x5);
 		} else {
 			if (bt_link_info->sco_exist) {
 				halbtc8723b1ant_limited_rx(btcoexist,
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index c53cbf3d52bd..015a8ec36703 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -453,7 +453,8 @@ static void _rtl_add_wowlan_patterns(struct ieee80211_hw *hw,
 	for (i = 0; i < wow->n_patterns; i++) {
 		memset(&rtl_pattern, 0, sizeof(struct rtl_wow_pattern));
 		memset(mask, 0, MAX_WOL_BIT_MASK_SIZE);
-		if (patterns[i].pattern_len > MAX_WOL_PATTERN_SIZE) {
+		if (patterns[i].pattern_len < 0 ||
+		    patterns[i].pattern_len > MAX_WOL_PATTERN_SIZE) {
 			RT_TRACE(rtlpriv, COMP_POWER, DBG_WARNING,
 				 "Pattern[%d] is too long\n", i);
 			continue;
@@ -945,7 +946,7 @@ static int rtl_op_sta_add(struct ieee80211_hw *hw,
 		memcpy(sta_entry->mac_addr, sta->addr, ETH_ALEN);
 		RT_TRACE(rtlpriv, COMP_MAC80211, DBG_DMESG,
 			"Add sta addr is %pM\n", sta->addr);
-		rtlpriv->cfg->ops->update_rate_tbl(hw, sta, 0);
+		rtlpriv->cfg->ops->update_rate_tbl(hw, sta, 0, true);
 	}
 
 	return 0;
@@ -1151,7 +1152,8 @@ static void rtl_op_bss_info_changed(struct ieee80211_hw *hw,
 			}
 
 			if (vif->type == NL80211_IFTYPE_STATION)
-				rtlpriv->cfg->ops->update_rate_tbl(hw, sta, 0);
+				rtlpriv->cfg->ops->update_rate_tbl(hw, sta, 0,
+								   true);
 			rcu_read_unlock();
 
 			/* to avoid AP Disassociation caused by inactivity */
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c
index 08dc8919ef60..b9a6d23364be 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.c
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.c
@@ -586,7 +586,7 @@ static void _rtl_pci_tx_isr(struct ieee80211_hw *hw, int prio)
 		skb = __skb_dequeue(&ring->queue);
 		pci_unmap_single(rtlpci->pdev,
 				 rtlpriv->cfg->ops->
-					     get_desc((u8 *)entry, true,
+					     get_desc(hw, (u8 *)entry, true,
 						      HW_DESC_TXBUFF_ADDR),
 				 skb->len, PCI_DMA_TODEVICE);
 
@@ -691,9 +691,10 @@ remap:
 		return 0;
 	rtlpci->rx_ring[rxring_idx].rx_buf[desc_idx] = skb;
 	if (rtlpriv->use_new_trx_flow) {
+		/* skb->cb may be 64 bit address */
 		rtlpriv->cfg->ops->set_desc(hw, (u8 *)entry, false,
 					    HW_DESC_RX_PREPARE,
-					    (u8 *)&bufferaddress);
+					    (u8 *)(dma_addr_t *)skb->cb);
 	} else {
 		rtlpriv->cfg->ops->set_desc(hw, (u8 *)entry, false,
 					    HW_DESC_RXBUFF_ADDR,
@@ -798,7 +799,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 			pdesc = &rtlpci->rx_ring[rxring_idx].desc[
 				rtlpci->rx_ring[rxring_idx].idx];
 
-			own = (u8)rtlpriv->cfg->ops->get_desc((u8 *)pdesc,
+			own = (u8)rtlpriv->cfg->ops->get_desc(hw, (u8 *)pdesc,
 							      false,
 							      HW_DESC_OWN);
 			if (own) /* wait data to be filled by hardware */
@@ -825,7 +826,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 							   (u8 *)buffer_desc,
 							   hw_queue);
 
-		len = rtlpriv->cfg->ops->get_desc((u8 *)pdesc, false,
+		len = rtlpriv->cfg->ops->get_desc(hw, (u8 *)pdesc, false,
 						  HW_DESC_RXPKT_LEN);
 
 		if (skb->end - skb->tail > len) {
@@ -1122,7 +1123,7 @@ static void _rtl_pci_prepare_bcn_tasklet(struct ieee80211_hw *hw)
 	if (pskb) {
 		pci_unmap_single(rtlpci->pdev,
 				 rtlpriv->cfg->ops->get_desc(
-				 (u8 *)entry, true, HW_DESC_TXBUFF_ADDR),
+				 hw, (u8 *)entry, true, HW_DESC_TXBUFF_ADDR),
 				 pskb->len, PCI_DMA_TODEVICE);
 		kfree_skb(pskb);
 	}
@@ -1378,7 +1379,8 @@ static void _rtl_pci_free_tx_ring(struct ieee80211_hw *hw,
 
 		pci_unmap_single(rtlpci->pdev,
 				 rtlpriv->cfg->
-					     ops->get_desc((u8 *)entry, true,
+					     ops->get_desc(hw, (u8 *)entry,
+						   true,
 						   HW_DESC_TXBUFF_ADDR),
 				 skb->len, PCI_DMA_TODEVICE);
 		kfree_skb(skb);
@@ -1507,7 +1509,7 @@ int rtl_pci_reset_trx_ring(struct ieee80211_hw *hw)
 			for (i = 0; i < rtlpci->rxringcount; i++) {
 				entry = &rtlpci->rx_ring[rxring_idx].desc[i];
 				bufferaddress =
-				  rtlpriv->cfg->ops->get_desc((u8 *)entry,
+				  rtlpriv->cfg->ops->get_desc(hw, (u8 *)entry,
 				  false , HW_DESC_RXBUFF_ADDR);
 				memset((u8 *)entry , 0 ,
 				       sizeof(*rtlpci->rx_ring
@@ -1560,7 +1562,7 @@ int rtl_pci_reset_trx_ring(struct ieee80211_hw *hw)
 
 				pci_unmap_single(rtlpci->pdev,
 						 rtlpriv->cfg->ops->
-							 get_desc((u8 *)
+							 get_desc(hw, (u8 *)
 							 entry,
 							 true,
 							 HW_DESC_TXBUFF_ADDR),
@@ -1673,7 +1675,7 @@ static int rtl_pci_tx(struct ieee80211_hw *hw,
 	if (rtlpriv->use_new_trx_flow) {
 		ptx_bd_desc = &ring->buffer_desc[idx];
 	} else {
-		own = (u8) rtlpriv->cfg->ops->get_desc((u8 *)pdesc,
+		own = (u8)rtlpriv->cfg->ops->get_desc(hw, (u8 *)pdesc,
 				true, HW_DESC_OWN);
 
 		if ((own == 1) && (hw_queue != BEACON_QUEUE)) {
@@ -2163,6 +2165,21 @@ static int rtl_pci_intr_mode_decide(struct ieee80211_hw *hw)
 	return ret;
 }
 
+static void platform_enable_dma64(struct pci_dev *pdev, bool dma64)
+{
+	u8	value;
+
+	pci_read_config_byte(pdev, 0x719, &value);
+
+	/* 0x719 Bit5 is DMA64 bit fetch. */
+	if (dma64)
+		value |= BIT(5);
+	else
+		value &= ~BIT(5);
+
+	pci_write_config_byte(pdev, 0x719, value);
+}
+
 int rtl_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *id)
 {
@@ -2181,13 +2198,25 @@ int rtl_pci_probe(struct pci_dev *pdev,
 		return err;
 	}
 
-	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
+	if (((struct rtl_hal_cfg *)id->driver_data)->mod_params->dma64 &&
+	    !pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+		if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) {
+			WARN_ONCE(true,
+				  "Unable to obtain 64bit DMA for consistent allocations\n");
+			err = -ENOMEM;
+			goto fail1;
+		}
+
+		platform_enable_dma64(pdev, true);
+	} else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
 		if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32))) {
 			WARN_ONCE(true,
 				  "rtlwifi: Unable to obtain 32bit DMA for consistent allocations\n");
 			err = -ENOMEM;
 			goto fail1;
 		}
+
+		platform_enable_dma64(pdev, false);
 	}
 
 	pci_set_master(pdev);
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.h b/drivers/net/wireless/realtek/rtlwifi/pci.h
index d9039ea10ba4..1af92b34979d 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.h
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.h
@@ -143,13 +143,7 @@ struct rtl_pci_capabilities_header {
  * RX wifi info == RX descriptor in old flow
  */
 struct rtl_tx_buffer_desc {
-#if (RTL8192EE_SEG_NUM == 2)
-	u32 dword[2*(DMA_IS_64BIT + 1)*8]; /*seg = 8*/
-#elif (RTL8192EE_SEG_NUM == 1)
-	u32 dword[2*(DMA_IS_64BIT + 1)*4]; /*seg = 4*/
-#elif (RTL8192EE_SEG_NUM == 0)
-	u32 dword[2*(DMA_IS_64BIT + 1)*2]; /*seg = 2*/
-#endif
+	u32 dword[4 * (1 << (BUFDESC_SEG_NUM + 1))];
 } __packed;
 
 struct rtl_tx_desc {
@@ -157,7 +151,7 @@ struct rtl_tx_desc {
 } __packed;
 
 struct rtl_rx_buffer_desc { /*rx buffer desc*/
-	u32 dword[2];
+	u32 dword[4];
 } __packed;
 
 struct rtl_rx_desc { /*old: rx desc new: rx wifi info*/
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/dm.c
index f936a491371b..207411d1b015 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/dm.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/dm.c
@@ -1221,7 +1221,8 @@ static void rtl88e_dm_refresh_rate_adaptive_mask(struct ieee80211_hw *hw)
 			sta = rtl_find_sta(hw, mac->bssid);
 			if (sta)
 				rtlpriv->cfg->ops->update_rate_tbl(hw, sta,
-								   p_ra->ratr_state);
+							p_ra->ratr_state,
+								   true);
 			rcu_read_unlock();
 
 			p_ra->pre_ratr_state = p_ra->ratr_state;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c
index 0ba26d27d11c..d31117d52381 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c
@@ -99,6 +99,7 @@ static void _rtl88ee_return_beacon_queue_skb(struct ieee80211_hw *hw)
 
 		pci_unmap_single(rtlpci->pdev,
 				 rtlpriv->cfg->ops->get_desc(
+				 hw,
 				 (u8 *)entry, true, HW_DESC_TXBUFF_ADDR),
 				 skb->len, PCI_DMA_TODEVICE);
 		kfree_skb(skb);
@@ -2076,7 +2077,7 @@ static void rtl88ee_update_hal_rate_table(struct ieee80211_hw *hw,
 }
 
 static void rtl88ee_update_hal_rate_mask(struct ieee80211_hw *hw,
-		struct ieee80211_sta *sta, u8 rssi_level)
+		struct ieee80211_sta *sta, u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_phy *rtlphy = &(rtlpriv->phy);
@@ -2207,12 +2208,12 @@ static void rtl88ee_update_hal_rate_mask(struct ieee80211_hw *hw,
 }
 
 void rtl88ee_update_hal_rate_tbl(struct ieee80211_hw *hw,
-		struct ieee80211_sta *sta, u8 rssi_level)
+		struct ieee80211_sta *sta, u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	if (rtlpriv->dm.useramask)
-		rtl88ee_update_hal_rate_mask(hw, sta, rssi_level);
+		rtl88ee_update_hal_rate_mask(hw, sta, rssi_level, update_bw);
 	else
 		rtl88ee_update_hal_rate_table(hw, sta);
 }
@@ -2235,7 +2236,7 @@ bool rtl88ee_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
-	enum rf_pwrstate e_rfpowerstate_toset, cur_rfstate;
+	enum rf_pwrstate e_rfpowerstate_toset;
 	u32 u4tmp;
 	bool b_actuallyset = false;
 
@@ -2254,8 +2255,6 @@ bool rtl88ee_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid)
 		spin_unlock(&rtlpriv->locks.rf_ps_lock);
 	}
 
-	cur_rfstate = ppsc->rfpwr_state;
-
 	u4tmp = rtl_read_dword(rtlpriv, REG_GPIO_OUTPUT);
 	e_rfpowerstate_toset = (u4tmp & BIT(31)) ? ERFON : ERFOFF;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.h
index d38dbca3c19e..719b78a3b7db 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.h
@@ -43,7 +43,8 @@ void rtl88ee_update_interrupt_mask(struct ieee80211_hw *hw,
 				   u32 add_msr, u32 rm_msr);
 void rtl88ee_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val);
 void rtl88ee_update_hal_rate_tbl(struct ieee80211_hw *hw,
-				 struct ieee80211_sta *sta, u8 rssi_level);
+				 struct ieee80211_sta *sta, u8 rssi_level,
+				 bool update_bw);
 void rtl88ee_update_channel_access_setting(struct ieee80211_hw *hw);
 bool rtl88ee_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid);
 void rtl88ee_enable_hw_security_config(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c
index 57e5d5c1d24b..35de3aeafcc9 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c
@@ -41,6 +41,7 @@
 
 static void rtl88e_init_aspm_vars(struct ieee80211_hw *hw)
 {
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
 	/*close ASPM for AMD defaultly */
@@ -77,7 +78,7 @@ static void rtl88e_init_aspm_vars(struct ieee80211_hw *hw)
 	 * 1 - Support ASPM,
 	 * 2 - According to chipset.
 	 */
-	rtlpci->const_support_pciaspm = 1;
+	rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support;
 }
 
 int rtl88e_init_sw_vars(struct ieee80211_hw *hw)
@@ -276,6 +277,7 @@ static struct rtl_mod_params rtl88ee_mod_params = {
 	.swctrl_lps = false,
 	.fwctrl_lps = false,
 	.msi_support = true,
+	.aspm_support = 1,
 	.debug_level = 0,
 	.debug_mask = 0,
 };
@@ -399,6 +401,7 @@ module_param_named(ips, rtl88ee_mod_params.inactiveps, bool, 0444);
 module_param_named(swlps, rtl88ee_mod_params.swctrl_lps, bool, 0444);
 module_param_named(fwlps, rtl88ee_mod_params.fwctrl_lps, bool, 0444);
 module_param_named(msi, rtl88ee_mod_params.msi_support, bool, 0444);
+module_param_named(aspm, rtl88ee_mod_params.aspm_support, int, 0444);
 module_param_named(disable_watchdog, rtl88ee_mod_params.disable_watchdog,
 		   bool, 0444);
 MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n");
@@ -406,6 +409,7 @@ MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n");
 MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n");
 MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n");
 MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 1)\n");
+MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n");
 MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)");
 MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)");
 MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n");
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c
index dd3e12b74447..9670732b2bc6 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c
@@ -786,7 +786,8 @@ void rtl88ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc,
 	}
 }
 
-u32 rtl88ee_get_desc(u8 *pdesc, bool istx, u8 desc_name)
+u64 rtl88ee_get_desc(struct ieee80211_hw *hw,
+		     u8 *pdesc, bool istx, u8 desc_name)
 {
 	u32 ret = 0;
 
@@ -828,7 +829,7 @@ bool rtl88ee_is_tx_desc_closed(struct ieee80211_hw *hw, u8 hw_queue, u16 index)
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue];
 	u8 *entry = (u8 *)(&ring->desc[ring->idx]);
-	u8 own = (u8)rtl88ee_get_desc(entry, true, HW_DESC_OWN);
+	u8 own = (u8)rtl88ee_get_desc(hw, entry, true, HW_DESC_OWN);
 
 	/*beacon packet will only use the first
 	 *descriptor defautly,and the own may not
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.h
index 9a1c2087adee..f902d6769aa8 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.h
@@ -782,7 +782,8 @@ bool rtl88ee_rx_query_desc(struct ieee80211_hw *hw,
 			   u8 *pdesc, struct sk_buff *skb);
 void rtl88ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc,
 		      bool istx, u8 desc_name, u8 *val);
-u32 rtl88ee_get_desc(u8 *pdesc, bool istx, u8 desc_name);
+u64 rtl88ee_get_desc(struct ieee80211_hw *hw,
+		     u8 *pdesc, bool istx, u8 desc_name);
 bool rtl88ee_is_tx_desc_closed(struct ieee80211_hw *hw,
 			       u8 hw_queue, u16 index);
 void rtl88ee_tx_polling(struct ieee80211_hw *hw, u8 hw_queue);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c
index 9956026bae0a..9310fad69cd9 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c
@@ -1865,7 +1865,7 @@ static void rtl92ce_update_hal_rate_table(struct ieee80211_hw *hw,
 }
 
 static void rtl92ce_update_hal_rate_mask(struct ieee80211_hw *hw,
-		struct ieee80211_sta *sta, u8 rssi_level)
+		struct ieee80211_sta *sta, u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_phy *rtlphy = &(rtlpriv->phy);
@@ -1995,12 +1995,12 @@ static void rtl92ce_update_hal_rate_mask(struct ieee80211_hw *hw,
 }
 
 void rtl92ce_update_hal_rate_tbl(struct ieee80211_hw *hw,
-		struct ieee80211_sta *sta, u8 rssi_level)
+		struct ieee80211_sta *sta, u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	if (rtlpriv->dm.useramask)
-		rtl92ce_update_hal_rate_mask(hw, sta, rssi_level);
+		rtl92ce_update_hal_rate_mask(hw, sta, rssi_level, update_bw);
 	else
 		rtl92ce_update_hal_rate_table(hw, sta);
 }
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.h
index 877f138a0cb9..7683c5dfe851 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.h
@@ -56,9 +56,8 @@ void rtl92ce_update_interrupt_mask(struct ieee80211_hw *hw,
 				   u32 add_msr, u32 rm_msr);
 void rtl92ce_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val);
 void rtl92ce_update_hal_rate_tbl(struct ieee80211_hw *hw,
-				 struct ieee80211_sta *sta, u8 rssi_level);
-void rtl92ce_update_hal_rate_tbl(struct ieee80211_hw *hw,
-				 struct ieee80211_sta *sta, u8 rssi_level);
+				 struct ieee80211_sta *sta, u8 rssi_level,
+				 bool update_bw);
 void rtl92ce_update_channel_access_setting(struct ieee80211_hw *hw);
 bool rtl92ce_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid);
 void rtl92ce_enable_hw_security_config(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
index 38f85bfdf0c7..71a6761d3648 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
@@ -44,6 +44,7 @@
 
 static void rtl92c_init_aspm_vars(struct ieee80211_hw *hw)
 {
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
 	/*close ASPM for AMD defaultly */
@@ -83,7 +84,7 @@ static void rtl92c_init_aspm_vars(struct ieee80211_hw *hw)
 	 * 1 - Support ASPM,
 	 * 2 - According to chipset.
 	 */
-	rtlpci->const_support_pciaspm = 1;
+	rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support;
 }
 
 int rtl92c_init_sw_vars(struct ieee80211_hw *hw)
@@ -252,6 +253,7 @@ static struct rtl_mod_params rtl92ce_mod_params = {
 	.inactiveps = true,
 	.swctrl_lps = false,
 	.fwctrl_lps = true,
+	.aspm_support = 1,
 	.debug_level = 0,
 	.debug_mask = 0,
 };
@@ -375,10 +377,12 @@ module_param_named(debug_mask, rtl92ce_mod_params.debug_mask, ullong, 0644);
 module_param_named(ips, rtl92ce_mod_params.inactiveps, bool, 0444);
 module_param_named(swlps, rtl92ce_mod_params.swctrl_lps, bool, 0444);
 module_param_named(fwlps, rtl92ce_mod_params.fwctrl_lps, bool, 0444);
+module_param_named(aspm, rtl92ce_mod_params.aspm_support, int, 0444);
 MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n");
 MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n");
 MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n");
 MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n");
+MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n");
 MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)");
 MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)");
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.c
index 94a4b39437cd..d36e0060cc7a 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.c
@@ -697,7 +697,8 @@ void rtl92ce_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
 	}
 }
 
-u32 rtl92ce_get_desc(u8 *p_desc, bool istx, u8 desc_name)
+u64 rtl92ce_get_desc(struct ieee80211_hw *hw, u8 *p_desc,
+		     bool istx, u8 desc_name)
 {
 	u32 ret = 0;
 
@@ -740,7 +741,7 @@ bool rtl92ce_is_tx_desc_closed(struct ieee80211_hw *hw,
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue];
 	u8 *entry = (u8 *)(&ring->desc[ring->idx]);
-	u8 own = (u8)rtl92ce_get_desc(entry, true, HW_DESC_OWN);
+	u8 own = (u8)rtl92ce_get_desc(hw, entry, true, HW_DESC_OWN);
 
 	/*beacon packet will only use the first
 	 *descriptor defautly,and the own may not
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.h
index 66291fc341e7..91f0bd6b752f 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.h
@@ -718,7 +718,8 @@ bool rtl92ce_rx_query_desc(struct ieee80211_hw *hw,
 			   u8 *pdesc, struct sk_buff *skb);
 void rtl92ce_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
 		      u8 desc_name, u8 *val);
-u32 rtl92ce_get_desc(u8 *pdesc, bool istx, u8 desc_name);
+u64 rtl92ce_get_desc(struct ieee80211_hw *hw, u8 *p_desc,
+		     bool istx, u8 desc_name);
 bool rtl92ce_is_tx_desc_closed(struct ieee80211_hw *hw,
 			       u8 hw_queue, u16 index);
 void rtl92ce_tx_polling(struct ieee80211_hw *hw, u8 hw_queue);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c
index 530e80f0ef0b..1e60f70481f5 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c
@@ -2006,7 +2006,7 @@ static void rtl92cu_update_hal_rate_table(struct ieee80211_hw *hw,
 
 static void rtl92cu_update_hal_rate_mask(struct ieee80211_hw *hw,
 					 struct ieee80211_sta *sta,
-					 u8 rssi_level)
+					 u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_phy *rtlphy = &(rtlpriv->phy);
@@ -2153,12 +2153,12 @@ static void rtl92cu_update_hal_rate_mask(struct ieee80211_hw *hw,
 
 void rtl92cu_update_hal_rate_tbl(struct ieee80211_hw *hw,
 				 struct ieee80211_sta *sta,
-				 u8 rssi_level)
+				 u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	if (rtlpriv->dm.useramask)
-		rtl92cu_update_hal_rate_mask(hw, sta, rssi_level);
+		rtl92cu_update_hal_rate_mask(hw, sta, rssi_level, update_bw);
 	else
 		rtl92cu_update_hal_rate_table(hw, sta);
 }
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.h
index 932f056f7ef8..ebd168400d45 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.h
@@ -104,6 +104,6 @@ void rtl92c_fill_h2c_cmd(struct ieee80211_hw *hw,
 bool rtl92cu_phy_mac_config(struct ieee80211_hw *hw);
 void rtl92cu_update_hal_rate_tbl(struct ieee80211_hw *hw,
 				 struct ieee80211_sta *sta,
-				 u8 rssi_level);
+				 u8 rssi_level, bool update_bw);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c
index f4129cf96e7c..85cedd083d2b 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c
@@ -490,7 +490,7 @@ static bool _rtl92d_cmd_send_packet(struct ieee80211_hw *hw,
 	spin_lock_irqsave(&rtlpriv->locks.irq_th_lock, flags);
 	pdesc = &ring->desc[idx];
 	/* discard output from call below */
-	rtlpriv->cfg->ops->get_desc((u8 *) pdesc, true, HW_DESC_OWN);
+	rtlpriv->cfg->ops->get_desc(hw, (u8 *)pdesc, true, HW_DESC_OWN);
 	rtlpriv->cfg->ops->fill_tx_cmddesc(hw, (u8 *) pdesc, 1, 1, skb);
 	__skb_queue_tail(&ring->queue, skb);
 	spin_unlock_irqrestore(&rtlpriv->locks.irq_th_lock, flags);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c
index cf28d25c551f..5a67f85fa165 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c
@@ -1897,7 +1897,7 @@ static void rtl92de_update_hal_rate_table(struct ieee80211_hw *hw,
 }
 
 static void rtl92de_update_hal_rate_mask(struct ieee80211_hw *hw,
-		struct ieee80211_sta *sta, u8 rssi_level)
+		struct ieee80211_sta *sta, u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_phy *rtlphy = &(rtlpriv->phy);
@@ -2033,12 +2033,12 @@ static void rtl92de_update_hal_rate_mask(struct ieee80211_hw *hw,
 }
 
 void rtl92de_update_hal_rate_tbl(struct ieee80211_hw *hw,
-		struct ieee80211_sta *sta, u8 rssi_level)
+		struct ieee80211_sta *sta, u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	if (rtlpriv->dm.useramask)
-		rtl92de_update_hal_rate_mask(hw, sta, rssi_level);
+		rtl92de_update_hal_rate_mask(hw, sta, rssi_level, update_bw);
 	else
 		rtl92de_update_hal_rate_table(hw, sta);
 }
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.h
index 24b03b9999be..85c565b86ae3 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.h
@@ -43,7 +43,8 @@ void rtl92de_update_interrupt_mask(struct ieee80211_hw *hw,
 				   u32 add_msr, u32 rm_msr);
 void rtl92de_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val);
 void rtl92de_update_hal_rate_tbl(struct ieee80211_hw *hw,
-				 struct ieee80211_sta *sta, u8 rssi_level);
+				 struct ieee80211_sta *sta, u8 rssi_level,
+				 bool update_bw);
 void rtl92de_update_channel_access_setting(struct ieee80211_hw *hw);
 bool rtl92de_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid);
 void rtl92de_enable_hw_security_config(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
index a6549f5f6c59..d5ba2bace79b 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
@@ -40,6 +40,7 @@
 
 static void rtl92d_init_aspm_vars(struct ieee80211_hw *hw)
 {
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
 	/*close ASPM for AMD defaultly */
@@ -79,7 +80,7 @@ static void rtl92d_init_aspm_vars(struct ieee80211_hw *hw)
 	 * 1 - Support ASPM,
 	 * 2 - According to chipset.
 	 */
-	rtlpci->const_support_pciaspm = 1;
+	rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support;
 }
 
 static int rtl92d_init_sw_vars(struct ieee80211_hw *hw)
@@ -254,6 +255,7 @@ static struct rtl_mod_params rtl92de_mod_params = {
 	.inactiveps = true,
 	.swctrl_lps = true,
 	.fwctrl_lps = false,
+	.aspm_support = 1,
 	.debug_level = 0,
 	.debug_mask = 0,
 };
@@ -369,11 +371,13 @@ module_param_named(debug_level, rtl92de_mod_params.debug_level, int, 0644);
 module_param_named(ips, rtl92de_mod_params.inactiveps, bool, 0444);
 module_param_named(swlps, rtl92de_mod_params.swctrl_lps, bool, 0444);
 module_param_named(fwlps, rtl92de_mod_params.fwctrl_lps, bool, 0444);
+module_param_named(aspm, rtl92de_mod_params.aspm_support, int, 0444);
 module_param_named(debug_mask, rtl92de_mod_params.debug_mask, ullong, 0644);
 MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n");
 MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n");
 MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 1)\n");
 MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 0)\n");
+MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n");
 MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)");
 MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)");
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c
index 86019f654428..d7b023cf7400 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c
@@ -821,7 +821,8 @@ void rtl92de_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
 	}
 }
 
-u32 rtl92de_get_desc(u8 *p_desc, bool istx, u8 desc_name)
+u64 rtl92de_get_desc(struct ieee80211_hw *hw,
+		     u8 *p_desc, bool istx, u8 desc_name)
 {
 	u32 ret = 0;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h
index 9bb6cc648590..f7f776539438 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h
@@ -735,7 +735,8 @@ bool rtl92de_rx_query_desc(struct ieee80211_hw *hw,
 			   u8 *pdesc, struct sk_buff *skb);
 void rtl92de_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
 		      u8 desc_name, u8 *val);
-u32 rtl92de_get_desc(u8 *pdesc, bool istx, u8 desc_name);
+u64 rtl92de_get_desc(struct ieee80211_hw *hw,
+		     u8 *p_desc, bool istx, u8 desc_name);
 void rtl92de_tx_polling(struct ieee80211_hw *hw, u8 hw_queue);
 void rtl92de_tx_fill_cmddesc(struct ieee80211_hw *hw, u8 *pdesc,
 			     bool b_firstseg, bool b_lastseg,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c
index e6b5786c7d4a..faed6e2dedf6 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c
@@ -1039,7 +1039,8 @@ static void rtl92ee_dm_refresh_rate_adaptive_mask(struct ieee80211_hw *hw)
 			sta = rtl_find_sta(hw, mac->bssid);
 			if (sta)
 				rtlpriv->cfg->ops->update_rate_tbl(hw, sta,
-							      p_ra->ratr_state);
+							      p_ra->ratr_state,
+							      true);
 			rcu_read_unlock();
 
 			p_ra->pre_ratr_state = p_ra->ratr_state;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.c
index 7eae27f8e173..f9563ae301ad 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.c
@@ -682,7 +682,7 @@ void rtl92ee_set_fw_rsvdpagepkt(struct ieee80211_hw *hw, bool b_dl_finished)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
 	struct sk_buff *skb = NULL;
-
+	bool rtstatus;
 	u32 totalpacketlen;
 	u8 u1rsvdpageloc[5] = { 0 };
 	bool b_dlok = false;
@@ -768,7 +768,9 @@ void rtl92ee_set_fw_rsvdpagepkt(struct ieee80211_hw *hw, bool b_dl_finished)
 	skb = dev_alloc_skb(totalpacketlen);
 	skb_put_data(skb, &reserved_page_packet, totalpacketlen);
 
-	b_dlok = true;
+	rtstatus = rtl_cmd_send_packet(hw, skb);
+	if (rtstatus)
+		b_dlok = true;
 
 	if (b_dlok) {
 		RT_TRACE(rtlpriv, COMP_POWER, DBG_LOUD ,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
index ef9394be7016..6fc3090c4b72 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
@@ -840,6 +840,31 @@ static bool _rtl92ee_init_mac(struct ieee80211_hw *hw)
 	/* Set TCR register */
 	rtl_write_dword(rtlpriv, REG_TCR, rtlpci->transmit_config);
 
+	/* Set TX/RX descriptor physical address -- HI part */
+	if (!rtlpriv->cfg->mod_params->dma64)
+		goto dma64_end;
+
+	rtl_write_dword(rtlpriv, REG_BCNQ_DESA + 4,
+			((u64)rtlpci->tx_ring[BEACON_QUEUE].buffer_desc_dma) >>
+				32);
+	rtl_write_dword(rtlpriv, REG_MGQ_DESA + 4,
+			(u64)rtlpci->tx_ring[MGNT_QUEUE].buffer_desc_dma >> 32);
+	rtl_write_dword(rtlpriv, REG_VOQ_DESA + 4,
+			(u64)rtlpci->tx_ring[VO_QUEUE].buffer_desc_dma >> 32);
+	rtl_write_dword(rtlpriv, REG_VIQ_DESA + 4,
+			(u64)rtlpci->tx_ring[VI_QUEUE].buffer_desc_dma >> 32);
+	rtl_write_dword(rtlpriv, REG_BEQ_DESA + 4,
+			(u64)rtlpci->tx_ring[BE_QUEUE].buffer_desc_dma >> 32);
+	rtl_write_dword(rtlpriv, REG_BKQ_DESA + 4,
+			(u64)rtlpci->tx_ring[BK_QUEUE].buffer_desc_dma >> 32);
+	rtl_write_dword(rtlpriv, REG_HQ0_DESA + 4,
+			(u64)rtlpci->tx_ring[HIGH_QUEUE].buffer_desc_dma >> 32);
+
+	rtl_write_dword(rtlpriv, REG_RX_DESA + 4,
+			(u64)rtlpci->rx_ring[RX_MPDU_QUEUE].dma >> 32);
+
+dma64_end:
+
 	/* Set TX/RX descriptor physical address(from OS API). */
 	rtl_write_dword(rtlpriv, REG_BCNQ_DESA,
 			((u64)rtlpci->tx_ring[BEACON_QUEUE].buffer_desc_dma) &
@@ -913,15 +938,9 @@ static bool _rtl92ee_init_mac(struct ieee80211_hw *hw)
 	rtl_write_word(rtlpriv, REG_HI7Q_TXBD_NUM,
 		       TX_DESC_NUM_92E | ((RTL8192EE_SEG_NUM << 12) & 0x3000));
 	/*Rx*/
-#if (DMA_IS_64BIT == 1)
 	rtl_write_word(rtlpriv, REG_RX_RXBD_NUM,
 		       RX_DESC_NUM_92E |
 		       ((RTL8192EE_SEG_NUM << 13) & 0x6000) | 0x8000);
-#else
-	rtl_write_word(rtlpriv, REG_RX_RXBD_NUM,
-		       RX_DESC_NUM_92E |
-		       ((RTL8192EE_SEG_NUM << 13) & 0x6000) | 0x0000);
-#endif
 
 	rtl_write_dword(rtlpriv, REG_TSFTIMER_HCI, 0XFFFFFFFF);
 
@@ -2251,7 +2270,7 @@ static u8 _rtl92ee_mrate_idx_to_arfr_id(struct ieee80211_hw *hw, u8 rate_index)
 
 static void rtl92ee_update_hal_rate_mask(struct ieee80211_hw *hw,
 					 struct ieee80211_sta *sta,
-					 u8 rssi_level)
+					 u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_phy *rtlphy = &rtlpriv->phy;
@@ -2370,7 +2389,7 @@ static void rtl92ee_update_hal_rate_mask(struct ieee80211_hw *hw,
 				       (ratr_index << 28);
 	rate_mask[0] = macid;
 	rate_mask[1] = ratr_index | (b_shortgi ? 0x80 : 0x00);
-	rate_mask[2] = curtxbw_40mhz;
+	rate_mask[2] = curtxbw_40mhz | ((!update_bw) << 3);
 	rate_mask[3] = (u8)(ratr_bitmap & 0x000000ff);
 	rate_mask[4] = (u8)((ratr_bitmap & 0x0000ff00) >> 8);
 	rate_mask[5] = (u8)((ratr_bitmap & 0x00ff0000) >> 16);
@@ -2385,12 +2404,13 @@ static void rtl92ee_update_hal_rate_mask(struct ieee80211_hw *hw,
 }
 
 void rtl92ee_update_hal_rate_tbl(struct ieee80211_hw *hw,
-				 struct ieee80211_sta *sta, u8 rssi_level)
+				 struct ieee80211_sta *sta, u8 rssi_level,
+				 bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	if (rtlpriv->dm.useramask)
-		rtl92ee_update_hal_rate_mask(hw, sta, rssi_level);
+		rtl92ee_update_hal_rate_mask(hw, sta, rssi_level, update_bw);
 }
 
 void rtl92ee_update_channel_access_setting(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.h
index 05413f189685..cd6aeb44b996 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.h
@@ -43,7 +43,8 @@ void rtl92ee_update_interrupt_mask(struct ieee80211_hw *hw,
 				   u32 add_msr, u32 rm_msr);
 void rtl92ee_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val);
 void rtl92ee_update_hal_rate_tbl(struct ieee80211_hw *hw,
-				 struct ieee80211_sta *sta, u8 rssi_level);
+				 struct ieee80211_sta *sta, u8 rssi_level,
+				 bool update_bw);
 void rtl92ee_update_channel_access_setting(struct ieee80211_hw *hw);
 bool rtl92ee_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid);
 void rtl92ee_enable_hw_security_config(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c
index a3490080d066..ef92a789871d 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c
@@ -44,6 +44,7 @@
 
 static void rtl92ee_init_aspm_vars(struct ieee80211_hw *hw)
 {
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
 	/*close ASPM for AMD defaultly */
@@ -83,7 +84,7 @@ static void rtl92ee_init_aspm_vars(struct ieee80211_hw *hw)
 	 * 1 - Support ASPM,
 	 * 2 - According to chipset.
 	 */
-	rtlpci->const_support_pciaspm = 1;
+	rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support;
 }
 
 int rtl92ee_init_sw_vars(struct ieee80211_hw *hw)
@@ -259,6 +260,8 @@ static struct rtl_mod_params rtl92ee_mod_params = {
 	.swctrl_lps = false,
 	.fwctrl_lps = true,
 	.msi_support = true,
+	.dma64 = false,
+	.aspm_support = 1,
 	.debug_level = 0,
 	.debug_mask = 0,
 };
@@ -376,6 +379,8 @@ module_param_named(ips, rtl92ee_mod_params.inactiveps, bool, 0444);
 module_param_named(swlps, rtl92ee_mod_params.swctrl_lps, bool, 0444);
 module_param_named(fwlps, rtl92ee_mod_params.fwctrl_lps, bool, 0444);
 module_param_named(msi, rtl92ee_mod_params.msi_support, bool, 0444);
+module_param_named(dma64, rtl92ee_mod_params.dma64, bool, 0444);
+module_param_named(aspm, rtl92ee_mod_params.aspm_support, int, 0444);
 module_param_named(disable_watchdog, rtl92ee_mod_params.disable_watchdog,
 		   bool, 0444);
 MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n");
@@ -383,6 +388,8 @@ MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n");
 MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n");
 MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n");
 MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 1)\n");
+MODULE_PARM_DESC(dma64, "Set to 1 to use DMA 64 (default 0)\n");
+MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n");
 MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)");
 MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)");
 MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n");
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.c
index c58393eab6a1..12255682e890 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.c
@@ -581,13 +581,9 @@ void rtl92ee_pre_fill_tx_bd_desc(struct ieee80211_hw *hw,
 	u8 i = 0;
 	u16 real_desc_size = 0x28;
 	u16	append_early_mode_size = 0;
-#if (RTL8192EE_SEG_NUM == 0)
-	u8 segmentnum = 2;
-#elif (RTL8192EE_SEG_NUM == 1)
-	u8 segmentnum = 4;
-#elif (RTL8192EE_SEG_NUM == 2)
-	u8 segmentnum = 8;
-#endif
+	u8 segmentnum = 1 << (RTL8192EE_SEG_NUM + 1);
+	dma_addr_t desc_dma_addr;
+	bool dma64 = rtlpriv->cfg->mod_params->dma64;
 
 	tx_page_size = 2;
 	current_bd_desc = rtlpci->tx_ring[queue_index].cur_tx_wp;
@@ -609,6 +605,10 @@ void rtl92ee_pre_fill_tx_bd_desc(struct ieee80211_hw *hw,
 			psblen += 1;
 	}
 
+	/* tx desc addr */
+	desc_dma_addr = rtlpci->tx_ring[queue_index].dma +
+			(current_bd_desc * TX_DESC_SIZE);
+
 	/* Reset */
 	SET_TX_BUFF_DESC_LEN_0(tx_bd_desc, 0);
 	SET_TX_BUFF_DESC_PSB(tx_bd_desc, 0);
@@ -618,17 +618,9 @@ void rtl92ee_pre_fill_tx_bd_desc(struct ieee80211_hw *hw,
 		SET_TXBUFFER_DESC_LEN_WITH_OFFSET(tx_bd_desc, i, 0);
 		SET_TXBUFFER_DESC_AMSDU_WITH_OFFSET(tx_bd_desc, i, 0);
 		SET_TXBUFFER_DESC_ADD_LOW_WITH_OFFSET(tx_bd_desc, i, 0);
-#if (DMA_IS_64BIT == 1)
-		SET_TXBUFFER_DESC_ADD_HIGT_WITH_OFFSET(tx_bd_desc, i, 0);
-#endif
+		SET_TXBUFFER_DESC_ADD_HIGH_WITH_OFFSET(tx_bd_desc, i, 0, dma64);
 	}
-	SET_TX_BUFF_DESC_LEN_1(tx_bd_desc, 0);
-	SET_TX_BUFF_DESC_AMSDU_1(tx_bd_desc, 0);
 
-	SET_TX_BUFF_DESC_LEN_2(tx_bd_desc, 0);
-	SET_TX_BUFF_DESC_AMSDU_2(tx_bd_desc, 0);
-	SET_TX_BUFF_DESC_LEN_3(tx_bd_desc, 0);
-	SET_TX_BUFF_DESC_AMSDU_3(tx_bd_desc, 0);
 	/* Clear all status */
 	CLEAR_PCI_TX_DESC_CONTENT(desc, TX_DESC_SIZE);
 
@@ -643,14 +635,16 @@ void rtl92ee_pre_fill_tx_bd_desc(struct ieee80211_hw *hw,
 		SET_TX_BUFF_DESC_LEN_0(tx_bd_desc, desc_size);
 	}
 	SET_TX_BUFF_DESC_PSB(tx_bd_desc, psblen);
-	SET_TX_BUFF_DESC_ADDR_LOW_0(tx_bd_desc,
-				    rtlpci->tx_ring[queue_index].dma +
-				    (current_bd_desc * TX_DESC_SIZE));
+	SET_TX_BUFF_DESC_ADDR_LOW_0(tx_bd_desc, desc_dma_addr);
+	SET_TX_BUFF_DESC_ADDR_HIGH_0(tx_bd_desc, ((u64)desc_dma_addr >> 32),
+				     dma64);
 
 	SET_TXBUFFER_DESC_LEN_WITH_OFFSET(tx_bd_desc, 1, pkt_len);
 	/* don't using extendsion mode. */
 	SET_TXBUFFER_DESC_AMSDU_WITH_OFFSET(tx_bd_desc, 1, 0);
 	SET_TXBUFFER_DESC_ADD_LOW_WITH_OFFSET(tx_bd_desc, 1, addr);
+	SET_TXBUFFER_DESC_ADD_HIGH_WITH_OFFSET(tx_bd_desc, 1,
+					       ((u64)addr >> 32), dma64);
 
 	SET_TX_DESC_PKT_SIZE(desc, (u16)(pkt_len));
 	SET_TX_DESC_TX_BUFFER_SIZE(desc, (u16)(pkt_len));
@@ -918,6 +912,7 @@ void rtl92ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
 	static bool over_run;
 	u32 tmp = 0;
 	u8 q_idx = *val;
+	bool dma64 = rtlpriv->cfg->mod_params->dma64;
 
 	if (istx) {
 		switch (desc_name) {
@@ -982,7 +977,12 @@ void rtl92ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
 						       MAX_RECEIVE_BUFFER_SIZE +
 						       RX_DESC_SIZE);
 
-			SET_RX_BUFFER_PHYSICAL_LOW(pdesc, *(u32 *)val);
+			SET_RX_BUFFER_PHYSICAL_LOW(pdesc, (*(dma_addr_t *)val) &
+						   DMA_BIT_MASK(32));
+			SET_RX_BUFFER_PHYSICAL_HIGH(pdesc,
+						    ((u64)(*(dma_addr_t *)val)
+						    >> 32),
+						    dma64);
 			break;
 		case HW_DESC_RXERO:
 			SET_RX_DESC_EOR(pdesc, 1);
@@ -996,9 +996,12 @@ void rtl92ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
 	}
 }
 
-u32 rtl92ee_get_desc(u8 *pdesc, bool istx, u8 desc_name)
+u64 rtl92ee_get_desc(struct ieee80211_hw *hw,
+		     u8 *pdesc, bool istx, u8 desc_name)
 {
-	u32 ret = 0;
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	u64 ret = 0;
+	bool dma64 = rtlpriv->cfg->mod_params->dma64;
 
 	if (istx) {
 		switch (desc_name) {
@@ -1007,6 +1010,8 @@ u32 rtl92ee_get_desc(u8 *pdesc, bool istx, u8 desc_name)
 			break;
 		case HW_DESC_TXBUFF_ADDR:
 			ret = GET_TXBUFFER_DESC_ADDR_LOW(pdesc, 1);
+			ret |= (u64)GET_TXBUFFER_DESC_ADDR_HIGH(pdesc, 1,
+								dma64) << 32;
 			break;
 		default:
 			WARN_ONCE(true,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.h
index b0105c529010..48c16fff20c6 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.h
@@ -26,24 +26,6 @@
 #ifndef __RTL92E_TRX_H__
 #define __RTL92E_TRX_H__
 
-#if (DMA_IS_64BIT == 1)
-#if (RTL8192EE_SEG_NUM == 2)
-#define TX_BD_DESC_SIZE					128
-#elif (RTL8192EE_SEG_NUM == 1)
-#define TX_BD_DESC_SIZE					64
-#elif (RTL8192EE_SEG_NUM == 0)
-#define TX_BD_DESC_SIZE					32
-#endif
-#else
-#if (RTL8192EE_SEG_NUM == 2)
-#define TX_BD_DESC_SIZE					64
-#elif (RTL8192EE_SEG_NUM == 1)
-#define TX_BD_DESC_SIZE					32
-#elif (RTL8192EE_SEG_NUM == 0)
-#define TX_BD_DESC_SIZE					16
-#endif
-#endif
-
 #define TX_DESC_SIZE					64
 
 #define RX_DRV_INFO_SIZE_UNIT				8
@@ -331,111 +313,34 @@
 	SET_BITS_TO_LE_4BYTE(__pdesc+(__set*16)+8, 0, 32, __val)
 
 /* for Txfilldescroptor92ee, fill the desc content. */
-#if (DMA_IS_64BIT == 1)
-#define SET_TXBUFFER_DESC_LEN_WITH_OFFSET(__pdesc, __offset, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*16), 0, 16, __val)
-#define SET_TXBUFFER_DESC_AMSDU_WITH_OFFSET(__pdesc, __offset, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*16), 31, 1, __val)
-#define SET_TXBUFFER_DESC_ADD_LOW_WITH_OFFSET(__pdesc, __offset, __val) \
-	SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*16)+4, 0, 32, __val)
-#define SET_TXBUFFER_DESC_ADD_HIGT_WITH_OFFSET(__pdesc, __offset, __val)\
-	SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*16)+8, 0, 32, __val)
-#define GET_TXBUFFER_DESC_ADDR_LOW(__pdesc, __offset)			\
-	LE_BITS_TO_4BYTE(__pdesc+(__offset*16)+4, 0, 32)
-#else
-#define SET_TXBUFFER_DESC_LEN_WITH_OFFSET(__pdesc, __offset, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*8), 0, 16, __val)
-#define SET_TXBUFFER_DESC_AMSDU_WITH_OFFSET(__pdesc, __offset, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*8), 31, 1, __val)
-#define SET_TXBUFFER_DESC_ADD_LOW_WITH_OFFSET(__pdesc, __offset, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*8)+4, 0, 32, __val)
-#define SET_TXBUFFER_DESC_ADD_HIGT_WITH_OFFSET(__pdesc, __offset, __val)
-#define GET_TXBUFFER_DESC_ADDR_LOW(__pdesc, __offset)			\
-	LE_BITS_TO_4BYTE(__pdesc+(__offset*8)+4, 0, 32)
-#endif
+#define SET_TXBUFFER_DESC_LEN_WITH_OFFSET(__pdesc, __offset, __val)            \
+	SET_BITS_TO_LE_4BYTE((__pdesc) + ((__offset) * 16), 0, 16, __val)
+#define SET_TXBUFFER_DESC_AMSDU_WITH_OFFSET(__pdesc, __offset, __val)          \
+	SET_BITS_TO_LE_4BYTE((__pdesc) + ((__offset) * 16), 31, 1, __val)
+#define SET_TXBUFFER_DESC_ADD_LOW_WITH_OFFSET(__pdesc, __offset, __val)        \
+	SET_BITS_TO_LE_4BYTE((__pdesc) + ((__offset) * 16) + 4, 0, 32, __val)
+#define SET_TXBUFFER_DESC_ADD_HIGH_WITH_OFFSET(pbd, off, val, dma64)	       \
+	(dma64 ? SET_BITS_TO_LE_4BYTE((pbd) + ((off) * 16) + 8, 0, 32, val) : 0)
+#define GET_TXBUFFER_DESC_ADDR_LOW(__pdesc, __offset)                          \
+	LE_BITS_TO_4BYTE((__pdesc) + ((__offset) * 16) + 4, 0, 32)
+#define GET_TXBUFFER_DESC_ADDR_HIGH(pbd, off, dma64)			       \
+	(dma64 ? LE_BITS_TO_4BYTE((pbd) + ((off) * 16) + 8, 0, 32) : 0)
 
 /* Dword 0 */
-#define SET_TX_BUFF_DESC_LEN_0(__pdesc, __val)		\
+#define SET_TX_BUFF_DESC_LEN_0(__pdesc, __val)                                 \
 	SET_BITS_TO_LE_4BYTE(__pdesc, 0, 14, __val)
-#define SET_TX_BUFF_DESC_PSB(__pdesc, __val)		\
+#define SET_TX_BUFF_DESC_PSB(__pdesc, __val)                                   \
 	SET_BITS_TO_LE_4BYTE(__pdesc, 16, 15, __val)
-#define SET_TX_BUFF_DESC_OWN(__pdesc, __val)		\
+#define SET_TX_BUFF_DESC_OWN(__pdesc, __val)                                   \
 	SET_BITS_TO_LE_4BYTE(__pdesc, 31, 1, __val)
 
 /* Dword 1 */
-#define SET_TX_BUFF_DESC_ADDR_LOW_0(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+4, 0, 32, __val)
-#if (DMA_IS_64BIT == 1)
+#define SET_TX_BUFF_DESC_ADDR_LOW_0(__pdesc, __val)                            \
+	SET_BITS_TO_LE_4BYTE((__pdesc) + 4, 0, 32, __val)
 /* Dword 2 */
-#define SET_TX_BUFF_DESC_ADDR_HIGH_0(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+8, 0, 32, __val)
+#define SET_TX_BUFF_DESC_ADDR_HIGH_0(bdesc, val, dma64)			       \
+	SET_TXBUFFER_DESC_ADD_HIGH_WITH_OFFSET(bdesc, 0, val, dma64)
 /* Dword 3 / RESERVED 0 */
-/* Dword 4 */
-#define SET_TX_BUFF_DESC_LEN_1(__pdesc, __val)		\
-	SET_BITS_TO_LE_4BYTE(__pdesc+16, 0, 16, __val)
-#define SET_TX_BUFF_DESC_AMSDU_1(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+16, 31, 1, __val)
-/* Dword 5 */
-#define SET_TX_BUFF_DESC_ADDR_LOW_1(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+20, 0, 32, __val)
-/* Dword 6 */
-#define SET_TX_BUFF_DESC_ADDR_HIGH_1(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+24, 0, 32, __val)
-/* Dword 7 / RESERVED 0 */
-/* Dword 8 */
-#define SET_TX_BUFF_DESC_LEN_2(__pdesc, __val)		\
-	SET_BITS_TO_LE_4BYTE(__pdesc+32, 0, 16, __val)
-#define SET_TX_BUFF_DESC_AMSDU_2(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+32, 31, 1, __val)
-/* Dword 9 */
-#define SET_TX_BUFF_DESC_ADDR_LOW_2(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+36, 0, 32, __val)
-/* Dword 10 */
-#define SET_TX_BUFF_DESC_ADDR_HIGH_2(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+40, 0, 32, __val)
-/* Dword 11 / RESERVED 0 */
-/* Dword 12 */
-#define SET_TX_BUFF_DESC_LEN_3(__pdesc, __val)		\
-	SET_BITS_TO_LE_4BYTE(__pdesc+48, 0, 16, __val)
-#define SET_TX_BUFF_DESC_AMSDU_3(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+48, 31, 1, __val)
-/* Dword 13 */
-#define SET_TX_BUFF_DESC_ADDR_LOW_3(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+52, 0, 32, __val)
-/* Dword 14 */
-#define SET_TX_BUFF_DESC_ADDR_HIGH_3(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+56, 0, 32, __val)
-/* Dword 15 / RESERVED 0 */
-#else
-#define SET_TX_BUFF_DESC_ADDR_HIGH_0(__pdesc, __val)
-/* Dword 2 */
-#define SET_TX_BUFF_DESC_LEN_1(__pdesc, __val)		\
-	SET_BITS_TO_LE_4BYTE(__pdesc+8, 0, 16, __val)
-#define SET_TX_BUFF_DESC_AMSDU_1(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+8, 31, 1, __val)
-/* Dword 3 */
-#define SET_TX_BUFF_DESC_ADDR_LOW_1(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+12, 0, 32, __val)
-#define SET_TX_BUFF_DESC_ADDR_HIGH_1(__pdesc, __val)
-/* Dword 4 */
-#define SET_TX_BUFF_DESC_LEN_2(__pdesc, __val)		\
-	SET_BITS_TO_LE_4BYTE(__pdesc+16, 0, 16, __val)
-#define SET_TX_BUFF_DESC_AMSDU_2(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+16, 31, 1, __val)
-/* Dword 5 */
-#define SET_TX_BUFF_DESC_ADDR_LOW_2(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+20, 0, 32, __val)
-#define SET_TX_BUFF_DESC_ADDR_HIGH_2(__pdesc, __val)
-/* Dword 6 */
-#define SET_TX_BUFF_DESC_LEN_3(__pdesc, __val)		\
-	SET_BITS_TO_LE_4BYTE(__pdesc+24, 0, 16, __val)
-#define SET_TX_BUFF_DESC_AMSDU_3(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+24, 31, 1, __val)
-/* Dword 7 */
-#define SET_TX_BUFF_DESC_ADDR_LOW_3(__pdesc, __val)	\
-	SET_BITS_TO_LE_4BYTE(__pdesc+28, 0, 32, __val)
-#define SET_TX_BUFF_DESC_ADDR_HIGH_3(__pdesc, __val)
-#endif
 
 /* RX buffer  */
 
@@ -463,8 +368,8 @@
 	SET_BITS_TO_LE_4BYTE(__status+4, 0, 32, __val)
 
 /* DWORD 2 */
-#define SET_RX_BUFFER_PHYSICAL_HIGH(__status, __val)	\
-	SET_BITS_TO_LE_4BYTE(__status+8, 0, 32, __val)
+#define SET_RX_BUFFER_PHYSICAL_HIGH(__rx_status_desc, __val, dma64)            \
+	(dma64 ? SET_BITS_TO_LE_4BYTE((__rx_status_desc) + 8, 0, 32, __val) : 0)
 
 #define GET_RX_DESC_PKT_LEN(__pdesc)			\
 	LE_BITS_TO_4BYTE(__pdesc, 0, 14)
@@ -850,7 +755,8 @@ bool rtl92ee_rx_query_desc(struct ieee80211_hw *hw,
 void rtl92ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
 		      u8 desc_name, u8 *val);
 
-u32 rtl92ee_get_desc(u8 *pdesc, bool istx, u8 desc_name);
+u64 rtl92ee_get_desc(struct ieee80211_hw *hw,
+		     u8 *pdesc, bool istx, u8 desc_name);
 bool rtl92ee_is_tx_desc_closed(struct ieee80211_hw *hw, u8 hw_queue, u16 index);
 void rtl92ee_tx_polling(struct ieee80211_hw *hw, u8 hw_queue);
 void rtl92ee_tx_fill_cmddesc(struct ieee80211_hw *hw, u8 *pdesc,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/dm.c
index 2c073a77b194..44f510a94b09 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/dm.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/dm.c
@@ -295,7 +295,8 @@ static void _rtl92s_dm_refresh_rateadaptive_mask(struct ieee80211_hw *hw)
 			sta = rtl_find_sta(hw, mac->bssid);
 			if (sta)
 				rtlpriv->cfg->ops->update_rate_tbl(hw, sta,
-							   ra->ratr_state);
+							   ra->ratr_state,
+							   true);
 			rcu_read_unlock();
 
 			ra->pre_ratr_state = ra->ratr_state;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.c
index ba1bd782238b..66be79ca4247 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.c
@@ -2129,7 +2129,7 @@ static void rtl92se_update_hal_rate_table(struct ieee80211_hw *hw,
 
 static void rtl92se_update_hal_rate_mask(struct ieee80211_hw *hw,
 					 struct ieee80211_sta *sta,
-					 u8 rssi_level)
+					 u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_phy *rtlphy = &(rtlpriv->phy);
@@ -2288,12 +2288,12 @@ static void rtl92se_update_hal_rate_mask(struct ieee80211_hw *hw,
 }
 
 void rtl92se_update_hal_rate_tbl(struct ieee80211_hw *hw,
-		struct ieee80211_sta *sta, u8 rssi_level)
+		struct ieee80211_sta *sta, u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	if (rtlpriv->dm.useramask)
-		rtl92se_update_hal_rate_mask(hw, sta, rssi_level);
+		rtl92se_update_hal_rate_mask(hw, sta, rssi_level, update_bw);
 	else
 		rtl92se_update_hal_rate_table(hw, sta);
 }
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.h
index 86bce1be83ce..3c93d30fcae7 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.h
@@ -59,7 +59,7 @@ void rtl92se_update_interrupt_mask(struct ieee80211_hw *hw,
 void rtl92se_set_hw_reg(struct ieee80211_hw *hw, u8 variable,
 			u8 *val);
 void rtl92se_update_hal_rate_tbl(struct ieee80211_hw *hw,
-		struct ieee80211_sta *sta, u8 rssi_level);
+		struct ieee80211_sta *sta, u8 rssi_level, bool update_bw);
 void rtl92se_update_channel_access_setting(struct ieee80211_hw *hw);
 bool rtl92se_gpio_radio_on_off_checking(struct ieee80211_hw *hw,
 					u8 *valid);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
index d7945b9db493..d55554b7fa9a 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
@@ -41,6 +41,7 @@
 
 static void rtl92s_init_aspm_vars(struct ieee80211_hw *hw)
 {
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
 	/*close ASPM for AMD defaultly */
@@ -77,7 +78,7 @@ static void rtl92s_init_aspm_vars(struct ieee80211_hw *hw)
 	 * 1 - Support ASPM,
 	 * 2 - According to chipset.
 	 */
-	rtlpci->const_support_pciaspm = 2;
+	rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support;
 }
 
 static void rtl92se_fw_cb(const struct firmware *firmware, void *context)
@@ -240,7 +241,7 @@ static bool rtl92se_is_tx_desc_closed(struct ieee80211_hw *hw, u8 hw_queue,
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue];
 	u8 *entry = (u8 *)(&ring->desc[ring->idx]);
-	u8 own = (u8)rtl92se_get_desc(entry, true, HW_DESC_OWN);
+	u8 own = (u8)rtl92se_get_desc(hw, entry, true, HW_DESC_OWN);
 
 	if (own)
 		return false;
@@ -297,6 +298,7 @@ static struct rtl_mod_params rtl92se_mod_params = {
 	.inactiveps = true,
 	.swctrl_lps = true,
 	.fwctrl_lps = false,
+	.aspm_support = 2,
 	.debug_level = 0,
 	.debug_mask = 0,
 };
@@ -422,10 +424,12 @@ module_param_named(debug_mask, rtl92se_mod_params.debug_mask, ullong, 0644);
 module_param_named(ips, rtl92se_mod_params.inactiveps, bool, 0444);
 module_param_named(swlps, rtl92se_mod_params.swctrl_lps, bool, 0444);
 module_param_named(fwlps, rtl92se_mod_params.fwctrl_lps, bool, 0444);
+module_param_named(aspm, rtl92se_mod_params.aspm_support, int, 0444);
 MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n");
 MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n");
 MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 1)\n");
 MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 0)\n");
+MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n");
 MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)");
 MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)");
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c
index a01dbd31d1b4..e1904c39f147 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c
@@ -610,7 +610,8 @@ void rtl92se_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
 	}
 }
 
-u32 rtl92se_get_desc(u8 *desc, bool istx, u8 desc_name)
+u64 rtl92se_get_desc(struct ieee80211_hw *hw,
+		     u8 *desc, bool istx, u8 desc_name)
 {
 	u32 ret = 0;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.h
index 728589138072..81a5445c04a3 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.h
@@ -38,7 +38,8 @@ bool rtl92se_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats,
 			   struct sk_buff *skb);
 void rtl92se_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
 		      u8 desc_name, u8 *val);
-u32 rtl92se_get_desc(u8 *pdesc, bool istx, u8 desc_name);
+u64 rtl92se_get_desc(struct ieee80211_hw *hw,
+		     u8 *desc, bool istx, u8 desc_name);
 void rtl92se_tx_polling(struct ieee80211_hw *hw, u8 hw_queue);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c
index 5ac7b815648a..8cfd4993c90a 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c
@@ -1943,7 +1943,7 @@ static void rtl8723e_update_hal_rate_table(struct ieee80211_hw *hw,
 
 static void rtl8723e_update_hal_rate_mask(struct ieee80211_hw *hw,
 					  struct ieee80211_sta *sta,
-					  u8 rssi_level)
+					  u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_phy *rtlphy = &(rtlpriv->phy);
@@ -2074,12 +2074,13 @@ static void rtl8723e_update_hal_rate_mask(struct ieee80211_hw *hw,
 }
 
 void rtl8723e_update_hal_rate_tbl(struct ieee80211_hw *hw,
-				  struct ieee80211_sta *sta, u8 rssi_level)
+				  struct ieee80211_sta *sta, u8 rssi_level,
+				  bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	if (rtlpriv->dm.useramask)
-		rtl8723e_update_hal_rate_mask(hw, sta, rssi_level);
+		rtl8723e_update_hal_rate_mask(hw, sta, rssi_level, update_bw);
 	else
 		rtl8723e_update_hal_rate_table(hw, sta);
 }
@@ -2103,7 +2104,7 @@ bool rtl8723e_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	struct rtl_phy *rtlphy = &(rtlpriv->phy);
-	enum rf_pwrstate e_rfpowerstate_toset, cur_rfstate;
+	enum rf_pwrstate e_rfpowerstate_toset;
 	u8 u1tmp;
 	bool b_actuallyset = false;
 
@@ -2122,8 +2123,6 @@ bool rtl8723e_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid)
 		spin_unlock(&rtlpriv->locks.rf_ps_lock);
 	}
 
-	cur_rfstate = ppsc->rfpwr_state;
-
 	rtl_write_byte(rtlpriv, REG_GPIO_IO_SEL_2,
 		       rtl_read_byte(rtlpriv, REG_GPIO_IO_SEL_2)&~(BIT(1)));
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.h
index 32c1ace97c3f..1e7063105c96 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.h
@@ -49,7 +49,8 @@ void rtl8723e_update_interrupt_mask(struct ieee80211_hw *hw,
 				    u32 add_msr, u32 rm_msr);
 void rtl8723e_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val);
 void rtl8723e_update_hal_rate_tbl(struct ieee80211_hw *hw,
-				  struct ieee80211_sta *sta, u8 rssi_level);
+				  struct ieee80211_sta *sta, u8 rssi_level,
+				  bool update_bw);
 void rtl8723e_update_channel_access_setting(struct ieee80211_hw *hw);
 bool rtl8723e_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid);
 void rtl8723e_enable_hw_security_config(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c
index 97b8bd294aa8..a545ea317323 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c
@@ -46,6 +46,7 @@
 
 static void rtl8723e_init_aspm_vars(struct ieee80211_hw *hw)
 {
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
 	/*close ASPM for AMD defaultly */
@@ -85,7 +86,7 @@ static void rtl8723e_init_aspm_vars(struct ieee80211_hw *hw)
 	 * 1 - Support ASPM,
 	 * 2 - According to chipset.
 	 */
-	rtlpci->const_support_pciaspm = 1;
+	rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support;
 }
 
 int rtl8723e_init_sw_vars(struct ieee80211_hw *hw)
@@ -268,6 +269,7 @@ static struct rtl_mod_params rtl8723e_mod_params = {
 	.inactiveps = true,
 	.swctrl_lps = false,
 	.fwctrl_lps = true,
+	.aspm_support = 1,
 	.debug_level = 0,
 	.debug_mask = 0,
 	.msi_support = false,
@@ -389,6 +391,7 @@ module_param_named(ips, rtl8723e_mod_params.inactiveps, bool, 0444);
 module_param_named(swlps, rtl8723e_mod_params.swctrl_lps, bool, 0444);
 module_param_named(fwlps, rtl8723e_mod_params.fwctrl_lps, bool, 0444);
 module_param_named(msi, rtl8723e_mod_params.msi_support, bool, 0444);
+module_param_named(aspm, rtl8723e_mod_params.aspm_support, int, 0444);
 module_param_named(disable_watchdog, rtl8723e_mod_params.disable_watchdog,
 		   bool, 0444);
 MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n");
@@ -396,6 +399,7 @@ MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n");
 MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n");
 MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n");
 MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 0)\n");
+MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n");
 MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)");
 MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)");
 MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n");
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c
index f713c7249fed..23485602a9a1 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c
@@ -643,7 +643,8 @@ void rtl8723e_set_desc(struct ieee80211_hw *hw, u8 *pdesc,
 	}
 }
 
-u32 rtl8723e_get_desc(u8 *pdesc, bool istx, u8 desc_name)
+u64 rtl8723e_get_desc(struct ieee80211_hw *hw,
+		      u8 *pdesc, bool istx, u8 desc_name)
 {
 	u32 ret = 0;
 
@@ -686,7 +687,7 @@ bool rtl8723e_is_tx_desc_closed(struct ieee80211_hw *hw,
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue];
 	u8 *entry = (u8 *)(&ring->desc[ring->idx]);
-	u8 own = (u8)rtl8723e_get_desc(entry, true, HW_DESC_OWN);
+	u8 own = (u8)rtl8723e_get_desc(hw, entry, true, HW_DESC_OWN);
 
 	/**
 	 *beacon packet will only use the first
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.h
index 43d4c791d563..985ce0b77ea5 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.h
@@ -708,7 +708,8 @@ bool rtl8723e_rx_query_desc(struct ieee80211_hw *hw,
 			    u8 *pdesc, struct sk_buff *skb);
 void rtl8723e_set_desc(struct ieee80211_hw *hw,
 		       u8 *pdesc, bool istx, u8 desc_name, u8 *val);
-u32 rtl8723e_get_desc(u8 *pdesc, bool istx, u8 desc_name);
+u64 rtl8723e_get_desc(struct ieee80211_hw *hw,
+		      u8 *pdesc, bool istx, u8 desc_name);
 bool rtl8723e_is_tx_desc_closed(struct ieee80211_hw *hw,
 				u8 hw_queue, u16 index);
 void rtl8723e_tx_polling(struct ieee80211_hw *hw, u8 hw_queue);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/dm.c
index 15c117e95a99..47e87a21ae27 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/dm.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/dm.c
@@ -984,7 +984,8 @@ static void rtl8723be_dm_refresh_rate_adaptive_mask(struct ieee80211_hw *hw)
 			sta = rtl_find_sta(hw, mac->bssid);
 			if (sta)
 				rtlpriv->cfg->ops->update_rate_tbl(hw, sta,
-							   p_ra->ratr_state);
+							   p_ra->ratr_state,
+							   true);
 			rcu_read_unlock();
 
 			p_ra->pre_ratr_state = p_ra->ratr_state;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
index 4d47b97adfed..239518bd31f1 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
@@ -60,6 +60,7 @@ static void _rtl8723be_return_beacon_queue_skb(struct ieee80211_hw *hw)
 
 		pci_unmap_single(rtlpci->pdev,
 				 rtlpriv->cfg->ops->get_desc(
+				 hw,
 				 (u8 *)entry, true, HW_DESC_TXBUFF_ADDR),
 				 skb->len, PCI_DMA_TODEVICE);
 		kfree_skb(skb);
@@ -2324,7 +2325,7 @@ static u8 _rtl8723be_mrate_idx_to_arfr_id(struct ieee80211_hw *hw,
 
 static void rtl8723be_update_hal_rate_mask(struct ieee80211_hw *hw,
 					   struct ieee80211_sta *sta,
-					   u8 rssi_level)
+					   u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_phy *rtlphy = &(rtlpriv->phy);
@@ -2440,7 +2441,7 @@ static void rtl8723be_update_hal_rate_mask(struct ieee80211_hw *hw,
 	rate_mask[0] = macid;
 	rate_mask[1] = _rtl8723be_mrate_idx_to_arfr_id(hw, ratr_index) |
 						      (shortgi ? 0x80 : 0x00);
-	rate_mask[2] = curtxbw_40mhz;
+	rate_mask[2] = curtxbw_40mhz | ((!update_bw) << 3);
 
 	rate_mask[3] = (u8)(ratr_bitmap & 0x000000ff);
 	rate_mask[4] = (u8)((ratr_bitmap & 0x0000ff00) >> 8);
@@ -2460,11 +2461,11 @@ static void rtl8723be_update_hal_rate_mask(struct ieee80211_hw *hw,
 
 void rtl8723be_update_hal_rate_tbl(struct ieee80211_hw *hw,
 				   struct ieee80211_sta *sta,
-				   u8 rssi_level)
+				   u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	if (rtlpriv->dm.useramask)
-		rtl8723be_update_hal_rate_mask(hw, sta, rssi_level);
+		rtl8723be_update_hal_rate_mask(hw, sta, rssi_level, update_bw);
 }
 
 void rtl8723be_update_channel_access_setting(struct ieee80211_hw *hw)
@@ -2486,7 +2487,7 @@ bool rtl8723be_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	struct rtl_phy *rtlphy = &(rtlpriv->phy);
-	enum rf_pwrstate e_rfpowerstate_toset, cur_rfstate;
+	enum rf_pwrstate e_rfpowerstate_toset;
 	u8 u1tmp;
 	bool b_actuallyset = false;
 
@@ -2505,8 +2506,6 @@ bool rtl8723be_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid)
 		spin_unlock(&rtlpriv->locks.rf_ps_lock);
 	}
 
-	cur_rfstate = ppsc->rfpwr_state;
-
 	rtl_write_byte(rtlpriv, REG_GPIO_IO_SEL_2,
 		       rtl_read_byte(rtlpriv, REG_GPIO_IO_SEL_2) & ~(BIT(1)));
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.h
index eae863d08de8..54d7afa7297e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.h
@@ -46,7 +46,7 @@ void rtl8723be_update_interrupt_mask(struct ieee80211_hw *hw,
 void rtl8723be_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val);
 void rtl8723be_update_hal_rate_tbl(struct ieee80211_hw *hw,
 				   struct ieee80211_sta *sta,
-				   u8 rssi_level);
+				   u8 rssi_level, bool update_bw);
 void rtl8723be_update_channel_access_setting(struct ieee80211_hw *hw);
 bool rtl8723be_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid);
 void rtl8723be_enable_hw_security_config(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
index 2b16a1467e78..6a42988aad65 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
@@ -46,6 +46,7 @@
 
 static void rtl8723be_init_aspm_vars(struct ieee80211_hw *hw)
 {
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
 	/*close ASPM for AMD defaultly */
@@ -82,7 +83,7 @@ static void rtl8723be_init_aspm_vars(struct ieee80211_hw *hw)
 	 * 1 - Support ASPM,
 	 * 2 - According to chipset.
 	 */
-	rtlpci->const_support_pciaspm = 1;
+	rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support;
 }
 
 int rtl8723be_init_sw_vars(struct ieee80211_hw *hw)
@@ -271,6 +272,7 @@ static struct rtl_mod_params rtl8723be_mod_params = {
 	.swctrl_lps = false,
 	.fwctrl_lps = true,
 	.msi_support = false,
+	.aspm_support = 1,
 	.disable_watchdog = false,
 	.debug_level = 0,
 	.debug_mask = 0,
@@ -396,6 +398,7 @@ module_param_named(ips, rtl8723be_mod_params.inactiveps, bool, 0444);
 module_param_named(swlps, rtl8723be_mod_params.swctrl_lps, bool, 0444);
 module_param_named(fwlps, rtl8723be_mod_params.fwctrl_lps, bool, 0444);
 module_param_named(msi, rtl8723be_mod_params.msi_support, bool, 0444);
+module_param_named(aspm, rtl8723be_mod_params.aspm_support, int, 0444);
 module_param_named(disable_watchdog, rtl8723be_mod_params.disable_watchdog,
 		   bool, 0444);
 module_param_named(ant_sel, rtl8723be_mod_params.ant_sel, int, 0444);
@@ -404,6 +407,7 @@ MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n");
 MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n");
 MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n");
 MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 0)\n");
+MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n");
 MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)");
 MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)");
 MODULE_PARM_DESC(disable_watchdog,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.c
index 0e8944119652..fd9b38aa08a1 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.c
@@ -695,7 +695,8 @@ void rtl8723be_set_desc(struct ieee80211_hw *hw, u8 *pdesc,
 	}
 }
 
-u32 rtl8723be_get_desc(u8 *pdesc, bool istx, u8 desc_name)
+u64 rtl8723be_get_desc(struct ieee80211_hw *hw,
+		       u8 *pdesc, bool istx, u8 desc_name)
 {
 	u32 ret = 0;
 
@@ -738,7 +739,7 @@ bool rtl8723be_is_tx_desc_closed(struct ieee80211_hw *hw,
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue];
 	u8 *entry = (u8 *)(&ring->desc[ring->idx]);
-	u8 own = (u8)rtl8723be_get_desc(entry, true, HW_DESC_OWN);
+	u8 own = (u8)rtl8723be_get_desc(hw, entry, true, HW_DESC_OWN);
 
 	/*beacon packet will only use the first
 	 *descriptor defautly,and the own may not
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.h
index 0274659f48ed..988bf0586674 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.h
@@ -624,7 +624,8 @@ bool rtl8723be_rx_query_desc(struct ieee80211_hw *hw,
 			     u8 *pdesc, struct sk_buff *skb);
 void rtl8723be_set_desc(struct ieee80211_hw *hw, u8 *pdesc,
 			bool istx, u8 desc_name, u8 *val);
-u32 rtl8723be_get_desc(u8 *pdesc, bool istx, u8 desc_name);
+u64 rtl8723be_get_desc(struct ieee80211_hw *hw,
+		       u8 *pdesc, bool istx, u8 desc_name);
 bool rtl8723be_is_tx_desc_closed(struct ieee80211_hw *hw,
 				 u8 hw_queue, u16 index);
 void rtl8723be_tx_polling(struct ieee80211_hw *hw, u8 hw_queue);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.c
index ac573d69f6d6..efa7e1262461 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.c
@@ -253,7 +253,8 @@ bool rtl8723_cmd_send_packet(struct ieee80211_hw *hw,
 	spin_lock_irqsave(&rtlpriv->locks.irq_th_lock, flags);
 
 	pdesc = &ring->desc[0];
-	own = (u8) rtlpriv->cfg->ops->get_desc((u8 *)pdesc, true, HW_DESC_OWN);
+	own = (u8)rtlpriv->cfg->ops->get_desc(hw, (u8 *)pdesc, true,
+					      HW_DESC_OWN);
 
 	rtlpriv->cfg->ops->fill_tx_cmddesc(hw, (u8 *)pdesc, 1, 1, skb);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c
index 32900c51f024..b11365a5ee1f 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c
@@ -2592,7 +2592,7 @@ static void rtl8821ae_dm_refresh_rate_adaptive_mask(struct ieee80211_hw *hw)
 			sta = rtl_find_sta(hw, mac->bssid);
 			if (sta)
 				rtlpriv->cfg->ops->update_rate_tbl(hw,
-						sta, p_ra->ratr_state);
+						sta, p_ra->ratr_state, true);
 			rcu_read_unlock();
 
 			p_ra->pre_ratr_state = p_ra->ratr_state;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
index 1d431d4bf6d2..6408bc8456f3 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
@@ -57,6 +57,7 @@ static void _rtl8821ae_return_beacon_queue_skb(struct ieee80211_hw *hw)
 
 		pci_unmap_single(rtlpci->pdev,
 				 rtlpriv->cfg->ops->get_desc(
+				 hw,
 				 (u8 *)entry, true, HW_DESC_TXBUFF_ADDR),
 				 skb->len, PCI_DMA_TODEVICE);
 		kfree_skb(skb);
@@ -3598,7 +3599,7 @@ static bool _rtl8821ae_get_ra_shortgi(struct ieee80211_hw *hw, struct ieee80211_
 }
 
 static void rtl8821ae_update_hal_rate_mask(struct ieee80211_hw *hw,
-		struct ieee80211_sta *sta, u8 rssi_level)
+		struct ieee80211_sta *sta, u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_phy *rtlphy = &rtlpriv->phy;
@@ -3777,7 +3778,7 @@ static void rtl8821ae_update_hal_rate_mask(struct ieee80211_hw *hw,
 
 	rate_mask[0] = macid;
 	rate_mask[1] = ratr_index | (b_shortgi ? 0x80 : 0x00);
-	rate_mask[2] = rtlphy->current_chan_bw
+	rate_mask[2] = rtlphy->current_chan_bw | ((!update_bw) << 3)
 			   | _rtl8821ae_get_vht_eni(wirelessmode, ratr_bitmap)
 			   | _rtl8821ae_get_ra_ldpc(hw, macid, sta_entry, wirelessmode);
 
@@ -3798,11 +3799,11 @@ static void rtl8821ae_update_hal_rate_mask(struct ieee80211_hw *hw,
 }
 
 void rtl8821ae_update_hal_rate_tbl(struct ieee80211_hw *hw,
-		struct ieee80211_sta *sta, u8 rssi_level)
+		struct ieee80211_sta *sta, u8 rssi_level, bool update_bw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	if (rtlpriv->dm.useramask)
-		rtl8821ae_update_hal_rate_mask(hw, sta, rssi_level);
+		rtl8821ae_update_hal_rate_mask(hw, sta, rssi_level, update_bw);
 	else
 		/*RT_TRACE(rtlpriv, COMP_RATR,DBG_LOUD,
 			   "rtl8821ae_update_hal_rate_tbl() Error! 8821ae FW RA Only\n");*/
@@ -3845,7 +3846,7 @@ bool rtl8821ae_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	struct rtl_phy *rtlphy = &rtlpriv->phy;
-	enum rf_pwrstate e_rfpowerstate_toset, cur_rfstate;
+	enum rf_pwrstate e_rfpowerstate_toset;
 	u8 u1tmp = 0;
 	bool b_actuallyset = false;
 
@@ -3864,8 +3865,6 @@ bool rtl8821ae_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid)
 		spin_unlock(&rtlpriv->locks.rf_ps_lock);
 	}
 
-	cur_rfstate = ppsc->rfpwr_state;
-
 	rtl_write_byte(rtlpriv, REG_GPIO_IO_SEL_2,
 			rtl_read_byte(rtlpriv,
 					REG_GPIO_IO_SEL_2) & ~(BIT(1)));
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.h
index a3553e3abaa1..50fa9c718189 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.h
@@ -46,7 +46,7 @@ void rtl8821ae_update_interrupt_mask(struct ieee80211_hw *hw,
 void rtl8821ae_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val);
 void rtl8821ae_update_hal_rate_tbl(struct ieee80211_hw *hw,
 				   struct ieee80211_sta *sta,
-				   u8 rssi_level);
+				   u8 rssi_level, bool update_bw);
 void rtl8821ae_update_channel_access_setting(struct ieee80211_hw *hw);
 bool rtl8821ae_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid);
 void rtl8821ae_enable_hw_security_config(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
index 0894ef48ab87..ab5d462b1a3a 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
@@ -43,6 +43,7 @@
 
 static void rtl8821ae_init_aspm_vars(struct ieee80211_hw *hw)
 {
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
 	/*close ASPM for AMD defaultly */
@@ -82,7 +83,7 @@ static void rtl8821ae_init_aspm_vars(struct ieee80211_hw *hw)
 	 * 1 - Support ASPM,
 	 * 2 - According to chipset.
 	 */
-	rtlpci->const_support_pciaspm = 1;
+	rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support;
 }
 
 /*InitializeVariables8812E*/
@@ -313,6 +314,7 @@ static struct rtl_mod_params rtl8821ae_mod_params = {
 	.swctrl_lps = false,
 	.fwctrl_lps = true,
 	.msi_support = true,
+	.aspm_support = 1,
 	.int_clear = true,
 	.debug_level = 0,
 	.debug_mask = 0,
@@ -444,6 +446,7 @@ module_param_named(ips, rtl8821ae_mod_params.inactiveps, bool, 0444);
 module_param_named(swlps, rtl8821ae_mod_params.swctrl_lps, bool, 0444);
 module_param_named(fwlps, rtl8821ae_mod_params.fwctrl_lps, bool, 0444);
 module_param_named(msi, rtl8821ae_mod_params.msi_support, bool, 0444);
+module_param_named(aspm, rtl8821ae_mod_params.aspm_support, int, 0444);
 module_param_named(disable_watchdog, rtl8821ae_mod_params.disable_watchdog,
 		   bool, 0444);
 module_param_named(int_clear, rtl8821ae_mod_params.int_clear, bool, 0444);
@@ -452,6 +455,7 @@ MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n");
 MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n");
 MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n");
 MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 1)\n");
+MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n");
 MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)");
 MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)");
 MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n");
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c
index 749818929e8f..1e1bacf562f3 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c
@@ -935,7 +935,8 @@ void rtl8821ae_set_desc(struct ieee80211_hw *hw, u8 *pdesc,
 	}
 }
 
-u32 rtl8821ae_get_desc(u8 *pdesc, bool istx, u8 desc_name)
+u64 rtl8821ae_get_desc(struct ieee80211_hw *hw,
+		       u8 *pdesc, bool istx, u8 desc_name)
 {
 	u32 ret = 0;
 
@@ -980,7 +981,7 @@ bool rtl8821ae_is_tx_desc_closed(struct ieee80211_hw *hw,
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue];
 	u8 *entry = (u8 *)(&ring->desc[ring->idx]);
-	u8 own = (u8)rtl8821ae_get_desc(entry, true, HW_DESC_OWN);
+	u8 own = (u8)rtl8821ae_get_desc(hw, entry, true, HW_DESC_OWN);
 
 	/**
 	 *beacon packet will only use the first
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h
index 9843a616dcec..221dd2b29d3b 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h
@@ -620,7 +620,8 @@ bool rtl8821ae_rx_query_desc(struct ieee80211_hw *hw,
 			     u8 *pdesc, struct sk_buff *skb);
 void rtl8821ae_set_desc(struct ieee80211_hw *hw, u8 *pdesc,
 			bool istx, u8 desc_name, u8 *val);
-u32 rtl8821ae_get_desc(u8 *pdesc, bool istx, u8 desc_name);
+u64 rtl8821ae_get_desc(struct ieee80211_hw *hw,
+		       u8 *pdesc, bool istx, u8 desc_name);
 bool rtl8821ae_is_tx_desc_closed(struct ieee80211_hw *hw,
 				 u8 hw_queue, u16 index);
 void rtl8821ae_tx_polling(struct ieee80211_hw *hw, u8 hw_queue);
diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h
index 1ab1024330fb..7dfc73b554f1 100644
--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h
+++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h
@@ -169,16 +169,14 @@ enum rtl8192c_h2c_cmd {
 #define MAX_BASE_NUM_IN_PHY_REG_PG_24G  6
 #define MAX_BASE_NUM_IN_PHY_REG_PG_5G	5
 
-#define RTL8192EE_SEG_NUM		1 /* 0:2 seg, 1: 4 seg, 2: 8 seg */
+#define BUFDESC_SEG_NUM		1 /* 0:2 seg, 1: 4 seg, 2: 8 seg */
 
 #define DEL_SW_IDX_SZ		30
-#define BAND_NUM			3
 
 /* For now, it's just for 8192ee
  * but not OK yet, keep it 0
  */
-#define DMA_IS_64BIT 0
-#define RTL8192EE_SEG_NUM		1 /* 0:2 seg, 1: 4 seg, 2: 8 seg */
+#define RTL8192EE_SEG_NUM		BUFDESC_SEG_NUM
 
 enum rf_tx_num {
 	RF_1TX = 0,
@@ -561,6 +559,11 @@ enum rf_type {
 	RF_1T2R = 1,
 	RF_2T2R = 2,
 	RF_2T2R_GREEN = 3,
+	RF_2T3R = 4,
+	RF_2T4R = 5,
+	RF_3T3R = 6,
+	RF_3T4R = 7,
+	RF_4T4R = 8,
 };
 
 enum ht_channel_width {
@@ -1014,10 +1017,17 @@ struct init_gain {
 };
 
 struct wireless_stats {
-	unsigned long txbytesunicast;
-	unsigned long txbytesmulticast;
-	unsigned long txbytesbroadcast;
-	unsigned long rxbytesunicast;
+	u64 txbytesunicast;
+	u64 txbytesmulticast;
+	u64 txbytesbroadcast;
+	u64 rxbytesunicast;
+
+	u64 txbytesunicast_inperiod;
+	u64 rxbytesunicast_inperiod;
+	u32 txbytesunicast_inperiod_tp;
+	u32 rxbytesunicast_inperiod_tp;
+	u64 txbytesunicast_last;
+	u64 rxbytesunicast_last;
 
 	long rx_snr_db[4];
 	/*Correct smoothed ss in Dbm, only used
@@ -1323,6 +1333,7 @@ struct rtl_sta_info {
 	struct rtl_tid_data tids[MAX_TID_COUNT];
 	/* just used for ap adhoc or mesh*/
 	struct rssi_sta rssi_stat;
+	u8 rssi_level;
 	u16 wireless_mode;
 	u8 ratr_index;
 	u8 mimo_ps;
@@ -1736,21 +1747,6 @@ struct rtl_dm {
 	s8	swing_diff_2g;
 	s8	swing_diff_5g;
 
-	u8 delta_swing_table_idx_24gccka_p[DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_24gccka_n[DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_24gcckb_p[DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_24gcckb_n[DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_24ga_p[DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_24ga_n[DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_24gb_p[DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_24gb_n[DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_5ga_p[BAND_NUM][DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_5ga_n[BAND_NUM][DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_5gb_p[BAND_NUM][DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_5gb_n[BAND_NUM][DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_24ga_p_8188e[DEL_SW_IDX_SZ];
-	u8 delta_swing_table_idx_24ga_n_8188e[DEL_SW_IDX_SZ];
-
 	/* DMSP */
 	bool supp_phymode_switch;
 
@@ -2127,7 +2123,8 @@ struct rtl_hal_ops {
 	void (*get_hw_reg) (struct ieee80211_hw *hw, u8 variable, u8 *val);
 	void (*set_hw_reg) (struct ieee80211_hw *hw, u8 variable, u8 *val);
 	void (*update_rate_tbl) (struct ieee80211_hw *hw,
-			      struct ieee80211_sta *sta, u8 rssi_level);
+			      struct ieee80211_sta *sta, u8 rssi_leve,
+			      bool update_bw);
 	void (*pre_fill_tx_bd_desc)(struct ieee80211_hw *hw, u8 *tx_bd_desc,
 				    u8 *desc, u8 queue_index,
 				    struct sk_buff *skb, dma_addr_t addr);
@@ -2162,7 +2159,8 @@ struct rtl_hal_ops {
 			     enum led_ctl_mode ledaction);
 	void (*set_desc)(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
 			 u8 desc_name, u8 *val);
-	u32 (*get_desc) (u8 *pdesc, bool istx, u8 desc_name);
+	u64 (*get_desc)(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
+			u8 desc_name);
 	bool (*is_tx_desc_closed) (struct ieee80211_hw *hw,
 				   u8 hw_queue, u16 index);
 	void (*tx_polling) (struct ieee80211_hw *hw, u8 hw_queue);
@@ -2261,6 +2259,12 @@ struct rtl_mod_params {
 	 */
 	bool msi_support;
 
+	/* default: 0 = dma 32 */
+	bool dma64;
+
+	/* default: 1 = enable aspm */
+	int aspm_support;
+
 	/* default 0: 1 means disable */
 	bool disable_watchdog;
 
@@ -2857,19 +2861,19 @@ value to host byte ordering.*/
 	cpu_to_le32( \
 		LE_BITS_CLEARED_TO_4BYTE(__pstart, __bitoffset, __bitlen) | \
 		((((u32)__val) & BIT_LEN_MASK_32(__bitlen)) << (__bitoffset)) \
-	);
+	)
 #define SET_BITS_TO_LE_2BYTE(__pstart, __bitoffset, __bitlen, __val) \
 	*((__le16 *)(__pstart)) = \
 	cpu_to_le16( \
 		LE_BITS_CLEARED_TO_2BYTE(__pstart, __bitoffset, __bitlen) | \
 		((((u16)__val) & BIT_LEN_MASK_16(__bitlen)) << (__bitoffset)) \
-	);
+	)
 #define SET_BITS_TO_LE_1BYTE(__pstart, __bitoffset, __bitlen, __val) \
 	*((u8 *)(__pstart)) = EF1BYTE \
 	( \
 		LE_BITS_CLEARED_TO_1BYTE(__pstart, __bitoffset, __bitlen) | \
 		((((u8)__val) & BIT_LEN_MASK_8(__bitlen)) << (__bitoffset)) \
-	);
+	)
 
 #define	N_BYTE_ALIGMENT(__value, __aligment) ((__aligment == 1) ? \
 	(__value) : (((__value + __aligment - 1) / __aligment) * __aligment))
diff --git a/drivers/net/wireless/rsi/rsi_91x_core.c b/drivers/net/wireless/rsi/rsi_91x_core.c
index 2b0516d2f63d..bc18a191aef9 100644
--- a/drivers/net/wireless/rsi/rsi_91x_core.c
+++ b/drivers/net/wireless/rsi/rsi_91x_core.c
@@ -95,6 +95,8 @@ static u32 rsi_get_num_pkts_dequeue(struct rsi_common *common, u8 q_num)
 	s16 txop = common->tx_qinfo[q_num].txop * 32;
 	__le16 r_txop;
 	struct ieee80211_rate rate;
+	struct ieee80211_hdr *wh;
+	struct ieee80211_vif *vif;
 
 	rate.bitrate = RSI_RATE_MCS0 * 5 * 10; /* Convert to Kbps */
 	if (q_num == VI_Q)
@@ -106,8 +108,10 @@ static u32 rsi_get_num_pkts_dequeue(struct rsi_common *common, u8 q_num)
 		return 0;
 
 	do {
+		wh = (struct ieee80211_hdr *)skb->data;
+		vif = rsi_get_vif(adapter, wh->addr2);
 		r_txop = ieee80211_generic_frame_duration(adapter->hw,
-							  adapter->vifs[0],
+							  vif,
 							  common->band,
 							  skb->len, &rate);
 		txop -= le16_to_cpu(r_txop);
@@ -334,6 +338,21 @@ struct rsi_sta *rsi_find_sta(struct rsi_common *common, u8 *mac_addr)
 	return NULL;
 }
 
+struct ieee80211_vif *rsi_get_vif(struct rsi_hw *adapter, u8 *mac)
+{
+	struct ieee80211_vif *vif;
+	int i;
+
+	for (i = 0; i < RSI_MAX_VIFS; i++) {
+		vif = adapter->vifs[i];
+		if (!vif)
+			continue;
+		if (!memcmp(vif->addr, mac, ETH_ALEN))
+			return vif;
+	}
+	return NULL;
+}
+
 /**
  * rsi_core_xmit() - This function transmits the packets received from mac80211
  * @common: Pointer to the driver private structure.
@@ -346,8 +365,8 @@ void rsi_core_xmit(struct rsi_common *common, struct sk_buff *skb)
 	struct rsi_hw *adapter = common->priv;
 	struct ieee80211_tx_info *info;
 	struct skb_info *tx_params;
-	struct ieee80211_hdr *wh;
-	struct ieee80211_vif *vif = adapter->vifs[0];
+	struct ieee80211_hdr *wh = NULL;
+	struct ieee80211_vif *vif;
 	u8 q_num, tid = 0;
 	struct rsi_sta *rsta = NULL;
 
@@ -366,6 +385,11 @@ void rsi_core_xmit(struct rsi_common *common, struct sk_buff *skb)
 	wh = (struct ieee80211_hdr *)&skb->data[0];
 	tx_params->sta_id = 0;
 
+	vif = rsi_get_vif(adapter, wh->addr2);
+	if (!vif)
+		goto xmit_fail;
+	tx_params->vif = vif;
+	tx_params->vap_id = ((struct vif_priv *)vif->drv_priv)->vap_id;
 	if ((ieee80211_is_mgmt(wh->frame_control)) ||
 	    (ieee80211_is_ctl(wh->frame_control)) ||
 	    (ieee80211_is_qos_nullfunc(wh->frame_control))) {
@@ -383,7 +407,8 @@ void rsi_core_xmit(struct rsi_common *common, struct sk_buff *skb)
 		q_num = skb->priority;
 		tx_params->tid = tid;
 
-		if ((vif->type == NL80211_IFTYPE_AP) &&
+		if (((vif->type == NL80211_IFTYPE_AP) ||
+		     (vif->type == NL80211_IFTYPE_P2P_GO)) &&
 		    (!is_broadcast_ether_addr(wh->addr1)) &&
 		    (!is_multicast_ether_addr(wh->addr1))) {
 			rsta = rsi_find_sta(common, wh->addr1);
diff --git a/drivers/net/wireless/rsi/rsi_91x_debugfs.c b/drivers/net/wireless/rsi/rsi_91x_debugfs.c
index e98eb55c26cc..8c6ca8e689e4 100644
--- a/drivers/net/wireless/rsi/rsi_91x_debugfs.c
+++ b/drivers/net/wireless/rsi/rsi_91x_debugfs.c
@@ -83,19 +83,12 @@ static int rsi_version_read(struct seq_file *seq, void *data)
 {
 	struct rsi_common *common = seq->private;
 
-	common->driver_ver.major = 0;
-	common->driver_ver.minor = 1;
-	common->driver_ver.release_num = 0;
-	common->driver_ver.patch_num = 0;
-	seq_printf(seq, "Driver : %x.%d.%d.%d\nLMAC   : %d.%d.%d.%d\n",
-		   common->driver_ver.major,
-		   common->driver_ver.minor,
-		   common->driver_ver.release_num,
-		   common->driver_ver.patch_num,
-		   common->fw_ver.major,
-		   common->fw_ver.minor,
-		   common->fw_ver.release_num,
-		   common->fw_ver.patch_num);
+	seq_printf(seq, "LMAC   : %d.%d.%d.%d\n",
+		   common->lmac_ver.major,
+		   common->lmac_ver.minor,
+		   common->lmac_ver.release_num,
+		   common->lmac_ver.patch_num);
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c
index 070dfd68bb83..689527d7007a 100644
--- a/drivers/net/wireless/rsi/rsi_91x_hal.c
+++ b/drivers/net/wireless/rsi/rsi_91x_hal.c
@@ -42,7 +42,7 @@ static int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb)
 	struct ieee80211_hdr *wh = NULL;
 	struct ieee80211_tx_info *info;
 	struct ieee80211_conf *conf = &adapter->hw->conf;
-	struct ieee80211_vif *vif = adapter->vifs[0];
+	struct ieee80211_vif *vif;
 	struct rsi_mgmt_desc *mgmt_desc;
 	struct skb_info *tx_params;
 	struct ieee80211_bss_conf *bss = NULL;
@@ -57,6 +57,7 @@ static int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb)
 
 	info = IEEE80211_SKB_CB(skb);
 	tx_params = (struct skb_info *)info->driver_data;
+	vif = tx_params->vif;
 
 	/* Update header size */
 	header_size = FRAME_DESC_SZ + sizeof(struct xtended_desc);
@@ -78,7 +79,7 @@ static int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb)
 
 	tx_params->internal_hdr_size = header_size;
 	memset(&skb->data[0], 0, header_size);
-	bss = &info->control.vif->bss_conf;
+	bss = &vif->bss_conf;
 	wh = (struct ieee80211_hdr *)&skb->data[header_size];
 
 	mgmt_desc = (struct rsi_mgmt_desc *)skb->data;
@@ -95,10 +96,10 @@ static int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb)
 
 	mgmt_desc->seq_ctrl =
 		cpu_to_le16(IEEE80211_SEQ_TO_SN(le16_to_cpu(wh->seq_ctrl)));
-	if (common->band == NL80211_BAND_2GHZ)
-		mgmt_desc->rate_info = RSI_RATE_1;
+	if ((common->band == NL80211_BAND_2GHZ) && !common->p2p_enabled)
+		mgmt_desc->rate_info = cpu_to_le16(RSI_RATE_1);
 	else
-		mgmt_desc->rate_info = RSI_RATE_6;
+		mgmt_desc->rate_info = cpu_to_le16(RSI_RATE_6);
 
 	if (conf_is_ht40(conf))
 		mgmt_desc->bbp_info = cpu_to_le16(FULL40M_ENABLE);
@@ -121,7 +122,8 @@ static int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb)
 		xtend_desc->retry_cnt = PROBE_RESP_RETRY_CNT;
 	}
 
-	if ((vif->type == NL80211_IFTYPE_AP) &&
+	if (((vif->type == NL80211_IFTYPE_AP) ||
+	     (vif->type == NL80211_IFTYPE_P2P_GO)) &&
 	    (ieee80211_is_action(wh->frame_control))) {
 		struct rsi_sta *rsta = rsi_find_sta(common, wh->addr1);
 
@@ -130,6 +132,10 @@ static int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb)
 		else
 			return -EINVAL;
 	}
+	mgmt_desc->rate_info |=
+		cpu_to_le16((tx_params->vap_id << RSI_DESC_VAP_ID_OFST) &
+			    RSI_DESC_VAP_ID_MASK);
+
 	return 0;
 }
 
@@ -151,7 +157,8 @@ static int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb)
 	u16 seq_num;
 
 	info = IEEE80211_SKB_CB(skb);
-	bss = &info->control.vif->bss_conf;
+	vif = info->control.vif;
+	bss = &vif->bss_conf;
 	tx_params = (struct skb_info *)info->driver_data;
 
 	header_size = FRAME_DESC_SZ + sizeof(struct xtended_desc);
@@ -175,7 +182,6 @@ static int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb)
 	xtend_desc = (struct xtended_desc *)&skb->data[FRAME_DESC_SZ];
 	wh = (struct ieee80211_hdr *)&skb->data[header_size];
 	seq_num = IEEE80211_SEQ_TO_SN(le16_to_cpu(wh->seq_ctrl));
-	vif = adapter->vifs[0];
 
 	data_desc->xtend_desc_size = header_size - FRAME_DESC_SZ;
 
@@ -184,7 +190,8 @@ static int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb)
 		data_desc->mac_flags |= cpu_to_le16(RSI_QOS_ENABLE);
 	}
 
-	if ((vif->type == NL80211_IFTYPE_STATION) &&
+	if (((vif->type == NL80211_IFTYPE_STATION) ||
+	     (vif->type == NL80211_IFTYPE_P2P_CLIENT)) &&
 	    (adapter->ps_state == PS_ENABLED))
 		wh->frame_control |= cpu_to_le16(RSI_SET_PS_ENABLE);
 
@@ -240,17 +247,23 @@ static int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb)
 		data_desc->frame_info |= cpu_to_le16(RSI_BROADCAST_PKT);
 		data_desc->sta_id = vap_id;
 
-		if (vif->type == NL80211_IFTYPE_AP) {
+		if ((vif->type == NL80211_IFTYPE_AP) ||
+		    (vif->type == NL80211_IFTYPE_P2P_GO)) {
 			if (common->band == NL80211_BAND_5GHZ)
 				data_desc->rate_info = cpu_to_le16(RSI_RATE_6);
 			else
 				data_desc->rate_info = cpu_to_le16(RSI_RATE_1);
 		}
 	}
-	if ((vif->type == NL80211_IFTYPE_AP) &&
+	if (((vif->type == NL80211_IFTYPE_AP) ||
+	     (vif->type == NL80211_IFTYPE_P2P_GO)) &&
 	    (ieee80211_has_moredata(wh->frame_control)))
 		data_desc->frame_info |= cpu_to_le16(MORE_DATA_PRESENT);
 
+	data_desc->rate_info |=
+		cpu_to_le16((tx_params->vap_id << RSI_DESC_VAP_ID_OFST) &
+			    RSI_DESC_VAP_ID_MASK);
+
 	return 0;
 }
 
@@ -258,7 +271,7 @@ static int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb)
 int rsi_send_data_pkt(struct rsi_common *common, struct sk_buff *skb)
 {
 	struct rsi_hw *adapter = common->priv;
-	struct ieee80211_vif *vif = adapter->vifs[0];
+	struct ieee80211_vif *vif;
 	struct ieee80211_tx_info *info;
 	struct ieee80211_bss_conf *bss;
 	int status = -EINVAL;
@@ -271,9 +284,12 @@ int rsi_send_data_pkt(struct rsi_common *common, struct sk_buff *skb)
 	info = IEEE80211_SKB_CB(skb);
 	if (!info->control.vif)
 		goto err;
-	bss = &info->control.vif->bss_conf;
+	vif = info->control.vif;
+	bss = &vif->bss_conf;
 
-	if ((vif->type == NL80211_IFTYPE_STATION) && (!bss->assoc))
+	if (((vif->type == NL80211_IFTYPE_STATION) ||
+	     (vif->type == NL80211_IFTYPE_P2P_CLIENT)) &&
+	    (!bss->assoc))
 		goto err;
 
 	status = rsi_prepare_data_desc(common, skb);
@@ -306,21 +322,11 @@ int rsi_send_mgmt_pkt(struct rsi_common *common,
 	struct ieee80211_tx_info *info;
 	struct skb_info *tx_params;
 	int status = -E2BIG;
-	u8 extnd_size;
 
 	info = IEEE80211_SKB_CB(skb);
 	tx_params = (struct skb_info *)info->driver_data;
-	extnd_size = ((uintptr_t)skb->data & 0x3);
 
 	if (tx_params->flags & INTERNAL_MGMT_PKT) {
-		skb->data[1] |= BIT(7); /* Immediate Wakeup bit*/
-		if ((extnd_size) > skb_headroom(skb)) {
-			rsi_dbg(ERR_ZONE, "%s: Unable to send pkt\n", __func__);
-			dev_kfree_skb(skb);
-			return -ENOSPC;
-		}
-		skb_push(skb, extnd_size);
-		skb->data[extnd_size + 4] = extnd_size;
 		status = adapter->host_intf_ops->write_pkt(common->priv,
 							   (u8 *)skb->data,
 							   skb->len);
@@ -352,12 +358,23 @@ int rsi_prepare_beacon(struct rsi_common *common, struct sk_buff *skb)
 	struct rsi_data_desc *bcn_frm;
 	struct ieee80211_hw *hw = common->priv->hw;
 	struct ieee80211_conf *conf = &hw->conf;
+	struct ieee80211_vif *vif;
 	struct sk_buff *mac_bcn;
-	u8 vap_id = 0;
-	u16 tim_offset;
-
+	u8 vap_id = 0, i;
+	u16 tim_offset = 0;
+
+	for (i = 0; i < RSI_MAX_VIFS; i++) {
+		vif = adapter->vifs[i];
+		if (!vif)
+			continue;
+		if ((vif->type == NL80211_IFTYPE_AP) ||
+		    (vif->type == NL80211_IFTYPE_P2P_GO))
+			break;
+	}
+	if (!vif)
+		return -EINVAL;
 	mac_bcn = ieee80211_beacon_get_tim(adapter->hw,
-					   adapter->vifs[adapter->sc_nvifs - 1],
+					   vif,
 					   &tim_offset, NULL);
 	if (!mac_bcn) {
 		rsi_dbg(ERR_ZONE, "Failed to get beacon from mac80211\n");
@@ -411,9 +428,8 @@ static void bl_cmd_timeout(unsigned long priv)
 
 static int bl_start_cmd_timer(struct rsi_hw *adapter, u32 timeout)
 {
-	init_timer(&adapter->bl_cmd_timer);
-	adapter->bl_cmd_timer.data = (unsigned long)adapter;
-	adapter->bl_cmd_timer.function = (void *)&bl_cmd_timeout;
+	setup_timer(&adapter->bl_cmd_timer, (void *)&bl_cmd_timeout,
+		    (unsigned long)adapter);
 	adapter->bl_cmd_timer.expires = (msecs_to_jiffies(timeout) + jiffies);
 
 	adapter->blcmd_timer_expired = false;
@@ -752,6 +768,7 @@ static int auto_fw_upgrade(struct rsi_hw *adapter, u8 *flash_content,
 
 static int rsi_load_firmware(struct rsi_hw *adapter)
 {
+	struct rsi_common *common = adapter->priv;
 	struct rsi_host_intf_ops *hif_ops = adapter->host_intf_ops;
 	const struct firmware *fw_entry = NULL;
 	u32 regout_val = 0, content_size;
@@ -827,6 +844,18 @@ static int rsi_load_firmware(struct rsi_hw *adapter)
 	content_size = fw_entry->size;
 	rsi_dbg(INFO_ZONE, "FW Length = %d bytes\n", content_size);
 
+	/* Get the firmware version */
+	common->lmac_ver.ver.info.fw_ver[0] =
+		flash_content[LMAC_VER_OFFSET] & 0xFF;
+	common->lmac_ver.ver.info.fw_ver[1] =
+		flash_content[LMAC_VER_OFFSET + 1] & 0xFF;
+	common->lmac_ver.major = flash_content[LMAC_VER_OFFSET + 2] & 0xFF;
+	common->lmac_ver.release_num =
+		flash_content[LMAC_VER_OFFSET + 3] & 0xFF;
+	common->lmac_ver.minor = flash_content[LMAC_VER_OFFSET + 4] & 0xFF;
+	common->lmac_ver.patch_num = 0;
+	rsi_print_version(common);
+
 	status = bl_write_header(adapter, flash_content, content_size);
 	if (status) {
 		rsi_dbg(ERR_ZONE,
diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
index fa12c05d9e23..b1f5dbbde3cb 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
@@ -139,6 +139,32 @@ static const u32 rsi_max_ap_stas[16] = {
 	4,	/* 14 - AP + BT Dual */
 };
 
+static const struct ieee80211_iface_limit rsi_iface_limits[] = {
+	{
+		.max = 1,
+		.types = BIT(NL80211_IFTYPE_STATION),
+	},
+	{
+		.max = 1,
+		.types = BIT(NL80211_IFTYPE_AP) |
+			BIT(NL80211_IFTYPE_P2P_CLIENT) |
+			BIT(NL80211_IFTYPE_P2P_GO),
+	},
+	{
+		.max = 1,
+		.types = BIT(NL80211_IFTYPE_P2P_DEVICE),
+	},
+};
+
+static const struct ieee80211_iface_combination rsi_iface_combinations[] = {
+	{
+		.num_different_channels = 1,
+		.max_interfaces = 3,
+		.limits = rsi_iface_limits,
+		.n_limits = ARRAY_SIZE(rsi_iface_limits),
+	},
+};
+
 /**
  * rsi_is_cipher_wep() -  This function determines if the cipher is WEP or not.
  * @common: Pointer to the driver private structure.
@@ -329,6 +355,24 @@ static void rsi_mac80211_stop(struct ieee80211_hw *hw)
 	mutex_unlock(&common->mutex);
 }
 
+static int rsi_map_intf_mode(enum nl80211_iftype vif_type)
+{
+	switch (vif_type) {
+	case NL80211_IFTYPE_STATION:
+		return RSI_OPMODE_STA;
+	case NL80211_IFTYPE_AP:
+		return RSI_OPMODE_AP;
+	case NL80211_IFTYPE_P2P_DEVICE:
+		return RSI_OPMODE_P2P_CLIENT;
+	case NL80211_IFTYPE_P2P_CLIENT:
+		return RSI_OPMODE_P2P_CLIENT;
+	case NL80211_IFTYPE_P2P_GO:
+		return RSI_OPMODE_P2P_GO;
+	default:
+		return RSI_OPMODE_UNSUPPORTED;
+	}
+}
+
 /**
  * rsi_mac80211_add_interface() - This function is called when a netdevice
  *				  attached to the hardware is enabled.
@@ -342,54 +386,62 @@ static int rsi_mac80211_add_interface(struct ieee80211_hw *hw,
 {
 	struct rsi_hw *adapter = hw->priv;
 	struct rsi_common *common = adapter->priv;
+	struct vif_priv *vif_info = (struct vif_priv *)vif->drv_priv;
 	enum opmode intf_mode;
-	int ret = -EOPNOTSUPP;
+	enum vap_status vap_status;
+	int vap_idx = -1, i;
 
 	vif->driver_flags |= IEEE80211_VIF_SUPPORTS_UAPSD;
 	mutex_lock(&common->mutex);
 
-	if (adapter->sc_nvifs > 1) {
-		mutex_unlock(&common->mutex);
-		return -EOPNOTSUPP;
-	}
-
-	switch (vif->type) {
-	case NL80211_IFTYPE_STATION:
-		rsi_dbg(INFO_ZONE, "Station Mode");
-		intf_mode = STA_OPMODE;
-		break;
-	case NL80211_IFTYPE_AP:
-		rsi_dbg(INFO_ZONE, "AP Mode");
-		intf_mode = AP_OPMODE;
-		break;
-	default:
+	intf_mode = rsi_map_intf_mode(vif->type);
+	if (intf_mode == RSI_OPMODE_UNSUPPORTED) {
 		rsi_dbg(ERR_ZONE,
 			"%s: Interface type %d not supported\n", __func__,
 			vif->type);
-		goto out;
+		mutex_unlock(&common->mutex);
+		return -EOPNOTSUPP;
+	}
+	if ((vif->type == NL80211_IFTYPE_P2P_DEVICE) ||
+	    (vif->type == NL80211_IFTYPE_P2P_CLIENT) ||
+	    (vif->type == NL80211_IFTYPE_P2P_GO))
+		common->p2p_enabled = true;
+
+	/* Get free vap index */
+	for (i = 0; i < RSI_MAX_VIFS; i++) {
+		if (!adapter->vifs[i]) {
+			vap_idx = i;
+			break;
+		}
+	}
+	if (vap_idx < 0) {
+		rsi_dbg(ERR_ZONE, "Reject: Max VAPs reached\n");
+		mutex_unlock(&common->mutex);
+		return -EOPNOTSUPP;
 	}
+	vif_info->vap_id = vap_idx;
+	adapter->vifs[vap_idx] = vif;
+	adapter->sc_nvifs++;
+	vap_status = VAP_ADD;
 
-	adapter->vifs[adapter->sc_nvifs++] = vif;
-	ret = rsi_set_vap_capabilities(common, intf_mode, common->mac_addr,
-				       0, VAP_ADD);
-	if (ret) {
+	if (rsi_set_vap_capabilities(common, intf_mode, vif->addr,
+				     vif_info->vap_id, vap_status)) {
 		rsi_dbg(ERR_ZONE, "Failed to set VAP capabilities\n");
-		goto out;
+		mutex_unlock(&common->mutex);
+		return -EINVAL;
 	}
 
-	if (vif->type == NL80211_IFTYPE_AP) {
-		int i;
-
+	if ((vif->type == NL80211_IFTYPE_AP) ||
+	    (vif->type == NL80211_IFTYPE_P2P_GO)) {
 		rsi_send_rx_filter_frame(common, DISALLOW_BEACONS);
 		common->min_rate = RSI_RATE_AUTO;
 		for (i = 0; i < common->max_stations; i++)
 			common->stations[i].sta = NULL;
 	}
 
-out:
 	mutex_unlock(&common->mutex);
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -406,6 +458,7 @@ static void rsi_mac80211_remove_interface(struct ieee80211_hw *hw,
 	struct rsi_hw *adapter = hw->priv;
 	struct rsi_common *common = adapter->priv;
 	enum opmode opmode;
+	int i;
 
 	rsi_dbg(INFO_ZONE, "Remove Interface Called\n");
 
@@ -416,23 +469,22 @@ static void rsi_mac80211_remove_interface(struct ieee80211_hw *hw,
 		return;
 	}
 
-	switch (vif->type) {
-	case NL80211_IFTYPE_STATION:
-		opmode = STA_OPMODE;
-		break;
-	case NL80211_IFTYPE_AP:
-		opmode = AP_OPMODE;
-		break;
-	default:
+	opmode = rsi_map_intf_mode(vif->type);
+	if (opmode == RSI_OPMODE_UNSUPPORTED) {
+		rsi_dbg(ERR_ZONE, "Opmode error : %d\n", opmode);
 		mutex_unlock(&common->mutex);
 		return;
 	}
-	rsi_set_vap_capabilities(common, opmode, vif->addr,
-				 0, VAP_DELETE);
-	adapter->sc_nvifs--;
-
-	if (!memcmp(adapter->vifs[0], vif, sizeof(struct ieee80211_vif)))
-		adapter->vifs[0] = NULL;
+	for (i = 0; i < RSI_MAX_VIFS; i++) {
+		if (!adapter->vifs[i])
+			continue;
+		if (vif == adapter->vifs[i]) {
+			rsi_set_vap_capabilities(common, opmode, vif->addr,
+						 i, VAP_DELETE);
+			adapter->sc_nvifs--;
+			adapter->vifs[i] = NULL;
+		}
+	}
 	mutex_unlock(&common->mutex);
 }
 
@@ -451,35 +503,44 @@ static int rsi_channel_change(struct ieee80211_hw *hw)
 	int status = -EOPNOTSUPP;
 	struct ieee80211_channel *curchan = hw->conf.chandef.chan;
 	u16 channel = curchan->hw_value;
-	struct ieee80211_bss_conf *bss = &adapter->vifs[0]->bss_conf;
+	struct ieee80211_vif *vif;
+	struct ieee80211_bss_conf *bss;
+	bool assoc = false;
+	int i;
 
 	rsi_dbg(INFO_ZONE,
 		"%s: Set channel: %d MHz type: %d channel_no %d\n",
 		__func__, curchan->center_freq,
 		curchan->flags, channel);
 
-	if (bss->assoc) {
+	for (i = 0; i < RSI_MAX_VIFS; i++) {
+		vif = adapter->vifs[i];
+		if (!vif)
+			continue;
+		if (vif->type == NL80211_IFTYPE_STATION) {
+			bss = &vif->bss_conf;
+			if (bss->assoc) {
+				assoc = true;
+				break;
+			}
+		}
+	}
+	if (assoc) {
 		if (!common->hw_data_qs_blocked &&
-		    (rsi_get_connected_channel(adapter) != channel)) {
+		    (rsi_get_connected_channel(vif) != channel)) {
 			rsi_dbg(INFO_ZONE, "blk data q %d\n", channel);
 			if (!rsi_send_block_unblock_frame(common, true))
 				common->hw_data_qs_blocked = true;
 		}
 	}
 
-	status = rsi_band_check(common);
+	status = rsi_band_check(common, curchan);
 	if (!status)
 		status = rsi_set_channel(adapter->priv, curchan);
 
-	if (bss->assoc) {
+	if (assoc) {
 		if (common->hw_data_qs_blocked &&
-		    (rsi_get_connected_channel(adapter) == channel)) {
-			rsi_dbg(INFO_ZONE, "unblk data q %d\n", channel);
-			if (!rsi_send_block_unblock_frame(common, false))
-				common->hw_data_qs_blocked = false;
-		}
-	} else {
-		if (common->hw_data_qs_blocked) {
+		    (rsi_get_connected_channel(vif) == channel)) {
 			rsi_dbg(INFO_ZONE, "unblk data q %d\n", channel);
 			if (!rsi_send_block_unblock_frame(common, false))
 				common->hw_data_qs_blocked = false;
@@ -531,7 +592,6 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw,
 {
 	struct rsi_hw *adapter = hw->priv;
 	struct rsi_common *common = adapter->priv;
-	struct ieee80211_vif *vif = adapter->vifs[0];
 	struct ieee80211_conf *conf = &hw->conf;
 	int status = -EOPNOTSUPP;
 
@@ -547,16 +607,30 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw,
 	}
 
 	/* Power save parameters */
-	if ((changed & IEEE80211_CONF_CHANGE_PS) &&
-	    (vif->type == NL80211_IFTYPE_STATION)) {
+	if (changed & IEEE80211_CONF_CHANGE_PS) {
+		struct ieee80211_vif *vif;
 		unsigned long flags;
+		int i, set_ps = 1;
 
-		spin_lock_irqsave(&adapter->ps_lock, flags);
-		if (conf->flags & IEEE80211_CONF_PS)
-			rsi_enable_ps(adapter);
-		else
-			rsi_disable_ps(adapter);
-		spin_unlock_irqrestore(&adapter->ps_lock, flags);
+		for (i = 0; i < RSI_MAX_VIFS; i++) {
+			vif = adapter->vifs[i];
+			if (!vif)
+				continue;
+			/* Don't go to power save if AP vap exists */
+			if ((vif->type == NL80211_IFTYPE_AP) ||
+			    (vif->type == NL80211_IFTYPE_P2P_GO)) {
+				set_ps = 0;
+				break;
+			}
+		}
+		if (set_ps) {
+			spin_lock_irqsave(&adapter->ps_lock, flags);
+			if (conf->flags & IEEE80211_CONF_PS)
+				rsi_enable_ps(adapter, vif);
+			else
+				rsi_disable_ps(adapter, vif);
+			spin_unlock_irqrestore(&adapter->ps_lock, flags);
+		}
 	}
 
 	/* RTS threshold */
@@ -580,16 +654,42 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw,
  *
  * Return: Current connected AP's channel number is returned.
  */
-u16 rsi_get_connected_channel(struct rsi_hw *adapter)
+u16 rsi_get_connected_channel(struct ieee80211_vif *vif)
 {
-	struct ieee80211_vif *vif = adapter->vifs[0];
-	if (vif) {
-		struct ieee80211_bss_conf *bss = &vif->bss_conf;
-		struct ieee80211_channel *channel = bss->chandef.chan;
-		return channel->hw_value;
-	}
+	struct ieee80211_bss_conf *bss;
+	struct ieee80211_channel *channel;
 
-	return 0;
+	if (!vif)
+		return 0;
+
+	bss = &vif->bss_conf;
+	channel = bss->chandef.chan;
+
+	if (!channel)
+		return 0;
+
+	return channel->hw_value;
+}
+
+static void rsi_switch_channel(struct rsi_hw *adapter,
+			       struct ieee80211_vif *vif)
+{
+	struct rsi_common *common = adapter->priv;
+	struct ieee80211_channel *channel;
+
+	if (common->iface_down)
+		return;
+	if (!vif)
+		return;
+
+	channel = vif->bss_conf.chandef.chan;
+
+	if (!channel)
+		return;
+
+	rsi_band_check(common, channel);
+	rsi_set_channel(common, channel);
+	rsi_dbg(INFO_ZONE, "Switched to channel - %d\n", channel->hw_value);
 }
 
 /**
@@ -626,12 +726,12 @@ static void rsi_mac80211_bss_info_changed(struct ieee80211_hw *hw,
 			rsi_send_rx_filter_frame(common, rx_filter_word);
 		}
 		rsi_inform_bss_status(common,
-				      STA_OPMODE,
+				      RSI_OPMODE_STA,
 				      bss_conf->assoc,
 				      bss_conf->bssid,
 				      bss_conf->qos,
 				      bss_conf->aid,
-				      NULL, 0);
+				      NULL, 0, vif);
 		adapter->ps_info.dtim_interval_duration = bss->dtim_period;
 		adapter->ps_info.listen_interval = conf->listen_interval;
 
@@ -639,7 +739,7 @@ static void rsi_mac80211_bss_info_changed(struct ieee80211_hw *hw,
 	if (bss->assoc) {
 		if (common->uapsd_bitmap) {
 			rsi_dbg(INFO_ZONE, "Configuring UAPSD\n");
-			rsi_conf_uapsd(adapter);
+			rsi_conf_uapsd(adapter, vif);
 		}
 	} else {
 		common->uapsd_bitmap = 0;
@@ -656,7 +756,8 @@ static void rsi_mac80211_bss_info_changed(struct ieee80211_hw *hw,
 	}
 
 	if ((changed & BSS_CHANGED_BEACON_ENABLED) &&
-	    (vif->type == NL80211_IFTYPE_AP)) {
+	    ((vif->type == NL80211_IFTYPE_AP) ||
+	     (vif->type == NL80211_IFTYPE_P2P_GO))) {
 		if (bss->enable_beacon) {
 			rsi_dbg(INFO_ZONE, "===> BEACON ENABLED <===\n");
 			common->beacon_enabled = 1;
@@ -775,7 +876,8 @@ static int rsi_hal_key_config(struct ieee80211_hw *hw,
 	rsi_dbg(ERR_ZONE, "%s: Cipher 0x%x key_type: %d key_len: %d\n",
 		__func__, key->cipher, key_type, key->keylen);
 
-	if (vif->type == NL80211_IFTYPE_AP) {
+	if ((vif->type == NL80211_IFTYPE_AP) ||
+	    (vif->type == NL80211_IFTYPE_P2P_GO)) {
 		if (sta) {
 			rsta = rsi_find_sta(adapter->priv, sta->addr);
 			if (rsta)
@@ -791,7 +893,8 @@ static int rsi_hal_key_config(struct ieee80211_hw *hw,
 						  RSI_PAIRWISE_KEY,
 						  key->keyidx,
 						  key->cipher,
-						  sta_id);
+						  sta_id,
+						  vif);
 			if (status)
 				return status;
 		}
@@ -803,7 +906,8 @@ static int rsi_hal_key_config(struct ieee80211_hw *hw,
 				key_type,
 				key->keyidx,
 				key->cipher,
-				sta_id);
+				sta_id,
+				vif);
 }
 
 /**
@@ -902,7 +1006,8 @@ static int rsi_mac80211_ampdu_action(struct ieee80211_hw *hw,
 	if (ssn != NULL)
 		seq_no = *ssn;
 
-	if (vif->type == NL80211_IFTYPE_AP) {
+	if ((vif->type == NL80211_IFTYPE_AP) ||
+	    (vif->type == NL80211_IFTYPE_P2P_GO)) {
 		rsta = rsi_find_sta(common, sta->addr);
 		if (!rsta) {
 			rsi_dbg(ERR_ZONE, "No station mapped\n");
@@ -936,9 +1041,11 @@ static int rsi_mac80211_ampdu_action(struct ieee80211_hw *hw,
 		break;
 
 	case IEEE80211_AMPDU_TX_START:
-		if (vif->type == NL80211_IFTYPE_STATION)
+		if ((vif->type == NL80211_IFTYPE_STATION) ||
+		    (vif->type == NL80211_IFTYPE_P2P_CLIENT))
 			common->vif_info[ii].seq_start = seq_no;
-		else if (vif->type == NL80211_IFTYPE_AP)
+		else if ((vif->type == NL80211_IFTYPE_AP) ||
+			 (vif->type == NL80211_IFTYPE_P2P_GO))
 			rsta->seq_start[tid] = seq_no;
 		ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		status = 0;
@@ -958,9 +1065,11 @@ static int rsi_mac80211_ampdu_action(struct ieee80211_hw *hw,
 		break;
 
 	case IEEE80211_AMPDU_TX_OPERATIONAL:
-		if (vif->type == NL80211_IFTYPE_STATION)
+		if ((vif->type == NL80211_IFTYPE_STATION) ||
+		    (vif->type == NL80211_IFTYPE_P2P_CLIENT))
 			seq_start = common->vif_info[ii].seq_start;
-		else if (vif->type == NL80211_IFTYPE_AP)
+		else if ((vif->type == NL80211_IFTYPE_AP) ||
+			 (vif->type == NL80211_IFTYPE_P2P_GO))
 			seq_start = rsta->seq_start[tid];
 		status = rsi_send_aggregation_params_frame(common,
 							   tid,
@@ -1039,9 +1148,9 @@ static int rsi_mac80211_set_rate_mask(struct ieee80211_hw *hw,
  */
 static void rsi_perform_cqm(struct rsi_common *common,
 			    u8 *bssid,
-			    s8 rssi)
+			    s8 rssi,
+			    struct ieee80211_vif *vif)
 {
-	struct rsi_hw *adapter = common->priv;
 	s8 last_event = common->cqm_info.last_cqm_event_rssi;
 	int thold = common->cqm_info.rssi_thold;
 	u32 hyst = common->cqm_info.rssi_hyst;
@@ -1057,7 +1166,7 @@ static void rsi_perform_cqm(struct rsi_common *common,
 
 	common->cqm_info.last_cqm_event_rssi = rssi;
 	rsi_dbg(INFO_ZONE, "CQM: Notifying event: %d\n", event);
-	ieee80211_cqm_rssi_notify(adapter->vifs[0], event, rssi, GFP_KERNEL);
+	ieee80211_cqm_rssi_notify(vif, event, rssi, GFP_KERNEL);
 
 	return;
 }
@@ -1077,7 +1186,9 @@ static void rsi_fill_rx_status(struct ieee80211_hw *hw,
 			       struct rsi_common *common,
 			       struct ieee80211_rx_status *rxs)
 {
-	struct ieee80211_bss_conf *bss = &common->priv->vifs[0]->bss_conf;
+	struct rsi_hw *adapter = common->priv;
+	struct ieee80211_vif *vif;
+	struct ieee80211_bss_conf *bss = NULL;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct skb_info *rx_params = (struct skb_info *)info->driver_data;
 	struct ieee80211_hdr *hdr;
@@ -1085,6 +1196,7 @@ static void rsi_fill_rx_status(struct ieee80211_hw *hw,
 	u8 hdrlen = 0;
 	u8 channel = rx_params->channel;
 	s32 freq;
+	int i;
 
 	hdr = ((struct ieee80211_hdr *)(skb->data));
 	hdrlen = ieee80211_hdrlen(hdr->frame_control);
@@ -1113,10 +1225,21 @@ static void rsi_fill_rx_status(struct ieee80211_hw *hw,
 		rxs->flag |= RX_FLAG_IV_STRIPPED;
 	}
 
+	for (i = 0; i < RSI_MAX_VIFS; i++) {
+		vif = adapter->vifs[i];
+		if (!vif)
+			continue;
+		if (vif->type == NL80211_IFTYPE_STATION) {
+			bss = &vif->bss_conf;
+			break;
+		}
+	}
+	if (!bss)
+		return;
 	/* CQM only for connected AP beacons, the RSSI is a weighted avg */
 	if (bss->assoc && !(memcmp(bss->bssid, hdr->addr2, ETH_ALEN))) {
 		if (ieee80211_is_beacon(hdr->frame_control))
-			rsi_perform_cqm(common, hdr->addr2, rxs->signal);
+			rsi_perform_cqm(common, hdr->addr2, rxs->signal, vif);
 	}
 
 	return;
@@ -1210,7 +1333,8 @@ static int rsi_mac80211_sta_add(struct ieee80211_hw *hw,
 
 	mutex_lock(&common->mutex);
 
-	if (vif->type == NL80211_IFTYPE_AP) {
+	if ((vif->type == NL80211_IFTYPE_AP) ||
+	    (vif->type == NL80211_IFTYPE_P2P_GO)) {
 		u8 cnt;
 		int sta_idx = -1;
 		int free_index = -1;
@@ -1259,8 +1383,9 @@ static int rsi_mac80211_sta_add(struct ieee80211_hw *hw,
 
 			/* Send peer notify to device */
 			rsi_dbg(INFO_ZONE, "Indicate bss status to device\n");
-			rsi_inform_bss_status(common, AP_OPMODE, 1, sta->addr,
-					      sta->wme, sta->aid, sta, sta_idx);
+			rsi_inform_bss_status(common, RSI_OPMODE_AP, 1,
+					      sta->addr, sta->wme, sta->aid,
+					      sta, sta_idx, vif);
 
 			if (common->key) {
 				struct ieee80211_key_conf *key = common->key;
@@ -1273,14 +1398,16 @@ static int rsi_mac80211_sta_add(struct ieee80211_hw *hw,
 							 RSI_PAIRWISE_KEY,
 							 key->keyidx,
 							 key->cipher,
-							 sta_idx);
+							 sta_idx,
+							 vif);
 			}
 
 			common->num_stations++;
 		}
 	}
 
-	if (vif->type == NL80211_IFTYPE_STATION) {
+	if ((vif->type == NL80211_IFTYPE_STATION) ||
+	    (vif->type == NL80211_IFTYPE_P2P_CLIENT)) {
 		rsi_set_min_rate(hw, sta, common);
 		if (sta->ht_cap.ht_supported) {
 			common->vif_info[0].is_ht = true;
@@ -1321,7 +1448,8 @@ static int rsi_mac80211_sta_remove(struct ieee80211_hw *hw,
 
 	mutex_lock(&common->mutex);
 
-	if (vif->type == NL80211_IFTYPE_AP) {
+	if ((vif->type == NL80211_IFTYPE_AP) ||
+	    (vif->type == NL80211_IFTYPE_P2P_GO)) {
 		u8 sta_idx, cnt;
 
 		/* Send peer notify to device */
@@ -1332,9 +1460,10 @@ static int rsi_mac80211_sta_remove(struct ieee80211_hw *hw,
 			if (!rsta->sta)
 				continue;
 			if (!memcmp(rsta->sta->addr, sta->addr, ETH_ALEN)) {
-				rsi_inform_bss_status(common, AP_OPMODE, 0,
+				rsi_inform_bss_status(common, RSI_OPMODE_AP, 0,
 						      sta->addr, sta->wme,
-						      sta->aid, sta, sta_idx);
+						      sta->aid, sta, sta_idx,
+						      vif);
 				rsta->sta = NULL;
 				rsta->sta_id = -1;
 				for (cnt = 0; cnt < IEEE80211_NUM_TIDS; cnt++)
@@ -1348,7 +1477,8 @@ static int rsi_mac80211_sta_remove(struct ieee80211_hw *hw,
 			rsi_dbg(ERR_ZONE, "%s: No station found\n", __func__);
 	}
 
-	if (vif->type == NL80211_IFTYPE_STATION) {
+	if ((vif->type == NL80211_IFTYPE_STATION) ||
+	    (vif->type == NL80211_IFTYPE_P2P_CLIENT)) {
 		/* Resetting all the fields to default values */
 		memcpy((u8 *)bss->bssid, (u8 *)sta->addr, ETH_ALEN);
 		bss->qos = sta->wme;
@@ -1508,6 +1638,114 @@ static void rsi_mac80211_rfkill_poll(struct ieee80211_hw *hw)
 	mutex_unlock(&common->mutex);
 }
 
+static void rsi_resume_conn_channel(struct rsi_common *common)
+{
+	struct rsi_hw *adapter = common->priv;
+	struct ieee80211_vif *vif;
+	int cnt;
+
+	for (cnt = 0; cnt < RSI_MAX_VIFS; cnt++) {
+		vif = adapter->vifs[cnt];
+		if (!vif)
+			continue;
+
+		if ((vif->type == NL80211_IFTYPE_AP) ||
+		    (vif->type == NL80211_IFTYPE_P2P_GO)) {
+			rsi_switch_channel(adapter, vif);
+			break;
+		}
+		if (((vif->type == NL80211_IFTYPE_STATION) ||
+		     (vif->type == NL80211_IFTYPE_P2P_CLIENT)) &&
+		    vif->bss_conf.assoc) {
+			rsi_switch_channel(adapter, vif);
+			break;
+		}
+	}
+}
+
+void rsi_roc_timeout(unsigned long data)
+{
+	struct rsi_common *common = (struct rsi_common *)data;
+
+	rsi_dbg(INFO_ZONE, "Remain on channel expired\n");
+
+	mutex_lock(&common->mutex);
+	ieee80211_remain_on_channel_expired(common->priv->hw);
+
+	if (timer_pending(&common->roc_timer))
+		del_timer(&common->roc_timer);
+
+	rsi_resume_conn_channel(common);
+	mutex_unlock(&common->mutex);
+}
+
+static int rsi_mac80211_roc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			    struct ieee80211_channel *chan, int duration,
+			    enum ieee80211_roc_type type)
+{
+	struct rsi_hw *adapter = (struct rsi_hw *)hw->priv;
+	struct rsi_common *common = (struct rsi_common *)adapter->priv;
+	int status = 0;
+
+	rsi_dbg(INFO_ZONE, "***** Remain on channel *****\n");
+
+	mutex_lock(&common->mutex);
+	rsi_dbg(INFO_ZONE, "%s: channel: %d duration: %dms\n",
+		__func__, chan->hw_value, duration);
+
+	if (timer_pending(&common->roc_timer)) {
+		rsi_dbg(INFO_ZONE, "Stop on-going ROC\n");
+		del_timer(&common->roc_timer);
+	}
+	common->roc_timer.expires = msecs_to_jiffies(duration) + jiffies;
+	add_timer(&common->roc_timer);
+
+	/* Configure band */
+	if (rsi_band_check(common, chan)) {
+		rsi_dbg(ERR_ZONE, "Failed to set band\n");
+		status = -EINVAL;
+		goto out;
+	}
+
+	/* Configure channel */
+	if (rsi_set_channel(common, chan)) {
+		rsi_dbg(ERR_ZONE, "Failed to set the channel\n");
+		status = -EINVAL;
+		goto out;
+	}
+
+	common->roc_vif = vif;
+	ieee80211_ready_on_channel(hw);
+	rsi_dbg(INFO_ZONE, "%s: Ready on channel :%d\n",
+		__func__, chan->hw_value);
+
+out:
+	mutex_unlock(&common->mutex);
+
+	return status;
+}
+
+static int rsi_mac80211_cancel_roc(struct ieee80211_hw *hw)
+{
+	struct rsi_hw *adapter = hw->priv;
+	struct rsi_common *common = adapter->priv;
+
+	rsi_dbg(INFO_ZONE, "Cancel remain on channel\n");
+
+	mutex_lock(&common->mutex);
+	if (!timer_pending(&common->roc_timer)) {
+		mutex_unlock(&common->mutex);
+		return 0;
+	}
+
+	del_timer(&common->roc_timer);
+
+	rsi_resume_conn_channel(common);
+	mutex_unlock(&common->mutex);
+
+	return 0;
+}
+
 static const struct ieee80211_ops mac80211_ops = {
 	.tx = rsi_mac80211_tx,
 	.start = rsi_mac80211_start,
@@ -1527,6 +1765,8 @@ static const struct ieee80211_ops mac80211_ops = {
 	.set_antenna = rsi_mac80211_set_antenna,
 	.get_antenna = rsi_mac80211_get_antenna,
 	.rfkill_poll = rsi_mac80211_rfkill_poll,
+	.remain_on_channel = rsi_mac80211_roc,
+	.cancel_remain_on_channel = rsi_mac80211_cancel_roc,
 };
 
 /**
@@ -1581,7 +1821,11 @@ int rsi_mac80211_attach(struct rsi_common *common)
 	ether_addr_copy(hw->wiphy->addr_mask, addr_mask);
 
 	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) |
-				 BIT(NL80211_IFTYPE_AP);
+				 BIT(NL80211_IFTYPE_AP) |
+				 BIT(NL80211_IFTYPE_P2P_DEVICE) |
+				 BIT(NL80211_IFTYPE_P2P_CLIENT) |
+				 BIT(NL80211_IFTYPE_P2P_GO);
+
 	wiphy->signal_type = CFG80211_SIGNAL_TYPE_MBM;
 	wiphy->retry_short = RETRY_SHORT;
 	wiphy->retry_long  = RETRY_LONG;
@@ -1608,6 +1852,14 @@ int rsi_mac80211_attach(struct rsi_common *common)
 
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
 
+	/* Wi-Fi direct parameters */
+	wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
+	wiphy->flags |= WIPHY_FLAG_OFFCHAN_TX;
+	wiphy->max_remain_on_channel_duration = 10000;
+	hw->max_listen_interval = 10;
+	wiphy->iface_combinations = rsi_iface_combinations;
+	wiphy->n_iface_combinations = ARRAY_SIZE(rsi_iface_combinations);
+
 	status = ieee80211_register_hw(hw);
 	if (status)
 		return status;
diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c
index 3e1e80888d98..71b8cfb8252e 100644
--- a/drivers/net/wireless/rsi/rsi_91x_main.c
+++ b/drivers/net/wireless/rsi/rsi_91x_main.c
@@ -20,6 +20,7 @@
 #include <linux/firmware.h>
 #include "rsi_mgmt.h"
 #include "rsi_common.h"
+#include "rsi_hal.h"
 
 u32 rsi_zone_enabled = /* INFO_ZONE |
 			INIT_ZONE |
@@ -56,6 +57,30 @@ void rsi_dbg(u32 zone, const char *fmt, ...)
 }
 EXPORT_SYMBOL_GPL(rsi_dbg);
 
+static char *opmode_str(int oper_mode)
+{
+	switch (oper_mode) {
+	case RSI_DEV_OPMODE_WIFI_ALONE:
+		return "Wi-Fi alone";
+	}
+
+	return "Unknown";
+}
+
+void rsi_print_version(struct rsi_common *common)
+{
+	rsi_dbg(ERR_ZONE, "================================================\n");
+	rsi_dbg(ERR_ZONE, "================ RSI Version Info ==============\n");
+	rsi_dbg(ERR_ZONE, "================================================\n");
+	rsi_dbg(ERR_ZONE, "FW Version\t: %d.%d.%d\n",
+		common->lmac_ver.major, common->lmac_ver.minor,
+		common->lmac_ver.release_num);
+	rsi_dbg(ERR_ZONE, "Operating mode\t: %d [%s]",
+		common->oper_mode, opmode_str(common->oper_mode));
+	rsi_dbg(ERR_ZONE, "Firmware file\t: %s", common->priv->fw_file_name);
+	rsi_dbg(ERR_ZONE, "================================================\n");
+}
+
 /**
  * rsi_prepare_skb() - This function prepares the skb.
  * @common: Pointer to the driver private structure.
@@ -74,6 +99,8 @@ static struct sk_buff *rsi_prepare_skb(struct rsi_common *common,
 	struct skb_info *rx_params;
 	struct sk_buff *skb = NULL;
 	u8 payload_offset;
+	struct ieee80211_vif *vif;
+	struct ieee80211_hdr *wh;
 
 	if (WARN(!pkt_len, "%s: Dummy pkt received", __func__))
 		return NULL;
@@ -92,11 +119,13 @@ static struct sk_buff *rsi_prepare_skb(struct rsi_common *common,
 	payload_offset = (extended_desc + FRAME_DESC_SZ);
 	skb_put(skb, pkt_len);
 	memcpy((skb->data), (buffer + payload_offset), skb->len);
+	wh = (struct ieee80211_hdr *)skb->data;
+	vif = rsi_get_vif(common->priv, wh->addr1);
 
 	info = IEEE80211_SKB_CB(skb);
 	rx_params = (struct skb_info *)info->driver_data;
 	rx_params->rssi = rsi_get_rssi(buffer);
-	rx_params->channel = rsi_get_connected_channel(common->priv);
+	rx_params->channel = rsi_get_connected_channel(vif);
 
 	return skb;
 }
@@ -233,6 +262,9 @@ struct rsi_hw *rsi_91x_init(void)
 
 	rsi_default_ps_params(adapter);
 	spin_lock_init(&adapter->ps_lock);
+	common->roc_timer.data = (unsigned long)common;
+	common->roc_timer.function = (void *)&rsi_roc_timeout;
+	init_timer(&common->roc_timer);
 	common->init_done = true;
 	return adapter;
 
diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
index f7b550f900c4..4b94190c9797 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
@@ -460,12 +460,12 @@ static int rsi_hal_send_sta_notify_frame(struct rsi_common *common,
 					 const unsigned char *bssid,
 					 u8 qos_enable,
 					 u16 aid,
-					 u16 sta_id)
+					 u16 sta_id,
+					 struct ieee80211_vif *vif)
 {
-	struct ieee80211_vif *vif = common->priv->vifs[0];
 	struct sk_buff *skb = NULL;
 	struct rsi_peer_notify *peer_notify;
-	u16 vap_id = 0;
+	u16 vap_id = ((struct vif_priv *)vif->drv_priv)->vap_id;
 	int status;
 	u16 frame_len = sizeof(struct rsi_peer_notify);
 
@@ -482,9 +482,9 @@ static int rsi_hal_send_sta_notify_frame(struct rsi_common *common,
 	memset(skb->data, 0, frame_len);
 	peer_notify = (struct rsi_peer_notify *)skb->data;
 
-	if (opmode == STA_OPMODE)
+	if (opmode == RSI_OPMODE_STA)
 		peer_notify->command = cpu_to_le16(PEER_TYPE_AP << 1);
-	else if (opmode == AP_OPMODE)
+	else if (opmode == RSI_OPMODE_AP)
 		peer_notify->command = cpu_to_le16(PEER_TYPE_STA << 1);
 
 	switch (notify_event) {
@@ -716,9 +716,9 @@ int rsi_hal_load_key(struct rsi_common *common,
 		     u8 key_type,
 		     u8 key_id,
 		     u32 cipher,
-		     s16 sta_id)
+		     s16 sta_id,
+		     struct ieee80211_vif *vif)
 {
-	struct ieee80211_vif *vif = common->priv->vifs[0];
 	struct sk_buff *skb = NULL;
 	struct rsi_set_key *set_key;
 	u16 key_descriptor = 0;
@@ -926,13 +926,13 @@ static int rsi_send_reset_mac(struct rsi_common *common)
  *
  * Return: 0 on success, corresponding error code on failure.
  */
-int rsi_band_check(struct rsi_common *common)
+int rsi_band_check(struct rsi_common *common,
+		   struct ieee80211_channel *curchan)
 {
 	struct rsi_hw *adapter = common->priv;
 	struct ieee80211_hw *hw = adapter->hw;
 	u8 prev_bw = common->channel_width;
 	u8 prev_ep = common->endpoint;
-	struct ieee80211_channel *curchan = hw->conf.chandef.chan;
 	int status = 0;
 
 	if (common->band != curchan->band) {
@@ -1160,9 +1160,9 @@ static bool rsi_map_rates(u16 rate, int *offset)
  */
 static int rsi_send_auto_rate_request(struct rsi_common *common,
 				      struct ieee80211_sta *sta,
-				      u16 sta_id)
+				      u16 sta_id,
+				      struct ieee80211_vif *vif)
 {
-	struct ieee80211_vif *vif = common->priv->vifs[0];
 	struct sk_buff *skb;
 	struct rsi_auto_rate *auto_rate;
 	int ii = 0, jj = 0, kk = 0;
@@ -1318,33 +1318,36 @@ void rsi_inform_bss_status(struct rsi_common *common,
 			   u8 qos_enable,
 			   u16 aid,
 			   struct ieee80211_sta *sta,
-			   u16 sta_id)
+			   u16 sta_id,
+			   struct ieee80211_vif *vif)
 {
 	if (status) {
-		if (opmode == STA_OPMODE)
+		if (opmode == RSI_OPMODE_STA)
 			common->hw_data_qs_blocked = true;
 		rsi_hal_send_sta_notify_frame(common,
 					      opmode,
 					      STA_CONNECTED,
 					      addr,
 					      qos_enable,
-					      aid, sta_id);
+					      aid, sta_id,
+					      vif);
 		if (common->min_rate == 0xffff)
-			rsi_send_auto_rate_request(common, sta, sta_id);
-		if (opmode == STA_OPMODE) {
+			rsi_send_auto_rate_request(common, sta, sta_id, vif);
+		if (opmode == RSI_OPMODE_STA) {
 			if (!rsi_send_block_unblock_frame(common, false))
 				common->hw_data_qs_blocked = false;
 		}
 	} else {
-		if (opmode == STA_OPMODE)
+		if (opmode == RSI_OPMODE_STA)
 			common->hw_data_qs_blocked = true;
 		rsi_hal_send_sta_notify_frame(common,
 					      opmode,
 					      STA_DISCONNECTED,
 					      addr,
 					      qos_enable,
-					      aid, sta_id);
-		if (opmode == STA_OPMODE)
+					      aid, sta_id,
+					      vif);
+		if (opmode == RSI_OPMODE_STA)
 			rsi_send_block_unblock_frame(common, true);
 	}
 }
@@ -1471,10 +1474,11 @@ int rsi_send_rx_filter_frame(struct rsi_common *common, u16 rx_filter_word)
 	return rsi_send_internal_mgmt_frame(common, skb);
 }
 
-int rsi_send_ps_request(struct rsi_hw *adapter, bool enable)
+int rsi_send_ps_request(struct rsi_hw *adapter, bool enable,
+			struct ieee80211_vif *vif)
 {
 	struct rsi_common *common = adapter->priv;
-	struct ieee80211_bss_conf *bss = &adapter->vifs[0]->bss_conf;
+	struct ieee80211_bss_conf *bss = &vif->bss_conf;
 	struct rsi_request_ps *ps;
 	struct rsi_ps_info *ps_info;
 	struct sk_buff *skb;
diff --git a/drivers/net/wireless/rsi/rsi_91x_ps.c b/drivers/net/wireless/rsi/rsi_91x_ps.c
index 48c79f035c59..523f5329d2b7 100644
--- a/drivers/net/wireless/rsi/rsi_91x_ps.c
+++ b/drivers/net/wireless/rsi/rsi_91x_ps.c
@@ -67,7 +67,7 @@ void rsi_default_ps_params(struct rsi_hw *adapter)
 	ps_info->deep_sleep_wakeup_period = RSI_DEF_DS_WAKEUP_PERIOD;
 }
 
-void rsi_enable_ps(struct rsi_hw *adapter)
+void rsi_enable_ps(struct rsi_hw *adapter, struct ieee80211_vif *vif)
 {
 	if (adapter->ps_state != PS_NONE) {
 		rsi_dbg(ERR_ZONE,
@@ -76,7 +76,7 @@ void rsi_enable_ps(struct rsi_hw *adapter)
 		return;
 	}
 
-	if (rsi_send_ps_request(adapter, true)) {
+	if (rsi_send_ps_request(adapter, true, vif)) {
 		rsi_dbg(ERR_ZONE,
 			"%s: Failed to send PS request to device\n",
 			__func__);
@@ -86,7 +86,8 @@ void rsi_enable_ps(struct rsi_hw *adapter)
 	rsi_modify_ps_state(adapter, PS_ENABLE_REQ_SENT);
 }
 
-void rsi_disable_ps(struct rsi_hw *adapter)
+/* This function is used to disable power save */
+void rsi_disable_ps(struct rsi_hw *adapter, struct ieee80211_vif *vif)
 {
 	if (adapter->ps_state != PS_ENABLED) {
 		rsi_dbg(ERR_ZONE,
@@ -95,7 +96,7 @@ void rsi_disable_ps(struct rsi_hw *adapter)
 		return;
 	}
 
-	if (rsi_send_ps_request(adapter, false)) {
+	if (rsi_send_ps_request(adapter, false, vif)) {
 		rsi_dbg(ERR_ZONE,
 			"%s: Failed to send PS request to device\n",
 			__func__);
@@ -105,16 +106,16 @@ void rsi_disable_ps(struct rsi_hw *adapter)
 	rsi_modify_ps_state(adapter, PS_DISABLE_REQ_SENT);
 }
 
-void rsi_conf_uapsd(struct rsi_hw *adapter)
+void rsi_conf_uapsd(struct rsi_hw *adapter, struct ieee80211_vif *vif)
 {
 	int ret;
 
 	if (adapter->ps_state != PS_ENABLED)
 		return;
 
-	ret = rsi_send_ps_request(adapter, false);
+	ret = rsi_send_ps_request(adapter, false, vif);
 	if (!ret)
-		ret = rsi_send_ps_request(adapter, true);
+		ret = rsi_send_ps_request(adapter, true, vif);
 	if (ret)
 		rsi_dbg(ERR_ZONE,
 			"%s: Failed to send PS request to device\n",
diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c
index 8d3a4839b6ef..b3f8006c0e9b 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c
@@ -1059,16 +1059,136 @@ static void rsi_disconnect(struct sdio_func *pfunction)
 }
 
 #ifdef CONFIG_PM
+static int rsi_set_sdio_pm_caps(struct rsi_hw *adapter)
+{
+	struct rsi_91x_sdiodev *dev =
+		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
+	struct sdio_func *func = dev->pfunction;
+	int ret;
+
+	ret = sdio_set_host_pm_flags(func, MMC_PM_KEEP_POWER);
+	if (ret)
+		rsi_dbg(ERR_ZONE, "Set sdio keep pwr flag failed: %d\n", ret);
+
+	return ret;
+}
+
+static int rsi_sdio_disable_interrupts(struct sdio_func *pfunc)
+{
+	struct rsi_hw *adapter = sdio_get_drvdata(pfunc);
+	u8 isr_status = 0, data = 0;
+	int ret;
+	unsigned long t1;
+
+	rsi_dbg(INFO_ZONE, "Waiting for interrupts to be cleared..");
+	t1 = jiffies;
+	do {
+		rsi_sdio_read_register(adapter, RSI_FN1_INT_REGISTER,
+				       &isr_status);
+		rsi_dbg(INFO_ZONE, ".");
+	} while ((isr_status) && (jiffies_to_msecs(jiffies - t1) < 20));
+	rsi_dbg(INFO_ZONE, "Interrupts cleared\n");
+
+	sdio_claim_host(pfunc);
+	ret = rsi_cmd52readbyte(pfunc->card, RSI_INT_ENABLE_REGISTER, &data);
+	if (ret < 0) {
+		rsi_dbg(ERR_ZONE,
+			"%s: Failed to read int enable register\n",
+			__func__);
+		goto done;
+	}
+
+	data &= RSI_INT_ENABLE_MASK;
+	ret = rsi_cmd52writebyte(pfunc->card, RSI_INT_ENABLE_REGISTER, data);
+	if (ret < 0) {
+		rsi_dbg(ERR_ZONE,
+			"%s: Failed to write to int enable register\n",
+			__func__);
+		goto done;
+	}
+	ret = rsi_cmd52readbyte(pfunc->card, RSI_INT_ENABLE_REGISTER, &data);
+	if (ret < 0) {
+		rsi_dbg(ERR_ZONE,
+			"%s: Failed to read int enable register\n",
+			__func__);
+		goto done;
+	}
+	rsi_dbg(INFO_ZONE, "int enable reg content = %x\n", data);
+
+done:
+	sdio_release_host(pfunc);
+	return ret;
+}
+
+static int rsi_sdio_enable_interrupts(struct sdio_func *pfunc)
+{
+	u8 data;
+	int ret;
+
+	sdio_claim_host(pfunc);
+	ret = rsi_cmd52readbyte(pfunc->card, RSI_INT_ENABLE_REGISTER, &data);
+	if (ret < 0) {
+		rsi_dbg(ERR_ZONE,
+			"%s: Failed to read int enable register\n", __func__);
+		goto done;
+	}
+
+	data |= ~RSI_INT_ENABLE_MASK & 0xff;
+
+	ret = rsi_cmd52writebyte(pfunc->card, RSI_INT_ENABLE_REGISTER, data);
+	if (ret < 0) {
+		rsi_dbg(ERR_ZONE,
+			"%s: Failed to write to int enable register\n",
+			__func__);
+		goto done;
+	}
+
+	ret = rsi_cmd52readbyte(pfunc->card, RSI_INT_ENABLE_REGISTER, &data);
+	if (ret < 0) {
+		rsi_dbg(ERR_ZONE,
+			"%s: Failed to read int enable register\n", __func__);
+		goto done;
+	}
+	rsi_dbg(INFO_ZONE, "int enable reg content = %x\n", data);
+
+done:
+	sdio_release_host(pfunc);
+	return ret;
+}
+
 static int rsi_suspend(struct device *dev)
 {
-	/* Not yet implemented */
-	return -ENOSYS;
+	int ret;
+	struct sdio_func *pfunction = dev_to_sdio_func(dev);
+	struct rsi_hw *adapter = sdio_get_drvdata(pfunction);
+	struct rsi_common *common;
+
+	if (!adapter) {
+		rsi_dbg(ERR_ZONE, "Device is not ready\n");
+		return -ENODEV;
+	}
+	common = adapter->priv;
+	rsi_sdio_disable_interrupts(pfunction);
+
+	ret = rsi_set_sdio_pm_caps(adapter);
+	if (ret)
+		rsi_dbg(INFO_ZONE,
+			"Setting power management caps failed\n");
+	common->fsm_state = FSM_CARD_NOT_READY;
+
+	return 0;
 }
 
 static int rsi_resume(struct device *dev)
 {
-	/* Not yet implemented */
-	return -ENOSYS;
+	struct sdio_func *pfunction = dev_to_sdio_func(dev);
+	struct rsi_hw *adapter = sdio_get_drvdata(pfunction);
+	struct rsi_common *common = adapter->priv;
+
+	common->fsm_state = FSM_MAC_INIT_DONE;
+	rsi_sdio_enable_interrupts(pfunction);
+
+	return 0;
 }
 
 static const struct dev_pm_ops rsi_pm_ops = {
diff --git a/drivers/net/wireless/rsi/rsi_91x_usb.c b/drivers/net/wireless/rsi/rsi_91x_usb.c
index 81df09dd2636..08730227cd18 100644
--- a/drivers/net/wireless/rsi/rsi_91x_usb.c
+++ b/drivers/net/wireless/rsi/rsi_91x_usb.c
@@ -73,8 +73,7 @@ static int rsi_write_multiple(struct rsi_hw *adapter,
 			      u8 *data,
 			      u32 count)
 {
-	struct rsi_91x_usbdev *dev =
-		(struct rsi_91x_usbdev *)adapter->rsi_dev;
+	struct rsi_91x_usbdev *dev;
 
 	if (!adapter)
 		return -ENODEV;
@@ -82,6 +81,7 @@ static int rsi_write_multiple(struct rsi_hw *adapter,
 	if (endpoint == 0)
 		return -EINVAL;
 
+	dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
 	if (dev->write_fail)
 		return -ENETDOWN;
 
diff --git a/drivers/net/wireless/rsi/rsi_common.h b/drivers/net/wireless/rsi/rsi_common.h
index e579d694d13c..272e18d750ff 100644
--- a/drivers/net/wireless/rsi/rsi_common.h
+++ b/drivers/net/wireless/rsi/rsi_common.h
@@ -79,9 +79,11 @@ static inline int rsi_kill_thread(struct rsi_thread *handle)
 }
 
 void rsi_mac80211_detach(struct rsi_hw *hw);
-u16 rsi_get_connected_channel(struct rsi_hw *adapter);
+u16 rsi_get_connected_channel(struct ieee80211_vif *vif);
 struct rsi_hw *rsi_91x_init(void);
 void rsi_91x_deinit(struct rsi_hw *adapter);
 int rsi_read_pkt(struct rsi_common *common, s32 rcv_pkt_len);
 struct rsi_sta *rsi_find_sta(struct rsi_common *common, u8 *mac_addr);
+struct ieee80211_vif *rsi_get_vif(struct rsi_hw *adapter, u8 *mac);
+void rsi_roc_timeout(unsigned long data);
 #endif
diff --git a/drivers/net/wireless/rsi/rsi_hal.h b/drivers/net/wireless/rsi/rsi_hal.h
index 7c145053da6d..a09d36b6b765 100644
--- a/drivers/net/wireless/rsi/rsi_hal.h
+++ b/drivers/net/wireless/rsi/rsi_hal.h
@@ -101,6 +101,9 @@
 
 #define BBP_INFO_40MHZ 0x6
 
+#define FW_FLASH_OFFSET			0x820
+#define LMAC_VER_OFFSET			(FW_FLASH_OFFSET + 0x200)
+
 struct bl_header {
 	__le32 flags;
 	__le32 image_no;
@@ -121,8 +124,7 @@ struct rsi_mgmt_desc {
 	u8 xtend_desc_size;
 	u8 header_len;
 	__le16 frame_info;
-	u8 rate_info;
-	u8 reserved1;
+	__le16 rate_info;
 	__le16 bbp_info;
 	__le16 seq_ctrl;
 	u8 reserved2;
diff --git a/drivers/net/wireless/rsi/rsi_main.h b/drivers/net/wireless/rsi/rsi_main.h
index 2c18dde633ea..a118b7aaeca0 100644
--- a/drivers/net/wireless/rsi/rsi_main.h
+++ b/drivers/net/wireless/rsi/rsi_main.h
@@ -60,7 +60,7 @@ enum RSI_FSM_STATES {
 extern u32 rsi_zone_enabled;
 extern __printf(2, 3) void rsi_dbg(u32 zone, const char *fmt, ...);
 
-#define RSI_MAX_VIFS                    1
+#define RSI_MAX_VIFS                    3
 #define NUM_EDCA_QUEUES                 4
 #define IEEE80211_ADDR_LEN              6
 #define FRAME_DESC_SZ                   16
@@ -113,8 +113,13 @@ extern __printf(2, 3) void rsi_dbg(u32 zone, const char *fmt, ...);
 struct version_info {
 	u16 major;
 	u16 minor;
-	u16 release_num;
-	u16 patch_num;
+	u8 release_num;
+	u8 patch_num;
+	union {
+		struct {
+			u8 fw_ver[8];
+		} info;
+	} ver;
 } __packed;
 
 struct skb_info {
@@ -124,6 +129,8 @@ struct skb_info {
 	s8 tid;
 	s8 sta_id;
 	u8 internal_hdr_size;
+	struct ieee80211_vif *vif;
+	u8 vap_id;
 };
 
 enum edca_queue {
@@ -157,6 +164,7 @@ struct vif_priv {
 	bool is_ht;
 	bool sgi;
 	u16 seq_start;
+	int vap_id;
 };
 
 struct rsi_event {
@@ -196,8 +204,7 @@ struct rsi_common {
 	struct vif_priv vif_info[RSI_MAX_VIFS];
 
 	bool mgmt_q_block;
-	struct version_info driver_ver;
-	struct version_info fw_ver;
+	struct version_info lmac_ver;
 
 	struct rsi_thread tx_thread;
 	struct sk_buff_head tx_queue[NUM_EDCA_QUEUES + 2];
@@ -270,6 +277,11 @@ struct rsi_common {
 	int num_stations;
 	int max_stations;
 	struct ieee80211_key_conf *key;
+
+	/* Wi-Fi direct mode related */
+	bool p2p_enabled;
+	struct timer_list roc_timer;
+	struct ieee80211_vif *roc_vif;
 };
 
 enum host_intf {
@@ -326,6 +338,8 @@ struct rsi_hw {
 	int (*determine_event_timeout)(struct rsi_hw *adapter);
 };
 
+void rsi_print_version(struct rsi_common *common);
+
 struct rsi_host_intf_ops {
 	int (*read_pkt)(struct rsi_hw *adapter, u8 *pkt, u32 len);
 	int (*write_pkt)(struct rsi_hw *adapter, u8 *pkt, u32 len);
diff --git a/drivers/net/wireless/rsi/rsi_mgmt.h b/drivers/net/wireless/rsi/rsi_mgmt.h
index c6e1fa669a27..e21723013f8d 100644
--- a/drivers/net/wireless/rsi/rsi_mgmt.h
+++ b/drivers/net/wireless/rsi/rsi_mgmt.h
@@ -189,6 +189,8 @@
 	 IEEE80211_WMM_IE_STA_QOSINFO_AC_BE | \
 	 IEEE80211_WMM_IE_STA_QOSINFO_AC_BK)
 
+#define RSI_DESC_VAP_ID_MASK		0xC000u
+#define RSI_DESC_VAP_ID_OFST		14
 #define RSI_DATA_DESC_MAC_BBP_INFO	BIT(0)
 #define RSI_DATA_DESC_NO_ACK_IND	BIT(9)
 #define RSI_DATA_DESC_QOS_EN		BIT(12)
@@ -200,8 +202,11 @@
 #define RSI_DATA_DESC_INSERT_SEQ_NO	BIT(2)
 
 enum opmode {
-	AP_OPMODE = 0,
-	STA_OPMODE,
+	RSI_OPMODE_UNSUPPORTED = -1,
+	RSI_OPMODE_AP = 0,
+	RSI_OPMODE_STA,
+	RSI_OPMODE_P2P_GO,
+	RSI_OPMODE_P2P_CLIENT
 };
 
 enum vap_status {
@@ -363,9 +368,9 @@ struct rsi_vap_caps {
 	u8 vif_type;
 	u8 channel_bw;
 	__le16 antenna_info;
+	__le16 token;
 	u8 radioid_macid;
 	u8 vap_id;
-	__le16 reserved3;
 	u8 mac_addr[6];
 	__le16 keep_alive_period;
 	u8 bssid[6];
@@ -613,14 +618,16 @@ int rsi_send_aggregation_params_frame(struct rsi_common *common, u16 tid,
 				      u16 ssn, u8 buf_size, u8 event,
 				      u8 sta_id);
 int rsi_hal_load_key(struct rsi_common *common, u8 *data, u16 key_len,
-		     u8 key_type, u8 key_id, u32 cipher, s16 sta_id);
+		     u8 key_type, u8 key_id, u32 cipher, s16 sta_id,
+		     struct ieee80211_vif *vif);
 int rsi_set_channel(struct rsi_common *common,
 		    struct ieee80211_channel *channel);
 int rsi_send_vap_dynamic_update(struct rsi_common *common);
 int rsi_send_block_unblock_frame(struct rsi_common *common, bool event);
 void rsi_inform_bss_status(struct rsi_common *common, enum opmode opmode,
 			   u8 status, const u8 *addr, u8 qos_enable, u16 aid,
-			   struct ieee80211_sta *sta, u16 sta_id);
+			   struct ieee80211_sta *sta, u16 sta_id,
+			   struct ieee80211_vif *vif);
 void rsi_indicate_pkt_to_os(struct rsi_common *common, struct sk_buff *skb);
 int rsi_mac80211_attach(struct rsi_common *common);
 void rsi_indicate_tx_status(struct rsi_hw *common, struct sk_buff *skb,
@@ -630,8 +637,10 @@ void rsi_core_qos_processor(struct rsi_common *common);
 void rsi_core_xmit(struct rsi_common *common, struct sk_buff *skb);
 int rsi_send_mgmt_pkt(struct rsi_common *common, struct sk_buff *skb);
 int rsi_send_data_pkt(struct rsi_common *common, struct sk_buff *skb);
-int rsi_band_check(struct rsi_common *common);
+int rsi_band_check(struct rsi_common *common, struct ieee80211_channel *chan);
 int rsi_send_rx_filter_frame(struct rsi_common *common, u16 rx_filter_word);
 int rsi_send_radio_params_update(struct rsi_common *common);
 int rsi_set_antenna(struct rsi_common *common, u8 antenna);
+int rsi_send_ps_request(struct rsi_hw *adapter, bool enable,
+			struct ieee80211_vif *vif);
 #endif
diff --git a/drivers/net/wireless/rsi/rsi_ps.h b/drivers/net/wireless/rsi/rsi_ps.h
index d8475873df36..98ff6a4ced57 100644
--- a/drivers/net/wireless/rsi/rsi_ps.h
+++ b/drivers/net/wireless/rsi/rsi_ps.h
@@ -55,10 +55,9 @@ struct rsi_ps_info {
 } __packed;
 
 char *str_psstate(enum ps_state state);
-void rsi_enable_ps(struct rsi_hw *adapter);
-void rsi_disable_ps(struct rsi_hw *adapter);
+void rsi_enable_ps(struct rsi_hw *adapter, struct ieee80211_vif *vif);
+void rsi_disable_ps(struct rsi_hw *adapter, struct ieee80211_vif *vif);
 int rsi_handle_ps_confirm(struct rsi_hw *adapter, u8 *msg);
 void rsi_default_ps_params(struct rsi_hw *hw);
-int rsi_send_ps_request(struct rsi_hw *adapter, bool enable);
-void rsi_conf_uapsd(struct rsi_hw *adapter);
+void rsi_conf_uapsd(struct rsi_hw *adapter, struct ieee80211_vif *vif);
 #endif
diff --git a/drivers/net/wireless/rsi/rsi_sdio.h b/drivers/net/wireless/rsi/rsi_sdio.h
index 95e4bed57baf..49c549ba6682 100644
--- a/drivers/net/wireless/rsi/rsi_sdio.h
+++ b/drivers/net/wireless/rsi/rsi_sdio.h
@@ -48,6 +48,8 @@ enum sdio_interrupt_type {
 
 #define RSI_DEVICE_BUFFER_STATUS_REGISTER       0xf3
 #define RSI_FN1_INT_REGISTER                    0xf9
+#define RSI_INT_ENABLE_REGISTER			0x04
+#define RSI_INT_ENABLE_MASK			0xfc
 #define RSI_SD_REQUEST_MASTER                   0x10000
 
 /* FOR SD CARD ONLY */
diff --git a/drivers/net/wireless/st/cw1200/pm.c b/drivers/net/wireless/st/cw1200/pm.c
index d2202ae92bdd..ded23df1ac1d 100644
--- a/drivers/net/wireless/st/cw1200/pm.c
+++ b/drivers/net/wireless/st/cw1200/pm.c
@@ -91,7 +91,7 @@ struct cw1200_suspend_state {
 	u8 prev_ps_mode;
 };
 
-static void cw1200_pm_stay_awake_tmo(unsigned long arg)
+static void cw1200_pm_stay_awake_tmo(struct timer_list *unused)
 {
 	/* XXX what's the point of this ? */
 }
@@ -101,8 +101,7 @@ int cw1200_pm_init(struct cw1200_pm_state *pm,
 {
 	spin_lock_init(&pm->lock);
 
-	setup_timer(&pm->stay_awake, cw1200_pm_stay_awake_tmo,
-		    (unsigned long)pm);
+	timer_setup(&pm->stay_awake, cw1200_pm_stay_awake_tmo, 0);
 
 	return 0;
 }
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 5b1d2e8402d9..a46a1e94505d 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -307,7 +307,7 @@ static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif)
 	return to_xenbus_device(vif->dev->dev.parent);
 }
 
-void xenvif_tx_credit_callback(unsigned long data);
+void xenvif_tx_credit_callback(struct timer_list *t);
 
 struct xenvif *xenvif_alloc(struct device *parent,
 			    domid_t domid,
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 4491ca5aee90..d6dff347f896 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -520,8 +520,7 @@ int xenvif_init_queue(struct xenvif_queue *queue)
 
 	queue->credit_bytes = queue->remaining_credit = ~0UL;
 	queue->credit_usec  = 0UL;
-	init_timer(&queue->credit_timeout);
-	queue->credit_timeout.function = xenvif_tx_credit_callback;
+	timer_setup(&queue->credit_timeout, xenvif_tx_credit_callback, 0);
 	queue->credit_window_start = get_jiffies_64();
 
 	queue->rx_queue_max = XENVIF_RX_QUEUE_BYTES;
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 5042ff8d449a..a27daa23c9dc 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -183,9 +183,9 @@ static void tx_add_credit(struct xenvif_queue *queue)
 	queue->rate_limited = false;
 }
 
-void xenvif_tx_credit_callback(unsigned long data)
+void xenvif_tx_credit_callback(struct timer_list *t)
 {
-	struct xenvif_queue *queue = (struct xenvif_queue *)data;
+	struct xenvif_queue *queue = from_timer(queue, t, credit_timeout);
 	tx_add_credit(queue);
 	xenvif_napi_schedule_or_enable_events(queue);
 }
@@ -700,8 +700,6 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size)
 
 	/* Still too big to send right now? Set a callback. */
 	if (size > queue->remaining_credit) {
-		queue->credit_timeout.data     =
-			(unsigned long)queue;
 		mod_timer(&queue->credit_timeout,
 			  next_credit);
 		queue->credit_window_start = next_credit;
diff --git a/drivers/pcmcia/electra_cf.c b/drivers/pcmcia/electra_cf.c
index c6fe2a4a7a6a..9671ded549f0 100644
--- a/drivers/pcmcia/electra_cf.c
+++ b/drivers/pcmcia/electra_cf.c
@@ -79,9 +79,9 @@ static int electra_cf_ss_init(struct pcmcia_socket *s)
 }
 
 /* the timer is primarily to kick this socket's pccardd */
-static void electra_cf_timer(unsigned long _cf)
+static void electra_cf_timer(struct timer_list *t)
 {
-	struct electra_cf_socket *cf = (void *) _cf;
+	struct electra_cf_socket *cf = from_timer(cf, t, timer);
 	int present = electra_cf_present(cf);
 
 	if (present != cf->present) {
@@ -95,7 +95,9 @@ static void electra_cf_timer(unsigned long _cf)
 
 static irqreturn_t electra_cf_irq(int irq, void *_cf)
 {
-	electra_cf_timer((unsigned long)_cf);
+	struct electra_cf_socket *cf = _cf;
+
+	electra_cf_timer(&cf->timer);
 	return IRQ_HANDLED;
 }
 
@@ -206,7 +208,7 @@ static int electra_cf_probe(struct platform_device *ofdev)
 	if (!cf)
 		return -ENOMEM;
 
-	setup_timer(&cf->timer, electra_cf_timer, (unsigned long)cf);
+	timer_setup(&cf->timer, electra_cf_timer, 0);
 	cf->irq = 0;
 
 	cf->ofdev = ofdev;
@@ -305,7 +307,7 @@ static int electra_cf_probe(struct platform_device *ofdev)
 		 cf->mem_phys, io.start, cf->irq);
 
 	cf->active = 1;
-	electra_cf_timer((unsigned long)cf);
+	electra_cf_timer(&cf->timer);
 	return 0;
 
 fail3:
diff --git a/drivers/s390/net/fsm.c b/drivers/s390/net/fsm.c
index e5dea67f902e..8c14c6c3ad3d 100644
--- a/drivers/s390/net/fsm.c
+++ b/drivers/s390/net/fsm.c
@@ -170,9 +170,7 @@ fsm_addtimer(fsm_timer *this, int millisec, int event, void *arg)
 	       this->fi->name, this, millisec);
 #endif
 
-	init_timer(&this->tl);
-	this->tl.function = (void *)fsm_expire_timer;
-	this->tl.data = (long)this;
+	setup_timer(&this->tl, (void *)fsm_expire_timer, (long)this);
 	this->expire_event = event;
 	this->event_arg = arg;
 	this->tl.expires = jiffies + (millisec * HZ) / 1000;
@@ -191,9 +189,7 @@ fsm_modtimer(fsm_timer *this, int millisec, int event, void *arg)
 #endif
 
 	del_timer(&this->tl);
-	init_timer(&this->tl);
-	this->tl.function = (void *)fsm_expire_timer;
-	this->tl.data = (long)this;
+	setup_timer(&this->tl, (void *)fsm_expire_timer, (long)this);
 	this->expire_event = event;
 	this->event_arg = arg;
 	this->tl.expires = jiffies + (millisec * HZ) / 1000;
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 47a13c5723c6..9cd569ef43ec 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -183,6 +183,21 @@ struct qeth_sbp_info {
 	__u32 reflect_promisc_primary:1;
 };
 
+struct qeth_vnicc_info {
+	/* supported/currently configured VNICCs; updated in IPA exchanges */
+	u32 sup_chars;
+	u32 cur_chars;
+	/* supported commands: bitmasks which VNICCs support respective cmd */
+	u32 set_char_sup;
+	u32 getset_timeout_sup;
+	/* timeout value for the learning characteristic */
+	u32 learning_timeout;
+	/* characteristics wanted/configured by user */
+	u32 wanted_chars;
+	/* has user explicitly enabled rx_bcast while online? */
+	bool rx_bcast_enabled;
+};
+
 static inline int qeth_is_ipa_supported(struct qeth_ipa_info *ipa,
 		enum qeth_ipa_funcs func)
 {
@@ -217,20 +232,6 @@ static inline int qeth_is_ipa_enabled(struct qeth_ipa_info *ipa,
 #define QETH_IDX_FUNC_LEVEL_OSD		 0x0101
 #define QETH_IDX_FUNC_LEVEL_IQD		 0x4108
 
-#define QETH_MODELLIST_ARRAY \
-	{{0x1731, 0x01, 0x1732, QETH_CARD_TYPE_OSD, QETH_MAX_QUEUES, 0}, \
-	 {0x1731, 0x05, 0x1732, QETH_CARD_TYPE_IQD, QETH_MAX_QUEUES, 0x103}, \
-	 {0x1731, 0x06, 0x1732, QETH_CARD_TYPE_OSN, QETH_MAX_QUEUES, 0}, \
-	 {0x1731, 0x02, 0x1732, QETH_CARD_TYPE_OSM, QETH_MAX_QUEUES, 0}, \
-	 {0x1731, 0x02, 0x1732, QETH_CARD_TYPE_OSX, QETH_MAX_QUEUES, 0}, \
-	 {0, 0, 0, 0, 0, 0} }
-#define QETH_CU_TYPE_IND	0
-#define QETH_CU_MODEL_IND	1
-#define QETH_DEV_TYPE_IND	2
-#define QETH_DEV_MODEL_IND	3
-#define QETH_QUEUE_NO_IND	4
-#define QETH_MULTICAST_IND	5
-
 #define QETH_REAL_CARD		1
 #define QETH_VLAN_CARD		2
 #define QETH_BUFSIZE		4096
@@ -674,6 +675,7 @@ struct qeth_card_options {
 	struct qeth_routing_info route6;
 	struct qeth_ipa_info ipa6;
 	struct qeth_sbp_info sbp; /* SETBRIDGEPORT options */
+	struct qeth_vnicc_info vnicc; /* VNICC options */
 	int fake_broadcast;
 	int layer2;
 	int performance_stats;
@@ -947,13 +949,13 @@ int qeth_get_priority_queue(struct qeth_card *, struct sk_buff *, int, int);
 int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb,
 			 int extra_elems, int data_offset);
 int qeth_get_elements_for_frags(struct sk_buff *);
-int qeth_do_send_packet_fast(struct qeth_card *card,
-			     struct qeth_qdio_out_q *queue, struct sk_buff *skb,
+int qeth_do_send_packet_fast(struct qeth_qdio_out_q *queue, struct sk_buff *skb,
 			     struct qeth_hdr *hdr, unsigned int offset,
 			     unsigned int hd_len);
 int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue,
 			struct sk_buff *skb, struct qeth_hdr *hdr,
-			unsigned int hd_len, unsigned int offset, int elements);
+			unsigned int offset, unsigned int hd_len,
+			int elements_needed);
 int qeth_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
 int qeth_core_get_sset_count(struct net_device *, int);
 void qeth_core_get_ethtool_stats(struct net_device *,
@@ -983,7 +985,7 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *,
 						 __u16, __u16,
 						 enum qeth_prot_versions);
 int qeth_set_features(struct net_device *, netdev_features_t);
-int qeth_recover_features(struct net_device *);
+void qeth_recover_features(struct net_device *dev);
 netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
 int qeth_vm_request_mac(struct qeth_card *card);
 int qeth_push_hdr(struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int len);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index bae7440abc01..457a4b4e8212 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -52,7 +52,6 @@ EXPORT_SYMBOL_GPL(qeth_core_header_cache);
 static struct kmem_cache *qeth_qdio_outbuf_cache;
 
 static struct device *qeth_core_root_dev;
-static unsigned int known_devices[][6] = QETH_MODELLIST_ARRAY;
 static struct lock_class_key qdio_out_skb_queue_key;
 static struct mutex qeth_mod_mutex;
 
@@ -1386,6 +1385,7 @@ static void qeth_init_qdio_info(struct qeth_card *card)
 	QETH_DBF_TEXT(SETUP, 4, "intqdinf");
 	atomic_set(&card->qdio.state, QETH_QDIO_UNINITIALIZED);
 	/* inbound */
+	card->qdio.no_in_queues = 1;
 	card->qdio.in_buf_size = QETH_IN_BUF_SIZE_DEFAULT;
 	if (card->info.type == QETH_CARD_TYPE_IQD)
 		card->qdio.init_pool.buf_count = QETH_IN_BUF_COUNT_HSDEFAULT;
@@ -1519,34 +1519,17 @@ out:
 	return NULL;
 }
 
-static int qeth_determine_card_type(struct qeth_card *card)
+static void qeth_determine_card_type(struct qeth_card *card)
 {
-	int i = 0;
-
 	QETH_DBF_TEXT(SETUP, 2, "detcdtyp");
 
 	card->qdio.do_prio_queueing = QETH_PRIOQ_DEFAULT;
 	card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
-	while (known_devices[i][QETH_DEV_MODEL_IND]) {
-		if ((CARD_RDEV(card)->id.dev_type ==
-				known_devices[i][QETH_DEV_TYPE_IND]) &&
-		    (CARD_RDEV(card)->id.dev_model ==
-				known_devices[i][QETH_DEV_MODEL_IND])) {
-			card->info.type = known_devices[i][QETH_DEV_MODEL_IND];
-			card->qdio.no_out_queues =
-				known_devices[i][QETH_QUEUE_NO_IND];
-			card->qdio.no_in_queues = 1;
-			card->info.is_multicast_different =
-				known_devices[i][QETH_MULTICAST_IND];
-			qeth_update_from_chp_desc(card);
-			return 0;
-		}
-		i++;
-	}
-	card->info.type = QETH_CARD_TYPE_UNKNOWN;
-	dev_err(&card->gdev->dev, "The adapter hardware is of an "
-		"unknown type\n");
-	return -ENOENT;
+	card->info.type = CARD_RDEV(card)->id.driver_info;
+	card->qdio.no_out_queues = QETH_MAX_QUEUES;
+	if (card->info.type == QETH_CARD_TYPE_IQD)
+		card->info.is_multicast_different = 0x0103;
+	qeth_update_from_chp_desc(card);
 }
 
 static int qeth_clear_channel(struct qeth_channel *channel)
@@ -2090,7 +2073,6 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 	spin_lock_irqsave(&card->lock, flags);
 	list_add_tail(&reply->list, &card->cmd_waiter_list);
 	spin_unlock_irqrestore(&card->lock, flags);
-	QETH_DBF_HEX(CTRL, 2, iob->data, QETH_DBF_CTRL_LEN);
 
 	while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ;
 	qeth_prepare_control_data(card, len, iob);
@@ -2233,23 +2215,15 @@ static int qeth_cm_setup(struct qeth_card *card)
 static int qeth_get_initial_mtu_for_card(struct qeth_card *card)
 {
 	switch (card->info.type) {
-	case QETH_CARD_TYPE_UNKNOWN:
-		return 1500;
 	case QETH_CARD_TYPE_IQD:
 		return card->info.max_mtu;
 	case QETH_CARD_TYPE_OSD:
-		switch (card->info.link_type) {
-		case QETH_LINK_TYPE_HSTR:
-		case QETH_LINK_TYPE_LANE_TR:
-			return 2000;
-		default:
-			return card->options.layer2 ? 1500 : 1492;
-		}
-	case QETH_CARD_TYPE_OSM:
 	case QETH_CARD_TYPE_OSX:
-		return card->options.layer2 ? 1500 : 1492;
+		if (!card->options.layer2)
+			return ETH_DATA_LEN - 8; /* L3: allow for LLC + SNAP */
+		/* fall through */
 	default:
-		return 1500;
+		return ETH_DATA_LEN;
 	}
 }
 
@@ -2279,7 +2253,6 @@ static int qeth_mtu_is_valid(struct qeth_card *card, int mtu)
 		return ((mtu >= 576) &&
 			(mtu <= card->info.max_mtu));
 	case QETH_CARD_TYPE_OSN:
-	case QETH_CARD_TYPE_UNKNOWN:
 	default:
 		return 1;
 	}
@@ -4040,35 +4013,23 @@ static int qeth_fill_buffer(struct qeth_qdio_out_q *queue,
 	return flush_cnt;
 }
 
-int qeth_do_send_packet_fast(struct qeth_card *card,
-			     struct qeth_qdio_out_q *queue, struct sk_buff *skb,
+int qeth_do_send_packet_fast(struct qeth_qdio_out_q *queue, struct sk_buff *skb,
 			     struct qeth_hdr *hdr, unsigned int offset,
 			     unsigned int hd_len)
 {
-	struct qeth_qdio_out_buffer *buffer;
-	int index;
+	int index = queue->next_buf_to_fill;
+	struct qeth_qdio_out_buffer *buffer = queue->bufs[index];
 
-	/* spin until we get the queue ... */
-	while (atomic_cmpxchg(&queue->state, QETH_OUT_Q_UNLOCKED,
-			      QETH_OUT_Q_LOCKED) != QETH_OUT_Q_UNLOCKED);
-	/* ... now we've got the queue */
-	index = queue->next_buf_to_fill;
-	buffer = queue->bufs[queue->next_buf_to_fill];
 	/*
 	 * check if buffer is empty to make sure that we do not 'overtake'
 	 * ourselves and try to fill a buffer that is already primed
 	 */
 	if (atomic_read(&buffer->state) != QETH_QDIO_BUF_EMPTY)
-		goto out;
-	queue->next_buf_to_fill = (queue->next_buf_to_fill + 1) %
-					  QDIO_MAX_BUFFERS_PER_Q;
-	atomic_set(&queue->state, QETH_OUT_Q_UNLOCKED);
+		return -EBUSY;
+	queue->next_buf_to_fill = (index + 1) % QDIO_MAX_BUFFERS_PER_Q;
 	qeth_fill_buffer(queue, buffer, skb, hdr, offset, hd_len);
 	qeth_flush_buffers(queue, index, 1);
 	return 0;
-out:
-	atomic_set(&queue->state, QETH_OUT_Q_UNLOCKED);
-	return -EBUSY;
 }
 EXPORT_SYMBOL_GPL(qeth_do_send_packet_fast);
 
@@ -4923,7 +4884,6 @@ static void qeth_qdio_establish_cq(struct qeth_card *card,
 	if (card->options.cq == QETH_CQ_ENABLED) {
 		int offset = QDIO_MAX_BUFFERS_PER_Q *
 			     (card->qdio.no_in_queues - 1);
-		i = QDIO_MAX_BUFFERS_PER_Q * (card->qdio.no_in_queues - 1);
 		for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; ++i) {
 			in_sbal_ptrs[offset + i] = (struct qdio_buffer *)
 				virt_to_phys(card->qdio.c_q->bufs[i].buffer);
@@ -5209,49 +5169,27 @@ out:
 }
 EXPORT_SYMBOL_GPL(qeth_core_hardsetup_card);
 
-static int qeth_create_skb_frag(struct qeth_qdio_buffer *qethbuffer,
-				struct qdio_buffer_element *element,
-				struct sk_buff **pskb, int offset, int *pfrag,
-				int data_len)
+static void qeth_create_skb_frag(struct qdio_buffer_element *element,
+				 struct sk_buff *skb, int offset, int data_len)
 {
 	struct page *page = virt_to_page(element->addr);
-	if (*pskb == NULL) {
-		if (qethbuffer->rx_skb) {
-			/* only if qeth_card.options.cq == QETH_CQ_ENABLED */
-			*pskb = qethbuffer->rx_skb;
-			qethbuffer->rx_skb = NULL;
-		} else {
-			*pskb = dev_alloc_skb(QETH_RX_PULL_LEN + ETH_HLEN);
-			if (!(*pskb))
-				return -ENOMEM;
-		}
+	unsigned int next_frag;
 
-		skb_reserve(*pskb, ETH_HLEN);
-		if (data_len <= QETH_RX_PULL_LEN) {
-			skb_put_data(*pskb, element->addr + offset, data_len);
-		} else {
-			get_page(page);
-			skb_put_data(*pskb, element->addr + offset,
-				     QETH_RX_PULL_LEN);
-			skb_fill_page_desc(*pskb, *pfrag, page,
-				offset + QETH_RX_PULL_LEN,
-				data_len - QETH_RX_PULL_LEN);
-			(*pskb)->data_len += data_len - QETH_RX_PULL_LEN;
-			(*pskb)->len      += data_len - QETH_RX_PULL_LEN;
-			(*pskb)->truesize += data_len - QETH_RX_PULL_LEN;
-			(*pfrag)++;
-		}
-	} else {
-		get_page(page);
-		skb_fill_page_desc(*pskb, *pfrag, page, offset, data_len);
-		(*pskb)->data_len += data_len;
-		(*pskb)->len      += data_len;
-		(*pskb)->truesize += data_len;
-		(*pfrag)++;
-	}
+	/* first fill the linear space */
+	if (!skb->len) {
+		unsigned int linear = min(data_len, skb_tailroom(skb));
 
+		skb_put_data(skb, element->addr + offset, linear);
+		data_len -= linear;
+		if (!data_len)
+			return;
+		offset += linear;
+		/* fall through to add page frag for remaining data */
+	}
 
-	return 0;
+	next_frag = skb_shinfo(skb)->nr_frags;
+	get_page(page);
+	skb_add_rx_frag(skb, next_frag, page, offset, data_len, data_len);
 }
 
 static inline int qeth_is_last_sbale(struct qdio_buffer_element *sbale)
@@ -5267,22 +5205,19 @@ struct sk_buff *qeth_core_get_next_skb(struct qeth_card *card,
 	struct qdio_buffer_element *element = *__element;
 	struct qdio_buffer *buffer = qethbuffer->buffer;
 	int offset = *__offset;
-	struct sk_buff *skb = NULL;
+	struct sk_buff *skb;
 	int skb_len = 0;
 	void *data_ptr;
 	int data_len;
 	int headroom = 0;
 	int use_rx_sg = 0;
-	int frag = 0;
 
 	/* qeth_hdr must not cross element boundaries */
-	if (element->length < offset + sizeof(struct qeth_hdr)) {
+	while (element->length < offset + sizeof(struct qeth_hdr)) {
 		if (qeth_is_last_sbale(element))
 			return NULL;
 		element++;
 		offset = 0;
-		if (element->length < sizeof(struct qeth_hdr))
-			return NULL;
 	}
 	*hdr = element->addr + offset;
 
@@ -5309,27 +5244,32 @@ struct sk_buff *qeth_core_get_next_skb(struct qeth_card *card,
 	if (((skb_len >= card->options.rx_sg_cb) &&
 	     (!(card->info.type == QETH_CARD_TYPE_OSN)) &&
 	     (!atomic_read(&card->force_alloc_skb))) ||
-	    (card->options.cq == QETH_CQ_ENABLED)) {
+	    (card->options.cq == QETH_CQ_ENABLED))
 		use_rx_sg = 1;
+
+	if (use_rx_sg && qethbuffer->rx_skb) {
+		/* QETH_CQ_ENABLED only: */
+		skb = qethbuffer->rx_skb;
+		qethbuffer->rx_skb = NULL;
 	} else {
-		skb = dev_alloc_skb(skb_len + headroom);
-		if (!skb)
-			goto no_mem;
-		if (headroom)
-			skb_reserve(skb, headroom);
+		unsigned int linear = (use_rx_sg) ? QETH_RX_PULL_LEN : skb_len;
+
+		skb = dev_alloc_skb(linear + headroom);
 	}
+	if (!skb)
+		goto no_mem;
+	if (headroom)
+		skb_reserve(skb, headroom);
 
 	data_ptr = element->addr + offset;
 	while (skb_len) {
 		data_len = min(skb_len, (int)(element->length - offset));
 		if (data_len) {
-			if (use_rx_sg) {
-				if (qeth_create_skb_frag(qethbuffer, element,
-				    &skb, offset, &frag, data_len))
-					goto no_mem;
-			} else {
+			if (use_rx_sg)
+				qeth_create_skb_frag(element, skb, offset,
+						     data_len);
+			else
 				skb_put_data(skb, data_ptr, data_len);
-			}
 		}
 		skb_len -= data_len;
 		if (skb_len) {
@@ -5429,7 +5369,7 @@ int qeth_poll(struct napi_struct *napi, int budget)
 		}
 	}
 
-	napi_complete(napi);
+	napi_complete_done(napi, work_done);
 	if (qdio_start_irq(card->data.ccwdev, 0))
 		napi_schedule(&card->napi);
 out:
@@ -5737,11 +5677,7 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 	gdev->cdev[1]->handler = qeth_irq;
 	gdev->cdev[2]->handler = qeth_irq;
 
-	rc = qeth_determine_card_type(card);
-	if (rc) {
-		QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc);
-		goto err_card;
-	}
+	qeth_determine_card_type(card);
 	rc = qeth_setup_card(card);
 	if (rc) {
 		QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc);
@@ -6416,32 +6352,29 @@ static int qeth_set_ipa_tso(struct qeth_card *card, int on)
 	return rc;
 }
 
-/* try to restore device features on a device after recovery */
-int qeth_recover_features(struct net_device *dev)
+#define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO)
+
+/**
+ * qeth_recover_features() - Restore device features after recovery
+ * @dev:	the recovering net_device
+ *
+ * Caller must hold rtnl lock.
+ */
+void qeth_recover_features(struct net_device *dev)
 {
+	netdev_features_t features = dev->features;
 	struct qeth_card *card = dev->ml_priv;
-	netdev_features_t recover = dev->features;
 
-	if (recover & NETIF_F_IP_CSUM) {
-		if (qeth_set_ipa_csum(card, 1, IPA_OUTBOUND_CHECKSUM))
-			recover ^= NETIF_F_IP_CSUM;
-	}
-	if (recover & NETIF_F_RXCSUM) {
-		if (qeth_set_ipa_csum(card, 1, IPA_INBOUND_CHECKSUM))
-			recover ^= NETIF_F_RXCSUM;
-	}
-	if (recover & NETIF_F_TSO) {
-		if (qeth_set_ipa_tso(card, 1))
-			recover ^= NETIF_F_TSO;
-	}
-
-	if (recover == dev->features)
-		return 0;
+	/* force-off any feature that needs an IPA sequence.
+	 * netdev_update_features() will restart them.
+	 */
+	dev->features &= ~QETH_HW_FEATURES;
+	netdev_update_features(dev);
 
+	if (features == dev->features)
+		return;
 	dev_warn(&card->gdev->dev,
 		 "Device recovery failed to restore all offload features\n");
-	dev->features = recover;
-	return -EIO;
 }
 EXPORT_SYMBOL_GPL(qeth_recover_features);
 
@@ -6498,8 +6431,7 @@ netdev_features_t qeth_fix_features(struct net_device *dev,
 	/* if the card isn't up, remove features that require hw changes */
 	if (card->state == CARD_STATE_DOWN ||
 	    card->state == CARD_STATE_RECOVER)
-		features = features & ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
-					NETIF_F_TSO);
+		features &= ~QETH_HW_FEATURES;
 	QETH_DBF_HEX(SETUP, 2, &features, sizeof(features));
 	return features;
 }
diff --git a/drivers/s390/net/qeth_core_mpc.c b/drivers/s390/net/qeth_core_mpc.c
index dafb8c643426..22428b769f9b 100644
--- a/drivers/s390/net/qeth_core_mpc.c
+++ b/drivers/s390/net/qeth_core_mpc.c
@@ -168,7 +168,7 @@ static struct ipa_rc_msg qeth_ipa_rc_msg[] = {
 	{IPA_RC_IP_TABLE_FULL,		"Add Addr IP Table Full - ipv6"},
 	{IPA_RC_UNKNOWN_ERROR,		"IPA command failed - reason unknown"},
 	{IPA_RC_UNSUPPORTED_COMMAND,	"Command not supported"},
-	{IPA_RC_TRACE_ALREADY_ACTIVE,	"trace already active"},
+	{IPA_RC_VNICC_OOSEQ,		"Command issued out of sequence"},
 	{IPA_RC_INVALID_FORMAT,		"invalid format or length"},
 	{IPA_RC_DUP_IPV6_REMOTE, "ipv6 address already registered remote"},
 	{IPA_RC_SBP_IQD_NOT_CONFIGURED,	"Not configured for bridgeport"},
@@ -194,6 +194,7 @@ static struct ipa_rc_msg qeth_ipa_rc_msg[] = {
 	{IPA_RC_L2_INVALID_VLAN_ID,	"L2 invalid vlan id"},
 	{IPA_RC_L2_DUP_VLAN_ID,		"L2 duplicate vlan id"},
 	{IPA_RC_L2_VLAN_ID_NOT_FOUND,	"L2 vlan id not found"},
+	{IPA_RC_VNICC_VNICBP,		"VNIC is BridgePort"},
 	{IPA_RC_SBP_OSA_NOT_CONFIGURED,	"Not configured for bridgeport"},
 	{IPA_RC_SBP_OSA_OS_MISMATCH,	"OS mismatch"},
 	{IPA_RC_SBP_OSA_ANO_DEV_PRIMARY, "Primary bridgeport exists already"},
@@ -254,6 +255,7 @@ static struct ipa_cmd_names qeth_ipa_cmd_names[] = {
 	{IPA_CMD_DELGMAC,	"delgmac"},
 	{IPA_CMD_SETVLAN,	"setvlan"},
 	{IPA_CMD_DELVLAN,	"delvlan"},
+	{IPA_CMD_VNICC,		"vnic_characteristics"},
 	{IPA_CMD_SETBRIDGEPORT_OSA,	"set_bridge_port(osa)"},
 	{IPA_CMD_SETCCID,	"setccid"},
 	{IPA_CMD_DELCCID,	"delccid"},
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index 55f3d234ea1d..ff6877f7b6f8 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -45,7 +45,6 @@ extern unsigned char IPA_PDU_HEADER[];
 #define IPA_CMD_PRIM_VERSION_NO 0x01
 
 enum qeth_card_types {
-	QETH_CARD_TYPE_UNKNOWN = 0,
 	QETH_CARD_TYPE_OSD     = 1,
 	QETH_CARD_TYPE_IQD     = 5,
 	QETH_CARD_TYPE_OSN     = 6,
@@ -91,6 +90,7 @@ enum qeth_ipa_cmds {
 	IPA_CMD_DELGMAC			= 0x24,
 	IPA_CMD_SETVLAN			= 0x25,
 	IPA_CMD_DELVLAN			= 0x26,
+	IPA_CMD_VNICC			= 0x2a,
 	IPA_CMD_SETBRIDGEPORT_OSA	= 0x2b,
 	IPA_CMD_SETCCID			= 0x41,
 	IPA_CMD_DELCCID			= 0x42,
@@ -166,6 +166,8 @@ enum qeth_ipa_return_codes {
 	IPA_RC_L2_INVALID_VLAN_ID	= 0x2015,
 	IPA_RC_L2_DUP_VLAN_ID		= 0x2016,
 	IPA_RC_L2_VLAN_ID_NOT_FOUND	= 0x2017,
+	IPA_RC_L2_VLAN_ID_NOT_ALLOWED	= 0x2050,
+	IPA_RC_VNICC_VNICBP		= 0x20B0,
 	IPA_RC_SBP_OSA_NOT_CONFIGURED	= 0x2B0C,
 	IPA_RC_SBP_OSA_OS_MISMATCH	= 0x2B10,
 	IPA_RC_SBP_OSA_ANO_DEV_PRIMARY	= 0x2B14,
@@ -198,6 +200,9 @@ enum qeth_ipa_return_codes {
 	IPA_RC_ENOMEM			= 0xfffe,
 	IPA_RC_FFFF			= 0xffff
 };
+/* for VNIC Characteristics */
+#define IPA_RC_VNICC_OOSEQ 0x0005
+
 /* for SET_DIAGNOSTIC_ASSIST */
 #define IPA_RC_INVALID_SUBCMD		IPA_RC_IP_TABLE_FULL
 #define IPA_RC_HARDWARE_AUTH_ERROR	IPA_RC_UNKNOWN_ERROR
@@ -552,6 +557,71 @@ struct qeth_ipacmd_diagass {
 	__u8   cdata[64];
 } __attribute__ ((packed));
 
+/* VNIC Characteristics IPA Command: *****************************************/
+/* IPA commands/sub commands for VNICC */
+#define IPA_VNICC_QUERY_CHARS		0x00000000L
+#define IPA_VNICC_QUERY_CMDS		0x00000001L
+#define IPA_VNICC_ENABLE		0x00000002L
+#define IPA_VNICC_DISABLE		0x00000004L
+#define IPA_VNICC_SET_TIMEOUT		0x00000008L
+#define IPA_VNICC_GET_TIMEOUT		0x00000010L
+
+/* VNICC flags */
+#define QETH_VNICC_FLOODING		0x80000000
+#define QETH_VNICC_MCAST_FLOODING	0x40000000
+#define QETH_VNICC_LEARNING		0x20000000
+#define QETH_VNICC_TAKEOVER_SETVMAC	0x10000000
+#define QETH_VNICC_TAKEOVER_LEARNING	0x08000000
+#define QETH_VNICC_BRIDGE_INVISIBLE	0x04000000
+#define QETH_VNICC_RX_BCAST		0x02000000
+
+/* VNICC default values */
+#define QETH_VNICC_ALL			0xff000000
+#define QETH_VNICC_DEFAULT		QETH_VNICC_RX_BCAST
+/* default VNICC timeout in seconds */
+#define QETH_VNICC_DEFAULT_TIMEOUT	600
+
+/* VNICC header */
+struct qeth_ipacmd_vnicc_hdr {
+	u32 sup;
+	u32 cur;
+};
+
+/* VNICC sub command header */
+struct qeth_vnicc_sub_hdr {
+	u16 data_length;
+	u16 reserved;
+	u32 sub_command;
+};
+
+/* query supported commands for VNIC characteristic */
+struct qeth_vnicc_query_cmds {
+	u32 vnic_char;
+	u32 sup_cmds;
+};
+
+/* enable/disable VNIC characteristic */
+struct qeth_vnicc_set_char {
+	u32 vnic_char;
+};
+
+/* get/set timeout for VNIC characteristic */
+struct qeth_vnicc_getset_timeout {
+	u32 vnic_char;
+	u32 timeout;
+};
+
+/* complete VNICC IPA command message */
+struct qeth_ipacmd_vnicc {
+	struct qeth_ipacmd_vnicc_hdr hdr;
+	struct qeth_vnicc_sub_hdr sub_hdr;
+	union {
+		struct qeth_vnicc_query_cmds query_cmds;
+		struct qeth_vnicc_set_char set_char;
+		struct qeth_vnicc_getset_timeout getset_timeout;
+	};
+};
+
 /* SETBRIDGEPORT IPA Command:	 *********************************************/
 enum qeth_ipa_sbp_cmd {
 	IPA_SBP_QUERY_COMMANDS_SUPPORTED	= 0x00000000L,
@@ -693,6 +763,7 @@ struct qeth_ipa_cmd {
 		struct qeth_ipacmd_diagass		diagass;
 		struct qeth_ipacmd_setbridgeport	sbp;
 		struct qeth_ipacmd_addr_change		addrchange;
+		struct qeth_ipacmd_vnicc		vnicc;
 	} data;
 } __attribute__ ((packed));
 
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index d1ee9e30c68b..b22ed2a57acd 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -475,10 +475,8 @@ static ssize_t qeth_dev_isolation_store(struct device *dev,
 		return -EINVAL;
 
 	mutex_lock(&card->conf_mutex);
-	/* check for unknown, too, in case we do not yet know who we are */
 	if (card->info.type != QETH_CARD_TYPE_OSD &&
-	    card->info.type != QETH_CARD_TYPE_OSX &&
-	    card->info.type != QETH_CARD_TYPE_UNKNOWN) {
+	    card->info.type != QETH_CARD_TYPE_OSX) {
 		rc = -EOPNOTSUPP;
 		dev_err(&card->gdev->dev, "Adapter does not "
 			"support QDIO data connection isolation\n");
diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h
index d4a8293d318d..09b1c4ef3dc9 100644
--- a/drivers/s390/net/qeth_l2.h
+++ b/drivers/s390/net/qeth_l2.h
@@ -15,6 +15,12 @@ int qeth_l2_create_device_attributes(struct device *);
 void qeth_l2_remove_device_attributes(struct device *);
 void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);
 
+int qeth_l2_vnicc_set_state(struct qeth_card *card, u32 vnicc, bool state);
+int qeth_l2_vnicc_get_state(struct qeth_card *card, u32 vnicc, bool *state);
+int qeth_l2_vnicc_set_timeout(struct qeth_card *card, u32 timeout);
+int qeth_l2_vnicc_get_timeout(struct qeth_card *card, u32 *timeout);
+bool qeth_l2_vnicc_is_in_use(struct qeth_card *card);
+
 struct qeth_mac {
 	u8 mac_addr[OSA_ADDR_LEN];
 	u8 is_uc:1;
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 760b023eae95..d2537c09126d 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -33,24 +33,10 @@ static void qeth_bridge_state_change(struct qeth_card *card,
 					struct qeth_ipa_cmd *cmd);
 static void qeth_bridge_host_event(struct qeth_card *card,
 					struct qeth_ipa_cmd *cmd);
-
-static int qeth_l2_verify_dev(struct net_device *dev)
-{
-	struct qeth_card *card;
-	unsigned long flags;
-	int rc = 0;
-
-	read_lock_irqsave(&qeth_core_card_list.rwlock, flags);
-	list_for_each_entry(card, &qeth_core_card_list.list, list) {
-		if (card->dev == dev) {
-			rc = QETH_REAL_CARD;
-			break;
-		}
-	}
-	read_unlock_irqrestore(&qeth_core_card_list.rwlock, flags);
-
-	return rc;
-}
+static void qeth_l2_vnicc_set_defaults(struct qeth_card *card);
+static void qeth_l2_vnicc_init(struct qeth_card *card);
+static bool qeth_l2_vnicc_recover_timeout(struct qeth_card *card, u32 vnicc,
+					  u32 *timeout);
 
 static struct net_device *qeth_l2_netdev_by_devno(unsigned char *read_dev_no)
 {
@@ -74,7 +60,7 @@ static struct net_device *qeth_l2_netdev_by_devno(unsigned char *read_dev_no)
 	return ndev;
 }
 
-static int qeth_setdel_makerc(struct qeth_card *card, int retcode)
+static int qeth_setdelmac_makerc(struct qeth_card *card, int retcode)
 {
 	int rc;
 
@@ -124,8 +110,8 @@ static int qeth_l2_send_setdelmac(struct qeth_card *card, __u8 *mac,
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.setdelmac.mac_length = OSA_ADDR_LEN;
 	memcpy(&cmd->data.setdelmac.mac, mac, OSA_ADDR_LEN);
-	return qeth_setdel_makerc(card, qeth_send_ipa_cmd(card, iob,
-					NULL, NULL));
+	return qeth_setdelmac_makerc(card, qeth_send_ipa_cmd(card, iob,
+					   NULL, NULL));
 }
 
 static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac)
@@ -285,17 +271,40 @@ static void qeth_l2_fill_header(struct qeth_hdr *hdr, struct sk_buff *skb,
 	}
 }
 
+static int qeth_setdelvlan_makerc(struct qeth_card *card, int retcode)
+{
+	if (retcode)
+		QETH_CARD_TEXT_(card, 2, "err%04x", retcode);
+
+	switch (retcode) {
+	case IPA_RC_SUCCESS:
+		return 0;
+	case IPA_RC_L2_INVALID_VLAN_ID:
+		return -EINVAL;
+	case IPA_RC_L2_DUP_VLAN_ID:
+		return -EEXIST;
+	case IPA_RC_L2_VLAN_ID_NOT_FOUND:
+		return -ENOENT;
+	case IPA_RC_L2_VLAN_ID_NOT_ALLOWED:
+		return -EPERM;
+	case -ENOMEM:
+		return -ENOMEM;
+	default:
+		return -EIO;
+	}
+}
+
 static int qeth_l2_send_setdelvlan_cb(struct qeth_card *card,
-			struct qeth_reply *reply, unsigned long data)
+				      struct qeth_reply *reply,
+				      unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
 
 	QETH_CARD_TEXT(card, 2, "L2sdvcb");
-	cmd = (struct qeth_ipa_cmd *) data;
 	if (cmd->hdr.return_code) {
-		QETH_DBF_MESSAGE(2, "Error in processing VLAN %i on %s: 0x%x. "
-			  "Continuing\n", cmd->data.setdelvlan.vlan_id,
-			  QETH_CARD_IFNAME(card), cmd->hdr.return_code);
+		QETH_DBF_MESSAGE(2, "Error in processing VLAN %i on %s: 0x%x.\n",
+				 cmd->data.setdelvlan.vlan_id,
+				 QETH_CARD_IFNAME(card), cmd->hdr.return_code);
 		QETH_CARD_TEXT_(card, 2, "L2VL%4x", cmd->hdr.command);
 		QETH_CARD_TEXT_(card, 2, "err%d", cmd->hdr.return_code);
 	}
@@ -303,7 +312,7 @@ static int qeth_l2_send_setdelvlan_cb(struct qeth_card *card,
 }
 
 static int qeth_l2_send_setdelvlan(struct qeth_card *card, __u16 i,
-				enum qeth_ipa_cmds ipacmd)
+				   enum qeth_ipa_cmds ipacmd)
 {
 	struct qeth_ipa_cmd *cmd;
 	struct qeth_cmd_buffer *iob;
@@ -314,8 +323,8 @@ static int qeth_l2_send_setdelvlan(struct qeth_card *card, __u16 i,
 		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.setdelvlan.vlan_id = i;
-	return qeth_send_ipa_cmd(card, iob,
-				 qeth_l2_send_setdelvlan_cb, NULL);
+	return qeth_setdelvlan_makerc(card, qeth_send_ipa_cmd(card, iob,
+					    qeth_l2_send_setdelvlan_cb, NULL));
 }
 
 static void qeth_l2_process_vlans(struct qeth_card *card)
@@ -339,10 +348,6 @@ static int qeth_l2_vlan_rx_add_vid(struct net_device *dev,
 	QETH_CARD_TEXT_(card, 4, "aid:%d", vid);
 	if (!vid)
 		return 0;
-	if (card->info.type == QETH_CARD_TYPE_OSM) {
-		QETH_CARD_TEXT(card, 3, "aidOSM");
-		return 0;
-	}
 	if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
 		QETH_CARD_TEXT(card, 3, "aidREC");
 		return 0;
@@ -372,10 +377,6 @@ static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev,
 	int rc = 0;
 
 	QETH_CARD_TEXT_(card, 4, "kid:%d", vid);
-	if (card->info.type == QETH_CARD_TYPE_OSM) {
-		QETH_CARD_TEXT(card, 3, "kidOSM");
-		return 0;
-	}
 	if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
 		QETH_CARD_TEXT(card, 3, "kidREC");
 		return 0;
@@ -541,11 +542,6 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p)
 
 	QETH_CARD_TEXT(card, 3, "setmac");
 
-	if (qeth_l2_verify_dev(dev) != QETH_REAL_CARD) {
-		QETH_CARD_TEXT(card, 3, "setmcINV");
-		return -EOPNOTSUPP;
-	}
-
 	if (card->info.type == QETH_CARD_TYPE_OSN ||
 	    card->info.type == QETH_CARD_TYPE_OSM ||
 	    card->info.type == QETH_CARD_TYPE_OSX) {
@@ -694,7 +690,7 @@ static int qeth_l2_xmit_iqd(struct qeth_card *card, struct sk_buff *skb,
 		rc = -E2BIG;
 		goto out;
 	}
-	rc = qeth_do_send_packet_fast(card, queue, skb, hdr, data_offset,
+	rc = qeth_do_send_packet_fast(queue, skb, hdr, data_offset,
 				      sizeof(*hdr) + data_offset);
 out:
 	if (rc)
@@ -919,6 +915,7 @@ static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
 	hash_init(card->mac_htable);
 	card->options.layer2 = 1;
 	card->info.hwtrap = 0;
+	qeth_l2_vnicc_set_defaults(card);
 	return 0;
 }
 
@@ -1005,7 +1002,11 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	} else {
 		card->dev->ethtool_ops = &qeth_l2_ethtool_ops;
 	}
-	card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	if (card->info.type == QETH_CARD_TYPE_OSM)
+		card->dev->features |= NETIF_F_VLAN_CHALLENGED;
+	else
+		card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
 		card->dev->hw_features = NETIF_F_SG;
 		card->dev->vlan_features = NETIF_F_SG;
@@ -1045,9 +1046,14 @@ static int qeth_l2_start_ipassists(struct qeth_card *card)
 
 static void qeth_l2_trace_features(struct qeth_card *card)
 {
-	QETH_CARD_TEXT(card, 2, "l2featur");
+	/* Set BridgePort features */
+	QETH_CARD_TEXT(card, 2, "featuSBP");
 	QETH_CARD_HEX(card, 2, &card->options.sbp.supported_funcs,
 		      sizeof(card->options.sbp.supported_funcs));
+	/* VNIC Characteristics features */
+	QETH_CARD_TEXT(card, 2, "feaVNICC");
+	QETH_CARD_HEX(card, 2, &card->options.vnicc.sup_chars,
+		      sizeof(card->options.vnicc.sup_chars));
 }
 
 static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
@@ -1072,8 +1078,6 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 	if (card->options.sbp.supported_funcs)
 		dev_info(&card->gdev->dev,
 		"The device represents a Bridge Capable Port\n");
-	qeth_trace_features(card);
-	qeth_l2_trace_features(card);
 
 	if (!card->dev && qeth_l2_setup_netdev(card)) {
 		rc = -ENODEV;
@@ -1090,6 +1094,12 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 	} else
 		card->info.hwtrap = 0;
 
+	/* for the rx_bcast characteristic, init VNICC after setmac */
+	qeth_l2_vnicc_init(card);
+
+	qeth_trace_features(card);
+	qeth_l2_trace_features(card);
+
 	qeth_l2_setup_bridgeport_attrs(card);
 
 	card->state = CARD_STATE_HARDSETUP;
@@ -1106,8 +1116,7 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 			goto out_remove;
 	}
 
-	if (card->info.type != QETH_CARD_TYPE_OSN &&
-	    card->info.type != QETH_CARD_TYPE_OSM)
+	if (card->info.type != QETH_CARD_TYPE_OSN)
 		qeth_l2_process_vlans(card);
 
 	netif_tx_disable(card->dev);
@@ -2039,6 +2048,454 @@ int qeth_bridgeport_an_set(struct qeth_card *card, int enable)
 }
 EXPORT_SYMBOL_GPL(qeth_bridgeport_an_set);
 
+static bool qeth_bridgeport_is_in_use(struct qeth_card *card)
+{
+	return (card->options.sbp.role || card->options.sbp.reflect_promisc ||
+		card->options.sbp.hostnotification);
+}
+
+/* VNIC Characteristics support */
+
+/* handle VNICC IPA command return codes; convert to error codes */
+static int qeth_l2_vnicc_makerc(struct qeth_card *card, int ipa_rc)
+{
+	int rc;
+
+	switch (ipa_rc) {
+	case IPA_RC_SUCCESS:
+		return ipa_rc;
+	case IPA_RC_L2_UNSUPPORTED_CMD:
+	case IPA_RC_NOTSUPP:
+		rc = -EOPNOTSUPP;
+		break;
+	case IPA_RC_VNICC_OOSEQ:
+		rc = -EALREADY;
+		break;
+	case IPA_RC_VNICC_VNICBP:
+		rc = -EBUSY;
+		break;
+	case IPA_RC_L2_ADDR_TABLE_FULL:
+		rc = -ENOSPC;
+		break;
+	case IPA_RC_L2_MAC_NOT_AUTH_BY_ADP:
+		rc = -EACCES;
+		break;
+	default:
+		rc = -EIO;
+	}
+
+	QETH_CARD_TEXT_(card, 2, "err%04x", ipa_rc);
+	return rc;
+}
+
+/* generic VNICC request call back control */
+struct _qeth_l2_vnicc_request_cbctl {
+	u32 sub_cmd;
+	struct {
+		u32 vnic_char;
+		u32 timeout;
+	} param;
+	struct {
+		union{
+			u32 *sup_cmds;
+			u32 *timeout;
+		};
+	} result;
+};
+
+/* generic VNICC request call back */
+static int qeth_l2_vnicc_request_cb(struct qeth_card *card,
+				    struct qeth_reply *reply,
+				    unsigned long data)
+{
+	struct _qeth_l2_vnicc_request_cbctl *cbctl =
+		(struct _qeth_l2_vnicc_request_cbctl *) reply->param;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
+	struct qeth_ipacmd_vnicc *rep = &cmd->data.vnicc;
+
+	QETH_CARD_TEXT(card, 2, "vniccrcb");
+	if (cmd->hdr.return_code)
+		return 0;
+	/* return results to caller */
+	card->options.vnicc.sup_chars = rep->hdr.sup;
+	card->options.vnicc.cur_chars = rep->hdr.cur;
+
+	if (cbctl->sub_cmd == IPA_VNICC_QUERY_CMDS)
+		*cbctl->result.sup_cmds = rep->query_cmds.sup_cmds;
+
+	if (cbctl->sub_cmd == IPA_VNICC_GET_TIMEOUT)
+		*cbctl->result.timeout = rep->getset_timeout.timeout;
+
+	return 0;
+}
+
+/* generic VNICC request */
+static int qeth_l2_vnicc_request(struct qeth_card *card,
+				 struct _qeth_l2_vnicc_request_cbctl *cbctl)
+{
+	struct qeth_ipacmd_vnicc *req;
+	struct qeth_cmd_buffer *iob;
+	struct qeth_ipa_cmd *cmd;
+	int rc;
+
+	QETH_CARD_TEXT(card, 2, "vniccreq");
+
+	/* get new buffer for request */
+	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_VNICC, 0);
+	if (!iob)
+		return -ENOMEM;
+
+	/* create header for request */
+	cmd = (struct qeth_ipa_cmd *)(iob->data + IPA_PDU_HEADER_SIZE);
+	req = &cmd->data.vnicc;
+
+	/* create sub command header for request */
+	req->sub_hdr.data_length = sizeof(req->sub_hdr);
+	req->sub_hdr.sub_command = cbctl->sub_cmd;
+
+	/* create sub command specific request fields */
+	switch (cbctl->sub_cmd) {
+	case IPA_VNICC_QUERY_CHARS:
+		break;
+	case IPA_VNICC_QUERY_CMDS:
+		req->sub_hdr.data_length += sizeof(req->query_cmds);
+		req->query_cmds.vnic_char = cbctl->param.vnic_char;
+		break;
+	case IPA_VNICC_ENABLE:
+	case IPA_VNICC_DISABLE:
+		req->sub_hdr.data_length += sizeof(req->set_char);
+		req->set_char.vnic_char = cbctl->param.vnic_char;
+		break;
+	case IPA_VNICC_SET_TIMEOUT:
+		req->getset_timeout.timeout = cbctl->param.timeout;
+		/* fallthrough */
+	case IPA_VNICC_GET_TIMEOUT:
+		req->sub_hdr.data_length += sizeof(req->getset_timeout);
+		req->getset_timeout.vnic_char = cbctl->param.vnic_char;
+		break;
+	default:
+		qeth_release_buffer(iob->channel, iob);
+		return -EOPNOTSUPP;
+	}
+
+	/* send request */
+	rc = qeth_send_ipa_cmd(card, iob, qeth_l2_vnicc_request_cb,
+			       (void *) cbctl);
+
+	return qeth_l2_vnicc_makerc(card, rc);
+}
+
+/* VNICC query VNIC characteristics request */
+static int qeth_l2_vnicc_query_chars(struct qeth_card *card)
+{
+	struct _qeth_l2_vnicc_request_cbctl cbctl;
+
+	/* prepare callback control */
+	cbctl.sub_cmd = IPA_VNICC_QUERY_CHARS;
+
+	QETH_CARD_TEXT(card, 2, "vniccqch");
+	return qeth_l2_vnicc_request(card, &cbctl);
+}
+
+/* VNICC query sub commands request */
+static int qeth_l2_vnicc_query_cmds(struct qeth_card *card, u32 vnic_char,
+				    u32 *sup_cmds)
+{
+	struct _qeth_l2_vnicc_request_cbctl cbctl;
+
+	/* prepare callback control */
+	cbctl.sub_cmd = IPA_VNICC_QUERY_CMDS;
+	cbctl.param.vnic_char = vnic_char;
+	cbctl.result.sup_cmds = sup_cmds;
+
+	QETH_CARD_TEXT(card, 2, "vniccqcm");
+	return qeth_l2_vnicc_request(card, &cbctl);
+}
+
+/* VNICC enable/disable characteristic request */
+static int qeth_l2_vnicc_set_char(struct qeth_card *card, u32 vnic_char,
+				      u32 cmd)
+{
+	struct _qeth_l2_vnicc_request_cbctl cbctl;
+
+	/* prepare callback control */
+	cbctl.sub_cmd = cmd;
+	cbctl.param.vnic_char = vnic_char;
+
+	QETH_CARD_TEXT(card, 2, "vniccedc");
+	return qeth_l2_vnicc_request(card, &cbctl);
+}
+
+/* VNICC get/set timeout for characteristic request */
+static int qeth_l2_vnicc_getset_timeout(struct qeth_card *card, u32 vnicc,
+					u32 cmd, u32 *timeout)
+{
+	struct _qeth_l2_vnicc_request_cbctl cbctl;
+
+	/* prepare callback control */
+	cbctl.sub_cmd = cmd;
+	cbctl.param.vnic_char = vnicc;
+	if (cmd == IPA_VNICC_SET_TIMEOUT)
+		cbctl.param.timeout = *timeout;
+	if (cmd == IPA_VNICC_GET_TIMEOUT)
+		cbctl.result.timeout = timeout;
+
+	QETH_CARD_TEXT(card, 2, "vniccgst");
+	return qeth_l2_vnicc_request(card, &cbctl);
+}
+
+/* set current VNICC flag state; called from sysfs store function */
+int qeth_l2_vnicc_set_state(struct qeth_card *card, u32 vnicc, bool state)
+{
+	int rc = 0;
+	u32 cmd;
+
+	QETH_CARD_TEXT(card, 2, "vniccsch");
+
+	/* do not change anything if BridgePort is enabled */
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
+	/* check if characteristic and enable/disable are supported */
+	if (!(card->options.vnicc.sup_chars & vnicc) ||
+	    !(card->options.vnicc.set_char_sup & vnicc))
+		return -EOPNOTSUPP;
+
+	/* set enable/disable command and store wanted characteristic */
+	if (state) {
+		cmd = IPA_VNICC_ENABLE;
+		card->options.vnicc.wanted_chars |= vnicc;
+	} else {
+		cmd = IPA_VNICC_DISABLE;
+		card->options.vnicc.wanted_chars &= ~vnicc;
+	}
+
+	/* do we need to do anything? */
+	if (card->options.vnicc.cur_chars == card->options.vnicc.wanted_chars)
+		return rc;
+
+	/* if card is not ready, simply stop here */
+	if (!qeth_card_hw_is_reachable(card)) {
+		if (state)
+			card->options.vnicc.cur_chars |= vnicc;
+		else
+			card->options.vnicc.cur_chars &= ~vnicc;
+		return rc;
+	}
+
+	rc = qeth_l2_vnicc_set_char(card, vnicc, cmd);
+	if (rc)
+		card->options.vnicc.wanted_chars =
+			card->options.vnicc.cur_chars;
+	else {
+		/* successful online VNICC change; handle special cases */
+		if (state && vnicc == QETH_VNICC_RX_BCAST)
+			card->options.vnicc.rx_bcast_enabled = true;
+		if (!state && vnicc == QETH_VNICC_LEARNING)
+			qeth_l2_vnicc_recover_timeout(card, vnicc,
+					&card->options.vnicc.learning_timeout);
+	}
+
+	return rc;
+}
+
+/* get current VNICC flag state; called from sysfs show function */
+int qeth_l2_vnicc_get_state(struct qeth_card *card, u32 vnicc, bool *state)
+{
+	int rc = 0;
+
+	QETH_CARD_TEXT(card, 2, "vniccgch");
+
+	/* do not get anything if BridgePort is enabled */
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
+	/* check if characteristic is supported */
+	if (!(card->options.vnicc.sup_chars & vnicc))
+		return -EOPNOTSUPP;
+
+	/* if card is ready, query current VNICC state */
+	if (qeth_card_hw_is_reachable(card))
+		rc = qeth_l2_vnicc_query_chars(card);
+
+	*state = (card->options.vnicc.cur_chars & vnicc) ? true : false;
+	return rc;
+}
+
+/* set VNICC timeout; called from sysfs store function. Currently, only learning
+ * supports timeout
+ */
+int qeth_l2_vnicc_set_timeout(struct qeth_card *card, u32 timeout)
+{
+	int rc = 0;
+
+	QETH_CARD_TEXT(card, 2, "vniccsto");
+
+	/* do not change anything if BridgePort is enabled */
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
+	/* check if characteristic and set_timeout are supported */
+	if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) ||
+	    !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING))
+		return -EOPNOTSUPP;
+
+	/* do we need to do anything? */
+	if (card->options.vnicc.learning_timeout == timeout)
+		return rc;
+
+	/* if card is not ready, simply store the value internally and return */
+	if (!qeth_card_hw_is_reachable(card)) {
+		card->options.vnicc.learning_timeout = timeout;
+		return rc;
+	}
+
+	/* send timeout value to card; if successful, store value internally */
+	rc = qeth_l2_vnicc_getset_timeout(card, QETH_VNICC_LEARNING,
+					  IPA_VNICC_SET_TIMEOUT, &timeout);
+	if (!rc)
+		card->options.vnicc.learning_timeout = timeout;
+
+	return rc;
+}
+
+/* get current VNICC timeout; called from sysfs show function. Currently, only
+ * learning supports timeout
+ */
+int qeth_l2_vnicc_get_timeout(struct qeth_card *card, u32 *timeout)
+{
+	int rc = 0;
+
+	QETH_CARD_TEXT(card, 2, "vniccgto");
+
+	/* do not get anything if BridgePort is enabled */
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
+	/* check if characteristic and get_timeout are supported */
+	if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) ||
+	    !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING))
+		return -EOPNOTSUPP;
+	/* if card is ready, get timeout. Otherwise, just return stored value */
+	*timeout = card->options.vnicc.learning_timeout;
+	if (qeth_card_hw_is_reachable(card))
+		rc = qeth_l2_vnicc_getset_timeout(card, QETH_VNICC_LEARNING,
+						  IPA_VNICC_GET_TIMEOUT,
+						  timeout);
+
+	return rc;
+}
+
+/* check if VNICC is currently enabled */
+bool qeth_l2_vnicc_is_in_use(struct qeth_card *card)
+{
+	/* if everything is turned off, VNICC is not active */
+	if (!card->options.vnicc.cur_chars)
+		return false;
+	/* default values are only OK if rx_bcast was not enabled by user
+	 * or the card is offline.
+	 */
+	if (card->options.vnicc.cur_chars == QETH_VNICC_DEFAULT) {
+		if (!card->options.vnicc.rx_bcast_enabled ||
+		    !qeth_card_hw_is_reachable(card))
+			return false;
+	}
+	return true;
+}
+
+/* recover user timeout setting */
+static bool qeth_l2_vnicc_recover_timeout(struct qeth_card *card, u32 vnicc,
+					  u32 *timeout)
+{
+	if (card->options.vnicc.sup_chars & vnicc &&
+	    card->options.vnicc.getset_timeout_sup & vnicc &&
+	    !qeth_l2_vnicc_getset_timeout(card, vnicc, IPA_VNICC_SET_TIMEOUT,
+					  timeout))
+		return false;
+	*timeout = QETH_VNICC_DEFAULT_TIMEOUT;
+	return true;
+}
+
+/* recover user characteristic setting */
+static bool qeth_l2_vnicc_recover_char(struct qeth_card *card, u32 vnicc,
+				       bool enable)
+{
+	u32 cmd = enable ? IPA_VNICC_ENABLE : IPA_VNICC_DISABLE;
+
+	if (card->options.vnicc.sup_chars & vnicc &&
+	    card->options.vnicc.set_char_sup & vnicc &&
+	    !qeth_l2_vnicc_set_char(card, vnicc, cmd))
+		return false;
+	card->options.vnicc.wanted_chars &= ~vnicc;
+	card->options.vnicc.wanted_chars |= QETH_VNICC_DEFAULT & vnicc;
+	return true;
+}
+
+/* (re-)initialize VNICC */
+static void qeth_l2_vnicc_init(struct qeth_card *card)
+{
+	u32 *timeout = &card->options.vnicc.learning_timeout;
+	unsigned int chars_len, i;
+	unsigned long chars_tmp;
+	u32 sup_cmds, vnicc;
+	bool enable, error;
+
+	QETH_CARD_TEXT(card, 2, "vniccini");
+	/* reset rx_bcast */
+	card->options.vnicc.rx_bcast_enabled = 0;
+	/* initial query and storage of VNIC characteristics */
+	if (qeth_l2_vnicc_query_chars(card)) {
+		if (card->options.vnicc.wanted_chars != QETH_VNICC_DEFAULT ||
+		    *timeout != QETH_VNICC_DEFAULT_TIMEOUT)
+			dev_err(&card->gdev->dev, "Configuring the VNIC characteristics failed\n");
+		/* fail quietly if user didn't change the default config */
+		card->options.vnicc.sup_chars = 0;
+		card->options.vnicc.cur_chars = 0;
+		card->options.vnicc.wanted_chars = QETH_VNICC_DEFAULT;
+		return;
+	}
+	/* get supported commands for each supported characteristic */
+	chars_tmp = card->options.vnicc.sup_chars;
+	chars_len = sizeof(card->options.vnicc.sup_chars) * BITS_PER_BYTE;
+	for_each_set_bit(i, &chars_tmp, chars_len) {
+		vnicc = BIT(i);
+		qeth_l2_vnicc_query_cmds(card, vnicc, &sup_cmds);
+		if (!(sup_cmds & IPA_VNICC_SET_TIMEOUT) ||
+		    !(sup_cmds & IPA_VNICC_GET_TIMEOUT))
+			card->options.vnicc.getset_timeout_sup &= ~vnicc;
+		if (!(sup_cmds & IPA_VNICC_ENABLE) ||
+		    !(sup_cmds & IPA_VNICC_DISABLE))
+			card->options.vnicc.set_char_sup &= ~vnicc;
+	}
+	/* enforce assumed default values and recover settings, if changed  */
+	error = qeth_l2_vnicc_recover_timeout(card, QETH_VNICC_LEARNING,
+					      timeout);
+	chars_tmp = card->options.vnicc.wanted_chars ^ QETH_VNICC_DEFAULT;
+	chars_tmp |= QETH_VNICC_BRIDGE_INVISIBLE;
+	chars_len = sizeof(card->options.vnicc.wanted_chars) * BITS_PER_BYTE;
+	for_each_set_bit(i, &chars_tmp, chars_len) {
+		vnicc = BIT(i);
+		enable = card->options.vnicc.wanted_chars & vnicc;
+		error |= qeth_l2_vnicc_recover_char(card, vnicc, enable);
+	}
+	if (error)
+		dev_err(&card->gdev->dev, "Configuring the VNIC characteristics failed\n");
+}
+
+/* configure default values of VNIC characteristics */
+static void qeth_l2_vnicc_set_defaults(struct qeth_card *card)
+{
+	/* characteristics values */
+	card->options.vnicc.sup_chars = QETH_VNICC_ALL;
+	card->options.vnicc.cur_chars = QETH_VNICC_DEFAULT;
+	card->options.vnicc.learning_timeout = QETH_VNICC_DEFAULT_TIMEOUT;
+	/* supported commands */
+	card->options.vnicc.set_char_sup = QETH_VNICC_ALL;
+	card->options.vnicc.getset_timeout_sup = QETH_VNICC_LEARNING;
+	/* settings wanted by users */
+	card->options.vnicc.wanted_chars = QETH_VNICC_DEFAULT;
+}
+
 module_init(qeth_l2_init);
 module_exit(qeth_l2_exit);
 MODULE_AUTHOR("Frank Blaschka <frank.blaschka@de.ibm.com>");
diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c
index d33d413f7150..f2c3b127b1e4 100644
--- a/drivers/s390/net/qeth_l2_sys.c
+++ b/drivers/s390/net/qeth_l2_sys.c
@@ -21,6 +21,9 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev,
 	if (!card)
 		return -EINVAL;
 
+	if (qeth_l2_vnicc_is_in_use(card))
+		return sprintf(buf, "n/a (VNIC characteristics)\n");
+
 	if (qeth_card_hw_is_reachable(card) &&
 					card->options.sbp.supported_funcs)
 		rc = qeth_bridgeport_query_ports(card,
@@ -61,6 +64,11 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev,
 static ssize_t qeth_bridge_port_role_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
+	struct qeth_card *card = dev_get_drvdata(dev);
+
+	if (qeth_l2_vnicc_is_in_use(card))
+		return sprintf(buf, "n/a (VNIC characteristics)\n");
+
 	return qeth_bridge_port_role_state_show(dev, attr, buf, 0);
 }
 
@@ -84,7 +92,10 @@ static ssize_t qeth_bridge_port_role_store(struct device *dev,
 
 	mutex_lock(&card->conf_mutex);
 
-	if (card->options.sbp.reflect_promisc) /* Forbid direct manipulation */
+	if (qeth_l2_vnicc_is_in_use(card))
+		rc = -EBUSY;
+	else if (card->options.sbp.reflect_promisc)
+		/* Forbid direct manipulation */
 		rc = -EPERM;
 	else if (qeth_card_hw_is_reachable(card)) {
 		rc = qeth_bridgeport_setrole(card, role);
@@ -104,6 +115,11 @@ static DEVICE_ATTR(bridge_role, 0644, qeth_bridge_port_role_show,
 static ssize_t qeth_bridge_port_state_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
+	struct qeth_card *card = dev_get_drvdata(dev);
+
+	if (qeth_l2_vnicc_is_in_use(card))
+		return sprintf(buf, "n/a (VNIC characteristics)\n");
+
 	return qeth_bridge_port_role_state_show(dev, attr, buf, 1);
 }
 
@@ -119,6 +135,9 @@ static ssize_t qeth_bridgeport_hostnotification_show(struct device *dev,
 	if (!card)
 		return -EINVAL;
 
+	if (qeth_l2_vnicc_is_in_use(card))
+		return sprintf(buf, "n/a (VNIC characteristics)\n");
+
 	enabled = card->options.sbp.hostnotification;
 
 	return sprintf(buf, "%d\n", enabled);
@@ -128,22 +147,21 @@ static ssize_t qeth_bridgeport_hostnotification_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
-	int rc = 0;
-	int enable;
+	bool enable;
+	int rc;
 
 	if (!card)
 		return -EINVAL;
 
-	if (sysfs_streq(buf, "0"))
-		enable = 0;
-	else if (sysfs_streq(buf, "1"))
-		enable = 1;
-	else
-		return -EINVAL;
+	rc = kstrtobool(buf, &enable);
+	if (rc)
+		return rc;
 
 	mutex_lock(&card->conf_mutex);
 
-	if (qeth_card_hw_is_reachable(card)) {
+	if (qeth_l2_vnicc_is_in_use(card))
+		rc = -EBUSY;
+	else if (qeth_card_hw_is_reachable(card)) {
 		rc = qeth_bridgeport_an_set(card, enable);
 		if (!rc)
 			card->options.sbp.hostnotification = enable;
@@ -168,6 +186,9 @@ static ssize_t qeth_bridgeport_reflect_show(struct device *dev,
 	if (!card)
 		return -EINVAL;
 
+	if (qeth_l2_vnicc_is_in_use(card))
+		return sprintf(buf, "n/a (VNIC characteristics)\n");
+
 	if (card->options.sbp.reflect_promisc) {
 		if (card->options.sbp.reflect_promisc_primary)
 			state = "primary";
@@ -203,7 +224,9 @@ static ssize_t qeth_bridgeport_reflect_store(struct device *dev,
 
 	mutex_lock(&card->conf_mutex);
 
-	if (card->options.sbp.role != QETH_SBP_ROLE_NONE)
+	if (qeth_l2_vnicc_is_in_use(card))
+		rc = -EBUSY;
+	else if (card->options.sbp.role != QETH_SBP_ROLE_NONE)
 		rc = -EPERM;
 	else {
 		card->options.sbp.reflect_promisc = enable;
@@ -232,16 +255,6 @@ static struct attribute_group qeth_l2_bridgeport_attr_group = {
 	.attrs = qeth_l2_bridgeport_attrs,
 };
 
-int qeth_l2_create_device_attributes(struct device *dev)
-{
-	return sysfs_create_group(&dev->kobj, &qeth_l2_bridgeport_attr_group);
-}
-
-void qeth_l2_remove_device_attributes(struct device *dev)
-{
-	sysfs_remove_group(&dev->kobj, &qeth_l2_bridgeport_attr_group);
-}
-
 /**
  * qeth_l2_setup_bridgeport_attrs() - set/restore attrs when turning online.
  * @card:			      qeth_card structure pointer
@@ -271,10 +284,168 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card)
 		qeth_bridgeport_an_set(card, 0);
 }
 
+/* VNIC CHARS support */
+
+/* convert sysfs attr name to VNIC characteristic */
+static u32 qeth_l2_vnicc_sysfs_attr_to_char(const char *attr_name)
+{
+	if (sysfs_streq(attr_name, "flooding"))
+		return QETH_VNICC_FLOODING;
+	else if (sysfs_streq(attr_name, "mcast_flooding"))
+		return QETH_VNICC_MCAST_FLOODING;
+	else if (sysfs_streq(attr_name, "learning"))
+		return QETH_VNICC_LEARNING;
+	else if (sysfs_streq(attr_name, "takeover_setvmac"))
+		return QETH_VNICC_TAKEOVER_SETVMAC;
+	else if (sysfs_streq(attr_name, "takeover_learning"))
+		return QETH_VNICC_TAKEOVER_LEARNING;
+	else if (sysfs_streq(attr_name, "bridge_invisible"))
+		return QETH_VNICC_BRIDGE_INVISIBLE;
+	else if (sysfs_streq(attr_name, "rx_bcast"))
+		return QETH_VNICC_RX_BCAST;
+
+	return 0;
+}
+
+/* get current timeout setting */
+static ssize_t qeth_vnicc_timeout_show(struct device *dev,
+				       struct device_attribute *attr, char *buf)
+{
+	struct qeth_card *card = dev_get_drvdata(dev);
+	u32 timeout;
+	int rc;
+
+	if (!card)
+		return -EINVAL;
+
+	rc = qeth_l2_vnicc_get_timeout(card, &timeout);
+	if (rc == -EBUSY)
+		return sprintf(buf, "n/a (BridgePort)\n");
+	if (rc == -EOPNOTSUPP)
+		return sprintf(buf, "n/a\n");
+	return rc ? rc : sprintf(buf, "%d\n", timeout);
+}
+
+/* change timeout setting */
+static ssize_t qeth_vnicc_timeout_store(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count)
+{
+	struct qeth_card *card = dev_get_drvdata(dev);
+	u32 timeout;
+	int rc;
+
+	if (!card)
+		return -EINVAL;
+
+	rc = kstrtou32(buf, 10, &timeout);
+	if (rc)
+		return rc;
+
+	mutex_lock(&card->conf_mutex);
+	rc = qeth_l2_vnicc_set_timeout(card, timeout);
+	mutex_unlock(&card->conf_mutex);
+	return rc ? rc : count;
+}
+
+/* get current setting of characteristic */
+static ssize_t qeth_vnicc_char_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct qeth_card *card = dev_get_drvdata(dev);
+	bool state;
+	u32 vnicc;
+	int rc;
+
+	if (!card)
+		return -EINVAL;
+
+	vnicc = qeth_l2_vnicc_sysfs_attr_to_char(attr->attr.name);
+	rc = qeth_l2_vnicc_get_state(card, vnicc, &state);
+
+	if (rc == -EBUSY)
+		return sprintf(buf, "n/a (BridgePort)\n");
+	if (rc == -EOPNOTSUPP)
+		return sprintf(buf, "n/a\n");
+	return rc ? rc : sprintf(buf, "%d\n", state);
+}
+
+/* change setting of characteristic */
+static ssize_t qeth_vnicc_char_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct qeth_card *card = dev_get_drvdata(dev);
+	bool state;
+	u32 vnicc;
+	int rc;
+
+	if (!card)
+		return -EINVAL;
+
+	if (kstrtobool(buf, &state))
+		return -EINVAL;
+
+	vnicc = qeth_l2_vnicc_sysfs_attr_to_char(attr->attr.name);
+	mutex_lock(&card->conf_mutex);
+	rc = qeth_l2_vnicc_set_state(card, vnicc, state);
+	mutex_unlock(&card->conf_mutex);
+
+	return rc ? rc : count;
+}
+
+static DEVICE_ATTR(flooding, 0644, qeth_vnicc_char_show, qeth_vnicc_char_store);
+static DEVICE_ATTR(mcast_flooding, 0644, qeth_vnicc_char_show,
+		   qeth_vnicc_char_store);
+static DEVICE_ATTR(learning, 0644, qeth_vnicc_char_show, qeth_vnicc_char_store);
+static DEVICE_ATTR(learning_timeout, 0644, qeth_vnicc_timeout_show,
+		   qeth_vnicc_timeout_store);
+static DEVICE_ATTR(takeover_setvmac, 0644, qeth_vnicc_char_show,
+		   qeth_vnicc_char_store);
+static DEVICE_ATTR(takeover_learning, 0644, qeth_vnicc_char_show,
+		   qeth_vnicc_char_store);
+static DEVICE_ATTR(bridge_invisible, 0644, qeth_vnicc_char_show,
+		   qeth_vnicc_char_store);
+static DEVICE_ATTR(rx_bcast, 0644, qeth_vnicc_char_show, qeth_vnicc_char_store);
+
+static struct attribute *qeth_l2_vnicc_attrs[] = {
+	&dev_attr_flooding.attr,
+	&dev_attr_mcast_flooding.attr,
+	&dev_attr_learning.attr,
+	&dev_attr_learning_timeout.attr,
+	&dev_attr_takeover_setvmac.attr,
+	&dev_attr_takeover_learning.attr,
+	&dev_attr_bridge_invisible.attr,
+	&dev_attr_rx_bcast.attr,
+	NULL,
+};
+
+static struct attribute_group qeth_l2_vnicc_attr_group = {
+	.attrs = qeth_l2_vnicc_attrs,
+	.name = "vnicc",
+};
+
+static const struct attribute_group *qeth_l2_only_attr_groups[] = {
+	&qeth_l2_bridgeport_attr_group,
+	&qeth_l2_vnicc_attr_group,
+	NULL,
+};
+
+int qeth_l2_create_device_attributes(struct device *dev)
+{
+	return sysfs_create_groups(&dev->kobj, qeth_l2_only_attr_groups);
+}
+
+void qeth_l2_remove_device_attributes(struct device *dev)
+{
+	sysfs_remove_groups(&dev->kobj, qeth_l2_only_attr_groups);
+}
+
 const struct attribute_group *qeth_l2_attr_groups[] = {
 	&qeth_device_attr_group,
 	&qeth_device_blkt_group,
-	/* l2 specific, see l2_{create,remove}_device_attributes(): */
+	/* l2 specific, see qeth_l2_only_attr_groups: */
 	&qeth_l2_bridgeport_attr_group,
+	&qeth_l2_vnicc_attr_group,
 	NULL,
 };
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index ab661a431f7c..aadd384316a3 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1553,7 +1553,7 @@ static void qeth_l3_free_vlan_addresses4(struct qeth_card *card,
 
 	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
 	if (!addr)
-		return;
+		goto out;
 
 	spin_lock_bh(&card->ip_lock);
 
@@ -1567,6 +1567,7 @@ static void qeth_l3_free_vlan_addresses4(struct qeth_card *card,
 	spin_unlock_bh(&card->ip_lock);
 
 	kfree(addr);
+out:
 	in_dev_put(in_dev);
 }
 
@@ -1591,7 +1592,7 @@ static void qeth_l3_free_vlan_addresses6(struct qeth_card *card,
 
 	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
 	if (!addr)
-		return;
+		goto out;
 
 	spin_lock_bh(&card->ip_lock);
 
@@ -1606,6 +1607,7 @@ static void qeth_l3_free_vlan_addresses6(struct qeth_card *card,
 	spin_unlock_bh(&card->ip_lock);
 
 	kfree(addr);
+out:
 	in6_dev_put(in6_dev);
 #endif /* CONFIG_QETH_IPV6 */
 }
@@ -1646,13 +1648,12 @@ static int qeth_l3_vlan_rx_kill_vid(struct net_device *dev,
 	return 0;
 }
 
-static int qeth_l3_rebuild_skb(struct qeth_card *card, struct sk_buff *skb,
-			       struct qeth_hdr *hdr, unsigned short *vlan_id)
+static void qeth_l3_rebuild_skb(struct qeth_card *card, struct sk_buff *skb,
+				struct qeth_hdr *hdr)
 {
 	__u16 prot;
 	struct iphdr *ip_hdr;
 	unsigned char tg_addr[MAX_ADDR_LEN];
-	int is_vlan = 0;
 
 	if (!(hdr->hdr.l3.flags & QETH_HDR_PASSTHRU)) {
 		prot = (hdr->hdr.l3.flags & QETH_HDR_IPV6) ? ETH_P_IPV6 :
@@ -1706,11 +1707,14 @@ static int qeth_l3_rebuild_skb(struct qeth_card *card, struct sk_buff *skb,
 
 	skb->protocol = eth_type_trans(skb, card->dev);
 
-	if (hdr->hdr.l3.ext_flags &
-	    (QETH_HDR_EXT_VLAN_FRAME | QETH_HDR_EXT_INCLUDE_VLAN_TAG)) {
-		*vlan_id = (hdr->hdr.l3.ext_flags & QETH_HDR_EXT_VLAN_FRAME) ?
-		 hdr->hdr.l3.vlan_id : *((u16 *)&hdr->hdr.l3.dest_addr[12]);
-		is_vlan = 1;
+	/* copy VLAN tag from hdr into skb */
+	if (!card->options.sniffer &&
+	    (hdr->hdr.l3.ext_flags & (QETH_HDR_EXT_VLAN_FRAME |
+				      QETH_HDR_EXT_INCLUDE_VLAN_TAG))) {
+		u16 tag = (hdr->hdr.l3.ext_flags & QETH_HDR_EXT_VLAN_FRAME) ?
+				hdr->hdr.l3.vlan_id :
+				*((u16 *)&hdr->hdr.l3.dest_addr[12]);
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tag);
 	}
 
 	if (card->dev->features & NETIF_F_RXCSUM) {
@@ -1724,7 +1728,6 @@ static int qeth_l3_rebuild_skb(struct qeth_card *card, struct sk_buff *skb,
 			skb->ip_summed = CHECKSUM_NONE;
 	} else
 		skb->ip_summed = CHECKSUM_NONE;
-	return is_vlan;
 }
 
 static int qeth_l3_process_inbound_buffer(struct qeth_card *card,
@@ -1733,8 +1736,6 @@ static int qeth_l3_process_inbound_buffer(struct qeth_card *card,
 	int work_done = 0;
 	struct sk_buff *skb;
 	struct qeth_hdr *hdr;
-	__u16 vlan_tag = 0;
-	int is_vlan;
 	unsigned int len;
 	__u16 magic;
 
@@ -1764,12 +1765,8 @@ static int qeth_l3_process_inbound_buffer(struct qeth_card *card,
 					card->dev->addr_len);
 				netif_receive_skb(skb);
 			} else {
-				is_vlan = qeth_l3_rebuild_skb(card, skb, hdr,
-						      &vlan_tag);
+				qeth_l3_rebuild_skb(card, skb, hdr);
 				len = skb->len;
-				if (is_vlan && !card->options.sniffer)
-					__vlan_hwaccel_put_tag(skb,
-						htons(ETH_P_8021Q), vlan_tag);
 				napi_gro_receive(&card->napi, skb);
 			}
 			break;
@@ -2771,8 +2768,8 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
 		rc = qeth_do_send_packet(card, queue, new_skb, hdr, hd_len,
 					 hd_len, elements);
 	} else
-		rc = qeth_do_send_packet_fast(card, queue, new_skb, hdr,
-					      data_offset, hd_len);
+		rc = qeth_do_send_packet_fast(queue, new_skb, hdr, data_offset,
+					      hd_len);
 
 	if (!rc) {
 		card->stats.tx_packets++;
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index 7a829ad77783..bd12fdf678be 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -1029,52 +1029,31 @@ static const struct attribute_group qeth_device_rxip_group = {
 	.attrs = qeth_rxip_device_attrs,
 };
 
+static const struct attribute_group *qeth_l3_only_attr_groups[] = {
+	&qeth_l3_device_attr_group,
+	&qeth_device_ipato_group,
+	&qeth_device_vipa_group,
+	&qeth_device_rxip_group,
+	NULL,
+};
+
 int qeth_l3_create_device_attributes(struct device *dev)
 {
-	int ret;
-
-	ret = sysfs_create_group(&dev->kobj, &qeth_l3_device_attr_group);
-	if (ret)
-		return ret;
-
-	ret = sysfs_create_group(&dev->kobj, &qeth_device_ipato_group);
-	if (ret) {
-		sysfs_remove_group(&dev->kobj, &qeth_l3_device_attr_group);
-		return ret;
-	}
-
-	ret = sysfs_create_group(&dev->kobj, &qeth_device_vipa_group);
-	if (ret) {
-		sysfs_remove_group(&dev->kobj, &qeth_l3_device_attr_group);
-		sysfs_remove_group(&dev->kobj, &qeth_device_ipato_group);
-		return ret;
-	}
-
-	ret = sysfs_create_group(&dev->kobj, &qeth_device_rxip_group);
-	if (ret) {
-		sysfs_remove_group(&dev->kobj, &qeth_l3_device_attr_group);
-		sysfs_remove_group(&dev->kobj, &qeth_device_ipato_group);
-		sysfs_remove_group(&dev->kobj, &qeth_device_vipa_group);
-		return ret;
-	}
-	return 0;
+	return sysfs_create_groups(&dev->kobj, qeth_l3_only_attr_groups);
 }
 
 void qeth_l3_remove_device_attributes(struct device *dev)
 {
-	sysfs_remove_group(&dev->kobj, &qeth_l3_device_attr_group);
-	sysfs_remove_group(&dev->kobj, &qeth_device_ipato_group);
-	sysfs_remove_group(&dev->kobj, &qeth_device_vipa_group);
-	sysfs_remove_group(&dev->kobj, &qeth_device_rxip_group);
+	sysfs_remove_groups(&dev->kobj, qeth_l3_only_attr_groups);
 }
 
 const struct attribute_group *qeth_l3_attr_groups[] = {
 	&qeth_device_attr_group,
 	&qeth_device_blkt_group,
-	/* l3 specific, see l3_{create,remove}_device_attributes(): */
+	/* l3 specific, see qeth_l3_only_attr_groups: */
 	&qeth_l3_device_attr_group,
 	&qeth_device_ipato_group,
 	&qeth_device_vipa_group,
 	&qeth_device_rxip_group,
-NULL,
+	NULL,
 };
diff --git a/drivers/scsi/qedi/Kconfig b/drivers/scsi/qedi/Kconfig
index 2ff753ce6e27..d1db92d24889 100644
--- a/drivers/scsi/qedi/Kconfig
+++ b/drivers/scsi/qedi/Kconfig
@@ -4,6 +4,7 @@ config QEDI
 	depends on QED
 	select SCSI_ISCSI_ATTRS
 	select QED_LL2
+	select QED_OOO
 	select QED_ISCSI
 	select ISCSI_BOOT_SYSFS
 	---help---
diff --git a/drivers/thunderbolt/Makefile b/drivers/thunderbolt/Makefile
index 4900febc6c8a..f2f0de27252b 100644
--- a/drivers/thunderbolt/Makefile
+++ b/drivers/thunderbolt/Makefile
@@ -1,3 +1,3 @@
 obj-${CONFIG_THUNDERBOLT} := thunderbolt.o
 thunderbolt-objs := nhi.o ctl.o tb.o switch.o cap.o path.o tunnel_pci.o eeprom.o
-thunderbolt-objs += domain.o dma_port.o icm.o
+thunderbolt-objs += domain.o dma_port.o icm.o property.o xdomain.o
diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c
index 423ae231fc6c..37a7f4c735d0 100644
--- a/drivers/thunderbolt/ctl.c
+++ b/drivers/thunderbolt/ctl.c
@@ -290,20 +290,6 @@ static void tb_cfg_print_error(struct tb_ctl *ctl,
 	}
 }
 
-static void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len)
-{
-	int i;
-	for (i = 0; i < len; i++)
-		dst[i] = cpu_to_be32(src[i]);
-}
-
-static void be32_to_cpu_array(u32 *dst, __be32 *src, size_t len)
-{
-	int i;
-	for (i = 0; i < len; i++)
-		dst[i] = be32_to_cpu(src[i]);
-}
-
 static __be32 tb_crc(const void *data, size_t len)
 {
 	return cpu_to_be32(~__crc32c_le(~0, data, len));
@@ -374,7 +360,7 @@ static int tb_ctl_tx(struct tb_ctl *ctl, const void *data, size_t len,
 	cpu_to_be32_array(pkg->buffer, data, len / 4);
 	*(__be32 *) (pkg->buffer + len) = tb_crc(pkg->buffer, len);
 
-	res = ring_tx(ctl->tx, &pkg->frame);
+	res = tb_ring_tx(ctl->tx, &pkg->frame);
 	if (res) /* ring is stopped */
 		tb_ctl_pkg_free(pkg);
 	return res;
@@ -383,15 +369,15 @@ static int tb_ctl_tx(struct tb_ctl *ctl, const void *data, size_t len,
 /**
  * tb_ctl_handle_event() - acknowledge a plug event, invoke ctl->callback
  */
-static void tb_ctl_handle_event(struct tb_ctl *ctl, enum tb_cfg_pkg_type type,
+static bool tb_ctl_handle_event(struct tb_ctl *ctl, enum tb_cfg_pkg_type type,
 				struct ctl_pkg *pkg, size_t size)
 {
-	ctl->callback(ctl->callback_data, type, pkg->buffer, size);
+	return ctl->callback(ctl->callback_data, type, pkg->buffer, size);
 }
 
 static void tb_ctl_rx_submit(struct ctl_pkg *pkg)
 {
-	ring_rx(pkg->ctl->rx, &pkg->frame); /*
+	tb_ring_rx(pkg->ctl->rx, &pkg->frame); /*
 					     * We ignore failures during stop.
 					     * All rx packets are referenced
 					     * from ctl->rx_packets, so we do
@@ -459,6 +445,8 @@ static void tb_ctl_rx_callback(struct tb_ring *ring, struct ring_frame *frame,
 		break;
 
 	case TB_CFG_PKG_EVENT:
+	case TB_CFG_PKG_XDOMAIN_RESP:
+	case TB_CFG_PKG_XDOMAIN_REQ:
 		if (*(__be32 *)(pkg->buffer + frame->size) != crc32) {
 			tb_ctl_err(pkg->ctl,
 				   "RX: checksum mismatch, dropping packet\n");
@@ -466,8 +454,9 @@ static void tb_ctl_rx_callback(struct tb_ring *ring, struct ring_frame *frame,
 		}
 		/* Fall through */
 	case TB_CFG_PKG_ICM_EVENT:
-		tb_ctl_handle_event(pkg->ctl, frame->eof, pkg, frame->size);
-		goto rx;
+		if (tb_ctl_handle_event(pkg->ctl, frame->eof, pkg, frame->size))
+			goto rx;
+		break;
 
 	default:
 		break;
@@ -626,11 +615,12 @@ struct tb_ctl *tb_ctl_alloc(struct tb_nhi *nhi, event_cb cb, void *cb_data)
 	if (!ctl->frame_pool)
 		goto err;
 
-	ctl->tx = ring_alloc_tx(nhi, 0, 10, RING_FLAG_NO_SUSPEND);
+	ctl->tx = tb_ring_alloc_tx(nhi, 0, 10, RING_FLAG_NO_SUSPEND);
 	if (!ctl->tx)
 		goto err;
 
-	ctl->rx = ring_alloc_rx(nhi, 0, 10, RING_FLAG_NO_SUSPEND);
+	ctl->rx = tb_ring_alloc_rx(nhi, 0, 10, RING_FLAG_NO_SUSPEND, 0xffff,
+				0xffff, NULL, NULL);
 	if (!ctl->rx)
 		goto err;
 
@@ -663,9 +653,9 @@ void tb_ctl_free(struct tb_ctl *ctl)
 		return;
 
 	if (ctl->rx)
-		ring_free(ctl->rx);
+		tb_ring_free(ctl->rx);
 	if (ctl->tx)
-		ring_free(ctl->tx);
+		tb_ring_free(ctl->tx);
 
 	/* free RX packets */
 	for (i = 0; i < TB_CTL_RX_PKG_COUNT; i++)
@@ -684,8 +674,8 @@ void tb_ctl_start(struct tb_ctl *ctl)
 {
 	int i;
 	tb_ctl_info(ctl, "control channel starting...\n");
-	ring_start(ctl->tx); /* is used to ack hotplug packets, start first */
-	ring_start(ctl->rx);
+	tb_ring_start(ctl->tx); /* is used to ack hotplug packets, start first */
+	tb_ring_start(ctl->rx);
 	for (i = 0; i < TB_CTL_RX_PKG_COUNT; i++)
 		tb_ctl_rx_submit(ctl->rx_packets[i]);
 
@@ -706,8 +696,8 @@ void tb_ctl_stop(struct tb_ctl *ctl)
 	ctl->running = false;
 	mutex_unlock(&ctl->request_queue_lock);
 
-	ring_stop(ctl->rx);
-	ring_stop(ctl->tx);
+	tb_ring_stop(ctl->rx);
+	tb_ring_stop(ctl->tx);
 
 	if (!list_empty(&ctl->request_queue))
 		tb_ctl_WARN(ctl, "dangling request in request_queue\n");
diff --git a/drivers/thunderbolt/ctl.h b/drivers/thunderbolt/ctl.h
index dd34f627ce49..3062e0b5f71e 100644
--- a/drivers/thunderbolt/ctl.h
+++ b/drivers/thunderbolt/ctl.h
@@ -9,6 +9,7 @@
 #define _TB_CFG
 
 #include <linux/kref.h>
+#include <linux/thunderbolt.h>
 
 #include "nhi.h"
 #include "tb_msgs.h"
@@ -16,7 +17,7 @@
 /* control channel */
 struct tb_ctl;
 
-typedef void (*event_cb)(void *data, enum tb_cfg_pkg_type type,
+typedef bool (*event_cb)(void *data, enum tb_cfg_pkg_type type,
 			 const void *buf, size_t size);
 
 struct tb_ctl *tb_ctl_alloc(struct tb_nhi *nhi, event_cb cb, void *cb_data);
diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c
index 9f2dcd48974d..9b90115319ce 100644
--- a/drivers/thunderbolt/domain.c
+++ b/drivers/thunderbolt/domain.c
@@ -20,6 +20,98 @@
 
 static DEFINE_IDA(tb_domain_ida);
 
+static bool match_service_id(const struct tb_service_id *id,
+			     const struct tb_service *svc)
+{
+	if (id->match_flags & TBSVC_MATCH_PROTOCOL_KEY) {
+		if (strcmp(id->protocol_key, svc->key))
+			return false;
+	}
+
+	if (id->match_flags & TBSVC_MATCH_PROTOCOL_ID) {
+		if (id->protocol_id != svc->prtcid)
+			return false;
+	}
+
+	if (id->match_flags & TBSVC_MATCH_PROTOCOL_VERSION) {
+		if (id->protocol_version != svc->prtcvers)
+			return false;
+	}
+
+	if (id->match_flags & TBSVC_MATCH_PROTOCOL_VERSION) {
+		if (id->protocol_revision != svc->prtcrevs)
+			return false;
+	}
+
+	return true;
+}
+
+static const struct tb_service_id *__tb_service_match(struct device *dev,
+						      struct device_driver *drv)
+{
+	struct tb_service_driver *driver;
+	const struct tb_service_id *ids;
+	struct tb_service *svc;
+
+	svc = tb_to_service(dev);
+	if (!svc)
+		return NULL;
+
+	driver = container_of(drv, struct tb_service_driver, driver);
+	if (!driver->id_table)
+		return NULL;
+
+	for (ids = driver->id_table; ids->match_flags != 0; ids++) {
+		if (match_service_id(ids, svc))
+			return ids;
+	}
+
+	return NULL;
+}
+
+static int tb_service_match(struct device *dev, struct device_driver *drv)
+{
+	return !!__tb_service_match(dev, drv);
+}
+
+static int tb_service_probe(struct device *dev)
+{
+	struct tb_service *svc = tb_to_service(dev);
+	struct tb_service_driver *driver;
+	const struct tb_service_id *id;
+
+	driver = container_of(dev->driver, struct tb_service_driver, driver);
+	id = __tb_service_match(dev, &driver->driver);
+
+	return driver->probe(svc, id);
+}
+
+static int tb_service_remove(struct device *dev)
+{
+	struct tb_service *svc = tb_to_service(dev);
+	struct tb_service_driver *driver;
+
+	driver = container_of(dev->driver, struct tb_service_driver, driver);
+	if (driver->remove)
+		driver->remove(svc);
+
+	return 0;
+}
+
+static void tb_service_shutdown(struct device *dev)
+{
+	struct tb_service_driver *driver;
+	struct tb_service *svc;
+
+	svc = tb_to_service(dev);
+	if (!svc || !dev->driver)
+		return;
+
+	driver = container_of(dev->driver, struct tb_service_driver, driver);
+	if (driver->shutdown)
+		driver->shutdown(svc);
+}
+
 static const char * const tb_security_names[] = {
 	[TB_SECURITY_NONE] = "none",
 	[TB_SECURITY_USER] = "user",
@@ -52,6 +144,10 @@ static const struct attribute_group *domain_attr_groups[] = {
 
 struct bus_type tb_bus_type = {
 	.name = "thunderbolt",
+	.match = tb_service_match,
+	.probe = tb_service_probe,
+	.remove = tb_service_remove,
+	.shutdown = tb_service_shutdown,
 };
 
 static void tb_domain_release(struct device *dev)
@@ -128,17 +224,26 @@ err_free:
 	return NULL;
 }
 
-static void tb_domain_event_cb(void *data, enum tb_cfg_pkg_type type,
+static bool tb_domain_event_cb(void *data, enum tb_cfg_pkg_type type,
 			       const void *buf, size_t size)
 {
 	struct tb *tb = data;
 
 	if (!tb->cm_ops->handle_event) {
 		tb_warn(tb, "domain does not have event handler\n");
-		return;
+		return true;
 	}
 
-	tb->cm_ops->handle_event(tb, type, buf, size);
+	switch (type) {
+	case TB_CFG_PKG_XDOMAIN_REQ:
+	case TB_CFG_PKG_XDOMAIN_RESP:
+		return tb_xdomain_handle_request(tb, type, buf, size);
+
+	default:
+		tb->cm_ops->handle_event(tb, type, buf, size);
+	}
+
+	return true;
 }
 
 /**
@@ -443,9 +548,92 @@ int tb_domain_disconnect_pcie_paths(struct tb *tb)
 	return tb->cm_ops->disconnect_pcie_paths(tb);
 }
 
+/**
+ * tb_domain_approve_xdomain_paths() - Enable DMA paths for XDomain
+ * @tb: Domain enabling the DMA paths
+ * @xd: XDomain DMA paths are created to
+ *
+ * Calls connection manager specific method to enable DMA paths to the
+ * XDomain in question.
+ *
+ * Return: 0% in case of success and negative errno otherwise. In
+ * particular returns %-ENOTSUPP if the connection manager
+ * implementation does not support XDomains.
+ */
+int tb_domain_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd)
+{
+	if (!tb->cm_ops->approve_xdomain_paths)
+		return -ENOTSUPP;
+
+	return tb->cm_ops->approve_xdomain_paths(tb, xd);
+}
+
+/**
+ * tb_domain_disconnect_xdomain_paths() - Disable DMA paths for XDomain
+ * @tb: Domain disabling the DMA paths
+ * @xd: XDomain whose DMA paths are disconnected
+ *
+ * Calls connection manager specific method to disconnect DMA paths to
+ * the XDomain in question.
+ *
+ * Return: 0% in case of success and negative errno otherwise. In
+ * particular returns %-ENOTSUPP if the connection manager
+ * implementation does not support XDomains.
+ */
+int tb_domain_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd)
+{
+	if (!tb->cm_ops->disconnect_xdomain_paths)
+		return -ENOTSUPP;
+
+	return tb->cm_ops->disconnect_xdomain_paths(tb, xd);
+}
+
+static int disconnect_xdomain(struct device *dev, void *data)
+{
+	struct tb_xdomain *xd;
+	struct tb *tb = data;
+	int ret = 0;
+
+	xd = tb_to_xdomain(dev);
+	if (xd && xd->tb == tb)
+		ret = tb_xdomain_disable_paths(xd);
+
+	return ret;
+}
+
+/**
+ * tb_domain_disconnect_all_paths() - Disconnect all paths for the domain
+ * @tb: Domain whose paths are disconnected
+ *
+ * This function can be used to disconnect all paths (PCIe, XDomain) for
+ * example in preparation for host NVM firmware upgrade. After this is
+ * called the paths cannot be established without resetting the switch.
+ *
+ * Return: %0 in case of success and negative errno otherwise.
+ */
+int tb_domain_disconnect_all_paths(struct tb *tb)
+{
+	int ret;
+
+	ret = tb_domain_disconnect_pcie_paths(tb);
+	if (ret)
+		return ret;
+
+	return bus_for_each_dev(&tb_bus_type, NULL, tb, disconnect_xdomain);
+}
+
 int tb_domain_init(void)
 {
-	return bus_register(&tb_bus_type);
+	int ret;
+
+	ret = tb_xdomain_init();
+	if (ret)
+		return ret;
+	ret = bus_register(&tb_bus_type);
+	if (ret)
+		tb_xdomain_exit();
+
+	return ret;
 }
 
 void tb_domain_exit(void)
@@ -453,4 +641,5 @@ void tb_domain_exit(void)
 	bus_unregister(&tb_bus_type);
 	ida_destroy(&tb_domain_ida);
 	tb_switch_exit();
+	tb_xdomain_exit();
 }
diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c
index 53250fc057e1..ab02d13f40b7 100644
--- a/drivers/thunderbolt/icm.c
+++ b/drivers/thunderbolt/icm.c
@@ -60,6 +60,8 @@
  * @get_route: Find a route string for given switch
  * @device_connected: Handle device connected ICM message
  * @device_disconnected: Handle device disconnected ICM message
+ * @xdomain_connected - Handle XDomain connected ICM message
+ * @xdomain_disconnected - Handle XDomain disconnected ICM message
  */
 struct icm {
 	struct mutex request_lock;
@@ -74,6 +76,10 @@ struct icm {
 				 const struct icm_pkg_header *hdr);
 	void (*device_disconnected)(struct tb *tb,
 				    const struct icm_pkg_header *hdr);
+	void (*xdomain_connected)(struct tb *tb,
+				  const struct icm_pkg_header *hdr);
+	void (*xdomain_disconnected)(struct tb *tb,
+				     const struct icm_pkg_header *hdr);
 };
 
 struct icm_notification {
@@ -89,7 +95,10 @@ static inline struct tb *icm_to_tb(struct icm *icm)
 
 static inline u8 phy_port_from_route(u64 route, u8 depth)
 {
-	return tb_switch_phy_port_from_link(route >> ((depth - 1) * 8));
+	u8 link;
+
+	link = depth ? route >> ((depth - 1) * 8) : route;
+	return tb_phy_port_from_link(link);
 }
 
 static inline u8 dual_link_from_link(u8 link)
@@ -320,6 +329,51 @@ static int icm_fr_challenge_switch_key(struct tb *tb, struct tb_switch *sw,
 	return 0;
 }
 
+static int icm_fr_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd)
+{
+	struct icm_fr_pkg_approve_xdomain_response reply;
+	struct icm_fr_pkg_approve_xdomain request;
+	int ret;
+
+	memset(&request, 0, sizeof(request));
+	request.hdr.code = ICM_APPROVE_XDOMAIN;
+	request.link_info = xd->depth << ICM_LINK_INFO_DEPTH_SHIFT | xd->link;
+	memcpy(&request.remote_uuid, xd->remote_uuid, sizeof(*xd->remote_uuid));
+
+	request.transmit_path = xd->transmit_path;
+	request.transmit_ring = xd->transmit_ring;
+	request.receive_path = xd->receive_path;
+	request.receive_ring = xd->receive_ring;
+
+	memset(&reply, 0, sizeof(reply));
+	ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply),
+			  1, ICM_TIMEOUT);
+	if (ret)
+		return ret;
+
+	if (reply.hdr.flags & ICM_FLAGS_ERROR)
+		return -EIO;
+
+	return 0;
+}
+
+static int icm_fr_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd)
+{
+	u8 phy_port;
+	u8 cmd;
+
+	phy_port = tb_phy_port_from_link(xd->link);
+	if (phy_port == 0)
+		cmd = NHI_MAILBOX_DISCONNECT_PA;
+	else
+		cmd = NHI_MAILBOX_DISCONNECT_PB;
+
+	nhi_mailbox_cmd(tb->nhi, cmd, 1);
+	usleep_range(10, 50);
+	nhi_mailbox_cmd(tb->nhi, cmd, 2);
+	return 0;
+}
+
 static void remove_switch(struct tb_switch *sw)
 {
 	struct tb_switch *parent_sw;
@@ -475,6 +529,141 @@ icm_fr_device_disconnected(struct tb *tb, const struct icm_pkg_header *hdr)
 	tb_switch_put(sw);
 }
 
+static void remove_xdomain(struct tb_xdomain *xd)
+{
+	struct tb_switch *sw;
+
+	sw = tb_to_switch(xd->dev.parent);
+	tb_port_at(xd->route, sw)->xdomain = NULL;
+	tb_xdomain_remove(xd);
+}
+
+static void
+icm_fr_xdomain_connected(struct tb *tb, const struct icm_pkg_header *hdr)
+{
+	const struct icm_fr_event_xdomain_connected *pkg =
+		(const struct icm_fr_event_xdomain_connected *)hdr;
+	struct tb_xdomain *xd;
+	struct tb_switch *sw;
+	u8 link, depth;
+	bool approved;
+	u64 route;
+
+	/*
+	 * After NVM upgrade adding root switch device fails because we
+	 * initiated reset. During that time ICM might still send
+	 * XDomain connected message which we ignore here.
+	 */
+	if (!tb->root_switch)
+		return;
+
+	link = pkg->link_info & ICM_LINK_INFO_LINK_MASK;
+	depth = (pkg->link_info & ICM_LINK_INFO_DEPTH_MASK) >>
+		ICM_LINK_INFO_DEPTH_SHIFT;
+	approved = pkg->link_info & ICM_LINK_INFO_APPROVED;
+
+	if (link > ICM_MAX_LINK || depth > ICM_MAX_DEPTH) {
+		tb_warn(tb, "invalid topology %u.%u, ignoring\n", link, depth);
+		return;
+	}
+
+	route = get_route(pkg->local_route_hi, pkg->local_route_lo);
+
+	xd = tb_xdomain_find_by_uuid(tb, &pkg->remote_uuid);
+	if (xd) {
+		u8 xd_phy_port, phy_port;
+
+		xd_phy_port = phy_port_from_route(xd->route, xd->depth);
+		phy_port = phy_port_from_route(route, depth);
+
+		if (xd->depth == depth && xd_phy_port == phy_port) {
+			xd->link = link;
+			xd->route = route;
+			xd->is_unplugged = false;
+			tb_xdomain_put(xd);
+			return;
+		}
+
+		/*
+		 * If we find an existing XDomain connection remove it
+		 * now. We need to go through login handshake and
+		 * everything anyway to be able to re-establish the
+		 * connection.
+		 */
+		remove_xdomain(xd);
+		tb_xdomain_put(xd);
+	}
+
+	/*
+	 * Look if there already exists an XDomain in the same place
+	 * than the new one and in that case remove it because it is
+	 * most likely another host that got disconnected.
+	 */
+	xd = tb_xdomain_find_by_link_depth(tb, link, depth);
+	if (!xd) {
+		u8 dual_link;
+
+		dual_link = dual_link_from_link(link);
+		if (dual_link)
+			xd = tb_xdomain_find_by_link_depth(tb, dual_link,
+							   depth);
+	}
+	if (xd) {
+		remove_xdomain(xd);
+		tb_xdomain_put(xd);
+	}
+
+	/*
+	 * If the user disconnected a switch during suspend and
+	 * connected another host to the same port, remove the switch
+	 * first.
+	 */
+	sw = get_switch_at_route(tb->root_switch, route);
+	if (sw)
+		remove_switch(sw);
+
+	sw = tb_switch_find_by_link_depth(tb, link, depth);
+	if (!sw) {
+		tb_warn(tb, "no switch exists at %u.%u, ignoring\n", link,
+			depth);
+		return;
+	}
+
+	xd = tb_xdomain_alloc(sw->tb, &sw->dev, route,
+			      &pkg->local_uuid, &pkg->remote_uuid);
+	if (!xd) {
+		tb_switch_put(sw);
+		return;
+	}
+
+	xd->link = link;
+	xd->depth = depth;
+
+	tb_port_at(route, sw)->xdomain = xd;
+
+	tb_xdomain_add(xd);
+	tb_switch_put(sw);
+}
+
+static void
+icm_fr_xdomain_disconnected(struct tb *tb, const struct icm_pkg_header *hdr)
+{
+	const struct icm_fr_event_xdomain_disconnected *pkg =
+		(const struct icm_fr_event_xdomain_disconnected *)hdr;
+	struct tb_xdomain *xd;
+
+	/*
+	 * If the connection is through one or multiple devices, the
+	 * XDomain device is removed along with them so it is fine if we
+	 * cannot find it here.
+	 */
+	xd = tb_xdomain_find_by_uuid(tb, &pkg->remote_uuid);
+	if (xd) {
+		remove_xdomain(xd);
+		tb_xdomain_put(xd);
+	}
+}
+
 static struct pci_dev *get_upstream_port(struct pci_dev *pdev)
 {
 	struct pci_dev *parent;
@@ -594,6 +783,12 @@ static void icm_handle_notification(struct work_struct *work)
 	case ICM_EVENT_DEVICE_DISCONNECTED:
 		icm->device_disconnected(tb, n->pkg);
 		break;
+	case ICM_EVENT_XDOMAIN_CONNECTED:
+		icm->xdomain_connected(tb, n->pkg);
+		break;
+	case ICM_EVENT_XDOMAIN_DISCONNECTED:
+		icm->xdomain_disconnected(tb, n->pkg);
+		break;
 	}
 
 	mutex_unlock(&tb->lock);
@@ -927,6 +1122,10 @@ static void icm_unplug_children(struct tb_switch *sw)
 
 		if (tb_is_upstream_port(port))
 			continue;
+		if (port->xdomain) {
+			port->xdomain->is_unplugged = true;
+			continue;
+		}
 		if (!port->remote)
 			continue;
 
@@ -943,6 +1142,13 @@ static void icm_free_unplugged_children(struct tb_switch *sw)
 
 		if (tb_is_upstream_port(port))
 			continue;
+
+		if (port->xdomain && port->xdomain->is_unplugged) {
+			tb_xdomain_remove(port->xdomain);
+			port->xdomain = NULL;
+			continue;
+		}
+
 		if (!port->remote)
 			continue;
 
@@ -1009,8 +1215,10 @@ static int icm_start(struct tb *tb)
 	tb->root_switch->no_nvm_upgrade = x86_apple_machine;
 
 	ret = tb_switch_add(tb->root_switch);
-	if (ret)
+	if (ret) {
 		tb_switch_put(tb->root_switch);
+		tb->root_switch = NULL;
+	}
 
 	return ret;
 }
@@ -1042,6 +1250,8 @@ static const struct tb_cm_ops icm_fr_ops = {
 	.add_switch_key = icm_fr_add_switch_key,
 	.challenge_switch_key = icm_fr_challenge_switch_key,
 	.disconnect_pcie_paths = icm_disconnect_pcie_paths,
+	.approve_xdomain_paths = icm_fr_approve_xdomain_paths,
+	.disconnect_xdomain_paths = icm_fr_disconnect_xdomain_paths,
 };
 
 struct tb *icm_probe(struct tb_nhi *nhi)
@@ -1064,6 +1274,8 @@ struct tb *icm_probe(struct tb_nhi *nhi)
 		icm->get_route = icm_fr_get_route;
 		icm->device_connected = icm_fr_device_connected;
 		icm->device_disconnected = icm_fr_device_disconnected;
+		icm->xdomain_connected = icm_fr_xdomain_connected;
+		icm->xdomain_disconnected = icm_fr_xdomain_disconnected;
 		tb->cm_ops = &icm_fr_ops;
 		break;
 
@@ -1077,6 +1289,8 @@ struct tb *icm_probe(struct tb_nhi *nhi)
 		icm->get_route = icm_ar_get_route;
 		icm->device_connected = icm_fr_device_connected;
 		icm->device_disconnected = icm_fr_device_disconnected;
+		icm->xdomain_connected = icm_fr_xdomain_connected;
+		icm->xdomain_disconnected = icm_fr_xdomain_disconnected;
 		tb->cm_ops = &icm_fr_ops;
 		break;
 	}
diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index 05af126a2435..419a7a90bce0 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -22,6 +22,14 @@
 #define RING_TYPE(ring) ((ring)->is_tx ? "TX ring" : "RX ring")
 
 /*
+ * Used to enable end-to-end workaround for missing RX packets. Do not
+ * use this ring for anything else.
+ */
+#define RING_E2E_UNUSED_HOPID	2
+/* HopIDs 0-7 are reserved by the Thunderbolt protocol */
+#define RING_FIRST_USABLE_HOPID	8
+
+/*
  * Minimal number of vectors when we use MSI-X. Two for control channel
  * Rx/Tx and the rest four are for cross domain DMA paths.
  */
@@ -206,8 +214,10 @@ static void ring_work(struct work_struct *work)
 	struct tb_ring *ring = container_of(work, typeof(*ring), work);
 	struct ring_frame *frame;
 	bool canceled = false;
+	unsigned long flags;
 	LIST_HEAD(done);
-	mutex_lock(&ring->lock);
+
+	spin_lock_irqsave(&ring->lock, flags);
 
 	if (!ring->running) {
 		/*  Move all frames to done and mark them as canceled. */
@@ -229,30 +239,14 @@ static void ring_work(struct work_struct *work)
 			frame->eof = ring->descriptors[ring->tail].eof;
 			frame->sof = ring->descriptors[ring->tail].sof;
 			frame->flags = ring->descriptors[ring->tail].flags;
-			if (frame->sof != 0)
-				dev_WARN(&ring->nhi->pdev->dev,
-					 "%s %d got unexpected SOF: %#x\n",
-					 RING_TYPE(ring), ring->hop,
-					 frame->sof);
-			/*
-			 * known flags:
-			 * raw not enabled, interupt not set: 0x2=0010
-			 * raw enabled: 0xa=1010
-			 * raw not enabled: 0xb=1011
-			 * partial frame (>MAX_FRAME_SIZE): 0xe=1110
-			 */
-			if (frame->flags != 0xa)
-				dev_WARN(&ring->nhi->pdev->dev,
-					 "%s %d got unexpected flags: %#x\n",
-					 RING_TYPE(ring), ring->hop,
-					 frame->flags);
 		}
 		ring->tail = (ring->tail + 1) % ring->size;
 	}
 	ring_write_descriptors(ring);
 
 invoke_callback:
-	mutex_unlock(&ring->lock); /* allow callbacks to schedule new work */
+	/* allow callbacks to schedule new work */
+	spin_unlock_irqrestore(&ring->lock, flags);
 	while (!list_empty(&done)) {
 		frame = list_first_entry(&done, typeof(*frame), list);
 		/*
@@ -260,29 +254,128 @@ invoke_callback:
 		 * Do not hold on to it.
 		 */
 		list_del_init(&frame->list);
-		frame->callback(ring, frame, canceled);
+		if (frame->callback)
+			frame->callback(ring, frame, canceled);
 	}
 }
 
-int __ring_enqueue(struct tb_ring *ring, struct ring_frame *frame)
+int __tb_ring_enqueue(struct tb_ring *ring, struct ring_frame *frame)
 {
+	unsigned long flags;
 	int ret = 0;
-	mutex_lock(&ring->lock);
+
+	spin_lock_irqsave(&ring->lock, flags);
 	if (ring->running) {
 		list_add_tail(&frame->list, &ring->queue);
 		ring_write_descriptors(ring);
 	} else {
 		ret = -ESHUTDOWN;
 	}
-	mutex_unlock(&ring->lock);
+	spin_unlock_irqrestore(&ring->lock, flags);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(__tb_ring_enqueue);
+
+/**
+ * tb_ring_poll() - Poll one completed frame from the ring
+ * @ring: Ring to poll
+ *
+ * This function can be called when @start_poll callback of the @ring
+ * has been called. It will read one completed frame from the ring and
+ * return it to the caller. Returns %NULL if there is no more completed
+ * frames.
+ */
+struct ring_frame *tb_ring_poll(struct tb_ring *ring)
+{
+	struct ring_frame *frame = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ring->lock, flags);
+	if (!ring->running)
+		goto unlock;
+	if (ring_empty(ring))
+		goto unlock;
+
+	if (ring->descriptors[ring->tail].flags & RING_DESC_COMPLETED) {
+		frame = list_first_entry(&ring->in_flight, typeof(*frame),
+					 list);
+		list_del_init(&frame->list);
+
+		if (!ring->is_tx) {
+			frame->size = ring->descriptors[ring->tail].length;
+			frame->eof = ring->descriptors[ring->tail].eof;
+			frame->sof = ring->descriptors[ring->tail].sof;
+			frame->flags = ring->descriptors[ring->tail].flags;
+		}
+
+		ring->tail = (ring->tail + 1) % ring->size;
+	}
+
+unlock:
+	spin_unlock_irqrestore(&ring->lock, flags);
+	return frame;
+}
+EXPORT_SYMBOL_GPL(tb_ring_poll);
+
+static void __ring_interrupt_mask(struct tb_ring *ring, bool mask)
+{
+	int idx = ring_interrupt_index(ring);
+	int reg = REG_RING_INTERRUPT_BASE + idx / 32 * 4;
+	int bit = idx % 32;
+	u32 val;
+
+	val = ioread32(ring->nhi->iobase + reg);
+	if (mask)
+		val &= ~BIT(bit);
+	else
+		val |= BIT(bit);
+	iowrite32(val, ring->nhi->iobase + reg);
+}
+
+/* Both @nhi->lock and @ring->lock should be held */
+static void __ring_interrupt(struct tb_ring *ring)
+{
+	if (!ring->running)
+		return;
+
+	if (ring->start_poll) {
+		__ring_interrupt_mask(ring, false);
+		ring->start_poll(ring->poll_data);
+	} else {
+		schedule_work(&ring->work);
+	}
+}
+
+/**
+ * tb_ring_poll_complete() - Re-start interrupt for the ring
+ * @ring: Ring to re-start the interrupt
+ *
+ * This will re-start (unmask) the ring interrupt once the user is done
+ * with polling.
+ */
+void tb_ring_poll_complete(struct tb_ring *ring)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ring->nhi->lock, flags);
+	spin_lock(&ring->lock);
+	if (ring->start_poll)
+		__ring_interrupt_mask(ring, false);
+	spin_unlock(&ring->lock);
+	spin_unlock_irqrestore(&ring->nhi->lock, flags);
+}
+EXPORT_SYMBOL_GPL(tb_ring_poll_complete);
 
 static irqreturn_t ring_msix(int irq, void *data)
 {
 	struct tb_ring *ring = data;
 
-	schedule_work(&ring->work);
+	spin_lock(&ring->nhi->lock);
+	spin_lock(&ring->lock);
+	__ring_interrupt(ring);
+	spin_unlock(&ring->lock);
+	spin_unlock(&ring->nhi->lock);
+
 	return IRQ_HANDLED;
 }
 
@@ -320,30 +413,81 @@ static void ring_release_msix(struct tb_ring *ring)
 	ring->irq = 0;
 }
 
-static struct tb_ring *ring_alloc(struct tb_nhi *nhi, u32 hop, int size,
-				  bool transmit, unsigned int flags)
+static int nhi_alloc_hop(struct tb_nhi *nhi, struct tb_ring *ring)
+{
+	int ret = 0;
+
+	spin_lock_irq(&nhi->lock);
+
+	if (ring->hop < 0) {
+		unsigned int i;
+
+		/*
+		 * Automatically allocate HopID from the non-reserved
+		 * range 8 .. hop_count - 1.
+		 */
+		for (i = RING_FIRST_USABLE_HOPID; i < nhi->hop_count; i++) {
+			if (ring->is_tx) {
+				if (!nhi->tx_rings[i]) {
+					ring->hop = i;
+					break;
+				}
+			} else {
+				if (!nhi->rx_rings[i]) {
+					ring->hop = i;
+					break;
+				}
+			}
+		}
+	}
+
+	if (ring->hop < 0 || ring->hop >= nhi->hop_count) {
+		dev_warn(&nhi->pdev->dev, "invalid hop: %d\n", ring->hop);
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+	if (ring->is_tx && nhi->tx_rings[ring->hop]) {
+		dev_warn(&nhi->pdev->dev, "TX hop %d already allocated\n",
+			 ring->hop);
+		ret = -EBUSY;
+		goto err_unlock;
+	} else if (!ring->is_tx && nhi->rx_rings[ring->hop]) {
+		dev_warn(&nhi->pdev->dev, "RX hop %d already allocated\n",
+			 ring->hop);
+		ret = -EBUSY;
+		goto err_unlock;
+	}
+
+	if (ring->is_tx)
+		nhi->tx_rings[ring->hop] = ring;
+	else
+		nhi->rx_rings[ring->hop] = ring;
+
+err_unlock:
+	spin_unlock_irq(&nhi->lock);
+
+	return ret;
+}
+
+static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size,
+				     bool transmit, unsigned int flags,
+				     u16 sof_mask, u16 eof_mask,
+				     void (*start_poll)(void *),
+				     void *poll_data)
 {
 	struct tb_ring *ring = NULL;
 	dev_info(&nhi->pdev->dev, "allocating %s ring %d of size %d\n",
 		 transmit ? "TX" : "RX", hop, size);
 
-	mutex_lock(&nhi->lock);
-	if (hop >= nhi->hop_count) {
-		dev_WARN(&nhi->pdev->dev, "invalid hop: %d\n", hop);
-		goto err;
-	}
-	if (transmit && nhi->tx_rings[hop]) {
-		dev_WARN(&nhi->pdev->dev, "TX hop %d already allocated\n", hop);
-		goto err;
-	} else if (!transmit && nhi->rx_rings[hop]) {
-		dev_WARN(&nhi->pdev->dev, "RX hop %d already allocated\n", hop);
-		goto err;
-	}
+	/* Tx Ring 2 is reserved for E2E workaround */
+	if (transmit && hop == RING_E2E_UNUSED_HOPID)
+		return NULL;
+
 	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
 	if (!ring)
-		goto err;
+		return NULL;
 
-	mutex_init(&ring->lock);
+	spin_lock_init(&ring->lock);
 	INIT_LIST_HEAD(&ring->queue);
 	INIT_LIST_HEAD(&ring->in_flight);
 	INIT_WORK(&ring->work, ring_work);
@@ -353,55 +497,88 @@ static struct tb_ring *ring_alloc(struct tb_nhi *nhi, u32 hop, int size,
 	ring->is_tx = transmit;
 	ring->size = size;
 	ring->flags = flags;
+	ring->sof_mask = sof_mask;
+	ring->eof_mask = eof_mask;
 	ring->head = 0;
 	ring->tail = 0;
 	ring->running = false;
-
-	if (ring_request_msix(ring, flags & RING_FLAG_NO_SUSPEND))
-		goto err;
+	ring->start_poll = start_poll;
+	ring->poll_data = poll_data;
 
 	ring->descriptors = dma_alloc_coherent(&ring->nhi->pdev->dev,
 			size * sizeof(*ring->descriptors),
 			&ring->descriptors_dma, GFP_KERNEL | __GFP_ZERO);
 	if (!ring->descriptors)
-		goto err;
+		goto err_free_ring;
+
+	if (ring_request_msix(ring, flags & RING_FLAG_NO_SUSPEND))
+		goto err_free_descs;
+
+	if (nhi_alloc_hop(nhi, ring))
+		goto err_release_msix;
 
-	if (transmit)
-		nhi->tx_rings[hop] = ring;
-	else
-		nhi->rx_rings[hop] = ring;
-	mutex_unlock(&nhi->lock);
 	return ring;
 
-err:
-	if (ring)
-		mutex_destroy(&ring->lock);
+err_release_msix:
+	ring_release_msix(ring);
+err_free_descs:
+	dma_free_coherent(&ring->nhi->pdev->dev,
+			  ring->size * sizeof(*ring->descriptors),
+			  ring->descriptors, ring->descriptors_dma);
+err_free_ring:
 	kfree(ring);
-	mutex_unlock(&nhi->lock);
+
 	return NULL;
 }
 
-struct tb_ring *ring_alloc_tx(struct tb_nhi *nhi, int hop, int size,
-			      unsigned int flags)
+/**
+ * tb_ring_alloc_tx() - Allocate DMA ring for transmit
+ * @nhi: Pointer to the NHI the ring is to be allocated
+ * @hop: HopID (ring) to allocate
+ * @size: Number of entries in the ring
+ * @flags: Flags for the ring
+ */
+struct tb_ring *tb_ring_alloc_tx(struct tb_nhi *nhi, int hop, int size,
+				 unsigned int flags)
 {
-	return ring_alloc(nhi, hop, size, true, flags);
+	return tb_ring_alloc(nhi, hop, size, true, flags, 0, 0, NULL, NULL);
 }
+EXPORT_SYMBOL_GPL(tb_ring_alloc_tx);
 
-struct tb_ring *ring_alloc_rx(struct tb_nhi *nhi, int hop, int size,
-			      unsigned int flags)
+/**
+ * tb_ring_alloc_rx() - Allocate DMA ring for receive
+ * @nhi: Pointer to the NHI the ring is to be allocated
+ * @hop: HopID (ring) to allocate. Pass %-1 for automatic allocation.
+ * @size: Number of entries in the ring
+ * @flags: Flags for the ring
+ * @sof_mask: Mask of PDF values that start a frame
+ * @eof_mask: Mask of PDF values that end a frame
+ * @start_poll: If not %NULL the ring will call this function when an
+ *		interrupt is triggered and masked, instead of callback
+ *		in each Rx frame.
+ * @poll_data: Optional data passed to @start_poll
+ */
+struct tb_ring *tb_ring_alloc_rx(struct tb_nhi *nhi, int hop, int size,
+				 unsigned int flags, u16 sof_mask, u16 eof_mask,
+				 void (*start_poll)(void *), void *poll_data)
 {
-	return ring_alloc(nhi, hop, size, false, flags);
+	return tb_ring_alloc(nhi, hop, size, false, flags, sof_mask, eof_mask,
+			     start_poll, poll_data);
 }
+EXPORT_SYMBOL_GPL(tb_ring_alloc_rx);
 
 /**
- * ring_start() - enable a ring
+ * tb_ring_start() - enable a ring
  *
- * Must not be invoked in parallel with ring_stop().
+ * Must not be invoked in parallel with tb_ring_stop().
  */
-void ring_start(struct tb_ring *ring)
+void tb_ring_start(struct tb_ring *ring)
 {
-	mutex_lock(&ring->nhi->lock);
-	mutex_lock(&ring->lock);
+	u16 frame_size;
+	u32 flags;
+
+	spin_lock_irq(&ring->nhi->lock);
+	spin_lock(&ring->lock);
 	if (ring->nhi->going_away)
 		goto err;
 	if (ring->running) {
@@ -411,43 +588,65 @@ void ring_start(struct tb_ring *ring)
 	dev_info(&ring->nhi->pdev->dev, "starting %s %d\n",
 		 RING_TYPE(ring), ring->hop);
 
+	if (ring->flags & RING_FLAG_FRAME) {
+		/* Means 4096 */
+		frame_size = 0;
+		flags = RING_FLAG_ENABLE;
+	} else {
+		frame_size = TB_FRAME_SIZE;
+		flags = RING_FLAG_ENABLE | RING_FLAG_RAW;
+	}
+
+	if (ring->flags & RING_FLAG_E2E && !ring->is_tx) {
+		u32 hop;
+
+		/*
+		 * In order not to lose Rx packets we enable end-to-end
+		 * workaround which transfers Rx credits to an unused Tx
+		 * HopID.
+		 */
+		hop = RING_E2E_UNUSED_HOPID << REG_RX_OPTIONS_E2E_HOP_SHIFT;
+		hop &= REG_RX_OPTIONS_E2E_HOP_MASK;
+		flags |= hop | RING_FLAG_E2E_FLOW_CONTROL;
+	}
+
 	ring_iowrite64desc(ring, ring->descriptors_dma, 0);
 	if (ring->is_tx) {
 		ring_iowrite32desc(ring, ring->size, 12);
 		ring_iowrite32options(ring, 0, 4); /* time releated ? */
-		ring_iowrite32options(ring,
-				      RING_FLAG_ENABLE | RING_FLAG_RAW, 0);
+		ring_iowrite32options(ring, flags, 0);
 	} else {
-		ring_iowrite32desc(ring,
-				   (TB_FRAME_SIZE << 16) | ring->size, 12);
-		ring_iowrite32options(ring, 0xffffffff, 4); /* SOF EOF mask */
-		ring_iowrite32options(ring,
-				      RING_FLAG_ENABLE | RING_FLAG_RAW, 0);
+		u32 sof_eof_mask = ring->sof_mask << 16 | ring->eof_mask;
+
+		ring_iowrite32desc(ring, (frame_size << 16) | ring->size, 12);
+		ring_iowrite32options(ring, sof_eof_mask, 4);
+		ring_iowrite32options(ring, flags, 0);
 	}
 	ring_interrupt_active(ring, true);
 	ring->running = true;
 err:
-	mutex_unlock(&ring->lock);
-	mutex_unlock(&ring->nhi->lock);
+	spin_unlock(&ring->lock);
+	spin_unlock_irq(&ring->nhi->lock);
 }
-
+EXPORT_SYMBOL_GPL(tb_ring_start);
 
 /**
- * ring_stop() - shutdown a ring
+ * tb_ring_stop() - shutdown a ring
  *
  * Must not be invoked from a callback.
  *
- * This method will disable the ring. Further calls to ring_tx/ring_rx will
- * return -ESHUTDOWN until ring_stop has been called.
+ * This method will disable the ring. Further calls to
+ * tb_ring_tx/tb_ring_rx will return -ESHUTDOWN until ring_stop has been
+ * called.
  *
  * All enqueued frames will be canceled and their callbacks will be executed
  * with frame->canceled set to true (on the callback thread). This method
  * returns only after all callback invocations have finished.
  */
-void ring_stop(struct tb_ring *ring)
+void tb_ring_stop(struct tb_ring *ring)
 {
-	mutex_lock(&ring->nhi->lock);
-	mutex_lock(&ring->lock);
+	spin_lock_irq(&ring->nhi->lock);
+	spin_lock(&ring->lock);
 	dev_info(&ring->nhi->pdev->dev, "stopping %s %d\n",
 		 RING_TYPE(ring), ring->hop);
 	if (ring->nhi->going_away)
@@ -468,8 +667,8 @@ void ring_stop(struct tb_ring *ring)
 	ring->running = false;
 
 err:
-	mutex_unlock(&ring->lock);
-	mutex_unlock(&ring->nhi->lock);
+	spin_unlock(&ring->lock);
+	spin_unlock_irq(&ring->nhi->lock);
 
 	/*
 	 * schedule ring->work to invoke callbacks on all remaining frames.
@@ -477,9 +676,10 @@ err:
 	schedule_work(&ring->work);
 	flush_work(&ring->work);
 }
+EXPORT_SYMBOL_GPL(tb_ring_stop);
 
 /*
- * ring_free() - free ring
+ * tb_ring_free() - free ring
  *
  * When this method returns all invocations of ring->callback will have
  * finished.
@@ -488,9 +688,9 @@ err:
  *
  * Must NOT be called from ring_frame->callback!
  */
-void ring_free(struct tb_ring *ring)
+void tb_ring_free(struct tb_ring *ring)
 {
-	mutex_lock(&ring->nhi->lock);
+	spin_lock_irq(&ring->nhi->lock);
 	/*
 	 * Dissociate the ring from the NHI. This also ensures that
 	 * nhi_interrupt_work cannot reschedule ring->work.
@@ -504,6 +704,7 @@ void ring_free(struct tb_ring *ring)
 		dev_WARN(&ring->nhi->pdev->dev, "%s %d still running\n",
 			 RING_TYPE(ring), ring->hop);
 	}
+	spin_unlock_irq(&ring->nhi->lock);
 
 	ring_release_msix(ring);
 
@@ -520,16 +721,15 @@ void ring_free(struct tb_ring *ring)
 		 RING_TYPE(ring),
 		 ring->hop);
 
-	mutex_unlock(&ring->nhi->lock);
 	/**
 	 * ring->work can no longer be scheduled (it is scheduled only
 	 * by nhi_interrupt_work, ring_stop and ring_msix). Wait for it
 	 * to finish before freeing the ring.
 	 */
 	flush_work(&ring->work);
-	mutex_destroy(&ring->lock);
 	kfree(ring);
 }
+EXPORT_SYMBOL_GPL(tb_ring_free);
 
 /**
  * nhi_mailbox_cmd() - Send a command through NHI mailbox
@@ -595,7 +795,7 @@ static void nhi_interrupt_work(struct work_struct *work)
 	int type = 0; /* current interrupt type 0: TX, 1: RX, 2: RX overflow */
 	struct tb_ring *ring;
 
-	mutex_lock(&nhi->lock);
+	spin_lock_irq(&nhi->lock);
 
 	/*
 	 * Starting at REG_RING_NOTIFY_BASE there are three status bitfields
@@ -630,10 +830,12 @@ static void nhi_interrupt_work(struct work_struct *work)
 				 hop);
 			continue;
 		}
-		/* we do not check ring->running, this is done in ring->work */
-		schedule_work(&ring->work);
+
+		spin_lock(&ring->lock);
+		__ring_interrupt(ring);
+		spin_unlock(&ring->lock);
 	}
-	mutex_unlock(&nhi->lock);
+	spin_unlock_irq(&nhi->lock);
 }
 
 static irqreturn_t nhi_msi(int irq, void *data)
@@ -651,6 +853,22 @@ static int nhi_suspend_noirq(struct device *dev)
 	return tb_domain_suspend_noirq(tb);
 }
 
+static void nhi_enable_int_throttling(struct tb_nhi *nhi)
+{
+	/* Throttling is specified in 256ns increments */
+	u32 throttle = DIV_ROUND_UP(128 * NSEC_PER_USEC, 256);
+	unsigned int i;
+
+	/*
+	 * Configure interrupt throttling for all vectors even if we
+	 * only use few.
+	 */
+	for (i = 0; i < MSIX_MAX_VECS; i++) {
+		u32 reg = REG_INT_THROTTLING_RATE + i * 4;
+		iowrite32(throttle, nhi->iobase + reg);
+	}
+}
+
 static int nhi_resume_noirq(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -663,6 +881,8 @@ static int nhi_resume_noirq(struct device *dev)
 	 */
 	if (!pci_device_is_present(pdev))
 		tb->nhi->going_away = true;
+	else
+		nhi_enable_int_throttling(tb->nhi);
 
 	return tb_domain_resume_noirq(tb);
 }
@@ -705,7 +925,6 @@ static void nhi_shutdown(struct tb_nhi *nhi)
 		devm_free_irq(&nhi->pdev->dev, nhi->pdev->irq, nhi);
 		flush_work(&nhi->interrupt_work);
 	}
-	mutex_destroy(&nhi->lock);
 	ida_destroy(&nhi->msix_ida);
 }
 
@@ -717,6 +936,8 @@ static int nhi_init_msi(struct tb_nhi *nhi)
 	/* In case someone left them on. */
 	nhi_disable_interrupts(nhi);
 
+	nhi_enable_int_throttling(nhi);
+
 	ida_init(&nhi->msix_ida);
 
 	/*
@@ -792,13 +1013,10 @@ static int nhi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return res;
 	}
 
-	mutex_init(&nhi->lock);
+	spin_lock_init(&nhi->lock);
 
 	pci_set_master(pdev);
 
-	/* magic value - clock related? */
-	iowrite32(3906250 / 10000, nhi->iobase + 0x38c00);
-
 	tb = icm_probe(nhi);
 	if (!tb)
 		tb = tb_probe(nhi);
@@ -926,5 +1144,5 @@ static void __exit nhi_unload(void)
 	tb_domain_exit();
 }
 
-module_init(nhi_init);
+fs_initcall(nhi_init);
 module_exit(nhi_unload);
diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h
index 1c7e6b92e235..4476ab4cfd0c 100644
--- a/drivers/thunderbolt/nhi.h
+++ b/drivers/thunderbolt/nhi.h
@@ -8,144 +8,7 @@
 #ifndef DSL3510_H_
 #define DSL3510_H_
 
-#include <linux/idr.h>
-#include <linux/mutex.h>
-#include <linux/workqueue.h>
-
-/**
- * struct tb_nhi - thunderbolt native host interface
- * @lock: Must be held during ring creation/destruction. Is acquired by
- *	  interrupt_work when dispatching interrupts to individual rings.
- * @pdev: Pointer to the PCI device
- * @iobase: MMIO space of the NHI
- * @tx_rings: All Tx rings available on this host controller
- * @rx_rings: All Rx rings available on this host controller
- * @msix_ida: Used to allocate MSI-X vectors for rings
- * @going_away: The host controller device is about to disappear so when
- *		this flag is set, avoid touching the hardware anymore.
- * @interrupt_work: Work scheduled to handle ring interrupt when no
- *		    MSI-X is used.
- * @hop_count: Number of rings (end point hops) supported by NHI.
- */
-struct tb_nhi {
-	struct mutex lock;
-	struct pci_dev *pdev;
-	void __iomem *iobase;
-	struct tb_ring **tx_rings;
-	struct tb_ring **rx_rings;
-	struct ida msix_ida;
-	bool going_away;
-	struct work_struct interrupt_work;
-	u32 hop_count;
-};
-
-/**
- * struct tb_ring - thunderbolt TX or RX ring associated with a NHI
- * @lock: Lock serializing actions to this ring. Must be acquired after
- *	  nhi->lock.
- * @nhi: Pointer to the native host controller interface
- * @size: Size of the ring
- * @hop: Hop (DMA channel) associated with this ring
- * @head: Head of the ring (write next descriptor here)
- * @tail: Tail of the ring (complete next descriptor here)
- * @descriptors: Allocated descriptors for this ring
- * @queue: Queue holding frames to be transferred over this ring
- * @in_flight: Queue holding frames that are currently in flight
- * @work: Interrupt work structure
- * @is_tx: Is the ring Tx or Rx
- * @running: Is the ring running
- * @irq: MSI-X irq number if the ring uses MSI-X. %0 otherwise.
- * @vector: MSI-X vector number the ring uses (only set if @irq is > 0)
- * @flags: Ring specific flags
- */
-struct tb_ring {
-	struct mutex lock;
-	struct tb_nhi *nhi;
-	int size;
-	int hop;
-	int head;
-	int tail;
-	struct ring_desc *descriptors;
-	dma_addr_t descriptors_dma;
-	struct list_head queue;
-	struct list_head in_flight;
-	struct work_struct work;
-	bool is_tx:1;
-	bool running:1;
-	int irq;
-	u8 vector;
-	unsigned int flags;
-};
-
-/* Leave ring interrupt enabled on suspend */
-#define RING_FLAG_NO_SUSPEND	BIT(0)
-
-struct ring_frame;
-typedef void (*ring_cb)(struct tb_ring*, struct ring_frame*, bool canceled);
-
-/**
- * struct ring_frame - for use with ring_rx/ring_tx
- */
-struct ring_frame {
-	dma_addr_t buffer_phy;
-	ring_cb callback;
-	struct list_head list;
-	u32 size:12; /* TX: in, RX: out*/
-	u32 flags:12; /* RX: out */
-	u32 eof:4; /* TX:in, RX: out */
-	u32 sof:4; /* TX:in, RX: out */
-};
-
-#define TB_FRAME_SIZE 0x100    /* minimum size for ring_rx */
-
-struct tb_ring *ring_alloc_tx(struct tb_nhi *nhi, int hop, int size,
-			      unsigned int flags);
-struct tb_ring *ring_alloc_rx(struct tb_nhi *nhi, int hop, int size,
-			      unsigned int flags);
-void ring_start(struct tb_ring *ring);
-void ring_stop(struct tb_ring *ring);
-void ring_free(struct tb_ring *ring);
-
-int __ring_enqueue(struct tb_ring *ring, struct ring_frame *frame);
-
-/**
- * ring_rx() - enqueue a frame on an RX ring
- *
- * frame->buffer, frame->buffer_phy and frame->callback have to be set. The
- * buffer must contain at least TB_FRAME_SIZE bytes.
- *
- * frame->callback will be invoked with frame->size, frame->flags, frame->eof,
- * frame->sof set once the frame has been received.
- *
- * If ring_stop is called after the packet has been enqueued frame->callback
- * will be called with canceled set to true.
- *
- * Return: Returns ESHUTDOWN if ring_stop has been called. Zero otherwise.
- */
-static inline int ring_rx(struct tb_ring *ring, struct ring_frame *frame)
-{
-	WARN_ON(ring->is_tx);
-	return __ring_enqueue(ring, frame);
-}
-
-/**
- * ring_tx() - enqueue a frame on an TX ring
- *
- * frame->buffer, frame->buffer_phy, frame->callback, frame->size, frame->eof
- * and frame->sof have to be set.
- *
- * frame->callback will be invoked with once the frame has been transmitted.
- *
- * If ring_stop is called after the packet has been enqueued frame->callback
- * will be called with canceled set to true.
- *
- * Return: Returns ESHUTDOWN if ring_stop has been called. Zero otherwise.
- */
-static inline int ring_tx(struct tb_ring *ring, struct ring_frame *frame)
-{
-	WARN_ON(!ring->is_tx);
-	return __ring_enqueue(ring, frame);
-}
+#include <linux/thunderbolt.h>
 
 enum nhi_fw_mode {
 	NHI_FW_SAFE_MODE,
@@ -158,6 +21,8 @@ enum nhi_mailbox_cmd {
 	NHI_MAILBOX_SAVE_DEVS = 0x05,
 	NHI_MAILBOX_DISCONNECT_PCIE_PATHS = 0x06,
 	NHI_MAILBOX_DRV_UNLOADS = 0x07,
+	NHI_MAILBOX_DISCONNECT_PA = 0x10,
+	NHI_MAILBOX_DISCONNECT_PB = 0x11,
 	NHI_MAILBOX_ALLOW_ALL_DEVS = 0x23,
 };
 
diff --git a/drivers/thunderbolt/nhi_regs.h b/drivers/thunderbolt/nhi_regs.h
index 752ec04305f3..b3e49d19c01e 100644
--- a/drivers/thunderbolt/nhi_regs.h
+++ b/drivers/thunderbolt/nhi_regs.h
@@ -18,13 +18,6 @@ enum ring_flags {
 	RING_FLAG_ENABLE = 1 << 31,
 };
 
-enum ring_desc_flags {
-	RING_DESC_ISOCH = 0x1, /* TX only? */
-	RING_DESC_COMPLETED = 0x2, /* set by NHI */
-	RING_DESC_POSTED = 0x4, /* always set this */
-	RING_DESC_INTERRUPT = 0x8, /* request an interrupt on completion */
-};
-
 /**
  * struct ring_desc - TX/RX ring entry
  *
@@ -78,6 +71,8 @@ struct ring_desc {
  * ..: unknown
  */
 #define REG_RX_OPTIONS_BASE	0x29800
+#define REG_RX_OPTIONS_E2E_HOP_MASK	GENMASK(22, 12)
+#define REG_RX_OPTIONS_E2E_HOP_SHIFT	12
 
 /*
  * three bitfields: tx, rx, rx overflow
@@ -96,6 +91,8 @@ struct ring_desc {
 #define REG_RING_INTERRUPT_BASE	0x38200
 #define RING_INTERRUPT_REG_COUNT(nhi) ((31 + 2 * nhi->hop_count) / 32)
 
+#define REG_INT_THROTTLING_RATE	0x38c00
+
 /* Interrupt Vector Allocation */
 #define REG_INT_VEC_ALLOC_BASE	0x38c40
 #define REG_INT_VEC_ALLOC_BITS	4
diff --git a/drivers/thunderbolt/property.c b/drivers/thunderbolt/property.c
new file mode 100644
index 000000000000..8fe913a95b4a
--- /dev/null
+++ b/drivers/thunderbolt/property.c
@@ -0,0 +1,670 @@
+/*
+ * Thunderbolt XDomain property support
+ *
+ * Copyright (C) 2017, Intel Corporation
+ * Authors: Michael Jamet <michael.jamet@intel.com>
+ *          Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/uuid.h>
+#include <linux/thunderbolt.h>
+
+struct tb_property_entry {
+	u32 key_hi;
+	u32 key_lo;
+	u16 length;
+	u8 reserved;
+	u8 type;
+	u32 value;
+};
+
+struct tb_property_rootdir_entry {
+	u32 magic;
+	u32 length;
+	struct tb_property_entry entries[];
+};
+
+struct tb_property_dir_entry {
+	u32 uuid[4];
+	struct tb_property_entry entries[];
+};
+
+#define TB_PROPERTY_ROOTDIR_MAGIC	0x55584401
+
+static struct tb_property_dir *__tb_property_parse_dir(const u32 *block,
+	size_t block_len, unsigned int dir_offset, size_t dir_len,
+	bool is_root);
+
+static inline void parse_dwdata(void *dst, const void *src, size_t dwords)
+{
+	be32_to_cpu_array(dst, src, dwords);
+}
+
+static inline void format_dwdata(void *dst, const void *src, size_t dwords)
+{
+	cpu_to_be32_array(dst, src, dwords);
+}
+
+static bool tb_property_entry_valid(const struct tb_property_entry *entry,
+				  size_t block_len)
+{
+	switch (entry->type) {
+	case TB_PROPERTY_TYPE_DIRECTORY:
+	case TB_PROPERTY_TYPE_DATA:
+	case TB_PROPERTY_TYPE_TEXT:
+		if (entry->length > block_len)
+			return false;
+		if (entry->value + entry->length > block_len)
+			return false;
+		break;
+
+	case TB_PROPERTY_TYPE_VALUE:
+		if (entry->length != 1)
+			return false;
+		break;
+	}
+
+	return true;
+}
+
+static bool tb_property_key_valid(const char *key)
+{
+	return key && strlen(key) <= TB_PROPERTY_KEY_SIZE;
+}
+
+static struct tb_property *
+tb_property_alloc(const char *key, enum tb_property_type type)
+{
+	struct tb_property *property;
+
+	property = kzalloc(sizeof(*property), GFP_KERNEL);
+	if (!property)
+		return NULL;
+
+	strcpy(property->key, key);
+	property->type = type;
+	INIT_LIST_HEAD(&property->list);
+
+	return property;
+}
+
+static struct tb_property *tb_property_parse(const u32 *block, size_t block_len,
+					const struct tb_property_entry *entry)
+{
+	char key[TB_PROPERTY_KEY_SIZE + 1];
+	struct tb_property *property;
+	struct tb_property_dir *dir;
+
+	if (!tb_property_entry_valid(entry, block_len))
+		return NULL;
+
+	parse_dwdata(key, entry, 2);
+	key[TB_PROPERTY_KEY_SIZE] = '\0';
+
+	property = tb_property_alloc(key, entry->type);
+	if (!property)
+		return NULL;
+
+	property->length = entry->length;
+
+	switch (property->type) {
+	case TB_PROPERTY_TYPE_DIRECTORY:
+		dir = __tb_property_parse_dir(block, block_len, entry->value,
+					      entry->length, false);
+		if (!dir) {
+			kfree(property);
+			return NULL;
+		}
+		property->value.dir = dir;
+		break;
+
+	case TB_PROPERTY_TYPE_DATA:
+		property->value.data = kcalloc(property->length, sizeof(u32),
+					       GFP_KERNEL);
+		if (!property->value.data) {
+			kfree(property);
+			return NULL;
+		}
+		parse_dwdata(property->value.data, block + entry->value,
+			     entry->length);
+		break;
+
+	case TB_PROPERTY_TYPE_TEXT:
+		property->value.text = kcalloc(property->length, sizeof(u32),
+					       GFP_KERNEL);
+		if (!property->value.text) {
+			kfree(property);
+			return NULL;
+		}
+		parse_dwdata(property->value.text, block + entry->value,
+			     entry->length);
+		/* Force null termination */
+		property->value.text[property->length * 4 - 1] = '\0';
+		break;
+
+	case TB_PROPERTY_TYPE_VALUE:
+		property->value.immediate = entry->value;
+		break;
+
+	default:
+		property->type = TB_PROPERTY_TYPE_UNKNOWN;
+		break;
+	}
+
+	return property;
+}
+
+static struct tb_property_dir *__tb_property_parse_dir(const u32 *block,
+	size_t block_len, unsigned int dir_offset, size_t dir_len, bool is_root)
+{
+	const struct tb_property_entry *entries;
+	size_t i, content_len, nentries;
+	unsigned int content_offset;
+	struct tb_property_dir *dir;
+
+	dir = kzalloc(sizeof(*dir), GFP_KERNEL);
+	if (!dir)
+		return NULL;
+
+	if (is_root) {
+		content_offset = dir_offset + 2;
+		content_len = dir_len;
+	} else {
+		dir->uuid = kmemdup(&block[dir_offset], sizeof(*dir->uuid),
+				    GFP_KERNEL);
+		content_offset = dir_offset + 4;
+		content_len = dir_len - 4; /* Length includes UUID */
+	}
+
+	entries = (const struct tb_property_entry *)&block[content_offset];
+	nentries = content_len / (sizeof(*entries) / 4);
+
+	INIT_LIST_HEAD(&dir->properties);
+
+	for (i = 0; i < nentries; i++) {
+		struct tb_property *property;
+
+		property = tb_property_parse(block, block_len, &entries[i]);
+		if (!property) {
+			tb_property_free_dir(dir);
+			return NULL;
+		}
+
+		list_add_tail(&property->list, &dir->properties);
+	}
+
+	return dir;
+}
+
+/**
+ * tb_property_parse_dir() - Parses properties from given property block
+ * @block: Property block to parse
+ * @block_len: Number of dword elements in the property block
+ *
+ * This function parses the XDomain properties data block into format that
+ * can be traversed using the helper functions provided by this module.
+ * Upon success returns the parsed directory. In case of error returns
+ * %NULL. The resulting &struct tb_property_dir needs to be released by
+ * calling tb_property_free_dir() when not needed anymore.
+ *
+ * The @block is expected to be root directory.
+ */
+struct tb_property_dir *tb_property_parse_dir(const u32 *block,
+					      size_t block_len)
+{
+	const struct tb_property_rootdir_entry *rootdir =
+		(const struct tb_property_rootdir_entry *)block;
+
+	if (rootdir->magic != TB_PROPERTY_ROOTDIR_MAGIC)
+		return NULL;
+	if (rootdir->length > block_len)
+		return NULL;
+
+	return __tb_property_parse_dir(block, block_len, 0, rootdir->length,
+				       true);
+}
+
+/**
+ * tb_property_create_dir() - Creates new property directory
+ * @uuid: UUID used to identify the particular directory
+ *
+ * Creates new, empty property directory. If @uuid is %NULL then the
+ * directory is assumed to be root directory.
+ */
+struct tb_property_dir *tb_property_create_dir(const uuid_t *uuid)
+{
+	struct tb_property_dir *dir;
+
+	dir = kzalloc(sizeof(*dir), GFP_KERNEL);
+	if (!dir)
+		return NULL;
+
+	INIT_LIST_HEAD(&dir->properties);
+	if (uuid) {
+		dir->uuid = kmemdup(uuid, sizeof(*dir->uuid), GFP_KERNEL);
+		if (!dir->uuid) {
+			kfree(dir);
+			return NULL;
+		}
+	}
+
+	return dir;
+}
+EXPORT_SYMBOL_GPL(tb_property_create_dir);
+
+static void tb_property_free(struct tb_property *property)
+{
+	switch (property->type) {
+	case TB_PROPERTY_TYPE_DIRECTORY:
+		tb_property_free_dir(property->value.dir);
+		break;
+
+	case TB_PROPERTY_TYPE_DATA:
+		kfree(property->value.data);
+		break;
+
+	case TB_PROPERTY_TYPE_TEXT:
+		kfree(property->value.text);
+		break;
+
+	default:
+		break;
+	}
+
+	kfree(property);
+}
+
+/**
+ * tb_property_free_dir() - Release memory allocated for property directory
+ * @dir: Directory to release
+ *
+ * This will release all the memory the directory occupies including all
+ * descendants. It is OK to pass %NULL @dir, then the function does
+ * nothing.
+ */
+void tb_property_free_dir(struct tb_property_dir *dir)
+{
+	struct tb_property *property, *tmp;
+
+	if (!dir)
+		return;
+
+	list_for_each_entry_safe(property, tmp, &dir->properties, list) {
+		list_del(&property->list);
+		tb_property_free(property);
+	}
+	kfree(dir->uuid);
+	kfree(dir);
+}
+EXPORT_SYMBOL_GPL(tb_property_free_dir);
+
+static size_t tb_property_dir_length(const struct tb_property_dir *dir,
+				     bool recurse, size_t *data_len)
+{
+	const struct tb_property *property;
+	size_t len = 0;
+
+	if (dir->uuid)
+		len += sizeof(*dir->uuid) / 4;
+	else
+		len += sizeof(struct tb_property_rootdir_entry) / 4;
+
+	list_for_each_entry(property, &dir->properties, list) {
+		len += sizeof(struct tb_property_entry) / 4;
+
+		switch (property->type) {
+		case TB_PROPERTY_TYPE_DIRECTORY:
+			if (recurse) {
+				len += tb_property_dir_length(
+					property->value.dir, recurse, data_len);
+			}
+			/* Reserve dword padding after each directory */
+			if (data_len)
+				*data_len += 1;
+			break;
+
+		case TB_PROPERTY_TYPE_DATA:
+		case TB_PROPERTY_TYPE_TEXT:
+			if (data_len)
+				*data_len += property->length;
+			break;
+
+		default:
+			break;
+		}
+	}
+
+	return len;
+}
+
+static ssize_t __tb_property_format_dir(const struct tb_property_dir *dir,
+	u32 *block, unsigned int start_offset, size_t block_len)
+{
+	unsigned int data_offset, dir_end;
+	const struct tb_property *property;
+	struct tb_property_entry *entry;
+	size_t dir_len, data_len = 0;
+	int ret;
+
+	/*
+	 * The structure of property block looks like following. Leaf
+	 * data/text is included right after the directory and each
+	 * directory follows each other (even nested ones).
+	 *
+	 * +----------+ <-- start_offset
+	 * |  header  | <-- root directory header
+	 * +----------+ ---
+	 * |  entry 0 | -^--------------------.
+	 * +----------+  |                    |
+	 * |  entry 1 | -|--------------------|--.
+	 * +----------+  |                    |  |
+	 * |  entry 2 | -|-----------------.  |  |
+	 * +----------+  |                 |  |  |
+	 * :          :  |  dir_len        |  |  |
+	 * .          .  |                 |  |  |
+	 * :          :  |                 |  |  |
+	 * +----------+  |                 |  |  |
+	 * |  entry n |  v                 |  |  |
+	 * +----------+ <-- data_offset    |  |  |
+	 * |  data 0  | <------------------|--'  |
+	 * +----------+                    |     |
+	 * |  data 1  | <------------------|-----'
+	 * +----------+                    |
+	 * | 00000000 | padding            |
+	 * +----------+ <-- dir_end <------'
+	 * |   UUID   | <-- directory UUID (child directory)
+	 * +----------+
+	 * |  entry 0 |
+	 * +----------+
+	 * |  entry 1 |
+	 * +----------+
+	 * :          :
+	 * .          .
+	 * :          :
+	 * +----------+
+	 * |  entry n |
+	 * +----------+
+	 * |  data 0  |
+	 * +----------+
+	 *
+	 * We use dir_end to hold pointer to the end of the directory. It
+	 * will increase as we add directories and each directory should be
+	 * added starting from previous dir_end.
+	 */
+	dir_len = tb_property_dir_length(dir, false, &data_len);
+	data_offset = start_offset + dir_len;
+	dir_end = start_offset + data_len + dir_len;
+
+	if (data_offset > dir_end)
+		return -EINVAL;
+	if (dir_end > block_len)
+		return -EINVAL;
+
+	/* Write headers first */
+	if (dir->uuid) {
+		struct tb_property_dir_entry *pe;
+
+		pe = (struct tb_property_dir_entry *)&block[start_offset];
+		memcpy(pe->uuid, dir->uuid, sizeof(pe->uuid));
+		entry = pe->entries;
+	} else {
+		struct tb_property_rootdir_entry *re;
+
+		re = (struct tb_property_rootdir_entry *)&block[start_offset];
+		re->magic = TB_PROPERTY_ROOTDIR_MAGIC;
+		re->length = dir_len - sizeof(*re) / 4;
+		entry = re->entries;
+	}
+
+	list_for_each_entry(property, &dir->properties, list) {
+		const struct tb_property_dir *child;
+
+		format_dwdata(entry, property->key, 2);
+		entry->type = property->type;
+
+		switch (property->type) {
+		case TB_PROPERTY_TYPE_DIRECTORY:
+			child = property->value.dir;
+			ret = __tb_property_format_dir(child, block, dir_end,
+						       block_len);
+			if (ret < 0)
+				return ret;
+			entry->length = tb_property_dir_length(child, false,
+							       NULL);
+			entry->value = dir_end;
+			dir_end = ret;
+			break;
+
+		case TB_PROPERTY_TYPE_DATA:
+			format_dwdata(&block[data_offset], property->value.data,
+				      property->length);
+			entry->length = property->length;
+			entry->value = data_offset;
+			data_offset += entry->length;
+			break;
+
+		case TB_PROPERTY_TYPE_TEXT:
+			format_dwdata(&block[data_offset], property->value.text,
+				      property->length);
+			entry->length = property->length;
+			entry->value = data_offset;
+			data_offset += entry->length;
+			break;
+
+		case TB_PROPERTY_TYPE_VALUE:
+			entry->length = property->length;
+			entry->value = property->value.immediate;
+			break;
+
+		default:
+			break;
+		}
+
+		entry++;
+	}
+
+	return dir_end;
+}
+
+/**
+ * tb_property_format_dir() - Formats directory to the packed XDomain format
+ * @dir: Directory to format
+ * @block: Property block where the packed data is placed
+ * @block_len: Length of the property block
+ *
+ * This function formats the directory to the packed format that can be
+ * then send over the thunderbolt fabric to receiving host. Returns %0 in
+ * case of success and negative errno on faulure. Passing %NULL in @block
+ * returns number of entries the block takes.
+ */
+ssize_t tb_property_format_dir(const struct tb_property_dir *dir, u32 *block,
+			       size_t block_len)
+{
+	ssize_t ret;
+
+	if (!block) {
+		size_t dir_len, data_len = 0;
+
+		dir_len = tb_property_dir_length(dir, true, &data_len);
+		return dir_len + data_len;
+	}
+
+	ret = __tb_property_format_dir(dir, block, 0, block_len);
+	return ret < 0 ? ret : 0;
+}
+
+/**
+ * tb_property_add_immediate() - Add immediate property to directory
+ * @parent: Directory to add the property
+ * @key: Key for the property
+ * @value: Immediate value to store with the property
+ */
+int tb_property_add_immediate(struct tb_property_dir *parent, const char *key,
+			      u32 value)
+{
+	struct tb_property *property;
+
+	if (!tb_property_key_valid(key))
+		return -EINVAL;
+
+	property = tb_property_alloc(key, TB_PROPERTY_TYPE_VALUE);
+	if (!property)
+		return -ENOMEM;
+
+	property->length = 1;
+	property->value.immediate = value;
+
+	list_add_tail(&property->list, &parent->properties);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tb_property_add_immediate);
+
+/**
+ * tb_property_add_data() - Adds arbitrary data property to directory
+ * @parent: Directory to add the property
+ * @key: Key for the property
+ * @buf: Data buffer to add
+ * @buflen: Number of bytes in the data buffer
+ *
+ * Function takes a copy of @buf and adds it to the directory.
+ */
+int tb_property_add_data(struct tb_property_dir *parent, const char *key,
+			 const void *buf, size_t buflen)
+{
+	/* Need to pad to dword boundary */
+	size_t size = round_up(buflen, 4);
+	struct tb_property *property;
+
+	if (!tb_property_key_valid(key))
+		return -EINVAL;
+
+	property = tb_property_alloc(key, TB_PROPERTY_TYPE_DATA);
+	if (!property)
+		return -ENOMEM;
+
+	property->length = size / 4;
+	property->value.data = kzalloc(size, GFP_KERNEL);
+	memcpy(property->value.data, buf, buflen);
+
+	list_add_tail(&property->list, &parent->properties);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tb_property_add_data);
+
+/**
+ * tb_property_add_text() - Adds string property to directory
+ * @parent: Directory to add the property
+ * @key: Key for the property
+ * @text: String to add
+ *
+ * Function takes a copy of @text and adds it to the directory.
+ */
+int tb_property_add_text(struct tb_property_dir *parent, const char *key,
+			 const char *text)
+{
+	/* Need to pad to dword boundary */
+	size_t size = round_up(strlen(text) + 1, 4);
+	struct tb_property *property;
+
+	if (!tb_property_key_valid(key))
+		return -EINVAL;
+
+	property = tb_property_alloc(key, TB_PROPERTY_TYPE_TEXT);
+	if (!property)
+		return -ENOMEM;
+
+	property->length = size / 4;
+	property->value.data = kzalloc(size, GFP_KERNEL);
+	strcpy(property->value.text, text);
+
+	list_add_tail(&property->list, &parent->properties);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tb_property_add_text);
+
+/**
+ * tb_property_add_dir() - Adds a directory to the parent directory
+ * @parent: Directory to add the property
+ * @key: Key for the property
+ * @dir: Directory to add
+ */
+int tb_property_add_dir(struct tb_property_dir *parent, const char *key,
+			struct tb_property_dir *dir)
+{
+	struct tb_property *property;
+
+	if (!tb_property_key_valid(key))
+		return -EINVAL;
+
+	property = tb_property_alloc(key, TB_PROPERTY_TYPE_DIRECTORY);
+	if (!property)
+		return -ENOMEM;
+
+	property->value.dir = dir;
+
+	list_add_tail(&property->list, &parent->properties);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tb_property_add_dir);
+
+/**
+ * tb_property_remove() - Removes property from a parent directory
+ * @property: Property to remove
+ *
+ * Note memory for @property is released as well so it is not allowed to
+ * touch the object after call to this function.
+ */
+void tb_property_remove(struct tb_property *property)
+{
+	list_del(&property->list);
+	kfree(property);
+}
+EXPORT_SYMBOL_GPL(tb_property_remove);
+
+/**
+ * tb_property_find() - Find a property from a directory
+ * @dir: Directory where the property is searched
+ * @key: Key to look for
+ * @type: Type of the property
+ *
+ * Finds and returns property from the given directory. Does not recurse
+ * into sub-directories. Returns %NULL if the property was not found.
+ */
+struct tb_property *tb_property_find(struct tb_property_dir *dir,
+	const char *key, enum tb_property_type type)
+{
+	struct tb_property *property;
+
+	list_for_each_entry(property, &dir->properties, list) {
+		if (property->type == type && !strcmp(property->key, key))
+			return property;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(tb_property_find);
+
+/**
+ * tb_property_get_next() - Get next property from directory
+ * @dir: Directory holding properties
+ * @prev: Previous property in the directory (%NULL returns the first)
+ */
+struct tb_property *tb_property_get_next(struct tb_property_dir *dir,
+					 struct tb_property *prev)
+{
+	if (prev) {
+		if (list_is_last(&prev->list, &dir->properties))
+			return NULL;
+		return list_next_entry(prev, list);
+	}
+	return list_first_entry_or_null(&dir->properties, struct tb_property,
+					list);
+}
+EXPORT_SYMBOL_GPL(tb_property_get_next);
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 3953d17202a8..da54ace4dd2f 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -172,11 +172,11 @@ static int nvm_authenticate_host(struct tb_switch *sw)
 
 	/*
 	 * Root switch NVM upgrade requires that we disconnect the
-	 * existing PCIe paths first (in case it is not in safe mode
+	 * existing paths first (in case it is not in safe mode
 	 * already).
 	 */
 	if (!sw->safe_mode) {
-		ret = tb_domain_disconnect_pcie_paths(sw->tb);
+		ret = tb_domain_disconnect_all_paths(sw->tb);
 		if (ret)
 			return ret;
 		/*
@@ -1364,6 +1364,9 @@ void tb_switch_remove(struct tb_switch *sw)
 		if (sw->ports[i].remote)
 			tb_switch_remove(sw->ports[i].remote->sw);
 		sw->ports[i].remote = NULL;
+		if (sw->ports[i].xdomain)
+			tb_xdomain_remove(sw->ports[i].xdomain);
+		sw->ports[i].xdomain = NULL;
 	}
 
 	if (!sw->is_unplugged)
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index d7ffc159bcf7..895c57a0a090 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -10,6 +10,7 @@
 
 #include <linux/nvmem-provider.h>
 #include <linux/pci.h>
+#include <linux/thunderbolt.h>
 #include <linux/uuid.h>
 
 #include "tb_regs.h"
@@ -40,23 +41,7 @@ struct tb_switch_nvm {
 	bool authenticating;
 };
 
-/**
- * enum tb_security_level - Thunderbolt security level
- * @TB_SECURITY_NONE: No security, legacy mode
- * @TB_SECURITY_USER: User approval required at minimum
- * @TB_SECURITY_SECURE: One time saved key required at minimum
- * @TB_SECURITY_DPONLY: Only tunnel Display port (and USB)
- */
-enum tb_security_level {
-	TB_SECURITY_NONE,
-	TB_SECURITY_USER,
-	TB_SECURITY_SECURE,
-	TB_SECURITY_DPONLY,
-};
-
 #define TB_SWITCH_KEY_SIZE		32
-/* Each physical port contains 2 links on modern controllers */
-#define TB_SWITCH_LINKS_PER_PHY_PORT	2
 
 /**
  * struct tb_switch - a thunderbolt switch
@@ -126,14 +111,25 @@ struct tb_switch {
 
 /**
  * struct tb_port - a thunderbolt port, part of a tb_switch
+ * @config: Cached port configuration read from registers
+ * @sw: Switch the port belongs to
+ * @remote: Remote port (%NULL if not connected)
+ * @xdomain: Remote host (%NULL if not connected)
+ * @cap_phy: Offset, zero if not found
+ * @port: Port number on switch
+ * @disabled: Disabled by eeprom
+ * @dual_link_port: If the switch is connected using two ports, points
+ *		    to the other port.
+ * @link_nr: Is this primary or secondary port on the dual_link.
  */
 struct tb_port {
 	struct tb_regs_port_header config;
 	struct tb_switch *sw;
-	struct tb_port *remote; /* remote port, NULL if not connected */
-	int cap_phy; /* offset, zero if not found */
-	u8 port; /* port number on switch */
-	bool disabled; /* disabled by eeprom */
+	struct tb_port *remote;
+	struct tb_xdomain *xdomain;
+	int cap_phy;
+	u8 port;
+	bool disabled;
 	struct tb_port *dual_link_port;
 	u8 link_nr:1;
 };
@@ -206,6 +202,8 @@ struct tb_path {
  * @add_switch_key: Add key to switch
  * @challenge_switch_key: Challenge switch using key
  * @disconnect_pcie_paths: Disconnects PCIe paths before NVM update
+ * @approve_xdomain_paths: Approve (establish) XDomain DMA paths
+ * @disconnect_xdomain_paths: Disconnect XDomain DMA paths
  */
 struct tb_cm_ops {
 	int (*driver_ready)(struct tb *tb);
@@ -222,33 +220,8 @@ struct tb_cm_ops {
 	int (*challenge_switch_key)(struct tb *tb, struct tb_switch *sw,
 				    const u8 *challenge, u8 *response);
 	int (*disconnect_pcie_paths)(struct tb *tb);
-};
-
-/**
- * struct tb - main thunderbolt bus structure
- * @dev: Domain device
- * @lock: Big lock. Must be held when accessing any struct
- *	  tb_switch / struct tb_port.
- * @nhi: Pointer to the NHI structure
- * @ctl: Control channel for this domain
- * @wq: Ordered workqueue for all domain specific work
- * @root_switch: Root switch of this domain
- * @cm_ops: Connection manager specific operations vector
- * @index: Linux assigned domain number
- * @security_level: Current security level
- * @privdata: Private connection manager specific data
- */
-struct tb {
-	struct device dev;
-	struct mutex lock;
-	struct tb_nhi *nhi;
-	struct tb_ctl *ctl;
-	struct workqueue_struct *wq;
-	struct tb_switch *root_switch;
-	const struct tb_cm_ops *cm_ops;
-	int index;
-	enum tb_security_level security_level;
-	unsigned long privdata[0];
+	int (*approve_xdomain_paths)(struct tb *tb, struct tb_xdomain *xd);
+	int (*disconnect_xdomain_paths)(struct tb *tb, struct tb_xdomain *xd);
 };
 
 static inline void *tb_priv(struct tb *tb)
@@ -369,13 +342,14 @@ static inline int tb_port_write(struct tb_port *port, const void *buffer,
 struct tb *icm_probe(struct tb_nhi *nhi);
 struct tb *tb_probe(struct tb_nhi *nhi);
 
-extern struct bus_type tb_bus_type;
 extern struct device_type tb_domain_type;
 extern struct device_type tb_switch_type;
 
 int tb_domain_init(void);
 void tb_domain_exit(void);
 void tb_switch_exit(void);
+int tb_xdomain_init(void);
+void tb_xdomain_exit(void);
 
 struct tb *tb_domain_alloc(struct tb_nhi *nhi, size_t privsize);
 int tb_domain_add(struct tb *tb);
@@ -388,6 +362,9 @@ int tb_domain_approve_switch(struct tb *tb, struct tb_switch *sw);
 int tb_domain_approve_switch_key(struct tb *tb, struct tb_switch *sw);
 int tb_domain_challenge_switch_key(struct tb *tb, struct tb_switch *sw);
 int tb_domain_disconnect_pcie_paths(struct tb *tb);
+int tb_domain_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd);
+int tb_domain_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd);
+int tb_domain_disconnect_all_paths(struct tb *tb);
 
 static inline void tb_domain_put(struct tb *tb)
 {
@@ -410,11 +387,6 @@ struct tb_switch *tb_switch_find_by_link_depth(struct tb *tb, u8 link,
 					       u8 depth);
 struct tb_switch *tb_switch_find_by_uuid(struct tb *tb, const uuid_t *uuid);
 
-static inline unsigned int tb_switch_phy_port_from_link(unsigned int link)
-{
-	return (link - 1) / TB_SWITCH_LINKS_PER_PHY_PORT;
-}
-
 static inline void tb_switch_put(struct tb_switch *sw)
 {
 	put_device(&sw->dev);
@@ -472,4 +444,14 @@ static inline u64 tb_downstream_route(struct tb_port *port)
 	       | ((u64) port->port << (port->sw->config.depth * 8));
 }
 
+bool tb_xdomain_handle_request(struct tb *tb, enum tb_cfg_pkg_type type,
+			       const void *buf, size_t size);
+struct tb_xdomain *tb_xdomain_alloc(struct tb *tb, struct device *parent,
+				    u64 route, const uuid_t *local_uuid,
+				    const uuid_t *remote_uuid);
+void tb_xdomain_add(struct tb_xdomain *xd);
+void tb_xdomain_remove(struct tb_xdomain *xd);
+struct tb_xdomain *tb_xdomain_find_by_link_depth(struct tb *tb, u8 link,
+						 u8 depth);
+
 #endif
diff --git a/drivers/thunderbolt/tb_msgs.h b/drivers/thunderbolt/tb_msgs.h
index de6441e4a060..b0a092baa605 100644
--- a/drivers/thunderbolt/tb_msgs.h
+++ b/drivers/thunderbolt/tb_msgs.h
@@ -15,23 +15,6 @@
 #include <linux/types.h>
 #include <linux/uuid.h>
 
-enum tb_cfg_pkg_type {
-	TB_CFG_PKG_READ = 1,
-	TB_CFG_PKG_WRITE = 2,
-	TB_CFG_PKG_ERROR = 3,
-	TB_CFG_PKG_NOTIFY_ACK = 4,
-	TB_CFG_PKG_EVENT = 5,
-	TB_CFG_PKG_XDOMAIN_REQ = 6,
-	TB_CFG_PKG_XDOMAIN_RESP = 7,
-	TB_CFG_PKG_OVERRIDE = 8,
-	TB_CFG_PKG_RESET = 9,
-	TB_CFG_PKG_ICM_EVENT = 10,
-	TB_CFG_PKG_ICM_CMD = 11,
-	TB_CFG_PKG_ICM_RESP = 12,
-	TB_CFG_PKG_PREPARE_TO_SLEEP = 0xd,
-
-};
-
 enum tb_cfg_space {
 	TB_CFG_HOPS = 0,
 	TB_CFG_PORT = 1,
@@ -118,11 +101,14 @@ enum icm_pkg_code {
 	ICM_CHALLENGE_DEVICE = 0x5,
 	ICM_ADD_DEVICE_KEY = 0x6,
 	ICM_GET_ROUTE = 0xa,
+	ICM_APPROVE_XDOMAIN = 0x10,
 };
 
 enum icm_event_code {
 	ICM_EVENT_DEVICE_CONNECTED = 3,
 	ICM_EVENT_DEVICE_DISCONNECTED = 4,
+	ICM_EVENT_XDOMAIN_CONNECTED = 6,
+	ICM_EVENT_XDOMAIN_DISCONNECTED = 7,
 };
 
 struct icm_pkg_header {
@@ -130,7 +116,7 @@ struct icm_pkg_header {
 	u8 flags;
 	u8 packet_id;
 	u8 total_packets;
-} __packed;
+};
 
 #define ICM_FLAGS_ERROR			BIT(0)
 #define ICM_FLAGS_NO_KEY		BIT(1)
@@ -139,20 +125,20 @@ struct icm_pkg_header {
 
 struct icm_pkg_driver_ready {
 	struct icm_pkg_header hdr;
-} __packed;
+};
 
 struct icm_pkg_driver_ready_response {
 	struct icm_pkg_header hdr;
 	u8 romver;
 	u8 ramver;
 	u16 security_level;
-} __packed;
+};
 
 /* Falcon Ridge & Alpine Ridge common messages */
 
 struct icm_fr_pkg_get_topology {
 	struct icm_pkg_header hdr;
-} __packed;
+};
 
 #define ICM_GET_TOPOLOGY_PACKETS	14
 
@@ -167,7 +153,7 @@ struct icm_fr_pkg_get_topology_response {
 	u32 reserved[2];
 	u32 ports[16];
 	u32 port_hop_info[16];
-} __packed;
+};
 
 #define ICM_SWITCH_USED			BIT(0)
 #define ICM_SWITCH_UPSTREAM_PORT_MASK	GENMASK(7, 1)
@@ -184,7 +170,7 @@ struct icm_fr_event_device_connected {
 	u8 connection_id;
 	u16 link_info;
 	u32 ep_name[55];
-} __packed;
+};
 
 #define ICM_LINK_INFO_LINK_MASK		0x7
 #define ICM_LINK_INFO_DEPTH_SHIFT	4
@@ -197,13 +183,32 @@ struct icm_fr_pkg_approve_device {
 	u8 connection_key;
 	u8 connection_id;
 	u16 reserved;
-} __packed;
+};
 
 struct icm_fr_event_device_disconnected {
 	struct icm_pkg_header hdr;
 	u16 reserved;
 	u16 link_info;
-} __packed;
+};
+
+struct icm_fr_event_xdomain_connected {
+	struct icm_pkg_header hdr;
+	u16 reserved;
+	u16 link_info;
+	uuid_t remote_uuid;
+	uuid_t local_uuid;
+	u32 local_route_hi;
+	u32 local_route_lo;
+	u32 remote_route_hi;
+	u32 remote_route_lo;
+};
+
+struct icm_fr_event_xdomain_disconnected {
+	struct icm_pkg_header hdr;
+	u16 reserved;
+	u16 link_info;
+	uuid_t remote_uuid;
+};
 
 struct icm_fr_pkg_add_device_key {
 	struct icm_pkg_header hdr;
@@ -212,7 +217,7 @@ struct icm_fr_pkg_add_device_key {
 	u8 connection_id;
 	u16 reserved;
 	u32 key[8];
-} __packed;
+};
 
 struct icm_fr_pkg_add_device_key_response {
 	struct icm_pkg_header hdr;
@@ -220,7 +225,7 @@ struct icm_fr_pkg_add_device_key_response {
 	u8 connection_key;
 	u8 connection_id;
 	u16 reserved;
-} __packed;
+};
 
 struct icm_fr_pkg_challenge_device {
 	struct icm_pkg_header hdr;
@@ -229,7 +234,7 @@ struct icm_fr_pkg_challenge_device {
 	u8 connection_id;
 	u16 reserved;
 	u32 challenge[8];
-} __packed;
+};
 
 struct icm_fr_pkg_challenge_device_response {
 	struct icm_pkg_header hdr;
@@ -239,7 +244,29 @@ struct icm_fr_pkg_challenge_device_response {
 	u16 reserved;
 	u32 challenge[8];
 	u32 response[8];
-} __packed;
+};
+
+struct icm_fr_pkg_approve_xdomain {
+	struct icm_pkg_header hdr;
+	u16 reserved;
+	u16 link_info;
+	uuid_t remote_uuid;
+	u16 transmit_path;
+	u16 transmit_ring;
+	u16 receive_path;
+	u16 receive_ring;
+};
+
+struct icm_fr_pkg_approve_xdomain_response {
+	struct icm_pkg_header hdr;
+	u16 reserved;
+	u16 link_info;
+	uuid_t remote_uuid;
+	u16 transmit_path;
+	u16 transmit_ring;
+	u16 receive_path;
+	u16 receive_ring;
+};
 
 /* Alpine Ridge only messages */
 
@@ -247,7 +274,7 @@ struct icm_ar_pkg_get_route {
 	struct icm_pkg_header hdr;
 	u16 reserved;
 	u16 link_info;
-} __packed;
+};
 
 struct icm_ar_pkg_get_route_response {
 	struct icm_pkg_header hdr;
@@ -255,6 +282,85 @@ struct icm_ar_pkg_get_route_response {
 	u16 link_info;
 	u32 route_hi;
 	u32 route_lo;
-} __packed;
+};
+
+/* XDomain messages */
+
+struct tb_xdomain_header {
+	u32 route_hi;
+	u32 route_lo;
+	u32 length_sn;
+};
+
+#define TB_XDOMAIN_LENGTH_MASK	GENMASK(5, 0)
+#define TB_XDOMAIN_SN_MASK	GENMASK(28, 27)
+#define TB_XDOMAIN_SN_SHIFT	27
+
+enum tb_xdp_type {
+	UUID_REQUEST_OLD = 1,
+	UUID_RESPONSE = 2,
+	PROPERTIES_REQUEST,
+	PROPERTIES_RESPONSE,
+	PROPERTIES_CHANGED_REQUEST,
+	PROPERTIES_CHANGED_RESPONSE,
+	ERROR_RESPONSE,
+	UUID_REQUEST = 12,
+};
+
+struct tb_xdp_header {
+	struct tb_xdomain_header xd_hdr;
+	uuid_t uuid;
+	u32 type;
+};
+
+struct tb_xdp_properties {
+	struct tb_xdp_header hdr;
+	uuid_t src_uuid;
+	uuid_t dst_uuid;
+	u16 offset;
+	u16 reserved;
+};
+
+struct tb_xdp_properties_response {
+	struct tb_xdp_header hdr;
+	uuid_t src_uuid;
+	uuid_t dst_uuid;
+	u16 offset;
+	u16 data_length;
+	u32 generation;
+	u32 data[0];
+};
+
+/*
+ * Max length of data array single XDomain property response is allowed
+ * to carry.
+ */
+#define TB_XDP_PROPERTIES_MAX_DATA_LENGTH	\
+	(((256 - 4 - sizeof(struct tb_xdp_properties_response))) / 4)
+
+/* Maximum size of the total property block in dwords we allow */
+#define TB_XDP_PROPERTIES_MAX_LENGTH		500
+
+struct tb_xdp_properties_changed {
+	struct tb_xdp_header hdr;
+	uuid_t src_uuid;
+};
+
+struct tb_xdp_properties_changed_response {
+	struct tb_xdp_header hdr;
+};
+
+enum tb_xdp_error {
+	ERROR_SUCCESS,
+	ERROR_UNKNOWN_PACKET,
+	ERROR_UNKNOWN_DOMAIN,
+	ERROR_NOT_SUPPORTED,
+	ERROR_NOT_READY,
+};
+
+struct tb_xdp_error_response {
+	struct tb_xdp_header hdr;
+	u32 error;
+};
 
 #endif
diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
new file mode 100644
index 000000000000..f25d88d4552b
--- /dev/null
+++ b/drivers/thunderbolt/xdomain.c
@@ -0,0 +1,1570 @@
+/*
+ * Thunderbolt XDomain discovery protocol support
+ *
+ * Copyright (C) 2017, Intel Corporation
+ * Authors: Michael Jamet <michael.jamet@intel.com>
+ *          Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/device.h>
+#include <linux/kmod.h>
+#include <linux/module.h>
+#include <linux/utsname.h>
+#include <linux/uuid.h>
+#include <linux/workqueue.h>
+
+#include "tb.h"
+
+#define XDOMAIN_DEFAULT_TIMEOUT			5000 /* ms */
+#define XDOMAIN_PROPERTIES_RETRIES		60
+#define XDOMAIN_PROPERTIES_CHANGED_RETRIES	10
+
+struct xdomain_request_work {
+	struct work_struct work;
+	struct tb_xdp_header *pkg;
+	struct tb *tb;
+};
+
+/* Serializes access to the properties and protocol handlers below */
+static DEFINE_MUTEX(xdomain_lock);
+
+/* Properties exposed to the remote domains */
+static struct tb_property_dir *xdomain_property_dir;
+static u32 *xdomain_property_block;
+static u32 xdomain_property_block_len;
+static u32 xdomain_property_block_gen;
+
+/* Additional protocol handlers */
+static LIST_HEAD(protocol_handlers);
+
+/* UUID for XDomain discovery protocol: b638d70e-42ff-40bb-97c2-90e2c0b2ff07 */
+static const uuid_t tb_xdp_uuid =
+	UUID_INIT(0xb638d70e, 0x42ff, 0x40bb,
+		  0x97, 0xc2, 0x90, 0xe2, 0xc0, 0xb2, 0xff, 0x07);
+
+static bool tb_xdomain_match(const struct tb_cfg_request *req,
+			     const struct ctl_pkg *pkg)
+{
+	switch (pkg->frame.eof) {
+	case TB_CFG_PKG_ERROR:
+		return true;
+
+	case TB_CFG_PKG_XDOMAIN_RESP: {
+		const struct tb_xdp_header *res_hdr = pkg->buffer;
+		const struct tb_xdp_header *req_hdr = req->request;
+
+		if (pkg->frame.size < req->response_size / 4)
+			return false;
+
+		/* Make sure route matches */
+		if ((res_hdr->xd_hdr.route_hi & ~BIT(31)) !=
+		     req_hdr->xd_hdr.route_hi)
+			return false;
+		if ((res_hdr->xd_hdr.route_lo) != req_hdr->xd_hdr.route_lo)
+			return false;
+
+		/* Check that the XDomain protocol matches */
+		if (!uuid_equal(&res_hdr->uuid, &req_hdr->uuid))
+			return false;
+
+		return true;
+	}
+
+	default:
+		return false;
+	}
+}
+
+static bool tb_xdomain_copy(struct tb_cfg_request *req,
+			    const struct ctl_pkg *pkg)
+{
+	memcpy(req->response, pkg->buffer, req->response_size);
+	req->result.err = 0;
+	return true;
+}
+
+static void response_ready(void *data)
+{
+	tb_cfg_request_put(data);
+}
+
+static int __tb_xdomain_response(struct tb_ctl *ctl, const void *response,
+				 size_t size, enum tb_cfg_pkg_type type)
+{
+	struct tb_cfg_request *req;
+
+	req = tb_cfg_request_alloc();
+	if (!req)
+		return -ENOMEM;
+
+	req->match = tb_xdomain_match;
+	req->copy = tb_xdomain_copy;
+	req->request = response;
+	req->request_size = size;
+	req->request_type = type;
+
+	return tb_cfg_request(ctl, req, response_ready, req);
+}
+
+/**
+ * tb_xdomain_response() - Send a XDomain response message
+ * @xd: XDomain to send the message
+ * @response: Response to send
+ * @size: Size of the response
+ * @type: PDF type of the response
+ *
+ * This can be used to send a XDomain response message to the other
+ * domain. No response for the message is expected.
+ *
+ * Return: %0 in case of success and negative errno in case of failure
+ */
+int tb_xdomain_response(struct tb_xdomain *xd, const void *response,
+			size_t size, enum tb_cfg_pkg_type type)
+{
+	return __tb_xdomain_response(xd->tb->ctl, response, size, type);
+}
+EXPORT_SYMBOL_GPL(tb_xdomain_response);
+
+static int __tb_xdomain_request(struct tb_ctl *ctl, const void *request,
+	size_t request_size, enum tb_cfg_pkg_type request_type, void *response,
+	size_t response_size, enum tb_cfg_pkg_type response_type,
+	unsigned int timeout_msec)
+{
+	struct tb_cfg_request *req;
+	struct tb_cfg_result res;
+
+	req = tb_cfg_request_alloc();
+	if (!req)
+		return -ENOMEM;
+
+	req->match = tb_xdomain_match;
+	req->copy = tb_xdomain_copy;
+	req->request = request;
+	req->request_size = request_size;
+	req->request_type = request_type;
+	req->response = response;
+	req->response_size = response_size;
+	req->response_type = response_type;
+
+	res = tb_cfg_request_sync(ctl, req, timeout_msec);
+
+	tb_cfg_request_put(req);
+
+	return res.err == 1 ? -EIO : res.err;
+}
+
+/**
+ * tb_xdomain_request() - Send a XDomain request
+ * @xd: XDomain to send the request
+ * @request: Request to send
+ * @request_size: Size of the request in bytes
+ * @request_type: PDF type of the request
+ * @response: Response is copied here
+ * @response_size: Expected size of the response in bytes
+ * @response_type: Expected PDF type of the response
+ * @timeout_msec: Timeout in milliseconds to wait for the response
+ *
+ * This function can be used to send XDomain control channel messages to
+ * the other domain. The function waits until the response is received
+ * or when timeout triggers. Whichever comes first.
+ *
+ * Return: %0 in case of success and negative errno in case of failure
+ */
+int tb_xdomain_request(struct tb_xdomain *xd, const void *request,
+	size_t request_size, enum tb_cfg_pkg_type request_type,
+	void *response, size_t response_size,
+	enum tb_cfg_pkg_type response_type, unsigned int timeout_msec)
+{
+	return __tb_xdomain_request(xd->tb->ctl, request, request_size,
+				    request_type, response, response_size,
+				    response_type, timeout_msec);
+}
+EXPORT_SYMBOL_GPL(tb_xdomain_request);
+
+static inline void tb_xdp_fill_header(struct tb_xdp_header *hdr, u64 route,
+	u8 sequence, enum tb_xdp_type type, size_t size)
+{
+	u32 length_sn;
+
+	length_sn = (size - sizeof(hdr->xd_hdr)) / 4;
+	length_sn |= (sequence << TB_XDOMAIN_SN_SHIFT) & TB_XDOMAIN_SN_MASK;
+
+	hdr->xd_hdr.route_hi = upper_32_bits(route);
+	hdr->xd_hdr.route_lo = lower_32_bits(route);
+	hdr->xd_hdr.length_sn = length_sn;
+	hdr->type = type;
+	memcpy(&hdr->uuid, &tb_xdp_uuid, sizeof(tb_xdp_uuid));
+}
+
+static int tb_xdp_handle_error(const struct tb_xdp_header *hdr)
+{
+	const struct tb_xdp_error_response *error;
+
+	if (hdr->type != ERROR_RESPONSE)
+		return 0;
+
+	error = (const struct tb_xdp_error_response *)hdr;
+
+	switch (error->error) {
+	case ERROR_UNKNOWN_PACKET:
+	case ERROR_UNKNOWN_DOMAIN:
+		return -EIO;
+	case ERROR_NOT_SUPPORTED:
+		return -ENOTSUPP;
+	case ERROR_NOT_READY:
+		return -EAGAIN;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int tb_xdp_error_response(struct tb_ctl *ctl, u64 route, u8 sequence,
+				 enum tb_xdp_error error)
+{
+	struct tb_xdp_error_response res;
+
+	memset(&res, 0, sizeof(res));
+	tb_xdp_fill_header(&res.hdr, route, sequence, ERROR_RESPONSE,
+			   sizeof(res));
+	res.error = error;
+
+	return __tb_xdomain_response(ctl, &res, sizeof(res),
+				     TB_CFG_PKG_XDOMAIN_RESP);
+}
+
+static int tb_xdp_properties_request(struct tb_ctl *ctl, u64 route,
+	const uuid_t *src_uuid, const uuid_t *dst_uuid, int retry,
+	u32 **block, u32 *generation)
+{
+	struct tb_xdp_properties_response *res;
+	struct tb_xdp_properties req;
+	u16 data_len, len;
+	size_t total_size;
+	u32 *data = NULL;
+	int ret;
+
+	total_size = sizeof(*res) + TB_XDP_PROPERTIES_MAX_DATA_LENGTH * 4;
+	res = kzalloc(total_size, GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
+
+	memset(&req, 0, sizeof(req));
+	tb_xdp_fill_header(&req.hdr, route, retry % 4, PROPERTIES_REQUEST,
+			   sizeof(req));
+	memcpy(&req.src_uuid, src_uuid, sizeof(*src_uuid));
+	memcpy(&req.dst_uuid, dst_uuid, sizeof(*dst_uuid));
+
+	len = 0;
+	data_len = 0;
+
+	do {
+		ret = __tb_xdomain_request(ctl, &req, sizeof(req),
+					   TB_CFG_PKG_XDOMAIN_REQ, res,
+					   total_size, TB_CFG_PKG_XDOMAIN_RESP,
+					   XDOMAIN_DEFAULT_TIMEOUT);
+		if (ret)
+			goto err;
+
+		ret = tb_xdp_handle_error(&res->hdr);
+		if (ret)
+			goto err;
+
+		/*
+		 * Package length includes the whole payload without the
+		 * XDomain header. Validate first that the package is at
+		 * least size of the response structure.
+		 */
+		len = res->hdr.xd_hdr.length_sn & TB_XDOMAIN_LENGTH_MASK;
+		if (len < sizeof(*res) / 4) {
+			ret = -EINVAL;
+			goto err;
+		}
+
+		len += sizeof(res->hdr.xd_hdr) / 4;
+		len -= sizeof(*res) / 4;
+
+		if (res->offset != req.offset) {
+			ret = -EINVAL;
+			goto err;
+		}
+
+		/*
+		 * First time allocate block that has enough space for
+		 * the whole properties block.
+		 */
+		if (!data) {
+			data_len = res->data_length;
+			if (data_len > TB_XDP_PROPERTIES_MAX_LENGTH) {
+				ret = -E2BIG;
+				goto err;
+			}
+
+			data = kcalloc(data_len, sizeof(u32), GFP_KERNEL);
+			if (!data) {
+				ret = -ENOMEM;
+				goto err;
+			}
+		}
+
+		memcpy(data + req.offset, res->data, len * 4);
+		req.offset += len;
+	} while (!data_len || req.offset < data_len);
+
+	*block = data;
+	*generation = res->generation;
+
+	kfree(res);
+
+	return data_len;
+
+err:
+	kfree(data);
+	kfree(res);
+
+	return ret;
+}
+
+static int tb_xdp_properties_response(struct tb *tb, struct tb_ctl *ctl,
+	u64 route, u8 sequence, const uuid_t *src_uuid,
+	const struct tb_xdp_properties *req)
+{
+	struct tb_xdp_properties_response *res;
+	size_t total_size;
+	u16 len;
+	int ret;
+
+	/*
+	 * Currently we expect all requests to be directed to us. The
+	 * protocol supports forwarding, though which we might add
+	 * support later on.
+	 */
+	if (!uuid_equal(src_uuid, &req->dst_uuid)) {
+		tb_xdp_error_response(ctl, route, sequence,
+				      ERROR_UNKNOWN_DOMAIN);
+		return 0;
+	}
+
+	mutex_lock(&xdomain_lock);
+
+	if (req->offset >= xdomain_property_block_len) {
+		mutex_unlock(&xdomain_lock);
+		return -EINVAL;
+	}
+
+	len = xdomain_property_block_len - req->offset;
+	len = min_t(u16, len, TB_XDP_PROPERTIES_MAX_DATA_LENGTH);
+	total_size = sizeof(*res) + len * 4;
+
+	res = kzalloc(total_size, GFP_KERNEL);
+	if (!res) {
+		mutex_unlock(&xdomain_lock);
+		return -ENOMEM;
+	}
+
+	tb_xdp_fill_header(&res->hdr, route, sequence, PROPERTIES_RESPONSE,
+			   total_size);
+	res->generation = xdomain_property_block_gen;
+	res->data_length = xdomain_property_block_len;
+	res->offset = req->offset;
+	uuid_copy(&res->src_uuid, src_uuid);
+	uuid_copy(&res->dst_uuid, &req->src_uuid);
+	memcpy(res->data, &xdomain_property_block[req->offset], len * 4);
+
+	mutex_unlock(&xdomain_lock);
+
+	ret = __tb_xdomain_response(ctl, res, total_size,
+				    TB_CFG_PKG_XDOMAIN_RESP);
+
+	kfree(res);
+	return ret;
+}
+
+static int tb_xdp_properties_changed_request(struct tb_ctl *ctl, u64 route,
+					     int retry, const uuid_t *uuid)
+{
+	struct tb_xdp_properties_changed_response res;
+	struct tb_xdp_properties_changed req;
+	int ret;
+
+	memset(&req, 0, sizeof(req));
+	tb_xdp_fill_header(&req.hdr, route, retry % 4,
+			   PROPERTIES_CHANGED_REQUEST, sizeof(req));
+	uuid_copy(&req.src_uuid, uuid);
+
+	memset(&res, 0, sizeof(res));
+	ret = __tb_xdomain_request(ctl, &req, sizeof(req),
+				   TB_CFG_PKG_XDOMAIN_REQ, &res, sizeof(res),
+				   TB_CFG_PKG_XDOMAIN_RESP,
+				   XDOMAIN_DEFAULT_TIMEOUT);
+	if (ret)
+		return ret;
+
+	return tb_xdp_handle_error(&res.hdr);
+}
+
+static int
+tb_xdp_properties_changed_response(struct tb_ctl *ctl, u64 route, u8 sequence)
+{
+	struct tb_xdp_properties_changed_response res;
+
+	memset(&res, 0, sizeof(res));
+	tb_xdp_fill_header(&res.hdr, route, sequence,
+			   PROPERTIES_CHANGED_RESPONSE, sizeof(res));
+	return __tb_xdomain_response(ctl, &res, sizeof(res),
+				     TB_CFG_PKG_XDOMAIN_RESP);
+}
+
+/**
+ * tb_register_protocol_handler() - Register protocol handler
+ * @handler: Handler to register
+ *
+ * This allows XDomain service drivers to hook into incoming XDomain
+ * messages. After this function is called the service driver needs to
+ * be able to handle calls to callback whenever a package with the
+ * registered protocol is received.
+ */
+int tb_register_protocol_handler(struct tb_protocol_handler *handler)
+{
+	if (!handler->uuid || !handler->callback)
+		return -EINVAL;
+	if (uuid_equal(handler->uuid, &tb_xdp_uuid))
+		return -EINVAL;
+
+	mutex_lock(&xdomain_lock);
+	list_add_tail(&handler->list, &protocol_handlers);
+	mutex_unlock(&xdomain_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tb_register_protocol_handler);
+
+/**
+ * tb_unregister_protocol_handler() - Unregister protocol handler
+ * @handler: Handler to unregister
+ *
+ * Removes the previously registered protocol handler.
+ */
+void tb_unregister_protocol_handler(struct tb_protocol_handler *handler)
+{
+	mutex_lock(&xdomain_lock);
+	list_del_init(&handler->list);
+	mutex_unlock(&xdomain_lock);
+}
+EXPORT_SYMBOL_GPL(tb_unregister_protocol_handler);
+
+static void tb_xdp_handle_request(struct work_struct *work)
+{
+	struct xdomain_request_work *xw = container_of(work, typeof(*xw), work);
+	const struct tb_xdp_header *pkg = xw->pkg;
+	const struct tb_xdomain_header *xhdr = &pkg->xd_hdr;
+	struct tb *tb = xw->tb;
+	struct tb_ctl *ctl = tb->ctl;
+	const uuid_t *uuid;
+	int ret = 0;
+	u32 sequence;
+	u64 route;
+
+	route = ((u64)xhdr->route_hi << 32 | xhdr->route_lo) & ~BIT_ULL(63);
+	sequence = xhdr->length_sn & TB_XDOMAIN_SN_MASK;
+	sequence >>= TB_XDOMAIN_SN_SHIFT;
+
+	mutex_lock(&tb->lock);
+	if (tb->root_switch)
+		uuid = tb->root_switch->uuid;
+	else
+		uuid = NULL;
+	mutex_unlock(&tb->lock);
+
+	if (!uuid) {
+		tb_xdp_error_response(ctl, route, sequence, ERROR_NOT_READY);
+		goto out;
+	}
+
+	switch (pkg->type) {
+	case PROPERTIES_REQUEST:
+		ret = tb_xdp_properties_response(tb, ctl, route, sequence, uuid,
+			(const struct tb_xdp_properties *)pkg);
+		break;
+
+	case PROPERTIES_CHANGED_REQUEST: {
+		const struct tb_xdp_properties_changed *xchg =
+			(const struct tb_xdp_properties_changed *)pkg;
+		struct tb_xdomain *xd;
+
+		ret = tb_xdp_properties_changed_response(ctl, route, sequence);
+
+		/*
+		 * Since the properties have been changed, let's update
+		 * the xdomain related to this connection as well in
+		 * case there is a change in services it offers.
+		 */
+		xd = tb_xdomain_find_by_uuid_locked(tb, &xchg->src_uuid);
+		if (xd) {
+			queue_delayed_work(tb->wq, &xd->get_properties_work,
+					   msecs_to_jiffies(50));
+			tb_xdomain_put(xd);
+		}
+
+		break;
+	}
+
+	default:
+		break;
+	}
+
+	if (ret) {
+		tb_warn(tb, "failed to send XDomain response for %#x\n",
+			pkg->type);
+	}
+
+out:
+	kfree(xw->pkg);
+	kfree(xw);
+}
+
+static void
+tb_xdp_schedule_request(struct tb *tb, const struct tb_xdp_header *hdr,
+			size_t size)
+{
+	struct xdomain_request_work *xw;
+
+	xw = kmalloc(sizeof(*xw), GFP_KERNEL);
+	if (!xw)
+		return;
+
+	INIT_WORK(&xw->work, tb_xdp_handle_request);
+	xw->pkg = kmemdup(hdr, size, GFP_KERNEL);
+	xw->tb = tb;
+
+	queue_work(tb->wq, &xw->work);
+}
+
+/**
+ * tb_register_service_driver() - Register XDomain service driver
+ * @drv: Driver to register
+ *
+ * Registers new service driver from @drv to the bus.
+ */
+int tb_register_service_driver(struct tb_service_driver *drv)
+{
+	drv->driver.bus = &tb_bus_type;
+	return driver_register(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(tb_register_service_driver);
+
+/**
+ * tb_unregister_service_driver() - Unregister XDomain service driver
+ * @xdrv: Driver to unregister
+ *
+ * Unregisters XDomain service driver from the bus.
+ */
+void tb_unregister_service_driver(struct tb_service_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(tb_unregister_service_driver);
+
+static ssize_t key_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	struct tb_service *svc = container_of(dev, struct tb_service, dev);
+
+	/*
+	 * It should be null terminated but anything else is pretty much
+	 * allowed.
+	 */
+	return sprintf(buf, "%*pEp\n", (int)strlen(svc->key), svc->key);
+}
+static DEVICE_ATTR_RO(key);
+
+static int get_modalias(struct tb_service *svc, char *buf, size_t size)
+{
+	return snprintf(buf, size, "tbsvc:k%sp%08Xv%08Xr%08X", svc->key,
+			svc->prtcid, svc->prtcvers, svc->prtcrevs);
+}
+
+static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct tb_service *svc = container_of(dev, struct tb_service, dev);
+
+	/* Full buffer size except new line and null termination */
+	get_modalias(svc, buf, PAGE_SIZE - 2);
+	return sprintf(buf, "%s\n", buf);
+}
+static DEVICE_ATTR_RO(modalias);
+
+static ssize_t prtcid_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct tb_service *svc = container_of(dev, struct tb_service, dev);
+
+	return sprintf(buf, "%u\n", svc->prtcid);
+}
+static DEVICE_ATTR_RO(prtcid);
+
+static ssize_t prtcvers_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct tb_service *svc = container_of(dev, struct tb_service, dev);
+
+	return sprintf(buf, "%u\n", svc->prtcvers);
+}
+static DEVICE_ATTR_RO(prtcvers);
+
+static ssize_t prtcrevs_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct tb_service *svc = container_of(dev, struct tb_service, dev);
+
+	return sprintf(buf, "%u\n", svc->prtcrevs);
+}
+static DEVICE_ATTR_RO(prtcrevs);
+
+static ssize_t prtcstns_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct tb_service *svc = container_of(dev, struct tb_service, dev);
+
+	return sprintf(buf, "0x%08x\n", svc->prtcstns);
+}
+static DEVICE_ATTR_RO(prtcstns);
+
+static struct attribute *tb_service_attrs[] = {
+	&dev_attr_key.attr,
+	&dev_attr_modalias.attr,
+	&dev_attr_prtcid.attr,
+	&dev_attr_prtcvers.attr,
+	&dev_attr_prtcrevs.attr,
+	&dev_attr_prtcstns.attr,
+	NULL,
+};
+
+static struct attribute_group tb_service_attr_group = {
+	.attrs = tb_service_attrs,
+};
+
+static const struct attribute_group *tb_service_attr_groups[] = {
+	&tb_service_attr_group,
+	NULL,
+};
+
+static int tb_service_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct tb_service *svc = container_of(dev, struct tb_service, dev);
+	char modalias[64];
+
+	get_modalias(svc, modalias, sizeof(modalias));
+	return add_uevent_var(env, "MODALIAS=%s", modalias);
+}
+
+static void tb_service_release(struct device *dev)
+{
+	struct tb_service *svc = container_of(dev, struct tb_service, dev);
+	struct tb_xdomain *xd = tb_service_parent(svc);
+
+	ida_simple_remove(&xd->service_ids, svc->id);
+	kfree(svc->key);
+	kfree(svc);
+}
+
+struct device_type tb_service_type = {
+	.name = "thunderbolt_service",
+	.groups = tb_service_attr_groups,
+	.uevent = tb_service_uevent,
+	.release = tb_service_release,
+};
+EXPORT_SYMBOL_GPL(tb_service_type);
+
+static int remove_missing_service(struct device *dev, void *data)
+{
+	struct tb_xdomain *xd = data;
+	struct tb_service *svc;
+
+	svc = tb_to_service(dev);
+	if (!svc)
+		return 0;
+
+	if (!tb_property_find(xd->properties, svc->key,
+			      TB_PROPERTY_TYPE_DIRECTORY))
+		device_unregister(dev);
+
+	return 0;
+}
+
+static int find_service(struct device *dev, void *data)
+{
+	const struct tb_property *p = data;
+	struct tb_service *svc;
+
+	svc = tb_to_service(dev);
+	if (!svc)
+		return 0;
+
+	return !strcmp(svc->key, p->key);
+}
+
+static int populate_service(struct tb_service *svc,
+			    struct tb_property *property)
+{
+	struct tb_property_dir *dir = property->value.dir;
+	struct tb_property *p;
+
+	/* Fill in standard properties */
+	p = tb_property_find(dir, "prtcid", TB_PROPERTY_TYPE_VALUE);
+	if (p)
+		svc->prtcid = p->value.immediate;
+	p = tb_property_find(dir, "prtcvers", TB_PROPERTY_TYPE_VALUE);
+	if (p)
+		svc->prtcvers = p->value.immediate;
+	p = tb_property_find(dir, "prtcrevs", TB_PROPERTY_TYPE_VALUE);
+	if (p)
+		svc->prtcrevs = p->value.immediate;
+	p = tb_property_find(dir, "prtcstns", TB_PROPERTY_TYPE_VALUE);
+	if (p)
+		svc->prtcstns = p->value.immediate;
+
+	svc->key = kstrdup(property->key, GFP_KERNEL);
+	if (!svc->key)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void enumerate_services(struct tb_xdomain *xd)
+{
+	struct tb_service *svc;
+	struct tb_property *p;
+	struct device *dev;
+
+	/*
+	 * First remove all services that are not available anymore in
+	 * the updated property block.
+	 */
+	device_for_each_child_reverse(&xd->dev, xd, remove_missing_service);
+
+	/* Then re-enumerate properties creating new services as we go */
+	tb_property_for_each(xd->properties, p) {
+		if (p->type != TB_PROPERTY_TYPE_DIRECTORY)
+			continue;
+
+		/* If the service exists already we are fine */
+		dev = device_find_child(&xd->dev, p, find_service);
+		if (dev) {
+			put_device(dev);
+			continue;
+		}
+
+		svc = kzalloc(sizeof(*svc), GFP_KERNEL);
+		if (!svc)
+			break;
+
+		if (populate_service(svc, p)) {
+			kfree(svc);
+			break;
+		}
+
+		svc->id = ida_simple_get(&xd->service_ids, 0, 0, GFP_KERNEL);
+		svc->dev.bus = &tb_bus_type;
+		svc->dev.type = &tb_service_type;
+		svc->dev.parent = &xd->dev;
+		dev_set_name(&svc->dev, "%s.%d", dev_name(&xd->dev), svc->id);
+
+		if (device_register(&svc->dev)) {
+			put_device(&svc->dev);
+			break;
+		}
+	}
+}
+
+static int populate_properties(struct tb_xdomain *xd,
+			       struct tb_property_dir *dir)
+{
+	const struct tb_property *p;
+
+	/* Required properties */
+	p = tb_property_find(dir, "deviceid", TB_PROPERTY_TYPE_VALUE);
+	if (!p)
+		return -EINVAL;
+	xd->device = p->value.immediate;
+
+	p = tb_property_find(dir, "vendorid", TB_PROPERTY_TYPE_VALUE);
+	if (!p)
+		return -EINVAL;
+	xd->vendor = p->value.immediate;
+
+	kfree(xd->device_name);
+	xd->device_name = NULL;
+	kfree(xd->vendor_name);
+	xd->vendor_name = NULL;
+
+	/* Optional properties */
+	p = tb_property_find(dir, "deviceid", TB_PROPERTY_TYPE_TEXT);
+	if (p)
+		xd->device_name = kstrdup(p->value.text, GFP_KERNEL);
+	p = tb_property_find(dir, "vendorid", TB_PROPERTY_TYPE_TEXT);
+	if (p)
+		xd->vendor_name = kstrdup(p->value.text, GFP_KERNEL);
+
+	return 0;
+}
+
+/* Called with @xd->lock held */
+static void tb_xdomain_restore_paths(struct tb_xdomain *xd)
+{
+	if (!xd->resume)
+		return;
+
+	xd->resume = false;
+	if (xd->transmit_path) {
+		dev_dbg(&xd->dev, "re-establishing DMA path\n");
+		tb_domain_approve_xdomain_paths(xd->tb, xd);
+	}
+}
+
+static void tb_xdomain_get_properties(struct work_struct *work)
+{
+	struct tb_xdomain *xd = container_of(work, typeof(*xd),
+					     get_properties_work.work);
+	struct tb_property_dir *dir;
+	struct tb *tb = xd->tb;
+	bool update = false;
+	u32 *block = NULL;
+	u32 gen = 0;
+	int ret;
+
+	ret = tb_xdp_properties_request(tb->ctl, xd->route, xd->local_uuid,
+					xd->remote_uuid, xd->properties_retries,
+					&block, &gen);
+	if (ret < 0) {
+		if (xd->properties_retries-- > 0) {
+			queue_delayed_work(xd->tb->wq, &xd->get_properties_work,
+					   msecs_to_jiffies(1000));
+		} else {
+			/* Give up now */
+			dev_err(&xd->dev,
+				"failed read XDomain properties from %pUb\n",
+				xd->remote_uuid);
+		}
+		return;
+	}
+
+	xd->properties_retries = XDOMAIN_PROPERTIES_RETRIES;
+
+	mutex_lock(&xd->lock);
+
+	/* Only accept newer generation properties */
+	if (xd->properties && gen <= xd->property_block_gen) {
+		/*
+		 * On resume it is likely that the properties block is
+		 * not changed (unless the other end added or removed
+		 * services). However, we need to make sure the existing
+		 * DMA paths are restored properly.
+		 */
+		tb_xdomain_restore_paths(xd);
+		goto err_free_block;
+	}
+
+	dir = tb_property_parse_dir(block, ret);
+	if (!dir) {
+		dev_err(&xd->dev, "failed to parse XDomain properties\n");
+		goto err_free_block;
+	}
+
+	ret = populate_properties(xd, dir);
+	if (ret) {
+		dev_err(&xd->dev, "missing XDomain properties in response\n");
+		goto err_free_dir;
+	}
+
+	/* Release the existing one */
+	if (xd->properties) {
+		tb_property_free_dir(xd->properties);
+		update = true;
+	}
+
+	xd->properties = dir;
+	xd->property_block_gen = gen;
+
+	tb_xdomain_restore_paths(xd);
+
+	mutex_unlock(&xd->lock);
+
+	kfree(block);
+
+	/*
+	 * Now the device should be ready enough so we can add it to the
+	 * bus and let userspace know about it. If the device is already
+	 * registered, we notify the userspace that it has changed.
+	 */
+	if (!update) {
+		if (device_add(&xd->dev)) {
+			dev_err(&xd->dev, "failed to add XDomain device\n");
+			return;
+		}
+	} else {
+		kobject_uevent(&xd->dev.kobj, KOBJ_CHANGE);
+	}
+
+	enumerate_services(xd);
+	return;
+
+err_free_dir:
+	tb_property_free_dir(dir);
+err_free_block:
+	kfree(block);
+	mutex_unlock(&xd->lock);
+}
+
+static void tb_xdomain_properties_changed(struct work_struct *work)
+{
+	struct tb_xdomain *xd = container_of(work, typeof(*xd),
+					     properties_changed_work.work);
+	int ret;
+
+	ret = tb_xdp_properties_changed_request(xd->tb->ctl, xd->route,
+				xd->properties_changed_retries, xd->local_uuid);
+	if (ret) {
+		if (xd->properties_changed_retries-- > 0)
+			queue_delayed_work(xd->tb->wq,
+					   &xd->properties_changed_work,
+					   msecs_to_jiffies(1000));
+		return;
+	}
+
+	xd->properties_changed_retries = XDOMAIN_PROPERTIES_CHANGED_RETRIES;
+}
+
+static ssize_t device_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev);
+
+	return sprintf(buf, "%#x\n", xd->device);
+}
+static DEVICE_ATTR_RO(device);
+
+static ssize_t
+device_name_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev);
+	int ret;
+
+	if (mutex_lock_interruptible(&xd->lock))
+		return -ERESTARTSYS;
+	ret = sprintf(buf, "%s\n", xd->device_name ? xd->device_name : "");
+	mutex_unlock(&xd->lock);
+
+	return ret;
+}
+static DEVICE_ATTR_RO(device_name);
+
+static ssize_t vendor_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev);
+
+	return sprintf(buf, "%#x\n", xd->vendor);
+}
+static DEVICE_ATTR_RO(vendor);
+
+static ssize_t
+vendor_name_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev);
+	int ret;
+
+	if (mutex_lock_interruptible(&xd->lock))
+		return -ERESTARTSYS;
+	ret = sprintf(buf, "%s\n", xd->vendor_name ? xd->vendor_name : "");
+	mutex_unlock(&xd->lock);
+
+	return ret;
+}
+static DEVICE_ATTR_RO(vendor_name);
+
+static ssize_t unique_id_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev);
+
+	return sprintf(buf, "%pUb\n", xd->remote_uuid);
+}
+static DEVICE_ATTR_RO(unique_id);
+
+static struct attribute *xdomain_attrs[] = {
+	&dev_attr_device.attr,
+	&dev_attr_device_name.attr,
+	&dev_attr_unique_id.attr,
+	&dev_attr_vendor.attr,
+	&dev_attr_vendor_name.attr,
+	NULL,
+};
+
+static struct attribute_group xdomain_attr_group = {
+	.attrs = xdomain_attrs,
+};
+
+static const struct attribute_group *xdomain_attr_groups[] = {
+	&xdomain_attr_group,
+	NULL,
+};
+
+static void tb_xdomain_release(struct device *dev)
+{
+	struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev);
+
+	put_device(xd->dev.parent);
+
+	tb_property_free_dir(xd->properties);
+	ida_destroy(&xd->service_ids);
+
+	kfree(xd->local_uuid);
+	kfree(xd->remote_uuid);
+	kfree(xd->device_name);
+	kfree(xd->vendor_name);
+	kfree(xd);
+}
+
+static void start_handshake(struct tb_xdomain *xd)
+{
+	xd->properties_retries = XDOMAIN_PROPERTIES_RETRIES;
+	xd->properties_changed_retries = XDOMAIN_PROPERTIES_CHANGED_RETRIES;
+
+	/* Start exchanging properties with the other host */
+	queue_delayed_work(xd->tb->wq, &xd->properties_changed_work,
+			   msecs_to_jiffies(100));
+	queue_delayed_work(xd->tb->wq, &xd->get_properties_work,
+			   msecs_to_jiffies(1000));
+}
+
+static void stop_handshake(struct tb_xdomain *xd)
+{
+	xd->properties_retries = 0;
+	xd->properties_changed_retries = 0;
+
+	cancel_delayed_work_sync(&xd->get_properties_work);
+	cancel_delayed_work_sync(&xd->properties_changed_work);
+}
+
+static int __maybe_unused tb_xdomain_suspend(struct device *dev)
+{
+	stop_handshake(tb_to_xdomain(dev));
+	return 0;
+}
+
+static int __maybe_unused tb_xdomain_resume(struct device *dev)
+{
+	struct tb_xdomain *xd = tb_to_xdomain(dev);
+
+	/*
+	 * Ask tb_xdomain_get_properties() restore any existing DMA
+	 * paths after properties are re-read.
+	 */
+	xd->resume = true;
+	start_handshake(xd);
+
+	return 0;
+}
+
+static const struct dev_pm_ops tb_xdomain_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(tb_xdomain_suspend, tb_xdomain_resume)
+};
+
+struct device_type tb_xdomain_type = {
+	.name = "thunderbolt_xdomain",
+	.release = tb_xdomain_release,
+	.pm = &tb_xdomain_pm_ops,
+};
+EXPORT_SYMBOL_GPL(tb_xdomain_type);
+
+/**
+ * tb_xdomain_alloc() - Allocate new XDomain object
+ * @tb: Domain where the XDomain belongs
+ * @parent: Parent device (the switch through the connection to the
+ *	    other domain is reached).
+ * @route: Route string used to reach the other domain
+ * @local_uuid: Our local domain UUID
+ * @remote_uuid: UUID of the other domain
+ *
+ * Allocates new XDomain structure and returns pointer to that. The
+ * object must be released by calling tb_xdomain_put().
+ */
+struct tb_xdomain *tb_xdomain_alloc(struct tb *tb, struct device *parent,
+				    u64 route, const uuid_t *local_uuid,
+				    const uuid_t *remote_uuid)
+{
+	struct tb_xdomain *xd;
+
+	xd = kzalloc(sizeof(*xd), GFP_KERNEL);
+	if (!xd)
+		return NULL;
+
+	xd->tb = tb;
+	xd->route = route;
+	ida_init(&xd->service_ids);
+	mutex_init(&xd->lock);
+	INIT_DELAYED_WORK(&xd->get_properties_work, tb_xdomain_get_properties);
+	INIT_DELAYED_WORK(&xd->properties_changed_work,
+			  tb_xdomain_properties_changed);
+
+	xd->local_uuid = kmemdup(local_uuid, sizeof(uuid_t), GFP_KERNEL);
+	if (!xd->local_uuid)
+		goto err_free;
+
+	xd->remote_uuid = kmemdup(remote_uuid, sizeof(uuid_t), GFP_KERNEL);
+	if (!xd->remote_uuid)
+		goto err_free_local_uuid;
+
+	device_initialize(&xd->dev);
+	xd->dev.parent = get_device(parent);
+	xd->dev.bus = &tb_bus_type;
+	xd->dev.type = &tb_xdomain_type;
+	xd->dev.groups = xdomain_attr_groups;
+	dev_set_name(&xd->dev, "%u-%llx", tb->index, route);
+
+	return xd;
+
+err_free_local_uuid:
+	kfree(xd->local_uuid);
+err_free:
+	kfree(xd);
+
+	return NULL;
+}
+
+/**
+ * tb_xdomain_add() - Add XDomain to the bus
+ * @xd: XDomain to add
+ *
+ * This function starts XDomain discovery protocol handshake and
+ * eventually adds the XDomain to the bus. After calling this function
+ * the caller needs to call tb_xdomain_remove() in order to remove and
+ * release the object regardless whether the handshake succeeded or not.
+ */
+void tb_xdomain_add(struct tb_xdomain *xd)
+{
+	/* Start exchanging properties with the other host */
+	start_handshake(xd);
+}
+
+static int unregister_service(struct device *dev, void *data)
+{
+	device_unregister(dev);
+	return 0;
+}
+
+/**
+ * tb_xdomain_remove() - Remove XDomain from the bus
+ * @xd: XDomain to remove
+ *
+ * This will stop all ongoing configuration work and remove the XDomain
+ * along with any services from the bus. When the last reference to @xd
+ * is released the object will be released as well.
+ */
+void tb_xdomain_remove(struct tb_xdomain *xd)
+{
+	stop_handshake(xd);
+
+	device_for_each_child_reverse(&xd->dev, xd, unregister_service);
+
+	if (!device_is_registered(&xd->dev))
+		put_device(&xd->dev);
+	else
+		device_unregister(&xd->dev);
+}
+
+/**
+ * tb_xdomain_enable_paths() - Enable DMA paths for XDomain connection
+ * @xd: XDomain connection
+ * @transmit_path: HopID of the transmit path the other end is using to
+ *		   send packets
+ * @transmit_ring: DMA ring used to receive packets from the other end
+ * @receive_path: HopID of the receive path the other end is using to
+ *		  receive packets
+ * @receive_ring: DMA ring used to send packets to the other end
+ *
+ * The function enables DMA paths accordingly so that after successful
+ * return the caller can send and receive packets using high-speed DMA
+ * path.
+ *
+ * Return: %0 in case of success and negative errno in case of error
+ */
+int tb_xdomain_enable_paths(struct tb_xdomain *xd, u16 transmit_path,
+			    u16 transmit_ring, u16 receive_path,
+			    u16 receive_ring)
+{
+	int ret;
+
+	mutex_lock(&xd->lock);
+
+	if (xd->transmit_path) {
+		ret = xd->transmit_path == transmit_path ? 0 : -EBUSY;
+		goto exit_unlock;
+	}
+
+	xd->transmit_path = transmit_path;
+	xd->transmit_ring = transmit_ring;
+	xd->receive_path = receive_path;
+	xd->receive_ring = receive_ring;
+
+	ret = tb_domain_approve_xdomain_paths(xd->tb, xd);
+
+exit_unlock:
+	mutex_unlock(&xd->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tb_xdomain_enable_paths);
+
+/**
+ * tb_xdomain_disable_paths() - Disable DMA paths for XDomain connection
+ * @xd: XDomain connection
+ *
+ * This does the opposite of tb_xdomain_enable_paths(). After call to
+ * this the caller is not expected to use the rings anymore.
+ *
+ * Return: %0 in case of success and negative errno in case of error
+ */
+int tb_xdomain_disable_paths(struct tb_xdomain *xd)
+{
+	int ret = 0;
+
+	mutex_lock(&xd->lock);
+	if (xd->transmit_path) {
+		xd->transmit_path = 0;
+		xd->transmit_ring = 0;
+		xd->receive_path = 0;
+		xd->receive_ring = 0;
+
+		ret = tb_domain_disconnect_xdomain_paths(xd->tb, xd);
+	}
+	mutex_unlock(&xd->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tb_xdomain_disable_paths);
+
+struct tb_xdomain_lookup {
+	const uuid_t *uuid;
+	u8 link;
+	u8 depth;
+};
+
+static struct tb_xdomain *switch_find_xdomain(struct tb_switch *sw,
+	const struct tb_xdomain_lookup *lookup)
+{
+	int i;
+
+	for (i = 1; i <= sw->config.max_port_number; i++) {
+		struct tb_port *port = &sw->ports[i];
+		struct tb_xdomain *xd;
+
+		if (tb_is_upstream_port(port))
+			continue;
+
+		if (port->xdomain) {
+			xd = port->xdomain;
+
+			if (lookup->uuid) {
+				if (uuid_equal(xd->remote_uuid, lookup->uuid))
+					return xd;
+			} else if (lookup->link == xd->link &&
+				   lookup->depth == xd->depth) {
+				return xd;
+			}
+		} else if (port->remote) {
+			xd = switch_find_xdomain(port->remote->sw, lookup);
+			if (xd)
+				return xd;
+		}
+	}
+
+	return NULL;
+}
+
+/**
+ * tb_xdomain_find_by_uuid() - Find an XDomain by UUID
+ * @tb: Domain where the XDomain belongs to
+ * @uuid: UUID to look for
+ *
+ * Finds XDomain by walking through the Thunderbolt topology below @tb.
+ * The returned XDomain will have its reference count increased so the
+ * caller needs to call tb_xdomain_put() when it is done with the
+ * object.
+ *
+ * This will find all XDomains including the ones that are not yet added
+ * to the bus (handshake is still in progress).
+ *
+ * The caller needs to hold @tb->lock.
+ */
+struct tb_xdomain *tb_xdomain_find_by_uuid(struct tb *tb, const uuid_t *uuid)
+{
+	struct tb_xdomain_lookup lookup;
+	struct tb_xdomain *xd;
+
+	memset(&lookup, 0, sizeof(lookup));
+	lookup.uuid = uuid;
+
+	xd = switch_find_xdomain(tb->root_switch, &lookup);
+	if (xd) {
+		get_device(&xd->dev);
+		return xd;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(tb_xdomain_find_by_uuid);
+
+/**
+ * tb_xdomain_find_by_link_depth() - Find an XDomain by link and depth
+ * @tb: Domain where the XDomain belongs to
+ * @link: Root switch link number
+ * @depth: Depth in the link
+ *
+ * Finds XDomain by walking through the Thunderbolt topology below @tb.
+ * The returned XDomain will have its reference count increased so the
+ * caller needs to call tb_xdomain_put() when it is done with the
+ * object.
+ *
+ * This will find all XDomains including the ones that are not yet added
+ * to the bus (handshake is still in progress).
+ *
+ * The caller needs to hold @tb->lock.
+ */
+struct tb_xdomain *tb_xdomain_find_by_link_depth(struct tb *tb, u8 link,
+						 u8 depth)
+{
+	struct tb_xdomain_lookup lookup;
+	struct tb_xdomain *xd;
+
+	memset(&lookup, 0, sizeof(lookup));
+	lookup.link = link;
+	lookup.depth = depth;
+
+	xd = switch_find_xdomain(tb->root_switch, &lookup);
+	if (xd) {
+		get_device(&xd->dev);
+		return xd;
+	}
+
+	return NULL;
+}
+
+bool tb_xdomain_handle_request(struct tb *tb, enum tb_cfg_pkg_type type,
+			       const void *buf, size_t size)
+{
+	const struct tb_protocol_handler *handler, *tmp;
+	const struct tb_xdp_header *hdr = buf;
+	unsigned int length;
+	int ret = 0;
+
+	/* We expect the packet is at least size of the header */
+	length = hdr->xd_hdr.length_sn & TB_XDOMAIN_LENGTH_MASK;
+	if (length != size / 4 - sizeof(hdr->xd_hdr) / 4)
+		return true;
+	if (length < sizeof(*hdr) / 4 - sizeof(hdr->xd_hdr) / 4)
+		return true;
+
+	/*
+	 * Handle XDomain discovery protocol packets directly here. For
+	 * other protocols (based on their UUID) we call registered
+	 * handlers in turn.
+	 */
+	if (uuid_equal(&hdr->uuid, &tb_xdp_uuid)) {
+		if (type == TB_CFG_PKG_XDOMAIN_REQ) {
+			tb_xdp_schedule_request(tb, hdr, size);
+			return true;
+		}
+		return false;
+	}
+
+	mutex_lock(&xdomain_lock);
+	list_for_each_entry_safe(handler, tmp, &protocol_handlers, list) {
+		if (!uuid_equal(&hdr->uuid, handler->uuid))
+			continue;
+
+		mutex_unlock(&xdomain_lock);
+		ret = handler->callback(buf, size, handler->data);
+		mutex_lock(&xdomain_lock);
+
+		if (ret)
+			break;
+	}
+	mutex_unlock(&xdomain_lock);
+
+	return ret > 0;
+}
+
+static int rebuild_property_block(void)
+{
+	u32 *block, len;
+	int ret;
+
+	ret = tb_property_format_dir(xdomain_property_dir, NULL, 0);
+	if (ret < 0)
+		return ret;
+
+	len = ret;
+
+	block = kcalloc(len, sizeof(u32), GFP_KERNEL);
+	if (!block)
+		return -ENOMEM;
+
+	ret = tb_property_format_dir(xdomain_property_dir, block, len);
+	if (ret) {
+		kfree(block);
+		return ret;
+	}
+
+	kfree(xdomain_property_block);
+	xdomain_property_block = block;
+	xdomain_property_block_len = len;
+	xdomain_property_block_gen++;
+
+	return 0;
+}
+
+static int update_xdomain(struct device *dev, void *data)
+{
+	struct tb_xdomain *xd;
+
+	xd = tb_to_xdomain(dev);
+	if (xd) {
+		queue_delayed_work(xd->tb->wq, &xd->properties_changed_work,
+				   msecs_to_jiffies(50));
+	}
+
+	return 0;
+}
+
+static void update_all_xdomains(void)
+{
+	bus_for_each_dev(&tb_bus_type, NULL, NULL, update_xdomain);
+}
+
+static bool remove_directory(const char *key, const struct tb_property_dir *dir)
+{
+	struct tb_property *p;
+
+	p = tb_property_find(xdomain_property_dir, key,
+			     TB_PROPERTY_TYPE_DIRECTORY);
+	if (p && p->value.dir == dir) {
+		tb_property_remove(p);
+		return true;
+	}
+	return false;
+}
+
+/**
+ * tb_register_property_dir() - Register property directory to the host
+ * @key: Key (name) of the directory to add
+ * @dir: Directory to add
+ *
+ * Service drivers can use this function to add new property directory
+ * to the host available properties. The other connected hosts are
+ * notified so they can re-read properties of this host if they are
+ * interested.
+ *
+ * Return: %0 on success and negative errno on failure
+ */
+int tb_register_property_dir(const char *key, struct tb_property_dir *dir)
+{
+	int ret;
+
+	if (WARN_ON(!xdomain_property_dir))
+		return -EAGAIN;
+
+	if (!key || strlen(key) > 8)
+		return -EINVAL;
+
+	mutex_lock(&xdomain_lock);
+	if (tb_property_find(xdomain_property_dir, key,
+			     TB_PROPERTY_TYPE_DIRECTORY)) {
+		ret = -EEXIST;
+		goto err_unlock;
+	}
+
+	ret = tb_property_add_dir(xdomain_property_dir, key, dir);
+	if (ret)
+		goto err_unlock;
+
+	ret = rebuild_property_block();
+	if (ret) {
+		remove_directory(key, dir);
+		goto err_unlock;
+	}
+
+	mutex_unlock(&xdomain_lock);
+	update_all_xdomains();
+	return 0;
+
+err_unlock:
+	mutex_unlock(&xdomain_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tb_register_property_dir);
+
+/**
+ * tb_unregister_property_dir() - Removes property directory from host
+ * @key: Key (name) of the directory
+ * @dir: Directory to remove
+ *
+ * This will remove the existing directory from this host and notify the
+ * connected hosts about the change.
+ */
+void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir)
+{
+	int ret = 0;
+
+	mutex_lock(&xdomain_lock);
+	if (remove_directory(key, dir))
+		ret = rebuild_property_block();
+	mutex_unlock(&xdomain_lock);
+
+	if (!ret)
+		update_all_xdomains();
+}
+EXPORT_SYMBOL_GPL(tb_unregister_property_dir);
+
+int tb_xdomain_init(void)
+{
+	int ret;
+
+	xdomain_property_dir = tb_property_create_dir(NULL);
+	if (!xdomain_property_dir)
+		return -ENOMEM;
+
+	/*
+	 * Initialize standard set of properties without any service
+	 * directories. Those will be added by service drivers
+	 * themselves when they are loaded.
+	 */
+	tb_property_add_immediate(xdomain_property_dir, "vendorid",
+				  PCI_VENDOR_ID_INTEL);
+	tb_property_add_text(xdomain_property_dir, "vendorid", "Intel Corp.");
+	tb_property_add_immediate(xdomain_property_dir, "deviceid", 0x1);
+	tb_property_add_text(xdomain_property_dir, "deviceid",
+			     utsname()->nodename);
+	tb_property_add_immediate(xdomain_property_dir, "devicerv", 0x80000100);
+
+	ret = rebuild_property_block();
+	if (ret) {
+		tb_property_free_dir(xdomain_property_dir);
+		xdomain_property_dir = NULL;
+	}
+
+	return ret;
+}
+
+void tb_xdomain_exit(void)
+{
+	kfree(xdomain_property_block);
+	tb_property_free_dir(xdomain_property_dir);
+}
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 58585ec8699e..68677d930e20 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -436,8 +436,8 @@ static bool vhost_exceeds_maxpend(struct vhost_net *net)
 	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
 	struct vhost_virtqueue *vq = &nvq->vq;
 
-	return (nvq->upend_idx + vq->num - VHOST_MAX_PEND) % UIO_MAXIOV
-		== nvq->done_idx;
+	return (nvq->upend_idx + UIO_MAXIOV - nvq->done_idx) % UIO_MAXIOV >
+	       min_t(unsigned int, VHOST_MAX_PEND, vq->num >> 2);
 }
 
 /* Expects to be always run from workqueue - which acts as
@@ -480,11 +480,6 @@ static void handle_tx(struct vhost_net *net)
 		if (zcopy)
 			vhost_zerocopy_signal_used(net, vq);
 
-		/* If more outstanding DMAs, queue the work.
-		 * Handle upend_idx wrap around
-		 */
-		if (unlikely(vhost_exceeds_maxpend(net)))
-			break;
 
 		head = vhost_net_tx_get_vq_desc(net, vq, vq->iov,
 						ARRAY_SIZE(vq->iov),
@@ -519,8 +514,7 @@ static void handle_tx(struct vhost_net *net)
 		len = msg_data_left(&msg);
 
 		zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN
-				   && (nvq->upend_idx + 1) % UIO_MAXIOV !=
-				      nvq->done_idx
+				   && !vhost_exceeds_maxpend(net)
 				   && vhost_net_tx_select_zcopy(net);
 
 		/* use msg_control to pass vhost zerocopy ubuf info to skb */
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 82e16556afea..3f03f7888302 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -100,6 +100,7 @@ struct afs_call {
 	bool			send_pages;	/* T if data from mapping should be sent */
 	bool			need_attention;	/* T if RxRPC poked us */
 	bool			async;		/* T if asynchronous */
+	bool			upgrade;	/* T to request service upgrade */
 	u16			service_id;	/* RxRPC service ID to call */
 	__be16			port;		/* target UDP port */
 	u32			operation_ID;	/* operation ID for an incoming call */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 0bf191f0dbaf..bb1e2caa1720 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -387,7 +387,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 					 tx_total_len, gfp,
 					 (async ?
 					  afs_wake_up_async_call :
-					  afs_wake_up_call_waiter));
+					  afs_wake_up_call_waiter),
+					 call->upgrade);
 	call->key = NULL;
 	if (IS_ERR(rxcall)) {
 		ret = PTR_ERR(rxcall);
@@ -406,7 +407,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 		      call->request_size);
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
-	msg.msg_flags		= (call->send_pages ? MSG_MORE : 0);
+	msg.msg_flags		= MSG_WAITALL | (call->send_pages ? MSG_MORE : 0);
 
 	/* We have to change the state *before* sending the last packet as
 	 * rxrpc might give us the reply before it returns from sending the
@@ -443,7 +444,7 @@ error_do_abort:
 		abort_code = 0;
 		offset = 0;
 		rxrpc_kernel_recv_data(afs_socket, rxcall, NULL, 0, &offset,
-				       false, &abort_code);
+				       false, &abort_code, &call->service_id);
 		ret = call->type->abort_to_error(abort_code);
 	}
 error_kill_call:
@@ -471,7 +472,8 @@ static void afs_deliver_to_call(struct afs_call *call)
 			size_t offset = 0;
 			ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall,
 						     NULL, 0, &offset, false,
-						     &call->abort_code);
+						     &call->abort_code,
+						     &call->service_id);
 			trace_afs_recv_data(call, 0, offset, false, ret);
 
 			if (ret == -EINPROGRESS || ret == -EAGAIN)
@@ -536,15 +538,26 @@ call_complete:
  */
 static int afs_wait_for_call_to_complete(struct afs_call *call)
 {
+	signed long rtt2, timeout;
 	int ret;
+	u64 rtt;
+	u32 life, last_life;
 
 	DECLARE_WAITQUEUE(myself, current);
 
 	_enter("");
 
+	rtt = rxrpc_kernel_get_rtt(afs_socket, call->rxcall);
+	rtt2 = nsecs_to_jiffies64(rtt) * 2;
+	if (rtt2 < 2)
+		rtt2 = 2;
+
+	timeout = rtt2;
+	last_life = rxrpc_kernel_check_life(afs_socket, call->rxcall);
+
 	add_wait_queue(&call->waitq, &myself);
 	for (;;) {
-		set_current_state(TASK_INTERRUPTIBLE);
+		set_current_state(TASK_UNINTERRUPTIBLE);
 
 		/* deliver any messages that are in the queue */
 		if (call->state < AFS_CALL_COMPLETE && call->need_attention) {
@@ -554,10 +567,20 @@ static int afs_wait_for_call_to_complete(struct afs_call *call)
 			continue;
 		}
 
-		if (call->state == AFS_CALL_COMPLETE ||
-		    signal_pending(current))
+		if (call->state == AFS_CALL_COMPLETE)
 			break;
-		schedule();
+
+		life = rxrpc_kernel_check_life(afs_socket, call->rxcall);
+		if (timeout == 0 &&
+		    life == last_life && signal_pending(current))
+				break;
+
+		if (life != last_life) {
+			timeout = rtt2;
+			last_life = life;
+		}
+
+		timeout = schedule_timeout(timeout);
 	}
 
 	remove_wait_queue(&call->waitq, &myself);
@@ -851,7 +874,8 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count,
 
 	ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall,
 				     buf, count, &call->offset,
-				     want_more, &call->abort_code);
+				     want_more, &call->abort_code,
+				     &call->service_id);
 	trace_afs_recv_data(call, count, call->offset, want_more, ret);
 	if (ret == 0 || ret == -EAGAIN)
 		return ret;
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 2b038442c352..3ce61342fa31 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -135,6 +135,7 @@ enum virtchnl_ops {
 	VIRTCHNL_OP_SET_RSS_HENA = 26,
 	VIRTCHNL_OP_ENABLE_VLAN_STRIPPING = 27,
 	VIRTCHNL_OP_DISABLE_VLAN_STRIPPING = 28,
+	VIRTCHNL_OP_REQUEST_QUEUES = 29,
 };
 
 /* This macro is used to generate a compilation error if a structure
@@ -235,6 +236,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource);
 #define VIRTCHNL_VF_OFFLOAD_RSS_AQ		0x00000008
 #define VIRTCHNL_VF_OFFLOAD_RSS_REG		0x00000010
 #define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR		0x00000020
+#define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES		0x00000040
 #define VIRTCHNL_VF_OFFLOAD_VLAN		0x00010000
 #define VIRTCHNL_VF_OFFLOAD_RX_POLLING		0x00020000
 #define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2	0x00040000
@@ -325,6 +327,21 @@ struct virtchnl_vsi_queue_config_info {
 	struct virtchnl_queue_pair_info qpair[1];
 };
 
+/* VIRTCHNL_OP_REQUEST_QUEUES
+ * VF sends this message to request the PF to allocate additional queues to
+ * this VF.  Each VF gets a guaranteed number of queues on init but asking for
+ * additional queues must be negotiated.  This is a best effort request as it
+ * is possible the PF does not have enough queues left to support the request.
+ * If the PF cannot support the number requested it will respond with the
+ * maximum number it is able to support.  If the request is successful, PF will
+ * then reset the VF to institute required changes.
+ */
+
+/* VF resource request */
+struct virtchnl_vf_res_request {
+	u16 num_queue_pairs;
+};
+
 VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info);
 
 /* VIRTCHNL_OP_CONFIG_IRQ_MAP
@@ -691,6 +708,9 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 	case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING:
 	case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING:
 		break;
+	case VIRTCHNL_OP_REQUEST_QUEUES:
+		valid_len = sizeof(struct virtchnl_vf_res_request);
+		break;
 	/* These are always errors coming from the VF. */
 	case VIRTCHNL_OP_EVENT:
 	case VIRTCHNL_OP_UNKNOWN:
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 44dfae288fcf..87a7db9feb38 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -15,27 +15,46 @@ struct bpf_sock_ops_kern;
 extern struct static_key_false cgroup_bpf_enabled_key;
 #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key)
 
+struct bpf_prog_list {
+	struct list_head node;
+	struct bpf_prog *prog;
+};
+
+struct bpf_prog_array;
+
 struct cgroup_bpf {
-	/*
-	 * Store two sets of bpf_prog pointers, one for programs that are
-	 * pinned directly to this cgroup, and one for those that are effective
-	 * when this cgroup is accessed.
+	/* array of effective progs in this cgroup */
+	struct bpf_prog_array __rcu *effective[MAX_BPF_ATTACH_TYPE];
+
+	/* attached progs to this cgroup and attach flags
+	 * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will
+	 * have either zero or one element
+	 * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS
 	 */
-	struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE];
-	struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE];
-	bool disallow_override[MAX_BPF_ATTACH_TYPE];
+	struct list_head progs[MAX_BPF_ATTACH_TYPE];
+	u32 flags[MAX_BPF_ATTACH_TYPE];
+
+	/* temp storage for effective prog array used by prog_attach/detach */
+	struct bpf_prog_array __rcu *inactive;
 };
 
 void cgroup_bpf_put(struct cgroup *cgrp);
-void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent);
-
-int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
-			struct bpf_prog *prog, enum bpf_attach_type type,
-			bool overridable);
-
-/* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */
-int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
-		      enum bpf_attach_type type, bool overridable);
+int cgroup_bpf_inherit(struct cgroup *cgrp);
+
+int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+			enum bpf_attach_type type, u32 flags);
+int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+			enum bpf_attach_type type, u32 flags);
+int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+		       union bpf_attr __user *uattr);
+
+/* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */
+int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, u32 flags);
+int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, u32 flags);
+int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+		     union bpf_attr __user *uattr);
 
 int __cgroup_bpf_run_filter_skb(struct sock *sk,
 				struct sk_buff *skb,
@@ -97,8 +116,7 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 
 struct cgroup_bpf {};
 static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
-static inline void cgroup_bpf_inherit(struct cgroup *cgrp,
-				      struct cgroup *parent) {}
+static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
 
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f1af7d63d678..520aeebe0d93 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -56,6 +56,10 @@ struct bpf_map {
 	struct work_struct work;
 	atomic_t usercnt;
 	struct bpf_map *inner_map_meta;
+	char name[BPF_OBJ_NAME_LEN];
+#ifdef CONFIG_SECURITY
+	void *security;
+#endif
 };
 
 /* function argument constraints */
@@ -137,6 +141,7 @@ enum bpf_reg_type {
 	PTR_TO_MAP_VALUE,	 /* reg points to map element value */
 	PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
 	PTR_TO_STACK,		 /* reg == frame_pointer + offset */
+	PTR_TO_PACKET_META,	 /* skb->data - meta_len */
 	PTR_TO_PACKET,		 /* reg points to skb->data */
 	PTR_TO_PACKET_END,	 /* skb->data + headlen */
 };
@@ -155,6 +160,11 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
 	aux->ctx_field_size = size;
 }
 
+struct bpf_prog_ops {
+	int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
+			union bpf_attr __user *uattr);
+};
+
 struct bpf_verifier_ops {
 	/* return eBPF function prototype for verification */
 	const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
@@ -170,8 +180,6 @@ struct bpf_verifier_ops {
 				  const struct bpf_insn *src,
 				  struct bpf_insn *dst,
 				  struct bpf_prog *prog, u32 *target_size);
-	int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
-			union bpf_attr __user *uattr);
 };
 
 struct bpf_prog_aux {
@@ -182,10 +190,15 @@ struct bpf_prog_aux {
 	u32 id;
 	struct latch_tree_node ksym_tnode;
 	struct list_head ksym_lnode;
-	const struct bpf_verifier_ops *ops;
+	const struct bpf_prog_ops *ops;
 	struct bpf_map **used_maps;
 	struct bpf_prog *prog;
 	struct user_struct *user;
+	u64 load_time; /* ns since boottime */
+	char name[BPF_OBJ_NAME_LEN];
+#ifdef CONFIG_SECURITY
+	void *security;
+#endif
 	union {
 		struct work_struct work;
 		struct rcu_head	rcu;
@@ -218,9 +231,6 @@ struct bpf_event_entry {
 	struct rcu_head rcu;
 };
 
-u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5);
-u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
-
 bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
 int bpf_prog_calc_tag(struct bpf_prog *fp);
 
@@ -237,17 +247,79 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr);
 
+/* an array of programs to be executed under rcu_lock.
+ *
+ * Typical usage:
+ * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN);
+ *
+ * the structure returned by bpf_prog_array_alloc() should be populated
+ * with program pointers and the last pointer must be NULL.
+ * The user has to keep refcnt on the program and make sure the program
+ * is removed from the array before bpf_prog_put().
+ * The 'struct bpf_prog_array *' should only be replaced with xchg()
+ * since other cpus are walking the array of pointers in parallel.
+ */
+struct bpf_prog_array {
+	struct rcu_head rcu;
+	struct bpf_prog *progs[0];
+};
+
+struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
+void bpf_prog_array_free(struct bpf_prog_array __rcu *progs);
+int bpf_prog_array_length(struct bpf_prog_array __rcu *progs);
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+				__u32 __user *prog_ids, u32 cnt);
+
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+				struct bpf_prog *old_prog);
+int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
+			struct bpf_prog *exclude_prog,
+			struct bpf_prog *include_prog,
+			struct bpf_prog_array **new_array);
+
+#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null)	\
+	({						\
+		struct bpf_prog **_prog, *__prog;	\
+		struct bpf_prog_array *_array;		\
+		u32 _ret = 1;				\
+		rcu_read_lock();			\
+		_array = rcu_dereference(array);	\
+		if (unlikely(check_non_null && !_array))\
+			goto _out;			\
+		_prog = _array->progs;			\
+		while ((__prog = READ_ONCE(*_prog))) {	\
+			_ret &= func(__prog, ctx);	\
+			_prog++;			\
+		}					\
+_out:							\
+		rcu_read_unlock();			\
+		_ret;					\
+	 })
+
+#define BPF_PROG_RUN_ARRAY(array, ctx, func)		\
+	__BPF_PROG_RUN_ARRAY(array, ctx, func, false)
+
+#define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func)	\
+	__BPF_PROG_RUN_ARRAY(array, ctx, func, true)
+
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
 
-#define BPF_PROG_TYPE(_id, _ops) \
-	extern const struct bpf_verifier_ops _ops;
+extern const struct file_operations bpf_map_fops;
+extern const struct file_operations bpf_prog_fops;
+
+#define BPF_PROG_TYPE(_id, _name) \
+	extern const struct bpf_prog_ops _name ## _prog_ops; \
+	extern const struct bpf_verifier_ops _name ## _verifier_ops;
 #define BPF_MAP_TYPE(_id, _ops) \
 	extern const struct bpf_map_ops _ops;
 #include <linux/bpf_types.h>
 #undef BPF_PROG_TYPE
 #undef BPF_MAP_TYPE
 
+extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops;
+extern const struct bpf_verifier_ops xdp_analyzer_ops;
+
 struct bpf_prog *bpf_prog_get(u32 ufd);
 struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type);
 struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i);
@@ -269,11 +341,11 @@ void bpf_map_area_free(void *base);
 
 extern int sysctl_unprivileged_bpf_disabled;
 
-int bpf_map_new_fd(struct bpf_map *map);
+int bpf_map_new_fd(struct bpf_map *map, int flags);
 int bpf_prog_new_fd(struct bpf_prog *prog);
 
 int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
-int bpf_obj_get_user(const char __user *pathname);
+int bpf_obj_get_user(const char __user *pathname, int flags);
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
@@ -292,6 +364,8 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
 				void *key, void *value, u64 map_flags);
 int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
 
+int bpf_get_file_flag(int flags);
+
 /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
  * forced to use 'long' read/writes to try to atomically copy long counters.
  * Best-effort only.  No barriers here, since it _will_ race with concurrent
@@ -316,6 +390,13 @@ struct net_device  *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
 void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
 void __dev_map_flush(struct bpf_map *map);
 
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
+void __cpu_map_insert_ctx(struct bpf_map *map, u32 index);
+void __cpu_map_flush(struct bpf_map *map);
+struct xdp_buff;
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+		    struct net_device *dev_rx);
+
 /* Return map's numa specified by userspace */
 static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
 {
@@ -323,7 +404,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
 		attr->numa_node : NUMA_NO_NODE;
 }
 
-#else
+#else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
 	return ERR_PTR(-EOPNOTSUPP);
@@ -368,7 +449,7 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
 {
 }
 
-static inline int bpf_obj_get_user(const char __user *pathname)
+static inline int bpf_obj_get_user(const char __user *pathname, int flags)
 {
 	return -EOPNOTSUPP;
 }
@@ -386,6 +467,28 @@ static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index)
 static inline void __dev_map_flush(struct bpf_map *map)
 {
 }
+
+static inline
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+	return NULL;
+}
+
+static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index)
+{
+}
+
+static inline void __cpu_map_flush(struct bpf_map *map)
+{
+}
+
+struct xdp_buff;
+static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
+				  struct xdp_buff *xdp,
+				  struct net_device *dev_rx)
+{
+	return 0;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL)
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index e1149327a0c0..53c5b9ad7220 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -2,22 +2,22 @@
 /* internal file - do not include directly */
 
 #ifdef CONFIG_NET
-BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act)
+BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb)
 #endif
 #ifdef CONFIG_BPF_EVENTS
-BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe)
+BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
+BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
 #endif
 
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
@@ -42,4 +42,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
 #ifdef CONFIG_STREAM_PARSER
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
 #endif
+BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
 #endif
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index b8d200f60a40..3b0976aaac75 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -88,14 +88,19 @@ enum bpf_stack_slot_type {
 
 #define BPF_REG_SIZE 8	/* size of eBPF register in bytes */
 
+struct bpf_stack_state {
+	struct bpf_reg_state spilled_ptr;
+	u8 slot_type[BPF_REG_SIZE];
+};
+
 /* state of the program:
  * type of all registers and stack info
  */
 struct bpf_verifier_state {
 	struct bpf_reg_state regs[MAX_BPF_REG];
-	u8 stack_slot_type[MAX_BPF_STACK];
-	struct bpf_reg_state spilled_regs[MAX_BPF_STACK / BPF_REG_SIZE];
 	struct bpf_verifier_state *parent;
+	int allocated_stack;
+	struct bpf_stack_state *stack;
 };
 
 /* linked list of verifier states used to prune search */
@@ -115,6 +120,21 @@ struct bpf_insn_aux_data {
 
 #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
 
+#define BPF_VERIFIER_TMP_LOG_SIZE	1024
+
+struct bpf_verifer_log {
+	u32 level;
+	char kbuf[BPF_VERIFIER_TMP_LOG_SIZE];
+	char __user *ubuf;
+	u32 len_used;
+	u32 len_total;
+};
+
+static inline bool bpf_verifier_log_full(const struct bpf_verifer_log *log)
+{
+	return log->len_used >= log->len_total - 1;
+}
+
 struct bpf_verifier_env;
 struct bpf_ext_analyzer_ops {
 	int (*insn_hook)(struct bpf_verifier_env *env,
@@ -126,10 +146,11 @@ struct bpf_ext_analyzer_ops {
  */
 struct bpf_verifier_env {
 	struct bpf_prog *prog;		/* eBPF program being verified */
+	const struct bpf_verifier_ops *ops;
 	struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */
 	int stack_size;			/* number of states to be processed */
 	bool strict_alignment;		/* perform strict pointer alignment checks */
-	struct bpf_verifier_state cur_state; /* current verifier state */
+	struct bpf_verifier_state *cur_state; /* current verifier state */
 	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
 	const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */
 	void *analyzer_priv; /* pointer to external analyzer's private data */
@@ -139,8 +160,15 @@ struct bpf_verifier_env {
 	bool allow_ptr_leaks;
 	bool seen_direct_write;
 	struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
+
+	struct bpf_verifer_log log;
 };
 
+static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env)
+{
+	return env->cur_state->regs;
+}
+
 int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
 		 void *priv);
 
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 4f087f86a741..8ff86b4c1b8a 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -64,6 +64,7 @@
 #define PHY_BRCM_EXT_IBND_TX_ENABLE	0x00002000
 #define PHY_BRCM_CLEAR_RGMII_MODE	0x00004000
 #define PHY_BRCM_DIS_TXCRXC_NOENRGY	0x00008000
+#define PHY_BRCM_EN_MASTER_MODE		0x00010000
 
 /* Broadcom BCM7xxx specific workarounds */
 #define PHY_BRCM_7XXX_REV(x)		(((x) >> 8) & 0xff)
diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h
index 133b76d0d2c0..451aaa0786ae 100644
--- a/include/linux/byteorder/generic.h
+++ b/include/linux/byteorder/generic.h
@@ -171,4 +171,20 @@ static inline void be64_add_cpu(__be64 *var, u64 val)
 	*var = cpu_to_be64(be64_to_cpu(*var) + val);
 }
 
+static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		dst[i] = cpu_to_be32(src[i]);
+}
+
+static inline void be32_to_cpu_array(u32 *dst, const __be32 *src, size_t len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		dst[i] = be32_to_cpu(src[i]);
+}
+
 #endif /* _LINUX_BYTEORDER_GENERIC_H */
diff --git a/include/linux/connector.h b/include/linux/connector.h
index f8fe8637d771..032102b19645 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -22,7 +22,7 @@
 #define __CONNECTOR_H
 
 
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 
 #include <linux/list.h>
 #include <linux/workqueue.h>
@@ -49,7 +49,7 @@ struct cn_callback_id {
 
 struct cn_callback_entry {
 	struct list_head callback_entry;
-	atomic_t refcnt;
+	refcount_t refcnt;
 	struct cn_queue_dev *pdev;
 
 	struct cn_callback_id id;
diff --git a/include/linux/dsa/lan9303.h b/include/linux/dsa/lan9303.h
new file mode 100644
index 000000000000..05d8d136baab
--- /dev/null
+++ b/include/linux/dsa/lan9303.h
@@ -0,0 +1,36 @@
+/* Included by drivers/net/dsa/lan9303.h and net/dsa/tag_lan9303.c */
+#include <linux/if_ether.h>
+
+struct lan9303;
+
+struct lan9303_phy_ops {
+	/* PHY 1 and 2 access*/
+	int	(*phy_read)(struct lan9303 *chip, int port, int regnum);
+	int	(*phy_write)(struct lan9303 *chip, int port,
+			     int regnum, u16 val);
+};
+
+#define LAN9303_NUM_ALR_RECORDS 512
+struct lan9303_alr_cache_entry {
+	u8  mac_addr[ETH_ALEN];
+	u8  port_map;           /* Bitmap of ports. Zero if unused entry */
+	u8  stp_override;       /* non zero if set ALR_DAT1_AGE_OVERRID */
+};
+
+struct lan9303 {
+	struct device *dev;
+	struct regmap *regmap;
+	struct regmap_irq_chip_data *irq_data;
+	struct gpio_desc *reset_gpio;
+	u32 reset_duration; /* in [ms] */
+	bool phy_addr_sel_strap;
+	struct dsa_switch *ds;
+	struct mutex indirect_mutex; /* protect indexed register access */
+	const struct lan9303_phy_ops *ops;
+	bool is_bridged; /* true if port 1 and 2 are bridged */
+	u32 swe_port_state; /* remember SWE_PORT_STATE while not bridged */
+	/* LAN9303 do not offer reading specific ALR entry. Cache all
+	 * static entries in a flat table
+	 **/
+	struct lan9303_alr_cache_entry alr_cache[LAN9303_NUM_ALR_RECORDS];
+};
diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h
index 34c0a5464c74..be1214731505 100644
--- a/include/linux/dynamic_queue_limits.h
+++ b/include/linux/dynamic_queue_limits.h
@@ -99,7 +99,7 @@ void dql_completed(struct dql *dql, unsigned int count);
 void dql_reset(struct dql *dql);
 
 /* Initialize dql state */
-int dql_init(struct dql *dql, unsigned hold_time);
+void dql_init(struct dql *dql, unsigned int hold_time);
 
 #endif /* _KERNEL_ */
 
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 2d9f80848d4b..263dbcad22fc 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -66,6 +66,7 @@ int eth_gro_complete(struct sk_buff *skb, int nhoff);
 /* Reserved Ethernet Addresses per IEEE 802.1Q */
 static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) =
 { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
+#define eth_stp_addr eth_reserved_addr_base
 
 /**
  * is_link_local_ether_addr - Determine if given Ethernet address is link-local
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 0c0146e7e274..2ec41a7eb54f 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -164,6 +164,16 @@ extern int
 __ethtool_get_link_ksettings(struct net_device *dev,
 			     struct ethtool_link_ksettings *link_ksettings);
 
+/**
+ * ethtool_intersect_link_masks - Given two link masks, AND them together
+ * @dst: first mask and where result is stored
+ * @src: second mask to intersect with
+ *
+ * Given two link mode masks, AND them together and save the result in dst.
+ */
+void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst,
+				  struct ethtool_link_ksettings *src);
+
 void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst,
 					     u32 legacy_u32);
 
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 48ec57e70f9f..0cd02ff4ae30 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -482,30 +482,36 @@ struct sk_filter {
 	struct bpf_prog	*prog;
 };
 
-#define BPF_PROG_RUN(filter, ctx)  (*filter->bpf_func)(ctx, filter->insnsi)
+#define BPF_PROG_RUN(filter, ctx)  (*(filter)->bpf_func)(ctx, (filter)->insnsi)
 
 #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN
 
 struct bpf_skb_data_end {
 	struct qdisc_skb_cb qdisc_cb;
+	void *data_meta;
 	void *data_end;
 };
 
 struct xdp_buff {
 	void *data;
 	void *data_end;
+	void *data_meta;
 	void *data_hard_start;
 };
 
-/* compute the linear packet data range [data, data_end) which
- * will be accessed by cls_bpf, act_bpf and lwt programs
+/* Compute the linear packet data range [data, data_end) which
+ * will be accessed by various program types (cls_bpf, act_bpf,
+ * lwt, ...). Subsystems allowing direct data access must (!)
+ * ensure that cb[] area can be written to when BPF program is
+ * invoked (otherwise cb[] save/restore is necessary).
  */
-static inline void bpf_compute_data_end(struct sk_buff *skb)
+static inline void bpf_compute_data_pointers(struct sk_buff *skb)
 {
 	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
 
 	BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb));
-	cb->data_end = skb->data + skb_headlen(skb);
+	cb->data_meta = skb->data - skb_metadata_len(skb);
+	cb->data_end  = skb->data + skb_headlen(skb);
 }
 
 static inline u8 *bpf_skb_cb(struct sk_buff *skb)
@@ -726,8 +732,22 @@ int xdp_do_redirect(struct net_device *dev,
 		    struct bpf_prog *prog);
 void xdp_do_flush_map(void);
 
+/* Drivers not supporting XDP metadata can use this helper, which
+ * rejects any room expansion for metadata as a result.
+ */
+static __always_inline void
+xdp_set_data_meta_invalid(struct xdp_buff *xdp)
+{
+	xdp->data_meta = xdp->data + 1;
+}
+
+static __always_inline bool
+xdp_data_meta_unsupported(const struct xdp_buff *xdp)
+{
+	return unlikely(xdp->data_meta > xdp->data);
+}
+
 void bpf_warn_invalid_xdp_action(u32 act);
-void bpf_warn_invalid_xdp_redirect(u32 ifindex);
 
 struct sock *do_sk_redirect_map(struct sk_buff *skb);
 
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 55a604ad459f..ee6657a0ed69 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2445,6 +2445,7 @@ enum ieee80211_sa_query_action {
 #define WLAN_OUI_TYPE_MICROSOFT_WPA	1
 #define WLAN_OUI_TYPE_MICROSOFT_WMM	2
 #define WLAN_OUI_TYPE_MICROSOFT_WPS	4
+#define WLAN_OUI_TYPE_MICROSOFT_TPC	8
 
 /*
  * WMM/802.11e Tspec Element
diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h
index 3355efc89781..6756fea18b69 100644
--- a/include/linux/if_arp.h
+++ b/include/linux/if_arp.h
@@ -31,7 +31,7 @@ static inline struct arphdr *arp_hdr(const struct sk_buff *skb)
 	return (struct arphdr *)skb_network_header(skb);
 }
 
-static inline int arp_hdr_len(struct net_device *dev)
+static inline unsigned int arp_hdr_len(const struct net_device *dev)
 {
 	switch (dev->type) {
 #if IS_ENABLED(CONFIG_FIREWIRE_NET)
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 3cd18ac0697f..02639ebea2f0 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -49,6 +49,7 @@ struct br_ip_list {
 #define BR_MULTICAST_TO_UNICAST	BIT(12)
 #define BR_VLAN_TUNNEL		BIT(13)
 #define BR_BCAST_FLOOD		BIT(14)
+#define BR_NEIGH_SUPPRESS	BIT(15)
 
 #define BR_DEFAULT_AGEING_TIME	(300 * HZ)
 
@@ -63,6 +64,7 @@ int br_multicast_list_adjacent(struct net_device *dev,
 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_enabled(const struct net_device *dev);
+bool br_multicast_router(const struct net_device *dev);
 #else
 static inline int br_multicast_list_adjacent(struct net_device *dev,
 					     struct list_head *br_ip_list)
@@ -83,6 +85,10 @@ static inline bool br_multicast_enabled(const struct net_device *dev)
 {
 	return false;
 }
+static inline bool br_multicast_router(const struct net_device *dev)
+{
+	return false;
+}
 #endif
 
 #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING)
diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h
index 46df7e565d6f..82a1b4e93570 100644
--- a/include/linux/if_frad.h
+++ b/include/linux/if_frad.h
@@ -83,6 +83,7 @@ struct frad_local
 
    /* fields that are used by the Sangoma SDLA cards */
    struct timer_list timer;
+   struct net_device *dev;
    int               type;		/* adapter type */
    int               state;		/* state of the S502/8 control latch */
    int               buffer;		/* current buffer for S508 firmware */
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 0e2c60efad2d..bedf54b6f943 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -11,13 +11,6 @@
 #include <linux/u64_stats_sync.h>
 
 struct macvlan_port;
-struct macvtap_queue;
-
-/*
- * Maximum times a macvtap device can be opened. This can be used to
- * configure the number of receive queue, e.g. for multiqueue virtio.
- */
-#define MAX_TAP_QUEUES	256
 
 #define MACVLAN_MC_FILTER_BITS	8
 #define MACVLAN_MC_FILTER_SZ	(1 << MACVLAN_MC_FILTER_BITS)
@@ -36,14 +29,6 @@ struct macvlan_dev {
 	netdev_features_t	set_features;
 	enum macvlan_mode	mode;
 	u16			flags;
-	/* This array tracks active taps. */
-	struct tap_queue	__rcu *taps[MAX_TAP_QUEUES];
-	/* This list tracks all taps (both enabled and disabled) */
-	struct list_head	queue_list;
-	int			numvtaps;
-	int			numqueues;
-	netdev_features_t	tap_features;
-	int			minor;
 	int			nest_level;
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	struct netpoll		*netpoll;
@@ -73,7 +58,8 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
 extern void macvlan_common_setup(struct net_device *dev);
 
 extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
-				  struct nlattr *tb[], struct nlattr *data[]);
+				  struct nlattr *tb[], struct nlattr *data[],
+				  struct netlink_ext_ack *extack);
 
 extern void macvlan_count_rx(const struct macvlan_dev *vlan,
 			     unsigned int len, bool success,
diff --git a/include/linux/if_phonet.h b/include/linux/if_phonet.h
index 3b5c60da2e2a..2d8486168ec5 100644
--- a/include/linux/if_phonet.h
+++ b/include/linux/if_phonet.h
@@ -11,5 +11,5 @@
 
 #include <uapi/linux/if_phonet.h>
 
-extern struct header_ops phonet_header_ops;
+extern const struct header_ops phonet_header_ops;
 #endif
diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h
index 13edf19ce9fb..3ecef57c31e3 100644
--- a/include/linux/if_tap.h
+++ b/include/linux/if_tap.h
@@ -23,6 +23,10 @@ static inline struct skb_array *tap_get_skb_array(struct file *f)
 #include <net/sock.h>
 #include <linux/skb_array.h>
 
+/*
+ * Maximum times a tap device can be opened. This can be used to
+ * configure the number of receive queue, e.g. for multiqueue virtio.
+ */
 #define MAX_TAP_QUEUES 256
 
 struct tap_queue;
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index 5058f061cb2b..1ac5bf95bfdd 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -155,6 +155,7 @@ struct in_ifaddr {
 struct in_validator_info {
 	__be32			ivi_addr;
 	struct in_device	*ivi_dev;
+	struct netlink_ext_ack	*extack;
 };
 
 int register_inetaddr_notifier(struct notifier_block *nb);
@@ -180,6 +181,7 @@ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst,
 			 __be32 local, int scope);
 struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
 				    __be32 mask);
+struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr);
 static __inline__ bool inet_ifa_match(__be32 addr, struct in_ifaddr *ifa)
 {
 	return !((addr^ifa->ifa_address)&ifa->ifa_mask);
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index c9258124e417..7161d8e7ee79 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1351,6 +1351,40 @@
  *	@inode we wish to get the security context of.
  *	@ctx is a pointer in which to place the allocated security context.
  *	@ctxlen points to the place to put the length of @ctx.
+ *
+ * Security hooks for using the eBPF maps and programs functionalities through
+ * eBPF syscalls.
+ *
+ * @bpf:
+ *	Do a initial check for all bpf syscalls after the attribute is copied
+ *	into the kernel. The actual security module can implement their own
+ *	rules to check the specific cmd they need.
+ *
+ * @bpf_map:
+ *	Do a check when the kernel generate and return a file descriptor for
+ *	eBPF maps.
+ *
+ *	@map: bpf map that we want to access
+ *	@mask: the access flags
+ *
+ * @bpf_prog:
+ *	Do a check when the kernel generate and return a file descriptor for
+ *	eBPF programs.
+ *
+ *	@prog: bpf prog that userspace want to use.
+ *
+ * @bpf_map_alloc_security:
+ *	Initialize the security field inside bpf map.
+ *
+ * @bpf_map_free_security:
+ *	Clean up the security information stored inside bpf map.
+ *
+ * @bpf_prog_alloc_security:
+ *	Initialize the security field inside bpf program.
+ *
+ * @bpf_prog_free_security:
+ *	Clean up the security information stored inside bpf prog.
+ *
  */
 union security_list_options {
 	int (*binder_set_context_mgr)(struct task_struct *mgr);
@@ -1682,6 +1716,17 @@ union security_list_options {
 				struct audit_context *actx);
 	void (*audit_rule_free)(void *lsmrule);
 #endif /* CONFIG_AUDIT */
+
+#ifdef CONFIG_BPF_SYSCALL
+	int (*bpf)(int cmd, union bpf_attr *attr,
+				 unsigned int size);
+	int (*bpf_map)(struct bpf_map *map, fmode_t fmode);
+	int (*bpf_prog)(struct bpf_prog *prog);
+	int (*bpf_map_alloc_security)(struct bpf_map *map);
+	void (*bpf_map_free_security)(struct bpf_map *map);
+	int (*bpf_prog_alloc_security)(struct bpf_prog_aux *aux);
+	void (*bpf_prog_free_security)(struct bpf_prog_aux *aux);
+#endif /* CONFIG_BPF_SYSCALL */
 };
 
 struct security_hook_heads {
@@ -1901,6 +1946,15 @@ struct security_hook_heads {
 	struct list_head audit_rule_match;
 	struct list_head audit_rule_free;
 #endif /* CONFIG_AUDIT */
+#ifdef CONFIG_BPF_SYSCALL
+	struct list_head bpf;
+	struct list_head bpf_map;
+	struct list_head bpf_prog;
+	struct list_head bpf_map_alloc_security;
+	struct list_head bpf_map_free_security;
+	struct list_head bpf_prog_alloc_security;
+	struct list_head bpf_prog_free_security;
+#endif /* CONFIG_BPF_SYSCALL */
 } __randomize_layout;
 
 /*
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index b0a57e043fa3..a9b5fed8f7c6 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -40,7 +40,7 @@
 #include <linux/cpu_rmap.h>
 #include <linux/crash_dump.h>
 
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 
 #include <linux/timecounter.h>
 
@@ -751,7 +751,7 @@ struct mlx4_cq {
 	int			cqn;
 	unsigned		vector;
 
-	atomic_t		refcount;
+	refcount_t		refcount;
 	struct completion	free;
 	struct {
 		struct list_head list;
@@ -768,7 +768,7 @@ struct mlx4_qp {
 
 	int			qpn;
 
-	atomic_t		refcount;
+	refcount_t		refcount;
 	struct completion	free;
 	u8			usage;
 };
@@ -781,7 +781,7 @@ struct mlx4_srq {
 	int			max_gs;
 	int			wqe_shift;
 
-	atomic_t		refcount;
+	refcount_t		refcount;
 	struct completion	free;
 };
 
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 95898847c7d4..6a57ec2f1ef7 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -35,7 +35,7 @@
 
 #include <rdma/ib_verbs.h>
 #include <linux/mlx5/driver.h>
-
+#include <linux/refcount.h>
 
 struct mlx5_core_cq {
 	u32			cqn;
@@ -43,7 +43,7 @@ struct mlx5_core_cq {
 	__be32		       *set_ci_db;
 	__be32		       *arm_db;
 	struct mlx5_uars_page  *uar;
-	atomic_t		refcount;
+	refcount_t		refcount;
 	struct completion	free;
 	unsigned		vector;
 	unsigned int		irqn;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 401c8972cc3a..08c77b7e59cb 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -49,6 +49,8 @@
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/doorbell.h>
 #include <linux/mlx5/srq.h>
+#include <linux/timecounter.h>
+#include <linux/ptp_clock_kernel.h>
 
 enum {
 	MLX5_BOARD_ID_LEN = 64,
@@ -760,6 +762,27 @@ struct mlx5_rsvd_gids {
 	struct ida ida;
 };
 
+#define MAX_PIN_NUM	8
+struct mlx5_pps {
+	u8                         pin_caps[MAX_PIN_NUM];
+	struct work_struct         out_work;
+	u64                        start[MAX_PIN_NUM];
+	u8                         enabled;
+};
+
+struct mlx5_clock {
+	rwlock_t                   lock;
+	struct cyclecounter        cycles;
+	struct timecounter         tc;
+	struct hwtstamp_config     hwtstamp_config;
+	u32                        nominal_c_mult;
+	unsigned long              overflow_period;
+	struct delayed_work        overflow_work;
+	struct ptp_clock          *ptp;
+	struct ptp_clock_info      ptp_info;
+	struct mlx5_pps            pps_info;
+};
+
 struct mlx5_core_dev {
 	struct pci_dev	       *pdev;
 	/* sync pci state */
@@ -800,6 +823,7 @@ struct mlx5_core_dev {
 #ifdef CONFIG_RFS_ACCEL
 	struct cpu_rmap         *rmap;
 #endif
+	struct mlx5_clock        clock;
 };
 
 struct mlx5_db {
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 1c2e8d6b7274..abb6dc2ebbf8 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -687,5 +687,31 @@ struct fsl_mc_device_id {
 	const char obj_type[16];
 };
 
+/**
+ * struct tb_service_id - Thunderbolt service identifiers
+ * @match_flags: Flags used to match the structure
+ * @protocol_key: Protocol key the service supports
+ * @protocol_id: Protocol id the service supports
+ * @protocol_version: Version of the protocol
+ * @protocol_revision: Revision of the protocol software
+ * @driver_data: Driver specific data
+ *
+ * Thunderbolt XDomain services are exposed as devices where each device
+ * carries the protocol information the service supports. Thunderbolt
+ * XDomain service drivers match against that information.
+ */
+struct tb_service_id {
+	__u32 match_flags;
+	char protocol_key[8 + 1];
+	__u32 protocol_id;
+	__u32 protocol_version;
+	__u32 protocol_revision;
+	kernel_ulong_t driver_data;
+};
+
+#define TBSVC_MATCH_PROTOCOL_KEY	0x0001
+#define TBSVC_MATCH_PROTOCOL_ID		0x0002
+#define TBSVC_MATCH_PROTOCOL_VERSION	0x0004
+#define TBSVC_MATCH_PROTOCOL_REVISION	0x0008
 
 #endif /* LINUX_MOD_DEVICETABLE_H */
diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index 65a70a7c51c1..5396521a776a 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -6,6 +6,8 @@
 #include <linux/pim.h>
 #include <linux/rhashtable.h>
 #include <net/sock.h>
+#include <net/fib_rules.h>
+#include <net/fib_notifier.h>
 #include <uapi/linux/mroute.h>
 
 #ifdef CONFIG_IP_MROUTE
@@ -19,6 +21,7 @@ int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
 int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg);
 int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
 int ip_mr_init(void);
+bool ipmr_rule_default(const struct fib_rule *rule);
 #else
 static inline int ip_mroute_setsockopt(struct sock *sock, int optname,
 				       char __user *optval, unsigned int optlen)
@@ -46,10 +49,16 @@ static inline int ip_mroute_opt(int opt)
 {
 	return 0;
 }
+
+static inline bool ipmr_rule_default(const struct fib_rule *rule)
+{
+	return true;
+}
 #endif
 
 struct vif_device {
 	struct net_device 	*dev;			/* Device we are using */
+	struct netdev_phys_item_id dev_parent_id;	/* Device parent ID    */
 	unsigned long	bytes_in,bytes_out;
 	unsigned long	pkt_in,pkt_out;		/* Statistics 			*/
 	unsigned long	rate_limit;		/* Traffic shaping (NI) 	*/
@@ -59,6 +68,14 @@ struct vif_device {
 	int		link;			/* Physical interface index	*/
 };
 
+struct vif_entry_notifier_info {
+	struct fib_notifier_info info;
+	struct net_device *dev;
+	vifi_t vif_index;
+	unsigned short vif_flags;
+	u32 tb_id;
+};
+
 #define VIFF_STATIC 0x8000
 
 #define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL)
@@ -82,9 +99,11 @@ struct mr_table {
 
 /* mfc_flags:
  * MFC_STATIC - the entry was added statically (not by a routing daemon)
+ * MFC_OFFLOAD - the entry was offloaded to the hardware
  */
 enum {
 	MFC_STATIC = BIT(0),
+	MFC_OFFLOAD = BIT(1),
 };
 
 struct mfc_cache_cmp_arg {
@@ -110,6 +129,7 @@ struct mfc_cache_cmp_arg {
  * @wrong_if: number of wrong source interface hits
  * @lastuse: time of last use of the group (traffic or update)
  * @ttls: OIF TTL threshold array
+ * @refcount: reference count for this entry
  * @list: global entry list
  * @rcu: used for entry destruction
  */
@@ -139,14 +159,40 @@ struct mfc_cache {
 			unsigned long wrong_if;
 			unsigned long lastuse;
 			unsigned char ttls[MAXVIFS];
+			refcount_t refcount;
 		} res;
 	} mfc_un;
 	struct list_head list;
 	struct rcu_head	rcu;
 };
 
+struct mfc_entry_notifier_info {
+	struct fib_notifier_info info;
+	struct mfc_cache *mfc;
+	u32 tb_id;
+};
+
 struct rtmsg;
 int ipmr_get_route(struct net *net, struct sk_buff *skb,
 		   __be32 saddr, __be32 daddr,
 		   struct rtmsg *rtm, u32 portid);
+
+#ifdef CONFIG_IP_MROUTE
+void ipmr_cache_free(struct mfc_cache *mfc_cache);
+#else
+static inline void ipmr_cache_free(struct mfc_cache *mfc_cache)
+{
+}
+#endif
+
+static inline void ipmr_cache_put(struct mfc_cache *c)
+{
+	if (refcount_dec_and_test(&c->mfc_un.res.refcount))
+		ipmr_cache_free(c);
+}
+static inline void ipmr_cache_hold(struct mfc_cache *c)
+{
+	refcount_inc(&c->mfc_un.res.refcount);
+}
+
 #endif
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2eaac7d75af4..7de7656550c2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -55,7 +55,7 @@
 struct netpoll_info;
 struct device;
 struct phy_device;
-struct dsa_switch_tree;
+struct dsa_port;
 
 /* 802.11 specific */
 struct wireless_dev;
@@ -775,6 +775,8 @@ enum tc_setup_type {
 	TC_SETUP_CLSFLOWER,
 	TC_SETUP_CLSMATCHALL,
 	TC_SETUP_CLSBPF,
+	TC_SETUP_BLOCK,
+	TC_SETUP_CBS,
 };
 
 /* These structures hold the attributes of xdp state that are being passed
@@ -826,6 +828,11 @@ struct xfrmdev_ops {
 };
 #endif
 
+struct dev_ifalias {
+	struct rcu_head rcuhead;
+	char ifalias[];
+};
+
 /*
  * This structure defines the management hooks for network devices.
  * The following hooks can be defined; unless noted otherwise, they are
@@ -1241,7 +1248,8 @@ struct net_device_ops {
 						     u32 flow_id);
 #endif
 	int			(*ndo_add_slave)(struct net_device *dev,
-						 struct net_device *slave_dev);
+						 struct net_device *slave_dev,
+						 struct netlink_ext_ack *extack);
 	int			(*ndo_del_slave)(struct net_device *dev,
 						 struct net_device *slave_dev);
 	netdev_features_t	(*ndo_fix_features)(struct net_device *dev,
@@ -1551,6 +1559,8 @@ enum netdev_priv_flags {
  *
  *	@rx_handler:		handler for received packets
  *	@rx_handler_data: 	XXX: need comments on this one
+ *	@miniq_ingress:		ingress/clsact qdisc specific data for
+ *				ingress processing
  *	@ingress_queue:		XXX: need comments on this one
  *	@broadcast:		hw bcast address
  *
@@ -1568,7 +1578,8 @@ enum netdev_priv_flags {
  *	@tx_global_lock: 	XXX: need comments on this one
  *
  *	@xps_maps:	XXX: need comments on this one
- *
+ *	@miniq_egress:		clsact qdisc specific data for
+ *				egress processing
  *	@watchdog_timeo:	Represents the timeout that is used by
  *				the watchdog (see dev_watchdog())
  *	@watchdog_timer:	List of timers
@@ -1632,7 +1643,7 @@ enum netdev_priv_flags {
 struct net_device {
 	char			name[IFNAMSIZ];
 	struct hlist_node	name_hlist;
-	char 			*ifalias;
+	struct dev_ifalias	__rcu *ifalias;
 	/*
 	 *	I/O specific fields
 	 *	FIXME: Merge these and struct ifmap into one
@@ -1752,7 +1763,7 @@ struct net_device {
 	struct vlan_info __rcu	*vlan_info;
 #endif
 #if IS_ENABLED(CONFIG_NET_DSA)
-	struct dsa_switch_tree	*dsa_ptr;
+	struct dsa_port		*dsa_ptr;
 #endif
 #if IS_ENABLED(CONFIG_TIPC)
 	struct tipc_bearer __rcu *tipc_ptr;
@@ -1787,7 +1798,7 @@ struct net_device {
 	void __rcu		*rx_handler_data;
 
 #ifdef CONFIG_NET_CLS_ACT
-	struct tcf_proto __rcu  *ingress_cl_list;
+	struct mini_Qdisc __rcu	*miniq_ingress;
 #endif
 	struct netdev_queue __rcu *ingress_queue;
 #ifdef CONFIG_NETFILTER_INGRESS
@@ -1818,7 +1829,7 @@ struct net_device {
 	struct xps_dev_maps __rcu *xps_maps;
 #endif
 #ifdef CONFIG_NET_CLS_ACT
-	struct tcf_proto __rcu  *egress_cl_list;
+	struct mini_Qdisc __rcu	*miniq_egress;
 #endif
 
 	/* These may be needed for future network-power-down code. */
@@ -2304,7 +2315,8 @@ int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
 
 struct netdev_notifier_info {
-	struct net_device *dev;
+	struct net_device	*dev;
+	struct netlink_ext_ack	*extack;
 };
 
 struct netdev_notifier_change_info {
@@ -2329,6 +2341,7 @@ static inline void netdev_notifier_info_init(struct netdev_notifier_info *info,
 					     struct net_device *dev)
 {
 	info->dev = dev;
+	info->extack = NULL;
 }
 
 static inline struct net_device *
@@ -2337,6 +2350,12 @@ netdev_notifier_info_to_dev(const struct netdev_notifier_info *info)
 	return info->dev;
 }
 
+static inline struct netlink_ext_ack *
+netdev_notifier_info_to_extack(const struct netdev_notifier_info *info)
+{
+	return info->extack;
+}
+
 int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
 
 
@@ -3246,6 +3265,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
 int netif_rx(struct sk_buff *skb);
 int netif_rx_ni(struct sk_buff *skb);
 int netif_receive_skb(struct sk_buff *skb);
+int netif_receive_skb_core(struct sk_buff *skb);
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
 void napi_gro_flush(struct napi_struct *napi, bool flush_old);
 struct sk_buff *napi_get_frags(struct napi_struct *napi);
@@ -3275,6 +3295,7 @@ void __dev_notify_flags(struct net_device *, unsigned int old_flags,
 			unsigned int gchanges);
 int dev_change_name(struct net_device *, const char *);
 int dev_set_alias(struct net_device *, const char *, size_t);
+int dev_get_alias(const struct net_device *, char *, size_t);
 int dev_change_net_namespace(struct net_device *, struct net *, const char *);
 int __dev_set_mtu(struct net_device *, int);
 int dev_set_mtu(struct net_device *, int);
@@ -3907,10 +3928,12 @@ void *netdev_adjacent_get_private(struct list_head *adj_list);
 void *netdev_lower_get_first_private_rcu(struct net_device *dev);
 struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
 struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
-int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev);
+int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev,
+			  struct netlink_ext_ack *extack);
 int netdev_master_upper_dev_link(struct net_device *dev,
 				 struct net_device *upper_dev,
-				 void *upper_priv, void *upper_info);
+				 void *upper_priv, void *upper_info,
+				 struct netlink_ext_ack *extack);
 void netdev_upper_dev_unlink(struct net_device *dev,
 			     struct net_device *upper_dev);
 void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
diff --git a/include/linux/once.h b/include/linux/once.h
index 6790884d3c57..9225ee6d96c7 100644
--- a/include/linux/once.h
+++ b/include/linux/once.h
@@ -6,7 +6,7 @@
 #include <linux/jump_label.h>
 
 bool __do_once_start(bool *done, unsigned long *flags);
-void __do_once_done(bool *done, struct static_key *once_key,
+void __do_once_done(bool *done, struct static_key_true *once_key,
 		    unsigned long *flags);
 
 /* Call a function exactly once. The idea of DO_ONCE() is to perform
@@ -39,8 +39,8 @@ void __do_once_done(bool *done, struct static_key *once_key,
 	({								     \
 		bool ___ret = false;					     \
 		static bool ___done = false;				     \
-		static struct static_key ___once_key = STATIC_KEY_INIT_TRUE; \
-		if (static_key_true(&___once_key)) {			     \
+		static DEFINE_STATIC_KEY_TRUE(___once_key);		     \
+		if (static_branch_unlikely(&___once_key)) {		     \
 			unsigned long ___flags;				     \
 			___ret = __do_once_start(&___done, &___flags);	     \
 			if (unlikely(___ret)) {				     \
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8e22f24ded6a..79b18a20cf5d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -806,6 +806,7 @@ struct perf_output_handle {
 struct bpf_perf_event_data_kern {
 	struct pt_regs *regs;
 	struct perf_sample_data *data;
+	struct perf_event *event;
 };
 
 #ifdef CONFIG_CGROUP_PERF
@@ -884,7 +885,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr,
 				void *context);
 extern void perf_pmu_migrate_context(struct pmu *pmu,
 				int src_cpu, int dst_cpu);
-int perf_event_read_local(struct perf_event *event, u64 *value);
+int perf_event_read_local(struct perf_event *event, u64 *value,
+			  u64 *enabled, u64 *running);
 extern u64 perf_event_read_value(struct perf_event *event,
 				 u64 *enabled, u64 *running);
 
@@ -1286,7 +1288,8 @@ static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *
 {
 	return ERR_PTR(-EINVAL);
 }
-static inline int perf_event_read_local(struct perf_event *event, u64 *value)
+static inline int perf_event_read_local(struct perf_event *event, u64 *value,
+					u64 *enabled, u64 *running)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h
index dd7a3b86bb9e..e755954d85fd 100644
--- a/include/linux/qed/qed_ll2_if.h
+++ b/include/linux/qed/qed_ll2_if.h
@@ -64,6 +64,7 @@ enum qed_ll2_roce_flavor_type {
 enum qed_ll2_tx_dest {
 	QED_LL2_TX_DEST_NW, /* Light L2 TX Destination to the Network */
 	QED_LL2_TX_DEST_LB, /* Light L2 TX Destination to the Loopback */
+	QED_LL2_TX_DEST_DROP, /* Light L2 Drop the TX packet */
 	QED_LL2_TX_DEST_MAX
 };
 
@@ -101,6 +102,7 @@ struct qed_ll2_comp_rx_data {
 	void *cookie;
 	dma_addr_t rx_buf_addr;
 	u16 parse_flags;
+	u16 err_flags;
 	u16 vlan;
 	bool b_last_packet;
 	u8 connection_handle;
@@ -149,11 +151,16 @@ void (*qed_ll2_release_tx_packet_cb)(void *cxt,
 				     dma_addr_t first_frag_addr,
 				     bool b_last_fragment, bool b_last_packet);
 
+typedef
+void (*qed_ll2_slowpath_cb)(void *cxt, u8 connection_handle,
+			    u32 opaque_data_0, u32 opaque_data_1);
+
 struct qed_ll2_cbs {
 	qed_ll2_complete_rx_packet_cb rx_comp_cb;
 	qed_ll2_release_rx_packet_cb rx_release_cb;
 	qed_ll2_complete_tx_packet_cb tx_comp_cb;
 	qed_ll2_release_tx_packet_cb tx_release_cb;
+	qed_ll2_slowpath_cb slowpath_cb;
 	void *cookie;
 };
 
@@ -170,6 +177,7 @@ struct qed_ll2_acquire_data_inputs {
 	enum qed_ll2_tx_dest tx_dest;
 	enum qed_ll2_error_handle ai_err_packet_too_big;
 	enum qed_ll2_error_handle ai_err_no_buf;
+	bool secondary_queue;
 	u8 gsi_enable;
 };
 
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index ff3dd2ec44b4..d090d466cd0b 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -18,9 +18,11 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst,
 			      u32 id, long expires, u32 error);
 
 void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags);
+void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change,
+			 gfp_t flags, int *new_nsid);
 struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
 				       unsigned change, u32 event,
-				       gfp_t flags);
+				       gfp_t flags, int *new_nsid);
 void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev,
 		       gfp_t flags);
 
diff --git a/include/linux/security.h b/include/linux/security.h
index ce6265960d6c..73f1ef625d40 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1730,6 +1730,54 @@ static inline void securityfs_remove(struct dentry *dentry)
 
 #endif
 
+#ifdef CONFIG_BPF_SYSCALL
+union bpf_attr;
+struct bpf_map;
+struct bpf_prog;
+struct bpf_prog_aux;
+#ifdef CONFIG_SECURITY
+extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size);
+extern int security_bpf_map(struct bpf_map *map, fmode_t fmode);
+extern int security_bpf_prog(struct bpf_prog *prog);
+extern int security_bpf_map_alloc(struct bpf_map *map);
+extern void security_bpf_map_free(struct bpf_map *map);
+extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux);
+extern void security_bpf_prog_free(struct bpf_prog_aux *aux);
+#else
+static inline int security_bpf(int cmd, union bpf_attr *attr,
+					     unsigned int size)
+{
+	return 0;
+}
+
+static inline int security_bpf_map(struct bpf_map *map, fmode_t fmode)
+{
+	return 0;
+}
+
+static inline int security_bpf_prog(struct bpf_prog *prog)
+{
+	return 0;
+}
+
+static inline int security_bpf_map_alloc(struct bpf_map *map)
+{
+	return 0;
+}
+
+static inline void security_bpf_map_free(struct bpf_map *map)
+{ }
+
+static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux)
+{
+	return 0;
+}
+
+static inline void security_bpf_prog_free(struct bpf_prog_aux *aux)
+{ }
+#endif /* CONFIG_SECURITY */
+#endif /* CONFIG_BPF_SYSCALL */
+
 #ifdef CONFIG_SECURITY
 
 static inline char *alloc_secdata(void)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 72299ef00061..03634ec2f918 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -489,8 +489,9 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
  * the end of the header data, ie. at skb->end.
  */
 struct skb_shared_info {
-	unsigned short	_unused;
-	unsigned char	nr_frags;
+	__u8		__unused;
+	__u8		meta_len;
+	__u8		nr_frags;
 	__u8		tx_flags;
 	unsigned short	gso_size;
 	/* Warning: this field is not always filled in (UFO)! */
@@ -616,6 +617,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@nf_trace: netfilter packet trace flag
  *	@protocol: Packet protocol from driver
  *	@destructor: Destruct function
+ *	@tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue)
  *	@_nfct: Associated connection, if any (with nfctinfo bits)
  *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
  *	@skb_iif: ifindex of device we arrived on
@@ -661,8 +663,12 @@ struct sk_buff {
 			struct sk_buff		*prev;
 
 			union {
-				ktime_t		tstamp;
-				u64		skb_mstamp;
+				struct net_device	*dev;
+				/* Some protocols might use this space to store information,
+				 * while device pointer would be NULL.
+				 * UDP receive path is one user.
+				 */
+				unsigned long		dev_scratch;
 			};
 		};
 		struct rb_node	rbnode; /* used in netem & tcp stack */
@@ -670,12 +676,8 @@ struct sk_buff {
 	struct sock		*sk;
 
 	union {
-		struct net_device	*dev;
-		/* Some protocols might use this space to store information,
-		 * while device pointer would be NULL.
-		 * UDP receive path is one user.
-		 */
-		unsigned long		dev_scratch;
+		ktime_t		tstamp;
+		u64		skb_mstamp;
 	};
 	/*
 	 * This is the control buffer. It is free to use for every
@@ -685,8 +687,14 @@ struct sk_buff {
 	 */
 	char			cb[48] __aligned(8);
 
-	unsigned long		_skb_refdst;
-	void			(*destructor)(struct sk_buff *skb);
+	union {
+		struct {
+			unsigned long	_skb_refdst;
+			void		(*destructor)(struct sk_buff *skb);
+		};
+		struct list_head	tcp_tsorted_anchor;
+	};
+
 #ifdef CONFIG_XFRM
 	struct	sec_path	*sp;
 #endif
@@ -771,6 +779,7 @@ struct sk_buff {
 	__u8			remcsum_offload:1;
 #ifdef CONFIG_NET_SWITCHDEV
 	__u8			offload_fwd_mark:1;
+	__u8			offload_mr_fwd_mark:1;
 #endif
 #ifdef CONFIG_NET_CLS_ACT
 	__u8			tc_skip_classify:1;
@@ -1457,27 +1466,8 @@ static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri)
 }
 
 /**
- *	skb_header_release - release reference to header
- *	@skb: buffer to operate on
- *
- *	Drop a reference to the header part of the buffer.  This is done
- *	by acquiring a payload reference.  You must not read from the header
- *	part of skb->data after this.
- *	Note : Check if you can use __skb_header_release() instead.
- */
-static inline void skb_header_release(struct sk_buff *skb)
-{
-	BUG_ON(skb->nohdr);
-	skb->nohdr = 1;
-	atomic_add(1 << SKB_DATAREF_SHIFT, &skb_shinfo(skb)->dataref);
-}
-
-/**
  *	__skb_header_release - release reference to header
  *	@skb: buffer to operate on
- *
- *	Variant of skb_header_release() assuming skb is private to caller.
- *	We can avoid one atomic operation.
  */
 static inline void __skb_header_release(struct sk_buff *skb)
 {
@@ -3168,6 +3158,12 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len)
 	return __skb_grow(skb, len);
 }
 
+#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode)
+#define skb_rb_first(root) rb_to_skb(rb_first(root))
+#define skb_rb_last(root)  rb_to_skb(rb_last(root))
+#define skb_rb_next(skb)   rb_to_skb(rb_next(&(skb)->rbnode))
+#define skb_rb_prev(skb)   rb_to_skb(rb_prev(&(skb)->rbnode))
+
 #define skb_queue_walk(queue, skb) \
 		for (skb = (queue)->next;					\
 		     skb != (struct sk_buff *)(queue);				\
@@ -3182,6 +3178,18 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len)
 		for (; skb != (struct sk_buff *)(queue);			\
 		     skb = skb->next)
 
+#define skb_rbtree_walk(skb, root)						\
+		for (skb = skb_rb_first(root); skb != NULL;			\
+		     skb = skb_rb_next(skb))
+
+#define skb_rbtree_walk_from(skb)						\
+		for (; skb != NULL;						\
+		     skb = skb_rb_next(skb))
+
+#define skb_rbtree_walk_from_safe(skb, tmp)					\
+		for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL);	\
+		     skb = tmp)
+
 #define skb_queue_walk_from_safe(queue, skb, tmp)				\
 		for (tmp = skb->next;						\
 		     skb != (struct sk_buff *)(queue);				\
@@ -3419,6 +3427,69 @@ static inline ktime_t net_invalid_timestamp(void)
 	return 0;
 }
 
+static inline u8 skb_metadata_len(const struct sk_buff *skb)
+{
+	return skb_shinfo(skb)->meta_len;
+}
+
+static inline void *skb_metadata_end(const struct sk_buff *skb)
+{
+	return skb_mac_header(skb);
+}
+
+static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
+					  const struct sk_buff *skb_b,
+					  u8 meta_len)
+{
+	const void *a = skb_metadata_end(skb_a);
+	const void *b = skb_metadata_end(skb_b);
+	/* Using more efficient varaiant than plain call to memcmp(). */
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+	u64 diffs = 0;
+
+	switch (meta_len) {
+#define __it(x, op) (x -= sizeof(u##op))
+#define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op))
+	case 32: diffs |= __it_diff(a, b, 64);
+	case 24: diffs |= __it_diff(a, b, 64);
+	case 16: diffs |= __it_diff(a, b, 64);
+	case  8: diffs |= __it_diff(a, b, 64);
+		break;
+	case 28: diffs |= __it_diff(a, b, 64);
+	case 20: diffs |= __it_diff(a, b, 64);
+	case 12: diffs |= __it_diff(a, b, 64);
+	case  4: diffs |= __it_diff(a, b, 32);
+		break;
+	}
+	return diffs;
+#else
+	return memcmp(a - meta_len, b - meta_len, meta_len);
+#endif
+}
+
+static inline bool skb_metadata_differs(const struct sk_buff *skb_a,
+					const struct sk_buff *skb_b)
+{
+	u8 len_a = skb_metadata_len(skb_a);
+	u8 len_b = skb_metadata_len(skb_b);
+
+	if (!(len_a | len_b))
+		return false;
+
+	return len_a != len_b ?
+	       true : __skb_metadata_differs(skb_a, skb_b, len_a);
+}
+
+static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len)
+{
+	skb_shinfo(skb)->meta_len = meta_len;
+}
+
+static inline void skb_metadata_clear(struct sk_buff *skb)
+{
+	skb_metadata_set(skb, 0);
+}
+
 struct sk_buff *skb_clone_sk(struct sk_buff *skb);
 
 #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4aa40ef02d32..8c431385b272 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -98,7 +98,8 @@ struct tcp_options_received {
 		tstamp_ok : 1,	/* TIMESTAMP seen on SYN packet		*/
 		dsack : 1,	/* D-SACK is scheduled			*/
 		wscale_ok : 1,	/* Wscale seen on SYN packet		*/
-		sack_ok : 4,	/* SACK seen on SYN packet		*/
+		sack_ok : 3,	/* SACK seen on SYN packet		*/
+		smc_ok : 1,	/* SMC seen on SYN packet		*/
 		snd_wscale : 4,	/* Window scaling received from sender	*/
 		rcv_wscale : 4;	/* Window scaling to send to receiver	*/
 	u8	num_sacks;	/* Number of SACK blocks		*/
@@ -110,6 +111,9 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
 {
 	rx_opt->tstamp_ok = rx_opt->sack_ok = 0;
 	rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
+#if IS_ENABLED(CONFIG_SMC)
+	rx_opt->smc_ok = 0;
+#endif
 }
 
 /* This is the max number of SACKS that we'll generate and process. It's safe
@@ -191,6 +195,7 @@ struct tcp_sock {
 	u32	tsoffset;	/* timestamp offset */
 
 	struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
+	struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */
 
 	u32	snd_wl1;	/* Sequence for window update		*/
 	u32	snd_wnd;	/* The window we expect to receive	*/
@@ -214,7 +219,8 @@ struct tcp_sock {
 	u8	chrono_type:2,	/* current chronograph type */
 		rate_app_limited:1,  /* rate_{delivered,interval_us} limited? */
 		fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
-		unused:4;
+		fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */
+		unused:3;
 	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
 		thin_lto    : 1,/* Use linear timeouts for thin streams */
 		unused1	    : 1,
@@ -227,7 +233,8 @@ struct tcp_sock {
 		syn_fastopen_ch:1, /* Active TFO re-enabling probe */
 		syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
 		save_syn:1,	/* Save headers of SYN packet */
-		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
+		is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
+		syn_smc:1;	/* SYN includes SMC */
 	u32	tlp_high_seq;	/* snd_nxt at the time of TLP retransmit. */
 
 /* RTT measurement */
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
new file mode 100644
index 000000000000..7b69853188b1
--- /dev/null
+++ b/include/linux/thunderbolt.h
@@ -0,0 +1,598 @@
+/*
+ * Thunderbolt service API
+ *
+ * Copyright (C) 2014 Andreas Noever <andreas.noever@gmail.com>
+ * Copyright (C) 2017, Intel Corporation
+ * Authors: Michael Jamet <michael.jamet@intel.com>
+ *          Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef THUNDERBOLT_H_
+#define THUNDERBOLT_H_
+
+#include <linux/device.h>
+#include <linux/idr.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/mod_devicetable.h>
+#include <linux/pci.h>
+#include <linux/uuid.h>
+#include <linux/workqueue.h>
+
+enum tb_cfg_pkg_type {
+	TB_CFG_PKG_READ = 1,
+	TB_CFG_PKG_WRITE = 2,
+	TB_CFG_PKG_ERROR = 3,
+	TB_CFG_PKG_NOTIFY_ACK = 4,
+	TB_CFG_PKG_EVENT = 5,
+	TB_CFG_PKG_XDOMAIN_REQ = 6,
+	TB_CFG_PKG_XDOMAIN_RESP = 7,
+	TB_CFG_PKG_OVERRIDE = 8,
+	TB_CFG_PKG_RESET = 9,
+	TB_CFG_PKG_ICM_EVENT = 10,
+	TB_CFG_PKG_ICM_CMD = 11,
+	TB_CFG_PKG_ICM_RESP = 12,
+	TB_CFG_PKG_PREPARE_TO_SLEEP = 13,
+};
+
+/**
+ * enum tb_security_level - Thunderbolt security level
+ * @TB_SECURITY_NONE: No security, legacy mode
+ * @TB_SECURITY_USER: User approval required at minimum
+ * @TB_SECURITY_SECURE: One time saved key required at minimum
+ * @TB_SECURITY_DPONLY: Only tunnel Display port (and USB)
+ */
+enum tb_security_level {
+	TB_SECURITY_NONE,
+	TB_SECURITY_USER,
+	TB_SECURITY_SECURE,
+	TB_SECURITY_DPONLY,
+};
+
+/**
+ * struct tb - main thunderbolt bus structure
+ * @dev: Domain device
+ * @lock: Big lock. Must be held when accessing any struct
+ *	  tb_switch / struct tb_port.
+ * @nhi: Pointer to the NHI structure
+ * @ctl: Control channel for this domain
+ * @wq: Ordered workqueue for all domain specific work
+ * @root_switch: Root switch of this domain
+ * @cm_ops: Connection manager specific operations vector
+ * @index: Linux assigned domain number
+ * @security_level: Current security level
+ * @privdata: Private connection manager specific data
+ */
+struct tb {
+	struct device dev;
+	struct mutex lock;
+	struct tb_nhi *nhi;
+	struct tb_ctl *ctl;
+	struct workqueue_struct *wq;
+	struct tb_switch *root_switch;
+	const struct tb_cm_ops *cm_ops;
+	int index;
+	enum tb_security_level security_level;
+	unsigned long privdata[0];
+};
+
+extern struct bus_type tb_bus_type;
+extern struct device_type tb_service_type;
+extern struct device_type tb_xdomain_type;
+
+#define TB_LINKS_PER_PHY_PORT	2
+
+static inline unsigned int tb_phy_port_from_link(unsigned int link)
+{
+	return (link - 1) / TB_LINKS_PER_PHY_PORT;
+}
+
+/**
+ * struct tb_property_dir - XDomain property directory
+ * @uuid: Directory UUID or %NULL if root directory
+ * @properties: List of properties in this directory
+ *
+ * User needs to provide serialization if needed.
+ */
+struct tb_property_dir {
+	const uuid_t *uuid;
+	struct list_head properties;
+};
+
+enum tb_property_type {
+	TB_PROPERTY_TYPE_UNKNOWN = 0x00,
+	TB_PROPERTY_TYPE_DIRECTORY = 0x44,
+	TB_PROPERTY_TYPE_DATA = 0x64,
+	TB_PROPERTY_TYPE_TEXT = 0x74,
+	TB_PROPERTY_TYPE_VALUE = 0x76,
+};
+
+#define TB_PROPERTY_KEY_SIZE	8
+
+/**
+ * struct tb_property - XDomain property
+ * @list: Used to link properties together in a directory
+ * @key: Key for the property (always terminated).
+ * @type: Type of the property
+ * @length: Length of the property data in dwords
+ * @value: Property value
+ *
+ * Users use @type to determine which field in @value is filled.
+ */
+struct tb_property {
+	struct list_head list;
+	char key[TB_PROPERTY_KEY_SIZE + 1];
+	enum tb_property_type type;
+	size_t length;
+	union {
+		struct tb_property_dir *dir;
+		u8 *data;
+		char *text;
+		u32 immediate;
+	} value;
+};
+
+struct tb_property_dir *tb_property_parse_dir(const u32 *block,
+					      size_t block_len);
+ssize_t tb_property_format_dir(const struct tb_property_dir *dir, u32 *block,
+			       size_t block_len);
+struct tb_property_dir *tb_property_create_dir(const uuid_t *uuid);
+void tb_property_free_dir(struct tb_property_dir *dir);
+int tb_property_add_immediate(struct tb_property_dir *parent, const char *key,
+			      u32 value);
+int tb_property_add_data(struct tb_property_dir *parent, const char *key,
+			 const void *buf, size_t buflen);
+int tb_property_add_text(struct tb_property_dir *parent, const char *key,
+			 const char *text);
+int tb_property_add_dir(struct tb_property_dir *parent, const char *key,
+			struct tb_property_dir *dir);
+void tb_property_remove(struct tb_property *tb_property);
+struct tb_property *tb_property_find(struct tb_property_dir *dir,
+			const char *key, enum tb_property_type type);
+struct tb_property *tb_property_get_next(struct tb_property_dir *dir,
+					 struct tb_property *prev);
+
+#define tb_property_for_each(dir, property)			\
+	for (property = tb_property_get_next(dir, NULL);	\
+	     property;						\
+	     property = tb_property_get_next(dir, property))
+
+int tb_register_property_dir(const char *key, struct tb_property_dir *dir);
+void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir);
+
+/**
+ * struct tb_xdomain - Cross-domain (XDomain) connection
+ * @dev: XDomain device
+ * @tb: Pointer to the domain
+ * @remote_uuid: UUID of the remote domain (host)
+ * @local_uuid: Cached local UUID
+ * @route: Route string the other domain can be reached
+ * @vendor: Vendor ID of the remote domain
+ * @device: Device ID of the demote domain
+ * @lock: Lock to serialize access to the following fields of this structure
+ * @vendor_name: Name of the vendor (or %NULL if not known)
+ * @device_name: Name of the device (or %NULL if not known)
+ * @is_unplugged: The XDomain is unplugged
+ * @resume: The XDomain is being resumed
+ * @transmit_path: HopID which the remote end expects us to transmit
+ * @transmit_ring: Local ring (hop) where outgoing packets are pushed
+ * @receive_path: HopID which we expect the remote end to transmit
+ * @receive_ring: Local ring (hop) where incoming packets arrive
+ * @service_ids: Used to generate IDs for the services
+ * @properties: Properties exported by the remote domain
+ * @property_block_gen: Generation of @properties
+ * @properties_lock: Lock protecting @properties.
+ * @get_properties_work: Work used to get remote domain properties
+ * @properties_retries: Number of times left to read properties
+ * @properties_changed_work: Work used to notify the remote domain that
+ *			     our properties have changed
+ * @properties_changed_retries: Number of times left to send properties
+ *				changed notification
+ * @link: Root switch link the remote domain is connected (ICM only)
+ * @depth: Depth in the chain the remote domain is connected (ICM only)
+ *
+ * This structure represents connection across two domains (hosts).
+ * Each XDomain contains zero or more services which are exposed as
+ * &struct tb_service objects.
+ *
+ * Service drivers may access this structure if they need to enumerate
+ * non-standard properties but they need hold @lock when doing so
+ * because properties can be changed asynchronously in response to
+ * changes in the remote domain.
+ */
+struct tb_xdomain {
+	struct device dev;
+	struct tb *tb;
+	uuid_t *remote_uuid;
+	const uuid_t *local_uuid;
+	u64 route;
+	u16 vendor;
+	u16 device;
+	struct mutex lock;
+	const char *vendor_name;
+	const char *device_name;
+	bool is_unplugged;
+	bool resume;
+	u16 transmit_path;
+	u16 transmit_ring;
+	u16 receive_path;
+	u16 receive_ring;
+	struct ida service_ids;
+	struct tb_property_dir *properties;
+	u32 property_block_gen;
+	struct delayed_work get_properties_work;
+	int properties_retries;
+	struct delayed_work properties_changed_work;
+	int properties_changed_retries;
+	u8 link;
+	u8 depth;
+};
+
+int tb_xdomain_enable_paths(struct tb_xdomain *xd, u16 transmit_path,
+			    u16 transmit_ring, u16 receive_path,
+			    u16 receive_ring);
+int tb_xdomain_disable_paths(struct tb_xdomain *xd);
+struct tb_xdomain *tb_xdomain_find_by_uuid(struct tb *tb, const uuid_t *uuid);
+
+static inline struct tb_xdomain *
+tb_xdomain_find_by_uuid_locked(struct tb *tb, const uuid_t *uuid)
+{
+	struct tb_xdomain *xd;
+
+	mutex_lock(&tb->lock);
+	xd = tb_xdomain_find_by_uuid(tb, uuid);
+	mutex_unlock(&tb->lock);
+
+	return xd;
+}
+
+static inline struct tb_xdomain *tb_xdomain_get(struct tb_xdomain *xd)
+{
+	if (xd)
+		get_device(&xd->dev);
+	return xd;
+}
+
+static inline void tb_xdomain_put(struct tb_xdomain *xd)
+{
+	if (xd)
+		put_device(&xd->dev);
+}
+
+static inline bool tb_is_xdomain(const struct device *dev)
+{
+	return dev->type == &tb_xdomain_type;
+}
+
+static inline struct tb_xdomain *tb_to_xdomain(struct device *dev)
+{
+	if (tb_is_xdomain(dev))
+		return container_of(dev, struct tb_xdomain, dev);
+	return NULL;
+}
+
+int tb_xdomain_response(struct tb_xdomain *xd, const void *response,
+			size_t size, enum tb_cfg_pkg_type type);
+int tb_xdomain_request(struct tb_xdomain *xd, const void *request,
+		       size_t request_size, enum tb_cfg_pkg_type request_type,
+		       void *response, size_t response_size,
+		       enum tb_cfg_pkg_type response_type,
+		       unsigned int timeout_msec);
+
+/**
+ * tb_protocol_handler - Protocol specific handler
+ * @uuid: XDomain messages with this UUID are dispatched to this handler
+ * @callback: Callback called with the XDomain message. Returning %1
+ *	      here tells the XDomain core that the message was handled
+ *	      by this handler and should not be forwared to other
+ *	      handlers.
+ * @data: Data passed with the callback
+ * @list: Handlers are linked using this
+ *
+ * Thunderbolt services can hook into incoming XDomain requests by
+ * registering protocol handler. Only limitation is that the XDomain
+ * discovery protocol UUID cannot be registered since it is handled by
+ * the core XDomain code.
+ *
+ * The @callback must check that the message is really directed to the
+ * service the driver implements.
+ */
+struct tb_protocol_handler {
+	const uuid_t *uuid;
+	int (*callback)(const void *buf, size_t size, void *data);
+	void *data;
+	struct list_head list;
+};
+
+int tb_register_protocol_handler(struct tb_protocol_handler *handler);
+void tb_unregister_protocol_handler(struct tb_protocol_handler *handler);
+
+/**
+ * struct tb_service - Thunderbolt service
+ * @dev: XDomain device
+ * @id: ID of the service (shown in sysfs)
+ * @key: Protocol key from the properties directory
+ * @prtcid: Protocol ID from the properties directory
+ * @prtcvers: Protocol version from the properties directory
+ * @prtcrevs: Protocol software revision from the properties directory
+ * @prtcstns: Protocol settings mask from the properties directory
+ *
+ * Each domain exposes set of services it supports as collection of
+ * properties. For each service there will be one corresponding
+ * &struct tb_service. Service drivers are bound to these.
+ */
+struct tb_service {
+	struct device dev;
+	int id;
+	const char *key;
+	u32 prtcid;
+	u32 prtcvers;
+	u32 prtcrevs;
+	u32 prtcstns;
+};
+
+static inline struct tb_service *tb_service_get(struct tb_service *svc)
+{
+	if (svc)
+		get_device(&svc->dev);
+	return svc;
+}
+
+static inline void tb_service_put(struct tb_service *svc)
+{
+	if (svc)
+		put_device(&svc->dev);
+}
+
+static inline bool tb_is_service(const struct device *dev)
+{
+	return dev->type == &tb_service_type;
+}
+
+static inline struct tb_service *tb_to_service(struct device *dev)
+{
+	if (tb_is_service(dev))
+		return container_of(dev, struct tb_service, dev);
+	return NULL;
+}
+
+/**
+ * tb_service_driver - Thunderbolt service driver
+ * @driver: Driver structure
+ * @probe: Called when the driver is probed
+ * @remove: Called when the driver is removed (optional)
+ * @shutdown: Called at shutdown time to stop the service (optional)
+ * @id_table: Table of service identifiers the driver supports
+ */
+struct tb_service_driver {
+	struct device_driver driver;
+	int (*probe)(struct tb_service *svc, const struct tb_service_id *id);
+	void (*remove)(struct tb_service *svc);
+	void (*shutdown)(struct tb_service *svc);
+	const struct tb_service_id *id_table;
+};
+
+#define TB_SERVICE(key, id)				\
+	.match_flags = TBSVC_MATCH_PROTOCOL_KEY |	\
+		       TBSVC_MATCH_PROTOCOL_ID,		\
+	.protocol_key = (key),				\
+	.protocol_id = (id)
+
+int tb_register_service_driver(struct tb_service_driver *drv);
+void tb_unregister_service_driver(struct tb_service_driver *drv);
+
+static inline void *tb_service_get_drvdata(const struct tb_service *svc)
+{
+	return dev_get_drvdata(&svc->dev);
+}
+
+static inline void tb_service_set_drvdata(struct tb_service *svc, void *data)
+{
+	dev_set_drvdata(&svc->dev, data);
+}
+
+static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc)
+{
+	return tb_to_xdomain(svc->dev.parent);
+}
+
+/**
+ * struct tb_nhi - thunderbolt native host interface
+ * @lock: Must be held during ring creation/destruction. Is acquired by
+ *	  interrupt_work when dispatching interrupts to individual rings.
+ * @pdev: Pointer to the PCI device
+ * @iobase: MMIO space of the NHI
+ * @tx_rings: All Tx rings available on this host controller
+ * @rx_rings: All Rx rings available on this host controller
+ * @msix_ida: Used to allocate MSI-X vectors for rings
+ * @going_away: The host controller device is about to disappear so when
+ *		this flag is set, avoid touching the hardware anymore.
+ * @interrupt_work: Work scheduled to handle ring interrupt when no
+ *		    MSI-X is used.
+ * @hop_count: Number of rings (end point hops) supported by NHI.
+ */
+struct tb_nhi {
+	spinlock_t lock;
+	struct pci_dev *pdev;
+	void __iomem *iobase;
+	struct tb_ring **tx_rings;
+	struct tb_ring **rx_rings;
+	struct ida msix_ida;
+	bool going_away;
+	struct work_struct interrupt_work;
+	u32 hop_count;
+};
+
+/**
+ * struct tb_ring - thunderbolt TX or RX ring associated with a NHI
+ * @lock: Lock serializing actions to this ring. Must be acquired after
+ *	  nhi->lock.
+ * @nhi: Pointer to the native host controller interface
+ * @size: Size of the ring
+ * @hop: Hop (DMA channel) associated with this ring
+ * @head: Head of the ring (write next descriptor here)
+ * @tail: Tail of the ring (complete next descriptor here)
+ * @descriptors: Allocated descriptors for this ring
+ * @queue: Queue holding frames to be transferred over this ring
+ * @in_flight: Queue holding frames that are currently in flight
+ * @work: Interrupt work structure
+ * @is_tx: Is the ring Tx or Rx
+ * @running: Is the ring running
+ * @irq: MSI-X irq number if the ring uses MSI-X. %0 otherwise.
+ * @vector: MSI-X vector number the ring uses (only set if @irq is > 0)
+ * @flags: Ring specific flags
+ * @sof_mask: Bit mask used to detect start of frame PDF
+ * @eof_mask: Bit mask used to detect end of frame PDF
+ * @start_poll: Called when ring interrupt is triggered to start
+ *		polling. Passing %NULL keeps the ring in interrupt mode.
+ * @poll_data: Data passed to @start_poll
+ */
+struct tb_ring {
+	spinlock_t lock;
+	struct tb_nhi *nhi;
+	int size;
+	int hop;
+	int head;
+	int tail;
+	struct ring_desc *descriptors;
+	dma_addr_t descriptors_dma;
+	struct list_head queue;
+	struct list_head in_flight;
+	struct work_struct work;
+	bool is_tx:1;
+	bool running:1;
+	int irq;
+	u8 vector;
+	unsigned int flags;
+	u16 sof_mask;
+	u16 eof_mask;
+	void (*start_poll)(void *data);
+	void *poll_data;
+};
+
+/* Leave ring interrupt enabled on suspend */
+#define RING_FLAG_NO_SUSPEND	BIT(0)
+/* Configure the ring to be in frame mode */
+#define RING_FLAG_FRAME		BIT(1)
+/* Enable end-to-end flow control */
+#define RING_FLAG_E2E		BIT(2)
+
+struct ring_frame;
+typedef void (*ring_cb)(struct tb_ring *, struct ring_frame *, bool canceled);
+
+/**
+ * enum ring_desc_flags - Flags for DMA ring descriptor
+ * %RING_DESC_ISOCH: Enable isonchronous DMA (Tx only)
+ * %RING_DESC_CRC_ERROR: In frame mode CRC check failed for the frame (Rx only)
+ * %RING_DESC_COMPLETED: Descriptor completed (set by NHI)
+ * %RING_DESC_POSTED: Always set this
+ * %RING_DESC_BUFFER_OVERRUN: RX buffer overrun
+ * %RING_DESC_INTERRUPT: Request an interrupt on completion
+ */
+enum ring_desc_flags {
+	RING_DESC_ISOCH = 0x1,
+	RING_DESC_CRC_ERROR = 0x1,
+	RING_DESC_COMPLETED = 0x2,
+	RING_DESC_POSTED = 0x4,
+	RING_DESC_BUFFER_OVERRUN = 0x04,
+	RING_DESC_INTERRUPT = 0x8,
+};
+
+/**
+ * struct ring_frame - For use with ring_rx/ring_tx
+ * @buffer_phy: DMA mapped address of the frame
+ * @callback: Callback called when the frame is finished (optional)
+ * @list: Frame is linked to a queue using this
+ * @size: Size of the frame in bytes (%0 means %4096)
+ * @flags: Flags for the frame (see &enum ring_desc_flags)
+ * @eof: End of frame protocol defined field
+ * @sof: Start of frame protocol defined field
+ */
+struct ring_frame {
+	dma_addr_t buffer_phy;
+	ring_cb callback;
+	struct list_head list;
+	u32 size:12;
+	u32 flags:12;
+	u32 eof:4;
+	u32 sof:4;
+};
+
+/* Minimum size for ring_rx */
+#define TB_FRAME_SIZE		0x100
+
+struct tb_ring *tb_ring_alloc_tx(struct tb_nhi *nhi, int hop, int size,
+				 unsigned int flags);
+struct tb_ring *tb_ring_alloc_rx(struct tb_nhi *nhi, int hop, int size,
+				 unsigned int flags, u16 sof_mask, u16 eof_mask,
+				 void (*start_poll)(void *), void *poll_data);
+void tb_ring_start(struct tb_ring *ring);
+void tb_ring_stop(struct tb_ring *ring);
+void tb_ring_free(struct tb_ring *ring);
+
+int __tb_ring_enqueue(struct tb_ring *ring, struct ring_frame *frame);
+
+/**
+ * tb_ring_rx() - enqueue a frame on an RX ring
+ * @ring: Ring to enqueue the frame
+ * @frame: Frame to enqueue
+ *
+ * @frame->buffer, @frame->buffer_phy have to be set. The buffer must
+ * contain at least %TB_FRAME_SIZE bytes.
+ *
+ * @frame->callback will be invoked with @frame->size, @frame->flags,
+ * @frame->eof, @frame->sof set once the frame has been received.
+ *
+ * If ring_stop() is called after the packet has been enqueued
+ * @frame->callback will be called with canceled set to true.
+ *
+ * Return: Returns %-ESHUTDOWN if ring_stop has been called. Zero otherwise.
+ */
+static inline int tb_ring_rx(struct tb_ring *ring, struct ring_frame *frame)
+{
+	WARN_ON(ring->is_tx);
+	return __tb_ring_enqueue(ring, frame);
+}
+
+/**
+ * tb_ring_tx() - enqueue a frame on an TX ring
+ * @ring: Ring the enqueue the frame
+ * @frame: Frame to enqueue
+ *
+ * @frame->buffer, @frame->buffer_phy, @frame->size, @frame->eof and
+ * @frame->sof have to be set.
+ *
+ * @frame->callback will be invoked with once the frame has been transmitted.
+ *
+ * If ring_stop() is called after the packet has been enqueued @frame->callback
+ * will be called with canceled set to true.
+ *
+ * Return: Returns %-ESHUTDOWN if ring_stop has been called. Zero otherwise.
+ */
+static inline int tb_ring_tx(struct tb_ring *ring, struct ring_frame *frame)
+{
+	WARN_ON(!ring->is_tx);
+	return __tb_ring_enqueue(ring, frame);
+}
+
+/* Used only when the ring is in polling mode */
+struct ring_frame *tb_ring_poll(struct tb_ring *ring);
+void tb_ring_poll_complete(struct tb_ring *ring);
+
+/**
+ * tb_ring_dma_device() - Return device used for DMA mapping
+ * @ring: Ring whose DMA device is retrieved
+ *
+ * Use this function when you are mapping DMA for buffers that are
+ * passed to the ring for sending/receiving.
+ */
+static inline struct device *tb_ring_dma_device(struct tb_ring *ring)
+{
+	return &ring->nhi->pdev->dev;
+}
+
+#endif /* THUNDERBOLT_H_ */
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 2bcb4dc6df1a..84014ecfa67f 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -272,14 +272,37 @@ struct trace_event_call {
 #ifdef CONFIG_PERF_EVENTS
 	int				perf_refcount;
 	struct hlist_head __percpu	*perf_events;
-	struct bpf_prog			*prog;
-	struct perf_event		*bpf_prog_owner;
+	struct bpf_prog_array __rcu	*prog_array;
 
 	int	(*perf_perm)(struct trace_event_call *,
 			     struct perf_event *);
 #endif
 };
 
+#ifdef CONFIG_PERF_EVENTS
+static inline bool bpf_prog_array_valid(struct trace_event_call *call)
+{
+	/*
+	 * This inline function checks whether call->prog_array
+	 * is valid or not. The function is called in various places,
+	 * outside rcu_read_lock/unlock, as a heuristic to speed up execution.
+	 *
+	 * If this function returns true, and later call->prog_array
+	 * becomes false inside rcu_read_lock/unlock region,
+	 * we bail out then. If this function return false,
+	 * there is a risk that we might miss a few events if the checking
+	 * were delayed until inside rcu_read_lock/unlock region and
+	 * call->prog_array happened to become non-NULL then.
+	 *
+	 * Here, READ_ONCE() is used instead of rcu_access_pointer().
+	 * rcu_access_pointer() requires the actual definition of
+	 * "struct bpf_prog_array" while READ_ONCE() only needs
+	 * a declaration of the same type.
+	 */
+	return !!READ_ONCE(call->prog_array);
+}
+#endif
+
 static inline const char *
 trace_event_name(struct trace_event_call *call)
 {
@@ -436,12 +459,23 @@ trace_trigger_soft_disabled(struct trace_event_file *file)
 }
 
 #ifdef CONFIG_BPF_EVENTS
-unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx);
+unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx);
+int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog);
+void perf_event_detach_bpf_prog(struct perf_event *event);
 #else
-static inline unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
+static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 {
 	return 1;
 }
+
+static inline int
+perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void perf_event_detach_bpf_prog(struct perf_event *event) { }
+
 #endif
 
 enum {
@@ -512,6 +546,7 @@ perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type,
 {
 	perf_tp_event(type, count, raw_data, size, regs, head, rctx, task, event);
 }
+
 #endif
 
 #endif /* _LINUX_TRACE_EVENT_H */
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 1e6df0eb058f..9b8950042c96 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -95,8 +95,7 @@ struct tc_action_ops {
 	int     (*walk)(struct net *, struct sk_buff *,
 			struct netlink_callback *, int, const struct tc_action_ops *);
 	void	(*stats_update)(struct tc_action *, u64, u32, u64);
-	int	(*get_dev)(const struct tc_action *a, struct net *net,
-			   struct net_device **mirred_dev);
+	struct net_device *(*get_dev)(const struct tc_action *a);
 };
 
 struct tc_action_net {
@@ -180,4 +179,38 @@ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
 #endif
 }
 
+typedef int tc_setup_cb_t(enum tc_setup_type type,
+			  void *type_data, void *cb_priv);
+
+#ifdef CONFIG_NET_CLS_ACT
+int tc_setup_cb_egdev_register(const struct net_device *dev,
+			       tc_setup_cb_t *cb, void *cb_priv);
+void tc_setup_cb_egdev_unregister(const struct net_device *dev,
+				  tc_setup_cb_t *cb, void *cb_priv);
+int tc_setup_cb_egdev_call(const struct net_device *dev,
+			   enum tc_setup_type type, void *type_data,
+			   bool err_stop);
+#else
+static inline
+int tc_setup_cb_egdev_register(const struct net_device *dev,
+			       tc_setup_cb_t *cb, void *cb_priv)
+{
+	return 0;
+}
+
+static inline
+void tc_setup_cb_egdev_unregister(const struct net_device *dev,
+				  tc_setup_cb_t *cb, void *cb_priv)
+{
+}
+
+static inline
+int tc_setup_cb_egdev_call(const struct net_device *dev,
+			   enum tc_setup_type type, void *type_data,
+			   bool err_stop)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 35f5aabd432f..3357332ea375 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -56,9 +56,10 @@ struct prefix_info {
 struct in6_validator_info {
 	struct in6_addr		i6vi_addr;
 	struct inet6_dev	*i6vi_dev;
+	struct netlink_ext_ack	*extack;
 };
 
-#define IN6_ADDR_HSIZE_SHIFT	4
+#define IN6_ADDR_HSIZE_SHIFT	8
 #define IN6_ADDR_HSIZE		(1 << IN6_ADDR_HSIZE_SHIFT)
 
 int addrconf_init(void);
@@ -95,8 +96,8 @@ int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
 		      u32 banned_flags);
 int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
 		    u32 banned_flags);
-int inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
-			 bool match_wildcard);
+bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
+			  bool match_wildcard);
 void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr);
 void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr);
 
@@ -208,7 +209,7 @@ void ipv6_mc_remap(struct inet6_dev *idev);
 void ipv6_mc_init_dev(struct inet6_dev *idev);
 void ipv6_mc_destroy_dev(struct inet6_dev *idev);
 int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed);
-void addrconf_dad_failure(struct inet6_ifaddr *ifp);
+void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp);
 
 bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group,
 			 const struct in6_addr *src_addr);
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 3ac79150291f..2b3a6eec4570 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -49,17 +49,19 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *,
 					   unsigned long,
 					   s64,
 					   gfp_t,
-					   rxrpc_notify_rx_t);
+					   rxrpc_notify_rx_t,
+					   bool);
 int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *,
 			   struct msghdr *, size_t,
 			   rxrpc_notify_end_tx_t);
 int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *,
-			   void *, size_t, size_t *, bool, u32 *);
+			   void *, size_t, size_t *, bool, u32 *, u16 *);
 bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
 			     u32, int, const char *);
 void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
 void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
 			   struct sockaddr_rxrpc *);
+u64 rxrpc_kernel_get_rtt(struct socket *, struct rxrpc_call *);
 int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
 			       rxrpc_user_attach_call_t, unsigned long, gfp_t);
 void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64);
@@ -67,5 +69,6 @@ int rxrpc_kernel_retry_call(struct socket *, struct rxrpc_call *,
 			    struct sockaddr_rxrpc *, struct key *);
 int rxrpc_kernel_check_call(struct socket *, struct rxrpc_call *,
 			    enum rxrpc_call_completion *, u32 *);
+u32 rxrpc_kernel_check_life(struct socket *, struct rxrpc_call *);
 
 #endif /* _NET_RXRPC_H */
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index f9fb566e75cf..9324ac2d9ff2 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -22,11 +22,13 @@
 
 #include "vsock_addr.h"
 
-/* vsock-specific sock->sk_state constants */
-#define VSOCK_SS_LISTEN 255
-
 #define LAST_RESERVED_PORT 1023
 
+#define VSOCK_HASH_SIZE         251
+extern struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1];
+extern struct list_head vsock_connected_table[VSOCK_HASH_SIZE];
+extern spinlock_t vsock_table_lock;
+
 #define vsock_sk(__sk)    ((struct vsock_sock *)__sk)
 #define sk_vsock(__vsk)   (&(__vsk)->sk)
 
@@ -175,6 +177,18 @@ const struct vsock_transport *vsock_core_get_transport(void);
 
 /**** UTILS ****/
 
+/* vsock_table_lock must be held */
+static inline bool __vsock_in_bound_table(struct vsock_sock *vsk)
+{
+	return !list_empty(&vsk->bound_table);
+}
+
+/* vsock_table_lock must be held */
+static inline bool __vsock_in_connected_table(struct vsock_sock *vsk)
+{
+	return !list_empty(&vsk->connected_table);
+}
+
 void vsock_release_pending(struct sock *pending);
 void vsock_add_pending(struct sock *listener, struct sock *pending);
 void vsock_remove_pending(struct sock *listener, struct sock *pending);
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 020142bb9735..e89cff0c4c23 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -147,6 +147,9 @@ void bt_err_ratelimited(const char *fmt, ...);
 #define bt_dev_dbg(hdev, fmt, ...)				\
 	BT_DBG("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
 
+#define bt_dev_err_ratelimited(hdev, fmt, ...)			\
+	BT_ERR_RATELIMITED("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
+
 /* Connection and socket states */
 enum {
 	BT_CONNECTED = 1, /* Equal to TCP_ESTABLISHED to make net code happy */
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index fe98f0a5bef0..1668211297a9 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -273,7 +273,7 @@ enum {
 #define HCI_AUTO_OFF_TIMEOUT	msecs_to_jiffies(2000)	/* 2 seconds */
 #define HCI_POWER_OFF_TIMEOUT	msecs_to_jiffies(5000)	/* 5 seconds */
 #define HCI_LE_CONN_TIMEOUT	msecs_to_jiffies(20000)	/* 20 seconds */
-#define HCI_LE_AUTOCONN_TIMEOUT	msecs_to_jiffies(2000)	/* 2 seconds */
+#define HCI_LE_AUTOCONN_TIMEOUT	msecs_to_jiffies(4000)	/* 4 seconds */
 
 /* HCI data types */
 #define HCI_COMMAND_PKT		0x01
diff --git a/include/net/bonding.h b/include/net/bonding.h
index b2e68657a216..f801fc940b29 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -330,7 +330,6 @@ static inline void bond_set_active_slave(struct slave *slave)
 		slave->backup = 0;
 		bond_queue_slave_event(slave);
 		bond_lower_state_changed(slave);
-		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
 	}
 }
 
@@ -340,7 +339,6 @@ static inline void bond_set_backup_slave(struct slave *slave)
 		slave->backup = 1;
 		bond_queue_slave_event(slave);
 		bond_lower_state_changed(slave);
-		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
 	}
 }
 
@@ -353,7 +351,6 @@ static inline void bond_set_slave_state(struct slave *slave,
 	slave->backup = slave_state;
 	if (notify) {
 		bond_lower_state_changed(slave);
-		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
 		bond_queue_slave_event(slave);
 		slave->should_notify = 0;
 	} else {
@@ -385,7 +382,6 @@ static inline void bond_slave_state_notify(struct bonding *bond)
 	bond_for_each_slave(bond, tmp, iter) {
 		if (tmp->should_notify) {
 			bond_lower_state_changed(tmp);
-			rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_ATOMIC);
 			tmp->should_notify = 0;
 		}
 	}
@@ -596,7 +592,8 @@ void bond_destroy_sysfs(struct bond_net *net);
 void bond_prepare_sysfs_group(struct bonding *bond);
 int bond_sysfs_slave_add(struct slave *slave);
 void bond_sysfs_slave_del(struct slave *slave);
-int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev);
+int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
+		 struct netlink_ext_ack *extack);
 int bond_release(struct net_device *bond_dev, struct net_device *slave_dev);
 u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb);
 int bond_set_carrier(struct bonding *bond);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index f12fa5245a45..8b8118a7fadb 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4347,19 +4347,6 @@ static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
 }
 
 /**
- * ieee80211_data_from_8023 - convert an 802.3 frame to 802.11
- * @skb: the 802.3 frame
- * @addr: the device MAC address
- * @iftype: the virtual interface type
- * @bssid: the network bssid (used only for iftype STATION and ADHOC)
- * @qos: build 802.11 QoS data frame
- * Return: 0 on success, or a negative error code.
- */
-int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
-			     enum nl80211_iftype iftype, const u8 *bssid,
-			     bool qos);
-
-/**
  * ieee80211_amsdu_to_8023s - decode an IEEE 802.11n A-MSDU frame
  *
  * Decode an IEEE 802.11 A-MSDU and convert it to a list of 802.3 frames.
@@ -5441,9 +5428,6 @@ cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid,
  * @req_ie_len: association request IEs length
  * @resp_ie: association response IEs (may be %NULL)
  * @resp_ie_len: assoc response IEs length
- * @authorized: true if the 802.1X authentication was done by the driver or is
- *	not needed (e.g., when Fast Transition protocol was used), false
- *	otherwise. Ignored for networks that don't use 802.1X authentication.
  */
 struct cfg80211_roam_info {
 	struct ieee80211_channel *channel;
@@ -5453,7 +5437,6 @@ struct cfg80211_roam_info {
 	size_t req_ie_len;
 	const u8 *resp_ie;
 	size_t resp_ie_len;
-	bool authorized;
 };
 
 /**
@@ -5478,6 +5461,23 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info,
 		     gfp_t gfp);
 
 /**
+ * cfg80211_port_authorized - notify cfg80211 of successful security association
+ *
+ * @dev: network device
+ * @bssid: the BSSID of the AP
+ * @gfp: allocation flags
+ *
+ * This function should be called by a driver that supports 4 way handshake
+ * offload after a security association was successfully established (i.e.,
+ * the 4 way handshake was completed successfully). The call to this function
+ * should be preceded with a call to cfg80211_connect_result(),
+ * cfg80211_connect_done(), cfg80211_connect_bss() or cfg80211_roamed() to
+ * indicate the 802.11 association.
+ */
+void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid,
+			      gfp_t gfp);
+
+/**
  * cfg80211_disconnected - notify cfg80211 that connection was dropped
  *
  * @dev: network device
@@ -5934,7 +5934,8 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len,
  * @ies: the IE buffer
  * @ielen: the length of the IE buffer
  * @ids: an array with element IDs that are allowed before
- *	the split
+ *	the split. A WLAN_EID_EXTENSION value means that the next
+ *	EID in the list is a sub-element of the EXTENSION IE.
  * @n_ids: the size of the element ID array
  * @after_ric: array IE types that come after the RIC element
  * @n_after_ric: size of the @after_ric array
@@ -5965,7 +5966,8 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen,
  * @ies: the IE buffer
  * @ielen: the length of the IE buffer
  * @ids: an array with element IDs that are allowed before
- *	the split
+ *	the split. A WLAN_EID_EXTENSION value means that the next
+ *	EID in the list is a sub-element of the EXTENSION IE.
  * @n_ids: the size of the element ID array
  * @offset: offset where to start splitting in the buffer
  *
diff --git a/include/net/dn.h b/include/net/dn.h
index fc0036228d20..56ab0726c641 100644
--- a/include/net/dn.h
+++ b/include/net/dn.h
@@ -123,13 +123,6 @@ struct dn_scp                                   /* Session Control Port */
 	unsigned long keepalive;
 	void (*keepalive_fxn)(struct sock *sk);
 
-	/*
-	 * This stuff is for the fast timer for delayed acks
-	 */
-	struct timer_list delack_timer;
-	int delack_pending;
-	void (*delack_fxn)(struct sock *sk);
-
 };
 
 static inline struct dn_scp *DN_SK(struct sock *sk)
diff --git a/include/net/dn_nsp.h b/include/net/dn_nsp.h
index 3a3e33d18456..413a15e5339c 100644
--- a/include/net/dn_nsp.h
+++ b/include/net/dn_nsp.h
@@ -17,7 +17,6 @@
 
 void dn_nsp_send_data_ack(struct sock *sk);
 void dn_nsp_send_oth_ack(struct sock *sk);
-void dn_nsp_delayed_ack(struct sock *sk);
 void dn_send_conn_ack(struct sock *sk);
 void dn_send_conn_conf(struct sock *sk, gfp_t gfp);
 void dn_nsp_send_disc(struct sock *sk, unsigned char type,
diff --git a/include/net/dsa.h b/include/net/dsa.h
index dd44d6ce1097..50e276dc4c01 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -130,11 +130,6 @@ struct dsa_switch_tree {
 	 */
 	struct dsa_platform_data	*pd;
 
-	/* Copy of tag_ops->rcv for faster access in hot path */
-	struct sk_buff *	(*rcv)(struct sk_buff *skb,
-				       struct net_device *dev,
-				       struct packet_type *pt);
-
 	/*
 	 * The switch port to which the CPU is attached.
 	 */
@@ -144,12 +139,6 @@ struct dsa_switch_tree {
 	 * Data for the individual switch chips.
 	 */
 	struct dsa_switch	*ds[DSA_MAX_SWITCHES];
-
-	/*
-	 * Tagging protocol operations for adding and removing an
-	 * encapsulation tag.
-	 */
-	const struct dsa_device_ops *tag_ops;
 };
 
 /* TC matchall action types, only mirroring for now */
@@ -175,11 +164,33 @@ struct dsa_mall_tc_entry {
 
 
 struct dsa_port {
+	/* A CPU port is physically connected to a master device.
+	 * A user port exposed to userspace has a slave device.
+	 */
+	union {
+		struct net_device *master;
+		struct net_device *slave;
+	};
+
+	/* CPU port tagging operations used by master or slave devices */
+	const struct dsa_device_ops *tag_ops;
+
+	/* Copies for faster access in master receive hot path */
+	struct dsa_switch_tree *dst;
+	struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev,
+			       struct packet_type *pt);
+
+	enum {
+		DSA_PORT_TYPE_UNUSED = 0,
+		DSA_PORT_TYPE_CPU,
+		DSA_PORT_TYPE_DSA,
+		DSA_PORT_TYPE_USER,
+	} type;
+
 	struct dsa_switch	*ds;
 	unsigned int		index;
 	const char		*name;
 	struct dsa_port		*cpu_dp;
-	struct net_device	*netdev;
 	struct device_node	*dn;
 	unsigned int		ageing_time;
 	u8			stp_state;
@@ -188,7 +199,6 @@ struct dsa_port {
 	/*
 	 * Original copy of the master netdev ethtool_ops
 	 */
-	struct ethtool_ops	ethtool_ops;
 	const struct ethtool_ops *orig_ethtool_ops;
 };
 
@@ -230,9 +240,6 @@ struct dsa_switch {
 	/*
 	 * Slave mii_bus and devices for the individual ports.
 	 */
-	u32			dsa_port_mask;
-	u32			cpu_port_mask;
-	u32			enabled_port_mask;
 	u32			phys_mii_mask;
 	struct mii_bus		*slave_mii_bus;
 
@@ -251,19 +258,41 @@ struct dsa_switch {
 	struct dsa_port ports[];
 };
 
+static inline const struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p)
+{
+	return &ds->ports[p];
+}
+
+static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p)
+{
+	return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED;
+}
+
 static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p)
 {
-	return !!(ds->cpu_port_mask & (1 << p));
+	return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_CPU;
 }
 
 static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p)
 {
-	return !!((ds->dsa_port_mask) & (1 << p));
+	return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_DSA;
+}
+
+static inline bool dsa_is_user_port(struct dsa_switch *ds, int p)
+{
+	return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER;
 }
 
-static inline bool dsa_is_normal_port(struct dsa_switch *ds, int p)
+static inline u32 dsa_user_ports(struct dsa_switch *ds)
 {
-	return !dsa_is_cpu_port(ds, p) && !dsa_is_dsa_port(ds, p);
+	u32 mask = 0;
+	int p;
+
+	for (p = 0; p < ds->num_ports; p++)
+		if (dsa_is_user_port(ds, p))
+			mask |= BIT(p);
+
+	return mask;
 }
 
 static inline u8 dsa_upstream_port(struct dsa_switch *ds)
@@ -295,7 +324,6 @@ struct dsa_switch_ops {
 	enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds);
 
 	int	(*setup)(struct dsa_switch *ds);
-	int	(*set_addr)(struct dsa_switch *ds, u8 *addr);
 	u32	(*get_phy_flags)(struct dsa_switch *ds, int port);
 
 	/*
@@ -475,4 +503,54 @@ static inline int dsa_switch_resume(struct dsa_switch *ds)
 }
 #endif /* CONFIG_PM_SLEEP */
 
+enum dsa_notifier_type {
+	DSA_PORT_REGISTER,
+	DSA_PORT_UNREGISTER,
+};
+
+struct dsa_notifier_info {
+	struct net_device *dev;
+};
+
+struct dsa_notifier_register_info {
+	struct dsa_notifier_info info;	/* must be first */
+	struct net_device *master;
+	unsigned int port_number;
+	unsigned int switch_number;
+};
+
+static inline struct net_device *
+dsa_notifier_info_to_dev(const struct dsa_notifier_info *info)
+{
+	return info->dev;
+}
+
+#if IS_ENABLED(CONFIG_NET_DSA)
+int register_dsa_notifier(struct notifier_block *nb);
+int unregister_dsa_notifier(struct notifier_block *nb);
+int call_dsa_notifiers(unsigned long val, struct net_device *dev,
+		       struct dsa_notifier_info *info);
+#else
+static inline int register_dsa_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int unregister_dsa_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev,
+				     struct dsa_notifier_info *info)
+{
+	return NOTIFY_DONE;
+}
+#endif
+
+/* Broadcom tag specific helpers to insert and extract queue/port number */
+#define BRCM_TAG_SET_PORT_QUEUE(p, q)	((p) << 8 | q)
+#define BRCM_TAG_GET_PORT(v)		((v) >> 8)
+#define BRCM_TAG_GET_QUEUE(v)		((v) & 0xff)
+
 #endif
diff --git a/include/net/dst.h b/include/net/dst.h
index 694c2e6ae618..b091fd536098 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -102,7 +102,7 @@ struct dst_entry {
 	union {
 		struct dst_entry	*next;
 		struct rtable __rcu	*rt_next;
-		struct rt6_info		*rt6_next;
+		struct rt6_info __rcu	*rt6_next;
 		struct dn_route __rcu	*dn_next;
 	};
 };
@@ -256,17 +256,18 @@ static inline void dst_hold(struct dst_entry *dst)
 	WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0);
 }
 
-static inline void dst_use(struct dst_entry *dst, unsigned long time)
+static inline void dst_use_noref(struct dst_entry *dst, unsigned long time)
 {
-	dst_hold(dst);
-	dst->__use++;
-	dst->lastuse = time;
+	if (unlikely(time != dst->lastuse)) {
+		dst->__use++;
+		dst->lastuse = time;
+	}
 }
 
-static inline void dst_use_noref(struct dst_entry *dst, unsigned long time)
+static inline void dst_hold_and_use(struct dst_entry *dst, unsigned long time)
 {
-	dst->__use++;
-	dst->lastuse = time;
+	dst_hold(dst);
+	dst_use_noref(dst, time);
 }
 
 static inline struct dst_entry *dst_clone(struct dst_entry *dst)
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 91bc7bdf6bf5..56cb3c38569a 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -25,7 +25,7 @@ struct metadata_dst {
 	} u;
 };
 
-static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
+static inline struct metadata_dst *skb_metadata_dst(const struct sk_buff *skb)
 {
 	struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb);
 
@@ -35,7 +35,8 @@ static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
 	return NULL;
 }
 
-static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb)
+static inline struct ip_tunnel_info *
+skb_tunnel_info(const struct sk_buff *skb)
 {
 	struct metadata_dst *md_dst = skb_metadata_dst(skb);
 	struct dst_entry *dst;
@@ -87,6 +88,7 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a,
 void metadata_dst_free(struct metadata_dst *);
 struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type,
 					gfp_t flags);
+void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst);
 struct metadata_dst __percpu *
 metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags);
 
diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h
index 669b9716dc7a..c91ec732afd6 100644
--- a/include/net/fib_notifier.h
+++ b/include/net/fib_notifier.h
@@ -9,6 +9,7 @@
 struct fib_notifier_info {
 	struct net *net;
 	int family;
+	struct netlink_ext_ack  *extack;
 };
 
 enum fib_event_type {
@@ -20,6 +21,8 @@ enum fib_event_type {
 	FIB_EVENT_RULE_DEL,
 	FIB_EVENT_NH_ADD,
 	FIB_EVENT_NH_DEL,
+	FIB_EVENT_VIF_ADD,
+	FIB_EVENT_VIF_DEL,
 };
 
 struct fib_notifier_ops {
diff --git a/include/net/fq.h b/include/net/fq.h
index 6d8521a30c5c..ac944a686840 100644
--- a/include/net/fq.h
+++ b/include/net/fq.h
@@ -90,6 +90,13 @@ typedef void fq_skb_free_t(struct fq *,
 			   struct fq_flow *,
 			   struct sk_buff *);
 
+/* Return %true to filter (drop) the frame. */
+typedef bool fq_skb_filter_t(struct fq *,
+			     struct fq_tin *,
+			     struct fq_flow *,
+			     struct sk_buff *,
+			     void *);
+
 typedef struct fq_flow *fq_flow_get_default_t(struct fq *,
 					      struct fq_tin *,
 					      int idx,
diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h
index ac1a2317941e..be7c0fab3478 100644
--- a/include/net/fq_impl.h
+++ b/include/net/fq_impl.h
@@ -12,24 +12,22 @@
 
 /* functions that are embedded into includer */
 
-static struct sk_buff *fq_flow_dequeue(struct fq *fq,
-				       struct fq_flow *flow)
+static void fq_adjust_removal(struct fq *fq,
+			      struct fq_flow *flow,
+			      struct sk_buff *skb)
 {
 	struct fq_tin *tin = flow->tin;
-	struct fq_flow *i;
-	struct sk_buff *skb;
-
-	lockdep_assert_held(&fq->lock);
-
-	skb = __skb_dequeue(&flow->queue);
-	if (!skb)
-		return NULL;
 
 	tin->backlog_bytes -= skb->len;
 	tin->backlog_packets--;
 	flow->backlog -= skb->len;
 	fq->backlog--;
 	fq->memory_usage -= skb->truesize;
+}
+
+static void fq_rejigger_backlog(struct fq *fq, struct fq_flow *flow)
+{
+	struct fq_flow *i;
 
 	if (flow->backlog == 0) {
 		list_del_init(&flow->backlogchain);
@@ -43,6 +41,21 @@ static struct sk_buff *fq_flow_dequeue(struct fq *fq,
 		list_move_tail(&flow->backlogchain,
 			       &i->backlogchain);
 	}
+}
+
+static struct sk_buff *fq_flow_dequeue(struct fq *fq,
+				       struct fq_flow *flow)
+{
+	struct sk_buff *skb;
+
+	lockdep_assert_held(&fq->lock);
+
+	skb = __skb_dequeue(&flow->queue);
+	if (!skb)
+		return NULL;
+
+	fq_adjust_removal(fq, flow, skb);
+	fq_rejigger_backlog(fq, flow);
 
 	return skb;
 }
@@ -191,6 +204,45 @@ static void fq_tin_enqueue(struct fq *fq,
 	}
 }
 
+static void fq_flow_filter(struct fq *fq,
+			   struct fq_flow *flow,
+			   fq_skb_filter_t filter_func,
+			   void *filter_data,
+			   fq_skb_free_t free_func)
+{
+	struct fq_tin *tin = flow->tin;
+	struct sk_buff *skb, *tmp;
+
+	lockdep_assert_held(&fq->lock);
+
+	skb_queue_walk_safe(&flow->queue, skb, tmp) {
+		if (!filter_func(fq, tin, flow, skb, filter_data))
+			continue;
+
+		__skb_unlink(skb, &flow->queue);
+		fq_adjust_removal(fq, flow, skb);
+		free_func(fq, tin, flow, skb);
+	}
+
+	fq_rejigger_backlog(fq, flow);
+}
+
+static void fq_tin_filter(struct fq *fq,
+			  struct fq_tin *tin,
+			  fq_skb_filter_t filter_func,
+			  void *filter_data,
+			  fq_skb_free_t free_func)
+{
+	struct fq_flow *flow;
+
+	lockdep_assert_held(&fq->lock);
+
+	list_for_each_entry(flow, &tin->new_flows, flowchain)
+		fq_flow_filter(fq, flow, filter_func, filter_data, free_func);
+	list_for_each_entry(flow, &tin->old_flows, flowchain)
+		fq_flow_filter(fq, flow, filter_func, filter_data, free_func);
+}
+
 static void fq_flow_reset(struct fq *fq,
 			  struct fq_flow *flow,
 			  fq_skb_free_t free_func)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 13e4c89a8231..0358745ea059 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -169,9 +169,9 @@ enum inet_csk_ack_state_t {
 };
 
 void inet_csk_init_xmit_timers(struct sock *sk,
-			       void (*retransmit_handler)(unsigned long),
-			       void (*delack_handler)(unsigned long),
-			       void (*keepalive_handler)(unsigned long));
+			       void (*retransmit_handler)(struct timer_list *),
+			       void (*delack_handler)(struct timer_list *),
+			       void (*keepalive_handler)(struct timer_list *));
 void inet_csk_clear_xmit_timers(struct sock *sk);
 
 static inline void inet_csk_schedule_ack(struct sock *sk)
diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index d30e4c869438..482a1b705362 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -134,11 +134,6 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph)
 	return 1;
 }
 
-static inline void IP6_ECN_clear(struct ipv6hdr *iph)
-{
-	*(__be32*)iph &= ~htonl(INET_ECN_MASK << 20);
-}
-
 static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
 {
 	dscp &= ~INET_ECN_MASK;
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index a6e4edd8d4a2..351f0c3cdcd9 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -96,7 +96,7 @@ struct inet_frags {
 	void			(*constructor)(struct inet_frag_queue *q,
 					       const void *arg);
 	void			(*destructor)(struct inet_frag_queue *);
-	void			(*frag_expire)(unsigned long data);
+	void			(*frag_expire)(struct timer_list *t);
 	struct kmem_cache	*frags_cachep;
 	const char		*frags_cache_name;
 };
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index db8162dd8c0b..2135c9ba6ac3 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -92,7 +92,8 @@ struct inet_request_sock {
 				wscale_ok  : 1,
 				ecn_ok	   : 1,
 				acked	   : 1,
-				no_srccheck: 1;
+				no_srccheck: 1,
+				smc_ok	   : 1;
 	kmemcheck_bitfield_end(flags);
 	u32                     ir_mark;
 	union {
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index d060d711a624..10c913816032 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -29,6 +29,14 @@
 #define FIB6_TABLE_HASHSZ 1
 #endif
 
+#define RT6_DEBUG 2
+
+#if RT6_DEBUG >= 3
+#define RT6_TRACE(x...) pr_debug(x)
+#else
+#define RT6_TRACE(x...) do { ; } while (0)
+#endif
+
 struct rt6_info;
 
 struct fib6_config {
@@ -60,25 +68,30 @@ struct fib6_config {
 };
 
 struct fib6_node {
-	struct fib6_node	*parent;
-	struct fib6_node	*left;
-	struct fib6_node	*right;
+	struct fib6_node __rcu	*parent;
+	struct fib6_node __rcu	*left;
+	struct fib6_node __rcu	*right;
 #ifdef CONFIG_IPV6_SUBTREES
-	struct fib6_node	*subtree;
+	struct fib6_node __rcu	*subtree;
 #endif
-	struct rt6_info		*leaf;
+	struct rt6_info __rcu	*leaf;
 
 	__u16			fn_bit;		/* bit key */
 	__u16			fn_flags;
 	int			fn_sernum;
-	struct rt6_info		*rr_ptr;
+	struct rt6_info __rcu	*rr_ptr;
 	struct rcu_head		rcu;
 };
 
+struct fib6_gc_args {
+	int			timeout;
+	int			more;
+};
+
 #ifndef CONFIG_IPV6_SUBTREES
 #define FIB6_SUBTREE(fn)	NULL
 #else
-#define FIB6_SUBTREE(fn)	((fn)->subtree)
+#define FIB6_SUBTREE(fn)	(rcu_dereference_protected((fn)->subtree, 1))
 #endif
 
 struct mx6_config {
@@ -98,6 +111,22 @@ struct rt6key {
 
 struct fib6_table;
 
+struct rt6_exception_bucket {
+	struct hlist_head	chain;
+	int			depth;
+};
+
+struct rt6_exception {
+	struct hlist_node	hlist;
+	struct rt6_info		*rt6i;
+	unsigned long		stamp;
+	struct rcu_head		rcu;
+};
+
+#define FIB6_EXCEPTION_BUCKET_SIZE_SHIFT 10
+#define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT)
+#define FIB6_MAX_DEPTH 5
+
 struct rt6_info {
 	struct dst_entry		dst;
 
@@ -134,14 +163,25 @@ struct rt6_info {
 
 	struct inet6_dev		*rt6i_idev;
 	struct rt6_info * __percpu	*rt6i_pcpu;
+	struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
 
 	u32				rt6i_metric;
 	u32				rt6i_pmtu;
 	/* more non-fragment space at head required */
 	unsigned short			rt6i_nfheader_len;
 	u8				rt6i_protocol;
+	u8				exception_bucket_flushed:1,
+					unused:7;
 };
 
+#define for_each_fib6_node_rt_rcu(fn)					\
+	for (rt = rcu_dereference((fn)->leaf); rt;			\
+	     rt = rcu_dereference(rt->dst.rt6_next))
+
+#define for_each_fib6_walker_rt(w)					\
+	for (rt = (w)->leaf; rt;					\
+	     rt = rcu_dereference_protected(rt->dst.rt6_next, 1))
+
 static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
 {
 	return ((struct rt6_info *)dst)->rt6i_idev;
@@ -188,6 +228,8 @@ static inline bool rt6_get_cookie_safe(const struct rt6_info *rt,
 
 	if (fn) {
 		*cookie = fn->fn_sernum;
+		/* pairs with smp_wmb() in fib6_update_sernum_upto_root() */
+		smp_rmb();
 		status = true;
 	}
 
@@ -248,7 +290,6 @@ struct fib6_walker {
 	struct fib6_node *root, *node;
 	struct rt6_info *leaf;
 	enum fib6_walk_state state;
-	bool prune;
 	unsigned int skip;
 	unsigned int count;
 	int (*func)(struct fib6_walker *);
@@ -256,12 +297,15 @@ struct fib6_walker {
 };
 
 struct rt6_statistics {
-	__u32		fib_nodes;
-	__u32		fib_route_nodes;
-	__u32		fib_rt_alloc;		/* permanent routes	*/
-	__u32		fib_rt_entries;		/* rt entries in table	*/
-	__u32		fib_rt_cache;		/* cache routes		*/
-	__u32		fib_discarded_routes;
+	__u32		fib_nodes;		/* all fib6 nodes */
+	__u32		fib_route_nodes;	/* intermediate nodes */
+	__u32		fib_rt_entries;		/* rt entries in fib table */
+	__u32		fib_rt_cache;		/* cached rt entries in exception table */
+	__u32		fib_discarded_routes;	/* total number of routes delete */
+
+	/* The following stats are not protected by any lock */
+	atomic_t	fib_rt_alloc;		/* total number of routes alloced */
+	atomic_t	fib_rt_uncache;		/* rt entries in uncached list */
 };
 
 #define RTN_TL_ROOT	0x0001
@@ -277,7 +321,7 @@ struct rt6_statistics {
 struct fib6_table {
 	struct hlist_node	tb6_hlist;
 	u32			tb6_id;
-	rwlock_t		tb6_lock;
+	spinlock_t		tb6_lock;
 	struct fib6_node	tb6_root;
 	struct inet_peer_base	tb6_peers;
 	unsigned int		flags;
@@ -325,7 +369,8 @@ struct fib6_node *fib6_lookup(struct fib6_node *root,
 
 struct fib6_node *fib6_locate(struct fib6_node *root,
 			      const struct in6_addr *daddr, int dst_len,
-			      const struct in6_addr *saddr, int src_len);
+			      const struct in6_addr *saddr, int src_len,
+			      bool exact_match);
 
 void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
 		    void *arg);
@@ -358,6 +403,8 @@ void __net_exit fib6_notifier_exit(struct net *net);
 unsigned int fib6_tables_seq_read(struct net *net);
 int fib6_tables_dump(struct net *net, struct notifier_block *nb);
 
+void fib6_update_sernum(struct rt6_info *rt);
+
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 int fib6_rules_init(void);
 void fib6_rules_cleanup(void);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index bee528135cf1..18e442ea93d8 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -96,6 +96,11 @@ int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack);
 int ip6_ins_rt(struct rt6_info *);
 int ip6_del_rt(struct rt6_info *);
 
+void rt6_flush_exceptions(struct rt6_info *rt);
+int rt6_remove_exception_rt(struct rt6_info *rt);
+void rt6_age_exceptions(struct rt6_info *rt, struct fib6_gc_args *gc_args,
+			unsigned long now);
+
 static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
 				      const struct in6_addr *daddr,
 				      unsigned int prefs,
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 1a7f7e424320..f80524396c06 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -122,9 +122,6 @@ struct fib_info {
 #define fib_rtt fib_metrics->metrics[RTAX_RTT-1]
 #define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1]
 	int			fib_nhs;
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-	int			fib_weight;
-#endif
 	struct rcu_head		rcu;
 	struct fib_nh		fib_nh[0];
 #define fib_dev		fib_nh[0].nh_dev
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index eb2321a13506..24628f6b09bf 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -259,7 +259,8 @@ int ip_tunnel_get_iflink(const struct net_device *dev);
 int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 		       struct rtnl_link_ops *ops, char *devname);
 
-void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops);
+void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id,
+			   struct rtnl_link_ops *ops);
 
 void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		    const struct iphdr *tnl_params, const u8 protocol);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 6eac5cf8f1e6..fb6d67012de6 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -51,6 +51,46 @@
 #define IPV6_DEFAULT_HOPLIMIT   64
 #define IPV6_DEFAULT_MCASTHOPS	1
 
+/* Limits on Hop-by-Hop and Destination options.
+ *
+ * Per RFC8200 there is no limit on the maximum number or lengths of options in
+ * Hop-by-Hop or Destination options other then the packet must fit in an MTU.
+ * We allow configurable limits in order to mitigate potential denial of
+ * service attacks.
+ *
+ * There are three limits that may be set:
+ *   - Limit the number of options in a Hop-by-Hop or Destination options
+ *     extension header
+ *   - Limit the byte length of a Hop-by-Hop or Destination options extension
+ *     header
+ *   - Disallow unknown options
+ *
+ * The limits are expressed in corresponding sysctls:
+ *
+ * ipv6.sysctl.max_dst_opts_cnt
+ * ipv6.sysctl.max_hbh_opts_cnt
+ * ipv6.sysctl.max_dst_opts_len
+ * ipv6.sysctl.max_hbh_opts_len
+ *
+ * max_*_opts_cnt is the number of TLVs that are allowed for Destination
+ * options or Hop-by-Hop options. If the number is less than zero then unknown
+ * TLVs are disallowed and the number of known options that are allowed is the
+ * absolute value. Setting the value to INT_MAX indicates no limit.
+ *
+ * max_*_opts_len is the length limit in bytes of a Destination or
+ * Hop-by-Hop options extension header. Setting the value to INT_MAX
+ * indicates no length limit.
+ *
+ * If a limit is exceeded when processing an extension header the packet is
+ * silently discarded.
+ */
+
+/* Default limits for Hop-by-Hop and Destination options */
+#define IP6_DEFAULT_MAX_DST_OPTS_CNT	 8
+#define IP6_DEFAULT_MAX_HBH_OPTS_CNT	 8
+#define IP6_DEFAULT_MAX_DST_OPTS_LEN	 INT_MAX /* No limit */
+#define IP6_DEFAULT_MAX_HBH_OPTS_LEN	 INT_MAX /* No limit */
+
 /*
  *	Addr type
  *	
@@ -300,8 +340,8 @@ static inline void fl6_sock_release(struct ip6_flowlabel *fl)
 
 void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info);
 
-int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
-			       struct icmp6hdr *thdr, int len);
+void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
+				struct icmp6hdr *thdr, int len);
 
 int ip6_ra_control(struct sock *sk, int sel);
 
diff --git a/include/net/llc_c_ac.h b/include/net/llc_c_ac.h
index f3be818e73c1..e766300b3e99 100644
--- a/include/net/llc_c_ac.h
+++ b/include/net/llc_c_ac.h
@@ -171,10 +171,10 @@ int llc_conn_ac_rst_sendack_flag(struct sock *sk, struct sk_buff *skb);
 int llc_conn_ac_send_i_rsp_as_ack(struct sock *sk, struct sk_buff *skb);
 int llc_conn_ac_send_i_as_ack(struct sock *sk, struct sk_buff *skb);
 
-void llc_conn_busy_tmr_cb(unsigned long timeout_data);
-void llc_conn_pf_cycle_tmr_cb(unsigned long timeout_data);
-void llc_conn_ack_tmr_cb(unsigned long timeout_data);
-void llc_conn_rej_tmr_cb(unsigned long timeout_data);
+void llc_conn_busy_tmr_cb(struct timer_list *t);
+void llc_conn_pf_cycle_tmr_cb(struct timer_list *t);
+void llc_conn_ack_tmr_cb(struct timer_list *t);
+void llc_conn_rej_tmr_cb(struct timer_list *t);
 
 void llc_conn_set_p_flag(struct sock *sk, u8 value);
 #endif /* LLC_C_AC_H */
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 885690fa39c8..cc9073e45be9 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -5441,8 +5441,14 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid,
  */
 void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn);
 
+/**
+ * ieee80211_manage_rx_ba_offl - helper to queue an RX BA work
+ * @vif: &struct ieee80211_vif pointer from the add_interface callback
+ * @addr: station mac address
+ * @tid: the rx tid
+ */
 void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, const u8 *addr,
-				 unsigned int bit);
+				 unsigned int tid);
 
 /**
  * ieee80211_start_rx_ba_session_offl - start a Rx BA session
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index a964366a7ef5..e421f86af043 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -191,8 +191,8 @@ struct neigh_hash_table {
 
 struct neigh_table {
 	int			family;
-	int			entry_size;
-	int			key_len;
+	unsigned int		entry_size;
+	unsigned int		key_len;
 	__be16			protocol;
 	__u32			(*hash)(const void *pkey,
 					const struct net_device *dev,
diff --git a/include/net/netevent.h b/include/net/netevent.h
index f728d9cad170..40e7bab68490 100644
--- a/include/net/netevent.h
+++ b/include/net/netevent.h
@@ -26,6 +26,7 @@ enum netevent_notif_type {
 	NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */
 	NETEVENT_REDIRECT,	   /* arg is struct netevent_redirect ptr */
 	NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */
+	NETEVENT_MULTIPATH_HASH_UPDATE, /* arg is struct net ptr */
 };
 
 int register_netevent_notifier(struct notifier_block *nb);
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 8fcff2837484..379550f8124a 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -37,6 +37,8 @@ struct inet_timewait_death_row {
 	int			sysctl_max_tw_buckets;
 };
 
+struct tcp_fastopen_context;
+
 struct netns_ipv4 {
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header	*forw_hdr;
@@ -53,6 +55,7 @@ struct netns_ipv4 {
 	struct fib_table __rcu	*fib_main;
 	struct fib_table __rcu	*fib_default;
 #endif
+	bool			fib_has_custom_local_routes;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	int			fib_num_tclassid_users;
 #endif
@@ -126,8 +129,40 @@ struct netns_ipv4 {
 	int sysctl_tcp_sack;
 	int sysctl_tcp_window_scaling;
 	int sysctl_tcp_timestamps;
+	int sysctl_tcp_early_retrans;
+	int sysctl_tcp_recovery;
+	int sysctl_tcp_thin_linear_timeouts;
+	int sysctl_tcp_slow_start_after_idle;
+	int sysctl_tcp_retrans_collapse;
+	int sysctl_tcp_stdurg;
+	int sysctl_tcp_rfc1337;
+	int sysctl_tcp_abort_on_overflow;
+	int sysctl_tcp_fack;
+	int sysctl_tcp_max_reordering;
+	int sysctl_tcp_dsack;
+	int sysctl_tcp_app_win;
+	int sysctl_tcp_adv_win_scale;
+	int sysctl_tcp_frto;
+	int sysctl_tcp_nometrics_save;
+	int sysctl_tcp_moderate_rcvbuf;
+	int sysctl_tcp_tso_win_divisor;
+	int sysctl_tcp_workaround_signed_windows;
+	int sysctl_tcp_limit_output_bytes;
+	int sysctl_tcp_challenge_ack_limit;
+	int sysctl_tcp_min_tso_segs;
+	int sysctl_tcp_min_rtt_wlen;
+	int sysctl_tcp_autocorking;
+	int sysctl_tcp_invalid_ratelimit;
+	int sysctl_tcp_pacing_ss_ratio;
+	int sysctl_tcp_pacing_ca_ratio;
 	struct inet_timewait_death_row tcp_death_row;
 	int sysctl_max_syn_backlog;
+	int sysctl_tcp_fastopen;
+	struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
+	spinlock_t tcp_fastopen_ctx_lock;
+	unsigned int sysctl_tcp_fastopen_blackhole_timeout;
+	atomic_t tfo_active_disable_times;
+	unsigned long tfo_active_disable_stamp;
 
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	int sysctl_udp_l3mdev_accept;
@@ -163,6 +198,9 @@ struct netns_ipv4 {
 	struct fib_notifier_ops	*notifier_ops;
 	unsigned int	fib_seq;	/* protected by rtnl_mutex */
 
+	struct fib_notifier_ops	*ipmr_notifier_ops;
+	unsigned int	ipmr_seq;	/* protected by rtnl_mutex */
+
 	atomic_t	rt_genid;
 };
 #endif
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index dc825a5ddd7f..987cc4569cb8 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -38,6 +38,10 @@ struct netns_sysctl_ipv6 {
 	int idgen_delay;
 	int flowlabel_state_ranges;
 	int flowlabel_reflect;
+	int max_dst_opts_cnt;
+	int max_hbh_opts_cnt;
+	int max_dst_opts_len;
+	int max_hbh_opts_len;
 };
 
 struct netns_ipv6 {
@@ -90,6 +94,11 @@ struct netns_ipv6 {
 	atomic_t		fib6_sernum;
 	struct seg6_pernet_data *seg6_data;
 	struct fib_notifier_ops	*notifier_ops;
+	struct {
+		struct hlist_head head;
+		spinlock_t	lock;
+		u32		seq;
+	} ip6addrlbl_table;
 };
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h
index 039cc29cb4a8..51e1a2a45d02 100644
--- a/include/net/phonet/phonet.h
+++ b/include/net/phonet/phonet.h
@@ -108,8 +108,10 @@ struct phonet_protocol {
 	int			sock_type;
 };
 
-int phonet_proto_register(unsigned int protocol, struct phonet_protocol *pp);
-void phonet_proto_unregister(unsigned int protocol, struct phonet_protocol *pp);
+int phonet_proto_register(unsigned int protocol,
+		const struct phonet_protocol *pp);
+void phonet_proto_unregister(unsigned int protocol,
+		const struct phonet_protocol *pp);
 
 int phonet_sysctl_init(void);
 void phonet_sysctl_exit(void);
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 70ca2437740e..98fef3221227 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -19,6 +19,19 @@ struct tcf_walker {
 int register_tcf_proto_ops(struct tcf_proto_ops *ops);
 int unregister_tcf_proto_ops(struct tcf_proto_ops *ops);
 
+enum tcf_block_binder_type {
+	TCF_BLOCK_BINDER_TYPE_UNSPEC,
+	TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
+	TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS,
+};
+
+struct tcf_block_ext_info {
+	enum tcf_block_binder_type binder_type;
+	tcf_chain_head_change_t *chain_head_change;
+	void *chain_head_change_priv;
+};
+
+struct tcf_block_cb;
 bool tcf_queue_work(struct work_struct *work);
 
 #ifdef CONFIG_NET_CLS
@@ -26,15 +39,52 @@ struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
 				bool create);
 void tcf_chain_put(struct tcf_chain *chain);
 int tcf_block_get(struct tcf_block **p_block,
-		  struct tcf_proto __rcu **p_filter_chain);
+		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q);
+int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
+		      struct tcf_block_ext_info *ei);
 void tcf_block_put(struct tcf_block *block);
+void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
+		       struct tcf_block_ext_info *ei);
+
+static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
+{
+	return block->q;
+}
+
+static inline struct net_device *tcf_block_dev(struct tcf_block *block)
+{
+	return tcf_block_q(block)->dev_queue->dev;
+}
+
+void *tcf_block_cb_priv(struct tcf_block_cb *block_cb);
+struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
+					 tc_setup_cb_t *cb, void *cb_ident);
+void tcf_block_cb_incref(struct tcf_block_cb *block_cb);
+unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb);
+struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
+					     tc_setup_cb_t *cb, void *cb_ident,
+					     void *cb_priv);
+int tcf_block_cb_register(struct tcf_block *block,
+			  tc_setup_cb_t *cb, void *cb_ident,
+			  void *cb_priv);
+void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb);
+void tcf_block_cb_unregister(struct tcf_block *block,
+			     tc_setup_cb_t *cb, void *cb_ident);
+
 int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		 struct tcf_result *res, bool compat_mode);
 
 #else
 static inline
 int tcf_block_get(struct tcf_block **p_block,
-		  struct tcf_proto __rcu **p_filter_chain)
+		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q)
+{
+	return 0;
+}
+
+static inline
+int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
+		      struct tcf_block_ext_info *ei)
 {
 	return 0;
 }
@@ -43,6 +93,86 @@ static inline void tcf_block_put(struct tcf_block *block)
 {
 }
 
+static inline
+void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
+		       struct tcf_block_ext_info *ei)
+{
+}
+
+static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
+{
+	return NULL;
+}
+
+static inline struct net_device *tcf_block_dev(struct tcf_block *block)
+{
+	return NULL;
+}
+
+static inline
+int tc_setup_cb_block_register(struct tcf_block *block, tc_setup_cb_t *cb,
+			       void *cb_priv)
+{
+	return 0;
+}
+
+static inline
+void tc_setup_cb_block_unregister(struct tcf_block *block, tc_setup_cb_t *cb,
+				  void *cb_priv)
+{
+}
+
+static inline
+void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
+{
+	return NULL;
+}
+
+static inline
+struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
+					 tc_setup_cb_t *cb, void *cb_ident)
+{
+	return NULL;
+}
+
+static inline
+void tcf_block_cb_incref(struct tcf_block_cb *block_cb)
+{
+}
+
+static inline
+unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
+{
+	return 0;
+}
+
+static inline
+struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
+					     tc_setup_cb_t *cb, void *cb_ident,
+					     void *cb_priv)
+{
+	return NULL;
+}
+
+static inline
+int tcf_block_cb_register(struct tcf_block *block,
+			  tc_setup_cb_t *cb, void *cb_ident,
+			  void *cb_priv)
+{
+	return 0;
+}
+
+static inline
+void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb)
+{
+}
+
+static inline
+void tcf_block_cb_unregister(struct tcf_block *block,
+			     tc_setup_cb_t *cb, void *cb_ident)
+{
+}
+
 static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			       struct tcf_result *res, bool compat_mode)
 {
@@ -57,36 +187,43 @@ __cls_set_class(unsigned long *clp, unsigned long cl)
 }
 
 static inline unsigned long
-cls_set_class(struct tcf_proto *tp, unsigned long *clp, 
-	unsigned long cl)
+cls_set_class(struct Qdisc *q, unsigned long *clp, unsigned long cl)
 {
 	unsigned long old_cl;
-	
-	tcf_tree_lock(tp);
+
+	sch_tree_lock(q);
 	old_cl = __cls_set_class(clp, cl);
-	tcf_tree_unlock(tp);
- 
+	sch_tree_unlock(q);
 	return old_cl;
 }
 
 static inline void
 tcf_bind_filter(struct tcf_proto *tp, struct tcf_result *r, unsigned long base)
 {
+	struct Qdisc *q = tp->chain->block->q;
 	unsigned long cl;
 
-	cl = tp->q->ops->cl_ops->bind_tcf(tp->q, base, r->classid);
-	cl = cls_set_class(tp, &r->class, cl);
+	/* Check q as it is not set for shared blocks. In that case,
+	 * setting class is not supported.
+	 */
+	if (!q)
+		return;
+	cl = q->ops->cl_ops->bind_tcf(q, base, r->classid);
+	cl = cls_set_class(q, &r->class, cl);
 	if (cl)
-		tp->q->ops->cl_ops->unbind_tcf(tp->q, cl);
+		q->ops->cl_ops->unbind_tcf(q, cl);
 }
 
 static inline void
 tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r)
 {
+	struct Qdisc *q = tp->chain->block->q;
 	unsigned long cl;
 
+	if (!q)
+		return;
 	if ((cl = __cls_set_class(&r->class, 0)) != 0)
-		tp->q->ops->cl_ops->unbind_tcf(tp->q, cl);
+		q->ops->cl_ops->unbind_tcf(q, cl);
 }
 
 struct tcf_exts {
@@ -208,8 +345,6 @@ void tcf_exts_destroy(struct tcf_exts *exts);
 void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src);
 int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts);
 int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts);
-int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts,
-		     struct net_device **hw_dev);
 
 /**
  * struct tcf_pkt_info - packet information
@@ -409,11 +544,24 @@ tcf_match_indev(struct sk_buff *skb, int ifindex)
 }
 #endif /* CONFIG_NET_CLS_IND */
 
+int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
+		     enum tc_setup_type type, void *type_data, bool err_stop);
+
+enum tc_block_command {
+	TC_BLOCK_BIND,
+	TC_BLOCK_UNBIND,
+};
+
+struct tc_block_offload {
+	enum tc_block_command command;
+	enum tcf_block_binder_type binder_type;
+	struct tcf_block *block;
+};
+
 struct tc_cls_common_offload {
 	u32 chain_index;
 	__be16 protocol;
 	u32 prio;
-	u32 classid;
 };
 
 static inline void
@@ -423,7 +571,6 @@ tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common,
 	cls_common->chain_index = tp->chain->index;
 	cls_common->protocol = tp->protocol;
 	cls_common->prio = tp->prio;
-	cls_common->classid = tp->classid;
 }
 
 struct tc_cls_u32_knode {
@@ -463,11 +610,7 @@ struct tc_cls_u32_offload {
 
 static inline bool tc_can_offload(const struct net_device *dev)
 {
-	if (!(dev->features & NETIF_F_HW_TC))
-		return false;
-	if (!dev->netdev_ops->ndo_setup_tc)
-		return false;
-	return true;
+	return dev->features & NETIF_F_HW_TC;
 }
 
 static inline bool tc_skip_hw(u32 flags)
@@ -475,13 +618,6 @@ static inline bool tc_skip_hw(u32 flags)
 	return (flags & TCA_CLS_FLAGS_SKIP_HW) ? true : false;
 }
 
-static inline bool tc_should_offload(const struct net_device *dev, u32 flags)
-{
-	if (tc_skip_hw(flags))
-		return false;
-	return tc_can_offload(dev);
-}
-
 static inline bool tc_skip_sw(u32 flags)
 {
 	return (flags & TCA_CLS_FLAGS_SKIP_SW) ? true : false;
@@ -518,7 +654,7 @@ struct tc_cls_flower_offload {
 	struct fl_flow_key *mask;
 	struct fl_flow_key *key;
 	struct tcf_exts *exts;
-	bool egress_dev;
+	u32 classid;
 };
 
 enum tc_matchall_command {
@@ -550,6 +686,15 @@ struct tc_cls_bpf_offload {
 	u32 gen_flags;
 };
 
+struct tc_mqprio_qopt_offload {
+	/* struct tc_mqprio_qopt must always be the first element */
+	struct tc_mqprio_qopt qopt;
+	u16 mode;
+	u16 shaper;
+	u32 flags;
+	u64 min_rate[TC_QOPT_MAX_QUEUE];
+	u64 max_rate[TC_QOPT_MAX_QUEUE];
+};
 
 /* This structure holds cookie structure that is passed from user
  * to the kernel for actions and classifiers
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index b3869f97d37d..d1f413f06c72 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -5,7 +5,9 @@
 #include <linux/jiffies.h>
 #include <linux/ktime.h>
 #include <linux/if_vlan.h>
+#include <linux/netdevice.h>
 #include <net/sch_generic.h>
+#include <net/net_namespace.h>
 #include <uapi/linux/pkt_sched.h>
 
 #define DEFAULT_TX_QUEUE_LEN	1000
@@ -134,17 +136,18 @@ static inline unsigned int psched_mtu(const struct net_device *dev)
 	return dev->mtu + dev->hard_header_len;
 }
 
-static inline bool is_classid_clsact_ingress(u32 classid)
+static inline struct net *qdisc_net(struct Qdisc *q)
 {
-	/* This also returns true for ingress qdisc */
-	return TC_H_MAJ(classid) == TC_H_MAJ(TC_H_CLSACT) &&
-	       TC_H_MIN(classid) != TC_H_MIN(TC_H_MIN_EGRESS);
+	return dev_net(q->dev_queue->dev);
 }
 
-static inline bool is_classid_clsact_egress(u32 classid)
-{
-	return TC_H_MAJ(classid) == TC_H_MAJ(TC_H_CLSACT) &&
-	       TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_EGRESS);
-}
+struct tc_cbs_qopt_offload {
+	u8 enable;
+	s32 queue;
+	s32 hicredit;
+	s32 locredit;
+	s32 idleslope;
+	s32 sendslope;
+};
 
 #endif
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 23e22054aa60..347015515a7d 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -150,6 +150,8 @@ struct fastopen_queue {
 	spinlock_t	lock;
 	int		qlen;		/* # of pending (TCP_SYN_RECV) reqs */
 	int		max_qlen;	/* != 0 iff TFO is currently enabled */
+
+	struct tcp_fastopen_context __rcu *ctx; /* cipher context for cookie */
 };
 
 /** struct request_sock_queue - queue of request_socks
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 7b938fbeebc1..ead018744ff5 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -94,9 +94,6 @@ struct rtnl_link_ops {
 
 	int			slave_maxtype;
 	const struct nla_policy	*slave_policy;
-	int			(*slave_validate)(struct nlattr *tb[],
-						  struct nlattr *data[],
-						  struct netlink_ext_ack *extack);
 	int			(*slave_changelink)(struct net_device *dev,
 						    struct net_device *slave_dev,
 						    struct nlattr *tb[],
@@ -155,8 +152,6 @@ struct rtnl_af_ops {
 	size_t			(*get_stats_af_size)(const struct net_device *dev);
 };
 
-void __rtnl_af_unregister(struct rtnl_af_ops *ops);
-
 void rtnl_af_register(struct rtnl_af_ops *ops);
 void rtnl_af_unregister(struct rtnl_af_ops *ops);
 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 236bfe5b2ffe..65d0d25f2648 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -95,7 +95,6 @@ struct Qdisc {
 	unsigned long		state;
 	struct Qdisc            *next_sched;
 	struct sk_buff		*skb_bad_txq;
-	struct rcu_head		rcu_head;
 	int			padded;
 	refcount_t		refcnt;
 
@@ -262,9 +261,12 @@ struct qdisc_skb_cb {
 	unsigned char		data[QDISC_CB_PRIV_LEN];
 };
 
+typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
+
 struct tcf_chain {
 	struct tcf_proto __rcu *filter_chain;
-	struct tcf_proto __rcu **p_filter_chain;
+	tcf_chain_head_change_t *chain_head_change;
+	void *chain_head_change_priv;
 	struct list_head list;
 	struct tcf_block *block;
 	u32 index; /* chain index */
@@ -273,6 +275,9 @@ struct tcf_chain {
 
 struct tcf_block {
 	struct list_head chain_list;
+	struct net *net;
+	struct Qdisc *q;
+	struct list_head cb_list;
 	struct work_struct work;
 };
 
@@ -361,9 +366,6 @@ static inline void sch_tree_unlock(const struct Qdisc *q)
 	spin_unlock_bh(qdisc_root_sleeping_lock(q));
 }
 
-#define tcf_tree_lock(tp)	sch_tree_lock((tp)->q)
-#define tcf_tree_unlock(tp)	sch_tree_unlock((tp)->q)
-
 extern struct Qdisc noop_qdisc;
 extern struct Qdisc_ops noop_qdisc_ops;
 extern struct Qdisc_ops pfifo_fast_ops;
@@ -413,6 +415,13 @@ qdisc_class_find(const struct Qdisc_class_hash *hash, u32 id)
 	return NULL;
 }
 
+static inline int tc_classid_to_hwtc(struct net_device *dev, u32 classid)
+{
+	u32 hwtc = TC_H_MIN(classid) - TC_H_MIN_PRIORITY;
+
+	return (hwtc < netdev_get_num_tc(dev)) ? hwtc : -EINVAL;
+}
+
 int qdisc_class_hash_init(struct Qdisc_class_hash *);
 void qdisc_class_hash_insert(struct Qdisc_class_hash *,
 			     struct Qdisc_class_common *);
@@ -896,4 +905,36 @@ static inline void psched_ratecfg_getrate(struct tc_ratespec *res,
 	res->linklayer = (r->linklayer & TC_LINKLAYER_MASK);
 }
 
+/* Mini Qdisc serves for specific needs of ingress/clsact Qdisc.
+ * The fast path only needs to access filter list and to update stats
+ */
+struct mini_Qdisc {
+	struct tcf_proto *filter_list;
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct gnet_stats_queue	__percpu *cpu_qstats;
+	struct rcu_head rcu;
+};
+
+static inline void mini_qdisc_bstats_cpu_update(struct mini_Qdisc *miniq,
+						const struct sk_buff *skb)
+{
+	bstats_cpu_update(this_cpu_ptr(miniq->cpu_bstats), skb);
+}
+
+static inline void mini_qdisc_qstats_cpu_drop(struct mini_Qdisc *miniq)
+{
+	this_cpu_inc(miniq->cpu_qstats->drops);
+}
+
+struct mini_Qdisc_pair {
+	struct mini_Qdisc miniq1;
+	struct mini_Qdisc miniq2;
+	struct mini_Qdisc __rcu **p_miniq;
+};
+
+void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
+			  struct tcf_proto *tp_head);
+void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
+			  struct mini_Qdisc __rcu **p_miniq);
+
 #endif
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 88233cf8b8d4..70fb397f65b0 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -72,7 +72,7 @@ typedef enum sctp_disposition (sctp_state_fn_t) (
 					const union sctp_subtype type,
 					void *arg,
 					struct sctp_cmd_seq *commands);
-typedef void (sctp_timer_event_t) (unsigned long);
+typedef void (sctp_timer_event_t) (struct timer_list *);
 struct sctp_sm_table_entry {
 	sctp_state_fn_t *fn;
 	const char *name;
@@ -314,10 +314,10 @@ int sctp_do_sm(struct net *net, enum sctp_event event_type,
 	       void *event_arg, gfp_t gfp);
 
 /* 2nd level prototypes */
-void sctp_generate_t3_rtx_event(unsigned long peer);
-void sctp_generate_heartbeat_event(unsigned long peer);
-void sctp_generate_reconf_event(unsigned long peer);
-void sctp_generate_proto_unreach_event(unsigned long peer);
+void sctp_generate_t3_rtx_event(struct timer_list *t);
+void sctp_generate_heartbeat_event(struct timer_list *t);
+void sctp_generate_reconf_event(struct timer_list *t);
+void sctp_generate_proto_unreach_event(struct timer_list *t);
 
 void sctp_ootb_pkt_free(struct sctp_packet *packet);
 
diff --git a/include/net/sctp/stream_sched.h b/include/net/sctp/stream_sched.h
new file mode 100644
index 000000000000..c676550a4c7d
--- /dev/null
+++ b/include/net/sctp/stream_sched.h
@@ -0,0 +1,72 @@
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * These are definitions used by the stream schedulers, defined in RFC
+ * draft ndata (https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-11)
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation  is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresses:
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *   Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#ifndef __sctp_stream_sched_h__
+#define __sctp_stream_sched_h__
+
+struct sctp_sched_ops {
+	/* Property handling for a given stream */
+	int (*set)(struct sctp_stream *stream, __u16 sid, __u16 value,
+		   gfp_t gfp);
+	int (*get)(struct sctp_stream *stream, __u16 sid, __u16 *value);
+
+	/* Init the specific scheduler */
+	int (*init)(struct sctp_stream *stream);
+	/* Init a stream */
+	int (*init_sid)(struct sctp_stream *stream, __u16 sid, gfp_t gfp);
+	/* Frees the entire thing */
+	void (*free)(struct sctp_stream *stream);
+
+	/* Enqueue a chunk */
+	void (*enqueue)(struct sctp_outq *q, struct sctp_datamsg *msg);
+	/* Dequeue a chunk */
+	struct sctp_chunk *(*dequeue)(struct sctp_outq *q);
+	/* Called only if the chunk fit the packet */
+	void (*dequeue_done)(struct sctp_outq *q, struct sctp_chunk *chunk);
+	/* Sched all chunks already enqueued */
+	void (*sched_all)(struct sctp_stream *steam);
+	/* Unched all chunks already enqueued */
+	void (*unsched_all)(struct sctp_stream *steam);
+};
+
+int sctp_sched_set_sched(struct sctp_association *asoc,
+			 enum sctp_sched_type sched);
+int sctp_sched_get_sched(struct sctp_association *asoc);
+int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid,
+			 __u16 value, gfp_t gfp);
+int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid,
+			 __u16 *value);
+void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch);
+
+void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch);
+int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp);
+struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream);
+
+#endif /* __sctp_stream_sched_h__ */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 0477945de1a3..16f949eef52f 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -380,6 +380,7 @@ struct sctp_sender_hb_info {
 
 int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 		     gfp_t gfp);
+int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid);
 void sctp_stream_free(struct sctp_stream *stream);
 void sctp_stream_clear(struct sctp_stream *stream);
 void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new);
@@ -529,8 +530,12 @@ struct sctp_chunk {
 	/* How many times this chunk have been sent, for prsctp RTX policy */
 	int sent_count;
 
-	/* This is our link to the per-transport transmitted list.  */
-	struct list_head transmitted_list;
+	union {
+		/* This is our link to the per-transport transmitted list.  */
+		struct list_head transmitted_list;
+		/* List in specific stream outq */
+		struct list_head stream_list;
+	};
 
 	/* This field is used by chunks that hold fragmented data.
 	 * For the first fragment this is the list that holds the rest of
@@ -640,6 +645,11 @@ void sctp_init_addrs(struct sctp_chunk *, union sctp_addr *,
 		     union sctp_addr *);
 const union sctp_addr *sctp_source(const struct sctp_chunk *chunk);
 
+static inline __u16 sctp_chunk_stream_no(struct sctp_chunk *ch)
+{
+	return ntohs(ch->subh.data_hdr->stream);
+}
+
 enum {
 	SCTP_ADDR_NEW,		/* new address added to assoc/ep */
 	SCTP_ADDR_SRC,		/* address can be used as source */
@@ -1012,6 +1022,9 @@ struct sctp_outq {
 	/* Data pending that has never been transmitted.  */
 	struct list_head out_chunk_list;
 
+	/* Stream scheduler being used */
+	struct sctp_sched_ops *sched;
+
 	unsigned int out_qlen;	/* Total length of queued data chunks. */
 
 	/* Error of send failed, may used in SCTP_SEND_FAILED event. */
@@ -1315,11 +1328,37 @@ struct sctp_inithdr_host {
 	__u32 initial_tsn;
 };
 
+struct sctp_stream_priorities {
+	/* List of priorities scheduled */
+	struct list_head prio_sched;
+	/* List of streams scheduled */
+	struct list_head active;
+	/* The next stream stream in line */
+	struct sctp_stream_out_ext *next;
+	__u16 prio;
+};
+
+struct sctp_stream_out_ext {
+	__u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
+	__u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
+	struct list_head outq; /* chunks enqueued by this stream */
+	union {
+		struct {
+			/* Scheduled streams list */
+			struct list_head prio_list;
+			struct sctp_stream_priorities *prio_head;
+		};
+		/* Fields used by RR scheduler */
+		struct {
+			struct list_head rr_list;
+		};
+	};
+};
+
 struct sctp_stream_out {
 	__u16	ssn;
 	__u8	state;
-	__u64	abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
-	__u64	abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
+	struct sctp_stream_out_ext *ext;
 };
 
 struct sctp_stream_in {
@@ -1331,6 +1370,22 @@ struct sctp_stream {
 	struct sctp_stream_in *in;
 	__u16 outcnt;
 	__u16 incnt;
+	/* Current stream being sent, if any */
+	struct sctp_stream_out *out_curr;
+	union {
+		/* Fields used by priority scheduler */
+		struct {
+			/* List of priorities scheduled */
+			struct list_head prio_list;
+		};
+		/* Fields used by RR scheduler */
+		struct {
+			/* List of streams scheduled */
+			struct list_head rr_list;
+			/* The next stream stream in line */
+			struct sctp_stream_out_ext *rr_next;
+		};
+	};
 };
 
 #define SCTP_STREAM_CLOSED		0x00
diff --git a/include/net/sock.h b/include/net/sock.h
index a6b9a8d1a6df..6f1be9726e02 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -60,7 +60,7 @@
 #include <linux/sched.h>
 #include <linux/wait.h>
 #include <linux/cgroup-defs.h>
-
+#include <linux/rbtree.h>
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>
 #include <linux/poll.h>
@@ -397,7 +397,10 @@ struct sock {
 	int			sk_wmem_queued;
 	refcount_t		sk_wmem_alloc;
 	unsigned long		sk_tsq_flags;
-	struct sk_buff		*sk_send_head;
+	union {
+		struct sk_buff	*sk_send_head;
+		struct rb_root	tcp_rtx_queue;
+	};
 	struct sk_buff_head	sk_write_queue;
 	__s32			sk_peek_off;
 	int			sk_write_pending;
@@ -734,10 +737,10 @@ static inline void sk_add_bind_node(struct sock *sk,
  *
  */
 #define sk_for_each_entry_offset_rcu(tpos, pos, head, offset)		       \
-	for (pos = rcu_dereference((head)->first);			       \
+	for (pos = rcu_dereference(hlist_first_rcu(head));		       \
 	     pos != NULL &&						       \
 		({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;});       \
-	     pos = rcu_dereference(pos->next))
+	     pos = rcu_dereference(hlist_next_rcu(pos)))
 
 static inline struct user_namespace *sk_user_ns(struct sock *sk)
 {
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index d767b7991887..d756fbe46625 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -51,6 +51,7 @@ enum switchdev_attr_id {
 	SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME,
 	SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING,
 	SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED,
+	SWITCHDEV_ATTR_ID_BRIDGE_MROUTER,
 };
 
 struct switchdev_attr {
diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h
index e82d93346b63..ef8dd0db70ce 100644
--- a/include/net/tc_act/tc_gact.h
+++ b/include/net/tc_act/tc_gact.h
@@ -34,6 +34,11 @@ static inline bool __is_tcf_gact_act(const struct tc_action *a, int act,
 	return false;
 }
 
+static inline bool is_tcf_gact_ok(const struct tc_action *a)
+{
+	return __is_tcf_gact_act(a, TC_ACT_OK, false);
+}
+
 static inline bool is_tcf_gact_shot(const struct tc_action *a)
 {
 	return __is_tcf_gact_act(a, TC_ACT_SHOT, false);
diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h
index ba6667125bcd..86d13b01b39d 100644
--- a/include/net/tc_act/tc_ife.h
+++ b/include/net/tc_act/tc_ife.h
@@ -7,12 +7,18 @@
 #include <linux/rtnetlink.h>
 #include <linux/module.h>
 
-struct tcf_ife_info {
-	struct tc_action common;
+struct tcf_ife_params {
 	u8 eth_dst[ETH_ALEN];
 	u8 eth_src[ETH_ALEN];
 	u16 eth_type;
 	u16 flags;
+
+	struct rcu_head rcu;
+};
+
+struct tcf_ife_info {
+	struct tc_action common;
+	struct tcf_ife_params __rcu *params;
 	/* list of metaids allowed */
 	struct list_head metalist;
 };
@@ -41,7 +47,7 @@ struct tcf_meta_ops {
 	struct module	*owner;
 };
 
-#define MODULE_ALIAS_IFE_META(metan)   MODULE_ALIAS("ifemeta" __stringify_1(metan))
+#define MODULE_ALIAS_IFE_META(metan)   MODULE_ALIAS("ife-meta-" metan)
 
 int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi);
 int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi);
diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h
index b2dbbfaefd22..21d253c9a8c6 100644
--- a/include/net/tc_act/tc_mirred.h
+++ b/include/net/tc_act/tc_mirred.h
@@ -11,6 +11,7 @@ struct tcf_mirred {
 	int			tcfm_ifindex;
 	bool			tcfm_mac_header_xmit;
 	struct net_device __rcu	*tcfm_dev;
+	struct net		*net;
 	struct list_head	tcfm_list;
 };
 #define to_mirred(a) ((struct tcf_mirred *)a)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e6d0002a1b0b..c2bf2a822b10 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -45,9 +45,6 @@
 
 #include <linux/seq_file.h>
 #include <linux/memcontrol.h>
-
-#include <linux/bpf.h>
-#include <linux/filter.h>
 #include <linux/bpf-cgroup.h>
 
 extern struct inet_hashinfo tcp_hashinfo;
@@ -191,6 +188,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
  * experimental options. See draft-ietf-tcpm-experimental-options-00.txt
  */
 #define TCPOPT_FASTOPEN_MAGIC	0xF989
+#define TCPOPT_SMC_MAGIC	0xE2D4C3D9
 
 /*
  *     TCP option lengths
@@ -203,6 +201,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOLEN_MD5SIG         18
 #define TCPOLEN_FASTOPEN_BASE  2
 #define TCPOLEN_EXP_FASTOPEN_BASE  4
+#define TCPOLEN_EXP_SMC_BASE   6
 
 /* But this is what stacks really send out. */
 #define TCPOLEN_TSTAMP_ALIGNED		12
@@ -213,6 +212,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOLEN_SACK_PERBLOCK		8
 #define TCPOLEN_MD5SIG_ALIGNED		20
 #define TCPOLEN_MSS_ALIGNED		4
+#define TCPOLEN_EXP_SMC_BASE_ALIGNED	8
 
 /* Flags in tp->nonagle */
 #define TCP_NAGLE_OFF		1	/* Nagle's algo is disabled */
@@ -240,41 +240,12 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 
 
 /* sysctl variables for tcp */
-extern int sysctl_tcp_fastopen;
-extern int sysctl_tcp_retrans_collapse;
-extern int sysctl_tcp_stdurg;
-extern int sysctl_tcp_rfc1337;
-extern int sysctl_tcp_abort_on_overflow;
 extern int sysctl_tcp_max_orphans;
-extern int sysctl_tcp_fack;
-extern int sysctl_tcp_reordering;
-extern int sysctl_tcp_max_reordering;
-extern int sysctl_tcp_dsack;
 extern long sysctl_tcp_mem[3];
 extern int sysctl_tcp_wmem[3];
 extern int sysctl_tcp_rmem[3];
-extern int sysctl_tcp_app_win;
-extern int sysctl_tcp_adv_win_scale;
-extern int sysctl_tcp_frto;
-extern int sysctl_tcp_nometrics_save;
-extern int sysctl_tcp_moderate_rcvbuf;
-extern int sysctl_tcp_tso_win_divisor;
-extern int sysctl_tcp_workaround_signed_windows;
-extern int sysctl_tcp_slow_start_after_idle;
-extern int sysctl_tcp_thin_linear_timeouts;
-extern int sysctl_tcp_thin_dupack;
-extern int sysctl_tcp_early_retrans;
-extern int sysctl_tcp_recovery;
-#define TCP_RACK_LOSS_DETECTION  0x1 /* Use RACK to detect losses */
 
-extern int sysctl_tcp_limit_output_bytes;
-extern int sysctl_tcp_challenge_ack_limit;
-extern int sysctl_tcp_min_tso_segs;
-extern int sysctl_tcp_min_rtt_wlen;
-extern int sysctl_tcp_autocorking;
-extern int sysctl_tcp_invalid_ratelimit;
-extern int sysctl_tcp_pacing_ss_ratio;
-extern int sysctl_tcp_pacing_ca_ratio;
+#define TCP_RACK_LOSS_DETECTION  0x1 /* Use RACK to detect losses */
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
@@ -417,6 +388,7 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
 void tcp_disable_fack(struct tcp_sock *tp);
 void tcp_close(struct sock *sk, long timeout);
 void tcp_init_sock(struct sock *sk);
+void tcp_init_transfer(struct sock *sk, int bpf_op);
 unsigned int tcp_poll(struct file *file, struct socket *sock,
 		      struct poll_table_struct *wait);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
@@ -551,7 +523,13 @@ void tcp_xmit_retransmit_queue(struct sock *);
 void tcp_simple_retransmit(struct sock *);
 void tcp_enter_recovery(struct sock *sk, bool ece_ack);
 int tcp_trim_head(struct sock *, struct sk_buff *, u32);
-int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int, gfp_t);
+enum tcp_queue {
+	TCP_FRAG_IN_WRITE_QUEUE,
+	TCP_FRAG_IN_RTX_QUEUE,
+};
+int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
+		 struct sk_buff *skb, u32 len,
+		 unsigned int mss_now, gfp_t gfp);
 
 void tcp_send_probe0(struct sock *);
 void tcp_send_partial(struct sock *);
@@ -796,12 +774,6 @@ struct tcp_skb_cb {
 			u16	tcp_gso_segs;
 			u16	tcp_gso_size;
 		};
-
-		/* Used to stash the receive timestamp while this skb is in the
-		 * out of order queue, as skb->tstamp is overwritten by the
-		 * rbnode.
-		 */
-		ktime_t		swtstamp;
 	};
 	__u8		tcp_flags;	/* TCP header flags. (tcp[13])	*/
 
@@ -1309,7 +1281,7 @@ static inline void tcp_slow_start_after_idle_check(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	s32 delta;
 
-	if (!sysctl_tcp_slow_start_after_idle || tp->packets_out ||
+	if (!sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle || tp->packets_out ||
 	    ca_ops->cong_control)
 		return;
 	delta = tcp_jiffies32 - tp->lsndtime;
@@ -1318,13 +1290,14 @@ static inline void tcp_slow_start_after_idle_check(struct sock *sk)
 }
 
 /* Determine a window scaling and initial window to offer. */
-void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd,
+void tcp_select_initial_window(const struct sock *sk, int __space,
+			       __u32 mss, __u32 *rcv_wnd,
 			       __u32 *window_clamp, int wscale_ok,
 			       __u8 *rcv_wscale, __u32 init_rcv_wnd);
 
-static inline int tcp_win_from_space(int space)
+static inline int tcp_win_from_space(const struct sock *sk, int space)
 {
-	int tcp_adv_win_scale = sysctl_tcp_adv_win_scale;
+	int tcp_adv_win_scale = sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale;
 
 	return tcp_adv_win_scale <= 0 ?
 		(space>>(-tcp_adv_win_scale)) :
@@ -1334,13 +1307,13 @@ static inline int tcp_win_from_space(int space)
 /* Note: caller must be prepared to deal with negative returns */
 static inline int tcp_space(const struct sock *sk)
 {
-	return tcp_win_from_space(sk->sk_rcvbuf -
+	return tcp_win_from_space(sk, sk->sk_rcvbuf -
 				  atomic_read(&sk->sk_rmem_alloc));
 }
 
 static inline int tcp_full_space(const struct sock *sk)
 {
-	return tcp_win_from_space(sk->sk_rcvbuf);
+	return tcp_win_from_space(sk, sk->sk_rcvbuf);
 }
 
 extern void tcp_openreq_init_rwin(struct request_sock *req,
@@ -1561,14 +1534,16 @@ struct tcp_fastopen_request {
 	int				copied;	/* queued in tcp_connect() */
 };
 void tcp_free_fastopen_req(struct tcp_sock *tp);
-
-extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
-int tcp_fastopen_reset_cipher(void *key, unsigned int len);
+void tcp_fastopen_destroy_cipher(struct sock *sk);
+void tcp_fastopen_ctx_destroy(struct net *net);
+int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
+			      void *key, unsigned int len);
 void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      struct request_sock *req,
-			      struct tcp_fastopen_cookie *foc);
-void tcp_fastopen_init_key_once(bool publish);
+			      struct tcp_fastopen_cookie *foc,
+			      const struct dst_entry *dst);
+void tcp_fastopen_init_key_once(struct net *net);
 bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 			     struct tcp_fastopen_cookie *cookie);
 bool tcp_fastopen_defer_connect(struct sock *sk, int *err);
@@ -1601,52 +1576,46 @@ enum tcp_chrono {
 void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type);
 void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type);
 
-/* write queue abstraction */
-static inline void tcp_write_queue_purge(struct sock *sk)
+/* This helper is needed, because skb->tcp_tsorted_anchor uses
+ * the same memory storage than skb->destructor/_skb_refdst
+ */
+static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb)
 {
-	struct sk_buff *skb;
-
-	tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
-	while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL)
-		sk_wmem_free_skb(sk, skb);
-	sk_mem_reclaim(sk);
-	tcp_clear_all_retrans_hints(tcp_sk(sk));
+	skb->destructor = NULL;
+	skb->_skb_refdst = 0UL;
 }
 
-static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
-{
-	return skb_peek(&sk->sk_write_queue);
+#define tcp_skb_tsorted_save(skb) {		\
+	unsigned long _save = skb->_skb_refdst;	\
+	skb->_skb_refdst = 0UL;
+
+#define tcp_skb_tsorted_restore(skb)		\
+	skb->_skb_refdst = _save;		\
 }
 
-static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk)
+void tcp_write_queue_purge(struct sock *sk);
+
+static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk)
 {
-	return skb_peek_tail(&sk->sk_write_queue);
+	return skb_rb_first(&sk->tcp_rtx_queue);
 }
 
-static inline struct sk_buff *tcp_write_queue_next(const struct sock *sk,
-						   const struct sk_buff *skb)
+static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
 {
-	return skb_queue_next(&sk->sk_write_queue, skb);
+	return skb_peek(&sk->sk_write_queue);
 }
 
-static inline struct sk_buff *tcp_write_queue_prev(const struct sock *sk,
-						   const struct sk_buff *skb)
+static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk)
 {
-	return skb_queue_prev(&sk->sk_write_queue, skb);
+	return skb_peek_tail(&sk->sk_write_queue);
 }
 
-#define tcp_for_write_queue(skb, sk)					\
-	skb_queue_walk(&(sk)->sk_write_queue, skb)
-
-#define tcp_for_write_queue_from(skb, sk)				\
-	skb_queue_walk_from(&(sk)->sk_write_queue, skb)
-
 #define tcp_for_write_queue_from_safe(skb, tmp, sk)			\
 	skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp)
 
 static inline struct sk_buff *tcp_send_head(const struct sock *sk)
 {
-	return sk->sk_send_head;
+	return skb_peek(&sk->sk_write_queue);
 }
 
 static inline bool tcp_skb_is_last(const struct sock *sk,
@@ -1655,29 +1624,30 @@ static inline bool tcp_skb_is_last(const struct sock *sk,
 	return skb_queue_is_last(&sk->sk_write_queue, skb);
 }
 
-static inline void tcp_advance_send_head(struct sock *sk, const struct sk_buff *skb)
+static inline bool tcp_write_queue_empty(const struct sock *sk)
 {
-	if (tcp_skb_is_last(sk, skb))
-		sk->sk_send_head = NULL;
-	else
-		sk->sk_send_head = tcp_write_queue_next(sk, skb);
+	return skb_queue_empty(&sk->sk_write_queue);
+}
+
+static inline bool tcp_rtx_queue_empty(const struct sock *sk)
+{
+	return RB_EMPTY_ROOT(&sk->tcp_rtx_queue);
+}
+
+static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk)
+{
+	return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk);
 }
 
 static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked)
 {
-	if (sk->sk_send_head == skb_unlinked) {
-		sk->sk_send_head = NULL;
+	if (tcp_write_queue_empty(sk))
 		tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
-	}
+
 	if (tcp_sk(sk)->highest_sack == skb_unlinked)
 		tcp_sk(sk)->highest_sack = NULL;
 }
 
-static inline void tcp_init_send_head(struct sock *sk)
-{
-	sk->sk_send_head = NULL;
-}
-
 static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_queue_tail(&sk->sk_write_queue, skb);
@@ -1688,8 +1658,7 @@ static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb
 	__tcp_add_write_queue_tail(sk, skb);
 
 	/* Queue it, remembering where we must start sending. */
-	if (sk->sk_send_head == NULL) {
-		sk->sk_send_head = skb;
+	if (sk->sk_write_queue.next == skb) {
 		tcp_chrono_start(sk, TCP_CHRONO_BUSY);
 
 		if (tcp_sk(sk)->highest_sack == NULL)
@@ -1697,38 +1666,33 @@ static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb
 	}
 }
 
-static inline void __tcp_add_write_queue_head(struct sock *sk, struct sk_buff *skb)
-{
-	__skb_queue_head(&sk->sk_write_queue, skb);
-}
-
-/* Insert buff after skb on the write queue of sk.  */
-static inline void tcp_insert_write_queue_after(struct sk_buff *skb,
-						struct sk_buff *buff,
-						struct sock *sk)
-{
-	__skb_queue_after(&sk->sk_write_queue, skb, buff);
-}
-
 /* Insert new before skb on the write queue of sk.  */
 static inline void tcp_insert_write_queue_before(struct sk_buff *new,
 						  struct sk_buff *skb,
 						  struct sock *sk)
 {
 	__skb_queue_before(&sk->sk_write_queue, skb, new);
-
-	if (sk->sk_send_head == skb)
-		sk->sk_send_head = new;
 }
 
 static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk)
 {
+	tcp_skb_tsorted_anchor_cleanup(skb);
 	__skb_unlink(skb, &sk->sk_write_queue);
 }
 
-static inline bool tcp_write_queue_empty(struct sock *sk)
+void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb);
+
+static inline void tcp_rtx_queue_unlink(struct sk_buff *skb, struct sock *sk)
 {
-	return skb_queue_empty(&sk->sk_write_queue);
+	tcp_skb_tsorted_anchor_cleanup(skb);
+	rb_erase(&skb->rbnode, &sk->tcp_rtx_queue);
+}
+
+static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct sock *sk)
+{
+	list_del(&skb->tcp_tsorted_anchor);
+	tcp_rtx_queue_unlink(skb, sk);
+	sk_wmem_free_skb(sk, skb);
 }
 
 static inline void tcp_push_pending_frames(struct sock *sk)
@@ -1757,8 +1721,9 @@ static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp)
 
 static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb)
 {
-	tcp_sk(sk)->highest_sack = tcp_skb_is_last(sk, skb) ? NULL :
-						tcp_write_queue_next(sk, skb);
+	struct sk_buff *next = skb_rb_next(skb);
+
+	tcp_sk(sk)->highest_sack = next ?: tcp_send_head(sk);
 }
 
 static inline struct sk_buff *tcp_highest_sack(struct sock *sk)
@@ -1768,7 +1733,9 @@ static inline struct sk_buff *tcp_highest_sack(struct sock *sk)
 
 static inline void tcp_highest_sack_reset(struct sock *sk)
 {
-	tcp_sk(sk)->highest_sack = tcp_write_queue_head(sk);
+	struct sk_buff *skb = tcp_rtx_queue_head(sk);
+
+	tcp_sk(sk)->highest_sack = skb ?: tcp_send_head(sk);
 }
 
 /* Called when old skb is about to be deleted and replaced by new skb */
@@ -1938,7 +1905,7 @@ extern void tcp_rack_reo_timeout(struct sock *sk);
 /* At how many usecs into the future should the RTO fire? */
 static inline s64 tcp_rto_delta_us(const struct sock *sk)
 {
-	const struct sk_buff *skb = tcp_write_queue_head(sk);
+	const struct sk_buff *skb = tcp_rtx_queue_head(sk);
 	u32 rto = inet_csk(sk)->icsk_rto;
 	u64 rto_time_stamp_us = skb->skb_mstamp + jiffies_to_usecs(rto);
 
@@ -2115,4 +2082,8 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
 {
 	return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN) == 1);
 }
+
+#if IS_ENABLED(CONFIG_SMC)
+extern struct static_key_false tcp_have_smc;
+#endif
 #endif	/* _TCP_H */
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index e015e164bac0..dc28a98ce97c 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1765,22 +1765,22 @@ static inline int xfrm_acquire_is_on(struct net *net)
 }
 #endif
 
-static inline int aead_len(struct xfrm_algo_aead *alg)
+static inline unsigned int aead_len(struct xfrm_algo_aead *alg)
 {
 	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
 }
 
-static inline int xfrm_alg_len(const struct xfrm_algo *alg)
+static inline unsigned int xfrm_alg_len(const struct xfrm_algo *alg)
 {
 	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
 }
 
-static inline int xfrm_alg_auth_len(const struct xfrm_algo_auth *alg)
+static inline unsigned int xfrm_alg_auth_len(const struct xfrm_algo_auth *alg)
 {
 	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
 }
 
-static inline int xfrm_replay_state_esn_len(struct xfrm_replay_state_esn *replay_esn)
+static inline unsigned int xfrm_replay_state_esn_len(struct xfrm_replay_state_esn *replay_esn)
 {
 	return sizeof(*replay_esn) + replay_esn->bmp_len * sizeof(__u32);
 }
diff --git a/include/trace/events/bpf.h b/include/trace/events/bpf.h
index cc749d7099fb..150185647e6b 100644
--- a/include/trace/events/bpf.h
+++ b/include/trace/events/bpf.h
@@ -5,6 +5,9 @@
 #if !defined(_TRACE_BPF_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_BPF_H
 
+/* These are only used within the BPF_SYSCALL code */
+#ifdef CONFIG_BPF_SYSCALL
+
 #include <linux/filter.h>
 #include <linux/bpf.h>
 #include <linux/fs.h>
@@ -346,7 +349,7 @@ TRACE_EVENT(bpf_map_next_key,
 		  __print_hex(__get_dynamic_array(nxt), __entry->key_len),
 		  __entry->key_trunc ? " ..." : "")
 );
-
+#endif /* CONFIG_BPF_SYSCALL */
 #endif /* _TRACE_BPF_H */
 
 #include <trace/define_trace.h>
diff --git a/include/trace/events/fib6.h b/include/trace/events/fib6.h
index d46e24702765..7e8d48a81b91 100644
--- a/include/trace/events/fib6.h
+++ b/include/trace/events/fib6.h
@@ -13,9 +13,9 @@
 TRACE_EVENT(fib6_table_lookup,
 
 	TP_PROTO(const struct net *net, const struct rt6_info *rt,
-		 u32 tb_id, const struct flowi6 *flp),
+		 struct fib6_table *table, const struct flowi6 *flp),
 
-	TP_ARGS(net, rt, tb_id, flp),
+	TP_ARGS(net, rt, table, flp),
 
 	TP_STRUCT__entry(
 		__field(	u32,	tb_id		)
@@ -35,7 +35,7 @@ TRACE_EVENT(fib6_table_lookup,
 	TP_fast_assign(
 		struct in6_addr *in6;
 
-		__entry->tb_id = tb_id;
+		__entry->tb_id = table->tb6_id;
 		__entry->oif = flp->flowi6_oif;
 		__entry->iif = flp->flowi6_iif;
 		__entry->tos = ip6_tclass(flp->flowlabel);
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
new file mode 100644
index 000000000000..07cccca6cbf1
--- /dev/null
+++ b/include/trace/events/tcp.h
@@ -0,0 +1,299 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM tcp
+
+#if !defined(_TRACE_TCP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_TCP_H
+
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/tracepoint.h>
+#include <net/ipv6.h>
+
+#define tcp_state_name(state)	{ state, #state }
+#define show_tcp_state_name(val)			\
+	__print_symbolic(val,				\
+		tcp_state_name(TCP_ESTABLISHED),	\
+		tcp_state_name(TCP_SYN_SENT),		\
+		tcp_state_name(TCP_SYN_RECV),		\
+		tcp_state_name(TCP_FIN_WAIT1),		\
+		tcp_state_name(TCP_FIN_WAIT2),		\
+		tcp_state_name(TCP_TIME_WAIT),		\
+		tcp_state_name(TCP_CLOSE),		\
+		tcp_state_name(TCP_CLOSE_WAIT),		\
+		tcp_state_name(TCP_LAST_ACK),		\
+		tcp_state_name(TCP_LISTEN),		\
+		tcp_state_name(TCP_CLOSING),		\
+		tcp_state_name(TCP_NEW_SYN_RECV))
+
+/*
+ * tcp event with arguments sk and skb
+ *
+ * Note: this class requires a valid sk pointer; while skb pointer could
+ *       be NULL.
+ */
+DECLARE_EVENT_CLASS(tcp_event_sk_skb,
+
+	TP_PROTO(const struct sock *sk, const struct sk_buff *skb),
+
+	TP_ARGS(sk, skb),
+
+	TP_STRUCT__entry(
+		__field(const void *, skbaddr)
+		__field(const void *, skaddr)
+		__field(__u16, sport)
+		__field(__u16, dport)
+		__array(__u8, saddr, 4)
+		__array(__u8, daddr, 4)
+		__array(__u8, saddr_v6, 16)
+		__array(__u8, daddr_v6, 16)
+	),
+
+	TP_fast_assign(
+		struct inet_sock *inet = inet_sk(sk);
+		struct in6_addr *pin6;
+		__be32 *p32;
+
+		__entry->skbaddr = skb;
+		__entry->skaddr = sk;
+
+		__entry->sport = ntohs(inet->inet_sport);
+		__entry->dport = ntohs(inet->inet_dport);
+
+		p32 = (__be32 *) __entry->saddr;
+		*p32 = inet->inet_saddr;
+
+		p32 = (__be32 *) __entry->daddr;
+		*p32 =  inet->inet_daddr;
+
+#if IS_ENABLED(CONFIG_IPV6)
+		if (sk->sk_family == AF_INET6) {
+			pin6 = (struct in6_addr *)__entry->saddr_v6;
+			*pin6 = sk->sk_v6_rcv_saddr;
+			pin6 = (struct in6_addr *)__entry->daddr_v6;
+			*pin6 = sk->sk_v6_daddr;
+		} else
+#endif
+		{
+			pin6 = (struct in6_addr *)__entry->saddr_v6;
+			ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
+			pin6 = (struct in6_addr *)__entry->daddr_v6;
+			ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);
+		}
+	),
+
+	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c",
+		  __entry->sport, __entry->dport, __entry->saddr, __entry->daddr,
+		  __entry->saddr_v6, __entry->daddr_v6)
+);
+
+DEFINE_EVENT(tcp_event_sk_skb, tcp_retransmit_skb,
+
+	TP_PROTO(const struct sock *sk, const struct sk_buff *skb),
+
+	TP_ARGS(sk, skb)
+);
+
+/*
+ * skb of trace_tcp_send_reset is the skb that caused RST. In case of
+ * active reset, skb should be NULL
+ */
+DEFINE_EVENT(tcp_event_sk_skb, tcp_send_reset,
+
+	TP_PROTO(const struct sock *sk, const struct sk_buff *skb),
+
+	TP_ARGS(sk, skb)
+);
+
+/*
+ * tcp event with arguments sk
+ *
+ * Note: this class requires a valid sk pointer.
+ */
+DECLARE_EVENT_CLASS(tcp_event_sk,
+
+	TP_PROTO(const struct sock *sk),
+
+	TP_ARGS(sk),
+
+	TP_STRUCT__entry(
+		__field(const void *, skaddr)
+		__field(__u16, sport)
+		__field(__u16, dport)
+		__array(__u8, saddr, 4)
+		__array(__u8, daddr, 4)
+		__array(__u8, saddr_v6, 16)
+		__array(__u8, daddr_v6, 16)
+	),
+
+	TP_fast_assign(
+		struct inet_sock *inet = inet_sk(sk);
+		struct in6_addr *pin6;
+		__be32 *p32;
+
+		__entry->skaddr = sk;
+
+		__entry->sport = ntohs(inet->inet_sport);
+		__entry->dport = ntohs(inet->inet_dport);
+
+		p32 = (__be32 *) __entry->saddr;
+		*p32 = inet->inet_saddr;
+
+		p32 = (__be32 *) __entry->daddr;
+		*p32 =  inet->inet_daddr;
+
+#if IS_ENABLED(CONFIG_IPV6)
+		if (sk->sk_family == AF_INET6) {
+			pin6 = (struct in6_addr *)__entry->saddr_v6;
+			*pin6 = sk->sk_v6_rcv_saddr;
+			pin6 = (struct in6_addr *)__entry->daddr_v6;
+			*pin6 = sk->sk_v6_daddr;
+		} else
+#endif
+		{
+			pin6 = (struct in6_addr *)__entry->saddr_v6;
+			ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
+			pin6 = (struct in6_addr *)__entry->daddr_v6;
+			ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);
+		}
+	),
+
+	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c",
+		  __entry->sport, __entry->dport,
+		  __entry->saddr, __entry->daddr,
+		  __entry->saddr_v6, __entry->daddr_v6)
+);
+
+DEFINE_EVENT(tcp_event_sk, tcp_receive_reset,
+
+	TP_PROTO(const struct sock *sk),
+
+	TP_ARGS(sk)
+);
+
+DEFINE_EVENT(tcp_event_sk, tcp_destroy_sock,
+
+	TP_PROTO(const struct sock *sk),
+
+	TP_ARGS(sk)
+);
+
+TRACE_EVENT(tcp_set_state,
+
+	TP_PROTO(const struct sock *sk, const int oldstate, const int newstate),
+
+	TP_ARGS(sk, oldstate, newstate),
+
+	TP_STRUCT__entry(
+		__field(const void *, skaddr)
+		__field(int, oldstate)
+		__field(int, newstate)
+		__field(__u16, sport)
+		__field(__u16, dport)
+		__array(__u8, saddr, 4)
+		__array(__u8, daddr, 4)
+		__array(__u8, saddr_v6, 16)
+		__array(__u8, daddr_v6, 16)
+	),
+
+	TP_fast_assign(
+		struct inet_sock *inet = inet_sk(sk);
+		struct in6_addr *pin6;
+		__be32 *p32;
+
+		__entry->skaddr = sk;
+		__entry->oldstate = oldstate;
+		__entry->newstate = newstate;
+
+		__entry->sport = ntohs(inet->inet_sport);
+		__entry->dport = ntohs(inet->inet_dport);
+
+		p32 = (__be32 *) __entry->saddr;
+		*p32 = inet->inet_saddr;
+
+		p32 = (__be32 *) __entry->daddr;
+		*p32 =  inet->inet_daddr;
+
+#if IS_ENABLED(CONFIG_IPV6)
+		if (sk->sk_family == AF_INET6) {
+			pin6 = (struct in6_addr *)__entry->saddr_v6;
+			*pin6 = sk->sk_v6_rcv_saddr;
+			pin6 = (struct in6_addr *)__entry->daddr_v6;
+			*pin6 = sk->sk_v6_daddr;
+		} else
+#endif
+		{
+			pin6 = (struct in6_addr *)__entry->saddr_v6;
+			ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
+			pin6 = (struct in6_addr *)__entry->daddr_v6;
+			ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);
+		}
+	),
+
+	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s",
+		  __entry->sport, __entry->dport,
+		  __entry->saddr, __entry->daddr,
+		  __entry->saddr_v6, __entry->daddr_v6,
+		  show_tcp_state_name(__entry->oldstate),
+		  show_tcp_state_name(__entry->newstate))
+);
+
+TRACE_EVENT(tcp_retransmit_synack,
+
+	TP_PROTO(const struct sock *sk, const struct request_sock *req),
+
+	TP_ARGS(sk, req),
+
+	TP_STRUCT__entry(
+		__field(const void *, skaddr)
+		__field(const void *, req)
+		__field(__u16, sport)
+		__field(__u16, dport)
+		__array(__u8, saddr, 4)
+		__array(__u8, daddr, 4)
+		__array(__u8, saddr_v6, 16)
+		__array(__u8, daddr_v6, 16)
+	),
+
+	TP_fast_assign(
+		struct inet_request_sock *ireq = inet_rsk(req);
+		struct in6_addr *pin6;
+		__be32 *p32;
+
+		__entry->skaddr = sk;
+		__entry->req = req;
+
+		__entry->sport = ireq->ir_num;
+		__entry->dport = ntohs(ireq->ir_rmt_port);
+
+		p32 = (__be32 *) __entry->saddr;
+		*p32 = ireq->ir_loc_addr;
+
+		p32 = (__be32 *) __entry->daddr;
+		*p32 = ireq->ir_rmt_addr;
+
+#if IS_ENABLED(CONFIG_IPV6)
+		if (sk->sk_family == AF_INET6) {
+			pin6 = (struct in6_addr *)__entry->saddr_v6;
+			*pin6 = ireq->ir_v6_loc_addr;
+			pin6 = (struct in6_addr *)__entry->daddr_v6;
+			*pin6 = ireq->ir_v6_rmt_addr;
+		} else
+#endif
+		{
+			pin6 = (struct in6_addr *)__entry->saddr_v6;
+			ipv6_addr_set_v4mapped(ireq->ir_loc_addr, pin6);
+			pin6 = (struct in6_addr *)__entry->daddr_v6;
+			ipv6_addr_set_v4mapped(ireq->ir_rmt_addr, pin6);
+		}
+	),
+
+	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c",
+		  __entry->sport, __entry->dport,
+		  __entry->saddr, __entry->daddr,
+		  __entry->saddr_v6, __entry->daddr_v6)
+);
+
+#endif /* _TRACE_TCP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index 810e94160c12..4cd0f05d0113 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -137,14 +137,90 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
 		  __entry->map_id, __entry->map_index)
 );
 
+#define devmap_ifindex(fwd, map)				\
+	(!fwd ? 0 :						\
+	 (!map ? 0 :						\
+	  ((map->map_type == BPF_MAP_TYPE_DEVMAP) ?		\
+	   ((struct net_device *)fwd)->ifindex : 0)))
+
 #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx)		\
-	 trace_xdp_redirect_map(dev, xdp, fwd ? fwd->ifindex : 0,	\
+	 trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map),	\
 				0, map, idx)
 
 #define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err)	\
-	 trace_xdp_redirect_map_err(dev, xdp, fwd ? fwd->ifindex : 0,	\
+	 trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map),	\
 				    err, map, idx)
 
+TRACE_EVENT(xdp_cpumap_kthread,
+
+	TP_PROTO(int map_id, unsigned int processed,  unsigned int drops,
+		 int sched),
+
+	TP_ARGS(map_id, processed, drops, sched),
+
+	TP_STRUCT__entry(
+		__field(int, map_id)
+		__field(u32, act)
+		__field(int, cpu)
+		__field(unsigned int, drops)
+		__field(unsigned int, processed)
+		__field(int, sched)
+	),
+
+	TP_fast_assign(
+		__entry->map_id		= map_id;
+		__entry->act		= XDP_REDIRECT;
+		__entry->cpu		= smp_processor_id();
+		__entry->drops		= drops;
+		__entry->processed	= processed;
+		__entry->sched	= sched;
+	),
+
+	TP_printk("kthread"
+		  " cpu=%d map_id=%d action=%s"
+		  " processed=%u drops=%u"
+		  " sched=%d",
+		  __entry->cpu, __entry->map_id,
+		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
+		  __entry->processed, __entry->drops,
+		  __entry->sched)
+);
+
+TRACE_EVENT(xdp_cpumap_enqueue,
+
+	TP_PROTO(int map_id, unsigned int processed,  unsigned int drops,
+		 int to_cpu),
+
+	TP_ARGS(map_id, processed, drops, to_cpu),
+
+	TP_STRUCT__entry(
+		__field(int, map_id)
+		__field(u32, act)
+		__field(int, cpu)
+		__field(unsigned int, drops)
+		__field(unsigned int, processed)
+		__field(int, to_cpu)
+	),
+
+	TP_fast_assign(
+		__entry->map_id		= map_id;
+		__entry->act		= XDP_REDIRECT;
+		__entry->cpu		= smp_processor_id();
+		__entry->drops		= drops;
+		__entry->processed	= processed;
+		__entry->to_cpu		= to_cpu;
+	),
+
+	TP_printk("enqueue"
+		  " cpu=%d map_id=%d action=%s"
+		  " processed=%u drops=%u"
+		  " to_cpu=%d",
+		  __entry->cpu, __entry->map_id,
+		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
+		  __entry->processed, __entry->drops,
+		  __entry->to_cpu)
+);
+
 #endif /* _TRACE_XDP_H */
 
 #include <trace/define_trace.h>
diff --git a/include/trace/perf.h b/include/trace/perf.h
index e4b249821684..dbc6c74defc3 100644
--- a/include/trace/perf.h
+++ b/include/trace/perf.h
@@ -35,7 +35,6 @@ perf_trace_##call(void *__data, proto)					\
 	struct trace_event_call *event_call = __data;			\
 	struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\
 	struct trace_event_raw_##call *entry;				\
-	struct bpf_prog *prog = event_call->prog;			\
 	struct pt_regs *__regs;						\
 	u64 __count = 1;						\
 	struct task_struct *__task = NULL;				\
@@ -47,8 +46,9 @@ perf_trace_##call(void *__data, proto)					\
 	__data_size = trace_event_get_offsets_##call(&__data_offsets, args); \
 									\
 	head = this_cpu_ptr(event_call->perf_events);			\
-	if (!prog && __builtin_constant_p(!__task) && !__task &&	\
-				hlist_empty(head))			\
+	if (!bpf_prog_array_valid(event_call) &&			\
+	    __builtin_constant_p(!__task) && !__task &&			\
+	    hlist_empty(head))						\
 		return;							\
 									\
 	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
index a83ddb7b63db..efd641c8a5d6 100644
--- a/include/uapi/linux/batman_adv.h
+++ b/include/uapi/linux/batman_adv.h
@@ -24,20 +24,6 @@
 
 /**
  * enum batadv_tt_client_flags - TT client specific flags
- * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table
- * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and the new
- *  update telling its new real location has not been received/sent yet
- * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi interface.
- *  This information is used by the "AP Isolation" feature
- * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This
- *  information is used by the Extended Isolation feature
- * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from the table
- * @BATADV_TT_CLIENT_NEW: this client has been added to the local table but has
- *  not been announced yet
- * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it is kept
- *  in the table for one more originator interval for consistency purposes
- * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be part of
- *  the network but no nnode has already announced it
  *
  * Bits from 0 to 7 are called _remote flags_ because they are sent on the wire.
  * Bits from 8 to 15 are called _local flags_ because they are used for local
@@ -48,160 +34,385 @@
  * in the TT CRC computation.
  */
 enum batadv_tt_client_flags {
+	/**
+	 * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table
+	 */
 	BATADV_TT_CLIENT_DEL     = (1 << 0),
+
+	/**
+	 * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and
+	 * the new update telling its new real location has not been
+	 * received/sent yet
+	 */
 	BATADV_TT_CLIENT_ROAM    = (1 << 1),
+
+	/**
+	 * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi
+	 * interface. This information is used by the "AP Isolation" feature
+	 */
 	BATADV_TT_CLIENT_WIFI    = (1 << 4),
+
+	/**
+	 * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This
+	 * information is used by the Extended Isolation feature
+	 */
 	BATADV_TT_CLIENT_ISOLA	 = (1 << 5),
+
+	/**
+	 * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from
+	 * the table
+	 */
 	BATADV_TT_CLIENT_NOPURGE = (1 << 8),
+
+	/**
+	 * @BATADV_TT_CLIENT_NEW: this client has been added to the local table
+	 * but has not been announced yet
+	 */
 	BATADV_TT_CLIENT_NEW     = (1 << 9),
+
+	/**
+	 * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it
+	 * is kept in the table for one more originator interval for consistency
+	 * purposes
+	 */
 	BATADV_TT_CLIENT_PENDING = (1 << 10),
+
+	/**
+	 * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be
+	 * part of the network but no nnode has already announced it
+	 */
 	BATADV_TT_CLIENT_TEMP	 = (1 << 11),
 };
 
 /**
  * enum batadv_nl_attrs - batman-adv netlink attributes
- *
- * @BATADV_ATTR_UNSPEC: unspecified attribute to catch errors
- * @BATADV_ATTR_VERSION: batman-adv version string
- * @BATADV_ATTR_ALGO_NAME: name of routing algorithm
- * @BATADV_ATTR_MESH_IFINDEX: index of the batman-adv interface
- * @BATADV_ATTR_MESH_IFNAME: name of the batman-adv interface
- * @BATADV_ATTR_MESH_ADDRESS: mac address of the batman-adv interface
- * @BATADV_ATTR_HARD_IFINDEX: index of the non-batman-adv interface
- * @BATADV_ATTR_HARD_IFNAME: name of the non-batman-adv interface
- * @BATADV_ATTR_HARD_ADDRESS: mac address of the non-batman-adv interface
- * @BATADV_ATTR_ORIG_ADDRESS: originator mac address
- * @BATADV_ATTR_TPMETER_RESULT: result of run (see batadv_tp_meter_status)
- * @BATADV_ATTR_TPMETER_TEST_TIME: time (msec) the run took
- * @BATADV_ATTR_TPMETER_BYTES: amount of acked bytes during run
- * @BATADV_ATTR_TPMETER_COOKIE: session cookie to match tp_meter session
- * @BATADV_ATTR_PAD: attribute used for padding for 64-bit alignment
- * @BATADV_ATTR_ACTIVE: Flag indicating if the hard interface is active
- * @BATADV_ATTR_TT_ADDRESS: Client MAC address
- * @BATADV_ATTR_TT_TTVN: Translation table version
- * @BATADV_ATTR_TT_LAST_TTVN: Previous translation table version
- * @BATADV_ATTR_TT_CRC32: CRC32 over translation table
- * @BATADV_ATTR_TT_VID: VLAN ID
- * @BATADV_ATTR_TT_FLAGS: Translation table client flags
- * @BATADV_ATTR_FLAG_BEST: Flags indicating entry is the best
- * @BATADV_ATTR_LAST_SEEN_MSECS: Time in milliseconds since last seen
- * @BATADV_ATTR_NEIGH_ADDRESS: Neighbour MAC address
- * @BATADV_ATTR_TQ: TQ to neighbour
- * @BATADV_ATTR_THROUGHPUT: Estimated throughput to Neighbour
- * @BATADV_ATTR_BANDWIDTH_UP: Reported uplink bandwidth
- * @BATADV_ATTR_BANDWIDTH_DOWN: Reported downlink bandwidth
- * @BATADV_ATTR_ROUTER: Gateway router MAC address
- * @BATADV_ATTR_BLA_OWN: Flag indicating own originator
- * @BATADV_ATTR_BLA_ADDRESS: Bridge loop avoidance claim MAC address
- * @BATADV_ATTR_BLA_VID: BLA VLAN ID
- * @BATADV_ATTR_BLA_BACKBONE: BLA gateway originator MAC address
- * @BATADV_ATTR_BLA_CRC: BLA CRC
- * @__BATADV_ATTR_AFTER_LAST: internal use
- * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available
- * @BATADV_ATTR_MAX: highest attribute number currently defined
  */
 enum batadv_nl_attrs {
+	/**
+	 * @BATADV_ATTR_UNSPEC: unspecified attribute to catch errors
+	 */
 	BATADV_ATTR_UNSPEC,
+
+	/**
+	 * @BATADV_ATTR_VERSION: batman-adv version string
+	 */
 	BATADV_ATTR_VERSION,
+
+	/**
+	 * @BATADV_ATTR_ALGO_NAME: name of routing algorithm
+	 */
 	BATADV_ATTR_ALGO_NAME,
+
+	/**
+	 * @BATADV_ATTR_MESH_IFINDEX: index of the batman-adv interface
+	 */
 	BATADV_ATTR_MESH_IFINDEX,
+
+	/**
+	 * @BATADV_ATTR_MESH_IFNAME: name of the batman-adv interface
+	 */
 	BATADV_ATTR_MESH_IFNAME,
+
+	/**
+	 * @BATADV_ATTR_MESH_ADDRESS: mac address of the batman-adv interface
+	 */
 	BATADV_ATTR_MESH_ADDRESS,
+
+	/**
+	 * @BATADV_ATTR_HARD_IFINDEX: index of the non-batman-adv interface
+	 */
 	BATADV_ATTR_HARD_IFINDEX,
+
+	/**
+	 * @BATADV_ATTR_HARD_IFNAME: name of the non-batman-adv interface
+	 */
 	BATADV_ATTR_HARD_IFNAME,
+
+	/**
+	 * @BATADV_ATTR_HARD_ADDRESS: mac address of the non-batman-adv
+	 * interface
+	 */
 	BATADV_ATTR_HARD_ADDRESS,
+
+	/**
+	 * @BATADV_ATTR_ORIG_ADDRESS: originator mac address
+	 */
 	BATADV_ATTR_ORIG_ADDRESS,
+
+	/**
+	 * @BATADV_ATTR_TPMETER_RESULT: result of run (see
+	 * batadv_tp_meter_status)
+	 */
 	BATADV_ATTR_TPMETER_RESULT,
+
+	/**
+	 * @BATADV_ATTR_TPMETER_TEST_TIME: time (msec) the run took
+	 */
 	BATADV_ATTR_TPMETER_TEST_TIME,
+
+	/**
+	 * @BATADV_ATTR_TPMETER_BYTES: amount of acked bytes during run
+	 */
 	BATADV_ATTR_TPMETER_BYTES,
+
+	/**
+	 * @BATADV_ATTR_TPMETER_COOKIE: session cookie to match tp_meter session
+	 */
 	BATADV_ATTR_TPMETER_COOKIE,
+
+	/**
+	 * @BATADV_ATTR_PAD: attribute used for padding for 64-bit alignment
+	 */
 	BATADV_ATTR_PAD,
+
+	/**
+	 * @BATADV_ATTR_ACTIVE: Flag indicating if the hard interface is active
+	 */
 	BATADV_ATTR_ACTIVE,
+
+	/**
+	 * @BATADV_ATTR_TT_ADDRESS: Client MAC address
+	 */
 	BATADV_ATTR_TT_ADDRESS,
+
+	/**
+	 * @BATADV_ATTR_TT_TTVN: Translation table version
+	 */
 	BATADV_ATTR_TT_TTVN,
+
+	/**
+	 * @BATADV_ATTR_TT_LAST_TTVN: Previous translation table version
+	 */
 	BATADV_ATTR_TT_LAST_TTVN,
+
+	/**
+	 * @BATADV_ATTR_TT_CRC32: CRC32 over translation table
+	 */
 	BATADV_ATTR_TT_CRC32,
+
+	/**
+	 * @BATADV_ATTR_TT_VID: VLAN ID
+	 */
 	BATADV_ATTR_TT_VID,
+
+	/**
+	 * @BATADV_ATTR_TT_FLAGS: Translation table client flags
+	 */
 	BATADV_ATTR_TT_FLAGS,
+
+	/**
+	 * @BATADV_ATTR_FLAG_BEST: Flags indicating entry is the best
+	 */
 	BATADV_ATTR_FLAG_BEST,
+
+	/**
+	 * @BATADV_ATTR_LAST_SEEN_MSECS: Time in milliseconds since last seen
+	 */
 	BATADV_ATTR_LAST_SEEN_MSECS,
+
+	/**
+	 * @BATADV_ATTR_NEIGH_ADDRESS: Neighbour MAC address
+	 */
 	BATADV_ATTR_NEIGH_ADDRESS,
+
+	/**
+	 * @BATADV_ATTR_TQ: TQ to neighbour
+	 */
 	BATADV_ATTR_TQ,
+
+	/**
+	 * @BATADV_ATTR_THROUGHPUT: Estimated throughput to Neighbour
+	 */
 	BATADV_ATTR_THROUGHPUT,
+
+	/**
+	 * @BATADV_ATTR_BANDWIDTH_UP: Reported uplink bandwidth
+	 */
 	BATADV_ATTR_BANDWIDTH_UP,
+
+	/**
+	 * @BATADV_ATTR_BANDWIDTH_DOWN: Reported downlink bandwidth
+	 */
 	BATADV_ATTR_BANDWIDTH_DOWN,
+
+	/**
+	 * @BATADV_ATTR_ROUTER: Gateway router MAC address
+	 */
 	BATADV_ATTR_ROUTER,
+
+	/**
+	 * @BATADV_ATTR_BLA_OWN: Flag indicating own originator
+	 */
 	BATADV_ATTR_BLA_OWN,
+
+	/**
+	 * @BATADV_ATTR_BLA_ADDRESS: Bridge loop avoidance claim MAC address
+	 */
 	BATADV_ATTR_BLA_ADDRESS,
+
+	/**
+	 * @BATADV_ATTR_BLA_VID: BLA VLAN ID
+	 */
 	BATADV_ATTR_BLA_VID,
+
+	/**
+	 * @BATADV_ATTR_BLA_BACKBONE: BLA gateway originator MAC address
+	 */
 	BATADV_ATTR_BLA_BACKBONE,
+
+	/**
+	 * @BATADV_ATTR_BLA_CRC: BLA CRC
+	 */
 	BATADV_ATTR_BLA_CRC,
+
 	/* add attributes above here, update the policy in netlink.c */
+
+	/**
+	 * @__BATADV_ATTR_AFTER_LAST: internal use
+	 */
 	__BATADV_ATTR_AFTER_LAST,
+
+	/**
+	 * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available
+	 */
 	NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST,
+
+	/**
+	 * @BATADV_ATTR_MAX: highest attribute number currently defined
+	 */
 	BATADV_ATTR_MAX = __BATADV_ATTR_AFTER_LAST - 1
 };
 
 /**
  * enum batadv_nl_commands - supported batman-adv netlink commands
- *
- * @BATADV_CMD_UNSPEC: unspecified command to catch errors
- * @BATADV_CMD_GET_MESH_INFO: Query basic information about batman-adv device
- * @BATADV_CMD_TP_METER: Start a tp meter session
- * @BATADV_CMD_TP_METER_CANCEL: Cancel a tp meter session
- * @BATADV_CMD_GET_ROUTING_ALGOS: Query the list of routing algorithms.
- * @BATADV_CMD_GET_HARDIFS: Query list of hard interfaces
- * @BATADV_CMD_GET_TRANSTABLE_LOCAL: Query list of local translations
- * @BATADV_CMD_GET_TRANSTABLE_GLOBAL Query list of global translations
- * @BATADV_CMD_GET_ORIGINATORS: Query list of originators
- * @BATADV_CMD_GET_NEIGHBORS: Query list of neighbours
- * @BATADV_CMD_GET_GATEWAYS: Query list of gateways
- * @BATADV_CMD_GET_BLA_CLAIM: Query list of bridge loop avoidance claims
- * @BATADV_CMD_GET_BLA_BACKBONE: Query list of bridge loop avoidance backbones
- * @__BATADV_CMD_AFTER_LAST: internal use
- * @BATADV_CMD_MAX: highest used command number
  */
 enum batadv_nl_commands {
+	/**
+	 * @BATADV_CMD_UNSPEC: unspecified command to catch errors
+	 */
 	BATADV_CMD_UNSPEC,
+
+	/**
+	 * @BATADV_CMD_GET_MESH_INFO: Query basic information about batman-adv
+	 * device
+	 */
 	BATADV_CMD_GET_MESH_INFO,
+
+	/**
+	 * @BATADV_CMD_TP_METER: Start a tp meter session
+	 */
 	BATADV_CMD_TP_METER,
+
+	/**
+	 * @BATADV_CMD_TP_METER_CANCEL: Cancel a tp meter session
+	 */
 	BATADV_CMD_TP_METER_CANCEL,
+
+	/**
+	 * @BATADV_CMD_GET_ROUTING_ALGOS: Query the list of routing algorithms.
+	 */
 	BATADV_CMD_GET_ROUTING_ALGOS,
+
+	/**
+	 * @BATADV_CMD_GET_HARDIFS: Query list of hard interfaces
+	 */
 	BATADV_CMD_GET_HARDIFS,
+
+	/**
+	 * @BATADV_CMD_GET_TRANSTABLE_LOCAL: Query list of local translations
+	 */
 	BATADV_CMD_GET_TRANSTABLE_LOCAL,
+
+	/**
+	 * @BATADV_CMD_GET_TRANSTABLE_GLOBAL: Query list of global translations
+	 */
 	BATADV_CMD_GET_TRANSTABLE_GLOBAL,
+
+	/**
+	 * @BATADV_CMD_GET_ORIGINATORS: Query list of originators
+	 */
 	BATADV_CMD_GET_ORIGINATORS,
+
+	/**
+	 * @BATADV_CMD_GET_NEIGHBORS: Query list of neighbours
+	 */
 	BATADV_CMD_GET_NEIGHBORS,
+
+	/**
+	 * @BATADV_CMD_GET_GATEWAYS: Query list of gateways
+	 */
 	BATADV_CMD_GET_GATEWAYS,
+
+	/**
+	 * @BATADV_CMD_GET_BLA_CLAIM: Query list of bridge loop avoidance claims
+	 */
 	BATADV_CMD_GET_BLA_CLAIM,
+
+	/**
+	 * @BATADV_CMD_GET_BLA_BACKBONE: Query list of bridge loop avoidance
+	 * backbones
+	 */
 	BATADV_CMD_GET_BLA_BACKBONE,
+
 	/* add new commands above here */
+
+	/**
+	 * @__BATADV_CMD_AFTER_LAST: internal use
+	 */
 	__BATADV_CMD_AFTER_LAST,
+
+	/**
+	 * @BATADV_CMD_MAX: highest used command number
+	 */
 	BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1
 };
 
 /**
  * enum batadv_tp_meter_reason - reason of a tp meter test run stop
- * @BATADV_TP_REASON_COMPLETE: sender finished tp run
- * @BATADV_TP_REASON_CANCEL: sender was stopped during run
- * @BATADV_TP_REASON_DST_UNREACHABLE: receiver could not be reached or didn't
- *  answer
- * @BATADV_TP_REASON_RESEND_LIMIT: (unused) sender retry reached limit
- * @BATADV_TP_REASON_ALREADY_ONGOING: test to or from the same node already
- *  ongoing
- * @BATADV_TP_REASON_MEMORY_ERROR: test was stopped due to low memory
- * @BATADV_TP_REASON_CANT_SEND: failed to send via outgoing interface
- * @BATADV_TP_REASON_TOO_MANY: too many ongoing sessions
  */
 enum batadv_tp_meter_reason {
+	/**
+	 * @BATADV_TP_REASON_COMPLETE: sender finished tp run
+	 */
 	BATADV_TP_REASON_COMPLETE		= 3,
+
+	/**
+	 * @BATADV_TP_REASON_CANCEL: sender was stopped during run
+	 */
 	BATADV_TP_REASON_CANCEL			= 4,
+
 	/* error status >= 128 */
+
+	/**
+	 * @BATADV_TP_REASON_DST_UNREACHABLE: receiver could not be reached or
+	 * didn't answer
+	 */
 	BATADV_TP_REASON_DST_UNREACHABLE	= 128,
+
+	/**
+	 * @BATADV_TP_REASON_RESEND_LIMIT: (unused) sender retry reached limit
+	 */
 	BATADV_TP_REASON_RESEND_LIMIT		= 129,
+
+	/**
+	 * @BATADV_TP_REASON_ALREADY_ONGOING: test to or from the same node
+	 * already ongoing
+	 */
 	BATADV_TP_REASON_ALREADY_ONGOING	= 130,
+
+	/**
+	 * @BATADV_TP_REASON_MEMORY_ERROR: test was stopped due to low memory
+	 */
 	BATADV_TP_REASON_MEMORY_ERROR		= 131,
+
+	/**
+	 * @BATADV_TP_REASON_CANT_SEND: failed to send via outgoing interface
+	 */
 	BATADV_TP_REASON_CANT_SEND		= 132,
+
+	/**
+	 * @BATADV_TP_REASON_TOO_MANY: too many ongoing sessions
+	 */
 	BATADV_TP_REASON_TOO_MANY		= 133,
 };
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 30f2ce76b517..a9820677c2ff 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -93,6 +93,7 @@ enum bpf_cmd {
 	BPF_PROG_GET_FD_BY_ID,
 	BPF_MAP_GET_FD_BY_ID,
 	BPF_OBJ_GET_INFO_BY_FD,
+	BPF_PROG_QUERY,
 };
 
 enum bpf_map_type {
@@ -112,6 +113,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_HASH_OF_MAPS,
 	BPF_MAP_TYPE_DEVMAP,
 	BPF_MAP_TYPE_SOCKMAP,
+	BPF_MAP_TYPE_CPUMAP,
 };
 
 enum bpf_prog_type {
@@ -144,11 +146,47 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
-/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
- * to the given target_fd cgroup the descendent cgroup will be able to
- * override effective bpf program that was inherited from this cgroup
+/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
+ *
+ * NONE(default): No further bpf programs allowed in the subtree.
+ *
+ * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
+ * the program in this cgroup yields to sub-cgroup program.
+ *
+ * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
+ * that cgroup program gets run in addition to the program in this cgroup.
+ *
+ * Only one program is allowed to be attached to a cgroup with
+ * NONE or BPF_F_ALLOW_OVERRIDE flag.
+ * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
+ * release old program and attach the new one. Attach flags has to match.
+ *
+ * Multiple programs are allowed to be attached to a cgroup with
+ * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
+ * (those that were attached first, run first)
+ * The programs of sub-cgroup are executed first, then programs of
+ * this cgroup and then programs of parent cgroup.
+ * When children program makes decision (like picking TCP CA or sock bind)
+ * parent program has a chance to override it.
+ *
+ * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
+ * A cgroup with NONE doesn't allow any programs in sub-cgroups.
+ * Ex1:
+ * cgrp1 (MULTI progs A, B) ->
+ *    cgrp2 (OVERRIDE prog C) ->
+ *      cgrp3 (MULTI prog D) ->
+ *        cgrp4 (OVERRIDE prog E) ->
+ *          cgrp5 (NONE prog F)
+ * the event in cgrp5 triggers execution of F,D,A,B in that order.
+ * if prog F is detached, the execution is E,D,A,B
+ * if prog F and D are detached, the execution is E,A,B
+ * if prog F, E and D are detached, the execution is C,A,B
+ *
+ * All eligible programs are executed regardless of return code from
+ * earlier programs.
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
+#define BPF_F_ALLOW_MULTI	(1U << 1)
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel
@@ -176,6 +214,15 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE		(1U << 2)
 
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
+
+#define BPF_OBJ_NAME_LEN 16U
+
+/* Flags for accessing BPF object */
+#define BPF_F_RDONLY		(1U << 3)
+#define BPF_F_WRONLY		(1U << 4)
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -189,6 +236,7 @@ union bpf_attr {
 		__u32	numa_node;	/* numa node (effective only if
 					 * BPF_F_NUMA_NODE is set).
 					 */
+		char	map_name[BPF_OBJ_NAME_LEN];
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -211,11 +259,13 @@ union bpf_attr {
 		__aligned_u64	log_buf;	/* user supplied buffer */
 		__u32		kern_version;	/* checked when prog_type=kprobe */
 		__u32		prog_flags;
+		char		prog_name[BPF_OBJ_NAME_LEN];
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
 		__aligned_u64	pathname;
 		__u32		bpf_fd;
+		__u32		file_flags;
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
@@ -243,6 +293,7 @@ union bpf_attr {
 			__u32		map_id;
 		};
 		__u32		next_id;
+		__u32		open_flags;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
@@ -250,6 +301,15 @@ union bpf_attr {
 		__u32		info_len;
 		__aligned_u64	info;
 	} info;
+
+	struct { /* anonymous struct used by BPF_PROG_QUERY command */
+		__u32		target_fd;	/* container object to query */
+		__u32		attach_type;
+		__u32		query_flags;
+		__u32		attach_flags;
+		__aligned_u64	prog_ids;
+		__u32		prog_cnt;
+	} query;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
@@ -554,12 +614,22 @@ union bpf_attr {
  * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
  *     Calls setsockopt. Not all opts are available, only those with
  *     integer optvals plus TCP_CONGESTION.
- *     Supported levels: SOL_SOCKET and IPROTO_TCP
+ *     Supported levels: SOL_SOCKET and IPPROTO_TCP
  *     @bpf_socket: pointer to bpf_socket
- *     @level: SOL_SOCKET or IPROTO_TCP
+ *     @level: SOL_SOCKET or IPPROTO_TCP
  *     @optname: option name
  *     @optval: pointer to option value
- *     @optlen: length of optval in byes
+ *     @optlen: length of optval in bytes
+ *     Return: 0 or negative error
+ *
+ * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen)
+ *     Calls getsockopt. Not all opts are available.
+ *     Supported levels: IPPROTO_TCP
+ *     @bpf_socket: pointer to bpf_socket
+ *     @level: IPPROTO_TCP
+ *     @optname: option name
+ *     @optval: pointer to option value
+ *     @optlen: length of optval in bytes
  *     Return: 0 or negative error
  *
  * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
@@ -583,6 +653,27 @@ union bpf_attr {
  *	@map: pointer to sockmap to update
  *	@key: key to insert/update sock in map
  *	@flags: same flags as map update elem
+ *
+ * int bpf_xdp_adjust_meta(xdp_md, delta)
+ *     Adjust the xdp_md.data_meta by delta
+ *     @xdp_md: pointer to xdp_md
+ *     @delta: An positive/negative integer to be added to xdp_md.data_meta
+ *     Return: 0 on success or negative on error
+ *
+ * int bpf_perf_event_read_value(map, flags, buf, buf_size)
+ *     read perf event counter value and perf event enabled/running time
+ *     @map: pointer to perf_event_array map
+ *     @flags: index of event in the map or bitmask flags
+ *     @buf: buf to fill
+ *     @buf_size: size of the buf
+ *     Return: 0 on success or negative error code
+ *
+ * int bpf_perf_prog_read_value(ctx, buf, buf_size)
+ *     read perf prog attached perf event counter and enabled/running time
+ *     @ctx: pointer to ctx
+ *     @buf: buf to fill
+ *     @buf_size: size of the buf
+ *     Return : 0 on success or negative error code
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -639,6 +730,10 @@ union bpf_attr {
 	FN(redirect_map),		\
 	FN(sk_redirect_map),		\
 	FN(sock_map_update),		\
+	FN(xdp_adjust_meta),		\
+	FN(perf_event_read_value),	\
+	FN(perf_prog_read_value),	\
+	FN(getsockopt),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -682,7 +777,9 @@ enum bpf_func_id {
 #define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
 #define BPF_F_DONT_FRAGMENT		(1ULL << 2)
 
-/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
+/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
+ * BPF_FUNC_perf_event_read_value flags.
+ */
 #define BPF_F_INDEX_MASK		0xffffffffULL
 #define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
@@ -716,7 +813,7 @@ struct __sk_buff {
 	__u32 data_end;
 	__u32 napi_id;
 
-	/* accessed by BPF_PROG_TYPE_sk_skb types */
+	/* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */
 	__u32 family;
 	__u32 remote_ip4;	/* Stored in network byte order */
 	__u32 local_ip4;	/* Stored in network byte order */
@@ -724,6 +821,9 @@ struct __sk_buff {
 	__u32 local_ip6[4];	/* Stored in network byte order */
 	__u32 remote_port;	/* Stored in network byte order */
 	__u32 local_port;	/* stored in host byte order */
+	/* ... here. */
+
+	__u32 data_meta;
 };
 
 struct bpf_tunnel_key {
@@ -784,6 +884,7 @@ enum xdp_action {
 struct xdp_md {
 	__u32 data;
 	__u32 data_end;
+	__u32 data_meta;
 };
 
 enum sk_action {
@@ -801,6 +902,11 @@ struct bpf_prog_info {
 	__u32 xlated_prog_len;
 	__aligned_u64 jited_prog_insns;
 	__aligned_u64 xlated_prog_insns;
+	__u64 load_time;	/* ns since boottime */
+	__u32 created_by_uid;
+	__u32 nr_map_ids;
+	__aligned_u64 map_ids;
+	char name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -810,6 +916,7 @@ struct bpf_map_info {
 	__u32 value_size;
 	__u32 max_entries;
 	__u32 map_flags;
+	char  name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
@@ -859,9 +966,22 @@ enum {
 	BPF_SOCK_OPS_NEEDS_ECN,		/* If connection's congestion control
 					 * needs ECN
 					 */
+	BPF_SOCK_OPS_BASE_RTT,		/* Get base RTT. The correct value is
+					 * based on the path and may be
+					 * dependent on the congestion control
+					 * algorithm. In general it indicates
+					 * a congestion threshold. RTTs above
+					 * this indicate congestion
+					 */
 };
 
 #define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
 #define TCP_BPF_SNDCWND_CLAMP	1002	/* Set sndcwnd_clamp */
 
+struct bpf_perf_event_value {
+	__u64 counter;
+	__u64 enabled;
+	__u64 running;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 1f00f0cd6790..b3cf5639ac8f 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -159,6 +159,7 @@ enum {
 	IFLA_PAD,
 	IFLA_XDP,
 	IFLA_EVENT,
+	IFLA_NEW_NETNSID,
 	__IFLA_MAX
 };
 
@@ -326,6 +327,8 @@ enum {
 	IFLA_BRPORT_MCAST_TO_UCAST,
 	IFLA_BRPORT_VLAN_TUNNEL,
 	IFLA_BRPORT_BCAST_FLOOD,
+	IFLA_BRPORT_GROUP_FWD_MASK,
+	IFLA_BRPORT_NEIGH_SUPPRESS,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -463,6 +466,7 @@ enum macsec_validation_type {
 enum {
 	IFLA_IPVLAN_UNSPEC,
 	IFLA_IPVLAN_MODE,
+	IFLA_IPVLAN_FLAGS,
 	__IFLA_IPVLAN_MAX
 };
 
@@ -475,6 +479,9 @@ enum ipvlan_mode {
 	IPVLAN_MODE_MAX
 };
 
+#define IPVLAN_F_PRIVATE	0x01
+#define IPVLAN_F_VEPA		0x02
+
 /* VXLAN section */
 enum {
 	IFLA_VXLAN_UNSPEC,
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 47ab4bc62e31..030d3e6d6029 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -61,6 +61,8 @@
 /* TUNSETIFF ifr flags */
 #define IFF_TUN		0x0001
 #define IFF_TAP		0x0002
+#define IFF_NAPI	0x0010
+#define IFF_NAPI_FRAGS	0x0020
 #define IFF_NO_PI	0x1000
 /* This flag has no real effect */
 #define IFF_ONE_QUEUE	0x2000
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 383b850aeb88..e68dadbd6d45 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -85,6 +85,7 @@ enum tunnel_encap_types {
 	TUNNEL_ENCAP_NONE,
 	TUNNEL_ENCAP_FOU,
 	TUNNEL_ENCAP_GUE,
+	TUNNEL_ENCAP_MPLS,
 };
 
 #define TUNNEL_ENCAP_FLAG_CSUM		(1<<0)
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index 2c002ffa9d6f..ed291e55f024 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -285,6 +285,7 @@ struct in6_flowlabel_req {
 #define IPV6_TRANSPARENT        75
 #define IPV6_UNICAST_IF         76
 #define IPV6_RECVFRAGSIZE	77
+#define IPV6_FREEBIND		78
 
 /*
  * Multicast Routing:
diff --git a/include/uapi/linux/ip6_tunnel.h b/include/uapi/linux/ip6_tunnel.h
index 51f29308ac6d..0245269b037c 100644
--- a/include/uapi/linux/ip6_tunnel.h
+++ b/include/uapi/linux/ip6_tunnel.h
@@ -21,6 +21,8 @@
 #define IP6_TNL_F_RCV_DSCP_COPY 0x10
 /* copy fwmark from inner packet */
 #define IP6_TNL_F_USE_ORIG_FWMARK 0x20
+/* allow remote endpoint on the local node */
+#define IP6_TNL_F_ALLOW_LOCAL_REMOTE 0x40
 
 struct ip6_tnl_parm {
 	char name[IFNAMSIZ];	/* name of tunnel device */
diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h
index a96eb17ad6fc..593800a18799 100644
--- a/include/uapi/linux/ipv6_route.h
+++ b/include/uapi/linux/ipv6_route.h
@@ -29,7 +29,7 @@
 
 #define RTF_ROUTEINFO	0x00800000	/* route information - RA	*/
 
-#define RTF_CACHE	0x01000000	/* cache entry			*/
+#define RTF_CACHE	0x01000000	/* read-only: can not be set by user */
 #define RTF_FLOW	0x02000000	/* flow significant route	*/
 #define RTF_POLICY	0x04000000	/* policy route			*/
 
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 51626b4175c0..f882fe1f9709 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -569,13 +569,14 @@
  *	authentication/association or not receiving a response from the AP.
  *	Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as
  *	well to remain backwards compatible.
- * @NL80211_CMD_ROAM: notifcation indicating the card/driver roamed by itself.
- *	When the driver roamed in a network that requires 802.1X authentication,
- *	%NL80211_ATTR_PORT_AUTHORIZED should be set if the 802.1X authentication
- *	was done by the driver or if roaming was done using Fast Transition
- *	protocol (in which case 802.1X authentication is not needed). If
- *	%NL80211_ATTR_PORT_AUTHORIZED is not set, user space is responsible for
- *	the 802.1X authentication.
+ *	When establishing a security association, drivers that support 4 way
+ *	handshake offload should send %NL80211_CMD_PORT_AUTHORIZED event when
+ *	the 4 way handshake is completed successfully.
+ * @NL80211_CMD_ROAM: Notification indicating the card/driver roamed by itself.
+ *	When a security association was established with the new AP (e.g. if
+ *	the FT protocol was used for roaming or the driver completed the 4 way
+ *	handshake), this event should be followed by an
+ *	%NL80211_CMD_PORT_AUTHORIZED event.
  * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify
  *	userspace that a connection was dropped by the AP or due to other
  *	reasons, for this the %NL80211_ATTR_DISCONNECTED_BY_AP and
@@ -982,6 +983,14 @@
  * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously
  *	configured PMK for the authenticator address identified by
  *	&NL80211_ATTR_MAC.
+ * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates that the 4 way
+ *	handshake was completed successfully by the driver. The BSSID is
+ *	specified with &NL80211_ATTR_MAC. Drivers that support 4 way handshake
+ *	offload should send this event after indicating 802.11 association with
+ *	&NL80211_CMD_CONNECT or &NL80211_CMD_ROAM. If the 4 way handshake failed
+ *	&NL80211_CMD_DISCONNECT should be indicated instead.
+ *
+ * @NL80211_CMD_RELOAD_REGDB: Request that the regdb firmware file is reloaded.
  *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
@@ -1185,6 +1194,10 @@ enum nl80211_commands {
 	NL80211_CMD_SET_PMK,
 	NL80211_CMD_DEL_PMK,
 
+	NL80211_CMD_PORT_AUTHORIZED,
+
+	NL80211_CMD_RELOAD_REGDB,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
@@ -1407,8 +1420,12 @@ enum nl80211_commands {
  *
  * @NL80211_ATTR_USE_MFP: Whether management frame protection (IEEE 802.11w) is
  *	used for the association (&enum nl80211_mfp, represented as a u32);
- *	this attribute can be used
- *	with %NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests
+ *	this attribute can be used with %NL80211_CMD_ASSOCIATE and
+ *	%NL80211_CMD_CONNECT requests. %NL80211_MFP_OPTIONAL is not allowed for
+ *	%NL80211_CMD_ASSOCIATE since user space SME is expected and hence, it
+ *	must have decided whether to use management frame protection or not.
+ *	Setting %NL80211_MFP_OPTIONAL with a %NL80211_CMD_CONNECT request will
+ *	let the driver (or the firmware) decide whether to use MFP or not.
  *
  * @NL80211_ATTR_STA_FLAGS2: Attribute containing a
  *	&struct nl80211_sta_flag_update.
@@ -2134,10 +2151,7 @@ enum nl80211_commands {
  *	in %NL80211_CMD_CONNECT to indicate that for 802.1X authentication it
  *	wants to use the supported offload of the 4-way handshake.
  * @NL80211_ATTR_PMKR0_NAME: PMK-R0 Name for offloaded FT.
- * @NL80211_ATTR_PORT_AUTHORIZED: flag attribute used in %NL80211_CMD_ROAMED
- *	notification indicating that that 802.1X authentication was done by
- *	the driver or is not needed (because roaming used the Fast Transition
- *	protocol).
+ * @NL80211_ATTR_PORT_AUTHORIZED: (reserved)
  *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
@@ -3947,10 +3961,12 @@ enum nl80211_key_type {
  * enum nl80211_mfp - Management frame protection state
  * @NL80211_MFP_NO: Management frame protection not used
  * @NL80211_MFP_REQUIRED: Management frame protection required
+ * @NL80211_MFP_OPTIONAL: Management frame protection is optional
  */
 enum nl80211_mfp {
 	NL80211_MFP_NO,
 	NL80211_MFP_REQUIRED,
+	NL80211_MFP_OPTIONAL,
 };
 
 enum nl80211_wpa_versions {
@@ -4914,6 +4930,17 @@ enum nl80211_feature_flags {
  *	handshake with 802.1X in station mode (will pass EAP frames to the host
  *	and accept the set_pmk/del_pmk commands), doing it in the host might not
  *	be supported.
+ * @NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME: Driver is capable of overriding
+ *	the max channel attribute in the FILS request params IE with the
+ *	actual dwell time.
+ * @NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP: Driver accepts broadcast probe
+ *	response
+ * @NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE: Driver supports sending
+ *	the first probe request in each channel at rate of at least 5.5Mbps.
+ * @NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: Driver supports
+ *	probe request tx deferral and suppression
+ * @NL80211_EXT_FEATURE_MFP_OPTIONAL: Driver supports the %NL80211_MFP_OPTIONAL
+ *	value in %NL80211_ATTR_USE_MFP.
  *
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
@@ -4936,6 +4963,11 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_FILS_SK_OFFLOAD,
 	NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK,
 	NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X,
+	NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME,
+	NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP,
+	NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE,
+	NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION,
+	NL80211_EXT_FEATURE_MFP_OPTIONAL,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,
@@ -5012,12 +5044,28 @@ enum nl80211_timeout_reason {
  *	locally administered 1, multicast 0) is assumed.
  *	This flag must not be requested when the feature isn't supported, check
  *	the nl80211 feature flags for the device.
+ * @NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME: fill the dwell time in the FILS
+ *	request parameters IE in the probe request
+ * @NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP: accept broadcast probe responses
+ * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE: send probe request frames at
+ *	rate of at least 5.5M. In case non OCE AP is dicovered in the channel,
+ *	only the first probe req in the channel will be sent in high rate.
+ * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: allow probe request
+ *	tx deferral (dot11FILSProbeDelay shall be set to 15ms)
+ *	and suppression (if it has received a broadcast Probe Response frame,
+ *	Beacon frame or FILS Discovery frame from an AP that the STA considers
+ *	a suitable candidate for (re-)association - suitable in terms of
+ *	SSID and/or RSSI
  */
 enum nl80211_scan_flags {
-	NL80211_SCAN_FLAG_LOW_PRIORITY			= 1<<0,
-	NL80211_SCAN_FLAG_FLUSH				= 1<<1,
-	NL80211_SCAN_FLAG_AP				= 1<<2,
-	NL80211_SCAN_FLAG_RANDOM_ADDR			= 1<<3,
+	NL80211_SCAN_FLAG_LOW_PRIORITY				= 1<<0,
+	NL80211_SCAN_FLAG_FLUSH					= 1<<1,
+	NL80211_SCAN_FLAG_AP					= 1<<2,
+	NL80211_SCAN_FLAG_RANDOM_ADDR				= 1<<3,
+	NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME			= 1<<4,
+	NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP		= 1<<5,
+	NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE		= 1<<6,
+	NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION	= 1<<7,
 };
 
 /**
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 36d0b161e066..ffe397daad49 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -360,6 +360,7 @@ enum ovs_tunnel_key_attr {
 	OVS_TUNNEL_KEY_ATTR_IPV6_SRC,		/* struct in6_addr src IPv6 address. */
 	OVS_TUNNEL_KEY_ATTR_IPV6_DST,		/* struct in6_addr dst IPv6 address. */
 	OVS_TUNNEL_KEY_ATTR_PAD,
+	OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS,	/* be32 ERSPAN index. */
 	__OVS_TUNNEL_KEY_ATTR_MAX
 };
 
@@ -807,6 +808,7 @@ struct ovs_action_push_eth {
  * packet.
  * @OVS_ACTION_ATTR_POP_ETH: Pop the outermost Ethernet header off the
  * packet.
+ * @OVS_ACTION_ATTR_CT_CLEAR: Clear conntrack state from the packet.
  *
  * Only a single header can be set with a single %OVS_ACTION_ATTR_SET.  Not all
  * fields within a header are modifiable, e.g. the IPv4 protocol and fragment
@@ -836,6 +838,7 @@ enum ovs_action_attr {
 	OVS_ACTION_ATTR_TRUNC,        /* u32 struct ovs_action_trunc. */
 	OVS_ACTION_ATTR_PUSH_ETH,     /* struct ovs_action_push_eth. */
 	OVS_ACTION_ATTR_POP_ETH,      /* No argument. */
+	OVS_ACTION_ATTR_CT_CLEAR,     /* No argument. */
 
 	__OVS_ACTION_ATTR_MAX,	      /* Nothing past this will be accepted
 				       * from userspace. */
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 703cd9df6cef..5002562868cc 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -75,6 +75,7 @@ struct tc_estimator {
 #define TC_H_INGRESS    (0xFFFFFFF1U)
 #define TC_H_CLSACT	TC_H_INGRESS
 
+#define TC_H_MIN_PRIORITY	0xFFE0U
 #define TC_H_MIN_INGRESS	0xFFF2U
 #define TC_H_MIN_EGRESS		0xFFF3U
 
@@ -626,6 +627,22 @@ enum {
 
 #define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1)
 
+enum {
+	TC_MQPRIO_MODE_DCB,
+	TC_MQPRIO_MODE_CHANNEL,
+	__TC_MQPRIO_MODE_MAX
+};
+
+#define __TC_MQPRIO_MODE_MAX (__TC_MQPRIO_MODE_MAX - 1)
+
+enum {
+	TC_MQPRIO_SHAPER_DCB,
+	TC_MQPRIO_SHAPER_BW_RATE,	/* Add new shapers below */
+	__TC_MQPRIO_SHAPER_MAX
+};
+
+#define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1)
+
 struct tc_mqprio_qopt {
 	__u8	num_tc;
 	__u8	prio_tc_map[TC_QOPT_BITMASK + 1];
@@ -634,6 +651,22 @@ struct tc_mqprio_qopt {
 	__u16	offset[TC_QOPT_MAX_QUEUE];
 };
 
+#define TC_MQPRIO_F_MODE		0x1
+#define TC_MQPRIO_F_SHAPER		0x2
+#define TC_MQPRIO_F_MIN_RATE		0x4
+#define TC_MQPRIO_F_MAX_RATE		0x8
+
+enum {
+	TCA_MQPRIO_UNSPEC,
+	TCA_MQPRIO_MODE,
+	TCA_MQPRIO_SHAPER,
+	TCA_MQPRIO_MIN_RATE64,
+	TCA_MQPRIO_MAX_RATE64,
+	__TCA_MQPRIO_MAX,
+};
+
+#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1)
+
 /* SFB */
 
 enum {
@@ -872,4 +905,23 @@ struct tc_pie_xstats {
 	__u32 maxq;             /* maximum queue size */
 	__u32 ecn_mark;         /* packets marked with ecn*/
 };
+
+/* CBS */
+struct tc_cbs_qopt {
+	__u8 offload;
+	__u8 _pad[3];
+	__s32 hicredit;
+	__s32 locredit;
+	__s32 idleslope;
+	__s32 sendslope;
+};
+
+enum {
+	TCA_CBS_UNSPEC,
+	TCA_CBS_PARMS,
+	__TCA_CBS_MAX,
+};
+
+#define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
+
 #endif
diff --git a/include/uapi/linux/qrtr.h b/include/uapi/linux/qrtr.h
index 5d9aab1f1893..f7e2fb3d752b 100644
--- a/include/uapi/linux/qrtr.h
+++ b/include/uapi/linux/qrtr.h
@@ -5,10 +5,45 @@
 #include <linux/socket.h>
 #include <linux/types.h>
 
+#define QRTR_NODE_BCAST	0xffffffffu
+#define QRTR_PORT_CTRL	0xfffffffeu
+
 struct sockaddr_qrtr {
 	__kernel_sa_family_t sq_family;
 	__u32 sq_node;
 	__u32 sq_port;
 };
 
+enum qrtr_pkt_type {
+	QRTR_TYPE_DATA		= 1,
+	QRTR_TYPE_HELLO		= 2,
+	QRTR_TYPE_BYE		= 3,
+	QRTR_TYPE_NEW_SERVER	= 4,
+	QRTR_TYPE_DEL_SERVER	= 5,
+	QRTR_TYPE_DEL_CLIENT	= 6,
+	QRTR_TYPE_RESUME_TX	= 7,
+	QRTR_TYPE_EXIT          = 8,
+	QRTR_TYPE_PING          = 9,
+	QRTR_TYPE_NEW_LOOKUP	= 10,
+	QRTR_TYPE_DEL_LOOKUP	= 11,
+};
+
+struct qrtr_ctrl_pkt {
+	__le32 cmd;
+
+	union {
+		struct {
+			__le32 service;
+			__le32 instance;
+			__le32 node;
+			__le32 port;
+		} server;
+
+		struct {
+			__le32 node;
+			__le32 port;
+		} client;
+	};
+} __packed;
+
 #endif /* _LINUX_QRTR_H */
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index a6d37c2ea355..d8b5f80c2ea6 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -431,6 +431,8 @@ enum {
 #define RTAX_QUICKACK RTAX_QUICKACK
 	RTAX_CC_ALGO,
 #define RTAX_CC_ALGO RTAX_CC_ALGO
+	RTAX_FASTOPEN_NO_COOKIE,
+#define RTAX_FASTOPEN_NO_COOKIE RTAX_FASTOPEN_NO_COOKIE
 	__RTAX_MAX
 };
 
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index cfe971296835..d9adab32dbee 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -123,6 +123,8 @@ typedef __s32 sctp_assoc_t;
 #define SCTP_RESET_ASSOC	120
 #define SCTP_ADD_STREAMS	121
 #define SCTP_SOCKOPT_PEELOFF_FLAGS 122
+#define SCTP_STREAM_SCHEDULER	123
+#define SCTP_STREAM_SCHEDULER_VALUE	124
 
 /* PR-SCTP policies */
 #define SCTP_PR_SCTP_NONE	0x0000
@@ -815,6 +817,12 @@ struct sctp_assoc_value {
     uint32_t                assoc_value;
 };
 
+struct sctp_stream_value {
+	sctp_assoc_t assoc_id;
+	uint16_t stream_id;
+	uint16_t stream_value;
+};
+
 /*
  * 7.2.2 Peer Address Information
  *
@@ -1089,4 +1097,12 @@ struct sctp_add_streams {
 	uint16_t sas_outstrms;
 };
 
+/* SCTP Stream schedulers */
+enum sctp_sched_type {
+	SCTP_SS_FCFS,
+	SCTP_SS_PRIO,
+	SCTP_SS_RR,
+	SCTP_SS_MAX = SCTP_SS_RR
+};
+
 #endif /* _UAPI_SCTP_H */
diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h
index 020696e07345..5dd671cf5776 100644
--- a/include/uapi/linux/tc_act/tc_mirred.h
+++ b/include/uapi/linux/tc_act/tc_mirred.h
@@ -10,13 +10,13 @@
 #define TCA_EGRESS_MIRROR 2 /* mirror packet to EGRESS */
 #define TCA_INGRESS_REDIR 3  /* packet redirect to INGRESS*/
 #define TCA_INGRESS_MIRROR 4 /* mirror packet to INGRESS */
-                                                                                
+
 struct tc_mirred {
 	tc_gen;
 	int                     eaction;   /* one of IN/EGRESS_MIRROR/REDIR */
 	__u32                   ifindex;  /* ifindex of egress port */
 };
-                                                                                
+
 enum {
 	TCA_MIRRED_UNSPEC,
 	TCA_MIRRED_TM,
@@ -25,5 +25,5 @@ enum {
 	__TCA_MIRRED_MAX
 };
 #define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1)
-                                                                                
+
 #endif
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 6a64beeecfad..b4a4f64635fa 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -120,6 +120,8 @@ enum {
 #define TCP_FASTOPEN_CONNECT	30	/* Attempt FastOpen with connect */
 #define TCP_ULP			31	/* Attach a ULP to a TCP connection */
 #define TCP_MD5SIG_EXT		32	/* TCP MD5 Signature with extensions */
+#define TCP_FASTOPEN_KEY	33	/* Set the key for Fast Open (cookie) */
+#define TCP_FASTOPEN_NO_COOKIE	34	/* Enable TFO without a TFO cookie */
 
 struct tcp_repair_opt {
 	__u32	opt_code;
diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h
index 77123614e973..35f79d1f8c3a 100644
--- a/include/uapi/linux/tipc.h
+++ b/include/uapi/linux/tipc.h
@@ -232,6 +232,21 @@ struct sockaddr_tipc {
 #define TIPC_SOCK_RECVQ_DEPTH	132	/* Default: none (read only) */
 #define TIPC_MCAST_BROADCAST    133     /* Default: TIPC selects. No arg */
 #define TIPC_MCAST_REPLICAST    134     /* Default: TIPC selects. No arg */
+#define TIPC_GROUP_JOIN         135     /* Takes struct tipc_group_req* */
+#define TIPC_GROUP_LEAVE        136     /* No argument */
+
+/*
+ * Flag values
+ */
+#define TIPC_GROUP_LOOPBACK     0x1  /* Receive copy of sent msg when match */
+#define TIPC_GROUP_MEMBER_EVTS  0x2  /* Receive membership events in socket */
+
+struct tipc_group_req {
+	__u32 type;      /* group id */
+	__u32 instance;  /* member id */
+	__u32 scope;     /* zone/cluster/node */
+	__u32 flags;
+};
 
 /*
  * Maximum sizes of TIPC bearer-related names (including terminating NULL)
diff --git a/include/uapi/linux/vm_sockets_diag.h b/include/uapi/linux/vm_sockets_diag.h
new file mode 100644
index 000000000000..14cd7dc5a187
--- /dev/null
+++ b/include/uapi/linux/vm_sockets_diag.h
@@ -0,0 +1,33 @@
+/* AF_VSOCK sock_diag(7) interface for querying open sockets */
+
+#ifndef _UAPI__VM_SOCKETS_DIAG_H__
+#define _UAPI__VM_SOCKETS_DIAG_H__
+
+#include <linux/types.h>
+
+/* Request */
+struct vsock_diag_req {
+	__u8	sdiag_family;	/* must be AF_VSOCK */
+	__u8	sdiag_protocol;	/* must be 0 */
+	__u16	pad;		/* must be 0 */
+	__u32	vdiag_states;	/* query bitmap (e.g. 1 << TCP_LISTEN) */
+	__u32	vdiag_ino;	/* must be 0 (reserved) */
+	__u32	vdiag_show;	/* must be 0 (reserved) */
+	__u32	vdiag_cookie[2];
+};
+
+/* Response */
+struct vsock_diag_msg {
+	__u8	vdiag_family;	/* AF_VSOCK */
+	__u8	vdiag_type;	/* SOCK_STREAM or SOCK_DGRAM */
+	__u8	vdiag_state;	/* sk_state (e.g. TCP_LISTEN) */
+	__u8	vdiag_shutdown; /* local RCV_SHUTDOWN | SEND_SHUTDOWN */
+	__u32   vdiag_src_cid;
+	__u32   vdiag_src_port;
+	__u32   vdiag_dst_cid;
+	__u32   vdiag_dst_port;
+	__u32	vdiag_ino;
+	__u32	vdiag_cookie[2];
+};
+
+#endif /* _UAPI__VM_SOCKETS_DIAG_H__ */
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index af3ab6164ff5..16e95c8e749e 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -3,8 +3,10 @@ obj-y := core.o
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
+obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
+obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
 ifeq ($(CONFIG_STREAM_PARSER),y)
 obj-$(CONFIG_BPF_SYSCALL) += sockmap.o
 endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index e2636737b69b..7c25426d3cf5 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -19,6 +19,9 @@
 
 #include "map_in_map.h"
 
+#define ARRAY_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
 	int i;
@@ -56,7 +59,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size == 0 || attr->map_flags & ~BPF_F_NUMA_NODE ||
+	    attr->value_size == 0 ||
+	    attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
 	    (percpu && numa_node != NUMA_NO_NODE))
 		return ERR_PTR(-EINVAL);
 
@@ -492,7 +496,7 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map,
 
 	ee = ERR_PTR(-EOPNOTSUPP);
 	event = perf_file->private_data;
-	if (perf_event_read_local(event, &value) == -EOPNOTSUPP)
+	if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP)
 		goto err_out;
 
 	ee = bpf_event_entry_gen(perf_file, map_file);
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 546113430049..3db5a17fcfe8 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -27,129 +27,405 @@ void cgroup_bpf_put(struct cgroup *cgrp)
 {
 	unsigned int type;
 
-	for (type = 0; type < ARRAY_SIZE(cgrp->bpf.prog); type++) {
-		struct bpf_prog *prog = cgrp->bpf.prog[type];
-
-		if (prog) {
-			bpf_prog_put(prog);
+	for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) {
+		struct list_head *progs = &cgrp->bpf.progs[type];
+		struct bpf_prog_list *pl, *tmp;
+
+		list_for_each_entry_safe(pl, tmp, progs, node) {
+			list_del(&pl->node);
+			bpf_prog_put(pl->prog);
+			kfree(pl);
 			static_branch_dec(&cgroup_bpf_enabled_key);
 		}
+		bpf_prog_array_free(cgrp->bpf.effective[type]);
+	}
+}
+
+/* count number of elements in the list.
+ * it's slow but the list cannot be long
+ */
+static u32 prog_list_length(struct list_head *head)
+{
+	struct bpf_prog_list *pl;
+	u32 cnt = 0;
+
+	list_for_each_entry(pl, head, node) {
+		if (!pl->prog)
+			continue;
+		cnt++;
 	}
+	return cnt;
+}
+
+/* if parent has non-overridable prog attached,
+ * disallow attaching new programs to the descendent cgroup.
+ * if parent has overridable or multi-prog, allow attaching
+ */
+static bool hierarchy_allows_attach(struct cgroup *cgrp,
+				    enum bpf_attach_type type,
+				    u32 new_flags)
+{
+	struct cgroup *p;
+
+	p = cgroup_parent(cgrp);
+	if (!p)
+		return true;
+	do {
+		u32 flags = p->bpf.flags[type];
+		u32 cnt;
+
+		if (flags & BPF_F_ALLOW_MULTI)
+			return true;
+		cnt = prog_list_length(&p->bpf.progs[type]);
+		WARN_ON_ONCE(cnt > 1);
+		if (cnt == 1)
+			return !!(flags & BPF_F_ALLOW_OVERRIDE);
+		p = cgroup_parent(p);
+	} while (p);
+	return true;
+}
+
+/* compute a chain of effective programs for a given cgroup:
+ * start from the list of programs in this cgroup and add
+ * all parent programs.
+ * Note that parent's F_ALLOW_OVERRIDE-type program is yielding
+ * to programs in this cgroup
+ */
+static int compute_effective_progs(struct cgroup *cgrp,
+				   enum bpf_attach_type type,
+				   struct bpf_prog_array __rcu **array)
+{
+	struct bpf_prog_array __rcu *progs;
+	struct bpf_prog_list *pl;
+	struct cgroup *p = cgrp;
+	int cnt = 0;
+
+	/* count number of effective programs by walking parents */
+	do {
+		if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+			cnt += prog_list_length(&p->bpf.progs[type]);
+		p = cgroup_parent(p);
+	} while (p);
+
+	progs = bpf_prog_array_alloc(cnt, GFP_KERNEL);
+	if (!progs)
+		return -ENOMEM;
+
+	/* populate the array with effective progs */
+	cnt = 0;
+	p = cgrp;
+	do {
+		if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+			list_for_each_entry(pl,
+					    &p->bpf.progs[type], node) {
+				if (!pl->prog)
+					continue;
+				rcu_dereference_protected(progs, 1)->
+					progs[cnt++] = pl->prog;
+			}
+		p = cgroup_parent(p);
+	} while (p);
+
+	*array = progs;
+	return 0;
+}
+
+static void activate_effective_progs(struct cgroup *cgrp,
+				     enum bpf_attach_type type,
+				     struct bpf_prog_array __rcu *array)
+{
+	struct bpf_prog_array __rcu *old_array;
+
+	old_array = xchg(&cgrp->bpf.effective[type], array);
+	/* free prog array after grace period, since __cgroup_bpf_run_*()
+	 * might be still walking the array
+	 */
+	bpf_prog_array_free(old_array);
 }
 
 /**
  * cgroup_bpf_inherit() - inherit effective programs from parent
  * @cgrp: the cgroup to modify
- * @parent: the parent to inherit from
  */
-void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
+int cgroup_bpf_inherit(struct cgroup *cgrp)
 {
-	unsigned int type;
+/* has to use marco instead of const int, since compiler thinks
+ * that array below is variable length
+ */
+#define	NR ARRAY_SIZE(cgrp->bpf.effective)
+	struct bpf_prog_array __rcu *arrays[NR] = {};
+	int i;
 
-	for (type = 0; type < ARRAY_SIZE(cgrp->bpf.effective); type++) {
-		struct bpf_prog *e;
+	for (i = 0; i < NR; i++)
+		INIT_LIST_HEAD(&cgrp->bpf.progs[i]);
 
-		e = rcu_dereference_protected(parent->bpf.effective[type],
-					      lockdep_is_held(&cgroup_mutex));
-		rcu_assign_pointer(cgrp->bpf.effective[type], e);
-		cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type];
-	}
+	for (i = 0; i < NR; i++)
+		if (compute_effective_progs(cgrp, i, &arrays[i]))
+			goto cleanup;
+
+	for (i = 0; i < NR; i++)
+		activate_effective_progs(cgrp, i, arrays[i]);
+
+	return 0;
+cleanup:
+	for (i = 0; i < NR; i++)
+		bpf_prog_array_free(arrays[i]);
+	return -ENOMEM;
 }
 
+#define BPF_CGROUP_MAX_PROGS 64
+
 /**
- * __cgroup_bpf_update() - Update the pinned program of a cgroup, and
+ * __cgroup_bpf_attach() - Attach the program to a cgroup, and
  *                         propagate the change to descendants
  * @cgrp: The cgroup which descendants to traverse
- * @parent: The parent of @cgrp, or %NULL if @cgrp is the root
- * @prog: A new program to pin
- * @type: Type of pinning operation (ingress/egress)
- *
- * Each cgroup has a set of two pointers for bpf programs; one for eBPF
- * programs it owns, and which is effective for execution.
- *
- * If @prog is not %NULL, this function attaches a new program to the cgroup
- * and releases the one that is currently attached, if any. @prog is then made
- * the effective program of type @type in that cgroup.
- *
- * If @prog is %NULL, the currently attached program of type @type is released,
- * and the effective program of the parent cgroup (if any) is inherited to
- * @cgrp.
- *
- * Then, the descendants of @cgrp are walked and the effective program for
- * each of them is set to the effective program of @cgrp unless the
- * descendant has its own program attached, in which case the subbranch is
- * skipped. This ensures that delegated subcgroups with own programs are left
- * untouched.
+ * @prog: A program to attach
+ * @type: Type of attach operation
  *
  * Must be called with cgroup_mutex held.
  */
-int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
-			struct bpf_prog *prog, enum bpf_attach_type type,
-			bool new_overridable)
+int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+			enum bpf_attach_type type, u32 flags)
 {
-	struct bpf_prog *old_prog, *effective = NULL;
-	struct cgroup_subsys_state *pos;
-	bool overridable = true;
-
-	if (parent) {
-		overridable = !parent->bpf.disallow_override[type];
-		effective = rcu_dereference_protected(parent->bpf.effective[type],
-						      lockdep_is_held(&cgroup_mutex));
-	}
-
-	if (prog && effective && !overridable)
-		/* if parent has non-overridable prog attached, disallow
-		 * attaching new programs to descendent cgroup
-		 */
+	struct list_head *progs = &cgrp->bpf.progs[type];
+	struct bpf_prog *old_prog = NULL;
+	struct cgroup_subsys_state *css;
+	struct bpf_prog_list *pl;
+	bool pl_was_allocated;
+	int err;
+
+	if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI))
+		/* invalid combination */
+		return -EINVAL;
+
+	if (!hierarchy_allows_attach(cgrp, type, flags))
 		return -EPERM;
 
-	if (prog && effective && overridable != new_overridable)
-		/* if parent has overridable prog attached, only
-		 * allow overridable programs in descendent cgroup
+	if (!list_empty(progs) && cgrp->bpf.flags[type] != flags)
+		/* Disallow attaching non-overridable on top
+		 * of existing overridable in this cgroup.
+		 * Disallow attaching multi-prog if overridable or none
 		 */
 		return -EPERM;
 
-	old_prog = cgrp->bpf.prog[type];
-
-	if (prog) {
-		overridable = new_overridable;
-		effective = prog;
-		if (old_prog &&
-		    cgrp->bpf.disallow_override[type] == new_overridable)
-			/* disallow attaching non-overridable on top
-			 * of existing overridable in this cgroup
-			 * and vice versa
-			 */
-			return -EPERM;
+	if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
+		return -E2BIG;
+
+	if (flags & BPF_F_ALLOW_MULTI) {
+		list_for_each_entry(pl, progs, node)
+			if (pl->prog == prog)
+				/* disallow attaching the same prog twice */
+				return -EINVAL;
+
+		pl = kmalloc(sizeof(*pl), GFP_KERNEL);
+		if (!pl)
+			return -ENOMEM;
+		pl_was_allocated = true;
+		pl->prog = prog;
+		list_add_tail(&pl->node, progs);
+	} else {
+		if (list_empty(progs)) {
+			pl = kmalloc(sizeof(*pl), GFP_KERNEL);
+			if (!pl)
+				return -ENOMEM;
+			pl_was_allocated = true;
+			list_add_tail(&pl->node, progs);
+		} else {
+			pl = list_first_entry(progs, typeof(*pl), node);
+			old_prog = pl->prog;
+			pl_was_allocated = false;
+		}
+		pl->prog = prog;
 	}
 
-	if (!prog && !old_prog)
-		/* report error when trying to detach and nothing is attached */
-		return -ENOENT;
-
-	cgrp->bpf.prog[type] = prog;
+	cgrp->bpf.flags[type] = flags;
 
-	css_for_each_descendant_pre(pos, &cgrp->self) {
-		struct cgroup *desc = container_of(pos, struct cgroup, self);
+	/* allocate and recompute effective prog arrays */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
 
-		/* skip the subtree if the descendant has its own program */
-		if (desc->bpf.prog[type] && desc != cgrp) {
-			pos = css_rightmost_descendant(pos);
-		} else {
-			rcu_assign_pointer(desc->bpf.effective[type],
-					   effective);
-			desc->bpf.disallow_override[type] = !overridable;
-		}
+		err = compute_effective_progs(desc, type, &desc->bpf.inactive);
+		if (err)
+			goto cleanup;
 	}
 
-	if (prog)
-		static_branch_inc(&cgroup_bpf_enabled_key);
+	/* all allocations were successful. Activate all prog arrays */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		activate_effective_progs(desc, type, desc->bpf.inactive);
+		desc->bpf.inactive = NULL;
+	}
 
+	static_branch_inc(&cgroup_bpf_enabled_key);
 	if (old_prog) {
 		bpf_prog_put(old_prog);
 		static_branch_dec(&cgroup_bpf_enabled_key);
 	}
 	return 0;
+
+cleanup:
+	/* oom while computing effective. Free all computed effective arrays
+	 * since they were not activated
+	 */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		bpf_prog_array_free(desc->bpf.inactive);
+		desc->bpf.inactive = NULL;
+	}
+
+	/* and cleanup the prog list */
+	pl->prog = old_prog;
+	if (pl_was_allocated) {
+		list_del(&pl->node);
+		kfree(pl);
+	}
+	return err;
+}
+
+/**
+ * __cgroup_bpf_detach() - Detach the program from a cgroup, and
+ *                         propagate the change to descendants
+ * @cgrp: The cgroup which descendants to traverse
+ * @prog: A program to detach or NULL
+ * @type: Type of detach operation
+ *
+ * Must be called with cgroup_mutex held.
+ */
+int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+			enum bpf_attach_type type, u32 unused_flags)
+{
+	struct list_head *progs = &cgrp->bpf.progs[type];
+	u32 flags = cgrp->bpf.flags[type];
+	struct bpf_prog *old_prog = NULL;
+	struct cgroup_subsys_state *css;
+	struct bpf_prog_list *pl;
+	int err;
+
+	if (flags & BPF_F_ALLOW_MULTI) {
+		if (!prog)
+			/* to detach MULTI prog the user has to specify valid FD
+			 * of the program to be detached
+			 */
+			return -EINVAL;
+	} else {
+		if (list_empty(progs))
+			/* report error when trying to detach and nothing is attached */
+			return -ENOENT;
+	}
+
+	if (flags & BPF_F_ALLOW_MULTI) {
+		/* find the prog and detach it */
+		list_for_each_entry(pl, progs, node) {
+			if (pl->prog != prog)
+				continue;
+			old_prog = prog;
+			/* mark it deleted, so it's ignored while
+			 * recomputing effective
+			 */
+			pl->prog = NULL;
+			break;
+		}
+		if (!old_prog)
+			return -ENOENT;
+	} else {
+		/* to maintain backward compatibility NONE and OVERRIDE cgroups
+		 * allow detaching with invalid FD (prog==NULL)
+		 */
+		pl = list_first_entry(progs, typeof(*pl), node);
+		old_prog = pl->prog;
+		pl->prog = NULL;
+	}
+
+	/* allocate and recompute effective prog arrays */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		err = compute_effective_progs(desc, type, &desc->bpf.inactive);
+		if (err)
+			goto cleanup;
+	}
+
+	/* all allocations were successful. Activate all prog arrays */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		activate_effective_progs(desc, type, desc->bpf.inactive);
+		desc->bpf.inactive = NULL;
+	}
+
+	/* now can actually delete it from this cgroup list */
+	list_del(&pl->node);
+	kfree(pl);
+	if (list_empty(progs))
+		/* last program was detached, reset flags to zero */
+		cgrp->bpf.flags[type] = 0;
+
+	bpf_prog_put(old_prog);
+	static_branch_dec(&cgroup_bpf_enabled_key);
+	return 0;
+
+cleanup:
+	/* oom while computing effective. Free all computed effective arrays
+	 * since they were not activated
+	 */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		bpf_prog_array_free(desc->bpf.inactive);
+		desc->bpf.inactive = NULL;
+	}
+
+	/* and restore back old_prog */
+	pl->prog = old_prog;
+	return err;
+}
+
+/* Must be called with cgroup_mutex held to avoid races. */
+int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+		       union bpf_attr __user *uattr)
+{
+	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+	enum bpf_attach_type type = attr->query.attach_type;
+	struct list_head *progs = &cgrp->bpf.progs[type];
+	u32 flags = cgrp->bpf.flags[type];
+	int cnt, ret = 0, i;
+
+	if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE)
+		cnt = bpf_prog_array_length(cgrp->bpf.effective[type]);
+	else
+		cnt = prog_list_length(progs);
+
+	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
+		return -EFAULT;
+	if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt)))
+		return -EFAULT;
+	if (attr->query.prog_cnt == 0 || !prog_ids || !cnt)
+		/* return early if user requested only program count + flags */
+		return 0;
+	if (attr->query.prog_cnt < cnt) {
+		cnt = attr->query.prog_cnt;
+		ret = -ENOSPC;
+	}
+
+	if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) {
+		return bpf_prog_array_copy_to_user(cgrp->bpf.effective[type],
+						   prog_ids, cnt);
+	} else {
+		struct bpf_prog_list *pl;
+		u32 id;
+
+		i = 0;
+		list_for_each_entry(pl, progs, node) {
+			id = pl->prog->aux->id;
+			if (copy_to_user(prog_ids + i, &id, sizeof(id)))
+				return -EFAULT;
+			if (++i == cnt)
+				break;
+		}
+	}
+	return ret;
 }
 
 /**
@@ -171,36 +447,26 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 				struct sk_buff *skb,
 				enum bpf_attach_type type)
 {
-	struct bpf_prog *prog;
+	unsigned int offset = skb->data - skb_network_header(skb);
+	struct sock *save_sk;
 	struct cgroup *cgrp;
-	int ret = 0;
+	int ret;
 
 	if (!sk || !sk_fullsock(sk))
 		return 0;
 
-	if (sk->sk_family != AF_INET &&
-	    sk->sk_family != AF_INET6)
+	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
 		return 0;
 
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-
-	rcu_read_lock();
-
-	prog = rcu_dereference(cgrp->bpf.effective[type]);
-	if (prog) {
-		unsigned int offset = skb->data - skb_network_header(skb);
-		struct sock *save_sk = skb->sk;
-
-		skb->sk = sk;
-		__skb_push(skb, offset);
-		ret = bpf_prog_run_save_cb(prog, skb) == 1 ? 0 : -EPERM;
-		__skb_pull(skb, offset);
-		skb->sk = save_sk;
-	}
-
-	rcu_read_unlock();
-
-	return ret;
+	save_sk = skb->sk;
+	skb->sk = sk;
+	__skb_push(skb, offset);
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
+				 bpf_prog_run_save_cb);
+	__skb_pull(skb, offset);
+	skb->sk = save_sk;
+	return ret == 1 ? 0 : -EPERM;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
 
@@ -221,19 +487,10 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
 			       enum bpf_attach_type type)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-	struct bpf_prog *prog;
-	int ret = 0;
-
-
-	rcu_read_lock();
-
-	prog = rcu_dereference(cgrp->bpf.effective[type]);
-	if (prog)
-		ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM;
-
-	rcu_read_unlock();
+	int ret;
 
-	return ret;
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sk, BPF_PROG_RUN);
+	return ret == 1 ? 0 : -EPERM;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
 
@@ -258,18 +515,10 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 				     enum bpf_attach_type type)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-	struct bpf_prog *prog;
-	int ret = 0;
-
-
-	rcu_read_lock();
+	int ret;
 
-	prog = rcu_dereference(cgrp->bpf.effective[type]);
-	if (prog)
-		ret = BPF_PROG_RUN(prog, sock_ops) == 1 ? 0 : -EPERM;
-
-	rcu_read_unlock();
-
-	return ret;
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sock_ops,
+				 BPF_PROG_RUN);
+	return ret == 1 ? 0 : -EPERM;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7b62df86be1d..7fe448799d76 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -309,12 +309,25 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog,
 
 static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
 {
+	const char *end = sym + KSYM_NAME_LEN;
+
 	BUILD_BUG_ON(sizeof("bpf_prog_") +
-		     sizeof(prog->tag) * 2 + 1 > KSYM_NAME_LEN);
+		     sizeof(prog->tag) * 2 +
+		     /* name has been null terminated.
+		      * We should need +1 for the '_' preceding
+		      * the name.  However, the null character
+		      * is double counted between the name and the
+		      * sizeof("bpf_prog_") above, so we omit
+		      * the +1 here.
+		      */
+		     sizeof(prog->aux->name) > KSYM_NAME_LEN);
 
 	sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_");
 	sym  = bin2hex(sym, prog->tag, sizeof(prog->tag));
-	*sym = 0;
+	if (prog->aux->name[0])
+		snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name);
+	else
+		*sym = 0;
 }
 
 static __always_inline unsigned long
@@ -1381,6 +1394,156 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
 
+static unsigned int __bpf_prog_ret1(const void *ctx,
+				    const struct bpf_insn *insn)
+{
+	return 1;
+}
+
+static struct bpf_prog_dummy {
+	struct bpf_prog prog;
+} dummy_bpf_prog = {
+	.prog = {
+		.bpf_func = __bpf_prog_ret1,
+	},
+};
+
+/* to avoid allocating empty bpf_prog_array for cgroups that
+ * don't have bpf program attached use one global 'empty_prog_array'
+ * It will not be modified the caller of bpf_prog_array_alloc()
+ * (since caller requested prog_cnt == 0)
+ * that pointer should be 'freed' by bpf_prog_array_free()
+ */
+static struct {
+	struct bpf_prog_array hdr;
+	struct bpf_prog *null_prog;
+} empty_prog_array = {
+	.null_prog = NULL,
+};
+
+struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
+{
+	if (prog_cnt)
+		return kzalloc(sizeof(struct bpf_prog_array) +
+			       sizeof(struct bpf_prog *) * (prog_cnt + 1),
+			       flags);
+
+	return &empty_prog_array.hdr;
+}
+
+void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
+{
+	if (!progs ||
+	    progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr)
+		return;
+	kfree_rcu(progs, rcu);
+}
+
+int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
+{
+	struct bpf_prog **prog;
+	u32 cnt = 0;
+
+	rcu_read_lock();
+	prog = rcu_dereference(progs)->progs;
+	for (; *prog; prog++)
+		cnt++;
+	rcu_read_unlock();
+	return cnt;
+}
+
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+				__u32 __user *prog_ids, u32 cnt)
+{
+	struct bpf_prog **prog;
+	u32 i = 0, id;
+
+	rcu_read_lock();
+	prog = rcu_dereference(progs)->progs;
+	for (; *prog; prog++) {
+		id = (*prog)->aux->id;
+		if (copy_to_user(prog_ids + i, &id, sizeof(id))) {
+			rcu_read_unlock();
+			return -EFAULT;
+		}
+		if (++i == cnt) {
+			prog++;
+			break;
+		}
+	}
+	rcu_read_unlock();
+	if (*prog)
+		return -ENOSPC;
+	return 0;
+}
+
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+				struct bpf_prog *old_prog)
+{
+	struct bpf_prog **prog = progs->progs;
+
+	for (; *prog; prog++)
+		if (*prog == old_prog) {
+			WRITE_ONCE(*prog, &dummy_bpf_prog.prog);
+			break;
+		}
+}
+
+int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
+			struct bpf_prog *exclude_prog,
+			struct bpf_prog *include_prog,
+			struct bpf_prog_array **new_array)
+{
+	int new_prog_cnt, carry_prog_cnt = 0;
+	struct bpf_prog **existing_prog;
+	struct bpf_prog_array *array;
+	int new_prog_idx = 0;
+
+	/* Figure out how many existing progs we need to carry over to
+	 * the new array.
+	 */
+	if (old_array) {
+		existing_prog = old_array->progs;
+		for (; *existing_prog; existing_prog++) {
+			if (*existing_prog != exclude_prog &&
+			    *existing_prog != &dummy_bpf_prog.prog)
+				carry_prog_cnt++;
+			if (*existing_prog == include_prog)
+				return -EEXIST;
+		}
+	}
+
+	/* How many progs (not NULL) will be in the new array? */
+	new_prog_cnt = carry_prog_cnt;
+	if (include_prog)
+		new_prog_cnt += 1;
+
+	/* Do we have any prog (not NULL) in the new array? */
+	if (!new_prog_cnt) {
+		*new_array = NULL;
+		return 0;
+	}
+
+	/* +1 as the end of prog_array is marked with NULL */
+	array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL);
+	if (!array)
+		return -ENOMEM;
+
+	/* Fill in the new prog array */
+	if (carry_prog_cnt) {
+		existing_prog = old_array->progs;
+		for (; *existing_prog; existing_prog++)
+			if (*existing_prog != exclude_prog &&
+			    *existing_prog != &dummy_bpf_prog.prog)
+				array->progs[new_prog_idx++] = *existing_prog;
+	}
+	if (include_prog)
+		array->progs[new_prog_idx++] = include_prog;
+	array->progs[new_prog_idx] = NULL;
+	*new_array = array;
+	return 0;
+}
+
 static void bpf_prog_free_deferred(struct work_struct *work)
 {
 	struct bpf_prog_aux *aux;
@@ -1498,5 +1661,8 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception);
 
+/* These are only used within the BPF_SYSCALL code */
+#ifdef CONFIG_BPF_SYSCALL
 EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_get_type);
 EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_put_rcu);
+#endif
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
new file mode 100644
index 000000000000..ce5b669003b2
--- /dev/null
+++ b/kernel/bpf/cpumap.c
@@ -0,0 +1,706 @@
+/* bpf/cpumap.c
+ *
+ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
+ * Released under terms in GPL version 2.  See COPYING.
+ */
+
+/* The 'cpumap' is primarily used as a backend map for XDP BPF helper
+ * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'.
+ *
+ * Unlike devmap which redirects XDP frames out another NIC device,
+ * this map type redirects raw XDP frames to another CPU.  The remote
+ * CPU will do SKB-allocation and call the normal network stack.
+ *
+ * This is a scalability and isolation mechanism, that allow
+ * separating the early driver network XDP layer, from the rest of the
+ * netstack, and assigning dedicated CPUs for this stage.  This
+ * basically allows for 10G wirespeed pre-filtering via bpf.
+ */
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/ptr_ring.h>
+
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+#include <linux/capability.h>
+#include <trace/events/xdp.h>
+
+#include <linux/netdevice.h>   /* netif_receive_skb_core */
+#include <linux/etherdevice.h> /* eth_type_trans */
+
+/* General idea: XDP packets getting XDP redirected to another CPU,
+ * will maximum be stored/queued for one driver ->poll() call.  It is
+ * guaranteed that setting flush bit and flush operation happen on
+ * same CPU.  Thus, cpu_map_flush operation can deduct via this_cpu_ptr()
+ * which queue in bpf_cpu_map_entry contains packets.
+ */
+
+#define CPU_MAP_BULK_SIZE 8  /* 8 == one cacheline on 64-bit archs */
+struct xdp_bulk_queue {
+	void *q[CPU_MAP_BULK_SIZE];
+	unsigned int count;
+};
+
+/* Struct for every remote "destination" CPU in map */
+struct bpf_cpu_map_entry {
+	u32 cpu;    /* kthread CPU and map index */
+	int map_id; /* Back reference to map */
+	u32 qsize;  /* Queue size placeholder for map lookup */
+
+	/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
+	struct xdp_bulk_queue __percpu *bulkq;
+
+	/* Queue with potential multi-producers, and single-consumer kthread */
+	struct ptr_ring *queue;
+	struct task_struct *kthread;
+	struct work_struct kthread_stop_wq;
+
+	atomic_t refcnt; /* Control when this struct can be free'ed */
+	struct rcu_head rcu;
+};
+
+struct bpf_cpu_map {
+	struct bpf_map map;
+	/* Below members specific for map type */
+	struct bpf_cpu_map_entry **cpu_map;
+	unsigned long __percpu *flush_needed;
+};
+
+static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
+			     struct xdp_bulk_queue *bq);
+
+static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
+{
+	return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
+}
+
+static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_cpu_map *cmap;
+	int err = -ENOMEM;
+	u64 cost;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 || attr->key_size != 4 ||
+	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+		return ERR_PTR(-EINVAL);
+
+	cmap = kzalloc(sizeof(*cmap), GFP_USER);
+	if (!cmap)
+		return ERR_PTR(-ENOMEM);
+
+	/* mandatory map attributes */
+	cmap->map.map_type = attr->map_type;
+	cmap->map.key_size = attr->key_size;
+	cmap->map.value_size = attr->value_size;
+	cmap->map.max_entries = attr->max_entries;
+	cmap->map.map_flags = attr->map_flags;
+	cmap->map.numa_node = bpf_map_attr_numa_node(attr);
+
+	/* Pre-limit array size based on NR_CPUS, not final CPU check */
+	if (cmap->map.max_entries > NR_CPUS) {
+		err = -E2BIG;
+		goto free_cmap;
+	}
+
+	/* make sure page count doesn't overflow */
+	cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *);
+	cost += cpu_map_bitmap_size(attr) * num_possible_cpus();
+	if (cost >= U32_MAX - PAGE_SIZE)
+		goto free_cmap;
+	cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	/* Notice returns -EPERM on if map size is larger than memlock limit */
+	ret = bpf_map_precharge_memlock(cmap->map.pages);
+	if (ret) {
+		err = ret;
+		goto free_cmap;
+	}
+
+	/* A per cpu bitfield with a bit per possible CPU in map  */
+	cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr),
+					    __alignof__(unsigned long));
+	if (!cmap->flush_needed)
+		goto free_cmap;
+
+	/* Alloc array for possible remote "destination" CPUs */
+	cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries *
+					   sizeof(struct bpf_cpu_map_entry *),
+					   cmap->map.numa_node);
+	if (!cmap->cpu_map)
+		goto free_percpu;
+
+	return &cmap->map;
+free_percpu:
+	free_percpu(cmap->flush_needed);
+free_cmap:
+	kfree(cmap);
+	return ERR_PTR(err);
+}
+
+void __cpu_map_queue_destructor(void *ptr)
+{
+	/* The tear-down procedure should have made sure that queue is
+	 * empty.  See __cpu_map_entry_replace() and work-queue
+	 * invoked cpu_map_kthread_stop(). Catch any broken behaviour
+	 * gracefully and warn once.
+	 */
+	if (WARN_ON_ONCE(ptr))
+		page_frag_free(ptr);
+}
+
+static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
+{
+	if (atomic_dec_and_test(&rcpu->refcnt)) {
+		/* The queue should be empty at this point */
+		ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor);
+		kfree(rcpu->queue);
+		kfree(rcpu);
+	}
+}
+
+static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
+{
+	atomic_inc(&rcpu->refcnt);
+}
+
+/* called from workqueue, to workaround syscall using preempt_disable */
+static void cpu_map_kthread_stop(struct work_struct *work)
+{
+	struct bpf_cpu_map_entry *rcpu;
+
+	rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
+
+	/* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
+	 * as it waits until all in-flight call_rcu() callbacks complete.
+	 */
+	rcu_barrier();
+
+	/* kthread_stop will wake_up_process and wait for it to complete */
+	kthread_stop(rcpu->kthread);
+}
+
+/* For now, xdp_pkt is a cpumap internal data structure, with info
+ * carried between enqueue to dequeue. It is mapped into the top
+ * headroom of the packet, to avoid allocating separate mem.
+ */
+struct xdp_pkt {
+	void *data;
+	u16 len;
+	u16 headroom;
+	u16 metasize;
+	struct net_device *dev_rx;
+};
+
+/* Convert xdp_buff to xdp_pkt */
+static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp)
+{
+	struct xdp_pkt *xdp_pkt;
+	int metasize;
+	int headroom;
+
+	/* Assure headroom is available for storing info */
+	headroom = xdp->data - xdp->data_hard_start;
+	metasize = xdp->data - xdp->data_meta;
+	metasize = metasize > 0 ? metasize : 0;
+	if (unlikely((headroom - metasize) < sizeof(*xdp_pkt)))
+		return NULL;
+
+	/* Store info in top of packet */
+	xdp_pkt = xdp->data_hard_start;
+
+	xdp_pkt->data = xdp->data;
+	xdp_pkt->len  = xdp->data_end - xdp->data;
+	xdp_pkt->headroom = headroom - sizeof(*xdp_pkt);
+	xdp_pkt->metasize = metasize;
+
+	return xdp_pkt;
+}
+
+struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
+				  struct xdp_pkt *xdp_pkt)
+{
+	unsigned int frame_size;
+	void *pkt_data_start;
+	struct sk_buff *skb;
+
+	/* build_skb need to place skb_shared_info after SKB end, and
+	 * also want to know the memory "truesize".  Thus, need to
+	 * know the memory frame size backing xdp_buff.
+	 *
+	 * XDP was designed to have PAGE_SIZE frames, but this
+	 * assumption is not longer true with ixgbe and i40e.  It
+	 * would be preferred to set frame_size to 2048 or 4096
+	 * depending on the driver.
+	 *   frame_size = 2048;
+	 *   frame_len  = frame_size - sizeof(*xdp_pkt);
+	 *
+	 * Instead, with info avail, skb_shared_info in placed after
+	 * packet len.  This, unfortunately fakes the truesize.
+	 * Another disadvantage of this approach, the skb_shared_info
+	 * is not at a fixed memory location, with mixed length
+	 * packets, which is bad for cache-line hotness.
+	 */
+	frame_size = SKB_DATA_ALIGN(xdp_pkt->len) + xdp_pkt->headroom +
+		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+	pkt_data_start = xdp_pkt->data - xdp_pkt->headroom;
+	skb = build_skb(pkt_data_start, frame_size);
+	if (!skb)
+		return NULL;
+
+	skb_reserve(skb, xdp_pkt->headroom);
+	__skb_put(skb, xdp_pkt->len);
+	if (xdp_pkt->metasize)
+		skb_metadata_set(skb, xdp_pkt->metasize);
+
+	/* Essential SKB info: protocol and skb->dev */
+	skb->protocol = eth_type_trans(skb, xdp_pkt->dev_rx);
+
+	/* Optional SKB info, currently missing:
+	 * - HW checksum info		(skb->ip_summed)
+	 * - HW RX hash			(skb_set_hash)
+	 * - RX ring dev queue index	(skb_record_rx_queue)
+	 */
+
+	return skb;
+}
+
+static int cpu_map_kthread_run(void *data)
+{
+	struct bpf_cpu_map_entry *rcpu = data;
+
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	/* When kthread gives stop order, then rcpu have been disconnected
+	 * from map, thus no new packets can enter. Remaining in-flight
+	 * per CPU stored packets are flushed to this queue.  Wait honoring
+	 * kthread_stop signal until queue is empty.
+	 */
+	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
+		unsigned int processed = 0, drops = 0, sched = 0;
+		struct xdp_pkt *xdp_pkt;
+
+		/* Release CPU reschedule checks */
+		if (__ptr_ring_empty(rcpu->queue)) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			/* Recheck to avoid lost wake-up */
+			if (__ptr_ring_empty(rcpu->queue)) {
+				schedule();
+				sched = 1;
+			} else {
+				__set_current_state(TASK_RUNNING);
+			}
+		} else {
+			sched = cond_resched();
+		}
+
+		/* Process packets in rcpu->queue */
+		local_bh_disable();
+		/*
+		 * The bpf_cpu_map_entry is single consumer, with this
+		 * kthread CPU pinned. Lockless access to ptr_ring
+		 * consume side valid as no-resize allowed of queue.
+		 */
+		while ((xdp_pkt = __ptr_ring_consume(rcpu->queue))) {
+			struct sk_buff *skb;
+			int ret;
+
+			skb = cpu_map_build_skb(rcpu, xdp_pkt);
+			if (!skb) {
+				page_frag_free(xdp_pkt);
+				continue;
+			}
+
+			/* Inject into network stack */
+			ret = netif_receive_skb_core(skb);
+			if (ret == NET_RX_DROP)
+				drops++;
+
+			/* Limit BH-disable period */
+			if (++processed == 8)
+				break;
+		}
+		/* Feedback loop via tracepoint */
+		trace_xdp_cpumap_kthread(rcpu->map_id, processed, drops, sched);
+
+		local_bh_enable(); /* resched point, may call do_softirq() */
+	}
+	__set_current_state(TASK_RUNNING);
+
+	put_cpu_map_entry(rcpu);
+	return 0;
+}
+
+struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id)
+{
+	gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN;
+	struct bpf_cpu_map_entry *rcpu;
+	int numa, err;
+
+	/* Have map->numa_node, but choose node of redirect target CPU */
+	numa = cpu_to_node(cpu);
+
+	rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa);
+	if (!rcpu)
+		return NULL;
+
+	/* Alloc percpu bulkq */
+	rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq),
+					 sizeof(void *), gfp);
+	if (!rcpu->bulkq)
+		goto free_rcu;
+
+	/* Alloc queue */
+	rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa);
+	if (!rcpu->queue)
+		goto free_bulkq;
+
+	err = ptr_ring_init(rcpu->queue, qsize, gfp);
+	if (err)
+		goto free_queue;
+
+	rcpu->cpu    = cpu;
+	rcpu->map_id = map_id;
+	rcpu->qsize  = qsize;
+
+	/* Setup kthread */
+	rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
+					       "cpumap/%d/map:%d", cpu, map_id);
+	if (IS_ERR(rcpu->kthread))
+		goto free_ptr_ring;
+
+	get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
+	get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
+
+	/* Make sure kthread runs on a single CPU */
+	kthread_bind(rcpu->kthread, cpu);
+	wake_up_process(rcpu->kthread);
+
+	return rcpu;
+
+free_ptr_ring:
+	ptr_ring_cleanup(rcpu->queue, NULL);
+free_queue:
+	kfree(rcpu->queue);
+free_bulkq:
+	free_percpu(rcpu->bulkq);
+free_rcu:
+	kfree(rcpu);
+	return NULL;
+}
+
+void __cpu_map_entry_free(struct rcu_head *rcu)
+{
+	struct bpf_cpu_map_entry *rcpu;
+	int cpu;
+
+	/* This cpu_map_entry have been disconnected from map and one
+	 * RCU graze-period have elapsed.  Thus, XDP cannot queue any
+	 * new packets and cannot change/set flush_needed that can
+	 * find this entry.
+	 */
+	rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu);
+
+	/* Flush remaining packets in percpu bulkq */
+	for_each_online_cpu(cpu) {
+		struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
+
+		/* No concurrent bq_enqueue can run at this point */
+		bq_flush_to_queue(rcpu, bq);
+	}
+	free_percpu(rcpu->bulkq);
+	/* Cannot kthread_stop() here, last put free rcpu resources */
+	put_cpu_map_entry(rcpu);
+}
+
+/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to
+ * ensure any driver rcu critical sections have completed, but this
+ * does not guarantee a flush has happened yet. Because driver side
+ * rcu_read_lock/unlock only protects the running XDP program.  The
+ * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a
+ * pending flush op doesn't fail.
+ *
+ * The bpf_cpu_map_entry is still used by the kthread, and there can
+ * still be pending packets (in queue and percpu bulkq).  A refcnt
+ * makes sure to last user (kthread_stop vs. call_rcu) free memory
+ * resources.
+ *
+ * The rcu callback __cpu_map_entry_free flush remaining packets in
+ * percpu bulkq to queue.  Due to caller map_delete_elem() disable
+ * preemption, cannot call kthread_stop() to make sure queue is empty.
+ * Instead a work_queue is started for stopping kthread,
+ * cpu_map_kthread_stop, which waits for an RCU graze period before
+ * stopping kthread, emptying the queue.
+ */
+void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
+			     u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
+{
+	struct bpf_cpu_map_entry *old_rcpu;
+
+	old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu);
+	if (old_rcpu) {
+		call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
+		INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);
+		schedule_work(&old_rcpu->kthread_stop_wq);
+	}
+}
+
+int cpu_map_delete_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	u32 key_cpu = *(u32 *)key;
+
+	if (key_cpu >= map->max_entries)
+		return -EINVAL;
+
+	/* notice caller map_delete_elem() use preempt_disable() */
+	__cpu_map_entry_replace(cmap, key_cpu, NULL);
+	return 0;
+}
+
+int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
+				u64 map_flags)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	struct bpf_cpu_map_entry *rcpu;
+
+	/* Array index key correspond to CPU number */
+	u32 key_cpu = *(u32 *)key;
+	/* Value is the queue size */
+	u32 qsize = *(u32 *)value;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		return -EINVAL;
+	if (unlikely(key_cpu >= cmap->map.max_entries))
+		return -E2BIG;
+	if (unlikely(map_flags == BPF_NOEXIST))
+		return -EEXIST;
+	if (unlikely(qsize > 16384)) /* sanity limit on qsize */
+		return -EOVERFLOW;
+
+	/* Make sure CPU is a valid possible cpu */
+	if (!cpu_possible(key_cpu))
+		return -ENODEV;
+
+	if (qsize == 0) {
+		rcpu = NULL; /* Same as deleting */
+	} else {
+		/* Updating qsize cause re-allocation of bpf_cpu_map_entry */
+		rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id);
+		if (!rcpu)
+			return -ENOMEM;
+	}
+	rcu_read_lock();
+	__cpu_map_entry_replace(cmap, key_cpu, rcpu);
+	rcu_read_unlock();
+	return 0;
+}
+
+void cpu_map_free(struct bpf_map *map)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	int cpu;
+	u32 i;
+
+	/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+	 * so the bpf programs (can be more than one that used this map) were
+	 * disconnected from events. Wait for outstanding critical sections in
+	 * these programs to complete. The rcu critical section only guarantees
+	 * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map.
+	 * It does __not__ ensure pending flush operations (if any) are
+	 * complete.
+	 */
+	synchronize_rcu();
+
+	/* To ensure all pending flush operations have completed wait for flush
+	 * bitmap to indicate all flush_needed bits to be zero on _all_ cpus.
+	 * Because the above synchronize_rcu() ensures the map is disconnected
+	 * from the program we can assume no new bits will be set.
+	 */
+	for_each_online_cpu(cpu) {
+		unsigned long *bitmap = per_cpu_ptr(cmap->flush_needed, cpu);
+
+		while (!bitmap_empty(bitmap, cmap->map.max_entries))
+			cond_resched();
+	}
+
+	/* For cpu_map the remote CPUs can still be using the entries
+	 * (struct bpf_cpu_map_entry).
+	 */
+	for (i = 0; i < cmap->map.max_entries; i++) {
+		struct bpf_cpu_map_entry *rcpu;
+
+		rcpu = READ_ONCE(cmap->cpu_map[i]);
+		if (!rcpu)
+			continue;
+
+		/* bq flush and cleanup happens after RCU graze-period */
+		__cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
+	}
+	free_percpu(cmap->flush_needed);
+	bpf_map_area_free(cmap->cpu_map);
+	kfree(cmap);
+}
+
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	struct bpf_cpu_map_entry *rcpu;
+
+	if (key >= map->max_entries)
+		return NULL;
+
+	rcpu = READ_ONCE(cmap->cpu_map[key]);
+	return rcpu;
+}
+
+static void *cpu_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_cpu_map_entry *rcpu =
+		__cpu_map_lookup_elem(map, *(u32 *)key);
+
+	return rcpu ? &rcpu->qsize : NULL;
+}
+
+static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	u32 index = key ? *(u32 *)key : U32_MAX;
+	u32 *next = next_key;
+
+	if (index >= cmap->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == cmap->map.max_entries - 1)
+		return -ENOENT;
+	*next = index + 1;
+	return 0;
+}
+
+const struct bpf_map_ops cpu_map_ops = {
+	.map_alloc		= cpu_map_alloc,
+	.map_free		= cpu_map_free,
+	.map_delete_elem	= cpu_map_delete_elem,
+	.map_update_elem	= cpu_map_update_elem,
+	.map_lookup_elem	= cpu_map_lookup_elem,
+	.map_get_next_key	= cpu_map_get_next_key,
+};
+
+static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
+			     struct xdp_bulk_queue *bq)
+{
+	unsigned int processed = 0, drops = 0;
+	const int to_cpu = rcpu->cpu;
+	struct ptr_ring *q;
+	int i;
+
+	if (unlikely(!bq->count))
+		return 0;
+
+	q = rcpu->queue;
+	spin_lock(&q->producer_lock);
+
+	for (i = 0; i < bq->count; i++) {
+		void *xdp_pkt = bq->q[i];
+		int err;
+
+		err = __ptr_ring_produce(q, xdp_pkt);
+		if (err) {
+			drops++;
+			page_frag_free(xdp_pkt); /* Free xdp_pkt */
+		}
+		processed++;
+	}
+	bq->count = 0;
+	spin_unlock(&q->producer_lock);
+
+	/* Feedback loop via tracepoints */
+	trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu);
+	return 0;
+}
+
+/* Runs under RCU-read-side, plus in softirq under NAPI protection.
+ * Thus, safe percpu variable access.
+ */
+static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt)
+{
+	struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
+
+	if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
+		bq_flush_to_queue(rcpu, bq);
+
+	/* Notice, xdp_buff/page MUST be queued here, long enough for
+	 * driver to code invoking us to finished, due to driver
+	 * (e.g. ixgbe) recycle tricks based on page-refcnt.
+	 *
+	 * Thus, incoming xdp_pkt is always queued here (else we race
+	 * with another CPU on page-refcnt and remaining driver code).
+	 * Queue time is very short, as driver will invoke flush
+	 * operation, when completing napi->poll call.
+	 */
+	bq->q[bq->count++] = xdp_pkt;
+	return 0;
+}
+
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+		    struct net_device *dev_rx)
+{
+	struct xdp_pkt *xdp_pkt;
+
+	xdp_pkt = convert_to_xdp_pkt(xdp);
+	if (unlikely(!xdp_pkt))
+		return -EOVERFLOW;
+
+	/* Info needed when constructing SKB on remote CPU */
+	xdp_pkt->dev_rx = dev_rx;
+
+	bq_enqueue(rcpu, xdp_pkt);
+	return 0;
+}
+
+void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed);
+
+	__set_bit(bit, bitmap);
+}
+
+void __cpu_map_flush(struct bpf_map *map)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed);
+	u32 bit;
+
+	/* The napi->poll softirq makes sure __cpu_map_insert_ctx()
+	 * and __cpu_map_flush() happen on same CPU. Thus, the percpu
+	 * bitmap indicate which percpu bulkq have packets.
+	 */
+	for_each_set_bit(bit, bitmap, map->max_entries) {
+		struct bpf_cpu_map_entry *rcpu = READ_ONCE(cmap->cpu_map[bit]);
+		struct xdp_bulk_queue *bq;
+
+		/* This is possible if entry is removed by user space
+		 * between xdp redirect and flush op.
+		 */
+		if (unlikely(!rcpu))
+			continue;
+
+		__clear_bit(bit, bitmap);
+
+		/* Flush all frames in bulkq to real queue */
+		bq = this_cpu_ptr(rcpu->bulkq);
+		bq_flush_to_queue(rcpu, bq);
+
+		/* If already running, costs spin_lock_irqsave + smb_mb */
+		wake_up_process(rcpu->kthread);
+	}
+}
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index e745d6a88224..ebdef54bf7df 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -50,6 +50,9 @@
 #include <linux/bpf.h>
 #include <linux/filter.h>
 
+#define DEV_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
 struct bpf_dtab_netdev {
 	struct net_device *dev;
 	struct bpf_dtab *dtab;
@@ -83,7 +86,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+	    attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
 	dtab = kzalloc(sizeof(*dtab), GFP_USER);
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
new file mode 100644
index 000000000000..e682850c9715
--- /dev/null
+++ b/kernel/bpf/disasm.c
@@ -0,0 +1,214 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/bpf.h>
+
+#include "disasm.h"
+
+#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x)
+static const char * const func_id_str[] = {
+	__BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN)
+};
+#undef __BPF_FUNC_STR_FN
+
+const char *func_id_name(int id)
+{
+	BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID);
+
+	if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id])
+		return func_id_str[id];
+	else
+		return "unknown";
+}
+
+const char *const bpf_class_string[8] = {
+	[BPF_LD]    = "ld",
+	[BPF_LDX]   = "ldx",
+	[BPF_ST]    = "st",
+	[BPF_STX]   = "stx",
+	[BPF_ALU]   = "alu",
+	[BPF_JMP]   = "jmp",
+	[BPF_RET]   = "BUG",
+	[BPF_ALU64] = "alu64",
+};
+
+const char *const bpf_alu_string[16] = {
+	[BPF_ADD >> 4]  = "+=",
+	[BPF_SUB >> 4]  = "-=",
+	[BPF_MUL >> 4]  = "*=",
+	[BPF_DIV >> 4]  = "/=",
+	[BPF_OR  >> 4]  = "|=",
+	[BPF_AND >> 4]  = "&=",
+	[BPF_LSH >> 4]  = "<<=",
+	[BPF_RSH >> 4]  = ">>=",
+	[BPF_NEG >> 4]  = "neg",
+	[BPF_MOD >> 4]  = "%=",
+	[BPF_XOR >> 4]  = "^=",
+	[BPF_MOV >> 4]  = "=",
+	[BPF_ARSH >> 4] = "s>>=",
+	[BPF_END >> 4]  = "endian",
+};
+
+static const char *const bpf_ldst_string[] = {
+	[BPF_W >> 3]  = "u32",
+	[BPF_H >> 3]  = "u16",
+	[BPF_B >> 3]  = "u8",
+	[BPF_DW >> 3] = "u64",
+};
+
+static const char *const bpf_jmp_string[16] = {
+	[BPF_JA >> 4]   = "jmp",
+	[BPF_JEQ >> 4]  = "==",
+	[BPF_JGT >> 4]  = ">",
+	[BPF_JLT >> 4]  = "<",
+	[BPF_JGE >> 4]  = ">=",
+	[BPF_JLE >> 4]  = "<=",
+	[BPF_JSET >> 4] = "&",
+	[BPF_JNE >> 4]  = "!=",
+	[BPF_JSGT >> 4] = "s>",
+	[BPF_JSLT >> 4] = "s<",
+	[BPF_JSGE >> 4] = "s>=",
+	[BPF_JSLE >> 4] = "s<=",
+	[BPF_CALL >> 4] = "call",
+	[BPF_EXIT >> 4] = "exit",
+};
+
+static void print_bpf_end_insn(bpf_insn_print_cb verbose,
+			       struct bpf_verifier_env *env,
+			       const struct bpf_insn *insn)
+{
+	verbose(env, "(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg,
+		BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le",
+		insn->imm, insn->dst_reg);
+}
+
+void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env,
+		    const struct bpf_insn *insn, bool allow_ptr_leaks)
+{
+	u8 class = BPF_CLASS(insn->code);
+
+	if (class == BPF_ALU || class == BPF_ALU64) {
+		if (BPF_OP(insn->code) == BPF_END) {
+			if (class == BPF_ALU64)
+				verbose(env, "BUG_alu64_%02x\n", insn->code);
+			else
+				print_bpf_end_insn(verbose, env, insn);
+		} else if (BPF_OP(insn->code) == BPF_NEG) {
+			verbose(env, "(%02x) r%d = %s-r%d\n",
+				insn->code, insn->dst_reg,
+				class == BPF_ALU ? "(u32) " : "",
+				insn->dst_reg);
+		} else if (BPF_SRC(insn->code) == BPF_X) {
+			verbose(env, "(%02x) %sr%d %s %sr%d\n",
+				insn->code, class == BPF_ALU ? "(u32) " : "",
+				insn->dst_reg,
+				bpf_alu_string[BPF_OP(insn->code) >> 4],
+				class == BPF_ALU ? "(u32) " : "",
+				insn->src_reg);
+		} else {
+			verbose(env, "(%02x) %sr%d %s %s%d\n",
+				insn->code, class == BPF_ALU ? "(u32) " : "",
+				insn->dst_reg,
+				bpf_alu_string[BPF_OP(insn->code) >> 4],
+				class == BPF_ALU ? "(u32) " : "",
+				insn->imm);
+		}
+	} else if (class == BPF_STX) {
+		if (BPF_MODE(insn->code) == BPF_MEM)
+			verbose(env, "(%02x) *(%s *)(r%d %+d) = r%d\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->dst_reg,
+				insn->off, insn->src_reg);
+		else if (BPF_MODE(insn->code) == BPF_XADD)
+			verbose(env, "(%02x) lock *(%s *)(r%d %+d) += r%d\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->dst_reg, insn->off,
+				insn->src_reg);
+		else
+			verbose(env, "BUG_%02x\n", insn->code);
+	} else if (class == BPF_ST) {
+		if (BPF_MODE(insn->code) != BPF_MEM) {
+			verbose(env, "BUG_st_%02x\n", insn->code);
+			return;
+		}
+		verbose(env, "(%02x) *(%s *)(r%d %+d) = %d\n",
+			insn->code,
+			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+			insn->dst_reg,
+			insn->off, insn->imm);
+	} else if (class == BPF_LDX) {
+		if (BPF_MODE(insn->code) != BPF_MEM) {
+			verbose(env, "BUG_ldx_%02x\n", insn->code);
+			return;
+		}
+		verbose(env, "(%02x) r%d = *(%s *)(r%d %+d)\n",
+			insn->code, insn->dst_reg,
+			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+			insn->src_reg, insn->off);
+	} else if (class == BPF_LD) {
+		if (BPF_MODE(insn->code) == BPF_ABS) {
+			verbose(env, "(%02x) r0 = *(%s *)skb[%d]\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->imm);
+		} else if (BPF_MODE(insn->code) == BPF_IND) {
+			verbose(env, "(%02x) r0 = *(%s *)skb[r%d + %d]\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->src_reg, insn->imm);
+		} else if (BPF_MODE(insn->code) == BPF_IMM &&
+			   BPF_SIZE(insn->code) == BPF_DW) {
+			/* At this point, we already made sure that the second
+			 * part of the ldimm64 insn is accessible.
+			 */
+			u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
+			bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+
+			if (map_ptr && !allow_ptr_leaks)
+				imm = 0;
+
+			verbose(env, "(%02x) r%d = 0x%llx\n", insn->code,
+				insn->dst_reg, (unsigned long long)imm);
+		} else {
+			verbose(env, "BUG_ld_%02x\n", insn->code);
+			return;
+		}
+	} else if (class == BPF_JMP) {
+		u8 opcode = BPF_OP(insn->code);
+
+		if (opcode == BPF_CALL) {
+			verbose(env, "(%02x) call %s#%d\n", insn->code,
+				func_id_name(insn->imm), insn->imm);
+		} else if (insn->code == (BPF_JMP | BPF_JA)) {
+			verbose(env, "(%02x) goto pc%+d\n",
+				insn->code, insn->off);
+		} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
+			verbose(env, "(%02x) exit\n", insn->code);
+		} else if (BPF_SRC(insn->code) == BPF_X) {
+			verbose(env, "(%02x) if r%d %s r%d goto pc%+d\n",
+				insn->code, insn->dst_reg,
+				bpf_jmp_string[BPF_OP(insn->code) >> 4],
+				insn->src_reg, insn->off);
+		} else {
+			verbose(env, "(%02x) if r%d %s 0x%x goto pc%+d\n",
+				insn->code, insn->dst_reg,
+				bpf_jmp_string[BPF_OP(insn->code) >> 4],
+				insn->imm, insn->off);
+		}
+	} else {
+		verbose(env, "(%02x) %s\n",
+			insn->code, bpf_class_string[class]);
+	}
+}
diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h
new file mode 100644
index 000000000000..8de977e420b6
--- /dev/null
+++ b/kernel/bpf/disasm.h
@@ -0,0 +1,32 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef __BPF_DISASM_H__
+#define __BPF_DISASM_H__
+
+#include <linux/bpf.h>
+#include <linux/kernel.h>
+#include <linux/stringify.h>
+
+extern const char *const bpf_alu_string[16];
+extern const char *const bpf_class_string[8];
+
+const char *func_id_name(int id);
+
+struct bpf_verifier_env;
+typedef void (*bpf_insn_print_cb)(struct bpf_verifier_env *env,
+				  const char *, ...);
+void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env,
+		    const struct bpf_insn *insn, bool allow_ptr_leaks);
+
+#endif
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 6533f08d1238..e469e05c8e83 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -18,8 +18,9 @@
 #include "bpf_lru_list.h"
 #include "map_in_map.h"
 
-#define HTAB_CREATE_FLAG_MASK \
-	(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE)
+#define HTAB_CREATE_FLAG_MASK						\
+	(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE |	\
+	 BPF_F_RDONLY | BPF_F_WRONLY)
 
 struct bucket {
 	struct hlist_nulls_head head;
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index be1dde967208..01aaef1a77c5 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -295,7 +295,7 @@ out:
 }
 
 static void *bpf_obj_do_get(const struct filename *pathname,
-			    enum bpf_type *type)
+			    enum bpf_type *type, int flags)
 {
 	struct inode *inode;
 	struct path path;
@@ -307,7 +307,7 @@ static void *bpf_obj_do_get(const struct filename *pathname,
 		return ERR_PTR(ret);
 
 	inode = d_backing_inode(path.dentry);
-	ret = inode_permission(inode, MAY_WRITE);
+	ret = inode_permission(inode, ACC_MODE(flags));
 	if (ret)
 		goto out;
 
@@ -326,18 +326,23 @@ out:
 	return ERR_PTR(ret);
 }
 
-int bpf_obj_get_user(const char __user *pathname)
+int bpf_obj_get_user(const char __user *pathname, int flags)
 {
 	enum bpf_type type = BPF_TYPE_UNSPEC;
 	struct filename *pname;
 	int ret = -ENOENT;
+	int f_flags;
 	void *raw;
 
+	f_flags = bpf_get_file_flag(flags);
+	if (f_flags < 0)
+		return f_flags;
+
 	pname = getname(pathname);
 	if (IS_ERR(pname))
 		return PTR_ERR(pname);
 
-	raw = bpf_obj_do_get(pname, &type);
+	raw = bpf_obj_do_get(pname, &type, f_flags);
 	if (IS_ERR(raw)) {
 		ret = PTR_ERR(raw);
 		goto out;
@@ -346,7 +351,7 @@ int bpf_obj_get_user(const char __user *pathname)
 	if (type == BPF_TYPE_PROG)
 		ret = bpf_prog_new_fd(raw);
 	else if (type == BPF_TYPE_MAP)
-		ret = bpf_map_new_fd(raw);
+		ret = bpf_map_new_fd(raw, f_flags);
 	else
 		goto out;
 
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 1b767844a76f..885e45479680 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -389,10 +389,99 @@ out:
 	return ret;
 }
 
-static int trie_delete_elem(struct bpf_map *map, void *key)
+/* Called from syscall or from eBPF program */
+static int trie_delete_elem(struct bpf_map *map, void *_key)
 {
-	/* TODO */
-	return -ENOSYS;
+	struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
+	struct bpf_lpm_trie_key *key = _key;
+	struct lpm_trie_node __rcu **trim, **trim2;
+	struct lpm_trie_node *node, *parent;
+	unsigned long irq_flags;
+	unsigned int next_bit;
+	size_t matchlen = 0;
+	int ret = 0;
+
+	if (key->prefixlen > trie->max_prefixlen)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&trie->lock, irq_flags);
+
+	/* Walk the tree looking for an exact key/length match and keeping
+	 * track of the path we traverse.  We will need to know the node
+	 * we wish to delete, and the slot that points to the node we want
+	 * to delete.  We may also need to know the nodes parent and the
+	 * slot that contains it.
+	 */
+	trim = &trie->root;
+	trim2 = trim;
+	parent = NULL;
+	while ((node = rcu_dereference_protected(
+		       *trim, lockdep_is_held(&trie->lock)))) {
+		matchlen = longest_prefix_match(trie, node, key);
+
+		if (node->prefixlen != matchlen ||
+		    node->prefixlen == key->prefixlen)
+			break;
+
+		parent = node;
+		trim2 = trim;
+		next_bit = extract_bit(key->data, node->prefixlen);
+		trim = &node->child[next_bit];
+	}
+
+	if (!node || node->prefixlen != key->prefixlen ||
+	    (node->flags & LPM_TREE_NODE_FLAG_IM)) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	trie->n_entries--;
+
+	/* If the node we are removing has two children, simply mark it
+	 * as intermediate and we are done.
+	 */
+	if (rcu_access_pointer(node->child[0]) &&
+	    rcu_access_pointer(node->child[1])) {
+		node->flags |= LPM_TREE_NODE_FLAG_IM;
+		goto out;
+	}
+
+	/* If the parent of the node we are about to delete is an intermediate
+	 * node, and the deleted node doesn't have any children, we can delete
+	 * the intermediate parent as well and promote its other child
+	 * up the tree.  Doing this maintains the invariant that all
+	 * intermediate nodes have exactly 2 children and that there are no
+	 * unnecessary intermediate nodes in the tree.
+	 */
+	if (parent && (parent->flags & LPM_TREE_NODE_FLAG_IM) &&
+	    !node->child[0] && !node->child[1]) {
+		if (node == rcu_access_pointer(parent->child[0]))
+			rcu_assign_pointer(
+				*trim2, rcu_access_pointer(parent->child[1]));
+		else
+			rcu_assign_pointer(
+				*trim2, rcu_access_pointer(parent->child[0]));
+		kfree_rcu(parent, rcu);
+		kfree_rcu(node, rcu);
+		goto out;
+	}
+
+	/* The node we are removing has either zero or one child. If there
+	 * is a child, move it into the removed node's slot then delete
+	 * the node.  Otherwise just clear the slot and delete the node.
+	 */
+	if (node->child[0])
+		rcu_assign_pointer(*trim, rcu_access_pointer(node->child[0]));
+	else if (node->child[1])
+		rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1]));
+	else
+		RCU_INIT_POINTER(*trim, NULL);
+	kfree_rcu(node, rcu);
+
+out:
+	raw_spin_unlock_irqrestore(&trie->lock, irq_flags);
+
+	return ret;
 }
 
 #define LPM_DATA_SIZE_MAX	256
@@ -406,7 +495,8 @@ static int trie_delete_elem(struct bpf_map *map, void *key)
 #define LPM_KEY_SIZE_MAX	LPM_KEY_SIZE(LPM_DATA_SIZE_MAX)
 #define LPM_KEY_SIZE_MIN	LPM_KEY_SIZE(LPM_DATA_SIZE_MIN)
 
-#define LPM_CREATE_FLAG_MASK	(BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE)
+#define LPM_CREATE_FLAG_MASK	(BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE |	\
+				 BPF_F_RDONLY | BPF_F_WRONLY)
 
 static struct bpf_map *trie_alloc(union bpf_attr *attr)
 {
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index dbd7b322a86b..5ee2e41893d9 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -41,6 +41,9 @@
 #include <net/strparser.h>
 #include <net/tcp.h>
 
+#define SOCK_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
 struct bpf_stab {
 	struct bpf_map map;
 	struct sock **sock_map;
@@ -122,7 +125,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
 	 */
 	TCP_SKB_CB(skb)->bpf.map = NULL;
 	skb->sk = psock->sock;
-	bpf_compute_data_end_sk_skb(skb);
+	bpf_compute_data_pointers(skb);
 	preempt_disable();
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
 	preempt_enable();
@@ -385,7 +388,7 @@ static int smap_parse_func_strparser(struct strparser *strp,
 	 * any socket yet.
 	 */
 	skb->sk = psock->sock;
-	bpf_compute_data_end_sk_skb(skb);
+	bpf_compute_data_pointers(skb);
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
 	skb->sk = NULL;
 	rcu_read_unlock();
@@ -508,7 +511,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+	    attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
 	if (attr->value_size > KMALLOC_MAX_SIZE)
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 135be433e9a0..a15bc636cc98 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -11,6 +11,9 @@
 #include <linux/perf_event.h>
 #include "percpu_freelist.h"
 
+#define STACK_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
 struct stack_map_bucket {
 	struct pcpu_freelist_node fnode;
 	u32 hash;
@@ -60,7 +63,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	if (!capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
-	if (attr->map_flags & ~BPF_F_NUMA_NODE)
+	if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
 	/* check sanity of attributes */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 25d074920a00..323be2473c4b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -23,6 +23,9 @@
 #include <linux/version.h>
 #include <linux/kernel.h>
 #include <linux/idr.h>
+#include <linux/cred.h>
+#include <linux/timekeeping.h>
+#include <linux/ctype.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
 			   (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
@@ -31,6 +34,8 @@
 #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
 #define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map))
 
+#define BPF_OBJ_FLAG_MASK   (BPF_F_RDONLY | BPF_F_WRONLY)
+
 DEFINE_PER_CPU(int, bpf_prog_active);
 static DEFINE_IDR(prog_idr);
 static DEFINE_SPINLOCK(prog_idr_lock);
@@ -207,6 +212,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
 	struct bpf_map *map = container_of(work, struct bpf_map, work);
 
 	bpf_map_uncharge_memlock(map);
+	security_bpf_map_free(map);
 	/* implementation dependent freeing */
 	map->ops->map_free(map);
 }
@@ -291,17 +297,54 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 }
 #endif
 
-static const struct file_operations bpf_map_fops = {
+static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz,
+			      loff_t *ppos)
+{
+	/* We need this handler such that alloc_file() enables
+	 * f_mode with FMODE_CAN_READ.
+	 */
+	return -EINVAL;
+}
+
+static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf,
+			       size_t siz, loff_t *ppos)
+{
+	/* We need this handler such that alloc_file() enables
+	 * f_mode with FMODE_CAN_WRITE.
+	 */
+	return -EINVAL;
+}
+
+const struct file_operations bpf_map_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_map_show_fdinfo,
 #endif
 	.release	= bpf_map_release,
+	.read		= bpf_dummy_read,
+	.write		= bpf_dummy_write,
 };
 
-int bpf_map_new_fd(struct bpf_map *map)
+int bpf_map_new_fd(struct bpf_map *map, int flags)
 {
+	int ret;
+
+	ret = security_bpf_map(map, OPEN_FMODE(flags));
+	if (ret < 0)
+		return ret;
+
 	return anon_inode_getfd("bpf-map", &bpf_map_fops, map,
-				O_RDWR | O_CLOEXEC);
+				flags | O_CLOEXEC);
+}
+
+int bpf_get_file_flag(int flags)
+{
+	if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY))
+		return -EINVAL;
+	if (flags & BPF_F_RDONLY)
+		return O_RDONLY;
+	if (flags & BPF_F_WRONLY)
+		return O_WRONLY;
+	return O_RDWR;
 }
 
 /* helper macro to check that unused fields 'union bpf_attr' are zero */
@@ -312,18 +355,46 @@ int bpf_map_new_fd(struct bpf_map *map)
 		   offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
 		   sizeof(attr->CMD##_LAST_FIELD)) != NULL
 
-#define BPF_MAP_CREATE_LAST_FIELD numa_node
+/* dst and src must have at least BPF_OBJ_NAME_LEN number of bytes.
+ * Return 0 on success and < 0 on error.
+ */
+static int bpf_obj_name_cpy(char *dst, const char *src)
+{
+	const char *end = src + BPF_OBJ_NAME_LEN;
+
+	memset(dst, 0, BPF_OBJ_NAME_LEN);
+
+	/* Copy all isalnum() and '_' char */
+	while (src < end && *src) {
+		if (!isalnum(*src) && *src != '_')
+			return -EINVAL;
+		*dst++ = *src++;
+	}
+
+	/* No '\0' found in BPF_OBJ_NAME_LEN number of bytes */
+	if (src == end)
+		return -EINVAL;
+
+	return 0;
+}
+
+#define BPF_MAP_CREATE_LAST_FIELD map_name
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
 	int numa_node = bpf_map_attr_numa_node(attr);
 	struct bpf_map *map;
+	int f_flags;
 	int err;
 
 	err = CHECK_ATTR(BPF_MAP_CREATE);
 	if (err)
 		return -EINVAL;
 
+	f_flags = bpf_get_file_flag(attr->map_flags);
+	if (f_flags < 0)
+		return f_flags;
+
 	if (numa_node != NUMA_NO_NODE &&
 	    ((unsigned int)numa_node >= nr_node_ids ||
 	     !node_online(numa_node)))
@@ -334,18 +405,26 @@ static int map_create(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
+	err = bpf_obj_name_cpy(map->name, attr->map_name);
+	if (err)
+		goto free_map_nouncharge;
+
 	atomic_set(&map->refcnt, 1);
 	atomic_set(&map->usercnt, 1);
 
-	err = bpf_map_charge_memlock(map);
+	err = security_bpf_map_alloc(map);
 	if (err)
 		goto free_map_nouncharge;
 
+	err = bpf_map_charge_memlock(map);
+	if (err)
+		goto free_map_sec;
+
 	err = bpf_map_alloc_id(map);
 	if (err)
 		goto free_map;
 
-	err = bpf_map_new_fd(map);
+	err = bpf_map_new_fd(map, f_flags);
 	if (err < 0) {
 		/* failed to allocate fd.
 		 * bpf_map_put() is needed because the above
@@ -362,6 +441,8 @@ static int map_create(union bpf_attr *attr)
 
 free_map:
 	bpf_map_uncharge_memlock(map);
+free_map_sec:
+	security_bpf_map_free(map);
 free_map_nouncharge:
 	map->ops->map_free(map);
 	return err;
@@ -460,6 +541,11 @@ static int map_lookup_elem(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
+	if (!(f.file->f_mode & FMODE_CAN_READ)) {
+		err = -EPERM;
+		goto err_put;
+	}
+
 	key = memdup_user(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
@@ -540,6 +626,11 @@ static int map_update_elem(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
+	if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+		err = -EPERM;
+		goto err_put;
+	}
+
 	key = memdup_user(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
@@ -562,6 +653,12 @@ static int map_update_elem(union bpf_attr *attr)
 	if (copy_from_user(value, uvalue, value_size) != 0)
 		goto free_value;
 
+	/* Need to create a kthread, thus must support schedule */
+	if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+		err = map->ops->map_update_elem(map, key, value, attr->flags);
+		goto out;
+	}
+
 	/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
 	 * inside bpf map update or delete otherwise deadlocks are possible
 	 */
@@ -592,7 +689,7 @@ static int map_update_elem(union bpf_attr *attr)
 	}
 	__this_cpu_dec(bpf_prog_active);
 	preempt_enable();
-
+out:
 	if (!err)
 		trace_bpf_map_update_elem(map, ufd, key, value);
 free_value:
@@ -623,6 +720,11 @@ static int map_delete_elem(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
+	if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+		err = -EPERM;
+		goto err_put;
+	}
+
 	key = memdup_user(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
@@ -666,6 +768,11 @@ static int map_get_next_key(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
+	if (!(f.file->f_mode & FMODE_CAN_READ)) {
+		err = -EPERM;
+		goto err_put;
+	}
+
 	if (ukey) {
 		key = memdup_user(ukey, map->key_size);
 		if (IS_ERR(key)) {
@@ -703,9 +810,9 @@ err_put:
 	return err;
 }
 
-static const struct bpf_verifier_ops * const bpf_prog_types[] = {
-#define BPF_PROG_TYPE(_id, _ops) \
-	[_id] = &_ops,
+static const struct bpf_prog_ops * const bpf_prog_types[] = {
+#define BPF_PROG_TYPE(_id, _name) \
+	[_id] = & _name ## _prog_ops,
 #define BPF_MAP_TYPE(_id, _ops)
 #include <linux/bpf_types.h>
 #undef BPF_PROG_TYPE
@@ -820,6 +927,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 
 	free_used_maps(aux);
 	bpf_prog_uncharge_memlock(aux->prog);
+	security_bpf_prog_free(aux);
 	bpf_prog_free(aux->prog);
 }
 
@@ -867,15 +975,23 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
 }
 #endif
 
-static const struct file_operations bpf_prog_fops = {
+const struct file_operations bpf_prog_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_prog_show_fdinfo,
 #endif
 	.release	= bpf_prog_release,
+	.read		= bpf_dummy_read,
+	.write		= bpf_dummy_write,
 };
 
 int bpf_prog_new_fd(struct bpf_prog *prog)
 {
+	int ret;
+
+	ret = security_bpf_prog(prog);
+	if (ret < 0)
+		return ret;
+
 	return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog,
 				O_RDWR | O_CLOEXEC);
 }
@@ -973,7 +1089,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
 EXPORT_SYMBOL_GPL(bpf_prog_get_type);
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD prog_flags
+#define	BPF_PROG_LOAD_LAST_FIELD prog_name
 
 static int bpf_prog_load(union bpf_attr *attr)
 {
@@ -1015,10 +1131,14 @@ static int bpf_prog_load(union bpf_attr *attr)
 	if (!prog)
 		return -ENOMEM;
 
-	err = bpf_prog_charge_memlock(prog);
+	err = security_bpf_prog_alloc(prog->aux);
 	if (err)
 		goto free_prog_nouncharge;
 
+	err = bpf_prog_charge_memlock(prog);
+	if (err)
+		goto free_prog_sec;
+
 	prog->len = attr->insn_cnt;
 
 	err = -EFAULT;
@@ -1037,6 +1157,11 @@ static int bpf_prog_load(union bpf_attr *attr)
 	if (err < 0)
 		goto free_prog;
 
+	prog->aux->load_time = ktime_get_boot_ns();
+	err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name);
+	if (err)
+		goto free_prog;
+
 	/* run eBPF verifier */
 	err = bpf_check(&prog, attr);
 	if (err < 0)
@@ -1071,16 +1196,18 @@ free_used_maps:
 	free_used_maps(prog->aux);
 free_prog:
 	bpf_prog_uncharge_memlock(prog);
+free_prog_sec:
+	security_bpf_prog_free(prog->aux);
 free_prog_nouncharge:
 	bpf_prog_free(prog);
 	return err;
 }
 
-#define BPF_OBJ_LAST_FIELD bpf_fd
+#define BPF_OBJ_LAST_FIELD file_flags
 
 static int bpf_obj_pin(const union bpf_attr *attr)
 {
-	if (CHECK_ATTR(BPF_OBJ))
+	if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0)
 		return -EINVAL;
 
 	return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname));
@@ -1088,10 +1215,12 @@ static int bpf_obj_pin(const union bpf_attr *attr)
 
 static int bpf_obj_get(const union bpf_attr *attr)
 {
-	if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0)
+	if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 ||
+	    attr->file_flags & ~BPF_OBJ_FLAG_MASK)
 		return -EINVAL;
 
-	return bpf_obj_get_user(u64_to_user_ptr(attr->pathname));
+	return bpf_obj_get_user(u64_to_user_ptr(attr->pathname),
+				attr->file_flags);
 }
 
 #ifdef CONFIG_CGROUP_BPF
@@ -1132,6 +1261,9 @@ static int sockmap_get_from_fd(const union bpf_attr *attr, bool attach)
 	return 0;
 }
 
+#define BPF_F_ATTACH_MASK \
+	(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
+
 static int bpf_prog_attach(const union bpf_attr *attr)
 {
 	enum bpf_prog_type ptype;
@@ -1145,7 +1277,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_PROG_ATTACH))
 		return -EINVAL;
 
-	if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE)
+	if (attr->attach_flags & ~BPF_F_ATTACH_MASK)
 		return -EINVAL;
 
 	switch (attr->attach_type) {
@@ -1176,8 +1308,8 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		return PTR_ERR(cgrp);
 	}
 
-	ret = cgroup_bpf_update(cgrp, prog, attr->attach_type,
-				attr->attach_flags & BPF_F_ALLOW_OVERRIDE);
+	ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+				attr->attach_flags);
 	if (ret)
 		bpf_prog_put(prog);
 	cgroup_put(cgrp);
@@ -1189,6 +1321,8 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 
 static int bpf_prog_detach(const union bpf_attr *attr)
 {
+	enum bpf_prog_type ptype;
+	struct bpf_prog *prog;
 	struct cgroup *cgrp;
 	int ret;
 
@@ -1201,26 +1335,67 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	switch (attr->attach_type) {
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
+		ptype = BPF_PROG_TYPE_CGROUP_SKB;
+		break;
 	case BPF_CGROUP_INET_SOCK_CREATE:
+		ptype = BPF_PROG_TYPE_CGROUP_SOCK;
+		break;
 	case BPF_CGROUP_SOCK_OPS:
-		cgrp = cgroup_get_from_fd(attr->target_fd);
-		if (IS_ERR(cgrp))
-			return PTR_ERR(cgrp);
-
-		ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false);
-		cgroup_put(cgrp);
+		ptype = BPF_PROG_TYPE_SOCK_OPS;
 		break;
 	case BPF_SK_SKB_STREAM_PARSER:
 	case BPF_SK_SKB_STREAM_VERDICT:
-		ret = sockmap_get_from_fd(attr, false);
-		break;
+		return sockmap_get_from_fd(attr, false);
 	default:
 		return -EINVAL;
 	}
 
+	cgrp = cgroup_get_from_fd(attr->target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+	if (IS_ERR(prog))
+		prog = NULL;
+
+	ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+	if (prog)
+		bpf_prog_put(prog);
+	cgroup_put(cgrp);
 	return ret;
 }
 
+#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
+
+static int bpf_prog_query(const union bpf_attr *attr,
+			  union bpf_attr __user *uattr)
+{
+	struct cgroup *cgrp;
+	int ret;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+	if (CHECK_ATTR(BPF_PROG_QUERY))
+		return -EINVAL;
+	if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE)
+		return -EINVAL;
+
+	switch (attr->query.attach_type) {
+	case BPF_CGROUP_INET_INGRESS:
+	case BPF_CGROUP_INET_EGRESS:
+	case BPF_CGROUP_INET_SOCK_CREATE:
+	case BPF_CGROUP_SOCK_OPS:
+		break;
+	default:
+		return -EINVAL;
+	}
+	cgrp = cgroup_get_from_fd(attr->query.target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+	ret = cgroup_bpf_query(cgrp, attr, uattr);
+	cgroup_put(cgrp);
+	return ret;
+}
 #endif /* CONFIG_CGROUP_BPF */
 
 #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
@@ -1305,20 +1480,26 @@ static int bpf_prog_get_fd_by_id(const union bpf_attr *attr)
 	return fd;
 }
 
-#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id
+#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags
 
 static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
 {
 	struct bpf_map *map;
 	u32 id = attr->map_id;
+	int f_flags;
 	int fd;
 
-	if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID))
+	if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) ||
+	    attr->open_flags & ~BPF_OBJ_FLAG_MASK)
 		return -EINVAL;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	f_flags = bpf_get_file_flag(attr->open_flags);
+	if (f_flags < 0)
+		return f_flags;
+
 	spin_lock_bh(&map_idr_lock);
 	map = idr_find(&map_idr, id);
 	if (map)
@@ -1330,7 +1511,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
-	fd = bpf_map_new_fd(map);
+	fd = bpf_map_new_fd(map, f_flags);
 	if (fd < 0)
 		bpf_map_put(map);
 
@@ -1358,8 +1539,25 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 
 	info.type = prog->type;
 	info.id = prog->aux->id;
+	info.load_time = prog->aux->load_time;
+	info.created_by_uid = from_kuid_munged(current_user_ns(),
+					       prog->aux->user->uid);
 
 	memcpy(info.tag, prog->tag, sizeof(prog->tag));
+	memcpy(info.name, prog->aux->name, sizeof(prog->aux->name));
+
+	ulen = info.nr_map_ids;
+	info.nr_map_ids = prog->aux->used_map_cnt;
+	ulen = min_t(u32, info.nr_map_ids, ulen);
+	if (ulen) {
+		u32 __user *user_map_ids = u64_to_user_ptr(info.map_ids);
+		u32 i;
+
+		for (i = 0; i < ulen; i++)
+			if (put_user(prog->aux->used_maps[i]->id,
+				     &user_map_ids[i]))
+				return -EFAULT;
+	}
 
 	if (!capable(CAP_SYS_ADMIN)) {
 		info.jited_prog_len = 0;
@@ -1413,6 +1611,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
 	info.value_size = map->value_size;
 	info.max_entries = map->max_entries;
 	info.map_flags = map->map_flags;
+	memcpy(info.name, map->name, sizeof(map->name));
 
 	if (copy_to_user(uinfo, &info, info_len) ||
 	    put_user(info_len, &uattr->info.info_len))
@@ -1467,6 +1666,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	if (copy_from_user(&attr, uattr, size) != 0)
 		return -EFAULT;
 
+	err = security_bpf(cmd, &attr, size);
+	if (err < 0)
+		return err;
+
 	switch (cmd) {
 	case BPF_MAP_CREATE:
 		err = map_create(&attr);
@@ -1499,6 +1702,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_PROG_DETACH:
 		err = bpf_prog_detach(&attr);
 		break;
+	case BPF_PROG_QUERY:
+		err = bpf_prog_query(&attr, uattr);
+		break;
 #endif
 	case BPF_PROG_TEST_RUN:
 		err = bpf_prog_test_run(&attr, uattr);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c48ca2a34b5e..04357ad5a812 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21,6 +21,17 @@
 #include <linux/vmalloc.h>
 #include <linux/stringify.h>
 
+#include "disasm.h"
+
+static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
+#define BPF_PROG_TYPE(_id, _name) \
+	[_id] = & _name ## _verifier_ops,
+#define BPF_MAP_TYPE(_id, _ops)
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+#undef BPF_MAP_TYPE
+};
+
 /* bpf_check() is a static code analyzer that walks eBPF program
  * instruction by instruction and updates register/stack state.
  * All paths of conditional branches are analyzed until 'bpf_exit' insn.
@@ -153,28 +164,42 @@ struct bpf_call_arg_meta {
 	int access_size;
 };
 
-/* verbose verifier prints what it's seeing
- * bpf_check() is called under lock, so no race to access these global vars
- */
-static u32 log_level, log_size, log_len;
-static char *log_buf;
-
 static DEFINE_MUTEX(bpf_verifier_lock);
 
 /* log_level controls verbosity level of eBPF verifier.
  * verbose() is used to dump the verification trace to the log, so the user
  * can figure out what's wrong with the program
  */
-static __printf(1, 2) void verbose(const char *fmt, ...)
+static __printf(2, 3) void verbose(struct bpf_verifier_env *env,
+				   const char *fmt, ...)
 {
+	struct bpf_verifer_log *log = &env->log;
+	unsigned int n;
 	va_list args;
 
-	if (log_level == 0 || log_len >= log_size - 1)
+	if (!log->level || !log->ubuf || bpf_verifier_log_full(log))
 		return;
 
 	va_start(args, fmt);
-	log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args);
+	n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args);
 	va_end(args);
+
+	WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1,
+		  "verifier log line truncated - local buffer too short\n");
+
+	n = min(log->len_total - log->len_used - 1, n);
+	log->kbuf[n] = '\0';
+
+	if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1))
+		log->len_used += n;
+	else
+		log->ubuf = NULL;
+}
+
+static bool type_is_pkt_pointer(enum bpf_reg_type type)
+{
+	return type == PTR_TO_PACKET ||
+	       type == PTR_TO_PACKET_META;
 }
 
 /* string representation of 'enum bpf_reg_type' */
@@ -187,26 +212,12 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
 	[PTR_TO_STACK]		= "fp",
 	[PTR_TO_PACKET]		= "pkt",
+	[PTR_TO_PACKET_META]	= "pkt_meta",
 	[PTR_TO_PACKET_END]	= "pkt_end",
 };
 
-#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x)
-static const char * const func_id_str[] = {
-	__BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN)
-};
-#undef __BPF_FUNC_STR_FN
-
-static const char *func_id_name(int id)
-{
-	BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID);
-
-	if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id])
-		return func_id_str[id];
-	else
-		return "unknown";
-}
-
-static void print_verifier_state(struct bpf_verifier_state *state)
+static void print_verifier_state(struct bpf_verifier_env *env,
+				 struct bpf_verifier_state *state)
 {
 	struct bpf_reg_state *reg;
 	enum bpf_reg_type t;
@@ -217,21 +228,21 @@ static void print_verifier_state(struct bpf_verifier_state *state)
 		t = reg->type;
 		if (t == NOT_INIT)
 			continue;
-		verbose(" R%d=%s", i, reg_type_str[t]);
+		verbose(env, " R%d=%s", i, reg_type_str[t]);
 		if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
 		    tnum_is_const(reg->var_off)) {
 			/* reg->off should be 0 for SCALAR_VALUE */
-			verbose("%lld", reg->var_off.value + reg->off);
+			verbose(env, "%lld", reg->var_off.value + reg->off);
 		} else {
-			verbose("(id=%d", reg->id);
+			verbose(env, "(id=%d", reg->id);
 			if (t != SCALAR_VALUE)
-				verbose(",off=%d", reg->off);
-			if (t == PTR_TO_PACKET)
-				verbose(",r=%d", reg->range);
+				verbose(env, ",off=%d", reg->off);
+			if (type_is_pkt_pointer(t))
+				verbose(env, ",r=%d", reg->range);
 			else if (t == CONST_PTR_TO_MAP ||
 				 t == PTR_TO_MAP_VALUE ||
 				 t == PTR_TO_MAP_VALUE_OR_NULL)
-				verbose(",ks=%d,vs=%d",
+				verbose(env, ",ks=%d,vs=%d",
 					reg->map_ptr->key_size,
 					reg->map_ptr->value_size);
 			if (tnum_is_const(reg->var_off)) {
@@ -239,243 +250,174 @@ static void print_verifier_state(struct bpf_verifier_state *state)
 				 * could be a pointer whose offset is too big
 				 * for reg->off
 				 */
-				verbose(",imm=%llx", reg->var_off.value);
+				verbose(env, ",imm=%llx", reg->var_off.value);
 			} else {
 				if (reg->smin_value != reg->umin_value &&
 				    reg->smin_value != S64_MIN)
-					verbose(",smin_value=%lld",
+					verbose(env, ",smin_value=%lld",
 						(long long)reg->smin_value);
 				if (reg->smax_value != reg->umax_value &&
 				    reg->smax_value != S64_MAX)
-					verbose(",smax_value=%lld",
+					verbose(env, ",smax_value=%lld",
 						(long long)reg->smax_value);
 				if (reg->umin_value != 0)
-					verbose(",umin_value=%llu",
+					verbose(env, ",umin_value=%llu",
 						(unsigned long long)reg->umin_value);
 				if (reg->umax_value != U64_MAX)
-					verbose(",umax_value=%llu",
+					verbose(env, ",umax_value=%llu",
 						(unsigned long long)reg->umax_value);
 				if (!tnum_is_unknown(reg->var_off)) {
 					char tn_buf[48];
 
 					tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-					verbose(",var_off=%s", tn_buf);
+					verbose(env, ",var_off=%s", tn_buf);
 				}
 			}
-			verbose(")");
+			verbose(env, ")");
 		}
 	}
-	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
-		if (state->stack_slot_type[i] == STACK_SPILL)
-			verbose(" fp%d=%s", -MAX_BPF_STACK + i,
-				reg_type_str[state->spilled_regs[i / BPF_REG_SIZE].type]);
+	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+		if (state->stack[i].slot_type[0] == STACK_SPILL)
+			verbose(env, " fp%d=%s",
+				-MAX_BPF_STACK + i * BPF_REG_SIZE,
+				reg_type_str[state->stack[i].spilled_ptr.type]);
 	}
-	verbose("\n");
+	verbose(env, "\n");
 }
 
-static const char *const bpf_class_string[] = {
-	[BPF_LD]    = "ld",
-	[BPF_LDX]   = "ldx",
-	[BPF_ST]    = "st",
-	[BPF_STX]   = "stx",
-	[BPF_ALU]   = "alu",
-	[BPF_JMP]   = "jmp",
-	[BPF_RET]   = "BUG",
-	[BPF_ALU64] = "alu64",
-};
-
-static const char *const bpf_alu_string[16] = {
-	[BPF_ADD >> 4]  = "+=",
-	[BPF_SUB >> 4]  = "-=",
-	[BPF_MUL >> 4]  = "*=",
-	[BPF_DIV >> 4]  = "/=",
-	[BPF_OR  >> 4]  = "|=",
-	[BPF_AND >> 4]  = "&=",
-	[BPF_LSH >> 4]  = "<<=",
-	[BPF_RSH >> 4]  = ">>=",
-	[BPF_NEG >> 4]  = "neg",
-	[BPF_MOD >> 4]  = "%=",
-	[BPF_XOR >> 4]  = "^=",
-	[BPF_MOV >> 4]  = "=",
-	[BPF_ARSH >> 4] = "s>>=",
-	[BPF_END >> 4]  = "endian",
-};
-
-static const char *const bpf_ldst_string[] = {
-	[BPF_W >> 3]  = "u32",
-	[BPF_H >> 3]  = "u16",
-	[BPF_B >> 3]  = "u8",
-	[BPF_DW >> 3] = "u64",
-};
-
-static const char *const bpf_jmp_string[16] = {
-	[BPF_JA >> 4]   = "jmp",
-	[BPF_JEQ >> 4]  = "==",
-	[BPF_JGT >> 4]  = ">",
-	[BPF_JLT >> 4]  = "<",
-	[BPF_JGE >> 4]  = ">=",
-	[BPF_JLE >> 4]  = "<=",
-	[BPF_JSET >> 4] = "&",
-	[BPF_JNE >> 4]  = "!=",
-	[BPF_JSGT >> 4] = "s>",
-	[BPF_JSLT >> 4] = "s<",
-	[BPF_JSGE >> 4] = "s>=",
-	[BPF_JSLE >> 4] = "s<=",
-	[BPF_CALL >> 4] = "call",
-	[BPF_EXIT >> 4] = "exit",
-};
+static int copy_stack_state(struct bpf_verifier_state *dst,
+			    const struct bpf_verifier_state *src)
+{
+	if (!src->stack)
+		return 0;
+	if (WARN_ON_ONCE(dst->allocated_stack < src->allocated_stack)) {
+		/* internal bug, make state invalid to reject the program */
+		memset(dst, 0, sizeof(*dst));
+		return -EFAULT;
+	}
+	memcpy(dst->stack, src->stack,
+	       sizeof(*src->stack) * (src->allocated_stack / BPF_REG_SIZE));
+	return 0;
+}
 
-static void print_bpf_insn(const struct bpf_verifier_env *env,
-			   const struct bpf_insn *insn)
+/* 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_verifier_state() to grow the stack size.
+ * Note there is a non-zero 'parent' pointer inside bpf_verifier_state
+ * which this function copies over. It points to previous bpf_verifier_state
+ * which is never reallocated
+ */
+static int realloc_verifier_state(struct bpf_verifier_state *state, int size,
+				  bool copy_old)
 {
-	u8 class = BPF_CLASS(insn->code);
-
-	if (class == BPF_ALU || class == BPF_ALU64) {
-		if (BPF_SRC(insn->code) == BPF_X)
-			verbose("(%02x) %sr%d %s %sr%d\n",
-				insn->code, class == BPF_ALU ? "(u32) " : "",
-				insn->dst_reg,
-				bpf_alu_string[BPF_OP(insn->code) >> 4],
-				class == BPF_ALU ? "(u32) " : "",
-				insn->src_reg);
-		else
-			verbose("(%02x) %sr%d %s %s%d\n",
-				insn->code, class == BPF_ALU ? "(u32) " : "",
-				insn->dst_reg,
-				bpf_alu_string[BPF_OP(insn->code) >> 4],
-				class == BPF_ALU ? "(u32) " : "",
-				insn->imm);
-	} else if (class == BPF_STX) {
-		if (BPF_MODE(insn->code) == BPF_MEM)
-			verbose("(%02x) *(%s *)(r%d %+d) = r%d\n",
-				insn->code,
-				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
-				insn->dst_reg,
-				insn->off, insn->src_reg);
-		else if (BPF_MODE(insn->code) == BPF_XADD)
-			verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n",
-				insn->code,
-				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
-				insn->dst_reg, insn->off,
-				insn->src_reg);
-		else
-			verbose("BUG_%02x\n", insn->code);
-	} else if (class == BPF_ST) {
-		if (BPF_MODE(insn->code) != BPF_MEM) {
-			verbose("BUG_st_%02x\n", insn->code);
-			return;
-		}
-		verbose("(%02x) *(%s *)(r%d %+d) = %d\n",
-			insn->code,
-			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
-			insn->dst_reg,
-			insn->off, insn->imm);
-	} else if (class == BPF_LDX) {
-		if (BPF_MODE(insn->code) != BPF_MEM) {
-			verbose("BUG_ldx_%02x\n", insn->code);
-			return;
+	u32 old_size = state->allocated_stack;
+	struct bpf_stack_state *new_stack;
+	int slot = size / BPF_REG_SIZE;
+
+	if (size <= old_size || !size) {
+		if (copy_old)
+			return 0;
+		state->allocated_stack = slot * BPF_REG_SIZE;
+		if (!size && old_size) {
+			kfree(state->stack);
+			state->stack = NULL;
 		}
-		verbose("(%02x) r%d = *(%s *)(r%d %+d)\n",
-			insn->code, insn->dst_reg,
-			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
-			insn->src_reg, insn->off);
-	} else if (class == BPF_LD) {
-		if (BPF_MODE(insn->code) == BPF_ABS) {
-			verbose("(%02x) r0 = *(%s *)skb[%d]\n",
-				insn->code,
-				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
-				insn->imm);
-		} else if (BPF_MODE(insn->code) == BPF_IND) {
-			verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n",
-				insn->code,
-				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
-				insn->src_reg, insn->imm);
-		} else if (BPF_MODE(insn->code) == BPF_IMM &&
-			   BPF_SIZE(insn->code) == BPF_DW) {
-			/* At this point, we already made sure that the second
-			 * part of the ldimm64 insn is accessible.
-			 */
-			u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
-			bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+		return 0;
+	}
+	new_stack = kmalloc_array(slot, sizeof(struct bpf_stack_state),
+				  GFP_KERNEL);
+	if (!new_stack)
+		return -ENOMEM;
+	if (copy_old) {
+		if (state->stack)
+			memcpy(new_stack, state->stack,
+			       sizeof(*new_stack) * (old_size / BPF_REG_SIZE));
+		memset(new_stack + old_size / BPF_REG_SIZE, 0,
+		       sizeof(*new_stack) * (size - old_size) / BPF_REG_SIZE);
+	}
+	state->allocated_stack = slot * BPF_REG_SIZE;
+	kfree(state->stack);
+	state->stack = new_stack;
+	return 0;
+}
 
-			if (map_ptr && !env->allow_ptr_leaks)
-				imm = 0;
+static void free_verifier_state(struct bpf_verifier_state *state,
+				bool free_self)
+{
+	kfree(state->stack);
+	if (free_self)
+		kfree(state);
+}
 
-			verbose("(%02x) r%d = 0x%llx\n", insn->code,
-				insn->dst_reg, (unsigned long long)imm);
-		} else {
-			verbose("BUG_ld_%02x\n", insn->code);
-			return;
-		}
-	} else if (class == BPF_JMP) {
-		u8 opcode = BPF_OP(insn->code);
+/* copy verifier state from src to dst growing dst stack space
+ * when necessary to accommodate larger src stack
+ */
+static int copy_verifier_state(struct bpf_verifier_state *dst,
+			       const struct bpf_verifier_state *src)
+{
+	int err;
 
-		if (opcode == BPF_CALL) {
-			verbose("(%02x) call %s#%d\n", insn->code,
-				func_id_name(insn->imm), insn->imm);
-		} else if (insn->code == (BPF_JMP | BPF_JA)) {
-			verbose("(%02x) goto pc%+d\n",
-				insn->code, insn->off);
-		} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
-			verbose("(%02x) exit\n", insn->code);
-		} else if (BPF_SRC(insn->code) == BPF_X) {
-			verbose("(%02x) if r%d %s r%d goto pc%+d\n",
-				insn->code, insn->dst_reg,
-				bpf_jmp_string[BPF_OP(insn->code) >> 4],
-				insn->src_reg, insn->off);
-		} else {
-			verbose("(%02x) if r%d %s 0x%x goto pc%+d\n",
-				insn->code, insn->dst_reg,
-				bpf_jmp_string[BPF_OP(insn->code) >> 4],
-				insn->imm, insn->off);
-		}
-	} else {
-		verbose("(%02x) %s\n", insn->code, bpf_class_string[class]);
-	}
+	err = realloc_verifier_state(dst, src->allocated_stack, false);
+	if (err)
+		return err;
+	memcpy(dst, src, offsetof(struct bpf_verifier_state, allocated_stack));
+	return copy_stack_state(dst, src);
 }
 
-static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx)
+static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
+		     int *insn_idx)
 {
-	struct bpf_verifier_stack_elem *elem;
-	int insn_idx;
+	struct bpf_verifier_state *cur = env->cur_state;
+	struct bpf_verifier_stack_elem *elem, *head = env->head;
+	int err;
 
 	if (env->head == NULL)
-		return -1;
+		return -ENOENT;
 
-	memcpy(&env->cur_state, &env->head->st, sizeof(env->cur_state));
-	insn_idx = env->head->insn_idx;
+	if (cur) {
+		err = copy_verifier_state(cur, &head->st);
+		if (err)
+			return err;
+	}
+	if (insn_idx)
+		*insn_idx = head->insn_idx;
 	if (prev_insn_idx)
-		*prev_insn_idx = env->head->prev_insn_idx;
-	elem = env->head->next;
-	kfree(env->head);
+		*prev_insn_idx = head->prev_insn_idx;
+	elem = head->next;
+	free_verifier_state(&head->st, false);
+	kfree(head);
 	env->head = elem;
 	env->stack_size--;
-	return insn_idx;
+	return 0;
 }
 
 static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
 					     int insn_idx, int prev_insn_idx)
 {
+	struct bpf_verifier_state *cur = env->cur_state;
 	struct bpf_verifier_stack_elem *elem;
+	int err;
 
-	elem = kmalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
+	elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
 	if (!elem)
 		goto err;
 
-	memcpy(&elem->st, &env->cur_state, sizeof(env->cur_state));
 	elem->insn_idx = insn_idx;
 	elem->prev_insn_idx = prev_insn_idx;
 	elem->next = env->head;
 	env->head = elem;
 	env->stack_size++;
+	err = copy_verifier_state(&elem->st, cur);
+	if (err)
+		goto err;
 	if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
-		verbose("BPF program is too complex\n");
+		verbose(env, "BPF program is too complex\n");
 		goto err;
 	}
 	return &elem->st;
 err:
 	/* pop all elements and return */
-	while (pop_stack(env, NULL) >= 0);
+	while (!pop_stack(env, NULL, NULL));
 	return NULL;
 }
 
@@ -507,10 +449,11 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg)
 	__mark_reg_known(reg, 0);
 }
 
-static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno)
+static void mark_reg_known_zero(struct bpf_verifier_env *env,
+				struct bpf_reg_state *regs, u32 regno)
 {
 	if (WARN_ON(regno >= MAX_BPF_REG)) {
-		verbose("mark_reg_known_zero(regs, %u)\n", regno);
+		verbose(env, "mark_reg_known_zero(regs, %u)\n", regno);
 		/* Something bad happened, let's kill all regs */
 		for (regno = 0; regno < MAX_BPF_REG; regno++)
 			__mark_reg_not_init(regs + regno);
@@ -519,6 +462,31 @@ static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno)
 	__mark_reg_known_zero(regs + regno);
 }
 
+static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg)
+{
+	return type_is_pkt_pointer(reg->type);
+}
+
+static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg)
+{
+	return reg_is_pkt_pointer(reg) ||
+	       reg->type == PTR_TO_PACKET_END;
+}
+
+/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */
+static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg,
+				    enum bpf_reg_type which)
+{
+	/* The register can already have a range from prior markings.
+	 * This is fine as long as it hasn't been advanced from its
+	 * origin.
+	 */
+	return reg->type == which &&
+	       reg->id == 0 &&
+	       reg->off == 0 &&
+	       tnum_equals_const(reg->var_off, 0);
+}
+
 /* Attempts to improve min/max values based on var_off information */
 static void __update_reg_bounds(struct bpf_reg_state *reg)
 {
@@ -595,10 +563,11 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg)
 	__mark_reg_unbounded(reg);
 }
 
-static void mark_reg_unknown(struct bpf_reg_state *regs, u32 regno)
+static void mark_reg_unknown(struct bpf_verifier_env *env,
+			     struct bpf_reg_state *regs, u32 regno)
 {
 	if (WARN_ON(regno >= MAX_BPF_REG)) {
-		verbose("mark_reg_unknown(regs, %u)\n", regno);
+		verbose(env, "mark_reg_unknown(regs, %u)\n", regno);
 		/* Something bad happened, let's kill all regs */
 		for (regno = 0; regno < MAX_BPF_REG; regno++)
 			__mark_reg_not_init(regs + regno);
@@ -613,10 +582,11 @@ static void __mark_reg_not_init(struct bpf_reg_state *reg)
 	reg->type = NOT_INIT;
 }
 
-static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno)
+static void mark_reg_not_init(struct bpf_verifier_env *env,
+			      struct bpf_reg_state *regs, u32 regno)
 {
 	if (WARN_ON(regno >= MAX_BPF_REG)) {
-		verbose("mark_reg_not_init(regs, %u)\n", regno);
+		verbose(env, "mark_reg_not_init(regs, %u)\n", regno);
 		/* Something bad happened, let's kill all regs */
 		for (regno = 0; regno < MAX_BPF_REG; regno++)
 			__mark_reg_not_init(regs + regno);
@@ -625,22 +595,23 @@ static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno)
 	__mark_reg_not_init(regs + regno);
 }
 
-static void init_reg_state(struct bpf_reg_state *regs)
+static void init_reg_state(struct bpf_verifier_env *env,
+			   struct bpf_reg_state *regs)
 {
 	int i;
 
 	for (i = 0; i < MAX_BPF_REG; i++) {
-		mark_reg_not_init(regs, i);
+		mark_reg_not_init(env, regs, i);
 		regs[i].live = REG_LIVE_NONE;
 	}
 
 	/* frame pointer */
 	regs[BPF_REG_FP].type = PTR_TO_STACK;
-	mark_reg_known_zero(regs, BPF_REG_FP);
+	mark_reg_known_zero(env, regs, BPF_REG_FP);
 
 	/* 1st arg to a function */
 	regs[BPF_REG_1].type = PTR_TO_CTX;
-	mark_reg_known_zero(regs, BPF_REG_1);
+	mark_reg_known_zero(env, regs, BPF_REG_1);
 }
 
 enum reg_arg_type {
@@ -671,29 +642,29 @@ static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno)
 static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
 			 enum reg_arg_type t)
 {
-	struct bpf_reg_state *regs = env->cur_state.regs;
+	struct bpf_reg_state *regs = env->cur_state->regs;
 
 	if (regno >= MAX_BPF_REG) {
-		verbose("R%d is invalid\n", regno);
+		verbose(env, "R%d is invalid\n", regno);
 		return -EINVAL;
 	}
 
 	if (t == SRC_OP) {
 		/* check whether register used as source operand can be read */
 		if (regs[regno].type == NOT_INIT) {
-			verbose("R%d !read_ok\n", regno);
+			verbose(env, "R%d !read_ok\n", regno);
 			return -EACCES;
 		}
-		mark_reg_read(&env->cur_state, regno);
+		mark_reg_read(env->cur_state, regno);
 	} else {
 		/* check whether register used as dest operand can be written to */
 		if (regno == BPF_REG_FP) {
-			verbose("frame pointer is read only\n");
+			verbose(env, "frame pointer is read only\n");
 			return -EACCES;
 		}
 		regs[regno].live |= REG_LIVE_WRITTEN;
 		if (t == DST_OP)
-			mark_reg_unknown(regs, regno);
+			mark_reg_unknown(env, regs, regno);
 	}
 	return 0;
 }
@@ -706,6 +677,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
 	case PTR_TO_STACK:
 	case PTR_TO_CTX:
 	case PTR_TO_PACKET:
+	case PTR_TO_PACKET_META:
 	case PTR_TO_PACKET_END:
 	case CONST_PTR_TO_MAP:
 		return true;
@@ -717,35 +689,48 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
 /* check_stack_read/write functions track spill/fill of registers,
  * stack boundary and alignment are checked in check_mem_access()
  */
-static int check_stack_write(struct bpf_verifier_state *state, int off,
+static int check_stack_write(struct bpf_verifier_env *env,
+			     struct bpf_verifier_state *state, int off,
 			     int size, int value_regno)
 {
-	int i, spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE;
+	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
+
+	err = realloc_verifier_state(state, round_up(slot + 1, BPF_REG_SIZE),
+				     true);
+	if (err)
+		return err;
 	/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
 	 * so it's aligned access and [off, off + size) are within stack limits
 	 */
+	if (!env->allow_ptr_leaks &&
+	    state->stack[spi].slot_type[0] == STACK_SPILL &&
+	    size != BPF_REG_SIZE) {
+		verbose(env, "attempt to corrupt spilled pointer on stack\n");
+		return -EACCES;
+	}
 
 	if (value_regno >= 0 &&
 	    is_spillable_regtype(state->regs[value_regno].type)) {
 
 		/* register containing pointer is being spilled into stack */
 		if (size != BPF_REG_SIZE) {
-			verbose("invalid size of register spill\n");
+			verbose(env, "invalid size of register spill\n");
 			return -EACCES;
 		}
 
 		/* save register state */
-		state->spilled_regs[spi] = state->regs[value_regno];
-		state->spilled_regs[spi].live |= REG_LIVE_WRITTEN;
+		state->stack[spi].spilled_ptr = state->regs[value_regno];
+		state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
 
 		for (i = 0; i < BPF_REG_SIZE; i++)
-			state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_SPILL;
+			state->stack[spi].slot_type[i] = STACK_SPILL;
 	} else {
 		/* regular write of data into stack */
-		state->spilled_regs[spi] = (struct bpf_reg_state) {};
+		state->stack[spi].spilled_ptr = (struct bpf_reg_state) {};
 
 		for (i = 0; i < size; i++)
-			state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_MISC;
+			state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
+				STACK_MISC;
 	}
 	return 0;
 }
@@ -756,54 +741,58 @@ static void mark_stack_slot_read(const struct bpf_verifier_state *state, int slo
 
 	while (parent) {
 		/* if read wasn't screened by an earlier write ... */
-		if (state->spilled_regs[slot].live & REG_LIVE_WRITTEN)
+		if (state->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN)
 			break;
 		/* ... then we depend on parent's value */
-		parent->spilled_regs[slot].live |= REG_LIVE_READ;
+		parent->stack[slot].spilled_ptr.live |= REG_LIVE_READ;
 		state = parent;
 		parent = state->parent;
 	}
 }
 
-static int check_stack_read(struct bpf_verifier_state *state, int off, int size,
+static int check_stack_read(struct bpf_verifier_env *env,
+			    struct bpf_verifier_state *state, int off, int size,
 			    int value_regno)
 {
-	u8 *slot_type;
-	int i, spi;
+	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
+	u8 *stype;
 
-	slot_type = &state->stack_slot_type[MAX_BPF_STACK + off];
+	if (state->allocated_stack <= slot) {
+		verbose(env, "invalid read from stack off %d+0 size %d\n",
+			off, size);
+		return -EACCES;
+	}
+	stype = state->stack[spi].slot_type;
 
-	if (slot_type[0] == STACK_SPILL) {
+	if (stype[0] == STACK_SPILL) {
 		if (size != BPF_REG_SIZE) {
-			verbose("invalid size of register spill\n");
+			verbose(env, "invalid size of register spill\n");
 			return -EACCES;
 		}
 		for (i = 1; i < BPF_REG_SIZE; i++) {
-			if (slot_type[i] != STACK_SPILL) {
-				verbose("corrupted spill memory\n");
+			if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) {
+				verbose(env, "corrupted spill memory\n");
 				return -EACCES;
 			}
 		}
 
-		spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE;
-
 		if (value_regno >= 0) {
 			/* restore register state from stack */
-			state->regs[value_regno] = state->spilled_regs[spi];
+			state->regs[value_regno] = state->stack[spi].spilled_ptr;
 			mark_stack_slot_read(state, spi);
 		}
 		return 0;
 	} else {
 		for (i = 0; i < size; i++) {
-			if (slot_type[i] != STACK_MISC) {
-				verbose("invalid read from stack off %d+%d size %d\n",
+			if (stype[(slot - i) % BPF_REG_SIZE] != STACK_MISC) {
+				verbose(env, "invalid read from stack off %d+%d size %d\n",
 					off, i, size);
 				return -EACCES;
 			}
 		}
 		if (value_regno >= 0)
 			/* have read misc data from the stack */
-			mark_reg_unknown(state->regs, value_regno);
+			mark_reg_unknown(env, state->regs, value_regno);
 		return 0;
 	}
 }
@@ -812,10 +801,11 @@ static int check_stack_read(struct bpf_verifier_state *state, int off, int size,
 static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
 			    int size)
 {
-	struct bpf_map *map = env->cur_state.regs[regno].map_ptr;
+	struct bpf_reg_state *regs = cur_regs(env);
+	struct bpf_map *map = regs[regno].map_ptr;
 
 	if (off < 0 || size <= 0 || off + size > map->value_size) {
-		verbose("invalid access to map value, value_size=%d off=%d size=%d\n",
+		verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
 			map->value_size, off, size);
 		return -EACCES;
 	}
@@ -824,9 +814,9 @@ static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
 
 /* check read/write into a map element with possible variable offset */
 static int check_map_access(struct bpf_verifier_env *env, u32 regno,
-				int off, int size)
+			    int off, int size)
 {
-	struct bpf_verifier_state *state = &env->cur_state;
+	struct bpf_verifier_state *state = env->cur_state;
 	struct bpf_reg_state *reg = &state->regs[regno];
 	int err;
 
@@ -834,8 +824,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 	 * need to try adding each of min_value and max_value to off
 	 * to make sure our theoretical access will be safe.
 	 */
-	if (log_level)
-		print_verifier_state(state);
+	if (env->log.level)
+		print_verifier_state(env, state);
 	/* The minimum value is only important with signed
 	 * comparisons where we can't assume the floor of a
 	 * value is 0.  If we are using signed variables for our
@@ -843,13 +833,14 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 	 * will have a set floor within our range.
 	 */
 	if (reg->smin_value < 0) {
-		verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
+		verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
 			regno);
 		return -EACCES;
 	}
 	err = __check_map_access(env, regno, reg->smin_value + off, size);
 	if (err) {
-		verbose("R%d min value is outside of the array range\n", regno);
+		verbose(env, "R%d min value is outside of the array range\n",
+			regno);
 		return err;
 	}
 
@@ -858,13 +849,14 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 	 * If reg->umax_value + off could overflow, treat that as unbounded too.
 	 */
 	if (reg->umax_value >= BPF_MAX_VAR_OFF) {
-		verbose("R%d unbounded memory access, make sure to bounds check any array access into a map\n",
+		verbose(env, "R%d unbounded memory access, make sure to bounds check any array access into a map\n",
 			regno);
 		return -EACCES;
 	}
 	err = __check_map_access(env, regno, reg->umax_value + off, size);
 	if (err)
-		verbose("R%d max value is outside of the array range\n", regno);
+		verbose(env, "R%d max value is outside of the array range\n",
+			regno);
 	return err;
 }
 
@@ -899,11 +891,11 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
 static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
 				 int off, int size)
 {
-	struct bpf_reg_state *regs = env->cur_state.regs;
+	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = &regs[regno];
 
 	if (off < 0 || size <= 0 || (u64)off + size > reg->range) {
-		verbose("invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
+		verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
 			off, size, regno, reg->id, reg->off, reg->range);
 		return -EACCES;
 	}
@@ -913,7 +905,7 @@ static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
 static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
 			       int size)
 {
-	struct bpf_reg_state *regs = env->cur_state.regs;
+	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = &regs[regno];
 	int err;
 
@@ -926,13 +918,13 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
 	 * detail to prove they're safe.
 	 */
 	if (reg->smin_value < 0) {
-		verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
+		verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
 			regno);
 		return -EACCES;
 	}
 	err = __check_packet_access(env, regno, off, size);
 	if (err) {
-		verbose("R%d offset is outside of the packet\n", regno);
+		verbose(env, "R%d offset is outside of the packet\n", regno);
 		return err;
 	}
 	return err;
@@ -946,12 +938,8 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
 		.reg_type = *reg_type,
 	};
 
-	/* for analyzer ctx accesses are already validated and converted */
-	if (env->analyzer_ops)
-		return 0;
-
-	if (env->prog->aux->ops->is_valid_access &&
-	    env->prog->aux->ops->is_valid_access(off, size, t, &info)) {
+	if (env->ops->is_valid_access &&
+	    env->ops->is_valid_access(off, size, t, &info)) {
 		/* A non zero info.ctx_field_size indicates that this field is a
 		 * candidate for later verifier transformation to load the whole
 		 * field and then apply a mask when accessed with a narrower
@@ -959,16 +947,19 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
 		 * will only allow for whole field access and rejects any other
 		 * type of narrower access.
 		 */
-		env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
 		*reg_type = info.reg_type;
 
+		if (env->analyzer_ops)
+			return 0;
+
+		env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
 		/* remember the offset of last byte accessed in ctx */
 		if (env->prog->aux->max_ctx_offset < off + size)
 			env->prog->aux->max_ctx_offset = off + size;
 		return 0;
 	}
 
-	verbose("invalid bpf_context access off=%d size=%d\n", off, size);
+	verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size);
 	return -EACCES;
 }
 
@@ -983,10 +974,11 @@ static bool __is_pointer_value(bool allow_ptr_leaks,
 
 static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
 {
-	return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]);
+	return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno);
 }
 
-static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
+static int check_pkt_ptr_alignment(struct bpf_verifier_env *env,
+				   const struct bpf_reg_state *reg,
 				   int off, int size, bool strict)
 {
 	struct tnum reg_off;
@@ -1011,7 +1003,8 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
 		char tn_buf[48];
 
 		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-		verbose("misaligned packet access off %d+%s+%d+%d size %d\n",
+		verbose(env,
+			"misaligned packet access off %d+%s+%d+%d size %d\n",
 			ip_align, tn_buf, reg->off, off, size);
 		return -EACCES;
 	}
@@ -1019,7 +1012,8 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
 	return 0;
 }
 
-static int check_generic_ptr_alignment(const struct bpf_reg_state *reg,
+static int check_generic_ptr_alignment(struct bpf_verifier_env *env,
+				       const struct bpf_reg_state *reg,
 				       const char *pointer_desc,
 				       int off, int size, bool strict)
 {
@@ -1034,7 +1028,7 @@ static int check_generic_ptr_alignment(const struct bpf_reg_state *reg,
 		char tn_buf[48];
 
 		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-		verbose("misaligned %saccess off %s+%d+%d size %d\n",
+		verbose(env, "misaligned %saccess off %s+%d+%d size %d\n",
 			pointer_desc, tn_buf, reg->off, off, size);
 		return -EACCES;
 	}
@@ -1051,8 +1045,11 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
 
 	switch (reg->type) {
 	case PTR_TO_PACKET:
-		/* special case, because of NET_IP_ALIGN */
-		return check_pkt_ptr_alignment(reg, off, size, strict);
+	case PTR_TO_PACKET_META:
+		/* Special case, because of NET_IP_ALIGN. Given metadata sits
+		 * right in front, treat it the very same way.
+		 */
+		return check_pkt_ptr_alignment(env, reg, off, size, strict);
 	case PTR_TO_MAP_VALUE:
 		pointer_desc = "value ";
 		break;
@@ -1065,7 +1062,8 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
 	default:
 		break;
 	}
-	return check_generic_ptr_alignment(reg, pointer_desc, off, size, strict);
+	return check_generic_ptr_alignment(env, reg, pointer_desc, off, size,
+					   strict);
 }
 
 /* check whether memory at (regno + off) is accessible for t = (read | write)
@@ -1078,8 +1076,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			    int bpf_size, enum bpf_access_type t,
 			    int value_regno)
 {
-	struct bpf_verifier_state *state = &env->cur_state;
-	struct bpf_reg_state *reg = &state->regs[regno];
+	struct bpf_verifier_state *state = env->cur_state;
+	struct bpf_reg_state *regs = cur_regs(env);
+	struct bpf_reg_state *reg = regs + regno;
 	int size, err = 0;
 
 	size = bpf_size_to_bytes(bpf_size);
@@ -1097,27 +1096,28 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 	if (reg->type == PTR_TO_MAP_VALUE) {
 		if (t == BPF_WRITE && value_regno >= 0 &&
 		    is_pointer_value(env, value_regno)) {
-			verbose("R%d leaks addr into map\n", value_regno);
+			verbose(env, "R%d leaks addr into map\n", value_regno);
 			return -EACCES;
 		}
 
 		err = check_map_access(env, regno, off, size);
 		if (!err && t == BPF_READ && value_regno >= 0)
-			mark_reg_unknown(state->regs, value_regno);
+			mark_reg_unknown(env, regs, value_regno);
 
 	} else if (reg->type == PTR_TO_CTX) {
 		enum bpf_reg_type reg_type = SCALAR_VALUE;
 
 		if (t == BPF_WRITE && value_regno >= 0 &&
 		    is_pointer_value(env, value_regno)) {
-			verbose("R%d leaks addr into ctx\n", value_regno);
+			verbose(env, "R%d leaks addr into ctx\n", value_regno);
 			return -EACCES;
 		}
 		/* ctx accesses must be at a fixed offset, so that we can
 		 * determine what type of data were returned.
 		 */
 		if (reg->off) {
-			verbose("dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n",
+			verbose(env,
+				"dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n",
 				regno, reg->off, off - reg->off);
 			return -EACCES;
 		}
@@ -1125,24 +1125,26 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			char tn_buf[48];
 
 			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-			verbose("variable ctx access var_off=%s off=%d size=%d",
+			verbose(env,
+				"variable ctx access var_off=%s off=%d size=%d",
 				tn_buf, off, size);
 			return -EACCES;
 		}
 		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
 		if (!err && t == BPF_READ && value_regno >= 0) {
 			/* ctx access returns either a scalar, or a
-			 * PTR_TO_PACKET[_END].  In the latter case, we know
-			 * the offset is zero.
+			 * PTR_TO_PACKET[_META,_END]. In the latter
+			 * case, we know the offset is zero.
 			 */
 			if (reg_type == SCALAR_VALUE)
-				mark_reg_unknown(state->regs, value_regno);
+				mark_reg_unknown(env, regs, value_regno);
 			else
-				mark_reg_known_zero(state->regs, value_regno);
-			state->regs[value_regno].id = 0;
-			state->regs[value_regno].off = 0;
-			state->regs[value_regno].range = 0;
-			state->regs[value_regno].type = reg_type;
+				mark_reg_known_zero(env, regs,
+						    value_regno);
+			regs[value_regno].id = 0;
+			regs[value_regno].off = 0;
+			regs[value_regno].range = 0;
+			regs[value_regno].type = reg_type;
 		}
 
 	} else if (reg->type == PTR_TO_STACK) {
@@ -1154,55 +1156,52 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			char tn_buf[48];
 
 			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-			verbose("variable stack access var_off=%s off=%d size=%d",
+			verbose(env, "variable stack access var_off=%s off=%d size=%d",
 				tn_buf, off, size);
 			return -EACCES;
 		}
 		off += reg->var_off.value;
 		if (off >= 0 || off < -MAX_BPF_STACK) {
-			verbose("invalid stack off=%d size=%d\n", off, size);
+			verbose(env, "invalid stack off=%d size=%d\n", off,
+				size);
 			return -EACCES;
 		}
 
 		if (env->prog->aux->stack_depth < -off)
 			env->prog->aux->stack_depth = -off;
 
-		if (t == BPF_WRITE) {
-			if (!env->allow_ptr_leaks &&
-			    state->stack_slot_type[MAX_BPF_STACK + off] == STACK_SPILL &&
-			    size != BPF_REG_SIZE) {
-				verbose("attempt to corrupt spilled pointer on stack\n");
-				return -EACCES;
-			}
-			err = check_stack_write(state, off, size, value_regno);
-		} else {
-			err = check_stack_read(state, off, size, value_regno);
-		}
-	} else if (reg->type == PTR_TO_PACKET) {
+		if (t == BPF_WRITE)
+			err = check_stack_write(env, state, off, size,
+						value_regno);
+		else
+			err = check_stack_read(env, state, off, size,
+					       value_regno);
+	} else if (reg_is_pkt_pointer(reg)) {
 		if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) {
-			verbose("cannot write into packet\n");
+			verbose(env, "cannot write into packet\n");
 			return -EACCES;
 		}
 		if (t == BPF_WRITE && value_regno >= 0 &&
 		    is_pointer_value(env, value_regno)) {
-			verbose("R%d leaks addr into packet\n", value_regno);
+			verbose(env, "R%d leaks addr into packet\n",
+				value_regno);
 			return -EACCES;
 		}
 		err = check_packet_access(env, regno, off, size);
 		if (!err && t == BPF_READ && value_regno >= 0)
-			mark_reg_unknown(state->regs, value_regno);
+			mark_reg_unknown(env, regs, value_regno);
 	} else {
-		verbose("R%d invalid mem access '%s'\n",
-			regno, reg_type_str[reg->type]);
+		verbose(env, "R%d invalid mem access '%s'\n", regno,
+			reg_type_str[reg->type]);
 		return -EACCES;
 	}
 
 	if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
-	    state->regs[value_regno].type == SCALAR_VALUE) {
+	    regs[value_regno].type == SCALAR_VALUE) {
 		/* b/h/w load zero-extends, mark upper bits as known 0 */
-		state->regs[value_regno].var_off = tnum_cast(
-					state->regs[value_regno].var_off, size);
-		__update_reg_bounds(&state->regs[value_regno]);
+		regs[value_regno].var_off =
+			tnum_cast(regs[value_regno].var_off, size);
+		__update_reg_bounds(&regs[value_regno]);
 	}
 	return err;
 }
@@ -1213,7 +1212,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 
 	if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) ||
 	    insn->imm != 0) {
-		verbose("BPF_XADD uses reserved fields\n");
+		verbose(env, "BPF_XADD uses reserved fields\n");
 		return -EINVAL;
 	}
 
@@ -1228,7 +1227,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 		return err;
 
 	if (is_pointer_value(env, insn->src_reg)) {
-		verbose("R%d leaks addr into mem\n", insn->src_reg);
+		verbose(env, "R%d leaks addr into mem\n", insn->src_reg);
 		return -EACCES;
 	}
 
@@ -1259,9 +1258,9 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 				int access_size, bool zero_size_allowed,
 				struct bpf_call_arg_meta *meta)
 {
-	struct bpf_verifier_state *state = &env->cur_state;
+	struct bpf_verifier_state *state = env->cur_state;
 	struct bpf_reg_state *regs = state->regs;
-	int off, i;
+	int off, i, slot, spi;
 
 	if (regs[regno].type != PTR_TO_STACK) {
 		/* Allow zero-byte read from NULL, regardless of pointer type */
@@ -1269,7 +1268,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 		    register_is_null(regs[regno]))
 			return 0;
 
-		verbose("R%d type=%s expected=%s\n", regno,
+		verbose(env, "R%d type=%s expected=%s\n", regno,
 			reg_type_str[regs[regno].type],
 			reg_type_str[PTR_TO_STACK]);
 		return -EACCES;
@@ -1280,13 +1279,13 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 		char tn_buf[48];
 
 		tnum_strn(tn_buf, sizeof(tn_buf), regs[regno].var_off);
-		verbose("invalid variable stack read R%d var_off=%s\n",
+		verbose(env, "invalid variable stack read R%d var_off=%s\n",
 			regno, tn_buf);
 	}
 	off = regs[regno].off + regs[regno].var_off.value;
 	if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
 	    access_size <= 0) {
-		verbose("invalid stack type R%d off=%d access_size=%d\n",
+		verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
 			regno, off, access_size);
 		return -EACCES;
 	}
@@ -1301,8 +1300,12 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 	}
 
 	for (i = 0; i < access_size; i++) {
-		if (state->stack_slot_type[MAX_BPF_STACK + off + i] != STACK_MISC) {
-			verbose("invalid indirect read from stack off %d+%d size %d\n",
+		slot = -(off + i) - 1;
+		spi = slot / BPF_REG_SIZE;
+		if (state->allocated_stack <= slot ||
+		    state->stack[spi].slot_type[slot % BPF_REG_SIZE] !=
+			STACK_MISC) {
+			verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
 				off, i, access_size);
 			return -EACCES;
 		}
@@ -1314,10 +1317,11 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 				   int access_size, bool zero_size_allowed,
 				   struct bpf_call_arg_meta *meta)
 {
-	struct bpf_reg_state *regs = env->cur_state.regs, *reg = &regs[regno];
+	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
 
 	switch (reg->type) {
 	case PTR_TO_PACKET:
+	case PTR_TO_PACKET_META:
 		return check_packet_access(env, regno, reg->off, access_size);
 	case PTR_TO_MAP_VALUE:
 		return check_map_access(env, regno, reg->off, access_size);
@@ -1331,7 +1335,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			  enum bpf_arg_type arg_type,
 			  struct bpf_call_arg_meta *meta)
 {
-	struct bpf_reg_state *regs = env->cur_state.regs, *reg = &regs[regno];
+	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
 	enum bpf_reg_type expected_type, type = reg->type;
 	int err = 0;
 
@@ -1344,22 +1348,24 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 
 	if (arg_type == ARG_ANYTHING) {
 		if (is_pointer_value(env, regno)) {
-			verbose("R%d leaks addr into helper function\n", regno);
+			verbose(env, "R%d leaks addr into helper function\n",
+				regno);
 			return -EACCES;
 		}
 		return 0;
 	}
 
-	if (type == PTR_TO_PACKET &&
+	if (type_is_pkt_pointer(type) &&
 	    !may_access_direct_pkt_data(env, meta, BPF_READ)) {
-		verbose("helper access to the packet is not allowed\n");
+		verbose(env, "helper access to the packet is not allowed\n");
 		return -EACCES;
 	}
 
 	if (arg_type == ARG_PTR_TO_MAP_KEY ||
 	    arg_type == ARG_PTR_TO_MAP_VALUE) {
 		expected_type = PTR_TO_STACK;
-		if (type != PTR_TO_PACKET && type != expected_type)
+		if (!type_is_pkt_pointer(type) &&
+		    type != expected_type)
 			goto err_type;
 	} else if (arg_type == ARG_CONST_SIZE ||
 		   arg_type == ARG_CONST_SIZE_OR_ZERO) {
@@ -1383,12 +1389,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		 */
 		if (register_is_null(*reg))
 			/* final test in check_stack_boundary() */;
-		else if (type != PTR_TO_PACKET && type != PTR_TO_MAP_VALUE &&
+		else if (!type_is_pkt_pointer(type) &&
+			 type != PTR_TO_MAP_VALUE &&
 			 type != expected_type)
 			goto err_type;
 		meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
 	} else {
-		verbose("unsupported arg_type %d\n", arg_type);
+		verbose(env, "unsupported arg_type %d\n", arg_type);
 		return -EFAULT;
 	}
 
@@ -1406,10 +1413,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			 * we have to check map_key here. Otherwise it means
 			 * that kernel subsystem misconfigured verifier
 			 */
-			verbose("invalid map_ptr to access map->key\n");
+			verbose(env, "invalid map_ptr to access map->key\n");
 			return -EACCES;
 		}
-		if (type == PTR_TO_PACKET)
+		if (type_is_pkt_pointer(type))
 			err = check_packet_access(env, regno, reg->off,
 						  meta->map_ptr->key_size);
 		else
@@ -1422,10 +1429,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		 */
 		if (!meta->map_ptr) {
 			/* kernel subsystem misconfigured verifier */
-			verbose("invalid map_ptr to access map->value\n");
+			verbose(env, "invalid map_ptr to access map->value\n");
 			return -EACCES;
 		}
-		if (type == PTR_TO_PACKET)
+		if (type_is_pkt_pointer(type))
 			err = check_packet_access(env, regno, reg->off,
 						  meta->map_ptr->value_size);
 		else
@@ -1442,7 +1449,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		 */
 		if (regno == 0) {
 			/* kernel subsystem misconfigured verifier */
-			verbose("ARG_CONST_SIZE cannot be first argument\n");
+			verbose(env,
+				"ARG_CONST_SIZE cannot be first argument\n");
 			return -EACCES;
 		}
 
@@ -1459,7 +1467,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			meta = NULL;
 
 		if (reg->smin_value < 0) {
-			verbose("R%d min value is negative, either use unsigned or 'var &= const'\n",
+			verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n",
 				regno);
 			return -EACCES;
 		}
@@ -1473,7 +1481,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		}
 
 		if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
-			verbose("R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
+			verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
 				regno);
 			return -EACCES;
 		}
@@ -1484,12 +1492,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 
 	return err;
 err_type:
-	verbose("R%d type=%s expected=%s\n", regno,
+	verbose(env, "R%d type=%s expected=%s\n", regno,
 		reg_type_str[type], reg_type_str[expected_type]);
 	return -EACCES;
 }
 
-static int check_map_func_compatibility(struct bpf_map *map, int func_id)
+static int check_map_func_compatibility(struct bpf_verifier_env *env,
+					struct bpf_map *map, int func_id)
 {
 	if (!map)
 		return 0;
@@ -1502,7 +1511,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		break;
 	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
 		if (func_id != BPF_FUNC_perf_event_read &&
-		    func_id != BPF_FUNC_perf_event_output)
+		    func_id != BPF_FUNC_perf_event_output &&
+		    func_id != BPF_FUNC_perf_event_read_value)
 			goto error;
 		break;
 	case BPF_MAP_TYPE_STACK_TRACE:
@@ -1522,6 +1532,11 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		if (func_id != BPF_FUNC_redirect_map)
 			goto error;
 		break;
+	/* Restrict bpf side of cpumap, open when use-cases appear */
+	case BPF_MAP_TYPE_CPUMAP:
+		if (func_id != BPF_FUNC_redirect_map)
+			goto error;
+		break;
 	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
 	case BPF_MAP_TYPE_HASH_OF_MAPS:
 		if (func_id != BPF_FUNC_map_lookup_elem)
@@ -1545,6 +1560,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		break;
 	case BPF_FUNC_perf_event_read:
 	case BPF_FUNC_perf_event_output:
+	case BPF_FUNC_perf_event_read_value:
 		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
 			goto error;
 		break;
@@ -1558,7 +1574,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 			goto error;
 		break;
 	case BPF_FUNC_redirect_map:
-		if (map->map_type != BPF_MAP_TYPE_DEVMAP)
+		if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
+		    map->map_type != BPF_MAP_TYPE_CPUMAP)
 			goto error;
 		break;
 	case BPF_FUNC_sk_redirect_map:
@@ -1575,7 +1592,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 
 	return 0;
 error:
-	verbose("cannot pass map_type %d into func %s#%d\n",
+	verbose(env, "cannot pass map_type %d into func %s#%d\n",
 		map->map_type, func_id_name(func_id), func_id);
 	return -EINVAL;
 }
@@ -1598,57 +1615,55 @@ static int check_raw_mode(const struct bpf_func_proto *fn)
 	return count > 1 ? -EINVAL : 0;
 }
 
-/* Packet data might have moved, any old PTR_TO_PACKET[_END] are now invalid,
- * so turn them into unknown SCALAR_VALUE.
+/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
+ * are now invalid, so turn them into unknown SCALAR_VALUE.
  */
 static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
 {
-	struct bpf_verifier_state *state = &env->cur_state;
+	struct bpf_verifier_state *state = env->cur_state;
 	struct bpf_reg_state *regs = state->regs, *reg;
 	int i;
 
 	for (i = 0; i < MAX_BPF_REG; i++)
-		if (regs[i].type == PTR_TO_PACKET ||
-		    regs[i].type == PTR_TO_PACKET_END)
-			mark_reg_unknown(regs, i);
+		if (reg_is_pkt_pointer_any(&regs[i]))
+			mark_reg_unknown(env, regs, i);
 
-	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
-		if (state->stack_slot_type[i] != STACK_SPILL)
+	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+		if (state->stack[i].slot_type[0] != STACK_SPILL)
 			continue;
-		reg = &state->spilled_regs[i / BPF_REG_SIZE];
-		if (reg->type != PTR_TO_PACKET &&
-		    reg->type != PTR_TO_PACKET_END)
-			continue;
-		__mark_reg_unknown(reg);
+		reg = &state->stack[i].spilled_ptr;
+		if (reg_is_pkt_pointer_any(reg))
+			__mark_reg_unknown(reg);
 	}
 }
 
 static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
 {
-	struct bpf_verifier_state *state = &env->cur_state;
 	const struct bpf_func_proto *fn = NULL;
-	struct bpf_reg_state *regs = state->regs;
+	struct bpf_reg_state *regs;
 	struct bpf_call_arg_meta meta;
 	bool changes_data;
 	int i, err;
 
 	/* find function prototype */
 	if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
-		verbose("invalid func %s#%d\n", func_id_name(func_id), func_id);
+		verbose(env, "invalid func %s#%d\n", func_id_name(func_id),
+			func_id);
 		return -EINVAL;
 	}
 
-	if (env->prog->aux->ops->get_func_proto)
-		fn = env->prog->aux->ops->get_func_proto(func_id);
+	if (env->ops->get_func_proto)
+		fn = env->ops->get_func_proto(func_id);
 
 	if (!fn) {
-		verbose("unknown func %s#%d\n", func_id_name(func_id), func_id);
+		verbose(env, "unknown func %s#%d\n", func_id_name(func_id),
+			func_id);
 		return -EINVAL;
 	}
 
 	/* eBPF programs must be GPL compatible to use GPL-ed functions */
 	if (!env->prog->gpl_compatible && fn->gpl_only) {
-		verbose("cannot call GPL only function from proprietary program\n");
+		verbose(env, "cannot call GPL only function from proprietary program\n");
 		return -EINVAL;
 	}
 
@@ -1662,7 +1677,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
 	 */
 	err = check_raw_mode(fn);
 	if (err) {
-		verbose("kernel subsystem misconfigured func %s#%d\n",
+		verbose(env, "kernel subsystem misconfigured func %s#%d\n",
 			func_id_name(func_id), func_id);
 		return err;
 	}
@@ -1693,16 +1708,17 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
 			return err;
 	}
 
+	regs = cur_regs(env);
 	/* reset caller saved regs */
 	for (i = 0; i < CALLER_SAVED_REGS; i++) {
-		mark_reg_not_init(regs, caller_saved[i]);
+		mark_reg_not_init(env, regs, caller_saved[i]);
 		check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
 	}
 
 	/* update return register (already marked as written above) */
 	if (fn->ret_type == RET_INTEGER) {
 		/* sets type to SCALAR_VALUE */
-		mark_reg_unknown(regs, BPF_REG_0);
+		mark_reg_unknown(env, regs, BPF_REG_0);
 	} else if (fn->ret_type == RET_VOID) {
 		regs[BPF_REG_0].type = NOT_INIT;
 	} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
@@ -1710,14 +1726,15 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
 
 		regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
 		/* There is no offset yet applied, variable or fixed */
-		mark_reg_known_zero(regs, BPF_REG_0);
+		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].off = 0;
 		/* remember map_ptr, so that check_map_access()
 		 * can check 'value_size' boundary of memory access
 		 * to map element returned from bpf_map_lookup_elem()
 		 */
 		if (meta.map_ptr == NULL) {
-			verbose("kernel subsystem misconfigured verifier\n");
+			verbose(env,
+				"kernel subsystem misconfigured verifier\n");
 			return -EINVAL;
 		}
 		regs[BPF_REG_0].map_ptr = meta.map_ptr;
@@ -1728,12 +1745,12 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
 		else if (insn_aux->map_ptr != meta.map_ptr)
 			insn_aux->map_ptr = BPF_MAP_PTR_POISON;
 	} else {
-		verbose("unknown return type %d of func %s#%d\n",
+		verbose(env, "unknown return type %d of func %s#%d\n",
 			fn->ret_type, func_id_name(func_id), func_id);
 		return -EINVAL;
 	}
 
-	err = check_map_func_compatibility(meta.map_ptr, func_id);
+	err = check_map_func_compatibility(env, meta.map_ptr, func_id);
 	if (err)
 		return err;
 
@@ -1780,7 +1797,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 				   const struct bpf_reg_state *ptr_reg,
 				   const struct bpf_reg_state *off_reg)
 {
-	struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg;
+	struct bpf_reg_state *regs = cur_regs(env), *dst_reg;
 	bool known = tnum_is_const(off_reg->var_off);
 	s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value,
 	    smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
@@ -1792,39 +1809,42 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	dst_reg = &regs[dst];
 
 	if (WARN_ON_ONCE(known && (smin_val != smax_val))) {
-		print_verifier_state(&env->cur_state);
-		verbose("verifier internal error: known but bad sbounds\n");
+		print_verifier_state(env, env->cur_state);
+		verbose(env,
+			"verifier internal error: known but bad sbounds\n");
 		return -EINVAL;
 	}
 	if (WARN_ON_ONCE(known && (umin_val != umax_val))) {
-		print_verifier_state(&env->cur_state);
-		verbose("verifier internal error: known but bad ubounds\n");
+		print_verifier_state(env, env->cur_state);
+		verbose(env,
+			"verifier internal error: known but bad ubounds\n");
 		return -EINVAL;
 	}
 
 	if (BPF_CLASS(insn->code) != BPF_ALU64) {
 		/* 32-bit ALU ops on pointers produce (meaningless) scalars */
 		if (!env->allow_ptr_leaks)
-			verbose("R%d 32-bit pointer arithmetic prohibited\n",
+			verbose(env,
+				"R%d 32-bit pointer arithmetic prohibited\n",
 				dst);
 		return -EACCES;
 	}
 
 	if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
 		if (!env->allow_ptr_leaks)
-			verbose("R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n",
+			verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n",
 				dst);
 		return -EACCES;
 	}
 	if (ptr_reg->type == CONST_PTR_TO_MAP) {
 		if (!env->allow_ptr_leaks)
-			verbose("R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
+			verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
 				dst);
 		return -EACCES;
 	}
 	if (ptr_reg->type == PTR_TO_PACKET_END) {
 		if (!env->allow_ptr_leaks)
-			verbose("R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n",
+			verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n",
 				dst);
 		return -EACCES;
 	}
@@ -1879,7 +1899,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		}
 		dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off);
 		dst_reg->off = ptr_reg->off;
-		if (ptr_reg->type == PTR_TO_PACKET) {
+		if (reg_is_pkt_pointer(ptr_reg)) {
 			dst_reg->id = ++env->id_gen;
 			/* something was added to pkt_ptr, set range to zero */
 			dst_reg->range = 0;
@@ -1889,7 +1909,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		if (dst_reg == off_reg) {
 			/* scalar -= pointer.  Creates an unknown scalar */
 			if (!env->allow_ptr_leaks)
-				verbose("R%d tried to subtract pointer from scalar\n",
+				verbose(env, "R%d tried to subtract pointer from scalar\n",
 					dst);
 			return -EACCES;
 		}
@@ -1899,7 +1919,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		 */
 		if (ptr_reg->type == PTR_TO_STACK) {
 			if (!env->allow_ptr_leaks)
-				verbose("R%d subtraction from stack pointer prohibited\n",
+				verbose(env, "R%d subtraction from stack pointer prohibited\n",
 					dst);
 			return -EACCES;
 		}
@@ -1939,7 +1959,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		}
 		dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off);
 		dst_reg->off = ptr_reg->off;
-		if (ptr_reg->type == PTR_TO_PACKET) {
+		if (reg_is_pkt_pointer(ptr_reg)) {
 			dst_reg->id = ++env->id_gen;
 			/* something was added to pkt_ptr, set range to zero */
 			if (smin_val < 0)
@@ -1954,13 +1974,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		 * ptr &= ~3 which would reduce min_value by 3.)
 		 */
 		if (!env->allow_ptr_leaks)
-			verbose("R%d bitwise operator %s on pointer prohibited\n",
+			verbose(env, "R%d bitwise operator %s on pointer prohibited\n",
 				dst, bpf_alu_string[opcode >> 4]);
 		return -EACCES;
 	default:
 		/* other operators (e.g. MUL,LSH) produce non-pointer results */
 		if (!env->allow_ptr_leaks)
-			verbose("R%d pointer arithmetic with %s operator prohibited\n",
+			verbose(env, "R%d pointer arithmetic with %s operator prohibited\n",
 				dst, bpf_alu_string[opcode >> 4]);
 		return -EACCES;
 	}
@@ -1976,7 +1996,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 				      struct bpf_reg_state *dst_reg,
 				      struct bpf_reg_state src_reg)
 {
-	struct bpf_reg_state *regs = env->cur_state.regs;
+	struct bpf_reg_state *regs = cur_regs(env);
 	u8 opcode = BPF_OP(insn->code);
 	bool src_known, dst_known;
 	s64 smin_val, smax_val;
@@ -2126,7 +2146,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 			/* Shifts greater than 63 are undefined.  This includes
 			 * shifts by a negative number.
 			 */
-			mark_reg_unknown(regs, insn->dst_reg);
+			mark_reg_unknown(env, regs, insn->dst_reg);
 			break;
 		}
 		/* We lose all sign bit information (except what we can pick
@@ -2154,7 +2174,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 			/* Shifts greater than 63 are undefined.  This includes
 			 * shifts by a negative number.
 			 */
-			mark_reg_unknown(regs, insn->dst_reg);
+			mark_reg_unknown(env, regs, insn->dst_reg);
 			break;
 		}
 		/* BPF_RSH is an unsigned shift, so make the appropriate casts */
@@ -2182,7 +2202,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		__update_reg_bounds(dst_reg);
 		break;
 	default:
-		mark_reg_unknown(regs, insn->dst_reg);
+		mark_reg_unknown(env, regs, insn->dst_reg);
 		break;
 	}
 
@@ -2197,7 +2217,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 				   struct bpf_insn *insn)
 {
-	struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg, *src_reg;
+	struct bpf_reg_state *regs = cur_regs(env), *dst_reg, *src_reg;
 	struct bpf_reg_state *ptr_reg = NULL, off_reg = {0};
 	u8 opcode = BPF_OP(insn->code);
 	int rc;
@@ -2214,12 +2234,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 				 * an arbitrary scalar.
 				 */
 				if (!env->allow_ptr_leaks) {
-					verbose("R%d pointer %s pointer prohibited\n",
+					verbose(env, "R%d pointer %s pointer prohibited\n",
 						insn->dst_reg,
 						bpf_alu_string[opcode >> 4]);
 					return -EACCES;
 				}
-				mark_reg_unknown(regs, insn->dst_reg);
+				mark_reg_unknown(env, regs, insn->dst_reg);
 				return 0;
 			} else {
 				/* scalar += pointer
@@ -2271,13 +2291,13 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 
 	/* Got here implies adding two SCALAR_VALUEs */
 	if (WARN_ON_ONCE(ptr_reg)) {
-		print_verifier_state(&env->cur_state);
-		verbose("verifier internal error: unexpected ptr_reg\n");
+		print_verifier_state(env, env->cur_state);
+		verbose(env, "verifier internal error: unexpected ptr_reg\n");
 		return -EINVAL;
 	}
 	if (WARN_ON(!src_reg)) {
-		print_verifier_state(&env->cur_state);
-		verbose("verifier internal error: no src_reg\n");
+		print_verifier_state(env, env->cur_state);
+		verbose(env, "verifier internal error: no src_reg\n");
 		return -EINVAL;
 	}
 	return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
@@ -2286,7 +2306,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 /* check validity of 32-bit and 64-bit arithmetic operations */
 static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 {
-	struct bpf_reg_state *regs = env->cur_state.regs;
+	struct bpf_reg_state *regs = cur_regs(env);
 	u8 opcode = BPF_OP(insn->code);
 	int err;
 
@@ -2295,14 +2315,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			if (BPF_SRC(insn->code) != 0 ||
 			    insn->src_reg != BPF_REG_0 ||
 			    insn->off != 0 || insn->imm != 0) {
-				verbose("BPF_NEG uses reserved fields\n");
+				verbose(env, "BPF_NEG uses reserved fields\n");
 				return -EINVAL;
 			}
 		} else {
 			if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
 			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
 			    BPF_CLASS(insn->code) == BPF_ALU64) {
-				verbose("BPF_END uses reserved fields\n");
+				verbose(env, "BPF_END uses reserved fields\n");
 				return -EINVAL;
 			}
 		}
@@ -2313,7 +2333,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			return err;
 
 		if (is_pointer_value(env, insn->dst_reg)) {
-			verbose("R%d pointer arithmetic prohibited\n",
+			verbose(env, "R%d pointer arithmetic prohibited\n",
 				insn->dst_reg);
 			return -EACCES;
 		}
@@ -2327,7 +2347,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 		if (BPF_SRC(insn->code) == BPF_X) {
 			if (insn->imm != 0 || insn->off != 0) {
-				verbose("BPF_MOV uses reserved fields\n");
+				verbose(env, "BPF_MOV uses reserved fields\n");
 				return -EINVAL;
 			}
 
@@ -2337,7 +2357,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 				return err;
 		} else {
 			if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
-				verbose("BPF_MOV uses reserved fields\n");
+				verbose(env, "BPF_MOV uses reserved fields\n");
 				return -EINVAL;
 			}
 		}
@@ -2357,11 +2377,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			} else {
 				/* R1 = (u32) R2 */
 				if (is_pointer_value(env, insn->src_reg)) {
-					verbose("R%d partial copy of pointer\n",
+					verbose(env,
+						"R%d partial copy of pointer\n",
 						insn->src_reg);
 					return -EACCES;
 				}
-				mark_reg_unknown(regs, insn->dst_reg);
+				mark_reg_unknown(env, regs, insn->dst_reg);
 				/* high 32 bits are known zero. */
 				regs[insn->dst_reg].var_off = tnum_cast(
 						regs[insn->dst_reg].var_off, 4);
@@ -2376,14 +2397,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		}
 
 	} else if (opcode > BPF_END) {
-		verbose("invalid BPF_ALU opcode %x\n", opcode);
+		verbose(env, "invalid BPF_ALU opcode %x\n", opcode);
 		return -EINVAL;
 
 	} else {	/* all other ALU ops: and, sub, xor, add, ... */
 
 		if (BPF_SRC(insn->code) == BPF_X) {
 			if (insn->imm != 0 || insn->off != 0) {
-				verbose("BPF_ALU uses reserved fields\n");
+				verbose(env, "BPF_ALU uses reserved fields\n");
 				return -EINVAL;
 			}
 			/* check src1 operand */
@@ -2392,7 +2413,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 				return err;
 		} else {
 			if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
-				verbose("BPF_ALU uses reserved fields\n");
+				verbose(env, "BPF_ALU uses reserved fields\n");
 				return -EINVAL;
 			}
 		}
@@ -2404,7 +2425,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 		if ((opcode == BPF_MOD || opcode == BPF_DIV) &&
 		    BPF_SRC(insn->code) == BPF_K && insn->imm == 0) {
-			verbose("div by zero\n");
+			verbose(env, "div by zero\n");
 			return -EINVAL;
 		}
 
@@ -2413,7 +2434,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
 
 			if (insn->imm < 0 || insn->imm >= size) {
-				verbose("invalid shift %d\n", insn->imm);
+				verbose(env, "invalid shift %d\n", insn->imm);
 				return -EINVAL;
 			}
 		}
@@ -2431,6 +2452,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 				   struct bpf_reg_state *dst_reg,
+				   enum bpf_reg_type type,
 				   bool range_right_open)
 {
 	struct bpf_reg_state *regs = state->regs, *reg;
@@ -2501,15 +2523,15 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 	 * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16.
 	 */
 	for (i = 0; i < MAX_BPF_REG; i++)
-		if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
+		if (regs[i].type == type && regs[i].id == dst_reg->id)
 			/* keep the maximum range already checked */
 			regs[i].range = max(regs[i].range, new_range);
 
-	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
-		if (state->stack_slot_type[i] != STACK_SPILL)
+	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+		if (state->stack[i].slot_type[0] != STACK_SPILL)
 			continue;
-		reg = &state->spilled_regs[i / BPF_REG_SIZE];
-		if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
+		reg = &state->stack[i].spilled_ptr;
+		if (reg->type == type && reg->id == dst_reg->id)
 			reg->range = max(reg->range, new_range);
 	}
 }
@@ -2758,29 +2780,122 @@ static void mark_map_regs(struct bpf_verifier_state *state, u32 regno,
 	for (i = 0; i < MAX_BPF_REG; i++)
 		mark_map_reg(regs, i, id, is_null);
 
-	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
-		if (state->stack_slot_type[i] != STACK_SPILL)
+	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+		if (state->stack[i].slot_type[0] != STACK_SPILL)
 			continue;
-		mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE, id, is_null);
+		mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null);
 	}
 }
 
+static bool try_match_pkt_pointers(const struct bpf_insn *insn,
+				   struct bpf_reg_state *dst_reg,
+				   struct bpf_reg_state *src_reg,
+				   struct bpf_verifier_state *this_branch,
+				   struct bpf_verifier_state *other_branch)
+{
+	if (BPF_SRC(insn->code) != BPF_X)
+		return false;
+
+	switch (BPF_OP(insn->code)) {
+	case BPF_JGT:
+		if ((dst_reg->type == PTR_TO_PACKET &&
+		     src_reg->type == PTR_TO_PACKET_END) ||
+		    (dst_reg->type == PTR_TO_PACKET_META &&
+		     reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
+			/* pkt_data' > pkt_end, pkt_meta' > pkt_data */
+			find_good_pkt_pointers(this_branch, dst_reg,
+					       dst_reg->type, false);
+		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
+			    src_reg->type == PTR_TO_PACKET) ||
+			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
+			    src_reg->type == PTR_TO_PACKET_META)) {
+			/* pkt_end > pkt_data', pkt_data > pkt_meta' */
+			find_good_pkt_pointers(other_branch, src_reg,
+					       src_reg->type, true);
+		} else {
+			return false;
+		}
+		break;
+	case BPF_JLT:
+		if ((dst_reg->type == PTR_TO_PACKET &&
+		     src_reg->type == PTR_TO_PACKET_END) ||
+		    (dst_reg->type == PTR_TO_PACKET_META &&
+		     reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
+			/* pkt_data' < pkt_end, pkt_meta' < pkt_data */
+			find_good_pkt_pointers(other_branch, dst_reg,
+					       dst_reg->type, true);
+		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
+			    src_reg->type == PTR_TO_PACKET) ||
+			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
+			    src_reg->type == PTR_TO_PACKET_META)) {
+			/* pkt_end < pkt_data', pkt_data > pkt_meta' */
+			find_good_pkt_pointers(this_branch, src_reg,
+					       src_reg->type, false);
+		} else {
+			return false;
+		}
+		break;
+	case BPF_JGE:
+		if ((dst_reg->type == PTR_TO_PACKET &&
+		     src_reg->type == PTR_TO_PACKET_END) ||
+		    (dst_reg->type == PTR_TO_PACKET_META &&
+		     reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
+			/* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */
+			find_good_pkt_pointers(this_branch, dst_reg,
+					       dst_reg->type, true);
+		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
+			    src_reg->type == PTR_TO_PACKET) ||
+			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
+			    src_reg->type == PTR_TO_PACKET_META)) {
+			/* pkt_end >= pkt_data', pkt_data >= pkt_meta' */
+			find_good_pkt_pointers(other_branch, src_reg,
+					       src_reg->type, false);
+		} else {
+			return false;
+		}
+		break;
+	case BPF_JLE:
+		if ((dst_reg->type == PTR_TO_PACKET &&
+		     src_reg->type == PTR_TO_PACKET_END) ||
+		    (dst_reg->type == PTR_TO_PACKET_META &&
+		     reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
+			/* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */
+			find_good_pkt_pointers(other_branch, dst_reg,
+					       dst_reg->type, false);
+		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
+			    src_reg->type == PTR_TO_PACKET) ||
+			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
+			    src_reg->type == PTR_TO_PACKET_META)) {
+			/* pkt_end <= pkt_data', pkt_data <= pkt_meta' */
+			find_good_pkt_pointers(this_branch, src_reg,
+					       src_reg->type, true);
+		} else {
+			return false;
+		}
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
 static int check_cond_jmp_op(struct bpf_verifier_env *env,
 			     struct bpf_insn *insn, int *insn_idx)
 {
-	struct bpf_verifier_state *other_branch, *this_branch = &env->cur_state;
+	struct bpf_verifier_state *other_branch, *this_branch = env->cur_state;
 	struct bpf_reg_state *regs = this_branch->regs, *dst_reg;
 	u8 opcode = BPF_OP(insn->code);
 	int err;
 
 	if (opcode > BPF_JSLE) {
-		verbose("invalid BPF_JMP opcode %x\n", opcode);
+		verbose(env, "invalid BPF_JMP opcode %x\n", opcode);
 		return -EINVAL;
 	}
 
 	if (BPF_SRC(insn->code) == BPF_X) {
 		if (insn->imm != 0) {
-			verbose("BPF_JMP uses reserved fields\n");
+			verbose(env, "BPF_JMP uses reserved fields\n");
 			return -EINVAL;
 		}
 
@@ -2790,13 +2905,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 			return err;
 
 		if (is_pointer_value(env, insn->src_reg)) {
-			verbose("R%d pointer comparison prohibited\n",
+			verbose(env, "R%d pointer comparison prohibited\n",
 				insn->src_reg);
 			return -EACCES;
 		}
 	} else {
 		if (insn->src_reg != BPF_REG_0) {
-			verbose("BPF_JMP uses reserved fields\n");
+			verbose(env, "BPF_JMP uses reserved fields\n");
 			return -EINVAL;
 		}
 	}
@@ -2871,52 +2986,15 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		 */
 		mark_map_regs(this_branch, insn->dst_reg, opcode == BPF_JNE);
 		mark_map_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ);
-	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
-		   dst_reg->type == PTR_TO_PACKET &&
-		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-		/* pkt_data' > pkt_end */
-		find_good_pkt_pointers(this_branch, dst_reg, false);
-	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
-		   dst_reg->type == PTR_TO_PACKET_END &&
-		   regs[insn->src_reg].type == PTR_TO_PACKET) {
-		/* pkt_end > pkt_data' */
-		find_good_pkt_pointers(other_branch, &regs[insn->src_reg], true);
-	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT &&
-		   dst_reg->type == PTR_TO_PACKET &&
-		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-		/* pkt_data' < pkt_end */
-		find_good_pkt_pointers(other_branch, dst_reg, true);
-	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT &&
-		   dst_reg->type == PTR_TO_PACKET_END &&
-		   regs[insn->src_reg].type == PTR_TO_PACKET) {
-		/* pkt_end < pkt_data' */
-		find_good_pkt_pointers(this_branch, &regs[insn->src_reg], false);
-	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
-		   dst_reg->type == PTR_TO_PACKET &&
-		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-		/* pkt_data' >= pkt_end */
-		find_good_pkt_pointers(this_branch, dst_reg, true);
-	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
-		   dst_reg->type == PTR_TO_PACKET_END &&
-		   regs[insn->src_reg].type == PTR_TO_PACKET) {
-		/* pkt_end >= pkt_data' */
-		find_good_pkt_pointers(other_branch, &regs[insn->src_reg], false);
-	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE &&
-		   dst_reg->type == PTR_TO_PACKET &&
-		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-		/* pkt_data' <= pkt_end */
-		find_good_pkt_pointers(other_branch, dst_reg, false);
-	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE &&
-		   dst_reg->type == PTR_TO_PACKET_END &&
-		   regs[insn->src_reg].type == PTR_TO_PACKET) {
-		/* pkt_end <= pkt_data' */
-		find_good_pkt_pointers(this_branch, &regs[insn->src_reg], true);
-	} else if (is_pointer_value(env, insn->dst_reg)) {
-		verbose("R%d pointer comparison prohibited\n", insn->dst_reg);
+	} else if (!try_match_pkt_pointers(insn, dst_reg, &regs[insn->src_reg],
+					   this_branch, other_branch) &&
+		   is_pointer_value(env, insn->dst_reg)) {
+		verbose(env, "R%d pointer comparison prohibited\n",
+			insn->dst_reg);
 		return -EACCES;
 	}
-	if (log_level)
-		print_verifier_state(this_branch);
+	if (env->log.level)
+		print_verifier_state(env, this_branch);
 	return 0;
 }
 
@@ -2931,15 +3009,15 @@ static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
 /* verify BPF_LD_IMM64 instruction */
 static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 {
-	struct bpf_reg_state *regs = env->cur_state.regs;
+	struct bpf_reg_state *regs = cur_regs(env);
 	int err;
 
 	if (BPF_SIZE(insn->code) != BPF_DW) {
-		verbose("invalid BPF_LD_IMM insn\n");
+		verbose(env, "invalid BPF_LD_IMM insn\n");
 		return -EINVAL;
 	}
 	if (insn->off != 0) {
-		verbose("BPF_LD_IMM64 uses reserved fields\n");
+		verbose(env, "BPF_LD_IMM64 uses reserved fields\n");
 		return -EINVAL;
 	}
 
@@ -2992,19 +3070,19 @@ static bool may_access_skb(enum bpf_prog_type type)
  */
 static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 {
-	struct bpf_reg_state *regs = env->cur_state.regs;
+	struct bpf_reg_state *regs = cur_regs(env);
 	u8 mode = BPF_MODE(insn->code);
 	int i, err;
 
 	if (!may_access_skb(env->prog->type)) {
-		verbose("BPF_LD_[ABS|IND] instructions not allowed for this program type\n");
+		verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n");
 		return -EINVAL;
 	}
 
 	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
 	    BPF_SIZE(insn->code) == BPF_DW ||
 	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
-		verbose("BPF_LD_[ABS|IND] uses reserved fields\n");
+		verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n");
 		return -EINVAL;
 	}
 
@@ -3014,7 +3092,8 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		return err;
 
 	if (regs[BPF_REG_6].type != PTR_TO_CTX) {
-		verbose("at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
+		verbose(env,
+			"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
 		return -EINVAL;
 	}
 
@@ -3027,7 +3106,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 	/* reset caller saved regs to unreadable */
 	for (i = 0; i < CALLER_SAVED_REGS; i++) {
-		mark_reg_not_init(regs, caller_saved[i]);
+		mark_reg_not_init(env, regs, caller_saved[i]);
 		check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
 	}
 
@@ -3035,7 +3114,44 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	 * the value fetched from the packet.
 	 * Already marked as written above.
 	 */
-	mark_reg_unknown(regs, BPF_REG_0);
+	mark_reg_unknown(env, regs, BPF_REG_0);
+	return 0;
+}
+
+static int check_return_code(struct bpf_verifier_env *env)
+{
+	struct bpf_reg_state *reg;
+	struct tnum range = tnum_range(0, 1);
+
+	switch (env->prog->type) {
+	case BPF_PROG_TYPE_CGROUP_SKB:
+	case BPF_PROG_TYPE_CGROUP_SOCK:
+	case BPF_PROG_TYPE_SOCK_OPS:
+		break;
+	default:
+		return 0;
+	}
+
+	reg = cur_regs(env) + BPF_REG_0;
+	if (reg->type != SCALAR_VALUE) {
+		verbose(env, "At program exit the register R0 is not a known value (%s)\n",
+			reg_type_str[reg->type]);
+		return -EINVAL;
+	}
+
+	if (!tnum_in(range, reg->var_off)) {
+		verbose(env, "At program exit the register R0 ");
+		if (!tnum_is_unknown(reg->var_off)) {
+			char tn_buf[48];
+
+			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+			verbose(env, "has value %s", tn_buf);
+		} else {
+			verbose(env, "has unknown scalar value");
+		}
+		verbose(env, " should have been 0 or 1\n");
+		return -EINVAL;
+	}
 	return 0;
 }
 
@@ -3099,7 +3215,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 		return 0;
 
 	if (w < 0 || w >= env->prog->len) {
-		verbose("jump out of range from insn %d to %d\n", t, w);
+		verbose(env, "jump out of range from insn %d to %d\n", t, w);
 		return -EINVAL;
 	}
 
@@ -3116,13 +3232,13 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 		insn_stack[cur_stack++] = w;
 		return 1;
 	} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
-		verbose("back-edge from insn %d to %d\n", t, w);
+		verbose(env, "back-edge from insn %d to %d\n", t, w);
 		return -EINVAL;
 	} else if (insn_state[w] == EXPLORED) {
 		/* forward- or cross-edge */
 		insn_state[t] = DISCOVERED | e;
 	} else {
-		verbose("insn state internal bug\n");
+		verbose(env, "insn state internal bug\n");
 		return -EFAULT;
 	}
 	return 0;
@@ -3216,7 +3332,7 @@ peek_stack:
 mark_explored:
 	insn_state[t] = EXPLORED;
 	if (cur_stack-- <= 0) {
-		verbose("pop stack internal bug\n");
+		verbose(env, "pop stack internal bug\n");
 		ret = -EFAULT;
 		goto err_free;
 	}
@@ -3225,7 +3341,7 @@ mark_explored:
 check_state:
 	for (i = 0; i < insn_cnt; i++) {
 		if (insn_state[i] != EXPLORED) {
-			verbose("unreachable insn %d\n", i);
+			verbose(env, "unreachable insn %d\n", i);
 			ret = -EINVAL;
 			goto err_free;
 		}
@@ -3340,8 +3456,9 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
 			return false;
 		/* Check our ids match any regs they're supposed to */
 		return check_ids(rold->id, rcur->id, idmap);
+	case PTR_TO_PACKET_META:
 	case PTR_TO_PACKET:
-		if (rcur->type != PTR_TO_PACKET)
+		if (rcur->type != rold->type)
 			return false;
 		/* We must have at least as much range as the old ptr
 		 * did, so that any accesses which were safe before are
@@ -3379,6 +3496,57 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
 	return false;
 }
 
+static bool stacksafe(struct bpf_verifier_state *old,
+		      struct bpf_verifier_state *cur,
+		      struct idpair *idmap)
+{
+	int i, spi;
+
+	/* if explored stack has more populated slots than current stack
+	 * such stacks are not equivalent
+	 */
+	if (old->allocated_stack > cur->allocated_stack)
+		return false;
+
+	/* walk slots of the explored stack and ignore any additional
+	 * slots in the current stack, since explored(safe) state
+	 * didn't use them
+	 */
+	for (i = 0; i < old->allocated_stack; i++) {
+		spi = i / BPF_REG_SIZE;
+
+		if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
+			continue;
+		if (old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
+		    cur->stack[spi].slot_type[i % BPF_REG_SIZE])
+			/* Ex: old explored (safe) state has STACK_SPILL in
+			 * this stack slot, but current has has STACK_MISC ->
+			 * this verifier states are not equivalent,
+			 * return false to continue verification of this path
+			 */
+			return false;
+		if (i % BPF_REG_SIZE)
+			continue;
+		if (old->stack[spi].slot_type[0] != STACK_SPILL)
+			continue;
+		if (!regsafe(&old->stack[spi].spilled_ptr,
+			     &cur->stack[spi].spilled_ptr,
+			     idmap))
+			/* when explored and current stack slot are both storing
+			 * spilled registers, check that stored pointers types
+			 * are the same as well.
+			 * Ex: explored safe path could have stored
+			 * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8}
+			 * but current path has stored:
+			 * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16}
+			 * such verifier states are not equivalent.
+			 * return false to continue verification of this path
+			 */
+			return false;
+	}
+	return true;
+}
+
 /* compare two verifier states
  *
  * all states stored in state_list are known to be valid, since
@@ -3423,37 +3591,8 @@ static bool states_equal(struct bpf_verifier_env *env,
 			goto out_free;
 	}
 
-	for (i = 0; i < MAX_BPF_STACK; i++) {
-		if (old->stack_slot_type[i] == STACK_INVALID)
-			continue;
-		if (old->stack_slot_type[i] != cur->stack_slot_type[i])
-			/* Ex: old explored (safe) state has STACK_SPILL in
-			 * this stack slot, but current has has STACK_MISC ->
-			 * this verifier states are not equivalent,
-			 * return false to continue verification of this path
-			 */
-			goto out_free;
-		if (i % BPF_REG_SIZE)
-			continue;
-		if (old->stack_slot_type[i] != STACK_SPILL)
-			continue;
-		if (!regsafe(&old->spilled_regs[i / BPF_REG_SIZE],
-			     &cur->spilled_regs[i / BPF_REG_SIZE],
-			     idmap))
-			/* when explored and current stack slot are both storing
-			 * spilled registers, check that stored pointers types
-			 * are the same as well.
-			 * Ex: explored safe path could have stored
-			 * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8}
-			 * but current path has stored:
-			 * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16}
-			 * such verifier states are not equivalent.
-			 * return false to continue verification of this path
-			 */
-			goto out_free;
-		else
-			continue;
-	}
+	if (!stacksafe(old, cur, idmap))
+		goto out_free;
 	ret = true;
 out_free:
 	kfree(idmap);
@@ -3489,17 +3628,19 @@ static bool do_propagate_liveness(const struct bpf_verifier_state *state,
 		}
 	}
 	/* ... and stack slots */
-	for (i = 0; i < MAX_BPF_STACK / BPF_REG_SIZE; i++) {
-		if (parent->stack_slot_type[i * BPF_REG_SIZE] != STACK_SPILL)
+	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE &&
+		    i < parent->allocated_stack / BPF_REG_SIZE; i++) {
+		if (parent->stack[i].slot_type[0] != STACK_SPILL)
 			continue;
-		if (state->stack_slot_type[i * BPF_REG_SIZE] != STACK_SPILL)
+		if (state->stack[i].slot_type[0] != STACK_SPILL)
 			continue;
-		if (parent->spilled_regs[i].live & REG_LIVE_READ)
+		if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ)
 			continue;
-		if (writes && (state->spilled_regs[i].live & REG_LIVE_WRITTEN))
+		if (writes &&
+		    (state->stack[i].spilled_ptr.live & REG_LIVE_WRITTEN))
 			continue;
-		if (state->spilled_regs[i].live & REG_LIVE_READ) {
-			parent->spilled_regs[i].live |= REG_LIVE_READ;
+		if (state->stack[i].spilled_ptr.live & REG_LIVE_READ) {
+			parent->stack[i].spilled_ptr.live |= REG_LIVE_READ;
 			touched = true;
 		}
 	}
@@ -3529,7 +3670,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 {
 	struct bpf_verifier_state_list *new_sl;
 	struct bpf_verifier_state_list *sl;
-	int i;
+	struct bpf_verifier_state *cur = env->cur_state;
+	int i, err;
 
 	sl = env->explored_states[insn_idx];
 	if (!sl)
@@ -3539,7 +3681,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 		return 0;
 
 	while (sl != STATE_LIST_MARK) {
-		if (states_equal(env, &sl->state, &env->cur_state)) {
+		if (states_equal(env, &sl->state, cur)) {
 			/* reached equivalent register/stack state,
 			 * prune the search.
 			 * Registers read by the continuation are read by us.
@@ -3550,7 +3692,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 			 * they'll be immediately forgotten as we're pruning
 			 * this state and will pop a new one.
 			 */
-			propagate_liveness(&sl->state, &env->cur_state);
+			propagate_liveness(&sl->state, cur);
 			return 1;
 		}
 		sl = sl->next;
@@ -3562,16 +3704,21 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 	 * it will be rejected. Since there are no loops, we won't be
 	 * seeing this 'insn_idx' instruction again on the way to bpf_exit
 	 */
-	new_sl = kmalloc(sizeof(struct bpf_verifier_state_list), GFP_USER);
+	new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
 	if (!new_sl)
 		return -ENOMEM;
 
 	/* add new state to the head of linked list */
-	memcpy(&new_sl->state, &env->cur_state, sizeof(env->cur_state));
+	err = copy_verifier_state(&new_sl->state, cur);
+	if (err) {
+		free_verifier_state(&new_sl->state, false);
+		kfree(new_sl);
+		return err;
+	}
 	new_sl->next = env->explored_states[insn_idx];
 	env->explored_states[insn_idx] = new_sl;
 	/* connect new state to parentage chain */
-	env->cur_state.parent = &new_sl->state;
+	cur->parent = &new_sl->state;
 	/* clear write marks in current state: the writes we did are not writes
 	 * our child did, so they don't screen off its reads from us.
 	 * (There are no read marks in current state, because reads always mark
@@ -3579,10 +3726,10 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 	 * explored_states can get read marks.)
 	 */
 	for (i = 0; i < BPF_REG_FP; i++)
-		env->cur_state.regs[i].live = REG_LIVE_NONE;
-	for (i = 0; i < MAX_BPF_STACK / BPF_REG_SIZE; i++)
-		if (env->cur_state.stack_slot_type[i * BPF_REG_SIZE] == STACK_SPILL)
-			env->cur_state.spilled_regs[i].live = REG_LIVE_NONE;
+		cur->regs[i].live = REG_LIVE_NONE;
+	for (i = 0; i < cur->allocated_stack / BPF_REG_SIZE; i++)
+		if (cur->stack[i].slot_type[0] == STACK_SPILL)
+			cur->stack[i].spilled_ptr.live = REG_LIVE_NONE;
 	return 0;
 }
 
@@ -3597,15 +3744,19 @@ static int ext_analyzer_insn_hook(struct bpf_verifier_env *env,
 
 static int do_check(struct bpf_verifier_env *env)
 {
-	struct bpf_verifier_state *state = &env->cur_state;
+	struct bpf_verifier_state *state;
 	struct bpf_insn *insns = env->prog->insnsi;
-	struct bpf_reg_state *regs = state->regs;
+	struct bpf_reg_state *regs;
 	int insn_cnt = env->prog->len;
 	int insn_idx, prev_insn_idx = 0;
 	int insn_processed = 0;
 	bool do_print_state = false;
 
-	init_reg_state(regs);
+	state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+	env->cur_state = state;
+	init_reg_state(env, state->regs);
 	state->parent = NULL;
 	insn_idx = 0;
 	for (;;) {
@@ -3614,7 +3765,7 @@ static int do_check(struct bpf_verifier_env *env)
 		int err;
 
 		if (insn_idx >= insn_cnt) {
-			verbose("invalid insn idx %d insn_cnt %d\n",
+			verbose(env, "invalid insn idx %d insn_cnt %d\n",
 				insn_idx, insn_cnt);
 			return -EFAULT;
 		}
@@ -3623,7 +3774,8 @@ static int do_check(struct bpf_verifier_env *env)
 		class = BPF_CLASS(insn->code);
 
 		if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
-			verbose("BPF program is too large. Processed %d insn\n",
+			verbose(env,
+				"BPF program is too large. Processed %d insn\n",
 				insn_processed);
 			return -E2BIG;
 		}
@@ -3633,12 +3785,12 @@ static int do_check(struct bpf_verifier_env *env)
 			return err;
 		if (err == 1) {
 			/* found equivalent state, can prune the search */
-			if (log_level) {
+			if (env->log.level) {
 				if (do_print_state)
-					verbose("\nfrom %d to %d: safe\n",
+					verbose(env, "\nfrom %d to %d: safe\n",
 						prev_insn_idx, insn_idx);
 				else
-					verbose("%d: safe\n", insn_idx);
+					verbose(env, "%d: safe\n", insn_idx);
 			}
 			goto process_bpf_exit;
 		}
@@ -3646,25 +3798,27 @@ static int do_check(struct bpf_verifier_env *env)
 		if (need_resched())
 			cond_resched();
 
-		if (log_level > 1 || (log_level && do_print_state)) {
-			if (log_level > 1)
-				verbose("%d:", insn_idx);
+		if (env->log.level > 1 || (env->log.level && do_print_state)) {
+			if (env->log.level > 1)
+				verbose(env, "%d:", insn_idx);
 			else
-				verbose("\nfrom %d to %d:",
+				verbose(env, "\nfrom %d to %d:",
 					prev_insn_idx, insn_idx);
-			print_verifier_state(&env->cur_state);
+			print_verifier_state(env, state);
 			do_print_state = false;
 		}
 
-		if (log_level) {
-			verbose("%d: ", insn_idx);
-			print_bpf_insn(env, insn);
+		if (env->log.level) {
+			verbose(env, "%d: ", insn_idx);
+			print_bpf_insn(verbose, env, insn,
+				       env->allow_ptr_leaks);
 		}
 
 		err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx);
 		if (err)
 			return err;
 
+		regs = cur_regs(env);
 		if (class == BPF_ALU || class == BPF_ALU64) {
 			err = check_alu_op(env, insn);
 			if (err)
@@ -3714,7 +3868,7 @@ static int do_check(struct bpf_verifier_env *env)
 				 * src_reg == stack|map in some other branch.
 				 * Reject it.
 				 */
-				verbose("same insn cannot be used with different pointers\n");
+				verbose(env, "same insn cannot be used with different pointers\n");
 				return -EINVAL;
 			}
 
@@ -3754,14 +3908,14 @@ static int do_check(struct bpf_verifier_env *env)
 			} else if (dst_reg_type != *prev_dst_type &&
 				   (dst_reg_type == PTR_TO_CTX ||
 				    *prev_dst_type == PTR_TO_CTX)) {
-				verbose("same insn cannot be used with different pointers\n");
+				verbose(env, "same insn cannot be used with different pointers\n");
 				return -EINVAL;
 			}
 
 		} else if (class == BPF_ST) {
 			if (BPF_MODE(insn->code) != BPF_MEM ||
 			    insn->src_reg != BPF_REG_0) {
-				verbose("BPF_ST uses reserved fields\n");
+				verbose(env, "BPF_ST uses reserved fields\n");
 				return -EINVAL;
 			}
 			/* check src operand */
@@ -3784,7 +3938,7 @@ static int do_check(struct bpf_verifier_env *env)
 				    insn->off != 0 ||
 				    insn->src_reg != BPF_REG_0 ||
 				    insn->dst_reg != BPF_REG_0) {
-					verbose("BPF_CALL uses reserved fields\n");
+					verbose(env, "BPF_CALL uses reserved fields\n");
 					return -EINVAL;
 				}
 
@@ -3797,7 +3951,7 @@ static int do_check(struct bpf_verifier_env *env)
 				    insn->imm != 0 ||
 				    insn->src_reg != BPF_REG_0 ||
 				    insn->dst_reg != BPF_REG_0) {
-					verbose("BPF_JA uses reserved fields\n");
+					verbose(env, "BPF_JA uses reserved fields\n");
 					return -EINVAL;
 				}
 
@@ -3809,7 +3963,7 @@ static int do_check(struct bpf_verifier_env *env)
 				    insn->imm != 0 ||
 				    insn->src_reg != BPF_REG_0 ||
 				    insn->dst_reg != BPF_REG_0) {
-					verbose("BPF_EXIT uses reserved fields\n");
+					verbose(env, "BPF_EXIT uses reserved fields\n");
 					return -EINVAL;
 				}
 
@@ -3824,13 +3978,18 @@ static int do_check(struct bpf_verifier_env *env)
 					return err;
 
 				if (is_pointer_value(env, BPF_REG_0)) {
-					verbose("R0 leaks addr as return value\n");
+					verbose(env, "R0 leaks addr as return value\n");
 					return -EACCES;
 				}
 
+				err = check_return_code(env);
+				if (err)
+					return err;
 process_bpf_exit:
-				insn_idx = pop_stack(env, &prev_insn_idx);
-				if (insn_idx < 0) {
+				err = pop_stack(env, &prev_insn_idx, &insn_idx);
+				if (err < 0) {
+					if (err != -ENOENT)
+						return err;
 					break;
 				} else {
 					do_print_state = true;
@@ -3856,19 +4015,19 @@ process_bpf_exit:
 
 				insn_idx++;
 			} else {
-				verbose("invalid BPF_LD mode\n");
+				verbose(env, "invalid BPF_LD mode\n");
 				return -EINVAL;
 			}
 		} else {
-			verbose("unknown insn class %d\n", class);
+			verbose(env, "unknown insn class %d\n", class);
 			return -EINVAL;
 		}
 
 		insn_idx++;
 	}
 
-	verbose("processed %d insns, stack depth %d\n",
-		insn_processed, env->prog->aux->stack_depth);
+	verbose(env, "processed %d insns, stack depth %d\n", insn_processed,
+		env->prog->aux->stack_depth);
 	return 0;
 }
 
@@ -3880,7 +4039,8 @@ static int check_map_prealloc(struct bpf_map *map)
 		!(map->map_flags & BPF_F_NO_PREALLOC);
 }
 
-static int check_map_prog_compatibility(struct bpf_map *map,
+static int check_map_prog_compatibility(struct bpf_verifier_env *env,
+					struct bpf_map *map,
 					struct bpf_prog *prog)
 
 {
@@ -3891,12 +4051,12 @@ static int check_map_prog_compatibility(struct bpf_map *map,
 	 */
 	if (prog->type == BPF_PROG_TYPE_PERF_EVENT) {
 		if (!check_map_prealloc(map)) {
-			verbose("perf_event programs can only use preallocated hash map\n");
+			verbose(env, "perf_event programs can only use preallocated hash map\n");
 			return -EINVAL;
 		}
 		if (map->inner_map_meta &&
 		    !check_map_prealloc(map->inner_map_meta)) {
-			verbose("perf_event programs can only use preallocated inner hash map\n");
+			verbose(env, "perf_event programs can only use preallocated inner hash map\n");
 			return -EINVAL;
 		}
 	}
@@ -3919,14 +4079,14 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		if (BPF_CLASS(insn->code) == BPF_LDX &&
 		    (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
-			verbose("BPF_LDX uses reserved fields\n");
+			verbose(env, "BPF_LDX uses reserved fields\n");
 			return -EINVAL;
 		}
 
 		if (BPF_CLASS(insn->code) == BPF_STX &&
 		    ((BPF_MODE(insn->code) != BPF_MEM &&
 		      BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) {
-			verbose("BPF_STX uses reserved fields\n");
+			verbose(env, "BPF_STX uses reserved fields\n");
 			return -EINVAL;
 		}
 
@@ -3937,7 +4097,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 			if (i == insn_cnt - 1 || insn[1].code != 0 ||
 			    insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
 			    insn[1].off != 0) {
-				verbose("invalid bpf_ld_imm64 insn\n");
+				verbose(env, "invalid bpf_ld_imm64 insn\n");
 				return -EINVAL;
 			}
 
@@ -3946,19 +4106,20 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 				goto next_insn;
 
 			if (insn->src_reg != BPF_PSEUDO_MAP_FD) {
-				verbose("unrecognized bpf_ld_imm64 insn\n");
+				verbose(env,
+					"unrecognized bpf_ld_imm64 insn\n");
 				return -EINVAL;
 			}
 
 			f = fdget(insn->imm);
 			map = __bpf_map_get(f);
 			if (IS_ERR(map)) {
-				verbose("fd %d is not pointing to valid bpf_map\n",
+				verbose(env, "fd %d is not pointing to valid bpf_map\n",
 					insn->imm);
 				return PTR_ERR(map);
 			}
 
-			err = check_map_prog_compatibility(map, env->prog);
+			err = check_map_prog_compatibility(env, map, env->prog);
 			if (err) {
 				fdput(f);
 				return err;
@@ -4067,7 +4228,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
  */
 static int convert_ctx_accesses(struct bpf_verifier_env *env)
 {
-	const struct bpf_verifier_ops *ops = env->prog->aux->ops;
+	const struct bpf_verifier_ops *ops = env->ops;
 	int i, cnt, size, ctx_field_size, delta = 0;
 	const int insn_cnt = env->prog->len;
 	struct bpf_insn insn_buf[16], *insn;
@@ -4080,7 +4241,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
 					env->prog);
 		if (cnt >= ARRAY_SIZE(insn_buf)) {
-			verbose("bpf verifier is misconfigured\n");
+			verbose(env, "bpf verifier is misconfigured\n");
 			return -EINVAL;
 		} else if (cnt) {
 			new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt);
@@ -4128,7 +4289,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 			u8 size_code;
 
 			if (type == BPF_WRITE) {
-				verbose("bpf verifier narrow ctx access misconfigured\n");
+				verbose(env, "bpf verifier narrow ctx access misconfigured\n");
 				return -EINVAL;
 			}
 
@@ -4147,7 +4308,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 					      &target_size);
 		if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) ||
 		    (ctx_field_size && !target_size)) {
-			verbose("bpf verifier is misconfigured\n");
+			verbose(env, "bpf verifier is misconfigured\n");
 			return -EINVAL;
 		}
 
@@ -4229,7 +4390,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 
 			cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf);
 			if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
-				verbose("bpf verifier is misconfigured\n");
+				verbose(env, "bpf verifier is misconfigured\n");
 				return -EINVAL;
 			}
 
@@ -4268,12 +4429,13 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			insn      = new_prog->insnsi + i + delta;
 		}
 patch_call_imm:
-		fn = prog->aux->ops->get_func_proto(insn->imm);
+		fn = env->ops->get_func_proto(insn->imm);
 		/* all functions that have prototype and verifier allowed
 		 * programs to call them, must be real in-kernel functions
 		 */
 		if (!fn->func) {
-			verbose("kernel subsystem misconfigured func %s#%d\n",
+			verbose(env,
+				"kernel subsystem misconfigured func %s#%d\n",
 				func_id_name(insn->imm), insn->imm);
 			return -EFAULT;
 		}
@@ -4297,6 +4459,7 @@ static void free_states(struct bpf_verifier_env *env)
 		if (sl)
 			while (sl != STATE_LIST_MARK) {
 				sln = sl->next;
+				free_verifier_state(&sl->state, false);
 				kfree(sl);
 				sl = sln;
 			}
@@ -4307,16 +4470,21 @@ static void free_states(struct bpf_verifier_env *env)
 
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 {
-	char __user *log_ubuf = NULL;
 	struct bpf_verifier_env *env;
+	struct bpf_verifer_log *log;
 	int ret = -EINVAL;
 
+	/* no program is valid */
+	if (ARRAY_SIZE(bpf_verifier_ops) == 0)
+		return -EINVAL;
+
 	/* 'struct bpf_verifier_env' can be global, but since it's not small,
 	 * allocate/free it every time bpf_check() is called
 	 */
 	env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
 	if (!env)
 		return -ENOMEM;
+	log = &env->log;
 
 	env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) *
 				     (*prog)->len);
@@ -4324,6 +4492,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 	if (!env->insn_aux_data)
 		goto err_free_env;
 	env->prog = *prog;
+	env->ops = bpf_verifier_ops[env->prog->type];
 
 	/* grab the mutex to protect few globals used by verifier */
 	mutex_lock(&bpf_verifier_lock);
@@ -4332,23 +4501,15 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 		/* user requested verbose verifier output
 		 * and supplied buffer to store the verification trace
 		 */
-		log_level = attr->log_level;
-		log_ubuf = (char __user *) (unsigned long) attr->log_buf;
-		log_size = attr->log_size;
-		log_len = 0;
+		log->level = attr->log_level;
+		log->ubuf = (char __user *) (unsigned long) attr->log_buf;
+		log->len_total = attr->log_size;
 
 		ret = -EINVAL;
-		/* log_* values have to be sane */
-		if (log_size < 128 || log_size > UINT_MAX >> 8 ||
-		    log_level == 0 || log_ubuf == NULL)
+		/* log attributes have to be sane */
+		if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
+		    !log->level || !log->ubuf)
 			goto err_unlock;
-
-		ret = -ENOMEM;
-		log_buf = vmalloc(log_size);
-		if (!log_buf)
-			goto err_unlock;
-	} else {
-		log_level = 0;
 	}
 
 	env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
@@ -4373,9 +4534,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 	env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
 
 	ret = do_check(env);
+	if (env->cur_state) {
+		free_verifier_state(env->cur_state, true);
+		env->cur_state = NULL;
+	}
 
 skip_full_check:
-	while (pop_stack(env, NULL) >= 0);
+	while (!pop_stack(env, NULL, NULL));
 	free_states(env);
 
 	if (ret == 0)
@@ -4385,17 +4550,11 @@ skip_full_check:
 	if (ret == 0)
 		ret = fixup_bpf_calls(env);
 
-	if (log_level && log_len >= log_size - 1) {
-		BUG_ON(log_len >= log_size);
-		/* verifier log exceeded user supplied buffer */
+	if (log->level && bpf_verifier_log_full(log))
 		ret = -ENOSPC;
-		/* fall through to return what was recorded */
-	}
-
-	/* copy verifier log back to user space including trailing zero */
-	if (log_level && copy_to_user(log_ubuf, log_buf, log_len + 1) != 0) {
+	if (log->level && !log->ubuf) {
 		ret = -EFAULT;
-		goto free_log_buf;
+		goto err_release_maps;
 	}
 
 	if (ret == 0 && env->used_map_cnt) {
@@ -4406,7 +4565,7 @@ skip_full_check:
 
 		if (!env->prog->aux->used_maps) {
 			ret = -ENOMEM;
-			goto free_log_buf;
+			goto err_release_maps;
 		}
 
 		memcpy(env->prog->aux->used_maps, env->used_maps,
@@ -4419,9 +4578,7 @@ skip_full_check:
 		convert_pseudo_ld_imm64(env);
 	}
 
-free_log_buf:
-	if (log_level)
-		vfree(log_buf);
+err_release_maps:
 	if (!env->prog->aux->used_maps)
 		/* if we didn't copy map pointers into bpf_prog_info, release
 		 * them now. Otherwise free_bpf_prog_info() will release them.
@@ -4436,12 +4593,23 @@ err_free_env:
 	return ret;
 }
 
+static const struct bpf_verifier_ops * const bpf_analyzer_ops[] = {
+#ifdef CONFIG_NET
+	[BPF_PROG_TYPE_XDP]		= &xdp_analyzer_ops,
+	[BPF_PROG_TYPE_SCHED_CLS]	= &tc_cls_act_analyzer_ops,
+#endif
+};
+
 int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
 		 void *priv)
 {
 	struct bpf_verifier_env *env;
 	int ret;
 
+	if (prog->type >= ARRAY_SIZE(bpf_analyzer_ops) ||
+	    !bpf_analyzer_ops[prog->type])
+		return -EOPNOTSUPP;
+
 	env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
 	if (!env)
 		return -ENOMEM;
@@ -4452,14 +4620,13 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
 	if (!env->insn_aux_data)
 		goto err_free_env;
 	env->prog = prog;
+	env->ops = bpf_analyzer_ops[env->prog->type];
 	env->analyzer_ops = ops;
 	env->analyzer_priv = priv;
 
 	/* grab the mutex to protect few globals used by verifier */
 	mutex_lock(&bpf_verifier_lock);
 
-	log_level = 0;
-
 	env->strict_alignment = false;
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
 		env->strict_alignment = true;
@@ -4478,9 +4645,13 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
 	env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
 
 	ret = do_check(env);
+	if (env->cur_state) {
+		free_verifier_state(env->cur_state, true);
+		env->cur_state = NULL;
+	}
 
 skip_full_check:
-	while (pop_stack(env, NULL) >= 0);
+	while (!pop_stack(env, NULL, NULL));
 	free_states(env);
 
 	mutex_unlock(&bpf_verifier_lock);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 44857278eb8a..00f5b358aeac 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1896,6 +1896,9 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
 	if (ret)
 		goto destroy_root;
 
+	ret = cgroup_bpf_inherit(root_cgrp);
+	WARN_ON_ONCE(ret);
+
 	trace_cgroup_setup_root(root);
 
 	/*
@@ -4721,6 +4724,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 	cgrp->self.parent = &parent->self;
 	cgrp->root = root;
 	cgrp->level = level;
+	ret = cgroup_bpf_inherit(cgrp);
+	if (ret)
+		goto out_idr_free;
 
 	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
 		cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;
@@ -4755,13 +4761,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 	if (!cgroup_on_dfl(cgrp))
 		cgrp->subtree_control = cgroup_control(cgrp);
 
-	if (parent)
-		cgroup_bpf_inherit(cgrp, parent);
-
 	cgroup_propagate_control(cgrp);
 
 	return cgrp;
 
+out_idr_free:
+	cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
 out_cancel_ref:
 	percpu_ref_exit(&cgrp->self.refcnt);
 out_free_cgrp:
@@ -5744,14 +5749,33 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd)
 #endif	/* CONFIG_SOCK_CGROUP_DATA */
 
 #ifdef CONFIG_CGROUP_BPF
-int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
-		      enum bpf_attach_type type, bool overridable)
+int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, u32 flags)
+{
+	int ret;
+
+	mutex_lock(&cgroup_mutex);
+	ret = __cgroup_bpf_attach(cgrp, prog, type, flags);
+	mutex_unlock(&cgroup_mutex);
+	return ret;
+}
+int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, u32 flags)
+{
+	int ret;
+
+	mutex_lock(&cgroup_mutex);
+	ret = __cgroup_bpf_detach(cgrp, prog, type, flags);
+	mutex_unlock(&cgroup_mutex);
+	return ret;
+}
+int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+		     union bpf_attr __user *uattr)
 {
-	struct cgroup *parent = cgroup_parent(cgrp);
 	int ret;
 
 	mutex_lock(&cgroup_mutex);
-	ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable);
+	ret = __cgroup_bpf_query(cgrp, attr, uattr);
 	mutex_unlock(&cgroup_mutex);
 	return ret;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9d93db81fa36..9660ee65fbef 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3684,10 +3684,12 @@ static inline u64 perf_event_count(struct perf_event *event)
  *     will not be local and we cannot read them atomically
  *   - must not have a pmu::count method
  */
-int perf_event_read_local(struct perf_event *event, u64 *value)
+int perf_event_read_local(struct perf_event *event, u64 *value,
+			  u64 *enabled, u64 *running)
 {
 	unsigned long flags;
 	int ret = 0;
+	u64 now;
 
 	/*
 	 * Disabling interrupts avoids all counter scheduling (context
@@ -3718,13 +3720,21 @@ int perf_event_read_local(struct perf_event *event, u64 *value)
 		goto out;
 	}
 
+	now = event->shadow_ctx_time + perf_clock();
+	if (enabled)
+		*enabled = now - event->tstamp_enabled;
 	/*
 	 * If the event is currently on this CPU, its either a per-task event,
 	 * or local to this CPU. Furthermore it means its ACTIVE (otherwise
 	 * oncpu == -1).
 	 */
-	if (event->oncpu == smp_processor_id())
+	if (event->oncpu == smp_processor_id()) {
 		event->pmu->read(event);
+		if (running)
+			*running = now - event->tstamp_running;
+	} else if (running) {
+		*running = event->total_time_running;
+	}
 
 	*value = local64_read(&event->count);
 out:
@@ -7944,11 +7954,9 @@ void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx,
 			       struct pt_regs *regs, struct hlist_head *head,
 			       struct task_struct *task)
 {
-	struct bpf_prog *prog = call->prog;
-
-	if (prog) {
+	if (bpf_prog_array_valid(call)) {
 		*(struct pt_regs **)raw_data = regs;
-		if (!trace_call_bpf(prog, raw_data) || hlist_empty(head)) {
+		if (!trace_call_bpf(call, raw_data) || hlist_empty(head)) {
 			perf_swevent_put_recursion_context(rctx);
 			return;
 		}
@@ -8072,6 +8080,7 @@ static void bpf_overflow_handler(struct perf_event *event,
 	struct bpf_perf_event_data_kern ctx = {
 		.data = data,
 		.regs = regs,
+		.event = event,
 	};
 	int ret = 0;
 
@@ -8136,13 +8145,11 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
 {
 	bool is_kprobe, is_tracepoint, is_syscall_tp;
 	struct bpf_prog *prog;
+	int ret;
 
 	if (event->attr.type != PERF_TYPE_TRACEPOINT)
 		return perf_event_set_bpf_handler(event, prog_fd);
 
-	if (event->tp_event->prog)
-		return -EEXIST;
-
 	is_kprobe = event->tp_event->flags & TRACE_EVENT_FL_UKPROBE;
 	is_tracepoint = event->tp_event->flags & TRACE_EVENT_FL_TRACEPOINT;
 	is_syscall_tp = is_syscall_trace_event(event->tp_event);
@@ -8170,26 +8177,20 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
 			return -EACCES;
 		}
 	}
-	event->tp_event->prog = prog;
-	event->tp_event->bpf_prog_owner = event;
 
-	return 0;
+	ret = perf_event_attach_bpf_prog(event, prog);
+	if (ret)
+		bpf_prog_put(prog);
+	return ret;
 }
 
 static void perf_event_free_bpf_prog(struct perf_event *event)
 {
-	struct bpf_prog *prog;
-
-	perf_event_free_bpf_handler(event);
-
-	if (!event->tp_event)
+	if (event->attr.type != PERF_TYPE_TRACEPOINT) {
+		perf_event_free_bpf_handler(event);
 		return;
-
-	prog = event->tp_event->prog;
-	if (prog && event->tp_event->bpf_prog_owner == event) {
-		event->tp_event->prog = NULL;
-		bpf_prog_put(prog);
 	}
+	perf_event_detach_bpf_prog(event);
 }
 
 #else
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index dc498b605d5d..506efe6e8ed9 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -15,9 +15,11 @@
 #include <linux/ctype.h>
 #include "trace.h"
 
+u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+
 /**
  * trace_call_bpf - invoke BPF program
- * @prog: BPF program
+ * @call: tracepoint event
  * @ctx: opaque context pointer
  *
  * kprobe handlers execute BPF programs via this helper.
@@ -29,7 +31,7 @@
  * 1 - store kprobe event into ring buffer
  * Other values are reserved and currently alias to 1
  */
-unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
+unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 {
 	unsigned int ret;
 
@@ -49,9 +51,22 @@ unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
 		goto out;
 	}
 
-	rcu_read_lock();
-	ret = BPF_PROG_RUN(prog, ctx);
-	rcu_read_unlock();
+	/*
+	 * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock
+	 * to all call sites, we did a bpf_prog_array_valid() there to check
+	 * whether call->prog_array is empty or not, which is
+	 * a heurisitc to speed up execution.
+	 *
+	 * If bpf_prog_array_valid() fetched prog_array was
+	 * non-NULL, we go into trace_call_bpf() and do the actual
+	 * proper rcu_dereference() under RCU lock.
+	 * If it turns out that prog_array is NULL then, we bail out.
+	 * For the opposite, if the bpf_prog_array_valid() fetched pointer
+	 * was NULL, you'll skip the prog_array with the risk of missing
+	 * out of events when it was updated in between this and the
+	 * rcu_dereference() which is accepted risk.
+	 */
+	ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, BPF_PROG_RUN);
 
  out:
 	__this_cpu_dec(bpf_prog_active);
@@ -255,14 +270,14 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 	return &bpf_trace_printk_proto;
 }
 
-BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
+static __always_inline int
+get_map_perf_counter(struct bpf_map *map, u64 flags,
+		     u64 *value, u64 *enabled, u64 *running)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	unsigned int cpu = smp_processor_id();
 	u64 index = flags & BPF_F_INDEX_MASK;
 	struct bpf_event_entry *ee;
-	u64 value = 0;
-	int err;
 
 	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
 		return -EINVAL;
@@ -275,7 +290,15 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
 	if (!ee)
 		return -ENOENT;
 
-	err = perf_event_read_local(ee->event, &value);
+	return perf_event_read_local(ee->event, value, enabled, running);
+}
+
+BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
+{
+	u64 value = 0;
+	int err;
+
+	err = get_map_perf_counter(map, flags, &value, NULL, NULL);
 	/*
 	 * this api is ugly since we miss [-22..-2] range of valid
 	 * counter values, but that's uapi
@@ -293,6 +316,33 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags,
+	   struct bpf_perf_event_value *, buf, u32, size)
+{
+	int err = -EINVAL;
+
+	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
+		goto clear;
+	err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled,
+				   &buf->running);
+	if (unlikely(err))
+		goto clear;
+	return 0;
+clear:
+	memset(buf, 0, size);
+	return err;
+}
+
+static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
+	.func		= bpf_perf_event_read_value,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
 static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd);
 
 static __always_inline u64
@@ -499,6 +549,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 		return &bpf_perf_event_output_proto;
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto;
+	case BPF_FUNC_perf_event_read_value:
+		return &bpf_perf_event_read_value_proto;
 	default:
 		return tracing_func_proto(func_id);
 	}
@@ -524,11 +576,14 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type
 	return true;
 }
 
-const struct bpf_verifier_ops kprobe_prog_ops = {
+const struct bpf_verifier_ops kprobe_verifier_ops = {
 	.get_func_proto  = kprobe_prog_func_proto,
 	.is_valid_access = kprobe_prog_is_valid_access,
 };
 
+const struct bpf_prog_ops kprobe_prog_ops = {
+};
+
 BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map,
 	   u64, flags, void *, data, u64, size)
 {
@@ -576,6 +631,32 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx,
+	   struct bpf_perf_event_value *, buf, u32, size)
+{
+	int err = -EINVAL;
+
+	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
+		goto clear;
+	err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled,
+				    &buf->running);
+	if (unlikely(err))
+		goto clear;
+	return 0;
+clear:
+	memset(buf, 0, size);
+	return err;
+}
+
+static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = {
+         .func           = bpf_perf_prog_read_value_tp,
+         .gpl_only       = true,
+         .ret_type       = RET_INTEGER,
+         .arg1_type      = ARG_PTR_TO_CTX,
+         .arg2_type      = ARG_PTR_TO_UNINIT_MEM,
+         .arg3_type      = ARG_CONST_SIZE,
+};
+
 static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -583,6 +664,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 		return &bpf_perf_event_output_proto_tp;
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto_tp;
+	case BPF_FUNC_perf_prog_read_value:
+		return &bpf_perf_prog_read_value_proto_tp;
 	default:
 		return tracing_func_proto(func_id);
 	}
@@ -602,11 +685,14 @@ static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type
 	return true;
 }
 
-const struct bpf_verifier_ops tracepoint_prog_ops = {
+const struct bpf_verifier_ops tracepoint_verifier_ops = {
 	.get_func_proto  = tp_prog_func_proto,
 	.is_valid_access = tp_prog_is_valid_access,
 };
 
+const struct bpf_prog_ops tracepoint_prog_ops = {
+};
+
 static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 				    struct bpf_insn_access_aux *info)
 {
@@ -662,8 +748,67 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
 	return insn - insn_buf;
 }
 
-const struct bpf_verifier_ops perf_event_prog_ops = {
+const struct bpf_verifier_ops perf_event_verifier_ops = {
 	.get_func_proto		= tp_prog_func_proto,
 	.is_valid_access	= pe_prog_is_valid_access,
 	.convert_ctx_access	= pe_prog_convert_ctx_access,
 };
+
+const struct bpf_prog_ops perf_event_prog_ops = {
+};
+
+static DEFINE_MUTEX(bpf_event_mutex);
+
+int perf_event_attach_bpf_prog(struct perf_event *event,
+			       struct bpf_prog *prog)
+{
+	struct bpf_prog_array __rcu *old_array;
+	struct bpf_prog_array *new_array;
+	int ret = -EEXIST;
+
+	mutex_lock(&bpf_event_mutex);
+
+	if (event->prog)
+		goto unlock;
+
+	old_array = event->tp_event->prog_array;
+	ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array);
+	if (ret < 0)
+		goto unlock;
+
+	/* set the new array to event->tp_event and set event->prog */
+	event->prog = prog;
+	rcu_assign_pointer(event->tp_event->prog_array, new_array);
+	bpf_prog_array_free(old_array);
+
+unlock:
+	mutex_unlock(&bpf_event_mutex);
+	return ret;
+}
+
+void perf_event_detach_bpf_prog(struct perf_event *event)
+{
+	struct bpf_prog_array __rcu *old_array;
+	struct bpf_prog_array *new_array;
+	int ret;
+
+	mutex_lock(&bpf_event_mutex);
+
+	if (!event->prog)
+		goto unlock;
+
+	old_array = event->tp_event->prog_array;
+	ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array);
+	if (ret < 0) {
+		bpf_prog_array_delete_safe(old_array, event->prog);
+	} else {
+		rcu_assign_pointer(event->tp_event->prog_array, new_array);
+		bpf_prog_array_free(old_array);
+	}
+
+	bpf_prog_put(event->prog);
+	event->prog = NULL;
+
+unlock:
+	mutex_unlock(&bpf_event_mutex);
+}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 8a907e12b6b9..abf92e478cfb 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1174,13 +1174,12 @@ static void
 kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 {
 	struct trace_event_call *call = &tk->tp.call;
-	struct bpf_prog *prog = call->prog;
 	struct kprobe_trace_entry_head *entry;
 	struct hlist_head *head;
 	int size, __size, dsize;
 	int rctx;
 
-	if (prog && !trace_call_bpf(prog, regs))
+	if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
 		return;
 
 	head = this_cpu_ptr(call->perf_events);
@@ -1210,13 +1209,12 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 		    struct pt_regs *regs)
 {
 	struct trace_event_call *call = &tk->tp.call;
-	struct bpf_prog *prog = call->prog;
 	struct kretprobe_trace_entry_head *entry;
 	struct hlist_head *head;
 	int size, __size, dsize;
 	int rctx;
 
-	if (prog && !trace_call_bpf(prog, regs))
+	if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
 		return;
 
 	head = this_cpu_ptr(call->perf_events);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index a2a642f2c64f..19bcaaac884b 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -560,9 +560,10 @@ static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
 static int sys_perf_refcount_enter;
 static int sys_perf_refcount_exit;
 
-static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs,
-			      struct syscall_metadata *sys_data,
-			      struct syscall_trace_enter *rec) {
+static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *regs,
+			       struct syscall_metadata *sys_data,
+			       struct syscall_trace_enter *rec)
+{
 	struct syscall_tp_t {
 		unsigned long long regs;
 		unsigned long syscall_nr;
@@ -574,7 +575,7 @@ static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs,
 	param.syscall_nr = rec->nr;
 	for (i = 0; i < sys_data->nb_args; i++)
 		param.args[i] = rec->args[i];
-	return trace_call_bpf(prog, &param);
+	return trace_call_bpf(call, &param);
 }
 
 static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
@@ -582,7 +583,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_enter *rec;
 	struct hlist_head *head;
-	struct bpf_prog *prog;
+	bool valid_prog_array;
 	int syscall_nr;
 	int rctx;
 	int size;
@@ -597,9 +598,9 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	if (!sys_data)
 		return;
 
-	prog = READ_ONCE(sys_data->enter_event->prog);
 	head = this_cpu_ptr(sys_data->enter_event->perf_events);
-	if (!prog && hlist_empty(head))
+	valid_prog_array = bpf_prog_array_valid(sys_data->enter_event);
+	if (!valid_prog_array && hlist_empty(head))
 		return;
 
 	/* get the size after alignment with the u32 buffer size field */
@@ -615,7 +616,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
 			       (unsigned long *)&rec->args);
 
-	if ((prog && !perf_call_bpf_enter(prog, regs, sys_data, rec)) ||
+	if ((valid_prog_array &&
+	     !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||
 	    hlist_empty(head)) {
 		perf_swevent_put_recursion_context(rctx);
 		return;
@@ -660,8 +662,9 @@ static void perf_sysenter_disable(struct trace_event_call *call)
 	mutex_unlock(&syscall_trace_lock);
 }
 
-static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs,
-			      struct syscall_trace_exit *rec) {
+static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *regs,
+			      struct syscall_trace_exit *rec)
+{
 	struct syscall_tp_t {
 		unsigned long long regs;
 		unsigned long syscall_nr;
@@ -671,7 +674,7 @@ static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs,
 	*(struct pt_regs **)&param = regs;
 	param.syscall_nr = rec->nr;
 	param.ret = rec->ret;
-	return trace_call_bpf(prog, &param);
+	return trace_call_bpf(call, &param);
 }
 
 static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
@@ -679,7 +682,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_exit *rec;
 	struct hlist_head *head;
-	struct bpf_prog *prog;
+	bool valid_prog_array;
 	int syscall_nr;
 	int rctx;
 	int size;
@@ -694,9 +697,9 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	if (!sys_data)
 		return;
 
-	prog = READ_ONCE(sys_data->exit_event->prog);
 	head = this_cpu_ptr(sys_data->exit_event->perf_events);
-	if (!prog && hlist_empty(head))
+	valid_prog_array = bpf_prog_array_valid(sys_data->exit_event);
+	if (!valid_prog_array && hlist_empty(head))
 		return;
 
 	/* We can probably do that at build time */
@@ -710,7 +713,8 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
 
-	if ((prog && !perf_call_bpf_exit(prog, regs, rec)) ||
+	if ((valid_prog_array &&
+	     !perf_call_bpf_exit(sys_data->exit_event, regs, rec)) ||
 	    hlist_empty(head)) {
 		perf_swevent_put_recursion_context(rctx);
 		return;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 4525e0271a53..153c0e411461 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1113,13 +1113,12 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 {
 	struct trace_event_call *call = &tu->tp.call;
 	struct uprobe_trace_entry_head *entry;
-	struct bpf_prog *prog = call->prog;
 	struct hlist_head *head;
 	void *data;
 	int size, esize;
 	int rctx;
 
-	if (prog && !trace_call_bpf(prog, regs))
+	if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
 		return;
 
 	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c
index 6a406fafb5d6..8dbfdf6445f8 100644
--- a/lib/dynamic_queue_limits.c
+++ b/lib/dynamic_queue_limits.c
@@ -128,12 +128,11 @@ void dql_reset(struct dql *dql)
 }
 EXPORT_SYMBOL(dql_reset);
 
-int dql_init(struct dql *dql, unsigned hold_time)
+void dql_init(struct dql *dql, unsigned int hold_time)
 {
 	dql->max_limit = DQL_MAX_LIMIT;
 	dql->min_limit = 0;
 	dql->slack_hold_time = hold_time;
 	dql_reset(dql);
-	return 0;
 }
 EXPORT_SYMBOL(dql_init);
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index f237a09a5862..c3e84edc47c9 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -294,6 +294,55 @@ static void cleanup_uevent_env(struct subprocess_info *info)
 }
 #endif
 
+static int kobject_uevent_net_broadcast(struct kobject *kobj,
+					struct kobj_uevent_env *env,
+					const char *action_string,
+					const char *devpath)
+{
+	int retval = 0;
+#if defined(CONFIG_NET)
+	struct sk_buff *skb = NULL;
+	struct uevent_sock *ue_sk;
+
+	/* send netlink message */
+	list_for_each_entry(ue_sk, &uevent_sock_list, list) {
+		struct sock *uevent_sock = ue_sk->sk;
+
+		if (!netlink_has_listeners(uevent_sock, 1))
+			continue;
+
+		if (!skb) {
+			/* allocate message with the maximum possible size */
+			size_t len = strlen(action_string) + strlen(devpath) + 2;
+			char *scratch;
+
+			retval = -ENOMEM;
+			skb = alloc_skb(len + env->buflen, GFP_KERNEL);
+			if (!skb)
+				continue;
+
+			/* add header */
+			scratch = skb_put(skb, len);
+			sprintf(scratch, "%s@%s", action_string, devpath);
+
+			skb_put_data(skb, env->buf, env->buflen);
+
+			NETLINK_CB(skb).dst_group = 1;
+		}
+
+		retval = netlink_broadcast_filtered(uevent_sock, skb_get(skb),
+						    0, 1, GFP_KERNEL,
+						    kobj_bcast_filter,
+						    kobj);
+		/* ENOBUFS should be handled in userspace */
+		if (retval == -ENOBUFS || retval == -ESRCH)
+			retval = 0;
+	}
+	consume_skb(skb);
+#endif
+	return retval;
+}
+
 static void zap_modalias_env(struct kobj_uevent_env *env)
 {
 	static const char modalias_prefix[] = "MODALIAS=";
@@ -336,9 +385,6 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 	const struct kset_uevent_ops *uevent_ops;
 	int i = 0;
 	int retval = 0;
-#ifdef CONFIG_NET
-	struct uevent_sock *ue_sk;
-#endif
 
 	pr_debug("kobject: '%s' (%p): %s\n",
 		 kobject_name(kobj), kobj, __func__);
@@ -460,46 +506,8 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 		mutex_unlock(&uevent_sock_mutex);
 		goto exit;
 	}
-
-#if defined(CONFIG_NET)
-	/* send netlink message */
-	list_for_each_entry(ue_sk, &uevent_sock_list, list) {
-		struct sock *uevent_sock = ue_sk->sk;
-		struct sk_buff *skb;
-		size_t len;
-
-		if (!netlink_has_listeners(uevent_sock, 1))
-			continue;
-
-		/* allocate message with the maximum possible size */
-		len = strlen(action_string) + strlen(devpath) + 2;
-		skb = alloc_skb(len + env->buflen, GFP_KERNEL);
-		if (skb) {
-			char *scratch;
-
-			/* add header */
-			scratch = skb_put(skb, len);
-			sprintf(scratch, "%s@%s", action_string, devpath);
-
-			/* copy keys to our continuous event payload buffer */
-			for (i = 0; i < env->envp_idx; i++) {
-				len = strlen(env->envp[i]) + 1;
-				scratch = skb_put(skb, len);
-				strcpy(scratch, env->envp[i]);
-			}
-
-			NETLINK_CB(skb).dst_group = 1;
-			retval = netlink_broadcast_filtered(uevent_sock, skb,
-							    0, 1, GFP_KERNEL,
-							    kobj_bcast_filter,
-							    kobj);
-			/* ENOBUFS should be handled in userspace */
-			if (retval == -ENOBUFS || retval == -ESRCH)
-				retval = 0;
-		} else
-			retval = -ENOMEM;
-	}
-#endif
+	retval = kobject_uevent_net_broadcast(kobj, env, action_string,
+					      devpath);
 	mutex_unlock(&uevent_sock_mutex);
 
 #ifdef CONFIG_UEVENT_HELPER
diff --git a/lib/once.c b/lib/once.c
index bfb7420d0de3..8b7d6235217e 100644
--- a/lib/once.c
+++ b/lib/once.c
@@ -6,7 +6,7 @@
 
 struct once_work {
 	struct work_struct work;
-	struct static_key *key;
+	struct static_key_true *key;
 };
 
 static void once_deferred(struct work_struct *w)
@@ -15,11 +15,11 @@ static void once_deferred(struct work_struct *w)
 
 	work = container_of(w, struct once_work, work);
 	BUG_ON(!static_key_enabled(work->key));
-	static_key_slow_dec(work->key);
+	static_branch_disable(work->key);
 	kfree(work);
 }
 
-static void once_disable_jump(struct static_key *key)
+static void once_disable_jump(struct static_key_true *key)
 {
 	struct once_work *w;
 
@@ -52,7 +52,7 @@ bool __do_once_start(bool *done, unsigned long *flags)
 }
 EXPORT_SYMBOL(__do_once_start);
 
-void __do_once_done(bool *done, struct static_key *once_key,
+void __do_once_done(bool *done, struct static_key_true *once_key,
 		    unsigned long *flags)
 	__releases(once_lock)
 {
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 0ffca990a833..8e83cbdc049c 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -23,14 +23,15 @@
 #include <linux/semaphore.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/random.h>
 #include <linux/vmalloc.h>
 
 #define MAX_ENTRIES	1000000
 #define TEST_INSERT_FAIL INT_MAX
 
-static int entries = 50000;
-module_param(entries, int, 0);
-MODULE_PARM_DESC(entries, "Number of entries to add (default: 50000)");
+static int parm_entries = 50000;
+module_param(parm_entries, int, 0);
+MODULE_PARM_DESC(parm_entries, "Number of entries to add (default: 50000)");
 
 static int runs = 4;
 module_param(runs, int, 0);
@@ -66,14 +67,18 @@ struct test_obj {
 	struct rhash_head	node;
 };
 
+struct test_obj_rhl {
+	struct test_obj_val	value;
+	struct rhlist_head	list_node;
+};
+
 struct thread_data {
+	unsigned int entries;
 	int id;
 	struct task_struct *task;
 	struct test_obj *objs;
 };
 
-static struct test_obj array[MAX_ENTRIES];
-
 static struct rhashtable_params test_rht_params = {
 	.head_offset = offsetof(struct test_obj, node),
 	.key_offset = offsetof(struct test_obj, value),
@@ -85,7 +90,7 @@ static struct rhashtable_params test_rht_params = {
 static struct semaphore prestart_sem;
 static struct semaphore startup_sem = __SEMAPHORE_INITIALIZER(startup_sem, 0);
 
-static int insert_retry(struct rhashtable *ht, struct rhash_head *obj,
+static int insert_retry(struct rhashtable *ht, struct test_obj *obj,
                         const struct rhashtable_params params)
 {
 	int err, retries = -1, enomem_retries = 0;
@@ -93,7 +98,7 @@ static int insert_retry(struct rhashtable *ht, struct rhash_head *obj,
 	do {
 		retries++;
 		cond_resched();
-		err = rhashtable_insert_fast(ht, obj, params);
+		err = rhashtable_insert_fast(ht, &obj->node, params);
 		if (err == -ENOMEM && enomem_retry) {
 			enomem_retries++;
 			err = -EBUSY;
@@ -107,11 +112,12 @@ static int insert_retry(struct rhashtable *ht, struct rhash_head *obj,
 	return err ? : retries;
 }
 
-static int __init test_rht_lookup(struct rhashtable *ht)
+static int __init test_rht_lookup(struct rhashtable *ht, struct test_obj *array,
+				  unsigned int entries)
 {
 	unsigned int i;
 
-	for (i = 0; i < entries * 2; i++) {
+	for (i = 0; i < entries; i++) {
 		struct test_obj *obj;
 		bool expected = !(i % 2);
 		struct test_obj_val key = {
@@ -144,7 +150,7 @@ static int __init test_rht_lookup(struct rhashtable *ht)
 	return 0;
 }
 
-static void test_bucket_stats(struct rhashtable *ht)
+static void test_bucket_stats(struct rhashtable *ht, unsigned int entries)
 {
 	unsigned int err, total = 0, chain_len = 0;
 	struct rhashtable_iter hti;
@@ -186,7 +192,8 @@ static void test_bucket_stats(struct rhashtable *ht)
 		pr_warn("Test failed: Total count mismatch ^^^");
 }
 
-static s64 __init test_rhashtable(struct rhashtable *ht)
+static s64 __init test_rhashtable(struct rhashtable *ht, struct test_obj *array,
+				  unsigned int entries)
 {
 	struct test_obj *obj;
 	int err;
@@ -203,7 +210,7 @@ static s64 __init test_rhashtable(struct rhashtable *ht)
 		struct test_obj *obj = &array[i];
 
 		obj->value.id = i * 2;
-		err = insert_retry(ht, &obj->node, test_rht_params);
+		err = insert_retry(ht, obj, test_rht_params);
 		if (err > 0)
 			insert_retries += err;
 		else if (err)
@@ -214,12 +221,12 @@ static s64 __init test_rhashtable(struct rhashtable *ht)
 		pr_info("  %u insertions retried due to memory pressure\n",
 			insert_retries);
 
-	test_bucket_stats(ht);
+	test_bucket_stats(ht, entries);
 	rcu_read_lock();
-	test_rht_lookup(ht);
+	test_rht_lookup(ht, array, entries);
 	rcu_read_unlock();
 
-	test_bucket_stats(ht);
+	test_bucket_stats(ht, entries);
 
 	pr_info("  Deleting %d keys\n", entries);
 	for (i = 0; i < entries; i++) {
@@ -244,9 +251,227 @@ static s64 __init test_rhashtable(struct rhashtable *ht)
 }
 
 static struct rhashtable ht;
+static struct rhltable rhlt;
+
+static int __init test_rhltable(unsigned int entries)
+{
+	struct test_obj_rhl *rhl_test_objects;
+	unsigned long *obj_in_table;
+	unsigned int i, j, k;
+	int ret, err;
+
+	if (entries == 0)
+		entries = 1;
+
+	rhl_test_objects = vzalloc(sizeof(*rhl_test_objects) * entries);
+	if (!rhl_test_objects)
+		return -ENOMEM;
+
+	ret = -ENOMEM;
+	obj_in_table = vzalloc(BITS_TO_LONGS(entries) * sizeof(unsigned long));
+	if (!obj_in_table)
+		goto out_free;
+
+	/* nulls_base not supported in rhlist interface */
+	test_rht_params.nulls_base = 0;
+	err = rhltable_init(&rhlt, &test_rht_params);
+	if (WARN_ON(err))
+		goto out_free;
+
+	k = prandom_u32();
+	ret = 0;
+	for (i = 0; i < entries; i++) {
+		rhl_test_objects[i].value.id = k;
+		err = rhltable_insert(&rhlt, &rhl_test_objects[i].list_node,
+				      test_rht_params);
+		if (WARN(err, "error %d on element %d\n", err, i))
+			break;
+		if (err == 0)
+			set_bit(i, obj_in_table);
+	}
+
+	if (err)
+		ret = err;
+
+	pr_info("test %d add/delete pairs into rhlist\n", entries);
+	for (i = 0; i < entries; i++) {
+		struct rhlist_head *h, *pos;
+		struct test_obj_rhl *obj;
+		struct test_obj_val key = {
+			.id = k,
+		};
+		bool found;
+
+		rcu_read_lock();
+		h = rhltable_lookup(&rhlt, &key, test_rht_params);
+		if (WARN(!h, "key not found during iteration %d of %d", i, entries)) {
+			rcu_read_unlock();
+			break;
+		}
+
+		if (i) {
+			j = i - 1;
+			rhl_for_each_entry_rcu(obj, pos, h, list_node) {
+				if (WARN(pos == &rhl_test_objects[j].list_node, "old element found, should be gone"))
+					break;
+			}
+		}
+
+		cond_resched_rcu();
+
+		found = false;
+
+		rhl_for_each_entry_rcu(obj, pos, h, list_node) {
+			if (pos == &rhl_test_objects[i].list_node) {
+				found = true;
+				break;
+			}
+		}
+
+		rcu_read_unlock();
+
+		if (WARN(!found, "element %d not found", i))
+			break;
+
+		err = rhltable_remove(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
+		WARN(err, "rhltable_remove: err %d for iteration %d\n", err, i);
+		if (err == 0)
+			clear_bit(i, obj_in_table);
+	}
+
+	if (ret == 0 && err)
+		ret = err;
+
+	for (i = 0; i < entries; i++) {
+		WARN(test_bit(i, obj_in_table), "elem %d allegedly still present", i);
+
+		err = rhltable_insert(&rhlt, &rhl_test_objects[i].list_node,
+				      test_rht_params);
+		if (WARN(err, "error %d on element %d\n", err, i))
+			break;
+		if (err == 0)
+			set_bit(i, obj_in_table);
+	}
+
+	pr_info("test %d random rhlist add/delete operations\n", entries);
+	for (j = 0; j < entries; j++) {
+		u32 i = prandom_u32_max(entries);
+		u32 prand = prandom_u32();
+
+		cond_resched();
+
+		if (prand == 0)
+			prand = prandom_u32();
+
+		if (prand & 1) {
+			prand >>= 1;
+			continue;
+		}
+
+		err = rhltable_remove(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
+		if (test_bit(i, obj_in_table)) {
+			clear_bit(i, obj_in_table);
+			if (WARN(err, "cannot remove element at slot %d", i))
+				continue;
+		} else {
+			if (WARN(err != -ENOENT, "removed non-existant element %d, error %d not %d",
+			     i, err, -ENOENT))
+				continue;
+		}
+
+		if (prand & 1) {
+			prand >>= 1;
+			continue;
+		}
+
+		err = rhltable_insert(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
+		if (err == 0) {
+			if (WARN(test_and_set_bit(i, obj_in_table), "succeeded to insert same object %d", i))
+				continue;
+		} else {
+			if (WARN(!test_bit(i, obj_in_table), "failed to insert object %d", i))
+				continue;
+		}
+
+		if (prand & 1) {
+			prand >>= 1;
+			continue;
+		}
+
+		i = prandom_u32_max(entries);
+		if (test_bit(i, obj_in_table)) {
+			err = rhltable_remove(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
+			WARN(err, "cannot remove element at slot %d", i);
+			if (err == 0)
+				clear_bit(i, obj_in_table);
+		} else {
+			err = rhltable_insert(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
+			WARN(err, "failed to insert object %d", i);
+			if (err == 0)
+				set_bit(i, obj_in_table);
+		}
+	}
+
+	for (i = 0; i < entries; i++) {
+		cond_resched();
+		err = rhltable_remove(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
+		if (test_bit(i, obj_in_table)) {
+			if (WARN(err, "cannot remove element at slot %d", i))
+				continue;
+		} else {
+			if (WARN(err != -ENOENT, "removed non-existant element, error %d not %d",
+				 err, -ENOENT))
+			continue;
+		}
+	}
+
+	rhltable_destroy(&rhlt);
+out_free:
+	vfree(rhl_test_objects);
+	vfree(obj_in_table);
+	return ret;
+}
+
+static int __init test_rhashtable_max(struct test_obj *array,
+				      unsigned int entries)
+{
+	unsigned int i, insert_retries = 0;
+	int err;
+
+	test_rht_params.max_size = roundup_pow_of_two(entries / 8);
+	err = rhashtable_init(&ht, &test_rht_params);
+	if (err)
+		return err;
+
+	for (i = 0; i < ht.max_elems; i++) {
+		struct test_obj *obj = &array[i];
+
+		obj->value.id = i * 2;
+		err = insert_retry(&ht, obj, test_rht_params);
+		if (err > 0)
+			insert_retries += err;
+		else if (err)
+			return err;
+	}
+
+	err = insert_retry(&ht, &array[ht.max_elems], test_rht_params);
+	if (err == -E2BIG) {
+		err = 0;
+	} else {
+		pr_info("insert element %u should have failed with %d, got %d\n",
+				ht.max_elems, -E2BIG, err);
+		if (err == 0)
+			err = -1;
+	}
+
+	rhashtable_destroy(&ht);
+
+	return err;
+}
 
 static int thread_lookup_test(struct thread_data *tdata)
 {
+	unsigned int entries = tdata->entries;
 	int i, err = 0;
 
 	for (i = 0; i < entries; i++) {
@@ -283,10 +508,10 @@ static int threadfunc(void *data)
 	if (down_interruptible(&startup_sem))
 		pr_err("  thread[%d]: down_interruptible failed\n", tdata->id);
 
-	for (i = 0; i < entries; i++) {
+	for (i = 0; i < tdata->entries; i++) {
 		tdata->objs[i].value.id = i;
 		tdata->objs[i].value.tid = tdata->id;
-		err = insert_retry(&ht, &tdata->objs[i].node, test_rht_params);
+		err = insert_retry(&ht, &tdata->objs[i], test_rht_params);
 		if (err > 0) {
 			insert_retries += err;
 		} else if (err) {
@@ -307,7 +532,7 @@ static int threadfunc(void *data)
 	}
 
 	for (step = 10; step > 0; step--) {
-		for (i = 0; i < entries; i += step) {
+		for (i = 0; i < tdata->entries; i += step) {
 			if (tdata->objs[i].value.id == TEST_INSERT_FAIL)
 				continue;
 			err = rhashtable_remove_fast(&ht, &tdata->objs[i].node,
@@ -338,17 +563,25 @@ out:
 
 static int __init test_rht_init(void)
 {
+	unsigned int entries;
 	int i, err, started_threads = 0, failed_threads = 0;
 	u64 total_time = 0;
 	struct thread_data *tdata;
 	struct test_obj *objs;
 
-	entries = min(entries, MAX_ENTRIES);
+	if (parm_entries < 0)
+		parm_entries = 1;
+
+	entries = min(parm_entries, MAX_ENTRIES);
 
 	test_rht_params.automatic_shrinking = shrinking;
 	test_rht_params.max_size = max_size ? : roundup_pow_of_two(entries);
 	test_rht_params.nelem_hint = size;
 
+	objs = vzalloc((test_rht_params.max_size + 1) * sizeof(struct test_obj));
+	if (!objs)
+		return -ENOMEM;
+
 	pr_info("Running rhashtable test nelem=%d, max_size=%d, shrinking=%d\n",
 		size, max_size, shrinking);
 
@@ -356,7 +589,8 @@ static int __init test_rht_init(void)
 		s64 time;
 
 		pr_info("Test %02d:\n", i);
-		memset(&array, 0, sizeof(array));
+		memset(objs, 0, test_rht_params.max_size * sizeof(struct test_obj));
+
 		err = rhashtable_init(&ht, &test_rht_params);
 		if (err < 0) {
 			pr_warn("Test failed: Unable to initialize hashtable: %d\n",
@@ -364,9 +598,10 @@ static int __init test_rht_init(void)
 			continue;
 		}
 
-		time = test_rhashtable(&ht);
+		time = test_rhashtable(&ht, objs, entries);
 		rhashtable_destroy(&ht);
 		if (time < 0) {
+			vfree(objs);
 			pr_warn("Test failed: return code %lld\n", time);
 			return -EINVAL;
 		}
@@ -374,6 +609,11 @@ static int __init test_rht_init(void)
 		total_time += time;
 	}
 
+	pr_info("test if its possible to exceed max_size %d: %s\n",
+			test_rht_params.max_size, test_rhashtable_max(objs, entries) == 0 ?
+			"no, ok" : "YES, failed");
+	vfree(objs);
+
 	do_div(total_time, runs);
 	pr_info("Average test time: %llu\n", total_time);
 
@@ -404,6 +644,7 @@ static int __init test_rht_init(void)
 	}
 	for (i = 0; i < tcount; i++) {
 		tdata[i].id = i;
+		tdata[i].entries = entries;
 		tdata[i].objs = objs + i * entries;
 		tdata[i].task = kthread_run(threadfunc, &tdata[i],
 		                            "rhashtable_thrad[%d]", i);
@@ -425,11 +666,17 @@ static int __init test_rht_init(void)
 			failed_threads++;
 		}
 	}
-	pr_info("Started %d threads, %d failed\n",
-	        started_threads, failed_threads);
 	rhashtable_destroy(&ht);
 	vfree(tdata);
 	vfree(objs);
+
+	/*
+	 * rhltable_remove is very expensive, default values can cause test
+	 * to run for 2 minutes or more,  use a smaller number instead.
+	 */
+	err = test_rhltable(entries / 16);
+	pr_info("Started %d threads, %d failed, rhltable test returns %d\n",
+	        started_threads, failed_threads, err);
 	return 0;
 }
 
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 9649579b5b9f..71c3e045505b 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -138,7 +138,7 @@ int vlan_check_real_dev(struct net_device *real_dev,
 	return 0;
 }
 
-int register_vlan_dev(struct net_device *dev)
+int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack)
 {
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev = vlan->real_dev;
@@ -174,7 +174,7 @@ int register_vlan_dev(struct net_device *dev)
 	if (err < 0)
 		goto out_uninit_mvrp;
 
-	err = netdev_upper_dev_link(real_dev, dev);
+	err = netdev_upper_dev_link(real_dev, dev, extack);
 	if (err)
 		goto out_unregister_netdev;
 
@@ -270,7 +270,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
 	vlan->flags = VLAN_FLAG_REORDER_HDR;
 
 	new_dev->rtnl_link_ops = &vlan_link_ops;
-	err = register_vlan_dev(new_dev);
+	err = register_vlan_dev(new_dev, NULL);
 	if (err < 0)
 		goto out_free_newdev;
 
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 0e7afdf86127..a8ba51030b75 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -108,7 +108,7 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result);
 int vlan_check_real_dev(struct net_device *real_dev,
 			__be16 protocol, u16 vlan_id);
 void vlan_setup(struct net_device *dev);
-int register_vlan_dev(struct net_device *dev);
+int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack);
 void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
 bool vlan_dev_inherit_address(struct net_device *dev,
 			      struct net_device *real_dev);
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 5e831de3103e..6e7c5a6a7930 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -160,7 +160,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		return err;
 
-	return register_vlan_dev(dev);
+	return register_vlan_dev(dev, extack);
 }
 
 static inline size_t vlan_qos_map_size(unsigned int n)
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 65f706e4344c..d4f6029d5109 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -153,7 +153,7 @@ static int neigh_check_cb(struct neighbour *n)
 	return 1;
 }
 
-static void idle_timer_check(unsigned long dummy)
+static void idle_timer_check(struct timer_list *unused)
 {
 	write_lock(&arp_tbl.lock);
 	__neigh_for_each_release(&arp_tbl, neigh_check_cb);
@@ -887,7 +887,7 @@ static int __init atm_clip_init(void)
 	register_netdevice_notifier(&clip_dev_notifier);
 	register_inetaddr_notifier(&clip_inet_notifier);
 
-	setup_timer(&idle_timer, idle_timer_check, 0);
+	timer_setup(&idle_timer, idle_timer_check, 0);
 
 #ifdef CONFIG_PROC_FS
 	{
diff --git a/net/atm/lec.c b/net/atm/lec.c
index a3d93a1bb133..c976196da3ea 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -1232,7 +1232,7 @@ static void lane2_associate_ind(struct net_device *dev, const u8 *mac_addr,
 #define LEC_ARP_REFRESH_INTERVAL (3*HZ)
 
 static void lec_arp_check_expire(struct work_struct *work);
-static void lec_arp_expire_arp(unsigned long data);
+static void lec_arp_expire_arp(struct timer_list *t);
 
 /*
  * Arp table funcs
@@ -1559,8 +1559,7 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv,
 	}
 	ether_addr_copy(to_return->mac_addr, mac_addr);
 	INIT_HLIST_NODE(&to_return->next);
-	setup_timer(&to_return->timer, lec_arp_expire_arp,
-			(unsigned long)to_return);
+	timer_setup(&to_return->timer, lec_arp_expire_arp, 0);
 	to_return->last_used = jiffies;
 	to_return->priv = priv;
 	skb_queue_head_init(&to_return->tx_wait);
@@ -1569,11 +1568,11 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv,
 }
 
 /* Arp sent timer expired */
-static void lec_arp_expire_arp(unsigned long data)
+static void lec_arp_expire_arp(struct timer_list *t)
 {
 	struct lec_arp_table *entry;
 
-	entry = (struct lec_arp_table *)data;
+	entry = from_timer(entry, t, timer);
 
 	pr_debug("\n");
 	if (entry->status == ESI_ARP_PENDING) {
@@ -1591,10 +1590,10 @@ static void lec_arp_expire_arp(unsigned long data)
 }
 
 /* Unknown/unused vcc expire, remove associated entry */
-static void lec_arp_expire_vcc(unsigned long data)
+static void lec_arp_expire_vcc(struct timer_list *t)
 {
 	unsigned long flags;
-	struct lec_arp_table *to_remove = (struct lec_arp_table *)data;
+	struct lec_arp_table *to_remove = from_timer(to_remove, t, timer);
 	struct lec_priv *priv = to_remove->priv;
 
 	del_timer(&to_remove->timer);
@@ -1799,7 +1798,7 @@ static struct atm_vcc *lec_arp_resolve(struct lec_priv *priv,
 		else
 			send_to_lecd(priv, l_arp_xmt, mac_to_find, NULL, NULL);
 		entry->timer.expires = jiffies + (1 * HZ);
-		entry->timer.function = lec_arp_expire_arp;
+		entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_arp;
 		add_timer(&entry->timer);
 		found = priv->mcast_vcc;
 	}
@@ -1999,7 +1998,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data,
 		entry->old_recv_push = old_push;
 		entry->status = ESI_UNKNOWN;
 		entry->timer.expires = jiffies + priv->vcc_timeout_period;
-		entry->timer.function = lec_arp_expire_vcc;
+		entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_vcc;
 		hlist_add_head(&entry->next, &priv->lec_no_forward);
 		add_timer(&entry->timer);
 		dump_arp_table(priv);
@@ -2083,7 +2082,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data,
 	entry->status = ESI_UNKNOWN;
 	hlist_add_head(&entry->next, &priv->lec_arp_empty_ones);
 	entry->timer.expires = jiffies + priv->vcc_timeout_period;
-	entry->timer.function = lec_arp_expire_vcc;
+	entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_vcc;
 	add_timer(&entry->timer);
 	pr_debug("After vcc was added\n");
 	dump_arp_table(priv);
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index 5677147209e8..883d25778fa4 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -95,7 +95,7 @@ static netdev_tx_t mpc_send_packet(struct sk_buff *skb,
 static int mpoa_event_listener(struct notifier_block *mpoa_notifier,
 			       unsigned long event, void *dev);
 static void mpc_timer_refresh(void);
-static void mpc_cache_check(unsigned long checking_time);
+static void mpc_cache_check(struct timer_list *unused);
 
 static struct llc_snap_hdr llc_snap_mpoa_ctrl = {
 	0xaa, 0xaa, 0x03,
@@ -799,7 +799,6 @@ static int atm_mpoa_mpoad_attach(struct atm_vcc *vcc, int arg)
 	int err;
 
 	if (mpcs == NULL) {
-		init_timer(&mpc_timer);
 		mpc_timer_refresh();
 
 		/* This lets us now how our LECs are doing */
@@ -1408,15 +1407,17 @@ static void clean_up(struct k_message *msg, struct mpoa_client *mpc, int action)
 	msg_to_mpoad(msg, mpc);
 }
 
+static unsigned long checking_time;
+
 static void mpc_timer_refresh(void)
 {
 	mpc_timer.expires = jiffies + (MPC_P2 * HZ);
-	mpc_timer.data = mpc_timer.expires;
-	mpc_timer.function = mpc_cache_check;
+	checking_time = mpc_timer.expires;
+	mpc_timer.function = (TIMER_FUNC_TYPE)mpc_cache_check;
 	add_timer(&mpc_timer);
 }
 
-static void mpc_cache_check(unsigned long checking_time)
+static void mpc_cache_check(struct timer_list *unused)
 {
 	struct mpoa_client *mpc = mpcs;
 	static unsigned long previous_resolving_check_time;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index f3f9d18891de..06eac1f50c5e 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -268,9 +268,9 @@ void ax25_destroy_socket(ax25_cb *);
 /*
  *	Handler for deferred kills.
  */
-static void ax25_destroy_timer(unsigned long data)
+static void ax25_destroy_timer(struct timer_list *t)
 {
-	ax25_cb *ax25=(ax25_cb *)data;
+	ax25_cb *ax25 = from_timer(ax25, t, dtimer);
 	struct sock *sk;
 
 	sk=ax25->sk;
@@ -326,8 +326,7 @@ void ax25_destroy_socket(ax25_cb *ax25)
 	if (ax25->sk != NULL) {
 		if (sk_has_allocations(ax25->sk)) {
 			/* Defer: outstanding buffers */
-			setup_timer(&ax25->dtimer, ax25_destroy_timer,
-					(unsigned long)ax25);
+			timer_setup(&ax25->dtimer, ax25_destroy_timer, 0);
 			ax25->dtimer.expires  = jiffies + 2 * HZ;
 			add_timer(&ax25->dtimer);
 		} else {
diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c
index 5fb2104b7304..e9d11313d45b 100644
--- a/net/ax25/ax25_ds_timer.c
+++ b/net/ax25/ax25_ds_timer.c
@@ -29,7 +29,7 @@
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 
-static void ax25_ds_timeout(unsigned long);
+static void ax25_ds_timeout(struct timer_list *);
 
 /*
  *	Add DAMA slave timeout timer to timer list.
@@ -41,8 +41,7 @@ static void ax25_ds_timeout(unsigned long);
 
 void ax25_ds_setup_timer(ax25_dev *ax25_dev)
 {
-	setup_timer(&ax25_dev->dama.slave_timer, ax25_ds_timeout,
-		    (unsigned long)ax25_dev);
+	timer_setup(&ax25_dev->dama.slave_timer, ax25_ds_timeout, 0);
 }
 
 void ax25_ds_del_timer(ax25_dev *ax25_dev)
@@ -66,9 +65,9 @@ void ax25_ds_set_timer(ax25_dev *ax25_dev)
  *	Silently discard all (slave) connections in case our master forgot us...
  */
 
-static void ax25_ds_timeout(unsigned long arg)
+static void ax25_ds_timeout(struct timer_list *t)
 {
-	ax25_dev *ax25_dev = (struct ax25_dev *) arg;
+	ax25_dev *ax25_dev = from_timer(ax25_dev, t, dama.slave_timer);
 	ax25_cb *ax25;
 
 	if (ax25_dev == NULL || !ax25_dev->dama.slave)
diff --git a/net/ax25/ax25_timer.c b/net/ax25/ax25_timer.c
index 23a6f38a80bf..c47b7ee1e4da 100644
--- a/net/ax25/ax25_timer.c
+++ b/net/ax25/ax25_timer.c
@@ -33,20 +33,19 @@
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 
-static void ax25_heartbeat_expiry(unsigned long);
-static void ax25_t1timer_expiry(unsigned long);
-static void ax25_t2timer_expiry(unsigned long);
-static void ax25_t3timer_expiry(unsigned long);
-static void ax25_idletimer_expiry(unsigned long);
+static void ax25_heartbeat_expiry(struct timer_list *);
+static void ax25_t1timer_expiry(struct timer_list *);
+static void ax25_t2timer_expiry(struct timer_list *);
+static void ax25_t3timer_expiry(struct timer_list *);
+static void ax25_idletimer_expiry(struct timer_list *);
 
 void ax25_setup_timers(ax25_cb *ax25)
 {
-	setup_timer(&ax25->timer, ax25_heartbeat_expiry, (unsigned long)ax25);
-	setup_timer(&ax25->t1timer, ax25_t1timer_expiry, (unsigned long)ax25);
-	setup_timer(&ax25->t2timer, ax25_t2timer_expiry, (unsigned long)ax25);
-	setup_timer(&ax25->t3timer, ax25_t3timer_expiry, (unsigned long)ax25);
-	setup_timer(&ax25->idletimer, ax25_idletimer_expiry,
-		    (unsigned long)ax25);
+	timer_setup(&ax25->timer, ax25_heartbeat_expiry, 0);
+	timer_setup(&ax25->t1timer, ax25_t1timer_expiry, 0);
+	timer_setup(&ax25->t2timer, ax25_t2timer_expiry, 0);
+	timer_setup(&ax25->t3timer, ax25_t3timer_expiry, 0);
+	timer_setup(&ax25->idletimer, ax25_idletimer_expiry, 0);
 }
 
 void ax25_start_heartbeat(ax25_cb *ax25)
@@ -120,10 +119,10 @@ unsigned long ax25_display_timer(struct timer_list *timer)
 
 EXPORT_SYMBOL(ax25_display_timer);
 
-static void ax25_heartbeat_expiry(unsigned long param)
+static void ax25_heartbeat_expiry(struct timer_list *t)
 {
 	int proto = AX25_PROTO_STD_SIMPLEX;
-	ax25_cb *ax25 = (ax25_cb *)param;
+	ax25_cb *ax25 = from_timer(ax25, t, timer);
 
 	if (ax25->ax25_dev)
 		proto = ax25->ax25_dev->values[AX25_VALUES_PROTOCOL];
@@ -145,9 +144,9 @@ static void ax25_heartbeat_expiry(unsigned long param)
 	}
 }
 
-static void ax25_t1timer_expiry(unsigned long param)
+static void ax25_t1timer_expiry(struct timer_list *t)
 {
-	ax25_cb *ax25 = (ax25_cb *)param;
+	ax25_cb *ax25 = from_timer(ax25, t, t1timer);
 
 	switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) {
 	case AX25_PROTO_STD_SIMPLEX:
@@ -164,9 +163,9 @@ static void ax25_t1timer_expiry(unsigned long param)
 	}
 }
 
-static void ax25_t2timer_expiry(unsigned long param)
+static void ax25_t2timer_expiry(struct timer_list *t)
 {
-	ax25_cb *ax25 = (ax25_cb *)param;
+	ax25_cb *ax25 = from_timer(ax25, t, t2timer);
 
 	switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) {
 	case AX25_PROTO_STD_SIMPLEX:
@@ -183,9 +182,9 @@ static void ax25_t2timer_expiry(unsigned long param)
 	}
 }
 
-static void ax25_t3timer_expiry(unsigned long param)
+static void ax25_t3timer_expiry(struct timer_list *t)
 {
-	ax25_cb *ax25 = (ax25_cb *)param;
+	ax25_cb *ax25 = from_timer(ax25, t, t3timer);
 
 	switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) {
 	case AX25_PROTO_STD_SIMPLEX:
@@ -204,9 +203,9 @@ static void ax25_t3timer_expiry(unsigned long param)
 	}
 }
 
-static void ax25_idletimer_expiry(unsigned long param)
+static void ax25_idletimer_expiry(struct timer_list *t)
 {
-	ax25_cb *ax25 = (ax25_cb *)param;
+	ax25_cb *ax25 = from_timer(ax25, t, idletimer);
 
 	switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) {
 	case AX25_PROTO_STD_SIMPLEX:
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 83ba5483455a..1b659ab652fb 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -916,8 +916,8 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface)
 	u16 tvlv_len = 0;
 	unsigned long send_time;
 
-	if ((hard_iface->if_status == BATADV_IF_NOT_IN_USE) ||
-	    (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED))
+	if (hard_iface->if_status == BATADV_IF_NOT_IN_USE ||
+	    hard_iface->if_status == BATADV_IF_TO_BE_REMOVED)
 		return;
 
 	/* the interface gets activated here to avoid race conditions between
@@ -1264,7 +1264,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node,
 	 * drops as they can't send and receive at the same time.
 	 */
 	tq_iface_penalty = BATADV_TQ_MAX_VALUE;
-	if (if_outgoing && (if_incoming == if_outgoing) &&
+	if (if_outgoing && if_incoming == if_outgoing &&
 	    batadv_is_wifi_hardif(if_outgoing))
 		tq_iface_penalty = batadv_hop_penalty(BATADV_TQ_MAX_VALUE,
 						      bat_priv);
@@ -1369,7 +1369,7 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr,
 				ret = BATADV_NEIGH_DUP;
 		} else {
 			set_mark = 0;
-			if (is_dup && (ret != BATADV_NEIGH_DUP))
+			if (is_dup && ret != BATADV_NEIGH_DUP)
 				ret = BATADV_ORIG_DUP;
 		}
 
@@ -1515,7 +1515,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset,
 	/* drop packet if sender is not a direct neighbor and if we
 	 * don't route towards it
 	 */
-	if (!is_single_hop_neigh && (!orig_neigh_router)) {
+	if (!is_single_hop_neigh && !orig_neigh_router) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 			   "Drop packet: OGM via unknown neighbor!\n");
 		goto out_neigh;
@@ -1535,7 +1535,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset,
 	sameseq = orig_ifinfo->last_real_seqno == ntohl(ogm_packet->seqno);
 	similar_ttl = (orig_ifinfo->last_ttl - 3) <= ogm_packet->ttl;
 
-	if (is_bidirect && ((dup_status == BATADV_NO_DUP) ||
+	if (is_bidirect && (dup_status == BATADV_NO_DUP ||
 			    (sameseq && similar_ttl))) {
 		batadv_iv_ogm_orig_update(bat_priv, orig_node,
 					  orig_ifinfo, ethhdr,
@@ -1553,8 +1553,8 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset,
 		/* OGMs from secondary interfaces should only scheduled once
 		 * per interface where it has been received, not multiple times
 		 */
-		if ((ogm_packet->ttl <= 2) &&
-		    (if_incoming != if_outgoing)) {
+		if (ogm_packet->ttl <= 2 &&
+		    if_incoming != if_outgoing) {
 			batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 				   "Drop packet: OGM from secondary interface and wrong outgoing interface\n");
 			goto out_neigh;
@@ -1590,7 +1590,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset,
 			      if_incoming, if_outgoing);
 
 out_neigh:
-	if ((orig_neigh_node) && (!is_single_hop_neigh))
+	if (orig_neigh_node && !is_single_hop_neigh)
 		batadv_orig_node_put(orig_neigh_node);
 out:
 	if (router_ifinfo)
@@ -2523,9 +2523,9 @@ batadv_iv_gw_get_best_gw_node(struct batadv_priv *bat_priv)
 			tmp_gw_factor *= 100 * 100;
 			tmp_gw_factor >>= 18;
 
-			if ((tmp_gw_factor > max_gw_factor) ||
-			    ((tmp_gw_factor == max_gw_factor) &&
-			     (tq_avg > max_tq))) {
+			if (tmp_gw_factor > max_gw_factor ||
+			    (tmp_gw_factor == max_gw_factor &&
+			     tq_avg > max_tq)) {
 				if (curr_gw)
 					batadv_gw_node_put(curr_gw);
 				curr_gw = gw_node;
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 4e2724c5b33d..341ceab8338d 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -19,7 +19,6 @@
 #include "main.h"
 
 #include <linux/atomic.h>
-#include <linux/bug.h>
 #include <linux/cache.h>
 #include <linux/errno.h>
 #include <linux/if_ether.h>
@@ -623,11 +622,11 @@ static int batadv_v_neigh_cmp(struct batadv_neigh_node *neigh1,
 	int ret = 0;
 
 	ifinfo1 = batadv_neigh_ifinfo_get(neigh1, if_outgoing1);
-	if (WARN_ON(!ifinfo1))
+	if (!ifinfo1)
 		goto err_ifinfo1;
 
 	ifinfo2 = batadv_neigh_ifinfo_get(neigh2, if_outgoing2);
-	if (WARN_ON(!ifinfo2))
+	if (!ifinfo2)
 		goto err_ifinfo2;
 
 	ret = ifinfo1->bat_v.throughput - ifinfo2->bat_v.throughput;
@@ -649,11 +648,11 @@ static bool batadv_v_neigh_is_sob(struct batadv_neigh_node *neigh1,
 	bool ret = false;
 
 	ifinfo1 = batadv_neigh_ifinfo_get(neigh1, if_outgoing1);
-	if (WARN_ON(!ifinfo1))
+	if (!ifinfo1)
 		goto err_ifinfo1;
 
 	ifinfo2 = batadv_neigh_ifinfo_get(neigh2, if_outgoing2);
-	if (WARN_ON(!ifinfo2))
+	if (!ifinfo2)
 		goto err_ifinfo2;
 
 	threshold = ifinfo1->bat_v.throughput / 4;
@@ -767,7 +766,7 @@ batadv_v_gw_get_best_gw_node(struct batadv_priv *bat_priv)
 		if (batadv_v_gw_throughput_get(gw_node, &bw) < 0)
 			goto next;
 
-		if (curr_gw && (bw <= max_bw))
+		if (curr_gw && bw <= max_bw)
 			goto next;
 
 		if (curr_gw)
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index bd1064d98e16..1de992c58b35 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -134,7 +134,7 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh)
 			hard_iface->bat_v.flags &= ~BATADV_FULL_DUPLEX;
 
 		throughput = link_settings.base.speed;
-		if (throughput && (throughput != SPEED_UNKNOWN))
+		if (throughput && throughput != SPEED_UNKNOWN)
 			return throughput * 10;
 	}
 
@@ -263,8 +263,8 @@ static void batadv_v_elp_periodic_work(struct work_struct *work)
 		goto out;
 
 	/* we are in the process of shutting this interface down */
-	if ((hard_iface->if_status == BATADV_IF_NOT_IN_USE) ||
-	    (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED))
+	if (hard_iface->if_status == BATADV_IF_NOT_IN_USE ||
+	    hard_iface->if_status == BATADV_IF_TO_BE_REMOVED)
 		goto out;
 
 	/* the interface was enabled but may not be ready yet */
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index 8be61734fc43..c251445a42a0 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -304,8 +304,8 @@ static u32 batadv_v_forward_penalty(struct batadv_priv *bat_priv,
 	 * due to the store & forward characteristics of WIFI.
 	 * Very low throughput values are the exception.
 	 */
-	if ((throughput > 10) &&
-	    (if_incoming == if_outgoing) &&
+	if (throughput > 10 &&
+	    if_incoming == if_outgoing &&
 	    !(if_incoming->bat_v.flags & BATADV_FULL_DUPLEX))
 		return throughput / 2;
 
@@ -455,7 +455,7 @@ static int batadv_v_ogm_metric_update(struct batadv_priv *bat_priv,
 	/* drop packets with old seqnos, however accept the first packet after
 	 * a host has been rebooted.
 	 */
-	if ((seq_diff < 0) && !protection_started)
+	if (seq_diff < 0 && !protection_started)
 		goto out;
 
 	neigh_node->last_seen = jiffies;
@@ -568,8 +568,8 @@ static bool batadv_v_ogm_route_update(struct batadv_priv *bat_priv,
 		router_throughput = router_ifinfo->bat_v.throughput;
 		neigh_throughput = neigh_ifinfo->bat_v.throughput;
 
-		if ((neigh_seq_diff < BATADV_OGM_MAX_ORIGDIFF) &&
-		    (router_throughput >= neigh_throughput))
+		if (neigh_seq_diff < BATADV_OGM_MAX_ORIGDIFF &&
+		    router_throughput >= neigh_throughput)
 			goto out;
 	}
 
@@ -621,7 +621,7 @@ batadv_v_ogm_process_per_outif(struct batadv_priv *bat_priv,
 		return;
 
 	/* only unknown & newer OGMs contain TVLVs we are interested in */
-	if ((seqno_age > 0) && (if_outgoing == BATADV_IF_DEFAULT))
+	if (seqno_age > 0 && if_outgoing == BATADV_IF_DEFAULT)
 		batadv_tvlv_containers_process(bat_priv, true, orig_node,
 					       NULL, NULL,
 					       (unsigned char *)(ogm2 + 1),
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index b6cfa78e9381..760c0de72582 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -492,8 +492,8 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res,
 	/* this is an hash collision with the temporary selected node. Choose
 	 * the one with the lowest address
 	 */
-	if ((tmp_max == max) && max_orig_node &&
-	    (batadv_compare_eth(candidate->orig, max_orig_node->orig) > 0))
+	if (tmp_max == max && max_orig_node &&
+	    batadv_compare_eth(candidate->orig, max_orig_node->orig) > 0)
 		goto out;
 
 	ret = true;
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index de9955d5224d..10d521f0b17f 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -248,12 +248,12 @@ void batadv_gw_election(struct batadv_priv *bat_priv)
 		}
 	}
 
-	if ((curr_gw) && (!next_gw)) {
+	if (curr_gw && !next_gw) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 			   "Removing selected gateway - no gateway in range\n");
 		batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_DEL,
 				    NULL);
-	} else if ((!curr_gw) && (next_gw)) {
+	} else if (!curr_gw && next_gw) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 			   "Adding route to gateway %pM (bandwidth: %u.%u/%u.%u MBit, tq: %i)\n",
 			   next_gw->orig_node->orig,
@@ -411,8 +411,8 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv,
 		goto out;
 	}
 
-	if ((gw_node->bandwidth_down == ntohl(gateway->bandwidth_down)) &&
-	    (gw_node->bandwidth_up == ntohl(gateway->bandwidth_up)))
+	if (gw_node->bandwidth_down == ntohl(gateway->bandwidth_down) &&
+	    gw_node->bandwidth_up == ntohl(gateway->bandwidth_up))
 		goto out;
 
 	batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index 33940c5c74a8..2c26039c23fc 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -56,8 +56,8 @@ bool batadv_parse_throughput(struct net_device *net_dev, char *buff,
 		if (strncasecmp(tmp_ptr, "mbit", 4) == 0)
 			bw_unit_type = BATADV_BW_UNIT_MBIT;
 
-		if ((strncasecmp(tmp_ptr, "kbit", 4) == 0) ||
-		    (bw_unit_type == BATADV_BW_UNIT_MBIT))
+		if (strncasecmp(tmp_ptr, "kbit", 4) == 0 ||
+		    bw_unit_type == BATADV_BW_UNIT_MBIT)
 			*tmp_ptr = '\0';
 	}
 
@@ -190,7 +190,7 @@ ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff,
 	if (!up_new)
 		up_new = 1;
 
-	if ((down_curr == down_new) && (up_curr == up_new))
+	if (down_curr == down_new && up_curr == up_new)
 		return count;
 
 	batadv_gw_reselect(bat_priv);
@@ -224,16 +224,16 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 	/* only fetch the tvlv value if the handler wasn't called via the
 	 * CIFNOTFND flag and if there is data to fetch
 	 */
-	if ((flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) ||
-	    (tvlv_value_len < sizeof(gateway))) {
+	if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND ||
+	    tvlv_value_len < sizeof(gateway)) {
 		gateway.bandwidth_down = 0;
 		gateway.bandwidth_up = 0;
 	} else {
 		gateway_ptr = tvlv_value;
 		gateway.bandwidth_down = gateway_ptr->bandwidth_down;
 		gateway.bandwidth_up = gateway_ptr->bandwidth_up;
-		if ((gateway.bandwidth_down == 0) ||
-		    (gateway.bandwidth_up == 0)) {
+		if (gateway.bandwidth_down == 0 ||
+		    gateway.bandwidth_up == 0) {
 			gateway.bandwidth_down = 0;
 			gateway.bandwidth_up = 0;
 		}
@@ -242,8 +242,8 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 	batadv_gw_node_update(bat_priv, orig, &gateway);
 
 	/* restart gateway selection */
-	if ((gateway.bandwidth_down != 0) &&
-	    (atomic_read(&bat_priv->gw.mode) == BATADV_GW_MODE_CLIENT))
+	if (gateway.bandwidth_down != 0 &&
+	    atomic_read(&bat_priv->gw.mode) == BATADV_GW_MODE_CLIENT)
 		batadv_gw_check_election(bat_priv, orig);
 }
 
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index e348f76ea8c1..4e3d5340ad96 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -504,8 +504,8 @@ static void batadv_check_known_mac_addr(const struct net_device *net_dev)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if ((hard_iface->if_status != BATADV_IF_ACTIVE) &&
-		    (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED))
+		if (hard_iface->if_status != BATADV_IF_ACTIVE &&
+		    hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)
 			continue;
 
 		if (hard_iface->net_dev == net_dev)
@@ -568,8 +568,8 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if ((hard_iface->if_status != BATADV_IF_ACTIVE) &&
-		    (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED))
+		if (hard_iface->if_status != BATADV_IF_ACTIVE &&
+		    hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)
 			continue;
 
 		if (hard_iface->soft_iface != soft_iface)
@@ -654,8 +654,8 @@ out:
 static void
 batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface)
 {
-	if ((hard_iface->if_status != BATADV_IF_ACTIVE) &&
-	    (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED))
+	if (hard_iface->if_status != BATADV_IF_ACTIVE &&
+	    hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)
 		return;
 
 	hard_iface->if_status = BATADV_IF_INACTIVE;
@@ -738,7 +738,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	bat_priv = netdev_priv(hard_iface->soft_iface);
 
 	ret = netdev_master_upper_dev_link(hard_iface->net_dev,
-					   soft_iface, NULL, NULL);
+					   soft_iface, NULL, NULL, NULL);
 	if (ret)
 		goto err_dev;
 
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index 8ead292886d1..bded31121d12 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -132,10 +132,10 @@ static ssize_t batadv_socket_read(struct file *file, char __user *buf,
 	size_t packet_len;
 	int error;
 
-	if ((file->f_flags & O_NONBLOCK) && (socket_client->queue_len == 0))
+	if ((file->f_flags & O_NONBLOCK) && socket_client->queue_len == 0)
 		return -EAGAIN;
 
-	if ((!buf) || (count < sizeof(struct batadv_icmp_packet)))
+	if (!buf || count < sizeof(struct batadv_icmp_packet))
 		return -EINVAL;
 
 	if (!access_ok(VERIFY_WRITE, buf, count))
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index fb381fb26a66..4daed7ad46f2 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -73,8 +73,8 @@
  * list traversals just rcu-locked
  */
 struct list_head batadv_hardif_list;
-static int (*batadv_rx_handler[256])(struct sk_buff *,
-				     struct batadv_hard_iface *);
+static int (*batadv_rx_handler[256])(struct sk_buff *skb,
+				     struct batadv_hard_iface *recv_if);
 
 unsigned char batadv_broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
 
@@ -540,12 +540,12 @@ batadv_recv_handler_register(u8 packet_type,
 			     int (*recv_handler)(struct sk_buff *,
 						 struct batadv_hard_iface *))
 {
-	int (*curr)(struct sk_buff *,
-		    struct batadv_hard_iface *);
+	int (*curr)(struct sk_buff *skb,
+		    struct batadv_hard_iface *recv_if);
 	curr = batadv_rx_handler[packet_type];
 
-	if ((curr != batadv_recv_unhandled_packet) &&
-	    (curr != batadv_recv_unhandled_unicast_packet))
+	if (curr != batadv_recv_unhandled_packet &&
+	    curr != batadv_recv_unhandled_unicast_packet)
 		return -EBUSY;
 
 	batadv_rx_handler[packet_type] = recv_handler;
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 05cc7637c064..edb2f239d04d 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -24,7 +24,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2017.3"
+#define BATADV_SOURCE_VERSION "2017.4"
 #endif
 
 /* B.A.T.M.A.N. parameters */
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index d327670641ac..e553a8770a89 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -1126,7 +1126,7 @@ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv,
 	bool orig_initialized;
 
 	if (orig_mcast_enabled && tvlv_value &&
-	    (tvlv_value_len >= sizeof(mcast_flags)))
+	    tvlv_value_len >= sizeof(mcast_flags))
 		mcast_flags = *(u8 *)tvlv_value;
 
 	spin_lock_bh(&orig->mcast_handler_lock);
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 8e2a4b205257..2967b86c13da 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -1062,9 +1062,9 @@ batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv,
 			continue;
 
 		/* don't purge if the interface is not (going) down */
-		if ((if_outgoing->if_status != BATADV_IF_INACTIVE) &&
-		    (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) &&
-		    (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED))
+		if (if_outgoing->if_status != BATADV_IF_INACTIVE &&
+		    if_outgoing->if_status != BATADV_IF_NOT_IN_USE &&
+		    if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)
 			continue;
 
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
@@ -1106,9 +1106,9 @@ batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv,
 			continue;
 
 		/* don't purge if the interface is not (going) down */
-		if ((if_outgoing->if_status != BATADV_IF_INACTIVE) &&
-		    (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) &&
-		    (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED))
+		if (if_outgoing->if_status != BATADV_IF_INACTIVE &&
+		    if_outgoing->if_status != BATADV_IF_NOT_IN_USE &&
+		    if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)
 			continue;
 
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
@@ -1155,13 +1155,13 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv,
 		last_seen = neigh_node->last_seen;
 		if_incoming = neigh_node->if_incoming;
 
-		if ((batadv_has_timed_out(last_seen, BATADV_PURGE_TIMEOUT)) ||
-		    (if_incoming->if_status == BATADV_IF_INACTIVE) ||
-		    (if_incoming->if_status == BATADV_IF_NOT_IN_USE) ||
-		    (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)) {
-			if ((if_incoming->if_status == BATADV_IF_INACTIVE) ||
-			    (if_incoming->if_status == BATADV_IF_NOT_IN_USE) ||
-			    (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED))
+		if (batadv_has_timed_out(last_seen, BATADV_PURGE_TIMEOUT) ||
+		    if_incoming->if_status == BATADV_IF_INACTIVE ||
+		    if_incoming->if_status == BATADV_IF_NOT_IN_USE ||
+		    if_incoming->if_status == BATADV_IF_TO_BE_REMOVED) {
+			if (if_incoming->if_status == BATADV_IF_INACTIVE ||
+			    if_incoming->if_status == BATADV_IF_NOT_IN_USE ||
+			    if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)
 				batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 					   "neighbor purge: originator %pM, neighbor: %pM, iface: %s\n",
 					   orig_node->orig, neigh_node->addr,
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index f10e3ff26f9d..40d9bf3e5bfe 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -93,14 +93,14 @@ static void _batadv_update_route(struct batadv_priv *bat_priv,
 	batadv_orig_ifinfo_put(orig_ifinfo);
 
 	/* route deleted */
-	if ((curr_router) && (!neigh_node)) {
+	if (curr_router && !neigh_node) {
 		batadv_dbg(BATADV_DBG_ROUTES, bat_priv,
 			   "Deleting route towards: %pM\n", orig_node->orig);
 		batadv_tt_global_del_orig(bat_priv, orig_node, -1,
 					  "Deleted route towards originator");
 
 	/* route added */
-	} else if ((!curr_router) && (neigh_node)) {
+	} else if (!curr_router && neigh_node) {
 		batadv_dbg(BATADV_DBG_ROUTES, bat_priv,
 			   "Adding route towards: %pM (via %pM)\n",
 			   orig_node->orig, neigh_node->addr);
@@ -381,7 +381,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
 	/* add record route information if not full */
 	if ((icmph->msg_type == BATADV_ECHO_REPLY ||
 	     icmph->msg_type == BATADV_ECHO_REQUEST) &&
-	    (skb->len >= sizeof(struct batadv_icmp_packet_rr))) {
+	    skb->len >= sizeof(struct batadv_icmp_packet_rr)) {
 		if (skb_linearize(skb) < 0)
 			goto free_skb;
 
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 054a65e6eb68..7895323fd2a7 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -142,7 +142,7 @@ int batadv_send_unicast_skb(struct sk_buff *skb,
 #ifdef CONFIG_BATMAN_ADV_BATMAN_V
 	hardif_neigh = batadv_hardif_neigh_get(neigh->if_incoming, neigh->addr);
 
-	if ((hardif_neigh) && (ret != NET_XMIT_DROP))
+	if (hardif_neigh && ret != NET_XMIT_DROP)
 		hardif_neigh->bat_v.last_unicast_tx = jiffies;
 
 	if (hardif_neigh)
@@ -615,8 +615,8 @@ batadv_forw_packet_list_steal(struct hlist_head *forw_list,
 		 * we delete only packets belonging to the given interface
 		 */
 		if (hard_iface &&
-		    (forw_packet->if_incoming != hard_iface) &&
-		    (forw_packet->if_outgoing != hard_iface))
+		    forw_packet->if_incoming != hard_iface &&
+		    forw_packet->if_outgoing != hard_iface)
 			continue;
 
 		hlist_del(&forw_packet->list);
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 10f7edfb176e..9f673cdfecf8 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -69,8 +69,8 @@ int batadv_skb_head_push(struct sk_buff *skb, unsigned int len)
 	int result;
 
 	/* TODO: We must check if we can release all references to non-payload
-	 * data using skb_header_release in our skbs to allow skb_cow_header to
-	 * work optimally. This means that those skbs are not allowed to read
+	 * data using __skb_header_release in our skbs to allow skb_cow_header
+	 * to work optimally. This means that those skbs are not allowed to read
 	 * or write any data which is before the current position of skb->data
 	 * after that call and thus allow other skbs with the same data buffer
 	 * to write freely in that area.
@@ -160,7 +160,7 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p)
 static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu)
 {
 	/* check ranges */
-	if ((new_mtu < 68) || (new_mtu > batadv_hardif_min_mtu(dev)))
+	if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev))
 		return -EINVAL;
 
 	dev->mtu = new_mtu;
@@ -863,11 +863,13 @@ free_bat_counters:
  * batadv_softif_slave_add - Add a slave interface to a batadv_soft_interface
  * @dev: batadv_soft_interface used as master interface
  * @slave_dev: net_device which should become the slave interface
+ * @extack: extended ACK report struct
  *
  * Return: 0 if successful or error otherwise.
  */
 static int batadv_softif_slave_add(struct net_device *dev,
-				   struct net_device *slave_dev)
+				   struct net_device *slave_dev,
+				   struct netlink_ext_ack *extack)
 {
 	struct batadv_hard_iface *hard_iface;
 	struct net *net = dev_net(dev);
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index 0ae8b30e4eaa..aa187fd42475 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -925,8 +925,8 @@ static int batadv_store_mesh_iface_finish(struct net_device *net_dev,
 	if (hard_iface->if_status == status_tmp)
 		goto out;
 
-	if ((hard_iface->soft_iface) &&
-	    (strncmp(hard_iface->soft_iface->name, ifname, IFNAMSIZ) == 0))
+	if (hard_iface->soft_iface &&
+	    strncmp(hard_iface->soft_iface->name, ifname, IFNAMSIZ) == 0)
 		goto out;
 
 	if (status_tmp == BATADV_IF_NOT_IN_USE) {
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
index bfe8effe9238..4b90033f35a8 100644
--- a/net/batman-adv/tp_meter.c
+++ b/net/batman-adv/tp_meter.c
@@ -1206,7 +1206,7 @@ static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst,
 
 	/* send the ack */
 	r = batadv_send_skb_to_orig(skb, orig_node, NULL);
-	if (unlikely(r < 0) || (r == NET_XMIT_DROP)) {
+	if (unlikely(r < 0) || r == NET_XMIT_DROP) {
 		ret = BATADV_TP_REASON_DST_UNREACHABLE;
 		goto out;
 	}
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index aad994edd3bb..51c2cf2d8923 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -573,7 +573,7 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 	hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK,
 				       &mgr->l2cap_conn->hcon->dst);
 	if (!hcon) {
-		BT_ERR("No phys link exist");
+		bt_dev_err(hdev, "no phys link exist");
 		rsp.status = A2MP_STATUS_NO_PHYSICAL_LINK_EXISTS;
 		goto clean;
 	}
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index ebcab5bbadd7..78bec8df8525 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -187,7 +187,7 @@ int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type)
 
 	/* Legacy key */
 	if (conn->key_type < 3) {
-		BT_ERR("Legacy key type %d", conn->key_type);
+		bt_dev_err(hdev, "legacy key type %d", conn->key_type);
 		return -EACCES;
 	}
 
@@ -207,7 +207,7 @@ int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type)
 	/* Derive Generic AMP Link Key (gamp) */
 	err = hmac_sha256(keybuf, HCI_AMP_LINK_KEY_SIZE, "gamp", 4, gamp_key);
 	if (err) {
-		BT_ERR("Could not derive Generic AMP Key: err %d", err);
+		bt_dev_err(hdev, "could not derive Generic AMP Key: err %d", err);
 		return err;
 	}
 
diff --git a/net/bluetooth/ecdh_helper.c b/net/bluetooth/ecdh_helper.c
index c7b1a9aee579..2155ce802877 100644
--- a/net/bluetooth/ecdh_helper.c
+++ b/net/bluetooth/ecdh_helper.c
@@ -23,7 +23,6 @@
 #include "ecdh_helper.h"
 
 #include <linux/scatterlist.h>
-#include <crypto/kpp.h>
 #include <crypto/ecdh.h>
 
 struct ecdh_completion {
@@ -50,55 +49,35 @@ static inline void swap_digits(u64 *in, u64 *out, unsigned int ndigits)
 		out[i] = __swab64(in[ndigits - 1 - i]);
 }
 
-bool compute_ecdh_secret(const u8 public_key[64], const u8 private_key[32],
-			 u8 secret[32])
+/* compute_ecdh_secret() - function assumes that the private key was
+ *                         already set.
+ * @tfm:          KPP tfm handle allocated with crypto_alloc_kpp().
+ * @public_key:   pair's ecc public key.
+ * secret:        memory where the ecdh computed shared secret will be saved.
+ *
+ * Return: zero on success; error code in case of error.
+ */
+int compute_ecdh_secret(struct crypto_kpp *tfm, const u8 public_key[64],
+			u8 secret[32])
 {
-	struct crypto_kpp *tfm;
 	struct kpp_request *req;
-	struct ecdh p;
+	u8 *tmp;
 	struct ecdh_completion result;
 	struct scatterlist src, dst;
-	u8 *tmp, *buf;
-	unsigned int buf_len;
-	int err = -ENOMEM;
+	int err;
 
 	tmp = kmalloc(64, GFP_KERNEL);
 	if (!tmp)
-		return false;
+		return -ENOMEM;
 
-	tfm = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
-	if (IS_ERR(tfm)) {
-		pr_err("alg: kpp: Failed to load tfm for kpp: %ld\n",
-		       PTR_ERR(tfm));
+	req = kpp_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		err = -ENOMEM;
 		goto free_tmp;
 	}
 
-	req = kpp_request_alloc(tfm, GFP_KERNEL);
-	if (!req)
-		goto free_kpp;
-
 	init_completion(&result.completion);
 
-	/* Security Manager Protocol holds digits in litte-endian order
-	 * while ECC API expect big-endian data
-	 */
-	swap_digits((u64 *)private_key, (u64 *)tmp, 4);
-	p.key = (char *)tmp;
-	p.key_size = 32;
-	/* Set curve_id */
-	p.curve_id = ECC_CURVE_NIST_P256;
-	buf_len = crypto_ecdh_key_len(&p);
-	buf = kmalloc(buf_len, GFP_KERNEL);
-	if (!buf)
-		goto free_req;
-
-	crypto_ecdh_encode_key(buf, buf_len, &p);
-
-	/* Set A private Key */
-	err = crypto_kpp_set_secret(tfm, (void *)buf, buf_len);
-	if (err)
-		goto free_all;
-
 	swap_digits((u64 *)public_key, (u64 *)tmp, 4); /* x */
 	swap_digits((u64 *)&public_key[32], (u64 *)&tmp[32], 4); /* y */
 
@@ -123,104 +102,129 @@ bool compute_ecdh_secret(const u8 public_key[64], const u8 private_key[32],
 	memcpy(secret, tmp, 32);
 
 free_all:
-	kzfree(buf);
-free_req:
 	kpp_request_free(req);
-free_kpp:
-	crypto_free_kpp(tfm);
 free_tmp:
-	kfree(tmp);
-	return (err == 0);
+	kzfree(tmp);
+	return err;
 }
 
-bool generate_ecdh_keys(u8 public_key[64], u8 private_key[32])
+/* set_ecdh_privkey() - set or generate ecc private key.
+ *
+ * Function generates an ecc private key in the crypto subsystem when receiving
+ * a NULL private key or sets the received key when not NULL.
+ *
+ * @tfm:           KPP tfm handle allocated with crypto_alloc_kpp().
+ * @private_key:   user's ecc private key. When not NULL, the key is expected
+ *                 in little endian format.
+ *
+ * Return: zero on success; error code in case of error.
+ */
+int set_ecdh_privkey(struct crypto_kpp *tfm, const u8 private_key[32])
+{
+	u8 *buf, *tmp = NULL;
+	unsigned int buf_len;
+	int err;
+	struct ecdh p = {0};
+
+	p.curve_id = ECC_CURVE_NIST_P256;
+
+	if (private_key) {
+		tmp = kmalloc(32, GFP_KERNEL);
+		if (!tmp)
+			return -ENOMEM;
+		swap_digits((u64 *)private_key, (u64 *)tmp, 4);
+		p.key = tmp;
+		p.key_size = 32;
+	}
+
+	buf_len = crypto_ecdh_key_len(&p);
+	buf = kmalloc(buf_len, GFP_KERNEL);
+	if (!buf) {
+		err = -ENOMEM;
+		goto free_tmp;
+	}
+
+	err = crypto_ecdh_encode_key(buf, buf_len, &p);
+	if (err)
+		goto free_all;
+
+	err = crypto_kpp_set_secret(tfm, buf, buf_len);
+	/* fall through */
+free_all:
+	kzfree(buf);
+free_tmp:
+	kzfree(tmp);
+	return err;
+}
+
+/* generate_ecdh_public_key() - function assumes that the private key was
+ *                              already set.
+ *
+ * @tfm:          KPP tfm handle allocated with crypto_alloc_kpp().
+ * @public_key:   memory where the computed ecc public key will be saved.
+ *
+ * Return: zero on success; error code in case of error.
+ */
+int generate_ecdh_public_key(struct crypto_kpp *tfm, u8 public_key[64])
 {
-	struct crypto_kpp *tfm;
 	struct kpp_request *req;
-	struct ecdh p;
+	u8 *tmp;
 	struct ecdh_completion result;
 	struct scatterlist dst;
-	u8 *tmp, *buf;
-	unsigned int buf_len;
-	int err = -ENOMEM;
-	const unsigned short max_tries = 16;
-	unsigned short tries = 0;
+	int err;
 
 	tmp = kmalloc(64, GFP_KERNEL);
 	if (!tmp)
-		return false;
+		return -ENOMEM;
 
-	tfm = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
-	if (IS_ERR(tfm)) {
-		pr_err("alg: kpp: Failed to load tfm for kpp: %ld\n",
-		       PTR_ERR(tfm));
+	req = kpp_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		err = -ENOMEM;
 		goto free_tmp;
 	}
 
-	req = kpp_request_alloc(tfm, GFP_KERNEL);
-	if (!req)
-		goto free_kpp;
-
 	init_completion(&result.completion);
+	sg_init_one(&dst, tmp, 64);
+	kpp_request_set_input(req, NULL, 0);
+	kpp_request_set_output(req, &dst, 64);
+	kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				 ecdh_complete, &result);
 
-	/* Set curve_id */
-	p.curve_id = ECC_CURVE_NIST_P256;
-	p.key_size = 32;
-	buf_len = crypto_ecdh_key_len(&p);
-	buf = kmalloc(buf_len, GFP_KERNEL);
-	if (!buf)
-		goto free_req;
-
-	do {
-		if (tries++ >= max_tries)
-			goto free_all;
-
-		/* Set private Key */
-		p.key = (char *)private_key;
-		crypto_ecdh_encode_key(buf, buf_len, &p);
-		err = crypto_kpp_set_secret(tfm, buf, buf_len);
-		if (err)
-			goto free_all;
-
-		sg_init_one(&dst, tmp, 64);
-		kpp_request_set_input(req, NULL, 0);
-		kpp_request_set_output(req, &dst, 64);
-		kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-					 ecdh_complete, &result);
-
-		err = crypto_kpp_generate_public_key(req);
-
-		if (err == -EINPROGRESS) {
-			wait_for_completion(&result.completion);
-			err = result.err;
-		}
-
-		/* Private key is not valid. Regenerate */
-		if (err == -EINVAL)
-			continue;
-
-		if (err < 0)
-			goto free_all;
-		else
-			break;
-
-	} while (true);
-
-	/* Keys are handed back in little endian as expected by Security
-	 * Manager Protocol
+	err = crypto_kpp_generate_public_key(req);
+	if (err == -EINPROGRESS) {
+		wait_for_completion(&result.completion);
+		err = result.err;
+	}
+	if (err < 0)
+		goto free_all;
+
+	/* The public key is handed back in little endian as expected by
+	 * the Security Manager Protocol.
 	 */
 	swap_digits((u64 *)tmp, (u64 *)public_key, 4); /* x */
 	swap_digits((u64 *)&tmp[32], (u64 *)&public_key[32], 4); /* y */
-	swap_digits((u64 *)private_key, (u64 *)tmp, 4);
-	memcpy(private_key, tmp, 32);
 
 free_all:
-	kzfree(buf);
-free_req:
 	kpp_request_free(req);
-free_kpp:
-	crypto_free_kpp(tfm);
 free_tmp:
 	kfree(tmp);
-	return (err == 0);
+	return err;
+}
+
+/* generate_ecdh_keys() - generate ecc key pair.
+ *
+ * @tfm:          KPP tfm handle allocated with crypto_alloc_kpp().
+ * @public_key:   memory where the computed ecc public key will be saved.
+ *
+ * Return: zero on success; error code in case of error.
+ */
+int generate_ecdh_keys(struct crypto_kpp *tfm, u8 public_key[64])
+{
+	int err;
+
+	err = set_ecdh_privkey(tfm, NULL);
+	if (err)
+		return err;
+
+	return generate_ecdh_public_key(tfm, public_key);
 }
diff --git a/net/bluetooth/ecdh_helper.h b/net/bluetooth/ecdh_helper.h
index 7a423faf76e5..a6f8d03d4aaf 100644
--- a/net/bluetooth/ecdh_helper.h
+++ b/net/bluetooth/ecdh_helper.h
@@ -20,8 +20,11 @@
  * COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
  * SOFTWARE IS DISCLAIMED.
  */
+#include <crypto/kpp.h>
 #include <linux/types.h>
 
-bool compute_ecdh_secret(const u8 pub_a[64], const u8 priv_b[32],
-			 u8 secret[32]);
-bool generate_ecdh_keys(u8 public_key[64], u8 private_key[32]);
+int compute_ecdh_secret(struct crypto_kpp *tfm, const u8 pair_public_key[64],
+			u8 secret[32]);
+int set_ecdh_privkey(struct crypto_kpp *tfm, const u8 *private_key);
+int generate_ecdh_public_key(struct crypto_kpp *tfm, u8 public_key[64]);
+int generate_ecdh_keys(struct crypto_kpp *tfm, u8 public_key[64]);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index dc59eae54717..a9682534c377 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -729,8 +729,8 @@ static void create_le_conn_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 		goto done;
 	}
 
-	BT_ERR("HCI request failed to create LE connection: status 0x%2.2x",
-	       status);
+	bt_dev_err(hdev, "request failed to create LE connection: "
+		   "status 0x%2.2x", status);
 
 	if (!conn)
 		goto done;
@@ -907,7 +907,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 		 */
 		if (hci_dev_test_flag(hdev, HCI_LE_SCAN) &&
 		    hdev->le_scan_type == LE_SCAN_ACTIVE) {
-			skb_queue_purge(&req.cmd_q);
+			hci_req_purge(&req);
 			hci_conn_del(conn);
 			return ERR_PTR(-EBUSY);
 		}
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 6bc679cd3481..40d260f2bea5 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -267,7 +267,7 @@ static int hci_init1_req(struct hci_request *req, unsigned long opt)
 		amp_init1(req);
 		break;
 	default:
-		BT_ERR("Unknown device type %d", hdev->dev_type);
+		bt_dev_err(hdev, "Unknown device type %d", hdev->dev_type);
 		break;
 	}
 
@@ -2150,8 +2150,7 @@ static void hci_error_reset(struct work_struct *work)
 	if (hdev->hw_error)
 		hdev->hw_error(hdev, hdev->hw_error_code);
 	else
-		BT_ERR("%s hardware error 0x%2.2x", hdev->name,
-		       hdev->hw_error_code);
+		bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code);
 
 	if (hci_dev_do_close(hdev))
 		return;
@@ -2524,9 +2523,9 @@ static void hci_cmd_timeout(struct work_struct *work)
 		struct hci_command_hdr *sent = (void *) hdev->sent_cmd->data;
 		u16 opcode = __le16_to_cpu(sent->opcode);
 
-		BT_ERR("%s command 0x%4.4x tx timeout", hdev->name, opcode);
+		bt_dev_err(hdev, "command 0x%4.4x tx timeout", opcode);
 	} else {
-		BT_ERR("%s command tx timeout", hdev->name);
+		bt_dev_err(hdev, "command tx timeout");
 	}
 
 	atomic_set(&hdev->cmd_cnt, 1);
@@ -2858,7 +2857,7 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev,
 
 	params = kzalloc(sizeof(*params), GFP_KERNEL);
 	if (!params) {
-		BT_ERR("Out of memory");
+		bt_dev_err(hdev, "out of memory");
 		return NULL;
 	}
 
@@ -3393,7 +3392,7 @@ static void hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 
 	err = hdev->send(hdev, skb);
 	if (err < 0) {
-		BT_ERR("%s sending frame failed (%d)", hdev->name, err);
+		bt_dev_err(hdev, "sending frame failed (%d)", err);
 		kfree_skb(skb);
 	}
 }
@@ -3408,7 +3407,7 @@ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen,
 
 	skb = hci_prepare_cmd(hdev, opcode, plen, param);
 	if (!skb) {
-		BT_ERR("%s no memory for command", hdev->name);
+		bt_dev_err(hdev, "no memory for command");
 		return -ENOMEM;
 	}
 
@@ -3493,7 +3492,7 @@ static void hci_queue_acl(struct hci_chan *chan, struct sk_buff_head *queue,
 		hci_add_acl_hdr(skb, chan->handle, flags);
 		break;
 	default:
-		BT_ERR("%s unknown dev_type %d", hdev->name, hdev->dev_type);
+		bt_dev_err(hdev, "unknown dev_type %d", hdev->dev_type);
 		return;
 	}
 
@@ -3618,7 +3617,7 @@ static struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type,
 			break;
 		default:
 			cnt = 0;
-			BT_ERR("Unknown link type");
+			bt_dev_err(hdev, "unknown link type %d", conn->type);
 		}
 
 		q = cnt / num;
@@ -3635,15 +3634,15 @@ static void hci_link_tx_to(struct hci_dev *hdev, __u8 type)
 	struct hci_conn_hash *h = &hdev->conn_hash;
 	struct hci_conn *c;
 
-	BT_ERR("%s link tx timeout", hdev->name);
+	bt_dev_err(hdev, "link tx timeout");
 
 	rcu_read_lock();
 
 	/* Kill stalled connections */
 	list_for_each_entry_rcu(c, &h->list, list) {
 		if (c->type == type && c->sent) {
-			BT_ERR("%s killing stalled connection %pMR",
-			       hdev->name, &c->dst);
+			bt_dev_err(hdev, "killing stalled connection %pMR",
+				   &c->dst);
 			hci_disconnect(c, HCI_ERROR_REMOTE_USER_TERM);
 		}
 	}
@@ -3724,7 +3723,7 @@ static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type,
 		break;
 	default:
 		cnt = 0;
-		BT_ERR("Unknown link type");
+		bt_dev_err(hdev, "unknown link type %d", chan->conn->type);
 	}
 
 	q = cnt / num;
@@ -4066,8 +4065,8 @@ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		l2cap_recv_acldata(conn, skb, flags);
 		return;
 	} else {
-		BT_ERR("%s ACL packet for unknown connection handle %d",
-		       hdev->name, handle);
+		bt_dev_err(hdev, "ACL packet for unknown connection handle %d",
+			   handle);
 	}
 
 	kfree_skb(skb);
@@ -4097,8 +4096,8 @@ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		sco_recv_scodata(conn, skb);
 		return;
 	} else {
-		BT_ERR("%s SCO packet for unknown connection handle %d",
-		       hdev->name, handle);
+		bt_dev_err(hdev, "SCO packet for unknown connection handle %d",
+			   handle);
 	}
 
 	kfree_skb(skb);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0b4dba08a14e..cd3bbb766c24 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1188,7 +1188,8 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
 		break;
 
 	default:
-		BT_ERR("Used reserved LE_Scan_Enable param %d", cp->enable);
+		bt_dev_err(hdev, "use of reserved LE_Scan_Enable param %d",
+			   cp->enable);
 		break;
 	}
 
@@ -1485,7 +1486,7 @@ static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status)
 			conn = hci_conn_add(hdev, ACL_LINK, &cp->bdaddr,
 					    HCI_ROLE_MASTER);
 			if (!conn)
-				BT_ERR("No memory for new connection");
+				bt_dev_err(hdev, "no memory for new connection");
 		}
 	}
 
@@ -2269,7 +2270,7 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr,
 				    HCI_ROLE_SLAVE);
 		if (!conn) {
-			BT_ERR("No memory for new connection");
+			bt_dev_err(hdev, "no memory for new connection");
 			hci_dev_unlock(hdev);
 			return;
 		}
@@ -2431,7 +2432,7 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 		if (!hci_conn_ssp_enabled(conn) &&
 		    test_bit(HCI_CONN_REAUTH_PEND, &conn->flags)) {
-			BT_INFO("re-auth of legacy device is not possible.");
+			bt_dev_info(hdev, "re-auth of legacy device is not possible.");
 		} else {
 			set_bit(HCI_CONN_AUTH, &conn->flags);
 			conn->sec_level = conn->pending_sec_level;
@@ -2535,8 +2536,7 @@ static void read_enc_key_size_complete(struct hci_dev *hdev, u8 status,
 	BT_DBG("%s status 0x%02x", hdev->name, status);
 
 	if (!skb || skb->len < sizeof(*rp)) {
-		BT_ERR("%s invalid HCI Read Encryption Key Size response",
-		       hdev->name);
+		bt_dev_err(hdev, "invalid read key size response");
 		return;
 	}
 
@@ -2554,8 +2554,8 @@ static void read_enc_key_size_complete(struct hci_dev *hdev, u8 status,
 	 * supported.
 	 */
 	if (rp->status) {
-		BT_ERR("%s failed to read key size for handle %u", hdev->name,
-		       handle);
+		bt_dev_err(hdev, "failed to read key size for handle %u",
+			   handle);
 		conn->enc_key_size = HCI_LINK_KEY_SIZE;
 	} else {
 		conn->enc_key_size = rp->key_size;
@@ -2664,7 +2664,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_req_add(&req, HCI_OP_READ_ENC_KEY_SIZE, sizeof(cp), &cp);
 
 		if (hci_req_run_skb(&req, read_enc_key_size_complete)) {
-			BT_ERR("Sending HCI Read Encryption Key Size failed");
+			bt_dev_err(hdev, "sending read key size failed");
 			conn->enc_key_size = HCI_LINK_KEY_SIZE;
 			goto notify;
 		}
@@ -3197,7 +3197,7 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	int i;
 
 	if (hdev->flow_ctl_mode != HCI_FLOW_CTL_MODE_PACKET_BASED) {
-		BT_ERR("Wrong event for mode %d", hdev->flow_ctl_mode);
+		bt_dev_err(hdev, "wrong event for mode %d", hdev->flow_ctl_mode);
 		return;
 	}
 
@@ -3249,7 +3249,8 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *skb)
 			break;
 
 		default:
-			BT_ERR("Unknown type %d conn %p", conn->type, conn);
+			bt_dev_err(hdev, "unknown type %d conn %p",
+				   conn->type, conn);
 			break;
 		}
 	}
@@ -3271,7 +3272,7 @@ static struct hci_conn *__hci_conn_lookup_handle(struct hci_dev *hdev,
 			return chan->conn;
 		break;
 	default:
-		BT_ERR("%s unknown dev_type %d", hdev->name, hdev->dev_type);
+		bt_dev_err(hdev, "unknown dev_type %d", hdev->dev_type);
 		break;
 	}
 
@@ -3284,7 +3285,7 @@ static void hci_num_comp_blocks_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	int i;
 
 	if (hdev->flow_ctl_mode != HCI_FLOW_CTL_MODE_BLOCK_BASED) {
-		BT_ERR("Wrong event for mode %d", hdev->flow_ctl_mode);
+		bt_dev_err(hdev, "wrong event for mode %d", hdev->flow_ctl_mode);
 		return;
 	}
 
@@ -3320,7 +3321,8 @@ static void hci_num_comp_blocks_evt(struct hci_dev *hdev, struct sk_buff *skb)
 			break;
 
 		default:
-			BT_ERR("Unknown type %d conn %p", conn->type, conn);
+			bt_dev_err(hdev, "unknown type %d conn %p",
+				   conn->type, conn);
 			break;
 		}
 	}
@@ -4479,7 +4481,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	if (!conn) {
 		conn = hci_conn_add(hdev, LE_LINK, &ev->bdaddr, ev->role);
 		if (!conn) {
-			BT_ERR("No memory for new connection");
+			bt_dev_err(hdev, "no memory for new connection");
 			goto unlock;
 		}
 
@@ -4749,8 +4751,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 	case LE_ADV_SCAN_RSP:
 		break;
 	default:
-		BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x",
-				   type);
+		bt_dev_err_ratelimited(hdev, "unknown advertising packet "
+				       "type: 0x%02x", type);
 		return;
 	}
 
@@ -4769,8 +4771,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 
 	/* Adjust for actual length */
 	if (len != real_len) {
-		BT_ERR_RATELIMITED("%s advertising data length corrected",
-				   hdev->name);
+		bt_dev_err_ratelimited(hdev, "advertising data len corrected");
 		len = real_len;
 	}
 
@@ -5192,7 +5193,7 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode,
 		return false;
 
 	if (skb->len < sizeof(*hdr)) {
-		BT_ERR("Too short HCI event");
+		bt_dev_err(hdev, "too short HCI event");
 		return false;
 	}
 
@@ -5206,12 +5207,13 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode,
 	}
 
 	if (hdr->evt != HCI_EV_CMD_COMPLETE) {
-		BT_DBG("Last event is not cmd complete (0x%2.2x)", hdr->evt);
+		bt_dev_err(hdev, "last event is not cmd complete (0x%2.2x)",
+			   hdr->evt);
 		return false;
 	}
 
 	if (skb->len < sizeof(*ev)) {
-		BT_ERR("Too short cmd_complete event");
+		bt_dev_err(hdev, "too short cmd_complete event");
 		return false;
 	}
 
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index b73ac149de34..abc0f3224dd1 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -41,6 +41,11 @@ void hci_req_init(struct hci_request *req, struct hci_dev *hdev)
 	req->err = 0;
 }
 
+void hci_req_purge(struct hci_request *req)
+{
+	skb_queue_purge(&req->cmd_q);
+}
+
 static int req_run(struct hci_request *req, hci_req_complete_t complete,
 		   hci_req_complete_skb_t complete_skb)
 {
@@ -331,8 +336,8 @@ void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen,
 
 	skb = hci_prepare_cmd(hdev, opcode, plen, param);
 	if (!skb) {
-		BT_ERR("%s no memory for command (opcode 0x%4.4x)",
-		       hdev->name, opcode);
+		bt_dev_err(hdev, "no memory for command (opcode 0x%4.4x)",
+			   opcode);
 		req->err = -ENOMEM;
 		return;
 	}
@@ -1421,7 +1426,7 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy,
 
 		err = smp_generate_rpa(hdev, hdev->irk, &hdev->rpa);
 		if (err < 0) {
-			BT_ERR("%s failed to generate new RPA", hdev->name);
+			bt_dev_err(hdev, "failed to generate new RPA");
 			return err;
 		}
 
@@ -1783,7 +1788,7 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason)
 
 	err = hci_req_run(&req, abort_conn_complete);
 	if (err && err != -ENODATA) {
-		BT_ERR("Failed to run HCI request: err %d", err);
+		bt_dev_err(conn->hdev, "failed to run HCI request: err %d", err);
 		return err;
 	}
 
@@ -1867,7 +1872,8 @@ static void le_scan_disable_work(struct work_struct *work)
 
 	hci_req_sync(hdev, le_scan_disable, 0, HCI_CMD_TIMEOUT, &status);
 	if (status) {
-		BT_ERR("Failed to disable LE scan: status 0x%02x", status);
+		bt_dev_err(hdev, "failed to disable LE scan: status 0x%02x",
+			   status);
 		return;
 	}
 
@@ -1898,7 +1904,7 @@ static void le_scan_disable_work(struct work_struct *work)
 	hci_req_sync(hdev, bredr_inquiry, DISCOV_INTERLEAVED_INQUIRY_LEN,
 		     HCI_CMD_TIMEOUT, &status);
 	if (status) {
-		BT_ERR("Inquiry failed: status 0x%02x", status);
+		bt_dev_err(hdev, "inquiry failed: status 0x%02x", status);
 		goto discov_stopped;
 	}
 
@@ -1940,7 +1946,8 @@ static void le_scan_restart_work(struct work_struct *work)
 
 	hci_req_sync(hdev, le_scan_restart, 0, HCI_CMD_TIMEOUT, &status);
 	if (status) {
-		BT_ERR("Failed to restart LE scan: status %d", status);
+		bt_dev_err(hdev, "failed to restart LE scan: status %d",
+			   status);
 		return;
 	}
 
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
index dde77bd59f91..702beb140d9f 100644
--- a/net/bluetooth/hci_request.h
+++ b/net/bluetooth/hci_request.h
@@ -36,6 +36,7 @@ struct hci_request {
 };
 
 void hci_req_init(struct hci_request *req, struct hci_dev *hdev);
+void hci_req_purge(struct hci_request *req);
 int hci_req_run(struct hci_request *req, hci_req_complete_t complete);
 int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete);
 void hci_req_add(struct hci_request *req, u16 opcode, u32 plen,
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 65d734c165bd..923e9a271872 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -251,15 +251,13 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
 }
 
 /* Send frame to sockets with specific channel */
-void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
-			 int flag, struct sock *skip_sk)
+static void __hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
+				  int flag, struct sock *skip_sk)
 {
 	struct sock *sk;
 
 	BT_DBG("channel %u len %d", channel, skb->len);
 
-	read_lock(&hci_sk_list.lock);
-
 	sk_for_each(sk, &hci_sk_list.head) {
 		struct sk_buff *nskb;
 
@@ -285,6 +283,13 @@ void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
 			kfree_skb(nskb);
 	}
 
+}
+
+void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
+			 int flag, struct sock *skip_sk)
+{
+	read_lock(&hci_sk_list.lock);
+	__hci_send_to_channel(channel, skb, flag, skip_sk);
 	read_unlock(&hci_sk_list.lock);
 }
 
@@ -388,8 +393,8 @@ void hci_send_monitor_ctrl_event(struct hci_dev *hdev, u16 event,
 		hdr->index = index;
 		hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE);
 
-		hci_send_to_channel(HCI_CHANNEL_MONITOR, skb,
-				    HCI_SOCK_TRUSTED, NULL);
+		__hci_send_to_channel(HCI_CHANNEL_MONITOR, skb,
+				      HCI_SOCK_TRUSTED, NULL);
 		kfree_skb(skb);
 	}
 
diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index d5c7c89ec4d6..9874844a95a9 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -51,7 +51,7 @@ void hci_conn_add_sysfs(struct hci_conn *conn)
 	dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle);
 
 	if (device_add(&conn->dev) < 0) {
-		BT_ERR("Failed to register connection device");
+		bt_dev_err(hdev, "failed to register connection device");
 		return;
 	}
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 1fba2a03f8ae..6e9fc86d8daf 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2159,8 +2159,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	key_count = __le16_to_cpu(cp->key_count);
 	if (key_count > max_key_count) {
-		BT_ERR("load_link_keys: too big key_count value %u",
-		       key_count);
+		bt_dev_err(hdev, "load_link_keys: too big key_count value %u",
+			   key_count);
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
 				       MGMT_STATUS_INVALID_PARAMS);
 	}
@@ -2168,8 +2168,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 	expected_len = sizeof(*cp) + key_count *
 					sizeof(struct mgmt_link_key_info);
 	if (expected_len != len) {
-		BT_ERR("load_link_keys: expected %u bytes, got %u bytes",
-		       expected_len, len);
+		bt_dev_err(hdev, "load_link_keys: expected %u bytes, got %u bytes",
+			   expected_len, len);
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
 				       MGMT_STATUS_INVALID_PARAMS);
 	}
@@ -2561,7 +2561,7 @@ static int pin_code_reply(struct sock *sk, struct hci_dev *hdev, void *data,
 
 		memcpy(&ncp.addr, &cp->addr, sizeof(ncp.addr));
 
-		BT_ERR("PIN code is not 16 bytes long");
+		bt_dev_err(hdev, "PIN code is not 16 bytes long");
 
 		err = send_pin_code_neg_reply(sk, hdev, &ncp);
 		if (err >= 0)
@@ -3391,7 +3391,8 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
 					MGMT_OP_ADD_REMOTE_OOB_DATA,
 					status, &cp->addr, sizeof(cp->addr));
 	} else {
-		BT_ERR("add_remote_oob_data: invalid length of %u bytes", len);
+		bt_dev_err(hdev, "add_remote_oob_data: invalid len of %u bytes",
+			   len);
 		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA,
 				      MGMT_STATUS_INVALID_PARAMS);
 	}
@@ -3604,8 +3605,8 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev,
 
 	uuid_count = __le16_to_cpu(cp->uuid_count);
 	if (uuid_count > max_uuid_count) {
-		BT_ERR("service_discovery: too big uuid_count value %u",
-		       uuid_count);
+		bt_dev_err(hdev, "service_discovery: too big uuid_count value %u",
+			   uuid_count);
 		err = mgmt_cmd_complete(sk, hdev->id,
 					MGMT_OP_START_SERVICE_DISCOVERY,
 					MGMT_STATUS_INVALID_PARAMS, &cp->type,
@@ -3615,8 +3616,8 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev,
 
 	expected_len = sizeof(*cp) + uuid_count * 16;
 	if (expected_len != len) {
-		BT_ERR("service_discovery: expected %u bytes, got %u bytes",
-		       expected_len, len);
+		bt_dev_err(hdev, "service_discovery: expected %u bytes, got %u bytes",
+			   expected_len, len);
 		err = mgmt_cmd_complete(sk, hdev->id,
 					MGMT_OP_START_SERVICE_DISCOVERY,
 					MGMT_STATUS_INVALID_PARAMS, &cp->type,
@@ -3943,7 +3944,7 @@ static void set_advertising_complete(struct hci_dev *hdev, u8 status,
 		err = hci_req_run(&req, enable_advertising_instance);
 
 	if (err)
-		BT_ERR("Failed to re-configure advertising");
+		bt_dev_err(hdev, "failed to re-configure advertising");
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -4664,15 +4665,16 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 
 	irk_count = __le16_to_cpu(cp->irk_count);
 	if (irk_count > max_irk_count) {
-		BT_ERR("load_irks: too big irk_count value %u", irk_count);
+		bt_dev_err(hdev, "load_irks: too big irk_count value %u",
+			   irk_count);
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS,
 				       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	expected_len = sizeof(*cp) + irk_count * sizeof(struct mgmt_irk_info);
 	if (expected_len != len) {
-		BT_ERR("load_irks: expected %u bytes, got %u bytes",
-		       expected_len, len);
+		bt_dev_err(hdev, "load_irks: expected %u bytes, got %u bytes",
+			   expected_len, len);
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS,
 				       MGMT_STATUS_INVALID_PARAMS);
 	}
@@ -4745,7 +4747,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 
 	key_count = __le16_to_cpu(cp->key_count);
 	if (key_count > max_key_count) {
-		BT_ERR("load_ltks: too big key_count value %u", key_count);
+		bt_dev_err(hdev, "load_ltks: too big key_count value %u",
+			   key_count);
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS,
 				       MGMT_STATUS_INVALID_PARAMS);
 	}
@@ -4753,8 +4756,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 	expected_len = sizeof(*cp) + key_count *
 					sizeof(struct mgmt_ltk_info);
 	if (expected_len != len) {
-		BT_ERR("load_keys: expected %u bytes, got %u bytes",
-		       expected_len, len);
+		bt_dev_err(hdev, "load_keys: expected %u bytes, got %u bytes",
+			   expected_len, len);
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS,
 				       MGMT_STATUS_INVALID_PARAMS);
 	}
@@ -4873,14 +4876,15 @@ static void conn_info_refresh_complete(struct hci_dev *hdev, u8 hci_status,
 	}
 
 	if (!cp) {
-		BT_ERR("invalid sent_cmd in conn_info response");
+		bt_dev_err(hdev, "invalid sent_cmd in conn_info response");
 		goto unlock;
 	}
 
 	handle = __le16_to_cpu(cp->handle);
 	conn = hci_conn_hash_lookup_handle(hdev, handle);
 	if (!conn) {
-		BT_ERR("unknown handle (%d) in conn_info response", handle);
+		bt_dev_err(hdev, "unknown handle (%d) in conn_info response",
+			   handle);
 		goto unlock;
 	}
 
@@ -5477,8 +5481,8 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	param_count = __le16_to_cpu(cp->param_count);
 	if (param_count > max_param_count) {
-		BT_ERR("load_conn_param: too big param_count value %u",
-		       param_count);
+		bt_dev_err(hdev, "load_conn_param: too big param_count value %u",
+			   param_count);
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM,
 				       MGMT_STATUS_INVALID_PARAMS);
 	}
@@ -5486,8 +5490,8 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data,
 	expected_len = sizeof(*cp) + param_count *
 					sizeof(struct mgmt_conn_param);
 	if (expected_len != len) {
-		BT_ERR("load_conn_param: expected %u bytes, got %u bytes",
-		       expected_len, len);
+		bt_dev_err(hdev, "load_conn_param: expected %u bytes, got %u bytes",
+			   expected_len, len);
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM,
 				       MGMT_STATUS_INVALID_PARAMS);
 	}
@@ -5512,7 +5516,7 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data,
 		} else if (param->addr.type == BDADDR_LE_RANDOM) {
 			addr_type = ADDR_LE_DEV_RANDOM;
 		} else {
-			BT_ERR("Ignoring invalid connection parameters");
+			bt_dev_err(hdev, "ignoring invalid connection parameters");
 			continue;
 		}
 
@@ -5525,14 +5529,14 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data,
 		       min, max, latency, timeout);
 
 		if (hci_check_conn_params(min, max, latency, timeout) < 0) {
-			BT_ERR("Ignoring invalid connection parameters");
+			bt_dev_err(hdev, "ignoring invalid connection parameters");
 			continue;
 		}
 
 		hci_param = hci_conn_params_add(hdev, &param->addr.bdaddr,
 						addr_type);
 		if (!hci_param) {
-			BT_ERR("Failed to add connection parameters");
+			bt_dev_err(hdev, "failed to add connection parameters");
 			continue;
 		}
 
@@ -6383,6 +6387,7 @@ static int remove_advertising(struct sock *sk, struct hci_dev *hdev,
 	if (skb_queue_empty(&req.cmd_q) ||
 	    !hdev_is_powered(hdev) ||
 	    hci_dev_test_flag(hdev, HCI_ADVERTISING)) {
+		hci_req_purge(&req);
 		rp.instance = cp->instance;
 		err = mgmt_cmd_complete(sk, hdev->id,
 					MGMT_OP_REMOVE_ADVERTISING,
diff --git a/net/bluetooth/selftest.c b/net/bluetooth/selftest.c
index 34a1227f4391..03e3c89c3046 100644
--- a/net/bluetooth/selftest.c
+++ b/net/bluetooth/selftest.c
@@ -138,12 +138,12 @@ static const u8 dhkey_3[32] __initconst = {
 	0x7c, 0x1c, 0xf9, 0x49, 0xe6, 0xd7, 0xaa, 0x70,
 };
 
-static int __init test_ecdh_sample(const u8 priv_a[32], const u8 priv_b[32],
-				   const u8 pub_a[64], const u8 pub_b[64],
-				   const u8 dhkey[32])
+static int __init test_ecdh_sample(struct crypto_kpp *tfm, const u8 priv_a[32],
+				   const u8 priv_b[32], const u8 pub_a[64],
+				   const u8 pub_b[64], const u8 dhkey[32])
 {
 	u8 *tmp, *dhkey_a, *dhkey_b;
-	int ret = 0;
+	int ret;
 
 	tmp = kmalloc(64, GFP_KERNEL);
 	if (!tmp)
@@ -152,17 +152,30 @@ static int __init test_ecdh_sample(const u8 priv_a[32], const u8 priv_b[32],
 	dhkey_a = &tmp[0];
 	dhkey_b = &tmp[32];
 
-	compute_ecdh_secret(pub_b, priv_a, dhkey_a);
-	compute_ecdh_secret(pub_a, priv_b, dhkey_b);
+	ret = set_ecdh_privkey(tfm, priv_a);
+	if (ret)
+		goto out;
+
+	ret = compute_ecdh_secret(tfm, pub_b, dhkey_a);
+	if (ret)
+		goto out;
 
 	if (memcmp(dhkey_a, dhkey, 32)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
+	ret = set_ecdh_privkey(tfm, priv_b);
+	if (ret)
+		goto out;
+
+	ret = compute_ecdh_secret(tfm, pub_a, dhkey_b);
+	if (ret)
+		goto out;
+
 	if (memcmp(dhkey_b, dhkey, 32))
 		ret = -EINVAL;
-
+	/* fall through*/
 out:
 	kfree(tmp);
 	return ret;
@@ -185,30 +198,43 @@ static const struct file_operations test_ecdh_fops = {
 
 static int __init test_ecdh(void)
 {
+	struct crypto_kpp *tfm;
 	ktime_t calltime, delta, rettime;
-	unsigned long long duration;
+	unsigned long long duration = 0;
 	int err;
 
 	calltime = ktime_get();
 
-	err = test_ecdh_sample(priv_a_1, priv_b_1, pub_a_1, pub_b_1, dhkey_1);
+	tfm = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
+	if (IS_ERR(tfm)) {
+		BT_ERR("Unable to create ECDH crypto context");
+		err = PTR_ERR(tfm);
+		goto done;
+	}
+
+	err = test_ecdh_sample(tfm, priv_a_1, priv_b_1, pub_a_1, pub_b_1,
+			       dhkey_1);
 	if (err) {
 		BT_ERR("ECDH sample 1 failed");
 		goto done;
 	}
 
-	err = test_ecdh_sample(priv_a_2, priv_b_2, pub_a_2, pub_b_2, dhkey_2);
+	err = test_ecdh_sample(tfm, priv_a_2, priv_b_2, pub_a_2, pub_b_2,
+			       dhkey_2);
 	if (err) {
 		BT_ERR("ECDH sample 2 failed");
 		goto done;
 	}
 
-	err = test_ecdh_sample(priv_a_3, priv_a_3, pub_a_3, pub_a_3, dhkey_3);
+	err = test_ecdh_sample(tfm, priv_a_3, priv_a_3, pub_a_3, pub_a_3,
+			       dhkey_3);
 	if (err) {
 		BT_ERR("ECDH sample 3 failed");
 		goto done;
 	}
 
+	crypto_free_kpp(tfm);
+
 	rettime = ktime_get();
 	delta = ktime_sub(rettime, calltime);
 	duration = (unsigned long long) ktime_to_ns(delta) >> 10;
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index a0ef89772c36..01117ae84f1d 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -26,6 +26,7 @@
 #include <crypto/algapi.h>
 #include <crypto/b128ops.h>
 #include <crypto/hash.h>
+#include <crypto/kpp.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@@ -83,7 +84,6 @@ enum {
 struct smp_dev {
 	/* Secure Connections OOB data */
 	u8			local_pk[64];
-	u8			local_sk[32];
 	u8			local_rand[16];
 	bool			debug_key;
 
@@ -92,6 +92,7 @@ struct smp_dev {
 
 	struct crypto_cipher	*tfm_aes;
 	struct crypto_shash	*tfm_cmac;
+	struct crypto_kpp	*tfm_ecdh;
 };
 
 struct smp_chan {
@@ -124,13 +125,13 @@ struct smp_chan {
 
 	/* Secure Connections variables */
 	u8			local_pk[64];
-	u8			local_sk[32];
 	u8			remote_pk[64];
 	u8			dhkey[32];
 	u8			mackey[16];
 
 	struct crypto_cipher	*tfm_aes;
 	struct crypto_shash	*tfm_cmac;
+	struct crypto_kpp	*tfm_ecdh;
 };
 
 /* These debug key values are defined in the SMP section of the core
@@ -565,22 +566,22 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16])
 
 	if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) {
 		BT_DBG("Using debug keys");
+		err = set_ecdh_privkey(smp->tfm_ecdh, debug_sk);
+		if (err)
+			return err;
 		memcpy(smp->local_pk, debug_pk, 64);
-		memcpy(smp->local_sk, debug_sk, 32);
 		smp->debug_key = true;
 	} else {
 		while (true) {
-			/* Seed private key with random number */
-			get_random_bytes(smp->local_sk, 32);
-
-			/* Generate local key pair for Secure Connections */
-			if (!generate_ecdh_keys(smp->local_pk, smp->local_sk))
-				return -EIO;
+			/* Generate key pair for Secure Connections */
+			err = generate_ecdh_keys(smp->tfm_ecdh, smp->local_pk);
+			if (err)
+				return err;
 
 			/* This is unlikely, but we need to check that
 			 * we didn't accidentially generate a debug key.
 			 */
-			if (crypto_memneq(smp->local_sk, debug_sk, 32))
+			if (crypto_memneq(smp->local_pk, debug_pk, 64))
 				break;
 		}
 		smp->debug_key = false;
@@ -588,7 +589,6 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16])
 
 	SMP_DBG("OOB Public Key X: %32phN", smp->local_pk);
 	SMP_DBG("OOB Public Key Y: %32phN", smp->local_pk + 32);
-	SMP_DBG("OOB Private Key:  %32phN", smp->local_sk);
 
 	get_random_bytes(smp->local_rand, 16);
 
@@ -771,6 +771,7 @@ static void smp_chan_destroy(struct l2cap_conn *conn)
 
 	crypto_free_cipher(smp->tfm_aes);
 	crypto_free_shash(smp->tfm_cmac);
+	crypto_free_kpp(smp->tfm_ecdh);
 
 	/* Ensure that we don't leave any debug key around if debug key
 	 * support hasn't been explicitly enabled.
@@ -995,7 +996,8 @@ static u8 smp_random(struct smp_chan *smp)
 		return SMP_UNSPECIFIED;
 
 	if (crypto_memneq(smp->pcnf, confirm, sizeof(smp->pcnf))) {
-		BT_ERR("Pairing failed (confirmation values mismatch)");
+		bt_dev_err(hcon->hdev, "pairing failed "
+			   "(confirmation values mismatch)");
 		return SMP_CONFIRM_FAILED;
 	}
 
@@ -1209,7 +1211,7 @@ static void sc_generate_ltk(struct smp_chan *smp)
 
 	key = hci_find_link_key(hdev, &hcon->dst);
 	if (!key) {
-		BT_ERR("%s No Link Key found to generate LTK", hdev->name);
+		bt_dev_err(hdev, "no Link Key found to generate LTK");
 		return;
 	}
 
@@ -1391,16 +1393,19 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 	smp->tfm_aes = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(smp->tfm_aes)) {
 		BT_ERR("Unable to create AES crypto context");
-		kzfree(smp);
-		return NULL;
+		goto zfree_smp;
 	}
 
 	smp->tfm_cmac = crypto_alloc_shash("cmac(aes)", 0, 0);
 	if (IS_ERR(smp->tfm_cmac)) {
 		BT_ERR("Unable to create CMAC crypto context");
-		crypto_free_cipher(smp->tfm_aes);
-		kzfree(smp);
-		return NULL;
+		goto free_cipher;
+	}
+
+	smp->tfm_ecdh = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
+	if (IS_ERR(smp->tfm_ecdh)) {
+		BT_ERR("Unable to create ECDH crypto context");
+		goto free_shash;
 	}
 
 	smp->conn = conn;
@@ -1413,6 +1418,14 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 	hci_conn_hold(conn->hcon);
 
 	return smp;
+
+free_shash:
+	crypto_free_shash(smp->tfm_cmac);
+free_cipher:
+	crypto_free_cipher(smp->tfm_aes);
+zfree_smp:
+	kzfree(smp);
+	return NULL;
 }
 
 static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16])
@@ -1883,7 +1896,6 @@ static u8 sc_send_public_key(struct smp_chan *smp)
 		smp_dev = chan->data;
 
 		memcpy(smp->local_pk, smp_dev->local_pk, 64);
-		memcpy(smp->local_sk, smp_dev->local_sk, 32);
 		memcpy(smp->lr, smp_dev->local_rand, 16);
 
 		if (smp_dev->debug_key)
@@ -1894,22 +1906,20 @@ static u8 sc_send_public_key(struct smp_chan *smp)
 
 	if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) {
 		BT_DBG("Using debug keys");
+		if (set_ecdh_privkey(smp->tfm_ecdh, debug_sk))
+			return SMP_UNSPECIFIED;
 		memcpy(smp->local_pk, debug_pk, 64);
-		memcpy(smp->local_sk, debug_sk, 32);
 		set_bit(SMP_FLAG_DEBUG_KEY, &smp->flags);
 	} else {
 		while (true) {
-			/* Seed private key with random number */
-			get_random_bytes(smp->local_sk, 32);
-
-			/* Generate local key pair for Secure Connections */
-			if (!generate_ecdh_keys(smp->local_pk, smp->local_sk))
+			/* Generate key pair for Secure Connections */
+			if (generate_ecdh_keys(smp->tfm_ecdh, smp->local_pk))
 				return SMP_UNSPECIFIED;
 
 			/* This is unlikely, but we need to check that
 			 * we didn't accidentially generate a debug key.
 			 */
-			if (crypto_memneq(smp->local_sk, debug_sk, 32))
+			if (crypto_memneq(smp->local_pk, debug_pk, 64))
 				break;
 		}
 	}
@@ -1917,7 +1927,6 @@ static u8 sc_send_public_key(struct smp_chan *smp)
 done:
 	SMP_DBG("Local Public Key X: %32phN", smp->local_pk);
 	SMP_DBG("Local Public Key Y: %32phN", smp->local_pk + 32);
-	SMP_DBG("Local Private Key:  %32phN", smp->local_sk);
 
 	smp_send_cmd(smp->conn, SMP_CMD_PUBLIC_KEY, 64, smp->local_pk);
 
@@ -2059,11 +2068,11 @@ static int fixup_sc_false_positive(struct smp_chan *smp)
 		return SMP_UNSPECIFIED;
 
 	if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) {
-		BT_ERR("Refusing SMP SC -> legacy fallback in SC-only mode");
+		bt_dev_err(hdev, "refusing legacy fallback in SC-only mode");
 		return SMP_UNSPECIFIED;
 	}
 
-	BT_ERR("Trying to fall back to legacy SMP");
+	bt_dev_err(hdev, "trying to fall back to legacy SMP");
 
 	req = (void *) &smp->preq[1];
 	rsp = (void *) &smp->prsp[1];
@@ -2074,7 +2083,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp)
 	auth = req->auth_req & AUTH_REQ_MASK(hdev);
 
 	if (tk_request(conn, 0, auth, rsp->io_capability, req->io_capability)) {
-		BT_ERR("Failed to fall back to legacy SMP");
+		bt_dev_err(hdev, "failed to fall back to legacy SMP");
 		return SMP_UNSPECIFIED;
 	}
 
@@ -2347,7 +2356,7 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 
 	chan = conn->smp;
 	if (!chan) {
-		BT_ERR("SMP security requested but not available");
+		bt_dev_err(hcon->hdev, "security requested but not available");
 		return 1;
 	}
 
@@ -2540,7 +2549,7 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn,
 	 */
 	if (!bacmp(&info->bdaddr, BDADDR_ANY) ||
 	    !hci_is_identity_address(&info->bdaddr, info->addr_type)) {
-		BT_ERR("Ignoring IRK with no identity address");
+		bt_dev_err(hcon->hdev, "ignoring IRK with no identity address");
 		goto distribute;
 	}
 
@@ -2645,6 +2654,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
 	struct l2cap_chan *chan = conn->smp;
 	struct smp_chan *smp = chan->data;
 	struct hci_dev *hdev = hcon->hdev;
+	struct crypto_kpp *tfm_ecdh;
 	struct smp_cmd_pairing_confirm cfm;
 	int err;
 
@@ -2677,7 +2687,18 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
 	SMP_DBG("Remote Public Key X: %32phN", smp->remote_pk);
 	SMP_DBG("Remote Public Key Y: %32phN", smp->remote_pk + 32);
 
-	if (!compute_ecdh_secret(smp->remote_pk, smp->local_sk, smp->dhkey))
+	/* Compute the shared secret on the same crypto tfm on which the private
+	 * key was set/generated.
+	 */
+	if (test_bit(SMP_FLAG_LOCAL_OOB, &smp->flags)) {
+		struct smp_dev *smp_dev = chan->data;
+
+		tfm_ecdh = smp_dev->tfm_ecdh;
+	} else {
+		tfm_ecdh = smp->tfm_ecdh;
+	}
+
+	if (compute_ecdh_secret(tfm_ecdh, smp->remote_pk, smp->dhkey))
 		return SMP_UNSPECIFIED;
 
 	SMP_DBG("DHKey %32phN", smp->dhkey);
@@ -2933,8 +2954,8 @@ done:
 	return err;
 
 drop:
-	BT_ERR("%s unexpected SMP command 0x%02x from %pMR", hcon->hdev->name,
-	       code, &hcon->dst);
+	bt_dev_err(hcon->hdev, "unexpected SMP command 0x%02x from %pMR",
+		   code, &hcon->dst);
 	kfree_skb(skb);
 	return 0;
 }
@@ -3001,8 +3022,7 @@ static void bredr_pairing(struct l2cap_chan *chan)
 
 	smp = smp_chan_create(conn);
 	if (!smp) {
-		BT_ERR("%s unable to create SMP context for BR/EDR",
-		       hdev->name);
+		bt_dev_err(hdev, "unable to create SMP context for BR/EDR");
 		return;
 	}
 
@@ -3169,6 +3189,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
 	struct smp_dev *smp;
 	struct crypto_cipher *tfm_aes;
 	struct crypto_shash *tfm_cmac;
+	struct crypto_kpp *tfm_ecdh;
 
 	if (cid == L2CAP_CID_SMP_BREDR) {
 		smp = NULL;
@@ -3194,8 +3215,18 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
 		return ERR_CAST(tfm_cmac);
 	}
 
+	tfm_ecdh = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
+	if (IS_ERR(tfm_ecdh)) {
+		BT_ERR("Unable to create ECDH crypto context");
+		crypto_free_shash(tfm_cmac);
+		crypto_free_cipher(tfm_aes);
+		kzfree(smp);
+		return ERR_CAST(tfm_ecdh);
+	}
+
 	smp->tfm_aes = tfm_aes;
 	smp->tfm_cmac = tfm_cmac;
+	smp->tfm_ecdh = tfm_ecdh;
 	smp->min_key_size = SMP_MIN_ENC_KEY_SIZE;
 	smp->max_key_size = SMP_MAX_ENC_KEY_SIZE;
 
@@ -3205,6 +3236,7 @@ create_chan:
 		if (smp) {
 			crypto_free_cipher(smp->tfm_aes);
 			crypto_free_shash(smp->tfm_cmac);
+			crypto_free_kpp(smp->tfm_ecdh);
 			kzfree(smp);
 		}
 		return ERR_PTR(-ENOMEM);
@@ -3252,6 +3284,7 @@ static void smp_del_chan(struct l2cap_chan *chan)
 		chan->data = NULL;
 		crypto_free_cipher(smp->tfm_aes);
 		crypto_free_shash(smp->tfm_cmac);
+		crypto_free_kpp(smp->tfm_ecdh);
 		kzfree(smp);
 	}
 
@@ -3490,25 +3523,18 @@ void smp_unregister(struct hci_dev *hdev)
 
 #if IS_ENABLED(CONFIG_BT_SELFTEST_SMP)
 
-static inline void swap_digits(u64 *in, u64 *out, unsigned int ndigits)
+static int __init test_debug_key(struct crypto_kpp *tfm_ecdh)
 {
-	int i;
-
-	for (i = 0; i < ndigits; i++)
-		out[i] = __swab64(in[ndigits - 1 - i]);
-}
-
-static int __init test_debug_key(void)
-{
-	u8 pk[64], sk[32];
-
-	swap_digits((u64 *)debug_sk, (u64 *)sk, 4);
+	u8 pk[64];
+	int err;
 
-	if (!generate_ecdh_keys(pk, sk))
-		return -EINVAL;
+	err = set_ecdh_privkey(tfm_ecdh, debug_sk);
+	if (err)
+		return err;
 
-	if (crypto_memneq(sk, debug_sk, 32))
-		return -EINVAL;
+	err = generate_ecdh_public_key(tfm_ecdh, pk);
+	if (err)
+		return err;
 
 	if (crypto_memneq(pk, debug_pk, 64))
 		return -EINVAL;
@@ -3763,7 +3789,8 @@ static const struct file_operations test_smp_fops = {
 };
 
 static int __init run_selftests(struct crypto_cipher *tfm_aes,
-				struct crypto_shash *tfm_cmac)
+				struct crypto_shash *tfm_cmac,
+				struct crypto_kpp *tfm_ecdh)
 {
 	ktime_t calltime, delta, rettime;
 	unsigned long long duration;
@@ -3771,7 +3798,7 @@ static int __init run_selftests(struct crypto_cipher *tfm_aes,
 
 	calltime = ktime_get();
 
-	err = test_debug_key();
+	err = test_debug_key(tfm_ecdh);
 	if (err) {
 		BT_ERR("debug_key test failed");
 		goto done;
@@ -3848,6 +3875,7 @@ int __init bt_selftest_smp(void)
 {
 	struct crypto_cipher *tfm_aes;
 	struct crypto_shash *tfm_cmac;
+	struct crypto_kpp *tfm_ecdh;
 	int err;
 
 	tfm_aes = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC);
@@ -3863,10 +3891,19 @@ int __init bt_selftest_smp(void)
 		return PTR_ERR(tfm_cmac);
 	}
 
-	err = run_selftests(tfm_aes, tfm_cmac);
+	tfm_ecdh = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0);
+	if (IS_ERR(tfm_ecdh)) {
+		BT_ERR("Unable to create ECDH crypto context");
+		crypto_free_shash(tfm_cmac);
+		crypto_free_cipher(tfm_aes);
+		return PTR_ERR(tfm_ecdh);
+	}
+
+	err = run_selftests(tfm_aes, tfm_cmac, tfm_ecdh);
 
 	crypto_free_shash(tfm_cmac);
 	crypto_free_cipher(tfm_aes);
+	crypto_free_kpp(tfm_ecdh);
 
 	return err;
 }
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 6be41a44d688..a86e6687026e 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -133,7 +133,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (is_l2)
 		__skb_push(skb, ETH_HLEN);
 	if (is_direct_pkt_access)
-		bpf_compute_data_end(skb);
+		bpf_compute_data_pointers(skb);
 	retval = bpf_test_run(prog, skb, repeat, &duration);
 	if (!is_l2)
 		__skb_push(skb, ETH_HLEN);
@@ -162,6 +162,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 
 	xdp.data_hard_start = data;
 	xdp.data = data + XDP_PACKET_HEADROOM + NET_IP_ALIGN;
+	xdp.data_meta = xdp.data;
 	xdp.data_end = xdp.data + size;
 
 	retval = bpf_test_run(prog, &xdp, repeat, &duration);
diff --git a/net/bridge/Makefile b/net/bridge/Makefile
index f760e62a672a..ac9ef337f0fa 100644
--- a/net/bridge/Makefile
+++ b/net/bridge/Makefile
@@ -8,7 +8,7 @@ obj-$(CONFIG_BRIDGE) += bridge.o
 bridge-y	:= br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \
 			br_ioctl.o br_stp.o br_stp_bpdu.o \
 			br_stp_if.o br_stp_timer.o br_netlink.o \
-			br_netlink_tunnel.o
+			br_netlink_tunnel.o br_arp_nd_proxy.o
 
 bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o
 
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 1407d1ba7577..6bf06e756df2 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -112,7 +112,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v
 	/* Events that may cause spanning tree to refresh */
 	if (event == NETDEV_CHANGEADDR || event == NETDEV_UP ||
 	    event == NETDEV_CHANGE || event == NETDEV_DOWN)
-		br_ifinfo_notify(RTM_NEWLINK, p);
+		br_ifinfo_notify(RTM_NEWLINK, NULL, p);
 
 	return NOTIFY_DONE;
 }
diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
new file mode 100644
index 000000000000..2cf7716254be
--- /dev/null
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -0,0 +1,469 @@
+/*
+ *  Handle bridge arp/nd proxy/suppress
+ *
+ *  Copyright (C) 2017 Cumulus Networks
+ *  Copyright (c) 2017 Roopa Prabhu <roopa@cumulusnetworks.com>
+ *
+ *  Authors:
+ *	Roopa Prabhu <roopa@cumulusnetworks.com>
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/neighbour.h>
+#include <net/arp.h>
+#include <linux/if_vlan.h>
+#include <linux/inetdevice.h>
+#include <net/addrconf.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ip6_checksum.h>
+#endif
+
+#include "br_private.h"
+
+void br_recalculate_neigh_suppress_enabled(struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+	bool neigh_suppress = false;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (p->flags & BR_NEIGH_SUPPRESS) {
+			neigh_suppress = true;
+			break;
+		}
+	}
+
+	br->neigh_suppress_enabled = neigh_suppress;
+}
+
+#if IS_ENABLED(CONFIG_INET)
+static void br_arp_send(struct net_bridge *br, struct net_bridge_port *p,
+			struct net_device *dev, __be32 dest_ip, __be32 src_ip,
+			const unsigned char *dest_hw,
+			const unsigned char *src_hw,
+			const unsigned char *target_hw,
+			__be16 vlan_proto, u16 vlan_tci)
+{
+	struct net_bridge_vlan_group *vg;
+	struct sk_buff *skb;
+	u16 pvid;
+
+	netdev_dbg(dev, "arp send dev %s dst %pI4 dst_hw %pM src %pI4 src_hw %pM\n",
+		   dev->name, &dest_ip, dest_hw, &src_ip, src_hw);
+
+	if (!vlan_tci) {
+		arp_send(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip,
+			 dest_hw, src_hw, target_hw);
+		return;
+	}
+
+	skb = arp_create(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip,
+			 dest_hw, src_hw, target_hw);
+	if (!skb)
+		return;
+
+	if (p)
+		vg = nbp_vlan_group_rcu(p);
+	else
+		vg = br_vlan_group_rcu(br);
+	pvid = br_get_pvid(vg);
+	if (pvid == (vlan_tci & VLAN_VID_MASK))
+		vlan_tci = 0;
+
+	if (vlan_tci)
+		__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
+
+	if (p) {
+		arp_xmit(skb);
+	} else {
+		skb_reset_mac_header(skb);
+		__skb_pull(skb, skb_network_offset(skb));
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb->pkt_type = PACKET_HOST;
+
+		netif_rx_ni(skb);
+	}
+}
+
+static int br_chk_addr_ip(struct net_device *dev, void *data)
+{
+	__be32 ip = *(__be32 *)data;
+	struct in_device *in_dev;
+	__be32 addr = 0;
+
+	in_dev = __in_dev_get_rcu(dev);
+	if (in_dev)
+		addr = inet_confirm_addr(dev_net(dev), in_dev, 0, ip,
+					 RT_SCOPE_HOST);
+
+	if (addr == ip)
+		return 1;
+
+	return 0;
+}
+
+static bool br_is_local_ip(struct net_device *dev, __be32 ip)
+{
+	if (br_chk_addr_ip(dev, &ip))
+		return true;
+
+	/* check if ip is configured on upper dev */
+	if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &ip))
+		return true;
+
+	return false;
+}
+
+void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
+			      u16 vid, struct net_bridge_port *p)
+{
+	struct net_device *dev = br->dev;
+	struct net_device *vlandev = dev;
+	struct neighbour *n;
+	struct arphdr *parp;
+	u8 *arpptr, *sha;
+	__be32 sip, tip;
+
+	BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
+
+	if ((dev->flags & IFF_NOARP) ||
+	    !pskb_may_pull(skb, arp_hdr_len(dev)))
+		return;
+
+	parp = arp_hdr(skb);
+
+	if (parp->ar_pro != htons(ETH_P_IP) ||
+	    parp->ar_hln != dev->addr_len ||
+	    parp->ar_pln != 4)
+		return;
+
+	arpptr = (u8 *)parp + sizeof(struct arphdr);
+	sha = arpptr;
+	arpptr += dev->addr_len;	/* sha */
+	memcpy(&sip, arpptr, sizeof(sip));
+	arpptr += sizeof(sip);
+	arpptr += dev->addr_len;	/* tha */
+	memcpy(&tip, arpptr, sizeof(tip));
+
+	if (ipv4_is_loopback(tip) ||
+	    ipv4_is_multicast(tip))
+		return;
+
+	if (br->neigh_suppress_enabled) {
+		if (p && (p->flags & BR_NEIGH_SUPPRESS))
+			return;
+		if (ipv4_is_zeronet(sip) || sip == tip) {
+			/* prevent flooding to neigh suppress ports */
+			BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+			return;
+		}
+	}
+
+	if (parp->ar_op != htons(ARPOP_REQUEST))
+		return;
+
+	if (vid != 0) {
+		vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto,
+						   vid);
+		if (!vlandev)
+			return;
+	}
+
+	if (br->neigh_suppress_enabled && br_is_local_ip(vlandev, tip)) {
+		/* its our local ip, so don't proxy reply
+		 * and don't forward to neigh suppress ports
+		 */
+		BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+		return;
+	}
+
+	n = neigh_lookup(&arp_tbl, &tip, vlandev);
+	if (n) {
+		struct net_bridge_fdb_entry *f;
+
+		if (!(n->nud_state & NUD_VALID)) {
+			neigh_release(n);
+			return;
+		}
+
+		f = br_fdb_find_rcu(br, n->ha, vid);
+		if (f) {
+			bool replied = false;
+
+			if ((p && (p->flags & BR_PROXYARP)) ||
+			    (f->dst && (f->dst->flags & (BR_PROXYARP_WIFI |
+							 BR_NEIGH_SUPPRESS)))) {
+				if (!vid)
+					br_arp_send(br, p, skb->dev, sip, tip,
+						    sha, n->ha, sha, 0, 0);
+				else
+					br_arp_send(br, p, skb->dev, sip, tip,
+						    sha, n->ha, sha,
+						    skb->vlan_proto,
+						    skb_vlan_tag_get(skb));
+				replied = true;
+			}
+
+			/* If we have replied or as long as we know the
+			 * mac, indicate to arp replied
+			 */
+			if (replied || br->neigh_suppress_enabled)
+				BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+		}
+
+		neigh_release(n);
+	}
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *msg)
+{
+	struct nd_msg *m;
+
+	m = skb_header_pointer(skb, skb_network_offset(skb) +
+			       sizeof(struct ipv6hdr), sizeof(*msg), msg);
+	if (!m)
+		return NULL;
+
+	if (m->icmph.icmp6_code != 0 ||
+	    (m->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION &&
+	     m->icmph.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT))
+		return NULL;
+
+	return m;
+}
+
+static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
+		       struct sk_buff *request, struct neighbour *n,
+		       __be16 vlan_proto, u16 vlan_tci, struct nd_msg *ns)
+{
+	struct net_device *dev = request->dev;
+	struct net_bridge_vlan_group *vg;
+	struct sk_buff *reply;
+	struct nd_msg *na;
+	struct ipv6hdr *pip6;
+	int na_olen = 8; /* opt hdr + ETH_ALEN for target */
+	int ns_olen;
+	int i, len;
+	u8 *daddr;
+	u16 pvid;
+
+	if (!dev)
+		return;
+
+	len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
+		sizeof(*na) + na_olen + dev->needed_tailroom;
+
+	reply = alloc_skb(len, GFP_ATOMIC);
+	if (!reply)
+		return;
+
+	reply->protocol = htons(ETH_P_IPV6);
+	reply->dev = dev;
+	skb_reserve(reply, LL_RESERVED_SPACE(dev));
+	skb_push(reply, sizeof(struct ethhdr));
+	skb_set_mac_header(reply, 0);
+
+	daddr = eth_hdr(request)->h_source;
+
+	/* Do we need option processing ? */
+	ns_olen = request->len - (skb_network_offset(request) +
+				  sizeof(struct ipv6hdr)) - sizeof(*ns);
+	for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) {
+		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
+			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
+			break;
+		}
+	}
+
+	/* Ethernet header */
+	ether_addr_copy(eth_hdr(reply)->h_dest, daddr);
+	ether_addr_copy(eth_hdr(reply)->h_source, n->ha);
+	eth_hdr(reply)->h_proto = htons(ETH_P_IPV6);
+	reply->protocol = htons(ETH_P_IPV6);
+
+	skb_pull(reply, sizeof(struct ethhdr));
+	skb_set_network_header(reply, 0);
+	skb_put(reply, sizeof(struct ipv6hdr));
+
+	/* IPv6 header */
+	pip6 = ipv6_hdr(reply);
+	memset(pip6, 0, sizeof(struct ipv6hdr));
+	pip6->version = 6;
+	pip6->priority = ipv6_hdr(request)->priority;
+	pip6->nexthdr = IPPROTO_ICMPV6;
+	pip6->hop_limit = 255;
+	pip6->daddr = ipv6_hdr(request)->saddr;
+	pip6->saddr = *(struct in6_addr *)n->primary_key;
+
+	skb_pull(reply, sizeof(struct ipv6hdr));
+	skb_set_transport_header(reply, 0);
+
+	na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen);
+
+	/* Neighbor Advertisement */
+	memset(na, 0, sizeof(*na) + na_olen);
+	na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
+	na->icmph.icmp6_router = 0; /* XXX: should be 1 ? */
+	na->icmph.icmp6_override = 1;
+	na->icmph.icmp6_solicited = 1;
+	na->target = ns->target;
+	ether_addr_copy(&na->opt[2], n->ha);
+	na->opt[0] = ND_OPT_TARGET_LL_ADDR;
+	na->opt[1] = na_olen >> 3;
+
+	na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr,
+						&pip6->daddr,
+						sizeof(*na) + na_olen,
+						IPPROTO_ICMPV6,
+						csum_partial(na, sizeof(*na) + na_olen, 0));
+
+	pip6->payload_len = htons(sizeof(*na) + na_olen);
+
+	skb_push(reply, sizeof(struct ipv6hdr));
+	skb_push(reply, sizeof(struct ethhdr));
+
+	reply->ip_summed = CHECKSUM_UNNECESSARY;
+
+	if (p)
+		vg = nbp_vlan_group_rcu(p);
+	else
+		vg = br_vlan_group_rcu(br);
+	pvid = br_get_pvid(vg);
+	if (pvid == (vlan_tci & VLAN_VID_MASK))
+		vlan_tci = 0;
+
+	if (vlan_tci)
+		__vlan_hwaccel_put_tag(reply, vlan_proto, vlan_tci);
+
+	netdev_dbg(dev, "nd send dev %s dst %pI6 dst_hw %pM src %pI6 src_hw %pM\n",
+		   dev->name, &pip6->daddr, daddr, &pip6->saddr, n->ha);
+
+	if (p) {
+		dev_queue_xmit(reply);
+	} else {
+		skb_reset_mac_header(reply);
+		__skb_pull(reply, skb_network_offset(reply));
+		reply->ip_summed = CHECKSUM_UNNECESSARY;
+		reply->pkt_type = PACKET_HOST;
+
+		netif_rx_ni(reply);
+	}
+}
+
+static int br_chk_addr_ip6(struct net_device *dev, void *data)
+{
+	struct in6_addr *addr = (struct in6_addr *)data;
+
+	if (ipv6_chk_addr(dev_net(dev), addr, dev, 0))
+		return 1;
+
+	return 0;
+}
+
+static bool br_is_local_ip6(struct net_device *dev, struct in6_addr *addr)
+
+{
+	if (br_chk_addr_ip6(dev, addr))
+		return true;
+
+	/* check if ip is configured on upper dev */
+	if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, addr))
+		return true;
+
+	return false;
+}
+
+void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
+		       u16 vid, struct net_bridge_port *p, struct nd_msg *msg)
+{
+	struct net_device *dev = br->dev;
+	struct net_device *vlandev = NULL;
+	struct in6_addr *saddr, *daddr;
+	struct ipv6hdr *iphdr;
+	struct neighbour *n;
+
+	BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
+
+	if (p && (p->flags & BR_NEIGH_SUPPRESS))
+		return;
+
+	if (msg->icmph.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT &&
+	    !msg->icmph.icmp6_solicited) {
+		/* prevent flooding to neigh suppress ports */
+		BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+		return;
+	}
+
+	if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
+		return;
+
+	iphdr = ipv6_hdr(skb);
+	saddr = &iphdr->saddr;
+	daddr = &iphdr->daddr;
+
+	if (ipv6_addr_any(saddr) || !ipv6_addr_cmp(saddr, daddr)) {
+		/* prevent flooding to neigh suppress ports */
+		BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+		return;
+	}
+
+	if (vid != 0) {
+		/* build neigh table lookup on the vlan device */
+		vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto,
+						   vid);
+		if (!vlandev)
+			return;
+	} else {
+		vlandev = dev;
+	}
+
+	if (br_is_local_ip6(vlandev, &msg->target)) {
+		/* its our own ip, so don't proxy reply
+		 * and don't forward to arp suppress ports
+		 */
+		BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+		return;
+	}
+
+	n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, vlandev);
+	if (n) {
+		struct net_bridge_fdb_entry *f;
+
+		if (!(n->nud_state & NUD_VALID)) {
+			neigh_release(n);
+			return;
+		}
+
+		f = br_fdb_find_rcu(br, n->ha, vid);
+		if (f) {
+			bool replied = false;
+
+			if (f->dst && (f->dst->flags & BR_NEIGH_SUPPRESS)) {
+				if (vid != 0)
+					br_nd_send(br, p, skb, n,
+						   skb->vlan_proto,
+						   skb_vlan_tag_get(skb), msg);
+				else
+					br_nd_send(br, p, skb, n, 0, 0, msg);
+				replied = true;
+			}
+
+			/* If we have replied or as long as we know the
+			 * mac, indicate to NEIGH_SUPPRESS ports that we
+			 * have replied
+			 */
+			if (replied || br->neigh_suppress_enabled)
+				BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+		}
+		neigh_release(n);
+	}
+}
+#endif
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index f6b6a92f1c48..af5b8c87f590 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -39,6 +39,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
 	const struct nf_br_ops *nf_ops;
 	const unsigned char *dest;
+	struct ethhdr *eth;
 	u16 vid = 0;
 
 	rcu_read_lock();
@@ -57,11 +58,30 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	BR_INPUT_SKB_CB(skb)->brdev = dev;
 
 	skb_reset_mac_header(skb);
+	eth = eth_hdr(skb);
 	skb_pull(skb, ETH_HLEN);
 
 	if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid))
 		goto out;
 
+	if (IS_ENABLED(CONFIG_INET) &&
+	    (eth->h_proto == htons(ETH_P_ARP) ||
+	     eth->h_proto == htons(ETH_P_RARP)) &&
+	    br->neigh_suppress_enabled) {
+		br_do_proxy_suppress_arp(skb, br, vid, NULL);
+	} else if (IS_ENABLED(CONFIG_IPV6) &&
+		   skb->protocol == htons(ETH_P_IPV6) &&
+		   br->neigh_suppress_enabled &&
+		   pskb_may_pull(skb, sizeof(struct ipv6hdr) +
+				 sizeof(struct nd_msg)) &&
+		   ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
+			struct nd_msg *msg, _msg;
+
+			msg = br_is_nd_neigh_msg(skb, &_msg);
+			if (msg)
+				br_do_suppress_nd(skb, br, vid, NULL, msg);
+	}
+
 	dest = eth_hdr(skb)->h_dest;
 	if (is_broadcast_ether_addr(dest)) {
 		br_flood(br, skb, BR_PKT_BROADCAST, false, true);
@@ -320,12 +340,13 @@ void br_netpoll_disable(struct net_bridge_port *p)
 
 #endif
 
-static int br_add_slave(struct net_device *dev, struct net_device *slave_dev)
+static int br_add_slave(struct net_device *dev, struct net_device *slave_dev,
+			struct netlink_ext_ack *extack)
 
 {
 	struct net_bridge *br = netdev_priv(dev);
 
-	return br_add_if(br, slave_dev);
+	return br_add_if(br, slave_dev, extack);
 }
 
 static int br_del_slave(struct net_device *dev, struct net_device *slave_dev)
@@ -400,7 +421,7 @@ void br_dev_setup(struct net_device *dev)
 	br->bridge_id.prio[0] = 0x80;
 	br->bridge_id.prio[1] = 0x00;
 
-	ether_addr_copy(br->group_addr, eth_reserved_addr_base);
+	ether_addr_copy(br->group_addr, eth_stp_addr);
 
 	br->stp_enabled = BR_NO_STP;
 	br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 48fb17417fac..b4eed113d2ec 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -204,7 +204,7 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
 		/* Do not flood to ports that enable proxy ARP */
 		if (p->flags & BR_PROXYARP)
 			continue;
-		if ((p->flags & BR_PROXYARP_WIFI) &&
+		if ((p->flags & (BR_PROXYARP_WIFI | BR_NEIGH_SUPPRESS)) &&
 		    BR_INPUT_SKB_CB(skb)->proxyarp_replied)
 			continue;
 
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index f3aef22931ab..9ba4ed65c52b 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -271,7 +271,7 @@ static void del_nbp(struct net_bridge_port *p)
 	br_stp_disable_port(p);
 	spin_unlock_bh(&br->lock);
 
-	br_ifinfo_notify(RTM_DELLINK, p);
+	br_ifinfo_notify(RTM_DELLINK, NULL, p);
 
 	list_del_rcu(&p->list);
 	if (netdev_get_fwd_headroom(dev) == br->dev->needed_headroom)
@@ -310,6 +310,8 @@ void br_dev_delete(struct net_device *dev, struct list_head *head)
 		del_nbp(p);
 	}
 
+	br_recalculate_neigh_suppress_enabled(br);
+
 	br_fdb_delete_by_port(br, NULL, 0, 1);
 
 	cancel_delayed_work_sync(&br->gc_work);
@@ -480,7 +482,8 @@ netdev_features_t br_features_recompute(struct net_bridge *br,
 }
 
 /* called with RTNL */
-int br_add_if(struct net_bridge *br, struct net_device *dev)
+int br_add_if(struct net_bridge *br, struct net_device *dev,
+	      struct netlink_ext_ack *extack)
 {
 	struct net_bridge_port *p;
 	int err = 0;
@@ -500,16 +503,22 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 		return -EINVAL;
 
 	/* No bridging of bridges */
-	if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit)
+	if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) {
+		NL_SET_ERR_MSG(extack,
+			       "Can not enslave a bridge to a bridge");
 		return -ELOOP;
+	}
 
 	/* Device is already being bridged */
 	if (br_port_exists(dev))
 		return -EBUSY;
 
 	/* No bridging devices that dislike that (e.g. wireless) */
-	if (dev->priv_flags & IFF_DONT_BRIDGE)
+	if (dev->priv_flags & IFF_DONT_BRIDGE) {
+		NL_SET_ERR_MSG(extack,
+			       "Device does not allow enslaving to a bridge");
 		return -EOPNOTSUPP;
+	}
 
 	p = new_nbp(br, dev);
 	if (IS_ERR(p))
@@ -540,7 +549,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 
 	dev->priv_flags |= IFF_BRIDGE_PORT;
 
-	err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL);
+	err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL, extack);
 	if (err)
 		goto err5;
 
@@ -580,7 +589,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 		br_stp_enable_port(p);
 	spin_unlock_bh(&br->lock);
 
-	br_ifinfo_notify(RTM_NEWLINK, p);
+	br_ifinfo_notify(RTM_NEWLINK, NULL, p);
 
 	if (changed_addr)
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);
@@ -653,4 +662,7 @@ void br_port_flags_change(struct net_bridge_port *p, unsigned long mask)
 
 	if (mask & BR_AUTO_MASK)
 		nbp_update_port_count(br);
+
+	if (mask & BR_NEIGH_SUPPRESS)
+		br_recalculate_neigh_suppress_enabled(br);
 }
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 7637f58c1226..a096d3e189da 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -71,62 +71,6 @@ static int br_pass_frame_up(struct sk_buff *skb)
 		       br_netif_receive_skb);
 }
 
-static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
-			    u16 vid, struct net_bridge_port *p)
-{
-	struct net_device *dev = br->dev;
-	struct neighbour *n;
-	struct arphdr *parp;
-	u8 *arpptr, *sha;
-	__be32 sip, tip;
-
-	BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
-
-	if ((dev->flags & IFF_NOARP) ||
-	    !pskb_may_pull(skb, arp_hdr_len(dev)))
-		return;
-
-	parp = arp_hdr(skb);
-
-	if (parp->ar_pro != htons(ETH_P_IP) ||
-	    parp->ar_op != htons(ARPOP_REQUEST) ||
-	    parp->ar_hln != dev->addr_len ||
-	    parp->ar_pln != 4)
-		return;
-
-	arpptr = (u8 *)parp + sizeof(struct arphdr);
-	sha = arpptr;
-	arpptr += dev->addr_len;	/* sha */
-	memcpy(&sip, arpptr, sizeof(sip));
-	arpptr += sizeof(sip);
-	arpptr += dev->addr_len;	/* tha */
-	memcpy(&tip, arpptr, sizeof(tip));
-
-	if (ipv4_is_loopback(tip) ||
-	    ipv4_is_multicast(tip))
-		return;
-
-	n = neigh_lookup(&arp_tbl, &tip, dev);
-	if (n) {
-		struct net_bridge_fdb_entry *f;
-
-		if (!(n->nud_state & NUD_VALID)) {
-			neigh_release(n);
-			return;
-		}
-
-		f = br_fdb_find_rcu(br, n->ha, vid);
-		if (f && ((p->flags & BR_PROXYARP) ||
-			  (f->dst && (f->dst->flags & BR_PROXYARP_WIFI)))) {
-			arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip,
-				 sha, n->ha, sha);
-			BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
-		}
-
-		neigh_release(n);
-	}
-}
-
 /* note: already called with rcu_read_lock */
 int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
@@ -171,8 +115,22 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 
 	BR_INPUT_SKB_CB(skb)->brdev = br->dev;
 
-	if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP))
-		br_do_proxy_arp(skb, br, vid, p);
+	if (IS_ENABLED(CONFIG_INET) &&
+	    (skb->protocol == htons(ETH_P_ARP) ||
+	     skb->protocol == htons(ETH_P_RARP))) {
+		br_do_proxy_suppress_arp(skb, br, vid, p);
+	} else if (IS_ENABLED(CONFIG_IPV6) &&
+		   skb->protocol == htons(ETH_P_IPV6) &&
+		   br->neigh_suppress_enabled &&
+		   pskb_may_pull(skb, sizeof(struct ipv6hdr) +
+				 sizeof(struct nd_msg)) &&
+		   ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
+			struct nd_msg *msg, _msg;
+
+			msg = br_is_nd_neigh_msg(skb, &_msg);
+			if (msg)
+				br_do_suppress_nd(skb, br, vid, p, msg);
+	}
 
 	switch (pkt_type) {
 	case BR_PKT_MULTICAST:
@@ -289,6 +247,7 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 		 *
 		 * Others reserved for future standardization
 		 */
+		fwd_mask |= p->group_fwd_mask;
 		switch (dest[5]) {
 		case 0x00:	/* Bridge Group Address */
 			/* If STP is turned off,
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index 7970f8540cbb..73b957fd639d 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -98,7 +98,7 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd)
 		return -EINVAL;
 
 	if (isadd)
-		ret = br_add_if(br, dev);
+		ret = br_add_if(br, dev, NULL);
 	else
 		ret = br_del_if(br, dev);
 
@@ -293,7 +293,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 
 	if (!ret) {
 		if (p)
-			br_ifinfo_notify(RTM_NEWLINK, p);
+			br_ifinfo_notify(RTM_NEWLINK, NULL, p);
 		else
 			netdev_state_change(br->dev);
 	}
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 8dc5c8d69bcd..5f7f0e9d446c 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -239,9 +239,9 @@ static void br_multicast_free_group(struct rcu_head *head)
 	kfree(mp);
 }
 
-static void br_multicast_group_expired(unsigned long data)
+static void br_multicast_group_expired(struct timer_list *t)
 {
-	struct net_bridge_mdb_entry *mp = (void *)data;
+	struct net_bridge_mdb_entry *mp = from_timer(mp, t, timer);
 	struct net_bridge *br = mp->br;
 	struct net_bridge_mdb_htable *mdb;
 
@@ -302,9 +302,9 @@ static void br_multicast_del_pg(struct net_bridge *br,
 	WARN_ON(1);
 }
 
-static void br_multicast_port_group_expired(unsigned long data)
+static void br_multicast_port_group_expired(struct timer_list *t)
 {
-	struct net_bridge_port_group *pg = (void *)data;
+	struct net_bridge_port_group *pg = from_timer(pg, t, timer);
 	struct net_bridge *br = pg->port->br;
 
 	spin_lock(&br->multicast_lock);
@@ -701,8 +701,7 @@ rehash:
 
 	mp->br = br;
 	mp->addr = *group;
-	setup_timer(&mp->timer, br_multicast_group_expired,
-		    (unsigned long)mp);
+	timer_setup(&mp->timer, br_multicast_group_expired, 0);
 
 	hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]);
 	mdb->size++;
@@ -729,8 +728,7 @@ struct net_bridge_port_group *br_multicast_new_port_group(
 	p->flags = flags;
 	rcu_assign_pointer(p->next, next);
 	hlist_add_head(&p->mglist, &port->mglist);
-	setup_timer(&p->timer, br_multicast_port_group_expired,
-		    (unsigned long)p);
+	timer_setup(&p->timer, br_multicast_port_group_expired, 0);
 
 	if (src)
 		memcpy(p->eth_addr, src, ETH_ALEN);
@@ -843,9 +841,10 @@ static int br_ip6_multicast_add_group(struct net_bridge *br,
 }
 #endif
 
-static void br_multicast_router_expired(unsigned long data)
+static void br_multicast_router_expired(struct timer_list *t)
 {
-	struct net_bridge_port *port = (void *)data;
+	struct net_bridge_port *port =
+			from_timer(port, t, multicast_router_timer);
 	struct net_bridge *br = port->br;
 
 	spin_lock(&br->multicast_lock);
@@ -859,8 +858,32 @@ out:
 	spin_unlock(&br->multicast_lock);
 }
 
-static void br_multicast_local_router_expired(unsigned long data)
+static void br_mc_router_state_change(struct net_bridge *p,
+				      bool is_mc_router)
 {
+	struct switchdev_attr attr = {
+		.orig_dev = p->dev,
+		.id = SWITCHDEV_ATTR_ID_BRIDGE_MROUTER,
+		.flags = SWITCHDEV_F_DEFER,
+		.u.mrouter = is_mc_router,
+	};
+
+	switchdev_port_attr_set(p->dev, &attr);
+}
+
+static void br_multicast_local_router_expired(struct timer_list *t)
+{
+	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))
+		goto out;
+
+	br_mc_router_state_change(br, false);
+out:
+	spin_unlock(&br->multicast_lock);
 }
 
 static void br_multicast_querier_expired(struct net_bridge *br,
@@ -876,17 +899,17 @@ out:
 	spin_unlock(&br->multicast_lock);
 }
 
-static void br_ip4_multicast_querier_expired(unsigned long data)
+static void br_ip4_multicast_querier_expired(struct timer_list *t)
 {
-	struct net_bridge *br = (void *)data;
+	struct net_bridge *br = from_timer(br, t, ip4_other_query.timer);
 
 	br_multicast_querier_expired(br, &br->ip4_own_query);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static void br_ip6_multicast_querier_expired(unsigned long data)
+static void br_ip6_multicast_querier_expired(struct timer_list *t)
 {
-	struct net_bridge *br = (void *)data;
+	struct net_bridge *br = from_timer(br, t, ip6_other_query.timer);
 
 	br_multicast_querier_expired(br, &br->ip6_own_query);
 }
@@ -987,17 +1010,17 @@ out:
 	spin_unlock(&br->multicast_lock);
 }
 
-static void br_ip4_multicast_port_query_expired(unsigned long data)
+static void br_ip4_multicast_port_query_expired(struct timer_list *t)
 {
-	struct net_bridge_port *port = (void *)data;
+	struct net_bridge_port *port = from_timer(port, t, ip4_own_query.timer);
 
 	br_multicast_port_query_expired(port, &port->ip4_own_query);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static void br_ip6_multicast_port_query_expired(unsigned long data)
+static void br_ip6_multicast_port_query_expired(struct timer_list *t)
 {
-	struct net_bridge_port *port = (void *)data;
+	struct net_bridge_port *port = from_timer(port, t, ip6_own_query.timer);
 
 	br_multicast_port_query_expired(port, &port->ip6_own_query);
 }
@@ -1019,13 +1042,13 @@ int br_multicast_add_port(struct net_bridge_port *port)
 {
 	port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY;
 
-	setup_timer(&port->multicast_router_timer, br_multicast_router_expired,
-		    (unsigned long)port);
-	setup_timer(&port->ip4_own_query.timer,
-		    br_ip4_multicast_port_query_expired, (unsigned long)port);
+	timer_setup(&port->multicast_router_timer,
+		    br_multicast_router_expired, 0);
+	timer_setup(&port->ip4_own_query.timer,
+		    br_ip4_multicast_port_query_expired, 0);
 #if IS_ENABLED(CONFIG_IPV6)
-	setup_timer(&port->ip6_own_query.timer,
-		    br_ip6_multicast_port_query_expired, (unsigned long)port);
+	timer_setup(&port->ip6_own_query.timer,
+		    br_ip6_multicast_port_query_expired, 0);
 #endif
 	br_mc_disabled_update(port->dev, port->br->multicast_disabled);
 
@@ -1364,9 +1387,12 @@ static void br_multicast_mark_router(struct net_bridge *br,
 	unsigned long now = jiffies;
 
 	if (!port) {
-		if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY)
+		if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) {
+			if (!timer_pending(&br->multicast_router_timer))
+				br_mc_router_state_change(br, true);
 			mod_timer(&br->multicast_router_timer,
 				  now + br->multicast_querier_interval);
+		}
 		return;
 	}
 
@@ -1906,17 +1932,17 @@ static void br_multicast_query_expired(struct net_bridge *br,
 	spin_unlock(&br->multicast_lock);
 }
 
-static void br_ip4_multicast_query_expired(unsigned long data)
+static void br_ip4_multicast_query_expired(struct timer_list *t)
 {
-	struct net_bridge *br = (void *)data;
+	struct net_bridge *br = from_timer(br, t, ip4_own_query.timer);
 
 	br_multicast_query_expired(br, &br->ip4_own_query, &br->ip4_querier);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static void br_ip6_multicast_query_expired(unsigned long data)
+static void br_ip6_multicast_query_expired(struct timer_list *t)
 {
-	struct net_bridge *br = (void *)data;
+	struct net_bridge *br = from_timer(br, t, ip6_own_query.timer);
 
 	br_multicast_query_expired(br, &br->ip6_own_query, &br->ip6_querier);
 }
@@ -1951,17 +1977,17 @@ void br_multicast_init(struct net_bridge *br)
 	br->has_ipv6_addr = 1;
 
 	spin_lock_init(&br->multicast_lock);
-	setup_timer(&br->multicast_router_timer,
+	timer_setup(&br->multicast_router_timer,
 		    br_multicast_local_router_expired, 0);
-	setup_timer(&br->ip4_other_query.timer,
-		    br_ip4_multicast_querier_expired, (unsigned long)br);
-	setup_timer(&br->ip4_own_query.timer, br_ip4_multicast_query_expired,
-		    (unsigned long)br);
+	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)
-	setup_timer(&br->ip6_other_query.timer,
-		    br_ip6_multicast_querier_expired, (unsigned long)br);
-	setup_timer(&br->ip6_own_query.timer, br_ip6_multicast_query_expired,
-		    (unsigned long)br);
+	timer_setup(&br->ip6_other_query.timer,
+		    br_ip6_multicast_querier_expired, 0);
+	timer_setup(&br->ip6_own_query.timer,
+		    br_ip6_multicast_query_expired, 0);
 #endif
 }
 
@@ -2042,9 +2068,14 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val)
 	switch (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);
-		/* fall through */
+		br->multicast_router = val;
+		err = 0;
+		break;
 	case MDB_RTR_TYPE_TEMP_QUERY:
+		if (br->multicast_router != MDB_RTR_TYPE_TEMP_QUERY)
+			br_mc_router_state_change(br, false);
 		br->multicast_router = val;
 		err = 0;
 		break;
@@ -2184,6 +2215,18 @@ bool br_multicast_enabled(const struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(br_multicast_enabled);
 
+bool br_multicast_router(const struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	bool is_router;
+
+	spin_lock_bh(&br->multicast_lock);
+	is_router = br_multicast_is_router(br);
+	spin_unlock_bh(&br->multicast_lock);
+	return is_router;
+}
+EXPORT_SYMBOL_GPL(br_multicast_router);
+
 int br_multicast_set_querier(struct net_bridge *br, unsigned long val)
 {
 	unsigned long max_delay;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index de2152730809..67bae0f11c67 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -138,6 +138,7 @@ static inline size_t br_port_info_size(void)
 		+ nla_total_size(1)	/* IFLA_BRPORT_PROXYARP */
 		+ nla_total_size(1)	/* IFLA_BRPORT_PROXYARP_WIFI */
 		+ nla_total_size(1)	/* IFLA_BRPORT_VLAN_TUNNEL */
+		+ nla_total_size(1)	/* IFLA_BRPORT_NEIGH_SUPPRESS */
 		+ nla_total_size(sizeof(struct ifla_bridge_id))	/* IFLA_BRPORT_ROOT_ID */
 		+ nla_total_size(sizeof(struct ifla_bridge_id))	/* IFLA_BRPORT_BRIDGE_ID */
 		+ nla_total_size(sizeof(u16))	/* IFLA_BRPORT_DESIGNATED_PORT */
@@ -152,6 +153,7 @@ static inline size_t br_port_info_size(void)
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 		+ nla_total_size(sizeof(u8))	/* IFLA_BRPORT_MULTICAST_ROUTER */
 #endif
+		+ nla_total_size(sizeof(u16))	/* IFLA_BRPORT_GROUP_FWD_MASK */
 		+ 0;
 }
 
@@ -208,7 +210,10 @@ static int br_port_fill_attrs(struct sk_buff *skb,
 		       p->topology_change_ack) ||
 	    nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) ||
 	    nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags &
-							BR_VLAN_TUNNEL)))
+							BR_VLAN_TUNNEL)) ||
+	    nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) ||
+	    nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS,
+		       !!(p->flags & BR_NEIGH_SUPPRESS)))
 		return -EMSGSIZE;
 
 	timerval = br_timer_value(&p->message_age_timer);
@@ -356,14 +361,14 @@ nla_put_failure:
  * Contains port and master info as well as carrier and bridge state.
  */
 static int br_fill_ifinfo(struct sk_buff *skb,
-			  struct net_bridge_port *port,
+			  const struct net_bridge_port *port,
 			  u32 pid, u32 seq, int event, unsigned int flags,
 			  u32 filter_mask, const struct net_device *dev)
 {
+	u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
 	struct net_bridge *br;
 	struct ifinfomsg *hdr;
 	struct nlmsghdr *nlh;
-	u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
 
 	if (port)
 		br = port->br;
@@ -449,28 +454,36 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-/*
- * Notify listeners of a change in port information
- */
-void br_ifinfo_notify(int event, struct net_bridge_port *port)
+/* Notify listeners of a change in bridge or port information */
+void br_ifinfo_notify(int event, const struct net_bridge *br,
+		      const struct net_bridge_port *port)
 {
-	struct net *net;
+	u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
+	struct net_device *dev;
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
-	u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
+	struct net *net;
+	u16 port_no = 0;
 
-	if (!port)
+	if (WARN_ON(!port && !br))
 		return;
 
-	net = dev_net(port->dev);
-	br_debug(port->br, "port %u(%s) event %d\n",
-		 (unsigned int)port->port_no, port->dev->name, event);
+	if (port) {
+		dev = port->dev;
+		br = port->br;
+		port_no = port->port_no;
+	} else {
+		dev = br->dev;
+	}
+
+	net = dev_net(dev);
+	br_debug(br, "port %u(%s) event %d\n", port_no, dev->name, event);
 
-	skb = nlmsg_new(br_nlmsg_size(port->dev, filter), GFP_ATOMIC);
+	skb = nlmsg_new(br_nlmsg_size(dev, filter), GFP_ATOMIC);
 	if (skb == NULL)
 		goto errout;
 
-	err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, port->dev);
+	err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in br_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -483,7 +496,6 @@ errout:
 	rtnl_set_sk_err(net, RTNLGRP_LINK, err);
 }
 
-
 /*
  * Dump information about all ports, in response to GETLINK
  */
@@ -501,8 +513,9 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 }
 
 static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
-			int cmd, struct bridge_vlan_info *vinfo)
+			int cmd, struct bridge_vlan_info *vinfo, bool *changed)
 {
+	bool curr_change;
 	int err = 0;
 
 	switch (cmd) {
@@ -511,22 +524,27 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
 			/* if the MASTER flag is set this will act on the global
 			 * per-VLAN entry as well
 			 */
-			err = nbp_vlan_add(p, vinfo->vid, vinfo->flags);
-			if (err)
-				break;
+			err = nbp_vlan_add(p, vinfo->vid, vinfo->flags,
+					   &curr_change);
 		} else {
 			vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY;
-			err = br_vlan_add(br, vinfo->vid, vinfo->flags);
+			err = br_vlan_add(br, vinfo->vid, vinfo->flags,
+					  &curr_change);
 		}
+		if (curr_change)
+			*changed = true;
 		break;
 
 	case RTM_DELLINK:
 		if (p) {
-			nbp_vlan_delete(p, vinfo->vid);
-			if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
-				br_vlan_delete(p->br, vinfo->vid);
-		} else {
-			br_vlan_delete(br, vinfo->vid);
+			if (!nbp_vlan_delete(p, vinfo->vid))
+				*changed = true;
+
+			if ((vinfo->flags & BRIDGE_VLAN_INFO_MASTER) &&
+			    !br_vlan_delete(p->br, vinfo->vid))
+				*changed = true;
+		} else if (!br_vlan_delete(br, vinfo->vid)) {
+			*changed = true;
 		}
 		break;
 	}
@@ -537,7 +555,8 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
 static int br_process_vlan_info(struct net_bridge *br,
 				struct net_bridge_port *p, int cmd,
 				struct bridge_vlan_info *vinfo_curr,
-				struct bridge_vlan_info **vinfo_last)
+				struct bridge_vlan_info **vinfo_last,
+				bool *changed)
 {
 	if (!vinfo_curr->vid || vinfo_curr->vid >= VLAN_VID_MASK)
 		return -EINVAL;
@@ -567,7 +586,7 @@ static int br_process_vlan_info(struct net_bridge *br,
 		       sizeof(struct bridge_vlan_info));
 		for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) {
 			tmp_vinfo.vid = v;
-			err = br_vlan_info(br, p, cmd, &tmp_vinfo);
+			err = br_vlan_info(br, p, cmd, &tmp_vinfo, changed);
 			if (err)
 				break;
 		}
@@ -576,13 +595,13 @@ static int br_process_vlan_info(struct net_bridge *br,
 		return err;
 	}
 
-	return br_vlan_info(br, p, cmd, vinfo_curr);
+	return br_vlan_info(br, p, cmd, vinfo_curr, changed);
 }
 
 static int br_afspec(struct net_bridge *br,
 		     struct net_bridge_port *p,
 		     struct nlattr *af_spec,
-		     int cmd)
+		     int cmd, bool *changed)
 {
 	struct bridge_vlan_info *vinfo_curr = NULL;
 	struct bridge_vlan_info *vinfo_last = NULL;
@@ -602,7 +621,8 @@ static int br_afspec(struct net_bridge *br,
 				return err;
 			err = br_process_vlan_tunnel_info(br, p, cmd,
 							  &tinfo_curr,
-							  &tinfo_last);
+							  &tinfo_last,
+							  changed);
 			if (err)
 				return err;
 			break;
@@ -611,7 +631,7 @@ static int br_afspec(struct net_bridge *br,
 				return -EINVAL;
 			vinfo_curr = nla_data(attr);
 			err = br_process_vlan_info(br, p, cmd, vinfo_curr,
-						   &vinfo_last);
+						   &vinfo_last, changed);
 			if (err)
 				return err;
 			break;
@@ -637,6 +657,8 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
 	[IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 },
 	[IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 },
 	[IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 },
+	[IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 },
+	[IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 },
 };
 
 /* Change the state of the port and notify spanning tree */
@@ -773,6 +795,20 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 			return err;
 	}
 #endif
+
+	if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) {
+		u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]);
+
+		if (fwd_mask & BR_GROUPFWD_MACPAUSE)
+			return -EINVAL;
+		p->group_fwd_mask = fwd_mask;
+	}
+
+	err = br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS,
+			       BR_NEIGH_SUPPRESS);
+	if (err)
+		return err;
+
 	br_port_flags_change(p, old_flags ^ p->flags);
 	return 0;
 }
@@ -780,10 +816,12 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 /* Change state and parameters on port. */
 int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
 {
+	struct net_bridge *br = (struct net_bridge *)netdev_priv(dev);
+	struct nlattr *tb[IFLA_BRPORT_MAX + 1];
+	struct net_bridge_port *p;
 	struct nlattr *protinfo;
 	struct nlattr *afspec;
-	struct net_bridge_port *p;
-	struct nlattr *tb[IFLA_BRPORT_MAX + 1];
+	bool changed = false;
 	int err = 0;
 
 	protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO);
@@ -819,15 +857,14 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
 		}
 		if (err)
 			goto out;
+		changed = true;
 	}
 
-	if (afspec) {
-		err = br_afspec((struct net_bridge *)netdev_priv(dev), p,
-				afspec, RTM_SETLINK);
-	}
+	if (afspec)
+		err = br_afspec(br, p, afspec, RTM_SETLINK, &changed);
 
-	if (err == 0)
-		br_ifinfo_notify(RTM_NEWLINK, p);
+	if (changed)
+		br_ifinfo_notify(RTM_NEWLINK, br, p);
 out:
 	return err;
 }
@@ -835,8 +872,10 @@ out:
 /* Delete port information */
 int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
 {
-	struct nlattr *afspec;
+	struct net_bridge *br = (struct net_bridge *)netdev_priv(dev);
 	struct net_bridge_port *p;
+	struct nlattr *afspec;
+	bool changed = false;
 	int err = 0;
 
 	afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
@@ -848,13 +887,12 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
 	if (!p && !(dev->priv_flags & IFF_EBRIDGE))
 		return -EINVAL;
 
-	err = br_afspec((struct net_bridge *)netdev_priv(dev), p,
-			afspec, RTM_DELLINK);
-	if (err == 0)
+	err = br_afspec(br, p, afspec, RTM_DELLINK, &changed);
+	if (changed)
 		/* Send RTM_NEWLINK because userspace
 		 * expects RTM_NEWLINK for vlan dels
 		 */
-		br_ifinfo_notify(RTM_NEWLINK, p);
+		br_ifinfo_notify(RTM_NEWLINK, br, p);
 
 	return err;
 }
diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c
index 3712c7f0e00c..da8cb99fd259 100644
--- a/net/bridge/br_netlink_tunnel.c
+++ b/net/bridge/br_netlink_tunnel.c
@@ -198,7 +198,7 @@ static const struct nla_policy vlan_tunnel_policy[IFLA_BRIDGE_VLAN_TUNNEL_MAX +
 };
 
 static int br_vlan_tunnel_info(struct net_bridge_port *p, int cmd,
-			       u16 vid, u32 tun_id)
+			       u16 vid, u32 tun_id, bool *changed)
 {
 	int err = 0;
 
@@ -208,9 +208,12 @@ static int br_vlan_tunnel_info(struct net_bridge_port *p, int cmd,
 	switch (cmd) {
 	case RTM_SETLINK:
 		err = nbp_vlan_tunnel_info_add(p, vid, tun_id);
+		if (!err)
+			*changed = true;
 		break;
 	case RTM_DELLINK:
-		nbp_vlan_tunnel_info_delete(p, vid);
+		if (!nbp_vlan_tunnel_info_delete(p, vid))
+			*changed = true;
 		break;
 	}
 
@@ -254,7 +257,8 @@ int br_parse_vlan_tunnel_info(struct nlattr *attr,
 int br_process_vlan_tunnel_info(struct net_bridge *br,
 				struct net_bridge_port *p, int cmd,
 				struct vtunnel_info *tinfo_curr,
-				struct vtunnel_info *tinfo_last)
+				struct vtunnel_info *tinfo_last,
+				bool *changed)
 {
 	int err;
 
@@ -272,7 +276,7 @@ int br_process_vlan_tunnel_info(struct net_bridge *br,
 			return -EINVAL;
 		t = tinfo_last->tunid;
 		for (v = tinfo_last->vid; v <= tinfo_curr->vid; v++) {
-			err = br_vlan_tunnel_info(p, cmd, v, t);
+			err = br_vlan_tunnel_info(p, cmd, v, t, changed);
 			if (err)
 				return err;
 			t++;
@@ -283,7 +287,7 @@ int br_process_vlan_tunnel_info(struct net_bridge *br,
 		if (tinfo_last->flags)
 			return -EINVAL;
 		err = br_vlan_tunnel_info(p, cmd, tinfo_curr->vid,
-					  tinfo_curr->tunid);
+					  tinfo_curr->tunid, changed);
 		if (err)
 			return err;
 		memset(tinfo_last, 0, sizeof(struct vtunnel_info));
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e870cfc85b14..40553d832b6e 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -36,7 +36,14 @@
 /* Control of forwarding link local multicast */
 #define BR_GROUPFWD_DEFAULT	0
 /* Don't allow forwarding of control protocols like STP, MAC PAUSE and LACP */
-#define BR_GROUPFWD_RESTRICTED	0x0007u
+enum {
+	BR_GROUPFWD_STP		= BIT(0),
+	BR_GROUPFWD_MACPAUSE	= BIT(1),
+	BR_GROUPFWD_LACP	= BIT(2),
+};
+
+#define BR_GROUPFWD_RESTRICTED (BR_GROUPFWD_STP | BR_GROUPFWD_MACPAUSE | \
+				BR_GROUPFWD_LACP)
 /* The Nearest Customer Bridge Group Address, 01-80-C2-00-00-[00,0B,0C,0D,0F] */
 #define BR_GROUPFWD_8021AD	0xB801u
 
@@ -268,6 +275,7 @@ struct net_bridge_port {
 #ifdef CONFIG_NET_SWITCHDEV
 	int				offload_fwd_mark;
 #endif
+	u16				group_fwd_mask;
 };
 
 #define br_auto_port(p) ((p)->flags & BR_AUTO_MASK)
@@ -396,6 +404,7 @@ struct net_bridge {
 #ifdef CONFIG_NET_SWITCHDEV
 	int offload_fwd_mark;
 #endif
+	bool				neigh_suppress_enabled;
 };
 
 struct br_input_skb_cb {
@@ -558,7 +567,8 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
 void br_port_carrier_check(struct net_bridge_port *p);
 int br_add_bridge(struct net *net, const char *name);
 int br_del_bridge(struct net *net, const char *name);
-int br_add_if(struct net_bridge *br, struct net_device *dev);
+int br_add_if(struct net_bridge *br, struct net_device *dev,
+	      struct netlink_ext_ack *extack);
 int br_del_if(struct net_bridge *br, struct net_device *dev);
 int br_min_mtu(const struct net_bridge *br);
 netdev_features_t br_features_recompute(struct net_bridge *br,
@@ -793,7 +803,8 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br,
 			       const struct net_bridge_port *port,
 			       struct net_bridge_vlan_group *vg,
 			       struct sk_buff *skb);
-int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags);
+int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags,
+		bool *changed);
 int br_vlan_delete(struct net_bridge *br, u16 vid);
 void br_vlan_flush(struct net_bridge *br);
 struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid);
@@ -806,7 +817,8 @@ int br_vlan_set_stats(struct net_bridge *br, unsigned long val);
 int br_vlan_init(struct net_bridge *br);
 int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val);
 int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid);
-int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags);
+int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
+		 bool *changed);
 int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
 void nbp_vlan_flush(struct net_bridge_port *port);
 int nbp_vlan_init(struct net_bridge_port *port);
@@ -893,8 +905,10 @@ static inline struct sk_buff *br_handle_vlan(struct net_bridge *br,
 	return skb;
 }
 
-static inline int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
+static inline int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags,
+			      bool *changed)
 {
+	*changed = false;
 	return -EOPNOTSUPP;
 }
 
@@ -916,8 +930,10 @@ static inline int br_vlan_init(struct net_bridge *br)
 	return 0;
 }
 
-static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
+static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
+			       bool *changed)
 {
+	*changed = false;
 	return -EOPNOTSUPP;
 }
 
@@ -1055,7 +1071,8 @@ extern int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr)
 extern struct rtnl_link_ops br_link_ops;
 int br_netlink_init(void);
 void br_netlink_fini(void);
-void br_ifinfo_notify(int event, struct net_bridge_port *port);
+void br_ifinfo_notify(int event, const struct net_bridge *br,
+		      const struct net_bridge_port *port);
 int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
 int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
 int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev,
@@ -1130,4 +1147,11 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb)
 }
 #endif /* CONFIG_NET_SWITCHDEV */
 
+/* br_arp_nd_proxy.c */
+void br_recalculate_neigh_suppress_enabled(struct net_bridge *br);
+void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
+			      u16 vid, struct net_bridge_port *p);
+void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
+		       u16 vid, struct net_bridge_port *p, struct nd_msg *msg);
+struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *m);
 #endif
diff --git a/net/bridge/br_private_tunnel.h b/net/bridge/br_private_tunnel.h
index 4a447a378ab3..a259471bfd78 100644
--- a/net/bridge/br_private_tunnel.h
+++ b/net/bridge/br_private_tunnel.h
@@ -26,7 +26,8 @@ int br_process_vlan_tunnel_info(struct net_bridge *br,
 				struct net_bridge_port *p,
 				int cmd,
 				struct vtunnel_info *tinfo_curr,
-				struct vtunnel_info *tinfo_last);
+				struct vtunnel_info *tinfo_last,
+				bool *changed);
 int br_get_vlan_tunnel_info_size(struct net_bridge_vlan_group *vg);
 int br_fill_vlan_tunnel_info(struct sk_buff *skb,
 			     struct net_bridge_vlan_group *vg);
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 8f56c2d1f1a7..b6941961a876 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -123,7 +123,7 @@ static void br_root_port_block(const struct net_bridge *br,
 		  (unsigned int) p->port_no, p->dev->name);
 
 	br_set_state(p, BR_STATE_LISTENING);
-	br_ifinfo_notify(RTM_NEWLINK, p);
+	br_ifinfo_notify(RTM_NEWLINK, NULL, p);
 
 	if (br->forward_delay > 0)
 		mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay);
@@ -403,7 +403,7 @@ static void br_make_blocking(struct net_bridge_port *p)
 			br_topology_change_detection(p->br);
 
 		br_set_state(p, BR_STATE_BLOCKING);
-		br_ifinfo_notify(RTM_NEWLINK, p);
+		br_ifinfo_notify(RTM_NEWLINK, NULL, p);
 
 		del_timer(&p->forward_delay_timer);
 	}
@@ -426,7 +426,7 @@ static void br_make_forwarding(struct net_bridge_port *p)
 	else
 		br_set_state(p, BR_STATE_LEARNING);
 
-	br_ifinfo_notify(RTM_NEWLINK, p);
+	br_ifinfo_notify(RTM_NEWLINK, NULL, p);
 
 	if (br->forward_delay != 0)
 		mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay);
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 89110319ef0f..808e2b914015 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -96,7 +96,7 @@ void br_stp_enable_port(struct net_bridge_port *p)
 {
 	br_init_port(p);
 	br_port_state_selection(p->br);
-	br_ifinfo_notify(RTM_NEWLINK, p);
+	br_ifinfo_notify(RTM_NEWLINK, NULL, p);
 }
 
 /* called under bridge lock */
@@ -111,7 +111,7 @@ void br_stp_disable_port(struct net_bridge_port *p)
 	p->topology_change_ack = 0;
 	p->config_pending = 0;
 
-	br_ifinfo_notify(RTM_NEWLINK, p);
+	br_ifinfo_notify(RTM_NEWLINK, NULL, p);
 
 	del_timer(&p->message_age_timer);
 	del_timer(&p->forward_delay_timer);
diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c
index 60b6fe277a8b..e7739de5f0e1 100644
--- a/net/bridge/br_stp_timer.c
+++ b/net/bridge/br_stp_timer.c
@@ -31,9 +31,9 @@ static int br_is_designated_for_some_port(const struct net_bridge *br)
 	return 0;
 }
 
-static void br_hello_timer_expired(unsigned long arg)
+static void br_hello_timer_expired(struct timer_list *t)
 {
-	struct net_bridge *br = (struct net_bridge *)arg;
+	struct net_bridge *br = from_timer(br, t, hello_timer);
 
 	br_debug(br, "hello timer expired\n");
 	spin_lock(&br->lock);
@@ -47,9 +47,9 @@ static void br_hello_timer_expired(unsigned long arg)
 	spin_unlock(&br->lock);
 }
 
-static void br_message_age_timer_expired(unsigned long arg)
+static void br_message_age_timer_expired(struct timer_list *t)
 {
-	struct net_bridge_port *p = (struct net_bridge_port *) arg;
+	struct net_bridge_port *p = from_timer(p, t, message_age_timer);
 	struct net_bridge *br = p->br;
 	const bridge_id *id = &p->designated_bridge;
 	int was_root;
@@ -80,9 +80,9 @@ static void br_message_age_timer_expired(unsigned long arg)
 	spin_unlock(&br->lock);
 }
 
-static void br_forward_delay_timer_expired(unsigned long arg)
+static void br_forward_delay_timer_expired(struct timer_list *t)
 {
-	struct net_bridge_port *p = (struct net_bridge_port *) arg;
+	struct net_bridge_port *p = from_timer(p, t, forward_delay_timer);
 	struct net_bridge *br = p->br;
 
 	br_debug(br, "port %u(%s) forward delay timer\n",
@@ -99,14 +99,14 @@ static void br_forward_delay_timer_expired(unsigned long arg)
 		netif_carrier_on(br->dev);
 	}
 	rcu_read_lock();
-	br_ifinfo_notify(RTM_NEWLINK, p);
+	br_ifinfo_notify(RTM_NEWLINK, NULL, p);
 	rcu_read_unlock();
 	spin_unlock(&br->lock);
 }
 
-static void br_tcn_timer_expired(unsigned long arg)
+static void br_tcn_timer_expired(struct timer_list *t)
 {
-	struct net_bridge *br = (struct net_bridge *) arg;
+	struct net_bridge *br = from_timer(br, t, tcn_timer);
 
 	br_debug(br, "tcn timer expired\n");
 	spin_lock(&br->lock);
@@ -118,9 +118,9 @@ static void br_tcn_timer_expired(unsigned long arg)
 	spin_unlock(&br->lock);
 }
 
-static void br_topology_change_timer_expired(unsigned long arg)
+static void br_topology_change_timer_expired(struct timer_list *t)
 {
-	struct net_bridge *br = (struct net_bridge *) arg;
+	struct net_bridge *br = from_timer(br, t, topology_change_timer);
 
 	br_debug(br, "topo change timer expired\n");
 	spin_lock(&br->lock);
@@ -129,9 +129,9 @@ static void br_topology_change_timer_expired(unsigned long arg)
 	spin_unlock(&br->lock);
 }
 
-static void br_hold_timer_expired(unsigned long arg)
+static void br_hold_timer_expired(struct timer_list *t)
 {
-	struct net_bridge_port *p = (struct net_bridge_port *) arg;
+	struct net_bridge_port *p = from_timer(p, t, hold_timer);
 
 	br_debug(p->br, "port %u(%s) hold timer expired\n",
 		 (unsigned int) p->port_no, p->dev->name);
@@ -144,27 +144,17 @@ static void br_hold_timer_expired(unsigned long arg)
 
 void br_stp_timer_init(struct net_bridge *br)
 {
-	setup_timer(&br->hello_timer, br_hello_timer_expired,
-		      (unsigned long) br);
-
-	setup_timer(&br->tcn_timer, br_tcn_timer_expired,
-		      (unsigned long) br);
-
-	setup_timer(&br->topology_change_timer,
-		      br_topology_change_timer_expired,
-		      (unsigned long) br);
+	timer_setup(&br->hello_timer, br_hello_timer_expired, 0);
+	timer_setup(&br->tcn_timer, br_tcn_timer_expired, 0);
+	timer_setup(&br->topology_change_timer,
+		    br_topology_change_timer_expired, 0);
 }
 
 void br_stp_port_timer_init(struct net_bridge_port *p)
 {
-	setup_timer(&p->message_age_timer, br_message_age_timer_expired,
-		      (unsigned long) p);
-
-	setup_timer(&p->forward_delay_timer, br_forward_delay_timer_expired,
-		      (unsigned long) p);
-
-	setup_timer(&p->hold_timer, br_hold_timer_expired,
-		      (unsigned long) p);
+	timer_setup(&p->message_age_timer, br_message_age_timer_expired, 0);
+	timer_setup(&p->forward_delay_timer, br_forward_delay_timer_expired, 0);
+	timer_setup(&p->hold_timer, br_hold_timer_expired, 0);
 }
 
 /* Report ticks left (in USER_HZ) used for API */
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 5d5d413a6cf8..0254c35b2bf0 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -165,6 +165,23 @@ static int store_flush(struct net_bridge_port *p, unsigned long v)
 }
 static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush);
 
+static ssize_t show_group_fwd_mask(struct net_bridge_port *p, char *buf)
+{
+	return sprintf(buf, "%#x\n", p->group_fwd_mask);
+}
+
+static int store_group_fwd_mask(struct net_bridge_port *p,
+				unsigned long v)
+{
+	if (v & BR_GROUPFWD_MACPAUSE)
+		return -EINVAL;
+	p->group_fwd_mask = v;
+
+	return 0;
+}
+static BRPORT_ATTR(group_fwd_mask, S_IRUGO | S_IWUSR, show_group_fwd_mask,
+		   store_group_fwd_mask);
+
 BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE);
 BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD);
 BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK);
@@ -174,6 +191,7 @@ BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP);
 BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI);
 BRPORT_ATTR_FLAG(multicast_flood, BR_MCAST_FLOOD);
 BRPORT_ATTR_FLAG(broadcast_flood, BR_BCAST_FLOOD);
+BRPORT_ATTR_FLAG(neigh_suppress, BR_NEIGH_SUPPRESS);
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
@@ -223,6 +241,8 @@ static const struct brport_attribute *brport_attrs[] = {
 	&brport_attr_proxyarp_wifi,
 	&brport_attr_multicast_flood,
 	&brport_attr_broadcast_flood,
+	&brport_attr_group_fwd_mask,
+	&brport_attr_neigh_suppress,
 	NULL
 };
 
@@ -260,7 +280,7 @@ static ssize_t brport_store(struct kobject *kobj,
 			ret = brport_attr->store(p, val);
 			spin_unlock_bh(&p->br->lock);
 			if (!ret) {
-				br_ifinfo_notify(RTM_NEWLINK, p);
+				br_ifinfo_notify(RTM_NEWLINK, NULL, p);
 				ret = count;
 			}
 		}
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 233a30040c91..51935270c651 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -32,27 +32,34 @@ static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid)
 	return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params);
 }
 
-static void __vlan_add_pvid(struct net_bridge_vlan_group *vg, u16 vid)
+static bool __vlan_add_pvid(struct net_bridge_vlan_group *vg, u16 vid)
 {
 	if (vg->pvid == vid)
-		return;
+		return false;
 
 	smp_wmb();
 	vg->pvid = vid;
+
+	return true;
 }
 
-static void __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid)
+static bool __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid)
 {
 	if (vg->pvid != vid)
-		return;
+		return false;
 
 	smp_wmb();
 	vg->pvid = 0;
+
+	return true;
 }
 
-static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
+/* return true if anything changed, false otherwise */
+static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
 {
 	struct net_bridge_vlan_group *vg;
+	u16 old_flags = v->flags;
+	bool ret;
 
 	if (br_vlan_is_master(v))
 		vg = br_vlan_group(v->br);
@@ -60,14 +67,16 @@ static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
 		vg = nbp_vlan_group(v->port);
 
 	if (flags & BRIDGE_VLAN_INFO_PVID)
-		__vlan_add_pvid(vg, v->vid);
+		ret = __vlan_add_pvid(vg, v->vid);
 	else
-		__vlan_delete_pvid(vg, v->vid);
+		ret = __vlan_delete_pvid(vg, v->vid);
 
 	if (flags & BRIDGE_VLAN_INFO_UNTAGGED)
 		v->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
 	else
 		v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED;
+
+	return ret || !!(old_flags ^ v->flags);
 }
 
 static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br,
@@ -151,8 +160,10 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid
 	vg = br_vlan_group(br);
 	masterv = br_vlan_find(vg, vid);
 	if (!masterv) {
+		bool changed;
+
 		/* missing global ctx, create it now */
-		if (br_vlan_add(br, vid, 0))
+		if (br_vlan_add(br, vid, 0, &changed))
 			return NULL;
 		masterv = br_vlan_find(vg, vid);
 		if (WARN_ON(!masterv))
@@ -232,8 +243,11 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags)
 
 		/* need to work on the master vlan too */
 		if (flags & BRIDGE_VLAN_INFO_MASTER) {
-			err = br_vlan_add(br, v->vid, flags |
-						      BRIDGE_VLAN_INFO_BRENTRY);
+			bool changed;
+
+			err = br_vlan_add(br, v->vid,
+					  flags | BRIDGE_VLAN_INFO_BRENTRY,
+					  &changed);
 			if (err)
 				goto out_filt;
 		}
@@ -550,8 +564,9 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
 
 /* Must be protected by RTNL.
  * Must be called with vid in range from 1 to 4094 inclusive.
+ * changed must be true only if the vlan was created or updated
  */
-int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
+int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed)
 {
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_vlan *vlan;
@@ -559,6 +574,7 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
 
 	ASSERT_RTNL();
 
+	*changed = false;
 	vg = br_vlan_group(br);
 	vlan = br_vlan_find(vg, vid);
 	if (vlan) {
@@ -576,8 +592,11 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
 			refcount_inc(&vlan->refcnt);
 			vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY;
 			vg->num_vlans++;
+			*changed = true;
 		}
-		__vlan_add_flags(vlan, flags);
+		if (__vlan_add_flags(vlan, flags))
+			*changed = true;
+
 		return 0;
 	}
 
@@ -600,6 +619,8 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
 	if (ret) {
 		free_percpu(vlan->stats);
 		kfree(vlan);
+	} else {
+		*changed = true;
 	}
 
 	return ret;
@@ -824,9 +845,10 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
 	const struct net_bridge_vlan *pvent;
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_port *p;
+	unsigned long *changed;
+	bool vlchange;
 	u16 old_pvid;
 	int err = 0;
-	unsigned long *changed;
 
 	if (!pvid) {
 		br_vlan_disable_default_pvid(br);
@@ -850,7 +872,8 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
 		err = br_vlan_add(br, pvid,
 				  BRIDGE_VLAN_INFO_PVID |
 				  BRIDGE_VLAN_INFO_UNTAGGED |
-				  BRIDGE_VLAN_INFO_BRENTRY);
+				  BRIDGE_VLAN_INFO_BRENTRY,
+				  &vlchange);
 		if (err)
 			goto out;
 		br_vlan_delete(br, old_pvid);
@@ -869,7 +892,8 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
 
 		err = nbp_vlan_add(p, pvid,
 				   BRIDGE_VLAN_INFO_PVID |
-				   BRIDGE_VLAN_INFO_UNTAGGED);
+				   BRIDGE_VLAN_INFO_UNTAGGED,
+				   &vlchange);
 		if (err)
 			goto err_port;
 		nbp_vlan_delete(p, old_pvid);
@@ -890,7 +914,8 @@ err_port:
 		if (old_pvid)
 			nbp_vlan_add(p, old_pvid,
 				     BRIDGE_VLAN_INFO_PVID |
-				     BRIDGE_VLAN_INFO_UNTAGGED);
+				     BRIDGE_VLAN_INFO_UNTAGGED,
+				     &vlchange);
 		nbp_vlan_delete(p, pvid);
 	}
 
@@ -899,7 +924,8 @@ err_port:
 			br_vlan_add(br, old_pvid,
 				    BRIDGE_VLAN_INFO_PVID |
 				    BRIDGE_VLAN_INFO_UNTAGGED |
-				    BRIDGE_VLAN_INFO_BRENTRY);
+				    BRIDGE_VLAN_INFO_BRENTRY,
+				    &vlchange);
 		br_vlan_delete(br, pvid);
 	}
 	goto out;
@@ -931,6 +957,7 @@ int br_vlan_init(struct net_bridge *br)
 {
 	struct net_bridge_vlan_group *vg;
 	int ret = -ENOMEM;
+	bool changed;
 
 	vg = kzalloc(sizeof(*vg), GFP_KERNEL);
 	if (!vg)
@@ -947,7 +974,7 @@ int br_vlan_init(struct net_bridge *br)
 	rcu_assign_pointer(br->vlgrp, vg);
 	ret = br_vlan_add(br, 1,
 			  BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED |
-			  BRIDGE_VLAN_INFO_BRENTRY);
+			  BRIDGE_VLAN_INFO_BRENTRY, &changed);
 	if (ret)
 		goto err_vlan_add;
 
@@ -992,9 +1019,12 @@ int nbp_vlan_init(struct net_bridge_port *p)
 	INIT_LIST_HEAD(&vg->vlan_list);
 	rcu_assign_pointer(p->vlgrp, vg);
 	if (p->br->default_pvid) {
+		bool changed;
+
 		ret = nbp_vlan_add(p, p->br->default_pvid,
 				   BRIDGE_VLAN_INFO_PVID |
-				   BRIDGE_VLAN_INFO_UNTAGGED);
+				   BRIDGE_VLAN_INFO_UNTAGGED,
+				   &changed);
 		if (ret)
 			goto err_vlan_add;
 	}
@@ -1016,8 +1046,10 @@ err_vlan_enabled:
 
 /* Must be protected by RTNL.
  * Must be called with vid in range from 1 to 4094 inclusive.
+ * changed must be true only if the vlan was created or updated
  */
-int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
+int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
+		 bool *changed)
 {
 	struct switchdev_obj_port_vlan v = {
 		.obj.orig_dev = port->dev,
@@ -1031,13 +1063,15 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
 
 	ASSERT_RTNL();
 
+	*changed = false;
 	vlan = br_vlan_find(nbp_vlan_group(port), vid);
 	if (vlan) {
 		/* Pass the flags to the hardware bridge */
 		ret = switchdev_port_obj_add(port->dev, &v.obj);
 		if (ret && ret != -EOPNOTSUPP)
 			return ret;
-		__vlan_add_flags(vlan, flags);
+		*changed = __vlan_add_flags(vlan, flags);
+
 		return 0;
 	}
 
@@ -1050,6 +1084,8 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
 	ret = __vlan_add(vlan, flags);
 	if (ret)
 		kfree(vlan);
+	else
+		*changed = true;
 
 	return ret;
 }
diff --git a/net/can/af_can.c b/net/can/af_can.c
index ecd5c703d11e..003b2d6d655f 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -887,8 +887,8 @@ static int can_pernet_init(struct net *net)
 	if (IS_ENABLED(CONFIG_PROC_FS)) {
 		/* the statistics are updated every second (timer triggered) */
 		if (stats_timer) {
-			setup_timer(&net->can.can_stattimer, can_stat_update,
-				    (unsigned long)net);
+			timer_setup(&net->can.can_stattimer, can_stat_update,
+				    0);
 			mod_timer(&net->can.can_stattimer,
 				  round_jiffies(jiffies + HZ));
 		}
diff --git a/net/can/af_can.h b/net/can/af_can.h
index d0ef45bb2a72..eca6463c6213 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -113,6 +113,6 @@ struct s_pstats {
 /* function prototypes for the CAN networklayer procfs (proc.c) */
 void can_init_proc(struct net *net);
 void can_remove_proc(struct net *net);
-void can_stat_update(unsigned long data);
+void can_stat_update(struct timer_list *t);
 
 #endif /* AF_CAN_H */
diff --git a/net/can/proc.c b/net/can/proc.c
index 83045f00c63c..d979b3dc49a6 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -115,9 +115,9 @@ static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif,
 	return rate;
 }
 
-void can_stat_update(unsigned long data)
+void can_stat_update(struct timer_list *t)
 {
-	struct net *net = (struct net *)data;
+	struct net *net = from_timer(net, t, can.can_stattimer);
 	struct s_stats *can_stats = net->can.can_stats;
 	unsigned long j = jiffies; /* snapshot */
 
@@ -221,7 +221,7 @@ static int can_stats_proc_show(struct seq_file *m, void *v)
 
 	seq_putc(m, '\n');
 
-	if (net->can.can_stattimer.function == can_stat_update) {
+	if (net->can.can_stattimer.function == (TIMER_FUNC_TYPE)can_stat_update) {
 		seq_printf(m, " %8ld %% total match ratio (RXMR)\n",
 				can_stats->total_rx_match_ratio);
 
@@ -291,7 +291,7 @@ static int can_reset_stats_proc_show(struct seq_file *m, void *v)
 
 	user_reset = 1;
 
-	if (net->can.can_stattimer.function == can_stat_update) {
+	if (net->can.can_stattimer.function == (TIMER_FUNC_TYPE)can_stat_update) {
 		seq_printf(m, "Scheduled statistic reset #%ld.\n",
 				can_pstats->stats_reset + 1);
 	} else {
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 3964c108b169..522873ed120b 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -189,7 +189,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
 			}
 			if (!skb->len) {
 				skb = skb_set_peeked(skb);
-				if (unlikely(IS_ERR(skb))) {
+				if (IS_ERR(skb)) {
 					*err = PTR_ERR(skb);
 					return NULL;
 				}
diff --git a/net/core/dev.c b/net/core/dev.c
index 11596a302a26..1423cf4d695c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -145,6 +145,7 @@
 #include <linux/crash_dump.h>
 #include <linux/sctp.h>
 #include <net/udp_tunnel.h>
+#include <linux/net_namespace.h>
 
 #include "net-sysfs.h"
 
@@ -162,7 +163,6 @@ static struct list_head offload_base __read_mostly;
 
 static int netif_rx_internal(struct sk_buff *skb);
 static int call_netdevice_notifiers_info(unsigned long val,
-					 struct net_device *dev,
 					 struct netdev_notifier_info *info);
 static struct napi_struct *napi_by_id(unsigned int napi_id);
 
@@ -188,6 +188,8 @@ static struct napi_struct *napi_by_id(unsigned int napi_id);
 DEFINE_RWLOCK(dev_base_lock);
 EXPORT_SYMBOL(dev_base_lock);
 
+static DEFINE_MUTEX(ifalias_mutex);
+
 /* protects napi_hash addition/deletion and napi_gen_id */
 static DEFINE_SPINLOCK(napi_hash_lock);
 
@@ -1265,29 +1267,53 @@ rollback:
  */
 int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 {
-	char *new_ifalias;
-
-	ASSERT_RTNL();
+	struct dev_ifalias *new_alias = NULL;
 
 	if (len >= IFALIASZ)
 		return -EINVAL;
 
-	if (!len) {
-		kfree(dev->ifalias);
-		dev->ifalias = NULL;
-		return 0;
+	if (len) {
+		new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL);
+		if (!new_alias)
+			return -ENOMEM;
+
+		memcpy(new_alias->ifalias, alias, len);
+		new_alias->ifalias[len] = 0;
 	}
 
-	new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
-	if (!new_ifalias)
-		return -ENOMEM;
-	dev->ifalias = new_ifalias;
-	memcpy(dev->ifalias, alias, len);
-	dev->ifalias[len] = 0;
+	mutex_lock(&ifalias_mutex);
+	rcu_swap_protected(dev->ifalias, new_alias,
+			   mutex_is_locked(&ifalias_mutex));
+	mutex_unlock(&ifalias_mutex);
+
+	if (new_alias)
+		kfree_rcu(new_alias, rcuhead);
 
 	return len;
 }
 
+/**
+ *	dev_get_alias - get ifalias of a device
+ *	@dev: device
+ *	@name: buffer to store name of ifalias
+ *	@len: size of buffer
+ *
+ *	get ifalias for a device.  Caller must make sure dev cannot go
+ *	away,  e.g. rcu read lock or own a reference count to device.
+ */
+int dev_get_alias(const struct net_device *dev, char *name, size_t len)
+{
+	const struct dev_ifalias *alias;
+	int ret = 0;
+
+	rcu_read_lock();
+	alias = rcu_dereference(dev->ifalias);
+	if (alias)
+		ret = snprintf(name, len, "%s", alias->ifalias);
+	rcu_read_unlock();
+
+	return ret;
+}
 
 /**
  *	netdev_features_change - device changes features
@@ -1312,10 +1338,11 @@ EXPORT_SYMBOL(netdev_features_change);
 void netdev_state_change(struct net_device *dev)
 {
 	if (dev->flags & IFF_UP) {
-		struct netdev_notifier_change_info change_info;
+		struct netdev_notifier_change_info change_info = {
+			.info.dev = dev,
+		};
 
-		change_info.flags_changed = 0;
-		call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+		call_netdevice_notifiers_info(NETDEV_CHANGE,
 					      &change_info.info);
 		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 	}
@@ -1536,9 +1563,10 @@ EXPORT_SYMBOL(dev_disable_lro);
 static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
 				   struct net_device *dev)
 {
-	struct netdev_notifier_info info;
+	struct netdev_notifier_info info = {
+		.dev = dev,
+	};
 
-	netdev_notifier_info_init(&info, dev);
 	return nb->notifier_call(nb, val, &info);
 }
 
@@ -1663,11 +1691,9 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
  */
 
 static int call_netdevice_notifiers_info(unsigned long val,
-					 struct net_device *dev,
 					 struct netdev_notifier_info *info)
 {
 	ASSERT_RTNL();
-	netdev_notifier_info_init(info, dev);
 	return raw_notifier_call_chain(&netdev_chain, val, info);
 }
 
@@ -1682,9 +1708,11 @@ static int call_netdevice_notifiers_info(unsigned long val,
 
 int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
 {
-	struct netdev_notifier_info info;
+	struct netdev_notifier_info info = {
+		.dev = dev,
+	};
 
-	return call_netdevice_notifiers_info(val, dev, &info);
+	return call_netdevice_notifiers_info(val, &info);
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
@@ -2012,6 +2040,7 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq)
 
 	return 0;
 }
+EXPORT_SYMBOL(netdev_txq_to_tc);
 
 #ifdef CONFIG_XPS
 static DEFINE_MUTEX(xps_map_mutex);
@@ -3245,22 +3274,22 @@ EXPORT_SYMBOL(dev_loopback_xmit);
 static struct sk_buff *
 sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 {
-	struct tcf_proto *cl = rcu_dereference_bh(dev->egress_cl_list);
+	struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress);
 	struct tcf_result cl_res;
 
-	if (!cl)
+	if (!miniq)
 		return skb;
 
 	/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
-	qdisc_bstats_cpu_update(cl->q, skb);
+	mini_qdisc_bstats_cpu_update(miniq, skb);
 
-	switch (tcf_classify(skb, cl, &cl_res, false)) {
+	switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
 	case TC_ACT_OK:
 	case TC_ACT_RECLASSIFY:
 		skb->tc_index = TC_H_MIN(cl_res.classid);
 		break;
 	case TC_ACT_SHOT:
-		qdisc_qstats_cpu_drop(cl->q);
+		mini_qdisc_qstats_cpu_drop(miniq);
 		*ret = NET_XMIT_DROP;
 		kfree_skb(skb);
 		return NULL;
@@ -3864,8 +3893,8 @@ drop:
 static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 				     struct bpf_prog *xdp_prog)
 {
+	u32 metalen, act = XDP_DROP;
 	struct xdp_buff xdp;
-	u32 act = XDP_DROP;
 	void *orig_data;
 	int hlen, off;
 	u32 mac_len;
@@ -3876,8 +3905,25 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	if (skb_cloned(skb))
 		return XDP_PASS;
 
-	if (skb_linearize(skb))
-		goto do_drop;
+	/* XDP packets must be linear and must have sufficient headroom
+	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
+	 * native XDP provides, thus we need to do it here as well.
+	 */
+	if (skb_is_nonlinear(skb) ||
+	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
+		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
+		int troom = skb->tail + skb->data_len - skb->end;
+
+		/* In case we have to go down the path and also linearize,
+		 * then lets do the pskb_expand_head() work just once here.
+		 */
+		if (pskb_expand_head(skb,
+				     hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
+				     troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
+			goto do_drop;
+		if (troom > 0 && __skb_linearize(skb))
+			goto do_drop;
+	}
 
 	/* The XDP program wants to see the packet starting at the MAC
 	 * header.
@@ -3885,6 +3931,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	mac_len = skb->data - skb_mac_header(skb);
 	hlen = skb_headlen(skb) + mac_len;
 	xdp.data = skb->data - mac_len;
+	xdp.data_meta = xdp.data;
 	xdp.data_end = xdp.data + hlen;
 	xdp.data_hard_start = skb->data - skb_headroom(skb);
 	orig_data = xdp.data;
@@ -3902,10 +3949,12 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	case XDP_REDIRECT:
 	case XDP_TX:
 		__skb_push(skb, mac_len);
-		/* fall through */
+		break;
 	case XDP_PASS:
+		metalen = xdp.data - xdp.data_meta;
+		if (metalen)
+			skb_metadata_set(skb, metalen);
 		break;
-
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		/* fall through */
@@ -4140,7 +4189,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 		   struct net_device *orig_dev)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	struct tcf_proto *cl = rcu_dereference_bh(skb->dev->ingress_cl_list);
+	struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress);
 	struct tcf_result cl_res;
 
 	/* If there's at least one ingress present somewhere (so
@@ -4148,8 +4197,9 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 	 * that are not configured with an ingress qdisc will bail
 	 * out here.
 	 */
-	if (!cl)
+	if (!miniq)
 		return skb;
+
 	if (*pt_prev) {
 		*ret = deliver_skb(skb, *pt_prev, orig_dev);
 		*pt_prev = NULL;
@@ -4157,15 +4207,15 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 
 	qdisc_skb_cb(skb)->pkt_len = skb->len;
 	skb->tc_at_ingress = 1;
-	qdisc_bstats_cpu_update(cl->q, skb);
+	mini_qdisc_bstats_cpu_update(miniq, skb);
 
-	switch (tcf_classify(skb, cl, &cl_res, false)) {
+	switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
 	case TC_ACT_OK:
 	case TC_ACT_RECLASSIFY:
 		skb->tc_index = TC_H_MIN(cl_res.classid);
 		break;
 	case TC_ACT_SHOT:
-		qdisc_qstats_cpu_drop(cl->q);
+		mini_qdisc_qstats_cpu_drop(miniq);
 		kfree_skb(skb);
 		return NULL;
 	case TC_ACT_STOLEN:
@@ -4443,6 +4493,33 @@ out:
 	return ret;
 }
 
+/**
+ *	netif_receive_skb_core - special purpose version of netif_receive_skb
+ *	@skb: buffer to process
+ *
+ *	More direct receive version of netif_receive_skb().  It should
+ *	only be used by callers that have a need to skip RPS and Generic XDP.
+ *	Caller must also take care of handling if (page_is_)pfmemalloc.
+ *
+ *	This function may only be called from softirq context and interrupts
+ *	should be enabled.
+ *
+ *	Return values (usually ignored):
+ *	NET_RX_SUCCESS: no congestion
+ *	NET_RX_DROP: packet was dropped
+ */
+int netif_receive_skb_core(struct sk_buff *skb)
+{
+	int ret;
+
+	rcu_read_lock();
+	ret = __netif_receive_skb_core(skb, false);
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(netif_receive_skb_core);
+
 static int __netif_receive_skb(struct sk_buff *skb)
 {
 	int ret;
@@ -4695,6 +4772,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
 		diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
 		diffs |= p->vlan_tci ^ skb->vlan_tci;
 		diffs |= skb_metadata_dst_cmp(p, skb);
+		diffs |= skb_metadata_differs(p, skb);
 		if (maclen == ETH_HLEN)
 			diffs |= compare_ether_header(skb_mac_header(p),
 						      skb_mac_header(skb));
@@ -6228,9 +6306,19 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
 
 static int __netdev_upper_dev_link(struct net_device *dev,
 				   struct net_device *upper_dev, bool master,
-				   void *upper_priv, void *upper_info)
-{
-	struct netdev_notifier_changeupper_info changeupper_info;
+				   void *upper_priv, void *upper_info,
+				   struct netlink_ext_ack *extack)
+{
+	struct netdev_notifier_changeupper_info changeupper_info = {
+		.info = {
+			.dev = dev,
+			.extack = extack,
+		},
+		.upper_dev = upper_dev,
+		.master = master,
+		.linking = true,
+		.upper_info = upper_info,
+	};
 	int ret = 0;
 
 	ASSERT_RTNL();
@@ -6248,12 +6336,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (master && netdev_master_upper_dev_get(dev))
 		return -EBUSY;
 
-	changeupper_info.upper_dev = upper_dev;
-	changeupper_info.master = master;
-	changeupper_info.linking = true;
-	changeupper_info.upper_info = upper_info;
-
-	ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
+	ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER,
 					    &changeupper_info.info);
 	ret = notifier_to_errno(ret);
 	if (ret)
@@ -6264,7 +6347,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (ret)
 		return ret;
 
-	ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
+	ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
 					    &changeupper_info.info);
 	ret = notifier_to_errno(ret);
 	if (ret)
@@ -6289,9 +6372,11 @@ rollback:
  * returns zero.
  */
 int netdev_upper_dev_link(struct net_device *dev,
-			  struct net_device *upper_dev)
+			  struct net_device *upper_dev,
+			  struct netlink_ext_ack *extack)
 {
-	return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL);
+	return __netdev_upper_dev_link(dev, upper_dev, false,
+				       NULL, NULL, extack);
 }
 EXPORT_SYMBOL(netdev_upper_dev_link);
 
@@ -6310,10 +6395,11 @@ EXPORT_SYMBOL(netdev_upper_dev_link);
  */
 int netdev_master_upper_dev_link(struct net_device *dev,
 				 struct net_device *upper_dev,
-				 void *upper_priv, void *upper_info)
+				 void *upper_priv, void *upper_info,
+				 struct netlink_ext_ack *extack)
 {
 	return __netdev_upper_dev_link(dev, upper_dev, true,
-				       upper_priv, upper_info);
+				       upper_priv, upper_info, extack);
 }
 EXPORT_SYMBOL(netdev_master_upper_dev_link);
 
@@ -6328,20 +6414,24 @@ EXPORT_SYMBOL(netdev_master_upper_dev_link);
 void netdev_upper_dev_unlink(struct net_device *dev,
 			     struct net_device *upper_dev)
 {
-	struct netdev_notifier_changeupper_info changeupper_info;
+	struct netdev_notifier_changeupper_info changeupper_info = {
+		.info = {
+			.dev = dev,
+		},
+		.upper_dev = upper_dev,
+		.linking = false,
+	};
 
 	ASSERT_RTNL();
 
-	changeupper_info.upper_dev = upper_dev;
 	changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev;
-	changeupper_info.linking = false;
 
-	call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
+	call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER,
 				      &changeupper_info.info);
 
 	__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
 
-	call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
+	call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
 				      &changeupper_info.info);
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
@@ -6357,11 +6447,13 @@ EXPORT_SYMBOL(netdev_upper_dev_unlink);
 void netdev_bonding_info_change(struct net_device *dev,
 				struct netdev_bonding_info *bonding_info)
 {
-	struct netdev_notifier_bonding_info	info;
+	struct netdev_notifier_bonding_info info = {
+		.info.dev = dev,
+	};
 
 	memcpy(&info.bonding_info, bonding_info,
 	       sizeof(struct netdev_bonding_info));
-	call_netdevice_notifiers_info(NETDEV_BONDING_INFO, dev,
+	call_netdevice_notifiers_info(NETDEV_BONDING_INFO,
 				      &info.info);
 }
 EXPORT_SYMBOL(netdev_bonding_info_change);
@@ -6487,11 +6579,13 @@ EXPORT_SYMBOL(dev_get_nest_level);
 void netdev_lower_state_changed(struct net_device *lower_dev,
 				void *lower_state_info)
 {
-	struct netdev_notifier_changelowerstate_info changelowerstate_info;
+	struct netdev_notifier_changelowerstate_info changelowerstate_info = {
+		.info.dev = lower_dev,
+	};
 
 	ASSERT_RTNL();
 	changelowerstate_info.lower_state_info = lower_state_info;
-	call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, lower_dev,
+	call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE,
 				      &changelowerstate_info.info);
 }
 EXPORT_SYMBOL(netdev_lower_state_changed);
@@ -6782,11 +6876,14 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
 
 	if (dev->flags & IFF_UP &&
 	    (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) {
-		struct netdev_notifier_change_info change_info;
+		struct netdev_notifier_change_info change_info = {
+			.info = {
+				.dev = dev,
+			},
+			.flags_changed = changes,
+		};
 
-		change_info.flags_changed = changes;
-		call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
-					      &change_info.info);
+		call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info);
 	}
 }
 
@@ -7157,7 +7254,7 @@ static void rollback_registered_many(struct list_head *head)
 		if (!dev->rtnl_link_ops ||
 		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
 			skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0,
-						     GFP_KERNEL);
+						     GFP_KERNEL, NULL);
 
 		/*
 		 *	Flush the unicast and multicast chains
@@ -7994,7 +8091,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 		unsigned int txqs, unsigned int rxqs)
 {
 	struct net_device *dev;
-	size_t alloc_size;
+	unsigned int alloc_size;
 	struct net_device *p;
 
 	BUG_ON(strlen(name) >= sizeof(dev->name));
@@ -8244,7 +8341,7 @@ EXPORT_SYMBOL(unregister_netdev);
 
 int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat)
 {
-	int err;
+	int err, new_nsid;
 
 	ASSERT_RTNL();
 
@@ -8300,7 +8397,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 	rcu_barrier();
 	call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev);
-	rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
+	if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net)
+		new_nsid = peernet2id_alloc(dev_net(dev), net);
+	else
+		new_nsid = peernet2id(dev_net(dev), net);
+	rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid);
 
 	/*
 	 *	Flush the unicast and multicast chains
diff --git a/net/core/dst.c b/net/core/dst.c
index a6c47da7d0f8..662a2d4a3d19 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -322,3 +322,19 @@ metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags)
 	return md_dst;
 }
 EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu);
+
+void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst)
+{
+#ifdef CONFIG_DST_CACHE
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct metadata_dst *one_md_dst = per_cpu_ptr(md_dst, cpu);
+
+		if (one_md_dst->type == METADATA_IP_TUNNEL)
+			dst_cache_destroy(&one_md_dst->u.tun_info.dst_cache);
+	}
+#endif
+	free_percpu(md_dst);
+}
+EXPORT_SYMBOL_GPL(metadata_dst_free_percpu);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 9a9a3d77e327..f8fcf450a36e 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -403,6 +403,22 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data)
 	return 0;
 }
 
+/* Given two link masks, AND them together and save the result in dst. */
+void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst,
+				  struct ethtool_link_ksettings *src)
+{
+	unsigned int size = BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS);
+	unsigned int idx = 0;
+
+	for (; idx < size; idx++) {
+		dst->link_modes.supported[idx] &=
+			src->link_modes.supported[idx];
+		dst->link_modes.advertising[idx] &=
+			src->link_modes.advertising[idx];
+	}
+}
+EXPORT_SYMBOL(ethtool_intersect_link_masks);
+
 void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst,
 					     u32 legacy_u32)
 {
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 9a6d97c1d810..fafd0a41e3f7 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -314,10 +314,12 @@ static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net,
 static int call_fib_rule_notifiers(struct net *net,
 				   enum fib_event_type event_type,
 				   struct fib_rule *rule,
-				   struct fib_rules_ops *ops)
+				   struct fib_rules_ops *ops,
+				   struct netlink_ext_ack *extack)
 {
 	struct fib_rule_notifier_info info = {
 		.info.family = ops->family,
+		.info.extack = extack,
 		.rule = rule,
 	};
 
@@ -609,7 +611,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (rule->tun_id)
 		ip_tunnel_need_metadata();
 
-	call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops);
+	call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops, extack);
 	notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid);
 	flush_route_cache(ops);
 	rules_ops_put(ops);
@@ -749,7 +751,8 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 			}
 		}
 
-		call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops);
+		call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops,
+					NULL);
 		notify_rule_change(RTM_DELRULE, rule, ops, nlh,
 				   NETLINK_CB(skb).portid);
 		fib_rule_put(rule);
diff --git a/net/core/filter.c b/net/core/filter.c
index 6ae94f825f72..a0112168d6f9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -43,6 +43,7 @@
 #include <linux/timer.h>
 #include <linux/uaccess.h>
 #include <asm/unaligned.h>
+#include <asm/cmpxchg.h>
 #include <linux/filter.h>
 #include <linux/ratelimit.h>
 #include <linux/seccomp.h>
@@ -1406,7 +1407,7 @@ static inline int bpf_try_make_writable(struct sk_buff *skb,
 {
 	int err = __bpf_try_make_writable(skb, write_len);
 
-	bpf_compute_data_end(skb);
+	bpf_compute_data_pointers(skb);
 	return err;
 }
 
@@ -1968,7 +1969,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto,
 	ret = skb_vlan_push(skb, vlan_proto, vlan_tci);
 	bpf_pull_mac_rcsum(skb);
 
-	bpf_compute_data_end(skb);
+	bpf_compute_data_pointers(skb);
 	return ret;
 }
 
@@ -1990,7 +1991,7 @@ BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb)
 	ret = skb_vlan_pop(skb);
 	bpf_pull_mac_rcsum(skb);
 
-	bpf_compute_data_end(skb);
+	bpf_compute_data_pointers(skb);
 	return ret;
 }
 
@@ -2184,7 +2185,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto,
 	 * need to be verified first.
 	 */
 	ret = bpf_skb_proto_xlat(skb, proto);
-	bpf_compute_data_end(skb);
+	bpf_compute_data_pointers(skb);
 	return ret;
 }
 
@@ -2309,7 +2310,7 @@ static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff)
 	ret = shrink ? bpf_skb_net_shrink(skb, len_diff_abs) :
 		       bpf_skb_net_grow(skb, len_diff_abs);
 
-	bpf_compute_data_end(skb);
+	bpf_compute_data_pointers(skb);
 	return ret;
 }
 
@@ -2400,7 +2401,7 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
 			skb_gso_reset(skb);
 	}
 
-	bpf_compute_data_end(skb);
+	bpf_compute_data_pointers(skb);
 	return ret;
 }
 
@@ -2440,7 +2441,7 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
 		skb_reset_mac_header(skb);
 	}
 
-	bpf_compute_data_end(skb);
+	bpf_compute_data_pointers(skb);
 	return 0;
 }
 
@@ -2453,14 +2454,26 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+static unsigned long xdp_get_metalen(const struct xdp_buff *xdp)
+{
+	return xdp_data_meta_unsupported(xdp) ? 0 :
+	       xdp->data - xdp->data_meta;
+}
+
 BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset)
 {
+	unsigned long metalen = xdp_get_metalen(xdp);
+	void *data_start = xdp->data_hard_start + metalen;
 	void *data = xdp->data + offset;
 
-	if (unlikely(data < xdp->data_hard_start ||
+	if (unlikely(data < data_start ||
 		     data > xdp->data_end - ETH_HLEN))
 		return -EINVAL;
 
+	if (metalen)
+		memmove(xdp->data_meta + offset,
+			xdp->data_meta, metalen);
+	xdp->data_meta += offset;
 	xdp->data = data;
 
 	return 0;
@@ -2474,6 +2487,33 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset)
+{
+	void *meta = xdp->data_meta + offset;
+	unsigned long metalen = xdp->data - meta;
+
+	if (xdp_data_meta_unsupported(xdp))
+		return -ENOTSUPP;
+	if (unlikely(meta < xdp->data_hard_start ||
+		     meta > xdp->data))
+		return -EINVAL;
+	if (unlikely((metalen & (sizeof(__u32) - 1)) ||
+		     (metalen > 32)))
+		return -EACCES;
+
+	xdp->data_meta = meta;
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
+	.func		= bpf_xdp_adjust_meta,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 static int __bpf_tx_xdp(struct net_device *dev,
 			struct bpf_map *map,
 			struct xdp_buff *xdp,
@@ -2488,10 +2528,36 @@ static int __bpf_tx_xdp(struct net_device *dev,
 	err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
 	if (err)
 		return err;
-	if (map)
+	dev->netdev_ops->ndo_xdp_flush(dev);
+	return 0;
+}
+
+static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
+			    struct bpf_map *map,
+			    struct xdp_buff *xdp,
+			    u32 index)
+{
+	int err;
+
+	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+		struct net_device *dev = fwd;
+
+		if (!dev->netdev_ops->ndo_xdp_xmit)
+			return -EOPNOTSUPP;
+
+		err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
+		if (err)
+			return err;
 		__dev_map_insert_ctx(map, index);
-	else
-		dev->netdev_ops->ndo_xdp_flush(dev);
+
+	} else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+		struct bpf_cpu_map_entry *rcpu = fwd;
+
+		err = cpu_map_enqueue(rcpu, xdp, dev_rx);
+		if (err)
+			return err;
+		__cpu_map_insert_ctx(map, index);
+	}
 	return 0;
 }
 
@@ -2501,11 +2567,33 @@ void xdp_do_flush_map(void)
 	struct bpf_map *map = ri->map_to_flush;
 
 	ri->map_to_flush = NULL;
-	if (map)
-		__dev_map_flush(map);
+	if (map) {
+		switch (map->map_type) {
+		case BPF_MAP_TYPE_DEVMAP:
+			__dev_map_flush(map);
+			break;
+		case BPF_MAP_TYPE_CPUMAP:
+			__cpu_map_flush(map);
+			break;
+		default:
+			break;
+		}
+	}
 }
 EXPORT_SYMBOL_GPL(xdp_do_flush_map);
 
+static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
+{
+	switch (map->map_type) {
+	case BPF_MAP_TYPE_DEVMAP:
+		return __dev_map_lookup_elem(map, index);
+	case BPF_MAP_TYPE_CPUMAP:
+		return __cpu_map_lookup_elem(map, index);
+	default:
+		return NULL;
+	}
+}
+
 static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog,
 				   unsigned long aux)
 {
@@ -2518,8 +2606,8 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
 	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
 	unsigned long map_owner = ri->map_owner;
 	struct bpf_map *map = ri->map;
-	struct net_device *fwd = NULL;
 	u32 index = ri->ifindex;
+	void *fwd = NULL;
 	int err;
 
 	ri->ifindex = 0;
@@ -2532,7 +2620,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
 		goto err;
 	}
 
-	fwd = __dev_map_lookup_elem(map, index);
+	fwd = __xdp_map_lookup_elem(map, index);
 	if (!fwd) {
 		err = -EINVAL;
 		goto err;
@@ -2540,7 +2628,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
 	if (ri->map_to_flush && ri->map_to_flush != map)
 		xdp_do_flush_map();
 
-	err = __bpf_tx_xdp(fwd, map, xdp, index);
+	err = __bpf_tx_xdp_map(dev, fwd, map, xdp, index);
 	if (unlikely(err))
 		goto err;
 
@@ -2582,54 +2670,88 @@ err:
 }
 EXPORT_SYMBOL_GPL(xdp_do_redirect);
 
-int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
-			    struct bpf_prog *xdp_prog)
+static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
+{
+	unsigned int len;
+
+	if (unlikely(!(fwd->flags & IFF_UP)))
+		return -ENETDOWN;
+
+	len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
+	if (skb->len > len)
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb,
+				struct bpf_prog *xdp_prog)
 {
 	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
 	unsigned long map_owner = ri->map_owner;
 	struct bpf_map *map = ri->map;
 	struct net_device *fwd = NULL;
 	u32 index = ri->ifindex;
-	unsigned int len;
 	int err = 0;
 
 	ri->ifindex = 0;
 	ri->map = NULL;
 	ri->map_owner = 0;
 
-	if (map) {
-		if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
-			err = -EFAULT;
-			map = NULL;
-			goto err;
-		}
-		fwd = __dev_map_lookup_elem(map, index);
-	} else {
-		fwd = dev_get_by_index_rcu(dev_net(dev), index);
+	if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
+		err = -EFAULT;
+		map = NULL;
+		goto err;
 	}
+	fwd = __xdp_map_lookup_elem(map, index);
 	if (unlikely(!fwd)) {
 		err = -EINVAL;
 		goto err;
 	}
 
-	if (unlikely(!(fwd->flags & IFF_UP))) {
-		err = -ENETDOWN;
+	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+		if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+			goto err;
+		skb->dev = fwd;
+	} else {
+		/* TODO: Handle BPF_MAP_TYPE_CPUMAP */
+		err = -EBADRQC;
 		goto err;
 	}
 
-	len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
-	if (skb->len > len) {
-		err = -EMSGSIZE;
+	_trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
+	return 0;
+err:
+	_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
+	return err;
+}
+
+int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
+			    struct bpf_prog *xdp_prog)
+{
+	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	u32 index = ri->ifindex;
+	struct net_device *fwd;
+	int err = 0;
+
+	if (ri->map)
+		return xdp_do_generic_redirect_map(dev, skb, xdp_prog);
+
+	ri->ifindex = 0;
+	fwd = dev_get_by_index_rcu(dev_net(dev), index);
+	if (unlikely(!fwd)) {
+		err = -EINVAL;
 		goto err;
 	}
 
+	if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+		goto err;
+
 	skb->dev = fwd;
-	map ? _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index)
-		: _trace_xdp_redirect(dev, xdp_prog, index);
+	_trace_xdp_redirect(dev, xdp_prog, index);
 	return 0;
 err:
-	map ? _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err)
-		: _trace_xdp_redirect_err(dev, xdp_prog, index, err);
+	_trace_xdp_redirect_err(dev, xdp_prog, index, err);
 	return err;
 }
 EXPORT_SYMBOL_GPL(xdp_do_generic_redirect);
@@ -2698,7 +2820,8 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_clone_redirect ||
 	    func == bpf_l3_csum_replace ||
 	    func == bpf_l4_csum_replace ||
-	    func == bpf_xdp_adjust_head)
+	    func == bpf_xdp_adjust_head ||
+	    func == bpf_xdp_adjust_meta)
 		return true;
 
 	return false;
@@ -2949,14 +3072,15 @@ static const struct bpf_func_proto *
 bpf_get_skb_set_tunnel_proto(enum bpf_func_id which)
 {
 	if (!md_dst) {
-		/* Race is not possible, since it's called from verifier
-		 * that is holding verifier mutex.
-		 */
-		md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX,
-						   METADATA_IP_TUNNEL,
-						   GFP_KERNEL);
-		if (!md_dst)
+		struct metadata_dst __percpu *tmp;
+
+		tmp = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX,
+						METADATA_IP_TUNNEL,
+						GFP_KERNEL);
+		if (!tmp)
 			return NULL;
+		if (cmpxchg(&md_dst, NULL, tmp))
+			metadata_dst_free_percpu(tmp);
 	}
 
 	switch (which) {
@@ -3151,7 +3275,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 
 static const struct bpf_func_proto bpf_setsockopt_proto = {
 	.func		= bpf_setsockopt,
-	.gpl_only	= true,
+	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_ANYTHING,
@@ -3160,6 +3284,47 @@ static const struct bpf_func_proto bpf_setsockopt_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
+	   int, level, int, optname, char *, optval, int, optlen)
+{
+	struct sock *sk = bpf_sock->sk;
+
+	if (!sk_fullsock(sk))
+		goto err_clear;
+
+#ifdef CONFIG_INET
+	if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) {
+		if (optname == TCP_CONGESTION) {
+			struct inet_connection_sock *icsk = inet_csk(sk);
+
+			if (!icsk->icsk_ca_ops || optlen <= 1)
+				goto err_clear;
+			strncpy(optval, icsk->icsk_ca_ops->name, optlen);
+			optval[optlen - 1] = 0;
+		} else {
+			goto err_clear;
+		}
+	} else {
+		goto err_clear;
+	}
+	return 0;
+#endif
+err_clear:
+	memset(optval, 0, optlen);
+	return -EINVAL;
+}
+
+static const struct bpf_func_proto bpf_getsockopt_proto = {
+	.func		= bpf_getsockopt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -3294,6 +3459,8 @@ xdp_func_proto(enum bpf_func_id func_id)
 		return &bpf_get_smp_processor_id_proto;
 	case BPF_FUNC_xdp_adjust_head:
 		return &bpf_xdp_adjust_head_proto;
+	case BPF_FUNC_xdp_adjust_meta:
+		return &bpf_xdp_adjust_meta_proto;
 	case BPF_FUNC_redirect:
 		return &bpf_xdp_redirect_proto;
 	case BPF_FUNC_redirect_map:
@@ -3336,6 +3503,8 @@ static const struct bpf_func_proto *
 	switch (func_id) {
 	case BPF_FUNC_setsockopt:
 		return &bpf_setsockopt_proto;
+	case BPF_FUNC_getsockopt:
+		return &bpf_getsockopt_proto;
 	case BPF_FUNC_sock_map_update:
 		return &bpf_sock_map_update_proto;
 	default:
@@ -3424,6 +3593,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
 	case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4):
 	case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4):
 	case bpf_ctx_range(struct __sk_buff, data):
+	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, data_end):
 		if (size != size_default)
 			return false;
@@ -3450,6 +3620,7 @@ static bool sk_filter_is_valid_access(int off, int size,
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range(struct __sk_buff, data):
+	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, data_end):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 		return false;
@@ -3474,6 +3645,7 @@ static bool lwt_is_valid_access(int off, int size,
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
+	case bpf_ctx_range(struct __sk_buff, data_meta):
 		return false;
 	}
 
@@ -3592,6 +3764,9 @@ static bool tc_cls_act_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data):
 		info->reg_type = PTR_TO_PACKET;
 		break;
+	case bpf_ctx_range(struct __sk_buff, data_meta):
+		info->reg_type = PTR_TO_PACKET_META;
+		break;
 	case bpf_ctx_range(struct __sk_buff, data_end):
 		info->reg_type = PTR_TO_PACKET_END;
 		break;
@@ -3602,6 +3777,25 @@ static bool tc_cls_act_is_valid_access(int off, int size,
 	return bpf_skb_is_valid_access(off, size, type, info);
 }
 
+static bool
+tc_cls_act_is_valid_access_analyzer(int off, int size,
+				    enum bpf_access_type type,
+				    struct bpf_insn_access_aux *info)
+{
+	switch (off) {
+	case offsetof(struct sk_buff, len):
+		return true;
+	case offsetof(struct sk_buff, data):
+		info->reg_type = PTR_TO_PACKET;
+		return true;
+	case offsetof(struct sk_buff, cb) +
+	     offsetof(struct bpf_skb_data_end, data_end):
+		info->reg_type = PTR_TO_PACKET_END;
+		return true;
+	}
+	return false;
+}
+
 static bool __is_valid_xdp_access(int off, int size)
 {
 	if (off < 0 || off >= sizeof(struct xdp_md))
@@ -3625,6 +3819,9 @@ static bool xdp_is_valid_access(int off, int size,
 	case offsetof(struct xdp_md, data):
 		info->reg_type = PTR_TO_PACKET;
 		break;
+	case offsetof(struct xdp_md, data_meta):
+		info->reg_type = PTR_TO_PACKET_META;
+		break;
 	case offsetof(struct xdp_md, data_end):
 		info->reg_type = PTR_TO_PACKET_END;
 		break;
@@ -3633,6 +3830,21 @@ static bool xdp_is_valid_access(int off, int size,
 	return __is_valid_xdp_access(off, size);
 }
 
+static bool xdp_is_valid_access_analyzer(int off, int size,
+					 enum bpf_access_type type,
+					 struct bpf_insn_access_aux *info)
+{
+	switch (off) {
+	case offsetof(struct xdp_buff, data):
+		info->reg_type = PTR_TO_PACKET;
+		return true;
+	case offsetof(struct xdp_buff, data_end):
+		info->reg_type = PTR_TO_PACKET_END;
+		return true;
+	}
+	return false;
+}
+
 void bpf_warn_invalid_xdp_action(u32 act)
 {
 	const u32 act_max = XDP_REDIRECT;
@@ -3683,6 +3895,12 @@ static bool sk_skb_is_valid_access(int off, int size,
 				   enum bpf_access_type type,
 				   struct bpf_insn_access_aux *info)
 {
+	switch (off) {
+	case bpf_ctx_range(struct __sk_buff, tc_classid):
+	case bpf_ctx_range(struct __sk_buff, data_meta):
+		return false;
+	}
+
 	if (type == BPF_WRITE) {
 		switch (off) {
 		case bpf_ctx_range(struct __sk_buff, tc_index):
@@ -3695,7 +3913,6 @@ static bool sk_skb_is_valid_access(int off, int size,
 
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, mark):
-	case bpf_ctx_range(struct __sk_buff, tc_classid):
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
 		info->reg_type = PTR_TO_PACKET;
@@ -3853,6 +4070,15 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 				      offsetof(struct sk_buff, data));
 		break;
 
+	case offsetof(struct __sk_buff, data_meta):
+		off  = si->off;
+		off -= offsetof(struct __sk_buff, data_meta);
+		off += offsetof(struct sk_buff, cb);
+		off += offsetof(struct bpf_skb_data_end, data_meta);
+		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg,
+				      si->src_reg, off);
+		break;
+
 	case offsetof(struct __sk_buff, data_end):
 		off  = si->off;
 		off -= offsetof(struct __sk_buff, data_end);
@@ -4101,6 +4327,11 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 				      si->dst_reg, si->src_reg,
 				      offsetof(struct xdp_buff, data));
 		break;
+	case offsetof(struct xdp_md, data_meta):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct xdp_buff, data_meta));
+		break;
 	case offsetof(struct xdp_md, data_end):
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end),
 				      si->dst_reg, si->src_reg,
@@ -4269,68 +4500,103 @@ static u32 sk_skb_convert_ctx_access(enum bpf_access_type type,
 	return insn - insn_buf;
 }
 
-const struct bpf_verifier_ops sk_filter_prog_ops = {
+const struct bpf_verifier_ops sk_filter_verifier_ops = {
 	.get_func_proto		= sk_filter_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
 };
 
-const struct bpf_verifier_ops tc_cls_act_prog_ops = {
+const struct bpf_prog_ops sk_filter_prog_ops = {
+};
+
+const struct bpf_verifier_ops tc_cls_act_verifier_ops = {
 	.get_func_proto		= tc_cls_act_func_proto,
 	.is_valid_access	= tc_cls_act_is_valid_access,
 	.convert_ctx_access	= tc_cls_act_convert_ctx_access,
 	.gen_prologue		= tc_cls_act_prologue,
+};
+
+const struct bpf_verifier_ops tc_cls_act_analyzer_ops = {
+	.is_valid_access	= tc_cls_act_is_valid_access_analyzer,
+};
+
+const struct bpf_prog_ops tc_cls_act_prog_ops = {
 	.test_run		= bpf_prog_test_run_skb,
 };
 
-const struct bpf_verifier_ops xdp_prog_ops = {
+const struct bpf_verifier_ops xdp_verifier_ops = {
 	.get_func_proto		= xdp_func_proto,
 	.is_valid_access	= xdp_is_valid_access,
 	.convert_ctx_access	= xdp_convert_ctx_access,
+};
+
+const struct bpf_verifier_ops xdp_analyzer_ops = {
+	.is_valid_access	= xdp_is_valid_access_analyzer,
+};
+
+const struct bpf_prog_ops xdp_prog_ops = {
 	.test_run		= bpf_prog_test_run_xdp,
 };
 
-const struct bpf_verifier_ops cg_skb_prog_ops = {
+const struct bpf_verifier_ops cg_skb_verifier_ops = {
 	.get_func_proto		= sk_filter_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
+};
+
+const struct bpf_prog_ops cg_skb_prog_ops = {
 	.test_run		= bpf_prog_test_run_skb,
 };
 
-const struct bpf_verifier_ops lwt_inout_prog_ops = {
+const struct bpf_verifier_ops lwt_inout_verifier_ops = {
 	.get_func_proto		= lwt_inout_func_proto,
 	.is_valid_access	= lwt_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
+};
+
+const struct bpf_prog_ops lwt_inout_prog_ops = {
 	.test_run		= bpf_prog_test_run_skb,
 };
 
-const struct bpf_verifier_ops lwt_xmit_prog_ops = {
+const struct bpf_verifier_ops lwt_xmit_verifier_ops = {
 	.get_func_proto		= lwt_xmit_func_proto,
 	.is_valid_access	= lwt_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
 	.gen_prologue		= tc_cls_act_prologue,
+};
+
+const struct bpf_prog_ops lwt_xmit_prog_ops = {
 	.test_run		= bpf_prog_test_run_skb,
 };
 
-const struct bpf_verifier_ops cg_sock_prog_ops = {
+const struct bpf_verifier_ops cg_sock_verifier_ops = {
 	.get_func_proto		= sock_filter_func_proto,
 	.is_valid_access	= sock_filter_is_valid_access,
 	.convert_ctx_access	= sock_filter_convert_ctx_access,
 };
 
-const struct bpf_verifier_ops sock_ops_prog_ops = {
+const struct bpf_prog_ops cg_sock_prog_ops = {
+};
+
+const struct bpf_verifier_ops sock_ops_verifier_ops = {
 	.get_func_proto		= sock_ops_func_proto,
 	.is_valid_access	= sock_ops_is_valid_access,
 	.convert_ctx_access	= sock_ops_convert_ctx_access,
 };
 
-const struct bpf_verifier_ops sk_skb_prog_ops = {
+const struct bpf_prog_ops sock_ops_prog_ops = {
+};
+
+const struct bpf_verifier_ops sk_skb_verifier_ops = {
 	.get_func_proto		= sk_skb_func_proto,
 	.is_valid_access	= sk_skb_is_valid_access,
 	.convert_ctx_access	= sk_skb_convert_ctx_access,
 	.gen_prologue		= sk_skb_prologue,
 };
 
+const struct bpf_prog_ops sk_skb_prog_ops = {
+};
+
 int sk_detach_filter(struct sock *sk)
 {
 	int ret = -ENOENT;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 0a977373d003..1f5caafb4492 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -5,6 +5,7 @@
 #include <linux/ipv6.h>
 #include <linux/if_vlan.h>
 #include <net/dsa.h>
+#include <net/dst_metadata.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/gre.h>
@@ -115,6 +116,102 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
 }
 EXPORT_SYMBOL(__skb_flow_get_ports);
 
+static void
+skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type,
+				   struct flow_dissector *flow_dissector,
+				   void *target_container)
+{
+	struct flow_dissector_key_control *ctrl;
+
+	if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL))
+		return;
+
+	ctrl = skb_flow_dissector_target(flow_dissector,
+					 FLOW_DISSECTOR_KEY_ENC_CONTROL,
+					 target_container);
+	ctrl->addr_type = type;
+}
+
+static void
+__skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
+			       struct flow_dissector *flow_dissector,
+			       void *target_container)
+{
+	struct ip_tunnel_info *info;
+	struct ip_tunnel_key *key;
+
+	/* A quick check to see if there might be something to do. */
+	if (!dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_ENC_KEYID) &&
+	    !dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) &&
+	    !dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) &&
+	    !dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_ENC_CONTROL) &&
+	    !dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_ENC_PORTS))
+		return;
+
+	info = skb_tunnel_info(skb);
+	if (!info)
+		return;
+
+	key = &info->key;
+
+	switch (ip_tunnel_info_af(info)) {
+	case AF_INET:
+		skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+						   flow_dissector,
+						   target_container);
+		if (dissector_uses_key(flow_dissector,
+				       FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+			struct flow_dissector_key_ipv4_addrs *ipv4;
+
+			ipv4 = skb_flow_dissector_target(flow_dissector,
+							 FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
+							 target_container);
+			ipv4->src = key->u.ipv4.src;
+			ipv4->dst = key->u.ipv4.dst;
+		}
+		break;
+	case AF_INET6:
+		skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+						   flow_dissector,
+						   target_container);
+		if (dissector_uses_key(flow_dissector,
+				       FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
+			struct flow_dissector_key_ipv6_addrs *ipv6;
+
+			ipv6 = skb_flow_dissector_target(flow_dissector,
+							 FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS,
+							 target_container);
+			ipv6->src = key->u.ipv6.src;
+			ipv6->dst = key->u.ipv6.dst;
+		}
+		break;
+	}
+
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_dissector_key_keyid *keyid;
+
+		keyid = skb_flow_dissector_target(flow_dissector,
+						  FLOW_DISSECTOR_KEY_ENC_KEYID,
+						  target_container);
+		keyid->keyid = tunnel_id_to_key32(key->tun_id);
+	}
+
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
+		struct flow_dissector_key_ports *tp;
+
+		tp = skb_flow_dissector_target(flow_dissector,
+					       FLOW_DISSECTOR_KEY_ENC_PORTS,
+					       target_container);
+		tp->src = key->tp_src;
+		tp->dst = key->tp_dst;
+	}
+}
+
 static enum flow_dissect_ret
 __skb_flow_dissect_mpls(const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
@@ -478,6 +575,9 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 					      FLOW_DISSECTOR_KEY_BASIC,
 					      target_container);
 
+	__skb_flow_dissect_tunnel_info(skb, flow_dissector,
+				       target_container);
+
 	if (dissector_uses_key(flow_dissector,
 			       FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
 		struct ethhdr *eth = eth_hdr(skb);
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 1307731ddfe4..e7e626fb87bb 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -51,7 +51,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 	 */
 	preempt_disable();
 	rcu_read_lock();
-	bpf_compute_data_end(skb);
+	bpf_compute_data_pointers(skb);
 	ret = bpf_prog_run_save_cb(lwt->prog, skb);
 	rcu_read_unlock();
 
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 16a1a4c4eb57..6ea3a1a7f36a 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -457,7 +457,7 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
 				     const void *pkey)
 {
 	struct neighbour *n;
-	int key_len = tbl->key_len;
+	unsigned int key_len = tbl->key_len;
 	u32 hash_val;
 	struct neigh_hash_table *nht;
 
@@ -488,7 +488,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
 				 struct net_device *dev, bool want_ref)
 {
 	u32 hash_val;
-	int key_len = tbl->key_len;
+	unsigned int key_len = tbl->key_len;
 	int error;
 	struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev);
 	struct neigh_hash_table *nht;
@@ -572,7 +572,7 @@ out_neigh_release:
 }
 EXPORT_SYMBOL(__neigh_create);
 
-static u32 pneigh_hash(const void *pkey, int key_len)
+static u32 pneigh_hash(const void *pkey, unsigned int key_len)
 {
 	u32 hash_val = *(u32 *)(pkey + key_len - 4);
 	hash_val ^= (hash_val >> 16);
@@ -585,7 +585,7 @@ static u32 pneigh_hash(const void *pkey, int key_len)
 static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n,
 					      struct net *net,
 					      const void *pkey,
-					      int key_len,
+					      unsigned int key_len,
 					      struct net_device *dev)
 {
 	while (n) {
@@ -601,7 +601,7 @@ static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n,
 struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl,
 		struct net *net, const void *pkey, struct net_device *dev)
 {
-	int key_len = tbl->key_len;
+	unsigned int key_len = tbl->key_len;
 	u32 hash_val = pneigh_hash(pkey, key_len);
 
 	return __pneigh_lookup_1(tbl->phash_buckets[hash_val],
@@ -614,7 +614,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
 				    struct net_device *dev, int creat)
 {
 	struct pneigh_entry *n;
-	int key_len = tbl->key_len;
+	unsigned int key_len = tbl->key_len;
 	u32 hash_val = pneigh_hash(pkey, key_len);
 
 	read_lock_bh(&tbl->lock);
@@ -659,7 +659,7 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
 		  struct net_device *dev)
 {
 	struct pneigh_entry *n, **np;
-	int key_len = tbl->key_len;
+	unsigned int key_len = tbl->key_len;
 	u32 hash_val = pneigh_hash(pkey, key_len);
 
 	write_lock_bh(&tbl->lock);
@@ -1662,7 +1662,7 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tbl == NULL)
 		return -EAFNOSUPPORT;
 
-	if (nla_len(dst_attr) < tbl->key_len)
+	if (nla_len(dst_attr) < (int)tbl->key_len)
 		goto out;
 
 	if (ndm->ndm_flags & NTF_PROXY) {
@@ -1730,7 +1730,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tbl == NULL)
 		return -EAFNOSUPPORT;
 
-	if (nla_len(tb[NDA_DST]) < tbl->key_len)
+	if (nla_len(tb[NDA_DST]) < (int)tbl->key_len)
 		goto out;
 	dst = nla_data(tb[NDA_DST]);
 	lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 927a6dcbad96..51d5836d8fb9 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -391,10 +391,7 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
 	if (len >  0 && buf[len - 1] == '\n')
 		--count;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
 	ret = dev_set_alias(netdev, buf, count);
-	rtnl_unlock();
 
 	return ret < 0 ? ret : len;
 }
@@ -403,13 +400,12 @@ static ssize_t ifalias_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
 	const struct net_device *netdev = to_net_dev(dev);
+	char tmp[IFALIASZ];
 	ssize_t ret = 0;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
-	if (netdev->ifalias)
-		ret = sprintf(buf, "%s\n", netdev->ifalias);
-	rtnl_unlock();
+	ret = dev_get_alias(netdev, tmp, sizeof(tmp));
+	if (ret > 0)
+		ret = sprintf(buf, "%s\n", tmp);
 	return ret;
 }
 static DEVICE_ATTR_RW(ifalias);
@@ -1488,7 +1484,10 @@ static void netdev_release(struct device *d)
 
 	BUG_ON(dev->reg_state != NETREG_RELEASED);
 
-	kfree(dev->ifalias);
+	/* no need to wait for rcu grace period:
+	 * device is dead and about to be freed.
+	 */
+	kfree(rcu_access_pointer(dev->ifalias));
 	netdev_freemem(dev);
 }
 
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index 71f209542364..380934580fa1 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -32,6 +32,7 @@
 #include <trace/events/napi.h>
 #include <trace/events/sock.h>
 #include <trace/events/udp.h>
+#include <trace/events/tcp.h>
 #include <trace/events/fib.h>
 #include <trace/events/qdisc.h>
 #if IS_ENABLED(CONFIG_IPV6)
@@ -49,3 +50,5 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_update);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5ace48926b19..de24d394c69e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -453,7 +453,7 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family)
 {
 	const struct rtnl_af_ops *ops;
 
-	list_for_each_entry(ops, &rtnl_af_ops, list) {
+	list_for_each_entry_rcu(ops, &rtnl_af_ops, list) {
 		if (ops->family == family)
 			return ops;
 	}
@@ -470,32 +470,22 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family)
 void rtnl_af_register(struct rtnl_af_ops *ops)
 {
 	rtnl_lock();
-	list_add_tail(&ops->list, &rtnl_af_ops);
+	list_add_tail_rcu(&ops->list, &rtnl_af_ops);
 	rtnl_unlock();
 }
 EXPORT_SYMBOL_GPL(rtnl_af_register);
 
 /**
- * __rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink.
- * @ops: struct rtnl_af_ops * to unregister
- *
- * The caller must hold the rtnl_mutex.
- */
-void __rtnl_af_unregister(struct rtnl_af_ops *ops)
-{
-	list_del(&ops->list);
-}
-EXPORT_SYMBOL_GPL(__rtnl_af_unregister);
-
-/**
  * rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink.
  * @ops: struct rtnl_af_ops * to unregister
  */
 void rtnl_af_unregister(struct rtnl_af_ops *ops)
 {
 	rtnl_lock();
-	__rtnl_af_unregister(ops);
+	list_del_rcu(&ops->list);
 	rtnl_unlock();
+
+	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(rtnl_af_unregister);
 
@@ -508,13 +498,15 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev,
 	/* IFLA_AF_SPEC */
 	size = nla_total_size(sizeof(struct nlattr));
 
-	list_for_each_entry(af_ops, &rtnl_af_ops, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
 		if (af_ops->get_link_af_size) {
 			/* AF_* + nested data */
 			size += nla_total_size(sizeof(struct nlattr)) +
 				af_ops->get_link_af_size(dev, ext_filter_mask);
 		}
 	}
+	rcu_read_unlock();
 
 	return size;
 }
@@ -522,11 +514,15 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev,
 static bool rtnl_have_link_slave_info(const struct net_device *dev)
 {
 	struct net_device *master_dev;
+	bool ret = false;
 
-	master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
+	rcu_read_lock();
+
+	master_dev = netdev_master_upper_dev_get_rcu((struct net_device *)dev);
 	if (master_dev && master_dev->rtnl_link_ops)
-		return true;
-	return false;
+		ret = true;
+	rcu_read_unlock();
+	return ret;
 }
 
 static int rtnl_link_slave_info_fill(struct sk_buff *skb,
@@ -923,6 +919,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
 	       + rtnl_xdp_size() /* IFLA_XDP */
 	       + nla_total_size(4)  /* IFLA_EVENT */
+	       + nla_total_size(4)  /* IFLA_NEW_NETNSID */
 	       + nla_total_size(1); /* IFLA_PROTO_DOWN */
 
 }
@@ -1211,6 +1208,36 @@ nla_put_vfinfo_failure:
 	return -EMSGSIZE;
 }
 
+static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb,
+					   struct net_device *dev,
+					   u32 ext_filter_mask)
+{
+	struct nlattr *vfinfo;
+	int i, num_vfs;
+
+	if (!dev->dev.parent || ((ext_filter_mask & RTEXT_FILTER_VF) == 0))
+		return 0;
+
+	num_vfs = dev_num_vf(dev->dev.parent);
+	if (nla_put_u32(skb, IFLA_NUM_VF, num_vfs))
+		return -EMSGSIZE;
+
+	if (!dev->netdev_ops->ndo_get_vf_config)
+		return 0;
+
+	vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST);
+	if (!vfinfo)
+		return -EMSGSIZE;
+
+	for (i = 0; i < num_vfs; i++) {
+		if (rtnl_fill_vfinfo(skb, dev, i, vfinfo))
+			return -EMSGSIZE;
+	}
+
+	nla_nest_end(skb, vfinfo);
+	return 0;
+}
+
 static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
 {
 	struct rtnl_link_ifmap map;
@@ -1307,16 +1334,106 @@ static u32 rtnl_get_event(unsigned long event)
 	return rtnl_event_type;
 }
 
+static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct net_device *upper_dev;
+	int ret = 0;
+
+	rcu_read_lock();
+
+	upper_dev = netdev_master_upper_dev_get_rcu(dev);
+	if (upper_dev)
+		ret = nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex);
+
+	rcu_read_unlock();
+	return ret;
+}
+
+static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev)
+{
+	int ifindex = dev_get_iflink(dev);
+
+	if (dev->ifindex == ifindex)
+		return 0;
+
+	return nla_put_u32(skb, IFLA_LINK, ifindex);
+}
+
+static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb,
+					      struct net_device *dev)
+{
+	char buf[IFALIASZ];
+	int ret;
+
+	ret = dev_get_alias(dev, buf, sizeof(buf));
+	return ret > 0 ? nla_put_string(skb, IFLA_IFALIAS, buf) : 0;
+}
+
+static int rtnl_fill_link_netnsid(struct sk_buff *skb,
+				  const struct net_device *dev)
+{
+	if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) {
+		struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
+
+		if (!net_eq(dev_net(dev), link_net)) {
+			int id = peernet2id_alloc(dev_net(dev), link_net);
+
+			if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
+				return -EMSGSIZE;
+		}
+	}
+
+	return 0;
+}
+
+static int rtnl_fill_link_af(struct sk_buff *skb,
+			     const struct net_device *dev,
+			     u32 ext_filter_mask)
+{
+	const struct rtnl_af_ops *af_ops;
+	struct nlattr *af_spec;
+
+	af_spec = nla_nest_start(skb, IFLA_AF_SPEC);
+	if (!af_spec)
+		return -EMSGSIZE;
+
+	list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
+		struct nlattr *af;
+		int err;
+
+		if (!af_ops->fill_link_af)
+			continue;
+
+		af = nla_nest_start(skb, af_ops->family);
+		if (!af)
+			return -EMSGSIZE;
+
+		err = af_ops->fill_link_af(skb, dev, ext_filter_mask);
+		/*
+		 * Caller may return ENODATA to indicate that there
+		 * was no data to be dumped. This is not an error, it
+		 * means we should trim the attribute header and
+		 * continue.
+		 */
+		if (err == -ENODATA)
+			nla_nest_cancel(skb, af);
+		else if (err < 0)
+			return -EMSGSIZE;
+
+		nla_nest_end(skb, af);
+	}
+
+	nla_nest_end(skb, af_spec);
+	return 0;
+}
+
 static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			    int type, u32 pid, u32 seq, u32 change,
 			    unsigned int flags, u32 ext_filter_mask,
-			    u32 event)
+			    u32 event, int *new_nsid)
 {
 	struct ifinfomsg *ifm;
 	struct nlmsghdr *nlh;
-	struct nlattr *af_spec;
-	struct rtnl_af_ops *af_ops;
-	struct net_device *upper_dev = netdev_master_upper_dev_get(dev);
 
 	ASSERT_RTNL();
 	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags);
@@ -1345,15 +1462,12 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 #ifdef CONFIG_RPS
 	    nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
 #endif
-	    (dev->ifindex != dev_get_iflink(dev) &&
-	     nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) ||
-	    (upper_dev &&
-	     nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) ||
+	    nla_put_iflink(skb, dev) ||
+	    put_master_ifindex(skb, dev) ||
 	    nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) ||
 	    (dev->qdisc &&
 	     nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) ||
-	    (dev->ifalias &&
-	     nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) ||
+	    nla_put_ifalias(skb, dev) ||
 	    nla_put_u32(skb, IFLA_CARRIER_CHANGES,
 			atomic_read(&dev->carrier_changes)) ||
 	    nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down))
@@ -1385,27 +1499,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 	if (rtnl_fill_stats(skb, dev))
 		goto nla_put_failure;
 
-	if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF) &&
-	    nla_put_u32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)))
+	if (rtnl_fill_vf(skb, dev, ext_filter_mask))
 		goto nla_put_failure;
 
-	if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent &&
-	    ext_filter_mask & RTEXT_FILTER_VF) {
-		int i;
-		struct nlattr *vfinfo;
-		int num_vfs = dev_num_vf(dev->dev.parent);
-
-		vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST);
-		if (!vfinfo)
-			goto nla_put_failure;
-		for (i = 0; i < num_vfs; i++) {
-			if (rtnl_fill_vfinfo(skb, dev, i, vfinfo))
-				goto nla_put_failure;
-		}
-
-		nla_nest_end(skb, vfinfo);
-	}
-
 	if (rtnl_port_fill(skb, dev, ext_filter_mask))
 		goto nla_put_failure;
 
@@ -1417,51 +1513,23 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			goto nla_put_failure;
 	}
 
-	if (dev->rtnl_link_ops &&
-	    dev->rtnl_link_ops->get_link_net) {
-		struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
-
-		if (!net_eq(dev_net(dev), link_net)) {
-			int id = peernet2id_alloc(dev_net(dev), link_net);
-
-			if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
-				goto nla_put_failure;
-		}
-	}
-
-	if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC)))
+	if (rtnl_fill_link_netnsid(skb, dev))
 		goto nla_put_failure;
 
-	list_for_each_entry(af_ops, &rtnl_af_ops, list) {
-		if (af_ops->fill_link_af) {
-			struct nlattr *af;
-			int err;
-
-			if (!(af = nla_nest_start(skb, af_ops->family)))
-				goto nla_put_failure;
-
-			err = af_ops->fill_link_af(skb, dev, ext_filter_mask);
-
-			/*
-			 * Caller may return ENODATA to indicate that there
-			 * was no data to be dumped. This is not an error, it
-			 * means we should trim the attribute header and
-			 * continue.
-			 */
-			if (err == -ENODATA)
-				nla_nest_cancel(skb, af);
-			else if (err < 0)
-				goto nla_put_failure;
-
-			nla_nest_end(skb, af);
-		}
-	}
+	if (new_nsid &&
+	    nla_put_s32(skb, IFLA_NEW_NETNSID, *new_nsid) < 0)
+		goto nla_put_failure;
 
-	nla_nest_end(skb, af_spec);
+	rcu_read_lock();
+	if (rtnl_fill_link_af(skb, dev, ext_filter_mask))
+		goto nla_put_failure_rcu;
+	rcu_read_unlock();
 
 	nlmsg_end(skb, nlh);
 	return 0;
 
+nla_put_failure_rcu:
+	rcu_read_unlock();
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
 	return -EMSGSIZE;
@@ -1661,7 +1729,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq, 0,
 					       flags,
-					       ext_filter_mask, 0);
+					       ext_filter_mask, 0, NULL);
 
 			if (err < 0) {
 				if (likely(skb->len))
@@ -1726,17 +1794,27 @@ 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;
 
-			if (!(af_ops = rtnl_af_lookup(nla_type(af))))
+			rcu_read_lock();
+			af_ops = rtnl_af_lookup(nla_type(af));
+			if (!af_ops) {
+				rcu_read_unlock();
 				return -EAFNOSUPPORT;
+			}
 
-			if (!af_ops->set_link_af)
+			if (!af_ops->set_link_af) {
+				rcu_read_unlock();
 				return -EOPNOTSUPP;
+			}
 
 			if (af_ops->validate_link_af) {
 				err = af_ops->validate_link_af(dev, af);
-				if (err < 0)
+				if (err < 0) {
+					rcu_read_unlock();
 					return err;
+				}
 			}
+
+			rcu_read_unlock();
 		}
 	}
 
@@ -1912,7 +1990,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	return err;
 }
 
-static int do_set_master(struct net_device *dev, int ifindex)
+static int do_set_master(struct net_device *dev, int ifindex,
+			 struct netlink_ext_ack *extack)
 {
 	struct net_device *upper_dev = netdev_master_upper_dev_get(dev);
 	const struct net_device_ops *ops;
@@ -1937,7 +2016,7 @@ static int do_set_master(struct net_device *dev, int ifindex)
 			return -EINVAL;
 		ops = upper_dev->netdev_ops;
 		if (ops->ndo_add_slave) {
-			err = ops->ndo_add_slave(upper_dev, dev);
+			err = ops->ndo_add_slave(upper_dev, dev, extack);
 			if (err)
 				return err;
 		} else {
@@ -2070,7 +2149,7 @@ static int do_setlink(const struct sk_buff *skb,
 	}
 
 	if (tb[IFLA_MASTER]) {
-		err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]));
+		err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
 		if (err)
 			goto errout;
 		status |= DO_SETLINK_MODIFIED;
@@ -2193,13 +2272,17 @@ 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;
 
-			if (!(af_ops = rtnl_af_lookup(nla_type(af))))
-				BUG();
+			rcu_read_lock();
+
+			BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af))));
 
 			err = af_ops->set_link_af(dev, af);
-			if (err < 0)
+			if (err < 0) {
+				rcu_read_unlock();
 				goto errout;
+			}
 
+			rcu_read_unlock();
 			status |= DO_SETLINK_NOTIFY;
 		}
 	}
@@ -2579,12 +2662,6 @@ replay:
 					return err;
 				slave_data = slave_attr;
 			}
-			if (m_ops->slave_validate) {
-				err = m_ops->slave_validate(tb, slave_data,
-							    extack);
-				if (err < 0)
-					return err;
-			}
 		}
 
 		if (dev) {
@@ -2714,7 +2791,8 @@ replay:
 				goto out_unregister;
 		}
 		if (tb[IFLA_MASTER]) {
-			err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]));
+			err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]),
+					    extack);
 			if (err)
 				goto out_unregister;
 		}
@@ -2774,7 +2852,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -ENOBUFS;
 
 	err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid,
-			       nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0);
+			       nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0, NULL);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in if_nlmsg_size */
 		WARN_ON(err == -EMSGSIZE);
@@ -2859,7 +2937,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 
 struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
 				       unsigned int change,
-				       u32 event, gfp_t flags)
+				       u32 event, gfp_t flags, int *new_nsid)
 {
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
@@ -2870,7 +2948,8 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
 	if (skb == NULL)
 		goto errout;
 
-	err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event);
+	err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event,
+			       new_nsid);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in if_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -2893,14 +2972,14 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags)
 
 static void rtmsg_ifinfo_event(int type, struct net_device *dev,
 			       unsigned int change, u32 event,
-			       gfp_t flags)
+			       gfp_t flags, int *new_nsid)
 {
 	struct sk_buff *skb;
 
 	if (dev->reg_state != NETREG_REGISTERED)
 		return;
 
-	skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags);
+	skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid);
 	if (skb)
 		rtmsg_ifinfo_send(skb, dev, flags);
 }
@@ -2908,9 +2987,15 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev,
 void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
 		  gfp_t flags)
 {
-	rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags);
+	rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, NULL);
+}
+
+void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change,
+			 gfp_t flags, int *new_nsid)
+{
+	rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags,
+			   new_nsid);
 }
-EXPORT_SYMBOL(rtmsg_ifinfo);
 
 static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
 				   struct net_device *dev,
@@ -3017,21 +3102,21 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm,
 }
 EXPORT_SYMBOL(ndo_dflt_fdb_add);
 
-static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid)
+static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid,
+			 struct netlink_ext_ack *extack)
 {
 	u16 vid = 0;
 
 	if (vlan_attr) {
 		if (nla_len(vlan_attr) != sizeof(u16)) {
-			pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan\n");
+			NL_SET_ERR_MSG(extack, "invalid vlan attribute size");
 			return -EINVAL;
 		}
 
 		vid = nla_get_u16(vlan_attr);
 
 		if (!vid || vid >= VLAN_VID_MASK) {
-			pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan id %d\n",
-				vid);
+			NL_SET_ERR_MSG(extack, "invalid vlan id");
 			return -EINVAL;
 		}
 	}
@@ -3056,24 +3141,24 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	ndm = nlmsg_data(nlh);
 	if (ndm->ndm_ifindex == 0) {
-		pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ifindex\n");
+		NL_SET_ERR_MSG(extack, "invalid ifindex");
 		return -EINVAL;
 	}
 
 	dev = __dev_get_by_index(net, ndm->ndm_ifindex);
 	if (dev == NULL) {
-		pr_info("PF_BRIDGE: RTM_NEWNEIGH with unknown ifindex\n");
+		NL_SET_ERR_MSG(extack, "unknown ifindex");
 		return -ENODEV;
 	}
 
 	if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
-		pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid address\n");
+		NL_SET_ERR_MSG(extack, "invalid address");
 		return -EINVAL;
 	}
 
 	addr = nla_data(tb[NDA_LLADDR]);
 
-	err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+	err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
 	if (err)
 		return err;
 
@@ -3160,24 +3245,24 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	ndm = nlmsg_data(nlh);
 	if (ndm->ndm_ifindex == 0) {
-		pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ifindex\n");
+		NL_SET_ERR_MSG(extack, "invalid ifindex");
 		return -EINVAL;
 	}
 
 	dev = __dev_get_by_index(net, ndm->ndm_ifindex);
 	if (dev == NULL) {
-		pr_info("PF_BRIDGE: RTM_DELNEIGH with unknown ifindex\n");
+		NL_SET_ERR_MSG(extack, "unknown ifindex");
 		return -ENODEV;
 	}
 
 	if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
-		pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid address\n");
+		NL_SET_ERR_MSG(extack, "invalid address");
 		return -EINVAL;
 	}
 
 	addr = nla_data(tb[NDA_LLADDR]);
 
-	err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+	err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
 	if (err)
 		return err;
 
@@ -3617,7 +3702,7 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	dev = __dev_get_by_index(net, ifm->ifi_index);
 	if (!dev) {
-		pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n");
+		NL_SET_ERR_MSG(extack, "unknown ifindex");
 		return -ENODEV;
 	}
 
@@ -3692,7 +3777,7 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	dev = __dev_get_by_index(net, ifm->ifi_index);
 	if (!dev) {
-		pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n");
+		NL_SET_ERR_MSG(extack, "unknown ifindex");
 		return -ENODEV;
 	}
 
@@ -3943,25 +4028,30 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
 		if (!attr)
 			goto nla_put_failure;
 
-		list_for_each_entry(af_ops, &rtnl_af_ops, list) {
+		rcu_read_lock();
+		list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
 			if (af_ops->fill_stats_af) {
 				struct nlattr *af;
 				int err;
 
 				af = nla_nest_start(skb, af_ops->family);
-				if (!af)
+				if (!af) {
+					rcu_read_unlock();
 					goto nla_put_failure;
-
+				}
 				err = af_ops->fill_stats_af(skb, dev);
 
-				if (err == -ENODATA)
+				if (err == -ENODATA) {
 					nla_nest_cancel(skb, af);
-				else if (err < 0)
+				} else if (err < 0) {
+					rcu_read_unlock();
 					goto nla_put_failure;
+				}
 
 				nla_nest_end(skb, af);
 			}
 		}
+		rcu_read_unlock();
 
 		nla_nest_end(skb, attr);
 
@@ -4030,7 +4120,8 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev,
 		/* for IFLA_STATS_AF_SPEC */
 		size += nla_total_size(0);
 
-		list_for_each_entry(af_ops, &rtnl_af_ops, list) {
+		rcu_read_lock();
+		list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
 			if (af_ops->get_stats_af_size) {
 				size += nla_total_size(
 					af_ops->get_stats_af_size(dev));
@@ -4039,6 +4130,7 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev,
 				size += nla_total_size(0);
 			}
 		}
+		rcu_read_unlock();
 	}
 
 	return size;
@@ -4292,9 +4384,10 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
 	case NETDEV_CHANGEUPPER:
 	case NETDEV_RESEND_IGMP:
 	case NETDEV_CHANGEINFODATA:
+	case NETDEV_CHANGELOWERSTATE:
 	case NETDEV_CHANGE_TX_QUEUE_LEN:
 		rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event),
-				   GFP_KERNEL);
+				   GFP_KERNEL, NULL);
 		break;
 	default:
 		break;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 24656076906d..97e604d55d55 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1354,8 +1354,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
 	/* Set the tail pointer and length */
 	skb_put(n, skb->len);
 
-	if (skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len))
-		BUG();
+	BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len));
 
 	copy_skb_header(n, skb);
 	return n;
@@ -1453,8 +1452,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 
 	BUG_ON(nhead < 0);
 
-	if (skb_shared(skb))
-		BUG();
+	BUG_ON(skb_shared(skb));
 
 	size = SKB_DATA_ALIGN(size);
 
@@ -1513,6 +1511,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 	skb->nohdr    = 0;
 	atomic_set(&skb_shinfo(skb)->dataref, 1);
 
+	skb_metadata_clear(skb);
+
 	/* It is not generally safe to change skb->truesize.
 	 * For the moment, we really care of rx path, or
 	 * when skb is orphaned (not attached to a socket).
@@ -1597,9 +1597,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
 		head_copy_off = newheadroom - head_copy_len;
 
 	/* Copy the linear header and data. */
-	if (skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
-			  skb->len + head_copy_len))
-		BUG();
+	BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
+			     skb->len + head_copy_len));
 
 	copy_skb_header(n, skb);
 
@@ -1880,8 +1879,8 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta)
 			return NULL;
 	}
 
-	if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta))
-		BUG();
+	BUG_ON(skb_copy_bits(skb, skb_headlen(skb),
+			     skb_tail_pointer(skb), delta));
 
 	/* Optimization: no fragments, no reasons to preestimate
 	 * size of pulled pages. Superb.
@@ -2852,12 +2851,15 @@ EXPORT_SYMBOL(skb_queue_purge);
  */
 void skb_rbtree_purge(struct rb_root *root)
 {
-	struct sk_buff *skb, *next;
+	struct rb_node *p = rb_first(root);
 
-	rbtree_postorder_for_each_entry_safe(skb, next, root, rbnode)
-		kfree_skb(skb);
+	while (p) {
+		struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
 
-	*root = RB_ROOT;
+		p = rb_next(p);
+		rb_erase(&skb->rbnode, root);
+		kfree_skb(skb);
+	}
 }
 
 /**
@@ -4766,6 +4768,7 @@ EXPORT_SYMBOL(kfree_skb_partial);
 bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 		      bool *fragstolen, int *delta_truesize)
 {
+	struct skb_shared_info *to_shinfo, *from_shinfo;
 	int i, delta, len = from->len;
 
 	*fragstolen = false;
@@ -4780,7 +4783,9 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 		return true;
 	}
 
-	if (skb_has_frag_list(to) || skb_has_frag_list(from))
+	to_shinfo = skb_shinfo(to);
+	from_shinfo = skb_shinfo(from);
+	if (to_shinfo->frag_list || from_shinfo->frag_list)
 		return false;
 	if (skb_zcopy(to) || skb_zcopy(from))
 		return false;
@@ -4789,8 +4794,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 		struct page *page;
 		unsigned int offset;
 
-		if (skb_shinfo(to)->nr_frags +
-		    skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS)
+		if (to_shinfo->nr_frags +
+		    from_shinfo->nr_frags >= MAX_SKB_FRAGS)
 			return false;
 
 		if (skb_head_is_locked(from))
@@ -4801,12 +4806,12 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 		page = virt_to_head_page(from->head);
 		offset = from->data - (unsigned char *)page_address(page);
 
-		skb_fill_page_desc(to, skb_shinfo(to)->nr_frags,
+		skb_fill_page_desc(to, to_shinfo->nr_frags,
 				   page, offset, skb_headlen(from));
 		*fragstolen = true;
 	} else {
-		if (skb_shinfo(to)->nr_frags +
-		    skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS)
+		if (to_shinfo->nr_frags +
+		    from_shinfo->nr_frags > MAX_SKB_FRAGS)
 			return false;
 
 		delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from));
@@ -4814,19 +4819,19 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 
 	WARN_ON_ONCE(delta < len);
 
-	memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags,
-	       skb_shinfo(from)->frags,
-	       skb_shinfo(from)->nr_frags * sizeof(skb_frag_t));
-	skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags;
+	memcpy(to_shinfo->frags + to_shinfo->nr_frags,
+	       from_shinfo->frags,
+	       from_shinfo->nr_frags * sizeof(skb_frag_t));
+	to_shinfo->nr_frags += from_shinfo->nr_frags;
 
 	if (!skb_cloned(from))
-		skb_shinfo(from)->nr_frags = 0;
+		from_shinfo->nr_frags = 0;
 
 	/* if the skb is not cloned this does nothing
 	 * since we set nr_frags to 0.
 	 */
-	for (i = 0; i < skb_shinfo(from)->nr_frags; i++)
-		skb_frag_ref(from, i);
+	for (i = 0; i < from_shinfo->nr_frags; i++)
+		__skb_frag_ref(&from_shinfo->frags[i]);
 
 	to->truesize += delta;
 	to->len += len;
diff --git a/net/core/sock.c b/net/core/sock.c
index 415f441c63b9..759400053110 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2685,7 +2685,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk_init_common(sk);
 	sk->sk_send_head	=	NULL;
 
-	init_timer(&sk->sk_timer);
+	timer_setup(&sk->sk_timer, NULL, 0);
 
 	sk->sk_allocation	=	GFP_KERNEL;
 	sk->sk_rcvbuf		=	sysctl_rmem_default;
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index e1295d5f2c56..1c75cd1255f6 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -126,10 +126,10 @@ static void ccid2_change_l_seq_window(struct sock *sk, u64 val)
 						  DCCPF_SEQ_WMAX));
 }
 
-static void ccid2_hc_tx_rto_expire(unsigned long data)
+static void ccid2_hc_tx_rto_expire(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)data;
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+	struct ccid2_hc_tx_sock *hc = from_timer(hc, t, tx_rtotimer);
+	struct sock *sk = hc->sk;
 	const bool sender_was_blocked = ccid2_cwnd_network_limited(hc);
 
 	bh_lock_sock(sk);
@@ -733,8 +733,8 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
 	hc->tx_rpdupack  = -1;
 	hc->tx_last_cong = hc->tx_lsndtime = hc->tx_cwnd_stamp = ccid2_jiffies32;
 	hc->tx_cwnd_used = 0;
-	setup_timer(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire,
-			(unsigned long)sk);
+	hc->sk		 = sk;
+	timer_setup(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire, 0);
 	INIT_LIST_HEAD(&hc->tx_av_chunks);
 	return 0;
 }
diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h
index 6e50ef2898fb..1af0116dc6ce 100644
--- a/net/dccp/ccids/ccid2.h
+++ b/net/dccp/ccids/ccid2.h
@@ -85,6 +85,7 @@ struct ccid2_hc_tx_sock {
 				tx_rto;
 	u64			tx_rtt_seq:48;
 	struct timer_list	tx_rtotimer;
+	struct sock		*sk;
 
 	/* Congestion Window validation (optional, RFC 2861) */
 	u32			tx_cwnd_used,
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index 119c04317d48..8b5ba6dffac7 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -195,10 +195,10 @@ static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hc,
 	}
 }
 
-static void ccid3_hc_tx_no_feedback_timer(unsigned long data)
+static void ccid3_hc_tx_no_feedback_timer(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)data;
-	struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
+	struct ccid3_hc_tx_sock *hc = from_timer(hc, t, tx_no_feedback_timer);
+	struct sock *sk = hc->sk;
 	unsigned long t_nfb = USEC_PER_SEC / 5;
 
 	bh_lock_sock(sk);
@@ -505,8 +505,9 @@ static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk)
 
 	hc->tx_state = TFRC_SSTATE_NO_SENT;
 	hc->tx_hist  = NULL;
-	setup_timer(&hc->tx_no_feedback_timer,
-			ccid3_hc_tx_no_feedback_timer, (unsigned long)sk);
+	hc->sk	     = sk;
+	timer_setup(&hc->tx_no_feedback_timer,
+		    ccid3_hc_tx_no_feedback_timer, 0);
 	return 0;
 }
 
diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h
index 1a9933c29672..813d91c6e1e2 100644
--- a/net/dccp/ccids/ccid3.h
+++ b/net/dccp/ccids/ccid3.h
@@ -106,6 +106,7 @@ struct ccid3_hc_tx_sock {
 	u8				tx_last_win_count;
 	ktime_t				tx_t_last_win_count;
 	struct timer_list		tx_no_feedback_timer;
+	struct sock			*sk;
 	ktime_t				tx_t_ld;
 	ktime_t				tx_t_nom;
 	struct tfrc_tx_hist_entry	*tx_hist;
diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c
index 08df7a3acb3d..876e18592d71 100644
--- a/net/dccp/ccids/lib/packet_history.c
+++ b/net/dccp/ccids/lib/packet_history.c
@@ -149,10 +149,8 @@ static void tfrc_rx_hist_swap(struct tfrc_rx_hist *h, const u8 a, const u8 b)
 {
 	const u8 idx_a = tfrc_rx_hist_index(h, a),
 		 idx_b = tfrc_rx_hist_index(h, b);
-	struct tfrc_rx_hist_entry *tmp = h->ring[idx_a];
 
-	h->ring[idx_a] = h->ring[idx_b];
-	h->ring[idx_b] = tmp;
+	swap(h->ring[idx_a], h->ring[idx_b]);
 }
 
 /*
diff --git a/net/dccp/input.c b/net/dccp/input.c
index fa6be9750bb4..d28d46bff6ab 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -534,6 +534,7 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk,
 	case DCCP_PKT_DATA:
 		if (sk->sk_state == DCCP_RESPOND)
 			break;
+		/* fall through */
 	case DCCP_PKT_DATAACK:
 	case DCCP_PKT_ACK:
 		/*
diff --git a/net/dccp/options.c b/net/dccp/options.c
index 51cdfc3bd8ca..4e40db017e19 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -227,8 +227,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
 			 * Ack vectors are processed by the TX CCID if it is
 			 * interested. The RX CCID need not parse Ack Vectors,
 			 * since it is only interested in clearing old state.
-			 * Fall through.
 			 */
+			/* fall through */
 		case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC:
 			if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk,
 						     pkt_type, opt, value, len))
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 3a2c34027758..b50a8732ff43 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -125,10 +125,11 @@ static void dccp_retransmit_timer(struct sock *sk)
 		__sk_dst_reset(sk);
 }
 
-static void dccp_write_timer(unsigned long data)
+static void dccp_write_timer(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)data;
-	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct inet_connection_sock *icsk =
+			from_timer(icsk, t, icsk_retransmit_timer);
+	struct sock *sk = &icsk->icsk_inet.sk;
 	int event = 0;
 
 	bh_lock_sock(sk);
@@ -161,19 +162,20 @@ out:
 	sock_put(sk);
 }
 
-static void dccp_keepalive_timer(unsigned long data)
+static void dccp_keepalive_timer(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)data;
+	struct sock *sk = from_timer(sk, t, sk_timer);
 
 	pr_err("dccp should not use a keepalive timer !\n");
 	sock_put(sk);
 }
 
 /* This is the same as tcp_delack_timer, sans prequeue & mem_reclaim stuff */
-static void dccp_delack_timer(unsigned long data)
+static void dccp_delack_timer(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)data;
-	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct inet_connection_sock *icsk =
+			from_timer(icsk, t, icsk_delack_timer);
+	struct sock *sk = &icsk->icsk_inet.sk;
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
@@ -232,10 +234,13 @@ static void dccp_write_xmitlet(unsigned long data)
 	bh_unlock_sock(sk);
 }
 
-static void dccp_write_xmit_timer(unsigned long data)
+static void dccp_write_xmit_timer(struct timer_list *t)
 {
-	dccp_write_xmitlet(data);
-	sock_put((struct sock *)data);
+	struct dccp_sock *dp = from_timer(dp, t, dccps_xmit_timer);
+	struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
+
+	dccp_write_xmitlet((unsigned long)sk);
+	sock_put(sk);
 }
 
 void dccp_init_xmit_timers(struct sock *sk)
@@ -243,8 +248,7 @@ void dccp_init_xmit_timers(struct sock *sk)
 	struct dccp_sock *dp = dccp_sk(sk);
 
 	tasklet_init(&dp->dccps_xmitlet, dccp_write_xmitlet, (unsigned long)sk);
-	setup_timer(&dp->dccps_xmit_timer, dccp_write_xmit_timer,
-							     (unsigned long)sk);
+	timer_setup(&dp->dccps_xmit_timer, dccp_write_xmit_timer, 0);
 	inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer,
 				  &dccp_keepalive_timer);
 }
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 73a0399dc7a2..518cea17b811 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -533,10 +533,6 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf
 	scp->keepalive = 10 * HZ;
 	scp->keepalive_fxn = dn_keepalive;
 
-	init_timer(&scp->delack_timer);
-	scp->delack_pending = 0;
-	scp->delack_fxn = dn_nsp_delayed_ack;
-
 	dn_start_slow_timer(sk);
 out:
 	return sk;
@@ -634,10 +630,12 @@ static void dn_destroy_sock(struct sock *sk)
 		goto disc_reject;
 	case DN_RUN:
 		scp->state = DN_DI;
+		/* fall through */
 	case DN_DI:
 	case DN_DR:
 disc_reject:
 		dn_nsp_send_disc(sk, NSP_DISCINIT, 0, sk->sk_allocation);
+		/* fall through */
 	case DN_NC:
 	case DN_NR:
 	case DN_RJ:
@@ -651,6 +649,7 @@ disc_reject:
 		break;
 	default:
 		printk(KERN_DEBUG "DECnet: dn_destroy_sock passed socket in invalid state\n");
+		/* fall through */
 	case DN_O:
 		dn_stop_slow_timer(sk);
 
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index df042b6d80b8..9153247dad28 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -1039,14 +1039,14 @@ static void dn_eth_down(struct net_device *dev)
 
 static void dn_dev_set_timer(struct net_device *dev);
 
-static void dn_dev_timer_func(unsigned long arg)
+static void dn_dev_timer_func(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)arg;
-	struct dn_dev *dn_db;
+	struct dn_dev *dn_db = from_timer(dn_db, t, timer);
+	struct net_device *dev;
 	struct dn_ifaddr *ifa;
 
 	rcu_read_lock();
-	dn_db = rcu_dereference(dev->dn_ptr);
+	dev = dn_db->dev;
 	if (dn_db->t3 <= dn_db->parms.t2) {
 		if (dn_db->parms.timer3) {
 			for (ifa = rcu_dereference(dn_db->ifa_list);
@@ -1071,8 +1071,6 @@ static void dn_dev_set_timer(struct net_device *dev)
 	if (dn_db->parms.t2 > dn_db->parms.t3)
 		dn_db->parms.t2 = dn_db->parms.t3;
 
-	dn_db->timer.data = (unsigned long)dev;
-	dn_db->timer.function = dn_dev_timer_func;
 	dn_db->timer.expires = jiffies + (dn_db->parms.t2 * HZ);
 
 	add_timer(&dn_db->timer);
@@ -1101,7 +1099,7 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err)
 
 	rcu_assign_pointer(dev->dn_ptr, dn_db);
 	dn_db->dev = dev;
-	init_timer(&dn_db->timer);
+	timer_setup(&dn_db->timer, dn_dev_timer_func, 0);
 
 	dn_db->uptime = jiffies;
 
diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
index 7ac086d5c0c0..1b2120645730 100644
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -776,12 +776,8 @@ static int dn_nsp_rx_packet(struct net *net, struct sock *sk2,
 	 * Swap src & dst and look up in the normal way.
 	 */
 	if (unlikely(cb->rt_flags & DN_RT_F_RTS)) {
-		__le16 tmp = cb->dst_port;
-		cb->dst_port = cb->src_port;
-		cb->src_port = tmp;
-		tmp = cb->dst;
-		cb->dst = cb->src;
-		cb->src = tmp;
+		swap(cb->dst_port, cb->src_port);
+		swap(cb->dst, cb->src);
 	}
 
 	/*
diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c
index 66f035e476ea..56a52a004c56 100644
--- a/net/decnet/dn_nsp_out.c
+++ b/net/decnet/dn_nsp_out.c
@@ -313,11 +313,8 @@ static __le16 *dn_mk_ack_header(struct sock *sk, struct sk_buff *skb, unsigned c
 	ackcrs |= 0x8000;
 
 	/* If this is an "other data/ack" message, swap acknum and ackcrs */
-	if (other) {
-		unsigned short tmp = acknum;
-		acknum = ackcrs;
-		ackcrs = tmp;
-	}
+	if (other)
+		swap(acknum, ackcrs);
 
 	/* Set "cross subchannel" bit in ackcrs */
 	ackcrs |= 0x2000;
@@ -491,17 +488,6 @@ void dn_send_conn_ack (struct sock *sk)
 	dn_nsp_send(skb);
 }
 
-void dn_nsp_delayed_ack(struct sock *sk)
-{
-	struct dn_scp *scp = DN_SK(sk);
-
-	if (scp->ackxmt_oth != scp->numoth_rcv)
-		dn_nsp_send_oth_ack(sk);
-
-	if (scp->ackxmt_dat != scp->numdat_rcv)
-		dn_nsp_send_data_ack(sk);
-}
-
 static int dn_nsp_retrans_conn_conf(struct sock *sk)
 {
 	struct dn_scp *scp = DN_SK(sk);
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 0bd3afd01dd2..bff5ab88cdbb 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -338,7 +338,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou
 					   dn_rt_hash_table[hash].chain);
 			rcu_assign_pointer(dn_rt_hash_table[hash].chain, rth);
 
-			dst_use(&rth->dst, now);
+			dst_hold_and_use(&rth->dst, now);
 			spin_unlock_bh(&dn_rt_hash_table[hash].lock);
 
 			dst_release_immediate(&rt->dst);
@@ -351,7 +351,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou
 	rcu_assign_pointer(rt->dst.dn_next, dn_rt_hash_table[hash].chain);
 	rcu_assign_pointer(dn_rt_hash_table[hash].chain, rt);
 
-	dst_use(&rt->dst, now);
+	dst_hold_and_use(&rt->dst, now);
 	spin_unlock_bh(&dn_rt_hash_table[hash].lock);
 	*rp = rt;
 	return 0;
@@ -1258,7 +1258,7 @@ static int __dn_route_output_key(struct dst_entry **pprt, const struct flowidn *
 			    (flp->flowidn_mark == rt->fld.flowidn_mark) &&
 			    dn_is_output_route(rt) &&
 			    (rt->fld.flowidn_oif == flp->flowidn_oif)) {
-				dst_use(&rt->dst, jiffies);
+				dst_hold_and_use(&rt->dst, jiffies);
 				rcu_read_unlock_bh();
 				*pprt = &rt->dst;
 				return 0;
@@ -1535,7 +1535,7 @@ static int dn_route_input(struct sk_buff *skb)
 		    (rt->fld.flowidn_oif == 0) &&
 		    (rt->fld.flowidn_mark == skb->mark) &&
 		    (rt->fld.flowidn_iif == cb->iif)) {
-			dst_use(&rt->dst, jiffies);
+			dst_hold_and_use(&rt->dst, jiffies);
 			rcu_read_unlock();
 			skb_dst_set(skb, (struct dst_entry *)rt);
 			return 0;
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 3d3c74193d06..e9a4a0f33e86 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # the core
 obj-$(CONFIG_NET_DSA) += dsa_core.o
-dsa_core-y += dsa.o dsa2.o legacy.o port.o slave.o switch.o
+dsa_core-y += dsa.o dsa2.o legacy.o master.o port.o slave.o switch.o
 
 # tagging formats
 dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 03c58b0eb082..b8f2d9f7c3ed 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -14,6 +14,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/notifier.h>
 #include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_platform.h>
@@ -67,37 +68,6 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = {
 	[DSA_TAG_PROTO_NONE] = &none_ops,
 };
 
-int dsa_cpu_dsa_setup(struct dsa_port *port)
-{
-	struct device_node *port_dn = port->dn;
-	struct dsa_switch *ds = port->ds;
-	struct phy_device *phydev;
-	int ret, mode;
-
-	if (of_phy_is_fixed_link(port_dn)) {
-		ret = of_phy_register_fixed_link(port_dn);
-		if (ret) {
-			dev_err(ds->dev, "failed to register fixed PHY\n");
-			return ret;
-		}
-		phydev = of_phy_find_device(port_dn);
-
-		mode = of_get_phy_mode(port_dn);
-		if (mode < 0)
-			mode = PHY_INTERFACE_MODE_NA;
-		phydev->interface = mode;
-
-		genphy_config_init(phydev);
-		genphy_read_status(phydev);
-		if (ds->ops->adjust_link)
-			ds->ops->adjust_link(ds, port->index, phydev);
-
-		put_device(&phydev->mdio.dev);
-	}
-
-	return 0;
-}
-
 const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol)
 {
 	const struct dsa_device_ops *ops;
@@ -112,42 +82,6 @@ const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol)
 	return ops;
 }
 
-int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp)
-{
-	struct dsa_switch *ds = cpu_dp->ds;
-	struct net_device *master;
-	struct ethtool_ops *cpu_ops;
-
-	master = cpu_dp->netdev;
-
-	cpu_ops = devm_kzalloc(ds->dev, sizeof(*cpu_ops), GFP_KERNEL);
-	if (!cpu_ops)
-		return -ENOMEM;
-
-	memcpy(&cpu_dp->ethtool_ops, master->ethtool_ops,
-	       sizeof(struct ethtool_ops));
-	cpu_dp->orig_ethtool_ops = master->ethtool_ops;
-	memcpy(cpu_ops, &cpu_dp->ethtool_ops,
-	       sizeof(struct ethtool_ops));
-	dsa_cpu_port_ethtool_init(cpu_ops);
-	master->ethtool_ops = cpu_ops;
-
-	return 0;
-}
-
-void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp)
-{
-	cpu_dp->netdev->ethtool_ops = cpu_dp->orig_ethtool_ops;
-}
-
-void dsa_cpu_dsa_destroy(struct dsa_port *port)
-{
-	struct device_node *port_dn = port->dn;
-
-	if (of_phy_is_fixed_link(port_dn))
-		of_phy_deregister_fixed_link(port_dn);
-}
-
 static int dev_is_class(struct device *dev, void *class)
 {
 	if (dev->class != NULL && !strcmp(dev->class->name, class))
@@ -188,12 +122,12 @@ EXPORT_SYMBOL_GPL(dsa_dev_to_net_device);
 static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 			  struct packet_type *pt, struct net_device *unused)
 {
-	struct dsa_switch_tree *dst = dev->dsa_ptr;
+	struct dsa_port *cpu_dp = dev->dsa_ptr;
 	struct sk_buff *nskb = NULL;
 	struct pcpu_sw_netstats *s;
 	struct dsa_slave_priv *p;
 
-	if (unlikely(dst == NULL)) {
+	if (unlikely(!cpu_dp)) {
 		kfree_skb(skb);
 		return 0;
 	}
@@ -202,7 +136,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb)
 		return 0;
 
-	nskb = dst->rcv(skb, dev, pt);
+	nskb = cpu_dp->rcv(skb, dev, pt);
 	if (!nskb) {
 		kfree_skb(skb);
 		return 0;
@@ -228,7 +162,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 #ifdef CONFIG_PM_SLEEP
 static bool dsa_is_port_initialized(struct dsa_switch *ds, int p)
 {
-	return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev;
+	return dsa_is_user_port(ds, p) && ds->ports[p].slave;
 }
 
 int dsa_switch_suspend(struct dsa_switch *ds)
@@ -240,7 +174,7 @@ int dsa_switch_suspend(struct dsa_switch *ds)
 		if (!dsa_is_port_initialized(ds, i))
 			continue;
 
-		ret = dsa_slave_suspend(ds->ports[i].netdev);
+		ret = dsa_slave_suspend(ds->ports[i].slave);
 		if (ret)
 			return ret;
 	}
@@ -267,7 +201,7 @@ int dsa_switch_resume(struct dsa_switch *ds)
 		if (!dsa_is_port_initialized(ds, i))
 			continue;
 
-		ret = dsa_slave_resume(ds->ports[i].netdev);
+		ret = dsa_slave_resume(ds->ports[i].slave);
 		if (ret)
 			return ret;
 	}
@@ -289,6 +223,28 @@ bool dsa_schedule_work(struct work_struct *work)
 	return queue_work(dsa_owq, work);
 }
 
+static ATOMIC_NOTIFIER_HEAD(dsa_notif_chain);
+
+int register_dsa_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_register(&dsa_notif_chain, nb);
+}
+EXPORT_SYMBOL_GPL(register_dsa_notifier);
+
+int unregister_dsa_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&dsa_notif_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_dsa_notifier);
+
+int call_dsa_notifiers(unsigned long val, struct net_device *dev,
+		       struct dsa_notifier_info *info)
+{
+	info->dev = dev;
+	return atomic_notifier_call_chain(&dsa_notif_chain, val, info);
+}
+EXPORT_SYMBOL_GPL(call_dsa_notifiers);
+
 static int __init dsa_init_module(void)
 {
 	int rc;
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 045d8a176279..797d1156b4e6 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -87,23 +87,17 @@ static void dsa_dst_del_ds(struct dsa_switch_tree *dst,
  */
 static bool dsa_port_is_valid(struct dsa_port *port)
 {
-	return !!(port->dn || port->name);
+	return port->type != DSA_PORT_TYPE_UNUSED;
 }
 
 static bool dsa_port_is_dsa(struct dsa_port *port)
 {
-	if (port->name && !strcmp(port->name, "dsa"))
-		return true;
-	else
-		return !!of_parse_phandle(port->dn, "link", 0);
+	return port->type == DSA_PORT_TYPE_DSA;
 }
 
 static bool dsa_port_is_cpu(struct dsa_port *port)
 {
-	if (port->name && !strcmp(port->name, "cpu"))
-		return true;
-	else
-		return !!of_parse_phandle(port->dn, "ethernet", 0);
+	return port->type == DSA_PORT_TYPE_CPU;
 }
 
 static bool dsa_ds_find_port_dn(struct dsa_switch *ds,
@@ -183,8 +177,6 @@ static int dsa_ds_complete(struct dsa_switch_tree *dst, struct dsa_switch *ds)
 		err = dsa_port_complete(dst, ds, port, index);
 		if (err != 0)
 			return err;
-
-		ds->dsa_port_mask |= BIT(index);
 	}
 
 	return 0;
@@ -219,7 +211,7 @@ static int dsa_dsa_port_apply(struct dsa_port *port)
 	struct dsa_switch *ds = port->ds;
 	int err;
 
-	err = dsa_cpu_dsa_setup(port);
+	err = dsa_port_fixed_link_register_of(port);
 	if (err) {
 		dev_warn(ds->dev, "Failed to setup dsa port %d: %d\n",
 			 port->index, err);
@@ -235,7 +227,7 @@ static int dsa_dsa_port_apply(struct dsa_port *port)
 static void dsa_dsa_port_unapply(struct dsa_port *port)
 {
 	devlink_port_unregister(&port->devlink_port);
-	dsa_cpu_dsa_destroy(port);
+	dsa_port_fixed_link_unregister_of(port);
 }
 
 static int dsa_cpu_port_apply(struct dsa_port *port)
@@ -243,7 +235,7 @@ static int dsa_cpu_port_apply(struct dsa_port *port)
 	struct dsa_switch *ds = port->ds;
 	int err;
 
-	err = dsa_cpu_dsa_setup(port);
+	err = dsa_port_fixed_link_register_of(port);
 	if (err) {
 		dev_warn(ds->dev, "Failed to setup cpu port %d: %d\n",
 			 port->index, err);
@@ -259,27 +251,19 @@ static int dsa_cpu_port_apply(struct dsa_port *port)
 static void dsa_cpu_port_unapply(struct dsa_port *port)
 {
 	devlink_port_unregister(&port->devlink_port);
-	dsa_cpu_dsa_destroy(port);
-	port->ds->cpu_port_mask &= ~BIT(port->index);
-
+	dsa_port_fixed_link_unregister_of(port);
 }
 
 static int dsa_user_port_apply(struct dsa_port *port)
 {
 	struct dsa_switch *ds = port->ds;
-	const char *name = port->name;
 	int err;
 
-	if (port->dn)
-		name = of_get_property(port->dn, "label", NULL);
-	if (!name)
-		name = "eth%d";
-
-	err = dsa_slave_create(port, name);
+	err = dsa_slave_create(port);
 	if (err) {
 		dev_warn(ds->dev, "Failed to create slave %d: %d\n",
 			 port->index, err);
-		port->netdev = NULL;
+		port->slave = NULL;
 		return err;
 	}
 
@@ -289,7 +273,7 @@ static int dsa_user_port_apply(struct dsa_port *port)
 	if (err)
 		return err;
 
-	devlink_port_type_eth_set(&port->devlink_port, port->netdev);
+	devlink_port_type_eth_set(&port->devlink_port, port->slave);
 
 	return 0;
 }
@@ -297,10 +281,9 @@ static int dsa_user_port_apply(struct dsa_port *port)
 static void dsa_user_port_unapply(struct dsa_port *port)
 {
 	devlink_port_unregister(&port->devlink_port);
-	if (port->netdev) {
-		dsa_slave_destroy(port->netdev);
-		port->netdev = NULL;
-		port->ds->enabled_port_mask &= ~(1 << port->index);
+	if (port->slave) {
+		dsa_slave_destroy(port->slave);
+		port->slave = NULL;
 	}
 }
 
@@ -315,7 +298,7 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
 	 * the slave MDIO bus driver rely on these values for probing PHY
 	 * devices or not
 	 */
-	ds->phys_mii_mask = ds->enabled_port_mask;
+	ds->phys_mii_mask |= dsa_user_ports(ds);
 
 	/* Add the switch to devlink before calling setup, so that setup can
 	 * add dpipe tables
@@ -336,12 +319,6 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
 	if (err)
 		return err;
 
-	if (ds->ops->set_addr) {
-		err = ds->ops->set_addr(ds, dst->cpu_dp->netdev->dev_addr);
-		if (err < 0)
-			return err;
-	}
-
 	if (!ds->slave_mii_bus && ds->ops->phy_read) {
 		ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
 		if (!ds->slave_mii_bus)
@@ -433,18 +410,17 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst)
 			return err;
 	}
 
-	if (dst->cpu_dp) {
-		err = dsa_cpu_port_ethtool_setup(dst->cpu_dp);
-		if (err)
-			return err;
-	}
-
 	/* If we use a tagging format that doesn't have an ethertype
 	 * field, make sure that all packets from this point on get
 	 * sent to the tag format's receive function.
 	 */
 	wmb();
-	dst->cpu_dp->netdev->dsa_ptr = dst;
+	dst->cpu_dp->master->dsa_ptr = dst->cpu_dp;
+
+	err = dsa_master_ethtool_setup(dst->cpu_dp->master);
+	if (err)
+		return err;
+
 	dst->applied = true;
 
 	return 0;
@@ -458,7 +434,9 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst)
 	if (!dst->applied)
 		return;
 
-	dst->cpu_dp->netdev->dsa_ptr = NULL;
+	dsa_master_ethtool_restore(dst->cpu_dp->master);
+
+	dst->cpu_dp->master->dsa_ptr = NULL;
 
 	/* If we used a tagging format that doesn't have an ethertype
 	 * field, make sure that all packets from this point get sent
@@ -474,10 +452,7 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst)
 		dsa_ds_unapply(dst, ds);
 	}
 
-	if (dst->cpu_dp) {
-		dsa_cpu_port_ethtool_restore(dst->cpu_dp);
-		dst->cpu_dp = NULL;
-	}
+	dst->cpu_dp = NULL;
 
 	pr_info("DSA: tree %d unapplied\n", dst->tree);
 	dst->applied = false;
@@ -487,44 +462,24 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index,
 			 struct dsa_switch_tree *dst,
 			 struct dsa_switch *ds)
 {
+	const struct dsa_device_ops *tag_ops;
 	enum dsa_tag_protocol tag_protocol;
-	struct net_device *ethernet_dev;
-	struct device_node *ethernet;
 
-	if (port->dn) {
-		ethernet = of_parse_phandle(port->dn, "ethernet", 0);
-		if (!ethernet)
-			return -EINVAL;
-		ethernet_dev = of_find_net_device_by_node(ethernet);
-		if (!ethernet_dev)
-			return -EPROBE_DEFER;
-	} else {
-		ethernet_dev = dsa_dev_to_net_device(ds->cd->netdev[index]);
-		if (!ethernet_dev)
-			return -EPROBE_DEFER;
-		dev_put(ethernet_dev);
-	}
-
-	if (!dst->cpu_dp) {
+	if (!dst->cpu_dp)
 		dst->cpu_dp = port;
-		dst->cpu_dp->netdev = ethernet_dev;
-	}
-
-	/* Initialize cpu_port_mask now for drv->setup()
-	 * to have access to a correct value, just like what
-	 * net/dsa/dsa.c::dsa_switch_setup_one does.
-	 */
-	ds->cpu_port_mask |= BIT(index);
 
 	tag_protocol = ds->ops->get_tag_protocol(ds);
-	dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol);
-	if (IS_ERR(dst->tag_ops)) {
+	tag_ops = dsa_resolve_tag_protocol(tag_protocol);
+	if (IS_ERR(tag_ops)) {
 		dev_warn(ds->dev, "No tagger for this switch\n");
-		ds->cpu_port_mask &= ~BIT(index);
-		return PTR_ERR(dst->tag_ops);
+		return PTR_ERR(tag_ops);
 	}
 
-	dst->rcv = dst->tag_ops->rcv;
+	dst->cpu_dp->tag_ops = tag_ops;
+
+	/* Make a few copies for faster access in master receive hot path */
+	dst->cpu_dp->rcv = dst->cpu_dp->tag_ops->rcv;
+	dst->cpu_dp->dst = dst;
 
 	return 0;
 }
@@ -545,12 +500,6 @@ static int dsa_ds_parse(struct dsa_switch_tree *dst, struct dsa_switch *ds)
 			err = dsa_cpu_parse(port, index, dst, ds);
 			if (err)
 				return err;
-		} else {
-			/* Initialize enabled_port_mask now for drv->setup()
-			 * to have access to a correct value, just like what
-			 * net/dsa/dsa.c::dsa_switch_setup_one does.
-			 */
-			ds->enabled_port_mask |= BIT(index);
 		}
 
 	}
@@ -605,11 +554,48 @@ static int dsa_dst_parse(struct dsa_switch_tree *dst)
 	return 0;
 }
 
-static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds)
+static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn)
 {
-	struct device_node *port;
-	int err;
+	struct device_node *ethernet = of_parse_phandle(dn, "ethernet", 0);
+	struct device_node *link = of_parse_phandle(dn, "link", 0);
+	const char *name = of_get_property(dn, "label", NULL);
+
+	if (ethernet) {
+		struct net_device *master;
+
+		master = of_find_net_device_by_node(ethernet);
+		if (!master)
+			return -EPROBE_DEFER;
+
+		dp->type = DSA_PORT_TYPE_CPU;
+		dp->master = master;
+	} else if (link) {
+		dp->type = DSA_PORT_TYPE_DSA;
+	} else {
+		if (!name)
+			name = "eth%d";
+
+		dp->type = DSA_PORT_TYPE_USER;
+		dp->name = name;
+	}
+
+	dp->dn = dn;
+
+	return 0;
+}
+
+static int dsa_parse_ports_of(struct device_node *dn, struct dsa_switch *ds)
+{
+	struct device_node *ports, *port;
+	struct dsa_port *dp;
 	u32 reg;
+	int err;
+
+	ports = of_get_child_by_name(dn, "ports");
+	if (!ports) {
+		dev_err(ds->dev, "no ports child node found\n");
+		return -EINVAL;
+	}
 
 	for_each_available_child_of_node(ports, port) {
 		err = of_property_read_u32(port, "reg", &reg);
@@ -619,22 +605,62 @@ static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds)
 		if (reg >= ds->num_ports)
 			return -EINVAL;
 
-		ds->ports[reg].dn = port;
+		dp = &ds->ports[reg];
+
+		err = dsa_port_parse_of(dp, port);
+		if (err)
+			return err;
 	}
 
 	return 0;
 }
 
+static int dsa_port_parse(struct dsa_port *dp, const char *name,
+			  struct device *dev)
+{
+	if (!strcmp(name, "cpu")) {
+		struct net_device *master;
+
+		master = dsa_dev_to_net_device(dev);
+		if (!master)
+			return -EPROBE_DEFER;
+
+		dev_put(master);
+
+		dp->type = DSA_PORT_TYPE_CPU;
+		dp->master = master;
+	} else if (!strcmp(name, "dsa")) {
+		dp->type = DSA_PORT_TYPE_DSA;
+	} else {
+		dp->type = DSA_PORT_TYPE_USER;
+	}
+
+	dp->name = name;
+
+	return 0;
+}
+
 static int dsa_parse_ports(struct dsa_chip_data *cd, struct dsa_switch *ds)
 {
 	bool valid_name_found = false;
+	struct dsa_port *dp;
+	struct device *dev;
+	const char *name;
 	unsigned int i;
+	int err;
 
 	for (i = 0; i < DSA_MAX_PORTS; i++) {
-		if (!cd->port_names[i])
+		name = cd->port_names[i];
+		dev = cd->netdev[i];
+		dp = &ds->ports[i];
+
+		if (!name)
 			continue;
 
-		ds->ports[i].name = cd->port_names[i];
+		err = dsa_port_parse(dp, name, dev);
+		if (err)
+			return err;
+
 		valid_name_found = true;
 	}
 
@@ -680,26 +706,11 @@ static int dsa_parse_member(struct dsa_chip_data *pd, u32 *tree, u32 *index)
 	return 0;
 }
 
-static struct device_node *dsa_get_ports(struct dsa_switch *ds,
-					 struct device_node *np)
-{
-	struct device_node *ports;
-
-	ports = of_get_child_by_name(np, "ports");
-	if (!ports) {
-		dev_err(ds->dev, "no ports child node found\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	return ports;
-}
-
 static int _dsa_register_switch(struct dsa_switch *ds)
 {
 	struct dsa_chip_data *pdata = ds->dev->platform_data;
 	struct device_node *np = ds->dev->of_node;
 	struct dsa_switch_tree *dst;
-	struct device_node *ports;
 	u32 tree, index;
 	int i, err;
 
@@ -708,11 +719,7 @@ static int _dsa_register_switch(struct dsa_switch *ds)
 		if (err)
 			return err;
 
-		ports = dsa_get_ports(ds, np);
-		if (IS_ERR(ports))
-			return PTR_ERR(ports);
-
-		err = dsa_parse_ports_dn(ports, ds);
+		err = dsa_parse_ports_of(np, ds);
 		if (err)
 			return err;
 	} else {
@@ -763,14 +770,8 @@ static int _dsa_register_switch(struct dsa_switch *ds)
 	}
 
 	err = dsa_dst_parse(dst);
-	if (err) {
-		if (err == -EPROBE_DEFER) {
-			dsa_dst_del_ds(dst, ds, ds->index);
-			return err;
-		}
-
+	if (err)
 		goto out_del_dst;
-	}
 
 	err = dsa_dst_apply(dst);
 	if (err) {
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 9c3eeb72462d..253a613c40cd 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -66,7 +66,7 @@ struct dsa_notifier_vlan_info {
 };
 
 struct dsa_slave_priv {
-	/* Copy of dp->ds->dst->tag_ops->xmit for faster access in hot path */
+	/* Copy of CPU port xmit for faster access in slave transmit hot path */
 	struct sk_buff *	(*xmit)(struct sk_buff *skb,
 					struct net_device *dev);
 
@@ -79,7 +79,6 @@ struct dsa_slave_priv {
 	 * The phylib phy_device pointer for the PHY connected
 	 * to this port.
 	 */
-	struct phy_device	*phy;
 	phy_interface_t		phy_interface;
 	int			old_link;
 	int			old_pause;
@@ -94,11 +93,7 @@ struct dsa_slave_priv {
 };
 
 /* dsa.c */
-int dsa_cpu_dsa_setup(struct dsa_port *port);
-void dsa_cpu_dsa_destroy(struct dsa_port *dport);
 const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol);
-int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp);
-void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp);
 bool dsa_schedule_work(struct work_struct *work);
 
 /* legacy.c */
@@ -112,10 +107,35 @@ int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
 		       struct net_device *dev,
 		       const unsigned char *addr, u16 vid);
 
+/* master.c */
+int dsa_master_ethtool_setup(struct net_device *dev);
+void dsa_master_ethtool_restore(struct net_device *dev);
+
+static inline struct net_device *dsa_master_find_slave(struct net_device *dev,
+						       int device, int port)
+{
+	struct dsa_port *cpu_dp = dev->dsa_ptr;
+	struct dsa_switch_tree *dst = cpu_dp->dst;
+	struct dsa_switch *ds;
+
+	if (device < 0 || device >= DSA_MAX_SWITCHES)
+		return NULL;
+
+	ds = dst->ds[device];
+	if (!ds)
+		return NULL;
+
+	if (port < 0 || port >= ds->num_ports)
+		return NULL;
+
+	return ds->ports[port].slave;
+}
+
 /* port.c */
 int dsa_port_set_state(struct dsa_port *dp, u8 state,
 		       struct switchdev_trans *trans);
-void dsa_port_set_state_now(struct dsa_port *dp, u8 state);
+int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy);
+void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy);
 int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br);
 void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br);
 int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering,
@@ -126,6 +146,7 @@ int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr,
 		     u16 vid);
 int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr,
 		     u16 vid);
+int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data);
 int dsa_port_mdb_add(struct dsa_port *dp,
 		     const struct switchdev_obj_port_mdb *mdb,
 		     struct switchdev_trans *trans);
@@ -136,17 +157,34 @@ int dsa_port_vlan_add(struct dsa_port *dp,
 		      struct switchdev_trans *trans);
 int dsa_port_vlan_del(struct dsa_port *dp,
 		      const struct switchdev_obj_port_vlan *vlan);
+int dsa_port_fixed_link_register_of(struct dsa_port *dp);
+void dsa_port_fixed_link_unregister_of(struct dsa_port *dp);
+
 /* slave.c */
 extern const struct dsa_device_ops notag_netdev_ops;
 void dsa_slave_mii_bus_init(struct dsa_switch *ds);
-void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops);
-int dsa_slave_create(struct dsa_port *port, const char *name);
+int dsa_slave_create(struct dsa_port *dp);
 void dsa_slave_destroy(struct net_device *slave_dev);
 int dsa_slave_suspend(struct net_device *slave_dev);
 int dsa_slave_resume(struct net_device *slave_dev);
 int dsa_slave_register_notifier(void);
 void dsa_slave_unregister_notifier(void);
 
+static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+
+	return p->dp;
+}
+
+static inline struct net_device *
+dsa_slave_to_master(const struct net_device *dev)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+
+	return dp->cpu_dp->master;
+}
+
 /* switch.c */
 int dsa_switch_register_notifier(struct dsa_switch *ds);
 void dsa_switch_unregister_notifier(struct dsa_switch *ds);
@@ -175,14 +213,4 @@ extern const struct dsa_device_ops qca_netdev_ops;
 /* tag_trailer.c */
 extern const struct dsa_device_ops trailer_netdev_ops;
 
-static inline struct net_device *dsa_master_netdev(struct dsa_slave_priv *p)
-{
-	return p->dp->cpu_dp->netdev;
-}
-
-static inline struct dsa_port *dsa_get_cpu_port(struct dsa_switch_tree *dst)
-{
-	return dst->cpu_dp;
-}
-
 #endif
diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c
index 91e6f7981d39..0511fe2feff7 100644
--- a/net/dsa/legacy.c
+++ b/net/dsa/legacy.c
@@ -86,7 +86,7 @@ static int dsa_cpu_dsa_setups(struct dsa_switch *ds)
 		if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
 			continue;
 
-		ret = dsa_cpu_dsa_setup(&ds->ports[port]);
+		ret = dsa_port_fixed_link_register_of(&ds->ports[port]);
 		if (ret)
 			return ret;
 	}
@@ -101,6 +101,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
 	struct dsa_chip_data *cd = ds->cd;
 	bool valid_name_found = false;
 	int index = ds->index;
+	struct dsa_port *dp;
 	int i, ret;
 
 	/*
@@ -109,9 +110,12 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
 	for (i = 0; i < ds->num_ports; i++) {
 		char *name;
 
+		dp = &ds->ports[i];
+
 		name = cd->port_names[i];
 		if (name == NULL)
 			continue;
+		dp->name = name;
 
 		if (!strcmp(name, "cpu")) {
 			if (dst->cpu_dp) {
@@ -120,12 +124,12 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
 				return -EINVAL;
 			}
 			dst->cpu_dp = &ds->ports[i];
-			dst->cpu_dp->netdev = master;
-			ds->cpu_port_mask |= 1 << i;
+			dst->cpu_dp->master = master;
+			dp->type = DSA_PORT_TYPE_CPU;
 		} else if (!strcmp(name, "dsa")) {
-			ds->dsa_port_mask |= 1 << i;
+			dp->type = DSA_PORT_TYPE_DSA;
 		} else {
-			ds->enabled_port_mask |= 1 << i;
+			dp->type = DSA_PORT_TYPE_USER;
 		}
 		valid_name_found = true;
 	}
@@ -136,7 +140,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
 	/* Make the built-in MII bus mask match the number of ports,
 	 * switch drivers can override this later
 	 */
-	ds->phys_mii_mask = ds->enabled_port_mask;
+	ds->phys_mii_mask |= dsa_user_ports(ds);
 
 	/*
 	 * If the CPU connects to this switch, set the switch tree
@@ -144,14 +148,19 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
 	 * switch.
 	 */
 	if (dst->cpu_dp->ds == ds) {
+		const struct dsa_device_ops *tag_ops;
 		enum dsa_tag_protocol tag_protocol;
 
 		tag_protocol = ops->get_tag_protocol(ds);
-		dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol);
-		if (IS_ERR(dst->tag_ops))
-			return PTR_ERR(dst->tag_ops);
+		tag_ops = dsa_resolve_tag_protocol(tag_protocol);
+		if (IS_ERR(tag_ops))
+			return PTR_ERR(tag_ops);
+
+		dst->cpu_dp->tag_ops = tag_ops;
 
-		dst->rcv = dst->tag_ops->rcv;
+		/* Few copies for faster access in master receive hot path */
+		dst->cpu_dp->rcv = dst->cpu_dp->tag_ops->rcv;
+		dst->cpu_dp->dst = dst;
 	}
 
 	memcpy(ds->rtable, cd->rtable, sizeof(ds->rtable));
@@ -167,12 +176,6 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
 	if (ret)
 		return ret;
 
-	if (ops->set_addr) {
-		ret = ops->set_addr(ds, master->dev_addr);
-		if (ret < 0)
-			return ret;
-	}
-
 	if (!ds->slave_mii_bus && ops->phy_read) {
 		ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
 		if (!ds->slave_mii_bus)
@@ -191,10 +194,10 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
 		ds->ports[i].dn = cd->port_dn[i];
 		ds->ports[i].cpu_dp = dst->cpu_dp;
 
-		if (!(ds->enabled_port_mask & (1 << i)))
+		if (dsa_is_user_port(ds, i))
 			continue;
 
-		ret = dsa_slave_create(&ds->ports[i], cd->port_names[i]);
+		ret = dsa_slave_create(&ds->ports[i]);
 		if (ret < 0)
 			netdev_err(master, "[%d]: can't create dsa slave device for port %d(%s): %d\n",
 				   index, i, cd->port_names[i], ret);
@@ -206,10 +209,6 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
 		netdev_err(master, "[%d] : can't configure CPU and DSA ports\n",
 			   index);
 
-	ret = dsa_cpu_port_ethtool_setup(ds->dst->cpu_dp);
-	if (ret)
-		return ret;
-
 	return 0;
 }
 
@@ -263,24 +262,20 @@ static void dsa_switch_destroy(struct dsa_switch *ds)
 
 	/* Destroy network devices for physical switch ports. */
 	for (port = 0; port < ds->num_ports; port++) {
-		if (!(ds->enabled_port_mask & (1 << port)))
+		if (!dsa_is_user_port(ds, port))
 			continue;
 
-		if (!ds->ports[port].netdev)
+		if (!ds->ports[port].slave)
 			continue;
 
-		dsa_slave_destroy(ds->ports[port].netdev);
+		dsa_slave_destroy(ds->ports[port].slave);
 	}
 
 	/* Disable configuration of the CPU and DSA ports */
 	for (port = 0; port < ds->num_ports; port++) {
 		if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
 			continue;
-		dsa_cpu_dsa_destroy(&ds->ports[port]);
-
-		/* Clearing a bit which is not set does no harm */
-		ds->cpu_port_mask |= ~(1 << port);
-		ds->dsa_port_mask |= ~(1 << port);
+		dsa_port_fixed_link_unregister_of(&ds->ports[port]);
 	}
 
 	if (ds->slave_mii_bus && ds->ops->phy_read)
@@ -604,9 +599,9 @@ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev,
 	 * sent to the tag format's receive function.
 	 */
 	wmb();
-	dev->dsa_ptr = dst;
+	dev->dsa_ptr = dst->cpu_dp;
 
-	return 0;
+	return dsa_master_ethtool_setup(dst->cpu_dp->master);
 }
 
 static int dsa_probe(struct platform_device *pdev)
@@ -671,7 +666,9 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst)
 {
 	int i;
 
-	dst->cpu_dp->netdev->dsa_ptr = NULL;
+	dsa_master_ethtool_restore(dst->cpu_dp->master);
+
+	dst->cpu_dp->master->dsa_ptr = NULL;
 
 	/* If we used a tagging format that doesn't have an ethertype
 	 * field, make sure that all packets from this point get sent
@@ -686,9 +683,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst)
 			dsa_switch_destroy(ds);
 	}
 
-	dsa_cpu_port_ethtool_restore(dst->cpu_dp);
-
-	dev_put(dst->cpu_dp->netdev);
+	dev_put(dst->cpu_dp->master);
 }
 
 static int dsa_remove(struct platform_device *pdev)
@@ -745,8 +740,7 @@ int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		       const unsigned char *addr, u16 vid,
 		       u16 flags)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_port *dp = p->dp;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 
 	return dsa_port_fdb_add(dp, addr, vid);
 }
@@ -755,8 +749,7 @@ int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
 		       struct net_device *dev,
 		       const unsigned char *addr, u16 vid)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_port *dp = p->dp;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 
 	return dsa_port_fdb_del(dp, addr, vid);
 }
diff --git a/net/dsa/master.c b/net/dsa/master.c
new file mode 100644
index 000000000000..5f3f57e372e0
--- /dev/null
+++ b/net/dsa/master.c
@@ -0,0 +1,117 @@
+/*
+ * Handling of a master device, switching frames via its switch fabric CPU port
+ *
+ * Copyright (c) 2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "dsa_priv.h"
+
+static void dsa_master_get_ethtool_stats(struct net_device *dev,
+					 struct ethtool_stats *stats,
+					 uint64_t *data)
+{
+	struct dsa_port *cpu_dp = dev->dsa_ptr;
+	const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
+	struct dsa_switch *ds = cpu_dp->ds;
+	int port = cpu_dp->index;
+	int count = 0;
+
+	if (ops && ops->get_sset_count && ops->get_ethtool_stats) {
+		count = ops->get_sset_count(dev, ETH_SS_STATS);
+		ops->get_ethtool_stats(dev, stats, data);
+	}
+
+	if (ds->ops->get_ethtool_stats)
+		ds->ops->get_ethtool_stats(ds, port, data + count);
+}
+
+static int dsa_master_get_sset_count(struct net_device *dev, int sset)
+{
+	struct dsa_port *cpu_dp = dev->dsa_ptr;
+	const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
+	struct dsa_switch *ds = cpu_dp->ds;
+	int count = 0;
+
+	if (ops && ops->get_sset_count)
+		count += ops->get_sset_count(dev, sset);
+
+	if (sset == ETH_SS_STATS && ds->ops->get_sset_count)
+		count += ds->ops->get_sset_count(ds);
+
+	return count;
+}
+
+static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset,
+				   uint8_t *data)
+{
+	struct dsa_port *cpu_dp = dev->dsa_ptr;
+	const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
+	struct dsa_switch *ds = cpu_dp->ds;
+	int port = cpu_dp->index;
+	int len = ETH_GSTRING_LEN;
+	int mcount = 0, count;
+	unsigned int i;
+	uint8_t pfx[4];
+	uint8_t *ndata;
+
+	snprintf(pfx, sizeof(pfx), "p%.2d", port);
+	/* We do not want to be NULL-terminated, since this is a prefix */
+	pfx[sizeof(pfx) - 1] = '_';
+
+	if (ops && ops->get_sset_count && ops->get_strings) {
+		mcount = ops->get_sset_count(dev, ETH_SS_STATS);
+		ops->get_strings(dev, stringset, data);
+	}
+
+	if (stringset == ETH_SS_STATS && ds->ops->get_strings) {
+		ndata = data + mcount * len;
+		/* This function copies ETH_GSTRINGS_LEN bytes, we will mangle
+		 * the output after to prepend our CPU port prefix we
+		 * constructed earlier
+		 */
+		ds->ops->get_strings(ds, port, ndata);
+		count = ds->ops->get_sset_count(ds);
+		for (i = 0; i < count; i++) {
+			memmove(ndata + (i * len + sizeof(pfx)),
+				ndata + i * len, len - sizeof(pfx));
+			memcpy(ndata + i * len, pfx, sizeof(pfx));
+		}
+	}
+}
+
+int dsa_master_ethtool_setup(struct net_device *dev)
+{
+	struct dsa_port *cpu_dp = dev->dsa_ptr;
+	struct dsa_switch *ds = cpu_dp->ds;
+	struct ethtool_ops *ops;
+
+	ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL);
+	if (!ops)
+		return -ENOMEM;
+
+	cpu_dp->orig_ethtool_ops = dev->ethtool_ops;
+	if (cpu_dp->orig_ethtool_ops)
+		memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops));
+
+	ops->get_sset_count = dsa_master_get_sset_count;
+	ops->get_ethtool_stats = dsa_master_get_ethtool_stats;
+	ops->get_strings = dsa_master_get_strings;
+
+	dev->ethtool_ops = ops;
+
+	return 0;
+}
+
+void dsa_master_ethtool_restore(struct net_device *dev)
+{
+	struct dsa_port *cpu_dp = dev->dsa_ptr;
+
+	dev->ethtool_ops = cpu_dp->orig_ethtool_ops;
+	cpu_dp->orig_ethtool_ops = NULL;
+}
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 659676ba3f8b..bb30b1a7de3a 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -12,6 +12,8 @@
 
 #include <linux/if_bridge.h>
 #include <linux/notifier.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
 
 #include "dsa_priv.h"
 
@@ -56,7 +58,7 @@ int dsa_port_set_state(struct dsa_port *dp, u8 state,
 	return 0;
 }
 
-void dsa_port_set_state_now(struct dsa_port *dp, u8 state)
+static void dsa_port_set_state_now(struct dsa_port *dp, u8 state)
 {
 	int err;
 
@@ -65,6 +67,35 @@ void dsa_port_set_state_now(struct dsa_port *dp, u8 state)
 		pr_err("DSA: failed to set STP state %u (%d)\n", state, err);
 }
 
+int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
+{
+	u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING;
+	struct dsa_switch *ds = dp->ds;
+	int port = dp->index;
+	int err;
+
+	if (ds->ops->port_enable) {
+		err = ds->ops->port_enable(ds, port, phy);
+		if (err)
+			return err;
+	}
+
+	dsa_port_set_state_now(dp, stp_state);
+
+	return 0;
+}
+
+void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy)
+{
+	struct dsa_switch *ds = dp->ds;
+	int port = dp->index;
+
+	dsa_port_set_state_now(dp, BR_STATE_DISABLED);
+
+	if (ds->ops->port_disable)
+		ds->ops->port_disable(ds, port, phy);
+}
+
 int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br)
 {
 	struct dsa_notifier_bridge_info info = {
@@ -173,6 +204,17 @@ int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr,
 	return dsa_port_notify(dp, DSA_NOTIFIER_FDB_DEL, &info);
 }
 
+int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data)
+{
+	struct dsa_switch *ds = dp->ds;
+	int port = dp->index;
+
+	if (!ds->ops->port_fdb_dump)
+		return -EOPNOTSUPP;
+
+	return ds->ops->port_fdb_dump(ds, port, cb, data);
+}
+
 int dsa_port_mdb_add(struct dsa_port *dp,
 		     const struct switchdev_obj_port_mdb *mdb,
 		     struct switchdev_trans *trans)
@@ -224,3 +266,48 @@ int dsa_port_vlan_del(struct dsa_port *dp,
 
 	return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info);
 }
+
+int dsa_port_fixed_link_register_of(struct dsa_port *dp)
+{
+	struct device_node *dn = dp->dn;
+	struct dsa_switch *ds = dp->ds;
+	struct phy_device *phydev;
+	int port = dp->index;
+	int mode;
+	int err;
+
+	if (of_phy_is_fixed_link(dn)) {
+		err = of_phy_register_fixed_link(dn);
+		if (err) {
+			dev_err(ds->dev,
+				"failed to register the fixed PHY of port %d\n",
+				port);
+			return err;
+		}
+
+		phydev = of_phy_find_device(dn);
+
+		mode = of_get_phy_mode(dn);
+		if (mode < 0)
+			mode = PHY_INTERFACE_MODE_NA;
+		phydev->interface = mode;
+
+		genphy_config_init(phydev);
+		genphy_read_status(phydev);
+
+		if (ds->ops->adjust_link)
+			ds->ops->adjust_link(ds, port, phydev);
+
+		put_device(&phydev->mdio.dev);
+	}
+
+	return 0;
+}
+
+void dsa_port_fixed_link_unregister_of(struct dsa_port *dp)
+{
+	struct device_node *dn = dp->dn;
+
+	if (of_phy_is_fixed_link(dn))
+		of_phy_deregister_fixed_link(dn);
+}
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 865e29e62bad..9b75d0ac4092 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -64,18 +64,13 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds)
 /* slave device handling ****************************************************/
 static int dsa_slave_get_iflink(const struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-
-	return dsa_master_netdev(p)->ifindex;
+	return dsa_slave_to_master(dev)->ifindex;
 }
 
 static int dsa_slave_open(struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_port *dp = p->dp;
-	struct dsa_switch *ds = dp->ds;
-	struct net_device *master = dsa_master_netdev(p);
-	u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING;
+	struct net_device *master = dsa_slave_to_master(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	int err;
 
 	if (!(master->flags & IFF_UP))
@@ -98,16 +93,12 @@ static int dsa_slave_open(struct net_device *dev)
 			goto clear_allmulti;
 	}
 
-	if (ds->ops->port_enable) {
-		err = ds->ops->port_enable(ds, p->dp->index, p->phy);
-		if (err)
-			goto clear_promisc;
-	}
-
-	dsa_port_set_state_now(p->dp, stp_state);
+	err = dsa_port_enable(dp, dev->phydev);
+	if (err)
+		goto clear_promisc;
 
-	if (p->phy)
-		phy_start(p->phy);
+	if (dev->phydev)
+		phy_start(dev->phydev);
 
 	return 0;
 
@@ -126,12 +117,13 @@ out:
 
 static int dsa_slave_close(struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct net_device *master = dsa_master_netdev(p);
-	struct dsa_switch *ds = p->dp->ds;
+	struct net_device *master = dsa_slave_to_master(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+
+	if (dev->phydev)
+		phy_stop(dev->phydev);
 
-	if (p->phy)
-		phy_stop(p->phy);
+	dsa_port_disable(dp, dev->phydev);
 
 	dev_mc_unsync(master, dev);
 	dev_uc_unsync(master, dev);
@@ -143,18 +135,12 @@ static int dsa_slave_close(struct net_device *dev)
 	if (!ether_addr_equal(dev->dev_addr, master->dev_addr))
 		dev_uc_del(master, dev->dev_addr);
 
-	if (ds->ops->port_disable)
-		ds->ops->port_disable(ds, p->dp->index, p->phy);
-
-	dsa_port_set_state_now(p->dp, BR_STATE_DISABLED);
-
 	return 0;
 }
 
 static void dsa_slave_change_rx_flags(struct net_device *dev, int change)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct net_device *master = dsa_master_netdev(p);
+	struct net_device *master = dsa_slave_to_master(dev);
 
 	if (change & IFF_ALLMULTI)
 		dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1);
@@ -164,8 +150,7 @@ static void dsa_slave_change_rx_flags(struct net_device *dev, int change)
 
 static void dsa_slave_set_rx_mode(struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct net_device *master = dsa_master_netdev(p);
+	struct net_device *master = dsa_slave_to_master(dev);
 
 	dev_mc_sync(master, dev);
 	dev_uc_sync(master, dev);
@@ -173,8 +158,7 @@ static void dsa_slave_set_rx_mode(struct net_device *dev)
 
 static int dsa_slave_set_mac_address(struct net_device *dev, void *a)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct net_device *master = dsa_master_netdev(p);
+	struct net_device *master = dsa_slave_to_master(dev);
 	struct sockaddr *addr = a;
 	int err;
 
@@ -255,43 +239,34 @@ dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		   struct net_device *dev, struct net_device *filter_dev,
 		   int *idx)
 {
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct dsa_slave_dump_ctx dump = {
 		.dev = dev,
 		.skb = skb,
 		.cb = cb,
 		.idx = *idx,
 	};
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_port *dp = p->dp;
-	struct dsa_switch *ds = dp->ds;
 	int err;
 
-	if (!ds->ops->port_fdb_dump)
-		return -EOPNOTSUPP;
-
-	err = ds->ops->port_fdb_dump(ds, dp->index,
-				     dsa_slave_port_fdb_do_dump,
-				     &dump);
+	err = dsa_port_fdb_dump(dp, dsa_slave_port_fdb_do_dump, &dump);
 	*idx = dump.idx;
+
 	return err;
 }
 
 static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-
-	if (p->phy != NULL)
-		return phy_mii_ioctl(p->phy, ifr, cmd);
+	if (!dev->phydev)
+		return -ENODEV;
 
-	return -EOPNOTSUPP;
+	return phy_mii_ioctl(dev->phydev, ifr, cmd);
 }
 
 static int dsa_slave_port_attr_set(struct net_device *dev,
 				   const struct switchdev_attr *attr,
 				   struct switchdev_trans *trans)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_port *dp = p->dp;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	int ret;
 
 	switch (attr->id) {
@@ -317,8 +292,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev,
 				  const struct switchdev_obj *obj,
 				  struct switchdev_trans *trans)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_port *dp = p->dp;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	int err;
 
 	/* For the prepare phase, ensure the full set of changes is feasable in
@@ -345,8 +319,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev,
 static int dsa_slave_port_obj_del(struct net_device *dev,
 				  const struct switchdev_obj *obj)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_port *dp = p->dp;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	int err;
 
 	switch (obj->id) {
@@ -367,8 +340,8 @@ static int dsa_slave_port_obj_del(struct net_device *dev,
 static int dsa_slave_port_attr_get(struct net_device *dev,
 				   struct switchdev_attr *attr)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 
 	switch (attr->id) {
 	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
@@ -385,10 +358,12 @@ static int dsa_slave_port_attr_get(struct net_device *dev,
 	return 0;
 }
 
-static inline netdev_tx_t dsa_netpoll_send_skb(struct dsa_slave_priv *p,
-					       struct sk_buff *skb)
+static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev,
+						     struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_POLL_CONTROLLER
+	struct dsa_slave_priv *p = netdev_priv(dev);
+
 	if (p->netpoll)
 		netpoll_send_skb(p->netpoll, skb);
 #else
@@ -422,43 +397,18 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * tag to be successfully transmitted
 	 */
 	if (unlikely(netpoll_tx_running(dev)))
-		return dsa_netpoll_send_skb(p, nskb);
+		return dsa_slave_netpoll_send_skb(dev, nskb);
 
 	/* Queue the SKB for transmission on the parent interface, but
 	 * do not modify its EtherType
 	 */
-	nskb->dev = dsa_master_netdev(p);
+	nskb->dev = dsa_slave_to_master(dev);
 	dev_queue_xmit(nskb);
 
 	return NETDEV_TX_OK;
 }
 
 /* ethtool operations *******************************************************/
-static int
-dsa_slave_get_link_ksettings(struct net_device *dev,
-			     struct ethtool_link_ksettings *cmd)
-{
-	struct dsa_slave_priv *p = netdev_priv(dev);
-
-	if (!p->phy)
-		return -EOPNOTSUPP;
-
-	phy_ethtool_ksettings_get(p->phy, cmd);
-
-	return 0;
-}
-
-static int
-dsa_slave_set_link_ksettings(struct net_device *dev,
-			     const struct ethtool_link_ksettings *cmd)
-{
-	struct dsa_slave_priv *p = netdev_priv(dev);
-
-	if (p->phy != NULL)
-		return phy_ethtool_ksettings_set(p->phy, cmd);
-
-	return -EOPNOTSUPP;
-}
 
 static void dsa_slave_get_drvinfo(struct net_device *dev,
 				  struct ethtool_drvinfo *drvinfo)
@@ -470,11 +420,11 @@ static void dsa_slave_get_drvinfo(struct net_device *dev,
 
 static int dsa_slave_get_regs_len(struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 
 	if (ds->ops->get_regs_len)
-		return ds->ops->get_regs_len(ds, p->dp->index);
+		return ds->ops->get_regs_len(ds, dp->index);
 
 	return -EOPNOTSUPP;
 }
@@ -482,39 +432,27 @@ static int dsa_slave_get_regs_len(struct net_device *dev)
 static void
 dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 
 	if (ds->ops->get_regs)
-		ds->ops->get_regs(ds, p->dp->index, regs, _p);
-}
-
-static int dsa_slave_nway_reset(struct net_device *dev)
-{
-	struct dsa_slave_priv *p = netdev_priv(dev);
-
-	if (p->phy != NULL)
-		return genphy_restart_aneg(p->phy);
-
-	return -EOPNOTSUPP;
+		ds->ops->get_regs(ds, dp->index, regs, _p);
 }
 
 static u32 dsa_slave_get_link(struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
+	if (!dev->phydev)
+		return -ENODEV;
 
-	if (p->phy != NULL) {
-		genphy_update_link(p->phy);
-		return p->phy->link;
-	}
+	genphy_update_link(dev->phydev);
 
-	return -EOPNOTSUPP;
+	return dev->phydev->link;
 }
 
 static int dsa_slave_get_eeprom_len(struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 
 	if (ds->cd && ds->cd->eeprom_len)
 		return ds->cd->eeprom_len;
@@ -528,8 +466,8 @@ static int dsa_slave_get_eeprom_len(struct net_device *dev)
 static int dsa_slave_get_eeprom(struct net_device *dev,
 				struct ethtool_eeprom *eeprom, u8 *data)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 
 	if (ds->ops->get_eeprom)
 		return ds->ops->get_eeprom(ds, eeprom, data);
@@ -540,8 +478,8 @@ static int dsa_slave_get_eeprom(struct net_device *dev,
 static int dsa_slave_set_eeprom(struct net_device *dev,
 				struct ethtool_eeprom *eeprom, u8 *data)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 
 	if (ds->ops->set_eeprom)
 		return ds->ops->set_eeprom(ds, eeprom, data);
@@ -552,8 +490,8 @@ static int dsa_slave_set_eeprom(struct net_device *dev,
 static void dsa_slave_get_strings(struct net_device *dev,
 				  uint32_t stringset, uint8_t *data)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 
 	if (stringset == ETH_SS_STATS) {
 		int len = ETH_GSTRING_LEN;
@@ -563,80 +501,7 @@ static void dsa_slave_get_strings(struct net_device *dev,
 		strncpy(data + 2 * len, "rx_packets", len);
 		strncpy(data + 3 * len, "rx_bytes", len);
 		if (ds->ops->get_strings)
-			ds->ops->get_strings(ds, p->dp->index, data + 4 * len);
-	}
-}
-
-static void dsa_cpu_port_get_ethtool_stats(struct net_device *dev,
-					   struct ethtool_stats *stats,
-					   uint64_t *data)
-{
-	struct dsa_switch_tree *dst = dev->dsa_ptr;
-	struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
-	struct dsa_switch *ds = cpu_dp->ds;
-	s8 cpu_port = cpu_dp->index;
-	int count = 0;
-
-	if (cpu_dp->ethtool_ops.get_sset_count) {
-		count = cpu_dp->ethtool_ops.get_sset_count(dev, ETH_SS_STATS);
-		cpu_dp->ethtool_ops.get_ethtool_stats(dev, stats, data);
-	}
-
-	if (ds->ops->get_ethtool_stats)
-		ds->ops->get_ethtool_stats(ds, cpu_port, data + count);
-}
-
-static int dsa_cpu_port_get_sset_count(struct net_device *dev, int sset)
-{
-	struct dsa_switch_tree *dst = dev->dsa_ptr;
-	struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
-	struct dsa_switch *ds = cpu_dp->ds;
-	int count = 0;
-
-	if (cpu_dp->ethtool_ops.get_sset_count)
-		count += cpu_dp->ethtool_ops.get_sset_count(dev, sset);
-
-	if (sset == ETH_SS_STATS && ds->ops->get_sset_count)
-		count += ds->ops->get_sset_count(ds);
-
-	return count;
-}
-
-static void dsa_cpu_port_get_strings(struct net_device *dev,
-				     uint32_t stringset, uint8_t *data)
-{
-	struct dsa_switch_tree *dst = dev->dsa_ptr;
-	struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
-	struct dsa_switch *ds = cpu_dp->ds;
-	s8 cpu_port = cpu_dp->index;
-	int len = ETH_GSTRING_LEN;
-	int mcount = 0, count;
-	unsigned int i;
-	uint8_t pfx[4];
-	uint8_t *ndata;
-
-	snprintf(pfx, sizeof(pfx), "p%.2d", cpu_port);
-	/* We do not want to be NULL-terminated, since this is a prefix */
-	pfx[sizeof(pfx) - 1] = '_';
-
-	if (cpu_dp->ethtool_ops.get_sset_count) {
-		mcount = cpu_dp->ethtool_ops.get_sset_count(dev, ETH_SS_STATS);
-		cpu_dp->ethtool_ops.get_strings(dev, stringset, data);
-	}
-
-	if (stringset == ETH_SS_STATS && ds->ops->get_strings) {
-		ndata = data + mcount * len;
-		/* This function copies ETH_GSTRINGS_LEN bytes, we will mangle
-		 * the output after to prepend our CPU port prefix we
-		 * constructed earlier
-		 */
-		ds->ops->get_strings(ds, cpu_port, ndata);
-		count = ds->ops->get_sset_count(ds);
-		for (i = 0; i < count; i++) {
-			memmove(ndata + (i * len + sizeof(pfx)),
-				ndata + i * len, len - sizeof(pfx));
-			memcpy(ndata + i * len, pfx, sizeof(pfx));
-		}
+			ds->ops->get_strings(ds, dp->index, data + 4 * len);
 	}
 }
 
@@ -644,8 +509,9 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev,
 					struct ethtool_stats *stats,
 					uint64_t *data)
 {
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_switch *ds = dp->ds;
 	struct pcpu_sw_netstats *s;
 	unsigned int start;
 	int i;
@@ -667,13 +533,13 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev,
 		data[3] += rx_bytes;
 	}
 	if (ds->ops->get_ethtool_stats)
-		ds->ops->get_ethtool_stats(ds, p->dp->index, data + 4);
+		ds->ops->get_ethtool_stats(ds, dp->index, data + 4);
 }
 
 static int dsa_slave_get_sset_count(struct net_device *dev, int sset)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 
 	if (sset == ETH_SS_STATS) {
 		int count;
@@ -690,77 +556,77 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset)
 
 static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 
 	if (ds->ops->get_wol)
-		ds->ops->get_wol(ds, p->dp->index, w);
+		ds->ops->get_wol(ds, dp->index, w);
 }
 
 static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 	int ret = -EOPNOTSUPP;
 
 	if (ds->ops->set_wol)
-		ret = ds->ops->set_wol(ds, p->dp->index, w);
+		ret = ds->ops->set_wol(ds, dp->index, w);
 
 	return ret;
 }
 
 static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 	int ret;
 
 	/* Port's PHY and MAC both need to be EEE capable */
-	if (!p->phy)
+	if (!dev->phydev)
 		return -ENODEV;
 
 	if (!ds->ops->set_mac_eee)
 		return -EOPNOTSUPP;
 
-	ret = ds->ops->set_mac_eee(ds, p->dp->index, e);
+	ret = ds->ops->set_mac_eee(ds, dp->index, e);
 	if (ret)
 		return ret;
 
 	if (e->eee_enabled) {
-		ret = phy_init_eee(p->phy, 0);
+		ret = phy_init_eee(dev->phydev, 0);
 		if (ret)
 			return ret;
 	}
 
-	return phy_ethtool_set_eee(p->phy, e);
+	return phy_ethtool_set_eee(dev->phydev, e);
 }
 
 static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 	int ret;
 
 	/* Port's PHY and MAC both need to be EEE capable */
-	if (!p->phy)
+	if (!dev->phydev)
 		return -ENODEV;
 
 	if (!ds->ops->get_mac_eee)
 		return -EOPNOTSUPP;
 
-	ret = ds->ops->get_mac_eee(ds, p->dp->index, e);
+	ret = ds->ops->get_mac_eee(ds, dp->index, e);
 	if (ret)
 		return ret;
 
-	return phy_ethtool_get_eee(p->phy, e);
+	return phy_ethtool_get_eee(dev->phydev, e);
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static int dsa_slave_netpoll_setup(struct net_device *dev,
 				   struct netpoll_info *ni)
 {
+	struct net_device *master = dsa_slave_to_master(dev);
 	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct net_device *master = dsa_master_netdev(p);
 	struct netpoll *netpoll;
 	int err = 0;
 
@@ -800,18 +666,18 @@ static void dsa_slave_poll_controller(struct net_device *dev)
 static int dsa_slave_get_phys_port_name(struct net_device *dev,
 					char *name, size_t len)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 
-	if (snprintf(name, len, "p%d", p->dp->index) >= len)
+	if (snprintf(name, len, "p%d", dp->index) >= len)
 		return -EINVAL;
 
 	return 0;
 }
 
 static struct dsa_mall_tc_entry *
-dsa_slave_mall_tc_entry_find(struct dsa_slave_priv *p,
-			     unsigned long cookie)
+dsa_slave_mall_tc_entry_find(struct net_device *dev, unsigned long cookie)
 {
+	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct dsa_mall_tc_entry *mall_tc_entry;
 
 	list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list)
@@ -825,14 +691,15 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev,
 				      struct tc_cls_matchall_offload *cls,
 				      bool ingress)
 {
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct dsa_mall_tc_entry *mall_tc_entry;
 	__be16 protocol = cls->common.protocol;
-	struct dsa_switch *ds = p->dp->ds;
 	struct net *net = dev_net(dev);
-	struct dsa_slave_priv *to_p;
+	struct dsa_switch *ds = dp->ds;
 	struct net_device *to_dev;
 	const struct tc_action *a;
+	struct dsa_port *to_dp;
 	int err = -EOPNOTSUPP;
 	LIST_HEAD(actions);
 	int ifindex;
@@ -865,13 +732,12 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev,
 		mall_tc_entry->type = DSA_PORT_MALL_MIRROR;
 		mirror = &mall_tc_entry->mirror;
 
-		to_p = netdev_priv(to_dev);
+		to_dp = dsa_slave_to_port(to_dev);
 
-		mirror->to_local_port = to_p->dp->index;
+		mirror->to_local_port = to_dp->index;
 		mirror->ingress = ingress;
 
-		err = ds->ops->port_mirror_add(ds, p->dp->index, mirror,
-					       ingress);
+		err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress);
 		if (err) {
 			kfree(mall_tc_entry);
 			return err;
@@ -886,14 +752,14 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev,
 static void dsa_slave_del_cls_matchall(struct net_device *dev,
 				       struct tc_cls_matchall_offload *cls)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct dsa_mall_tc_entry *mall_tc_entry;
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_switch *ds = dp->ds;
 
 	if (!ds->ops->port_mirror_del)
 		return;
 
-	mall_tc_entry = dsa_slave_mall_tc_entry_find(p, cls->cookie);
+	mall_tc_entry = dsa_slave_mall_tc_entry_find(dev, cls->cookie);
 	if (!mall_tc_entry)
 		return;
 
@@ -901,8 +767,7 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev,
 
 	switch (mall_tc_entry->type) {
 	case DSA_PORT_MALL_MIRROR:
-		ds->ops->port_mirror_del(ds, p->dp->index,
-					 &mall_tc_entry->mirror);
+		ds->ops->port_mirror_del(ds, dp->index, &mall_tc_entry->mirror);
 		break;
 	default:
 		WARN_ON(1);
@@ -912,17 +777,9 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev,
 }
 
 static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev,
-					   struct tc_cls_matchall_offload *cls)
+					   struct tc_cls_matchall_offload *cls,
+					   bool ingress)
 {
-	bool ingress;
-
-	if (is_classid_clsact_ingress(cls->common.classid))
-		ingress = true;
-	else if (is_classid_clsact_egress(cls->common.classid))
-		ingress = false;
-	else
-		return -EOPNOTSUPP;
-
 	if (cls->common.chain_index)
 		return -EOPNOTSUPP;
 
@@ -937,12 +794,63 @@ static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev,
 	}
 }
 
+static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				       void *cb_priv, bool ingress)
+{
+	struct net_device *dev = cb_priv;
+
+	if (!tc_can_offload(dev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSMATCHALL:
+		return dsa_slave_setup_tc_cls_matchall(dev, type_data, ingress);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int dsa_slave_setup_tc_block_cb_ig(enum tc_setup_type type,
+					  void *type_data, void *cb_priv)
+{
+	return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, true);
+}
+
+static int dsa_slave_setup_tc_block_cb_eg(enum tc_setup_type type,
+					  void *type_data, void *cb_priv)
+{
+	return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, false);
+}
+
+static int dsa_slave_setup_tc_block(struct net_device *dev,
+				    struct tc_block_offload *f)
+{
+	tc_setup_cb_t *cb;
+
+	if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		cb = dsa_slave_setup_tc_block_cb_ig;
+	else if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
+		cb = dsa_slave_setup_tc_block_cb_eg;
+	else
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block, cb, dev, dev);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, cb, dev);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			      void *type_data)
 {
 	switch (type) {
-	case TC_SETUP_CLSMATCHALL:
-		return dsa_slave_setup_tc_cls_matchall(dev, type_data);
+	case TC_SETUP_BLOCK:
+		return dsa_slave_setup_tc_block(dev, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -976,42 +884,35 @@ static void dsa_slave_get_stats64(struct net_device *dev,
 	}
 }
 
-void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops)
-{
-	ops->get_sset_count = dsa_cpu_port_get_sset_count;
-	ops->get_ethtool_stats = dsa_cpu_port_get_ethtool_stats;
-	ops->get_strings = dsa_cpu_port_get_strings;
-}
-
 static int dsa_slave_get_rxnfc(struct net_device *dev,
 			       struct ethtool_rxnfc *nfc, u32 *rule_locs)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 
 	if (!ds->ops->get_rxnfc)
 		return -EOPNOTSUPP;
 
-	return ds->ops->get_rxnfc(ds, p->dp->index, nfc, rule_locs);
+	return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs);
 }
 
 static int dsa_slave_set_rxnfc(struct net_device *dev,
 			       struct ethtool_rxnfc *nfc)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
 
 	if (!ds->ops->set_rxnfc)
 		return -EOPNOTSUPP;
 
-	return ds->ops->set_rxnfc(ds, p->dp->index, nfc);
+	return ds->ops->set_rxnfc(ds, dp->index, nfc);
 }
 
 static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_drvinfo		= dsa_slave_get_drvinfo,
 	.get_regs_len		= dsa_slave_get_regs_len,
 	.get_regs		= dsa_slave_get_regs,
-	.nway_reset		= dsa_slave_nway_reset,
+	.nway_reset		= phy_ethtool_nway_reset,
 	.get_link		= dsa_slave_get_link,
 	.get_eeprom_len		= dsa_slave_get_eeprom_len,
 	.get_eeprom		= dsa_slave_get_eeprom,
@@ -1023,8 +924,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_wol		= dsa_slave_get_wol,
 	.set_eee		= dsa_slave_set_eee,
 	.get_eee		= dsa_slave_get_eee,
-	.get_link_ksettings	= dsa_slave_get_link_ksettings,
-	.set_link_ksettings	= dsa_slave_set_link_ksettings,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 	.get_rxnfc		= dsa_slave_get_rxnfc,
 	.set_rxnfc		= dsa_slave_set_rxnfc,
 };
@@ -1064,78 +965,81 @@ static struct device_type dsa_type = {
 
 static void dsa_slave_adjust_link(struct net_device *dev)
 {
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_switch *ds = dp->ds;
 	unsigned int status_changed = 0;
 
-	if (p->old_link != p->phy->link) {
+	if (p->old_link != dev->phydev->link) {
 		status_changed = 1;
-		p->old_link = p->phy->link;
+		p->old_link = dev->phydev->link;
 	}
 
-	if (p->old_duplex != p->phy->duplex) {
+	if (p->old_duplex != dev->phydev->duplex) {
 		status_changed = 1;
-		p->old_duplex = p->phy->duplex;
+		p->old_duplex = dev->phydev->duplex;
 	}
 
-	if (p->old_pause != p->phy->pause) {
+	if (p->old_pause != dev->phydev->pause) {
 		status_changed = 1;
-		p->old_pause = p->phy->pause;
+		p->old_pause = dev->phydev->pause;
 	}
 
 	if (ds->ops->adjust_link && status_changed)
-		ds->ops->adjust_link(ds, p->dp->index, p->phy);
+		ds->ops->adjust_link(ds, dp->index, dev->phydev);
 
 	if (status_changed)
-		phy_print_status(p->phy);
+		phy_print_status(dev->phydev);
 }
 
 static int dsa_slave_fixed_link_update(struct net_device *dev,
 				       struct fixed_phy_status *status)
 {
-	struct dsa_slave_priv *p;
 	struct dsa_switch *ds;
+	struct dsa_port *dp;
 
 	if (dev) {
-		p = netdev_priv(dev);
-		ds = p->dp->ds;
+		dp = dsa_slave_to_port(dev);
+		ds = dp->ds;
 		if (ds->ops->fixed_link_update)
-			ds->ops->fixed_link_update(ds, p->dp->index, status);
+			ds->ops->fixed_link_update(ds, dp->index, status);
 	}
 
 	return 0;
 }
 
 /* slave device setup *******************************************************/
-static int dsa_slave_phy_connect(struct dsa_slave_priv *p,
-				 struct net_device *slave_dev,
-				 int addr)
+static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr)
 {
-	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *dp = dsa_slave_to_port(slave_dev);
+	struct dsa_slave_priv *p = netdev_priv(slave_dev);
+	struct dsa_switch *ds = dp->ds;
 
-	p->phy = mdiobus_get_phy(ds->slave_mii_bus, addr);
-	if (!p->phy) {
+	slave_dev->phydev = mdiobus_get_phy(ds->slave_mii_bus, addr);
+	if (!slave_dev->phydev) {
 		netdev_err(slave_dev, "no phy at %d\n", addr);
 		return -ENODEV;
 	}
 
 	/* Use already configured phy mode */
 	if (p->phy_interface == PHY_INTERFACE_MODE_NA)
-		p->phy_interface = p->phy->interface;
-	return phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
-				  p->phy_interface);
+		p->phy_interface = slave_dev->phydev->interface;
+
+	return phy_connect_direct(slave_dev, slave_dev->phydev,
+				  dsa_slave_adjust_link, p->phy_interface);
 }
 
-static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
-				struct net_device *slave_dev)
+static int dsa_slave_phy_setup(struct net_device *slave_dev)
 {
-	struct dsa_switch *ds = p->dp->ds;
-	struct device_node *phy_dn, *port_dn;
+	struct dsa_port *dp = dsa_slave_to_port(slave_dev);
+	struct dsa_slave_priv *p = netdev_priv(slave_dev);
+	struct device_node *port_dn = dp->dn;
+	struct dsa_switch *ds = dp->ds;
+	struct device_node *phy_dn;
 	bool phy_is_fixed = false;
 	u32 phy_flags = 0;
 	int mode, ret;
 
-	port_dn = p->dp->dn;
 	mode = of_get_phy_mode(port_dn);
 	if (mode < 0)
 		mode = PHY_INTERFACE_MODE_NA;
@@ -1156,52 +1060,35 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
 	}
 
 	if (ds->ops->get_phy_flags)
-		phy_flags = ds->ops->get_phy_flags(ds, p->dp->index);
+		phy_flags = ds->ops->get_phy_flags(ds, dp->index);
 
 	if (phy_dn) {
-		int phy_id = of_mdio_parse_addr(&slave_dev->dev, phy_dn);
-
-		/* If this PHY address is part of phys_mii_mask, which means
-		 * that we need to divert reads and writes to/from it, then we
-		 * want to bind this device using the slave MII bus created by
-		 * DSA to make that happen.
-		 */
-		if (!phy_is_fixed && phy_id >= 0 &&
-		    (ds->phys_mii_mask & (1 << phy_id))) {
-			ret = dsa_slave_phy_connect(p, slave_dev, phy_id);
-			if (ret) {
-				netdev_err(slave_dev, "failed to connect to phy%d: %d\n", phy_id, ret);
-				of_node_put(phy_dn);
-				return ret;
-			}
-		} else {
-			p->phy = of_phy_connect(slave_dev, phy_dn,
-						dsa_slave_adjust_link,
-						phy_flags,
-						p->phy_interface);
-		}
-
+		slave_dev->phydev = of_phy_connect(slave_dev, phy_dn,
+						   dsa_slave_adjust_link,
+						   phy_flags,
+						   p->phy_interface);
 		of_node_put(phy_dn);
 	}
 
-	if (p->phy && phy_is_fixed)
-		fixed_phy_set_link_update(p->phy, dsa_slave_fixed_link_update);
+	if (slave_dev->phydev && phy_is_fixed)
+		fixed_phy_set_link_update(slave_dev->phydev,
+					  dsa_slave_fixed_link_update);
 
 	/* We could not connect to a designated PHY, so use the switch internal
 	 * MDIO bus instead
 	 */
-	if (!p->phy) {
-		ret = dsa_slave_phy_connect(p, slave_dev, p->dp->index);
+	if (!slave_dev->phydev) {
+		ret = dsa_slave_phy_connect(slave_dev, dp->index);
 		if (ret) {
 			netdev_err(slave_dev, "failed to connect to port %d: %d\n",
-				   p->dp->index, ret);
+				   dp->index, ret);
 			if (phy_is_fixed)
 				of_phy_deregister_fixed_link(port_dn);
 			return ret;
 		}
 	}
 
-	phy_attached_info(p->phy);
+	phy_attached_info(slave_dev->phydev);
 
 	return 0;
 }
@@ -1221,12 +1108,12 @@ int dsa_slave_suspend(struct net_device *slave_dev)
 
 	netif_device_detach(slave_dev);
 
-	if (p->phy) {
-		phy_stop(p->phy);
+	if (slave_dev->phydev) {
+		phy_stop(slave_dev->phydev);
 		p->old_pause = -1;
 		p->old_link = -1;
 		p->old_duplex = -1;
-		phy_suspend(p->phy);
+		phy_suspend(slave_dev->phydev);
 	}
 
 	return 0;
@@ -1234,31 +1121,40 @@ int dsa_slave_suspend(struct net_device *slave_dev)
 
 int dsa_slave_resume(struct net_device *slave_dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(slave_dev);
-
 	netif_device_attach(slave_dev);
 
-	if (p->phy) {
-		phy_resume(p->phy);
-		phy_start(p->phy);
+	if (slave_dev->phydev) {
+		phy_resume(slave_dev->phydev);
+		phy_start(slave_dev->phydev);
 	}
 
 	return 0;
 }
 
-int dsa_slave_create(struct dsa_port *port, const char *name)
+static void dsa_slave_notify(struct net_device *dev, unsigned long val)
 {
+	struct net_device *master = dsa_slave_to_master(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_notifier_register_info rinfo = {
+		.switch_number = dp->ds->index,
+		.port_number = dp->index,
+		.master = master,
+		.info.dev = dev,
+	};
+
+	call_dsa_notifiers(val, dev, &rinfo.info);
+}
+
+int dsa_slave_create(struct dsa_port *port)
+{
+	struct dsa_port *cpu_dp = port->cpu_dp;
+	struct net_device *master = cpu_dp->master;
 	struct dsa_switch *ds = port->ds;
-	struct dsa_switch_tree *dst = ds->dst;
-	struct net_device *master;
+	const char *name = port->name;
 	struct net_device *slave_dev;
 	struct dsa_slave_priv *p;
-	struct dsa_port *cpu_dp;
 	int ret;
 
-	cpu_dp = ds->dst->cpu_dp;
-	master = cpu_dp->netdev;
-
 	if (!ds->num_tx_queues)
 		ds->num_tx_queues = 1;
 
@@ -1294,22 +1190,24 @@ int dsa_slave_create(struct dsa_port *port, const char *name)
 	}
 	p->dp = port;
 	INIT_LIST_HEAD(&p->mall_tc_list);
-	p->xmit = dst->tag_ops->xmit;
+	p->xmit = cpu_dp->tag_ops->xmit;
 
 	p->old_pause = -1;
 	p->old_link = -1;
 	p->old_duplex = -1;
 
-	port->netdev = slave_dev;
+	port->slave = slave_dev;
 
 	netif_carrier_off(slave_dev);
 
-	ret = dsa_slave_phy_setup(p, slave_dev);
+	ret = dsa_slave_phy_setup(slave_dev);
 	if (ret) {
 		netdev_err(master, "error %d setting up slave phy\n", ret);
 		goto out_free;
 	}
 
+	dsa_slave_notify(slave_dev, DSA_PORT_REGISTER);
+
 	ret = register_netdev(slave_dev);
 	if (ret) {
 		netdev_err(master, "error %d registering interface %s\n",
@@ -1320,30 +1218,30 @@ int dsa_slave_create(struct dsa_port *port, const char *name)
 	return 0;
 
 out_phy:
-	phy_disconnect(p->phy);
-	if (of_phy_is_fixed_link(p->dp->dn))
-		of_phy_deregister_fixed_link(p->dp->dn);
+	phy_disconnect(slave_dev->phydev);
+	if (of_phy_is_fixed_link(port->dn))
+		of_phy_deregister_fixed_link(port->dn);
 out_free:
 	free_percpu(p->stats64);
 	free_netdev(slave_dev);
-	port->netdev = NULL;
+	port->slave = NULL;
 	return ret;
 }
 
 void dsa_slave_destroy(struct net_device *slave_dev)
 {
+	struct dsa_port *dp = dsa_slave_to_port(slave_dev);
 	struct dsa_slave_priv *p = netdev_priv(slave_dev);
-	struct device_node *port_dn;
-
-	port_dn = p->dp->dn;
+	struct device_node *port_dn = dp->dn;
 
 	netif_carrier_off(slave_dev);
-	if (p->phy) {
-		phy_disconnect(p->phy);
+	if (slave_dev->phydev) {
+		phy_disconnect(slave_dev->phydev);
 
 		if (of_phy_is_fixed_link(port_dn))
 			of_phy_deregister_fixed_link(port_dn);
 	}
+	dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER);
 	unregister_netdev(slave_dev);
 	free_percpu(p->stats64);
 	free_netdev(slave_dev);
@@ -1357,8 +1255,7 @@ static bool dsa_slave_dev_check(struct net_device *dev)
 static int dsa_slave_changeupper(struct net_device *dev,
 				 struct netdev_notifier_changeupper_info *info)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_port *dp = p->dp;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	int err = NOTIFY_DONE;
 
 	if (netif_is_bridge_master(info->upper_dev)) {
@@ -1379,7 +1276,7 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (dev->netdev_ops != &dsa_slave_netdev_ops)
+	if (!dsa_slave_dev_check(dev))
 		return NOTIFY_DONE;
 
 	if (event == NETDEV_CHANGEUPPER)
@@ -1401,14 +1298,14 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work)
 		container_of(work, struct dsa_switchdev_event_work, work);
 	struct net_device *dev = switchdev_work->dev;
 	struct switchdev_notifier_fdb_info *fdb_info;
-	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	int err;
 
 	rtnl_lock();
 	switch (switchdev_work->event) {
 	case SWITCHDEV_FDB_ADD_TO_DEVICE:
 		fdb_info = &switchdev_work->fdb_info;
-		err = dsa_port_fdb_add(p->dp, fdb_info->addr, fdb_info->vid);
+		err = dsa_port_fdb_add(dp, fdb_info->addr, fdb_info->vid);
 		if (err) {
 			netdev_dbg(dev, "fdb add failed err=%d\n", err);
 			break;
@@ -1419,7 +1316,7 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work)
 
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:
 		fdb_info = &switchdev_work->fdb_info;
-		err = dsa_port_fdb_del(p->dp, fdb_info->addr, fdb_info->vid);
+		err = dsa_port_fdb_del(dp, fdb_info->addr, fdb_info->vid);
 		if (err) {
 			netdev_dbg(dev, "fdb del failed err=%d\n", err);
 			dev_close(dev);
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index dbb016434ace..9e082bae3cb0 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -61,7 +61,7 @@
 
 static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u16 queue = skb_get_queue_mapping(skb);
 	u8 *brcm_tag;
 
@@ -82,9 +82,14 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev
 		       ((queue & BRCM_IG_TC_MASK) << BRCM_IG_TC_SHIFT);
 	brcm_tag[1] = 0;
 	brcm_tag[2] = 0;
-	if (p->dp->index == 8)
+	if (dp->index == 8)
 		brcm_tag[2] = BRCM_IG_DSTMAP2_MASK;
-	brcm_tag[3] = (1 << p->dp->index) & BRCM_IG_DSTMAP1_MASK;
+	brcm_tag[3] = (1 << dp->index) & BRCM_IG_DSTMAP1_MASK;
+
+	/* Now tell the master network device about the desired output queue
+	 * as well
+	 */
+	skb_set_queue_mapping(skb, BRCM_TAG_SET_PORT_QUEUE(dp->index, queue));
 
 	return skb;
 }
@@ -92,9 +97,6 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev
 static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 				    struct packet_type *pt)
 {
-	struct dsa_switch_tree *dst = dev->dsa_ptr;
-	struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
-	struct dsa_switch *ds = cpu_dp->ds;
 	int source_port;
 	u8 *brcm_tag;
 
@@ -117,8 +119,8 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	/* Locate which port this is coming from */
 	source_port = brcm_tag[3] & BRCM_EG_PID_MASK;
 
-	/* Validate port against switch setup, either the port is totally */
-	if (source_port >= ds->num_ports || !ds->ports[source_port].netdev)
+	skb->dev = dsa_master_find_slave(dev, 0, source_port);
+	if (!skb->dev)
 		return NULL;
 
 	/* Remove Broadcom tag and update checksum */
@@ -129,8 +131,6 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 		skb->data - ETH_HLEN - BRCM_TAG_LEN,
 		2 * ETH_ALEN);
 
-	skb->dev = ds->ports[source_port].netdev;
-
 	return skb;
 }
 
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index fbf9ca954773..dbbcdafed8c3 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -18,7 +18,7 @@
 
 static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u8 *dsa_header;
 
 	/*
@@ -34,8 +34,8 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
 		 * Construct tagged FROM_CPU DSA tag from 802.1q tag.
 		 */
 		dsa_header = skb->data + 2 * ETH_ALEN;
-		dsa_header[0] = 0x60 | p->dp->ds->index;
-		dsa_header[1] = p->dp->index << 3;
+		dsa_header[0] = 0x60 | dp->ds->index;
+		dsa_header[1] = dp->index << 3;
 
 		/*
 		 * Move CFI field from byte 2 to byte 1.
@@ -55,8 +55,8 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
 		 * Construct untagged FROM_CPU DSA tag.
 		 */
 		dsa_header = skb->data + 2 * ETH_ALEN;
-		dsa_header[0] = 0x40 | p->dp->ds->index;
-		dsa_header[1] = p->dp->index << 3;
+		dsa_header[0] = 0x40 | dp->ds->index;
+		dsa_header[1] = dp->index << 3;
 		dsa_header[2] = 0x00;
 		dsa_header[3] = 0x00;
 	}
@@ -67,8 +67,6 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
 static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
 			       struct packet_type *pt)
 {
-	struct dsa_switch_tree *dst = dev->dsa_ptr;
-	struct dsa_switch *ds;
 	u8 *dsa_header;
 	int source_device;
 	int source_port;
@@ -93,18 +91,8 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
 	source_device = dsa_header[0] & 0x1f;
 	source_port = (dsa_header[1] >> 3) & 0x1f;
 
-	/*
-	 * Check that the source device exists and that the source
-	 * port is a registered DSA port.
-	 */
-	if (source_device >= DSA_MAX_SWITCHES)
-		return NULL;
-
-	ds = dst->ds[source_device];
-	if (!ds)
-		return NULL;
-
-	if (source_port >= ds->num_ports || !ds->ports[source_port].netdev)
+	skb->dev = dsa_master_find_slave(dev, source_device, source_port);
+	if (!skb->dev)
 		return NULL;
 
 	/*
@@ -153,8 +141,6 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
 			2 * ETH_ALEN);
 	}
 
-	skb->dev = ds->ports[source_port].netdev;
-
 	return skb;
 }
 
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 76367ba1b2e2..f38a626b3a05 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -19,7 +19,7 @@
 
 static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u8 *edsa_header;
 
 	/*
@@ -43,8 +43,8 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
 		edsa_header[1] = ETH_P_EDSA & 0xff;
 		edsa_header[2] = 0x00;
 		edsa_header[3] = 0x00;
-		edsa_header[4] = 0x60 | p->dp->ds->index;
-		edsa_header[5] = p->dp->index << 3;
+		edsa_header[4] = 0x60 | dp->ds->index;
+		edsa_header[5] = dp->index << 3;
 
 		/*
 		 * Move CFI field from byte 6 to byte 5.
@@ -68,8 +68,8 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
 		edsa_header[1] = ETH_P_EDSA & 0xff;
 		edsa_header[2] = 0x00;
 		edsa_header[3] = 0x00;
-		edsa_header[4] = 0x40 | p->dp->ds->index;
-		edsa_header[5] = p->dp->index << 3;
+		edsa_header[4] = 0x40 | dp->ds->index;
+		edsa_header[5] = dp->index << 3;
 		edsa_header[6] = 0x00;
 		edsa_header[7] = 0x00;
 	}
@@ -80,8 +80,6 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
 static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
 				struct packet_type *pt)
 {
-	struct dsa_switch_tree *dst = dev->dsa_ptr;
-	struct dsa_switch *ds;
 	u8 *edsa_header;
 	int source_device;
 	int source_port;
@@ -106,18 +104,8 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
 	source_device = edsa_header[0] & 0x1f;
 	source_port = (edsa_header[1] >> 3) & 0x1f;
 
-	/*
-	 * Check that the source device exists and that the source
-	 * port is a registered DSA port.
-	 */
-	if (source_device >= DSA_MAX_SWITCHES)
-		return NULL;
-
-	ds = dst->ds[source_device];
-	if (!ds)
-		return NULL;
-
-	if (source_port >= ds->num_ports || !ds->ports[source_port].netdev)
+	skb->dev = dsa_master_find_slave(dev, source_device, source_port);
+	if (!skb->dev)
 		return NULL;
 
 	/*
@@ -172,8 +160,6 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
 			2 * ETH_ALEN);
 	}
 
-	skb->dev = ds->ports[source_port].netdev;
-
 	return skb;
 }
 
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 010ca0a336c4..0f62effad88f 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -34,7 +34,7 @@
 
 static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct sk_buff *nskb;
 	int padlen;
 	u8 *tag;
@@ -72,7 +72,7 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN);
 	tag[0] = 0;
-	tag[1] = 1 << p->dp->index; /* destination port */
+	tag[1] = 1 << dp->index; /* destination port */
 
 	return nskb;
 }
@@ -80,22 +80,19 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev)
 static struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev,
 			       struct packet_type *pt)
 {
-	struct dsa_switch_tree *dst = dev->dsa_ptr;
-	struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
-	struct dsa_switch *ds = cpu_dp->ds;
 	u8 *tag;
 	int source_port;
 
 	tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
 
 	source_port = tag[0] & 7;
-	if (source_port >= ds->num_ports || !ds->ports[source_port].netdev)
+
+	skb->dev = dsa_master_find_slave(dev, 0, source_port);
+	if (!skb->dev)
 		return NULL;
 
 	pskb_trim_rcsum(skb, skb->len - KSZ_EGRESS_TAG_LEN);
 
-	skb->dev = ds->ports[source_port].netdev;
-
 	return skb;
 }
 
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index 0b9826105e42..e526c8967b98 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -11,6 +11,7 @@
  * GNU General Public License for more details.
  *
  */
+#include <linux/dsa/lan9303.h>
 #include <linux/etherdevice.h>
 #include <linux/list.h>
 #include <linux/slab.h>
@@ -39,10 +40,26 @@
  */
 
 #define LAN9303_TAG_LEN 4
+# define LAN9303_TAG_TX_USE_ALR BIT(3)
+# define LAN9303_TAG_TX_STP_OVERRIDE BIT(4)
+
+/* Decide whether to transmit using ALR lookup, or transmit directly to
+ * port using tag. ALR learning is performed only when using ALR lookup.
+ * If the two external ports are bridged and the frame is unicast,
+ * then use ALR lookup to allow ALR learning on CPU port.
+ * Otherwise transmit directly to port with STP state override.
+ * See also: lan9303_separate_ports() and lan9303.pdf 6.4.10.1
+ */
+static int lan9303_xmit_use_arl(struct dsa_port *dp, u8 *dest_addr)
+{
+	struct lan9303 *chip = dp->ds->priv;
+
+	return chip->is_bridged && !is_multicast_ether_addr(dest_addr);
+}
 
 static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u16 *lan9303_tag;
 
 	/* insert a special VLAN tag between the MAC addresses
@@ -62,7 +79,10 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	lan9303_tag = (u16 *)(skb->data + 2 * ETH_ALEN);
 	lan9303_tag[0] = htons(ETH_P_8021Q);
-	lan9303_tag[1] = htons(p->dp->index | BIT(4));
+	lan9303_tag[1] = lan9303_xmit_use_arl(dp, skb->data) ?
+				LAN9303_TAG_TX_USE_ALR :
+				dp->index | LAN9303_TAG_TX_STP_OVERRIDE;
+	lan9303_tag[1] = htons(lan9303_tag[1]);
 
 	return skb;
 }
@@ -71,17 +91,8 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev,
 			struct packet_type *pt)
 {
 	u16 *lan9303_tag;
-	struct dsa_switch_tree *dst = dev->dsa_ptr;
-	struct dsa_switch *ds;
 	unsigned int source_port;
 
-	ds = dst->ds[0];
-
-	if (unlikely(!ds)) {
-		dev_warn_ratelimited(&dev->dev, "Dropping packet, due to missing DSA switch device\n");
-		return NULL;
-	}
-
 	if (unlikely(!pskb_may_pull(skb, LAN9303_TAG_LEN))) {
 		dev_warn_ratelimited(&dev->dev,
 				     "Dropping packet, cannot pull\n");
@@ -103,25 +114,20 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	source_port = ntohs(lan9303_tag[1]) & 0x3;
 
-	if (source_port >= ds->num_ports) {
+	skb->dev = dsa_master_find_slave(dev, 0, source_port);
+	if (!skb->dev) {
 		dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n");
 		return NULL;
 	}
 
-	if (!ds->ports[source_port].netdev) {
-		dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid netdev or device\n");
-		return NULL;
-	}
-
 	/* remove the special VLAN tag between the MAC addresses
 	 * and the current ethertype field.
 	 */
 	skb_pull_rcsum(skb, 2 + 2);
 	memmove(skb->data - ETH_HLEN, skb->data - (ETH_HLEN + LAN9303_TAG_LEN),
 		2 * ETH_ALEN);
-
-	/* forward the packet to the dedicated interface */
-	skb->dev = ds->ports[source_port].netdev;
+	skb->offload_fwd_mark = !ether_addr_equal(skb->data - ETH_HLEN,
+						  eth_stp_addr);
 
 	return skb;
 }
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index ec8ee5f43255..8475434af7d5 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -23,7 +23,7 @@
 static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 				    struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u8 *mtk_tag;
 
 	if (skb_cow_head(skb, MTK_HDR_LEN) < 0)
@@ -36,7 +36,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 	/* Build the tag after the MAC Source Address */
 	mtk_tag = skb->data + 2 * ETH_ALEN;
 	mtk_tag[0] = 0;
-	mtk_tag[1] = (1 << p->dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
+	mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
 	mtk_tag[2] = 0;
 	mtk_tag[3] = 0;
 
@@ -46,8 +46,6 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 				   struct packet_type *pt)
 {
-	struct dsa_switch_tree *dst = dev->dsa_ptr;
-	struct dsa_switch *ds;
 	int port;
 	__be16 *phdr, hdr;
 
@@ -68,20 +66,12 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 		skb->data - ETH_HLEN - MTK_HDR_LEN,
 		2 * ETH_ALEN);
 
-	/* This protocol doesn't support cascading multiple
-	 * switches so it's safe to assume the switch is first
-	 * in the tree.
-	 */
-	ds = dst->ds[0];
-	if (!ds)
-		return NULL;
-
 	/* Get source port information */
 	port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK);
-	if (!ds->ports[port].netdev)
-		return NULL;
 
-	skb->dev = ds->ports[port].netdev;
+	skb->dev = dsa_master_find_slave(dev, 0, port);
+	if (!skb->dev)
+		return NULL;
 
 	return skb;
 }
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 1d4c70711c0f..613f4ee97771 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -38,7 +38,7 @@
 
 static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u16 *phdr, hdr;
 
 	dev->stats.tx_packets++;
@@ -54,8 +54,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Set the version field, and set destination port information */
 	hdr = QCA_HDR_VERSION << QCA_HDR_XMIT_VERSION_S |
-		QCA_HDR_XMIT_FROM_CPU |
-		BIT(p->dp->index);
+		QCA_HDR_XMIT_FROM_CPU | BIT(dp->index);
 
 	*phdr = htons(hdr);
 
@@ -65,9 +64,6 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
 static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 				   struct packet_type *pt)
 {
-	struct dsa_switch_tree *dst = dev->dsa_ptr;
-	struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
-	struct dsa_switch *ds;
 	u8 ver;
 	int port;
 	__be16 *phdr, hdr;
@@ -92,20 +88,12 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - QCA_HDR_LEN,
 		ETH_HLEN - QCA_HDR_LEN);
 
-	/* This protocol doesn't support cascading multiple switches so it's
-	 * safe to assume the switch is first in the tree
-	 */
-	ds = cpu_dp->ds;
-	if (!ds)
-		return NULL;
-
 	/* Get source port information */
 	port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK);
-	if (!ds->ports[port].netdev)
-		return NULL;
 
-	/* Update skb & forward the frame accordingly */
-	skb->dev = ds->ports[port].netdev;
+	skb->dev = dsa_master_find_slave(dev, 0, port);
+	if (!skb->dev)
+		return NULL;
 
 	return skb;
 }
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index d2fd4923aa3e..7d20e1f3de28 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -16,7 +16,7 @@
 
 static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct sk_buff *nskb;
 	int padlen;
 	u8 *trailer;
@@ -48,7 +48,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	trailer = skb_put(nskb, 4);
 	trailer[0] = 0x80;
-	trailer[1] = 1 << p->dp->index;
+	trailer[1] = 1 << dp->index;
 	trailer[2] = 0x10;
 	trailer[3] = 0x00;
 
@@ -58,9 +58,6 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
 static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
 				   struct packet_type *pt)
 {
-	struct dsa_switch_tree *dst = dev->dsa_ptr;
-	struct dsa_port *cpu_dp = dsa_get_cpu_port(dst);
-	struct dsa_switch *ds = cpu_dp->ds;
 	u8 *trailer;
 	int source_port;
 
@@ -73,13 +70,13 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
 		return NULL;
 
 	source_port = trailer[1] & 7;
-	if (source_port >= ds->num_ports || !ds->ports[source_port].netdev)
+
+	skb->dev = dsa_master_find_slave(dev, 0, source_port);
+	if (!skb->dev)
 		return NULL;
 
 	pskb_trim_rcsum(skb, skb->len - 4);
 
-	skb->dev = ds->ports[source_port].netdev;
-
 	return skb;
 }
 
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 172d8309f89e..b8cd43c9ed5b 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -328,12 +328,12 @@ out:
 
 /* Announce (supervision frame) timer function
  */
-static void hsr_announce(unsigned long data)
+static void hsr_announce(struct timer_list *t)
 {
 	struct hsr_priv *hsr;
 	struct hsr_port *master;
 
-	hsr = (struct hsr_priv *) data;
+	hsr = from_timer(hsr, t, announce_timer);
 
 	rcu_read_lock();
 	master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
@@ -463,9 +463,8 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 	hsr->sequence_nr = HSR_SEQNR_START;
 	hsr->sup_sequence_nr = HSR_SUP_SEQNR_START;
 
-	setup_timer(&hsr->announce_timer, hsr_announce, (unsigned long)hsr);
-
-	setup_timer(&hsr->prune_timer, hsr_prune_nodes, (unsigned long)hsr);
+	timer_setup(&hsr->announce_timer, hsr_announce, 0);
+	timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0);
 
 	ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr);
 	hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec;
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 284a9b820df8..286ceb41ac0c 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -365,16 +365,14 @@ static struct hsr_port *get_late_port(struct hsr_priv *hsr,
 /* Remove stale sequence_nr records. Called by timer every
  * HSR_LIFE_CHECK_INTERVAL (two seconds or so).
  */
-void hsr_prune_nodes(unsigned long data)
+void hsr_prune_nodes(struct timer_list *t)
 {
-	struct hsr_priv *hsr;
+	struct hsr_priv *hsr = from_timer(hsr, t, prune_timer);
 	struct hsr_node *node;
 	struct hsr_port *port;
 	unsigned long timestamp;
 	unsigned long time_a, time_b;
 
-	hsr = (struct hsr_priv *) data;
-
 	rcu_read_lock();
 	list_for_each_entry_rcu(node, &hsr->node_db, mac_list) {
 		/* Shorthand */
diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h
index 4e04f0e868e9..370b45998121 100644
--- a/net/hsr/hsr_framereg.h
+++ b/net/hsr/hsr_framereg.h
@@ -33,7 +33,7 @@ void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port,
 int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node,
 			   u16 sequence_nr);
 
-void hsr_prune_nodes(unsigned long data);
+void hsr_prune_nodes(struct timer_list *t);
 
 int hsr_create_self_node(struct list_head *self_node_db,
 			 unsigned char addr_a[ETH_ALEN],
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index f85b08baff16..85bf86ad6b18 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -80,12 +80,13 @@ static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
 	fq->daddr = *arg->dst;
 }
 
-static void lowpan_frag_expire(unsigned long data)
+static void lowpan_frag_expire(struct timer_list *t)
 {
+	struct inet_frag_queue *frag = from_timer(frag, t, timer);
 	struct frag_queue *fq;
 	struct net *net;
 
-	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+	fq = container_of(frag, struct frag_queue, q);
 	net = container_of(fq->q.net, struct net, ieee802154_lowpan.frags);
 
 	spin_lock(&fq->q.lock);
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 6bde9e5a5503..96636e3b7aa9 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -89,7 +89,7 @@ int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info)
 	return genlmsg_reply(msg, info);
 }
 
-static const struct genl_ops ieee8021154_ops[] = {
+static const struct genl_ops ieee802154_ops[] = {
 	/* see nl-phy.c */
 	IEEE802154_DUMP(IEEE802154_LIST_PHY, ieee802154_list_phy,
 			ieee802154_dump_phy),
@@ -137,8 +137,8 @@ struct genl_family nl802154_family __ro_after_init = {
 	.version	= 1,
 	.maxattr	= IEEE802154_ATTR_MAX,
 	.module		= THIS_MODULE,
-	.ops		= ieee8021154_ops,
-	.n_ops		= ARRAY_SIZE(ieee8021154_ops),
+	.ops		= ieee802154_ops,
+	.n_ops		= ARRAY_SIZE(ieee802154_ops),
 	.mcgrps		= ieee802154_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(ieee802154_mcgrps),
 };
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e31108e5ef79..ce4aa827be05 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -195,7 +195,7 @@ int inet_listen(struct socket *sock, int backlog)
 {
 	struct sock *sk = sock->sk;
 	unsigned char old_state;
-	int err;
+	int err, tcp_fastopen;
 
 	lock_sock(sk);
 
@@ -217,11 +217,12 @@ int inet_listen(struct socket *sock, int backlog)
 		 * because the socket was in TCP_LISTEN state previously but
 		 * was shutdown() rather than close().
 		 */
-		if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
-		    (sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+		tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+		if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
+		    (tcp_fastopen & TFO_SERVER_ENABLE) &&
 		    !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) {
 			fastopen_queue_tune(sk, backlog);
-			tcp_fastopen_init_key_once(true);
+			tcp_fastopen_init_key_once(sock_net(sk));
 		}
 
 		err = inet_csk_listen_start(sk, backlog);
@@ -826,6 +827,7 @@ int inet_shutdown(struct socket *sock, int how)
 		err = -ENOTCONN;
 		/* Hack to wake up other listeners, who can poll for
 		   POLLHUP, even on eg. unconnected UDP sockets -- RR */
+		/* fall through */
 	default:
 		sk->sk_shutdown |= how;
 		if (sk->sk_prot->shutdown)
@@ -839,7 +841,7 @@ int inet_shutdown(struct socket *sock, int how)
 	case TCP_LISTEN:
 		if (!(how & RCV_SHUTDOWN))
 			break;
-		/* Fall through */
+		/* fall through */
 	case TCP_SYN_SENT:
 		err = sk->sk_prot->disconnect(sk, O_NONBLOCK);
 		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 7c45b8896709..a8d7c5a9fb05 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1180,6 +1180,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	case SIOCSARP:
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
+		/* fall through */
 	case SIOCGARP:
 		err = copy_from_user(&r, arg, sizeof(struct arpreq));
 		if (err)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index d7adc0616599..a4573bccd6da 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -137,22 +137,12 @@ static void inet_hash_remove(struct in_ifaddr *ifa)
  */
 struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
 {
-	u32 hash = inet_addr_hash(net, addr);
 	struct net_device *result = NULL;
 	struct in_ifaddr *ifa;
 
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) {
-		if (ifa->ifa_local == addr) {
-			struct net_device *dev = ifa->ifa_dev->dev;
-
-			if (!net_eq(dev_net(dev), net))
-				continue;
-			result = dev;
-			break;
-		}
-	}
-	if (!result) {
+	ifa = inet_lookup_ifaddr_rcu(net, addr);
+	if (!ifa) {
 		struct flowi4 fl4 = { .daddr = addr };
 		struct fib_result res = { 0 };
 		struct fib_table *local;
@@ -165,6 +155,8 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
 		    !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) &&
 		    res.type == RTN_LOCAL)
 			result = FIB_RES_DEV(res);
+	} else {
+		result = ifa->ifa_dev->dev;
 	}
 	if (result && devref)
 		dev_hold(result);
@@ -173,6 +165,20 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
 }
 EXPORT_SYMBOL(__ip_dev_find);
 
+/* called under RCU lock */
+struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr)
+{
+	u32 hash = inet_addr_hash(net, addr);
+	struct in_ifaddr *ifa;
+
+	hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash)
+		if (ifa->ifa_local == addr &&
+		    net_eq(dev_net(ifa->ifa_dev->dev), net))
+			return ifa;
+
+	return NULL;
+}
+
 static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);
 
 static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
@@ -438,7 +444,7 @@ static void check_lifetime(struct work_struct *work);
 static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime);
 
 static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
-			     u32 portid)
+			     u32 portid, struct netlink_ext_ack *extack)
 {
 	struct in_device *in_dev = ifa->ifa_dev;
 	struct in_ifaddr *ifa1, **ifap, **last_primary;
@@ -483,6 +489,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 	 */
 	ivi.ivi_addr = ifa->ifa_address;
 	ivi.ivi_dev = ifa->ifa_dev;
+	ivi.extack = extack;
 	ret = blocking_notifier_call_chain(&inetaddr_validator_chain,
 					   NETDEV_UP, &ivi);
 	ret = notifier_to_errno(ret);
@@ -515,7 +522,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 
 static int inet_insert_ifa(struct in_ifaddr *ifa)
 {
-	return __inet_insert_ifa(ifa, NULL, 0);
+	return __inet_insert_ifa(ifa, NULL, 0, NULL);
 }
 
 static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
@@ -896,7 +903,8 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 				return ret;
 			}
 		}
-		return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid);
+		return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid,
+					 extack);
 	} else {
 		inet_free_ifa(ifa);
 
@@ -1516,6 +1524,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
 		if (inetdev_valid_mtu(dev->mtu))
 			break;
 		/* disable IP when MTU is not enough */
+		/* fall through */
 	case NETDEV_UNREGISTER:
 		inetdev_destroy(in_dev);
 		break;
@@ -1751,7 +1760,7 @@ 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_rtnl(dev))
+	if (dev && !__in_dev_get_rcu(dev))
 		return -EAFNOSUPPORT;
 
 	err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy, NULL);
@@ -1775,7 +1784,7 @@ 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 in_device *in_dev = __in_dev_get_rtnl(dev);
+	struct in_device *in_dev = __in_dev_get_rcu(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 37819ab4cc74..f52d27a422c3 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -73,6 +73,11 @@ fail:
 	fib_free_table(main_table);
 	return -ENOMEM;
 }
+
+static bool fib4_has_custom_rules(struct net *net)
+{
+	return false;
+}
 #else
 
 struct fib_table *fib_new_table(struct net *net, u32 id)
@@ -128,6 +133,11 @@ struct fib_table *fib_get_table(struct net *net, u32 id)
 	}
 	return NULL;
 }
+
+static bool fib4_has_custom_rules(struct net *net)
+{
+	return net->ipv4.fib_has_custom_rules;
+}
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
 
 static void fib_replace_table(struct net *net, struct fib_table *old,
@@ -345,9 +355,6 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	if (res.type != RTN_UNICAST &&
 	    (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
 		goto e_inval;
-	if (!rpf && !fib_num_tclassid_users(net) &&
-	    (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev)))
-		goto last_resort;
 	fib_combine_itag(itag, &res);
 	dev_match = false;
 
@@ -402,13 +409,28 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 			struct in_device *idev, u32 *itag)
 {
 	int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev);
+	struct net *net = dev_net(dev);
 
-	if (!r && !fib_num_tclassid_users(dev_net(dev)) &&
-	    IN_DEV_ACCEPT_LOCAL(idev) &&
+	if (!r && !fib_num_tclassid_users(net) &&
 	    (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) {
+		if (IN_DEV_ACCEPT_LOCAL(idev))
+			goto ok;
+		/* with custom local routes in place, checking local addresses
+		 * only will be too optimistic, with custom rules, checking
+		 * local addresses only can be too strict, e.g. due to vrf
+		 */
+		if (net->ipv4.fib_has_custom_local_routes ||
+		    fib4_has_custom_rules(net))
+			goto full_check;
+		if (inet_lookup_ifaddr_rcu(net, src))
+			return -EINVAL;
+
+ok:
 		*itag = 0;
 		return 0;
 	}
+
+full_check:
 	return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag);
 }
 
@@ -759,6 +781,8 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	err = fib_table_insert(net, tb, &cfg, extack);
+	if (!err && cfg.fc_type == RTN_LOCAL)
+		net->ipv4.fib_has_custom_local_routes = true;
 errout:
 	return err;
 }
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 01ed22139ac2..589caaa90613 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -601,17 +601,9 @@ static void fib_rebalance(struct fib_info *fi)
 		atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
 	} endfor_nexthops(fi);
 }
-
-static inline void fib_add_weight(struct fib_info *fi,
-				  const struct fib_nh *nh)
-{
-	fi->fib_weight += nh->nh_weight;
-}
-
 #else /* CONFIG_IP_ROUTE_MULTIPATH */
 
 #define fib_rebalance(fi) do { } while (0)
-#define fib_add_weight(fi, nh) do { } while (0)
 
 #endif /* CONFIG_IP_ROUTE_MULTIPATH */
 
@@ -774,8 +766,8 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
  *					|
  *					|-> {local prefix} (terminal node)
  */
-static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
-			struct fib_nh *nh, struct netlink_ext_ack *extack)
+static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
+			struct netlink_ext_ack *extack)
 {
 	int err = 0;
 	struct net *net;
@@ -1258,7 +1250,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 		int linkdown = 0;
 
 		change_nexthops(fi) {
-			err = fib_check_nh(cfg, fi, nexthop_nh, extack);
+			err = fib_check_nh(cfg, nexthop_nh, extack);
 			if (err != 0)
 				goto failure;
 			if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN)
@@ -1275,7 +1267,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 
 	change_nexthops(fi) {
 		fib_info_update_nh_saddr(net, nexthop_nh);
-		fib_add_weight(fi, nexthop_nh);
 	} endfor_nexthops(fi)
 
 	fib_rebalance(fi);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index c636650a6a70..5ddc4aefff12 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -87,32 +87,32 @@
 
 static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
 				   enum fib_event_type event_type, u32 dst,
-				   int dst_len, struct fib_info *fi,
-				   u8 tos, u8 type, u32 tb_id)
+				   int dst_len, struct fib_alias *fa)
 {
 	struct fib_entry_notifier_info info = {
 		.dst = dst,
 		.dst_len = dst_len,
-		.fi = fi,
-		.tos = tos,
-		.type = type,
-		.tb_id = tb_id,
+		.fi = fa->fa_info,
+		.tos = fa->fa_tos,
+		.type = fa->fa_type,
+		.tb_id = fa->tb_id,
 	};
 	return call_fib4_notifier(nb, net, event_type, &info.info);
 }
 
 static int call_fib_entry_notifiers(struct net *net,
 				    enum fib_event_type event_type, u32 dst,
-				    int dst_len, struct fib_info *fi,
-				    u8 tos, u8 type, u32 tb_id)
+				    int dst_len, struct fib_alias *fa,
+				    struct netlink_ext_ack *extack)
 {
 	struct fib_entry_notifier_info info = {
+		.info.extack = extack,
 		.dst = dst,
 		.dst_len = dst_len,
-		.fi = fi,
-		.tos = tos,
-		.type = type,
-		.tb_id = tb_id,
+		.fi = fa->fa_info,
+		.tos = fa->fa_tos,
+		.type = fa->fa_type,
+		.tb_id = fa->tb_id,
 	};
 	return call_fib4_notifiers(net, event_type, &info.info);
 }
@@ -1216,9 +1216,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 			new_fa->fa_default = -1;
 
 			call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE,
-						 key, plen, fi,
-						 new_fa->fa_tos, cfg->fc_type,
-						 tb->tb_id);
+						 key, plen, new_fa, extack);
 			rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen,
 				  tb->tb_id, &cfg->fc_nlinfo, nlflags);
 
@@ -1273,8 +1271,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 		tb->tb_num_default++;
 
 	rt_cache_flush(cfg->fc_nlinfo.nl_net);
-	call_fib_entry_notifiers(net, event, key, plen, fi, tos, cfg->fc_type,
-				 tb->tb_id);
+	call_fib_entry_notifiers(net, event, key, plen, new_fa, extack);
 	rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id,
 		  &cfg->fc_nlinfo, nlflags);
 succeeded:
@@ -1574,8 +1571,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
 		return -ESRCH;
 
 	call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, plen,
-				 fa_to_delete->fa_info, tos,
-				 fa_to_delete->fa_type, tb->tb_id);
+				 fa_to_delete, extack);
 	rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id,
 		  &cfg->fc_nlinfo, 0);
 
@@ -1892,9 +1888,8 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
 
 			call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL,
 						 n->key,
-						 KEYLENGTH - fa->fa_slen,
-						 fi, fa->fa_tos, fa->fa_type,
-						 tb->tb_id);
+						 KEYLENGTH - fa->fa_slen, fa,
+						 NULL);
 			hlist_del_rcu(&fa->fa_list);
 			fib_release_info(fa->fa_info);
 			alias_free_mem_rcu(fa);
@@ -1932,8 +1927,7 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l,
 			continue;
 
 		call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key,
-					KEYLENGTH - fa->fa_slen, fi, fa->fa_tos,
-					fa->fa_type, fa->tb_id);
+					KEYLENGTH - fa->fa_slen, fa);
 	}
 }
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 681e33998e03..1617604c9284 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -782,7 +782,7 @@ static bool icmp_tag_validation(int proto)
 }
 
 /*
- *	Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and
+ *	Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEEDED, ICMP_QUENCH, and
  *	ICMP_PARAMETERPROB.
  */
 
@@ -810,7 +810,8 @@ static bool icmp_unreach(struct sk_buff *skb)
 	if (iph->ihl < 5) /* Mangled header, drop. */
 		goto out_err;
 
-	if (icmph->type == ICMP_DEST_UNREACH) {
+	switch (icmph->type) {
+	case ICMP_DEST_UNREACH:
 		switch (icmph->code & 15) {
 		case ICMP_NET_UNREACH:
 		case ICMP_HOST_UNREACH:
@@ -846,8 +847,16 @@ static bool icmp_unreach(struct sk_buff *skb)
 		}
 		if (icmph->code > NR_ICMP_UNREACH)
 			goto out;
-	} else if (icmph->type == ICMP_PARAMETERPROB)
+		break;
+	case ICMP_PARAMETERPROB:
 		info = ntohl(icmph->un.gateway) >> 24;
+		break;
+	case ICMP_TIME_EXCEEDED:
+		__ICMP_INC_STATS(net, ICMP_MIB_INTIMEEXCDS);
+		if (icmph->code == ICMP_EXC_FRAGTIME)
+			goto out;
+		break;
+	}
 
 	/*
 	 *	Throw it at our lower layers
@@ -959,8 +968,9 @@ static bool icmp_timestamp(struct sk_buff *skb)
 	 */
 	icmp_param.data.times[1] = inet_current_timestamp();
 	icmp_param.data.times[2] = icmp_param.data.times[1];
-	if (skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4))
-		BUG();
+
+	BUG_ON(skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4));
+
 	icmp_param.data.icmph	   = *icmp_hdr(skb);
 	icmp_param.data.icmph.type = ICMP_TIMESTAMPREPLY;
 	icmp_param.data.icmph.code = 0;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b47a59cb3573..4ca46dc08e63 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -39,11 +39,11 @@ EXPORT_SYMBOL(inet_csk_timer_bug_msg);
  *                          IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
  *                          and 0.0.0.0 equals to 0.0.0.0 only
  */
-static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
-				const struct in6_addr *sk2_rcv_saddr6,
-				__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
-				bool sk1_ipv6only, bool sk2_ipv6only,
-				bool match_wildcard)
+static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
+				 const struct in6_addr *sk2_rcv_saddr6,
+				 __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
+				 bool sk1_ipv6only, bool sk2_ipv6only,
+				 bool match_wildcard)
 {
 	int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
 	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
@@ -52,29 +52,29 @@ static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 	if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) {
 		if (!sk2_ipv6only) {
 			if (sk1_rcv_saddr == sk2_rcv_saddr)
-				return 1;
+				return true;
 			if (!sk1_rcv_saddr || !sk2_rcv_saddr)
 				return match_wildcard;
 		}
-		return 0;
+		return false;
 	}
 
 	if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
-		return 1;
+		return true;
 
 	if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
 	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
-		return 1;
+		return true;
 
 	if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
 	    !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
-		return 1;
+		return true;
 
 	if (sk2_rcv_saddr6 &&
 	    ipv6_addr_equal(sk1_rcv_saddr6, sk2_rcv_saddr6))
-		return 1;
+		return true;
 
-	return 0;
+	return false;
 }
 #endif
 
@@ -82,20 +82,20 @@ static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
  * match_wildcard == false: addresses must be exactly the same, i.e.
  *                          0.0.0.0 only equals to 0.0.0.0
  */
-static int ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
-				bool sk2_ipv6only, bool match_wildcard)
+static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
+				 bool sk2_ipv6only, bool match_wildcard)
 {
 	if (!sk2_ipv6only) {
 		if (sk1_rcv_saddr == sk2_rcv_saddr)
-			return 1;
+			return true;
 		if (!sk1_rcv_saddr || !sk2_rcv_saddr)
 			return match_wildcard;
 	}
-	return 0;
+	return false;
 }
 
-int inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
-			 bool match_wildcard)
+bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
+			  bool match_wildcard)
 {
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == AF_INET6)
@@ -495,17 +495,15 @@ EXPORT_SYMBOL(inet_csk_accept);
  * to optimize.
  */
 void inet_csk_init_xmit_timers(struct sock *sk,
-			       void (*retransmit_handler)(unsigned long),
-			       void (*delack_handler)(unsigned long),
-			       void (*keepalive_handler)(unsigned long))
+			       void (*retransmit_handler)(struct timer_list *t),
+			       void (*delack_handler)(struct timer_list *t),
+			       void (*keepalive_handler)(struct timer_list *t))
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
-	setup_timer(&icsk->icsk_retransmit_timer, retransmit_handler,
-			(unsigned long)sk);
-	setup_timer(&icsk->icsk_delack_timer, delack_handler,
-			(unsigned long)sk);
-	setup_timer(&sk->sk_timer, keepalive_handler, (unsigned long)sk);
+	timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0);
+	timer_setup(&icsk->icsk_delack_timer, delack_handler, 0);
+	timer_setup(&sk->sk_timer, keepalive_handler, 0);
 	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
 }
 EXPORT_SYMBOL(inet_csk_init_xmit_timers);
@@ -676,9 +674,9 @@ void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req
 }
 EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put);
 
-static void reqsk_timer_handler(unsigned long data)
+static void reqsk_timer_handler(struct timer_list *t)
 {
-	struct request_sock *req = (struct request_sock *)data;
+	struct request_sock *req = from_timer(req, t, rsk_timer);
 	struct sock *sk_listener = req->rsk_listener;
 	struct net *net = sock_net(sk_listener);
 	struct inet_connection_sock *icsk = inet_csk(sk_listener);
@@ -749,8 +747,7 @@ static void reqsk_queue_hash_req(struct request_sock *req,
 	req->num_timeout = 0;
 	req->sk = NULL;
 
-	setup_pinned_timer(&req->rsk_timer, reqsk_timer_handler,
-			    (unsigned long)req);
+	timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
 	mod_timer(&req->rsk_timer, jiffies + timeout);
 
 	inet_ehash_insert(req_to_sk(req), NULL);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index af74d0433453..7f3ef5c287a1 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -147,7 +147,7 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
 	spin_unlock(&hb->chain_lock);
 
 	hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
-		f->frag_expire((unsigned long) fq);
+		f->frag_expire(&fq->timer);
 
 	return evicted;
 }
@@ -366,7 +366,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 	f->constructor(q, arg);
 	add_frag_mem_limit(nf, f->qsize);
 
-	setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
+	timer_setup(&q->timer, f->frag_expire, 0);
 	spin_lock_init(&q->lock);
 	refcount_set(&q->refcnt, 1);
 
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 5b039159e67a..a4bab81f1462 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -142,9 +142,9 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
 
-static void tw_timer_handler(unsigned long data)
+static void tw_timer_handler(struct timer_list *t)
 {
-	struct inet_timewait_sock *tw = (struct inet_timewait_sock *)data;
+	struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer);
 
 	if (tw->tw_kill)
 		__NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED);
@@ -188,8 +188,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
 		tw->tw_prot	    = sk->sk_prot_creator;
 		atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie));
 		twsk_net_set(tw, sock_net(sk));
-		setup_pinned_timer(&tw->tw_timer, tw_timer_handler,
-				   (unsigned long)tw);
+		timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED);
 		/*
 		 * Because we use RCU lookups, we should not set tw_refcnt
 		 * to a non null value before everything is setup for this
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index b20c8ac64081..914d56928578 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -284,14 +284,17 @@ EXPORT_SYMBOL(inet_peer_xrlim_allow);
 
 void inetpeer_invalidate_tree(struct inet_peer_base *base)
 {
-	struct inet_peer *p, *n;
+	struct rb_node *p = rb_first(&base->rb_root);
 
-	rbtree_postorder_for_each_entry_safe(p, n, &base->rb_root, rb_node) {
-		inet_putpeer(p);
+	while (p) {
+		struct inet_peer *peer = rb_entry(p, struct inet_peer, rb_node);
+
+		p = rb_next(p);
+		rb_erase(&peer->rb_node, &base->rb_root);
+		inet_putpeer(peer);
 		cond_resched();
 	}
 
-	base->rb_root = RB_ROOT;
 	base->total = 0;
 }
 EXPORT_SYMBOL(inetpeer_invalidate_tree);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index df8fe0503de0..bbf1b94942c0 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -191,12 +191,13 @@ static bool frag_expire_skip_icmp(u32 user)
 /*
  * Oops, a fragment queue timed out.  Kill it and send an ICMP reply.
  */
-static void ip_expire(unsigned long arg)
+static void ip_expire(struct timer_list *t)
 {
+	struct inet_frag_queue *frag = from_timer(frag, t, timer);
 	struct ipq *qp;
 	struct net *net;
 
-	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
+	qp = container_of(frag, struct ipq, q);
 	net = container_of(qp->q.net, struct net, ipv4.frags);
 
 	rcu_read_lock();
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 467e44d7587d..c105a315b1a3 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -579,8 +579,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
 	if (gre_handle_offloads(skb, false))
 		goto err_free_rt;
 
-	if (skb->len > dev->mtu) {
-		pskb_trim(skb, dev->mtu);
+	if (skb->len > dev->mtu + dev->hard_header_len) {
+		pskb_trim(skb, dev->mtu + dev->hard_header_len);
 		truncate = true;
 	}
 
@@ -731,8 +731,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 	if (skb_cow_head(skb, dev->needed_headroom))
 		goto free_skb;
 
-	if (skb->len - dev->hard_header_len > dev->mtu) {
-		pskb_trim(skb, dev->mtu);
+	if (skb->len > dev->mtu + dev->hard_header_len) {
+		pskb_trim(skb, dev->mtu + dev->hard_header_len);
 		truncate = true;
 	}
 
@@ -1011,15 +1011,14 @@ static int __net_init ipgre_init_net(struct net *net)
 	return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL);
 }
 
-static void __net_exit ipgre_exit_net(struct net *net)
+static void __net_exit ipgre_exit_batch_net(struct list_head *list_net)
 {
-	struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id);
-	ip_tunnel_delete_net(itn, &ipgre_link_ops);
+	ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops);
 }
 
 static struct pernet_operations ipgre_net_ops = {
 	.init = ipgre_init_net,
-	.exit = ipgre_exit_net,
+	.exit_batch = ipgre_exit_batch_net,
 	.id   = &ipgre_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
@@ -1542,15 +1541,14 @@ static int __net_init ipgre_tap_init_net(struct net *net)
 	return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0");
 }
 
-static void __net_exit ipgre_tap_exit_net(struct net *net)
+static void __net_exit ipgre_tap_exit_batch_net(struct list_head *list_net)
 {
-	struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id);
-	ip_tunnel_delete_net(itn, &ipgre_tap_ops);
+	ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops);
 }
 
 static struct pernet_operations ipgre_tap_net_ops = {
 	.init = ipgre_tap_init_net,
-	.exit = ipgre_tap_exit_net,
+	.exit_batch = ipgre_tap_exit_batch_net,
 	.id   = &gre_tap_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
@@ -1561,16 +1559,14 @@ static int __net_init erspan_init_net(struct net *net)
 				  &erspan_link_ops, "erspan0");
 }
 
-static void __net_exit erspan_exit_net(struct net *net)
+static void __net_exit erspan_exit_batch_net(struct list_head *net_list)
 {
-	struct ip_tunnel_net *itn = net_generic(net, erspan_net_id);
-
-	ip_tunnel_delete_net(itn, &erspan_link_ops);
+	ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops);
 }
 
 static struct pernet_operations erspan_net_ops = {
 	.init = erspan_init_net,
-	.exit = erspan_exit_net,
+	.exit_batch = erspan_exit_batch_net,
 	.id   = &erspan_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index e9805ad664ac..fe6fee728ce4 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1061,16 +1061,22 @@ static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
 	}
 }
 
-void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
+void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id,
+			   struct rtnl_link_ops *ops)
 {
+	struct ip_tunnel_net *itn;
+	struct net *net;
 	LIST_HEAD(list);
 
 	rtnl_lock();
-	ip_tunnel_destroy(itn, &list, ops);
+	list_for_each_entry(net, net_list, exit_list) {
+		itn = net_generic(net, id);
+		ip_tunnel_destroy(itn, &list, ops);
+	}
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
-EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);
+EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets);
 
 int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 		      struct ip_tunnel_parm *p, __u32 fwmark)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 89453cf62158..949f432a5f04 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -198,15 +198,6 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-	if (tunnel->err_count > 0) {
-		if (time_before(jiffies,
-				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
-			tunnel->err_count--;
-			dst_link_failure(skb);
-		} else
-			tunnel->err_count = 0;
-	}
-
 	mtu = dst_mtu(dst);
 	if (skb->len > mtu) {
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
@@ -453,15 +444,14 @@ static int __net_init vti_init_net(struct net *net)
 	return 0;
 }
 
-static void __net_exit vti_exit_net(struct net *net)
+static void __net_exit vti_exit_batch_net(struct list_head *list_net)
 {
-	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
-	ip_tunnel_delete_net(itn, &vti_link_ops);
+	ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops);
 }
 
 static struct pernet_operations vti_net_ops = {
 	.init = vti_init_net,
-	.exit = vti_exit_net,
+	.exit_batch = vti_exit_batch_net,
 	.id   = &vti_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index cdd627355ed1..c891235b4966 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -659,15 +659,14 @@ static int __net_init ipip_init_net(struct net *net)
 	return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0");
 }
 
-static void __net_exit ipip_exit_net(struct net *net)
+static void __net_exit ipip_exit_batch_net(struct list_head *list_net)
 {
-	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
-	ip_tunnel_delete_net(itn, &ipip_link_ops);
+	ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops);
 }
 
 static struct pernet_operations ipip_net_ops = {
 	.init = ipip_init_net,
-	.exit = ipip_exit_net,
+	.exit_batch = ipip_exit_batch_net,
 	.id   = &ipip_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c9b3e6e069ae..40a43ad294cb 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -67,6 +67,7 @@
 #include <net/fib_rules.h>
 #include <linux/netconf.h>
 #include <net/nexthop.h>
+#include <net/switchdev.h>
 
 struct ipmr_rule {
 	struct fib_rule		common;
@@ -264,6 +265,22 @@ static void __net_exit ipmr_rules_exit(struct net *net)
 	fib_rules_unregister(net->ipv4.mr_rules_ops);
 	rtnl_unlock();
 }
+
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+	return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR);
+}
+
+static unsigned int ipmr_rules_seq_read(struct net *net)
+{
+	return fib_rules_seq_read(net, RTNL_FAMILY_IPMR);
+}
+
+bool ipmr_rule_default(const struct fib_rule *rule)
+{
+	return fib_rule_matchall(rule) && rule->table == RT_TABLE_DEFAULT;
+}
+EXPORT_SYMBOL(ipmr_rule_default);
 #else
 #define ipmr_for_each_table(mrt, net) \
 	for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
@@ -298,6 +315,22 @@ static void __net_exit ipmr_rules_exit(struct net *net)
 	net->ipv4.mrt = NULL;
 	rtnl_unlock();
 }
+
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+	return 0;
+}
+
+static unsigned int ipmr_rules_seq_read(struct net *net)
+{
+	return 0;
+}
+
+bool ipmr_rule_default(const struct fib_rule *rule)
+{
+	return true;
+}
+EXPORT_SYMBOL(ipmr_rule_default);
 #endif
 
 static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg,
@@ -587,6 +620,82 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 }
 #endif
 
+static int call_ipmr_vif_entry_notifier(struct notifier_block *nb,
+					struct net *net,
+					enum fib_event_type event_type,
+					struct vif_device *vif,
+					vifi_t vif_index, u32 tb_id)
+{
+	struct vif_entry_notifier_info info = {
+		.info = {
+			.family = RTNL_FAMILY_IPMR,
+			.net = net,
+		},
+		.dev = vif->dev,
+		.vif_index = vif_index,
+		.vif_flags = vif->flags,
+		.tb_id = tb_id,
+	};
+
+	return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static int call_ipmr_vif_entry_notifiers(struct net *net,
+					 enum fib_event_type event_type,
+					 struct vif_device *vif,
+					 vifi_t vif_index, u32 tb_id)
+{
+	struct vif_entry_notifier_info info = {
+		.info = {
+			.family = RTNL_FAMILY_IPMR,
+			.net = net,
+		},
+		.dev = vif->dev,
+		.vif_index = vif_index,
+		.vif_flags = vif->flags,
+		.tb_id = tb_id,
+	};
+
+	ASSERT_RTNL();
+	net->ipv4.ipmr_seq++;
+	return call_fib_notifiers(net, event_type, &info.info);
+}
+
+static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb,
+					struct net *net,
+					enum fib_event_type event_type,
+					struct mfc_cache *mfc, u32 tb_id)
+{
+	struct mfc_entry_notifier_info info = {
+		.info = {
+			.family = RTNL_FAMILY_IPMR,
+			.net = net,
+		},
+		.mfc = mfc,
+		.tb_id = tb_id
+	};
+
+	return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static int call_ipmr_mfc_entry_notifiers(struct net *net,
+					 enum fib_event_type event_type,
+					 struct mfc_cache *mfc, u32 tb_id)
+{
+	struct mfc_entry_notifier_info info = {
+		.info = {
+			.family = RTNL_FAMILY_IPMR,
+			.net = net,
+		},
+		.mfc = mfc,
+		.tb_id = tb_id
+	};
+
+	ASSERT_RTNL();
+	net->ipv4.ipmr_seq++;
+	return call_fib_notifiers(net, event_type, &info.info);
+}
+
 /**
  *	vif_delete - Delete a VIF entry
  *	@notify: Set to 1, if the caller is a notifier_call
@@ -594,6 +703,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 		      struct list_head *head)
 {
+	struct net *net = read_pnet(&mrt->net);
 	struct vif_device *v;
 	struct net_device *dev;
 	struct in_device *in_dev;
@@ -603,6 +713,10 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 
 	v = &mrt->vif_table[vifi];
 
+	if (VIF_EXISTS(mrt, vifi))
+		call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_DEL, v, vifi,
+					      mrt->id);
+
 	write_lock_bh(&mrt_lock);
 	dev = v->dev;
 	v->dev = NULL;
@@ -652,10 +766,11 @@ static void ipmr_cache_free_rcu(struct rcu_head *head)
 	kmem_cache_free(mrt_cachep, c);
 }
 
-static inline void ipmr_cache_free(struct mfc_cache *c)
+void ipmr_cache_free(struct mfc_cache *c)
 {
 	call_rcu(&c->rcu, ipmr_cache_free_rcu);
 }
+EXPORT_SYMBOL(ipmr_cache_free);
 
 /* Destroy an unresolved cache entry, killing queued skbs
  * and reporting error to netlink readers.
@@ -754,6 +869,9 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 		   struct vifctl *vifc, int mrtsock)
 {
 	int vifi = vifc->vifc_vifi;
+	struct switchdev_attr attr = {
+		.id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
+	};
 	struct vif_device *v = &mrt->vif_table[vifi];
 	struct net_device *dev;
 	struct in_device *in_dev;
@@ -828,6 +946,13 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 
 	/* Fill in the VIF structures */
 
+	attr.orig_dev = dev;
+	if (!switchdev_port_attr_get(dev, &attr)) {
+		memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len);
+		v->dev_parent_id.id_len = attr.u.ppid.id_len;
+	} else {
+		v->dev_parent_id.id_len = 0;
+	}
 	v->rate_limit = vifc->vifc_rate_limit;
 	v->local = vifc->vifc_lcl_addr.s_addr;
 	v->remote = vifc->vifc_rmt_addr.s_addr;
@@ -851,6 +976,7 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 	if (vifi+1 > mrt->maxvif)
 		mrt->maxvif = vifi+1;
 	write_unlock_bh(&mrt_lock);
+	call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, vifi, mrt->id);
 	return 0;
 }
 
@@ -949,6 +1075,7 @@ static struct mfc_cache *ipmr_cache_alloc(void)
 	if (c) {
 		c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 		c->mfc_un.res.minvif = MAXVIFS;
+		refcount_set(&c->mfc_un.res.refcount, 1);
 	}
 	return c;
 }
@@ -1150,6 +1277,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi,
 
 static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
 {
+	struct net *net = read_pnet(&mrt->net);
 	struct mfc_cache *c;
 
 	/* The entries are added/deleted only under RTNL */
@@ -1161,8 +1289,9 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
 		return -ENOENT;
 	rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
 	list_del_rcu(&c->list);
+	call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id);
 	mroute_netlink_event(mrt, c, RTM_DELROUTE);
-	ipmr_cache_free(c);
+	ipmr_cache_put(c);
 
 	return 0;
 }
@@ -1189,6 +1318,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 		if (!mrtsock)
 			c->mfc_flags |= MFC_STATIC;
 		write_unlock_bh(&mrt_lock);
+		call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c,
+					      mrt->id);
 		mroute_netlink_event(mrt, c, RTM_NEWROUTE);
 		return 0;
 	}
@@ -1238,6 +1369,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 		ipmr_cache_resolve(net, mrt, uc, c);
 		ipmr_cache_free(uc);
 	}
+	call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id);
 	mroute_netlink_event(mrt, c, RTM_NEWROUTE);
 	return 0;
 }
@@ -1245,6 +1377,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 /* Close the multicast socket, and clear the vif tables etc */
 static void mroute_clean_tables(struct mr_table *mrt, bool all)
 {
+	struct net *net = read_pnet(&mrt->net);
 	struct mfc_cache *c, *tmp;
 	LIST_HEAD(list);
 	int i;
@@ -1263,8 +1396,10 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
 			continue;
 		rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
 		list_del_rcu(&c->list);
+		call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c,
+					      mrt->id);
 		mroute_netlink_event(mrt, c, RTM_DELROUTE);
-		ipmr_cache_free(c);
+		ipmr_cache_put(c);
 	}
 
 	if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
@@ -1393,6 +1528,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 	case MRT_ADD_MFC:
 	case MRT_DEL_MFC:
 		parent = -1;
+		/* fall through */
 	case MRT_ADD_MFC_PROXY:
 	case MRT_DEL_MFC_PROXY:
 		if (optlen != sizeof(mfc)) {
@@ -1724,10 +1860,33 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk,
 	return dst_output(net, sk, skb);
 }
 
+#ifdef CONFIG_NET_SWITCHDEV
+static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt,
+				   int in_vifi, int out_vifi)
+{
+	struct vif_device *out_vif = &mrt->vif_table[out_vifi];
+	struct vif_device *in_vif = &mrt->vif_table[in_vifi];
+
+	if (!skb->offload_mr_fwd_mark)
+		return false;
+	if (!out_vif->dev_parent_id.id_len || !in_vif->dev_parent_id.id_len)
+		return false;
+	return netdev_phys_item_id_same(&out_vif->dev_parent_id,
+					&in_vif->dev_parent_id);
+}
+#else
+static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt,
+				   int in_vifi, int out_vifi)
+{
+	return false;
+}
+#endif
+
 /* Processing handlers for ipmr_forward */
 
 static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
-			    struct sk_buff *skb, struct mfc_cache *c, int vifi)
+			    int in_vifi, struct sk_buff *skb,
+			    struct mfc_cache *c, int vifi)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct vif_device *vif = &mrt->vif_table[vifi];
@@ -1748,6 +1907,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 		goto out_free;
 	}
 
+	if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi))
+		goto out_free;
+
 	if (vif->flags & VIFF_TUNNEL) {
 		rt = ip_route_output_ports(net, &fl4, NULL,
 					   vif->remote, vif->local,
@@ -1925,8 +2087,8 @@ forward:
 				struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 
 				if (skb2)
-					ipmr_queue_xmit(net, mrt, skb2, cache,
-							psend);
+					ipmr_queue_xmit(net, mrt, true_vifi,
+							skb2, cache, psend);
 			}
 			psend = ct;
 		}
@@ -1937,9 +2099,10 @@ last_forward:
 			struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 
 			if (skb2)
-				ipmr_queue_xmit(net, mrt, skb2, cache, psend);
+				ipmr_queue_xmit(net, mrt, true_vifi, skb2,
+						cache, psend);
 		} else {
-			ipmr_queue_xmit(net, mrt, skb, cache, psend);
+			ipmr_queue_xmit(net, mrt, true_vifi, skb, cache, psend);
 			return;
 		}
 	}
@@ -2156,6 +2319,9 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 	    nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0)
 		return -EMSGSIZE;
 
+	if (c->mfc_flags & MFC_OFFLOAD)
+		rtm->rtm_flags |= RTNH_F_OFFLOAD;
+
 	if (!(mp_attr = nla_nest_start(skb, RTA_MULTIPATH)))
 		return -EMSGSIZE;
 
@@ -3048,14 +3214,87 @@ static const struct net_protocol pim_protocol = {
 };
 #endif
 
+static unsigned int ipmr_seq_read(struct net *net)
+{
+	ASSERT_RTNL();
+
+	return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net);
+}
+
+static int ipmr_dump(struct net *net, struct notifier_block *nb)
+{
+	struct mr_table *mrt;
+	int err;
+
+	err = ipmr_rules_dump(net, nb);
+	if (err)
+		return err;
+
+	ipmr_for_each_table(mrt, net) {
+		struct vif_device *v = &mrt->vif_table[0];
+		struct mfc_cache *mfc;
+		int vifi;
+
+		/* Notifiy on table VIF entries */
+		read_lock(&mrt_lock);
+		for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) {
+			if (!v->dev)
+				continue;
+
+			call_ipmr_vif_entry_notifier(nb, net, FIB_EVENT_VIF_ADD,
+						     v, vifi, mrt->id);
+		}
+		read_unlock(&mrt_lock);
+
+		/* Notify on table MFC entries */
+		list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
+			call_ipmr_mfc_entry_notifier(nb, net,
+						     FIB_EVENT_ENTRY_ADD, mfc,
+						     mrt->id);
+	}
+
+	return 0;
+}
+
+static const struct fib_notifier_ops ipmr_notifier_ops_template = {
+	.family		= RTNL_FAMILY_IPMR,
+	.fib_seq_read	= ipmr_seq_read,
+	.fib_dump	= ipmr_dump,
+	.owner		= THIS_MODULE,
+};
+
+static int __net_init ipmr_notifier_init(struct net *net)
+{
+	struct fib_notifier_ops *ops;
+
+	net->ipv4.ipmr_seq = 0;
+
+	ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+	net->ipv4.ipmr_notifier_ops = ops;
+
+	return 0;
+}
+
+static void __net_exit ipmr_notifier_exit(struct net *net)
+{
+	fib_notifier_ops_unregister(net->ipv4.ipmr_notifier_ops);
+	net->ipv4.ipmr_notifier_ops = NULL;
+}
+
 /* Setup for IP multicast routing */
 static int __net_init ipmr_net_init(struct net *net)
 {
 	int err;
 
+	err = ipmr_notifier_init(net);
+	if (err)
+		goto ipmr_notifier_fail;
+
 	err = ipmr_rules_init(net);
 	if (err < 0)
-		goto fail;
+		goto ipmr_rules_fail;
 
 #ifdef CONFIG_PROC_FS
 	err = -ENOMEM;
@@ -3072,7 +3311,9 @@ proc_cache_fail:
 proc_vif_fail:
 	ipmr_rules_exit(net);
 #endif
-fail:
+ipmr_rules_fail:
+	ipmr_notifier_exit(net);
+ipmr_notifier_fail:
 	return err;
 }
 
@@ -3082,6 +3323,7 @@ static void __net_exit ipmr_net_exit(struct net *net)
 	remove_proc_entry("ip_mr_cache", net->proc_net);
 	remove_proc_entry("ip_mr_vif", net->proc_net);
 #endif
+	ipmr_notifier_exit(net);
 	ipmr_rules_exit(net);
 }
 
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index a0f37b208268..0443ca4120b0 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -276,7 +276,8 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
 			else
 				return NF_ACCEPT;
 		}
-		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
+		/* Only ICMPs can be IP_CT_IS_REPLY: */
+		/* fall through */
 	case IP_CT_NEW:
 		/* Seen it before?  This can happen for loopback, retrans,
 		 * or local packets.
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3d9f1c2f81c5..bc40bd411196 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1250,7 +1250,7 @@ static void set_class_tag(struct rtable *rt, u32 tag)
 static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
 {
 	unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr);
-	unsigned int advmss = max_t(unsigned int, dst->dev->mtu - header_size,
+	unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
 				    ip_rt_min_advmss);
 
 	return min(advmss, IPV4_MAX_PMTU - header_size);
@@ -3038,7 +3038,6 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
 
 int __init ip_rt_init(void)
 {
-	int rc = 0;
 	int cpu;
 
 	ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
@@ -3095,7 +3094,7 @@ int __init ip_rt_init(void)
 #endif
 	register_pernet_subsys(&rt_genid_ops);
 	register_pernet_subsys(&ipv4_inetpeer_ops);
-	return rc;
+	return 0;
 }
 
 #ifdef CONFIG_SYSCTL
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 77cf32a80952..fda37f2862c9 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -385,7 +385,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	/* Try to redo what tcp_v4_send_synack did. */
 	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
 
-	tcp_select_initial_window(tcp_full_space(sk), req->mss,
+	tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
 				  &req->rsk_rcv_wnd, &req->rsk_window_clamp,
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(&rt->dst, RTAX_INITRWND));
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0989e739d098..a82b44038308 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -26,6 +26,7 @@
 #include <net/inet_frag.h>
 #include <net/ping.h>
 #include <net/protocol.h>
+#include <net/netevent.h>
 
 static int zero;
 static int one = 1;
@@ -252,10 +253,12 @@ static int proc_allowed_congestion_control(struct ctl_table *ctl,
 	return ret;
 }
 
-static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
+static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 				 void __user *buffer, size_t *lenp,
 				 loff_t *ppos)
 {
+	struct net *net = container_of(table->data, struct net,
+	    ipv4.sysctl_tcp_fastopen);
 	struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
 	struct tcp_fastopen_context *ctxt;
 	int ret;
@@ -266,7 +269,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
 		return -ENOMEM;
 
 	rcu_read_lock();
-	ctxt = rcu_dereference(tcp_fastopen_ctx);
+	ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
 	if (ctxt)
 		memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
 	else
@@ -283,12 +286,8 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
 			ret = -EINVAL;
 			goto bad_key;
 		}
-		/* Generate a dummy secret but don't publish it. This
-		 * is needed so we don't regenerate a new key on the
-		 * first invocation of tcp_fastopen_cookie_gen
-		 */
-		tcp_fastopen_init_key_once(false);
-		tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH);
+		tcp_fastopen_reset_cipher(net, NULL, user_key,
+					  TCP_FASTOPEN_KEY_LENGTH);
 	}
 
 bad_key:
@@ -359,11 +358,13 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table,
 					     void __user *buffer,
 					     size_t *lenp, loff_t *ppos)
 {
+	struct net *net = container_of(table->data, struct net,
+	    ipv4.sysctl_tcp_fastopen_blackhole_timeout);
 	int ret;
 
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (write && ret == 0)
-		tcp_fastopen_active_timeout_reset();
+		atomic_set(&net->ipv4.tfo_active_disable_times, 0);
 
 	return ret;
 }
@@ -386,15 +387,25 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
 	return ret;
 }
 
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write,
+					  void __user *buffer, size_t *lenp,
+					  loff_t *ppos)
+{
+	struct net *net = container_of(table->data, struct net,
+	    ipv4.sysctl_fib_multipath_hash_policy);
+	int ret;
+
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (write && ret == 0)
+		call_netevent_notifiers(NETEVENT_MULTIPATH_HASH_UPDATE, net);
+
+	return ret;
+}
+#endif
+
 static struct ctl_table ipv4_table[] = {
 	{
-		.procname	= "tcp_retrans_collapse",
-		.data		= &sysctl_tcp_retrans_collapse,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tcp_max_orphans",
 		.data		= &sysctl_tcp_max_orphans,
 		.maxlen		= sizeof(int),
@@ -402,48 +413,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
-		.procname	= "tcp_fastopen",
-		.data		= &sysctl_tcp_fastopen,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "tcp_fastopen_key",
-		.mode		= 0600,
-		.maxlen		= ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
-		.proc_handler	= proc_tcp_fastopen_key,
-	},
-	{
-		.procname	= "tcp_fastopen_blackhole_timeout_sec",
-		.data		= &sysctl_tcp_fastopen_blackhole_timeout,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_tfo_blackhole_detect_timeout,
-		.extra1		= &zero,
-	},
-	{
-		.procname	= "tcp_abort_on_overflow",
-		.data		= &sysctl_tcp_abort_on_overflow,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_stdurg",
-		.data		= &sysctl_tcp_stdurg,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_rfc1337",
-		.data		= &sysctl_tcp_rfc1337,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "inet_peer_threshold",
 		.data		= &inet_peer_threshold,
 		.maxlen		= sizeof(int),
@@ -465,34 +434,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
-		.procname	= "tcp_fack",
-		.data		= &sysctl_tcp_fack,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_recovery",
-		.data		= &sysctl_tcp_recovery,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "tcp_max_reordering",
-		.data		= &sysctl_tcp_max_reordering,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_dsack",
-		.data		= &sysctl_tcp_dsack,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tcp_mem",
 		.maxlen		= sizeof(sysctl_tcp_mem),
 		.data		= &sysctl_tcp_mem,
@@ -516,36 +457,6 @@ static struct ctl_table ipv4_table[] = {
 		.extra1		= &one,
 	},
 	{
-		.procname	= "tcp_app_win",
-		.data		= &sysctl_tcp_app_win,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_adv_win_scale",
-		.data		= &sysctl_tcp_adv_win_scale,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &tcp_adv_win_scale_min,
-		.extra2		= &tcp_adv_win_scale_max,
-	},
-	{
-		.procname	= "tcp_frto",
-		.data		= &sysctl_tcp_frto,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_min_rtt_wlen",
-		.data		= &sysctl_tcp_min_rtt_wlen,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tcp_low_latency",
 		.data		= &sysctl_tcp_low_latency,
 		.maxlen		= sizeof(int),
@@ -553,60 +464,11 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
-		.procname	= "tcp_no_metrics_save",
-		.data		= &sysctl_tcp_nometrics_save,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "tcp_moderate_rcvbuf",
-		.data		= &sysctl_tcp_moderate_rcvbuf,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "tcp_tso_win_divisor",
-		.data		= &sysctl_tcp_tso_win_divisor,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
 		.procname	= "tcp_congestion_control",
 		.mode		= 0644,
 		.maxlen		= TCP_CA_NAME_MAX,
 		.proc_handler	= proc_tcp_congestion_control,
 	},
-	{
-		.procname	= "tcp_workaround_signed_windows",
-		.data		= &sysctl_tcp_workaround_signed_windows,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_limit_output_bytes",
-		.data		= &sysctl_tcp_limit_output_bytes,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_challenge_ack_limit",
-		.data		= &sysctl_tcp_challenge_ack_limit,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
-		.procname	= "tcp_slow_start_after_idle",
-		.data		= &sysctl_tcp_slow_start_after_idle,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 #ifdef CONFIG_NETLABEL
 	{
 		.procname	= "cipso_cache_enable",
@@ -650,65 +512,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler   = proc_allowed_congestion_control,
 	},
 	{
-		.procname       = "tcp_thin_linear_timeouts",
-		.data           = &sysctl_tcp_thin_linear_timeouts,
-		.maxlen         = sizeof(int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec
-	},
-	{
-		.procname	= "tcp_early_retrans",
-		.data		= &sysctl_tcp_early_retrans,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &four,
-	},
-	{
-		.procname	= "tcp_min_tso_segs",
-		.data		= &sysctl_tcp_min_tso_segs,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
-		.extra2		= &gso_max_segs,
-	},
-	{
-		.procname	= "tcp_pacing_ss_ratio",
-		.data		= &sysctl_tcp_pacing_ss_ratio,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &thousand,
-	},
-	{
-		.procname	= "tcp_pacing_ca_ratio",
-		.data		= &sysctl_tcp_pacing_ca_ratio,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &thousand,
-	},
-	{
-		.procname	= "tcp_autocorking",
-		.data		= &sysctl_tcp_autocorking,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
-	},
-	{
-		.procname	= "tcp_invalid_ratelimit",
-		.data		= &sysctl_tcp_invalid_ratelimit,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_ms_jiffies,
-	},
-	{
 		.procname	= "tcp_available_ulp",
 		.maxlen		= TCP_ULP_BUF_MAX,
 		.mode		= 0444,
@@ -1086,6 +889,28 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "tcp_fastopen",
+		.data		= &init_net.ipv4.sysctl_tcp_fastopen,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_fastopen_key",
+		.mode		= 0600,
+		.data		= &init_net.ipv4.sysctl_tcp_fastopen,
+		.maxlen		= ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
+		.proc_handler	= proc_tcp_fastopen_key,
+	},
+	{
+		.procname	= "tcp_fastopen_blackhole_timeout_sec",
+		.data		= &init_net.ipv4.sysctl_tcp_fastopen_blackhole_timeout,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_tfo_blackhole_detect_timeout,
+		.extra1		= &zero,
+	},
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	{
 		.procname	= "fib_multipath_use_neigh",
@@ -1101,7 +926,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.data		= &init_net.ipv4.sysctl_fib_multipath_hash_policy,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_fib_multipath_hash_policy,
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
@@ -1145,6 +970,200 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "tcp_early_retrans",
+		.data		= &init_net.ipv4.sysctl_tcp_early_retrans,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &four,
+	},
+	{
+		.procname	= "tcp_recovery",
+		.data		= &init_net.ipv4.sysctl_tcp_recovery,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname       = "tcp_thin_linear_timeouts",
+		.data           = &init_net.ipv4.sysctl_tcp_thin_linear_timeouts,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec
+	},
+	{
+		.procname	= "tcp_slow_start_after_idle",
+		.data		= &init_net.ipv4.sysctl_tcp_slow_start_after_idle,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_retrans_collapse",
+		.data		= &init_net.ipv4.sysctl_tcp_retrans_collapse,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_stdurg",
+		.data		= &init_net.ipv4.sysctl_tcp_stdurg,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_rfc1337",
+		.data		= &init_net.ipv4.sysctl_tcp_rfc1337,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_abort_on_overflow",
+		.data		= &init_net.ipv4.sysctl_tcp_abort_on_overflow,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_fack",
+		.data		= &init_net.ipv4.sysctl_tcp_fack,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_max_reordering",
+		.data		= &init_net.ipv4.sysctl_tcp_max_reordering,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_dsack",
+		.data		= &init_net.ipv4.sysctl_tcp_dsack,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_app_win",
+		.data		= &init_net.ipv4.sysctl_tcp_app_win,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_adv_win_scale",
+		.data		= &init_net.ipv4.sysctl_tcp_adv_win_scale,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &tcp_adv_win_scale_min,
+		.extra2		= &tcp_adv_win_scale_max,
+	},
+	{
+		.procname	= "tcp_frto",
+		.data		= &init_net.ipv4.sysctl_tcp_frto,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_no_metrics_save",
+		.data		= &init_net.ipv4.sysctl_tcp_nometrics_save,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_moderate_rcvbuf",
+		.data		= &init_net.ipv4.sysctl_tcp_moderate_rcvbuf,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_tso_win_divisor",
+		.data		= &init_net.ipv4.sysctl_tcp_tso_win_divisor,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_workaround_signed_windows",
+		.data		= &init_net.ipv4.sysctl_tcp_workaround_signed_windows,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_limit_output_bytes",
+		.data		= &init_net.ipv4.sysctl_tcp_limit_output_bytes,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_challenge_ack_limit",
+		.data		= &init_net.ipv4.sysctl_tcp_challenge_ack_limit,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_min_tso_segs",
+		.data		= &init_net.ipv4.sysctl_tcp_min_tso_segs,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &gso_max_segs,
+	},
+	{
+		.procname	= "tcp_min_rtt_wlen",
+		.data		= &init_net.ipv4.sysctl_tcp_min_rtt_wlen,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "tcp_autocorking",
+		.data		= &init_net.ipv4.sysctl_tcp_autocorking,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{
+		.procname	= "tcp_invalid_ratelimit",
+		.data		= &init_net.ipv4.sysctl_tcp_invalid_ratelimit,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+	},
+	{
+		.procname	= "tcp_pacing_ss_ratio",
+		.data		= &init_net.ipv4.sysctl_tcp_pacing_ss_ratio,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &thousand,
+	},
+	{
+		.procname	= "tcp_pacing_ca_ratio",
+		.data		= &init_net.ipv4.sysctl_tcp_pacing_ca_ratio,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &thousand,
+	},
 	{ }
 };
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5091402720ab..a7a0f316eb86 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -270,6 +270,7 @@
 #include <linux/time.h>
 #include <linux/slab.h>
 #include <linux/errqueue.h>
+#include <linux/static_key.h>
 
 #include <net/icmp.h>
 #include <net/inet_common.h>
@@ -282,9 +283,7 @@
 #include <asm/ioctls.h>
 #include <net/busy_poll.h>
 
-int sysctl_tcp_min_tso_segs __read_mostly = 2;
-
-int sysctl_tcp_autocorking __read_mostly = 1;
+#include <trace/events/tcp.h>
 
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
@@ -300,6 +299,11 @@ EXPORT_SYMBOL(sysctl_tcp_wmem);
 atomic_long_t tcp_memory_allocated;	/* Current allocated memory. */
 EXPORT_SYMBOL(tcp_memory_allocated);
 
+#if IS_ENABLED(CONFIG_SMC)
+DEFINE_STATIC_KEY_FALSE(tcp_have_smc);
+EXPORT_SYMBOL(tcp_have_smc);
+#endif
+
 /*
  * Current number of TCP sockets.
  */
@@ -413,8 +417,10 @@ void tcp_init_sock(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	tp->out_of_order_queue = RB_ROOT;
+	sk->tcp_rtx_queue = RB_ROOT;
 	tcp_init_xmit_timers(sk);
 	INIT_LIST_HEAD(&tp->tsq_node);
+	INIT_LIST_HEAD(&tp->tsorted_sent_queue);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
@@ -456,8 +462,22 @@ void tcp_init_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(tcp_init_sock);
 
-static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb)
+void tcp_init_transfer(struct sock *sk, int bpf_op)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	tcp_mtup_init(sk);
+	icsk->icsk_af_ops->rebuild_header(sk);
+	tcp_init_metrics(sk);
+	tcp_call_bpf(sk, bpf_op);
+	tcp_init_congestion_control(sk);
+	tcp_init_buffer_space(sk);
+}
+
+static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
 {
+	struct sk_buff *skb = tcp_write_queue_tail(sk);
+
 	if (tsflags && skb) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 		struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
@@ -675,7 +695,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
 				int size_goal)
 {
 	return skb->len < size_goal &&
-	       sysctl_tcp_autocorking &&
+	       sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
 	       skb != tcp_write_queue_head(sk) &&
 	       refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
 }
@@ -686,10 +706,9 @@ static void tcp_push(struct sock *sk, int flags, int mss_now,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 
-	if (!tcp_send_head(sk))
-		return;
-
 	skb = tcp_write_queue_tail(sk);
+	if (!skb)
+		return;
 	if (!(flags & MSG_MORE) || forced_push(tp))
 		tcp_mark_push(tp, skb);
 
@@ -869,6 +888,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
 			 * available to the caller, no more, no less.
 			 */
 			skb->reserved_tailroom = skb->end - skb->tail - size;
+			INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
 			return skb;
 		}
 		__kfree_skb(skb);
@@ -948,14 +968,14 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 		int copy, i;
 		bool can_coalesce;
 
-		if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0 ||
+		if (!skb || (copy = size_goal - skb->len) <= 0 ||
 		    !tcp_skb_can_collapse_to(skb)) {
 new_segment:
 			if (!sk_stream_memory_free(sk))
 				goto wait_for_sndbuf;
 
 			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
-						  skb_queue_empty(&sk->sk_write_queue));
+					tcp_rtx_and_write_queues_empty(sk));
 			if (!skb)
 				goto wait_for_memory;
 
@@ -1027,7 +1047,7 @@ wait_for_memory:
 
 out:
 	if (copied) {
-		tcp_tx_timestamp(sk, sk->sk_tsflags, tcp_write_queue_tail(sk));
+		tcp_tx_timestamp(sk, sk->sk_tsflags);
 		if (!(flags & MSG_SENDPAGE_NOTLAST))
 			tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
 	}
@@ -1126,7 +1146,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	struct sockaddr *uaddr = msg->msg_name;
 	int err, flags;
 
-	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+	if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
 	    (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
 	     uaddr->sa_family == AF_UNSPEC))
 		return -EOPNOTSUPP;
@@ -1183,7 +1203,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 			goto out_err;
 		}
 
-		skb = tcp_send_head(sk) ? tcp_write_queue_tail(sk) : NULL;
+		skb = tcp_write_queue_tail(sk);
 		uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb));
 		if (!uarg) {
 			err = -ENOBUFS;
@@ -1259,7 +1279,7 @@ restart:
 		int max = size_goal;
 
 		skb = tcp_write_queue_tail(sk);
-		if (tcp_send_head(sk)) {
+		if (skb) {
 			if (skb->ip_summed == CHECKSUM_NONE)
 				max = mss_now;
 			copy = max - skb->len;
@@ -1279,7 +1299,7 @@ new_segment:
 				process_backlog = false;
 				goto restart;
 			}
-			first_skb = skb_queue_empty(&sk->sk_write_queue);
+			first_skb = tcp_rtx_and_write_queues_empty(sk);
 			skb = sk_stream_alloc_skb(sk,
 						  select_size(sk, sg, first_skb),
 						  sk->sk_allocation,
@@ -1404,7 +1424,7 @@ wait_for_memory:
 
 out:
 	if (copied) {
-		tcp_tx_timestamp(sk, sockc.tsflags, tcp_write_queue_tail(sk));
+		tcp_tx_timestamp(sk, sockc.tsflags);
 		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
 	}
 out_nopush:
@@ -1505,6 +1525,13 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
 
 	/* XXX -- need to support SO_PEEK_OFF */
 
+	skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
+		err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
+		if (err)
+			return err;
+		copied += skb->len;
+	}
+
 	skb_queue_walk(&sk->sk_write_queue, skb) {
 		err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
 		if (err)
@@ -2017,6 +2044,8 @@ void tcp_set_state(struct sock *sk, int state)
 {
 	int oldstate = sk->sk_state;
 
+	trace_tcp_set_state(sk, oldstate, state);
+
 	switch (state) {
 	case TCP_ESTABLISHED:
 		if (oldstate != TCP_ESTABLISHED)
@@ -2304,6 +2333,37 @@ static inline bool tcp_need_reset(int state)
 		TCPF_FIN_WAIT2 | TCPF_SYN_RECV);
 }
 
+static void tcp_rtx_queue_purge(struct sock *sk)
+{
+	struct rb_node *p = rb_first(&sk->tcp_rtx_queue);
+
+	while (p) {
+		struct sk_buff *skb = rb_to_skb(p);
+
+		p = rb_next(p);
+		/* Since we are deleting whole queue, no need to
+		 * list_del(&skb->tcp_tsorted_anchor)
+		 */
+		tcp_rtx_queue_unlink(skb, sk);
+		sk_wmem_free_skb(sk, skb);
+	}
+}
+
+void tcp_write_queue_purge(struct sock *sk)
+{
+	struct sk_buff *skb;
+
+	tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
+	while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
+		tcp_skb_tsorted_anchor_cleanup(skb);
+		sk_wmem_free_skb(sk, skb);
+	}
+	tcp_rtx_queue_purge(sk);
+	INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue);
+	sk_mem_reclaim(sk);
+	tcp_clear_all_retrans_hints(tcp_sk(sk));
+}
+
 int tcp_disconnect(struct sock *sk, int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
@@ -2362,7 +2422,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	 * issue in __tcp_select_window()
 	 */
 	icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
-	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
 	dst_release(sk->sk_rx_dst);
@@ -2454,7 +2513,7 @@ static int tcp_repair_options_est(struct sock *sk,
 				return -EINVAL;
 
 			tp->rx_opt.sack_ok |= TCP_SACK_SEEN;
-			if (sysctl_tcp_fack)
+			if (sock_net(sk)->ipv4.sysctl_tcp_fack)
 				tcp_enable_fack(tp);
 			break;
 		case TCPOPT_TIMESTAMP:
@@ -2518,6 +2577,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		release_sock(sk);
 		return err;
 	}
+	case TCP_FASTOPEN_KEY: {
+		__u8 key[TCP_FASTOPEN_KEY_LENGTH];
+
+		if (optlen != sizeof(key))
+			return -EINVAL;
+
+		if (copy_from_user(key, optval, optlen))
+			return -EFAULT;
+
+		return tcp_fastopen_reset_cipher(net, sk, key, sizeof(key));
+	}
 	default:
 		/* fallthru */
 		break;
@@ -2749,7 +2819,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_FASTOPEN:
 		if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
 		    TCPF_LISTEN))) {
-			tcp_fastopen_init_key_once(true);
+			tcp_fastopen_init_key_once(net);
 
 			fastopen_queue_tune(sk, val);
 		} else {
@@ -2759,7 +2829,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_FASTOPEN_CONNECT:
 		if (val > 1 || val < 0) {
 			err = -EINVAL;
-		} else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+		} else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
 			if (sk->sk_state == TCP_CLOSE)
 				tp->fastopen_connect = val;
 			else
@@ -2768,6 +2838,14 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 			err = -EOPNOTSUPP;
 		}
 		break;
+	case TCP_FASTOPEN_NO_COOKIE:
+		if (val > 1 || val < 0)
+			err = -EINVAL;
+		else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
+			err = -EINVAL;
+		else
+			tp->fastopen_no_cookie = val;
+		break;
 	case TCP_TIMESTAMP:
 		if (!tp->repair)
 			err = -EPERM;
@@ -3104,6 +3182,28 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			return -EFAULT;
 		return 0;
 
+	case TCP_FASTOPEN_KEY: {
+		__u8 key[TCP_FASTOPEN_KEY_LENGTH];
+		struct tcp_fastopen_context *ctx;
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+
+		rcu_read_lock();
+		ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx);
+		if (ctx)
+			memcpy(key, ctx->key, sizeof(key));
+		else
+			len = 0;
+		rcu_read_unlock();
+
+		len = min_t(unsigned int, len, sizeof(key));
+		if (put_user(len, optlen))
+			return -EFAULT;
+		if (copy_to_user(optval, key, len))
+			return -EFAULT;
+		return 0;
+	}
 	case TCP_THIN_LINEAR_TIMEOUTS:
 		val = tp->thin_lto;
 		break;
@@ -3166,6 +3266,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		val = tp->fastopen_connect;
 		break;
 
+	case TCP_FASTOPEN_NO_COOKIE:
+		val = tp->fastopen_no_cookie;
+		break;
+
 	case TCP_TIMESTAMP:
 		val = tcp_time_stamp_raw() + tp->tsoffset;
 		break;
diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c
index 66ac69f7bd19..06fbe102a425 100644
--- a/net/ipv4/tcp_cdg.c
+++ b/net/ipv4/tcp_cdg.c
@@ -389,7 +389,7 @@ static void tcp_cdg_release(struct sock *sk)
 	kfree(ca->gradients);
 }
 
-struct tcp_congestion_ops tcp_cdg __read_mostly = {
+static struct tcp_congestion_ops tcp_cdg __read_mostly = {
 	.cong_avoid = tcp_cdg_cong_avoid,
 	.cwnd_event = tcp_cdg_cwnd_event,
 	.pkts_acked = tcp_cdg_acked,
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index fbbeda647774..78c192ee03a4 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -10,15 +10,18 @@
 #include <net/inetpeer.h>
 #include <net/tcp.h>
 
-int sysctl_tcp_fastopen __read_mostly = TFO_CLIENT_ENABLE;
-
-struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
-
-static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock);
-
-void tcp_fastopen_init_key_once(bool publish)
+void tcp_fastopen_init_key_once(struct net *net)
 {
-	static u8 key[TCP_FASTOPEN_KEY_LENGTH];
+	u8 key[TCP_FASTOPEN_KEY_LENGTH];
+	struct tcp_fastopen_context *ctxt;
+
+	rcu_read_lock();
+	ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
+	if (ctxt) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
 
 	/* tcp_fastopen_reset_cipher publishes the new context
 	 * atomically, so we allow this race happening here.
@@ -26,8 +29,8 @@ void tcp_fastopen_init_key_once(bool publish)
 	 * All call sites of tcp_fastopen_cookie_gen also check
 	 * for a valid cookie, so this is an acceptable risk.
 	 */
-	if (net_get_random_once(key, sizeof(key)) && publish)
-		tcp_fastopen_reset_cipher(key, sizeof(key));
+	get_random_bytes(key, sizeof(key));
+	tcp_fastopen_reset_cipher(net, NULL, key, sizeof(key));
 }
 
 static void tcp_fastopen_ctx_free(struct rcu_head *head)
@@ -38,10 +41,37 @@ static void tcp_fastopen_ctx_free(struct rcu_head *head)
 	kfree(ctx);
 }
 
-int tcp_fastopen_reset_cipher(void *key, unsigned int len)
+void tcp_fastopen_destroy_cipher(struct sock *sk)
+{
+	struct tcp_fastopen_context *ctx;
+
+	ctx = rcu_dereference_protected(
+			inet_csk(sk)->icsk_accept_queue.fastopenq.ctx, 1);
+	if (ctx)
+		call_rcu(&ctx->rcu, tcp_fastopen_ctx_free);
+}
+
+void tcp_fastopen_ctx_destroy(struct net *net)
+{
+	struct tcp_fastopen_context *ctxt;
+
+	spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
+
+	ctxt = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
+				lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+	rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, NULL);
+	spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
+
+	if (ctxt)
+		call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free);
+}
+
+int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
+			      void *key, unsigned int len)
 {
-	int err;
 	struct tcp_fastopen_context *ctx, *octx;
+	struct fastopen_queue *q;
+	int err;
 
 	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
@@ -62,26 +92,37 @@ error:		kfree(ctx);
 	}
 	memcpy(ctx->key, key, len);
 
-	spin_lock(&tcp_fastopen_ctx_lock);
 
-	octx = rcu_dereference_protected(tcp_fastopen_ctx,
-				lockdep_is_held(&tcp_fastopen_ctx_lock));
-	rcu_assign_pointer(tcp_fastopen_ctx, ctx);
-	spin_unlock(&tcp_fastopen_ctx_lock);
+	spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
+	if (sk) {
+		q = &inet_csk(sk)->icsk_accept_queue.fastopenq;
+		octx = rcu_dereference_protected(q->ctx,
+			lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+		rcu_assign_pointer(q->ctx, ctx);
+	} else {
+		octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
+			lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+		rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx);
+	}
+	spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
 
 	if (octx)
 		call_rcu(&octx->rcu, tcp_fastopen_ctx_free);
 	return err;
 }
 
-static bool __tcp_fastopen_cookie_gen(const void *path,
+static bool __tcp_fastopen_cookie_gen(struct sock *sk, const void *path,
 				      struct tcp_fastopen_cookie *foc)
 {
 	struct tcp_fastopen_context *ctx;
 	bool ok = false;
 
 	rcu_read_lock();
-	ctx = rcu_dereference(tcp_fastopen_ctx);
+
+	ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx);
+	if (!ctx)
+		ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx);
+
 	if (ctx) {
 		crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
 		foc->len = TCP_FASTOPEN_COOKIE_SIZE;
@@ -97,7 +138,8 @@ static bool __tcp_fastopen_cookie_gen(const void *path,
  *
  * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
  */
-static bool tcp_fastopen_cookie_gen(struct request_sock *req,
+static bool tcp_fastopen_cookie_gen(struct sock *sk,
+				    struct request_sock *req,
 				    struct sk_buff *syn,
 				    struct tcp_fastopen_cookie *foc)
 {
@@ -105,7 +147,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
 		const struct iphdr *iph = ip_hdr(syn);
 
 		__be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
-		return __tcp_fastopen_cookie_gen(path, foc);
+		return __tcp_fastopen_cookie_gen(sk, path, foc);
 	}
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -113,13 +155,13 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
 		const struct ipv6hdr *ip6h = ipv6_hdr(syn);
 		struct tcp_fastopen_cookie tmp;
 
-		if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
+		if (__tcp_fastopen_cookie_gen(sk, &ip6h->saddr, &tmp)) {
 			struct in6_addr *buf = &tmp.addr;
 			int i;
 
 			for (i = 0; i < 4; i++)
 				buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
-			return __tcp_fastopen_cookie_gen(buf, foc);
+			return __tcp_fastopen_cookie_gen(sk, buf, foc);
 		}
 	}
 #endif
@@ -217,12 +259,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	refcount_set(&req->rsk_refcnt, 2);
 
 	/* Now finish processing the fastopen child socket. */
-	inet_csk(child)->icsk_af_ops->rebuild_header(child);
-	tcp_init_congestion_control(child);
-	tcp_mtup_init(child);
-	tcp_init_metrics(child);
-	tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
-	tcp_init_buffer_space(child);
+	tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
 
 	tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
 
@@ -272,33 +309,45 @@ static bool tcp_fastopen_queue_check(struct sock *sk)
 	return true;
 }
 
+static bool tcp_fastopen_no_cookie(const struct sock *sk,
+				   const struct dst_entry *dst,
+				   int flag)
+{
+	return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) ||
+	       tcp_sk(sk)->fastopen_no_cookie ||
+	       (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE));
+}
+
 /* Returns true if we should perform Fast Open on the SYN. The cookie (foc)
  * may be updated and return the client in the SYN-ACK later. E.g., Fast Open
  * cookie request (foc->len == 0).
  */
 struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      struct request_sock *req,
-			      struct tcp_fastopen_cookie *foc)
+			      struct tcp_fastopen_cookie *foc,
+			      const struct dst_entry *dst)
 {
-	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
 	bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
+	int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
 	struct sock *child;
 
 	if (foc->len == 0) /* Client requests a cookie */
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD);
 
-	if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+	if (!((tcp_fastopen & TFO_SERVER_ENABLE) &&
 	      (syn_data || foc->len >= 0) &&
 	      tcp_fastopen_queue_check(sk))) {
 		foc->len = -1;
 		return NULL;
 	}
 
-	if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
+	if (syn_data &&
+	    tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD))
 		goto fastopen;
 
 	if (foc->len >= 0 &&  /* Client presents or requests a cookie */
-	    tcp_fastopen_cookie_gen(req, skb, &valid_foc) &&
+	    tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc) &&
 	    foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
 	    foc->len == valid_foc.len &&
 	    !memcmp(foc->val, valid_foc.val, foc->len)) {
@@ -331,6 +380,7 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 			       struct tcp_fastopen_cookie *cookie)
 {
 	unsigned long last_syn_loss = 0;
+	const struct dst_entry *dst;
 	int syn_loss = 0;
 
 	tcp_fastopen_cache_get(sk, mss, cookie, &syn_loss, &last_syn_loss);
@@ -348,7 +398,9 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 		return false;
 	}
 
-	if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) {
+	dst = __sk_dst_get(sk);
+
+	if (tcp_fastopen_no_cookie(sk, dst, TFO_CLIENT_NO_COOKIE)) {
 		cookie->len = -1;
 		return true;
 	}
@@ -402,25 +454,16 @@ EXPORT_SYMBOL(tcp_fastopen_defer_connect);
  * TFO connection with data exchanges.
  */
 
-/* Default to 1hr */
-unsigned int sysctl_tcp_fastopen_blackhole_timeout __read_mostly = 60 * 60;
-static atomic_t tfo_active_disable_times __read_mostly = ATOMIC_INIT(0);
-static unsigned long tfo_active_disable_stamp __read_mostly;
-
 /* Disable active TFO and record current jiffies and
  * tfo_active_disable_times
  */
 void tcp_fastopen_active_disable(struct sock *sk)
 {
-	atomic_inc(&tfo_active_disable_times);
-	tfo_active_disable_stamp = jiffies;
-	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENBLACKHOLE);
-}
+	struct net *net = sock_net(sk);
 
-/* Reset tfo_active_disable_times to 0 */
-void tcp_fastopen_active_timeout_reset(void)
-{
-	atomic_set(&tfo_active_disable_times, 0);
+	atomic_inc(&net->ipv4.tfo_active_disable_times);
+	net->ipv4.tfo_active_disable_stamp = jiffies;
+	NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE);
 }
 
 /* Calculate timeout for tfo active disable
@@ -429,17 +472,18 @@ void tcp_fastopen_active_timeout_reset(void)
  */
 bool tcp_fastopen_active_should_disable(struct sock *sk)
 {
-	int tfo_da_times = atomic_read(&tfo_active_disable_times);
-	int multiplier;
+	unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
+	int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
 	unsigned long timeout;
+	int multiplier;
 
 	if (!tfo_da_times)
 		return false;
 
 	/* Limit timout to max: 2^6 * initial timeout */
 	multiplier = 1 << min(tfo_da_times - 1, 6);
-	timeout = multiplier * sysctl_tcp_fastopen_blackhole_timeout * HZ;
-	if (time_before(jiffies, tfo_active_disable_stamp + timeout))
+	timeout = multiplier * tfo_bh_timeout * HZ;
+	if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout))
 		return true;
 
 	/* Mark check bit so we can check for successful active TFO
@@ -458,27 +502,25 @@ bool tcp_fastopen_active_should_disable(struct sock *sk)
 void tcp_fastopen_active_disable_ofo_check(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct rb_node *p;
-	struct sk_buff *skb;
 	struct dst_entry *dst;
+	struct sk_buff *skb;
 
 	if (!tp->syn_fastopen)
 		return;
 
 	if (!tp->data_segs_in) {
-		p = rb_first(&tp->out_of_order_queue);
-		if (p && !rb_next(p)) {
-			skb = rb_entry(p, struct sk_buff, rbnode);
+		skb = skb_rb_first(&tp->out_of_order_queue);
+		if (skb && !skb_rb_next(skb)) {
 			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
 				tcp_fastopen_active_disable(sk);
 				return;
 			}
 		}
 	} else if (tp->syn_fastopen_ch &&
-		   atomic_read(&tfo_active_disable_times)) {
+		   atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) {
 		dst = sk_dst_get(sk);
 		if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK)))
-			tcp_fastopen_active_timeout_reset();
+			atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0);
 		dst_release(dst);
 	}
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5a87a00641d3..8393b405ea98 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -76,25 +76,10 @@
 #include <linux/ipsec.h>
 #include <asm/unaligned.h>
 #include <linux/errqueue.h>
+#include <trace/events/tcp.h>
+#include <linux/static_key.h>
 
-int sysctl_tcp_fack __read_mostly;
-int sysctl_tcp_max_reordering __read_mostly = 300;
-int sysctl_tcp_dsack __read_mostly = 1;
-int sysctl_tcp_app_win __read_mostly = 31;
-int sysctl_tcp_adv_win_scale __read_mostly = 1;
-EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
-
-/* rfc5961 challenge ack rate limiting */
-int sysctl_tcp_challenge_ack_limit = 1000;
-
-int sysctl_tcp_stdurg __read_mostly;
-int sysctl_tcp_rfc1337 __read_mostly;
 int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
-int sysctl_tcp_frto __read_mostly = 2;
-int sysctl_tcp_min_rtt_wlen __read_mostly = 300;
-int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
-int sysctl_tcp_early_retrans __read_mostly = 3;
-int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
 
 #define FLAG_DATA		0x01 /* Incoming frame contained data.		*/
 #define FLAG_WIN_UPDATE		0x02 /* Incoming ACK was a window update.	*/
@@ -368,8 +353,8 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	/* Optimize this! */
-	int truesize = tcp_win_from_space(skb->truesize) >> 1;
-	int window = tcp_win_from_space(sysctl_tcp_rmem[2]) >> 1;
+	int truesize = tcp_win_from_space(sk, skb->truesize) >> 1;
+	int window = tcp_win_from_space(sk, sysctl_tcp_rmem[2]) >> 1;
 
 	while (tp->rcv_ssthresh <= window) {
 		if (truesize <= skb->len)
@@ -394,7 +379,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 		/* Check #2. Increase window, if skb with such overhead
 		 * will fit to rcvbuf in future.
 		 */
-		if (tcp_win_from_space(skb->truesize) <= skb->len)
+		if (tcp_win_from_space(sk, skb->truesize) <= skb->len)
 			incr = 2 * tp->advmss;
 		else
 			incr = __tcp_grow_window(sk, skb);
@@ -420,7 +405,7 @@ static void tcp_fixup_rcvbuf(struct sock *sk)
 	/* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency
 	 * Allow enough cushion so that sender is not limited by our window
 	 */
-	if (sysctl_tcp_moderate_rcvbuf)
+	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)
 		rcvmem <<= 2;
 
 	if (sk->sk_rcvbuf < rcvmem)
@@ -432,6 +417,7 @@ static void tcp_fixup_rcvbuf(struct sock *sk)
  */
 void tcp_init_buffer_space(struct sock *sk)
 {
+	int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
 	struct tcp_sock *tp = tcp_sk(sk);
 	int maxwin;
 
@@ -450,14 +436,14 @@ void tcp_init_buffer_space(struct sock *sk)
 	if (tp->window_clamp >= maxwin) {
 		tp->window_clamp = maxwin;
 
-		if (sysctl_tcp_app_win && maxwin > 4 * tp->advmss)
+		if (tcp_app_win && maxwin > 4 * tp->advmss)
 			tp->window_clamp = max(maxwin -
-					       (maxwin >> sysctl_tcp_app_win),
+					       (maxwin >> tcp_app_win),
 					       4 * tp->advmss);
 	}
 
 	/* Force reservation of one segment. */
-	if (sysctl_tcp_app_win &&
+	if (tcp_app_win &&
 	    tp->window_clamp > 2 * tp->advmss &&
 	    tp->window_clamp + tp->advmss > maxwin)
 		tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss);
@@ -610,7 +596,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 	 * <prev RTT . ><current RTT .. ><next RTT .... >
 	 */
 
-	if (sysctl_tcp_moderate_rcvbuf &&
+	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
 		int rcvwin, rcvmem, rcvbuf;
 
@@ -634,7 +620,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 		}
 
 		rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
-		while (tcp_win_from_space(rcvmem) < tp->advmss)
+		while (tcp_win_from_space(sk, rcvmem) < tp->advmss)
 			rcvmem += 128;
 
 		rcvbuf = min(rcvwin / tp->advmss * rcvmem, sysctl_tcp_rmem[2]);
@@ -781,15 +767,6 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
 	tp->srtt_us = max(1U, srtt);
 }
 
-/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
- * Note: TCP stack does not yet implement pacing.
- * FQ packet scheduler can be used to implement cheap but effective
- * TCP pacing, to smooth the burst on large writes when packets
- * in flight is significantly lower than cwnd (or rwin)
- */
-int sysctl_tcp_pacing_ss_ratio __read_mostly = 200;
-int sysctl_tcp_pacing_ca_ratio __read_mostly = 120;
-
 static void tcp_update_pacing_rate(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -807,9 +784,9 @@ static void tcp_update_pacing_rate(struct sock *sk)
 	 *	 end of slow start and should slow down.
 	 */
 	if (tp->snd_cwnd < tp->snd_ssthresh / 2)
-		rate *= sysctl_tcp_pacing_ss_ratio;
+		rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio;
 	else
-		rate *= sysctl_tcp_pacing_ca_ratio;
+		rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio;
 
 	rate *= max(tp->snd_cwnd, tp->packets_out);
 
@@ -891,7 +868,7 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
 		return;
 
 	if (metric > tp->reordering) {
-		tp->reordering = min(sysctl_tcp_max_reordering, metric);
+		tp->reordering = min(sock_net(sk)->ipv4.sysctl_tcp_max_reordering, metric);
 
 #if FASTRETRANS_DEBUG > 1
 		pr_debug("Disorder%d %d %u f%u s%u rr%d\n",
@@ -1143,6 +1120,7 @@ struct tcp_sacktag_state {
 	u64	last_sackt;
 	struct rate_sample *rate;
 	int	flag;
+	unsigned int mss_now;
 };
 
 /* Check if skb is fully within the SACK block. In presence of GSO skbs,
@@ -1192,7 +1170,8 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 		if (pkt_len >= skb->len && !in_sack)
 			return 0;
 
-		err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC);
+		err = tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
+				   pkt_len, mss, GFP_ATOMIC);
 		if (err < 0)
 			return err;
 	}
@@ -1289,13 +1268,13 @@ static u8 tcp_sacktag_one(struct sock *sk,
 /* Shift newly-SACKed bytes from this skb to the immediately previous
  * already-SACKed sk_buff. Mark the newly-SACKed bytes as such.
  */
-static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
+static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
+			    struct sk_buff *skb,
 			    struct tcp_sacktag_state *state,
 			    unsigned int pcount, int shifted, int mss,
 			    bool dup_sack)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *prev = tcp_write_queue_prev(sk, skb);
 	u32 start_seq = TCP_SKB_CB(skb)->seq;	/* start of newly-SACKed */
 	u32 end_seq = start_seq + shifted;	/* end of newly-SACKed */
 
@@ -1364,8 +1343,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 	if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp))
 		TCP_SKB_CB(prev)->tx.delivered_mstamp = 0;
 
-	tcp_unlink_write_queue(skb, sk);
-	sk_wmem_free_skb(sk, skb);
+	tcp_rtx_queue_unlink_and_free(skb, sk);
 
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKMERGED);
 
@@ -1415,9 +1393,9 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 		goto fallback;
 
 	/* Can only happen with delayed DSACK + discard craziness */
-	if (unlikely(skb == tcp_write_queue_head(sk)))
+	prev = skb_rb_prev(skb);
+	if (!prev)
 		goto fallback;
-	prev = tcp_write_queue_prev(sk, skb);
 
 	if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
 		goto fallback;
@@ -1496,18 +1474,17 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 
 	if (!skb_shift(prev, skb, len))
 		goto fallback;
-	if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack))
+	if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack))
 		goto out;
 
 	/* Hole filled allows collapsing with the next as well, this is very
 	 * useful when hole on every nth skb pattern happens
 	 */
-	if (prev == tcp_write_queue_tail(sk))
+	skb = skb_rb_next(prev);
+	if (!skb)
 		goto out;
-	skb = tcp_write_queue_next(sk, prev);
 
 	if (!skb_can_shift(skb) ||
-	    (skb == tcp_send_head(sk)) ||
 	    ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) ||
 	    (mss != tcp_skb_seglen(skb)))
 		goto out;
@@ -1515,7 +1492,8 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 	len = skb->len;
 	if (skb_shift(prev, skb, len)) {
 		pcount += tcp_skb_pcount(skb);
-		tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0);
+		tcp_shifted_skb(sk, prev, skb, state, tcp_skb_pcount(skb),
+				len, mss, 0);
 	}
 
 out:
@@ -1539,13 +1517,10 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *tmp;
 
-	tcp_for_write_queue_from(skb, sk) {
+	skb_rbtree_walk_from(skb) {
 		int in_sack = 0;
 		bool dup_sack = dup_sack_in;
 
-		if (skb == tcp_send_head(sk))
-			break;
-
 		/* queue is in-order => we can short-circuit the walk early */
 		if (!before(TCP_SKB_CB(skb)->seq, end_seq))
 			break;
@@ -1594,6 +1569,8 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 						tcp_skb_pcount(skb),
 						skb->skb_mstamp);
 			tcp_rate_skb_delivered(sk, skb, state->rate);
+			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
+				list_del_init(&skb->tcp_tsorted_anchor);
 
 			if (!before(TCP_SKB_CB(skb)->seq,
 				    tcp_highest_sack_seq(tp)))
@@ -1605,23 +1582,44 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 	return skb;
 }
 
-/* Avoid all extra work that is being done by sacktag while walking in
- * a normal way
- */
+static struct sk_buff *tcp_sacktag_bsearch(struct sock *sk,
+					   struct tcp_sacktag_state *state,
+					   u32 seq)
+{
+	struct rb_node *parent, **p = &sk->tcp_rtx_queue.rb_node;
+	struct sk_buff *skb;
+	int unack_bytes;
+
+	while (*p) {
+		parent = *p;
+		skb = rb_to_skb(parent);
+		if (before(seq, TCP_SKB_CB(skb)->seq)) {
+			p = &parent->rb_left;
+			continue;
+		}
+		if (!before(seq, TCP_SKB_CB(skb)->end_seq)) {
+			p = &parent->rb_right;
+			continue;
+		}
+
+		state->fack_count = 0;
+		unack_bytes = TCP_SKB_CB(skb)->seq - tcp_sk(sk)->snd_una;
+		if (state->mss_now && unack_bytes > 0)
+			state->fack_count = unack_bytes / state->mss_now;
+
+		return skb;
+	}
+	return NULL;
+}
+
 static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk,
 					struct tcp_sacktag_state *state,
 					u32 skip_to_seq)
 {
-	tcp_for_write_queue_from(skb, sk) {
-		if (skb == tcp_send_head(sk))
-			break;
-
-		if (after(TCP_SKB_CB(skb)->end_seq, skip_to_seq))
-			break;
+	if (skb && after(TCP_SKB_CB(skb)->seq, skip_to_seq))
+		return skb;
 
-		state->fack_count += tcp_skb_pcount(skb);
-	}
-	return skb;
+	return tcp_sacktag_bsearch(sk, state, skip_to_seq);
 }
 
 static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb,
@@ -1743,8 +1741,9 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 		}
 	}
 
-	skb = tcp_write_queue_head(sk);
+	state->mss_now = tcp_current_mss(sk);
 	state->fack_count = 0;
+	skb = NULL;
 	i = 0;
 
 	if (!tp->sacked_out) {
@@ -1968,7 +1967,7 @@ void tcp_enter_loss(struct sock *sk)
 	if (tcp_is_reno(tp))
 		tcp_reset_reno_sack(tp);
 
-	skb = tcp_write_queue_head(sk);
+	skb = tcp_rtx_queue_head(sk);
 	is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED);
 	if (is_reneg) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
@@ -1977,10 +1976,7 @@ void tcp_enter_loss(struct sock *sk)
 	}
 	tcp_clear_all_retrans_hints(tp);
 
-	tcp_for_write_queue(skb, sk) {
-		if (skb == tcp_send_head(sk))
-			break;
-
+	skb_rbtree_walk_from(skb) {
 		mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
 			     is_reneg);
 		if (mark_lost)
@@ -2014,7 +2010,7 @@ void tcp_enter_loss(struct sock *sk)
 	 * falsely raise the receive window, which results in repeated
 	 * timeouts and stop-and-go behavior.
 	 */
-	tp->frto = sysctl_tcp_frto &&
+	tp->frto = net->ipv4.sysctl_tcp_frto &&
 		   (new_recovery || icsk->icsk_retransmits) &&
 		   !inet_csk(sk)->icsk_mtup.probe_size;
 }
@@ -2206,20 +2202,18 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 	const u32 loss_high = tcp_is_sack(tp) ?  tp->snd_nxt : tp->high_seq;
 
 	WARN_ON(packets > tp->packets_out);
-	if (tp->lost_skb_hint) {
-		skb = tp->lost_skb_hint;
-		cnt = tp->lost_cnt_hint;
+	skb = tp->lost_skb_hint;
+	if (skb) {
 		/* Head already handled? */
-		if (mark_head && skb != tcp_write_queue_head(sk))
+		if (mark_head && after(TCP_SKB_CB(skb)->seq, tp->snd_una))
 			return;
+		cnt = tp->lost_cnt_hint;
 	} else {
-		skb = tcp_write_queue_head(sk);
+		skb = tcp_rtx_queue_head(sk);
 		cnt = 0;
 	}
 
-	tcp_for_write_queue_from(skb, sk) {
-		if (skb == tcp_send_head(sk))
-			break;
+	skb_rbtree_walk_from(skb) {
 		/* TODO: do this better */
 		/* this is not the most efficient way to do this... */
 		tp->lost_skb_hint = skb;
@@ -2243,7 +2237,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 			/* If needed, chop off the prefix to mark as lost. */
 			lost = (packets - oldcnt) * mss;
 			if (lost < skb->len &&
-			    tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0)
+			    tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
+					 lost, mss, GFP_ATOMIC) < 0)
 				break;
 			cnt = packets;
 		}
@@ -2327,16 +2322,16 @@ static bool tcp_any_retrans_done(const struct sock *sk)
 	if (tp->retrans_out)
 		return true;
 
-	skb = tcp_write_queue_head(sk);
+	skb = tcp_rtx_queue_head(sk);
 	if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS))
 		return true;
 
 	return false;
 }
 
-#if FASTRETRANS_DEBUG > 1
 static void DBGUNDO(struct sock *sk, const char *msg)
 {
+#if FASTRETRANS_DEBUG > 1
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_sock *inet = inet_sk(sk);
 
@@ -2358,10 +2353,8 @@ static void DBGUNDO(struct sock *sk, const char *msg)
 			 tp->packets_out);
 	}
 #endif
-}
-#else
-#define DBGUNDO(x...) do { } while (0)
 #endif
+}
 
 static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
 {
@@ -2370,9 +2363,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
 	if (unmark_loss) {
 		struct sk_buff *skb;
 
-		tcp_for_write_queue(skb, sk) {
-			if (skb == tcp_send_head(sk))
-				break;
+		skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
 			TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
 		}
 		tp->lost_out = 0;
@@ -2617,9 +2608,7 @@ void tcp_simple_retransmit(struct sock *sk)
 	unsigned int mss = tcp_current_mss(sk);
 	u32 prior_lost = tp->lost_out;
 
-	tcp_for_write_queue(skb, sk) {
-		if (skb == tcp_send_head(sk))
-			break;
+	skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
 		if (tcp_skb_seglen(skb) > mss &&
 		    !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
 			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
@@ -2713,7 +2702,7 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
 			 * is updated in tcp_ack()). Otherwise fall back to
 			 * the conventional recovery.
 			 */
-			if (tcp_send_head(sk) &&
+			if (!tcp_write_queue_empty(sk) &&
 			    after(tcp_wnd_end(tp), tp->snd_nxt)) {
 				*rexmit = REXMIT_NEW;
 				return;
@@ -2775,7 +2764,7 @@ static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	/* Use RACK to detect loss */
-	if (sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) {
+	if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) {
 		u32 prior_retrans = tp->retrans_out;
 
 		tcp_rack_mark_lost(sk);
@@ -2805,9 +2794,9 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
 	bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
 				    (tcp_fackets_out(tp) > tp->reordering));
 
-	if (WARN_ON(!tp->packets_out && tp->sacked_out))
+	if (!tp->packets_out && tp->sacked_out)
 		tp->sacked_out = 0;
-	if (WARN_ON(!tp->sacked_out && tp->fackets_out))
+	if (!tp->sacked_out && tp->fackets_out)
 		tp->fackets_out = 0;
 
 	/* Now state machine starts.
@@ -2874,6 +2863,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
 		      (*ack_flag & FLAG_LOST_RETRANS)))
 			return;
 		/* Change state if cwnd is undone or retransmits are lost */
+		/* fall through */
 	default:
 		if (tcp_is_reno(tp)) {
 			if (flag & FLAG_SND_UNA_ADVANCED)
@@ -2914,8 +2904,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
 
 static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
 {
+	u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 wlen = sysctl_tcp_min_rtt_wlen * HZ;
 
 	minmax_running_min(&tp->rtt_min, wlen, tcp_jiffies32,
 			   rtt_us ? : jiffies_to_usecs(1));
@@ -3057,8 +3047,11 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
 
 	shinfo = skb_shinfo(skb);
 	if (!before(shinfo->tskey, prior_snd_una) &&
-	    before(shinfo->tskey, tcp_sk(sk)->snd_una))
-		__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+	    before(shinfo->tskey, tcp_sk(sk)->snd_una)) {
+		tcp_skb_tsorted_save(skb) {
+			__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+		} tcp_skb_tsorted_restore(skb);
+	}
 }
 
 /* Remove acknowledged frames from the retransmission queue. If our packet
@@ -3074,11 +3067,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 prior_sacked = tp->sacked_out;
 	u32 reord = tp->packets_out;
+	struct sk_buff *skb, *next;
 	bool fully_acked = true;
 	long sack_rtt_us = -1L;
 	long seq_rtt_us = -1L;
 	long ca_rtt_us = -1L;
-	struct sk_buff *skb;
 	u32 pkts_acked = 0;
 	u32 last_in_flight = 0;
 	bool rtt_update;
@@ -3086,7 +3079,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 
 	first_ackt = 0;
 
-	while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
+	for (skb = skb_rb_first(&sk->tcp_rtx_queue); skb; skb = next) {
 		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
 		u8 sacked = scb->sacked;
 		u32 acked_pcount;
@@ -3104,8 +3097,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 				break;
 			fully_acked = false;
 		} else {
-			/* Speedup tcp_unlink_write_queue() and next loop */
-			prefetchw(skb->next);
 			acked_pcount = tcp_skb_pcount(skb);
 		}
 
@@ -3157,12 +3148,12 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 		if (!fully_acked)
 			break;
 
-		tcp_unlink_write_queue(skb, sk);
-		sk_wmem_free_skb(sk, skb);
+		next = skb_rb_next(skb);
 		if (unlikely(skb == tp->retransmit_skb_hint))
 			tp->retransmit_skb_hint = NULL;
 		if (unlikely(skb == tp->lost_skb_hint))
 			tp->lost_skb_hint = NULL;
+		tcp_rtx_queue_unlink_and_free(skb, sk);
 	}
 
 	if (!skb)
@@ -3254,12 +3245,14 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 
 static void tcp_ack_probe(struct sock *sk)
 {
-	const struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct sk_buff *head = tcp_send_head(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 
 	/* Was it a usable window open? */
-
-	if (!after(TCP_SKB_CB(tcp_send_head(sk))->end_seq, tcp_wnd_end(tp))) {
+	if (!head)
+		return;
+	if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) {
 		icsk->icsk_backoff = 0;
 		inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
 		/* Socket must be waked up by subsequent tcp_data_snd_check().
@@ -3379,7 +3372,7 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
 			tp->pred_flags = 0;
 			tcp_fast_path_check(sk);
 
-			if (tcp_send_head(sk))
+			if (!tcp_write_queue_empty(sk))
 				tcp_slow_start_after_idle_check(sk);
 
 			if (nwin > tp->max_window) {
@@ -3400,7 +3393,7 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
 	if (*last_oow_ack_time) {
 		s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
 
-		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
+		if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
 			NET_INC_STATS(net, mib_idx);
 			return true;	/* rate-limited: don't send yet! */
 		}
@@ -3436,10 +3429,11 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 	static u32 challenge_timestamp;
 	static unsigned int challenge_count;
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
 	u32 count, now;
 
 	/* First check our per-socket dupack rate limit. */
-	if (__tcp_oow_rate_limited(sock_net(sk),
+	if (__tcp_oow_rate_limited(net,
 				   LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
 				   &tp->last_oow_ack_time))
 		return;
@@ -3447,16 +3441,16 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 	/* Then check host-wide RFC 5961 rate limit. */
 	now = jiffies / HZ;
 	if (now != challenge_timestamp) {
-		u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1;
+		u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
+		u32 half = (ack_limit + 1) >> 1;
 
 		challenge_timestamp = now;
-		WRITE_ONCE(challenge_count, half +
-			   prandom_u32_max(sysctl_tcp_challenge_ack_limit));
+		WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit));
 	}
 	count = READ_ONCE(challenge_count);
 	if (count > 0) {
 		WRITE_ONCE(challenge_count, count - 1);
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
+		NET_INC_STATS(net, LINUX_MIB_TCPCHALLENGEACK);
 		tcp_send_ack(sk);
 	}
 }
@@ -3564,8 +3558,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	sack_state.first_sackt = 0;
 	sack_state.rate = &rs;
 
-	/* We very likely will need to access write queue head. */
-	prefetchw(sk->sk_write_queue.next);
+	/* We very likely will need to access rtx queue. */
+	prefetch(sk->tcp_rtx_queue.rb_node);
 
 	/* If the ack is older than previous acks
 	 * then we can probably ignore it.
@@ -3679,8 +3673,7 @@ no_queue:
 	 * being used to time the probes, and is probably far higher than
 	 * it needs to be for normal retransmission.
 	 */
-	if (tcp_send_head(sk))
-		tcp_ack_probe(sk);
+	tcp_ack_probe(sk);
 
 	if (tp->tlp_high_seq)
 		tcp_process_tlp_ack(sk, ack, flag);
@@ -3722,6 +3715,21 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie,
 	foc->exp = exp_opt;
 }
 
+static void smc_parse_options(const struct tcphdr *th,
+			      struct tcp_options_received *opt_rx,
+			      const unsigned char *ptr,
+			      int opsize)
+{
+#if IS_ENABLED(CONFIG_SMC)
+	if (static_branch_unlikely(&tcp_have_smc)) {
+		if (th->syn && !(opsize & 1) &&
+		    opsize >= TCPOLEN_EXP_SMC_BASE &&
+		    get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC)
+			opt_rx->smc_ok = 1;
+	}
+#endif
+}
+
 /* Look for tcp options. Normally only called on SYN and SYNACK packets.
  * But, this can also be called on packets in the established flow when
  * the fast version below fails.
@@ -3829,6 +3837,9 @@ void tcp_parse_options(const struct net *net,
 					tcp_parse_fastopen_option(opsize -
 						TCPOLEN_EXP_FASTOPEN_BASE,
 						ptr + 2, th->syn, foc, true);
+				else
+					smc_parse_options(th, opt_rx, ptr,
+							  opsize);
 				break;
 
 			}
@@ -3996,6 +4007,8 @@ static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq)
 /* When we get a reset we do this. */
 void tcp_reset(struct sock *sk)
 {
+	trace_tcp_receive_reset(sk);
+
 	/* We want the right error as BSD sees it (and indeed as we do). */
 	switch (sk->sk_state) {
 	case TCP_SYN_SENT:
@@ -4118,7 +4131,7 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+	if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
 		int mib_idx;
 
 		if (before(seq, tp->rcv_nxt))
@@ -4153,7 +4166,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
 		tcp_enter_quickack_mode(sk);
 
-		if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+		if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
 			u32 end_seq = TCP_SKB_CB(skb)->end_seq;
 
 			if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
@@ -4269,11 +4282,6 @@ static void tcp_sack_remove(struct tcp_sock *tp)
 	tp->rx_opt.num_sacks = num_sacks;
 }
 
-enum tcp_queue {
-	OOO_QUEUE,
-	RCV_QUEUE,
-};
-
 /**
  * tcp_try_coalesce - try to merge skb to prior one
  * @sk: socket
@@ -4289,7 +4297,6 @@ enum tcp_queue {
  * Returns true if caller should free @from instead of queueing it
  */
 static bool tcp_try_coalesce(struct sock *sk,
-			     enum tcp_queue dest,
 			     struct sk_buff *to,
 			     struct sk_buff *from,
 			     bool *fragstolen)
@@ -4314,10 +4321,7 @@ static bool tcp_try_coalesce(struct sock *sk,
 
 	if (TCP_SKB_CB(from)->has_rxtstamp) {
 		TCP_SKB_CB(to)->has_rxtstamp = true;
-		if (dest == OOO_QUEUE)
-			TCP_SKB_CB(to)->swtstamp = TCP_SKB_CB(from)->swtstamp;
-		else
-			to->tstamp = from->tstamp;
+		to->tstamp = from->tstamp;
 	}
 
 	return true;
@@ -4342,7 +4346,7 @@ static void tcp_ofo_queue(struct sock *sk)
 
 	p = rb_first(&tp->out_of_order_queue);
 	while (p) {
-		skb = rb_entry(p, struct sk_buff, rbnode);
+		skb = rb_to_skb(p);
 		if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
 			break;
 
@@ -4354,9 +4358,6 @@ static void tcp_ofo_queue(struct sock *sk)
 		}
 		p = rb_next(p);
 		rb_erase(&skb->rbnode, &tp->out_of_order_queue);
-		/* Replace tstamp which was stomped by rbnode */
-		if (TCP_SKB_CB(skb)->has_rxtstamp)
-			skb->tstamp = TCP_SKB_CB(skb)->swtstamp;
 
 		if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) {
 			SOCK_DEBUG(sk, "ofo packet was already received\n");
@@ -4368,8 +4369,7 @@ static void tcp_ofo_queue(struct sock *sk)
 			   TCP_SKB_CB(skb)->end_seq);
 
 		tail = skb_peek_tail(&sk->sk_receive_queue);
-		eaten = tail && tcp_try_coalesce(sk, RCV_QUEUE,
-						 tail, skb, &fragstolen);
+		eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
 		tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
 		fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
 		if (!eaten)
@@ -4410,7 +4410,7 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
 static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct rb_node **p, *q, *parent;
+	struct rb_node **p, *parent;
 	struct sk_buff *skb1;
 	u32 seq, end_seq;
 	bool fragstolen;
@@ -4423,10 +4423,6 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		return;
 	}
 
-	/* Stash tstamp to avoid being stomped on by rbnode */
-	if (TCP_SKB_CB(skb)->has_rxtstamp)
-		TCP_SKB_CB(skb)->swtstamp = skb->tstamp;
-
 	/* Disable header prediction. */
 	tp->pred_flags = 0;
 	inet_csk_schedule_ack(sk);
@@ -4454,7 +4450,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	/* In the typical case, we are adding an skb to the end of the list.
 	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
 	 */
-	if (tcp_try_coalesce(sk, OOO_QUEUE, tp->ooo_last_skb,
+	if (tcp_try_coalesce(sk, tp->ooo_last_skb,
 			     skb, &fragstolen)) {
 coalesce_done:
 		tcp_grow_window(sk, skb);
@@ -4473,7 +4469,7 @@ coalesce_done:
 	parent = NULL;
 	while (*p) {
 		parent = *p;
-		skb1 = rb_entry(parent, struct sk_buff, rbnode);
+		skb1 = rb_to_skb(parent);
 		if (before(seq, TCP_SKB_CB(skb1)->seq)) {
 			p = &parent->rb_left;
 			continue;
@@ -4505,7 +4501,7 @@ coalesce_done:
 				__kfree_skb(skb1);
 				goto merge_right;
 			}
-		} else if (tcp_try_coalesce(sk, OOO_QUEUE, skb1,
+		} else if (tcp_try_coalesce(sk, skb1,
 					    skb, &fragstolen)) {
 			goto coalesce_done;
 		}
@@ -4518,9 +4514,7 @@ insert:
 
 merge_right:
 	/* Remove other segments covered by skb. */
-	while ((q = rb_next(&skb->rbnode)) != NULL) {
-		skb1 = rb_entry(q, struct sk_buff, rbnode);
-
+	while ((skb1 = skb_rb_next(skb)) != NULL) {
 		if (!after(end_seq, TCP_SKB_CB(skb1)->seq))
 			break;
 		if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
@@ -4535,7 +4529,7 @@ merge_right:
 		tcp_drop(sk, skb1);
 	}
 	/* If there is no skb after us, we are the last_skb ! */
-	if (!q)
+	if (!skb1)
 		tp->ooo_last_skb = skb;
 
 add_sack:
@@ -4557,7 +4551,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
 
 	__skb_pull(skb, hdrlen);
 	eaten = (tail &&
-		 tcp_try_coalesce(sk, RCV_QUEUE, tail,
+		 tcp_try_coalesce(sk, tail,
 				  skb, fragstolen)) ? 1 : 0;
 	tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
 	if (!eaten) {
@@ -4721,7 +4715,7 @@ static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *li
 	if (list)
 		return !skb_queue_is_last(list, skb) ? skb->next : NULL;
 
-	return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode);
+	return skb_rb_next(skb);
 }
 
 static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,
@@ -4742,7 +4736,7 @@ static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,
 }
 
 /* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */
-static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
+void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
@@ -4750,7 +4744,7 @@ static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
 
 	while (*p) {
 		parent = *p;
-		skb1 = rb_entry(parent, struct sk_buff, rbnode);
+		skb1 = rb_to_skb(parent);
 		if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq))
 			p = &parent->rb_left;
 		else
@@ -4797,7 +4791,7 @@ restart:
 		 *   overlaps to the next one.
 		 */
 		if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
-		    (tcp_win_from_space(skb->truesize) > skb->len ||
+		    (tcp_win_from_space(sk, skb->truesize) > skb->len ||
 		     before(TCP_SKB_CB(skb)->seq, start))) {
 			end_of_skbs = false;
 			break;
@@ -4869,26 +4863,19 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb, *head;
-	struct rb_node *p;
 	u32 start, end;
 
-	p = rb_first(&tp->out_of_order_queue);
-	skb = rb_entry_safe(p, struct sk_buff, rbnode);
+	skb = skb_rb_first(&tp->out_of_order_queue);
 new_range:
 	if (!skb) {
-		p = rb_last(&tp->out_of_order_queue);
-		/* Note: This is possible p is NULL here. We do not
-		 * use rb_entry_safe(), as ooo_last_skb is valid only
-		 * if rbtree is not empty.
-		 */
-		tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode);
+		tp->ooo_last_skb = skb_rb_last(&tp->out_of_order_queue);
 		return;
 	}
 	start = TCP_SKB_CB(skb)->seq;
 	end = TCP_SKB_CB(skb)->end_seq;
 
 	for (head = skb;;) {
-		skb = tcp_skb_next(skb, NULL);
+		skb = skb_rb_next(skb);
 
 		/* Range is terminated when we see a gap or when
 		 * we are at the queue end.
@@ -4931,14 +4918,14 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
 	do {
 		prev = rb_prev(node);
 		rb_erase(node, &tp->out_of_order_queue);
-		tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode));
+		tcp_drop(sk, rb_to_skb(node));
 		sk_mem_reclaim(sk);
 		if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
 		    !tcp_under_memory_pressure(sk))
 			break;
 		node = prev;
 	} while (node);
-	tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode);
+	tp->ooo_last_skb = rb_to_skb(prev);
 
 	/* Reset SACK state.  A conforming SACK implementation will
 	 * do the same at a timeout based retransmit.  When a connection
@@ -5113,7 +5100,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th)
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 ptr = ntohs(th->urg_ptr);
 
-	if (ptr && !sysctl_tcp_stdurg)
+	if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg)
 		ptr--;
 	ptr += ntohl(th->seq);
 
@@ -5533,20 +5520,13 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 		security_inet_conn_established(sk, skb);
 	}
 
-	/* Make sure socket is routed, for correct metrics.  */
-	icsk->icsk_af_ops->rebuild_header(sk);
-
-	tcp_init_metrics(sk);
-	tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
-	tcp_init_congestion_control(sk);
+	tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
 
 	/* Prevent spurious tcp_cwnd_restart() on first data
 	 * packet.
 	 */
 	tp->lsndtime = tcp_jiffies32;
 
-	tcp_init_buffer_space(sk);
-
 	if (sock_flag(sk, SOCK_KEEPOPEN))
 		inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp));
 
@@ -5560,7 +5540,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 				    struct tcp_fastopen_cookie *cookie)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL;
+	struct sk_buff *data = tp->syn_data ? tcp_rtx_queue_head(sk) : NULL;
 	u16 mss = tp->rx_opt.mss_clamp, try_exp = 0;
 	bool syn_drop = false;
 
@@ -5595,9 +5575,8 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 	tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp);
 
 	if (data) { /* Retransmit unacked data in SYN */
-		tcp_for_write_queue_from(data, sk) {
-			if (data == tcp_send_head(sk) ||
-			    __tcp_retransmit_skb(sk, data, 1))
+		skb_rbtree_walk_from(data) {
+			if (__tcp_retransmit_skb(sk, data, 1))
 				break;
 		}
 		tcp_rearm_rto(sk);
@@ -5615,6 +5594,16 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 	return false;
 }
 
+static void smc_check_reset_syn(struct tcp_sock *tp)
+{
+#if IS_ENABLED(CONFIG_SMC)
+	if (static_branch_unlikely(&tcp_have_smc)) {
+		if (tp->syn_smc && !tp->rx_opt.smc_ok)
+			tp->syn_smc = 0;
+	}
+#endif
+}
+
 static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 					 const struct tcphdr *th)
 {
@@ -5710,10 +5699,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			tp->tcp_header_len = sizeof(struct tcphdr);
 		}
 
-		if (tcp_is_sack(tp) && sysctl_tcp_fack)
+		if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_fack)
 			tcp_enable_fack(tp);
 
-		tcp_mtup_init(sk);
 		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		tcp_initialize_rcv_mss(sk);
 
@@ -5722,6 +5710,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		 * is initialized. */
 		tp->copied_seq = tp->rcv_nxt;
 
+		smc_check_reset_syn(tp);
+
 		smp_mb();
 
 		tcp_finish_connect(sk, skb);
@@ -5939,15 +5929,18 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (req) {
 			inet_csk(sk)->icsk_retransmits = 0;
 			reqsk_fastopen_remove(sk, req, false);
+			/* Re-arm the timer because data may have been sent out.
+			 * This is similar to the regular data transmission case
+			 * when new data has just been ack'ed.
+			 *
+			 * (TFO) - we could try to be more aggressive and
+			 * retransmitting any data sooner based on when they
+			 * are sent out.
+			 */
+			tcp_rearm_rto(sk);
 		} else {
-			/* Make sure socket is routed, for correct metrics. */
-			icsk->icsk_af_ops->rebuild_header(sk);
-			tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
-			tcp_init_congestion_control(sk);
-
-			tcp_mtup_init(sk);
+			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
 			tp->copied_seq = tp->rcv_nxt;
-			tcp_init_buffer_space(sk);
 		}
 		smp_mb();
 		tcp_set_state(sk, TCP_ESTABLISHED);
@@ -5967,19 +5960,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (tp->rx_opt.tstamp_ok)
 			tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
 
-		if (req) {
-			/* Re-arm the timer because data may have been sent out.
-			 * This is similar to the regular data transmission case
-			 * when new data has just been ack'ed.
-			 *
-			 * (TFO) - we could try to be more aggressive and
-			 * retransmitting any data sooner based on when they
-			 * are sent out.
-			 */
-			tcp_rearm_rto(sk);
-		} else
-			tcp_init_metrics(sk);
-
 		if (!inet_csk(sk)->icsk_ca_ops->cong_control)
 			tcp_update_pacing_rate(sk);
 
@@ -6076,6 +6056,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	case TCP_LAST_ACK:
 		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
 			break;
+		/* fall through */
 	case TCP_FIN_WAIT1:
 	case TCP_FIN_WAIT2:
 		/* RFC 793 says to queue data in these states,
@@ -6184,6 +6165,9 @@ static void tcp_openreq_init(struct request_sock *req,
 	ireq->ir_rmt_port = tcp_hdr(skb)->source;
 	ireq->ir_num = ntohs(tcp_hdr(skb)->dest);
 	ireq->ir_mark = inet_request_mark(sk, skb);
+#if IS_ENABLED(CONFIG_SMC)
+	ireq->smc_ok = rx_opt->smc_ok;
+#endif
 }
 
 struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
@@ -6359,7 +6343,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	tcp_openreq_init_rwin(req, sk, dst);
 	if (!want_cookie) {
 		tcp_reqsk_record_syn(sk, req, skb);
-		fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc);
+		fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst);
 	}
 	if (fastopen_sk) {
 		af_ops->send_synack(fastopen_sk, dst, &fl, req,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5b027c69cbc5..0162c577bb9c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -85,6 +85,8 @@
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
+#include <trace/events/tcp.h>
+
 #ifdef CONFIG_TCP_MD5SIG
 static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 			       __be32 daddr, __be32 saddr, const struct tcphdr *th);
@@ -480,7 +482,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 					       TCP_TIMEOUT_INIT;
 		icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
 
-		skb = tcp_write_queue_head(sk);
+		skb = tcp_rtx_queue_head(sk);
 		BUG_ON(!skb);
 
 		tcp_mstamp_refresh(tp);
@@ -701,8 +703,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	 * routing might fail in this case. No choice here, if we choose to force
 	 * input interface, we will misroute in case of asymmetric route.
 	 */
-	if (sk)
+	if (sk) {
 		arg.bound_dev_if = sk->sk_bound_dev_if;
+		trace_tcp_send_reset(sk, skb);
+	}
 
 	BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
 		     offsetof(struct inet_timewait_sock, tw_bound_dev_if));
@@ -1783,8 +1787,9 @@ do_time_wait:
 			refcounted = false;
 			goto process;
 		}
-		/* Fall through to ACK */
 	}
+		/* to ACK */
+		/* fall through */
 	case TCP_TW_ACK:
 		tcp_v4_timewait_ack(sk, skb);
 		break;
@@ -1864,6 +1869,8 @@ void tcp_v4_destroy_sock(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	trace_tcp_destroy_sock(sk);
+
 	tcp_clear_xmit_timers(sk);
 
 	tcp_cleanup_congestion_control(sk);
@@ -1896,6 +1903,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 
 	/* If socket is aborted during connect operation */
 	tcp_free_fastopen_req(tp);
+	tcp_fastopen_destroy_cipher(sk);
 	tcp_saved_syn_free(tp);
 
 	sk_sockets_allocated_dec(sk);
@@ -2476,6 +2484,36 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_sack = 1;
 	net->ipv4.sysctl_tcp_window_scaling = 1;
 	net->ipv4.sysctl_tcp_timestamps = 1;
+	net->ipv4.sysctl_tcp_early_retrans = 3;
+	net->ipv4.sysctl_tcp_recovery = TCP_RACK_LOSS_DETECTION;
+	net->ipv4.sysctl_tcp_slow_start_after_idle = 1; /* By default, RFC2861 behavior.  */
+	net->ipv4.sysctl_tcp_retrans_collapse = 1;
+	net->ipv4.sysctl_tcp_max_reordering = 300;
+	net->ipv4.sysctl_tcp_dsack = 1;
+	net->ipv4.sysctl_tcp_app_win = 31;
+	net->ipv4.sysctl_tcp_adv_win_scale = 1;
+	net->ipv4.sysctl_tcp_frto = 2;
+	net->ipv4.sysctl_tcp_moderate_rcvbuf = 1;
+	/* This limits the percentage of the congestion window which we
+	 * will allow a single TSO frame to consume.  Building TSO frames
+	 * which are too large can cause TCP streams to be bursty.
+	 */
+	net->ipv4.sysctl_tcp_tso_win_divisor = 3;
+	/* Default TSQ limit of four TSO segments */
+	net->ipv4.sysctl_tcp_limit_output_bytes = 262144;
+	/* rfc5961 challenge ack rate limiting */
+	net->ipv4.sysctl_tcp_challenge_ack_limit = 1000;
+	net->ipv4.sysctl_tcp_min_tso_segs = 2;
+	net->ipv4.sysctl_tcp_min_rtt_wlen = 300;
+	net->ipv4.sysctl_tcp_autocorking = 1;
+	net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2;
+	net->ipv4.sysctl_tcp_pacing_ss_ratio = 200;
+	net->ipv4.sysctl_tcp_pacing_ca_ratio = 120;
+
+	net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
+	spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
+	net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;
+	atomic_set(&net->ipv4.tfo_active_disable_times, 0);
 
 	return 0;
 fail:
@@ -2486,7 +2524,12 @@ fail:
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
 {
+	struct net *net;
+
 	inet_twsk_purge(&tcp_hashinfo, AF_INET);
+
+	list_for_each_entry(net, net_exit_list, exit_list)
+		tcp_fastopen_ctx_destroy(net);
 }
 
 static struct pernet_operations __net_initdata tcp_sk_ops = {
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 0f0d740f6c8b..9d5ddebfd831 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -21,8 +21,6 @@
 #include <net/tcp.h>
 #include <net/genetlink.h>
 
-int sysctl_tcp_nometrics_save __read_mostly;
-
 static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *saddr,
 						   const struct inetpeer_addr *daddr,
 						   struct net *net, unsigned int hash);
@@ -331,7 +329,7 @@ void tcp_update_metrics(struct sock *sk)
 	int m;
 
 	sk_dst_confirm(sk);
-	if (sysctl_tcp_nometrics_save || !dst)
+	if (net->ipv4.sysctl_tcp_nometrics_save || !dst)
 		return;
 
 	rcu_read_lock();
@@ -893,10 +891,14 @@ static void tcp_metrics_flush_all(struct net *net)
 
 	for (row = 0; row < max_rows; row++, hb++) {
 		struct tcp_metrics_block __rcu **pp;
+		bool match;
+
 		spin_lock_bh(&tcp_metrics_lock);
 		pp = &hb->chain;
 		for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) {
-			if (net_eq(tm_net(tm), net)) {
+			match = net ? net_eq(tm_net(tm), net) :
+				!atomic_read(&tm_net(tm)->count);
+			if (match) {
 				*pp = tm->tcpm_next;
 				kfree_rcu(tm, rcu_head);
 			} else {
@@ -1019,14 +1021,14 @@ static int __net_init tcp_net_metrics_init(struct net *net)
 	return 0;
 }
 
-static void __net_exit tcp_net_metrics_exit(struct net *net)
+static void __net_exit tcp_net_metrics_exit_batch(struct list_head *net_exit_list)
 {
-	tcp_metrics_flush_all(net);
+	tcp_metrics_flush_all(NULL);
 }
 
 static __net_initdata struct pernet_operations tcp_net_metrics_ops = {
-	.init	=	tcp_net_metrics_init,
-	.exit	=	tcp_net_metrics_exit,
+	.init		=	tcp_net_metrics_init,
+	.exit_batch	=	tcp_net_metrics_exit_batch,
 };
 
 void __init tcp_metrics_init(void)
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 188a6f31356d..3c65c1a3f944 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -23,13 +23,12 @@
 #include <linux/slab.h>
 #include <linux/sysctl.h>
 #include <linux/workqueue.h>
+#include <linux/static_key.h>
 #include <net/tcp.h>
 #include <net/inet_common.h>
 #include <net/xfrm.h>
 #include <net/busy_poll.h>
 
-int sysctl_tcp_abort_on_overflow __read_mostly;
-
 static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
 {
 	if (seq == s_win)
@@ -180,7 +179,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 			 * Oh well... nobody has a sufficient solution to this
 			 * protocol bug yet.
 			 */
-			if (sysctl_tcp_rfc1337 == 0) {
+			if (twsk_net(tw)->ipv4.sysctl_tcp_rfc1337 == 0) {
 kill:
 				inet_twsk_deschedule_put(tw);
 				return TCP_TW_SUCCESS;
@@ -298,8 +297,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 			key = tp->af_specific->md5_lookup(sk, sk);
 			if (key) {
 				tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
-				if (tcptw->tw_md5_key && !tcp_alloc_md5sig_pool())
-					BUG();
+				BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool());
 			}
 		} while (0);
 #endif
@@ -371,7 +369,7 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 		full_space = rcv_wnd * mss;
 
 	/* tcp_full_space because it is guaranteed to be the first packet */
-	tcp_select_initial_window(full_space,
+	tcp_select_initial_window(sk_listener, full_space,
 		mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
 		&req->rsk_rcv_wnd,
 		&req->rsk_window_clamp,
@@ -417,6 +415,21 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
 }
 EXPORT_SYMBOL_GPL(tcp_ca_openreq_child);
 
+static void smc_check_reset_syn_req(struct tcp_sock *oldtp,
+				    struct request_sock *req,
+				    struct tcp_sock *newtp)
+{
+#if IS_ENABLED(CONFIG_SMC)
+	struct inet_request_sock *ireq;
+
+	if (static_branch_unlikely(&tcp_have_smc)) {
+		ireq = inet_rsk(req);
+		if (oldtp->syn_smc && !ireq->smc_ok)
+			newtp->syn_smc = 0;
+	}
+#endif
+}
+
 /* This is not only more efficient than what we used to do, it eliminates
  * a lot of code duplication between IPv4/IPv6 SYN recv processing. -DaveM
  *
@@ -434,6 +447,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		struct tcp_request_sock *treq = tcp_rsk(req);
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
 		struct tcp_sock *newtp = tcp_sk(newsk);
+		struct tcp_sock *oldtp = tcp_sk(sk);
+
+		smc_check_reset_syn_req(oldtp, req, newtp);
 
 		/* Now setup tcp_sock */
 		newtp->pred_flags = 0;
@@ -446,6 +462,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
 
 		INIT_LIST_HEAD(&newtp->tsq_node);
+		INIT_LIST_HEAD(&newtp->tsorted_sent_queue);
 
 		tcp_init_wl(newtp, treq->rcv_isn);
 
@@ -493,7 +510,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 
 		newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
 		if ((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) {
-			if (sysctl_tcp_fack)
+			if (sock_net(sk)->ipv4.sysctl_tcp_fack)
 				tcp_enable_fack(newtp);
 		}
 		newtp->window_clamp = req->rsk_window_clamp;
@@ -764,7 +781,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	return inet_csk_complete_hashdance(sk, child, req, own_req);
 
 listen_overflow:
-	if (!sysctl_tcp_abort_on_overflow) {
+	if (!sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow) {
 		inet_rsk(req)->acked = 1;
 		return NULL;
 	}
diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
index 125fc1450b01..0529e29e2941 100644
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -39,7 +39,7 @@
  * nv_cong_dec_mult	Decrease cwnd by X% (30%) of congestion when detected
  * nv_ssthresh_factor	On congestion set ssthresh to this * <desired cwnd> / 8
  * nv_rtt_factor	RTT averaging factor
- * nv_loss_dec_factor	Decrease cwnd by this (50%) when losses occur
+ * nv_loss_dec_factor	Decrease cwnd to this (80%) when losses occur
  * nv_dec_eval_min_calls	Wait this many RTT measurements before dec cwnd
  * nv_inc_eval_min_calls	Wait this many RTT measurements before inc cwnd
  * nv_ssthresh_eval_min_calls	Wait this many RTT measurements before stopping
@@ -61,7 +61,7 @@ static int nv_min_cwnd __read_mostly = 2;
 static int nv_cong_dec_mult __read_mostly = 30 * 128 / 100; /* = 30% */
 static int nv_ssthresh_factor __read_mostly = 8; /* = 1 */
 static int nv_rtt_factor __read_mostly = 128; /* = 1/2*old + 1/2*new */
-static int nv_loss_dec_factor __read_mostly = 512; /* => 50% */
+static int nv_loss_dec_factor __read_mostly = 819; /* => 80% */
 static int nv_cwnd_growth_rate_neg __read_mostly = 8;
 static int nv_cwnd_growth_rate_pos __read_mostly; /* 0 => fixed like Reno */
 static int nv_dec_eval_min_calls __read_mostly = 60;
@@ -101,6 +101,11 @@ struct tcpnv {
 	u32 nv_last_rtt;	/* last rtt */
 	u32 nv_min_rtt;		/* active min rtt. Used to determine slope */
 	u32 nv_min_rtt_new;	/* min rtt for future use */
+	u32 nv_base_rtt;        /* If non-zero it represents the threshold for
+				 * congestion */
+	u32 nv_lower_bound_rtt; /* Used in conjunction with nv_base_rtt. It is
+				 * set to 80% of nv_base_rtt. It helps reduce
+				 * unfairness between flows */
 	u32 nv_rtt_max_rate;	/* max rate seen during current RTT */
 	u32 nv_rtt_start_seq;	/* current RTT ends when packet arrives
 				 * acking beyond nv_rtt_start_seq */
@@ -132,9 +137,24 @@ static inline void tcpnv_reset(struct tcpnv *ca, struct sock *sk)
 static void tcpnv_init(struct sock *sk)
 {
 	struct tcpnv *ca = inet_csk_ca(sk);
+	int base_rtt;
 
 	tcpnv_reset(ca, sk);
 
+	/* See if base_rtt is available from socket_ops bpf program.
+	 * It is meant to be used in environments, such as communication
+	 * within a datacenter, where we have reasonable estimates of
+	 * RTTs
+	 */
+	base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT);
+	if (base_rtt > 0) {
+		ca->nv_base_rtt = base_rtt;
+		ca->nv_lower_bound_rtt = (base_rtt * 205) >> 8; /* 80% */
+	} else {
+		ca->nv_base_rtt = 0;
+		ca->nv_lower_bound_rtt = 0;
+	}
+
 	ca->nv_allow_cwnd_growth = 1;
 	ca->nv_min_rtt_reset_jiffies = jiffies + 2 * HZ;
 	ca->nv_min_rtt = NV_INIT_RTT;
@@ -144,6 +164,19 @@ static void tcpnv_init(struct sock *sk)
 	ca->cwnd_growth_factor = 0;
 }
 
+/* If provided, apply upper (base_rtt) and lower (lower_bound_rtt)
+ * bounds to RTT.
+ */
+inline u32 nv_get_bounded_rtt(struct tcpnv *ca, u32 val)
+{
+	if (ca->nv_lower_bound_rtt > 0 && val < ca->nv_lower_bound_rtt)
+		return ca->nv_lower_bound_rtt;
+	else if (ca->nv_base_rtt > 0 && val > ca->nv_base_rtt)
+		return ca->nv_base_rtt;
+	else
+		return val;
+}
+
 static void tcpnv_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -265,6 +298,9 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample)
 	if (ca->nv_eval_call_cnt < 255)
 		ca->nv_eval_call_cnt++;
 
+	/* Apply bounds to rtt. Only used to update min_rtt */
+	avg_rtt = nv_get_bounded_rtt(ca, avg_rtt);
+
 	/* update min rtt if necessary */
 	if (avg_rtt < ca->nv_min_rtt)
 		ca->nv_min_rtt = avg_rtt;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 478909f4694d..b98b2f7f07e7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -41,40 +41,25 @@
 #include <linux/compiler.h>
 #include <linux/gfp.h>
 #include <linux/module.h>
+#include <linux/static_key.h>
 
-/* People can turn this off for buggy TCP's found in printers etc. */
-int sysctl_tcp_retrans_collapse __read_mostly = 1;
-
-/* People can turn this on to work with those rare, broken TCPs that
- * interpret the window field as a signed quantity.
- */
-int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
-
-/* Default TSQ limit of four TSO segments */
-int sysctl_tcp_limit_output_bytes __read_mostly = 262144;
-
-/* This limits the percentage of the congestion window which we
- * will allow a single TSO frame to consume.  Building TSO frames
- * which are too large can cause TCP streams to be bursty.
- */
-int sysctl_tcp_tso_win_divisor __read_mostly = 3;
-
-/* By default, RFC2861 behavior.  */
-int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
+#include <trace/events/tcp.h>
 
 static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 			   int push_one, gfp_t gfp);
 
 /* Account for new data that has been sent to the network. */
-static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb)
+static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int prior_packets = tp->packets_out;
 
-	tcp_advance_send_head(sk, skb);
 	tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
 
+	__skb_unlink(skb, &sk->sk_write_queue);
+	tcp_rbtree_insert(&sk->tcp_rtx_queue, skb);
+
 	tp->packets_out += tcp_skb_pcount(skb);
 	if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
@@ -203,7 +188,7 @@ u32 tcp_default_init_rwnd(u32 mss)
  * be a multiple of mss if possible. We assume here that mss >= 1.
  * This MUST be enforced by all callers.
  */
-void tcp_select_initial_window(int __space, __u32 mss,
+void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 			       __u32 *rcv_wnd, __u32 *window_clamp,
 			       int wscale_ok, __u8 *rcv_wscale,
 			       __u32 init_rcv_wnd)
@@ -227,7 +212,7 @@ void tcp_select_initial_window(int __space, __u32 mss,
 	 * which we interpret as a sign the remote TCP is not
 	 * misinterpreting the window field as a signed quantity.
 	 */
-	if (sysctl_tcp_workaround_signed_windows)
+	if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
 		(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
 	else
 		(*rcv_wnd) = space;
@@ -287,7 +272,8 @@ static u16 tcp_select_window(struct sock *sk)
 	/* Make sure we do not exceed the maximum possible
 	 * scaled window.
 	 */
-	if (!tp->rx_opt.rcv_wscale && sysctl_tcp_workaround_signed_windows)
+	if (!tp->rx_opt.rcv_wscale &&
+	    sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
 		new_win = min(new_win, MAX_TCP_WINDOW);
 	else
 		new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
@@ -418,6 +404,22 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
 #define OPTION_MD5		(1 << 2)
 #define OPTION_WSCALE		(1 << 3)
 #define OPTION_FAST_OPEN_COOKIE	(1 << 8)
+#define OPTION_SMC		(1 << 9)
+
+static void smc_options_write(__be32 *ptr, u16 *options)
+{
+#if IS_ENABLED(CONFIG_SMC)
+	if (static_branch_unlikely(&tcp_have_smc)) {
+		if (unlikely(OPTION_SMC & *options)) {
+			*ptr++ = htonl((TCPOPT_NOP  << 24) |
+				       (TCPOPT_NOP  << 16) |
+				       (TCPOPT_EXP <<  8) |
+				       (TCPOLEN_EXP_SMC_BASE));
+			*ptr++ = htonl(TCPOPT_SMC_MAGIC);
+		}
+	}
+#endif
+}
 
 struct tcp_out_options {
 	u16 options;		/* bit field of OPTION_* */
@@ -536,6 +538,41 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 		}
 		ptr += (len + 3) >> 2;
 	}
+
+	smc_options_write(ptr, &options);
+}
+
+static void smc_set_option(const struct tcp_sock *tp,
+			   struct tcp_out_options *opts,
+			   unsigned int *remaining)
+{
+#if IS_ENABLED(CONFIG_SMC)
+	if (static_branch_unlikely(&tcp_have_smc)) {
+		if (tp->syn_smc) {
+			if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) {
+				opts->options |= OPTION_SMC;
+				*remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED;
+			}
+		}
+	}
+#endif
+}
+
+static void smc_set_option_cond(const struct tcp_sock *tp,
+				const struct inet_request_sock *ireq,
+				struct tcp_out_options *opts,
+				unsigned int *remaining)
+{
+#if IS_ENABLED(CONFIG_SMC)
+	if (static_branch_unlikely(&tcp_have_smc)) {
+		if (tp->syn_smc && ireq->smc_ok) {
+			if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) {
+				opts->options |= OPTION_SMC;
+				*remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED;
+			}
+		}
+	}
+#endif
 }
 
 /* Compute TCP options for SYN packets. This is not the final
@@ -603,11 +640,14 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
+	smc_set_option(tp, opts, &remaining);
+
 	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
 /* Set up TCP options for SYN-ACKs. */
-static unsigned int tcp_synack_options(struct request_sock *req,
+static unsigned int tcp_synack_options(const struct sock *sk,
+				       struct request_sock *req,
 				       unsigned int mss, struct sk_buff *skb,
 				       struct tcp_out_options *opts,
 				       const struct tcp_md5sig_key *md5,
@@ -663,6 +703,8 @@ static unsigned int tcp_synack_options(struct request_sock *req,
 		}
 	}
 
+	smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
+
 	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
@@ -973,6 +1015,12 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
 		      HRTIMER_MODE_ABS_PINNED);
 }
 
+static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
+{
+	skb->skb_mstamp = tp->tcp_mstamp;
+	list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
+}
+
 /* This routine actually transmits TCP packets queued in by
  * tcp_do_sendmsg().  This is used by both the initial
  * transmission and possible later retransmissions.
@@ -1005,10 +1053,14 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
 			- tp->snd_una;
 		oskb = skb;
-		if (unlikely(skb_cloned(skb)))
-			skb = pskb_copy(skb, gfp_mask);
-		else
-			skb = skb_clone(skb, gfp_mask);
+
+		tcp_skb_tsorted_save(oskb) {
+			if (unlikely(skb_cloned(oskb)))
+				skb = pskb_copy(oskb, gfp_mask);
+			else
+				skb = skb_clone(oskb, gfp_mask);
+		} tcp_skb_tsorted_restore(oskb);
+
 		if (unlikely(!skb))
 			return -ENOBUFS;
 	}
@@ -1129,7 +1181,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		err = net_xmit_eval(err);
 	}
 	if (!err && oskb) {
-		oskb->skb_mstamp = tp->tcp_mstamp;
+		tcp_update_skb_after_send(tp, oskb);
 		tcp_rate_skb_sent(sk, oskb);
 	}
 	return err;
@@ -1241,12 +1293,25 @@ static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2)
 	TCP_SKB_CB(skb)->eor = 0;
 }
 
+/* Insert buff after skb on the write or rtx queue of sk.  */
+static void tcp_insert_write_queue_after(struct sk_buff *skb,
+					 struct sk_buff *buff,
+					 struct sock *sk,
+					 enum tcp_queue tcp_queue)
+{
+	if (tcp_queue == TCP_FRAG_IN_WRITE_QUEUE)
+		__skb_queue_after(&sk->sk_write_queue, skb, buff);
+	else
+		tcp_rbtree_insert(&sk->tcp_rtx_queue, buff);
+}
+
 /* Function to create two new TCP segments.  Shrinks the given segment
  * to the specified size and appends a new segment with the rest of the
  * packet to the list.  This won't be called frequently, I hope.
  * Remember, these are still headerless SKBs at this point.
  */
-int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
+int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
+		 struct sk_buff *skb, u32 len,
 		 unsigned int mss_now, gfp_t gfp)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -1329,7 +1394,9 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 
 	/* Link BUFF into the send queue. */
 	__skb_header_release(buff);
-	tcp_insert_write_queue_after(skb, buff, sk);
+	tcp_insert_write_queue_after(skb, buff, sk, tcp_queue);
+	if (tcp_queue == TCP_FRAG_IN_RTX_QUEUE)
+		list_add(&buff->tcp_tsorted_anchor, &skb->tcp_tsorted_anchor);
 
 	return 0;
 }
@@ -1607,7 +1674,7 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
 		if (tp->packets_out > tp->snd_cwnd_used)
 			tp->snd_cwnd_used = tp->packets_out;
 
-		if (sysctl_tcp_slow_start_after_idle &&
+		if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle &&
 		    (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto &&
 		    !ca_ops->cong_control)
 			tcp_cwnd_application_limited(sk);
@@ -1616,10 +1683,10 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
 		 * is caused by insufficient sender buffer:
 		 * 1) just sent some data (see tcp_write_xmit)
 		 * 2) not cwnd limited (this else condition)
-		 * 3) no more data to send (null tcp_send_head )
+		 * 3) no more data to send (tcp_write_queue_empty())
 		 * 4) application is hitting buffer limit (SOCK_NOSPACE)
 		 */
-		if (!tcp_send_head(sk) && sk->sk_socket &&
+		if (tcp_write_queue_empty(sk) && sk->sk_socket &&
 		    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags) &&
 		    (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))
 			tcp_chrono_start(sk, TCP_CHRONO_SNDBUF_LIMITED);
@@ -1694,7 +1761,8 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
 	u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0;
 
 	return tso_segs ? :
-		tcp_tso_autosize(sk, mss_now, sysctl_tcp_min_tso_segs);
+		tcp_tso_autosize(sk, mss_now,
+				 sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
 }
 
 /* Returns the portion of skb which can be sent right away */
@@ -1815,7 +1883,8 @@ static bool tcp_snd_wnd_test(const struct tcp_sock *tp,
  * know that all the data is in scatter-gather pages, and that the
  * packet has never been sent out before (and thus is not cloned).
  */
-static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
+static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue,
+			struct sk_buff *skb, unsigned int len,
 			unsigned int mss_now, gfp_t gfp)
 {
 	struct sk_buff *buff;
@@ -1824,7 +1893,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 
 	/* All of a TSO frame must be composed of paged data.  */
 	if (skb->len != skb->data_len)
-		return tcp_fragment(sk, skb, len, mss_now, gfp);
+		return tcp_fragment(sk, tcp_queue, skb, len, mss_now, gfp);
 
 	buff = sk_stream_alloc_skb(sk, 0, gfp, true);
 	if (unlikely(!buff))
@@ -1860,7 +1929,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 
 	/* Link BUFF into the send queue. */
 	__skb_header_release(buff);
-	tcp_insert_write_queue_after(skb, buff, sk);
+	tcp_insert_write_queue_after(skb, buff, sk, tcp_queue);
 
 	return 0;
 }
@@ -1910,7 +1979,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
 		goto send_now;
 
-	win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor);
+	win_divisor = ACCESS_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_win_divisor);
 	if (win_divisor) {
 		u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
 
@@ -1930,8 +1999,10 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 			goto send_now;
 	}
 
-	head = tcp_write_queue_head(sk);
-
+	/* TODO : use tsorted_sent_queue ? */
+	head = tcp_rtx_queue_head(sk);
+	if (!head)
+		goto send_now;
 	age = tcp_stamp_us_delta(tp->tcp_mstamp, head->skb_mstamp);
 	/* If next ACK is likely to come too late (half srtt), do not defer */
 	if (age < (tp->srtt_us >> 4))
@@ -2146,17 +2217,17 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 	unsigned int limit;
 
 	limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10);
-	limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes);
+	limit = min_t(u32, limit,
+		      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
 	limit <<= factor;
 
 	if (refcount_read(&sk->sk_wmem_alloc) > limit) {
-		/* Always send the 1st or 2nd skb in write queue.
+		/* Always send skb if rtx queue is empty.
 		 * No need to wait for TX completion to call us back,
 		 * after softirq/tasklet schedule.
 		 * This helps when TX completions are delayed too much.
 		 */
-		if (skb == sk->sk_write_queue.next ||
-		    skb->prev == sk->sk_write_queue.next)
+		if (tcp_rtx_queue_empty(sk))
 			return false;
 
 		set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
@@ -2207,7 +2278,7 @@ void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type)
 	 * it's the "most interesting" or current chrono we are
 	 * tracking and starts busy chrono if we have pending data.
 	 */
-	if (tcp_write_queue_empty(sk))
+	if (tcp_rtx_and_write_queues_empty(sk))
 		tcp_chrono_set(tp, TCP_CHRONO_UNSPEC);
 	else if (type == tp->chrono_type)
 		tcp_chrono_set(tp, TCP_CHRONO_BUSY);
@@ -2263,7 +2334,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
 			/* "skb_mstamp" is used as a start point for the retransmit timer */
-			skb->skb_mstamp = tp->tcp_mstamp;
+			tcp_update_skb_after_send(tp, skb);
 			goto repair; /* Skip network transmission */
 		}
 
@@ -2302,7 +2373,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 						    nonagle);
 
 		if (skb->len > limit &&
-		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
+		    unlikely(tso_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE,
+					  skb, limit, mss_now, gfp)))
 			break;
 
 		if (test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags))
@@ -2342,7 +2414,7 @@ repair:
 		tcp_cwnd_validate(sk, is_cwnd_limited);
 		return false;
 	}
-	return !tp->packets_out && tcp_send_head(sk);
+	return !tp->packets_out && !tcp_write_queue_empty(sk);
 }
 
 bool tcp_schedule_loss_probe(struct sock *sk)
@@ -2350,6 +2422,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 timeout, rto_delta_us;
+	int early_retrans;
 
 	/* Don't do any loss probe on a Fast Open connection before 3WHS
 	 * finishes.
@@ -2357,16 +2430,17 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	if (tp->fastopen_rsk)
 		return false;
 
+	early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans;
 	/* Schedule a loss probe in 2*RTT for SACK capable connections
 	 * in Open state, that are either limited by cwnd or application.
 	 */
-	if ((sysctl_tcp_early_retrans != 3 && sysctl_tcp_early_retrans != 4) ||
+	if ((early_retrans != 3 && early_retrans != 4) ||
 	    !tp->packets_out || !tcp_is_sack(tp) ||
 	    icsk->icsk_ca_state != TCP_CA_Open)
 		return false;
 
 	if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) &&
-	     tcp_send_head(sk))
+	     !tcp_write_queue_empty(sk))
 		return false;
 
 	/* Probe timeout is 2*rtt. Add minimum RTO to account
@@ -2419,18 +2493,14 @@ void tcp_send_loss_probe(struct sock *sk)
 	int mss = tcp_current_mss(sk);
 
 	skb = tcp_send_head(sk);
-	if (skb) {
-		if (tcp_snd_wnd_test(tp, skb, mss)) {
-			pcount = tp->packets_out;
-			tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
-			if (tp->packets_out > pcount)
-				goto probe_sent;
-			goto rearm_timer;
-		}
-		skb = tcp_write_queue_prev(sk, skb);
-	} else {
-		skb = tcp_write_queue_tail(sk);
+	if (skb && tcp_snd_wnd_test(tp, skb, mss)) {
+		pcount = tp->packets_out;
+		tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
+		if (tp->packets_out > pcount)
+			goto probe_sent;
+		goto rearm_timer;
 	}
+	skb = skb_rb_last(&sk->tcp_rtx_queue);
 
 	/* At most one outstanding TLP retransmission. */
 	if (tp->tlp_high_seq)
@@ -2448,10 +2518,11 @@ void tcp_send_loss_probe(struct sock *sk)
 		goto rearm_timer;
 
 	if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) {
-		if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss,
+		if (unlikely(tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
+					  (pcount - 1) * mss, mss,
 					  GFP_ATOMIC)))
 			goto rearm_timer;
-		skb = tcp_write_queue_next(sk, skb);
+		skb = skb_rb_next(skb);
 	}
 
 	if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
@@ -2651,7 +2722,7 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb,
 static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *next_skb = tcp_write_queue_next(sk, skb);
+	struct sk_buff *next_skb = skb_rb_next(skb);
 	int skb_size, next_skb_size;
 
 	skb_size = skb->len;
@@ -2668,8 +2739,6 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 	}
 	tcp_highest_sack_replace(sk, next_skb, skb);
 
-	tcp_unlink_write_queue(next_skb, sk);
-
 	if (next_skb->ip_summed == CHECKSUM_PARTIAL)
 		skb->ip_summed = CHECKSUM_PARTIAL;
 
@@ -2697,7 +2766,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 
 	tcp_skb_collapse_tstamp(skb, next_skb);
 
-	sk_wmem_free_skb(sk, next_skb);
+	tcp_rtx_queue_unlink_and_free(next_skb, sk);
 	return true;
 }
 
@@ -2708,8 +2777,6 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb)
 		return false;
 	if (skb_cloned(skb))
 		return false;
-	if (skb == tcp_send_head(sk))
-		return false;
 	/* Some heuristics for collapsing over SACK'd could be invented */
 	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
 		return false;
@@ -2727,12 +2794,12 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
 	struct sk_buff *skb = to, *tmp;
 	bool first = true;
 
-	if (!sysctl_tcp_retrans_collapse)
+	if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)
 		return;
 	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 		return;
 
-	tcp_for_write_queue_from_safe(skb, tmp, sk) {
+	skb_rbtree_walk_from_safe(skb, tmp) {
 		if (!tcp_can_collapse(sk, skb))
 			break;
 
@@ -2807,7 +2874,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 
 	len = cur_mss * segs;
 	if (skb->len > len) {
-		if (tcp_fragment(sk, skb, len, cur_mss, GFP_ATOMIC))
+		if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len,
+				 cur_mss, GFP_ATOMIC))
 			return -ENOMEM; /* We'll try again later. */
 	} else {
 		if (skb_unclone(skb, GFP_ATOMIC))
@@ -2841,11 +2909,14 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb;
 
-		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
-		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-			     -ENOBUFS;
+		tcp_skb_tsorted_save(skb) {
+			nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
+			err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+				     -ENOBUFS;
+		} tcp_skb_tsorted_restore(skb);
+
 		if (!err) {
-			skb->skb_mstamp = tp->tcp_mstamp;
+			tcp_update_skb_after_send(tp, skb);
 			tcp_rate_skb_sent(sk, skb);
 		}
 	} else {
@@ -2854,6 +2925,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 
 	if (likely(!err)) {
 		TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
+		trace_tcp_retransmit_skb(sk, skb);
 	} else if (err != -EBUSY) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
 	}
@@ -2897,29 +2969,21 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 void tcp_xmit_retransmit_queue(struct sock *sk)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct sk_buff *skb, *rtx_head, *hole = NULL;
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb;
-	struct sk_buff *hole = NULL;
 	u32 max_segs;
 	int mib_idx;
 
 	if (!tp->packets_out)
 		return;
 
-	if (tp->retransmit_skb_hint) {
-		skb = tp->retransmit_skb_hint;
-	} else {
-		skb = tcp_write_queue_head(sk);
-	}
-
+	rtx_head = tcp_rtx_queue_head(sk);
+	skb = tp->retransmit_skb_hint ?: rtx_head;
 	max_segs = tcp_tso_segs(sk, tcp_current_mss(sk));
-	tcp_for_write_queue_from(skb, sk) {
+	skb_rbtree_walk_from(skb) {
 		__u8 sacked;
 		int segs;
 
-		if (skb == tcp_send_head(sk))
-			break;
-
 		if (tcp_pacing_check(sk))
 			break;
 
@@ -2964,7 +3028,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 		if (tcp_in_cwnd_reduction(sk))
 			tp->prr_out += tcp_skb_pcount(skb);
 
-		if (skb == tcp_write_queue_head(sk) &&
+		if (skb == rtx_head &&
 		    icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT)
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 						  inet_csk(sk)->icsk_rto,
@@ -3006,12 +3070,15 @@ void tcp_send_fin(struct sock *sk)
 	 * Note: in the latter case, FIN packet will be sent after a timeout,
 	 * as TCP stack thinks it has already been transmitted.
 	 */
-	if (tskb && (tcp_send_head(sk) || tcp_under_memory_pressure(sk))) {
+	if (!tskb && tcp_under_memory_pressure(sk))
+		tskb = skb_rb_last(&sk->tcp_rtx_queue);
+
+	if (tskb) {
 coalesce:
 		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
 		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
-		if (!tcp_send_head(sk)) {
+		if (tcp_write_queue_empty(sk)) {
 			/* This means tskb was already sent.
 			 * Pretend we included the FIN on previous transmit.
 			 * We need to set tp->snd_nxt to the value it would have
@@ -3028,6 +3095,7 @@ coalesce:
 				goto coalesce;
 			return;
 		}
+		INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
 		skb_reserve(skb, MAX_TCP_HEADER);
 		sk_forced_mem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
@@ -3064,6 +3132,11 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	/* Send it off. */
 	if (tcp_transmit_skb(sk, skb, 0, priority))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
+
+	/* skb of trace_tcp_send_reset() keeps the skb that caused RST,
+	 * skb here is different to the troublesome skb, so use NULL
+	 */
+	trace_tcp_send_reset(sk, NULL);
 }
 
 /* Send a crossed SYN-ACK during socket establishment.
@@ -3076,20 +3149,24 @@ int tcp_send_synack(struct sock *sk)
 {
 	struct sk_buff *skb;
 
-	skb = tcp_write_queue_head(sk);
+	skb = tcp_rtx_queue_head(sk);
 	if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
-		pr_debug("%s: wrong queue state\n", __func__);
+		pr_err("%s: wrong queue state\n", __func__);
 		return -EFAULT;
 	}
 	if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) {
 		if (skb_cloned(skb)) {
-			struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC);
+			struct sk_buff *nskb;
+
+			tcp_skb_tsorted_save(skb) {
+				nskb = skb_copy(skb, GFP_ATOMIC);
+			} tcp_skb_tsorted_restore(skb);
 			if (!nskb)
 				return -ENOMEM;
-			tcp_unlink_write_queue(skb, sk);
+			INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor);
+			tcp_rtx_queue_unlink_and_free(skb, sk);
 			__skb_header_release(nskb);
-			__tcp_add_write_queue_head(sk, nskb);
-			sk_wmem_free_skb(sk, skb);
+			tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb);
 			sk->sk_wmem_queued += nskb->truesize;
 			sk_mem_charge(sk, nskb->truesize);
 			skb = nskb;
@@ -3166,8 +3243,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
 #endif
 	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
-	tcp_header_size = tcp_synack_options(req, mss, skb, &opts, md5, foc) +
-			  sizeof(*th);
+	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
+					     foc) + sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
@@ -3268,7 +3345,7 @@ static void tcp_connect_init(struct sock *sk)
 	if (rcv_wnd == 0)
 		rcv_wnd = dst_metric(dst, RTAX_INITRWND);
 
-	tcp_select_initial_window(tcp_full_space(sk),
+	tcp_select_initial_window(sk, tcp_full_space(sk),
 				  tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
 				  &tp->rcv_wnd,
 				  &tp->window_clamp,
@@ -3307,7 +3384,6 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
 
 	tcb->end_seq += skb->len;
 	__skb_header_release(skb);
-	__tcp_add_write_queue_tail(sk, skb);
 	sk->sk_wmem_queued += skb->truesize;
 	sk_mem_charge(sk, skb->truesize);
 	tp->write_seq = tcb->end_seq;
@@ -3355,6 +3431,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		int copied = copy_from_iter(skb_put(syn_data, space), space,
 					    &fo->data->msg_iter);
 		if (unlikely(!copied)) {
+			tcp_skb_tsorted_anchor_cleanup(syn_data);
 			kfree_skb(syn_data);
 			goto fallback;
 		}
@@ -3385,12 +3462,13 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH;
 	if (!err) {
 		tp->syn_data = (fo->copied > 0);
+		tcp_rbtree_insert(&sk->tcp_rtx_queue, syn_data);
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT);
 		goto done;
 	}
 
-	/* data was not sent, this is our new send_head */
-	sk->sk_send_head = syn_data;
+	/* data was not sent, put it in write_queue */
+	__skb_queue_tail(&sk->sk_write_queue, syn_data);
 	tp->packets_out -= tcp_skb_pcount(syn_data);
 
 fallback:
@@ -3433,6 +3511,7 @@ int tcp_connect(struct sock *sk)
 	tp->retrans_stamp = tcp_time_stamp(tp);
 	tcp_connect_queue_skb(sk, buff);
 	tcp_ecn_send_syn(sk, buff);
+	tcp_rbtree_insert(&sk->tcp_rtx_queue, buff);
 
 	/* Send off SYN; include data in Fast Open. */
 	err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) :
@@ -3627,7 +3706,8 @@ int tcp_write_wakeup(struct sock *sk, int mib)
 		    skb->len > mss) {
 			seg_size = min(seg_size, mss);
 			TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
-			if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC))
+			if (tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE,
+					 skb, seg_size, mss, GFP_ATOMIC))
 				return -1;
 		} else if (!tcp_skb_pcount(skb))
 			tcp_set_skb_tso_segs(skb, mss);
@@ -3657,7 +3737,7 @@ void tcp_send_probe0(struct sock *sk)
 
 	err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE);
 
-	if (tp->packets_out || !tcp_send_head(sk)) {
+	if (tp->packets_out || tcp_write_queue_empty(sk)) {
 		/* Cancel probe timer, if it is not required. */
 		icsk->icsk_probes_out = 0;
 		icsk->icsk_backoff = 0;
@@ -3698,6 +3778,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
 		if (unlikely(tcp_passive_fastopen(sk)))
 			tcp_sk(sk)->total_retrans++;
+		trace_tcp_retransmit_synack(sk, req);
 	}
 	return res;
 }
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index be8ef1e5dfef..ac3e9c6d3a3d 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -2,8 +2,6 @@
 #include <linux/tcp.h>
 #include <net/tcp.h>
 
-int sysctl_tcp_recovery __read_mostly = TCP_RACK_LOSS_DETECTION;
-
 static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -46,7 +44,7 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
 static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb;
+	struct sk_buff *skb, *n;
 	u32 reo_wnd;
 
 	*reo_timeout = 0;
@@ -59,45 +57,31 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 	if ((tp->rack.reord || !tp->lost_out) && tcp_min_rtt(tp) != ~0U)
 		reo_wnd = max(tcp_min_rtt(tp) >> 2, reo_wnd);
 
-	tcp_for_write_queue(skb, sk) {
+	list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue,
+				 tcp_tsorted_anchor) {
 		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
+		s32 remaining;
 
-		if (skb == tcp_send_head(sk))
-			break;
-
-		/* Skip ones already (s)acked */
-		if (!after(scb->end_seq, tp->snd_una) ||
-		    scb->sacked & TCPCB_SACKED_ACKED)
+		/* Skip ones marked lost but not yet retransmitted */
+		if ((scb->sacked & TCPCB_LOST) &&
+		    !(scb->sacked & TCPCB_SACKED_RETRANS))
 			continue;
 
-		if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp,
-					tp->rack.end_seq, scb->end_seq)) {
-			/* Step 3 in draft-cheng-tcpm-rack-00.txt:
-			 * A packet is lost if its elapsed time is beyond
-			 * the recent RTT plus the reordering window.
-			 */
-			u32 elapsed = tcp_stamp_us_delta(tp->tcp_mstamp,
-							 skb->skb_mstamp);
-			s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed;
-
-			if (remaining < 0) {
-				tcp_rack_mark_skb_lost(sk, skb);
-				continue;
-			}
-
-			/* Skip ones marked lost but not yet retransmitted */
-			if ((scb->sacked & TCPCB_LOST) &&
-			    !(scb->sacked & TCPCB_SACKED_RETRANS))
-				continue;
+		if (!tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp,
+					 tp->rack.end_seq, scb->end_seq))
+			break;
 
+		/* A packet is lost if it has not been s/acked beyond
+		 * the recent RTT plus the reordering window.
+		 */
+		remaining = tp->rack.rtt_us + reo_wnd -
+			    tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp);
+		if (remaining < 0) {
+			tcp_rack_mark_skb_lost(sk, skb);
+			list_del_init(&skb->tcp_tsorted_anchor);
+		} else {
 			/* Record maximum wait time (+1 to avoid 0) */
 			*reo_timeout = max_t(u32, *reo_timeout, 1 + remaining);
-
-		} else if (!(scb->sacked & TCPCB_RETRANS)) {
-			/* Original data are sent sequentially so stop early
-			 * b/c the rest are all sent after rack_sent
-			 */
-			break;
 		}
 	}
 }
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 655dd8d7f064..035a1ef1f2d8 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -22,8 +22,6 @@
 #include <linux/gfp.h>
 #include <net/tcp.h>
 
-int sysctl_tcp_thin_linear_timeouts __read_mostly;
-
 /**
  *  tcp_write_err() - close socket and save error info
  *  @sk:  The socket the error has appeared on.
@@ -156,8 +154,13 @@ static bool retransmits_timed_out(struct sock *sk,
 		return false;
 
 	start_ts = tcp_sk(sk)->retrans_stamp;
-	if (unlikely(!start_ts))
-		start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk));
+	if (unlikely(!start_ts)) {
+		struct sk_buff *head = tcp_rtx_queue_head(sk);
+
+		if (!head)
+			return false;
+		start_ts = tcp_skb_timestamp(head);
+	}
 
 	if (likely(timeout == 0)) {
 		linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);
@@ -283,15 +286,17 @@ out:
  *
  *  Returns: Nothing (void)
  */
-static void tcp_delack_timer(unsigned long data)
+static void tcp_delack_timer(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)data;
+	struct inet_connection_sock *icsk =
+			from_timer(icsk, t, icsk_delack_timer);
+	struct sock *sk = &icsk->icsk_inet.sk;
 
 	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk)) {
 		tcp_delack_timer_handler(sk);
 	} else {
-		inet_csk(sk)->icsk_ack.blocked = 1;
+		icsk->icsk_ack.blocked = 1;
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
 		/* deleguate our work to tcp_release_cb() */
 		if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags))
@@ -304,11 +309,12 @@ static void tcp_delack_timer(unsigned long data)
 static void tcp_probe_timer(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct sk_buff *skb = tcp_send_head(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int max_probes;
 	u32 start_ts;
 
-	if (tp->packets_out || !tcp_send_head(sk)) {
+	if (tp->packets_out || !skb) {
 		icsk->icsk_probes_out = 0;
 		return;
 	}
@@ -321,9 +327,9 @@ static void tcp_probe_timer(struct sock *sk)
 	 * corresponding system limit. We also implement similar policy when
 	 * we use RTO to probe window in tcp_retransmit_timer().
 	 */
-	start_ts = tcp_skb_timestamp(tcp_send_head(sk));
+	start_ts = tcp_skb_timestamp(skb);
 	if (!start_ts)
-		tcp_send_head(sk)->skb_mstamp = tp->tcp_mstamp;
+		skb->skb_mstamp = tp->tcp_mstamp;
 	else if (icsk->icsk_user_timeout &&
 		 (s32)(tcp_time_stamp(tp) - start_ts) >
 		 jiffies_to_msecs(icsk->icsk_user_timeout))
@@ -408,7 +414,7 @@ void tcp_retransmit_timer(struct sock *sk)
 	if (!tp->packets_out)
 		goto out;
 
-	WARN_ON(tcp_write_queue_empty(sk));
+	WARN_ON(tcp_rtx_queue_empty(sk));
 
 	tp->tlp_high_seq = 0;
 
@@ -441,7 +447,7 @@ void tcp_retransmit_timer(struct sock *sk)
 			goto out;
 		}
 		tcp_enter_loss(sk);
-		tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1);
+		tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1);
 		__sk_dst_reset(sk);
 		goto out_reset_timer;
 	}
@@ -473,7 +479,7 @@ void tcp_retransmit_timer(struct sock *sk)
 
 	tcp_enter_loss(sk);
 
-	if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1) > 0) {
+	if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) {
 		/* Retransmission failed because of local congestion,
 		 * do not backoff.
 		 */
@@ -514,7 +520,7 @@ out_reset_timer:
 	 * linear-timeout retransmissions into a black hole
 	 */
 	if (sk->sk_state == TCP_ESTABLISHED &&
-	    (tp->thin_lto || sysctl_tcp_thin_linear_timeouts) &&
+	    (tp->thin_lto || net->ipv4.sysctl_tcp_thin_linear_timeouts) &&
 	    tcp_stream_is_thin(tp) &&
 	    icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
 		icsk->icsk_backoff = 0;
@@ -570,9 +576,11 @@ out:
 	sk_mem_reclaim(sk);
 }
 
-static void tcp_write_timer(unsigned long data)
+static void tcp_write_timer(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)data;
+	struct inet_connection_sock *icsk =
+			from_timer(icsk, t, icsk_retransmit_timer);
+	struct sock *sk = &icsk->icsk_inet.sk;
 
 	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk)) {
@@ -607,9 +615,9 @@ void tcp_set_keepalive(struct sock *sk, int val)
 EXPORT_SYMBOL_GPL(tcp_set_keepalive);
 
 
-static void tcp_keepalive_timer (unsigned long data)
+static void tcp_keepalive_timer (struct timer_list *t)
 {
-	struct sock *sk = (struct sock *) data;
+	struct sock *sk = from_timer(sk, t, sk_timer);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 elapsed;
@@ -647,7 +655,7 @@ static void tcp_keepalive_timer (unsigned long data)
 	elapsed = keepalive_time_when(tp);
 
 	/* It is alive without keepalive 8) */
-	if (tp->packets_out || tcp_send_head(sk))
+	if (tp->packets_out || !tcp_write_queue_empty(sk))
 		goto resched;
 
 	elapsed = keepalive_time_elapsed(tp);
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 218cfcc77650..ee113ff15fd0 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -158,7 +158,7 @@ EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event);
 
 static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp)
 {
-	return  min(tp->snd_ssthresh, tp->snd_cwnd-1);
+	return  min(tp->snd_ssthresh, tp->snd_cwnd);
 }
 
 static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ebfbccae62fd..a6699af05539 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1209,8 +1209,7 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
 	if (likely(partial)) {
 		up->forward_deficit += size;
 		size = up->forward_deficit;
-		if (size < (sk->sk_rcvbuf >> 2) &&
-		    !skb_queue_empty(&up->reader_queue))
+		if (size < (sk->sk_rcvbuf >> 2))
 			return;
 	} else {
 		size += up->forward_deficit;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8a1c846d3df9..69b8cdb43aa2 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -152,7 +152,7 @@ static void ipv6_regen_rndid(struct inet6_dev *idev);
 static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
 
 static int ipv6_generate_eui64(u8 *eui, struct net_device *dev);
-static int ipv6_count_addresses(struct inet6_dev *idev);
+static int ipv6_count_addresses(const struct inet6_dev *idev);
 static int ipv6_generate_stable_address(struct in6_addr *addr,
 					u8 dad_count,
 					const struct inet6_dev *idev);
@@ -192,8 +192,6 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
 
 static void inet6_prefix_notify(int event, struct inet6_dev *idev,
 				struct prefix_info *pinfo);
-static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
-			       struct net_device *dev);
 
 static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.forwarding		= 0,
@@ -303,10 +301,10 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.disable_policy		= 0,
 };
 
-/* Check if a valid qdisc is available */
-static inline bool addrconf_qdisc_ok(const struct net_device *dev)
+/* Check if link is ready: is it up and is a valid qdisc available */
+static inline bool addrconf_link_ready(const struct net_device *dev)
 {
-	return !qdisc_tx_is_noop(dev);
+	return netif_oper_up(dev) && !qdisc_tx_is_noop(dev);
 }
 
 static void addrconf_del_rs_timer(struct inet6_dev *idev)
@@ -451,7 +449,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 
 	ndev->token = in6addr_any;
 
-	if (netif_running(dev) && addrconf_qdisc_ok(dev))
+	if (netif_running(dev) && addrconf_link_ready(dev))
 		ndev->if_flags |= IF_READY;
 
 	ipv6_mc_init_dev(ndev);
@@ -616,23 +614,23 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[NETCONFA_MAX+1];
+	struct inet6_dev *in6_dev = NULL;
+	struct net_device *dev = NULL;
 	struct netconfmsg *ncm;
 	struct sk_buff *skb;
 	struct ipv6_devconf *devconf;
-	struct inet6_dev *in6_dev;
-	struct net_device *dev;
 	int ifindex;
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX,
 			  devconf_ipv6_policy, extack);
 	if (err < 0)
-		goto errout;
+		return err;
 
-	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
-		goto errout;
+		return -EINVAL;
 
+	err = -EINVAL;
 	ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]);
 	switch (ifindex) {
 	case NETCONFA_IFINDEX_ALL:
@@ -642,10 +640,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 		devconf = net->ipv6.devconf_dflt;
 		break;
 	default:
-		dev = __dev_get_by_index(net, ifindex);
+		dev = dev_get_by_index(net, ifindex);
 		if (!dev)
-			goto errout;
-		in6_dev = __in6_dev_get(dev);
+			return -EINVAL;
+		in6_dev = in6_dev_get(dev);
 		if (!in6_dev)
 			goto errout;
 		devconf = &in6_dev->cnf;
@@ -653,7 +651,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 	}
 
 	err = -ENOBUFS;
-	skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_ATOMIC);
+	skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL);
 	if (!skb)
 		goto errout;
 
@@ -669,6 +667,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 	}
 	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
 errout:
+	if (in6_dev)
+		in6_dev_put(in6_dev);
+	if (dev)
+		dev_put(dev);
 	return err;
 }
 
@@ -945,12 +947,50 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp)
 			break;
 	}
 
-	list_add_tail(&ifp->if_list, p);
+	list_add_tail_rcu(&ifp->if_list, p);
 }
 
-static u32 inet6_addr_hash(const struct in6_addr *addr)
+static u32 inet6_addr_hash(const struct net *net, const struct in6_addr *addr)
 {
-	return hash_32(ipv6_addr_hash(addr), IN6_ADDR_HSIZE_SHIFT);
+	u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net);
+
+	return hash_32(val, IN6_ADDR_HSIZE_SHIFT);
+}
+
+static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
+			       struct net_device *dev, unsigned int hash)
+{
+	struct inet6_ifaddr *ifp;
+
+	hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) {
+		if (!net_eq(dev_net(ifp->idev->dev), net))
+			continue;
+		if (ipv6_addr_equal(&ifp->addr, addr)) {
+			if (!dev || ifp->idev->dev == dev)
+				return true;
+		}
+	}
+	return false;
+}
+
+static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa)
+{
+	unsigned int hash = inet6_addr_hash(dev_net(dev), &ifa->addr);
+	int err = 0;
+
+	spin_lock(&addrconf_hash_lock);
+
+	/* Ignore adding duplicate addresses on an interface */
+	if (ipv6_chk_same_addr(dev_net(dev), &ifa->addr, dev, hash)) {
+		ADBG("ipv6_add_addr: already assigned\n");
+		err = -EEXIST;
+	} else {
+		hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]);
+	}
+
+	spin_unlock(&addrconf_hash_lock);
+
+	return err;
 }
 
 /* On success it returns ifp with increased reference count */
@@ -958,13 +998,13 @@ static u32 inet6_addr_hash(const struct in6_addr *addr)
 static struct inet6_ifaddr *
 ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	      const struct in6_addr *peer_addr, int pfxlen,
-	      int scope, u32 flags, u32 valid_lft, u32 prefered_lft)
+	      int scope, u32 flags, u32 valid_lft, u32 prefered_lft,
+	      bool can_block, struct netlink_ext_ack *extack)
 {
+	gfp_t gfp_flags = can_block ? GFP_KERNEL : GFP_ATOMIC;
 	struct net *net = dev_net(idev->dev);
 	struct inet6_ifaddr *ifa = NULL;
-	struct rt6_info *rt;
-	struct in6_validator_info i6vi;
-	unsigned int hash;
+	struct rt6_info *rt = NULL;
 	int err = 0;
 	int addr_type = ipv6_addr_type(addr);
 
@@ -974,42 +1014,33 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	     addr_type & IPV6_ADDR_LOOPBACK))
 		return ERR_PTR(-EADDRNOTAVAIL);
 
-	rcu_read_lock_bh();
-
-	in6_dev_hold(idev);
-
 	if (idev->dead) {
 		err = -ENODEV;			/*XXX*/
-		goto out2;
+		goto out;
 	}
 
 	if (idev->cnf.disable_ipv6) {
 		err = -EACCES;
-		goto out2;
-	}
-
-	i6vi.i6vi_addr = *addr;
-	i6vi.i6vi_dev = idev;
-	rcu_read_unlock_bh();
-
-	err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi);
-
-	rcu_read_lock_bh();
-	err = notifier_to_errno(err);
-	if (err)
-		goto out2;
-
-	spin_lock(&addrconf_hash_lock);
-
-	/* Ignore adding duplicate addresses on an interface */
-	if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) {
-		ADBG("ipv6_add_addr: already assigned\n");
-		err = -EEXIST;
 		goto out;
 	}
 
-	ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC);
+	/* validator notifier needs to be blocking;
+	 * do not call in atomic context
+	 */
+	if (can_block) {
+		struct in6_validator_info i6vi = {
+			.i6vi_addr = *addr,
+			.i6vi_dev = idev,
+			.extack = extack,
+		};
+
+		err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi);
+		err = notifier_to_errno(err);
+		if (err < 0)
+			goto out;
+	}
 
+	ifa = kzalloc(sizeof(*ifa), gfp_flags);
 	if (!ifa) {
 		ADBG("ipv6_add_addr: malloc failed\n");
 		err = -ENOBUFS;
@@ -1019,6 +1050,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	rt = addrconf_dst_alloc(idev, addr, false);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
+		rt = NULL;
 		goto out;
 	}
 
@@ -1049,16 +1081,21 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	ifa->rt = rt;
 
 	ifa->idev = idev;
+	in6_dev_hold(idev);
+
 	/* For caller */
 	refcount_set(&ifa->refcnt, 1);
 
-	/* Add to big hash table */
-	hash = inet6_addr_hash(addr);
+	rcu_read_lock_bh();
 
-	hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]);
-	spin_unlock(&addrconf_hash_lock);
+	err = ipv6_add_addr_hash(idev->dev, ifa);
+	if (err < 0) {
+		rcu_read_unlock_bh();
+		goto out;
+	}
 
 	write_lock(&idev->lock);
+
 	/* Add to inet6_dev unicast addr list. */
 	ipv6_link_dev_addr(idev, ifa);
 
@@ -1069,21 +1106,23 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 
 	in6_ifa_hold(ifa);
 	write_unlock(&idev->lock);
-out2:
+
 	rcu_read_unlock_bh();
 
-	if (likely(err == 0))
-		inet6addr_notifier_call_chain(NETDEV_UP, ifa);
-	else {
-		kfree(ifa);
-		in6_dev_put(idev);
+	inet6addr_notifier_call_chain(NETDEV_UP, ifa);
+out:
+	if (unlikely(err < 0)) {
+		if (rt)
+			ip6_rt_put(rt);
+		if (ifa) {
+			if (ifa->idev)
+				in6_dev_put(ifa->idev);
+			kfree(ifa);
+		}
 		ifa = ERR_PTR(err);
 	}
 
 	return ifa;
-out:
-	spin_unlock(&addrconf_hash_lock);
-	goto out2;
 }
 
 enum cleanup_prefix_rt_t {
@@ -1204,7 +1243,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 	if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE))
 		action = check_cleanup_prefix_route(ifp, &expires);
 
-	list_del_init(&ifp->if_list);
+	list_del_rcu(&ifp->if_list);
 	__in6_ifa_put(ifp);
 
 	write_unlock_bh(&ifp->idev->lock);
@@ -1330,7 +1369,7 @@ retry:
 
 	ift = ipv6_add_addr(idev, &addr, NULL, tmp_plen,
 			    ipv6_addr_scope(&addr), addr_flags,
-			    tmp_valid_lft, tmp_prefered_lft);
+			    tmp_valid_lft, tmp_prefered_lft, true, NULL);
 	if (IS_ERR(ift)) {
 		in6_ifa_put(ifp);
 		in6_dev_put(idev);
@@ -1558,8 +1597,7 @@ static int __ipv6_dev_get_saddr(struct net *net,
 {
 	struct ipv6_saddr_score *score = &scores[1 - hiscore_idx], *hiscore = &scores[hiscore_idx];
 
-	read_lock_bh(&idev->lock);
-	list_for_each_entry(score->ifa, &idev->addr_list, if_list) {
+	list_for_each_entry_rcu(score->ifa, &idev->addr_list, if_list) {
 		int i;
 
 		/*
@@ -1609,11 +1647,6 @@ static int __ipv6_dev_get_saddr(struct net *net,
 				}
 				break;
 			} else if (minihiscore < miniscore) {
-				if (hiscore->ifa)
-					in6_ifa_put(hiscore->ifa);
-
-				in6_ifa_hold(score->ifa);
-
 				swap(hiscore, score);
 				hiscore_idx = 1 - hiscore_idx;
 
@@ -1625,7 +1658,6 @@ static int __ipv6_dev_get_saddr(struct net *net,
 		}
 	}
 out:
-	read_unlock_bh(&idev->lock);
 	return hiscore_idx;
 }
 
@@ -1662,6 +1694,7 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 	int dst_type;
 	bool use_oif_addr = false;
 	int hiscore_idx = 0;
+	int ret = 0;
 
 	dst_type = __ipv6_addr_type(daddr);
 	dst.addr = daddr;
@@ -1737,15 +1770,14 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 	}
 
 out:
-	rcu_read_unlock();
-
 	hiscore = &scores[hiscore_idx];
 	if (!hiscore->ifa)
-		return -EADDRNOTAVAIL;
+		ret = -EADDRNOTAVAIL;
+	else
+		*saddr = hiscore->ifa->addr;
 
-	*saddr = hiscore->ifa->addr;
-	in6_ifa_put(hiscore->ifa);
-	return 0;
+	rcu_read_unlock();
+	return ret;
 }
 EXPORT_SYMBOL(ipv6_dev_get_saddr);
 
@@ -1785,15 +1817,15 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
 	return err;
 }
 
-static int ipv6_count_addresses(struct inet6_dev *idev)
+static int ipv6_count_addresses(const struct inet6_dev *idev)
 {
+	const struct inet6_ifaddr *ifp;
 	int cnt = 0;
-	struct inet6_ifaddr *ifp;
 
-	read_lock_bh(&idev->lock);
-	list_for_each_entry(ifp, &idev->addr_list, if_list)
+	rcu_read_lock();
+	list_for_each_entry_rcu(ifp, &idev->addr_list, if_list)
 		cnt++;
-	read_unlock_bh(&idev->lock);
+	rcu_read_unlock();
 	return cnt;
 }
 
@@ -1808,11 +1840,11 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
 			    const struct net_device *dev, int strict,
 			    u32 banned_flags)
 {
+	unsigned int hash = inet6_addr_hash(net, addr);
 	struct inet6_ifaddr *ifp;
-	unsigned int hash = inet6_addr_hash(addr);
 	u32 ifp_flags;
 
-	rcu_read_lock_bh();
+	rcu_read_lock();
 	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
@@ -1826,32 +1858,16 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
 		    !(ifp_flags&banned_flags) &&
 		    (!dev || ifp->idev->dev == dev ||
 		     !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) {
-			rcu_read_unlock_bh();
+			rcu_read_unlock();
 			return 1;
 		}
 	}
 
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 	return 0;
 }
 EXPORT_SYMBOL(ipv6_chk_addr_and_flags);
 
-static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
-			       struct net_device *dev)
-{
-	unsigned int hash = inet6_addr_hash(addr);
-	struct inet6_ifaddr *ifp;
-
-	hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) {
-		if (!net_eq(dev_net(ifp->idev->dev), net))
-			continue;
-		if (ipv6_addr_equal(&ifp->addr, addr)) {
-			if (!dev || ifp->idev->dev == dev)
-				return true;
-		}
-	}
-	return false;
-}
 
 /* Compares an address/prefix_len with addresses on device @dev.
  * If one is found it returns true.
@@ -1859,20 +1875,18 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
 bool ipv6_chk_custom_prefix(const struct in6_addr *addr,
 	const unsigned int prefix_len, struct net_device *dev)
 {
-	struct inet6_dev *idev;
-	struct inet6_ifaddr *ifa;
+	const struct inet6_ifaddr *ifa;
+	const struct inet6_dev *idev;
 	bool ret = false;
 
 	rcu_read_lock();
 	idev = __in6_dev_get(dev);
 	if (idev) {
-		read_lock_bh(&idev->lock);
-		list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) {
 			ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len);
 			if (ret)
 				break;
 		}
-		read_unlock_bh(&idev->lock);
 	}
 	rcu_read_unlock();
 
@@ -1882,22 +1896,20 @@ EXPORT_SYMBOL(ipv6_chk_custom_prefix);
 
 int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev)
 {
-	struct inet6_dev *idev;
-	struct inet6_ifaddr *ifa;
+	const struct inet6_ifaddr *ifa;
+	const struct inet6_dev *idev;
 	int	onlink;
 
 	onlink = 0;
 	rcu_read_lock();
 	idev = __in6_dev_get(dev);
 	if (idev) {
-		read_lock_bh(&idev->lock);
-		list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) {
 			onlink = ipv6_prefix_equal(addr, &ifa->addr,
 						   ifa->prefix_len);
 			if (onlink)
 				break;
 		}
-		read_unlock_bh(&idev->lock);
 	}
 	rcu_read_unlock();
 	return onlink;
@@ -1907,11 +1919,11 @@ EXPORT_SYMBOL(ipv6_chk_prefix);
 struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr,
 				     struct net_device *dev, int strict)
 {
+	unsigned int hash = inet6_addr_hash(net, addr);
 	struct inet6_ifaddr *ifp, *result = NULL;
-	unsigned int hash = inet6_addr_hash(addr);
 
-	rcu_read_lock_bh();
-	hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) {
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
 		if (ipv6_addr_equal(&ifp->addr, addr)) {
@@ -1923,7 +1935,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add
 			}
 		}
 	}
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 
 	return result;
 }
@@ -1975,7 +1987,7 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp)
 	return err;
 }
 
-void addrconf_dad_failure(struct inet6_ifaddr *ifp)
+void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp)
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct net *net = dev_net(ifp->idev->dev);
@@ -1985,8 +1997,8 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 		return;
 	}
 
-	net_info_ratelimited("%s: IPv6 duplicate address %pI6c detected!\n",
-			     ifp->idev->dev->name, &ifp->addr);
+	net_info_ratelimited("%s: IPv6 duplicate address %pI6c used by %pM detected!\n",
+			     ifp->idev->dev->name, &ifp->addr, eth_hdr(skb)->h_source);
 
 	spin_lock_bh(&ifp->lock);
 
@@ -2025,7 +2037,7 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 
 		ifp2 = ipv6_add_addr(idev, &new_addr, NULL, pfxlen,
 				     scope, flags, valid_lft,
-				     preferred_lft);
+				     preferred_lft, false, NULL);
 		if (IS_ERR(ifp2))
 			goto lock_errdad;
 
@@ -2321,24 +2333,24 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 	if (!table)
 		return NULL;
 
-	read_lock_bh(&table->tb6_lock);
-	fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0);
+	rcu_read_lock();
+	fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0, true);
 	if (!fn)
 		goto out;
 
-	noflags |= RTF_CACHE;
-	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
+	for_each_fib6_node_rt_rcu(fn) {
 		if (rt->dst.dev->ifindex != dev->ifindex)
 			continue;
 		if ((rt->rt6i_flags & flags) != flags)
 			continue;
 		if ((rt->rt6i_flags & noflags) != 0)
 			continue;
-		dst_hold(&rt->dst);
+		if (!dst_hold_safe(&rt->dst))
+			rt = NULL;
 		break;
 	}
 out:
-	read_unlock_bh(&table->tb6_lock);
+	rcu_read_unlock();
 	return rt;
 }
 
@@ -2483,7 +2495,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
 					    pinfo->prefix_len,
 					    addr_type&IPV6_ADDR_SCOPE_MASK,
 					    addr_flags, valid_lft,
-					    prefered_lft);
+					    prefered_lft, false, NULL);
 
 		if (IS_ERR_OR_NULL(ifp))
 			return -1;
@@ -2793,7 +2805,8 @@ static int inet6_addr_add(struct net *net, int ifindex,
 			  const struct in6_addr *pfx,
 			  const struct in6_addr *peer_pfx,
 			  unsigned int plen, __u32 ifa_flags,
-			  __u32 prefered_lft, __u32 valid_lft)
+			  __u32 prefered_lft, __u32 valid_lft,
+			  struct netlink_ext_ack *extack)
 {
 	struct inet6_ifaddr *ifp;
 	struct inet6_dev *idev;
@@ -2852,7 +2865,7 @@ static int inet6_addr_add(struct net *net, int ifindex,
 	}
 
 	ifp = ipv6_add_addr(idev, pfx, peer_pfx, plen, scope, ifa_flags,
-			    valid_lft, prefered_lft);
+			    valid_lft, prefered_lft, true, extack);
 
 	if (!IS_ERR(ifp)) {
 		if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
@@ -2937,7 +2950,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg)
 	rtnl_lock();
 	err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, NULL,
 			     ireq.ifr6_prefixlen, IFA_F_PERMANENT,
-			     INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
+			     INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, NULL);
 	rtnl_unlock();
 	return err;
 }
@@ -2967,7 +2980,8 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 
 	ifp = ipv6_add_addr(idev, addr, NULL, plen,
 			    scope, IFA_F_PERMANENT,
-			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
+			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME,
+			    true, NULL);
 	if (!IS_ERR(ifp)) {
 		spin_lock_bh(&ifp->lock);
 		ifp->flags &= ~IFA_F_TENTATIVE;
@@ -3067,7 +3081,7 @@ void addrconf_add_linklocal(struct inet6_dev *idev,
 #endif
 
 	ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags,
-			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
+			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, true, NULL);
 	if (!IS_ERR(ifp)) {
 		addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0);
 		addrconf_dad_start(ifp);
@@ -3297,7 +3311,7 @@ static int fixup_permanent_addr(struct inet6_dev *idev,
 		struct rt6_info *rt, *prev;
 
 		rt = addrconf_dst_alloc(idev, &ifp->addr, false);
-		if (unlikely(IS_ERR(rt)))
+		if (IS_ERR(rt))
 			return PTR_ERR(rt);
 
 		/* ifp->rt can be accessed outside of rtnl */
@@ -3404,7 +3418,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			/* restore routes for permanent addresses */
 			addrconf_permanent_addr(dev);
 
-			if (!addrconf_qdisc_ok(dev)) {
+			if (!addrconf_link_ready(dev)) {
 				/* device is not ready yet. */
 				pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n",
 					dev->name);
@@ -3419,7 +3433,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 				run_pending = 1;
 			}
 		} else if (event == NETDEV_CHANGE) {
-			if (!addrconf_qdisc_ok(dev)) {
+			if (!addrconf_link_ready(dev)) {
 				/* device is still not ready. */
 				break;
 			}
@@ -3563,7 +3577,6 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	struct net *net = dev_net(dev);
 	struct inet6_dev *idev;
 	struct inet6_ifaddr *ifa, *tmp;
-	struct list_head del_list;
 	int _keep_addr;
 	bool keep_addr;
 	int state, i;
@@ -3655,7 +3668,6 @@ restart:
 	 */
 	keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6);
 
-	INIT_LIST_HEAD(&del_list);
 	list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
 		struct rt6_info *rt = NULL;
 		bool keep;
@@ -3664,8 +3676,6 @@ restart:
 
 		keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
 			!addr_is_local(&ifa->addr);
-		if (!keep)
-			list_move(&ifa->if_list, &del_list);
 
 		write_unlock_bh(&idev->lock);
 		spin_lock_bh(&ifa->lock);
@@ -3699,19 +3709,14 @@ restart:
 		}
 
 		write_lock_bh(&idev->lock);
+		if (!keep) {
+			list_del_rcu(&ifa->if_list);
+			in6_ifa_put(ifa);
+		}
 	}
 
 	write_unlock_bh(&idev->lock);
 
-	/* now clean up addresses to be removed */
-	while (!list_empty(&del_list)) {
-		ifa = list_first_entry(&del_list,
-				       struct inet6_ifaddr, if_list);
-		list_del(&ifa->if_list);
-
-		in6_ifa_put(ifa);
-	}
-
 	/* Step 5: Discard anycast and multicast list */
 	if (how) {
 		ipv6_ac_destroy_dev(idev);
@@ -4093,9 +4098,9 @@ struct if6_iter_state {
 
 static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos)
 {
-	struct inet6_ifaddr *ifa = NULL;
 	struct if6_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
+	struct inet6_ifaddr *ifa = NULL;
 	int p = 0;
 
 	/* initial bucket if pos is 0 */
@@ -4105,7 +4110,7 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos)
 	}
 
 	for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) {
-		hlist_for_each_entry_rcu_bh(ifa, &inet6_addr_lst[state->bucket],
+		hlist_for_each_entry_rcu(ifa, &inet6_addr_lst[state->bucket],
 					 addr_lst) {
 			if (!net_eq(dev_net(ifa->idev->dev), net))
 				continue;
@@ -4131,7 +4136,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 	struct if6_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
 
-	hlist_for_each_entry_continue_rcu_bh(ifa, addr_lst) {
+	hlist_for_each_entry_continue_rcu(ifa, addr_lst) {
 		if (!net_eq(dev_net(ifa->idev->dev), net))
 			continue;
 		state->offset++;
@@ -4140,7 +4145,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 
 	while (++state->bucket < IN6_ADDR_HSIZE) {
 		state->offset = 0;
-		hlist_for_each_entry_rcu_bh(ifa,
+		hlist_for_each_entry_rcu(ifa,
 				     &inet6_addr_lst[state->bucket], addr_lst) {
 			if (!net_eq(dev_net(ifa->idev->dev), net))
 				continue;
@@ -4153,9 +4158,9 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 }
 
 static void *if6_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(rcu_bh)
+	__acquires(rcu)
 {
-	rcu_read_lock_bh();
+	rcu_read_lock();
 	return if6_get_first(seq, *pos);
 }
 
@@ -4169,9 +4174,9 @@ static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 }
 
 static void if6_seq_stop(struct seq_file *seq, void *v)
-	__releases(rcu_bh)
+	__releases(rcu)
 {
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 }
 
 static int if6_seq_show(struct seq_file *seq, void *v)
@@ -4240,12 +4245,12 @@ void if6_proc_exit(void)
 /* Check if address is a home address configured on any interface. */
 int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
 {
-	int ret = 0;
+	unsigned int hash = inet6_addr_hash(net, addr);
 	struct inet6_ifaddr *ifp = NULL;
-	unsigned int hash = inet6_addr_hash(addr);
+	int ret = 0;
 
-	rcu_read_lock_bh();
-	hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) {
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
 		if (ipv6_addr_equal(&ifp->addr, addr) &&
@@ -4254,7 +4259,7 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
 			break;
 		}
 	}
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 	return ret;
 }
 #endif
@@ -4580,7 +4585,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		 */
 		return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx,
 				      ifm->ifa_prefixlen, ifa_flags,
-				      preferred_lft, valid_lft);
+				      preferred_lft, valid_lft, extack);
 	}
 
 	if (nlh->nlmsg_flags & NLM_F_EXCL ||
@@ -4907,17 +4912,15 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy,
 			  extack);
 	if (err < 0)
-		goto errout;
+		return err;
 
 	addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer);
-	if (!addr) {
-		err = -EINVAL;
-		goto errout;
-	}
+	if (!addr)
+		return -EINVAL;
 
 	ifm = nlmsg_data(nlh);
 	if (ifm->ifa_index)
-		dev = __dev_get_by_index(net, ifm->ifa_index);
+		dev = dev_get_by_index(net, ifm->ifa_index);
 
 	ifa = ipv6_get_ifaddr(net, addr, dev, 1);
 	if (!ifa) {
@@ -4943,6 +4946,8 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 errout_ifa:
 	in6_ifa_put(ifa);
 errout:
+	if (dev)
+		dev_put(dev);
 	return err;
 }
 
@@ -5899,10 +5904,9 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
 		spin_lock(&ifa->lock);
 		if (ifa->rt) {
 			struct rt6_info *rt = ifa->rt;
-			struct fib6_table *table = rt->rt6i_table;
 			int cpu;
 
-			read_lock(&table->tb6_lock);
+			rcu_read_lock();
 			addrconf_set_nopolicy(ifa->rt, val);
 			if (rt->rt6i_pcpu) {
 				for_each_possible_cpu(cpu) {
@@ -5912,7 +5916,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
 					addrconf_set_nopolicy(*rtp, val);
 				}
 			}
-			read_unlock(&table->tb6_lock);
+			rcu_read_unlock();
 		}
 		spin_unlock(&ifa->lock);
 	}
@@ -6586,13 +6590,13 @@ int __init addrconf_init(void)
 	__rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, 0);
 	__rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, 0);
 	__rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr,
-			inet6_dump_ifaddr, 0);
+			inet6_dump_ifaddr, RTNL_FLAG_DOIT_UNLOCKED);
 	__rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL,
 			inet6_dump_ifmcaddr, 0);
 	__rtnl_register(PF_INET6, RTM_GETANYCAST, NULL,
 			inet6_dump_ifacaddr, 0);
 	__rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf,
-			inet6_netconf_dump_devconf, 0);
+			inet6_netconf_dump_devconf, RTNL_FLAG_DOIT_UNLOCKED);
 
 	ipv6_addr_label_rtnl_register();
 
@@ -6619,9 +6623,9 @@ void addrconf_cleanup(void)
 	unregister_pernet_subsys(&addrconf_ops);
 	ipv6_addr_label_cleanup();
 
-	rtnl_lock();
+	rtnl_af_unregister(&inet6_ops);
 
-	__rtnl_af_unregister(&inet6_ops);
+	rtnl_lock();
 
 	/* clean dev list */
 	for_each_netdev(&init_net, dev) {
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 9e3488d50b15..32b564dfd02a 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -88,7 +88,7 @@ int __ipv6_addr_type(const struct in6_addr *addr)
 EXPORT_SYMBOL(__ipv6_addr_type);
 
 static ATOMIC_NOTIFIER_HEAD(inet6addr_chain);
-static ATOMIC_NOTIFIER_HEAD(inet6addr_validator_chain);
+static BLOCKING_NOTIFIER_HEAD(inet6addr_validator_chain);
 
 int register_inet6addr_notifier(struct notifier_block *nb)
 {
@@ -110,19 +110,20 @@ EXPORT_SYMBOL(inet6addr_notifier_call_chain);
 
 int register_inet6addr_validator_notifier(struct notifier_block *nb)
 {
-	return atomic_notifier_chain_register(&inet6addr_validator_chain, nb);
+	return blocking_notifier_chain_register(&inet6addr_validator_chain, nb);
 }
 EXPORT_SYMBOL(register_inet6addr_validator_notifier);
 
 int unregister_inet6addr_validator_notifier(struct notifier_block *nb)
 {
-	return atomic_notifier_chain_unregister(&inet6addr_validator_chain, nb);
+	return blocking_notifier_chain_unregister(&inet6addr_validator_chain,
+						  nb);
 }
 EXPORT_SYMBOL(unregister_inet6addr_validator_notifier);
 
 int inet6addr_validator_notifier_call_chain(unsigned long val, void *v)
 {
-	return atomic_notifier_call_chain(&inet6addr_validator_chain, val, v);
+	return blocking_notifier_call_chain(&inet6addr_validator_chain, val, v);
 }
 EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain);
 
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index f664871feca6..00e1f8ee08f8 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -19,7 +19,6 @@
 #include <linux/if_addrlabel.h>
 #include <linux/netlink.h>
 #include <linux/rtnetlink.h>
-#include <linux/refcount.h>
 
 #if 0
 #define ADDRLABEL(x...) printk(x)
@@ -31,30 +30,15 @@
  * Policy Table
  */
 struct ip6addrlbl_entry {
-	possible_net_t lbl_net;
 	struct in6_addr prefix;
 	int prefixlen;
 	int ifindex;
 	int addrtype;
 	u32 label;
 	struct hlist_node list;
-	refcount_t refcnt;
 	struct rcu_head rcu;
 };
 
-static struct ip6addrlbl_table
-{
-	struct hlist_head head;
-	spinlock_t lock;
-	u32 seq;
-} ip6addrlbl_table;
-
-static inline
-struct net *ip6addrlbl_net(const struct ip6addrlbl_entry *lbl)
-{
-	return read_pnet(&lbl->lbl_net);
-}
-
 /*
  * Default policy table (RFC6724 + extensions)
  *
@@ -126,36 +110,11 @@ static const __net_initconst struct ip6addrlbl_init_table
 	}
 };
 
-/* Object management */
-static inline void ip6addrlbl_free(struct ip6addrlbl_entry *p)
-{
-	kfree(p);
-}
-
-static void ip6addrlbl_free_rcu(struct rcu_head *h)
-{
-	ip6addrlbl_free(container_of(h, struct ip6addrlbl_entry, rcu));
-}
-
-static bool ip6addrlbl_hold(struct ip6addrlbl_entry *p)
-{
-	return refcount_inc_not_zero(&p->refcnt);
-}
-
-static inline void ip6addrlbl_put(struct ip6addrlbl_entry *p)
-{
-	if (refcount_dec_and_test(&p->refcnt))
-		call_rcu(&p->rcu, ip6addrlbl_free_rcu);
-}
-
 /* Find label */
-static bool __ip6addrlbl_match(struct net *net,
-			       const struct ip6addrlbl_entry *p,
+static bool __ip6addrlbl_match(const struct ip6addrlbl_entry *p,
 			       const struct in6_addr *addr,
 			       int addrtype, int ifindex)
 {
-	if (!net_eq(ip6addrlbl_net(p), net))
-		return false;
 	if (p->ifindex && p->ifindex != ifindex)
 		return false;
 	if (p->addrtype && p->addrtype != addrtype)
@@ -170,8 +129,9 @@ static struct ip6addrlbl_entry *__ipv6_addr_label(struct net *net,
 						  int type, int ifindex)
 {
 	struct ip6addrlbl_entry *p;
-	hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) {
-		if (__ip6addrlbl_match(net, p, addr, type, ifindex))
+
+	hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) {
+		if (__ip6addrlbl_match(p, addr, type, ifindex))
 			return p;
 	}
 	return NULL;
@@ -197,8 +157,7 @@ u32 ipv6_addr_label(struct net *net,
 }
 
 /* allocate one entry */
-static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net,
-						 const struct in6_addr *prefix,
+static struct ip6addrlbl_entry *ip6addrlbl_alloc(const struct in6_addr *prefix,
 						 int prefixlen, int ifindex,
 						 u32 label)
 {
@@ -237,24 +196,22 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net,
 	newp->addrtype = addrtype;
 	newp->label = label;
 	INIT_HLIST_NODE(&newp->list);
-	write_pnet(&newp->lbl_net, net);
-	refcount_set(&newp->refcnt, 1);
 	return newp;
 }
 
 /* add a label */
-static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace)
+static int __ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp,
+			    int replace)
 {
-	struct hlist_node *n;
 	struct ip6addrlbl_entry *last = NULL, *p = NULL;
+	struct hlist_node *n;
 	int ret = 0;
 
 	ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", __func__, newp,
 		  replace);
 
-	hlist_for_each_entry_safe(p, n,	&ip6addrlbl_table.head, list) {
+	hlist_for_each_entry_safe(p, n,	&net->ipv6.ip6addrlbl_table.head, list) {
 		if (p->prefixlen == newp->prefixlen &&
-		    net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) &&
 		    p->ifindex == newp->ifindex &&
 		    ipv6_addr_equal(&p->prefix, &newp->prefix)) {
 			if (!replace) {
@@ -262,7 +219,7 @@ static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace)
 				goto out;
 			}
 			hlist_replace_rcu(&p->list, &newp->list);
-			ip6addrlbl_put(p);
+			kfree_rcu(p, rcu);
 			goto out;
 		} else if ((p->prefixlen == newp->prefixlen && !p->ifindex) ||
 			   (p->prefixlen < newp->prefixlen)) {
@@ -274,10 +231,10 @@ static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace)
 	if (last)
 		hlist_add_behind_rcu(&newp->list, &last->list);
 	else
-		hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head);
+		hlist_add_head_rcu(&newp->list, &net->ipv6.ip6addrlbl_table.head);
 out:
 	if (!ret)
-		ip6addrlbl_table.seq++;
+		net->ipv6.ip6addrlbl_table.seq++;
 	return ret;
 }
 
@@ -293,14 +250,14 @@ static int ip6addrlbl_add(struct net *net,
 		  __func__, prefix, prefixlen, ifindex, (unsigned int)label,
 		  replace);
 
-	newp = ip6addrlbl_alloc(net, prefix, prefixlen, ifindex, label);
+	newp = ip6addrlbl_alloc(prefix, prefixlen, ifindex, label);
 	if (IS_ERR(newp))
 		return PTR_ERR(newp);
-	spin_lock(&ip6addrlbl_table.lock);
-	ret = __ip6addrlbl_add(newp, replace);
-	spin_unlock(&ip6addrlbl_table.lock);
+	spin_lock(&net->ipv6.ip6addrlbl_table.lock);
+	ret = __ip6addrlbl_add(net, newp, replace);
+	spin_unlock(&net->ipv6.ip6addrlbl_table.lock);
 	if (ret)
-		ip6addrlbl_free(newp);
+		kfree(newp);
 	return ret;
 }
 
@@ -316,13 +273,12 @@ static int __ip6addrlbl_del(struct net *net,
 	ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n",
 		  __func__, prefix, prefixlen, ifindex);
 
-	hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) {
+	hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) {
 		if (p->prefixlen == prefixlen &&
-		    net_eq(ip6addrlbl_net(p), net) &&
 		    p->ifindex == ifindex &&
 		    ipv6_addr_equal(&p->prefix, prefix)) {
 			hlist_del_rcu(&p->list);
-			ip6addrlbl_put(p);
+			kfree_rcu(p, rcu);
 			ret = 0;
 			break;
 		}
@@ -341,9 +297,9 @@ static int ip6addrlbl_del(struct net *net,
 		  __func__, prefix, prefixlen, ifindex);
 
 	ipv6_addr_prefix(&prefix_buf, prefix, prefixlen);
-	spin_lock(&ip6addrlbl_table.lock);
+	spin_lock(&net->ipv6.ip6addrlbl_table.lock);
 	ret = __ip6addrlbl_del(net, &prefix_buf, prefixlen, ifindex);
-	spin_unlock(&ip6addrlbl_table.lock);
+	spin_unlock(&net->ipv6.ip6addrlbl_table.lock);
 	return ret;
 }
 
@@ -355,6 +311,9 @@ static int __net_init ip6addrlbl_net_init(struct net *net)
 
 	ADDRLABEL(KERN_DEBUG "%s\n", __func__);
 
+	spin_lock_init(&net->ipv6.ip6addrlbl_table.lock);
+	INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head);
+
 	for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) {
 		int ret = ip6addrlbl_add(net,
 					 ip6addrlbl_init_table[i].prefix,
@@ -374,14 +333,12 @@ static void __net_exit ip6addrlbl_net_exit(struct net *net)
 	struct hlist_node *n;
 
 	/* Remove all labels belonging to the exiting net */
-	spin_lock(&ip6addrlbl_table.lock);
-	hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) {
-		if (net_eq(ip6addrlbl_net(p), net)) {
-			hlist_del_rcu(&p->list);
-			ip6addrlbl_put(p);
-		}
+	spin_lock(&net->ipv6.ip6addrlbl_table.lock);
+	hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) {
+		hlist_del_rcu(&p->list);
+		kfree_rcu(p, rcu);
 	}
-	spin_unlock(&ip6addrlbl_table.lock);
+	spin_unlock(&net->ipv6.ip6addrlbl_table.lock);
 }
 
 static struct pernet_operations ipv6_addr_label_ops = {
@@ -391,8 +348,6 @@ static struct pernet_operations ipv6_addr_label_ops = {
 
 int __init ipv6_addr_label_init(void)
 {
-	spin_lock_init(&ip6addrlbl_table.lock);
-
 	return register_pernet_subsys(&ipv6_addr_label_ops);
 }
 
@@ -511,11 +466,10 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	int err;
 
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) {
-		if (idx >= s_idx &&
-		    net_eq(ip6addrlbl_net(p), net)) {
+	hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) {
+		if (idx >= s_idx) {
 			err = ip6addrlbl_fill(skb, p,
-					      ip6addrlbl_table.seq,
+					      net->ipv6.ip6addrlbl_table.seq,
 					      NETLINK_CB(cb->skb).portid,
 					      cb->nlh->nlmsg_seq,
 					      RTM_NEWADDRLABEL,
@@ -568,38 +522,28 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	addr = nla_data(tb[IFAL_ADDRESS]);
 
-	rcu_read_lock();
-	p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index);
-	if (p && !ip6addrlbl_hold(p))
-		p = NULL;
-	lseq = ip6addrlbl_table.seq;
-	rcu_read_unlock();
-
-	if (!p) {
-		err = -ESRCH;
-		goto out;
-	}
-
 	skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL);
-	if (!skb) {
-		ip6addrlbl_put(p);
+	if (!skb)
 		return -ENOBUFS;
-	}
 
-	err = ip6addrlbl_fill(skb, p, lseq,
-			      NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
-			      RTM_NEWADDRLABEL, 0);
+	err = -ESRCH;
 
-	ip6addrlbl_put(p);
+	rcu_read_lock();
+	p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index);
+	lseq = net->ipv6.ip6addrlbl_table.seq;
+	if (p)
+		err = ip6addrlbl_fill(skb, p, lseq,
+				      NETLINK_CB(in_skb).portid,
+				      nlh->nlmsg_seq,
+				      RTM_NEWADDRLABEL, 0);
+	rcu_read_unlock();
 
 	if (err < 0) {
 		WARN_ON(err == -EMSGSIZE);
 		kfree_skb(skb);
-		goto out;
+	} else {
+		err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
 	}
-
-	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
-out:
 	return err;
 }
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index fe5262fd6aa5..c26f71234b9c 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -810,6 +810,10 @@ static int __net_init inet6_net_init(struct net *net)
 	net->ipv6.sysctl.idgen_retries = 3;
 	net->ipv6.sysctl.idgen_delay = 1 * HZ;
 	net->ipv6.sysctl.flowlabel_state_ranges = 0;
+	net->ipv6.sysctl.max_dst_opts_cnt = IP6_DEFAULT_MAX_DST_OPTS_CNT;
+	net->ipv6.sysctl.max_hbh_opts_cnt = IP6_DEFAULT_MAX_HBH_OPTS_CNT;
+	net->ipv6.sysctl.max_dst_opts_len = IP6_DEFAULT_MAX_DST_OPTS_LEN;
+	net->ipv6.sysctl.max_hbh_opts_len = IP6_DEFAULT_MAX_HBH_OPTS_LEN;
 	atomic_set(&net->ipv6.fib6_sernum, 1);
 
 	err = ipv6_init_mibs(net);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 7802b72196f3..37bb33fbc742 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -271,6 +271,7 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir)
 		case NEXTHDR_DEST:
 			if (dir == XFRM_POLICY_OUT)
 				ipv6_rearrange_destopt(iph, exthdr.opth);
+			/* fall through */
 		case NEXTHDR_HOP:
 			if (!zero_out_mutable_opts(exthdr.opth)) {
 				net_dbg_ratelimited("overrun %sopts\n",
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 89910e2c10f4..4000b71bfdc5 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -483,8 +483,8 @@ static inline int esp_remove_trailer(struct sk_buff *skb)
 		goto out;
 	}
 
-	if (skb_copy_bits(skb, skb->len - alen - 2, nexthdr, 2))
-		BUG();
+	ret = skb_copy_bits(skb, skb->len - alen - 2, nexthdr, 2);
+	BUG_ON(ret);
 
 	ret = -EINVAL;
 	padlen = nexthdr[0];
@@ -559,14 +559,14 @@ static void esp_input_restore_header(struct sk_buff *skb)
 static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi)
 {
 	struct xfrm_state *x = xfrm_input_state(skb);
-	struct ip_esp_hdr *esph = (struct ip_esp_hdr *)skb->data;
 
 	/* For ESN we move the header forward by 4 bytes to
 	 * accomodate the high bits.  We will move it back after
 	 * decryption.
 	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
-		esph = skb_push(skb, 4);
+		struct ip_esp_hdr *esph = skb_push(skb, 4);
+
 		*seqhi = esph->spi;
 		esph->spi = esph->seq_no;
 		esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 95516138e861..83bd75713535 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -74,8 +74,20 @@ struct tlvtype_proc {
 
 /* An unknown option is detected, decide what to do */
 
-static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff)
+static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff,
+			       bool disallow_unknowns)
 {
+	if (disallow_unknowns) {
+		/* If unknown TLVs are disallowed by configuration
+		 * then always silently drop packet. Note this also
+		 * means no ICMP parameter problem is sent which
+		 * could be a good property to mitigate a reflection DOS
+		 * attack.
+		 */
+
+		goto drop;
+	}
+
 	switch ((skb_network_header(skb)[optoff] & 0xC0) >> 6) {
 	case 0: /* ignore */
 		return true;
@@ -89,25 +101,36 @@ static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff)
 		 */
 		if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr))
 			break;
+		/* fall through */
 	case 2: /* send ICMP PARM PROB regardless and drop packet */
 		icmpv6_param_prob(skb, ICMPV6_UNK_OPTION, optoff);
 		return false;
 	}
 
+drop:
 	kfree_skb(skb);
 	return false;
 }
 
 /* Parse tlv encoded option header (hop-by-hop or destination) */
 
-static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb)
+static bool ip6_parse_tlv(const struct tlvtype_proc *procs,
+			  struct sk_buff *skb,
+			  int max_count)
 {
-	const struct tlvtype_proc *curr;
+	int len = (skb_transport_header(skb)[1] + 1) << 3;
 	const unsigned char *nh = skb_network_header(skb);
 	int off = skb_network_header_len(skb);
-	int len = (skb_transport_header(skb)[1] + 1) << 3;
+	const struct tlvtype_proc *curr;
+	bool disallow_unknowns = false;
+	int tlv_count = 0;
 	int padlen = 0;
 
+	if (unlikely(max_count < 0)) {
+		disallow_unknowns = true;
+		max_count = -max_count;
+	}
+
 	if (skb_transport_offset(skb) + len > skb_headlen(skb))
 		goto bad;
 
@@ -148,6 +171,11 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb)
 		default: /* Other TLV code so scan list */
 			if (optlen > len)
 				goto bad;
+
+			tlv_count++;
+			if (tlv_count > max_count)
+				goto bad;
+
 			for (curr = procs; curr->type >= 0; curr++) {
 				if (curr->type == nh[off]) {
 					/* type specific length/alignment
@@ -158,10 +186,10 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb)
 					break;
 				}
 			}
-			if (curr->type < 0) {
-				if (ip6_tlvopt_unknown(skb, off) == 0)
-					return false;
-			}
+			if (curr->type < 0 &&
+			    !ip6_tlvopt_unknown(skb, off, disallow_unknowns))
+				return false;
+
 			padlen = 0;
 			break;
 		}
@@ -186,7 +214,6 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
 	struct ipv6_destopt_hao *hao;
 	struct inet6_skb_parm *opt = IP6CB(skb);
 	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
-	struct in6_addr tmp_addr;
 	int ret;
 
 	if (opt->dsthao) {
@@ -228,9 +255,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->ip_summed = CHECKSUM_NONE;
 
-	tmp_addr = ipv6h->saddr;
-	ipv6h->saddr = hao->addr;
-	hao->addr = tmp_addr;
+	swap(ipv6h->saddr, hao->addr);
 
 	if (skb->tstamp == 0)
 		__net_timestamp(skb);
@@ -260,23 +285,31 @@ static int ipv6_destopt_rcv(struct sk_buff *skb)
 	__u16 dstbuf;
 #endif
 	struct dst_entry *dst = skb_dst(skb);
+	struct net *net = dev_net(skb->dev);
+	int extlen;
 
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) ||
 	    !pskb_may_pull(skb, (skb_transport_offset(skb) +
 				 ((skb_transport_header(skb)[1] + 1) << 3)))) {
 		__IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
 				IPSTATS_MIB_INHDRERRORS);
+fail_and_free:
 		kfree_skb(skb);
 		return -1;
 	}
 
+	extlen = (skb_transport_header(skb)[1] + 1) << 3;
+	if (extlen > net->ipv6.sysctl.max_dst_opts_len)
+		goto fail_and_free;
+
 	opt->lastopt = opt->dst1 = skb_network_header_len(skb);
 #if IS_ENABLED(CONFIG_IPV6_MIP6)
 	dstbuf = opt->dst1;
 #endif
 
-	if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) {
-		skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3;
+	if (ip6_parse_tlv(tlvprocdestopt_lst, skb,
+			  init_net.ipv6.sysctl.max_dst_opts_cnt)) {
+		skb->transport_header += extlen;
 		opt = IP6CB(skb);
 #if IS_ENABLED(CONFIG_IPV6_MIP6)
 		opt->nhoff = dstbuf;
@@ -805,6 +838,8 @@ static const struct tlvtype_proc tlvprochopopt_lst[] = {
 int ipv6_parse_hopopts(struct sk_buff *skb)
 {
 	struct inet6_skb_parm *opt = IP6CB(skb);
+	struct net *net = dev_net(skb->dev);
+	int extlen;
 
 	/*
 	 * skb_network_header(skb) is equal to skb->data, and
@@ -815,13 +850,19 @@ int ipv6_parse_hopopts(struct sk_buff *skb)
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + 8) ||
 	    !pskb_may_pull(skb, (sizeof(struct ipv6hdr) +
 				 ((skb_transport_header(skb)[1] + 1) << 3)))) {
+fail_and_free:
 		kfree_skb(skb);
 		return -1;
 	}
 
+	extlen = (skb_transport_header(skb)[1] + 1) << 3;
+	if (extlen > net->ipv6.sysctl.max_hbh_opts_len)
+		goto fail_and_free;
+
 	opt->flags |= IP6SKB_HOPBYHOP;
-	if (ip6_parse_tlv(tlvprochopopt_lst, skb)) {
-		skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3;
+	if (ip6_parse_tlv(tlvprochopopt_lst, skb,
+			  init_net.ipv6.sysctl.max_hbh_opts_cnt)) {
+		skb->transport_header += extlen;
 		opt = IP6CB(skb);
 		opt->nhoff = sizeof(struct ipv6hdr);
 		return 1;
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 305e2ed730bf..11025f8d124b 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -99,7 +99,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
 				break;
 			hdrlen = 8;
 		} else if (nexthdr == NEXTHDR_AUTH)
-			hdrlen = (hp->hdrlen+2)<<2;
+			hdrlen = ipv6_authlen(hp);
 		else
 			hdrlen = ipv6_optlen(hp);
 
@@ -187,7 +187,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 {
 	unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
 	u8 nexthdr = ipv6_hdr(skb)->nexthdr;
-	unsigned int len;
 	bool found;
 
 	if (fragoff)
@@ -204,7 +203,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 		start = *offset + sizeof(struct ipv6hdr);
 		nexthdr = ip6->nexthdr;
 	}
-	len = skb->len - start;
 
 	do {
 		struct ipv6_opt_hdr _hdr, *hp;
@@ -273,7 +271,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 
 		if (!found) {
 			nexthdr = hp->nexthdr;
-			len -= hdrlen;
 			start += hdrlen;
 		}
 	} while (!found);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 5acb54405b10..6ae5dd3f4d0d 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -250,16 +250,15 @@ static bool opt_unrec(struct sk_buff *skb, __u32 offset)
 	return (*op & 0xC0) == 0x80;
 }
 
-int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
-			       struct icmp6hdr *thdr, int len)
+void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
+				struct icmp6hdr *thdr, int len)
 {
 	struct sk_buff *skb;
 	struct icmp6hdr *icmp6h;
-	int err = 0;
 
 	skb = skb_peek(&sk->sk_write_queue);
 	if (!skb)
-		goto out;
+		return;
 
 	icmp6h = icmp6_hdr(skb);
 	memcpy(icmp6h, thdr, sizeof(struct icmp6hdr));
@@ -287,8 +286,6 @@ int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
 						      tmp_csum);
 	}
 	ip6_push_pending_frames(sk);
-out:
-	return err;
 }
 
 struct icmpv6_msg {
@@ -438,7 +435,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	int iif = 0;
 	int addr_type = 0;
 	int len;
-	int err = 0;
 	u32 mark = IP6_REPLY_MARK(net, skb->mark);
 
 	if ((u8 *)hdr < skb->head ||
@@ -575,17 +571,16 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	rcu_read_lock();
 	idev = __in6_dev_get(skb->dev);
 
-	err = ip6_append_data(sk, icmpv6_getfrag, &msg,
-			      len + sizeof(struct icmp6hdr),
-			      sizeof(struct icmp6hdr),
-			      &ipc6, &fl6, (struct rt6_info *)dst,
-			      MSG_DONTWAIT, &sockc_unused);
-	if (err) {
+	if (ip6_append_data(sk, icmpv6_getfrag, &msg,
+			    len + sizeof(struct icmp6hdr),
+			    sizeof(struct icmp6hdr),
+			    &ipc6, &fl6, (struct rt6_info *)dst,
+			    MSG_DONTWAIT, &sockc_unused)) {
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
-		err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
-						 len + sizeof(struct icmp6hdr));
+		icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
+					   len + sizeof(struct icmp6hdr));
 	}
 	rcu_read_unlock();
 out_dst_release:
@@ -682,7 +677,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	struct icmpv6_msg msg;
 	struct dst_entry *dst;
 	struct ipcm6_cookie ipc6;
-	int err = 0;
 	u32 mark = IP6_REPLY_MARK(net, skb->mark);
 	struct sockcm_cookie sockc_unused = {0};
 
@@ -719,8 +713,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
-	err = ip6_dst_lookup(net, sk, &dst, &fl6);
-	if (err)
+	if (ip6_dst_lookup(net, sk, &dst, &fl6))
 		goto out;
 	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
 	if (IS_ERR(dst))
@@ -737,17 +730,16 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	ipc6.dontfrag = np->dontfrag;
 	ipc6.opt = NULL;
 
-	err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
-				sizeof(struct icmp6hdr), &ipc6, &fl6,
-				(struct rt6_info *)dst, MSG_DONTWAIT,
-				&sockc_unused);
-
-	if (err) {
+	if (ip6_append_data(sk, icmpv6_getfrag, &msg,
+			    skb->len + sizeof(struct icmp6hdr),
+			    sizeof(struct icmp6hdr), &ipc6, &fl6,
+			    (struct rt6_info *)dst, MSG_DONTWAIT,
+			    &sockc_unused)) {
 		__ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
-		err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
-						 skb->len + sizeof(struct icmp6hdr));
+		icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
+					   skb->len + sizeof(struct icmp6hdr));
 	}
 	dst_release(dst);
 out:
@@ -872,10 +864,8 @@ static int icmpv6_rcv(struct sk_buff *skb)
 			goto discard_it;
 		hdr = icmp6_hdr(skb);
 
-		/*
-		 *	Drop through to notify
-		 */
-
+		/* to notify */
+		/* fall through */
 	case ICMPV6_DEST_UNREACH:
 	case ICMPV6_TIME_EXCEED:
 	case ICMPV6_PARAMPROB:
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e5308d7cbd75..2e2804f5823e 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -38,14 +38,6 @@
 #include <net/ip6_fib.h>
 #include <net/ip6_route.h>
 
-#define RT6_DEBUG 2
-
-#if RT6_DEBUG >= 3
-#define RT6_TRACE(x...) pr_debug(x)
-#else
-#define RT6_TRACE(x...) do { ; } while (0)
-#endif
-
 static struct kmem_cache *fib6_node_kmem __read_mostly;
 
 struct fib6_cleaner {
@@ -62,9 +54,12 @@ struct fib6_cleaner {
 #define FWS_INIT FWS_L
 #endif
 
-static void fib6_prune_clones(struct net *net, struct fib6_node *fn);
-static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn);
-static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn);
+static struct rt6_info *fib6_find_prefix(struct net *net,
+					 struct fib6_table *table,
+					 struct fib6_node *fn);
+static struct fib6_node *fib6_repair_tree(struct net *net,
+					  struct fib6_table *table,
+					  struct fib6_node *fn);
 static int fib6_walk(struct net *net, struct fib6_walker *w);
 static int fib6_walk_continue(struct fib6_walker *w);
 
@@ -110,6 +105,20 @@ enum {
 	FIB6_NO_SERNUM_CHANGE = 0,
 };
 
+void fib6_update_sernum(struct rt6_info *rt)
+{
+	struct fib6_table *table = rt->rt6i_table;
+	struct net *net = dev_net(rt->dst.dev);
+	struct fib6_node *fn;
+
+	spin_lock_bh(&table->tb6_lock);
+	fn = rcu_dereference_protected(rt->rt6i_node,
+			lockdep_is_held(&table->tb6_lock));
+	if (fn)
+		fn->fn_sernum = fib6_new_sernum(net);
+	spin_unlock_bh(&table->tb6_lock);
+}
+
 /*
  *	Auxiliary address test functions for the radix tree.
  *
@@ -140,18 +149,21 @@ static __be32 addr_bit_set(const void *token, int fn_bit)
 	       addr[fn_bit >> 5];
 }
 
-static struct fib6_node *node_alloc(void)
+static struct fib6_node *node_alloc(struct net *net)
 {
 	struct fib6_node *fn;
 
 	fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC);
+	if (fn)
+		net->ipv6.rt6_stats->fib_nodes++;
 
 	return fn;
 }
 
-static void node_free_immediate(struct fib6_node *fn)
+static void node_free_immediate(struct net *net, struct fib6_node *fn)
 {
 	kmem_cache_free(fib6_node_kmem, fn);
+	net->ipv6.rt6_stats->fib_nodes--;
 }
 
 static void node_free_rcu(struct rcu_head *head)
@@ -161,9 +173,10 @@ static void node_free_rcu(struct rcu_head *head)
 	kmem_cache_free(fib6_node_kmem, fn);
 }
 
-static void node_free(struct fib6_node *fn)
+static void node_free(struct net *net, struct fib6_node *fn)
 {
 	call_rcu(&fn->rcu, node_free_rcu);
+	net->ipv6.rt6_stats->fib_nodes--;
 }
 
 void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
@@ -185,9 +198,6 @@ void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
 			*ppcpu_rt = NULL;
 		}
 	}
-
-	free_percpu(non_pcpu_rt->rt6i_pcpu);
-	non_pcpu_rt->rt6i_pcpu = NULL;
 }
 EXPORT_SYMBOL_GPL(rt6_free_pcpu);
 
@@ -205,8 +215,7 @@ static void fib6_link_table(struct net *net, struct fib6_table *tb)
 	 * Initialize table lock at a single place to give lockdep a key,
 	 * tables aren't visible prior to being linked to the list.
 	 */
-	rwlock_init(&tb->tb6_lock);
-
+	spin_lock_init(&tb->tb6_lock);
 	h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1);
 
 	/*
@@ -225,7 +234,8 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
 	table = kzalloc(sizeof(*table), GFP_ATOMIC);
 	if (table) {
 		table->tb6_id = id;
-		table->tb6_root.leaf = net->ipv6.ip6_null_entry;
+		rcu_assign_pointer(table->tb6_root.leaf,
+				   net->ipv6.ip6_null_entry);
 		table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 		inet_peer_base_init(&table->tb6_peers);
 	}
@@ -322,11 +332,8 @@ unsigned int fib6_tables_seq_read(struct net *net)
 		struct hlist_head *head = &net->ipv6.fib_table_hash[h];
 		struct fib6_table *tb;
 
-		hlist_for_each_entry_rcu(tb, head, tb6_hlist) {
-			read_lock_bh(&tb->tb6_lock);
+		hlist_for_each_entry_rcu(tb, head, tb6_hlist)
 			fib_seq += tb->fib_seq;
-			read_unlock_bh(&tb->tb6_lock);
-		}
 	}
 	rcu_read_unlock();
 
@@ -346,9 +353,11 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net,
 
 static int call_fib6_entry_notifiers(struct net *net,
 				     enum fib_event_type event_type,
-				     struct rt6_info *rt)
+				     struct rt6_info *rt,
+				     struct netlink_ext_ack *extack)
 {
 	struct fib6_entry_notifier_info info = {
+		.info.extack = extack,
 		.rt = rt,
 	};
 
@@ -372,7 +381,7 @@ static int fib6_node_dump(struct fib6_walker *w)
 {
 	struct rt6_info *rt;
 
-	for (rt = w->leaf; rt; rt = rt->dst.rt6_next)
+	for_each_fib6_walker_rt(w)
 		fib6_rt_dump(rt, w->args);
 	w->leaf = NULL;
 	return 0;
@@ -382,9 +391,9 @@ static void fib6_table_dump(struct net *net, struct fib6_table *tb,
 			    struct fib6_walker *w)
 {
 	w->root = &tb->tb6_root;
-	read_lock_bh(&tb->tb6_lock);
+	spin_lock_bh(&tb->tb6_lock);
 	fib6_walk(net, w);
-	read_unlock_bh(&tb->tb6_lock);
+	spin_unlock_bh(&tb->tb6_lock);
 }
 
 /* Called with rcu_read_lock() */
@@ -421,7 +430,7 @@ static int fib6_dump_node(struct fib6_walker *w)
 	int res;
 	struct rt6_info *rt;
 
-	for (rt = w->leaf; rt; rt = rt->dst.rt6_next) {
+	for_each_fib6_walker_rt(w) {
 		res = rt6_dump_route(rt, w->args);
 		if (res < 0) {
 			/* Frame is full, suspend walking */
@@ -480,9 +489,9 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
 		w->count = 0;
 		w->skip = 0;
 
-		read_lock_bh(&table->tb6_lock);
+		spin_lock_bh(&table->tb6_lock);
 		res = fib6_walk(net, w);
-		read_unlock_bh(&table->tb6_lock);
+		spin_unlock_bh(&table->tb6_lock);
 		if (res > 0) {
 			cb->args[4] = 1;
 			cb->args[5] = w->root->fn_sernum;
@@ -497,9 +506,9 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
 		} else
 			w->skip = 0;
 
-		read_lock_bh(&table->tb6_lock);
+		spin_lock_bh(&table->tb6_lock);
 		res = fib6_walk_continue(w);
-		read_unlock_bh(&table->tb6_lock);
+		spin_unlock_bh(&table->tb6_lock);
 		if (res <= 0) {
 			fib6_walker_unlink(net, w);
 			cb->args[4] = 0;
@@ -580,11 +589,13 @@ out:
  *	node.
  */
 
-static struct fib6_node *fib6_add_1(struct fib6_node *root,
-				     struct in6_addr *addr, int plen,
-				     int offset, int allow_create,
-				     int replace_required, int sernum,
-				     struct netlink_ext_ack *extack)
+static struct fib6_node *fib6_add_1(struct net *net,
+				    struct fib6_table *table,
+				    struct fib6_node *root,
+				    struct in6_addr *addr, int plen,
+				    int offset, int allow_create,
+				    int replace_required,
+				    struct netlink_ext_ack *extack)
 {
 	struct fib6_node *fn, *in, *ln;
 	struct fib6_node *pn = NULL;
@@ -599,7 +610,9 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 	fn = root;
 
 	do {
-		key = (struct rt6key *)((u8 *)fn->leaf + offset);
+		struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
+					    lockdep_is_held(&table->tb6_lock));
+		key = (struct rt6key *)((u8 *)leaf + offset);
 
 		/*
 		 *	Prefix match
@@ -625,12 +638,10 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 		if (plen == fn->fn_bit) {
 			/* clean up an intermediate node */
 			if (!(fn->fn_flags & RTN_RTINFO)) {
-				rt6_release(fn->leaf);
-				fn->leaf = NULL;
+				RCU_INIT_POINTER(fn->leaf, NULL);
+				rt6_release(leaf);
 			}
 
-			fn->fn_sernum = sernum;
-
 			return fn;
 		}
 
@@ -639,10 +650,13 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 		 */
 
 		/* Try to walk down on tree. */
-		fn->fn_sernum = sernum;
 		dir = addr_bit_set(addr, fn->fn_bit);
 		pn = fn;
-		fn = dir ? fn->right : fn->left;
+		fn = dir ?
+		     rcu_dereference_protected(fn->right,
+					lockdep_is_held(&table->tb6_lock)) :
+		     rcu_dereference_protected(fn->left,
+					lockdep_is_held(&table->tb6_lock));
 	} while (fn);
 
 	if (!allow_create) {
@@ -668,19 +682,17 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 	 *	Create new leaf node without children.
 	 */
 
-	ln = node_alloc();
+	ln = node_alloc(net);
 
 	if (!ln)
 		return ERR_PTR(-ENOMEM);
 	ln->fn_bit = plen;
-
-	ln->parent = pn;
-	ln->fn_sernum = sernum;
+	RCU_INIT_POINTER(ln->parent, pn);
 
 	if (dir)
-		pn->right = ln;
+		rcu_assign_pointer(pn->right, ln);
 	else
-		pn->left  = ln;
+		rcu_assign_pointer(pn->left, ln);
 
 	return ln;
 
@@ -694,7 +706,8 @@ insert_above:
 	 * and the current
 	 */
 
-	pn = fn->parent;
+	pn = rcu_dereference_protected(fn->parent,
+				       lockdep_is_held(&table->tb6_lock));
 
 	/* find 1st bit in difference between the 2 addrs.
 
@@ -710,14 +723,14 @@ insert_above:
 	 *	(new leaf node)[ln] (old node)[fn]
 	 */
 	if (plen > bit) {
-		in = node_alloc();
-		ln = node_alloc();
+		in = node_alloc(net);
+		ln = node_alloc(net);
 
 		if (!in || !ln) {
 			if (in)
-				node_free_immediate(in);
+				node_free_immediate(net, in);
 			if (ln)
-				node_free_immediate(ln);
+				node_free_immediate(net, ln);
 			return ERR_PTR(-ENOMEM);
 		}
 
@@ -731,31 +744,28 @@ insert_above:
 
 		in->fn_bit = bit;
 
-		in->parent = pn;
+		RCU_INIT_POINTER(in->parent, pn);
 		in->leaf = fn->leaf;
-		atomic_inc(&in->leaf->rt6i_ref);
-
-		in->fn_sernum = sernum;
+		atomic_inc(&rcu_dereference_protected(in->leaf,
+				lockdep_is_held(&table->tb6_lock))->rt6i_ref);
 
 		/* update parent pointer */
 		if (dir)
-			pn->right = in;
+			rcu_assign_pointer(pn->right, in);
 		else
-			pn->left  = in;
+			rcu_assign_pointer(pn->left, in);
 
 		ln->fn_bit = plen;
 
-		ln->parent = in;
-		fn->parent = in;
-
-		ln->fn_sernum = sernum;
+		RCU_INIT_POINTER(ln->parent, in);
+		rcu_assign_pointer(fn->parent, in);
 
 		if (addr_bit_set(addr, bit)) {
-			in->right = ln;
-			in->left  = fn;
+			rcu_assign_pointer(in->right, ln);
+			rcu_assign_pointer(in->left, fn);
 		} else {
-			in->left  = ln;
-			in->right = fn;
+			rcu_assign_pointer(in->left, ln);
+			rcu_assign_pointer(in->right, fn);
 		}
 	} else { /* plen <= bit */
 
@@ -765,28 +775,26 @@ insert_above:
 		 *	     (old node)[fn] NULL
 		 */
 
-		ln = node_alloc();
+		ln = node_alloc(net);
 
 		if (!ln)
 			return ERR_PTR(-ENOMEM);
 
 		ln->fn_bit = plen;
 
-		ln->parent = pn;
-
-		ln->fn_sernum = sernum;
-
-		if (dir)
-			pn->right = ln;
-		else
-			pn->left  = ln;
+		RCU_INIT_POINTER(ln->parent, pn);
 
 		if (addr_bit_set(&key->addr, plen))
-			ln->right = fn;
+			RCU_INIT_POINTER(ln->right, fn);
 		else
-			ln->left  = fn;
+			RCU_INIT_POINTER(ln->left, fn);
+
+		rcu_assign_pointer(fn->parent, ln);
 
-		fn->parent = ln;
+		if (dir)
+			rcu_assign_pointer(pn->right, ln);
+		else
+			rcu_assign_pointer(pn->left, ln);
 	}
 	return ln;
 }
@@ -832,6 +840,8 @@ static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc)
 static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
 			  struct net *net)
 {
+	struct fib6_table *table = rt->rt6i_table;
+
 	if (atomic_read(&rt->rt6i_ref) != 1) {
 		/* This route is used as dummy address holder in some split
 		 * nodes. It is not leaked, but it still holds other resources,
@@ -840,12 +850,17 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
 		 * to still alive ones.
 		 */
 		while (fn) {
-			if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
-				fn->leaf = fib6_find_prefix(net, fn);
-				atomic_inc(&fn->leaf->rt6i_ref);
+			struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
+					    lockdep_is_held(&table->tb6_lock));
+			struct rt6_info *new_leaf;
+			if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) {
+				new_leaf = fib6_find_prefix(net, table, fn);
+				atomic_inc(&new_leaf->rt6i_ref);
+				rcu_assign_pointer(fn->leaf, new_leaf);
 				rt6_release(rt);
 			}
-			fn = fn->parent;
+			fn = rcu_dereference_protected(fn->parent,
+				    lockdep_is_held(&table->tb6_lock));
 		}
 	}
 }
@@ -855,11 +870,14 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
  */
 
 static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
-			    struct nl_info *info, struct mx6_config *mxc)
+			    struct nl_info *info, struct mx6_config *mxc,
+			    struct netlink_ext_ack *extack)
 {
+	struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
+				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 	struct rt6_info *iter = NULL;
-	struct rt6_info **ins;
-	struct rt6_info **fallback_ins = NULL;
+	struct rt6_info __rcu **ins;
+	struct rt6_info __rcu **fallback_ins = NULL;
 	int replace = (info->nlh &&
 		       (info->nlh->nlmsg_flags & NLM_F_REPLACE));
 	int add = (!info->nlh ||
@@ -874,7 +892,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 
 	ins = &fn->leaf;
 
-	for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) {
+	for (iter = leaf; iter;
+	     iter = rcu_dereference_protected(iter->dst.rt6_next,
+				lockdep_is_held(&rt->rt6i_table->tb6_lock))) {
 		/*
 		 *	Search for duplicates
 		 */
@@ -936,7 +956,8 @@ next_iter:
 	if (fallback_ins && !found) {
 		/* No ECMP-able route found, replace first non-ECMP one */
 		ins = fallback_ins;
-		iter = *ins;
+		iter = rcu_dereference_protected(*ins,
+				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 		found++;
 	}
 
@@ -950,7 +971,7 @@ next_iter:
 		struct rt6_info *sibling, *temp_sibling;
 
 		/* Find the first route that have the same metric */
-		sibling = fn->leaf;
+		sibling = leaf;
 		while (sibling) {
 			if (sibling->rt6i_metric == rt->rt6i_metric &&
 			    rt6_qualify_for_ecmp(sibling)) {
@@ -958,7 +979,8 @@ next_iter:
 					      &sibling->rt6i_siblings);
 				break;
 			}
-			sibling = sibling->dst.rt6_next;
+			sibling = rcu_dereference_protected(sibling->dst.rt6_next,
+				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 		}
 		/* For each sibling in the list, increment the counter of
 		 * siblings. BUG() if counters does not match, list of siblings
@@ -987,12 +1009,12 @@ add:
 		if (err)
 			return err;
 
-		rt->dst.rt6_next = iter;
-		*ins = rt;
-		rcu_assign_pointer(rt->rt6i_node, fn);
+		rcu_assign_pointer(rt->dst.rt6_next, iter);
 		atomic_inc(&rt->rt6i_ref);
+		rcu_assign_pointer(rt->rt6i_node, fn);
+		rcu_assign_pointer(*ins, rt);
 		call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_ADD,
-					  rt);
+					  rt, extack);
 		if (!info->skip_notify)
 			inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
 		info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
@@ -1016,12 +1038,12 @@ add:
 		if (err)
 			return err;
 
-		*ins = rt;
+		atomic_inc(&rt->rt6i_ref);
 		rcu_assign_pointer(rt->rt6i_node, fn);
 		rt->dst.rt6_next = iter->dst.rt6_next;
-		atomic_inc(&rt->rt6i_ref);
+		rcu_assign_pointer(*ins, rt);
 		call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE,
-					  rt);
+					  rt, extack);
 		if (!info->skip_notify)
 			inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
 		if (!(fn->fn_flags & RTN_RTINFO)) {
@@ -1031,14 +1053,15 @@ add:
 		nsiblings = iter->rt6i_nsiblings;
 		iter->rt6i_node = NULL;
 		fib6_purge_rt(iter, fn, info->nl_net);
-		if (fn->rr_ptr == iter)
+		if (rcu_access_pointer(fn->rr_ptr) == iter)
 			fn->rr_ptr = NULL;
 		rt6_release(iter);
 
 		if (nsiblings) {
 			/* Replacing an ECMP route, remove all siblings */
 			ins = &rt->dst.rt6_next;
-			iter = *ins;
+			iter = rcu_dereference_protected(*ins,
+				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 			while (iter) {
 				if (iter->rt6i_metric > rt->rt6i_metric)
 					break;
@@ -1046,14 +1069,16 @@ add:
 					*ins = iter->dst.rt6_next;
 					iter->rt6i_node = NULL;
 					fib6_purge_rt(iter, fn, info->nl_net);
-					if (fn->rr_ptr == iter)
+					if (rcu_access_pointer(fn->rr_ptr) == iter)
 						fn->rr_ptr = NULL;
 					rt6_release(iter);
 					nsiblings--;
+					info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
 				} else {
 					ins = &iter->dst.rt6_next;
 				}
-				iter = *ins;
+				iter = rcu_dereference_protected(*ins,
+					lockdep_is_held(&rt->rt6i_table->tb6_lock));
 			}
 			WARN_ON(nsiblings != 0);
 		}
@@ -1077,16 +1102,33 @@ void fib6_force_start_gc(struct net *net)
 			  jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
 }
 
+static void fib6_update_sernum_upto_root(struct rt6_info *rt,
+					 int sernum)
+{
+	struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
+				lockdep_is_held(&rt->rt6i_table->tb6_lock));
+
+	/* paired with smp_rmb() in rt6_get_cookie_safe() */
+	smp_wmb();
+	while (fn) {
+		fn->fn_sernum = sernum;
+		fn = rcu_dereference_protected(fn->parent,
+				lockdep_is_held(&rt->rt6i_table->tb6_lock));
+	}
+}
+
 /*
  *	Add routing information to the routing tree.
  *	<destination addr>/<source addr>
  *	with source addr info in sub-trees
+ *	Need to own table->tb6_lock
  */
 
 int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 	     struct nl_info *info, struct mx6_config *mxc,
 	     struct netlink_ext_ack *extack)
 {
+	struct fib6_table *table = rt->rt6i_table;
 	struct fib6_node *fn, *pn = NULL;
 	int err = -ENOMEM;
 	int allow_create = 1;
@@ -1095,6 +1137,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 
 	if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt)))
 		return -EINVAL;
+	if (WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE))
+		return -EINVAL;
 
 	if (info->nlh) {
 		if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -1105,9 +1149,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 	if (!allow_create && !replace_required)
 		pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n");
 
-	fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen,
+	fn = fib6_add_1(info->nl_net, table, root,
+			&rt->rt6i_dst.addr, rt->rt6i_dst.plen,
 			offsetof(struct rt6_info, rt6i_dst), allow_create,
-			replace_required, sernum, extack);
+			replace_required, extack);
 	if (IS_ERR(fn)) {
 		err = PTR_ERR(fn);
 		fn = NULL;
@@ -1120,7 +1165,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 	if (rt->rt6i_src.plen) {
 		struct fib6_node *sn;
 
-		if (!fn->subtree) {
+		if (!rcu_access_pointer(fn->subtree)) {
 			struct fib6_node *sfn;
 
 			/*
@@ -1134,42 +1179,40 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			 */
 
 			/* Create subtree root node */
-			sfn = node_alloc();
+			sfn = node_alloc(info->nl_net);
 			if (!sfn)
 				goto failure;
 
-			sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
 			atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
+			rcu_assign_pointer(sfn->leaf,
+					   info->nl_net->ipv6.ip6_null_entry);
 			sfn->fn_flags = RTN_ROOT;
-			sfn->fn_sernum = sernum;
 
 			/* Now add the first leaf node to new subtree */
 
-			sn = fib6_add_1(sfn, &rt->rt6i_src.addr,
-					rt->rt6i_src.plen,
+			sn = fib6_add_1(info->nl_net, table, sfn,
+					&rt->rt6i_src.addr, rt->rt6i_src.plen,
 					offsetof(struct rt6_info, rt6i_src),
-					allow_create, replace_required, sernum,
-					extack);
+					allow_create, replace_required, extack);
 
 			if (IS_ERR(sn)) {
 				/* If it is failed, discard just allocated
 				   root, and then (in failure) stale node
 				   in main tree.
 				 */
-				node_free_immediate(sfn);
+				node_free_immediate(info->nl_net, sfn);
 				err = PTR_ERR(sn);
 				goto failure;
 			}
 
 			/* Now link new subtree to main tree */
-			sfn->parent = fn;
-			fn->subtree = sfn;
+			rcu_assign_pointer(sfn->parent, fn);
+			rcu_assign_pointer(fn->subtree, sfn);
 		} else {
-			sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr,
-					rt->rt6i_src.plen,
+			sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn),
+					&rt->rt6i_src.addr, rt->rt6i_src.plen,
 					offsetof(struct rt6_info, rt6i_src),
-					allow_create, replace_required, sernum,
-					extack);
+					allow_create, replace_required, extack);
 
 			if (IS_ERR(sn)) {
 				err = PTR_ERR(sn);
@@ -1177,19 +1220,18 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			}
 		}
 
-		if (!fn->leaf) {
-			fn->leaf = rt;
+		if (!rcu_access_pointer(fn->leaf)) {
 			atomic_inc(&rt->rt6i_ref);
+			rcu_assign_pointer(fn->leaf, rt);
 		}
 		fn = sn;
 	}
 #endif
 
-	err = fib6_add_rt2node(fn, rt, info, mxc);
+	err = fib6_add_rt2node(fn, rt, info, mxc, extack);
 	if (!err) {
+		fib6_update_sernum_upto_root(rt, sernum);
 		fib6_start_gc(info->nl_net, rt);
-		if (!(rt->rt6i_flags & RTF_CACHE))
-			fib6_prune_clones(info->nl_net, pn);
 	}
 
 out:
@@ -1199,19 +1241,23 @@ out:
 		 * If fib6_add_1 has cleared the old leaf pointer in the
 		 * super-tree leaf node we have to find a new one for it.
 		 */
-		if (pn != fn && pn->leaf == rt) {
-			pn->leaf = NULL;
+		struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf,
+					    lockdep_is_held(&table->tb6_lock));
+		if (pn != fn && pn_leaf == rt) {
+			pn_leaf = NULL;
+			RCU_INIT_POINTER(pn->leaf, NULL);
 			atomic_dec(&rt->rt6i_ref);
 		}
-		if (pn != fn && !pn->leaf && !(pn->fn_flags & RTN_RTINFO)) {
-			pn->leaf = fib6_find_prefix(info->nl_net, pn);
+		if (pn != fn && !pn_leaf && !(pn->fn_flags & RTN_RTINFO)) {
+			pn_leaf = fib6_find_prefix(info->nl_net, table, pn);
 #if RT6_DEBUG >= 2
-			if (!pn->leaf) {
-				WARN_ON(pn->leaf == NULL);
-				pn->leaf = info->nl_net->ipv6.ip6_null_entry;
+			if (!pn_leaf) {
+				WARN_ON(!pn_leaf);
+				pn_leaf = info->nl_net->ipv6.ip6_null_entry;
 			}
 #endif
-			atomic_inc(&pn->leaf->rt6i_ref);
+			atomic_inc(&pn_leaf->rt6i_ref);
+			rcu_assign_pointer(pn->leaf, pn_leaf);
 		}
 #endif
 		goto failure;
@@ -1226,7 +1272,7 @@ failure:
 	 * fn->leaf.
 	 */
 	if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)))
-		fib6_repair_tree(info->nl_net, fn);
+		fib6_repair_tree(info->nl_net, table, fn);
 	/* Always release dst as dst->__refcnt is guaranteed
 	 * to be taken before entering this function
 	 */
@@ -1264,7 +1310,8 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
 
 		dir = addr_bit_set(args->addr, fn->fn_bit);
 
-		next = dir ? fn->right : fn->left;
+		next = dir ? rcu_dereference(fn->right) :
+			     rcu_dereference(fn->left);
 
 		if (next) {
 			fn = next;
@@ -1274,18 +1321,22 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
 	}
 
 	while (fn) {
-		if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) {
+		struct fib6_node *subtree = FIB6_SUBTREE(fn);
+
+		if (subtree || fn->fn_flags & RTN_RTINFO) {
+			struct rt6_info *leaf = rcu_dereference(fn->leaf);
 			struct rt6key *key;
 
-			key = (struct rt6key *) ((u8 *) fn->leaf +
-						 args->offset);
+			if (!leaf)
+				goto backtrack;
+
+			key = (struct rt6key *) ((u8 *)leaf + args->offset);
 
 			if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) {
 #ifdef CONFIG_IPV6_SUBTREES
-				if (fn->subtree) {
+				if (subtree) {
 					struct fib6_node *sfn;
-					sfn = fib6_lookup_1(fn->subtree,
-							    args + 1);
+					sfn = fib6_lookup_1(subtree, args + 1);
 					if (!sfn)
 						goto backtrack;
 					fn = sfn;
@@ -1295,18 +1346,18 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
 					return fn;
 			}
 		}
-#ifdef CONFIG_IPV6_SUBTREES
 backtrack:
-#endif
 		if (fn->fn_flags & RTN_ROOT)
 			break;
 
-		fn = fn->parent;
+		fn = rcu_dereference(fn->parent);
 	}
 
 	return NULL;
 }
 
+/* called with rcu_read_lock() held
+ */
 struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
 			      const struct in6_addr *saddr)
 {
@@ -1337,54 +1388,87 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *dad
 /*
  *	Get node with specified destination prefix (and source prefix,
  *	if subtrees are used)
+ *	exact_match == true means we try to find fn with exact match of
+ *	the passed in prefix addr
+ *	exact_match == false means we try to find fn with longest prefix
+ *	match of the passed in prefix addr. This is useful for finding fn
+ *	for cached route as it will be stored in the exception table under
+ *	the node with longest prefix length.
  */
 
 
 static struct fib6_node *fib6_locate_1(struct fib6_node *root,
 				       const struct in6_addr *addr,
-				       int plen, int offset)
+				       int plen, int offset,
+				       bool exact_match)
 {
-	struct fib6_node *fn;
+	struct fib6_node *fn, *prev = NULL;
 
 	for (fn = root; fn ; ) {
-		struct rt6key *key = (struct rt6key *)((u8 *)fn->leaf + offset);
+		struct rt6_info *leaf = rcu_dereference(fn->leaf);
+		struct rt6key *key;
+
+		/* This node is being deleted */
+		if (!leaf) {
+			if (plen <= fn->fn_bit)
+				goto out;
+			else
+				goto next;
+		}
+
+		key = (struct rt6key *)((u8 *)leaf + offset);
 
 		/*
 		 *	Prefix match
 		 */
 		if (plen < fn->fn_bit ||
 		    !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit))
-			return NULL;
+			goto out;
 
 		if (plen == fn->fn_bit)
 			return fn;
 
+		prev = fn;
+
+next:
 		/*
 		 *	We have more bits to go
 		 */
 		if (addr_bit_set(addr, fn->fn_bit))
-			fn = fn->right;
+			fn = rcu_dereference(fn->right);
 		else
-			fn = fn->left;
+			fn = rcu_dereference(fn->left);
 	}
-	return NULL;
+out:
+	if (exact_match)
+		return NULL;
+	else
+		return prev;
 }
 
 struct fib6_node *fib6_locate(struct fib6_node *root,
 			      const struct in6_addr *daddr, int dst_len,
-			      const struct in6_addr *saddr, int src_len)
+			      const struct in6_addr *saddr, int src_len,
+			      bool exact_match)
 {
 	struct fib6_node *fn;
 
 	fn = fib6_locate_1(root, daddr, dst_len,
-			   offsetof(struct rt6_info, rt6i_dst));
+			   offsetof(struct rt6_info, rt6i_dst),
+			   exact_match);
 
 #ifdef CONFIG_IPV6_SUBTREES
 	if (src_len) {
 		WARN_ON(saddr == NULL);
-		if (fn && fn->subtree)
-			fn = fib6_locate_1(fn->subtree, saddr, src_len,
-					   offsetof(struct rt6_info, rt6i_src));
+		if (fn) {
+			struct fib6_node *subtree = FIB6_SUBTREE(fn);
+
+			if (subtree) {
+				fn = fib6_locate_1(subtree, saddr, src_len,
+					   offsetof(struct rt6_info, rt6i_src),
+					   exact_match);
+			}
+		}
 	}
 #endif
 
@@ -1400,16 +1484,26 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
  *
  */
 
-static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn)
+static struct rt6_info *fib6_find_prefix(struct net *net,
+					 struct fib6_table *table,
+					 struct fib6_node *fn)
 {
+	struct fib6_node *child_left, *child_right;
+
 	if (fn->fn_flags & RTN_ROOT)
 		return net->ipv6.ip6_null_entry;
 
 	while (fn) {
-		if (fn->left)
-			return fn->left->leaf;
-		if (fn->right)
-			return fn->right->leaf;
+		child_left = rcu_dereference_protected(fn->left,
+				    lockdep_is_held(&table->tb6_lock));
+		child_right = rcu_dereference_protected(fn->right,
+				    lockdep_is_held(&table->tb6_lock));
+		if (child_left)
+			return rcu_dereference_protected(child_left->leaf,
+					lockdep_is_held(&table->tb6_lock));
+		if (child_right)
+			return rcu_dereference_protected(child_right->leaf,
+					lockdep_is_held(&table->tb6_lock));
 
 		fn = FIB6_SUBTREE(fn);
 	}
@@ -1419,31 +1513,49 @@ static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn)
 /*
  *	Called to trim the tree of intermediate nodes when possible. "fn"
  *	is the node we want to try and remove.
+ *	Need to own table->tb6_lock
  */
 
 static struct fib6_node *fib6_repair_tree(struct net *net,
-					   struct fib6_node *fn)
+					  struct fib6_table *table,
+					  struct fib6_node *fn)
 {
 	int children;
 	int nstate;
-	struct fib6_node *child, *pn;
+	struct fib6_node *child;
 	struct fib6_walker *w;
 	int iter = 0;
 
 	for (;;) {
+		struct fib6_node *fn_r = rcu_dereference_protected(fn->right,
+					    lockdep_is_held(&table->tb6_lock));
+		struct fib6_node *fn_l = rcu_dereference_protected(fn->left,
+					    lockdep_is_held(&table->tb6_lock));
+		struct fib6_node *pn = rcu_dereference_protected(fn->parent,
+					    lockdep_is_held(&table->tb6_lock));
+		struct fib6_node *pn_r = rcu_dereference_protected(pn->right,
+					    lockdep_is_held(&table->tb6_lock));
+		struct fib6_node *pn_l = rcu_dereference_protected(pn->left,
+					    lockdep_is_held(&table->tb6_lock));
+		struct rt6_info *fn_leaf = rcu_dereference_protected(fn->leaf,
+					    lockdep_is_held(&table->tb6_lock));
+		struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf,
+					    lockdep_is_held(&table->tb6_lock));
+		struct rt6_info *new_fn_leaf;
+
 		RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter);
 		iter++;
 
 		WARN_ON(fn->fn_flags & RTN_RTINFO);
 		WARN_ON(fn->fn_flags & RTN_TL_ROOT);
-		WARN_ON(fn->leaf);
+		WARN_ON(fn_leaf);
 
 		children = 0;
 		child = NULL;
-		if (fn->right)
-			child = fn->right, children |= 1;
-		if (fn->left)
-			child = fn->left, children |= 2;
+		if (fn_r)
+			child = fn_r, children |= 1;
+		if (fn_l)
+			child = fn_l, children |= 2;
 
 		if (children == 3 || FIB6_SUBTREE(fn)
 #ifdef CONFIG_IPV6_SUBTREES
@@ -1451,36 +1563,36 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 		    || (children && fn->fn_flags & RTN_ROOT)
 #endif
 		    ) {
-			fn->leaf = fib6_find_prefix(net, fn);
+			new_fn_leaf = fib6_find_prefix(net, table, fn);
 #if RT6_DEBUG >= 2
-			if (!fn->leaf) {
-				WARN_ON(!fn->leaf);
-				fn->leaf = net->ipv6.ip6_null_entry;
+			if (!new_fn_leaf) {
+				WARN_ON(!new_fn_leaf);
+				new_fn_leaf = net->ipv6.ip6_null_entry;
 			}
 #endif
-			atomic_inc(&fn->leaf->rt6i_ref);
-			return fn->parent;
+			atomic_inc(&new_fn_leaf->rt6i_ref);
+			rcu_assign_pointer(fn->leaf, new_fn_leaf);
+			return pn;
 		}
 
-		pn = fn->parent;
 #ifdef CONFIG_IPV6_SUBTREES
 		if (FIB6_SUBTREE(pn) == fn) {
 			WARN_ON(!(fn->fn_flags & RTN_ROOT));
-			FIB6_SUBTREE(pn) = NULL;
+			RCU_INIT_POINTER(pn->subtree, NULL);
 			nstate = FWS_L;
 		} else {
 			WARN_ON(fn->fn_flags & RTN_ROOT);
 #endif
-			if (pn->right == fn)
-				pn->right = child;
-			else if (pn->left == fn)
-				pn->left = child;
+			if (pn_r == fn)
+				rcu_assign_pointer(pn->right, child);
+			else if (pn_l == fn)
+				rcu_assign_pointer(pn->left, child);
 #if RT6_DEBUG >= 2
 			else
 				WARN_ON(1);
 #endif
 			if (child)
-				child->parent = pn;
+				rcu_assign_pointer(child->parent, pn);
 			nstate = FWS_R;
 #ifdef CONFIG_IPV6_SUBTREES
 		}
@@ -1489,19 +1601,12 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 		read_lock(&net->ipv6.fib6_walker_lock);
 		FOR_WALKERS(net, w) {
 			if (!child) {
-				if (w->root == fn) {
-					w->root = w->node = NULL;
-					RT6_TRACE("W %p adjusted by delroot 1\n", w);
-				} else if (w->node == fn) {
+				if (w->node == fn) {
 					RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate);
 					w->node = pn;
 					w->state = nstate;
 				}
 			} else {
-				if (w->root == fn) {
-					w->root = child;
-					RT6_TRACE("W %p adjusted by delroot 2\n", w);
-				}
 				if (w->node == fn) {
 					w->node = child;
 					if (children&2) {
@@ -1516,33 +1621,39 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 		}
 		read_unlock(&net->ipv6.fib6_walker_lock);
 
-		node_free(fn);
+		node_free(net, fn);
 		if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn))
 			return pn;
 
-		rt6_release(pn->leaf);
-		pn->leaf = NULL;
+		RCU_INIT_POINTER(pn->leaf, NULL);
+		rt6_release(pn_leaf);
 		fn = pn;
 	}
 }
 
-static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
-			   struct nl_info *info)
+static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
+			   struct rt6_info __rcu **rtp, struct nl_info *info)
 {
 	struct fib6_walker *w;
-	struct rt6_info *rt = *rtp;
+	struct rt6_info *rt = rcu_dereference_protected(*rtp,
+				    lockdep_is_held(&table->tb6_lock));
 	struct net *net = info->nl_net;
 
 	RT6_TRACE("fib6_del_route\n");
 
+	WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE);
+
 	/* Unlink it */
 	*rtp = rt->dst.rt6_next;
 	rt->rt6i_node = NULL;
 	net->ipv6.rt6_stats->fib_rt_entries--;
 	net->ipv6.rt6_stats->fib_discarded_routes++;
 
+	/* Flush all cached dst in exception table */
+	rt6_flush_exceptions(rt);
+
 	/* Reset round-robin state, if necessary */
-	if (fn->rr_ptr == rt)
+	if (rcu_access_pointer(fn->rr_ptr) == rt)
 		fn->rr_ptr = NULL;
 
 	/* Remove this entry from other siblings */
@@ -1561,36 +1672,38 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 	FOR_WALKERS(net, w) {
 		if (w->state == FWS_C && w->leaf == rt) {
 			RT6_TRACE("walker %p adjusted by delroute\n", w);
-			w->leaf = rt->dst.rt6_next;
+			w->leaf = rcu_dereference_protected(rt->dst.rt6_next,
+					    lockdep_is_held(&table->tb6_lock));
 			if (!w->leaf)
 				w->state = FWS_U;
 		}
 	}
 	read_unlock(&net->ipv6.fib6_walker_lock);
 
-	rt->dst.rt6_next = NULL;
-
 	/* If it was last route, expunge its radix tree node */
-	if (!fn->leaf) {
+	if (!rcu_access_pointer(fn->leaf)) {
 		fn->fn_flags &= ~RTN_RTINFO;
 		net->ipv6.rt6_stats->fib_route_nodes--;
-		fn = fib6_repair_tree(net, fn);
+		fn = fib6_repair_tree(net, table, fn);
 	}
 
 	fib6_purge_rt(rt, fn, net);
 
-	call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt);
+	call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL);
 	if (!info->skip_notify)
 		inet6_rt_notify(RTM_DELROUTE, rt, info, 0);
 	rt6_release(rt);
 }
 
+/* Need to own table->tb6_lock */
 int fib6_del(struct rt6_info *rt, struct nl_info *info)
 {
 	struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
 				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
+	struct fib6_table *table = rt->rt6i_table;
 	struct net *net = info->nl_net;
-	struct rt6_info **rtp;
+	struct rt6_info __rcu **rtp;
+	struct rt6_info __rcu **rtp_next;
 
 #if RT6_DEBUG >= 2
 	if (rt->dst.obsolete > 0) {
@@ -1603,28 +1716,22 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
 
 	WARN_ON(!(fn->fn_flags & RTN_RTINFO));
 
-	if (!(rt->rt6i_flags & RTF_CACHE)) {
-		struct fib6_node *pn = fn;
-#ifdef CONFIG_IPV6_SUBTREES
-		/* clones of this route might be in another subtree */
-		if (rt->rt6i_src.plen) {
-			while (!(pn->fn_flags & RTN_ROOT))
-				pn = pn->parent;
-			pn = pn->parent;
-		}
-#endif
-		fib6_prune_clones(info->nl_net, pn);
-	}
+	/* remove cached dst from exception table */
+	if (rt->rt6i_flags & RTF_CACHE)
+		return rt6_remove_exception_rt(rt);
 
 	/*
 	 *	Walk the leaf entries looking for ourself
 	 */
 
-	for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->dst.rt6_next) {
-		if (*rtp == rt) {
-			fib6_del_route(fn, rtp, info);
+	for (rtp = &fn->leaf; *rtp; rtp = rtp_next) {
+		struct rt6_info *cur = rcu_dereference_protected(*rtp,
+					lockdep_is_held(&table->tb6_lock));
+		if (rt == cur) {
+			fib6_del_route(table, fn, rtp, info);
 			return 0;
 		}
+		rtp_next = &cur->dst.rt6_next;
 	}
 	return -ENOENT;
 }
@@ -1651,22 +1758,22 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
  *	0   -> walk is complete.
  *	>0  -> walk is incomplete (i.e. suspended)
  *	<0  -> walk is terminated by an error.
+ *
+ *	This function is called with tb6_lock held.
  */
 
 static int fib6_walk_continue(struct fib6_walker *w)
 {
-	struct fib6_node *fn, *pn;
+	struct fib6_node *fn, *pn, *left, *right;
+
+	/* w->root should always be table->tb6_root */
+	WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT));
 
 	for (;;) {
 		fn = w->node;
 		if (!fn)
 			return 0;
 
-		if (w->prune && fn != w->root &&
-		    fn->fn_flags & RTN_RTINFO && w->state < FWS_C) {
-			w->state = FWS_C;
-			w->leaf = fn->leaf;
-		}
 		switch (w->state) {
 #ifdef CONFIG_IPV6_SUBTREES
 		case FWS_S:
@@ -1676,21 +1783,26 @@ static int fib6_walk_continue(struct fib6_walker *w)
 			}
 			w->state = FWS_L;
 #endif
+			/* fall through */
 		case FWS_L:
-			if (fn->left) {
-				w->node = fn->left;
+			left = rcu_dereference_protected(fn->left, 1);
+			if (left) {
+				w->node = left;
 				w->state = FWS_INIT;
 				continue;
 			}
 			w->state = FWS_R;
+			/* fall through */
 		case FWS_R:
-			if (fn->right) {
-				w->node = fn->right;
+			right = rcu_dereference_protected(fn->right, 1);
+			if (right) {
+				w->node = right;
 				w->state = FWS_INIT;
 				continue;
 			}
 			w->state = FWS_C;
-			w->leaf = fn->leaf;
+			w->leaf = rcu_dereference_protected(fn->leaf, 1);
+			/* fall through */
 		case FWS_C:
 			if (w->leaf && fn->fn_flags & RTN_RTINFO) {
 				int err;
@@ -1709,10 +1821,13 @@ static int fib6_walk_continue(struct fib6_walker *w)
 			}
 skip:
 			w->state = FWS_U;
+			/* fall through */
 		case FWS_U:
 			if (fn == w->root)
 				return 0;
-			pn = fn->parent;
+			pn = rcu_dereference_protected(fn->parent, 1);
+			left = rcu_dereference_protected(pn->left, 1);
+			right = rcu_dereference_protected(pn->right, 1);
 			w->node = pn;
 #ifdef CONFIG_IPV6_SUBTREES
 			if (FIB6_SUBTREE(pn) == fn) {
@@ -1721,13 +1836,13 @@ skip:
 				continue;
 			}
 #endif
-			if (pn->left == fn) {
+			if (left == fn) {
 				w->state = FWS_R;
 				continue;
 			}
-			if (pn->right == fn) {
+			if (right == fn) {
 				w->state = FWS_C;
-				w->leaf = w->node->leaf;
+				w->leaf = rcu_dereference_protected(w->node->leaf, 1);
 				continue;
 			}
 #if RT6_DEBUG >= 2
@@ -1770,7 +1885,7 @@ static int fib6_clean_node(struct fib6_walker *w)
 		return 0;
 	}
 
-	for (rt = w->leaf; rt; rt = rt->dst.rt6_next) {
+	for_each_fib6_walker_rt(w) {
 		res = c->func(rt, c->arg);
 		if (res < 0) {
 			w->leaf = rt;
@@ -1798,20 +1913,16 @@ static int fib6_clean_node(struct fib6_walker *w)
  *	func is called on each route.
  *		It may return -1 -> delete this route.
  *		              0  -> continue walking
- *
- *	prune==1 -> only immediate children of node (certainly,
- *	ignoring pure split nodes) will be scanned.
  */
 
 static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 			    int (*func)(struct rt6_info *, void *arg),
-			    bool prune, int sernum, void *arg)
+			    int sernum, void *arg)
 {
 	struct fib6_cleaner c;
 
 	c.w.root = root;
 	c.w.func = fib6_clean_node;
-	c.w.prune = prune;
 	c.w.count = 0;
 	c.w.skip = 0;
 	c.func = func;
@@ -1834,10 +1945,10 @@ static void __fib6_clean_all(struct net *net,
 	for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
 		head = &net->ipv6.fib_table_hash[h];
 		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
-			write_lock_bh(&table->tb6_lock);
+			spin_lock_bh(&table->tb6_lock);
 			fib6_clean_tree(net, &table->tb6_root,
-					func, false, sernum, arg);
-			write_unlock_bh(&table->tb6_lock);
+					func, sernum, arg);
+			spin_unlock_bh(&table->tb6_lock);
 		}
 	}
 	rcu_read_unlock();
@@ -1849,22 +1960,6 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *),
 	__fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg);
 }
 
-static int fib6_prune_clone(struct rt6_info *rt, void *arg)
-{
-	if (rt->rt6i_flags & RTF_CACHE) {
-		RT6_TRACE("pruning clone %p\n", rt);
-		return -1;
-	}
-
-	return 0;
-}
-
-static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
-{
-	fib6_clean_tree(net, fn, fib6_prune_clone, true,
-			FIB6_NO_SERNUM_CHANGE, NULL);
-}
-
 static void fib6_flush_trees(struct net *net)
 {
 	int new_sernum = fib6_new_sernum(net);
@@ -1876,12 +1971,6 @@ static void fib6_flush_trees(struct net *net)
  *	Garbage collection
  */
 
-struct fib6_gc_args
-{
-	int			timeout;
-	int			more;
-};
-
 static int fib6_age(struct rt6_info *rt, void *arg)
 {
 	struct fib6_gc_args *gc_args = arg;
@@ -1890,9 +1979,6 @@ static int fib6_age(struct rt6_info *rt, void *arg)
 	/*
 	 *	check addrconf expiration here.
 	 *	Routes are expired even if they are in use.
-	 *
-	 *	Also age clones. Note, that clones are aged out
-	 *	only if they are not in use now.
 	 */
 
 	if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) {
@@ -1901,31 +1987,14 @@ static int fib6_age(struct rt6_info *rt, void *arg)
 			return -1;
 		}
 		gc_args->more++;
-	} else if (rt->rt6i_flags & RTF_CACHE) {
-		if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout))
-			rt->dst.obsolete = DST_OBSOLETE_KILL;
-		if (atomic_read(&rt->dst.__refcnt) == 1 &&
-		    rt->dst.obsolete == DST_OBSOLETE_KILL) {
-			RT6_TRACE("aging clone %p\n", rt);
-			return -1;
-		} else if (rt->rt6i_flags & RTF_GATEWAY) {
-			struct neighbour *neigh;
-			__u8 neigh_flags = 0;
-
-			neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway);
-			if (neigh) {
-				neigh_flags = neigh->flags;
-				neigh_release(neigh);
-			}
-			if (!(neigh_flags & NTF_ROUTER)) {
-				RT6_TRACE("purging route %p via non-router but gateway\n",
-					  rt);
-				return -1;
-			}
-		}
-		gc_args->more++;
 	}
 
+	/*	Also age clones in the exception table.
+	 *	Note, that clones are aged out
+	 *	only if they are not in use now.
+	 */
+	rt6_age_exceptions(rt, gc_args, now);
+
 	return 0;
 }
 
@@ -1993,7 +2062,8 @@ static int __net_init fib6_net_init(struct net *net)
 		goto out_fib_table_hash;
 
 	net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN;
-	net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry;
+	rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf,
+			   net->ipv6.ip6_null_entry);
 	net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
 		RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 	inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers);
@@ -2004,7 +2074,8 @@ static int __net_init fib6_net_init(struct net *net)
 	if (!net->ipv6.fib6_local_tbl)
 		goto out_fib6_main_tbl;
 	net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL;
-	net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry;
+	rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf,
+			   net->ipv6.ip6_null_entry);
 	net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
 		RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 	inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers);
@@ -2134,7 +2205,9 @@ static int ipv6_route_yield(struct fib6_walker *w)
 		return 1;
 
 	do {
-		iter->w.leaf = iter->w.leaf->dst.rt6_next;
+		iter->w.leaf = rcu_dereference_protected(
+				iter->w.leaf->dst.rt6_next,
+				lockdep_is_held(&iter->tbl->tb6_lock));
 		iter->skip--;
 		if (!iter->skip && iter->w.leaf)
 			return 1;
@@ -2199,7 +2272,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	if (!v)
 		goto iter_table;
 
-	n = ((struct rt6_info *)v)->dst.rt6_next;
+	n = rcu_dereference_bh(((struct rt6_info *)v)->dst.rt6_next);
 	if (n) {
 		++*pos;
 		return n;
@@ -2207,9 +2280,9 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 iter_table:
 	ipv6_route_check_sernum(iter);
-	read_lock(&iter->tbl->tb6_lock);
+	spin_lock_bh(&iter->tbl->tb6_lock);
 	r = fib6_walk_continue(&iter->w);
-	read_unlock(&iter->tbl->tb6_lock);
+	spin_unlock_bh(&iter->tbl->tb6_lock);
 	if (r > 0) {
 		if (v)
 			++*pos;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 59c121b932ac..3e10c51e7e0c 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1164,19 +1164,21 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit ip6gre_exit_net(struct net *net)
+static void __net_exit ip6gre_exit_batch_net(struct list_head *net_list)
 {
+	struct net *net;
 	LIST_HEAD(list);
 
 	rtnl_lock();
-	ip6gre_destroy_tunnels(net, &list);
+	list_for_each_entry(net, net_list, exit_list)
+		ip6gre_destroy_tunnels(net, &list);
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
 
 static struct pernet_operations ip6gre_net_ops = {
 	.init = ip6gre_init_net,
-	.exit = ip6gre_exit_net,
+	.exit_batch = ip6gre_exit_batch_net,
 	.id   = &ip6gre_net_id,
 	.size = sizeof(struct ip6gre_net),
 };
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a1c24443cd9e..439d65f7e094 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -593,6 +593,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	case NDISC_REDIRECT:
 		rel_type = ICMP_REDIRECT;
 		rel_code = ICMP_REDIR_HOST;
+		/* fall through */
 	default:
 		return 0;
 	}
@@ -769,7 +770,8 @@ int ip6_tnl_rcv_ctl(struct ip6_tnl *t,
 
 		if ((ipv6_addr_is_multicast(laddr) ||
 		     likely(ipv6_chk_addr(net, laddr, ldev, 0))) &&
-		    likely(!ipv6_chk_addr(net, raddr, NULL, 0)))
+		    ((p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) ||
+		     likely(!ipv6_chk_addr(net, raddr, NULL, 0))))
 			ret = 1;
 	}
 	return ret;
@@ -999,7 +1001,8 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t,
 		if (unlikely(!ipv6_chk_addr(net, laddr, ldev, 0)))
 			pr_warn("%s xmit: Local address not yet configured!\n",
 				p->name);
-		else if (!ipv6_addr_is_multicast(raddr) &&
+		else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) &&
+			 !ipv6_addr_is_multicast(raddr) &&
 			 unlikely(ipv6_chk_addr(net, raddr, NULL, 0)))
 			pr_warn("%s xmit: Routing loop! Remote address found on this node!\n",
 				p->name);
@@ -2168,17 +2171,16 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = {
 	.priority	=	1,
 };
 
-static void __net_exit ip6_tnl_destroy_tunnels(struct net *net)
+static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head *list)
 {
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	struct net_device *dev, *aux;
 	int h;
 	struct ip6_tnl *t;
-	LIST_HEAD(list);
 
 	for_each_netdev_safe(net, dev, aux)
 		if (dev->rtnl_link_ops == &ip6_link_ops)
-			unregister_netdevice_queue(dev, &list);
+			unregister_netdevice_queue(dev, list);
 
 	for (h = 0; h < IP6_TUNNEL_HASH_SIZE; h++) {
 		t = rtnl_dereference(ip6n->tnls_r_l[h]);
@@ -2187,12 +2189,10 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net)
 			 * been added to the list by the previous loop.
 			 */
 			if (!net_eq(dev_net(t->dev), net))
-				unregister_netdevice_queue(t->dev, &list);
+				unregister_netdevice_queue(t->dev, list);
 			t = rtnl_dereference(t->next);
 		}
 	}
-
-	unregister_netdevice_many(&list);
 }
 
 static int __net_init ip6_tnl_init_net(struct net *net)
@@ -2236,16 +2236,21 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit ip6_tnl_exit_net(struct net *net)
+static void __net_exit ip6_tnl_exit_batch_net(struct list_head *net_list)
 {
+	struct net *net;
+	LIST_HEAD(list);
+
 	rtnl_lock();
-	ip6_tnl_destroy_tunnels(net);
+	list_for_each_entry(net, net_list, exit_list)
+		ip6_tnl_destroy_tunnels(net, &list);
+	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
 
 static struct pernet_operations ip6_tnl_net_ops = {
 	.init = ip6_tnl_init_net,
-	.exit = ip6_tnl_exit_net,
+	.exit_batch = ip6_tnl_exit_batch_net,
 	.id   = &ip6_tnl_net_id,
 	.size = sizeof(struct ip6_tnl_net),
 };
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index bcdc2d557de1..dbb74f3c57a7 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -1053,23 +1053,22 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = {
 	.get_link_net	= ip6_tnl_get_link_net,
 };
 
-static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n)
+static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n,
+					    struct list_head *list)
 {
 	int h;
 	struct ip6_tnl *t;
-	LIST_HEAD(list);
 
 	for (h = 0; h < IP6_VTI_HASH_SIZE; h++) {
 		t = rtnl_dereference(ip6n->tnls_r_l[h]);
 		while (t) {
-			unregister_netdevice_queue(t->dev, &list);
+			unregister_netdevice_queue(t->dev, list);
 			t = rtnl_dereference(t->next);
 		}
 	}
 
 	t = rtnl_dereference(ip6n->tnls_wc[0]);
-	unregister_netdevice_queue(t->dev, &list);
-	unregister_netdevice_many(&list);
+	unregister_netdevice_queue(t->dev, list);
 }
 
 static int __net_init vti6_init_net(struct net *net)
@@ -1109,18 +1108,24 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit vti6_exit_net(struct net *net)
+static void __net_exit vti6_exit_batch_net(struct list_head *net_list)
 {
-	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+	struct vti6_net *ip6n;
+	struct net *net;
+	LIST_HEAD(list);
 
 	rtnl_lock();
-	vti6_destroy_tunnels(ip6n);
+	list_for_each_entry(net, net_list, exit_list) {
+		ip6n = net_generic(net, vti6_net_id);
+		vti6_destroy_tunnels(ip6n, &list);
+	}
+	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
 
 static struct pernet_operations vti6_net_ops = {
 	.init = vti6_init_net,
-	.exit = vti6_exit_net,
+	.exit_batch = vti6_exit_batch_net,
 	.id   = &vti6_net_id,
 	.size = sizeof(struct vti6_net),
 };
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index f5500f5444e9..59fad81e5f7a 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1722,6 +1722,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 	case MRT6_ADD_MFC:
 	case MRT6_DEL_MFC:
 		parent = -1;
+		/* fall through */
 	case MRT6_ADD_MFC_PROXY:
 	case MRT6_DEL_MFC_PROXY:
 		if (optlen < sizeof(mfc))
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index a5e466d4e093..b9404feabd78 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -377,6 +377,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		retv = 0;
 		break;
 
+	case IPV6_FREEBIND:
+		if (optlen < sizeof(int))
+			goto e_inval;
+		/* we also don't have a separate freebind bit for IPV6 */
+		inet_sk(sk)->freebind = valbool;
+		retv = 0;
+		break;
+
 	case IPV6_RECVORIGDSTADDR:
 		if (optlen < sizeof(int))
 			goto e_inval;
@@ -1214,6 +1222,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		val = inet_sk(sk)->transparent;
 		break;
 
+	case IPV6_FREEBIND:
+		val = inet_sk(sk)->freebind;
+		break;
+
 	case IPV6_RECVORIGDSTADDR:
 		val = np->rxopt.bits.rxorigdstaddr;
 		break;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 266a530414d7..f9c3ffe04382 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -46,6 +46,7 @@
 #endif
 
 #include <linux/if_addr.h>
+#include <linux/if_ether.h>
 #include <linux/if_arp.h>
 #include <linux/ipv6.h>
 #include <linux/icmpv6.h>
@@ -822,7 +823,7 @@ have_ifp:
 				 * who is doing DAD
 				 * so fail our DAD process
 				 */
-				addrconf_dad_failure(ifp);
+				addrconf_dad_failure(skb, ifp);
 				return;
 			} else {
 				/*
@@ -975,7 +976,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
 	if (ifp) {
 		if (skb->pkt_type != PACKET_LOOPBACK
 		    && (ifp->flags & IFA_F_TENTATIVE)) {
-				addrconf_dad_failure(ifp);
+				addrconf_dad_failure(skb, ifp);
 				return;
 		}
 		/* What should we make now? The advertisement
@@ -989,8 +990,8 @@ static void ndisc_recv_na(struct sk_buff *skb)
 		 */
 		if (skb->pkt_type != PACKET_LOOPBACK)
 			ND_PRINTK(1, warn,
-				  "NA: someone advertises our address %pI6 on %s!\n",
-				  &ifp->addr, ifp->idev->dev->name);
+				  "NA: %pM advertised our address %pI6c on %s!\n",
+				  eth_hdr(skb)->h_source, &ifp->addr, ifp->idev->dev->name);
 		in6_ifa_put(ifp);
 		return;
 	}
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index b263bf3a19f7..977d8900cfd1 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -169,12 +169,13 @@ static unsigned int nf_hashfn(const struct inet_frag_queue *q)
 	return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr);
 }
 
-static void nf_ct_frag6_expire(unsigned long data)
+static void nf_ct_frag6_expire(struct timer_list *t)
 {
+	struct inet_frag_queue *frag = from_timer(frag, t, timer);
 	struct frag_queue *fq;
 	struct net *net;
 
-	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+	fq = container_of(frag, struct frag_queue, q);
 	net = container_of(fq->q.net, struct net, nf_frag.frags);
 
 	ip6_expire_frag_queue(net, fq, &nf_frags);
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index 46d6dba50698..1d2fb9267d6f 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -290,7 +290,8 @@ nf_nat_ipv6_fn(void *priv, struct sk_buff *skb,
 			else
 				return NF_ACCEPT;
 		}
-		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
+		/* Only ICMPs can be IP_CT_IS_REPLY: */
+		/* fall through */
 	case IP_CT_NEW:
 		/* Seen it before?  This can happen for loopback, retrans,
 		 * or local packets.
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index ac826dd338ff..d12c55dad7d1 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -154,9 +154,8 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 				ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
-		err = icmpv6_push_pending_frames(sk, &fl6,
-						 (struct icmp6hdr *) &pfh.icmph,
-						 len);
+		icmpv6_push_pending_frames(sk, &fl6,
+					   (struct icmp6hdr *)&pfh.icmph, len);
 	}
 	release_sock(sk);
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index e4462b0ff801..761a473a07c5 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1055,6 +1055,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname,
 		if (optname == IPV6_CHECKSUM ||
 		    optname == IPV6_HDRINCL)
 			break;
+		/* fall through */
 	default:
 		return ipv6_setsockopt(sk, level, optname, optval, optlen);
 	}
@@ -1077,6 +1078,7 @@ static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname,
 		if (optname == IPV6_CHECKSUM ||
 		    optname == IPV6_HDRINCL)
 			break;
+		/* fall through */
 	default:
 		return compat_ipv6_setsockopt(sk, level, optname,
 					      optval, optlen);
@@ -1138,6 +1140,7 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname,
 		if (optname == IPV6_CHECKSUM ||
 		    optname == IPV6_HDRINCL)
 			break;
+		/* fall through */
 	default:
 		return ipv6_getsockopt(sk, level, optname, optval, optlen);
 	}
@@ -1160,6 +1163,7 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname,
 		if (optname == IPV6_CHECKSUM ||
 		    optname == IPV6_HDRINCL)
 			break;
+		/* fall through */
 	default:
 		return compat_ipv6_getsockopt(sk, level, optname,
 					      optval, optlen);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 846012eae526..afbc000ad4f2 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -170,12 +170,13 @@ out:
 }
 EXPORT_SYMBOL(ip6_expire_frag_queue);
 
-static void ip6_frag_expire(unsigned long data)
+static void ip6_frag_expire(struct timer_list *t)
 {
+	struct inet_frag_queue *frag = from_timer(frag, t, timer);
 	struct frag_queue *fq;
 	struct net *net;
 
-	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+	fq = container_of(frag, struct frag_queue, q);
 	net = container_of(fq->q.net, struct net, ipv6.frags);
 
 	ip6_expire_frag_queue(net, fq, &ip6_frags);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a96d5b385d8f..70d9659fc1e9 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -44,6 +44,7 @@
 #include <linux/seq_file.h>
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
+#include <linux/jhash.h>
 #include <net/net_namespace.h>
 #include <net/snmp.h>
 #include <net/ipv6.h>
@@ -104,6 +105,9 @@ static int rt6_fill_node(struct net *net,
 			 struct in6_addr *dst, struct in6_addr *src,
 			 int iif, int type, u32 portid, u32 seq,
 			 unsigned int flags);
+static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
+					   struct in6_addr *daddr,
+					   struct in6_addr *saddr);
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct rt6_info *rt6_add_route_info(struct net *net,
@@ -139,9 +143,11 @@ static void rt6_uncached_list_del(struct rt6_info *rt)
 {
 	if (!list_empty(&rt->rt6i_uncached)) {
 		struct uncached_list *ul = rt->rt6i_uncached_list;
+		struct net *net = dev_net(rt->dst.dev);
 
 		spin_lock_bh(&ul->lock);
 		list_del(&rt->rt6i_uncached);
+		atomic_dec(&net->ipv6.rt6_stats->fib_rt_uncache);
 		spin_unlock_bh(&ul->lock);
 	}
 }
@@ -355,8 +361,10 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net,
 	struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
 					1, DST_OBSOLETE_FORCE_CHK, flags);
 
-	if (rt)
+	if (rt) {
 		rt6_info_init(rt);
+		atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc);
+	}
 
 	return rt;
 }
@@ -369,17 +377,7 @@ struct rt6_info *ip6_dst_alloc(struct net *net,
 
 	if (rt) {
 		rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC);
-		if (rt->rt6i_pcpu) {
-			int cpu;
-
-			for_each_possible_cpu(cpu) {
-				struct rt6_info **p;
-
-				p = per_cpu_ptr(rt->rt6i_pcpu, cpu);
-				/* no one shares rt */
-				*p =  NULL;
-			}
-		} else {
+		if (!rt->rt6i_pcpu) {
 			dst_release_immediate(&rt->dst);
 			return NULL;
 		}
@@ -392,6 +390,7 @@ EXPORT_SYMBOL(ip6_dst_alloc);
 static void ip6_dst_destroy(struct dst_entry *dst)
 {
 	struct rt6_info *rt = (struct rt6_info *)dst;
+	struct rt6_exception_bucket *bucket;
 	struct dst_entry *from = dst->from;
 	struct inet6_dev *idev;
 
@@ -404,6 +403,11 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 		rt->rt6i_idev = NULL;
 		in6_dev_put(idev);
 	}
+	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, 1);
+	if (bucket) {
+		rt->rt6i_exception_bucket = NULL;
+		kfree(bucket);
+	}
 
 	dst->from = NULL;
 	dst_release(from);
@@ -478,7 +482,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
 }
 
 /*
- *	Route lookup. Any table->tb6_lock is implied.
+ *	Route lookup. rcu_read_lock() should be held.
  */
 
 static inline struct rt6_info *rt6_device_match(struct net *net,
@@ -493,7 +497,7 @@ static inline struct rt6_info *rt6_device_match(struct net *net,
 	if (!oif && ipv6_addr_any(saddr))
 		goto out;
 
-	for (sprt = rt; sprt; sprt = sprt->dst.rt6_next) {
+	for (sprt = rt; sprt; sprt = rcu_dereference(sprt->dst.rt6_next)) {
 		struct net_device *dev = sprt->dst.dev;
 
 		if (oif) {
@@ -702,6 +706,7 @@ out:
 }
 
 static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
+				     struct rt6_info *leaf,
 				     struct rt6_info *rr_head,
 				     u32 metric, int oif, int strict,
 				     bool *do_rr)
@@ -711,7 +716,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
 
 	match = NULL;
 	cont = NULL;
-	for (rt = rr_head; rt; rt = rt->dst.rt6_next) {
+	for (rt = rr_head; rt; rt = rcu_dereference(rt->dst.rt6_next)) {
 		if (rt->rt6i_metric != metric) {
 			cont = rt;
 			break;
@@ -720,7 +725,8 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
 		match = find_match(rt, oif, strict, &mpri, match, do_rr);
 	}
 
-	for (rt = fn->leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) {
+	for (rt = leaf; rt && rt != rr_head;
+	     rt = rcu_dereference(rt->dst.rt6_next)) {
 		if (rt->rt6i_metric != metric) {
 			cont = rt;
 			break;
@@ -732,37 +738,59 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
 	if (match || !cont)
 		return match;
 
-	for (rt = cont; rt; rt = rt->dst.rt6_next)
+	for (rt = cont; rt; rt = rcu_dereference(rt->dst.rt6_next))
 		match = find_match(rt, oif, strict, &mpri, match, do_rr);
 
 	return match;
 }
 
-static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
+static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
+				   int oif, int strict)
 {
+	struct rt6_info *leaf = rcu_dereference(fn->leaf);
 	struct rt6_info *match, *rt0;
-	struct net *net;
 	bool do_rr = false;
+	int key_plen;
 
-	rt0 = fn->rr_ptr;
+	if (!leaf || leaf == net->ipv6.ip6_null_entry)
+		return net->ipv6.ip6_null_entry;
+
+	rt0 = rcu_dereference(fn->rr_ptr);
 	if (!rt0)
-		fn->rr_ptr = rt0 = fn->leaf;
+		rt0 = leaf;
 
-	match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict,
+	/* Double check to make sure fn is not an intermediate node
+	 * and fn->leaf does not points to its child's leaf
+	 * (This might happen if all routes under fn are deleted from
+	 * the tree and fib6_repair_tree() is called on the node.)
+	 */
+	key_plen = rt0->rt6i_dst.plen;
+#ifdef CONFIG_IPV6_SUBTREES
+	if (rt0->rt6i_src.plen)
+		key_plen = rt0->rt6i_src.plen;
+#endif
+	if (fn->fn_bit != key_plen)
+		return net->ipv6.ip6_null_entry;
+
+	match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict,
 			     &do_rr);
 
 	if (do_rr) {
-		struct rt6_info *next = rt0->dst.rt6_next;
+		struct rt6_info *next = rcu_dereference(rt0->dst.rt6_next);
 
 		/* no entries matched; do round-robin */
 		if (!next || next->rt6i_metric != rt0->rt6i_metric)
-			next = fn->leaf;
-
-		if (next != rt0)
-			fn->rr_ptr = next;
+			next = leaf;
+
+		if (next != rt0) {
+			spin_lock_bh(&leaf->rt6i_table->tb6_lock);
+			/* make sure next is not being deleted from the tree */
+			if (next->rt6i_node)
+				rcu_assign_pointer(fn->rr_ptr, next);
+			spin_unlock_bh(&leaf->rt6i_table->tb6_lock);
+		}
 	}
 
-	net = dev_net(rt0->dst.dev);
 	return match ? match : net->ipv6.ip6_null_entry;
 }
 
@@ -850,13 +878,14 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
 					struct in6_addr *saddr)
 {
-	struct fib6_node *pn;
+	struct fib6_node *pn, *sn;
 	while (1) {
 		if (fn->fn_flags & RTN_TL_ROOT)
 			return NULL;
-		pn = fn->parent;
-		if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn)
-			fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr);
+		pn = rcu_dereference(fn->parent);
+		sn = FIB6_SUBTREE(pn);
+		if (sn && sn != fn)
+			fn = fib6_lookup(sn, NULL, saddr);
 		else
 			fn = pn;
 		if (fn->fn_flags & RTN_RTINFO)
@@ -864,29 +893,59 @@ static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
 	}
 }
 
+static bool ip6_hold_safe(struct net *net, struct rt6_info **prt,
+			  bool null_fallback)
+{
+	struct rt6_info *rt = *prt;
+
+	if (dst_hold_safe(&rt->dst))
+		return true;
+	if (null_fallback) {
+		rt = net->ipv6.ip6_null_entry;
+		dst_hold(&rt->dst);
+	} else {
+		rt = NULL;
+	}
+	*prt = rt;
+	return false;
+}
+
 static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 					     struct fib6_table *table,
 					     struct flowi6 *fl6, int flags)
 {
+	struct rt6_info *rt, *rt_cache;
 	struct fib6_node *fn;
-	struct rt6_info *rt;
 
-	read_lock_bh(&table->tb6_lock);
+	rcu_read_lock();
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
-	rt = fn->leaf;
-	rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags);
-	if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
-		rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif, flags);
+	rt = rcu_dereference(fn->leaf);
+	if (!rt) {
+		rt = net->ipv6.ip6_null_entry;
+	} else {
+		rt = rt6_device_match(net, rt, &fl6->saddr,
+				      fl6->flowi6_oif, flags);
+		if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
+			rt = rt6_multipath_select(rt, fl6,
+						  fl6->flowi6_oif, flags);
+	}
 	if (rt == net->ipv6.ip6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
 			goto restart;
 	}
-	dst_use(&rt->dst, jiffies);
-	read_unlock_bh(&table->tb6_lock);
+	/* Search through exception table */
+	rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr);
+	if (rt_cache)
+		rt = rt_cache;
+
+	if (ip6_hold_safe(net, &rt, true))
+		dst_use_noref(&rt->dst, jiffies);
+
+	rcu_read_unlock();
 
-	trace_fib6_table_lookup(net, rt, table->tb6_id, fl6);
+	trace_fib6_table_lookup(net, rt, table, fl6);
 
 	return rt;
 
@@ -938,9 +997,9 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
 	struct fib6_table *table;
 
 	table = rt->rt6i_table;
-	write_lock_bh(&table->tb6_lock);
+	spin_lock_bh(&table->tb6_lock);
 	err = fib6_add(&table->tb6_root, rt, info, mxc, extack);
-	write_unlock_bh(&table->tb6_lock);
+	spin_unlock_bh(&table->tb6_lock);
 
 	return err;
 }
@@ -1038,7 +1097,7 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
 	return pcpu_rt;
 }
 
-/* It should be called with read_lock_bh(&tb6_lock) acquired */
+/* It should be called with rcu_read_lock() acquired */
 static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
 {
 	struct rt6_info *pcpu_rt, **p;
@@ -1046,16 +1105,14 @@ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
 	p = this_cpu_ptr(rt->rt6i_pcpu);
 	pcpu_rt = *p;
 
-	if (pcpu_rt) {
-		dst_hold(&pcpu_rt->dst);
+	if (pcpu_rt && ip6_hold_safe(NULL, &pcpu_rt, false))
 		rt6_dst_from_metrics_check(pcpu_rt);
-	}
+
 	return pcpu_rt;
 }
 
 static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
 {
-	struct fib6_table *table = rt->rt6i_table;
 	struct rt6_info *pcpu_rt, *prev, **p;
 
 	pcpu_rt = ip6_rt_pcpu_alloc(rt);
@@ -1066,36 +1123,526 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
 		return net->ipv6.ip6_null_entry;
 	}
 
-	read_lock_bh(&table->tb6_lock);
-	if (rt->rt6i_pcpu) {
-		p = this_cpu_ptr(rt->rt6i_pcpu);
-		prev = cmpxchg(p, NULL, pcpu_rt);
-		if (prev) {
-			/* If someone did it before us, return prev instead */
-			dst_release_immediate(&pcpu_rt->dst);
-			pcpu_rt = prev;
-		}
-	} else {
-		/* rt has been removed from the fib6 tree
-		 * before we have a chance to acquire the read_lock.
-		 * In this case, don't brother to create a pcpu rt
-		 * since rt is going away anyway.  The next
-		 * dst_check() will trigger a re-lookup.
-		 */
-		dst_release_immediate(&pcpu_rt->dst);
-		pcpu_rt = rt;
-	}
 	dst_hold(&pcpu_rt->dst);
+	p = this_cpu_ptr(rt->rt6i_pcpu);
+	prev = cmpxchg(p, NULL, pcpu_rt);
+	BUG_ON(prev);
+
 	rt6_dst_from_metrics_check(pcpu_rt);
-	read_unlock_bh(&table->tb6_lock);
 	return pcpu_rt;
 }
 
+/* exception hash table implementation
+ */
+static DEFINE_SPINLOCK(rt6_exception_lock);
+
+/* Remove rt6_ex from hash table and free the memory
+ * Caller must hold rt6_exception_lock
+ */
+static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
+				 struct rt6_exception *rt6_ex)
+{
+	struct net *net;
+
+	if (!bucket || !rt6_ex)
+		return;
+
+	net = dev_net(rt6_ex->rt6i->dst.dev);
+	rt6_ex->rt6i->rt6i_node = NULL;
+	hlist_del_rcu(&rt6_ex->hlist);
+	rt6_release(rt6_ex->rt6i);
+	kfree_rcu(rt6_ex, rcu);
+	WARN_ON_ONCE(!bucket->depth);
+	bucket->depth--;
+	net->ipv6.rt6_stats->fib_rt_cache--;
+}
+
+/* Remove oldest rt6_ex in bucket and free the memory
+ * Caller must hold rt6_exception_lock
+ */
+static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket)
+{
+	struct rt6_exception *rt6_ex, *oldest = NULL;
+
+	if (!bucket)
+		return;
+
+	hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
+		if (!oldest || time_before(rt6_ex->stamp, oldest->stamp))
+			oldest = rt6_ex;
+	}
+	rt6_remove_exception(bucket, oldest);
+}
+
+static u32 rt6_exception_hash(const struct in6_addr *dst,
+			      const struct in6_addr *src)
+{
+	static u32 seed __read_mostly;
+	u32 val;
+
+	net_get_random_once(&seed, sizeof(seed));
+	val = jhash(dst, sizeof(*dst), seed);
+
+#ifdef CONFIG_IPV6_SUBTREES
+	if (src)
+		val = jhash(src, sizeof(*src), val);
+#endif
+	return hash_32(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT);
+}
+
+/* Helper function to find the cached rt in the hash table
+ * and update bucket pointer to point to the bucket for this
+ * (daddr, saddr) pair
+ * Caller must hold rt6_exception_lock
+ */
+static struct rt6_exception *
+__rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket,
+			      const struct in6_addr *daddr,
+			      const struct in6_addr *saddr)
+{
+	struct rt6_exception *rt6_ex;
+	u32 hval;
+
+	if (!(*bucket) || !daddr)
+		return NULL;
+
+	hval = rt6_exception_hash(daddr, saddr);
+	*bucket += hval;
+
+	hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) {
+		struct rt6_info *rt6 = rt6_ex->rt6i;
+		bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr);
+
+#ifdef CONFIG_IPV6_SUBTREES
+		if (matched && saddr)
+			matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr);
+#endif
+		if (matched)
+			return rt6_ex;
+	}
+	return NULL;
+}
+
+/* Helper function to find the cached rt in the hash table
+ * and update bucket pointer to point to the bucket for this
+ * (daddr, saddr) pair
+ * Caller must hold rcu_read_lock()
+ */
+static struct rt6_exception *
+__rt6_find_exception_rcu(struct rt6_exception_bucket **bucket,
+			 const struct in6_addr *daddr,
+			 const struct in6_addr *saddr)
+{
+	struct rt6_exception *rt6_ex;
+	u32 hval;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	if (!(*bucket) || !daddr)
+		return NULL;
+
+	hval = rt6_exception_hash(daddr, saddr);
+	*bucket += hval;
+
+	hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) {
+		struct rt6_info *rt6 = rt6_ex->rt6i;
+		bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr);
+
+#ifdef CONFIG_IPV6_SUBTREES
+		if (matched && saddr)
+			matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr);
+#endif
+		if (matched)
+			return rt6_ex;
+	}
+	return NULL;
+}
+
+static int rt6_insert_exception(struct rt6_info *nrt,
+				struct rt6_info *ort)
+{
+	struct net *net = dev_net(ort->dst.dev);
+	struct rt6_exception_bucket *bucket;
+	struct in6_addr *src_key = NULL;
+	struct rt6_exception *rt6_ex;
+	int err = 0;
+
+	/* ort can't be a cache or pcpu route */
+	if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
+		ort = (struct rt6_info *)ort->dst.from;
+	WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU));
+
+	spin_lock_bh(&rt6_exception_lock);
+
+	if (ort->exception_bucket_flushed) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	bucket = rcu_dereference_protected(ort->rt6i_exception_bucket,
+					lockdep_is_held(&rt6_exception_lock));
+	if (!bucket) {
+		bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket),
+				 GFP_ATOMIC);
+		if (!bucket) {
+			err = -ENOMEM;
+			goto out;
+		}
+		rcu_assign_pointer(ort->rt6i_exception_bucket, bucket);
+	}
+
+#ifdef CONFIG_IPV6_SUBTREES
+	/* rt6i_src.plen != 0 indicates ort is in subtree
+	 * and exception table is indexed by a hash of
+	 * both rt6i_dst and rt6i_src.
+	 * Otherwise, the exception table is indexed by
+	 * a hash of only rt6i_dst.
+	 */
+	if (ort->rt6i_src.plen)
+		src_key = &nrt->rt6i_src.addr;
+#endif
+
+	/* Update rt6i_prefsrc as it could be changed
+	 * in rt6_remove_prefsrc()
+	 */
+	nrt->rt6i_prefsrc = ort->rt6i_prefsrc;
+	/* rt6_mtu_change() might lower mtu on ort.
+	 * Only insert this exception route if its mtu
+	 * is less than ort's mtu value.
+	 */
+	if (nrt->rt6i_pmtu >= dst_mtu(&ort->dst)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr,
+					       src_key);
+	if (rt6_ex)
+		rt6_remove_exception(bucket, rt6_ex);
+
+	rt6_ex = kzalloc(sizeof(*rt6_ex), GFP_ATOMIC);
+	if (!rt6_ex) {
+		err = -ENOMEM;
+		goto out;
+	}
+	rt6_ex->rt6i = nrt;
+	rt6_ex->stamp = jiffies;
+	atomic_inc(&nrt->rt6i_ref);
+	nrt->rt6i_node = ort->rt6i_node;
+	hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain);
+	bucket->depth++;
+	net->ipv6.rt6_stats->fib_rt_cache++;
+
+	if (bucket->depth > FIB6_MAX_DEPTH)
+		rt6_exception_remove_oldest(bucket);
+
+out:
+	spin_unlock_bh(&rt6_exception_lock);
+
+	/* Update fn->fn_sernum to invalidate all cached dst */
+	if (!err) {
+		fib6_update_sernum(ort);
+		fib6_force_start_gc(net);
+	}
+
+	return err;
+}
+
+void rt6_flush_exceptions(struct rt6_info *rt)
+{
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	struct hlist_node *tmp;
+	int i;
+
+	spin_lock_bh(&rt6_exception_lock);
+	/* Prevent rt6_insert_exception() to recreate the bucket list */
+	rt->exception_bucket_flushed = 1;
+
+	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
+				    lockdep_is_held(&rt6_exception_lock));
+	if (!bucket)
+		goto out;
+
+	for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+		hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist)
+			rt6_remove_exception(bucket, rt6_ex);
+		WARN_ON_ONCE(bucket->depth);
+		bucket++;
+	}
+
+out:
+	spin_unlock_bh(&rt6_exception_lock);
+}
+
+/* Find cached rt in the hash table inside passed in rt
+ * Caller has to hold rcu_read_lock()
+ */
+static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
+					   struct in6_addr *daddr,
+					   struct in6_addr *saddr)
+{
+	struct rt6_exception_bucket *bucket;
+	struct in6_addr *src_key = NULL;
+	struct rt6_exception *rt6_ex;
+	struct rt6_info *res = NULL;
+
+	bucket = rcu_dereference(rt->rt6i_exception_bucket);
+
+#ifdef CONFIG_IPV6_SUBTREES
+	/* rt6i_src.plen != 0 indicates rt is in subtree
+	 * and exception table is indexed by a hash of
+	 * both rt6i_dst and rt6i_src.
+	 * Otherwise, the exception table is indexed by
+	 * a hash of only rt6i_dst.
+	 */
+	if (rt->rt6i_src.plen)
+		src_key = saddr;
+#endif
+	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
+
+	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
+		res = rt6_ex->rt6i;
+
+	return res;
+}
+
+/* Remove the passed in cached rt from the hash table that contains it */
+int rt6_remove_exception_rt(struct rt6_info *rt)
+{
+	struct rt6_info *from = (struct rt6_info *)rt->dst.from;
+	struct rt6_exception_bucket *bucket;
+	struct in6_addr *src_key = NULL;
+	struct rt6_exception *rt6_ex;
+	int err;
+
+	if (!from ||
+	    !(rt->rt6i_flags & RTF_CACHE))
+		return -EINVAL;
+
+	if (!rcu_access_pointer(from->rt6i_exception_bucket))
+		return -ENOENT;
+
+	spin_lock_bh(&rt6_exception_lock);
+	bucket = rcu_dereference_protected(from->rt6i_exception_bucket,
+				    lockdep_is_held(&rt6_exception_lock));
+#ifdef CONFIG_IPV6_SUBTREES
+	/* rt6i_src.plen != 0 indicates 'from' is in subtree
+	 * and exception table is indexed by a hash of
+	 * both rt6i_dst and rt6i_src.
+	 * Otherwise, the exception table is indexed by
+	 * a hash of only rt6i_dst.
+	 */
+	if (from->rt6i_src.plen)
+		src_key = &rt->rt6i_src.addr;
+#endif
+	rt6_ex = __rt6_find_exception_spinlock(&bucket,
+					       &rt->rt6i_dst.addr,
+					       src_key);
+	if (rt6_ex) {
+		rt6_remove_exception(bucket, rt6_ex);
+		err = 0;
+	} else {
+		err = -ENOENT;
+	}
+
+	spin_unlock_bh(&rt6_exception_lock);
+	return err;
+}
+
+/* Find rt6_ex which contains the passed in rt cache and
+ * refresh its stamp
+ */
+static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
+{
+	struct rt6_info *from = (struct rt6_info *)rt->dst.from;
+	struct rt6_exception_bucket *bucket;
+	struct in6_addr *src_key = NULL;
+	struct rt6_exception *rt6_ex;
+
+	if (!from ||
+	    !(rt->rt6i_flags & RTF_CACHE))
+		return;
+
+	rcu_read_lock();
+	bucket = rcu_dereference(from->rt6i_exception_bucket);
+
+#ifdef CONFIG_IPV6_SUBTREES
+	/* rt6i_src.plen != 0 indicates 'from' is in subtree
+	 * and exception table is indexed by a hash of
+	 * both rt6i_dst and rt6i_src.
+	 * Otherwise, the exception table is indexed by
+	 * a hash of only rt6i_dst.
+	 */
+	if (from->rt6i_src.plen)
+		src_key = &rt->rt6i_src.addr;
+#endif
+	rt6_ex = __rt6_find_exception_rcu(&bucket,
+					  &rt->rt6i_dst.addr,
+					  src_key);
+	if (rt6_ex)
+		rt6_ex->stamp = jiffies;
+
+	rcu_read_unlock();
+}
+
+static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt)
+{
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	int i;
+
+	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
+					lockdep_is_held(&rt6_exception_lock));
+
+	if (bucket) {
+		for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+			hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
+				rt6_ex->rt6i->rt6i_prefsrc.plen = 0;
+			}
+			bucket++;
+		}
+	}
+}
+
+static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu)
+{
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	int i;
+
+	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
+					lockdep_is_held(&rt6_exception_lock));
+
+	if (bucket) {
+		for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+			hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
+				struct rt6_info *entry = rt6_ex->rt6i;
+				/* For RTF_CACHE with rt6i_pmtu == 0
+				 * (i.e. a redirected route),
+				 * the metrics of its rt->dst.from has already
+				 * been updated.
+				 */
+				if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu)
+					entry->rt6i_pmtu = mtu;
+			}
+			bucket++;
+		}
+	}
+}
+
+#define RTF_CACHE_GATEWAY	(RTF_GATEWAY | RTF_CACHE)
+
+static void rt6_exceptions_clean_tohost(struct rt6_info *rt,
+					struct in6_addr *gateway)
+{
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	struct hlist_node *tmp;
+	int i;
+
+	if (!rcu_access_pointer(rt->rt6i_exception_bucket))
+		return;
+
+	spin_lock_bh(&rt6_exception_lock);
+	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
+				     lockdep_is_held(&rt6_exception_lock));
+
+	if (bucket) {
+		for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+			hlist_for_each_entry_safe(rt6_ex, tmp,
+						  &bucket->chain, hlist) {
+				struct rt6_info *entry = rt6_ex->rt6i;
+
+				if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) ==
+				    RTF_CACHE_GATEWAY &&
+				    ipv6_addr_equal(gateway,
+						    &entry->rt6i_gateway)) {
+					rt6_remove_exception(bucket, rt6_ex);
+				}
+			}
+			bucket++;
+		}
+	}
+
+	spin_unlock_bh(&rt6_exception_lock);
+}
+
+static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
+				      struct rt6_exception *rt6_ex,
+				      struct fib6_gc_args *gc_args,
+				      unsigned long now)
+{
+	struct rt6_info *rt = rt6_ex->rt6i;
+
+	/* we are pruning and obsoleting aged-out and non gateway exceptions
+	 * even if others have still references to them, so that on next
+	 * dst_check() such references can be dropped.
+	 * EXPIRES exceptions - e.g. pmtu-generated ones are pruned when
+	 * expired, independently from their aging, as per RFC 8201 section 4
+	 */
+	if (!(rt->rt6i_flags & RTF_EXPIRES) &&
+	    time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) {
+		RT6_TRACE("aging clone %p\n", rt);
+		rt6_remove_exception(bucket, rt6_ex);
+		return;
+	} else if (rt->rt6i_flags & RTF_GATEWAY) {
+		struct neighbour *neigh;
+		__u8 neigh_flags = 0;
+
+		neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway);
+		if (neigh) {
+			neigh_flags = neigh->flags;
+			neigh_release(neigh);
+		}
+		if (!(neigh_flags & NTF_ROUTER)) {
+			RT6_TRACE("purging route %p via non-router but gateway\n",
+				  rt);
+			rt6_remove_exception(bucket, rt6_ex);
+			return;
+		}
+	} else if (__rt6_check_expired(rt)) {
+		RT6_TRACE("purging expired route %p\n", rt);
+		rt6_remove_exception(bucket, rt6_ex);
+		return;
+	}
+	gc_args->more++;
+}
+
+void rt6_age_exceptions(struct rt6_info *rt,
+			struct fib6_gc_args *gc_args,
+			unsigned long now)
+{
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	struct hlist_node *tmp;
+	int i;
+
+	if (!rcu_access_pointer(rt->rt6i_exception_bucket))
+		return;
+
+	spin_lock_bh(&rt6_exception_lock);
+	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
+				    lockdep_is_held(&rt6_exception_lock));
+
+	if (bucket) {
+		for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+			hlist_for_each_entry_safe(rt6_ex, tmp,
+						  &bucket->chain, hlist) {
+				rt6_age_examine_exception(bucket, rt6_ex,
+							  gc_args, now);
+			}
+			bucket++;
+		}
+	}
+	spin_unlock_bh(&rt6_exception_lock);
+}
+
 struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 			       int oif, struct flowi6 *fl6, int flags)
 {
 	struct fib6_node *fn, *saved_fn;
-	struct rt6_info *rt;
+	struct rt6_info *rt, *rt_cache;
 	int strict = 0;
 
 	strict |= flags & RT6_LOOKUP_F_IFACE;
@@ -1103,7 +1650,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 	if (net->ipv6.devconf_all->forwarding == 0)
 		strict |= RT6_LOOKUP_F_REACHABLE;
 
-	read_lock_bh(&table->tb6_lock);
+	rcu_read_lock();
 
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 	saved_fn = fn;
@@ -1112,7 +1659,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 		oif = 0;
 
 redo_rt6_select:
-	rt = rt6_select(fn, oif, strict);
+	rt = rt6_select(net, fn, oif, strict);
 	if (rt->rt6i_nsiblings)
 		rt = rt6_multipath_select(rt, fl6, oif, strict);
 	if (rt == net->ipv6.ip6_null_entry) {
@@ -1127,14 +1674,23 @@ redo_rt6_select:
 		}
 	}
 
+	/*Search through exception table */
+	rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr);
+	if (rt_cache)
+		rt = rt_cache;
 
-	if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) {
-		dst_use(&rt->dst, jiffies);
-		read_unlock_bh(&table->tb6_lock);
-
-		rt6_dst_from_metrics_check(rt);
-
-		trace_fib6_table_lookup(net, rt, table->tb6_id, fl6);
+	if (rt == net->ipv6.ip6_null_entry) {
+		rcu_read_unlock();
+		dst_hold(&rt->dst);
+		trace_fib6_table_lookup(net, rt, table, fl6);
+		return rt;
+	} else if (rt->rt6i_flags & RTF_CACHE) {
+		if (ip6_hold_safe(net, &rt, true)) {
+			dst_use_noref(&rt->dst, jiffies);
+			rt6_dst_from_metrics_check(rt);
+		}
+		rcu_read_unlock();
+		trace_fib6_table_lookup(net, rt, table, fl6);
 		return rt;
 	} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
 			    !(rt->rt6i_flags & RTF_GATEWAY))) {
@@ -1146,8 +1702,14 @@ redo_rt6_select:
 
 		struct rt6_info *uncached_rt;
 
-		dst_use(&rt->dst, jiffies);
-		read_unlock_bh(&table->tb6_lock);
+		if (ip6_hold_safe(net, &rt, true)) {
+			dst_use_noref(&rt->dst, jiffies);
+		} else {
+			rcu_read_unlock();
+			uncached_rt = rt;
+			goto uncached_rt_out;
+		}
+		rcu_read_unlock();
 
 		uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL);
 		dst_release(&rt->dst);
@@ -1157,12 +1719,14 @@ redo_rt6_select:
 			 * No need for another dst_hold()
 			 */
 			rt6_uncached_list_add(uncached_rt);
+			atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache);
 		} else {
 			uncached_rt = net->ipv6.ip6_null_entry;
 			dst_hold(&uncached_rt->dst);
 		}
 
-		trace_fib6_table_lookup(net, uncached_rt, table->tb6_id, fl6);
+uncached_rt_out:
+		trace_fib6_table_lookup(net, uncached_rt, table, fl6);
 		return uncached_rt;
 
 	} else {
@@ -1170,26 +1734,28 @@ redo_rt6_select:
 
 		struct rt6_info *pcpu_rt;
 
-		rt->dst.lastuse = jiffies;
-		rt->dst.__use++;
+		dst_use_noref(&rt->dst, jiffies);
+		local_bh_disable();
 		pcpu_rt = rt6_get_pcpu_route(rt);
 
-		if (pcpu_rt) {
-			read_unlock_bh(&table->tb6_lock);
-		} else {
-			/* We have to do the read_unlock first
-			 * because rt6_make_pcpu_route() may trigger
-			 * ip6_dst_gc() which will take the write_lock.
-			 */
-			dst_hold(&rt->dst);
-			read_unlock_bh(&table->tb6_lock);
-			pcpu_rt = rt6_make_pcpu_route(rt);
-			dst_release(&rt->dst);
+		if (!pcpu_rt) {
+			/* atomic_inc_not_zero() is needed when using rcu */
+			if (atomic_inc_not_zero(&rt->rt6i_ref)) {
+				/* No dst_hold() on rt is needed because grabbing
+				 * rt->rt6i_ref makes sure rt can't be released.
+				 */
+				pcpu_rt = rt6_make_pcpu_route(rt);
+				rt6_release(rt);
+			} else {
+				/* rt is already removed from tree */
+				pcpu_rt = net->ipv6.ip6_null_entry;
+				dst_hold(&pcpu_rt->dst);
+			}
 		}
-
-		trace_fib6_table_lookup(net, pcpu_rt, table->tb6_id, fl6);
+		local_bh_enable();
+		rcu_read_unlock();
+		trace_fib6_table_lookup(net, pcpu_rt, table, fl6);
 		return pcpu_rt;
-
 	}
 }
 EXPORT_SYMBOL_GPL(ip6_pol_route);
@@ -1328,6 +1894,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 		       DST_OBSOLETE_DEAD, 0);
 	if (rt) {
 		rt6_info_init(rt);
+		atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc);
 
 		new = &rt->dst;
 		new->__use = 1;
@@ -1491,23 +2058,17 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 
 	if (!rt6_cache_allowed_for_pmtu(rt6)) {
 		rt6_do_update_pmtu(rt6, mtu);
+		/* update rt6_ex->stamp for cache */
+		if (rt6->rt6i_flags & RTF_CACHE)
+			rt6_update_exception_stamp_rt(rt6);
 	} else if (daddr) {
 		struct rt6_info *nrt6;
 
 		nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr);
 		if (nrt6) {
 			rt6_do_update_pmtu(nrt6, mtu);
-
-			/* ip6_ins_rt(nrt6) will bump the
-			 * rt6->rt6i_node->fn_sernum
-			 * which will fail the next rt6_check() and
-			 * invalidate the sk->sk_dst_cache.
-			 */
-			ip6_ins_rt(nrt6);
-			/* Release the reference taken in
-			 * ip6_rt_cache_alloc()
-			 */
-			dst_release(&nrt6->dst);
+			if (rt6_insert_exception(nrt6, rt6))
+				dst_release_immediate(&nrt6->dst);
 		}
 	}
 }
@@ -1571,7 +2132,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 					     int flags)
 {
 	struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
-	struct rt6_info *rt;
+	struct rt6_info *rt, *rt_cache;
 	struct fib6_node *fn;
 
 	/* Get the "current" route for this destination and
@@ -1584,10 +2145,10 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 	 * routes.
 	 */
 
-	read_lock_bh(&table->tb6_lock);
+	rcu_read_lock();
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
-	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
+	for_each_fib6_node_rt_rcu(fn) {
 		if (rt6_check_expired(rt))
 			continue;
 		if (rt->dst.error)
@@ -1596,8 +2157,23 @@ restart:
 			continue;
 		if (fl6->flowi6_oif != rt->dst.dev->ifindex)
 			continue;
-		if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway))
+		/* rt_cache's gateway might be different from its 'parent'
+		 * in the case of an ip redirect.
+		 * So we keep searching in the exception table if the gateway
+		 * is different.
+		 */
+		if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) {
+			rt_cache = rt6_find_cached_rt(rt,
+						      &fl6->daddr,
+						      &fl6->saddr);
+			if (rt_cache &&
+			    ipv6_addr_equal(&rdfl->gateway,
+					    &rt_cache->rt6i_gateway)) {
+				rt = rt_cache;
+				break;
+			}
 			continue;
+		}
 		break;
 	}
 
@@ -1615,11 +2191,11 @@ restart:
 	}
 
 out:
-	dst_hold(&rt->dst);
+	ip6_hold_safe(net, &rt, true);
 
-	read_unlock_bh(&table->tb6_lock);
+	rcu_read_unlock();
 
-	trace_fib6_table_lookup(net, rt, table->tb6_id, fl6);
+	trace_fib6_table_lookup(net, rt, table, fl6);
 	return rt;
 };
 
@@ -1766,6 +2342,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 	 * do proper release of the net_device
 	 */
 	rt6_uncached_list_add(rt);
+	atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache);
 
 	dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0);
 
@@ -1901,6 +2478,12 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
 		goto out;
 	}
 
+	/* RTF_CACHE is an internal flag; can not be set by userspace */
+	if (cfg->fc_flags & RTF_CACHE) {
+		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE");
+		goto out;
+	}
+
 	if (cfg->fc_dst_len > 128) {
 		NL_SET_ERR_MSG(extack, "Invalid prefix length");
 		goto out;
@@ -2216,9 +2799,9 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
 	}
 
 	table = rt->rt6i_table;
-	write_lock_bh(&table->tb6_lock);
+	spin_lock_bh(&table->tb6_lock);
 	err = fib6_del(rt, info);
-	write_unlock_bh(&table->tb6_lock);
+	spin_unlock_bh(&table->tb6_lock);
 
 out:
 	ip6_rt_put(rt);
@@ -2244,7 +2827,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
 	if (rt == net->ipv6.ip6_null_entry)
 		goto out_put;
 	table = rt->rt6i_table;
-	write_lock_bh(&table->tb6_lock);
+	spin_lock_bh(&table->tb6_lock);
 
 	if (rt->rt6i_nsiblings && cfg->fc_delete_all_nh) {
 		struct rt6_info *sibling, *next_sibling;
@@ -2274,7 +2857,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
 
 	err = fib6_del(rt, info);
 out_unlock:
-	write_unlock_bh(&table->tb6_lock);
+	spin_unlock_bh(&table->tb6_lock);
 out_put:
 	ip6_rt_put(rt);
 
@@ -2288,9 +2871,9 @@ out_put:
 static int ip6_route_del(struct fib6_config *cfg,
 			 struct netlink_ext_ack *extack)
 {
+	struct rt6_info *rt, *rt_cache;
 	struct fib6_table *table;
 	struct fib6_node *fn;
-	struct rt6_info *rt;
 	int err = -ESRCH;
 
 	table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table);
@@ -2299,17 +2882,22 @@ static int ip6_route_del(struct fib6_config *cfg,
 		return err;
 	}
 
-	read_lock_bh(&table->tb6_lock);
+	rcu_read_lock();
 
 	fn = fib6_locate(&table->tb6_root,
 			 &cfg->fc_dst, cfg->fc_dst_len,
-			 &cfg->fc_src, cfg->fc_src_len);
+			 &cfg->fc_src, cfg->fc_src_len,
+			 !(cfg->fc_flags & RTF_CACHE));
 
 	if (fn) {
-		for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
-			if ((rt->rt6i_flags & RTF_CACHE) &&
-			    !(cfg->fc_flags & RTF_CACHE))
-				continue;
+		for_each_fib6_node_rt_rcu(fn) {
+			if (cfg->fc_flags & RTF_CACHE) {
+				rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst,
+							      &cfg->fc_src);
+				if (!rt_cache)
+					continue;
+				rt = rt_cache;
+			}
 			if (cfg->fc_ifindex &&
 			    (!rt->dst.dev ||
 			     rt->dst.dev->ifindex != cfg->fc_ifindex))
@@ -2321,8 +2909,9 @@ static int ip6_route_del(struct fib6_config *cfg,
 				continue;
 			if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol)
 				continue;
-			dst_hold(&rt->dst);
-			read_unlock_bh(&table->tb6_lock);
+			if (!dst_hold_safe(&rt->dst))
+				break;
+			rcu_read_unlock();
 
 			/* if gateway was specified only delete the one hop */
 			if (cfg->fc_flags & RTF_GATEWAY)
@@ -2331,7 +2920,7 @@ static int ip6_route_del(struct fib6_config *cfg,
 			return __ip6_del_rt_siblings(rt, cfg);
 		}
 	}
-	read_unlock_bh(&table->tb6_lock);
+	rcu_read_unlock();
 
 	return err;
 }
@@ -2435,8 +3024,14 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	nrt->rt6i_protocol = RTPROT_REDIRECT;
 	nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
 
-	if (ip6_ins_rt(nrt))
-		goto out_release;
+	/* No need to remove rt from the exception table if rt is
+	 * a cached route because rt6_insert_exception() will
+	 * takes care of it
+	 */
+	if (rt6_insert_exception(nrt, rt)) {
+		dst_release_immediate(&nrt->dst);
+		goto out;
+	}
 
 	netevent.old = &rt->dst;
 	netevent.new = &nrt->dst;
@@ -2444,17 +3039,6 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	netevent.neigh = neigh;
 	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
 
-	if (rt->rt6i_flags & RTF_CACHE) {
-		rt = (struct rt6_info *) dst_clone(&rt->dst);
-		ip6_del_rt(rt);
-	}
-
-out_release:
-	/* Release the reference taken in
-	 * ip6_rt_cache_alloc()
-	 */
-	dst_release(&nrt->dst);
-
 out:
 	neigh_release(neigh);
 }
@@ -2511,23 +3095,23 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
 	if (!table)
 		return NULL;
 
-	read_lock_bh(&table->tb6_lock);
-	fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0);
+	rcu_read_lock();
+	fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0, true);
 	if (!fn)
 		goto out;
 
-	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
+	for_each_fib6_node_rt_rcu(fn) {
 		if (rt->dst.dev->ifindex != ifindex)
 			continue;
 		if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
 			continue;
 		if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr))
 			continue;
-		dst_hold(&rt->dst);
+		ip6_hold_safe(NULL, &rt, false);
 		break;
 	}
 out:
-	read_unlock_bh(&table->tb6_lock);
+	rcu_read_unlock();
 	return rt;
 }
 
@@ -2573,16 +3157,16 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev
 	if (!table)
 		return NULL;
 
-	read_lock_bh(&table->tb6_lock);
-	for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
+	rcu_read_lock();
+	for_each_fib6_node_rt_rcu(&table->tb6_root) {
 		if (dev == rt->dst.dev &&
 		    ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
 		    ipv6_addr_equal(&rt->rt6i_gateway, addr))
 			break;
 	}
 	if (rt)
-		dst_hold(&rt->dst);
-	read_unlock_bh(&table->tb6_lock);
+		ip6_hold_safe(NULL, &rt, false);
+	rcu_read_unlock();
 	return rt;
 }
 
@@ -2620,17 +3204,20 @@ static void __rt6_purge_dflt_routers(struct fib6_table *table)
 	struct rt6_info *rt;
 
 restart:
-	read_lock_bh(&table->tb6_lock);
-	for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
+	rcu_read_lock();
+	for_each_fib6_node_rt_rcu(&table->tb6_root) {
 		if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
 		    (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) {
-			dst_hold(&rt->dst);
-			read_unlock_bh(&table->tb6_lock);
-			ip6_del_rt(rt);
+			if (dst_hold_safe(&rt->dst)) {
+				rcu_read_unlock();
+				ip6_del_rt(rt);
+			} else {
+				rcu_read_unlock();
+			}
 			goto restart;
 		}
 	}
-	read_unlock_bh(&table->tb6_lock);
+	rcu_read_unlock();
 
 	table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER;
 }
@@ -2818,8 +3405,12 @@ static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
 	if (((void *)rt->dst.dev == dev || !dev) &&
 	    rt != net->ipv6.ip6_null_entry &&
 	    ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) {
+		spin_lock_bh(&rt6_exception_lock);
 		/* remove prefsrc entry */
 		rt->rt6i_prefsrc.plen = 0;
+		/* need to update cache as well */
+		rt6_exceptions_remove_prefsrc(rt);
+		spin_unlock_bh(&rt6_exception_lock);
 	}
 	return 0;
 }
@@ -2836,18 +3427,23 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
 }
 
 #define RTF_RA_ROUTER		(RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)
-#define RTF_CACHE_GATEWAY	(RTF_GATEWAY | RTF_CACHE)
 
 /* Remove routers and update dst entries when gateway turn into host. */
 static int fib6_clean_tohost(struct rt6_info *rt, void *arg)
 {
 	struct in6_addr *gateway = (struct in6_addr *)arg;
 
-	if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) ||
-	     ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) &&
-	     ipv6_addr_equal(gateway, &rt->rt6i_gateway)) {
+	if (((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
+	    ipv6_addr_equal(gateway, &rt->rt6i_gateway)) {
 		return -1;
 	}
+
+	/* Further clean up cached routes in exception table.
+	 * This is needed because cached route may have a different
+	 * gateway than its 'parent' in the case of an ip redirect.
+	 */
+	rt6_exceptions_clean_tohost(rt, gateway);
+
 	return 0;
 }
 
@@ -2926,19 +3522,14 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
 	if (rt->dst.dev == arg->dev &&
 	    dst_metric_raw(&rt->dst, RTAX_MTU) &&
 	    !dst_metric_locked(&rt->dst, RTAX_MTU)) {
-		if (rt->rt6i_flags & RTF_CACHE) {
-			/* For RTF_CACHE with rt6i_pmtu == 0
-			 * (i.e. a redirected route),
-			 * the metrics of its rt->dst.from has already
-			 * been updated.
-			 */
-			if (rt->rt6i_pmtu && rt->rt6i_pmtu > arg->mtu)
-				rt->rt6i_pmtu = arg->mtu;
-		} else if (dst_mtu(&rt->dst) >= arg->mtu ||
-			   (dst_mtu(&rt->dst) < arg->mtu &&
-			    dst_mtu(&rt->dst) == idev->cnf.mtu6)) {
+		spin_lock_bh(&rt6_exception_lock);
+		if (dst_mtu(&rt->dst) >= arg->mtu ||
+		    (dst_mtu(&rt->dst) < arg->mtu &&
+		     dst_mtu(&rt->dst) == idev->cnf.mtu6)) {
 			dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
 		}
+		rt6_exceptions_update_pmtu(rt, arg->mtu);
+		spin_unlock_bh(&rt6_exception_lock);
 	}
 	return 0;
 }
@@ -3839,7 +4430,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v)
 	seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n",
 		   net->ipv6.rt6_stats->fib_nodes,
 		   net->ipv6.rt6_stats->fib_route_nodes,
-		   net->ipv6.rt6_stats->fib_rt_alloc,
+		   atomic_read(&net->ipv6.rt6_stats->fib_rt_alloc),
 		   net->ipv6.rt6_stats->fib_rt_entries,
 		   net->ipv6.rt6_stats->fib_rt_cache,
 		   dst_entries_get_slow(&net->ipv6.ip6_dst_ops),
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index ac912bb21747..d60ddcb0bfe2 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -91,29 +91,35 @@ struct sit_net {
  * Must be invoked with rcu_read_lock
  */
 static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net,
-		struct net_device *dev, __be32 remote, __be32 local)
+					     struct net_device *dev,
+					     __be32 remote, __be32 local,
+					     int sifindex)
 {
 	unsigned int h0 = HASH(remote);
 	unsigned int h1 = HASH(local);
 	struct ip_tunnel *t;
 	struct sit_net *sitn = net_generic(net, sit_net_id);
+	int ifindex = dev ? dev->ifindex : 0;
 
 	for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) {
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
-		    (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
+		    (!dev || !t->parms.link || ifindex == t->parms.link ||
+		     sifindex == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
 	for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) {
 		if (remote == t->parms.iph.daddr &&
-		    (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
+		    (!dev || !t->parms.link || ifindex == t->parms.link ||
+		     sifindex == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
 	for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) {
 		if (local == t->parms.iph.saddr &&
-		    (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
+		    (!dev || !t->parms.link || ifindex == t->parms.link ||
+		     sifindex == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -486,6 +492,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 	const int code = icmp_hdr(skb)->code;
 	unsigned int data_len = 0;
 	struct ip_tunnel *t;
+	int sifindex;
 	int err;
 
 	switch (type) {
@@ -517,10 +524,9 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 
 	err = -ENOENT;
 
-	t = ipip6_tunnel_lookup(dev_net(skb->dev),
-				skb->dev,
-				iph->daddr,
-				iph->saddr);
+	sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0;
+	t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
+				iph->daddr, iph->saddr, sifindex);
 	if (!t)
 		goto out;
 
@@ -633,10 +639,12 @@ static int ipip6_rcv(struct sk_buff *skb)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct ip_tunnel *tunnel;
+	int sifindex;
 	int err;
 
+	sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0;
 	tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
-				     iph->saddr, iph->daddr);
+				     iph->saddr, iph->daddr, sifindex);
 	if (tunnel) {
 		struct pcpu_sw_netstats *tstats;
 
@@ -704,10 +712,13 @@ static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto)
 {
 	const struct iphdr *iph;
 	struct ip_tunnel *tunnel;
+	int sifindex;
+
+	sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0;
 
 	iph = ip_hdr(skb);
 	tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
-				     iph->saddr, iph->daddr);
+				     iph->saddr, iph->daddr, sifindex);
 	if (tunnel) {
 		const struct tnl_ptk_info *tpi;
 
@@ -1848,19 +1859,22 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit sit_exit_net(struct net *net)
+static void __net_exit sit_exit_batch_net(struct list_head *net_list)
 {
 	LIST_HEAD(list);
+	struct net *net;
 
 	rtnl_lock();
-	sit_destroy_tunnels(net, &list);
+	list_for_each_entry(net, net_list, exit_list)
+		sit_destroy_tunnels(net, &list);
+
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
 
 static struct pernet_operations sit_net_ops = {
 	.init = sit_init_net,
-	.exit = sit_exit_net,
+	.exit_batch = sit_exit_batch_net,
 	.id   = &sit_net_id,
 	.size = sizeof(struct sit_net),
 };
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 4e7817abc0b9..e7a3a6b6cf56 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -244,7 +244,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	}
 
 	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
-	tcp_select_initial_window(tcp_full_space(sk), req->mss,
+	tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
 				  &req->rsk_rcv_wnd, &req->rsk_window_clamp,
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(dst, RTAX_INITRWND));
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index f7051ba5b8af..a789a8ac6a64 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -98,6 +98,34 @@ static struct ctl_table ipv6_table_template[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "max_dst_opts_number",
+		.data		= &init_net.ipv6.sysctl.max_dst_opts_cnt,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "max_hbh_opts_number",
+		.data		= &init_net.ipv6.sysctl.max_hbh_opts_cnt,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "max_dst_opts_length",
+		.data		= &init_net.ipv6.sysctl.max_dst_opts_len,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "max_hbh_length",
+		.data		= &init_net.ipv6.sysctl.max_hbh_opts_len,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 	{ }
 };
 
@@ -158,6 +186,10 @@ static int __net_init ipv6_sysctl_net_init(struct net *net)
 	ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges;
 	ipv6_table[8].data = &net->ipv6.sysctl.ip_nonlocal_bind;
 	ipv6_table[9].data = &net->ipv6.sysctl.flowlabel_reflect;
+	ipv6_table[10].data = &net->ipv6.sysctl.max_dst_opts_cnt;
+	ipv6_table[11].data = &net->ipv6.sysctl.max_hbh_opts_cnt;
+	ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len;
+	ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len;
 
 	ipv6_route_table = ipv6_route_sysctl_init(net);
 	if (!ipv6_route_table)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 64d94afa427f..0e2529958b52 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -69,6 +69,8 @@
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
+#include <trace/events/tcp.h>
+
 static void	tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb);
 static void	tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 				      struct request_sock *req);
@@ -890,7 +892,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 	int genhash;
 	struct sock *sk1 = NULL;
 #endif
-	int oif;
+	int oif = 0;
 
 	if (th->rst)
 		return;
@@ -939,7 +941,11 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 		ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len -
 			  (th->doff << 2);
 
-	oif = sk ? sk->sk_bound_dev_if : 0;
+	if (sk) {
+		oif = sk->sk_bound_dev_if;
+		trace_tcp_send_reset(sk, skb);
+	}
+
 	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1577,8 +1583,9 @@ do_time_wait:
 			refcounted = false;
 			goto process;
 		}
-		/* Fall through to ACK */
 	}
+		/* to ACK */
+		/* fall through */
 	case TCP_TW_ACK:
 		tcp_v6_timewait_ack(sk, skb);
 		break;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 17e95a0386b3..885ade234a49 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -153,6 +153,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 		switch (nexthdr) {
 		case NEXTHDR_FRAGMENT:
 			onlyproto = 1;
+			/* fall through */
 		case NEXTHDR_ROUTING:
 		case NEXTHDR_HOP:
 		case NEXTHDR_DEST:
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index ac598ec90589..d21a9d128d3e 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1867,6 +1867,7 @@ static int ipx_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		rc = -EPERM;
 		if (!capable(CAP_NET_ADMIN))
 			break;
+		/* fall through */
 	case SIOCGIFADDR:
 		rc = ipxitf_ioctl(cmd, argp);
 		break;
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index af4e76ac88ff..0b750a22c4b9 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1650,7 +1650,7 @@ static int kcm_clone(struct socket *osock, struct kcm_clone *info,
 	}
 
 	newfile = sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name);
-	if (unlikely(IS_ERR(newfile))) {
+	if (IS_ERR(newfile)) {
 		err = PTR_ERR(newfile);
 		goto out_sock_alloc_fail;
 	}
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 02d61101b108..7c8d1eb757a5 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -100,8 +100,6 @@ struct l2tp_skb_cb {
 
 #define L2TP_SKB_CB(skb)	((struct l2tp_skb_cb *) &skb->cb[sizeof(struct inet_skb_parm)])
 
-static atomic_t l2tp_tunnel_count;
-static atomic_t l2tp_session_count;
 static struct workqueue_struct *l2tp_wq;
 
 /* per-net private data for this module */
@@ -216,12 +214,10 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_get);
 
-/* Lookup a session. A new reference is held on the returned session.
- * Optionally calls session->ref() too if do_ref is true.
- */
+/* Lookup a session. A new reference is held on the returned session. */
 struct l2tp_session *l2tp_session_get(const struct net *net,
 				      struct l2tp_tunnel *tunnel,
-				      u32 session_id, bool do_ref)
+				      u32 session_id)
 {
 	struct hlist_head *session_list;
 	struct l2tp_session *session;
@@ -235,8 +231,6 @@ struct l2tp_session *l2tp_session_get(const struct net *net,
 		hlist_for_each_entry_rcu(session, session_list, global_hlist) {
 			if (session->session_id == session_id) {
 				l2tp_session_inc_refcount(session);
-				if (do_ref && session->ref)
-					session->ref(session);
 				rcu_read_unlock_bh();
 
 				return session;
@@ -252,8 +246,6 @@ struct l2tp_session *l2tp_session_get(const struct net *net,
 	hlist_for_each_entry(session, session_list, hlist) {
 		if (session->session_id == session_id) {
 			l2tp_session_inc_refcount(session);
-			if (do_ref && session->ref)
-				session->ref(session);
 			read_unlock_bh(&tunnel->hlist_lock);
 
 			return session;
@@ -265,8 +257,7 @@ struct l2tp_session *l2tp_session_get(const struct net *net,
 }
 EXPORT_SYMBOL_GPL(l2tp_session_get);
 
-struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
-					  bool do_ref)
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth)
 {
 	int hash;
 	struct l2tp_session *session;
@@ -277,8 +268,6 @@ struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
 		hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) {
 			if (++count > nth) {
 				l2tp_session_inc_refcount(session);
-				if (do_ref && session->ref)
-					session->ref(session);
 				read_unlock_bh(&tunnel->hlist_lock);
 				return session;
 			}
@@ -295,8 +284,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_get_nth);
  * This is very inefficient but is only used by management interfaces.
  */
 struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
-						const char *ifname,
-						bool do_ref)
+						const char *ifname)
 {
 	struct l2tp_net *pn = l2tp_pernet(net);
 	int hash;
@@ -307,8 +295,6 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
 		hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) {
 			if (!strcmp(session->ifname, ifname)) {
 				l2tp_session_inc_refcount(session);
-				if (do_ref && session->ref)
-					session->ref(session);
 				rcu_read_unlock_bh();
 
 				return session;
@@ -322,8 +308,8 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
 }
 EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname);
 
-static int l2tp_session_add_to_tunnel(struct l2tp_tunnel *tunnel,
-				      struct l2tp_session *session)
+int l2tp_session_register(struct l2tp_session *session,
+			  struct l2tp_tunnel *tunnel)
 {
 	struct l2tp_session *session_walk;
 	struct hlist_head *g_head;
@@ -380,6 +366,7 @@ err_tlock:
 
 	return err;
 }
+EXPORT_SYMBOL_GPL(l2tp_session_register);
 
 /* Lookup a tunnel by id
  */
@@ -484,9 +471,6 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff *
 		(*session->recv_skb)(session, skb, L2TP_SKB_CB(skb)->length);
 	else
 		kfree_skb(skb);
-
-	if (session->deref)
-		(*session->deref)(session);
 }
 
 /* Dequeue skbs from the session's reorder_q, subject to packet order.
@@ -515,8 +499,6 @@ start:
 			session->reorder_skip = 1;
 			__skb_unlink(skb, &session->reorder_q);
 			kfree_skb(skb);
-			if (session->deref)
-				(*session->deref)(session);
 			continue;
 		}
 
@@ -689,9 +671,6 @@ discard:
  * a data (not control) frame before coming here. Fields up to the
  * session-id have already been parsed and ptr points to the data
  * after the session-id.
- *
- * session->ref() must have been called prior to l2tp_recv_common().
- * session->deref() will be called automatically after skb is processed.
  */
 void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		      unsigned char *ptr, unsigned char *optr, u16 hdrflags,
@@ -858,9 +837,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 discard:
 	atomic_long_inc(&session->stats.rx_errors);
 	kfree_skb(skb);
-
-	if (session->deref)
-		(*session->deref)(session);
 }
 EXPORT_SYMBOL(l2tp_recv_common);
 
@@ -874,8 +850,6 @@ int l2tp_session_queue_purge(struct l2tp_session *session)
 	while ((skb = skb_dequeue(&session->reorder_q))) {
 		atomic_long_inc(&session->stats.rx_errors);
 		kfree_skb(skb);
-		if (session->deref)
-			(*session->deref)(session);
 	}
 	return 0;
 }
@@ -967,13 +941,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
 	}
 
 	/* Find the session context */
-	session = l2tp_session_get(tunnel->l2tp_net, tunnel, session_id, true);
+	session = l2tp_session_get(tunnel->l2tp_net, tunnel, session_id);
 	if (!session || !session->recv_skb) {
-		if (session) {
-			if (session->deref)
-				session->deref(session);
+		if (session)
 			l2tp_session_dec_refcount(session);
-		}
 
 		/* Not found? Pass to userspace to deal with */
 		l2tp_info(tunnel, L2TP_MSG_DATA,
@@ -1274,7 +1245,6 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
 	list_del_rcu(&tunnel->list);
 	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
-	atomic_dec(&l2tp_tunnel_count);
 
 	l2tp_tunnel_closeall(tunnel);
 
@@ -1317,9 +1287,6 @@ again:
 			if (test_and_set_bit(0, &session->dead))
 				goto again;
 
-			if (session->ref != NULL)
-				(*session->ref)(session);
-
 			write_unlock_bh(&tunnel->hlist_lock);
 
 			__l2tp_session_unhash(session);
@@ -1328,9 +1295,6 @@ again:
 			if (session->session_close != NULL)
 				(*session->session_close)(session);
 
-			if (session->deref != NULL)
-				(*session->deref)(session);
-
 			l2tp_session_dec_refcount(session);
 
 			write_lock_bh(&tunnel->hlist_lock);
@@ -1661,7 +1625,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 
 	/* Add tunnel to our list */
 	INIT_LIST_HEAD(&tunnel->list);
-	atomic_inc(&l2tp_tunnel_count);
 
 	/* Bump the reference count. The tunnel context is deleted
 	 * only when this drops to zero. Must be done before list insertion
@@ -1707,8 +1670,6 @@ void l2tp_session_free(struct l2tp_session *session)
 
 	if (tunnel) {
 		BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
-		if (session->session_id != 0)
-			atomic_dec(&l2tp_session_count);
 		sock_put(tunnel->sock);
 		session->tunnel = NULL;
 		l2tp_tunnel_dec_refcount(tunnel);
@@ -1754,15 +1715,13 @@ int l2tp_session_delete(struct l2tp_session *session)
 	if (test_and_set_bit(0, &session->dead))
 		return 0;
 
-	if (session->ref)
-		(*session->ref)(session);
 	__l2tp_session_unhash(session);
 	l2tp_session_queue_purge(session);
 	if (session->session_close != NULL)
 		(*session->session_close)(session);
-	if (session->deref)
-		(*session->deref)(session);
+
 	l2tp_session_dec_refcount(session);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(l2tp_session_delete);
@@ -1788,7 +1747,6 @@ EXPORT_SYMBOL_GPL(l2tp_session_set_header_len);
 struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
 {
 	struct l2tp_session *session;
-	int err;
 
 	session = kzalloc(sizeof(struct l2tp_session) + priv_size, GFP_KERNEL);
 	if (session != NULL) {
@@ -1846,17 +1804,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
 
 		refcount_set(&session->ref_count, 1);
 
-		err = l2tp_session_add_to_tunnel(tunnel, session);
-		if (err) {
-			kfree(session);
-
-			return ERR_PTR(err);
-		}
-
-		/* Ignore management session in session count value */
-		if (session->session_id != 0)
-			atomic_inc(&l2tp_session_count);
-
 		return session;
 	}
 
@@ -1891,7 +1838,7 @@ static __net_exit void l2tp_exit_net(struct net *net)
 
 	rcu_read_lock_bh();
 	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		(void)l2tp_tunnel_delete(tunnel);
+		l2tp_tunnel_delete(tunnel);
 	}
 	rcu_read_unlock_bh();
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 67c79d9b5c6c..9534e16965cc 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -129,8 +129,6 @@ struct l2tp_session {
 	int (*build_header)(struct l2tp_session *session, void *buf);
 	void (*recv_skb)(struct l2tp_session *session, struct sk_buff *skb, int data_len);
 	void (*session_close)(struct l2tp_session *session);
-	void (*ref)(struct l2tp_session *session);
-	void (*deref)(struct l2tp_session *session);
 #if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
 	void (*show)(struct seq_file *m, void *priv);
 #endif
@@ -245,12 +243,10 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id);
 
 struct l2tp_session *l2tp_session_get(const struct net *net,
 				      struct l2tp_tunnel *tunnel,
-				      u32 session_id, bool do_ref);
-struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
-					  bool do_ref);
+				      u32 session_id);
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth);
 struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
-						const char *ifname,
-						bool do_ref);
+						const char *ifname);
 struct l2tp_tunnel *l2tp_tunnel_find(const struct net *net, u32 tunnel_id);
 struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth);
 
@@ -263,6 +259,9 @@ struct l2tp_session *l2tp_session_create(int priv_size,
 					 struct l2tp_tunnel *tunnel,
 					 u32 session_id, u32 peer_session_id,
 					 struct l2tp_session_cfg *cfg);
+int l2tp_session_register(struct l2tp_session *session,
+			  struct l2tp_tunnel *tunnel);
+
 void __l2tp_session_unhash(struct l2tp_session *session);
 int l2tp_session_delete(struct l2tp_session *session);
 void l2tp_session_free(struct l2tp_session *session);
@@ -295,37 +294,17 @@ static inline void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel)
 /* Session reference counts. Incremented when code obtains a reference
  * to a session.
  */
-static inline void l2tp_session_inc_refcount_1(struct l2tp_session *session)
+static inline void l2tp_session_inc_refcount(struct l2tp_session *session)
 {
 	refcount_inc(&session->ref_count);
 }
 
-static inline void l2tp_session_dec_refcount_1(struct l2tp_session *session)
+static inline void l2tp_session_dec_refcount(struct l2tp_session *session)
 {
 	if (refcount_dec_and_test(&session->ref_count))
 		l2tp_session_free(session);
 }
 
-#ifdef L2TP_REFCNT_DEBUG
-#define l2tp_session_inc_refcount(_s)					\
-do {									\
-	pr_debug("l2tp_session_inc_refcount: %s:%d %s: cnt=%d\n",	\
-		 __func__, __LINE__, (_s)->name,			\
-		 refcount_read(&_s->ref_count));			\
-	l2tp_session_inc_refcount_1(_s);				\
-} while (0)
-#define l2tp_session_dec_refcount(_s)					\
-do {									\
-	pr_debug("l2tp_session_dec_refcount: %s:%d %s: cnt=%d\n",	\
-		 __func__, __LINE__, (_s)->name,			\
-		 refcount_read(&_s->ref_count));			\
-	l2tp_session_dec_refcount_1(_s);				\
-} while (0)
-#else
-#define l2tp_session_inc_refcount(s) l2tp_session_inc_refcount_1(s)
-#define l2tp_session_dec_refcount(s) l2tp_session_dec_refcount_1(s)
-#endif
-
 #define l2tp_printk(ptr, type, func, fmt, ...)				\
 do {									\
 	if (((ptr)->debug) & (type))					\
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 53bae54c4d6e..eb69411bcb47 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -53,7 +53,7 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd)
 
 static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
 {
-	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
+	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx);
 	pd->session_idx++;
 
 	if (pd->session == NULL) {
@@ -241,8 +241,6 @@ static int l2tp_dfs_seq_show(struct seq_file *m, void *v)
 		l2tp_dfs_seq_tunnel_show(m, pd->tunnel);
 	} else {
 		l2tp_dfs_seq_session_show(m, pd->session);
-		if (pd->session->deref)
-			pd->session->deref(pd->session);
 		l2tp_session_dec_refcount(pd->session);
 	}
 
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 014a7bc2a872..3e2dec1fb0f5 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -41,7 +41,6 @@
 
 /* via netdev_priv() */
 struct l2tp_eth {
-	struct net_device	*dev;
 	struct sock		*tunnel_sock;
 	struct l2tp_session	*session;
 	atomic_long_t		tx_bytes;
@@ -54,15 +53,12 @@ struct l2tp_eth {
 
 /* via l2tp_session_priv() */
 struct l2tp_eth_sess {
-	struct net_device	*dev;
+	struct net_device __rcu *dev;
 };
 
 
 static int l2tp_eth_dev_init(struct net_device *dev)
 {
-	struct l2tp_eth *priv = netdev_priv(dev);
-
-	priv->dev = dev;
 	eth_hw_addr_random(dev);
 	eth_broadcast_addr(dev->broadcast);
 	netdev_lockdep_set_classes(dev);
@@ -72,7 +68,14 @@ static int l2tp_eth_dev_init(struct net_device *dev)
 
 static void l2tp_eth_dev_uninit(struct net_device *dev)
 {
-	dev_put(dev);
+	struct l2tp_eth *priv = netdev_priv(dev);
+	struct l2tp_eth_sess *spriv;
+
+	spriv = l2tp_session_priv(priv->session);
+	RCU_INIT_POINTER(spriv->dev, NULL);
+	/* No need for synchronize_net() here. We're called by
+	 * unregister_netdev*(), which does the synchronisation for us.
+	 */
 }
 
 static int l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -130,8 +133,8 @@ static void l2tp_eth_dev_setup(struct net_device *dev)
 static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len)
 {
 	struct l2tp_eth_sess *spriv = l2tp_session_priv(session);
-	struct net_device *dev = spriv->dev;
-	struct l2tp_eth *priv = netdev_priv(dev);
+	struct net_device *dev;
+	struct l2tp_eth *priv;
 
 	if (session->debug & L2TP_MSG_DATA) {
 		unsigned int length;
@@ -155,16 +158,25 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb,
 	skb_dst_drop(skb);
 	nf_reset(skb);
 
+	rcu_read_lock();
+	dev = rcu_dereference(spriv->dev);
+	if (!dev)
+		goto error_rcu;
+
+	priv = netdev_priv(dev);
 	if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) {
 		atomic_long_inc(&priv->rx_packets);
 		atomic_long_add(data_len, &priv->rx_bytes);
 	} else {
 		atomic_long_inc(&priv->rx_errors);
 	}
+	rcu_read_unlock();
+
 	return;
 
+error_rcu:
+	rcu_read_unlock();
 error:
-	atomic_long_inc(&priv->rx_errors);
 	kfree_skb(skb);
 }
 
@@ -175,11 +187,15 @@ static void l2tp_eth_delete(struct l2tp_session *session)
 
 	if (session) {
 		spriv = l2tp_session_priv(session);
-		dev = spriv->dev;
+
+		rtnl_lock();
+		dev = rtnl_dereference(spriv->dev);
 		if (dev) {
-			unregister_netdev(dev);
-			spriv->dev = NULL;
+			unregister_netdevice(dev);
+			rtnl_unlock();
 			module_put(THIS_MODULE);
+		} else {
+			rtnl_unlock();
 		}
 	}
 }
@@ -189,9 +205,20 @@ static void l2tp_eth_show(struct seq_file *m, void *arg)
 {
 	struct l2tp_session *session = arg;
 	struct l2tp_eth_sess *spriv = l2tp_session_priv(session);
-	struct net_device *dev = spriv->dev;
+	struct net_device *dev;
+
+	rcu_read_lock();
+	dev = rcu_dereference(spriv->dev);
+	if (!dev) {
+		rcu_read_unlock();
+		return;
+	}
+	dev_hold(dev);
+	rcu_read_unlock();
 
 	seq_printf(m, "   interface %s\n", dev->name);
+
+	dev_put(dev);
 }
 #endif
 
@@ -268,14 +295,14 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 				      peer_session_id, cfg);
 	if (IS_ERR(session)) {
 		rc = PTR_ERR(session);
-		goto out;
+		goto err;
 	}
 
 	dev = alloc_netdev(sizeof(*priv), name, name_assign_type,
 			   l2tp_eth_dev_setup);
 	if (!dev) {
 		rc = -ENOMEM;
-		goto out_del_session;
+		goto err_sess;
 	}
 
 	dev_net_set(dev, net);
@@ -284,7 +311,6 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 	l2tp_eth_adjust_mtu(tunnel, session, dev);
 
 	priv = netdev_priv(dev);
-	priv->dev = dev;
 	priv->session = session;
 
 	priv->tunnel_sock = tunnel->sock;
@@ -295,26 +321,48 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 #endif
 
 	spriv = l2tp_session_priv(session);
-	spriv->dev = dev;
 
-	rc = register_netdev(dev);
-	if (rc < 0)
-		goto out_del_dev;
+	l2tp_session_inc_refcount(session);
+
+	rtnl_lock();
+
+	/* Register both device and session while holding the rtnl lock. This
+	 * ensures that l2tp_eth_delete() will see that there's a device to
+	 * unregister, even if it happened to run before we assign spriv->dev.
+	 */
+	rc = l2tp_session_register(session, tunnel);
+	if (rc < 0) {
+		rtnl_unlock();
+		goto err_sess_dev;
+	}
+
+	rc = register_netdevice(dev);
+	if (rc < 0) {
+		rtnl_unlock();
+		l2tp_session_delete(session);
+		l2tp_session_dec_refcount(session);
+		free_netdev(dev);
+
+		return rc;
+	}
 
-	__module_get(THIS_MODULE);
-	/* Must be done after register_netdev() */
 	strlcpy(session->ifname, dev->name, IFNAMSIZ);
+	rcu_assign_pointer(spriv->dev, dev);
 
-	dev_hold(dev);
+	rtnl_unlock();
+
+	l2tp_session_dec_refcount(session);
+
+	__module_get(THIS_MODULE);
 
 	return 0;
 
-out_del_dev:
+err_sess_dev:
+	l2tp_session_dec_refcount(session);
 	free_netdev(dev);
-	spriv->dev = NULL;
-out_del_session:
-	l2tp_session_delete(session);
-out:
+err_sess:
+	kfree(session);
+err:
 	return rc;
 }
 
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 4d322c1b7233..6dbe450400a2 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -143,7 +143,7 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	}
 
 	/* Ok, this is a data packet. Lookup the session. */
-	session = l2tp_session_get(net, NULL, session_id, true);
+	session = l2tp_session_get(net, NULL, session_id);
 	if (!session)
 		goto discard;
 
@@ -205,8 +205,6 @@ pass_up:
 	return sk_receive_skb(sk, skb, 1);
 
 discard_sess:
-	if (session->deref)
-		session->deref(session);
 	l2tp_session_dec_refcount(session);
 	goto discard;
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 88b397c30d86..59ebb6e4f735 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -156,7 +156,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	}
 
 	/* Ok, this is a data packet. Lookup the session. */
-	session = l2tp_session_get(net, NULL, session_id, true);
+	session = l2tp_session_get(net, NULL, session_id);
 	if (!session)
 		goto discard;
 
@@ -219,8 +219,6 @@ pass_up:
 	return sk_receive_skb(sk, skb, 1);
 
 discard_sess:
-	if (session->deref)
-		session->deref(session);
 	l2tp_session_dec_refcount(session);
 	goto discard;
 
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 7135f4645d3a..a1f24fb2be98 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -48,8 +48,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq,
 /* Accessed under genl lock */
 static const struct l2tp_nl_cmd_ops *l2tp_nl_cmd_ops[__L2TP_PWTYPE_MAX];
 
-static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info,
-						bool do_ref)
+static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info)
 {
 	u32 tunnel_id;
 	u32 session_id;
@@ -60,15 +59,14 @@ static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info,
 
 	if (info->attrs[L2TP_ATTR_IFNAME]) {
 		ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]);
-		session = l2tp_session_get_by_ifname(net, ifname, do_ref);
+		session = l2tp_session_get_by_ifname(net, ifname);
 	} else if ((info->attrs[L2TP_ATTR_SESSION_ID]) &&
 		   (info->attrs[L2TP_ATTR_CONN_ID])) {
 		tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]);
 		session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]);
 		tunnel = l2tp_tunnel_get(net, tunnel_id);
 		if (tunnel) {
-			session = l2tp_session_get(net, tunnel, session_id,
-						   do_ref);
+			session = l2tp_session_get(net, tunnel, session_id);
 			l2tp_tunnel_dec_refcount(tunnel);
 		}
 	}
@@ -282,7 +280,7 @@ static int l2tp_nl_cmd_tunnel_delete(struct sk_buff *skb, struct genl_info *info
 	l2tp_tunnel_notify(&l2tp_nl_family, info,
 			   tunnel, L2TP_CMD_TUNNEL_DELETE);
 
-	(void) l2tp_tunnel_delete(tunnel);
+	l2tp_tunnel_delete(tunnel);
 
 	l2tp_tunnel_dec_refcount(tunnel);
 
@@ -406,7 +404,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 		if (nla_put_u16(skb, L2TP_ATTR_UDP_SPORT, ntohs(inet->inet_sport)) ||
 		    nla_put_u16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport)))
 			goto nla_put_failure;
-		/* NOBREAK */
+		/* fall through  */
 	case L2TP_ENCAPTYPE_IP:
 #if IS_ENABLED(CONFIG_IPV6)
 		if (np) {
@@ -649,7 +647,7 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 							   &cfg);
 
 	if (ret >= 0) {
-		session = l2tp_session_get(net, tunnel, session_id, false);
+		session = l2tp_session_get(net, tunnel, session_id);
 		if (session) {
 			ret = l2tp_session_notify(&l2tp_nl_family, info, session,
 						  L2TP_CMD_SESSION_CREATE);
@@ -669,7 +667,7 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf
 	struct l2tp_session *session;
 	u16 pw_type;
 
-	session = l2tp_nl_session_get(info, true);
+	session = l2tp_nl_session_get(info);
 	if (session == NULL) {
 		ret = -ENODEV;
 		goto out;
@@ -683,8 +681,6 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf
 		if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete)
 			ret = (*l2tp_nl_cmd_ops[pw_type]->session_delete)(session);
 
-	if (session->deref)
-		session->deref(session);
 	l2tp_session_dec_refcount(session);
 
 out:
@@ -696,7 +692,7 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 	int ret = 0;
 	struct l2tp_session *session;
 
-	session = l2tp_nl_session_get(info, false);
+	session = l2tp_nl_session_get(info);
 	if (session == NULL) {
 		ret = -ENODEV;
 		goto out;
@@ -828,7 +824,7 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info)
 	struct sk_buff *msg;
 	int ret;
 
-	session = l2tp_nl_session_get(info, false);
+	session = l2tp_nl_session_get(info);
 	if (session == NULL) {
 		ret = -ENODEV;
 		goto err;
@@ -874,7 +870,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 				goto out;
 		}
 
-		session = l2tp_session_get_nth(tunnel, si, false);
+		session = l2tp_session_get_nth(tunnel, si);
 		if (session == NULL) {
 			ti++;
 			tunnel = NULL;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 0c2738349442..5f5c78b632d0 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -122,8 +122,11 @@
 struct pppol2tp_session {
 	int			owner;		/* pid that opened the socket */
 
-	struct sock		*sock;		/* Pointer to the session
+	struct mutex		sk_lock;	/* Protects .sk */
+	struct sock __rcu	*sk;		/* Pointer to the session
 						 * PPPoX socket */
+	struct sock		*__sk;		/* Copy of .sk, for cleanup */
+	struct rcu_head		rcu;		/* For asynchronous release */
 	struct sock		*tunnel_sock;	/* Pointer to the tunnel UDP
 						 * socket */
 	int			flags;		/* accessed by PPPIOCGFLAGS.
@@ -138,6 +141,24 @@ static const struct ppp_channel_ops pppol2tp_chan_ops = {
 
 static const struct proto_ops pppol2tp_ops;
 
+/* Retrieves the pppol2tp socket associated to a session.
+ * A reference is held on the returned socket, so this function must be paired
+ * with sock_put().
+ */
+static struct sock *pppol2tp_session_get_sock(struct l2tp_session *session)
+{
+	struct pppol2tp_session *ps = l2tp_session_priv(session);
+	struct sock *sk;
+
+	rcu_read_lock();
+	sk = rcu_dereference(ps->sk);
+	if (sk)
+		sock_hold(sk);
+	rcu_read_unlock();
+
+	return sk;
+}
+
 /* Helpers to obtain tunnel/session contexts from sockets.
  */
 static inline struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk)
@@ -224,7 +245,8 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
 	/* If the socket is bound, send it in to PPP's input queue. Otherwise
 	 * queue it on the session socket.
 	 */
-	sk = ps->sock;
+	rcu_read_lock();
+	sk = rcu_dereference(ps->sk);
 	if (sk == NULL)
 		goto no_sock;
 
@@ -247,30 +269,16 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
 			kfree_skb(skb);
 		}
 	}
+	rcu_read_unlock();
 
 	return;
 
 no_sock:
+	rcu_read_unlock();
 	l2tp_info(session, L2TP_MSG_DATA, "%s: no socket\n", session->name);
 	kfree_skb(skb);
 }
 
-static void pppol2tp_session_sock_hold(struct l2tp_session *session)
-{
-	struct pppol2tp_session *ps = l2tp_session_priv(session);
-
-	if (ps->sock)
-		sock_hold(ps->sock);
-}
-
-static void pppol2tp_session_sock_put(struct l2tp_session *session)
-{
-	struct pppol2tp_session *ps = l2tp_session_priv(session);
-
-	if (ps->sock)
-		sock_put(ps->sock);
-}
-
 /************************************************************************
  * Transmit handling
  ***********************************************************************/
@@ -431,17 +439,16 @@ abort:
  */
 static void pppol2tp_session_close(struct l2tp_session *session)
 {
-	struct pppol2tp_session *ps = l2tp_session_priv(session);
-	struct sock *sk = ps->sock;
-	struct socket *sock = sk->sk_socket;
+	struct sock *sk;
 
 	BUG_ON(session->magic != L2TP_SESSION_MAGIC);
 
-	if (sock)
-		inet_shutdown(sock, SEND_SHUTDOWN);
-
-	/* Don't let the session go away before our socket does */
-	l2tp_session_inc_refcount(session);
+	sk = pppol2tp_session_get_sock(session);
+	if (sk) {
+		if (sk->sk_socket)
+			inet_shutdown(sk->sk_socket, SEND_SHUTDOWN);
+		sock_put(sk);
+	}
 }
 
 /* Really kill the session socket. (Called from sock_put() if
@@ -461,6 +468,14 @@ static void pppol2tp_session_destruct(struct sock *sk)
 	}
 }
 
+static void pppol2tp_put_sk(struct rcu_head *head)
+{
+	struct pppol2tp_session *ps;
+
+	ps = container_of(head, typeof(*ps), rcu);
+	sock_put(ps->__sk);
+}
+
 /* Called when the PPPoX socket (session) is closed.
  */
 static int pppol2tp_release(struct socket *sock)
@@ -486,11 +501,23 @@ static int pppol2tp_release(struct socket *sock)
 
 	session = pppol2tp_sock_to_session(sk);
 
-	/* Purge any queued data */
 	if (session != NULL) {
-		__l2tp_session_unhash(session);
-		l2tp_session_queue_purge(session);
-		sock_put(sk);
+		struct pppol2tp_session *ps;
+
+		l2tp_session_delete(session);
+
+		ps = l2tp_session_priv(session);
+		mutex_lock(&ps->sk_lock);
+		ps->__sk = rcu_dereference_protected(ps->sk,
+						     lockdep_is_held(&ps->sk_lock));
+		RCU_INIT_POINTER(ps->sk, NULL);
+		mutex_unlock(&ps->sk_lock);
+		call_rcu(&ps->rcu, pppol2tp_put_sk);
+
+		/* Rely on the sock_put() call at the end of the function for
+		 * dropping the reference held by pppol2tp_sock_to_session().
+		 * The last reference will be dropped by pppol2tp_put_sk().
+		 */
 	}
 	release_sock(sk);
 
@@ -557,16 +584,47 @@ out:
 static void pppol2tp_show(struct seq_file *m, void *arg)
 {
 	struct l2tp_session *session = arg;
-	struct pppol2tp_session *ps = l2tp_session_priv(session);
+	struct sock *sk;
+
+	sk = pppol2tp_session_get_sock(session);
+	if (sk) {
+		struct pppox_sock *po = pppox_sk(sk);
 
-	if (ps) {
-		struct pppox_sock *po = pppox_sk(ps->sock);
-		if (po)
-			seq_printf(m, "   interface %s\n", ppp_dev_name(&po->chan));
+		seq_printf(m, "   interface %s\n", ppp_dev_name(&po->chan));
+		sock_put(sk);
 	}
 }
 #endif
 
+static void pppol2tp_session_init(struct l2tp_session *session)
+{
+	struct pppol2tp_session *ps;
+	struct dst_entry *dst;
+
+	session->recv_skb = pppol2tp_recv;
+	session->session_close = pppol2tp_session_close;
+#if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
+	session->show = pppol2tp_show;
+#endif
+
+	ps = l2tp_session_priv(session);
+	mutex_init(&ps->sk_lock);
+	ps->tunnel_sock = session->tunnel->sock;
+	ps->owner = current->pid;
+
+	/* If PMTU discovery was enabled, use the MTU that was discovered */
+	dst = sk_dst_get(session->tunnel->sock);
+	if (dst) {
+		u32 pmtu = dst_mtu(dst);
+
+		if (pmtu) {
+			session->mtu = pmtu - PPPOL2TP_HEADER_OVERHEAD;
+			session->mru = pmtu - PPPOL2TP_HEADER_OVERHEAD;
+		}
+		dst_release(dst);
+	}
+}
+
 /* connect() handler. Attach a PPPoX socket to a tunnel UDP socket
  */
 static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
@@ -578,7 +636,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	struct l2tp_session *session = NULL;
 	struct l2tp_tunnel *tunnel;
 	struct pppol2tp_session *ps;
-	struct dst_entry *dst;
 	struct l2tp_session_cfg cfg = { 0, };
 	int error = 0;
 	u32 tunnel_id, peer_tunnel_id;
@@ -688,7 +745,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	if (tunnel->peer_tunnel_id == 0)
 		tunnel->peer_tunnel_id = peer_tunnel_id;
 
-	session = l2tp_session_get(sock_net(sk), tunnel, session_id, false);
+	session = l2tp_session_get(sock_net(sk), tunnel, session_id);
 	if (session) {
 		drop_refcnt = true;
 		ps = l2tp_session_priv(session);
@@ -696,13 +753,17 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 		/* Using a pre-existing session is fine as long as it hasn't
 		 * been connected yet.
 		 */
-		if (ps->sock) {
+		mutex_lock(&ps->sk_lock);
+		if (rcu_dereference_protected(ps->sk,
+					      lockdep_is_held(&ps->sk_lock))) {
+			mutex_unlock(&ps->sk_lock);
 			error = -EEXIST;
 			goto end;
 		}
 
 		/* consistency checks */
 		if (ps->tunnel_sock != tunnel->sock) {
+			mutex_unlock(&ps->sk_lock);
 			error = -EEXIST;
 			goto end;
 		}
@@ -718,35 +779,19 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 			error = PTR_ERR(session);
 			goto end;
 		}
-	}
-
-	/* Associate session with its PPPoL2TP socket */
-	ps = l2tp_session_priv(session);
-	ps->owner	     = current->pid;
-	ps->sock	     = sk;
-	ps->tunnel_sock = tunnel->sock;
-
-	session->recv_skb	= pppol2tp_recv;
-	session->session_close	= pppol2tp_session_close;
-#if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
-	session->show		= pppol2tp_show;
-#endif
-
-	/* We need to know each time a skb is dropped from the reorder
-	 * queue.
-	 */
-	session->ref = pppol2tp_session_sock_hold;
-	session->deref = pppol2tp_session_sock_put;
 
-	/* If PMTU discovery was enabled, use the MTU that was discovered */
-	dst = sk_dst_get(tunnel->sock);
-	if (dst != NULL) {
-		u32 pmtu = dst_mtu(dst);
+		pppol2tp_session_init(session);
+		ps = l2tp_session_priv(session);
+		l2tp_session_inc_refcount(session);
 
-		if (pmtu != 0)
-			session->mtu = session->mru = pmtu -
-				PPPOL2TP_HEADER_OVERHEAD;
-		dst_release(dst);
+		mutex_lock(&ps->sk_lock);
+		error = l2tp_session_register(session, tunnel);
+		if (error < 0) {
+			mutex_unlock(&ps->sk_lock);
+			kfree(session);
+			goto end;
+		}
+		drop_refcnt = true;
 	}
 
 	/* Special case: if source & dest session_id == 0x0000, this
@@ -771,12 +816,23 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	po->chan.mtu	 = session->mtu;
 
 	error = ppp_register_net_channel(sock_net(sk), &po->chan);
-	if (error)
+	if (error) {
+		mutex_unlock(&ps->sk_lock);
 		goto end;
+	}
 
 out_no_ppp:
 	/* This is how we get the session context from the socket. */
 	sk->sk_user_data = session;
+	rcu_assign_pointer(ps->sk, sk);
+	mutex_unlock(&ps->sk_lock);
+
+	/* Keep the reference we've grabbed on the session: sk doesn't expect
+	 * the session to disappear. pppol2tp_session_destruct() is responsible
+	 * for dropping it.
+	 */
+	drop_refcnt = false;
+
 	sk->sk_state = PPPOX_CONNECTED;
 	l2tp_info(session, L2TP_MSG_CONTROL, "%s: created\n",
 		  session->name);
@@ -800,12 +856,11 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel,
 {
 	int error;
 	struct l2tp_session *session;
-	struct pppol2tp_session *ps;
 
 	/* Error if tunnel socket is not prepped */
 	if (!tunnel->sock) {
 		error = -ENOENT;
-		goto out;
+		goto err;
 	}
 
 	/* Default MTU values. */
@@ -820,18 +875,20 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel,
 				      peer_session_id, cfg);
 	if (IS_ERR(session)) {
 		error = PTR_ERR(session);
-		goto out;
+		goto err;
 	}
 
-	ps = l2tp_session_priv(session);
-	ps->tunnel_sock = tunnel->sock;
+	pppol2tp_session_init(session);
 
-	l2tp_info(session, L2TP_MSG_CONTROL, "%s: created\n",
-		  session->name);
+	error = l2tp_session_register(session, tunnel);
+	if (error < 0)
+		goto err_sess;
 
-	error = 0;
+	return 0;
 
-out:
+err_sess:
+	kfree(session);
+err:
 	return error;
 }
 
@@ -992,12 +1049,10 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
 		 "%s: pppol2tp_session_ioctl(cmd=%#x, arg=%#lx)\n",
 		 session->name, cmd, arg);
 
-	sk = ps->sock;
+	sk = pppol2tp_session_get_sock(session);
 	if (!sk)
 		return -EBADR;
 
-	sock_hold(sk);
-
 	switch (cmd) {
 	case SIOCGIFMTU:
 		err = -ENXIO;
@@ -1143,13 +1198,11 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
 			/* resend to session ioctl handler */
 			struct l2tp_session *session =
 				l2tp_session_get(sock_net(sk), tunnel,
-						 stats.session_id, true);
+						 stats.session_id);
 
 			if (session) {
 				err = pppol2tp_session_ioctl(session, cmd,
 							     arg);
-				if (session->deref)
-					session->deref(session);
 				l2tp_session_dec_refcount(session);
 			} else {
 				err = -EBADR;
@@ -1273,7 +1326,6 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
 				       int optname, int val)
 {
 	int err = 0;
-	struct pppol2tp_session *ps = l2tp_session_priv(session);
 
 	switch (optname) {
 	case PPPOL2TP_SO_RECVSEQ:
@@ -1294,8 +1346,8 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
 		}
 		session->send_seq = !!val;
 		{
-			struct sock *ssk      = ps->sock;
-			struct pppox_sock *po = pppox_sk(ssk);
+			struct pppox_sock *po = pppox_sk(sk);
+
 			po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ :
 				PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
 		}
@@ -1566,7 +1618,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
 
 static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
 {
-	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
+	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx);
 	pd->session_idx++;
 
 	if (pd->session == NULL) {
@@ -1634,8 +1686,9 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
 {
 	struct l2tp_session *session = v;
 	struct l2tp_tunnel *tunnel = session->tunnel;
-	struct pppol2tp_session *ps = l2tp_session_priv(session);
-	struct pppox_sock *po = pppox_sk(ps->sock);
+	unsigned char state;
+	char user_data_ok;
+	struct sock *sk;
 	u32 ip = 0;
 	u16 port = 0;
 
@@ -1645,6 +1698,15 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
 		port = ntohs(inet->inet_sport);
 	}
 
+	sk = pppol2tp_session_get_sock(session);
+	if (sk) {
+		state = sk->sk_state;
+		user_data_ok = (session == sk->sk_user_data) ? 'Y' : 'N';
+	} else {
+		state = 0;
+		user_data_ok = 'N';
+	}
+
 	seq_printf(m, "  SESSION '%s' %08X/%d %04X/%04X -> "
 		   "%04X/%04X %d %c\n",
 		   session->name, ip, port,
@@ -1652,9 +1714,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
 		   session->session_id,
 		   tunnel->peer_tunnel_id,
 		   session->peer_session_id,
-		   ps->sock->sk_state,
-		   (session == ps->sock->sk_user_data) ?
-		   'Y' : 'N');
+		   state, user_data_ok);
 	seq_printf(m, "   %d/%d/%c/%c/%s %08x %u\n",
 		   session->mtu, session->mru,
 		   session->recv_seq ? 'R' : '-',
@@ -1671,8 +1731,12 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
 		   atomic_long_read(&session->stats.rx_bytes),
 		   atomic_long_read(&session->stats.rx_errors));
 
-	if (po)
+	if (sk) {
+		struct pppox_sock *po = pppox_sk(sk);
+
 		seq_printf(m, "   interface %s\n", ppp_dev_name(&po->chan));
+		sock_put(sk);
+	}
 }
 
 static int pppol2tp_seq_show(struct seq_file *m, void *v)
@@ -1697,8 +1761,6 @@ static int pppol2tp_seq_show(struct seq_file *m, void *v)
 		pppol2tp_seq_tunnel_show(m, pd->tunnel);
 	} else {
 		pppol2tp_seq_session_show(m, pd->session);
-		if (pd->session->deref)
-			pd->session->deref(pd->session);
 		l2tp_session_dec_refcount(pd->session);
 	}
 
diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c
index e15314e3b464..db6e0afe3a20 100644
--- a/net/lapb/lapb_iface.c
+++ b/net/lapb/lapb_iface.c
@@ -127,8 +127,8 @@ static struct lapb_cb *lapb_create_cb(void)
 	skb_queue_head_init(&lapb->write_queue);
 	skb_queue_head_init(&lapb->ack_queue);
 
-	init_timer(&lapb->t1timer);
-	init_timer(&lapb->t2timer);
+	timer_setup(&lapb->t1timer, NULL, 0);
+	timer_setup(&lapb->t2timer, NULL, 0);
 
 	lapb->t1      = LAPB_DEFAULT_T1;
 	lapb->t2      = LAPB_DEFAULT_T2;
diff --git a/net/lapb/lapb_timer.c b/net/lapb/lapb_timer.c
index 1a5535bc3b8d..8bb469cb3abe 100644
--- a/net/lapb/lapb_timer.c
+++ b/net/lapb/lapb_timer.c
@@ -35,15 +35,14 @@
 #include <linux/interrupt.h>
 #include <net/lapb.h>
 
-static void lapb_t1timer_expiry(unsigned long);
-static void lapb_t2timer_expiry(unsigned long);
+static void lapb_t1timer_expiry(struct timer_list *);
+static void lapb_t2timer_expiry(struct timer_list *);
 
 void lapb_start_t1timer(struct lapb_cb *lapb)
 {
 	del_timer(&lapb->t1timer);
 
-	lapb->t1timer.data     = (unsigned long)lapb;
-	lapb->t1timer.function = &lapb_t1timer_expiry;
+	lapb->t1timer.function = (TIMER_FUNC_TYPE)lapb_t1timer_expiry;
 	lapb->t1timer.expires  = jiffies + lapb->t1;
 
 	add_timer(&lapb->t1timer);
@@ -53,8 +52,7 @@ void lapb_start_t2timer(struct lapb_cb *lapb)
 {
 	del_timer(&lapb->t2timer);
 
-	lapb->t2timer.data     = (unsigned long)lapb;
-	lapb->t2timer.function = &lapb_t2timer_expiry;
+	lapb->t2timer.function = (TIMER_FUNC_TYPE)lapb_t2timer_expiry;
 	lapb->t2timer.expires  = jiffies + lapb->t2;
 
 	add_timer(&lapb->t2timer);
@@ -75,9 +73,9 @@ int lapb_t1timer_running(struct lapb_cb *lapb)
 	return timer_pending(&lapb->t1timer);
 }
 
-static void lapb_t2timer_expiry(unsigned long param)
+static void lapb_t2timer_expiry(struct timer_list *t)
 {
-	struct lapb_cb *lapb = (struct lapb_cb *)param;
+	struct lapb_cb *lapb = from_timer(lapb, t, t2timer);
 
 	if (lapb->condition & LAPB_ACK_PENDING_CONDITION) {
 		lapb->condition &= ~LAPB_ACK_PENDING_CONDITION;
@@ -85,9 +83,9 @@ static void lapb_t2timer_expiry(unsigned long param)
 	}
 }
 
-static void lapb_t1timer_expiry(unsigned long param)
+static void lapb_t1timer_expiry(struct timer_list *t)
 {
-	struct lapb_cb *lapb = (struct lapb_cb *)param;
+	struct lapb_cb *lapb = from_timer(lapb, t, t1timer);
 
 	switch (lapb->state) {
 
diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c
index ea225bd2672c..f59648018060 100644
--- a/net/llc/llc_c_ac.c
+++ b/net/llc/llc_c_ac.c
@@ -1318,9 +1318,8 @@ static int llc_conn_ac_inc_vs_by_1(struct sock *sk, struct sk_buff *skb)
 	return 0;
 }
 
-static void llc_conn_tmr_common_cb(unsigned long timeout_data, u8 type)
+static void llc_conn_tmr_common_cb(struct sock *sk, u8 type)
 {
-	struct sock *sk = (struct sock *)timeout_data;
 	struct sk_buff *skb = alloc_skb(0, GFP_ATOMIC);
 
 	bh_lock_sock(sk);
@@ -1334,24 +1333,32 @@ static void llc_conn_tmr_common_cb(unsigned long timeout_data, u8 type)
 	bh_unlock_sock(sk);
 }
 
-void llc_conn_pf_cycle_tmr_cb(unsigned long timeout_data)
+void llc_conn_pf_cycle_tmr_cb(struct timer_list *t)
 {
-	llc_conn_tmr_common_cb(timeout_data, LLC_CONN_EV_TYPE_P_TMR);
+	struct llc_sock *llc = from_timer(llc, t, pf_cycle_timer.timer);
+
+	llc_conn_tmr_common_cb(&llc->sk, LLC_CONN_EV_TYPE_P_TMR);
 }
 
-void llc_conn_busy_tmr_cb(unsigned long timeout_data)
+void llc_conn_busy_tmr_cb(struct timer_list *t)
 {
-	llc_conn_tmr_common_cb(timeout_data, LLC_CONN_EV_TYPE_BUSY_TMR);
+	struct llc_sock *llc = from_timer(llc, t, busy_state_timer.timer);
+
+	llc_conn_tmr_common_cb(&llc->sk, LLC_CONN_EV_TYPE_BUSY_TMR);
 }
 
-void llc_conn_ack_tmr_cb(unsigned long timeout_data)
+void llc_conn_ack_tmr_cb(struct timer_list *t)
 {
-	llc_conn_tmr_common_cb(timeout_data, LLC_CONN_EV_TYPE_ACK_TMR);
+	struct llc_sock *llc = from_timer(llc, t, ack_timer.timer);
+
+	llc_conn_tmr_common_cb(&llc->sk, LLC_CONN_EV_TYPE_ACK_TMR);
 }
 
-void llc_conn_rej_tmr_cb(unsigned long timeout_data)
+void llc_conn_rej_tmr_cb(struct timer_list *t)
 {
-	llc_conn_tmr_common_cb(timeout_data, LLC_CONN_EV_TYPE_REJ_TMR);
+	struct llc_sock *llc = from_timer(llc, t, rej_sent_timer.timer);
+
+	llc_conn_tmr_common_cb(&llc->sk, LLC_CONN_EV_TYPE_REJ_TMR);
 }
 
 int llc_conn_ac_rst_vs(struct sock *sk, struct sk_buff *skb)
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 5e91b47f0d2a..9177dbb16dce 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -902,20 +902,16 @@ static void llc_sk_init(struct sock *sk)
 	llc->inc_cntr = llc->dec_cntr = 2;
 	llc->dec_step = llc->connect_step = 1;
 
-	setup_timer(&llc->ack_timer.timer, llc_conn_ack_tmr_cb,
-			(unsigned long)sk);
+	timer_setup(&llc->ack_timer.timer, llc_conn_ack_tmr_cb, 0);
 	llc->ack_timer.expire	      = sysctl_llc2_ack_timeout;
 
-	setup_timer(&llc->pf_cycle_timer.timer, llc_conn_pf_cycle_tmr_cb,
-			(unsigned long)sk);
+	timer_setup(&llc->pf_cycle_timer.timer, llc_conn_pf_cycle_tmr_cb, 0);
 	llc->pf_cycle_timer.expire	   = sysctl_llc2_p_timeout;
 
-	setup_timer(&llc->rej_sent_timer.timer, llc_conn_rej_tmr_cb,
-			(unsigned long)sk);
+	timer_setup(&llc->rej_sent_timer.timer, llc_conn_rej_tmr_cb, 0);
 	llc->rej_sent_timer.expire	   = sysctl_llc2_rej_timeout;
 
-	setup_timer(&llc->busy_state_timer.timer, llc_conn_busy_tmr_cb,
-			(unsigned long)sk);
+	timer_setup(&llc->busy_state_timer.timer, llc_conn_busy_tmr_cb, 0);
 	llc->busy_state_timer.expire	     = sysctl_llc2_busy_timeout;
 
 	llc->n2 = 2;   /* max retransmit */
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index 80bfe29099f6..e3589ade62e0 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -7,6 +7,7 @@ mac80211-y := \
 	driver-ops.o \
 	sta_info.o \
 	wep.o \
+	aead_api.o \
 	wpa.o \
 	scan.o offchannel.o \
 	ht.o agg-tx.o agg-rx.o \
@@ -16,8 +17,6 @@ mac80211-y := \
 	rate.o \
 	michael.o \
 	tkip.o \
-	aes_ccm.o \
-	aes_gcm.o \
 	aes_cmac.o \
 	aes_gmac.o \
 	fils_aead.o \
diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aead_api.c
index a4e0d59a40dd..160f9df30402 100644
--- a/net/mac80211/aes_ccm.c
+++ b/net/mac80211/aead_api.c
@@ -1,6 +1,7 @@
 /*
  * Copyright 2003-2004, Instant802 Networks, Inc.
  * Copyright 2005-2006, Devicescape Software, Inc.
+ * Copyright 2014-2015, Qualcomm Atheros, Inc.
  *
  * Rewrite: Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
  *
@@ -12,30 +13,29 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/err.h>
+#include <linux/scatterlist.h>
 #include <crypto/aead.h>
 
-#include <net/mac80211.h>
-#include "key.h"
-#include "aes_ccm.h"
+#include "aead_api.h"
 
-int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
-			      u8 *data, size_t data_len, u8 *mic,
-			      size_t mic_len)
+int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len,
+		 u8 *data, size_t data_len, u8 *mic)
 {
+	size_t mic_len = crypto_aead_authsize(tfm);
 	struct scatterlist sg[3];
 	struct aead_request *aead_req;
 	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
 	u8 *__aad;
 
-	aead_req = kzalloc(reqsize + CCM_AAD_LEN, GFP_ATOMIC);
+	aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC);
 	if (!aead_req)
 		return -ENOMEM;
 
 	__aad = (u8 *)aead_req + reqsize;
-	memcpy(__aad, aad, CCM_AAD_LEN);
+	memcpy(__aad, aad, aad_len);
 
 	sg_init_table(sg, 3);
-	sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad));
+	sg_set_buf(&sg[0], __aad, aad_len);
 	sg_set_buf(&sg[1], data, data_len);
 	sg_set_buf(&sg[2], mic, mic_len);
 
@@ -49,10 +49,10 @@ int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 	return 0;
 }
 
-int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
-			      u8 *data, size_t data_len, u8 *mic,
-			      size_t mic_len)
+int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len,
+		 u8 *data, size_t data_len, u8 *mic)
 {
+	size_t mic_len = crypto_aead_authsize(tfm);
 	struct scatterlist sg[3];
 	struct aead_request *aead_req;
 	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
@@ -62,15 +62,15 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 	if (data_len == 0)
 		return -EINVAL;
 
-	aead_req = kzalloc(reqsize + CCM_AAD_LEN, GFP_ATOMIC);
+	aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC);
 	if (!aead_req)
 		return -ENOMEM;
 
 	__aad = (u8 *)aead_req + reqsize;
-	memcpy(__aad, aad, CCM_AAD_LEN);
+	memcpy(__aad, aad, aad_len);
 
 	sg_init_table(sg, 3);
-	sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad));
+	sg_set_buf(&sg[0], __aad, aad_len);
 	sg_set_buf(&sg[1], data, data_len);
 	sg_set_buf(&sg[2], mic, mic_len);
 
@@ -84,14 +84,14 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 	return err;
 }
 
-struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[],
-						    size_t key_len,
-						    size_t mic_len)
+struct crypto_aead *
+aead_key_setup_encrypt(const char *alg, const u8 key[],
+		       size_t key_len, size_t mic_len)
 {
 	struct crypto_aead *tfm;
 	int err;
 
-	tfm = crypto_alloc_aead("ccm(aes)", 0, CRYPTO_ALG_ASYNC);
+	tfm = crypto_alloc_aead(alg, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm))
 		return tfm;
 
@@ -109,7 +109,7 @@ free_aead:
 	return ERR_PTR(err);
 }
 
-void ieee80211_aes_key_free(struct crypto_aead *tfm)
+void aead_key_free(struct crypto_aead *tfm)
 {
 	crypto_free_aead(tfm);
 }
diff --git a/net/mac80211/aead_api.h b/net/mac80211/aead_api.h
new file mode 100644
index 000000000000..5e39ea843bbf
--- /dev/null
+++ b/net/mac80211/aead_api.h
@@ -0,0 +1,27 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _AEAD_API_H
+#define _AEAD_API_H
+
+#include <crypto/aead.h>
+#include <linux/crypto.h>
+
+struct crypto_aead *
+aead_key_setup_encrypt(const char *alg, const u8 key[],
+		       size_t key_len, size_t mic_len);
+
+int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
+		 size_t aad_len, u8 *data,
+		 size_t data_len, u8 *mic);
+
+int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
+		 size_t aad_len, u8 *data,
+		 size_t data_len, u8 *mic);
+
+void aead_key_free(struct crypto_aead *tfm);
+
+#endif /* _AEAD_API_H */
diff --git a/net/mac80211/aes_ccm.h b/net/mac80211/aes_ccm.h
index fcd3254c5cf0..e9b7ca0bde5b 100644
--- a/net/mac80211/aes_ccm.h
+++ b/net/mac80211/aes_ccm.h
@@ -10,19 +10,39 @@
 #ifndef AES_CCM_H
 #define AES_CCM_H
 
-#include <linux/crypto.h>
+#include "aead_api.h"
 
 #define CCM_AAD_LEN	32
 
-struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[],
-						    size_t key_len,
-						    size_t mic_len);
-int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
-			      u8 *data, size_t data_len, u8 *mic,
-			      size_t mic_len);
-int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
-			      u8 *data, size_t data_len, u8 *mic,
-			      size_t mic_len);
-void ieee80211_aes_key_free(struct crypto_aead *tfm);
+static inline struct crypto_aead *
+ieee80211_aes_key_setup_encrypt(const u8 key[], size_t key_len, size_t mic_len)
+{
+	return aead_key_setup_encrypt("ccm(aes)", key, key_len, mic_len);
+}
+
+static inline int
+ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm,
+			  u8 *b_0, u8 *aad, u8 *data,
+			  size_t data_len, u8 *mic)
+{
+	return aead_encrypt(tfm, b_0, aad + 2,
+			    be16_to_cpup((__be16 *)aad),
+			    data, data_len, mic);
+}
+
+static inline int
+ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm,
+			  u8 *b_0, u8 *aad, u8 *data,
+			  size_t data_len, u8 *mic)
+{
+	return aead_decrypt(tfm, b_0, aad + 2,
+			    be16_to_cpup((__be16 *)aad),
+			    data, data_len, mic);
+}
+
+static inline void ieee80211_aes_key_free(struct crypto_aead *tfm)
+{
+	return aead_key_free(tfm);
+}
 
 #endif /* AES_CCM_H */
diff --git a/net/mac80211/aes_gcm.c b/net/mac80211/aes_gcm.c
deleted file mode 100644
index 8a4397cc1b08..000000000000
--- a/net/mac80211/aes_gcm.c
+++ /dev/null
@@ -1,109 +0,0 @@
-/*
- * Copyright 2014-2015, Qualcomm Atheros, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/err.h>
-#include <crypto/aead.h>
-
-#include <net/mac80211.h>
-#include "key.h"
-#include "aes_gcm.h"
-
-int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
-			      u8 *data, size_t data_len, u8 *mic)
-{
-	struct scatterlist sg[3];
-	struct aead_request *aead_req;
-	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
-	u8 *__aad;
-
-	aead_req = kzalloc(reqsize + GCM_AAD_LEN, GFP_ATOMIC);
-	if (!aead_req)
-		return -ENOMEM;
-
-	__aad = (u8 *)aead_req + reqsize;
-	memcpy(__aad, aad, GCM_AAD_LEN);
-
-	sg_init_table(sg, 3);
-	sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad));
-	sg_set_buf(&sg[1], data, data_len);
-	sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN);
-
-	aead_request_set_tfm(aead_req, tfm);
-	aead_request_set_crypt(aead_req, sg, sg, data_len, j_0);
-	aead_request_set_ad(aead_req, sg[0].length);
-
-	crypto_aead_encrypt(aead_req);
-	kzfree(aead_req);
-	return 0;
-}
-
-int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
-			      u8 *data, size_t data_len, u8 *mic)
-{
-	struct scatterlist sg[3];
-	struct aead_request *aead_req;
-	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
-	u8 *__aad;
-	int err;
-
-	if (data_len == 0)
-		return -EINVAL;
-
-	aead_req = kzalloc(reqsize + GCM_AAD_LEN, GFP_ATOMIC);
-	if (!aead_req)
-		return -ENOMEM;
-
-	__aad = (u8 *)aead_req + reqsize;
-	memcpy(__aad, aad, GCM_AAD_LEN);
-
-	sg_init_table(sg, 3);
-	sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad));
-	sg_set_buf(&sg[1], data, data_len);
-	sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN);
-
-	aead_request_set_tfm(aead_req, tfm);
-	aead_request_set_crypt(aead_req, sg, sg,
-			       data_len + IEEE80211_GCMP_MIC_LEN, j_0);
-	aead_request_set_ad(aead_req, sg[0].length);
-
-	err = crypto_aead_decrypt(aead_req);
-	kzfree(aead_req);
-
-	return err;
-}
-
-struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[],
-							size_t key_len)
-{
-	struct crypto_aead *tfm;
-	int err;
-
-	tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(tfm))
-		return tfm;
-
-	err = crypto_aead_setkey(tfm, key, key_len);
-	if (err)
-		goto free_aead;
-	err = crypto_aead_setauthsize(tfm, IEEE80211_GCMP_MIC_LEN);
-	if (err)
-		goto free_aead;
-
-	return tfm;
-
-free_aead:
-	crypto_free_aead(tfm);
-	return ERR_PTR(err);
-}
-
-void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm)
-{
-	crypto_free_aead(tfm);
-}
diff --git a/net/mac80211/aes_gcm.h b/net/mac80211/aes_gcm.h
index 55aed5352494..d2b096033009 100644
--- a/net/mac80211/aes_gcm.h
+++ b/net/mac80211/aes_gcm.h
@@ -9,16 +9,38 @@
 #ifndef AES_GCM_H
 #define AES_GCM_H
 
-#include <linux/crypto.h>
+#include "aead_api.h"
 
 #define GCM_AAD_LEN	32
 
-int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
-			      u8 *data, size_t data_len, u8 *mic);
-int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
-			      u8 *data, size_t data_len, u8 *mic);
-struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[],
-							size_t key_len);
-void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm);
+static inline int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm,
+					    u8 *j_0, u8 *aad,  u8 *data,
+					    size_t data_len, u8 *mic)
+{
+	return aead_encrypt(tfm, j_0, aad + 2,
+			    be16_to_cpup((__be16 *)aad),
+			    data, data_len, mic);
+}
+
+static inline int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm,
+					    u8 *j_0, u8 *aad, u8 *data,
+					    size_t data_len, u8 *mic)
+{
+	return aead_decrypt(tfm, j_0, aad + 2,
+			    be16_to_cpup((__be16 *)aad),
+			    data, data_len, mic);
+}
+
+static inline struct crypto_aead *
+ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], size_t key_len)
+{
+	return aead_key_setup_encrypt("gcm(aes)", key,
+				      key_len, IEEE80211_GCMP_MIC_LEN);
+}
+
+static inline void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm)
+{
+	return aead_key_free(tfm);
+}
 
 #endif /* AES_GCM_H */
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 2849a1fc41c5..88cc1ae935ea 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -459,7 +459,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local,
 }
 
 void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif,
-				 const u8 *addr, unsigned int bit)
+				 const u8 *addr, unsigned int tid)
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct ieee80211_local *local = sdata->local;
@@ -470,7 +470,7 @@ void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif,
 	if (!sta)
 		goto unlock;
 
-	set_bit(bit, sta->ampdu_mlme.tid_rx_manage_offl);
+	set_bit(tid, sta->ampdu_mlme.tid_rx_manage_offl);
 	ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work);
  unlock:
 	rcu_read_unlock();
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index d6d0b4201e40..41f5e48f8021 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -290,13 +290,15 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta,
 {
 	int i;
 
+	mutex_lock(&sta->ampdu_mlme.mtx);
 	for (i = 0; i <  IEEE80211_NUM_TIDS; i++) {
-		__ieee80211_stop_tx_ba_session(sta, i, reason);
-		__ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT,
-					       WLAN_REASON_QSTA_LEAVE_QBSS,
-					       reason != AGG_STOP_DESTROY_STA &&
-					       reason != AGG_STOP_PEER_REQUEST);
+		___ieee80211_stop_tx_ba_session(sta, i, reason);
+		___ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT,
+						WLAN_REASON_QSTA_LEAVE_QBSS,
+						reason != AGG_STOP_DESTROY_STA &&
+						reason != AGG_STOP_PEER_REQUEST);
 	}
+	mutex_unlock(&sta->ampdu_mlme.mtx);
 
 	/* stopping might queue the work again - so cancel only afterwards */
 	cancel_work_sync(&sta->ampdu_mlme.work);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 9675814f64db..68f874e73561 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2009,6 +2009,8 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata,
 			struct txq_info *txq, int tid);
 void ieee80211_txq_purge(struct ieee80211_local *local,
 			 struct txq_info *txqi);
+void ieee80211_txq_remove_vlan(struct ieee80211_local *local,
+			       struct ieee80211_sub_if_data *sdata);
 void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
 			 u16 transaction, u16 auth_alg, u16 status,
 			 const u8 *extra, size_t extra_len, const u8 *bssid,
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index f75029abf728..13b16f90e1cf 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -793,9 +793,7 @@ static int ieee80211_open(struct net_device *dev)
 static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 			      bool going_down)
 {
-	struct ieee80211_sub_if_data *txq_sdata = sdata;
 	struct ieee80211_local *local = sdata->local;
-	struct fq *fq = &local->fq;
 	unsigned long flags;
 	struct sk_buff *skb, *tmp;
 	u32 hw_reconf_flags = 0;
@@ -939,9 +937,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP_VLAN:
-		txq_sdata = container_of(sdata->bss,
-					 struct ieee80211_sub_if_data, u.ap);
-
 		mutex_lock(&local->mtx);
 		list_del(&sdata->u.vlan.list);
 		mutex_unlock(&local->mtx);
@@ -998,8 +993,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 		skb_queue_purge(&sdata->skb_queue);
 	}
 
-	sdata->bss = NULL;
-
 	spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
 	for (i = 0; i < IEEE80211_MAX_QUEUES; i++) {
 		skb_queue_walk_safe(&local->pending[i], skb, tmp) {
@@ -1012,22 +1005,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	}
 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 
-	if (txq_sdata->vif.txq) {
-		struct txq_info *txqi = to_txq_info(txq_sdata->vif.txq);
-
-		/*
-		 * FIXME FIXME
-		 *
-		 * We really shouldn't purge the *entire* txqi since that
-		 * contains frames for the other AP_VLANs (and possibly
-		 * the AP itself) as well, but there's no API in FQ now
-		 * to be able to filter.
-		 */
+	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+		ieee80211_txq_remove_vlan(local, sdata);
 
-		spin_lock_bh(&fq->lock);
-		ieee80211_txq_purge(local, txqi);
-		spin_unlock_bh(&fq->lock);
-	}
+	sdata->bss = NULL;
 
 	if (local->open_count == 0)
 		ieee80211_clear_tx_pending(local);
@@ -1772,7 +1753,9 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 				 sizeof(void *));
 		int txq_size = 0;
 
-		if (local->ops->wake_tx_queue)
+		if (local->ops->wake_tx_queue &&
+		    type != NL80211_IFTYPE_AP_VLAN &&
+		    type != NL80211_IFTYPE_MONITOR)
 			txq_size += sizeof(struct txq_info) +
 				    local->hw.txq_data_size;
 
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index a550c707cd8a..7a76c4a6df30 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -675,8 +675,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
 	enum nl80211_band band;
 	u8 *pos;
 	struct ieee80211_sub_if_data *sdata;
-	int hdr_len = offsetof(struct ieee80211_mgmt, u.beacon) +
-		      sizeof(mgmt->u.beacon);
+	int hdr_len = offsetofend(struct ieee80211_mgmt, u.beacon);
 
 	sdata = container_of(ifmsh, struct ieee80211_sub_if_data, u.mesh);
 	rcu_read_lock();
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index 7e5f271e3c30..465b7853edc0 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -275,6 +275,7 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata,
 			   u8 *hw_addr, struct ieee802_11_elems *ie);
 bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie);
 u32 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata);
+void mesh_plink_timer(struct timer_list *t);
 void mesh_plink_broken(struct sta_info *sta);
 u32 mesh_plink_deactivate(struct sta_info *sta);
 u32 mesh_plink_open(struct sta_info *sta);
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index d8bbd0d2225a..146ec6c0f12f 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -111,8 +111,8 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags,
 	struct sk_buff *skb;
 	struct ieee80211_mgmt *mgmt;
 	u8 *pos, ie_len;
-	int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.mesh_action) +
-		      sizeof(mgmt->u.action.u.mesh_action);
+	int hdr_len = offsetofend(struct ieee80211_mgmt,
+				  u.action.u.mesh_action);
 
 	skb = dev_alloc_skb(local->tx_headroom +
 			    hdr_len +
@@ -242,8 +242,8 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
 	struct ieee80211_mgmt *mgmt;
 	u8 *pos, ie_len;
-	int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.mesh_action) +
-		      sizeof(mgmt->u.action.u.mesh_action);
+	int hdr_len = offsetofend(struct ieee80211_mgmt,
+				  u.action.u.mesh_action);
 
 	if (time_before(jiffies, ifmsh->next_perr))
 		return -EAGAIN;
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index f69c6c38ca43..e2d00cce3c17 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -220,8 +220,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata,
 	bool include_plid = false;
 	u16 peering_proto = 0;
 	u8 *pos, ie_len = 4;
-	int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.self_prot) +
-		      sizeof(mgmt->u.action.u.self_prot);
+	int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.self_prot);
 	int err = -ENOMEM;
 
 	skb = dev_alloc_skb(local->tx_headroom +
@@ -604,8 +603,9 @@ out:
 	ieee80211_mbss_info_change_notify(sdata, changed);
 }
 
-static void mesh_plink_timer(unsigned long data)
+void mesh_plink_timer(struct timer_list *t)
 {
+	struct mesh_sta *mesh = from_timer(mesh, t, plink_timer);
 	struct sta_info *sta;
 	u16 reason = 0;
 	struct ieee80211_sub_if_data *sdata;
@@ -617,7 +617,7 @@ static void mesh_plink_timer(unsigned long data)
 	 * del_timer_sync() this timer after having made sure
 	 * it cannot be readded (by deleting the plink.)
 	 */
-	sta = (struct sta_info *) data;
+	sta = mesh->plink_sta;
 
 	if (sta->sdata->local->quiescing)
 		return;
@@ -697,11 +697,8 @@ static void mesh_plink_timer(unsigned long data)
 
 static inline void mesh_plink_timer_set(struct sta_info *sta, u32 timeout)
 {
-	sta->mesh->plink_timer.expires = jiffies + msecs_to_jiffies(timeout);
-	sta->mesh->plink_timer.data = (unsigned long) sta;
-	sta->mesh->plink_timer.function = mesh_plink_timer;
 	sta->mesh->plink_timeout = timeout;
-	add_timer(&sta->mesh->plink_timer);
+	mod_timer(&sta->mesh->plink_timer, jiffies + msecs_to_jiffies(timeout));
 }
 
 static bool llid_in_use(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 3b8e2709d8de..e4ededa1909d 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -145,7 +145,6 @@ static u32
 ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 			     struct ieee80211_supported_band *sband,
 			     struct ieee80211_channel *channel,
-			     const struct ieee80211_ht_cap *ht_cap,
 			     const struct ieee80211_ht_operation *ht_oper,
 			     const struct ieee80211_vht_operation *vht_oper,
 			     struct cfg80211_chan_def *chandef, bool tracking)
@@ -163,20 +162,13 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 	chandef->center_freq1 = channel->center_freq;
 	chandef->center_freq2 = 0;
 
-	if (!ht_cap || !ht_oper || !sta_ht_cap.ht_supported) {
+	if (!ht_oper || !sta_ht_cap.ht_supported) {
 		ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT;
 		goto out;
 	}
 
 	chandef->width = NL80211_CHAN_WIDTH_20;
 
-	if (!(ht_cap->cap_info &
-	      cpu_to_le16(IEEE80211_HT_CAP_SUP_WIDTH_20_40))) {
-		ret = IEEE80211_STA_DISABLE_40MHZ;
-		vht_chandef = *chandef;
-		goto out;
-	}
-
 	ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan,
 						  channel->band);
 	/* check that channel matches the right operating channel */
@@ -344,7 +336,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata,
 
 	/* calculate new channel (type) based on HT/VHT operation IEs */
 	flags = ieee80211_determine_chantype(sdata, sband, chan,
-					     ht_cap, ht_oper, vht_oper,
+					     ht_oper, vht_oper,
 					     &chandef, true);
 
 	/*
@@ -780,11 +772,12 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 			WLAN_EID_SUPPORTED_REGULATORY_CLASSES,
 			WLAN_EID_HT_CAPABILITY,
 			WLAN_EID_BSS_COEX_2040,
+			/* luckily this is almost always there */
 			WLAN_EID_EXT_CAPABILITY,
 			WLAN_EID_QOS_TRAFFIC_CAPA,
 			WLAN_EID_TIM_BCAST_REQ,
 			WLAN_EID_INTERWORKING,
-			/* 60GHz doesn't happen right now */
+			/* 60 GHz (Multi-band, DMG, MMS) can't happen */
 			WLAN_EID_VHT_CAPABILITY,
 			WLAN_EID_OPMODE_NOTIF,
 		};
@@ -811,22 +804,16 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	/* if present, add any custom IEs that go before VHT */
 	if (assoc_data->ie_len) {
 		static const u8 before_vht[] = {
-			WLAN_EID_SSID,
-			WLAN_EID_SUPP_RATES,
-			WLAN_EID_EXT_SUPP_RATES,
-			WLAN_EID_PWR_CAPABILITY,
-			WLAN_EID_SUPPORTED_CHANNELS,
-			WLAN_EID_RSN,
-			WLAN_EID_QOS_CAPA,
-			WLAN_EID_RRM_ENABLED_CAPABILITIES,
-			WLAN_EID_MOBILITY_DOMAIN,
-			WLAN_EID_SUPPORTED_REGULATORY_CLASSES,
-			WLAN_EID_HT_CAPABILITY,
+			/*
+			 * no need to list the ones split off before HT
+			 * or generated here
+			 */
 			WLAN_EID_BSS_COEX_2040,
 			WLAN_EID_EXT_CAPABILITY,
 			WLAN_EID_QOS_TRAFFIC_CAPA,
 			WLAN_EID_TIM_BCAST_REQ,
 			WLAN_EID_INTERWORKING,
+			/* 60 GHz (Multi-band, DMG, MMS) can't happen */
 		};
 
 		/* RIC already taken above, so no need to handle here anymore */
@@ -4317,7 +4304,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 
 	ifmgd->flags |= ieee80211_determine_chantype(sdata, sband,
 						     cbss->channel,
-						     ht_cap, ht_oper, vht_oper,
+						     ht_oper, vht_oper,
 						     &chandef, false);
 
 	sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss),
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 47d2ed570470..ef2becaade50 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -7,7 +7,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
- * Copyright 2016  Intel Deutschland GmbH
+ * Copyright 2016-2017  Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -183,6 +183,20 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
 	return bss;
 }
 
+static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata,
+					u32 scan_flags, const u8 *da)
+{
+	if (!sdata)
+		return false;
+	/* accept broadcast for OCE */
+	if (scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP &&
+	    is_broadcast_ether_addr(da))
+		return true;
+	if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR)
+		return true;
+	return ether_addr_equal(da, sdata->vif.addr);
+}
+
 void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 {
 	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
@@ -208,19 +222,24 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 	if (ieee80211_is_probe_resp(mgmt->frame_control)) {
 		struct cfg80211_scan_request *scan_req;
 		struct cfg80211_sched_scan_request *sched_scan_req;
+		u32 scan_req_flags = 0, sched_scan_req_flags = 0;
 
 		scan_req = rcu_dereference(local->scan_req);
 		sched_scan_req = rcu_dereference(local->sched_scan_req);
 
-		/* ignore ProbeResp to foreign address unless scanning
-		 * with randomised address
+		if (scan_req)
+			scan_req_flags = scan_req->flags;
+
+		if (sched_scan_req)
+			sched_scan_req_flags = sched_scan_req->flags;
+
+		/* ignore ProbeResp to foreign address or non-bcast (OCE)
+		 * unless scanning with randomised address
 		 */
-		if (!(sdata1 &&
-		      (ether_addr_equal(mgmt->da, sdata1->vif.addr) ||
-		       scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)) &&
-		    !(sdata2 &&
-		      (ether_addr_equal(mgmt->da, sdata2->vif.addr) ||
-		       sched_scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)))
+		if (!ieee80211_scan_accept_presp(sdata1, scan_req_flags,
+						 mgmt->da) &&
+		    !ieee80211_scan_accept_presp(sdata2, sched_scan_req_flags,
+						 mgmt->da))
 			return;
 
 		elements = mgmt->u.probe_resp.variable;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 69615016d5bf..9673e157bf8f 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -329,10 +329,12 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 		sta->mesh = kzalloc(sizeof(*sta->mesh), gfp);
 		if (!sta->mesh)
 			goto free;
+		sta->mesh->plink_sta = sta;
 		spin_lock_init(&sta->mesh->plink_lock);
 		if (ieee80211_vif_is_mesh(&sdata->vif) &&
 		    !sdata->u.mesh.user_mpm)
-			init_timer(&sta->mesh->plink_timer);
+			timer_setup(&sta->mesh->plink_timer, mesh_plink_timer,
+				    0);
 		sta->mesh->nonpeer_pm = NL80211_MESH_POWER_ACTIVE;
 	}
 #endif
@@ -515,6 +517,31 @@ static int sta_info_insert_drv_state(struct ieee80211_local *local,
 	return err;
 }
 
+static void
+ieee80211_recalc_p2p_go_ps_allowed(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	bool allow_p2p_go_ps = sdata->vif.p2p;
+	struct sta_info *sta;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sta, &local->sta_list, list) {
+		if (sdata != sta->sdata ||
+		    !test_sta_flag(sta, WLAN_STA_ASSOC))
+			continue;
+		if (!sta->sta.support_p2p_ps) {
+			allow_p2p_go_ps = false;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	if (allow_p2p_go_ps != sdata->vif.bss_conf.allow_p2p_go_ps) {
+		sdata->vif.bss_conf.allow_p2p_go_ps = allow_p2p_go_ps;
+		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_P2P_PS);
+	}
+}
+
 /*
  * should be called with sta_mtx locked
  * this function replaces the mutex lock
@@ -561,6 +588,13 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 		goto out_remove;
 
 	set_sta_flag(sta, WLAN_STA_INSERTED);
+
+	if (sta->sta_state >= IEEE80211_STA_ASSOC) {
+		ieee80211_recalc_min_chandef(sta->sdata);
+		if (!sta->sta.support_p2p_ps)
+			ieee80211_recalc_p2p_go_ps_allowed(sta->sdata);
+	}
+
 	/* accept BA sessions now */
 	clear_sta_flag(sta, WLAN_STA_BLOCK_BA);
 
@@ -1788,31 +1822,6 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta,
 }
 EXPORT_SYMBOL(ieee80211_sta_set_buffered);
 
-static void
-ieee80211_recalc_p2p_go_ps_allowed(struct ieee80211_sub_if_data *sdata)
-{
-	struct ieee80211_local *local = sdata->local;
-	bool allow_p2p_go_ps = sdata->vif.p2p;
-	struct sta_info *sta;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(sta, &local->sta_list, list) {
-		if (sdata != sta->sdata ||
-		    !test_sta_flag(sta, WLAN_STA_ASSOC))
-			continue;
-		if (!sta->sta.support_p2p_ps) {
-			allow_p2p_go_ps = false;
-			break;
-		}
-	}
-	rcu_read_unlock();
-
-	if (allow_p2p_go_ps != sdata->vif.bss_conf.allow_p2p_go_ps) {
-		sdata->vif.bss_conf.allow_p2p_go_ps = allow_p2p_go_ps;
-		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_P2P_PS);
-	}
-}
-
 int sta_info_move_state(struct sta_info *sta,
 			enum ieee80211_sta_state new_state)
 {
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 3acbdfa9f649..5c54acd10562 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -344,6 +344,7 @@ DECLARE_EWMA(mesh_fail_avg, 20, 8)
  * @plink_state: peer link state
  * @plink_timeout: timeout of peer link
  * @plink_timer: peer link watch timer
+ * @plink_sta: peer link watch timer's sta_info
  * @t_offset: timing offset relative to this host
  * @t_offset_setpoint: reference timing offset of this sta to be used when
  * 	calculating clockdrift
@@ -356,6 +357,7 @@ DECLARE_EWMA(mesh_fail_avg, 20, 8)
  */
 struct mesh_sta {
 	struct timer_list plink_timer;
+	struct sta_info *plink_sta;
 
 	s64 t_offset;
 	s64 t_offset_setpoint;
@@ -398,7 +400,7 @@ struct ieee80211_sta_rx_stats {
 	u64 msdu[IEEE80211_NUM_TIDS + 1];
 };
 
-/**
+/*
  * The bandwidth threshold below which the per-station CoDel parameters will be
  * scaled to be more lenient (to prevent starvation of slow stations). This
  * value will be scaled by the number of active stations when it is being
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 94826680cf2b..7b8154474b9e 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1396,6 +1396,40 @@ static void ieee80211_txq_enqueue(struct ieee80211_local *local,
 		       fq_flow_get_default_func);
 }
 
+static bool fq_vlan_filter_func(struct fq *fq, struct fq_tin *tin,
+				struct fq_flow *flow, struct sk_buff *skb,
+				void *data)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+	return info->control.vif == data;
+}
+
+void ieee80211_txq_remove_vlan(struct ieee80211_local *local,
+			       struct ieee80211_sub_if_data *sdata)
+{
+	struct fq *fq = &local->fq;
+	struct txq_info *txqi;
+	struct fq_tin *tin;
+	struct ieee80211_sub_if_data *ap;
+
+	if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_AP_VLAN))
+		return;
+
+	ap = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap);
+
+	if (!ap->vif.txq)
+		return;
+
+	txqi = to_txq_info(ap->vif.txq);
+	tin = &txqi->tin;
+
+	spin_lock_bh(&fq->lock);
+	fq_tin_filter(fq, tin, fq_vlan_filter_func, &sdata->vif,
+		      fq_skb_free_func);
+	spin_unlock_bh(&fq->lock);
+}
+
 void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata,
 			struct sta_info *sta,
 			struct txq_info *txqi, int tid)
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 6aef6793d052..d57e5f6bd8b6 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1392,10 +1392,10 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local,
 	/* insert custom IEs that go before HT */
 	if (ie && ie_len) {
 		static const u8 before_ht[] = {
-			WLAN_EID_SSID,
-			WLAN_EID_SUPP_RATES,
-			WLAN_EID_REQUEST,
-			WLAN_EID_EXT_SUPP_RATES,
+			/*
+			 * no need to list the ones split off already
+			 * (or generated here)
+			 */
 			WLAN_EID_DS_PARAMS,
 			WLAN_EID_SUPPORTED_REGULATORY_CLASSES,
 		};
@@ -1424,20 +1424,17 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local,
 	/* insert custom IEs that go before VHT */
 	if (ie && ie_len) {
 		static const u8 before_vht[] = {
-			WLAN_EID_SSID,
-			WLAN_EID_SUPP_RATES,
-			WLAN_EID_REQUEST,
-			WLAN_EID_EXT_SUPP_RATES,
-			WLAN_EID_DS_PARAMS,
-			WLAN_EID_SUPPORTED_REGULATORY_CLASSES,
-			WLAN_EID_HT_CAPABILITY,
+			/*
+			 * no need to list the ones split off already
+			 * (or generated here)
+			 */
 			WLAN_EID_BSS_COEX_2040,
 			WLAN_EID_EXT_CAPABILITY,
 			WLAN_EID_SSID_LIST,
 			WLAN_EID_CHANNEL_USAGE,
 			WLAN_EID_INTERWORKING,
 			WLAN_EID_MESH_ID,
-			/* 60 GHz can't happen here right now */
+			/* 60 GHz (Multi-band, DMG, MMS) can't happen */
 		};
 		noffset = ieee80211_ie_split(ie, ie_len,
 					     before_vht, ARRAY_SIZE(before_vht),
@@ -2980,8 +2977,8 @@ int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_mgmt *mgmt;
 	struct ieee80211_local *local = sdata->local;
 	int freq;
-	int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.chan_switch) +
-			       sizeof(mgmt->u.action.u.chan_switch);
+	int hdr_len = offsetofend(struct ieee80211_mgmt,
+				  u.action.u.chan_switch);
 	u8 *pos;
 
 	if (sdata->vif.type != NL80211_IFTYPE_ADHOC &&
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index 19ec2189d3ac..b9276ac849fa 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -386,6 +386,16 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta)
 
 	bw = ieee80211_sta_cap_rx_bw(sta);
 	bw = min(bw, sta->cur_max_bandwidth);
+
+	/* Don't consider AP's bandwidth for TDLS peers, section 11.23.1 of
+	 * IEEE80211-2016 specification makes higher bandwidth operation
+	 * possible on the TDLS link if the peers have wider bandwidth
+	 * capability.
+	 */
+	if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) &&
+	    test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW))
+		return bw;
+
 	bw = min(bw, ieee80211_chan_width_to_rx_bw(bss_width));
 
 	return bw;
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index 0d722ea98a1b..b58722d9de37 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -464,7 +464,7 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb,
 	pos += IEEE80211_CCMP_HDR_LEN;
 	ccmp_special_blocks(skb, pn, b_0, aad);
 	return ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len,
-					 skb_put(skb, mic_len), mic_len);
+					 skb_put(skb, mic_len));
 }
 
 
@@ -543,7 +543,7 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx,
 				    key->u.ccmp.tfm, b_0, aad,
 				    skb->data + hdrlen + IEEE80211_CCMP_HDR_LEN,
 				    data_len,
-				    skb->data + skb->len - mic_len, mic_len))
+				    skb->data + skb->len - mic_len))
 				return RX_DROP_UNUSABLE;
 		}
 
diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
index 1e1c9b20bab7..2fb703d70803 100644
--- a/net/mac802154/llsec.c
+++ b/net/mac802154/llsec.c
@@ -623,13 +623,18 @@ llsec_do_encrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 	u8 iv[16];
 	struct scatterlist src;
 	SKCIPHER_REQUEST_ON_STACK(req, key->tfm0);
-	int err;
+	int err, datalen;
+	unsigned char *data;
 
 	llsec_geniv(iv, sec->params.hwaddr, &hdr->sec);
-	sg_init_one(&src, skb->data, skb->len);
+	/* Compute data payload offset and data length */
+	data = skb_mac_header(skb) + skb->mac_len;
+	datalen = skb_tail_pointer(skb) - data;
+	sg_init_one(&src, data, datalen);
+
 	skcipher_request_set_tfm(req, key->tfm0);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
-	skcipher_request_set_crypt(req, &src, &src, skb->len, iv);
+	skcipher_request_set_crypt(req, &src, &src, datalen, iv);
 	err = crypto_skcipher_encrypt(req);
 	skcipher_request_zero(req);
 	return err;
@@ -713,7 +718,8 @@ int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb)
 	if (hlen < 0 || hdr.fc.type != IEEE802154_FC_TYPE_DATA)
 		return -EINVAL;
 
-	if (!hdr.fc.security_enabled || hdr.sec.level == 0) {
+	if (!hdr.fc.security_enabled ||
+	    (hdr.sec.level == IEEE802154_SCF_SECLEVEL_NONE)) {
 		skb_push(skb, hlen);
 		return 0;
 	}
diff --git a/net/mpls/Kconfig b/net/mpls/Kconfig
index 5c467ef97311..801ea9098387 100644
--- a/net/mpls/Kconfig
+++ b/net/mpls/Kconfig
@@ -24,6 +24,7 @@ config NET_MPLS_GSO
 
 config MPLS_ROUTING
 	tristate "MPLS: routing support"
+	depends on NET_IP_TUNNEL || NET_IP_TUNNEL=n
 	---help---
 	 Add support for forwarding of mpls packets.
 
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index c5b9ce41d66f..8ca9915befc8 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -16,6 +16,7 @@
 #include <net/arp.h>
 #include <net/ip_fib.h>
 #include <net/netevent.h>
+#include <net/ip_tunnels.h>
 #include <net/netns/generic.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -39,6 +40,36 @@ static int one = 1;
 static int label_limit = (1 << 20) - 1;
 static int ttl_max = 255;
 
+#if IS_ENABLED(CONFIG_NET_IP_TUNNEL)
+static size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e)
+{
+	return sizeof(struct mpls_shim_hdr);
+}
+
+static const struct ip_tunnel_encap_ops mpls_iptun_ops = {
+	.encap_hlen	= ipgre_mpls_encap_hlen,
+};
+
+static int ipgre_tunnel_encap_add_mpls_ops(void)
+{
+	return ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS);
+}
+
+static void ipgre_tunnel_encap_del_mpls_ops(void)
+{
+	ip_tunnel_encap_del_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS);
+}
+#else
+static int ipgre_tunnel_encap_add_mpls_ops(void)
+{
+	return 0;
+}
+
+static void ipgre_tunnel_encap_del_mpls_ops(void)
+{
+}
+#endif
+
 static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
 		       struct nlmsghdr *nlh, struct net *net, u32 portid,
 		       unsigned int nlm_flags);
@@ -2485,6 +2516,10 @@ static int __init mpls_init(void)
 		      0);
 	rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf,
 		      mpls_netconf_dump_devconf, 0);
+	err = ipgre_tunnel_encap_add_mpls_ops();
+	if (err)
+		pr_err("Can't add mpls over gre tunnel ops\n");
+
 	err = 0;
 out:
 	return err;
@@ -2502,6 +2537,7 @@ static void __exit mpls_exit(void)
 	dev_remove_pack(&mpls_packet_type);
 	unregister_netdevice_notifier(&mpls_dev_notifier);
 	unregister_pernet_subsys(&mpls_net_ops);
+	ipgre_tunnel_encap_del_mpls_ops();
 }
 module_exit(mpls_exit);
 
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 28c42b22b748..47baf914eec2 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -38,7 +38,7 @@ static inline int ncsi_filter_size(int table)
 	return sizes[table];
 }
 
-u32 *ncsi_get_filter(struct ncsi_channel *nc, int table, int index)
+static u32 *ncsi_get_filter(struct ncsi_channel *nc, int table, int index)
 {
 	struct ncsi_channel_filter *ncf;
 	int size;
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 8ad2b52a0b32..5ca18f07683b 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -37,11 +37,11 @@
 #define get_ext(set, map, id)	((map)->extensions + ((set)->dsize * (id)))
 
 static void
-mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
+mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t))
 {
 	struct mtype *map = set->data;
 
-	setup_timer(&map->gc, gc, (unsigned long)set);
+	timer_setup(&map->gc, gc, 0);
 	mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ);
 }
 
@@ -272,10 +272,10 @@ out:
 }
 
 static void
-mtype_gc(unsigned long ul_set)
+mtype_gc(struct timer_list *t)
 {
-	struct ip_set *set = (struct ip_set *)ul_set;
-	struct mtype *map = set->data;
+	struct mtype *map = from_timer(map, t, gc);
+	struct ip_set *set = map->set;
 	void *x;
 	u32 id;
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index 4783efff0bde..d8975a0b4282 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -48,6 +48,7 @@ struct bitmap_ip {
 	size_t memsize;		/* members size */
 	u8 netmask;		/* subnet netmask */
 	struct timer_list gc;	/* garbage collection */
+	struct ip_set *set;	/* attached to this ip_set */
 	unsigned char extensions[0]	/* data extensions */
 		__aligned(__alignof__(u64));
 };
@@ -232,6 +233,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
 	map->netmask = netmask;
 	set->timeout = IPSET_NO_TIMEOUT;
 
+	map->set = set;
 	set->data = map;
 	set->family = NFPROTO_IPV4;
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 9a065f672d3a..4c279fbd2d5d 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -52,6 +52,7 @@ struct bitmap_ipmac {
 	u32 elements;		/* number of max elements in the set */
 	size_t memsize;		/* members size */
 	struct timer_list gc;	/* garbage collector */
+	struct ip_set *set;	/* attached to this ip_set */
 	unsigned char extensions[0]	/* MAC + data extensions */
 		__aligned(__alignof__(u64));
 };
@@ -307,6 +308,7 @@ init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
 	map->elements = elements;
 	set->timeout = IPSET_NO_TIMEOUT;
 
+	map->set = set;
 	set->data = map;
 	set->family = NFPROTO_IPV4;
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 7f0c733358a4..7f9bbd7c98b5 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -40,6 +40,7 @@ struct bitmap_port {
 	u32 elements;		/* number of max elements in the set */
 	size_t memsize;		/* members size */
 	struct timer_list gc;	/* garbage collection */
+	struct ip_set *set;	/* attached to this ip_set */
 	unsigned char extensions[0]	/* data extensions */
 		__aligned(__alignof__(u64));
 };
@@ -214,6 +215,7 @@ init_map_port(struct ip_set *set, struct bitmap_port *map,
 	map->last_port = last_port;
 	set->timeout = IPSET_NO_TIMEOUT;
 
+	map->set = set;
 	set->data = map;
 	set->family = NFPROTO_UNSPEC;
 
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 51063d9ed0f7..efffc8eabafe 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -280,6 +280,7 @@ htable_bits(u32 hashsize)
 struct htype {
 	struct htable __rcu *table; /* the hash table */
 	struct timer_list gc;	/* garbage collection when timeout enabled */
+	struct ip_set *set;	/* attached to this ip_set */
 	u32 maxelem;		/* max elements in the hash */
 	u32 initval;		/* random jhash init value */
 #ifdef IP_SET_HASH_WITH_MARKMASK
@@ -429,11 +430,11 @@ mtype_destroy(struct ip_set *set)
 }
 
 static void
-mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
+mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t))
 {
 	struct htype *h = set->data;
 
-	setup_timer(&h->gc, gc, (unsigned long)set);
+	timer_setup(&h->gc, gc, 0);
 	mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ);
 	pr_debug("gc initialized, run in every %u\n",
 		 IPSET_GC_PERIOD(set->timeout));
@@ -526,10 +527,10 @@ mtype_expire(struct ip_set *set, struct htype *h)
 }
 
 static void
-mtype_gc(unsigned long ul_set)
+mtype_gc(struct timer_list *t)
 {
-	struct ip_set *set = (struct ip_set *)ul_set;
-	struct htype *h = set->data;
+	struct htype *h = from_timer(h, t, gc);
+	struct ip_set *set = h->set;
 
 	pr_debug("called\n");
 	spin_lock_bh(&set->lock);
@@ -1314,6 +1315,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 	t->htable_bits = hbits;
 	RCU_INIT_POINTER(h->table, t);
 
+	h->set = set;
 	set->data = h;
 #ifndef IP_SET_PROTO_UNDEF
 	if (set->family == NFPROTO_IPV4) {
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 178d4eba013b..c9b4e05ad940 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -44,6 +44,7 @@ struct set_adt_elem {
 struct list_set {
 	u32 size;		/* size of set list array */
 	struct timer_list gc;	/* garbage collection */
+	struct ip_set *set;	/* attached to this ip_set */
 	struct net *net;	/* namespace */
 	struct list_head members; /* the set members */
 };
@@ -571,10 +572,10 @@ static const struct ip_set_type_variant set_variant = {
 };
 
 static void
-list_set_gc(unsigned long ul_set)
+list_set_gc(struct timer_list *t)
 {
-	struct ip_set *set = (struct ip_set *)ul_set;
-	struct list_set *map = set->data;
+	struct list_set *map = from_timer(map, t, gc);
+	struct ip_set *set = map->set;
 
 	spin_lock_bh(&set->lock);
 	set_cleanup_entries(set);
@@ -585,11 +586,11 @@ list_set_gc(unsigned long ul_set)
 }
 
 static void
-list_set_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
+list_set_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t))
 {
 	struct list_set *map = set->data;
 
-	setup_timer(&map->gc, gc, (unsigned long)set);
+	timer_setup(&map->gc, gc, 0);
 	mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ);
 }
 
@@ -606,6 +607,7 @@ init_list_set(struct net *net, struct ip_set *set, u32 size)
 
 	map->size = size;
 	map->net = net;
+	map->set = set;
 	INIT_LIST_HEAD(&map->members);
 	set->data = map;
 
diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c
index 29123934887b..041da0d9c06f 100644
--- a/net/netfilter/xt_bpf.c
+++ b/net/netfilter/xt_bpf.c
@@ -56,7 +56,7 @@ static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret)
 	int retval, fd;
 
 	set_fs(KERNEL_DS);
-	fd = bpf_obj_get_user(path);
+	fd = bpf_obj_get_user(path, 0);
 	set_fs(oldfs);
 	if (fd < 0)
 		return fd;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index b93148e8e9fb..26ded4239611 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2313,17 +2313,16 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 	 * requests to cap the error message, and get extra error data if
 	 * requested.
 	 */
+	if (nlk_has_extack && extack && extack->_msg)
+		tlvlen += nla_total_size(strlen(extack->_msg) + 1);
+
 	if (err) {
 		if (!(nlk->flags & NETLINK_F_CAP_ACK))
 			payload += nlmsg_len(nlh);
 		else
 			flags |= NLM_F_CAPPED;
-		if (nlk_has_extack && extack) {
-			if (extack->_msg)
-				tlvlen += nla_total_size(strlen(extack->_msg) + 1);
-			if (extack->bad_attr)
-				tlvlen += nla_total_size(sizeof(u32));
-		}
+		if (nlk_has_extack && extack && extack->bad_attr)
+			tlvlen += nla_total_size(sizeof(u32));
 	} else {
 		flags |= NLM_F_CAPPED;
 
@@ -2336,16 +2335,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 
 	skb = nlmsg_new(payload + tlvlen, GFP_KERNEL);
 	if (!skb) {
-		struct sock *sk;
-
-		sk = netlink_lookup(sock_net(in_skb->sk),
-				    in_skb->sk->sk_protocol,
-				    NETLINK_CB(in_skb).portid);
-		if (sk) {
-			sk->sk_err = ENOBUFS;
-			sk->sk_error_report(sk);
-			sock_put(sk);
-		}
+		NETLINK_CB(in_skb).sk->sk_err = ENOBUFS;
+		NETLINK_CB(in_skb).sk->sk_error_report(NETLINK_CB(in_skb).sk);
 		return;
 	}
 
@@ -2356,10 +2347,11 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 	memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) ? nlh->nlmsg_len : sizeof(*nlh));
 
 	if (nlk_has_extack && extack) {
+		if (extack->_msg) {
+			WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG,
+					       extack->_msg));
+		}
 		if (err) {
-			if (extack->_msg)
-				WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG,
-						       extack->_msg));
 			if (extack->bad_attr &&
 			    !WARN_ON((u8 *)extack->bad_attr < in_skb->data ||
 				     (u8 *)extack->bad_attr >= in_skb->data +
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index ebf16f7f9089..2dec3583c97d 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -241,9 +241,9 @@ void nr_destroy_socket(struct sock *);
 /*
  *	Handler for deferred kills.
  */
-static void nr_destroy_timer(unsigned long data)
+static void nr_destroy_timer(struct timer_list *t)
 {
-	struct sock *sk=(struct sock *)data;
+	struct sock *sk = from_timer(sk, t, sk_timer);
 	bh_lock_sock(sk);
 	sock_hold(sk);
 	nr_destroy_socket(sk);
@@ -284,7 +284,7 @@ void nr_destroy_socket(struct sock *sk)
 
 	if (sk_has_allocations(sk)) {
 		/* Defer: outstanding buffers */
-		sk->sk_timer.function = nr_destroy_timer;
+		sk->sk_timer.function = (TIMER_FUNC_TYPE)nr_destroy_timer;
 		sk->sk_timer.expires  = jiffies + 2 * HZ;
 		add_timer(&sk->sk_timer);
 	} else
diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c
index 80dbd0beb516..fbfdae452ff9 100644
--- a/net/netrom/nr_in.c
+++ b/net/netrom/nr_in.c
@@ -125,7 +125,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb,
 
 	case NR_DISCREQ:
 		nr_write_internal(sk, NR_DISCACK);
-
+		/* fall through */
 	case NR_DISCACK:
 		nr_disconnect(sk, 0);
 		break;
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index 0c59354e280e..75e6ba970fde 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -80,6 +80,19 @@ static struct nr_neigh *nr_neigh_get_dev(ax25_address *callsign,
 
 static void nr_remove_neigh(struct nr_neigh *);
 
+/*      re-sort the routes in quality order.    */
+static void re_sort_routes(struct nr_node *nr_node, int x, int y)
+{
+	if (nr_node->routes[y].quality > nr_node->routes[x].quality) {
+		if (nr_node->which == x)
+			nr_node->which = y;
+		else if (nr_node->which == y)
+			nr_node->which = x;
+
+		swap(nr_node->routes[x], nr_node->routes[y]);
+	}
+}
+
 /*
  *	Add a new route to a node, and in the process add the node and the
  *	neighbour if it is new.
@@ -90,7 +103,6 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic,
 {
 	struct nr_node  *nr_node;
 	struct nr_neigh *nr_neigh;
-	struct nr_route nr_route;
 	int i, found;
 	struct net_device *odev;
 
@@ -251,49 +263,11 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic,
 	/* Now re-sort the routes in quality order */
 	switch (nr_node->count) {
 	case 3:
-		if (nr_node->routes[1].quality > nr_node->routes[0].quality) {
-			switch (nr_node->which) {
-			case 0:
-				nr_node->which = 1;
-				break;
-			case 1:
-				nr_node->which = 0;
-				break;
-			}
-			nr_route           = nr_node->routes[0];
-			nr_node->routes[0] = nr_node->routes[1];
-			nr_node->routes[1] = nr_route;
-		}
-		if (nr_node->routes[2].quality > nr_node->routes[1].quality) {
-			switch (nr_node->which) {
-			case 1:  nr_node->which = 2;
-				break;
-
-			case 2:  nr_node->which = 1;
-				break;
-
-			default:
-				break;
-			}
-			nr_route           = nr_node->routes[1];
-			nr_node->routes[1] = nr_node->routes[2];
-			nr_node->routes[2] = nr_route;
-		}
+		re_sort_routes(nr_node, 0, 1);
+		re_sort_routes(nr_node, 1, 2);
+		/* fall through */
 	case 2:
-		if (nr_node->routes[1].quality > nr_node->routes[0].quality) {
-			switch (nr_node->which) {
-			case 0:  nr_node->which = 1;
-				break;
-
-			case 1:  nr_node->which = 0;
-				break;
-
-			default: break;
-			}
-			nr_route           = nr_node->routes[0];
-			nr_node->routes[0] = nr_node->routes[1];
-			nr_node->routes[1] = nr_route;
-			}
+		re_sort_routes(nr_node, 0, 1);
 	case 1:
 		break;
 	}
@@ -384,6 +358,7 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n
 				switch (i) {
 				case 0:
 					nr_node->routes[0] = nr_node->routes[1];
+					/* fall through */
 				case 1:
 					nr_node->routes[1] = nr_node->routes[2];
 				case 2:
@@ -553,6 +528,7 @@ void nr_rt_device_down(struct net_device *dev)
 						switch (i) {
 						case 0:
 							t->routes[0] = t->routes[1];
+							/* fall through */
 						case 1:
 							t->routes[1] = t->routes[2];
 						case 2:
diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c
index 94d05806a9a2..43569aea0f5e 100644
--- a/net/netrom/nr_timer.c
+++ b/net/netrom/nr_timer.c
@@ -29,24 +29,23 @@
 #include <linux/interrupt.h>
 #include <net/netrom.h>
 
-static void nr_heartbeat_expiry(unsigned long);
-static void nr_t1timer_expiry(unsigned long);
-static void nr_t2timer_expiry(unsigned long);
-static void nr_t4timer_expiry(unsigned long);
-static void nr_idletimer_expiry(unsigned long);
+static void nr_heartbeat_expiry(struct timer_list *);
+static void nr_t1timer_expiry(struct timer_list *);
+static void nr_t2timer_expiry(struct timer_list *);
+static void nr_t4timer_expiry(struct timer_list *);
+static void nr_idletimer_expiry(struct timer_list *);
 
 void nr_init_timers(struct sock *sk)
 {
 	struct nr_sock *nr = nr_sk(sk);
 
-	setup_timer(&nr->t1timer, nr_t1timer_expiry, (unsigned long)sk);
-	setup_timer(&nr->t2timer, nr_t2timer_expiry, (unsigned long)sk);
-	setup_timer(&nr->t4timer, nr_t4timer_expiry, (unsigned long)sk);
-	setup_timer(&nr->idletimer, nr_idletimer_expiry, (unsigned long)sk);
+	timer_setup(&nr->t1timer, nr_t1timer_expiry, 0);
+	timer_setup(&nr->t2timer, nr_t2timer_expiry, 0);
+	timer_setup(&nr->t4timer, nr_t4timer_expiry, 0);
+	timer_setup(&nr->idletimer, nr_idletimer_expiry, 0);
 
 	/* initialized by sock_init_data */
-	sk->sk_timer.data     = (unsigned long)sk;
-	sk->sk_timer.function = &nr_heartbeat_expiry;
+	sk->sk_timer.function = (TIMER_FUNC_TYPE)nr_heartbeat_expiry;
 }
 
 void nr_start_t1timer(struct sock *sk)
@@ -113,9 +112,9 @@ int nr_t1timer_running(struct sock *sk)
 	return timer_pending(&nr_sk(sk)->t1timer);
 }
 
-static void nr_heartbeat_expiry(unsigned long param)
+static void nr_heartbeat_expiry(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)param;
+	struct sock *sk = from_timer(sk, t, sk_timer);
 	struct nr_sock *nr = nr_sk(sk);
 
 	bh_lock_sock(sk);
@@ -152,10 +151,10 @@ static void nr_heartbeat_expiry(unsigned long param)
 	bh_unlock_sock(sk);
 }
 
-static void nr_t2timer_expiry(unsigned long param)
+static void nr_t2timer_expiry(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)param;
-	struct nr_sock *nr = nr_sk(sk);
+	struct nr_sock *nr = from_timer(nr, t, t2timer);
+	struct sock *sk = &nr->sock;
 
 	bh_lock_sock(sk);
 	if (nr->condition & NR_COND_ACK_PENDING) {
@@ -165,19 +164,20 @@ static void nr_t2timer_expiry(unsigned long param)
 	bh_unlock_sock(sk);
 }
 
-static void nr_t4timer_expiry(unsigned long param)
+static void nr_t4timer_expiry(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)param;
+	struct nr_sock *nr = from_timer(nr, t, t4timer);
+	struct sock *sk = &nr->sock;
 
 	bh_lock_sock(sk);
 	nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY;
 	bh_unlock_sock(sk);
 }
 
-static void nr_idletimer_expiry(unsigned long param)
+static void nr_idletimer_expiry(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)param;
-	struct nr_sock *nr = nr_sk(sk);
+	struct nr_sock *nr = from_timer(nr, t, idletimer);
+	struct sock *sk = &nr->sock;
 
 	bh_lock_sock(sk);
 
@@ -202,10 +202,10 @@ static void nr_idletimer_expiry(unsigned long param)
 	bh_unlock_sock(sk);
 }
 
-static void nr_t1timer_expiry(unsigned long param)
+static void nr_t1timer_expiry(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)param;
-	struct nr_sock *nr = nr_sk(sk);
+	struct nr_sock *nr = from_timer(nr, t, t1timer);
+	struct sock *sk = &nr->sock;
 
 	bh_lock_sock(sk);
 	switch (nr->state) {
diff --git a/net/nfc/core.c b/net/nfc/core.c
index 5cf33df888c3..e5e23c2cbe74 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -1094,9 +1094,8 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops,
 	dev->targets_generation = 1;
 
 	if (ops->check_presence) {
-		init_timer(&dev->check_pres_timer);
-		dev->check_pres_timer.data = (unsigned long)dev;
-		dev->check_pres_timer.function = nfc_check_pres_timeout;
+		setup_timer(&dev->check_pres_timer, nfc_check_pres_timeout,
+			    (unsigned long)dev);
 
 		INIT_WORK(&dev->check_pres_work, nfc_check_pres_work);
 	}
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index b740fef0acc5..a8a6e7814e09 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -1004,9 +1004,8 @@ int nfc_hci_register_device(struct nfc_hci_dev *hdev)
 
 	INIT_WORK(&hdev->msg_tx_work, nfc_hci_msg_tx_work);
 
-	init_timer(&hdev->cmd_timer);
-	hdev->cmd_timer.data = (unsigned long)hdev;
-	hdev->cmd_timer.function = nfc_hci_cmd_timeout;
+	setup_timer(&hdev->cmd_timer, nfc_hci_cmd_timeout,
+		    (unsigned long)hdev);
 
 	skb_queue_head_init(&hdev->rx_hcp_frags);
 
diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c
index 17e59a009ce6..58df37eae1e8 100644
--- a/net/nfc/hci/llc_shdlc.c
+++ b/net/nfc/hci/llc_shdlc.c
@@ -763,17 +763,14 @@ static void *llc_shdlc_init(struct nfc_hci_dev *hdev, xmit_to_drv_t xmit_to_drv,
 	mutex_init(&shdlc->state_mutex);
 	shdlc->state = SHDLC_DISCONNECTED;
 
-	init_timer(&shdlc->connect_timer);
-	shdlc->connect_timer.data = (unsigned long)shdlc;
-	shdlc->connect_timer.function = llc_shdlc_connect_timeout;
+	setup_timer(&shdlc->connect_timer, llc_shdlc_connect_timeout,
+		    (unsigned long)shdlc);
 
-	init_timer(&shdlc->t1_timer);
-	shdlc->t1_timer.data = (unsigned long)shdlc;
-	shdlc->t1_timer.function = llc_shdlc_t1_timeout;
+	setup_timer(&shdlc->t1_timer, llc_shdlc_t1_timeout,
+		    (unsigned long)shdlc);
 
-	init_timer(&shdlc->t2_timer);
-	shdlc->t2_timer.data = (unsigned long)shdlc;
-	shdlc->t2_timer.function = llc_shdlc_t2_timeout;
+	setup_timer(&shdlc->t2_timer, llc_shdlc_t2_timeout,
+		    (unsigned long)shdlc);
 
 	shdlc->w = SHDLC_MAX_WINDOW;
 	shdlc->srej_support = SHDLC_SREJ_SUPPORT;
diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c
index 02eef5cf3cce..7988185072e5 100644
--- a/net/nfc/llcp_core.c
+++ b/net/nfc/llcp_core.c
@@ -1573,9 +1573,8 @@ int nfc_llcp_register_device(struct nfc_dev *ndev)
 	INIT_LIST_HEAD(&local->list);
 	kref_init(&local->ref);
 	mutex_init(&local->sdp_lock);
-	init_timer(&local->link_timer);
-	local->link_timer.data = (unsigned long) local;
-	local->link_timer.function = nfc_llcp_symm_timer;
+	setup_timer(&local->link_timer, nfc_llcp_symm_timer,
+		    (unsigned long)local);
 
 	skb_queue_head_init(&local->tx_queue);
 	INIT_WORK(&local->tx_work, nfc_llcp_tx_work);
@@ -1601,9 +1600,8 @@ int nfc_llcp_register_device(struct nfc_dev *ndev)
 
 	mutex_init(&local->sdreq_lock);
 	INIT_HLIST_HEAD(&local->pending_sdreqs);
-	init_timer(&local->sdreq_timer);
-	local->sdreq_timer.data = (unsigned long) local;
-	local->sdreq_timer.function = nfc_llcp_sdreq_timer;
+	setup_timer(&local->sdreq_timer, nfc_llcp_sdreq_timer,
+		    (unsigned long)local);
 	INIT_WORK(&local->sdreq_timeout_work, nfc_llcp_sdreq_timeout_work);
 
 	list_add(&local->list, &llcp_devices);
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index a54a556fcdb5..a551232daf61 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1203,6 +1203,10 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 				return err == -EINPROGRESS ? 0 : err;
 			break;
 
+		case OVS_ACTION_ATTR_CT_CLEAR:
+			err = ovs_ct_clear(skb, key);
+			break;
+
 		case OVS_ACTION_ATTR_PUSH_ETH:
 			err = push_eth(skb, key, nla_data(a));
 			break;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index d558e882ca0c..b27c5c6d9cab 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -752,6 +752,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 			}
 		}
 		/* Non-ICMP, fall thru to initialize if needed. */
+		/* fall through */
 	case IP_CT_NEW:
 		/* Seen it before?  This can happen for loopback, retrans,
 		 * or local packets.
@@ -1129,6 +1130,17 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 	return err;
 }
 
+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);
+	}
+
+	return 0;
+}
+
 static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name,
 			     const struct sw_flow_key *key, bool log)
 {
diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h
index bc7efd1867ab..399dfdd2c4f9 100644
--- a/net/openvswitch/conntrack.h
+++ b/net/openvswitch/conntrack.h
@@ -30,6 +30,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *, struct sk_buff *);
 
 int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *,
 		   const struct ovs_conntrack_info *);
+int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key);
 
 void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key);
 int ovs_ct_put_key(const struct sw_flow_key *swkey,
@@ -73,6 +74,12 @@ static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 	return -ENOTSUPP;
 }
 
+static inline int ovs_ct_clear(struct sk_buff *skb,
+			       struct sw_flow_key *key)
+{
+	return -ENOTSUPP;
+}
+
 static inline void ovs_ct_fill_key(const struct sk_buff *skb,
 				   struct sw_flow_key *key)
 {
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index e8eb427ce6d1..dc0d79092e74 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -48,6 +48,7 @@
 #include <net/ndisc.h>
 #include <net/mpls.h>
 #include <net/vxlan.h>
+#include <net/erspan.h>
 
 #include "flow_netlink.h"
 
@@ -75,6 +76,7 @@ static bool actions_may_change_flow(const struct nlattr *actions)
 			break;
 
 		case OVS_ACTION_ATTR_CT:
+		case OVS_ACTION_ATTR_CT_CLEAR:
 		case OVS_ACTION_ATTR_HASH:
 		case OVS_ACTION_ATTR_POP_ETH:
 		case OVS_ACTION_ATTR_POP_MPLS:
@@ -319,7 +321,8 @@ size_t ovs_tun_key_attr_size(void)
 		 * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it.
 		 */
 		+ nla_total_size(2)    /* OVS_TUNNEL_KEY_ATTR_TP_SRC */
-		+ nla_total_size(2);   /* OVS_TUNNEL_KEY_ATTR_TP_DST */
+		+ nla_total_size(2)    /* OVS_TUNNEL_KEY_ATTR_TP_DST */
+		+ nla_total_size(4);   /* OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS */
 }
 
 size_t ovs_key_attr_size(void)
@@ -371,6 +374,7 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1]
 						.next = ovs_vxlan_ext_key_lens },
 	[OVS_TUNNEL_KEY_ATTR_IPV6_SRC]      = { .len = sizeof(struct in6_addr) },
 	[OVS_TUNNEL_KEY_ATTR_IPV6_DST]      = { .len = sizeof(struct in6_addr) },
+	[OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS]   = { .len = sizeof(u32) },
 };
 
 /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute.  */
@@ -593,6 +597,33 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr,
 	return 0;
 }
 
+static int erspan_tun_opt_from_nlattr(const struct nlattr *attr,
+				      struct sw_flow_match *match, bool is_mask,
+				      bool log)
+{
+	unsigned long opt_key_offset;
+	struct erspan_metadata opts;
+
+	BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts));
+
+	memset(&opts, 0, sizeof(opts));
+	opts.index = nla_get_be32(attr);
+
+	/* Index has only 20-bit */
+	if (ntohl(opts.index) & ~INDEX_MASK) {
+		OVS_NLERR(log, "ERSPAN index number %x too large.",
+			  ntohl(opts.index));
+		return -EINVAL;
+	}
+
+	SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), is_mask);
+	opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts));
+	SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts),
+				  is_mask);
+
+	return 0;
+}
+
 static int ip_tun_from_nlattr(const struct nlattr *attr,
 			      struct sw_flow_match *match, bool is_mask,
 			      bool log)
@@ -700,6 +731,19 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			break;
 		case OVS_TUNNEL_KEY_ATTR_PAD:
 			break;
+		case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS:
+			if (opts_type) {
+				OVS_NLERR(log, "Multiple metadata blocks provided");
+				return -EINVAL;
+			}
+
+			err = erspan_tun_opt_from_nlattr(a, match, is_mask, log);
+			if (err)
+				return err;
+
+			tun_flags |= TUNNEL_ERSPAN_OPT;
+			opts_type = type;
+			break;
 		default:
 			OVS_NLERR(log, "Unknown IP tunnel attribute %d",
 				  type);
@@ -824,6 +868,10 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb,
 		else if (output->tun_flags & TUNNEL_VXLAN_OPT &&
 			 vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len))
 			return -EMSGSIZE;
+		else if (output->tun_flags & TUNNEL_ERSPAN_OPT &&
+			 nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS,
+				      ((struct erspan_metadata *)tun_opts)->index))
+			return -EMSGSIZE;
 	}
 
 	return 0;
@@ -2195,6 +2243,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 			break;
 		case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS:
 			break;
+		case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS:
+			break;
 		}
 	};
 
@@ -2479,6 +2529,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			[OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
 			[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash),
 			[OVS_ACTION_ATTR_CT] = (u32)-1,
+			[OVS_ACTION_ATTR_CT_CLEAR] = 0,
 			[OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc),
 			[OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth),
 			[OVS_ACTION_ATTR_POP_ETH] = 0,
@@ -2620,6 +2671,9 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			skip_copy = true;
 			break;
 
+		case OVS_ACTION_ATTR_CT_CLEAR:
+			break;
+
 		case OVS_ACTION_ATTR_PUSH_ETH:
 			/* Disallow pushing an Ethernet header if one
 			 * is already present */
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index 0389398fa4ab..2e5e7a41d8ef 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -108,7 +108,8 @@ struct vport *ovs_netdev_link(struct vport *vport, const char *name)
 
 	rtnl_lock();
 	err = netdev_master_upper_dev_link(vport->dev,
-					   get_dpdev(vport->dp), NULL, NULL);
+					   get_dpdev(vport->dp),
+					   NULL, NULL, NULL);
 	if (err)
 		goto error_unlock;
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 2986941164b1..9603f6ff17a4 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -201,11 +201,8 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *,
 static int prb_queue_frozen(struct tpacket_kbdq_core *);
 static void prb_open_block(struct tpacket_kbdq_core *,
 		struct tpacket_block_desc *);
-static void prb_retire_rx_blk_timer_expired(unsigned long);
+static void prb_retire_rx_blk_timer_expired(struct timer_list *);
 static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *);
-static void prb_init_blk_timer(struct packet_sock *,
-		struct tpacket_kbdq_core *,
-		void (*func) (unsigned long));
 static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *);
 static void prb_clear_rxhash(struct tpacket_kbdq_core *,
 		struct tpacket3_hdr *);
@@ -540,22 +537,14 @@ static void prb_shutdown_retire_blk_timer(struct packet_sock *po,
 	prb_del_retire_blk_timer(pkc);
 }
 
-static void prb_init_blk_timer(struct packet_sock *po,
-		struct tpacket_kbdq_core *pkc,
-		void (*func) (unsigned long))
-{
-	init_timer(&pkc->retire_blk_timer);
-	pkc->retire_blk_timer.data = (long)po;
-	pkc->retire_blk_timer.function = func;
-	pkc->retire_blk_timer.expires = jiffies;
-}
-
 static void prb_setup_retire_blk_timer(struct packet_sock *po)
 {
 	struct tpacket_kbdq_core *pkc;
 
 	pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
-	prb_init_blk_timer(po, pkc, prb_retire_rx_blk_timer_expired);
+	timer_setup(&pkc->retire_blk_timer, prb_retire_rx_blk_timer_expired,
+		    0);
+	pkc->retire_blk_timer.expires = jiffies;
 }
 
 static int prb_calc_retire_blk_tmo(struct packet_sock *po,
@@ -673,9 +662,10 @@ static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc)
  * prb_calc_retire_blk_tmo() calculates the tmo.
  *
  */
-static void prb_retire_rx_blk_timer_expired(unsigned long data)
+static void prb_retire_rx_blk_timer_expired(struct timer_list *t)
 {
-	struct packet_sock *po = (struct packet_sock *)data;
+	struct packet_sock *po =
+		from_timer(po, t, rx_ring.prb_bdqc.retire_blk_timer);
 	struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
 	unsigned int frozen;
 	struct tpacket_block_desc *pbd;
diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index f925753668a7..3b0ef691f5b1 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -35,11 +35,11 @@
 #include <net/phonet/pn_dev.h>
 
 /* Transport protocol registration */
-static struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly;
+static const struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly;
 
-static struct phonet_protocol *phonet_proto_get(unsigned int protocol)
+static const struct phonet_protocol *phonet_proto_get(unsigned int protocol)
 {
-	struct phonet_protocol *pp;
+	const struct phonet_protocol *pp;
 
 	if (protocol >= PHONET_NPROTO)
 		return NULL;
@@ -53,7 +53,7 @@ static struct phonet_protocol *phonet_proto_get(unsigned int protocol)
 	return pp;
 }
 
-static inline void phonet_proto_put(struct phonet_protocol *pp)
+static inline void phonet_proto_put(const struct phonet_protocol *pp)
 {
 	module_put(pp->prot->owner);
 }
@@ -65,7 +65,7 @@ static int pn_socket_create(struct net *net, struct socket *sock, int protocol,
 {
 	struct sock *sk;
 	struct pn_sock *pn;
-	struct phonet_protocol *pnp;
+	const struct phonet_protocol *pnp;
 	int err;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -149,7 +149,7 @@ static int pn_header_parse(const struct sk_buff *skb, unsigned char *haddr)
 	return 1;
 }
 
-struct header_ops phonet_header_ops = {
+const struct header_ops phonet_header_ops = {
 	.create = pn_header_create,
 	.parse = pn_header_parse,
 };
@@ -470,7 +470,7 @@ static struct packet_type phonet_packet_type __read_mostly = {
 static DEFINE_MUTEX(proto_tab_lock);
 
 int __init_or_module phonet_proto_register(unsigned int protocol,
-						struct phonet_protocol *pp)
+				const struct phonet_protocol *pp)
 {
 	int err = 0;
 
@@ -492,7 +492,8 @@ int __init_or_module phonet_proto_register(unsigned int protocol,
 }
 EXPORT_SYMBOL(phonet_proto_register);
 
-void phonet_proto_unregister(unsigned int protocol, struct phonet_protocol *pp)
+void phonet_proto_unregister(unsigned int protocol,
+			const struct phonet_protocol *pp)
 {
 	mutex_lock(&proto_tab_lock);
 	BUG_ON(proto_tab[protocol] != pp);
diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c
index 5e710435ffa9..b44fb9018fb8 100644
--- a/net/phonet/datagram.c
+++ b/net/phonet/datagram.c
@@ -195,7 +195,7 @@ static struct proto pn_proto = {
 	.name		= "PHONET",
 };
 
-static struct phonet_protocol pn_dgram_proto = {
+static const struct phonet_protocol pn_dgram_proto = {
 	.ops		= &phonet_dgram_ops,
 	.prot		= &pn_proto,
 	.sock_type	= SOCK_DGRAM,
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index e81537991ddf..9fc76b19cd3c 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -1351,7 +1351,7 @@ static struct proto pep_proto = {
 	.name		= "PNPIPE",
 };
 
-static struct phonet_protocol pep_pn_proto = {
+static const struct phonet_protocol pep_pn_proto = {
 	.ops		= &phonet_stream_ops,
 	.prot		= &pep_proto,
 	.sock_type	= SOCK_SEQPACKET,
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index c2f5c13550c0..e458ece96d3d 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -20,26 +20,15 @@
 
 #include "qrtr.h"
 
-#define QRTR_PROTO_VER 1
+#define QRTR_PROTO_VER_1 1
+#define QRTR_PROTO_VER_2 3
 
 /* auto-bind range */
 #define QRTR_MIN_EPH_SOCKET 0x4000
 #define QRTR_MAX_EPH_SOCKET 0x7fff
 
-enum qrtr_pkt_type {
-	QRTR_TYPE_DATA		= 1,
-	QRTR_TYPE_HELLO		= 2,
-	QRTR_TYPE_BYE		= 3,
-	QRTR_TYPE_NEW_SERVER	= 4,
-	QRTR_TYPE_DEL_SERVER	= 5,
-	QRTR_TYPE_DEL_CLIENT	= 6,
-	QRTR_TYPE_RESUME_TX	= 7,
-	QRTR_TYPE_EXIT		= 8,
-	QRTR_TYPE_PING		= 9,
-};
-
 /**
- * struct qrtr_hdr - (I|R)PCrouter packet header
+ * struct qrtr_hdr_v1 - (I|R)PCrouter packet header version 1
  * @version: protocol version
  * @type: packet type; one of QRTR_TYPE_*
  * @src_node_id: source node
@@ -49,7 +38,7 @@ enum qrtr_pkt_type {
  * @dst_node_id: destination node
  * @dst_port_id: destination port
  */
-struct qrtr_hdr {
+struct qrtr_hdr_v1 {
 	__le32 version;
 	__le32 type;
 	__le32 src_node_id;
@@ -60,9 +49,44 @@ struct qrtr_hdr {
 	__le32 dst_port_id;
 } __packed;
 
-#define QRTR_HDR_SIZE sizeof(struct qrtr_hdr)
-#define QRTR_NODE_BCAST ((unsigned int)-1)
-#define QRTR_PORT_CTRL ((unsigned int)-2)
+/**
+ * struct qrtr_hdr_v2 - (I|R)PCrouter packet header later versions
+ * @version: protocol version
+ * @type: packet type; one of QRTR_TYPE_*
+ * @flags: bitmask of QRTR_FLAGS_*
+ * @optlen: length of optional header data
+ * @size: length of packet, excluding this header and optlen
+ * @src_node_id: source node
+ * @src_port_id: source port
+ * @dst_node_id: destination node
+ * @dst_port_id: destination port
+ */
+struct qrtr_hdr_v2 {
+	u8 version;
+	u8 type;
+	u8 flags;
+	u8 optlen;
+	__le32 size;
+	__le16 src_node_id;
+	__le16 src_port_id;
+	__le16 dst_node_id;
+	__le16 dst_port_id;
+};
+
+#define QRTR_FLAGS_CONFIRM_RX	BIT(0)
+
+struct qrtr_cb {
+	u32 src_node;
+	u32 src_port;
+	u32 dst_node;
+	u32 dst_port;
+
+	u8 type;
+	u8 confirm_rx;
+};
+
+#define QRTR_HDR_MAX_SIZE max_t(size_t, sizeof(struct qrtr_hdr_v1), \
+					sizeof(struct qrtr_hdr_v2))
 
 struct qrtr_sock {
 	/* WARNING: sk must be the first member */
@@ -111,8 +135,12 @@ struct qrtr_node {
 	struct list_head item;
 };
 
-static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb);
-static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb);
+static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb,
+			      int type, struct sockaddr_qrtr *from,
+			      struct sockaddr_qrtr *to);
+static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
+			      int type, struct sockaddr_qrtr *from,
+			      struct sockaddr_qrtr *to);
 
 /* Release node resources and free the node.
  *
@@ -150,10 +178,27 @@ static void qrtr_node_release(struct qrtr_node *node)
 }
 
 /* Pass an outgoing packet socket buffer to the endpoint driver. */
-static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb)
+static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
+			     int type, struct sockaddr_qrtr *from,
+			     struct sockaddr_qrtr *to)
 {
+	struct qrtr_hdr_v1 *hdr;
+	size_t len = skb->len;
 	int rc = -ENODEV;
 
+	hdr = skb_push(skb, sizeof(*hdr));
+	hdr->version = cpu_to_le32(QRTR_PROTO_VER_1);
+	hdr->type = cpu_to_le32(type);
+	hdr->src_node_id = cpu_to_le32(from->sq_node);
+	hdr->src_port_id = cpu_to_le32(from->sq_port);
+	hdr->dst_node_id = cpu_to_le32(to->sq_node);
+	hdr->dst_port_id = cpu_to_le32(to->sq_port);
+
+	hdr->size = cpu_to_le32(len);
+	hdr->confirm_rx = 0;
+
+	skb_put_padto(skb, ALIGN(len, 4));
+
 	mutex_lock(&node->ep_lock);
 	if (node->ep)
 		rc = node->ep->xmit(node->ep, skb);
@@ -207,125 +252,103 @@ static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid)
 int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 {
 	struct qrtr_node *node = ep->node;
-	const struct qrtr_hdr *phdr = data;
+	const struct qrtr_hdr_v1 *v1;
+	const struct qrtr_hdr_v2 *v2;
 	struct sk_buff *skb;
-	unsigned int psize;
+	struct qrtr_cb *cb;
 	unsigned int size;
-	unsigned int type;
 	unsigned int ver;
-	unsigned int dst;
-
-	if (len < QRTR_HDR_SIZE || len & 3)
-		return -EINVAL;
-
-	ver = le32_to_cpu(phdr->version);
-	size = le32_to_cpu(phdr->size);
-	type = le32_to_cpu(phdr->type);
-	dst = le32_to_cpu(phdr->dst_port_id);
-
-	psize = (size + 3) & ~3;
+	size_t hdrlen;
 
-	if (ver != QRTR_PROTO_VER)
-		return -EINVAL;
-
-	if (len != psize + QRTR_HDR_SIZE)
-		return -EINVAL;
-
-	if (dst != QRTR_PORT_CTRL && type != QRTR_TYPE_DATA)
+	if (len & 3)
 		return -EINVAL;
 
 	skb = netdev_alloc_skb(NULL, len);
 	if (!skb)
 		return -ENOMEM;
 
-	skb_reset_transport_header(skb);
-	skb_put_data(skb, data, len);
-
-	skb_queue_tail(&node->rx_queue, skb);
-	schedule_work(&node->work);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(qrtr_endpoint_post);
+	cb = (struct qrtr_cb *)skb->cb;
 
-static struct sk_buff *qrtr_alloc_ctrl_packet(u32 type, size_t pkt_len,
-					      u32 src_node, u32 dst_node)
-{
-	struct qrtr_hdr *hdr;
-	struct sk_buff *skb;
-
-	skb = alloc_skb(QRTR_HDR_SIZE + pkt_len, GFP_KERNEL);
-	if (!skb)
-		return NULL;
-	skb_reset_transport_header(skb);
+	/* Version field in v1 is little endian, so this works for both cases */
+	ver = *(u8*)data;
 
-	hdr = skb_put(skb, QRTR_HDR_SIZE);
-	hdr->version = cpu_to_le32(QRTR_PROTO_VER);
-	hdr->type = cpu_to_le32(type);
-	hdr->src_node_id = cpu_to_le32(src_node);
-	hdr->src_port_id = cpu_to_le32(QRTR_PORT_CTRL);
-	hdr->confirm_rx = cpu_to_le32(0);
-	hdr->size = cpu_to_le32(pkt_len);
-	hdr->dst_node_id = cpu_to_le32(dst_node);
-	hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL);
+	switch (ver) {
+	case QRTR_PROTO_VER_1:
+		v1 = data;
+		hdrlen = sizeof(*v1);
 
-	return skb;
-}
+		cb->type = le32_to_cpu(v1->type);
+		cb->src_node = le32_to_cpu(v1->src_node_id);
+		cb->src_port = le32_to_cpu(v1->src_port_id);
+		cb->confirm_rx = !!v1->confirm_rx;
+		cb->dst_node = le32_to_cpu(v1->dst_node_id);
+		cb->dst_port = le32_to_cpu(v1->dst_port_id);
 
-/* Allocate and construct a resume-tx packet. */
-static struct sk_buff *qrtr_alloc_resume_tx(u32 src_node,
-					    u32 dst_node, u32 port)
-{
-	const int pkt_len = 20;
-	struct sk_buff *skb;
-	__le32 *buf;
+		size = le32_to_cpu(v1->size);
+		break;
+	case QRTR_PROTO_VER_2:
+		v2 = data;
+		hdrlen = sizeof(*v2) + v2->optlen;
+
+		cb->type = v2->type;
+		cb->confirm_rx = !!(v2->flags & QRTR_FLAGS_CONFIRM_RX);
+		cb->src_node = le16_to_cpu(v2->src_node_id);
+		cb->src_port = le16_to_cpu(v2->src_port_id);
+		cb->dst_node = le16_to_cpu(v2->dst_node_id);
+		cb->dst_port = le16_to_cpu(v2->dst_port_id);
+
+		if (cb->src_port == (u16)QRTR_PORT_CTRL)
+			cb->src_port = QRTR_PORT_CTRL;
+		if (cb->dst_port == (u16)QRTR_PORT_CTRL)
+			cb->dst_port = QRTR_PORT_CTRL;
+
+		size = le32_to_cpu(v2->size);
+		break;
+	default:
+		pr_err("qrtr: Invalid version %d\n", ver);
+		goto err;
+	}
 
-	skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_RESUME_TX, pkt_len,
-				     src_node, dst_node);
-	if (!skb)
-		return NULL;
+	if (len != ALIGN(size, 4) + hdrlen)
+		goto err;
 
-	buf = skb_put_zero(skb, pkt_len);
-	buf[0] = cpu_to_le32(QRTR_TYPE_RESUME_TX);
-	buf[1] = cpu_to_le32(src_node);
-	buf[2] = cpu_to_le32(port);
+	if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA)
+		goto err;
 
-	return skb;
-}
+	skb_put_data(skb, data + hdrlen, size);
 
-/* Allocate and construct a BYE message to signal remote termination */
-static struct sk_buff *qrtr_alloc_local_bye(u32 src_node)
-{
-	const int pkt_len = 20;
-	struct sk_buff *skb;
-	__le32 *buf;
+	skb_queue_tail(&node->rx_queue, skb);
+	schedule_work(&node->work);
 
-	skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_BYE, pkt_len,
-				     src_node, qrtr_local_nid);
-	if (!skb)
-		return NULL;
+	return 0;
 
-	buf = skb_put_zero(skb, pkt_len);
-	buf[0] = cpu_to_le32(QRTR_TYPE_BYE);
+err:
+	kfree_skb(skb);
+	return -EINVAL;
 
-	return skb;
 }
+EXPORT_SYMBOL_GPL(qrtr_endpoint_post);
 
-static struct sk_buff *qrtr_alloc_del_client(struct sockaddr_qrtr *sq)
+/**
+ * qrtr_alloc_ctrl_packet() - allocate control packet skb
+ * @pkt: reference to qrtr_ctrl_pkt pointer
+ *
+ * Returns newly allocated sk_buff, or NULL on failure
+ *
+ * This function allocates a sk_buff large enough to carry a qrtr_ctrl_pkt and
+ * on success returns a reference to the control packet in @pkt.
+ */
+static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt)
 {
-	const int pkt_len = 20;
+	const int pkt_len = sizeof(struct qrtr_ctrl_pkt);
 	struct sk_buff *skb;
-	__le32 *buf;
 
-	skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_DEL_CLIENT, pkt_len,
-				     sq->sq_node, QRTR_NODE_BCAST);
+	skb = alloc_skb(QRTR_HDR_MAX_SIZE + pkt_len, GFP_KERNEL);
 	if (!skb)
 		return NULL;
 
-	buf = skb_put_zero(skb, pkt_len);
-	buf[0] = cpu_to_le32(QRTR_TYPE_DEL_CLIENT);
-	buf[1] = cpu_to_le32(sq->sq_node);
-	buf[2] = cpu_to_le32(sq->sq_port);
+	skb_reserve(skb, QRTR_HDR_MAX_SIZE);
+	*pkt = skb_put_zero(skb, pkt_len);
 
 	return skb;
 }
@@ -340,24 +363,26 @@ static void qrtr_port_put(struct qrtr_sock *ipc);
 static void qrtr_node_rx_work(struct work_struct *work)
 {
 	struct qrtr_node *node = container_of(work, struct qrtr_node, work);
+	struct qrtr_ctrl_pkt *pkt;
+	struct sockaddr_qrtr dst;
+	struct sockaddr_qrtr src;
 	struct sk_buff *skb;
 
 	while ((skb = skb_dequeue(&node->rx_queue)) != NULL) {
-		const struct qrtr_hdr *phdr;
-		u32 dst_node, dst_port;
 		struct qrtr_sock *ipc;
-		u32 src_node;
+		struct qrtr_cb *cb;
 		int confirm;
 
-		phdr = (const struct qrtr_hdr *)skb_transport_header(skb);
-		src_node = le32_to_cpu(phdr->src_node_id);
-		dst_node = le32_to_cpu(phdr->dst_node_id);
-		dst_port = le32_to_cpu(phdr->dst_port_id);
-		confirm = !!phdr->confirm_rx;
+		cb = (struct qrtr_cb *)skb->cb;
+		src.sq_node = cb->src_node;
+		src.sq_port = cb->src_port;
+		dst.sq_node = cb->dst_node;
+		dst.sq_port = cb->dst_port;
+		confirm = !!cb->confirm_rx;
 
-		qrtr_node_assign(node, src_node);
+		qrtr_node_assign(node, cb->src_node);
 
-		ipc = qrtr_port_lookup(dst_port);
+		ipc = qrtr_port_lookup(cb->dst_port);
 		if (!ipc) {
 			kfree_skb(skb);
 		} else {
@@ -368,10 +393,16 @@ static void qrtr_node_rx_work(struct work_struct *work)
 		}
 
 		if (confirm) {
-			skb = qrtr_alloc_resume_tx(dst_node, node->nid, dst_port);
+			skb = qrtr_alloc_ctrl_packet(&pkt);
 			if (!skb)
 				break;
-			if (qrtr_node_enqueue(node, skb))
+
+			pkt->cmd = cpu_to_le32(QRTR_TYPE_RESUME_TX);
+			pkt->client.node = cpu_to_le32(dst.sq_node);
+			pkt->client.port = cpu_to_le32(dst.sq_port);
+
+			if (qrtr_node_enqueue(node, skb, QRTR_TYPE_RESUME_TX,
+					      &dst, &src))
 				break;
 		}
 	}
@@ -421,6 +452,9 @@ EXPORT_SYMBOL_GPL(qrtr_endpoint_register);
 void qrtr_endpoint_unregister(struct qrtr_endpoint *ep)
 {
 	struct qrtr_node *node = ep->node;
+	struct sockaddr_qrtr src = {AF_QIPCRTR, node->nid, QRTR_PORT_CTRL};
+	struct sockaddr_qrtr dst = {AF_QIPCRTR, qrtr_local_nid, QRTR_PORT_CTRL};
+	struct qrtr_ctrl_pkt *pkt;
 	struct sk_buff *skb;
 
 	mutex_lock(&node->ep_lock);
@@ -428,9 +462,11 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep)
 	mutex_unlock(&node->ep_lock);
 
 	/* Notify the local controller about the event */
-	skb = qrtr_alloc_local_bye(node->nid);
-	if (skb)
-		qrtr_local_enqueue(NULL, skb);
+	skb = qrtr_alloc_ctrl_packet(&pkt);
+	if (skb) {
+		pkt->cmd = cpu_to_le32(QRTR_TYPE_BYE);
+		qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst);
+	}
 
 	qrtr_node_release(node);
 	ep->node = NULL;
@@ -466,13 +502,24 @@ static void qrtr_port_put(struct qrtr_sock *ipc)
 /* Remove port assignment. */
 static void qrtr_port_remove(struct qrtr_sock *ipc)
 {
+	struct qrtr_ctrl_pkt *pkt;
 	struct sk_buff *skb;
 	int port = ipc->us.sq_port;
+	struct sockaddr_qrtr to;
 
-	skb = qrtr_alloc_del_client(&ipc->us);
+	to.sq_family = AF_QIPCRTR;
+	to.sq_node = QRTR_NODE_BCAST;
+	to.sq_port = QRTR_PORT_CTRL;
+
+	skb = qrtr_alloc_ctrl_packet(&pkt);
 	if (skb) {
+		pkt->cmd = cpu_to_le32(QRTR_TYPE_DEL_CLIENT);
+		pkt->client.node = cpu_to_le32(ipc->us.sq_node);
+		pkt->client.port = cpu_to_le32(ipc->us.sq_port);
+
 		skb_set_owner_w(skb, &ipc->sk);
-		qrtr_bcast_enqueue(NULL, skb);
+		qrtr_bcast_enqueue(NULL, skb, QRTR_TYPE_DEL_CLIENT, &ipc->us,
+				   &to);
 	}
 
 	if (port == QRTR_PORT_CTRL)
@@ -541,7 +588,7 @@ static void qrtr_reset_ports(void)
 
 		sock_hold(&ipc->sk);
 		ipc->sk.sk_err = ENETRESET;
-		wake_up_interruptible(sk_sleep(&ipc->sk));
+		ipc->sk.sk_error_report(&ipc->sk);
 		sock_put(&ipc->sk);
 	}
 	mutex_unlock(&qrtr_port_lock);
@@ -620,19 +667,23 @@ static int qrtr_bind(struct socket *sock, struct sockaddr *saddr, int len)
 }
 
 /* Queue packet to local peer socket. */
-static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb)
+static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb,
+			      int type, struct sockaddr_qrtr *from,
+			      struct sockaddr_qrtr *to)
 {
-	const struct qrtr_hdr *phdr;
 	struct qrtr_sock *ipc;
+	struct qrtr_cb *cb;
 
-	phdr = (const struct qrtr_hdr *)skb_transport_header(skb);
-
-	ipc = qrtr_port_lookup(le32_to_cpu(phdr->dst_port_id));
+	ipc = qrtr_port_lookup(to->sq_port);
 	if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */
 		kfree_skb(skb);
 		return -ENODEV;
 	}
 
+	cb = (struct qrtr_cb *)skb->cb;
+	cb->src_node = from->sq_node;
+	cb->src_port = from->sq_port;
+
 	if (sock_queue_rcv_skb(&ipc->sk, skb)) {
 		qrtr_port_put(ipc);
 		kfree_skb(skb);
@@ -645,7 +696,9 @@ static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb)
 }
 
 /* Queue packet for broadcast. */
-static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb)
+static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
+			      int type, struct sockaddr_qrtr *from,
+			      struct sockaddr_qrtr *to)
 {
 	struct sk_buff *skbn;
 
@@ -655,11 +708,11 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb)
 		if (!skbn)
 			break;
 		skb_set_owner_w(skbn, skb->sk);
-		qrtr_node_enqueue(node, skbn);
+		qrtr_node_enqueue(node, skbn, type, from, to);
 	}
 	mutex_unlock(&qrtr_node_lock);
 
-	qrtr_local_enqueue(node, skb);
+	qrtr_local_enqueue(node, skb, type, from, to);
 
 	return 0;
 }
@@ -667,13 +720,14 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb)
 static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	DECLARE_SOCKADDR(struct sockaddr_qrtr *, addr, msg->msg_name);
-	int (*enqueue_fn)(struct qrtr_node *, struct sk_buff *);
+	int (*enqueue_fn)(struct qrtr_node *, struct sk_buff *, int,
+			  struct sockaddr_qrtr *, struct sockaddr_qrtr *);
 	struct qrtr_sock *ipc = qrtr_sk(sock->sk);
 	struct sock *sk = sock->sk;
 	struct qrtr_node *node;
-	struct qrtr_hdr *hdr;
 	struct sk_buff *skb;
 	size_t plen;
+	u32 type = QRTR_TYPE_DATA;
 	int rc;
 
 	if (msg->msg_flags & ~(MSG_DONTWAIT))
@@ -722,37 +776,19 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	}
 
 	plen = (len + 3) & ~3;
-	skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_SIZE,
+	skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_MAX_SIZE,
 				  msg->msg_flags & MSG_DONTWAIT, &rc);
 	if (!skb)
 		goto out_node;
 
-	skb_reset_transport_header(skb);
-	skb_put(skb, len + QRTR_HDR_SIZE);
-
-	hdr = (struct qrtr_hdr *)skb_transport_header(skb);
-	hdr->version = cpu_to_le32(QRTR_PROTO_VER);
-	hdr->src_node_id = cpu_to_le32(ipc->us.sq_node);
-	hdr->src_port_id = cpu_to_le32(ipc->us.sq_port);
-	hdr->confirm_rx = cpu_to_le32(0);
-	hdr->size = cpu_to_le32(len);
-	hdr->dst_node_id = cpu_to_le32(addr->sq_node);
-	hdr->dst_port_id = cpu_to_le32(addr->sq_port);
+	skb_reserve(skb, QRTR_HDR_MAX_SIZE);
 
-	rc = skb_copy_datagram_from_iter(skb, QRTR_HDR_SIZE,
-					 &msg->msg_iter, len);
+	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc) {
 		kfree_skb(skb);
 		goto out_node;
 	}
 
-	if (plen != len) {
-		rc = skb_pad(skb, plen - len);
-		if (rc)
-			goto out_node;
-		skb_put(skb, plen - len);
-	}
-
 	if (ipc->us.sq_port == QRTR_PORT_CTRL) {
 		if (len < 4) {
 			rc = -EINVAL;
@@ -761,12 +797,11 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		}
 
 		/* control messages already require the type as 'command' */
-		skb_copy_bits(skb, QRTR_HDR_SIZE, &hdr->type, 4);
-	} else {
-		hdr->type = cpu_to_le32(QRTR_TYPE_DATA);
+		skb_copy_bits(skb, 0, &type, 4);
+		type = le32_to_cpu(type);
 	}
 
-	rc = enqueue_fn(node, skb);
+	rc = enqueue_fn(node, skb, type, &ipc->us, addr);
 	if (rc >= 0)
 		rc = len;
 
@@ -781,9 +816,9 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg,
 			size_t size, int flags)
 {
 	DECLARE_SOCKADDR(struct sockaddr_qrtr *, addr, msg->msg_name);
-	const struct qrtr_hdr *phdr;
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
+	struct qrtr_cb *cb;
 	int copied, rc;
 
 	lock_sock(sk);
@@ -800,22 +835,22 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg,
 		return rc;
 	}
 
-	phdr = (const struct qrtr_hdr *)skb_transport_header(skb);
-	copied = le32_to_cpu(phdr->size);
+	copied = skb->len;
 	if (copied > size) {
 		copied = size;
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	rc = skb_copy_datagram_msg(skb, QRTR_HDR_SIZE, msg, copied);
+	rc = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (rc < 0)
 		goto out;
 	rc = copied;
 
 	if (addr) {
+		cb = (struct qrtr_cb *)skb->cb;
 		addr->sq_family = AF_QIPCRTR;
-		addr->sq_node = le32_to_cpu(phdr->src_node_id);
-		addr->sq_port = le32_to_cpu(phdr->src_port_id);
+		addr->sq_node = cb->src_node;
+		addr->sq_port = cb->src_port;
 		msg->msg_namelen = sizeof(*addr);
 	}
 
@@ -908,7 +943,7 @@ static int qrtr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	case TIOCINQ:
 		skb = skb_peek(&sk->sk_receive_queue);
 		if (skb)
-			len = skb->len - QRTR_HDR_SIZE;
+			len = skb->len;
 		rc = put_user(len, (int __user *)argp);
 		break;
 	case SIOCGIFADDR:
diff --git a/net/rds/ib.c b/net/rds/ib.c
index a0954ace3774..36dd2099048a 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -126,6 +126,7 @@ void rds_ib_dev_put(struct rds_ib_device *rds_ibdev)
 static void rds_ib_add_one(struct ib_device *device)
 {
 	struct rds_ib_device *rds_ibdev;
+	bool has_fr, has_fmr;
 
 	/* Only handle IB (no iWARP) devices */
 	if (device->node_type != RDMA_NODE_IB_CA)
@@ -143,11 +144,11 @@ static void rds_ib_add_one(struct ib_device *device)
 	rds_ibdev->max_wrs = device->attrs.max_qp_wr;
 	rds_ibdev->max_sge = min(device->attrs.max_sge, RDS_IB_MAX_SGE);
 
-	rds_ibdev->has_fr = (device->attrs.device_cap_flags &
-				  IB_DEVICE_MEM_MGT_EXTENSIONS);
-	rds_ibdev->has_fmr = (device->alloc_fmr && device->dealloc_fmr &&
-			    device->map_phys_fmr && device->unmap_fmr);
-	rds_ibdev->use_fastreg = (rds_ibdev->has_fr && !rds_ibdev->has_fmr);
+	has_fr = (device->attrs.device_cap_flags &
+		  IB_DEVICE_MEM_MGT_EXTENSIONS);
+	has_fmr = (device->alloc_fmr && device->dealloc_fmr &&
+		   device->map_phys_fmr && device->unmap_fmr);
+	rds_ibdev->use_fastreg = (has_fr && !has_fmr);
 
 	rds_ibdev->fmr_max_remaps = device->attrs.max_map_per_fmr?: 32;
 	rds_ibdev->max_1m_mrs = device->attrs.max_mr ?
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 86a8578d95b8..a6f4d7d68e95 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -216,8 +216,6 @@ struct rds_ib_device {
 	struct list_head	conn_list;
 	struct ib_device	*dev;
 	struct ib_pd		*pd;
-	bool                    has_fmr;
-	bool                    has_fr;
 	bool                    use_fastreg;
 
 	unsigned int		max_mrs;
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 9a3c54e659e9..e678699268a2 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -601,11 +601,11 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev,
 	if (pool_type == RDS_IB_MR_1M_POOL) {
 		/* +1 allows for unaligned MRs */
 		pool->fmr_attr.max_pages = RDS_MR_1M_MSG_SIZE + 1;
-		pool->max_items = RDS_MR_1M_POOL_SIZE;
+		pool->max_items = rds_ibdev->max_1m_mrs;
 	} else {
 		/* pool_type == RDS_IB_MR_8K_POOL */
 		pool->fmr_attr.max_pages = RDS_MR_8K_MSG_SIZE + 1;
-		pool->max_items = RDS_MR_8K_POOL_SIZE;
+		pool->max_items = rds_ibdev->max_8k_mrs;
 	}
 
 	pool->max_free_pinned = pool->max_items * pool->fmr_attr.max_pages / 4;
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 4a9729257023..6a5c4992cf61 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -318,9 +318,11 @@ void rose_destroy_socket(struct sock *);
 /*
  *	Handler for deferred kills.
  */
-static void rose_destroy_timer(unsigned long data)
+static void rose_destroy_timer(struct timer_list *t)
 {
-	rose_destroy_socket((struct sock *)data);
+	struct sock *sk = from_timer(sk, t, sk_timer);
+
+	rose_destroy_socket(sk);
 }
 
 /*
@@ -353,8 +355,7 @@ void rose_destroy_socket(struct sock *sk)
 
 	if (sk_has_allocations(sk)) {
 		/* Defer: outstanding buffers */
-		setup_timer(&sk->sk_timer, rose_destroy_timer,
-				(unsigned long)sk);
+		timer_setup(&sk->sk_timer, rose_destroy_timer, 0);
 		sk->sk_timer.expires  = jiffies + 10 * HZ;
 		add_timer(&sk->sk_timer);
 	} else
@@ -538,8 +539,8 @@ static int rose_create(struct net *net, struct socket *sock, int protocol,
 	sock->ops    = &rose_proto_ops;
 	sk->sk_protocol = protocol;
 
-	init_timer(&rose->timer);
-	init_timer(&rose->idletimer);
+	timer_setup(&rose->timer, NULL, 0);
+	timer_setup(&rose->idletimer, NULL, 0);
 
 	rose->t1   = msecs_to_jiffies(sysctl_rose_call_request_timeout);
 	rose->t2   = msecs_to_jiffies(sysctl_rose_reset_request_timeout);
@@ -582,8 +583,8 @@ static struct sock *rose_make_new(struct sock *osk)
 	sk->sk_state    = TCP_ESTABLISHED;
 	sock_copy_flags(sk, osk);
 
-	init_timer(&rose->timer);
-	init_timer(&rose->idletimer);
+	timer_setup(&rose->timer, NULL, 0);
+	timer_setup(&rose->idletimer, NULL, 0);
 
 	orose		= rose_sk(osk);
 	rose->t1	= orose->t1;
diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c
index 0a6394754e81..9bbbfe325c5a 100644
--- a/net/rose/rose_in.c
+++ b/net/rose/rose_in.c
@@ -219,6 +219,7 @@ static int rose_state4_machine(struct sock *sk, struct sk_buff *skb, int framety
 	switch (frametype) {
 	case ROSE_RESET_REQUEST:
 		rose_write_internal(sk, ROSE_RESET_CONFIRMATION);
+		/* fall through */
 	case ROSE_RESET_CONFIRMATION:
 		rose_stop_timer(sk);
 		rose_start_idletimer(sk);
diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c
index c76638cc2cd5..cda4c6678ef1 100644
--- a/net/rose/rose_link.c
+++ b/net/rose/rose_link.c
@@ -27,8 +27,8 @@
 #include <linux/interrupt.h>
 #include <net/rose.h>
 
-static void rose_ftimer_expiry(unsigned long);
-static void rose_t0timer_expiry(unsigned long);
+static void rose_ftimer_expiry(struct timer_list *);
+static void rose_t0timer_expiry(struct timer_list *);
 
 static void rose_transmit_restart_confirmation(struct rose_neigh *neigh);
 static void rose_transmit_restart_request(struct rose_neigh *neigh);
@@ -37,8 +37,7 @@ void rose_start_ftimer(struct rose_neigh *neigh)
 {
 	del_timer(&neigh->ftimer);
 
-	neigh->ftimer.data     = (unsigned long)neigh;
-	neigh->ftimer.function = &rose_ftimer_expiry;
+	neigh->ftimer.function = (TIMER_FUNC_TYPE)rose_ftimer_expiry;
 	neigh->ftimer.expires  =
 		jiffies + msecs_to_jiffies(sysctl_rose_link_fail_timeout);
 
@@ -49,8 +48,7 @@ static void rose_start_t0timer(struct rose_neigh *neigh)
 {
 	del_timer(&neigh->t0timer);
 
-	neigh->t0timer.data     = (unsigned long)neigh;
-	neigh->t0timer.function = &rose_t0timer_expiry;
+	neigh->t0timer.function = (TIMER_FUNC_TYPE)rose_t0timer_expiry;
 	neigh->t0timer.expires  =
 		jiffies + msecs_to_jiffies(sysctl_rose_restart_request_timeout);
 
@@ -77,13 +75,13 @@ static int rose_t0timer_running(struct rose_neigh *neigh)
 	return timer_pending(&neigh->t0timer);
 }
 
-static void rose_ftimer_expiry(unsigned long param)
+static void rose_ftimer_expiry(struct timer_list *t)
 {
 }
 
-static void rose_t0timer_expiry(unsigned long param)
+static void rose_t0timer_expiry(struct timer_list *t)
 {
-	struct rose_neigh *neigh = (struct rose_neigh *)param;
+	struct rose_neigh *neigh = from_timer(neigh, t, t0timer);
 
 	rose_transmit_restart_request(neigh);
 
diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c
index 344456206b70..7af4f99c4a93 100644
--- a/net/rose/rose_loopback.c
+++ b/net/rose/rose_loopback.c
@@ -19,12 +19,13 @@ static struct sk_buff_head loopback_queue;
 static struct timer_list loopback_timer;
 
 static void rose_set_loopback_timer(void);
+static void rose_loopback_timer(struct timer_list *unused);
 
 void rose_loopback_init(void)
 {
 	skb_queue_head_init(&loopback_queue);
 
-	init_timer(&loopback_timer);
+	timer_setup(&loopback_timer, rose_loopback_timer, 0);
 }
 
 static int rose_loopback_running(void)
@@ -50,20 +51,16 @@ int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh)
 	return 1;
 }
 
-static void rose_loopback_timer(unsigned long);
 
 static void rose_set_loopback_timer(void)
 {
 	del_timer(&loopback_timer);
 
-	loopback_timer.data     = 0;
-	loopback_timer.function = &rose_loopback_timer;
 	loopback_timer.expires  = jiffies + 10;
-
 	add_timer(&loopback_timer);
 }
 
-static void rose_loopback_timer(unsigned long param)
+static void rose_loopback_timer(struct timer_list *unused)
 {
 	struct sk_buff *skb;
 	struct net_device *dev;
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index 452bbb38d943..8ca3124df83f 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -104,8 +104,8 @@ static int __must_check rose_add_node(struct rose_route_struct *rose_route,
 
 		skb_queue_head_init(&rose_neigh->queue);
 
-		init_timer(&rose_neigh->ftimer);
-		init_timer(&rose_neigh->t0timer);
+		timer_setup(&rose_neigh->ftimer, NULL, 0);
+		timer_setup(&rose_neigh->t0timer, NULL, 0);
 
 		if (rose_route->ndigis != 0) {
 			rose_neigh->digipeat =
@@ -346,6 +346,7 @@ static int rose_del_node(struct rose_route_struct *rose_route,
 				case 0:
 					rose_node->neighbour[0] =
 						rose_node->neighbour[1];
+					/* fall through */
 				case 1:
 					rose_node->neighbour[1] =
 						rose_node->neighbour[2];
@@ -390,8 +391,8 @@ void rose_add_loopback_neigh(void)
 
 	skb_queue_head_init(&sn->queue);
 
-	init_timer(&sn->ftimer);
-	init_timer(&sn->t0timer);
+	timer_setup(&sn->ftimer, NULL, 0);
+	timer_setup(&sn->t0timer, NULL, 0);
 
 	spin_lock_bh(&rose_neigh_list_lock);
 	sn->next = rose_neigh_list;
@@ -507,6 +508,7 @@ void rose_rt_device_down(struct net_device *dev)
 				switch (i) {
 				case 0:
 					t->neighbour[0] = t->neighbour[1];
+					/* fall through */
 				case 1:
 					t->neighbour[1] = t->neighbour[2];
 				case 2:
diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c
index bc5469d6d9cb..ea613b2a9735 100644
--- a/net/rose/rose_timer.c
+++ b/net/rose/rose_timer.c
@@ -28,16 +28,15 @@
 #include <linux/interrupt.h>
 #include <net/rose.h>
 
-static void rose_heartbeat_expiry(unsigned long);
-static void rose_timer_expiry(unsigned long);
-static void rose_idletimer_expiry(unsigned long);
+static void rose_heartbeat_expiry(struct timer_list *t);
+static void rose_timer_expiry(struct timer_list *);
+static void rose_idletimer_expiry(struct timer_list *);
 
 void rose_start_heartbeat(struct sock *sk)
 {
 	del_timer(&sk->sk_timer);
 
-	sk->sk_timer.data     = (unsigned long)sk;
-	sk->sk_timer.function = &rose_heartbeat_expiry;
+	sk->sk_timer.function = (TIMER_FUNC_TYPE)rose_heartbeat_expiry;
 	sk->sk_timer.expires  = jiffies + 5 * HZ;
 
 	add_timer(&sk->sk_timer);
@@ -49,8 +48,7 @@ void rose_start_t1timer(struct sock *sk)
 
 	del_timer(&rose->timer);
 
-	rose->timer.data     = (unsigned long)sk;
-	rose->timer.function = &rose_timer_expiry;
+	rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry;
 	rose->timer.expires  = jiffies + rose->t1;
 
 	add_timer(&rose->timer);
@@ -62,8 +60,7 @@ void rose_start_t2timer(struct sock *sk)
 
 	del_timer(&rose->timer);
 
-	rose->timer.data     = (unsigned long)sk;
-	rose->timer.function = &rose_timer_expiry;
+	rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry;
 	rose->timer.expires  = jiffies + rose->t2;
 
 	add_timer(&rose->timer);
@@ -75,8 +72,7 @@ void rose_start_t3timer(struct sock *sk)
 
 	del_timer(&rose->timer);
 
-	rose->timer.data     = (unsigned long)sk;
-	rose->timer.function = &rose_timer_expiry;
+	rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry;
 	rose->timer.expires  = jiffies + rose->t3;
 
 	add_timer(&rose->timer);
@@ -88,8 +84,7 @@ void rose_start_hbtimer(struct sock *sk)
 
 	del_timer(&rose->timer);
 
-	rose->timer.data     = (unsigned long)sk;
-	rose->timer.function = &rose_timer_expiry;
+	rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry;
 	rose->timer.expires  = jiffies + rose->hb;
 
 	add_timer(&rose->timer);
@@ -102,8 +97,7 @@ void rose_start_idletimer(struct sock *sk)
 	del_timer(&rose->idletimer);
 
 	if (rose->idle > 0) {
-		rose->idletimer.data     = (unsigned long)sk;
-		rose->idletimer.function = &rose_idletimer_expiry;
+		rose->idletimer.function = (TIMER_FUNC_TYPE)rose_idletimer_expiry;
 		rose->idletimer.expires  = jiffies + rose->idle;
 
 		add_timer(&rose->idletimer);
@@ -125,9 +119,9 @@ void rose_stop_idletimer(struct sock *sk)
 	del_timer(&rose_sk(sk)->idletimer);
 }
 
-static void rose_heartbeat_expiry(unsigned long param)
+static void rose_heartbeat_expiry(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)param;
+	struct sock *sk = from_timer(sk, t, sk_timer);
 	struct rose_sock *rose = rose_sk(sk);
 
 	bh_lock_sock(sk);
@@ -163,10 +157,10 @@ static void rose_heartbeat_expiry(unsigned long param)
 	bh_unlock_sock(sk);
 }
 
-static void rose_timer_expiry(unsigned long param)
+static void rose_timer_expiry(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)param;
-	struct rose_sock *rose = rose_sk(sk);
+	struct rose_sock *rose = from_timer(rose, t, timer);
+	struct sock *sk = &rose->sock;
 
 	bh_lock_sock(sk);
 	switch (rose->state) {
@@ -192,9 +186,10 @@ static void rose_timer_expiry(unsigned long param)
 	bh_unlock_sock(sk);
 }
 
-static void rose_idletimer_expiry(unsigned long param)
+static void rose_idletimer_expiry(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)param;
+	struct rose_sock *rose = from_timer(rose, t, idletimer);
+	struct sock *sk = &rose->sock;
 
 	bh_lock_sock(sk);
 	rose_clear_queues(sk);
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 4b0a8288c98a..344b2dcad52d 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -246,6 +246,7 @@ static int rxrpc_listen(struct socket *sock, int backlog)
 			ret = 0;
 			break;
 		}
+		/* Fall through */
 	default:
 		ret = -EBUSY;
 		break;
@@ -265,6 +266,7 @@ static int rxrpc_listen(struct socket *sock, int backlog)
  * @tx_total_len: Total length of data to transmit during the call (or -1)
  * @gfp: The allocation constraints
  * @notify_rx: Where to send notifications instead of socket queue
+ * @upgrade: Request service upgrade for call
  *
  * Allow a kernel service to begin a call on the nominated socket.  This just
  * sets up all the internal tracking structures and allocates connection and
@@ -279,7 +281,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 					   unsigned long user_call_ID,
 					   s64 tx_total_len,
 					   gfp_t gfp,
-					   rxrpc_notify_rx_t notify_rx)
+					   rxrpc_notify_rx_t notify_rx,
+					   bool upgrade)
 {
 	struct rxrpc_conn_parameters cp;
 	struct rxrpc_call *call;
@@ -304,6 +307,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 	cp.key			= key;
 	cp.security_level	= 0;
 	cp.exclusive		= false;
+	cp.upgrade		= upgrade;
 	cp.service_id		= srx->srx_service;
 	call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, tx_total_len,
 				     gfp);
@@ -338,6 +342,25 @@ void rxrpc_kernel_end_call(struct socket *sock, struct rxrpc_call *call)
 EXPORT_SYMBOL(rxrpc_kernel_end_call);
 
 /**
+ * rxrpc_kernel_check_life - Check to see whether a call is still alive
+ * @sock: The socket the call is on
+ * @call: The call to check
+ *
+ * Allow a kernel service to find out whether a call is still alive - ie. we're
+ * getting ACKs from the server.  Returns a number representing the life state
+ * which can be compared to that returned by a previous call.
+ *
+ * If this is a client call, ping ACKs will be sent to the server to find out
+ * whether it's still responsive and whether the call is still alive on the
+ * server.
+ */
+u32 rxrpc_kernel_check_life(struct socket *sock, struct rxrpc_call *call)
+{
+	return call->acks_latest;
+}
+EXPORT_SYMBOL(rxrpc_kernel_check_life);
+
+/**
  * rxrpc_kernel_check_call - Check a call's state
  * @sock: The socket the call is on
  * @call: The call to check
@@ -538,6 +561,7 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 			m->msg_name = &rx->connect_srx;
 			m->msg_namelen = sizeof(rx->connect_srx);
 		}
+		/* Fall through */
 	case RXRPC_SERVER_BOUND:
 	case RXRPC_SERVER_LISTENING:
 		ret = rxrpc_do_sendmsg(rx, m, len);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index e56e23ed2229..1e37eb1c0c66 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1125,6 +1125,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
 	case RXRPC_PACKET_TYPE_BUSY:
 		if (sp->hdr.flags & RXRPC_CLIENT_INITIATED)
 			goto discard;
+		/* Fall through */
 
 	case RXRPC_PACKET_TYPE_DATA:
 		if (sp->hdr.callNumber == 0)
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 5787f97f5330..d02a99f37f5f 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -411,3 +411,16 @@ void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call,
 	*_srx = call->peer->srx;
 }
 EXPORT_SYMBOL(rxrpc_kernel_get_peer);
+
+/**
+ * rxrpc_kernel_get_rtt - Get a call's peer RTT
+ * @sock: The socket on which the call is in progress.
+ * @call: The call to query
+ *
+ * Get the call's peer RTT.
+ */
+u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call)
+{
+	return call->peer->rtt;
+}
+EXPORT_SYMBOL(rxrpc_kernel_get_rtt);
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index bdece21f313d..e4937b3f3685 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -607,6 +607,7 @@ wait_error:
  * @_offset: The running offset into the buffer.
  * @want_more: True if more data is expected to be read
  * @_abort: Where the abort code is stored if -ECONNABORTED is returned
+ * @_service: Where to store the actual service ID (may be upgraded)
  *
  * Allow a kernel service to receive data and pick up information about the
  * state of a call.  Returns 0 if got what was asked for and there's more
@@ -624,7 +625,7 @@ wait_error:
  */
 int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 			   void *buf, size_t size, size_t *_offset,
-			   bool want_more, u32 *_abort)
+			   bool want_more, u32 *_abort, u16 *_service)
 {
 	struct iov_iter iter;
 	struct kvec iov;
@@ -680,6 +681,8 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 read_phase_complete:
 	ret = 1;
 out:
+	if (_service)
+		*_service = call->service_id;
 	mutex_unlock(&call->user_mutex);
 	_leave(" = %d [%zu,%d]", ret, *_offset, *_abort);
 	return ret;
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 9ea6f972767e..7d2595582c09 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -38,12 +38,86 @@ struct rxrpc_send_params {
 };
 
 /*
+ * Wait for space to appear in the Tx queue or a signal to occur.
+ */
+static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
+					 struct rxrpc_call *call,
+					 long *timeo)
+{
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (call->tx_top - call->tx_hard_ack <
+		    min_t(unsigned int, call->tx_winsize,
+			  call->cong_cwnd + call->cong_extra))
+			return 0;
+
+		if (call->state >= RXRPC_CALL_COMPLETE)
+			return call->error;
+
+		if (signal_pending(current))
+			return sock_intr_errno(*timeo);
+
+		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
+		mutex_unlock(&call->user_mutex);
+		*timeo = schedule_timeout(*timeo);
+		if (mutex_lock_interruptible(&call->user_mutex) < 0)
+			return sock_intr_errno(*timeo);
+	}
+}
+
+/*
+ * Wait for space to appear in the Tx queue uninterruptibly, but with
+ * a timeout of 2*RTT if no progress was made and a signal occurred.
+ */
+static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
+					    struct rxrpc_call *call)
+{
+	rxrpc_seq_t tx_start, tx_win;
+	signed long rtt2, timeout;
+	u64 rtt;
+
+	rtt = READ_ONCE(call->peer->rtt);
+	rtt2 = nsecs_to_jiffies64(rtt) * 2;
+	if (rtt2 < 1)
+		rtt2 = 1;
+
+	timeout = rtt2;
+	tx_start = READ_ONCE(call->tx_hard_ack);
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+
+		tx_win = READ_ONCE(call->tx_hard_ack);
+		if (call->tx_top - tx_win <
+		    min_t(unsigned int, call->tx_winsize,
+			  call->cong_cwnd + call->cong_extra))
+			return 0;
+
+		if (call->state >= RXRPC_CALL_COMPLETE)
+			return call->error;
+
+		if (timeout == 0 &&
+		    tx_win == tx_start && signal_pending(current))
+			return -EINTR;
+
+		if (tx_win != tx_start) {
+			timeout = rtt2;
+			tx_start = tx_win;
+		}
+
+		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
+		timeout = schedule_timeout(timeout);
+	}
+}
+
+/*
  * wait for space to appear in the transmit/ACK window
  * - caller holds the socket locked
  */
 static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
 				    struct rxrpc_call *call,
-				    long *timeo)
+				    long *timeo,
+				    bool waitall)
 {
 	DECLARE_WAITQUEUE(myself, current);
 	int ret;
@@ -53,30 +127,10 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
 
 	add_wait_queue(&call->waitq, &myself);
 
-	for (;;) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		ret = 0;
-		if (call->tx_top - call->tx_hard_ack <
-		    min_t(unsigned int, call->tx_winsize,
-			  call->cong_cwnd + call->cong_extra))
-			break;
-		if (call->state >= RXRPC_CALL_COMPLETE) {
-			ret = call->error;
-			break;
-		}
-		if (signal_pending(current)) {
-			ret = sock_intr_errno(*timeo);
-			break;
-		}
-
-		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
-		mutex_unlock(&call->user_mutex);
-		*timeo = schedule_timeout(*timeo);
-		if (mutex_lock_interruptible(&call->user_mutex) < 0) {
-			ret = sock_intr_errno(*timeo);
-			break;
-		}
-	}
+	if (waitall)
+		ret = rxrpc_wait_for_tx_window_nonintr(rx, call);
+	else
+		ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo);
 
 	remove_wait_queue(&call->waitq, &myself);
 	set_current_state(TASK_RUNNING);
@@ -166,6 +220,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
 					  ktime_get_real());
 			if (!last)
 				break;
+			/* Fall through */
 		case RXRPC_CALL_SERVER_SEND_REPLY:
 			call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
 			rxrpc_notify_end_tx(rx, call, notify_end_tx);
@@ -254,7 +309,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 				if (msg->msg_flags & MSG_DONTWAIT)
 					goto maybe_error;
 				ret = rxrpc_wait_for_tx_window(rx, call,
-							       &timeo);
+							       &timeo,
+							       msg->msg_flags & MSG_WAITALL);
 				if (ret < 0)
 					goto maybe_error;
 			}
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index e70ed26485a2..c03d86a7775e 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -172,6 +172,17 @@ config NET_SCH_TBF
 	  To compile this code as a module, choose M here: the
 	  module will be called sch_tbf.
 
+config NET_SCH_CBS
+	tristate "Credit Based Shaper (CBS)"
+	---help---
+	  Say Y here if you want to use the Credit Based Shaper (CBS) packet
+	  scheduling algorithm.
+
+	  See the top of <file:net/sched/sch_cbs.c> for more details.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called sch_cbs.
+
 config NET_SCH_GRED
 	tristate "Generic Random Early Detection (GRED)"
 	---help---
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 9e43a4721ef8..5b635447e3f8 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -53,6 +53,7 @@ obj-$(CONFIG_NET_SCH_FQ_CODEL)	+= sch_fq_codel.o
 obj-$(CONFIG_NET_SCH_FQ)	+= sch_fq.o
 obj-$(CONFIG_NET_SCH_HHF)	+= sch_hhf.o
 obj-$(CONFIG_NET_SCH_PIE)	+= sch_pie.o
+obj-$(CONFIG_NET_SCH_CBS)	+= sch_cbs.o
 
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index ca2ff0b3123f..ff4d69082376 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -21,6 +21,8 @@
 #include <linux/kmod.h>
 #include <linux/err.h>
 #include <linux/module.h>
+#include <linux/rhashtable.h>
+#include <linux/list.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/sch_generic.h>
@@ -1253,8 +1255,227 @@ out_module_put:
 	return skb->len;
 }
 
+struct tcf_action_net {
+	struct rhashtable egdev_ht;
+};
+
+static unsigned int tcf_action_net_id;
+
+struct tcf_action_egdev_cb {
+	struct list_head list;
+	tc_setup_cb_t *cb;
+	void *cb_priv;
+};
+
+struct tcf_action_egdev {
+	struct rhash_head ht_node;
+	const struct net_device *dev;
+	unsigned int refcnt;
+	struct list_head cb_list;
+};
+
+static const struct rhashtable_params tcf_action_egdev_ht_params = {
+	.key_offset = offsetof(struct tcf_action_egdev, dev),
+	.head_offset = offsetof(struct tcf_action_egdev, ht_node),
+	.key_len = sizeof(const struct net_device *),
+};
+
+static struct tcf_action_egdev *
+tcf_action_egdev_lookup(const struct net_device *dev)
+{
+	struct net *net = dev_net(dev);
+	struct tcf_action_net *tan = net_generic(net, tcf_action_net_id);
+
+	return rhashtable_lookup_fast(&tan->egdev_ht, &dev,
+				      tcf_action_egdev_ht_params);
+}
+
+static struct tcf_action_egdev *
+tcf_action_egdev_get(const struct net_device *dev)
+{
+	struct tcf_action_egdev *egdev;
+	struct tcf_action_net *tan;
+
+	egdev = tcf_action_egdev_lookup(dev);
+	if (egdev)
+		goto inc_ref;
+
+	egdev = kzalloc(sizeof(*egdev), GFP_KERNEL);
+	if (!egdev)
+		return NULL;
+	INIT_LIST_HEAD(&egdev->cb_list);
+	egdev->dev = dev;
+	tan = net_generic(dev_net(dev), tcf_action_net_id);
+	rhashtable_insert_fast(&tan->egdev_ht, &egdev->ht_node,
+			       tcf_action_egdev_ht_params);
+
+inc_ref:
+	egdev->refcnt++;
+	return egdev;
+}
+
+static void tcf_action_egdev_put(struct tcf_action_egdev *egdev)
+{
+	struct tcf_action_net *tan;
+
+	if (--egdev->refcnt)
+		return;
+	tan = net_generic(dev_net(egdev->dev), tcf_action_net_id);
+	rhashtable_remove_fast(&tan->egdev_ht, &egdev->ht_node,
+			       tcf_action_egdev_ht_params);
+	kfree(egdev);
+}
+
+static struct tcf_action_egdev_cb *
+tcf_action_egdev_cb_lookup(struct tcf_action_egdev *egdev,
+			   tc_setup_cb_t *cb, void *cb_priv)
+{
+	struct tcf_action_egdev_cb *egdev_cb;
+
+	list_for_each_entry(egdev_cb, &egdev->cb_list, list)
+		if (egdev_cb->cb == cb && egdev_cb->cb_priv == cb_priv)
+			return egdev_cb;
+	return NULL;
+}
+
+static int tcf_action_egdev_cb_call(struct tcf_action_egdev *egdev,
+				    enum tc_setup_type type,
+				    void *type_data, bool err_stop)
+{
+	struct tcf_action_egdev_cb *egdev_cb;
+	int ok_count = 0;
+	int err;
+
+	list_for_each_entry(egdev_cb, &egdev->cb_list, list) {
+		err = egdev_cb->cb(type, type_data, egdev_cb->cb_priv);
+		if (err) {
+			if (err_stop)
+				return err;
+		} else {
+			ok_count++;
+		}
+	}
+	return ok_count;
+}
+
+static int tcf_action_egdev_cb_add(struct tcf_action_egdev *egdev,
+				   tc_setup_cb_t *cb, void *cb_priv)
+{
+	struct tcf_action_egdev_cb *egdev_cb;
+
+	egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv);
+	if (WARN_ON(egdev_cb))
+		return -EEXIST;
+	egdev_cb = kzalloc(sizeof(*egdev_cb), GFP_KERNEL);
+	if (!egdev_cb)
+		return -ENOMEM;
+	egdev_cb->cb = cb;
+	egdev_cb->cb_priv = cb_priv;
+	list_add(&egdev_cb->list, &egdev->cb_list);
+	return 0;
+}
+
+static void tcf_action_egdev_cb_del(struct tcf_action_egdev *egdev,
+				    tc_setup_cb_t *cb, void *cb_priv)
+{
+	struct tcf_action_egdev_cb *egdev_cb;
+
+	egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv);
+	if (WARN_ON(!egdev_cb))
+		return;
+	list_del(&egdev_cb->list);
+	kfree(egdev_cb);
+}
+
+static int __tc_setup_cb_egdev_register(const struct net_device *dev,
+					tc_setup_cb_t *cb, void *cb_priv)
+{
+	struct tcf_action_egdev *egdev = tcf_action_egdev_get(dev);
+	int err;
+
+	if (!egdev)
+		return -ENOMEM;
+	err = tcf_action_egdev_cb_add(egdev, cb, cb_priv);
+	if (err)
+		goto err_cb_add;
+	return 0;
+
+err_cb_add:
+	tcf_action_egdev_put(egdev);
+	return err;
+}
+int tc_setup_cb_egdev_register(const struct net_device *dev,
+			       tc_setup_cb_t *cb, void *cb_priv)
+{
+	int err;
+
+	rtnl_lock();
+	err = __tc_setup_cb_egdev_register(dev, cb, cb_priv);
+	rtnl_unlock();
+	return err;
+}
+EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_register);
+
+static void __tc_setup_cb_egdev_unregister(const struct net_device *dev,
+					   tc_setup_cb_t *cb, void *cb_priv)
+{
+	struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev);
+
+	if (WARN_ON(!egdev))
+		return;
+	tcf_action_egdev_cb_del(egdev, cb, cb_priv);
+	tcf_action_egdev_put(egdev);
+}
+void tc_setup_cb_egdev_unregister(const struct net_device *dev,
+				  tc_setup_cb_t *cb, void *cb_priv)
+{
+	rtnl_lock();
+	__tc_setup_cb_egdev_unregister(dev, cb, cb_priv);
+	rtnl_unlock();
+}
+EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_unregister);
+
+int tc_setup_cb_egdev_call(const struct net_device *dev,
+			   enum tc_setup_type type, void *type_data,
+			   bool err_stop)
+{
+	struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev);
+
+	if (!egdev)
+		return 0;
+	return tcf_action_egdev_cb_call(egdev, type, type_data, err_stop);
+}
+EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_call);
+
+static __net_init int tcf_action_net_init(struct net *net)
+{
+	struct tcf_action_net *tan = net_generic(net, tcf_action_net_id);
+
+	return rhashtable_init(&tan->egdev_ht, &tcf_action_egdev_ht_params);
+}
+
+static void __net_exit tcf_action_net_exit(struct net *net)
+{
+	struct tcf_action_net *tan = net_generic(net, tcf_action_net_id);
+
+	rhashtable_destroy(&tan->egdev_ht);
+}
+
+static struct pernet_operations tcf_action_net_ops = {
+	.init = tcf_action_net_init,
+	.exit = tcf_action_net_exit,
+	.id = &tcf_action_net_id,
+	.size = sizeof(struct tcf_action_net),
+};
+
 static int __init tc_action_init(void)
 {
+	int err;
+
+	err = register_pernet_subsys(&tcf_action_net_ops);
+	if (err)
+		return err;
+
 	rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action,
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 9bce8cc84cbb..035ed268290b 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -49,11 +49,11 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
 	filter = rcu_dereference(prog->filter);
 	if (at_ingress) {
 		__skb_push(skb, skb->mac_len);
-		bpf_compute_data_end(skb);
+		bpf_compute_data_pointers(skb);
 		filter_res = BPF_PROG_RUN(filter, skb);
 		__skb_pull(skb, skb->mac_len);
 	} else {
-		bpf_compute_data_end(skb);
+		bpf_compute_data_pointers(skb);
 		filter_res = BPF_PROG_RUN(filter, skb);
 	}
 	rcu_read_unlock();
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index f65e4b5058e0..eca272533418 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -248,6 +248,22 @@ static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len)
 	return ret;
 }
 
+#ifdef CONFIG_MODULES
+static const char *ife_meta_id2name(u32 metaid)
+{
+	switch (metaid) {
+	case IFE_META_SKBMARK:
+		return "skbmark";
+	case IFE_META_PRIO:
+		return "skbprio";
+	case IFE_META_TCINDEX:
+		return "tcindex";
+	default:
+		return "unknown";
+	}
+}
+#endif
+
 /* called when adding new meta information
  * under ife->tcf_lock for existing action
 */
@@ -263,7 +279,7 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
 		if (exists)
 			spin_unlock_bh(&ife->tcf_lock);
 		rtnl_unlock();
-		request_module("ifemeta%u", metaid);
+		request_module("ife-meta-%s", ife_meta_id2name(metaid));
 		rtnl_lock();
 		if (exists)
 			spin_lock_bh(&ife->tcf_lock);
@@ -392,10 +408,14 @@ static void _tcf_ife_cleanup(struct tc_action *a, int bind)
 static void tcf_ife_cleanup(struct tc_action *a, int bind)
 {
 	struct tcf_ife_info *ife = to_ife(a);
+	struct tcf_ife_params *p;
 
 	spin_lock_bh(&ife->tcf_lock);
 	_tcf_ife_cleanup(a, bind);
 	spin_unlock_bh(&ife->tcf_lock);
+
+	p = rcu_dereference_protected(ife->params, 1);
+	kfree_rcu(p, rcu);
 }
 
 /* under ife->tcf_lock for existing action */
@@ -432,6 +452,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	struct tc_action_net *tn = net_generic(net, ife_net_id);
 	struct nlattr *tb[TCA_IFE_MAX + 1];
 	struct nlattr *tb2[IFE_META_MAX + 1];
+	struct tcf_ife_params *p, *p_old;
 	struct tcf_ife_info *ife;
 	u16 ife_type = ETH_P_IFE;
 	struct tc_ife *parm;
@@ -450,24 +471,41 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 
 	parm = nla_data(tb[TCA_IFE_PARMS]);
 
+	/* IFE_DECODE is 0 and indicates the opposite of IFE_ENCODE because
+	 * they cannot run as the same time. Check on all other values which
+	 * are not supported right now.
+	 */
+	if (parm->flags & ~IFE_ENCODE)
+		return -EINVAL;
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
 	exists = tcf_idr_check(tn, parm->index, a, bind);
-	if (exists && bind)
+	if (exists && bind) {
+		kfree(p);
 		return 0;
+	}
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops,
-				     bind, false);
-		if (ret)
+				     bind, true);
+		if (ret) {
+			kfree(p);
 			return ret;
+		}
 		ret = ACT_P_CREATED;
 	} else {
 		tcf_idr_release(*a, bind);
-		if (!ovr)
+		if (!ovr) {
+			kfree(p);
 			return -EEXIST;
+		}
 	}
 
 	ife = to_ife(*a);
-	ife->flags = parm->flags;
+	p->flags = parm->flags;
 
 	if (parm->flags & IFE_ENCODE) {
 		if (tb[TCA_IFE_TYPE])
@@ -478,24 +516,25 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 			saddr = nla_data(tb[TCA_IFE_SMAC]);
 	}
 
-	if (exists)
-		spin_lock_bh(&ife->tcf_lock);
 	ife->tcf_action = parm->action;
 
 	if (parm->flags & IFE_ENCODE) {
 		if (daddr)
-			ether_addr_copy(ife->eth_dst, daddr);
+			ether_addr_copy(p->eth_dst, daddr);
 		else
-			eth_zero_addr(ife->eth_dst);
+			eth_zero_addr(p->eth_dst);
 
 		if (saddr)
-			ether_addr_copy(ife->eth_src, saddr);
+			ether_addr_copy(p->eth_src, saddr);
 		else
-			eth_zero_addr(ife->eth_src);
+			eth_zero_addr(p->eth_src);
 
-		ife->eth_type = ife_type;
+		p->eth_type = ife_type;
 	}
 
+	if (exists)
+		spin_lock_bh(&ife->tcf_lock);
+
 	if (ret == ACT_P_CREATED)
 		INIT_LIST_HEAD(&ife->metalist);
 
@@ -511,6 +550,7 @@ metadata_parse_err:
 
 			if (exists)
 				spin_unlock_bh(&ife->tcf_lock);
+			kfree(p);
 			return err;
 		}
 
@@ -531,6 +571,7 @@ metadata_parse_err:
 
 			if (exists)
 				spin_unlock_bh(&ife->tcf_lock);
+			kfree(p);
 			return err;
 		}
 	}
@@ -538,6 +579,11 @@ metadata_parse_err:
 	if (exists)
 		spin_unlock_bh(&ife->tcf_lock);
 
+	p_old = rtnl_dereference(ife->params);
+	rcu_assign_pointer(ife->params, p);
+	if (p_old)
+		kfree_rcu(p_old, rcu);
+
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 
@@ -549,12 +595,13 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 {
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tcf_ife_info *ife = to_ife(a);
+	struct tcf_ife_params *p = rtnl_dereference(ife->params);
 	struct tc_ife opt = {
 		.index = ife->tcf_index,
 		.refcnt = ife->tcf_refcnt - ref,
 		.bindcnt = ife->tcf_bindcnt - bind,
 		.action = ife->tcf_action,
-		.flags = ife->flags,
+		.flags = p->flags,
 	};
 	struct tcf_t t;
 
@@ -565,17 +612,17 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD))
 		goto nla_put_failure;
 
-	if (!is_zero_ether_addr(ife->eth_dst)) {
-		if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, ife->eth_dst))
+	if (!is_zero_ether_addr(p->eth_dst)) {
+		if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, p->eth_dst))
 			goto nla_put_failure;
 	}
 
-	if (!is_zero_ether_addr(ife->eth_src)) {
-		if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, ife->eth_src))
+	if (!is_zero_ether_addr(p->eth_src)) {
+		if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, p->eth_src))
 			goto nla_put_failure;
 	}
 
-	if (nla_put(skb, TCA_IFE_TYPE, 2, &ife->eth_type))
+	if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type))
 		goto nla_put_failure;
 
 	if (dump_metalist(skb, ife)) {
@@ -617,19 +664,15 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 	u8 *tlv_data;
 	u16 metalen;
 
-	spin_lock(&ife->tcf_lock);
-	bstats_update(&ife->tcf_bstats, skb);
+	bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb);
 	tcf_lastuse_update(&ife->tcf_tm);
-	spin_unlock(&ife->tcf_lock);
 
 	if (skb_at_tc_ingress(skb))
 		skb_push(skb, skb->dev->hard_header_len);
 
 	tlv_data = ife_decode(skb, &metalen);
 	if (unlikely(!tlv_data)) {
-		spin_lock(&ife->tcf_lock);
-		ife->tcf_qstats.drops++;
-		spin_unlock(&ife->tcf_lock);
+		qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
 		return TC_ACT_SHOT;
 	}
 
@@ -647,14 +690,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 			 */
 			pr_info_ratelimited("Unknown metaid %d dlen %d\n",
 					    mtype, dlen);
-			ife->tcf_qstats.overlimits++;
+			qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats));
 		}
 	}
 
 	if (WARN_ON(tlv_data != ifehdr_end)) {
-		spin_lock(&ife->tcf_lock);
-		ife->tcf_qstats.drops++;
-		spin_unlock(&ife->tcf_lock);
+		qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
 		return TC_ACT_SHOT;
 	}
 
@@ -683,7 +724,7 @@ static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife)
 }
 
 static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
-			  struct tcf_result *res)
+			  struct tcf_result *res, struct tcf_ife_params *p)
 {
 	struct tcf_ife_info *ife = to_ife(a);
 	int action = ife->tcf_action;
@@ -706,23 +747,20 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
 			exceed_mtu = true;
 	}
 
-	spin_lock(&ife->tcf_lock);
-	bstats_update(&ife->tcf_bstats, skb);
+	bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb);
 	tcf_lastuse_update(&ife->tcf_tm);
 
 	if (!metalen) {		/* no metadata to send */
 		/* abuse overlimits to count when we allow packet
 		 * with no metadata
 		 */
-		ife->tcf_qstats.overlimits++;
-		spin_unlock(&ife->tcf_lock);
+		qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats));
 		return action;
 	}
 	/* could be stupid policy setup or mtu config
 	 * so lets be conservative.. */
 	if ((action == TC_ACT_SHOT) || exceed_mtu) {
-		ife->tcf_qstats.drops++;
-		spin_unlock(&ife->tcf_lock);
+		qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
 		return TC_ACT_SHOT;
 	}
 
@@ -731,6 +769,8 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
 
 	ife_meta = ife_encode(skb, metalen);
 
+	spin_lock(&ife->tcf_lock);
+
 	/* XXX: we dont have a clever way of telling encode to
 	 * not repeat some of the computations that are done by
 	 * ops->presence_check...
@@ -742,25 +782,24 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
 		}
 		if (err < 0) {
 			/* too corrupt to keep around if overwritten */
-			ife->tcf_qstats.drops++;
 			spin_unlock(&ife->tcf_lock);
+			qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
 			return TC_ACT_SHOT;
 		}
 		skboff += err;
 	}
+	spin_unlock(&ife->tcf_lock);
 	oethh = (struct ethhdr *)skb->data;
 
-	if (!is_zero_ether_addr(ife->eth_src))
-		ether_addr_copy(oethh->h_source, ife->eth_src);
-	if (!is_zero_ether_addr(ife->eth_dst))
-		ether_addr_copy(oethh->h_dest, ife->eth_dst);
-	oethh->h_proto = htons(ife->eth_type);
+	if (!is_zero_ether_addr(p->eth_src))
+		ether_addr_copy(oethh->h_source, p->eth_src);
+	if (!is_zero_ether_addr(p->eth_dst))
+		ether_addr_copy(oethh->h_dest, p->eth_dst);
+	oethh->h_proto = htons(p->eth_type);
 
 	if (skb_at_tc_ingress(skb))
 		skb_pull(skb, skb->dev->hard_header_len);
 
-	spin_unlock(&ife->tcf_lock);
-
 	return action;
 }
 
@@ -768,21 +807,19 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a,
 		       struct tcf_result *res)
 {
 	struct tcf_ife_info *ife = to_ife(a);
+	struct tcf_ife_params *p;
+	int ret;
+
+	rcu_read_lock();
+	p = rcu_dereference(ife->params);
+	if (p->flags & IFE_ENCODE) {
+		ret = tcf_ife_encode(skb, a, res, p);
+		rcu_read_unlock();
+		return ret;
+	}
+	rcu_read_unlock();
 
-	if (ife->flags & IFE_ENCODE)
-		return tcf_ife_encode(skb, a, res);
-
-	if (!(ife->flags & IFE_ENCODE))
-		return tcf_ife_decode(skb, a, res);
-
-	pr_info_ratelimited("unknown failure(policy neither de/encode\n");
-	spin_lock(&ife->tcf_lock);
-	bstats_update(&ife->tcf_bstats, skb);
-	tcf_lastuse_update(&ife->tcf_tm);
-	ife->tcf_qstats.drops++;
-	spin_unlock(&ife->tcf_lock);
-
-	return TC_ACT_SHOT;
+	return tcf_ife_decode(skb, a, res);
 }
 
 static int tcf_ife_walker(struct net *net, struct sk_buff *skb,
diff --git a/net/sched/act_meta_mark.c b/net/sched/act_meta_mark.c
index 82892170ce4f..1e3f10e5da99 100644
--- a/net/sched/act_meta_mark.c
+++ b/net/sched/act_meta_mark.c
@@ -76,4 +76,4 @@ module_exit(ifemark_cleanup_module);
 MODULE_AUTHOR("Jamal Hadi Salim(2015)");
 MODULE_DESCRIPTION("Inter-FE skb mark metadata module");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS_IFE_META(IFE_META_SKBMARK);
+MODULE_ALIAS_IFE_META("skbmark");
diff --git a/net/sched/act_meta_skbprio.c b/net/sched/act_meta_skbprio.c
index 26bf4d86030b..4033f9fc4d4a 100644
--- a/net/sched/act_meta_skbprio.c
+++ b/net/sched/act_meta_skbprio.c
@@ -73,4 +73,4 @@ module_exit(ifeprio_cleanup_module);
 MODULE_AUTHOR("Jamal Hadi Salim(2015)");
 MODULE_DESCRIPTION("Inter-FE skb prio metadata action");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS_IFE_META(IFE_META_PRIO);
+MODULE_ALIAS_IFE_META("skbprio");
diff --git a/net/sched/act_meta_skbtcindex.c b/net/sched/act_meta_skbtcindex.c
index 3b35774ce890..2ea1f26c9e96 100644
--- a/net/sched/act_meta_skbtcindex.c
+++ b/net/sched/act_meta_skbtcindex.c
@@ -76,4 +76,4 @@ module_exit(ifetc_index_cleanup_module);
 MODULE_AUTHOR("Jamal Hadi Salim(2016)");
 MODULE_DESCRIPTION("Inter-FE skb tc_index metadata module");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS_IFE_META(IFE_META_SKBTCINDEX);
+MODULE_ALIAS_IFE_META("tcindex");
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 84759cfd5a33..8df5775bbf22 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -140,6 +140,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	m->tcfm_eaction = parm->eaction;
 	if (dev != NULL) {
 		m->tcfm_ifindex = parm->ifindex;
+		m->net = net;
 		if (ret != ACT_P_CREATED)
 			dev_put(rcu_dereference_protected(m->tcfm_dev, 1));
 		dev_hold(dev);
@@ -313,15 +314,11 @@ static struct notifier_block mirred_device_notifier = {
 	.notifier_call = mirred_device_event,
 };
 
-static int tcf_mirred_device(const struct tc_action *a, struct net *net,
-			     struct net_device **mirred_dev)
+static struct net_device *tcf_mirred_get_dev(const struct tc_action *a)
 {
-	int ifindex = tcf_mirred_ifindex(a);
+	struct tcf_mirred *m = to_mirred(a);
 
-	*mirred_dev = __dev_get_by_index(net, ifindex);
-	if (!*mirred_dev)
-		return -EINVAL;
-	return 0;
+	return __dev_get_by_index(m->net, m->tcfm_ifindex);
 }
 
 static struct tc_action_ops act_mirred_ops = {
@@ -336,7 +333,7 @@ static struct tc_action_ops act_mirred_ops = {
 	.walk		=	tcf_mirred_walker,
 	.lookup		=	tcf_mirred_search,
 	.size		=	sizeof(struct tcf_mirred),
-	.get_dev	=	tcf_mirred_device,
+	.get_dev	=	tcf_mirred_get_dev,
 };
 
 static __net_init int mirred_init_net(struct net *net)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index b2d310745487..206e19f4fc01 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -195,12 +195,19 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
 	return chain;
 }
 
+static void tcf_chain_head_change(struct tcf_chain *chain,
+				  struct tcf_proto *tp_head)
+{
+	if (chain->chain_head_change)
+		chain->chain_head_change(tp_head,
+					 chain->chain_head_change_priv);
+}
+
 static void tcf_chain_flush(struct tcf_chain *chain)
 {
 	struct tcf_proto *tp;
 
-	if (chain->p_filter_chain)
-		RCU_INIT_POINTER(*chain->p_filter_chain, NULL);
+	tcf_chain_head_change(chain, NULL);
 	while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) {
 		RCU_INIT_POINTER(chain->filter_chain, tp->next);
 		tcf_chain_put(chain);
@@ -242,15 +249,35 @@ void tcf_chain_put(struct tcf_chain *chain)
 }
 EXPORT_SYMBOL(tcf_chain_put);
 
-static void
-tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain,
-			       struct tcf_proto __rcu **p_filter_chain)
+static void tcf_block_offload_cmd(struct tcf_block *block, struct Qdisc *q,
+				  struct tcf_block_ext_info *ei,
+				  enum tc_block_command command)
 {
-	chain->p_filter_chain = p_filter_chain;
+	struct net_device *dev = q->dev_queue->dev;
+	struct tc_block_offload bo = {};
+
+	if (!dev->netdev_ops->ndo_setup_tc)
+		return;
+	bo.command = command;
+	bo.binder_type = ei->binder_type;
+	bo.block = block;
+	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
 }
 
-int tcf_block_get(struct tcf_block **p_block,
-		  struct tcf_proto __rcu **p_filter_chain)
+static void tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
+				   struct tcf_block_ext_info *ei)
+{
+	tcf_block_offload_cmd(block, q, ei, TC_BLOCK_BIND);
+}
+
+static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
+				     struct tcf_block_ext_info *ei)
+{
+	tcf_block_offload_cmd(block, q, ei, TC_BLOCK_UNBIND);
+}
+
+int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
+		      struct tcf_block_ext_info *ei)
 {
 	struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
 	struct tcf_chain *chain;
@@ -259,13 +286,20 @@ int tcf_block_get(struct tcf_block **p_block,
 	if (!block)
 		return -ENOMEM;
 	INIT_LIST_HEAD(&block->chain_list);
+	INIT_LIST_HEAD(&block->cb_list);
+
 	/* Create chain 0 by default, it has to be always present. */
 	chain = tcf_chain_create(block, 0);
 	if (!chain) {
 		err = -ENOMEM;
 		goto err_chain_create;
 	}
-	tcf_chain_filter_chain_ptr_set(chain, p_filter_chain);
+	WARN_ON(!ei->chain_head_change);
+	chain->chain_head_change = ei->chain_head_change;
+	chain->chain_head_change_priv = ei->chain_head_change_priv;
+	block->net = qdisc_net(q);
+	block->q = q;
+	tcf_block_offload_bind(block, q, ei);
 	*p_block = block;
 	return 0;
 
@@ -273,6 +307,26 @@ err_chain_create:
 	kfree(block);
 	return err;
 }
+EXPORT_SYMBOL(tcf_block_get_ext);
+
+static void tcf_chain_head_change_dflt(struct tcf_proto *tp_head, void *priv)
+{
+	struct tcf_proto __rcu **p_filter_chain = priv;
+
+	rcu_assign_pointer(*p_filter_chain, tp_head);
+}
+
+int tcf_block_get(struct tcf_block **p_block,
+		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q)
+{
+	struct tcf_block_ext_info ei = {
+		.chain_head_change = tcf_chain_head_change_dflt,
+		.chain_head_change_priv = p_filter_chain,
+	};
+
+	WARN_ON(!p_filter_chain);
+	return tcf_block_get_ext(p_block, q, &ei);
+}
 EXPORT_SYMBOL(tcf_block_get);
 
 static void tcf_block_put_final(struct work_struct *work)
@@ -292,25 +346,140 @@ static void tcf_block_put_final(struct work_struct *work)
  * actions should be all removed after flushing. However, filters are now
  * destroyed in tc filter workqueue with RTNL lock, they can not race here.
  */
-void tcf_block_put(struct tcf_block *block)
+void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
+		       struct tcf_block_ext_info *ei)
 {
 	struct tcf_chain *chain, *tmp;
 
-	if (!block)
-		return;
-
 	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
 		tcf_chain_flush(chain);
 
+	tcf_block_offload_unbind(block, q, ei);
+
 	INIT_WORK(&block->work, tcf_block_put_final);
-	/* Wait for RCU callbacks to release the reference count and make
-	 * sure their works have been queued before this.
+	/* Wait for existing RCU callbacks to cool down, make sure their works
+	 * have been queued before this. We can not flush pending works here
+	 * because we are holding the RTNL lock.
 	 */
 	rcu_barrier();
 	tcf_queue_work(&block->work);
 }
+EXPORT_SYMBOL(tcf_block_put_ext);
+
+void tcf_block_put(struct tcf_block *block)
+{
+	struct tcf_block_ext_info ei = {0, };
+
+	if (!block)
+		return;
+	tcf_block_put_ext(block, block->q, &ei);
+}
+
 EXPORT_SYMBOL(tcf_block_put);
 
+struct tcf_block_cb {
+	struct list_head list;
+	tc_setup_cb_t *cb;
+	void *cb_ident;
+	void *cb_priv;
+	unsigned int refcnt;
+};
+
+void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
+{
+	return block_cb->cb_priv;
+}
+EXPORT_SYMBOL(tcf_block_cb_priv);
+
+struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
+					 tc_setup_cb_t *cb, void *cb_ident)
+{	struct tcf_block_cb *block_cb;
+
+	list_for_each_entry(block_cb, &block->cb_list, list)
+		if (block_cb->cb == cb && block_cb->cb_ident == cb_ident)
+			return block_cb;
+	return NULL;
+}
+EXPORT_SYMBOL(tcf_block_cb_lookup);
+
+void tcf_block_cb_incref(struct tcf_block_cb *block_cb)
+{
+	block_cb->refcnt++;
+}
+EXPORT_SYMBOL(tcf_block_cb_incref);
+
+unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
+{
+	return --block_cb->refcnt;
+}
+EXPORT_SYMBOL(tcf_block_cb_decref);
+
+struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
+					     tc_setup_cb_t *cb, void *cb_ident,
+					     void *cb_priv)
+{
+	struct tcf_block_cb *block_cb;
+
+	block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
+	if (!block_cb)
+		return NULL;
+	block_cb->cb = cb;
+	block_cb->cb_ident = cb_ident;
+	block_cb->cb_priv = cb_priv;
+	list_add(&block_cb->list, &block->cb_list);
+	return block_cb;
+}
+EXPORT_SYMBOL(__tcf_block_cb_register);
+
+int tcf_block_cb_register(struct tcf_block *block,
+			  tc_setup_cb_t *cb, void *cb_ident,
+			  void *cb_priv)
+{
+	struct tcf_block_cb *block_cb;
+
+	block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv);
+	return block_cb ? 0 : -ENOMEM;
+}
+EXPORT_SYMBOL(tcf_block_cb_register);
+
+void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb)
+{
+	list_del(&block_cb->list);
+	kfree(block_cb);
+}
+EXPORT_SYMBOL(__tcf_block_cb_unregister);
+
+void tcf_block_cb_unregister(struct tcf_block *block,
+			     tc_setup_cb_t *cb, void *cb_ident)
+{
+	struct tcf_block_cb *block_cb;
+
+	block_cb = tcf_block_cb_lookup(block, cb, cb_ident);
+	if (!block_cb)
+		return;
+	__tcf_block_cb_unregister(block_cb);
+}
+EXPORT_SYMBOL(tcf_block_cb_unregister);
+
+static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type,
+			     void *type_data, bool err_stop)
+{
+	struct tcf_block_cb *block_cb;
+	int ok_count = 0;
+	int err;
+
+	list_for_each_entry(block_cb, &block->cb_list, list) {
+		err = block_cb->cb(type, type_data, block_cb->cb_priv);
+		if (err) {
+			if (err_stop)
+				return err;
+		} else {
+			ok_count++;
+		}
+	}
+	return ok_count;
+}
+
 /* Main classifier routine: scans classifier chain attached
  * to this qdisc, (optionally) tests for protocol and asks
  * specific classifiers.
@@ -379,9 +548,8 @@ static void tcf_chain_tp_insert(struct tcf_chain *chain,
 				struct tcf_chain_info *chain_info,
 				struct tcf_proto *tp)
 {
-	if (chain->p_filter_chain &&
-	    *chain_info->pprev == chain->filter_chain)
-		rcu_assign_pointer(*chain->p_filter_chain, tp);
+	if (*chain_info->pprev == chain->filter_chain)
+		tcf_chain_head_change(chain, tp);
 	RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info));
 	rcu_assign_pointer(*chain_info->pprev, tp);
 	tcf_chain_hold(chain);
@@ -393,8 +561,8 @@ static void tcf_chain_tp_remove(struct tcf_chain *chain,
 {
 	struct tcf_proto *next = rtnl_dereference(chain_info->next);
 
-	if (chain->p_filter_chain && tp == chain->filter_chain)
-		RCU_INIT_POINTER(*chain->p_filter_chain, next);
+	if (tp == chain->filter_chain)
+		tcf_chain_head_change(chain, next);
 	RCU_INIT_POINTER(*chain_info->pprev, next);
 	tcf_chain_put(chain);
 }
@@ -427,8 +595,8 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
 }
 
 static int tcf_fill_node(struct net *net, struct sk_buff *skb,
-			 struct tcf_proto *tp, void *fh, u32 portid,
-			 u32 seq, u16 flags, int event)
+			 struct tcf_proto *tp, struct Qdisc *q, u32 parent,
+			 void *fh, u32 portid, u32 seq, u16 flags, int event)
 {
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
@@ -441,8 +609,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
 	tcm->tcm_family = AF_UNSPEC;
 	tcm->tcm__pad1 = 0;
 	tcm->tcm__pad2 = 0;
-	tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex;
-	tcm->tcm_parent = tp->classid;
+	tcm->tcm_ifindex = qdisc_dev(q)->ifindex;
+	tcm->tcm_parent = parent;
 	tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol);
 	if (nla_put_string(skb, TCA_KIND, tp->ops->kind))
 		goto nla_put_failure;
@@ -465,6 +633,7 @@ nla_put_failure:
 
 static int tfilter_notify(struct net *net, struct sk_buff *oskb,
 			  struct nlmsghdr *n, struct tcf_proto *tp,
+			  struct Qdisc *q, u32 parent,
 			  void *fh, int event, bool unicast)
 {
 	struct sk_buff *skb;
@@ -474,7 +643,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
 	if (!skb)
 		return -ENOBUFS;
 
-	if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq,
+	if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq,
 			  n->nlmsg_flags, event) <= 0) {
 		kfree_skb(skb);
 		return -EINVAL;
@@ -489,6 +658,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
 
 static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
 			      struct nlmsghdr *n, struct tcf_proto *tp,
+			      struct Qdisc *q, u32 parent,
 			      void *fh, bool unicast, bool *last)
 {
 	struct sk_buff *skb;
@@ -499,7 +669,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
 	if (!skb)
 		return -ENOBUFS;
 
-	if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq,
+	if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq,
 			  n->nlmsg_flags, RTM_DELTFILTER) <= 0) {
 		kfree_skb(skb);
 		return -EINVAL;
@@ -519,6 +689,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
 }
 
 static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
+				 struct Qdisc *q, u32 parent,
 				 struct nlmsghdr *n,
 				 struct tcf_chain *chain, int event)
 {
@@ -526,7 +697,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
 
 	for (tp = rtnl_dereference(chain->filter_chain);
 	     tp; tp = rtnl_dereference(tp->next))
-		tfilter_notify(net, oskb, n, tp, 0, event, false);
+		tfilter_notify(net, oskb, n, tp, q, parent, 0, event, false);
 }
 
 /* Add/change/delete/get a filter node */
@@ -645,7 +816,8 @@ replay:
 	}
 
 	if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) {
-		tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER);
+		tfilter_notify_chain(net, skb, q, parent, n,
+				     chain, RTM_DELTFILTER);
 		tcf_chain_flush(chain);
 		err = 0;
 		goto errout;
@@ -692,7 +864,7 @@ replay:
 	if (!fh) {
 		if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) {
 			tcf_chain_tp_remove(chain, &chain_info, tp);
-			tfilter_notify(net, skb, n, tp, fh,
+			tfilter_notify(net, skb, n, tp, q, parent, fh,
 				       RTM_DELTFILTER, false);
 			tcf_proto_destroy(tp);
 			err = 0;
@@ -717,8 +889,8 @@ replay:
 			}
 			break;
 		case RTM_DELTFILTER:
-			err = tfilter_del_notify(net, skb, n, tp, fh, false,
-						 &last);
+			err = tfilter_del_notify(net, skb, n, tp, q, parent,
+						 fh, false, &last);
 			if (err)
 				goto errout;
 			if (last) {
@@ -727,7 +899,7 @@ replay:
 			}
 			goto errout;
 		case RTM_GETTFILTER:
-			err = tfilter_notify(net, skb, n, tp, fh,
+			err = tfilter_notify(net, skb, n, tp, q, parent, fh,
 					     RTM_NEWTFILTER, true);
 			goto errout;
 		default:
@@ -741,7 +913,8 @@ replay:
 	if (err == 0) {
 		if (tp_created)
 			tcf_chain_tp_insert(chain, &chain_info, tp);
-		tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false);
+		tfilter_notify(net, skb, n, tp, q, parent, fh,
+			       RTM_NEWTFILTER, false);
 	} else {
 		if (tp_created)
 			tcf_proto_destroy(tp);
@@ -760,6 +933,8 @@ struct tcf_dump_args {
 	struct tcf_walker w;
 	struct sk_buff *skb;
 	struct netlink_callback *cb;
+	struct Qdisc *q;
+	u32 parent;
 };
 
 static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
@@ -767,13 +942,14 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
 	struct tcf_dump_args *a = (void *)arg;
 	struct net *net = sock_net(a->skb->sk);
 
-	return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid,
+	return tcf_fill_node(net, a->skb, tp, a->q, a->parent,
+			     n, NETLINK_CB(a->cb->skb).portid,
 			     a->cb->nlh->nlmsg_seq, NLM_F_MULTI,
 			     RTM_NEWTFILTER);
 }
 
-static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb,
-			   struct netlink_callback *cb,
+static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
+			   struct sk_buff *skb, struct netlink_callback *cb,
 			   long index_start, long *p_index)
 {
 	struct net *net = sock_net(skb->sk);
@@ -795,7 +971,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb,
 			memset(&cb->args[1], 0,
 			       sizeof(cb->args) - sizeof(cb->args[0]));
 		if (cb->args[1] == 0) {
-			if (tcf_fill_node(net, skb, tp, 0,
+			if (tcf_fill_node(net, skb, tp, q, parent, 0,
 					  NETLINK_CB(cb->skb).portid,
 					  cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					  RTM_NEWTFILTER) <= 0)
@@ -808,6 +984,8 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb,
 		arg.w.fn = tcf_node_dump;
 		arg.skb = skb;
 		arg.cb = cb;
+		arg.q = q;
+		arg.parent = parent;
 		arg.w.stop = 0;
 		arg.w.skip = cb->args[1] - 1;
 		arg.w.count = 0;
@@ -833,6 +1011,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 	const struct Qdisc_class_ops *cops;
 	long index_start;
 	long index;
+	u32 parent;
 	int err;
 
 	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
@@ -846,10 +1025,13 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 	if (!dev)
 		return skb->len;
 
-	if (!tcm->tcm_parent)
+	parent = tcm->tcm_parent;
+	if (!parent) {
 		q = dev->qdisc;
-	else
+		parent = q->handle;
+	} else {
 		q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
+	}
 	if (!q)
 		goto out;
 	cops = q->ops->cl_ops;
@@ -873,7 +1055,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		if (tca[TCA_CHAIN] &&
 		    nla_get_u32(tca[TCA_CHAIN]) != chain->index)
 			continue;
-		if (!tcf_chain_dump(chain, skb, cb, index_start, &index))
+		if (!tcf_chain_dump(chain, q, parent, skb, cb,
+				    index_start, &index))
 			break;
 	}
 
@@ -1014,29 +1197,56 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
 }
 EXPORT_SYMBOL(tcf_exts_dump_stats);
 
-int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts,
-		     struct net_device **hw_dev)
+static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts,
+				       enum tc_setup_type type,
+				       void *type_data, bool err_stop)
 {
+	int ok_count = 0;
 #ifdef CONFIG_NET_CLS_ACT
 	const struct tc_action *a;
-	LIST_HEAD(actions);
+	struct net_device *dev;
+	int i, ret;
 
 	if (!tcf_exts_has_actions(exts))
-		return -EINVAL;
+		return 0;
 
-	tcf_exts_to_list(exts, &actions);
-	list_for_each_entry(a, &actions, list) {
-		if (a->ops->get_dev) {
-			a->ops->get_dev(a, dev_net(dev), hw_dev);
-			break;
-		}
+	for (i = 0; i < exts->nr_actions; i++) {
+		a = exts->actions[i];
+		if (!a->ops->get_dev)
+			continue;
+		dev = a->ops->get_dev(a);
+		if (!dev)
+			continue;
+		ret = tc_setup_cb_egdev_call(dev, type, type_data, err_stop);
+		if (ret < 0)
+			return ret;
+		ok_count += ret;
 	}
-	if (*hw_dev)
-		return 0;
 #endif
-	return -EOPNOTSUPP;
+	return ok_count;
+}
+
+int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
+		     enum tc_setup_type type, void *type_data, bool err_stop)
+{
+	int ok_count;
+	int ret;
+
+	ret = tcf_block_cb_call(block, type, type_data, err_stop);
+	if (ret < 0)
+		return ret;
+	ok_count = ret;
+
+	if (!exts)
+		return ok_count;
+	ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
+	if (ret < 0)
+		return ret;
+	ok_count += ret;
+
+	return ok_count;
 }
-EXPORT_SYMBOL(tcf_exts_get_dev);
+EXPORT_SYMBOL(tc_setup_cb_call);
 
 static int __init tc_filter_init(void)
 {
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index f177649a2419..871351358c10 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -17,13 +17,14 @@
 #include <linux/errno.h>
 #include <linux/rtnetlink.h>
 #include <linux/skbuff.h>
+#include <linux/idr.h>
 #include <net/netlink.h>
 #include <net/act_api.h>
 #include <net/pkt_cls.h>
 
 struct basic_head {
-	u32			hgenerator;
 	struct list_head	flist;
+	struct idr		handle_idr;
 	struct rcu_head		rcu;
 };
 
@@ -81,6 +82,7 @@ static int basic_init(struct tcf_proto *tp)
 	if (head == NULL)
 		return -ENOBUFS;
 	INIT_LIST_HEAD(&head->flist);
+	idr_init(&head->handle_idr);
 	rcu_assign_pointer(tp->root, head);
 	return 0;
 }
@@ -113,8 +115,10 @@ static void basic_destroy(struct tcf_proto *tp)
 	list_for_each_entry_safe(f, n, &head->flist, link) {
 		list_del_rcu(&f->link);
 		tcf_unbind_filter(tp, &f->res);
+		idr_remove_ext(&head->handle_idr, f->handle);
 		call_rcu(&f->rcu, basic_delete_filter);
 	}
+	idr_destroy(&head->handle_idr);
 	kfree_rcu(head, rcu);
 }
 
@@ -125,6 +129,7 @@ static int basic_delete(struct tcf_proto *tp, void *arg, bool *last)
 
 	list_del_rcu(&f->link);
 	tcf_unbind_filter(tp, &f->res);
+	idr_remove_ext(&head->handle_idr, f->handle);
 	call_rcu(&f->rcu, basic_delete_filter);
 	*last = list_empty(&head->flist);
 	return 0;
@@ -168,6 +173,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 	struct nlattr *tb[TCA_BASIC_MAX + 1];
 	struct basic_filter *fold = (struct basic_filter *) *arg;
 	struct basic_filter *fnew;
+	unsigned long idr_index;
 
 	if (tca[TCA_OPTIONS] == NULL)
 		return -EINVAL;
@@ -190,33 +196,33 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = -EINVAL;
 	if (handle) {
 		fnew->handle = handle;
-	} else if (fold) {
-		fnew->handle = fold->handle;
+		if (!fold) {
+			err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index,
+					    handle, handle + 1, GFP_KERNEL);
+			if (err)
+				goto errout;
+		}
 	} else {
-		unsigned int i = 0x80000000;
-		do {
-			if (++head->hgenerator == 0x7FFFFFFF)
-				head->hgenerator = 1;
-		} while (--i > 0 && basic_get(tp, head->hgenerator));
-
-		if (i <= 0) {
-			pr_err("Insufficient number of handles\n");
+		err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index,
+				    1, 0x7FFFFFFF, GFP_KERNEL);
+		if (err)
 			goto errout;
-		}
-
-		fnew->handle = head->hgenerator;
+		fnew->handle = idr_index;
 	}
 
 	err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr);
-	if (err < 0)
+	if (err < 0) {
+		if (!fold)
+			idr_remove_ext(&head->handle_idr, fnew->handle);
 		goto errout;
+	}
 
 	*arg = fnew;
 
 	if (fold) {
+		idr_replace_ext(&head->handle_idr, fnew, fnew->handle);
 		list_replace_rcu(&fold->link, &fnew->link);
 		tcf_unbind_filter(tp, &fold->res);
 		call_rcu(&fold->rcu, basic_delete_filter);
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 037a3ae86829..bc3edde1b9d7 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -17,6 +17,7 @@
 #include <linux/skbuff.h>
 #include <linux/filter.h>
 #include <linux/bpf.h>
+#include <linux/idr.h>
 
 #include <net/rtnetlink.h>
 #include <net/pkt_cls.h>
@@ -32,7 +33,7 @@ MODULE_DESCRIPTION("TC BPF based classifier");
 
 struct cls_bpf_head {
 	struct list_head plist;
-	u32 hgen;
+	struct idr handle_idr;
 	struct rcu_head rcu;
 };
 
@@ -102,11 +103,11 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		} else if (at_ingress) {
 			/* It is safe to push/pull even if skb_shared() */
 			__skb_push(skb, skb->mac_len);
-			bpf_compute_data_end(skb);
+			bpf_compute_data_pointers(skb);
 			filter_res = BPF_PROG_RUN(prog->filter, skb);
 			__skb_pull(skb, skb->mac_len);
 		} else {
-			bpf_compute_data_end(skb);
+			bpf_compute_data_pointers(skb);
 			filter_res = BPF_PROG_RUN(prog->filter, skb);
 		}
 
@@ -149,7 +150,9 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog)
 static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 			       enum tc_clsbpf_command cmd)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
+	bool addorrep = cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE;
+	struct tcf_block *block = tp->chain->block;
+	bool skip_sw = tc_skip_sw(prog->gen_flags);
 	struct tc_cls_bpf_offload cls_bpf = {};
 	int err;
 
@@ -161,17 +164,25 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 	cls_bpf.exts_integrated = prog->exts_integrated;
 	cls_bpf.gen_flags = prog->gen_flags;
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSBPF, &cls_bpf);
-	if (!err && (cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE))
-		prog->gen_flags |= TCA_CLS_FLAGS_IN_HW;
+	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, skip_sw);
+	if (addorrep) {
+		if (err < 0) {
+			cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY);
+			return err;
+		} else if (err > 0) {
+			prog->gen_flags |= TCA_CLS_FLAGS_IN_HW;
+		}
+	}
+
+	if (addorrep && skip_sw && !(prog->gen_flags & TCA_CLS_FLAGS_IN_HW))
+		return -EINVAL;
 
-	return err;
+	return 0;
 }
 
 static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 			   struct cls_bpf_prog *oldprog)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
 	struct cls_bpf_prog *obj = prog;
 	enum tc_clsbpf_command cmd;
 	bool skip_sw;
@@ -181,7 +192,7 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 		(oldprog && tc_skip_sw(oldprog->gen_flags));
 
 	if (oldprog && oldprog->offloaded) {
-		if (tc_should_offload(dev, prog->gen_flags)) {
+		if (!tc_skip_hw(prog->gen_flags)) {
 			cmd = TC_CLSBPF_REPLACE;
 		} else if (!tc_skip_sw(prog->gen_flags)) {
 			obj = oldprog;
@@ -190,14 +201,14 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 			return -EINVAL;
 		}
 	} else {
-		if (!tc_should_offload(dev, prog->gen_flags))
+		if (tc_skip_hw(prog->gen_flags))
 			return skip_sw ? -EINVAL : 0;
 		cmd = TC_CLSBPF_ADD;
 	}
 
 	ret = cls_bpf_offload_cmd(tp, obj, cmd);
 	if (ret)
-		return skip_sw ? ret : 0;
+		return ret;
 
 	obj->offloaded = true;
 	if (oldprog)
@@ -241,6 +252,7 @@ static int cls_bpf_init(struct tcf_proto *tp)
 		return -ENOBUFS;
 
 	INIT_LIST_HEAD_RCU(&head->plist);
+	idr_init(&head->handle_idr);
 	rcu_assign_pointer(tp->root, head);
 
 	return 0;
@@ -279,6 +291,9 @@ static void cls_bpf_delete_prog_rcu(struct rcu_head *rcu)
 
 static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog)
 {
+	struct cls_bpf_head *head = rtnl_dereference(tp->root);
+
+	idr_remove_ext(&head->handle_idr, prog->handle);
 	cls_bpf_stop_offload(tp, prog);
 	list_del_rcu(&prog->link);
 	tcf_unbind_filter(tp, &prog->res);
@@ -302,6 +317,7 @@ static void cls_bpf_destroy(struct tcf_proto *tp)
 	list_for_each_entry_safe(prog, tmp, &head->plist, link)
 		__cls_bpf_delete(tp, prog);
 
+	idr_destroy(&head->handle_idr);
 	kfree_rcu(head, rcu);
 }
 
@@ -436,27 +452,6 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp,
 	return 0;
 }
 
-static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp,
-				   struct cls_bpf_head *head)
-{
-	unsigned int i = 0x80000000;
-	u32 handle;
-
-	do {
-		if (++head->hgen == 0x7FFFFFFF)
-			head->hgen = 1;
-	} while (--i > 0 && cls_bpf_get(tp, head->hgen));
-
-	if (unlikely(i == 0)) {
-		pr_err("Insufficient number of handles\n");
-		handle = 0;
-	} else {
-		handle = head->hgen;
-	}
-
-	return handle;
-}
-
 static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 			  struct tcf_proto *tp, unsigned long base,
 			  u32 handle, struct nlattr **tca,
@@ -466,6 +461,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 	struct cls_bpf_prog *oldprog = *arg;
 	struct nlattr *tb[TCA_BPF_MAX + 1];
 	struct cls_bpf_prog *prog;
+	unsigned long idr_index;
 	int ret;
 
 	if (tca[TCA_OPTIONS] == NULL)
@@ -491,21 +487,30 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 		}
 	}
 
-	if (handle == 0)
-		prog->handle = cls_bpf_grab_new_handle(tp, head);
-	else
+	if (handle == 0) {
+		ret = idr_alloc_ext(&head->handle_idr, prog, &idr_index,
+				    1, 0x7FFFFFFF, GFP_KERNEL);
+		if (ret)
+			goto errout;
+		prog->handle = idr_index;
+	} else {
+		if (!oldprog) {
+			ret = idr_alloc_ext(&head->handle_idr, prog, &idr_index,
+					    handle, handle + 1, GFP_KERNEL);
+			if (ret)
+				goto errout;
+		}
 		prog->handle = handle;
-	if (prog->handle == 0) {
-		ret = -EINVAL;
-		goto errout;
 	}
 
 	ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], ovr);
 	if (ret < 0)
-		goto errout;
+		goto errout_idr;
 
 	ret = cls_bpf_offload(tp, prog, oldprog);
 	if (ret) {
+		if (!oldprog)
+			idr_remove_ext(&head->handle_idr, prog->handle);
 		__cls_bpf_delete_prog(prog);
 		return ret;
 	}
@@ -514,6 +519,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 		prog->gen_flags |= TCA_CLS_FLAGS_NOT_IN_HW;
 
 	if (oldprog) {
+		idr_replace_ext(&head->handle_idr, prog, handle);
 		list_replace_rcu(&oldprog->link, &prog->link);
 		tcf_unbind_filter(tp, &oldprog->res);
 		call_rcu(&oldprog->rcu, cls_bpf_delete_prog_rcu);
@@ -524,6 +530,9 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 	*arg = prog;
 	return 0;
 
+errout_idr:
+	if (!oldprog)
+		idr_remove_ext(&head->handle_idr, prog->handle);
 errout:
 	tcf_exts_destroy(&prog->exts);
 	kfree(prog);
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 67f3a2af6aab..9c08fcdaf41c 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -348,9 +348,9 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	return -1;
 }
 
-static void flow_perturbation(unsigned long arg)
+static void flow_perturbation(struct timer_list *t)
 {
-	struct flow_filter *f = (struct flow_filter *)arg;
+	struct flow_filter *f = from_timer(f, t, perturb_timer);
 
 	get_random_bytes(&f->hashrnd, 4);
 	if (f->perturb_period)
@@ -504,8 +504,11 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 			perturb_period = nla_get_u32(tb[TCA_FLOW_PERTURB]) * HZ;
 		}
 
-		if (TC_H_MAJ(baseclass) == 0)
-			baseclass = TC_H_MAKE(tp->q->handle, baseclass);
+		if (TC_H_MAJ(baseclass) == 0) {
+			struct Qdisc *q = tcf_block_q(tp->chain->block);
+
+			baseclass = TC_H_MAKE(q->handle, baseclass);
+		}
 		if (TC_H_MIN(baseclass) == 0)
 			baseclass = TC_H_MAKE(baseclass, 1);
 
@@ -515,8 +518,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 		get_random_bytes(&fnew->hashrnd, 4);
 	}
 
-	setup_deferrable_timer(&fnew->perturb_timer, flow_perturbation,
-			       (unsigned long)fnew);
+	timer_setup(&fnew->perturb_timer, flow_perturbation, TIMER_DEFERRABLE);
 
 	netif_keep_dst(qdisc_dev(tp->q));
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 5b5722c8b32c..c99fa9e5be46 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -155,37 +155,12 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	struct cls_fl_filter *f;
 	struct fl_flow_key skb_key;
 	struct fl_flow_key skb_mkey;
-	struct ip_tunnel_info *info;
 
 	if (!atomic_read(&head->ht.nelems))
 		return -1;
 
 	fl_clear_masked_range(&skb_key, &head->mask);
 
-	info = skb_tunnel_info(skb);
-	if (info) {
-		struct ip_tunnel_key *key = &info->key;
-
-		switch (ip_tunnel_info_af(info)) {
-		case AF_INET:
-			skb_key.enc_control.addr_type =
-				FLOW_DISSECTOR_KEY_IPV4_ADDRS;
-			skb_key.enc_ipv4.src = key->u.ipv4.src;
-			skb_key.enc_ipv4.dst = key->u.ipv4.dst;
-			break;
-		case AF_INET6:
-			skb_key.enc_control.addr_type =
-				FLOW_DISSECTOR_KEY_IPV6_ADDRS;
-			skb_key.enc_ipv6.src = key->u.ipv6.src;
-			skb_key.enc_ipv6.dst = key->u.ipv6.dst;
-			break;
-		}
-
-		skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id);
-		skb_key.enc_tp.src = key->tp_src;
-		skb_key.enc_tp.dst = key->tp_dst;
-	}
-
 	skb_key.indev_ifindex = skb->skb_iif;
 	/* skb_flow_dissect() does not set n_proto in case an unknown protocol,
 	 * so do it rather here.
@@ -239,17 +214,14 @@ static void fl_destroy_filter(struct rcu_head *head)
 static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f)
 {
 	struct tc_cls_flower_offload cls_flower = {};
-	struct net_device *dev = f->hw_dev;
-
-	if (!tc_can_offload(dev))
-		return;
+	struct tcf_block *block = tp->chain->block;
 
 	tc_cls_common_offload_init(&cls_flower.common, tp);
 	cls_flower.command = TC_CLSFLOWER_DESTROY;
 	cls_flower.cookie = (unsigned long) f;
-	cls_flower.egress_dev = f->hw_dev != tp->q->dev_queue->dev;
 
-	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, &cls_flower);
+	tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
+			 &cls_flower, false);
 }
 
 static int fl_hw_replace_filter(struct tcf_proto *tp,
@@ -257,22 +229,11 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 				struct fl_flow_key *mask,
 				struct cls_fl_filter *f)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
 	struct tc_cls_flower_offload cls_flower = {};
+	struct tcf_block *block = tp->chain->block;
+	bool skip_sw = tc_skip_sw(f->flags);
 	int err;
 
-	if (!tc_can_offload(dev)) {
-		if (tcf_exts_get_dev(dev, &f->exts, &f->hw_dev) ||
-		    (f->hw_dev && !tc_can_offload(f->hw_dev))) {
-			f->hw_dev = dev;
-			return tc_skip_sw(f->flags) ? -EINVAL : 0;
-		}
-		dev = f->hw_dev;
-		cls_flower.egress_dev = true;
-	} else {
-		f->hw_dev = dev;
-	}
-
 	tc_cls_common_offload_init(&cls_flower.common, tp);
 	cls_flower.command = TC_CLSFLOWER_REPLACE;
 	cls_flower.cookie = (unsigned long) f;
@@ -280,33 +241,36 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 	cls_flower.mask = mask;
 	cls_flower.key = &f->mkey;
 	cls_flower.exts = &f->exts;
+	cls_flower.classid = f->res.classid;
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER,
-					    &cls_flower);
-	if (!err)
+	err = tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
+			       &cls_flower, skip_sw);
+	if (err < 0) {
+		fl_hw_destroy_filter(tp, f);
+		return err;
+	} else if (err > 0) {
 		f->flags |= TCA_CLS_FLAGS_IN_HW;
+	}
+
+	if (skip_sw && !(f->flags & TCA_CLS_FLAGS_IN_HW))
+		return -EINVAL;
 
-	if (tc_skip_sw(f->flags))
-		return err;
 	return 0;
 }
 
 static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
 {
 	struct tc_cls_flower_offload cls_flower = {};
-	struct net_device *dev = f->hw_dev;
-
-	if (!tc_can_offload(dev))
-		return;
+	struct tcf_block *block = tp->chain->block;
 
 	tc_cls_common_offload_init(&cls_flower.common, tp);
 	cls_flower.command = TC_CLSFLOWER_STATS;
 	cls_flower.cookie = (unsigned long) f;
 	cls_flower.exts = &f->exts;
-	cls_flower.egress_dev = f->hw_dev != tp->q->dev_queue->dev;
+	cls_flower.classid = f->res.classid;
 
-	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER,
-				      &cls_flower);
+	tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
+			 &cls_flower, false);
 }
 
 static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f)
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 99183b8621ec..5908f56f76da 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -28,6 +28,7 @@
 #include <net/netlink.h>
 #include <net/act_api.h>
 #include <net/pkt_cls.h>
+#include <net/sch_generic.h>
 
 #define HTSIZE 256
 
@@ -86,9 +87,11 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			}
 		}
 	} else {
+		struct Qdisc *q = tcf_block_q(tp->chain->block);
+
 		/* Old method: classify the packet using its skb mark. */
 		if (id && (TC_H_MAJ(id) == 0 ||
-			   !(TC_H_MAJ(id ^ tp->q->handle)))) {
+			   !(TC_H_MAJ(id ^ q->handle)))) {
 			res->classid = id;
 			res->class = 0;
 			return 0;
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index c33f711b9019..95dc997873e8 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -63,12 +63,27 @@ static void mall_destroy_rcu(struct rcu_head *rcu)
 	tcf_queue_work(&head->work);
 }
 
+static void mall_destroy_hw_filter(struct tcf_proto *tp,
+				   struct cls_mall_head *head,
+				   unsigned long cookie)
+{
+	struct tc_cls_matchall_offload cls_mall = {};
+	struct tcf_block *block = tp->chain->block;
+
+	tc_cls_common_offload_init(&cls_mall.common, tp);
+	cls_mall.command = TC_CLSMATCHALL_DESTROY;
+	cls_mall.cookie = cookie;
+
+	tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL, &cls_mall, false);
+}
+
 static int mall_replace_hw_filter(struct tcf_proto *tp,
 				  struct cls_mall_head *head,
 				  unsigned long cookie)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
 	struct tc_cls_matchall_offload cls_mall = {};
+	struct tcf_block *block = tp->chain->block;
+	bool skip_sw = tc_skip_sw(head->flags);
 	int err;
 
 	tc_cls_common_offload_init(&cls_mall.common, tp);
@@ -76,37 +91,29 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
 	cls_mall.exts = &head->exts;
 	cls_mall.cookie = cookie;
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSMATCHALL,
-					    &cls_mall);
-	if (!err)
+	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL,
+			       &cls_mall, skip_sw);
+	if (err < 0) {
+		mall_destroy_hw_filter(tp, head, cookie);
+		return err;
+	} else if (err > 0) {
 		head->flags |= TCA_CLS_FLAGS_IN_HW;
+	}
 
-	return err;
-}
-
-static void mall_destroy_hw_filter(struct tcf_proto *tp,
-				   struct cls_mall_head *head,
-				   unsigned long cookie)
-{
-	struct net_device *dev = tp->q->dev_queue->dev;
-	struct tc_cls_matchall_offload cls_mall = {};
-
-	tc_cls_common_offload_init(&cls_mall.common, tp);
-	cls_mall.command = TC_CLSMATCHALL_DESTROY;
-	cls_mall.cookie = cookie;
+	if (skip_sw && !(head->flags & TCA_CLS_FLAGS_IN_HW))
+		return -EINVAL;
 
-	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSMATCHALL, &cls_mall);
+	return 0;
 }
 
 static void mall_destroy(struct tcf_proto *tp)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
-	struct net_device *dev = tp->q->dev_queue->dev;
 
 	if (!head)
 		return;
 
-	if (tc_should_offload(dev, head->flags))
+	if (!tc_skip_hw(head->flags))
 		mall_destroy_hw_filter(tp, head, (unsigned long) head);
 
 	call_rcu(&head->rcu, mall_destroy_rcu);
@@ -146,7 +153,6 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 		       void **arg, bool ovr)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
-	struct net_device *dev = tp->q->dev_queue->dev;
 	struct nlattr *tb[TCA_MATCHALL_MAX + 1];
 	struct cls_mall_head *new;
 	u32 flags = 0;
@@ -186,14 +192,10 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 	if (err)
 		goto err_set_parms;
 
-	if (tc_should_offload(dev, flags)) {
+	if (!tc_skip_hw(new->flags)) {
 		err = mall_replace_hw_filter(tp, new, (unsigned long) new);
-		if (err) {
-			if (tc_skip_sw(flags))
-				goto err_replace_hw_filter;
-			else
-				err = 0;
-		}
+		if (err)
+			goto err_replace_hw_filter;
 	}
 
 	if (!tc_in_hw(new->flags))
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index beaa95e09c25..d6abfa6757f2 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -13,6 +13,7 @@
 #include <net/act_api.h>
 #include <net/netlink.h>
 #include <net/pkt_cls.h>
+#include <net/sch_generic.h>
 
 /*
  * Passing parameters to the root seems to be done more awkwardly than really
@@ -96,9 +97,11 @@ static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 
 	f = tcindex_lookup(p, key);
 	if (!f) {
+		struct Qdisc *q = tcf_block_q(tp->chain->block);
+
 		if (!p->fall_through)
 			return -1;
-		res->classid = TC_H_MAKE(TC_H_MAJ(tp->q->handle), key);
+		res->classid = TC_H_MAKE(TC_H_MAJ(q->handle), key);
 		res->class = 0;
 		pr_debug("alg 0x%x\n", res->classid);
 		return 0;
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index dadd1b344497..86145867b424 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -46,6 +46,7 @@
 #include <net/act_api.h>
 #include <net/pkt_cls.h>
 #include <linux/netdevice.h>
+#include <linux/idr.h>
 
 struct tc_u_knode {
 	struct tc_u_knode __rcu	*next;
@@ -85,6 +86,7 @@ struct tc_u_hnode {
 	struct tc_u_common	*tp_c;
 	int			refcnt;
 	unsigned int		divisor;
+	struct idr		handle_idr;
 	struct rcu_head		rcu;
 	/* The 'ht' field MUST be the last field in structure to allow for
 	 * more entries allocated at end of structure.
@@ -94,9 +96,9 @@ struct tc_u_hnode {
 
 struct tc_u_common {
 	struct tc_u_hnode __rcu	*hlist;
-	struct Qdisc		*q;
+	struct tcf_block	*block;
 	int			refcnt;
-	u32			hgenerator;
+	struct idr		handle_idr;
 	struct hlist_node	hnode;
 	struct rcu_head		rcu;
 };
@@ -314,19 +316,19 @@ static void *u32_get(struct tcf_proto *tp, u32 handle)
 	return u32_lookup_key(ht, handle);
 }
 
-static u32 gen_new_htid(struct tc_u_common *tp_c)
+static u32 gen_new_htid(struct tc_u_common *tp_c, struct tc_u_hnode *ptr)
 {
-	int i = 0x800;
+	unsigned long idr_index;
+	int err;
 
-	/* hgenerator only used inside rtnl lock it is safe to increment
+	/* This is only used inside rtnl lock it is safe to increment
 	 * without read _copy_ update semantics
 	 */
-	do {
-		if (++tp_c->hgenerator == 0x7FF)
-			tp_c->hgenerator = 1;
-	} while (--i > 0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20));
-
-	return i > 0 ? (tp_c->hgenerator|0x800)<<20 : 0;
+	err = idr_alloc_ext(&tp_c->handle_idr, ptr, &idr_index,
+			    1, 0x7FF, GFP_KERNEL);
+	if (err)
+		return 0;
+	return (u32)(idr_index | 0x800) << 20;
 }
 
 static struct hlist_head *tc_u_common_hash;
@@ -336,11 +338,7 @@ static struct hlist_head *tc_u_common_hash;
 
 static unsigned int tc_u_hash(const struct tcf_proto *tp)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
-	u32 qhandle = tp->q->handle;
-	int ifindex = dev->ifindex;
-
-	return hash_64((u64)ifindex << 32 | qhandle, U32_HASH_SHIFT);
+	return hash_ptr(tp->chain->block, U32_HASH_SHIFT);
 }
 
 static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp)
@@ -350,7 +348,7 @@ static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp)
 
 	h = tc_u_hash(tp);
 	hlist_for_each_entry(tc, &tc_u_common_hash[h], hnode) {
-		if (tc->q == tp->q)
+		if (tc->block == tp->chain->block)
 			return tc;
 	}
 	return NULL;
@@ -369,8 +367,9 @@ static int u32_init(struct tcf_proto *tp)
 		return -ENOBUFS;
 
 	root_ht->refcnt++;
-	root_ht->handle = tp_c ? gen_new_htid(tp_c) : 0x80000000;
+	root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000;
 	root_ht->prio = tp->prio;
+	idr_init(&root_ht->handle_idr);
 
 	if (tp_c == NULL) {
 		tp_c = kzalloc(sizeof(*tp_c), GFP_KERNEL);
@@ -378,8 +377,9 @@ static int u32_init(struct tcf_proto *tp)
 			kfree(root_ht);
 			return -ENOBUFS;
 		}
-		tp_c->q = tp->q;
+		tp_c->block = tp->chain->block;
 		INIT_HLIST_NODE(&tp_c->hnode);
+		idr_init(&tp_c->handle_idr);
 
 		h = tc_u_hash(tp);
 		hlist_add_head(&tp_c->hnode, &tc_u_common_hash[h]);
@@ -485,71 +485,69 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 	return 0;
 }
 
-static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle)
+static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
+	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
 
-	if (!tc_should_offload(dev, 0))
-		return;
-
 	tc_cls_common_offload_init(&cls_u32.common, tp);
-	cls_u32.command = TC_CLSU32_DELETE_KNODE;
-	cls_u32.knode.handle = handle;
+	cls_u32.command = TC_CLSU32_DELETE_HNODE;
+	cls_u32.hnode.divisor = h->divisor;
+	cls_u32.hnode.handle = h->handle;
+	cls_u32.hnode.prio = h->prio;
 
-	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32);
+	tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false);
 }
 
 static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h,
 				u32 flags)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
+	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
+	bool skip_sw = tc_skip_sw(flags);
+	bool offloaded = false;
 	int err;
 
-	if (!tc_should_offload(dev, flags))
-		return tc_skip_sw(flags) ? -EINVAL : 0;
-
 	tc_cls_common_offload_init(&cls_u32.common, tp);
 	cls_u32.command = TC_CLSU32_NEW_HNODE;
 	cls_u32.hnode.divisor = h->divisor;
 	cls_u32.hnode.handle = h->handle;
 	cls_u32.hnode.prio = h->prio;
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32);
-	if (tc_skip_sw(flags))
+	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw);
+	if (err < 0) {
+		u32_clear_hw_hnode(tp, h);
 		return err;
+	} else if (err > 0) {
+		offloaded = true;
+	}
+
+	if (skip_sw && !offloaded)
+		return -EINVAL;
 
 	return 0;
 }
 
-static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h)
+static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
+	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
 
-	if (!tc_should_offload(dev, 0))
-		return;
-
 	tc_cls_common_offload_init(&cls_u32.common, tp);
-	cls_u32.command = TC_CLSU32_DELETE_HNODE;
-	cls_u32.hnode.divisor = h->divisor;
-	cls_u32.hnode.handle = h->handle;
-	cls_u32.hnode.prio = h->prio;
+	cls_u32.command = TC_CLSU32_DELETE_KNODE;
+	cls_u32.knode.handle = handle;
 
-	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32);
+	tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false);
 }
 
 static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 				u32 flags)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
+	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
+	bool skip_sw = tc_skip_sw(flags);
 	int err;
 
-	if (!tc_should_offload(dev, flags))
-		return tc_skip_sw(flags) ? -EINVAL : 0;
-
 	tc_cls_common_offload_init(&cls_u32.common, tp);
 	cls_u32.command = TC_CLSU32_REPLACE_KNODE;
 	cls_u32.knode.handle = n->handle;
@@ -566,13 +564,16 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	if (n->ht_down)
 		cls_u32.knode.link_handle = n->ht_down->handle;
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32);
-
-	if (!err)
+	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw);
+	if (err < 0) {
+		u32_remove_hw_knode(tp, n->handle);
+		return err;
+	} else if (err > 0) {
 		n->flags |= TCA_CLS_FLAGS_IN_HW;
+	}
 
-	if (tc_skip_sw(flags))
-		return err;
+	if (skip_sw && !(n->flags && TCA_CLS_FLAGS_IN_HW))
+		return -EINVAL;
 
 	return 0;
 }
@@ -588,6 +589,7 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht)
 					 rtnl_dereference(n->next));
 			tcf_unbind_filter(tp, &n->res);
 			u32_remove_hw_knode(tp, n->handle);
+			idr_remove_ext(&ht->handle_idr, n->handle);
 			call_rcu(&n->rcu, u32_delete_key_freepf_rcu);
 		}
 	}
@@ -609,6 +611,8 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht)
 	     hn = &phn->next, phn = rtnl_dereference(*hn)) {
 		if (phn == ht) {
 			u32_clear_hw_hnode(tp, ht);
+			idr_destroy(&ht->handle_idr);
+			idr_remove_ext(&tp_c->handle_idr, ht->handle);
 			RCU_INIT_POINTER(*hn, ht->next);
 			kfree_rcu(ht, rcu);
 			return 0;
@@ -656,6 +660,7 @@ static void u32_destroy(struct tcf_proto *tp)
 			kfree_rcu(ht, rcu);
 		}
 
+		idr_destroy(&tp_c->handle_idr);
 		kfree(tp_c);
 	}
 
@@ -724,27 +729,21 @@ ret:
 	return ret;
 }
 
-#define NR_U32_NODE (1<<12)
-static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle)
+static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid)
 {
-	struct tc_u_knode *n;
-	unsigned long i;
-	unsigned long *bitmap = kzalloc(BITS_TO_LONGS(NR_U32_NODE) * sizeof(unsigned long),
-					GFP_KERNEL);
-	if (!bitmap)
-		return handle | 0xFFF;
-
-	for (n = rtnl_dereference(ht->ht[TC_U32_HASH(handle)]);
-	     n;
-	     n = rtnl_dereference(n->next))
-		set_bit(TC_U32_NODE(n->handle), bitmap);
-
-	i = find_next_zero_bit(bitmap, NR_U32_NODE, 0x800);
-	if (i >= NR_U32_NODE)
-		i = find_next_zero_bit(bitmap, NR_U32_NODE, 1);
+	unsigned long idr_index;
+	u32 start = htid | 0x800;
+	u32 max = htid | 0xFFF;
+	u32 min = htid;
+
+	if (idr_alloc_ext(&ht->handle_idr, NULL, &idr_index,
+			  start, max + 1, GFP_KERNEL)) {
+		if (idr_alloc_ext(&ht->handle_idr, NULL, &idr_index,
+				  min + 1, max + 1, GFP_KERNEL))
+			return max;
+	}
 
-	kfree(bitmap);
-	return handle | (i >= NR_U32_NODE ? 0xFFF : i);
+	return (u32)idr_index;
 }
 
 static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = {
@@ -829,6 +828,7 @@ static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c,
 		if (pins->handle == n->handle)
 			break;
 
+	idr_replace_ext(&ht->handle_idr, n, n->handle);
 	RCU_INIT_POINTER(n->next, pins->next);
 	rcu_assign_pointer(*ins, n);
 }
@@ -960,22 +960,33 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 			return -EINVAL;
 		if (TC_U32_KEY(handle))
 			return -EINVAL;
-		if (handle == 0) {
-			handle = gen_new_htid(tp->data);
-			if (handle == 0)
-				return -ENOMEM;
-		}
 		ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL);
 		if (ht == NULL)
 			return -ENOBUFS;
+		if (handle == 0) {
+			handle = gen_new_htid(tp->data, ht);
+			if (handle == 0) {
+				kfree(ht);
+				return -ENOMEM;
+			}
+		} else {
+			err = idr_alloc_ext(&tp_c->handle_idr, ht, NULL,
+					    handle, handle + 1, GFP_KERNEL);
+			if (err) {
+				kfree(ht);
+				return err;
+			}
+		}
 		ht->tp_c = tp_c;
 		ht->refcnt = 1;
 		ht->divisor = divisor;
 		ht->handle = handle;
 		ht->prio = tp->prio;
+		idr_init(&ht->handle_idr);
 
 		err = u32_replace_hw_hnode(tp, ht, flags);
 		if (err) {
+			idr_remove_ext(&tp_c->handle_idr, handle);
 			kfree(ht);
 			return err;
 		}
@@ -1009,24 +1020,33 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		if (TC_U32_HTID(handle) && TC_U32_HTID(handle^htid))
 			return -EINVAL;
 		handle = htid | TC_U32_NODE(handle);
+		err = idr_alloc_ext(&ht->handle_idr, NULL, NULL,
+				    handle, handle + 1,
+				    GFP_KERNEL);
+		if (err)
+			return err;
 	} else
 		handle = gen_new_kid(ht, htid);
 
-	if (tb[TCA_U32_SEL] == NULL)
-		return -EINVAL;
+	if (tb[TCA_U32_SEL] == NULL) {
+		err = -EINVAL;
+		goto erridr;
+	}
 
 	s = nla_data(tb[TCA_U32_SEL]);
 
 	n = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL);
-	if (n == NULL)
-		return -ENOBUFS;
+	if (n == NULL) {
+		err = -ENOBUFS;
+		goto erridr;
+	}
 
 #ifdef CONFIG_CLS_U32_PERF
 	size = sizeof(struct tc_u32_pcnt) + s->nkeys * sizeof(u64);
 	n->pf = __alloc_percpu(size, __alignof__(struct tc_u32_pcnt));
 	if (!n->pf) {
-		kfree(n);
-		return -ENOBUFS;
+		err = -ENOBUFS;
+		goto errfree;
 	}
 #endif
 
@@ -1089,9 +1109,12 @@ errhw:
 errout:
 	tcf_exts_destroy(&n->exts);
 #ifdef CONFIG_CLS_U32_PERF
+errfree:
 	free_percpu(n->pf);
 #endif
 	kfree(n);
+erridr:
+	idr_remove_ext(&ht->handle_idr, handle);
 	return err;
 }
 
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 03b677bc0700..1331a4c2d8ff 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -178,7 +178,7 @@ static int tcf_em_validate(struct tcf_proto *tp,
 	struct tcf_ematch_hdr *em_hdr = nla_data(nla);
 	int data_len = nla_len(nla) - sizeof(*em_hdr);
 	void *data = (void *) em_hdr + sizeof(*em_hdr);
-	struct net *net = dev_net(qdisc_dev(tp->q));
+	struct net *net = tp->chain->block->net;
 
 	if (!TCF_EM_REL_VALID(em_hdr->flags))
 		goto errout;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 22bc6fc48311..b6c4f536876b 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1502,7 +1502,6 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
 	int s_idx, s_q_idx;
 	struct net_device *dev;
 	const struct nlmsghdr *nlh = cb->nlh;
-	struct tcmsg *tcm = nlmsg_data(nlh);
 	struct nlattr *tca[TCA_MAX + 1];
 	int err;
 
@@ -1512,7 +1511,7 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
 	idx = 0;
 	ASSERT_RTNL();
 
-	err = nlmsg_parse(nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL);
+	err = nlmsg_parse(nlh, sizeof(struct tcmsg), tca, TCA_MAX, NULL, NULL);
 	if (err < 0)
 		return err;
 
@@ -1664,9 +1663,11 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
 	struct tcf_bind_args *a = (void *)arg;
 
 	if (tp->ops->bind_class) {
-		tcf_tree_lock(tp);
+		struct Qdisc *q = tcf_block_q(tp->chain->block);
+
+		sch_tree_lock(q);
 		tp->ops->bind_class(n, a->classid, a->cl);
-		tcf_tree_unlock(tp);
+		sch_tree_unlock(q);
 	}
 	return 0;
 }
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index c5fcdf1a58a0..2dbd249c0b2f 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -281,7 +281,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent,
 		goto err_out;
 	}
 
-	error = tcf_block_get(&flow->block, &flow->filter_list);
+	error = tcf_block_get(&flow->block, &flow->filter_list, sch);
 	if (error) {
 		kfree(flow);
 		goto err_out;
@@ -546,7 +546,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt)
 		p->link.q = &noop_qdisc;
 	pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q);
 
-	err = tcf_block_get(&p->link.block, &p->link.filter_list);
+	err = tcf_block_get(&p->link.block, &p->link.filter_list, sch);
 	if (err)
 		return err;
 
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index dcef97fa8047..6361be7881f1 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -255,6 +255,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 		case TC_ACT_STOLEN:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			/* fall through */
 		case TC_ACT_SHOT:
 			return NULL;
 		case TC_ACT_RECLASSIFY:
@@ -1566,7 +1567,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 	if (cl == NULL)
 		goto failure;
 
-	err = tcf_block_get(&cl->block, &cl->filter_list);
+	err = tcf_block_get(&cl->block, &cl->filter_list, sch);
 	if (err) {
 		kfree(cl);
 		return err;
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
new file mode 100644
index 000000000000..bdb533b7fb8c
--- /dev/null
+++ b/net/sched/sch_cbs.c
@@ -0,0 +1,373 @@
+/*
+ * net/sched/sch_cbs.c	Credit Based Shaper
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Vinicius Costa Gomes <vinicius.gomes@intel.com>
+ *
+ */
+
+/* Credit Based Shaper (CBS)
+ * =========================
+ *
+ * This is a simple rate-limiting shaper aimed at TSN applications on
+ * systems with known traffic workloads.
+ *
+ * Its algorithm is defined by the IEEE 802.1Q-2014 Specification,
+ * Section 8.6.8.2, and explained in more detail in the Annex L of the
+ * same specification.
+ *
+ * There are four tunables to be considered:
+ *
+ *	'idleslope': Idleslope is the rate of credits that is
+ *	accumulated (in kilobits per second) when there is at least
+ *	one packet waiting for transmission. Packets are transmitted
+ *	when the current value of credits is equal or greater than
+ *	zero. When there is no packet to be transmitted the amount of
+ *	credits is set to zero. This is the main tunable of the CBS
+ *	algorithm.
+ *
+ *	'sendslope':
+ *	Sendslope is the rate of credits that is depleted (it should be a
+ *	negative number of kilobits per second) when a transmission is
+ *	ocurring. It can be calculated as follows, (IEEE 802.1Q-2014 Section
+ *	8.6.8.2 item g):
+ *
+ *	sendslope = idleslope - port_transmit_rate
+ *
+ *	'hicredit': Hicredit defines the maximum amount of credits (in
+ *	bytes) that can be accumulated. Hicredit depends on the
+ *	characteristics of interfering traffic,
+ *	'max_interference_size' is the maximum size of any burst of
+ *	traffic that can delay the transmission of a frame that is
+ *	available for transmission for this traffic class, (IEEE
+ *	802.1Q-2014 Annex L, Equation L-3):
+ *
+ *	hicredit = max_interference_size * (idleslope / port_transmit_rate)
+ *
+ *	'locredit': Locredit is the minimum amount of credits that can
+ *	be reached. It is a function of the traffic flowing through
+ *	this qdisc (IEEE 802.1Q-2014 Annex L, Equation L-2):
+ *
+ *	locredit = max_frame_size * (sendslope / port_transmit_rate)
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/netlink.h>
+#include <net/sch_generic.h>
+#include <net/pkt_sched.h>
+
+#define BYTES_PER_KBIT (1000LL / 8)
+
+struct cbs_sched_data {
+	bool offload;
+	int queue;
+	s64 port_rate; /* in bytes/s */
+	s64 last; /* timestamp in ns */
+	s64 credits; /* in bytes */
+	s32 locredit; /* in bytes */
+	s32 hicredit; /* in bytes */
+	s64 sendslope; /* in bytes/s */
+	s64 idleslope; /* in bytes/s */
+	struct qdisc_watchdog watchdog;
+	int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch);
+	struct sk_buff *(*dequeue)(struct Qdisc *sch);
+};
+
+static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch)
+{
+	return qdisc_enqueue_tail(skb, sch);
+}
+
+static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+
+	if (sch->q.qlen == 0 && q->credits > 0) {
+		/* We need to stop accumulating credits when there's
+		 * no enqueued packets and q->credits is positive.
+		 */
+		q->credits = 0;
+		q->last = ktime_get_ns();
+	}
+
+	return qdisc_enqueue_tail(skb, sch);
+}
+
+static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+
+	return q->enqueue(skb, sch);
+}
+
+/* timediff is in ns, slope is in bytes/s */
+static s64 timediff_to_credits(s64 timediff, s64 slope)
+{
+	return div64_s64(timediff * slope, NSEC_PER_SEC);
+}
+
+static s64 delay_from_credits(s64 credits, s64 slope)
+{
+	if (unlikely(slope == 0))
+		return S64_MAX;
+
+	return div64_s64(-credits * NSEC_PER_SEC, slope);
+}
+
+static s64 credits_from_len(unsigned int len, s64 slope, s64 port_rate)
+{
+	if (unlikely(port_rate == 0))
+		return S64_MAX;
+
+	return div64_s64(len * slope, port_rate);
+}
+
+static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+	s64 now = ktime_get_ns();
+	struct sk_buff *skb;
+	s64 credits;
+	int len;
+
+	if (q->credits < 0) {
+		credits = timediff_to_credits(now - q->last, q->idleslope);
+
+		credits = q->credits + credits;
+		q->credits = min_t(s64, credits, q->hicredit);
+
+		if (q->credits < 0) {
+			s64 delay;
+
+			delay = delay_from_credits(q->credits, q->idleslope);
+			qdisc_watchdog_schedule_ns(&q->watchdog, now + delay);
+
+			q->last = now;
+
+			return NULL;
+		}
+	}
+
+	skb = qdisc_dequeue_head(sch);
+	if (!skb)
+		return NULL;
+
+	len = qdisc_pkt_len(skb);
+
+	/* As sendslope is a negative number, this will decrease the
+	 * amount of q->credits.
+	 */
+	credits = credits_from_len(len, q->sendslope, q->port_rate);
+	credits += q->credits;
+
+	q->credits = max_t(s64, credits, q->locredit);
+	q->last = now;
+
+	return skb;
+}
+
+static struct sk_buff *cbs_dequeue_offload(struct Qdisc *sch)
+{
+	return qdisc_dequeue_head(sch);
+}
+
+static struct sk_buff *cbs_dequeue(struct Qdisc *sch)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+
+	return q->dequeue(sch);
+}
+
+static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = {
+	[TCA_CBS_PARMS]	= { .len = sizeof(struct tc_cbs_qopt) },
+};
+
+static void cbs_disable_offload(struct net_device *dev,
+				struct cbs_sched_data *q)
+{
+	struct tc_cbs_qopt_offload cbs = { };
+	const struct net_device_ops *ops;
+	int err;
+
+	if (!q->offload)
+		return;
+
+	q->enqueue = cbs_enqueue_soft;
+	q->dequeue = cbs_dequeue_soft;
+
+	ops = dev->netdev_ops;
+	if (!ops->ndo_setup_tc)
+		return;
+
+	cbs.queue = q->queue;
+	cbs.enable = 0;
+
+	err = ops->ndo_setup_tc(dev, TC_SETUP_CBS, &cbs);
+	if (err < 0)
+		pr_warn("Couldn't disable CBS offload for queue %d\n",
+			cbs.queue);
+}
+
+static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q,
+			      const struct tc_cbs_qopt *opt)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	struct tc_cbs_qopt_offload cbs = { };
+	int err;
+
+	if (!ops->ndo_setup_tc)
+		return -EOPNOTSUPP;
+
+	cbs.queue = q->queue;
+
+	cbs.enable = 1;
+	cbs.hicredit = opt->hicredit;
+	cbs.locredit = opt->locredit;
+	cbs.idleslope = opt->idleslope;
+	cbs.sendslope = opt->sendslope;
+
+	err = ops->ndo_setup_tc(dev, TC_SETUP_CBS, &cbs);
+	if (err < 0)
+		return err;
+
+	q->enqueue = cbs_enqueue_offload;
+	q->dequeue = cbs_dequeue_offload;
+
+	return 0;
+}
+
+static int cbs_change(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	struct nlattr *tb[TCA_CBS_MAX + 1];
+	struct tc_cbs_qopt *qopt;
+	int err;
+
+	err = nla_parse_nested(tb, TCA_CBS_MAX, opt, cbs_policy, NULL);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_CBS_PARMS])
+		return -EINVAL;
+
+	qopt = nla_data(tb[TCA_CBS_PARMS]);
+
+	if (!qopt->offload) {
+		struct ethtool_link_ksettings ecmd;
+		s64 link_speed;
+
+		if (!__ethtool_get_link_ksettings(dev, &ecmd))
+			link_speed = ecmd.base.speed;
+		else
+			link_speed = SPEED_1000;
+
+		q->port_rate = link_speed * 1000 * BYTES_PER_KBIT;
+
+		cbs_disable_offload(dev, q);
+	} else {
+		err = cbs_enable_offload(dev, q, qopt);
+		if (err < 0)
+			return err;
+	}
+
+	/* Everything went OK, save the parameters used. */
+	q->hicredit = qopt->hicredit;
+	q->locredit = qopt->locredit;
+	q->idleslope = qopt->idleslope * BYTES_PER_KBIT;
+	q->sendslope = qopt->sendslope * BYTES_PER_KBIT;
+	q->offload = qopt->offload;
+
+	return 0;
+}
+
+static int cbs_init(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+
+	if (!opt)
+		return -EINVAL;
+
+	q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
+
+	q->enqueue = cbs_enqueue_soft;
+	q->dequeue = cbs_dequeue_soft;
+
+	qdisc_watchdog_init(&q->watchdog, sch);
+
+	return cbs_change(sch, opt);
+}
+
+static void cbs_destroy(struct Qdisc *sch)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+
+	qdisc_watchdog_cancel(&q->watchdog);
+
+	cbs_disable_offload(dev, q);
+}
+
+static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct tc_cbs_qopt opt = { };
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, TCA_OPTIONS);
+	if (!nest)
+		goto nla_put_failure;
+
+	opt.hicredit = q->hicredit;
+	opt.locredit = q->locredit;
+	opt.sendslope = div64_s64(q->sendslope, BYTES_PER_KBIT);
+	opt.idleslope = div64_s64(q->idleslope, BYTES_PER_KBIT);
+	opt.offload = q->offload;
+
+	if (nla_put(skb, TCA_CBS_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	return nla_nest_end(skb, nest);
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -1;
+}
+
+static struct Qdisc_ops cbs_qdisc_ops __read_mostly = {
+	.id		=	"cbs",
+	.priv_size	=	sizeof(struct cbs_sched_data),
+	.enqueue	=	cbs_enqueue,
+	.dequeue	=	cbs_dequeue,
+	.peek		=	qdisc_peek_dequeued,
+	.init		=	cbs_init,
+	.reset		=	qdisc_reset_queue,
+	.destroy	=	cbs_destroy,
+	.change		=	cbs_change,
+	.dump		=	cbs_dump,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init cbs_module_init(void)
+{
+	return register_qdisc(&cbs_qdisc_ops);
+}
+
+static void __exit cbs_module_exit(void)
+{
+	unregister_qdisc(&cbs_qdisc_ops);
+}
+module_init(cbs_module_init)
+module_exit(cbs_module_exit)
+MODULE_LICENSE("GPL");
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 2d0e8d4bdc29..5bbcef3dcd8c 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -321,6 +321,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
 		case TC_ACT_STOLEN:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			/* fall through */
 		case TC_ACT_SHOT:
 			return NULL;
 		}
@@ -412,7 +413,7 @@ static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 	struct drr_sched *q = qdisc_priv(sch);
 	int err;
 
-	err = tcf_block_get(&q->block, &q->filter_list);
+	err = tcf_block_get(&q->block, &q->filter_list, sch);
 	if (err)
 		return err;
 	err = qdisc_class_hash_init(&q->clhash);
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 2836c80c7aa5..fb4fb71c68cf 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -344,7 +344,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
 	if (!opt)
 		goto errout;
 
-	err = tcf_block_get(&p->block, &p->filter_list);
+	err = tcf_block_get(&p->block, &p->filter_list, sch);
 	if (err)
 		return err;
 
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index de3b57ceca7b..0305d791ea94 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -105,6 +105,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch,
 		case TC_ACT_QUEUED:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			/* fall through */
 		case TC_ACT_SHOT:
 			return 0;
 		}
@@ -481,7 +482,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt)
 			return err;
 	}
 
-	err = tcf_block_get(&q->block, &q->filter_list);
+	err = tcf_block_get(&q->block, &q->filter_list, sch);
 	if (err)
 		return err;
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index bf8c81e07c70..3839cbbdc32b 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -288,9 +288,9 @@ unsigned long dev_trans_start(struct net_device *dev)
 }
 EXPORT_SYMBOL(dev_trans_start);
 
-static void dev_watchdog(unsigned long arg)
+static void dev_watchdog(struct timer_list *t)
 {
-	struct net_device *dev = (struct net_device *)arg;
+	struct net_device *dev = from_timer(dev, t, watchdog_timer);
 
 	netif_tx_lock(dev);
 	if (!qdisc_tx_is_noop(dev)) {
@@ -603,8 +603,14 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	struct Qdisc *sch;
 	unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size;
 	int err = -ENOBUFS;
-	struct net_device *dev = dev_queue->dev;
+	struct net_device *dev;
+
+	if (!dev_queue) {
+		err = -EINVAL;
+		goto errout;
+	}
 
+	dev = dev_queue->dev;
 	p = kzalloc_node(size, GFP_KERNEL,
 			 netdev_queue_numa_node_read(dev_queue));
 
@@ -689,10 +695,8 @@ void qdisc_reset(struct Qdisc *qdisc)
 }
 EXPORT_SYMBOL(qdisc_reset);
 
-static void qdisc_rcu_free(struct rcu_head *head)
+static void qdisc_free(struct Qdisc *qdisc)
 {
-	struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head);
-
 	if (qdisc_is_percpu_stats(qdisc)) {
 		free_percpu(qdisc->cpu_bstats);
 		free_percpu(qdisc->cpu_qstats);
@@ -725,11 +729,7 @@ void qdisc_destroy(struct Qdisc *qdisc)
 
 	kfree_skb_list(qdisc->gso_skb);
 	kfree_skb(qdisc->skb_bad_txq);
-	/*
-	 * gen_estimator est_timer() might access qdisc->q.lock,
-	 * wait a RCU grace period before freeing qdisc.
-	 */
-	call_rcu(&qdisc->rcu_head, qdisc_rcu_free);
+	qdisc_free(qdisc);
 }
 EXPORT_SYMBOL(qdisc_destroy);
 
@@ -960,7 +960,7 @@ void dev_init_scheduler(struct net_device *dev)
 	if (dev_ingress_queue(dev))
 		dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
 
-	setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev);
+	timer_setup(&dev->watchdog_timer, dev_watchdog, 0);
 }
 
 static void shutdown_scheduler_queue(struct net_device *dev,
@@ -1024,3 +1024,49 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r,
 	}
 }
 EXPORT_SYMBOL(psched_ratecfg_precompute);
+
+static void mini_qdisc_rcu_func(struct rcu_head *head)
+{
+}
+
+void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
+			  struct tcf_proto *tp_head)
+{
+	struct mini_Qdisc *miniq_old = rtnl_dereference(*miniqp->p_miniq);
+	struct mini_Qdisc *miniq;
+
+	if (!tp_head) {
+		RCU_INIT_POINTER(*miniqp->p_miniq, NULL);
+		return;
+	}
+
+	miniq = !miniq_old || miniq_old == &miniqp->miniq2 ?
+		&miniqp->miniq1 : &miniqp->miniq2;
+
+	/* We need to make sure that readers won't see the miniq
+	 * we are about to modify. So wait until previous call_rcu_bh callback
+	 * is done.
+	 */
+	rcu_barrier_bh();
+	miniq->filter_list = tp_head;
+	rcu_assign_pointer(*miniqp->p_miniq, miniq);
+
+	if (miniq_old)
+		/* This is counterpart of the rcu barrier above. We need to
+		 * block potential new user of miniq_old until all readers
+		 * are not seeing it.
+		 */
+		call_rcu_bh(&miniq_old->rcu, mini_qdisc_rcu_func);
+}
+EXPORT_SYMBOL(mini_qdisc_pair_swap);
+
+void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
+			  struct mini_Qdisc __rcu **p_miniq)
+{
+	miniqp->miniq1.cpu_bstats = qdisc->cpu_bstats;
+	miniqp->miniq1.cpu_qstats = qdisc->cpu_qstats;
+	miniqp->miniq2.cpu_bstats = qdisc->cpu_bstats;
+	miniqp->miniq2.cpu_qstats = qdisc->cpu_qstats;
+	miniqp->p_miniq = p_miniq;
+}
+EXPORT_SYMBOL(mini_qdisc_pair_init);
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 3f88b75488b0..d04068a97d81 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1033,7 +1033,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 	if (cl == NULL)
 		return -ENOBUFS;
 
-	err = tcf_block_get(&cl->block, &cl->filter_list);
+	err = tcf_block_get(&cl->block, &cl->filter_list, sch);
 	if (err) {
 		kfree(cl);
 		return err;
@@ -1144,6 +1144,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 		case TC_ACT_STOLEN:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			/* fall through */
 		case TC_ACT_SHOT:
 			return NULL;
 		}
@@ -1405,7 +1406,7 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 		return err;
 	q->eligible = RB_ROOT;
 
-	err = tcf_block_get(&q->root.block, &q->root.filter_list);
+	err = tcf_block_get(&q->root.block, &q->root.filter_list, sch);
 	if (err)
 		return err;
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 7e148376ba52..fa0380730ff0 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -142,6 +142,7 @@ struct htb_class {
 	struct rb_node		node[TC_HTB_NUMPRIO];	/* node for self or feed tree */
 
 	unsigned int drops ____cacheline_aligned_in_smp;
+	unsigned int		overlimits;
 };
 
 struct htb_level {
@@ -243,6 +244,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
 		case TC_ACT_STOLEN:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			/* fall through */
 		case TC_ACT_SHOT:
 			return NULL;
 		}
@@ -533,6 +535,9 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff)
 	if (new_mode == cl->cmode)
 		return;
 
+	if (new_mode == HTB_CANT_SEND)
+		cl->overlimits++;
+
 	if (cl->prio_activity) {	/* not necessary: speed optimization */
 		if (cl->cmode != HTB_CANT_SEND)
 			htb_deactivate_prios(q, cl);
@@ -1026,7 +1031,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt)
 	if (!opt)
 		return -EINVAL;
 
-	err = tcf_block_get(&q->block, &q->filter_list);
+	err = tcf_block_get(&q->block, &q->filter_list, sch);
 	if (err)
 		return err;
 
@@ -1143,6 +1148,7 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d)
 	struct htb_class *cl = (struct htb_class *)arg;
 	struct gnet_stats_queue qs = {
 		.drops = cl->drops,
+		.overlimits = cl->overlimits,
 	};
 	__u32 qlen = 0;
 
@@ -1388,7 +1394,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		if (!cl)
 			goto failure;
 
-		err = tcf_block_get(&cl->block, &cl->filter_list);
+		err = tcf_block_get(&cl->block, &cl->filter_list, sch);
 		if (err) {
 			kfree(cl);
 			goto failure;
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 44de4ee51ce9..5ecc38f35d47 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -20,6 +20,8 @@
 
 struct ingress_sched_data {
 	struct tcf_block *block;
+	struct tcf_block_ext_info block_info;
+	struct mini_Qdisc_pair miniqp;
 };
 
 static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg)
@@ -53,13 +55,26 @@ static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl)
 	return q->block;
 }
 
+static void clsact_chain_head_change(struct tcf_proto *tp_head, void *priv)
+{
+	struct mini_Qdisc_pair *miniqp = priv;
+
+	mini_qdisc_pair_swap(miniqp, tp_head);
+}
+
 static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct ingress_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
 	int err;
 
-	err = tcf_block_get(&q->block, &dev->ingress_cl_list);
+	mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress);
+
+	q->block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
+	q->block_info.chain_head_change = clsact_chain_head_change;
+	q->block_info.chain_head_change_priv = &q->miniqp;
+
+	err = tcf_block_get_ext(&q->block, sch, &q->block_info);
 	if (err)
 		return err;
 
@@ -73,7 +88,7 @@ static void ingress_destroy(struct Qdisc *sch)
 {
 	struct ingress_sched_data *q = qdisc_priv(sch);
 
-	tcf_block_put(q->block);
+	tcf_block_put_ext(q->block, sch, &q->block_info);
 	net_dec_ingress_queue();
 }
 
@@ -114,6 +129,10 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = {
 struct clsact_sched_data {
 	struct tcf_block *ingress_block;
 	struct tcf_block *egress_block;
+	struct tcf_block_ext_info ingress_block_info;
+	struct tcf_block_ext_info egress_block_info;
+	struct mini_Qdisc_pair miniqp_ingress;
+	struct mini_Qdisc_pair miniqp_egress;
 };
 
 static unsigned long clsact_find(struct Qdisc *sch, u32 classid)
@@ -153,13 +172,25 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
 	struct net_device *dev = qdisc_dev(sch);
 	int err;
 
-	err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list);
+	mini_qdisc_pair_init(&q->miniqp_ingress, sch, &dev->miniq_ingress);
+
+	q->ingress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
+	q->ingress_block_info.chain_head_change = clsact_chain_head_change;
+	q->ingress_block_info.chain_head_change_priv = &q->miniqp_ingress;
+
+	err = tcf_block_get_ext(&q->ingress_block, sch, &q->ingress_block_info);
 	if (err)
 		return err;
 
-	err = tcf_block_get(&q->egress_block, &dev->egress_cl_list);
+	mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress);
+
+	q->egress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS;
+	q->egress_block_info.chain_head_change = clsact_chain_head_change;
+	q->egress_block_info.chain_head_change_priv = &q->miniqp_egress;
+
+	err = tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info);
 	if (err)
-		return err;
+		goto err_egress_block_get;
 
 	net_inc_ingress_queue();
 	net_inc_egress_queue();
@@ -167,14 +198,18 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
 	sch->flags |= TCQ_F_CPUSTATS;
 
 	return 0;
+
+err_egress_block_get:
+	tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info);
+	return err;
 }
 
 static void clsact_destroy(struct Qdisc *sch)
 {
 	struct clsact_sched_data *q = qdisc_priv(sch);
 
-	tcf_block_put(q->egress_block);
-	tcf_block_put(q->ingress_block);
+	tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
+	tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info);
 
 	net_dec_ingress_queue();
 	net_dec_egress_queue();
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index f3a3e507422b..213b586a06a0 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -130,15 +130,7 @@ static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl)
 static struct netdev_queue *mq_select_queue(struct Qdisc *sch,
 					    struct tcmsg *tcm)
 {
-	unsigned int ntx = TC_H_MIN(tcm->tcm_parent);
-	struct netdev_queue *dev_queue = mq_queue_get(sch, ntx);
-
-	if (!dev_queue) {
-		struct net_device *dev = qdisc_dev(sch);
-
-		return netdev_get_tx_queue(dev, 0);
-	}
-	return dev_queue;
+	return mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent));
 }
 
 static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 6bcdfe6e7b63..4d5ed45123f0 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -18,10 +18,16 @@
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/sch_generic.h>
+#include <net/pkt_cls.h>
 
 struct mqprio_sched {
 	struct Qdisc		**qdiscs;
+	u16 mode;
+	u16 shaper;
 	int hw_offload;
+	u32 flags;
+	u64 min_rate[TC_QOPT_MAX_QUEUE];
+	u64 max_rate[TC_QOPT_MAX_QUEUE];
 };
 
 static void mqprio_destroy(struct Qdisc *sch)
@@ -39,9 +45,17 @@ static void mqprio_destroy(struct Qdisc *sch)
 	}
 
 	if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) {
-		struct tc_mqprio_qopt mqprio = {};
+		struct tc_mqprio_qopt_offload mqprio = { { 0 } };
 
-		dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, &mqprio);
+		switch (priv->mode) {
+		case TC_MQPRIO_MODE_DCB:
+		case TC_MQPRIO_MODE_CHANNEL:
+			dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO,
+						      &mqprio);
+			break;
+		default:
+			return;
+		}
 	} else {
 		netdev_set_num_tc(dev, 0);
 	}
@@ -97,6 +111,26 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt)
 	return 0;
 }
 
+static const struct nla_policy mqprio_policy[TCA_MQPRIO_MAX + 1] = {
+	[TCA_MQPRIO_MODE]	= { .len = sizeof(u16) },
+	[TCA_MQPRIO_SHAPER]	= { .len = sizeof(u16) },
+	[TCA_MQPRIO_MIN_RATE64]	= { .type = NLA_NESTED },
+	[TCA_MQPRIO_MAX_RATE64]	= { .type = NLA_NESTED },
+};
+
+static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+		      const struct nla_policy *policy, int len)
+{
+	int nested_len = nla_len(nla) - NLA_ALIGN(len);
+
+	if (nested_len >= nla_attr_size(0))
+		return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len),
+				 nested_len, policy, NULL);
+
+	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
+	return 0;
+}
+
 static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct net_device *dev = qdisc_dev(sch);
@@ -105,6 +139,10 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 	struct Qdisc *qdisc;
 	int i, err = -EOPNOTSUPP;
 	struct tc_mqprio_qopt *qopt = NULL;
+	struct nlattr *tb[TCA_MQPRIO_MAX + 1];
+	struct nlattr *attr;
+	int rem;
+	int len;
 
 	BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE);
 	BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK);
@@ -115,6 +153,10 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 	if (!netif_is_multiqueue(dev))
 		return -EOPNOTSUPP;
 
+	/* make certain can allocate enough classids to handle queues */
+	if (dev->num_tx_queues >= TC_H_MIN_PRIORITY)
+		return -ENOMEM;
+
 	if (!opt || nla_len(opt) < sizeof(*qopt))
 		return -EINVAL;
 
@@ -122,6 +164,59 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 	if (mqprio_parse_opt(dev, qopt))
 		return -EINVAL;
 
+	len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt));
+	if (len > 0) {
+		err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy,
+				 sizeof(*qopt));
+		if (err < 0)
+			return err;
+
+		if (!qopt->hw)
+			return -EINVAL;
+
+		if (tb[TCA_MQPRIO_MODE]) {
+			priv->flags |= TC_MQPRIO_F_MODE;
+			priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]);
+		}
+
+		if (tb[TCA_MQPRIO_SHAPER]) {
+			priv->flags |= TC_MQPRIO_F_SHAPER;
+			priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]);
+		}
+
+		if (tb[TCA_MQPRIO_MIN_RATE64]) {
+			if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE)
+				return -EINVAL;
+			i = 0;
+			nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64],
+					    rem) {
+				if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64)
+					return -EINVAL;
+				if (i >= qopt->num_tc)
+					break;
+				priv->min_rate[i] = *(u64 *)nla_data(attr);
+				i++;
+			}
+			priv->flags |= TC_MQPRIO_F_MIN_RATE;
+		}
+
+		if (tb[TCA_MQPRIO_MAX_RATE64]) {
+			if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE)
+				return -EINVAL;
+			i = 0;
+			nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64],
+					    rem) {
+				if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64)
+					return -EINVAL;
+				if (i >= qopt->num_tc)
+					break;
+				priv->max_rate[i] = *(u64 *)nla_data(attr);
+				i++;
+			}
+			priv->flags |= TC_MQPRIO_F_MAX_RATE;
+		}
+	}
+
 	/* pre-allocate qdisc, attachment can't fail */
 	priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
 			       GFP_KERNEL);
@@ -146,14 +241,36 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 	 * supplied and verified mapping
 	 */
 	if (qopt->hw) {
-		struct tc_mqprio_qopt mqprio = *qopt;
+		struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt};
 
-		err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO,
+		switch (priv->mode) {
+		case TC_MQPRIO_MODE_DCB:
+			if (priv->shaper != TC_MQPRIO_SHAPER_DCB)
+				return -EINVAL;
+			break;
+		case TC_MQPRIO_MODE_CHANNEL:
+			mqprio.flags = priv->flags;
+			if (priv->flags & TC_MQPRIO_F_MODE)
+				mqprio.mode = priv->mode;
+			if (priv->flags & TC_MQPRIO_F_SHAPER)
+				mqprio.shaper = priv->shaper;
+			if (priv->flags & TC_MQPRIO_F_MIN_RATE)
+				for (i = 0; i < mqprio.qopt.num_tc; i++)
+					mqprio.min_rate[i] = priv->min_rate[i];
+			if (priv->flags & TC_MQPRIO_F_MAX_RATE)
+				for (i = 0; i < mqprio.qopt.num_tc; i++)
+					mqprio.max_rate[i] = priv->max_rate[i];
+			break;
+		default:
+			return -EINVAL;
+		}
+		err = dev->netdev_ops->ndo_setup_tc(dev,
+						    TC_SETUP_MQPRIO,
 						    &mqprio);
 		if (err)
 			return err;
 
-		priv->hw_offload = mqprio.hw;
+		priv->hw_offload = mqprio.qopt.hw;
 	} else {
 		netdev_set_num_tc(dev, qopt->num_tc);
 		for (i = 0; i < qopt->num_tc; i++)
@@ -193,7 +310,7 @@ static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch,
 					     unsigned long cl)
 {
 	struct net_device *dev = qdisc_dev(sch);
-	unsigned long ntx = cl - 1 - netdev_get_num_tc(dev);
+	unsigned long ntx = cl - 1;
 
 	if (ntx >= dev->num_tx_queues)
 		return NULL;
@@ -223,11 +340,51 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
 	return 0;
 }
 
+static int dump_rates(struct mqprio_sched *priv,
+		      struct tc_mqprio_qopt *opt, struct sk_buff *skb)
+{
+	struct nlattr *nest;
+	int i;
+
+	if (priv->flags & TC_MQPRIO_F_MIN_RATE) {
+		nest = nla_nest_start(skb, TCA_MQPRIO_MIN_RATE64);
+		if (!nest)
+			goto nla_put_failure;
+
+		for (i = 0; i < opt->num_tc; i++) {
+			if (nla_put(skb, TCA_MQPRIO_MIN_RATE64,
+				    sizeof(priv->min_rate[i]),
+				    &priv->min_rate[i]))
+				goto nla_put_failure;
+		}
+		nla_nest_end(skb, nest);
+	}
+
+	if (priv->flags & TC_MQPRIO_F_MAX_RATE) {
+		nest = nla_nest_start(skb, TCA_MQPRIO_MAX_RATE64);
+		if (!nest)
+			goto nla_put_failure;
+
+		for (i = 0; i < opt->num_tc; i++) {
+			if (nla_put(skb, TCA_MQPRIO_MAX_RATE64,
+				    sizeof(priv->max_rate[i]),
+				    &priv->max_rate[i]))
+				goto nla_put_failure;
+		}
+		nla_nest_end(skb, nest);
+	}
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -1;
+}
+
 static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct net_device *dev = qdisc_dev(sch);
 	struct mqprio_sched *priv = qdisc_priv(sch);
-	unsigned char *b = skb_tail_pointer(skb);
+	struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb);
 	struct tc_mqprio_qopt opt = { 0 };
 	struct Qdisc *qdisc;
 	unsigned int i;
@@ -258,12 +415,25 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 		opt.offset[i] = dev->tc_to_txq[i].offset;
 	}
 
-	if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
+	if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt))
+		goto nla_put_failure;
+
+	if ((priv->flags & TC_MQPRIO_F_MODE) &&
+	    nla_put_u16(skb, TCA_MQPRIO_MODE, priv->mode))
 		goto nla_put_failure;
 
-	return skb->len;
+	if ((priv->flags & TC_MQPRIO_F_SHAPER) &&
+	    nla_put_u16(skb, TCA_MQPRIO_SHAPER, priv->shaper))
+		goto nla_put_failure;
+
+	if ((priv->flags & TC_MQPRIO_F_MIN_RATE ||
+	     priv->flags & TC_MQPRIO_F_MAX_RATE) &&
+	    (dump_rates(priv, &opt, skb) != 0))
+		goto nla_put_failure;
+
+	return nla_nest_end(skb, nla);
 nla_put_failure:
-	nlmsg_trim(skb, b);
+	nlmsg_trim(skb, nla);
 	return -1;
 }
 
@@ -282,38 +452,35 @@ static unsigned long mqprio_find(struct Qdisc *sch, u32 classid)
 	struct net_device *dev = qdisc_dev(sch);
 	unsigned int ntx = TC_H_MIN(classid);
 
-	if (ntx > dev->num_tx_queues + netdev_get_num_tc(dev))
-		return 0;
-	return ntx;
+	/* There are essentially two regions here that have valid classid
+	 * values. The first region will have a classid value of 1 through
+	 * num_tx_queues. All of these are backed by actual Qdiscs.
+	 */
+	if (ntx < TC_H_MIN_PRIORITY)
+		return (ntx <= dev->num_tx_queues) ? ntx : 0;
+
+	/* The second region represents the hardware traffic classes. These
+	 * are represented by classid values of TC_H_MIN_PRIORITY through
+	 * TC_H_MIN_PRIORITY + netdev_get_num_tc - 1
+	 */
+	return ((ntx - TC_H_MIN_PRIORITY) < netdev_get_num_tc(dev)) ? ntx : 0;
 }
 
 static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl,
 			 struct sk_buff *skb, struct tcmsg *tcm)
 {
-	struct net_device *dev = qdisc_dev(sch);
+	if (cl < TC_H_MIN_PRIORITY) {
+		struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
+		struct net_device *dev = qdisc_dev(sch);
+		int tc = netdev_txq_to_tc(dev, cl - 1);
 
-	if (cl <= netdev_get_num_tc(dev)) {
+		tcm->tcm_parent = (tc < 0) ? 0 :
+			TC_H_MAKE(TC_H_MAJ(sch->handle),
+				  TC_H_MIN(tc + TC_H_MIN_PRIORITY));
+		tcm->tcm_info = dev_queue->qdisc_sleeping->handle;
+	} else {
 		tcm->tcm_parent = TC_H_ROOT;
 		tcm->tcm_info = 0;
-	} else {
-		int i;
-		struct netdev_queue *dev_queue;
-
-		dev_queue = mqprio_queue_get(sch, cl);
-		tcm->tcm_parent = 0;
-		for (i = 0; i < netdev_get_num_tc(dev); i++) {
-			struct netdev_tc_txq tc = dev->tc_to_txq[i];
-			int q_idx = cl - netdev_get_num_tc(dev);
-
-			if (q_idx > tc.offset &&
-			    q_idx <= tc.offset + tc.count) {
-				tcm->tcm_parent =
-					TC_H_MAKE(TC_H_MAJ(sch->handle),
-						  TC_H_MIN(i + 1));
-				break;
-			}
-		}
-		tcm->tcm_info = dev_queue->qdisc_sleeping->handle;
 	}
 	tcm->tcm_handle |= TC_H_MIN(cl);
 	return 0;
@@ -324,15 +491,14 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	__releases(d->lock)
 	__acquires(d->lock)
 {
-	struct net_device *dev = qdisc_dev(sch);
-
-	if (cl <= netdev_get_num_tc(dev)) {
+	if (cl >= TC_H_MIN_PRIORITY) {
 		int i;
 		__u32 qlen = 0;
 		struct Qdisc *qdisc;
 		struct gnet_stats_queue qstats = {0};
 		struct gnet_stats_basic_packed bstats = {0};
-		struct netdev_tc_txq tc = dev->tc_to_txq[cl - 1];
+		struct net_device *dev = qdisc_dev(sch);
+		struct netdev_tc_txq tc = dev->tc_to_txq[cl & TC_BITMASK];
 
 		/* Drop lock here it will be reclaimed before touching
 		 * statistics this is required because the d->lock we
@@ -385,17 +551,36 @@ static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
 
 	/* Walk hierarchy with a virtual class per tc */
 	arg->count = arg->skip;
-	for (ntx = arg->skip;
-	     ntx < dev->num_tx_queues + netdev_get_num_tc(dev);
-	     ntx++) {
+	for (ntx = arg->skip; ntx < netdev_get_num_tc(dev); ntx++) {
+		if (arg->fn(sch, ntx + TC_H_MIN_PRIORITY, arg) < 0) {
+			arg->stop = 1;
+			return;
+		}
+		arg->count++;
+	}
+
+	/* Pad the values and skip over unused traffic classes */
+	if (ntx < TC_MAX_QUEUE) {
+		arg->count = TC_MAX_QUEUE;
+		ntx = TC_MAX_QUEUE;
+	}
+
+	/* Reset offset, sort out remaining per-queue qdiscs */
+	for (ntx -= TC_MAX_QUEUE; ntx < dev->num_tx_queues; ntx++) {
 		if (arg->fn(sch, ntx + 1, arg) < 0) {
 			arg->stop = 1;
-			break;
+			return;
 		}
 		arg->count++;
 	}
 }
 
+static struct netdev_queue *mqprio_select_queue(struct Qdisc *sch,
+						struct tcmsg *tcm)
+{
+	return mqprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent));
+}
+
 static const struct Qdisc_class_ops mqprio_class_ops = {
 	.graft		= mqprio_graft,
 	.leaf		= mqprio_leaf,
@@ -403,6 +588,7 @@ static const struct Qdisc_class_ops mqprio_class_ops = {
 	.walk		= mqprio_walk,
 	.dump		= mqprio_dump_class,
 	.dump_stats	= mqprio_dump_class_stats,
+	.select_queue	= mqprio_select_queue,
 };
 
 static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = {
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index ff4fc3e0facd..012216386c0b 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -54,6 +54,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 	case TC_ACT_QUEUED:
 	case TC_ACT_TRAP:
 		*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+		/* fall through */
 	case TC_ACT_SHOT:
 		return NULL;
 	}
@@ -245,7 +246,7 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt)
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = tcf_block_get(&q->block, &q->filter_list);
+	err = tcf_block_get(&q->block, &q->filter_list, sch);
 	if (err)
 		return err;
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index b1266e75ca43..db0228a65e8c 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -146,15 +146,8 @@ struct netem_sched_data {
  */
 struct netem_skb_cb {
 	psched_time_t	time_to_send;
-	ktime_t		tstamp_save;
 };
 
-
-static struct sk_buff *netem_rb_to_skb(struct rb_node *rb)
-{
-	return rb_entry(rb, struct sk_buff, rbnode);
-}
-
 static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb)
 {
 	/* we assume we can use skb next/prev/tstamp as storage for rb_node */
@@ -362,12 +355,13 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche
 static void tfifo_reset(struct Qdisc *sch)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
-	struct rb_node *p;
+	struct rb_node *p = rb_first(&q->t_root);
 
-	while ((p = rb_first(&q->t_root))) {
-		struct sk_buff *skb = netem_rb_to_skb(p);
+	while (p) {
+		struct sk_buff *skb = rb_to_skb(p);
 
-		rb_erase(p, &q->t_root);
+		p = rb_next(p);
+		rb_erase(&skb->rbnode, &q->t_root);
 		rtnl_kfree_skbs(skb, skb);
 	}
 }
@@ -382,7 +376,7 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 		struct sk_buff *skb;
 
 		parent = *p;
-		skb = netem_rb_to_skb(parent);
+		skb = rb_to_skb(parent);
 		if (tnext >= netem_skb_cb(skb)->time_to_send)
 			p = &parent->rb_right;
 		else
@@ -538,7 +532,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 				struct sk_buff *t_skb;
 				struct netem_skb_cb *t_last;
 
-				t_skb = netem_rb_to_skb(rb_last(&q->t_root));
+				t_skb = skb_rb_last(&q->t_root);
 				t_last = netem_skb_cb(t_skb);
 				if (!last ||
 				    t_last->time_to_send > last->time_to_send) {
@@ -561,7 +555,6 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		}
 
 		cb->time_to_send = now + delay;
-		cb->tstamp_save = skb->tstamp;
 		++q->counter;
 		tfifo_enqueue(skb, sch);
 	} else {
@@ -618,7 +611,7 @@ deliver:
 	if (p) {
 		psched_time_t time_to_send;
 
-		skb = netem_rb_to_skb(p);
+		skb = rb_to_skb(p);
 
 		/* if more time remaining? */
 		time_to_send = netem_skb_cb(skb)->time_to_send;
@@ -629,7 +622,10 @@ deliver:
 			qdisc_qstats_backlog_dec(sch, skb);
 			skb->next = NULL;
 			skb->prev = NULL;
-			skb->tstamp = netem_skb_cb(skb)->tstamp_save;
+			/* skb->dev shares skb->rbnode area,
+			 * we need to restore its value.
+			 */
+			skb->dev = qdisc_dev(sch);
 
 #ifdef CONFIG_NET_CLS_ACT
 			/*
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index 6c2791d6102d..776c694c77c7 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -74,6 +74,7 @@ struct pie_sched_data {
 	struct pie_vars vars;
 	struct pie_stats stats;
 	struct timer_list adapt_timer;
+	struct Qdisc *sch;
 };
 
 static void pie_params_init(struct pie_params *params)
@@ -422,10 +423,10 @@ static void calculate_probability(struct Qdisc *sch)
 		pie_vars_init(&q->vars);
 }
 
-static void pie_timer(unsigned long arg)
+static void pie_timer(struct timer_list *t)
 {
-	struct Qdisc *sch = (struct Qdisc *)arg;
-	struct pie_sched_data *q = qdisc_priv(sch);
+	struct pie_sched_data *q = from_timer(q, t, adapt_timer);
+	struct Qdisc *sch = q->sch;
 	spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
 
 	spin_lock(root_lock);
@@ -446,7 +447,8 @@ static int pie_init(struct Qdisc *sch, struct nlattr *opt)
 	pie_vars_init(&q->vars);
 	sch->limit = q->params.limit;
 
-	setup_timer(&q->adapt_timer, pie_timer, (unsigned long)sch);
+	q->sch = sch;
+	timer_setup(&q->adapt_timer, pie_timer, 0);
 
 	if (opt) {
 		int err = pie_change(sch, opt);
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 2dd6c68ae91e..2c79559a0d31 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -50,6 +50,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 		case TC_ACT_QUEUED:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			/* fall through */
 		case TC_ACT_SHOT:
 			return NULL;
 		}
@@ -212,7 +213,7 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt)
 	if (!opt)
 		return -EINVAL;
 
-	err = tcf_block_get(&q->block, &q->filter_list);
+	err = tcf_block_get(&q->block, &q->filter_list, sch);
 	if (err)
 		return err;
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 6ddfd4991108..6962b37a3ad3 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -709,6 +709,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 		case TC_ACT_STOLEN:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			/* fall through */
 		case TC_ACT_SHOT:
 			return NULL;
 		}
@@ -1419,7 +1420,7 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 	int i, j, err;
 	u32 max_cl_shift, maxbudg_shift, max_classes;
 
-	err = tcf_block_get(&q->block, &q->filter_list);
+	err = tcf_block_get(&q->block, &q->filter_list, sch);
 	if (err)
 		return err;
 
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 93b9d70a9b28..fdfdb56aaae2 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -40,6 +40,7 @@ struct red_sched_data {
 	u32			limit;		/* HARD maximal queue length */
 	unsigned char		flags;
 	struct timer_list	adapt_timer;
+	struct Qdisc		*sch;
 	struct red_parms	parms;
 	struct red_vars		vars;
 	struct red_stats	stats;
@@ -221,10 +222,10 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 	return 0;
 }
 
-static inline void red_adaptative_timer(unsigned long arg)
+static inline void red_adaptative_timer(struct timer_list *t)
 {
-	struct Qdisc *sch = (struct Qdisc *)arg;
-	struct red_sched_data *q = qdisc_priv(sch);
+	struct red_sched_data *q = from_timer(q, t, adapt_timer);
+	struct Qdisc *sch = q->sch;
 	spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
 
 	spin_lock(root_lock);
@@ -238,7 +239,8 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt)
 	struct red_sched_data *q = qdisc_priv(sch);
 
 	q->qdisc = &noop_qdisc;
-	setup_timer(&q->adapt_timer, red_adaptative_timer, (unsigned long)sch);
+	q->sch = sch;
+	timer_setup(&q->adapt_timer, red_adaptative_timer, 0);
 	return red_change(sch, opt);
 }
 
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index cc39e170b4aa..0678debdd856 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -268,6 +268,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl,
 		case TC_ACT_QUEUED:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			/* fall through */
 		case TC_ACT_SHOT:
 			return false;
 		}
@@ -553,7 +554,7 @@ static int sfb_init(struct Qdisc *sch, struct nlattr *opt)
 	struct sfb_sched_data *q = qdisc_priv(sch);
 	int err;
 
-	err = tcf_block_get(&q->block, &q->filter_list);
+	err = tcf_block_get(&q->block, &q->filter_list, sch);
 	if (err)
 		return err;
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 74ea863b8240..890f4a4564e7 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -145,6 +145,7 @@ struct sfq_sched_data {
 	int		perturb_period;
 	unsigned int	quantum;	/* Allotment per round: MUST BE >= MTU */
 	struct timer_list perturb_timer;
+	struct Qdisc	*sch;
 };
 
 /*
@@ -189,6 +190,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 		case TC_ACT_QUEUED:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			/* fall through */
 		case TC_ACT_SHOT:
 			return 0;
 		}
@@ -604,10 +606,10 @@ drop:
 	qdisc_tree_reduce_backlog(sch, dropped, drop_len);
 }
 
-static void sfq_perturbation(unsigned long arg)
+static void sfq_perturbation(struct timer_list *t)
 {
-	struct Qdisc *sch = (struct Qdisc *)arg;
-	struct sfq_sched_data *q = qdisc_priv(sch);
+	struct sfq_sched_data *q = from_timer(q, t, perturb_timer);
+	struct Qdisc *sch = q->sch;
 	spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
 
 	spin_lock(root_lock);
@@ -722,10 +724,9 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
 	int i;
 	int err;
 
-	setup_deferrable_timer(&q->perturb_timer, sfq_perturbation,
-			       (unsigned long)sch);
+	timer_setup(&q->perturb_timer, sfq_perturbation, TIMER_DEFERRABLE);
 
-	err = tcf_block_get(&q->block, &q->filter_list);
+	err = tcf_block_get(&q->block, &q->filter_list, sch);
 	if (err)
 		return err;
 
diff --git a/net/sctp/Makefile b/net/sctp/Makefile
index 8c434af3e68f..1ca84a288443 100644
--- a/net/sctp/Makefile
+++ b/net/sctp/Makefile
@@ -13,7 +13,8 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \
 	  inqueue.o outqueue.o ulpqueue.o \
 	  tsnmap.o bind_addr.o socket.o primitive.o \
 	  output.o input.o debug.o stream.o auth.o \
-	  offload.o
+	  offload.o stream_sched.o stream_sched_prio.o \
+	  stream_sched_rr.o
 
 sctp_probe-y := probe.o
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index dfb9651e818b..69394f4d6091 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -149,8 +149,7 @@ static struct sctp_association *sctp_association_init(
 
 	/* Initializes the timers */
 	for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i)
-		setup_timer(&asoc->timers[i], sctp_timer_events[i],
-				(unsigned long)asoc);
+		timer_setup(&asoc->timers[i], sctp_timer_events[i], 0);
 
 	/* Pull default initialization values from the sock options.
 	 * Note: This assumes that the values have already been
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index 3afac275ee82..7b261afc47b9 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -311,10 +311,10 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk)
 
 		if (chunk->sent_count) {
 			chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
-			streamout->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
+			streamout->ext->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
 		} else {
 			chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
-			streamout->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
+			streamout->ext->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
 		}
 		return 1;
 	} else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) &&
@@ -323,7 +323,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk)
 			&chunk->asoc->stream.out[chunk->sinfo.sinfo_stream];
 
 		chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
-		streamout->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
+		streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
 		return 1;
 	} else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) &&
 		   chunk->msg->expires_at &&
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 2966ff400755..4db012aa25f7 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -50,6 +50,7 @@
 
 #include <net/sctp/sctp.h>
 #include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
 
 /* Declare internal functions here.  */
 static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn);
@@ -72,32 +73,38 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp);
 
 /* Add data to the front of the queue. */
 static inline void sctp_outq_head_data(struct sctp_outq *q,
-					struct sctp_chunk *ch)
+				       struct sctp_chunk *ch)
 {
+	struct sctp_stream_out_ext *oute;
+	__u16 stream;
+
 	list_add(&ch->list, &q->out_chunk_list);
 	q->out_qlen += ch->skb->len;
+
+	stream = sctp_chunk_stream_no(ch);
+	oute = q->asoc->stream.out[stream].ext;
+	list_add(&ch->stream_list, &oute->outq);
 }
 
 /* Take data from the front of the queue. */
 static inline struct sctp_chunk *sctp_outq_dequeue_data(struct sctp_outq *q)
 {
-	struct sctp_chunk *ch = NULL;
-
-	if (!list_empty(&q->out_chunk_list)) {
-		struct list_head *entry = q->out_chunk_list.next;
-
-		ch = list_entry(entry, struct sctp_chunk, list);
-		list_del_init(entry);
-		q->out_qlen -= ch->skb->len;
-	}
-	return ch;
+	return q->sched->dequeue(q);
 }
+
 /* Add data chunk to the end of the queue. */
 static inline void sctp_outq_tail_data(struct sctp_outq *q,
 				       struct sctp_chunk *ch)
 {
+	struct sctp_stream_out_ext *oute;
+	__u16 stream;
+
 	list_add_tail(&ch->list, &q->out_chunk_list);
 	q->out_qlen += ch->skb->len;
+
+	stream = sctp_chunk_stream_no(ch);
+	oute = q->asoc->stream.out[stream].ext;
+	list_add_tail(&ch->stream_list, &oute->outq);
 }
 
 /*
@@ -207,6 +214,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q)
 	INIT_LIST_HEAD(&q->retransmit);
 	INIT_LIST_HEAD(&q->sacked);
 	INIT_LIST_HEAD(&q->abandoned);
+	sctp_sched_set_sched(asoc, SCTP_SS_FCFS);
 }
 
 /* Free the outqueue structure and any related pending chunks.
@@ -258,6 +266,7 @@ static void __sctp_outq_teardown(struct sctp_outq *q)
 
 	/* Throw away any leftover data chunks. */
 	while ((chunk = sctp_outq_dequeue_data(q)) != NULL) {
+		sctp_sched_dequeue_done(q, chunk);
 
 		/* Mark as send failure. */
 		sctp_chunk_fail(chunk, q->error);
@@ -366,7 +375,7 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
 		streamout = &asoc->stream.out[chk->sinfo.sinfo_stream];
 		asoc->sent_cnt_removable--;
 		asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
-		streamout->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
+		streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
 
 		if (!chk->tsn_gap_acked) {
 			if (chk->transport)
@@ -391,20 +400,21 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc,
 	struct sctp_outq *q = &asoc->outqueue;
 	struct sctp_chunk *chk, *temp;
 
+	q->sched->unsched_all(&asoc->stream);
+
 	list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) {
 		if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
 		    chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)
 			continue;
 
-		list_del_init(&chk->list);
-		q->out_qlen -= chk->skb->len;
+		sctp_sched_dequeue_common(q, chk);
 		asoc->sent_cnt_removable--;
 		asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
 		if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) {
 			struct sctp_stream_out *streamout =
 				&asoc->stream.out[chk->sinfo.sinfo_stream];
 
-			streamout->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
+			streamout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
 		}
 
 		msg_len -= SCTP_DATA_SNDSIZE(chk) +
@@ -415,6 +425,8 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc,
 			break;
 	}
 
+	q->sched->sched_all(&asoc->stream);
+
 	return msg_len;
 }
 
@@ -1033,22 +1045,9 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
 		while ((chunk = sctp_outq_dequeue_data(q)) != NULL) {
 			__u32 sid = ntohs(chunk->subh.data_hdr->stream);
 
-			/* RFC 2960 6.5 Every DATA chunk MUST carry a valid
-			 * stream identifier.
-			 */
-			if (chunk->sinfo.sinfo_stream >= asoc->stream.outcnt) {
-
-				/* Mark as failed send. */
-				sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM);
-				if (asoc->peer.prsctp_capable &&
-				    SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags))
-					asoc->sent_cnt_removable--;
-				sctp_chunk_free(chunk);
-				continue;
-			}
-
 			/* Has this chunk expired? */
 			if (sctp_chunk_abandoned(chunk)) {
+				sctp_sched_dequeue_done(q, chunk);
 				sctp_chunk_fail(chunk, 0);
 				sctp_chunk_free(chunk);
 				continue;
@@ -1070,6 +1069,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
 				new_transport = asoc->peer.active_path;
 			if (new_transport->state == SCTP_UNCONFIRMED) {
 				WARN_ONCE(1, "Attempt to send packet on unconfirmed path.");
+				sctp_sched_dequeue_done(q, chunk);
 				sctp_chunk_fail(chunk, 0);
 				sctp_chunk_free(chunk);
 				continue;
@@ -1133,6 +1133,11 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
 				else
 					asoc->stats.oodchunks++;
 
+				/* Only now it's safe to consider this
+				 * chunk as sent, sched-wise.
+				 */
+				sctp_sched_dequeue_done(q, chunk);
+
 				break;
 
 			default:
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index fcd80feb293f..f5172c21349b 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -622,9 +622,9 @@ static void sctp_v4_ecn_capable(struct sock *sk)
 	INET_ECN_xmit(sk);
 }
 
-static void sctp_addr_wq_timeout_handler(unsigned long arg)
+static void sctp_addr_wq_timeout_handler(struct timer_list *t)
 {
-	struct net *net = (struct net *)arg;
+	struct net *net = from_timer(net, t, sctp.addr_wq_timer);
 	struct sctp_sockaddr_entry *addrw, *temp;
 	struct sctp_sock *sp;
 
@@ -1304,8 +1304,7 @@ static int __net_init sctp_defaults_init(struct net *net)
 	INIT_LIST_HEAD(&net->sctp.auto_asconf_splist);
 	spin_lock_init(&net->sctp.addr_wq_lock);
 	net->sctp.addr_wq_timer.expires = 0;
-	setup_timer(&net->sctp.addr_wq_timer, sctp_addr_wq_timeout_handler,
-		    (unsigned long)net);
+	timer_setup(&net->sctp.addr_wq_timer, sctp_addr_wq_timeout_handler, 0);
 
 	return 0;
 
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index e2d9a4b49c9c..df94d77401e7 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -50,6 +50,7 @@
 #include <net/sock.h>
 #include <net/sctp/sctp.h>
 #include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
 
 static int sctp_cmd_interpreter(enum sctp_event event_type,
 				union sctp_subtype subtype,
@@ -242,9 +243,10 @@ nomem:
 /* When the T3-RTX timer expires, it calls this function to create the
  * relevant state machine event.
  */
-void sctp_generate_t3_rtx_event(unsigned long peer)
+void sctp_generate_t3_rtx_event(struct timer_list *t)
 {
-	struct sctp_transport *transport = (struct sctp_transport *) peer;
+	struct sctp_transport *transport =
+		from_timer(transport, t, T3_rtx_timer);
 	struct sctp_association *asoc = transport->asoc;
 	struct sock *sk = asoc->base.sk;
 	struct net *net = sock_net(sk);
@@ -318,50 +320,63 @@ out_unlock:
 	sctp_association_put(asoc);
 }
 
-static void sctp_generate_t1_cookie_event(unsigned long data)
+static void sctp_generate_t1_cookie_event(struct timer_list *t)
 {
-	struct sctp_association *asoc = (struct sctp_association *) data;
+	struct sctp_association *asoc =
+		from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T1_COOKIE]);
+
 	sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T1_COOKIE);
 }
 
-static void sctp_generate_t1_init_event(unsigned long data)
+static void sctp_generate_t1_init_event(struct timer_list *t)
 {
-	struct sctp_association *asoc = (struct sctp_association *) data;
+	struct sctp_association *asoc =
+		from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T1_INIT]);
+
 	sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T1_INIT);
 }
 
-static void sctp_generate_t2_shutdown_event(unsigned long data)
+static void sctp_generate_t2_shutdown_event(struct timer_list *t)
 {
-	struct sctp_association *asoc = (struct sctp_association *) data;
+	struct sctp_association *asoc =
+		from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN]);
+
 	sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T2_SHUTDOWN);
 }
 
-static void sctp_generate_t4_rto_event(unsigned long data)
+static void sctp_generate_t4_rto_event(struct timer_list *t)
 {
-	struct sctp_association *asoc = (struct sctp_association *) data;
+	struct sctp_association *asoc =
+		from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T4_RTO]);
+
 	sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T4_RTO);
 }
 
-static void sctp_generate_t5_shutdown_guard_event(unsigned long data)
+static void sctp_generate_t5_shutdown_guard_event(struct timer_list *t)
 {
-	struct sctp_association *asoc = (struct sctp_association *)data;
+	struct sctp_association *asoc =
+		from_timer(asoc, t,
+			   timers[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD]);
+
 	sctp_generate_timeout_event(asoc,
 				    SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD);
 
 } /* sctp_generate_t5_shutdown_guard_event() */
 
-static void sctp_generate_autoclose_event(unsigned long data)
+static void sctp_generate_autoclose_event(struct timer_list *t)
 {
-	struct sctp_association *asoc = (struct sctp_association *) data;
+	struct sctp_association *asoc =
+		from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE]);
+
 	sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_AUTOCLOSE);
 }
 
 /* Generate a heart beat event.  If the sock is busy, reschedule.   Make
  * sure that the transport is still valid.
  */
-void sctp_generate_heartbeat_event(unsigned long data)
+void sctp_generate_heartbeat_event(struct timer_list *t)
 {
-	struct sctp_transport *transport = (struct sctp_transport *) data;
+	struct sctp_transport *transport = from_timer(transport, t, hb_timer);
 	struct sctp_association *asoc = transport->asoc;
 	struct sock *sk = asoc->base.sk;
 	struct net *net = sock_net(sk);
@@ -404,9 +419,10 @@ out_unlock:
 /* Handle the timeout of the ICMP protocol unreachable timer.  Trigger
  * the correct state machine transition that will close the association.
  */
-void sctp_generate_proto_unreach_event(unsigned long data)
+void sctp_generate_proto_unreach_event(struct timer_list *t)
 {
-	struct sctp_transport *transport = (struct sctp_transport *)data;
+	struct sctp_transport *transport =
+		from_timer(transport, t, proto_unreach_timer);
 	struct sctp_association *asoc = transport->asoc;
 	struct sock *sk = asoc->base.sk;
 	struct net *net = sock_net(sk);
@@ -438,9 +454,10 @@ out_unlock:
 }
 
  /* Handle the timeout of the RE-CONFIG timer. */
-void sctp_generate_reconf_event(unsigned long data)
+void sctp_generate_reconf_event(struct timer_list *t)
 {
-	struct sctp_transport *transport = (struct sctp_transport *)data;
+	struct sctp_transport *transport =
+		from_timer(transport, t, reconf_timer);
 	struct sctp_association *asoc = transport->asoc;
 	struct sock *sk = asoc->base.sk;
 	struct net *net = sock_net(sk);
@@ -470,24 +487,27 @@ out_unlock:
 }
 
 /* Inject a SACK Timeout event into the state machine.  */
-static void sctp_generate_sack_event(unsigned long data)
+static void sctp_generate_sack_event(struct timer_list *t)
 {
-	struct sctp_association *asoc = (struct sctp_association *)data;
+	struct sctp_association *asoc =
+		from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_SACK]);
+
 	sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_SACK);
 }
 
 sctp_timer_event_t *sctp_timer_events[SCTP_NUM_TIMEOUT_TYPES] = {
-	NULL,
-	sctp_generate_t1_cookie_event,
-	sctp_generate_t1_init_event,
-	sctp_generate_t2_shutdown_event,
-	NULL,
-	sctp_generate_t4_rto_event,
-	sctp_generate_t5_shutdown_guard_event,
-	NULL,
-	NULL,
-	sctp_generate_sack_event,
-	sctp_generate_autoclose_event,
+	[SCTP_EVENT_TIMEOUT_NONE] =		NULL,
+	[SCTP_EVENT_TIMEOUT_T1_COOKIE] =	sctp_generate_t1_cookie_event,
+	[SCTP_EVENT_TIMEOUT_T1_INIT] =		sctp_generate_t1_init_event,
+	[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] =	sctp_generate_t2_shutdown_event,
+	[SCTP_EVENT_TIMEOUT_T3_RTX] =		NULL,
+	[SCTP_EVENT_TIMEOUT_T4_RTO] =		sctp_generate_t4_rto_event,
+	[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD] =
+					sctp_generate_t5_shutdown_guard_event,
+	[SCTP_EVENT_TIMEOUT_HEARTBEAT] =	NULL,
+	[SCTP_EVENT_TIMEOUT_RECONF] =		NULL,
+	[SCTP_EVENT_TIMEOUT_SACK] =		sctp_generate_sack_event,
+	[SCTP_EVENT_TIMEOUT_AUTOCLOSE] =	sctp_generate_autoclose_event,
 };
 
 
@@ -1089,6 +1109,8 @@ static void sctp_cmd_send_msg(struct sctp_association *asoc,
 
 	list_for_each_entry(chunk, &msg->chunks, frag_list)
 		sctp_outq_tail(&asoc->outqueue, chunk, gfp);
+
+	asoc->outqueue.sched->enqueue(&asoc->outqueue, msg);
 }
 
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6f45d1713452..b029757bea03 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -79,6 +79,7 @@
 #include <net/sock.h>
 #include <net/sctp/sctp.h>
 #include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
 
 /* Forward declarations for internal helper functions. */
 static int sctp_writeable(struct sock *sk);
@@ -1957,6 +1958,13 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 		goto out_free;
 	}
 
+	/* Allocate sctp_stream_out_ext if not already done */
+	if (unlikely(!asoc->stream.out[sinfo->sinfo_stream].ext)) {
+		err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream);
+		if (err)
+			goto out_free;
+	}
+
 	if (sctp_wspace(asoc) < msg_len)
 		sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc));
 
@@ -3937,6 +3945,64 @@ out:
 	return retval;
 }
 
+static int sctp_setsockopt_scheduler(struct sock *sk,
+				     char __user *optval,
+				     unsigned int optlen)
+{
+	struct sctp_association *asoc;
+	struct sctp_assoc_value params;
+	int retval = -EINVAL;
+
+	if (optlen < sizeof(params))
+		goto out;
+
+	optlen = sizeof(params);
+	if (copy_from_user(&params, optval, optlen)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	if (params.assoc_value > SCTP_SS_MAX)
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (!asoc)
+		goto out;
+
+	retval = sctp_sched_set_sched(asoc, params.assoc_value);
+
+out:
+	return retval;
+}
+
+static int sctp_setsockopt_scheduler_value(struct sock *sk,
+					   char __user *optval,
+					   unsigned int optlen)
+{
+	struct sctp_association *asoc;
+	struct sctp_stream_value params;
+	int retval = -EINVAL;
+
+	if (optlen < sizeof(params))
+		goto out;
+
+	optlen = sizeof(params);
+	if (copy_from_user(&params, optval, optlen)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (!asoc)
+		goto out;
+
+	retval = sctp_sched_set_value(asoc, params.stream_id,
+				      params.stream_value, GFP_KERNEL);
+
+out:
+	return retval;
+}
+
 /* API 6.2 setsockopt(), getsockopt()
  *
  * Applications use setsockopt() and getsockopt() to set or retrieve
@@ -4118,6 +4184,12 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	case SCTP_ADD_STREAMS:
 		retval = sctp_setsockopt_add_streams(sk, optval, optlen);
 		break;
+	case SCTP_STREAM_SCHEDULER:
+		retval = sctp_setsockopt_scheduler(sk, optval, optlen);
+		break;
+	case SCTP_STREAM_SCHEDULER_VALUE:
+		retval = sctp_setsockopt_scheduler_value(sk, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -6679,7 +6751,7 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len,
 					   char __user *optval,
 					   int __user *optlen)
 {
-	struct sctp_stream_out *streamout;
+	struct sctp_stream_out_ext *streamoute;
 	struct sctp_association *asoc;
 	struct sctp_prstatus params;
 	int retval = -EINVAL;
@@ -6702,21 +6774,29 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len,
 	if (!asoc || params.sprstat_sid >= asoc->stream.outcnt)
 		goto out;
 
-	streamout = &asoc->stream.out[params.sprstat_sid];
+	streamoute = asoc->stream.out[params.sprstat_sid].ext;
+	if (!streamoute) {
+		/* Not allocated yet, means all stats are 0 */
+		params.sprstat_abandoned_unsent = 0;
+		params.sprstat_abandoned_sent = 0;
+		retval = 0;
+		goto out;
+	}
+
 	if (policy == SCTP_PR_SCTP_NONE) {
 		params.sprstat_abandoned_unsent = 0;
 		params.sprstat_abandoned_sent = 0;
 		for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) {
 			params.sprstat_abandoned_unsent +=
-				streamout->abandoned_unsent[policy];
+				streamoute->abandoned_unsent[policy];
 			params.sprstat_abandoned_sent +=
-				streamout->abandoned_sent[policy];
+				streamoute->abandoned_sent[policy];
 		}
 	} else {
 		params.sprstat_abandoned_unsent =
-			streamout->abandoned_unsent[__SCTP_PR_INDEX(policy)];
+			streamoute->abandoned_unsent[__SCTP_PR_INDEX(policy)];
 		params.sprstat_abandoned_sent =
-			streamout->abandoned_sent[__SCTP_PR_INDEX(policy)];
+			streamoute->abandoned_sent[__SCTP_PR_INDEX(policy)];
 	}
 
 	if (put_user(len, optlen) || copy_to_user(optval, &params, len)) {
@@ -6812,6 +6892,85 @@ out:
 	return retval;
 }
 
+static int sctp_getsockopt_scheduler(struct sock *sk, int len,
+				     char __user *optval,
+				     int __user *optlen)
+{
+	struct sctp_assoc_value params;
+	struct sctp_association *asoc;
+	int retval = -EFAULT;
+
+	if (len < sizeof(params)) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	len = sizeof(params);
+	if (copy_from_user(&params, optval, len))
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (!asoc) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	params.assoc_value = sctp_sched_get_sched(asoc);
+
+	if (put_user(len, optlen))
+		goto out;
+
+	if (copy_to_user(optval, &params, len))
+		goto out;
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
+static int sctp_getsockopt_scheduler_value(struct sock *sk, int len,
+					   char __user *optval,
+					   int __user *optlen)
+{
+	struct sctp_stream_value params;
+	struct sctp_association *asoc;
+	int retval = -EFAULT;
+
+	if (len < sizeof(params)) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	len = sizeof(params);
+	if (copy_from_user(&params, optval, len))
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (!asoc) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	retval = sctp_sched_get_value(asoc, params.stream_id,
+				      &params.stream_value);
+	if (retval)
+		goto out;
+
+	if (put_user(len, optlen)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	if (copy_to_user(optval, &params, len)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+out:
+	return retval;
+}
+
 static int sctp_getsockopt(struct sock *sk, int level, int optname,
 			   char __user *optval, int __user *optlen)
 {
@@ -6994,6 +7153,14 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 		retval = sctp_getsockopt_enable_strreset(sk, len, optval,
 							 optlen);
 		break;
+	case SCTP_STREAM_SCHEDULER:
+		retval = sctp_getsockopt_scheduler(sk, len, optval,
+						   optlen);
+		break;
+	case SCTP_STREAM_SCHEDULER_VALUE:
+		retval = sctp_getsockopt_scheduler_value(sk, len, optval,
+							 optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index fa8371ff05c4..b8c8cabb1a58 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -32,44 +32,181 @@
  *    Xin Long <lucien.xin@gmail.com>
  */
 
+#include <linux/list.h>
 #include <net/sctp/sctp.h>
 #include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
+
+/* Migrates chunks from stream queues to new stream queues if needed,
+ * but not across associations. Also, removes those chunks to streams
+ * higher than the new max.
+ */
+static void sctp_stream_outq_migrate(struct sctp_stream *stream,
+				     struct sctp_stream *new, __u16 outcnt)
+{
+	struct sctp_association *asoc;
+	struct sctp_chunk *ch, *temp;
+	struct sctp_outq *outq;
+	int i;
+
+	asoc = container_of(stream, struct sctp_association, stream);
+	outq = &asoc->outqueue;
+
+	list_for_each_entry_safe(ch, temp, &outq->out_chunk_list, list) {
+		__u16 sid = sctp_chunk_stream_no(ch);
+
+		if (sid < outcnt)
+			continue;
+
+		sctp_sched_dequeue_common(outq, ch);
+		/* No need to call dequeue_done here because
+		 * the chunks are not scheduled by now.
+		 */
+
+		/* Mark as failed send. */
+		sctp_chunk_fail(ch, SCTP_ERROR_INV_STRM);
+		if (asoc->peer.prsctp_capable &&
+		    SCTP_PR_PRIO_ENABLED(ch->sinfo.sinfo_flags))
+			asoc->sent_cnt_removable--;
+
+		sctp_chunk_free(ch);
+	}
+
+	if (new) {
+		/* Here we actually move the old ext stuff into the new
+		 * buffer, because we want to keep it. Then
+		 * sctp_stream_update will swap ->out pointers.
+		 */
+		for (i = 0; i < outcnt; i++) {
+			kfree(new->out[i].ext);
+			new->out[i].ext = stream->out[i].ext;
+			stream->out[i].ext = NULL;
+		}
+	}
+
+	for (i = outcnt; i < stream->outcnt; i++)
+		kfree(stream->out[i].ext);
+}
+
+static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
+				 gfp_t gfp)
+{
+	struct sctp_stream_out *out;
+
+	out = kmalloc_array(outcnt, sizeof(*out), gfp);
+	if (!out)
+		return -ENOMEM;
+
+	if (stream->out) {
+		memcpy(out, stream->out, min(outcnt, stream->outcnt) *
+					 sizeof(*out));
+		kfree(stream->out);
+	}
+
+	if (outcnt > stream->outcnt)
+		memset(out + stream->outcnt, 0,
+		       (outcnt - stream->outcnt) * sizeof(*out));
+
+	stream->out = out;
+
+	return 0;
+}
+
+static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt,
+				gfp_t gfp)
+{
+	struct sctp_stream_in *in;
+
+	in = kmalloc_array(incnt, sizeof(*stream->in), gfp);
+
+	if (!in)
+		return -ENOMEM;
+
+	if (stream->in) {
+		memcpy(in, stream->in, min(incnt, stream->incnt) *
+				       sizeof(*in));
+		kfree(stream->in);
+	}
+
+	if (incnt > stream->incnt)
+		memset(in + stream->incnt, 0,
+		       (incnt - stream->incnt) * sizeof(*in));
+
+	stream->in = in;
+
+	return 0;
+}
 
 int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 		     gfp_t gfp)
 {
-	int i;
+	struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream);
+	int i, ret = 0;
+
+	gfp |= __GFP_NOWARN;
 
 	/* Initial stream->out size may be very big, so free it and alloc
-	 * a new one with new outcnt to save memory.
+	 * a new one with new outcnt to save memory if needed.
 	 */
-	kfree(stream->out);
+	if (outcnt == stream->outcnt)
+		goto in;
 
-	stream->out = kcalloc(outcnt, sizeof(*stream->out), gfp);
-	if (!stream->out)
-		return -ENOMEM;
+	/* Filter out chunks queued on streams that won't exist anymore */
+	sched->unsched_all(stream);
+	sctp_stream_outq_migrate(stream, NULL, outcnt);
+	sched->sched_all(stream);
+
+	i = sctp_stream_alloc_out(stream, outcnt, gfp);
+	if (i)
+		return i;
 
 	stream->outcnt = outcnt;
 	for (i = 0; i < stream->outcnt; i++)
 		stream->out[i].state = SCTP_STREAM_OPEN;
 
+	sched->init(stream);
+
+in:
 	if (!incnt)
-		return 0;
+		goto out;
 
-	stream->in = kcalloc(incnt, sizeof(*stream->in), gfp);
-	if (!stream->in) {
-		kfree(stream->out);
-		stream->out = NULL;
-		return -ENOMEM;
+	i = sctp_stream_alloc_in(stream, incnt, gfp);
+	if (i) {
+		ret = -ENOMEM;
+		goto free;
 	}
 
 	stream->incnt = incnt;
+	goto out;
 
-	return 0;
+free:
+	sched->free(stream);
+	kfree(stream->out);
+	stream->out = NULL;
+out:
+	return ret;
+}
+
+int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
+{
+	struct sctp_stream_out_ext *soute;
+
+	soute = kzalloc(sizeof(*soute), GFP_KERNEL);
+	if (!soute)
+		return -ENOMEM;
+	stream->out[sid].ext = soute;
+
+	return sctp_sched_init_sid(stream, sid, GFP_KERNEL);
 }
 
 void sctp_stream_free(struct sctp_stream *stream)
 {
+	struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream);
+	int i;
+
+	sched->free(stream);
+	for (i = 0; i < stream->outcnt; i++)
+		kfree(stream->out[i].ext);
 	kfree(stream->out);
 	kfree(stream->in);
 }
@@ -87,6 +224,10 @@ void sctp_stream_clear(struct sctp_stream *stream)
 
 void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new)
 {
+	struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream);
+
+	sched->unsched_all(stream);
+	sctp_stream_outq_migrate(stream, new, new->outcnt);
 	sctp_stream_free(stream);
 
 	stream->out = new->out;
@@ -94,6 +235,8 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new)
 	stream->outcnt = new->outcnt;
 	stream->incnt  = new->incnt;
 
+	sched->sched_all(stream);
+
 	new->out = NULL;
 	new->in  = NULL;
 }
@@ -250,7 +393,7 @@ int sctp_send_add_streams(struct sctp_association *asoc,
 {
 	struct sctp_stream *stream = &asoc->stream;
 	struct sctp_chunk *chunk = NULL;
-	int retval = -ENOMEM;
+	int retval;
 	__u32 outcnt, incnt;
 	__u16 out, in;
 
@@ -276,20 +419,16 @@ int sctp_send_add_streams(struct sctp_association *asoc,
 	}
 
 	if (out) {
-		struct sctp_stream_out *streamout;
-
-		streamout = krealloc(stream->out, outcnt * sizeof(*streamout),
-				     GFP_KERNEL);
-		if (!streamout)
+		retval = sctp_stream_alloc_out(stream, outcnt, GFP_KERNEL);
+		if (retval)
 			goto out;
-
-		memset(streamout + stream->outcnt, 0, out * sizeof(*streamout));
-		stream->out = streamout;
 	}
 
 	chunk = sctp_make_strreset_addstrm(asoc, out, in);
-	if (!chunk)
+	if (!chunk) {
+		retval = -ENOMEM;
 		goto out;
+	}
 
 	asoc->strreset_chunk = chunk;
 	sctp_chunk_hold(asoc->strreset_chunk);
@@ -609,7 +748,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out(
 	struct sctp_strreset_addstrm *addstrm = param.v;
 	struct sctp_stream *stream = &asoc->stream;
 	__u32 result = SCTP_STRRESET_DENIED;
-	struct sctp_stream_in *streamin;
 	__u32 request_seq, incnt;
 	__u16 in, i;
 
@@ -656,13 +794,9 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out(
 	if (!in || incnt > SCTP_MAX_STREAM)
 		goto out;
 
-	streamin = krealloc(stream->in, incnt * sizeof(*streamin),
-			    GFP_ATOMIC);
-	if (!streamin)
+	if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC))
 		goto out;
 
-	memset(streamin + stream->incnt, 0, in * sizeof(*streamin));
-	stream->in = streamin;
 	stream->incnt = incnt;
 
 	result = SCTP_STRRESET_PERFORMED;
@@ -684,10 +818,10 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in(
 	struct sctp_strreset_addstrm *addstrm = param.v;
 	struct sctp_stream *stream = &asoc->stream;
 	__u32 result = SCTP_STRRESET_DENIED;
-	struct sctp_stream_out *streamout;
 	struct sctp_chunk *chunk = NULL;
 	__u32 request_seq, outcnt;
 	__u16 out, i;
+	int ret;
 
 	request_seq = ntohl(addstrm->request_seq);
 	if (TSN_lt(asoc->strreset_inseq, request_seq) ||
@@ -716,14 +850,10 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in(
 	if (!out || outcnt > SCTP_MAX_STREAM)
 		goto out;
 
-	streamout = krealloc(stream->out, outcnt * sizeof(*streamout),
-			     GFP_ATOMIC);
-	if (!streamout)
+	ret = sctp_stream_alloc_out(stream, outcnt, GFP_ATOMIC);
+	if (ret)
 		goto out;
 
-	memset(streamout + stream->outcnt, 0, out * sizeof(*streamout));
-	stream->out = streamout;
-
 	chunk = sctp_make_strreset_addstrm(asoc, out, 0);
 	if (!chunk)
 		goto out;
diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c
new file mode 100644
index 000000000000..0b83ec51e43b
--- /dev/null
+++ b/net/sctp/stream_sched.c
@@ -0,0 +1,275 @@
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp stream queue/scheduling.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresched(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *    Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#include <linux/list.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
+
+/* First Come First Serve (a.k.a. FIFO)
+ * RFC DRAFT ndata Section 3.1
+ */
+static int sctp_sched_fcfs_set(struct sctp_stream *stream, __u16 sid,
+			       __u16 value, gfp_t gfp)
+{
+	return 0;
+}
+
+static int sctp_sched_fcfs_get(struct sctp_stream *stream, __u16 sid,
+			       __u16 *value)
+{
+	*value = 0;
+	return 0;
+}
+
+static int sctp_sched_fcfs_init(struct sctp_stream *stream)
+{
+	return 0;
+}
+
+static int sctp_sched_fcfs_init_sid(struct sctp_stream *stream, __u16 sid,
+				    gfp_t gfp)
+{
+	return 0;
+}
+
+static void sctp_sched_fcfs_free(struct sctp_stream *stream)
+{
+}
+
+static void sctp_sched_fcfs_enqueue(struct sctp_outq *q,
+				    struct sctp_datamsg *msg)
+{
+}
+
+static struct sctp_chunk *sctp_sched_fcfs_dequeue(struct sctp_outq *q)
+{
+	struct sctp_stream *stream = &q->asoc->stream;
+	struct sctp_chunk *ch = NULL;
+	struct list_head *entry;
+
+	if (list_empty(&q->out_chunk_list))
+		goto out;
+
+	if (stream->out_curr) {
+		ch = list_entry(stream->out_curr->ext->outq.next,
+				struct sctp_chunk, stream_list);
+	} else {
+		entry = q->out_chunk_list.next;
+		ch = list_entry(entry, struct sctp_chunk, list);
+	}
+
+	sctp_sched_dequeue_common(q, ch);
+
+out:
+	return ch;
+}
+
+static void sctp_sched_fcfs_dequeue_done(struct sctp_outq *q,
+					 struct sctp_chunk *chunk)
+{
+}
+
+static void sctp_sched_fcfs_sched_all(struct sctp_stream *stream)
+{
+}
+
+static void sctp_sched_fcfs_unsched_all(struct sctp_stream *stream)
+{
+}
+
+static struct sctp_sched_ops sctp_sched_fcfs = {
+	.set = sctp_sched_fcfs_set,
+	.get = sctp_sched_fcfs_get,
+	.init = sctp_sched_fcfs_init,
+	.init_sid = sctp_sched_fcfs_init_sid,
+	.free = sctp_sched_fcfs_free,
+	.enqueue = sctp_sched_fcfs_enqueue,
+	.dequeue = sctp_sched_fcfs_dequeue,
+	.dequeue_done = sctp_sched_fcfs_dequeue_done,
+	.sched_all = sctp_sched_fcfs_sched_all,
+	.unsched_all = sctp_sched_fcfs_unsched_all,
+};
+
+/* API to other parts of the stack */
+
+extern struct sctp_sched_ops sctp_sched_prio;
+extern struct sctp_sched_ops sctp_sched_rr;
+
+static struct sctp_sched_ops *sctp_sched_ops[] = {
+	&sctp_sched_fcfs,
+	&sctp_sched_prio,
+	&sctp_sched_rr,
+};
+
+int sctp_sched_set_sched(struct sctp_association *asoc,
+			 enum sctp_sched_type sched)
+{
+	struct sctp_sched_ops *n = sctp_sched_ops[sched];
+	struct sctp_sched_ops *old = asoc->outqueue.sched;
+	struct sctp_datamsg *msg = NULL;
+	struct sctp_chunk *ch;
+	int i, ret = 0;
+
+	if (old == n)
+		return ret;
+
+	if (sched > SCTP_SS_MAX)
+		return -EINVAL;
+
+	if (old) {
+		old->free(&asoc->stream);
+
+		/* Give the next scheduler a clean slate. */
+		for (i = 0; i < asoc->stream.outcnt; i++) {
+			void *p = asoc->stream.out[i].ext;
+
+			if (!p)
+				continue;
+
+			p += offsetofend(struct sctp_stream_out_ext, outq);
+			memset(p, 0, sizeof(struct sctp_stream_out_ext) -
+				     offsetofend(struct sctp_stream_out_ext, outq));
+		}
+	}
+
+	asoc->outqueue.sched = n;
+	n->init(&asoc->stream);
+	for (i = 0; i < asoc->stream.outcnt; i++) {
+		if (!asoc->stream.out[i].ext)
+			continue;
+
+		ret = n->init_sid(&asoc->stream, i, GFP_KERNEL);
+		if (ret)
+			goto err;
+	}
+
+	/* We have to requeue all chunks already queued. */
+	list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) {
+		if (ch->msg == msg)
+			continue;
+		msg = ch->msg;
+		n->enqueue(&asoc->outqueue, msg);
+	}
+
+	return ret;
+
+err:
+	n->free(&asoc->stream);
+	asoc->outqueue.sched = &sctp_sched_fcfs; /* Always safe */
+
+	return ret;
+}
+
+int sctp_sched_get_sched(struct sctp_association *asoc)
+{
+	int i;
+
+	for (i = 0; i <= SCTP_SS_MAX; i++)
+		if (asoc->outqueue.sched == sctp_sched_ops[i])
+			return i;
+
+	return 0;
+}
+
+int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid,
+			 __u16 value, gfp_t gfp)
+{
+	if (sid >= asoc->stream.outcnt)
+		return -EINVAL;
+
+	if (!asoc->stream.out[sid].ext) {
+		int ret;
+
+		ret = sctp_stream_init_ext(&asoc->stream, sid);
+		if (ret)
+			return ret;
+	}
+
+	return asoc->outqueue.sched->set(&asoc->stream, sid, value, gfp);
+}
+
+int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid,
+			 __u16 *value)
+{
+	if (sid >= asoc->stream.outcnt)
+		return -EINVAL;
+
+	if (!asoc->stream.out[sid].ext)
+		return 0;
+
+	return asoc->outqueue.sched->get(&asoc->stream, sid, value);
+}
+
+void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch)
+{
+	if (!list_is_last(&ch->frag_list, &ch->msg->chunks)) {
+		struct sctp_stream_out *sout;
+		__u16 sid;
+
+		/* datamsg is not finish, so save it as current one,
+		 * in case application switch scheduler or a higher
+		 * priority stream comes in.
+		 */
+		sid = sctp_chunk_stream_no(ch);
+		sout = &q->asoc->stream.out[sid];
+		q->asoc->stream.out_curr = sout;
+		return;
+	}
+
+	q->asoc->stream.out_curr = NULL;
+	q->sched->dequeue_done(q, ch);
+}
+
+/* Auxiliary functions for the schedulers */
+void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch)
+{
+	list_del_init(&ch->list);
+	list_del_init(&ch->stream_list);
+	q->out_qlen -= ch->skb->len;
+}
+
+int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp)
+{
+	struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream);
+
+	INIT_LIST_HEAD(&stream->out[sid].ext->outq);
+	return sched->init_sid(stream, sid, gfp);
+}
+
+struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream)
+{
+	struct sctp_association *asoc;
+
+	asoc = container_of(stream, struct sctp_association, stream);
+
+	return asoc->outqueue.sched;
+}
diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c
new file mode 100644
index 000000000000..384dbf3c8760
--- /dev/null
+++ b/net/sctp/stream_sched_prio.c
@@ -0,0 +1,347 @@
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp stream queue/scheduling.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresched(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *    Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#include <linux/list.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
+
+/* Priority handling
+ * RFC DRAFT ndata section 3.4
+ */
+
+static void sctp_sched_prio_unsched_all(struct sctp_stream *stream);
+
+static struct sctp_stream_priorities *sctp_sched_prio_new_head(
+			struct sctp_stream *stream, int prio, gfp_t gfp)
+{
+	struct sctp_stream_priorities *p;
+
+	p = kmalloc(sizeof(*p), gfp);
+	if (!p)
+		return NULL;
+
+	INIT_LIST_HEAD(&p->prio_sched);
+	INIT_LIST_HEAD(&p->active);
+	p->next = NULL;
+	p->prio = prio;
+
+	return p;
+}
+
+static struct sctp_stream_priorities *sctp_sched_prio_get_head(
+			struct sctp_stream *stream, int prio, gfp_t gfp)
+{
+	struct sctp_stream_priorities *p;
+	int i;
+
+	/* Look into scheduled priorities first, as they are sorted and
+	 * we can find it fast IF it's scheduled.
+	 */
+	list_for_each_entry(p, &stream->prio_list, prio_sched) {
+		if (p->prio == prio)
+			return p;
+		if (p->prio > prio)
+			break;
+	}
+
+	/* No luck. So we search on all streams now. */
+	for (i = 0; i < stream->outcnt; i++) {
+		if (!stream->out[i].ext)
+			continue;
+
+		p = stream->out[i].ext->prio_head;
+		if (!p)
+			/* Means all other streams won't be initialized
+			 * as well.
+			 */
+			break;
+		if (p->prio == prio)
+			return p;
+	}
+
+	/* If not even there, allocate a new one. */
+	return sctp_sched_prio_new_head(stream, prio, gfp);
+}
+
+static void sctp_sched_prio_next_stream(struct sctp_stream_priorities *p)
+{
+	struct list_head *pos;
+
+	pos = p->next->prio_list.next;
+	if (pos == &p->active)
+		pos = pos->next;
+	p->next = list_entry(pos, struct sctp_stream_out_ext, prio_list);
+}
+
+static bool sctp_sched_prio_unsched(struct sctp_stream_out_ext *soute)
+{
+	bool scheduled = false;
+
+	if (!list_empty(&soute->prio_list)) {
+		struct sctp_stream_priorities *prio_head = soute->prio_head;
+
+		/* Scheduled */
+		scheduled = true;
+
+		if (prio_head->next == soute)
+			/* Try to move to the next stream */
+			sctp_sched_prio_next_stream(prio_head);
+
+		list_del_init(&soute->prio_list);
+
+		/* Also unsched the priority if this was the last stream */
+		if (list_empty(&prio_head->active)) {
+			list_del_init(&prio_head->prio_sched);
+			/* If there is no stream left, clear next */
+			prio_head->next = NULL;
+		}
+	}
+
+	return scheduled;
+}
+
+static void sctp_sched_prio_sched(struct sctp_stream *stream,
+				  struct sctp_stream_out_ext *soute)
+{
+	struct sctp_stream_priorities *prio, *prio_head;
+
+	prio_head = soute->prio_head;
+
+	/* Nothing to do if already scheduled */
+	if (!list_empty(&soute->prio_list))
+		return;
+
+	/* Schedule the stream. If there is a next, we schedule the new
+	 * one before it, so it's the last in round robin order.
+	 * If there isn't, we also have to schedule the priority.
+	 */
+	if (prio_head->next) {
+		list_add(&soute->prio_list, prio_head->next->prio_list.prev);
+		return;
+	}
+
+	list_add(&soute->prio_list, &prio_head->active);
+	prio_head->next = soute;
+
+	list_for_each_entry(prio, &stream->prio_list, prio_sched) {
+		if (prio->prio > prio_head->prio) {
+			list_add(&prio_head->prio_sched, prio->prio_sched.prev);
+			return;
+		}
+	}
+
+	list_add_tail(&prio_head->prio_sched, &stream->prio_list);
+}
+
+static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid,
+			       __u16 prio, gfp_t gfp)
+{
+	struct sctp_stream_out *sout = &stream->out[sid];
+	struct sctp_stream_out_ext *soute = sout->ext;
+	struct sctp_stream_priorities *prio_head, *old;
+	bool reschedule = false;
+	int i;
+
+	prio_head = sctp_sched_prio_get_head(stream, prio, gfp);
+	if (!prio_head)
+		return -ENOMEM;
+
+	reschedule = sctp_sched_prio_unsched(soute);
+	old = soute->prio_head;
+	soute->prio_head = prio_head;
+	if (reschedule)
+		sctp_sched_prio_sched(stream, soute);
+
+	if (!old)
+		/* Happens when we set the priority for the first time */
+		return 0;
+
+	for (i = 0; i < stream->outcnt; i++) {
+		soute = stream->out[i].ext;
+		if (soute && soute->prio_head == old)
+			/* It's still in use, nothing else to do here. */
+			return 0;
+	}
+
+	/* No hits, we are good to free it. */
+	kfree(old);
+
+	return 0;
+}
+
+static int sctp_sched_prio_get(struct sctp_stream *stream, __u16 sid,
+			       __u16 *value)
+{
+	*value = stream->out[sid].ext->prio_head->prio;
+	return 0;
+}
+
+static int sctp_sched_prio_init(struct sctp_stream *stream)
+{
+	INIT_LIST_HEAD(&stream->prio_list);
+
+	return 0;
+}
+
+static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid,
+				    gfp_t gfp)
+{
+	INIT_LIST_HEAD(&stream->out[sid].ext->prio_list);
+	return sctp_sched_prio_set(stream, sid, 0, gfp);
+}
+
+static void sctp_sched_prio_free(struct sctp_stream *stream)
+{
+	struct sctp_stream_priorities *prio, *n;
+	LIST_HEAD(list);
+	int i;
+
+	/* As we don't keep a list of priorities, to avoid multiple
+	 * frees we have to do it in 3 steps:
+	 *   1. unsched everyone, so the lists are free to use in 2.
+	 *   2. build the list of the priorities
+	 *   3. free the list
+	 */
+	sctp_sched_prio_unsched_all(stream);
+	for (i = 0; i < stream->outcnt; i++) {
+		if (!stream->out[i].ext)
+			continue;
+		prio = stream->out[i].ext->prio_head;
+		if (prio && list_empty(&prio->prio_sched))
+			list_add(&prio->prio_sched, &list);
+	}
+	list_for_each_entry_safe(prio, n, &list, prio_sched) {
+		list_del_init(&prio->prio_sched);
+		kfree(prio);
+	}
+}
+
+static void sctp_sched_prio_enqueue(struct sctp_outq *q,
+				    struct sctp_datamsg *msg)
+{
+	struct sctp_stream *stream;
+	struct sctp_chunk *ch;
+	__u16 sid;
+
+	ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list);
+	sid = sctp_chunk_stream_no(ch);
+	stream = &q->asoc->stream;
+	sctp_sched_prio_sched(stream, stream->out[sid].ext);
+}
+
+static struct sctp_chunk *sctp_sched_prio_dequeue(struct sctp_outq *q)
+{
+	struct sctp_stream *stream = &q->asoc->stream;
+	struct sctp_stream_priorities *prio;
+	struct sctp_stream_out_ext *soute;
+	struct sctp_chunk *ch = NULL;
+
+	/* Bail out quickly if queue is empty */
+	if (list_empty(&q->out_chunk_list))
+		goto out;
+
+	/* Find which chunk is next. It's easy, it's either the current
+	 * one or the first chunk on the next active stream.
+	 */
+	if (stream->out_curr) {
+		soute = stream->out_curr->ext;
+	} else {
+		prio = list_entry(stream->prio_list.next,
+				  struct sctp_stream_priorities, prio_sched);
+		soute = prio->next;
+	}
+	ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list);
+	sctp_sched_dequeue_common(q, ch);
+
+out:
+	return ch;
+}
+
+static void sctp_sched_prio_dequeue_done(struct sctp_outq *q,
+					 struct sctp_chunk *ch)
+{
+	struct sctp_stream_priorities *prio;
+	struct sctp_stream_out_ext *soute;
+	__u16 sid;
+
+	/* Last chunk on that msg, move to the next stream on
+	 * this priority.
+	 */
+	sid = sctp_chunk_stream_no(ch);
+	soute = q->asoc->stream.out[sid].ext;
+	prio = soute->prio_head;
+
+	sctp_sched_prio_next_stream(prio);
+
+	if (list_empty(&soute->outq))
+		sctp_sched_prio_unsched(soute);
+}
+
+static void sctp_sched_prio_sched_all(struct sctp_stream *stream)
+{
+	struct sctp_association *asoc;
+	struct sctp_stream_out *sout;
+	struct sctp_chunk *ch;
+
+	asoc = container_of(stream, struct sctp_association, stream);
+	list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) {
+		__u16 sid;
+
+		sid = sctp_chunk_stream_no(ch);
+		sout = &stream->out[sid];
+		if (sout->ext)
+			sctp_sched_prio_sched(stream, sout->ext);
+	}
+}
+
+static void sctp_sched_prio_unsched_all(struct sctp_stream *stream)
+{
+	struct sctp_stream_priorities *p, *tmp;
+	struct sctp_stream_out_ext *soute, *souttmp;
+
+	list_for_each_entry_safe(p, tmp, &stream->prio_list, prio_sched)
+		list_for_each_entry_safe(soute, souttmp, &p->active, prio_list)
+			sctp_sched_prio_unsched(soute);
+}
+
+struct sctp_sched_ops sctp_sched_prio = {
+	.set = sctp_sched_prio_set,
+	.get = sctp_sched_prio_get,
+	.init = sctp_sched_prio_init,
+	.init_sid = sctp_sched_prio_init_sid,
+	.free = sctp_sched_prio_free,
+	.enqueue = sctp_sched_prio_enqueue,
+	.dequeue = sctp_sched_prio_dequeue,
+	.dequeue_done = sctp_sched_prio_dequeue_done,
+	.sched_all = sctp_sched_prio_sched_all,
+	.unsched_all = sctp_sched_prio_unsched_all,
+};
diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c
new file mode 100644
index 000000000000..7612a438c5b9
--- /dev/null
+++ b/net/sctp/stream_sched_rr.c
@@ -0,0 +1,201 @@
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp stream queue/scheduling.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresched(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *    Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#include <linux/list.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
+
+/* Priority handling
+ * RFC DRAFT ndata section 3.2
+ */
+static void sctp_sched_rr_unsched_all(struct sctp_stream *stream);
+
+static void sctp_sched_rr_next_stream(struct sctp_stream *stream)
+{
+	struct list_head *pos;
+
+	pos = stream->rr_next->rr_list.next;
+	if (pos == &stream->rr_list)
+		pos = pos->next;
+	stream->rr_next = list_entry(pos, struct sctp_stream_out_ext, rr_list);
+}
+
+static void sctp_sched_rr_unsched(struct sctp_stream *stream,
+				  struct sctp_stream_out_ext *soute)
+{
+	if (stream->rr_next == soute)
+		/* Try to move to the next stream */
+		sctp_sched_rr_next_stream(stream);
+
+	list_del_init(&soute->rr_list);
+
+	/* If we have no other stream queued, clear next */
+	if (list_empty(&stream->rr_list))
+		stream->rr_next = NULL;
+}
+
+static void sctp_sched_rr_sched(struct sctp_stream *stream,
+				struct sctp_stream_out_ext *soute)
+{
+	if (!list_empty(&soute->rr_list))
+		/* Already scheduled. */
+		return;
+
+	/* Schedule the stream */
+	list_add_tail(&soute->rr_list, &stream->rr_list);
+
+	if (!stream->rr_next)
+		stream->rr_next = soute;
+}
+
+static int sctp_sched_rr_set(struct sctp_stream *stream, __u16 sid,
+			     __u16 prio, gfp_t gfp)
+{
+	return 0;
+}
+
+static int sctp_sched_rr_get(struct sctp_stream *stream, __u16 sid,
+			     __u16 *value)
+{
+	return 0;
+}
+
+static int sctp_sched_rr_init(struct sctp_stream *stream)
+{
+	INIT_LIST_HEAD(&stream->rr_list);
+	stream->rr_next = NULL;
+
+	return 0;
+}
+
+static int sctp_sched_rr_init_sid(struct sctp_stream *stream, __u16 sid,
+				  gfp_t gfp)
+{
+	INIT_LIST_HEAD(&stream->out[sid].ext->rr_list);
+
+	return 0;
+}
+
+static void sctp_sched_rr_free(struct sctp_stream *stream)
+{
+	sctp_sched_rr_unsched_all(stream);
+}
+
+static void sctp_sched_rr_enqueue(struct sctp_outq *q,
+				  struct sctp_datamsg *msg)
+{
+	struct sctp_stream *stream;
+	struct sctp_chunk *ch;
+	__u16 sid;
+
+	ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list);
+	sid = sctp_chunk_stream_no(ch);
+	stream = &q->asoc->stream;
+	sctp_sched_rr_sched(stream, stream->out[sid].ext);
+}
+
+static struct sctp_chunk *sctp_sched_rr_dequeue(struct sctp_outq *q)
+{
+	struct sctp_stream *stream = &q->asoc->stream;
+	struct sctp_stream_out_ext *soute;
+	struct sctp_chunk *ch = NULL;
+
+	/* Bail out quickly if queue is empty */
+	if (list_empty(&q->out_chunk_list))
+		goto out;
+
+	/* Find which chunk is next */
+	if (stream->out_curr)
+		soute = stream->out_curr->ext;
+	else
+		soute = stream->rr_next;
+	ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list);
+
+	sctp_sched_dequeue_common(q, ch);
+
+out:
+	return ch;
+}
+
+static void sctp_sched_rr_dequeue_done(struct sctp_outq *q,
+				       struct sctp_chunk *ch)
+{
+	struct sctp_stream_out_ext *soute;
+	__u16 sid;
+
+	/* Last chunk on that msg, move to the next stream */
+	sid = sctp_chunk_stream_no(ch);
+	soute = q->asoc->stream.out[sid].ext;
+
+	sctp_sched_rr_next_stream(&q->asoc->stream);
+
+	if (list_empty(&soute->outq))
+		sctp_sched_rr_unsched(&q->asoc->stream, soute);
+}
+
+static void sctp_sched_rr_sched_all(struct sctp_stream *stream)
+{
+	struct sctp_association *asoc;
+	struct sctp_stream_out_ext *soute;
+	struct sctp_chunk *ch;
+
+	asoc = container_of(stream, struct sctp_association, stream);
+	list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) {
+		__u16 sid;
+
+		sid = sctp_chunk_stream_no(ch);
+		soute = stream->out[sid].ext;
+		if (soute)
+			sctp_sched_rr_sched(stream, soute);
+	}
+}
+
+static void sctp_sched_rr_unsched_all(struct sctp_stream *stream)
+{
+	struct sctp_stream_out_ext *soute, *tmp;
+
+	list_for_each_entry_safe(soute, tmp, &stream->rr_list, rr_list)
+		sctp_sched_rr_unsched(stream, soute);
+}
+
+struct sctp_sched_ops sctp_sched_rr = {
+	.set = sctp_sched_rr_set,
+	.get = sctp_sched_rr_get,
+	.init = sctp_sched_rr_init,
+	.init_sid = sctp_sched_rr_init_sid,
+	.free = sctp_sched_rr_free,
+	.enqueue = sctp_sched_rr_enqueue,
+	.dequeue = sctp_sched_rr_dequeue,
+	.dequeue_done = sctp_sched_rr_dequeue_done,
+	.sched_all = sctp_sched_rr_sched_all,
+	.unsched_all = sctp_sched_rr_unsched_all,
+};
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 2d9bd3776bc8..1e5a22430cf5 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -87,14 +87,11 @@ static struct sctp_transport *sctp_transport_init(struct net *net,
 	INIT_LIST_HEAD(&peer->send_ready);
 	INIT_LIST_HEAD(&peer->transports);
 
-	setup_timer(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event,
-		    (unsigned long)peer);
-	setup_timer(&peer->hb_timer, sctp_generate_heartbeat_event,
-		    (unsigned long)peer);
-	setup_timer(&peer->reconf_timer, sctp_generate_reconf_event,
-		    (unsigned long)peer);
-	setup_timer(&peer->proto_unreach_timer,
-		    sctp_generate_proto_unreach_event, (unsigned long)peer);
+	timer_setup(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event, 0);
+	timer_setup(&peer->hb_timer, sctp_generate_heartbeat_event, 0);
+	timer_setup(&peer->reconf_timer, sctp_generate_reconf_event, 0);
+	timer_setup(&peer->proto_unreach_timer,
+		    sctp_generate_proto_unreach_event, 0);
 
 	/* Initialize the 64-bit random nonce sent with heartbeat. */
 	get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce));
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 745f145d4c4d..6451c5013e06 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -390,6 +390,12 @@ static int smc_connect_rdma(struct smc_sock *smc)
 	int rc = 0;
 	u8 ibport;
 
+	if (!tcp_sk(smc->clcsock->sk)->syn_smc) {
+		/* peer has not signalled SMC-capability */
+		smc->use_fallback = true;
+		goto out_connected;
+	}
+
 	/* IPSec connections opt out of SMC-R optimizations */
 	if (using_ipsec(smc)) {
 		reason_code = SMC_CLC_DECL_IPSEC;
@@ -555,6 +561,7 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr,
 	}
 
 	smc_copy_sock_settings_to_clc(smc);
+	tcp_sk(smc->clcsock->sk)->syn_smc = 1;
 	rc = kernel_connect(smc->clcsock, addr, alen, flags);
 	if (rc)
 		goto out;
@@ -759,6 +766,12 @@ static void smc_listen_work(struct work_struct *work)
 	u8 prefix_len;
 	u8 ibport;
 
+	/* check if peer is smc capable */
+	if (!tcp_sk(newclcsock->sk)->syn_smc) {
+		new_smc->use_fallback = true;
+		goto out_connected;
+	}
+
 	/* do inband token exchange -
 	 *wait for and receive SMC Proposal CLC message
 	 */
@@ -808,7 +821,7 @@ static void smc_listen_work(struct work_struct *work)
 		rc = local_contact;
 		if (rc == -ENOMEM)
 			reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
-		goto decline_rdma;
+		goto decline_rdma_unlock;
 	}
 	link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
 
@@ -816,7 +829,7 @@ static void smc_listen_work(struct work_struct *work)
 	rc = smc_buf_create(new_smc);
 	if (rc) {
 		reason_code = SMC_CLC_DECL_MEM;
-		goto decline_rdma;
+		goto decline_rdma_unlock;
 	}
 
 	smc_close_init(new_smc);
@@ -831,7 +844,7 @@ static void smc_listen_work(struct work_struct *work)
 					     buf_desc->mr_rx[SMC_SINGLE_LINK]);
 			if (rc) {
 				reason_code = SMC_CLC_DECL_INTERR;
-				goto decline_rdma;
+				goto decline_rdma_unlock;
 			}
 		}
 	}
@@ -839,15 +852,15 @@ static void smc_listen_work(struct work_struct *work)
 
 	rc = smc_clc_send_accept(new_smc, local_contact);
 	if (rc)
-		goto out_err;
+		goto out_err_unlock;
 
 	/* receive SMC Confirm CLC message */
 	reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
 				       SMC_CLC_CONFIRM);
 	if (reason_code < 0)
-		goto out_err;
+		goto out_err_unlock;
 	if (reason_code > 0)
-		goto decline_rdma;
+		goto decline_rdma_unlock;
 	smc_conn_save_peer_info(new_smc, &cclc);
 	if (local_contact == SMC_FIRST_CONTACT)
 		smc_link_save_peer_info(link, &cclc);
@@ -855,34 +868,34 @@ static void smc_listen_work(struct work_struct *work)
 	rc = smc_rmb_rtoken_handling(&new_smc->conn, &cclc);
 	if (rc) {
 		reason_code = SMC_CLC_DECL_INTERR;
-		goto decline_rdma;
+		goto decline_rdma_unlock;
 	}
 
 	if (local_contact == SMC_FIRST_CONTACT) {
 		rc = smc_ib_ready_link(link);
 		if (rc) {
 			reason_code = SMC_CLC_DECL_INTERR;
-			goto decline_rdma;
+			goto decline_rdma_unlock;
 		}
 		/* QP confirmation over RoCE fabric */
 		reason_code = smc_serv_conf_first_link(new_smc);
 		if (reason_code < 0) {
 			/* peer is not aware of a problem */
 			rc = reason_code;
-			goto out_err;
+			goto out_err_unlock;
 		}
 		if (reason_code > 0)
-			goto decline_rdma;
+			goto decline_rdma_unlock;
 	}
 
 	smc_tx_init(new_smc);
+	mutex_unlock(&smc_create_lgr_pending);
 
 out_connected:
 	sk_refcnt_debug_inc(newsmcsk);
 	if (newsmcsk->sk_state == SMC_INIT)
 		newsmcsk->sk_state = SMC_ACTIVE;
 enqueue:
-	mutex_unlock(&smc_create_lgr_pending);
 	lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
 	if (lsmc->sk.sk_state == SMC_LISTEN) {
 		smc_accept_enqueue(&lsmc->sk, newsmcsk);
@@ -896,6 +909,8 @@ enqueue:
 	sock_put(&lsmc->sk); /* sock_hold in smc_tcp_listen_work */
 	return;
 
+decline_rdma_unlock:
+	mutex_unlock(&smc_create_lgr_pending);
 decline_rdma:
 	/* RDMA setup failed, switch back to TCP */
 	smc_conn_free(&new_smc->conn);
@@ -907,6 +922,8 @@ decline_rdma:
 	}
 	goto out_connected;
 
+out_err_unlock:
+	mutex_unlock(&smc_create_lgr_pending);
 out_err:
 	newsmcsk->sk_state = SMC_CLOSED;
 	smc_conn_free(&new_smc->conn);
@@ -963,6 +980,7 @@ static int smc_listen(struct socket *sock, int backlog)
 	 * them to the clc socket -- copy smc socket options to clc socket
 	 */
 	smc_copy_sock_settings_to_clc(smc);
+	tcp_sk(smc->clcsock->sk)->syn_smc = 1;
 
 	rc = kernel_listen(smc->clcsock, backlog);
 	if (rc)
@@ -1405,6 +1423,7 @@ static int __init smc_init(void)
 		goto out_sock;
 	}
 
+	static_branch_enable(&tcp_have_smc);
 	return 0;
 
 out_sock:
@@ -1429,6 +1448,7 @@ static void __exit smc_exit(void)
 		list_del_init(&lgr->list);
 		smc_lgr_free(lgr); /* free link group */
 	}
+	static_branch_disable(&tcp_have_smc);
 	smc_ib_unregister_client();
 	sock_unregister(PF_SMC);
 	proto_unregister(&smc_proto);
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 535e72cfc64b..87f7bede6eab 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -63,10 +63,12 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 	bh_unlock_sock(&smc->sk);
 }
 
-int smc_cdc_get_free_slot(struct smc_link *link,
+int smc_cdc_get_free_slot(struct smc_connection *conn,
 			  struct smc_wr_buf **wr_buf,
 			  struct smc_cdc_tx_pend **pend)
 {
+	struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+
 	return smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf,
 				       (struct smc_wr_tx_pend_priv **)pend);
 }
@@ -119,8 +121,7 @@ int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
 	struct smc_wr_buf *wr_buf;
 	int rc;
 
-	rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], &wr_buf,
-				   &pend);
+	rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
 	if (rc)
 		return rc;
 
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index bea61dadaf36..149ceda1b088 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -207,7 +207,8 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
 
 struct smc_cdc_tx_pend;
 
-int smc_cdc_get_free_slot(struct smc_link *link, struct smc_wr_buf **wr_buf,
+int smc_cdc_get_free_slot(struct smc_connection *conn,
+			  struct smc_wr_buf **wr_buf,
 			  struct smc_cdc_tx_pend **pend);
 void smc_cdc_tx_dismiss_slots(struct smc_connection *conn);
 int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf,
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 2427a1f3d0d1..48615d2ac4aa 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -361,7 +361,8 @@ static void smc_close_passive_work(struct work_struct *work)
 	case SMC_PEERCLOSEWAIT1:
 		if (rxflags->peer_done_writing)
 			sk->sk_state = SMC_PEERCLOSEWAIT2;
-		/* fall through to check for closing */
+		/* fall through */
+		/* to check for closing */
 	case SMC_PEERCLOSEWAIT2:
 	case SMC_PEERFINCLOSEWAIT:
 		if (!smc_cdc_rxed_any_close(&smc->conn))
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 413e3868fbf3..2578fbd95664 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -381,10 +381,14 @@ static int smc_link_determine_gid(struct smc_link_group *lgr)
 		if (ib_query_gid(lnk->smcibdev->ibdev, lnk->ibport, i, &gid,
 				 &gattr))
 			continue;
-		if (gattr.ndev &&
-		    (vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id)) {
-			lnk->gid = gid;
-			return 0;
+		if (gattr.ndev) {
+			if (is_vlan_dev(gattr.ndev) &&
+			    vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id) {
+				lnk->gid = gid;
+				dev_put(gattr.ndev);
+				return 0;
+			}
+			dev_put(gattr.ndev);
 		}
 	}
 	return -ENODEV;
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 9033b8a36fe1..90f1a7f9085c 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -370,26 +370,17 @@ void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev,
 
 static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
 {
-	struct net_device *ndev;
+	struct ib_gid_attr gattr;
 	int rc;
 
 	rc = ib_query_gid(smcibdev->ibdev, ibport, 0,
-			  &smcibdev->gid[ibport - 1], NULL);
-	/* the SMC protocol requires specification of the roce MAC address;
-	 * if net_device cannot be determined, it can be derived from gid 0
-	 */
-	ndev = smcibdev->ibdev->get_netdev(smcibdev->ibdev, ibport);
-	if (ndev) {
-		memcpy(&smcibdev->mac, ndev->dev_addr, ETH_ALEN);
-		dev_put(ndev);
-	} else if (!rc) {
-		memcpy(&smcibdev->mac[ibport - 1][0],
-		       &smcibdev->gid[ibport - 1].raw[8], 3);
-		memcpy(&smcibdev->mac[ibport - 1][3],
-		       &smcibdev->gid[ibport - 1].raw[13], 3);
-		smcibdev->mac[ibport - 1][0] &= ~0x02;
-	}
-	return rc;
+			  &smcibdev->gid[ibport - 1], &gattr);
+	if (rc || !gattr.ndev)
+		return -ENODEV;
+
+	memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN);
+	dev_put(gattr.ndev);
+	return 0;
 }
 
 /* Create an identifier unique for this instance of SMC-R.
@@ -420,6 +411,7 @@ int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
 			   &smcibdev->pattr[ibport - 1]);
 	if (rc)
 		goto out;
+	/* the SMC protocol requires specification of the RoCE MAC address */
 	rc = smc_ib_fill_gid_and_mac(smcibdev, ibport);
 	if (rc)
 		goto out;
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 710ab3fbf607..c48dc2d5fd3a 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -397,8 +397,7 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
 	int rc;
 
 	spin_lock_bh(&conn->send_lock);
-	rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], &wr_buf,
-				   &pend);
+	rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
 	if (rc < 0) {
 		if (rc == -EBUSY) {
 			struct smc_sock *smc =
@@ -467,8 +466,7 @@ void smc_tx_consumer_update(struct smc_connection *conn)
 	    ((to_confirm > conn->rmbe_update_limit) &&
 	     ((to_confirm > (conn->rmbe_size / 2)) ||
 	      conn->local_rx_ctrl.prod_flags.write_blocked))) {
-		rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK],
-					   &wr_buf, &pend);
+		rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
 		if (!rc)
 			rc = smc_cdc_msg_send(conn, wr_buf, pend);
 		if (rc < 0) {
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 0cc83839c13c..5dea47eb31bb 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -44,7 +44,7 @@ static mempool_t	*rpc_buffer_mempool __read_mostly;
 
 static void			rpc_async_schedule(struct work_struct *);
 static void			 rpc_release_task(struct rpc_task *task);
-static void __rpc_queue_timer_fn(unsigned long ptr);
+static void __rpc_queue_timer_fn(struct timer_list *t);
 
 /*
  * RPC tasks sit here while waiting for conditions to improve.
@@ -228,7 +228,7 @@ static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const c
 	queue->maxpriority = nr_queues - 1;
 	rpc_reset_waitqueue_priority(queue);
 	queue->qlen = 0;
-	setup_timer(&queue->timer_list.timer, __rpc_queue_timer_fn, (unsigned long)queue);
+	timer_setup(&queue->timer_list.timer, __rpc_queue_timer_fn, 0);
 	INIT_LIST_HEAD(&queue->timer_list.list);
 	rpc_assign_waitqueue_name(queue, qname);
 }
@@ -635,9 +635,9 @@ void rpc_wake_up_status(struct rpc_wait_queue *queue, int status)
 }
 EXPORT_SYMBOL_GPL(rpc_wake_up_status);
 
-static void __rpc_queue_timer_fn(unsigned long ptr)
+static void __rpc_queue_timer_fn(struct timer_list *t)
 {
-	struct rpc_wait_queue *queue = (struct rpc_wait_queue *)ptr;
+	struct rpc_wait_queue *queue = from_timer(queue, t, timer_list.timer);
 	struct rpc_task *task, *n;
 	unsigned long expires, now, timeo;
 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index aa04666f929d..33f4ae68426d 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -455,7 +455,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 	serv->sv_xdrsize   = xdrsize;
 	INIT_LIST_HEAD(&serv->sv_tempsocks);
 	INIT_LIST_HEAD(&serv->sv_permsocks);
-	init_timer(&serv->sv_temptimer);
+	timer_setup(&serv->sv_temptimer, NULL, 0);
 	spin_lock_init(&serv->sv_lock);
 
 	__svc_init_bc(serv);
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index d16a8b423c20..71de77bd4423 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -28,7 +28,7 @@ module_param(svc_rpc_per_connection_limit, uint, 0644);
 static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt);
 static int svc_deferred_recv(struct svc_rqst *rqstp);
 static struct cache_deferred_req *svc_defer(struct cache_req *req);
-static void svc_age_temp_xprts(unsigned long closure);
+static void svc_age_temp_xprts(struct timer_list *t);
 static void svc_delete_xprt(struct svc_xprt *xprt);
 
 /* apparently the "standard" is that clients close
@@ -785,8 +785,7 @@ static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt
 	serv->sv_tmpcnt++;
 	if (serv->sv_temptimer.function == NULL) {
 		/* setup timer to age temp transports */
-		setup_timer(&serv->sv_temptimer, svc_age_temp_xprts,
-			    (unsigned long)serv);
+		serv->sv_temptimer.function = (TIMER_FUNC_TYPE)svc_age_temp_xprts;
 		mod_timer(&serv->sv_temptimer,
 			  jiffies + svc_conn_age_period * HZ);
 	}
@@ -960,9 +959,9 @@ out:
  * Timer function to close old temporary transports, using
  * a mark-and-sweep algorithm.
  */
-static void svc_age_temp_xprts(unsigned long closure)
+static void svc_age_temp_xprts(struct timer_list *t)
 {
-	struct svc_serv *serv = (struct svc_serv *)closure;
+	struct svc_serv *serv = from_timer(serv, t, sv_temptimer);
 	struct svc_xprt *xprt;
 	struct list_head *le, *next;
 
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 898485e3ece4..6160d17a31c4 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -696,9 +696,9 @@ xprt_schedule_autodisconnect(struct rpc_xprt *xprt)
 }
 
 static void
-xprt_init_autodisconnect(unsigned long data)
+xprt_init_autodisconnect(struct timer_list *t)
 {
-	struct rpc_xprt *xprt = (struct rpc_xprt *)data;
+	struct rpc_xprt *xprt = from_timer(xprt, t, timer);
 
 	spin_lock(&xprt->transport_lock);
 	if (!list_empty(&xprt->recv))
@@ -1422,10 +1422,9 @@ found:
 		xprt->idle_timeout = 0;
 	INIT_WORK(&xprt->task_cleanup, xprt_autoclose);
 	if (xprt_has_timer(xprt))
-		setup_timer(&xprt->timer, xprt_init_autodisconnect,
-			    (unsigned long)xprt);
+		timer_setup(&xprt->timer, xprt_init_autodisconnect, 0);
 	else
-		init_timer(&xprt->timer);
+		timer_setup(&xprt->timer, NULL, 0);
 
 	if (strlen(args->servername) > RPC_MAXNETNAMELEN) {
 		xprt_destroy(xprt);
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index 2bfaa9d4b403..37bb0bfbd936 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -9,7 +9,7 @@ tipc-y	+= addr.o bcast.o bearer.o \
 	   core.o link.o discover.o msg.o  \
 	   name_distr.o  subscr.o monitor.o name_table.o net.o  \
 	   netlink.o netlink_compat.o node.o socket.o eth_media.o \
-	   server.o socket.o
+	   server.o socket.o group.o
 
 tipc-$(CONFIG_TIPC_MEDIA_UDP)	+= udp_media.o
 tipc-$(CONFIG_TIPC_MEDIA_IB)	+= ib_media.o
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index a140dd4a84af..329325bd553e 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -258,20 +258,20 @@ static int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts,
 static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts,
 			   struct tipc_nlist *dests, u16 *cong_link_cnt)
 {
+	struct tipc_dest *dst, *tmp;
 	struct sk_buff_head _pkts;
-	struct u32_item *n, *tmp;
-	u32 dst, selector;
+	u32 dnode, selector;
 
 	selector = msg_link_selector(buf_msg(skb_peek(pkts)));
 	skb_queue_head_init(&_pkts);
 
-	list_for_each_entry_safe(n, tmp, &dests->list, list) {
-		dst = n->value;
-		if (!tipc_msg_pskb_copy(dst, pkts, &_pkts))
+	list_for_each_entry_safe(dst, tmp, &dests->list, list) {
+		dnode = dst->node;
+		if (!tipc_msg_pskb_copy(dnode, pkts, &_pkts))
 			return -ENOMEM;
 
 		/* Any other return value than -ELINKCONG is ignored */
-		if (tipc_node_xmit(net, &_pkts, dst, selector) == -ELINKCONG)
+		if (tipc_node_xmit(net, &_pkts, dnode, selector) == -ELINKCONG)
 			(*cong_link_cnt)++;
 	}
 	return 0;
@@ -554,7 +554,7 @@ void tipc_nlist_add(struct tipc_nlist *nl, u32 node)
 {
 	if (node == nl->self)
 		nl->local = true;
-	else if (u32_push(&nl->list, node))
+	else if (tipc_dest_push(&nl->list, node, 0))
 		nl->remote++;
 }
 
@@ -562,13 +562,13 @@ void tipc_nlist_del(struct tipc_nlist *nl, u32 node)
 {
 	if (node == nl->self)
 		nl->local = false;
-	else if (u32_del(&nl->list, node))
+	else if (tipc_dest_del(&nl->list, node, 0))
 		nl->remote--;
 }
 
 void tipc_nlist_purge(struct tipc_nlist *nl)
 {
-	u32_list_purge(&nl->list);
+	tipc_dest_list_purge(&nl->list);
 	nl->remote = 0;
 	nl->local = 0;
 }
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 5cc5398be722..964342689f2c 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -132,6 +132,11 @@ static inline struct list_head *tipc_nodes(struct net *net)
 	return &tipc_net(net)->node_list;
 }
 
+static inline struct tipc_server *tipc_topsrv(struct net *net)
+{
+	return tipc_net(net)->topsrv;
+}
+
 static inline unsigned int tipc_hashfn(u32 addr)
 {
 	return addr & (NODE_HTABLE_SIZE - 1);
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 02462d67d191..92e4828c6b09 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -224,9 +224,9 @@ void tipc_disc_remove_dest(struct tipc_link_req *req)
  *
  * Called whenever a link setup request timer associated with a bearer expires.
  */
-static void disc_timeout(unsigned long data)
+static void disc_timeout(struct timer_list *t)
 {
-	struct tipc_link_req *req = (struct tipc_link_req *)data;
+	struct tipc_link_req *req = from_timer(req, t, timer);
 	struct sk_buff *skb;
 	int max_delay;
 
@@ -292,7 +292,7 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b,
 	req->num_nodes = 0;
 	req->timer_intv = TIPC_LINK_REQ_INIT;
 	spin_lock_init(&req->lock);
-	setup_timer(&req->timer, disc_timeout, (unsigned long)req);
+	timer_setup(&req->timer, disc_timeout, 0);
 	mod_timer(&req->timer, jiffies + req->timer_intv);
 	b->link_req = req;
 	*skb = skb_clone(req->buf, GFP_ATOMIC);
diff --git a/net/tipc/group.c b/net/tipc/group.c
new file mode 100644
index 000000000000..7821085a7dd8
--- /dev/null
+++ b/net/tipc/group.c
@@ -0,0 +1,871 @@
+/*
+ * net/tipc/group.c: TIPC group messaging code
+ *
+ * Copyright (c) 2017, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "core.h"
+#include "addr.h"
+#include "group.h"
+#include "bcast.h"
+#include "server.h"
+#include "msg.h"
+#include "socket.h"
+#include "node.h"
+#include "name_table.h"
+#include "subscr.h"
+
+#define ADV_UNIT (((MAX_MSG_SIZE + MAX_H_SIZE) / FLOWCTL_BLK_SZ) + 1)
+#define ADV_IDLE ADV_UNIT
+#define ADV_ACTIVE (ADV_UNIT * 12)
+
+enum mbr_state {
+	MBR_QUARANTINED,
+	MBR_DISCOVERED,
+	MBR_JOINING,
+	MBR_PUBLISHED,
+	MBR_JOINED,
+	MBR_PENDING,
+	MBR_ACTIVE,
+	MBR_RECLAIMING,
+	MBR_REMITTED,
+	MBR_LEAVING
+};
+
+struct tipc_member {
+	struct rb_node tree_node;
+	struct list_head list;
+	struct list_head congested;
+	struct sk_buff *event_msg;
+	struct sk_buff_head deferredq;
+	struct tipc_group *group;
+	u32 node;
+	u32 port;
+	u32 instance;
+	enum mbr_state state;
+	u16 advertised;
+	u16 window;
+	u16 bc_rcv_nxt;
+	u16 bc_syncpt;
+	u16 bc_acked;
+	bool usr_pending;
+};
+
+struct tipc_group {
+	struct rb_root members;
+	struct list_head congested;
+	struct list_head pending;
+	struct list_head active;
+	struct list_head reclaiming;
+	struct tipc_nlist dests;
+	struct net *net;
+	int subid;
+	u32 type;
+	u32 instance;
+	u32 domain;
+	u32 scope;
+	u32 portid;
+	u16 member_cnt;
+	u16 active_cnt;
+	u16 max_active;
+	u16 bc_snd_nxt;
+	u16 bc_ackers;
+	bool loopback;
+	bool events;
+};
+
+static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m,
+				  int mtyp, struct sk_buff_head *xmitq);
+
+static void tipc_group_decr_active(struct tipc_group *grp,
+				   struct tipc_member *m)
+{
+	if (m->state == MBR_ACTIVE || m->state == MBR_RECLAIMING)
+		grp->active_cnt--;
+}
+
+static int tipc_group_rcvbuf_limit(struct tipc_group *grp)
+{
+	int max_active, active_pool, idle_pool;
+	int mcnt = grp->member_cnt + 1;
+
+	/* Limit simultaneous reception from other members */
+	max_active = min(mcnt / 8, 64);
+	max_active = max(max_active, 16);
+	grp->max_active = max_active;
+
+	/* Reserve blocks for active and idle members */
+	active_pool = max_active * ADV_ACTIVE;
+	idle_pool = (mcnt - max_active) * ADV_IDLE;
+
+	/* Scale to bytes, considering worst-case truesize/msgsize ratio */
+	return (active_pool + idle_pool) * FLOWCTL_BLK_SZ * 4;
+}
+
+u16 tipc_group_bc_snd_nxt(struct tipc_group *grp)
+{
+	return grp->bc_snd_nxt;
+}
+
+static bool tipc_group_is_enabled(struct tipc_member *m)
+{
+	return m->state != MBR_QUARANTINED && m->state != MBR_LEAVING;
+}
+
+static bool tipc_group_is_receiver(struct tipc_member *m)
+{
+	return m && m->state >= MBR_JOINED;
+}
+
+u32 tipc_group_exclude(struct tipc_group *grp)
+{
+	if (!grp->loopback)
+		return grp->portid;
+	return 0;
+}
+
+int tipc_group_size(struct tipc_group *grp)
+{
+	return grp->member_cnt;
+}
+
+struct tipc_group *tipc_group_create(struct net *net, u32 portid,
+				     struct tipc_group_req *mreq)
+{
+	struct tipc_group *grp;
+	u32 type = mreq->type;
+
+	grp = kzalloc(sizeof(*grp), GFP_ATOMIC);
+	if (!grp)
+		return NULL;
+	tipc_nlist_init(&grp->dests, tipc_own_addr(net));
+	INIT_LIST_HEAD(&grp->congested);
+	INIT_LIST_HEAD(&grp->active);
+	INIT_LIST_HEAD(&grp->pending);
+	INIT_LIST_HEAD(&grp->reclaiming);
+	grp->members = RB_ROOT;
+	grp->net = net;
+	grp->portid = portid;
+	grp->domain = addr_domain(net, mreq->scope);
+	grp->type = type;
+	grp->instance = mreq->instance;
+	grp->scope = mreq->scope;
+	grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK;
+	grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS;
+	if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, &grp->subid))
+		return grp;
+	kfree(grp);
+	return NULL;
+}
+
+void tipc_group_delete(struct net *net, struct tipc_group *grp)
+{
+	struct rb_root *tree = &grp->members;
+	struct tipc_member *m, *tmp;
+	struct sk_buff_head xmitq;
+
+	__skb_queue_head_init(&xmitq);
+
+	rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) {
+		tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq);
+		list_del(&m->list);
+		kfree(m);
+	}
+	tipc_node_distr_xmit(net, &xmitq);
+	tipc_nlist_purge(&grp->dests);
+	tipc_topsrv_kern_unsubscr(net, grp->subid);
+	kfree(grp);
+}
+
+struct tipc_member *tipc_group_find_member(struct tipc_group *grp,
+					   u32 node, u32 port)
+{
+	struct rb_node *n = grp->members.rb_node;
+	u64 nkey, key = (u64)node << 32 | port;
+	struct tipc_member *m;
+
+	while (n) {
+		m = container_of(n, struct tipc_member, tree_node);
+		nkey = (u64)m->node << 32 | m->port;
+		if (key < nkey)
+			n = n->rb_left;
+		else if (key > nkey)
+			n = n->rb_right;
+		else
+			return m;
+	}
+	return NULL;
+}
+
+static struct tipc_member *tipc_group_find_dest(struct tipc_group *grp,
+						u32 node, u32 port)
+{
+	struct tipc_member *m;
+
+	m = tipc_group_find_member(grp, node, port);
+	if (m && tipc_group_is_enabled(m))
+		return m;
+	return NULL;
+}
+
+static struct tipc_member *tipc_group_find_node(struct tipc_group *grp,
+						u32 node)
+{
+	struct tipc_member *m;
+	struct rb_node *n;
+
+	for (n = rb_first(&grp->members); n; n = rb_next(n)) {
+		m = container_of(n, struct tipc_member, tree_node);
+		if (m->node == node)
+			return m;
+	}
+	return NULL;
+}
+
+static void tipc_group_add_to_tree(struct tipc_group *grp,
+				   struct tipc_member *m)
+{
+	u64 nkey, key = (u64)m->node << 32 | m->port;
+	struct rb_node **n, *parent = NULL;
+	struct tipc_member *tmp;
+
+	n = &grp->members.rb_node;
+	while (*n) {
+		tmp = container_of(*n, struct tipc_member, tree_node);
+		parent = *n;
+		tmp = container_of(parent, struct tipc_member, tree_node);
+		nkey = (u64)tmp->node << 32 | tmp->port;
+		if (key < nkey)
+			n = &(*n)->rb_left;
+		else if (key > nkey)
+			n = &(*n)->rb_right;
+		else
+			return;
+	}
+	rb_link_node(&m->tree_node, parent, n);
+	rb_insert_color(&m->tree_node, &grp->members);
+}
+
+static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
+						    u32 node, u32 port,
+						    int state)
+{
+	struct tipc_member *m;
+
+	m = kzalloc(sizeof(*m), GFP_ATOMIC);
+	if (!m)
+		return NULL;
+	INIT_LIST_HEAD(&m->list);
+	INIT_LIST_HEAD(&m->congested);
+	__skb_queue_head_init(&m->deferredq);
+	m->group = grp;
+	m->node = node;
+	m->port = port;
+	m->bc_acked = grp->bc_snd_nxt - 1;
+	grp->member_cnt++;
+	tipc_group_add_to_tree(grp, m);
+	tipc_nlist_add(&grp->dests, m->node);
+	m->state = state;
+	return m;
+}
+
+void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port)
+{
+	tipc_group_create_member(grp, node, port, MBR_DISCOVERED);
+}
+
+static void tipc_group_delete_member(struct tipc_group *grp,
+				     struct tipc_member *m)
+{
+	rb_erase(&m->tree_node, &grp->members);
+	grp->member_cnt--;
+
+	/* Check if we were waiting for replicast ack from this member */
+	if (grp->bc_ackers && less(m->bc_acked, grp->bc_snd_nxt - 1))
+		grp->bc_ackers--;
+
+	list_del_init(&m->list);
+	list_del_init(&m->congested);
+	tipc_group_decr_active(grp, m);
+
+	/* If last member on a node, remove node from dest list */
+	if (!tipc_group_find_node(grp, m->node))
+		tipc_nlist_del(&grp->dests, m->node);
+
+	kfree(m);
+}
+
+struct tipc_nlist *tipc_group_dests(struct tipc_group *grp)
+{
+	return &grp->dests;
+}
+
+void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq,
+		     int *scope)
+{
+	seq->type = grp->type;
+	seq->lower = grp->instance;
+	seq->upper = grp->instance;
+	*scope = grp->scope;
+}
+
+void tipc_group_update_member(struct tipc_member *m, int len)
+{
+	struct tipc_group *grp = m->group;
+	struct tipc_member *_m, *tmp;
+
+	if (!tipc_group_is_enabled(m))
+		return;
+
+	m->window -= len;
+
+	if (m->window >= ADV_IDLE)
+		return;
+
+	if (!list_empty(&m->congested))
+		return;
+
+	/* Sort member into congested members' list */
+	list_for_each_entry_safe(_m, tmp, &grp->congested, congested) {
+		if (m->window > _m->window)
+			continue;
+		list_add_tail(&m->congested, &_m->congested);
+		return;
+	}
+	list_add_tail(&m->congested, &grp->congested);
+}
+
+void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack)
+{
+	u16 prev = grp->bc_snd_nxt - 1;
+	struct tipc_member *m;
+	struct rb_node *n;
+
+	for (n = rb_first(&grp->members); n; n = rb_next(n)) {
+		m = container_of(n, struct tipc_member, tree_node);
+		if (tipc_group_is_enabled(m)) {
+			tipc_group_update_member(m, len);
+			m->bc_acked = prev;
+		}
+	}
+
+	/* Mark number of acknowledges to expect, if any */
+	if (ack)
+		grp->bc_ackers = grp->member_cnt;
+	grp->bc_snd_nxt++;
+}
+
+bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport,
+		     int len, struct tipc_member **mbr)
+{
+	struct sk_buff_head xmitq;
+	struct tipc_member *m;
+	int adv, state;
+
+	m = tipc_group_find_dest(grp, dnode, dport);
+	*mbr = m;
+	if (!m)
+		return false;
+	if (m->usr_pending)
+		return true;
+	if (m->window >= len)
+		return false;
+	m->usr_pending = true;
+
+	/* If not fully advertised, do it now to prevent mutual blocking */
+	adv = m->advertised;
+	state = m->state;
+	if (state < MBR_JOINED)
+		return true;
+	if (state == MBR_JOINED && adv == ADV_IDLE)
+		return true;
+	if (state == MBR_ACTIVE && adv == ADV_ACTIVE)
+		return true;
+	if (state == MBR_PENDING && adv == ADV_IDLE)
+		return true;
+	skb_queue_head_init(&xmitq);
+	tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, &xmitq);
+	tipc_node_distr_xmit(grp->net, &xmitq);
+	return true;
+}
+
+bool tipc_group_bc_cong(struct tipc_group *grp, int len)
+{
+	struct tipc_member *m = NULL;
+
+	/* If prev bcast was replicast, reject until all receivers have acked */
+	if (grp->bc_ackers)
+		return true;
+
+	if (list_empty(&grp->congested))
+		return false;
+
+	m = list_first_entry(&grp->congested, struct tipc_member, congested);
+	if (m->window >= len)
+		return false;
+
+	return tipc_group_cong(grp, m->node, m->port, len, &m);
+}
+
+/* tipc_group_sort_msg() - sort msg into queue by bcast sequence number
+ */
+static void tipc_group_sort_msg(struct sk_buff *skb, struct sk_buff_head *defq)
+{
+	struct tipc_msg *_hdr, *hdr = buf_msg(skb);
+	u16 bc_seqno = msg_grp_bc_seqno(hdr);
+	struct sk_buff *_skb, *tmp;
+	int mtyp = msg_type(hdr);
+
+	/* Bcast/mcast may be bypassed by ucast or other bcast, - sort it in */
+	if (mtyp == TIPC_GRP_BCAST_MSG || mtyp == TIPC_GRP_MCAST_MSG) {
+		skb_queue_walk_safe(defq, _skb, tmp) {
+			_hdr = buf_msg(_skb);
+			if (!less(bc_seqno, msg_grp_bc_seqno(_hdr)))
+				continue;
+			__skb_queue_before(defq, _skb, skb);
+			return;
+		}
+		/* Bcast was not bypassed, - add to tail */
+	}
+	/* Unicasts are never bypassed, - always add to tail */
+	__skb_queue_tail(defq, skb);
+}
+
+/* tipc_group_filter_msg() - determine if we should accept arriving message
+ */
+void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq,
+			   struct sk_buff_head *xmitq)
+{
+	struct sk_buff *skb = __skb_dequeue(inputq);
+	bool ack, deliver, update, leave = false;
+	struct sk_buff_head *defq;
+	struct tipc_member *m;
+	struct tipc_msg *hdr;
+	u32 node, port;
+	int mtyp, blks;
+
+	if (!skb)
+		return;
+
+	hdr = buf_msg(skb);
+	node =  msg_orignode(hdr);
+	port = msg_origport(hdr);
+
+	if (!msg_in_group(hdr))
+		goto drop;
+
+	m = tipc_group_find_member(grp, node, port);
+	if (!tipc_group_is_receiver(m))
+		goto drop;
+
+	if (less(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt))
+		goto drop;
+
+	TIPC_SKB_CB(skb)->orig_member = m->instance;
+	defq = &m->deferredq;
+	tipc_group_sort_msg(skb, defq);
+
+	while ((skb = skb_peek(defq))) {
+		hdr = buf_msg(skb);
+		mtyp = msg_type(hdr);
+		deliver = true;
+		ack = false;
+		update = false;
+
+		if (more(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt))
+			break;
+
+		/* Decide what to do with message */
+		switch (mtyp) {
+		case TIPC_GRP_MCAST_MSG:
+			if (msg_nameinst(hdr) != grp->instance) {
+				update = true;
+				deliver = false;
+			}
+			/* Fall thru */
+		case TIPC_GRP_BCAST_MSG:
+			m->bc_rcv_nxt++;
+			ack = msg_grp_bc_ack_req(hdr);
+			break;
+		case TIPC_GRP_UCAST_MSG:
+			break;
+		case TIPC_GRP_MEMBER_EVT:
+			if (m->state == MBR_LEAVING)
+				leave = true;
+			if (!grp->events)
+				deliver = false;
+			break;
+		default:
+			break;
+		}
+
+		/* Execute decisions */
+		__skb_dequeue(defq);
+		if (deliver)
+			__skb_queue_tail(inputq, skb);
+		else
+			kfree_skb(skb);
+
+		if (ack)
+			tipc_group_proto_xmit(grp, m, GRP_ACK_MSG, xmitq);
+
+		if (leave) {
+			tipc_group_delete_member(grp, m);
+			__skb_queue_purge(defq);
+			break;
+		}
+		if (!update)
+			continue;
+
+		blks = msg_blocks(hdr);
+		tipc_group_update_rcv_win(grp, blks, node, port, xmitq);
+	}
+	return;
+drop:
+	kfree_skb(skb);
+}
+
+void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node,
+			       u32 port, struct sk_buff_head *xmitq)
+{
+	struct list_head *active = &grp->active;
+	int max_active = grp->max_active;
+	int reclaim_limit = max_active * 3 / 4;
+	int active_cnt = grp->active_cnt;
+	struct tipc_member *m, *rm;
+
+	m = tipc_group_find_member(grp, node, port);
+	if (!m)
+		return;
+
+	m->advertised -= blks;
+
+	switch (m->state) {
+	case MBR_JOINED:
+		/* Reclaim advertised space from least active member */
+		if (!list_empty(active) && active_cnt >= reclaim_limit) {
+			rm = list_first_entry(active, struct tipc_member, list);
+			rm->state = MBR_RECLAIMING;
+			list_move_tail(&rm->list, &grp->reclaiming);
+			tipc_group_proto_xmit(grp, rm, GRP_RECLAIM_MSG, xmitq);
+		}
+		/* If max active, become pending and wait for reclaimed space */
+		if (active_cnt >= max_active) {
+			m->state = MBR_PENDING;
+			list_add_tail(&m->list, &grp->pending);
+			break;
+		}
+		/* Otherwise become active */
+		m->state = MBR_ACTIVE;
+		list_add_tail(&m->list, &grp->active);
+		grp->active_cnt++;
+		/* Fall through */
+	case MBR_ACTIVE:
+		if (!list_is_last(&m->list, &grp->active))
+			list_move_tail(&m->list, &grp->active);
+		if (m->advertised > (ADV_ACTIVE * 3 / 4))
+			break;
+		tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq);
+		break;
+	case MBR_REMITTED:
+		if (m->advertised > ADV_IDLE)
+			break;
+		m->state = MBR_JOINED;
+		if (m->advertised < ADV_IDLE) {
+			pr_warn_ratelimited("Rcv unexpected msg after REMIT\n");
+			tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq);
+		}
+		break;
+	case MBR_RECLAIMING:
+	case MBR_DISCOVERED:
+	case MBR_JOINING:
+	case MBR_LEAVING:
+	default:
+		break;
+	}
+}
+
+static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m,
+				  int mtyp, struct sk_buff_head *xmitq)
+{
+	struct tipc_msg *hdr;
+	struct sk_buff *skb;
+	int adv = 0;
+
+	skb = tipc_msg_create(GROUP_PROTOCOL, mtyp, INT_H_SIZE, 0,
+			      m->node, tipc_own_addr(grp->net),
+			      m->port, grp->portid, 0);
+	if (!skb)
+		return;
+
+	if (m->state == MBR_ACTIVE)
+		adv = ADV_ACTIVE - m->advertised;
+	else if (m->state == MBR_JOINED || m->state == MBR_PENDING)
+		adv = ADV_IDLE - m->advertised;
+
+	hdr = buf_msg(skb);
+
+	if (mtyp == GRP_JOIN_MSG) {
+		msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt);
+		msg_set_adv_win(hdr, adv);
+		m->advertised += adv;
+	} else if (mtyp == GRP_LEAVE_MSG) {
+		msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt);
+	} else if (mtyp == GRP_ADV_MSG) {
+		msg_set_adv_win(hdr, adv);
+		m->advertised += adv;
+	} else if (mtyp == GRP_ACK_MSG) {
+		msg_set_grp_bc_acked(hdr, m->bc_rcv_nxt);
+	} else if (mtyp == GRP_REMIT_MSG) {
+		msg_set_grp_remitted(hdr, m->window);
+	}
+	__skb_queue_tail(xmitq, skb);
+}
+
+void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup,
+			  struct tipc_msg *hdr, struct sk_buff_head *inputq,
+			  struct sk_buff_head *xmitq)
+{
+	u32 node = msg_orignode(hdr);
+	u32 port = msg_origport(hdr);
+	struct tipc_member *m, *pm;
+	struct tipc_msg *ehdr;
+	u16 remitted, in_flight;
+
+	if (!grp)
+		return;
+
+	m = tipc_group_find_member(grp, node, port);
+
+	switch (msg_type(hdr)) {
+	case GRP_JOIN_MSG:
+		if (!m)
+			m = tipc_group_create_member(grp, node, port,
+						     MBR_QUARANTINED);
+		if (!m)
+			return;
+		m->bc_syncpt = msg_grp_bc_syncpt(hdr);
+		m->bc_rcv_nxt = m->bc_syncpt;
+		m->window += msg_adv_win(hdr);
+
+		/* Wait until PUBLISH event is received */
+		if (m->state == MBR_DISCOVERED) {
+			m->state = MBR_JOINING;
+		} else if (m->state == MBR_PUBLISHED) {
+			m->state = MBR_JOINED;
+			*usr_wakeup = true;
+			m->usr_pending = false;
+			tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq);
+			ehdr = buf_msg(m->event_msg);
+			msg_set_grp_bc_seqno(ehdr, m->bc_syncpt);
+			__skb_queue_tail(inputq, m->event_msg);
+		}
+		if (m->window < ADV_IDLE)
+			tipc_group_update_member(m, 0);
+		else
+			list_del_init(&m->congested);
+		return;
+	case GRP_LEAVE_MSG:
+		if (!m)
+			return;
+		m->bc_syncpt = msg_grp_bc_syncpt(hdr);
+
+		/* Wait until WITHDRAW event is received */
+		if (m->state != MBR_LEAVING) {
+			tipc_group_decr_active(grp, m);
+			m->state = MBR_LEAVING;
+			return;
+		}
+		/* Otherwise deliver already received WITHDRAW event */
+		ehdr = buf_msg(m->event_msg);
+		msg_set_grp_bc_seqno(ehdr, m->bc_syncpt);
+		__skb_queue_tail(inputq, m->event_msg);
+		*usr_wakeup = true;
+		list_del_init(&m->congested);
+		return;
+	case GRP_ADV_MSG:
+		if (!m)
+			return;
+		m->window += msg_adv_win(hdr);
+		*usr_wakeup = m->usr_pending;
+		m->usr_pending = false;
+		list_del_init(&m->congested);
+		return;
+	case GRP_ACK_MSG:
+		if (!m)
+			return;
+		m->bc_acked = msg_grp_bc_acked(hdr);
+		if (--grp->bc_ackers)
+			break;
+		*usr_wakeup = true;
+		m->usr_pending = false;
+		return;
+	case GRP_RECLAIM_MSG:
+		if (!m)
+			return;
+		*usr_wakeup = m->usr_pending;
+		m->usr_pending = false;
+		tipc_group_proto_xmit(grp, m, GRP_REMIT_MSG, xmitq);
+		m->window = ADV_IDLE;
+		return;
+	case GRP_REMIT_MSG:
+		if (!m || m->state != MBR_RECLAIMING)
+			return;
+
+		list_del_init(&m->list);
+		grp->active_cnt--;
+		remitted = msg_grp_remitted(hdr);
+
+		/* Messages preceding the REMIT still in receive queue */
+		if (m->advertised > remitted) {
+			m->state = MBR_REMITTED;
+			in_flight = m->advertised - remitted;
+		}
+		/* All messages preceding the REMIT have been read */
+		if (m->advertised <= remitted) {
+			m->state = MBR_JOINED;
+			in_flight = 0;
+		}
+		/* ..and the REMIT overtaken by more messages => re-advertise */
+		if (m->advertised < remitted)
+			tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq);
+
+		m->advertised = ADV_IDLE + in_flight;
+
+		/* Set oldest pending member to active and advertise */
+		if (list_empty(&grp->pending))
+			return;
+		pm = list_first_entry(&grp->pending, struct tipc_member, list);
+		pm->state = MBR_ACTIVE;
+		list_move_tail(&pm->list, &grp->active);
+		grp->active_cnt++;
+		if (pm->advertised <= (ADV_ACTIVE * 3 / 4))
+			tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq);
+		return;
+	default:
+		pr_warn("Received unknown GROUP_PROTO message\n");
+	}
+}
+
+/* tipc_group_member_evt() - receive and handle a member up/down event
+ */
+void tipc_group_member_evt(struct tipc_group *grp,
+			   bool *usr_wakeup,
+			   int *sk_rcvbuf,
+			   struct sk_buff *skb,
+			   struct sk_buff_head *inputq,
+			   struct sk_buff_head *xmitq)
+{
+	struct tipc_msg *hdr = buf_msg(skb);
+	struct tipc_event *evt = (void *)msg_data(hdr);
+	u32 instance = evt->found_lower;
+	u32 node = evt->port.node;
+	u32 port = evt->port.ref;
+	int event = evt->event;
+	struct tipc_member *m;
+	struct net *net;
+	bool node_up;
+	u32 self;
+
+	if (!grp)
+		goto drop;
+
+	net = grp->net;
+	self = tipc_own_addr(net);
+	if (!grp->loopback && node == self && port == grp->portid)
+		goto drop;
+
+	/* Convert message before delivery to user */
+	msg_set_hdr_sz(hdr, GROUP_H_SIZE);
+	msg_set_user(hdr, TIPC_CRITICAL_IMPORTANCE);
+	msg_set_type(hdr, TIPC_GRP_MEMBER_EVT);
+	msg_set_origport(hdr, port);
+	msg_set_orignode(hdr, node);
+	msg_set_nametype(hdr, grp->type);
+	msg_set_grp_evt(hdr, event);
+
+	m = tipc_group_find_member(grp, node, port);
+
+	if (event == TIPC_PUBLISHED) {
+		if (!m)
+			m = tipc_group_create_member(grp, node, port,
+						     MBR_DISCOVERED);
+		if (!m)
+			goto drop;
+
+		/* Hold back event if JOIN message not yet received */
+		if (m->state == MBR_DISCOVERED) {
+			m->event_msg = skb;
+			m->state = MBR_PUBLISHED;
+		} else {
+			msg_set_grp_bc_seqno(hdr, m->bc_syncpt);
+			__skb_queue_tail(inputq, skb);
+			m->state = MBR_JOINED;
+			*usr_wakeup = true;
+			m->usr_pending = false;
+		}
+		m->instance = instance;
+		TIPC_SKB_CB(skb)->orig_member = m->instance;
+		tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq);
+		if (m->window < ADV_IDLE)
+			tipc_group_update_member(m, 0);
+		else
+			list_del_init(&m->congested);
+	} else if (event == TIPC_WITHDRAWN) {
+		if (!m)
+			goto drop;
+
+		TIPC_SKB_CB(skb)->orig_member = m->instance;
+
+		*usr_wakeup = true;
+		m->usr_pending = false;
+		node_up = tipc_node_is_up(net, node);
+
+		/* Hold back event if more messages might be expected */
+		if (m->state != MBR_LEAVING && node_up) {
+			m->event_msg = skb;
+			tipc_group_decr_active(grp, m);
+			m->state = MBR_LEAVING;
+		} else {
+			if (node_up)
+				msg_set_grp_bc_seqno(hdr, m->bc_syncpt);
+			else
+				msg_set_grp_bc_seqno(hdr, m->bc_rcv_nxt);
+			__skb_queue_tail(inputq, skb);
+		}
+		list_del_init(&m->congested);
+	}
+	*sk_rcvbuf = tipc_group_rcvbuf_limit(grp);
+	return;
+drop:
+	kfree_skb(skb);
+}
diff --git a/net/tipc/group.h b/net/tipc/group.h
new file mode 100644
index 000000000000..d525e1cd7de5
--- /dev/null
+++ b/net/tipc/group.h
@@ -0,0 +1,73 @@
+/*
+ * net/tipc/group.h: Include file for TIPC group unicast/multicast functions
+ *
+ * Copyright (c) 2017, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_GROUP_H
+#define _TIPC_GROUP_H
+
+#include "core.h"
+
+struct tipc_group;
+struct tipc_member;
+struct tipc_msg;
+
+struct tipc_group *tipc_group_create(struct net *net, u32 portid,
+				     struct tipc_group_req *mreq);
+void tipc_group_delete(struct net *net, struct tipc_group *grp);
+void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port);
+struct tipc_nlist *tipc_group_dests(struct tipc_group *grp);
+void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq,
+		     int *scope);
+u32 tipc_group_exclude(struct tipc_group *grp);
+void tipc_group_filter_msg(struct tipc_group *grp,
+			   struct sk_buff_head *inputq,
+			   struct sk_buff_head *xmitq);
+void tipc_group_member_evt(struct tipc_group *grp, bool *wakeup,
+			   int *sk_rcvbuf, struct sk_buff *skb,
+			   struct sk_buff_head *inputq,
+			   struct sk_buff_head *xmitq);
+void tipc_group_proto_rcv(struct tipc_group *grp, bool *wakeup,
+			  struct tipc_msg *hdr,
+			  struct sk_buff_head *inputq,
+			  struct sk_buff_head *xmitq);
+void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack);
+bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport,
+		     int len, struct tipc_member **m);
+bool tipc_group_bc_cong(struct tipc_group *grp, int len);
+void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node,
+			       u32 port, struct sk_buff_head *xmitq);
+u16 tipc_group_bc_snd_nxt(struct tipc_group *grp);
+void tipc_group_update_member(struct tipc_member *m, int len);
+int tipc_group_size(struct tipc_group *grp);
+#endif
diff --git a/net/tipc/link.c b/net/tipc/link.c
index ac0144f532aa..870b9b8f877a 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1039,6 +1039,7 @@ int tipc_link_retrans(struct tipc_link *l, struct tipc_link *nacker,
 static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
 			    struct sk_buff_head *inputq)
 {
+	struct sk_buff_head *mc_inputq = l->bc_rcvlink->inputq;
 	struct tipc_msg *hdr = buf_msg(skb);
 
 	switch (msg_user(hdr)) {
@@ -1046,13 +1047,16 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
 	case TIPC_MEDIUM_IMPORTANCE:
 	case TIPC_HIGH_IMPORTANCE:
 	case TIPC_CRITICAL_IMPORTANCE:
-		if (unlikely(msg_type(hdr) == TIPC_MCAST_MSG)) {
-			skb_queue_tail(l->bc_rcvlink->inputq, skb);
+		if (unlikely(msg_in_group(hdr) || msg_mcast(hdr))) {
+			skb_queue_tail(mc_inputq, skb);
 			return true;
 		}
 	case CONN_MANAGER:
 		skb_queue_tail(inputq, skb);
 		return true;
+	case GROUP_PROTOCOL:
+		skb_queue_tail(mc_inputq, skb);
+		return true;
 	case NAME_DISTRIBUTOR:
 		l->bc_rcvlink->state = LINK_ESTABLISHED;
 		skb_queue_tail(l->namedq, skb);
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 9e109bb1a207..8e884ed06d4b 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -530,8 +530,11 @@ void tipc_mon_prep(struct net *net, void *data, int *dlen,
 	u16 gen = mon->dom_gen;
 	u16 len;
 
-	if (!tipc_mon_is_active(net, mon))
+	/* Send invalid record if not active */
+	if (!tipc_mon_is_active(net, mon)) {
+		dom->len = 0;
 		return;
+	}
 
 	/* Send only a dummy record with ack if peer has acked our last sent */
 	if (likely(state->acked_gen == gen)) {
@@ -559,6 +562,12 @@ void tipc_mon_get_state(struct net *net, u32 addr,
 	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
 	struct tipc_peer *peer;
 
+	if (!tipc_mon_is_active(net, mon)) {
+		state->probing = false;
+		state->monitoring = true;
+		return;
+	}
+
 	/* Used cached state if table has not changed */
 	if (!state->probing &&
 	    (state->list_gen == mon->list_gen) &&
@@ -578,9 +587,9 @@ void tipc_mon_get_state(struct net *net, u32 addr,
 	read_unlock_bh(&mon->lock);
 }
 
-static void mon_timeout(unsigned long m)
+static void mon_timeout(struct timer_list *t)
 {
-	struct tipc_monitor *mon = (void *)m;
+	struct tipc_monitor *mon = from_timer(mon, t, timer);
 	struct tipc_peer *self;
 	int best_member_cnt = dom_size(mon->peer_cnt) - 1;
 
@@ -623,7 +632,7 @@ int tipc_mon_create(struct net *net, int bearer_id)
 	self->is_up = true;
 	self->is_head = true;
 	INIT_LIST_HEAD(&self->list);
-	setup_timer(&mon->timer, mon_timeout, (unsigned long)mon);
+	timer_setup(&mon->timer, mon_timeout, 0);
 	mon->timer_intv = msecs_to_jiffies(MON_TIMEOUT + (tn->random & 0xffff));
 	mod_timer(&mon->timer, jiffies + mon->timer_intv);
 	return 0;
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 17146c16ee2d..1649d456e22d 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -666,3 +666,10 @@ void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno,
 	}
 	kfree_skb(skb);
 }
+
+void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb,
+		     struct sk_buff_head *xmitq)
+{
+	if (tipc_msg_reverse(tipc_own_addr(net), &skb, err))
+		__skb_queue_tail(xmitq, skb);
+}
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index c843fd2bc48d..cedf811317fb 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/msg.h: Include file for TIPC message header routines
  *
- * Copyright (c) 2000-2007, 2014-2015 Ericsson AB
+ * Copyright (c) 2000-2007, 2014-2017 Ericsson AB
  * Copyright (c) 2005-2008, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -61,10 +61,14 @@ struct plist;
 /*
  * Payload message types
  */
-#define TIPC_CONN_MSG		0
-#define TIPC_MCAST_MSG		1
-#define TIPC_NAMED_MSG		2
-#define TIPC_DIRECT_MSG		3
+#define TIPC_CONN_MSG           0
+#define TIPC_MCAST_MSG          1
+#define TIPC_NAMED_MSG          2
+#define TIPC_DIRECT_MSG         3
+#define TIPC_GRP_MEMBER_EVT     4
+#define TIPC_GRP_BCAST_MSG      5
+#define TIPC_GRP_MCAST_MSG      6
+#define TIPC_GRP_UCAST_MSG      7
 
 /*
  * Internal message users
@@ -73,11 +77,13 @@ struct plist;
 #define  MSG_BUNDLER          6
 #define  LINK_PROTOCOL        7
 #define  CONN_MANAGER         8
+#define  GROUP_PROTOCOL       9
 #define  TUNNEL_PROTOCOL      10
 #define  NAME_DISTRIBUTOR     11
 #define  MSG_FRAGMENTER       12
 #define  LINK_CONFIG          13
 #define  SOCK_WAKEUP          14       /* pseudo user */
+#define  TOP_SRV              15       /* pseudo user */
 
 /*
  * Message header sizes
@@ -86,6 +92,7 @@ struct plist;
 #define BASIC_H_SIZE              32	/* Basic payload message */
 #define NAMED_H_SIZE              40	/* Named payload message */
 #define MCAST_H_SIZE              44	/* Multicast payload message */
+#define GROUP_H_SIZE              44	/* Group payload message */
 #define INT_H_SIZE                40	/* Internal messages */
 #define MIN_H_SIZE                24	/* Smallest legal TIPC header size */
 #define MAX_H_SIZE                60	/* Largest possible TIPC header size */
@@ -96,6 +103,7 @@ struct plist;
 
 struct tipc_skb_cb {
 	u32 bytes_read;
+	u32 orig_member;
 	struct sk_buff *tail;
 	bool validated;
 	u16 chain_imp;
@@ -188,6 +196,11 @@ static inline u32 msg_size(struct tipc_msg *m)
 	return msg_bits(m, 0, 0, 0x1ffff);
 }
 
+static inline u32 msg_blocks(struct tipc_msg *m)
+{
+	return (msg_size(m) / 1024) + 1;
+}
+
 static inline u32 msg_data_sz(struct tipc_msg *m)
 {
 	return msg_size(m) - msg_hdr_sz(m);
@@ -251,6 +264,18 @@ static inline void msg_set_type(struct tipc_msg *m, u32 n)
 	msg_set_bits(m, 1, 29, 0x7, n);
 }
 
+static inline int msg_in_group(struct tipc_msg *m)
+{
+	int mtyp = msg_type(m);
+
+	return mtyp >= TIPC_GRP_MEMBER_EVT && mtyp <= TIPC_GRP_UCAST_MSG;
+}
+
+static inline bool msg_is_grp_evt(struct tipc_msg *m)
+{
+	return msg_type(m) == TIPC_GRP_MEMBER_EVT;
+}
+
 static inline u32 msg_named(struct tipc_msg *m)
 {
 	return msg_type(m) == TIPC_NAMED_MSG;
@@ -258,7 +283,10 @@ static inline u32 msg_named(struct tipc_msg *m)
 
 static inline u32 msg_mcast(struct tipc_msg *m)
 {
-	return msg_type(m) == TIPC_MCAST_MSG;
+	int mtyp = msg_type(m);
+
+	return ((mtyp == TIPC_MCAST_MSG) || (mtyp == TIPC_GRP_BCAST_MSG) ||
+		(mtyp == TIPC_GRP_MCAST_MSG));
 }
 
 static inline u32 msg_connected(struct tipc_msg *m)
@@ -514,6 +542,16 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n)
 #define DSC_RESP_MSG		1
 
 /*
+ * Group protocol message types
+ */
+#define GRP_JOIN_MSG         0
+#define GRP_LEAVE_MSG        1
+#define GRP_ADV_MSG          2
+#define GRP_ACK_MSG          3
+#define GRP_RECLAIM_MSG      4
+#define GRP_REMIT_MSG        5
+
+/*
  * Word 1
  */
 static inline u32 msg_seq_gap(struct tipc_msg *m)
@@ -764,12 +802,12 @@ static inline void msg_set_conn_ack(struct tipc_msg *m, u32 n)
 	msg_set_bits(m, 9, 16, 0xffff, n);
 }
 
-static inline u32 msg_adv_win(struct tipc_msg *m)
+static inline u16 msg_adv_win(struct tipc_msg *m)
 {
 	return msg_bits(m, 9, 0, 0xffff);
 }
 
-static inline void msg_set_adv_win(struct tipc_msg *m, u32 n)
+static inline void msg_set_adv_win(struct tipc_msg *m, u16 n)
 {
 	msg_set_bits(m, 9, 0, 0xffff, n);
 }
@@ -794,6 +832,68 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n)
 	msg_set_bits(m, 9, 0, 0xffff, n);
 }
 
+static inline u16 msg_grp_bc_syncpt(struct tipc_msg *m)
+{
+	return msg_bits(m, 9, 16, 0xffff);
+}
+
+static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n)
+{
+	msg_set_bits(m, 9, 16, 0xffff, n);
+}
+
+static inline u16 msg_grp_bc_acked(struct tipc_msg *m)
+{
+	return msg_bits(m, 9, 16, 0xffff);
+}
+
+static inline void msg_set_grp_bc_acked(struct tipc_msg *m, u16 n)
+{
+	msg_set_bits(m, 9, 16, 0xffff, n);
+}
+
+static inline u16 msg_grp_remitted(struct tipc_msg *m)
+{
+	return msg_bits(m, 9, 16, 0xffff);
+}
+
+static inline void msg_set_grp_remitted(struct tipc_msg *m, u16 n)
+{
+	msg_set_bits(m, 9, 16, 0xffff, n);
+}
+
+/* Word 10
+ */
+static inline u16 msg_grp_evt(struct tipc_msg *m)
+{
+	return msg_bits(m, 10, 0, 0x3);
+}
+
+static inline void msg_set_grp_evt(struct tipc_msg *m, int n)
+{
+	msg_set_bits(m, 10, 0, 0x3, n);
+}
+
+static inline u16 msg_grp_bc_ack_req(struct tipc_msg *m)
+{
+	return msg_bits(m, 10, 0, 0x1);
+}
+
+static inline void msg_set_grp_bc_ack_req(struct tipc_msg *m, bool n)
+{
+	msg_set_bits(m, 10, 0, 0x1, n);
+}
+
+static inline u16 msg_grp_bc_seqno(struct tipc_msg *m)
+{
+	return msg_bits(m, 10, 16, 0xffff);
+}
+
+static inline void msg_set_grp_bc_seqno(struct tipc_msg *m, u32 n)
+{
+	msg_set_bits(m, 10, 16, 0xffff, n);
+}
+
 static inline bool msg_peer_link_is_up(struct tipc_msg *m)
 {
 	if (likely(msg_user(m) != LINK_PROTOCOL))
@@ -818,6 +918,8 @@ static inline bool msg_is_reset(struct tipc_msg *hdr)
 struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp);
 bool tipc_msg_validate(struct sk_buff *skb);
 bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err);
+void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb,
+		     struct sk_buff_head *xmitq);
 void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type,
 		   u32 hsize, u32 destnode);
 struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz,
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index bd0aac87b41a..b3829bcf63c7 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -43,6 +43,7 @@
 #include "bcast.h"
 #include "addr.h"
 #include "node.h"
+#include "group.h"
 #include <net/genetlink.h>
 
 #define TIPC_NAMETBL_SIZE 1024		/* must be a power of 2 */
@@ -596,18 +597,47 @@ not_found:
 	return ref;
 }
 
-/**
- * tipc_nametbl_mc_translate - find multicast destinations
- *
- * Creates list of all local ports that overlap the given multicast address;
- * also determines if any off-node ports overlap.
- *
- * Note: Publications with a scope narrower than 'limit' are ignored.
- * (i.e. local node-scope publications mustn't receive messages arriving
- * from another node, even if the multcast link brought it here)
- *
- * Returns non-zero if any off-node ports overlap
- */
+bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain,
+			 struct list_head *dsts, int *dstcnt, u32 exclude,
+			 bool all)
+{
+	u32 self = tipc_own_addr(net);
+	struct publication *publ;
+	struct name_info *info;
+	struct name_seq *seq;
+	struct sub_seq *sseq;
+
+	if (!tipc_in_scope(domain, self))
+		return false;
+
+	*dstcnt = 0;
+	rcu_read_lock();
+	seq = nametbl_find_seq(net, type);
+	if (unlikely(!seq))
+		goto exit;
+	spin_lock_bh(&seq->lock);
+	sseq = nameseq_find_subseq(seq, instance);
+	if (likely(sseq)) {
+		info = sseq->info;
+		list_for_each_entry(publ, &info->zone_list, zone_list) {
+			if (!tipc_in_scope(domain, publ->node))
+				continue;
+			if (publ->ref == exclude && publ->node == self)
+				continue;
+			tipc_dest_push(dsts, publ->node, publ->ref);
+			(*dstcnt)++;
+			if (all)
+				continue;
+			list_move_tail(&publ->zone_list, &info->zone_list);
+			break;
+		}
+	}
+	spin_unlock_bh(&seq->lock);
+exit:
+	rcu_read_unlock();
+	return !list_empty(dsts);
+}
+
 int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper,
 			      u32 limit, struct list_head *dports)
 {
@@ -634,7 +664,7 @@ int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper,
 		info = sseq->info;
 		list_for_each_entry(publ, &info->node_list, node_list) {
 			if (publ->scope <= limit)
-				u32_push(dports, publ->ref);
+				tipc_dest_push(dports, 0, publ->ref);
 		}
 
 		if (info->cluster_list_size != info->node_list_size)
@@ -667,7 +697,7 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower,
 	spin_lock_bh(&seq->lock);
 	sseq = seq->sseqs + nameseq_locate_subseq(seq, lower);
 	stop = seq->sseqs + seq->first_free;
-	for (; sseq->lower <= upper && sseq != stop; sseq++) {
+	for (; sseq != stop && sseq->lower <= upper; sseq++) {
 		info = sseq->info;
 		list_for_each_entry(publ, &info->zone_list, zone_list) {
 			if (tipc_in_scope(domain, publ->node))
@@ -679,6 +709,37 @@ exit:
 	rcu_read_unlock();
 }
 
+/* tipc_nametbl_build_group - build list of communication group members
+ */
+void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp,
+			      u32 type, u32 domain)
+{
+	struct sub_seq *sseq, *stop;
+	struct name_info *info;
+	struct publication *p;
+	struct name_seq *seq;
+
+	rcu_read_lock();
+	seq = nametbl_find_seq(net, type);
+	if (!seq)
+		goto exit;
+
+	spin_lock_bh(&seq->lock);
+	sseq = seq->sseqs;
+	stop = seq->sseqs + seq->first_free;
+	for (; sseq != stop; sseq++) {
+		info = sseq->info;
+		list_for_each_entry(p, &info->zone_list, zone_list) {
+			if (!tipc_in_scope(domain, p->node))
+				continue;
+			tipc_group_add_member(grp, p->node, p->ref);
+		}
+	}
+	spin_unlock_bh(&seq->lock);
+exit:
+	rcu_read_unlock();
+}
+
 /*
  * tipc_nametbl_publish - add name publication to network name tables
  */
@@ -1057,78 +1118,79 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-bool u32_find(struct list_head *l, u32 value)
+struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port)
 {
-	struct u32_item *item;
+	u64 value = (u64)node << 32 | port;
+	struct tipc_dest *dst;
 
-	list_for_each_entry(item, l, list) {
-		if (item->value == value)
-			return true;
+	list_for_each_entry(dst, l, list) {
+		if (dst->value != value)
+			continue;
+		return dst;
 	}
-	return false;
+	return NULL;
 }
 
-bool u32_push(struct list_head *l, u32 value)
+bool tipc_dest_push(struct list_head *l, u32 node, u32 port)
 {
-	struct u32_item *item;
+	u64 value = (u64)node << 32 | port;
+	struct tipc_dest *dst;
 
-	list_for_each_entry(item, l, list) {
-		if (item->value == value)
-			return false;
-	}
-	item = kmalloc(sizeof(*item), GFP_ATOMIC);
-	if (unlikely(!item))
+	if (tipc_dest_find(l, node, port))
 		return false;
 
-	item->value = value;
-	list_add(&item->list, l);
+	dst = kmalloc(sizeof(*dst), GFP_ATOMIC);
+	if (unlikely(!dst))
+		return false;
+	dst->value = value;
+	list_add(&dst->list, l);
 	return true;
 }
 
-u32 u32_pop(struct list_head *l)
+bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port)
 {
-	struct u32_item *item;
-	u32 value = 0;
+	struct tipc_dest *dst;
 
 	if (list_empty(l))
-		return 0;
-	item = list_first_entry(l, typeof(*item), list);
-	value = item->value;
-	list_del(&item->list);
-	kfree(item);
-	return value;
+		return false;
+	dst = list_first_entry(l, typeof(*dst), list);
+	if (port)
+		*port = dst->port;
+	if (node)
+		*node = dst->node;
+	list_del(&dst->list);
+	kfree(dst);
+	return true;
 }
 
-bool u32_del(struct list_head *l, u32 value)
+bool tipc_dest_del(struct list_head *l, u32 node, u32 port)
 {
-	struct u32_item *item, *tmp;
+	struct tipc_dest *dst;
 
-	list_for_each_entry_safe(item, tmp, l, list) {
-		if (item->value != value)
-			continue;
-		list_del(&item->list);
-		kfree(item);
-		return true;
-	}
-	return false;
+	dst = tipc_dest_find(l, node, port);
+	if (!dst)
+		return false;
+	list_del(&dst->list);
+	kfree(dst);
+	return true;
 }
 
-void u32_list_purge(struct list_head *l)
+void tipc_dest_list_purge(struct list_head *l)
 {
-	struct u32_item *item, *tmp;
+	struct tipc_dest *dst, *tmp;
 
-	list_for_each_entry_safe(item, tmp, l, list) {
-		list_del(&item->list);
-		kfree(item);
+	list_for_each_entry_safe(dst, tmp, l, list) {
+		list_del(&dst->list);
+		kfree(dst);
 	}
 }
 
-int u32_list_len(struct list_head *l)
+int tipc_dest_list_len(struct list_head *l)
 {
-	struct u32_item *item;
+	struct tipc_dest *dst;
 	int i = 0;
 
-	list_for_each_entry(item, l, list) {
+	list_for_each_entry(dst, l, list) {
 		i++;
 	}
 	return i;
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index 6ebdeb1d84a5..71926e429446 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -40,6 +40,7 @@
 struct tipc_subscription;
 struct tipc_plist;
 struct tipc_nlist;
+struct tipc_group;
 
 /*
  * TIPC name types reserved for internal TIPC use (both current and planned)
@@ -101,9 +102,14 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb);
 u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *node);
 int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper,
 			      u32 limit, struct list_head *dports);
+void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp,
+			      u32 type, u32 domain);
 void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower,
 				   u32 upper, u32 domain,
 				   struct tipc_nlist *nodes);
+bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain,
+			 struct list_head *dsts, int *dstcnt, u32 exclude,
+			 bool all);
 struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower,
 					 u32 upper, u32 scope, u32 port_ref,
 					 u32 key);
@@ -120,16 +126,22 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s);
 int tipc_nametbl_init(struct net *net);
 void tipc_nametbl_stop(struct net *net);
 
-struct u32_item {
+struct tipc_dest {
 	struct list_head list;
-	u32 value;
+	union {
+		struct {
+			u32 port;
+			u32 node;
+		};
+		u64 value;
+	};
 };
 
-bool u32_push(struct list_head *l, u32 value);
-u32 u32_pop(struct list_head *l);
-bool u32_find(struct list_head *l, u32 value);
-bool u32_del(struct list_head *l, u32 value);
-void u32_list_purge(struct list_head *l);
-int u32_list_len(struct list_head *l);
+struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port);
+bool tipc_dest_push(struct list_head *l, u32 node, u32 port);
+bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port);
+bool tipc_dest_del(struct list_head *l, u32 node, u32 port);
+void tipc_dest_list_purge(struct list_head *l);
+int tipc_dest_list_len(struct list_head *l);
 
 #endif
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 198dbc7adbe1..009a81631280 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -153,11 +153,11 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id,
 				bool delete);
 static void node_lost_contact(struct tipc_node *n, struct sk_buff_head *inputq);
 static void tipc_node_delete(struct tipc_node *node);
-static void tipc_node_timeout(unsigned long data);
+static void tipc_node_timeout(struct timer_list *t);
 static void tipc_node_fsm_evt(struct tipc_node *n, int evt);
 static struct tipc_node *tipc_node_find(struct net *net, u32 addr);
 static void tipc_node_put(struct tipc_node *node);
-static bool tipc_node_is_up(struct tipc_node *n);
+static bool node_is_up(struct tipc_node *n);
 
 struct tipc_sock_conn {
 	u32 port;
@@ -361,7 +361,7 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities)
 		goto exit;
 	}
 	tipc_node_get(n);
-	setup_timer(&n->timer, tipc_node_timeout, (unsigned long)n);
+	timer_setup(&n->timer, tipc_node_timeout, 0);
 	n->keepalive_intv = U32_MAX;
 	hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]);
 	list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
@@ -500,9 +500,9 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port)
 
 /* tipc_node_timeout - handle expiration of node timer
  */
-static void tipc_node_timeout(unsigned long data)
+static void tipc_node_timeout(struct timer_list *t)
 {
-	struct tipc_node *n = (struct tipc_node *)data;
+	struct tipc_node *n = from_timer(n, t, timer);
 	struct tipc_link_entry *le;
 	struct sk_buff_head xmitq;
 	int bearer_id;
@@ -657,7 +657,7 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
 		*slot1 = i;
 	}
 
-	if (!tipc_node_is_up(n)) {
+	if (!node_is_up(n)) {
 		if (tipc_link_peer_is_down(l))
 			tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT);
 		tipc_node_fsm_evt(n, SELF_LOST_CONTACT_EVT);
@@ -717,11 +717,27 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
 	tipc_sk_rcv(n->net, &le->inputq);
 }
 
-static bool tipc_node_is_up(struct tipc_node *n)
+static bool node_is_up(struct tipc_node *n)
 {
 	return n->active_links[0] != INVALID_BEARER_ID;
 }
 
+bool tipc_node_is_up(struct net *net, u32 addr)
+{
+	struct tipc_node *n;
+	bool retval = false;
+
+	if (in_own_node(net, addr))
+		return true;
+
+	n = tipc_node_find(net, addr);
+	if (!n)
+		return false;
+	retval = node_is_up(n);
+	tipc_node_put(n);
+	return retval;
+}
+
 void tipc_node_check_dest(struct net *net, u32 onode,
 			  struct tipc_bearer *b,
 			  u16 capabilities, u32 signature,
@@ -1149,7 +1165,7 @@ static int __tipc_nl_add_node(struct tipc_nl_msg *msg, struct tipc_node *node)
 
 	if (nla_put_u32(msg->skb, TIPC_NLA_NODE_ADDR, node->addr))
 		goto attr_msg_full;
-	if (tipc_node_is_up(node))
+	if (node_is_up(node))
 		if (nla_put_flag(msg->skb, TIPC_NLA_NODE_UP))
 			goto attr_msg_full;
 
@@ -1238,6 +1254,22 @@ int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode,
 	return 0;
 }
 
+/* tipc_node_distr_xmit(): send single buffer msgs to individual destinations
+ * Note: this is only for SYSTEM_IMPORTANCE messages, which cannot be rejected
+ */
+int tipc_node_distr_xmit(struct net *net, struct sk_buff_head *xmitq)
+{
+	struct sk_buff *skb;
+	u32 selector, dnode;
+
+	while ((skb = __skb_dequeue(xmitq))) {
+		selector = msg_origport(buf_msg(skb));
+		dnode = msg_destnode(buf_msg(skb));
+		tipc_node_xmit_skb(net, skb, dnode, selector);
+	}
+	return 0;
+}
+
 void tipc_node_broadcast(struct net *net, struct sk_buff *skb)
 {
 	struct sk_buff *txskb;
@@ -1249,7 +1281,7 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb)
 		dst = n->addr;
 		if (in_own_node(net, dst))
 			continue;
-		if (!tipc_node_is_up(n))
+		if (!node_is_up(n))
 			continue;
 		txskb = pskb_copy(skb, GFP_ATOMIC);
 		if (!txskb)
diff --git a/net/tipc/node.h b/net/tipc/node.h
index 898c22916984..acd58d23a70e 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -48,7 +48,8 @@ enum {
 	TIPC_BCAST_SYNCH      = (1 << 1),
 	TIPC_BCAST_STATE_NACK = (1 << 2),
 	TIPC_BLOCK_FLOWCTL    = (1 << 3),
-	TIPC_BCAST_RCAST      = (1 << 4)
+	TIPC_BCAST_RCAST      = (1 << 4),
+	TIPC_MCAST_GROUPS     = (1 << 5)
 };
 
 #define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \
@@ -68,6 +69,7 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node,
 			   char *linkname, size_t len);
 int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode,
 		   int selector);
+int tipc_node_distr_xmit(struct net *net, struct sk_buff_head *list);
 int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest,
 		       u32 selector);
 void tipc_node_subscribe(struct net *net, struct list_head *subscr, u32 addr);
@@ -76,6 +78,7 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb);
 int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port);
 void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port);
 int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel);
+bool tipc_node_is_up(struct net *net, u32 addr);
 u16 tipc_node_get_capabilities(struct net *net, u32 addr);
 int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb);
 int tipc_nl_node_dump_link(struct sk_buff *skb, struct netlink_callback *cb);
diff --git a/net/tipc/server.c b/net/tipc/server.c
index 3cd6402e812c..acaef80fb88c 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -36,6 +36,8 @@
 #include "server.h"
 #include "core.h"
 #include "socket.h"
+#include "addr.h"
+#include "msg.h"
 #include <net/sock.h>
 #include <linux/module.h>
 
@@ -105,13 +107,11 @@ static void tipc_conn_kref_release(struct kref *kref)
 		kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr));
 		sock_release(sock);
 		con->sock = NULL;
-
-		spin_lock_bh(&s->idr_lock);
-		idr_remove(&s->conn_idr, con->conid);
-		s->idr_in_use--;
-		spin_unlock_bh(&s->idr_lock);
 	}
-
+	spin_lock_bh(&s->idr_lock);
+	idr_remove(&s->conn_idr, con->conid);
+	s->idr_in_use--;
+	spin_unlock_bh(&s->idr_lock);
 	tipc_clean_outqueues(con);
 	kfree(con);
 }
@@ -197,7 +197,8 @@ static void tipc_close_conn(struct tipc_conn *con)
 	struct tipc_server *s = con->server;
 
 	if (test_and_clear_bit(CF_CONNECTED, &con->flags)) {
-		tipc_unregister_callbacks(con);
+		if (con->sock)
+			tipc_unregister_callbacks(con);
 
 		if (con->conid)
 			s->tipc_conn_release(con->conid, con->usr_data);
@@ -207,8 +208,8 @@ static void tipc_close_conn(struct tipc_conn *con)
 		 * are harmless for us here as we have already deleted this
 		 * connection from server connection list.
 		 */
-		kernel_sock_shutdown(con->sock, SHUT_RDWR);
-
+		if (con->sock)
+			kernel_sock_shutdown(con->sock, SHUT_RDWR);
 		conn_put(con);
 	}
 }
@@ -487,38 +488,104 @@ void tipc_conn_terminate(struct tipc_server *s, int conid)
 	}
 }
 
+bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type,
+			     u32 lower, u32 upper, int *conid)
+{
+	struct tipc_subscriber *scbr;
+	struct tipc_subscr sub;
+	struct tipc_server *s;
+	struct tipc_conn *con;
+
+	sub.seq.type = type;
+	sub.seq.lower = lower;
+	sub.seq.upper = upper;
+	sub.timeout = TIPC_WAIT_FOREVER;
+	sub.filter = TIPC_SUB_PORTS;
+	*(u32 *)&sub.usr_handle = port;
+
+	con = tipc_alloc_conn(tipc_topsrv(net));
+	if (IS_ERR(con))
+		return false;
+
+	*conid = con->conid;
+	s = con->server;
+	scbr = s->tipc_conn_new(*conid);
+	if (!scbr) {
+		tipc_close_conn(con);
+		return false;
+	}
+
+	con->usr_data = scbr;
+	con->sock = NULL;
+	s->tipc_conn_recvmsg(net, *conid, NULL, scbr, &sub, sizeof(sub));
+	return true;
+}
+
+void tipc_topsrv_kern_unsubscr(struct net *net, int conid)
+{
+	struct tipc_conn *con;
+
+	con = tipc_conn_lookup(tipc_topsrv(net), conid);
+	if (!con)
+		return;
+	tipc_close_conn(con);
+	conn_put(con);
+}
+
+static void tipc_send_kern_top_evt(struct net *net, struct tipc_event *evt)
+{
+	u32 port = *(u32 *)&evt->s.usr_handle;
+	u32 self = tipc_own_addr(net);
+	struct sk_buff_head evtq;
+	struct sk_buff *skb;
+
+	skb = tipc_msg_create(TOP_SRV, 0, INT_H_SIZE, sizeof(*evt),
+			      self, self, port, port, 0);
+	if (!skb)
+		return;
+	msg_set_dest_droppable(buf_msg(skb), true);
+	memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt));
+	skb_queue_head_init(&evtq);
+	__skb_queue_tail(&evtq, skb);
+	tipc_sk_rcv(net, &evtq);
+}
+
 static void tipc_send_to_sock(struct tipc_conn *con)
 {
-	int count = 0;
 	struct tipc_server *s = con->server;
 	struct outqueue_entry *e;
+	struct tipc_event *evt;
 	struct msghdr msg;
+	int count = 0;
 	int ret;
 
 	spin_lock_bh(&con->outqueue_lock);
 	while (test_bit(CF_CONNECTED, &con->flags)) {
-		e = list_entry(con->outqueue.next, struct outqueue_entry,
-			       list);
+		e = list_entry(con->outqueue.next, struct outqueue_entry, list);
 		if ((struct list_head *) e == &con->outqueue)
 			break;
-		spin_unlock_bh(&con->outqueue_lock);
 
-		memset(&msg, 0, sizeof(msg));
-		msg.msg_flags = MSG_DONTWAIT;
+		spin_unlock_bh(&con->outqueue_lock);
 
-		if (s->type == SOCK_DGRAM || s->type == SOCK_RDM) {
-			msg.msg_name = &e->dest;
-			msg.msg_namelen = sizeof(struct sockaddr_tipc);
-		}
-		ret = kernel_sendmsg(con->sock, &msg, &e->iov, 1,
-				     e->iov.iov_len);
-		if (ret == -EWOULDBLOCK || ret == 0) {
-			cond_resched();
-			goto out;
-		} else if (ret < 0) {
-			goto send_err;
+		if (con->sock) {
+			memset(&msg, 0, sizeof(msg));
+			msg.msg_flags = MSG_DONTWAIT;
+			if (s->type == SOCK_DGRAM || s->type == SOCK_RDM) {
+				msg.msg_name = &e->dest;
+				msg.msg_namelen = sizeof(struct sockaddr_tipc);
+			}
+			ret = kernel_sendmsg(con->sock, &msg, &e->iov, 1,
+					     e->iov.iov_len);
+			if (ret == -EWOULDBLOCK || ret == 0) {
+				cond_resched();
+				goto out;
+			} else if (ret < 0) {
+				goto send_err;
+			}
+		} else {
+			evt = e->iov.iov_base;
+			tipc_send_kern_top_evt(s->net, evt);
 		}
-
 		/* Don't starve users filling buffers */
 		if (++count >= MAX_SEND_MSG_COUNT) {
 			cond_resched();
diff --git a/net/tipc/server.h b/net/tipc/server.h
index 34f8055afa3b..2113c9192633 100644
--- a/net/tipc/server.h
+++ b/net/tipc/server.h
@@ -83,13 +83,16 @@ struct tipc_server {
 int tipc_conn_sendmsg(struct tipc_server *s, int conid,
 		      struct sockaddr_tipc *addr, void *data, size_t len);
 
+bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type,
+			     u32 lower, u32 upper, int *conid);
+void tipc_topsrv_kern_unsubscr(struct net *net, int conid);
+
 /**
  * tipc_conn_terminate - terminate connection with server
  *
  * Note: Must call it in process context since it might sleep
  */
 void tipc_conn_terminate(struct tipc_server *s, int conid);
-
 int tipc_server_start(struct tipc_server *s);
 
 void tipc_server_stop(struct tipc_server *s);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index d50edd6e0019..5d18c0caa92b 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/socket.c: TIPC socket API
  *
- * Copyright (c) 2001-2007, 2012-2016, Ericsson AB
+ * Copyright (c) 2001-2007, 2012-2017, Ericsson AB
  * Copyright (c) 2004-2008, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -45,9 +45,10 @@
 #include "socket.h"
 #include "bcast.h"
 #include "netlink.h"
+#include "group.h"
 
 #define CONN_TIMEOUT_DEFAULT	8000	/* default connect timeout = 8s */
-#define CONN_PROBING_INTERVAL	msecs_to_jiffies(3600000)  /* [ms] => 1 h */
+#define CONN_PROBING_INTV	msecs_to_jiffies(3600000)  /* [ms] => 1 h */
 #define TIPC_FWD_MSG		1
 #define TIPC_MAX_PORT		0xffffffff
 #define TIPC_MIN_PORT		1
@@ -61,6 +62,11 @@ enum {
 	TIPC_CONNECTING = TCP_SYN_SENT,
 };
 
+struct sockaddr_pair {
+	struct sockaddr_tipc sock;
+	struct sockaddr_tipc member;
+};
+
 /**
  * struct tipc_sock - TIPC socket structure
  * @sk: socket - interacts with 'port' and with user via the socket API
@@ -78,7 +84,7 @@ enum {
  * @conn_timeout: the time we can wait for an unresponded setup request
  * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
  * @cong_link_cnt: number of congested links
- * @sent_unacked: # messages sent by socket, and not yet acked by peer
+ * @snt_unacked: # messages sent by socket, and not yet acked by peer
  * @rcv_unacked: # messages read by user, but not yet acked back to peer
  * @peer: 'connected' peer for dgram/rdm
  * @node: hash table node
@@ -109,20 +115,22 @@ struct tipc_sock {
 	struct rhash_head node;
 	struct tipc_mc_method mc_method;
 	struct rcu_head rcu;
+	struct tipc_group *group;
 };
 
-static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb);
+static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
 static void tipc_data_ready(struct sock *sk);
 static void tipc_write_space(struct sock *sk);
 static void tipc_sock_destruct(struct sock *sk);
 static int tipc_release(struct socket *sock);
 static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
 		       bool kern);
-static void tipc_sk_timeout(unsigned long data);
+static void tipc_sk_timeout(struct timer_list *t);
 static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
 			   struct tipc_name_seq const *seq);
 static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
 			    struct tipc_name_seq const *seq);
+static int tipc_sk_leave(struct tipc_sock *tsk);
 static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid);
 static int tipc_sk_insert(struct tipc_sock *tsk);
 static void tipc_sk_remove(struct tipc_sock *tsk);
@@ -193,6 +201,11 @@ static bool tsk_conn_cong(struct tipc_sock *tsk)
 	return tsk->snt_unacked > tsk->snd_win;
 }
 
+static u16 tsk_blocks(int len)
+{
+	return ((len / FLOWCTL_BLK_SZ) + 1);
+}
+
 /* tsk_blocks(): translate a buffer size in bytes to number of
  * advertisable blocks, taking into account the ratio truesize(len)/len
  * We can trust that this ratio is always < 4 for len >= FLOWCTL_BLK_SZ
@@ -451,9 +464,9 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 		      NAMED_H_SIZE, 0);
 
 	msg_set_origport(msg, tsk->portid);
-	setup_timer(&sk->sk_timer, tipc_sk_timeout, (unsigned long)tsk);
+	timer_setup(&sk->sk_timer, tipc_sk_timeout, 0);
 	sk->sk_shutdown = 0;
-	sk->sk_backlog_rcv = tipc_backlog_rcv;
+	sk->sk_backlog_rcv = tipc_sk_backlog_rcv;
 	sk->sk_rcvbuf = sysctl_tipc_rmem[1];
 	sk->sk_data_ready = tipc_data_ready;
 	sk->sk_write_space = tipc_write_space;
@@ -559,13 +572,14 @@ static int tipc_release(struct socket *sock)
 
 	__tipc_shutdown(sock, TIPC_ERR_NO_PORT);
 	sk->sk_shutdown = SHUTDOWN_MASK;
+	tipc_sk_leave(tsk);
 	tipc_sk_withdraw(tsk, 0, NULL);
 	sk_stop_timer(sk, &sk->sk_timer);
 	tipc_sk_remove(tsk);
 
 	/* Reject any messages that accumulated in backlog queue */
 	release_sock(sk);
-	u32_list_purge(&tsk->cong_links);
+	tipc_dest_list_purge(&tsk->cong_links);
 	tsk->cong_link_cnt = 0;
 	call_rcu(&tsk->rcu, tipc_sk_callback);
 	sock->sk = NULL;
@@ -601,7 +615,10 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
 		res = tipc_sk_withdraw(tsk, 0, NULL);
 		goto exit;
 	}
-
+	if (tsk->group) {
+		res = -EACCES;
+		goto exit;
+	}
 	if (uaddr_len < sizeof(struct sockaddr_tipc)) {
 		res = -EINVAL;
 		goto exit;
@@ -698,38 +715,41 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
-	u32 mask = 0;
+	struct tipc_group *grp = tsk->group;
+	u32 revents = 0;
 
 	sock_poll_wait(file, sk_sleep(sk), wait);
 
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
-		mask |= POLLRDHUP | POLLIN | POLLRDNORM;
+		revents |= POLLRDHUP | POLLIN | POLLRDNORM;
 	if (sk->sk_shutdown == SHUTDOWN_MASK)
-		mask |= POLLHUP;
+		revents |= POLLHUP;
 
 	switch (sk->sk_state) {
 	case TIPC_ESTABLISHED:
 		if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
-			mask |= POLLOUT;
+			revents |= POLLOUT;
 		/* fall thru' */
 	case TIPC_LISTEN:
 	case TIPC_CONNECTING:
 		if (!skb_queue_empty(&sk->sk_receive_queue))
-			mask |= (POLLIN | POLLRDNORM);
+			revents |= POLLIN | POLLRDNORM;
 		break;
 	case TIPC_OPEN:
-		if (!tsk->cong_link_cnt)
-			mask |= POLLOUT;
-		if (tipc_sk_type_connectionless(sk) &&
-		    (!skb_queue_empty(&sk->sk_receive_queue)))
-			mask |= (POLLIN | POLLRDNORM);
+		if (!grp || tipc_group_size(grp))
+			if (!tsk->cong_link_cnt)
+				revents |= POLLOUT;
+		if (!tipc_sk_type_connectionless(sk))
+			break;
+		if (skb_queue_empty(&sk->sk_receive_queue))
+			break;
+		revents |= POLLIN | POLLRDNORM;
 		break;
 	case TIPC_DISCONNECTING:
-		mask = (POLLIN | POLLRDNORM | POLLHUP);
+		revents = POLLIN | POLLRDNORM | POLLHUP;
 		break;
 	}
-
-	return mask;
+	return revents;
 }
 
 /**
@@ -757,6 +777,9 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 	struct tipc_nlist dsts;
 	int rc;
 
+	if (tsk->group)
+		return -EACCES;
+
 	/* Block or return if any destination link is congested */
 	rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt);
 	if (unlikely(rc))
@@ -794,6 +817,296 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 }
 
 /**
+ * tipc_send_group_msg - send a message to a member in the group
+ * @net: network namespace
+ * @m: message to send
+ * @mb: group member
+ * @dnode: destination node
+ * @dport: destination port
+ * @dlen: total length of message data
+ */
+static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk,
+			       struct msghdr *m, struct tipc_member *mb,
+			       u32 dnode, u32 dport, int dlen)
+{
+	u16 bc_snd_nxt = tipc_group_bc_snd_nxt(tsk->group);
+	struct tipc_mc_method *method = &tsk->mc_method;
+	int blks = tsk_blocks(GROUP_H_SIZE + dlen);
+	struct tipc_msg *hdr = &tsk->phdr;
+	struct sk_buff_head pkts;
+	int mtu, rc;
+
+	/* Complete message header */
+	msg_set_type(hdr, TIPC_GRP_UCAST_MSG);
+	msg_set_hdr_sz(hdr, GROUP_H_SIZE);
+	msg_set_destport(hdr, dport);
+	msg_set_destnode(hdr, dnode);
+	msg_set_grp_bc_seqno(hdr, bc_snd_nxt);
+
+	/* Build message as chain of buffers */
+	skb_queue_head_init(&pkts);
+	mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
+	rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
+	if (unlikely(rc != dlen))
+		return rc;
+
+	/* Send message */
+	rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
+	if (unlikely(rc == -ELINKCONG)) {
+		tipc_dest_push(&tsk->cong_links, dnode, 0);
+		tsk->cong_link_cnt++;
+	}
+
+	/* Update send window */
+	tipc_group_update_member(mb, blks);
+
+	/* A broadcast sent within next EXPIRE period must follow same path */
+	method->rcast = true;
+	method->mandatory = true;
+	return dlen;
+}
+
+/**
+ * tipc_send_group_unicast - send message to a member in the group
+ * @sock: socket structure
+ * @m: message to send
+ * @dlen: total length of message data
+ * @timeout: timeout to wait for wakeup
+ *
+ * Called from function tipc_sendmsg(), which has done all sanity checks
+ * Returns the number of bytes sent on success, or errno
+ */
+static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m,
+				   int dlen, long timeout)
+{
+	struct sock *sk = sock->sk;
+	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
+	int blks = tsk_blocks(GROUP_H_SIZE + dlen);
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_group *grp = tsk->group;
+	struct net *net = sock_net(sk);
+	struct tipc_member *mb = NULL;
+	u32 node, port;
+	int rc;
+
+	node = dest->addr.id.node;
+	port = dest->addr.id.ref;
+	if (!port && !node)
+		return -EHOSTUNREACH;
+
+	/* Block or return if destination link or member is congested */
+	rc = tipc_wait_for_cond(sock, &timeout,
+				!tipc_dest_find(&tsk->cong_links, node, 0) &&
+				!tipc_group_cong(grp, node, port, blks, &mb));
+	if (unlikely(rc))
+		return rc;
+
+	if (unlikely(!mb))
+		return -EHOSTUNREACH;
+
+	rc = tipc_send_group_msg(net, tsk, m, mb, node, port, dlen);
+
+	return rc ? rc : dlen;
+}
+
+/**
+ * tipc_send_group_anycast - send message to any member with given identity
+ * @sock: socket structure
+ * @m: message to send
+ * @dlen: total length of message data
+ * @timeout: timeout to wait for wakeup
+ *
+ * Called from function tipc_sendmsg(), which has done all sanity checks
+ * Returns the number of bytes sent on success, or errno
+ */
+static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
+				   int dlen, long timeout)
+{
+	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
+	struct sock *sk = sock->sk;
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct list_head *cong_links = &tsk->cong_links;
+	int blks = tsk_blocks(GROUP_H_SIZE + dlen);
+	struct tipc_group *grp = tsk->group;
+	struct tipc_member *first = NULL;
+	struct tipc_member *mbr = NULL;
+	struct net *net = sock_net(sk);
+	u32 node, port, exclude;
+	u32 type, inst, domain;
+	struct list_head dsts;
+	int lookups = 0;
+	int dstcnt, rc;
+	bool cong;
+
+	INIT_LIST_HEAD(&dsts);
+
+	type = dest->addr.name.name.type;
+	inst = dest->addr.name.name.instance;
+	domain = addr_domain(net, dest->scope);
+	exclude = tipc_group_exclude(grp);
+
+	while (++lookups < 4) {
+		first = NULL;
+
+		/* Look for a non-congested destination member, if any */
+		while (1) {
+			if (!tipc_nametbl_lookup(net, type, inst, domain, &dsts,
+						 &dstcnt, exclude, false))
+				return -EHOSTUNREACH;
+			tipc_dest_pop(&dsts, &node, &port);
+			cong = tipc_group_cong(grp, node, port, blks, &mbr);
+			if (!cong)
+				break;
+			if (mbr == first)
+				break;
+			if (!first)
+				first = mbr;
+		}
+
+		/* Start over if destination was not in member list */
+		if (unlikely(!mbr))
+			continue;
+
+		if (likely(!cong && !tipc_dest_find(cong_links, node, 0)))
+			break;
+
+		/* Block or return if destination link or member is congested */
+		rc = tipc_wait_for_cond(sock, &timeout,
+					!tipc_dest_find(cong_links, node, 0) &&
+					!tipc_group_cong(grp, node, port,
+							 blks, &mbr));
+		if (unlikely(rc))
+			return rc;
+
+		/* Send, unless destination disappeared while waiting */
+		if (likely(mbr))
+			break;
+	}
+
+	if (unlikely(lookups >= 4))
+		return -EHOSTUNREACH;
+
+	rc = tipc_send_group_msg(net, tsk, m, mbr, node, port, dlen);
+
+	return rc ? rc : dlen;
+}
+
+/**
+ * tipc_send_group_bcast - send message to all members in communication group
+ * @sk: socket structure
+ * @m: message to send
+ * @dlen: total length of message data
+ * @timeout: timeout to wait for wakeup
+ *
+ * Called from function tipc_sendmsg(), which has done all sanity checks
+ * Returns the number of bytes sent on success, or errno
+ */
+static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
+				 int dlen, long timeout)
+{
+	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
+	struct sock *sk = sock->sk;
+	struct net *net = sock_net(sk);
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_group *grp = tsk->group;
+	struct tipc_nlist *dsts = tipc_group_dests(grp);
+	struct tipc_mc_method *method = &tsk->mc_method;
+	bool ack = method->mandatory && method->rcast;
+	int blks = tsk_blocks(MCAST_H_SIZE + dlen);
+	struct tipc_msg *hdr = &tsk->phdr;
+	int mtu = tipc_bcast_get_mtu(net);
+	struct sk_buff_head pkts;
+	int rc = -EHOSTUNREACH;
+
+	if (!dsts->local && !dsts->remote)
+		return -EHOSTUNREACH;
+
+	/* Block or return if any destination link or member is congested */
+	rc = tipc_wait_for_cond(sock, &timeout,	!tsk->cong_link_cnt &&
+				!tipc_group_bc_cong(grp, blks));
+	if (unlikely(rc))
+		return rc;
+
+	/* Complete message header */
+	if (dest) {
+		msg_set_type(hdr, TIPC_GRP_MCAST_MSG);
+		msg_set_nameinst(hdr, dest->addr.name.name.instance);
+	} else {
+		msg_set_type(hdr, TIPC_GRP_BCAST_MSG);
+		msg_set_nameinst(hdr, 0);
+	}
+	msg_set_hdr_sz(hdr, GROUP_H_SIZE);
+	msg_set_destport(hdr, 0);
+	msg_set_destnode(hdr, 0);
+	msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp));
+
+	/* Avoid getting stuck with repeated forced replicasts */
+	msg_set_grp_bc_ack_req(hdr, ack);
+
+	/* Build message as chain of buffers */
+	skb_queue_head_init(&pkts);
+	rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
+	if (unlikely(rc != dlen))
+		return rc;
+
+	/* Send message */
+	rc = tipc_mcast_xmit(net, &pkts, method, dsts, &tsk->cong_link_cnt);
+	if (unlikely(rc))
+		return rc;
+
+	/* Update broadcast sequence number and send windows */
+	tipc_group_update_bc_members(tsk->group, blks, ack);
+
+	/* Broadcast link is now free to choose method for next broadcast */
+	method->mandatory = false;
+	method->expires = jiffies;
+
+	return dlen;
+}
+
+/**
+ * tipc_send_group_mcast - send message to all members with given identity
+ * @sock: socket structure
+ * @m: message to send
+ * @dlen: total length of message data
+ * @timeout: timeout to wait for wakeup
+ *
+ * Called from function tipc_sendmsg(), which has done all sanity checks
+ * Returns the number of bytes sent on success, or errno
+ */
+static int tipc_send_group_mcast(struct socket *sock, struct msghdr *m,
+				 int dlen, long timeout)
+{
+	struct sock *sk = sock->sk;
+	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
+	struct tipc_name_seq *seq = &dest->addr.nameseq;
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_group *grp = tsk->group;
+	struct net *net = sock_net(sk);
+	u32 domain, exclude, dstcnt;
+	struct list_head dsts;
+
+	INIT_LIST_HEAD(&dsts);
+
+	if (seq->lower != seq->upper)
+		return -ENOTSUPP;
+
+	domain = addr_domain(net, dest->scope);
+	exclude = tipc_group_exclude(grp);
+	if (!tipc_nametbl_lookup(net, seq->type, seq->lower, domain,
+				 &dsts, &dstcnt, exclude, true))
+		return -EHOSTUNREACH;
+
+	if (dstcnt == 1) {
+		tipc_dest_pop(&dsts, &dest->addr.id.node, &dest->addr.id.ref);
+		return tipc_send_group_unicast(sock, m, dlen, timeout);
+	}
+
+	tipc_dest_list_purge(&dsts);
+	return tipc_send_group_bcast(sock, m, dlen, timeout);
+}
+
+/**
  * tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets
  * @arrvq: queue with arriving messages, to be cloned after destination lookup
  * @inputq: queue with cloned messages, delivered to socket after dest lookup
@@ -803,13 +1116,15 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 		       struct sk_buff_head *inputq)
 {
-	struct tipc_msg *msg;
-	struct list_head dports;
-	u32 portid;
 	u32 scope = TIPC_CLUSTER_SCOPE;
-	struct sk_buff_head tmpq;
-	uint hsz;
+	u32 self = tipc_own_addr(net);
 	struct sk_buff *skb, *_skb;
+	u32 lower = 0, upper = ~0;
+	struct sk_buff_head tmpq;
+	u32 portid, oport, onode;
+	struct list_head dports;
+	struct tipc_msg *msg;
+	int user, mtyp, hsz;
 
 	__skb_queue_head_init(&tmpq);
 	INIT_LIST_HEAD(&dports);
@@ -817,17 +1132,32 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 	skb = tipc_skb_peek(arrvq, &inputq->lock);
 	for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) {
 		msg = buf_msg(skb);
+		user = msg_user(msg);
+		mtyp = msg_type(msg);
+		if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) {
+			spin_lock_bh(&inputq->lock);
+			if (skb_peek(arrvq) == skb) {
+				__skb_dequeue(arrvq);
+				__skb_queue_tail(inputq, skb);
+			}
+			refcount_dec(&skb->users);
+			spin_unlock_bh(&inputq->lock);
+			continue;
+		}
 		hsz = skb_headroom(skb) + msg_hdr_sz(msg);
-
-		if (in_own_node(net, msg_orignode(msg)))
+		oport = msg_origport(msg);
+		onode = msg_orignode(msg);
+		if (onode == self)
 			scope = TIPC_NODE_SCOPE;
 
 		/* Create destination port list and message clones: */
-		tipc_nametbl_mc_translate(net,
-					  msg_nametype(msg), msg_namelower(msg),
-					  msg_nameupper(msg), scope, &dports);
-		portid = u32_pop(&dports);
-		for (; portid; portid = u32_pop(&dports)) {
+		if (!msg_in_group(msg)) {
+			lower = msg_namelower(msg);
+			upper = msg_nameupper(msg);
+		}
+		tipc_nametbl_mc_translate(net, msg_nametype(msg), lower, upper,
+					  scope, &dports);
+		while (tipc_dest_pop(&dports, NULL, &portid)) {
 			_skb = __pskb_copy(skb, hsz, GFP_ATOMIC);
 			if (_skb) {
 				msg_set_destport(buf_msg(_skb), portid);
@@ -850,16 +1180,16 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 }
 
 /**
- * tipc_sk_proto_rcv - receive a connection mng protocol message
+ * tipc_sk_conn_proto_rcv - receive a connection mng protocol message
  * @tsk: receiving socket
  * @skb: pointer to message buffer.
  */
-static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
-			      struct sk_buff_head *xmitq)
+static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
+				   struct sk_buff_head *xmitq)
 {
-	struct sock *sk = &tsk->sk;
-	u32 onode = tsk_own_node(tsk);
 	struct tipc_msg *hdr = buf_msg(skb);
+	u32 onode = tsk_own_node(tsk);
+	struct sock *sk = &tsk->sk;
 	int mtyp = msg_type(hdr);
 	bool conn_cong;
 
@@ -931,6 +1261,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	long timeout = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
 	struct list_head *clinks = &tsk->cong_links;
 	bool syn = !tipc_sk_type_connectionless(sk);
+	struct tipc_group *grp = tsk->group;
 	struct tipc_msg *hdr = &tsk->phdr;
 	struct tipc_name_seq *seq;
 	struct sk_buff_head pkts;
@@ -941,18 +1272,31 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE))
 		return -EMSGSIZE;
 
+	if (likely(dest)) {
+		if (unlikely(m->msg_namelen < sizeof(*dest)))
+			return -EINVAL;
+		if (unlikely(dest->family != AF_TIPC))
+			return -EINVAL;
+	}
+
+	if (grp) {
+		if (!dest)
+			return tipc_send_group_bcast(sock, m, dlen, timeout);
+		if (dest->addrtype == TIPC_ADDR_NAME)
+			return tipc_send_group_anycast(sock, m, dlen, timeout);
+		if (dest->addrtype == TIPC_ADDR_ID)
+			return tipc_send_group_unicast(sock, m, dlen, timeout);
+		if (dest->addrtype == TIPC_ADDR_MCAST)
+			return tipc_send_group_mcast(sock, m, dlen, timeout);
+		return -EINVAL;
+	}
+
 	if (unlikely(!dest)) {
 		dest = &tsk->peer;
 		if (!syn || dest->family != AF_TIPC)
 			return -EDESTADDRREQ;
 	}
 
-	if (unlikely(m->msg_namelen < sizeof(*dest)))
-		return -EINVAL;
-
-	if (unlikely(dest->family != AF_TIPC))
-		return -EINVAL;
-
 	if (unlikely(syn)) {
 		if (sk->sk_state == TIPC_LISTEN)
 			return -EPIPE;
@@ -985,7 +1329,6 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 		msg_set_destport(hdr, dport);
 		if (unlikely(!dport && !dnode))
 			return -EHOSTUNREACH;
-
 	} else if (dest->addrtype == TIPC_ADDR_ID) {
 		dnode = dest->addr.id.node;
 		msg_set_type(hdr, TIPC_DIRECT_MSG);
@@ -996,7 +1339,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	}
 
 	/* Block or return if destination link is congested */
-	rc = tipc_wait_for_cond(sock, &timeout, !u32_find(clinks, dnode));
+	rc = tipc_wait_for_cond(sock, &timeout,
+				!tipc_dest_find(clinks, dnode, 0));
 	if (unlikely(rc))
 		return rc;
 
@@ -1008,7 +1352,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 
 	rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
 	if (unlikely(rc == -ELINKCONG)) {
-		u32_push(clinks, dnode);
+		tipc_dest_push(clinks, dnode, 0);
 		tsk->cong_link_cnt++;
 		rc = 0;
 	}
@@ -1128,7 +1472,7 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
 	msg_set_lookup_scope(msg, 0);
 	msg_set_hdr_sz(msg, SHORT_H_SIZE);
 
-	sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTERVAL);
+	sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTV);
 	tipc_set_sk_state(sk, TIPC_ESTABLISHED);
 	tipc_node_add_conn(net, peer_node, tsk->portid, peer_port);
 	tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid);
@@ -1142,26 +1486,38 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
 }
 
 /**
- * set_orig_addr - capture sender's address for received message
+ * tipc_sk_set_orig_addr - capture sender's address for received message
  * @m: descriptor for message info
- * @msg: received message header
+ * @hdr: received message header
  *
  * Note: Address is not captured if not requested by receiver.
  */
-static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg)
+static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
 {
-	DECLARE_SOCKADDR(struct sockaddr_tipc *, addr, m->msg_name);
+	DECLARE_SOCKADDR(struct sockaddr_pair *, srcaddr, m->msg_name);
+	struct tipc_msg *hdr = buf_msg(skb);
 
-	if (addr) {
-		addr->family = AF_TIPC;
-		addr->addrtype = TIPC_ADDR_ID;
-		memset(&addr->addr, 0, sizeof(addr->addr));
-		addr->addr.id.ref = msg_origport(msg);
-		addr->addr.id.node = msg_orignode(msg);
-		addr->addr.name.domain = 0;	/* could leave uninitialized */
-		addr->scope = 0;		/* could leave uninitialized */
-		m->msg_namelen = sizeof(struct sockaddr_tipc);
-	}
+	if (!srcaddr)
+		return;
+
+	srcaddr->sock.family = AF_TIPC;
+	srcaddr->sock.addrtype = TIPC_ADDR_ID;
+	srcaddr->sock.addr.id.ref = msg_origport(hdr);
+	srcaddr->sock.addr.id.node = msg_orignode(hdr);
+	srcaddr->sock.addr.name.domain = 0;
+	srcaddr->sock.scope = 0;
+	m->msg_namelen = sizeof(struct sockaddr_tipc);
+
+	if (!msg_in_group(hdr))
+		return;
+
+	/* Group message users may also want to know sending member's id */
+	srcaddr->member.family = AF_TIPC;
+	srcaddr->member.addrtype = TIPC_ADDR_NAME;
+	srcaddr->member.addr.name.name.type = msg_nametype(hdr);
+	srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member;
+	srcaddr->member.addr.name.domain = 0;
+	m->msg_namelen = sizeof(*srcaddr);
 }
 
 /**
@@ -1318,11 +1674,13 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 			size_t buflen,	int flags)
 {
 	struct sock *sk = sock->sk;
-	struct tipc_sock *tsk = tipc_sk(sk);
-	struct sk_buff *skb;
-	struct tipc_msg *hdr;
 	bool connected = !tipc_sk_type_connectionless(sk);
+	struct tipc_sock *tsk = tipc_sk(sk);
 	int rc, err, hlen, dlen, copy;
+	struct sk_buff_head xmitq;
+	struct tipc_msg *hdr;
+	struct sk_buff *skb;
+	bool grp_evt;
 	long timeout;
 
 	/* Catch invalid receive requests */
@@ -1336,8 +1694,8 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 	}
 	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
+	/* Step rcv queue to first msg with data or error; wait if necessary */
 	do {
-		/* Look at first msg in receive queue; wait if necessary */
 		rc = tipc_wait_for_rcvmsg(sock, &timeout);
 		if (unlikely(rc))
 			goto exit;
@@ -1346,13 +1704,14 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 		dlen = msg_data_sz(hdr);
 		hlen = msg_hdr_sz(hdr);
 		err = msg_errcode(hdr);
+		grp_evt = msg_is_grp_evt(hdr);
 		if (likely(dlen || err))
 			break;
 		tsk_advance_rx_queue(sk);
 	} while (1);
 
 	/* Collect msg meta data, including error code and rejected data */
-	set_orig_addr(m, hdr);
+	tipc_sk_set_orig_addr(m, skb);
 	rc = tipc_sk_anc_data_recv(m, hdr, tsk);
 	if (unlikely(rc))
 		goto exit;
@@ -1372,15 +1731,33 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 	if (unlikely(rc))
 		goto exit;
 
+	/* Mark message as group event if applicable */
+	if (unlikely(grp_evt)) {
+		if (msg_grp_evt(hdr) == TIPC_WITHDRAWN)
+			m->msg_flags |= MSG_EOR;
+		m->msg_flags |= MSG_OOB;
+		copy = 0;
+	}
+
 	/* Caption of data or error code/rejected data was successful */
 	if (unlikely(flags & MSG_PEEK))
 		goto exit;
 
+	/* Send group flow control advertisement when applicable */
+	if (tsk->group && msg_in_group(hdr) && !grp_evt) {
+		skb_queue_head_init(&xmitq);
+		tipc_group_update_rcv_win(tsk->group, tsk_blocks(hlen + dlen),
+					  msg_orignode(hdr), msg_origport(hdr),
+					  &xmitq);
+		tipc_node_distr_xmit(sock_net(sk), &xmitq);
+	}
+
 	tsk_advance_rx_queue(sk);
+
 	if (likely(!connected))
 		goto exit;
 
-	/* Send connection flow control ack when applicable */
+	/* Send connection flow control advertisement when applicable */
 	tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen);
 	if (tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE)
 		tipc_sk_send_ack(tsk);
@@ -1446,7 +1823,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
 
 		/* Collect msg meta data, incl. error code and rejected data */
 		if (!copied) {
-			set_orig_addr(m, hdr);
+			tipc_sk_set_orig_addr(m, skb);
 			rc = tipc_sk_anc_data_recv(m, hdr, tsk);
 			if (rc)
 				break;
@@ -1532,14 +1909,51 @@ static void tipc_sock_destruct(struct sock *sk)
 	__skb_queue_purge(&sk->sk_receive_queue);
 }
 
+static void tipc_sk_proto_rcv(struct sock *sk,
+			      struct sk_buff_head *inputq,
+			      struct sk_buff_head *xmitq)
+{
+	struct sk_buff *skb = __skb_dequeue(inputq);
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_msg *hdr = buf_msg(skb);
+	struct tipc_group *grp = tsk->group;
+	bool wakeup = false;
+
+	switch (msg_user(hdr)) {
+	case CONN_MANAGER:
+		tipc_sk_conn_proto_rcv(tsk, skb, xmitq);
+		return;
+	case SOCK_WAKEUP:
+		tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0);
+		tsk->cong_link_cnt--;
+		wakeup = true;
+		break;
+	case GROUP_PROTOCOL:
+		tipc_group_proto_rcv(grp, &wakeup, hdr, inputq, xmitq);
+		break;
+	case TOP_SRV:
+		tipc_group_member_evt(tsk->group, &wakeup, &sk->sk_rcvbuf,
+				      skb, inputq, xmitq);
+		skb = NULL;
+		break;
+	default:
+		break;
+	}
+
+	if (wakeup)
+		sk->sk_write_space(sk);
+
+	kfree_skb(skb);
+}
+
 /**
- * filter_connect - Handle all incoming messages for a connection-based socket
+ * tipc_filter_connect - Handle incoming message for a connection-based socket
  * @tsk: TIPC socket
  * @skb: pointer to message buffer. Set to NULL if buffer is consumed
  *
  * Returns true if everything ok, false otherwise
  */
-static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
+static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
 {
 	struct sock *sk = &tsk->sk;
 	struct net *net = sock_net(sk);
@@ -1643,6 +2057,9 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
 	struct tipc_sock *tsk = tipc_sk(sk);
 	struct tipc_msg *hdr = buf_msg(skb);
 
+	if (unlikely(msg_in_group(hdr)))
+		return sk->sk_rcvbuf;
+
 	if (unlikely(!msg_connected(hdr)))
 		return sk->sk_rcvbuf << msg_importance(hdr);
 
@@ -1653,7 +2070,7 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
 }
 
 /**
- * filter_rcv - validate incoming message
+ * tipc_sk_filter_rcv - validate incoming message
  * @sk: socket
  * @skb: pointer to message.
  *
@@ -1662,99 +2079,71 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
  *
  * Called with socket lock already taken
  *
- * Returns true if message was added to socket receive queue, otherwise false
  */
-static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
-		       struct sk_buff_head *xmitq)
+static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
+			       struct sk_buff_head *xmitq)
 {
+	bool sk_conn = !tipc_sk_type_connectionless(sk);
 	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_group *grp = tsk->group;
 	struct tipc_msg *hdr = buf_msg(skb);
-	unsigned int limit = rcvbuf_limit(sk, skb);
-	int err = TIPC_OK;
-	int usr = msg_user(hdr);
-	u32 onode;
+	struct net *net = sock_net(sk);
+	struct sk_buff_head inputq;
+	int limit, err = TIPC_OK;
 
-	if (unlikely(msg_user(hdr) == CONN_MANAGER)) {
-		tipc_sk_proto_rcv(tsk, skb, xmitq);
-		return false;
-	}
+	TIPC_SKB_CB(skb)->bytes_read = 0;
+	__skb_queue_head_init(&inputq);
+	__skb_queue_tail(&inputq, skb);
 
-	if (unlikely(usr == SOCK_WAKEUP)) {
-		onode = msg_orignode(hdr);
-		kfree_skb(skb);
-		u32_del(&tsk->cong_links, onode);
-		tsk->cong_link_cnt--;
-		sk->sk_write_space(sk);
-		return false;
-	}
+	if (unlikely(!msg_isdata(hdr)))
+		tipc_sk_proto_rcv(sk, &inputq, xmitq);
 
-	/* Drop if illegal message type */
-	if (unlikely(msg_type(hdr) > TIPC_DIRECT_MSG)) {
-		kfree_skb(skb);
-		return false;
-	}
+	if (unlikely(grp))
+		tipc_group_filter_msg(grp, &inputq, xmitq);
 
-	/* Reject if wrong message type for current socket state */
-	if (tipc_sk_type_connectionless(sk)) {
-		if (msg_connected(hdr)) {
+	/* Validate and add to receive buffer if there is space */
+	while ((skb = __skb_dequeue(&inputq))) {
+		hdr = buf_msg(skb);
+		limit = rcvbuf_limit(sk, skb);
+		if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) ||
+		    (!sk_conn && msg_connected(hdr)) ||
+		    (!grp && msg_in_group(hdr)))
 			err = TIPC_ERR_NO_PORT;
-			goto reject;
-		}
-	} else if (unlikely(!filter_connect(tsk, skb))) {
-		err = TIPC_ERR_NO_PORT;
-		goto reject;
-	}
+		else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit)
+			err = TIPC_ERR_OVERLOAD;
 
-	/* Reject message if there isn't room to queue it */
-	if (unlikely(sk_rmem_alloc_get(sk) + skb->truesize >= limit)) {
-		err = TIPC_ERR_OVERLOAD;
-		goto reject;
+		if (unlikely(err)) {
+			tipc_skb_reject(net, err, skb, xmitq);
+			err = TIPC_OK;
+			continue;
+		}
+		__skb_queue_tail(&sk->sk_receive_queue, skb);
+		skb_set_owner_r(skb, sk);
+		sk->sk_data_ready(sk);
 	}
-
-	/* Enqueue message */
-	TIPC_SKB_CB(skb)->bytes_read = 0;
-	__skb_queue_tail(&sk->sk_receive_queue, skb);
-	skb_set_owner_r(skb, sk);
-
-	sk->sk_data_ready(sk);
-	return true;
-
-reject:
-	if (tipc_msg_reverse(tsk_own_node(tsk), &skb, err))
-		__skb_queue_tail(xmitq, skb);
-	return false;
 }
 
 /**
- * tipc_backlog_rcv - handle incoming message from backlog queue
+ * tipc_sk_backlog_rcv - handle incoming message from backlog queue
  * @sk: socket
  * @skb: message
  *
  * Caller must hold socket lock
- *
- * Returns 0
  */
-static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 {
-	unsigned int truesize = skb->truesize;
+	unsigned int before = sk_rmem_alloc_get(sk);
 	struct sk_buff_head xmitq;
-	u32 dnode, selector;
+	unsigned int added;
 
 	__skb_queue_head_init(&xmitq);
 
-	if (likely(filter_rcv(sk, skb, &xmitq))) {
-		atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt);
-		return 0;
-	}
+	tipc_sk_filter_rcv(sk, skb, &xmitq);
+	added = sk_rmem_alloc_get(sk) - before;
+	atomic_add(added, &tipc_sk(sk)->dupl_rcvcnt);
 
-	if (skb_queue_empty(&xmitq))
-		return 0;
-
-	/* Send response/rejected message */
-	skb = __skb_dequeue(&xmitq);
-	dnode = msg_destnode(buf_msg(skb));
-	selector = msg_origport(buf_msg(skb));
-	tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
+	/* Send pending response/rejected messages, if any */
+	tipc_node_distr_xmit(sock_net(sk), &xmitq);
 	return 0;
 }
 
@@ -1786,7 +2175,7 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
 
 		/* Add message directly to receive queue if possible */
 		if (!sock_owned_by_user(sk)) {
-			filter_rcv(sk, skb, xmitq);
+			tipc_sk_filter_rcv(sk, skb, xmitq);
 			continue;
 		}
 
@@ -1833,14 +2222,10 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
 				spin_unlock_bh(&sk->sk_lock.slock);
 			}
 			/* Send pending response/rejected messages, if any */
-			while ((skb = __skb_dequeue(&xmitq))) {
-				dnode = msg_destnode(buf_msg(skb));
-				tipc_node_xmit_skb(net, skb, dnode, dport);
-			}
+			tipc_node_distr_xmit(sock_net(sk), &xmitq);
 			sock_put(sk);
 			continue;
 		}
-
 		/* No destination socket => dequeue skb if still there */
 		skb = tipc_skb_dequeue(inputq, dport);
 		if (!skb)
@@ -1903,28 +2288,32 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
 	int previous;
 	int res = 0;
 
+	if (destlen != sizeof(struct sockaddr_tipc))
+		return -EINVAL;
+
 	lock_sock(sk);
 
-	/* DGRAM/RDM connect(), just save the destaddr */
-	if (tipc_sk_type_connectionless(sk)) {
-		if (dst->family == AF_UNSPEC) {
-			memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc));
-		} else if (destlen != sizeof(struct sockaddr_tipc)) {
-			res = -EINVAL;
-		} else {
-			memcpy(&tsk->peer, dest, destlen);
-		}
+	if (tsk->group) {
+		res = -EINVAL;
 		goto exit;
 	}
 
-	/*
-	 * Reject connection attempt using multicast address
-	 *
-	 * Note: send_msg() validates the rest of the address fields,
-	 *       so there's no need to do it here
-	 */
-	if (dst->addrtype == TIPC_ADDR_MCAST) {
+	if (dst->family == AF_UNSPEC) {
+		memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc));
+		if (!tipc_sk_type_connectionless(sk))
+			res = -EINVAL;
+		goto exit;
+	} else if (dst->family != AF_TIPC) {
 		res = -EINVAL;
+	}
+	if (dst->addrtype != TIPC_ADDR_ID && dst->addrtype != TIPC_ADDR_NAME)
+		res = -EINVAL;
+	if (res)
+		goto exit;
+
+	/* DGRAM/RDM connect(), just save the destaddr */
+	if (tipc_sk_type_connectionless(sk)) {
+		memcpy(&tsk->peer, dest, destlen);
 		goto exit;
 	}
 
@@ -2141,46 +2530,43 @@ static int tipc_shutdown(struct socket *sock, int how)
 	return res;
 }
 
-static void tipc_sk_timeout(unsigned long data)
+static void tipc_sk_timeout(struct timer_list *t)
 {
-	struct tipc_sock *tsk = (struct tipc_sock *)data;
-	struct sock *sk = &tsk->sk;
-	struct sk_buff *skb = NULL;
-	u32 peer_port, peer_node;
+	struct sock *sk = from_timer(sk, t, sk_timer);
+	struct tipc_sock *tsk = tipc_sk(sk);
+	u32 peer_port = tsk_peer_port(tsk);
+	u32 peer_node = tsk_peer_node(tsk);
 	u32 own_node = tsk_own_node(tsk);
+	u32 own_port = tsk->portid;
+	struct net *net = sock_net(sk);
+	struct sk_buff *skb = NULL;
 
 	bh_lock_sock(sk);
-	if (!tipc_sk_connected(sk)) {
-		bh_unlock_sock(sk);
+	if (!tipc_sk_connected(sk))
+		goto exit;
+
+	/* Try again later if socket is busy */
+	if (sock_owned_by_user(sk)) {
+		sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 20);
 		goto exit;
 	}
-	peer_port = tsk_peer_port(tsk);
-	peer_node = tsk_peer_node(tsk);
 
 	if (tsk->probe_unacked) {
-		if (!sock_owned_by_user(sk)) {
-			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
-			tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk),
-					      tsk_peer_port(tsk));
-			sk->sk_state_change(sk);
-		} else {
-			/* Try again later */
-			sk_reset_timer(sk, &sk->sk_timer, (HZ / 20));
-		}
-
-		bh_unlock_sock(sk);
+		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+		tipc_node_remove_conn(net, peer_node, peer_port);
+		sk->sk_state_change(sk);
 		goto exit;
 	}
-
-	skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE,
-			      INT_H_SIZE, 0, peer_node, own_node,
-			      peer_port, tsk->portid, TIPC_OK);
+	/* Send new probe */
+	skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE, INT_H_SIZE, 0,
+			      peer_node, own_node, peer_port, own_port,
+			      TIPC_OK);
 	tsk->probe_unacked = true;
-	sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTERVAL);
+	sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTV);
+exit:
 	bh_unlock_sock(sk);
 	if (skb)
-		tipc_node_xmit_skb(sock_net(sk), skb, peer_node, tsk->portid);
-exit:
+		tipc_node_xmit_skb(net, skb, peer_node, own_port);
 	sock_put(sk);
 }
 
@@ -2345,6 +2731,58 @@ void tipc_sk_rht_destroy(struct net *net)
 	rhashtable_destroy(&tn->sk_rht);
 }
 
+static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq)
+{
+	struct net *net = sock_net(&tsk->sk);
+	u32 domain = addr_domain(net, mreq->scope);
+	struct tipc_group *grp = tsk->group;
+	struct tipc_msg *hdr = &tsk->phdr;
+	struct tipc_name_seq seq;
+	int rc;
+
+	if (mreq->type < TIPC_RESERVED_TYPES)
+		return -EACCES;
+	if (grp)
+		return -EACCES;
+	grp = tipc_group_create(net, tsk->portid, mreq);
+	if (!grp)
+		return -ENOMEM;
+	tsk->group = grp;
+	msg_set_lookup_scope(hdr, mreq->scope);
+	msg_set_nametype(hdr, mreq->type);
+	msg_set_dest_droppable(hdr, true);
+	seq.type = mreq->type;
+	seq.lower = mreq->instance;
+	seq.upper = seq.lower;
+	tipc_nametbl_build_group(net, grp, mreq->type, domain);
+	rc = tipc_sk_publish(tsk, mreq->scope, &seq);
+	if (rc) {
+		tipc_group_delete(net, grp);
+		tsk->group = NULL;
+	}
+
+	/* Eliminate any risk that a broadcast overtakes the sent JOIN */
+	tsk->mc_method.rcast = true;
+	tsk->mc_method.mandatory = true;
+	return rc;
+}
+
+static int tipc_sk_leave(struct tipc_sock *tsk)
+{
+	struct net *net = sock_net(&tsk->sk);
+	struct tipc_group *grp = tsk->group;
+	struct tipc_name_seq seq;
+	int scope;
+
+	if (!grp)
+		return -EINVAL;
+	tipc_group_self(grp, &seq, &scope);
+	tipc_group_delete(net, grp);
+	tsk->group = NULL;
+	tipc_sk_withdraw(tsk, scope, &seq);
+	return 0;
+}
+
 /**
  * tipc_setsockopt - set socket option
  * @sock: socket structure
@@ -2363,6 +2801,7 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_group_req mreq;
 	u32 value = 0;
 	int res = 0;
 
@@ -2378,9 +2817,14 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
 	case TIPC_CONN_TIMEOUT:
 		if (ol < sizeof(value))
 			return -EINVAL;
-		res = get_user(value, (u32 __user *)ov);
-		if (res)
-			return res;
+		if (get_user(value, (u32 __user *)ov))
+			return -EFAULT;
+		break;
+	case TIPC_GROUP_JOIN:
+		if (ol < sizeof(mreq))
+			return -EINVAL;
+		if (copy_from_user(&mreq, ov, sizeof(mreq)))
+			return -EFAULT;
 		break;
 	default:
 		if (ov || ol)
@@ -2413,6 +2857,12 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
 		tsk->mc_method.rcast = true;
 		tsk->mc_method.mandatory = true;
 		break;
+	case TIPC_GROUP_JOIN:
+		res = tipc_sk_join(tsk, &mreq);
+		break;
+	case TIPC_GROUP_LEAVE:
+		res = tipc_sk_leave(tsk);
+		break;
 	default:
 		res = -EINVAL;
 	}
@@ -2440,7 +2890,8 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
-	int len;
+	struct tipc_name_seq seq;
+	int len, scope;
 	u32 value;
 	int res;
 
@@ -2474,6 +2925,12 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
 	case TIPC_SOCK_RECVQ_DEPTH:
 		value = skb_queue_len(&sk->sk_receive_queue);
 		break;
+	case TIPC_GROUP_JOIN:
+		seq.type = 0;
+		if (tsk->group)
+			tipc_group_self(tsk->group, &seq, &scope);
+		value = seq.type;
+		break;
 	default:
 		res = -EINVAL;
 	}
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index be3d9e3183dc..251065dfd8df 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -133,9 +133,9 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower,
 				node);
 }
 
-static void tipc_subscrp_timeout(unsigned long data)
+static void tipc_subscrp_timeout(struct timer_list *t)
 {
-	struct tipc_subscription *sub = (struct tipc_subscription *)data;
+	struct tipc_subscription *sub = from_timer(sub, t, timer);
 	struct tipc_subscriber *subscriber = sub->subscriber;
 
 	spin_lock_bh(&subscriber->lock);
@@ -303,7 +303,7 @@ static void tipc_subscrp_subscribe(struct net *net, struct tipc_subscr *s,
 	tipc_subscrb_get(subscriber);
 	spin_unlock_bh(&subscriber->lock);
 
-	setup_timer(&sub->timer, tipc_subscrp_timeout, (unsigned long)sub);
+	timer_setup(&sub->timer, tipc_subscrp_timeout, 0);
 	timeout = htohl(sub->evt.s.timeout, swap);
 
 	if (timeout != TIPC_WAIT_FOREVER)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 7f46bab4ce5c..a9ee634f3c42 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -814,6 +814,7 @@ static int unix_create(struct net *net, struct socket *sock, int protocol,
 		 */
 	case SOCK_RAW:
 		sock->type = SOCK_DGRAM;
+		/* fall through */
 	case SOCK_DGRAM:
 		sock->ops = &unix_dgram_ops;
 		break;
diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig
index a24369d175fd..970f96489fe7 100644
--- a/net/vmw_vsock/Kconfig
+++ b/net/vmw_vsock/Kconfig
@@ -15,6 +15,16 @@ config VSOCKETS
 	  To compile this driver as a module, choose M here: the module
 	  will be called vsock. If unsure, say N.
 
+config VSOCKETS_DIAG
+	tristate "Virtual Sockets monitoring interface"
+	depends on VSOCKETS
+	default y
+	help
+	  Support for PF_VSOCK sockets monitoring interface used by the ss tool.
+	  If unsure, say Y.
+
+	  Enable this module so userspace applications can query open sockets.
+
 config VMWARE_VMCI_VSOCKETS
 	tristate "VMware VMCI transport for Virtual Sockets"
 	depends on VSOCKETS && VMWARE_VMCI
diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile
index 30a263320e4f..7c6f9a0b67b0 100644
--- a/net/vmw_vsock/Makefile
+++ b/net/vmw_vsock/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_VSOCKETS) += vsock.o
+obj-$(CONFIG_VSOCKETS_DIAG) += vsock_diag.o
 obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o
 obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o
 obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o
@@ -7,6 +8,8 @@ obj-$(CONFIG_HYPERV_VSOCKETS) += hv_sock.o
 
 vsock-y += af_vsock.o af_vsock_tap.o vsock_addr.o
 
+vsock_diag-y += diag.o
+
 vmw_vsock_vmci_transport-y += vmci_transport.o vmci_transport_notify.o \
 	vmci_transport_notify_qstate.o
 
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index dfc8c51e4d74..5d28abf87fbf 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -36,7 +36,7 @@
  * not support simultaneous connects (two "client" sockets connecting).
  *
  * - "Server" sockets are referred to as listener sockets throughout this
- * implementation because they are in the VSOCK_SS_LISTEN state.  When a
+ * implementation because they are in the TCP_LISTEN state.  When a
  * connection request is received (the second kind of socket mentioned above),
  * we create a new socket and refer to it as a pending socket.  These pending
  * sockets are placed on the pending connection list of the listener socket.
@@ -82,6 +82,15 @@
  * argument, we must ensure the reference count is increased to ensure the
  * socket isn't freed before the function is run; the deferred function will
  * then drop the reference.
+ *
+ * - sk->sk_state uses the TCP state constants because they are widely used by
+ * other address families and exposed to userspace tools like ss(8):
+ *
+ *   TCP_CLOSE - unconnected
+ *   TCP_SYN_SENT - connecting
+ *   TCP_ESTABLISHED - connected
+ *   TCP_CLOSING - disconnecting
+ *   TCP_LISTEN - listening
  */
 
 #include <linux/types.h>
@@ -153,7 +162,6 @@ EXPORT_SYMBOL_GPL(vm_sockets_get_local_cid);
  * vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets.  The hash function
  * mods with VSOCK_HASH_SIZE to ensure this.
  */
-#define VSOCK_HASH_SIZE         251
 #define MAX_PORT_RETRIES        24
 
 #define VSOCK_HASH(addr)        ((addr)->svm_port % VSOCK_HASH_SIZE)
@@ -168,9 +176,12 @@ EXPORT_SYMBOL_GPL(vm_sockets_get_local_cid);
 #define vsock_connected_sockets_vsk(vsk)				\
 	vsock_connected_sockets(&(vsk)->remote_addr, &(vsk)->local_addr)
 
-static struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1];
-static struct list_head vsock_connected_table[VSOCK_HASH_SIZE];
-static DEFINE_SPINLOCK(vsock_table_lock);
+struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1];
+EXPORT_SYMBOL_GPL(vsock_bind_table);
+struct list_head vsock_connected_table[VSOCK_HASH_SIZE];
+EXPORT_SYMBOL_GPL(vsock_connected_table);
+DEFINE_SPINLOCK(vsock_table_lock);
+EXPORT_SYMBOL_GPL(vsock_table_lock);
 
 /* Autobind this socket to the local address if necessary. */
 static int vsock_auto_bind(struct vsock_sock *vsk)
@@ -184,7 +195,7 @@ static int vsock_auto_bind(struct vsock_sock *vsk)
 	return __vsock_bind(sk, &local_addr);
 }
 
-static void vsock_init_tables(void)
+static int __init vsock_init_tables(void)
 {
 	int i;
 
@@ -193,6 +204,7 @@ static void vsock_init_tables(void)
 
 	for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++)
 		INIT_LIST_HEAD(&vsock_connected_table[i]);
+	return 0;
 }
 
 static void __vsock_insert_bound(struct list_head *list,
@@ -248,16 +260,6 @@ static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src,
 	return NULL;
 }
 
-static bool __vsock_in_bound_table(struct vsock_sock *vsk)
-{
-	return !list_empty(&vsk->bound_table);
-}
-
-static bool __vsock_in_connected_table(struct vsock_sock *vsk)
-{
-	return !list_empty(&vsk->connected_table);
-}
-
 static void vsock_insert_unbound(struct vsock_sock *vsk)
 {
 	spin_lock_bh(&vsock_table_lock);
@@ -485,7 +487,7 @@ void vsock_pending_work(struct work_struct *work)
 	if (vsock_in_connected_table(vsk))
 		vsock_remove_connected(vsk);
 
-	sk->sk_state = SS_FREE;
+	sk->sk_state = TCP_CLOSE;
 
 out:
 	release_sock(sk);
@@ -625,7 +627,6 @@ struct sock *__vsock_create(struct net *net,
 
 	sk->sk_destruct = vsock_sk_destruct;
 	sk->sk_backlog_rcv = vsock_queue_rcv_skb;
-	sk->sk_state = 0;
 	sock_reset_flag(sk, SOCK_DONE);
 
 	INIT_LIST_HEAD(&vsk->bound_table);
@@ -899,7 +900,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
 		/* Listening sockets that have connections in their accept
 		 * queue can be read.
 		 */
-		if (sk->sk_state == VSOCK_SS_LISTEN
+		if (sk->sk_state == TCP_LISTEN
 		    && !vsock_is_accept_queue_empty(sk))
 			mask |= POLLIN | POLLRDNORM;
 
@@ -928,7 +929,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
 		}
 
 		/* Connected sockets that can produce data can be written. */
-		if (sk->sk_state == SS_CONNECTED) {
+		if (sk->sk_state == TCP_ESTABLISHED) {
 			if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
 				bool space_avail_now = false;
 				int ret = transport->notify_poll_out(
@@ -950,7 +951,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
 		 * POLLOUT|POLLWRNORM when peer is closed and nothing to read,
 		 * but local send is not shutdown.
 		 */
-		if (sk->sk_state == SS_UNCONNECTED) {
+		if (sk->sk_state == TCP_CLOSE) {
 			if (!(sk->sk_shutdown & SEND_SHUTDOWN))
 				mask |= POLLOUT | POLLWRNORM;
 
@@ -1120,9 +1121,9 @@ static void vsock_connect_timeout(struct work_struct *work)
 	sk = sk_vsock(vsk);
 
 	lock_sock(sk);
-	if (sk->sk_state == SS_CONNECTING &&
+	if (sk->sk_state == TCP_SYN_SENT &&
 	    (sk->sk_shutdown != SHUTDOWN_MASK)) {
-		sk->sk_state = SS_UNCONNECTED;
+		sk->sk_state = TCP_CLOSE;
 		sk->sk_err = ETIMEDOUT;
 		sk->sk_error_report(sk);
 		cancel = 1;
@@ -1168,7 +1169,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 		err = -EALREADY;
 		break;
 	default:
-		if ((sk->sk_state == VSOCK_SS_LISTEN) ||
+		if ((sk->sk_state == TCP_LISTEN) ||
 		    vsock_addr_cast(addr, addr_len, &remote_addr) != 0) {
 			err = -EINVAL;
 			goto out;
@@ -1191,7 +1192,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 		if (err)
 			goto out;
 
-		sk->sk_state = SS_CONNECTING;
+		sk->sk_state = TCP_SYN_SENT;
 
 		err = transport->connect(vsk);
 		if (err < 0)
@@ -1211,7 +1212,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 	timeout = vsk->connect_timeout;
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 
-	while (sk->sk_state != SS_CONNECTED && sk->sk_err == 0) {
+	while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) {
 		if (flags & O_NONBLOCK) {
 			/* If we're not going to block, we schedule a timeout
 			 * function to generate a timeout on the connection
@@ -1234,13 +1235,13 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 
 		if (signal_pending(current)) {
 			err = sock_intr_errno(timeout);
-			sk->sk_state = SS_UNCONNECTED;
+			sk->sk_state = TCP_CLOSE;
 			sock->state = SS_UNCONNECTED;
 			vsock_transport_cancel_pkt(vsk);
 			goto out_wait;
 		} else if (timeout == 0) {
 			err = -ETIMEDOUT;
-			sk->sk_state = SS_UNCONNECTED;
+			sk->sk_state = TCP_CLOSE;
 			sock->state = SS_UNCONNECTED;
 			vsock_transport_cancel_pkt(vsk);
 			goto out_wait;
@@ -1251,7 +1252,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 
 	if (sk->sk_err) {
 		err = -sk->sk_err;
-		sk->sk_state = SS_UNCONNECTED;
+		sk->sk_state = TCP_CLOSE;
 		sock->state = SS_UNCONNECTED;
 	} else {
 		err = 0;
@@ -1284,7 +1285,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
 		goto out;
 	}
 
-	if (listener->sk_state != VSOCK_SS_LISTEN) {
+	if (listener->sk_state != TCP_LISTEN) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -1374,7 +1375,7 @@ static int vsock_listen(struct socket *sock, int backlog)
 	}
 
 	sk->sk_max_ack_backlog = backlog;
-	sk->sk_state = VSOCK_SS_LISTEN;
+	sk->sk_state = TCP_LISTEN;
 
 	err = 0;
 
@@ -1554,7 +1555,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	/* Callers should not provide a destination with stream sockets. */
 	if (msg->msg_namelen) {
-		err = sk->sk_state == SS_CONNECTED ? -EISCONN : -EOPNOTSUPP;
+		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
 		goto out;
 	}
 
@@ -1565,7 +1566,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		goto out;
 	}
 
-	if (sk->sk_state != SS_CONNECTED ||
+	if (sk->sk_state != TCP_ESTABLISHED ||
 	    !vsock_addr_bound(&vsk->local_addr)) {
 		err = -ENOTCONN;
 		goto out;
@@ -1689,7 +1690,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	lock_sock(sk);
 
-	if (sk->sk_state != SS_CONNECTED) {
+	if (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 occured with the
@@ -1957,8 +1958,6 @@ int __vsock_core_init(const struct vsock_transport *t, struct module *owner)
 	vsock_proto.owner = owner;
 	transport = t;
 
-	vsock_init_tables();
-
 	vsock_device.minor = MISC_DYNAMIC_MINOR;
 	err = misc_register(&vsock_device);
 	if (err) {
@@ -2019,6 +2018,8 @@ const struct vsock_transport *vsock_core_get_transport(void)
 }
 EXPORT_SYMBOL_GPL(vsock_core_get_transport);
 
+module_init(vsock_init_tables);
+
 MODULE_AUTHOR("VMware, Inc.");
 MODULE_DESCRIPTION("VMware Virtual Socket Family");
 MODULE_VERSION("1.0.2.0-k");
diff --git a/net/vmw_vsock/diag.c b/net/vmw_vsock/diag.c
new file mode 100644
index 000000000000..31b567652250
--- /dev/null
+++ b/net/vmw_vsock/diag.c
@@ -0,0 +1,186 @@
+/*
+ * vsock sock_diag(7) module
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation version 2 and no later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/module.h>
+#include <linux/sock_diag.h>
+#include <linux/vm_sockets_diag.h>
+#include <net/af_vsock.h>
+
+static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
+			u32 portid, u32 seq, u32 flags)
+{
+	struct vsock_sock *vsk = vsock_sk(sk);
+	struct vsock_diag_msg *rep;
+	struct nlmsghdr *nlh;
+
+	nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep),
+			flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	rep = nlmsg_data(nlh);
+	rep->vdiag_family = AF_VSOCK;
+
+	/* Lock order dictates that sk_lock is acquired before
+	 * vsock_table_lock, so we cannot lock here.  Simply don't take
+	 * sk_lock; sk is guaranteed to stay alive since vsock_table_lock is
+	 * held.
+	 */
+	rep->vdiag_type = sk->sk_type;
+	rep->vdiag_state = sk->sk_state;
+	rep->vdiag_shutdown = sk->sk_shutdown;
+	rep->vdiag_src_cid = vsk->local_addr.svm_cid;
+	rep->vdiag_src_port = vsk->local_addr.svm_port;
+	rep->vdiag_dst_cid = vsk->remote_addr.svm_cid;
+	rep->vdiag_dst_port = vsk->remote_addr.svm_port;
+	rep->vdiag_ino = sock_i_ino(sk);
+
+	sock_diag_save_cookie(sk, rep->vdiag_cookie);
+
+	return 0;
+}
+
+static int vsock_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct vsock_diag_req *req;
+	struct vsock_sock *vsk;
+	unsigned int bucket;
+	unsigned int last_i;
+	unsigned int table;
+	struct net *net;
+	unsigned int i;
+
+	req = nlmsg_data(cb->nlh);
+	net = sock_net(skb->sk);
+
+	/* State saved between calls: */
+	table = cb->args[0];
+	bucket = cb->args[1];
+	i = last_i = cb->args[2];
+
+	/* TODO VMCI pending sockets? */
+
+	spin_lock_bh(&vsock_table_lock);
+
+	/* Bind table (locally created sockets) */
+	if (table == 0) {
+		while (bucket < ARRAY_SIZE(vsock_bind_table)) {
+			struct list_head *head = &vsock_bind_table[bucket];
+
+			i = 0;
+			list_for_each_entry(vsk, head, bound_table) {
+				struct sock *sk = sk_vsock(vsk);
+
+				if (!net_eq(sock_net(sk), net))
+					continue;
+				if (i < last_i)
+					goto next_bind;
+				if (!(req->vdiag_states & (1 << sk->sk_state)))
+					goto next_bind;
+				if (sk_diag_fill(sk, skb,
+						 NETLINK_CB(cb->skb).portid,
+						 cb->nlh->nlmsg_seq,
+						 NLM_F_MULTI) < 0)
+					goto done;
+next_bind:
+				i++;
+			}
+			last_i = 0;
+			bucket++;
+		}
+
+		table++;
+		bucket = 0;
+	}
+
+	/* Connected table (accepted connections) */
+	while (bucket < ARRAY_SIZE(vsock_connected_table)) {
+		struct list_head *head = &vsock_connected_table[bucket];
+
+		i = 0;
+		list_for_each_entry(vsk, head, connected_table) {
+			struct sock *sk = sk_vsock(vsk);
+
+			/* Skip sockets we've already seen above */
+			if (__vsock_in_bound_table(vsk))
+				continue;
+
+			if (!net_eq(sock_net(sk), net))
+				continue;
+			if (i < last_i)
+				goto next_connected;
+			if (!(req->vdiag_states & (1 << sk->sk_state)))
+				goto next_connected;
+			if (sk_diag_fill(sk, skb,
+					 NETLINK_CB(cb->skb).portid,
+					 cb->nlh->nlmsg_seq,
+					 NLM_F_MULTI) < 0)
+				goto done;
+next_connected:
+			i++;
+		}
+		last_i = 0;
+		bucket++;
+	}
+
+done:
+	spin_unlock_bh(&vsock_table_lock);
+
+	cb->args[0] = table;
+	cb->args[1] = bucket;
+	cb->args[2] = i;
+
+	return skb->len;
+}
+
+static int vsock_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
+{
+	int hdrlen = sizeof(struct vsock_diag_req);
+	struct net *net = sock_net(skb->sk);
+
+	if (nlmsg_len(h) < hdrlen)
+		return -EINVAL;
+
+	if (h->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = vsock_diag_dump,
+		};
+		return netlink_dump_start(net->diag_nlsk, skb, h, &c);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static const struct sock_diag_handler vsock_diag_handler = {
+	.family = AF_VSOCK,
+	.dump = vsock_diag_handler_dump,
+};
+
+static int __init vsock_diag_init(void)
+{
+	return sock_diag_register(&vsock_diag_handler);
+}
+
+static void __exit vsock_diag_exit(void)
+{
+	sock_diag_unregister(&vsock_diag_handler);
+}
+
+module_init(vsock_diag_init);
+module_exit(vsock_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG,
+			       40 /* AF_VSOCK */);
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index e21991fe883a..5583df708b8c 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -312,7 +312,7 @@ static void hvs_close_connection(struct vmbus_channel *chan)
 
 	lock_sock(sk);
 
-	sk->sk_state = SS_UNCONNECTED;
+	sk->sk_state = TCP_CLOSE;
 	sock_set_flag(sk, SOCK_DONE);
 	vsk->peer_shutdown |= SEND_SHUTDOWN | RCV_SHUTDOWN;
 
@@ -349,9 +349,8 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 		return;
 
 	lock_sock(sk);
-
-	if ((conn_from_host && sk->sk_state != VSOCK_SS_LISTEN) ||
-	    (!conn_from_host && sk->sk_state != SS_CONNECTING))
+	if ((conn_from_host && sk->sk_state != TCP_LISTEN) ||
+	    (!conn_from_host && sk->sk_state != TCP_SYN_SENT))
 		goto out;
 
 	if (conn_from_host) {
@@ -363,7 +362,7 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 		if (!new)
 			goto out;
 
-		new->sk_state = SS_CONNECTING;
+		new->sk_state = TCP_SYN_SENT;
 		vnew = vsock_sk(new);
 		hvs_new = vnew->trans;
 		hvs_new->chan = chan;
@@ -390,7 +389,7 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 	vmbus_set_chn_rescind_callback(chan, hvs_close_connection);
 
 	if (conn_from_host) {
-		new->sk_state = SS_CONNECTED;
+		new->sk_state = TCP_ESTABLISHED;
 		sk->sk_ack_backlog++;
 
 		hvs_addr_init(&vnew->local_addr, if_type);
@@ -403,7 +402,7 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 
 		vsock_enqueue_accept(sk, new);
 	} else {
-		sk->sk_state = SS_CONNECTED;
+		sk->sk_state = TCP_ESTABLISHED;
 		sk->sk_socket->state = SS_CONNECTED;
 
 		vsock_insert_connected(vsock_sk(sk));
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 403d86e80162..8e03bd3f3668 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -414,7 +414,7 @@ static void virtio_vsock_event_fill(struct virtio_vsock *vsock)
 static void virtio_vsock_reset_sock(struct sock *sk)
 {
 	lock_sock(sk);
-	sk->sk_state = SS_UNCONNECTED;
+	sk->sk_state = TCP_CLOSE;
 	sk->sk_err = ECONNRESET;
 	sk->sk_error_report(sk);
 	release_sock(sk);
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index edba7ab97563..3ae3a33da70b 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -708,7 +708,7 @@ static void virtio_transport_do_close(struct vsock_sock *vsk,
 	sock_set_flag(sk, SOCK_DONE);
 	vsk->peer_shutdown = SHUTDOWN_MASK;
 	if (vsock_stream_has_data(vsk) <= 0)
-		sk->sk_state = SS_DISCONNECTING;
+		sk->sk_state = TCP_CLOSING;
 	sk->sk_state_change(sk);
 
 	if (vsk->close_work_scheduled &&
@@ -748,8 +748,8 @@ static bool virtio_transport_close(struct vsock_sock *vsk)
 {
 	struct sock *sk = &vsk->sk;
 
-	if (!(sk->sk_state == SS_CONNECTED ||
-	      sk->sk_state == SS_DISCONNECTING))
+	if (!(sk->sk_state == TCP_ESTABLISHED ||
+	      sk->sk_state == TCP_CLOSING))
 		return true;
 
 	/* Already received SHUTDOWN from peer, reply with RST */
@@ -801,7 +801,7 @@ virtio_transport_recv_connecting(struct sock *sk,
 
 	switch (le16_to_cpu(pkt->hdr.op)) {
 	case VIRTIO_VSOCK_OP_RESPONSE:
-		sk->sk_state = SS_CONNECTED;
+		sk->sk_state = TCP_ESTABLISHED;
 		sk->sk_socket->state = SS_CONNECTED;
 		vsock_insert_connected(vsk);
 		sk->sk_state_change(sk);
@@ -821,7 +821,7 @@ virtio_transport_recv_connecting(struct sock *sk,
 
 destroy:
 	virtio_transport_reset(vsk, pkt);
-	sk->sk_state = SS_UNCONNECTED;
+	sk->sk_state = TCP_CLOSE;
 	sk->sk_err = skerr;
 	sk->sk_error_report(sk);
 	return err;
@@ -857,7 +857,7 @@ virtio_transport_recv_connected(struct sock *sk,
 			vsk->peer_shutdown |= SEND_SHUTDOWN;
 		if (vsk->peer_shutdown == SHUTDOWN_MASK &&
 		    vsock_stream_has_data(vsk) <= 0)
-			sk->sk_state = SS_DISCONNECTING;
+			sk->sk_state = TCP_CLOSING;
 		if (le32_to_cpu(pkt->hdr.flags))
 			sk->sk_state_change(sk);
 		break;
@@ -928,7 +928,7 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt)
 
 	lock_sock_nested(child, SINGLE_DEPTH_NESTING);
 
-	child->sk_state = SS_CONNECTED;
+	child->sk_state = TCP_ESTABLISHED;
 
 	vchild = vsock_sk(child);
 	vsock_addr_init(&vchild->local_addr, le64_to_cpu(pkt->hdr.dst_cid),
@@ -1016,18 +1016,18 @@ void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt)
 		sk->sk_write_space(sk);
 
 	switch (sk->sk_state) {
-	case VSOCK_SS_LISTEN:
+	case TCP_LISTEN:
 		virtio_transport_recv_listen(sk, pkt);
 		virtio_transport_free_pkt(pkt);
 		break;
-	case SS_CONNECTING:
+	case TCP_SYN_SENT:
 		virtio_transport_recv_connecting(sk, pkt);
 		virtio_transport_free_pkt(pkt);
 		break;
-	case SS_CONNECTED:
+	case TCP_ESTABLISHED:
 		virtio_transport_recv_connected(sk, pkt);
 		break;
-	case SS_DISCONNECTING:
+	case TCP_CLOSING:
 		virtio_transport_recv_disconnecting(sk, pkt);
 		virtio_transport_free_pkt(pkt);
 		break;
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 10ae7823a19d..391775e3575c 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -21,7 +21,6 @@
 #include <linux/kernel.h>
 #include <linux/kmod.h>
 #include <linux/list.h>
-#include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/net.h>
@@ -743,7 +742,7 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg)
 		/* The local context ID may be out of date, update it. */
 		vsk->local_addr.svm_cid = dst.svm_cid;
 
-		if (sk->sk_state == SS_CONNECTED)
+		if (sk->sk_state == TCP_ESTABLISHED)
 			vmci_trans(vsk)->notify_ops->handle_notify_pkt(
 					sk, pkt, true, &dst, &src,
 					&bh_process_pkt);
@@ -801,7 +800,9 @@ static void vmci_transport_handle_detach(struct sock *sk)
 		 * left in our consume queue.
 		 */
 		if (vsock_stream_has_data(vsk) <= 0) {
-			if (sk->sk_state == SS_CONNECTING) {
+			sk->sk_state = TCP_CLOSE;
+
+			if (sk->sk_state == TCP_SYN_SENT) {
 				/* The peer may detach from a queue pair while
 				 * we are still in the connecting state, i.e.,
 				 * if the peer VM is killed after attaching to
@@ -810,12 +811,10 @@ static void vmci_transport_handle_detach(struct sock *sk)
 				 * event like a reset.
 				 */
 
-				sk->sk_state = SS_UNCONNECTED;
 				sk->sk_err = ECONNRESET;
 				sk->sk_error_report(sk);
 				return;
 			}
-			sk->sk_state = SS_UNCONNECTED;
 		}
 		sk->sk_state_change(sk);
 	}
@@ -883,17 +882,17 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work)
 	vsock_sk(sk)->local_addr.svm_cid = pkt->dg.dst.context;
 
 	switch (sk->sk_state) {
-	case VSOCK_SS_LISTEN:
+	case TCP_LISTEN:
 		vmci_transport_recv_listen(sk, pkt);
 		break;
-	case SS_CONNECTING:
+	case TCP_SYN_SENT:
 		/* Processing of pending connections for servers goes through
 		 * the listening socket, so see vmci_transport_recv_listen()
 		 * for that path.
 		 */
 		vmci_transport_recv_connecting_client(sk, pkt);
 		break;
-	case SS_CONNECTED:
+	case TCP_ESTABLISHED:
 		vmci_transport_recv_connected(sk, pkt);
 		break;
 	default:
@@ -942,7 +941,7 @@ static int vmci_transport_recv_listen(struct sock *sk,
 		vsock_sk(pending)->local_addr.svm_cid = pkt->dg.dst.context;
 
 		switch (pending->sk_state) {
-		case SS_CONNECTING:
+		case TCP_SYN_SENT:
 			err = vmci_transport_recv_connecting_server(sk,
 								    pending,
 								    pkt);
@@ -1072,7 +1071,7 @@ static int vmci_transport_recv_listen(struct sock *sk,
 	vsock_add_pending(sk, pending);
 	sk->sk_ack_backlog++;
 
-	pending->sk_state = SS_CONNECTING;
+	pending->sk_state = TCP_SYN_SENT;
 	vmci_trans(vpending)->produce_size =
 		vmci_trans(vpending)->consume_size = qp_size;
 	vmci_trans(vpending)->queue_pair_size = qp_size;
@@ -1197,11 +1196,11 @@ vmci_transport_recv_connecting_server(struct sock *listener,
 	 * the socket will be valid until it is removed from the queue.
 	 *
 	 * If we fail sending the attach below, we remove the socket from the
-	 * connected list and move the socket to SS_UNCONNECTED before
+	 * connected list and move the socket to TCP_CLOSE before
 	 * releasing the lock, so a pending slow path processing of an incoming
 	 * packet will not see the socket in the connected state in that case.
 	 */
-	pending->sk_state = SS_CONNECTED;
+	pending->sk_state = TCP_ESTABLISHED;
 
 	vsock_insert_connected(vpending);
 
@@ -1232,7 +1231,7 @@ vmci_transport_recv_connecting_server(struct sock *listener,
 
 destroy:
 	pending->sk_err = skerr;
-	pending->sk_state = SS_UNCONNECTED;
+	pending->sk_state = TCP_CLOSE;
 	/* As long as we drop our reference, all necessary cleanup will handle
 	 * when the cleanup function drops its reference and our destruct
 	 * implementation is called.  Note that since the listen handler will
@@ -1270,7 +1269,7 @@ vmci_transport_recv_connecting_client(struct sock *sk,
 		 * accounting (it can already be found since it's in the bound
 		 * table).
 		 */
-		sk->sk_state = SS_CONNECTED;
+		sk->sk_state = TCP_ESTABLISHED;
 		sk->sk_socket->state = SS_CONNECTED;
 		vsock_insert_connected(vsk);
 		sk->sk_state_change(sk);
@@ -1338,7 +1337,7 @@ vmci_transport_recv_connecting_client(struct sock *sk,
 destroy:
 	vmci_transport_send_reset(sk, pkt);
 
-	sk->sk_state = SS_UNCONNECTED;
+	sk->sk_state = TCP_CLOSE;
 	sk->sk_err = skerr;
 	sk->sk_error_report(sk);
 	return err;
@@ -1526,7 +1525,7 @@ static int vmci_transport_recv_connected(struct sock *sk,
 		sock_set_flag(sk, SOCK_DONE);
 		vsk->peer_shutdown = SHUTDOWN_MASK;
 		if (vsock_stream_has_data(vsk) <= 0)
-			sk->sk_state = SS_DISCONNECTING;
+			sk->sk_state = TCP_CLOSING;
 
 		sk->sk_state_change(sk);
 		break;
@@ -1790,7 +1789,7 @@ static int vmci_transport_connect(struct vsock_sock *vsk)
 		err = vmci_transport_send_conn_request(
 			sk, vmci_trans(vsk)->queue_pair_size);
 		if (err < 0) {
-			sk->sk_state = SS_UNCONNECTED;
+			sk->sk_state = TCP_CLOSE;
 			return err;
 		}
 	} else {
@@ -1800,7 +1799,7 @@ static int vmci_transport_connect(struct vsock_sock *vsk)
 				sk, vmci_trans(vsk)->queue_pair_size,
 				supported_proto_versions);
 		if (err < 0) {
-			sk->sk_state = SS_UNCONNECTED;
+			sk->sk_state = TCP_CLOSE;
 			return err;
 		}
 
diff --git a/net/vmw_vsock/vmci_transport_notify.c b/net/vmw_vsock/vmci_transport_notify.c
index 1406db4d97d1..41fb427f150a 100644
--- a/net/vmw_vsock/vmci_transport_notify.c
+++ b/net/vmw_vsock/vmci_transport_notify.c
@@ -355,7 +355,7 @@ vmci_transport_notify_pkt_poll_in(struct sock *sk,
 		 * queue. Ask for notifications when there is something to
 		 * read.
 		 */
-		if (sk->sk_state == SS_CONNECTED) {
+		if (sk->sk_state == TCP_ESTABLISHED) {
 			if (!send_waiting_read(sk, 1))
 				return -1;
 
diff --git a/net/vmw_vsock/vmci_transport_notify_qstate.c b/net/vmw_vsock/vmci_transport_notify_qstate.c
index f3a0afc46208..0cc84f2bb05e 100644
--- a/net/vmw_vsock/vmci_transport_notify_qstate.c
+++ b/net/vmw_vsock/vmci_transport_notify_qstate.c
@@ -176,7 +176,7 @@ vmci_transport_notify_pkt_poll_in(struct sock *sk,
 		 * queue. Ask for notifications when there is something to
 		 * read.
 		 */
-		if (sk->sk_state == SS_CONNECTED)
+		if (sk->sk_state == TCP_ESTABLISHED)
 			vsock_block_update_write_window(sk);
 		*data_ready_now = false;
 	}
diff --git a/net/wireless/.gitignore b/net/wireless/.gitignore
index c33451b896d9..61cbc304a3d3 100644
--- a/net/wireless/.gitignore
+++ b/net/wireless/.gitignore
@@ -1 +1,2 @@
-regdb.c
+shipped-certs.c
+extra-certs.c
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index 6c606120abfe..da91bb547db3 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -19,6 +19,7 @@ config WEXT_PRIV
 config CFG80211
 	tristate "cfg80211 - wireless configuration API"
 	depends on RFKILL || !RFKILL
+	select FW_LOADER
 	---help---
 	  cfg80211 is the Linux wireless LAN (802.11) configuration API.
 	  Enable this if you have a wireless device.
@@ -82,6 +83,36 @@ config CFG80211_CERTIFICATION_ONUS
 	  you are a wireless researcher and are working in a controlled
 	  and approved environment by your local regulatory agency.
 
+config CFG80211_REQUIRE_SIGNED_REGDB
+	bool "require regdb signature" if CFG80211_CERTIFICATION_ONUS
+	default y
+	select SYSTEM_DATA_VERIFICATION
+	help
+	  Require that in addition to the "regulatory.db" file a
+	  "regulatory.db.p7s" can be loaded with a valid PKCS#7
+	  signature for the regulatory.db file made by one of the
+	  keys in the certs/ directory.
+
+config CFG80211_USE_KERNEL_REGDB_KEYS
+	bool "allow regdb keys shipped with the kernel" if CFG80211_CERTIFICATION_ONUS
+	default y
+	depends on CFG80211_REQUIRE_SIGNED_REGDB
+	help
+	  Allow the regulatory database to be signed by one of the keys for
+	  which certificates are part of the kernel sources
+	  (in net/wireless/certs/).
+
+	  This is currently only Seth Forshee's key, who is the regulatory
+	  database maintainer.
+
+config CFG80211_EXTRA_REGDB_KEYDIR
+	string "additional regdb key directory" if CFG80211_CERTIFICATION_ONUS
+	depends on CFG80211_REQUIRE_SIGNED_REGDB
+	help
+	  If selected, point to a directory with DER-encoded X.509
+	  certificates like in the kernel sources (net/wireless/certs/)
+	  that shall be accepted for a signed regulatory database.
+
 config CFG80211_REG_CELLULAR_HINTS
 	bool "cfg80211 regulatory support for cellular base station hints"
 	depends on CFG80211_CERTIFICATION_ONUS
@@ -139,35 +170,14 @@ config CFG80211_DEBUGFS
 
 	  If unsure, say N.
 
-config CFG80211_INTERNAL_REGDB
-	bool "use statically compiled regulatory rules database" if EXPERT
-	default n
-	depends on CFG80211
-	---help---
-	  This option generates an internal data structure representing
-	  the wireless regulatory rules described in net/wireless/db.txt
-	  and includes code to query that database. This is an alternative
-	  to using CRDA for defining regulatory rules for the kernel.
-
-	  Using this option requires some parsing of the db.txt at build time,
-	  the parser will be upkept with the latest wireless-regdb updates but
-	  older wireless-regdb formats will be ignored. The parser may later
-	  be replaced to avoid issues with conflicts on versions of
-	  wireless-regdb.
-
-	  For details see:
-
-	  http://wireless.kernel.org/en/developers/Regulatory
-
-	  Most distributions have a CRDA package. So if unsure, say N.
-
 config CFG80211_CRDA_SUPPORT
-	bool "support CRDA" if CFG80211_INTERNAL_REGDB
+	bool "support CRDA" if EXPERT
 	default y
 	depends on CFG80211
 	help
 	  You should enable this option unless you know for sure you have no
-	  need for it, for example when using internal regdb (above.)
+	  need for it, for example when using internal regdb (above) or the
+	  database loaded as a firmware file.
 
 	  If unsure, say Y.
 
diff --git a/net/wireless/Makefile b/net/wireless/Makefile
index b7c0300e0b08..278d979c211a 100644
--- a/net/wireless/Makefile
+++ b/net/wireless/Makefile
@@ -15,11 +15,27 @@ cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o ap.o trace.o ocb.o
 cfg80211-$(CONFIG_OF) += of.o
 cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o
 cfg80211-$(CONFIG_CFG80211_WEXT) += wext-compat.o wext-sme.o
-cfg80211-$(CONFIG_CFG80211_INTERNAL_REGDB) += regdb.o
 
 CFLAGS_trace.o := -I$(src)
 
-$(obj)/regdb.c: $(src)/db.txt $(src)/genregdb.awk
-	@$(AWK) -f $(srctree)/$(src)/genregdb.awk < $< > $@
+cfg80211-$(CONFIG_CFG80211_USE_KERNEL_REGDB_KEYS) += shipped-certs.o
+ifneq ($(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR),)
+cfg80211-y += extra-certs.o
+endif
 
-clean-files := regdb.c
+$(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.x509)
+	@$(kecho) "  GEN     $@"
+	@echo '#include "reg.h"' > $@
+	@echo 'const u8 shipped_regdb_certs[] = {' >> $@
+	@for f in $^ ; do hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ ; done
+	@echo '};' >> $@
+	@echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);' >> $@
+
+$(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \
+		      $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%)/*.x509)
+	@$(kecho) "  GEN     $@"
+	@echo '#include "reg.h"' > $@
+	@echo 'const u8 extra_regdb_certs[] = {' >> $@
+	@for f in $^ ; do test -f $$f && hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ || true ; done
+	@echo '};' >> $@
+	@echo 'unsigned int extra_regdb_certs_len = sizeof(extra_regdb_certs);' >> $@
diff --git a/net/wireless/certs/sforshee.x509 b/net/wireless/certs/sforshee.x509
new file mode 100644
index 000000000000..c6f8f9d6b988
--- /dev/null
+++ b/net/wireless/certs/sforshee.x509
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index fad1b5baf8ff..a48859982a32 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -465,7 +465,7 @@ bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef,
 			  struct ieee80211_channel *chan)
 {
 	int width;
-	u32 cf_offset, freq;
+	u32 freq;
 
 	if (chandef->chan->center_freq == chan->center_freq)
 		return true;
@@ -474,8 +474,6 @@ bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef,
 	if (width <= 20)
 		return false;
 
-	cf_offset = width / 2 - 10;
-
 	for (freq = chandef->center_freq1 - width / 2 + 10;
 	     freq <= chandef->center_freq1 + width / 2 - 10; freq += 20) {
 		if (chan->center_freq == freq)
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 7b33e8c366bc..fdde0d98fde1 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1384,7 +1384,7 @@ out_fail_sysfs:
 out_fail_pernet:
 	return err;
 }
-subsys_initcall(cfg80211_init);
+fs_initcall(cfg80211_init);
 
 static void __exit cfg80211_exit(void)
 {
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 705835047f98..d2f7e8b8a097 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -217,6 +217,7 @@ enum cfg80211_event_type {
 	EVENT_DISCONNECTED,
 	EVENT_IBSS_JOINED,
 	EVENT_STOPPED,
+	EVENT_PORT_AUTHORIZED,
 };
 
 struct cfg80211_event {
@@ -236,6 +237,9 @@ struct cfg80211_event {
 			u8 bssid[ETH_ALEN];
 			struct ieee80211_channel *channel;
 		} ij;
+		struct {
+			u8 bssid[ETH_ALEN];
+		} pa;
 	};
 };
 
@@ -386,6 +390,7 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev,
 			bool wextev);
 void __cfg80211_roamed(struct wireless_dev *wdev,
 		       struct cfg80211_roam_info *info);
+void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid);
 int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev,
 			      struct wireless_dev *wdev);
 void cfg80211_autodisconnect_wk(struct work_struct *work);
diff --git a/net/wireless/db.txt b/net/wireless/db.txt
deleted file mode 100644
index a2fc3a09ccdc..000000000000
--- a/net/wireless/db.txt
+++ /dev/null
@@ -1,17 +0,0 @@
-#
-# This file is a placeholder to prevent accidental build breakage if someone
-# enables CONFIG_CFG80211_INTERNAL_REGDB.  Almost no one actually needs to
-# enable that build option.
-#
-# You should be using CRDA instead.  It is even better if you use the CRDA
-# package provided by your distribution, since they will probably keep it
-# up-to-date on your behalf.
-#
-# If you _really_ intend to use CONFIG_CFG80211_INTERNAL_REGDB then you will
-# need to replace this file with one containing appropriately formatted
-# regulatory rules that cover the regulatory domains you will be using.  Your
-# best option is to extract the db.txt file from the wireless-regdb git
-# repository:
-#
-#   git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-regdb.git
-#
diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk
deleted file mode 100644
index baf2426b555a..000000000000
--- a/net/wireless/genregdb.awk
+++ /dev/null
@@ -1,158 +0,0 @@
-#!/usr/bin/awk -f
-#
-# genregdb.awk -- generate regdb.c from db.txt
-#
-# Actually, it reads from stdin (presumed to be db.txt) and writes
-# to stdout (presumed to be regdb.c), but close enough...
-#
-# Copyright 2009 John W. Linville <linville@tuxdriver.com>
-#
-# Permission to use, copy, modify, and/or distribute this software for any
-# purpose with or without fee is hereby granted, provided that the above
-# copyright notice and this permission notice appear in all copies.
-#
-# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
-# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
-# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
-# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
-# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
-# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
-# OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
-
-BEGIN {
-	active = 0
-	rules = 0;
-	print "/*"
-	print " * DO NOT EDIT -- file generated from data in db.txt"
-	print " */"
-	print ""
-	print "#include <linux/nl80211.h>"
-	print "#include <net/cfg80211.h>"
-	print "#include \"regdb.h\""
-	print ""
-	regdb = "const struct ieee80211_regdomain *reg_regdb[] = {\n"
-}
-
-function parse_country_head() {
-	country=$2
-	sub(/:/, "", country)
-	printf "static const struct ieee80211_regdomain regdom_%s = {\n", country
-	printf "\t.alpha2 = \"%s\",\n", country
-	if ($NF ~ /DFS-ETSI/)
-		printf "\t.dfs_region = NL80211_DFS_ETSI,\n"
-	else if ($NF ~ /DFS-FCC/)
-		printf "\t.dfs_region = NL80211_DFS_FCC,\n"
-	else if ($NF ~ /DFS-JP/)
-		printf "\t.dfs_region = NL80211_DFS_JP,\n"
-	printf "\t.reg_rules = {\n"
-	active = 1
-	regdb = regdb "\t&regdom_" country ",\n"
-}
-
-function parse_reg_rule()
-{
-	flag_starts_at = 7
-
-	start = $1
-	sub(/\(/, "", start)
-	end = $3
-	bw = $5
-	sub(/\),/, "", bw)
-	gain = 0
-	power = $6
-	# power might be in mW...
-	units = $7
-	dfs_cac = 0
-
-	sub(/\(/, "", power)
-	sub(/\),/, "", power)
-	sub(/\),/, "", units)
-	sub(/\)/, "", units)
-
-	if (units == "mW") {
-		flag_starts_at = 8
-		power = 10 * log(power)/log(10)
-		if ($8 ~ /[[:digit:]]/) {
-			flag_starts_at = 9
-			dfs_cac = $8
-		}
-	} else {
-		if ($7 ~ /[[:digit:]]/) {
-			flag_starts_at = 8
-			dfs_cac = $7
-		}
-	}
-	sub(/\(/, "", dfs_cac)
-	sub(/\),/, "", dfs_cac)
-	flagstr = ""
-	for (i=flag_starts_at; i<=NF; i++)
-		flagstr = flagstr $i
-	split(flagstr, flagarray, ",")
-	flags = ""
-	for (arg in flagarray) {
-		if (flagarray[arg] == "NO-OFDM") {
-			flags = flags "\n\t\t\tNL80211_RRF_NO_OFDM | "
-		} else if (flagarray[arg] == "NO-CCK") {
-			flags = flags "\n\t\t\tNL80211_RRF_NO_CCK | "
-		} else if (flagarray[arg] == "NO-INDOOR") {
-			flags = flags "\n\t\t\tNL80211_RRF_NO_INDOOR | "
-		} else if (flagarray[arg] == "NO-OUTDOOR") {
-			flags = flags "\n\t\t\tNL80211_RRF_NO_OUTDOOR | "
-		} else if (flagarray[arg] == "DFS") {
-			flags = flags "\n\t\t\tNL80211_RRF_DFS | "
-		} else if (flagarray[arg] == "PTP-ONLY") {
-			flags = flags "\n\t\t\tNL80211_RRF_PTP_ONLY | "
-		} else if (flagarray[arg] == "PTMP-ONLY") {
-			flags = flags "\n\t\t\tNL80211_RRF_PTMP_ONLY | "
-		} else if (flagarray[arg] == "PASSIVE-SCAN") {
-			flags = flags "\n\t\t\tNL80211_RRF_NO_IR | "
-		} else if (flagarray[arg] == "NO-IBSS") {
-			flags = flags "\n\t\t\tNL80211_RRF_NO_IR | "
-		} else if (flagarray[arg] == "NO-IR") {
-			flags = flags "\n\t\t\tNL80211_RRF_NO_IR | "
-		} else if (flagarray[arg] == "AUTO-BW") {
-			flags = flags "\n\t\t\tNL80211_RRF_AUTO_BW | "
-		}
-
-	}
-	flags = flags "0"
-	printf "\t\tREG_RULE_EXT(%d, %d, %d, %d, %.0f, %d, %s),\n", start, end, bw, gain, power, dfs_cac, flags
-	rules++
-}
-
-function print_tail_country()
-{
-	active = 0
-	printf "\t},\n"
-	printf "\t.n_reg_rules = %d\n", rules
-	printf "};\n\n"
-	rules = 0;
-}
-
-/^[ \t]*#/ {
-	# Ignore
-}
-
-!active && /^[ \t]*$/ {
-	# Ignore
-}
-
-!active && /country/ {
-	parse_country_head()
-}
-
-active && /^[ \t]*\(/ {
-	parse_reg_rule()
-}
-
-active && /^[ \t]*$/ {
-	print_tail_country()
-}
-
-END {
-	if (active)
-		print_tail_country()
-	print regdb "};"
-	print ""
-	print "int reg_regdb_size = ARRAY_SIZE(reg_regdb);"
-}
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d396cb61a280..fce2cbe6a193 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2130,6 +2130,15 @@ static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
 		case NL80211_CHAN_HT40MINUS:
 			cfg80211_chandef_create(chandef, chandef->chan,
 						chantype);
+			/* user input for center_freq is incorrect */
+			if (info->attrs[NL80211_ATTR_CENTER_FREQ1] &&
+			    chandef->center_freq1 != nla_get_u32(
+					info->attrs[NL80211_ATTR_CENTER_FREQ1]))
+				return -EINVAL;
+			/* center_freq2 must be zero */
+			if (info->attrs[NL80211_ATTR_CENTER_FREQ2] &&
+			    nla_get_u32(info->attrs[NL80211_ATTR_CENTER_FREQ2]))
+				return -EINVAL;
 			break;
 		default:
 			return -EINVAL;
@@ -5677,6 +5686,11 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info)
 	}
 }
 
+static int nl80211_reload_regdb(struct sk_buff *skb, struct genl_info *info)
+{
+	return reg_reload_regdb();
+}
+
 static int nl80211_get_mesh_config(struct sk_buff *skb,
 				   struct genl_info *info)
 {
@@ -6618,6 +6632,77 @@ static bool cfg80211_off_channel_oper_allowed(struct wireless_dev *wdev)
 	return regulatory_pre_cac_allowed(wdev->wiphy);
 }
 
+static int
+nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev,
+			 void *request, struct nlattr **attrs,
+			 bool is_sched_scan)
+{
+	u8 *mac_addr, *mac_addr_mask;
+	u32 *flags;
+	enum nl80211_feature_flags randomness_flag;
+
+	if (!attrs[NL80211_ATTR_SCAN_FLAGS])
+		return 0;
+
+	if (is_sched_scan) {
+		struct cfg80211_sched_scan_request *req = request;
+
+		randomness_flag = wdev ?
+				  NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR :
+				  NL80211_FEATURE_ND_RANDOM_MAC_ADDR;
+		flags = &req->flags;
+		mac_addr = req->mac_addr;
+		mac_addr_mask = req->mac_addr_mask;
+	} else {
+		struct cfg80211_scan_request *req = request;
+
+		randomness_flag = NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR;
+		flags = &req->flags;
+		mac_addr = req->mac_addr;
+		mac_addr_mask = req->mac_addr_mask;
+	}
+
+	*flags = nla_get_u32(attrs[NL80211_ATTR_SCAN_FLAGS]);
+
+	if ((*flags & NL80211_SCAN_FLAG_LOW_PRIORITY) &&
+	    !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN))
+		return -EOPNOTSUPP;
+
+	if (*flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
+		int err;
+
+		if (!(wiphy->features & randomness_flag) ||
+		    (wdev && wdev->current_bss))
+			return -EOPNOTSUPP;
+
+		err = nl80211_parse_random_mac(attrs, mac_addr, mac_addr_mask);
+		if (err)
+			return err;
+	}
+
+	if ((*flags & NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME) &&
+	    !wiphy_ext_feature_isset(wiphy,
+				     NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME))
+		return -EOPNOTSUPP;
+
+	if ((*flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP) &&
+	   !wiphy_ext_feature_isset(wiphy,
+				    NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP))
+		return -EOPNOTSUPP;
+
+	if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) &&
+	    !wiphy_ext_feature_isset(wiphy,
+				     NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION))
+		return -EOPNOTSUPP;
+
+	if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE) &&
+	    !wiphy_ext_feature_isset(wiphy,
+				     NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -6823,34 +6908,10 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 			nla_get_flag(info->attrs[NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY]);
 	}
 
-	if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) {
-		request->flags = nla_get_u32(
-			info->attrs[NL80211_ATTR_SCAN_FLAGS]);
-		if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) &&
-		    !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) {
-			err = -EOPNOTSUPP;
-			goto out_free;
-		}
-
-		if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
-			if (!(wiphy->features &
-					NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR)) {
-				err = -EOPNOTSUPP;
-				goto out_free;
-			}
-
-			if (wdev->current_bss) {
-				err = -EOPNOTSUPP;
-				goto out_free;
-			}
-
-			err = nl80211_parse_random_mac(info->attrs,
-						       request->mac_addr,
-						       request->mac_addr_mask);
-			if (err)
-				goto out_free;
-		}
-	}
+	err = nl80211_check_scan_flags(wiphy, wdev, request, info->attrs,
+				       false);
+	if (err)
+		goto out_free;
 
 	request->no_cck =
 		nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]);
@@ -7298,37 +7359,9 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 		       request->ie_len);
 	}
 
-	if (attrs[NL80211_ATTR_SCAN_FLAGS]) {
-		request->flags = nla_get_u32(
-			attrs[NL80211_ATTR_SCAN_FLAGS]);
-		if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) &&
-		    !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) {
-			err = -EOPNOTSUPP;
-			goto out_free;
-		}
-
-		if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
-			u32 flg = NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR;
-
-			if (!wdev) /* must be net-detect */
-				flg = NL80211_FEATURE_ND_RANDOM_MAC_ADDR;
-
-			if (!(wiphy->features & flg)) {
-				err = -EOPNOTSUPP;
-				goto out_free;
-			}
-
-			if (wdev && wdev->current_bss) {
-				err = -EOPNOTSUPP;
-				goto out_free;
-			}
-
-			err = nl80211_parse_random_mac(attrs, request->mac_addr,
-						       request->mac_addr_mask);
-			if (err)
-				goto out_free;
-		}
-	}
+	err = nl80211_check_scan_flags(wiphy, wdev, request, attrs, true);
+	if (err)
+		goto out_free;
 
 	if (attrs[NL80211_ATTR_SCHED_SCAN_DELAY])
 		request->delay =
@@ -8932,8 +8965,14 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 
 	if (info->attrs[NL80211_ATTR_USE_MFP]) {
 		connect.mfp = nla_get_u32(info->attrs[NL80211_ATTR_USE_MFP]);
+		if (connect.mfp == NL80211_MFP_OPTIONAL &&
+		    !wiphy_ext_feature_isset(&rdev->wiphy,
+					     NL80211_EXT_FEATURE_MFP_OPTIONAL))
+			return -EOPNOTSUPP;
+
 		if (connect.mfp != NL80211_MFP_REQUIRED &&
-		    connect.mfp != NL80211_MFP_NO)
+		    connect.mfp != NL80211_MFP_NO &&
+		    connect.mfp != NL80211_MFP_OPTIONAL)
 			return -EINVAL;
 	} else {
 		connect.mfp = NL80211_MFP_NO;
@@ -12685,6 +12724,12 @@ static const struct genl_ops nl80211_ops[] = {
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
+		.cmd = NL80211_CMD_RELOAD_REGDB,
+		.doit = nl80211_reload_regdb,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
 		.cmd = NL80211_CMD_GET_MESH_CONFIG,
 		.doit = nl80211_get_mesh_config,
 		.policy = nl80211_policy,
@@ -13812,9 +13857,7 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
 		     info->req_ie)) ||
 	    (info->resp_ie &&
 	     nla_put(msg, NL80211_ATTR_RESP_IE, info->resp_ie_len,
-		     info->resp_ie)) ||
-	    (info->authorized &&
-	     nla_put_flag(msg, NL80211_ATTR_PORT_AUTHORIZED)))
+		     info->resp_ie)))
 		goto nla_put_failure;
 
 	genlmsg_end(msg, hdr);
@@ -13828,6 +13871,36 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
 	nlmsg_free(msg);
 }
 
+void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev,
+				  struct net_device *netdev, const u8 *bssid)
+{
+	struct sk_buff *msg;
+	void *hdr;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_PORT_AUTHORIZED);
+	if (!hdr) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	if (nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
+				NL80211_MCGRP_MLME, GFP_KERNEL);
+	return;
+
+ nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	nlmsg_free(msg);
+}
+
 void nl80211_send_disconnected(struct cfg80211_registered_device *rdev,
 			       struct net_device *netdev, u16 reason,
 			       const u8 *ie, size_t ie_len, bool from_ap)
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index fc415c8f7aac..79e47fe60c35 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -59,6 +59,8 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev,
 void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
 			 struct net_device *netdev,
 			 struct cfg80211_roam_info *info, gfp_t gfp);
+void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev,
+				  struct net_device *netdev, const u8 *bssid);
 void nl80211_send_disconnected(struct cfg80211_registered_device *rdev,
 			       struct net_device *netdev, u16 reason,
 			       const u8 *ie, size_t ie_len, bool from_ap);
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 6e94f6934a0e..3871998059de 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -53,12 +53,13 @@
 #include <linux/ctype.h>
 #include <linux/nl80211.h>
 #include <linux/platform_device.h>
+#include <linux/verification.h>
 #include <linux/moduleparam.h>
+#include <linux/firmware.h>
 #include <net/cfg80211.h>
 #include "core.h"
 #include "reg.h"
 #include "rdev-ops.h"
-#include "regdb.h"
 #include "nl80211.h"
 
 /*
@@ -100,7 +101,7 @@ static struct regulatory_request core_request_world = {
 static struct regulatory_request __rcu *last_request =
 	(void __force __rcu *)&core_request_world;
 
-/* To trigger userspace events */
+/* To trigger userspace events and load firmware */
 static struct platform_device *reg_pdev;
 
 /*
@@ -443,7 +444,6 @@ reg_copy_regd(const struct ieee80211_regdomain *src_regd)
 	return regd;
 }
 
-#ifdef CONFIG_CFG80211_INTERNAL_REGDB
 struct reg_regdb_apply_request {
 	struct list_head list;
 	const struct ieee80211_regdomain *regdom;
@@ -475,55 +475,26 @@ static void reg_regdb_apply(struct work_struct *work)
 
 static DECLARE_WORK(reg_regdb_work, reg_regdb_apply);
 
-static int reg_query_builtin(const char *alpha2)
+static int reg_schedule_apply(const struct ieee80211_regdomain *regdom)
 {
-	const struct ieee80211_regdomain *regdom = NULL;
 	struct reg_regdb_apply_request *request;
-	unsigned int i;
-
-	for (i = 0; i < reg_regdb_size; i++) {
-		if (alpha2_equal(alpha2, reg_regdb[i]->alpha2)) {
-			regdom = reg_regdb[i];
-			break;
-		}
-	}
-
-	if (!regdom)
-		return -ENODATA;
 
 	request = kzalloc(sizeof(struct reg_regdb_apply_request), GFP_KERNEL);
-	if (!request)
-		return -ENOMEM;
-
-	request->regdom = reg_copy_regd(regdom);
-	if (IS_ERR_OR_NULL(request->regdom)) {
-		kfree(request);
+	if (!request) {
+		kfree(regdom);
 		return -ENOMEM;
 	}
 
+	request->regdom = regdom;
+
 	mutex_lock(&reg_regdb_apply_mutex);
 	list_add_tail(&request->list, &reg_regdb_apply_list);
 	mutex_unlock(&reg_regdb_apply_mutex);
 
 	schedule_work(&reg_regdb_work);
-
 	return 0;
 }
 
-/* Feel free to add any other sanity checks here */
-static void reg_regdb_size_check(void)
-{
-	/* We should ideally BUILD_BUG_ON() but then random builds would fail */
-	WARN_ONCE(!reg_regdb_size, "db.txt is empty, you should update it...");
-}
-#else
-static inline void reg_regdb_size_check(void) {}
-static inline int reg_query_builtin(const char *alpha2)
-{
-	return -ENODATA;
-}
-#endif /* CONFIG_CFG80211_INTERNAL_REGDB */
-
 #ifdef CONFIG_CFG80211_CRDA_SUPPORT
 /* Max number of consecutive attempts to communicate with CRDA  */
 #define REG_MAX_CRDA_TIMEOUTS 10
@@ -599,10 +570,402 @@ static inline int call_crda(const char *alpha2)
 }
 #endif /* CONFIG_CFG80211_CRDA_SUPPORT */
 
+/* code to directly load a firmware database through request_firmware */
+static const struct fwdb_header *regdb;
+
+struct fwdb_country {
+	u8 alpha2[2];
+	__be16 coll_ptr;
+	/* this struct cannot be extended */
+} __packed __aligned(4);
+
+struct fwdb_collection {
+	u8 len;
+	u8 n_rules;
+	u8 dfs_region;
+	/* no optional data yet */
+	/* aligned to 2, then followed by __be16 array of rule pointers */
+} __packed __aligned(4);
+
+enum fwdb_flags {
+	FWDB_FLAG_NO_OFDM	= BIT(0),
+	FWDB_FLAG_NO_OUTDOOR	= BIT(1),
+	FWDB_FLAG_DFS		= BIT(2),
+	FWDB_FLAG_NO_IR		= BIT(3),
+	FWDB_FLAG_AUTO_BW	= BIT(4),
+};
+
+struct fwdb_rule {
+	u8 len;
+	u8 flags;
+	__be16 max_eirp;
+	__be32 start, end, max_bw;
+	/* start of optional data */
+	__be16 cac_timeout;
+} __packed __aligned(4);
+
+#define FWDB_MAGIC 0x52474442
+#define FWDB_VERSION 20
+
+struct fwdb_header {
+	__be32 magic;
+	__be32 version;
+	struct fwdb_country country[];
+} __packed __aligned(4);
+
+static bool valid_rule(const u8 *data, unsigned int size, u16 rule_ptr)
+{
+	struct fwdb_rule *rule = (void *)(data + (rule_ptr << 2));
+
+	if ((u8 *)rule + sizeof(rule->len) > data + size)
+		return false;
+
+	/* mandatory fields */
+	if (rule->len < offsetofend(struct fwdb_rule, max_bw))
+		return false;
+
+	return true;
+}
+
+static bool valid_country(const u8 *data, unsigned int size,
+			  const struct fwdb_country *country)
+{
+	unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2;
+	struct fwdb_collection *coll = (void *)(data + ptr);
+	__be16 *rules_ptr;
+	unsigned int i;
+
+	/* make sure we can read len/n_rules */
+	if ((u8 *)coll + offsetofend(typeof(*coll), n_rules) > data + size)
+		return false;
+
+	/* make sure base struct and all rules fit */
+	if ((u8 *)coll + ALIGN(coll->len, 2) +
+	    (coll->n_rules * 2) > data + size)
+		return false;
+
+	/* mandatory fields must exist */
+	if (coll->len < offsetofend(struct fwdb_collection, dfs_region))
+		return false;
+
+	rules_ptr = (void *)((u8 *)coll + ALIGN(coll->len, 2));
+
+	for (i = 0; i < coll->n_rules; i++) {
+		u16 rule_ptr = be16_to_cpu(rules_ptr[i]);
+
+		if (!valid_rule(data, size, rule_ptr))
+			return false;
+	}
+
+	return true;
+}
+
+#ifdef CONFIG_CFG80211_REQUIRE_SIGNED_REGDB
+static struct key *builtin_regdb_keys;
+
+static void __init load_keys_from_buffer(const u8 *p, unsigned int buflen)
+{
+	const u8 *end = p + buflen;
+	size_t plen;
+	key_ref_t key;
+
+	while (p < end) {
+		/* Each cert begins with an ASN.1 SEQUENCE tag and must be more
+		 * than 256 bytes in size.
+		 */
+		if (end - p < 4)
+			goto dodgy_cert;
+		if (p[0] != 0x30 &&
+		    p[1] != 0x82)
+			goto dodgy_cert;
+		plen = (p[2] << 8) | p[3];
+		plen += 4;
+		if (plen > end - p)
+			goto dodgy_cert;
+
+		key = key_create_or_update(make_key_ref(builtin_regdb_keys, 1),
+					   "asymmetric", NULL, p, plen,
+					   ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+					    KEY_USR_VIEW | KEY_USR_READ),
+					   KEY_ALLOC_NOT_IN_QUOTA |
+					   KEY_ALLOC_BUILT_IN |
+					   KEY_ALLOC_BYPASS_RESTRICTION);
+		if (IS_ERR(key)) {
+			pr_err("Problem loading in-kernel X.509 certificate (%ld)\n",
+			       PTR_ERR(key));
+		} else {
+			pr_notice("Loaded X.509 cert '%s'\n",
+				  key_ref_to_ptr(key)->description);
+			key_ref_put(key);
+		}
+		p += plen;
+	}
+
+	return;
+
+dodgy_cert:
+	pr_err("Problem parsing in-kernel X.509 certificate list\n");
+}
+
+static int __init load_builtin_regdb_keys(void)
+{
+	builtin_regdb_keys =
+		keyring_alloc(".builtin_regdb_keys",
+			      KUIDT_INIT(0), KGIDT_INIT(0), current_cred(),
+			      ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+			      KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH),
+			      KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL);
+	if (IS_ERR(builtin_regdb_keys))
+		return PTR_ERR(builtin_regdb_keys);
+
+	pr_notice("Loading compiled-in X.509 certificates for regulatory database\n");
+
+#ifdef CONFIG_CFG80211_USE_KERNEL_REGDB_KEYS
+	load_keys_from_buffer(shipped_regdb_certs, shipped_regdb_certs_len);
+#endif
+#ifdef CONFIG_CFG80211_EXTRA_REGDB_KEYDIR
+	if (CONFIG_CFG80211_EXTRA_REGDB_KEYDIR[0] != '\0')
+		load_keys_from_buffer(extra_regdb_certs, extra_regdb_certs_len);
+#endif
+
+	return 0;
+}
+
+static bool regdb_has_valid_signature(const u8 *data, unsigned int size)
+{
+	const struct firmware *sig;
+	bool result;
+
+	if (request_firmware(&sig, "regulatory.db.p7s", &reg_pdev->dev))
+		return false;
+
+	result = verify_pkcs7_signature(data, size, sig->data, sig->size,
+					builtin_regdb_keys,
+					VERIFYING_UNSPECIFIED_SIGNATURE,
+					NULL, NULL) == 0;
+
+	release_firmware(sig);
+
+	return result;
+}
+
+static void free_regdb_keyring(void)
+{
+	key_put(builtin_regdb_keys);
+}
+#else
+static int load_builtin_regdb_keys(void)
+{
+	return 0;
+}
+
+static bool regdb_has_valid_signature(const u8 *data, unsigned int size)
+{
+	return true;
+}
+
+static void free_regdb_keyring(void)
+{
+}
+#endif /* CONFIG_CFG80211_REQUIRE_SIGNED_REGDB */
+
+static bool valid_regdb(const u8 *data, unsigned int size)
+{
+	const struct fwdb_header *hdr = (void *)data;
+	const struct fwdb_country *country;
+
+	if (size < sizeof(*hdr))
+		return false;
+
+	if (hdr->magic != cpu_to_be32(FWDB_MAGIC))
+		return false;
+
+	if (hdr->version != cpu_to_be32(FWDB_VERSION))
+		return false;
+
+	if (!regdb_has_valid_signature(data, size))
+		return false;
+
+	country = &hdr->country[0];
+	while ((u8 *)(country + 1) <= data + size) {
+		if (!country->coll_ptr)
+			break;
+		if (!valid_country(data, size, country))
+			return false;
+		country++;
+	}
+
+	return true;
+}
+
+static int regdb_query_country(const struct fwdb_header *db,
+			       const struct fwdb_country *country)
+{
+	unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2;
+	struct fwdb_collection *coll = (void *)((u8 *)db + ptr);
+	struct ieee80211_regdomain *regdom;
+	unsigned int size_of_regd;
+	unsigned int i;
+
+	size_of_regd =
+		sizeof(struct ieee80211_regdomain) +
+		coll->n_rules * sizeof(struct ieee80211_reg_rule);
+
+	regdom = kzalloc(size_of_regd, GFP_KERNEL);
+	if (!regdom)
+		return -ENOMEM;
+
+	regdom->n_reg_rules = coll->n_rules;
+	regdom->alpha2[0] = country->alpha2[0];
+	regdom->alpha2[1] = country->alpha2[1];
+	regdom->dfs_region = coll->dfs_region;
+
+	for (i = 0; i < regdom->n_reg_rules; i++) {
+		__be16 *rules_ptr = (void *)((u8 *)coll + ALIGN(coll->len, 2));
+		unsigned int rule_ptr = be16_to_cpu(rules_ptr[i]) << 2;
+		struct fwdb_rule *rule = (void *)((u8 *)db + rule_ptr);
+		struct ieee80211_reg_rule *rrule = &regdom->reg_rules[i];
+
+		rrule->freq_range.start_freq_khz = be32_to_cpu(rule->start);
+		rrule->freq_range.end_freq_khz = be32_to_cpu(rule->end);
+		rrule->freq_range.max_bandwidth_khz = be32_to_cpu(rule->max_bw);
+
+		rrule->power_rule.max_antenna_gain = 0;
+		rrule->power_rule.max_eirp = be16_to_cpu(rule->max_eirp);
+
+		rrule->flags = 0;
+		if (rule->flags & FWDB_FLAG_NO_OFDM)
+			rrule->flags |= NL80211_RRF_NO_OFDM;
+		if (rule->flags & FWDB_FLAG_NO_OUTDOOR)
+			rrule->flags |= NL80211_RRF_NO_OUTDOOR;
+		if (rule->flags & FWDB_FLAG_DFS)
+			rrule->flags |= NL80211_RRF_DFS;
+		if (rule->flags & FWDB_FLAG_NO_IR)
+			rrule->flags |= NL80211_RRF_NO_IR;
+		if (rule->flags & FWDB_FLAG_AUTO_BW)
+			rrule->flags |= NL80211_RRF_AUTO_BW;
+
+		rrule->dfs_cac_ms = 0;
+
+		/* handle optional data */
+		if (rule->len >= offsetofend(struct fwdb_rule, cac_timeout))
+			rrule->dfs_cac_ms =
+				1000 * be16_to_cpu(rule->cac_timeout);
+	}
+
+	return reg_schedule_apply(regdom);
+}
+
+static int query_regdb(const char *alpha2)
+{
+	const struct fwdb_header *hdr = regdb;
+	const struct fwdb_country *country;
+
+	ASSERT_RTNL();
+
+	if (IS_ERR(regdb))
+		return PTR_ERR(regdb);
+
+	country = &hdr->country[0];
+	while (country->coll_ptr) {
+		if (alpha2_equal(alpha2, country->alpha2))
+			return regdb_query_country(regdb, country);
+		country++;
+	}
+
+	return -ENODATA;
+}
+
+static void regdb_fw_cb(const struct firmware *fw, void *context)
+{
+	int set_error = 0;
+	bool restore = true;
+	void *db;
+
+	if (!fw) {
+		pr_info("failed to load regulatory.db\n");
+		set_error = -ENODATA;
+	} else if (!valid_regdb(fw->data, fw->size)) {
+		pr_info("loaded regulatory.db is malformed or signature is missing/invalid\n");
+		set_error = -EINVAL;
+	}
+
+	rtnl_lock();
+	if (WARN_ON(regdb && !IS_ERR(regdb))) {
+		/* just restore and free new db */
+	} else if (set_error) {
+		regdb = ERR_PTR(set_error);
+	} else if (fw) {
+		db = kmemdup(fw->data, fw->size, GFP_KERNEL);
+		if (db) {
+			regdb = db;
+			restore = context && query_regdb(context);
+		} else {
+			restore = true;
+		}
+	}
+
+	if (restore)
+		restore_regulatory_settings(true);
+
+	rtnl_unlock();
+
+	kfree(context);
+
+	release_firmware(fw);
+}
+
+static int query_regdb_file(const char *alpha2)
+{
+	ASSERT_RTNL();
+
+	if (regdb)
+		return query_regdb(alpha2);
+
+	alpha2 = kmemdup(alpha2, 2, GFP_KERNEL);
+	if (!alpha2)
+		return -ENOMEM;
+
+	return request_firmware_nowait(THIS_MODULE, true, "regulatory.db",
+				       &reg_pdev->dev, GFP_KERNEL,
+				       (void *)alpha2, regdb_fw_cb);
+}
+
+int reg_reload_regdb(void)
+{
+	const struct firmware *fw;
+	void *db;
+	int err;
+
+	err = request_firmware(&fw, "regulatory.db", &reg_pdev->dev);
+	if (err)
+		return err;
+
+	if (!valid_regdb(fw->data, fw->size)) {
+		err = -ENODATA;
+		goto out;
+	}
+
+	db = kmemdup(fw->data, fw->size, GFP_KERNEL);
+	if (!db) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	rtnl_lock();
+	if (!IS_ERR_OR_NULL(regdb))
+		kfree(regdb);
+	regdb = db;
+	rtnl_unlock();
+
+ out:
+	release_firmware(fw);
+	return err;
+}
+
 static bool reg_query_database(struct regulatory_request *request)
 {
-	/* query internal regulatory database (if it exists) */
-	if (reg_query_builtin(request->alpha2) == 0)
+	if (query_regdb_file(request->alpha2) == 0)
 		return true;
 
 	if (call_crda(request->alpha2) == 0)
@@ -3285,6 +3648,10 @@ int __init regulatory_init(void)
 {
 	int err = 0;
 
+	err = load_builtin_regdb_keys();
+	if (err)
+		return err;
+
 	reg_pdev = platform_device_register_simple("regulatory", 0, NULL, 0);
 	if (IS_ERR(reg_pdev))
 		return PTR_ERR(reg_pdev);
@@ -3293,8 +3660,6 @@ int __init regulatory_init(void)
 	spin_lock_init(&reg_pending_beacons_lock);
 	spin_lock_init(&reg_indoor_lock);
 
-	reg_regdb_size_check();
-
 	rcu_assign_pointer(cfg80211_regdomain, cfg80211_world_regdom);
 
 	user_alpha2[0] = '9';
@@ -3360,4 +3725,9 @@ void regulatory_exit(void)
 		list_del(&reg_request->list);
 		kfree(reg_request);
 	}
+
+	if (!IS_ERR_OR_NULL(regdb))
+		kfree(regdb);
+
+	free_regdb_keyring();
 }
diff --git a/net/wireless/reg.h b/net/wireless/reg.h
index ca7fedf2e7a1..9ceeb5f3a7cb 100644
--- a/net/wireless/reg.h
+++ b/net/wireless/reg.h
@@ -1,5 +1,8 @@
 #ifndef __NET_WIRELESS_REG_H
 #define __NET_WIRELESS_REG_H
+
+#include <net/cfg80211.h>
+
 /*
  * Copyright 2008-2011	Luis R. Rodriguez <mcgrof@qca.qualcomm.com>
  *
@@ -179,4 +182,15 @@ void regulatory_propagate_dfs_state(struct wiphy *wiphy,
  * @wiphy2 - wiphy it's dfs_region to be checked against that of wiphy1
  */
 bool reg_dfs_domain_same(struct wiphy *wiphy1, struct wiphy *wiphy2);
+
+/**
+ * reg_reload_regdb - reload the regulatory.db firmware file
+ */
+int reg_reload_regdb(void);
+
+extern const u8 shipped_regdb_certs[];
+extern unsigned int shipped_regdb_certs_len;
+extern const u8 extra_regdb_certs[];
+extern unsigned int extra_regdb_certs_len;
+
 #endif  /* __NET_WIRELESS_REG_H */
diff --git a/net/wireless/regdb.h b/net/wireless/regdb.h
deleted file mode 100644
index 3279cfcefb0c..000000000000
--- a/net/wireless/regdb.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef __REGDB_H__
-#define __REGDB_H__
-
-/*
- * Copyright 2009 John W. Linville <linville@tuxdriver.com>
- *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
- */
-
-extern const struct ieee80211_regdomain *reg_regdb[];
-extern int reg_regdb_size;
-
-#endif /* __REGDB_H__ */
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 3dd05a08c60a..fdb3646274a5 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -956,7 +956,6 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info,
 	ev->rm.resp_ie_len = info->resp_ie_len;
 	memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len);
 	ev->rm.bss = info->bss;
-	ev->rm.authorized = info->authorized;
 
 	spin_lock_irqsave(&wdev->event_lock, flags);
 	list_add_tail(&ev->list, &wdev->event_list);
@@ -965,6 +964,50 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info,
 }
 EXPORT_SYMBOL(cfg80211_roamed);
 
+void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid)
+{
+	ASSERT_WDEV_LOCK(wdev);
+
+	if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION))
+		return;
+
+	if (WARN_ON(!wdev->current_bss) ||
+	    WARN_ON(!ether_addr_equal(wdev->current_bss->pub.bssid, bssid)))
+		return;
+
+	nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev,
+				     bssid);
+}
+
+void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid,
+			      gfp_t gfp)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+	struct cfg80211_event *ev;
+	unsigned long flags;
+
+	if (WARN_ON(!bssid))
+		return;
+
+	ev = kzalloc(sizeof(*ev), gfp);
+	if (!ev)
+		return;
+
+	ev->type = EVENT_PORT_AUTHORIZED;
+	memcpy(ev->pa.bssid, bssid, ETH_ALEN);
+
+	/*
+	 * Use the wdev event list so that if there are pending
+	 * connected/roamed events, they will be reported first.
+	 */
+	spin_lock_irqsave(&wdev->event_lock, flags);
+	list_add_tail(&ev->list, &wdev->event_list);
+	spin_unlock_irqrestore(&wdev->event_lock, flags);
+	queue_work(cfg80211_wq, &rdev->event_work);
+}
+EXPORT_SYMBOL(cfg80211_port_authorized);
+
 void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 			     size_t ie_len, u16 reason, bool from_ap)
 {
diff --git a/net/wireless/util.c b/net/wireless/util.c
index c1238d582fd1..c69160694b6c 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -158,32 +158,30 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband)
 	case NL80211_BAND_2GHZ:
 		want = 7;
 		for (i = 0; i < sband->n_bitrates; i++) {
-			if (sband->bitrates[i].bitrate == 10) {
+			switch (sband->bitrates[i].bitrate) {
+			case 10:
+			case 20:
+			case 55:
+			case 110:
 				sband->bitrates[i].flags |=
 					IEEE80211_RATE_MANDATORY_B |
 					IEEE80211_RATE_MANDATORY_G;
 				want--;
-			}
-
-			if (sband->bitrates[i].bitrate == 20 ||
-			    sband->bitrates[i].bitrate == 55 ||
-			    sband->bitrates[i].bitrate == 110 ||
-			    sband->bitrates[i].bitrate == 60 ||
-			    sband->bitrates[i].bitrate == 120 ||
-			    sband->bitrates[i].bitrate == 240) {
+				break;
+			case 60:
+			case 120:
+			case 240:
 				sband->bitrates[i].flags |=
 					IEEE80211_RATE_MANDATORY_G;
 				want--;
-			}
-
-			if (sband->bitrates[i].bitrate != 10 &&
-			    sband->bitrates[i].bitrate != 20 &&
-			    sband->bitrates[i].bitrate != 55 &&
-			    sband->bitrates[i].bitrate != 110)
+				/* fall through */
+			default:
 				sband->bitrates[i].flags |=
 					IEEE80211_RATE_ERP_G;
+				break;
+			}
 		}
-		WARN_ON(want != 0 && want != 3 && want != 6);
+		WARN_ON(want != 0 && want != 3);
 		break;
 	case NL80211_BAND_60GHZ:
 		/* check for mandatory HT MCS 1..4 */
@@ -530,121 +528,6 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
 }
 EXPORT_SYMBOL(ieee80211_data_to_8023_exthdr);
 
-int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
-			     enum nl80211_iftype iftype,
-			     const u8 *bssid, bool qos)
-{
-	struct ieee80211_hdr hdr;
-	u16 hdrlen, ethertype;
-	__le16 fc;
-	const u8 *encaps_data;
-	int encaps_len, skip_header_bytes;
-	int nh_pos, h_pos;
-	int head_need;
-
-	if (unlikely(skb->len < ETH_HLEN))
-		return -EINVAL;
-
-	nh_pos = skb_network_header(skb) - skb->data;
-	h_pos = skb_transport_header(skb) - skb->data;
-
-	/* convert Ethernet header to proper 802.11 header (based on
-	 * operation mode) */
-	ethertype = (skb->data[12] << 8) | skb->data[13];
-	fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA);
-
-	switch (iftype) {
-	case NL80211_IFTYPE_AP:
-	case NL80211_IFTYPE_AP_VLAN:
-	case NL80211_IFTYPE_P2P_GO:
-		fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS);
-		/* DA BSSID SA */
-		memcpy(hdr.addr1, skb->data, ETH_ALEN);
-		memcpy(hdr.addr2, addr, ETH_ALEN);
-		memcpy(hdr.addr3, skb->data + ETH_ALEN, ETH_ALEN);
-		hdrlen = 24;
-		break;
-	case NL80211_IFTYPE_STATION:
-	case NL80211_IFTYPE_P2P_CLIENT:
-		fc |= cpu_to_le16(IEEE80211_FCTL_TODS);
-		/* BSSID SA DA */
-		memcpy(hdr.addr1, bssid, ETH_ALEN);
-		memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN);
-		memcpy(hdr.addr3, skb->data, ETH_ALEN);
-		hdrlen = 24;
-		break;
-	case NL80211_IFTYPE_OCB:
-	case NL80211_IFTYPE_ADHOC:
-		/* DA SA BSSID */
-		memcpy(hdr.addr1, skb->data, ETH_ALEN);
-		memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN);
-		memcpy(hdr.addr3, bssid, ETH_ALEN);
-		hdrlen = 24;
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	if (qos) {
-		fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA);
-		hdrlen += 2;
-	}
-
-	hdr.frame_control = fc;
-	hdr.duration_id = 0;
-	hdr.seq_ctrl = 0;
-
-	skip_header_bytes = ETH_HLEN;
-	if (ethertype == ETH_P_AARP || ethertype == ETH_P_IPX) {
-		encaps_data = bridge_tunnel_header;
-		encaps_len = sizeof(bridge_tunnel_header);
-		skip_header_bytes -= 2;
-	} else if (ethertype >= ETH_P_802_3_MIN) {
-		encaps_data = rfc1042_header;
-		encaps_len = sizeof(rfc1042_header);
-		skip_header_bytes -= 2;
-	} else {
-		encaps_data = NULL;
-		encaps_len = 0;
-	}
-
-	skb_pull(skb, skip_header_bytes);
-	nh_pos -= skip_header_bytes;
-	h_pos -= skip_header_bytes;
-
-	head_need = hdrlen + encaps_len - skb_headroom(skb);
-
-	if (head_need > 0 || skb_cloned(skb)) {
-		head_need = max(head_need, 0);
-		if (head_need)
-			skb_orphan(skb);
-
-		if (pskb_expand_head(skb, head_need, 0, GFP_ATOMIC))
-			return -ENOMEM;
-	}
-
-	if (encaps_data) {
-		memcpy(skb_push(skb, encaps_len), encaps_data, encaps_len);
-		nh_pos += encaps_len;
-		h_pos += encaps_len;
-	}
-
-	memcpy(skb_push(skb, hdrlen), &hdr, hdrlen);
-
-	nh_pos += hdrlen;
-	h_pos += hdrlen;
-
-	/* Update skb pointers to various headers since this modified frame
-	 * is going to go through Linux networking code that may potentially
-	 * need things like pointer to IP header. */
-	skb_reset_mac_header(skb);
-	skb_set_network_header(skb, nh_pos);
-	skb_set_transport_header(skb, h_pos);
-
-	return 0;
-}
-EXPORT_SYMBOL(ieee80211_data_from_8023);
-
 static void
 __frame_add_frag(struct sk_buff *skb, struct page *page,
 		 void *ptr, int len, int size)
@@ -964,6 +847,9 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev)
 		case EVENT_STOPPED:
 			__cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev);
 			break;
+		case EVENT_PORT_AUTHORIZED:
+			__cfg80211_port_authorized(wdev, ev->pa.bssid);
+			break;
 		}
 		wdev_unlock(wdev);
 
@@ -1368,13 +1254,29 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len,
 }
 EXPORT_SYMBOL(cfg80211_get_p2p_attr);
 
-static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id)
+static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id, bool id_ext)
 {
 	int i;
 
-	for (i = 0; i < n_ids; i++)
-		if (ids[i] == id)
+	/* Make sure array values are legal */
+	if (WARN_ON(ids[n_ids - 1] == WLAN_EID_EXTENSION))
+		return false;
+
+	i = 0;
+	while (i < n_ids) {
+		if (ids[i] == WLAN_EID_EXTENSION) {
+			if (id_ext && (ids[i + 1] == id))
+				return true;
+
+			i += 2;
+			continue;
+		}
+
+		if (ids[i] == id && !id_ext)
 			return true;
+
+		i++;
+	}
 	return false;
 }
 
@@ -1404,14 +1306,36 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen,
 {
 	size_t pos = offset;
 
-	while (pos < ielen && ieee80211_id_in_list(ids, n_ids, ies[pos])) {
+	while (pos < ielen) {
+		u8 ext = 0;
+
+		if (ies[pos] == WLAN_EID_EXTENSION)
+			ext = 2;
+		if ((pos + ext) >= ielen)
+			break;
+
+		if (!ieee80211_id_in_list(ids, n_ids, ies[pos + ext],
+					  ies[pos] == WLAN_EID_EXTENSION))
+			break;
+
 		if (ies[pos] == WLAN_EID_RIC_DATA && n_after_ric) {
 			pos = skip_ie(ies, ielen, pos);
 
-			while (pos < ielen &&
-			       !ieee80211_id_in_list(after_ric, n_after_ric,
-						     ies[pos]))
-				pos = skip_ie(ies, ielen, pos);
+			while (pos < ielen) {
+				if (ies[pos] == WLAN_EID_EXTENSION)
+					ext = 2;
+				else
+					ext = 0;
+
+				if ((pos + ext) >= ielen)
+					break;
+
+				if (!ieee80211_id_in_list(after_ric,
+							  n_after_ric,
+							  ies[pos + ext],
+							  ext == 2))
+					pos = skip_ie(ies, ielen, pos);
+			}
 		} else {
 			pos = skip_ie(ies, ielen, pos);
 		}
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index ac095936552d..ea87143314f3 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -374,9 +374,11 @@ static void __x25_destroy_socket(struct sock *);
 /*
  *	handler for deferred kills.
  */
-static void x25_destroy_timer(unsigned long data)
+static void x25_destroy_timer(struct timer_list *t)
 {
-	x25_destroy_socket_from_timer((struct sock *)data);
+	struct sock *sk = from_timer(sk, t, sk_timer);
+
+	x25_destroy_socket_from_timer(sk);
 }
 
 /*
@@ -413,8 +415,7 @@ static void __x25_destroy_socket(struct sock *sk)
 	if (sk_has_allocations(sk)) {
 		/* Defer: outstanding buffers */
 		sk->sk_timer.expires  = jiffies + 10 * HZ;
-		sk->sk_timer.function = x25_destroy_timer;
-		sk->sk_timer.data = (unsigned long)sk;
+		sk->sk_timer.function = (TIMER_FUNC_TYPE)x25_destroy_timer;
 		add_timer(&sk->sk_timer);
 	} else {
 		/* drop last reference so sock_put will free */
diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c
index 997ff7b2509b..ad1734d36ed7 100644
--- a/net/x25/x25_facilities.c
+++ b/net/x25/x25_facilities.c
@@ -103,7 +103,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities,
 					*vc_fac_mask |= X25_MASK_REVERSE;
 					break;
 				}
-
+				/*fall through */
 			case X25_FAC_THROUGHPUT:
 				facilities->throughput = p[1];
 				*vc_fac_mask |= X25_MASK_THROUGHPUT;
diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c
index 7ac50098a375..3c12cae32001 100644
--- a/net/x25/x25_in.c
+++ b/net/x25/x25_in.c
@@ -345,6 +345,7 @@ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametyp
 
 		case X25_RESET_REQUEST:
 			x25_write_internal(sk, X25_RESET_CONFIRMATION);
+			/* fall through */
 		case X25_RESET_CONFIRMATION: {
 			x25_stop_timer(sk);
 			x25->condition = 0x00;
diff --git a/net/x25/x25_timer.c b/net/x25/x25_timer.c
index 5c5db1a36399..1dfba3c23459 100644
--- a/net/x25/x25_timer.c
+++ b/net/x25/x25_timer.c
@@ -26,18 +26,17 @@
 #include <net/tcp_states.h>
 #include <net/x25.h>
 
-static void x25_heartbeat_expiry(unsigned long);
-static void x25_timer_expiry(unsigned long);
+static void x25_heartbeat_expiry(struct timer_list *t);
+static void x25_timer_expiry(struct timer_list *t);
 
 void x25_init_timers(struct sock *sk)
 {
 	struct x25_sock *x25 = x25_sk(sk);
 
-	setup_timer(&x25->timer, x25_timer_expiry, (unsigned long)sk);
+	timer_setup(&x25->timer, x25_timer_expiry, 0);
 
 	/* initialized by sock_init_data */
-	sk->sk_timer.data     = (unsigned long)sk;
-	sk->sk_timer.function = &x25_heartbeat_expiry;
+	sk->sk_timer.function = (TIMER_FUNC_TYPE)x25_heartbeat_expiry;
 }
 
 void x25_start_heartbeat(struct sock *sk)
@@ -93,9 +92,9 @@ unsigned long x25_display_timer(struct sock *sk)
 	return x25->timer.expires - jiffies;
 }
 
-static void x25_heartbeat_expiry(unsigned long param)
+static void x25_heartbeat_expiry(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)param;
+	struct sock *sk = from_timer(sk, t, sk_timer);
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) /* can currently only occur in state 3 */
@@ -160,9 +159,10 @@ static inline void x25_do_timer_expiry(struct sock * sk)
 	}
 }
 
-static void x25_timer_expiry(unsigned long param)
+static void x25_timer_expiry(struct timer_list *t)
 {
-	struct sock *sk = (struct sock *)param;
+	struct x25_sock *x25 = from_timer(x25, t, timer);
+	struct sock *sk = &x25->sk;
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) { /* can currently only occur in state 3 */
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 8cafb3c0a4ac..f02b1743b239 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -57,7 +57,7 @@ static __read_mostly seqcount_t xfrm_policy_hash_generation;
 static void xfrm_init_pmtu(struct dst_entry *dst);
 static int stale_bundle(struct dst_entry *dst);
 static int xfrm_bundle_ok(struct xfrm_dst *xdst);
-static void xfrm_policy_queue_process(unsigned long arg);
+static void xfrm_policy_queue_process(struct timer_list *t);
 
 static void __xfrm_policy_link(struct xfrm_policy *pol, int dir);
 static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
@@ -179,9 +179,9 @@ static inline unsigned long make_jiffies(long secs)
 		return secs*HZ;
 }
 
-static void xfrm_policy_timer(unsigned long data)
+static void xfrm_policy_timer(struct timer_list *t)
 {
-	struct xfrm_policy *xp = (struct xfrm_policy *)data;
+	struct xfrm_policy *xp = from_timer(xp, t, timer);
 	unsigned long now = get_seconds();
 	long next = LONG_MAX;
 	int warn = 0;
@@ -267,10 +267,9 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp)
 		rwlock_init(&policy->lock);
 		refcount_set(&policy->refcnt, 1);
 		skb_queue_head_init(&policy->polq.hold_queue);
-		setup_timer(&policy->timer, xfrm_policy_timer,
-				(unsigned long)policy);
-		setup_timer(&policy->polq.hold_timer, xfrm_policy_queue_process,
-			    (unsigned long)policy);
+		timer_setup(&policy->timer, xfrm_policy_timer, 0);
+		timer_setup(&policy->polq.hold_timer,
+			    xfrm_policy_queue_process, 0);
 	}
 	return policy;
 }
@@ -1852,12 +1851,12 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 	return xdst;
 }
 
-static void xfrm_policy_queue_process(unsigned long arg)
+static void xfrm_policy_queue_process(struct timer_list *t)
 {
 	struct sk_buff *skb;
 	struct sock *sk;
 	struct dst_entry *dst;
-	struct xfrm_policy *pol = (struct xfrm_policy *)arg;
+	struct xfrm_policy *pol = from_timer(pol, t, polq.hold_timer);
 	struct net *net = xp_net(pol);
 	struct xfrm_policy_queue *pq = &pol->polq;
 	struct flowi fl;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index e44a0fed48dd..983b0233767b 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -42,7 +42,7 @@ static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type)
 		return 0;
 
 	algp = nla_data(rt);
-	if (nla_len(rt) < xfrm_alg_len(algp))
+	if (nla_len(rt) < (int)xfrm_alg_len(algp))
 		return -EINVAL;
 
 	switch (type) {
@@ -68,7 +68,7 @@ static int verify_auth_trunc(struct nlattr **attrs)
 		return 0;
 
 	algp = nla_data(rt);
-	if (nla_len(rt) < xfrm_alg_auth_len(algp))
+	if (nla_len(rt) < (int)xfrm_alg_auth_len(algp))
 		return -EINVAL;
 
 	algp->alg_name[sizeof(algp->alg_name) - 1] = '\0';
@@ -84,7 +84,7 @@ static int verify_aead(struct nlattr **attrs)
 		return 0;
 
 	algp = nla_data(rt);
-	if (nla_len(rt) < aead_len(algp))
+	if (nla_len(rt) < (int)aead_len(algp))
 		return -EINVAL;
 
 	algp->alg_name[sizeof(algp->alg_name) - 1] = '\0';
@@ -130,7 +130,7 @@ static inline int verify_replay(struct xfrm_usersa_info *p,
 		if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8)
 			return -EINVAL;
 
-		if (nla_len(rt) < xfrm_replay_state_esn_len(rs) &&
+		if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) &&
 		    nla_len(rt) != sizeof(*rs))
 			return -EINVAL;
 	}
@@ -404,7 +404,7 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es
 					 struct nlattr *rp)
 {
 	struct xfrm_replay_state_esn *up;
-	int ulen;
+	unsigned int ulen;
 
 	if (!replay_esn || !rp)
 		return 0;
@@ -414,7 +414,7 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es
 
 	/* Check the overall length and the internal bitmap length to avoid
 	 * potential overflow. */
-	if (nla_len(rp) < ulen ||
+	if (nla_len(rp) < (int)ulen ||
 	    xfrm_replay_state_esn_len(replay_esn) != ulen ||
 	    replay_esn->bmp_len != up->bmp_len)
 		return -EINVAL;
@@ -430,14 +430,14 @@ static int xfrm_alloc_replay_state_esn(struct xfrm_replay_state_esn **replay_esn
 				       struct nlattr *rta)
 {
 	struct xfrm_replay_state_esn *p, *pp, *up;
-	int klen, ulen;
+	unsigned int klen, ulen;
 
 	if (!rta)
 		return 0;
 
 	up = nla_data(rta);
 	klen = xfrm_replay_state_esn_len(up);
-	ulen = nla_len(rta) >= klen ? klen : sizeof(*up);
+	ulen = nla_len(rta) >= (int)klen ? klen : sizeof(*up);
 
 	p = kzalloc(klen, GFP_KERNEL);
 	if (!p)
@@ -458,9 +458,9 @@ static int xfrm_alloc_replay_state_esn(struct xfrm_replay_state_esn **replay_esn
 	return 0;
 }
 
-static inline int xfrm_user_sec_ctx_size(struct xfrm_sec_ctx *xfrm_ctx)
+static inline unsigned int xfrm_user_sec_ctx_size(struct xfrm_sec_ctx *xfrm_ctx)
 {
-	int len = 0;
+	unsigned int len = 0;
 
 	if (xfrm_ctx) {
 		len += sizeof(struct xfrm_user_sec_ctx);
@@ -1032,7 +1032,7 @@ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb,
 		return -1;
 }
 
-static inline size_t xfrm_spdinfo_msgsize(void)
+static inline unsigned int xfrm_spdinfo_msgsize(void)
 {
 	return NLMSG_ALIGN(4)
 	       + nla_total_size(sizeof(struct xfrmu_spdinfo))
@@ -1147,18 +1147,19 @@ static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u32 *flags = nlmsg_data(nlh);
 	u32 sportid = NETLINK_CB(skb).portid;
 	u32 seq = nlh->nlmsg_seq;
+	int err;
 
 	r_skb = nlmsg_new(xfrm_spdinfo_msgsize(), GFP_ATOMIC);
 	if (r_skb == NULL)
 		return -ENOMEM;
 
-	if (build_spdinfo(r_skb, net, sportid, seq, *flags) < 0)
-		BUG();
+	err = build_spdinfo(r_skb, net, sportid, seq, *flags);
+	BUG_ON(err < 0);
 
 	return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid);
 }
 
-static inline size_t xfrm_sadinfo_msgsize(void)
+static inline unsigned int xfrm_sadinfo_msgsize(void)
 {
 	return NLMSG_ALIGN(4)
 	       + nla_total_size(sizeof(struct xfrmu_sadhinfo))
@@ -1205,13 +1206,14 @@ static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u32 *flags = nlmsg_data(nlh);
 	u32 sportid = NETLINK_CB(skb).portid;
 	u32 seq = nlh->nlmsg_seq;
+	int err;
 
 	r_skb = nlmsg_new(xfrm_sadinfo_msgsize(), GFP_ATOMIC);
 	if (r_skb == NULL)
 		return -ENOMEM;
 
-	if (build_sadinfo(r_skb, net, sportid, seq, *flags) < 0)
-		BUG();
+	err = build_sadinfo(r_skb, net, sportid, seq, *flags);
+	BUG_ON(err < 0);
 
 	return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid);
 }
@@ -1634,7 +1636,7 @@ static inline int copy_to_user_sec_ctx(struct xfrm_policy *xp, struct sk_buff *s
 		return copy_sec_ctx(xp->security, skb);
 	return 0;
 }
-static inline size_t userpolicy_type_attrsize(void)
+static inline unsigned int userpolicy_type_attrsize(void)
 {
 #ifdef CONFIG_XFRM_SUB_POLICY
 	return nla_total_size(sizeof(struct xfrm_userpolicy_type));
@@ -1853,9 +1855,9 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return 0;
 }
 
-static inline size_t xfrm_aevent_msgsize(struct xfrm_state *x)
+static inline unsigned int xfrm_aevent_msgsize(struct xfrm_state *x)
 {
-	size_t replay_size = x->replay_esn ?
+	unsigned int replay_size = x->replay_esn ?
 			      xfrm_replay_state_esn_len(x->replay_esn) :
 			      sizeof(struct xfrm_replay_state);
 
@@ -1960,8 +1962,9 @@ static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh,
 	c.seq = nlh->nlmsg_seq;
 	c.portid = nlh->nlmsg_pid;
 
-	if (build_aevent(r_skb, x, &c) < 0)
-		BUG();
+	err = build_aevent(r_skb, x, &c);
+	BUG_ON(err < 0);
+
 	err = nlmsg_unicast(net->xfrm.nlsk, r_skb, NETLINK_CB(skb).portid);
 	spin_unlock_bh(&x->lock);
 	xfrm_state_put(x);
@@ -2324,8 +2327,8 @@ static int copy_to_user_kmaddress(const struct xfrm_kmaddress *k, struct sk_buff
 	return nla_put(skb, XFRMA_KMADDRESS, sizeof(uk), &uk);
 }
 
-static inline size_t xfrm_migrate_msgsize(int num_migrate, int with_kma,
-					  int with_encp)
+static inline unsigned int xfrm_migrate_msgsize(int num_migrate, int with_kma,
+						int with_encp)
 {
 	return NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_id))
 	      + (with_kma ? nla_total_size(sizeof(struct xfrm_kmaddress)) : 0)
@@ -2388,6 +2391,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 {
 	struct net *net = &init_net;
 	struct sk_buff *skb;
+	int err;
 
 	skb = nlmsg_new(xfrm_migrate_msgsize(num_migrate, !!k, !!encap),
 			GFP_ATOMIC);
@@ -2395,8 +2399,8 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		return -ENOMEM;
 
 	/* build migrate */
-	if (build_migrate(skb, m, num_migrate, k, sel, encap, dir, type) < 0)
-		BUG();
+	err = build_migrate(skb, m, num_migrate, k, sel, encap, dir, type);
+	BUG_ON(err < 0);
 
 	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE);
 }
@@ -2572,7 +2576,7 @@ static void xfrm_netlink_rcv(struct sk_buff *skb)
 	mutex_unlock(&net->xfrm.xfrm_cfg_mutex);
 }
 
-static inline size_t xfrm_expire_msgsize(void)
+static inline unsigned int xfrm_expire_msgsize(void)
 {
 	return NLMSG_ALIGN(sizeof(struct xfrm_user_expire))
 	       + nla_total_size(sizeof(struct xfrm_mark));
@@ -2623,13 +2627,14 @@ static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event
 {
 	struct net *net = xs_net(x);
 	struct sk_buff *skb;
+	int err;
 
 	skb = nlmsg_new(xfrm_aevent_msgsize(x), GFP_ATOMIC);
 	if (skb == NULL)
 		return -ENOMEM;
 
-	if (build_aevent(skb, x, c) < 0)
-		BUG();
+	err = build_aevent(skb, x, c);
+	BUG_ON(err < 0);
 
 	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_AEVENTS);
 }
@@ -2660,9 +2665,9 @@ static int xfrm_notify_sa_flush(const struct km_event *c)
 	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA);
 }
 
-static inline size_t xfrm_sa_len(struct xfrm_state *x)
+static inline unsigned int xfrm_sa_len(struct xfrm_state *x)
 {
-	size_t l = 0;
+	unsigned int l = 0;
 	if (x->aead)
 		l += nla_total_size(aead_len(x->aead));
 	if (x->aalg) {
@@ -2707,8 +2712,9 @@ static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c)
 	struct xfrm_usersa_id *id;
 	struct nlmsghdr *nlh;
 	struct sk_buff *skb;
-	int len = xfrm_sa_len(x);
-	int headlen, err;
+	unsigned int len = xfrm_sa_len(x);
+	unsigned int headlen;
+	int err;
 
 	headlen = sizeof(*p);
 	if (c->event == XFRM_MSG_DELSA) {
@@ -2782,8 +2788,8 @@ static int xfrm_send_state_notify(struct xfrm_state *x, const struct km_event *c
 
 }
 
-static inline size_t xfrm_acquire_msgsize(struct xfrm_state *x,
-					  struct xfrm_policy *xp)
+static inline unsigned int xfrm_acquire_msgsize(struct xfrm_state *x,
+						struct xfrm_policy *xp)
 {
 	return NLMSG_ALIGN(sizeof(struct xfrm_user_acquire))
 	       + nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr)
@@ -2835,13 +2841,14 @@ static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt,
 {
 	struct net *net = xs_net(x);
 	struct sk_buff *skb;
+	int err;
 
 	skb = nlmsg_new(xfrm_acquire_msgsize(x, xp), GFP_ATOMIC);
 	if (skb == NULL)
 		return -ENOMEM;
 
-	if (build_acquire(skb, x, xt, xp) < 0)
-		BUG();
+	err = build_acquire(skb, x, xt, xp);
+	BUG_ON(err < 0);
 
 	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_ACQUIRE);
 }
@@ -2906,7 +2913,7 @@ static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt,
 	return xp;
 }
 
-static inline size_t xfrm_polexpire_msgsize(struct xfrm_policy *xp)
+static inline unsigned int xfrm_polexpire_msgsize(struct xfrm_policy *xp)
 {
 	return NLMSG_ALIGN(sizeof(struct xfrm_user_polexpire))
 	       + nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr)
@@ -2950,26 +2957,28 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct
 {
 	struct net *net = xp_net(xp);
 	struct sk_buff *skb;
+	int err;
 
 	skb = nlmsg_new(xfrm_polexpire_msgsize(xp), GFP_ATOMIC);
 	if (skb == NULL)
 		return -ENOMEM;
 
-	if (build_polexpire(skb, xp, dir, c) < 0)
-		BUG();
+	err = build_polexpire(skb, xp, dir, c);
+	BUG_ON(err < 0);
 
 	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE);
 }
 
 static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c)
 {
-	int len = nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr);
+	unsigned int len = nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr);
 	struct net *net = xp_net(xp);
 	struct xfrm_userpolicy_info *p;
 	struct xfrm_userpolicy_id *id;
 	struct nlmsghdr *nlh;
 	struct sk_buff *skb;
-	int headlen, err;
+	unsigned int headlen;
+	int err;
 
 	headlen = sizeof(*p);
 	if (c->event == XFRM_MSG_DELPOLICY) {
@@ -3076,7 +3085,7 @@ static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, const struct
 
 }
 
-static inline size_t xfrm_report_msgsize(void)
+static inline unsigned int xfrm_report_msgsize(void)
 {
 	return NLMSG_ALIGN(sizeof(struct xfrm_user_report));
 }
@@ -3110,18 +3119,19 @@ static int xfrm_send_report(struct net *net, u8 proto,
 			    struct xfrm_selector *sel, xfrm_address_t *addr)
 {
 	struct sk_buff *skb;
+	int err;
 
 	skb = nlmsg_new(xfrm_report_msgsize(), GFP_ATOMIC);
 	if (skb == NULL)
 		return -ENOMEM;
 
-	if (build_report(skb, proto, sel, addr) < 0)
-		BUG();
+	err = build_report(skb, proto, sel, addr);
+	BUG_ON(err < 0);
 
 	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_REPORT);
 }
 
-static inline size_t xfrm_mapping_msgsize(void)
+static inline unsigned int xfrm_mapping_msgsize(void)
 {
 	return NLMSG_ALIGN(sizeof(struct xfrm_user_mapping));
 }
@@ -3157,6 +3167,7 @@ static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
 {
 	struct net *net = xs_net(x);
 	struct sk_buff *skb;
+	int err;
 
 	if (x->id.proto != IPPROTO_ESP)
 		return -EINVAL;
@@ -3168,8 +3179,8 @@ static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
 	if (skb == NULL)
 		return -ENOMEM;
 
-	if (build_mapping(skb, x, ipaddr, sport) < 0)
-		BUG();
+	err = build_mapping(skb, x, ipaddr, sport);
+	BUG_ON(err < 0);
 
 	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MAPPING);
 }
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 9b4a66e3363e..6a9321ec348a 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -40,6 +40,7 @@ hostprogs-y += per_socket_stats_example
 hostprogs-y += load_sock_ops
 hostprogs-y += xdp_redirect
 hostprogs-y += xdp_redirect_map
+hostprogs-y += xdp_redirect_cpu
 hostprogs-y += xdp_monitor
 hostprogs-y += syscall_tp
 
@@ -85,6 +86,7 @@ test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o
 per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o
 xdp_redirect-objs := bpf_load.o $(LIBBPF) xdp_redirect_user.o
 xdp_redirect_map-objs := bpf_load.o $(LIBBPF) xdp_redirect_map_user.o
+xdp_redirect_cpu-objs := bpf_load.o $(LIBBPF) xdp_redirect_cpu_user.o
 xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o
 syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
 
@@ -128,8 +130,10 @@ always += tcp_bufs_kern.o
 always += tcp_cong_kern.o
 always += tcp_iw_kern.o
 always += tcp_clamp_kern.o
+always += tcp_basertt_kern.o
 always += xdp_redirect_kern.o
 always += xdp_redirect_map_kern.o
+always += xdp_redirect_cpu_kern.o
 always += xdp_monitor_kern.o
 always += syscall_tp_kern.o
 
@@ -170,6 +174,7 @@ HOSTLOADLIBES_xdp_tx_iptunnel += -lelf
 HOSTLOADLIBES_test_map_in_map += -lelf
 HOSTLOADLIBES_xdp_redirect += -lelf
 HOSTLOADLIBES_xdp_redirect_map += -lelf
+HOSTLOADLIBES_xdp_redirect_cpu += -lelf
 HOSTLOADLIBES_xdp_monitor += -lelf
 HOSTLOADLIBES_syscall_tp += -lelf
 
@@ -178,6 +183,12 @@ HOSTLOADLIBES_syscall_tp += -lelf
 LLC ?= llc
 CLANG ?= clang
 
+# Detect that we're cross compiling and use the cross compiler
+ifdef CROSS_COMPILE
+HOSTCC = $(CROSS_COMPILE)gcc
+CLANG_ARCH_ARGS = -target $(ARCH)
+endif
+
 # Trick to allow make to be run from this directory
 all:
 	$(MAKE) -C ../../ $(CURDIR)/
@@ -225,9 +236,9 @@ $(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h
 $(obj)/%.o: $(src)/%.c
 	$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
 		-I$(srctree)/tools/testing/selftests/bpf/ \
-		-D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
-		-Wno-compare-distinct-pointer-types \
+		-D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \
+		-D__TARGET_ARCH_$(ARCH) -Wno-compare-distinct-pointer-types \
 		-Wno-gnu-variable-sized-type-not-at-end \
 		-Wno-address-of-packed-member -Wno-tautological-compare \
-		-Wno-unknown-warning-option \
+		-Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \
 		-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst
index 79f9a58f1872..5f27e4faca50 100644
--- a/samples/bpf/README.rst
+++ b/samples/bpf/README.rst
@@ -64,3 +64,13 @@ It is also possible to point make to the newly compiled 'llc' or
 'clang' command via redefining LLC or CLANG on the make command line::
 
  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
+
+Cross compiling samples
+-----------------------
+In order to cross-compile, say for arm64 targets, export CROSS_COMPILE and ARCH
+environment variables before calling make. This will direct make to build
+samples for the cross target.
+
+export ARCH=arm64
+export CROSS_COMPILE="aarch64-linux-gnu-"
+make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 2325d7ad76df..522ca9252d6c 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -222,6 +222,7 @@ static int load_maps(struct bpf_map_data *maps, int nr_maps,
 			int inner_map_fd = map_fd[maps[i].def.inner_map_idx];
 
 			map_fd[i] = bpf_create_map_in_map_node(maps[i].def.type,
+							maps[i].name,
 							maps[i].def.key_size,
 							inner_map_fd,
 							maps[i].def.max_entries,
@@ -229,6 +230,7 @@ static int load_maps(struct bpf_map_data *maps, int nr_maps,
 							numa_node);
 		} else {
 			map_fd[i] = bpf_create_map_node(maps[i].def.type,
+							maps[i].name,
 							maps[i].def.key_size,
 							maps[i].def.value_size,
 							maps[i].def.max_entries,
diff --git a/samples/bpf/cgroup_helpers.c b/samples/bpf/cgroup_helpers.c
index 09afaddfc9ba..f3bca3ade0f3 100644
--- a/samples/bpf/cgroup_helpers.c
+++ b/samples/bpf/cgroup_helpers.c
@@ -57,7 +57,7 @@ int setup_cgroup_environment(void)
 		return 1;
 	}
 
-	if (mount("none", CGROUP_MOUNT_PATH, "cgroup2", 0, NULL)) {
+	if (mount("none", CGROUP_MOUNT_PATH, "cgroup2", 0, NULL) && errno != EBUSY) {
 		log_err("mount cgroup2");
 		return 1;
 	}
@@ -164,7 +164,7 @@ int create_and_get_cgroup(char *path)
 
 	format_cgroup_path(cgroup_path, path);
 	if (mkdir(cgroup_path, 0777) && errno != EEXIST) {
-		log_err("mkdiring cgroup");
+		log_err("mkdiring cgroup %s .. %s", path, cgroup_path);
 		return 0;
 	}
 
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index 098c857f1eda..2b2ffb97018b 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -266,7 +266,7 @@ int stress_hash_map_lookup(struct pt_regs *ctx)
 	return 0;
 }
 
-SEC("kprobe/sys_getpgrp")
+SEC("kprobe/sys_getppid")
 int stress_array_map_lookup(struct pt_regs *ctx)
 {
 	u32 key = 1, i;
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index f388254896f6..519d9af4b04a 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -137,6 +137,7 @@ static void do_test_lru(enum test_type test, int cpu)
 
 			inner_lru_map_fds[cpu] =
 				bpf_create_map_node(BPF_MAP_TYPE_LRU_HASH,
+						    test_map_names[INNER_LRU_HASH_PREALLOC],
 						    sizeof(uint32_t),
 						    sizeof(long),
 						    inner_lru_hash_size, 0,
@@ -282,7 +283,7 @@ static void test_array_lookup(int cpu)
 
 	start_time = time_get_ns();
 	for (i = 0; i < max_cnt; i++)
-		syscall(__NR_getpgrp, 0);
+		syscall(__NR_getppid, 0);
 	printf("%d:array_lookup %lld lookups per sec\n",
 	       cpu, max_cnt * 1000000000ll * 64 / (time_get_ns() - start_time));
 }
diff --git a/samples/bpf/syscall_tp_user.c b/samples/bpf/syscall_tp_user.c
index a3cb91ebf4e7..9169d3207f18 100644
--- a/samples/bpf/syscall_tp_user.c
+++ b/samples/bpf/syscall_tp_user.c
@@ -23,6 +23,13 @@
  * This requires kernel CONFIG_FTRACE_SYSCALLS to be set.
  */
 
+static void usage(const char *cmd)
+{
+	printf("USAGE: %s [-i num_progs] [-h]\n", cmd);
+	printf("       -i num_progs      # number of progs of the test\n");
+	printf("       -h                # help\n");
+}
+
 static void verify_map(int map_id)
 {
 	__u32 key = 0;
@@ -32,22 +39,29 @@ static void verify_map(int map_id)
 		fprintf(stderr, "map_lookup failed: %s\n", strerror(errno));
 		return;
 	}
-	if (val == 0)
+	if (val == 0) {
 		fprintf(stderr, "failed: map #%d returns value 0\n", map_id);
+		return;
+	}
+	val = 0;
+	if (bpf_map_update_elem(map_id, &key, &val, BPF_ANY) != 0) {
+		fprintf(stderr, "map_update failed: %s\n", strerror(errno));
+		return;
+	}
 }
 
-int main(int argc, char **argv)
+static int test(char *filename, int num_progs)
 {
-	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
-	char filename[256];
-	int fd;
+	int i, fd, map0_fds[num_progs], map1_fds[num_progs];
 
-	setrlimit(RLIMIT_MEMLOCK, &r);
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-
-	if (load_bpf_file(filename)) {
-		fprintf(stderr, "%s", bpf_log_buf);
-		return 1;
+	for (i = 0; i < num_progs; i++) {
+		if (load_bpf_file(filename)) {
+			fprintf(stderr, "%s", bpf_log_buf);
+			return 1;
+		}
+		printf("prog #%d: map ids %d %d\n", i, map_fd[0], map_fd[1]);
+		map0_fds[i] = map_fd[0];
+		map1_fds[i] = map_fd[1];
 	}
 
 	/* current load_bpf_file has perf_event_open default pid = -1
@@ -64,8 +78,34 @@ int main(int argc, char **argv)
 	close(fd);
 
 	/* verify the map */
-	verify_map(map_fd[0]);
-	verify_map(map_fd[1]);
+	for (i = 0; i < num_progs; i++) {
+		verify_map(map0_fds[i]);
+		verify_map(map1_fds[i]);
+	}
 
 	return 0;
 }
+
+int main(int argc, char **argv)
+{
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	int opt, num_progs = 1;
+	char filename[256];
+
+	while ((opt = getopt(argc, argv, "i:h")) != -1) {
+		switch (opt) {
+		case 'i':
+			num_progs = atoi(optarg);
+			break;
+		case 'h':
+		default:
+			usage(argv[0]);
+			return 0;
+		}
+	}
+
+	setrlimit(RLIMIT_MEMLOCK, &r);
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	return test(filename, num_progs);
+}
diff --git a/samples/bpf/tcp_basertt_kern.c b/samples/bpf/tcp_basertt_kern.c
new file mode 100644
index 000000000000..4bf4fc597db9
--- /dev/null
+++ b/samples/bpf/tcp_basertt_kern.c
@@ -0,0 +1,78 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * BPF program to set base_rtt to 80us when host is running TCP-NV and
+ * both hosts are in the same datacenter (as determined by IPv6 prefix).
+ *
+ * Use load_sock_ops to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define DEBUG 1
+
+#define bpf_printk(fmt, ...)					\
+({								\
+	       char ____fmt[] = fmt;				\
+	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				##__VA_ARGS__);			\
+})
+
+SEC("sockops")
+int bpf_basertt(struct bpf_sock_ops *skops)
+{
+	char cong[20];
+	char nv[] = "nv";
+	int rv = 0, n;
+	int op;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Check if both hosts are in the same datacenter. For this
+	 * example they are if the 1st 5.5 bytes in the IPv6 address
+	 * are the same.
+	 */
+	if (skops->family == AF_INET6 &&
+	    skops->local_ip6[0] == skops->remote_ip6[0] &&
+	    (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) ==
+	    (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) {
+		switch (op) {
+		case BPF_SOCK_OPS_BASE_RTT:
+			n = bpf_getsockopt(skops, SOL_TCP, TCP_CONGESTION,
+					   cong, sizeof(cong));
+			if (!n && !__builtin_memcmp(cong, nv, sizeof(nv)+1)) {
+				/* Set base_rtt to 80us */
+				rv = 80;
+			} else if (n) {
+				rv = n;
+			} else {
+				rv = -1;
+			}
+			break;
+		default:
+			rv = -1;
+		}
+	} else {
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/tcp_bbf.readme b/samples/bpf/tcp_bbf.readme
new file mode 100644
index 000000000000..831fb601e3c9
--- /dev/null
+++ b/samples/bpf/tcp_bbf.readme
@@ -0,0 +1,26 @@
+This file describes how to run the tcp_*_kern.o tcp_bpf (or socket_ops)
+programs. These programs attach to a cgroupv2. The following commands create
+a cgroupv2 and attach a bash shell to the group.
+
+  mkdir -p /tmp/cgroupv2
+  mount -t cgroup2 none /tmp/cgroupv2
+  mkdir -p /tmp/cgroupv2/foo
+  bash
+  echo $$ >> /tmp/cgroupv2/foo/cgroup.procs
+
+Anything that runs under this shell belongs to the foo cgroupv2 To load
+(attach) one of the tcp_*_kern.o programs:
+
+  ./load_sock_ops -l /tmp/cgroupv2/foo tcp_basertt_kern.o
+
+If the "-l" flag is used, the load_sock_ops program will continue to run
+printing the BPF log buffer. The tcp_*_kern.o programs use special print
+functions to print logging information (if enabled by the ifdef).
+
+If using netperf/netserver to create traffic, you need to run them under the
+cgroupv2 to which the BPF programs are attached (i.e. under bash shell
+attached to the cgroupv2).
+
+To remove (unattach) a socket_ops BPF program from a cgroupv2:
+
+  ./load_sock_ops -r /tmp/cgroupv2/foo
diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c
index 3049b1f26267..3e8232cc04a8 100644
--- a/samples/bpf/test_cgrp2_attach2.c
+++ b/samples/bpf/test_cgrp2_attach2.c
@@ -30,7 +30,7 @@
 
 #define FOO		"/foo"
 #define BAR		"/foo/bar/"
-#define PING_CMD	"ping -c1 -w1 127.0.0.1"
+#define PING_CMD	"ping -c1 -w1 127.0.0.1 > /dev/null"
 
 char bpf_log_buf[BPF_LOG_BUF_SIZE];
 
@@ -55,8 +55,7 @@ static int prog_load(int verdict)
 	return ret;
 }
 
-
-int main(int argc, char **argv)
+static int test_foo_bar(void)
 {
 	int drop_prog, allow_prog, foo = 0, bar = 0, rc = 0;
 
@@ -189,8 +188,223 @@ out:
 	close(bar);
 	cleanup_cgroup_environment();
 	if (!rc)
-		printf("PASS\n");
+		printf("### override:PASS\n");
 	else
-		printf("FAIL\n");
+		printf("### override:FAIL\n");
 	return rc;
 }
+
+static int map_fd = -1;
+
+static int prog_load_cnt(int verdict, int val)
+{
+	if (map_fd < 0)
+		map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
+	if (map_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
+	struct bpf_insn prog[] = {
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */
+		BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
+		BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+	int ret;
+
+	ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+			       prog, insns_cnt, "GPL", 0,
+			       bpf_log_buf, BPF_LOG_BUF_SIZE);
+
+	if (ret < 0) {
+		log_err("Loading program");
+		printf("Output from verifier:\n%s\n-------\n", bpf_log_buf);
+		return 0;
+	}
+	return ret;
+}
+
+
+static int test_multiprog(void)
+{
+	__u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id;
+	int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0;
+	int drop_prog, allow_prog[6] = {}, rc = 0;
+	unsigned long long value;
+	int i = 0;
+
+	for (i = 0; i < 6; i++) {
+		allow_prog[i] = prog_load_cnt(1, 1 << i);
+		if (!allow_prog[i])
+			goto err;
+	}
+	drop_prog = prog_load_cnt(0, 1);
+	if (!drop_prog)
+		goto err;
+
+	if (setup_cgroup_environment())
+		goto err;
+
+	cg1 = create_and_get_cgroup("/cg1");
+	if (!cg1)
+		goto err;
+	cg2 = create_and_get_cgroup("/cg1/cg2");
+	if (!cg2)
+		goto err;
+	cg3 = create_and_get_cgroup("/cg1/cg2/cg3");
+	if (!cg3)
+		goto err;
+	cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4");
+	if (!cg4)
+		goto err;
+	cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5");
+	if (!cg5)
+		goto err;
+
+	if (join_cgroup("/cg1/cg2/cg3/cg4/cg5"))
+		goto err;
+
+	if (bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, 2)) {
+		log_err("Attaching prog to cg1");
+		goto err;
+	}
+	if (!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, 2)) {
+		log_err("Unexpected success attaching the same prog to cg1");
+		goto err;
+	}
+	if (bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS, 2)) {
+		log_err("Attaching prog2 to cg1");
+		goto err;
+	}
+	if (bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS, 1)) {
+		log_err("Attaching prog to cg2");
+		goto err;
+	}
+	if (bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS, 2)) {
+		log_err("Attaching prog to cg3");
+		goto err;
+	}
+	if (bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS, 1)) {
+		log_err("Attaching prog to cg4");
+		goto err;
+	}
+	if (bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0)) {
+		log_err("Attaching prog to cg5");
+		goto err;
+	}
+	assert(system(PING_CMD) == 0);
+	assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
+	assert(value == 1 + 2 + 8 + 32);
+
+	/* query the number of effective progs in cg5 */
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
+			      NULL, NULL, &prog_cnt) == 0);
+	assert(prog_cnt == 4);
+	/* retrieve prog_ids of effective progs in cg5 */
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
+			      &attach_flags, prog_ids, &prog_cnt) == 0);
+	assert(prog_cnt == 4);
+	assert(attach_flags == 0);
+	saved_prog_id = prog_ids[0];
+	/* check enospc handling */
+	prog_ids[0] = 0;
+	prog_cnt = 2;
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
+			      &attach_flags, prog_ids, &prog_cnt) == -1 &&
+	       errno == ENOSPC);
+	assert(prog_cnt == 4);
+	/* check that prog_ids are returned even when buffer is too small */
+	assert(prog_ids[0] == saved_prog_id);
+	/* retrieve prog_id of single attached prog in cg5 */
+	prog_ids[0] = 0;
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0,
+			      NULL, prog_ids, &prog_cnt) == 0);
+	assert(prog_cnt == 1);
+	assert(prog_ids[0] == saved_prog_id);
+
+	/* detach bottom program and ping again */
+	if (bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Detaching prog from cg5");
+		goto err;
+	}
+	value = 0;
+	assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0);
+	assert(system(PING_CMD) == 0);
+	assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
+	assert(value == 1 + 2 + 8 + 16);
+
+	/* detach 3rd from bottom program and ping again */
+	errno = 0;
+	if (!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Unexpected success on detach from cg3");
+		goto err;
+	}
+	if (bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Detaching from cg3");
+		goto err;
+	}
+	value = 0;
+	assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0);
+	assert(system(PING_CMD) == 0);
+	assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
+	assert(value == 1 + 2 + 16);
+
+	/* detach 2nd from bottom program and ping again */
+	if (bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Detaching prog from cg4");
+		goto err;
+	}
+	value = 0;
+	assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0);
+	assert(system(PING_CMD) == 0);
+	assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
+	assert(value == 1 + 2 + 4);
+
+	prog_cnt = 4;
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
+			      &attach_flags, prog_ids, &prog_cnt) == 0);
+	assert(prog_cnt == 3);
+	assert(attach_flags == 0);
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0,
+			      NULL, prog_ids, &prog_cnt) == 0);
+	assert(prog_cnt == 0);
+	goto out;
+err:
+	rc = 1;
+
+out:
+	for (i = 0; i < 6; i++)
+		if (allow_prog[i] > 0)
+			close(allow_prog[i]);
+	close(cg1);
+	close(cg2);
+	close(cg3);
+	close(cg4);
+	close(cg5);
+	cleanup_cgroup_environment();
+	if (!rc)
+		printf("### multi:PASS\n");
+	else
+		printf("### multi:FAIL\n");
+	return rc;
+}
+
+int main(int argc, char **argv)
+{
+	int rc = 0;
+
+	rc = test_foo_bar();
+	if (rc)
+		return rc;
+
+	return test_multiprog();
+}
diff --git a/samples/bpf/trace_event_kern.c b/samples/bpf/trace_event_kern.c
index 41b6115a32eb..a77a583d94d4 100644
--- a/samples/bpf/trace_event_kern.c
+++ b/samples/bpf/trace_event_kern.c
@@ -37,10 +37,14 @@ struct bpf_map_def SEC("maps") stackmap = {
 SEC("perf_event")
 int bpf_prog1(struct bpf_perf_event_data *ctx)
 {
+	char time_fmt1[] = "Time Enabled: %llu, Time Running: %llu";
+	char time_fmt2[] = "Get Time Failed, ErrCode: %d";
 	char fmt[] = "CPU-%d period %lld ip %llx";
 	u32 cpu = bpf_get_smp_processor_id();
+	struct bpf_perf_event_value value_buf;
 	struct key_t key;
 	u64 *val, one = 1;
+	int ret;
 
 	if (ctx->sample_period < 10000)
 		/* ignore warmup */
@@ -54,6 +58,12 @@ int bpf_prog1(struct bpf_perf_event_data *ctx)
 		return 0;
 	}
 
+	ret = bpf_perf_prog_read_value(ctx, (void *)&value_buf, sizeof(struct bpf_perf_event_value));
+	if (!ret)
+	  bpf_trace_printk(time_fmt1, sizeof(time_fmt1), value_buf.enabled, value_buf.running);
+	else
+	  bpf_trace_printk(time_fmt2, sizeof(time_fmt2), ret);
+
 	val = bpf_map_lookup_elem(&counts, &key);
 	if (val)
 		(*val)++;
diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c
index 7bd827b84a67..bf4f1b6d9a52 100644
--- a/samples/bpf/trace_event_user.c
+++ b/samples/bpf/trace_event_user.c
@@ -127,6 +127,9 @@ static void test_perf_event_all_cpu(struct perf_event_attr *attr)
 	int *pmu_fd = malloc(nr_cpus * sizeof(int));
 	int i, error = 0;
 
+	/* system wide perf event, no need to inherit */
+	attr->inherit = 0;
+
 	/* open perf_event on all cpus */
 	for (i = 0; i < nr_cpus; i++) {
 		pmu_fd[i] = sys_perf_event_open(attr, -1, i, -1, 0);
@@ -154,6 +157,11 @@ static void test_perf_event_task(struct perf_event_attr *attr)
 {
 	int pmu_fd;
 
+	/* per task perf event, enable inherit so the "dd ..." command can be traced properly.
+	 * Enabling inherit will cause bpf_perf_prog_read_time helper failure.
+	 */
+	attr->inherit = 1;
+
 	/* open task bound event */
 	pmu_fd = sys_perf_event_open(attr, 0, -1, -1, 0);
 	if (pmu_fd < 0) {
@@ -175,14 +183,12 @@ static void test_bpf_perf_event(void)
 		.freq = 1,
 		.type = PERF_TYPE_HARDWARE,
 		.config = PERF_COUNT_HW_CPU_CYCLES,
-		.inherit = 1,
 	};
 	struct perf_event_attr attr_type_sw = {
 		.sample_freq = SAMPLE_FREQ,
 		.freq = 1,
 		.type = PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_CPU_CLOCK,
-		.inherit = 1,
 	};
 	struct perf_event_attr attr_hw_cache_l1d = {
 		.sample_freq = SAMPLE_FREQ,
@@ -192,7 +198,6 @@ static void test_bpf_perf_event(void)
 			PERF_COUNT_HW_CACHE_L1D |
 			(PERF_COUNT_HW_CACHE_OP_READ << 8) |
 			(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16),
-		.inherit = 1,
 	};
 	struct perf_event_attr attr_hw_cache_branch_miss = {
 		.sample_freq = SAMPLE_FREQ,
@@ -202,7 +207,6 @@ static void test_bpf_perf_event(void)
 			PERF_COUNT_HW_CACHE_BPU |
 			(PERF_COUNT_HW_CACHE_OP_READ << 8) |
 			(PERF_COUNT_HW_CACHE_RESULT_MISS << 16),
-		.inherit = 1,
 	};
 	struct perf_event_attr attr_type_raw = {
 		.sample_freq = SAMPLE_FREQ,
@@ -210,7 +214,6 @@ static void test_bpf_perf_event(void)
 		.type = PERF_TYPE_RAW,
 		/* Intel Instruction Retired */
 		.config = 0xc0,
-		.inherit = 1,
 	};
 
 	printf("Test HW_CPU_CYCLES\n");
diff --git a/samples/bpf/tracex6_kern.c b/samples/bpf/tracex6_kern.c
index e7d180305974..46c557afac73 100644
--- a/samples/bpf/tracex6_kern.c
+++ b/samples/bpf/tracex6_kern.c
@@ -15,6 +15,12 @@ struct bpf_map_def SEC("maps") values = {
 	.value_size = sizeof(u64),
 	.max_entries = 64,
 };
+struct bpf_map_def SEC("maps") values2 = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(int),
+	.value_size = sizeof(struct bpf_perf_event_value),
+	.max_entries = 64,
+};
 
 SEC("kprobe/htab_map_get_next_key")
 int bpf_prog1(struct pt_regs *ctx)
@@ -37,5 +43,25 @@ int bpf_prog1(struct pt_regs *ctx)
 	return 0;
 }
 
+SEC("kprobe/htab_map_lookup_elem")
+int bpf_prog2(struct pt_regs *ctx)
+{
+	u32 key = bpf_get_smp_processor_id();
+	struct bpf_perf_event_value *val, buf;
+	int error;
+
+	error = bpf_perf_event_read_value(&counters, key, &buf, sizeof(buf));
+	if (error)
+		return 0;
+
+	val = bpf_map_lookup_elem(&values2, &key);
+	if (val)
+		*val = buf;
+	else
+		bpf_map_update_elem(&values2, &key, &buf, BPF_NOEXIST);
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
 u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/tracex6_user.c b/samples/bpf/tracex6_user.c
index a8c22dcf8e4e..89ab8d408474 100644
--- a/samples/bpf/tracex6_user.c
+++ b/samples/bpf/tracex6_user.c
@@ -23,6 +23,7 @@
 
 static void check_on_cpu(int cpu, struct perf_event_attr *attr)
 {
+	struct bpf_perf_event_value value2;
 	int pmu_fd, error = 0;
 	cpu_set_t set;
 	__u64 value;
@@ -47,8 +48,18 @@ static void check_on_cpu(int cpu, struct perf_event_attr *attr)
 		fprintf(stderr, "Value missing for CPU %d\n", cpu);
 		error = 1;
 		goto on_exit;
+	} else {
+		fprintf(stderr, "CPU %d: %llu\n", cpu, value);
+	}
+	/* The above bpf_map_lookup_elem should trigger the second kprobe */
+	if (bpf_map_lookup_elem(map_fd[2], &cpu, &value2)) {
+		fprintf(stderr, "Value2 missing for CPU %d\n", cpu);
+		error = 1;
+		goto on_exit;
+	} else {
+		fprintf(stderr, "CPU %d: counter: %llu, enabled: %llu, running: %llu\n", cpu,
+			value2.counter, value2.enabled, value2.running);
 	}
-	fprintf(stderr, "CPU %d: %llu\n", cpu, value);
 
 on_exit:
 	assert(bpf_map_delete_elem(map_fd[0], &cpu) == 0 || error);
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index 2431c0321b71..fdaefe91801d 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -14,6 +14,7 @@
 #include <string.h>
 #include <unistd.h>
 #include <libgen.h>
+#include <sys/resource.h>
 
 #include "bpf_load.h"
 #include "bpf_util.h"
@@ -69,6 +70,7 @@ static void usage(const char *prog)
 
 int main(int argc, char **argv)
 {
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	const char *optstr = "SN";
 	char filename[256];
 	int opt;
@@ -91,6 +93,12 @@ int main(int argc, char **argv)
 		usage(basename(argv[0]));
 		return 1;
 	}
+
+	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+		perror("setrlimit(RLIMIT_MEMLOCK)");
+		return 1;
+	}
+
 	ifindex = strtoul(argv[optind], NULL, 0);
 
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
diff --git a/samples/bpf/xdp_monitor_kern.c b/samples/bpf/xdp_monitor_kern.c
index 74f3fd8ed729..2fe2f761a0d0 100644
--- a/samples/bpf/xdp_monitor_kern.c
+++ b/samples/bpf/xdp_monitor_kern.c
@@ -13,23 +13,27 @@ struct bpf_map_def SEC("maps") redirect_err_cnt = {
 	/* TODO: have entries for all possible errno's */
 };
 
+#define XDP_UNKNOWN	XDP_REDIRECT + 1
+struct bpf_map_def SEC("maps") exception_cnt = {
+	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(u64),
+	.max_entries	= XDP_UNKNOWN + 1,
+};
+
 /* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format
  * Code in:                kernel/include/trace/events/xdp.h
  */
 struct xdp_redirect_ctx {
-	unsigned short common_type;	//	offset:0;  size:2; signed:0;
-	unsigned char common_flags;	//	offset:2;  size:1; signed:0;
-	unsigned char common_preempt_count;//	offset:3;  size:1; signed:0;
-	int common_pid;			//	offset:4;  size:4; signed:1;
-
-	int prog_id;			//	offset:8;  size:4; signed:1;
-	u32 act;			//	offset:12  size:4; signed:0;
-	int ifindex;			//	offset:16  size:4; signed:1;
-	int err;			//	offset:20  size:4; signed:1;
-	int to_ifindex;			//	offset:24  size:4; signed:1;
-	u32 map_id;			//	offset:28  size:4; signed:0;
-	int map_index;			//	offset:32  size:4; signed:1;
-};					//	offset:36
+	u64 __pad;		// First 8 bytes are not accessible by bpf code
+	int prog_id;		//	offset:8;  size:4; signed:1;
+	u32 act;		//	offset:12  size:4; signed:0;
+	int ifindex;		//	offset:16  size:4; signed:1;
+	int err;		//	offset:20  size:4; signed:1;
+	int to_ifindex;		//	offset:24  size:4; signed:1;
+	u32 map_id;		//	offset:28  size:4; signed:0;
+	int map_index;		//	offset:32  size:4; signed:1;
+};				//	offset:36
 
 enum {
 	XDP_REDIRECT_SUCCESS = 0,
@@ -48,7 +52,7 @@ int xdp_redirect_collect_stat(struct xdp_redirect_ctx *ctx)
 
 	cnt  = bpf_map_lookup_elem(&redirect_err_cnt, &key);
 	if (!cnt)
-		return 0;
+		return 1;
 	*cnt += 1;
 
 	return 0; /* Indicate event was filtered (no further processing)*/
@@ -86,3 +90,31 @@ int trace_xdp_redirect_map(struct xdp_redirect_ctx *ctx)
 {
 	return xdp_redirect_collect_stat(ctx);
 }
+
+/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_exception/format
+ * Code in:                kernel/include/trace/events/xdp.h
+ */
+struct xdp_exception_ctx {
+	u64 __pad;	// First 8 bytes are not accessible by bpf code
+	int prog_id;	//	offset:8;  size:4; signed:1;
+	u32 act;	//	offset:12; size:4; signed:0;
+	int ifindex;	//	offset:16; size:4; signed:1;
+};
+
+SEC("tracepoint/xdp/xdp_exception")
+int trace_xdp_exception(struct xdp_exception_ctx *ctx)
+{
+	u64 *cnt;;
+	u32 key;
+
+	key = ctx->act;
+	if (key > XDP_REDIRECT)
+		key = XDP_UNKNOWN;
+
+	cnt = bpf_map_lookup_elem(&exception_cnt, &key);
+	if (!cnt)
+		return 1;
+	*cnt += 1;
+
+	return 0;
+}
diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c
index b51b4f5e3257..eaba165b3549 100644
--- a/samples/bpf/xdp_monitor_user.c
+++ b/samples/bpf/xdp_monitor_user.c
@@ -20,6 +20,7 @@ static const char *__doc_err_only__=
 #include <unistd.h>
 #include <locale.h>
 
+#include <sys/resource.h>
 #include <getopt.h>
 #include <net/if.h>
 #include <time.h>
@@ -61,7 +62,7 @@ static void usage(char *argv[])
 }
 
 #define NANOSEC_PER_SEC 1000000000 /* 10^9 */
-__u64 gettime(void)
+static __u64 gettime(void)
 {
 	struct timespec t;
 	int res;
@@ -89,6 +90,23 @@ static const char *err2str(int err)
 		return redir_names[err];
 	return NULL;
 }
+/* enum xdp_action */
+#define XDP_UNKNOWN	XDP_REDIRECT + 1
+#define XDP_ACTION_MAX (XDP_UNKNOWN + 1)
+static const char *xdp_action_names[XDP_ACTION_MAX] = {
+	[XDP_ABORTED]	= "XDP_ABORTED",
+	[XDP_DROP]	= "XDP_DROP",
+	[XDP_PASS]	= "XDP_PASS",
+	[XDP_TX]	= "XDP_TX",
+	[XDP_REDIRECT]	= "XDP_REDIRECT",
+	[XDP_UNKNOWN]	= "XDP_UNKNOWN",
+};
+static const char *action2str(int action)
+{
+	if (action < XDP_ACTION_MAX)
+		return xdp_action_names[action];
+	return NULL;
+}
 
 struct record {
 	__u64 counter;
@@ -97,6 +115,7 @@ struct record {
 
 struct stats_record {
 	struct record xdp_redir[REDIR_RES_MAX];
+	struct record xdp_exception[XDP_ACTION_MAX];
 };
 
 static void stats_print_headers(bool err_only)
@@ -104,39 +123,72 @@ static void stats_print_headers(bool err_only)
 	if (err_only)
 		printf("\n%s\n", __doc_err_only__);
 
-	printf("%-14s %-10s %-18s %-9s\n",
-	       "XDP_REDIRECT", "pps ", "pps-human-readable", "measure-period");
+	printf("%-14s %-11s %-10s %-18s %-9s\n",
+	       "ACTION", "result", "pps ", "pps-human-readable", "measure-period");
+}
+
+static double calc_period(struct record *r, struct record *p)
+{
+	double period_ = 0;
+	__u64 period = 0;
+
+	period = r->timestamp - p->timestamp;
+	if (period > 0)
+		period_ = ((double) period / NANOSEC_PER_SEC);
+
+	return period_;
+}
+
+static double calc_pps(struct record *r, struct record *p, double period)
+{
+	__u64 packets = 0;
+	double pps = 0;
+
+	if (period > 0) {
+		packets = r->counter - p->counter;
+		pps = packets / period;
+	}
+	return pps;
 }
 
 static void stats_print(struct stats_record *rec,
 			struct stats_record *prev,
 			bool err_only)
 {
+	double period = 0, pps = 0;
+	struct record *r, *p;
 	int i = 0;
 
+	char *fmt = "%-14s %-11s %-10.0f %'-18.0f %f\n";
+
+	/* tracepoint: xdp:xdp_redirect_* */
 	if (err_only)
 		i = REDIR_ERROR;
 
 	for (; i < REDIR_RES_MAX; i++) {
-		struct record *r = &rec->xdp_redir[i];
-		struct record *p = &prev->xdp_redir[i];
-		__u64 period  = 0;
-		__u64 packets = 0;
-		double pps = 0;
-		double period_ = 0;
+		r = &rec->xdp_redir[i];
+		p = &prev->xdp_redir[i];
 
 		if (p->timestamp) {
-			packets = r->counter - p->counter;
-			period  = r->timestamp - p->timestamp;
-			if (period > 0) {
-				period_ = ((double) period / NANOSEC_PER_SEC);
-				pps = packets / period_;
-			}
+			period = calc_period(r, p);
+			pps = calc_pps(r, p, period);
 		}
+		printf(fmt, "XDP_REDIRECT", err2str(i), pps, pps, period);
+	}
 
-		printf("%-14s %-10.0f %'-18.0f %f\n",
-		       err2str(i), pps, pps, period_);
+	/* tracepoint: xdp:xdp_exception */
+	for (i = 0; i < XDP_ACTION_MAX; i++) {
+		r = &rec->xdp_exception[i];
+		p = &prev->xdp_exception[i];
+		if (p->timestamp) {
+			period = calc_period(r, p);
+			pps = calc_pps(r, p, period);
+		}
+		if (pps > 0)
+			printf(fmt, action2str(i), "Exception",
+			       pps, pps, period);
 	}
+	printf("\n");
 }
 
 static __u64 get_key32_value64_percpu(int fd, __u32 key)
@@ -160,25 +212,33 @@ static __u64 get_key32_value64_percpu(int fd, __u32 key)
 	return sum;
 }
 
-static bool stats_collect(int fd, struct stats_record *rec)
+static bool stats_collect(struct stats_record *rec)
 {
+	int fd;
 	int i;
 
 	/* TODO: Detect if someone unloaded the perf event_fd's, as
 	 * this can happen by someone running perf-record -e
 	 */
 
+	fd = map_data[0].fd; /* map0: redirect_err_cnt */
 	for (i = 0; i < REDIR_RES_MAX; i++) {
 		rec->xdp_redir[i].timestamp = gettime();
 		rec->xdp_redir[i].counter = get_key32_value64_percpu(fd, i);
 	}
+
+	fd = map_data[1].fd; /* map1: exception_cnt */
+	for (i = 0; i < XDP_ACTION_MAX; i++) {
+		rec->xdp_exception[i].timestamp = gettime();
+		rec->xdp_exception[i].counter = get_key32_value64_percpu(fd, i);
+	}
+
 	return true;
 }
 
 static void stats_poll(int interval, bool err_only)
 {
 	struct stats_record rec, prev;
-	int map_fd;
 
 	memset(&rec, 0, sizeof(rec));
 
@@ -190,23 +250,24 @@ static void stats_poll(int interval, bool err_only)
 		printf("\n%s", __doc__);
 
 	/* TODO Need more advanced stats on error types */
-	if (verbose)
-		printf(" - Stats map: %s\n", map_data[0].name);
-	map_fd = map_data[0].fd;
-
-	stats_print_headers(err_only);
+	if (verbose) {
+		printf(" - Stats map0: %s\n", map_data[0].name);
+		printf(" - Stats map1: %s\n", map_data[1].name);
+		printf("\n");
+	}
 	fflush(stdout);
 
 	while (1) {
 		memcpy(&prev, &rec, sizeof(rec));
-		stats_collect(map_fd, &rec);
+		stats_collect(&rec);
+		stats_print_headers(err_only);
 		stats_print(&rec, &prev, err_only);
 		fflush(stdout);
 		sleep(interval);
 	}
 }
 
-void print_bpf_prog_info(void)
+static void print_bpf_prog_info(void)
 {
 	int i;
 
@@ -235,6 +296,7 @@ void print_bpf_prog_info(void)
 
 int main(int argc, char **argv)
 {
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	int longindex = 0, opt;
 	int ret = EXIT_SUCCESS;
 	char bpf_obj_file[256];
@@ -265,13 +327,18 @@ int main(int argc, char **argv)
 		}
 	}
 
+	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+		perror("setrlimit(RLIMIT_MEMLOCK)");
+		return EXIT_FAILURE;
+	}
+
 	if (load_bpf_file(bpf_obj_file)) {
 		printf("ERROR - bpf_log_buf: %s", bpf_log_buf);
-		return 1;
+		return EXIT_FAILURE;
 	}
 	if (!prog_fd[0]) {
 		printf("ERROR - load_bpf_file: %s\n", strerror(errno));
-		return 1;
+		return EXIT_FAILURE;
 	}
 
 	if (debug) {
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
new file mode 100644
index 000000000000..303e9e7161f3
--- /dev/null
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -0,0 +1,609 @@
+/*  XDP redirect to CPUs via cpumap (BPF_MAP_TYPE_CPUMAP)
+ *
+ *  GPLv2, Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
+ */
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/if_vlan.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/ipv6.h>
+#include <uapi/linux/in.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/udp.h>
+
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+#define MAX_CPUS 12 /* WARNING - sync with _user.c */
+
+/* Special map type that can XDP_REDIRECT frames to another CPU */
+struct bpf_map_def SEC("maps") cpu_map = {
+	.type		= BPF_MAP_TYPE_CPUMAP,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(u32),
+	.max_entries	= MAX_CPUS,
+};
+
+/* Common stats data record to keep userspace more simple */
+struct datarec {
+	__u64 processed;
+	__u64 dropped;
+	__u64 issue;
+};
+
+/* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
+ * feedback.  Redirect TX errors can be caught via a tracepoint.
+ */
+struct bpf_map_def SEC("maps") rx_cnt = {
+	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(struct datarec),
+	.max_entries	= 1,
+};
+
+/* Used by trace point */
+struct bpf_map_def SEC("maps") redirect_err_cnt = {
+	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(struct datarec),
+	.max_entries	= 2,
+	/* TODO: have entries for all possible errno's */
+};
+
+/* Used by trace point */
+struct bpf_map_def SEC("maps") cpumap_enqueue_cnt = {
+	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(struct datarec),
+	.max_entries	= MAX_CPUS,
+};
+
+/* Used by trace point */
+struct bpf_map_def SEC("maps") cpumap_kthread_cnt = {
+	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(struct datarec),
+	.max_entries	= 1,
+};
+
+/* Set of maps controlling available CPU, and for iterating through
+ * selectable redirect CPUs.
+ */
+struct bpf_map_def SEC("maps") cpus_available = {
+	.type		= BPF_MAP_TYPE_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(u32),
+	.max_entries	= MAX_CPUS,
+};
+struct bpf_map_def SEC("maps") cpus_count = {
+	.type		= BPF_MAP_TYPE_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(u32),
+	.max_entries	= 1,
+};
+struct bpf_map_def SEC("maps") cpus_iterator = {
+	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(u32),
+	.max_entries	= 1,
+};
+
+/* Used by trace point */
+struct bpf_map_def SEC("maps") exception_cnt = {
+	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(struct datarec),
+	.max_entries	= 1,
+};
+
+/* Helper parse functions */
+
+/* Parse Ethernet layer 2, extract network layer 3 offset and protocol
+ *
+ * Returns false on error and non-supported ether-type
+ */
+struct vlan_hdr {
+	__be16 h_vlan_TCI;
+	__be16 h_vlan_encapsulated_proto;
+};
+
+static __always_inline
+bool parse_eth(struct ethhdr *eth, void *data_end,
+	       u16 *eth_proto, u64 *l3_offset)
+{
+	u16 eth_type;
+	u64 offset;
+
+	offset = sizeof(*eth);
+	if ((void *)eth + offset > data_end)
+		return false;
+
+	eth_type = eth->h_proto;
+
+	/* Skip non 802.3 Ethertypes */
+	if (unlikely(ntohs(eth_type) < ETH_P_802_3_MIN))
+		return false;
+
+	/* Handle VLAN tagged packet */
+	if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) {
+		struct vlan_hdr *vlan_hdr;
+
+		vlan_hdr = (void *)eth + offset;
+		offset += sizeof(*vlan_hdr);
+		if ((void *)eth + offset > data_end)
+			return false;
+		eth_type = vlan_hdr->h_vlan_encapsulated_proto;
+	}
+	/* TODO: Handle double VLAN tagged packet */
+
+	*eth_proto = ntohs(eth_type);
+	*l3_offset = offset;
+	return true;
+}
+
+static __always_inline
+u16 get_dest_port_ipv4_udp(struct xdp_md *ctx, u64 nh_off)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct iphdr *iph = data + nh_off;
+	struct udphdr *udph;
+	u16 dport;
+
+	if (iph + 1 > data_end)
+		return 0;
+	if (!(iph->protocol == IPPROTO_UDP))
+		return 0;
+
+	udph = (void *)(iph + 1);
+	if (udph + 1 > data_end)
+		return 0;
+
+	dport = ntohs(udph->dest);
+	return dport;
+}
+
+static __always_inline
+int get_proto_ipv4(struct xdp_md *ctx, u64 nh_off)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct iphdr *iph = data + nh_off;
+
+	if (iph + 1 > data_end)
+		return 0;
+	return iph->protocol;
+}
+
+static __always_inline
+int get_proto_ipv6(struct xdp_md *ctx, u64 nh_off)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct ipv6hdr *ip6h = data + nh_off;
+
+	if (ip6h + 1 > data_end)
+		return 0;
+	return ip6h->nexthdr;
+}
+
+SEC("xdp_cpu_map0")
+int  xdp_prognum0_no_touch(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct datarec *rec;
+	u32 *cpu_selected;
+	u32 cpu_dest;
+	u32 key = 0;
+
+	/* Only use first entry in cpus_available */
+	cpu_selected = bpf_map_lookup_elem(&cpus_available, &key);
+	if (!cpu_selected)
+		return XDP_ABORTED;
+	cpu_dest = *cpu_selected;
+
+	/* Count RX packet in map */
+	rec = bpf_map_lookup_elem(&rx_cnt, &key);
+	if (!rec)
+		return XDP_ABORTED;
+	rec->processed++;
+
+	if (cpu_dest >= MAX_CPUS) {
+		rec->issue++;
+		return XDP_ABORTED;
+	}
+
+	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+SEC("xdp_cpu_map1_touch_data")
+int  xdp_prognum1_touch_data(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct ethhdr *eth = data;
+	struct datarec *rec;
+	u32 *cpu_selected;
+	u32 cpu_dest;
+	u16 eth_type;
+	u32 key = 0;
+
+	/* Only use first entry in cpus_available */
+	cpu_selected = bpf_map_lookup_elem(&cpus_available, &key);
+	if (!cpu_selected)
+		return XDP_ABORTED;
+	cpu_dest = *cpu_selected;
+
+	/* Validate packet length is minimum Eth header size */
+	if (eth + 1 > data_end)
+		return XDP_ABORTED;
+
+	/* Count RX packet in map */
+	rec = bpf_map_lookup_elem(&rx_cnt, &key);
+	if (!rec)
+		return XDP_ABORTED;
+	rec->processed++;
+
+	/* Read packet data, and use it (drop non 802.3 Ethertypes) */
+	eth_type = eth->h_proto;
+	if (ntohs(eth_type) < ETH_P_802_3_MIN) {
+		rec->dropped++;
+		return XDP_DROP;
+	}
+
+	if (cpu_dest >= MAX_CPUS) {
+		rec->issue++;
+		return XDP_ABORTED;
+	}
+
+	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+SEC("xdp_cpu_map2_round_robin")
+int  xdp_prognum2_round_robin(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct ethhdr *eth = data;
+	struct datarec *rec;
+	u32 cpu_dest;
+	u32 *cpu_lookup;
+	u32 key0 = 0;
+
+	u32 *cpu_selected;
+	u32 *cpu_iterator;
+	u32 *cpu_max;
+	u32 cpu_idx;
+
+	cpu_max = bpf_map_lookup_elem(&cpus_count, &key0);
+	if (!cpu_max)
+		return XDP_ABORTED;
+
+	cpu_iterator = bpf_map_lookup_elem(&cpus_iterator, &key0);
+	if (!cpu_iterator)
+		return XDP_ABORTED;
+	cpu_idx = *cpu_iterator;
+
+	*cpu_iterator += 1;
+	if (*cpu_iterator == *cpu_max)
+		*cpu_iterator = 0;
+
+	cpu_selected = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
+	if (!cpu_selected)
+		return XDP_ABORTED;
+	cpu_dest = *cpu_selected;
+
+	/* Count RX packet in map */
+	rec = bpf_map_lookup_elem(&rx_cnt, &key0);
+	if (!rec)
+		return XDP_ABORTED;
+	rec->processed++;
+
+	if (cpu_dest >= MAX_CPUS) {
+		rec->issue++;
+		return XDP_ABORTED;
+	}
+
+	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+SEC("xdp_cpu_map3_proto_separate")
+int  xdp_prognum3_proto_separate(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct ethhdr *eth = data;
+	u8 ip_proto = IPPROTO_UDP;
+	struct datarec *rec;
+	u16 eth_proto = 0;
+	u64 l3_offset = 0;
+	u32 cpu_dest = 0;
+	u32 cpu_idx = 0;
+	u32 *cpu_lookup;
+	u32 key = 0;
+
+	/* Count RX packet in map */
+	rec = bpf_map_lookup_elem(&rx_cnt, &key);
+	if (!rec)
+		return XDP_ABORTED;
+	rec->processed++;
+
+	if (!(parse_eth(eth, data_end, &eth_proto, &l3_offset)))
+		return XDP_PASS; /* Just skip */
+
+	/* Extract L4 protocol */
+	switch (eth_proto) {
+	case ETH_P_IP:
+		ip_proto = get_proto_ipv4(ctx, l3_offset);
+		break;
+	case ETH_P_IPV6:
+		ip_proto = get_proto_ipv6(ctx, l3_offset);
+		break;
+	case ETH_P_ARP:
+		cpu_idx = 0; /* ARP packet handled on separate CPU */
+		break;
+	default:
+		cpu_idx = 0;
+	}
+
+	/* Choose CPU based on L4 protocol */
+	switch (ip_proto) {
+	case IPPROTO_ICMP:
+	case IPPROTO_ICMPV6:
+		cpu_idx = 2;
+		break;
+	case IPPROTO_TCP:
+		cpu_idx = 0;
+		break;
+	case IPPROTO_UDP:
+		cpu_idx = 1;
+		break;
+	default:
+		cpu_idx = 0;
+	}
+
+	cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
+	if (!cpu_lookup)
+		return XDP_ABORTED;
+	cpu_dest = *cpu_lookup;
+
+	if (cpu_dest >= MAX_CPUS) {
+		rec->issue++;
+		return XDP_ABORTED;
+	}
+
+	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+SEC("xdp_cpu_map4_ddos_filter_pktgen")
+int  xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct ethhdr *eth = data;
+	u8 ip_proto = IPPROTO_UDP;
+	struct datarec *rec;
+	u16 eth_proto = 0;
+	u64 l3_offset = 0;
+	u32 cpu_dest = 0;
+	u32 cpu_idx = 0;
+	u16 dest_port;
+	u32 *cpu_lookup;
+	u32 key = 0;
+
+	/* Count RX packet in map */
+	rec = bpf_map_lookup_elem(&rx_cnt, &key);
+	if (!rec)
+		return XDP_ABORTED;
+	rec->processed++;
+
+	if (!(parse_eth(eth, data_end, &eth_proto, &l3_offset)))
+		return XDP_PASS; /* Just skip */
+
+	/* Extract L4 protocol */
+	switch (eth_proto) {
+	case ETH_P_IP:
+		ip_proto = get_proto_ipv4(ctx, l3_offset);
+		break;
+	case ETH_P_IPV6:
+		ip_proto = get_proto_ipv6(ctx, l3_offset);
+		break;
+	case ETH_P_ARP:
+		cpu_idx = 0; /* ARP packet handled on separate CPU */
+		break;
+	default:
+		cpu_idx = 0;
+	}
+
+	/* Choose CPU based on L4 protocol */
+	switch (ip_proto) {
+	case IPPROTO_ICMP:
+	case IPPROTO_ICMPV6:
+		cpu_idx = 2;
+		break;
+	case IPPROTO_TCP:
+		cpu_idx = 0;
+		break;
+	case IPPROTO_UDP:
+		cpu_idx = 1;
+		/* DDoS filter UDP port 9 (pktgen) */
+		dest_port = get_dest_port_ipv4_udp(ctx, l3_offset);
+		if (dest_port == 9) {
+			if (rec)
+				rec->dropped++;
+			return XDP_DROP;
+		}
+		break;
+	default:
+		cpu_idx = 0;
+	}
+
+	cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
+	if (!cpu_lookup)
+		return XDP_ABORTED;
+	cpu_dest = *cpu_lookup;
+
+	if (cpu_dest >= MAX_CPUS) {
+		rec->issue++;
+		return XDP_ABORTED;
+	}
+
+	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+
+char _license[] SEC("license") = "GPL";
+
+/*** Trace point code ***/
+
+/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format
+ * Code in:                kernel/include/trace/events/xdp.h
+ */
+struct xdp_redirect_ctx {
+	u64 __pad;	// First 8 bytes are not accessible by bpf code
+	int prog_id;	//	offset:8;  size:4; signed:1;
+	u32 act;	//	offset:12  size:4; signed:0;
+	int ifindex;	//	offset:16  size:4; signed:1;
+	int err;	//	offset:20  size:4; signed:1;
+	int to_ifindex;	//	offset:24  size:4; signed:1;
+	u32 map_id;	//	offset:28  size:4; signed:0;
+	int map_index;	//	offset:32  size:4; signed:1;
+};			//	offset:36
+
+enum {
+	XDP_REDIRECT_SUCCESS = 0,
+	XDP_REDIRECT_ERROR = 1
+};
+
+static __always_inline
+int xdp_redirect_collect_stat(struct xdp_redirect_ctx *ctx)
+{
+	u32 key = XDP_REDIRECT_ERROR;
+	struct datarec *rec;
+	int err = ctx->err;
+
+	if (!err)
+		key = XDP_REDIRECT_SUCCESS;
+
+	rec = bpf_map_lookup_elem(&redirect_err_cnt, &key);
+	if (!rec)
+		return 0;
+	rec->dropped += 1;
+
+	return 0; /* Indicate event was filtered (no further processing)*/
+	/*
+	 * Returning 1 here would allow e.g. a perf-record tracepoint
+	 * to see and record these events, but it doesn't work well
+	 * in-practice as stopping perf-record also unload this
+	 * bpf_prog.  Plus, there is additional overhead of doing so.
+	 */
+}
+
+SEC("tracepoint/xdp/xdp_redirect_err")
+int trace_xdp_redirect_err(struct xdp_redirect_ctx *ctx)
+{
+	return xdp_redirect_collect_stat(ctx);
+}
+
+SEC("tracepoint/xdp/xdp_redirect_map_err")
+int trace_xdp_redirect_map_err(struct xdp_redirect_ctx *ctx)
+{
+	return xdp_redirect_collect_stat(ctx);
+}
+
+/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_exception/format
+ * Code in:                kernel/include/trace/events/xdp.h
+ */
+struct xdp_exception_ctx {
+	u64 __pad;	// First 8 bytes are not accessible by bpf code
+	int prog_id;	//	offset:8;  size:4; signed:1;
+	u32 act;	//	offset:12; size:4; signed:0;
+	int ifindex;	//	offset:16; size:4; signed:1;
+};
+
+SEC("tracepoint/xdp/xdp_exception")
+int trace_xdp_exception(struct xdp_exception_ctx *ctx)
+{
+	struct datarec *rec;
+	u32 key = 0;
+
+	rec = bpf_map_lookup_elem(&exception_cnt, &key);
+	if (!rec)
+		return 1;
+	rec->dropped += 1;
+
+	return 0;
+}
+
+/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_enqueue/format
+ * Code in:         kernel/include/trace/events/xdp.h
+ */
+struct cpumap_enqueue_ctx {
+	u64 __pad;		// First 8 bytes are not accessible by bpf code
+	int map_id;		//	offset:8;  size:4; signed:1;
+	u32 act;		//	offset:12; size:4; signed:0;
+	int cpu;		//	offset:16; size:4; signed:1;
+	unsigned int drops;	//	offset:20; size:4; signed:0;
+	unsigned int processed;	//	offset:24; size:4; signed:0;
+	int to_cpu;		//	offset:28; size:4; signed:1;
+};
+
+SEC("tracepoint/xdp/xdp_cpumap_enqueue")
+int trace_xdp_cpumap_enqueue(struct cpumap_enqueue_ctx *ctx)
+{
+	u32 to_cpu = ctx->to_cpu;
+	struct datarec *rec;
+
+	if (to_cpu >= MAX_CPUS)
+		return 1;
+
+	rec = bpf_map_lookup_elem(&cpumap_enqueue_cnt, &to_cpu);
+	if (!rec)
+		return 0;
+	rec->processed += ctx->processed;
+	rec->dropped   += ctx->drops;
+
+	/* Record bulk events, then userspace can calc average bulk size */
+	if (ctx->processed > 0)
+		rec->issue += 1;
+
+	/* Inception: It's possible to detect overload situations, via
+	 * this tracepoint.  This can be used for creating a feedback
+	 * loop to XDP, which can take appropriate actions to mitigate
+	 * this overload situation.
+	 */
+	return 0;
+}
+
+/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_kthread/format
+ * Code in:         kernel/include/trace/events/xdp.h
+ */
+struct cpumap_kthread_ctx {
+	u64 __pad;		// First 8 bytes are not accessible by bpf code
+	int map_id;		//	offset:8;  size:4; signed:1;
+	u32 act;		//	offset:12; size:4; signed:0;
+	int cpu;		//	offset:16; size:4; signed:1;
+	unsigned int drops;	//	offset:20; size:4; signed:0;
+	unsigned int processed;	//	offset:24; size:4; signed:0;
+	int sched;		//	offset:28; size:4; signed:1;
+};
+
+SEC("tracepoint/xdp/xdp_cpumap_kthread")
+int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx)
+{
+	struct datarec *rec;
+	u32 key = 0;
+
+	rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &key);
+	if (!rec)
+		return 0;
+	rec->processed += ctx->processed;
+	rec->dropped   += ctx->drops;
+
+	/* Count times kthread yielded CPU via schedule call */
+	if (ctx->sched)
+		rec->issue++;
+
+	return 0;
+}
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
new file mode 100644
index 000000000000..35fec9fecb57
--- /dev/null
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -0,0 +1,697 @@
+/* GPLv2 Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
+ */
+static const char *__doc__ =
+	" XDP redirect with a CPU-map type \"BPF_MAP_TYPE_CPUMAP\"";
+
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <unistd.h>
+#include <locale.h>
+#include <sys/resource.h>
+#include <getopt.h>
+#include <net/if.h>
+#include <time.h>
+
+#include <arpa/inet.h>
+#include <linux/if_link.h>
+
+#define MAX_CPUS 12 /* WARNING - sync with _kern.c */
+
+/* How many xdp_progs are defined in _kern.c */
+#define MAX_PROG 5
+
+/* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead
+ * use bpf/libbpf.h), but cannot as (currently) needed for XDP
+ * attaching to a device via set_link_xdp_fd()
+ */
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#include "bpf_util.h"
+
+static int ifindex = -1;
+static char ifname_buf[IF_NAMESIZE];
+static char *ifname;
+
+static __u32 xdp_flags;
+
+/* Exit return codes */
+#define EXIT_OK		0
+#define EXIT_FAIL		1
+#define EXIT_FAIL_OPTION	2
+#define EXIT_FAIL_XDP		3
+#define EXIT_FAIL_BPF		4
+#define EXIT_FAIL_MEM		5
+
+static const struct option long_options[] = {
+	{"help",	no_argument,		NULL, 'h' },
+	{"dev",		required_argument,	NULL, 'd' },
+	{"skb-mode",	no_argument,		NULL, 'S' },
+	{"debug",	no_argument,		NULL, 'D' },
+	{"sec",		required_argument,	NULL, 's' },
+	{"prognum",	required_argument,	NULL, 'p' },
+	{"qsize",	required_argument,	NULL, 'q' },
+	{"cpu",		required_argument,	NULL, 'c' },
+	{"stress-mode", no_argument,		NULL, 'x' },
+	{"no-separators", no_argument,		NULL, 'z' },
+	{0, 0, NULL,  0 }
+};
+
+static void int_exit(int sig)
+{
+	fprintf(stderr,
+		"Interrupted: Removing XDP program on ifindex:%d device:%s\n",
+		ifindex, ifname);
+	if (ifindex > -1)
+		set_link_xdp_fd(ifindex, -1, xdp_flags);
+	exit(EXIT_OK);
+}
+
+static void usage(char *argv[])
+{
+	int i;
+
+	printf("\nDOCUMENTATION:\n%s\n", __doc__);
+	printf("\n");
+	printf(" Usage: %s (options-see-below)\n", argv[0]);
+	printf(" Listing options:\n");
+	for (i = 0; long_options[i].name != 0; i++) {
+		printf(" --%-12s", long_options[i].name);
+		if (long_options[i].flag != NULL)
+			printf(" flag (internal value:%d)",
+				*long_options[i].flag);
+		else
+			printf(" short-option: -%c",
+				long_options[i].val);
+		printf("\n");
+	}
+	printf("\n");
+}
+
+/* gettime returns the current time of day in nanoseconds.
+ * Cost: clock_gettime (ns) => 26ns (CLOCK_MONOTONIC)
+ *       clock_gettime (ns) =>  9ns (CLOCK_MONOTONIC_COARSE)
+ */
+#define NANOSEC_PER_SEC 1000000000 /* 10^9 */
+static __u64 gettime(void)
+{
+	struct timespec t;
+	int res;
+
+	res = clock_gettime(CLOCK_MONOTONIC, &t);
+	if (res < 0) {
+		fprintf(stderr, "Error with gettimeofday! (%i)\n", res);
+		exit(EXIT_FAIL);
+	}
+	return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
+}
+
+/* Common stats data record shared with _kern.c */
+struct datarec {
+	__u64 processed;
+	__u64 dropped;
+	__u64 issue;
+};
+struct record {
+	__u64 timestamp;
+	struct datarec total;
+	struct datarec *cpu;
+};
+struct stats_record {
+	struct record rx_cnt;
+	struct record redir_err;
+	struct record kthread;
+	struct record exception;
+	struct record enq[MAX_CPUS];
+};
+
+static bool map_collect_percpu(int fd, __u32 key, struct record *rec)
+{
+	/* For percpu maps, userspace gets a value per possible CPU */
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	struct datarec values[nr_cpus];
+	__u64 sum_processed = 0;
+	__u64 sum_dropped = 0;
+	__u64 sum_issue = 0;
+	int i;
+
+	if ((bpf_map_lookup_elem(fd, &key, values)) != 0) {
+		fprintf(stderr,
+			"ERR: bpf_map_lookup_elem failed key:0x%X\n", key);
+		return false;
+	}
+	/* Get time as close as possible to reading map contents */
+	rec->timestamp = gettime();
+
+	/* Record and sum values from each CPU */
+	for (i = 0; i < nr_cpus; i++) {
+		rec->cpu[i].processed = values[i].processed;
+		sum_processed        += values[i].processed;
+		rec->cpu[i].dropped = values[i].dropped;
+		sum_dropped        += values[i].dropped;
+		rec->cpu[i].issue = values[i].issue;
+		sum_issue        += values[i].issue;
+	}
+	rec->total.processed = sum_processed;
+	rec->total.dropped   = sum_dropped;
+	rec->total.issue     = sum_issue;
+	return true;
+}
+
+static struct datarec *alloc_record_per_cpu(void)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	struct datarec *array;
+	size_t size;
+
+	size = sizeof(struct datarec) * nr_cpus;
+	array = malloc(size);
+	memset(array, 0, size);
+	if (!array) {
+		fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
+		exit(EXIT_FAIL_MEM);
+	}
+	return array;
+}
+
+static struct stats_record *alloc_stats_record(void)
+{
+	struct stats_record *rec;
+	int i;
+
+	rec = malloc(sizeof(*rec));
+	memset(rec, 0, sizeof(*rec));
+	if (!rec) {
+		fprintf(stderr, "Mem alloc error\n");
+		exit(EXIT_FAIL_MEM);
+	}
+	rec->rx_cnt.cpu    = alloc_record_per_cpu();
+	rec->redir_err.cpu = alloc_record_per_cpu();
+	rec->kthread.cpu   = alloc_record_per_cpu();
+	rec->exception.cpu = alloc_record_per_cpu();
+	for (i = 0; i < MAX_CPUS; i++)
+		rec->enq[i].cpu = alloc_record_per_cpu();
+
+	return rec;
+}
+
+static void free_stats_record(struct stats_record *r)
+{
+	int i;
+
+	for (i = 0; i < MAX_CPUS; i++)
+		free(r->enq[i].cpu);
+	free(r->exception.cpu);
+	free(r->kthread.cpu);
+	free(r->redir_err.cpu);
+	free(r->rx_cnt.cpu);
+	free(r);
+}
+
+static double calc_period(struct record *r, struct record *p)
+{
+	double period_ = 0;
+	__u64 period = 0;
+
+	period = r->timestamp - p->timestamp;
+	if (period > 0)
+		period_ = ((double) period / NANOSEC_PER_SEC);
+
+	return period_;
+}
+
+static __u64 calc_pps(struct datarec *r, struct datarec *p, double period_)
+{
+	__u64 packets = 0;
+	__u64 pps = 0;
+
+	if (period_ > 0) {
+		packets = r->processed - p->processed;
+		pps = packets / period_;
+	}
+	return pps;
+}
+
+static __u64 calc_drop_pps(struct datarec *r, struct datarec *p, double period_)
+{
+	__u64 packets = 0;
+	__u64 pps = 0;
+
+	if (period_ > 0) {
+		packets = r->dropped - p->dropped;
+		pps = packets / period_;
+	}
+	return pps;
+}
+
+static __u64 calc_errs_pps(struct datarec *r,
+			    struct datarec *p, double period_)
+{
+	__u64 packets = 0;
+	__u64 pps = 0;
+
+	if (period_ > 0) {
+		packets = r->issue - p->issue;
+		pps = packets / period_;
+	}
+	return pps;
+}
+
+static void stats_print(struct stats_record *stats_rec,
+			struct stats_record *stats_prev,
+			int prog_num)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	double pps = 0, drop = 0, err = 0;
+	struct record *rec, *prev;
+	int to_cpu;
+	double t;
+	int i;
+
+	/* Header */
+	printf("Running XDP/eBPF prog_num:%d\n", prog_num);
+	printf("%-15s %-7s %-14s %-11s %-9s\n",
+	       "XDP-cpumap", "CPU:to", "pps", "drop-pps", "extra-info");
+
+	/* XDP rx_cnt */
+	{
+		char *fmt_rx = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n";
+		char *fm2_rx = "%-15s %-7s %'-14.0f %'-11.0f\n";
+		char *errstr = "";
+
+		rec  = &stats_rec->rx_cnt;
+		prev = &stats_prev->rx_cnt;
+		t = calc_period(rec, prev);
+		for (i = 0; i < nr_cpus; i++) {
+			struct datarec *r = &rec->cpu[i];
+			struct datarec *p = &prev->cpu[i];
+
+			pps = calc_pps(r, p, t);
+			drop = calc_drop_pps(r, p, t);
+			err  = calc_errs_pps(r, p, t);
+			if (err > 0)
+				errstr = "cpu-dest/err";
+			if (pps > 0)
+				printf(fmt_rx, "XDP-RX",
+					i, pps, drop, err, errstr);
+		}
+		pps  = calc_pps(&rec->total, &prev->total, t);
+		drop = calc_drop_pps(&rec->total, &prev->total, t);
+		err  = calc_errs_pps(&rec->total, &prev->total, t);
+		printf(fm2_rx, "XDP-RX", "total", pps, drop);
+	}
+
+	/* cpumap enqueue stats */
+	for (to_cpu = 0; to_cpu < MAX_CPUS; to_cpu++) {
+		char *fmt = "%-15s %3d:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n";
+		char *fm2 = "%-15s %3s:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n";
+		char *errstr = "";
+
+		rec  =  &stats_rec->enq[to_cpu];
+		prev = &stats_prev->enq[to_cpu];
+		t = calc_period(rec, prev);
+		for (i = 0; i < nr_cpus; i++) {
+			struct datarec *r = &rec->cpu[i];
+			struct datarec *p = &prev->cpu[i];
+
+			pps  = calc_pps(r, p, t);
+			drop = calc_drop_pps(r, p, t);
+			err  = calc_errs_pps(r, p, t);
+			if (err > 0) {
+				errstr = "bulk-average";
+				err = pps / err; /* calc average bulk size */
+			}
+			if (pps > 0)
+				printf(fmt, "cpumap-enqueue",
+				       i, to_cpu, pps, drop, err, errstr);
+		}
+		pps = calc_pps(&rec->total, &prev->total, t);
+		if (pps > 0) {
+			drop = calc_drop_pps(&rec->total, &prev->total, t);
+			err  = calc_errs_pps(&rec->total, &prev->total, t);
+			if (err > 0) {
+				errstr = "bulk-average";
+				err = pps / err; /* calc average bulk size */
+			}
+			printf(fm2, "cpumap-enqueue",
+			       "sum", to_cpu, pps, drop, err, errstr);
+		}
+	}
+
+	/* cpumap kthread stats */
+	{
+		char *fmt_k = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n";
+		char *fm2_k = "%-15s %-7s %'-14.0f %'-11.0f %'-10.0f %s\n";
+		char *e_str = "";
+
+		rec  = &stats_rec->kthread;
+		prev = &stats_prev->kthread;
+		t = calc_period(rec, prev);
+		for (i = 0; i < nr_cpus; i++) {
+			struct datarec *r = &rec->cpu[i];
+			struct datarec *p = &prev->cpu[i];
+
+			pps  = calc_pps(r, p, t);
+			drop = calc_drop_pps(r, p, t);
+			err  = calc_errs_pps(r, p, t);
+			if (err > 0)
+				e_str = "sched";
+			if (pps > 0)
+				printf(fmt_k, "cpumap_kthread",
+				       i, pps, drop, err, e_str);
+		}
+		pps = calc_pps(&rec->total, &prev->total, t);
+		drop = calc_drop_pps(&rec->total, &prev->total, t);
+		err  = calc_errs_pps(&rec->total, &prev->total, t);
+		if (err > 0)
+			e_str = "sched-sum";
+		printf(fm2_k, "cpumap_kthread", "total", pps, drop, err, e_str);
+	}
+
+	/* XDP redirect err tracepoints (very unlikely) */
+	{
+		char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n";
+		char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n";
+
+		rec  = &stats_rec->redir_err;
+		prev = &stats_prev->redir_err;
+		t = calc_period(rec, prev);
+		for (i = 0; i < nr_cpus; i++) {
+			struct datarec *r = &rec->cpu[i];
+			struct datarec *p = &prev->cpu[i];
+
+			pps  = calc_pps(r, p, t);
+			drop = calc_drop_pps(r, p, t);
+			if (pps > 0)
+				printf(fmt_err, "redirect_err", i, pps, drop);
+		}
+		pps = calc_pps(&rec->total, &prev->total, t);
+		drop = calc_drop_pps(&rec->total, &prev->total, t);
+		printf(fm2_err, "redirect_err", "total", pps, drop);
+	}
+
+	/* XDP general exception tracepoints */
+	{
+		char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n";
+		char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n";
+
+		rec  = &stats_rec->exception;
+		prev = &stats_prev->exception;
+		t = calc_period(rec, prev);
+		for (i = 0; i < nr_cpus; i++) {
+			struct datarec *r = &rec->cpu[i];
+			struct datarec *p = &prev->cpu[i];
+
+			pps  = calc_pps(r, p, t);
+			drop = calc_drop_pps(r, p, t);
+			if (pps > 0)
+				printf(fmt_err, "xdp_exception", i, pps, drop);
+		}
+		pps = calc_pps(&rec->total, &prev->total, t);
+		drop = calc_drop_pps(&rec->total, &prev->total, t);
+		printf(fm2_err, "xdp_exception", "total", pps, drop);
+	}
+
+	printf("\n");
+	fflush(stdout);
+}
+
+static void stats_collect(struct stats_record *rec)
+{
+	int fd, i;
+
+	fd = map_fd[1]; /* map: rx_cnt */
+	map_collect_percpu(fd, 0, &rec->rx_cnt);
+
+	fd = map_fd[2]; /* map: redirect_err_cnt */
+	map_collect_percpu(fd, 1, &rec->redir_err);
+
+	fd = map_fd[3]; /* map: cpumap_enqueue_cnt */
+	for (i = 0; i < MAX_CPUS; i++)
+		map_collect_percpu(fd, i, &rec->enq[i]);
+
+	fd = map_fd[4]; /* map: cpumap_kthread_cnt */
+	map_collect_percpu(fd, 0, &rec->kthread);
+
+	fd = map_fd[8]; /* map: exception_cnt */
+	map_collect_percpu(fd, 0, &rec->exception);
+}
+
+
+/* Pointer swap trick */
+static inline void swap(struct stats_record **a, struct stats_record **b)
+{
+	struct stats_record *tmp;
+
+	tmp = *a;
+	*a = *b;
+	*b = tmp;
+}
+
+static int create_cpu_entry(__u32 cpu, __u32 queue_size,
+			    __u32 avail_idx, bool new)
+{
+	__u32 curr_cpus_count = 0;
+	__u32 key = 0;
+	int ret;
+
+	/* Add a CPU entry to cpumap, as this allocate a cpu entry in
+	 * the kernel for the cpu.
+	 */
+	ret = bpf_map_update_elem(map_fd[0], &cpu, &queue_size, 0);
+	if (ret) {
+		fprintf(stderr, "Create CPU entry failed (err:%d)\n", ret);
+		exit(EXIT_FAIL_BPF);
+	}
+
+	/* Inform bpf_prog's that a new CPU is available to select
+	 * from via some control maps.
+	 */
+	/* map_fd[5] = cpus_available */
+	ret = bpf_map_update_elem(map_fd[5], &avail_idx, &cpu, 0);
+	if (ret) {
+		fprintf(stderr, "Add to avail CPUs failed\n");
+		exit(EXIT_FAIL_BPF);
+	}
+
+	/* When not replacing/updating existing entry, bump the count */
+	/* map_fd[6] = cpus_count */
+	ret = bpf_map_lookup_elem(map_fd[6], &key, &curr_cpus_count);
+	if (ret) {
+		fprintf(stderr, "Failed reading curr cpus_count\n");
+		exit(EXIT_FAIL_BPF);
+	}
+	if (new) {
+		curr_cpus_count++;
+		ret = bpf_map_update_elem(map_fd[6], &key, &curr_cpus_count, 0);
+		if (ret) {
+			fprintf(stderr, "Failed write curr cpus_count\n");
+			exit(EXIT_FAIL_BPF);
+		}
+	}
+	/* map_fd[7] = cpus_iterator */
+	printf("%s CPU:%u as idx:%u queue_size:%d (total cpus_count:%u)\n",
+	       new ? "Add-new":"Replace", cpu, avail_idx,
+	       queue_size, curr_cpus_count);
+
+	return 0;
+}
+
+/* CPUs are zero-indexed. Thus, add a special sentinel default value
+ * in map cpus_available to mark CPU index'es not configured
+ */
+static void mark_cpus_unavailable(void)
+{
+	__u32 invalid_cpu = MAX_CPUS;
+	int ret, i;
+
+	for (i = 0; i < MAX_CPUS; i++) {
+		/* map_fd[5] = cpus_available */
+		ret = bpf_map_update_elem(map_fd[5], &i, &invalid_cpu, 0);
+		if (ret) {
+			fprintf(stderr, "Failed marking CPU unavailable\n");
+			exit(EXIT_FAIL_BPF);
+		}
+	}
+}
+
+/* Stress cpumap management code by concurrently changing underlying cpumap */
+static void stress_cpumap(void)
+{
+	/* Changing qsize will cause kernel to free and alloc a new
+	 * bpf_cpu_map_entry, with an associated/complicated tear-down
+	 * procedure.
+	 */
+	create_cpu_entry(1,  1024, 0, false);
+	create_cpu_entry(1,   128, 0, false);
+	create_cpu_entry(1, 16000, 0, false);
+}
+
+static void stats_poll(int interval, bool use_separators, int prog_num,
+		       bool stress_mode)
+{
+	struct stats_record *record, *prev;
+
+	record = alloc_stats_record();
+	prev   = alloc_stats_record();
+	stats_collect(record);
+
+	/* Trick to pretty printf with thousands separators use %' */
+	if (use_separators)
+		setlocale(LC_NUMERIC, "en_US");
+
+	while (1) {
+		swap(&prev, &record);
+		stats_collect(record);
+		stats_print(record, prev, prog_num);
+		sleep(interval);
+		if (stress_mode)
+			stress_cpumap();
+	}
+
+	free_stats_record(record);
+	free_stats_record(prev);
+}
+
+int main(int argc, char **argv)
+{
+	struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+	bool use_separators = true;
+	bool stress_mode = false;
+	char filename[256];
+	bool debug = false;
+	int added_cpus = 0;
+	int longindex = 0;
+	int interval = 2;
+	int prog_num = 0;
+	int add_cpu = -1;
+	__u32 qsize;
+	int opt;
+
+	/* Notice: choosing he queue size is very important with the
+	 * ixgbe driver, because it's driver page recycling trick is
+	 * dependend on pages being returned quickly.  The number of
+	 * out-standing packets in the system must be less-than 2x
+	 * RX-ring size.
+	 */
+	qsize = 128+64;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+		perror("setrlimit(RLIMIT_MEMLOCK)");
+		return 1;
+	}
+
+	if (load_bpf_file(filename)) {
+		fprintf(stderr, "ERR in load_bpf_file(): %s", bpf_log_buf);
+		return EXIT_FAIL;
+	}
+
+	if (!prog_fd[0]) {
+		fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno));
+		return EXIT_FAIL;
+	}
+
+	mark_cpus_unavailable();
+
+	/* Parse commands line args */
+	while ((opt = getopt_long(argc, argv, "hSd:",
+				  long_options, &longindex)) != -1) {
+		switch (opt) {
+		case 'd':
+			if (strlen(optarg) >= IF_NAMESIZE) {
+				fprintf(stderr, "ERR: --dev name too long\n");
+				goto error;
+			}
+			ifname = (char *)&ifname_buf;
+			strncpy(ifname, optarg, IF_NAMESIZE);
+			ifindex = if_nametoindex(ifname);
+			if (ifindex == 0) {
+				fprintf(stderr,
+					"ERR: --dev name unknown err(%d):%s\n",
+					errno, strerror(errno));
+				goto error;
+			}
+			break;
+		case 's':
+			interval = atoi(optarg);
+			break;
+		case 'S':
+			xdp_flags |= XDP_FLAGS_SKB_MODE;
+			break;
+		case 'D':
+			debug = true;
+			break;
+		case 'x':
+			stress_mode = true;
+			break;
+		case 'z':
+			use_separators = false;
+			break;
+		case 'p':
+			/* Selecting eBPF prog to load */
+			prog_num = atoi(optarg);
+			if (prog_num < 0 || prog_num >= MAX_PROG) {
+				fprintf(stderr,
+					"--prognum too large err(%d):%s\n",
+					errno, strerror(errno));
+				goto error;
+			}
+			break;
+		case 'c':
+			/* Add multiple CPUs */
+			add_cpu = strtoul(optarg, NULL, 0);
+			if (add_cpu >= MAX_CPUS) {
+				fprintf(stderr,
+				"--cpu nr too large for cpumap err(%d):%s\n",
+					errno, strerror(errno));
+				goto error;
+			}
+			create_cpu_entry(add_cpu, qsize, added_cpus, true);
+			added_cpus++;
+			break;
+		case 'q':
+			qsize = atoi(optarg);
+			break;
+		case 'h':
+		error:
+		default:
+			usage(argv);
+			return EXIT_FAIL_OPTION;
+		}
+	}
+	/* Required option */
+	if (ifindex == -1) {
+		fprintf(stderr, "ERR: required option --dev missing\n");
+		usage(argv);
+		return EXIT_FAIL_OPTION;
+	}
+	/* Required option */
+	if (add_cpu == -1) {
+		fprintf(stderr, "ERR: required option --cpu missing\n");
+		fprintf(stderr, " Specify multiple --cpu option to add more\n");
+		usage(argv);
+		return EXIT_FAIL_OPTION;
+	}
+
+	/* Remove XDP program when program is interrupted */
+	signal(SIGINT, int_exit);
+
+	if (set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) {
+		fprintf(stderr, "link set xdp fd failed\n");
+		return EXIT_FAIL_XDP;
+	}
+
+	if (debug) {
+		printf("Debug-mode reading trace pipe (fix #define DEBUG)\n");
+		read_trace_pipe();
+	}
+
+	stats_poll(interval, use_separators, prog_num, stress_mode);
+	return EXIT_OK;
+}
diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c
index d4d86a273fba..978a532f0748 100644
--- a/samples/bpf/xdp_redirect_map_user.c
+++ b/samples/bpf/xdp_redirect_map_user.c
@@ -20,6 +20,7 @@
 #include <string.h>
 #include <unistd.h>
 #include <libgen.h>
+#include <sys/resource.h>
 
 #include "bpf_load.h"
 #include "bpf_util.h"
@@ -74,6 +75,7 @@ static void usage(const char *prog)
 
 int main(int argc, char **argv)
 {
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	const char *optstr = "SN";
 	char filename[256];
 	int ret, opt, key = 0;
@@ -97,6 +99,11 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
+	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+		perror("setrlimit(RLIMIT_MEMLOCK)");
+		return 1;
+	}
+
 	ifindex_in = strtoul(argv[optind], NULL, 0);
 	ifindex_out = strtoul(argv[optind + 1], NULL, 0);
 	printf("input: %d output: %d\n", ifindex_in, ifindex_out);
diff --git a/samples/pktgen/functions.sh b/samples/pktgen/functions.sh
index 205e4cde4601..f8bb3cd0f4ce 100644
--- a/samples/pktgen/functions.sh
+++ b/samples/pktgen/functions.sh
@@ -119,3 +119,46 @@ function root_check_run_with_sudo() {
 	err 4 "cannot perform sudo run of $0"
     fi
 }
+
+# Exact input device's NUMA node info
+function get_iface_node()
+{
+    local node=$(</sys/class/net/$1/device/numa_node)
+    if [[ $node == -1 ]]; then
+        echo 0
+    else
+        echo $node
+    fi
+}
+
+# Given an Dev/iface, get its queues' irq numbers
+function get_iface_irqs()
+{
+	local IFACE=$1
+	local queues="${IFACE}-.*TxRx"
+
+	irqs=$(grep "$queues" /proc/interrupts | cut -f1 -d:)
+	[ -z "$irqs" ] && irqs=$(grep $IFACE /proc/interrupts | cut -f1 -d:)
+	[ -z "$irqs" ] && irqs=$(for i in `ls -Ux /sys/class/net/$IFACE/device/msi_irqs` ;\
+	    do grep "$i:.*TxRx" /proc/interrupts | grep -v fdir | cut -f 1 -d : ;\
+	    done)
+	[ -z "$irqs" ] && err 3 "Could not find interrupts for $IFACE"
+
+	echo $irqs
+}
+
+# Given a NUMA node, return cpu ids belonging to it.
+function get_node_cpus()
+{
+	local node=$1
+	local node_cpu_list
+	local node_cpu_range_list=`cut -f1- -d, --output-delimiter=" " \
+	                  /sys/devices/system/node/node$node/cpulist`
+
+	for cpu_range in $node_cpu_range_list
+	do
+	    node_cpu_list="$node_cpu_list "`seq -s " " ${cpu_range//-/ }`
+	done
+
+	echo $node_cpu_list
+}
diff --git a/samples/pktgen/pktgen.conf-1-1-ip6 b/samples/pktgen/pktgen.conf-1-1-ip6
deleted file mode 100755
index 62426afeef84..000000000000
--- a/samples/pktgen/pktgen.conf-1-1-ip6
+++ /dev/null
@@ -1,61 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-#modprobe pktgen
-
-
-function pgset() {
-    local result
-
-    echo $1 > $PGDEV
-
-    result=`cat $PGDEV | fgrep "Result: OK:"`
-    if [ "$result" = "" ]; then
-         cat $PGDEV | fgrep Result:
-    fi
-}
-
-# Config Start Here -----------------------------------------------------------
-
-
-# thread config
-# Each CPU has its own thread. One CPU example. We add eth1.
-# IPv6. Note increase in minimal packet length
-
-PGDEV=/proc/net/pktgen/kpktgend_0
-  echo "Removing all devices"
- pgset "rem_device_all"
-  echo "Adding eth1"
- pgset "add_device eth1"
-
-
-# device config
-# delay 0
-
-CLONE_SKB="clone_skb 1000000"
-# NIC adds 4 bytes CRC
-PKT_SIZE="pkt_size 66"
-
-# COUNT 0 means forever
-#COUNT="count 0"
-COUNT="count 10000000"
-DELAY="delay 0"
-
-PGDEV=/proc/net/pktgen/eth1
-  echo "Configuring $PGDEV"
- pgset "$COUNT"
- pgset "$CLONE_SKB"
- pgset "$PKT_SIZE"
- pgset "$DELAY"
- pgset "dst6 fec0::1"
- pgset "src6 fec0::2"
- pgset "dst_mac  00:04:23:08:91:dc"
-
-# Time to run
-PGDEV=/proc/net/pktgen/pgctrl
-
- echo "Running... ctrl^C to stop"
- trap true INT
- pgset "start"
- echo "Done"
- cat /proc/net/pktgen/eth1
diff --git a/samples/pktgen/pktgen.conf-1-1-ip6-rdos b/samples/pktgen/pktgen.conf-1-1-ip6-rdos
deleted file mode 100755
index 3ac3eb1f3504..000000000000
--- a/samples/pktgen/pktgen.conf-1-1-ip6-rdos
+++ /dev/null
@@ -1,64 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-#modprobe pktgen
-
-
-function pgset() {
-    local result
-
-    echo $1 > $PGDEV
-
-    result=`cat $PGDEV | fgrep "Result: OK:"`
-    if [ "$result" = "" ]; then
-         cat $PGDEV | fgrep Result:
-    fi
-}
-
-# Config Start Here -----------------------------------------------------------
-
-
-# thread config
-# Each CPU has its own thread. One CPU example. We add eth1.
-# IPv6. Note increase in minimal packet length
-
-PGDEV=/proc/net/pktgen/kpktgend_0
-  echo "Removing all devices"
- pgset "rem_device_all"
-  echo "Adding eth1"
- pgset "add_device eth1"
-
-
-# device config
-# delay 0 means maximum speed.
-
-# We need to do alloc for every skb since we cannot clone here.
-CLONE_SKB="clone_skb 0"
-
-# NIC adds 4 bytes CRC
-PKT_SIZE="pkt_size 66"
-
-# COUNT 0 means forever
-#COUNT="count 0"
-COUNT="count 10000000"
-DELAY="delay 0"
-
-PGDEV=/proc/net/pktgen/eth1
-  echo "Configuring $PGDEV"
- pgset "$COUNT"
- pgset "$CLONE_SKB"
- pgset "$PKT_SIZE"
- pgset "$DELAY"
- pgset "dst6_min fec0::1"
- pgset "dst6_max fec0::FFFF:FFFF"
-
- pgset "dst_mac  00:04:23:08:91:dc"
-
-# Time to run
-PGDEV=/proc/net/pktgen/pgctrl
-
- echo "Running... ctrl^C to stop"
- trap true INT
- pgset "start"
- echo "Done"
- cat /proc/net/pktgen/eth1
diff --git a/samples/pktgen/pktgen.conf-1-2 b/samples/pktgen/pktgen.conf-1-2
deleted file mode 100755
index a85552760762..000000000000
--- a/samples/pktgen/pktgen.conf-1-2
+++ /dev/null
@@ -1,70 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-#modprobe pktgen
-
-
-function pgset() {
-    local result
-
-    echo $1 > $PGDEV
-
-    result=`cat $PGDEV | fgrep "Result: OK:"`
-    if [ "$result" = "" ]; then
-         cat $PGDEV | fgrep Result:
-    fi
-}
-
-# Config Start Here -----------------------------------------------------------
-
-
-# thread config
-# One CPU means one thread. One CPU example. We add eth1, eth2 respectivly.
-
-PGDEV=/proc/net/pktgen/kpktgend_0
-  echo "Removing all devices"
- pgset "rem_device_all"
-  echo "Adding eth1"
- pgset "add_device eth1"
-  echo "Adding eth2"
- pgset "add_device eth2"
-
-
-# device config
-# delay 0 means maximum speed.
-
-CLONE_SKB="clone_skb 1000000"
-# NIC adds 4 bytes CRC
-PKT_SIZE="pkt_size 60"
-
-# COUNT 0 means forever
-#COUNT="count 0"
-COUNT="count 10000000"
-DELAY="delay 0"
-
-PGDEV=/proc/net/pktgen/eth1
-  echo "Configuring $PGDEV"
- pgset "$COUNT"
- pgset "$CLONE_SKB"
- pgset "$PKT_SIZE"
- pgset "$DELAY"
- pgset "dst 10.10.11.2"
- pgset "dst_mac  00:04:23:08:91:dc"
-
-PGDEV=/proc/net/pktgen/eth2
-  echo "Configuring $PGDEV"
- pgset "$COUNT"
- pgset "$CLONE_SKB"
- pgset "$PKT_SIZE"
- pgset "$DELAY"
- pgset "dst 192.168.2.2"
- pgset "dst_mac  00:04:23:08:91:de"
-
-# Time to run
-PGDEV=/proc/net/pktgen/pgctrl
-
- echo "Running... ctrl^C to stop"
- trap true INT
- pgset "start"
- echo "Done"
- cat /proc/net/pktgen/eth1 /proc/net/pktgen/eth2
diff --git a/samples/pktgen/pktgen_sample03_burst_single_flow.sh b/samples/pktgen/pktgen_sample03_burst_single_flow.sh
index 4c2e4217638a..8fdd36722d9e 100755
--- a/samples/pktgen/pktgen_sample03_burst_single_flow.sh
+++ b/samples/pktgen/pktgen_sample03_burst_single_flow.sh
@@ -31,7 +31,7 @@ if [ -z "$DEST_IP" ]; then
 fi
 [ -z "$DST_MAC" ]   && DST_MAC="90:e2:ba:ff:ff:ff"
 [ -z "$BURST" ]     && BURST=32
-[ -z "$CLONE_SKB" ] && CLONE_SKB="100000"
+[ -z "$CLONE_SKB" ] && CLONE_SKB="0" # No need for clones when bursting
 [ -z "$COUNT" ]     && COUNT="0" # Zero means indefinitely
 
 # Base Config
diff --git a/samples/pktgen/pktgen_sample06_numa_awared_queue_irq_affinity.sh b/samples/pktgen/pktgen_sample06_numa_awared_queue_irq_affinity.sh
new file mode 100755
index 000000000000..353adc17205e
--- /dev/null
+++ b/samples/pktgen/pktgen_sample06_numa_awared_queue_irq_affinity.sh
@@ -0,0 +1,97 @@
+#!/bin/bash
+#
+# Multiqueue: Using pktgen threads for sending on multiple CPUs
+#  * adding devices to kernel threads which are in the same NUMA node
+#  * bound devices queue's irq affinity to the threads, 1:1 mapping
+#  * notice the naming scheme for keeping device names unique
+#  * nameing scheme: dev@thread_number
+#  * flow variation via random UDP source port
+#
+basedir=`dirname $0`
+source ${basedir}/functions.sh
+root_check_run_with_sudo "$@"
+#
+# Required param: -i dev in $DEV
+source ${basedir}/parameters.sh
+
+# Base Config
+DELAY="0"        # Zero means max speed
+[ -z "$COUNT" ]     && COUNT="20000000"   # Zero means indefinitely
+[ -z "$CLONE_SKB" ] && CLONE_SKB="0"
+
+# Flow variation random source port between min and max
+UDP_MIN=9
+UDP_MAX=109
+
+node=`get_iface_node $DEV`
+irq_array=(`get_iface_irqs $DEV`)
+cpu_array=(`get_node_cpus $node`)
+
+[ $THREADS -gt ${#irq_array[*]} -o $THREADS -gt ${#cpu_array[*]}  ] && \
+	err 1 "Thread number $THREADS exceeds: min (${#irq_array[*]},${#cpu_array[*]})"
+
+# (example of setting default params in your script)
+if [ -z "$DEST_IP" ]; then
+    [ -z "$IP6" ] && DEST_IP="198.18.0.42" || DEST_IP="FD00::1"
+fi
+[ -z "$DST_MAC" ] && DST_MAC="90:e2:ba:ff:ff:ff"
+
+# General cleanup everything since last run
+pg_ctrl "reset"
+
+# Threads are specified with parameter -t value in $THREADS
+for ((i = 0; i < $THREADS; i++)); do
+    # The device name is extended with @name, using thread number to
+    # make then unique, but any name will do.
+    # Set the queue's irq affinity to this $thread (processor)
+    # if '-f' is designated, offset cpu id
+    thread=${cpu_array[$((i+F_THREAD))]}
+    dev=${DEV}@${thread}
+    echo $thread > /proc/irq/${irq_array[$i]}/smp_affinity_list
+    info "irq ${irq_array[$i]} is set affinity to `cat /proc/irq/${irq_array[$i]}/smp_affinity_list`"
+
+    # Add remove all other devices and add_device $dev to thread
+    pg_thread $thread "rem_device_all"
+    pg_thread $thread "add_device" $dev
+
+    # select queue and bind the queue and $dev in 1:1 relationship
+    queue_num=$i
+    info "queue number is $queue_num"
+    pg_set $dev "queue_map_min $queue_num"
+    pg_set $dev "queue_map_max $queue_num"
+
+    # Notice config queue to map to cpu (mirrors smp_processor_id())
+    # It is beneficial to map IRQ /proc/irq/*/smp_affinity 1:1 to CPU number
+    pg_set $dev "flag QUEUE_MAP_CPU"
+
+    # Base config of dev
+    pg_set $dev "count $COUNT"
+    pg_set $dev "clone_skb $CLONE_SKB"
+    pg_set $dev "pkt_size $PKT_SIZE"
+    pg_set $dev "delay $DELAY"
+
+    # Flag example disabling timestamping
+    pg_set $dev "flag NO_TIMESTAMP"
+
+    # Destination
+    pg_set $dev "dst_mac $DST_MAC"
+    pg_set $dev "dst$IP6 $DEST_IP"
+
+    # Setup random UDP port src range
+    pg_set $dev "flag UDPSRC_RND"
+    pg_set $dev "udp_src_min $UDP_MIN"
+    pg_set $dev "udp_src_max $UDP_MAX"
+done
+
+# start_run
+echo "Running... ctrl^C to stop" >&2
+pg_ctrl "start"
+echo "Done" >&2
+
+# Print results
+for ((i = 0; i < $THREADS; i++)); do
+    thread=${cpu_array[$((i+F_THREAD))]}
+    dev=${DEV}@${thread}
+    echo "Device: $dev"
+    cat /proc/net/pktgen/$dev | grep -A2 "Result:"
+done
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index 6d0193a3c591..9826b9a6543c 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -207,5 +207,12 @@ int main(void)
 	DEVID_FIELD(fsl_mc_device_id, vendor);
 	DEVID_FIELD(fsl_mc_device_id, obj_type);
 
+	DEVID(tb_service_id);
+	DEVID_FIELD(tb_service_id, match_flags);
+	DEVID_FIELD(tb_service_id, protocol_key);
+	DEVID_FIELD(tb_service_id, protocol_id);
+	DEVID_FIELD(tb_service_id, protocol_version);
+	DEVID_FIELD(tb_service_id, protocol_revision);
+
 	return 0;
 }
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 29d6699d5a06..6ef6e63f96fd 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -1301,6 +1301,31 @@ static int do_fsl_mc_entry(const char *filename, void *symval,
 }
 ADD_TO_DEVTABLE("fslmc", fsl_mc_device_id, do_fsl_mc_entry);
 
+/* Looks like: tbsvc:kSpNvNrN */
+static int do_tbsvc_entry(const char *filename, void *symval, char *alias)
+{
+	DEF_FIELD(symval, tb_service_id, match_flags);
+	DEF_FIELD_ADDR(symval, tb_service_id, protocol_key);
+	DEF_FIELD(symval, tb_service_id, protocol_id);
+	DEF_FIELD(symval, tb_service_id, protocol_version);
+	DEF_FIELD(symval, tb_service_id, protocol_revision);
+
+	strcpy(alias, "tbsvc:");
+	if (match_flags & TBSVC_MATCH_PROTOCOL_KEY)
+		sprintf(alias + strlen(alias), "k%s", *protocol_key);
+	else
+		strcat(alias + strlen(alias), "k*");
+	ADD(alias, "p", match_flags & TBSVC_MATCH_PROTOCOL_ID, protocol_id);
+	ADD(alias, "v", match_flags & TBSVC_MATCH_PROTOCOL_VERSION,
+	    protocol_version);
+	ADD(alias, "r", match_flags & TBSVC_MATCH_PROTOCOL_REVISION,
+	    protocol_revision);
+
+	add_wildcard(alias);
+	return 1;
+}
+ADD_TO_DEVTABLE("tbsvc", tb_service_id, do_tbsvc_entry);
+
 /* Does namelen bytes of name exactly match the symbol? */
 static bool sym_is(const char *name, unsigned namelen, const char *symbol)
 {
diff --git a/security/security.c b/security/security.c
index 4bf0f571b4ef..1cd8526cb0b7 100644
--- a/security/security.c
+++ b/security/security.c
@@ -12,6 +12,7 @@
  *	(at your option) any later version.
  */
 
+#include <linux/bpf.h>
 #include <linux/capability.h>
 #include <linux/dcache.h>
 #include <linux/module.h>
@@ -1703,3 +1704,34 @@ int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule,
 				actx);
 }
 #endif /* CONFIG_AUDIT */
+
+#ifdef CONFIG_BPF_SYSCALL
+int security_bpf(int cmd, union bpf_attr *attr, unsigned int size)
+{
+	return call_int_hook(bpf, 0, cmd, attr, size);
+}
+int security_bpf_map(struct bpf_map *map, fmode_t fmode)
+{
+	return call_int_hook(bpf_map, 0, map, fmode);
+}
+int security_bpf_prog(struct bpf_prog *prog)
+{
+	return call_int_hook(bpf_prog, 0, prog);
+}
+int security_bpf_map_alloc(struct bpf_map *map)
+{
+	return call_int_hook(bpf_map_alloc_security, 0, map);
+}
+int security_bpf_prog_alloc(struct bpf_prog_aux *aux)
+{
+	return call_int_hook(bpf_prog_alloc_security, 0, aux);
+}
+void security_bpf_map_free(struct bpf_map *map)
+{
+	call_void_hook(bpf_map_free_security, map);
+}
+void security_bpf_prog_free(struct bpf_prog_aux *aux)
+{
+	call_void_hook(bpf_prog_free_security, aux);
+}
+#endif /* CONFIG_BPF_SYSCALL */
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index f5d304736852..2e3a627fc0b1 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -85,6 +85,7 @@
 #include <linux/export.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
+#include <linux/bpf.h>
 
 #include "avc.h"
 #include "objsec.h"
@@ -1814,6 +1815,10 @@ static inline int file_path_has_perm(const struct cred *cred,
 	return inode_has_perm(cred, file_inode(file), av, &ad);
 }
 
+#ifdef CONFIG_BPF_SYSCALL
+static int bpf_fd_pass(struct file *file, u32 sid);
+#endif
+
 /* Check whether a task can use an open file descriptor to
    access an inode in a given way.  Check access to the
    descriptor itself, and then use dentry_has_perm to
@@ -1844,6 +1849,12 @@ static int file_has_perm(const struct cred *cred,
 			goto out;
 	}
 
+#ifdef CONFIG_BPF_SYSCALL
+	rc = bpf_fd_pass(file, cred_sid(cred));
+	if (rc)
+		return rc;
+#endif
+
 	/* av is zero if only checking access to the descriptor. */
 	rc = 0;
 	if (av)
@@ -2164,6 +2175,12 @@ static int selinux_binder_transfer_file(struct task_struct *from,
 			return rc;
 	}
 
+#ifdef CONFIG_BPF_SYSCALL
+	rc = bpf_fd_pass(file, sid);
+	if (rc)
+		return rc;
+#endif
+
 	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
 		return 0;
 
@@ -6252,6 +6269,139 @@ static void selinux_ib_free_security(void *ib_sec)
 }
 #endif
 
+#ifdef CONFIG_BPF_SYSCALL
+static int selinux_bpf(int cmd, union bpf_attr *attr,
+				     unsigned int size)
+{
+	u32 sid = current_sid();
+	int ret;
+
+	switch (cmd) {
+	case BPF_MAP_CREATE:
+		ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__MAP_CREATE,
+				   NULL);
+		break;
+	case BPF_PROG_LOAD:
+		ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__PROG_LOAD,
+				   NULL);
+		break;
+	default:
+		ret = 0;
+		break;
+	}
+
+	return ret;
+}
+
+static u32 bpf_map_fmode_to_av(fmode_t fmode)
+{
+	u32 av = 0;
+
+	if (fmode & FMODE_READ)
+		av |= BPF__MAP_READ;
+	if (fmode & FMODE_WRITE)
+		av |= BPF__MAP_WRITE;
+	return av;
+}
+
+/* This function will check the file pass through unix socket or binder to see
+ * if it is a bpf related object. And apply correspinding checks on the bpf
+ * object based on the type. The bpf maps and programs, not like other files and
+ * socket, are using a shared anonymous inode inside the kernel as their inode.
+ * So checking that inode cannot identify if the process have privilege to
+ * access the bpf object and that's why we have to add this additional check in
+ * selinux_file_receive and selinux_binder_transfer_files.
+ */
+static int bpf_fd_pass(struct file *file, u32 sid)
+{
+	struct bpf_security_struct *bpfsec;
+	struct bpf_prog *prog;
+	struct bpf_map *map;
+	int ret;
+
+	if (file->f_op == &bpf_map_fops) {
+		map = file->private_data;
+		bpfsec = map->security;
+		ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+				   bpf_map_fmode_to_av(file->f_mode), NULL);
+		if (ret)
+			return ret;
+	} else if (file->f_op == &bpf_prog_fops) {
+		prog = file->private_data;
+		bpfsec = prog->aux->security;
+		ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+				   BPF__PROG_RUN, NULL);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode)
+{
+	u32 sid = current_sid();
+	struct bpf_security_struct *bpfsec;
+
+	bpfsec = map->security;
+	return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+			    bpf_map_fmode_to_av(fmode), NULL);
+}
+
+static int selinux_bpf_prog(struct bpf_prog *prog)
+{
+	u32 sid = current_sid();
+	struct bpf_security_struct *bpfsec;
+
+	bpfsec = prog->aux->security;
+	return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+			    BPF__PROG_RUN, NULL);
+}
+
+static int selinux_bpf_map_alloc(struct bpf_map *map)
+{
+	struct bpf_security_struct *bpfsec;
+
+	bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL);
+	if (!bpfsec)
+		return -ENOMEM;
+
+	bpfsec->sid = current_sid();
+	map->security = bpfsec;
+
+	return 0;
+}
+
+static void selinux_bpf_map_free(struct bpf_map *map)
+{
+	struct bpf_security_struct *bpfsec = map->security;
+
+	map->security = NULL;
+	kfree(bpfsec);
+}
+
+static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux)
+{
+	struct bpf_security_struct *bpfsec;
+
+	bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL);
+	if (!bpfsec)
+		return -ENOMEM;
+
+	bpfsec->sid = current_sid();
+	aux->security = bpfsec;
+
+	return 0;
+}
+
+static void selinux_bpf_prog_free(struct bpf_prog_aux *aux)
+{
+	struct bpf_security_struct *bpfsec = aux->security;
+
+	aux->security = NULL;
+	kfree(bpfsec);
+}
+#endif
+
 static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr),
 	LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction),
@@ -6471,6 +6621,16 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(audit_rule_match, selinux_audit_rule_match),
 	LSM_HOOK_INIT(audit_rule_free, selinux_audit_rule_free),
 #endif
+
+#ifdef CONFIG_BPF_SYSCALL
+	LSM_HOOK_INIT(bpf, selinux_bpf),
+	LSM_HOOK_INIT(bpf_map, selinux_bpf_map),
+	LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog),
+	LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc),
+	LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc),
+	LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free),
+	LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free),
+#endif
 };
 
 static __init int selinux_init(void)
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index cc35695d97b4..acdee7795297 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -238,6 +238,8 @@ struct security_class_mapping secclass_map[] = {
 	  { "access", NULL } },
 	{ "infiniband_endport",
 	  { "manage_subnet", NULL } },
+	{ "bpf",
+	  {"map_create", "map_read", "map_write", "prog_load", "prog_run"} },
 	{ NULL }
   };
 
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index 1649cd18eb0b..3d54468ce334 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -150,6 +150,10 @@ struct pkey_security_struct {
 	u32	sid;	/* SID of pkey */
 };
 
+struct bpf_security_struct {
+	u32 sid;  /*SID of bpf obj creater*/
+};
+
 extern unsigned int selinux_checkreqprot;
 
 #endif /* _SELINUX_OBJSEC_H_ */
diff --git a/tools/Makefile b/tools/Makefile
index c4f41ef9a7a7..c03b4f69d5b7 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -20,7 +20,7 @@ help:
 	@echo '  kvm_stat               - top-like utility for displaying kvm statistics'
 	@echo '  leds                   - LEDs  tools'
 	@echo '  liblockdep             - user-space wrapper for kernel locking-validator'
-	@echo '  net                    - misc networking tools'
+	@echo '  bpf                    - misc BPF tools'
 	@echo '  perf                   - Linux performance measurement and analysis tool'
 	@echo '  selftests              - various kernel selftests'
 	@echo '  spi                    - spi tools'
@@ -58,7 +58,7 @@ acpi: FORCE
 cpupower: FORCE
 	$(call descend,power/$@)
 
-cgroup firewire hv guest spi usb virtio vm net iio gpio objtool leds: FORCE
+cgroup firewire hv guest spi usb virtio vm bpf iio gpio objtool leds: FORCE
 	$(call descend,$@)
 
 liblockdep: FORCE
@@ -92,7 +92,7 @@ kvm_stat: FORCE
 
 all: acpi cgroup cpupower gpio hv firewire liblockdep \
 		perf selftests spi turbostat usb \
-		virtio vm net x86_energy_perf_policy \
+		virtio vm bpf x86_energy_perf_policy \
 		tmon freefall iio objtool kvm_stat
 
 acpi_install:
@@ -101,7 +101,7 @@ acpi_install:
 cpupower_install:
 	$(call descend,power/$(@:_install=),install)
 
-cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install net_install objtool_install:
+cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install bpf_install objtool_install:
 	$(call descend,$(@:_install=),install)
 
 liblockdep_install:
@@ -125,7 +125,7 @@ kvm_stat_install:
 install: acpi_install cgroup_install cpupower_install gpio_install \
 		hv_install firewire_install iio_install liblockdep_install \
 		perf_install selftests_install turbostat_install usb_install \
-		virtio_install vm_install net_install x86_energy_perf_policy_install \
+		virtio_install vm_install bpf_install x86_energy_perf_policy_install \
 		tmon_install freefall_install objtool_install kvm_stat_install
 
 acpi_clean:
@@ -134,7 +134,7 @@ acpi_clean:
 cpupower_clean:
 	$(call descend,power/cpupower,clean)
 
-cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean leds_clean:
+cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean:
 	$(call descend,$(@:_clean=),clean)
 
 liblockdep_clean:
@@ -170,7 +170,7 @@ build_clean:
 
 clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \
 		perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \
-		vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
+		vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
 		freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \
 		gpio_clean objtool_clean leds_clean
 
diff --git a/tools/net/Makefile b/tools/bpf/Makefile
index 5830670feae1..07a6697466ef 100644
--- a/tools/net/Makefile
+++ b/tools/bpf/Makefile
@@ -4,6 +4,7 @@ prefix = /usr
 CC = gcc
 LEX = flex
 YACC = bison
+MAKE = make
 
 CFLAGS += -Wall -O2
 CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
@@ -14,7 +15,7 @@ CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
 %.lex.c: %.l
 	$(LEX) -o $@ $<
 
-all : bpf_jit_disasm bpf_dbg bpf_asm
+all: bpf_jit_disasm bpf_dbg bpf_asm bpftool
 
 bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm'
 bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
@@ -27,10 +28,21 @@ bpf_asm : LDLIBS =
 bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
 bpf_exp.lex.o : bpf_exp.yacc.c
 
-clean :
+clean: bpftool_clean
 	rm -rf *.o bpf_jit_disasm bpf_dbg bpf_asm bpf_exp.yacc.* bpf_exp.lex.*
 
-install :
+install: bpftool_install
 	install bpf_jit_disasm $(prefix)/bin/bpf_jit_disasm
 	install bpf_dbg $(prefix)/bin/bpf_dbg
 	install bpf_asm $(prefix)/bin/bpf_asm
+
+bpftool:
+	$(MAKE) -C bpftool
+
+bpftool_install:
+	$(MAKE) -C bpftool install
+
+bpftool_clean:
+	$(MAKE) -C bpftool clean
+
+.PHONY: bpftool FORCE
diff --git a/tools/net/bpf_asm.c b/tools/bpf/bpf_asm.c
index c15aef097b04..c15aef097b04 100644
--- a/tools/net/bpf_asm.c
+++ b/tools/bpf/bpf_asm.c
diff --git a/tools/net/bpf_dbg.c b/tools/bpf/bpf_dbg.c
index 4f254bcc4423..4f254bcc4423 100644
--- a/tools/net/bpf_dbg.c
+++ b/tools/bpf/bpf_dbg.c
diff --git a/tools/net/bpf_exp.l b/tools/bpf/bpf_exp.l
index bd83149e7be0..bd83149e7be0 100644
--- a/tools/net/bpf_exp.l
+++ b/tools/bpf/bpf_exp.l
diff --git a/tools/net/bpf_exp.y b/tools/bpf/bpf_exp.y
index 56ba1de50784..56ba1de50784 100644
--- a/tools/net/bpf_exp.y
+++ b/tools/bpf/bpf_exp.y
diff --git a/tools/net/bpf_jit_disasm.c b/tools/bpf/bpf_jit_disasm.c
index 422d9abd666a..75bf526a0168 100644
--- a/tools/net/bpf_jit_disasm.c
+++ b/tools/bpf/bpf_jit_disasm.c
@@ -27,6 +27,7 @@
 #include <sys/klog.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <limits.h>
 
 #define CMD_ACTION_SIZE_BUFFER		10
 #define CMD_ACTION_READ_ALL		3
@@ -51,7 +52,7 @@ static void get_exec_path(char *tpath, size_t size)
 static void get_asm_insns(uint8_t *image, size_t len, int opcodes)
 {
 	int count, i, pc = 0;
-	char tpath[256];
+	char tpath[PATH_MAX];
 	struct disassemble_info info;
 	disassembler_ftype disassemble;
 	bfd *bfdf;
diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile
new file mode 100644
index 000000000000..bde77d7c4390
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/Makefile
@@ -0,0 +1,34 @@
+include ../../../scripts/Makefile.include
+include ../../../scripts/utilities.mak
+
+INSTALL ?= install
+RM ?= rm -f
+
+# Make the path relative to DESTDIR, not prefix
+ifndef DESTDIR
+prefix?=$(HOME)
+endif
+mandir ?= $(prefix)/share/man
+man8dir = $(mandir)/man8
+
+MAN8_RST = $(wildcard *.rst)
+
+_DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST))
+DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8))
+
+man: man8
+man8: $(DOC_MAN8)
+
+$(OUTPUT)%.8: %.rst
+	rst2man $< > $@
+
+clean:
+	$(call QUIET_CLEAN, Documentation) $(RM) $(DOC_MAN8)
+
+install: man
+	$(call QUIET_INSTALL, Documentation-man) \
+		$(INSTALL) -d -m 755 $(DESTDIR)$(man8dir); \
+		$(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir);
+
+.PHONY: man man8 clean install
+.DEFAULT_GOAL := man
diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
new file mode 100644
index 000000000000..abb9ee940b15
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -0,0 +1,128 @@
+================
+bpftool-map
+================
+-------------------------------------------------------------------------------
+tool for inspection and simple manipulation of eBPF maps
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+	**bpftool** [*OPTIONS*] **map** *COMMAND*
+
+	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] }
+
+	*COMMANDS* :=
+	{ **show** | **dump** | **update** | **lookup** | **getnext** | **delete**
+	| **pin** | **help** }
+
+MAP COMMANDS
+=============
+
+|	**bpftool** **map show**   [*MAP*]
+|	**bpftool** **map dump**    *MAP*
+|	**bpftool** **map update**  *MAP*  **key** *BYTES*   **value** *VALUE* [*UPDATE_FLAGS*]
+|	**bpftool** **map lookup**  *MAP*  **key** *BYTES*
+|	**bpftool** **map getnext** *MAP* [**key** *BYTES*]
+|	**bpftool** **map delete**  *MAP*  **key** *BYTES*
+|	**bpftool** **map pin**     *MAP*  *FILE*
+|	**bpftool** **map help**
+|
+|	*MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
+|	*VALUE* := { *BYTES* | *MAP* | *PROGRAM* }
+|	*UPDATE_FLAGS* := { **any** | **exist** | **noexist** }
+
+DESCRIPTION
+===========
+	**bpftool map show**   [*MAP*]
+		  Show information about loaded maps.  If *MAP* is specified
+		  show information only about given map, otherwise list all
+		  maps currently loaded on the system.
+
+		  Output will start with map ID followed by map type and
+		  zero or more named attributes (depending on kernel version).
+
+	**bpftool map dump**    *MAP*
+		  Dump all entries in a given *MAP*.
+
+	**bpftool map update**  *MAP*  **key** *BYTES*   **value** *VALUE* [*UPDATE_FLAGS*]
+		  Update map entry for a given *KEY*.
+
+		  *UPDATE_FLAGS* can be one of: **any** update existing entry
+		  or add if doesn't exit; **exist** update only if entry already
+		  exists; **noexist** update only if entry doesn't exist.
+
+	**bpftool map lookup**  *MAP*  **key** *BYTES*
+		  Lookup **key** in the map.
+
+	**bpftool map getnext** *MAP* [**key** *BYTES*]
+		  Get next key.  If *key* is not specified, get first key.
+
+	**bpftool map delete**  *MAP*  **key** *BYTES*
+		  Remove entry from the map.
+
+	**bpftool map pin**     *MAP*  *FILE*
+		  Pin map *MAP* as *FILE*.
+
+		  Note: *FILE* must be located in *bpffs* mount.
+
+	**bpftool map help**
+		  Print short help message.
+
+OPTIONS
+=======
+	-h, --help
+		  Print short generic help message (similar to **bpftool help**).
+
+	-v, --version
+		  Print version number (similar to **bpftool version**).
+
+	-j, --json
+		  Generate JSON output. For commands that cannot produce JSON, this
+		  option has no effect.
+
+	-p, --pretty
+		  Generate human-readable JSON output. Implies **-j**.
+
+EXAMPLES
+========
+**# bpftool map show**
+::
+
+  10: hash  name some_map  flags 0x0
+	key 4B  value 8B  max_entries 2048  memlock 167936B
+
+**# bpftool map update id 10 key 13 00 07 00 value 02 00 00 00 01 02 03 04**
+
+**# bpftool map lookup id 10 key 0 1 2 3**
+
+::
+
+  key: 00 01 02 03 value: 00 01 02 03 04 05 06 07
+
+
+**# bpftool map dump id 10**
+::
+
+  key: 00 01 02 03  value: 00 01 02 03 04 05 06 07
+  key: 0d 00 07 00  value: 02 00 00 00 01 02 03 04
+  Found 2 elements
+
+**# bpftool map getnext id 10 key 0 1 2 3**
+::
+
+  key:
+  00 01 02 03
+  next key:
+  0d 00 07 00
+
+|
+| **# mount -t bpf none /sys/fs/bpf/**
+| **# bpftool map pin id 10 /sys/fs/bpf/map**
+| **# bpftool map del pinned /sys/fs/bpf/map key 13 00 07 00**
+
+SEE ALSO
+========
+	**bpftool**\ (8), **bpftool-prog**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
new file mode 100644
index 000000000000..0f25d3c39e05
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -0,0 +1,147 @@
+================
+bpftool-prog
+================
+-------------------------------------------------------------------------------
+tool for inspection and simple manipulation of eBPF progs
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+	**bpftool** [*OPTIONS*] **prog** *COMMAND*
+
+	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] }
+
+	*COMMANDS* :=
+	{ **show** | **dump xlated** | **dump jited** | **pin** | **help** }
+
+MAP COMMANDS
+=============
+
+|	**bpftool** **prog show** [*PROG*]
+|	**bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes**}]
+|	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
+|	**bpftool** **prog pin** *PROG* *FILE*
+|	**bpftool** **prog help**
+|
+|	*PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
+
+DESCRIPTION
+===========
+	**bpftool prog show** [*PROG*]
+		  Show information about loaded programs.  If *PROG* is
+		  specified show information only about given program, otherwise
+		  list all programs currently loaded on the system.
+
+		  Output will start with program ID followed by program type and
+		  zero or more named attributes (depending on kernel version).
+
+	**bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** }]
+		  Dump eBPF instructions of the program from the kernel.
+		  If *FILE* is specified image will be written to a file,
+		  otherwise it will be disassembled and printed to stdout.
+
+		  **opcodes** controls if raw opcodes will be printed.
+
+	**bpftool prog dump jited**  *PROG* [{ **file** *FILE* | **opcodes** }]
+		  Dump jited image (host machine code) of the program.
+		  If *FILE* is specified image will be written to a file,
+		  otherwise it will be disassembled and printed to stdout.
+
+		  **opcodes** controls if raw opcodes will be printed.
+
+	**bpftool prog pin** *PROG* *FILE*
+		  Pin program *PROG* as *FILE*.
+
+		  Note: *FILE* must be located in *bpffs* mount.
+
+	**bpftool prog help**
+		  Print short help message.
+
+OPTIONS
+=======
+	-h, --help
+		  Print short generic help message (similar to **bpftool help**).
+
+	-v, --version
+		  Print version number (similar to **bpftool version**).
+
+	-j, --json
+		  Generate JSON output. For commands that cannot produce JSON, this
+		  option has no effect.
+
+	-p, --pretty
+		  Generate human-readable JSON output. Implies **-j**.
+
+EXAMPLES
+========
+**# bpftool prog show**
+::
+
+  10: xdp  name some_prog  tag 005a3d2123620c8b
+	loaded_at Sep 29/20:11  uid 0
+	xlated 528B  jited 370B  memlock 4096B  map_ids 10
+
+**# bpftool --json --pretty prog show**
+
+::
+
+    {
+        "programs": [{
+                "id": 10,
+                "type": "xdp",
+                "tag": "005a3d2123620c8b",
+                "loaded_at": "Sep 29/20:11",
+                "uid": 0,
+                "bytes_xlated": 528,
+                "jited": true,
+                "bytes_jited": 370,
+                "bytes_memlock": 4096,
+                "map_ids": [10
+                ]
+            }
+        ]
+    }
+
+|
+| **# bpftool prog dump xlated id 10 file /tmp/t**
+| **# ls -l /tmp/t**
+|   -rw------- 1 root root 560 Jul 22 01:42 /tmp/t
+
+**# bpftool prog dum jited tag 005a3d2123620c8b**
+
+::
+
+    push   %rbp
+    mov    %rsp,%rbp
+    sub    $0x228,%rsp
+    sub    $0x28,%rbp
+    mov    %rbx,0x0(%rbp)
+
+|
+| **# mount -t bpf none /sys/fs/bpf/**
+| **# bpftool prog pin id 10 /sys/fs/bpf/prog**
+| **# ls -l /sys/fs/bpf/**
+|   -rw------- 1 root root 0 Jul 22 01:43 prog
+
+**# bpftool prog dum jited pinned /sys/fs/bpf/prog opcodes**
+
+::
+
+    push   %rbp
+    55
+    mov    %rsp,%rbp
+    48 89 e5
+    sub    $0x228,%rsp
+    48 81 ec 28 02 00 00
+    sub    $0x28,%rbp
+    48 83 ed 28
+    mov    %rbx,0x0(%rbp)
+    48 89 5d 00
+
+
+SEE ALSO
+========
+	**bpftool**\ (8), **bpftool-map**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
new file mode 100644
index 000000000000..926c03d5a8da
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -0,0 +1,56 @@
+================
+BPFTOOL
+================
+-------------------------------------------------------------------------------
+tool for inspection and simple manipulation of eBPF programs and maps
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+	**bpftool** [*OPTIONS*] *OBJECT* { *COMMAND* | **help** }
+
+	**bpftool** **batch file** *FILE*
+
+	**bpftool** **version**
+
+	*OBJECT* := { **map** | **program** }
+
+	*OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** }
+	| { **-j** | **--json** } [{ **-p** | **--pretty** }] }
+
+	*MAP-COMMANDS* :=
+	{ **show** | **dump** | **update** | **lookup** | **getnext** | **delete**
+	| **pin** | **help** }
+
+	*PROG-COMMANDS* := { **show** | **dump jited** | **dump xlated** | **pin**
+	| **help** }
+
+DESCRIPTION
+===========
+	*bpftool* allows for inspection and simple modification of BPF objects
+	on the system.
+
+	Note that format of the output of all tools is not guaranteed to be
+	stable and should not be depended upon.
+
+OPTIONS
+=======
+	-h, --help
+		  Print short help message (similar to **bpftool help**).
+
+	-v, --version
+		  Print version number (similar to **bpftool version**).
+
+	-j, --json
+		  Generate JSON output. For commands that cannot produce JSON, this
+		  option has no effect.
+
+	-p, --pretty
+		  Generate human-readable JSON output. Implies **-j**.
+
+SEE ALSO
+========
+	**bpftool-map**\ (8), **bpftool-prog**\ (8)
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
new file mode 100644
index 000000000000..813826c50936
--- /dev/null
+++ b/tools/bpf/bpftool/Makefile
@@ -0,0 +1,92 @@
+include ../../scripts/Makefile.include
+
+include ../../scripts/utilities.mak
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+ifneq ($(objtree),)
+#$(info Determined 'objtree' to be $(objtree))
+endif
+
+ifneq ($(OUTPUT),)
+#$(info Determined 'OUTPUT' to be $(OUTPUT))
+# Adding $(OUTPUT) as a directory to look for source files,
+# because use generated output files as sources dependency
+# for flex/bison parsers.
+VPATH += $(OUTPUT)
+export VPATH
+endif
+
+ifeq ($(V),1)
+  Q =
+else
+  Q = @
+endif
+
+BPF_DIR	= $(srctree)/tools/lib/bpf/
+
+ifneq ($(OUTPUT),)
+  BPF_PATH=$(OUTPUT)
+else
+  BPF_PATH=$(BPF_DIR)
+endif
+
+LIBBPF = $(BPF_PATH)libbpf.a
+
+$(LIBBPF): FORCE
+	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT)
+
+$(LIBBPF)-clean:
+	$(call QUIET_CLEAN, libbpf)
+	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) clean >/dev/null
+
+prefix = /usr
+bash_compdir ?= $(prefix)/share/bash-completion/completions
+
+CC = gcc
+
+CFLAGS += -O2
+CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow
+CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf -I$(srctree)/kernel/bpf/
+LIBS = -lelf -lbfd -lopcodes $(LIBBPF)
+
+include $(wildcard *.d)
+
+all: $(OUTPUT)bpftool
+
+SRCS=$(wildcard *.c)
+OBJS=$(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
+
+$(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
+	$(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
+
+$(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
+	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^ $(LIBS)
+
+$(OUTPUT)%.o: %.c
+	$(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
+
+clean: $(LIBBPF)-clean
+	$(call QUIET_CLEAN, bpftool)
+	$(Q)rm -rf $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d
+
+install:
+	install $(OUTPUT)bpftool $(prefix)/sbin/bpftool
+	install -m 0755 -d $(bash_compdir)
+	install -m 0644 bash-completion/bpftool $(bash_compdir)
+
+doc:
+	$(Q)$(MAKE) -C Documentation/
+
+doc-install:
+	$(Q)$(MAKE) -C Documentation/ install
+
+FORCE:
+
+.PHONY: all clean FORCE
+.DEFAULT_GOAL := all
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
new file mode 100644
index 000000000000..7febee05c8e7
--- /dev/null
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -0,0 +1,354 @@
+# bpftool(8) bash completion                               -*- shell-script -*-
+#
+# Copyright (C) 2017 Netronome Systems, Inc.
+#
+# This software is dual licensed under the GNU General License
+# Version 2, June 1991 as shown in the file COPYING in the top-level
+# directory of this source tree or the BSD 2-Clause License provided
+# below.  You have the option to license this software under the
+# complete terms of either license.
+#
+# The BSD 2-Clause License:
+#
+#     Redistribution and use in source and binary forms, with or
+#     without modification, are permitted provided that the following
+#     conditions are met:
+#
+#      1. Redistributions of source code must retain the above
+#         copyright notice, this list of conditions and the following
+#         disclaimer.
+#
+#      2. Redistributions in binary form must reproduce the above
+#         copyright notice, this list of conditions and the following
+#         disclaimer in the documentation and/or other materials
+#         provided with the distribution.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+#
+# Author: Quentin Monnet <quentin.monnet@netronome.com>
+
+# Takes a list of words in argument; each one of them is added to COMPREPLY if
+# it is not already present on the command line. Returns no value.
+_bpftool_once_attr()
+{
+    local w idx found
+    for w in $*; do
+        found=0
+        for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+            if [[ $w == ${words[idx]} ]]; then
+                found=1
+                break
+            fi
+        done
+        [[ $found -eq 0 ]] && \
+            COMPREPLY+=( $( compgen -W "$w" -- "$cur" ) )
+    done
+}
+
+# Takes a list of words in argument; adds them all to COMPREPLY if none of them
+# is already present on the command line. Returns no value.
+_bpftool_one_of_list()
+{
+    local w idx
+    for w in $*; do
+        for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+            [[ $w == ${words[idx]} ]] && return 1
+        done
+    done
+    COMPREPLY+=( $( compgen -W "$*" -- "$cur" ) )
+}
+
+_bpftool_get_map_ids()
+{
+    COMPREPLY+=( $( compgen -W "$( bpftool -jp map  2>&1 | \
+        command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) )
+}
+
+_bpftool_get_prog_ids()
+{
+    COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \
+        command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) )
+}
+
+_bpftool_get_prog_tags()
+{
+    COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \
+        command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) )
+}
+
+# For bpftool map update: retrieve type of the map to update.
+_bpftool_map_update_map_type()
+{
+    local keyword ref
+    for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+        if [[ ${words[$((idx-2))]} == "update" ]]; then
+            keyword=${words[$((idx-1))]}
+            ref=${words[$((idx))]}
+        fi
+    done
+    [[ -z $ref ]] && return 0
+
+    local type
+    type=$(bpftool -jp map show $keyword $ref | \
+        command sed -n 's/.*"type": "\(.*\)",$/\1/p')
+    printf $type
+}
+
+_bpftool_map_update_get_id()
+{
+    # Is it the map to update, or a map to insert into the map to update?
+    # Search for "value" keyword.
+    local idx value
+    for (( idx=7; idx < ${#words[@]}-1; idx++ )); do
+        if [[ ${words[idx]} == "value" ]]; then
+            value=1
+            break
+        fi
+    done
+    [[ $value -eq 0 ]] && _bpftool_get_map_ids && return 0
+
+    # Id to complete is for a value. It can be either prog id or map id. This
+    # depends on the type of the map to update.
+    local type=$(_bpftool_map_update_map_type)
+    case $type in
+        array_of_maps|hash_of_maps)
+            _bpftool_get_map_ids
+            return 0
+            ;;
+        prog_array)
+            _bpftool_get_prog_ids
+            return 0
+            ;;
+        *)
+            return 0
+            ;;
+    esac
+}
+
+_bpftool()
+{
+    local cur prev words objword
+    _init_completion || return
+
+    # Deal with simplest keywords
+    case $prev in
+        help|key|opcodes)
+            return 0
+            ;;
+        tag)
+            _bpftool_get_prog_tags
+            return 0
+            ;;
+        file|pinned)
+            _filedir
+            return 0
+            ;;
+        batch)
+            COMPREPLY=( $( compgen -W 'file' -- "$cur" ) )
+            return 0
+            ;;
+    esac
+
+    # Search for object and command
+    local object command cmdword
+    for (( cmdword=1; cmdword < ${#words[@]}-1; cmdword++ )); do
+        [[ -n $object ]] && command=${words[cmdword]} && break
+        [[ ${words[cmdword]} != -* ]] && object=${words[cmdword]}
+    done
+
+    if [[ -z $object ]]; then
+        case $cur in
+            -*)
+                local c='--version --json --pretty'
+                COMPREPLY=( $( compgen -W "$c" -- "$cur" ) )
+                return 0
+                ;;
+            *)
+                COMPREPLY=( $( compgen -W "$( bpftool help 2>&1 | \
+                    command sed \
+                    -e '/OBJECT := /!d' \
+                    -e 's/.*{//' \
+                    -e 's/}.*//' \
+                    -e 's/|//g' )" -- "$cur" ) )
+                COMPREPLY+=( $( compgen -W 'batch help' -- "$cur" ) )
+                return 0
+                ;;
+        esac
+    fi
+
+    [[ $command == help ]] && return 0
+
+    # Completion depends on object and command in use
+    case $object in
+        prog)
+            case $prev in
+                id)
+                    _bpftool_get_prog_ids
+                    return 0
+                    ;;
+            esac
+
+            local PROG_TYPE='id pinned tag'
+            case $command in
+                show)
+                    [[ $prev != "$command" ]] && return 0
+                    COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+                    return 0
+                    ;;
+                dump)
+                    case $prev in
+                        $command)
+                            COMPREPLY+=( $( compgen -W "xlated jited" -- \
+                                "$cur" ) )
+                            return 0
+                            ;;
+                        xlated|jited)
+                            COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \
+                                "$cur" ) )
+                            return 0
+                            ;;
+                    *)
+                            _bpftool_once_attr 'file'
+                            COMPREPLY+=( $( compgen -W 'opcodes' -- \
+                                "$cur" ) )
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                pin)
+                    if [[ $prev == "$command" ]]; then
+                        COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+                    else
+                        _filedir
+                    fi
+                    return 0
+                    ;;
+                *)
+                    [[ $prev == $object ]] && \
+                        COMPREPLY=( $( compgen -W 'dump help pin show' -- \
+                            "$cur" ) )
+                    ;;
+            esac
+            ;;
+        map)
+            local MAP_TYPE='id pinned'
+            case $command in
+                show|dump)
+                    case $prev in
+                        $command)
+                            COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        id)
+                            _bpftool_get_map_ids
+                            return 0
+                            ;;
+                        *)
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                lookup|getnext|delete)
+                    case $prev in
+                        $command)
+                            COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        id)
+                            _bpftool_get_map_ids
+                            return 0
+                            ;;
+                        key)
+                            return 0
+                            ;;
+                        *)
+                            _bpftool_once_attr 'key'
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                update)
+                    case $prev in
+                        $command)
+                            COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        id)
+                            _bpftool_map_update_get_id
+                            return 0
+                            ;;
+                        key)
+                            return 0
+                            ;;
+                        value)
+                            # We can have bytes, or references to a prog or a
+                            # map, depending on the type of the map to update.
+                            case $(_bpftool_map_update_map_type) in
+                                array_of_maps|hash_of_maps)
+                                    local MAP_TYPE='id pinned'
+                                    COMPREPLY+=( $( compgen -W "$MAP_TYPE" \
+                                        -- "$cur" ) )
+                                    return 0
+                                    ;;
+                                prog_array)
+                                    local PROG_TYPE='id pinned tag'
+                                    COMPREPLY+=( $( compgen -W "$PROG_TYPE" \
+                                        -- "$cur" ) )
+                                    return 0
+                                    ;;
+                                *)
+                                    return 0
+                                    ;;
+                            esac
+                            return 0
+                            ;;
+                        *)
+                            _bpftool_once_attr 'key'
+                            local UPDATE_FLAGS='any exist noexist'
+                            for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+                                if [[ ${words[idx]} == 'value' ]]; then
+                                    # 'value' is present, but is not the last
+                                    # word i.e. we can now have UPDATE_FLAGS.
+                                    _bpftool_one_of_list "$UPDATE_FLAGS"
+                                    return 0
+                                fi
+                            done
+                            for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+                                if [[ ${words[idx]} == 'key' ]]; then
+                                    # 'key' is present, but is not the last
+                                    # word i.e. we can now have 'value'.
+                                    _bpftool_once_attr 'value'
+                                    return 0
+                                fi
+                            done
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                pin)
+                    if [[ $prev == "$command" ]]; then
+                        COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+                    else
+                        _filedir
+                    fi
+                    return 0
+                    ;;
+                *)
+                    [[ $prev == $object ]] && \
+                        COMPREPLY=( $( compgen -W 'delete dump getnext help \
+                            lookup pin show update' -- "$cur" ) )
+                    ;;
+            esac
+            ;;
+    esac
+} &&
+complete -F _bpftool bpftool
+
+# ex: ts=4 sw=4 et filetype=sh
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
new file mode 100644
index 000000000000..f0288269dae8
--- /dev/null
+++ b/tools/bpf/bpftool/common.c
@@ -0,0 +1,281 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#include <errno.h>
+#include <libgen.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/limits.h>
+#include <linux/magic.h>
+#include <sys/mount.h>
+#include <sys/types.h>
+#include <sys/vfs.h>
+
+#include <bpf.h>
+
+#include "main.h"
+
+static bool is_bpffs(char *path)
+{
+	struct statfs st_fs;
+
+	if (statfs(path, &st_fs) < 0)
+		return false;
+
+	return (unsigned long)st_fs.f_type == BPF_FS_MAGIC;
+}
+
+static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
+{
+	bool bind_done = false;
+
+	while (mount("", target, "none", MS_PRIVATE | MS_REC, NULL)) {
+		if (errno != EINVAL || bind_done) {
+			snprintf(buff, bufflen,
+				 "mount --make-private %s failed: %s",
+				 target, strerror(errno));
+			return -1;
+		}
+
+		if (mount(target, target, "none", MS_BIND, NULL)) {
+			snprintf(buff, bufflen,
+				 "mount --bind %s %s failed: %s",
+				 target, target, strerror(errno));
+			return -1;
+		}
+
+		bind_done = true;
+	}
+
+	if (mount("bpf", target, "bpf", 0, "mode=0700")) {
+		snprintf(buff, bufflen, "mount -t bpf bpf %s failed: %s",
+			 target, strerror(errno));
+		return -1;
+	}
+
+	return 0;
+}
+
+int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
+{
+	enum bpf_obj_type type;
+	int fd;
+
+	fd = bpf_obj_get(path);
+	if (fd < 0) {
+		p_err("bpf obj get (%s): %s", path,
+		      errno == EACCES && !is_bpffs(dirname(path)) ?
+		    "directory not in bpf file system (bpffs)" :
+		    strerror(errno));
+		return -1;
+	}
+
+	type = get_fd_type(fd);
+	if (type < 0) {
+		close(fd);
+		return type;
+	}
+	if (type != exp_type) {
+		p_err("incorrect object type: %s", get_fd_type_name(type));
+		close(fd);
+		return -1;
+	}
+
+	return fd;
+}
+
+int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
+{
+	char err_str[ERR_MAX_LEN];
+	unsigned int id;
+	char *endptr;
+	char *file;
+	char *dir;
+	int err;
+	int fd;
+
+	if (!is_prefix(*argv, "id")) {
+		p_err("expected 'id' got %s", *argv);
+		return -1;
+	}
+	NEXT_ARG();
+
+	id = strtoul(*argv, &endptr, 0);
+	if (*endptr) {
+		p_err("can't parse %s as ID", *argv);
+		return -1;
+	}
+	NEXT_ARG();
+
+	if (argc != 1)
+		usage();
+
+	fd = get_fd_by_id(id);
+	if (fd < 0) {
+		p_err("can't get prog by id (%u): %s", id, strerror(errno));
+		return -1;
+	}
+
+	err = bpf_obj_pin(fd, *argv);
+	if (!err)
+		goto out_close;
+
+	file = malloc(strlen(*argv) + 1);
+	strcpy(file, *argv);
+	dir = dirname(file);
+
+	if (errno != EPERM || is_bpffs(dir)) {
+		p_err("can't pin the object (%s): %s", *argv, strerror(errno));
+		goto out_free;
+	}
+
+	/* Attempt to mount bpffs, then retry pinning. */
+	err = mnt_bpffs(dir, err_str, ERR_MAX_LEN);
+	if (!err) {
+		err = bpf_obj_pin(fd, *argv);
+		if (err)
+			p_err("can't pin the object (%s): %s", *argv,
+			      strerror(errno));
+	} else {
+		err_str[ERR_MAX_LEN - 1] = '\0';
+		p_err("can't mount BPF file system to pin the object (%s): %s",
+		      *argv, err_str);
+	}
+
+out_free:
+	free(file);
+out_close:
+	close(fd);
+	return err;
+}
+
+const char *get_fd_type_name(enum bpf_obj_type type)
+{
+	static const char * const names[] = {
+		[BPF_OBJ_UNKNOWN]	= "unknown",
+		[BPF_OBJ_PROG]		= "prog",
+		[BPF_OBJ_MAP]		= "map",
+	};
+
+	if (type < 0 || type >= ARRAY_SIZE(names) || !names[type])
+		return names[BPF_OBJ_UNKNOWN];
+
+	return names[type];
+}
+
+int get_fd_type(int fd)
+{
+	char path[PATH_MAX];
+	char buf[512];
+	ssize_t n;
+
+	snprintf(path, sizeof(path), "/proc/%d/fd/%d", getpid(), fd);
+
+	n = readlink(path, buf, sizeof(buf));
+	if (n < 0) {
+		p_err("can't read link type: %s", strerror(errno));
+		return -1;
+	}
+	if (n == sizeof(path)) {
+		p_err("can't read link type: path too long!");
+		return -1;
+	}
+
+	if (strstr(buf, "bpf-map"))
+		return BPF_OBJ_MAP;
+	else if (strstr(buf, "bpf-prog"))
+		return BPF_OBJ_PROG;
+
+	return BPF_OBJ_UNKNOWN;
+}
+
+char *get_fdinfo(int fd, const char *key)
+{
+	char path[PATH_MAX];
+	char *line = NULL;
+	size_t line_n = 0;
+	ssize_t n;
+	FILE *fdi;
+
+	snprintf(path, sizeof(path), "/proc/%d/fdinfo/%d", getpid(), fd);
+
+	fdi = fopen(path, "r");
+	if (!fdi) {
+		p_err("can't open fdinfo: %s", strerror(errno));
+		return NULL;
+	}
+
+	while ((n = getline(&line, &line_n, fdi))) {
+		char *value;
+		int len;
+
+		if (!strstr(line, key))
+			continue;
+
+		fclose(fdi);
+
+		value = strchr(line, '\t');
+		if (!value || !value[1]) {
+			p_err("malformed fdinfo!?");
+			free(line);
+			return NULL;
+		}
+		value++;
+
+		len = strlen(value);
+		memmove(line, value, len);
+		line[len - 1] = '\0';
+
+		return line;
+	}
+
+	p_err("key '%s' not found in fdinfo", key);
+	free(line);
+	fclose(fdi);
+	return NULL;
+}
+
+void print_hex_data_json(uint8_t *data, size_t len)
+{
+	unsigned int i;
+
+	jsonw_start_array(json_wtr);
+	for (i = 0; i < len; i++)
+		jsonw_printf(json_wtr, "\"0x%02hhx\"", data[i]);
+	jsonw_end_array(json_wtr);
+}
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
new file mode 100644
index 000000000000..1551d3918d4c
--- /dev/null
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -0,0 +1,162 @@
+/*
+ * Based on:
+ *
+ * Minimal BPF JIT image disassembler
+ *
+ * Disassembles BPF JIT compiler emitted opcodes back to asm insn's for
+ * debugging or verification purposes.
+ *
+ * Copyright 2013 Daniel Borkmann <daniel@iogearbox.net>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+#include <stdarg.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <unistd.h>
+#include <string.h>
+#include <bfd.h>
+#include <dis-asm.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <limits.h>
+
+#include "json_writer.h"
+#include "main.h"
+
+static void get_exec_path(char *tpath, size_t size)
+{
+	ssize_t len;
+	char *path;
+
+	snprintf(tpath, size, "/proc/%d/exe", (int) getpid());
+	tpath[size - 1] = 0;
+
+	path = strdup(tpath);
+	assert(path);
+
+	len = readlink(path, tpath, size - 1);
+	assert(len > 0);
+	tpath[len] = 0;
+
+	free(path);
+}
+
+static int oper_count;
+static int fprintf_json(void *out, const char *fmt, ...)
+{
+	va_list ap;
+	char *s;
+
+	va_start(ap, fmt);
+	if (!oper_count) {
+		int i;
+
+		s = va_arg(ap, char *);
+
+		/* Strip trailing spaces */
+		i = strlen(s) - 1;
+		while (s[i] == ' ')
+			s[i--] = '\0';
+
+		jsonw_string_field(json_wtr, "operation", s);
+		jsonw_name(json_wtr, "operands");
+		jsonw_start_array(json_wtr);
+		oper_count++;
+	} else if (!strcmp(fmt, ",")) {
+		   /* Skip */
+	} else {
+		s = va_arg(ap, char *);
+		jsonw_string(json_wtr, s);
+		oper_count++;
+	}
+	va_end(ap);
+	return 0;
+}
+
+void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes)
+{
+	disassembler_ftype disassemble;
+	struct disassemble_info info;
+	int count, i, pc = 0;
+	char tpath[PATH_MAX];
+	bfd *bfdf;
+
+	if (!len)
+		return;
+
+	memset(tpath, 0, sizeof(tpath));
+	get_exec_path(tpath, sizeof(tpath));
+
+	bfdf = bfd_openr(tpath, NULL);
+	assert(bfdf);
+	assert(bfd_check_format(bfdf, bfd_object));
+
+	if (json_output)
+		init_disassemble_info(&info, stdout,
+				      (fprintf_ftype) fprintf_json);
+	else
+		init_disassemble_info(&info, stdout,
+				      (fprintf_ftype) fprintf);
+	info.arch = bfd_get_arch(bfdf);
+	info.mach = bfd_get_mach(bfdf);
+	info.buffer = image;
+	info.buffer_length = len;
+
+	disassemble_init_for_target(&info);
+
+	disassemble = disassembler(bfdf);
+	assert(disassemble);
+
+	if (json_output)
+		jsonw_start_array(json_wtr);
+	do {
+		if (json_output) {
+			jsonw_start_object(json_wtr);
+			oper_count = 0;
+			jsonw_name(json_wtr, "pc");
+			jsonw_printf(json_wtr, "\"0x%x\"", pc);
+		} else {
+			printf("%4x:\t", pc);
+		}
+
+		count = disassemble(pc, &info);
+		if (json_output) {
+			/* Operand array, was started in fprintf_json. Before
+			 * that, make sure we have a _null_ value if no operand
+			 * other than operation code was present.
+			 */
+			if (oper_count == 1)
+				jsonw_null(json_wtr);
+			jsonw_end_array(json_wtr);
+		}
+
+		if (opcodes) {
+			if (json_output) {
+				jsonw_name(json_wtr, "opcodes");
+				jsonw_start_array(json_wtr);
+				for (i = 0; i < count; ++i)
+					jsonw_printf(json_wtr, "\"0x%02hhx\"",
+						     (uint8_t)image[pc + i]);
+				jsonw_end_array(json_wtr);
+			} else {
+				printf("\n\t");
+				for (i = 0; i < count; ++i)
+					printf("%02x ",
+					       (uint8_t)image[pc + i]);
+			}
+		}
+		if (json_output)
+			jsonw_end_object(json_wtr);
+		else
+			printf("\n");
+
+		pc += count;
+	} while (count > 0 && pc < len);
+	if (json_output)
+		jsonw_end_array(json_wtr);
+
+	bfd_close(bfdf);
+}
diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c
new file mode 100644
index 000000000000..c6eef76322ae
--- /dev/null
+++ b/tools/bpf/bpftool/json_writer.c
@@ -0,0 +1,356 @@
+/*
+ * Simple streaming JSON writer
+ *
+ * This takes care of the annoying bits of JSON syntax like the commas
+ * after elements
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Stephen Hemminger <stephen@networkplumber.org>
+ */
+
+#include <stdio.h>
+#include <stdbool.h>
+#include <stdarg.h>
+#include <assert.h>
+#include <malloc.h>
+#include <inttypes.h>
+#include <stdint.h>
+
+#include "json_writer.h"
+
+struct json_writer {
+	FILE		*out;	/* output file */
+	unsigned	depth;  /* nesting */
+	bool		pretty; /* optional whitepace */
+	char		sep;	/* either nul or comma */
+};
+
+/* indentation for pretty print */
+static void jsonw_indent(json_writer_t *self)
+{
+	unsigned i;
+	for (i = 0; i < self->depth; ++i)
+		fputs("    ", self->out);
+}
+
+/* end current line and indent if pretty printing */
+static void jsonw_eol(json_writer_t *self)
+{
+	if (!self->pretty)
+		return;
+
+	putc('\n', self->out);
+	jsonw_indent(self);
+}
+
+/* If current object is not empty print a comma */
+static void jsonw_eor(json_writer_t *self)
+{
+	if (self->sep != '\0')
+		putc(self->sep, self->out);
+	self->sep = ',';
+}
+
+
+/* Output JSON encoded string */
+/* Handles C escapes, does not do Unicode */
+static void jsonw_puts(json_writer_t *self, const char *str)
+{
+	putc('"', self->out);
+	for (; *str; ++str)
+		switch (*str) {
+		case '\t':
+			fputs("\\t", self->out);
+			break;
+		case '\n':
+			fputs("\\n", self->out);
+			break;
+		case '\r':
+			fputs("\\r", self->out);
+			break;
+		case '\f':
+			fputs("\\f", self->out);
+			break;
+		case '\b':
+			fputs("\\b", self->out);
+			break;
+		case '\\':
+			fputs("\\n", self->out);
+			break;
+		case '"':
+			fputs("\\\"", self->out);
+			break;
+		case '\'':
+			fputs("\\\'", self->out);
+			break;
+		default:
+			putc(*str, self->out);
+		}
+	putc('"', self->out);
+}
+
+/* Create a new JSON stream */
+json_writer_t *jsonw_new(FILE *f)
+{
+	json_writer_t *self = malloc(sizeof(*self));
+	if (self) {
+		self->out = f;
+		self->depth = 0;
+		self->pretty = false;
+		self->sep = '\0';
+	}
+	return self;
+}
+
+/* End output to JSON stream */
+void jsonw_destroy(json_writer_t **self_p)
+{
+	json_writer_t *self = *self_p;
+
+	assert(self->depth == 0);
+	fputs("\n", self->out);
+	fflush(self->out);
+	free(self);
+	*self_p = NULL;
+}
+
+void jsonw_pretty(json_writer_t *self, bool on)
+{
+	self->pretty = on;
+}
+
+/* Basic blocks */
+static void jsonw_begin(json_writer_t *self, int c)
+{
+	jsonw_eor(self);
+	putc(c, self->out);
+	++self->depth;
+	self->sep = '\0';
+}
+
+static void jsonw_end(json_writer_t *self, int c)
+{
+	assert(self->depth > 0);
+
+	--self->depth;
+	if (self->sep != '\0')
+		jsonw_eol(self);
+	putc(c, self->out);
+	self->sep = ',';
+}
+
+
+/* Add a JSON property name */
+void jsonw_name(json_writer_t *self, const char *name)
+{
+	jsonw_eor(self);
+	jsonw_eol(self);
+	self->sep = '\0';
+	jsonw_puts(self, name);
+	putc(':', self->out);
+	if (self->pretty)
+		putc(' ', self->out);
+}
+
+void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap)
+{
+	jsonw_eor(self);
+	putc('"', self->out);
+	vfprintf(self->out, fmt, ap);
+	putc('"', self->out);
+}
+
+void jsonw_printf(json_writer_t *self, const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	jsonw_eor(self);
+	vfprintf(self->out, fmt, ap);
+	va_end(ap);
+}
+
+/* Collections */
+void jsonw_start_object(json_writer_t *self)
+{
+	jsonw_begin(self, '{');
+}
+
+void jsonw_end_object(json_writer_t *self)
+{
+	jsonw_end(self, '}');
+}
+
+void jsonw_start_array(json_writer_t *self)
+{
+	jsonw_begin(self, '[');
+}
+
+void jsonw_end_array(json_writer_t *self)
+{
+	jsonw_end(self, ']');
+}
+
+/* JSON value types */
+void jsonw_string(json_writer_t *self, const char *value)
+{
+	jsonw_eor(self);
+	jsonw_puts(self, value);
+}
+
+void jsonw_bool(json_writer_t *self, bool val)
+{
+	jsonw_printf(self, "%s", val ? "true" : "false");
+}
+
+void jsonw_null(json_writer_t *self)
+{
+	jsonw_printf(self, "null");
+}
+
+void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num)
+{
+	jsonw_printf(self, fmt, num);
+}
+
+#ifdef notused
+void jsonw_float(json_writer_t *self, double num)
+{
+	jsonw_printf(self, "%g", num);
+}
+#endif
+
+void jsonw_hu(json_writer_t *self, unsigned short num)
+{
+	jsonw_printf(self, "%hu", num);
+}
+
+void jsonw_uint(json_writer_t *self, uint64_t num)
+{
+	jsonw_printf(self, "%"PRIu64, num);
+}
+
+void jsonw_lluint(json_writer_t *self, unsigned long long int num)
+{
+	jsonw_printf(self, "%llu", num);
+}
+
+void jsonw_int(json_writer_t *self, int64_t num)
+{
+	jsonw_printf(self, "%"PRId64, num);
+}
+
+/* Basic name/value objects */
+void jsonw_string_field(json_writer_t *self, const char *prop, const char *val)
+{
+	jsonw_name(self, prop);
+	jsonw_string(self, val);
+}
+
+void jsonw_bool_field(json_writer_t *self, const char *prop, bool val)
+{
+	jsonw_name(self, prop);
+	jsonw_bool(self, val);
+}
+
+#ifdef notused
+void jsonw_float_field(json_writer_t *self, const char *prop, double val)
+{
+	jsonw_name(self, prop);
+	jsonw_float(self, val);
+}
+#endif
+
+void jsonw_float_field_fmt(json_writer_t *self,
+			   const char *prop,
+			   const char *fmt,
+			   double val)
+{
+	jsonw_name(self, prop);
+	jsonw_float_fmt(self, fmt, val);
+}
+
+void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num)
+{
+	jsonw_name(self, prop);
+	jsonw_uint(self, num);
+}
+
+void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num)
+{
+	jsonw_name(self, prop);
+	jsonw_hu(self, num);
+}
+
+void jsonw_lluint_field(json_writer_t *self,
+			const char *prop,
+			unsigned long long int num)
+{
+	jsonw_name(self, prop);
+	jsonw_lluint(self, num);
+}
+
+void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num)
+{
+	jsonw_name(self, prop);
+	jsonw_int(self, num);
+}
+
+void jsonw_null_field(json_writer_t *self, const char *prop)
+{
+	jsonw_name(self, prop);
+	jsonw_null(self);
+}
+
+#ifdef TEST
+int main(int argc, char **argv)
+{
+	json_writer_t *wr = jsonw_new(stdout);
+
+	jsonw_start_object(wr);
+	jsonw_pretty(wr, true);
+	jsonw_name(wr, "Vyatta");
+	jsonw_start_object(wr);
+	jsonw_string_field(wr, "url", "http://vyatta.com");
+	jsonw_uint_field(wr, "downloads", 2000000ul);
+	jsonw_float_field(wr, "stock", 8.16);
+
+	jsonw_name(wr, "ARGV");
+	jsonw_start_array(wr);
+	while (--argc)
+		jsonw_string(wr, *++argv);
+	jsonw_end_array(wr);
+
+	jsonw_name(wr, "empty");
+	jsonw_start_array(wr);
+	jsonw_end_array(wr);
+
+	jsonw_name(wr, "NIL");
+	jsonw_start_object(wr);
+	jsonw_end_object(wr);
+
+	jsonw_null_field(wr, "my_null");
+
+	jsonw_name(wr, "special chars");
+	jsonw_start_array(wr);
+	jsonw_string_field(wr, "slash", "/");
+	jsonw_string_field(wr, "newline", "\n");
+	jsonw_string_field(wr, "tab", "\t");
+	jsonw_string_field(wr, "ff", "\f");
+	jsonw_string_field(wr, "quote", "\"");
+	jsonw_string_field(wr, "tick", "\'");
+	jsonw_string_field(wr, "backslash", "\\");
+	jsonw_end_array(wr);
+
+	jsonw_end_object(wr);
+
+	jsonw_end_object(wr);
+	jsonw_destroy(&wr);
+	return 0;
+}
+
+#endif
diff --git a/tools/bpf/bpftool/json_writer.h b/tools/bpf/bpftool/json_writer.h
new file mode 100644
index 000000000000..0fa2fb1b6351
--- /dev/null
+++ b/tools/bpf/bpftool/json_writer.h
@@ -0,0 +1,72 @@
+/*
+ * Simple streaming JSON writer
+ *
+ * This takes care of the annoying bits of JSON syntax like the commas
+ * after elements
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Stephen Hemminger <stephen@networkplumber.org>
+ */
+
+#ifndef _JSON_WRITER_H_
+#define _JSON_WRITER_H_
+
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdarg.h>
+
+/* Opaque class structure */
+typedef struct json_writer json_writer_t;
+
+/* Create a new JSON stream */
+json_writer_t *jsonw_new(FILE *f);
+/* End output to JSON stream */
+void jsonw_destroy(json_writer_t **self_p);
+
+/* Cause output to have pretty whitespace */
+void jsonw_pretty(json_writer_t *self, bool on);
+
+/* Add property name */
+void jsonw_name(json_writer_t *self, const char *name);
+
+/* Add value  */
+void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap);
+void jsonw_printf(json_writer_t *self, const char *fmt, ...);
+void jsonw_string(json_writer_t *self, const char *value);
+void jsonw_bool(json_writer_t *self, bool value);
+void jsonw_float(json_writer_t *self, double number);
+void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num);
+void jsonw_uint(json_writer_t *self, uint64_t number);
+void jsonw_hu(json_writer_t *self, unsigned short number);
+void jsonw_int(json_writer_t *self, int64_t number);
+void jsonw_null(json_writer_t *self);
+void jsonw_lluint(json_writer_t *self, unsigned long long int num);
+
+/* Useful Combinations of name and value */
+void jsonw_string_field(json_writer_t *self, const char *prop, const char *val);
+void jsonw_bool_field(json_writer_t *self, const char *prop, bool value);
+void jsonw_float_field(json_writer_t *self, const char *prop, double num);
+void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num);
+void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num);
+void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num);
+void jsonw_null_field(json_writer_t *self, const char *prop);
+void jsonw_lluint_field(json_writer_t *self, const char *prop,
+			unsigned long long int num);
+void jsonw_float_field_fmt(json_writer_t *self, const char *prop,
+			   const char *fmt, double val);
+
+/* Collections */
+void jsonw_start_object(json_writer_t *self);
+void jsonw_end_object(json_writer_t *self);
+
+void jsonw_start_array(json_writer_t *self);
+void jsonw_end_array(json_writer_t *self);
+
+/* Override default exception handling */
+typedef void (jsonw_err_handler_fn)(const char *);
+
+#endif /* _JSON_WRITER_H_ */
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
new file mode 100644
index 000000000000..78d9afb74ef4
--- /dev/null
+++ b/tools/bpf/bpftool/main.c
@@ -0,0 +1,315 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#include <bfd.h>
+#include <ctype.h>
+#include <errno.h>
+#include <getopt.h>
+#include <linux/bpf.h>
+#include <linux/version.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <bpf.h>
+
+#include "main.h"
+
+const char *bin_name;
+static int last_argc;
+static char **last_argv;
+static int (*last_do_help)(int argc, char **argv);
+json_writer_t *json_wtr;
+bool pretty_output;
+bool json_output;
+
+void usage(void)
+{
+	last_do_help(last_argc - 1, last_argv + 1);
+
+	exit(-1);
+}
+
+static int do_help(int argc, char **argv)
+{
+	if (json_output) {
+		jsonw_null(json_wtr);
+		return 0;
+	}
+
+	fprintf(stderr,
+		"Usage: %s [OPTIONS] OBJECT { COMMAND | help }\n"
+		"       %s batch file FILE\n"
+		"       %s version\n"
+		"\n"
+		"       OBJECT := { prog | map }\n"
+		"       " HELP_SPEC_OPTIONS "\n"
+		"",
+		bin_name, bin_name, bin_name);
+
+	return 0;
+}
+
+static int do_version(int argc, char **argv)
+{
+	unsigned int version[3];
+
+	version[0] = LINUX_VERSION_CODE >> 16;
+	version[1] = LINUX_VERSION_CODE >> 8 & 0xf;
+	version[2] = LINUX_VERSION_CODE & 0xf;
+
+	if (json_output) {
+		jsonw_start_object(json_wtr);
+		jsonw_name(json_wtr, "version");
+		jsonw_printf(json_wtr, "\"%u.%u.%u\"",
+			     version[0], version[1], version[2]);
+		jsonw_end_object(json_wtr);
+	} else {
+		printf("%s v%u.%u.%u\n", bin_name,
+		       version[0], version[1], version[2]);
+	}
+	return 0;
+}
+
+int cmd_select(const struct cmd *cmds, int argc, char **argv,
+	       int (*help)(int argc, char **argv))
+{
+	unsigned int i;
+
+	last_argc = argc;
+	last_argv = argv;
+	last_do_help = help;
+
+	if (argc < 1 && cmds[0].func)
+		return cmds[0].func(argc, argv);
+
+	for (i = 0; cmds[i].func; i++)
+		if (is_prefix(*argv, cmds[i].cmd))
+			return cmds[i].func(argc - 1, argv + 1);
+
+	help(argc - 1, argv + 1);
+
+	return -1;
+}
+
+bool is_prefix(const char *pfx, const char *str)
+{
+	if (!pfx)
+		return false;
+	if (strlen(str) < strlen(pfx))
+		return false;
+
+	return !memcmp(str, pfx, strlen(pfx));
+}
+
+void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep)
+{
+	unsigned char *data = arg;
+	unsigned int i;
+
+	for (i = 0; i < n; i++) {
+		const char *pfx = "";
+
+		if (!i)
+			/* nothing */;
+		else if (!(i % 16))
+			fprintf(f, "\n");
+		else if (!(i % 8))
+			fprintf(f, "  ");
+		else
+			pfx = sep;
+
+		fprintf(f, "%s%02hhx", i ? pfx : "", data[i]);
+	}
+}
+
+static int do_batch(int argc, char **argv);
+
+static const struct cmd cmds[] = {
+	{ "help",	do_help },
+	{ "batch",	do_batch },
+	{ "prog",	do_prog },
+	{ "map",	do_map },
+	{ "version",	do_version },
+	{ 0 }
+};
+
+static int do_batch(int argc, char **argv)
+{
+	unsigned int lines = 0;
+	char *n_argv[4096];
+	char buf[65536];
+	int n_argc;
+	FILE *fp;
+	int err;
+	int i;
+
+	if (argc < 2) {
+		p_err("too few parameters for batch");
+		return -1;
+	} else if (!is_prefix(*argv, "file")) {
+		p_err("expected 'file', got: %s", *argv);
+		return -1;
+	} else if (argc > 2) {
+		p_err("too many parameters for batch");
+		return -1;
+	}
+	NEXT_ARG();
+
+	fp = fopen(*argv, "r");
+	if (!fp) {
+		p_err("Can't open file (%s): %s", *argv, strerror(errno));
+		return -1;
+	}
+
+	if (json_output)
+		jsonw_start_array(json_wtr);
+	while (fgets(buf, sizeof(buf), fp)) {
+		if (strlen(buf) == sizeof(buf) - 1) {
+			errno = E2BIG;
+			break;
+		}
+
+		n_argc = 0;
+		n_argv[n_argc] = strtok(buf, " \t\n");
+
+		while (n_argv[n_argc]) {
+			n_argc++;
+			if (n_argc == ARRAY_SIZE(n_argv)) {
+				p_err("line %d has too many arguments, skip",
+				      lines);
+				n_argc = 0;
+				break;
+			}
+			n_argv[n_argc] = strtok(NULL, " \t\n");
+		}
+
+		if (!n_argc)
+			continue;
+
+		if (json_output) {
+			jsonw_start_object(json_wtr);
+			jsonw_name(json_wtr, "command");
+			jsonw_start_array(json_wtr);
+			for (i = 0; i < n_argc; i++)
+				jsonw_string(json_wtr, n_argv[i]);
+			jsonw_end_array(json_wtr);
+			jsonw_name(json_wtr, "output");
+		}
+
+		err = cmd_select(cmds, n_argc, n_argv, do_help);
+
+		if (json_output)
+			jsonw_end_object(json_wtr);
+
+		if (err)
+			goto err_close;
+
+		lines++;
+	}
+
+	if (errno && errno != ENOENT) {
+		perror("reading batch file failed");
+		err = -1;
+	} else {
+		p_info("processed %d lines", lines);
+		err = 0;
+	}
+err_close:
+	fclose(fp);
+
+	if (json_output)
+		jsonw_end_array(json_wtr);
+
+	return err;
+}
+
+int main(int argc, char **argv)
+{
+	static const struct option options[] = {
+		{ "json",	no_argument,	NULL,	'j' },
+		{ "help",	no_argument,	NULL,	'h' },
+		{ "pretty",	no_argument,	NULL,	'p' },
+		{ "version",	no_argument,	NULL,	'V' },
+		{ 0 }
+	};
+	int opt, ret;
+
+	last_do_help = do_help;
+	pretty_output = false;
+	json_output = false;
+	bin_name = argv[0];
+
+	while ((opt = getopt_long(argc, argv, "Vhpj",
+				  options, NULL)) >= 0) {
+		switch (opt) {
+		case 'V':
+			return do_version(argc, argv);
+		case 'h':
+			return do_help(argc, argv);
+		case 'p':
+			pretty_output = true;
+			/* fall through */
+		case 'j':
+			json_output = true;
+			break;
+		default:
+			usage();
+		}
+	}
+
+	argc -= optind;
+	argv += optind;
+	if (argc < 0)
+		usage();
+
+	if (json_output) {
+		json_wtr = jsonw_new(stdout);
+		if (!json_wtr) {
+			p_err("failed to create JSON writer");
+			return -1;
+		}
+		jsonw_pretty(json_wtr, pretty_output);
+	}
+
+	bfd_init();
+
+	ret = cmd_select(cmds, argc, argv, do_help);
+
+	if (json_output)
+		jsonw_destroy(&json_wtr);
+
+	return ret;
+}
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
new file mode 100644
index 000000000000..d315d01be645
--- /dev/null
+++ b/tools/bpf/bpftool/main.h
@@ -0,0 +1,131 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#ifndef __BPF_TOOL_H
+#define __BPF_TOOL_H
+
+/* BFD and kernel.h both define GCC_VERSION, differently */
+#undef GCC_VERSION
+#include <stdbool.h>
+#include <stdio.h>
+#include <linux/bpf.h>
+#include <linux/kernel.h>
+
+#include "json_writer.h"
+
+#define ptr_to_u64(ptr)	((__u64)(unsigned long)(ptr))
+
+#define NEXT_ARG()	({ argc--; argv++; if (argc < 0) usage(); })
+#define NEXT_ARGP()	({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
+#define BAD_ARG()	({ p_err("what is '%s'?\n", *argv); -1; })
+
+#define ERR_MAX_LEN	1024
+
+#define BPF_TAG_FMT	"%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx"
+
+#define HELP_SPEC_PROGRAM						\
+	"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
+#define HELP_SPEC_OPTIONS						\
+	"OPTIONS := { {-j|--json} [{-p|--pretty}] }"
+
+enum bpf_obj_type {
+	BPF_OBJ_UNKNOWN,
+	BPF_OBJ_PROG,
+	BPF_OBJ_MAP,
+};
+
+extern const char *bin_name;
+
+extern json_writer_t *json_wtr;
+extern bool json_output;
+
+bool is_prefix(const char *pfx, const char *str);
+void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep);
+void usage(void) __attribute__((noreturn));
+
+struct cmd {
+	const char *cmd;
+	int (*func)(int argc, char **argv);
+};
+
+int cmd_select(const struct cmd *cmds, int argc, char **argv,
+	       int (*help)(int argc, char **argv));
+
+int get_fd_type(int fd);
+const char *get_fd_type_name(enum bpf_obj_type type);
+char *get_fdinfo(int fd, const char *key);
+int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type);
+int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32));
+
+int do_prog(int argc, char **arg);
+int do_map(int argc, char **arg);
+
+int prog_parse_fd(int *argc, char ***argv);
+
+void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes);
+void print_hex_data_json(uint8_t *data, size_t len);
+
+static inline void p_err(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	if (json_output) {
+		jsonw_start_object(json_wtr);
+		jsonw_name(json_wtr, "error");
+		jsonw_vprintf_enquote(json_wtr, fmt, ap);
+		jsonw_end_object(json_wtr);
+	} else {
+		fprintf(stderr, "Error: ");
+		vfprintf(stderr, fmt, ap);
+		fprintf(stderr, "\n");
+	}
+	va_end(ap);
+}
+
+static inline void p_info(const char *fmt, ...)
+{
+	va_list ap;
+
+	if (json_output)
+		return;
+
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	fprintf(stderr, "\n");
+	va_end(ap);
+}
+
+#endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
new file mode 100644
index 000000000000..e978ab23a77f
--- /dev/null
+++ b/tools/bpf/bpftool/map.c
@@ -0,0 +1,877 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#include <assert.h>
+#include <ctype.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include <bpf.h>
+
+#include "main.h"
+
+static const char * const map_type_name[] = {
+	[BPF_MAP_TYPE_UNSPEC]		= "unspec",
+	[BPF_MAP_TYPE_HASH]		= "hash",
+	[BPF_MAP_TYPE_ARRAY]		= "array",
+	[BPF_MAP_TYPE_PROG_ARRAY]	= "prog_array",
+	[BPF_MAP_TYPE_PERF_EVENT_ARRAY]	= "perf_event_array",
+	[BPF_MAP_TYPE_PERCPU_HASH]	= "percpu_hash",
+	[BPF_MAP_TYPE_PERCPU_ARRAY]	= "percpu_array",
+	[BPF_MAP_TYPE_STACK_TRACE]	= "stack_trace",
+	[BPF_MAP_TYPE_CGROUP_ARRAY]	= "cgroup_array",
+	[BPF_MAP_TYPE_LRU_HASH]		= "lru_hash",
+	[BPF_MAP_TYPE_LRU_PERCPU_HASH]	= "lru_percpu_hash",
+	[BPF_MAP_TYPE_LPM_TRIE]		= "lpm_trie",
+	[BPF_MAP_TYPE_ARRAY_OF_MAPS]	= "array_of_maps",
+	[BPF_MAP_TYPE_HASH_OF_MAPS]	= "hash_of_maps",
+	[BPF_MAP_TYPE_DEVMAP]		= "devmap",
+	[BPF_MAP_TYPE_SOCKMAP]		= "sockmap",
+};
+
+static unsigned int get_possible_cpus(void)
+{
+	static unsigned int result;
+	char buf[128];
+	long int n;
+	char *ptr;
+	int fd;
+
+	if (result)
+		return result;
+
+	fd = open("/sys/devices/system/cpu/possible", O_RDONLY);
+	if (fd < 0) {
+		p_err("can't open sysfs possible cpus");
+		exit(-1);
+	}
+
+	n = read(fd, buf, sizeof(buf));
+	if (n < 2) {
+		p_err("can't read sysfs possible cpus");
+		exit(-1);
+	}
+	close(fd);
+
+	if (n == sizeof(buf)) {
+		p_err("read sysfs possible cpus overflow");
+		exit(-1);
+	}
+
+	ptr = buf;
+	n = 0;
+	while (*ptr && *ptr != '\n') {
+		unsigned int a, b;
+
+		if (sscanf(ptr, "%u-%u", &a, &b) == 2) {
+			n += b - a + 1;
+
+			ptr = strchr(ptr, '-') + 1;
+		} else if (sscanf(ptr, "%u", &a) == 1) {
+			n++;
+		} else {
+			assert(0);
+		}
+
+		while (isdigit(*ptr))
+			ptr++;
+		if (*ptr == ',')
+			ptr++;
+	}
+
+	result = n;
+
+	return result;
+}
+
+static bool map_is_per_cpu(__u32 type)
+{
+	return type == BPF_MAP_TYPE_PERCPU_HASH ||
+	       type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+	       type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
+static bool map_is_map_of_maps(__u32 type)
+{
+	return type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+	       type == BPF_MAP_TYPE_HASH_OF_MAPS;
+}
+
+static bool map_is_map_of_progs(__u32 type)
+{
+	return type == BPF_MAP_TYPE_PROG_ARRAY;
+}
+
+static void *alloc_value(struct bpf_map_info *info)
+{
+	if (map_is_per_cpu(info->type))
+		return malloc(info->value_size * get_possible_cpus());
+	else
+		return malloc(info->value_size);
+}
+
+static int map_parse_fd(int *argc, char ***argv)
+{
+	int fd;
+
+	if (is_prefix(**argv, "id")) {
+		unsigned int id;
+		char *endptr;
+
+		NEXT_ARGP();
+
+		id = strtoul(**argv, &endptr, 0);
+		if (*endptr) {
+			p_err("can't parse %s as ID", **argv);
+			return -1;
+		}
+		NEXT_ARGP();
+
+		fd = bpf_map_get_fd_by_id(id);
+		if (fd < 0)
+			p_err("get map by id (%u): %s", id, strerror(errno));
+		return fd;
+	} else if (is_prefix(**argv, "pinned")) {
+		char *path;
+
+		NEXT_ARGP();
+
+		path = **argv;
+		NEXT_ARGP();
+
+		return open_obj_pinned_any(path, BPF_OBJ_MAP);
+	}
+
+	p_err("expected 'id' or 'pinned', got: '%s'?", **argv);
+	return -1;
+}
+
+static int
+map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
+{
+	int err;
+	int fd;
+
+	fd = map_parse_fd(argc, argv);
+	if (fd < 0)
+		return -1;
+
+	err = bpf_obj_get_info_by_fd(fd, info, info_len);
+	if (err) {
+		p_err("can't get map info: %s", strerror(errno));
+		close(fd);
+		return err;
+	}
+
+	return fd;
+}
+
+static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
+			     unsigned char *value)
+{
+	jsonw_start_object(json_wtr);
+
+	if (!map_is_per_cpu(info->type)) {
+		jsonw_name(json_wtr, "key");
+		print_hex_data_json(key, info->key_size);
+		jsonw_name(json_wtr, "value");
+		print_hex_data_json(value, info->value_size);
+	} else {
+		unsigned int i, n;
+
+		n = get_possible_cpus();
+
+		jsonw_name(json_wtr, "key");
+		print_hex_data_json(key, info->key_size);
+
+		jsonw_name(json_wtr, "values");
+		jsonw_start_array(json_wtr);
+		for (i = 0; i < n; i++) {
+			jsonw_start_object(json_wtr);
+
+			jsonw_int_field(json_wtr, "cpu", i);
+
+			jsonw_name(json_wtr, "value");
+			print_hex_data_json(value + i * info->value_size,
+					    info->value_size);
+
+			jsonw_end_object(json_wtr);
+		}
+		jsonw_end_array(json_wtr);
+	}
+
+	jsonw_end_object(json_wtr);
+}
+
+static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
+			      unsigned char *value)
+{
+	if (!map_is_per_cpu(info->type)) {
+		bool single_line, break_names;
+
+		break_names = info->key_size > 16 || info->value_size > 16;
+		single_line = info->key_size + info->value_size <= 24 &&
+			!break_names;
+
+		printf("key:%c", break_names ? '\n' : ' ');
+		fprint_hex(stdout, key, info->key_size, " ");
+
+		printf(single_line ? "  " : "\n");
+
+		printf("value:%c", break_names ? '\n' : ' ');
+		fprint_hex(stdout, value, info->value_size, " ");
+
+		printf("\n");
+	} else {
+		unsigned int i, n;
+
+		n = get_possible_cpus();
+
+		printf("key:\n");
+		fprint_hex(stdout, key, info->key_size, " ");
+		printf("\n");
+		for (i = 0; i < n; i++) {
+			printf("value (CPU %02d):%c",
+			       i, info->value_size > 16 ? '\n' : ' ');
+			fprint_hex(stdout, value + i * info->value_size,
+				   info->value_size, " ");
+			printf("\n");
+		}
+	}
+}
+
+static char **parse_bytes(char **argv, const char *name, unsigned char *val,
+			  unsigned int n)
+{
+	unsigned int i = 0;
+	char *endptr;
+
+	while (i < n && argv[i]) {
+		val[i] = strtoul(argv[i], &endptr, 0);
+		if (*endptr) {
+			p_err("error parsing byte: %s", argv[i]);
+			return NULL;
+		}
+		i++;
+	}
+
+	if (i != n) {
+		p_err("%s expected %d bytes got %d", name, n, i);
+		return NULL;
+	}
+
+	return argv + i;
+}
+
+static int parse_elem(char **argv, struct bpf_map_info *info,
+		      void *key, void *value, __u32 key_size, __u32 value_size,
+		      __u32 *flags, __u32 **value_fd)
+{
+	if (!*argv) {
+		if (!key && !value)
+			return 0;
+		p_err("did not find %s", key ? "key" : "value");
+		return -1;
+	}
+
+	if (is_prefix(*argv, "key")) {
+		if (!key) {
+			if (key_size)
+				p_err("duplicate key");
+			else
+				p_err("unnecessary key");
+			return -1;
+		}
+
+		argv = parse_bytes(argv + 1, "key", key, key_size);
+		if (!argv)
+			return -1;
+
+		return parse_elem(argv, info, NULL, value, key_size, value_size,
+				  flags, value_fd);
+	} else if (is_prefix(*argv, "value")) {
+		int fd;
+
+		if (!value) {
+			if (value_size)
+				p_err("duplicate value");
+			else
+				p_err("unnecessary value");
+			return -1;
+		}
+
+		argv++;
+
+		if (map_is_map_of_maps(info->type)) {
+			int argc = 2;
+
+			if (value_size != 4) {
+				p_err("value smaller than 4B for map in map?");
+				return -1;
+			}
+			if (!argv[0] || !argv[1]) {
+				p_err("not enough value arguments for map in map");
+				return -1;
+			}
+
+			fd = map_parse_fd(&argc, &argv);
+			if (fd < 0)
+				return -1;
+
+			*value_fd = value;
+			**value_fd = fd;
+		} else if (map_is_map_of_progs(info->type)) {
+			int argc = 2;
+
+			if (value_size != 4) {
+				p_err("value smaller than 4B for map of progs?");
+				return -1;
+			}
+			if (!argv[0] || !argv[1]) {
+				p_err("not enough value arguments for map of progs");
+				return -1;
+			}
+
+			fd = prog_parse_fd(&argc, &argv);
+			if (fd < 0)
+				return -1;
+
+			*value_fd = value;
+			**value_fd = fd;
+		} else {
+			argv = parse_bytes(argv, "value", value, value_size);
+			if (!argv)
+				return -1;
+		}
+
+		return parse_elem(argv, info, key, NULL, key_size, value_size,
+				  flags, NULL);
+	} else if (is_prefix(*argv, "any") || is_prefix(*argv, "noexist") ||
+		   is_prefix(*argv, "exist")) {
+		if (!flags) {
+			p_err("flags specified multiple times: %s", *argv);
+			return -1;
+		}
+
+		if (is_prefix(*argv, "any"))
+			*flags = BPF_ANY;
+		else if (is_prefix(*argv, "noexist"))
+			*flags = BPF_NOEXIST;
+		else if (is_prefix(*argv, "exist"))
+			*flags = BPF_EXIST;
+
+		return parse_elem(argv + 1, info, key, value, key_size,
+				  value_size, NULL, value_fd);
+	}
+
+	p_err("expected key or value, got: %s", *argv);
+	return -1;
+}
+
+static int show_map_close_json(int fd, struct bpf_map_info *info)
+{
+	char *memlock;
+
+	memlock = get_fdinfo(fd, "memlock");
+	close(fd);
+
+	jsonw_start_object(json_wtr);
+
+	jsonw_uint_field(json_wtr, "id", info->id);
+	if (info->type < ARRAY_SIZE(map_type_name))
+		jsonw_string_field(json_wtr, "type",
+				   map_type_name[info->type]);
+	else
+		jsonw_uint_field(json_wtr, "type", info->type);
+
+	if (*info->name)
+		jsonw_string_field(json_wtr, "name", info->name);
+
+	jsonw_name(json_wtr, "flags");
+	jsonw_printf(json_wtr, "%#x", info->map_flags);
+	jsonw_uint_field(json_wtr, "bytes_key", info->key_size);
+	jsonw_uint_field(json_wtr, "bytes_value", info->value_size);
+	jsonw_uint_field(json_wtr, "max_entries", info->max_entries);
+
+	if (memlock)
+		jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock));
+	free(memlock);
+
+	jsonw_end_object(json_wtr);
+
+	return 0;
+}
+
+static int show_map_close_plain(int fd, struct bpf_map_info *info)
+{
+	char *memlock;
+
+	memlock = get_fdinfo(fd, "memlock");
+	close(fd);
+
+	printf("%u: ", info->id);
+	if (info->type < ARRAY_SIZE(map_type_name))
+		printf("%s  ", map_type_name[info->type]);
+	else
+		printf("type %u  ", info->type);
+
+	if (*info->name)
+		printf("name %s  ", info->name);
+
+	printf("flags 0x%x\n", info->map_flags);
+	printf("\tkey %uB  value %uB  max_entries %u",
+	       info->key_size, info->value_size, info->max_entries);
+
+	if (memlock)
+		printf("  memlock %sB", memlock);
+	free(memlock);
+
+	printf("\n");
+
+	return 0;
+}
+
+static int do_show(int argc, char **argv)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	__u32 id = 0;
+	int err;
+	int fd;
+
+	if (argc == 2) {
+		fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+		if (fd < 0)
+			return -1;
+
+		if (json_output)
+			return show_map_close_json(fd, &info);
+		else
+			return show_map_close_plain(fd, &info);
+	}
+
+	if (argc)
+		return BAD_ARG();
+
+	if (json_output)
+		jsonw_start_array(json_wtr);
+	while (true) {
+		err = bpf_map_get_next_id(id, &id);
+		if (err) {
+			if (errno == ENOENT)
+				break;
+			p_err("can't get next map: %s%s", strerror(errno),
+			      errno == EINVAL ? " -- kernel too old?" : "");
+			return -1;
+		}
+
+		fd = bpf_map_get_fd_by_id(id);
+		if (fd < 0) {
+			p_err("can't get map by id (%u): %s",
+			      id, strerror(errno));
+			return -1;
+		}
+
+		err = bpf_obj_get_info_by_fd(fd, &info, &len);
+		if (err) {
+			p_err("can't get map info: %s", strerror(errno));
+			close(fd);
+			return -1;
+		}
+
+		if (json_output)
+			show_map_close_json(fd, &info);
+		else
+			show_map_close_plain(fd, &info);
+	}
+	if (json_output)
+		jsonw_end_array(json_wtr);
+
+	return errno == ENOENT ? 0 : -1;
+}
+
+static int do_dump(int argc, char **argv)
+{
+	void *key, *value, *prev_key;
+	unsigned int num_elems = 0;
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	int err;
+	int fd;
+
+	if (argc != 2)
+		usage();
+
+	fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+	if (fd < 0)
+		return -1;
+
+	if (map_is_map_of_maps(info.type) || map_is_map_of_progs(info.type)) {
+		p_err("Dumping maps of maps and program maps not supported");
+		close(fd);
+		return -1;
+	}
+
+	key = malloc(info.key_size);
+	value = alloc_value(&info);
+	if (!key || !value) {
+		p_err("mem alloc failed");
+		err = -1;
+		goto exit_free;
+	}
+
+	prev_key = NULL;
+	if (json_output)
+		jsonw_start_array(json_wtr);
+	while (true) {
+		err = bpf_map_get_next_key(fd, prev_key, key);
+		if (err) {
+			if (errno == ENOENT)
+				err = 0;
+			break;
+		}
+
+		if (!bpf_map_lookup_elem(fd, key, value)) {
+			if (json_output)
+				print_entry_json(&info, key, value);
+			else
+				print_entry_plain(&info, key, value);
+		} else {
+			if (json_output) {
+				jsonw_name(json_wtr, "key");
+				print_hex_data_json(key, info.key_size);
+				jsonw_name(json_wtr, "value");
+				jsonw_start_object(json_wtr);
+				jsonw_string_field(json_wtr, "error",
+						   "can't lookup element");
+				jsonw_end_object(json_wtr);
+			} else {
+				p_info("can't lookup element with key: ");
+				fprint_hex(stderr, key, info.key_size, " ");
+				fprintf(stderr, "\n");
+			}
+		}
+
+		prev_key = key;
+		num_elems++;
+	}
+
+	if (json_output)
+		jsonw_end_array(json_wtr);
+	else
+		printf("Found %u element%s\n", num_elems,
+		       num_elems != 1 ? "s" : "");
+
+exit_free:
+	free(key);
+	free(value);
+	close(fd);
+
+	return err;
+}
+
+static int do_update(int argc, char **argv)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	__u32 *value_fd = NULL;
+	__u32 flags = BPF_ANY;
+	void *key, *value;
+	int fd, err;
+
+	if (argc < 2)
+		usage();
+
+	fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+	if (fd < 0)
+		return -1;
+
+	key = malloc(info.key_size);
+	value = alloc_value(&info);
+	if (!key || !value) {
+		p_err("mem alloc failed");
+		err = -1;
+		goto exit_free;
+	}
+
+	err = parse_elem(argv, &info, key, value, info.key_size,
+			 info.value_size, &flags, &value_fd);
+	if (err)
+		goto exit_free;
+
+	err = bpf_map_update_elem(fd, key, value, flags);
+	if (err) {
+		p_err("update failed: %s", strerror(errno));
+		goto exit_free;
+	}
+
+exit_free:
+	if (value_fd)
+		close(*value_fd);
+	free(key);
+	free(value);
+	close(fd);
+
+	if (!err && json_output)
+		jsonw_null(json_wtr);
+	return err;
+}
+
+static int do_lookup(int argc, char **argv)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	void *key, *value;
+	int err;
+	int fd;
+
+	if (argc < 2)
+		usage();
+
+	fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+	if (fd < 0)
+		return -1;
+
+	key = malloc(info.key_size);
+	value = alloc_value(&info);
+	if (!key || !value) {
+		p_err("mem alloc failed");
+		err = -1;
+		goto exit_free;
+	}
+
+	err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL);
+	if (err)
+		goto exit_free;
+
+	err = bpf_map_lookup_elem(fd, key, value);
+	if (!err) {
+		if (json_output)
+			print_entry_json(&info, key, value);
+		else
+			print_entry_plain(&info, key, value);
+	} else if (errno == ENOENT) {
+		if (json_output) {
+			jsonw_null(json_wtr);
+		} else {
+			printf("key:\n");
+			fprint_hex(stdout, key, info.key_size, " ");
+			printf("\n\nNot found\n");
+		}
+	} else {
+		p_err("lookup failed: %s", strerror(errno));
+	}
+
+exit_free:
+	free(key);
+	free(value);
+	close(fd);
+
+	return err;
+}
+
+static int do_getnext(int argc, char **argv)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	void *key, *nextkey;
+	int err;
+	int fd;
+
+	if (argc < 2)
+		usage();
+
+	fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+	if (fd < 0)
+		return -1;
+
+	key = malloc(info.key_size);
+	nextkey = malloc(info.key_size);
+	if (!key || !nextkey) {
+		p_err("mem alloc failed");
+		err = -1;
+		goto exit_free;
+	}
+
+	if (argc) {
+		err = parse_elem(argv, &info, key, NULL, info.key_size, 0,
+				 NULL, NULL);
+		if (err)
+			goto exit_free;
+	} else {
+		free(key);
+		key = NULL;
+	}
+
+	err = bpf_map_get_next_key(fd, key, nextkey);
+	if (err) {
+		p_err("can't get next key: %s", strerror(errno));
+		goto exit_free;
+	}
+
+	if (json_output) {
+		jsonw_start_object(json_wtr);
+		if (key) {
+			jsonw_name(json_wtr, "key");
+			print_hex_data_json(key, info.key_size);
+		} else {
+			jsonw_null_field(json_wtr, "key");
+		}
+		jsonw_name(json_wtr, "next_key");
+		print_hex_data_json(nextkey, info.key_size);
+		jsonw_end_object(json_wtr);
+	} else {
+		if (key) {
+			printf("key:\n");
+			fprint_hex(stdout, key, info.key_size, " ");
+			printf("\n");
+		} else {
+			printf("key: None\n");
+		}
+		printf("next key:\n");
+		fprint_hex(stdout, nextkey, info.key_size, " ");
+		printf("\n");
+	}
+
+exit_free:
+	free(nextkey);
+	free(key);
+	close(fd);
+
+	return err;
+}
+
+static int do_delete(int argc, char **argv)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	void *key;
+	int err;
+	int fd;
+
+	if (argc < 2)
+		usage();
+
+	fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+	if (fd < 0)
+		return -1;
+
+	key = malloc(info.key_size);
+	if (!key) {
+		p_err("mem alloc failed");
+		err = -1;
+		goto exit_free;
+	}
+
+	err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL);
+	if (err)
+		goto exit_free;
+
+	err = bpf_map_delete_elem(fd, key);
+	if (err)
+		p_err("delete failed: %s", strerror(errno));
+
+exit_free:
+	free(key);
+	close(fd);
+
+	if (!err && json_output)
+		jsonw_null(json_wtr);
+	return err;
+}
+
+static int do_pin(int argc, char **argv)
+{
+	int err;
+
+	err = do_pin_any(argc, argv, bpf_map_get_fd_by_id);
+	if (!err && json_output)
+		jsonw_null(json_wtr);
+	return err;
+}
+
+static int do_help(int argc, char **argv)
+{
+	if (json_output) {
+		jsonw_null(json_wtr);
+		return 0;
+	}
+
+	fprintf(stderr,
+		"Usage: %s %s show   [MAP]\n"
+		"       %s %s dump    MAP\n"
+		"       %s %s update  MAP  key BYTES value VALUE [UPDATE_FLAGS]\n"
+		"       %s %s lookup  MAP  key BYTES\n"
+		"       %s %s getnext MAP [key BYTES]\n"
+		"       %s %s delete  MAP  key BYTES\n"
+		"       %s %s pin     MAP  FILE\n"
+		"       %s %s help\n"
+		"\n"
+		"       MAP := { id MAP_ID | pinned FILE }\n"
+		"       " HELP_SPEC_PROGRAM "\n"
+		"       VALUE := { BYTES | MAP | PROG }\n"
+		"       UPDATE_FLAGS := { any | exist | noexist }\n"
+		"       " HELP_SPEC_OPTIONS "\n"
+		"",
+		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
+		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
+		bin_name, argv[-2], bin_name, argv[-2]);
+
+	return 0;
+}
+
+static const struct cmd cmds[] = {
+	{ "show",	do_show },
+	{ "help",	do_help },
+	{ "dump",	do_dump },
+	{ "update",	do_update },
+	{ "lookup",	do_lookup },
+	{ "getnext",	do_getnext },
+	{ "delete",	do_delete },
+	{ "pin",	do_pin },
+	{ 0 }
+};
+
+int do_map(int argc, char **argv)
+{
+	return cmd_select(cmds, argc, argv, do_help);
+}
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
new file mode 100644
index 000000000000..250f80fd46aa
--- /dev/null
+++ b/tools/bpf/bpftool/prog.c
@@ -0,0 +1,647 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include <bpf.h>
+
+#include "main.h"
+#include "disasm.h"
+
+static const char * const prog_type_name[] = {
+	[BPF_PROG_TYPE_UNSPEC]		= "unspec",
+	[BPF_PROG_TYPE_SOCKET_FILTER]	= "socket_filter",
+	[BPF_PROG_TYPE_KPROBE]		= "kprobe",
+	[BPF_PROG_TYPE_SCHED_CLS]	= "sched_cls",
+	[BPF_PROG_TYPE_SCHED_ACT]	= "sched_act",
+	[BPF_PROG_TYPE_TRACEPOINT]	= "tracepoint",
+	[BPF_PROG_TYPE_XDP]		= "xdp",
+	[BPF_PROG_TYPE_PERF_EVENT]	= "perf_event",
+	[BPF_PROG_TYPE_CGROUP_SKB]	= "cgroup_skb",
+	[BPF_PROG_TYPE_CGROUP_SOCK]	= "cgroup_sock",
+	[BPF_PROG_TYPE_LWT_IN]		= "lwt_in",
+	[BPF_PROG_TYPE_LWT_OUT]		= "lwt_out",
+	[BPF_PROG_TYPE_LWT_XMIT]	= "lwt_xmit",
+	[BPF_PROG_TYPE_SOCK_OPS]	= "sock_ops",
+	[BPF_PROG_TYPE_SK_SKB]		= "sk_skb",
+};
+
+static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
+{
+	struct timespec real_time_ts, boot_time_ts;
+	time_t wallclock_secs;
+	struct tm load_tm;
+
+	buf[--size] = '\0';
+
+	if (clock_gettime(CLOCK_REALTIME, &real_time_ts) ||
+	    clock_gettime(CLOCK_BOOTTIME, &boot_time_ts)) {
+		perror("Can't read clocks");
+		snprintf(buf, size, "%llu", nsecs / 1000000000);
+		return;
+	}
+
+	wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) +
+		nsecs / 1000000000;
+
+	if (!localtime_r(&wallclock_secs, &load_tm)) {
+		snprintf(buf, size, "%llu", nsecs / 1000000000);
+		return;
+	}
+
+	strftime(buf, size, "%b %d/%H:%M", &load_tm);
+}
+
+static int prog_fd_by_tag(unsigned char *tag)
+{
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	unsigned int id = 0;
+	int err;
+	int fd;
+
+	while (true) {
+		err = bpf_prog_get_next_id(id, &id);
+		if (err) {
+			p_err("%s", strerror(errno));
+			return -1;
+		}
+
+		fd = bpf_prog_get_fd_by_id(id);
+		if (fd < 0) {
+			p_err("can't get prog by id (%u): %s",
+			      id, strerror(errno));
+			return -1;
+		}
+
+		err = bpf_obj_get_info_by_fd(fd, &info, &len);
+		if (err) {
+			p_err("can't get prog info (%u): %s",
+			      id, strerror(errno));
+			close(fd);
+			return -1;
+		}
+
+		if (!memcmp(tag, info.tag, BPF_TAG_SIZE))
+			return fd;
+
+		close(fd);
+	}
+}
+
+int prog_parse_fd(int *argc, char ***argv)
+{
+	int fd;
+
+	if (is_prefix(**argv, "id")) {
+		unsigned int id;
+		char *endptr;
+
+		NEXT_ARGP();
+
+		id = strtoul(**argv, &endptr, 0);
+		if (*endptr) {
+			p_err("can't parse %s as ID", **argv);
+			return -1;
+		}
+		NEXT_ARGP();
+
+		fd = bpf_prog_get_fd_by_id(id);
+		if (fd < 0)
+			p_err("get by id (%u): %s", id, strerror(errno));
+		return fd;
+	} else if (is_prefix(**argv, "tag")) {
+		unsigned char tag[BPF_TAG_SIZE];
+
+		NEXT_ARGP();
+
+		if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2,
+			   tag + 3, tag + 4, tag + 5, tag + 6, tag + 7)
+		    != BPF_TAG_SIZE) {
+			p_err("can't parse tag");
+			return -1;
+		}
+		NEXT_ARGP();
+
+		return prog_fd_by_tag(tag);
+	} else if (is_prefix(**argv, "pinned")) {
+		char *path;
+
+		NEXT_ARGP();
+
+		path = **argv;
+		NEXT_ARGP();
+
+		return open_obj_pinned_any(path, BPF_OBJ_PROG);
+	}
+
+	p_err("expected 'id', 'tag' or 'pinned', got: '%s'?", **argv);
+	return -1;
+}
+
+static void show_prog_maps(int fd, u32 num_maps)
+{
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	__u32 map_ids[num_maps];
+	unsigned int i;
+	int err;
+
+	info.nr_map_ids = num_maps;
+	info.map_ids = ptr_to_u64(map_ids);
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	if (err || !info.nr_map_ids)
+		return;
+
+	if (json_output) {
+		jsonw_name(json_wtr, "map_ids");
+		jsonw_start_array(json_wtr);
+		for (i = 0; i < info.nr_map_ids; i++)
+			jsonw_uint(json_wtr, map_ids[i]);
+		jsonw_end_array(json_wtr);
+	} else {
+		printf("  map_ids ");
+		for (i = 0; i < info.nr_map_ids; i++)
+			printf("%u%s", map_ids[i],
+			       i == info.nr_map_ids - 1 ? "" : ",");
+	}
+}
+
+static void print_prog_json(struct bpf_prog_info *info, int fd)
+{
+	char *memlock;
+
+	jsonw_start_object(json_wtr);
+	jsonw_uint_field(json_wtr, "id", info->id);
+	if (info->type < ARRAY_SIZE(prog_type_name))
+		jsonw_string_field(json_wtr, "type",
+				   prog_type_name[info->type]);
+	else
+		jsonw_uint_field(json_wtr, "type", info->type);
+
+	if (*info->name)
+		jsonw_string_field(json_wtr, "name", info->name);
+
+	jsonw_name(json_wtr, "tag");
+	jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"",
+		     info->tag[0], info->tag[1], info->tag[2], info->tag[3],
+		     info->tag[4], info->tag[5], info->tag[6], info->tag[7]);
+
+	if (info->load_time) {
+		char buf[32];
+
+		print_boot_time(info->load_time, buf, sizeof(buf));
+
+		/* Piggy back on load_time, since 0 uid is a valid one */
+		jsonw_string_field(json_wtr, "loaded_at", buf);
+		jsonw_uint_field(json_wtr, "uid", info->created_by_uid);
+	}
+
+	jsonw_uint_field(json_wtr, "bytes_xlated", info->xlated_prog_len);
+
+	if (info->jited_prog_len) {
+		jsonw_bool_field(json_wtr, "jited", true);
+		jsonw_uint_field(json_wtr, "bytes_jited", info->jited_prog_len);
+	} else {
+		jsonw_bool_field(json_wtr, "jited", false);
+	}
+
+	memlock = get_fdinfo(fd, "memlock");
+	if (memlock)
+		jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock));
+	free(memlock);
+
+	if (info->nr_map_ids)
+		show_prog_maps(fd, info->nr_map_ids);
+
+	jsonw_end_object(json_wtr);
+}
+
+static void print_prog_plain(struct bpf_prog_info *info, int fd)
+{
+	char *memlock;
+
+	printf("%u: ", info->id);
+	if (info->type < ARRAY_SIZE(prog_type_name))
+		printf("%s  ", prog_type_name[info->type]);
+	else
+		printf("type %u  ", info->type);
+
+	if (*info->name)
+		printf("name %s  ", info->name);
+
+	printf("tag ");
+	fprint_hex(stdout, info->tag, BPF_TAG_SIZE, "");
+	printf("\n");
+
+	if (info->load_time) {
+		char buf[32];
+
+		print_boot_time(info->load_time, buf, sizeof(buf));
+
+		/* Piggy back on load_time, since 0 uid is a valid one */
+		printf("\tloaded_at %s  uid %u\n", buf, info->created_by_uid);
+	}
+
+	printf("\txlated %uB", info->xlated_prog_len);
+
+	if (info->jited_prog_len)
+		printf("  jited %uB", info->jited_prog_len);
+	else
+		printf("  not jited");
+
+	memlock = get_fdinfo(fd, "memlock");
+	if (memlock)
+		printf("  memlock %sB", memlock);
+	free(memlock);
+
+	if (info->nr_map_ids)
+		show_prog_maps(fd, info->nr_map_ids);
+
+	printf("\n");
+}
+
+static int show_prog(int fd)
+{
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	int err;
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	if (err) {
+		p_err("can't get prog info: %s", strerror(errno));
+		return -1;
+	}
+
+	if (json_output)
+		print_prog_json(&info, fd);
+	else
+		print_prog_plain(&info, fd);
+
+	return 0;
+}
+
+static int do_show(int argc, char **argv)
+{
+	__u32 id = 0;
+	int err;
+	int fd;
+
+	if (argc == 2) {
+		fd = prog_parse_fd(&argc, &argv);
+		if (fd < 0)
+			return -1;
+
+		return show_prog(fd);
+	}
+
+	if (argc)
+		return BAD_ARG();
+
+	if (json_output)
+		jsonw_start_array(json_wtr);
+	while (true) {
+		err = bpf_prog_get_next_id(id, &id);
+		if (err) {
+			if (errno == ENOENT) {
+				err = 0;
+				break;
+			}
+			p_err("can't get next program: %s%s", strerror(errno),
+			      errno == EINVAL ? " -- kernel too old?" : "");
+			err = -1;
+			break;
+		}
+
+		fd = bpf_prog_get_fd_by_id(id);
+		if (fd < 0) {
+			p_err("can't get prog by id (%u): %s",
+			      id, strerror(errno));
+			err = -1;
+			break;
+		}
+
+		err = show_prog(fd);
+		close(fd);
+		if (err)
+			break;
+	}
+
+	if (json_output)
+		jsonw_end_array(json_wtr);
+
+	return err;
+}
+
+static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	vprintf(fmt, args);
+	va_end(args);
+}
+
+static void dump_xlated_plain(void *buf, unsigned int len, bool opcodes)
+{
+	struct bpf_insn *insn = buf;
+	bool double_insn = false;
+	unsigned int i;
+
+	for (i = 0; i < len / sizeof(*insn); i++) {
+		if (double_insn) {
+			double_insn = false;
+			continue;
+		}
+
+		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
+
+		printf("% 4d: ", i);
+		print_bpf_insn(print_insn, NULL, insn + i, true);
+
+		if (opcodes) {
+			printf("       ");
+			fprint_hex(stdout, insn + i, 8, " ");
+			if (double_insn && i < len - 1) {
+				printf(" ");
+				fprint_hex(stdout, insn + i + 1, 8, " ");
+			}
+			printf("\n");
+		}
+	}
+}
+
+static void print_insn_json(struct bpf_verifier_env *env, const char *fmt, ...)
+{
+	unsigned int l = strlen(fmt);
+	char chomped_fmt[l];
+	va_list args;
+
+	va_start(args, fmt);
+	if (l > 0) {
+		strncpy(chomped_fmt, fmt, l - 1);
+		chomped_fmt[l - 1] = '\0';
+	}
+	jsonw_vprintf_enquote(json_wtr, chomped_fmt, args);
+	va_end(args);
+}
+
+static void dump_xlated_json(void *buf, unsigned int len, bool opcodes)
+{
+	struct bpf_insn *insn = buf;
+	bool double_insn = false;
+	unsigned int i;
+
+	jsonw_start_array(json_wtr);
+	for (i = 0; i < len / sizeof(*insn); i++) {
+		if (double_insn) {
+			double_insn = false;
+			continue;
+		}
+		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
+
+		jsonw_start_object(json_wtr);
+		jsonw_name(json_wtr, "disasm");
+		print_bpf_insn(print_insn_json, NULL, insn + i, true);
+
+		if (opcodes) {
+			jsonw_name(json_wtr, "opcodes");
+			jsonw_start_object(json_wtr);
+
+			jsonw_name(json_wtr, "code");
+			jsonw_printf(json_wtr, "\"0x%02hhx\"", insn[i].code);
+
+			jsonw_name(json_wtr, "src_reg");
+			jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].src_reg);
+
+			jsonw_name(json_wtr, "dst_reg");
+			jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].dst_reg);
+
+			jsonw_name(json_wtr, "off");
+			print_hex_data_json((uint8_t *)(&insn[i].off), 2);
+
+			jsonw_name(json_wtr, "imm");
+			if (double_insn && i < len - 1)
+				print_hex_data_json((uint8_t *)(&insn[i].imm),
+						    12);
+			else
+				print_hex_data_json((uint8_t *)(&insn[i].imm),
+						    4);
+			jsonw_end_object(json_wtr);
+		}
+		jsonw_end_object(json_wtr);
+	}
+	jsonw_end_array(json_wtr);
+}
+
+static int do_dump(int argc, char **argv)
+{
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	unsigned int buf_size;
+	char *filepath = NULL;
+	bool opcodes = false;
+	unsigned char *buf;
+	__u32 *member_len;
+	__u64 *member_ptr;
+	ssize_t n;
+	int err;
+	int fd;
+
+	if (is_prefix(*argv, "jited")) {
+		member_len = &info.jited_prog_len;
+		member_ptr = &info.jited_prog_insns;
+	} else if (is_prefix(*argv, "xlated")) {
+		member_len = &info.xlated_prog_len;
+		member_ptr = &info.xlated_prog_insns;
+	} else {
+		p_err("expected 'xlated' or 'jited', got: %s", *argv);
+		return -1;
+	}
+	NEXT_ARG();
+
+	if (argc < 2)
+		usage();
+
+	fd = prog_parse_fd(&argc, &argv);
+	if (fd < 0)
+		return -1;
+
+	if (is_prefix(*argv, "file")) {
+		NEXT_ARG();
+		if (!argc) {
+			p_err("expected file path");
+			return -1;
+		}
+
+		filepath = *argv;
+		NEXT_ARG();
+	} else if (is_prefix(*argv, "opcodes")) {
+		opcodes = true;
+		NEXT_ARG();
+	}
+
+	if (argc) {
+		usage();
+		return -1;
+	}
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	if (err) {
+		p_err("can't get prog info: %s", strerror(errno));
+		return -1;
+	}
+
+	if (!*member_len) {
+		p_info("no instructions returned");
+		close(fd);
+		return 0;
+	}
+
+	buf_size = *member_len;
+
+	buf = malloc(buf_size);
+	if (!buf) {
+		p_err("mem alloc failed");
+		close(fd);
+		return -1;
+	}
+
+	memset(&info, 0, sizeof(info));
+
+	*member_ptr = ptr_to_u64(buf);
+	*member_len = buf_size;
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	close(fd);
+	if (err) {
+		p_err("can't get prog info: %s", strerror(errno));
+		goto err_free;
+	}
+
+	if (*member_len > buf_size) {
+		p_err("too many instructions returned");
+		goto err_free;
+	}
+
+	if (filepath) {
+		fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600);
+		if (fd < 0) {
+			p_err("can't open file %s: %s", filepath,
+			      strerror(errno));
+			goto err_free;
+		}
+
+		n = write(fd, buf, *member_len);
+		close(fd);
+		if (n != *member_len) {
+			p_err("error writing output file: %s",
+			      n < 0 ? strerror(errno) : "short write");
+			goto err_free;
+		}
+	} else {
+		if (member_len == &info.jited_prog_len)
+			disasm_print_insn(buf, *member_len, opcodes);
+		else
+			if (json_output)
+				dump_xlated_json(buf, *member_len, opcodes);
+			else
+				dump_xlated_plain(buf, *member_len, opcodes);
+	}
+
+	free(buf);
+
+	return 0;
+
+err_free:
+	free(buf);
+	return -1;
+}
+
+static int do_pin(int argc, char **argv)
+{
+	int err;
+
+	err = do_pin_any(argc, argv, bpf_prog_get_fd_by_id);
+	if (!err && json_output)
+		jsonw_null(json_wtr);
+	return err;
+}
+
+static int do_help(int argc, char **argv)
+{
+	if (json_output) {
+		jsonw_null(json_wtr);
+		return 0;
+	}
+
+	fprintf(stderr,
+		"Usage: %s %s show [PROG]\n"
+		"       %s %s dump xlated PROG [{ file FILE | opcodes }]\n"
+		"       %s %s dump jited  PROG [{ file FILE | opcodes }]\n"
+		"       %s %s pin   PROG FILE\n"
+		"       %s %s help\n"
+		"\n"
+		"       " HELP_SPEC_PROGRAM "\n"
+		"       " HELP_SPEC_OPTIONS "\n"
+		"",
+		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
+		bin_name, argv[-2], bin_name, argv[-2]);
+
+	return 0;
+}
+
+static const struct cmd cmds[] = {
+	{ "show",	do_show },
+	{ "help",	do_help },
+	{ "dump",	do_dump },
+	{ "pin",	do_pin },
+	{ 0 }
+};
+
+int do_prog(int argc, char **argv)
+{
+	return cmd_select(cmds, argc, argv, do_help);
+}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 01cc7ba39924..7cebba491011 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -92,6 +92,7 @@ enum bpf_cmd {
 	BPF_PROG_GET_FD_BY_ID,
 	BPF_MAP_GET_FD_BY_ID,
 	BPF_OBJ_GET_INFO_BY_FD,
+	BPF_PROG_QUERY,
 };
 
 enum bpf_map_type {
@@ -111,6 +112,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_HASH_OF_MAPS,
 	BPF_MAP_TYPE_DEVMAP,
 	BPF_MAP_TYPE_SOCKMAP,
+	BPF_MAP_TYPE_CPUMAP,
 };
 
 enum bpf_prog_type {
@@ -143,11 +145,47 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
-/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
- * to the given target_fd cgroup the descendent cgroup will be able to
- * override effective bpf program that was inherited from this cgroup
+/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
+ *
+ * NONE(default): No further bpf programs allowed in the subtree.
+ *
+ * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
+ * the program in this cgroup yields to sub-cgroup program.
+ *
+ * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
+ * that cgroup program gets run in addition to the program in this cgroup.
+ *
+ * Only one program is allowed to be attached to a cgroup with
+ * NONE or BPF_F_ALLOW_OVERRIDE flag.
+ * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
+ * release old program and attach the new one. Attach flags has to match.
+ *
+ * Multiple programs are allowed to be attached to a cgroup with
+ * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
+ * (those that were attached first, run first)
+ * The programs of sub-cgroup are executed first, then programs of
+ * this cgroup and then programs of parent cgroup.
+ * When children program makes decision (like picking TCP CA or sock bind)
+ * parent program has a chance to override it.
+ *
+ * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
+ * A cgroup with NONE doesn't allow any programs in sub-cgroups.
+ * Ex1:
+ * cgrp1 (MULTI progs A, B) ->
+ *    cgrp2 (OVERRIDE prog C) ->
+ *      cgrp3 (MULTI prog D) ->
+ *        cgrp4 (OVERRIDE prog E) ->
+ *          cgrp5 (NONE prog F)
+ * the event in cgrp5 triggers execution of F,D,A,B in that order.
+ * if prog F is detached, the execution is E,D,A,B
+ * if prog F and D are detached, the execution is E,A,B
+ * if prog F, E and D are detached, the execution is C,A,B
+ *
+ * All eligible programs are executed regardless of return code from
+ * earlier programs.
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
+#define BPF_F_ALLOW_MULTI	(1U << 1)
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel
@@ -175,6 +213,15 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE		(1U << 2)
 
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
+
+#define BPF_OBJ_NAME_LEN 16U
+
+/* Flags for accessing BPF object */
+#define BPF_F_RDONLY		(1U << 3)
+#define BPF_F_WRONLY		(1U << 4)
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -188,6 +235,7 @@ union bpf_attr {
 		__u32	numa_node;	/* numa node (effective only if
 					 * BPF_F_NUMA_NODE is set).
 					 */
+		char	map_name[BPF_OBJ_NAME_LEN];
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -210,11 +258,13 @@ union bpf_attr {
 		__aligned_u64	log_buf;	/* user supplied buffer */
 		__u32		kern_version;	/* checked when prog_type=kprobe */
 		__u32		prog_flags;
+		char		prog_name[BPF_OBJ_NAME_LEN];
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
 		__aligned_u64	pathname;
 		__u32		bpf_fd;
+		__u32		file_flags;
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
@@ -242,6 +292,7 @@ union bpf_attr {
 			__u32		map_id;
 		};
 		__u32		next_id;
+		__u32		open_flags;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
@@ -249,6 +300,15 @@ union bpf_attr {
 		__u32		info_len;
 		__aligned_u64	info;
 	} info;
+
+	struct { /* anonymous struct used by BPF_PROG_QUERY command */
+		__u32		target_fd;	/* container object to query */
+		__u32		attach_type;
+		__u32		query_flags;
+		__u32		attach_flags;
+		__aligned_u64	prog_ids;
+		__u32		prog_cnt;
+	} query;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
@@ -553,12 +613,22 @@ union bpf_attr {
  * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
  *     Calls setsockopt. Not all opts are available, only those with
  *     integer optvals plus TCP_CONGESTION.
- *     Supported levels: SOL_SOCKET and IPROTO_TCP
+ *     Supported levels: SOL_SOCKET and IPPROTO_TCP
  *     @bpf_socket: pointer to bpf_socket
- *     @level: SOL_SOCKET or IPROTO_TCP
+ *     @level: SOL_SOCKET or IPPROTO_TCP
  *     @optname: option name
  *     @optval: pointer to option value
- *     @optlen: length of optval in byes
+ *     @optlen: length of optval in bytes
+ *     Return: 0 or negative error
+ *
+ * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen)
+ *     Calls getsockopt. Not all opts are available.
+ *     Supported levels: IPPROTO_TCP
+ *     @bpf_socket: pointer to bpf_socket
+ *     @level: IPPROTO_TCP
+ *     @optname: option name
+ *     @optval: pointer to option value
+ *     @optlen: length of optval in bytes
  *     Return: 0 or negative error
  *
  * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
@@ -569,10 +639,9 @@ union bpf_attr {
  *     @flags: reserved for future use
  *     Return: 0 on success or negative error code
  *
- * int bpf_sk_redirect_map(skb, map, key, flags)
+ * int bpf_sk_redirect_map(map, key, flags)
  *     Redirect skb to a sock in map using key as a lookup key for the
  *     sock in map.
- *     @skb: pointer to skb
  *     @map: pointer to sockmap
  *     @key: key to lookup sock in map
  *     @flags: reserved for future use
@@ -583,6 +652,27 @@ union bpf_attr {
  *	@map: pointer to sockmap to update
  *	@key: key to insert/update sock in map
  *	@flags: same flags as map update elem
+ *
+ * int bpf_xdp_adjust_meta(xdp_md, delta)
+ *     Adjust the xdp_md.data_meta by delta
+ *     @xdp_md: pointer to xdp_md
+ *     @delta: An positive/negative integer to be added to xdp_md.data_meta
+ *     Return: 0 on success or negative on error
+ *
+ * int bpf_perf_event_read_value(map, flags, buf, buf_size)
+ *     read perf event counter value and perf event enabled/running time
+ *     @map: pointer to perf_event_array map
+ *     @flags: index of event in the map or bitmask flags
+ *     @buf: buf to fill
+ *     @buf_size: size of the buf
+ *     Return: 0 on success or negative error code
+ *
+ * int bpf_perf_prog_read_value(ctx, buf, buf_size)
+ *     read perf prog attached perf event counter and enabled/running time
+ *     @ctx: pointer to ctx
+ *     @buf: buf to fill
+ *     @buf_size: size of the buf
+ *     Return : 0 on success or negative error code
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -639,6 +729,10 @@ union bpf_attr {
 	FN(redirect_map),		\
 	FN(sk_redirect_map),		\
 	FN(sock_map_update),		\
+	FN(xdp_adjust_meta),		\
+	FN(perf_event_read_value),	\
+	FN(perf_prog_read_value),	\
+	FN(getsockopt),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -682,7 +776,9 @@ enum bpf_func_id {
 #define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
 #define BPF_F_DONT_FRAGMENT		(1ULL << 2)
 
-/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
+/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
+ * BPF_FUNC_perf_event_read_value flags.
+ */
 #define BPF_F_INDEX_MASK		0xffffffffULL
 #define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
@@ -716,7 +812,7 @@ struct __sk_buff {
 	__u32 data_end;
 	__u32 napi_id;
 
-	/* accessed by BPF_PROG_TYPE_sk_skb types */
+	/* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */
 	__u32 family;
 	__u32 remote_ip4;	/* Stored in network byte order */
 	__u32 local_ip4;	/* Stored in network byte order */
@@ -724,6 +820,9 @@ struct __sk_buff {
 	__u32 local_ip6[4];	/* Stored in network byte order */
 	__u32 remote_port;	/* Stored in network byte order */
 	__u32 local_port;	/* stored in host byte order */
+	/* ... here. */
+
+	__u32 data_meta;
 };
 
 struct bpf_tunnel_key {
@@ -784,6 +883,7 @@ enum xdp_action {
 struct xdp_md {
 	__u32 data;
 	__u32 data_end;
+	__u32 data_meta;
 };
 
 enum sk_action {
@@ -801,6 +901,11 @@ struct bpf_prog_info {
 	__u32 xlated_prog_len;
 	__aligned_u64 jited_prog_insns;
 	__aligned_u64 xlated_prog_insns;
+	__u64 load_time;	/* ns since boottime */
+	__u32 created_by_uid;
+	__u32 nr_map_ids;
+	__aligned_u64 map_ids;
+	char name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -810,6 +915,7 @@ struct bpf_map_info {
 	__u32 value_size;
 	__u32 max_entries;
 	__u32 map_flags;
+	char  name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
@@ -859,9 +965,22 @@ enum {
 	BPF_SOCK_OPS_NEEDS_ECN,		/* If connection's congestion control
 					 * needs ECN
 					 */
+	BPF_SOCK_OPS_BASE_RTT,		/* Get base RTT. The correct value is
+					 * based on the path and may be
+					 * dependent on the congestion control
+					 * algorithm. In general it indicates
+					 * a congestion threshold. RTTs above
+					 * this indicate congestion
+					 */
 };
 
 #define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
 #define TCP_BPF_SNDCWND_CLAMP	1002	/* Set sndcwnd_clamp */
 
+struct bpf_perf_event_value {
+	__u64 counter;
+	__u64 enabled;
+	__u64 running;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 1d6907d379c9..5128677e4117 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -46,6 +46,8 @@
 # endif
 #endif
 
+#define min(x, y) ((x) < (y) ? (x) : (y))
+
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
@@ -57,10 +59,11 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 	return syscall(__NR_bpf, cmd, attr, size);
 }
 
-int bpf_create_map_node(enum bpf_map_type map_type, int key_size,
-			int value_size, int max_entries, __u32 map_flags,
-			int node)
+int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
+			int key_size, int value_size, int max_entries,
+			__u32 map_flags, int node)
 {
+	__u32 name_len = name ? strlen(name) : 0;
 	union bpf_attr attr;
 
 	memset(&attr, '\0', sizeof(attr));
@@ -70,6 +73,8 @@ int bpf_create_map_node(enum bpf_map_type map_type, int key_size,
 	attr.value_size = value_size;
 	attr.max_entries = max_entries;
 	attr.map_flags = map_flags;
+	memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
+
 	if (node >= 0) {
 		attr.map_flags |= BPF_F_NUMA_NODE;
 		attr.numa_node = node;
@@ -81,14 +86,23 @@ int bpf_create_map_node(enum bpf_map_type map_type, int key_size,
 int bpf_create_map(enum bpf_map_type map_type, int key_size,
 		   int value_size, int max_entries, __u32 map_flags)
 {
-	return bpf_create_map_node(map_type, key_size, value_size,
+	return bpf_create_map_node(map_type, NULL, key_size, value_size,
 				   max_entries, map_flags, -1);
 }
 
-int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size,
-			       int inner_map_fd, int max_entries,
+int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
+			int key_size, int value_size, int max_entries,
+			__u32 map_flags)
+{
+	return bpf_create_map_node(map_type, name, key_size, value_size,
+				   max_entries, map_flags, -1);
+}
+
+int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
+			       int key_size, int inner_map_fd, int max_entries,
 			       __u32 map_flags, int node)
 {
+	__u32 name_len = name ? strlen(name) : 0;
 	union bpf_attr attr;
 
 	memset(&attr, '\0', sizeof(attr));
@@ -99,6 +113,8 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size,
 	attr.inner_map_fd = inner_map_fd;
 	attr.max_entries = max_entries;
 	attr.map_flags = map_flags;
+	memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
+
 	if (node >= 0) {
 		attr.map_flags |= BPF_F_NUMA_NODE;
 		attr.numa_node = node;
@@ -107,19 +123,24 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size,
 	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
 
-int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
-			  int inner_map_fd, int max_entries, __u32 map_flags)
+int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
+			  int key_size, int inner_map_fd, int max_entries,
+			  __u32 map_flags)
 {
-	return bpf_create_map_in_map_node(map_type, key_size, inner_map_fd,
-					  max_entries, map_flags, -1);
+	return bpf_create_map_in_map_node(map_type, name, key_size,
+					  inner_map_fd, max_entries, map_flags,
+					  -1);
 }
 
-int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
-		     size_t insns_cnt, const char *license,
-		     __u32 kern_version, char *log_buf, size_t log_buf_sz)
+int bpf_load_program_name(enum bpf_prog_type type, const char *name,
+			  const struct bpf_insn *insns,
+			  size_t insns_cnt, const char *license,
+			  __u32 kern_version, char *log_buf,
+			  size_t log_buf_sz)
 {
 	int fd;
 	union bpf_attr attr;
+	__u32 name_len = name ? strlen(name) : 0;
 
 	bzero(&attr, sizeof(attr));
 	attr.prog_type = type;
@@ -130,6 +151,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	attr.log_size = 0;
 	attr.log_level = 0;
 	attr.kern_version = kern_version;
+	memcpy(attr.prog_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
 
 	fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 	if (fd >= 0 || !log_buf || !log_buf_sz)
@@ -143,6 +165,15 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 }
 
+int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+		     size_t insns_cnt, const char *license,
+		     __u32 kern_version, char *log_buf,
+		     size_t log_buf_sz)
+{
+	return bpf_load_program_name(type, NULL, insns, insns_cnt, license,
+				     kern_version, log_buf, log_buf_sz);
+}
+
 int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 		       size_t insns_cnt, int strict_alignment,
 		       const char *license, __u32 kern_version,
@@ -260,6 +291,38 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
 }
 
+int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, 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));
+}
+
+int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
+		   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt)
+{
+	union bpf_attr attr;
+	int ret;
+
+	bzero(&attr, sizeof(attr));
+	attr.query.target_fd	= target_fd;
+	attr.query.attach_type	= type;
+	attr.query.query_flags	= query_flags;
+	attr.query.prog_cnt	= *prog_cnt;
+	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;
+}
+
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 		      void *data_out, __u32 *size_out, __u32 *retval,
 		      __u32 *duration)
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index b8ea5843c39e..6534889e2b2f 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -24,19 +24,28 @@
 #include <linux/bpf.h>
 #include <stddef.h>
 
-int bpf_create_map_node(enum bpf_map_type map_type, int key_size,
-			int value_size, int max_entries, __u32 map_flags,
-			int node);
+int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
+			int key_size, int value_size, int max_entries,
+			__u32 map_flags, int node);
+int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
+			int key_size, int value_size, int max_entries,
+			__u32 map_flags);
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
 		   int max_entries, __u32 map_flags);
-int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size,
-			       int inner_map_fd, int max_entries,
+int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
+			       int key_size, int inner_map_fd, int max_entries,
 			       __u32 map_flags, int node);
-int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
-			  int inner_map_fd, int max_entries, __u32 map_flags);
+int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
+			  int key_size, int inner_map_fd, int max_entries,
+			  __u32 map_flags);
 
 /* Recommend log buffer size */
 #define BPF_LOG_BUF_SIZE 65536
+int bpf_load_program_name(enum bpf_prog_type type, const char *name,
+			  const struct bpf_insn *insns,
+			  size_t insns_cnt, const char *license,
+			  __u32 kern_version, char *log_buf,
+			  size_t log_buf_sz);
 int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 		     size_t insns_cnt, const char *license,
 		     __u32 kern_version, char *log_buf,
@@ -57,6 +66,7 @@ int bpf_obj_get(const char *pathname);
 int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
 		    unsigned int flags);
 int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
+int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type);
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 		      void *data_out, __u32 *size_out, __u32 *retval,
 		      __u32 *duration);
@@ -65,5 +75,6 @@ int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
 int bpf_prog_get_fd_by_id(__u32 id);
 int bpf_map_get_fd_by_id(__u32 id);
 int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
-
+int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
+		   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt);
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 35f6dfcdc565..5aa45f89da93 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -171,6 +171,7 @@ int libbpf_strerror(int err, char *buf, size_t size)
 struct bpf_program {
 	/* Index in elf obj file, for relocation use. */
 	int idx;
+	char *name;
 	char *section_name;
 	struct bpf_insn *insns;
 	size_t insns_cnt;
@@ -283,6 +284,7 @@ static void bpf_program__exit(struct bpf_program *prog)
 	prog->clear_priv = NULL;
 
 	bpf_program__unload(prog);
+	zfree(&prog->name);
 	zfree(&prog->section_name);
 	zfree(&prog->insns);
 	zfree(&prog->reloc_desc);
@@ -293,26 +295,27 @@ static void bpf_program__exit(struct bpf_program *prog)
 }
 
 static int
-bpf_program__init(void *data, size_t size, char *name, int idx,
-		    struct bpf_program *prog)
+bpf_program__init(void *data, size_t size, char *section_name, int idx,
+		  struct bpf_program *prog)
 {
 	if (size < sizeof(struct bpf_insn)) {
-		pr_warning("corrupted section '%s'\n", name);
+		pr_warning("corrupted section '%s'\n", section_name);
 		return -EINVAL;
 	}
 
 	bzero(prog, sizeof(*prog));
 
-	prog->section_name = strdup(name);
+	prog->section_name = strdup(section_name);
 	if (!prog->section_name) {
-		pr_warning("failed to alloc name for prog %s\n",
-			   name);
+		pr_warning("failed to alloc name for prog under section %s\n",
+			   section_name);
 		goto errout;
 	}
 
 	prog->insns = malloc(size);
 	if (!prog->insns) {
-		pr_warning("failed to alloc insns for %s\n", name);
+		pr_warning("failed to alloc insns for prog under section %s\n",
+			   section_name);
 		goto errout;
 	}
 	prog->insns_cnt = size / sizeof(struct bpf_insn);
@@ -331,12 +334,12 @@ errout:
 
 static int
 bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
-			char *name, int idx)
+			char *section_name, int idx)
 {
 	struct bpf_program prog, *progs;
 	int nr_progs, err;
 
-	err = bpf_program__init(data, size, name, idx, &prog);
+	err = bpf_program__init(data, size, section_name, idx, &prog);
 	if (err)
 		return err;
 
@@ -350,8 +353,8 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
 		 * is still valid, so don't need special treat for
 		 * bpf_close_object().
 		 */
-		pr_warning("failed to alloc a new program '%s'\n",
-			   name);
+		pr_warning("failed to alloc a new program under section '%s'\n",
+			   section_name);
 		bpf_program__exit(&prog);
 		return -ENOMEM;
 	}
@@ -364,6 +367,54 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
 	return 0;
 }
 
+static int
+bpf_object__init_prog_names(struct bpf_object *obj)
+{
+	Elf_Data *symbols = obj->efile.symbols;
+	struct bpf_program *prog;
+	size_t pi, si;
+
+	for (pi = 0; pi < obj->nr_programs; pi++) {
+		char *name = NULL;
+
+		prog = &obj->programs[pi];
+
+		for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;
+		     si++) {
+			GElf_Sym sym;
+
+			if (!gelf_getsym(symbols, si, &sym))
+				continue;
+			if (sym.st_shndx != prog->idx)
+				continue;
+
+			name = elf_strptr(obj->efile.elf,
+					  obj->efile.strtabidx,
+					  sym.st_name);
+			if (!name) {
+				pr_warning("failed to get sym name string for prog %s\n",
+					   prog->section_name);
+				return -LIBBPF_ERRNO__LIBELF;
+			}
+		}
+
+		if (!name) {
+			pr_warning("failed to find sym for prog %s\n",
+				   prog->section_name);
+			return -EINVAL;
+		}
+
+		prog->name = strdup(name);
+		if (!prog->name) {
+			pr_warning("failed to allocate memory for prog sym %s\n",
+				   name);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
 static struct bpf_object *bpf_object__new(const char *path,
 					  void *obj_buf,
 					  size_t obj_buf_sz)
@@ -528,31 +579,6 @@ bpf_object__init_kversion(struct bpf_object *obj,
 	return 0;
 }
 
-static int
-bpf_object__validate_maps(struct bpf_object *obj)
-{
-	int i;
-
-	/*
-	 * If there's only 1 map, the only error case should have been
-	 * catched in bpf_object__init_maps().
-	 */
-	if (!obj->maps || !obj->nr_maps || (obj->nr_maps == 1))
-		return 0;
-
-	for (i = 1; i < obj->nr_maps; i++) {
-		const struct bpf_map *a = &obj->maps[i - 1];
-		const struct bpf_map *b = &obj->maps[i];
-
-		if (b->offset - a->offset < sizeof(struct bpf_map_def)) {
-			pr_warning("corrupted map section in %s: map \"%s\" too small\n",
-				   obj->path, a->name);
-			return -EINVAL;
-		}
-	}
-	return 0;
-}
-
 static int compare_bpf_map(const void *_a, const void *_b)
 {
 	const struct bpf_map *a = _a;
@@ -564,7 +590,7 @@ static int compare_bpf_map(const void *_a, const void *_b)
 static int
 bpf_object__init_maps(struct bpf_object *obj)
 {
-	int i, map_idx, nr_maps = 0;
+	int i, map_idx, map_def_sz, nr_maps = 0;
 	Elf_Scn *scn;
 	Elf_Data *data;
 	Elf_Data *symbols = obj->efile.symbols;
@@ -607,6 +633,15 @@ bpf_object__init_maps(struct bpf_object *obj)
 	if (!nr_maps)
 		return 0;
 
+	/* Assume equally sized map definitions */
+	map_def_sz = data->d_size / nr_maps;
+	if (!data->d_size || (data->d_size % nr_maps) != 0) {
+		pr_warning("unable to determine map definition size "
+			   "section %s, %d maps in %zd bytes\n",
+			   obj->path, nr_maps, data->d_size);
+		return -EINVAL;
+	}
+
 	obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
 	if (!obj->maps) {
 		pr_warning("alloc maps for object failed\n");
@@ -639,7 +674,7 @@ bpf_object__init_maps(struct bpf_object *obj)
 				      obj->efile.strtabidx,
 				      sym.st_name);
 		obj->maps[map_idx].offset = sym.st_value;
-		if (sym.st_value + sizeof(struct bpf_map_def) > data->d_size) {
+		if (sym.st_value + map_def_sz > data->d_size) {
 			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
 				   obj->path, map_name);
 			return -EINVAL;
@@ -653,12 +688,40 @@ bpf_object__init_maps(struct bpf_object *obj)
 		pr_debug("map %d is \"%s\"\n", map_idx,
 			 obj->maps[map_idx].name);
 		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
-		obj->maps[map_idx].def = *def;
+		/*
+		 * If the definition of the map in the object file fits in
+		 * bpf_map_def, copy it.  Any extra fields in our version
+		 * of bpf_map_def will default to zero as a result of the
+		 * calloc above.
+		 */
+		if (map_def_sz <= sizeof(struct bpf_map_def)) {
+			memcpy(&obj->maps[map_idx].def, def, map_def_sz);
+		} else {
+			/*
+			 * Here the map structure being read is bigger than what
+			 * we expect, truncate if the excess bits are all zero.
+			 * If they are not zero, reject this map as
+			 * incompatible.
+			 */
+			char *b;
+			for (b = ((char *)def) + sizeof(struct bpf_map_def);
+			     b < ((char *)def) + map_def_sz; b++) {
+				if (*b != 0) {
+					pr_warning("maps section in %s: \"%s\" "
+						   "has unrecognized, non-zero "
+						   "options\n",
+						   obj->path, map_name);
+					return -EINVAL;
+				}
+			}
+			memcpy(&obj->maps[map_idx].def, def,
+			       sizeof(struct bpf_map_def));
+		}
 		map_idx++;
 	}
 
 	qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
-	return bpf_object__validate_maps(obj);
+	return 0;
 }
 
 static int bpf_object__elf_collect(struct bpf_object *obj)
@@ -766,8 +829,12 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		pr_warning("Corrupted ELF file: index of strtab invalid\n");
 		return LIBBPF_ERRNO__FORMAT;
 	}
-	if (obj->efile.maps_shndx >= 0)
+	if (obj->efile.maps_shndx >= 0) {
 		err = bpf_object__init_maps(obj);
+		if (err)
+			goto out;
+	}
+	err = bpf_object__init_prog_names(obj);
 out:
 	return err;
 }
@@ -870,11 +937,12 @@ bpf_object__create_maps(struct bpf_object *obj)
 		struct bpf_map_def *def = &obj->maps[i].def;
 		int *pfd = &obj->maps[i].fd;
 
-		*pfd = bpf_create_map(def->type,
-				      def->key_size,
-				      def->value_size,
-				      def->max_entries,
-				      0);
+		*pfd = bpf_create_map_name(def->type,
+					   obj->maps[i].name,
+					   def->key_size,
+					   def->value_size,
+					   def->max_entries,
+					   def->map_flags);
 		if (*pfd < 0) {
 			size_t j;
 			int err = *pfd;
@@ -982,7 +1050,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 }
 
 static int
-load_program(enum bpf_prog_type type, struct bpf_insn *insns,
+load_program(enum bpf_prog_type type, const char *name, struct bpf_insn *insns,
 	     int insns_cnt, char *license, u32 kern_version, int *pfd)
 {
 	int ret;
@@ -995,8 +1063,8 @@ load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 	if (!log_buf)
 		pr_warning("Alloc log buffer for bpf loader error, continue without log\n");
 
-	ret = bpf_load_program(type, insns, insns_cnt, license,
-			       kern_version, log_buf, BPF_LOG_BUF_SIZE);
+	ret = bpf_load_program_name(type, name, insns, insns_cnt, license,
+				    kern_version, log_buf, BPF_LOG_BUF_SIZE);
 
 	if (ret >= 0) {
 		*pfd = ret;
@@ -1021,9 +1089,9 @@ load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 		if (type != BPF_PROG_TYPE_KPROBE) {
 			int fd;
 
-			fd = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
-					      insns_cnt, license, kern_version,
-					      NULL, 0);
+			fd = bpf_load_program_name(BPF_PROG_TYPE_KPROBE, name,
+						   insns, insns_cnt, license,
+						   kern_version, NULL, 0);
 			if (fd >= 0) {
 				close(fd);
 				ret = -LIBBPF_ERRNO__PROGTYPE;
@@ -1067,8 +1135,8 @@ bpf_program__load(struct bpf_program *prog,
 			pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
 				   prog->section_name, prog->instances.nr);
 		}
-		err = load_program(prog->type, prog->insns, prog->insns_cnt,
-				   license, kern_version, &fd);
+		err = load_program(prog->type, prog->name, prog->insns,
+				   prog->insns_cnt, license, kern_version, &fd);
 		if (!err)
 			prog->instances.fds[0] = fd;
 		goto out;
@@ -1096,7 +1164,8 @@ bpf_program__load(struct bpf_program *prog,
 			continue;
 		}
 
-		err = load_program(prog->type, result.new_insn_ptr,
+		err = load_program(prog->type, prog->name,
+				   result.new_insn_ptr,
 				   result.new_insn_cnt,
 				   license, kern_version, &fd);
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 7959086eb9c9..6e20003109e0 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -207,6 +207,7 @@ struct bpf_map_def {
 	unsigned int key_size;
 	unsigned int value_size;
 	unsigned int max_entries;
+	unsigned int map_flags;
 };
 
 /*
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index eab7644a07b4..4f0734aa6e93 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -13,12 +13,13 @@ CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../i
 LDLIBS += -lcap -lelf
 
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
-	test_align
+	test_align test_verifier_log
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
-	test_pkt_md_access.o test_xdp_redirect.o sockmap_parse_prog.o sockmap_verdict_prog.o
+	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
+	sockmap_verdict_prog.o
 
-TEST_PROGS := test_kmod.sh test_xdp_redirect.sh
+TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh
 
 include ../lib.mk
 
@@ -35,8 +36,20 @@ $(BPFOBJ): force
 	$(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
 
 CLANG ?= clang
+LLC   ?= llc
+
+PROBE := $(shell llc -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
+
+# Let newer LLVM versions transparently probe the kernel for availability
+# of full BPF instruction set.
+ifeq ($(PROBE),)
+  CPU ?= probe
+else
+  CPU ?= generic
+endif
 
 %.o: %.c
 	$(CLANG) -I. -I./include/uapi -I../../../include/uapi \
-		-Wno-compare-distinct-pointer-types \
-		-O2 -target bpf -c $< -o $@
+		 -Wno-compare-distinct-pointer-types          \
+		 -O2 -target bpf -emit-llvm -c $< -o - |      \
+	$(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 50353c10573c..fd9a17fa8a8b 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -63,14 +63,25 @@ static unsigned long long (*bpf_get_prandom_u32)(void) =
 	(void *) BPF_FUNC_get_prandom_u32;
 static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
 	(void *) BPF_FUNC_xdp_adjust_head;
+static int (*bpf_xdp_adjust_meta)(void *ctx, int offset) =
+	(void *) BPF_FUNC_xdp_adjust_meta;
 static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
 			     int optlen) =
 	(void *) BPF_FUNC_setsockopt;
+static int (*bpf_getsockopt)(void *ctx, int level, int optname, void *optval,
+			     int optlen) =
+	(void *) BPF_FUNC_getsockopt;
 static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) =
 	(void *) BPF_FUNC_sk_redirect_map;
 static int (*bpf_sock_map_update)(void *map, void *key, void *value,
 				  unsigned long long flags) =
 	(void *) BPF_FUNC_sock_map_update;
+static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
+					void *buf, unsigned int buf_size) =
+	(void *) BPF_FUNC_perf_event_read_value;
+static int (*bpf_perf_prog_read_value)(void *ctx, void *buf,
+				       unsigned int buf_size) =
+	(void *) BPF_FUNC_perf_prog_read_value;
 
 
 /* llvm builtin functions that eBPF C program may use to
@@ -110,7 +121,47 @@ static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
 static int (*bpf_skb_change_head)(void *, int len, int flags) =
 	(void *) BPF_FUNC_skb_change_head;
 
+/* Scan the ARCH passed in from ARCH env variable (see Makefile) */
+#if defined(__TARGET_ARCH_x86)
+	#define bpf_target_x86
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_s930x)
+	#define bpf_target_s930x
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_arm64)
+	#define bpf_target_arm64
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_mips)
+	#define bpf_target_mips
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_powerpc)
+	#define bpf_target_powerpc
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_sparc)
+	#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
+#elif defined(__s390x__)
+	#define bpf_target_s930x
+#elif defined(__aarch64__)
+	#define bpf_target_arm64
+#elif defined(__mips__)
+	#define bpf_target_mips
+#elif defined(__powerpc__)
+	#define bpf_target_powerpc
+#elif defined(__sparc__)
+	#define bpf_target_sparc
+#endif
+#endif
+
+#if defined(bpf_target_x86)
 
 #define PT_REGS_PARM1(x) ((x)->di)
 #define PT_REGS_PARM2(x) ((x)->si)
@@ -123,7 +174,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->ip)
 
-#elif defined(__s390x__)
+#elif defined(bpf_target_s390x)
 
 #define PT_REGS_PARM1(x) ((x)->gprs[2])
 #define PT_REGS_PARM2(x) ((x)->gprs[3])
@@ -136,7 +187,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->gprs[15])
 #define PT_REGS_IP(x) ((x)->psw.addr)
 
-#elif defined(__aarch64__)
+#elif defined(bpf_target_arm64)
 
 #define PT_REGS_PARM1(x) ((x)->regs[0])
 #define PT_REGS_PARM2(x) ((x)->regs[1])
@@ -149,7 +200,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->pc)
 
-#elif defined(__mips__)
+#elif defined(bpf_target_mips)
 
 #define PT_REGS_PARM1(x) ((x)->regs[4])
 #define PT_REGS_PARM2(x) ((x)->regs[5])
@@ -162,7 +213,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->regs[29])
 #define PT_REGS_IP(x) ((x)->cp0_epc)
 
-#elif defined(__powerpc__)
+#elif defined(bpf_target_powerpc)
 
 #define PT_REGS_PARM1(x) ((x)->gpr[3])
 #define PT_REGS_PARM2(x) ((x)->gpr[4])
@@ -173,7 +224,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->nip)
 
-#elif defined(__sparc__)
+#elif defined(bpf_target_sparc)
 
 #define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
 #define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
@@ -183,6 +234,8 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
 #define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
 #define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
+
+/* Should this also be a bpf_target check for the sparc case? */
 #if defined(__arch64__)
 #define PT_REGS_IP(x) ((x)->tpc)
 #else
@@ -191,10 +244,10 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 
 #endif
 
-#ifdef __powerpc__
+#ifdef bpf_target_powerpc
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#elif defined(__sparc__)
+#elif 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
diff --git a/tools/testing/selftests/bpf/sockmap_parse_prog.c b/tools/testing/selftests/bpf/sockmap_parse_prog.c
index fae3b96c3aa4..a1dec2b6d9c5 100644
--- a/tools/testing/selftests/bpf/sockmap_parse_prog.c
+++ b/tools/testing/selftests/bpf/sockmap_parse_prog.c
@@ -29,9 +29,6 @@ int bpf_prog1(struct __sk_buff *skb)
 	 * fields.
 	 */
 	d[7] = 1;
-
-	bpf_printk("parse: data[0] = (%u): local_port %i remote %i\n",
-		   d[0], lport, bpf_ntohl(rport));
 	return skb->len;
 }
 
diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
index 2cd2d552938b..d7bea972cb21 100644
--- a/tools/testing/selftests/bpf/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
@@ -58,8 +58,6 @@ int bpf_prog2(struct __sk_buff *skb)
 	d[6] = 0xe;
 	d[7] = 0xf;
 
-	bpf_printk("verdict: data[0] = redir(%u:%u)\n", map, sk);
-
 	if (!map)
 		return bpf_sk_redirect_map(skb, &sock_map_rx, sk, 0);
 	return bpf_sk_redirect_map(skb, &sock_map_tx, sk, 0);
diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c
index f93a333cbf2c..f61480641b6e 100644
--- a/tools/testing/selftests/bpf/test_lpm_map.c
+++ b/tools/testing/selftests/bpf/test_lpm_map.c
@@ -32,6 +32,10 @@ struct tlpm_node {
 	uint8_t key[];
 };
 
+static struct tlpm_node *tlpm_match(struct tlpm_node *list,
+				    const uint8_t *key,
+				    size_t n_bits);
+
 static struct tlpm_node *tlpm_add(struct tlpm_node *list,
 				  const uint8_t *key,
 				  size_t n_bits)
@@ -39,9 +43,17 @@ static struct tlpm_node *tlpm_add(struct tlpm_node *list,
 	struct tlpm_node *node;
 	size_t n;
 
+	n = (n_bits + 7) / 8;
+
+	/* 'overwrite' an equivalent entry if one already exists */
+	node = tlpm_match(list, key, n_bits);
+	if (node && node->n_bits == n_bits) {
+		memcpy(node->key, key, n);
+		return list;
+	}
+
 	/* add new entry with @key/@n_bits to @list and return new head */
 
-	n = (n_bits + 7) / 8;
 	node = malloc(sizeof(*node) + n);
 	assert(node);
 
@@ -93,6 +105,34 @@ static struct tlpm_node *tlpm_match(struct tlpm_node *list,
 	return best;
 }
 
+static struct tlpm_node *tlpm_delete(struct tlpm_node *list,
+				     const uint8_t *key,
+				     size_t n_bits)
+{
+	struct tlpm_node *best = tlpm_match(list, key, n_bits);
+	struct tlpm_node *node;
+
+	if (!best || best->n_bits != n_bits)
+		return list;
+
+	if (best == list) {
+		node = best->next;
+		free(best);
+		return node;
+	}
+
+	for (node = list; node; node = node->next) {
+		if (node->next == best) {
+			node->next = best->next;
+			free(best);
+			return list;
+		}
+	}
+	/* should never get here */
+	assert(0);
+	return list;
+}
+
 static void test_lpm_basic(void)
 {
 	struct tlpm_node *list = NULL, *t1, *t2;
@@ -115,6 +155,13 @@ static void test_lpm_basic(void)
 	assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 15));
 	assert(!tlpm_match(list, (uint8_t[]){ 0x7f, 0xff }, 16));
 
+	list = tlpm_delete(list, (uint8_t[]){ 0xff, 0xff }, 16);
+	assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8));
+	assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16));
+
+	list = tlpm_delete(list, (uint8_t[]){ 0xff }, 8);
+	assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8));
+
 	tlpm_clear(list);
 }
 
@@ -159,7 +206,7 @@ static void test_lpm_order(void)
 
 static void test_lpm_map(int keysize)
 {
-	size_t i, j, n_matches, n_nodes, n_lookups;
+	size_t i, j, n_matches, n_matches_after_delete, n_nodes, n_lookups;
 	struct tlpm_node *t, *list = NULL;
 	struct bpf_lpm_trie_key *key;
 	uint8_t *data, *value;
@@ -171,6 +218,7 @@ static void test_lpm_map(int keysize)
 	 */
 
 	n_matches = 0;
+	n_matches_after_delete = 0;
 	n_nodes = 1 << 8;
 	n_lookups = 1 << 16;
 
@@ -224,15 +272,54 @@ static void test_lpm_map(int keysize)
 		}
 	}
 
+	/* Remove the first half of the elements in the tlpm and the
+	 * corresponding nodes from the bpf-lpm.  Then run the same
+	 * large number of random lookups in both and make sure they match.
+	 * Note: we need to count the number of nodes actually inserted
+	 * since there may have been duplicates.
+	 */
+	for (i = 0, t = list; t; i++, t = t->next)
+		;
+	for (j = 0; j < i / 2; ++j) {
+		key->prefixlen = list->n_bits;
+		memcpy(key->data, list->key, keysize);
+		r = bpf_map_delete_elem(map, key);
+		assert(!r);
+		list = tlpm_delete(list, list->key, list->n_bits);
+		assert(list);
+	}
+	for (i = 0; i < n_lookups; ++i) {
+		for (j = 0; j < keysize; ++j)
+			data[j] = rand() & 0xff;
+
+		t = tlpm_match(list, data, 8 * keysize);
+
+		key->prefixlen = 8 * keysize;
+		memcpy(key->data, data, keysize);
+		r = bpf_map_lookup_elem(map, key, value);
+		assert(!r || errno == ENOENT);
+		assert(!t == !!r);
+
+		if (t) {
+			++n_matches_after_delete;
+			assert(t->n_bits == value[keysize]);
+			for (j = 0; j < t->n_bits; ++j)
+				assert((t->key[j / 8] & (1 << (7 - j % 8))) ==
+				       (value[j / 8] & (1 << (7 - j % 8))));
+		}
+	}
+
 	close(map);
 	tlpm_clear(list);
 
 	/* With 255 random nodes in the map, we are pretty likely to match
 	 * something on every lookup. For statistics, use this:
 	 *
-	 *     printf("  nodes: %zu\n"
-	 *            "lookups: %zu\n"
-	 *            "matches: %zu\n", n_nodes, n_lookups, n_matches);
+	 *     printf("          nodes: %zu\n"
+	 *            "        lookups: %zu\n"
+	 *            "        matches: %zu\n"
+	 *            "matches(delete): %zu\n",
+	 *            n_nodes, n_lookups, n_matches, n_matches_after_delete);
 	 */
 }
 
@@ -332,6 +419,108 @@ static void test_lpm_ipaddr(void)
 	close(map_fd_ipv6);
 }
 
+static void test_lpm_delete(void)
+{
+	struct bpf_lpm_trie_key *key;
+	size_t key_size;
+	int map_fd;
+	__u64 value;
+
+	key_size = sizeof(*key) + sizeof(__u32);
+	key = alloca(key_size);
+
+	map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
+				key_size, sizeof(value),
+				100, BPF_F_NO_PREALLOC);
+	assert(map_fd >= 0);
+
+	/* Add nodes:
+	 * 192.168.0.0/16   (1)
+	 * 192.168.0.0/24   (2)
+	 * 192.168.128.0/24 (3)
+	 * 192.168.1.0/24   (4)
+	 *
+	 *         (1)
+	 *        /   \
+         *     (IM)    (3)
+	 *    /   \
+         *   (2)  (4)
+	 */
+	value = 1;
+	key->prefixlen = 16;
+	inet_pton(AF_INET, "192.168.0.0", key->data);
+	assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
+
+	value = 2;
+	key->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.0.0", key->data);
+	assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
+
+	value = 3;
+	key->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.128.0", key->data);
+	assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
+
+	value = 4;
+	key->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.1.0", key->data);
+	assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
+
+	/* remove non-existent node */
+	key->prefixlen = 32;
+	inet_pton(AF_INET, "10.0.0.1", key->data);
+	assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 &&
+		errno == ENOENT);
+
+	/* assert initial lookup */
+	key->prefixlen = 32;
+	inet_pton(AF_INET, "192.168.0.1", key->data);
+	assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
+	assert(value == 2);
+
+	/* remove leaf node */
+	key->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.0.0", key->data);
+	assert(bpf_map_delete_elem(map_fd, key) == 0);
+
+	key->prefixlen = 32;
+	inet_pton(AF_INET, "192.168.0.1", key->data);
+	assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
+	assert(value == 1);
+
+	/* remove leaf (and intermediary) node */
+	key->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.1.0", key->data);
+	assert(bpf_map_delete_elem(map_fd, key) == 0);
+
+	key->prefixlen = 32;
+	inet_pton(AF_INET, "192.168.1.1", key->data);
+	assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
+	assert(value == 1);
+
+	/* remove root node */
+	key->prefixlen = 16;
+	inet_pton(AF_INET, "192.168.0.0", key->data);
+	assert(bpf_map_delete_elem(map_fd, key) == 0);
+
+	key->prefixlen = 32;
+	inet_pton(AF_INET, "192.168.128.1", key->data);
+	assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
+	assert(value == 3);
+
+	/* remove last node */
+	key->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.128.0", key->data);
+	assert(bpf_map_delete_elem(map_fd, key) == 0);
+
+	key->prefixlen = 32;
+	inet_pton(AF_INET, "192.168.128.1", key->data);
+	assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 &&
+		errno == ENOENT);
+
+	close(map_fd);
+}
+
 int main(void)
 {
 	struct rlimit limit  = { RLIM_INFINITY, RLIM_INFINITY };
@@ -354,6 +543,8 @@ int main(void)
 
 	test_lpm_ipaddr();
 
+	test_lpm_delete();
+
 	printf("test_lpm: OK\n");
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 50ce52d2013d..040356ecc862 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1043,6 +1043,51 @@ static void test_map_parallel(void)
 	assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT);
 }
 
+static void test_map_rdonly(void)
+{
+	int fd, key = 0, value = 0;
+
+	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
+			    MAP_SIZE, map_flags | BPF_F_RDONLY);
+	if (fd < 0) {
+		printf("Failed to create map for read only test '%s'!\n",
+		       strerror(errno));
+		exit(1);
+	}
+
+	key = 1;
+	value = 1234;
+	/* Insert key=1 element. */
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == -1 &&
+	       errno == EPERM);
+
+	/* Check that key=2 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);
+}
+
+static void test_map_wronly(void)
+{
+	int fd, key = 0, value = 0;
+
+	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
+			    MAP_SIZE, map_flags | BPF_F_WRONLY);
+	if (fd < 0) {
+		printf("Failed to create map for read only test '%s'!\n",
+		       strerror(errno));
+		exit(1);
+	}
+
+	key = 1;
+	value = 1234;
+	/* Insert key=1 element. */
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
+
+	/* Check that key=2 is not found. */
+	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == EPERM);
+	assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == EPERM);
+}
+
 static void run_all_tests(void)
 {
 	test_hashmap(0, NULL);
@@ -1060,6 +1105,9 @@ static void run_all_tests(void)
 	test_map_large();
 	test_map_parallel();
 	test_map_stress();
+
+	test_map_rdonly();
+	test_map_wronly();
 }
 
 int main(void)
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 11ee25cea227..69427531408d 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -10,6 +10,7 @@
 #include <string.h>
 #include <assert.h>
 #include <stdlib.h>
+#include <time.h>
 
 #include <linux/types.h>
 typedef __u16 __sum16;
@@ -19,6 +20,8 @@ typedef __u16 __sum16;
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
+#include <linux/filter.h>
+#include <linux/unistd.h>
 
 #include <sys/wait.h>
 #include <sys/resource.h>
@@ -273,16 +276,26 @@ static void test_bpf_obj_id(void)
 	const int nr_iters = 2;
 	const char *file = "./test_obj_id.o";
 	const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
+	const char *expected_prog_name = "test_obj_id";
+	const char *expected_map_name = "test_map_id";
+	const __u64 nsec_per_sec = 1000000000;
 
 	struct bpf_object *objs[nr_iters];
 	int prog_fds[nr_iters], map_fds[nr_iters];
 	/* +1 to test for the info_len returned by kernel */
 	struct bpf_prog_info prog_infos[nr_iters + 1];
 	struct bpf_map_info map_infos[nr_iters + 1];
+	/* Each prog only uses one map. +1 to test nr_map_ids
+	 * returned by kernel.
+	 */
+	__u32 map_ids[nr_iters + 1];
 	char jited_insns[128], xlated_insns[128], zeros[128];
 	__u32 i, next_id, info_len, nr_id_found, duration = 0;
+	struct timespec real_time_ts, boot_time_ts;
 	int sysctl_fd, jit_enabled = 0, err = 0;
 	__u64 array_value;
+	uid_t my_uid = getuid();
+	time_t now, load_time;
 
 	sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
 	if (sysctl_fd != -1) {
@@ -307,6 +320,7 @@ static void test_bpf_obj_id(void)
 	/* Check bpf_obj_get_info_by_fd() */
 	bzero(zeros, sizeof(zeros));
 	for (i = 0; i < nr_iters; i++) {
+		now = time(NULL);
 		err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER,
 				    &objs[i], &prog_fds[i]);
 		/* test_obj_id.o is a dumb prog. It should never fail
@@ -316,6 +330,38 @@ static void test_bpf_obj_id(void)
 			error_cnt++;
 		assert(!err);
 
+		/* Insert a magic value to the map */
+		map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id");
+		assert(map_fds[i] >= 0);
+		err = bpf_map_update_elem(map_fds[i], &array_key,
+					  &array_magic_value, 0);
+		assert(!err);
+
+		/* Check getting map info */
+		info_len = sizeof(struct bpf_map_info) * 2;
+		bzero(&map_infos[i], info_len);
+		err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i],
+					     &info_len);
+		if (CHECK(err ||
+			  map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
+			  map_infos[i].key_size != sizeof(__u32) ||
+			  map_infos[i].value_size != sizeof(__u64) ||
+			  map_infos[i].max_entries != 1 ||
+			  map_infos[i].map_flags != 0 ||
+			  info_len != sizeof(struct bpf_map_info) ||
+			  strcmp((char *)map_infos[i].name, expected_map_name),
+			  "get-map-info(fd)",
+			  "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n",
+			  err, errno,
+			  map_infos[i].type, BPF_MAP_TYPE_ARRAY,
+			  info_len, sizeof(struct bpf_map_info),
+			  map_infos[i].key_size,
+			  map_infos[i].value_size,
+			  map_infos[i].max_entries,
+			  map_infos[i].map_flags,
+			  map_infos[i].name, expected_map_name))
+			goto done;
+
 		/* Check getting prog info */
 		info_len = sizeof(struct bpf_prog_info) * 2;
 		bzero(&prog_infos[i], info_len);
@@ -325,8 +371,16 @@ static void test_bpf_obj_id(void)
 		prog_infos[i].jited_prog_len = sizeof(jited_insns);
 		prog_infos[i].xlated_prog_insns = ptr_to_u64(xlated_insns);
 		prog_infos[i].xlated_prog_len = sizeof(xlated_insns);
+		prog_infos[i].map_ids = ptr_to_u64(map_ids + i);
+		prog_infos[i].nr_map_ids = 2;
+		err = clock_gettime(CLOCK_REALTIME, &real_time_ts);
+		assert(!err);
+		err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts);
+		assert(!err);
 		err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i],
 					     &info_len);
+		load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec)
+			+ (prog_infos[i].load_time / nsec_per_sec);
 		if (CHECK(err ||
 			  prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER ||
 			  info_len != sizeof(struct bpf_prog_info) ||
@@ -334,9 +388,14 @@ static void test_bpf_obj_id(void)
 			  (jit_enabled &&
 			   !memcmp(jited_insns, zeros, sizeof(zeros))) ||
 			  !prog_infos[i].xlated_prog_len ||
-			  !memcmp(xlated_insns, zeros, sizeof(zeros)),
+			  !memcmp(xlated_insns, zeros, sizeof(zeros)) ||
+			  load_time < now - 60 || load_time > now + 60 ||
+			  prog_infos[i].created_by_uid != my_uid ||
+			  prog_infos[i].nr_map_ids != 1 ||
+			  *(int *)prog_infos[i].map_ids != map_infos[i].id ||
+			  strcmp((char *)prog_infos[i].name, expected_prog_name),
 			  "get-prog-info(fd)",
-			  "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d\n",
+			  "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n",
 			  err, errno, i,
 			  prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
 			  info_len, sizeof(struct bpf_prog_info),
@@ -344,36 +403,12 @@ static void test_bpf_obj_id(void)
 			  prog_infos[i].jited_prog_len,
 			  prog_infos[i].xlated_prog_len,
 			  !!memcmp(jited_insns, zeros, sizeof(zeros)),
-			  !!memcmp(xlated_insns, zeros, sizeof(zeros))))
-			goto done;
-
-		map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id");
-		assert(map_fds[i] >= 0);
-		err = bpf_map_update_elem(map_fds[i], &array_key,
-					  &array_magic_value, 0);
-		assert(!err);
-
-		/* Check getting map info */
-		info_len = sizeof(struct bpf_map_info) * 2;
-		bzero(&map_infos[i], info_len);
-		err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i],
-					     &info_len);
-		if (CHECK(err ||
-			  map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
-			  map_infos[i].key_size != sizeof(__u32) ||
-			  map_infos[i].value_size != sizeof(__u64) ||
-			  map_infos[i].max_entries != 1 ||
-			  map_infos[i].map_flags != 0 ||
-			  info_len != sizeof(struct bpf_map_info),
-			  "get-map-info(fd)",
-			  "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X\n",
-			  err, errno,
-			  map_infos[i].type, BPF_MAP_TYPE_ARRAY,
-			  info_len, sizeof(struct bpf_map_info),
-			  map_infos[i].key_size,
-			  map_infos[i].value_size,
-			  map_infos[i].max_entries,
-			  map_infos[i].map_flags))
+			  !!memcmp(xlated_insns, zeros, sizeof(zeros)),
+			  load_time, now,
+			  prog_infos[i].created_by_uid, my_uid,
+			  prog_infos[i].nr_map_ids, 1,
+			  *(int *)prog_infos[i].map_ids, map_infos[i].id,
+			  prog_infos[i].name, expected_prog_name))
 			goto done;
 	}
 
@@ -382,6 +417,7 @@ static void test_bpf_obj_id(void)
 	next_id = 0;
 	while (!bpf_prog_get_next_id(next_id, &next_id)) {
 		struct bpf_prog_info prog_info = {};
+		__u32 saved_map_id;
 		int prog_fd;
 
 		info_len = sizeof(prog_info);
@@ -404,16 +440,33 @@ static void test_bpf_obj_id(void)
 
 		nr_id_found++;
 
+		/* Negative test:
+		 * prog_info.nr_map_ids = 1
+		 * prog_info.map_ids = NULL
+		 */
+		prog_info.nr_map_ids = 1;
+		err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
+		if (CHECK(!err || errno != EFAULT,
+			  "get-prog-fd-bad-nr-map-ids", "err %d errno %d(%d)",
+			  err, errno, EFAULT))
+			break;
+		bzero(&prog_info, sizeof(prog_info));
+		info_len = sizeof(prog_info);
+
+		saved_map_id = *(int *)(prog_infos[i].map_ids);
+		prog_info.map_ids = prog_infos[i].map_ids;
+		prog_info.nr_map_ids = 2;
 		err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
 		prog_infos[i].jited_prog_insns = 0;
 		prog_infos[i].xlated_prog_insns = 0;
 		CHECK(err || info_len != sizeof(struct bpf_prog_info) ||
-		      memcmp(&prog_info, &prog_infos[i], info_len),
+		      memcmp(&prog_info, &prog_infos[i], info_len) ||
+		      *(int *)prog_info.map_ids != saved_map_id,
 		      "get-prog-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%lu) memcmp %d\n",
+		      "err %d errno %d info_len %u(%lu) memcmp %d map_id %u(%u)\n",
 		      err, errno, info_len, sizeof(struct bpf_prog_info),
-		      memcmp(&prog_info, &prog_infos[i], info_len));
-
+		      memcmp(&prog_info, &prog_infos[i], info_len),
+		      *(int *)prog_info.map_ids, saved_map_id);
 		close(prog_fd);
 	}
 	CHECK(nr_id_found != nr_iters,
@@ -495,6 +548,75 @@ static void test_pkt_md_access(void)
 	bpf_object__close(obj);
 }
 
+static void test_obj_name(void)
+{
+	struct {
+		const char *name;
+		int success;
+		int expected_errno;
+	} tests[] = {
+		{ "", 1, 0 },
+		{ "_123456789ABCDE", 1, 0 },
+		{ "_123456789ABCDEF", 0, EINVAL },
+		{ "_123456789ABCD\n", 0, EINVAL },
+	};
+	struct bpf_insn prog[] = {
+		BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	__u32 duration = 0;
+	int i;
+
+	for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
+		size_t name_len = strlen(tests[i].name) + 1;
+		union bpf_attr attr;
+		size_t ncopy;
+		int fd;
+
+		/* test different attr.prog_name during BPF_PROG_LOAD */
+		ncopy = name_len < sizeof(attr.prog_name) ?
+			name_len : sizeof(attr.prog_name);
+		bzero(&attr, sizeof(attr));
+		attr.prog_type = BPF_PROG_TYPE_SCHED_CLS;
+		attr.insn_cnt = 2;
+		attr.insns = ptr_to_u64(prog);
+		attr.license = ptr_to_u64("");
+		memcpy(attr.prog_name, tests[i].name, ncopy);
+
+		fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
+		CHECK((tests[i].success && fd < 0) ||
+		      (!tests[i].success && fd != -1) ||
+		      (!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)
+			close(fd);
+
+		/* test different attr.map_name during BPF_MAP_CREATE */
+		ncopy = name_len < sizeof(attr.map_name) ?
+			name_len : sizeof(attr.map_name);
+		bzero(&attr, sizeof(attr));
+		attr.map_type = BPF_MAP_TYPE_ARRAY;
+		attr.key_size = 4;
+		attr.value_size = 4;
+		attr.max_entries = 1;
+		attr.map_flags = 0;
+		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 && 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)
+			close(fd);
+	}
+}
+
 int main(void)
 {
 	struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
@@ -507,6 +629,7 @@ int main(void)
 	test_tcp_estats();
 	test_bpf_obj_id();
 	test_pkt_md_access();
+	test_obj_name();
 
 	printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
 	return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 64ae21f64489..bb3c4ad8c59f 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -6658,6 +6658,253 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 	},
 	{
+		"meta access, test1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 8),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid access to packet, off=-8",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test3",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid access to packet",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test4",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid access to packet",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test5",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_4, 3),
+			BPF_MOV64_IMM(BPF_REG_2, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_xdp_adjust_meta),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "R3 !read_ok",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test6",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_0, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid access to packet",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test7",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test8",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xFFFF),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test9",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xFFFF),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 1),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid access to packet",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test10",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_IMM(BPF_REG_5, 42),
+			BPF_MOV64_IMM(BPF_REG_6, 24),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8),
+			BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_5),
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_5, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid access to packet",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test11",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_IMM(BPF_REG_5, 42),
+			BPF_MOV64_IMM(BPF_REG_6, 24),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8),
+			BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_5),
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_5, BPF_REG_5, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"meta access, test12",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 16),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_4, 5),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 0),
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 16),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
 		"arithmetic ops make PTR_TO_CTX unusable",
 		.insns = {
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
@@ -7151,6 +7398,520 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_XDP,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
+	{
+		"XDP pkt read, pkt_meta' > pkt_data, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_meta' > pkt_data, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_meta' > pkt_data, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data > pkt_meta', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data > pkt_meta', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data > pkt_meta', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_meta' < pkt_data, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_meta' < pkt_data, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_meta' < pkt_data, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data < pkt_meta', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data < pkt_meta', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data < pkt_meta', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_meta' >= pkt_data, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_meta' >= pkt_data, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_meta' >= pkt_data, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data >= pkt_meta', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data >= pkt_meta', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data >= pkt_meta', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_meta' <= pkt_data, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_meta' <= pkt_data, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_meta' <= pkt_data, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data <= pkt_meta', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data <= pkt_meta', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data <= pkt_meta', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data_meta)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"bpf_exit with invalid return code. test1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 has value (0x0; 0xffffffff)",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test3",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 3),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 has value (0x0; 0x3)",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test4",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test5",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 has value (0x2; 0x0)",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test6",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 is not a known value (ctx)",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
+	{
+		"bpf_exit with invalid return code. test7",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 4),
+			BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_2),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 has unknown scalar value",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -7198,7 +7959,7 @@ static int create_map_in_map(void)
 		return inner_map_fd;
 	}
 
-	outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL,
 					     sizeof(int), inner_map_fd, 1, 0);
 	if (outer_map_fd < 0)
 		printf("Failed to create array of maps '%s'!\n",
diff --git a/tools/testing/selftests/bpf/test_verifier_log.c b/tools/testing/selftests/bpf/test_verifier_log.c
new file mode 100644
index 000000000000..3cc0b561489e
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_verifier_log.c
@@ -0,0 +1,171 @@
+#include <errno.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/unistd.h>
+
+#include <bpf/bpf.h>
+
+#define LOG_SIZE (1 << 20)
+
+#define err(str...)	printf("ERROR: " str)
+
+static const struct bpf_insn code_sample[] = {
+	/* We need a few instructions to pass the min log length */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+		     BPF_FUNC_map_lookup_elem),
+	BPF_EXIT_INSN(),
+};
+
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
+static int load(char *log, size_t log_len, int log_level)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	attr.insn_cnt = (__u32)(sizeof(code_sample) / sizeof(struct bpf_insn));
+	attr.insns = ptr_to_u64(code_sample);
+	attr.license = ptr_to_u64("GPL");
+	attr.log_buf = ptr_to_u64(log);
+	attr.log_size = log_len;
+	attr.log_level = log_level;
+
+	return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
+}
+
+static void check_ret(int ret, int exp_errno)
+{
+	if (ret > 0) {
+		close(ret);
+		err("broken sample loaded successfully!?\n");
+		exit(1);
+	}
+
+	if (!ret || errno != exp_errno) {
+		err("Program load returned: ret:%d/errno:%d, expected ret:%d/errno:%d\n",
+		    ret, errno, -1, exp_errno);
+		exit(1);
+	}
+}
+
+static void check_ones(const char *buf, size_t len, const char *msg)
+{
+	while (len--)
+		if (buf[len] != 1) {
+			err("%s", msg);
+			exit(1);
+		}
+}
+
+static void test_log_good(char *log, size_t buf_len, size_t log_len,
+			  size_t exp_len, int exp_errno, const char *full_log)
+{
+	size_t len;
+	int ret;
+
+	memset(log, 1, buf_len);
+
+	ret = load(log, log_len, 1);
+	check_ret(ret, exp_errno);
+
+	len = strnlen(log, buf_len);
+	if (len == buf_len) {
+		err("verifier did not NULL terminate the log\n");
+		exit(1);
+	}
+	if (exp_len && len != exp_len) {
+		err("incorrect log length expected:%zd have:%zd\n",
+		    exp_len, len);
+		exit(1);
+	}
+
+	if (strchr(log, 1)) {
+		err("verifier leaked a byte through\n");
+		exit(1);
+	}
+
+	check_ones(log + len + 1, buf_len - len - 1,
+		   "verifier wrote bytes past NULL termination\n");
+
+	if (memcmp(full_log, log, LOG_SIZE)) {
+		err("log did not match expected output\n");
+		exit(1);
+	}
+}
+
+static void test_log_bad(char *log, size_t log_len, int log_level)
+{
+	int ret;
+
+	ret = load(log, log_len, log_level);
+	check_ret(ret, EINVAL);
+	if (log)
+		check_ones(log, LOG_SIZE,
+			   "verifier touched log with bad parameters\n");
+}
+
+int main(int argc, char **argv)
+{
+	char full_log[LOG_SIZE];
+	char log[LOG_SIZE];
+	size_t want_len;
+	int i;
+
+	memset(log, 1, LOG_SIZE);
+
+	/* Test incorrect attr */
+	printf("Test log_level 0...\n");
+	test_log_bad(log, LOG_SIZE, 0);
+
+	printf("Test log_size < 128...\n");
+	test_log_bad(log, 15, 1);
+
+	printf("Test log_buff = NULL...\n");
+	test_log_bad(NULL, LOG_SIZE, 1);
+
+	/* Test with log big enough */
+	printf("Test oversized buffer...\n");
+	test_log_good(full_log, LOG_SIZE, LOG_SIZE, 0, EACCES, full_log);
+
+	want_len = strlen(full_log);
+
+	printf("Test exact buffer...\n");
+	test_log_good(log, LOG_SIZE, want_len + 2, want_len, EACCES, full_log);
+
+	printf("Test undersized buffers...\n");
+	for (i = 0; i < 64; i++) {
+		full_log[want_len - i + 1] = 1;
+		full_log[want_len - i] = 0;
+
+		test_log_good(log, LOG_SIZE, want_len + 1 - i, want_len - i,
+			      ENOSPC, full_log);
+	}
+
+	printf("test_verifier_log: OK\n");
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_xdp_meta.c b/tools/testing/selftests/bpf/test_xdp_meta.c
new file mode 100644
index 000000000000..8d0182650653
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_meta.c
@@ -0,0 +1,53 @@
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/pkt_cls.h>
+
+#include "bpf_helpers.h"
+
+#define __round_mask(x, y) ((__typeof__(x))((y) - 1))
+#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1)
+#define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem
+
+SEC("t")
+int ing_cls(struct __sk_buff *ctx)
+{
+	__u8 *data, *data_meta, *data_end;
+	__u32 diff = 0;
+
+	data_meta = ctx_ptr(ctx, data_meta);
+	data_end  = ctx_ptr(ctx, data_end);
+	data      = ctx_ptr(ctx, data);
+
+	if (data + ETH_ALEN > data_end ||
+	    data_meta + round_up(ETH_ALEN, 4) > data)
+		return TC_ACT_SHOT;
+
+	diff |= ((__u32 *)data_meta)[0] ^ ((__u32 *)data)[0];
+	diff |= ((__u16 *)data_meta)[2] ^ ((__u16 *)data)[2];
+
+	return diff ? TC_ACT_SHOT : TC_ACT_OK;
+}
+
+SEC("x")
+int ing_xdp(struct xdp_md *ctx)
+{
+	__u8 *data, *data_meta, *data_end;
+	int ret;
+
+	ret = bpf_xdp_adjust_meta(ctx, -round_up(ETH_ALEN, 4));
+	if (ret < 0)
+		return XDP_DROP;
+
+	data_meta = ctx_ptr(ctx, data_meta);
+	data_end  = ctx_ptr(ctx, data_end);
+	data      = ctx_ptr(ctx, data);
+
+	if (data + ETH_ALEN > data_end ||
+	    data_meta + round_up(ETH_ALEN, 4) > data)
+		return XDP_DROP;
+
+	__builtin_memcpy(data_meta, data, ETH_ALEN);
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh
new file mode 100755
index 000000000000..307aa856cee3
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_meta.sh
@@ -0,0 +1,51 @@
+#!/bin/sh
+
+cleanup()
+{
+	if [ "$?" = "0" ]; then
+		echo "selftests: test_xdp_meta [PASS]";
+	else
+		echo "selftests: test_xdp_meta [FAILED]";
+	fi
+
+	set +e
+	ip netns del ns1 2> /dev/null
+	ip netns del ns2 2> /dev/null
+}
+
+ip link set dev lo xdp off 2>/dev/null > /dev/null
+if [ $? -ne 0 ];then
+	echo "selftests: [SKIP] Could not run test without the ip xdp support"
+	exit 0
+fi
+set -e
+
+ip netns add ns1
+ip netns add ns2
+
+trap cleanup 0 2 3 6 9
+
+ip link add veth1 type veth peer name veth2
+
+ip link set veth1 netns ns1
+ip link set veth2 netns ns2
+
+ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth1
+ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth2
+
+ip netns exec ns1 tc qdisc add dev veth1 clsact
+ip netns exec ns2 tc qdisc add dev veth2 clsact
+
+ip netns exec ns1 tc filter add dev veth1 ingress bpf da obj test_xdp_meta.o sec t
+ip netns exec ns2 tc filter add dev veth2 ingress bpf da obj test_xdp_meta.o sec t
+
+ip netns exec ns1 ip link set dev veth1 xdp obj test_xdp_meta.o sec x
+ip netns exec ns2 ip link set dev veth2 xdp obj test_xdp_meta.o sec x
+
+ip netns exec ns1 ip link set dev veth1 up
+ip netns exec ns2 ip link set dev veth2 up
+
+ip netns exec ns1 ping -c 1 10.1.1.22
+ip netns exec ns2 ping -c 1 10.1.1.11
+
+exit 0
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 57b5ff576240..5215493166c9 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -15,6 +15,14 @@ check_err()
 	fi
 }
 
+# same but inverted -- used when command must fail for test to pass
+check_fail()
+{
+	if [ $1 -eq 0 ]; then
+		ret=1
+	fi
+}
+
 kci_add_dummy()
 {
 	ip link add name "$devdummy" type dummy
@@ -29,6 +37,26 @@ kci_del_dummy()
 	check_err $?
 }
 
+kci_test_netconf()
+{
+	dev="$1"
+	r=$ret
+
+	ip netconf show dev "$dev" > /dev/null
+	check_err $?
+
+	for f in 4 6; do
+		ip -$f netconf show dev "$dev" > /dev/null
+		check_err $?
+	done
+
+	if [ $ret -ne 0 ] ;then
+		echo "FAIL: ip netconf show $dev"
+		test $r -eq 0 && ret=0
+		return 1
+	fi
+}
+
 # add a bridge with vlans on top
 kci_test_bridge()
 {
@@ -55,6 +83,11 @@ kci_test_bridge()
 	check_err $?
 	ip r s t all > /dev/null
 	check_err $?
+
+	for name in "$devbr" "$vlandev" "$devdummy" ; do
+		kci_test_netconf "$name"
+	done
+
 	ip -6 addr del dev "$vlandev" dead:42::1234/64
 	check_err $?
 
@@ -92,6 +125,9 @@ kci_test_gre()
 	check_err $?
 	ip addr > /dev/null
 	check_err $?
+
+	kci_test_netconf "$gredev"
+
 	ip addr del dev "$devdummy" 10.23.7.11/24
 	check_err $?
 
@@ -235,6 +271,237 @@ kci_test_addrlabel()
 	echo "PASS: ipv6 addrlabel"
 }
 
+kci_test_ifalias()
+{
+	ret=0
+	namewant=$(uuidgen)
+	syspathname="/sys/class/net/$devdummy/ifalias"
+
+	ip link set dev "$devdummy" alias "$namewant"
+	check_err $?
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: cannot set interface alias of $devdummy to $namewant"
+		return 1
+	fi
+
+	ip link show "$devdummy" | grep -q "alias $namewant"
+	check_err $?
+
+	if [ -r "$syspathname" ] ; then
+		read namehave < "$syspathname"
+		if [ "$namewant" != "$namehave" ]; then
+			echo "FAIL: did set ifalias $namewant but got $namehave"
+			return 1
+		fi
+
+		namewant=$(uuidgen)
+		echo "$namewant" > "$syspathname"
+	        ip link show "$devdummy" | grep -q "alias $namewant"
+		check_err $?
+
+		# sysfs interface allows to delete alias again
+		echo "" > "$syspathname"
+
+	        ip link show "$devdummy" | grep -q "alias $namewant"
+		check_fail $?
+
+		for i in $(seq 1 100); do
+			uuidgen > "$syspathname" &
+		done
+
+		wait
+
+		# re-add the alias -- kernel should free mem when dummy dev is removed
+		ip link set dev "$devdummy" alias "$namewant"
+		check_err $?
+	fi
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: set interface alias $devdummy to $namewant"
+		return 1
+	fi
+
+	echo "PASS: set ifalias $namewant for $devdummy"
+}
+
+kci_test_vrf()
+{
+	vrfname="test-vrf"
+	ret=0
+
+	ip link show type vrf 2>/dev/null
+	if [ $? -ne 0 ]; then
+		echo "SKIP: vrf: iproute2 too old"
+		return 0
+	fi
+
+	ip link add "$vrfname" type vrf table 10
+	check_err $?
+	if [ $ret -ne 0 ];then
+		echo "FAIL: can't add vrf interface, skipping test"
+		return 0
+	fi
+
+	ip -br link show type vrf | grep -q "$vrfname"
+	check_err $?
+	if [ $ret -ne 0 ];then
+		echo "FAIL: created vrf device not found"
+		return 1
+	fi
+
+	ip link set dev "$vrfname" up
+	check_err $?
+
+	ip link set dev "$devdummy" master "$vrfname"
+	check_err $?
+	ip link del dev "$vrfname"
+	check_err $?
+
+	if [ $ret -ne 0 ];then
+		echo "FAIL: vrf"
+		return 1
+	fi
+
+	echo "PASS: vrf"
+}
+
+kci_test_encap_vxlan()
+{
+	ret=0
+	vxlan="test-vxlan0"
+	vlan="test-vlan0"
+	testns="$1"
+
+	ip netns exec "$testns" ip link add "$vxlan" type vxlan id 42 group 239.1.1.1 \
+		dev "$devdummy" dstport 4789 2>/dev/null
+	if [ $? -ne 0 ]; then
+		echo "FAIL: can't add vxlan interface, skipping test"
+		return 0
+	fi
+	check_err $?
+
+	ip netns exec "$testns" ip addr add 10.2.11.49/24 dev "$vxlan"
+	check_err $?
+
+	ip netns exec "$testns" ip link set up dev "$vxlan"
+	check_err $?
+
+	ip netns exec "$testns" ip link add link "$vxlan" name "$vlan" type vlan id 1
+	check_err $?
+
+	ip netns exec "$testns" ip link del "$vxlan"
+	check_err $?
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: vxlan"
+		return 1
+	fi
+	echo "PASS: vxlan"
+}
+
+kci_test_encap_fou()
+{
+	ret=0
+	name="test-fou"
+	testns="$1"
+
+	ip fou help 2>&1 |grep -q 'Usage: ip fou'
+	if [ $? -ne 0 ];then
+		echo "SKIP: fou: iproute2 too old"
+		return 1
+	fi
+
+	ip netns exec "$testns" ip fou add port 7777 ipproto 47 2>/dev/null
+	if [ $? -ne 0 ];then
+		echo "FAIL: can't add fou port 7777, skipping test"
+		return 1
+	fi
+
+	ip netns exec "$testns" ip fou add port 8888 ipproto 4
+	check_err $?
+
+	ip netns exec "$testns" ip fou del port 9999 2>/dev/null
+	check_fail $?
+
+	ip netns exec "$testns" ip fou del port 7777
+	check_err $?
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: fou"
+		return 1
+	fi
+
+	echo "PASS: fou"
+}
+
+# test various encap methods, use netns to avoid unwanted interference
+kci_test_encap()
+{
+	testns="testns"
+	ret=0
+
+	ip netns add "$testns"
+	if [ $? -ne 0 ]; then
+		echo "SKIP encap tests: cannot add net namespace $testns"
+		return 1
+	fi
+
+	ip netns exec "$testns" ip link set lo up
+	check_err $?
+
+	ip netns exec "$testns" ip link add name "$devdummy" type dummy
+	check_err $?
+	ip netns exec "$testns" ip link set "$devdummy" up
+	check_err $?
+
+	kci_test_encap_vxlan "$testns"
+	kci_test_encap_fou "$testns"
+
+	ip netns del "$testns"
+}
+
+kci_test_macsec()
+{
+	msname="test_macsec0"
+	ret=0
+
+	ip macsec help 2>&1 | grep -q "^Usage: ip macsec"
+	if [ $? -ne 0 ]; then
+		echo "SKIP: macsec: iproute2 too old"
+		return 0
+	fi
+
+	ip link add link "$devdummy" "$msname" type macsec port 42 encrypt on
+	check_err $?
+	if [ $ret -ne 0 ];then
+		echo "FAIL: can't add macsec interface, skipping test"
+		return 1
+	fi
+
+	ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012
+	check_err $?
+
+	ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef"
+	check_err $?
+
+	ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on key 00 0123456789abcdef0123456789abcdef
+	check_err $?
+
+	ip macsec show > /dev/null
+	check_err $?
+
+	ip link del dev "$msname"
+	check_err $?
+
+	if [ $ret -ne 0 ];then
+		echo "FAIL: macsec"
+		return 1
+	fi
+
+	echo "PASS: macsec"
+}
+
 kci_test_rtnl()
 {
 	kci_add_dummy
@@ -249,6 +516,10 @@ kci_test_rtnl()
 	kci_test_gre
 	kci_test_bridge
 	kci_test_addrlabel
+	kci_test_ifalias
+	kci_test_vrf
+	kci_test_encap
+	kci_test_macsec
 
 	kci_del_dummy
 }
diff --git a/tools/testing/selftests/tc-testing/.gitignore b/tools/testing/selftests/tc-testing/.gitignore
index c18dd8d83cee..7a60b85e148f 100644
--- a/tools/testing/selftests/tc-testing/.gitignore
+++ b/tools/testing/selftests/tc-testing/.gitignore
@@ -1 +1,2 @@
 __pycache__/
+*.pyc
diff --git a/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt b/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt
index 4e09257bc443..00438331ba47 100644
--- a/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt
+++ b/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt
@@ -34,6 +34,12 @@ category:     A list of single-word descriptions covering what the command
 setup:        The list of commands required to ensure the command under test
               succeeds. For example: if testing a filter, the command to create
               the qdisc would appear here.
+	      This list can be empty.
+	      Each command can be a string to be executed, or a list consisting
+	      of a string which is a command to be executed, followed by 1 or
+	      more acceptable exit codes for this command.
+	      If only a string is given for the command, then an exit code of 0
+	      will be expected.
 cmdUnderTest: The tc command being tested itself.
 expExitCode:  The code returned by the command under test upon its termination.
               tdc will compare this value against the actual returned value.
@@ -49,6 +55,12 @@ matchCount:   How many times the regex in matchPattern should match. A value
 teardown:     The list of commands to clean up after the test is completed.
               The environment should be returned to the same state as when
               this test was started: qdiscs deleted, actions flushed, etc.
+	      This list can be empty.
+	      Each command can be a string to be executed, or a list consisting
+	      of a string which is a command to be executed, followed by 1 or
+	      more acceptable exit codes for this command.
+	      If only a string is given for the command, then an exit code of 0
+	      will be expected.
 
 
 SETUP/TEARDOWN ERRORS
diff --git a/tools/testing/selftests/tc-testing/creating-testcases/example.json b/tools/testing/selftests/tc-testing/creating-testcases/example.json
new file mode 100644
index 000000000000..5ec501200970
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/creating-testcases/example.json
@@ -0,0 +1,55 @@
+[
+    {
+        "id": "1f",
+        "name": "simple test to test framework",
+        "category": [
+            "example"
+        ],
+        "setup": [
+            "mkdir mytest"
+        ],
+        "cmdUnderTest": "touch mytest/blorfl",
+        "expExitCode": "0",
+        "verifyCmd": "ls mytest/* | grep '[b]lorfl'",
+        "matchPattern": "orfl",
+        "matchCount": "1",
+        "teardown": [
+            "rm -rf mytest"
+        ]
+    },
+    {
+        "id": "2f",
+        "name": "simple test, no need for verify",
+        "category": [
+            "example"
+        ],
+        "setup": [
+            "mkdir mytest",
+            "touch mytest/blorfl"
+        ],
+        "cmdUnderTest": "ls mytest/blorfl",
+        "expExitCode": "0",
+        "verifyCmd": "/bin/true",
+        "matchPattern": " ",
+        "matchCount": "0",
+        "teardown": [
+            "rm -rf mytest"
+        ]
+    },
+    {
+        "id": "3f",
+        "name": "simple test, no need for setup or teardown (or verify)",
+        "category": [
+            "example"
+        ],
+        "setup": [
+        ],
+        "cmdUnderTest": "ip l l lo",
+        "expExitCode": "0",
+        "verifyCmd": "/bin/true",
+        "matchPattern": " ",
+        "matchCount": "0",
+        "teardown": [
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/creating-testcases/template.json b/tools/testing/selftests/tc-testing/creating-testcases/template.json
index 87971744bdd4..8b99b86d65bd 100644
--- a/tools/testing/selftests/tc-testing/creating-testcases/template.json
+++ b/tools/testing/selftests/tc-testing/creating-testcases/template.json
@@ -26,7 +26,13 @@
             ""
         ],
         "setup": [
-            ""
+            "",
+	    [
+		"",
+		0,
+		1,
+		255
+	    ]
         ],
         "cmdUnderTest": "",
         "expExitCode": "",
@@ -34,7 +40,12 @@
         "matchPattern": "",
         "matchCount": "",
         "teardown": [
-            ""
+            "",
+	    [
+		"",
+		0,
+		255
+            ]
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
new file mode 100644
index 000000000000..e2187b6e0b7a
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
@@ -0,0 +1,469 @@
+[
+    {
+        "id": "e89a",
+        "name": "Add valid pass action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pass index 8",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pass.*index 8 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "a02c",
+        "name": "Add valid pipe action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pipe index 6",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pipe.*index 6 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "feef",
+        "name": "Add valid reclassify action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action reclassify index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify.*index 5 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "8a7a",
+        "name": "Add valid drop action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action drop index 30",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 30 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "9a52",
+        "name": "Add valid continue action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action continue index 432",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action continue.*index 432 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "d700",
+        "name": "Add invalid action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pump index 386",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action.*index 386 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "9215",
+        "name": "Add action with duplicate index",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pipe index 15"
+        ],
+        "cmdUnderTest": "$TC actions add action drop index 15",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 15 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "798e",
+        "name": "Add action with index exceeding 32-bit maximum",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action drop index 4294967296",
+        "expExitCode": "255",
+        "verifyCmd": "actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 4294967296 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "22be",
+        "name": "Add action with index at 32-bit maximum",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action drop index 4294967295",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 4294967295 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "ac2a",
+        "name": "List actions",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action reclassify index 101",
+            "$TC actions add action reclassify index 102",
+            "$TC actions add action reclassify index 103",
+            "$TC actions add action reclassify index 104",
+            "$TC actions add action reclassify index 105"
+        ],
+        "cmdUnderTest": "$TC actions list action gact",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify",
+        "matchCount": "5",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "3edf",
+        "name": "Flush gact actions",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            "$TC actions add action reclassify index 101",
+            "$TC actions add action reclassify index 102",
+            "$TC actions add action reclassify index 103",
+            "$TC actions add action reclassify index 104",
+            "$TC actions add action reclassify index 105"
+        ],
+        "cmdUnderTest": "$TC actions flush action gact",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify",
+        "matchCount": "0",
+        "teardown": []
+    },
+    {
+        "id": "63ec",
+        "name": "Delete pass action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pass index 1"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pass.*index 1 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "46be",
+        "name": "Delete pipe action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pipe index 9"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 9",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pipe.*index 9 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "2e08",
+        "name": "Delete reclassify action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action reclassify index 65536"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 65536",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify.*index 65536 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "99c4",
+        "name": "Delete drop action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action drop index 16"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 16",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 16 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "fb6b",
+        "name": "Delete continue action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action continue index 32"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 32",
+        "expExitCode": "0",
+        "verifyCmd": "actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action continue.*index 32 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "0eb3",
+        "name": "Delete non-existent action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 2",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "f02c",
+        "name": "Replace gact action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action drop index 10",
+            "$TC actions add action drop index 12"
+        ],
+        "cmdUnderTest": "$TC actions replace action ok index 12",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action gact",
+        "matchPattern": "action order [0-9]*: gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "525f",
+        "name": "Get gact action by index",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action drop index 3900800700"
+        ],
+        "cmdUnderTest": "$TC actions get action gact index 3900800700",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action gact index 3900800700",
+        "matchPattern": "index 3900800700",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
new file mode 100644
index 000000000000..9f34f0753969
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
@@ -0,0 +1,52 @@
+[
+    {
+        "id": "a568",
+        "name": "Add action with ife type",
+        "category": [
+            "actions",
+            "ife"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action ife",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action ife encode type 0xDEAD index 1"
+        ],
+        "cmdUnderTest": "$TC actions get action ife index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action ife index 1",
+        "matchPattern": "type 0xDEAD",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action ife"
+        ]
+    },
+    {
+        "id": "b983",
+        "name": "Add action without ife type",
+        "category": [
+            "actions",
+            "ife"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action ife",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action ife encode index 1"
+        ],
+        "cmdUnderTest": "$TC actions get action ife index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action ife index 1",
+        "matchPattern": "type 0xED3E",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action ife"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
new file mode 100644
index 000000000000..0fcccf18399b
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
@@ -0,0 +1,223 @@
+[
+    {
+        "id": "5124",
+        "name": "Add mirred mirror to egress action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress mirror index 1 dev lo",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 1 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "6fb4",
+        "name": "Add mirred redirect to egress action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress redirect index 2 dev lo action pipe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "ba38",
+        "name": "Get mirred actions",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress mirror index 1 dev lo",
+            "$TC actions add action mirred egress redirect index 2 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions show action mirred",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "[Mirror|Redirect] to device lo",
+        "matchCount": "2",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "d7c0",
+        "name": "Add invalid mirred direction",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred inbound mirror index 20 dev lo",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 20 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "e213",
+        "name": "Add invalid mirred action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress remirror index 20 dev lo",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress.*to device lo\\).*index 20 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "2d89",
+        "name": "Add mirred action with invalid device",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress mirror index 20 dev eltoh",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(.*to device eltoh\\).*index 20 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "300b",
+        "name": "Add mirred action with duplicate index",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress redirect index 15 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress mirror index 15 dev lo",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 15 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "a70e",
+        "name": "Delete mirred mirror action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress mirror index 5 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions del action mirred index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 5 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "3fb3",
+        "name": "Delete mirred redirect action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress redirect index 5 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions del action mirred index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 5 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
new file mode 100644
index 000000000000..0e602a3f9393
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -0,0 +1,527 @@
+[
+    {
+        "id": "49aa",
+        "name": "Add valid basic police action",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 1kbit burst 10k index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 1Kbit burst 10Kb",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "3abe",
+        "name": "Add police action with duplicate index",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 4Mbit burst 120k index 9"
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 8kbit burst 24k index 9",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x9",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "49fa",
+        "name": "Add valid police action with mtu",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 90kbit burst 10k mtu 1k index 98",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 98",
+        "matchPattern": "action order [0-9]*:  police 0x62 rate 90Kbit burst 10Kb mtu 1Kb",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "7943",
+        "name": "Add valid police action with peakrate",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 90kbit burst 10k mtu 2kb peakrate 100kbit index 3",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x3 rate 90Kbit burst 10Kb mtu 2Kb peakrate 100Kbit",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "055e",
+        "name": "Add police action with peakrate and no mtu",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 5kbit burst 6kb peakrate 10kbit index 9",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x9 rate 5Kb burst 10Kb",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "f057",
+        "name": "Add police action with valid overhead",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 1mbit burst 100k overhead 64 index 64",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 64",
+        "matchPattern": "action order [0-9]*:  police 0x40 rate 1Mbit burst 100Kb mtu 2Kb action reclassify overhead 64b",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "7ffb",
+        "name": "Add police action with ethernet linklayer type",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 2mbit burst 200k linklayer ethernet index 8",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions show action police",
+        "matchPattern": "action order [0-9]*:  police 0x8 rate 2Mbit burst 200Kb mtu 2Kb action reclassify overhead 0b",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "3dda",
+        "name": "Add police action with atm linklayer type",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 2mbit burst 200k linklayer atm index 8",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions show action police",
+        "matchPattern": "action order [0-9]*:  police 0x8 rate 2Mbit burst 200Kb mtu 2Kb action reclassify overhead 0b linklayer atm",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "551b",
+        "name": "Add police actions with conform-exceed control continue/drop",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed continue/drop index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 1",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 3Mbit burst 250Kb mtu 2Kb action continue/drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "0c70",
+        "name": "Add police actions with conform-exceed control pass/reclassify",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed pass/reclassify index 4",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x4 rate 3Mbit burst 250Kb mtu 2Kb action pass/reclassify",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "d946",
+        "name": "Add police actions with conform-exceed control pass/pipe",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed pass/pipe index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x5 rate 3Mbit burst 250Kb mtu 2Kb action pass/pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "336e",
+        "name": "Delete police action",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 5mbit burst 2m index 12"
+        ],
+        "cmdUnderTest": "$TC actions delete action police index 12",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0xc rate 5Mb burst 2Mb",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "77fa",
+        "name": "Get single police action from many actions",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 1mbit burst 100k index 1",
+            "$TC actions add action police rate 2mbit burst 200k index 2",
+            "$TC actions add action police rate 3mbit burst 300k index 3",
+            "$TC actions add action police rate 4mbit burst 400k index 4",
+            "$TC actions add action police rate 5mbit burst 500k index 5",
+            "$TC actions add action police rate 6mbit burst 600k index 6",
+            "$TC actions add action police rate 7mbit burst 700k index 7",
+            "$TC actions add action police rate 8mbit burst 800k index 8"
+        ],
+        "cmdUnderTest": "$TC actions get action police index 4",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 4",
+        "matchPattern": "action order [0-9]*:  police 0x4 rate 4Mbit burst 400Kb",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "aa43",
+        "name": "Get single police action without specifying index",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 1mbit burst 100k index 1"
+        ],
+        "cmdUnderTest": "$TC actions get action police",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action police",
+        "matchPattern": "action order [0-9]*:  police",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "858b",
+        "name": "List police actions",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 1mbit burst 100k index 1",
+            "$TC actions add action police rate 2mbit burst 200k index 2",
+            "$TC actions add action police rate 3mbit burst 300k index 3",
+            "$TC actions add action police rate 4mbit burst 400k index 4",
+            "$TC actions add action police rate 5mbit burst 500k index 5",
+            "$TC actions add action police rate 6mbit burst 600k index 6",
+            "$TC actions add action police rate 7mbit burst 700k index 7",
+            "$TC actions add action police rate 8mbit burst 800k index 8"
+        ],
+        "cmdUnderTest": "$TC actions list action police",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x[1-8] rate [1-8]Mbit burst [1-8]00Kb",
+        "matchCount": "8",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "1c3a",
+        "name": "Flush police actions",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            "$TC actions add action police rate 1mbit burst 100k index 1",
+            "$TC actions add action police rate 2mbit burst 200k index 2",
+            "$TC actions add action police rate 3mbit burst 300k index 3",
+            "$TC actions add action police rate 4mbit burst 400k index 4",
+            "$TC actions add action police rate 5mbit burst 500k index 5",
+            "$TC actions add action police rate 6mbit burst 600k index 6",
+            "$TC actions add action police rate 7mbit burst 700k index 7",
+            "$TC actions add action police rate 8mbit burst 800k index 8"
+        ],
+        "cmdUnderTest": "$TC actions flush action police",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police",
+        "matchCount": "0",
+        "teardown": [
+            ""
+        ]
+    },
+    {
+        "id": "7326",
+        "name": "Add police action with control continue",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m continue index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 1",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action continue",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "34fa",
+        "name": "Add police action with control drop",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m drop index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "8dd5",
+        "name": "Add police action with control ok",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m ok index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "b9d1",
+        "name": "Add police action with control reclassify",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m reclassify index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 1",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action reclassify",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "c534",
+        "name": "Add police action with control pipe",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m pipe index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
new file mode 100644
index 000000000000..e89a7aa4012d
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
@@ -0,0 +1,130 @@
+[
+    {
+        "id": "b078",
+        "name": "Add simple action",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action simple sdata \"A triumph\" index 60",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <A triumph>.*index 60 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
+    {
+        "id": "6d4c",
+        "name": "Add simple action with duplicate index",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"Aruba\" index 4"
+        ],
+        "cmdUnderTest": "$TC actions add action simple sdata \"Jamaica\" index 4",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <Jamaica>.*ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
+    {
+        "id": "2542",
+        "name": "List simple actions",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"Rock\"",
+            "$TC actions add action simple sdata \"Paper\"",
+            "$TC actions add action simple sdata \"Scissors\" index 98"
+        ],
+        "cmdUnderTest": "$TC actions list action simple",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>",
+        "matchCount": "3",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
+    {
+        "id": "ea67",
+        "name": "Delete simple action",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"Blinkenlights\" index 1"
+        ],
+        "cmdUnderTest": "$TC actions delete action simple index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <Blinkenlights>.*index 1 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
+    {
+        "id": "8ff1",
+        "name": "Flush simple actions",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"Kirk\"",
+            "$TC actions add action simple sdata \"Spock\" index 50",
+            "$TC actions add action simple sdata \"McCoy\" index 9"
+        ],
+        "cmdUnderTest": "$TC actions flush action simple",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>",
+        "matchCount": "0",
+        "teardown": [
+            ""
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
new file mode 100644
index 000000000000..99635ea4722e
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
@@ -0,0 +1,320 @@
+[
+    {
+        "id": "6236",
+        "name": "Add skbedit action with valid mark",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit mark 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "407b",
+        "name": "Add skbedit action with invalid mark",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 666777888999",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit mark",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "081d",
+        "name": "Add skbedit action with priority",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit prio 99",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit priority :99",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "cc37",
+        "name": "Add skbedit action with invalid priority",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit prio foo",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit priority",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "3c95",
+        "name": "Add skbedit action with queue_mapping",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit queue_mapping 909",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "985c",
+        "name": "Add skbedit action with invalid queue_mapping",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit queue_mapping 67000",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit queue_mapping",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "224f",
+        "name": "Add skbedit action with ptype host",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit ptype host",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit ptype host",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "d1a3",
+        "name": "Add skbedit action with ptype otherhost",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit ptype otherhost",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit ptype otherhost",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "b9c6",
+        "name": "Add skbedit action with invalid ptype",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit ptype openair",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit ptype openair",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "5172",
+        "name": "List skbedit actions",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbedit ptype otherhost",
+            "$TC actions add action skbedit ptype broadcast",
+            "$TC actions add action skbedit mark 59",
+            "$TC actions add action skbedit mark 409"
+        ],
+        "cmdUnderTest": "$TC actions list action skbedit",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit",
+        "matchCount": "4",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "a6d6",
+        "name": "Add skbedit action with index",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 808 index 4040404040",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "index 4040404040",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "38f3",
+        "name": "Delete skbedit action",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbedit mark 42 index 9009"
+        ],
+        "cmdUnderTest": "$TC actions del action skbedit index 9009",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit mark 42",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "ce97",
+        "name": "Flush skbedit actions",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            "$TC actions add action skbedit mark 500",
+            "$TC actions add action skbedit mark 501",
+            "$TC actions add action skbedit mark 502",
+            "$TC actions add action skbedit mark 503",
+            "$TC actions add action skbedit mark 504",
+            "$TC actions add action skbedit mark 505",
+            "$TC actions add action skbedit mark 506"
+        ],
+        "cmdUnderTest": "$TC actions flush action skbedit",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
new file mode 100644
index 000000000000..e34075059c26
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
@@ -0,0 +1,372 @@
+[
+    {
+        "id": "7d50",
+        "name": "Add skbmod action to set destination mac",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set dmac 11:22:33:44:55:66 index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set dmac 11:22:33:44:55:66\\s+index 5",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "9b29",
+        "name": "Add skbmod action to set source mac",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set smac 77:88:99:AA:BB:CC index 7",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action skbmod index 7",
+        "matchPattern": "action order [0-9]*: skbmod pipe set smac 77:88:99:aa:bb:cc\\s+index 7",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "1724",
+        "name": "Add skbmod action with invalid mac",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set smac 00:44:55:44:55",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set smac 00:44:55:44:55",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "3cf1",
+        "name": "Add skbmod action with valid etype",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0xfefe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0xFEFE",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "a749",
+        "name": "Add skbmod action with invalid etype",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0xfefef",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0xFEFEF",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "bfe6",
+        "name": "Add skbmod action to swap mac",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod swap mac",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action skbmod index 1",
+        "matchPattern": "action order [0-9]*: skbmod pipe swap mac",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "839b",
+        "name": "Add skbmod action with control pipe",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod swap mac pipe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe swap mac",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "c167",
+        "name": "Add skbmod action with control reclassify",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0xbeef reclassify",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod reclassify set etype 0xBEEF",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "0c2f",
+        "name": "Add skbmod action with control drop",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0x0001 drop",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action skbmod index 1",
+        "matchPattern": "action order [0-9]*: skbmod drop set etype 0x1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "d113",
+        "name": "Add skbmod action with control continue",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0x1 continue",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod continue set etype 0x1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "7242",
+        "name": "Add skbmod action with control pass",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set smac 00:00:00:00:00:01 pass",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pass set smac 00:00:00:00:00:01",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "58cb",
+        "name": "List skbmod actions",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbmod set etype 0x0001",
+            "$TC actions add action skbmod set etype 0x0011",
+            "$TC actions add action skbmod set etype 0x0021",
+            "$TC actions add action skbmod set etype 0x0031",
+            "$TC actions add action skbmod set etype 0x0041"
+        ],
+        "cmdUnderTest": "$TC actions ls action skbmod",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod",
+        "matchCount": "5",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "9aa8",
+        "name": "Get a single skbmod action from a list",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbmod set etype 0x0001",
+            "$TC actions add action skbmod set etype 0x0011",
+            "$TC actions add action skbmod set etype 0x0021",
+            "$TC actions add action skbmod set etype 0x0031",
+            "$TC actions add action skbmod set etype 0x0041"
+        ],
+        "cmdUnderTest": "$TC actions ls action skbmod",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action skbmod index 4",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x0031",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "e93a",
+        "name": "Delete an skbmod action",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbmod set etype 0x1111 index 909"
+        ],
+        "cmdUnderTest": "$TC actions del action skbmod index 909",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x1111\\s+index 909",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "40c2",
+        "name": "Flush skbmod actions",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            "$TC actions add action skbmod set etype 0x0001",
+            "$TC actions add action skbmod set etype 0x0011",
+            "$TC actions add action skbmod set etype 0x0021",
+            "$TC actions add action skbmod set etype 0x0031",
+            "$TC actions add action skbmod set etype 0x0041"
+        ],
+        "cmdUnderTest": "$TC actions flush action skbmod",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json
deleted file mode 100644
index 6973bdc5b5bf..000000000000
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json
+++ /dev/null
@@ -1,1165 +0,0 @@
-[
-    {
-        "id": "e89a",
-        "name": "Add valid pass action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action pass index 8",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action pass.*index 8 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "a02c",
-        "name": "Add valid pipe action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action pipe index 6",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action pipe.*index 6 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "feef",
-        "name": "Add valid reclassify action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action reclassify index 5",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action reclassify.*index 5 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "8a7a",
-        "name": "Add valid drop action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action drop index 30",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 30 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "9a52",
-        "name": "Add valid continue action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action continue index 432",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action continue.*index 432 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "d700",
-        "name": "Add invalid action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action pump index 386",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action.*index 386 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "9215",
-        "name": "Add action with duplicate index",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action pipe index 15"
-        ],
-        "cmdUnderTest": "$TC actions add action drop index 15",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 15 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "798e",
-        "name": "Add action with index exceeding 32-bit maximum",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action drop index 4294967296",
-        "expExitCode": "255",
-        "verifyCmd": "actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 4294967296 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "22be",
-        "name": "Add action with index at 32-bit maximum",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action drop index 4294967295",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 4294967295 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "ac2a",
-        "name": "List actions",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action reclassify index 101",
-            "$TC actions add action reclassify index 102",
-            "$TC actions add action reclassify index 103",
-            "$TC actions add action reclassify index 104",
-            "$TC actions add action reclassify index 105"
-        ],
-        "cmdUnderTest": "$TC actions list action gact",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action reclassify",
-        "matchCount": "5",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "63ec",
-        "name": "Delete pass action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action pass index 1"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action pass.*index 1 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "46be",
-        "name": "Delete pipe action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action pipe index 9"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 9",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action pipe.*index 9 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "2e08",
-        "name": "Delete reclassify action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action reclassify index 65536"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 65536",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action reclassify.*index 65536 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "99c4",
-        "name": "Delete drop action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action drop index 16"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 16",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 16 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "fb6b",
-        "name": "Delete continue action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action continue index 32"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 32",
-        "expExitCode": "0",
-        "verifyCmd": "actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action continue.*index 32 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "0eb3",
-        "name": "Delete non-existent action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 2",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "5124",
-        "name": "Add mirred mirror to egress action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress mirror index 1 dev lo",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 1 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "6fb4",
-        "name": "Add mirred redirect to egress action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress redirect index 2 dev lo action pipe",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "ba38",
-        "name": "Get mirred actions",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress mirror index 1 dev lo",
-            "$TC actions add action mirred egress redirect index 2 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions show action mirred",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "[Mirror|Redirect] to device lo",
-        "matchCount": "2",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "d7c0",
-        "name": "Add invalid mirred direction",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred inbound mirror index 20 dev lo",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 20 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "e213",
-        "name": "Add invalid mirred action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress remirror index 20 dev lo",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress.*to device lo\\).*index 20 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "2d89",
-        "name": "Add mirred action with invalid device",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress mirror index 20 dev eltoh",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(.*to device eltoh\\).*index 20 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "300b",
-        "name": "Add mirred action with duplicate index",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress redirect index 15 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress mirror index 15 dev lo",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 15 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "a70e",
-        "name": "Delete mirred mirror action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress mirror index 5 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions del action mirred index 5",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 5 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "3fb3",
-        "name": "Delete mirred redirect action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress redirect index 5 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions del action mirred index 5",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 5 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "b078",
-        "name": "Add simple action",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action simple sdata \"A triumph\" index 60",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <A triumph>.*index 60 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action simple"
-        ]
-    },
-    {
-        "id": "6d4c",
-        "name": "Add simple action with duplicate index",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action simple sdata \"Aruba\" index 4"
-        ],
-        "cmdUnderTest": "$TC actions add action simple sdata \"Jamaica\" index 4",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <Jamaica>.*ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action simple"
-        ]
-    },
-    {
-        "id": "2542",
-        "name": "List simple actions",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action simple sdata \"Rock\"",
-            "$TC actions add action simple sdata \"Paper\"",
-            "$TC actions add action simple sdata \"Scissors\" index 98"
-        ],
-        "cmdUnderTest": "$TC actions list action simple",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>",
-        "matchCount": "3",
-        "teardown": [
-            "$TC actions flush action simple"
-        ]
-    },
-    {
-        "id": "ea67",
-        "name": "Delete simple action",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action simple sdata \"Blinkenlights\" index 1"
-        ],
-        "cmdUnderTest": "$TC actions delete action simple index 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <Blinkenlights>.*index 1 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action simple"
-        ]
-    },
-    {
-        "id": "8ff1",
-        "name": "Flush simple actions",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action simple sdata \"Kirk\"",
-            "$TC actions add action simple sdata \"Spock\" index 50",
-            "$TC actions add action simple sdata \"McCoy\" index 9"
-        ],
-        "cmdUnderTest": "$TC actions flush action simple",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>",
-        "matchCount": "0",
-        "teardown": [
-            ""
-        ]
-    },
-    {
-        "id": "6236",
-        "name": "Add skbedit action with valid mark",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit mark 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit mark 1",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "407b",
-        "name": "Add skbedit action with invalid mark",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit mark 666777888999",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit mark",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "081d",
-        "name": "Add skbedit action with priority",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit prio 99",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit priority :99",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "cc37",
-        "name": "Add skbedit action with invalid priority",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit prio foo",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit priority",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "3c95",
-        "name": "Add skbedit action with queue_mapping",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit queue_mapping 909",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "985c",
-        "name": "Add skbedit action with invalid queue_mapping",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit queue_mapping 67000",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit queue_mapping",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "224f",
-        "name": "Add skbedit action with ptype host",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit ptype host",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype host",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "d1a3",
-        "name": "Add skbedit action with ptype otherhost",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit ptype otherhost",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype otherhost",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "b9c6",
-        "name": "Add skbedit action with invalid ptype",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit ptype openair",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype openair",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "5172",
-        "name": "List skbedit actions",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action skbedit ptype otherhost",
-            "$TC actions add action skbedit ptype broadcast",
-            "$TC actions add action skbedit mark 59",
-            "$TC actions add action skbedit mark 409"
-        ],
-        "cmdUnderTest": "$TC actions list action skbedit",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit",
-        "matchCount": "4",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "a6d6",
-        "name": "Add skbedit action with index",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit mark 808 index 4040404040",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "index 4040404040",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "38f3",
-        "name": "Delete skbedit action",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action skbedit mark 42 index 9009"
-        ],
-        "cmdUnderTest": "$TC actions del action skbedit index 9009",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit mark 42",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "ce97",
-        "name": "Flush skbedit actions",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            "$TC actions add action skbedit mark 500",
-            "$TC actions add action skbedit mark 501",
-            "$TC actions add action skbedit mark 502",
-            "$TC actions add action skbedit mark 503",
-            "$TC actions add action skbedit mark 504",
-            "$TC actions add action skbedit mark 505",
-            "$TC actions add action skbedit mark 506"
-        ],
-        "cmdUnderTest": "$TC actions flush action skbedit",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "f02c",
-        "name": "Replace gact action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action drop index 10",
-            "$TC actions add action drop index 12"
-        ],
-        "cmdUnderTest": "$TC actions replace action ok index 12",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions ls action gact",
-        "matchPattern": "action order [0-9]*: gact action pass",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "525f",
-        "name": "Get gact action by index",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action drop index 3900800700"
-        ],
-        "cmdUnderTest": "$TC actions get action gact index 3900800700",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions get action gact index 3900800700",
-        "matchPattern": "index 3900800700",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "a568",
-        "name": "Add action with ife type",
-        "category": [
-            "actions",
-            "ife"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action ife",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action ife encode type 0xDEAD index 1"
-        ],
-        "cmdUnderTest": "$TC actions get action ife index 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions get action ife index 1",
-        "matchPattern": "type 0xDEAD",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action ife"
-        ]
-    },
-    {
-        "id": "b983",
-        "name": "Add action without ife type",
-        "category": [
-            "actions",
-            "ife"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action ife",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action ife encode index 1"
-        ],
-        "cmdUnderTest": "$TC actions get action ife index 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions get action ife index 1",
-        "matchPattern": "type 0xED3E",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action ife"
-        ]
-    }
-]
\ No newline at end of file
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index b8462e1b74f9..fc373fdf2bdc 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -50,7 +50,7 @@ def exec_cmd(command, nsonly=True):
         stderr=subprocess.PIPE)
     (rawout, serr) = proc.communicate()
 
-    if proc.returncode != 0:
+    if proc.returncode != 0 and len(serr) > 0:
         foutput = serr.decode("utf-8")
     else:
         foutput = rawout.decode("utf-8")
@@ -180,15 +180,20 @@ def has_blank_ids(idlist):
 
 def load_from_file(filename):
     """
-    Open the JSON file containing the test cases and return them as an
-    ordered dictionary object.
+    Open the JSON file containing the test cases and return them
+    as list of ordered dictionary objects.
     """
-    with open(filename) as test_data:
-        testlist = json.load(test_data, object_pairs_hook=OrderedDict)
-    idlist = get_id_list(testlist)
-    if (has_blank_ids(idlist)):
-        for k in testlist:
-            k['filename'] = filename
+    try:
+        with open(filename) as test_data:
+            testlist = json.load(test_data, object_pairs_hook=OrderedDict)
+    except json.JSONDecodeError as jde:
+        print('IGNORING test case file {}\n\tBECAUSE:  {}'.format(filename, jde))
+        testlist = list()
+    else:
+        idlist = get_id_list(testlist)
+        if (has_blank_ids(idlist)):
+            for k in testlist:
+                k['filename'] = filename
     return testlist
 
 
@@ -210,7 +215,7 @@ def set_args(parser):
                         help='Run tests only from the specified category, or if no category is specified, list known categories.')
     parser.add_argument('-f', '--file', type=str,
                         help='Run tests from the specified file')
-    parser.add_argument('-l', '--list', type=str, nargs='?', const="", metavar='CATEGORY',
+    parser.add_argument('-l', '--list', type=str, nargs='?', const="++", metavar='CATEGORY',
                         help='List all test cases, or those only within the specified category')
     parser.add_argument('-s', '--show', type=str, nargs=1, metavar='ID', dest='showID',
                         help='Display the test case with specified id')
@@ -367,10 +372,10 @@ def set_operation_mode(args):
     testcases = get_categorized_testlist(alltests, ucat)
 
     if args.list:
-        if (len(args.list) == 0):
+        if (args.list == "++"):
             list_test_cases(alltests)
             exit(0)
-        elif(len(args.list > 0)):
+        elif(len(args.list) > 0):
             if (args.list not in ucat):
                 print("Unknown category " + args.list)
                 print("Available categories:")
diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index eb188c729dd6..a023d0d62b25 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -18,3 +18,17 @@ NAMES = {
           # Name of the namespace to use
           'NS': 'tcut'
         }
+
+
+ENVIR = { }
+
+# put customizations in tdc_config_local.py
+try:
+    from tdc_config_local import *
+except ImportError as ie:
+    pass
+
+try:
+    NAMES.update(EXTRA_NAMES)
+except NameError as ne:
+    pass
diff --git a/tools/testing/selftests/tc-testing/tdc_config_local_template.py b/tools/testing/selftests/tc-testing/tdc_config_local_template.py
new file mode 100644
index 000000000000..d48fc732a399
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tdc_config_local_template.py
@@ -0,0 +1,23 @@
+"""
+tdc_config_local.py - tdc plugin-writer-specified values
+
+Copyright (C) 2017 bjb@mojatatu.com
+"""
+
+import os
+
+ENVIR = os.environ.copy()
+
+ENV_LD_LIBRARY_PATH = os.getenv('LD_LIBRARY_PATH', '')
+ENV_OTHER_LIB = os.getenv('OTHER_LIB', '')
+
+
+# example adding value to NAMES, without editing tdc_config.py
+EXTRA_NAMES = dict()
+EXTRA_NAMES['SOME_BIN'] = os.path.join(os.getenv('OTHER_BIN', ''), 'some_bin')
+
+
+# example adding values to ENVIR, without editing tdc_config.py
+ENVIR['VALGRIND_LIB'] = '/usr/lib/valgrind'
+ENVIR['VALGRIND_BIN'] = '/usr/bin/valgrind'
+ENVIR['VGDB_BIN'] = '/usr/bin/vgdb'
diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py
index ccf2d2458703..db381120a566 100644
--- a/tools/testing/selftests/tc-testing/tdc_helper.py
+++ b/tools/testing/selftests/tc-testing/tdc_helper.py
@@ -16,7 +16,7 @@ def get_categorized_testlist(alltests, ucat):
 
 
 def get_unique_item(lst):
-    """ For a list, return a set of the unique items in the list. """
+    """ For a list, return a list of the unique items in the list. """
     return list(set(lst))
 
 
@@ -58,7 +58,7 @@ def print_sll(items):
 def print_test_case(tcase):
     """ Pretty-printing of a given test case. """
     for k in tcase.keys():
-        if (type(tcase[k]) == list):
+        if (isinstance(tcase[k], list)):
             print(k + ":")
             print_list(tcase[k])
         else:
diff --git a/tools/testing/vsock/.gitignore b/tools/testing/vsock/.gitignore
new file mode 100644
index 000000000000..dc5f11faf530
--- /dev/null
+++ b/tools/testing/vsock/.gitignore
@@ -0,0 +1,2 @@
+*.d
+vsock_diag_test
diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile
new file mode 100644
index 000000000000..66ba0924194d
--- /dev/null
+++ b/tools/testing/vsock/Makefile
@@ -0,0 +1,9 @@
+all: test
+test: vsock_diag_test
+vsock_diag_test: vsock_diag_test.o timeout.o control.o
+
+CFLAGS += -g -O2 -Werror -Wall -I. -I../../include/uapi -I../../include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE
+.PHONY: all test clean
+clean:
+	${RM} *.o *.d vsock_diag_test
+-include *.d
diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README
new file mode 100644
index 000000000000..2cc6d7302db6
--- /dev/null
+++ b/tools/testing/vsock/README
@@ -0,0 +1,36 @@
+AF_VSOCK test suite
+-------------------
+These tests exercise net/vmw_vsock/ host<->guest sockets for VMware, KVM, and
+Hyper-V.
+
+The following tests are available:
+
+  * vsock_diag_test - vsock_diag.ko module for listing open sockets
+
+The following prerequisite steps are not automated and must be performed prior
+to running tests:
+
+1. Build the kernel and these tests.
+2. Install the kernel and tests on the host.
+3. Install the kernel and tests inside the guest.
+4. Boot the guest and ensure that the AF_VSOCK transport is enabled.
+
+Invoke test binaries in both directions as follows:
+
+  # host=server, guest=client
+  (host)# $TEST_BINARY --mode=server \
+                       --control-port=1234 \
+                       --peer-cid=3
+  (guest)# $TEST_BINARY --mode=client \
+                        --control-host=$HOST_IP \
+                        --control-port=1234 \
+                        --peer-cid=2
+
+  # host=client, guest=server
+  (guest)# $TEST_BINARY --mode=server \
+                        --control-port=1234 \
+                        --peer-cid=2
+  (host)# $TEST_BINARY --mode=client \
+                       --control-port=$GUEST_IP \
+                       --control-port=1234 \
+                       --peer-cid=3
diff --git a/tools/testing/vsock/control.c b/tools/testing/vsock/control.c
new file mode 100644
index 000000000000..90fd47f0e422
--- /dev/null
+++ b/tools/testing/vsock/control.c
@@ -0,0 +1,219 @@
+/* Control socket for client/server test execution
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+/* The client and server may need to coordinate to avoid race conditions like
+ * the client attempting to connect to a socket that the server is not
+ * listening on yet.  The control socket offers a communications channel for
+ * such coordination tasks.
+ *
+ * If the client calls control_expectln("LISTENING"), then it will block until
+ * the server calls control_writeln("LISTENING").  This provides a simple
+ * mechanism for coordinating between the client and the server.
+ */
+
+#include <errno.h>
+#include <netdb.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include "timeout.h"
+#include "control.h"
+
+static int control_fd = -1;
+
+/* Open the control socket, either in server or client mode */
+void control_init(const char *control_host,
+		  const char *control_port,
+		  bool server)
+{
+	struct addrinfo hints = {
+		.ai_socktype = SOCK_STREAM,
+	};
+	struct addrinfo *result = NULL;
+	struct addrinfo *ai;
+	int ret;
+
+	ret = getaddrinfo(control_host, control_port, &hints, &result);
+	if (ret != 0) {
+		fprintf(stderr, "%s\n", gai_strerror(ret));
+		exit(EXIT_FAILURE);
+	}
+
+	for (ai = result; ai; ai = ai->ai_next) {
+		int fd;
+		int val = 1;
+
+		fd = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol);
+		if (fd < 0)
+			continue;
+
+		if (!server) {
+			if (connect(fd, ai->ai_addr, ai->ai_addrlen) < 0)
+				goto next;
+			control_fd = fd;
+			printf("Control socket connected to %s:%s.\n",
+			       control_host, control_port);
+			break;
+		}
+
+		if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR,
+			       &val, sizeof(val)) < 0) {
+			perror("setsockopt");
+			exit(EXIT_FAILURE);
+		}
+
+		if (bind(fd, ai->ai_addr, ai->ai_addrlen) < 0)
+			goto next;
+		if (listen(fd, 1) < 0)
+			goto next;
+
+		printf("Control socket listening on %s:%s\n",
+		       control_host, control_port);
+		fflush(stdout);
+
+		control_fd = accept(fd, NULL, 0);
+		close(fd);
+
+		if (control_fd < 0) {
+			perror("accept");
+			exit(EXIT_FAILURE);
+		}
+		printf("Control socket connection accepted...\n");
+		break;
+
+next:
+		close(fd);
+	}
+
+	if (control_fd < 0) {
+		fprintf(stderr, "Control socket initialization failed.  Invalid address %s:%s?\n",
+			control_host, control_port);
+		exit(EXIT_FAILURE);
+	}
+
+	freeaddrinfo(result);
+}
+
+/* Free resources */
+void control_cleanup(void)
+{
+	close(control_fd);
+	control_fd = -1;
+}
+
+/* Write a line to the control socket */
+void control_writeln(const char *str)
+{
+	ssize_t len = strlen(str);
+	ssize_t ret;
+
+	timeout_begin(TIMEOUT);
+
+	do {
+		ret = send(control_fd, str, len, MSG_MORE);
+		timeout_check("send");
+	} while (ret < 0 && errno == EINTR);
+
+	if (ret != len) {
+		perror("send");
+		exit(EXIT_FAILURE);
+	}
+
+	do {
+		ret = send(control_fd, "\n", 1, 0);
+		timeout_check("send");
+	} while (ret < 0 && errno == EINTR);
+
+	if (ret != 1) {
+		perror("send");
+		exit(EXIT_FAILURE);
+	}
+
+	timeout_end();
+}
+
+/* Return the next line from the control socket (without the trailing newline).
+ *
+ * The program terminates if a timeout occurs.
+ *
+ * The caller must free() the returned string.
+ */
+char *control_readln(void)
+{
+	char *buf = NULL;
+	size_t idx = 0;
+	size_t buflen = 0;
+
+	timeout_begin(TIMEOUT);
+
+	for (;;) {
+		ssize_t ret;
+
+		if (idx >= buflen) {
+			char *new_buf;
+
+			new_buf = realloc(buf, buflen + 80);
+			if (!new_buf) {
+				perror("realloc");
+				exit(EXIT_FAILURE);
+			}
+
+			buf = new_buf;
+			buflen += 80;
+		}
+
+		do {
+			ret = recv(control_fd, &buf[idx], 1, 0);
+			timeout_check("recv");
+		} while (ret < 0 && errno == EINTR);
+
+		if (ret == 0) {
+			fprintf(stderr, "unexpected EOF on control socket\n");
+			exit(EXIT_FAILURE);
+		}
+
+		if (ret != 1) {
+			perror("recv");
+			exit(EXIT_FAILURE);
+		}
+
+		if (buf[idx] == '\n') {
+			buf[idx] = '\0';
+			break;
+		}
+
+		idx++;
+	}
+
+	timeout_end();
+
+	return buf;
+}
+
+/* Wait until a given line is received or a timeout occurs */
+void control_expectln(const char *str)
+{
+	char *line;
+
+	line = control_readln();
+	if (strcmp(str, line) != 0) {
+		fprintf(stderr, "expected \"%s\" on control socket, got \"%s\"\n",
+			str, line);
+		exit(EXIT_FAILURE);
+	}
+
+	free(line);
+}
diff --git a/tools/testing/vsock/control.h b/tools/testing/vsock/control.h
new file mode 100644
index 000000000000..54a07efd267c
--- /dev/null
+++ b/tools/testing/vsock/control.h
@@ -0,0 +1,13 @@
+#ifndef CONTROL_H
+#define CONTROL_H
+
+#include <stdbool.h>
+
+void control_init(const char *control_host, const char *control_port,
+		  bool server);
+void control_cleanup(void);
+void control_writeln(const char *str);
+char *control_readln(void);
+void control_expectln(const char *str);
+
+#endif /* CONTROL_H */
diff --git a/tools/testing/vsock/timeout.c b/tools/testing/vsock/timeout.c
new file mode 100644
index 000000000000..c49b3003b2db
--- /dev/null
+++ b/tools/testing/vsock/timeout.c
@@ -0,0 +1,64 @@
+/* Timeout API for single-threaded programs that use blocking
+ * syscalls (read/write/send/recv/connect/accept).
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+/* Use the following pattern:
+ *
+ *   timeout_begin(TIMEOUT);
+ *   do {
+ *       ret = accept(...);
+ *       timeout_check("accept");
+ *   } while (ret < 0 && ret == EINTR);
+ *   timeout_end();
+ */
+
+#include <stdlib.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <stdio.h>
+#include "timeout.h"
+
+static volatile bool timeout;
+
+/* SIGALRM handler function.  Do not use sleep(2), alarm(2), or
+ * setitimer(2) while using this API - they may interfere with each
+ * other.
+ */
+void sigalrm(int signo)
+{
+	timeout = true;
+}
+
+/* Start a timeout.  Call timeout_check() to verify that the timeout hasn't
+ * expired.  timeout_end() must be called to stop the timeout.  Timeouts cannot
+ * be nested.
+ */
+void timeout_begin(unsigned int seconds)
+{
+	alarm(seconds);
+}
+
+/* Exit with an error message if the timeout has expired */
+void timeout_check(const char *operation)
+{
+	if (timeout) {
+		fprintf(stderr, "%s timed out\n", operation);
+		exit(EXIT_FAILURE);
+	}
+}
+
+/* Stop a timeout */
+void timeout_end(void)
+{
+	alarm(0);
+	timeout = false;
+}
diff --git a/tools/testing/vsock/timeout.h b/tools/testing/vsock/timeout.h
new file mode 100644
index 000000000000..77db9ce9860a
--- /dev/null
+++ b/tools/testing/vsock/timeout.h
@@ -0,0 +1,14 @@
+#ifndef TIMEOUT_H
+#define TIMEOUT_H
+
+enum {
+	/* Default timeout */
+	TIMEOUT = 10 /* seconds */
+};
+
+void sigalrm(int signo);
+void timeout_begin(unsigned int seconds);
+void timeout_check(const char *operation);
+void timeout_end(void);
+
+#endif /* TIMEOUT_H */
diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c
new file mode 100644
index 000000000000..e896a4af52f4
--- /dev/null
+++ b/tools/testing/vsock/vsock_diag_test.c
@@ -0,0 +1,681 @@
+/*
+ * vsock_diag_test - vsock_diag.ko test suite
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <getopt.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <signal.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <linux/list.h>
+#include <linux/net.h>
+#include <linux/netlink.h>
+#include <linux/sock_diag.h>
+#include <netinet/tcp.h>
+
+#include "../../../include/uapi/linux/vm_sockets.h"
+#include "../../../include/uapi/linux/vm_sockets_diag.h"
+
+#include "timeout.h"
+#include "control.h"
+
+enum test_mode {
+	TEST_MODE_UNSET,
+	TEST_MODE_CLIENT,
+	TEST_MODE_SERVER
+};
+
+/* Per-socket status */
+struct vsock_stat {
+	struct list_head list;
+	struct vsock_diag_msg msg;
+};
+
+static const char *sock_type_str(int type)
+{
+	switch (type) {
+	case SOCK_DGRAM:
+		return "DGRAM";
+	case SOCK_STREAM:
+		return "STREAM";
+	default:
+		return "INVALID TYPE";
+	}
+}
+
+static const char *sock_state_str(int state)
+{
+	switch (state) {
+	case TCP_CLOSE:
+		return "UNCONNECTED";
+	case TCP_SYN_SENT:
+		return "CONNECTING";
+	case TCP_ESTABLISHED:
+		return "CONNECTED";
+	case TCP_CLOSING:
+		return "DISCONNECTING";
+	case TCP_LISTEN:
+		return "LISTEN";
+	default:
+		return "INVALID STATE";
+	}
+}
+
+static const char *sock_shutdown_str(int shutdown)
+{
+	switch (shutdown) {
+	case 1:
+		return "RCV_SHUTDOWN";
+	case 2:
+		return "SEND_SHUTDOWN";
+	case 3:
+		return "RCV_SHUTDOWN | SEND_SHUTDOWN";
+	default:
+		return "0";
+	}
+}
+
+static void print_vsock_addr(FILE *fp, unsigned int cid, unsigned int port)
+{
+	if (cid == VMADDR_CID_ANY)
+		fprintf(fp, "*:");
+	else
+		fprintf(fp, "%u:", cid);
+
+	if (port == VMADDR_PORT_ANY)
+		fprintf(fp, "*");
+	else
+		fprintf(fp, "%u", port);
+}
+
+static void print_vsock_stat(FILE *fp, struct vsock_stat *st)
+{
+	print_vsock_addr(fp, st->msg.vdiag_src_cid, st->msg.vdiag_src_port);
+	fprintf(fp, " ");
+	print_vsock_addr(fp, st->msg.vdiag_dst_cid, st->msg.vdiag_dst_port);
+	fprintf(fp, " %s %s %s %u\n",
+		sock_type_str(st->msg.vdiag_type),
+		sock_state_str(st->msg.vdiag_state),
+		sock_shutdown_str(st->msg.vdiag_shutdown),
+		st->msg.vdiag_ino);
+}
+
+static void print_vsock_stats(FILE *fp, struct list_head *head)
+{
+	struct vsock_stat *st;
+
+	list_for_each_entry(st, head, list)
+		print_vsock_stat(fp, st);
+}
+
+static struct vsock_stat *find_vsock_stat(struct list_head *head, int fd)
+{
+	struct vsock_stat *st;
+	struct stat stat;
+
+	if (fstat(fd, &stat) < 0) {
+		perror("fstat");
+		exit(EXIT_FAILURE);
+	}
+
+	list_for_each_entry(st, head, list)
+		if (st->msg.vdiag_ino == stat.st_ino)
+			return st;
+
+	fprintf(stderr, "cannot find fd %d\n", fd);
+	exit(EXIT_FAILURE);
+}
+
+static void check_no_sockets(struct list_head *head)
+{
+	if (!list_empty(head)) {
+		fprintf(stderr, "expected no sockets\n");
+		print_vsock_stats(stderr, head);
+		exit(1);
+	}
+}
+
+static void check_num_sockets(struct list_head *head, int expected)
+{
+	struct list_head *node;
+	int n = 0;
+
+	list_for_each(node, head)
+		n++;
+
+	if (n != expected) {
+		fprintf(stderr, "expected %d sockets, found %d\n",
+			expected, n);
+		print_vsock_stats(stderr, head);
+		exit(EXIT_FAILURE);
+	}
+}
+
+static void check_socket_state(struct vsock_stat *st, __u8 state)
+{
+	if (st->msg.vdiag_state != state) {
+		fprintf(stderr, "expected socket state %#x, got %#x\n",
+			state, st->msg.vdiag_state);
+		exit(EXIT_FAILURE);
+	}
+}
+
+static void send_req(int fd)
+{
+	struct sockaddr_nl nladdr = {
+		.nl_family = AF_NETLINK,
+	};
+	struct {
+		struct nlmsghdr nlh;
+		struct vsock_diag_req vreq;
+	} req = {
+		.nlh = {
+			.nlmsg_len = sizeof(req),
+			.nlmsg_type = SOCK_DIAG_BY_FAMILY,
+			.nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP,
+		},
+		.vreq = {
+			.sdiag_family = AF_VSOCK,
+			.vdiag_states = ~(__u32)0,
+		},
+	};
+	struct iovec iov = {
+		.iov_base = &req,
+		.iov_len = sizeof(req),
+	};
+	struct msghdr msg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+
+	for (;;) {
+		if (sendmsg(fd, &msg, 0) < 0) {
+			if (errno == EINTR)
+				continue;
+
+			perror("sendmsg");
+			exit(EXIT_FAILURE);
+		}
+
+		return;
+	}
+}
+
+static ssize_t recv_resp(int fd, void *buf, size_t len)
+{
+	struct sockaddr_nl nladdr = {
+		.nl_family = AF_NETLINK,
+	};
+	struct iovec iov = {
+		.iov_base = buf,
+		.iov_len = len,
+	};
+	struct msghdr msg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+	ssize_t ret;
+
+	do {
+		ret = recvmsg(fd, &msg, 0);
+	} while (ret < 0 && errno == EINTR);
+
+	if (ret < 0) {
+		perror("recvmsg");
+		exit(EXIT_FAILURE);
+	}
+
+	return ret;
+}
+
+static void add_vsock_stat(struct list_head *sockets,
+			   const struct vsock_diag_msg *resp)
+{
+	struct vsock_stat *st;
+
+	st = malloc(sizeof(*st));
+	if (!st) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	st->msg = *resp;
+	list_add_tail(&st->list, sockets);
+}
+
+/*
+ * Read vsock stats into a list.
+ */
+static void read_vsock_stat(struct list_head *sockets)
+{
+	long buf[8192 / sizeof(long)];
+	int fd;
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
+	if (fd < 0) {
+		perror("socket");
+		exit(EXIT_FAILURE);
+	}
+
+	send_req(fd);
+
+	for (;;) {
+		const struct nlmsghdr *h;
+		ssize_t ret;
+
+		ret = recv_resp(fd, buf, sizeof(buf));
+		if (ret == 0)
+			goto done;
+		if (ret < sizeof(*h)) {
+			fprintf(stderr, "short read of %zd bytes\n", ret);
+			exit(EXIT_FAILURE);
+		}
+
+		h = (struct nlmsghdr *)buf;
+
+		while (NLMSG_OK(h, ret)) {
+			if (h->nlmsg_type == NLMSG_DONE)
+				goto done;
+
+			if (h->nlmsg_type == NLMSG_ERROR) {
+				const struct nlmsgerr *err = NLMSG_DATA(h);
+
+				if (h->nlmsg_len < NLMSG_LENGTH(sizeof(*err)))
+					fprintf(stderr, "NLMSG_ERROR\n");
+				else {
+					errno = -err->error;
+					perror("NLMSG_ERROR");
+				}
+
+				exit(EXIT_FAILURE);
+			}
+
+			if (h->nlmsg_type != SOCK_DIAG_BY_FAMILY) {
+				fprintf(stderr, "unexpected nlmsg_type %#x\n",
+					h->nlmsg_type);
+				exit(EXIT_FAILURE);
+			}
+			if (h->nlmsg_len <
+			    NLMSG_LENGTH(sizeof(struct vsock_diag_msg))) {
+				fprintf(stderr, "short vsock_diag_msg\n");
+				exit(EXIT_FAILURE);
+			}
+
+			add_vsock_stat(sockets, NLMSG_DATA(h));
+
+			h = NLMSG_NEXT(h, ret);
+		}
+	}
+
+done:
+	close(fd);
+}
+
+static void free_sock_stat(struct list_head *sockets)
+{
+	struct vsock_stat *st;
+	struct vsock_stat *next;
+
+	list_for_each_entry_safe(st, next, sockets, list)
+		free(st);
+}
+
+static void test_no_sockets(unsigned int peer_cid)
+{
+	LIST_HEAD(sockets);
+
+	read_vsock_stat(&sockets);
+
+	check_no_sockets(&sockets);
+
+	free_sock_stat(&sockets);
+}
+
+static void test_listen_socket_server(unsigned int peer_cid)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} addr = {
+		.svm = {
+			.svm_family = AF_VSOCK,
+			.svm_port = 1234,
+			.svm_cid = VMADDR_CID_ANY,
+		},
+	};
+	LIST_HEAD(sockets);
+	struct vsock_stat *st;
+	int fd;
+
+	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+	if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+		perror("bind");
+		exit(EXIT_FAILURE);
+	}
+
+	if (listen(fd, 1) < 0) {
+		perror("listen");
+		exit(EXIT_FAILURE);
+	}
+
+	read_vsock_stat(&sockets);
+
+	check_num_sockets(&sockets, 1);
+	st = find_vsock_stat(&sockets, fd);
+	check_socket_state(st, TCP_LISTEN);
+
+	close(fd);
+	free_sock_stat(&sockets);
+}
+
+static void test_connect_client(unsigned int peer_cid)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} addr = {
+		.svm = {
+			.svm_family = AF_VSOCK,
+			.svm_port = 1234,
+			.svm_cid = peer_cid,
+		},
+	};
+	int fd;
+	int ret;
+	LIST_HEAD(sockets);
+	struct vsock_stat *st;
+
+	control_expectln("LISTENING");
+
+	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+	timeout_begin(TIMEOUT);
+	do {
+		ret = connect(fd, &addr.sa, sizeof(addr.svm));
+		timeout_check("connect");
+	} while (ret < 0 && errno == EINTR);
+	timeout_end();
+
+	if (ret < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	read_vsock_stat(&sockets);
+
+	check_num_sockets(&sockets, 1);
+	st = find_vsock_stat(&sockets, fd);
+	check_socket_state(st, TCP_ESTABLISHED);
+
+	control_expectln("DONE");
+	control_writeln("DONE");
+
+	close(fd);
+	free_sock_stat(&sockets);
+}
+
+static void test_connect_server(unsigned int peer_cid)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} addr = {
+		.svm = {
+			.svm_family = AF_VSOCK,
+			.svm_port = 1234,
+			.svm_cid = VMADDR_CID_ANY,
+		},
+	};
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} clientaddr;
+	socklen_t clientaddr_len = sizeof(clientaddr.svm);
+	LIST_HEAD(sockets);
+	struct vsock_stat *st;
+	int fd;
+	int client_fd;
+
+	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+	if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+		perror("bind");
+		exit(EXIT_FAILURE);
+	}
+
+	if (listen(fd, 1) < 0) {
+		perror("listen");
+		exit(EXIT_FAILURE);
+	}
+
+	control_writeln("LISTENING");
+
+	timeout_begin(TIMEOUT);
+	do {
+		client_fd = accept(fd, &clientaddr.sa, &clientaddr_len);
+		timeout_check("accept");
+	} while (client_fd < 0 && errno == EINTR);
+	timeout_end();
+
+	if (client_fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+	if (clientaddr.sa.sa_family != AF_VSOCK) {
+		fprintf(stderr, "expected AF_VSOCK from accept(2), got %d\n",
+			clientaddr.sa.sa_family);
+		exit(EXIT_FAILURE);
+	}
+	if (clientaddr.svm.svm_cid != peer_cid) {
+		fprintf(stderr, "expected peer CID %u from accept(2), got %u\n",
+			peer_cid, clientaddr.svm.svm_cid);
+		exit(EXIT_FAILURE);
+	}
+
+	read_vsock_stat(&sockets);
+
+	check_num_sockets(&sockets, 2);
+	find_vsock_stat(&sockets, fd);
+	st = find_vsock_stat(&sockets, client_fd);
+	check_socket_state(st, TCP_ESTABLISHED);
+
+	control_writeln("DONE");
+	control_expectln("DONE");
+
+	close(client_fd);
+	close(fd);
+	free_sock_stat(&sockets);
+}
+
+static struct {
+	const char *name;
+	void (*run_client)(unsigned int peer_cid);
+	void (*run_server)(unsigned int peer_cid);
+} test_cases[] = {
+	{
+		.name = "No sockets",
+		.run_server = test_no_sockets,
+	},
+	{
+		.name = "Listen socket",
+		.run_server = test_listen_socket_server,
+	},
+	{
+		.name = "Connect",
+		.run_client = test_connect_client,
+		.run_server = test_connect_server,
+	},
+	{},
+};
+
+static void init_signals(void)
+{
+	struct sigaction act = {
+		.sa_handler = sigalrm,
+	};
+
+	sigaction(SIGALRM, &act, NULL);
+	signal(SIGPIPE, SIG_IGN);
+}
+
+static unsigned int parse_cid(const char *str)
+{
+	char *endptr = NULL;
+	unsigned long int n;
+
+	errno = 0;
+	n = strtoul(str, &endptr, 10);
+	if (errno || *endptr != '\0') {
+		fprintf(stderr, "malformed CID \"%s\"\n", str);
+		exit(EXIT_FAILURE);
+	}
+	return n;
+}
+
+static const char optstring[] = "";
+static const struct option longopts[] = {
+	{
+		.name = "control-host",
+		.has_arg = required_argument,
+		.val = 'H',
+	},
+	{
+		.name = "control-port",
+		.has_arg = required_argument,
+		.val = 'P',
+	},
+	{
+		.name = "mode",
+		.has_arg = required_argument,
+		.val = 'm',
+	},
+	{
+		.name = "peer-cid",
+		.has_arg = required_argument,
+		.val = 'p',
+	},
+	{
+		.name = "help",
+		.has_arg = no_argument,
+		.val = '?',
+	},
+	{},
+};
+
+static void usage(void)
+{
+	fprintf(stderr, "Usage: vsock_diag_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid>\n"
+		"\n"
+		"  Server: vsock_diag_test --control-port=1234 --mode=server --peer-cid=3\n"
+		"  Client: vsock_diag_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n"
+		"\n"
+		"Run vsock_diag.ko tests.  Must be launched in both\n"
+		"guest and host.  One side must use --mode=client and\n"
+		"the other side must use --mode=server.\n"
+		"\n"
+		"A TCP control socket connection is used to coordinate tests\n"
+		"between the client and the server.  The server requires a\n"
+		"listen address and the client requires an address to\n"
+		"connect to.\n"
+		"\n"
+		"The CID of the other side must be given with --peer-cid=<cid>.\n");
+	exit(EXIT_FAILURE);
+}
+
+int main(int argc, char **argv)
+{
+	const char *control_host = NULL;
+	const char *control_port = NULL;
+	int mode = TEST_MODE_UNSET;
+	unsigned int peer_cid = VMADDR_CID_ANY;
+	int i;
+
+	init_signals();
+
+	for (;;) {
+		int opt = getopt_long(argc, argv, optstring, longopts, NULL);
+
+		if (opt == -1)
+			break;
+
+		switch (opt) {
+		case 'H':
+			control_host = optarg;
+			break;
+		case 'm':
+			if (strcmp(optarg, "client") == 0)
+				mode = TEST_MODE_CLIENT;
+			else if (strcmp(optarg, "server") == 0)
+				mode = TEST_MODE_SERVER;
+			else {
+				fprintf(stderr, "--mode must be \"client\" or \"server\"\n");
+				return EXIT_FAILURE;
+			}
+			break;
+		case 'p':
+			peer_cid = parse_cid(optarg);
+			break;
+		case 'P':
+			control_port = optarg;
+			break;
+		case '?':
+		default:
+			usage();
+		}
+	}
+
+	if (!control_port)
+		usage();
+	if (mode == TEST_MODE_UNSET)
+		usage();
+	if (peer_cid == VMADDR_CID_ANY)
+		usage();
+
+	if (!control_host) {
+		if (mode != TEST_MODE_SERVER)
+			usage();
+		control_host = "0.0.0.0";
+	}
+
+	control_init(control_host, control_port, mode == TEST_MODE_SERVER);
+
+	for (i = 0; test_cases[i].name; i++) {
+		void (*run)(unsigned int peer_cid);
+
+		printf("%s...", test_cases[i].name);
+		fflush(stdout);
+
+		if (mode == TEST_MODE_CLIENT)
+			run = test_cases[i].run_client;
+		else
+			run = test_cases[i].run_server;
+
+		if (run)
+			run(peer_cid);
+
+		printf("ok\n");
+	}
+
+	control_cleanup();
+	return EXIT_SUCCESS;
+}