D: RCU and variants
D: rcutorture module
-N: Mike McLagan
-E: mike.mclagan@linux.org
-W: http://www.invlogic.com/~mmclagan
-D: DLCI/FRAD drivers for Sangoma SDLAs
-S: Innovative Logic Corp
-S: Post Office Box 1068
-S: Laurel, Maryland 20732
-S: USA
-
N: Bradley McLean
E: brad@bradpc.gaylord.com
D: Device driver hacker
information with description of all internal kernel types. See
Documentation/bpf/btf.rst for detailed description of format
itself.
+
+What: /sys/kernel/btf/<module-name>
+Date: Nov 2020
+KernelVersion: 5.11
+Contact: bpf@vger.kernel.org
+Description:
+ Read-only binary attribute exposing kernel module's BTF type
+ information as an add-on to the kernel's BTF (/sys/kernel/btf/vmlinux).
unicode
vga-softcursor
video-output
- wimax/index
xfs
.. only:: subproject and html
+++ /dev/null
-.. include:: <isonum.txt>
-
-====================================================
-Driver for the Intel Wireless Wimax Connection 2400m
-====================================================
-
-:Copyright: |copy| 2008 Intel Corporation < linux-wimax@intel.com >
-
- This provides a driver for the Intel Wireless WiMAX Connection 2400m
- and a basic Linux kernel WiMAX stack.
-
-1. Requirements
-===============
-
- * Linux installation with Linux kernel 2.6.22 or newer (if building
- from a separate tree)
- * Intel i2400m Echo Peak or Baxter Peak; this includes the Intel
- Wireless WiMAX/WiFi Link 5x50 series.
- * build tools:
-
- + Linux kernel development package for the target kernel; to
- build against your currently running kernel, you need to have
- the kernel development package corresponding to the running
- image installed (usually if your kernel is named
- linux-VERSION, the development package is called
- linux-dev-VERSION or linux-headers-VERSION).
- + GNU C Compiler, make
-
-2. Compilation and installation
-===============================
-
-2.1. Compilation of the drivers included in the kernel
-------------------------------------------------------
-
- Configure the kernel; to enable the WiMAX drivers select Drivers >
- Networking Drivers > WiMAX device support. Enable all of them as
- modules (easier).
-
- If USB or SDIO are not enabled in the kernel configuration, the options
- to build the i2400m USB or SDIO drivers will not show. Enable said
- subsystems and go back to the WiMAX menu to enable the drivers.
-
- Compile and install your kernel as usual.
-
-2.2. Compilation of the drivers distributed as an standalone module
--------------------------------------------------------------------
-
- To compile::
-
- $ cd source/directory
- $ make
-
- Once built you can load and unload using the provided load.sh script;
- load.sh will load the modules, load.sh u will unload them.
-
- To install in the default kernel directories (and enable auto loading
- when the device is plugged)::
-
- $ make install
- $ depmod -a
-
- If your kernel development files are located in a non standard
- directory or if you want to build for a kernel that is not the
- currently running one, set KDIR to the right location::
-
- $ make KDIR=/path/to/kernel/dev/tree
-
- For more information, please contact linux-wimax@intel.com.
-
-3. Installing the firmware
---------------------------
-
- The firmware can be obtained from http://linuxwimax.org or might have
- been supplied with your hardware.
-
- It has to be installed in the target system::
-
- $ cp FIRMWAREFILE.sbcf /lib/firmware/i2400m-fw-BUSTYPE-1.3.sbcf
-
- * NOTE: if your firmware came in an .rpm or .deb file, just install
- it as normal, with the rpm (rpm -i FIRMWARE.rpm) or dpkg
- (dpkg -i FIRMWARE.deb) commands. No further action is needed.
- * BUSTYPE will be usb or sdio, depending on the hardware you have.
- Each hardware type comes with its own firmware and will not work
- with other types.
-
-4. Design
-=========
-
- This package contains two major parts: a WiMAX kernel stack and a
- driver for the Intel i2400m.
-
- The WiMAX stack is designed to provide for common WiMAX control
- services to current and future WiMAX devices from any vendor; please
- see README.wimax for details.
-
- The i2400m kernel driver is broken up in two main parts: the bus
- generic driver and the bus-specific drivers. The bus generic driver
- forms the drivercore and contain no knowledge of the actual method we
- use to connect to the device. The bus specific drivers are just the
- glue to connect the bus-generic driver and the device. Currently only
- USB and SDIO are supported. See drivers/net/wimax/i2400m/i2400m.h for
- more information.
-
- The bus generic driver is logically broken up in two parts: OS-glue and
- hardware-glue. The OS-glue interfaces with Linux. The hardware-glue
- interfaces with the device on using an interface provided by the
- bus-specific driver. The reason for this breakup is to be able to
- easily reuse the hardware-glue to write drivers for other OSes; note
- the hardware glue part is written as a native Linux driver; no
- abstraction layers are used, so to port to another OS, the Linux kernel
- API calls should be replaced with the target OS's.
-
-5. Usage
-========
-
- To load the driver, follow the instructions in the install section;
- once the driver is loaded, plug in the device (unless it is permanently
- plugged in). The driver will enumerate the device, upload the firmware
- and output messages in the kernel log (dmesg, /var/log/messages or
- /var/log/kern.log) such as::
-
- ...
- i2400m_usb 5-4:1.0: firmware interface version 8.0.0
- i2400m_usb 5-4:1.0: WiMAX interface wmx0 (00:1d:e1:01:94:2c) ready
-
- At this point the device is ready to work.
-
- Current versions require the Intel WiMAX Network Service in userspace
- to make things work. See the network service's README for instructions
- on how to scan, connect and disconnect.
-
-5.1. Module parameters
-----------------------
-
- Module parameters can be set at kernel or module load time or by
- echoing values::
-
- $ echo VALUE > /sys/module/MODULENAME/parameters/PARAMETERNAME
-
- To make changes permanent, for example, for the i2400m module, you can
- also create a file named /etc/modprobe.d/i2400m containing::
-
- options i2400m idle_mode_disabled=1
-
- To find which parameters are supported by a module, run::
-
- $ modinfo path/to/module.ko
-
- During kernel bootup (if the driver is linked in the kernel), specify
- the following to the kernel command line::
-
- i2400m.PARAMETER=VALUE
-
-5.1.1. i2400m: idle_mode_disabled
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
- The i2400m module supports a parameter to disable idle mode. This
- parameter, once set, will take effect only when the device is
- reinitialized by the driver (eg: following a reset or a reconnect).
-
-5.2. Debug operations: debugfs entries
---------------------------------------
-
- The driver will register debugfs entries that allow the user to tweak
- debug settings. There are three main container directories where
- entries are placed, which correspond to the three blocks a i2400m WiMAX
- driver has:
-
- * /sys/kernel/debug/wimax:DEVNAME/ for the generic WiMAX stack
- controls
- * /sys/kernel/debug/wimax:DEVNAME/i2400m for the i2400m generic
- driver controls
- * /sys/kernel/debug/wimax:DEVNAME/i2400m-usb (or -sdio) for the
- bus-specific i2400m-usb or i2400m-sdio controls).
-
- Of course, if debugfs is mounted in a directory other than
- /sys/kernel/debug, those paths will change.
-
-5.2.1. Increasing debug output
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
- The files named *dl_* indicate knobs for controlling the debug output
- of different submodules::
-
- # find /sys/kernel/debug/wimax\:wmx0 -name \*dl_\*
- /sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_tx
- /sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_rx
- /sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_notif
- /sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_fw
- /sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_usb
- /sys/kernel/debug/wimax:wmx0/i2400m/dl_tx
- /sys/kernel/debug/wimax:wmx0/i2400m/dl_rx
- /sys/kernel/debug/wimax:wmx0/i2400m/dl_rfkill
- /sys/kernel/debug/wimax:wmx0/i2400m/dl_netdev
- /sys/kernel/debug/wimax:wmx0/i2400m/dl_fw
- /sys/kernel/debug/wimax:wmx0/i2400m/dl_debugfs
- /sys/kernel/debug/wimax:wmx0/i2400m/dl_driver
- /sys/kernel/debug/wimax:wmx0/i2400m/dl_control
- /sys/kernel/debug/wimax:wmx0/wimax_dl_stack
- /sys/kernel/debug/wimax:wmx0/wimax_dl_op_rfkill
- /sys/kernel/debug/wimax:wmx0/wimax_dl_op_reset
- /sys/kernel/debug/wimax:wmx0/wimax_dl_op_msg
- /sys/kernel/debug/wimax:wmx0/wimax_dl_id_table
- /sys/kernel/debug/wimax:wmx0/wimax_dl_debugfs
-
- By reading the file you can obtain the current value of said debug
- level; by writing to it, you can set it.
-
- To increase the debug level of, for example, the i2400m's generic TX
- engine, just write::
-
- $ echo 3 > /sys/kernel/debug/wimax:wmx0/i2400m/dl_tx
-
- Increasing numbers yield increasing debug information; for details of
- what is printed and the available levels, check the source. The code
- uses 0 for disabled and increasing values until 8.
-
-5.2.2. RX and TX statistics
-^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
- The i2400m/rx_stats and i2400m/tx_stats provide statistics about the
- data reception/delivery from the device::
-
- $ cat /sys/kernel/debug/wimax:wmx0/i2400m/rx_stats
- 45 1 3 34 3104 48 480
-
- The numbers reported are:
-
- * packets/RX-buffer: total, min, max
- * RX-buffers: total RX buffers received, accumulated RX buffer size
- in bytes, min size received, max size received
-
- Thus, to find the average buffer size received, divide accumulated
- RX-buffer / total RX-buffers.
-
- To clear the statistics back to 0, write anything to the rx_stats file::
-
- $ echo 1 > /sys/kernel/debug/wimax:wmx0/i2400m_rx_stats
-
- Likewise for TX.
-
- Note the packets this debug file refers to are not network packet, but
- packets in the sense of the device-specific protocol for communication
- to the host. See drivers/net/wimax/i2400m/tx.c.
-
-5.2.3. Tracing messages received from user space
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
- To echo messages received from user space into the trace pipe that the
- i2400m driver creates, set the debug file i2400m/trace_msg_from_user to
- 1::
-
- $ echo 1 > /sys/kernel/debug/wimax:wmx0/i2400m/trace_msg_from_user
-
-5.2.4. Performing a device reset
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
- By writing a 0, a 1 or a 2 to the file
- /sys/kernel/debug/wimax:wmx0/reset, the driver performs a warm (without
- disconnecting from the bus), cold (disconnecting from the bus) or bus
- (bus specific) reset on the device.
-
-5.2.5. Asking the device to enter power saving mode
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
- By writing any value to the /sys/kernel/debug/wimax:wmx0 file, the
- device will attempt to enter power saving mode.
-
-6. Troubleshooting
-==================
-
-6.1. Driver complains about ``i2400m-fw-usb-1.2.sbcf: request failed``
-----------------------------------------------------------------------
-
- If upon connecting the device, the following is output in the kernel
- log::
-
- i2400m_usb 5-4:1.0: fw i2400m-fw-usb-1.3.sbcf: request failed: -2
-
- This means that the driver cannot locate the firmware file named
- /lib/firmware/i2400m-fw-usb-1.2.sbcf. Check that the file is present in
- the right location.
+++ /dev/null
-.. SPDX-License-Identifier: GPL-2.0
-
-===============
-WiMAX subsystem
-===============
-
-.. toctree::
- :maxdepth: 2
-
- wimax
-
- i2400m
-
-.. only:: subproject and html
-
- Indices
- =======
-
- * :ref:`genindex`
+++ /dev/null
-.. include:: <isonum.txt>
-
-========================
-Linux kernel WiMAX stack
-========================
-
-:Copyright: |copy| 2008 Intel Corporation < linux-wimax@intel.com >
-
- This provides a basic Linux kernel WiMAX stack to provide a common
- control API for WiMAX devices, usable from kernel and user space.
-
-1. Design
-=========
-
- The WiMAX stack is designed to provide for common WiMAX control
- services to current and future WiMAX devices from any vendor.
-
- Because currently there is only one and we don't know what would be the
- common services, the APIs it currently provides are very minimal.
- However, it is done in such a way that it is easily extensible to
- accommodate future requirements.
-
- The stack works by embedding a struct wimax_dev in your device's
- control structures. This provides a set of callbacks that the WiMAX
- stack will call in order to implement control operations requested by
- the user. As well, the stack provides API functions that the driver
- calls to notify about changes of state in the device.
-
- The stack exports the API calls needed to control the device to user
- space using generic netlink as a marshalling mechanism. You can access
- them using your own code or use the wrappers provided for your
- convenience in libwimax (in the wimax-tools package).
-
- For detailed information on the stack, please see
- include/linux/wimax.h.
-
-2. Usage
-========
-
- For usage in a driver (registration, API, etc) please refer to the
- instructions in the header file include/linux/wimax.h.
-
- When a device is registered with the WiMAX stack, a set of debugfs
- files will appear in /sys/kernel/debug/wimax:wmxX can tweak for
- control.
-
-2.1. Obtaining debug information: debugfs entries
--------------------------------------------------
-
- The WiMAX stack is compiled, by default, with debug messages that can
- be used to diagnose issues. By default, said messages are disabled.
-
- The drivers will register debugfs entries that allow the user to tweak
- debug settings.
-
- Each driver, when registering with the stack, will cause a debugfs
- directory named wimax:DEVICENAME to be created; optionally, it might
- create more subentries below it.
-
-2.1.1. Increasing debug output
-------------------------------
-
- The files named *dl_* indicate knobs for controlling the debug output
- of different submodules of the WiMAX stack::
-
- # find /sys/kernel/debug/wimax\:wmx0 -name \*dl_\*
- /sys/kernel/debug/wimax:wmx0/wimax_dl_stack
- /sys/kernel/debug/wimax:wmx0/wimax_dl_op_rfkill
- /sys/kernel/debug/wimax:wmx0/wimax_dl_op_reset
- /sys/kernel/debug/wimax:wmx0/wimax_dl_op_msg
- /sys/kernel/debug/wimax:wmx0/wimax_dl_id_table
- /sys/kernel/debug/wimax:wmx0/wimax_dl_debugfs
- /sys/kernel/debug/wimax:wmx0/.... # other driver specific files
-
- NOTE:
- Of course, if debugfs is mounted in a directory other than
- /sys/kernel/debug, those paths will change.
-
- By reading the file you can obtain the current value of said debug
- level; by writing to it, you can set it.
-
- To increase the debug level of, for example, the id-table submodule,
- just write:
-
- $ echo 3 > /sys/kernel/debug/wimax:wmx0/wimax_dl_id_table
-
- Increasing numbers yield increasing debug information; for details of
- what is printed and the available levels, check the source. The code
- uses 0 for disabled and increasing values until 8.
- const: per
clock-frequency:
+ $ref: /schemas/types.yaml#/definitions/uint32
description: |
The oscillator frequency driving the flexcan device, filled in by the
boot loader. This property should only be used the used operating system
by default.
0: clock source 0 (oscillator clock)
1: clock source 1 (peripheral clock)
- $ref: /schemas/types.yaml#/definitions/uint32
+ $ref: /schemas/types.yaml#/definitions/uint8
default: 1
minimum: 0
maximum: 1
interrupts = <48 0x2>;
interrupt-parent = <&mpic>;
clock-frequency = <200000000>;
- fsl,clk-source = <0>;
+ fsl,clk-source = /bits/ 8 <0>;
};
- |
#include <dt-bindings/interrupt-controller/irq.h>
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/dsa/hirschmann,hellcreek.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Hirschmann Hellcreek TSN Switch Device Tree Bindings
+
+allOf:
+ - $ref: dsa.yaml#
+
+maintainers:
+ - Andrew Lunn <andrew@lunn.ch>
+ - Florian Fainelli <f.fainelli@gmail.com>
+ - Vivien Didelot <vivien.didelot@gmail.com>
+ - Kurt Kanzenbach <kurt@linutronix.de>
+
+description:
+ The Hellcreek TSN Switch IP is a 802.1Q Ethernet compliant switch. It supports
+ the Precision Time Protocol, Hardware Timestamping as well the Time Aware
+ Shaper.
+
+properties:
+ compatible:
+ items:
+ - const: hirschmann,hellcreek-de1soc-r1
+
+ reg:
+ description:
+ The physical base address and size of TSN and PTP memory base
+ minItems: 2
+ maxItems: 2
+
+ reg-names:
+ items:
+ - const: tsn
+ - const: ptp
+
+ leds:
+ type: object
+ properties:
+ '#address-cells':
+ const: 1
+ '#size-cells':
+ const: 0
+
+ patternProperties:
+ "^led@[01]$":
+ type: object
+ description: Hellcreek leds
+ $ref: ../../leds/common.yaml#
+
+ properties:
+ reg:
+ items:
+ - enum: [0, 1]
+ description: Led number
+
+ label: true
+
+ default-state: true
+
+ required:
+ - reg
+
+ additionalProperties: false
+
+ additionalProperties: false
+
+required:
+ - compatible
+ - reg
+ - reg-names
+ - ethernet-ports
+ - leds
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ switch0: switch@ff240000 {
+ compatible = "hirschmann,hellcreek-de1soc-r1";
+ reg = <0xff240000 0x1000>,
+ <0xff250000 0x1000>;
+ reg-names = "tsn", "ptp";
+ dsa,member = <0 0>;
+
+ ethernet-ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+ label = "cpu";
+ ethernet = <&gmac0>;
+ };
+
+ port@2 {
+ reg = <2>;
+ label = "lan0";
+ phy-handle = <&phy1>;
+ };
+
+ port@3 {
+ reg = <3>;
+ label = "lan1";
+ phy-handle = <&phy2>;
+ };
+ };
+
+ leds {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ led@0 {
+ reg = <0>;
+ label = "sync_good";
+ default-state = "on";
+ };
+
+ led@1 {
+ reg = <1>;
+ label = "is_gm";
+ default-state = "off";
+ };
+ };
+ };
+++ /dev/null
-Microchip KSZ Series Ethernet switches
-==================================
-
-Required properties:
-
-- compatible: For external switch chips, compatible string must be exactly one
- of the following:
- - "microchip,ksz8765"
- - "microchip,ksz8794"
- - "microchip,ksz8795"
- - "microchip,ksz9477"
- - "microchip,ksz9897"
- - "microchip,ksz9896"
- - "microchip,ksz9567"
- - "microchip,ksz8565"
- - "microchip,ksz9893"
- - "microchip,ksz9563"
- - "microchip,ksz8563"
-
-Optional properties:
-
-- reset-gpios : Should be a gpio specifier for a reset line
-- microchip,synclko-125 : Set if the output SYNCLKO frequency should be set to
- 125MHz instead of 25MHz.
-
-See Documentation/devicetree/bindings/net/dsa/dsa.txt for a list of additional
-required and optional properties.
-
-Examples:
-
-Ethernet switch connected via SPI to the host, CPU port wired to eth0:
-
- eth0: ethernet@10001000 {
- fixed-link {
- speed = <1000>;
- full-duplex;
- };
- };
-
- spi1: spi@f8008000 {
- pinctrl-0 = <&pinctrl_spi_ksz>;
- cs-gpios = <&pioC 25 0>;
- id = <1>;
-
- ksz9477: ksz9477@0 {
- compatible = "microchip,ksz9477";
- reg = <0>;
-
- spi-max-frequency = <44000000>;
- spi-cpha;
- spi-cpol;
-
- ports {
- #address-cells = <1>;
- #size-cells = <0>;
- port@0 {
- reg = <0>;
- label = "lan1";
- };
- port@1 {
- reg = <1>;
- label = "lan2";
- };
- port@2 {
- reg = <2>;
- label = "lan3";
- };
- port@3 {
- reg = <3>;
- label = "lan4";
- };
- port@4 {
- reg = <4>;
- label = "lan5";
- };
- port@5 {
- reg = <5>;
- label = "cpu";
- ethernet = <ð0>;
- fixed-link {
- speed = <1000>;
- full-duplex;
- };
- };
- };
- };
- ksz8565: ksz8565@0 {
- compatible = "microchip,ksz8565";
- reg = <0>;
-
- spi-max-frequency = <44000000>;
- spi-cpha;
- spi-cpol;
-
- ports {
- #address-cells = <1>;
- #size-cells = <0>;
- port@0 {
- reg = <0>;
- label = "lan1";
- };
- port@1 {
- reg = <1>;
- label = "lan2";
- };
- port@2 {
- reg = <2>;
- label = "lan3";
- };
- port@3 {
- reg = <3>;
- label = "lan4";
- };
- port@6 {
- reg = <6>;
- label = "cpu";
- ethernet = <ð0>;
- fixed-link {
- speed = <1000>;
- full-duplex;
- };
- };
- };
- };
- };
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/dsa/microchip,ksz.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Microchip KSZ Series Ethernet switches
+
+maintainers:
+ - Marek Vasut <marex@denx.de>
+ - Woojung Huh <Woojung.Huh@microchip.com>
+
+allOf:
+ - $ref: dsa.yaml#
+
+properties:
+ # See Documentation/devicetree/bindings/net/dsa/dsa.yaml for a list of additional
+ # required and optional properties.
+ compatible:
+ enum:
+ - microchip,ksz8765
+ - microchip,ksz8794
+ - microchip,ksz8795
+ - microchip,ksz9477
+ - microchip,ksz9897
+ - microchip,ksz9896
+ - microchip,ksz9567
+ - microchip,ksz8565
+ - microchip,ksz9893
+ - microchip,ksz9563
+ - microchip,ksz8563
+
+ reset-gpios:
+ description:
+ Should be a gpio specifier for a reset line.
+ maxItems: 1
+
+ microchip,synclko-125:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ Set if the output SYNCLKO frequency should be set to 125MHz instead of 25MHz.
+
+required:
+ - compatible
+ - reg
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ #include <dt-bindings/gpio/gpio.h>
+
+ // Ethernet switch connected via SPI to the host, CPU port wired to eth0:
+ eth0 {
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
+
+ spi0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ pinctrl-0 = <&pinctrl_spi_ksz>;
+ cs-gpios = <&pioC 25 0>;
+ id = <1>;
+
+ ksz9477: switch@0 {
+ compatible = "microchip,ksz9477";
+ reg = <0>;
+ reset-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>;
+
+ spi-max-frequency = <44000000>;
+
+ ethernet-ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ port@0 {
+ reg = <0>;
+ label = "lan1";
+ };
+ port@1 {
+ reg = <1>;
+ label = "lan2";
+ };
+ port@2 {
+ reg = <2>;
+ label = "lan3";
+ };
+ port@3 {
+ reg = <3>;
+ label = "lan4";
+ };
+ port@4 {
+ reg = <4>;
+ label = "lan5";
+ };
+ port@5 {
+ reg = <5>;
+ label = "cpu";
+ ethernet = <ð0>;
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
+ };
+ };
+
+ ksz8565: switch@1 {
+ compatible = "microchip,ksz8565";
+ reg = <1>;
+
+ spi-max-frequency = <44000000>;
+
+ ethernet-ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ port@0 {
+ reg = <0>;
+ label = "lan1";
+ };
+ port@1 {
+ reg = <1>;
+ label = "lan2";
+ };
+ port@2 {
+ reg = <2>;
+ label = "lan3";
+ };
+ port@3 {
+ reg = <3>;
+ label = "lan4";
+ };
+ port@6 {
+ reg = <6>;
+ label = "cpu";
+ ethernet = <ð0>;
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
+ };
+ };
+ };
+...
- interrupts: Should contain ethernet controller interrupt
Optional properties:
+- phy-handle: See ethernet.txt file in the same directory.
- phy-mode: See ethernet.txt file in the same directory. If the property is
absent, "rgmii" is assumed. Supported values are "rgmii*" and "rmii" for
aspeed parts. Other (unknown) parts will accept any value.
- "MACCLK": The MAC IP clock
- "RCLK": Clock gate for the RMII RCLK
+Optional subnodes:
+- mdio: See mdio.txt file in the same directory.
+
Example:
mac0: ethernet@1e660000 {
interrupts = <2>;
use-ncsi;
};
+
+Example with phy-handle:
+
+ mac1: ethernet@1e680000 {
+ compatible = "aspeed,ast2500-mac", "faraday,ftgmac100";
+ reg = <0x1e680000 0x180>;
+ interrupts = <2>;
+
+ phy-handle = <&phy>;
+ phy-mode = "rgmii";
+
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ phy: ethernet-phy@1 {
+ compatible = "ethernet-phy-ieee802.3-c22";
+ reg = <1>;
+ };
+ };
+ };
- reg: address on the bus
- interrupts: GPIO interrupt to which the chip is connected
- enable-gpios: Output GPIO pin used for enabling/disabling the chip
-- firmware-gpios: Output GPIO pin used to enter firmware download mode
Optional SoC Specific Properties:
- pinctrl-names: Contains only one value - "default".
- pintctrl-0: Specifies the pin control groups used for this controller.
+- firmware-gpios: Output GPIO pin used to enter firmware download mode
Example (for ARM-based BeagleBone with NPC100 NFC controller on I2C2):
properties:
compatible:
- const: samsung,s3fwrn5-i2c
+ enum:
+ - samsung,s3fwrn5-i2c
+ - samsung,s3fwrn82
en-gpios:
maxItems: 1
required:
- compatible
- en-gpios
- - interrupts
- - reg
- wake-gpios
+allOf:
+ - if:
+ properties:
+ compatible:
+ contains:
+ const: samsung,s3fwrn5-i2c
+ then:
+ required:
+ - interrupts
+ - reg
+
examples:
- |
#include <dt-bindings/gpio/gpio.h>
wake-gpios = <&gpj0 2 GPIO_ACTIVE_HIGH>;
};
};
+ # UART example on Raspberry Pi
+ - |
+ uart0 {
+ status = "okay";
+
+ nfc {
+ compatible = "samsung,s3fwrn82";
+
+ en-gpios = <&gpio 20 GPIO_ACTIVE_HIGH>;
+ wake-gpios = <&gpio 16 GPIO_ACTIVE_HIGH>;
+
+ status = "okay";
+ };
+ };
description: HiDeep Inc.
"^himax,.*":
description: Himax Technologies, Inc.
+ "^hirschmann,.*":
+ description: Hirschmann Automation and Control GmbH
"^hisilicon,.*":
description: Hisilicon Limited.
"^hit,.*":
on the socket as usual. There are also CAN specific socket options
described below.
-The basic CAN frame structure and the sockaddr structure are defined
-in include/linux/can.h:
+The Classical CAN frame structure (aka CAN 2.0B), the CAN FD frame structure
+and the sockaddr structure are defined in include/linux/can.h:
.. code-block:: C
struct can_frame {
canid_t can_id; /* 32 bit CAN_ID + EFF/RTR/ERR flags */
- __u8 can_dlc; /* frame payload length in byte (0 .. 8) */
+ union {
+ /* CAN frame payload length in byte (0 .. CAN_MAX_DLEN)
+ * was previously named can_dlc so we need to carry that
+ * name for legacy support
+ */
+ __u8 len;
+ __u8 can_dlc; /* deprecated */
+ };
__u8 __pad; /* padding */
__u8 __res0; /* reserved / padding */
- __u8 __res1; /* reserved / padding */
+ __u8 len8_dlc; /* optional DLC for 8 byte payload length (9 .. 15) */
__u8 data[8] __attribute__((aligned(8)));
};
+Remark: The len element contains the payload length in bytes and should be
+used instead of can_dlc. The deprecated can_dlc was misleadingly named as
+it always contained the plain payload length in bytes and not the so called
+'data length code' (DLC).
+
+To pass the raw DLC from/to a Classical CAN network device the len8_dlc
+element can contain values 9 .. 15 when the len element is 8 (the real
+payload length for all DLC values greater or equal to 8).
+
The alignment of the (linear) payload data[] to a 64bit boundary
allows the user to define their own structs and unions to easily access
the CAN payload. There is no given byteorder on the CAN bus by
/* transport protocol class address info (e.g. ISOTP) */
struct { canid_t rx_id, tx_id; } tp;
+ /* J1939 address information */
+ struct {
+ /* 8 byte name when using dynamic addressing */
+ __u64 name;
+
+ /* pgn:
+ * 8 bit: PS in PDU2 case, else 0
+ * 8 bit: PF
+ * 1 bit: DP
+ * 1 bit: reserved
+ */
+ __u32 pgn;
+
+ /* 1 byte address */
+ __u8 addr;
+ } j1939;
+
/* reserved for future CAN protocols address information */
} can_addr;
};
bytes of payload (struct can_frame) like the CAN_RAW socket. Therefore e.g.
the CAN_RAW socket supports a new socket option CAN_RAW_FD_FRAMES that
switches the socket into a mode that allows the handling of CAN FD frames
-and (legacy) CAN frames simultaneously (see :ref:`socketcan-rawfd`).
+and Classical CAN frames simultaneously (see :ref:`socketcan-rawfd`).
The struct canfd_frame is defined in include/linux/can.h:
length and the DLC has a 1:1 mapping in the range of 0 .. 8. To preserve
the easy handling of the length information the canfd_frame.len element
contains a plain length value from 0 .. 64. So both canfd_frame.len and
-can_frame.can_dlc are equal and contain a length information and no DLC.
+can_frame.len are equal and contain a length information and no DLC.
For details about the distinction of CAN and CAN FD capable devices and
the mapping to the bus-relevant data length code (DLC), see :ref:`socketcan-can-fd-driver`.
.. code-block:: C
- #define CAN_MTU (sizeof(struct can_frame)) == 16 => 'legacy' CAN frame
+ #define CAN_MTU (sizeof(struct can_frame)) == 16 => Classical CAN frame
#define CANFD_MTU (sizeof(struct canfd_frame)) == 72 => CAN FD frame
printf("got CAN FD frame with length %d\n", cfd.len);
/* cfd.flags contains valid data */
} else if (nbytes == CAN_MTU) {
- printf("got legacy CAN frame with length %d\n", cfd.len);
+ printf("got Classical CAN frame with length %d\n", cfd.len);
/* cfd.flags is undefined */
} else {
fprintf(stderr, "read: invalid CAN(FD) frame\n");
printf("%02X ", cfd.data[i]);
When reading with size CANFD_MTU only returns CAN_MTU bytes that have
-been received from the socket a legacy CAN frame has been read into the
+been received from the socket a Classical CAN frame has been read into the
provided CAN FD structure. Note that the canfd_frame.flags data field is
not specified in the struct can_frame and therefore it is only valid in
CANFD_MTU sized CAN FD frames.
To build a CAN FD aware application use struct canfd_frame as basic CAN
data structure for CAN_RAW based applications. When the application is
executed on an older Linux kernel and switching the CAN_RAW_FD_FRAMES
-socket option returns an error: No problem. You'll get legacy CAN frames
+socket option returns an error: No problem. You'll get Classical CAN frames
or CAN FD frames and can process them the same way.
When sending to CAN devices make sure that the device is capable to handle
RX_RTR_FRAME:
Send reply for RTR-request (placed in op->frames[0]).
+CAN_FD_FRAME:
+ The CAN frames following the bcm_msg_head are struct canfd_frame's
Broadcast Manager Transmission Timers
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stats - SocketCAN core statistics (rx/tx frames, match ratios, ...)
reset_stats - manual statistic reset
- version - prints the SocketCAN core version and the ABI version
+ version - prints SocketCAN core and ABI version (removed in Linux 5.10)
Writing Own CAN Protocol Modules
dev->type = ARPHRD_CAN; /* the netdevice hardware type */
dev->flags = IFF_NOARP; /* CAN has no arp */
- dev->mtu = CAN_MTU; /* sizeof(struct can_frame) -> legacy CAN interface */
+ dev->mtu = CAN_MTU; /* sizeof(struct can_frame) -> Classical CAN interface */
or alternative, when the controller supports CAN with flexible data rate:
dev->mtu = CANFD_MTU; /* sizeof(struct canfd_frame) -> CAN FD interface */
[ fd { on | off } ]
[ fd-non-iso { on | off } ]
[ presume-ack { on | off } ]
+ [ cc-len8-dlc { on | off } ]
[ restart-ms TIME-MS ]
[ restart ]
second bit timing has to be specified in order to enable the CAN FD bitrate.
Additionally CAN FD capable CAN controllers support up to 64 bytes of
-payload. The representation of this length in can_frame.can_dlc and
+payload. The representation of this length in can_frame.len and
canfd_frame.len for userspace applications and inside the Linux network
layer is a plain value from 0 .. 64 instead of the CAN 'data length code'.
-The data length code was a 1:1 mapping to the payload length in the legacy
+The data length code was a 1:1 mapping to the payload length in the Classical
CAN frames anyway. The payload length to the bus-relevant DLC mapping is
only performed inside the CAN drivers, preferably with the helper
-functions can_dlc2len() and can_len2dlc().
+functions can_fd_dlc2len() and can_fd_len2dlc().
The CAN netdevice driver capabilities can be distinguished by the network
devices maximum transfer unit (MTU)::
- MTU = 16 (CAN_MTU) => sizeof(struct can_frame) => 'legacy' CAN device
+ MTU = 16 (CAN_MTU) => sizeof(struct can_frame) => Classical CAN device
MTU = 72 (CANFD_MTU) => sizeof(struct canfd_frame) => CAN FD capable device
The CAN device MTU can be retrieved e.g. with a SIOCGIFMTU ioctl() syscall.
-N.B. CAN FD capable devices can also handle and send legacy CAN frames.
+N.B. CAN FD capable devices can also handle and send Classical CAN frames.
When configuring CAN FD capable CAN controllers an additional 'data' bitrate
has to be set. This bitrate for the data phase of the CAN FD frame has to be
* - ``esp_parsing``
- ``drop``
- Traps packets dropped due to an error in the ESP header parsing
+ * - ``blackhole_nexthop``
+ - ``drop``
+ - Traps packets that the device decided to drop in case they hit a
+ blackhole nexthop
Driver-specific Packet Traps
============================
=========
The ``netdevsim`` driver exposes resources to control the number of FIB
-entries and FIB rule entries that the driver will allow.
+entries, FIB rule entries and nexthops that the driver will allow.
.. code:: shell
$ devlink resource set netdevsim/netdevsim0 path /IPv4/fib-rules size 16
$ devlink resource set netdevsim/netdevsim0 path /IPv6/fib size 64
$ devlink resource set netdevsim/netdevsim0 path /IPv6/fib-rules size 16
+ $ devlink resource set netdevsim/netdevsim0 path /nexthops size 16
$ devlink dev reload netdevsim/netdevsim0
Driver-specific Traps
+++ /dev/null
-.. SPDX-License-Identifier: GPL-2.0
-
-================
-Frame Relay (FR)
-================
-
-Frame Relay (FR) support for linux is built into a two tiered system of device
-drivers. The upper layer implements RFC1490 FR specification, and uses the
-Data Link Connection Identifier (DLCI) as its hardware address. Usually these
-are assigned by your network supplier, they give you the number/numbers of
-the Virtual Connections (VC) assigned to you.
-
-Each DLCI is a point-to-point link between your machine and a remote one.
-As such, a separate device is needed to accommodate the routing. Within the
-net-tools archives is 'dlcicfg'. This program will communicate with the
-base "DLCI" device, and create new net devices named 'dlci00', 'dlci01'...
-The configuration script will ask you how many DLCIs you need, as well as
-how many DLCIs you want to assign to each Frame Relay Access Device (FRAD).
-
-The DLCI uses a number of function calls to communicate with the FRAD, all
-of which are stored in the FRAD's private data area. assoc/deassoc,
-activate/deactivate and dlci_config. The DLCI supplies a receive function
-to the FRAD to accept incoming packets.
-
-With this initial offering, only 1 FRAD driver is available. With many thanks
-to Sangoma Technologies, David Mandelstam & Gene Kozin, the S502A, S502E &
-S508 are supported. This driver is currently set up for only FR, but as
-Sangoma makes more firmware modules available, it can be updated to provide
-them as well.
-
-Configuration of the FRAD makes use of another net-tools program, 'fradcfg'.
-This program makes use of a configuration file (which dlcicfg can also read)
-to specify the types of boards to be configured as FRADs, as well as perform
-any board specific configuration. The Sangoma module of fradcfg loads the
-FR firmware into the card, sets the irq/port/memory information, and provides
-an initial configuration.
-
-Additional FRAD device drivers can be added as hardware is available.
-
-At this time, the dlcicfg and fradcfg programs have not been incorporated into
-the net-tools distribution. They can be found at ftp.invlogic.com, in
-/pub/linux. Note that with OS/2 FTPD, you end up in /pub by default, so just
-use 'cd linux'. v0.10 is for use on pre-2.0.3 and earlier, v0.15 is for
-pre-2.0.4 and later.
eql
fib_trie
filter
- framerelay
generic-hdlc
generic_netlink
gen_stats
lapb-module
mac80211-injection
mpls-sysctl
+ mptcp-sysctl
multiqueue
netconsole
netdev-features
tcp-thin
team
timestamping
+ tipc
tproxy
tuntap
udplite
Default: 1000 (1 seconds)
+ignore_routes_with_linkdown - BOOLEAN
+ Ignore routes whose link is down when performing a FIB lookup.
+
promote_secondaries - BOOLEAN
When a primary IP address is removed from this interface
promote a corresponding secondary IP address instead of
Default: 1
+udp_port - INTEGER
+ The listening port for the local UDP tunneling sock. Normally it's
+ using the IANA-assigned UDP port number 9899 (sctp-tunneling).
+
+ This UDP sock is used for processing the incoming UDP-encapsulated
+ SCTP packets (from RFC6951), and shared by all applications in the
+ same net namespace. This UDP sock will be closed when the value is
+ set to 0.
+
+ The value will also be used to set the src port of the UDP header
+ for the outgoing UDP-encapsulated SCTP packets. For the dest port,
+ please refer to 'encap_port' below.
+
+ Default: 0
+
+encap_port - INTEGER
+ The default remote UDP encapsulation port.
+
+ This value is used to set the dest port of the UDP header for the
+ outgoing UDP-encapsulated SCTP packets by default. Users can also
+ change the value for each sock/asoc/transport by using setsockopt.
+ For further information, please refer to RFC6951.
+
+ Note that when connecting to a remote server, the client should set
+ this to the port that the UDP tunneling sock on the peer server is
+ listening to and the local UDP tunneling sock on the client also
+ must be started. On the server, it would get the encap_port from
+ the incoming packet's source port.
+
+ Default: 0
+
``/proc/sys/net/core/*``
========================
PGN
---
+The J1939 protocol uses the 29-bit CAN identifier with the following structure:
+
+ ============ ============== ====================
+ 29 bit CAN-ID
+ --------------------------------------------------
+ Bit positions within the CAN-ID
+ --------------------------------------------------
+ 28 ... 26 25 ... 8 7 ... 0
+ ============ ============== ====================
+ Priority PGN SA (Source Address)
+ ============ ============== ====================
+
The PGN (Parameter Group Number) is a number to identify a packet. The PGN
is composed as follows:
-1 bit : Reserved Bit
-1 bit : Data Page
-8 bits : PF (PDU Format)
-8 bits : PS (PDU Specific)
+
+ ============ ============== ================= =================
+ PGN
+ ------------------------------------------------------------------
+ Bit positions within the CAN-ID
+ ------------------------------------------------------------------
+ 25 24 23 ... 16 15 ... 8
+ ============ ============== ================= =================
+ R (Reserved) DP (Data Page) PF (PDU Format) PS (PDU Specific)
+ ============ ============== ================= =================
In J1939-21 distinction is made between PDU1 format (where PF < 240) and PDU2
format (where PF >= 240). Furthermore, when using the PDU2 format, the PS-field
contains a so-called Group Extension, which is part of the PGN. When using PDU2
format, the Group Extension is set in the PS-field.
+ ============== ========================
+ PDU1 Format (specific) (peer to peer)
+ ----------------------------------------
+ Bit positions within the CAN-ID
+ ----------------------------------------
+ 23 ... 16 15 ... 8
+ ============== ========================
+ 00h ... EFh DA (Destination address)
+ ============== ========================
+
+ ============== ========================
+ PDU2 Format (global) (broadcast)
+ ----------------------------------------
+ Bit positions within the CAN-ID
+ ----------------------------------------
+ 23 ... 16 15 ... 8
+ ============== ========================
+ F0h ... FFh GE (Group Extenstion)
+ ============== ========================
+
On the other hand, when using PDU1 format, the PS-field contains a so-called
Destination Address, which is _not_ part of the PGN. When communicating a PGN
from user space to kernel (or vice versa) and PDU2 format is used, the PS-field
.. kernel-doc:: net/sunrpc/clnt.c
:export:
-WiMAX
------
-
-.. kernel-doc:: net/wimax/op-msg.c
- :export:
-
-.. kernel-doc:: net/wimax/op-reset.c
- :export:
-
-.. kernel-doc:: net/wimax/op-rfkill.c
- :export:
-
-.. kernel-doc:: net/wimax/stack.c
- :export:
-
-.. kernel-doc:: include/net/wimax.h
- :internal:
-
-.. kernel-doc:: include/uapi/linux/wimax.h
- :internal:
-
Network device support
======================
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+MPTCP Sysfs variables
+=====================
+
+/proc/sys/net/mptcp/* Variables
+===============================
+
+enabled - INTEGER
+ Control whether MPTCP sockets can be created.
+
+ MPTCP sockets can be created if the value is nonzero. This is
+ a per-namespace sysctl.
+
+ Default: 1
+
+add_addr_timeout - INTEGER (seconds)
+ Set the timeout after which an ADD_ADDR control message will be
+ resent to an MPTCP peer that has not acknowledged a previous
+ ADD_ADDR message.
+
+ The default value matches TCP_RTO_MAX. This is a per-namespace
+ sysctl.
+
+ Default: 120
* page_pool_get_dma_dir(): Retrieve the stored DMA direction.
+* page_pool_put_page_bulk(): Tries to refill a number of pages into the
+ ptr_ring cache holding ptr_ring producer lock. If the ptr_ring is full,
+ page_pool_put_page_bulk() will release leftover pages to the page allocator.
+ page_pool_put_page_bulk() is suitable to be run inside the driver NAPI tx
+ completion loop for the XDP_REDIRECT use case.
+ Please note the caller must not use data area after running
+ page_pool_put_page_bulk(), as this function overwrites it.
+
Coding examples
===============
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+=================
+Linux Kernel TIPC
+=================
+
+TIPC (Transparent Inter Process Communication) is a protocol that is
+specially designed for intra-cluster communication.
+
+For more information about TIPC, see http://tipc.sourceforge.net.
+
+TIPC Base Types
+---------------
+
+.. kernel-doc:: net/tipc/subscr.h
+ :internal:
+
+.. kernel-doc:: net/tipc/bearer.h
+ :internal:
+
+.. kernel-doc:: net/tipc/name_table.h
+ :internal:
+
+.. kernel-doc:: net/tipc/name_distr.h
+ :internal:
+
+.. kernel-doc:: net/tipc/bcast.c
+ :internal:
+
+TIPC Bearer Interfaces
+----------------------
+
+.. kernel-doc:: net/tipc/bearer.c
+ :internal:
+
+.. kernel-doc:: net/tipc/udp_media.c
+ :internal:
+
+TIPC Crypto Interfaces
+----------------------
+
+.. kernel-doc:: net/tipc/crypto.c
+ :internal:
+
+TIPC Discoverer Interfaces
+--------------------------
+
+.. kernel-doc:: net/tipc/discover.c
+ :internal:
+
+TIPC Link Interfaces
+--------------------
+
+.. kernel-doc:: net/tipc/link.c
+ :internal:
+
+TIPC msg Interfaces
+-------------------
+
+.. kernel-doc:: net/tipc/msg.c
+ :internal:
+
+TIPC Name Interfaces
+--------------------
+
+.. kernel-doc:: net/tipc/name_table.c
+ :internal:
+
+.. kernel-doc:: net/tipc/name_distr.c
+ :internal:
+
+TIPC Node Management Interfaces
+-------------------------------
+
+.. kernel-doc:: net/tipc/node.c
+ :internal:
+
+TIPC Socket Interfaces
+----------------------
+
+.. kernel-doc:: net/tipc/socket.c
+ :internal:
+
+TIPC Network Topology Interfaces
+--------------------------------
+
+.. kernel-doc:: net/tipc/subscr.c
+ :internal:
+
+TIPC Server Interfaces
+----------------------
+
+.. kernel-doc:: net/tipc/topsrv.c
+ :internal:
+
+TIPC Trace Interfaces
+---------------------
+
+.. kernel-doc:: net/tipc/trace.c
+ :internal:
SSTATE_MAGIC 0x5302 serial_state ``include/linux/serial.h``
SLIP_MAGIC 0x5302 slip ``drivers/net/slip.h``
STRIP_MAGIC 0x5303 strip ``drivers/net/strip.c``
-X25_ASY_MAGIC 0x5303 x25_asy ``drivers/net/x25_asy.h``
SIXPACK_MAGIC 0x5304 sixpack ``drivers/net/hamradio/6pack.h``
AX25_MAGIC 0x5316 ax_disp ``drivers/net/mkiss.h``
TTY_MAGIC 0x5401 tty_struct ``include/linux/tty.h``
SSTATE_MAGIC 0x5302 serial_state ``include/linux/serial.h``
SLIP_MAGIC 0x5302 slip ``drivers/net/slip.h``
STRIP_MAGIC 0x5303 strip ``drivers/net/strip.c``
-X25_ASY_MAGIC 0x5303 x25_asy ``drivers/net/x25_asy.h``
SIXPACK_MAGIC 0x5304 sixpack ``drivers/net/hamradio/6pack.h``
AX25_MAGIC 0x5316 ax_disp ``drivers/net/mkiss.h``
TTY_MAGIC 0x5401 tty_struct ``include/linux/tty.h``
unicode
vga-softcursor
video-output
- wimax/index
xfs
.. only:: subproject and html
SSTATE_MAGIC 0x5302 serial_state ``include/linux/serial.h``
SLIP_MAGIC 0x5302 slip ``drivers/net/slip.h``
STRIP_MAGIC 0x5303 strip ``drivers/net/strip.c``
-X25_ASY_MAGIC 0x5303 x25_asy ``drivers/net/x25_asy.h``
SIXPACK_MAGIC 0x5304 sixpack ``drivers/net/hamradio/6pack.h``
AX25_MAGIC 0x5316 ax_disp ``drivers/net/mkiss.h``
TTY_MAGIC 0x5401 tty_struct ``include/linux/tty.h``
W: http://floatingpoint.sourceforge.net/emulator/index.html
F: arch/x86/math-emu/
-FRAME RELAY DLCI/FRAD (Sangoma drivers too)
-L: netdev@vger.kernel.org
-S: Orphan
-F: drivers/net/wan/dlci.c
-F: drivers/net/wan/sdla.c
-
FRAMEBUFFER LAYER
M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
L: dri-devel@lists.freedesktop.org
F: include/uapi/linux/if_hippi.h
F: net/802/hippi.c
+HIRSCHMANN HELLCREEK ETHERNET SWITCH DRIVER
+M: Kurt Kanzenbach <kurt@linutronix.de>
+L: netdev@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/net/dsa/hirschmann,hellcreek.yaml
+F: drivers/net/dsa/hirschmann/*
+F: include/linux/platform_data/hirschmann-hellcreek.h
+F: net/dsa/tag_hellcreek.c
+
HISILICON DMA DRIVER
M: Zhou Wang <wangzhou1@hisilicon.com>
L: dmaengine@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/iwlwifi/iwlwifi.git
F: drivers/net/wireless/intel/iwlwifi/
-INTEL WIRELESS WIMAX CONNECTION 2400
-M: Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
-M: linux-wimax@intel.com
-L: wimax@linuxwimax.org (subscribers-only)
-S: Supported
-W: http://linuxwimax.org
-F: Documentation/admin-guide/wimax/i2400m.rst
-F: drivers/net/wimax/i2400m/
-F: include/uapi/linux/wimax/i2400m.h
-
INTEL WMI SLIM BOOTLOADER (SBL) FIRMWARE UPDATE DRIVER
M: Jithu Joseph <jithu.joseph@intel.com>
R: Maurice Ma <maurice.ma@intel.com>
L: linux-crypto@vger.kernel.org
S: Maintained
F: drivers/crypto/marvell/
+F: include/linux/soc/marvell/octeontx2/
MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2)
M: Mirko Lindner <mlindner@marvell.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/marvell/octeontx2/nic/
+F: include/linux/soc/marvell/octeontx2/
MARVELL OCTEONTX2 RVU ADMIN FUNCTION DRIVER
M: Sunil Goutham <sgoutham@marvell.com>
M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
L: netdev@vger.kernel.org
S: Maintained
-F: Documentation/devicetree/bindings/net/dsa/ksz.txt
+F: Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
F: drivers/net/dsa/microchip/*
F: include/linux/platform_data/microchip-ksz.h
F: net/dsa/tag_ksz.c
S: Maintained
W: https://github.com/multipath-tcp/mptcp_net-next/wiki
B: https://github.com/multipath-tcp/mptcp_net-next/issues
+F: Documentation/networking/mptcp-sysctl.rst
F: include/net/mptcp.h
F: include/uapi/linux/mptcp.h
F: net/mptcp/
W: https://wireless.wiki.kernel.org/en/users/Drivers/wil6210
F: drivers/net/wireless/ath/wil6210/
-WIMAX STACK
-M: Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
-M: linux-wimax@intel.com
-L: wimax@linuxwimax.org (subscribers-only)
-S: Supported
-W: http://linuxwimax.org
-F: Documentation/admin-guide/wimax/wimax.rst
-F: include/linux/wimax/debug.h
-F: include/net/wimax.h
-F: include/uapi/linux/wimax.h
-F: net/wimax/
-
WINBOND CIR DRIVER
M: David Härdeman <david@hardeman.nu>
S: Maintained
CONFIG_HDLC_FR=m
CONFIG_HDLC_PPP=m
CONFIG_HDLC_X25=m
-CONFIG_DLCI=m
CONFIG_WAN_ROUTER_DRIVERS=m
CONFIG_ATM_TCP=m
# CONFIG_INPUT_KEYBOARD is not set
CONFIG_DSCC4=m
CONFIG_DSCC4_PCISYNC=y
CONFIG_DSCC4_PCI_RST=y
-CONFIG_DLCI=m
CONFIG_LAPBETHER=m
-CONFIG_X25_ASY=m
# CONFIG_INPUT_KEYBOARD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
CONFIG_DSCC4=m
CONFIG_DSCC4_PCISYNC=y
CONFIG_DSCC4_PCI_RST=y
-CONFIG_DLCI=m
CONFIG_LAPBETHER=m
-CONFIG_X25_ASY=m
# CONFIG_KEYBOARD_ATKBD is not set
CONFIG_KEYBOARD_GPIO=y
# CONFIG_INPUT_MOUSE is not set
struct sk_buff *skb;
unsigned long flags, timeout;
int read, write, lastread = -1;
- APRINTK(!in_interrupt(),
- "lanai_shutdown_tx_vci called w/o process context!\n");
+
if (lvcc->vbase == NULL) /* We were never bound to a VCI */
return;
/* 15.2.1 - wait for queue to drain */
static void ns_close(struct atm_vcc *vcc);
static void fill_tst(ns_dev * card, int n, vc_map * vc);
static int ns_send(struct atm_vcc *vcc, struct sk_buff *skb);
+static int ns_send_bh(struct atm_vcc *vcc, struct sk_buff *skb);
static int push_scqe(ns_dev * card, vc_map * vc, scq_info * scq, ns_scqe * tbd,
- struct sk_buff *skb);
+ struct sk_buff *skb, bool may_sleep);
static void process_tsq(ns_dev * card);
static void drain_scq(ns_dev * card, scq_info * scq, int pos);
static void process_rsq(ns_dev * card);
.close = ns_close,
.ioctl = ns_ioctl,
.send = ns_send,
+ .send_bh = ns_send_bh,
.phy_put = ns_phy_put,
.phy_get = ns_phy_get,
.proc_read = ns_proc_read,
card->tst_addr = new_tst;
}
-static int ns_send(struct atm_vcc *vcc, struct sk_buff *skb)
+static int _ns_send(struct atm_vcc *vcc, struct sk_buff *skb, bool may_sleep)
{
ns_dev *card;
vc_map *vc;
scq = card->scq0;
}
- if (push_scqe(card, vc, scq, &scqe, skb) != 0) {
+ if (push_scqe(card, vc, scq, &scqe, skb, may_sleep) != 0) {
atomic_inc(&vcc->stats->tx_err);
dma_unmap_single(&card->pcidev->dev, NS_PRV_DMA(skb), skb->len,
DMA_TO_DEVICE);
return 0;
}
+static int ns_send(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+ return _ns_send(vcc, skb, true);
+}
+
+static int ns_send_bh(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+ return _ns_send(vcc, skb, false);
+}
+
static int push_scqe(ns_dev * card, vc_map * vc, scq_info * scq, ns_scqe * tbd,
- struct sk_buff *skb)
+ struct sk_buff *skb, bool may_sleep)
{
unsigned long flags;
ns_scqe tsr;
spin_lock_irqsave(&scq->lock, flags);
while (scq->tail == scq->next) {
- if (in_interrupt()) {
+ if (!may_sleep) {
spin_unlock_irqrestore(&scq->lock, flags);
printk("nicstar%d: Error pushing TBD.\n", card->index);
return 1;
int has_run = 0;
while (scq->tail == scq->next) {
- if (in_interrupt()) {
+ if (!may_sleep) {
data = scq_virt_to_bus(scq, scq->next);
ns_write_sram(card, scq->scd, &data, 1);
spin_unlock_irqrestore(&scq->lock, flags);
}
EXPORT_SYMBOL_GPL(mhi_queue_buf);
+bool mhi_queue_is_full(struct mhi_device *mhi_dev, enum dma_data_direction dir)
+{
+ struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl;
+ struct mhi_chan *mhi_chan = (dir == DMA_TO_DEVICE) ?
+ mhi_dev->ul_chan : mhi_dev->dl_chan;
+ struct mhi_ring *tre_ring = &mhi_chan->tre_ring;
+
+ return mhi_is_ring_full(mhi_cntrl, tre_ring);
+}
+EXPORT_SYMBOL_GPL(mhi_queue_is_full);
+
int mhi_send_cmd(struct mhi_controller *mhi_cntrl,
struct mhi_chan *mhi_chan,
enum mhi_cmd_type cmd)
}
}
-static int caam_qi_napi_schedule(struct qman_portal *p, struct caam_napi *np)
+static int caam_qi_napi_schedule(struct qman_portal *p, struct caam_napi *np,
+ bool sched_napi)
{
- /*
- * In case of threaded ISR, for RT kernels in_irq() does not return
- * appropriate value, so use in_serving_softirq to distinguish between
- * softirq and irq contexts.
- */
- if (unlikely(in_irq() || !in_serving_softirq())) {
+ if (sched_napi) {
/* Disable QMan IRQ source and invoke NAPI */
qman_p_irqsource_remove(p, QM_PIRQ_DQRI);
np->p = p;
static enum qman_cb_dqrr_result caam_rsp_fq_dqrr_cb(struct qman_portal *p,
struct qman_fq *rsp_fq,
- const struct qm_dqrr_entry *dqrr)
+ const struct qm_dqrr_entry *dqrr,
+ bool sched_napi)
{
struct caam_napi *caam_napi = raw_cpu_ptr(&pcpu_qipriv.caam_napi);
struct caam_drv_req *drv_req;
struct caam_drv_private *priv = dev_get_drvdata(qidev);
u32 status;
- if (caam_qi_napi_schedule(p, caam_napi))
+ if (caam_qi_napi_schedule(p, caam_napi, sched_napi))
return qman_cb_dqrr_stop;
fd = &dqrr->fd;
if (tb[RDMA_NLDEV_ATTR_DEV_NAME]) {
char name[IB_DEVICE_NAME_MAX] = {};
- nla_strlcpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
+ nla_strscpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
IB_DEVICE_NAME_MAX);
if (strlen(name) == 0) {
err = -EINVAL;
!tb[RDMA_NLDEV_ATTR_LINK_TYPE] || !tb[RDMA_NLDEV_ATTR_NDEV_NAME])
return -EINVAL;
- nla_strlcpy(ibdev_name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
+ nla_strscpy(ibdev_name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
sizeof(ibdev_name));
if (strchr(ibdev_name, '%') || strlen(ibdev_name) == 0)
return -EINVAL;
- nla_strlcpy(type, tb[RDMA_NLDEV_ATTR_LINK_TYPE], sizeof(type));
- nla_strlcpy(ndev_name, tb[RDMA_NLDEV_ATTR_NDEV_NAME],
+ nla_strscpy(type, tb[RDMA_NLDEV_ATTR_LINK_TYPE], sizeof(type));
+ nla_strscpy(ndev_name, tb[RDMA_NLDEV_ATTR_NDEV_NAME],
sizeof(ndev_name));
ndev = dev_get_by_name(sock_net(skb->sk), ndev_name);
if (err || !tb[RDMA_NLDEV_ATTR_CHARDEV_TYPE])
return -EINVAL;
- nla_strlcpy(client_name, tb[RDMA_NLDEV_ATTR_CHARDEV_TYPE],
+ nla_strscpy(client_name, tb[RDMA_NLDEV_ATTR_CHARDEV_TYPE],
sizeof(client_name));
if (tb[RDMA_NLDEV_ATTR_DEV_INDEX]) {
u32 extra_bytes;
u32 tlen, qpnum;
bool do_work, do_cnp;
- struct hfi1_ipoib_dev_priv *priv;
trace_hfi1_rcvhdr(packet);
if (unlikely(!skb))
goto drop;
- priv = hfi1_ipoib_priv(netdev);
- hfi1_ipoib_update_rx_netstats(priv, 1, skb->len);
+ dev_sw_netstats_rx_add(netdev, skb->len);
skb->dev = netdev;
skb->pkt_type = PACKET_HOST;
const struct net_device_ops *netdev_ops;
struct rvt_qp *qp;
- struct pcpu_sw_netstats __percpu *netstats;
};
/* hfi1 ipoib rdma netdev's private data structure */
return &((struct hfi1_ipoib_rdma_netdev *)netdev_priv(dev))->dev_priv;
}
-static inline void
-hfi1_ipoib_update_rx_netstats(struct hfi1_ipoib_dev_priv *priv,
- u64 packets,
- u64 bytes)
-{
- struct pcpu_sw_netstats *netstats = this_cpu_ptr(priv->netstats);
-
- u64_stats_update_begin(&netstats->syncp);
- netstats->rx_packets += packets;
- netstats->rx_bytes += bytes;
- u64_stats_update_end(&netstats->syncp);
-}
-
-static inline void
-hfi1_ipoib_update_tx_netstats(struct hfi1_ipoib_dev_priv *priv,
- u64 packets,
- u64 bytes)
-{
- struct pcpu_sw_netstats *netstats = this_cpu_ptr(priv->netstats);
-
- u64_stats_update_begin(&netstats->syncp);
- netstats->tx_packets += packets;
- netstats->tx_bytes += bytes;
- u64_stats_update_end(&netstats->syncp);
-}
-
int hfi1_ipoib_send_dma(struct net_device *dev,
struct sk_buff *skb,
struct ib_ah *address,
struct hfi1_ipoib_dev_priv *priv = hfi1_ipoib_priv(dev);
int ret;
- priv->netstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
ret = priv->netdev_ops->ndo_init(dev);
if (ret)
return priv->netdev_ops->ndo_stop(dev);
}
-static void hfi1_ipoib_dev_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *storage)
-{
- struct hfi1_ipoib_dev_priv *priv = hfi1_ipoib_priv(dev);
-
- netdev_stats_to_stats64(storage, &dev->stats);
- dev_fetch_sw_netstats(storage, priv->netstats);
-}
-
static const struct net_device_ops hfi1_ipoib_netdev_ops = {
.ndo_init = hfi1_ipoib_dev_init,
.ndo_uninit = hfi1_ipoib_dev_uninit,
.ndo_open = hfi1_ipoib_dev_open,
.ndo_stop = hfi1_ipoib_dev_stop,
- .ndo_get_stats64 = hfi1_ipoib_dev_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
};
static int hfi1_ipoib_send(struct net_device *dev,
hfi1_ipoib_txreq_deinit(priv);
hfi1_ipoib_rxq_deinit(priv->netdev);
- free_percpu(priv->netstats);
+ free_percpu(dev->tstats);
}
static void hfi1_ipoib_free_rdma_netdev(struct net_device *dev)
struct hfi1_ipoib_dev_priv *priv = tx->priv;
if (likely(!tx->sdma_status)) {
- hfi1_ipoib_update_tx_netstats(priv, 1, tx->skb->len);
+ dev_sw_netstats_tx_add(priv->netdev, 1, tx->skb->len);
} else {
++priv->netdev->stats.tx_errors;
dd_dev_warn(priv->dd,
#include <linux/compiler.h>
#include <linux/module.h>
+#include <linux/ethtool.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/major.h>
* the project's page is at https://linuxtv.org
*/
+#include <linux/ethtool.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
mostly intended for developers or support to debug vsock issues. If
unsure, say N.
+config MHI_NET
+ tristate "MHI network driver"
+ depends on MHI_BUS
+ help
+ This is the network driver for MHI bus. It can be used with
+ QCOM based WWAN modems (like SDX55). Say Y or M.
+
endif # NET_CORE
config SUNGEM_PHY
source "drivers/net/wireless/Kconfig"
-source "drivers/net/wimax/Kconfig"
-
source "drivers/net/wan/Kconfig"
source "drivers/net/ieee802154/Kconfig"
obj-$(CONFIG_NLMON) += nlmon.o
obj-$(CONFIG_NET_VRF) += vrf.o
obj-$(CONFIG_VSOCKMON) += vsockmon.o
+obj-$(CONFIG_MHI_NET) += mhi_net.o
#
# Networking Drivers
obj-$(CONFIG_SUNGEM_PHY) += sungem_phy.o
obj-$(CONFIG_WAN) += wan/
obj-$(CONFIG_WLAN) += wireless/
-obj-$(CONFIG_WIMAX) += wimax/
obj-$(CONFIG_IEEE802154) += ieee802154/
obj-$(CONFIG_VMXNET3) += vmxnet3/
.ndo_open = bareudp_open,
.ndo_stop = bareudp_stop,
.ndo_start_xmit = bareudp_xmit,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_fill_metadata_dst = bareudp_fill_metadata_dst,
};
};
/* Info for udev, that this is a virtual tunnel endpoint */
-static struct device_type bareudp_type = {
+static const struct device_type bareudp_type = {
.name = "bareudp",
};
}
#define BOND_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
- NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
+ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \
NETIF_F_HIGHDMA | NETIF_F_LRO)
#define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
- NETIF_F_RXCSUM | NETIF_F_ALL_TSO)
+ NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE)
#define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
- NETIF_F_ALL_TSO)
+ NETIF_F_GSO_SOFTWARE)
static void bond_compute_features(struct bonding *bond)
bond_dev->vlan_features = vlan_features;
bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
NETIF_F_HW_VLAN_CTAG_TX |
- NETIF_F_HW_VLAN_STAG_TX |
- NETIF_F_GSO_UDP_L4;
+ NETIF_F_HW_VLAN_STAG_TX;
#ifdef CONFIG_XFRM_OFFLOAD
bond_dev->hw_enc_features |= xfrm_features;
#endif /* CONFIG_XFRM_OFFLOAD */
NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_CTAG_FILTER;
- bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4;
+ bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
#ifdef CONFIG_XFRM_OFFLOAD
bond_dev->hw_features |= BOND_XFRM_FEATURES;
#endif /* CONFIG_XFRM_OFFLOAD */
// SPDX-License-Identifier: GPL-2.0
#include <linux/proc_fs.h>
+#include <linux/ethtool.h>
#include <linux/export.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
}
reg_mid = at91_can_id_to_reg_mid(cf->can_id);
reg_mcr = ((cf->can_id & CAN_RTR_FLAG) ? AT91_MCR_MRTR : 0) |
- (cf->can_dlc << 16) | AT91_MCR_MTCR;
+ (cf->len << 16) | AT91_MCR_MTCR;
/* disable MB while writing ID (see datasheet) */
set_mb_mode(priv, mb, AT91_MB_MODE_DISABLED);
/* This triggers transmission */
at91_write(priv, AT91_MCR(mb), reg_mcr);
- stats->tx_bytes += cf->can_dlc;
+ stats->tx_bytes += cf->len;
/* _NOTE_: subtract AT91_MB_TX_FIRST offset from mb! */
can_put_echo_skb(skb, dev, mb - get_mb_tx_first(priv));
cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_receive_skb(skb);
}
cf->can_id = (reg_mid >> 18) & CAN_SFF_MASK;
reg_msr = at91_read(priv, AT91_MSR(mb));
- cf->can_dlc = get_can_dlc((reg_msr >> 16) & 0xf);
+ cf->len = can_cc_dlc2len((reg_msr >> 16) & 0xf);
if (reg_msr & AT91_MSR_MRTR)
cf->can_id |= CAN_RTR_FLAG;
at91_read_mb(dev, mb, cf);
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_receive_skb(skb);
can_led_event(dev, CAN_LED_EVENT_RX);
at91_poll_err_frame(dev, cf, reg_sr);
dev->stats.rx_packets++;
- dev->stats.rx_bytes += cf->can_dlc;
+ dev->stats.rx_bytes += cf->len;
netif_receive_skb(skb);
return 1;
at91_irq_err_state(dev, cf, new_state);
dev->stats.rx_packets++;
- dev->stats.rx_bytes += cf->can_dlc;
+ dev->stats.rx_bytes += cf->len;
netif_rx(skb);
priv->can.state = new_state;
struct can_frame *frame, int idx)
{
struct c_can_priv *priv = netdev_priv(dev);
- u16 ctrl = IF_MCONT_TX | frame->can_dlc;
+ u16 ctrl = IF_MCONT_TX | frame->len;
bool rtr = frame->can_id & CAN_RTR_FLAG;
u32 arb = IF_ARB_MSGVAL;
int i;
if (priv->type == BOSCH_D_CAN) {
u32 data = 0, dreg = C_CAN_IFACE(DATA1_REG, iface);
- for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+ for (i = 0; i < frame->len; i += 4, dreg += 2) {
data = (u32)frame->data[i];
data |= (u32)frame->data[i + 1] << 8;
data |= (u32)frame->data[i + 2] << 16;
priv->write_reg32(priv, dreg, data);
}
} else {
- for (i = 0; i < frame->can_dlc; i += 2) {
+ for (i = 0; i < frame->len; i += 2) {
priv->write_reg(priv,
C_CAN_IFACE(DATA1_REG, iface) + i / 2,
frame->data[i] |
return -ENOMEM;
}
- frame->can_dlc = get_can_dlc(ctrl & 0x0F);
+ frame->len = can_cc_dlc2len(ctrl & 0x0F);
arb = priv->read_reg32(priv, C_CAN_IFACE(ARB1_REG, iface));
int i, dreg = C_CAN_IFACE(DATA1_REG, iface);
if (priv->type == BOSCH_D_CAN) {
- for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+ for (i = 0; i < frame->len; i += 4, dreg += 2) {
data = priv->read_reg32(priv, dreg);
frame->data[i] = data;
frame->data[i + 1] = data >> 8;
frame->data[i + 3] = data >> 24;
}
} else {
- for (i = 0; i < frame->can_dlc; i += 2, dreg++) {
+ for (i = 0; i < frame->len; i += 2, dreg++) {
data = priv->read_reg(priv, dreg);
frame->data[i] = data;
frame->data[i + 1] = data >> 8;
}
stats->rx_packets++;
- stats->rx_bytes += frame->can_dlc;
+ stats->rx_bytes += frame->len;
netif_receive_skb(skb);
return 0;
* transmit as we might race against do_tx().
*/
c_can_setup_tx_object(dev, IF_TX, frame, idx);
- priv->dlc[idx] = frame->can_dlc;
+ priv->dlc[idx] = frame->len;
can_put_echo_skb(skb, dev, idx);
/* Update the active bits */
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_receive_skb(skb);
return 1;
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_receive_skb(skb);
return 1;
}
u32 id;
int i;
- dlc = cf->can_dlc;
+ dlc = cf->len;
id = cf->can_id;
rtr = cf->can_id & CAN_RTR_FLAG ? 0 : MSGCFG_DIR;
cf->can_id = CAN_RTR_FLAG;
if (config & MSGCFG_XTD)
cf->can_id |= CAN_EFF_FLAG;
- cf->can_dlc = 0;
+ cf->len = 0;
} else {
if (config & MSGCFG_XTD) {
id = cc770_read_reg(priv, msgobj[mo].id[3]);
}
cf->can_id = id;
- cf->can_dlc = get_can_dlc((config & 0xf0) >> 4);
- for (i = 0; i < cf->can_dlc; i++)
+ cf->len = can_cc_dlc2len((config & 0xf0) >> 4);
+ for (i = 0; i < cf->len; i++)
cf->data[i] = cc770_read_reg(priv, msgobj[mo].data[i]);
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
return 0;
}
cf = (struct can_frame *)priv->tx_skb->data;
- stats->tx_bytes += cf->can_dlc;
+ stats->tx_bytes += cf->len;
stats->tx_packets++;
can_put_echo_skb(priv->tx_skb, dev, 0);
static const u8 dlc2len[] = {0, 1, 2, 3, 4, 5, 6, 7,
8, 12, 16, 20, 24, 32, 48, 64};
-/* get data length from can_dlc with sanitized can_dlc */
-u8 can_dlc2len(u8 can_dlc)
+/* get data length from raw data length code (DLC) */
+u8 can_fd_dlc2len(u8 dlc)
{
- return dlc2len[can_dlc & 0x0F];
+ return dlc2len[dlc & 0x0F];
}
-EXPORT_SYMBOL_GPL(can_dlc2len);
+EXPORT_SYMBOL_GPL(can_fd_dlc2len);
static const u8 len2dlc[] = {0, 1, 2, 3, 4, 5, 6, 7, 8, /* 0 - 8 */
9, 9, 9, 9, /* 9 - 12 */
15, 15, 15, 15, 15, 15, 15, 15}; /* 57 - 64 */
/* map the sanitized data length to an appropriate data length code */
-u8 can_len2dlc(u8 len)
+u8 can_fd_len2dlc(u8 len)
{
if (unlikely(len > 64))
return 0xF;
return len2dlc[len];
}
-EXPORT_SYMBOL_GPL(can_len2dlc);
+EXPORT_SYMBOL_GPL(can_fd_len2dlc);
#ifdef CONFIG_CAN_CALC_BITTIMING
#define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */
netif_rx_ni(skb);
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
restart:
netdev_dbg(dev, "restarted\n");
return NULL;
(*cf)->can_id = CAN_ERR_FLAG;
- (*cf)->can_dlc = CAN_ERR_DLC;
+ (*cf)->len = CAN_ERR_DLC;
return skb;
}
#define FLEXCAN_QUIRK_BROKEN_PERR_STATE BIT(6)
/* default to BE register access */
#define FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN BIT(7)
-/* Setup stop mode to support wakeup */
-#define FLEXCAN_QUIRK_SETUP_STOP_MODE BIT(8)
+/* Setup stop mode with GPR to support wakeup */
+#define FLEXCAN_QUIRK_SETUP_STOP_MODE_GPR BIT(8)
/* Support CAN-FD mode */
#define FLEXCAN_QUIRK_SUPPORT_FD BIT(9)
/* support memory detection and correction */
static const struct flexcan_devtype_data fsl_imx6q_devtype_data = {
.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
- FLEXCAN_QUIRK_SETUP_STOP_MODE,
+ FLEXCAN_QUIRK_SETUP_STOP_MODE_GPR,
};
static const struct flexcan_devtype_data fsl_imx8qm_devtype_data = {
static struct flexcan_devtype_data fsl_imx8mp_devtype_data = {
.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP |
- FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_SETUP_STOP_MODE |
+ FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_SETUP_STOP_MODE_GPR |
FLEXCAN_QUIRK_SUPPORT_FD | FLEXCAN_QUIRK_SUPPORT_ECC,
};
struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
u32 can_id;
u32 data;
- u32 ctrl = FLEXCAN_MB_CODE_TX_DATA | ((can_len2dlc(cfd->len)) << 16);
+ u32 ctrl = FLEXCAN_MB_CODE_TX_DATA | ((can_fd_len2dlc(cfd->len)) << 16);
int i;
if (can_dropped_invalid_skb(dev, skb))
cfd->can_id = (reg_id >> 18) & CAN_SFF_MASK;
if (reg_ctrl & FLEXCAN_MB_CNT_EDL) {
- cfd->len = can_dlc2len(get_canfd_dlc((reg_ctrl >> 16) & 0xf));
+ cfd->len = can_fd_dlc2len((reg_ctrl >> 16) & 0xf);
if (reg_ctrl & FLEXCAN_MB_CNT_BRS)
cfd->flags |= CANFD_BRS;
} else {
- cfd->len = get_can_dlc((reg_ctrl >> 16) & 0xf);
+ cfd->len = can_cc_dlc2len((reg_ctrl >> 16) & 0xf);
if (reg_ctrl & FLEXCAN_MB_CNT_RTR)
cfd->can_id |= CAN_RTR_FLAG;
priv->write(reg_ctrl2, ®s->ctrl2);
}
+static int flexcan_rx_offload_setup(struct net_device *dev)
+{
+ struct flexcan_priv *priv = netdev_priv(dev);
+ int err;
+
+ if (priv->can.ctrlmode & CAN_CTRLMODE_FD)
+ priv->mb_size = sizeof(struct flexcan_mb) + CANFD_MAX_DLEN;
+ else
+ priv->mb_size = sizeof(struct flexcan_mb) + CAN_MAX_DLEN;
+ priv->mb_count = (sizeof(priv->regs->mb[0]) / priv->mb_size) +
+ (sizeof(priv->regs->mb[1]) / priv->mb_size);
+
+ if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP)
+ priv->tx_mb_reserved =
+ flexcan_get_mb(priv, FLEXCAN_TX_MB_RESERVED_OFF_TIMESTAMP);
+ else
+ priv->tx_mb_reserved =
+ flexcan_get_mb(priv, FLEXCAN_TX_MB_RESERVED_OFF_FIFO);
+ priv->tx_mb_idx = priv->mb_count - 1;
+ priv->tx_mb = flexcan_get_mb(priv, priv->tx_mb_idx);
+ priv->tx_mask = FLEXCAN_IFLAG_MB(priv->tx_mb_idx);
+
+ priv->offload.mailbox_read = flexcan_mailbox_read;
+
+ if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) {
+ priv->offload.mb_first = FLEXCAN_RX_MB_OFF_TIMESTAMP_FIRST;
+ priv->offload.mb_last = priv->mb_count - 2;
+
+ priv->rx_mask = GENMASK_ULL(priv->offload.mb_last,
+ priv->offload.mb_first);
+ err = can_rx_offload_add_timestamp(dev, &priv->offload);
+ } else {
+ priv->rx_mask = FLEXCAN_IFLAG_RX_FIFO_OVERFLOW |
+ FLEXCAN_IFLAG_RX_FIFO_AVAILABLE;
+ err = can_rx_offload_add_fifo(dev, &priv->offload,
+ FLEXCAN_NAPI_WEIGHT);
+ }
+
+ return err;
+}
+
+static void flexcan_chip_interrupts_enable(const struct net_device *dev)
+{
+ const struct flexcan_priv *priv = netdev_priv(dev);
+ struct flexcan_regs __iomem *regs = priv->regs;
+ u64 reg_imask;
+
+ disable_irq(dev->irq);
+ priv->write(priv->reg_ctrl_default, ®s->ctrl);
+ reg_imask = priv->rx_mask | priv->tx_mask;
+ priv->write(upper_32_bits(reg_imask), ®s->imask2);
+ priv->write(lower_32_bits(reg_imask), ®s->imask1);
+ enable_irq(dev->irq);
+}
+
+static void flexcan_chip_interrupts_disable(const struct net_device *dev)
+{
+ const struct flexcan_priv *priv = netdev_priv(dev);
+ struct flexcan_regs __iomem *regs = priv->regs;
+
+ priv->write(0, ®s->imask2);
+ priv->write(0, ®s->imask1);
+ priv->write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL,
+ ®s->ctrl);
+}
+
/* flexcan_chip_start
*
* this functions is entered with clocks enabled
struct flexcan_priv *priv = netdev_priv(dev);
struct flexcan_regs __iomem *regs = priv->regs;
u32 reg_mcr, reg_ctrl, reg_ctrl2, reg_mecr;
- u64 reg_imask;
int err, i;
struct flexcan_mb __iomem *mb;
priv->can.state = CAN_STATE_ERROR_ACTIVE;
- /* enable interrupts atomically */
- disable_irq(dev->irq);
- priv->write(priv->reg_ctrl_default, ®s->ctrl);
- reg_imask = priv->rx_mask | priv->tx_mask;
- priv->write(upper_32_bits(reg_imask), ®s->imask2);
- priv->write(lower_32_bits(reg_imask), ®s->imask1);
- enable_irq(dev->irq);
-
/* print chip status */
netdev_dbg(dev, "%s: reading mcr=0x%08x ctrl=0x%08x\n", __func__,
priv->read(®s->mcr), priv->read(®s->ctrl));
static int __flexcan_chip_stop(struct net_device *dev, bool disable_on_error)
{
struct flexcan_priv *priv = netdev_priv(dev);
- struct flexcan_regs __iomem *regs = priv->regs;
int err;
/* freeze + disable module */
if (err && !disable_on_error)
goto out_chip_unfreeze;
- /* Disable all interrupts */
- priv->write(0, ®s->imask2);
- priv->write(0, ®s->imask1);
- priv->write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL,
- ®s->ctrl);
-
priv->can.state = CAN_STATE_STOPPED;
return 0;
if (err)
goto out_close;
- err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev);
+ err = flexcan_rx_offload_setup(dev);
if (err)
goto out_transceiver_disable;
- if (priv->can.ctrlmode & CAN_CTRLMODE_FD)
- priv->mb_size = sizeof(struct flexcan_mb) + CANFD_MAX_DLEN;
- else
- priv->mb_size = sizeof(struct flexcan_mb) + CAN_MAX_DLEN;
- priv->mb_count = (sizeof(priv->regs->mb[0]) / priv->mb_size) +
- (sizeof(priv->regs->mb[1]) / priv->mb_size);
-
- if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP)
- priv->tx_mb_reserved =
- flexcan_get_mb(priv, FLEXCAN_TX_MB_RESERVED_OFF_TIMESTAMP);
- else
- priv->tx_mb_reserved =
- flexcan_get_mb(priv, FLEXCAN_TX_MB_RESERVED_OFF_FIFO);
- priv->tx_mb_idx = priv->mb_count - 1;
- priv->tx_mb = flexcan_get_mb(priv, priv->tx_mb_idx);
- priv->tx_mask = FLEXCAN_IFLAG_MB(priv->tx_mb_idx);
-
- priv->offload.mailbox_read = flexcan_mailbox_read;
+ err = flexcan_chip_start(dev);
+ if (err)
+ goto out_can_rx_offload_del;
- if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) {
- priv->offload.mb_first = FLEXCAN_RX_MB_OFF_TIMESTAMP_FIRST;
- priv->offload.mb_last = priv->mb_count - 2;
+ can_rx_offload_enable(&priv->offload);
- priv->rx_mask = GENMASK_ULL(priv->offload.mb_last,
- priv->offload.mb_first);
- err = can_rx_offload_add_timestamp(dev, &priv->offload);
- } else {
- priv->rx_mask = FLEXCAN_IFLAG_RX_FIFO_OVERFLOW |
- FLEXCAN_IFLAG_RX_FIFO_AVAILABLE;
- err = can_rx_offload_add_fifo(dev, &priv->offload,
- FLEXCAN_NAPI_WEIGHT);
- }
+ err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev);
if (err)
- goto out_free_irq;
+ goto out_can_rx_offload_disable;
- /* start chip and queuing */
- err = flexcan_chip_start(dev);
- if (err)
- goto out_offload_del;
+ flexcan_chip_interrupts_enable(dev);
can_led_event(dev, CAN_LED_EVENT_OPEN);
- can_rx_offload_enable(&priv->offload);
netif_start_queue(dev);
return 0;
- out_offload_del:
+ out_can_rx_offload_disable:
+ can_rx_offload_disable(&priv->offload);
+ flexcan_chip_stop(dev);
+ out_can_rx_offload_del:
can_rx_offload_del(&priv->offload);
- out_free_irq:
- free_irq(dev->irq, dev);
out_transceiver_disable:
flexcan_transceiver_disable(priv);
out_close:
struct flexcan_priv *priv = netdev_priv(dev);
netif_stop_queue(dev);
+ flexcan_chip_interrupts_disable(dev);
+ free_irq(dev->irq, dev);
can_rx_offload_disable(&priv->offload);
flexcan_chip_stop_disable_on_error(dev);
can_rx_offload_del(&priv->offload);
- free_irq(dev->irq, dev);
flexcan_transceiver_disable(priv);
-
close_candev(dev);
+
pm_runtime_put(priv->dev);
can_led_event(dev, CAN_LED_EVENT_STOP);
if (err)
return err;
+ flexcan_chip_interrupts_enable(dev);
+
netif_wake_queue(dev);
break;
of_can_transceiver(dev);
devm_can_led_init(dev);
- if (priv->devtype_data->quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE) {
+ if (priv->devtype_data->quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_GPR) {
err = flexcan_setup_stop_mode(pdev);
if (err)
dev_dbg(&pdev->dev, "failed to setup stop-mode\n");
if (err)
return err;
+ flexcan_chip_interrupts_disable(dev);
+
err = pinctrl_pm_select_sleep_state(device);
if (err)
return err;
err = flexcan_chip_start(dev);
if (err)
return err;
+
+ flexcan_chip_interrupts_enable(dev);
}
}
cf->can_id = ((slot[0] & GRCAN_MSG_BID)
>> GRCAN_MSG_BID_BIT);
}
- cf->can_dlc = get_can_dlc((slot[1] & GRCAN_MSG_DLC)
+ cf->len = can_cc_dlc2len((slot[1] & GRCAN_MSG_DLC)
>> GRCAN_MSG_DLC_BIT);
if (rtr) {
cf->can_id |= CAN_RTR_FLAG;
} else {
- for (i = 0; i < cf->can_dlc; i++) {
+ for (i = 0; i < cf->len; i++) {
j = GRCAN_MSG_DATA_SLOT_INDEX(i);
shift = GRCAN_MSG_DATA_SHIFT(i);
cf->data[i] = (u8)(slot[j] >> shift);
/* Update statistics and read pointer */
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_receive_skb(skb);
rd = grcan_ring_add(rd, GRCAN_MSG_SIZE, dma->rx.size);
eff = cf->can_id & CAN_EFF_FLAG;
rtr = cf->can_id & CAN_RTR_FLAG;
id = cf->can_id & (eff ? CAN_EFF_MASK : CAN_SFF_MASK);
- dlc = cf->can_dlc;
+ dlc = cf->len;
if (eff)
tmp = (id << GRCAN_MSG_EID_BIT) & GRCAN_MSG_EID;
else
* can_put_echo_skb would be an error unless other measures are
* taken.
*/
- priv->txdlc[slotindex] = cf->can_dlc; /* Store dlc for statistics */
+ priv->txdlc[slotindex] = cf->len; /* Store dlc for statistics */
can_put_echo_skb(skb, dev, slotindex);
/* Make sure everything is written before allowing hardware to
dlc = (rxdlc >> IFI_CANFD_RXFIFO_DLC_DLC_OFFSET) &
IFI_CANFD_RXFIFO_DLC_DLC_MASK;
if (rxdlc & IFI_CANFD_RXFIFO_DLC_EDL)
- cf->len = can_dlc2len(dlc);
+ cf->len = can_fd_dlc2len(dlc);
else
- cf->len = get_can_dlc(dlc);
+ cf->len = can_cc_dlc2len(dlc);
rxid = readl(priv->base + IFI_CANFD_RXFIFO_ID);
id = (rxid >> IFI_CANFD_RXFIFO_ID_ID_OFFSET);
writel(IFI_CANFD_ERROR_CTR_ER_ENABLE, priv->base + IFI_CANFD_ERROR_CTR);
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_receive_skb(skb);
return 1;
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_receive_skb(skb);
return 1;
txid = cf->can_id & CAN_SFF_MASK;
}
- txdlc = can_len2dlc(cf->len);
+ txdlc = can_fd_len2dlc(cf->len);
if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) && can_is_canfd_skb(skb)) {
txdlc |= IFI_CANFD_TXFIFO_DLC_EDL;
if (cf->flags & CANFD_BRS)
cf->can_id |= desc->data[0] << 3;
cf->can_id |= (desc->data[1] & 0xe0) >> 5;
- cf->can_dlc = get_can_dlc(desc->data[1] & ICAN3_CAN_DLC_MASK);
- memcpy(cf->data, &desc->data[2], cf->can_dlc);
+ cf->len = can_cc_dlc2len(desc->data[1] & ICAN3_CAN_DLC_MASK);
+ memcpy(cf->data, &desc->data[2], cf->len);
} else {
- cf->can_dlc = get_can_dlc(desc->data[0] & ICAN3_CAN_DLC_MASK);
+ cf->len = can_cc_dlc2len(desc->data[0] & ICAN3_CAN_DLC_MASK);
if (desc->data[0] & ICAN3_EFF_RTR)
cf->can_id |= CAN_RTR_FLAG;
cf->can_id |= desc->data[3] >> 5; /* 2-0 */
}
- memcpy(cf->data, &desc->data[6], cf->can_dlc);
+ memcpy(cf->data, &desc->data[6], cf->len);
}
}
/* we always use the extended format, with the ECHO flag set */
desc->command = ICAN3_CAN_TYPE_EFF;
- desc->data[0] |= cf->can_dlc;
+ desc->data[0] |= cf->len;
desc->data[1] |= ICAN3_ECHO;
/* support single transmission (no retries) mode */
}
/* copy the data bits into the descriptor */
- memcpy(&desc->data[6], cf->data, cf->can_dlc);
+ memcpy(&desc->data[6], cf->data, cf->len);
}
/*
}
cf = (struct can_frame *)skb->data;
- dlc = cf->can_dlc;
+ dlc = cf->len;
/* check flag whether this packet has to be looped back */
if (skb->pkt_type != PACKET_LOOPBACK) {
if (cf->can_id != echo_cf->can_id)
return false;
- if (cf->can_dlc != echo_cf->can_dlc)
+ if (cf->len != echo_cf->len)
return false;
- return memcmp(cf->data, echo_cf->data, cf->can_dlc) == 0;
+ return memcmp(cf->data, echo_cf->data, cf->len) == 0;
}
/*
/* update statistics, receive the skb */
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_receive_skb(skb);
err_noalloc:
p->header[0] |= KVASER_PCIEFD_RPACKET_IDE;
p->header[0] |= cf->can_id & CAN_EFF_MASK;
- p->header[1] |= can_len2dlc(cf->len) << KVASER_PCIEFD_RPACKET_DLC_SHIFT;
+ p->header[1] |= can_fd_len2dlc(cf->len) << KVASER_PCIEFD_RPACKET_DLC_SHIFT;
p->header[1] |= KVASER_PCIEFD_TPACKET_AREQ;
if (can_is_canfd_skb(skb)) {
if (p->header[0] & KVASER_PCIEFD_RPACKET_IDE)
cf->can_id |= CAN_EFF_FLAG;
- cf->len = can_dlc2len(p->header[1] >> KVASER_PCIEFD_RPACKET_DLC_SHIFT);
+ cf->len = can_fd_dlc2len(p->header[1] >> KVASER_PCIEFD_RPACKET_DLC_SHIFT);
if (p->header[0] & KVASER_PCIEFD_RPACKET_RTR)
cf->can_id |= CAN_RTR_FLAG;
cf->data[7] = bec.rxerr;
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
return 0;
if (skb) {
cf->can_id |= CAN_ERR_BUSERROR;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
stats->rx_packets++;
netif_rx(skb);
} else {
if (!(p->header[0] & KVASER_PCIEFD_RPACKET_RTR)) {
u8 data_len;
- data_len = can_dlc2len(p->header[1] >>
+ data_len = can_fd_dlc2len(p->header[1] >>
KVASER_PCIEFD_RPACKET_DLC_SHIFT);
pos += DIV_ROUND_UP(data_len, 4);
}
# SPDX-License-Identifier: GPL-2.0-only
-config CAN_M_CAN
+menuconfig CAN_M_CAN
tristate "Bosch M_CAN support"
help
Say Y here if you want support for Bosch M_CAN controller framework.
This is common support for devices that embed the Bosch M_CAN IP.
+if CAN_M_CAN
+
config CAN_M_CAN_PLATFORM
tristate "Bosch M_CAN support for io-mapped devices"
depends on HAS_IOMEM
- depends on CAN_M_CAN
help
Say Y here if you want support for IO Mapped Bosch M_CAN controller.
This support is for devices that have the Bosch M_CAN controller
IP embedded into the device and the IP is IO Mapped to the processor.
config CAN_M_CAN_TCAN4X5X
- depends on CAN_M_CAN
depends on SPI
select REGMAP_SPI
tristate "TCAN4X5X M_CAN device"
Say Y here if you want support for Texas Instruments TCAN4x5x
M_CAN controller. This device is a peripheral device that uses the
SPI bus for communication.
+
+endif
}
if (dlc & RX_BUF_FDF)
- cf->len = can_dlc2len((dlc >> 16) & 0x0F);
+ cf->len = can_fd_dlc2len((dlc >> 16) & 0x0F);
else
- cf->len = get_can_dlc((dlc >> 16) & 0x0F);
+ cf->len = can_cc_dlc2len((dlc >> 16) & 0x0F);
id = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_ID);
if (id & RX_BUF_XTD)
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_receive_skb(skb);
return 1;
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_receive_skb(skb);
return 1;
/* message ram configuration */
m_can_fifo_write(cdev, 0, M_CAN_FIFO_ID, id);
m_can_fifo_write(cdev, 0, M_CAN_FIFO_DLC,
- can_len2dlc(cf->len) << 16);
+ can_fd_len2dlc(cf->len) << 16);
for (i = 0; i < cf->len; i += 4)
m_can_fifo_write(cdev, 0,
m_can_fifo_write(cdev, putidx, M_CAN_FIFO_DLC,
((putidx << TX_BUF_MM_SHIFT) &
TX_BUF_MM_MASK) |
- (can_len2dlc(cf->len) << 16) |
+ (can_fd_len2dlc(cf->len) << 16) |
fdflags | TX_BUF_EFC);
for (i = 0; i < cf->len; i += 4)
}
EXPORT_SYMBOL_GPL(m_can_class_register);
+void m_can_class_unregister(struct m_can_classdev *m_can_dev)
+{
+ unregister_candev(m_can_dev->net);
+
+ m_can_clk_stop(m_can_dev);
+}
+EXPORT_SYMBOL_GPL(m_can_class_unregister);
+
int m_can_class_suspend(struct device *dev)
{
struct net_device *ndev = dev_get_drvdata(dev);
}
EXPORT_SYMBOL_GPL(m_can_class_resume);
-void m_can_class_unregister(struct m_can_classdev *m_can_dev)
-{
- unregister_candev(m_can_dev->net);
-
- m_can_clk_stop(m_can_dev);
-}
-EXPORT_SYMBOL_GPL(m_can_class_unregister);
-
MODULE_AUTHOR("Dong Aisheng <b29396@freescale.com>");
MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com>");
MODULE_LICENSE("GPL v2");
void *device_data;
int version;
- int freq;
u32 irqstatus;
int pm_clock_support;
m_can_class_free_dev(mcan_class->net);
- platform_set_drvdata(pdev, NULL);
-
return 0;
}
struct gpio_desc *device_wake_gpio;
struct gpio_desc *device_state_gpio;
struct regulator *power;
-
- /* Register based ip */
- int mram_start;
- int reg_offset;
};
static struct can_bittiming_const tcan4x5x_bittiming_const = {
struct tcan4x5x_priv *priv = cdev->device_data;
u32 val;
- regmap_read(priv->regmap, priv->reg_offset + reg, &val);
+ regmap_read(priv->regmap, TCAN4X5X_MCAN_OFFSET + reg, &val);
return val;
}
struct tcan4x5x_priv *priv = cdev->device_data;
u32 val;
- regmap_read(priv->regmap, priv->mram_start + addr_offset, &val);
+ regmap_read(priv->regmap, TCAN4X5X_MRAM_START + addr_offset, &val);
return val;
}
{
struct tcan4x5x_priv *priv = cdev->device_data;
- return regmap_write(priv->regmap, priv->reg_offset + reg, val);
+ return regmap_write(priv->regmap, TCAN4X5X_MCAN_OFFSET + reg, val);
}
static int tcan4x5x_write_fifo(struct m_can_classdev *cdev,
{
struct tcan4x5x_priv *priv = cdev->device_data;
- return regmap_write(priv->regmap, priv->mram_start + addr_offset, val);
+ return regmap_write(priv->regmap, TCAN4X5X_MRAM_START + addr_offset, val);
}
static int tcan4x5x_power_enable(struct regulator *reg, int enable)
if (ret)
return ret;
- ret = tcan4x5x_write_tcan_reg(cdev, TCAN4X5X_ERROR_STATUS,
- TCAN4X5X_CLEAR_ALL_INT);
- if (ret)
- return ret;
-
- return ret;
+ return tcan4x5x_write_tcan_reg(cdev, TCAN4X5X_ERROR_STATUS,
+ TCAN4X5X_CLEAR_ALL_INT);
}
static int tcan4x5x_init(struct m_can_classdev *cdev)
TCAN4X5X_DISABLE_INH_MSK, 0x01);
}
-static int tcan4x5x_parse_config(struct m_can_classdev *cdev)
+static int tcan4x5x_get_gpios(struct m_can_classdev *cdev)
{
struct tcan4x5x_priv *tcan4x5x = cdev->device_data;
int ret;
goto out_m_can_class_free_dev;
}
- priv->reg_offset = TCAN4X5X_MCAN_OFFSET;
- priv->mram_start = TCAN4X5X_MRAM_START;
priv->spi = spi;
priv->mcan_dev = mcan_class;
if (ret)
goto out_m_can_class_free_dev;
- ret = tcan4x5x_parse_config(mcan_class);
+ ret = tcan4x5x_get_gpios(mcan_class);
if (ret)
goto out_power;
tcan4x5x_power_enable(priv->power, 0);
out_m_can_class_free_dev:
m_can_class_free_dev(mcan_class->net);
- dev_err(&spi->dev, "Probe failed, err=%d\n", ret);
-
return ret;
}
void __iomem *data = ®s->tx.dsr1_0;
u16 *payload = (u16 *)frame->data;
- for (i = 0; i < frame->can_dlc / 2; i++) {
+ for (i = 0; i < frame->len / 2; i++) {
out_be16(data, *payload++);
data += 2 + _MSCAN_RESERVED_DSR_SIZE;
}
/* write remaining byte if necessary */
- if (frame->can_dlc & 1)
- out_8(data, frame->data[frame->can_dlc - 1]);
+ if (frame->len & 1)
+ out_8(data, frame->data[frame->len - 1]);
}
- out_8(®s->tx.dlr, frame->can_dlc);
+ out_8(®s->tx.dlr, frame->len);
out_8(®s->tx.tbpr, priv->cur_pri);
/* Start transmission. */
if (can_id & 1)
frame->can_id |= CAN_RTR_FLAG;
- frame->can_dlc = get_can_dlc(in_8(®s->rx.dlr) & 0xf);
+ frame->len = can_cc_dlc2len(in_8(®s->rx.dlr) & 0xf);
if (!(frame->can_id & CAN_RTR_FLAG)) {
void __iomem *data = ®s->rx.dsr1_0;
u16 *payload = (u16 *)frame->data;
- for (i = 0; i < frame->can_dlc / 2; i++) {
+ for (i = 0; i < frame->len / 2; i++) {
*payload++ = in_be16(data);
data += 2 + _MSCAN_RESERVED_DSR_SIZE;
}
/* read remaining byte if necessary */
- if (frame->can_dlc & 1)
- frame->data[frame->can_dlc - 1] = in_8(data);
+ if (frame->len & 1)
+ frame->data[frame->len - 1] = in_8(data);
}
out_8(®s->canrflg, MSCAN_RXF);
}
}
priv->shadow_statflg = canrflg & MSCAN_STAT_MSK;
- frame->can_dlc = CAN_ERR_DLC;
+ frame->len = CAN_ERR_DLC;
out_8(®s->canrflg, MSCAN_ERR_IF);
}
mscan_get_err_frame(dev, frame, canrflg);
stats->rx_packets++;
- stats->rx_bytes += frame->can_dlc;
+ stats->rx_bytes += frame->len;
work_done++;
netif_receive_skb(skb);
}
netif_receive_skb(skb);
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
}
static irqreturn_t pch_can_interrupt(int irq, void *dev_id)
if (id2 & PCH_ID2_DIR)
cf->can_id |= CAN_RTR_FLAG;
- cf->can_dlc = get_can_dlc((ioread32(&priv->regs->
+ cf->len = can_cc_dlc2len((ioread32(&priv->regs->
ifregs[0].mcont)) & 0xF);
- for (i = 0; i < cf->can_dlc; i += 2) {
+ for (i = 0; i < cf->len; i += 2) {
data_reg = ioread16(&priv->regs->ifregs[0].data[i / 2]);
cf->data[i] = data_reg;
cf->data[i + 1] = data_reg >> 8;
rcv_pkts++;
stats->rx_packets++;
quota--;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
pch_fifo_thresh(priv, obj_num);
obj_num++;
iowrite32(PCH_CMASK_RX_TX_GET | PCH_CMASK_CLRINTPND,
&priv->regs->ifregs[1].cmask);
pch_can_rw_msg_obj(&priv->regs->ifregs[1].creq, int_stat);
- dlc = get_can_dlc(ioread32(&priv->regs->ifregs[1].mcont) &
+ dlc = can_cc_dlc2len(ioread32(&priv->regs->ifregs[1].mcont) &
PCH_IF_MCONT_DLC);
stats->tx_bytes += dlc;
stats->tx_packets++;
iowrite32(id2, &priv->regs->ifregs[1].id2);
/* Copy data to register */
- for (i = 0; i < cf->can_dlc; i += 2) {
+ for (i = 0; i < cf->len; i += 2) {
iowrite16(cf->data[i] | (cf->data[i + 1] << 8),
&priv->regs->ifregs[1].data[i / 2]);
}
can_put_echo_skb(skb, ndev, tx_obj_no - PCH_RX_OBJ_END - 1);
/* Set the size of the data. Update if2_mcont */
- iowrite32(cf->can_dlc | PCH_IF_MCONT_NEWDAT | PCH_IF_MCONT_TXRQXT |
+ iowrite32(cf->len | PCH_IF_MCONT_NEWDAT | PCH_IF_MCONT_TXRQXT |
PCH_IF_MCONT_TXIE, &priv->regs->ifregs[1].mcont);
pch_can_rw_msg_obj(&priv->regs->ifregs[1].creq, tx_obj_no);
u8 cf_len;
if (rx_msg_flags & PUCAN_MSG_EXT_DATA_LEN)
- cf_len = can_dlc2len(get_canfd_dlc(pucan_msg_get_dlc(msg)));
+ cf_len = can_fd_dlc2len(pucan_msg_get_dlc(msg));
else
- cf_len = get_can_dlc(pucan_msg_get_dlc(msg));
+ cf_len = can_cc_dlc2len(pucan_msg_get_dlc(msg));
/* if this frame is an echo, */
if (rx_msg_flags & PUCAN_MSG_LOOPED_BACK) {
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
pucan_netif_rx(skb, msg->ts_low, msg->ts_high);
return 0;
cf->data[6] = priv->bec.txerr;
cf->data[7] = priv->bec.rxerr;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
stats->rx_packets++;
netif_rx(skb);
unsigned long flags;
bool should_stop_tx_queue;
int room_left;
- u8 can_dlc;
+ u8 len;
if (can_dropped_invalid_skb(ndev, skb))
return NETDEV_TX_OK;
if (can_is_canfd_skb(skb)) {
/* CAN FD frame format */
- can_dlc = can_len2dlc(cf->len);
+ len = can_fd_len2dlc(cf->len);
msg_flags |= PUCAN_MSG_EXT_DATA_LEN;
msg_flags |= PUCAN_MSG_ERROR_STATE_IND;
} else {
/* CAN 2.0 frame format */
- can_dlc = cf->len;
+ len = cf->len;
if (cf->can_id & CAN_RTR_FLAG)
msg_flags |= PUCAN_MSG_RTR;
msg_flags |= PUCAN_MSG_SELF_RECEIVE;
msg->flags = cpu_to_le16(msg_flags);
- msg->channel_dlc = PUCAN_MSG_CHANNEL_DLC(priv->index, can_dlc);
+ msg->channel_dlc = PUCAN_MSG_CHANNEL_DLC(priv->index, len);
memcpy(msg->d, cf->data, cf->len);
/* struct msg client field is used as an index in the echo skbs ring */
if (skb) {
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
}
if (cf->can_id & CAN_RTR_FLAG) { /* Remote transmission request */
data |= RCAR_CAN_RTR;
} else {
- for (i = 0; i < cf->can_dlc; i++)
+ for (i = 0; i < cf->len; i++)
writeb(cf->data[i],
&priv->regs->mb[RCAR_CAN_TX_FIFO_MBX].data[i]);
}
writel(data, &priv->regs->mb[RCAR_CAN_TX_FIFO_MBX].id);
- writeb(cf->can_dlc, &priv->regs->mb[RCAR_CAN_TX_FIFO_MBX].dlc);
+ writeb(cf->len, &priv->regs->mb[RCAR_CAN_TX_FIFO_MBX].dlc);
- priv->tx_dlc[priv->tx_head % RCAR_CAN_FIFO_DEPTH] = cf->can_dlc;
+ priv->tx_dlc[priv->tx_head % RCAR_CAN_FIFO_DEPTH] = cf->len;
can_put_echo_skb(skb, ndev, priv->tx_head % RCAR_CAN_FIFO_DEPTH);
priv->tx_head++;
/* Start Tx: write 0xff to the TFPCR register to increment
cf->can_id = (data >> RCAR_CAN_SID_SHIFT) & CAN_SFF_MASK;
dlc = readb(&priv->regs->mb[RCAR_CAN_RX_FIFO_MBX].dlc);
- cf->can_dlc = get_can_dlc(dlc);
+ cf->len = can_cc_dlc2len(dlc);
if (data & RCAR_CAN_RTR) {
cf->can_id |= CAN_RTR_FLAG;
} else {
- for (dlc = 0; dlc < cf->can_dlc; dlc++)
+ for (dlc = 0; dlc < cf->len; dlc++)
cf->data[dlc] =
readb(&priv->regs->mb[RCAR_CAN_RX_FIFO_MBX].data[dlc]);
}
can_led_event(priv->ndev, CAN_LED_EVENT_RX);
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
stats->rx_packets++;
netif_receive_skb(skb);
}
rcar_canfd_write(priv->base, RCANFD_CERFL(ch),
RCANFD_CERFL_ERR(~cerfl));
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
can_change_state(ndev, cf, tx_state, rx_state);
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
}
if (cf->can_id & CAN_RTR_FLAG)
id |= RCANFD_CFID_CFRTR;
- dlc = RCANFD_CFPTR_CFDLC(can_len2dlc(cf->len));
+ dlc = RCANFD_CFPTR_CFDLC(can_fd_len2dlc(cf->len));
if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
rcar_canfd_write(priv->base,
if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
if (sts & RCANFD_RFFDSTS_RFFDF)
- cf->len = can_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
+ cf->len = can_fd_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
else
- cf->len = get_can_dlc(RCANFD_RFPTR_RFDLC(dlc));
+ cf->len = can_cc_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
if (sts & RCANFD_RFFDSTS_RFESI) {
cf->flags |= CANFD_ESI;
rcar_canfd_get_data(priv, cf, RCANFD_F_RFDF(ridx, 0));
}
} else {
- cf->len = get_can_dlc(RCANFD_RFPTR_RFDLC(dlc));
+ cf->len = can_cc_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
if (id & RCANFD_RFID_RFRTR)
cf->can_id |= CAN_RTR_FLAG;
else
work_done++;
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_receive_skb(skb);
}
struct sja1000_priv *priv = netdev_priv(dev);
struct can_frame *cf = (struct can_frame *)skb->data;
uint8_t fi;
- uint8_t dlc;
canid_t id;
uint8_t dreg;
u8 cmd_reg_val = 0x00;
netif_stop_queue(dev);
- fi = dlc = cf->can_dlc;
+ fi = can_get_cc_dlc(cf, priv->can.ctrlmode);
id = cf->can_id;
if (id & CAN_RTR_FLAG)
priv->write_reg(priv, SJA1000_ID2, (id & 0x00000007) << 5);
}
- for (i = 0; i < dlc; i++)
+ for (i = 0; i < cf->len; i++)
priv->write_reg(priv, dreg++, cf->data[i]);
can_put_echo_skb(skb, dev, 0);
| (priv->read_reg(priv, SJA1000_ID2) >> 5);
}
- cf->can_dlc = get_can_dlc(fi & 0x0F);
+ can_frame_set_cc_len(cf, fi & 0x0F, priv->can.ctrlmode);
if (fi & SJA1000_FI_RTR) {
id |= CAN_RTR_FLAG;
} else {
- for (i = 0; i < cf->can_dlc; i++)
+ for (i = 0; i < cf->len; i++)
cf->data[i] = priv->read_reg(priv, dreg++);
}
sja1000_write_cmdreg(priv, CMD_RRB);
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
can_led_event(dev, CAN_LED_EVENT_RX);
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
return 0;
CAN_CTRLMODE_3_SAMPLES |
CAN_CTRLMODE_ONE_SHOT |
CAN_CTRLMODE_BERR_REPORTING |
- CAN_CTRLMODE_PRESUME_ACK;
+ CAN_CTRLMODE_PRESUME_ACK |
+ CAN_CTRLMODE_CC_LEN8_DLC;
spin_lock_init(&priv->cmdreg_lock);
/*
* A CAN frame has a can_id (11 bit standard frame format OR 29 bit extended
- * frame format) a data length code (can_dlc) which can be from 0 to 8
- * and up to <can_dlc> data bytes as payload.
+ * frame format) a data length code (len) which can be from 0 to 8
+ * and up to <len> data bytes as payload.
* Additionally a CAN frame may become a remote transmission frame if the
* RTR-bit is set. This causes another ECU to send a CAN frame with the
* given can_id.
*
* Examples:
*
- * t1230 : can_id 0x123, can_dlc 0, no data
- * t4563112233 : can_id 0x456, can_dlc 3, data 0x11 0x22 0x33
- * T12ABCDEF2AA55 : extended can_id 0x12ABCDEF, can_dlc 2, data 0xAA 0x55
- * r1230 : can_id 0x123, can_dlc 0, no data, remote transmission request
+ * t1230 : can_id 0x123, len 0, no data
+ * t4563112233 : can_id 0x456, len 3, data 0x11 0x22 0x33
+ * T12ABCDEF2AA55 : extended can_id 0x12ABCDEF, len 2, data 0xAA 0x55
+ * r1230 : can_id 0x123, len 0, no data, remote transmission request
*
*/
fallthrough;
case 't':
/* store dlc ASCII value and terminate SFF CAN ID string */
- cf.can_dlc = sl->rbuff[SLC_CMD_LEN + SLC_SFF_ID_LEN];
+ cf.len = sl->rbuff[SLC_CMD_LEN + SLC_SFF_ID_LEN];
sl->rbuff[SLC_CMD_LEN + SLC_SFF_ID_LEN] = 0;
/* point to payload data behind the dlc */
cmd += SLC_CMD_LEN + SLC_SFF_ID_LEN + 1;
case 'T':
cf.can_id |= CAN_EFF_FLAG;
/* store dlc ASCII value and terminate EFF CAN ID string */
- cf.can_dlc = sl->rbuff[SLC_CMD_LEN + SLC_EFF_ID_LEN];
+ cf.len = sl->rbuff[SLC_CMD_LEN + SLC_EFF_ID_LEN];
sl->rbuff[SLC_CMD_LEN + SLC_EFF_ID_LEN] = 0;
/* point to payload data behind the dlc */
cmd += SLC_CMD_LEN + SLC_EFF_ID_LEN + 1;
cf.can_id |= tmpid;
- /* get can_dlc from sanitized ASCII value */
- if (cf.can_dlc >= '0' && cf.can_dlc < '9')
- cf.can_dlc -= '0';
+ /* get len from sanitized ASCII value */
+ if (cf.len >= '0' && cf.len < '9')
+ cf.len -= '0';
else
return;
/* RTR frames may have a dlc > 0 but they never have any data bytes */
if (!(cf.can_id & CAN_RTR_FLAG)) {
- for (i = 0; i < cf.can_dlc; i++) {
+ for (i = 0; i < cf.len; i++) {
tmp = hex_to_bin(*cmd++);
if (tmp < 0)
return;
skb_put_data(skb, &cf, sizeof(struct can_frame));
sl->dev->stats.rx_packets++;
- sl->dev->stats.rx_bytes += cf.can_dlc;
+ sl->dev->stats.rx_bytes += cf.len;
netif_rx_ni(skb);
}
pos += (cf->can_id & CAN_EFF_FLAG) ? SLC_EFF_ID_LEN : SLC_SFF_ID_LEN;
- *pos++ = cf->can_dlc + '0';
+ *pos++ = cf->len + '0';
/* RTR frames may have a dlc > 0 but they never have any data bytes */
if (!(cf->can_id & CAN_RTR_FLAG)) {
- for (i = 0; i < cf->can_dlc; i++)
+ for (i = 0; i < cf->len; i++)
pos = hex_byte_pack_upper(pos, cf->data[i]);
}
actual = sl->tty->ops->write(sl->tty, sl->xbuff, pos - sl->xbuff);
sl->xleft = (pos - sl->xbuff) - actual;
sl->xhead = sl->xbuff + actual;
- sl->dev->stats.tx_bytes += cf->can_dlc;
+ sl->dev->stats.tx_bytes += cf->len;
}
/* Write out any remaining transmit buffer. Scheduled when tty is writable */
*/
memset(&msg, 0, sizeof(msg));
msg.can_id = CAN_ERR_FLAG | CAN_ERR_RESTARTED;
- msg.can_dlc = CAN_ERR_DLC;
+ msg.len = CAN_ERR_DLC;
for (j = 0; j < ARRAY_SIZE(card->net); ++j) {
if (!(bus_bitmask_start & (1 << j)))
continue;
if (priv->index)
*ptr |= CMD_BUS2;
++ptr;
- *ptr++ = cf->can_dlc;
+ *ptr++ = cf->len;
*ptr++ = (cf->can_id >> 0);
*ptr++ = (cf->can_id >> 8);
if (cf->can_id & CAN_EFF_FLAG) {
ptr += 1;
}
if (!(cf->can_id & CAN_RTR_FLAG))
- memcpy(ptr, &cf->data[0], cf->can_dlc);
+ memcpy(ptr, &cf->data[0], cf->len);
memcpy_toio(&card->dpram[DPRAM_TX + DPRAM_TX_SIZE * fifo_wr],
buf, DPRAM_TX_SIZE);
if (++fifo_wr >= DPRAM_TX_CNT)
iowrite8(0, &card->dpram[DPRAM_RX_LOST]);
/* prepare msg */
msg.can_id = CAN_ERR_FLAG | CAN_ERR_CRTL;
- msg.can_dlc = CAN_ERR_DLC;
+ msg.len = CAN_ERR_DLC;
msg.data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
/*
* service to all buses, we don't know which it was applicable
state = *ptr++;
msg.can_id = CAN_ERR_FLAG;
- msg.can_dlc = CAN_ERR_DLC;
+ msg.len = CAN_ERR_DLC;
if (state & SF_MASK_BUSOFF) {
can_state = CAN_STATE_BUS_OFF;
} else {
if (cmd & CMD_RTR)
msg.can_id |= CAN_RTR_FLAG;
- msg.can_dlc = get_can_dlc(*ptr++);
+ msg.len = can_cc_dlc2len(*ptr++);
if (cmd & CMD_XTD) {
msg.can_id |= CAN_EFF_FLAG;
msg.can_id |= le32_to_cpup((void *)ptr);
--card->tx.pending;
++netdev->stats.tx_packets;
if (!(msg.can_id & CAN_RTR_FLAG))
- netdev->stats.tx_bytes += msg.can_dlc;
+ netdev->stats.tx_bytes += msg.len;
} else {
int ret;
if (ret == NET_RX_SUCCESS) {
++netdev->stats.rx_packets;
if (!(msg.can_id & CAN_RTR_FLAG))
- netdev->stats.rx_bytes += msg.can_dlc;
+ netdev->stats.rx_bytes += msg.len;
} else {
++netdev->stats.rx_dropped;
}
((frame->can_id & CAN_EFF_MASK) << 1) |
((frame->can_id & CAN_RTR_FLAG) ? 1 : 0);
- buf[HI3110_FIFO_EXT_DLC_OFF] = frame->can_dlc;
+ buf[HI3110_FIFO_EXT_DLC_OFF] = frame->len;
memcpy(buf + HI3110_FIFO_EXT_DATA_OFF,
- frame->data, frame->can_dlc);
+ frame->data, frame->len);
hi3110_hw_tx_frame(spi, buf, HI3110_TX_EXT_BUF_LEN -
- (HI3110_CAN_MAX_DATA_LEN - frame->can_dlc));
+ (HI3110_CAN_MAX_DATA_LEN - frame->len));
} else {
/* Standard frame */
buf[HI3110_FIFO_ID_OFF] = (frame->can_id & CAN_SFF_MASK) >> 3;
((frame->can_id & CAN_SFF_MASK) << 5) |
((frame->can_id & CAN_RTR_FLAG) ? (1 << 4) : 0);
- buf[HI3110_FIFO_STD_DLC_OFF] = frame->can_dlc;
+ buf[HI3110_FIFO_STD_DLC_OFF] = frame->len;
memcpy(buf + HI3110_FIFO_STD_DATA_OFF,
- frame->data, frame->can_dlc);
+ frame->data, frame->len);
hi3110_hw_tx_frame(spi, buf, HI3110_TX_STD_BUF_LEN -
- (HI3110_CAN_MAX_DATA_LEN - frame->can_dlc));
+ (HI3110_CAN_MAX_DATA_LEN - frame->len));
}
}
}
/* Data length */
- frame->can_dlc = get_can_dlc(buf[HI3110_FIFO_WOTIME_DLC_OFF] & 0x0F);
+ frame->len = can_cc_dlc2len(buf[HI3110_FIFO_WOTIME_DLC_OFF] & 0x0F);
if (buf[HI3110_FIFO_WOTIME_ID_OFF + 3] & HI3110_FIFO_WOTIME_ID_RTR)
frame->can_id |= CAN_RTR_FLAG;
else
memcpy(frame->data, buf + HI3110_FIFO_WOTIME_DAT_OFF,
- frame->can_dlc);
+ frame->len);
priv->net->stats.rx_packets++;
- priv->net->stats.rx_bytes += frame->can_dlc;
+ priv->net->stats.rx_bytes += frame->len;
can_led_event(priv->net, CAN_LED_EVENT_RX);
} else {
frame = (struct can_frame *)priv->tx_skb->data;
hi3110_hw_tx(spi, frame);
- priv->tx_len = 1 + frame->can_dlc;
+ priv->tx_len = 1 + frame->len;
can_put_echo_skb(priv->tx_skb, net, 0);
priv->tx_skb = NULL;
}
((eid >> SIDL_EID_SHIFT) & SIDL_EID_MASK);
buf[TXBEID8_OFF] = GET_BYTE(eid, 1);
buf[TXBEID0_OFF] = GET_BYTE(eid, 0);
- buf[TXBDLC_OFF] = (rtr << DLC_RTR_SHIFT) | frame->can_dlc;
- memcpy(buf + TXBDAT_OFF, frame->data, frame->can_dlc);
- mcp251x_hw_tx_frame(spi, buf, frame->can_dlc, tx_buf_idx);
+ buf[TXBDLC_OFF] = (rtr << DLC_RTR_SHIFT) | frame->len;
+ memcpy(buf + TXBDAT_OFF, frame->data, frame->len);
+ mcp251x_hw_tx_frame(spi, buf, frame->len, tx_buf_idx);
/* use INSTRUCTION_RTS, to avoid "repeated frame problem" */
priv->spi_tx_buf[0] = INSTRUCTION_RTS(1 << tx_buf_idx);
for (i = 1; i < RXBDAT_OFF; i++)
buf[i] = mcp251x_read_reg(spi, RXBCTRL(buf_idx) + i);
- len = get_can_dlc(buf[RXBDLC_OFF] & RXBDLC_LEN_MASK);
+ len = can_cc_dlc2len(buf[RXBDLC_OFF] & RXBDLC_LEN_MASK);
for (; i < (RXBDAT_OFF + len); i++)
buf[i] = mcp251x_read_reg(spi, RXBCTRL(buf_idx) + i);
} else {
frame->can_id |= CAN_RTR_FLAG;
}
/* Data length */
- frame->can_dlc = get_can_dlc(buf[RXBDLC_OFF] & RXBDLC_LEN_MASK);
- memcpy(frame->data, buf + RXBDAT_OFF, frame->can_dlc);
+ frame->len = can_cc_dlc2len(buf[RXBDLC_OFF] & RXBDLC_LEN_MASK);
+ memcpy(frame->data, buf + RXBDAT_OFF, frame->len);
priv->net->stats.rx_packets++;
- priv->net->stats.rx_bytes += frame->can_dlc;
+ priv->net->stats.rx_bytes += frame->len;
can_led_event(priv->net, CAN_LED_EVENT_RX);
} else {
frame = (struct can_frame *)priv->tx_skb->data;
- if (frame->can_dlc > CAN_FRAME_MAX_DATA_LEN)
- frame->can_dlc = CAN_FRAME_MAX_DATA_LEN;
+ if (frame->len > CAN_FRAME_MAX_DATA_LEN)
+ frame->len = CAN_FRAME_MAX_DATA_LEN;
mcp251x_hw_tx(spi, frame, 0);
- priv->tx_len = 1 + frame->can_dlc;
+ priv->tx_len = 1 + frame->len;
can_put_echo_skb(priv->tx_skb, net, 0);
priv->tx_skb = NULL;
}
static void mcp251xfd_ring_init(struct mcp251xfd_priv *priv)
{
+ struct mcp251xfd_tef_ring *tef_ring;
struct mcp251xfd_tx_ring *tx_ring;
struct mcp251xfd_rx_ring *rx_ring, *prev_rx_ring = NULL;
struct mcp251xfd_tx_obj *tx_obj;
u32 val;
u16 addr;
u8 len;
- int i;
+ int i, j;
/* TEF */
- priv->tef.head = 0;
- priv->tef.tail = 0;
+ tef_ring = priv->tef;
+ tef_ring->head = 0;
+ tef_ring->tail = 0;
+
+ /* FIFO increment TEF tail pointer */
+ addr = MCP251XFD_REG_TEFCON;
+ val = MCP251XFD_REG_TEFCON_UINC;
+ len = mcp251xfd_cmd_prepare_write_reg(priv, &tef_ring->uinc_buf,
+ addr, val, val);
+
+ for (j = 0; j < ARRAY_SIZE(tef_ring->uinc_xfer); j++) {
+ struct spi_transfer *xfer;
+
+ xfer = &tef_ring->uinc_xfer[j];
+ xfer->tx_buf = &tef_ring->uinc_buf;
+ xfer->len = len;
+ xfer->cs_change = 1;
+ xfer->cs_change_delay.value = 0;
+ xfer->cs_change_delay.unit = SPI_DELAY_UNIT_NSECS;
+ }
/* TX */
tx_ring = priv->tx;
prev_rx_ring->obj_num;
prev_rx_ring = rx_ring;
+
+ /* FIFO increment RX tail pointer */
+ addr = MCP251XFD_REG_FIFOCON(rx_ring->fifo_nr);
+ val = MCP251XFD_REG_FIFOCON_UINC;
+ len = mcp251xfd_cmd_prepare_write_reg(priv, &rx_ring->uinc_buf,
+ addr, val, val);
+
+ for (j = 0; j < ARRAY_SIZE(rx_ring->uinc_xfer); j++) {
+ struct spi_transfer *xfer;
+
+ xfer = &rx_ring->uinc_xfer[j];
+ xfer->tx_buf = &rx_ring->uinc_buf;
+ xfer->len = len;
+ xfer->cs_change = 1;
+ xfer->cs_change_delay.value = 0;
+ xfer->cs_change_delay.unit = SPI_DELAY_UNIT_NSECS;
+ }
}
}
int rx_obj_num;
rx_obj_num = ram_free / rx_obj_size;
- rx_obj_num = min(1 << (fls(rx_obj_num) - 1), 32);
+ rx_obj_num = min(1 << (fls(rx_obj_num) - 1),
+ MCP251XFD_RX_OBJ_NUM_MAX);
rx_ring = kzalloc(sizeof(*rx_ring) + rx_obj_size * rx_obj_num,
GFP_KERNEL);
return 0;
}
- if (err)
- return err;
-
- return -ETIMEDOUT;
+ return err;
}
static int mcp251xfd_chip_clock_init(const struct mcp251xfd_priv *priv)
tef_sta & MCP251XFD_REG_TEFSTA_TEFFIF ?
"full" : tef_sta & MCP251XFD_REG_TEFSTA_TEFNEIF ?
"not empty" : "empty",
- seq, priv->tef.tail, priv->tef.head, tx_ring->head);
+ seq, priv->tef->tail, priv->tef->head, tx_ring->head);
/* The Sequence Number in the TEF doesn't match our tef_tail. */
return -EAGAIN;
mcp251xfd_handle_tefif_one(struct mcp251xfd_priv *priv,
const struct mcp251xfd_hw_tef_obj *hw_tef_obj)
{
- struct mcp251xfd_tx_ring *tx_ring = priv->tx;
struct net_device_stats *stats = &priv->ndev->stats;
u32 seq, seq_masked, tef_tail_masked;
- int err;
seq = FIELD_GET(MCP251XFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK,
hw_tef_obj->flags);
*/
seq_masked = seq &
field_mask(MCP251XFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK);
- tef_tail_masked = priv->tef.tail &
+ tef_tail_masked = priv->tef->tail &
field_mask(MCP251XFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK);
if (seq_masked != tef_tail_masked)
return mcp251xfd_handle_tefif_recover(priv, seq);
mcp251xfd_get_tef_tail(priv),
hw_tef_obj->ts);
stats->tx_packets++;
+ priv->tef->tail++;
- /* finally increment the TEF pointer */
- err = regmap_update_bits(priv->map_reg, MCP251XFD_REG_TEFCON,
- GENMASK(15, 8),
- MCP251XFD_REG_TEFCON_UINC);
- if (err)
- return err;
-
- priv->tef.tail++;
- tx_ring->tail++;
-
- return mcp251xfd_check_tef_tail(priv);
+ return 0;
}
static int mcp251xfd_tef_ring_update(struct mcp251xfd_priv *priv)
/* chip_tx_tail, is the next TX-Object send by the HW.
* The new TEF head must be >= the old head, ...
*/
- new_head = round_down(priv->tef.head, tx_ring->obj_num) + chip_tx_tail;
- if (new_head <= priv->tef.head)
+ new_head = round_down(priv->tef->head, tx_ring->obj_num) + chip_tx_tail;
+ if (new_head <= priv->tef->head)
new_head += tx_ring->obj_num;
/* ... but it cannot exceed the TX head. */
- priv->tef.head = min(new_head, tx_ring->head);
+ priv->tef->head = min(new_head, tx_ring->head);
return mcp251xfd_check_tef_tail(priv);
}
}
out_netif_wake_queue:
+ len = i; /* number of handled goods TEFs */
+ if (len) {
+ struct mcp251xfd_tef_ring *ring = priv->tef;
+ struct mcp251xfd_tx_ring *tx_ring = priv->tx;
+ struct spi_transfer *last_xfer;
+
+ tx_ring->tail += len;
+
+ /* Increment the TEF FIFO tail pointer 'len' times in
+ * a single SPI message.
+ */
+
+ /* Note:
+ *
+ * "cs_change == 1" on the last transfer results in an
+ * active chip select after the complete SPI
+ * message. This causes the controller to interpret
+ * the next register access as data. Temporary set
+ * "cs_change" of the last transfer to "0" to properly
+ * deactivate the chip select at the end of the
+ * message.
+ */
+ last_xfer = &ring->uinc_xfer[len - 1];
+ last_xfer->cs_change = 0;
+ err = spi_sync_transfer(priv->spi, ring->uinc_xfer, len);
+ last_xfer->cs_change = 1;
+ if (err)
+ return err;
+
+ err = mcp251xfd_check_tef_tail(priv);
+ if (err)
+ return err;
+ }
+
mcp251xfd_ecc_tefif_successful(priv);
if (mcp251xfd_get_tx_free(priv->tx)) {
cfd->flags |= CANFD_BRS;
dlc = FIELD_GET(MCP251XFD_OBJ_FLAGS_DLC, hw_rx_obj->flags);
- cfd->len = can_dlc2len(get_canfd_dlc(dlc));
+ cfd->len = can_fd_dlc2len(dlc);
} else {
if (hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_RTR)
cfd->can_id |= CAN_RTR_FLAG;
- cfd->len = get_can_dlc(FIELD_GET(MCP251XFD_OBJ_FLAGS_DLC,
+ cfd->len = can_cc_dlc2len(FIELD_GET(MCP251XFD_OBJ_FLAGS_DLC,
hw_rx_obj->flags));
}
if (err)
stats->rx_fifo_errors++;
- ring->tail++;
-
- /* finally increment the RX pointer */
- return regmap_update_bits(priv->map_reg,
- MCP251XFD_REG_FIFOCON(ring->fifo_nr),
- GENMASK(15, 8),
- MCP251XFD_REG_FIFOCON_UINC);
+ return 0;
}
static inline int
return err;
while ((len = mcp251xfd_get_rx_linear_len(ring))) {
+ struct spi_transfer *last_xfer;
+
rx_tail = mcp251xfd_get_rx_tail(ring);
err = mcp251xfd_rx_obj_read(priv, ring, hw_rx_obj,
if (err)
return err;
}
+
+ /* Increment the RX FIFO tail pointer 'len' times in a
+ * single SPI message.
+ */
+ ring->tail += len;
+
+ /* Note:
+ *
+ * "cs_change == 1" on the last transfer results in an
+ * active chip select after the complete SPI
+ * message. This causes the controller to interpret
+ * the next register access as data. Temporary set
+ * "cs_change" of the last transfer to "0" to properly
+ * deactivate the chip select at the end of the
+ * message.
+ */
+ last_xfer = &ring->uinc_xfer[len - 1];
+ last_xfer->cs_change = 0;
+ err = spi_sync_transfer(priv->spi, ring->uinc_xfer, len);
+ last_xfer->cs_change = 1;
+ if (err)
+ return err;
}
return 0;
* harm, only the lower 7 bits will be transferred into the
* TEF object.
*/
- dlc = can_len2dlc(cfd->len);
+ dlc = can_fd_len2dlc(cfd->len);
flags |= FIELD_PREP(MCP251XFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK, seq) |
FIELD_PREP(MCP251XFD_OBJ_FLAGS_DLC, dlc);
/* Clear data at end of CAN frame */
offset = round_down(cfd->len, sizeof(u32));
- len = round_up(can_dlc2len(dlc), sizeof(u32)) - offset;
+ len = round_up(can_fd_dlc2len(dlc), sizeof(u32)) - offset;
if (MCP251XFD_SANITIZE_CAN && len)
memset(hw_tx_obj->data + offset, 0x0, len);
memcpy(hw_tx_obj->data, cfd->data, cfd->len);
/* Number of bytes to be written into the RAM of the controller */
len = sizeof(hw_tx_obj->id) + sizeof(hw_tx_obj->flags);
if (MCP251XFD_SANITIZE_CAN)
- len += round_up(can_dlc2len(dlc), sizeof(u32));
+ len += round_up(can_fd_dlc2len(dlc), sizeof(u32));
else
len += round_up(cfd->len, sizeof(u32));
* FIFO setup: tef: 8*12 bytes = 96 bytes, tx: 8*16 bytes = 128 bytes
* FIFO setup: tef: 4*12 bytes = 48 bytes, tx: 4*72 bytes = 288 bytes
*/
+#define MCP251XFD_RX_OBJ_NUM_MAX 32
#define MCP251XFD_TX_OBJ_NUM_CAN 8
#define MCP251XFD_TX_OBJ_NUM_CANFD 4
u8 data[sizeof_field(struct canfd_frame, data)];
};
-struct mcp251xfd_tef_ring {
- unsigned int head;
- unsigned int tail;
-
- /* u8 obj_num equals tx_ring->obj_num */
- /* u8 obj_size equals sizeof(struct mcp251xfd_hw_tef_obj) */
-};
-
struct __packed mcp251xfd_buf_cmd {
__be16 cmd;
};
union mcp251xfd_tx_obj_load_buf buf;
};
+struct mcp251xfd_tef_ring {
+ unsigned int head;
+ unsigned int tail;
+
+ /* u8 obj_num equals tx_ring->obj_num */
+ /* u8 obj_size equals sizeof(struct mcp251xfd_hw_tef_obj) */
+
+ union mcp251xfd_write_reg_buf uinc_buf;
+ struct spi_transfer uinc_xfer[MCP251XFD_TX_OBJ_NUM_MAX];
+};
+
struct mcp251xfd_tx_ring {
unsigned int head;
unsigned int tail;
u8 obj_num;
u8 obj_size;
+ union mcp251xfd_write_reg_buf uinc_buf;
+ struct spi_transfer uinc_xfer[MCP251XFD_RX_OBJ_NUM_MAX];
struct mcp251xfd_hw_rx_obj_canfd obj[];
};
struct spi_device *spi;
u32 spi_max_speed_hz_orig;
- struct mcp251xfd_tef_ring tef;
+ struct mcp251xfd_tef_ring tef[1];
struct mcp251xfd_tx_ring tx[1];
struct mcp251xfd_rx_ring *rx[1];
static inline u8 mcp251xfd_get_tef_head(const struct mcp251xfd_priv *priv)
{
- return priv->tef.head & (priv->tx->obj_num - 1);
+ return priv->tef->head & (priv->tx->obj_num - 1);
}
static inline u8 mcp251xfd_get_tef_tail(const struct mcp251xfd_priv *priv)
{
- return priv->tef.tail & (priv->tx->obj_num - 1);
+ return priv->tef->tail & (priv->tx->obj_num - 1);
}
static inline u8 mcp251xfd_get_tef_len(const struct mcp251xfd_priv *priv)
{
- return priv->tef.head - priv->tef.tail;
+ return priv->tef->head - priv->tef->tail;
}
static inline u8 mcp251xfd_get_tef_linear_len(const struct mcp251xfd_priv *priv)
netif_stop_queue(dev);
id = cf->can_id;
- dlc = cf->can_dlc;
+ dlc = cf->len;
msg_flag_n = dlc;
if (id & CAN_RTR_FLAG)
return;
fi = readl(priv->base + SUN4I_REG_BUF0_ADDR);
- cf->can_dlc = get_can_dlc(fi & 0x0F);
+ cf->len = can_cc_dlc2len(fi & 0x0F);
if (fi & SUN4I_MSG_EFF_FLAG) {
dreg = SUN4I_REG_BUF5_ADDR;
id = (readl(priv->base + SUN4I_REG_BUF1_ADDR) << 21) |
if (fi & SUN4I_MSG_RTR_FLAG)
id |= CAN_RTR_FLAG;
else
- for (i = 0; i < cf->can_dlc; i++)
+ for (i = 0; i < cf->len; i++)
cf->data[i] = readl(priv->base + dreg + i * 4);
cf->can_id = id;
sun4i_can_write_cmdreg(priv, SUN4I_CMD_RELEASE_RBUF);
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
can_led_event(dev, CAN_LED_EVENT_RX);
if (likely(skb)) {
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
} else {
return -ENOMEM;
spin_unlock_irqrestore(&priv->mbx_lock, flags);
/* Prepare mailbox for transmission */
- data = cf->can_dlc | (get_tx_head_prio(priv) << 8);
+ data = cf->len | (get_tx_head_prio(priv) << 8);
if (cf->can_id & CAN_RTR_FLAG) /* Remote transmission request */
data |= HECC_CANMCF_RTR;
hecc_write_mbx(priv, mbxno, HECC_CANMCF, data);
hecc_write_mbx(priv, mbxno, HECC_CANMID, data);
hecc_write_mbx(priv, mbxno, HECC_CANMDL,
be32_to_cpu(*(__be32 *)(cf->data)));
- if (cf->can_dlc > 4)
+ if (cf->len > 4)
hecc_write_mbx(priv, mbxno, HECC_CANMDH,
be32_to_cpu(*(__be32 *)(cf->data + 4)));
else
data = hecc_read_mbx(priv, mbxno, HECC_CANMCF);
if (data & HECC_CANMCF_RTR)
cf->can_id |= CAN_RTR_FLAG;
- cf->can_dlc = get_can_dlc(data & 0xF);
+ cf->len = can_cc_dlc2len(data & 0xF);
data = hecc_read_mbx(priv, mbxno, HECC_CANMDL);
*(__be32 *)(cf->data) = cpu_to_be32(data);
- if (cf->can_dlc > 4) {
+ if (cf->len > 4) {
data = hecc_read_mbx(priv, mbxno, HECC_CANMDH);
*(__be32 *)(cf->data + 4) = cpu_to_be32(data);
}
- Kvaser Leaf Light "China"
- Kvaser BlackBird SemiPro
- Kvaser USBcan R
+ - Kvaser USBcan R v2
- Kvaser Leaf Light v2
+ - Kvaser Leaf Light R v2
- Kvaser Mini PCI Express HS
- Kvaser Mini PCI Express 2xHS
- Kvaser USBcan Light 2xHS
- Kvaser USBcan Light 4xHS
- Kvaser USBcan Pro 2xHS v2
- Kvaser USBcan Pro 5xHS
+ - Kvaser U100
+ - Kvaser U100P
+ - Kvaser U100S
- ATI Memorator Pro 2xHS v2
- ATI USBcan Pro 2xHS v2
return;
cf->can_id = le32_to_cpu(msg->msg.can_msg.id);
- cf->can_dlc = get_can_dlc(msg->msg.can_msg.length & 0xF);
+ cf->len = can_cc_dlc2len(msg->msg.can_msg.length & 0xF);
if (msg->type == CPC_MSG_TYPE_EXT_CAN_FRAME ||
msg->type == CPC_MSG_TYPE_EXT_RTR_FRAME)
msg->type == CPC_MSG_TYPE_EXT_RTR_FRAME) {
cf->can_id |= CAN_RTR_FLAG;
} else {
- for (i = 0; i < cf->can_dlc; i++)
+ for (i = 0; i < cf->len; i++)
cf->data[i] = msg->msg.can_msg.msg[i];
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
msg = (struct ems_cpc_msg *)&buf[CPC_HEADER_SIZE];
msg->msg.can_msg.id = cpu_to_le32(cf->can_id & CAN_ERR_MASK);
- msg->msg.can_msg.length = cf->can_dlc;
+ msg->msg.can_msg.length = cf->len;
if (cf->can_id & CAN_RTR_FLAG) {
msg->type = cf->can_id & CAN_EFF_FLAG ?
msg->type = cf->can_id & CAN_EFF_FLAG ?
CPC_CMD_TYPE_EXT_CAN_FRAME : CPC_CMD_TYPE_CAN_FRAME;
- for (i = 0; i < cf->can_dlc; i++)
+ for (i = 0; i < cf->len; i++)
msg->msg.can_msg.msg[i] = cf->data[i];
- msg->length = CPC_CAN_MSG_MIN_SIZE + cf->can_dlc;
+ msg->length = CPC_CAN_MSG_MIN_SIZE + cf->len;
}
for (i = 0; i < MAX_TX_URBS; i++) {
context->dev = dev;
context->echo_index = i;
- context->dlc = cf->can_dlc;
+ context->dlc = cf->len;
usb_fill_bulk_urb(urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), buf,
size, ems_usb_write_bulk_callback, context);
struct esd_tx_urb_context {
struct esd_usb2_net_priv *priv;
u32 echo_index;
- int dlc;
+ int len; /* CAN payload length */
};
struct esd_usb2 {
priv->bec.rxerr = rxerr;
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
}
}
cf->can_id = id & ESD_IDMASK;
- cf->can_dlc = get_can_dlc(msg->msg.rx.dlc & ~ESD_RTR);
+ can_frame_set_cc_len(cf, msg->msg.rx.dlc & ~ESD_RTR,
+ priv->can.ctrlmode);
if (id & ESD_EXTID)
cf->can_id |= CAN_EFF_FLAG;
if (msg->msg.rx.dlc & ESD_RTR) {
cf->can_id |= CAN_RTR_FLAG;
} else {
- for (i = 0; i < cf->can_dlc; i++)
+ for (i = 0; i < cf->len; i++)
cf->data[i] = msg->msg.rx.data[i];
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
if (!msg->msg.txdone.status) {
stats->tx_packets++;
- stats->tx_bytes += context->dlc;
+ stats->tx_bytes += context->len;
can_get_echo_skb(netdev, context->echo_index);
} else {
stats->tx_errors++;
msg->msg.hdr.len = 3; /* minimal length */
msg->msg.hdr.cmd = CMD_CAN_TX;
msg->msg.tx.net = priv->index;
- msg->msg.tx.dlc = cf->can_dlc;
+ msg->msg.tx.dlc = can_get_cc_dlc(cf, priv->can.ctrlmode);
msg->msg.tx.id = cpu_to_le32(cf->can_id & CAN_ERR_MASK);
if (cf->can_id & CAN_RTR_FLAG)
if (cf->can_id & CAN_EFF_FLAG)
msg->msg.tx.id |= cpu_to_le32(ESD_EXTID);
- for (i = 0; i < cf->can_dlc; i++)
+ for (i = 0; i < cf->len; i++)
msg->msg.tx.data[i] = cf->data[i];
- msg->msg.hdr.len += (cf->can_dlc + 3) >> 2;
+ msg->msg.hdr.len += (cf->len + 3) >> 2;
for (i = 0; i < MAX_TX_URBS; i++) {
if (priv->tx_contexts[i].echo_index == MAX_TX_URBS) {
context->priv = priv;
context->echo_index = i;
- context->dlc = cf->can_dlc;
+ context->len = cf->len;
/* hnd must not be 0 - MSB is stripped in txdone handling */
msg->msg.tx.hnd = 0x80000000 | i; /* returned in TX done message */
priv->index = index;
priv->can.state = CAN_STATE_STOPPED;
- priv->can.ctrlmode_supported = CAN_CTRLMODE_LISTENONLY;
+ priv->can.ctrlmode_supported = CAN_CTRLMODE_LISTENONLY |
+ CAN_CTRLMODE_CC_LEN8_DLC;
if (le16_to_cpu(dev->udev->descriptor.idProduct) ==
USB_CANUSBM_PRODUCT_ID)
* Many thanks to all socketcan devs!
*/
+#include <linux/ethtool.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/module.h>
cf->can_id = le32_to_cpu(hf->can_id);
- cf->can_dlc = get_can_dlc(hf->can_dlc);
+ can_frame_set_cc_len(cf, hf->can_dlc, dev->can.ctrlmode);
memcpy(cf->data, hf->data, 8);
/* ERROR frames tell us information about the controller */
goto resubmit_urb;
cf->can_id |= CAN_ERR_CRTL;
- cf->can_dlc = CAN_ERR_DLC;
+ cf->len = CAN_ERR_DLC;
cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
stats->rx_over_errors++;
stats->rx_errors++;
cf = (struct can_frame *)skb->data;
hf->can_id = cpu_to_le32(cf->can_id);
- hf->can_dlc = cf->can_dlc;
- memcpy(hf->data, cf->data, cf->can_dlc);
+ hf->can_dlc = can_get_cc_dlc(cf, dev->can.ctrlmode);
+
+ memcpy(hf->data, cf->data, cf->len);
usb_fill_bulk_urb(urb, dev->udev,
usb_sndbulkpipe(dev->udev, GSUSB_ENDPOINT_OUT),
dev->can.bittiming_const = &dev->bt_const;
dev->can.do_set_bittiming = gs_usb_set_bittiming;
- dev->can.ctrlmode_supported = 0;
+ dev->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC;
feature = le32_to_cpu(bt_const->feature);
if (feature & GS_CAN_FEATURE_LISTEN_ONLY)
#define USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID 290
#define USB_USBCAN_LIGHT_2HS_PRODUCT_ID 291
#define USB_MINI_PCIE_2HS_PRODUCT_ID 292
+#define USB_USBCAN_R_V2_PRODUCT_ID 294
+#define USB_LEAF_LIGHT_R_V2_PRODUCT_ID 295
+#define USB_LEAF_LIGHT_HS_V2_OEM2_PRODUCT_ID 296
+#define USB_LEAF_PRODUCT_ID_END \
+ USB_LEAF_LIGHT_HS_V2_OEM2_PRODUCT_ID
/* Kvaser USBCan-II devices product ids */
#define USB_USBCAN_REVB_PRODUCT_ID 2
#define USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID 268
#define USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID 269
#define USB_HYBRID_PRO_CANLIN_PRODUCT_ID 270
+#define USB_U100_PRODUCT_ID 273
+#define USB_U100P_PRODUCT_ID 274
+#define USB_U100S_PRODUCT_ID 275
+#define USB_HYDRA_PRODUCT_ID_END \
+ USB_U100S_PRODUCT_ID
static inline bool kvaser_is_leaf(const struct usb_device_id *id)
{
return (id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID &&
id->idProduct <= USB_CAN_R_PRODUCT_ID) ||
(id->idProduct >= USB_LEAF_LITE_V2_PRODUCT_ID &&
- id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID);
+ id->idProduct <= USB_LEAF_PRODUCT_ID_END);
}
static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
static inline bool kvaser_is_hydra(const struct usb_device_id *id)
{
return id->idProduct >= USB_BLACKBIRD_V2_PRODUCT_ID &&
- id->idProduct <= USB_HYBRID_PRO_CANLIN_PRODUCT_ID;
+ id->idProduct <= USB_HYDRA_PRODUCT_ID_END;
}
static const struct usb_device_id kvaser_usb_table[] = {
{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID) },
{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID) },
{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID) },
+ { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_R_V2_PRODUCT_ID) },
+ { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_R_V2_PRODUCT_ID) },
+ { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM2_PRODUCT_ID) },
/* USBCANII USB product IDs */
{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID),
{ USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID) },
{ USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID) },
{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_CANLIN_PRODUCT_ID) },
+ { USB_DEVICE(KVASER_VENDOR_ID, USB_U100_PRODUCT_ID) },
+ { USB_DEVICE(KVASER_VENDOR_ID, USB_U100P_PRODUCT_ID) },
+ { USB_DEVICE(KVASER_VENDOR_ID, USB_U100S_PRODUCT_ID) },
{ }
};
MODULE_DEVICE_TABLE(usb, kvaser_usb_table);
cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
return 0;
/* Forward declarations */
static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_kcan;
static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_flexc;
+static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_rt;
#define KVASER_USB_HYDRA_BULK_EP_IN_ADDR 0x82
#define KVASER_USB_HYDRA_BULK_EP_OUT_ADDR 0x02
#define KVASER_USB_HYDRA_SW_FLAG_CANFD BIT(10)
#define KVASER_USB_HYDRA_SW_FLAG_NONISO BIT(11)
#define KVASER_USB_HYDRA_SW_FLAG_EXT_CAP BIT(12)
+#define KVASER_USB_HYDRA_SW_FLAG_CAN_FREQ_80M BIT(13)
struct kvaser_cmd_sw_detail_res {
__le32 sw_flags;
__le32 sw_version;
.brp_inc = 1,
};
+static const struct can_bittiming_const kvaser_usb_hydra_rt_bittiming_c = {
+ .name = "kvaser_usb_rt",
+ .tseg1_min = 2,
+ .tseg1_max = 96,
+ .tseg2_min = 2,
+ .tseg2_max = 32,
+ .sjw_max = 32,
+ .brp_min = 1,
+ .brp_max = 1024,
+ .brp_inc = 1,
+};
+
+static const struct can_bittiming_const kvaser_usb_hydra_rtd_bittiming_c = {
+ .name = "kvaser_usb_rt",
+ .tseg1_min = 2,
+ .tseg1_max = 39,
+ .tseg2_min = 2,
+ .tseg2_max = 8,
+ .sjw_max = 8,
+ .brp_min = 1,
+ .brp_max = 1024,
+ .brp_inc = 1,
+};
+
#define KVASER_USB_HYDRA_TRANSID_BITS 12
#define KVASER_USB_HYDRA_TRANSID_MASK \
GENMASK(KVASER_USB_HYDRA_TRANSID_BITS - 1, 0)
stats = &netdev->stats;
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
cf->data[7] = bec.rxerr;
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
priv->bec.txerr = bec.txerr;
stats->tx_errors++;
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
struct net_device_stats *stats = &priv->netdev->stats;
stats->tx_packets++;
- stats->tx_bytes += can_dlc2len(context->dlc);
+ stats->tx_bytes += can_fd_dlc2len(context->dlc);
}
spin_lock_irqsave(&priv->tx_contexts_lock, irq_flags);
if (flags & KVASER_USB_HYDRA_CF_FLAG_OVERRUN)
kvaser_usb_can_rx_over_error(priv->netdev);
- cf->can_dlc = get_can_dlc(cmd->rx_can.dlc);
+ cf->len = can_cc_dlc2len(cmd->rx_can.dlc);
if (flags & KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME)
cf->can_id |= CAN_RTR_FLAG;
else
- memcpy(cf->data, cmd->rx_can.data, cf->can_dlc);
+ memcpy(cf->data, cmd->rx_can.data, cf->len);
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
kvaser_usb_can_rx_over_error(priv->netdev);
if (flags & KVASER_USB_HYDRA_CF_FLAG_FDF) {
- cf->len = can_dlc2len(get_canfd_dlc(dlc));
+ cf->len = can_fd_dlc2len(dlc);
if (flags & KVASER_USB_HYDRA_CF_FLAG_BRS)
cf->flags |= CANFD_BRS;
if (flags & KVASER_USB_HYDRA_CF_FLAG_ESI)
cf->flags |= CANFD_ESI;
} else {
- cf->len = get_can_dlc(dlc);
+ cf->len = can_cc_dlc2len(dlc);
}
if (flags & KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME)
struct kvaser_usb *dev = priv->dev;
struct kvaser_cmd_ext *cmd;
struct canfd_frame *cf = (struct canfd_frame *)skb->data;
- u8 dlc = can_len2dlc(cf->len);
+ u8 dlc = can_fd_len2dlc(cf->len);
u8 nbr_of_bytes = cf->len;
u32 flags;
u32 id;
u32 flags;
u32 id;
- *frame_len = cf->can_dlc;
+ *frame_len = cf->len;
cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_ATOMIC);
if (!cmd)
id = cf->can_id & CAN_SFF_MASK;
}
- cmd->tx_can.dlc = cf->can_dlc;
+ cmd->tx_can.dlc = cf->len;
flags = (cf->can_id & CAN_EFF_FLAG ?
KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID : 0);
if (flags & KVASER_USB_HYDRA_SW_FLAG_FREQ_80M)
dev->cfg = &kvaser_usb_hydra_dev_cfg_kcan;
+ else if (flags & KVASER_USB_HYDRA_SW_FLAG_CAN_FREQ_80M)
+ dev->cfg = &kvaser_usb_hydra_dev_cfg_rt;
else
dev->cfg = &kvaser_usb_hydra_dev_cfg_flexc;
.timestamp_freq = 1,
.bittiming_const = &kvaser_usb_hydra_flexc_bittiming_c,
};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_rt = {
+ .clock = {
+ .freq = 80000000,
+ },
+ .timestamp_freq = 24,
+ .bittiming_const = &kvaser_usb_hydra_rt_bittiming_c,
+ .data_bittiming_const = &kvaser_usb_hydra_rtd_bittiming_c,
+};
u8 *cmd_tx_can_flags = NULL; /* GCC */
struct can_frame *cf = (struct can_frame *)skb->data;
- *frame_len = cf->can_dlc;
+ *frame_len = cf->len;
cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC);
if (cmd) {
cmd->u.tx_can.data[1] = cf->can_id & 0x3f;
}
- cmd->u.tx_can.data[5] = cf->can_dlc;
- memcpy(&cmd->u.tx_can.data[6], cf->data, cf->can_dlc);
+ cmd->u.tx_can.data[5] = cf->len;
+ memcpy(&cmd->u.tx_can.data[6], cf->data, cf->len);
if (cf->can_id & CAN_RTR_FLAG)
*cmd_tx_can_flags |= MSG_FLAG_REMOTE_FRAME;
cf->can_id |= CAN_ERR_RESTARTED;
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
} else {
netdev_err(priv->netdev,
{
struct can_frame *cf;
struct can_frame tmp_cf = { .can_id = CAN_ERR_FLAG,
- .can_dlc = CAN_ERR_DLC };
+ .len = CAN_ERR_DLC };
struct sk_buff *skb;
struct net_device_stats *stats;
struct kvaser_usb_net_priv *priv;
cf->data[7] = es->rxerr;
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
else
cf->can_id &= CAN_SFF_MASK;
- cf->can_dlc = get_can_dlc(cmd->u.leaf.log_message.dlc);
+ cf->len = can_cc_dlc2len(cmd->u.leaf.log_message.dlc);
if (cmd->u.leaf.log_message.flags & MSG_FLAG_REMOTE_FRAME)
cf->can_id |= CAN_RTR_FLAG;
else
memcpy(cf->data, &cmd->u.leaf.log_message.data,
- cf->can_dlc);
+ cf->len);
} else {
cf->can_id = ((rx_data[0] & 0x1f) << 6) | (rx_data[1] & 0x3f);
cf->can_id |= CAN_EFF_FLAG;
}
- cf->can_dlc = get_can_dlc(rx_data[5]);
+ cf->len = can_cc_dlc2len(rx_data[5]);
if (cmd->u.rx_can_header.flag & MSG_FLAG_REMOTE_FRAME)
cf->can_id |= CAN_RTR_FLAG;
else
- memcpy(cf->data, &rx_data[6], cf->can_dlc);
+ memcpy(cf->data, &rx_data[6], cf->len);
}
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
if (cf) {
ctx->can = true;
- ctx->dlc = cf->can_dlc;
+ ctx->dlc = cf->len;
} else {
ctx->can = false;
ctx->dlc = 0;
usb_msg.eid = 0;
}
- usb_msg.dlc = cf->can_dlc;
+ usb_msg.dlc = cf->len;
memcpy(usb_msg.data, cf->data, usb_msg.dlc);
if (msg->dlc & MCBA_DLC_RTR_MASK)
cf->can_id |= CAN_RTR_FLAG;
- cf->can_dlc = get_can_dlc(msg->dlc & MCBA_DLC_MASK);
+ cf->len = can_cc_dlc2len(msg->dlc & MCBA_DLC_MASK);
- memcpy(cf->data, msg->data, cf->can_dlc);
+ memcpy(cf->data, msg->data, cf->len);
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
can_led_event(priv->netdev, CAN_LED_EVENT_RX);
netif_rx(skb);
}
mc->netdev->stats.rx_packets++;
- mc->netdev->stats.rx_bytes += cf->can_dlc;
+ mc->netdev->stats.rx_bytes += cf->len;
netif_rx(skb);
return 0;
cf->can_id = le16_to_cpu(tmp16) >> 5;
}
- cf->can_dlc = get_can_dlc(rec_len);
+ can_frame_set_cc_len(cf, rec_len, mc->pdev->dev.can.ctrlmode);
/* Only first packet timestamp is a word */
if (pcan_usb_decode_ts(mc, !mc->rec_ts_idx))
if ((mc->ptr + rec_len) > mc->end)
goto decode_failed;
- memcpy(cf->data, mc->ptr, cf->can_dlc);
+ memcpy(cf->data, mc->ptr, cf->len);
mc->ptr += rec_len;
}
/* update statistics */
mc->netdev->stats.rx_packets++;
- mc->netdev->stats.rx_bytes += cf->can_dlc;
+ mc->netdev->stats.rx_bytes += cf->len;
/* push the skb */
netif_rx(skb);
pc = obuf + PCAN_USB_MSG_HEADER_LEN;
/* status/len byte */
- *pc = cf->can_dlc;
+ *pc = can_get_cc_dlc(cf, dev->can.ctrlmode);
+
if (cf->can_id & CAN_RTR_FLAG)
*pc |= PCAN_USB_STATUSLEN_RTR;
/* can data */
if (!(cf->can_id & CAN_RTR_FLAG)) {
- memcpy(pc, cf->data, cf->can_dlc);
- pc += cf->can_dlc;
+ memcpy(pc, cf->data, cf->len);
+ pc += cf->len;
}
obuf[(*size)-1] = (u8)(stats->tx_packets & 0xff);
.device_id = PCAN_USB_PRODUCT_ID,
.ctrl_count = 1,
.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY |
- CAN_CTRLMODE_BERR_REPORTING,
+ CAN_CTRLMODE_BERR_REPORTING |
+ CAN_CTRLMODE_CC_LEN8_DLC,
.clock = {
.freq = PCAN_USB_CRYSTAL_HZ / 2 ,
},
netif_trans_update(netdev);
break;
- default:
- if (net_ratelimit())
- netdev_err(netdev, "Tx urb aborted (%d)\n",
- urb->status);
case -EPROTO:
case -ENOENT:
case -ECONNRESET:
case -ESHUTDOWN:
+ break;
+ default:
+ if (net_ratelimit())
+ netdev_err(netdev, "Tx urb aborted (%d)\n",
+ urb->status);
break;
}
if (rx_msg_flags & PUCAN_MSG_ERROR_STATE_IND)
cfd->flags |= CANFD_ESI;
- cfd->len = can_dlc2len(get_canfd_dlc(pucan_msg_get_dlc(rm)));
+ cfd->len = can_fd_dlc2len(pucan_msg_get_dlc(rm));
} else {
/* CAN 2.0 frame case */
skb = alloc_can_skb(netdev, (struct can_frame **)&cfd);
if (!skb)
return -ENOMEM;
- cfd->len = get_can_dlc(pucan_msg_get_dlc(rm));
+ can_frame_set_cc_len((struct can_frame *)cfd,
+ pucan_msg_get_dlc(rm),
+ dev->can.ctrlmode);
}
cfd->can_id = le32_to_cpu(rm->can_id);
peak_usb_netif_rx(skb, &usb_if->time_ref, le32_to_cpu(sm->ts_low));
netdev->stats.rx_packets++;
- netdev->stats.rx_bytes += cf->can_dlc;
+ netdev->stats.rx_bytes += cf->len;
return 0;
}
struct pucan_tx_msg *tx_msg = (struct pucan_tx_msg *)obuf;
struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
u16 tx_msg_size, tx_msg_flags;
- u8 can_dlc;
+ u8 dlc;
if (cfd->len > CANFD_MAX_DLEN)
return -EINVAL;
if (can_is_canfd_skb(skb)) {
/* considering a CANFD frame */
- can_dlc = can_len2dlc(cfd->len);
+ dlc = can_fd_len2dlc(cfd->len);
tx_msg_flags |= PUCAN_MSG_EXT_DATA_LEN;
tx_msg_flags |= PUCAN_MSG_ERROR_STATE_IND;
} else {
/* CAND 2.0 frames */
- can_dlc = cfd->len;
+ dlc = can_get_cc_dlc((struct can_frame *)cfd,
+ dev->can.ctrlmode);
if (cfd->can_id & CAN_RTR_FLAG)
tx_msg_flags |= PUCAN_MSG_RTR;
}
tx_msg->flags = cpu_to_le16(tx_msg_flags);
- tx_msg->channel_dlc = PUCAN_MSG_CHANNEL_DLC(dev->ctrl_idx, can_dlc);
+ tx_msg->channel_dlc = PUCAN_MSG_CHANNEL_DLC(dev->ctrl_idx, dlc);
memcpy(tx_msg->d, cfd->data, cfd->len);
/* add null size message to tag the end (messages are 32-bits aligned)
.device_id = PCAN_USBFD_PRODUCT_ID,
.ctrl_count = PCAN_USBFD_CHANNEL_COUNT,
.ctrlmode_supported = CAN_CTRLMODE_FD |
- CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY,
+ CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY |
+ CAN_CTRLMODE_CC_LEN8_DLC,
.clock = {
.freq = PCAN_UFD_CRYSTAL_HZ,
},
.device_id = PCAN_USBCHIP_PRODUCT_ID,
.ctrl_count = PCAN_USBFD_CHANNEL_COUNT,
.ctrlmode_supported = CAN_CTRLMODE_FD |
- CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY,
+ CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY |
+ CAN_CTRLMODE_CC_LEN8_DLC,
.clock = {
.freq = PCAN_UFD_CRYSTAL_HZ,
},
.device_id = PCAN_USBPROFD_PRODUCT_ID,
.ctrl_count = PCAN_USBPROFD_CHANNEL_COUNT,
.ctrlmode_supported = CAN_CTRLMODE_FD |
- CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY,
+ CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY |
+ CAN_CTRLMODE_CC_LEN8_DLC,
.clock = {
.freq = PCAN_UFD_CRYSTAL_HZ,
},
.device_id = PCAN_USBX6_PRODUCT_ID,
.ctrl_count = PCAN_USBPROFD_CHANNEL_COUNT,
.ctrlmode_supported = CAN_CTRLMODE_FD |
- CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY,
+ CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY |
+ CAN_CTRLMODE_CC_LEN8_DLC,
.clock = {
.freq = PCAN_UFD_CRYSTAL_HZ,
},
return -ENOMEM;
can_frame->can_id = le32_to_cpu(rx->id);
- can_frame->can_dlc = rx->len & 0x0f;
+ can_frame->len = rx->len & 0x0f;
if (rx->flags & PCAN_USBPRO_EXT)
can_frame->can_id |= CAN_EFF_FLAG;
if (rx->flags & PCAN_USBPRO_RTR)
can_frame->can_id |= CAN_RTR_FLAG;
else
- memcpy(can_frame->data, rx->data, can_frame->can_dlc);
+ memcpy(can_frame->data, rx->data, can_frame->len);
hwts = skb_hwtstamps(skb);
peak_usb_get_ts_time(&usb_if->time_ref, le32_to_cpu(rx->ts32),
&hwts->hwtstamp);
netdev->stats.rx_packets++;
- netdev->stats.rx_bytes += can_frame->can_dlc;
+ netdev->stats.rx_bytes += can_frame->len;
netif_rx(skb);
return 0;
hwts = skb_hwtstamps(skb);
peak_usb_get_ts_time(&usb_if->time_ref, le32_to_cpu(er->ts32), &hwts->hwtstamp);
netdev->stats.rx_packets++;
- netdev->stats.rx_bytes += can_frame->can_dlc;
+ netdev->stats.rx_bytes += can_frame->len;
netif_rx(skb);
return 0;
pcan_msg_init_empty(&usb_msg, obuf, *size);
- if ((cf->can_id & CAN_RTR_FLAG) || (cf->can_dlc == 0))
+ if ((cf->can_id & CAN_RTR_FLAG) || (cf->len == 0))
data_type = PCAN_USBPRO_TXMSG0;
- else if (cf->can_dlc <= 4)
+ else if (cf->len <= 4)
data_type = PCAN_USBPRO_TXMSG4;
else
data_type = PCAN_USBPRO_TXMSG8;
- len = (dev->ctrl_idx << 4) | (cf->can_dlc & 0x0f);
+ len = (dev->ctrl_idx << 4) | (cf->len & 0x0f);
flags = 0;
if (cf->can_id & CAN_EFF_FLAG)
struct ucan_urb_context *context_array;
};
-static u8 ucan_get_can_dlc(struct ucan_can_msg *msg, u16 len)
+static u8 ucan_can_cc_dlc2len(struct ucan_can_msg *msg, u16 len)
{
if (le32_to_cpu(msg->id) & CAN_RTR_FLAG)
- return get_can_dlc(msg->dlc);
+ return can_cc_dlc2len(msg->dlc);
else
- return get_can_dlc(len - (UCAN_IN_HDR_SIZE + sizeof(msg->id)));
+ return can_cc_dlc2len(len - (UCAN_IN_HDR_SIZE + sizeof(msg->id)));
}
static void ucan_release_context_array(struct ucan_priv *up)
cf->can_id = canid;
/* compute DLC taking RTR_FLAG into account */
- cf->can_dlc = ucan_get_can_dlc(&m->msg.can_msg, len);
+ cf->len = ucan_can_cc_dlc2len(&m->msg.can_msg, len);
/* copy the payload of non RTR frames */
if (!(cf->can_id & CAN_RTR_FLAG) || (cf->can_id & CAN_ERR_FLAG))
- memcpy(cf->data, m->msg.can_msg.data, cf->can_dlc);
+ memcpy(cf->data, m->msg.can_msg.data, cf->len);
/* don't count error frames as real packets */
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
/* pass it to Linux */
netif_rx(skb);
mlen = UCAN_OUT_HDR_SIZE +
offsetof(struct ucan_can_msg, dlc) +
sizeof(m->msg.can_msg.dlc);
- m->msg.can_msg.dlc = cf->can_dlc;
+ m->msg.can_msg.dlc = cf->len;
} else {
mlen = UCAN_OUT_HDR_SIZE +
- sizeof(m->msg.can_msg.id) + cf->can_dlc;
- memcpy(m->msg.can_msg.data, cf->data, cf->can_dlc);
+ sizeof(m->msg.can_msg.id) + cf->len;
+ memcpy(m->msg.can_msg.data, cf->data, cf->len);
}
m->len = cpu_to_le16(mlen);
- context->dlc = cf->can_dlc;
+ context->dlc = cf->len;
m->subtype = echo_index;
priv->bec.rxerr = rxerr;
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
return;
cf->can_id = be32_to_cpu(msg->id);
- cf->can_dlc = get_can_dlc(msg->dlc & 0xF);
+ can_frame_set_cc_len(cf, msg->dlc & 0xF, priv->can.ctrlmode);
if (msg->flags & USB_8DEV_EXTID)
cf->can_id |= CAN_EFF_FLAG;
if (msg->flags & USB_8DEV_RTR)
cf->can_id |= CAN_RTR_FLAG;
else
- memcpy(cf->data, msg->data, cf->can_dlc);
+ memcpy(cf->data, msg->data, cf->len);
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
can_led_event(priv->netdev, CAN_LED_EVENT_RX);
msg->flags |= USB_8DEV_EXTID;
msg->id = cpu_to_be32(cf->can_id & CAN_ERR_MASK);
- msg->dlc = cf->can_dlc;
- memcpy(msg->data, cf->data, cf->can_dlc);
+ msg->dlc = can_get_cc_dlc(cf, priv->can.ctrlmode);
+ memcpy(msg->data, cf->data, cf->len);
msg->end = USB_8DEV_DATA_END;
for (i = 0; i < MAX_TX_URBS; i++) {
context->priv = priv;
context->echo_index = i;
- context->dlc = cf->can_dlc;
+ context->dlc = cf->len;
usb_fill_bulk_urb(urb, priv->udev,
usb_sndbulkpipe(priv->udev, USB_8DEV_ENDP_DATA_TX),
priv->can.do_get_berr_counter = usb_8dev_get_berr_counter;
priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
CAN_CTRLMODE_LISTENONLY |
- CAN_CTRLMODE_ONE_SHOT;
+ CAN_CTRLMODE_ONE_SHOT |
+ CAN_CTRLMODE_CC_LEN8_DLC;
netdev->netdev_ops = &usb_8dev_netdev_ops;
}
if (ifmp && tbp[IFLA_IFNAME]) {
- nla_strlcpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
+ nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
name_assign_type = NET_NAME_USER;
} else {
snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
/* register first device */
if (tb[IFLA_IFNAME])
- nla_strlcpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
+ nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
else
snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d");
id |= XCAN_IDR_SRR_MASK;
}
- dlc = can_len2dlc(cf->len) << XCAN_DLCR_DLC_SHIFT;
+ dlc = can_fd_len2dlc(cf->len) << XCAN_DLCR_DLC_SHIFT;
if (can_is_canfd_skb(skb)) {
if (cf->flags & CANFD_BRS)
dlc |= XCAN_DLCR_BRS_MASK;
XCAN_DLCR_DLC_SHIFT;
/* Change Xilinx CAN data length format to socketCAN data format */
- cf->can_dlc = get_can_dlc(dlc);
+ cf->len = can_cc_dlc2len(dlc);
/* Change Xilinx CAN ID format to socketCAN ID format */
if (id_xcan & XCAN_IDR_IDE_MASK) {
if (!(cf->can_id & CAN_RTR_FLAG)) {
/* Change Xilinx CAN data format to socketCAN data format */
- if (cf->can_dlc > 0)
+ if (cf->len > 0)
*(__be32 *)(cf->data) = cpu_to_be32(data[0]);
- if (cf->can_dlc > 4)
+ if (cf->len > 4)
*(__be32 *)(cf->data + 4) = cpu_to_be32(data[1]);
}
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
stats->rx_packets++;
netif_receive_skb(skb);
* format
*/
if (dlc & XCAN_DLCR_EDL_MASK)
- cf->len = can_dlc2len((dlc & XCAN_DLCR_DLC_MASK) >>
+ cf->len = can_fd_dlc2len((dlc & XCAN_DLCR_DLC_MASK) >>
XCAN_DLCR_DLC_SHIFT);
else
- cf->len = get_can_dlc((dlc & XCAN_DLCR_DLC_MASK) >>
+ cf->len = can_cc_dlc2len((dlc & XCAN_DLCR_DLC_MASK) >>
XCAN_DLCR_DLC_SHIFT);
/* Change Xilinx CAN ID format to socketCAN ID format */
struct net_device_stats *stats = &ndev->stats;
stats->rx_packets++;
- stats->rx_bytes += cf->can_dlc;
+ stats->rx_bytes += cf->len;
netif_rx(skb);
}
}
This enables support for a fake mock-up switch chip which
exercises the DSA APIs.
+source "drivers/net/dsa/hirschmann/Kconfig"
+
config NET_DSA_LANTIQ_GSWIP
tristate "Lantiq / Intel GSWIP"
depends on HAS_IOMEM && NET_DSA
obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_PLATFORM) += vitesse-vsc73xx-platform.o
obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_SPI) += vitesse-vsc73xx-spi.o
obj-y += b53/
+obj-y += hirschmann/
obj-y += microchip/
obj-y += mv88e6xxx/
obj-y += ocelot/
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+config NET_DSA_HIRSCHMANN_HELLCREEK
+ tristate "Hirschmann Hellcreek TSN Switch support"
+ depends on HAS_IOMEM
+ depends on NET_DSA
+ depends on PTP_1588_CLOCK
+ select NET_DSA_TAG_HELLCREEK
+ help
+ This driver adds support for Hirschmann Hellcreek TSN switches.
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_NET_DSA_HIRSCHMANN_HELLCREEK) += hellcreek_sw.o
+hellcreek_sw-objs := hellcreek.o
+hellcreek_sw-objs += hellcreek_ptp.o
+hellcreek_sw-objs += hellcreek_hwtstamp.o
--- /dev/null
+// SPDX-License-Identifier: (GPL-2.0 or MIT)
+/*
+ * DSA driver for:
+ * Hirschmann Hellcreek TSN switch.
+ *
+ * Copyright (C) 2019,2020 Linutronix GmbH
+ * Author Kurt Kanzenbach <kurt@linutronix.de>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/platform_device.h>
+#include <linux/bitops.h>
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
+#include <linux/etherdevice.h>
+#include <linux/random.h>
+#include <linux/iopoll.h>
+#include <linux/mutex.h>
+#include <linux/delay.h>
+#include <net/dsa.h>
+
+#include "hellcreek.h"
+#include "hellcreek_ptp.h"
+#include "hellcreek_hwtstamp.h"
+
+static const struct hellcreek_counter hellcreek_counter[] = {
+ { 0x00, "RxFiltered", },
+ { 0x01, "RxOctets1k", },
+ { 0x02, "RxVTAG", },
+ { 0x03, "RxL2BAD", },
+ { 0x04, "RxOverloadDrop", },
+ { 0x05, "RxUC", },
+ { 0x06, "RxMC", },
+ { 0x07, "RxBC", },
+ { 0x08, "RxRS<64", },
+ { 0x09, "RxRS64", },
+ { 0x0a, "RxRS65_127", },
+ { 0x0b, "RxRS128_255", },
+ { 0x0c, "RxRS256_511", },
+ { 0x0d, "RxRS512_1023", },
+ { 0x0e, "RxRS1024_1518", },
+ { 0x0f, "RxRS>1518", },
+ { 0x10, "TxTailDropQueue0", },
+ { 0x11, "TxTailDropQueue1", },
+ { 0x12, "TxTailDropQueue2", },
+ { 0x13, "TxTailDropQueue3", },
+ { 0x14, "TxTailDropQueue4", },
+ { 0x15, "TxTailDropQueue5", },
+ { 0x16, "TxTailDropQueue6", },
+ { 0x17, "TxTailDropQueue7", },
+ { 0x18, "RxTrafficClass0", },
+ { 0x19, "RxTrafficClass1", },
+ { 0x1a, "RxTrafficClass2", },
+ { 0x1b, "RxTrafficClass3", },
+ { 0x1c, "RxTrafficClass4", },
+ { 0x1d, "RxTrafficClass5", },
+ { 0x1e, "RxTrafficClass6", },
+ { 0x1f, "RxTrafficClass7", },
+ { 0x21, "TxOctets1k", },
+ { 0x22, "TxVTAG", },
+ { 0x23, "TxL2BAD", },
+ { 0x25, "TxUC", },
+ { 0x26, "TxMC", },
+ { 0x27, "TxBC", },
+ { 0x28, "TxTS<64", },
+ { 0x29, "TxTS64", },
+ { 0x2a, "TxTS65_127", },
+ { 0x2b, "TxTS128_255", },
+ { 0x2c, "TxTS256_511", },
+ { 0x2d, "TxTS512_1023", },
+ { 0x2e, "TxTS1024_1518", },
+ { 0x2f, "TxTS>1518", },
+ { 0x30, "TxTrafficClassOverrun0", },
+ { 0x31, "TxTrafficClassOverrun1", },
+ { 0x32, "TxTrafficClassOverrun2", },
+ { 0x33, "TxTrafficClassOverrun3", },
+ { 0x34, "TxTrafficClassOverrun4", },
+ { 0x35, "TxTrafficClassOverrun5", },
+ { 0x36, "TxTrafficClassOverrun6", },
+ { 0x37, "TxTrafficClassOverrun7", },
+ { 0x38, "TxTrafficClass0", },
+ { 0x39, "TxTrafficClass1", },
+ { 0x3a, "TxTrafficClass2", },
+ { 0x3b, "TxTrafficClass3", },
+ { 0x3c, "TxTrafficClass4", },
+ { 0x3d, "TxTrafficClass5", },
+ { 0x3e, "TxTrafficClass6", },
+ { 0x3f, "TxTrafficClass7", },
+};
+
+static u16 hellcreek_read(struct hellcreek *hellcreek, unsigned int offset)
+{
+ return readw(hellcreek->base + offset);
+}
+
+static u16 hellcreek_read_ctrl(struct hellcreek *hellcreek)
+{
+ return readw(hellcreek->base + HR_CTRL_C);
+}
+
+static u16 hellcreek_read_stat(struct hellcreek *hellcreek)
+{
+ return readw(hellcreek->base + HR_SWSTAT);
+}
+
+static void hellcreek_write(struct hellcreek *hellcreek, u16 data,
+ unsigned int offset)
+{
+ writew(data, hellcreek->base + offset);
+}
+
+static void hellcreek_select_port(struct hellcreek *hellcreek, int port)
+{
+ u16 val = port << HR_PSEL_PTWSEL_SHIFT;
+
+ hellcreek_write(hellcreek, val, HR_PSEL);
+}
+
+static void hellcreek_select_prio(struct hellcreek *hellcreek, int prio)
+{
+ u16 val = prio << HR_PSEL_PRTCWSEL_SHIFT;
+
+ hellcreek_write(hellcreek, val, HR_PSEL);
+}
+
+static void hellcreek_select_counter(struct hellcreek *hellcreek, int counter)
+{
+ u16 val = counter << HR_CSEL_SHIFT;
+
+ hellcreek_write(hellcreek, val, HR_CSEL);
+
+ /* Data sheet states to wait at least 20 internal clock cycles */
+ ndelay(200);
+}
+
+static void hellcreek_select_vlan(struct hellcreek *hellcreek, int vid,
+ bool pvid)
+{
+ u16 val = 0;
+
+ /* Set pvid bit first */
+ if (pvid)
+ val |= HR_VIDCFG_PVID;
+ hellcreek_write(hellcreek, val, HR_VIDCFG);
+
+ /* Set vlan */
+ val |= vid << HR_VIDCFG_VID_SHIFT;
+ hellcreek_write(hellcreek, val, HR_VIDCFG);
+}
+
+static int hellcreek_wait_until_ready(struct hellcreek *hellcreek)
+{
+ u16 val;
+
+ /* Wait up to 1ms, although 3 us should be enough */
+ return readx_poll_timeout(hellcreek_read_ctrl, hellcreek,
+ val, val & HR_CTRL_C_READY,
+ 3, 1000);
+}
+
+static int hellcreek_wait_until_transitioned(struct hellcreek *hellcreek)
+{
+ u16 val;
+
+ return readx_poll_timeout_atomic(hellcreek_read_ctrl, hellcreek,
+ val, !(val & HR_CTRL_C_TRANSITION),
+ 1, 1000);
+}
+
+static int hellcreek_wait_fdb_ready(struct hellcreek *hellcreek)
+{
+ u16 val;
+
+ return readx_poll_timeout_atomic(hellcreek_read_stat, hellcreek,
+ val, !(val & HR_SWSTAT_BUSY),
+ 1, 1000);
+}
+
+static int hellcreek_detect(struct hellcreek *hellcreek)
+{
+ u16 id, rel_low, rel_high, date_low, date_high, tgd_ver;
+ u8 tgd_maj, tgd_min;
+ u32 rel, date;
+
+ id = hellcreek_read(hellcreek, HR_MODID_C);
+ rel_low = hellcreek_read(hellcreek, HR_REL_L_C);
+ rel_high = hellcreek_read(hellcreek, HR_REL_H_C);
+ date_low = hellcreek_read(hellcreek, HR_BLD_L_C);
+ date_high = hellcreek_read(hellcreek, HR_BLD_H_C);
+ tgd_ver = hellcreek_read(hellcreek, TR_TGDVER);
+
+ if (id != hellcreek->pdata->module_id)
+ return -ENODEV;
+
+ rel = rel_low | (rel_high << 16);
+ date = date_low | (date_high << 16);
+ tgd_maj = (tgd_ver & TR_TGDVER_REV_MAJ_MASK) >> TR_TGDVER_REV_MAJ_SHIFT;
+ tgd_min = (tgd_ver & TR_TGDVER_REV_MIN_MASK) >> TR_TGDVER_REV_MIN_SHIFT;
+
+ dev_info(hellcreek->dev, "Module ID=%02x Release=%04x Date=%04x TGD Version=%02x.%02x\n",
+ id, rel, date, tgd_maj, tgd_min);
+
+ return 0;
+}
+
+static void hellcreek_feature_detect(struct hellcreek *hellcreek)
+{
+ u16 features;
+
+ features = hellcreek_read(hellcreek, HR_FEABITS0);
+
+ /* Currently we only detect the size of the FDB table */
+ hellcreek->fdb_entries = ((features & HR_FEABITS0_FDBBINS_MASK) >>
+ HR_FEABITS0_FDBBINS_SHIFT) * 32;
+
+ dev_info(hellcreek->dev, "Feature detect: FDB entries=%zu\n",
+ hellcreek->fdb_entries);
+}
+
+static enum dsa_tag_protocol hellcreek_get_tag_protocol(struct dsa_switch *ds,
+ int port,
+ enum dsa_tag_protocol mp)
+{
+ return DSA_TAG_PROTO_HELLCREEK;
+}
+
+static int hellcreek_port_enable(struct dsa_switch *ds, int port,
+ struct phy_device *phy)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ struct hellcreek_port *hellcreek_port;
+ u16 val;
+
+ hellcreek_port = &hellcreek->ports[port];
+
+ dev_dbg(hellcreek->dev, "Enable port %d\n", port);
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ hellcreek_select_port(hellcreek, port);
+ val = hellcreek_port->ptcfg;
+ val |= HR_PTCFG_ADMIN_EN;
+ hellcreek_write(hellcreek, val, HR_PTCFG);
+ hellcreek_port->ptcfg = val;
+
+ mutex_unlock(&hellcreek->reg_lock);
+
+ return 0;
+}
+
+static void hellcreek_port_disable(struct dsa_switch *ds, int port)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ struct hellcreek_port *hellcreek_port;
+ u16 val;
+
+ hellcreek_port = &hellcreek->ports[port];
+
+ dev_dbg(hellcreek->dev, "Disable port %d\n", port);
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ hellcreek_select_port(hellcreek, port);
+ val = hellcreek_port->ptcfg;
+ val &= ~HR_PTCFG_ADMIN_EN;
+ hellcreek_write(hellcreek, val, HR_PTCFG);
+ hellcreek_port->ptcfg = val;
+
+ mutex_unlock(&hellcreek->reg_lock);
+}
+
+static void hellcreek_get_strings(struct dsa_switch *ds, int port,
+ u32 stringset, uint8_t *data)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(hellcreek_counter); ++i) {
+ const struct hellcreek_counter *counter = &hellcreek_counter[i];
+
+ strlcpy(data + i * ETH_GSTRING_LEN,
+ counter->name, ETH_GSTRING_LEN);
+ }
+}
+
+static int hellcreek_get_sset_count(struct dsa_switch *ds, int port, int sset)
+{
+ if (sset != ETH_SS_STATS)
+ return 0;
+
+ return ARRAY_SIZE(hellcreek_counter);
+}
+
+static void hellcreek_get_ethtool_stats(struct dsa_switch *ds, int port,
+ uint64_t *data)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ struct hellcreek_port *hellcreek_port;
+ int i;
+
+ hellcreek_port = &hellcreek->ports[port];
+
+ for (i = 0; i < ARRAY_SIZE(hellcreek_counter); ++i) {
+ const struct hellcreek_counter *counter = &hellcreek_counter[i];
+ u8 offset = counter->offset + port * 64;
+ u16 high, low;
+ u64 value;
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ hellcreek_select_counter(hellcreek, offset);
+
+ /* The registers are locked internally by selecting the
+ * counter. So low and high can be read without reading high
+ * again.
+ */
+ high = hellcreek_read(hellcreek, HR_CRDH);
+ low = hellcreek_read(hellcreek, HR_CRDL);
+ value = ((u64)high << 16) | low;
+
+ hellcreek_port->counter_values[i] += value;
+ data[i] = hellcreek_port->counter_values[i];
+
+ mutex_unlock(&hellcreek->reg_lock);
+ }
+}
+
+static u16 hellcreek_private_vid(int port)
+{
+ return VLAN_N_VID - port + 1;
+}
+
+static int hellcreek_vlan_prepare(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_vlan *vlan)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ int i;
+
+ dev_dbg(hellcreek->dev, "VLAN prepare for port %d\n", port);
+
+ /* Restriction: Make sure that nobody uses the "private" VLANs. These
+ * VLANs are internally used by the driver to ensure port
+ * separation. Thus, they cannot be used by someone else.
+ */
+ for (i = 0; i < hellcreek->pdata->num_ports; ++i) {
+ const u16 restricted_vid = hellcreek_private_vid(i);
+ u16 vid;
+
+ if (!dsa_is_user_port(ds, i))
+ continue;
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid)
+ if (vid == restricted_vid)
+ return -EBUSY;
+ }
+
+ return 0;
+}
+
+static void hellcreek_select_vlan_params(struct hellcreek *hellcreek, int port,
+ int *shift, int *mask)
+{
+ switch (port) {
+ case 0:
+ *shift = HR_VIDMBRCFG_P0MBR_SHIFT;
+ *mask = HR_VIDMBRCFG_P0MBR_MASK;
+ break;
+ case 1:
+ *shift = HR_VIDMBRCFG_P1MBR_SHIFT;
+ *mask = HR_VIDMBRCFG_P1MBR_MASK;
+ break;
+ case 2:
+ *shift = HR_VIDMBRCFG_P2MBR_SHIFT;
+ *mask = HR_VIDMBRCFG_P2MBR_MASK;
+ break;
+ case 3:
+ *shift = HR_VIDMBRCFG_P3MBR_SHIFT;
+ *mask = HR_VIDMBRCFG_P3MBR_MASK;
+ break;
+ default:
+ *shift = *mask = 0;
+ dev_err(hellcreek->dev, "Unknown port %d selected!\n", port);
+ }
+}
+
+static void hellcreek_apply_vlan(struct hellcreek *hellcreek, int port, u16 vid,
+ bool pvid, bool untagged)
+{
+ int shift, mask;
+ u16 val;
+
+ dev_dbg(hellcreek->dev, "Apply VLAN: port=%d vid=%u pvid=%d untagged=%d",
+ port, vid, pvid, untagged);
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ hellcreek_select_port(hellcreek, port);
+ hellcreek_select_vlan(hellcreek, vid, pvid);
+
+ /* Setup port vlan membership */
+ hellcreek_select_vlan_params(hellcreek, port, &shift, &mask);
+ val = hellcreek->vidmbrcfg[vid];
+ val &= ~mask;
+ if (untagged)
+ val |= HELLCREEK_VLAN_UNTAGGED_MEMBER << shift;
+ else
+ val |= HELLCREEK_VLAN_TAGGED_MEMBER << shift;
+
+ hellcreek_write(hellcreek, val, HR_VIDMBRCFG);
+ hellcreek->vidmbrcfg[vid] = val;
+
+ mutex_unlock(&hellcreek->reg_lock);
+}
+
+static void hellcreek_unapply_vlan(struct hellcreek *hellcreek, int port,
+ u16 vid)
+{
+ int shift, mask;
+ u16 val;
+
+ dev_dbg(hellcreek->dev, "Unapply VLAN: port=%d vid=%u\n", port, vid);
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ hellcreek_select_vlan(hellcreek, vid, 0);
+
+ /* Setup port vlan membership */
+ hellcreek_select_vlan_params(hellcreek, port, &shift, &mask);
+ val = hellcreek->vidmbrcfg[vid];
+ val &= ~mask;
+ val |= HELLCREEK_VLAN_NO_MEMBER << shift;
+
+ hellcreek_write(hellcreek, val, HR_VIDMBRCFG);
+ hellcreek->vidmbrcfg[vid] = val;
+
+ mutex_unlock(&hellcreek->reg_lock);
+}
+
+static void hellcreek_vlan_add(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_vlan *vlan)
+{
+ bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+ bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+ struct hellcreek *hellcreek = ds->priv;
+ u16 vid;
+
+ dev_dbg(hellcreek->dev, "Add VLANs (%d -- %d) on port %d, %s, %s\n",
+ vlan->vid_begin, vlan->vid_end, port,
+ untagged ? "untagged" : "tagged",
+ pvid ? "PVID" : "no PVID");
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid)
+ hellcreek_apply_vlan(hellcreek, port, vid, pvid, untagged);
+}
+
+static int hellcreek_vlan_del(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_vlan *vlan)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ u16 vid;
+
+ dev_dbg(hellcreek->dev, "Remove VLANs (%d -- %d) on port %d\n",
+ vlan->vid_begin, vlan->vid_end, port);
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid)
+ hellcreek_unapply_vlan(hellcreek, port, vid);
+
+ return 0;
+}
+
+static void hellcreek_port_stp_state_set(struct dsa_switch *ds, int port,
+ u8 state)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ struct hellcreek_port *hellcreek_port;
+ const char *new_state;
+ u16 val;
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ hellcreek_port = &hellcreek->ports[port];
+ val = hellcreek_port->ptcfg;
+
+ switch (state) {
+ case BR_STATE_DISABLED:
+ new_state = "DISABLED";
+ val |= HR_PTCFG_BLOCKED;
+ val &= ~HR_PTCFG_LEARNING_EN;
+ break;
+ case BR_STATE_BLOCKING:
+ new_state = "BLOCKING";
+ val |= HR_PTCFG_BLOCKED;
+ val &= ~HR_PTCFG_LEARNING_EN;
+ break;
+ case BR_STATE_LISTENING:
+ new_state = "LISTENING";
+ val |= HR_PTCFG_BLOCKED;
+ val &= ~HR_PTCFG_LEARNING_EN;
+ break;
+ case BR_STATE_LEARNING:
+ new_state = "LEARNING";
+ val |= HR_PTCFG_BLOCKED;
+ val |= HR_PTCFG_LEARNING_EN;
+ break;
+ case BR_STATE_FORWARDING:
+ new_state = "FORWARDING";
+ val &= ~HR_PTCFG_BLOCKED;
+ val |= HR_PTCFG_LEARNING_EN;
+ break;
+ default:
+ new_state = "UNKNOWN";
+ }
+
+ hellcreek_select_port(hellcreek, port);
+ hellcreek_write(hellcreek, val, HR_PTCFG);
+ hellcreek_port->ptcfg = val;
+
+ mutex_unlock(&hellcreek->reg_lock);
+
+ dev_dbg(hellcreek->dev, "Configured STP state for port %d: %s\n",
+ port, new_state);
+}
+
+static void hellcreek_setup_ingressflt(struct hellcreek *hellcreek, int port,
+ bool enable)
+{
+ struct hellcreek_port *hellcreek_port = &hellcreek->ports[port];
+ u16 ptcfg;
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ ptcfg = hellcreek_port->ptcfg;
+
+ if (enable)
+ ptcfg |= HR_PTCFG_INGRESSFLT;
+ else
+ ptcfg &= ~HR_PTCFG_INGRESSFLT;
+
+ hellcreek_select_port(hellcreek, port);
+ hellcreek_write(hellcreek, ptcfg, HR_PTCFG);
+ hellcreek_port->ptcfg = ptcfg;
+
+ mutex_unlock(&hellcreek->reg_lock);
+}
+
+static void hellcreek_setup_vlan_awareness(struct hellcreek *hellcreek,
+ bool enable)
+{
+ u16 swcfg;
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ swcfg = hellcreek->swcfg;
+
+ if (enable)
+ swcfg |= HR_SWCFG_VLAN_UNAWARE;
+ else
+ swcfg &= ~HR_SWCFG_VLAN_UNAWARE;
+
+ hellcreek_write(hellcreek, swcfg, HR_SWCFG);
+
+ mutex_unlock(&hellcreek->reg_lock);
+}
+
+/* Default setup for DSA: VLAN <X>: CPU and Port <X> egress untagged. */
+static void hellcreek_setup_vlan_membership(struct dsa_switch *ds, int port,
+ bool enabled)
+{
+ const u16 vid = hellcreek_private_vid(port);
+ int upstream = dsa_upstream_port(ds, port);
+ struct hellcreek *hellcreek = ds->priv;
+
+ /* Apply vid to port as egress untagged and port vlan id */
+ if (enabled)
+ hellcreek_apply_vlan(hellcreek, port, vid, true, true);
+ else
+ hellcreek_unapply_vlan(hellcreek, port, vid);
+
+ /* Apply vid to cpu port as well */
+ if (enabled)
+ hellcreek_apply_vlan(hellcreek, upstream, vid, false, true);
+ else
+ hellcreek_unapply_vlan(hellcreek, upstream, vid);
+}
+
+static int hellcreek_port_bridge_join(struct dsa_switch *ds, int port,
+ struct net_device *br)
+{
+ struct hellcreek *hellcreek = ds->priv;
+
+ dev_dbg(hellcreek->dev, "Port %d joins a bridge\n", port);
+
+ /* When joining a vlan_filtering bridge, keep the switch VLAN aware */
+ if (!ds->vlan_filtering)
+ hellcreek_setup_vlan_awareness(hellcreek, false);
+
+ /* Drop private vlans */
+ hellcreek_setup_vlan_membership(ds, port, false);
+
+ return 0;
+}
+
+static void hellcreek_port_bridge_leave(struct dsa_switch *ds, int port,
+ struct net_device *br)
+{
+ struct hellcreek *hellcreek = ds->priv;
+
+ dev_dbg(hellcreek->dev, "Port %d leaves a bridge\n", port);
+
+ /* Enable VLAN awareness */
+ hellcreek_setup_vlan_awareness(hellcreek, true);
+
+ /* Enable private vlans */
+ hellcreek_setup_vlan_membership(ds, port, true);
+}
+
+static int __hellcreek_fdb_add(struct hellcreek *hellcreek,
+ const struct hellcreek_fdb_entry *entry)
+{
+ u16 meta = 0;
+
+ dev_dbg(hellcreek->dev, "Add static FDB entry: MAC=%pM, MASK=0x%02x, "
+ "OBT=%d, REPRIO_EN=%d, PRIO=%d\n", entry->mac, entry->portmask,
+ entry->is_obt, entry->reprio_en, entry->reprio_tc);
+
+ /* Add mac address */
+ hellcreek_write(hellcreek, entry->mac[1] | (entry->mac[0] << 8), HR_FDBWDH);
+ hellcreek_write(hellcreek, entry->mac[3] | (entry->mac[2] << 8), HR_FDBWDM);
+ hellcreek_write(hellcreek, entry->mac[5] | (entry->mac[4] << 8), HR_FDBWDL);
+
+ /* Meta data */
+ meta |= entry->portmask << HR_FDBWRM0_PORTMASK_SHIFT;
+ if (entry->is_obt)
+ meta |= HR_FDBWRM0_OBT;
+ if (entry->reprio_en) {
+ meta |= HR_FDBWRM0_REPRIO_EN;
+ meta |= entry->reprio_tc << HR_FDBWRM0_REPRIO_TC_SHIFT;
+ }
+ hellcreek_write(hellcreek, meta, HR_FDBWRM0);
+
+ /* Commit */
+ hellcreek_write(hellcreek, 0x00, HR_FDBWRCMD);
+
+ /* Wait until done */
+ return hellcreek_wait_fdb_ready(hellcreek);
+}
+
+static int __hellcreek_fdb_del(struct hellcreek *hellcreek,
+ const struct hellcreek_fdb_entry *entry)
+{
+ dev_dbg(hellcreek->dev, "Delete FDB entry: MAC=%pM!\n", entry->mac);
+
+ /* Delete by matching idx */
+ hellcreek_write(hellcreek, entry->idx | HR_FDBWRCMD_FDBDEL, HR_FDBWRCMD);
+
+ /* Wait until done */
+ return hellcreek_wait_fdb_ready(hellcreek);
+}
+
+/* Retrieve the index of a FDB entry by mac address. Currently we search through
+ * the complete table in hardware. If that's too slow, we might have to cache
+ * the complete FDB table in software.
+ */
+static int hellcreek_fdb_get(struct hellcreek *hellcreek,
+ const unsigned char *dest,
+ struct hellcreek_fdb_entry *entry)
+{
+ size_t i;
+
+ /* Set read pointer to zero: The read of HR_FDBMAX (read-only register)
+ * should reset the internal pointer. But, that doesn't work. The vendor
+ * suggested a subsequent write as workaround. Same for HR_FDBRDH below.
+ */
+ hellcreek_read(hellcreek, HR_FDBMAX);
+ hellcreek_write(hellcreek, 0x00, HR_FDBMAX);
+
+ /* We have to read the complete table, because the switch/driver might
+ * enter new entries anywhere.
+ */
+ for (i = 0; i < hellcreek->fdb_entries; ++i) {
+ unsigned char addr[ETH_ALEN];
+ u16 meta, mac;
+
+ meta = hellcreek_read(hellcreek, HR_FDBMDRD);
+ mac = hellcreek_read(hellcreek, HR_FDBRDL);
+ addr[5] = mac & 0xff;
+ addr[4] = (mac & 0xff00) >> 8;
+ mac = hellcreek_read(hellcreek, HR_FDBRDM);
+ addr[3] = mac & 0xff;
+ addr[2] = (mac & 0xff00) >> 8;
+ mac = hellcreek_read(hellcreek, HR_FDBRDH);
+ addr[1] = mac & 0xff;
+ addr[0] = (mac & 0xff00) >> 8;
+
+ /* Force next entry */
+ hellcreek_write(hellcreek, 0x00, HR_FDBRDH);
+
+ if (memcmp(addr, dest, ETH_ALEN))
+ continue;
+
+ /* Match found */
+ entry->idx = i;
+ entry->portmask = (meta & HR_FDBMDRD_PORTMASK_MASK) >>
+ HR_FDBMDRD_PORTMASK_SHIFT;
+ entry->age = (meta & HR_FDBMDRD_AGE_MASK) >>
+ HR_FDBMDRD_AGE_SHIFT;
+ entry->is_obt = !!(meta & HR_FDBMDRD_OBT);
+ entry->pass_blocked = !!(meta & HR_FDBMDRD_PASS_BLOCKED);
+ entry->is_static = !!(meta & HR_FDBMDRD_STATIC);
+ entry->reprio_tc = (meta & HR_FDBMDRD_REPRIO_TC_MASK) >>
+ HR_FDBMDRD_REPRIO_TC_SHIFT;
+ entry->reprio_en = !!(meta & HR_FDBMDRD_REPRIO_EN);
+ memcpy(entry->mac, addr, sizeof(addr));
+
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+static int hellcreek_fdb_add(struct dsa_switch *ds, int port,
+ const unsigned char *addr, u16 vid)
+{
+ struct hellcreek_fdb_entry entry = { 0 };
+ struct hellcreek *hellcreek = ds->priv;
+ int ret;
+
+ dev_dbg(hellcreek->dev, "Add FDB entry for MAC=%pM\n", addr);
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ ret = hellcreek_fdb_get(hellcreek, addr, &entry);
+ if (ret) {
+ /* Not found */
+ memcpy(entry.mac, addr, sizeof(entry.mac));
+ entry.portmask = BIT(port);
+
+ ret = __hellcreek_fdb_add(hellcreek, &entry);
+ if (ret) {
+ dev_err(hellcreek->dev, "Failed to add FDB entry!\n");
+ goto out;
+ }
+ } else {
+ /* Found */
+ ret = __hellcreek_fdb_del(hellcreek, &entry);
+ if (ret) {
+ dev_err(hellcreek->dev, "Failed to delete FDB entry!\n");
+ goto out;
+ }
+
+ entry.portmask |= BIT(port);
+
+ ret = __hellcreek_fdb_add(hellcreek, &entry);
+ if (ret) {
+ dev_err(hellcreek->dev, "Failed to add FDB entry!\n");
+ goto out;
+ }
+ }
+
+out:
+ mutex_unlock(&hellcreek->reg_lock);
+
+ return ret;
+}
+
+static int hellcreek_fdb_del(struct dsa_switch *ds, int port,
+ const unsigned char *addr, u16 vid)
+{
+ struct hellcreek_fdb_entry entry = { 0 };
+ struct hellcreek *hellcreek = ds->priv;
+ int ret;
+
+ dev_dbg(hellcreek->dev, "Delete FDB entry for MAC=%pM\n", addr);
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ ret = hellcreek_fdb_get(hellcreek, addr, &entry);
+ if (ret) {
+ /* Not found */
+ dev_err(hellcreek->dev, "FDB entry for deletion not found!\n");
+ } else {
+ /* Found */
+ ret = __hellcreek_fdb_del(hellcreek, &entry);
+ if (ret) {
+ dev_err(hellcreek->dev, "Failed to delete FDB entry!\n");
+ goto out;
+ }
+
+ entry.portmask &= ~BIT(port);
+
+ if (entry.portmask != 0x00) {
+ ret = __hellcreek_fdb_add(hellcreek, &entry);
+ if (ret) {
+ dev_err(hellcreek->dev, "Failed to add FDB entry!\n");
+ goto out;
+ }
+ }
+ }
+
+out:
+ mutex_unlock(&hellcreek->reg_lock);
+
+ return ret;
+}
+
+static int hellcreek_fdb_dump(struct dsa_switch *ds, int port,
+ dsa_fdb_dump_cb_t *cb, void *data)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ u16 entries;
+ size_t i;
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ /* Set read pointer to zero: The read of HR_FDBMAX (read-only register)
+ * should reset the internal pointer. But, that doesn't work. The vendor
+ * suggested a subsequent write as workaround. Same for HR_FDBRDH below.
+ */
+ entries = hellcreek_read(hellcreek, HR_FDBMAX);
+ hellcreek_write(hellcreek, 0x00, HR_FDBMAX);
+
+ dev_dbg(hellcreek->dev, "FDB dump for port %d, entries=%d!\n", port, entries);
+
+ /* Read table */
+ for (i = 0; i < hellcreek->fdb_entries; ++i) {
+ unsigned char null_addr[ETH_ALEN] = { 0 };
+ struct hellcreek_fdb_entry entry = { 0 };
+ u16 meta, mac;
+
+ meta = hellcreek_read(hellcreek, HR_FDBMDRD);
+ mac = hellcreek_read(hellcreek, HR_FDBRDL);
+ entry.mac[5] = mac & 0xff;
+ entry.mac[4] = (mac & 0xff00) >> 8;
+ mac = hellcreek_read(hellcreek, HR_FDBRDM);
+ entry.mac[3] = mac & 0xff;
+ entry.mac[2] = (mac & 0xff00) >> 8;
+ mac = hellcreek_read(hellcreek, HR_FDBRDH);
+ entry.mac[1] = mac & 0xff;
+ entry.mac[0] = (mac & 0xff00) >> 8;
+
+ /* Force next entry */
+ hellcreek_write(hellcreek, 0x00, HR_FDBRDH);
+
+ /* Check valid */
+ if (!memcmp(entry.mac, null_addr, ETH_ALEN))
+ continue;
+
+ entry.portmask = (meta & HR_FDBMDRD_PORTMASK_MASK) >>
+ HR_FDBMDRD_PORTMASK_SHIFT;
+ entry.is_static = !!(meta & HR_FDBMDRD_STATIC);
+
+ /* Check port mask */
+ if (!(entry.portmask & BIT(port)))
+ continue;
+
+ cb(entry.mac, 0, entry.is_static, data);
+ }
+
+ mutex_unlock(&hellcreek->reg_lock);
+
+ return 0;
+}
+
+static int hellcreek_vlan_filtering(struct dsa_switch *ds, int port,
+ bool vlan_filtering,
+ struct switchdev_trans *trans)
+{
+ struct hellcreek *hellcreek = ds->priv;
+
+ if (switchdev_trans_ph_prepare(trans))
+ return 0;
+
+ dev_dbg(hellcreek->dev, "%s VLAN filtering on port %d\n",
+ vlan_filtering ? "Enable" : "Disable", port);
+
+ /* Configure port to drop packages with not known vids */
+ hellcreek_setup_ingressflt(hellcreek, port, vlan_filtering);
+
+ /* Enable VLAN awareness on the switch. This save due to
+ * ds->vlan_filtering_is_global.
+ */
+ hellcreek_setup_vlan_awareness(hellcreek, vlan_filtering);
+
+ return 0;
+}
+
+static int hellcreek_enable_ip_core(struct hellcreek *hellcreek)
+{
+ int ret;
+ u16 val;
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ val = hellcreek_read(hellcreek, HR_CTRL_C);
+ val |= HR_CTRL_C_ENABLE;
+ hellcreek_write(hellcreek, val, HR_CTRL_C);
+ ret = hellcreek_wait_until_transitioned(hellcreek);
+
+ mutex_unlock(&hellcreek->reg_lock);
+
+ return ret;
+}
+
+static void hellcreek_setup_cpu_and_tunnel_port(struct hellcreek *hellcreek)
+{
+ struct hellcreek_port *tunnel_port = &hellcreek->ports[TUNNEL_PORT];
+ struct hellcreek_port *cpu_port = &hellcreek->ports[CPU_PORT];
+ u16 ptcfg = 0;
+
+ ptcfg |= HR_PTCFG_LEARNING_EN | HR_PTCFG_ADMIN_EN;
+
+ mutex_lock(&hellcreek->reg_lock);
+
+ hellcreek_select_port(hellcreek, CPU_PORT);
+ hellcreek_write(hellcreek, ptcfg, HR_PTCFG);
+
+ hellcreek_select_port(hellcreek, TUNNEL_PORT);
+ hellcreek_write(hellcreek, ptcfg, HR_PTCFG);
+
+ cpu_port->ptcfg = ptcfg;
+ tunnel_port->ptcfg = ptcfg;
+
+ mutex_unlock(&hellcreek->reg_lock);
+}
+
+static void hellcreek_setup_tc_identity_mapping(struct hellcreek *hellcreek)
+{
+ int i;
+
+ /* The switch has multiple egress queues per port. The queue is selected
+ * via the PCP field in the VLAN header. The switch internally deals
+ * with traffic classes instead of PCP values and this mapping is
+ * configurable.
+ *
+ * The default mapping is (PCP - TC):
+ * 7 - 7
+ * 6 - 6
+ * 5 - 5
+ * 4 - 4
+ * 3 - 3
+ * 2 - 1
+ * 1 - 0
+ * 0 - 2
+ *
+ * The default should be an identity mapping.
+ */
+
+ for (i = 0; i < 8; ++i) {
+ mutex_lock(&hellcreek->reg_lock);
+
+ hellcreek_select_prio(hellcreek, i);
+ hellcreek_write(hellcreek,
+ i << HR_PRTCCFG_PCP_TC_MAP_SHIFT,
+ HR_PRTCCFG);
+
+ mutex_unlock(&hellcreek->reg_lock);
+ }
+}
+
+static int hellcreek_setup_fdb(struct hellcreek *hellcreek)
+{
+ static struct hellcreek_fdb_entry ptp = {
+ /* MAC: 01-1B-19-00-00-00 */
+ .mac = { 0x01, 0x1b, 0x19, 0x00, 0x00, 0x00 },
+ .portmask = 0x03, /* Management ports */
+ .age = 0,
+ .is_obt = 0,
+ .pass_blocked = 0,
+ .is_static = 1,
+ .reprio_tc = 6, /* TC: 6 as per IEEE 802.1AS */
+ .reprio_en = 1,
+ };
+ static struct hellcreek_fdb_entry p2p = {
+ /* MAC: 01-80-C2-00-00-0E */
+ .mac = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x0e },
+ .portmask = 0x03, /* Management ports */
+ .age = 0,
+ .is_obt = 0,
+ .pass_blocked = 0,
+ .is_static = 1,
+ .reprio_tc = 6, /* TC: 6 as per IEEE 802.1AS */
+ .reprio_en = 1,
+ };
+ int ret;
+
+ mutex_lock(&hellcreek->reg_lock);
+ ret = __hellcreek_fdb_add(hellcreek, &ptp);
+ if (ret)
+ goto out;
+ ret = __hellcreek_fdb_add(hellcreek, &p2p);
+out:
+ mutex_unlock(&hellcreek->reg_lock);
+
+ return ret;
+}
+
+static int hellcreek_setup(struct dsa_switch *ds)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ u16 swcfg = 0;
+ int ret, i;
+
+ dev_dbg(hellcreek->dev, "Set up the switch\n");
+
+ /* Let's go */
+ ret = hellcreek_enable_ip_core(hellcreek);
+ if (ret) {
+ dev_err(hellcreek->dev, "Failed to enable IP core!\n");
+ return ret;
+ }
+
+ /* Enable CPU/Tunnel ports */
+ hellcreek_setup_cpu_and_tunnel_port(hellcreek);
+
+ /* Switch config: Keep defaults, enable FDB aging and learning and tag
+ * each frame from/to cpu port for DSA tagging. Also enable the length
+ * aware shaping mode. This eliminates the need for Qbv guard bands.
+ */
+ swcfg |= HR_SWCFG_FDBAGE_EN |
+ HR_SWCFG_FDBLRN_EN |
+ HR_SWCFG_ALWAYS_OBT |
+ (HR_SWCFG_LAS_ON << HR_SWCFG_LAS_MODE_SHIFT);
+ hellcreek->swcfg = swcfg;
+ hellcreek_write(hellcreek, swcfg, HR_SWCFG);
+
+ /* Initial vlan membership to reflect port separation */
+ for (i = 0; i < ds->num_ports; ++i) {
+ if (!dsa_is_user_port(ds, i))
+ continue;
+
+ hellcreek_setup_vlan_membership(ds, i, true);
+ }
+
+ /* Configure PCP <-> TC mapping */
+ hellcreek_setup_tc_identity_mapping(hellcreek);
+
+ /* Allow VLAN configurations while not filtering which is the default
+ * for new DSA drivers.
+ */
+ ds->configure_vlan_while_not_filtering = true;
+
+ /* The VLAN awareness is a global switch setting. Therefore, mixed vlan
+ * filtering setups are not supported.
+ */
+ ds->vlan_filtering_is_global = true;
+
+ /* Intercept _all_ PTP multicast traffic */
+ ret = hellcreek_setup_fdb(hellcreek);
+ if (ret) {
+ dev_err(hellcreek->dev,
+ "Failed to insert static PTP FDB entries\n");
+ return ret;
+ }
+
+ return 0;
+}
+
+static void hellcreek_phylink_validate(struct dsa_switch *ds, int port,
+ unsigned long *supported,
+ struct phylink_link_state *state)
+{
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+ struct hellcreek *hellcreek = ds->priv;
+
+ dev_dbg(hellcreek->dev, "Phylink validate for port %d\n", port);
+
+ /* The MAC settings are a hardware configuration option and cannot be
+ * changed at run time or by strapping. Therefore the attached PHYs
+ * should be programmed to only advertise settings which are supported
+ * by the hardware.
+ */
+ if (hellcreek->pdata->is_100_mbits)
+ phylink_set(mask, 100baseT_Full);
+ else
+ phylink_set(mask, 1000baseT_Full);
+
+ bitmap_and(supported, supported, mask,
+ __ETHTOOL_LINK_MODE_MASK_NBITS);
+ bitmap_and(state->advertising, state->advertising, mask,
+ __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
+static int
+hellcreek_port_prechangeupper(struct dsa_switch *ds, int port,
+ struct netdev_notifier_changeupper_info *info)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ bool used = true;
+ int ret = -EBUSY;
+ u16 vid;
+ int i;
+
+ dev_dbg(hellcreek->dev, "Pre change upper for port %d\n", port);
+
+ /*
+ * Deny VLAN devices on top of lan ports with the same VLAN ids, because
+ * it breaks the port separation due to the private VLANs. Example:
+ *
+ * lan0.100 *and* lan1.100 cannot be used in parallel. However, lan0.99
+ * and lan1.100 works.
+ */
+
+ if (!is_vlan_dev(info->upper_dev))
+ return 0;
+
+ vid = vlan_dev_vlan_id(info->upper_dev);
+
+ /* For all ports, check bitmaps */
+ mutex_lock(&hellcreek->vlan_lock);
+ for (i = 0; i < hellcreek->pdata->num_ports; ++i) {
+ if (!dsa_is_user_port(ds, i))
+ continue;
+
+ if (port == i)
+ continue;
+
+ used = used && test_bit(vid, hellcreek->ports[i].vlan_dev_bitmap);
+ }
+
+ if (used)
+ goto out;
+
+ /* Update bitmap */
+ set_bit(vid, hellcreek->ports[port].vlan_dev_bitmap);
+
+ ret = 0;
+
+out:
+ mutex_unlock(&hellcreek->vlan_lock);
+
+ return ret;
+}
+
+static const struct dsa_switch_ops hellcreek_ds_ops = {
+ .get_ethtool_stats = hellcreek_get_ethtool_stats,
+ .get_sset_count = hellcreek_get_sset_count,
+ .get_strings = hellcreek_get_strings,
+ .get_tag_protocol = hellcreek_get_tag_protocol,
+ .get_ts_info = hellcreek_get_ts_info,
+ .phylink_validate = hellcreek_phylink_validate,
+ .port_bridge_join = hellcreek_port_bridge_join,
+ .port_bridge_leave = hellcreek_port_bridge_leave,
+ .port_disable = hellcreek_port_disable,
+ .port_enable = hellcreek_port_enable,
+ .port_fdb_add = hellcreek_fdb_add,
+ .port_fdb_del = hellcreek_fdb_del,
+ .port_fdb_dump = hellcreek_fdb_dump,
+ .port_hwtstamp_set = hellcreek_port_hwtstamp_set,
+ .port_hwtstamp_get = hellcreek_port_hwtstamp_get,
+ .port_prechangeupper = hellcreek_port_prechangeupper,
+ .port_rxtstamp = hellcreek_port_rxtstamp,
+ .port_stp_state_set = hellcreek_port_stp_state_set,
+ .port_txtstamp = hellcreek_port_txtstamp,
+ .port_vlan_add = hellcreek_vlan_add,
+ .port_vlan_del = hellcreek_vlan_del,
+ .port_vlan_filtering = hellcreek_vlan_filtering,
+ .port_vlan_prepare = hellcreek_vlan_prepare,
+ .setup = hellcreek_setup,
+};
+
+static int hellcreek_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct hellcreek *hellcreek;
+ struct resource *res;
+ int ret, i;
+
+ hellcreek = devm_kzalloc(dev, sizeof(*hellcreek), GFP_KERNEL);
+ if (!hellcreek)
+ return -ENOMEM;
+
+ hellcreek->vidmbrcfg = devm_kcalloc(dev, VLAN_N_VID,
+ sizeof(*hellcreek->vidmbrcfg),
+ GFP_KERNEL);
+ if (!hellcreek->vidmbrcfg)
+ return -ENOMEM;
+
+ hellcreek->pdata = of_device_get_match_data(dev);
+
+ hellcreek->ports = devm_kcalloc(dev, hellcreek->pdata->num_ports,
+ sizeof(*hellcreek->ports),
+ GFP_KERNEL);
+ if (!hellcreek->ports)
+ return -ENOMEM;
+
+ for (i = 0; i < hellcreek->pdata->num_ports; ++i) {
+ struct hellcreek_port *port = &hellcreek->ports[i];
+
+ port->counter_values =
+ devm_kcalloc(dev,
+ ARRAY_SIZE(hellcreek_counter),
+ sizeof(*port->counter_values),
+ GFP_KERNEL);
+ if (!port->counter_values)
+ return -ENOMEM;
+
+ port->vlan_dev_bitmap =
+ devm_kcalloc(dev,
+ BITS_TO_LONGS(VLAN_N_VID),
+ sizeof(unsigned long),
+ GFP_KERNEL);
+ if (!port->vlan_dev_bitmap)
+ return -ENOMEM;
+
+ port->hellcreek = hellcreek;
+ port->port = i;
+ }
+
+ mutex_init(&hellcreek->reg_lock);
+ mutex_init(&hellcreek->vlan_lock);
+ mutex_init(&hellcreek->ptp_lock);
+
+ hellcreek->dev = dev;
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "tsn");
+ if (!res) {
+ dev_err(dev, "No memory region provided!\n");
+ return -ENODEV;
+ }
+
+ hellcreek->base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(hellcreek->base)) {
+ dev_err(dev, "No memory available!\n");
+ return PTR_ERR(hellcreek->base);
+ }
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ptp");
+ if (!res) {
+ dev_err(dev, "No PTP memory region provided!\n");
+ return -ENODEV;
+ }
+
+ hellcreek->ptp_base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(hellcreek->ptp_base)) {
+ dev_err(dev, "No memory available!\n");
+ return PTR_ERR(hellcreek->ptp_base);
+ }
+
+ ret = hellcreek_detect(hellcreek);
+ if (ret) {
+ dev_err(dev, "No (known) chip found!\n");
+ return ret;
+ }
+
+ ret = hellcreek_wait_until_ready(hellcreek);
+ if (ret) {
+ dev_err(dev, "Switch didn't become ready!\n");
+ return ret;
+ }
+
+ hellcreek_feature_detect(hellcreek);
+
+ hellcreek->ds = devm_kzalloc(dev, sizeof(*hellcreek->ds), GFP_KERNEL);
+ if (!hellcreek->ds)
+ return -ENOMEM;
+
+ hellcreek->ds->dev = dev;
+ hellcreek->ds->priv = hellcreek;
+ hellcreek->ds->ops = &hellcreek_ds_ops;
+ hellcreek->ds->num_ports = hellcreek->pdata->num_ports;
+ hellcreek->ds->num_tx_queues = HELLCREEK_NUM_EGRESS_QUEUES;
+
+ ret = dsa_register_switch(hellcreek->ds);
+ if (ret) {
+ dev_err_probe(dev, ret, "Unable to register switch\n");
+ return ret;
+ }
+
+ ret = hellcreek_ptp_setup(hellcreek);
+ if (ret) {
+ dev_err(dev, "Failed to setup PTP!\n");
+ goto err_ptp_setup;
+ }
+
+ ret = hellcreek_hwtstamp_setup(hellcreek);
+ if (ret) {
+ dev_err(dev, "Failed to setup hardware timestamping!\n");
+ goto err_tstamp_setup;
+ }
+
+ platform_set_drvdata(pdev, hellcreek);
+
+ return 0;
+
+err_tstamp_setup:
+ hellcreek_ptp_free(hellcreek);
+err_ptp_setup:
+ dsa_unregister_switch(hellcreek->ds);
+
+ return ret;
+}
+
+static int hellcreek_remove(struct platform_device *pdev)
+{
+ struct hellcreek *hellcreek = platform_get_drvdata(pdev);
+
+ hellcreek_hwtstamp_free(hellcreek);
+ hellcreek_ptp_free(hellcreek);
+ dsa_unregister_switch(hellcreek->ds);
+ platform_set_drvdata(pdev, NULL);
+
+ return 0;
+}
+
+static const struct hellcreek_platform_data de1soc_r1_pdata = {
+ .num_ports = 4,
+ .is_100_mbits = 1,
+ .qbv_support = 1,
+ .qbv_on_cpu_port = 1,
+ .qbu_support = 0,
+ .module_id = 0x4c30,
+};
+
+static const struct of_device_id hellcreek_of_match[] = {
+ {
+ .compatible = "hirschmann,hellcreek-de1soc-r1",
+ .data = &de1soc_r1_pdata,
+ },
+ { /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, hellcreek_of_match);
+
+static struct platform_driver hellcreek_driver = {
+ .probe = hellcreek_probe,
+ .remove = hellcreek_remove,
+ .driver = {
+ .name = "hellcreek",
+ .of_match_table = hellcreek_of_match,
+ },
+};
+module_platform_driver(hellcreek_driver);
+
+MODULE_AUTHOR("Kurt Kanzenbach <kurt@linutronix.de>");
+MODULE_DESCRIPTION("Hirschmann Hellcreek driver");
+MODULE_LICENSE("Dual MIT/GPL");
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 or MIT) */
+/*
+ * DSA driver for:
+ * Hirschmann Hellcreek TSN switch.
+ *
+ * Copyright (C) 2019,2020 Linutronix GmbH
+ * Author Kurt Kanzenbach <kurt@linutronix.de>
+ */
+
+#ifndef _HELLCREEK_H_
+#define _HELLCREEK_H_
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/leds.h>
+#include <linux/platform_data/hirschmann-hellcreek.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/timecounter.h>
+#include <net/dsa.h>
+
+/* Ports:
+ * - 0: CPU
+ * - 1: Tunnel
+ * - 2: TSN front port 1
+ * - 3: TSN front port 2
+ * - ...
+ */
+#define CPU_PORT 0
+#define TUNNEL_PORT 1
+
+#define HELLCREEK_VLAN_NO_MEMBER 0x0
+#define HELLCREEK_VLAN_UNTAGGED_MEMBER 0x1
+#define HELLCREEK_VLAN_TAGGED_MEMBER 0x3
+#define HELLCREEK_NUM_EGRESS_QUEUES 8
+
+/* Register definitions */
+#define HR_MODID_C (0 * 2)
+#define HR_REL_L_C (1 * 2)
+#define HR_REL_H_C (2 * 2)
+#define HR_BLD_L_C (3 * 2)
+#define HR_BLD_H_C (4 * 2)
+#define HR_CTRL_C (5 * 2)
+#define HR_CTRL_C_READY BIT(14)
+#define HR_CTRL_C_TRANSITION BIT(13)
+#define HR_CTRL_C_ENABLE BIT(0)
+
+#define HR_PSEL (0xa6 * 2)
+#define HR_PSEL_PTWSEL_SHIFT 4
+#define HR_PSEL_PTWSEL_MASK GENMASK(5, 4)
+#define HR_PSEL_PRTCWSEL_SHIFT 0
+#define HR_PSEL_PRTCWSEL_MASK GENMASK(2, 0)
+
+#define HR_PTCFG (0xa7 * 2)
+#define HR_PTCFG_MLIMIT_EN BIT(13)
+#define HR_PTCFG_UMC_FLT BIT(10)
+#define HR_PTCFG_UUC_FLT BIT(9)
+#define HR_PTCFG_UNTRUST BIT(8)
+#define HR_PTCFG_TAG_REQUIRED BIT(7)
+#define HR_PTCFG_PPRIO_SHIFT 4
+#define HR_PTCFG_PPRIO_MASK GENMASK(6, 4)
+#define HR_PTCFG_INGRESSFLT BIT(3)
+#define HR_PTCFG_BLOCKED BIT(2)
+#define HR_PTCFG_LEARNING_EN BIT(1)
+#define HR_PTCFG_ADMIN_EN BIT(0)
+
+#define HR_PRTCCFG (0xa8 * 2)
+#define HR_PRTCCFG_PCP_TC_MAP_SHIFT 0
+#define HR_PRTCCFG_PCP_TC_MAP_MASK GENMASK(2, 0)
+
+#define HR_CSEL (0x8d * 2)
+#define HR_CSEL_SHIFT 0
+#define HR_CSEL_MASK GENMASK(7, 0)
+#define HR_CRDL (0x8e * 2)
+#define HR_CRDH (0x8f * 2)
+
+#define HR_SWTRC_CFG (0x90 * 2)
+#define HR_SWTRC0 (0x91 * 2)
+#define HR_SWTRC1 (0x92 * 2)
+#define HR_PFREE (0x93 * 2)
+#define HR_MFREE (0x94 * 2)
+
+#define HR_FDBAGE (0x97 * 2)
+#define HR_FDBMAX (0x98 * 2)
+#define HR_FDBRDL (0x99 * 2)
+#define HR_FDBRDM (0x9a * 2)
+#define HR_FDBRDH (0x9b * 2)
+
+#define HR_FDBMDRD (0x9c * 2)
+#define HR_FDBMDRD_PORTMASK_SHIFT 0
+#define HR_FDBMDRD_PORTMASK_MASK GENMASK(3, 0)
+#define HR_FDBMDRD_AGE_SHIFT 4
+#define HR_FDBMDRD_AGE_MASK GENMASK(7, 4)
+#define HR_FDBMDRD_OBT BIT(8)
+#define HR_FDBMDRD_PASS_BLOCKED BIT(9)
+#define HR_FDBMDRD_STATIC BIT(11)
+#define HR_FDBMDRD_REPRIO_TC_SHIFT 12
+#define HR_FDBMDRD_REPRIO_TC_MASK GENMASK(14, 12)
+#define HR_FDBMDRD_REPRIO_EN BIT(15)
+
+#define HR_FDBWDL (0x9d * 2)
+#define HR_FDBWDM (0x9e * 2)
+#define HR_FDBWDH (0x9f * 2)
+#define HR_FDBWRM0 (0xa0 * 2)
+#define HR_FDBWRM0_PORTMASK_SHIFT 0
+#define HR_FDBWRM0_PORTMASK_MASK GENMASK(3, 0)
+#define HR_FDBWRM0_OBT BIT(8)
+#define HR_FDBWRM0_PASS_BLOCKED BIT(9)
+#define HR_FDBWRM0_REPRIO_TC_SHIFT 12
+#define HR_FDBWRM0_REPRIO_TC_MASK GENMASK(14, 12)
+#define HR_FDBWRM0_REPRIO_EN BIT(15)
+#define HR_FDBWRM1 (0xa1 * 2)
+
+#define HR_FDBWRCMD (0xa2 * 2)
+#define HR_FDBWRCMD_FDBDEL BIT(9)
+
+#define HR_SWCFG (0xa3 * 2)
+#define HR_SWCFG_GM_STATEMD BIT(15)
+#define HR_SWCFG_LAS_MODE_SHIFT 12
+#define HR_SWCFG_LAS_MODE_MASK GENMASK(13, 12)
+#define HR_SWCFG_LAS_OFF (0x00)
+#define HR_SWCFG_LAS_ON (0x01)
+#define HR_SWCFG_LAS_STATIC (0x10)
+#define HR_SWCFG_CT_EN BIT(11)
+#define HR_SWCFG_VLAN_UNAWARE BIT(10)
+#define HR_SWCFG_ALWAYS_OBT BIT(9)
+#define HR_SWCFG_FDBAGE_EN BIT(5)
+#define HR_SWCFG_FDBLRN_EN BIT(4)
+
+#define HR_SWSTAT (0xa4 * 2)
+#define HR_SWSTAT_FAIL BIT(4)
+#define HR_SWSTAT_BUSY BIT(0)
+
+#define HR_SWCMD (0xa5 * 2)
+#define HW_SWCMD_FLUSH BIT(0)
+
+#define HR_VIDCFG (0xaa * 2)
+#define HR_VIDCFG_VID_SHIFT 0
+#define HR_VIDCFG_VID_MASK GENMASK(11, 0)
+#define HR_VIDCFG_PVID BIT(12)
+
+#define HR_VIDMBRCFG (0xab * 2)
+#define HR_VIDMBRCFG_P0MBR_SHIFT 0
+#define HR_VIDMBRCFG_P0MBR_MASK GENMASK(1, 0)
+#define HR_VIDMBRCFG_P1MBR_SHIFT 2
+#define HR_VIDMBRCFG_P1MBR_MASK GENMASK(3, 2)
+#define HR_VIDMBRCFG_P2MBR_SHIFT 4
+#define HR_VIDMBRCFG_P2MBR_MASK GENMASK(5, 4)
+#define HR_VIDMBRCFG_P3MBR_SHIFT 6
+#define HR_VIDMBRCFG_P3MBR_MASK GENMASK(7, 6)
+
+#define HR_FEABITS0 (0xac * 2)
+#define HR_FEABITS0_FDBBINS_SHIFT 4
+#define HR_FEABITS0_FDBBINS_MASK GENMASK(7, 4)
+#define HR_FEABITS0_PCNT_SHIFT 8
+#define HR_FEABITS0_PCNT_MASK GENMASK(11, 8)
+#define HR_FEABITS0_MCNT_SHIFT 12
+#define HR_FEABITS0_MCNT_MASK GENMASK(15, 12)
+
+#define TR_QTRACK (0xb1 * 2)
+#define TR_TGDVER (0xb3 * 2)
+#define TR_TGDVER_REV_MIN_MASK GENMASK(7, 0)
+#define TR_TGDVER_REV_MIN_SHIFT 0
+#define TR_TGDVER_REV_MAJ_MASK GENMASK(15, 8)
+#define TR_TGDVER_REV_MAJ_SHIFT 8
+#define TR_TGDSEL (0xb4 * 2)
+#define TR_TGDSEL_TDGSEL_MASK GENMASK(1, 0)
+#define TR_TGDSEL_TDGSEL_SHIFT 0
+#define TR_TGDCTRL (0xb5 * 2)
+#define TR_TGDCTRL_GATE_EN BIT(0)
+#define TR_TGDCTRL_CYC_SNAP BIT(4)
+#define TR_TGDCTRL_SNAP_EST BIT(5)
+#define TR_TGDCTRL_ADMINGATESTATES_MASK GENMASK(15, 8)
+#define TR_TGDCTRL_ADMINGATESTATES_SHIFT 8
+#define TR_TGDSTAT0 (0xb6 * 2)
+#define TR_TGDSTAT1 (0xb7 * 2)
+#define TR_ESTWRL (0xb8 * 2)
+#define TR_ESTWRH (0xb9 * 2)
+#define TR_ESTCMD (0xba * 2)
+#define TR_ESTCMD_ESTSEC_MASK GENMASK(2, 0)
+#define TR_ESTCMD_ESTSEC_SHIFT 0
+#define TR_ESTCMD_ESTARM BIT(4)
+#define TR_ESTCMD_ESTSWCFG BIT(5)
+#define TR_EETWRL (0xbb * 2)
+#define TR_EETWRH (0xbc * 2)
+#define TR_EETCMD (0xbd * 2)
+#define TR_EETCMD_EETSEC_MASK GEMASK(2, 0)
+#define TR_EETCMD_EETSEC_SHIFT 0
+#define TR_EETCMD_EETARM BIT(4)
+#define TR_CTWRL (0xbe * 2)
+#define TR_CTWRH (0xbf * 2)
+#define TR_LCNSL (0xc1 * 2)
+#define TR_LCNSH (0xc2 * 2)
+#define TR_LCS (0xc3 * 2)
+#define TR_GCLDAT (0xc4 * 2)
+#define TR_GCLDAT_GCLWRGATES_MASK GENMASK(7, 0)
+#define TR_GCLDAT_GCLWRGATES_SHIFT 0
+#define TR_GCLDAT_GCLWRLAST BIT(8)
+#define TR_GCLDAT_GCLOVRI BIT(9)
+#define TR_GCLTIL (0xc5 * 2)
+#define TR_GCLTIH (0xc6 * 2)
+#define TR_GCLCMD (0xc7 * 2)
+#define TR_GCLCMD_GCLWRADR_MASK GENMASK(7, 0)
+#define TR_GCLCMD_GCLWRADR_SHIFT 0
+#define TR_GCLCMD_INIT_GATE_STATES_MASK GENMASK(15, 8)
+#define TR_GCLCMD_INIT_GATE_STATES_SHIFT 8
+
+struct hellcreek_counter {
+ u8 offset;
+ const char *name;
+};
+
+struct hellcreek;
+
+/* State flags for hellcreek_port_hwtstamp::state */
+enum {
+ HELLCREEK_HWTSTAMP_ENABLED,
+ HELLCREEK_HWTSTAMP_TX_IN_PROGRESS,
+};
+
+/* A structure to hold hardware timestamping information per port */
+struct hellcreek_port_hwtstamp {
+ /* Timestamping state */
+ unsigned long state;
+
+ /* Resources for receive timestamping */
+ struct sk_buff_head rx_queue; /* For synchronization messages */
+
+ /* Resources for transmit timestamping */
+ unsigned long tx_tstamp_start;
+ struct sk_buff *tx_skb;
+
+ /* Current timestamp configuration */
+ struct hwtstamp_config tstamp_config;
+};
+
+struct hellcreek_port {
+ struct hellcreek *hellcreek;
+ unsigned long *vlan_dev_bitmap;
+ int port;
+ u16 ptcfg; /* ptcfg shadow */
+ u64 *counter_values;
+
+ /* Per-port timestamping resources */
+ struct hellcreek_port_hwtstamp port_hwtstamp;
+};
+
+struct hellcreek_fdb_entry {
+ size_t idx;
+ unsigned char mac[ETH_ALEN];
+ u8 portmask;
+ u8 age;
+ u8 is_obt;
+ u8 pass_blocked;
+ u8 is_static;
+ u8 reprio_tc;
+ u8 reprio_en;
+};
+
+struct hellcreek {
+ const struct hellcreek_platform_data *pdata;
+ struct device *dev;
+ struct dsa_switch *ds;
+ struct ptp_clock *ptp_clock;
+ struct ptp_clock_info ptp_clock_info;
+ struct hellcreek_port *ports;
+ struct delayed_work overflow_work;
+ struct led_classdev led_is_gm;
+ struct led_classdev led_sync_good;
+ struct mutex reg_lock; /* Switch IP register lock */
+ struct mutex vlan_lock; /* VLAN bitmaps lock */
+ struct mutex ptp_lock; /* PTP IP register lock */
+ void __iomem *base;
+ void __iomem *ptp_base;
+ u16 swcfg; /* swcfg shadow */
+ u8 *vidmbrcfg; /* vidmbrcfg shadow */
+ u64 seconds; /* PTP seconds */
+ u64 last_ts; /* Used for overflow detection */
+ u16 status_out; /* ptp.status_out shadow */
+ size_t fdb_entries;
+};
+
+#endif /* _HELLCREEK_H_ */
--- /dev/null
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * DSA driver for:
+ * Hirschmann Hellcreek TSN switch.
+ *
+ * Copyright (C) 2019,2020 Hochschule Offenburg
+ * Copyright (C) 2019,2020 Linutronix GmbH
+ * Authors: Kamil Alkhouri <kamil.alkhouri@hs-offenburg.de>
+ * Kurt Kanzenbach <kurt@linutronix.de>
+ */
+
+#include <linux/ptp_classify.h>
+
+#include "hellcreek.h"
+#include "hellcreek_hwtstamp.h"
+#include "hellcreek_ptp.h"
+
+int hellcreek_get_ts_info(struct dsa_switch *ds, int port,
+ struct ethtool_ts_info *info)
+{
+ struct hellcreek *hellcreek = ds->priv;
+
+ info->phc_index = hellcreek->ptp_clock ?
+ ptp_clock_index(hellcreek->ptp_clock) : -1;
+ info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+ SOF_TIMESTAMPING_RX_HARDWARE |
+ SOF_TIMESTAMPING_RAW_HARDWARE;
+
+ /* enabled tx timestamping */
+ info->tx_types = BIT(HWTSTAMP_TX_ON);
+
+ /* L2 & L4 PTPv2 event rx messages are timestamped */
+ info->rx_filters = BIT(HWTSTAMP_FILTER_PTP_V2_EVENT);
+
+ return 0;
+}
+
+/* Enabling/disabling TX and RX HW timestamping for different PTP messages is
+ * not available in the switch. Thus, this function only serves as a check if
+ * the user requested what is actually available or not
+ */
+static int hellcreek_set_hwtstamp_config(struct hellcreek *hellcreek, int port,
+ struct hwtstamp_config *config)
+{
+ struct hellcreek_port_hwtstamp *ps =
+ &hellcreek->ports[port].port_hwtstamp;
+ bool tx_tstamp_enable = false;
+ bool rx_tstamp_enable = false;
+
+ /* Interaction with the timestamp hardware is prevented here. It is
+ * enabled when this config function ends successfully
+ */
+ clear_bit_unlock(HELLCREEK_HWTSTAMP_ENABLED, &ps->state);
+
+ /* Reserved for future extensions */
+ if (config->flags)
+ return -EINVAL;
+
+ switch (config->tx_type) {
+ case HWTSTAMP_TX_ON:
+ tx_tstamp_enable = true;
+ break;
+
+ /* TX HW timestamping can't be disabled on the switch */
+ case HWTSTAMP_TX_OFF:
+ config->tx_type = HWTSTAMP_TX_ON;
+ break;
+
+ default:
+ return -ERANGE;
+ }
+
+ switch (config->rx_filter) {
+ /* RX HW timestamping can't be disabled on the switch */
+ case HWTSTAMP_FILTER_NONE:
+ config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+ break;
+
+ 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:
+ config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+ rx_tstamp_enable = true;
+ break;
+
+ /* RX HW timestamping can't be enabled for all messages on the switch */
+ case HWTSTAMP_FILTER_ALL:
+ config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+ break;
+
+ default:
+ return -ERANGE;
+ }
+
+ if (!tx_tstamp_enable)
+ return -ERANGE;
+
+ if (!rx_tstamp_enable)
+ return -ERANGE;
+
+ /* If this point is reached, then the requested hwtstamp config is
+ * compatible with the hwtstamp offered by the switch. Therefore,
+ * enable the interaction with the HW timestamping
+ */
+ set_bit(HELLCREEK_HWTSTAMP_ENABLED, &ps->state);
+
+ return 0;
+}
+
+int hellcreek_port_hwtstamp_set(struct dsa_switch *ds, int port,
+ struct ifreq *ifr)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ struct hellcreek_port_hwtstamp *ps;
+ struct hwtstamp_config config;
+ int err;
+
+ ps = &hellcreek->ports[port].port_hwtstamp;
+
+ if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+ return -EFAULT;
+
+ err = hellcreek_set_hwtstamp_config(hellcreek, port, &config);
+ if (err)
+ return err;
+
+ /* Save the chosen configuration to be returned later */
+ memcpy(&ps->tstamp_config, &config, sizeof(config));
+
+ return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
+ -EFAULT : 0;
+}
+
+int hellcreek_port_hwtstamp_get(struct dsa_switch *ds, int port,
+ struct ifreq *ifr)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ struct hellcreek_port_hwtstamp *ps;
+ struct hwtstamp_config *config;
+
+ ps = &hellcreek->ports[port].port_hwtstamp;
+ config = &ps->tstamp_config;
+
+ return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
+ -EFAULT : 0;
+}
+
+/* Returns a pointer to the PTP header if the caller should time stamp, or NULL
+ * if the caller should not.
+ */
+static struct ptp_header *hellcreek_should_tstamp(struct hellcreek *hellcreek,
+ int port, struct sk_buff *skb,
+ unsigned int type)
+{
+ struct hellcreek_port_hwtstamp *ps =
+ &hellcreek->ports[port].port_hwtstamp;
+ struct ptp_header *hdr;
+
+ hdr = ptp_parse_header(skb, type);
+ if (!hdr)
+ return NULL;
+
+ if (!test_bit(HELLCREEK_HWTSTAMP_ENABLED, &ps->state))
+ return NULL;
+
+ return hdr;
+}
+
+static u64 hellcreek_get_reserved_field(const struct ptp_header *hdr)
+{
+ return be32_to_cpu(hdr->reserved2);
+}
+
+static void hellcreek_clear_reserved_field(struct ptp_header *hdr)
+{
+ hdr->reserved2 = 0;
+}
+
+static int hellcreek_ptp_hwtstamp_available(struct hellcreek *hellcreek,
+ unsigned int ts_reg)
+{
+ u16 status;
+
+ status = hellcreek_ptp_read(hellcreek, ts_reg);
+
+ if (status & PR_TS_STATUS_TS_LOST)
+ dev_err(hellcreek->dev,
+ "Tx time stamp lost! This should never happen!\n");
+
+ /* If hwtstamp is not available, this means the previous hwtstamp was
+ * successfully read, and the one we need is not yet available
+ */
+ return (status & PR_TS_STATUS_TS_AVAIL) ? 1 : 0;
+}
+
+/* Get nanoseconds timestamp from timestamping unit */
+static u64 hellcreek_ptp_hwtstamp_read(struct hellcreek *hellcreek,
+ unsigned int ts_reg)
+{
+ u16 nsl, nsh;
+
+ nsh = hellcreek_ptp_read(hellcreek, ts_reg);
+ nsh = hellcreek_ptp_read(hellcreek, ts_reg);
+ nsh = hellcreek_ptp_read(hellcreek, ts_reg);
+ nsh = hellcreek_ptp_read(hellcreek, ts_reg);
+ nsl = hellcreek_ptp_read(hellcreek, ts_reg);
+
+ return (u64)nsl | ((u64)nsh << 16);
+}
+
+static int hellcreek_txtstamp_work(struct hellcreek *hellcreek,
+ struct hellcreek_port_hwtstamp *ps, int port)
+{
+ struct skb_shared_hwtstamps shhwtstamps;
+ unsigned int status_reg, data_reg;
+ struct sk_buff *tmp_skb;
+ int ts_status;
+ u64 ns = 0;
+
+ if (!ps->tx_skb)
+ return 0;
+
+ switch (port) {
+ case 2:
+ status_reg = PR_TS_TX_P1_STATUS_C;
+ data_reg = PR_TS_TX_P1_DATA_C;
+ break;
+ case 3:
+ status_reg = PR_TS_TX_P2_STATUS_C;
+ data_reg = PR_TS_TX_P2_DATA_C;
+ break;
+ default:
+ dev_err(hellcreek->dev, "Wrong port for timestamping!\n");
+ return 0;
+ }
+
+ ts_status = hellcreek_ptp_hwtstamp_available(hellcreek, status_reg);
+
+ /* Not available yet? */
+ if (ts_status == 0) {
+ /* Check whether the operation of reading the tx timestamp has
+ * exceeded its allowed period
+ */
+ if (time_is_before_jiffies(ps->tx_tstamp_start +
+ TX_TSTAMP_TIMEOUT)) {
+ dev_err(hellcreek->dev,
+ "Timeout while waiting for Tx timestamp!\n");
+ goto free_and_clear_skb;
+ }
+
+ /* The timestamp should be available quickly, while getting it
+ * in high priority. Restart the work
+ */
+ return 1;
+ }
+
+ mutex_lock(&hellcreek->ptp_lock);
+ ns = hellcreek_ptp_hwtstamp_read(hellcreek, data_reg);
+ ns += hellcreek_ptp_gettime_seconds(hellcreek, ns);
+ mutex_unlock(&hellcreek->ptp_lock);
+
+ /* Now we have the timestamp in nanoseconds, store it in the correct
+ * structure in order to send it to the user
+ */
+ memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+ shhwtstamps.hwtstamp = ns_to_ktime(ns);
+
+ tmp_skb = ps->tx_skb;
+ ps->tx_skb = NULL;
+
+ /* skb_complete_tx_timestamp() frees up the client to make another
+ * timestampable transmit. We have to be ready for it by clearing the
+ * ps->tx_skb "flag" beforehand
+ */
+ clear_bit_unlock(HELLCREEK_HWTSTAMP_TX_IN_PROGRESS, &ps->state);
+
+ /* Deliver a clone of the original outgoing tx_skb with tx hwtstamp */
+ skb_complete_tx_timestamp(tmp_skb, &shhwtstamps);
+
+ return 0;
+
+free_and_clear_skb:
+ dev_kfree_skb_any(ps->tx_skb);
+ ps->tx_skb = NULL;
+ clear_bit_unlock(HELLCREEK_HWTSTAMP_TX_IN_PROGRESS, &ps->state);
+
+ return 0;
+}
+
+static void hellcreek_get_rxts(struct hellcreek *hellcreek,
+ struct hellcreek_port_hwtstamp *ps,
+ struct sk_buff *skb, struct sk_buff_head *rxq,
+ int port)
+{
+ struct skb_shared_hwtstamps *shwt;
+ struct sk_buff_head received;
+ unsigned long flags;
+
+ /* The latched timestamp belongs to one of the received frames. */
+ __skb_queue_head_init(&received);
+
+ /* Lock & disable interrupts */
+ spin_lock_irqsave(&rxq->lock, flags);
+
+ /* Add the reception queue "rxq" to the "received" queue an reintialize
+ * "rxq". From now on, we deal with "received" not with "rxq"
+ */
+ skb_queue_splice_tail_init(rxq, &received);
+
+ spin_unlock_irqrestore(&rxq->lock, flags);
+
+ for (; skb; skb = __skb_dequeue(&received)) {
+ struct ptp_header *hdr;
+ unsigned int type;
+ u64 ns;
+
+ /* Get nanoseconds from ptp packet */
+ type = SKB_PTP_TYPE(skb);
+ hdr = ptp_parse_header(skb, type);
+ ns = hellcreek_get_reserved_field(hdr);
+ hellcreek_clear_reserved_field(hdr);
+
+ /* Add seconds part */
+ mutex_lock(&hellcreek->ptp_lock);
+ ns += hellcreek_ptp_gettime_seconds(hellcreek, ns);
+ mutex_unlock(&hellcreek->ptp_lock);
+
+ /* Save time stamp */
+ shwt = skb_hwtstamps(skb);
+ memset(shwt, 0, sizeof(*shwt));
+ shwt->hwtstamp = ns_to_ktime(ns);
+ netif_rx_ni(skb);
+ }
+}
+
+static void hellcreek_rxtstamp_work(struct hellcreek *hellcreek,
+ struct hellcreek_port_hwtstamp *ps,
+ int port)
+{
+ struct sk_buff *skb;
+
+ skb = skb_dequeue(&ps->rx_queue);
+ if (skb)
+ hellcreek_get_rxts(hellcreek, ps, skb, &ps->rx_queue, port);
+}
+
+long hellcreek_hwtstamp_work(struct ptp_clock_info *ptp)
+{
+ struct hellcreek *hellcreek = ptp_to_hellcreek(ptp);
+ struct dsa_switch *ds = hellcreek->ds;
+ int i, restart = 0;
+
+ for (i = 0; i < ds->num_ports; i++) {
+ struct hellcreek_port_hwtstamp *ps;
+
+ if (!dsa_is_user_port(ds, i))
+ continue;
+
+ ps = &hellcreek->ports[i].port_hwtstamp;
+
+ if (test_bit(HELLCREEK_HWTSTAMP_TX_IN_PROGRESS, &ps->state))
+ restart |= hellcreek_txtstamp_work(hellcreek, ps, i);
+
+ hellcreek_rxtstamp_work(hellcreek, ps, i);
+ }
+
+ return restart ? 1 : -1;
+}
+
+bool hellcreek_port_txtstamp(struct dsa_switch *ds, int port,
+ struct sk_buff *clone, unsigned int type)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ struct hellcreek_port_hwtstamp *ps;
+ struct ptp_header *hdr;
+
+ ps = &hellcreek->ports[port].port_hwtstamp;
+
+ /* Check if the driver is expected to do HW timestamping */
+ if (!(skb_shinfo(clone)->tx_flags & SKBTX_HW_TSTAMP))
+ return false;
+
+ /* Make sure the message is a PTP message that needs to be timestamped
+ * and the interaction with the HW timestamping is enabled. If not, stop
+ * here
+ */
+ hdr = hellcreek_should_tstamp(hellcreek, port, clone, type);
+ if (!hdr)
+ return false;
+
+ if (test_and_set_bit_lock(HELLCREEK_HWTSTAMP_TX_IN_PROGRESS,
+ &ps->state))
+ return false;
+
+ ps->tx_skb = clone;
+
+ /* store the number of ticks occurred since system start-up till this
+ * moment
+ */
+ ps->tx_tstamp_start = jiffies;
+
+ ptp_schedule_worker(hellcreek->ptp_clock, 0);
+
+ return true;
+}
+
+bool hellcreek_port_rxtstamp(struct dsa_switch *ds, int port,
+ struct sk_buff *skb, unsigned int type)
+{
+ struct hellcreek *hellcreek = ds->priv;
+ struct hellcreek_port_hwtstamp *ps;
+ struct ptp_header *hdr;
+
+ ps = &hellcreek->ports[port].port_hwtstamp;
+
+ /* This check only fails if the user did not initialize hardware
+ * timestamping beforehand.
+ */
+ if (ps->tstamp_config.rx_filter != HWTSTAMP_FILTER_PTP_V2_EVENT)
+ return false;
+
+ /* Make sure the message is a PTP message that needs to be timestamped
+ * and the interaction with the HW timestamping is enabled. If not, stop
+ * here
+ */
+ hdr = hellcreek_should_tstamp(hellcreek, port, skb, type);
+ if (!hdr)
+ return false;
+
+ SKB_PTP_TYPE(skb) = type;
+
+ skb_queue_tail(&ps->rx_queue, skb);
+
+ ptp_schedule_worker(hellcreek->ptp_clock, 0);
+
+ return true;
+}
+
+static void hellcreek_hwtstamp_port_setup(struct hellcreek *hellcreek, int port)
+{
+ struct hellcreek_port_hwtstamp *ps =
+ &hellcreek->ports[port].port_hwtstamp;
+
+ skb_queue_head_init(&ps->rx_queue);
+}
+
+int hellcreek_hwtstamp_setup(struct hellcreek *hellcreek)
+{
+ struct dsa_switch *ds = hellcreek->ds;
+ int i;
+
+ /* Initialize timestamping ports. */
+ for (i = 0; i < ds->num_ports; ++i) {
+ if (!dsa_is_user_port(ds, i))
+ continue;
+
+ hellcreek_hwtstamp_port_setup(hellcreek, i);
+ }
+
+ /* Select the synchronized clock as the source timekeeper for the
+ * timestamps and enable inline timestamping.
+ */
+ hellcreek_ptp_write(hellcreek, PR_SETTINGS_C_TS_SRC_TK_MASK |
+ PR_SETTINGS_C_RES3TS,
+ PR_SETTINGS_C);
+
+ return 0;
+}
+
+void hellcreek_hwtstamp_free(struct hellcreek *hellcreek)
+{
+ /* Nothing todo */
+}
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * DSA driver for:
+ * Hirschmann Hellcreek TSN switch.
+ *
+ * Copyright (C) 2019,2020 Hochschule Offenburg
+ * Copyright (C) 2019,2020 Linutronix GmbH
+ * Authors: Kurt Kanzenbach <kurt@linutronix.de>
+ * Kamil Alkhouri <kamil.alkhouri@hs-offenburg.de>
+ */
+
+#ifndef _HELLCREEK_HWTSTAMP_H_
+#define _HELLCREEK_HWTSTAMP_H_
+
+#include <net/dsa.h>
+#include "hellcreek.h"
+
+/* Timestamp Register */
+#define PR_TS_RX_P1_STATUS_C (0x1d * 2)
+#define PR_TS_RX_P1_DATA_C (0x1e * 2)
+#define PR_TS_TX_P1_STATUS_C (0x1f * 2)
+#define PR_TS_TX_P1_DATA_C (0x20 * 2)
+#define PR_TS_RX_P2_STATUS_C (0x25 * 2)
+#define PR_TS_RX_P2_DATA_C (0x26 * 2)
+#define PR_TS_TX_P2_STATUS_C (0x27 * 2)
+#define PR_TS_TX_P2_DATA_C (0x28 * 2)
+
+#define PR_TS_STATUS_TS_AVAIL BIT(2)
+#define PR_TS_STATUS_TS_LOST BIT(3)
+
+#define SKB_PTP_TYPE(__skb) (*(unsigned int *)((__skb)->cb))
+
+/* TX_TSTAMP_TIMEOUT: This limits the time spent polling for a TX
+ * timestamp. When working properly, hardware will produce a timestamp
+ * within 1ms. Software may enounter delays, so the timeout is set
+ * accordingly.
+ */
+#define TX_TSTAMP_TIMEOUT msecs_to_jiffies(40)
+
+int hellcreek_port_hwtstamp_set(struct dsa_switch *ds, int port,
+ struct ifreq *ifr);
+int hellcreek_port_hwtstamp_get(struct dsa_switch *ds, int port,
+ struct ifreq *ifr);
+
+bool hellcreek_port_rxtstamp(struct dsa_switch *ds, int port,
+ struct sk_buff *clone, unsigned int type);
+bool hellcreek_port_txtstamp(struct dsa_switch *ds, int port,
+ struct sk_buff *clone, unsigned int type);
+
+int hellcreek_get_ts_info(struct dsa_switch *ds, int port,
+ struct ethtool_ts_info *info);
+
+long hellcreek_hwtstamp_work(struct ptp_clock_info *ptp);
+
+int hellcreek_hwtstamp_setup(struct hellcreek *chip);
+void hellcreek_hwtstamp_free(struct hellcreek *chip);
+
+#endif /* _HELLCREEK_HWTSTAMP_H_ */
--- /dev/null
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * DSA driver for:
+ * Hirschmann Hellcreek TSN switch.
+ *
+ * Copyright (C) 2019,2020 Hochschule Offenburg
+ * Copyright (C) 2019,2020 Linutronix GmbH
+ * Authors: Kamil Alkhouri <kamil.alkhouri@hs-offenburg.de>
+ * Kurt Kanzenbach <kurt@linutronix.de>
+ */
+
+#include <linux/ptp_clock_kernel.h>
+#include "hellcreek.h"
+#include "hellcreek_ptp.h"
+#include "hellcreek_hwtstamp.h"
+
+u16 hellcreek_ptp_read(struct hellcreek *hellcreek, unsigned int offset)
+{
+ return readw(hellcreek->ptp_base + offset);
+}
+
+void hellcreek_ptp_write(struct hellcreek *hellcreek, u16 data,
+ unsigned int offset)
+{
+ writew(data, hellcreek->ptp_base + offset);
+}
+
+/* Get nanoseconds from PTP clock */
+static u64 hellcreek_ptp_clock_read(struct hellcreek *hellcreek)
+{
+ u16 nsl, nsh;
+
+ /* Take a snapshot */
+ hellcreek_ptp_write(hellcreek, PR_COMMAND_C_SS, PR_COMMAND_C);
+
+ /* The time of the day is saved as 96 bits. However, due to hardware
+ * limitations the seconds are not or only partly kept in the PTP
+ * core. Currently only three bits for the seconds are available. That's
+ * why only the nanoseconds are used and the seconds are tracked in
+ * software. Anyway due to internal locking all five registers should be
+ * read.
+ */
+ nsh = hellcreek_ptp_read(hellcreek, PR_SS_SYNC_DATA_C);
+ nsh = hellcreek_ptp_read(hellcreek, PR_SS_SYNC_DATA_C);
+ nsh = hellcreek_ptp_read(hellcreek, PR_SS_SYNC_DATA_C);
+ nsh = hellcreek_ptp_read(hellcreek, PR_SS_SYNC_DATA_C);
+ nsl = hellcreek_ptp_read(hellcreek, PR_SS_SYNC_DATA_C);
+
+ return (u64)nsl | ((u64)nsh << 16);
+}
+
+static u64 __hellcreek_ptp_gettime(struct hellcreek *hellcreek)
+{
+ u64 ns;
+
+ ns = hellcreek_ptp_clock_read(hellcreek);
+ if (ns < hellcreek->last_ts)
+ hellcreek->seconds++;
+ hellcreek->last_ts = ns;
+ ns += hellcreek->seconds * NSEC_PER_SEC;
+
+ return ns;
+}
+
+/* Retrieve the seconds parts in nanoseconds for a packet timestamped with @ns.
+ * There has to be a check whether an overflow occurred between the packet
+ * arrival and now. If so use the correct seconds (-1) for calculating the
+ * packet arrival time.
+ */
+u64 hellcreek_ptp_gettime_seconds(struct hellcreek *hellcreek, u64 ns)
+{
+ u64 s;
+
+ __hellcreek_ptp_gettime(hellcreek);
+ if (hellcreek->last_ts > ns)
+ s = hellcreek->seconds * NSEC_PER_SEC;
+ else
+ s = (hellcreek->seconds - 1) * NSEC_PER_SEC;
+
+ return s;
+}
+
+static int hellcreek_ptp_gettime(struct ptp_clock_info *ptp,
+ struct timespec64 *ts)
+{
+ struct hellcreek *hellcreek = ptp_to_hellcreek(ptp);
+ u64 ns;
+
+ mutex_lock(&hellcreek->ptp_lock);
+ ns = __hellcreek_ptp_gettime(hellcreek);
+ mutex_unlock(&hellcreek->ptp_lock);
+
+ *ts = ns_to_timespec64(ns);
+
+ return 0;
+}
+
+static int hellcreek_ptp_settime(struct ptp_clock_info *ptp,
+ const struct timespec64 *ts)
+{
+ struct hellcreek *hellcreek = ptp_to_hellcreek(ptp);
+ u16 secl, nsh, nsl;
+
+ secl = ts->tv_sec & 0xffff;
+ nsh = ((u32)ts->tv_nsec & 0xffff0000) >> 16;
+ nsl = ts->tv_nsec & 0xffff;
+
+ mutex_lock(&hellcreek->ptp_lock);
+
+ /* Update overflow data structure */
+ hellcreek->seconds = ts->tv_sec;
+ hellcreek->last_ts = ts->tv_nsec;
+
+ /* Set time in clock */
+ hellcreek_ptp_write(hellcreek, 0x00, PR_CLOCK_WRITE_C);
+ hellcreek_ptp_write(hellcreek, 0x00, PR_CLOCK_WRITE_C);
+ hellcreek_ptp_write(hellcreek, secl, PR_CLOCK_WRITE_C);
+ hellcreek_ptp_write(hellcreek, nsh, PR_CLOCK_WRITE_C);
+ hellcreek_ptp_write(hellcreek, nsl, PR_CLOCK_WRITE_C);
+
+ mutex_unlock(&hellcreek->ptp_lock);
+
+ return 0;
+}
+
+static int hellcreek_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+ struct hellcreek *hellcreek = ptp_to_hellcreek(ptp);
+ u16 negative = 0, addendh, addendl;
+ u32 addend;
+ u64 adj;
+
+ if (scaled_ppm < 0) {
+ negative = 1;
+ scaled_ppm = -scaled_ppm;
+ }
+
+ /* IP-Core adjusts the nominal frequency by adding or subtracting 1 ns
+ * from the 8 ns (period of the oscillator) every time the accumulator
+ * register overflows. The value stored in the addend register is added
+ * to the accumulator register every 8 ns.
+ *
+ * addend value = (2^30 * accumulator_overflow_rate) /
+ * oscillator_frequency
+ * where:
+ *
+ * oscillator_frequency = 125 MHz
+ * accumulator_overflow_rate = 125 MHz * scaled_ppm * 2^-16 * 10^-6 * 8
+ */
+ adj = scaled_ppm;
+ adj <<= 11;
+ addend = (u32)div_u64(adj, 15625);
+
+ addendh = (addend & 0xffff0000) >> 16;
+ addendl = addend & 0xffff;
+
+ negative = (negative << 15) & 0x8000;
+
+ mutex_lock(&hellcreek->ptp_lock);
+
+ /* Set drift register */
+ hellcreek_ptp_write(hellcreek, negative, PR_CLOCK_DRIFT_C);
+ hellcreek_ptp_write(hellcreek, 0x00, PR_CLOCK_DRIFT_C);
+ hellcreek_ptp_write(hellcreek, 0x00, PR_CLOCK_DRIFT_C);
+ hellcreek_ptp_write(hellcreek, addendh, PR_CLOCK_DRIFT_C);
+ hellcreek_ptp_write(hellcreek, addendl, PR_CLOCK_DRIFT_C);
+
+ mutex_unlock(&hellcreek->ptp_lock);
+
+ return 0;
+}
+
+static int hellcreek_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+ struct hellcreek *hellcreek = ptp_to_hellcreek(ptp);
+ u16 negative = 0, counth, countl;
+ u32 count_val;
+
+ /* If the offset is larger than IP-Core slow offset resources. Don't
+ * consider slow adjustment. Rather, add the offset directly to the
+ * current time
+ */
+ if (abs(delta) > MAX_SLOW_OFFSET_ADJ) {
+ struct timespec64 now, then = ns_to_timespec64(delta);
+
+ hellcreek_ptp_gettime(ptp, &now);
+ now = timespec64_add(now, then);
+ hellcreek_ptp_settime(ptp, &now);
+
+ return 0;
+ }
+
+ if (delta < 0) {
+ negative = 1;
+ delta = -delta;
+ }
+
+ /* 'count_val' does not exceed the maximum register size (2^30) */
+ count_val = div_s64(delta, MAX_NS_PER_STEP);
+
+ counth = (count_val & 0xffff0000) >> 16;
+ countl = count_val & 0xffff;
+
+ negative = (negative << 15) & 0x8000;
+
+ mutex_lock(&hellcreek->ptp_lock);
+
+ /* Set offset write register */
+ hellcreek_ptp_write(hellcreek, negative, PR_CLOCK_OFFSET_C);
+ hellcreek_ptp_write(hellcreek, MAX_NS_PER_STEP, PR_CLOCK_OFFSET_C);
+ hellcreek_ptp_write(hellcreek, MIN_CLK_CYCLES_BETWEEN_STEPS,
+ PR_CLOCK_OFFSET_C);
+ hellcreek_ptp_write(hellcreek, countl, PR_CLOCK_OFFSET_C);
+ hellcreek_ptp_write(hellcreek, counth, PR_CLOCK_OFFSET_C);
+
+ mutex_unlock(&hellcreek->ptp_lock);
+
+ return 0;
+}
+
+static int hellcreek_ptp_enable(struct ptp_clock_info *ptp,
+ struct ptp_clock_request *rq, int on)
+{
+ return -EOPNOTSUPP;
+}
+
+static void hellcreek_ptp_overflow_check(struct work_struct *work)
+{
+ struct delayed_work *dw = to_delayed_work(work);
+ struct hellcreek *hellcreek;
+
+ hellcreek = dw_overflow_to_hellcreek(dw);
+
+ mutex_lock(&hellcreek->ptp_lock);
+ __hellcreek_ptp_gettime(hellcreek);
+ mutex_unlock(&hellcreek->ptp_lock);
+
+ schedule_delayed_work(&hellcreek->overflow_work,
+ HELLCREEK_OVERFLOW_PERIOD);
+}
+
+static enum led_brightness hellcreek_get_brightness(struct hellcreek *hellcreek,
+ int led)
+{
+ return (hellcreek->status_out & led) ? 1 : 0;
+}
+
+static void hellcreek_set_brightness(struct hellcreek *hellcreek, int led,
+ enum led_brightness b)
+{
+ mutex_lock(&hellcreek->ptp_lock);
+
+ if (b)
+ hellcreek->status_out |= led;
+ else
+ hellcreek->status_out &= ~led;
+
+ hellcreek_ptp_write(hellcreek, hellcreek->status_out, STATUS_OUT);
+
+ mutex_unlock(&hellcreek->ptp_lock);
+}
+
+static void hellcreek_led_sync_good_set(struct led_classdev *ldev,
+ enum led_brightness b)
+{
+ struct hellcreek *hellcreek = led_to_hellcreek(ldev, led_sync_good);
+
+ hellcreek_set_brightness(hellcreek, STATUS_OUT_SYNC_GOOD, b);
+}
+
+static enum led_brightness hellcreek_led_sync_good_get(struct led_classdev *ldev)
+{
+ struct hellcreek *hellcreek = led_to_hellcreek(ldev, led_sync_good);
+
+ return hellcreek_get_brightness(hellcreek, STATUS_OUT_SYNC_GOOD);
+}
+
+static void hellcreek_led_is_gm_set(struct led_classdev *ldev,
+ enum led_brightness b)
+{
+ struct hellcreek *hellcreek = led_to_hellcreek(ldev, led_is_gm);
+
+ hellcreek_set_brightness(hellcreek, STATUS_OUT_IS_GM, b);
+}
+
+static enum led_brightness hellcreek_led_is_gm_get(struct led_classdev *ldev)
+{
+ struct hellcreek *hellcreek = led_to_hellcreek(ldev, led_is_gm);
+
+ return hellcreek_get_brightness(hellcreek, STATUS_OUT_IS_GM);
+}
+
+/* There two available LEDs internally called sync_good and is_gm. However, the
+ * user might want to use a different label and specify the default state. Take
+ * those properties from device tree.
+ */
+static int hellcreek_led_setup(struct hellcreek *hellcreek)
+{
+ struct device_node *leds, *led = NULL;
+ const char *label, *state;
+ int ret = -EINVAL;
+
+ leds = of_find_node_by_name(hellcreek->dev->of_node, "leds");
+ if (!leds) {
+ dev_err(hellcreek->dev, "No LEDs specified in device tree!\n");
+ return ret;
+ }
+
+ hellcreek->status_out = 0;
+
+ led = of_get_next_available_child(leds, led);
+ if (!led) {
+ dev_err(hellcreek->dev, "First LED not specified!\n");
+ goto out;
+ }
+
+ ret = of_property_read_string(led, "label", &label);
+ hellcreek->led_sync_good.name = ret ? "sync_good" : label;
+
+ ret = of_property_read_string(led, "default-state", &state);
+ if (!ret) {
+ if (!strcmp(state, "on"))
+ hellcreek->led_sync_good.brightness = 1;
+ else if (!strcmp(state, "off"))
+ hellcreek->led_sync_good.brightness = 0;
+ else if (!strcmp(state, "keep"))
+ hellcreek->led_sync_good.brightness =
+ hellcreek_get_brightness(hellcreek,
+ STATUS_OUT_SYNC_GOOD);
+ }
+
+ hellcreek->led_sync_good.max_brightness = 1;
+ hellcreek->led_sync_good.brightness_set = hellcreek_led_sync_good_set;
+ hellcreek->led_sync_good.brightness_get = hellcreek_led_sync_good_get;
+
+ led = of_get_next_available_child(leds, led);
+ if (!led) {
+ dev_err(hellcreek->dev, "Second LED not specified!\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = of_property_read_string(led, "label", &label);
+ hellcreek->led_is_gm.name = ret ? "is_gm" : label;
+
+ ret = of_property_read_string(led, "default-state", &state);
+ if (!ret) {
+ if (!strcmp(state, "on"))
+ hellcreek->led_is_gm.brightness = 1;
+ else if (!strcmp(state, "off"))
+ hellcreek->led_is_gm.brightness = 0;
+ else if (!strcmp(state, "keep"))
+ hellcreek->led_is_gm.brightness =
+ hellcreek_get_brightness(hellcreek,
+ STATUS_OUT_IS_GM);
+ }
+
+ hellcreek->led_is_gm.max_brightness = 1;
+ hellcreek->led_is_gm.brightness_set = hellcreek_led_is_gm_set;
+ hellcreek->led_is_gm.brightness_get = hellcreek_led_is_gm_get;
+
+ /* Set initial state */
+ if (hellcreek->led_sync_good.brightness == 1)
+ hellcreek_set_brightness(hellcreek, STATUS_OUT_SYNC_GOOD, 1);
+ if (hellcreek->led_is_gm.brightness == 1)
+ hellcreek_set_brightness(hellcreek, STATUS_OUT_IS_GM, 1);
+
+ /* Register both leds */
+ led_classdev_register(hellcreek->dev, &hellcreek->led_sync_good);
+ led_classdev_register(hellcreek->dev, &hellcreek->led_is_gm);
+
+ ret = 0;
+
+out:
+ of_node_put(leds);
+
+ return ret;
+}
+
+int hellcreek_ptp_setup(struct hellcreek *hellcreek)
+{
+ u16 status;
+ int ret;
+
+ /* Set up the overflow work */
+ INIT_DELAYED_WORK(&hellcreek->overflow_work,
+ hellcreek_ptp_overflow_check);
+
+ /* Setup PTP clock */
+ hellcreek->ptp_clock_info.owner = THIS_MODULE;
+ snprintf(hellcreek->ptp_clock_info.name,
+ sizeof(hellcreek->ptp_clock_info.name),
+ dev_name(hellcreek->dev));
+
+ /* IP-Core can add up to 0.5 ns per 8 ns cycle, which means
+ * accumulator_overflow_rate shall not exceed 62.5 MHz (which adjusts
+ * the nominal frequency by 6.25%)
+ */
+ hellcreek->ptp_clock_info.max_adj = 62500000;
+ hellcreek->ptp_clock_info.n_alarm = 0;
+ hellcreek->ptp_clock_info.n_pins = 0;
+ hellcreek->ptp_clock_info.n_ext_ts = 0;
+ hellcreek->ptp_clock_info.n_per_out = 0;
+ hellcreek->ptp_clock_info.pps = 0;
+ hellcreek->ptp_clock_info.adjfine = hellcreek_ptp_adjfine;
+ hellcreek->ptp_clock_info.adjtime = hellcreek_ptp_adjtime;
+ hellcreek->ptp_clock_info.gettime64 = hellcreek_ptp_gettime;
+ hellcreek->ptp_clock_info.settime64 = hellcreek_ptp_settime;
+ hellcreek->ptp_clock_info.enable = hellcreek_ptp_enable;
+ hellcreek->ptp_clock_info.do_aux_work = hellcreek_hwtstamp_work;
+
+ hellcreek->ptp_clock = ptp_clock_register(&hellcreek->ptp_clock_info,
+ hellcreek->dev);
+ if (IS_ERR(hellcreek->ptp_clock))
+ return PTR_ERR(hellcreek->ptp_clock);
+
+ /* Enable the offset correction process, if no offset correction is
+ * already taking place
+ */
+ status = hellcreek_ptp_read(hellcreek, PR_CLOCK_STATUS_C);
+ if (!(status & PR_CLOCK_STATUS_C_OFS_ACT))
+ hellcreek_ptp_write(hellcreek,
+ status | PR_CLOCK_STATUS_C_ENA_OFS,
+ PR_CLOCK_STATUS_C);
+
+ /* Enable the drift correction process */
+ hellcreek_ptp_write(hellcreek, status | PR_CLOCK_STATUS_C_ENA_DRIFT,
+ PR_CLOCK_STATUS_C);
+
+ /* LED setup */
+ ret = hellcreek_led_setup(hellcreek);
+ if (ret) {
+ if (hellcreek->ptp_clock)
+ ptp_clock_unregister(hellcreek->ptp_clock);
+ return ret;
+ }
+
+ schedule_delayed_work(&hellcreek->overflow_work,
+ HELLCREEK_OVERFLOW_PERIOD);
+
+ return 0;
+}
+
+void hellcreek_ptp_free(struct hellcreek *hellcreek)
+{
+ led_classdev_unregister(&hellcreek->led_is_gm);
+ led_classdev_unregister(&hellcreek->led_sync_good);
+ cancel_delayed_work_sync(&hellcreek->overflow_work);
+ if (hellcreek->ptp_clock)
+ ptp_clock_unregister(hellcreek->ptp_clock);
+ hellcreek->ptp_clock = NULL;
+}
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * DSA driver for:
+ * Hirschmann Hellcreek TSN switch.
+ *
+ * Copyright (C) 2019,2020 Hochschule Offenburg
+ * Copyright (C) 2019,2020 Linutronix GmbH
+ * Authors: Kurt Kanzenbach <kurt@linutronix.de>
+ * Kamil Alkhouri <kamil.alkhouri@hs-offenburg.de>
+ */
+
+#ifndef _HELLCREEK_PTP_H_
+#define _HELLCREEK_PTP_H_
+
+#include <linux/bitops.h>
+#include <linux/ptp_clock_kernel.h>
+
+#include "hellcreek.h"
+
+/* Every jump in time is 7 ns */
+#define MAX_NS_PER_STEP 7L
+
+/* Correct offset at every clock cycle */
+#define MIN_CLK_CYCLES_BETWEEN_STEPS 0
+
+/* Maximum available slow offset resources */
+#define MAX_SLOW_OFFSET_ADJ \
+ ((unsigned long long)((1 << 30) - 1) * MAX_NS_PER_STEP)
+
+/* four times a second overflow check */
+#define HELLCREEK_OVERFLOW_PERIOD (HZ / 4)
+
+/* PTP Register */
+#define PR_SETTINGS_C (0x09 * 2)
+#define PR_SETTINGS_C_RES3TS BIT(4)
+#define PR_SETTINGS_C_TS_SRC_TK_SHIFT 8
+#define PR_SETTINGS_C_TS_SRC_TK_MASK GENMASK(9, 8)
+#define PR_COMMAND_C (0x0a * 2)
+#define PR_COMMAND_C_SS BIT(0)
+
+#define PR_CLOCK_STATUS_C (0x0c * 2)
+#define PR_CLOCK_STATUS_C_ENA_DRIFT BIT(12)
+#define PR_CLOCK_STATUS_C_OFS_ACT BIT(13)
+#define PR_CLOCK_STATUS_C_ENA_OFS BIT(14)
+
+#define PR_CLOCK_READ_C (0x0d * 2)
+#define PR_CLOCK_WRITE_C (0x0e * 2)
+#define PR_CLOCK_OFFSET_C (0x0f * 2)
+#define PR_CLOCK_DRIFT_C (0x10 * 2)
+
+#define PR_SS_FREE_DATA_C (0x12 * 2)
+#define PR_SS_SYNT_DATA_C (0x14 * 2)
+#define PR_SS_SYNC_DATA_C (0x16 * 2)
+#define PR_SS_DRAC_DATA_C (0x18 * 2)
+
+#define STATUS_OUT (0x60 * 2)
+#define STATUS_OUT_SYNC_GOOD BIT(0)
+#define STATUS_OUT_IS_GM BIT(1)
+
+int hellcreek_ptp_setup(struct hellcreek *hellcreek);
+void hellcreek_ptp_free(struct hellcreek *hellcreek);
+u16 hellcreek_ptp_read(struct hellcreek *hellcreek, unsigned int offset);
+void hellcreek_ptp_write(struct hellcreek *hellcreek, u16 data,
+ unsigned int offset);
+u64 hellcreek_ptp_gettime_seconds(struct hellcreek *hellcreek, u64 ns);
+
+#define ptp_to_hellcreek(ptp) \
+ container_of(ptp, struct hellcreek, ptp_clock_info)
+
+#define dw_overflow_to_hellcreek(dw) \
+ container_of(dw, struct hellcreek, overflow_work)
+
+#define led_to_hellcreek(ldev, led) \
+ container_of(ldev, struct hellcreek, led)
+
+#endif /* _HELLCREEK_PTP_H_ */
static const struct {
char string[ETH_GSTRING_LEN];
-} mib_names[TOTAL_SWITCH_COUNTER_NUM] = {
+} mib_names[] = {
{ "rx_hi" },
{ "rx_undersize" },
{ "rx_fragments" },
u8 check;
int loop;
- ctrl_addr = addr + SWITCH_COUNTER_NUM * port;
+ ctrl_addr = addr + dev->reg_mib_cnt * port;
ctrl_addr |= IND_ACC_TABLE(TABLE_MIB | TABLE_READ);
mutex_lock(&dev->alu_mutex);
u8 check;
int loop;
- addr -= SWITCH_COUNTER_NUM;
+ addr -= dev->reg_mib_cnt;
ctrl_addr = (KS_MIB_TOTAL_RX_1 - KS_MIB_TOTAL_RX_0) * port;
ctrl_addr += addr + KS_MIB_TOTAL_RX_0;
ctrl_addr |= IND_ACC_TABLE(TABLE_MIB | TABLE_READ);
int i;
ksz8795_r_table(dev, TABLE_VLAN, addr, &data);
- addr *= 4;
- for (i = 0; i < 4; i++) {
+ addr *= dev->phy_port_cnt;
+ for (i = 0; i < dev->phy_port_cnt; i++) {
dev->vlan_cache[addr + i].table[0] = (u16)data;
data >>= VLAN_TABLE_S;
}
u64 buf;
data = (u16 *)&buf;
- addr = vid / 4;
+ addr = vid / dev->phy_port_cnt;
index = vid & 3;
ksz8795_r_table(dev, TABLE_VLAN, addr, &buf);
*vlan = data[index];
u64 buf;
data = (u16 *)&buf;
- addr = vid / 4;
+ addr = vid / dev->phy_port_cnt;
index = vid & 3;
ksz8795_r_table(dev, TABLE_VLAN, addr, &buf);
data[index] = vlan;
static void ksz8795_get_strings(struct dsa_switch *ds, int port,
u32 stringset, uint8_t *buf)
{
+ struct ksz_device *dev = ds->priv;
int i;
- for (i = 0; i < TOTAL_SWITCH_COUNTER_NUM; i++) {
+ for (i = 0; i < dev->mib_cnt; i++) {
memcpy(buf + i * ETH_GSTRING_LEN, mib_names[i].string,
ETH_GSTRING_LEN);
}
switch (state) {
case BR_STATE_DISABLED:
data |= PORT_LEARN_DISABLE;
- if (port < SWITCH_PORT_NUM)
+ if (port < dev->phy_port_cnt)
member = 0;
break;
case BR_STATE_LISTENING:
data |= (PORT_RX_ENABLE | PORT_LEARN_DISABLE);
- if (port < SWITCH_PORT_NUM &&
+ if (port < dev->phy_port_cnt &&
p->stp_state == BR_STATE_DISABLED)
member = dev->host_mask | p->vid_member;
break;
break;
case BR_STATE_BLOCKING:
data |= PORT_LEARN_DISABLE;
- if (port < SWITCH_PORT_NUM &&
+ if (port < dev->phy_port_cnt &&
p->stp_state == BR_STATE_DISABLED)
member = dev->host_mask | p->vid_member;
break;
static void ksz8795_flush_dyn_mac_table(struct ksz_device *dev, int port)
{
- u8 learn[TOTAL_PORT_NUM];
+ u8 learn[DSA_MAX_PORTS];
int first, index, cnt;
struct ksz_port *p;
- if ((uint)port < TOTAL_PORT_NUM) {
+ if ((uint)port < dev->port_cnt) {
first = port;
cnt = port + 1;
} else {
/* Flush all ports. */
first = 0;
- cnt = dev->mib_port_cnt;
+ cnt = dev->port_cnt;
}
for (index = first; index < cnt; index++) {
p = &dev->ports[index];
u8 remote;
int i;
- ds->num_ports = dev->port_cnt + 1;
-
/* Switch marks the maximum frame with extra byte as oversize. */
ksz_cfg(dev, REG_SW_CTRL_2, SW_LEGAL_PACKET_DISABLE, true);
ksz_cfg(dev, S_TAIL_TAG_CTRL, SW_TAIL_TAG_ENABLE, true);
ksz8795_port_setup(dev, dev->cpu_port, true);
dev->member = dev->host_mask;
- for (i = 0; i < SWITCH_PORT_NUM; i++) {
+ for (i = 0; i < dev->phy_port_cnt; i++) {
p = &dev->ports[i];
/* Initialize to non-zero so that ksz_cfg_port_member() will
ksz8795_port_stp_state_set(ds, i, BR_STATE_DISABLED);
/* Last port may be disabled. */
- if (i == dev->port_cnt)
+ if (i == dev->phy_port_cnt)
break;
p->on = 1;
p->phy = 1;
(BROADCAST_STORM_VALUE *
BROADCAST_STORM_PROT_RATE) / 100);
- for (i = 0; i < VLAN_TABLE_ENTRIES; i++)
+ for (i = 0; i < (dev->num_vlans / 4); i++)
ksz8795_r_vlan_entries(dev, i);
/* Setup STP address for STP operation. */
(id2 != CHIP_ID_94 && id2 != CHIP_ID_95))
return -ENODEV;
- dev->mib_port_cnt = TOTAL_PORT_NUM;
- dev->phy_port_cnt = SWITCH_PORT_NUM;
- dev->port_cnt = SWITCH_PORT_NUM;
-
if (id2 == CHIP_ID_95) {
u8 val;
if (val & PORT_FIBER_MODE)
id2 = 0x65;
} else if (id2 == CHIP_ID_94) {
- dev->port_cnt--;
- dev->last_port = dev->port_cnt;
id2 = 0x94;
}
id16 &= ~0xff;
id16 |= id2;
dev->chip_id = id16;
- dev->cpu_port = dev->mib_port_cnt - 1;
- dev->host_mask = BIT(dev->cpu_port);
-
return 0;
}
.num_alus = 0,
.num_statics = 8,
.cpu_ports = 0x10, /* can be configured as cpu port */
- .port_cnt = 4, /* total physical port count */
+ .port_cnt = 5, /* total cpu and user ports */
},
{
.chip_id = 0x8794,
.num_alus = 0,
.num_statics = 8,
.cpu_ports = 0x10, /* can be configured as cpu port */
- .port_cnt = 3, /* total physical port count */
+ .port_cnt = 4, /* total cpu and user ports */
},
{
.chip_id = 0x8765,
.num_alus = 0,
.num_statics = 8,
.cpu_ports = 0x10, /* can be configured as cpu port */
- .port_cnt = 4, /* total physical port count */
+ .port_cnt = 5, /* total cpu and user ports */
},
};
dev->port_mask = BIT(dev->port_cnt) - 1;
dev->port_mask |= dev->host_mask;
- dev->reg_mib_cnt = SWITCH_COUNTER_NUM;
- dev->mib_cnt = TOTAL_SWITCH_COUNTER_NUM;
+ dev->reg_mib_cnt = KSZ8795_COUNTER_NUM;
+ dev->mib_cnt = ARRAY_SIZE(mib_names);
+
+ dev->phy_port_cnt = dev->port_cnt - 1;
+
+ dev->cpu_port = dev->port_cnt - 1;
+ dev->host_mask = BIT(dev->cpu_port);
- i = dev->mib_port_cnt;
- dev->ports = devm_kzalloc(dev->dev, sizeof(struct ksz_port) * i,
+ dev->ports = devm_kzalloc(dev->dev,
+ dev->port_cnt * sizeof(struct ksz_port),
GFP_KERNEL);
if (!dev->ports)
return -ENOMEM;
- for (i = 0; i < dev->mib_port_cnt; i++) {
+ for (i = 0; i < dev->port_cnt; i++) {
mutex_init(&dev->ports[i].mib.cnt_mutex);
dev->ports[i].mib.counters =
devm_kzalloc(dev->dev,
sizeof(u64) *
- (TOTAL_SWITCH_COUNTER_NUM + 1),
+ (dev->mib_cnt + 1),
GFP_KERNEL);
if (!dev->ports[i].mib.counters)
return -ENOMEM;
}
/* set the real number of ports */
- dev->ds->num_ports = dev->port_cnt + 1;
+ dev->ds->num_ports = dev->port_cnt;
return 0;
}
#define KS_PRIO_IN_REG 4
-#define TOTAL_PORT_NUM 5
-
-/* Host port can only be last of them. */
-#define SWITCH_PORT_NUM (TOTAL_PORT_NUM - 1)
-
#define KSZ8795_COUNTER_NUM 0x20
-#define TOTAL_KSZ8795_COUNTER_NUM (KSZ8795_COUNTER_NUM + 4)
-
-#define SWITCH_COUNTER_NUM KSZ8795_COUNTER_NUM
-#define TOTAL_SWITCH_COUNTER_NUM TOTAL_KSZ8795_COUNTER_NUM
/* Common names used by other drivers */
#define TAIL_TAG_OVERRIDE BIT(6)
#define TAIL_TAG_LOOKUP BIT(7)
-#define VLAN_TABLE_ENTRIES (4096 / 4)
#define FID_ENTRIES 128
#endif
if (spi->dev.platform_data)
dev->pdata = spi->dev.platform_data;
+ /* setup spi */
+ spi->mode = SPI_MODE_3;
+ ret = spi_setup(spi);
+ if (ret)
+ return ret;
+
ret = ksz8795_switch_register(dev);
/* Main DSA driver may not be started yet. */
SW_FLUSH_OPTION_M << SW_FLUSH_OPTION_S,
SW_FLUSH_OPTION_DYN_MAC << SW_FLUSH_OPTION_S);
- if (port < dev->mib_port_cnt) {
+ if (port < dev->port_cnt) {
/* flush individual port */
ksz_pread8(dev, port, P_STP_CTRL, &data);
if (!(data & PORT_LEARN_DISABLE))
struct ksz_port *p;
int i;
- ds->num_ports = dev->port_cnt;
-
for (i = 0; i < dev->port_cnt; i++) {
if (dsa_is_cpu_port(ds, i) && (dev->cpu_ports & (1 << i))) {
phy_interface_t interface;
dev->member = dev->host_mask;
- for (i = 0; i < dev->mib_port_cnt; i++) {
+ for (i = 0; i < dev->port_cnt; i++) {
if (i == dev->cpu_port)
continue;
p = &dev->ports[i];
return ret;
/* Number of ports can be reduced depending on chip. */
- dev->mib_port_cnt = TOTAL_PORT_NUM;
dev->phy_port_cnt = 5;
/* Default capability is gigabit capable. */
/* Chip does not support gigabit. */
if (data8 & SW_QW_ABLE)
dev->features &= ~GBIT_SUPPORT;
- dev->mib_port_cnt = 3;
dev->phy_port_cnt = 2;
} else {
dev_info(dev->dev, "Found KSZ9477 or compatible\n");
dev->reg_mib_cnt = SWITCH_COUNTER_NUM;
dev->mib_cnt = TOTAL_SWITCH_COUNTER_NUM;
- i = dev->mib_port_cnt;
- dev->ports = devm_kzalloc(dev->dev, sizeof(struct ksz_port) * i,
+ dev->ports = devm_kzalloc(dev->dev,
+ dev->port_cnt * sizeof(struct ksz_port),
GFP_KERNEL);
if (!dev->ports)
return -ENOMEM;
- for (i = 0; i < dev->mib_port_cnt; i++) {
+ for (i = 0; i < dev->port_cnt; i++) {
mutex_init(&dev->ports[i].mib.cnt_mutex);
dev->ports[i].mib.counters =
devm_kzalloc(dev->dev,
if (spi->dev.platform_data)
dev->pdata = spi->dev.platform_data;
+ /* setup spi */
+ spi->mode = SPI_MODE_3;
+ ret = spi_setup(spi);
+ if (ret)
+ return ret;
+
ret = ksz9477_switch_register(dev);
/* Main DSA driver may not be started yet. */
struct ksz_port *p;
int i;
- for (i = 0; i < dev->mib_port_cnt; i++) {
+ for (i = 0; i < dev->port_cnt; i++) {
if (dsa_is_unused_port(dev->ds, i))
continue;
INIT_DELAYED_WORK(&dev->mib_read, ksz_mib_read_work);
- for (i = 0; i < dev->mib_port_cnt; i++)
+ for (i = 0; i < dev->port_cnt; i++)
dev->dev_ops->port_init_cnt(dev, i);
}
EXPORT_SYMBOL_GPL(ksz_init_mib_timer);
ret = of_get_phy_mode(dev->dev->of_node, &interface);
if (ret == 0)
dev->compat_interface = interface;
- ports = of_get_child_by_name(dev->dev->of_node, "ports");
+ ports = of_get_child_by_name(dev->dev->of_node, "ethernet-ports");
+ if (!ports)
+ ports = of_get_child_by_name(dev->dev->of_node, "ports");
if (ports)
for_each_available_child_of_node(ports, port) {
if (of_property_read_u32(port, "reg",
int port_cnt;
int reg_mib_cnt;
int mib_cnt;
- int mib_port_cnt;
- int last_port; /* ports after that not used */
phy_interface_t compat_interface;
u32 regs_size;
bool phy_errata_9477;
val |= 0x190000 << RG_COREPLL_SDM_PCW_S;
mt7530_write(priv, MT7531_PLLGP_CR0, val);
break;
- };
+ }
/* Set feedback divide ratio update signal to high */
val = mt7530_read(priv, MT7531_PLLGP_CR0);
mutex_unlock(&priv->reg_mutex);
}
+static int
+mt7530_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
+{
+ struct mt7530_priv *priv = ds->priv;
+ struct mii_bus *bus = priv->bus;
+ int length;
+ u32 val;
+
+ /* When a new MTU is set, DSA always set the CPU port's MTU to the
+ * largest MTU of the slave ports. Because the switch only has a global
+ * RX length register, only allowing CPU port here is enough.
+ */
+ if (!dsa_is_cpu_port(ds, port))
+ return 0;
+
+ mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+ val = mt7530_mii_read(priv, MT7530_GMACCR);
+ val &= ~MAX_RX_PKT_LEN_MASK;
+
+ /* RX length also includes Ethernet header, MTK tag, and FCS length */
+ length = new_mtu + ETH_HLEN + MTK_HDR_LEN + ETH_FCS_LEN;
+ if (length <= 1522) {
+ val |= MAX_RX_PKT_LEN_1522;
+ } else if (length <= 1536) {
+ val |= MAX_RX_PKT_LEN_1536;
+ } else if (length <= 1552) {
+ val |= MAX_RX_PKT_LEN_1552;
+ } else {
+ val &= ~MAX_RX_JUMBO_MASK;
+ val |= MAX_RX_JUMBO(DIV_ROUND_UP(length, 1024));
+ val |= MAX_RX_PKT_LEN_JUMBO;
+ }
+
+ mt7530_mii_write(priv, MT7530_GMACCR, val);
+
+ mutex_unlock(&bus->mdio_lock);
+
+ return 0;
+}
+
+static int
+mt7530_port_max_mtu(struct dsa_switch *ds, int port)
+{
+ return MT7530_MAX_MTU;
+}
+
static void
mt7530_stp_state_set(struct dsa_switch *ds, int port, u8 state)
{
.get_sset_count = mt7530_get_sset_count,
.port_enable = mt7530_port_enable,
.port_disable = mt7530_port_disable,
+ .port_change_mtu = mt7530_port_change_mtu,
+ .port_max_mtu = mt7530_port_max_mtu,
.port_stp_state_set = mt7530_stp_state_set,
.port_bridge_join = mt7530_port_bridge_join,
.port_bridge_leave = mt7530_port_bridge_leave,
#define MT7530_NUM_FDB_RECORDS 2048
#define MT7530_ALL_MEMBERS 0xff
+#define MTK_HDR_LEN 4
+#define MT7530_MAX_MTU (15 * 1024 - ETH_HLEN - ETH_FCS_LEN - MTK_HDR_LEN)
+
enum mt753x_id {
ID_MT7530 = 0,
ID_MT7621 = 1,
#define MT7531_DBG_CNT(x) (0x3018 + (x) * 0x100)
#define MT7531_DIS_CLR BIT(31)
+#define MT7530_GMACCR 0x30e0
+#define MAX_RX_JUMBO(x) ((x) << 2)
+#define MAX_RX_JUMBO_MASK GENMASK(5, 2)
+#define MAX_RX_PKT_LEN_MASK GENMASK(1, 0)
+#define MAX_RX_PKT_LEN_1522 0x0
+#define MAX_RX_PKT_LEN_1536 0x1
+#define MAX_RX_PKT_LEN_1552 0x2
+#define MAX_RX_PKT_LEN_JUMBO 0x3
+
/* Register for MIB */
#define MT7530_PORT_MIB_COUNTER(x) (0x4000 + (x) * 0x100)
#define MT7530_MIB_CCR 0x4fe0
mv88e6xxx_reg_lock(chip);
if ((!mv88e6xxx_port_ppu_updates(chip, port) ||
- mode == MLO_AN_FIXED) && ops->port_set_link)
- err = ops->port_set_link(chip, port, LINK_FORCED_DOWN);
+ mode == MLO_AN_FIXED) && ops->port_sync_link)
+ err = ops->port_sync_link(chip, port, mode, false);
mv88e6xxx_reg_unlock(chip);
if (err)
goto error;
}
- if (ops->port_set_link)
- err = ops->port_set_link(chip, port, LINK_FORCED_UP);
+ if (ops->port_sync_link)
+ err = ops->port_sync_link(chip, port, mode, true);
}
error:
mv88e6xxx_reg_unlock(chip);
static int mv88e6xxx_vtu_setup(struct mv88e6xxx_chip *chip)
{
- if (!chip->info->max_vid)
+ if (!mv88e6xxx_max_vid(chip))
return 0;
return mv88e6xxx_g1_vtu_flush(chip);
}
/* Set every FID bit used by the VLAN entries */
- vlan.vid = chip->info->max_vid;
+ vlan.vid = mv88e6xxx_max_vid(chip);
vlan.valid = false;
do {
break;
set_bit(vlan.fid, fid_bitmap);
- } while (vlan.vid < chip->info->max_vid);
+ } while (vlan.vid < mv88e6xxx_max_vid(chip));
return 0;
}
int err;
if (switchdev_trans_ph_prepare(trans))
- return chip->info->max_vid ? 0 : -EOPNOTSUPP;
+ return mv88e6xxx_max_vid(chip) ? 0 : -EOPNOTSUPP;
mv88e6xxx_reg_lock(chip);
err = mv88e6xxx_port_set_8021q_mode(chip, port, mode);
struct mv88e6xxx_chip *chip = ds->priv;
int err;
- if (!chip->info->max_vid)
+ if (!mv88e6xxx_max_vid(chip))
return -EOPNOTSUPP;
/* If the requested port doesn't belong to the same bridge as the VLAN
u8 member;
u16 vid;
- if (!chip->info->max_vid)
+ if (!mv88e6xxx_max_vid(chip))
return;
if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port))
u16 pvid, vid;
int err = 0;
- if (!chip->info->max_vid)
+ if (!mv88e6xxx_max_vid(chip))
return -EOPNOTSUPP;
mv88e6xxx_reg_lock(chip);
return err;
/* Dump VLANs' Filtering Information Databases */
- vlan.vid = chip->info->max_vid;
+ vlan.vid = mv88e6xxx_max_vid(chip);
vlan.valid = false;
do {
cb, data);
if (err)
return err;
- } while (vlan.vid < chip->info->max_vid);
+ } while (vlan.vid < mv88e6xxx_max_vid(chip));
return err;
}
chip->ds = ds;
ds->slave_mii_bus = mv88e6xxx_default_mdio_bus(chip);
+ ds->configure_vlan_while_not_filtering = true;
mv88e6xxx_reg_lock(chip);
.phy_read = mv88e6185_phy_ppu_read,
.phy_write = mv88e6185_phy_ppu_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
.phy_read = mv88e6185_phy_ppu_read,
.phy_write = mv88e6185_phy_ppu_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6185_port_sync_link,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_set_frame_mode = mv88e6085_port_set_frame_mode,
.port_set_egress_floods = mv88e6185_port_set_egress_floods,
.stats_get_strings = mv88e6095_stats_get_strings,
.stats_get_stats = mv88e6095_stats_get_stats,
.mgmt_rsvd2cpu = mv88e6185_g2_mgmt_rsvd2cpu,
+ .serdes_power = mv88e6185_serdes_power,
+ .serdes_get_lane = mv88e6185_serdes_get_lane,
+ .serdes_pcs_get_state = mv88e6185_serdes_pcs_get_state,
.ppu_enable = mv88e6185_g1_ppu_enable,
.ppu_disable = mv88e6185_g1_ppu_disable,
.reset = mv88e6185_g1_reset,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6185_port_sync_link,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
.set_egress_port = mv88e6095_g1_set_egress_port,
.watchdog_ops = &mv88e6097_watchdog_ops,
.mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu,
+ .serdes_power = mv88e6185_serdes_power,
+ .serdes_get_lane = mv88e6185_serdes_get_lane,
+ .serdes_pcs_get_state = mv88e6185_serdes_pcs_get_state,
+ .serdes_irq_mapping = mv88e6390_serdes_irq_mapping,
+ .serdes_irq_enable = mv88e6097_serdes_irq_enable,
+ .serdes_irq_status = mv88e6097_serdes_irq_status,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
.rmu_disable = mv88e6085_g1_rmu_disable,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_set_frame_mode = mv88e6085_port_set_frame_mode,
.port_set_egress_floods = mv88e6352_port_set_egress_floods,
.phy_read = mv88e6185_phy_ppu_read,
.phy_write = mv88e6185_phy_ppu_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6341_port_set_speed_duplex,
.port_max_speed_mode = mv88e6341_port_max_speed_mode,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
.phy_read = mv88e6165_phy_read,
.phy_write = mv88e6165_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6352_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6352_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.phy_read = mv88e6185_phy_ppu_read,
.phy_write = mv88e6185_phy_ppu_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6185_port_sync_link,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_set_frame_mode = mv88e6085_port_set_frame_mode,
.port_set_egress_floods = mv88e6185_port_set_egress_floods,
.set_egress_port = mv88e6095_g1_set_egress_port,
.watchdog_ops = &mv88e6097_watchdog_ops,
.mgmt_rsvd2cpu = mv88e6185_g2_mgmt_rsvd2cpu,
+ .serdes_power = mv88e6185_serdes_power,
+ .serdes_get_lane = mv88e6185_serdes_get_lane,
+ .serdes_pcs_get_state = mv88e6185_serdes_pcs_get_state,
.set_cascade_port = mv88e6185_g1_set_cascade_port,
.ppu_enable = mv88e6185_g1_ppu_enable,
.ppu_disable = mv88e6185_g1_ppu_disable,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6390_port_set_speed_duplex,
.port_max_speed_mode = mv88e6390_port_max_speed_mode,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6390x_port_set_speed_duplex,
.port_max_speed_mode = mv88e6390x_port_max_speed_mode,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6390_port_set_speed_duplex,
.port_max_speed_mode = mv88e6390_port_max_speed_mode,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6352_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6250_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6390_port_set_speed_duplex,
.port_max_speed_mode = mv88e6390_port_max_speed_mode,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6341_port_set_speed_duplex,
.port_max_speed_mode = mv88e6341_port_max_speed_mode,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6352_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6390_port_set_speed_duplex,
.port_max_speed_mode = mv88e6390_port_max_speed_mode,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
.port_set_link = mv88e6xxx_port_set_link,
+ .port_sync_link = mv88e6xxx_port_sync_link,
.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
.port_set_speed_duplex = mv88e6390x_port_set_speed_duplex,
.port_max_speed_mode = mv88e6390x_port_max_speed_mode,
MV88E6XXX_REGION_GLOBAL1 = 0,
MV88E6XXX_REGION_GLOBAL2,
MV88E6XXX_REGION_ATU,
+ MV88E6XXX_REGION_VTU,
_MV88E6XXX_REGION_MAX,
};
*/
int (*port_set_link)(struct mv88e6xxx_chip *chip, int port, int link);
+ /* Synchronise the port link state with that of the SERDES
+ */
+ int (*port_sync_link)(struct mv88e6xxx_chip *chip, int port, unsigned int mode, bool isup);
+
#define PAUSE_ON 1
#define PAUSE_OFF 0
return chip->info->num_ports;
}
+static inline unsigned int mv88e6xxx_max_vid(struct mv88e6xxx_chip *chip)
+{
+ return chip->info->max_vid;
+}
+
static inline u16 mv88e6xxx_port_mask(struct mv88e6xxx_chip *chip)
{
return GENMASK((s32)mv88e6xxx_num_ports(chip) - 1, 0);
return err;
}
+/**
+ * struct mv88e6xxx_devlink_vtu_entry - Devlink VTU entry
+ * @fid: Global1/2: FID and VLAN policy.
+ * @sid: Global1/3: SID, unknown filters and learning.
+ * @op: Global1/5: FID (old chipsets).
+ * @vid: Global1/6: VID, valid, and page.
+ * @data: Global1/7-9: Membership data and priority override.
+ * @resvd: Reserved. Also happens to align the size to 16B.
+ *
+ * The VTU entry format varies between chipset generations, the
+ * descriptions above represent the superset of all possible
+ * information, not all fields are valid on all devices. Since this is
+ * a low-level debug interface, copy all data verbatim and defer
+ * parsing to the consumer.
+ */
+struct mv88e6xxx_devlink_vtu_entry {
+ u16 fid;
+ u16 sid;
+ u16 op;
+ u16 vid;
+ u16 data[3];
+ u16 resvd;
+};
+
+static int mv88e6xxx_region_vtu_snapshot(struct devlink *dl,
+ const struct devlink_region_ops *ops,
+ struct netlink_ext_ack *extack,
+ u8 **data)
+{
+ struct mv88e6xxx_devlink_vtu_entry *table, *entry;
+ struct dsa_switch *ds = dsa_devlink_to_ds(dl);
+ struct mv88e6xxx_chip *chip = ds->priv;
+ struct mv88e6xxx_vtu_entry vlan;
+ int err;
+
+ table = kcalloc(mv88e6xxx_max_vid(chip) + 1,
+ sizeof(struct mv88e6xxx_devlink_vtu_entry),
+ GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+
+ entry = table;
+ vlan.vid = mv88e6xxx_max_vid(chip);
+ vlan.valid = false;
+
+ mv88e6xxx_reg_lock(chip);
+
+ do {
+ err = mv88e6xxx_g1_vtu_getnext(chip, &vlan);
+ if (err)
+ break;
+
+ if (!vlan.valid)
+ break;
+
+ err = err ? : mv88e6xxx_g1_read(chip, MV88E6352_G1_VTU_FID,
+ &entry->fid);
+ err = err ? : mv88e6xxx_g1_read(chip, MV88E6352_G1_VTU_SID,
+ &entry->sid);
+ err = err ? : mv88e6xxx_g1_read(chip, MV88E6XXX_G1_VTU_OP,
+ &entry->op);
+ err = err ? : mv88e6xxx_g1_read(chip, MV88E6XXX_G1_VTU_VID,
+ &entry->vid);
+ err = err ? : mv88e6xxx_g1_read(chip, MV88E6XXX_G1_VTU_DATA1,
+ &entry->data[0]);
+ err = err ? : mv88e6xxx_g1_read(chip, MV88E6XXX_G1_VTU_DATA2,
+ &entry->data[1]);
+ err = err ? : mv88e6xxx_g1_read(chip, MV88E6XXX_G1_VTU_DATA3,
+ &entry->data[2]);
+ if (err)
+ break;
+
+ entry++;
+ } while (vlan.vid < mv88e6xxx_max_vid(chip));
+
+ mv88e6xxx_reg_unlock(chip);
+
+ if (err) {
+ kfree(table);
+ return err;
+ }
+
+ *data = (u8 *)table;
+ return 0;
+}
+
static int mv88e6xxx_region_port_snapshot(struct devlink_port *devlink_port,
const struct devlink_port_region_ops *ops,
struct netlink_ext_ack *extack,
.destructor = kfree,
};
+static struct devlink_region_ops mv88e6xxx_region_vtu_ops = {
+ .name = "vtu",
+ .snapshot = mv88e6xxx_region_vtu_snapshot,
+ .destructor = kfree,
+};
+
static const struct devlink_port_region_ops mv88e6xxx_region_port_ops = {
.name = "port",
.snapshot = mv88e6xxx_region_port_snapshot,
.ops = &mv88e6xxx_region_atu_ops
/* calculated at runtime */
},
+ [MV88E6XXX_REGION_VTU] = {
+ .ops = &mv88e6xxx_region_vtu_ops
+ /* calculated at runtime */
+ },
};
static void
ops = mv88e6xxx_regions[i].ops;
size = mv88e6xxx_regions[i].size;
- if (i == MV88E6XXX_REGION_ATU)
+ switch (i) {
+ case MV88E6XXX_REGION_ATU:
size = mv88e6xxx_num_databases(chip) *
sizeof(struct mv88e6xxx_devlink_atu_entry);
+ break;
+ case MV88E6XXX_REGION_VTU:
+ size = mv88e6xxx_max_vid(chip) *
+ sizeof(struct mv88e6xxx_devlink_vtu_entry);
+ break;
+ }
region = dsa_devlink_region_create(ds, ops, 1, size);
if (IS_ERR(region))
int mv88e6165_g1_atu_get_hash(struct mv88e6xxx_chip *chip, u8 *hash);
int mv88e6165_g1_atu_set_hash(struct mv88e6xxx_chip *chip, u8 hash);
+int mv88e6xxx_g1_vtu_getnext(struct mv88e6xxx_chip *chip,
+ struct mv88e6xxx_vtu_entry *entry);
int mv88e6185_g1_vtu_getnext(struct mv88e6xxx_chip *chip,
struct mv88e6xxx_vtu_entry *entry);
int mv88e6185_g1_vtu_loadpurge(struct mv88e6xxx_chip *chip,
return 0;
}
-static int mv88e6xxx_g1_vtu_getnext(struct mv88e6xxx_chip *chip,
- struct mv88e6xxx_vtu_entry *entry)
+int mv88e6xxx_g1_vtu_getnext(struct mv88e6xxx_chip *chip,
+ struct mv88e6xxx_vtu_entry *entry)
{
int err;
return 0;
}
+int mv88e6xxx_port_sync_link(struct mv88e6xxx_chip *chip, int port, unsigned int mode, bool isup)
+{
+ const struct mv88e6xxx_ops *ops = chip->info->ops;
+ int err = 0;
+ int link;
+
+ if (isup)
+ link = LINK_FORCED_UP;
+ else
+ link = LINK_FORCED_DOWN;
+
+ if (ops->port_set_link)
+ err = ops->port_set_link(chip, port, link);
+
+ return err;
+}
+
+int mv88e6185_port_sync_link(struct mv88e6xxx_chip *chip, int port, unsigned int mode, bool isup)
+{
+ const struct mv88e6xxx_ops *ops = chip->info->ops;
+ int err = 0;
+ int link;
+
+ if (mode == MLO_AN_INBAND)
+ link = LINK_UNFORCED;
+ else if (isup)
+ link = LINK_FORCED_UP;
+ else
+ link = LINK_FORCED_DOWN;
+
+ if (ops->port_set_link)
+ err = ops->port_set_link(chip, port, link);
+
+ return err;
+}
+
static int mv88e6xxx_port_set_speed_duplex(struct mv88e6xxx_chip *chip,
int port, int speed, bool alt_bit,
bool force_bit, int duplex)
int mv88e6xxx_port_set_link(struct mv88e6xxx_chip *chip, int port, int link);
+int mv88e6xxx_port_sync_link(struct mv88e6xxx_chip *chip, int port, unsigned int mode, bool isup);
+int mv88e6185_port_sync_link(struct mv88e6xxx_chip *chip, int port, unsigned int mode, bool isup);
+
int mv88e6065_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port,
int speed, int duplex);
int mv88e6185_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port,
{
u16 *p = _p;
u16 reg;
+ int err;
int i;
if (!mv88e6352_port_has_serdes(chip, port))
return;
for (i = 0 ; i < 32; i++) {
- mv88e6352_serdes_read(chip, i, ®);
- p[i] = reg;
+ err = mv88e6352_serdes_read(chip, i, ®);
+ if (!err)
+ p[i] = reg;
}
}
return lane;
}
+int mv88e6185_serdes_power(struct mv88e6xxx_chip *chip, int port, u8 lane,
+ bool up)
+{
+ /* The serdes power can't be controlled on this switch chip but we need
+ * to supply this function to avoid returning -EOPNOTSUPP in
+ * mv88e6xxx_serdes_power_up/mv88e6xxx_serdes_power_down
+ */
+ return 0;
+}
+
+u8 mv88e6185_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
+{
+ /* There are no configurable serdes lanes on this switch chip but we
+ * need to return non-zero so that callers of
+ * mv88e6xxx_serdes_get_lane() know this is a serdes port.
+ */
+ switch (chip->ports[port].cmode) {
+ case MV88E6185_PORT_STS_CMODE_SERDES:
+ case MV88E6185_PORT_STS_CMODE_1000BASE_X:
+ return 0xff;
+ default:
+ return 0;
+ }
+}
+
+int mv88e6185_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
+ u8 lane, struct phylink_link_state *state)
+{
+ int err;
+ u16 status;
+
+ err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &status);
+ if (err)
+ return err;
+
+ state->link = !!(status & MV88E6XXX_PORT_STS_LINK);
+
+ if (state->link) {
+ state->duplex = status & MV88E6XXX_PORT_STS_DUPLEX ? DUPLEX_FULL : DUPLEX_HALF;
+
+ switch (status & MV88E6XXX_PORT_STS_SPEED_MASK) {
+ case MV88E6XXX_PORT_STS_SPEED_1000:
+ state->speed = SPEED_1000;
+ break;
+ case MV88E6XXX_PORT_STS_SPEED_100:
+ state->speed = SPEED_100;
+ break;
+ case MV88E6XXX_PORT_STS_SPEED_10:
+ state->speed = SPEED_10;
+ break;
+ default:
+ dev_err(chip->dev, "invalid PHY speed\n");
+ return -EINVAL;
+ }
+ } else {
+ state->duplex = DUPLEX_UNKNOWN;
+ state->speed = SPEED_UNKNOWN;
+ }
+
+ return 0;
+}
+
+int mv88e6097_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, u8 lane,
+ bool enable)
+{
+ u8 cmode = chip->ports[port].cmode;
+
+ /* The serdes interrupts are enabled in the G2_INT_MASK register. We
+ * need to return 0 to avoid returning -EOPNOTSUPP in
+ * mv88e6xxx_serdes_irq_enable/mv88e6xxx_serdes_irq_disable
+ */
+ switch (cmode) {
+ case MV88E6185_PORT_STS_CMODE_SERDES:
+ case MV88E6185_PORT_STS_CMODE_1000BASE_X:
+ return 0;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+static void mv88e6097_serdes_irq_link(struct mv88e6xxx_chip *chip, int port)
+{
+ u16 status;
+ int err;
+
+ err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &status);
+ if (err) {
+ dev_err(chip->dev, "can't read port status: %d\n", err);
+ return;
+ }
+
+ dsa_port_phylink_mac_change(chip->ds, port, !!(status & MV88E6XXX_PORT_STS_LINK));
+}
+
+irqreturn_t mv88e6097_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
+ u8 lane)
+{
+ u8 cmode = chip->ports[port].cmode;
+
+ switch (cmode) {
+ case MV88E6185_PORT_STS_CMODE_SERDES:
+ case MV88E6185_PORT_STS_CMODE_1000BASE_X:
+ mv88e6097_serdes_irq_link(chip, port);
+ return IRQ_HANDLED;
+ }
+
+ return IRQ_NONE;
+}
+
u8 mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
{
u8 cmode = chip->ports[port].cmode;
u16 *p = _p;
int lane;
u16 reg;
+ int err;
int i;
lane = mv88e6xxx_serdes_get_lane(chip, port);
return;
for (i = 0 ; i < ARRAY_SIZE(mv88e6390_serdes_regs); i++) {
- mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
- mv88e6390_serdes_regs[i], ®);
- p[i] = reg;
+ err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+ mv88e6390_serdes_regs[i], ®);
+ if (!err)
+ p[i] = reg;
}
}
#define MV88E6390_PG_CONTROL 0xf010
#define MV88E6390_PG_CONTROL_ENABLE_PC BIT(0)
+u8 mv88e6185_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
u8 mv88e6341_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
u8 mv88e6352_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
u8 mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
u8 lane, unsigned int mode,
phy_interface_t interface,
const unsigned long *advertise);
+int mv88e6185_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
+ u8 lane, struct phylink_link_state *state);
int mv88e6352_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
u8 lane, struct phylink_link_state *state);
int mv88e6390_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
int port);
unsigned int mv88e6390_serdes_irq_mapping(struct mv88e6xxx_chip *chip,
int port);
+int mv88e6185_serdes_power(struct mv88e6xxx_chip *chip, int port, u8 lane,
+ bool up);
int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, u8 lane,
bool on);
int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, u8 lane,
bool on);
+int mv88e6097_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, u8 lane,
+ bool enable);
int mv88e6352_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, u8 lane,
bool enable);
int mv88e6390_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, u8 lane,
bool enable);
+irqreturn_t mv88e6097_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
+ u8 lane);
irqreturn_t mv88e6352_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
u8 lane);
irqreturn_t mv88e6390_serdes_irq_status(struct mv88e6xxx_chip *chip, int port,
ocelot_port_bridge_leave(ocelot, port, br);
}
-/* This callback needs to be present */
static int felix_vlan_prepare(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_vlan *vlan)
{
+ struct ocelot *ocelot = ds->priv;
+ u16 vid, flags = vlan->flags;
+ int err;
+
+ /* Ocelot switches copy frames as-is to the CPU, so the flags:
+ * egress-untagged or not, pvid or not, make no difference. This
+ * behavior is already better than what DSA just tries to approximate
+ * when it installs the VLAN with the same flags on the CPU port.
+ * Just accept any configuration, and don't let ocelot deny installing
+ * multiple native VLANs on the NPI port, because the switch doesn't
+ * look at the port tag settings towards the NPI interface anyway.
+ */
+ if (port == ocelot->npi)
+ return 0;
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+ err = ocelot_vlan_prepare(ocelot, port, vid,
+ flags & BRIDGE_VLAN_INFO_PVID,
+ flags & BRIDGE_VLAN_INFO_UNTAGGED);
+ if (err)
+ return err;
+ }
+
return 0;
}
u16 vid;
int err;
- if (dsa_is_cpu_port(ds, port))
- flags &= ~BRIDGE_VLAN_INFO_UNTAGGED;
-
for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
err = ocelot_vlan_add(ocelot, port, vid,
flags & BRIDGE_VLAN_INFO_PVID,
dev->flags &= ~IFF_MULTICAST;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST;
- dev->features |= NETIF_F_ALL_TSO;
+ dev->features |= NETIF_F_GSO_SOFTWARE;
dev->features |= NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_LLTX;
dev->features |= NETIF_F_GSO_ENCAP_ALL;
dev->hw_features |= dev->features;
default:
return MAC8390_APPLE;
}
- break;
case NUBUS_DRSW_APPLE:
switch (fres->dr_hw) {
default:
return MAC8390_APPLE;
}
- break;
case NUBUS_DRSW_ASANTE:
return MAC8390_ASANTE;
- break;
case NUBUS_DRSW_TECHWORKS:
case NUBUS_DRSW_DAYNA2:
return MAC8390_CABLETRON;
else
return MAC8390_APPLE;
- break;
case NUBUS_DRSW_FARALLON:
return MAC8390_FARALLON;
- break;
case NUBUS_DRSW_KINETICS:
switch (fres->dr_hw) {
default:
return MAC8390_KINETICS;
}
- break;
case NUBUS_DRSW_DAYNA:
/*
return MAC8390_NONE;
else
return MAC8390_DAYNA;
- break;
}
return MAC8390_NONE;
}
retry:
#endif
-#ifdef NE8390_RW_BUGFIX
+#ifdef NE_RW_BUGFIX
/* Handle the read-before-write bug the same way as the
Crynwr packet driver -- the NatSemi method doesn't work.
Actually this doesn't always work either, but if you have
/* We should already be in page 0, but to be safe... */
outb(E8390_PAGE0+E8390_START+E8390_NODMA, nic_base + NE_CMD);
-#ifdef NE8390_RW_BUGFIX
+#ifdef NE_RW_BUGFIX
/* Handle the read-before-write bug the same way as the
* Crynwr packet driver -- the NatSemi method doesn't work.
* Actually this doesn't always work either, but if you have
* Copyright 2015-2020 Amazon.com, Inc. or its affiliates. All rights reserved.
*/
+#include <linux/ethtool.h>
#include <linux/pci.h>
#include "ena_netdev.h"
for (i = 0; i < sizeof(cfg->prio_tc_map); i++)
cfg->prio_tc_map[i] = cfg->tcs * i / 8;
- cfg->is_qos = (tcs != 0 ? true : false);
+ cfg->is_qos = !!tcs;
cfg->is_ptp = (cfg->tcs <= AQ_HW_PTP_TC);
if (!cfg->is_ptp)
netdev_warn(self->ndev, "%s\n",
#ifndef AQ_NIC_H
#define AQ_NIC_H
+#include <linux/ethtool.h>
+
#include "aq_common.h"
#include "aq_rss.h"
#include "aq_hw.h"
#define DRV_VER_MIN 10
#define DRV_VER_UPD 1
+#include <linux/ethtool.h>
#include <linux/interrupt.h>
#include <linux/rhashtable.h>
#include <linux/crash_dump.h>
return -EPERM;
}
- devlink_flash_update_begin_notify(dl);
devlink_flash_update_status_notify(dl, "Preparing to flash", NULL, 0, 0);
- rc = bnxt_flash_package_from_file(bp->dev, params->file_name, 0);
+ rc = bnxt_flash_package_from_fw_obj(bp->dev, params->fw, 0);
if (!rc)
devlink_flash_update_status_notify(dl, "Flashing done", NULL, 0, 0);
else
devlink_flash_update_status_notify(dl, "Flashing failed", NULL, 0, 0);
- devlink_flash_update_end_notify(dl);
return rc;
}
return rc;
}
-int bnxt_flash_package_from_file(struct net_device *dev, const char *filename,
- u32 install_type)
+int bnxt_flash_package_from_fw_obj(struct net_device *dev, const struct firmware *fw,
+ u32 install_type)
{
struct bnxt *bp = netdev_priv(dev);
struct hwrm_nvm_install_update_output *resp = bp->hwrm_cmd_resp_addr;
struct hwrm_nvm_install_update_input install = {0};
- const struct firmware *fw;
u32 item_len;
int rc = 0;
u16 index;
return rc;
}
- rc = request_firmware(&fw, filename, &dev->dev);
- if (rc != 0) {
- netdev_err(dev, "PKG error %d requesting file: %s\n",
- rc, filename);
- return rc;
- }
-
if (fw->size > item_len) {
netdev_err(dev, "PKG insufficient update area in nvram: %lu\n",
(unsigned long)fw->size);
dma_handle);
}
}
- release_firmware(fw);
if (rc)
goto err_exit;
return rc;
}
+static int bnxt_flash_package_from_file(struct net_device *dev, const char *filename,
+ u32 install_type)
+{
+ const struct firmware *fw;
+ int rc;
+
+ rc = request_firmware(&fw, filename, &dev->dev);
+ if (rc != 0) {
+ netdev_err(dev, "PKG error %d requesting file: %s\n",
+ rc, filename);
+ return rc;
+ }
+
+ rc = bnxt_flash_package_from_fw_obj(dev, fw, install_type);
+
+ release_firmware(fw);
+
+ return rc;
+}
+
static int bnxt_flash_device(struct net_device *dev,
struct ethtool_flash *flash)
{
u16 bnxt_get_fw_auto_link_speeds(u32);
int bnxt_hwrm_nvm_get_dev_info(struct bnxt *bp,
struct hwrm_nvm_get_dev_info_output *nvm_dev_info);
-int bnxt_flash_package_from_file(struct net_device *dev, const char *filename,
- u32 install_type);
+int bnxt_flash_package_from_fw_obj(struct net_device *dev, const struct firmware *fw,
+ u32 install_type);
void bnxt_ethtool_init(struct bnxt *bp);
void bnxt_ethtool_free(struct bnxt *bp);
* the Free Software Foundation.
*/
+#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
#define MACB_RBQPH 0x04D4
/* GEM register offsets. */
+#define GEM_NCR 0x0000 /* Network Control */
#define GEM_NCFGR 0x0004 /* Network Config */
#define GEM_USRIO 0x000c /* User IO */
#define GEM_DMACFG 0x0010 /* DMA Configuration */
#define GEM_JML 0x0048 /* Jumbo Max Length */
+#define GEM_HS_MAC_CONFIG 0x0050 /* GEM high speed config */
#define GEM_HRB 0x0080 /* Hash Bottom */
#define GEM_HRT 0x0084 /* Hash Top */
#define GEM_SA1B 0x0088 /* Specific1 Bottom */
#define GEM_DCFG7 0x0298 /* Design Config 7 */
#define GEM_DCFG8 0x029C /* Design Config 8 */
#define GEM_DCFG10 0x02A4 /* Design Config 10 */
+#define GEM_DCFG12 0x02AC /* Design Config 12 */
+#define GEM_USX_CONTROL 0x0A80 /* High speed PCS control register */
+#define GEM_USX_STATUS 0x0A88 /* High speed PCS status register */
#define GEM_TXBDCTRL 0x04cc /* TX Buffer Descriptor control register */
#define GEM_RXBDCTRL 0x04d0 /* RX Buffer Descriptor control register */
#define MACB_IRXFCS_OFFSET 19
#define MACB_IRXFCS_SIZE 1
+/* GEM specific NCR bitfields. */
+#define GEM_ENABLE_HS_MAC_OFFSET 31
+#define GEM_ENABLE_HS_MAC_SIZE 1
+
/* GEM specific NCFGR bitfields. */
+#define GEM_FD_OFFSET 1 /* Full duplex */
+#define GEM_FD_SIZE 1
#define GEM_GBE_OFFSET 10 /* Gigabit mode enable */
#define GEM_GBE_SIZE 1
#define GEM_PCSSEL_OFFSET 11
#define GEM_PCSSEL_SIZE 1
+#define GEM_PAE_OFFSET 13 /* Pause enable */
+#define GEM_PAE_SIZE 1
#define GEM_CLK_OFFSET 18 /* MDC clock division */
#define GEM_CLK_SIZE 3
#define GEM_DBW_OFFSET 21 /* Data bus width */
#define MACB_REV_OFFSET 0
#define MACB_REV_SIZE 16
+/* Bitfield in HS_MAC_CONFIG */
+#define GEM_HS_MAC_SPEED_OFFSET 0
+#define GEM_HS_MAC_SPEED_SIZE 3
+
/* Bitfields in DCFG1. */
#define GEM_IRQCOR_OFFSET 23
#define GEM_IRQCOR_SIZE 1
#define GEM_DBWDEF_OFFSET 25
#define GEM_DBWDEF_SIZE 3
+#define GEM_NO_PCS_OFFSET 0
+#define GEM_NO_PCS_SIZE 1
/* Bitfields in DCFG2. */
#define GEM_RX_PKT_BUFF_OFFSET 20
#define GEM_RXBD_RDBUFF_OFFSET 8
#define GEM_RXBD_RDBUFF_SIZE 4
+/* Bitfields in DCFG12. */
+#define GEM_HIGH_SPEED_OFFSET 26
+#define GEM_HIGH_SPEED_SIZE 1
+
+/* Bitfields in USX_CONTROL. */
+#define GEM_USX_CTRL_SPEED_OFFSET 14
+#define GEM_USX_CTRL_SPEED_SIZE 3
+#define GEM_SERDES_RATE_OFFSET 12
+#define GEM_SERDES_RATE_SIZE 2
+#define GEM_RX_SCR_BYPASS_OFFSET 9
+#define GEM_RX_SCR_BYPASS_SIZE 1
+#define GEM_TX_SCR_BYPASS_OFFSET 8
+#define GEM_TX_SCR_BYPASS_SIZE 1
+#define GEM_TX_EN_OFFSET 1
+#define GEM_TX_EN_SIZE 1
+#define GEM_SIGNAL_OK_OFFSET 0
+#define GEM_SIGNAL_OK_SIZE 1
+
+/* Bitfields in USX_STATUS. */
+#define GEM_USX_BLOCK_LOCK_OFFSET 0
+#define GEM_USX_BLOCK_LOCK_SIZE 1
+
/* Bitfields in TISUBN */
#define GEM_SUBNSINCR_OFFSET 0
#define GEM_SUBNSINCRL_OFFSET 24
#define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000
#define MACB_CAPS_SG_DISABLED 0x40000000
#define MACB_CAPS_MACB_IS_GEM 0x80000000
+#define MACB_CAPS_PCS 0x01000000
+#define MACB_CAPS_HIGH_SPEED 0x02000000
/* LSO settings */
#define MACB_LSO_UFO_ENABLE 0x01
struct mii_bus *mii_bus;
struct phylink *phylink;
struct phylink_config phylink_config;
+ struct phylink_pcs phylink_pcs;
u32 caps;
unsigned int dma_burst_length;
#define MACB_WOL_HAS_MAGIC_PACKET (0x1 << 0)
#define MACB_WOL_ENABLED (0x1 << 1)
+#define HS_SPEED_10000M 4
+#define MACB_SERDES_RATE_10G 1
+
/* Graceful stop timeouts in us. We should allow up to
* 1 frame time (10 Mbits/s, full-duplex, ignoring collisions)
*/
state->interface != PHY_INTERFACE_MODE_RMII &&
state->interface != PHY_INTERFACE_MODE_GMII &&
state->interface != PHY_INTERFACE_MODE_SGMII &&
+ state->interface != PHY_INTERFACE_MODE_10GBASER &&
!phy_interface_mode_is_rgmii(state->interface)) {
bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
return;
return;
}
+ if (state->interface == PHY_INTERFACE_MODE_10GBASER &&
+ !(bp->caps & MACB_CAPS_HIGH_SPEED &&
+ bp->caps & MACB_CAPS_PCS)) {
+ bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
+ return;
+ }
+
phylink_set_port_modes(mask);
phylink_set(mask, Autoneg);
phylink_set(mask, Asym_Pause);
+ if (bp->caps & MACB_CAPS_GIGABIT_MODE_AVAILABLE &&
+ (state->interface == PHY_INTERFACE_MODE_NA ||
+ state->interface == PHY_INTERFACE_MODE_10GBASER)) {
+ phylink_set(mask, 10000baseCR_Full);
+ phylink_set(mask, 10000baseER_Full);
+ phylink_set(mask, 10000baseKR_Full);
+ phylink_set(mask, 10000baseLR_Full);
+ phylink_set(mask, 10000baseLRM_Full);
+ phylink_set(mask, 10000baseSR_Full);
+ phylink_set(mask, 10000baseT_Full);
+ if (state->interface != PHY_INTERFACE_MODE_NA)
+ goto out;
+ }
+
phylink_set(mask, 10baseT_Half);
phylink_set(mask, 10baseT_Full);
phylink_set(mask, 100baseT_Half);
if (!(bp->caps & MACB_CAPS_NO_GIGABIT_HALF))
phylink_set(mask, 1000baseT_Half);
}
-
+out:
bitmap_and(supported, supported, mask, __ETHTOOL_LINK_MODE_MASK_NBITS);
bitmap_and(state->advertising, state->advertising, mask,
__ETHTOOL_LINK_MODE_MASK_NBITS);
}
-static void macb_mac_pcs_get_state(struct phylink_config *config,
+static void macb_usx_pcs_link_up(struct phylink_pcs *pcs, unsigned int mode,
+ phy_interface_t interface, int speed,
+ int duplex)
+{
+ struct macb *bp = container_of(pcs, struct macb, phylink_pcs);
+ u32 config;
+
+ config = gem_readl(bp, USX_CONTROL);
+ config = GEM_BFINS(SERDES_RATE, MACB_SERDES_RATE_10G, config);
+ config = GEM_BFINS(USX_CTRL_SPEED, HS_SPEED_10000M, config);
+ config &= ~(GEM_BIT(TX_SCR_BYPASS) | GEM_BIT(RX_SCR_BYPASS));
+ config |= GEM_BIT(TX_EN);
+ gem_writel(bp, USX_CONTROL, config);
+}
+
+static void macb_usx_pcs_get_state(struct phylink_pcs *pcs,
struct phylink_link_state *state)
+{
+ struct macb *bp = container_of(pcs, struct macb, phylink_pcs);
+ u32 val;
+
+ state->speed = SPEED_10000;
+ state->duplex = 1;
+ state->an_complete = 1;
+
+ val = gem_readl(bp, USX_STATUS);
+ state->link = !!(val & GEM_BIT(USX_BLOCK_LOCK));
+ val = gem_readl(bp, NCFGR);
+ if (val & GEM_BIT(PAE))
+ state->pause = MLO_PAUSE_RX;
+}
+
+static int macb_usx_pcs_config(struct phylink_pcs *pcs,
+ unsigned int mode,
+ phy_interface_t interface,
+ const unsigned long *advertising,
+ bool permit_pause_to_mac)
+{
+ struct macb *bp = container_of(pcs, struct macb, phylink_pcs);
+
+ gem_writel(bp, USX_CONTROL, gem_readl(bp, USX_CONTROL) |
+ GEM_BIT(SIGNAL_OK));
+
+ return 0;
+}
+
+static void macb_pcs_get_state(struct phylink_pcs *pcs,
+ struct phylink_link_state *state)
{
state->link = 0;
}
-static void macb_mac_an_restart(struct phylink_config *config)
+static void macb_pcs_an_restart(struct phylink_pcs *pcs)
{
/* Not supported */
}
+static int macb_pcs_config(struct phylink_pcs *pcs,
+ unsigned int mode,
+ phy_interface_t interface,
+ const unsigned long *advertising,
+ bool permit_pause_to_mac)
+{
+ return 0;
+}
+
+static const struct phylink_pcs_ops macb_phylink_usx_pcs_ops = {
+ .pcs_get_state = macb_usx_pcs_get_state,
+ .pcs_config = macb_usx_pcs_config,
+ .pcs_link_up = macb_usx_pcs_link_up,
+};
+
+static const struct phylink_pcs_ops macb_phylink_pcs_ops = {
+ .pcs_get_state = macb_pcs_get_state,
+ .pcs_an_restart = macb_pcs_an_restart,
+ .pcs_config = macb_pcs_config,
+};
+
static void macb_mac_config(struct phylink_config *config, unsigned int mode,
const struct phylink_link_state *state)
{
struct macb *bp = netdev_priv(ndev);
unsigned long flags;
u32 old_ctrl, ctrl;
+ u32 old_ncr, ncr;
spin_lock_irqsave(&bp->lock, flags);
old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR);
+ old_ncr = ncr = macb_or_gem_readl(bp, NCR);
if (bp->caps & MACB_CAPS_MACB_IS_EMAC) {
if (state->interface == PHY_INTERFACE_MODE_RMII)
ctrl |= MACB_BIT(RM9200_RMII);
} else if (macb_is_gem(bp)) {
ctrl &= ~(GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL));
+ ncr &= ~GEM_BIT(ENABLE_HS_MAC);
- if (state->interface == PHY_INTERFACE_MODE_SGMII)
+ if (state->interface == PHY_INTERFACE_MODE_SGMII) {
ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
+ } else if (state->interface == PHY_INTERFACE_MODE_10GBASER) {
+ ctrl |= GEM_BIT(PCSSEL);
+ ncr |= GEM_BIT(ENABLE_HS_MAC);
+ }
}
/* Apply the new configuration, if any */
if (old_ctrl ^ ctrl)
macb_or_gem_writel(bp, NCFGR, ctrl);
+ if (old_ncr ^ ncr)
+ macb_or_gem_writel(bp, NCR, ncr);
+
spin_unlock_irqrestore(&bp->lock, flags);
}
macb_or_gem_writel(bp, NCFGR, ctrl);
+ if (bp->phy_interface == PHY_INTERFACE_MODE_10GBASER)
+ gem_writel(bp, HS_MAC_CONFIG, GEM_BFINS(HS_MAC_SPEED, HS_SPEED_10000M,
+ gem_readl(bp, HS_MAC_CONFIG)));
+
spin_unlock_irqrestore(&bp->lock, flags);
/* Enable Rx and Tx */
netif_tx_wake_all_queues(ndev);
}
+static int macb_mac_prepare(struct phylink_config *config, unsigned int mode,
+ phy_interface_t interface)
+{
+ struct net_device *ndev = to_net_dev(config->dev);
+ struct macb *bp = netdev_priv(ndev);
+
+ if (interface == PHY_INTERFACE_MODE_10GBASER)
+ bp->phylink_pcs.ops = &macb_phylink_usx_pcs_ops;
+ else if (interface == PHY_INTERFACE_MODE_SGMII)
+ bp->phylink_pcs.ops = &macb_phylink_pcs_ops;
+ else
+ bp->phylink_pcs.ops = NULL;
+
+ if (bp->phylink_pcs.ops)
+ phylink_set_pcs(bp->phylink, &bp->phylink_pcs);
+
+ return 0;
+}
+
static const struct phylink_mac_ops macb_phylink_ops = {
.validate = macb_validate,
- .mac_pcs_get_state = macb_mac_pcs_get_state,
- .mac_an_restart = macb_mac_an_restart,
+ .mac_prepare = macb_mac_prepare,
.mac_config = macb_mac_config,
.mac_link_down = macb_mac_link_down,
.mac_link_up = macb_mac_link_up,
dcfg = gem_readl(bp, DCFG1);
if (GEM_BFEXT(IRQCOR, dcfg) == 0)
bp->caps |= MACB_CAPS_ISR_CLEAR_ON_WRITE;
+ if (GEM_BFEXT(NO_PCS, dcfg) == 0)
+ bp->caps |= MACB_CAPS_PCS;
+ dcfg = gem_readl(bp, DCFG12);
+ if (GEM_BFEXT(HIGH_SPEED, dcfg) == 1)
+ bp->caps |= MACB_CAPS_HIGH_SPEED;
dcfg = gem_readl(bp, DCFG2);
if ((dcfg & (GEM_BIT(RX_PKT_BUFF) | GEM_BIT(TX_PKT_BUFF))) == 0)
bp->caps |= MACB_CAPS_FIFO_MODE;
}
if (IS_ERR_OR_NULL(*pclk)) {
- err = PTR_ERR(*pclk);
- if (!err)
- err = -ENODEV;
-
+ err = IS_ERR(*pclk) ? PTR_ERR(*pclk) : -ENODEV;
dev_err(&pdev->dev, "failed to get macb_clk (%d)\n", err);
return err;
}
if (IS_ERR_OR_NULL(*hclk)) {
- err = PTR_ERR(*hclk);
- if (!err)
- err = -ENODEV;
-
+ err = IS_ERR(*hclk) ? PTR_ERR(*hclk) : -ENODEV;
dev_err(&pdev->dev, "failed to get hclk (%d)\n", err);
return err;
}
#include "cn66xx_device.h"
#include "cn68xx_device.h"
#include "cn68xx_regs.h"
-#include "cn68xx_device.h"
static void lio_cn68xx_set_dpi_regs(struct octeon_device *oct)
{
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
* NONINFRINGEMENT. See the GNU General Public License for more details.
***********************************************************************/
+#include <linux/ethtool.h>
#include <linux/netdevice.h>
#include <linux/net_tstamp.h>
#include <linux/pci.h>
/* ETHTOOL Support for VNIC_VF Device*/
+#include <linux/ethtool.h>
#include <linux/pci.h>
#include <linux/net_tstamp.h>
#include <linux/bitops.h>
#include <linux/cache.h>
+#include <linux/ethtool.h>
#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/netdevice.h>
seq_printf(seq, "%-12s", s); \
for (i = 0; i < n; ++i) \
seq_printf(seq, " %16" fmt_spec, v); \
- seq_putc(seq, '\n'); \
+ seq_putc(seq, '\n'); \
} while (0)
#define S(s, v) S3("s", s, v)
#define T3(fmt_spec, s, v) S3(fmt_spec, s, tx[i].v)
* SOFTWARE.
*/
+#include <linux/ethtool.h>
#include <linux/pci.h>
#include "t4vf_common.h"
struct list_head na_node;
unsigned int send_page_order;
int max_host_sndbuf;
+ u32 round_robin_cnt;
struct key_map kmap;
unsigned int cdev_state;
};
csk->sndbuf = csk->snd_win;
csk->ulp_mode = ULP_MODE_TLS;
step = cdev->lldi->nrxq / cdev->lldi->nchan;
- csk->rss_qid = cdev->lldi->rxq_ids[port_id * step];
rxq_idx = port_id * step;
+ rxq_idx += cdev->round_robin_cnt++ % step;
+ csk->rss_qid = cdev->lldi->rxq_ids[rxq_idx];
csk->txq_idx = (rxq_idx < cdev->lldi->ntxq) ? rxq_idx :
port_id * step;
csk->sndbuf = newsk->sk_sndbuf;
config DM9000
tristate "DM9000 support"
- depends on ARM || MIPS || COLDFIRE || NIOS2
+ depends on ARM || MIPS || COLDFIRE || NIOS2 || COMPILE_TEST
select CRC32
select MII
help
static void dm9000_dumpblk_8bit(void __iomem *reg, int count)
{
int i;
- int tmp;
for (i = 0; i < count; i++)
- tmp = readb(reg);
+ readb(reg);
}
static void dm9000_dumpblk_16bit(void __iomem *reg, int count)
{
int i;
- int tmp;
count = (count + 1) >> 1;
for (i = 0; i < count; i++)
- tmp = readw(reg);
+ readw(reg);
}
static void dm9000_dumpblk_32bit(void __iomem *reg, int count)
{
int i;
- int tmp;
count = (count + 3) >> 2;
for (i = 0; i < count; i++)
- tmp = readl(reg);
+ readl(reg);
}
/*
static SIMPLE_DEV_PM_OPS(de_pm_ops, de_suspend, de_resume);
+static void de_shutdown(struct pci_dev *pdev)
+{
+ struct net_device *dev = pci_get_drvdata(pdev);
+
+ rtnl_lock();
+ dev_close(dev);
+ rtnl_unlock();
+}
+
static struct pci_driver de_driver = {
.name = DRV_NAME,
.id_table = de_pci_tbl,
.probe = de_init_one,
.remove = de_remove_one,
+ .shutdown = de_shutdown,
.driver.pm = &de_pm_ops,
};
static unsigned char last_phys_addr[ETH_ALEN] = {
0x00, 'L', 'i', 'n', 'u', 'x'
};
+#if defined(__i386__) || defined(__x86_64__) /* Patch up x86 BIOS bug. */
static int last_irq;
+#endif
int i, irq;
unsigned short sum;
unsigned char *ee_data;
for (i = 0; i < 6; i++)
last_phys_addr[i] = dev->dev_addr[i];
+#if defined(__i386__) || defined(__x86_64__) /* Patch up x86 BIOS bug. */
last_irq = irq;
+#endif
/* The lower four bits are the media type. */
if (board_idx >= 0 && board_idx < MAX_UNITS) {
schedule_work(&priv->reset_task);
}
-static int ftgmac100_mii_probe(struct ftgmac100 *priv, phy_interface_t intf)
+static int ftgmac100_mii_probe(struct net_device *netdev)
{
- struct net_device *netdev = priv->netdev;
+ struct ftgmac100 *priv = netdev_priv(netdev);
+ struct platform_device *pdev = to_platform_device(priv->dev);
+ struct device_node *np = pdev->dev.of_node;
struct phy_device *phydev;
+ phy_interface_t phy_intf;
+ int err;
+
+ /* Default to RGMII. It's a gigabit part after all */
+ err = of_get_phy_mode(np, &phy_intf);
+ if (err)
+ phy_intf = PHY_INTERFACE_MODE_RGMII;
+
+ /* Aspeed only supports these. I don't know about other IP
+ * block vendors so I'm going to just let them through for
+ * now. Note that this is only a warning if for some obscure
+ * reason the DT really means to lie about it or it's a newer
+ * part we don't know about.
+ *
+ * On the Aspeed SoC there are additionally straps and SCU
+ * control bits that could tell us what the interface is
+ * (or allow us to configure it while the IP block is held
+ * in reset). For now I chose to keep this driver away from
+ * those SoC specific bits and assume the device-tree is
+ * right and the SCU has been configured properly by pinmux
+ * or the firmware.
+ */
+ if (priv->is_aspeed && !(phy_interface_mode_is_rgmii(phy_intf))) {
+ netdev_warn(netdev,
+ "Unsupported PHY mode %s !\n",
+ phy_modes(phy_intf));
+ }
phydev = phy_find_first(priv->mii_bus);
if (!phydev) {
}
phydev = phy_connect(netdev, phydev_name(phydev),
- &ftgmac100_adjust_link, intf);
+ &ftgmac100_adjust_link, phy_intf);
if (IS_ERR(phydev)) {
netdev_err(netdev, "%s: Could not attach to PHY\n", netdev->name);
{
struct ftgmac100 *priv = netdev_priv(netdev);
struct platform_device *pdev = to_platform_device(priv->dev);
- phy_interface_t phy_intf = PHY_INTERFACE_MODE_RGMII;
struct device_node *np = pdev->dev.of_node;
+ struct device_node *mdio_np;
int i, err = 0;
u32 reg;
iowrite32(reg, priv->base + FTGMAC100_OFFSET_REVR);
}
- /* Get PHY mode from device-tree */
- if (np) {
- /* Default to RGMII. It's a gigabit part after all */
- err = of_get_phy_mode(np, &phy_intf);
- if (err)
- phy_intf = PHY_INTERFACE_MODE_RGMII;
-
- /* Aspeed only supports these. I don't know about other IP
- * block vendors so I'm going to just let them through for
- * now. Note that this is only a warning if for some obscure
- * reason the DT really means to lie about it or it's a newer
- * part we don't know about.
- *
- * On the Aspeed SoC there are additionally straps and SCU
- * control bits that could tell us what the interface is
- * (or allow us to configure it while the IP block is held
- * in reset). For now I chose to keep this driver away from
- * those SoC specific bits and assume the device-tree is
- * right and the SCU has been configured properly by pinmux
- * or the firmware.
- */
- if (priv->is_aspeed &&
- phy_intf != PHY_INTERFACE_MODE_RMII &&
- phy_intf != PHY_INTERFACE_MODE_RGMII &&
- phy_intf != PHY_INTERFACE_MODE_RGMII_ID &&
- phy_intf != PHY_INTERFACE_MODE_RGMII_RXID &&
- phy_intf != PHY_INTERFACE_MODE_RGMII_TXID) {
- netdev_warn(netdev,
- "Unsupported PHY mode %s !\n",
- phy_modes(phy_intf));
- }
- }
-
priv->mii_bus->name = "ftgmac100_mdio";
snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%d",
pdev->name, pdev->id);
for (i = 0; i < PHY_MAX_ADDR; i++)
priv->mii_bus->irq[i] = PHY_POLL;
- err = mdiobus_register(priv->mii_bus);
+ mdio_np = of_get_child_by_name(np, "mdio");
+
+ err = of_mdiobus_register(priv->mii_bus, mdio_np);
if (err) {
dev_err(priv->dev, "Cannot register MDIO bus!\n");
goto err_register_mdiobus;
}
- err = ftgmac100_mii_probe(priv, phy_intf);
- if (err) {
- dev_err(priv->dev, "MII Probe failed!\n");
- goto err_mii_probe;
- }
+ of_node_put(mdio_np);
return 0;
-err_mii_probe:
- mdiobus_unregister(priv->mii_bus);
err_register_mdiobus:
mdiobus_free(priv->mii_bus);
return err;
}
+static void ftgmac100_phy_disconnect(struct net_device *netdev)
+{
+ if (!netdev->phydev)
+ return;
+
+ phy_disconnect(netdev->phydev);
+}
+
static void ftgmac100_destroy_mdio(struct net_device *netdev)
{
struct ftgmac100 *priv = netdev_priv(netdev);
- if (!netdev->phydev)
+ if (!priv->mii_bus)
return;
- phy_disconnect(netdev->phydev);
mdiobus_unregister(priv->mii_bus);
mdiobus_free(priv->mii_bus);
}
if (np && of_get_property(np, "use-ncsi", NULL)) {
if (!IS_ENABLED(CONFIG_NET_NCSI)) {
dev_err(&pdev->dev, "NCSI stack not enabled\n");
- goto err_ncsi_dev;
+ goto err_phy_connect;
}
dev_info(&pdev->dev, "Using NCSI interface\n");
priv->use_ncsi = true;
priv->ndev = ncsi_register_dev(netdev, ftgmac100_ncsi_handler);
if (!priv->ndev)
- goto err_ncsi_dev;
+ goto err_phy_connect;
} else if (np && of_get_property(np, "phy-handle", NULL)) {
struct phy_device *phy;
+ /* Support "mdio"/"phy" child nodes for ast2400/2500 with
+ * an embedded MDIO controller. Automatically scan the DTS for
+ * available PHYs and register them.
+ */
+ if (of_device_is_compatible(np, "aspeed,ast2400-mac") ||
+ of_device_is_compatible(np, "aspeed,ast2500-mac")) {
+ err = ftgmac100_setup_mdio(netdev);
+ if (err)
+ goto err_setup_mdio;
+ }
+
phy = of_phy_get_and_connect(priv->netdev, np,
&ftgmac100_adjust_link);
if (!phy) {
dev_err(&pdev->dev, "Failed to connect to phy\n");
- goto err_setup_mdio;
+ goto err_phy_connect;
}
/* Indicate that we support PAUSE frames (see comment in
err = ftgmac100_setup_mdio(netdev);
if (err)
goto err_setup_mdio;
+
+ err = ftgmac100_mii_probe(netdev);
+ if (err) {
+ dev_err(priv->dev, "MII probe failed!\n");
+ goto err_ncsi_dev;
+ }
+
}
if (priv->is_aspeed) {
err = ftgmac100_setup_clk(priv);
if (err)
- goto err_ncsi_dev;
+ goto err_phy_connect;
}
/* Default ring sizes */
err_register_netdev:
clk_disable_unprepare(priv->rclk);
clk_disable_unprepare(priv->clk);
+err_phy_connect:
+ ftgmac100_phy_disconnect(netdev);
err_ncsi_dev:
if (priv->ndev)
ncsi_unregister_dev(priv->ndev);
*/
cancel_work_sync(&priv->reset_task);
+ ftgmac100_phy_disconnect(netdev);
ftgmac100_destroy_mdio(netdev);
iounmap(priv->base);
#include <linux/dma-mapping.h>
#include <linux/sort.h>
#include <linux/phy_fixed.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
#include <soc/fsl/bman.h>
#include <soc/fsl/qman.h>
#include "fman.h"
#define DPAA_HWA_SIZE (DPAA_PARSE_RESULTS_SIZE + DPAA_TIME_STAMP_SIZE \
+ DPAA_HASH_RESULTS_SIZE)
#define DPAA_RX_PRIV_DATA_DEFAULT_SIZE (DPAA_TX_PRIV_DATA_SIZE + \
- dpaa_rx_extra_headroom)
+ XDP_PACKET_HEADROOM - DPAA_HWA_SIZE)
#ifdef CONFIG_DPAA_ERRATUM_A050385
#define DPAA_RX_PRIV_DATA_A050385_SIZE (DPAA_A050385_ALIGN - DPAA_HWA_SIZE)
#define DPAA_RX_PRIV_DATA_SIZE (fman_has_errata_a050385() ? \
dpaa_fq->fqid = qman_fq_fqid(fq);
+ if (dpaa_fq->fq_type == FQ_TYPE_RX_DEFAULT ||
+ dpaa_fq->fq_type == FQ_TYPE_RX_PCD) {
+ err = xdp_rxq_info_reg(&dpaa_fq->xdp_rxq, dpaa_fq->net_dev,
+ dpaa_fq->fqid);
+ if (err) {
+ dev_err(dev, "xdp_rxq_info_reg() = %d\n", err);
+ return err;
+ }
+
+ err = xdp_rxq_info_reg_mem_model(&dpaa_fq->xdp_rxq,
+ MEM_TYPE_PAGE_ORDER0, NULL);
+ if (err) {
+ dev_err(dev, "xdp_rxq_info_reg_mem_model() = %d\n",
+ err);
+ xdp_rxq_info_unreg(&dpaa_fq->xdp_rxq);
+ return err;
+ }
+ }
+
return 0;
}
}
}
+ if ((dpaa_fq->fq_type == FQ_TYPE_RX_DEFAULT ||
+ dpaa_fq->fq_type == FQ_TYPE_RX_PCD) &&
+ xdp_rxq_info_is_reg(&dpaa_fq->xdp_rxq))
+ xdp_rxq_info_unreg(&dpaa_fq->xdp_rxq);
+
qman_destroy_fq(fq);
list_del(&dpaa_fq->list);
*
* Return the skb backpointer, since for S/G frames the buffer containing it
* gets freed here.
+ *
+ * No skb backpointer is set when transmitting XDP frames. Cleanup the buffer
+ * and return NULL in this case.
*/
static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
const struct qm_fd *fd, bool ts)
dma_addr_t addr = qm_fd_addr(fd);
void *vaddr = phys_to_virt(addr);
const struct qm_sg_entry *sgt;
+ struct dpaa_eth_swbp *swbp;
struct sk_buff *skb;
u64 ns;
int i;
}
} else {
dma_unmap_single(priv->tx_dma_dev, addr,
- priv->tx_headroom + qm_fd_get_length(fd),
+ qm_fd_get_offset(fd) + qm_fd_get_length(fd),
dma_dir);
}
- skb = *(struct sk_buff **)vaddr;
+ swbp = (struct dpaa_eth_swbp *)vaddr;
+ skb = swbp->skb;
+
+ /* No skb backpointer is set when running XDP. An xdp_frame
+ * backpointer is saved instead.
+ */
+ if (!skb) {
+ xdp_return_frame(swbp->xdpf);
+ return NULL;
+ }
/* DMA unmapping is required before accessing the HW provided info */
if (ts && priv->tx_tstamp &&
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
if (WARN_ONCE(!skb, "Build skb failure on Rx\n"))
goto free_buffer;
- WARN_ON(fd_off != priv->rx_headroom);
skb_reserve(skb, fd_off);
skb_put(skb, qm_fd_get_length(fd));
{
struct net_device *net_dev = priv->net_dev;
enum dma_data_direction dma_dir;
+ struct dpaa_eth_swbp *swbp;
unsigned char *buff_start;
- struct sk_buff **skbh;
dma_addr_t addr;
int err;
buff_start = skb->data - priv->tx_headroom;
dma_dir = DMA_TO_DEVICE;
- skbh = (struct sk_buff **)buff_start;
- *skbh = skb;
+ swbp = (struct dpaa_eth_swbp *)buff_start;
+ swbp->skb = skb;
/* Enable L3/L4 hardware checksum computation.
*
const enum dma_data_direction dma_dir = DMA_TO_DEVICE;
const int nr_frags = skb_shinfo(skb)->nr_frags;
struct net_device *net_dev = priv->net_dev;
+ struct dpaa_eth_swbp *swbp;
struct qm_sg_entry *sgt;
- struct sk_buff **skbh;
void *buff_start;
skb_frag_t *frag;
dma_addr_t addr;
qm_fd_set_sg(fd, priv->tx_headroom, skb->len);
/* DMA map the SGT page */
- skbh = (struct sk_buff **)buff_start;
- *skbh = skb;
+ swbp = (struct dpaa_eth_swbp *)buff_start;
+ swbp->skb = skb;
addr = dma_map_page(priv->tx_dma_dev, p, 0,
priv->tx_headroom + DPAA_SGT_SIZE, dma_dir);
}
#ifdef CONFIG_DPAA_ERRATUM_A050385
-static int dpaa_a050385_wa(struct net_device *net_dev, struct sk_buff **s)
+static int dpaa_a050385_wa_skb(struct net_device *net_dev, struct sk_buff **s)
{
struct dpaa_priv *priv = netdev_priv(net_dev);
struct sk_buff *new_skb, *skb = *s;
return 0;
}
+
+static int dpaa_a050385_wa_xdpf(struct dpaa_priv *priv,
+ struct xdp_frame **init_xdpf)
+{
+ struct xdp_frame *new_xdpf, *xdpf = *init_xdpf;
+ void *new_buff;
+ struct page *p;
+
+ /* Check the data alignment and make sure the headroom is large
+ * enough to store the xdpf backpointer. Use an aligned headroom
+ * value.
+ *
+ * Due to alignment constraints, we give XDP access to the full 256
+ * byte frame headroom. If the XDP program uses all of it, copy the
+ * data to a new buffer and make room for storing the backpointer.
+ */
+ if (PTR_IS_ALIGNED(xdpf->data, DPAA_A050385_ALIGN) &&
+ xdpf->headroom >= priv->tx_headroom) {
+ xdpf->headroom = priv->tx_headroom;
+ return 0;
+ }
+
+ p = dev_alloc_pages(0);
+ if (unlikely(!p))
+ return -ENOMEM;
+
+ /* Copy the data to the new buffer at a properly aligned offset */
+ new_buff = page_address(p);
+ memcpy(new_buff + priv->tx_headroom, xdpf->data, xdpf->len);
+
+ /* Create an XDP frame around the new buffer in a similar fashion
+ * to xdp_convert_buff_to_frame.
+ */
+ new_xdpf = new_buff;
+ new_xdpf->data = new_buff + priv->tx_headroom;
+ new_xdpf->len = xdpf->len;
+ new_xdpf->headroom = priv->tx_headroom;
+ new_xdpf->frame_sz = DPAA_BP_RAW_SIZE;
+ new_xdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
+
+ /* Release the initial buffer */
+ xdp_return_frame_rx_napi(xdpf);
+
+ *init_xdpf = new_xdpf;
+ return 0;
+}
#endif
static netdev_tx_t
#ifdef CONFIG_DPAA_ERRATUM_A050385
if (unlikely(fman_has_errata_a050385())) {
- if (dpaa_a050385_wa(net_dev, &skb))
+ if (dpaa_a050385_wa_skb(net_dev, &skb))
goto enomem;
nonlinear = skb_is_nonlinear(skb);
}
{
struct dpaa_napi_portal *np =
container_of(napi, struct dpaa_napi_portal, napi);
+ int cleaned;
- int cleaned = qman_p_poll_dqrr(np->p, budget);
+ np->xdp_act = 0;
+
+ cleaned = qman_p_poll_dqrr(np->p, budget);
if (cleaned < budget) {
napi_complete_done(napi, cleaned);
qman_p_irqsource_add(np->p, QM_PIRQ_DQRI);
}
+ if (np->xdp_act & XDP_REDIRECT)
+ xdp_do_flush();
+
return cleaned;
}
}
static inline int dpaa_eth_napi_schedule(struct dpaa_percpu_priv *percpu_priv,
- struct qman_portal *portal)
+ struct qman_portal *portal, bool sched_napi)
{
- if (unlikely(in_irq() || !in_serving_softirq())) {
+ if (sched_napi) {
/* Disable QMan IRQ and invoke NAPI */
qman_p_irqsource_remove(portal, QM_PIRQ_DQRI);
static enum qman_cb_dqrr_result rx_error_dqrr(struct qman_portal *portal,
struct qman_fq *fq,
- const struct qm_dqrr_entry *dq)
+ const struct qm_dqrr_entry *dq,
+ bool sched_napi)
{
struct dpaa_fq *dpaa_fq = container_of(fq, struct dpaa_fq, fq_base);
struct dpaa_percpu_priv *percpu_priv;
percpu_priv = this_cpu_ptr(priv->percpu_priv);
- if (dpaa_eth_napi_schedule(percpu_priv, portal))
+ if (dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi))
return qman_cb_dqrr_stop;
dpaa_eth_refill_bpools(priv);
return qman_cb_dqrr_consume;
}
+static int dpaa_xdp_xmit_frame(struct net_device *net_dev,
+ struct xdp_frame *xdpf)
+{
+ struct dpaa_priv *priv = netdev_priv(net_dev);
+ struct rtnl_link_stats64 *percpu_stats;
+ struct dpaa_percpu_priv *percpu_priv;
+ struct dpaa_eth_swbp *swbp;
+ struct netdev_queue *txq;
+ void *buff_start;
+ struct qm_fd fd;
+ dma_addr_t addr;
+ int err;
+
+ percpu_priv = this_cpu_ptr(priv->percpu_priv);
+ percpu_stats = &percpu_priv->stats;
+
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+ if (unlikely(fman_has_errata_a050385())) {
+ if (dpaa_a050385_wa_xdpf(priv, &xdpf)) {
+ err = -ENOMEM;
+ goto out_error;
+ }
+ }
+#endif
+
+ if (xdpf->headroom < DPAA_TX_PRIV_DATA_SIZE) {
+ err = -EINVAL;
+ goto out_error;
+ }
+
+ buff_start = xdpf->data - xdpf->headroom;
+
+ /* Leave empty the skb backpointer at the start of the buffer.
+ * Save the XDP frame for easy cleanup on confirmation.
+ */
+ swbp = (struct dpaa_eth_swbp *)buff_start;
+ swbp->skb = NULL;
+ swbp->xdpf = xdpf;
+
+ qm_fd_clear_fd(&fd);
+ fd.bpid = FSL_DPAA_BPID_INV;
+ fd.cmd |= cpu_to_be32(FM_FD_CMD_FCO);
+ qm_fd_set_contig(&fd, xdpf->headroom, xdpf->len);
+
+ addr = dma_map_single(priv->tx_dma_dev, buff_start,
+ xdpf->headroom + xdpf->len,
+ DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(priv->tx_dma_dev, addr))) {
+ err = -EINVAL;
+ goto out_error;
+ }
+
+ qm_fd_addr_set64(&fd, addr);
+
+ /* Bump the trans_start */
+ txq = netdev_get_tx_queue(net_dev, smp_processor_id());
+ txq->trans_start = jiffies;
+
+ err = dpaa_xmit(priv, percpu_stats, smp_processor_id(), &fd);
+ if (err) {
+ dma_unmap_single(priv->tx_dma_dev, addr,
+ qm_fd_get_offset(&fd) + qm_fd_get_length(&fd),
+ DMA_TO_DEVICE);
+ goto out_error;
+ }
+
+ return 0;
+
+out_error:
+ percpu_stats->tx_errors++;
+ return err;
+}
+
+static u32 dpaa_run_xdp(struct dpaa_priv *priv, struct qm_fd *fd, void *vaddr,
+ struct dpaa_fq *dpaa_fq, unsigned int *xdp_meta_len)
+{
+ ssize_t fd_off = qm_fd_get_offset(fd);
+ struct bpf_prog *xdp_prog;
+ struct xdp_frame *xdpf;
+ struct xdp_buff xdp;
+ u32 xdp_act;
+ int err;
+
+ rcu_read_lock();
+
+ xdp_prog = READ_ONCE(priv->xdp_prog);
+ if (!xdp_prog) {
+ rcu_read_unlock();
+ return XDP_PASS;
+ }
+
+ xdp.data = vaddr + fd_off;
+ xdp.data_meta = xdp.data;
+ xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
+ xdp.data_end = xdp.data + qm_fd_get_length(fd);
+ xdp.frame_sz = DPAA_BP_RAW_SIZE - DPAA_TX_PRIV_DATA_SIZE;
+ xdp.rxq = &dpaa_fq->xdp_rxq;
+
+ /* We reserve a fixed headroom of 256 bytes under the erratum and we
+ * offer it all to XDP programs to use. If no room is left for the
+ * xdpf backpointer on TX, we will need to copy the data.
+ * Disable metadata support since data realignments might be required
+ * and the information can be lost.
+ */
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+ if (unlikely(fman_has_errata_a050385())) {
+ xdp_set_data_meta_invalid(&xdp);
+ xdp.data_hard_start = vaddr;
+ xdp.frame_sz = DPAA_BP_RAW_SIZE;
+ }
+#endif
+
+ xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+ /* Update the length and the offset of the FD */
+ qm_fd_set_contig(fd, xdp.data - vaddr, xdp.data_end - xdp.data);
+
+ switch (xdp_act) {
+ case XDP_PASS:
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+ *xdp_meta_len = xdp_data_meta_unsupported(&xdp) ? 0 :
+ xdp.data - xdp.data_meta;
+#else
+ *xdp_meta_len = xdp.data - xdp.data_meta;
+#endif
+ break;
+ case XDP_TX:
+ /* We can access the full headroom when sending the frame
+ * back out
+ */
+ xdp.data_hard_start = vaddr;
+ xdp.frame_sz = DPAA_BP_RAW_SIZE;
+ xdpf = xdp_convert_buff_to_frame(&xdp);
+ if (unlikely(!xdpf)) {
+ free_pages((unsigned long)vaddr, 0);
+ break;
+ }
+
+ if (dpaa_xdp_xmit_frame(priv->net_dev, xdpf))
+ xdp_return_frame_rx_napi(xdpf);
+
+ break;
+ case XDP_REDIRECT:
+ /* Allow redirect to use the full headroom */
+ xdp.data_hard_start = vaddr;
+ xdp.frame_sz = DPAA_BP_RAW_SIZE;
+
+ err = xdp_do_redirect(priv->net_dev, &xdp, xdp_prog);
+ if (err) {
+ trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act);
+ free_pages((unsigned long)vaddr, 0);
+ }
+ break;
+ default:
+ bpf_warn_invalid_xdp_action(xdp_act);
+ fallthrough;
+ case XDP_ABORTED:
+ trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act);
+ fallthrough;
+ case XDP_DROP:
+ /* Free the buffer */
+ free_pages((unsigned long)vaddr, 0);
+ break;
+ }
+
+ rcu_read_unlock();
+
+ return xdp_act;
+}
+
static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
struct qman_fq *fq,
- const struct qm_dqrr_entry *dq)
+ const struct qm_dqrr_entry *dq,
+ bool sched_napi)
{
+ bool ts_valid = false, hash_valid = false;
struct skb_shared_hwtstamps *shhwtstamps;
+ unsigned int skb_len, xdp_meta_len = 0;
struct rtnl_link_stats64 *percpu_stats;
struct dpaa_percpu_priv *percpu_priv;
const struct qm_fd *fd = &dq->fd;
dma_addr_t addr = qm_fd_addr(fd);
+ struct dpaa_napi_portal *np;
enum qm_fd_format fd_format;
struct net_device *net_dev;
u32 fd_status, hash_offset;
+ struct qm_sg_entry *sgt;
struct dpaa_bp *dpaa_bp;
+ struct dpaa_fq *dpaa_fq;
struct dpaa_priv *priv;
- unsigned int skb_len;
struct sk_buff *skb;
int *count_ptr;
+ u32 xdp_act;
void *vaddr;
+ u32 hash;
u64 ns;
+ np = container_of(&portal, struct dpaa_napi_portal, p);
+ dpaa_fq = container_of(fq, struct dpaa_fq, fq_base);
fd_status = be32_to_cpu(fd->status);
fd_format = qm_fd_get_format(fd);
- net_dev = ((struct dpaa_fq *)fq)->net_dev;
+ net_dev = dpaa_fq->net_dev;
priv = netdev_priv(net_dev);
dpaa_bp = dpaa_bpid2pool(dq->fd.bpid);
if (!dpaa_bp)
percpu_priv = this_cpu_ptr(priv->percpu_priv);
percpu_stats = &percpu_priv->stats;
- if (unlikely(dpaa_eth_napi_schedule(percpu_priv, portal)))
+ if (unlikely(dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi)))
return qman_cb_dqrr_stop;
/* Make sure we didn't run out of buffers */
count_ptr = this_cpu_ptr(dpaa_bp->percpu_count);
(*count_ptr)--;
- if (likely(fd_format == qm_fd_contig))
+ /* Extract the timestamp stored in the headroom before running XDP */
+ if (priv->rx_tstamp) {
+ if (!fman_port_get_tstamp(priv->mac_dev->port[RX], vaddr, &ns))
+ ts_valid = true;
+ else
+ WARN_ONCE(1, "fman_port_get_tstamp failed!\n");
+ }
+
+ /* Extract the hash stored in the headroom before running XDP */
+ if (net_dev->features & NETIF_F_RXHASH && priv->keygen_in_use &&
+ !fman_port_get_hash_result_offset(priv->mac_dev->port[RX],
+ &hash_offset)) {
+ hash = be32_to_cpu(*(u32 *)(vaddr + hash_offset));
+ hash_valid = true;
+ }
+
+ if (likely(fd_format == qm_fd_contig)) {
+ xdp_act = dpaa_run_xdp(priv, (struct qm_fd *)fd, vaddr,
+ dpaa_fq, &xdp_meta_len);
+ np->xdp_act |= xdp_act;
+ if (xdp_act != XDP_PASS) {
+ percpu_stats->rx_packets++;
+ percpu_stats->rx_bytes += qm_fd_get_length(fd);
+ return qman_cb_dqrr_consume;
+ }
skb = contig_fd_to_skb(priv, fd);
- else
+ } else {
+ /* XDP doesn't support S/G frames. Return the fragments to the
+ * buffer pool and release the SGT.
+ */
+ if (READ_ONCE(priv->xdp_prog)) {
+ WARN_ONCE(1, "S/G frames not supported under XDP\n");
+ sgt = vaddr + qm_fd_get_offset(fd);
+ dpaa_release_sgt_members(sgt);
+ free_pages((unsigned long)vaddr, 0);
+ return qman_cb_dqrr_consume;
+ }
skb = sg_fd_to_skb(priv, fd);
+ }
if (!skb)
return qman_cb_dqrr_consume;
- if (priv->rx_tstamp) {
+ if (xdp_meta_len)
+ skb_metadata_set(skb, xdp_meta_len);
+
+ /* Set the previously extracted timestamp */
+ if (ts_valid) {
shhwtstamps = skb_hwtstamps(skb);
memset(shhwtstamps, 0, sizeof(*shhwtstamps));
-
- if (!fman_port_get_tstamp(priv->mac_dev->port[RX], vaddr, &ns))
- shhwtstamps->hwtstamp = ns_to_ktime(ns);
- else
- dev_warn(net_dev->dev.parent, "fman_port_get_tstamp failed!\n");
+ shhwtstamps->hwtstamp = ns_to_ktime(ns);
}
skb->protocol = eth_type_trans(skb, net_dev);
- if (net_dev->features & NETIF_F_RXHASH && priv->keygen_in_use &&
- !fman_port_get_hash_result_offset(priv->mac_dev->port[RX],
- &hash_offset)) {
+ /* Set the previously extracted hash */
+ if (hash_valid) {
enum pkt_hash_types type;
/* if L4 exists, it was used in the hash generation */
type = be32_to_cpu(fd->status) & FM_FD_STAT_L4CV ?
PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3;
- skb_set_hash(skb, be32_to_cpu(*(u32 *)(vaddr + hash_offset)),
- type);
+ skb_set_hash(skb, hash, type);
}
skb_len = skb->len;
static enum qman_cb_dqrr_result conf_error_dqrr(struct qman_portal *portal,
struct qman_fq *fq,
- const struct qm_dqrr_entry *dq)
+ const struct qm_dqrr_entry *dq,
+ bool sched_napi)
{
struct dpaa_percpu_priv *percpu_priv;
struct net_device *net_dev;
percpu_priv = this_cpu_ptr(priv->percpu_priv);
- if (dpaa_eth_napi_schedule(percpu_priv, portal))
+ if (dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi))
return qman_cb_dqrr_stop;
dpaa_tx_error(net_dev, priv, percpu_priv, &dq->fd, fq->fqid);
static enum qman_cb_dqrr_result conf_dflt_dqrr(struct qman_portal *portal,
struct qman_fq *fq,
- const struct qm_dqrr_entry *dq)
+ const struct qm_dqrr_entry *dq,
+ bool sched_napi)
{
struct dpaa_percpu_priv *percpu_priv;
struct net_device *net_dev;
percpu_priv = this_cpu_ptr(priv->percpu_priv);
- if (dpaa_eth_napi_schedule(percpu_priv, portal))
+ if (dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi))
return qman_cb_dqrr_stop;
dpaa_tx_conf(net_dev, priv, percpu_priv, &dq->fd, fq->fqid);
for_each_online_cpu(i) {
percpu_priv = per_cpu_ptr(priv->percpu_priv, i);
- percpu_priv->np.down = 0;
+ percpu_priv->np.down = false;
napi_enable(&percpu_priv->np.napi);
}
}
for_each_online_cpu(i) {
percpu_priv = per_cpu_ptr(priv->percpu_priv, i);
- percpu_priv->np.down = 1;
+ percpu_priv->np.down = true;
napi_disable(&percpu_priv->np.napi);
}
}
return err;
}
+static bool xdp_validate_mtu(struct dpaa_priv *priv, int mtu)
+{
+ int max_contig_data = priv->dpaa_bp->size - priv->rx_headroom;
+
+ /* We do not support S/G fragments when XDP is enabled.
+ * Limit the MTU in relation to the buffer size.
+ */
+ if (mtu + VLAN_ETH_HLEN + ETH_FCS_LEN > max_contig_data) {
+ dev_warn(priv->net_dev->dev.parent,
+ "The maximum MTU for XDP is %d\n",
+ max_contig_data - VLAN_ETH_HLEN - ETH_FCS_LEN);
+ return false;
+ }
+
+ return true;
+}
+
+static int dpaa_change_mtu(struct net_device *net_dev, int new_mtu)
+{
+ struct dpaa_priv *priv = netdev_priv(net_dev);
+
+ if (priv->xdp_prog && !xdp_validate_mtu(priv, new_mtu))
+ return -EINVAL;
+
+ net_dev->mtu = new_mtu;
+ return 0;
+}
+
+static int dpaa_setup_xdp(struct net_device *net_dev, struct netdev_bpf *bpf)
+{
+ struct dpaa_priv *priv = netdev_priv(net_dev);
+ struct bpf_prog *old_prog;
+ int err;
+ bool up;
+
+ /* S/G fragments are not supported in XDP-mode */
+ if (bpf->prog && !xdp_validate_mtu(priv, net_dev->mtu)) {
+ NL_SET_ERR_MSG_MOD(bpf->extack, "MTU too large for XDP");
+ return -EINVAL;
+ }
+
+ up = netif_running(net_dev);
+
+ if (up)
+ dpaa_eth_stop(net_dev);
+
+ old_prog = xchg(&priv->xdp_prog, bpf->prog);
+ if (old_prog)
+ bpf_prog_put(old_prog);
+
+ if (up) {
+ err = dpaa_open(net_dev);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(bpf->extack, "dpaa_open() failed");
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+static int dpaa_xdp(struct net_device *net_dev, struct netdev_bpf *xdp)
+{
+ switch (xdp->command) {
+ case XDP_SETUP_PROG:
+ return dpaa_setup_xdp(net_dev, xdp);
+ default:
+ return -EINVAL;
+ }
+}
+
+static int dpaa_xdp_xmit(struct net_device *net_dev, int n,
+ struct xdp_frame **frames, u32 flags)
+{
+ struct xdp_frame *xdpf;
+ int i, err, drops = 0;
+
+ if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+ return -EINVAL;
+
+ if (!netif_running(net_dev))
+ return -ENETDOWN;
+
+ for (i = 0; i < n; i++) {
+ xdpf = frames[i];
+ err = dpaa_xdp_xmit_frame(net_dev, xdpf);
+ if (err) {
+ xdp_return_frame_rx_napi(xdpf);
+ drops++;
+ }
+ }
+
+ return n - drops;
+}
+
static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
{
struct dpaa_priv *priv = netdev_priv(dev);
.ndo_set_rx_mode = dpaa_set_rx_mode,
.ndo_do_ioctl = dpaa_ioctl,
.ndo_setup_tc = dpaa_setup_tc,
+ .ndo_change_mtu = dpaa_change_mtu,
+ .ndo_bpf = dpaa_xdp,
+ .ndo_xdp_xmit = dpaa_xdp_xmit,
};
static int dpaa_napi_add(struct net_device *net_dev)
*/
headroom = (u16)(bl[port].priv_data_size + DPAA_HWA_SIZE);
- if (port == RX)
+ if (port == RX) {
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+ if (unlikely(fman_has_errata_a050385()))
+ headroom = XDP_PACKET_HEADROOM;
+#endif
+
return ALIGN(headroom, DPAA_FD_RX_DATA_ALIGNMENT);
- else
+ } else {
return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT);
+ }
}
static int dpaa_eth_probe(struct platform_device *pdev)
u16 channel;
u8 wq;
enum dpaa_fq_type fq_type;
+ struct xdp_rxq_info xdp_rxq;
};
struct dpaa_fq_cbs {
struct napi_struct napi;
struct qman_portal *p;
bool down;
+ int xdp_act;
};
struct dpaa_percpu_priv {
u16 priv_data_size;
};
+/* Information to be used on the Tx confirmation path. Stored just
+ * before the start of the transmit buffer. Maximum size allowed
+ * is DPAA_TX_PRIV_DATA_SIZE bytes.
+ */
+struct dpaa_eth_swbp {
+ struct sk_buff *skb;
+ struct xdp_frame *xdpf;
+};
+
struct dpaa_priv {
struct dpaa_percpu_priv __percpu *percpu_priv;
struct dpaa_bp *dpaa_bp;
bool tx_tstamp; /* Tx timestamping enabled */
bool rx_tstamp; /* Rx timestamping enabled */
+
+ struct bpf_prog *xdp_prog;
};
/* from dpaa_ethtool.c */
if (skb->cb[0] == TX_TSTAMP_ONESTEP_SYNC) {
if (dpaa2_eth_ptp_parse(skb, &msgtype, &twostep, &udp,
&offset1, &offset2) ||
- msgtype != 0 || twostep) {
+ msgtype != PTP_MSGTYPE_SYNC || twostep) {
WARN_ONCE(1, "Bad packet for one-step timestamping\n");
return;
}
if (skb->cb[0] == TX_TSTAMP_ONESTEP_SYNC) {
if (!dpaa2_eth_ptp_parse(skb, &msgtype, &twostep, &udp,
&offset1, &offset2))
- if (msgtype == 0 && twostep == 0) {
+ if (msgtype == PTP_MSGTYPE_SYNC && twostep == 0) {
skb_queue_tail(&priv->tx_skbs, skb);
queue_work(priv->dpaa2_ptp_wq,
&priv->tx_onestep_tstamp);
return NETDEV_TX_OK;
}
-static bool enetc_tx_csum(struct sk_buff *skb, union enetc_tx_bd *txbd)
-{
- int l3_start, l3_hsize;
- u16 l3_flags, l4_flags;
-
- if (skb->ip_summed != CHECKSUM_PARTIAL)
- return false;
-
- switch (skb->csum_offset) {
- case offsetof(struct tcphdr, check):
- l4_flags = ENETC_TXBD_L4_TCP;
- break;
- case offsetof(struct udphdr, check):
- l4_flags = ENETC_TXBD_L4_UDP;
- break;
- default:
- skb_checksum_help(skb);
- return false;
- }
-
- l3_start = skb_network_offset(skb);
- l3_hsize = skb_network_header_len(skb);
-
- l3_flags = 0;
- if (skb->protocol == htons(ETH_P_IPV6))
- l3_flags = ENETC_TXBD_L3_IPV6;
-
- /* write BD fields */
- txbd->l3_csoff = enetc_txbd_l3_csoff(l3_start, l3_hsize, l3_flags);
- txbd->l4_csoff = l4_flags;
-
- return true;
-}
-
static void enetc_unmap_tx_buff(struct enetc_bdr *tx_ring,
struct enetc_tx_swbd *tx_swbd)
{
if (do_vlan || do_tstamp)
flags |= ENETC_TXBD_FLAGS_EX;
- if (enetc_tx_csum(skb, &temp_bd))
- flags |= ENETC_TXBD_FLAGS_CSUM | ENETC_TXBD_FLAGS_L4CS;
- else if (tx_ring->tsd_enable)
+ if (tx_ring->tsd_enable)
flags |= ENETC_TXBD_FLAGS_TSE | ENETC_TXBD_FLAGS_TXSTART;
/* first BD needs frm_len and offload flags set */
temp_bd.frm_len = cpu_to_le16(skb->len);
temp_bd.flags = flags;
- if (flags & ENETC_TXBD_FLAGS_TSE) {
- u32 temp;
-
- temp = (skb->skb_mstamp_ns >> 5 & ENETC_TXBD_TXSTART_MASK)
- | (flags << ENETC_TXBD_FLAGS_OFFSET);
- temp_bd.txstart = cpu_to_le32(temp);
- }
+ if (flags & ENETC_TXBD_FLAGS_TSE)
+ temp_bd.txstart = enetc_txbd_set_tx_start(skb->skb_mstamp_ns,
+ flags);
if (flags & ENETC_TXBD_FLAGS_EX) {
u8 e_flags = 0;
static void enetc_detect_errata(struct enetc_si *si)
{
if (si->pdev->revision == ENETC_REV1)
- si->errata = ENETC_ERR_TXCSUM | ENETC_ERR_VLAN_ISOL |
- ENETC_ERR_UCMCSWP;
+ si->errata = ENETC_ERR_VLAN_ISOL | ENETC_ERR_UCMCSWP;
}
int enetc_pci_probe(struct pci_dev *pdev, const char *name, int sizeof_priv)
#define ENETC_REV1 0x1
enum enetc_errata {
- ENETC_ERR_TXCSUM = BIT(0),
- ENETC_ERR_VLAN_ISOL = BIT(1),
- ENETC_ERR_UCMCSWP = BIT(2),
+ ENETC_ERR_VLAN_ISOL = BIT(0),
+ ENETC_ERR_UCMCSWP = BIT(1),
};
#define ENETC_SI_F_QBV BIT(0)
__le16 frm_len;
union {
struct {
- __le16 l3_csoff;
- u8 l4_csoff;
+ u8 reserved[3];
u8 flags;
}; /* default layout */
__le32 txstart;
} wb; /* writeback descriptor */
};
-#define ENETC_TXBD_FLAGS_L4CS BIT(0)
-#define ENETC_TXBD_FLAGS_TSE BIT(1)
-#define ENETC_TXBD_FLAGS_W BIT(2)
-#define ENETC_TXBD_FLAGS_CSUM BIT(3)
-#define ENETC_TXBD_FLAGS_TXSTART BIT(4)
-#define ENETC_TXBD_FLAGS_EX BIT(6)
-#define ENETC_TXBD_FLAGS_F BIT(7)
+enum enetc_txbd_flags {
+ ENETC_TXBD_FLAGS_RES0 = BIT(0), /* reserved */
+ ENETC_TXBD_FLAGS_TSE = BIT(1),
+ ENETC_TXBD_FLAGS_W = BIT(2),
+ ENETC_TXBD_FLAGS_RES3 = BIT(3), /* reserved */
+ ENETC_TXBD_FLAGS_TXSTART = BIT(4),
+ ENETC_TXBD_FLAGS_EX = BIT(6),
+ ENETC_TXBD_FLAGS_F = BIT(7)
+};
#define ENETC_TXBD_TXSTART_MASK GENMASK(24, 0)
#define ENETC_TXBD_FLAGS_OFFSET 24
+
+static inline __le32 enetc_txbd_set_tx_start(u64 tx_start, u8 flags)
+{
+ u32 temp;
+
+ temp = (tx_start >> 5 & ENETC_TXBD_TXSTART_MASK) |
+ (flags << ENETC_TXBD_FLAGS_OFFSET);
+
+ return cpu_to_le32(temp);
+}
+
static inline void enetc_clear_tx_bd(union enetc_tx_bd *txbd)
{
memset(txbd, 0, sizeof(*txbd));
}
-/* L3 csum flags */
-#define ENETC_TXBD_L3_IPCS BIT(7)
-#define ENETC_TXBD_L3_IPV6 BIT(15)
-
-#define ENETC_TXBD_L3_START_MASK GENMASK(6, 0)
-#define ENETC_TXBD_L3_SET_HSIZE(val) ((((val) >> 2) & 0x7f) << 8)
-
/* Extension flags */
#define ENETC_TXBD_E_FLAGS_VLAN_INS BIT(0)
#define ENETC_TXBD_E_FLAGS_TWO_STEP_PTP BIT(2)
-static inline __le16 enetc_txbd_l3_csoff(int start, int hdr_sz, u16 l3_flags)
-{
- return cpu_to_le16(l3_flags | ENETC_TXBD_L3_SET_HSIZE(hdr_sz) |
- (start & ENETC_TXBD_L3_START_MASK));
-}
-
-/* L4 csum flags */
-#define ENETC_TXBD_L4_UDP BIT(5)
-#define ENETC_TXBD_L4_TCP BIT(6)
-
union enetc_rx_bd {
struct {
__le64 addr;
u8 smac_m[6];
u8 dmac_h[6];
u8 dmac_m[6];
- u32 sip_h[4];
- u32 sip_m[4];
- u32 dip_h[4];
- u32 dip_m[4];
+ __be32 sip_h[4];
+ __be32 sip_m[4];
+ __be32 dip_h[4];
+ __be32 dip_m[4];
u16 ethtype_h;
u16 ethtype_m;
u16 ethtype4_h;
ndev->watchdog_timeo = 5 * HZ;
ndev->max_mtu = ENETC_MAX_MTU;
- ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+ ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK;
- ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG |
- NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+ ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM |
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX;
if (si->num_rss)
ndev->hw_features |= NETIF_F_RXHASH;
- if (si->errata & ENETC_ERR_TXCSUM) {
- ndev->hw_features &= ~NETIF_F_HW_CSUM;
- ndev->features &= ~NETIF_F_HW_CSUM;
- }
-
ndev->priv_flags |= IFF_UNICAST_FLT;
if (si->hw_features & ENETC_SI_F_QBV)
return -ENOMEM;
}
- cbd.addr[0] = lower_32_bits(dma);
- cbd.addr[1] = upper_32_bits(dma);
+ cbd.addr[0] = cpu_to_le32(lower_32_bits(dma));
+ cbd.addr[1] = cpu_to_le32(upper_32_bits(dma));
cbd.cls = BDCR_CMD_PORT_GCL;
cbd.status_flags = 0;
return -ENOMEM;
}
- cbd.addr[0] = lower_32_bits(dma);
- cbd.addr[1] = upper_32_bits(dma);
+ cbd.addr[0] = cpu_to_le32(lower_32_bits(dma));
+ cbd.addr[1] = cpu_to_le32(upper_32_bits(dma));
eth_broadcast_addr(si_data->dmac);
- si_data->vid_vidm_tg =
- cpu_to_le16(ENETC_CBDR_SID_VID_MASK
- + ((0x3 << 14) | ENETC_CBDR_SID_VIDM));
+ si_data->vid_vidm_tg = (ENETC_CBDR_SID_VID_MASK
+ + ((0x3 << 14) | ENETC_CBDR_SID_VIDM));
si_conf = &cbd.sid_set;
/* Only one port supported for one entry, set itself */
- si_conf->iports = 1 << enetc_get_port(priv);
+ si_conf->iports = cpu_to_le32(1 << enetc_get_port(priv));
si_conf->id_type = 1;
si_conf->oui[2] = 0x0;
si_conf->oui[1] = 0x80;
si_conf->en = 0x80;
si_conf->stream_handle = cpu_to_le32(sid->handle);
- si_conf->iports = 1 << enetc_get_port(priv);
+ si_conf->iports = cpu_to_le32(1 << enetc_get_port(priv));
si_conf->id_type = sid->filtertype;
si_conf->oui[2] = 0x0;
si_conf->oui[1] = 0x80;
cbd.length = cpu_to_le16(data_size);
- cbd.addr[0] = lower_32_bits(dma);
- cbd.addr[1] = upper_32_bits(dma);
+ cbd.addr[0] = cpu_to_le32(lower_32_bits(dma));
+ cbd.addr[1] = cpu_to_le32(upper_32_bits(dma));
/* VIDM default to be 1.
* VID Match. If set (b1) then the VID must match, otherwise
*/
if (si_conf->id_type == STREAMID_TYPE_NULL) {
ether_addr_copy(si_data->dmac, sid->dst_mac);
- si_data->vid_vidm_tg =
- cpu_to_le16((sid->vid & ENETC_CBDR_SID_VID_MASK) +
- ((((u16)(sid->tagged) & 0x3) << 14)
- | ENETC_CBDR_SID_VIDM));
+ si_data->vid_vidm_tg = (sid->vid & ENETC_CBDR_SID_VID_MASK) +
+ ((((u16)(sid->tagged) & 0x3) << 14)
+ | ENETC_CBDR_SID_VIDM);
} else if (si_conf->id_type == STREAMID_TYPE_SMAC) {
ether_addr_copy(si_data->smac, sid->src_mac);
- si_data->vid_vidm_tg =
- cpu_to_le16((sid->vid & ENETC_CBDR_SID_VID_MASK) +
- ((((u16)(sid->tagged) & 0x3) << 14)
- | ENETC_CBDR_SID_VIDM));
+ si_data->vid_vidm_tg = (sid->vid & ENETC_CBDR_SID_VID_MASK) +
+ ((((u16)(sid->tagged) & 0x3) << 14)
+ | ENETC_CBDR_SID_VIDM);
}
err = enetc_send_cmd(priv->si, &cbd);
}
sfi_config->sg_inst_table_index = cpu_to_le16(sfi->gate_id);
- sfi_config->input_ports = 1 << enetc_get_port(priv);
+ sfi_config->input_ports = cpu_to_le32(1 << enetc_get_port(priv));
/* The priority value which may be matched against the
* frame’s priority value to determine a match for this entry.
err = -ENOMEM;
goto exit;
}
- cbd.addr[0] = lower_32_bits(dma);
- cbd.addr[1] = upper_32_bits(dma);
+ cbd.addr[0] = cpu_to_le32(lower_32_bits(dma));
+ cbd.addr[1] = cpu_to_le32(upper_32_bits(dma));
cbd.length = cpu_to_le16(data_size);
if (err)
goto exit;
- cnt->matching_frames_count =
- ((u64)le32_to_cpu(data_buf->matchh) << 32)
- + data_buf->matchl;
+ cnt->matching_frames_count = ((u64)data_buf->matchh << 32) +
+ data_buf->matchl;
- cnt->not_passing_sdu_count =
- ((u64)le32_to_cpu(data_buf->msdu_droph) << 32)
- + data_buf->msdu_dropl;
+ cnt->not_passing_sdu_count = ((u64)data_buf->msdu_droph << 32) +
+ data_buf->msdu_dropl;
cnt->passing_sdu_count = cnt->matching_frames_count
- cnt->not_passing_sdu_count;
cnt->not_passing_frames_count =
- ((u64)le32_to_cpu(data_buf->stream_gate_droph) << 32)
- + le32_to_cpu(data_buf->stream_gate_dropl);
+ ((u64)data_buf->stream_gate_droph << 32) +
+ data_buf->stream_gate_dropl;
- cnt->passing_frames_count = cnt->matching_frames_count
- - cnt->not_passing_sdu_count
- - cnt->not_passing_frames_count;
+ cnt->passing_frames_count = cnt->matching_frames_count -
+ cnt->not_passing_sdu_count -
+ cnt->not_passing_frames_count;
- cnt->red_frames_count =
- ((u64)le32_to_cpu(data_buf->flow_meter_droph) << 32)
- + le32_to_cpu(data_buf->flow_meter_dropl);
+ cnt->red_frames_count = ((u64)data_buf->flow_meter_droph << 32) +
+ data_buf->flow_meter_dropl;
exit:
kfree(data_buf);
return -ENOMEM;
}
- cbd.addr[0] = lower_32_bits(dma);
- cbd.addr[1] = upper_32_bits(dma);
+ cbd.addr[0] = cpu_to_le32(lower_32_bits(dma));
+ cbd.addr[1] = cpu_to_le32(upper_32_bits(dma));
sgce = &sgcl_data->sgcl[0];
sgcl_config->agtst = 0x80;
- sgcl_data->ct = cpu_to_le32(sgi->cycletime);
- sgcl_data->cte = cpu_to_le32(sgi->cycletimext);
+ sgcl_data->ct = sgi->cycletime;
+ sgcl_data->cte = sgi->cycletimext;
if (sgi->init_ipv >= 0)
sgcl_config->aipv = (sgi->init_ipv & 0x7) | 0x8;
to->msdu[2] = (from->maxoctets >> 16) & 0xFF;
}
- to->interval = cpu_to_le32(from->interval);
+ to->interval = from->interval;
}
/* If basetime is less than now, calculate start time */
err = get_start_ns(now, sgi->cycletime, &start);
if (err)
goto exit;
- sgcl_data->btl = cpu_to_le32(lower_32_bits(start));
- sgcl_data->bth = cpu_to_le32(upper_32_bits(start));
+ sgcl_data->btl = lower_32_bits(start);
+ sgcl_data->bth = upper_32_bits(start);
} else {
u32 hi, lo;
hi = upper_32_bits(sgi->basetime);
lo = lower_32_bits(sgi->basetime);
- sgcl_data->bth = cpu_to_le32(hi);
- sgcl_data->btl = cpu_to_le32(lo);
+ sgcl_data->bth = hi;
+ sgcl_data->btl = lo;
}
err = enetc_send_cmd(priv->si, &cbd);
ndev->watchdog_timeo = 5 * HZ;
ndev->max_mtu = ENETC_MAX_MTU;
- ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+ ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX;
- ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG |
- NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+ ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM |
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX;
if (si->num_rss)
ndev->hw_features |= NETIF_F_RXHASH;
- if (si->errata & ENETC_ERR_TXCSUM) {
- ndev->hw_features &= ~NETIF_F_HW_CSUM;
- ndev->features &= ~NETIF_F_HW_CSUM;
- }
-
/* pick up primary MAC address from SI */
enetc_get_primary_mac_addr(&si->hw, ndev->dev_addr);
}
addresses */
#define TX_TIMEOUT (1*HZ)
-#define SKB_ALLOC_TIMEOUT 100000
#define PHY_INIT_TIMEOUT 100000
#define PHY_CHANGE_TIME 2
* Copyright (C) 2015-2019 Google, Inc.
*/
+#include <linux/ethtool.h>
#include <linux/rtnetlink.h>
#include "gve.h"
#include "gve_adminq.h"
#include <linux/dcbnl.h>
#include <linux/delay.h>
#include <linux/device.h>
+#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/pci.h>
HNAE3_DEV_SUPPORT_FD_FORWARD_TC_B,
HNAE3_DEV_SUPPORT_PTP_B,
HNAE3_DEV_SUPPORT_INT_QL_B,
- HNAE3_DEV_SUPPORT_SIMPLE_BD_B,
+ HNAE3_DEV_SUPPORT_HW_TX_CSUM_B,
HNAE3_DEV_SUPPORT_TX_PUSH_B,
HNAE3_DEV_SUPPORT_PHY_IMP_B,
HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B,
HNAE3_DEV_SUPPORT_HW_PAD_B,
HNAE3_DEV_SUPPORT_STASH_B,
+ HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B,
};
#define hnae3_dev_fd_supported(hdev) \
#define hnae3_dev_int_ql_supported(hdev) \
test_bit(HNAE3_DEV_SUPPORT_INT_QL_B, (hdev)->ae_dev->caps)
-#define hnae3_dev_simple_bd_supported(hdev) \
- test_bit(HNAE3_DEV_SUPPORT_SIMPLE_BD_B, (hdev)->ae_dev->caps)
+#define hnae3_dev_hw_csum_supported(hdev) \
+ test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, (hdev)->ae_dev->caps)
#define hnae3_dev_tx_push_supported(hdev) \
test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, (hdev)->ae_dev->caps)
u16 rss_ind_tbl_size;
u16 rss_key_size;
u16 int_ql_max; /* max value of interrupt coalesce based on INT_QL */
+ u16 max_int_gl; /* max value of interrupt coalesce based on INT_GL */
u8 max_non_tso_bd_num; /* max BD number of one non-TSO packet */
};
struct hnae3_roce_private_info {
struct net_device *netdev;
void __iomem *roce_io_base;
+ void __iomem *roce_mem_base;
int base_vector;
int num_vectors;
u32 tx_index, rx_index;
u32 q_num, value;
dma_addr_t addr;
+ u16 mss_hw_csum;
+ u32 l234info;
int cnt;
cnt = sscanf(&cmd_buf[8], "%u %u", &q_num, &tx_index);
tx_desc = &ring->desc[tx_index];
addr = le64_to_cpu(tx_desc->addr);
+ mss_hw_csum = le16_to_cpu(tx_desc->tx.mss_hw_csum);
dev_info(dev, "TX Queue Num: %u, BD Index: %u\n", q_num, tx_index);
dev_info(dev, "(TX)addr: %pad\n", &addr);
dev_info(dev, "(TX)vlan_tag: %u\n", le16_to_cpu(tx_desc->tx.vlan_tag));
dev_info(dev, "(TX)send_size: %u\n",
le16_to_cpu(tx_desc->tx.send_size));
- dev_info(dev, "(TX)vlan_tso: %u\n", tx_desc->tx.type_cs_vlan_tso);
- dev_info(dev, "(TX)l2_len: %u\n", tx_desc->tx.l2_len);
- dev_info(dev, "(TX)l3_len: %u\n", tx_desc->tx.l3_len);
- dev_info(dev, "(TX)l4_len: %u\n", tx_desc->tx.l4_len);
+
+ if (mss_hw_csum & BIT(HNS3_TXD_HW_CS_B)) {
+ u32 offset = le32_to_cpu(tx_desc->tx.ol_type_vlan_len_msec);
+ u32 start = le32_to_cpu(tx_desc->tx.type_cs_vlan_tso_len);
+
+ dev_info(dev, "(TX)csum start: %u\n",
+ hnae3_get_field(start,
+ HNS3_TXD_CSUM_START_M,
+ HNS3_TXD_CSUM_START_S));
+ dev_info(dev, "(TX)csum offset: %u\n",
+ hnae3_get_field(offset,
+ HNS3_TXD_CSUM_OFFSET_M,
+ HNS3_TXD_CSUM_OFFSET_S));
+ } else {
+ dev_info(dev, "(TX)vlan_tso: %u\n",
+ tx_desc->tx.type_cs_vlan_tso);
+ dev_info(dev, "(TX)l2_len: %u\n", tx_desc->tx.l2_len);
+ dev_info(dev, "(TX)l3_len: %u\n", tx_desc->tx.l3_len);
+ dev_info(dev, "(TX)l4_len: %u\n", tx_desc->tx.l4_len);
+ dev_info(dev, "(TX)vlan_msec: %u\n",
+ tx_desc->tx.ol_type_vlan_msec);
+ dev_info(dev, "(TX)ol2_len: %u\n", tx_desc->tx.ol2_len);
+ dev_info(dev, "(TX)ol3_len: %u\n", tx_desc->tx.ol3_len);
+ dev_info(dev, "(TX)ol4_len: %u\n", tx_desc->tx.ol4_len);
+ }
+
dev_info(dev, "(TX)vlan_tag: %u\n",
le16_to_cpu(tx_desc->tx.outer_vlan_tag));
dev_info(dev, "(TX)tv: %u\n", le16_to_cpu(tx_desc->tx.tv));
- dev_info(dev, "(TX)vlan_msec: %u\n", tx_desc->tx.ol_type_vlan_msec);
- dev_info(dev, "(TX)ol2_len: %u\n", tx_desc->tx.ol2_len);
- dev_info(dev, "(TX)ol3_len: %u\n", tx_desc->tx.ol3_len);
- dev_info(dev, "(TX)ol4_len: %u\n", tx_desc->tx.ol4_len);
- dev_info(dev, "(TX)paylen: %u\n", le32_to_cpu(tx_desc->tx.paylen));
+ dev_info(dev, "(TX)paylen_ol4cs: %u\n",
+ le32_to_cpu(tx_desc->tx.paylen_ol4cs));
dev_info(dev, "(TX)vld_ra_ri: %u\n",
le16_to_cpu(tx_desc->tx.bdtp_fe_sc_vld_ra_ri));
- dev_info(dev, "(TX)mss: %u\n", le16_to_cpu(tx_desc->tx.mss));
+ dev_info(dev, "(TX)mss_hw_csum: %u\n", mss_hw_csum);
ring = &priv->ring[q_num + h->kinfo.num_tqps];
value = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_TAIL_REG);
rx_desc = &ring->desc[rx_index];
addr = le64_to_cpu(rx_desc->addr);
+ l234info = le32_to_cpu(rx_desc->rx.l234_info);
dev_info(dev, "RX Queue Num: %u, BD Index: %u\n", q_num, rx_index);
dev_info(dev, "(RX)addr: %pad\n", &addr);
- dev_info(dev, "(RX)l234_info: %u\n",
- le32_to_cpu(rx_desc->rx.l234_info));
+ dev_info(dev, "(RX)l234_info: %u\n", l234info);
+
+ if (l234info & BIT(HNS3_RXD_L2_CSUM_B)) {
+ u32 lo, hi;
+
+ lo = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_L_M,
+ HNS3_RXD_L2_CSUM_L_S);
+ hi = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_H_M,
+ HNS3_RXD_L2_CSUM_H_S);
+ dev_info(dev, "(RX)csum: %u\n", lo | hi << 8);
+ }
+
dev_info(dev, "(RX)pkt_len: %u\n", le16_to_cpu(rx_desc->rx.pkt_len));
dev_info(dev, "(RX)size: %u\n", le16_to_cpu(rx_desc->rx.size));
dev_info(dev, "(RX)rss_hash: %u\n", le32_to_cpu(rx_desc->rx.rss_hash));
test_bit(HNAE3_DEV_SUPPORT_PTP_B, caps) ? "yes" : "no");
dev_info(&h->pdev->dev, "support INT QL: %s\n",
test_bit(HNAE3_DEV_SUPPORT_INT_QL_B, caps) ? "yes" : "no");
+ dev_info(&h->pdev->dev, "support HW TX csum: %s\n",
+ test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, caps) ? "yes" : "no");
+ dev_info(&h->pdev->dev, "support UDP tunnel csum: %s\n",
+ test_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, caps) ?
+ "yes" : "no");
}
static void hns3_dbg_dev_specs(struct hnae3_handle *h)
dev_info(priv->dev, "Desc num per RX queue: %u\n", kinfo->num_rx_desc);
dev_info(priv->dev, "Total number of enabled TCs: %u\n", kinfo->num_tc);
dev_info(priv->dev, "MAX INT QL: %u\n", dev_specs->int_ql_max);
+ dev_info(priv->dev, "MAX INT GL: %u\n", dev_specs->max_int_gl);
}
static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
* GL and RL(Rate Limiter) are 2 ways to acheive interrupt coalescing
*/
- if (rl_reg > 0 && !tqp_vector->tx_group.coal.gl_adapt_enable &&
- !tqp_vector->rx_group.coal.gl_adapt_enable)
+ if (rl_reg > 0 && !tqp_vector->tx_group.coal.adapt_enable &&
+ !tqp_vector->rx_group.coal.adapt_enable)
/* According to the hardware, the range of rl_reg is
* 0-59 and the unit is 4.
*/
void hns3_set_vector_coalesce_rx_gl(struct hns3_enet_tqp_vector *tqp_vector,
u32 gl_value)
{
- u32 rx_gl_reg = hns3_gl_usec_to_reg(gl_value);
+ u32 new_val;
- writel(rx_gl_reg, tqp_vector->mask_addr + HNS3_VECTOR_GL0_OFFSET);
+ if (tqp_vector->rx_group.coal.unit_1us)
+ new_val = gl_value | HNS3_INT_GL_1US;
+ else
+ new_val = hns3_gl_usec_to_reg(gl_value);
+
+ writel(new_val, tqp_vector->mask_addr + HNS3_VECTOR_GL0_OFFSET);
}
void hns3_set_vector_coalesce_tx_gl(struct hns3_enet_tqp_vector *tqp_vector,
u32 gl_value)
{
- u32 tx_gl_reg = hns3_gl_usec_to_reg(gl_value);
+ u32 new_val;
+
+ if (tqp_vector->tx_group.coal.unit_1us)
+ new_val = gl_value | HNS3_INT_GL_1US;
+ else
+ new_val = hns3_gl_usec_to_reg(gl_value);
+
+ writel(new_val, tqp_vector->mask_addr + HNS3_VECTOR_GL1_OFFSET);
+}
+
+void hns3_set_vector_coalesce_tx_ql(struct hns3_enet_tqp_vector *tqp_vector,
+ u32 ql_value)
+{
+ writel(ql_value, tqp_vector->mask_addr + HNS3_VECTOR_TX_QL_OFFSET);
+}
- writel(tx_gl_reg, tqp_vector->mask_addr + HNS3_VECTOR_GL1_OFFSET);
+void hns3_set_vector_coalesce_rx_ql(struct hns3_enet_tqp_vector *tqp_vector,
+ u32 ql_value)
+{
+ writel(ql_value, tqp_vector->mask_addr + HNS3_VECTOR_RX_QL_OFFSET);
}
-static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector,
- struct hns3_nic_priv *priv)
+static void hns3_vector_coalesce_init(struct hns3_enet_tqp_vector *tqp_vector,
+ struct hns3_nic_priv *priv)
{
+ struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev);
+ struct hns3_enet_coalesce *tx_coal = &tqp_vector->tx_group.coal;
+ struct hns3_enet_coalesce *rx_coal = &tqp_vector->rx_group.coal;
+
/* initialize the configuration for interrupt coalescing.
* 1. GL (Interrupt Gap Limiter)
* 2. RL (Interrupt Rate Limiter)
+ * 3. QL (Interrupt Quantity Limiter)
*
* Default: enable interrupt coalescing self-adaptive and GL
*/
- tqp_vector->tx_group.coal.gl_adapt_enable = 1;
- tqp_vector->rx_group.coal.gl_adapt_enable = 1;
+ tx_coal->adapt_enable = 1;
+ rx_coal->adapt_enable = 1;
+
+ tx_coal->int_gl = HNS3_INT_GL_50K;
+ rx_coal->int_gl = HNS3_INT_GL_50K;
- tqp_vector->tx_group.coal.int_gl = HNS3_INT_GL_50K;
- tqp_vector->rx_group.coal.int_gl = HNS3_INT_GL_50K;
+ rx_coal->flow_level = HNS3_FLOW_LOW;
+ tx_coal->flow_level = HNS3_FLOW_LOW;
- tqp_vector->rx_group.coal.flow_level = HNS3_FLOW_LOW;
- tqp_vector->tx_group.coal.flow_level = HNS3_FLOW_LOW;
+ /* device version above V3(include V3), GL can configure 1us
+ * unit, so uses 1us unit.
+ */
+ if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) {
+ tx_coal->unit_1us = 1;
+ rx_coal->unit_1us = 1;
+ }
+
+ if (ae_dev->dev_specs.int_ql_max) {
+ tx_coal->ql_enable = 1;
+ rx_coal->ql_enable = 1;
+ tx_coal->int_ql_max = ae_dev->dev_specs.int_ql_max;
+ rx_coal->int_ql_max = ae_dev->dev_specs.int_ql_max;
+ tx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG;
+ rx_coal->int_ql = HNS3_INT_QL_DEFAULT_CFG;
+ }
}
-static void hns3_vector_gl_rl_init_hw(struct hns3_enet_tqp_vector *tqp_vector,
- struct hns3_nic_priv *priv)
+static void
+hns3_vector_coalesce_init_hw(struct hns3_enet_tqp_vector *tqp_vector,
+ struct hns3_nic_priv *priv)
{
+ struct hns3_enet_coalesce *tx_coal = &tqp_vector->tx_group.coal;
+ struct hns3_enet_coalesce *rx_coal = &tqp_vector->rx_group.coal;
struct hnae3_handle *h = priv->ae_handle;
- hns3_set_vector_coalesce_tx_gl(tqp_vector,
- tqp_vector->tx_group.coal.int_gl);
- hns3_set_vector_coalesce_rx_gl(tqp_vector,
- tqp_vector->rx_group.coal.int_gl);
+ hns3_set_vector_coalesce_tx_gl(tqp_vector, tx_coal->int_gl);
+ hns3_set_vector_coalesce_rx_gl(tqp_vector, rx_coal->int_gl);
hns3_set_vector_coalesce_rl(tqp_vector, h->kinfo.int_rl_setting);
+
+ if (tx_coal->ql_enable)
+ hns3_set_vector_coalesce_tx_ql(tqp_vector, tx_coal->int_ql);
+
+ if (rx_coal->ql_enable)
+ hns3_set_vector_coalesce_rx_ql(tqp_vector, rx_coal->int_ql);
}
static int hns3_nic_set_real_num_queue(struct net_device *netdev)
}
}
-static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
+static int hns3_set_tso(struct sk_buff *skb, u32 *paylen_fdop_ol4cs,
u16 *mss, u32 *type_cs_vlan_tso)
{
u32 l4_offset, hdr_len;
SKB_GSO_GRE_CSUM |
SKB_GSO_UDP_TUNNEL |
SKB_GSO_UDP_TUNNEL_CSUM)) {
- if ((!(skb_shinfo(skb)->gso_type &
- SKB_GSO_PARTIAL)) &&
- (skb_shinfo(skb)->gso_type &
- SKB_GSO_UDP_TUNNEL_CSUM)) {
- /* Software should clear the udp's checksum
- * field when tso is needed.
- */
- l4.udp->check = 0;
- }
/* reset l3&l4 pointers from outer to inner headers */
l3.hdr = skb_inner_network_header(skb);
l4.hdr = skb_inner_transport_header(skb);
}
/* find the txbd field values */
- *paylen = skb->len - hdr_len;
+ *paylen_fdop_ol4cs = skb->len - hdr_len;
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_TSO_B, 1);
+ /* offload outer UDP header checksum */
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)
+ hns3_set_field(*paylen_fdop_ol4cs, HNS3_TXD_OL4CS_B, 1);
+
/* get MSS for TSO */
*mss = skb_shinfo(skb)->gso_size;
*/
static bool hns3_tunnel_csum_bug(struct sk_buff *skb)
{
+ struct hns3_nic_priv *priv = netdev_priv(skb->dev);
+ struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev);
union l4_hdr_info l4;
+ /* device version above V3(include V3), the hardware can
+ * do this checksum offload.
+ */
+ if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
+ return false;
+
l4.hdr = skb_transport_header(skb);
if (!(!skb->encapsulation &&
return 0;
}
+/* check if the hardware is capable of checksum offloading */
+static bool hns3_check_hw_tx_csum(struct sk_buff *skb)
+{
+ struct hns3_nic_priv *priv = netdev_priv(skb->dev);
+
+ /* Kindly note, due to backward compatibility of the TX descriptor,
+ * HW checksum of the non-IP packets and GSO packets is handled at
+ * different place in the following code
+ */
+ if (skb->csum_not_inet || skb_is_gso(skb) ||
+ !test_bit(HNS3_NIC_STATE_HW_TX_CSUM_ENABLE, &priv->state))
+ return false;
+
+ return true;
+}
+
static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
struct sk_buff *skb, struct hns3_desc *desc)
{
u32 ol_type_vlan_len_msec = 0;
+ u32 paylen_ol4cs = skb->len;
u32 type_cs_vlan_tso = 0;
- u32 paylen = skb->len;
+ u16 mss_hw_csum = 0;
u16 inner_vtag = 0;
u16 out_vtag = 0;
- u16 mss = 0;
int ret;
ret = hns3_handle_vtags(ring, skb);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
u8 ol4_proto, il4_proto;
+ if (hns3_check_hw_tx_csum(skb)) {
+ /* set checksum start and offset, defined in 2 Bytes */
+ hns3_set_field(type_cs_vlan_tso, HNS3_TXD_CSUM_START_S,
+ skb_checksum_start_offset(skb) >> 1);
+ hns3_set_field(ol_type_vlan_len_msec,
+ HNS3_TXD_CSUM_OFFSET_S,
+ skb->csum_offset >> 1);
+ mss_hw_csum |= BIT(HNS3_TXD_HW_CS_B);
+ goto out_hw_tx_csum;
+ }
+
skb_reset_mac_len(skb);
ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
return ret;
}
- ret = hns3_set_tso(skb, &paylen, &mss,
+ ret = hns3_set_tso(skb, &paylen_ol4cs, &mss_hw_csum,
&type_cs_vlan_tso);
if (unlikely(ret < 0)) {
u64_stats_update_begin(&ring->syncp);
}
}
+out_hw_tx_csum:
/* Set txbd */
desc->tx.ol_type_vlan_len_msec =
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_le32(paylen);
- desc->tx.mss = cpu_to_le16(mss);
+ desc->tx.paylen_ol4cs = cpu_to_le32(paylen_ol4cs);
+ desc->tx.mss_hw_csum = cpu_to_le16(mss_hw_csum);
desc->tx.vlan_tag = cpu_to_le16(inner_vtag);
desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag);
netdev->priv_flags |= IFF_UNICAST_FLT;
- netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
- NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
+ netdev->hw_enc_features |= NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC |
- NETIF_F_TSO_MANGLEID | NETIF_F_FRAGLIST;
+ NETIF_F_SCTP_CRC | NETIF_F_TSO_MANGLEID | NETIF_F_FRAGLIST;
netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
- netdev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
- NETIF_F_HW_VLAN_CTAG_FILTER |
+ netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC |
- NETIF_F_FRAGLIST;
+ NETIF_F_SCTP_CRC | NETIF_F_FRAGLIST;
- netdev->vlan_features |=
- NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |
+ netdev->vlan_features |= NETIF_F_RXCSUM |
NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO |
NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC |
- NETIF_F_FRAGLIST;
+ NETIF_F_SCTP_CRC | NETIF_F_FRAGLIST;
- netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
- NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
+ netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC |
- NETIF_F_FRAGLIST;
+ NETIF_F_SCTP_CRC | NETIF_F_FRAGLIST;
if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
netdev->hw_features |= NETIF_F_GRO_HW;
netdev->vlan_features |= NETIF_F_GSO_UDP_L4;
netdev->hw_enc_features |= NETIF_F_GSO_UDP_L4;
}
+
+ if (test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps)) {
+ netdev->hw_features |= NETIF_F_HW_CSUM;
+ netdev->features |= NETIF_F_HW_CSUM;
+ netdev->vlan_features |= NETIF_F_HW_CSUM;
+ netdev->hw_enc_features |= NETIF_F_HW_CSUM;
+ } else {
+ netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+ netdev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+ netdev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+ netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+ }
+
+ if (test_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, ae_dev->caps)) {
+ netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+ netdev->features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+ netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+ netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+ }
}
static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
return 0;
}
+static void hns3_checksum_complete(struct hns3_enet_ring *ring,
+ struct sk_buff *skb, u32 l234info)
+{
+ u32 lo, hi;
+
+ u64_stats_update_begin(&ring->syncp);
+ ring->stats.csum_complete++;
+ u64_stats_update_end(&ring->syncp);
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ lo = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_L_M,
+ HNS3_RXD_L2_CSUM_L_S);
+ hi = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_H_M,
+ HNS3_RXD_L2_CSUM_H_S);
+ skb->csum = csum_unfold((__force __sum16)(lo | hi << 8));
+}
+
static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
u32 l234info, u32 bd_base_info, u32 ol_info)
{
if (!(netdev->features & NETIF_F_RXCSUM))
return;
+ if (l234info & BIT(HNS3_RXD_L2_CSUM_B)) {
+ hns3_checksum_complete(ring, skb, l234info);
+ return;
+ }
+
/* check if hardware has done checksum */
if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B)))
return;
tqp_vector->last_jiffies + msecs_to_jiffies(1000)))
return;
- if (rx_group->coal.gl_adapt_enable) {
+ if (rx_group->coal.adapt_enable) {
rx_update = hns3_get_new_int_gl(rx_group);
if (rx_update)
hns3_set_vector_coalesce_rx_gl(tqp_vector,
rx_group->coal.int_gl);
}
- if (tx_group->coal.gl_adapt_enable) {
+ if (tx_group->coal.adapt_enable) {
tx_update = hns3_get_new_int_gl(tx_group);
if (tx_update)
hns3_set_vector_coalesce_tx_gl(tqp_vector,
for (i = 0; i < priv->vector_num; i++) {
tqp_vector = &priv->tqp_vector[i];
- hns3_vector_gl_rl_init_hw(tqp_vector, priv);
+ hns3_vector_coalesce_init_hw(tqp_vector, priv);
tqp_vector->num_tqps = 0;
}
static int hns3_nic_alloc_vector_data(struct hns3_nic_priv *priv)
{
-#define HNS3_VECTOR_PF_MAX_NUM 64
-
struct hnae3_handle *h = priv->ae_handle;
struct hns3_enet_tqp_vector *tqp_vector;
struct hnae3_vector_info *vector;
/* RSS size, cpu online and vector_num should be the same */
/* Should consider 2p/4p later */
vector_num = min_t(u16, num_online_cpus(), tqp_num);
- vector_num = min_t(u16, vector_num, HNS3_VECTOR_PF_MAX_NUM);
vector = devm_kcalloc(&pdev->dev, vector_num, sizeof(*vector),
GFP_KERNEL);
tqp_vector->idx = i;
tqp_vector->mask_addr = vector[i].io_addr;
tqp_vector->vector_irq = vector[i].vector;
- hns3_vector_gl_rl_init(tqp_vector, priv);
+ hns3_vector_coalesce_init(tqp_vector, priv);
}
out:
/* MTU range: (ETH_MIN_MTU(kernel default) - 9702) */
netdev->max_mtu = HNS3_MAX_MTU;
+ if (test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps))
+ set_bit(HNS3_NIC_STATE_HW_TX_CSUM_ENABLE, &priv->state);
+
set_bit(HNS3_NIC_STATE_INITED, &priv->state);
if (netif_msg_drv(handle))
HNS3_NIC_STATE_SERVICE_INITED,
HNS3_NIC_STATE_SERVICE_SCHED,
HNS3_NIC_STATE2_RESET_REQUESTED,
+ HNS3_NIC_STATE_HW_TX_CSUM_ENABLE,
HNS3_NIC_STATE_MAX
};
#define HNS3_RXD_STRP_TAGP_S 13
#define HNS3_RXD_STRP_TAGP_M (0x3 << HNS3_RXD_STRP_TAGP_S)
+#define HNS3_RXD_L2_CSUM_B 15
+#define HNS3_RXD_L2_CSUM_L_S 4
+#define HNS3_RXD_L2_CSUM_L_M (0xff << HNS3_RXD_L2_CSUM_L_S)
+#define HNS3_RXD_L2_CSUM_H_S 24
+#define HNS3_RXD_L2_CSUM_H_M (0xff << HNS3_RXD_L2_CSUM_H_S)
+
#define HNS3_RXD_L2E_B 16
#define HNS3_RXD_L3E_B 17
#define HNS3_RXD_L4E_B 18
#define HNS3_TXD_L4LEN_S 24
#define HNS3_TXD_L4LEN_M (0xff << HNS3_TXD_L4LEN_S)
+#define HNS3_TXD_CSUM_START_S 8
+#define HNS3_TXD_CSUM_START_M (0xffff << HNS3_TXD_CSUM_START_S)
+
#define HNS3_TXD_OL3T_S 0
#define HNS3_TXD_OL3T_M (0x3 << HNS3_TXD_OL3T_S)
#define HNS3_TXD_OVLAN_B 2
#define HNS3_TXD_TUNTYPE_S 4
#define HNS3_TXD_TUNTYPE_M (0xf << HNS3_TXD_TUNTYPE_S)
+#define HNS3_TXD_CSUM_OFFSET_S 8
+#define HNS3_TXD_CSUM_OFFSET_M (0xffff << HNS3_TXD_CSUM_OFFSET_S)
+
#define HNS3_TXD_BDTYPE_S 0
#define HNS3_TXD_BDTYPE_M (0xf << HNS3_TXD_BDTYPE_S)
#define HNS3_TXD_FE_B 4
#define HNS3_TXD_DECTTL_S 12
#define HNS3_TXD_DECTTL_M (0xf << HNS3_TXD_DECTTL_S)
+#define HNS3_TXD_OL4CS_B 22
+
#define HNS3_TXD_MSS_S 0
#define HNS3_TXD_MSS_M (0x3fff << HNS3_TXD_MSS_S)
+#define HNS3_TXD_HW_CS_B 14
#define HNS3_VECTOR_TX_IRQ BIT_ULL(0)
#define HNS3_VECTOR_RX_IRQ BIT_ULL(1)
#define HNS3_VECTOR_GL2_OFFSET 0x300
#define HNS3_VECTOR_RL_OFFSET 0x900
#define HNS3_VECTOR_RL_EN_B 6
+#define HNS3_VECTOR_TX_QL_OFFSET 0xe00
+#define HNS3_VECTOR_RX_QL_OFFSET 0xf00
#define HNS3_RING_EN_B 0
};
};
- __le32 paylen;
+ __le32 paylen_ol4cs;
__le16 bdtp_fe_sc_vld_ra_ri;
- __le16 mss;
+ __le16 mss_hw_csum;
} tx;
struct {
u64 err_bd_num;
u64 l2_err;
u64 l3l4_csum_err;
+ u64 csum_complete;
u64 rx_multicast;
u64 non_reuse_pg;
};
HNS3_FLOW_ULTRA = 3,
};
-#define HNS3_INT_GL_MAX 0x1FE0
#define HNS3_INT_GL_50K 0x0014
#define HNS3_INT_GL_20K 0x0032
#define HNS3_INT_GL_18K 0x0036
#define HNS3_INT_GL_8K 0x007C
+#define HNS3_INT_GL_1US BIT(31)
+
#define HNS3_INT_RL_MAX 0x00EC
#define HNS3_INT_RL_ENABLE_MASK 0x40
+#define HNS3_INT_QL_DEFAULT_CFG 0x20
+
struct hns3_enet_coalesce {
u16 int_gl;
- u8 gl_adapt_enable;
+ u16 int_ql;
+ u16 int_ql_max;
+ u8 adapt_enable:1;
+ u8 ql_enable:1;
+ u8 unit_1us:1;
enum hns3_flow_level_range flow_level;
};
u32 gl_value);
void hns3_set_vector_coalesce_rl(struct hns3_enet_tqp_vector *tqp_vector,
u32 rl_value);
+void hns3_set_vector_coalesce_rx_ql(struct hns3_enet_tqp_vector *tqp_vector,
+ u32 ql_value);
+void hns3_set_vector_coalesce_tx_ql(struct hns3_enet_tqp_vector *tqp_vector,
+ u32 ql_value);
void hns3_enable_vlan_filter(struct net_device *netdev, bool enable);
void hns3_request_update_promisc_mode(struct hnae3_handle *handle);
HNS3_TQP_STAT("err_bd_num", err_bd_num),
HNS3_TQP_STAT("l2_err", l2_err),
HNS3_TQP_STAT("l3l4_csum_err", l3l4_csum_err),
+ HNS3_TQP_STAT("csum_complete", csum_complete),
HNS3_TQP_STAT("multicast", rx_multicast),
HNS3_TQP_STAT("non_reuse_pg", non_reuse_pg),
};
rx_vector = priv->ring[queue_num + queue].tqp_vector;
cmd->use_adaptive_tx_coalesce =
- tx_vector->tx_group.coal.gl_adapt_enable;
+ tx_vector->tx_group.coal.adapt_enable;
cmd->use_adaptive_rx_coalesce =
- rx_vector->rx_group.coal.gl_adapt_enable;
+ rx_vector->rx_group.coal.adapt_enable;
cmd->tx_coalesce_usecs = tx_vector->tx_group.coal.int_gl;
cmd->rx_coalesce_usecs = rx_vector->rx_group.coal.int_gl;
cmd->tx_coalesce_usecs_high = h->kinfo.int_rl_setting;
cmd->rx_coalesce_usecs_high = h->kinfo.int_rl_setting;
+ cmd->tx_max_coalesced_frames = tx_vector->tx_group.coal.int_ql;
+ cmd->rx_max_coalesced_frames = rx_vector->rx_group.coal.int_ql;
+
return 0;
}
static int hns3_check_gl_coalesce_para(struct net_device *netdev,
struct ethtool_coalesce *cmd)
{
+ struct hnae3_handle *handle = hns3_get_handle(netdev);
+ struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
u32 rx_gl, tx_gl;
- if (cmd->rx_coalesce_usecs > HNS3_INT_GL_MAX) {
+ if (cmd->rx_coalesce_usecs > ae_dev->dev_specs.max_int_gl) {
netdev_err(netdev,
- "Invalid rx-usecs value, rx-usecs range is 0-%d\n",
- HNS3_INT_GL_MAX);
+ "invalid rx-usecs value, rx-usecs range is 0-%u\n",
+ ae_dev->dev_specs.max_int_gl);
return -EINVAL;
}
- if (cmd->tx_coalesce_usecs > HNS3_INT_GL_MAX) {
+ if (cmd->tx_coalesce_usecs > ae_dev->dev_specs.max_int_gl) {
netdev_err(netdev,
- "Invalid tx-usecs value, tx-usecs range is 0-%d\n",
- HNS3_INT_GL_MAX);
+ "invalid tx-usecs value, tx-usecs range is 0-%u\n",
+ ae_dev->dev_specs.max_int_gl);
return -EINVAL;
}
+ /* device version above V3(include V3), GL uses 1us unit,
+ * so the round down is not needed.
+ */
+ if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
+ return 0;
+
rx_gl = hns3_gl_round_down(cmd->rx_coalesce_usecs);
if (rx_gl != cmd->rx_coalesce_usecs) {
netdev_info(netdev,
return 0;
}
+static int hns3_check_ql_coalesce_param(struct net_device *netdev,
+ struct ethtool_coalesce *cmd)
+{
+ struct hnae3_handle *handle = hns3_get_handle(netdev);
+ struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
+
+ if ((cmd->tx_max_coalesced_frames || cmd->rx_max_coalesced_frames) &&
+ !ae_dev->dev_specs.int_ql_max) {
+ netdev_err(netdev, "coalesced frames is not supported\n");
+ return -EOPNOTSUPP;
+ }
+
+ if (cmd->tx_max_coalesced_frames > ae_dev->dev_specs.int_ql_max ||
+ cmd->rx_max_coalesced_frames > ae_dev->dev_specs.int_ql_max) {
+ netdev_err(netdev,
+ "invalid coalesced_frames value, range is 0-%u\n",
+ ae_dev->dev_specs.int_ql_max);
+ return -ERANGE;
+ }
+
+ return 0;
+}
+
static int hns3_check_coalesce_para(struct net_device *netdev,
struct ethtool_coalesce *cmd)
{
return ret;
}
+ ret = hns3_check_ql_coalesce_param(netdev, cmd);
+ if (ret)
+ return ret;
+
if (cmd->use_adaptive_tx_coalesce == 1 ||
cmd->use_adaptive_rx_coalesce == 1) {
netdev_info(netdev,
tx_vector = priv->ring[queue].tqp_vector;
rx_vector = priv->ring[queue_num + queue].tqp_vector;
- tx_vector->tx_group.coal.gl_adapt_enable =
+ tx_vector->tx_group.coal.adapt_enable =
cmd->use_adaptive_tx_coalesce;
- rx_vector->rx_group.coal.gl_adapt_enable =
+ rx_vector->rx_group.coal.adapt_enable =
cmd->use_adaptive_rx_coalesce;
tx_vector->tx_group.coal.int_gl = cmd->tx_coalesce_usecs;
rx_vector->rx_group.coal.int_gl = cmd->rx_coalesce_usecs;
+ tx_vector->tx_group.coal.int_ql = cmd->tx_max_coalesced_frames;
+ rx_vector->rx_group.coal.int_ql = cmd->rx_max_coalesced_frames;
+
hns3_set_vector_coalesce_tx_gl(tx_vector,
tx_vector->tx_group.coal.int_gl);
hns3_set_vector_coalesce_rx_gl(rx_vector,
hns3_set_vector_coalesce_rl(tx_vector, h->kinfo.int_rl_setting);
hns3_set_vector_coalesce_rl(rx_vector, h->kinfo.int_rl_setting);
+
+ if (tx_vector->tx_group.coal.ql_enable)
+ hns3_set_vector_coalesce_tx_ql(tx_vector,
+ tx_vector->tx_group.coal.int_ql);
+ if (rx_vector->rx_group.coal.ql_enable)
+ hns3_set_vector_coalesce_rx_ql(rx_vector,
+ rx_vector->rx_group.coal.int_ql);
}
static int hns3_set_coalesce(struct net_device *netdev,
#define HNS3_ETHTOOL_COALESCE (ETHTOOL_COALESCE_USECS | \
ETHTOOL_COALESCE_USE_ADAPTIVE | \
ETHTOOL_COALESCE_RX_USECS_HIGH | \
- ETHTOOL_COALESCE_TX_USECS_HIGH)
+ ETHTOOL_COALESCE_TX_USECS_HIGH | \
+ ETHTOOL_COALESCE_MAX_FRAMES)
static const struct ethtool_ops hns3vf_ethtool_ops = {
.supported_coalesce_params = HNS3_ETHTOOL_COALESCE,
set_bit(HNAE3_DEV_SUPPORT_INT_QL_B, ae_dev->caps);
if (hnae3_get_bit(caps, HCLGE_CAP_TQP_TXRX_INDEP_B))
set_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, ae_dev->caps);
+ if (hnae3_get_bit(caps, HCLGE_CAP_HW_TX_CSUM_B))
+ set_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps);
+ if (hnae3_get_bit(caps, HCLGE_CAP_UDP_TUNNEL_CSUM_B))
+ set_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, ae_dev->caps);
}
static enum hclge_cmd_status
#define HCLGE_TQP_REG_OFFSET 0x80000
#define HCLGE_TQP_REG_SIZE 0x200
+#define HCLGE_TQP_MAX_SIZE_DEV_V2 1024
+#define HCLGE_TQP_EXT_REG_OFFSET 0x100
+
#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_ctrl_vector_chain_cmd {
- u8 int_vector_id;
+#define HCLGE_VECTOR_ID_L_S 0
+#define HCLGE_VECTOR_ID_L_M GENMASK(7, 0)
+ u8 int_vector_id_l;
u8 int_cause_num;
#define HCLGE_INT_TYPE_S 0
#define HCLGE_INT_TYPE_M GENMASK(1, 0)
#define HCLGE_INT_GL_IDX_M GENMASK(14, 13)
__le16 tqp_type_and_id[HCLGE_VECTOR_ELEMENTS_PER_CMD];
u8 vfid;
- u8 rsv;
+#define HCLGE_VECTOR_ID_H_S 8
+#define HCLGE_VECTOR_ID_H_M GENMASK(15, 8)
+ u8 int_vector_id_h;
};
#define HCLGE_MAX_TC_NUM 8
HCLGE_CAP_FD_FORWARD_TC_B,
HCLGE_CAP_PTP_B,
HCLGE_CAP_INT_QL_B,
- HCLGE_CAP_SIMPLE_BD_B,
+ HCLGE_CAP_HW_TX_CSUM_B,
HCLGE_CAP_TX_PUSH_B,
HCLGE_CAP_PHY_IMP_B,
HCLGE_CAP_TQP_TXRX_INDEP_B,
HCLGE_CAP_HW_PAD_B,
HCLGE_CAP_STASH_B,
+ HCLGE_CAP_UDP_TUNNEL_CSUM_B,
};
#define HCLGE_QUERY_CAP_LENGTH 3
__le16 tqp_num;
__le16 buf_size;
__le16 msixcap_localid_ba_nic;
- __le16 msixcap_localid_ba_rocee;
-#define HCLGE_MSIX_OFT_ROCEE_S 0
-#define HCLGE_MSIX_OFT_ROCEE_M GENMASK(15, 0)
-#define HCLGE_PF_VEC_NUM_S 0
-#define HCLGE_PF_VEC_NUM_M GENMASK(7, 0)
- __le16 pf_intr_vector_number;
+ __le16 msixcap_localid_number_nic;
+ __le16 pf_intr_vector_number_roce;
__le16 pf_own_fun_number;
__le16 tx_buf_size;
__le16 dv_buf_size;
- __le32 rsv[2];
+ __le16 ext_tqp_num;
+ u8 rsv[6];
};
#define HCLGE_CFG_OFFSET_S 0
u8 rsv[22];
};
-#define HCLGE_RING_ID_MASK GENMASK(9, 0)
#define HCLGE_TQP_ENABLE_B 0
#define HCLGE_MAC_CFG_AN_EN_B 0
__le32 max_tm_rate;
};
+#define HCLGE_DEF_MAX_INT_GL 0x1FE0U
+
+struct hclge_dev_specs_1_cmd {
+ __le32 rsv0;
+ __le16 max_int_gl;
+ u8 rsv1[18];
+};
+
int hclge_cmd_init(struct hclge_dev *hdev);
static inline void hclge_write_reg(void __iomem *base, u32 reg, u32 value)
{
#include "hclge_main.h"
#include "hclge_dcb.h"
#include "hclge_tm.h"
-#include "hclge_dcb.h"
#include "hnae3.h"
#define BW_PERCENT 100
dev_info(&hdev->pdev->dev, "PG_P pg_id: %u\n", pg_shap_cfg_cmd->pg_id);
dev_info(&hdev->pdev->dev, "PG_P pg_shapping: 0x%x\n",
le32_to_cpu(pg_shap_cfg_cmd->pg_shapping_para));
+ dev_info(&hdev->pdev->dev, "PG_P flag: %#x\n", pg_shap_cfg_cmd->flag);
+ dev_info(&hdev->pdev->dev, "PG_P pg_rate: %u(Mbps)\n",
+ le32_to_cpu(pg_shap_cfg_cmd->pg_rate));
cmd = HCLGE_OPC_TM_PORT_SHAPPING;
hclge_cmd_setup_basic_desc(&desc, cmd, true);
port_shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data;
dev_info(&hdev->pdev->dev, "PORT port_shapping: 0x%x\n",
le32_to_cpu(port_shap_cfg_cmd->port_shapping_para));
+ dev_info(&hdev->pdev->dev, "PORT flag: %#x\n", port_shap_cfg_cmd->flag);
+ dev_info(&hdev->pdev->dev, "PORT port_rate: %u(Mbps)\n",
+ le32_to_cpu(port_shap_cfg_cmd->port_rate));
cmd = HCLGE_OPC_TM_PG_SCH_MODE_CFG;
hclge_cmd_setup_basic_desc(&desc, cmd, true);
dev_info(&hdev->pdev->dev, "PRI_C pri_id: %u\n", shap_cfg_cmd->pri_id);
dev_info(&hdev->pdev->dev, "PRI_C pri_shapping: 0x%x\n",
le32_to_cpu(shap_cfg_cmd->pri_shapping_para));
+ dev_info(&hdev->pdev->dev, "PRI_C flag: %#x\n", shap_cfg_cmd->flag);
+ dev_info(&hdev->pdev->dev, "PRI_C pri_rate: %u(Mbps)\n",
+ le32_to_cpu(shap_cfg_cmd->pri_rate));
cmd = HCLGE_OPC_TM_PRI_P_SHAPPING;
hclge_cmd_setup_basic_desc(&desc, cmd, true);
dev_info(&hdev->pdev->dev, "PRI_P pri_id: %u\n", shap_cfg_cmd->pri_id);
dev_info(&hdev->pdev->dev, "PRI_P pri_shapping: 0x%x\n",
le32_to_cpu(shap_cfg_cmd->pri_shapping_para));
+ dev_info(&hdev->pdev->dev, "PRI_P flag: %#x\n", shap_cfg_cmd->flag);
+ dev_info(&hdev->pdev->dev, "PRI_P pri_rate: %u(Mbps)\n",
+ le32_to_cpu(shap_cfg_cmd->pri_rate));
hclge_dbg_dump_tm_pg(hdev);
{
struct hclge_bp_to_qs_map_cmd *bp_to_qs_map_cmd;
struct hclge_nq_to_qs_link_cmd *nq_to_qs_map;
+ u32 qset_mapping[HCLGE_BP_EXT_GRP_NUM];
struct hclge_qs_to_pri_link_cmd *map;
struct hclge_tqp_tx_queue_tc_cmd *tc;
enum hclge_opcode_type cmd;
struct hclge_desc desc;
int queue_id, group_id;
- u32 qset_mapping[32];
int tc_id, qset_id;
int pri_id, ret;
+ u16 qs_id_l;
+ u16 qs_id_h;
+ u8 grp_num;
u32 i;
ret = kstrtouint(cmd_buf, 0, &queue_id);
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret)
goto err_tm_map_cmd_send;
- qset_id = le16_to_cpu(nq_to_qs_map->qset_id) & 0x3FF;
+ qset_id = le16_to_cpu(nq_to_qs_map->qset_id);
+
+ /* convert qset_id to the following format, drop the vld bit
+ * | qs_id_h | vld | qs_id_l |
+ * qset_id: | 15 ~ 11 | 10 | 9 ~ 0 |
+ * \ \ / /
+ * \ \ / /
+ * qset_id: | 15 | 14 ~ 10 | 9 ~ 0 |
+ */
+ qs_id_l = hnae3_get_field(qset_id, HCLGE_TM_QS_ID_L_MSK,
+ HCLGE_TM_QS_ID_L_S);
+ qs_id_h = hnae3_get_field(qset_id, HCLGE_TM_QS_ID_H_EXT_MSK,
+ HCLGE_TM_QS_ID_H_EXT_S);
+ qset_id = 0;
+ hnae3_set_field(qset_id, HCLGE_TM_QS_ID_L_MSK, HCLGE_TM_QS_ID_L_S,
+ qs_id_l);
+ hnae3_set_field(qset_id, HCLGE_TM_QS_ID_H_MSK, HCLGE_TM_QS_ID_H_S,
+ qs_id_h);
cmd = HCLGE_OPC_TM_QS_TO_PRI_LINK;
map = (struct hclge_qs_to_pri_link_cmd *)desc.data;
return;
}
+ grp_num = hdev->num_tqps <= HCLGE_TQP_MAX_SIZE_DEV_V2 ?
+ HCLGE_BP_GRP_NUM : HCLGE_BP_EXT_GRP_NUM;
cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING;
bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data;
- for (group_id = 0; group_id < 32; group_id++) {
+ for (group_id = 0; group_id < grp_num; group_id++) {
hclge_cmd_setup_basic_desc(&desc, cmd, true);
bp_to_qs_map_cmd->tc_id = tc_id;
bp_to_qs_map_cmd->qs_group_id = group_id;
dev_info(&hdev->pdev->dev, "index | tm bp qset maping:\n");
i = 0;
- for (group_id = 0; group_id < 4; group_id++) {
+ for (group_id = 0; group_id < grp_num / 8; group_id++) {
dev_info(&hdev->pdev->dev,
"%04d | %08x:%08x:%08x:%08x:%08x:%08x:%08x:%08x\n",
group_id * 256, qset_mapping[(u32)(i + 7)],
u8 ir_u, ir_b, ir_s, bs_b, bs_s;
struct hclge_desc desc;
u32 shapping_para;
+ u32 rate;
int ret;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QCN_SHAPPING_CFG, true);
ir_s = hclge_tm_get_field(shapping_para, IR_S);
bs_b = hclge_tm_get_field(shapping_para, BS_B);
bs_s = hclge_tm_get_field(shapping_para, BS_S);
+ rate = le32_to_cpu(shap_cfg_cmd->qs_rate);
dev_info(&hdev->pdev->dev,
- "qs%u ir_b:%u, ir_u:%u, ir_s:%u, bs_b:%u, bs_s:%u\n",
- qsid, ir_b, ir_u, ir_s, bs_b, bs_s);
+ "qs%u ir_b:%u, ir_u:%u, ir_s:%u, bs_b:%u, bs_s:%u, flag:%#x, rate:%u(Mbps)\n",
+ qsid, ir_b, ir_u, ir_s, bs_b, bs_s, shap_cfg_cmd->flag, rate);
}
static void hclge_dbg_dump_qs_shaper_all(struct hclge_dev *hdev)
hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_RX_STATS,
true);
- desc[0].data[0] = cpu_to_le32((tqp->index & 0x1ff));
+ desc[0].data[0] = cpu_to_le32(tqp->index);
ret = hclge_cmd_send(&hdev->hw, desc, 1);
if (ret) {
dev_err(&hdev->pdev->dev,
HCLGE_OPC_QUERY_TX_STATS,
true);
- desc[0].data[0] = cpu_to_le32((tqp->index & 0x1ff));
+ desc[0].data[0] = cpu_to_le32(tqp->index);
ret = hclge_cmd_send(&hdev->hw, desc, 1);
if (ret) {
dev_err(&hdev->pdev->dev,
}
req = (struct hclge_pf_res_cmd *)desc.data;
- hdev->num_tqps = le16_to_cpu(req->tqp_num);
+ hdev->num_tqps = le16_to_cpu(req->tqp_num) +
+ le16_to_cpu(req->ext_tqp_num);
hdev->pkt_buf_size = le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S;
if (req->tx_buf_size)
hdev->dv_buf_size = roundup(hdev->dv_buf_size, HCLGE_BUF_SIZE_UNIT);
+ hdev->num_nic_msi = le16_to_cpu(req->msixcap_localid_number_nic);
+ if (hdev->num_nic_msi < HNAE3_MIN_VECTOR_NUM) {
+ dev_err(&hdev->pdev->dev,
+ "only %u msi resources available, not enough for pf(min:2).\n",
+ hdev->num_nic_msi);
+ return -EINVAL;
+ }
+
if (hnae3_dev_roce_supported(hdev)) {
- hdev->roce_base_msix_offset =
- hnae3_get_field(le16_to_cpu(req->msixcap_localid_ba_rocee),
- HCLGE_MSIX_OFT_ROCEE_M, HCLGE_MSIX_OFT_ROCEE_S);
hdev->num_roce_msi =
- hnae3_get_field(le16_to_cpu(req->pf_intr_vector_number),
- HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
-
- /* nic's msix numbers is always equals to the roce's. */
- hdev->num_nic_msi = hdev->num_roce_msi;
+ le16_to_cpu(req->pf_intr_vector_number_roce);
/* PF should have NIC vectors and Roce vectors,
* NIC vectors are queued before Roce vectors.
*/
- hdev->num_msi = hdev->num_roce_msi +
- hdev->roce_base_msix_offset;
+ hdev->num_msi = hdev->num_nic_msi + hdev->num_roce_msi;
} else {
- hdev->num_msi =
- hnae3_get_field(le16_to_cpu(req->pf_intr_vector_number),
- HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
-
- hdev->num_nic_msi = hdev->num_msi;
- }
-
- if (hdev->num_nic_msi < HNAE3_MIN_VECTOR_NUM) {
- dev_err(&hdev->pdev->dev,
- "Just %u msi resources, not enough for pf(min:2).\n",
- hdev->num_nic_msi);
- return -EINVAL;
+ hdev->num_msi = hdev->num_nic_msi;
}
return 0;
ae_dev->dev_specs.rss_ind_tbl_size = HCLGE_RSS_IND_TBL_SIZE;
ae_dev->dev_specs.rss_key_size = HCLGE_RSS_KEY_SIZE;
ae_dev->dev_specs.max_tm_rate = HCLGE_ETHER_MAX_RATE;
+ ae_dev->dev_specs.max_int_gl = HCLGE_DEF_MAX_INT_GL;
}
static void hclge_parse_dev_specs(struct hclge_dev *hdev,
{
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
struct hclge_dev_specs_0_cmd *req0;
+ struct hclge_dev_specs_1_cmd *req1;
req0 = (struct hclge_dev_specs_0_cmd *)desc[0].data;
+ req1 = (struct hclge_dev_specs_1_cmd *)desc[1].data;
ae_dev->dev_specs.max_non_tso_bd_num = req0->max_non_tso_bd_num;
ae_dev->dev_specs.rss_ind_tbl_size =
le16_to_cpu(req0->rss_ind_tbl_size);
+ ae_dev->dev_specs.int_ql_max = le16_to_cpu(req0->int_ql_max);
ae_dev->dev_specs.rss_key_size = le16_to_cpu(req0->rss_key_size);
ae_dev->dev_specs.max_tm_rate = le32_to_cpu(req0->max_tm_rate);
+ ae_dev->dev_specs.max_int_gl = le16_to_cpu(req1->max_int_gl);
}
static void hclge_check_dev_specs(struct hclge_dev *hdev)
dev_specs->rss_key_size = HCLGE_RSS_KEY_SIZE;
if (!dev_specs->max_tm_rate)
dev_specs->max_tm_rate = HCLGE_ETHER_MAX_RATE;
+ if (!dev_specs->max_int_gl)
+ dev_specs->max_int_gl = HCLGE_DEF_MAX_INT_GL;
}
static int hclge_query_dev_specs(struct hclge_dev *hdev)
tqp->q.buf_size = hdev->rx_buf_len;
tqp->q.tx_desc_num = hdev->num_tx_desc;
tqp->q.rx_desc_num = hdev->num_rx_desc;
- tqp->q.io_base = hdev->hw.io_base + HCLGE_TQP_REG_OFFSET +
- i * HCLGE_TQP_REG_SIZE;
+
+ /* need an extended offset to configure queues >=
+ * HCLGE_TQP_MAX_SIZE_DEV_V2
+ */
+ if (i < HCLGE_TQP_MAX_SIZE_DEV_V2)
+ tqp->q.io_base = hdev->hw.io_base +
+ HCLGE_TQP_REG_OFFSET +
+ i * HCLGE_TQP_REG_SIZE;
+ else
+ tqp->q.io_base = hdev->hw.io_base +
+ HCLGE_TQP_REG_OFFSET +
+ HCLGE_TQP_EXT_REG_OFFSET +
+ (i - HCLGE_TQP_MAX_SIZE_DEV_V2) *
+ HCLGE_TQP_REG_SIZE;
tqp++;
}
{
struct hnae3_handle *roce = &vport->roce;
struct hnae3_handle *nic = &vport->nic;
+ struct hclge_dev *hdev = vport->back;
roce->rinfo.num_vectors = vport->back->num_roce_msi;
- if (vport->back->num_msi_left < vport->roce.rinfo.num_vectors ||
- vport->back->num_msi_left == 0)
+ if (hdev->num_msi < hdev->num_nic_msi + hdev->num_roce_msi)
return -EINVAL;
- roce->rinfo.base_vector = vport->back->roce_base_vector;
+ roce->rinfo.base_vector = hdev->roce_base_vector;
roce->rinfo.netdev = nic->kinfo.netdev;
- roce->rinfo.roce_io_base = vport->back->hw.io_base;
+ roce->rinfo.roce_io_base = hdev->hw.io_base;
+ roce->rinfo.roce_mem_base = hdev->hw.mem_base;
roce->pdev = nic->pdev;
roce->ae_algo = nic->ae_algo;
hdev->base_msi_vector = pdev->irq;
hdev->roce_base_vector = hdev->base_msi_vector +
- hdev->roce_base_msix_offset;
+ hdev->num_nic_msi;
hdev->vector_status = devm_kcalloc(&pdev->dev, hdev->num_msi,
sizeof(u16), GFP_KERNEL);
return container_of(handle, struct hclge_vport, nic);
}
+static void hclge_get_vector_info(struct hclge_dev *hdev, u16 idx,
+ struct hnae3_vector_info *vector_info)
+{
+#define HCLGE_PF_MAX_VECTOR_NUM_DEV_V2 64
+
+ vector_info->vector = pci_irq_vector(hdev->pdev, idx);
+
+ /* need an extend offset to config vector >= 64 */
+ if (idx - 1 < HCLGE_PF_MAX_VECTOR_NUM_DEV_V2)
+ vector_info->io_addr = hdev->hw.io_base +
+ HCLGE_VECTOR_REG_BASE +
+ (idx - 1) * HCLGE_VECTOR_REG_OFFSET;
+ else
+ vector_info->io_addr = hdev->hw.io_base +
+ HCLGE_VECTOR_EXT_REG_BASE +
+ (idx - 1) / HCLGE_PF_MAX_VECTOR_NUM_DEV_V2 *
+ HCLGE_VECTOR_REG_OFFSET_H +
+ (idx - 1) % HCLGE_PF_MAX_VECTOR_NUM_DEV_V2 *
+ HCLGE_VECTOR_REG_OFFSET;
+
+ hdev->vector_status[idx] = hdev->vport[0].vport_id;
+ hdev->vector_irq[idx] = vector_info->vector;
+}
+
static int hclge_get_vector(struct hnae3_handle *handle, u16 vector_num,
struct hnae3_vector_info *vector_info)
{
struct hnae3_vector_info *vector = vector_info;
struct hclge_dev *hdev = vport->back;
int alloc = 0;
- int i, j;
+ u16 i = 0;
+ u16 j;
vector_num = min_t(u16, hdev->num_nic_msi - 1, vector_num);
vector_num = min(hdev->num_msi_left, vector_num);
for (j = 0; j < vector_num; j++) {
- for (i = 1; i < hdev->num_msi; i++) {
+ while (++i < hdev->num_nic_msi) {
if (hdev->vector_status[i] == HCLGE_INVALID_VPORT) {
- vector->vector = pci_irq_vector(hdev->pdev, i);
- vector->io_addr = hdev->hw.io_base +
- HCLGE_VECTOR_REG_BASE +
- (i - 1) * HCLGE_VECTOR_REG_OFFSET +
- vport->vport_id *
- HCLGE_VECTOR_VF_OFFSET;
- hdev->vector_status[i] = vport->vport_id;
- hdev->vector_irq[i] = vector->vector;
-
+ hclge_get_vector_info(hdev, i, vector);
vector++;
alloc++;
op = en ? HCLGE_OPC_ADD_RING_TO_VECTOR : HCLGE_OPC_DEL_RING_TO_VECTOR;
hclge_cmd_setup_basic_desc(&desc, op, false);
- req->int_vector_id = vector_id;
+ req->int_vector_id_l = hnae3_get_field(vector_id,
+ HCLGE_VECTOR_ID_L_M,
+ HCLGE_VECTOR_ID_L_S);
+ req->int_vector_id_h = hnae3_get_field(vector_id,
+ HCLGE_VECTOR_ID_H_M,
+ HCLGE_VECTOR_ID_H_S);
i = 0;
for (node = ring_chain; node; node = node->next) {
hclge_cmd_setup_basic_desc(&desc,
op,
false);
- req->int_vector_id = vector_id;
+ req->int_vector_id_l =
+ hnae3_get_field(vector_id,
+ HCLGE_VECTOR_ID_L_M,
+ HCLGE_VECTOR_ID_L_S);
+ req->int_vector_id_h =
+ hnae3_get_field(vector_id,
+ HCLGE_VECTOR_ID_H_M,
+ HCLGE_VECTOR_ID_H_S);
}
}
int ret;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_COM_TQP_QUEUE, false);
- req->tqp_id = cpu_to_le16(tqp_id & HCLGE_RING_ID_MASK);
+ req->tqp_id = cpu_to_le16(tqp_id);
req->stream_id = cpu_to_le16(stream_id);
if (enable)
req->enable |= 1U << HCLGE_TQP_ENABLE_B;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RESET_TQP_QUEUE, false);
req = (struct hclge_reset_tqp_queue_cmd *)desc.data;
- req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK);
+ req->tqp_id = cpu_to_le16(queue_id);
if (enable)
hnae3_set_bit(req->reset_req, HCLGE_TQP_RESET_B, 1U);
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RESET_TQP_QUEUE, true);
req = (struct hclge_reset_tqp_queue_cmd *)desc.data;
- req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK);
+ req->tqp_id = cpu_to_le16(queue_id);
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret) {
}
}
+static int hclge_dev_mem_map(struct hclge_dev *hdev)
+{
+#define HCLGE_MEM_BAR 4
+
+ struct pci_dev *pdev = hdev->pdev;
+ struct hclge_hw *hw = &hdev->hw;
+
+ /* for device does not have device memory, return directly */
+ if (!(pci_select_bars(pdev, IORESOURCE_MEM) & BIT(HCLGE_MEM_BAR)))
+ return 0;
+
+ hw->mem_base = devm_ioremap_wc(&pdev->dev,
+ pci_resource_start(pdev, HCLGE_MEM_BAR),
+ pci_resource_len(pdev, HCLGE_MEM_BAR));
+ if (!hw->mem_base) {
+ dev_err(&pdev->dev, "failed to map device memory\n");
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
static int hclge_pci_init(struct hclge_dev *hdev)
{
struct pci_dev *pdev = hdev->pdev;
goto err_clr_master;
}
+ ret = hclge_dev_mem_map(hdev);
+ if (ret)
+ goto err_unmap_io_base;
+
hdev->num_req_vfs = pci_sriov_get_totalvfs(pdev);
return 0;
+
+err_unmap_io_base:
+ pcim_iounmap(pdev, hdev->hw.io_base);
err_clr_master:
pci_clear_master(pdev);
pci_release_regions(pdev);
{
struct pci_dev *pdev = hdev->pdev;
+ if (hdev->hw.mem_base)
+ devm_iounmap(&pdev->dev, hdev->hw.mem_base);
+
pcim_iounmap(pdev, hdev->hw.io_base);
pci_free_irq_vectors(pdev);
pci_clear_master(pdev);
(HCLGE_PF_CFG_BLOCK_SIZE / HCLGE_CFG_RD_LEN_BYTES)
#define HCLGE_VECTOR_REG_BASE 0x20000
+#define HCLGE_VECTOR_EXT_REG_BASE 0x30000
#define HCLGE_MISC_VECTOR_REG_BASE 0x20400
#define HCLGE_VECTOR_REG_OFFSET 0x4
+#define HCLGE_VECTOR_REG_OFFSET_H 0x1000
#define HCLGE_VECTOR_VF_OFFSET 0x100000
#define HCLGE_CMDQ_TX_ADDR_L_REG 0x27000
struct hclge_hw {
void __iomem *io_base;
+ void __iomem *mem_base;
struct hclge_mac mac;
int num_vec;
struct hclge_cmq cmq;
u16 num_msi;
u16 num_msi_left;
u16 num_msi_used;
- u16 roce_base_msix_offset;
u32 base_msi_vector;
u16 *vector_status;
int *vector_irq;
{
struct hclge_nq_to_qs_link_cmd *map;
struct hclge_desc desc;
+ u16 qs_id_l;
+ u16 qs_id_h;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_NQ_TO_QS_LINK, false);
map = (struct hclge_nq_to_qs_link_cmd *)desc.data;
map->nq_id = cpu_to_le16(q_id);
+
+ /* convert qs_id to the following format to support qset_id >= 1024
+ * qs_id: | 15 | 14 ~ 10 | 9 ~ 0 |
+ * / / \ \
+ * / / \ \
+ * qset_id: | 15 ~ 11 | 10 | 9 ~ 0 |
+ * | qs_id_h | vld | qs_id_l |
+ */
+ qs_id_l = hnae3_get_field(qs_id, HCLGE_TM_QS_ID_L_MSK,
+ HCLGE_TM_QS_ID_L_S);
+ qs_id_h = hnae3_get_field(qs_id, HCLGE_TM_QS_ID_H_MSK,
+ HCLGE_TM_QS_ID_H_S);
+ hnae3_set_field(qs_id, HCLGE_TM_QS_ID_L_MSK, HCLGE_TM_QS_ID_L_S,
+ qs_id_l);
+ hnae3_set_field(qs_id, HCLGE_TM_QS_ID_H_EXT_MSK, HCLGE_TM_QS_ID_H_EXT_S,
+ qs_id_h);
map->qset_id = cpu_to_le16(qs_id | HCLGE_TM_Q_QS_LINK_VLD_MSK);
return hclge_cmd_send(&hdev->hw, &desc, 1);
static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev,
enum hclge_shap_bucket bucket, u8 pg_id,
- u32 shapping_para)
+ u32 shapping_para, u32 rate)
{
struct hclge_pg_shapping_cmd *shap_cfg_cmd;
enum hclge_opcode_type opcode;
shap_cfg_cmd->pg_shapping_para = cpu_to_le32(shapping_para);
+ hnae3_set_bit(shap_cfg_cmd->flag, HCLGE_TM_RATE_VLD, 1);
+
+ shap_cfg_cmd->pg_rate = cpu_to_le32(rate);
+
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
shap_cfg_cmd->port_shapping_para = cpu_to_le32(shapping_para);
+ hnae3_set_bit(shap_cfg_cmd->flag, HCLGE_TM_RATE_VLD, 1);
+
+ shap_cfg_cmd->port_rate = cpu_to_le32(hdev->hw.mac.speed);
+
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev,
enum hclge_shap_bucket bucket, u8 pri_id,
- u32 shapping_para)
+ u32 shapping_para, u32 rate)
{
struct hclge_pri_shapping_cmd *shap_cfg_cmd;
enum hclge_opcode_type opcode;
shap_cfg_cmd->pri_shapping_para = cpu_to_le32(shapping_para);
+ hnae3_set_bit(shap_cfg_cmd->flag, HCLGE_TM_RATE_VLD, 1);
+
+ shap_cfg_cmd->pri_rate = cpu_to_le32(rate);
+
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
shap_cfg_cmd->qs_id = cpu_to_le16(vport->qs_offset + i);
shap_cfg_cmd->qs_shapping_para = cpu_to_le32(shaper_para);
+ hnae3_set_bit(shap_cfg_cmd->flag, HCLGE_TM_RATE_VLD, 1);
+ shap_cfg_cmd->qs_rate = cpu_to_le32(max_tx_rate);
+
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret) {
dev_err(&hdev->pdev->dev,
}
}
-static void hclge_pfc_info_init(struct hclge_dev *hdev)
+static void hclge_update_fc_mode_by_dcb_flag(struct hclge_dev *hdev)
{
if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE)) {
if (hdev->fc_mode_last_time == HCLGE_FC_PFC)
}
}
+static void hclge_update_fc_mode(struct hclge_dev *hdev)
+{
+ if (!hdev->tm_info.pfc_en) {
+ hdev->tm_info.fc_mode = hdev->fc_mode_last_time;
+ return;
+ }
+
+ if (hdev->tm_info.fc_mode != HCLGE_FC_PFC) {
+ hdev->fc_mode_last_time = hdev->tm_info.fc_mode;
+ hdev->tm_info.fc_mode = HCLGE_FC_PFC;
+ }
+}
+
+static void hclge_pfc_info_init(struct hclge_dev *hdev)
+{
+ if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
+ hclge_update_fc_mode(hdev);
+ else
+ hclge_update_fc_mode_by_dcb_flag(hdev);
+}
+
static void hclge_tm_schd_info_init(struct hclge_dev *hdev)
{
hclge_tm_pg_info_init(hdev);
/* Pg to pri */
for (i = 0; i < hdev->tm_info.num_pg; i++) {
+ u32 rate = hdev->tm_info.pg_info[i].bw_limit;
+
/* Calc shaper para */
- ret = hclge_shaper_para_calc(hdev->tm_info.pg_info[i].bw_limit,
- HCLGE_SHAPER_LVL_PG,
+ ret = hclge_shaper_para_calc(rate, HCLGE_SHAPER_LVL_PG,
&ir_para, max_tm_rate);
if (ret)
return ret;
HCLGE_SHAPER_BS_S_DEF);
ret = hclge_tm_pg_shapping_cfg(hdev,
HCLGE_TM_SHAP_C_BUCKET, i,
- shaper_para);
+ shaper_para, rate);
if (ret)
return ret;
HCLGE_SHAPER_BS_S_DEF);
ret = hclge_tm_pg_shapping_cfg(hdev,
HCLGE_TM_SHAP_P_BUCKET, i,
- shaper_para);
+ shaper_para, rate);
if (ret)
return ret;
}
u32 i;
for (i = 0; i < hdev->tm_info.num_tc; i++) {
- ret = hclge_shaper_para_calc(hdev->tm_info.tc_info[i].bw_limit,
- HCLGE_SHAPER_LVL_PRI,
+ u32 rate = hdev->tm_info.tc_info[i].bw_limit;
+
+ ret = hclge_shaper_para_calc(rate, HCLGE_SHAPER_LVL_PRI,
&ir_para, max_tm_rate);
if (ret)
return ret;
HCLGE_SHAPER_BS_U_DEF,
HCLGE_SHAPER_BS_S_DEF);
ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_C_BUCKET, i,
- shaper_para);
+ shaper_para, rate);
if (ret)
return ret;
HCLGE_SHAPER_BS_U_DEF,
HCLGE_SHAPER_BS_S_DEF);
ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_P_BUCKET, i,
- shaper_para);
+ shaper_para, rate);
if (ret)
return ret;
}
HCLGE_SHAPER_BS_U_DEF,
HCLGE_SHAPER_BS_S_DEF);
ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_C_BUCKET,
- vport->vport_id, shaper_para);
+ vport->vport_id, shaper_para,
+ vport->bw_limit);
if (ret)
return ret;
HCLGE_SHAPER_BS_U_DEF,
HCLGE_SHAPER_BS_S_DEF);
ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_P_BUCKET,
- vport->vport_id, shaper_para);
+ vport->vport_id, shaper_para,
+ vport->bw_limit);
if (ret)
return ret;
hdev->tm_info.pfc_en);
}
-/* Each Tc has a 1024 queue sets to backpress, it divides to
- * 32 group, each group contains 32 queue sets, which can be
- * represented by u32 bitmap.
+/* for the queues that use for backpress, divides to several groups,
+ * each group contains 32 queue sets, which can be represented by u32 bitmap.
*/
static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc)
{
+ u16 grp_id_shift = HCLGE_BP_GRP_ID_S;
+ u16 grp_id_mask = HCLGE_BP_GRP_ID_M;
+ u8 grp_num = HCLGE_BP_GRP_NUM;
int i;
- for (i = 0; i < HCLGE_BP_GRP_NUM; i++) {
+ if (hdev->num_tqps > HCLGE_TQP_MAX_SIZE_DEV_V2) {
+ grp_num = HCLGE_BP_EXT_GRP_NUM;
+ grp_id_mask = HCLGE_BP_EXT_GRP_ID_M;
+ grp_id_shift = HCLGE_BP_EXT_GRP_ID_S;
+ }
+
+ for (i = 0; i < grp_num; i++) {
u32 qs_bitmap = 0;
int k, ret;
u16 qs_id = vport->qs_offset + tc;
u8 grp, sub_grp;
- grp = hnae3_get_field(qs_id, HCLGE_BP_GRP_ID_M,
- HCLGE_BP_GRP_ID_S);
+ grp = hnae3_get_field(qs_id, grp_id_mask, grp_id_shift);
sub_grp = hnae3_get_field(qs_id, HCLGE_BP_SUB_GRP_ID_M,
HCLGE_BP_SUB_GRP_ID_S);
if (i == grp)
__le16 nq_id;
__le16 rsvd;
#define HCLGE_TM_Q_QS_LINK_VLD_MSK BIT(10)
+#define HCLGE_TM_QS_ID_L_MSK GENMASK(9, 0)
+#define HCLGE_TM_QS_ID_L_S 0
+#define HCLGE_TM_QS_ID_H_MSK GENMASK(14, 10)
+#define HCLGE_TM_QS_ID_H_S 10
+#define HCLGE_TM_QS_ID_H_EXT_S 11
+#define HCLGE_TM_QS_ID_H_EXT_MSK GENMASK(15, 11)
__le16 qset_id;
};
HCLGE_TM_SHAP_P_BUCKET,
};
+/* set bit HCLGE_TM_RATE_VLD to 1 means use 'rate' to config shaping */
+#define HCLGE_TM_RATE_VLD 0
+
struct hclge_pri_shapping_cmd {
u8 pri_id;
u8 rsvd[3];
__le32 pri_shapping_para;
+ u8 flag;
+ u8 rsvd1[3];
+ __le32 pri_rate;
};
struct hclge_pg_shapping_cmd {
u8 pg_id;
u8 rsvd[3];
__le32 pg_shapping_para;
+ u8 flag;
+ u8 rsvd1[3];
+ __le32 pg_rate;
};
struct hclge_qs_shapping_cmd {
__le16 qs_id;
u8 rsvd[2];
__le32 qs_shapping_para;
+ u8 flag;
+ u8 rsvd1[3];
+ __le32 qs_rate;
};
#define HCLGE_BP_GRP_NUM 32
#define HCLGE_BP_SUB_GRP_ID_M GENMASK(4, 0)
#define HCLGE_BP_GRP_ID_S 5
#define HCLGE_BP_GRP_ID_M GENMASK(9, 5)
+
+#define HCLGE_BP_EXT_GRP_NUM 40
+#define HCLGE_BP_EXT_GRP_ID_S 5
+#define HCLGE_BP_EXT_GRP_ID_M GENMASK(10, 5)
+
struct hclge_bp_to_qs_map_cmd {
u8 tc_id;
u8 rsvd[2];
struct hclge_port_shapping_cmd {
__le32 port_shapping_para;
+ u8 flag;
+ u8 rsvd[3];
+ __le32 port_rate;
};
struct hclge_shaper_ir_para {
set_bit(HNAE3_DEV_SUPPORT_INT_QL_B, ae_dev->caps);
if (hnae3_get_bit(caps, HCLGEVF_CAP_TQP_TXRX_INDEP_B))
set_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, ae_dev->caps);
+ if (hnae3_get_bit(caps, HCLGEVF_CAP_HW_TX_CSUM_B))
+ set_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps);
+ if (hnae3_get_bit(caps, HCLGEVF_CAP_UDP_TUNNEL_CSUM_B))
+ set_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, ae_dev->caps);
}
static int hclgevf_cmd_query_version_and_capability(struct hclgevf_dev *hdev)
#define HCLGEVF_TQP_REG_OFFSET 0x80000
#define HCLGEVF_TQP_REG_SIZE 0x200
+#define HCLGEVF_TQP_MAX_SIZE_DEV_V2 1024
+#define HCLGEVF_TQP_EXT_REG_OFFSET 0x100
+
struct hclgevf_tqp_map {
__le16 tqp_id; /* Absolute tqp id for in this pf */
u8 tqp_vf; /* VF id */
HCLGEVF_CAP_FD_FORWARD_TC_B,
HCLGEVF_CAP_PTP_B,
HCLGEVF_CAP_INT_QL_B,
- HCLGEVF_CAP_SIMPLE_BD_B,
+ HCLGEVF_CAP_HW_TX_CSUM_B,
HCLGEVF_CAP_TX_PUSH_B,
HCLGEVF_CAP_PHY_IMP_B,
HCLGEVF_CAP_TQP_TXRX_INDEP_B,
HCLGEVF_CAP_HW_PAD_B,
HCLGEVF_CAP_STASH_B,
+ HCLGEVF_CAP_UDP_TUNNEL_CSUM_B,
};
#define HCLGEVF_QUERY_CAP_LENGTH 3
u8 rsv1[5];
};
+#define HCLGEVF_DEF_MAX_INT_GL 0x1FE0U
+
+struct hclgevf_dev_specs_1_cmd {
+ __le32 rsv0;
+ __le16 max_int_gl;
+ u8 rsv1[18];
+};
+
static inline void hclgevf_write_reg(void __iomem *base, u32 reg, u32 value)
{
writel(value, base + reg);
tqp->q.buf_size = hdev->rx_buf_len;
tqp->q.tx_desc_num = hdev->num_tx_desc;
tqp->q.rx_desc_num = hdev->num_rx_desc;
- tqp->q.io_base = hdev->hw.io_base + HCLGEVF_TQP_REG_OFFSET +
- i * HCLGEVF_TQP_REG_SIZE;
+
+ /* need an extended offset to configure queues >=
+ * HCLGEVF_TQP_MAX_SIZE_DEV_V2.
+ */
+ if (i < HCLGEVF_TQP_MAX_SIZE_DEV_V2)
+ tqp->q.io_base = hdev->hw.io_base +
+ HCLGEVF_TQP_REG_OFFSET +
+ i * HCLGEVF_TQP_REG_SIZE;
+ else
+ tqp->q.io_base = hdev->hw.io_base +
+ HCLGEVF_TQP_REG_OFFSET +
+ HCLGEVF_TQP_EXT_REG_OFFSET +
+ (i - HCLGEVF_TQP_MAX_SIZE_DEV_V2) *
+ HCLGEVF_TQP_REG_SIZE;
tqp++;
}
roce->rinfo.netdev = nic->kinfo.netdev;
roce->rinfo.roce_io_base = hdev->hw.io_base;
+ roce->rinfo.roce_mem_base = hdev->hw.mem_base;
roce->pdev = nic->pdev;
roce->ae_algo = nic->ae_algo;
}
}
+static int hclgevf_dev_mem_map(struct hclgevf_dev *hdev)
+{
+#define HCLGEVF_MEM_BAR 4
+
+ struct pci_dev *pdev = hdev->pdev;
+ struct hclgevf_hw *hw = &hdev->hw;
+
+ /* for device does not have device memory, return directly */
+ if (!(pci_select_bars(pdev, IORESOURCE_MEM) & BIT(HCLGEVF_MEM_BAR)))
+ return 0;
+
+ hw->mem_base = devm_ioremap_wc(&pdev->dev,
+ pci_resource_start(pdev,
+ HCLGEVF_MEM_BAR),
+ pci_resource_len(pdev, HCLGEVF_MEM_BAR));
+ if (!hw->mem_base) {
+ dev_err(&pdev->dev, "failed to map device memory\n");
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
static int hclgevf_pci_init(struct hclgevf_dev *hdev)
{
struct pci_dev *pdev = hdev->pdev;
goto err_clr_master;
}
+ ret = hclgevf_dev_mem_map(hdev);
+ if (ret)
+ goto err_unmap_io_base;
+
return 0;
+err_unmap_io_base:
+ pci_iounmap(pdev, hdev->hw.io_base);
err_clr_master:
pci_clear_master(pdev);
pci_release_regions(pdev);
{
struct pci_dev *pdev = hdev->pdev;
+ if (hdev->hw.mem_base)
+ devm_iounmap(&pdev->dev, hdev->hw.mem_base);
+
pci_iounmap(pdev, hdev->hw.io_base);
pci_clear_master(pdev);
pci_release_regions(pdev);
HCLGEVF_MAX_NON_TSO_BD_NUM;
ae_dev->dev_specs.rss_ind_tbl_size = HCLGEVF_RSS_IND_TBL_SIZE;
ae_dev->dev_specs.rss_key_size = HCLGEVF_RSS_KEY_SIZE;
+ ae_dev->dev_specs.max_int_gl = HCLGEVF_DEF_MAX_INT_GL;
}
static void hclgevf_parse_dev_specs(struct hclgevf_dev *hdev,
{
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
struct hclgevf_dev_specs_0_cmd *req0;
+ struct hclgevf_dev_specs_1_cmd *req1;
req0 = (struct hclgevf_dev_specs_0_cmd *)desc[0].data;
+ req1 = (struct hclgevf_dev_specs_1_cmd *)desc[1].data;
ae_dev->dev_specs.max_non_tso_bd_num = req0->max_non_tso_bd_num;
ae_dev->dev_specs.rss_ind_tbl_size =
le16_to_cpu(req0->rss_ind_tbl_size);
+ ae_dev->dev_specs.int_ql_max = le16_to_cpu(req0->int_ql_max);
ae_dev->dev_specs.rss_key_size = le16_to_cpu(req0->rss_key_size);
+ ae_dev->dev_specs.max_int_gl = le16_to_cpu(req1->max_int_gl);
}
static void hclgevf_check_dev_specs(struct hclgevf_dev *hdev)
dev_specs->rss_ind_tbl_size = HCLGEVF_RSS_IND_TBL_SIZE;
if (!dev_specs->rss_key_size)
dev_specs->rss_key_size = HCLGEVF_RSS_KEY_SIZE;
+ if (!dev_specs->max_int_gl)
+ dev_specs->max_int_gl = HCLGEVF_DEF_MAX_INT_GL;
}
static int hclgevf_query_dev_specs(struct hclgevf_dev *hdev)
struct hclgevf_hw {
void __iomem *io_base;
+ void __iomem *mem_base;
int num_vec;
struct hclgevf_cmq cmq;
struct hclgevf_mac mac;
struct netlink_ext_ack *extack)
{
struct hinic_devlink_priv *priv = devlink_priv(devlink);
- const struct firmware *fw;
- int err;
-
- err = request_firmware_direct(&fw, params->file_name,
- &priv->hwdev->hwif->pdev->dev);
- if (err)
- return err;
-
- err = hinic_firmware_update(priv, fw, extack);
- release_firmware(fw);
- return err;
+ return hinic_firmware_update(priv, params->fw, extack);
}
static const struct devlink_ops hinic_devlink_ops = {
#define HINIC_PORT_H
#include <linux/types.h>
+#include <linux/ethtool.h>
#include <linux/etherdevice.h>
#include <linux/bitops.h>
static int ibmvnic_send_crq_init(struct ibmvnic_adapter *);
static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *);
static int ibmvnic_send_crq(struct ibmvnic_adapter *, union ibmvnic_crq *);
-static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle,
- union sub_crq *sub_crq);
static int send_subcrq_indirect(struct ibmvnic_adapter *, u64, u64, u64);
static irqreturn_t ibmvnic_interrupt_rx(int irq, void *instance);
static int enable_scrq_irq(struct ibmvnic_adapter *,
int count = pool->size - atomic_read(&pool->available);
u64 handle = adapter->rx_scrq[pool->index]->handle;
struct device *dev = &adapter->vdev->dev;
+ struct ibmvnic_ind_xmit_queue *ind_bufp;
+ struct ibmvnic_sub_crq_queue *rx_scrq;
+ union sub_crq *sub_crq;
int buffers_added = 0;
unsigned long lpar_rc;
- union sub_crq sub_crq;
struct sk_buff *skb;
unsigned int offset;
dma_addr_t dma_addr;
if (!pool->active)
return;
+ rx_scrq = adapter->rx_scrq[pool->index];
+ ind_bufp = &rx_scrq->ind_buf;
for (i = 0; i < count; ++i) {
- skb = alloc_skb(pool->buff_size, GFP_ATOMIC);
+ skb = netdev_alloc_skb(adapter->netdev, pool->buff_size);
if (!skb) {
dev_err(dev, "Couldn't replenish rx buff\n");
adapter->replenish_no_mem++;
pool->rx_buff[index].pool_index = pool->index;
pool->rx_buff[index].size = pool->buff_size;
- memset(&sub_crq, 0, sizeof(sub_crq));
- sub_crq.rx_add.first = IBMVNIC_CRQ_CMD;
- sub_crq.rx_add.correlator =
+ sub_crq = &ind_bufp->indir_arr[ind_bufp->index++];
+ memset(sub_crq, 0, sizeof(*sub_crq));
+ sub_crq->rx_add.first = IBMVNIC_CRQ_CMD;
+ sub_crq->rx_add.correlator =
cpu_to_be64((u64)&pool->rx_buff[index]);
- sub_crq.rx_add.ioba = cpu_to_be32(dma_addr);
- sub_crq.rx_add.map_id = pool->long_term_buff.map_id;
+ sub_crq->rx_add.ioba = cpu_to_be32(dma_addr);
+ sub_crq->rx_add.map_id = pool->long_term_buff.map_id;
/* The length field of the sCRQ is defined to be 24 bits so the
* buffer size needs to be left shifted by a byte before it is
#ifdef __LITTLE_ENDIAN__
shift = 8;
#endif
- sub_crq.rx_add.len = cpu_to_be32(pool->buff_size << shift);
-
- lpar_rc = send_subcrq(adapter, handle, &sub_crq);
- if (lpar_rc != H_SUCCESS)
- goto failure;
-
- buffers_added++;
- adapter->replenish_add_buff_success++;
+ sub_crq->rx_add.len = cpu_to_be32(pool->buff_size << shift);
pool->next_free = (pool->next_free + 1) % pool->size;
+ if (ind_bufp->index == IBMVNIC_MAX_IND_DESCS ||
+ i == count - 1) {
+ lpar_rc =
+ send_subcrq_indirect(adapter, handle,
+ (u64)ind_bufp->indir_dma,
+ (u64)ind_bufp->index);
+ if (lpar_rc != H_SUCCESS)
+ goto failure;
+ buffers_added += ind_bufp->index;
+ adapter->replenish_add_buff_success += ind_bufp->index;
+ ind_bufp->index = 0;
+ }
}
atomic_add(buffers_added, &pool->available);
return;
failure:
if (lpar_rc != H_PARAMETER && lpar_rc != H_CLOSED)
dev_err_ratelimited(dev, "rx: replenish packet buffer failed\n");
- pool->free_map[pool->next_free] = index;
- pool->rx_buff[index].skb = NULL;
-
- dev_kfree_skb_any(skb);
- adapter->replenish_add_buff_failure++;
- atomic_add(buffers_added, &pool->available);
+ for (i = ind_bufp->index - 1; i >= 0; --i) {
+ struct ibmvnic_rx_buff *rx_buff;
+ pool->next_free = pool->next_free == 0 ?
+ pool->size - 1 : pool->next_free - 1;
+ sub_crq = &ind_bufp->indir_arr[i];
+ rx_buff = (struct ibmvnic_rx_buff *)
+ be64_to_cpu(sub_crq->rx_add.correlator);
+ index = (int)(rx_buff - pool->rx_buff);
+ pool->free_map[pool->next_free] = index;
+ dev_kfree_skb_any(pool->rx_buff[index].skb);
+ pool->rx_buff[index].skb = NULL;
+ }
+ ind_bufp->index = 0;
if (lpar_rc == H_CLOSED || adapter->failover_pending) {
/* Disable buffer pool replenishment and report carrier off if
* queue is closed or pending failover.
if (rx_pool->buff_size != buff_size) {
free_long_term_buff(adapter, &rx_pool->long_term_buff);
- rx_pool->buff_size = buff_size;
+ rx_pool->buff_size = ALIGN(buff_size, L1_CACHE_BYTES);
rc = alloc_long_term_buff(adapter,
&rx_pool->long_term_buff,
rx_pool->size *
rx_pool->size = adapter->req_rx_add_entries_per_subcrq;
rx_pool->index = i;
- rx_pool->buff_size = buff_size;
+ rx_pool->buff_size = ALIGN(buff_size, L1_CACHE_BYTES);
rx_pool->active = 1;
rx_pool->free_map = kcalloc(rx_pool->size, sizeof(int),
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int tx_subcrqs;
+ u64 buff_size;
int i, rc;
tx_subcrqs = adapter->num_active_tx_scrqs;
adapter->num_active_tx_pools = tx_subcrqs;
for (i = 0; i < tx_subcrqs; i++) {
+ buff_size = adapter->req_mtu + VLAN_HLEN;
+ buff_size = ALIGN(buff_size, L1_CACHE_BYTES);
rc = init_one_tx_pool(netdev, &adapter->tx_pool[i],
adapter->req_tx_entries_per_subcrq,
- adapter->req_mtu + VLAN_HLEN);
+ buff_size);
if (rc) {
release_tx_pools(adapter);
return rc;
if (prev_state == VNIC_CLOSED)
enable_irq(adapter->tx_scrq[i]->irq);
enable_scrq_irq(adapter, adapter->tx_scrq[i]);
+ netdev_tx_reset_queue(netdev_get_tx_queue(netdev, i));
}
rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP);
* L2/L3/L4 packet header descriptors to be sent by send_subcrq_indirect.
*/
-static void build_hdr_descs_arr(struct ibmvnic_tx_buff *txbuff,
+static void build_hdr_descs_arr(struct sk_buff *skb,
+ union sub_crq *indir_arr,
int *num_entries, u8 hdr_field)
{
int hdr_len[3] = {0, 0, 0};
+ u8 hdr_data[140] = {0};
int tot_len;
- u8 *hdr_data = txbuff->hdr_data;
- tot_len = build_hdr_data(hdr_field, txbuff->skb, hdr_len,
- txbuff->hdr_data);
+ tot_len = build_hdr_data(hdr_field, skb, hdr_len,
+ hdr_data);
*num_entries += create_hdr_descs(hdr_field, hdr_data, tot_len, hdr_len,
- txbuff->indir_arr + 1);
+ indir_arr + 1);
}
static int ibmvnic_xmit_workarounds(struct sk_buff *skb,
return 0;
}
+static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter,
+ struct ibmvnic_sub_crq_queue *tx_scrq)
+{
+ struct ibmvnic_ind_xmit_queue *ind_bufp;
+ struct ibmvnic_tx_buff *tx_buff;
+ struct ibmvnic_tx_pool *tx_pool;
+ union sub_crq tx_scrq_entry;
+ int queue_num;
+ int entries;
+ int index;
+ int i;
+
+ ind_bufp = &tx_scrq->ind_buf;
+ entries = (u64)ind_bufp->index;
+ queue_num = tx_scrq->pool_index;
+
+ for (i = entries - 1; i >= 0; --i) {
+ tx_scrq_entry = ind_bufp->indir_arr[i];
+ if (tx_scrq_entry.v1.type != IBMVNIC_TX_DESC)
+ continue;
+ index = be32_to_cpu(tx_scrq_entry.v1.correlator);
+ if (index & IBMVNIC_TSO_POOL_MASK) {
+ tx_pool = &adapter->tso_pool[queue_num];
+ index &= ~IBMVNIC_TSO_POOL_MASK;
+ } else {
+ tx_pool = &adapter->tx_pool[queue_num];
+ }
+ tx_pool->free_map[tx_pool->consumer_index] = index;
+ tx_pool->consumer_index = tx_pool->consumer_index == 0 ?
+ tx_pool->num_buffers - 1 :
+ tx_pool->consumer_index - 1;
+ tx_buff = &tx_pool->tx_buff[index];
+ adapter->netdev->stats.tx_packets--;
+ adapter->netdev->stats.tx_bytes -= tx_buff->skb->len;
+ adapter->tx_stats_buffers[queue_num].packets--;
+ adapter->tx_stats_buffers[queue_num].bytes -=
+ tx_buff->skb->len;
+ dev_kfree_skb_any(tx_buff->skb);
+ tx_buff->skb = NULL;
+ adapter->netdev->stats.tx_dropped++;
+ }
+ ind_bufp->index = 0;
+ if (atomic_sub_return(entries, &tx_scrq->used) <=
+ (adapter->req_tx_entries_per_subcrq / 2) &&
+ __netif_subqueue_stopped(adapter->netdev, queue_num)) {
+ netif_wake_subqueue(adapter->netdev, queue_num);
+ netdev_dbg(adapter->netdev, "Started queue %d\n",
+ queue_num);
+ }
+}
+
+static int ibmvnic_tx_scrq_flush(struct ibmvnic_adapter *adapter,
+ struct ibmvnic_sub_crq_queue *tx_scrq)
+{
+ struct ibmvnic_ind_xmit_queue *ind_bufp;
+ u64 dma_addr;
+ u64 entries;
+ u64 handle;
+ int rc;
+
+ ind_bufp = &tx_scrq->ind_buf;
+ dma_addr = (u64)ind_bufp->indir_dma;
+ entries = (u64)ind_bufp->index;
+ handle = tx_scrq->handle;
+
+ if (!entries)
+ return 0;
+ rc = send_subcrq_indirect(adapter, handle, dma_addr, entries);
+ if (rc)
+ ibmvnic_tx_scrq_clean_buffer(adapter, tx_scrq);
+ else
+ ind_bufp->index = 0;
+ return 0;
+}
+
static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
int queue_num = skb_get_queue_mapping(skb);
u8 *hdrs = (u8 *)&adapter->tx_rx_desc_req;
struct device *dev = &adapter->vdev->dev;
+ struct ibmvnic_ind_xmit_queue *ind_bufp;
struct ibmvnic_tx_buff *tx_buff = NULL;
struct ibmvnic_sub_crq_queue *tx_scrq;
struct ibmvnic_tx_pool *tx_pool;
unsigned int tx_send_failed = 0;
+ netdev_tx_t ret = NETDEV_TX_OK;
unsigned int tx_map_failed = 0;
+ union sub_crq indir_arr[16];
unsigned int tx_dropped = 0;
unsigned int tx_packets = 0;
unsigned int tx_bytes = 0;
unsigned char *dst;
int index = 0;
u8 proto = 0;
- u64 handle;
- netdev_tx_t ret = NETDEV_TX_OK;
+
+ tx_scrq = adapter->tx_scrq[queue_num];
+ txq = netdev_get_tx_queue(netdev, queue_num);
+ ind_bufp = &tx_scrq->ind_buf;
if (test_bit(0, &adapter->resetting)) {
if (!netif_subqueue_stopped(netdev, skb))
tx_send_failed++;
tx_dropped++;
ret = NETDEV_TX_OK;
+ ibmvnic_tx_scrq_flush(adapter, tx_scrq);
goto out;
}
tx_dropped++;
tx_send_failed++;
ret = NETDEV_TX_OK;
+ ibmvnic_tx_scrq_flush(adapter, tx_scrq);
goto out;
}
if (skb_is_gso(skb))
else
tx_pool = &adapter->tx_pool[queue_num];
- tx_scrq = adapter->tx_scrq[queue_num];
- txq = netdev_get_tx_queue(netdev, skb_get_queue_mapping(skb));
- handle = tx_scrq->handle;
-
index = tx_pool->free_map[tx_pool->consumer_index];
if (index == IBMVNIC_INVALID_MAP) {
tx_send_failed++;
tx_dropped++;
ret = NETDEV_TX_OK;
+ ibmvnic_tx_scrq_flush(adapter, tx_scrq);
goto out;
}
tx_buff = &tx_pool->tx_buff[index];
tx_buff->skb = skb;
- tx_buff->data_dma[0] = data_dma_addr;
- tx_buff->data_len[0] = skb->len;
tx_buff->index = index;
tx_buff->pool_index = queue_num;
- tx_buff->last_frag = true;
memset(&tx_crq, 0, sizeof(tx_crq));
tx_crq.v1.first = IBMVNIC_CRQ_CMD;
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) {
- build_hdr_descs_arr(tx_buff, &num_entries, *hdrs);
- tx_crq.v1.n_crq_elem = num_entries;
- tx_buff->num_entries = num_entries;
- tx_buff->indir_arr[0] = tx_crq;
- tx_buff->indir_dma = dma_map_single(dev, tx_buff->indir_arr,
- sizeof(tx_buff->indir_arr),
- DMA_TO_DEVICE);
- if (dma_mapping_error(dev, tx_buff->indir_dma)) {
- dev_kfree_skb_any(skb);
- tx_buff->skb = NULL;
- if (!firmware_has_feature(FW_FEATURE_CMO))
- dev_err(dev, "tx: unable to map descriptor array\n");
- tx_map_failed++;
- tx_dropped++;
- ret = NETDEV_TX_OK;
- goto tx_err_out;
- }
- lpar_rc = send_subcrq_indirect(adapter, handle,
- (u64)tx_buff->indir_dma,
- (u64)num_entries);
- dma_unmap_single(dev, tx_buff->indir_dma,
- sizeof(tx_buff->indir_arr), DMA_TO_DEVICE);
- } else {
- tx_buff->num_entries = num_entries;
- lpar_rc = send_subcrq(adapter, handle,
- &tx_crq);
- }
- if (lpar_rc != H_SUCCESS) {
- if (lpar_rc != H_CLOSED && lpar_rc != H_PARAMETER)
- dev_err_ratelimited(dev, "tx: send failed\n");
- dev_kfree_skb_any(skb);
- tx_buff->skb = NULL;
- if (lpar_rc == H_CLOSED || adapter->failover_pending) {
- /* Disable TX and report carrier off if queue is closed
- * or pending failover.
- * Firmware guarantees that a signal will be sent to the
- * driver, triggering a reset or some other action.
- */
- netif_tx_stop_all_queues(netdev);
- netif_carrier_off(netdev);
- }
+ if ((*hdrs >> 7) & 1)
+ build_hdr_descs_arr(skb, indir_arr, &num_entries, *hdrs);
- tx_send_failed++;
- tx_dropped++;
- ret = NETDEV_TX_OK;
- goto tx_err_out;
+ tx_crq.v1.n_crq_elem = num_entries;
+ tx_buff->num_entries = num_entries;
+ /* flush buffer if current entry can not fit */
+ if (num_entries + ind_bufp->index > IBMVNIC_MAX_IND_DESCS) {
+ lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+ if (lpar_rc != H_SUCCESS)
+ goto tx_flush_err;
+ }
+
+ indir_arr[0] = tx_crq;
+ memcpy(&ind_bufp->indir_arr[ind_bufp->index], &indir_arr[0],
+ num_entries * sizeof(struct ibmvnic_generic_scrq));
+ ind_bufp->index += num_entries;
+ if (__netdev_tx_sent_queue(txq, skb->len,
+ netdev_xmit_more() &&
+ ind_bufp->index < IBMVNIC_MAX_IND_DESCS)) {
+ lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+ if (lpar_rc != H_SUCCESS)
+ goto tx_err;
}
if (atomic_add_return(num_entries, &tx_scrq->used)
ret = NETDEV_TX_OK;
goto out;
-tx_err_out:
- /* roll back consumer index and map array*/
- if (tx_pool->consumer_index == 0)
- tx_pool->consumer_index =
- tx_pool->num_buffers - 1;
- else
- tx_pool->consumer_index--;
- tx_pool->free_map[tx_pool->consumer_index] = index;
+tx_flush_err:
+ dev_kfree_skb_any(skb);
+ tx_buff->skb = NULL;
+ tx_pool->consumer_index = tx_pool->consumer_index == 0 ?
+ tx_pool->num_buffers - 1 :
+ tx_pool->consumer_index - 1;
+ tx_dropped++;
+tx_err:
+ if (lpar_rc != H_CLOSED && lpar_rc != H_PARAMETER)
+ dev_err_ratelimited(dev, "tx: send failed\n");
+
+ if (lpar_rc == H_CLOSED || adapter->failover_pending) {
+ /* Disable TX and report carrier off if queue is closed
+ * or pending failover.
+ * Firmware guarantees that a signal will be sent to the
+ * driver, triggering a reset or some other action.
+ */
+ netif_tx_stop_all_queues(netdev);
+ netif_carrier_off(netdev);
+ }
out:
netdev->stats.tx_dropped += tx_dropped;
netdev->stats.tx_bytes += tx_bytes;
static int ibmvnic_poll(struct napi_struct *napi, int budget)
{
- struct net_device *netdev = napi->dev;
- struct ibmvnic_adapter *adapter = netdev_priv(netdev);
- int scrq_num = (int)(napi - adapter->napi);
- int frames_processed = 0;
+ struct ibmvnic_sub_crq_queue *rx_scrq;
+ struct ibmvnic_adapter *adapter;
+ struct net_device *netdev;
+ int frames_processed;
+ int scrq_num;
+
+ netdev = napi->dev;
+ adapter = netdev_priv(netdev);
+ scrq_num = (int)(napi - adapter->napi);
+ frames_processed = 0;
+ rx_scrq = adapter->rx_scrq[scrq_num];
restart_poll:
while (frames_processed < budget) {
if (unlikely(test_bit(0, &adapter->resetting) &&
adapter->reset_reason != VNIC_RESET_NON_FATAL)) {
- enable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]);
+ enable_scrq_irq(adapter, rx_scrq);
napi_complete_done(napi, frames_processed);
return frames_processed;
}
- if (!pending_scrq(adapter, adapter->rx_scrq[scrq_num]))
+ if (!pending_scrq(adapter, rx_scrq))
break;
/* The queue entry at the current index is peeked at above
* to determine that there is a valid descriptor awaiting
* holds a valid descriptor before reading its contents.
*/
dma_rmb();
- next = ibmvnic_next_scrq(adapter, adapter->rx_scrq[scrq_num]);
+ next = ibmvnic_next_scrq(adapter, rx_scrq);
rx_buff =
(struct ibmvnic_rx_buff *)be64_to_cpu(next->
rx_comp.correlator);
frames_processed++;
}
- if (adapter->state != VNIC_CLOSING)
+ if (adapter->state != VNIC_CLOSING &&
+ ((atomic_read(&adapter->rx_pool[scrq_num].available) <
+ adapter->req_rx_add_entries_per_subcrq / 2) ||
+ frames_processed < budget))
replenish_rx_pool(adapter, &adapter->rx_pool[scrq_num]);
-
if (frames_processed < budget) {
- enable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]);
- napi_complete_done(napi, frames_processed);
- if (pending_scrq(adapter, adapter->rx_scrq[scrq_num]) &&
- napi_reschedule(napi)) {
- disable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]);
- goto restart_poll;
+ if (napi_complete_done(napi, frames_processed)) {
+ enable_scrq_irq(adapter, rx_scrq);
+ if (pending_scrq(adapter, rx_scrq)) {
+ rmb();
+ if (napi_reschedule(napi)) {
+ disable_scrq_irq(adapter, rx_scrq);
+ goto restart_poll;
+ }
+ }
}
}
return frames_processed;
irq_dispose_mapping(scrq->irq);
scrq->irq = 0;
}
+
if (scrq->msgs) {
memset(scrq->msgs, 0, 4 * PAGE_SIZE);
atomic_set(&scrq->used, 0);
scrq->cur = 0;
+ scrq->ind_buf.index = 0;
} else {
netdev_dbg(adapter->netdev, "Invalid scrq reset\n");
return -EINVAL;
}
}
+ dma_free_coherent(dev,
+ IBMVNIC_IND_ARR_SZ,
+ scrq->ind_buf.indir_arr,
+ scrq->ind_buf.indir_dma);
+
dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE,
DMA_BIDIRECTIONAL);
free_pages((unsigned long)scrq->msgs, 2);
scrq->adapter = adapter;
scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs);
+ scrq->ind_buf.index = 0;
+
+ scrq->ind_buf.indir_arr =
+ dma_alloc_coherent(dev,
+ IBMVNIC_IND_ARR_SZ,
+ &scrq->ind_buf.indir_dma,
+ GFP_KERNEL);
+
+ if (!scrq->ind_buf.indir_arr)
+ goto indir_failed;
+
spin_lock_init(&scrq->lock);
netdev_dbg(adapter->netdev,
return scrq;
+indir_failed:
+ do {
+ rc = plpar_hcall_norets(H_FREE_SUB_CRQ,
+ adapter->vdev->unit_address,
+ scrq->crq_num);
+ } while (rc == H_BUSY || rc == H_IS_LONG_BUSY(rc));
reg_failed:
dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE,
DMA_BIDIRECTIONAL);
struct device *dev = &adapter->vdev->dev;
struct ibmvnic_tx_pool *tx_pool;
struct ibmvnic_tx_buff *txbuff;
+ struct netdev_queue *txq;
union sub_crq *next;
int index;
- int i, j;
+ int i;
restart_loop:
while (pending_scrq(adapter, scrq)) {
unsigned int pool = scrq->pool_index;
int num_entries = 0;
+ int total_bytes = 0;
+ int num_packets = 0;
/* The queue entry at the current index is peeked at above
* to determine that there is a valid descriptor awaiting
}
txbuff = &tx_pool->tx_buff[index];
-
- for (j = 0; j < IBMVNIC_MAX_FRAGS_PER_CRQ; j++) {
- if (!txbuff->data_dma[j])
- continue;
-
- txbuff->data_dma[j] = 0;
- }
-
- if (txbuff->last_frag) {
- dev_kfree_skb_any(txbuff->skb);
+ num_packets++;
+ num_entries += txbuff->num_entries;
+ if (txbuff->skb) {
+ total_bytes += txbuff->skb->len;
+ dev_consume_skb_irq(txbuff->skb);
txbuff->skb = NULL;
+ } else {
+ netdev_warn(adapter->netdev,
+ "TX completion received with NULL socket buffer\n");
}
-
- num_entries += txbuff->num_entries;
-
tx_pool->free_map[tx_pool->producer_index] = index;
tx_pool->producer_index =
(tx_pool->producer_index + 1) %
/* remove tx_comp scrq*/
next->tx_comp.first = 0;
+ txq = netdev_get_tx_queue(adapter->netdev, scrq->pool_index);
+ netdev_tx_completed_queue(txq, num_packets, total_bytes);
+
if (atomic_sub_return(num_entries, &scrq->used) <=
(adapter->req_tx_entries_per_subcrq / 2) &&
__netif_subqueue_stopped(adapter->netdev,
}
}
-static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle,
- union sub_crq *sub_crq)
-{
- unsigned int ua = adapter->vdev->unit_address;
- struct device *dev = &adapter->vdev->dev;
- u64 *u64_crq = (u64 *)sub_crq;
- int rc;
-
- netdev_dbg(adapter->netdev,
- "Sending sCRQ %016lx: %016lx %016lx %016lx %016lx\n",
- (unsigned long int)cpu_to_be64(remote_handle),
- (unsigned long int)cpu_to_be64(u64_crq[0]),
- (unsigned long int)cpu_to_be64(u64_crq[1]),
- (unsigned long int)cpu_to_be64(u64_crq[2]),
- (unsigned long int)cpu_to_be64(u64_crq[3]));
-
- /* Make sure the hypervisor sees the complete request */
- mb();
-
- rc = plpar_hcall_norets(H_SEND_SUB_CRQ, ua,
- cpu_to_be64(remote_handle),
- cpu_to_be64(u64_crq[0]),
- cpu_to_be64(u64_crq[1]),
- cpu_to_be64(u64_crq[2]),
- cpu_to_be64(u64_crq[3]));
-
- if (rc)
- print_subcrq_error(dev, rc, __func__);
-
- return rc;
-}
-
static int send_subcrq_indirect(struct ibmvnic_adapter *adapter,
u64 remote_handle, u64 ioba, u64 num_entries)
{
#define IBMVNIC_BUFFS_PER_POOL 100
#define IBMVNIC_MAX_QUEUES 16
#define IBMVNIC_MAX_QUEUE_SZ 4096
+#define IBMVNIC_MAX_IND_DESCS 128
+#define IBMVNIC_IND_ARR_SZ (IBMVNIC_MAX_IND_DESCS * 32)
#define IBMVNIC_TSO_BUF_SZ 65536
#define IBMVNIC_TSO_BUFS 64
#define IBMVNIC_TCP_CHKSUM 0x20
#define IBMVNIC_UDP_CHKSUM 0x08
-#define IBMVNIC_MAX_FRAGS_PER_CRQ 3
-
struct ibmvnic_tx_desc {
u8 first;
u8 type;
struct ibmvnic_rx_buff_add_desc rx_add;
};
+struct ibmvnic_ind_xmit_queue {
+ union sub_crq *indir_arr;
+ dma_addr_t indir_dma;
+ int index;
+};
+
struct ibmvnic_sub_crq_queue {
union sub_crq *msgs;
int size, cur;
spinlock_t lock;
struct sk_buff *rx_skb_top;
struct ibmvnic_adapter *adapter;
+ struct ibmvnic_ind_xmit_queue ind_buf;
atomic_t used;
char name[32];
u64 handle;
-};
+} ____cacheline_aligned;
struct ibmvnic_long_term_buff {
unsigned char *buff;
struct ibmvnic_tx_buff {
struct sk_buff *skb;
- dma_addr_t data_dma[IBMVNIC_MAX_FRAGS_PER_CRQ];
- unsigned int data_len[IBMVNIC_MAX_FRAGS_PER_CRQ];
int index;
int pool_index;
- bool last_frag;
- union sub_crq indir_arr[6];
- u8 hdr_data[140];
- dma_addr_t indir_dma;
int num_entries;
};
struct ibmvnic_long_term_buff long_term_buff;
int num_buffers;
int buf_size;
-};
+} ____cacheline_aligned;
struct ibmvnic_rx_buff {
struct sk_buff *skb;
int next_alloc;
int active;
struct ibmvnic_long_term_buff long_term_buff;
-};
+} ____cacheline_aligned;
struct ibmvnic_vpd {
unsigned char *buff;
atomic_t running_cap_crqs;
bool wait_capability;
- struct ibmvnic_sub_crq_queue **tx_scrq;
- struct ibmvnic_sub_crq_queue **rx_scrq;
+ struct ibmvnic_sub_crq_queue **tx_scrq ____cacheline_aligned;
+ struct ibmvnic_sub_crq_queue **rx_scrq ____cacheline_aligned;
/* rx structs */
struct napi_struct *napi;
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2013 - 2019 Intel Corporation. */
+#include <linux/ethtool.h>
#include <linux/vmalloc.h>
#include "fm10k.h"
} else if (vf->link_forced) {
pfe.event_data.link_event.link_status = vf->link_up;
pfe.event_data.link_event.link_speed =
- (vf->link_up ? VIRTCHNL_LINK_SPEED_40GB : 0);
+ (vf->link_up ? i40e_virtchnl_link_speed(ls->link_speed) : 0);
} else {
pfe.event_data.link_event.link_status =
ls->link_info & I40E_AQ_LINK_UP;
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_pf *pf = np->vsi->back;
+ struct i40e_link_status *ls = &pf->hw.phy.link_info;
struct virtchnl_pf_event pfe;
struct i40e_hw *hw = &pf->hw;
struct i40e_vf *vf;
vf->link_forced = true;
vf->link_up = true;
pfe.event_data.link_event.link_status = true;
- pfe.event_data.link_event.link_speed = VIRTCHNL_LINK_SPEED_40GB;
+ pfe.event_data.link_event.link_speed = i40e_virtchnl_link_speed(ls->link_speed);
break;
case IFLA_VF_LINK_STATE_DISABLE:
vf->link_forced = true;
continue;
}
- bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
if (!size)
struct netlink_ext_ack *extack)
{
struct ice_pf *pf = devlink_priv(devlink);
- struct device *dev = &pf->pdev->dev;
struct ice_hw *hw = &pf->hw;
- const struct firmware *fw;
u8 preservation;
int err;
if (err)
return err;
- err = request_firmware(&fw, params->file_name, dev);
- if (err) {
- NL_SET_ERR_MSG_MOD(extack, "Unable to read file from disk");
- return err;
- }
-
- dev_dbg(dev, "Beginning flash update with file '%s'\n", params->file_name);
-
- devlink_flash_update_begin_notify(devlink);
devlink_flash_update_status_notify(devlink, "Preparing to flash", NULL, 0, 0);
- err = ice_flash_pldm_image(pf, fw, preservation, extack);
- devlink_flash_update_end_notify(devlink);
-
- release_firmware(fw);
- return err;
+ return ice_flash_pldm_image(pf, params->fw, preservation, extack);
}
static const struct devlink_ops ice_devlink_ops = {
spin_lock_bh(&hw->mbx_lock);
if (hw->mac.ops.set_vfta(hw, vid, true)) {
- dev_err(&adapter->pdev->dev, "Failed to add vlan id %d\n", vid);
+ dev_warn(&adapter->pdev->dev, "Vlan id %d\n is not added", vid);
spin_unlock_bh(&hw->mbx_lock);
return -EINVAL;
}
/* Allow time for pending master requests to run */
if (mac->ops.reset_hw(hw))
- dev_err(&adapter->pdev->dev, "PF still resetting\n");
+ dev_warn(&adapter->pdev->dev, "PF still resetting\n");
mac->ops.init_hw(hw);
struct netdev_queue *nq, bool napi)
{
unsigned int bytes_compl = 0, pkts_compl = 0;
+ struct xdp_frame_bulk bq;
int i;
+ xdp_frame_bulk_init(&bq);
+
+ rcu_read_lock(); /* need for xdp_return_frame_bulk */
+
for (i = 0; i < num; i++) {
struct mvneta_tx_buf *buf = &txq->buf[txq->txq_get_index];
struct mvneta_tx_desc *tx_desc = txq->descs +
if (napi && buf->type == MVNETA_TYPE_XDP_TX)
xdp_return_frame_rx_napi(buf->xdpf);
else
- xdp_return_frame(buf->xdpf);
+ xdp_return_frame_bulk(buf->xdpf, &bq);
}
}
+ xdp_flush_frame_bulk(&bq);
+
+ rcu_read_unlock();
netdev_tx_completed_queue(nq, pkts_compl, bytes_compl);
}
static void
mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
- struct xdp_buff *xdp, int sync_len, bool napi)
+ struct xdp_buff *xdp, struct skb_shared_info *sinfo,
+ int sync_len)
{
- struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
int i;
for (i = 0; i < sinfo->nr_frags; i++)
page_pool_put_full_page(rxq->page_pool,
- skb_frag_page(&sinfo->frags[i]), napi);
+ skb_frag_page(&sinfo->frags[i]), true);
page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data),
- sync_len, napi);
+ sync_len, true);
}
static int
struct bpf_prog *prog, struct xdp_buff *xdp,
u32 frame_sz, struct mvneta_stats *stats)
{
+ struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
unsigned int len, data_len, sync;
u32 ret, act;
err = xdp_do_redirect(pp->dev, xdp, prog);
if (unlikely(err)) {
- mvneta_xdp_put_buff(pp, rxq, xdp, sync, true);
+ mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
ret = MVNETA_XDP_DROPPED;
} else {
ret = MVNETA_XDP_REDIR;
case XDP_TX:
ret = mvneta_xdp_xmit_back(pp, xdp);
if (ret != MVNETA_XDP_TX)
- mvneta_xdp_put_buff(pp, rxq, xdp, sync, true);
+ mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
break;
default:
bpf_warn_invalid_xdp_action(act);
trace_xdp_exception(pp->dev, prog, act);
fallthrough;
case XDP_DROP:
- mvneta_xdp_put_buff(pp, rxq, xdp, sync, true);
+ mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
ret = MVNETA_XDP_DROPPED;
stats->xdp_drop++;
break;
struct mvneta_rx_desc *rx_desc,
struct mvneta_rx_queue *rxq,
struct xdp_buff *xdp, int *size,
+ struct skb_shared_info *xdp_sinfo,
struct page *page)
{
- struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
struct net_device *dev = pp->dev;
enum dma_data_direction dma_dir;
int data_len, len;
len, dma_dir);
rx_desc->buf_phys_addr = 0;
- if (data_len > 0 && sinfo->nr_frags < MAX_SKB_FRAGS) {
- skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags];
+ if (data_len > 0 && xdp_sinfo->nr_frags < MAX_SKB_FRAGS) {
+ skb_frag_t *frag = &xdp_sinfo->frags[xdp_sinfo->nr_frags++];
skb_frag_off_set(frag, pp->rx_offset_correction);
skb_frag_size_set(frag, data_len);
__skb_frag_set_page(frag, page);
- sinfo->nr_frags++;
+
+ /* last fragment */
+ if (len == *size) {
+ struct skb_shared_info *sinfo;
+
+ sinfo = xdp_get_shared_info_from_buff(xdp);
+ sinfo->nr_frags = xdp_sinfo->nr_frags;
+ memcpy(sinfo->frags, xdp_sinfo->frags,
+ sinfo->nr_frags * sizeof(skb_frag_t));
+ }
} else {
page_pool_put_full_page(rxq->page_pool, page, true);
}
{
int rx_proc = 0, rx_todo, refill, size = 0;
struct net_device *dev = pp->dev;
- struct xdp_buff xdp_buf = {
- .frame_sz = PAGE_SIZE,
- .rxq = &rxq->xdp_rxq,
- };
+ struct skb_shared_info sinfo;
struct mvneta_stats ps = {};
struct bpf_prog *xdp_prog;
u32 desc_status, frame_sz;
+ struct xdp_buff xdp_buf;
+
+ xdp_buf.data_hard_start = NULL;
+ xdp_buf.frame_sz = PAGE_SIZE;
+ xdp_buf.rxq = &rxq->xdp_rxq;
+
+ sinfo.nr_frags = 0;
/* Get number of received packets */
rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq);
rx_desc->buf_phys_addr = 0;
page_pool_put_full_page(rxq->page_pool, page,
true);
- continue;
+ goto next;
}
mvneta_swbm_add_rx_fragment(pp, rx_desc, rxq, &xdp_buf,
- &size, page);
+ &size, &sinfo, page);
} /* Middle or Last descriptor */
if (!(rx_status & MVNETA_RXD_LAST_DESC))
continue;
if (size) {
- mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1, true);
+ mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);
goto next;
}
if (IS_ERR(skb)) {
struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
- mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1, true);
+ mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);
u64_stats_update_begin(&stats->syncp);
stats->es.skb_alloc_error++;
napi_gro_receive(napi, skb);
next:
xdp_buf.data_hard_start = NULL;
+ sinfo.nr_frags = 0;
}
rcu_read_unlock();
if (xdp_buf.data_hard_start)
- mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1, true);
+ mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);
if (ps.xdp_redirect)
xdp_do_flush_map();
/* Maximum number of supported ports */
#define MVPP2_MAX_PORTS 4
+/* Loopback port index */
+#define MVPP2_LOOPBACK_PORT_INDEX 3
+
/* Maximum number of TXQs used by single port */
#define MVPP2_MAX_TXQ 8
#define MVPP2_TX_DESC_ALIGN (MVPP2_DESC_ALIGNED_SIZE - 1)
/* RX FIFO constants */
+#define MVPP2_RX_FIFO_PORT_DATA_SIZE_44KB 0xb000
#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(data_size) ((data_size) >> 6)
#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
-#define MVPP2_TX_FIFO_THRESHOLD_MIN 256
-#define MVPP2_TX_FIFO_THRESHOLD_10KB \
- (MVPP22_TX_FIFO_DATA_SIZE_10KB * 1024 - MVPP2_TX_FIFO_THRESHOLD_MIN)
-#define MVPP2_TX_FIFO_THRESHOLD_3KB \
- (MVPP22_TX_FIFO_DATA_SIZE_3KB * 1024 - MVPP2_TX_FIFO_THRESHOLD_MIN)
+#define MVPP22_TX_FIFO_DATA_SIZE_16KB 16
+#define MVPP22_TX_FIFO_DATA_SIZE_10KB 10
+#define MVPP22_TX_FIFO_DATA_SIZE_3KB 3
+#define MVPP2_TX_FIFO_THRESHOLD_MIN 256 /* Bytes */
+#define MVPP2_TX_FIFO_THRESHOLD(kb) \
+ ((kb) * 1024 - MVPP2_TX_FIFO_THRESHOLD_MIN)
/* RX buffer constants */
#define MVPP2_SKB_SHINFO_SIZE \
/* List of pointers to port structures */
int port_count;
struct mvpp2_port *port_list[MVPP2_MAX_PORTS];
+ /* Map of enabled ports */
+ unsigned long port_map;
+
struct mvpp2_tai *tai;
/* Number of Tx threads used */
struct mvpp2_tx_queue *txq,
struct mvpp2_txq_pcpu *txq_pcpu, int num)
{
+ struct xdp_frame_bulk bq;
int i;
+ xdp_frame_bulk_init(&bq);
+
+ rcu_read_lock(); /* need for xdp_return_frame_bulk */
+
for (i = 0; i < num; i++) {
struct mvpp2_txq_pcpu_buf *tx_buf =
txq_pcpu->buffs + txq_pcpu->txq_get_index;
dev_kfree_skb_any(tx_buf->skb);
else if (tx_buf->type == MVPP2_TYPE_XDP_TX ||
tx_buf->type == MVPP2_TYPE_XDP_NDO)
- xdp_return_frame(tx_buf->xdpf);
+ xdp_return_frame_bulk(tx_buf->xdpf, &bq);
mvpp2_txq_inc_get(txq_pcpu);
}
+ xdp_flush_frame_bulk(&bq);
+
+ rcu_read_unlock();
}
static inline struct mvpp2_rx_queue *mvpp2_get_rx_queue(struct mvpp2_port *port,
mvpp2_write(priv, MVPP2_RX_FIFO_INIT_REG, 0x1);
}
-static void mvpp22_rx_fifo_init(struct mvpp2 *priv)
+static void mvpp22_rx_fifo_set_hw(struct mvpp2 *priv, int port, int data_size)
{
- int port;
+ int attr_size = MVPP2_RX_FIFO_PORT_ATTR_SIZE(data_size);
- /* 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(port), data_size);
+ mvpp2_write(priv, MVPP2_RX_ATTR_FIFO_SIZE_REG(port), attr_size);
+}
- 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);
+/* Initialize TX FIFO's: the total FIFO size is 48kB on PPv2.2.
+ * 4kB fixed space must be assigned for the loopback port.
+ * Redistribute remaining avialable 44kB space among all active ports.
+ * Guarantee minimum 32kB for 10G port and 8kB for port 1, capable of 2.5G
+ * SGMII link.
+ */
+static void mvpp22_rx_fifo_init(struct mvpp2 *priv)
+{
+ int remaining_ports_count;
+ unsigned long port_map;
+ int size_remainder;
+ int port, size;
+
+ /* The loopback requires fixed 4kB of the FIFO space assignment. */
+ mvpp22_rx_fifo_set_hw(priv, MVPP2_LOOPBACK_PORT_INDEX,
+ MVPP2_RX_FIFO_PORT_DATA_SIZE_4KB);
+ port_map = priv->port_map & ~BIT(MVPP2_LOOPBACK_PORT_INDEX);
+
+ /* Set RX FIFO size to 0 for inactive ports. */
+ for_each_clear_bit(port, &port_map, MVPP2_LOOPBACK_PORT_INDEX)
+ mvpp22_rx_fifo_set_hw(priv, port, 0);
+
+ /* Assign remaining RX FIFO space among all active ports. */
+ size_remainder = MVPP2_RX_FIFO_PORT_DATA_SIZE_44KB;
+ remaining_ports_count = hweight_long(port_map);
+
+ for_each_set_bit(port, &port_map, MVPP2_LOOPBACK_PORT_INDEX) {
+ if (remaining_ports_count == 1)
+ size = size_remainder;
+ else if (port == 0)
+ size = max(size_remainder / remaining_ports_count,
+ MVPP2_RX_FIFO_PORT_DATA_SIZE_32KB);
+ else if (port == 1)
+ size = max(size_remainder / remaining_ports_count,
+ MVPP2_RX_FIFO_PORT_DATA_SIZE_8KB);
+ else
+ size = size_remainder / remaining_ports_count;
- 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);
+ size_remainder -= size;
+ remaining_ports_count--;
- 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);
+ mvpp22_rx_fifo_set_hw(priv, port, size);
}
mvpp2_write(priv, MVPP2_RX_MIN_PKT_SIZE_REG,
mvpp2_write(priv, MVPP2_RX_FIFO_INIT_REG, 0x1);
}
-/* Initialize Tx FIFO's: the total FIFO size is 19kB on PPv2.2 and 10G
- * interfaces must have a Tx FIFO size of 10kB. As only port 0 can do 10G,
- * configure its Tx FIFO size to 10kB and the others ports Tx FIFO size to 3kB.
+static void mvpp22_tx_fifo_set_hw(struct mvpp2 *priv, int port, int size)
+{
+ int threshold = MVPP2_TX_FIFO_THRESHOLD(size);
+
+ mvpp2_write(priv, MVPP22_TX_FIFO_SIZE_REG(port), size);
+ mvpp2_write(priv, MVPP22_TX_FIFO_THRESH_REG(port), threshold);
+}
+
+/* Initialize TX FIFO's: the total FIFO size is 19kB on PPv2.2.
+ * 3kB fixed space must be assigned for the loopback port.
+ * Redistribute remaining avialable 16kB space among all active ports.
+ * The 10G interface should use 10kB (which is maximum possible size
+ * per single port).
*/
static void mvpp22_tx_fifo_init(struct mvpp2 *priv)
{
- int port, size, thrs;
-
- for (port = 0; port < MVPP2_MAX_PORTS; port++) {
- if (port == 0) {
+ int remaining_ports_count;
+ unsigned long port_map;
+ int size_remainder;
+ int port, size;
+
+ /* The loopback requires fixed 3kB of the FIFO space assignment. */
+ mvpp22_tx_fifo_set_hw(priv, MVPP2_LOOPBACK_PORT_INDEX,
+ MVPP22_TX_FIFO_DATA_SIZE_3KB);
+ port_map = priv->port_map & ~BIT(MVPP2_LOOPBACK_PORT_INDEX);
+
+ /* Set TX FIFO size to 0 for inactive ports. */
+ for_each_clear_bit(port, &port_map, MVPP2_LOOPBACK_PORT_INDEX)
+ mvpp22_tx_fifo_set_hw(priv, port, 0);
+
+ /* Assign remaining TX FIFO space among all active ports. */
+ size_remainder = MVPP22_TX_FIFO_DATA_SIZE_16KB;
+ remaining_ports_count = hweight_long(port_map);
+
+ for_each_set_bit(port, &port_map, MVPP2_LOOPBACK_PORT_INDEX) {
+ if (remaining_ports_count == 1)
+ size = min(size_remainder,
+ MVPP22_TX_FIFO_DATA_SIZE_10KB);
+ else if (port == 0)
size = MVPP22_TX_FIFO_DATA_SIZE_10KB;
- thrs = MVPP2_TX_FIFO_THRESHOLD_10KB;
- } else {
- size = MVPP22_TX_FIFO_DATA_SIZE_3KB;
- thrs = MVPP2_TX_FIFO_THRESHOLD_3KB;
- }
- mvpp2_write(priv, MVPP22_TX_FIFO_SIZE_REG(port), size);
- mvpp2_write(priv, MVPP22_TX_FIFO_THRESH_REG(port), thrs);
+ else
+ size = size_remainder / remaining_ports_count;
+
+ size_remainder -= size;
+ remaining_ports_count--;
+
+ mvpp22_tx_fifo_set_hw(priv, port, size);
}
}
goto err_axi_clk;
}
+ /* Map DTS-active ports. Should be done before FIFO mvpp2_init */
+ fwnode_for_each_available_child_node(fwnode, port_fwnode) {
+ if (!fwnode_property_read_u32(port_fwnode, "port-id", &i))
+ priv->port_map |= BIT(i);
+ }
+
/* Initialize network controller */
err = mvpp2_init(pdev, priv);
if (err < 0) {
octeontx2_mbox-y := mbox.o rvu_trace.o
octeontx2_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \
- rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o
+ rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o rvu_npc_fs.o \
+ rvu_cpt.o
return cgx->cgx_id;
}
+u8 cgx_lmac_get_p2x(int cgx_id, int lmac_id)
+{
+ struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ u64 cfg;
+
+ cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_CFG);
+
+ return (cfg & CMR_P2X_SEL_MASK) >> CMR_P2X_SEL_SHIFT;
+}
+
/* Ensure the required lock for event queue(where asynchronous events are
* posted) is acquired before calling this API. Else an asynchronous event(with
* latest link status) can reach the destination before this function returns
minor_ver = FIELD_GET(RESP_MINOR_VER, resp);
dev_dbg(dev, "Firmware command interface version = %d.%d\n",
major_ver, minor_ver);
- if (major_ver != CGX_FIRMWARE_MAJOR_VER ||
- minor_ver != CGX_FIRMWARE_MINOR_VER)
+ if (major_ver != CGX_FIRMWARE_MAJOR_VER)
return -EIO;
else
return 0;
/* Registers */
#define CGXX_CMRX_CFG 0x00
+#define CMR_P2X_SEL_MASK GENMASK_ULL(61, 59)
+#define CMR_P2X_SEL_SHIFT 59ULL
+#define CMR_P2X_SEL_NIX0 1ULL
+#define CMR_P2X_SEL_NIX1 2ULL
#define CMR_EN BIT_ULL(55)
#define DATA_PKT_TX_EN BIT_ULL(53)
#define DATA_PKT_RX_EN BIT_ULL(54)
int cgx_lmac_set_pause_frm(void *cgxd, int lmac_id,
u8 tx_pause, u8 rx_pause);
void cgx_lmac_ptp_config(void *cgxd, int lmac_id, bool enable);
+u8 cgx_lmac_get_p2x(int cgx_id, int lmac_id);
#endif /* CGX_H */
#define NIX_RX_ACTIONOP_UCAST_IPSEC (0x2ull)
#define NIX_RX_ACTIONOP_MCAST (0x3ull)
#define NIX_RX_ACTIONOP_RSS (0x4ull)
+/* Use the RX action set in the default unicast entry */
+#define NIX_RX_ACTION_DEFAULT (0xfull)
/* NIX TX action operation*/
#define NIX_TX_ACTIONOP_DROP (0x0ull)
#define NPC_MCAM_KEY_X2 1
#define NPC_MCAM_KEY_X4 2
-#define NIX_INTF_RX 0
-#define NIX_INTF_TX 1
+#define NIX_INTFX_RX(a) (0x0ull | (a) << 1)
+#define NIX_INTFX_TX(a) (0x1ull | (a) << 1)
+
+/* Default interfaces are NIX0_RX and NIX0_TX */
+#define NIX_INTF_RX NIX_INTFX_RX(0)
+#define NIX_INTF_TX NIX_INTFX_TX(0)
#define NIX_INTF_TYPE_CGX 0
#define NIX_INTF_TYPE_LBK 1
NIX0_RX = 0x0,
NIX0_TX = 0x1,
NPA0_U = 0x2,
+ NIX1_RX = 0x4,
+ NIX1_TX = 0x5,
};
enum ndc_ctype_e {
#define OTX2_MBOX_REQ_SIG (0xdead)
#define OTX2_MBOX_RSP_SIG (0xbeef)
u16 sig; /* Signature, for validating corrupted msgs */
-#define OTX2_MBOX_VERSION (0x0001)
+#define OTX2_MBOX_VERSION (0x0007)
u16 ver; /* Version of msg's structure for this ID */
u16 next_msgoff; /* Offset of next msg within mailbox region */
int rc; /* Msg process'ed response code */
/* SSO/SSOW mbox IDs (range 0x600 - 0x7FF) */ \
/* TIM mbox IDs (range 0x800 - 0x9FF) */ \
/* CPT mbox IDs (range 0xA00 - 0xBFF) */ \
+M(CPT_LF_ALLOC, 0xA00, cpt_lf_alloc, cpt_lf_alloc_req_msg, \
+ msg_rsp) \
+M(CPT_LF_FREE, 0xA01, cpt_lf_free, msg_req, msg_rsp) \
+M(CPT_RD_WR_REGISTER, 0xA02, cpt_rd_wr_register, cpt_rd_wr_reg_msg, \
+ cpt_rd_wr_reg_msg) \
/* NPC mbox IDs (range 0x6000 - 0x7FFF) */ \
M(NPC_MCAM_ALLOC_ENTRY, 0x6000, npc_mcam_alloc_entry, npc_mcam_alloc_entry_req,\
npc_mcam_alloc_entry_rsp) \
npc_mcam_alloc_and_write_entry_rsp) \
M(NPC_GET_KEX_CFG, 0x600c, npc_get_kex_cfg, \
msg_req, npc_get_kex_cfg_rsp) \
+M(NPC_INSTALL_FLOW, 0x600d, npc_install_flow, \
+ npc_install_flow_req, npc_install_flow_rsp) \
+M(NPC_DELETE_FLOW, 0x600e, npc_delete_flow, \
+ npc_delete_flow_req, msg_rsp) \
+M(NPC_MCAM_READ_ENTRY, 0x600f, npc_mcam_read_entry, \
+ npc_mcam_read_entry_req, \
+ npc_mcam_read_entry_rsp) \
+M(NPC_MCAM_READ_BASE_RULE, 0x6011, npc_read_base_steer_rule, \
+ msg_req, npc_mcam_read_base_rule_rsp) \
/* NIX mbox IDs (range 0x8000 - 0xFFFF) */ \
M(NIX_LF_ALLOC, 0x8000, nix_lf_alloc, \
nix_lf_alloc_req, nix_lf_alloc_rsp) \
-M(NIX_LF_FREE, 0x8001, nix_lf_free, msg_req, msg_rsp) \
+M(NIX_LF_FREE, 0x8001, nix_lf_free, nix_lf_free_req, msg_rsp) \
M(NIX_AQ_ENQ, 0x8002, nix_aq_enq, nix_aq_enq_req, nix_aq_enq_rsp) \
M(NIX_HWCTX_DISABLE, 0x8003, nix_hwctx_disable, \
hwctx_disable_req, msg_rsp) \
M(NIX_TXSCH_FREE, 0x8005, nix_txsch_free, nix_txsch_free_req, msg_rsp) \
M(NIX_TXSCHQ_CFG, 0x8006, nix_txschq_cfg, nix_txschq_config, msg_rsp) \
M(NIX_STATS_RST, 0x8007, nix_stats_rst, msg_req, msg_rsp) \
-M(NIX_VTAG_CFG, 0x8008, nix_vtag_cfg, nix_vtag_config, msg_rsp) \
+M(NIX_VTAG_CFG, 0x8008, nix_vtag_cfg, nix_vtag_config, \
+ nix_vtag_config_rsp) \
M(NIX_RSS_FLOWKEY_CFG, 0x8009, nix_rss_flowkey_cfg, \
nix_rss_flowkey_cfg, \
nix_rss_flowkey_cfg_rsp) \
M(NIX_LSO_FORMAT_CFG, 0x8011, nix_lso_format_cfg, \
nix_lso_format_cfg, \
nix_lso_format_cfg_rsp) \
-M(NIX_RXVLAN_ALLOC, 0x8012, nix_rxvlan_alloc, msg_req, msg_rsp) \
M(NIX_LF_PTP_TX_ENABLE, 0x8013, nix_lf_ptp_tx_enable, msg_req, msg_rsp) \
M(NIX_LF_PTP_TX_DISABLE, 0x8014, nix_lf_ptp_tx_disable, msg_req, msg_rsp) \
M(NIX_BP_ENABLE, 0x8016, nix_bp_enable, nix_bp_cfg_req, \
* or to detach partial of a cetain resource type.
* Rest of the fields specify how many of what type to
* be attached.
+ * To request LFs from two blocks of same type this mailbox
+ * can be sent twice as below:
+ * struct rsrc_attach *attach;
+ * .. Allocate memory for message ..
+ * attach->cptlfs = 3; <3 LFs from CPT0>
+ * .. Send message ..
+ * .. Allocate memory for message ..
+ * attach->modify = 1;
+ * attach->cpt_blkaddr = BLKADDR_CPT1;
+ * attach->cptlfs = 2; <2 LFs from CPT1>
+ * .. Send message ..
*/
struct rsrc_attach {
struct mbox_msghdr hdr;
u16 ssow;
u16 timlfs;
u16 cptlfs;
+ int cpt_blkaddr; /* BLKADDR_CPT0/BLKADDR_CPT1 or 0 for BLKADDR_CPT0 */
};
/* Structure for relinquishing resources.
u16 ssow_msixoff[MAX_RVU_BLKLF_CNT];
u16 timlf_msixoff[MAX_RVU_BLKLF_CNT];
u16 cptlf_msixoff[MAX_RVU_BLKLF_CNT];
+ u8 cpt1_lfs;
+ u16 cpt1_lf_msixoff[MAX_RVU_BLKLF_CNT];
};
struct get_hw_cap_rsp {
NIX_AF_ERR_LSO_CFG_FAIL = -418,
NIX_AF_INVAL_NPA_PF_FUNC = -419,
NIX_AF_INVAL_SSO_PF_FUNC = -420,
+ NIX_AF_ERR_TX_VTAG_NOSPC = -421,
+ NIX_AF_ERR_RX_VTAG_INUSE = -422,
+};
+
+/* For NIX RX vtag action */
+enum nix_rx_vtag0_type {
+ NIX_AF_LFX_RX_VTAG_TYPE0, /* reserved for rx vlan offload */
+ NIX_AF_LFX_RX_VTAG_TYPE1,
+ NIX_AF_LFX_RX_VTAG_TYPE2,
+ NIX_AF_LFX_RX_VTAG_TYPE3,
+ NIX_AF_LFX_RX_VTAG_TYPE4,
+ NIX_AF_LFX_RX_VTAG_TYPE5,
+ NIX_AF_LFX_RX_VTAG_TYPE6,
+ NIX_AF_LFX_RX_VTAG_TYPE7,
};
/* For NIX LF context alloc and init */
u8 lf_tx_stats; /* NIX_AF_CONST1::LF_TX_STATS */
u16 cints; /* NIX_AF_CONST2::CINTS */
u16 qints; /* NIX_AF_CONST2::QINTS */
+ u8 cgx_links; /* No. of CGX links present in HW */
+ u8 lbk_links; /* No. of LBK links present in HW */
+ u8 sdp_links; /* No. of SDP links present in HW */
+};
+
+struct nix_lf_free_req {
+ struct mbox_msghdr hdr;
+#define NIX_LF_DISABLE_FLOWS BIT_ULL(0)
+#define NIX_LF_DONT_FREE_TX_VTAG BIT_ULL(1)
+ u64 flags;
};
/* NIX AQ enqueue msg */
union {
/* valid when cfg_type is '0' */
struct {
- /* tx vlan0 tag(C-VLAN) */
- u64 vlan0;
- /* tx vlan1 tag(S-VLAN) */
- u64 vlan1;
- /* insert tx vlan tag */
- u8 insert_vlan :1;
- /* insert tx double vlan tag */
- u8 double_vlan :1;
+ u64 vtag0;
+ u64 vtag1;
+
+ /* cfg_vtag0 & cfg_vtag1 fields are valid
+ * when free_vtag0 & free_vtag1 are '0's.
+ */
+ /* cfg_vtag0 = 1 to configure vtag0 */
+ u8 cfg_vtag0 :1;
+ /* cfg_vtag1 = 1 to configure vtag1 */
+ u8 cfg_vtag1 :1;
+
+ /* vtag0_idx & vtag1_idx are only valid when
+ * both cfg_vtag0 & cfg_vtag1 are '0's,
+ * these fields are used along with free_vtag0
+ * & free_vtag1 to free the nix lf's tx_vlan
+ * configuration.
+ *
+ * Denotes the indices of tx_vtag def registers
+ * that needs to be cleared and freed.
+ */
+ int vtag0_idx;
+ int vtag1_idx;
+
+ /* free_vtag0 & free_vtag1 fields are valid
+ * when cfg_vtag0 & cfg_vtag1 are '0's.
+ */
+ /* free_vtag0 = 1 clears vtag0 configuration
+ * vtag0_idx denotes the index to be cleared.
+ */
+ u8 free_vtag0 :1;
+ /* free_vtag1 = 1 clears vtag1 configuration
+ * vtag1_idx denotes the index to be cleared.
+ */
+ u8 free_vtag1 :1;
} tx;
/* valid when cfg_type is '1' */
};
};
+struct nix_vtag_config_rsp {
+ struct mbox_msghdr hdr;
+ int vtag0_idx;
+ int vtag1_idx;
+ /* Indices of tx_vtag def registers used to configure
+ * tx vtag0 & vtag1 headers, these indices are valid
+ * when nix_vtag_config mbox requested for vtag0 and/
+ * or vtag1 configuration.
+ */
+};
+
struct nix_rss_flowkey_cfg {
struct mbox_msghdr hdr;
int mcam_index; /* MCAM entry index to modify */
#define NIX_FLOW_KEY_TYPE_INNR_SCTP BIT(16)
#define NIX_FLOW_KEY_TYPE_INNR_ETH_DMAC BIT(17)
#define NIX_FLOW_KEY_TYPE_VLAN BIT(20)
+#define NIX_FLOW_KEY_TYPE_IPV4_PROTO BIT(21)
u32 flowkey_cfg; /* Flowkey types selected */
u8 group; /* RSS context or group */
};
u8 mkex_pfl_name[MKEX_NAME_LEN];
};
+struct flow_msg {
+ unsigned char dmac[6];
+ unsigned char smac[6];
+ __be16 etype;
+ __be16 vlan_etype;
+ __be16 vlan_tci;
+ union {
+ __be32 ip4src;
+ __be32 ip6src[4];
+ };
+ union {
+ __be32 ip4dst;
+ __be32 ip6dst[4];
+ };
+ u8 tos;
+ u8 ip_ver;
+ u8 ip_proto;
+ u8 tc;
+ __be16 sport;
+ __be16 dport;
+};
+
+struct npc_install_flow_req {
+ struct mbox_msghdr hdr;
+ struct flow_msg packet;
+ struct flow_msg mask;
+ u64 features;
+ u16 entry;
+ u16 channel;
+ u8 intf;
+ u8 set_cntr; /* If counter is available set counter for this entry ? */
+ u8 default_rule;
+ u8 append; /* overwrite(0) or append(1) flow to default rule? */
+ u16 vf;
+ /* action */
+ u32 index;
+ u16 match_id;
+ u8 flow_key_alg;
+ u8 op;
+ /* vtag rx action */
+ u8 vtag0_type;
+ u8 vtag0_valid;
+ u8 vtag1_type;
+ u8 vtag1_valid;
+ /* vtag tx action */
+ u16 vtag0_def;
+ u8 vtag0_op;
+ u16 vtag1_def;
+ u8 vtag1_op;
+};
+
+struct npc_install_flow_rsp {
+ struct mbox_msghdr hdr;
+ int counter; /* negative if no counter else counter number */
+};
+
+struct npc_delete_flow_req {
+ struct mbox_msghdr hdr;
+ u16 entry;
+ u16 start;/*Disable range of entries */
+ u16 end;
+ u8 all; /* PF + VFs */
+};
+
+struct npc_mcam_read_entry_req {
+ struct mbox_msghdr hdr;
+ u16 entry; /* MCAM entry to read */
+};
+
+struct npc_mcam_read_entry_rsp {
+ struct mbox_msghdr hdr;
+ struct mcam_entry entry_data;
+ u8 intf;
+ u8 enable;
+};
+
+struct npc_mcam_read_base_rule_rsp {
+ struct mbox_msghdr hdr;
+ struct mcam_entry entry;
+};
+
enum ptp_op {
PTP_OP_ADJFINE = 0,
PTP_OP_GET_CLOCK = 1,
u64 clk;
};
+/* CPT mailbox error codes
+ * Range 901 - 1000.
+ */
+enum cpt_af_status {
+ CPT_AF_ERR_PARAM = -901,
+ CPT_AF_ERR_GRP_INVALID = -902,
+ CPT_AF_ERR_LF_INVALID = -903,
+ CPT_AF_ERR_ACCESS_DENIED = -904,
+ CPT_AF_ERR_SSO_PF_FUNC_INVALID = -905,
+ CPT_AF_ERR_NIX_PF_FUNC_INVALID = -906
+};
+
+/* CPT mbox message formats */
+struct cpt_rd_wr_reg_msg {
+ struct mbox_msghdr hdr;
+ u64 reg_offset;
+ u64 *ret_val;
+ u64 val;
+ u8 is_write;
+};
+
+struct cpt_lf_alloc_req_msg {
+ struct mbox_msghdr hdr;
+ u16 nix_pf_func;
+ u16 sso_pf_func;
+ u16 eng_grpmsk;
+};
+
#endif /* MBOX_H */
NPC_LT_LH_CUSTOM1 = 0xF,
};
+/* NPC port kind defines how the incoming or outgoing packets
+ * are processed. NPC accepts packets from up to 64 pkinds.
+ * Software assigns pkind for each incoming port such as CGX
+ * Ethernet interfaces, LBK interfaces, etc.
+ */
+enum npc_pkind_type {
+ NPC_TX_DEF_PKIND = 63ULL, /* NIX-TX PKIND */
+};
+
+/* list of known and supported fields in packet header and
+ * fields present in key structure.
+ */
+enum key_fields {
+ NPC_DMAC,
+ NPC_SMAC,
+ NPC_ETYPE,
+ NPC_OUTER_VID,
+ NPC_TOS,
+ NPC_SIP_IPV4,
+ NPC_DIP_IPV4,
+ NPC_SIP_IPV6,
+ NPC_DIP_IPV6,
+ NPC_SPORT_TCP,
+ NPC_DPORT_TCP,
+ NPC_SPORT_UDP,
+ NPC_DPORT_UDP,
+ NPC_SPORT_SCTP,
+ NPC_DPORT_SCTP,
+ NPC_HEADER_FIELDS_MAX,
+ NPC_CHAN = NPC_HEADER_FIELDS_MAX, /* Valid when Rx */
+ NPC_PF_FUNC, /* Valid when Tx */
+ NPC_ERRLEV,
+ NPC_ERRCODE,
+ NPC_LXMB,
+ NPC_LA,
+ NPC_LB,
+ NPC_LC,
+ NPC_LD,
+ NPC_LE,
+ NPC_LF,
+ NPC_LG,
+ NPC_LH,
+ /* Ethertype for untagged frame */
+ NPC_ETYPE_ETHER,
+ /* Ethertype for single tagged frame */
+ NPC_ETYPE_TAG1,
+ /* Ethertype for double tagged frame */
+ NPC_ETYPE_TAG2,
+ /* outer vlan tci for single tagged frame */
+ NPC_VLAN_TAG1,
+ /* outer vlan tci for double tagged frame */
+ NPC_VLAN_TAG2,
+ /* other header fields programmed to extract but not of our interest */
+ NPC_UNKNOWN,
+ NPC_KEY_FIELDS_MAX,
+};
+
struct npc_kpu_profile_cam {
u8 state;
u8 state_mask;
/* NPC_AF_INTFX_KEX_CFG field masks */
#define NPC_PARSE_NIBBLE GENMASK_ULL(30, 0)
+/* NPC_PARSE_KEX_S nibble definitions for each field */
+#define NPC_PARSE_NIBBLE_CHAN GENMASK_ULL(2, 0)
+#define NPC_PARSE_NIBBLE_ERRLEV BIT_ULL(3)
+#define NPC_PARSE_NIBBLE_ERRCODE GENMASK_ULL(5, 4)
+#define NPC_PARSE_NIBBLE_L2L3_BCAST BIT_ULL(6)
+#define NPC_PARSE_NIBBLE_LA_FLAGS GENMASK_ULL(8, 7)
+#define NPC_PARSE_NIBBLE_LA_LTYPE BIT_ULL(9)
+#define NPC_PARSE_NIBBLE_LB_FLAGS GENMASK_ULL(11, 10)
+#define NPC_PARSE_NIBBLE_LB_LTYPE BIT_ULL(12)
+#define NPC_PARSE_NIBBLE_LC_FLAGS GENMASK_ULL(14, 13)
+#define NPC_PARSE_NIBBLE_LC_LTYPE BIT_ULL(15)
+#define NPC_PARSE_NIBBLE_LD_FLAGS GENMASK_ULL(17, 16)
+#define NPC_PARSE_NIBBLE_LD_LTYPE BIT_ULL(18)
+#define NPC_PARSE_NIBBLE_LE_FLAGS GENMASK_ULL(20, 19)
+#define NPC_PARSE_NIBBLE_LE_LTYPE BIT_ULL(21)
+#define NPC_PARSE_NIBBLE_LF_FLAGS GENMASK_ULL(23, 22)
+#define NPC_PARSE_NIBBLE_LF_LTYPE BIT_ULL(24)
+#define NPC_PARSE_NIBBLE_LG_FLAGS GENMASK_ULL(26, 25)
+#define NPC_PARSE_NIBBLE_LG_LTYPE BIT_ULL(27)
+#define NPC_PARSE_NIBBLE_LH_FLAGS GENMASK_ULL(29, 28)
+#define NPC_PARSE_NIBBLE_LH_LTYPE BIT_ULL(30)
+
+struct nix_tx_action {
+#if defined(__BIG_ENDIAN_BITFIELD)
+ u64 rsvd_63_48 :16;
+ u64 match_id :16;
+ u64 index :20;
+ u64 rsvd_11_8 :8;
+ u64 op :4;
+#else
+ u64 op :4;
+ u64 rsvd_11_8 :8;
+ u64 index :20;
+ u64 match_id :16;
+ u64 rsvd_63_48 :16;
+#endif
+};
+
/* NIX Receive Vtag Action Structure */
-#define VTAG0_VALID_BIT BIT_ULL(15)
-#define VTAG0_TYPE_MASK GENMASK_ULL(14, 12)
-#define VTAG0_LID_MASK GENMASK_ULL(10, 8)
-#define VTAG0_RELPTR_MASK GENMASK_ULL(7, 0)
+#define RX_VTAG0_VALID_BIT BIT_ULL(15)
+#define RX_VTAG0_TYPE_MASK GENMASK_ULL(14, 12)
+#define RX_VTAG0_LID_MASK GENMASK_ULL(10, 8)
+#define RX_VTAG0_RELPTR_MASK GENMASK_ULL(7, 0)
+#define RX_VTAG1_VALID_BIT BIT_ULL(47)
+#define RX_VTAG1_TYPE_MASK GENMASK_ULL(46, 44)
+#define RX_VTAG1_LID_MASK GENMASK_ULL(42, 40)
+#define RX_VTAG1_RELPTR_MASK GENMASK_ULL(39, 32)
+
+/* NIX Transmit Vtag Action Structure */
+#define TX_VTAG0_DEF_MASK GENMASK_ULL(25, 16)
+#define TX_VTAG0_OP_MASK GENMASK_ULL(13, 12)
+#define TX_VTAG0_LID_MASK GENMASK_ULL(10, 8)
+#define TX_VTAG0_RELPTR_MASK GENMASK_ULL(7, 0)
+#define TX_VTAG1_DEF_MASK GENMASK_ULL(57, 48)
+#define TX_VTAG1_OP_MASK GENMASK_ULL(45, 44)
+#define TX_VTAG1_LID_MASK GENMASK_ULL(42, 40)
+#define TX_VTAG1_RELPTR_MASK GENMASK_ULL(39, 32)
struct npc_mcam_kex {
/* MKEX Profle Header */
struct npc_lt_def pck_iip4;
};
+struct rvu_npc_mcam_rule {
+ struct flow_msg packet;
+ struct flow_msg mask;
+ u8 intf;
+ union {
+ struct nix_tx_action tx_action;
+ struct nix_rx_action rx_action;
+ };
+ u64 vtag_action;
+ struct list_head list;
+ u64 features;
+ u16 owner;
+ u16 entry;
+ u16 cntr;
+ bool has_cntr;
+ u8 default_rule;
+ bool enable;
+ bool vfvlan_cfg;
+};
+
#endif /* NPC_H */
(((bytesm1) << 16) | ((hdr_ofs) << 8) | ((ena) << 7) | \
((flags_ena) << 6) | ((key_ofs) & 0x3F))
+/* Rx parse key extract nibble enable */
+#define NPC_PARSE_NIBBLE_INTF_RX (NPC_PARSE_NIBBLE_CHAN | \
+ NPC_PARSE_NIBBLE_LA_LTYPE | \
+ NPC_PARSE_NIBBLE_LB_LTYPE | \
+ NPC_PARSE_NIBBLE_LC_LTYPE | \
+ NPC_PARSE_NIBBLE_LD_LTYPE | \
+ NPC_PARSE_NIBBLE_LE_LTYPE)
+/* Tx parse key extract nibble enable */
+#define NPC_PARSE_NIBBLE_INTF_TX (NPC_PARSE_NIBBLE_LA_LTYPE | \
+ NPC_PARSE_NIBBLE_LB_LTYPE | \
+ NPC_PARSE_NIBBLE_LC_LTYPE | \
+ NPC_PARSE_NIBBLE_LD_LTYPE | \
+ NPC_PARSE_NIBBLE_LE_LTYPE)
+
enum npc_kpu_parser_state {
NPC_S_NA = 0,
NPC_S_KPU1_ETHER,
},
};
-static const struct npc_mcam_kex npc_mkex_default = {
+static struct npc_mcam_kex npc_mkex_default = {
.mkex_sign = MKEX_SIGN,
.name = "default",
.kpu_version = NPC_KPU_PROFILE_VER,
.keyx_cfg = {
- /* nibble: LA..LE (ltype only) + Channel */
- [NIX_INTF_RX] = ((u64)NPC_MCAM_KEY_X2 << 32) | 0x49247,
- [NIX_INTF_TX] = ((u64)NPC_MCAM_KEY_X2 << 32) | ((1ULL << 19) - 1),
+ /* nibble: LA..LE (ltype only) + channel */
+ [NIX_INTF_RX] = ((u64)NPC_MCAM_KEY_X2 << 32) | NPC_PARSE_NIBBLE_INTF_RX,
+ /* nibble: LA..LE (ltype only) */
+ [NIX_INTF_TX] = ((u64)NPC_MCAM_KEY_X2 << 32) | NPC_PARSE_NIBBLE_INTF_TX,
},
.intf_lid_lt_ld = {
/* Default RX MCAM KEX profile */
/* Layer B: Single VLAN (CTAG) */
/* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */
[NPC_LT_LB_CTAG] = {
- KEX_LD_CFG(0x03, 0x0, 0x1, 0x0, 0x4),
+ KEX_LD_CFG(0x03, 0x2, 0x1, 0x0, 0x4),
},
/* Layer B: Stacked VLAN (STAG|QinQ) */
[NPC_LT_LB_STAG_QINQ] = {
- /* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */
- KEX_LD_CFG(0x03, 0x4, 0x1, 0x0, 0x4),
+ /* Outer VLAN: 2 bytes, KW0[63:48] */
+ KEX_LD_CFG(0x01, 0x2, 0x1, 0x0, 0x6),
+ /* Ethertype: 2 bytes, KW0[47:32] */
+ KEX_LD_CFG(0x01, 0x8, 0x1, 0x0, 0x4),
},
[NPC_LT_LB_FDSA] = {
/* SWITCH PORT: 1 byte, KW0[63:48] */
[NPC_LID_LD] = {
/* Layer D:UDP */
[NPC_LT_LD_UDP] = {
- /* SPORT: 2 bytes, KW3[15:0] */
- KEX_LD_CFG(0x1, 0x0, 0x1, 0x0, 0x18),
- /* DPORT: 2 bytes, KW3[31:16] */
- KEX_LD_CFG(0x1, 0x2, 0x1, 0x0, 0x1a),
+ /* SPORT+DPORT: 4 bytes, KW3[31:0] */
+ KEX_LD_CFG(0x3, 0x0, 0x1, 0x0, 0x18),
+ },
+ /* Layer D:TCP */
+ [NPC_LT_LD_TCP] = {
+ /* SPORT+DPORT: 4 bytes, KW3[31:0] */
+ KEX_LD_CFG(0x3, 0x0, 0x1, 0x0, 0x18),
+ },
+ },
+ },
+
+ /* Default TX MCAM KEX profile */
+ [NIX_INTF_TX] = {
+ [NPC_LID_LA] = {
+ /* Layer A: NIX_INST_HDR_S + Ethernet */
+ /* NIX appends 8 bytes of NIX_INST_HDR_S at the
+ * start of each TX packet supplied to NPC.
+ */
+ [NPC_LT_LA_IH_NIX_ETHER] = {
+ /* PF_FUNC: 2B , KW0 [47:32] */
+ KEX_LD_CFG(0x01, 0x0, 0x1, 0x0, 0x4),
+ /* DMAC: 6 bytes, KW1[63:16] */
+ KEX_LD_CFG(0x05, 0x8, 0x1, 0x0, 0xa),
+ },
+ },
+ [NPC_LID_LB] = {
+ /* Layer B: Single VLAN (CTAG) */
+ [NPC_LT_LB_CTAG] = {
+ /* CTAG VLAN[2..3] KW0[63:48] */
+ KEX_LD_CFG(0x01, 0x2, 0x1, 0x0, 0x6),
+ /* CTAG VLAN[2..3] KW1[15:0] */
+ KEX_LD_CFG(0x01, 0x4, 0x1, 0x0, 0x8),
+ },
+ /* Layer B: Stacked VLAN (STAG|QinQ) */
+ [NPC_LT_LB_STAG_QINQ] = {
+ /* Outer VLAN: 2 bytes, KW0[63:48] */
+ KEX_LD_CFG(0x01, 0x2, 0x1, 0x0, 0x6),
+ /* Outer VLAN: 2 Bytes, KW1[15:0] */
+ KEX_LD_CFG(0x01, 0x8, 0x1, 0x0, 0x8),
+ },
+ },
+ [NPC_LID_LC] = {
+ /* Layer C: IPv4 */
+ [NPC_LT_LC_IP] = {
+ /* SIP+DIP: 8 bytes, KW2[63:0] */
+ KEX_LD_CFG(0x07, 0xc, 0x1, 0x0, 0x10),
+ /* TOS: 1 byte, KW1[63:56] */
+ KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0xf),
+ },
+ /* Layer C: IPv6 */
+ [NPC_LT_LC_IP6] = {
+ /* Everything up to SADDR: 8 bytes, KW2[63:0] */
+ KEX_LD_CFG(0x07, 0x0, 0x1, 0x0, 0x10),
+ },
+ },
+ [NPC_LID_LD] = {
+ /* Layer D:UDP */
+ [NPC_LT_LD_UDP] = {
+ /* SPORT+DPORT: 4 bytes, KW3[31:0] */
+ KEX_LD_CFG(0x3, 0x0, 0x1, 0x0, 0x18),
},
/* Layer D:TCP */
[NPC_LT_LD_TCP] = {
- /* SPORT: 2 bytes, KW3[15:0] */
- KEX_LD_CFG(0x1, 0x0, 0x1, 0x0, 0x18),
- /* DPORT: 2 bytes, KW3[31:16] */
- KEX_LD_CFG(0x1, 0x2, 0x1, 0x0, 0x1a),
+ /* SPORT+DPORT: 4 bytes, KW3[31:0] */
+ KEX_LD_CFG(0x3, 0x0, 0x1, 0x0, 0x18),
},
},
},
hw->cap.nix_shaping = true;
hw->cap.nix_tx_link_bp = true;
hw->cap.nix_rx_multicast = true;
+ hw->rvu = rvu;
if (is_rvu_96xx_B0(rvu)) {
hw->cap.nix_fixed_txschq_mapping = true;
* multiple blocks of same type.
*
* @pcifunc has to be zero when no LF is yet attached.
+ *
+ * For a pcifunc if LFs are attached from multiple blocks of same type, then
+ * return blkaddr of first encountered block.
*/
int rvu_get_blkaddr(struct rvu *rvu, int blktype, u16 pcifunc)
{
devnum = rvu_get_pf(pcifunc);
}
- /* Check if the 'pcifunc' has a NIX LF from 'BLKADDR_NIX0' */
+ /* Check if the 'pcifunc' has a NIX LF from 'BLKADDR_NIX0' or
+ * 'BLKADDR_NIX1'.
+ */
if (blktype == BLKTYPE_NIX) {
- reg = is_pf ? RVU_PRIV_PFX_NIX0_CFG : RVU_PRIV_HWVFX_NIX0_CFG;
+ reg = is_pf ? RVU_PRIV_PFX_NIXX_CFG(0) :
+ RVU_PRIV_HWVFX_NIXX_CFG(0);
cfg = rvu_read64(rvu, BLKADDR_RVUM, reg | (devnum << 16));
- if (cfg)
+ if (cfg) {
blkaddr = BLKADDR_NIX0;
+ goto exit;
+ }
+
+ reg = is_pf ? RVU_PRIV_PFX_NIXX_CFG(1) :
+ RVU_PRIV_HWVFX_NIXX_CFG(1);
+ cfg = rvu_read64(rvu, BLKADDR_RVUM, reg | (devnum << 16));
+ if (cfg)
+ blkaddr = BLKADDR_NIX1;
}
- /* Check if the 'pcifunc' has a CPT LF from 'BLKADDR_CPT0' */
if (blktype == BLKTYPE_CPT) {
- reg = is_pf ? RVU_PRIV_PFX_CPT0_CFG : RVU_PRIV_HWVFX_CPT0_CFG;
+ reg = is_pf ? RVU_PRIV_PFX_CPTX_CFG(0) :
+ RVU_PRIV_HWVFX_CPTX_CFG(0);
cfg = rvu_read64(rvu, BLKADDR_RVUM, reg | (devnum << 16));
- if (cfg)
+ if (cfg) {
blkaddr = BLKADDR_CPT0;
+ goto exit;
+ }
+
+ reg = is_pf ? RVU_PRIV_PFX_CPTX_CFG(1) :
+ RVU_PRIV_HWVFX_CPTX_CFG(1);
+ cfg = rvu_read64(rvu, BLKADDR_RVUM, reg | (devnum << 16));
+ if (cfg)
+ blkaddr = BLKADDR_CPT1;
}
exit:
block->fn_map[lf] = attach ? pcifunc : 0;
- switch (block->type) {
- case BLKTYPE_NPA:
+ switch (block->addr) {
+ case BLKADDR_NPA:
pfvf->npalf = attach ? true : false;
num_lfs = pfvf->npalf;
break;
- case BLKTYPE_NIX:
+ case BLKADDR_NIX0:
+ case BLKADDR_NIX1:
pfvf->nixlf = attach ? true : false;
num_lfs = pfvf->nixlf;
break;
- case BLKTYPE_SSO:
+ case BLKADDR_SSO:
attach ? pfvf->sso++ : pfvf->sso--;
num_lfs = pfvf->sso;
break;
- case BLKTYPE_SSOW:
+ case BLKADDR_SSOW:
attach ? pfvf->ssow++ : pfvf->ssow--;
num_lfs = pfvf->ssow;
break;
- case BLKTYPE_TIM:
+ case BLKADDR_TIM:
attach ? pfvf->timlfs++ : pfvf->timlfs--;
num_lfs = pfvf->timlfs;
break;
- case BLKTYPE_CPT:
+ case BLKADDR_CPT0:
attach ? pfvf->cptlfs++ : pfvf->cptlfs--;
num_lfs = pfvf->cptlfs;
break;
+ case BLKADDR_CPT1:
+ attach ? pfvf->cpt1_lfs++ : pfvf->cpt1_lfs--;
+ num_lfs = pfvf->cpt1_lfs;
+ break;
}
reg = is_pf ? block->pf_lfcnt_reg : block->vf_lfcnt_reg;
/* Do a HW reset of all RVU blocks */
rvu_block_reset(rvu, BLKADDR_NPA, NPA_AF_BLK_RST);
rvu_block_reset(rvu, BLKADDR_NIX0, NIX_AF_BLK_RST);
+ rvu_block_reset(rvu, BLKADDR_NIX1, NIX_AF_BLK_RST);
rvu_block_reset(rvu, BLKADDR_NPC, NPC_AF_BLK_RST);
rvu_block_reset(rvu, BLKADDR_SSO, SSO_AF_BLK_RST);
rvu_block_reset(rvu, BLKADDR_TIM, TIM_AF_BLK_RST);
rvu_block_reset(rvu, BLKADDR_CPT0, CPT_AF_BLK_RST);
+ rvu_block_reset(rvu, BLKADDR_CPT1, CPT_AF_BLK_RST);
rvu_block_reset(rvu, BLKADDR_NDC_NIX0_RX, NDC_AF_BLK_RST);
rvu_block_reset(rvu, BLKADDR_NDC_NIX0_TX, NDC_AF_BLK_RST);
+ rvu_block_reset(rvu, BLKADDR_NDC_NIX1_RX, NDC_AF_BLK_RST);
+ rvu_block_reset(rvu, BLKADDR_NDC_NIX1_TX, NDC_AF_BLK_RST);
rvu_block_reset(rvu, BLKADDR_NDC_NPA0, NDC_AF_BLK_RST);
}
u64 *mac;
for (pf = 0; pf < hw->total_pfs; pf++) {
+ /* For PF0(AF), Assign MAC address to only VFs (LBKVFs) */
+ if (!pf)
+ goto lbkvf;
+
if (!is_pf_cgxmapped(rvu, pf))
continue;
/* Assign MAC address to PF */
} else {
eth_random_addr(pfvf->mac_addr);
}
+ ether_addr_copy(pfvf->default_mac, pfvf->mac_addr);
- /* Assign MAC address to VFs */
+lbkvf:
+ /* Assign MAC address to VFs*/
rvu_get_pf_numvfs(rvu, pf, &numvfs, &hwvf);
for (vf = 0; vf < numvfs; vf++, hwvf++) {
pfvf = &rvu->hwvf[hwvf];
} else {
eth_random_addr(pfvf->mac_addr);
}
+ ether_addr_copy(pfvf->default_mac, pfvf->mac_addr);
}
}
}
iounmap(rvu->fwdata);
}
+static int rvu_setup_nix_hw_resource(struct rvu *rvu, int blkaddr)
+{
+ struct rvu_hwinfo *hw = rvu->hw;
+ struct rvu_block *block;
+ int blkid;
+ u64 cfg;
+
+ /* Init NIX LF's bitmap */
+ block = &hw->block[blkaddr];
+ if (!block->implemented)
+ return 0;
+ blkid = (blkaddr == BLKADDR_NIX0) ? 0 : 1;
+ cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST2);
+ block->lf.max = cfg & 0xFFF;
+ block->addr = blkaddr;
+ block->type = BLKTYPE_NIX;
+ block->lfshift = 8;
+ block->lookup_reg = NIX_AF_RVU_LF_CFG_DEBUG;
+ block->pf_lfcnt_reg = RVU_PRIV_PFX_NIXX_CFG(blkid);
+ block->vf_lfcnt_reg = RVU_PRIV_HWVFX_NIXX_CFG(blkid);
+ block->lfcfg_reg = NIX_PRIV_LFX_CFG;
+ block->msixcfg_reg = NIX_PRIV_LFX_INT_CFG;
+ block->lfreset_reg = NIX_AF_LF_RST;
+ sprintf(block->name, "NIX%d", blkid);
+ rvu->nix_blkaddr[blkid] = blkaddr;
+ return rvu_alloc_bitmap(&block->lf);
+}
+
+static int rvu_setup_cpt_hw_resource(struct rvu *rvu, int blkaddr)
+{
+ struct rvu_hwinfo *hw = rvu->hw;
+ struct rvu_block *block;
+ int blkid;
+ u64 cfg;
+
+ /* Init CPT LF's bitmap */
+ block = &hw->block[blkaddr];
+ if (!block->implemented)
+ return 0;
+ blkid = (blkaddr == BLKADDR_CPT0) ? 0 : 1;
+ cfg = rvu_read64(rvu, blkaddr, CPT_AF_CONSTANTS0);
+ block->lf.max = cfg & 0xFF;
+ block->addr = blkaddr;
+ block->type = BLKTYPE_CPT;
+ block->multislot = true;
+ block->lfshift = 3;
+ block->lookup_reg = CPT_AF_RVU_LF_CFG_DEBUG;
+ block->pf_lfcnt_reg = RVU_PRIV_PFX_CPTX_CFG(blkid);
+ block->vf_lfcnt_reg = RVU_PRIV_HWVFX_CPTX_CFG(blkid);
+ block->lfcfg_reg = CPT_PRIV_LFX_CFG;
+ block->msixcfg_reg = CPT_PRIV_LFX_INT_CFG;
+ block->lfreset_reg = CPT_AF_LF_RST;
+ sprintf(block->name, "CPT%d", blkid);
+ return rvu_alloc_bitmap(&block->lf);
+}
+
static int rvu_setup_hw_resources(struct rvu *rvu)
{
struct rvu_hwinfo *hw = rvu->hw;
return err;
nix:
- /* Init NIX LF's bitmap */
- block = &hw->block[BLKADDR_NIX0];
- if (!block->implemented)
- goto sso;
- cfg = rvu_read64(rvu, BLKADDR_NIX0, NIX_AF_CONST2);
- block->lf.max = cfg & 0xFFF;
- block->addr = BLKADDR_NIX0;
- block->type = BLKTYPE_NIX;
- block->lfshift = 8;
- block->lookup_reg = NIX_AF_RVU_LF_CFG_DEBUG;
- block->pf_lfcnt_reg = RVU_PRIV_PFX_NIX0_CFG;
- block->vf_lfcnt_reg = RVU_PRIV_HWVFX_NIX0_CFG;
- block->lfcfg_reg = NIX_PRIV_LFX_CFG;
- block->msixcfg_reg = NIX_PRIV_LFX_INT_CFG;
- block->lfreset_reg = NIX_AF_LF_RST;
- sprintf(block->name, "NIX");
- err = rvu_alloc_bitmap(&block->lf);
+ err = rvu_setup_nix_hw_resource(rvu, BLKADDR_NIX0);
+ if (err)
+ return err;
+ err = rvu_setup_nix_hw_resource(rvu, BLKADDR_NIX1);
if (err)
return err;
-sso:
/* Init SSO group's bitmap */
block = &hw->block[BLKADDR_SSO];
if (!block->implemented)
return err;
cpt:
- /* Init CPT LF's bitmap */
- block = &hw->block[BLKADDR_CPT0];
- if (!block->implemented)
- goto init;
- cfg = rvu_read64(rvu, BLKADDR_CPT0, CPT_AF_CONSTANTS0);
- block->lf.max = cfg & 0xFF;
- block->addr = BLKADDR_CPT0;
- block->type = BLKTYPE_CPT;
- block->multislot = true;
- block->lfshift = 3;
- block->lookup_reg = CPT_AF_RVU_LF_CFG_DEBUG;
- block->pf_lfcnt_reg = RVU_PRIV_PFX_CPT0_CFG;
- block->vf_lfcnt_reg = RVU_PRIV_HWVFX_CPT0_CFG;
- block->lfcfg_reg = CPT_PRIV_LFX_CFG;
- block->msixcfg_reg = CPT_PRIV_LFX_INT_CFG;
- block->lfreset_reg = CPT_AF_LF_RST;
- sprintf(block->name, "CPT");
- err = rvu_alloc_bitmap(&block->lf);
+ err = rvu_setup_cpt_hw_resource(rvu, BLKADDR_CPT0);
+ if (err)
+ return err;
+ err = rvu_setup_cpt_hw_resource(rvu, BLKADDR_CPT1);
if (err)
return err;
-init:
/* Allocate memory for PFVF data */
rvu->pf = devm_kcalloc(rvu->dev, hw->total_pfs,
sizeof(struct rvu_pfvf), GFP_KERNEL);
/* Get current count of a RVU block's LF/slots
* provisioned to a given RVU func.
*/
-static u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blktype)
+u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blkaddr)
+{
+ switch (blkaddr) {
+ case BLKADDR_NPA:
+ return pfvf->npalf ? 1 : 0;
+ case BLKADDR_NIX0:
+ case BLKADDR_NIX1:
+ return pfvf->nixlf ? 1 : 0;
+ case BLKADDR_SSO:
+ return pfvf->sso;
+ case BLKADDR_SSOW:
+ return pfvf->ssow;
+ case BLKADDR_TIM:
+ return pfvf->timlfs;
+ case BLKADDR_CPT0:
+ return pfvf->cptlfs;
+ case BLKADDR_CPT1:
+ return pfvf->cpt1_lfs;
+ }
+ return 0;
+}
+
+/* Return true if LFs of block type are attached to pcifunc */
+static bool is_blktype_attached(struct rvu_pfvf *pfvf, int blktype)
{
switch (blktype) {
case BLKTYPE_NPA:
case BLKTYPE_NIX:
return pfvf->nixlf ? 1 : 0;
case BLKTYPE_SSO:
- return pfvf->sso;
+ return !!pfvf->sso;
case BLKTYPE_SSOW:
- return pfvf->ssow;
+ return !!pfvf->ssow;
case BLKTYPE_TIM:
- return pfvf->timlfs;
+ return !!pfvf->timlfs;
case BLKTYPE_CPT:
- return pfvf->cptlfs;
+ return pfvf->cptlfs || pfvf->cpt1_lfs;
}
- return 0;
+
+ return false;
}
bool is_pffunc_map_valid(struct rvu *rvu, u16 pcifunc, int blktype)
pfvf = rvu_get_pfvf(rvu, pcifunc);
/* Check if this PFFUNC has a LF of type blktype attached */
- if (!rvu_get_rsrc_mapcount(pfvf, blktype))
+ if (!is_blktype_attached(pfvf, blktype))
return false;
return true;
if (blkaddr < 0)
return;
+ if (blktype == BLKTYPE_NIX)
+ rvu_nix_reset_mac(pfvf, pcifunc);
+
block = &hw->block[blkaddr];
- num_lfs = rvu_get_rsrc_mapcount(pfvf, block->type);
+ num_lfs = rvu_get_rsrc_mapcount(pfvf, block->addr);
if (!num_lfs)
return;
continue;
else if ((blkid == BLKADDR_NIX0) && !detach->nixlf)
continue;
+ else if ((blkid == BLKADDR_NIX1) && !detach->nixlf)
+ continue;
else if ((blkid == BLKADDR_SSO) && !detach->sso)
continue;
else if ((blkid == BLKADDR_SSOW) && !detach->ssow)
continue;
else if ((blkid == BLKADDR_CPT0) && !detach->cptlfs)
continue;
+ else if ((blkid == BLKADDR_CPT1) && !detach->cptlfs)
+ continue;
}
rvu_detach_block(rvu, pcifunc, block->type);
}
return rvu_detach_rsrcs(rvu, detach, detach->hdr.pcifunc);
}
-static void rvu_attach_block(struct rvu *rvu, int pcifunc,
- int blktype, int num_lfs)
+static int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
+{
+ struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+ int blkaddr = BLKADDR_NIX0, vf;
+ struct rvu_pfvf *pf;
+
+ /* All CGX mapped PFs are set with assigned NIX block during init */
+ if (is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) {
+ pf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK);
+ blkaddr = pf->nix_blkaddr;
+ } else if (is_afvf(pcifunc)) {
+ vf = pcifunc - 1;
+ /* Assign NIX based on VF number. All even numbered VFs get
+ * NIX0 and odd numbered gets NIX1
+ */
+ blkaddr = (vf & 1) ? BLKADDR_NIX1 : BLKADDR_NIX0;
+ /* NIX1 is not present on all silicons */
+ if (!is_block_implemented(rvu->hw, BLKADDR_NIX1))
+ blkaddr = BLKADDR_NIX0;
+ }
+
+ switch (blkaddr) {
+ case BLKADDR_NIX1:
+ pfvf->nix_blkaddr = BLKADDR_NIX1;
+ pfvf->nix_rx_intf = NIX_INTFX_RX(1);
+ pfvf->nix_tx_intf = NIX_INTFX_TX(1);
+ break;
+ case BLKADDR_NIX0:
+ default:
+ pfvf->nix_blkaddr = BLKADDR_NIX0;
+ pfvf->nix_rx_intf = NIX_INTFX_RX(0);
+ pfvf->nix_tx_intf = NIX_INTFX_TX(0);
+ break;
+ }
+
+ return pfvf->nix_blkaddr;
+}
+
+static int rvu_get_attach_blkaddr(struct rvu *rvu, int blktype,
+ u16 pcifunc, struct rsrc_attach *attach)
+{
+ int blkaddr;
+
+ switch (blktype) {
+ case BLKTYPE_NIX:
+ blkaddr = rvu_get_nix_blkaddr(rvu, pcifunc);
+ break;
+ case BLKTYPE_CPT:
+ if (attach->hdr.ver < RVU_MULTI_BLK_VER)
+ return rvu_get_blkaddr(rvu, blktype, 0);
+ blkaddr = attach->cpt_blkaddr ? attach->cpt_blkaddr :
+ BLKADDR_CPT0;
+ if (blkaddr != BLKADDR_CPT0 && blkaddr != BLKADDR_CPT1)
+ return -ENODEV;
+ break;
+ default:
+ return rvu_get_blkaddr(rvu, blktype, 0);
+ };
+
+ if (is_block_implemented(rvu->hw, blkaddr))
+ return blkaddr;
+
+ return -ENODEV;
+}
+
+static void rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype,
+ int num_lfs, struct rsrc_attach *attach)
{
struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
struct rvu_hwinfo *hw = rvu->hw;
if (!num_lfs)
return;
- blkaddr = rvu_get_blkaddr(rvu, blktype, 0);
+ blkaddr = rvu_get_attach_blkaddr(rvu, blktype, pcifunc, attach);
if (blkaddr < 0)
return;
struct rsrc_attach *req, u16 pcifunc)
{
struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+ int free_lfs, mappedlfs, blkaddr;
struct rvu_hwinfo *hw = rvu->hw;
struct rvu_block *block;
- int free_lfs, mappedlfs;
/* Only one NPA LF can be attached */
- if (req->npalf && !rvu_get_rsrc_mapcount(pfvf, BLKTYPE_NPA)) {
+ if (req->npalf && !is_blktype_attached(pfvf, BLKTYPE_NPA)) {
block = &hw->block[BLKADDR_NPA];
free_lfs = rvu_rsrc_free_count(&block->lf);
if (!free_lfs)
}
/* Only one NIX LF can be attached */
- if (req->nixlf && !rvu_get_rsrc_mapcount(pfvf, BLKTYPE_NIX)) {
- block = &hw->block[BLKADDR_NIX0];
+ if (req->nixlf && !is_blktype_attached(pfvf, BLKTYPE_NIX)) {
+ blkaddr = rvu_get_attach_blkaddr(rvu, BLKTYPE_NIX,
+ pcifunc, req);
+ if (blkaddr < 0)
+ return blkaddr;
+ block = &hw->block[blkaddr];
free_lfs = rvu_rsrc_free_count(&block->lf);
if (!free_lfs)
goto fail;
pcifunc, req->sso, block->lf.max);
return -EINVAL;
}
- mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->type);
+ mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr);
free_lfs = rvu_rsrc_free_count(&block->lf);
/* Check if additional resources are available */
if (req->sso > mappedlfs &&
pcifunc, req->sso, block->lf.max);
return -EINVAL;
}
- mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->type);
+ mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr);
free_lfs = rvu_rsrc_free_count(&block->lf);
if (req->ssow > mappedlfs &&
((req->ssow - mappedlfs) > free_lfs))
pcifunc, req->timlfs, block->lf.max);
return -EINVAL;
}
- mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->type);
+ mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr);
free_lfs = rvu_rsrc_free_count(&block->lf);
if (req->timlfs > mappedlfs &&
((req->timlfs - mappedlfs) > free_lfs))
}
if (req->cptlfs) {
- block = &hw->block[BLKADDR_CPT0];
+ blkaddr = rvu_get_attach_blkaddr(rvu, BLKTYPE_CPT,
+ pcifunc, req);
+ if (blkaddr < 0)
+ return blkaddr;
+ block = &hw->block[blkaddr];
if (req->cptlfs > block->lf.max) {
dev_err(&rvu->pdev->dev,
"Func 0x%x: Invalid CPTLF req, %d > max %d\n",
pcifunc, req->cptlfs, block->lf.max);
return -EINVAL;
}
- mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->type);
+ mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr);
free_lfs = rvu_rsrc_free_count(&block->lf);
if (req->cptlfs > mappedlfs &&
((req->cptlfs - mappedlfs) > free_lfs))
return -ENOSPC;
}
+static bool rvu_attach_from_same_block(struct rvu *rvu, int blktype,
+ struct rsrc_attach *attach)
+{
+ int blkaddr, num_lfs;
+
+ blkaddr = rvu_get_attach_blkaddr(rvu, blktype,
+ attach->hdr.pcifunc, attach);
+ if (blkaddr < 0)
+ return false;
+
+ num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, attach->hdr.pcifunc),
+ blkaddr);
+ /* Requester already has LFs from given block ? */
+ return !!num_lfs;
+}
+
int rvu_mbox_handler_attach_resources(struct rvu *rvu,
struct rsrc_attach *attach,
struct msg_rsp *rsp)
/* Now attach the requested resources */
if (attach->npalf)
- rvu_attach_block(rvu, pcifunc, BLKTYPE_NPA, 1);
+ rvu_attach_block(rvu, pcifunc, BLKTYPE_NPA, 1, attach);
if (attach->nixlf)
- rvu_attach_block(rvu, pcifunc, BLKTYPE_NIX, 1);
+ rvu_attach_block(rvu, pcifunc, BLKTYPE_NIX, 1, attach);
if (attach->sso) {
/* RVU func doesn't know which exact LF or slot is attached
*/
if (attach->modify)
rvu_detach_block(rvu, pcifunc, BLKTYPE_SSO);
- rvu_attach_block(rvu, pcifunc, BLKTYPE_SSO, attach->sso);
+ rvu_attach_block(rvu, pcifunc, BLKTYPE_SSO,
+ attach->sso, attach);
}
if (attach->ssow) {
if (attach->modify)
rvu_detach_block(rvu, pcifunc, BLKTYPE_SSOW);
- rvu_attach_block(rvu, pcifunc, BLKTYPE_SSOW, attach->ssow);
+ rvu_attach_block(rvu, pcifunc, BLKTYPE_SSOW,
+ attach->ssow, attach);
}
if (attach->timlfs) {
if (attach->modify)
rvu_detach_block(rvu, pcifunc, BLKTYPE_TIM);
- rvu_attach_block(rvu, pcifunc, BLKTYPE_TIM, attach->timlfs);
+ rvu_attach_block(rvu, pcifunc, BLKTYPE_TIM,
+ attach->timlfs, attach);
}
if (attach->cptlfs) {
- if (attach->modify)
+ if (attach->modify &&
+ rvu_attach_from_same_block(rvu, BLKTYPE_CPT, attach))
rvu_detach_block(rvu, pcifunc, BLKTYPE_CPT);
- rvu_attach_block(rvu, pcifunc, BLKTYPE_CPT, attach->cptlfs);
+ rvu_attach_block(rvu, pcifunc, BLKTYPE_CPT,
+ attach->cptlfs, attach);
}
exit:
struct rvu_hwinfo *hw = rvu->hw;
u16 pcifunc = req->hdr.pcifunc;
struct rvu_pfvf *pfvf;
- int lf, slot;
+ int lf, slot, blkaddr;
pfvf = rvu_get_pfvf(rvu, pcifunc);
if (!pfvf->msix.bmap)
lf = rvu_get_lf(rvu, &hw->block[BLKADDR_NPA], pcifunc, 0);
rsp->npa_msixoff = rvu_get_msix_offset(rvu, pfvf, BLKADDR_NPA, lf);
- lf = rvu_get_lf(rvu, &hw->block[BLKADDR_NIX0], pcifunc, 0);
- rsp->nix_msixoff = rvu_get_msix_offset(rvu, pfvf, BLKADDR_NIX0, lf);
+ /* Get BLKADDR from which LFs are attached to pcifunc */
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+ if (blkaddr < 0) {
+ rsp->nix_msixoff = MSIX_VECTOR_INVALID;
+ } else {
+ lf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0);
+ rsp->nix_msixoff = rvu_get_msix_offset(rvu, pfvf, blkaddr, lf);
+ }
rsp->sso = pfvf->sso;
for (slot = 0; slot < rsp->sso; slot++) {
rsp->cptlf_msixoff[slot] =
rvu_get_msix_offset(rvu, pfvf, BLKADDR_CPT0, lf);
}
+
+ rsp->cpt1_lfs = pfvf->cpt1_lfs;
+ for (slot = 0; slot < rsp->cpt1_lfs; slot++) {
+ lf = rvu_get_lf(rvu, &hw->block[BLKADDR_CPT1], pcifunc, slot);
+ rsp->cpt1_lf_msixoff[slot] =
+ rvu_get_msix_offset(rvu, pfvf, BLKADDR_CPT1, lf);
+ }
+
return 0;
}
block = &rvu->hw->block[blkaddr];
num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, pcifunc),
- block->type);
+ block->addr);
if (!num_lfs)
return;
for (slot = 0; slot < num_lfs; slot++) {
continue;
/* Cleanup LF and reset it */
- if (block->addr == BLKADDR_NIX0)
+ if (block->addr == BLKADDR_NIX0 || block->addr == BLKADDR_NIX1)
rvu_nix_lf_teardown(rvu, pcifunc, block->addr, lf);
else if (block->addr == BLKADDR_NPA)
rvu_npa_lf_teardown(rvu, pcifunc, lf);
* 3. Cleanup pools (NPA)
*/
rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NIX0);
+ rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NIX1);
rvu_blklf_teardown(rvu, pcifunc, BLKADDR_CPT0);
+ rvu_blklf_teardown(rvu, pcifunc, BLKADDR_CPT1);
rvu_blklf_teardown(rvu, pcifunc, BLKADDR_TIM);
rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSOW);
rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSO);
#define PCI_DEVID_OCTEONTX2_LBK 0xA061
-static int lbk_get_num_chans(void)
+int rvu_get_num_lbk_chans(void)
{
struct pci_dev *pdev;
void __iomem *base;
return 0;
}
- chans = lbk_get_num_chans();
+ chans = rvu_get_num_lbk_chans();
if (chans < 0)
return chans;
#include "rvu_struct.h"
#include "common.h"
#include "mbox.h"
+#include "npc.h"
/* PCI device IDs */
#define PCI_DEVID_OCTEONTX2_RVU_AF 0xA065
#define PCI_MBOX_BAR_NUM 4
#define NAME_SIZE 32
+#define MAX_NIX_BLKS 2
/* PF_FUNC */
#define RVU_PFVF_PF_SHIFT 10
struct dentry *npa;
struct dentry *nix;
struct dentry *npc;
+ struct dentry *cpt;
struct dump_ctx npa_aura_ctx;
struct dump_ctx npa_pool_ctx;
struct dump_ctx nix_cq_ctx;
int max;
};
+/* layer metadata to uniquely identify a packet header field */
+struct npc_layer_mdata {
+ u8 lid;
+ u8 ltype;
+ u8 hdr;
+ u8 key;
+ u8 len;
+};
+
+/* Structure to represent a field present in the
+ * generated key. A key field may present anywhere and can
+ * be of any size in the generated key. Once this structure
+ * is populated for fields of interest then field's presence
+ * and location (if present) can be known.
+ */
+struct npc_key_field {
+ /* Masks where all set bits indicate position
+ * of a field in the key
+ */
+ u64 kw_mask[NPC_MAX_KWS_IN_KEY];
+ /* Number of words in the key a field spans. If a field is
+ * of 16 bytes and key offset is 4 then the field will use
+ * 4 bytes in KW0, 8 bytes in KW1 and 4 bytes in KW2 and
+ * nr_kws will be 3(KW0, KW1 and KW2).
+ */
+ int nr_kws;
+ /* used by packet header fields */
+ struct npc_layer_mdata layer_mdata;
+};
+
struct npc_mcam {
struct rsrc_bmap counters;
struct mutex lock; /* MCAM entries and counters update lock */
u16 *entry2cntr_map;
u16 *cntr2pfvf_map;
u16 *cntr_refcnt;
+ u16 *entry2target_pffunc;
u8 keysize; /* MCAM keysize 112/224/448 bits */
u8 banks; /* Number of MCAM banks */
u8 banks_per_entry;/* Number of keywords in key */
u16 hprio_count;
u16 hprio_end;
u16 rx_miss_act_cntr; /* Counter for RX MISS action */
+ /* fields present in the generated key */
+ struct npc_key_field tx_key_fields[NPC_KEY_FIELDS_MAX];
+ struct npc_key_field rx_key_fields[NPC_KEY_FIELDS_MAX];
+ u64 tx_features;
+ u64 rx_features;
+ struct list_head mcam_rules;
};
/* Structure for per RVU func info ie PF/VF */
u16 ssow;
u16 cptlfs;
u16 timlfs;
+ u16 cpt1_lfs;
u8 cgx_lmac;
/* Block LF's MSIX vector info */
u16 maxlen;
u16 minlen;
+ u8 pf_set_vf_cfg;
u8 mac_addr[ETH_ALEN]; /* MAC address of this PF/VF */
+ u8 default_mac[ETH_ALEN]; /* MAC address from FWdata */
/* Broadcast pkt replication info */
u16 bcast_mce_idx;
struct nix_mce_list bcast_mce_list;
- /* VLAN offload */
- struct mcam_entry entry;
- int rxvlan_index;
- bool rxvlan;
+ struct rvu_npc_mcam_rule *def_ucast_rule;
bool cgx_in_use; /* this PF/VF using CGX? */
int cgx_users; /* number of cgx users - used only by PFs */
+
+ u8 nix_blkaddr; /* BLKADDR_NIX0/1 assigned to this PF */
+ u8 nix_rx_intf; /* NIX0_RX/NIX1_RX interface to NPC */
+ u8 nix_tx_intf; /* NIX0_TX/NIX1_TX interface to NPC */
};
struct nix_txsch {
u8 in_use;
};
+struct nix_txvlan {
+#define NIX_TX_VTAG_DEF_MAX 0x400
+ struct rsrc_bmap rsrc;
+ u16 *entry2pfvf_map;
+ struct mutex rsrc_lock; /* Serialize resource alloc/free */
+};
+
struct nix_hw {
+ int blkaddr;
+ struct rvu *rvu;
struct nix_txsch txsch[NIX_TXSCH_LVL_CNT]; /* Tx schedulers */
struct nix_mcast mcast;
struct nix_flowkey flowkey;
struct nix_mark_format mark_format;
struct nix_lso lso;
+ struct nix_txvlan txvlan;
};
/* RVU block's capabilities or functionality,
u8 lbk_links;
u8 sdp_links;
u8 npc_kpus; /* No of parser units */
+ u8 npc_pkinds; /* No of port kinds */
+ u8 npc_intfs; /* No of interfaces */
+ u8 npc_kpu_entries; /* No of KPU entries */
+ u16 npc_counters; /* No of match stats counters */
+ bool npc_ext_set; /* Extended register set */
struct hw_cap cap;
struct rvu_block block[BLK_COUNT]; /* Block info */
- struct nix_hw *nix0;
+ struct nix_hw *nix;
+ struct rvu *rvu;
struct npc_pkind pkind;
struct npc_mcam mcam;
};
const struct npc_lt_def_cfg *lt_def;
const struct npc_kpu_profile_action *ikpu; /* array[pkinds] */
const struct npc_kpu_profile *kpu; /* array[kpus] */
- const struct npc_mcam_kex *mkex;
+ struct npc_mcam_kex *mkex;
size_t pkinds;
size_t kpus;
};
struct rvu_pfvf *hwvf;
struct mutex rsrc_lock; /* Serialize resource alloc/free */
int vfs; /* Number of VFs attached to RVU */
+ int nix_blkaddr[MAX_NIX_BLKS];
/* Mbox */
struct mbox_wq_info afpf_wq_info;
int rvu_rsrc_free_count(struct rsrc_bmap *rsrc);
int rvu_alloc_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc);
bool rvu_rsrc_check_contig(struct rsrc_bmap *rsrc, int nrsrc);
+u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blkaddr);
int rvu_get_pf(u16 pcifunc);
struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc);
void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf);
int rvu_lf_reset(struct rvu *rvu, struct rvu_block *block, int lf);
int rvu_get_blkaddr(struct rvu *rvu, int blktype, u16 pcifunc);
int rvu_poll_reg(struct rvu *rvu, u64 block, u64 offset, u64 mask, bool zero);
+int rvu_get_num_lbk_chans(void);
/* RVU HW reg validation */
enum regmap_block {
void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf);
int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr);
int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add);
+struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr);
+int rvu_get_next_nix_blkaddr(struct rvu *rvu, int blkaddr);
+void rvu_nix_reset_mac(struct rvu_pfvf *pfvf, int pcifunc);
/* NPC APIs */
int rvu_npc_init(struct rvu *rvu);
void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
int nixlf, u64 chan);
void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable);
-int rvu_npc_update_rxvlan(struct rvu *rvu, u16 pcifunc, int nixlf);
void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
+void rvu_npc_free_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
void rvu_npc_enable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
void rvu_npc_get_mcam_counter_alloc_info(struct rvu *rvu, u16 pcifunc,
int blkaddr, int *alloc_cnt,
int *enable_cnt);
+bool is_npc_intf_tx(u8 intf);
+bool is_npc_intf_rx(u8 intf);
+bool is_npc_interface_valid(struct rvu *rvu, u8 intf);
+int rvu_npc_get_tx_nibble_cfg(struct rvu *rvu, u64 nibble_ena);
+int npc_mcam_verify_channel(struct rvu *rvu, u16 pcifunc, u8 intf, u16 channel);
+int npc_flow_steering_init(struct rvu *rvu, int blkaddr);
+const char *npc_get_field_name(u8 hdr);
+bool rvu_npc_write_default_rule(struct rvu *rvu, int blkaddr, int nixlf,
+ u16 pcifunc, u8 intf, struct mcam_entry *entry,
+ int *entry_index);
+int npc_get_bank(struct npc_mcam *mcam, int index);
+void npc_mcam_enable_flows(struct rvu *rvu, u16 target);
+void npc_mcam_disable_flows(struct rvu *rvu, u16 target);
+void npc_enable_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
+ int blkaddr, int index, bool enable);
+void npc_read_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
+ int blkaddr, u16 src, struct mcam_entry *entry,
+ u8 *intf, u8 *ena);
#ifdef CONFIG_DEBUG_FS
void rvu_dbg_init(struct rvu *rvu);
return rvu->cgx_idmap[cgx_id];
}
+/* Based on P2X connectivity find mapped NIX block for a PF */
+static void rvu_map_cgx_nix_block(struct rvu *rvu, int pf,
+ int cgx_id, int lmac_id)
+{
+ struct rvu_pfvf *pfvf = &rvu->pf[pf];
+ u8 p2x;
+
+ p2x = cgx_lmac_get_p2x(cgx_id, lmac_id);
+ /* Firmware sets P2X_SELECT as either NIX0 or NIX1 */
+ pfvf->nix_blkaddr = BLKADDR_NIX0;
+ if (p2x == CMR_P2X_SEL_NIX1)
+ pfvf->nix_blkaddr = BLKADDR_NIX1;
+}
+
static int rvu_map_cgx_lmac_pf(struct rvu *rvu)
{
struct npc_pkind *pkind = &rvu->hw->pkind;
rvu->cgxlmac2pf_map[CGX_OFFSET(cgx) + lmac] = 1 << pf;
free_pkind = rvu_alloc_rsrc(&pkind->rsrc);
pkind->pfchan_map[free_pkind] = ((pf) & 0x3F) << 16;
+ rvu_map_cgx_nix_block(rvu, pf, cgx, lmac);
rvu->cgx_mapped_pfs++;
}
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include <linux/pci.h>
+#include "rvu_struct.h"
+#include "rvu_reg.h"
+#include "mbox.h"
+#include "rvu.h"
+
+/* CPT PF device id */
+#define PCI_DEVID_OTX2_CPT_PF 0xA0FD
+
+static int get_cpt_pf_num(struct rvu *rvu)
+{
+ int i, domain_nr, cpt_pf_num = -1;
+ struct pci_dev *pdev;
+
+ domain_nr = pci_domain_nr(rvu->pdev->bus);
+ for (i = 0; i < rvu->hw->total_pfs; i++) {
+ pdev = pci_get_domain_bus_and_slot(domain_nr, i + 1, 0);
+ if (!pdev)
+ continue;
+
+ if (pdev->device == PCI_DEVID_OTX2_CPT_PF) {
+ cpt_pf_num = i;
+ put_device(&pdev->dev);
+ break;
+ }
+ put_device(&pdev->dev);
+ }
+ return cpt_pf_num;
+}
+
+static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc)
+{
+ int cpt_pf_num = get_cpt_pf_num(rvu);
+
+ if (rvu_get_pf(pcifunc) != cpt_pf_num)
+ return false;
+ if (pcifunc & RVU_PFVF_FUNC_MASK)
+ return false;
+
+ return true;
+}
+
+static bool is_cpt_vf(struct rvu *rvu, u16 pcifunc)
+{
+ int cpt_pf_num = get_cpt_pf_num(rvu);
+
+ if (rvu_get_pf(pcifunc) != cpt_pf_num)
+ return false;
+ if (!(pcifunc & RVU_PFVF_FUNC_MASK))
+ return false;
+
+ return true;
+}
+
+int rvu_mbox_handler_cpt_lf_alloc(struct rvu *rvu,
+ struct cpt_lf_alloc_req_msg *req,
+ struct msg_rsp *rsp)
+{
+ u16 pcifunc = req->hdr.pcifunc;
+ struct rvu_block *block;
+ int cptlf, blkaddr;
+ int num_lfs, slot;
+ u64 val;
+
+ if (req->eng_grpmsk == 0x0)
+ return CPT_AF_ERR_GRP_INVALID;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+ if (blkaddr < 0)
+ return blkaddr;
+
+ block = &rvu->hw->block[blkaddr];
+ num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, pcifunc),
+ block->addr);
+ if (!num_lfs)
+ return CPT_AF_ERR_LF_INVALID;
+
+ /* Check if requested 'CPTLF <=> NIXLF' mapping is valid */
+ if (req->nix_pf_func) {
+ /* If default, use 'this' CPTLF's PFFUNC */
+ if (req->nix_pf_func == RVU_DEFAULT_PF_FUNC)
+ req->nix_pf_func = pcifunc;
+ if (!is_pffunc_map_valid(rvu, req->nix_pf_func, BLKTYPE_NIX))
+ return CPT_AF_ERR_NIX_PF_FUNC_INVALID;
+ }
+
+ /* Check if requested 'CPTLF <=> SSOLF' mapping is valid */
+ if (req->sso_pf_func) {
+ /* If default, use 'this' CPTLF's PFFUNC */
+ if (req->sso_pf_func == RVU_DEFAULT_PF_FUNC)
+ req->sso_pf_func = pcifunc;
+ if (!is_pffunc_map_valid(rvu, req->sso_pf_func, BLKTYPE_SSO))
+ return CPT_AF_ERR_SSO_PF_FUNC_INVALID;
+ }
+
+ for (slot = 0; slot < num_lfs; slot++) {
+ cptlf = rvu_get_lf(rvu, block, pcifunc, slot);
+ if (cptlf < 0)
+ return CPT_AF_ERR_LF_INVALID;
+
+ /* Set CPT LF group and priority */
+ val = (u64)req->eng_grpmsk << 48 | 1;
+ rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), val);
+
+ /* Set CPT LF NIX_PF_FUNC and SSO_PF_FUNC */
+ val = (u64)req->nix_pf_func << 48 |
+ (u64)req->sso_pf_func << 32;
+ rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), val);
+ }
+
+ return 0;
+}
+
+int rvu_mbox_handler_cpt_lf_free(struct rvu *rvu, struct msg_req *req,
+ struct msg_rsp *rsp)
+{
+ u16 pcifunc = req->hdr.pcifunc;
+ struct rvu_block *block;
+ int cptlf, blkaddr;
+ int num_lfs, slot;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+ if (blkaddr < 0)
+ return blkaddr;
+
+ block = &rvu->hw->block[blkaddr];
+ num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, pcifunc),
+ block->addr);
+ if (!num_lfs)
+ return CPT_AF_ERR_LF_INVALID;
+
+ for (slot = 0; slot < num_lfs; slot++) {
+ cptlf = rvu_get_lf(rvu, block, pcifunc, slot);
+ if (cptlf < 0)
+ return CPT_AF_ERR_LF_INVALID;
+
+ /* Reset CPT LF group and priority */
+ rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), 0x0);
+ /* Reset CPT LF NIX_PF_FUNC and SSO_PF_FUNC */
+ rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), 0x0);
+ }
+
+ return 0;
+}
+
+static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req)
+{
+ u64 offset = req->reg_offset;
+ int blkaddr, num_lfs, lf;
+ struct rvu_block *block;
+ struct rvu_pfvf *pfvf;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+
+ /* Registers that can be accessed from PF/VF */
+ if ((offset & 0xFF000) == CPT_AF_LFX_CTL(0) ||
+ (offset & 0xFF000) == CPT_AF_LFX_CTL2(0)) {
+ if (offset & 7)
+ return false;
+
+ lf = (offset & 0xFFF) >> 3;
+ block = &rvu->hw->block[blkaddr];
+ pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc);
+ num_lfs = rvu_get_rsrc_mapcount(pfvf, block->addr);
+ if (lf >= num_lfs)
+ /* Slot is not valid for that PF/VF */
+ return false;
+
+ /* Translate local LF used by VFs to global CPT LF */
+ lf = rvu_get_lf(rvu, &rvu->hw->block[blkaddr],
+ req->hdr.pcifunc, lf);
+ if (lf < 0)
+ return false;
+
+ return true;
+ } else if (!(req->hdr.pcifunc & RVU_PFVF_FUNC_MASK)) {
+ /* Registers that can be accessed from PF */
+ switch (offset) {
+ case CPT_AF_CTL:
+ case CPT_AF_PF_FUNC:
+ case CPT_AF_BLK_RST:
+ case CPT_AF_CONSTANTS1:
+ return true;
+ }
+
+ switch (offset & 0xFF000) {
+ case CPT_AF_EXEX_STS(0):
+ case CPT_AF_EXEX_CTL(0):
+ case CPT_AF_EXEX_CTL2(0):
+ case CPT_AF_EXEX_UCODE_BASE(0):
+ if (offset & 7)
+ return false;
+ break;
+ default:
+ return false;
+ }
+ return true;
+ }
+ return false;
+}
+
+int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu,
+ struct cpt_rd_wr_reg_msg *req,
+ struct cpt_rd_wr_reg_msg *rsp)
+{
+ int blkaddr;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+ if (blkaddr < 0)
+ return blkaddr;
+
+ /* This message is accepted only if sent from CPT PF/VF */
+ if (!is_cpt_pf(rvu, req->hdr.pcifunc) &&
+ !is_cpt_vf(rvu, req->hdr.pcifunc))
+ return CPT_AF_ERR_ACCESS_DENIED;
+
+ rsp->reg_offset = req->reg_offset;
+ rsp->ret_val = req->ret_val;
+ rsp->is_write = req->is_write;
+
+ if (!is_valid_offset(rvu, req))
+ return CPT_AF_ERR_ACCESS_DENIED;
+
+ if (req->is_write)
+ rvu_write64(rvu, blkaddr, req->reg_offset, req->val);
+ else
+ rsp->val = rvu_read64(rvu, blkaddr, req->reg_offset);
+
+ return 0;
+}
[CGX_STAT17] = "Control/PAUSE packets sent",
};
+enum cpt_eng_type {
+ CPT_AE_TYPE = 1,
+ CPT_SE_TYPE = 2,
+ CPT_IE_TYPE = 3,
+};
+
#define NDC_MAX_BANK(rvu, blk_addr) (rvu_read64(rvu, \
blk_addr, NDC_AF_CONST) & 0xFF)
RVU_DEBUG_FOPS(rsrc_status, rsrc_attach_status, NULL);
-static bool rvu_dbg_is_valid_lf(struct rvu *rvu, int blktype, int lf,
+static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused)
+{
+ struct rvu *rvu = filp->private;
+ struct pci_dev *pdev = NULL;
+ char cgx[10], lmac[10];
+ struct rvu_pfvf *pfvf;
+ int pf, domain, blkid;
+ u8 cgx_id, lmac_id;
+ u16 pcifunc;
+
+ domain = 2;
+ seq_puts(filp, "PCI dev\t\tRVU PF Func\tNIX block\tCGX\tLMAC\n");
+ for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
+ if (!is_pf_cgxmapped(rvu, pf))
+ continue;
+
+ pdev = pci_get_domain_bus_and_slot(domain, pf + 1, 0);
+ if (!pdev)
+ continue;
+
+ cgx[0] = 0;
+ lmac[0] = 0;
+ pcifunc = pf << 10;
+ pfvf = rvu_get_pfvf(rvu, pcifunc);
+
+ if (pfvf->nix_blkaddr == BLKADDR_NIX0)
+ blkid = 0;
+ else
+ blkid = 1;
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id,
+ &lmac_id);
+ sprintf(cgx, "CGX%d", cgx_id);
+ sprintf(lmac, "LMAC%d", lmac_id);
+ seq_printf(filp, "%s\t0x%x\t\tNIX%d\t\t%s\t%s\n",
+ dev_name(&pdev->dev), pcifunc, blkid, cgx, lmac);
+ }
+ return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(rvu_pf_cgx_map, rvu_pf_cgx_map_display, NULL);
+
+static bool rvu_dbg_is_valid_lf(struct rvu *rvu, int blkaddr, int lf,
u16 *pcifunc)
{
struct rvu_block *block;
struct rvu_hwinfo *hw;
- int blkaddr;
-
- blkaddr = rvu_get_blkaddr(rvu, blktype, 0);
- if (blkaddr < 0) {
- dev_warn(rvu->dev, "Invalid blktype\n");
- return false;
- }
hw = rvu->hw;
block = &hw->block[blkaddr];
{
void (*print_qsize)(struct seq_file *filp,
struct rvu_pfvf *pfvf) = NULL;
+ struct dentry *current_dir;
struct rvu_pfvf *pfvf;
struct rvu *rvu;
int qsize_id;
u16 pcifunc;
+ int blkaddr;
rvu = filp->private;
switch (blktype) {
return -EINVAL;
}
- if (!rvu_dbg_is_valid_lf(rvu, blktype, qsize_id, &pcifunc))
+ if (blktype == BLKTYPE_NPA) {
+ blkaddr = BLKADDR_NPA;
+ } else {
+ current_dir = filp->file->f_path.dentry->d_parent;
+ blkaddr = (!strcmp(current_dir->d_name.name, "nix1") ?
+ BLKADDR_NIX1 : BLKADDR_NIX0);
+ }
+
+ if (!rvu_dbg_is_valid_lf(rvu, blkaddr, qsize_id, &pcifunc))
return -EINVAL;
pfvf = rvu_get_pfvf(rvu, pcifunc);
struct seq_file *seqfile = filp->private_data;
char *cmd_buf, *cmd_buf_tmp, *subtoken;
struct rvu *rvu = seqfile->private;
+ struct dentry *current_dir;
+ int blkaddr;
u16 pcifunc;
int ret, lf;
goto qsize_write_done;
}
- if (!rvu_dbg_is_valid_lf(rvu, blktype, lf, &pcifunc)) {
+ if (blktype == BLKTYPE_NPA) {
+ blkaddr = BLKADDR_NPA;
+ } else {
+ current_dir = filp->f_path.dentry->d_parent;
+ blkaddr = (!strcmp(current_dir->d_name.name, "nix1") ?
+ BLKADDR_NIX1 : BLKADDR_NIX0);
+ }
+
+ if (!rvu_dbg_is_valid_lf(rvu, blkaddr, lf, &pcifunc)) {
ret = -EINVAL;
goto qsize_write_done;
}
return -EINVAL;
}
- if (!rvu_dbg_is_valid_lf(rvu, BLKTYPE_NPA, npalf, &pcifunc))
+ if (!rvu_dbg_is_valid_lf(rvu, BLKADDR_NPA, npalf, &pcifunc))
return -EINVAL;
pfvf = rvu_get_pfvf(rvu, pcifunc);
int max_id = 0;
u16 pcifunc;
- if (!rvu_dbg_is_valid_lf(rvu, BLKTYPE_NPA, npalf, &pcifunc))
+ if (!rvu_dbg_is_valid_lf(rvu, BLKADDR_NPA, npalf, &pcifunc))
return -EINVAL;
pfvf = rvu_get_pfvf(rvu, pcifunc);
int ctype, int transaction)
{
u64 req, out_req, lat, cant_alloc;
- struct rvu *rvu = s->private;
+ struct nix_hw *nix_hw;
+ struct rvu *rvu;
int port;
+ if (blk_addr == BLKADDR_NDC_NPA0) {
+ rvu = s->private;
+ } else {
+ nix_hw = s->private;
+ rvu = nix_hw->rvu;
+ }
+
for (port = 0; port < NDC_MAX_PORT; port++) {
req = rvu_read64(rvu, blk_addr, NDC_AF_PORTX_RTX_RWX_REQ_PC
(port, ctype, transaction));
static int ndc_blk_hits_miss_stats(struct seq_file *s, int idx, int blk_addr)
{
- struct rvu *rvu = s->private;
+ struct nix_hw *nix_hw;
+ struct rvu *rvu;
int bank, max_bank;
+ if (blk_addr == BLKADDR_NDC_NPA0) {
+ rvu = s->private;
+ } else {
+ nix_hw = s->private;
+ rvu = nix_hw->rvu;
+ }
+
max_bank = NDC_MAX_BANK(rvu, blk_addr);
for (bank = 0; bank < max_bank; bank++) {
seq_printf(s, "BANK:%d\n", bank);
static int rvu_dbg_nix_ndc_rx_cache_display(struct seq_file *filp, void *unused)
{
- return ndc_blk_cache_stats(filp, NIX0_RX,
- BLKADDR_NDC_NIX0_RX);
+ struct nix_hw *nix_hw = filp->private;
+ int blkaddr = 0;
+ int ndc_idx = 0;
+
+ blkaddr = (nix_hw->blkaddr == BLKADDR_NIX1 ?
+ BLKADDR_NDC_NIX1_RX : BLKADDR_NDC_NIX0_RX);
+ ndc_idx = (nix_hw->blkaddr == BLKADDR_NIX1 ? NIX1_RX : NIX0_RX);
+
+ return ndc_blk_cache_stats(filp, ndc_idx, blkaddr);
}
RVU_DEBUG_SEQ_FOPS(nix_ndc_rx_cache, nix_ndc_rx_cache_display, NULL);
static int rvu_dbg_nix_ndc_tx_cache_display(struct seq_file *filp, void *unused)
{
- return ndc_blk_cache_stats(filp, NIX0_TX,
- BLKADDR_NDC_NIX0_TX);
+ struct nix_hw *nix_hw = filp->private;
+ int blkaddr = 0;
+ int ndc_idx = 0;
+
+ blkaddr = (nix_hw->blkaddr == BLKADDR_NIX1 ?
+ BLKADDR_NDC_NIX1_TX : BLKADDR_NDC_NIX0_TX);
+ ndc_idx = (nix_hw->blkaddr == BLKADDR_NIX1 ? NIX1_TX : NIX0_TX);
+
+ return ndc_blk_cache_stats(filp, ndc_idx, blkaddr);
}
RVU_DEBUG_SEQ_FOPS(nix_ndc_tx_cache, nix_ndc_tx_cache_display, NULL);
static int rvu_dbg_nix_ndc_rx_hits_miss_display(struct seq_file *filp,
void *unused)
{
- return ndc_blk_hits_miss_stats(filp,
- NPA0_U, BLKADDR_NDC_NIX0_RX);
+ struct nix_hw *nix_hw = filp->private;
+ int ndc_idx = NPA0_U;
+ int blkaddr = 0;
+
+ blkaddr = (nix_hw->blkaddr == BLKADDR_NIX1 ?
+ BLKADDR_NDC_NIX1_RX : BLKADDR_NDC_NIX0_RX);
+
+ return ndc_blk_hits_miss_stats(filp, ndc_idx, blkaddr);
}
RVU_DEBUG_SEQ_FOPS(nix_ndc_rx_hits_miss, nix_ndc_rx_hits_miss_display, NULL);
static int rvu_dbg_nix_ndc_tx_hits_miss_display(struct seq_file *filp,
void *unused)
{
- return ndc_blk_hits_miss_stats(filp,
- NPA0_U, BLKADDR_NDC_NIX0_TX);
+ struct nix_hw *nix_hw = filp->private;
+ int ndc_idx = NPA0_U;
+ int blkaddr = 0;
+
+ blkaddr = (nix_hw->blkaddr == BLKADDR_NIX1 ?
+ BLKADDR_NDC_NIX1_TX : BLKADDR_NDC_NIX0_TX);
+
+ return ndc_blk_hits_miss_stats(filp, ndc_idx, blkaddr);
}
RVU_DEBUG_SEQ_FOPS(nix_ndc_tx_hits_miss, nix_ndc_tx_hits_miss_display, NULL);
{
void (*print_nix_ctx)(struct seq_file *filp,
struct nix_aq_enq_rsp *rsp) = NULL;
- struct rvu *rvu = filp->private;
+ struct nix_hw *nix_hw = filp->private;
+ struct rvu *rvu = nix_hw->rvu;
struct nix_aq_enq_req aq_req;
struct nix_aq_enq_rsp rsp;
char *ctype_string = NULL;
return -EINVAL;
}
- if (!rvu_dbg_is_valid_lf(rvu, BLKTYPE_NIX, nixlf, &pcifunc))
+ if (!rvu_dbg_is_valid_lf(rvu, nix_hw->blkaddr, nixlf, &pcifunc))
return -EINVAL;
pfvf = rvu_get_pfvf(rvu, pcifunc);
}
static int write_nix_queue_ctx(struct rvu *rvu, bool all, int nixlf,
- int id, int ctype, char *ctype_string)
+ int id, int ctype, char *ctype_string,
+ struct seq_file *m)
{
+ struct nix_hw *nix_hw = m->private;
struct rvu_pfvf *pfvf;
int max_id = 0;
u16 pcifunc;
- if (!rvu_dbg_is_valid_lf(rvu, BLKTYPE_NIX, nixlf, &pcifunc))
+ if (!rvu_dbg_is_valid_lf(rvu, nix_hw->blkaddr, nixlf, &pcifunc))
return -EINVAL;
pfvf = rvu_get_pfvf(rvu, pcifunc);
int ctype)
{
struct seq_file *m = filp->private_data;
- struct rvu *rvu = m->private;
+ struct nix_hw *nix_hw = m->private;
+ struct rvu *rvu = nix_hw->rvu;
char *cmd_buf, *ctype_string;
int nixlf, id = 0, ret;
bool all = false;
goto done;
} else {
ret = write_nix_queue_ctx(rvu, all, nixlf, id, ctype,
- ctype_string);
+ ctype_string, m);
}
done:
kfree(cmd_buf);
RVU_DEBUG_SEQ_FOPS(nix_qsize, nix_qsize_display, nix_qsize_write);
-static void rvu_dbg_nix_init(struct rvu *rvu)
+static void rvu_dbg_nix_init(struct rvu *rvu, int blkaddr)
{
- const struct device *dev = &rvu->pdev->dev;
- struct dentry *pfile;
+ struct nix_hw *nix_hw;
- rvu->rvu_dbg.nix = debugfs_create_dir("nix", rvu->rvu_dbg.root);
- if (!rvu->rvu_dbg.nix) {
- dev_err(rvu->dev, "create debugfs dir failed for nix\n");
+ if (!is_block_implemented(rvu->hw, blkaddr))
return;
- }
-
- pfile = debugfs_create_file("sq_ctx", 0600, rvu->rvu_dbg.nix, rvu,
- &rvu_dbg_nix_sq_ctx_fops);
- if (!pfile)
- goto create_failed;
-
- pfile = debugfs_create_file("rq_ctx", 0600, rvu->rvu_dbg.nix, rvu,
- &rvu_dbg_nix_rq_ctx_fops);
- if (!pfile)
- goto create_failed;
-
- pfile = debugfs_create_file("cq_ctx", 0600, rvu->rvu_dbg.nix, rvu,
- &rvu_dbg_nix_cq_ctx_fops);
- if (!pfile)
- goto create_failed;
- pfile = debugfs_create_file("ndc_tx_cache", 0600, rvu->rvu_dbg.nix, rvu,
- &rvu_dbg_nix_ndc_tx_cache_fops);
- if (!pfile)
- goto create_failed;
-
- pfile = debugfs_create_file("ndc_rx_cache", 0600, rvu->rvu_dbg.nix, rvu,
- &rvu_dbg_nix_ndc_rx_cache_fops);
- if (!pfile)
- goto create_failed;
-
- pfile = debugfs_create_file("ndc_tx_hits_miss", 0600, rvu->rvu_dbg.nix,
- rvu, &rvu_dbg_nix_ndc_tx_hits_miss_fops);
- if (!pfile)
- goto create_failed;
-
- pfile = debugfs_create_file("ndc_rx_hits_miss", 0600, rvu->rvu_dbg.nix,
- rvu, &rvu_dbg_nix_ndc_rx_hits_miss_fops);
- if (!pfile)
- goto create_failed;
-
- pfile = debugfs_create_file("qsize", 0600, rvu->rvu_dbg.nix, rvu,
- &rvu_dbg_nix_qsize_fops);
- if (!pfile)
- goto create_failed;
+ if (blkaddr == BLKADDR_NIX0) {
+ rvu->rvu_dbg.nix = debugfs_create_dir("nix", rvu->rvu_dbg.root);
+ nix_hw = &rvu->hw->nix[0];
+ } else {
+ rvu->rvu_dbg.nix = debugfs_create_dir("nix1",
+ rvu->rvu_dbg.root);
+ nix_hw = &rvu->hw->nix[1];
+ }
- return;
-create_failed:
- dev_err(dev, "Failed to create debugfs dir/file for NIX\n");
- debugfs_remove_recursive(rvu->rvu_dbg.nix);
+ debugfs_create_file("sq_ctx", 0600, rvu->rvu_dbg.nix, nix_hw,
+ &rvu_dbg_nix_sq_ctx_fops);
+ debugfs_create_file("rq_ctx", 0600, rvu->rvu_dbg.nix, nix_hw,
+ &rvu_dbg_nix_rq_ctx_fops);
+ debugfs_create_file("cq_ctx", 0600, rvu->rvu_dbg.nix, nix_hw,
+ &rvu_dbg_nix_cq_ctx_fops);
+ debugfs_create_file("ndc_tx_cache", 0600, rvu->rvu_dbg.nix, nix_hw,
+ &rvu_dbg_nix_ndc_tx_cache_fops);
+ debugfs_create_file("ndc_rx_cache", 0600, rvu->rvu_dbg.nix, nix_hw,
+ &rvu_dbg_nix_ndc_rx_cache_fops);
+ debugfs_create_file("ndc_tx_hits_miss", 0600, rvu->rvu_dbg.nix, nix_hw,
+ &rvu_dbg_nix_ndc_tx_hits_miss_fops);
+ debugfs_create_file("ndc_rx_hits_miss", 0600, rvu->rvu_dbg.nix, nix_hw,
+ &rvu_dbg_nix_ndc_rx_hits_miss_fops);
+ debugfs_create_file("qsize", 0600, rvu->rvu_dbg.nix, rvu,
+ &rvu_dbg_nix_qsize_fops);
}
static void rvu_dbg_npa_init(struct rvu *rvu)
{
- const struct device *dev = &rvu->pdev->dev;
- struct dentry *pfile;
-
rvu->rvu_dbg.npa = debugfs_create_dir("npa", rvu->rvu_dbg.root);
- if (!rvu->rvu_dbg.npa)
- return;
-
- pfile = debugfs_create_file("qsize", 0600, rvu->rvu_dbg.npa, rvu,
- &rvu_dbg_npa_qsize_fops);
- if (!pfile)
- goto create_failed;
-
- pfile = debugfs_create_file("aura_ctx", 0600, rvu->rvu_dbg.npa, rvu,
- &rvu_dbg_npa_aura_ctx_fops);
- if (!pfile)
- goto create_failed;
-
- pfile = debugfs_create_file("pool_ctx", 0600, rvu->rvu_dbg.npa, rvu,
- &rvu_dbg_npa_pool_ctx_fops);
- if (!pfile)
- goto create_failed;
-
- pfile = debugfs_create_file("ndc_cache", 0600, rvu->rvu_dbg.npa, rvu,
- &rvu_dbg_npa_ndc_cache_fops);
- if (!pfile)
- goto create_failed;
-
- pfile = debugfs_create_file("ndc_hits_miss", 0600, rvu->rvu_dbg.npa,
- rvu, &rvu_dbg_npa_ndc_hits_miss_fops);
- if (!pfile)
- goto create_failed;
-
- return;
-create_failed:
- dev_err(dev, "Failed to create debugfs dir/file for NPA\n");
- debugfs_remove_recursive(rvu->rvu_dbg.npa);
+ debugfs_create_file("qsize", 0600, rvu->rvu_dbg.npa, rvu,
+ &rvu_dbg_npa_qsize_fops);
+ debugfs_create_file("aura_ctx", 0600, rvu->rvu_dbg.npa, rvu,
+ &rvu_dbg_npa_aura_ctx_fops);
+ debugfs_create_file("pool_ctx", 0600, rvu->rvu_dbg.npa, rvu,
+ &rvu_dbg_npa_pool_ctx_fops);
+ debugfs_create_file("ndc_cache", 0600, rvu->rvu_dbg.npa, rvu,
+ &rvu_dbg_npa_ndc_cache_fops);
+ debugfs_create_file("ndc_hits_miss", 0600, rvu->rvu_dbg.npa, rvu,
+ &rvu_dbg_npa_ndc_hits_miss_fops);
}
#define PRINT_CGX_CUML_NIXRX_STATUS(idx, name) \
static void rvu_dbg_cgx_init(struct rvu *rvu)
{
- const struct device *dev = &rvu->pdev->dev;
- struct dentry *pfile;
int i, lmac_id;
char dname[20];
void *cgx;
rvu->rvu_dbg.lmac =
debugfs_create_dir(dname, rvu->rvu_dbg.cgx);
- pfile = debugfs_create_file("stats", 0600,
- rvu->rvu_dbg.lmac, cgx,
- &rvu_dbg_cgx_stat_fops);
- if (!pfile)
- goto create_failed;
+ debugfs_create_file("stats", 0600, rvu->rvu_dbg.lmac,
+ cgx, &rvu_dbg_cgx_stat_fops);
}
}
- return;
-
-create_failed:
- dev_err(dev, "Failed to create debugfs dir/file for CGX\n");
- debugfs_remove_recursive(rvu->rvu_dbg.cgx_root);
}
/* NPC debugfs APIs */
struct rvu *rvu = filp->private;
int pf, vf, numvfs, blkaddr;
struct npc_mcam *mcam;
- u16 pcifunc;
+ u16 pcifunc, counters;
u64 cfg;
blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
return -ENODEV;
mcam = &rvu->hw->mcam;
+ counters = rvu->hw->npc_counters;
seq_puts(filp, "\nNPC MCAM info:\n");
/* MCAM keywidth on receive and transmit sides */
seq_printf(filp, "\t\t Available \t: %d\n", mcam->bmap_fcnt);
/* MCAM counters */
- cfg = rvu_read64(rvu, blkaddr, NPC_AF_CONST);
- cfg = (cfg >> 48) & 0xFFFF;
- seq_printf(filp, "\n\t\t MCAM counters \t: %lld\n", cfg);
- seq_printf(filp, "\t\t Reserved \t: %lld\n", cfg - mcam->counters.max);
+ seq_printf(filp, "\n\t\t MCAM counters \t: %d\n", counters);
+ seq_printf(filp, "\t\t Reserved \t: %d\n",
+ counters - mcam->counters.max);
seq_printf(filp, "\t\t Available \t: %d\n",
rvu_rsrc_free_count(&mcam->counters));
RVU_DEBUG_SEQ_FOPS(npc_rx_miss_act, npc_rx_miss_stats_display, NULL);
-static void rvu_dbg_npc_init(struct rvu *rvu)
+static void rvu_dbg_npc_mcam_show_flows(struct seq_file *s,
+ struct rvu_npc_mcam_rule *rule)
{
- const struct device *dev = &rvu->pdev->dev;
- struct dentry *pfile;
+ u8 bit;
+
+ for_each_set_bit(bit, (unsigned long *)&rule->features, 64) {
+ seq_printf(s, "\t%s ", npc_get_field_name(bit));
+ switch (bit) {
+ case NPC_DMAC:
+ seq_printf(s, "%pM ", rule->packet.dmac);
+ seq_printf(s, "mask %pM\n", rule->mask.dmac);
+ break;
+ case NPC_SMAC:
+ seq_printf(s, "%pM ", rule->packet.smac);
+ seq_printf(s, "mask %pM\n", rule->mask.smac);
+ break;
+ case NPC_ETYPE:
+ seq_printf(s, "0x%x ", ntohs(rule->packet.etype));
+ seq_printf(s, "mask 0x%x\n", ntohs(rule->mask.etype));
+ break;
+ case NPC_OUTER_VID:
+ seq_printf(s, "%d ", ntohs(rule->packet.vlan_tci));
+ seq_printf(s, "mask 0x%x\n",
+ ntohs(rule->mask.vlan_tci));
+ break;
+ case NPC_TOS:
+ seq_printf(s, "%d ", rule->packet.tos);
+ seq_printf(s, "mask 0x%x\n", rule->mask.tos);
+ break;
+ case NPC_SIP_IPV4:
+ seq_printf(s, "%pI4 ", &rule->packet.ip4src);
+ seq_printf(s, "mask %pI4\n", &rule->mask.ip4src);
+ break;
+ case NPC_DIP_IPV4:
+ seq_printf(s, "%pI4 ", &rule->packet.ip4dst);
+ seq_printf(s, "mask %pI4\n", &rule->mask.ip4dst);
+ break;
+ case NPC_SIP_IPV6:
+ seq_printf(s, "%pI6 ", rule->packet.ip6src);
+ seq_printf(s, "mask %pI6\n", rule->mask.ip6src);
+ break;
+ case NPC_DIP_IPV6:
+ seq_printf(s, "%pI6 ", rule->packet.ip6dst);
+ seq_printf(s, "mask %pI6\n", rule->mask.ip6dst);
+ break;
+ case NPC_SPORT_TCP:
+ case NPC_SPORT_UDP:
+ case NPC_SPORT_SCTP:
+ seq_printf(s, "%d ", ntohs(rule->packet.sport));
+ seq_printf(s, "mask 0x%x\n", ntohs(rule->mask.sport));
+ break;
+ case NPC_DPORT_TCP:
+ case NPC_DPORT_UDP:
+ case NPC_DPORT_SCTP:
+ seq_printf(s, "%d ", ntohs(rule->packet.dport));
+ seq_printf(s, "mask 0x%x\n", ntohs(rule->mask.dport));
+ break;
+ default:
+ break;
+ }
+ }
+}
+
+static void rvu_dbg_npc_mcam_show_action(struct seq_file *s,
+ struct rvu_npc_mcam_rule *rule)
+{
+ if (rule->intf == NIX_INTF_TX) {
+ switch (rule->tx_action.op) {
+ case NIX_TX_ACTIONOP_DROP:
+ seq_puts(s, "\taction: Drop\n");
+ break;
+ case NIX_TX_ACTIONOP_UCAST_DEFAULT:
+ seq_puts(s, "\taction: Unicast to default channel\n");
+ break;
+ case NIX_TX_ACTIONOP_UCAST_CHAN:
+ seq_printf(s, "\taction: Unicast to channel %d\n",
+ rule->tx_action.index);
+ break;
+ case NIX_TX_ACTIONOP_MCAST:
+ seq_puts(s, "\taction: Multicast\n");
+ break;
+ case NIX_TX_ACTIONOP_DROP_VIOL:
+ seq_puts(s, "\taction: Lockdown Violation Drop\n");
+ break;
+ default:
+ break;
+ };
+ } else {
+ switch (rule->rx_action.op) {
+ case NIX_RX_ACTIONOP_DROP:
+ seq_puts(s, "\taction: Drop\n");
+ break;
+ case NIX_RX_ACTIONOP_UCAST:
+ seq_printf(s, "\taction: Direct to queue %d\n",
+ rule->rx_action.index);
+ break;
+ case NIX_RX_ACTIONOP_RSS:
+ seq_puts(s, "\taction: RSS\n");
+ break;
+ case NIX_RX_ACTIONOP_UCAST_IPSEC:
+ seq_puts(s, "\taction: Unicast ipsec\n");
+ break;
+ case NIX_RX_ACTIONOP_MCAST:
+ seq_puts(s, "\taction: Multicast\n");
+ break;
+ default:
+ break;
+ };
+ }
+}
+
+static const char *rvu_dbg_get_intf_name(int intf)
+{
+ switch (intf) {
+ case NIX_INTFX_RX(0):
+ return "NIX0_RX";
+ case NIX_INTFX_RX(1):
+ return "NIX1_RX";
+ case NIX_INTFX_TX(0):
+ return "NIX0_TX";
+ case NIX_INTFX_TX(1):
+ return "NIX1_TX";
+ default:
+ break;
+ }
+
+ return "unknown";
+}
+
+static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused)
+{
+ struct rvu_npc_mcam_rule *iter;
+ struct rvu *rvu = s->private;
+ struct npc_mcam *mcam;
+ int pf, vf = -1;
+ int blkaddr;
+ u16 target;
+ u64 hits;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+ if (blkaddr < 0)
+ return 0;
+
+ mcam = &rvu->hw->mcam;
+
+ mutex_lock(&mcam->lock);
+ list_for_each_entry(iter, &mcam->mcam_rules, list) {
+ pf = (iter->owner >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK;
+ seq_printf(s, "\n\tInstalled by: PF%d ", pf);
+
+ if (iter->owner & RVU_PFVF_FUNC_MASK) {
+ vf = (iter->owner & RVU_PFVF_FUNC_MASK) - 1;
+ seq_printf(s, "VF%d", vf);
+ }
+ seq_puts(s, "\n");
+
+ seq_printf(s, "\tdirection: %s\n", is_npc_intf_rx(iter->intf) ?
+ "RX" : "TX");
+ seq_printf(s, "\tinterface: %s\n",
+ rvu_dbg_get_intf_name(iter->intf));
+ seq_printf(s, "\tmcam entry: %d\n", iter->entry);
+
+ rvu_dbg_npc_mcam_show_flows(s, iter);
+ if (iter->intf == NIX_INTF_RX) {
+ target = iter->rx_action.pf_func;
+ pf = (target >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK;
+ seq_printf(s, "\tForward to: PF%d ", pf);
+
+ if (target & RVU_PFVF_FUNC_MASK) {
+ vf = (target & RVU_PFVF_FUNC_MASK) - 1;
+ seq_printf(s, "VF%d", vf);
+ }
+ seq_puts(s, "\n");
+ }
+
+ rvu_dbg_npc_mcam_show_action(s, iter);
+ seq_printf(s, "\tenabled: %s\n", iter->enable ? "yes" : "no");
+
+ if (!iter->has_cntr)
+ continue;
+ seq_printf(s, "\tcounter: %d\n", iter->cntr);
+ hits = rvu_read64(rvu, blkaddr, NPC_AF_MATCH_STATX(iter->cntr));
+ seq_printf(s, "\thits: %lld\n", hits);
+ }
+ mutex_unlock(&mcam->lock);
+
+ return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(npc_mcam_rules, npc_mcam_show_rules, NULL);
+
+static void rvu_dbg_npc_init(struct rvu *rvu)
+{
rvu->rvu_dbg.npc = debugfs_create_dir("npc", rvu->rvu_dbg.root);
- if (!rvu->rvu_dbg.npc)
- return;
- pfile = debugfs_create_file("mcam_info", 0444, rvu->rvu_dbg.npc,
- rvu, &rvu_dbg_npc_mcam_info_fops);
- if (!pfile)
- goto create_failed;
+ debugfs_create_file("mcam_info", 0444, rvu->rvu_dbg.npc, rvu,
+ &rvu_dbg_npc_mcam_info_fops);
+ debugfs_create_file("mcam_rules", 0444, rvu->rvu_dbg.npc, rvu,
+ &rvu_dbg_npc_mcam_rules_fops);
+ debugfs_create_file("rx_miss_act_stats", 0444, rvu->rvu_dbg.npc, rvu,
+ &rvu_dbg_npc_rx_miss_act_fops);
+}
- pfile = debugfs_create_file("rx_miss_act_stats", 0444, rvu->rvu_dbg.npc,
- rvu, &rvu_dbg_npc_rx_miss_act_fops);
- if (!pfile)
- goto create_failed;
+/* CPT debugfs APIs */
+static int cpt_eng_sts_display(struct seq_file *filp, u8 eng_type)
+{
+ struct rvu *rvu = filp->private;
+ u64 busy_sts = 0, free_sts = 0;
+ u32 e_min = 0, e_max = 0, e, i;
+ u16 max_ses, max_ies, max_aes;
+ int blkaddr;
+ u64 reg;
- return;
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+ if (blkaddr < 0)
+ return -ENODEV;
+
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_CONSTANTS1);
+ max_ses = reg & 0xffff;
+ max_ies = (reg >> 16) & 0xffff;
+ max_aes = (reg >> 32) & 0xffff;
+
+ switch (eng_type) {
+ case CPT_AE_TYPE:
+ e_min = max_ses + max_ies;
+ e_max = max_ses + max_ies + max_aes;
+ break;
+ case CPT_SE_TYPE:
+ e_min = 0;
+ e_max = max_ses;
+ break;
+ case CPT_IE_TYPE:
+ e_min = max_ses;
+ e_max = max_ses + max_ies;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ for (e = e_min, i = 0; e < e_max; e++, i++) {
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_STS(e));
+ if (reg & 0x1)
+ busy_sts |= 1ULL << i;
+
+ if (reg & 0x2)
+ free_sts |= 1ULL << i;
+ }
+ seq_printf(filp, "FREE STS : 0x%016llx\n", free_sts);
+ seq_printf(filp, "BUSY STS : 0x%016llx\n", busy_sts);
-create_failed:
- dev_err(dev, "Failed to create debugfs dir/file for NPC\n");
- debugfs_remove_recursive(rvu->rvu_dbg.npc);
+ return 0;
}
-void rvu_dbg_init(struct rvu *rvu)
+static int rvu_dbg_cpt_ae_sts_display(struct seq_file *filp, void *unused)
{
- struct device *dev = &rvu->pdev->dev;
- struct dentry *pfile;
+ return cpt_eng_sts_display(filp, CPT_AE_TYPE);
+}
- rvu->rvu_dbg.root = debugfs_create_dir(DEBUGFS_DIR_NAME, NULL);
- if (!rvu->rvu_dbg.root) {
- dev_err(rvu->dev, "%s failed\n", __func__);
- return;
+RVU_DEBUG_SEQ_FOPS(cpt_ae_sts, cpt_ae_sts_display, NULL);
+
+static int rvu_dbg_cpt_se_sts_display(struct seq_file *filp, void *unused)
+{
+ return cpt_eng_sts_display(filp, CPT_SE_TYPE);
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_se_sts, cpt_se_sts_display, NULL);
+
+static int rvu_dbg_cpt_ie_sts_display(struct seq_file *filp, void *unused)
+{
+ return cpt_eng_sts_display(filp, CPT_IE_TYPE);
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_ie_sts, cpt_ie_sts_display, NULL);
+
+static int rvu_dbg_cpt_engines_info_display(struct seq_file *filp, void *unused)
+{
+ struct rvu *rvu = filp->private;
+ u16 max_ses, max_ies, max_aes;
+ u32 e_max, e;
+ int blkaddr;
+ u64 reg;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+ if (blkaddr < 0)
+ return -ENODEV;
+
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_CONSTANTS1);
+ max_ses = reg & 0xffff;
+ max_ies = (reg >> 16) & 0xffff;
+ max_aes = (reg >> 32) & 0xffff;
+
+ e_max = max_ses + max_ies + max_aes;
+
+ seq_puts(filp, "===========================================\n");
+ for (e = 0; e < e_max; e++) {
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_CTL2(e));
+ seq_printf(filp, "CPT Engine[%u] Group Enable 0x%02llx\n", e,
+ reg & 0xff);
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_ACTIVE(e));
+ seq_printf(filp, "CPT Engine[%u] Active Info 0x%llx\n", e,
+ reg);
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_CTL(e));
+ seq_printf(filp, "CPT Engine[%u] Control 0x%llx\n", e,
+ reg);
+ seq_puts(filp, "===========================================\n");
+ }
+ return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_engines_info, cpt_engines_info_display, NULL);
+
+static int rvu_dbg_cpt_lfs_info_display(struct seq_file *filp, void *unused)
+{
+ struct rvu *rvu = filp->private;
+ struct rvu_hwinfo *hw = rvu->hw;
+ struct rvu_block *block;
+ int blkaddr;
+ u64 reg;
+ u32 lf;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+ if (blkaddr < 0)
+ return -ENODEV;
+
+ block = &hw->block[blkaddr];
+ if (!block->lf.bmap)
+ return -ENODEV;
+
+ seq_puts(filp, "===========================================\n");
+ for (lf = 0; lf < block->lf.max; lf++) {
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL(lf));
+ seq_printf(filp, "CPT Lf[%u] CTL 0x%llx\n", lf, reg);
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL2(lf));
+ seq_printf(filp, "CPT Lf[%u] CTL2 0x%llx\n", lf, reg);
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_LFX_PTR_CTL(lf));
+ seq_printf(filp, "CPT Lf[%u] PTR_CTL 0x%llx\n", lf, reg);
+ reg = rvu_read64(rvu, blkaddr, block->lfcfg_reg |
+ (lf << block->lfshift));
+ seq_printf(filp, "CPT Lf[%u] CFG 0x%llx\n", lf, reg);
+ seq_puts(filp, "===========================================\n");
}
- pfile = debugfs_create_file("rsrc_alloc", 0444, rvu->rvu_dbg.root, rvu,
- &rvu_dbg_rsrc_status_fops);
- if (!pfile)
- goto create_failed;
+ return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_lfs_info, cpt_lfs_info_display, NULL);
+
+static int rvu_dbg_cpt_err_info_display(struct seq_file *filp, void *unused)
+{
+ struct rvu *rvu = filp->private;
+ u64 reg0, reg1;
+ int blkaddr;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+ if (blkaddr < 0)
+ return -ENODEV;
+
+ reg0 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(0));
+ reg1 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(1));
+ seq_printf(filp, "CPT_AF_FLTX_INT: 0x%llx 0x%llx\n", reg0, reg1);
+ reg0 = rvu_read64(rvu, blkaddr, CPT_AF_PSNX_EXE(0));
+ reg1 = rvu_read64(rvu, blkaddr, CPT_AF_PSNX_EXE(1));
+ seq_printf(filp, "CPT_AF_PSNX_EXE: 0x%llx 0x%llx\n", reg0, reg1);
+ reg0 = rvu_read64(rvu, blkaddr, CPT_AF_PSNX_LF(0));
+ seq_printf(filp, "CPT_AF_PSNX_LF: 0x%llx\n", reg0);
+ reg0 = rvu_read64(rvu, blkaddr, CPT_AF_RVU_INT);
+ seq_printf(filp, "CPT_AF_RVU_INT: 0x%llx\n", reg0);
+ reg0 = rvu_read64(rvu, blkaddr, CPT_AF_RAS_INT);
+ seq_printf(filp, "CPT_AF_RAS_INT: 0x%llx\n", reg0);
+ reg0 = rvu_read64(rvu, blkaddr, CPT_AF_EXE_ERR_INFO);
+ seq_printf(filp, "CPT_AF_EXE_ERR_INFO: 0x%llx\n", reg0);
+
+ return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_err_info, cpt_err_info_display, NULL);
+
+static int rvu_dbg_cpt_pc_display(struct seq_file *filp, void *unused)
+{
+ struct rvu *rvu;
+ int blkaddr;
+ u64 reg;
+
+ rvu = filp->private;
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, 0);
+ if (blkaddr < 0)
+ return -ENODEV;
+
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_INST_REQ_PC);
+ seq_printf(filp, "CPT instruction requests %llu\n", reg);
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_INST_LATENCY_PC);
+ seq_printf(filp, "CPT instruction latency %llu\n", reg);
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_RD_REQ_PC);
+ seq_printf(filp, "CPT NCB read requests %llu\n", reg);
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_RD_LATENCY_PC);
+ seq_printf(filp, "CPT NCB read latency %llu\n", reg);
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_RD_UC_PC);
+ seq_printf(filp, "CPT read requests caused by UC fills %llu\n", reg);
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_ACTIVE_CYCLES_PC);
+ seq_printf(filp, "CPT active cycles pc %llu\n", reg);
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_CPTCLK_CNT);
+ seq_printf(filp, "CPT clock count pc %llu\n", reg);
+
+ return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(cpt_pc, cpt_pc_display, NULL);
+
+static void rvu_dbg_cpt_init(struct rvu *rvu)
+{
+ if (!is_block_implemented(rvu->hw, BLKADDR_CPT0))
+ return;
+
+ rvu->rvu_dbg.cpt = debugfs_create_dir("cpt", rvu->rvu_dbg.root);
+
+ debugfs_create_file("cpt_pc", 0600, rvu->rvu_dbg.cpt, rvu,
+ &rvu_dbg_cpt_pc_fops);
+ debugfs_create_file("cpt_ae_sts", 0600, rvu->rvu_dbg.cpt, rvu,
+ &rvu_dbg_cpt_ae_sts_fops);
+ debugfs_create_file("cpt_se_sts", 0600, rvu->rvu_dbg.cpt, rvu,
+ &rvu_dbg_cpt_se_sts_fops);
+ debugfs_create_file("cpt_ie_sts", 0600, rvu->rvu_dbg.cpt, rvu,
+ &rvu_dbg_cpt_ie_sts_fops);
+ debugfs_create_file("cpt_engines_info", 0600, rvu->rvu_dbg.cpt, rvu,
+ &rvu_dbg_cpt_engines_info_fops);
+ debugfs_create_file("cpt_lfs_info", 0600, rvu->rvu_dbg.cpt, rvu,
+ &rvu_dbg_cpt_lfs_info_fops);
+ debugfs_create_file("cpt_err_info", 0600, rvu->rvu_dbg.cpt, rvu,
+ &rvu_dbg_cpt_err_info_fops);
+}
+
+void rvu_dbg_init(struct rvu *rvu)
+{
+ rvu->rvu_dbg.root = debugfs_create_dir(DEBUGFS_DIR_NAME, NULL);
+
+ debugfs_create_file("rsrc_alloc", 0444, rvu->rvu_dbg.root, rvu,
+ &rvu_dbg_rsrc_status_fops);
+ debugfs_create_file("rvu_pf_cgx_map", 0444, rvu->rvu_dbg.root, rvu,
+ &rvu_dbg_rvu_pf_cgx_map_fops);
rvu_dbg_npa_init(rvu);
- rvu_dbg_nix_init(rvu);
+ rvu_dbg_nix_init(rvu, BLKADDR_NIX0);
+
+ rvu_dbg_nix_init(rvu, BLKADDR_NIX1);
rvu_dbg_cgx_init(rvu);
rvu_dbg_npc_init(rvu);
-
- return;
-
-create_failed:
- dev_err(dev, "Failed to create debugfs dir\n");
- debugfs_remove_recursive(rvu->rvu_dbg.root);
+ rvu_dbg_cpt_init(rvu);
}
void rvu_dbg_exit(struct rvu *rvu)
#include "npc.h"
#include "cgx.h"
+static void nix_free_tx_vtag_entries(struct rvu *rvu, u16 pcifunc);
static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req,
int type, int chan_id);
u16 pcifunc;
};
+int rvu_get_next_nix_blkaddr(struct rvu *rvu, int blkaddr)
+{
+ int i = 0;
+
+ /*If blkaddr is 0, return the first nix block address*/
+ if (blkaddr == 0)
+ return rvu->nix_blkaddr[blkaddr];
+
+ while (i + 1 < MAX_NIX_BLKS) {
+ if (rvu->nix_blkaddr[i] == blkaddr)
+ return rvu->nix_blkaddr[i + 1];
+ i++;
+ }
+
+ return 0;
+}
+
bool is_nixlf_attached(struct rvu *rvu, u16 pcifunc)
{
struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
int rvu_get_nixlf_count(struct rvu *rvu)
{
+ int blkaddr = 0, max = 0;
struct rvu_block *block;
- int blkaddr;
- blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, 0);
- if (blkaddr < 0)
- return 0;
- block = &rvu->hw->block[blkaddr];
- return block->lf.max;
+ blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr);
+ while (blkaddr) {
+ block = &rvu->hw->block[blkaddr];
+ max += block->lf.max;
+ blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr);
+ }
+ return max;
}
int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr)
return idx;
}
-static inline struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr)
+struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr)
{
- if (blkaddr == BLKADDR_NIX0 && hw->nix0)
- return hw->nix0;
+ int nix_blkaddr = 0, i = 0;
+ struct rvu *rvu = hw->rvu;
+ nix_blkaddr = rvu_get_next_nix_blkaddr(rvu, nix_blkaddr);
+ while (nix_blkaddr) {
+ if (blkaddr == nix_blkaddr && hw->nix)
+ return &hw->nix[i];
+ nix_blkaddr = rvu_get_next_nix_blkaddr(rvu, nix_blkaddr);
+ i++;
+ }
return NULL;
}
static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
{
struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+ int pkind, pf, vf, lbkid;
u8 cgx_id, lmac_id;
- int pkind, pf, vf;
int err;
pf = rvu_get_pf(pcifunc);
case NIX_INTF_TYPE_LBK:
vf = (pcifunc & RVU_PFVF_FUNC_MASK) - 1;
+ /* If NIX1 block is present on the silicon then NIXes are
+ * assigned alternatively for lbk interfaces. NIX0 should
+ * send packets on lbk link 1 channels and NIX1 should send
+ * on lbk link 0 channels for the communication between
+ * NIX0 and NIX1.
+ */
+ lbkid = 0;
+ if (rvu->hw->lbk_links > 1)
+ lbkid = vf & 0x1 ? 0 : 1;
+
/* Note that AF's VFs work in pairs and talk over consecutive
* loopback channels.Therefore if odd number of AF VFs are
* enabled then the last VF remains with no pair.
*/
- pfvf->rx_chan_base = NIX_CHAN_LBK_CHX(0, vf);
- pfvf->tx_chan_base = vf & 0x1 ? NIX_CHAN_LBK_CHX(0, vf - 1) :
- NIX_CHAN_LBK_CHX(0, vf + 1);
+ pfvf->rx_chan_base = NIX_CHAN_LBK_CHX(lbkid, vf);
+ pfvf->tx_chan_base = vf & 0x1 ?
+ NIX_CHAN_LBK_CHX(lbkid, vf - 1) :
+ NIX_CHAN_LBK_CHX(lbkid, vf + 1);
pfvf->rx_chan_cnt = 1;
pfvf->tx_chan_cnt = 1;
rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
pfvf->maxlen = 0;
pfvf->minlen = 0;
- pfvf->rxvlan = false;
/* Remove this PF_FUNC from bcast pkt replication list */
err = nix_update_bcast_mce_list(rvu, pcifunc, false);
return 0;
}
-static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
- struct nix_aq_enq_rsp *rsp)
+static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
+ struct nix_aq_enq_req *req,
+ struct nix_aq_enq_rsp *rsp)
{
struct rvu_hwinfo *hw = rvu->hw;
u16 pcifunc = req->hdr.pcifunc;
bool ena;
u64 cfg;
- blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
- if (blkaddr < 0)
- return NIX_AF_ERR_AF_LF_INVALID;
-
+ blkaddr = nix_hw->blkaddr;
block = &hw->block[blkaddr];
aq = block->aq;
if (!aq) {
break;
case NIX_AQ_CTYPE_MCE:
cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_MCAST_CFG);
+
/* Check if index exceeds MCE list length */
- if (!hw->nix0->mcast.mce_ctx ||
+ if (!nix_hw->mcast.mce_ctx ||
(req->qidx >= (256UL << (cfg & 0xF))))
rc = NIX_AF_ERR_AQ_ENQUEUE;
return 0;
}
+static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
+ struct nix_aq_enq_rsp *rsp)
+{
+ struct nix_hw *nix_hw;
+ int blkaddr;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, req->hdr.pcifunc);
+ if (blkaddr < 0)
+ return NIX_AF_ERR_AF_LF_INVALID;
+
+ nix_hw = get_nix_hw(rvu->hw, blkaddr);
+ if (!nix_hw)
+ return -EINVAL;
+
+ return rvu_nix_blk_aq_enq_inst(rvu, nix_hw, req, rsp);
+}
+
static const char *nix_get_ctx_name(int ctype)
{
switch (ctype) {
/* Config Rx pkt length, csum checks and apad enable / disable */
rvu_write64(rvu, blkaddr, NIX_AF_LFX_RX_CFG(nixlf), req->rx_cfg);
+ /* Configure pkind for TX parse config */
+ cfg = NPC_TX_DEF_PKIND;
+ rvu_write64(rvu, blkaddr, NIX_AF_LFX_TX_PARSE_CFG(nixlf), cfg);
+
intf = is_afvf(pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
err = nix_interface_init(rvu, pcifunc, intf, nixlf);
if (err)
/* Disable NPC entries as NIXLF's contexts are not initialized yet */
rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
+ /* Configure RX VTAG Type 7 (strip) for vf vlan */
+ rvu_write64(rvu, blkaddr,
+ NIX_AF_LFX_RX_VTAG_TYPEX(nixlf, NIX_AF_LFX_RX_VTAG_TYPE7),
+ VTAGSIZE_T4 | VTAG_STRIP);
+
goto exit;
free_mem:
cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST2);
rsp->qints = ((cfg >> 12) & 0xFFF);
rsp->cints = ((cfg >> 24) & 0xFFF);
+ rsp->cgx_links = hw->cgx_links;
+ rsp->lbk_links = hw->lbk_links;
+ rsp->sdp_links = hw->sdp_links;
+
return rc;
}
-int rvu_mbox_handler_nix_lf_free(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_nix_lf_free(struct rvu *rvu, struct nix_lf_free_req *req,
struct msg_rsp *rsp)
{
struct rvu_hwinfo *hw = rvu->hw;
if (nixlf < 0)
return NIX_AF_ERR_AF_LF_INVALID;
+ if (req->flags & NIX_LF_DISABLE_FLOWS)
+ rvu_npc_disable_mcam_entries(rvu, pcifunc, nixlf);
+ else
+ rvu_npc_free_mcam_entries(rvu, pcifunc, nixlf);
+
+ /* Free any tx vtag def entries used by this NIX LF */
+ if (!(req->flags & NIX_LF_DONT_FREE_TX_VTAG))
+ nix_free_tx_vtag_entries(rvu, pcifunc);
+
nix_interface_deinit(rvu, pcifunc, nixlf);
/* Reset this NIX LF */
{
u64 regval = req->vtag_size;
- if (req->rx.vtag_type > 7 || req->vtag_size > VTAGSIZE_T8)
+ if (req->rx.vtag_type > NIX_AF_LFX_RX_VTAG_TYPE7 ||
+ req->vtag_size > VTAGSIZE_T8)
return -EINVAL;
+ /* RX VTAG Type 7 reserved for vf vlan */
+ if (req->rx.vtag_type == NIX_AF_LFX_RX_VTAG_TYPE7)
+ return NIX_AF_ERR_RX_VTAG_INUSE;
+
if (req->rx.capture_vtag)
regval |= BIT_ULL(5);
if (req->rx.strip_vtag)
return 0;
}
+static int nix_tx_vtag_free(struct rvu *rvu, int blkaddr,
+ u16 pcifunc, int index)
+{
+ struct nix_hw *nix_hw = get_nix_hw(rvu->hw, blkaddr);
+ struct nix_txvlan *vlan = &nix_hw->txvlan;
+
+ if (vlan->entry2pfvf_map[index] != pcifunc)
+ return NIX_AF_ERR_PARAM;
+
+ rvu_write64(rvu, blkaddr,
+ NIX_AF_TX_VTAG_DEFX_DATA(index), 0x0ull);
+ rvu_write64(rvu, blkaddr,
+ NIX_AF_TX_VTAG_DEFX_CTL(index), 0x0ull);
+
+ vlan->entry2pfvf_map[index] = 0;
+ rvu_free_rsrc(&vlan->rsrc, index);
+
+ return 0;
+}
+
+static void nix_free_tx_vtag_entries(struct rvu *rvu, u16 pcifunc)
+{
+ struct nix_txvlan *vlan;
+ struct nix_hw *nix_hw;
+ int index, blkaddr;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+ if (blkaddr < 0)
+ return;
+
+ nix_hw = get_nix_hw(rvu->hw, blkaddr);
+ vlan = &nix_hw->txvlan;
+
+ mutex_lock(&vlan->rsrc_lock);
+ /* Scan all the entries and free the ones mapped to 'pcifunc' */
+ for (index = 0; index < vlan->rsrc.max; index++) {
+ if (vlan->entry2pfvf_map[index] == pcifunc)
+ nix_tx_vtag_free(rvu, blkaddr, pcifunc, index);
+ }
+ mutex_unlock(&vlan->rsrc_lock);
+}
+
+static int nix_tx_vtag_alloc(struct rvu *rvu, int blkaddr,
+ u64 vtag, u8 size)
+{
+ struct nix_hw *nix_hw = get_nix_hw(rvu->hw, blkaddr);
+ struct nix_txvlan *vlan = &nix_hw->txvlan;
+ u64 regval;
+ int index;
+
+ mutex_lock(&vlan->rsrc_lock);
+
+ index = rvu_alloc_rsrc(&vlan->rsrc);
+ if (index < 0) {
+ mutex_unlock(&vlan->rsrc_lock);
+ return index;
+ }
+
+ mutex_unlock(&vlan->rsrc_lock);
+
+ regval = size ? vtag : vtag << 32;
+
+ rvu_write64(rvu, blkaddr,
+ NIX_AF_TX_VTAG_DEFX_DATA(index), regval);
+ rvu_write64(rvu, blkaddr,
+ NIX_AF_TX_VTAG_DEFX_CTL(index), size);
+
+ return index;
+}
+
+static int nix_tx_vtag_decfg(struct rvu *rvu, int blkaddr,
+ struct nix_vtag_config *req)
+{
+ struct nix_hw *nix_hw = get_nix_hw(rvu->hw, blkaddr);
+ struct nix_txvlan *vlan = &nix_hw->txvlan;
+ u16 pcifunc = req->hdr.pcifunc;
+ int idx0 = req->tx.vtag0_idx;
+ int idx1 = req->tx.vtag1_idx;
+ int err = 0;
+
+ if (req->tx.free_vtag0 && req->tx.free_vtag1)
+ if (vlan->entry2pfvf_map[idx0] != pcifunc ||
+ vlan->entry2pfvf_map[idx1] != pcifunc)
+ return NIX_AF_ERR_PARAM;
+
+ mutex_lock(&vlan->rsrc_lock);
+
+ if (req->tx.free_vtag0) {
+ err = nix_tx_vtag_free(rvu, blkaddr, pcifunc, idx0);
+ if (err)
+ goto exit;
+ }
+
+ if (req->tx.free_vtag1)
+ err = nix_tx_vtag_free(rvu, blkaddr, pcifunc, idx1);
+
+exit:
+ mutex_unlock(&vlan->rsrc_lock);
+ return err;
+}
+
+static int nix_tx_vtag_cfg(struct rvu *rvu, int blkaddr,
+ struct nix_vtag_config *req,
+ struct nix_vtag_config_rsp *rsp)
+{
+ struct nix_hw *nix_hw = get_nix_hw(rvu->hw, blkaddr);
+ struct nix_txvlan *vlan = &nix_hw->txvlan;
+ u16 pcifunc = req->hdr.pcifunc;
+
+ if (req->tx.cfg_vtag0) {
+ rsp->vtag0_idx =
+ nix_tx_vtag_alloc(rvu, blkaddr,
+ req->tx.vtag0, req->vtag_size);
+
+ if (rsp->vtag0_idx < 0)
+ return NIX_AF_ERR_TX_VTAG_NOSPC;
+
+ vlan->entry2pfvf_map[rsp->vtag0_idx] = pcifunc;
+ }
+
+ if (req->tx.cfg_vtag1) {
+ rsp->vtag1_idx =
+ nix_tx_vtag_alloc(rvu, blkaddr,
+ req->tx.vtag1, req->vtag_size);
+
+ if (rsp->vtag1_idx < 0)
+ goto err_free;
+
+ vlan->entry2pfvf_map[rsp->vtag1_idx] = pcifunc;
+ }
+
+ return 0;
+
+err_free:
+ if (req->tx.cfg_vtag0)
+ nix_tx_vtag_free(rvu, blkaddr, pcifunc, rsp->vtag0_idx);
+
+ return NIX_AF_ERR_TX_VTAG_NOSPC;
+}
+
int rvu_mbox_handler_nix_vtag_cfg(struct rvu *rvu,
struct nix_vtag_config *req,
- struct msg_rsp *rsp)
+ struct nix_vtag_config_rsp *rsp)
{
u16 pcifunc = req->hdr.pcifunc;
int blkaddr, nixlf, err;
return err;
if (req->cfg_type) {
+ /* rx vtag configuration */
err = nix_rx_vtag_cfg(rvu, nixlf, blkaddr, req);
if (err)
return NIX_AF_ERR_PARAM;
} else {
- /* TODO: handle tx vtag configuration */
- return 0;
+ /* tx vtag configuration */
+ if ((req->tx.cfg_vtag0 || req->tx.cfg_vtag1) &&
+ (req->tx.free_vtag0 || req->tx.free_vtag1))
+ return NIX_AF_ERR_PARAM;
+
+ if (req->tx.cfg_vtag0 || req->tx.cfg_vtag1)
+ return nix_tx_vtag_cfg(rvu, blkaddr, req, rsp);
+
+ if (req->tx.free_vtag0 || req->tx.free_vtag1)
+ return nix_tx_vtag_decfg(rvu, blkaddr, req);
}
return 0;
}
-static int nix_setup_mce(struct rvu *rvu, int mce, u8 op,
- u16 pcifunc, int next, bool eol)
+static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw,
+ int mce, u8 op, u16 pcifunc, int next, bool eol)
{
struct nix_aq_enq_req aq_req;
int err;
/* All fields valid */
*(u64 *)(&aq_req.mce_mask) = ~0ULL;
- err = rvu_nix_aq_enq_inst(rvu, &aq_req, NULL);
+ err = rvu_nix_blk_aq_enq_inst(rvu, nix_hw, &aq_req, NULL);
if (err) {
dev_err(rvu->dev, "Failed to setup Bcast MCE for PF%d:VF%d\n",
rvu_get_pf(pcifunc), pcifunc & RVU_PFVF_FUNC_MASK);
next_idx = idx + 1;
/* EOL should be set in last MCE */
- err = nix_setup_mce(rvu, idx, NIX_AQ_INSTOP_WRITE,
- mce->pcifunc, next_idx,
- (next_idx > last_idx) ? true : false);
+ err = nix_blk_setup_mce(rvu, nix_hw, idx, NIX_AQ_INSTOP_WRITE,
+ mce->pcifunc, next_idx,
+ (next_idx > last_idx) ? true : false);
if (err)
goto end;
idx++;
numvfs = (cfg >> 12) & 0xFF;
pfvf = &rvu->pf[pf];
+
+ /* This NIX0/1 block mapped to PF ? */
+ if (pfvf->nix_blkaddr != nix_hw->blkaddr)
+ continue;
+
/* Save the start MCE */
pfvf->bcast_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1);
* Will be updated when a NIXLF is attached/detached to
* these PF/VFs.
*/
- err = nix_setup_mce(rvu, pfvf->bcast_mce_idx + idx,
- NIX_AQ_INSTOP_INIT,
- pcifunc, 0, true);
+ err = nix_blk_setup_mce(rvu, nix_hw,
+ pfvf->bcast_mce_idx + idx,
+ NIX_AQ_INSTOP_INIT,
+ pcifunc, 0, true);
if (err)
return err;
}
return nix_setup_bcast_tables(rvu, nix_hw);
}
+static int nix_setup_txvlan(struct rvu *rvu, struct nix_hw *nix_hw)
+{
+ struct nix_txvlan *vlan = &nix_hw->txvlan;
+ int err;
+
+ /* Allocate resource bimap for tx vtag def registers*/
+ vlan->rsrc.max = NIX_TX_VTAG_DEF_MAX;
+ err = rvu_alloc_bitmap(&vlan->rsrc);
+ if (err)
+ return -ENOMEM;
+
+ /* Alloc memory for saving entry to RVU PFFUNC allocation mapping */
+ vlan->entry2pfvf_map = devm_kcalloc(rvu->dev, vlan->rsrc.max,
+ sizeof(u16), GFP_KERNEL);
+ if (!vlan->entry2pfvf_map)
+ goto free_mem;
+
+ mutex_init(&vlan->rsrc_lock);
+ return 0;
+
+free_mem:
+ kfree(vlan->rsrc.bmap);
+ return -ENOMEM;
+}
+
static int nix_setup_txschq(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
{
struct nix_txsch *txsch;
/* This should be set to 1, when SEL_CHAN is set */
field->bytesm1 = 1;
break;
+ case NIX_FLOW_KEY_TYPE_IPV4_PROTO:
+ field->lid = NPC_LID_LC;
+ field->hdr_offset = 9; /* offset */
+ field->bytesm1 = 0; /* 1 byte */
+ field->ltype_match = NPC_LT_LC_IP;
+ field->ltype_mask = 0xF;
+ break;
case NIX_FLOW_KEY_TYPE_IPV4:
case NIX_FLOW_KEY_TYPE_INNR_IPV4:
field->lid = NPC_LID_LC;
struct nix_set_mac_addr *req,
struct msg_rsp *rsp)
{
+ bool from_vf = req->hdr.pcifunc & RVU_PFVF_FUNC_MASK;
u16 pcifunc = req->hdr.pcifunc;
int blkaddr, nixlf, err;
struct rvu_pfvf *pfvf;
pfvf = rvu_get_pfvf(rvu, pcifunc);
+ /* VF can't overwrite admin(PF) changes */
+ if (from_vf && pfvf->pf_set_vf_cfg)
+ return -EPERM;
+
ether_addr_copy(pfvf->mac_addr, req->mac_addr);
rvu_npc_install_ucast_entry(rvu, pcifunc, nixlf,
pfvf->rx_chan_base, req->mac_addr);
- rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
-
return 0;
}
else
rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
pfvf->rx_chan_base, allmulti);
-
- rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
-
return 0;
}
return 0;
}
-int rvu_mbox_handler_nix_rxvlan_alloc(struct rvu *rvu, struct msg_req *req,
- struct msg_rsp *rsp)
-{
- struct npc_mcam_alloc_entry_req alloc_req = { };
- struct npc_mcam_alloc_entry_rsp alloc_rsp = { };
- struct npc_mcam_free_entry_req free_req = { };
- u16 pcifunc = req->hdr.pcifunc;
- int blkaddr, nixlf, err;
- struct rvu_pfvf *pfvf;
-
- /* LBK VFs do not have separate MCAM UCAST entry hence
- * skip allocating rxvlan for them
- */
- if (is_afvf(pcifunc))
- return 0;
-
- pfvf = rvu_get_pfvf(rvu, pcifunc);
- if (pfvf->rxvlan)
- return 0;
-
- /* alloc new mcam entry */
- alloc_req.hdr.pcifunc = pcifunc;
- alloc_req.count = 1;
-
- err = rvu_mbox_handler_npc_mcam_alloc_entry(rvu, &alloc_req,
- &alloc_rsp);
- if (err)
- return err;
-
- /* update entry to enable rxvlan offload */
- blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
- if (blkaddr < 0) {
- err = NIX_AF_ERR_AF_LF_INVALID;
- goto free_entry;
- }
-
- nixlf = rvu_get_lf(rvu, &rvu->hw->block[blkaddr], pcifunc, 0);
- if (nixlf < 0) {
- err = NIX_AF_ERR_AF_LF_INVALID;
- goto free_entry;
- }
-
- pfvf->rxvlan_index = alloc_rsp.entry_list[0];
- /* all it means is that rxvlan_index is valid */
- pfvf->rxvlan = true;
-
- err = rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
- if (err)
- goto free_entry;
-
- return 0;
-free_entry:
- free_req.hdr.pcifunc = pcifunc;
- free_req.entry = alloc_rsp.entry_list[0];
- rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, rsp);
- pfvf->rxvlan = false;
- return err;
-}
-
int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req,
struct msg_rsp *rsp)
{
return 0;
}
-int rvu_nix_init(struct rvu *rvu)
+static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw)
{
const struct npc_lt_def_cfg *ltdefs;
struct rvu_hwinfo *hw = rvu->hw;
+ int blkaddr = nix_hw->blkaddr;
struct rvu_block *block;
- int blkaddr, err;
+ int err;
u64 cfg;
- blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, 0);
- if (blkaddr < 0)
- return 0;
block = &hw->block[blkaddr];
if (is_rvu_96xx_B0(rvu)) {
hw->cgx = (cfg >> 12) & 0xF;
hw->lmac_per_cgx = (cfg >> 8) & 0xF;
hw->cgx_links = hw->cgx * hw->lmac_per_cgx;
- hw->lbk_links = 1;
+ hw->lbk_links = (cfg >> 24) & 0xF;
hw->sdp_links = 1;
/* Initialize admin queue */
/* Restore CINT timer delay to HW reset values */
rvu_write64(rvu, blkaddr, NIX_AF_CINT_DELAY, 0x0ULL);
- if (blkaddr == BLKADDR_NIX0) {
- hw->nix0 = devm_kzalloc(rvu->dev,
- sizeof(struct nix_hw), GFP_KERNEL);
- if (!hw->nix0)
- return -ENOMEM;
+ if (is_block_implemented(hw, blkaddr)) {
+ err = nix_setup_txschq(rvu, nix_hw, blkaddr);
+ if (err)
+ return err;
- err = nix_setup_txschq(rvu, hw->nix0, blkaddr);
+ err = nix_af_mark_format_setup(rvu, nix_hw, blkaddr);
if (err)
return err;
- err = nix_af_mark_format_setup(rvu, hw->nix0, blkaddr);
+ err = nix_setup_mcast(rvu, nix_hw, blkaddr);
if (err)
return err;
- err = nix_setup_mcast(rvu, hw->nix0, blkaddr);
+ err = nix_setup_txvlan(rvu, nix_hw);
if (err)
return err;
/* Configure segmentation offload formats */
- nix_setup_lso(rvu, hw->nix0, blkaddr);
+ nix_setup_lso(rvu, nix_hw, blkaddr);
/* Config Outer/Inner L2, IP, TCP, UDP and SCTP NPC layer info.
* This helps HW protocol checker to identify headers
return 0;
}
-void rvu_nix_freemem(struct rvu *rvu)
+int rvu_nix_init(struct rvu *rvu)
{
struct rvu_hwinfo *hw = rvu->hw;
- struct rvu_block *block;
+ struct nix_hw *nix_hw;
+ int blkaddr = 0, err;
+ int i = 0;
+
+ hw->nix = devm_kcalloc(rvu->dev, MAX_NIX_BLKS, sizeof(struct nix_hw),
+ GFP_KERNEL);
+ if (!hw->nix)
+ return -ENOMEM;
+
+ blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr);
+ while (blkaddr) {
+ nix_hw = &hw->nix[i];
+ nix_hw->rvu = rvu;
+ nix_hw->blkaddr = blkaddr;
+ err = rvu_nix_block_init(rvu, nix_hw);
+ if (err)
+ return err;
+ blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr);
+ i++;
+ }
+
+ return 0;
+}
+
+static void rvu_nix_block_freemem(struct rvu *rvu, int blkaddr,
+ struct rvu_block *block)
+{
struct nix_txsch *txsch;
struct nix_mcast *mcast;
+ struct nix_txvlan *vlan;
struct nix_hw *nix_hw;
- int blkaddr, lvl;
+ int lvl;
- blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, 0);
- if (blkaddr < 0)
- return;
-
- block = &hw->block[blkaddr];
rvu_aq_free(rvu, block->aq);
- if (blkaddr == BLKADDR_NIX0) {
+ if (is_block_implemented(rvu->hw, blkaddr)) {
nix_hw = get_nix_hw(rvu->hw, blkaddr);
if (!nix_hw)
return;
kfree(txsch->schq.bmap);
}
+ vlan = &nix_hw->txvlan;
+ kfree(vlan->rsrc.bmap);
+ mutex_destroy(&vlan->rsrc_lock);
+ devm_kfree(rvu->dev, vlan->entry2pfvf_map);
+
mcast = &nix_hw->mcast;
qmem_free(rvu->dev, mcast->mce_ctx);
qmem_free(rvu->dev, mcast->mcast_buf);
}
}
+void rvu_nix_freemem(struct rvu *rvu)
+{
+ struct rvu_hwinfo *hw = rvu->hw;
+ struct rvu_block *block;
+ int blkaddr = 0;
+
+ blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr);
+ while (blkaddr) {
+ block = &hw->block[blkaddr];
+ rvu_nix_block_freemem(rvu, blkaddr, block);
+ blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr);
+ }
+}
+
int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
struct msg_rsp *rsp)
{
rvu_npc_enable_default_entries(rvu, pcifunc, nixlf);
+ npc_mcam_enable_flows(rvu, pcifunc);
+
return rvu_cgx_start_stop_io(rvu, pcifunc, true);
}
rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
+ npc_mcam_disable_flows(rvu, pcifunc);
+
return rvu_cgx_start_stop_io(rvu, pcifunc, false);
}
ctx_req.hdr.pcifunc = pcifunc;
/* Cleanup NPC MCAM entries, free Tx scheduler queues being used */
+ rvu_npc_disable_mcam_entries(rvu, pcifunc, nixlf);
+ rvu_npc_free_mcam_entries(rvu, pcifunc, nixlf);
nix_interface_deinit(rvu, pcifunc, nixlf);
nix_rx_sync(rvu, blkaddr);
nix_txschq_free(rvu, pcifunc);
return 0;
}
+
+void rvu_nix_reset_mac(struct rvu_pfvf *pfvf, int pcifunc)
+{
+ bool from_vf = !!(pcifunc & RVU_PFVF_FUNC_MASK);
+
+ /* overwrite vf mac address with default_mac */
+ if (from_vf)
+ ether_addr_copy(pfvf->mac_addr, pfvf->default_mac);
+}
#define NPC_PARSE_RESULT_DMAC_OFFSET 8
#define NPC_HW_TSTAMP_OFFSET 8
+#define NPC_KEX_CHAN_MASK 0xFFFULL
+#define NPC_KEX_PF_FUNC_MASK 0xFFFFULL
static const char def_pfl_name[] = "default";
static void npc_mcam_free_all_counters(struct rvu *rvu, struct npc_mcam *mcam,
u16 pcifunc);
+bool is_npc_intf_tx(u8 intf)
+{
+ return !!(intf & 0x1);
+}
+
+bool is_npc_intf_rx(u8 intf)
+{
+ return !(intf & 0x1);
+}
+
+bool is_npc_interface_valid(struct rvu *rvu, u8 intf)
+{
+ struct rvu_hwinfo *hw = rvu->hw;
+
+ return intf < hw->npc_intfs;
+}
+
+int rvu_npc_get_tx_nibble_cfg(struct rvu *rvu, u64 nibble_ena)
+{
+ /* Due to a HW issue in these silicon versions, parse nibble enable
+ * configuration has to be identical for both Rx and Tx interfaces.
+ */
+ if (is_rvu_96xx_B0(rvu))
+ return nibble_ena;
+ return 0;
+}
+
+static int npc_mcam_verify_pf_func(struct rvu *rvu,
+ struct mcam_entry *entry_data, u8 intf,
+ u16 pcifunc)
+{
+ u16 pf_func, pf_func_mask;
+
+ if (is_npc_intf_rx(intf))
+ return 0;
+
+ pf_func_mask = (entry_data->kw_mask[0] >> 32) &
+ NPC_KEX_PF_FUNC_MASK;
+ pf_func = (entry_data->kw[0] >> 32) & NPC_KEX_PF_FUNC_MASK;
+
+ pf_func = be16_to_cpu((__force __be16)pf_func);
+ if (pf_func_mask != NPC_KEX_PF_FUNC_MASK ||
+ ((pf_func & ~RVU_PFVF_FUNC_MASK) !=
+ (pcifunc & ~RVU_PFVF_FUNC_MASK)))
+ return -EINVAL;
+
+ return 0;
+}
+
+int npc_mcam_verify_channel(struct rvu *rvu, u16 pcifunc, u8 intf, u16 channel)
+{
+ int pf = rvu_get_pf(pcifunc);
+ u8 cgx_id, lmac_id;
+ int base = 0, end;
+
+ if (is_npc_intf_tx(intf))
+ return 0;
+
+ if (is_afvf(pcifunc)) {
+ end = rvu_get_num_lbk_chans();
+ if (end < 0)
+ return -EINVAL;
+ } else {
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ base = NIX_CHAN_CGX_LMAC_CHX(cgx_id, lmac_id, 0x0);
+ /* CGX mapped functions has maximum of 16 channels */
+ end = NIX_CHAN_CGX_LMAC_CHX(cgx_id, lmac_id, 0xF);
+ }
+
+ if (channel < base || channel > end)
+ return -EINVAL;
+
+ return 0;
+}
+
void rvu_npc_set_pkind(struct rvu *rvu, int pkind, struct rvu_pfvf *pfvf)
{
int blkaddr;
return 0;
}
+static int npc_get_ucast_mcam_index(struct npc_mcam *mcam, u16 pcifunc,
+ int nixlf)
+{
+ struct rvu_hwinfo *hw = container_of(mcam, struct rvu_hwinfo, mcam);
+ struct rvu *rvu = hw->rvu;
+ int blkaddr = 0, max = 0;
+ struct rvu_block *block;
+ struct rvu_pfvf *pfvf;
+
+ pfvf = rvu_get_pfvf(rvu, pcifunc);
+ /* Given a PF/VF and NIX LF number calculate the unicast mcam
+ * entry index based on the NIX block assigned to the PF/VF.
+ */
+ blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr);
+ while (blkaddr) {
+ if (pfvf->nix_blkaddr == blkaddr)
+ break;
+ block = &rvu->hw->block[blkaddr];
+ max += block->lf.max;
+ blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr);
+ }
+
+ return mcam->nixlf_offset + (max + nixlf) * RSVD_MCAM_ENTRIES_PER_NIXLF;
+}
+
static int npc_get_nixlf_mcam_index(struct npc_mcam *mcam,
u16 pcifunc, int nixlf, int type)
{
return index + 1;
}
- return (mcam->nixlf_offset + (nixlf * RSVD_MCAM_ENTRIES_PER_NIXLF));
+ return npc_get_ucast_mcam_index(mcam, pcifunc, nixlf);
}
-static int npc_get_bank(struct npc_mcam *mcam, int index)
+int npc_get_bank(struct npc_mcam *mcam, int index)
{
int bank = index / mcam->banksize;
return (cfg & 1);
}
-static void npc_enable_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
- int blkaddr, int index, bool enable)
+void npc_enable_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
+ int blkaddr, int index, bool enable)
{
int bank = npc_get_bank(mcam, index);
int actbank = bank;
*cam0 = ~*cam1 & kw_mask;
}
+static void npc_fill_entryword(struct mcam_entry *entry, int idx,
+ u64 cam0, u64 cam1)
+{
+ /* Similar to npc_get_keyword, but fills mcam_entry structure from
+ * CAM registers.
+ */
+ switch (idx) {
+ case 0:
+ entry->kw[0] = cam1;
+ entry->kw_mask[0] = cam1 ^ cam0;
+ break;
+ case 1:
+ entry->kw[1] = cam1;
+ entry->kw_mask[1] = cam1 ^ cam0;
+ break;
+ case 2:
+ entry->kw[1] |= (cam1 & CAM_MASK(16)) << 48;
+ entry->kw[2] = (cam1 >> 16) & CAM_MASK(48);
+ entry->kw_mask[1] |= ((cam1 ^ cam0) & CAM_MASK(16)) << 48;
+ entry->kw_mask[2] = ((cam1 ^ cam0) >> 16) & CAM_MASK(48);
+ break;
+ case 3:
+ entry->kw[2] |= (cam1 & CAM_MASK(16)) << 48;
+ entry->kw[3] = (cam1 >> 16) & CAM_MASK(32);
+ entry->kw_mask[2] |= ((cam1 ^ cam0) & CAM_MASK(16)) << 48;
+ entry->kw_mask[3] = ((cam1 ^ cam0) >> 16) & CAM_MASK(32);
+ break;
+ case 4:
+ entry->kw[3] |= (cam1 & CAM_MASK(32)) << 32;
+ entry->kw[4] = (cam1 >> 32) & CAM_MASK(32);
+ entry->kw_mask[3] |= ((cam1 ^ cam0) & CAM_MASK(32)) << 32;
+ entry->kw_mask[4] = ((cam1 ^ cam0) >> 32) & CAM_MASK(32);
+ break;
+ case 5:
+ entry->kw[4] |= (cam1 & CAM_MASK(32)) << 32;
+ entry->kw[5] = (cam1 >> 32) & CAM_MASK(16);
+ entry->kw_mask[4] |= ((cam1 ^ cam0) & CAM_MASK(32)) << 32;
+ entry->kw_mask[5] = ((cam1 ^ cam0) >> 32) & CAM_MASK(16);
+ break;
+ case 6:
+ entry->kw[5] |= (cam1 & CAM_MASK(48)) << 16;
+ entry->kw[6] = (cam1 >> 48) & CAM_MASK(16);
+ entry->kw_mask[5] |= ((cam1 ^ cam0) & CAM_MASK(48)) << 16;
+ entry->kw_mask[6] = ((cam1 ^ cam0) >> 48) & CAM_MASK(16);
+ break;
+ case 7:
+ entry->kw[6] |= (cam1 & CAM_MASK(48)) << 16;
+ entry->kw_mask[6] |= ((cam1 ^ cam0) & CAM_MASK(48)) << 16;
+ break;
+ }
+}
+
+static void npc_get_default_entry_action(struct rvu *rvu, struct npc_mcam *mcam,
+ int blkaddr, int index,
+ struct mcam_entry *entry)
+{
+ u16 owner, target_func;
+ struct rvu_pfvf *pfvf;
+ int bank, nixlf;
+ u64 rx_action;
+
+ owner = mcam->entry2pfvf_map[index];
+ target_func = (entry->action >> 4) & 0xffff;
+ /* return incase target is PF or LBK or rule owner is not PF */
+ if (is_afvf(target_func) || (owner & RVU_PFVF_FUNC_MASK) ||
+ !(target_func & RVU_PFVF_FUNC_MASK))
+ return;
+
+ pfvf = rvu_get_pfvf(rvu, target_func);
+ mcam->entry2target_pffunc[index] = target_func;
+ /* return if nixlf is not attached or initialized */
+ if (!is_nixlf_attached(rvu, target_func) || !pfvf->def_ucast_rule)
+ return;
+
+ /* get VF ucast entry rule */
+ nix_get_nixlf(rvu, target_func, &nixlf, NULL);
+ index = npc_get_nixlf_mcam_index(mcam, target_func,
+ nixlf, NIXLF_UCAST_ENTRY);
+ bank = npc_get_bank(mcam, index);
+ index &= (mcam->banksize - 1);
+
+ rx_action = rvu_read64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_ACTION(index, bank));
+ if (rx_action)
+ entry->action = rx_action;
+}
+
static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
int blkaddr, int index, u8 intf,
struct mcam_entry *entry, bool enable)
NPC_AF_MCAMEX_BANKX_CAMX_W1(index, bank, 0), cam0);
}
+ /* copy VF default entry action to the VF mcam entry */
+ if (intf == NIX_INTF_RX && actindex < mcam->bmap_entries)
+ npc_get_default_entry_action(rvu, mcam, blkaddr, actindex,
+ entry);
+
/* Set 'action' */
rvu_write64(rvu, blkaddr,
NPC_AF_MCAMEX_BANKX_ACTION(index, actbank), entry->action);
npc_enable_mcam_entry(rvu, mcam, blkaddr, actindex, true);
}
+void npc_read_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
+ int blkaddr, u16 src,
+ struct mcam_entry *entry, u8 *intf, u8 *ena)
+{
+ int sbank = npc_get_bank(mcam, src);
+ int bank, kw = 0;
+ u64 cam0, cam1;
+
+ src &= (mcam->banksize - 1);
+ bank = sbank;
+
+ for (; bank < (sbank + mcam->banks_per_entry); bank++, kw = kw + 2) {
+ cam1 = rvu_read64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_CAMX_W0(src, bank, 1));
+ cam0 = rvu_read64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_CAMX_W0(src, bank, 0));
+ npc_fill_entryword(entry, kw, cam0, cam1);
+
+ cam1 = rvu_read64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_CAMX_W1(src, bank, 1));
+ cam0 = rvu_read64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_CAMX_W1(src, bank, 0));
+ npc_fill_entryword(entry, kw + 1, cam0, cam1);
+ }
+
+ entry->action = rvu_read64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_ACTION(src, sbank));
+ entry->vtag_action =
+ rvu_read64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_TAG_ACT(src, sbank));
+ *intf = rvu_read64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_CAMX_INTF(src, sbank, 1)) & 3;
+ *ena = rvu_read64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_CFG(src, sbank)) & 1;
+}
+
static void npc_copy_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
int blkaddr, u16 src, u16 dest)
{
int nixlf, u64 chan, u8 *mac_addr)
{
struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+ struct npc_install_flow_req req = { 0 };
+ struct npc_install_flow_rsp rsp = { 0 };
struct npc_mcam *mcam = &rvu->hw->mcam;
- struct mcam_entry entry = { {0} };
struct nix_rx_action action;
- int blkaddr, index, kwi;
- u64 mac = 0;
+ int blkaddr, index;
/* AF's VFs work in promiscuous mode */
if (is_afvf(pcifunc))
if (blkaddr < 0)
return;
- for (index = ETH_ALEN - 1; index >= 0; index--)
- mac |= ((u64)*mac_addr++) << (8 * index);
-
index = npc_get_nixlf_mcam_index(mcam, pcifunc,
nixlf, NIXLF_UCAST_ENTRY);
- /* Match ingress channel and DMAC */
- entry.kw[0] = chan;
- entry.kw_mask[0] = 0xFFFULL;
-
- kwi = NPC_PARSE_RESULT_DMAC_OFFSET / sizeof(u64);
- entry.kw[kwi] = mac;
- entry.kw_mask[kwi] = BIT_ULL(48) - 1;
-
/* Don't change the action if entry is already enabled
* Otherwise RSS action may get overwritten.
*/
action.pf_func = pcifunc;
}
- entry.action = *(u64 *)&action;
- npc_config_mcam_entry(rvu, mcam, blkaddr, index,
- NIX_INTF_RX, &entry, true);
-
- /* add VLAN matching, setup action and save entry back for later */
- entry.kw[0] |= (NPC_LT_LB_STAG_QINQ | NPC_LT_LB_CTAG) << 20;
- entry.kw_mask[0] |= (NPC_LT_LB_STAG_QINQ & NPC_LT_LB_CTAG) << 20;
+ req.default_rule = 1;
+ ether_addr_copy(req.packet.dmac, mac_addr);
+ eth_broadcast_addr((u8 *)&req.mask.dmac);
+ req.features = BIT_ULL(NPC_DMAC);
+ req.channel = chan;
+ req.intf = pfvf->nix_rx_intf;
+ req.op = action.op;
+ req.hdr.pcifunc = 0; /* AF is requester */
+ req.vf = action.pf_func;
+ req.index = action.index;
+ req.match_id = action.match_id;
+ req.flow_key_alg = action.flow_key_alg;
- entry.vtag_action = VTAG0_VALID_BIT |
- FIELD_PREP(VTAG0_TYPE_MASK, 0) |
- FIELD_PREP(VTAG0_LID_MASK, NPC_LID_LA) |
- FIELD_PREP(VTAG0_RELPTR_MASK, 12);
-
- memcpy(&pfvf->entry, &entry, sizeof(entry));
+ rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
}
void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
int nixlf, u64 chan, bool allmulti)
{
+ struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
struct npc_mcam *mcam = &rvu->hw->mcam;
int blkaddr, ucast_idx, index, kwi;
struct mcam_entry entry = { {0} };
entry.action = *(u64 *)&action;
npc_config_mcam_entry(rvu, mcam, blkaddr, index,
- NIX_INTF_RX, &entry, true);
+ pfvf->nix_rx_intf, &entry, true);
}
static void npc_enadis_promisc_entry(struct rvu *rvu, u16 pcifunc,
/* Get 'pcifunc' of PF device */
pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK;
+ pfvf = rvu_get_pfvf(rvu, pcifunc);
index = npc_get_nixlf_mcam_index(mcam, pcifunc,
nixlf, NIXLF_BCAST_ENTRY);
action.op = NIX_RX_ACTIONOP_UCAST;
action.pf_func = pcifunc;
} else {
- pfvf = rvu_get_pfvf(rvu, pcifunc);
action.index = pfvf->bcast_mce_idx;
action.op = NIX_RX_ACTIONOP_MCAST;
}
entry.action = *(u64 *)&action;
npc_config_mcam_entry(rvu, mcam, blkaddr, index,
- NIX_INTF_RX, &entry, true);
+ pfvf->nix_rx_intf, &entry, true);
}
void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable)
npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
}
+static void npc_update_vf_flow_entry(struct rvu *rvu, struct npc_mcam *mcam,
+ int blkaddr, u16 pcifunc, u64 rx_action)
+{
+ int actindex, index, bank;
+ bool enable;
+
+ if (!(pcifunc & RVU_PFVF_FUNC_MASK))
+ return;
+
+ mutex_lock(&mcam->lock);
+ for (index = 0; index < mcam->bmap_entries; index++) {
+ if (mcam->entry2target_pffunc[index] == pcifunc) {
+ bank = npc_get_bank(mcam, index);
+ actindex = index;
+ index &= (mcam->banksize - 1);
+
+ /* read vf flow entry enable status */
+ enable = is_mcam_entry_enabled(rvu, mcam, blkaddr,
+ actindex);
+ /* disable before mcam entry update */
+ npc_enable_mcam_entry(rvu, mcam, blkaddr, actindex,
+ false);
+ /* update 'action' */
+ rvu_write64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_ACTION(index, bank),
+ rx_action);
+ if (enable)
+ npc_enable_mcam_entry(rvu, mcam, blkaddr,
+ actindex, true);
+ }
+ }
+ mutex_unlock(&mcam->lock);
+}
+
void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
int group, int alg_idx, int mcam_index)
{
struct npc_mcam *mcam = &rvu->hw->mcam;
struct nix_rx_action action;
int blkaddr, index, bank;
+ struct rvu_pfvf *pfvf;
blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
if (blkaddr < 0)
rvu_write64(rvu, blkaddr,
NPC_AF_MCAMEX_BANKX_ACTION(index, bank), *(u64 *)&action);
+ /* update the VF flow rule action with the VF default entry action */
+ if (mcam_index < 0)
+ npc_update_vf_flow_entry(rvu, mcam, blkaddr, pcifunc,
+ *(u64 *)&action);
+
+ /* update the action change in default rule */
+ pfvf = rvu_get_pfvf(rvu, pcifunc);
+ if (pfvf->def_ucast_rule)
+ pfvf->def_ucast_rule->rx_action = action;
+
index = npc_get_nixlf_mcam_index(mcam, pcifunc,
nixlf, NIXLF_PROMISC_ENTRY);
NPC_AF_MCAMEX_BANKX_ACTION(index, bank),
*(u64 *)&action);
}
-
- rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
}
static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf);
else
rvu_npc_disable_promisc_entry(rvu, pcifunc, nixlf);
-
- rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
}
void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
}
void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+ struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct rvu_npc_mcam_rule *rule;
+ int blkaddr;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+ if (blkaddr < 0)
+ return;
+
+ mutex_lock(&mcam->lock);
+
+ /* Disable MCAM entries directing traffic to this 'pcifunc' */
+ list_for_each_entry(rule, &mcam->mcam_rules, list) {
+ if (is_npc_intf_rx(rule->intf) &&
+ rule->rx_action.pf_func == pcifunc) {
+ npc_enable_mcam_entry(rvu, mcam, blkaddr,
+ rule->entry, false);
+ rule->enable = false;
+ /* Indicate that default rule is disabled */
+ if (rule->default_rule)
+ pfvf->def_ucast_rule = NULL;
+ }
+ }
+
+ mutex_unlock(&mcam->lock);
+
+ npc_mcam_disable_flows(rvu, pcifunc);
+
+ rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
+}
+
+void rvu_npc_free_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
{
struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct rvu_npc_mcam_rule *rule, *tmp;
int blkaddr;
blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
mutex_lock(&mcam->lock);
- /* Disable and free all MCAM entries mapped to this 'pcifunc' */
+ /* Free all MCAM entries owned by this 'pcifunc' */
npc_mcam_free_all_entries(rvu, mcam, blkaddr, pcifunc);
- /* Free all MCAM counters mapped to this 'pcifunc' */
+ /* Free all MCAM counters owned by this 'pcifunc' */
npc_mcam_free_all_counters(rvu, mcam, pcifunc);
+ /* Delete MCAM entries owned by this 'pcifunc' */
+ list_for_each_entry_safe(rule, tmp, &mcam->mcam_rules, list) {
+ if (rule->owner == pcifunc && !rule->default_rule) {
+ list_del(&rule->list);
+ kfree(rule);
+ }
+ }
+
mutex_unlock(&mcam->lock);
rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
rvu_write64(rvu, blkaddr, \
NPC_AF_INTFX_LDATAX_FLAGSX_CFG(intf, ld, flags), cfg)
-static void npc_program_mkex_profile(struct rvu *rvu, int blkaddr,
- const struct npc_mcam_kex *mkex)
+static void npc_program_mkex_rx(struct rvu *rvu, int blkaddr,
+ struct npc_mcam_kex *mkex, u8 intf)
{
int lid, lt, ld, fl;
- rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_RX),
- mkex->keyx_cfg[NIX_INTF_RX]);
- rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_TX),
- mkex->keyx_cfg[NIX_INTF_TX]);
+ if (is_npc_intf_tx(intf))
+ return;
- for (ld = 0; ld < NPC_MAX_LD; ld++)
- rvu_write64(rvu, blkaddr, NPC_AF_KEX_LDATAX_FLAGS_CFG(ld),
- mkex->kex_ld_flags[ld]);
+ rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(intf),
+ mkex->keyx_cfg[NIX_INTF_RX]);
+ /* Program LDATA */
for (lid = 0; lid < NPC_MAX_LID; lid++) {
for (lt = 0; lt < NPC_MAX_LT; lt++) {
- for (ld = 0; ld < NPC_MAX_LD; ld++) {
- SET_KEX_LD(NIX_INTF_RX, lid, lt, ld,
+ for (ld = 0; ld < NPC_MAX_LD; ld++)
+ SET_KEX_LD(intf, lid, lt, ld,
mkex->intf_lid_lt_ld[NIX_INTF_RX]
[lid][lt][ld]);
-
- SET_KEX_LD(NIX_INTF_TX, lid, lt, ld,
- mkex->intf_lid_lt_ld[NIX_INTF_TX]
- [lid][lt][ld]);
- }
}
}
-
+ /* Program LFLAGS */
for (ld = 0; ld < NPC_MAX_LD; ld++) {
- for (fl = 0; fl < NPC_MAX_LFL; fl++) {
- SET_KEX_LDFLAGS(NIX_INTF_RX, ld, fl,
+ for (fl = 0; fl < NPC_MAX_LFL; fl++)
+ SET_KEX_LDFLAGS(intf, ld, fl,
mkex->intf_ld_flags[NIX_INTF_RX]
[ld][fl]);
+ }
+}
- SET_KEX_LDFLAGS(NIX_INTF_TX, ld, fl,
+static void npc_program_mkex_tx(struct rvu *rvu, int blkaddr,
+ struct npc_mcam_kex *mkex, u8 intf)
+{
+ int lid, lt, ld, fl;
+
+ if (is_npc_intf_rx(intf))
+ return;
+
+ rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(intf),
+ mkex->keyx_cfg[NIX_INTF_TX]);
+
+ /* Program LDATA */
+ for (lid = 0; lid < NPC_MAX_LID; lid++) {
+ for (lt = 0; lt < NPC_MAX_LT; lt++) {
+ for (ld = 0; ld < NPC_MAX_LD; ld++)
+ SET_KEX_LD(intf, lid, lt, ld,
+ mkex->intf_lid_lt_ld[NIX_INTF_TX]
+ [lid][lt][ld]);
+ }
+ }
+ /* Program LFLAGS */
+ for (ld = 0; ld < NPC_MAX_LD; ld++) {
+ for (fl = 0; fl < NPC_MAX_LFL; fl++)
+ SET_KEX_LDFLAGS(intf, ld, fl,
mkex->intf_ld_flags[NIX_INTF_TX]
[ld][fl]);
- }
+ }
+}
+
+static void npc_program_mkex_profile(struct rvu *rvu, int blkaddr,
+ struct npc_mcam_kex *mkex)
+{
+ struct rvu_hwinfo *hw = rvu->hw;
+ u8 intf;
+ int ld;
+
+ for (ld = 0; ld < NPC_MAX_LD; ld++)
+ rvu_write64(rvu, blkaddr, NPC_AF_KEX_LDATAX_FLAGS_CFG(ld),
+ mkex->kex_ld_flags[ld]);
+
+ for (intf = 0; intf < hw->npc_intfs; intf++) {
+ npc_program_mkex_rx(rvu, blkaddr, mkex, intf);
+ npc_program_mkex_tx(rvu, blkaddr, mkex, intf);
}
}
kpu, profile->cam_entries, profile->action_entries);
}
- max_entries = rvu_read64(rvu, blkaddr, NPC_AF_CONST1) & 0xFFF;
+ max_entries = rvu->hw->npc_kpu_entries;
/* Program CAM match entries for previous KPU extracted data */
num_entries = min_t(int, profile->cam_entries, max_entries);
int num_pkinds, num_kpus, idx;
struct npc_pkind *pkind;
- /* Get HW limits */
- hw->npc_kpus = (rvu_read64(rvu, blkaddr, NPC_AF_CONST) >> 8) & 0x1F;
-
/* Disable all KPUs and their entries */
for (idx = 0; idx < hw->npc_kpus; idx++) {
rvu_write64(rvu, blkaddr,
int rsvd, err;
u64 cfg;
- /* Get HW limits */
- cfg = rvu_read64(rvu, blkaddr, NPC_AF_CONST);
- mcam->banks = (cfg >> 44) & 0xF;
- mcam->banksize = (cfg >> 28) & 0xFFFF;
- mcam->counters.max = (cfg >> 48) & 0xFFFF;
-
/* Actual number of MCAM entries vary by entry size */
cfg = (rvu_read64(rvu, blkaddr,
NPC_AF_INTFX_KEX_CFG(0)) >> 32) & 0x07;
mcam->hprio_count = mcam->lprio_count;
mcam->hprio_end = mcam->hprio_count;
- /* Reserve last counter for MCAM RX miss action which is set to
- * drop pkt. This way we will know how many pkts didn't match
- * any MCAM entry.
- */
- mcam->counters.max--;
- mcam->rx_miss_act_cntr = mcam->counters.max;
/* Allocate bitmap for managing MCAM counters and memory
* for saving counter to RVU PFFUNC allocation mapping.
if (!mcam->cntr_refcnt)
goto free_mem;
+ /* Alloc memory for saving target device of mcam rule */
+ mcam->entry2target_pffunc = devm_kcalloc(rvu->dev, mcam->total_entries,
+ sizeof(u16), GFP_KERNEL);
+ if (!mcam->entry2target_pffunc)
+ goto free_mem;
+
mutex_init(&mcam->lock);
return 0;
return -ENOMEM;
}
+static void rvu_npc_hw_init(struct rvu *rvu, int blkaddr)
+{
+ struct npc_pkind *pkind = &rvu->hw->pkind;
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct rvu_hwinfo *hw = rvu->hw;
+ u64 npc_const, npc_const1;
+ u64 npc_const2 = 0;
+
+ npc_const = rvu_read64(rvu, blkaddr, NPC_AF_CONST);
+ npc_const1 = rvu_read64(rvu, blkaddr, NPC_AF_CONST1);
+ if (npc_const1 & BIT_ULL(63))
+ npc_const2 = rvu_read64(rvu, blkaddr, NPC_AF_CONST2);
+
+ pkind->rsrc.max = (npc_const1 >> 12) & 0xFFULL;
+ hw->npc_kpu_entries = npc_const1 & 0xFFFULL;
+ hw->npc_kpus = (npc_const >> 8) & 0x1FULL;
+ hw->npc_intfs = npc_const & 0xFULL;
+ hw->npc_counters = (npc_const >> 48) & 0xFFFFULL;
+
+ mcam->banks = (npc_const >> 44) & 0xFULL;
+ mcam->banksize = (npc_const >> 28) & 0xFFFFULL;
+ /* Extended set */
+ if (npc_const2) {
+ hw->npc_ext_set = true;
+ hw->npc_counters = (npc_const2 >> 16) & 0xFFFFULL;
+ mcam->banksize = npc_const2 & 0xFFFFULL;
+ }
+
+ mcam->counters.max = hw->npc_counters;
+}
+
+static void rvu_npc_setup_interfaces(struct rvu *rvu, int blkaddr)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct rvu_hwinfo *hw = rvu->hw;
+ u64 nibble_ena, rx_kex, tx_kex;
+ u8 intf;
+
+ /* Reserve last counter for MCAM RX miss action which is set to
+ * drop packet. This way we will know how many pkts didn't match
+ * any MCAM entry.
+ */
+ mcam->counters.max--;
+ mcam->rx_miss_act_cntr = mcam->counters.max;
+
+ rx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_RX];
+ tx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_TX];
+ nibble_ena = FIELD_GET(NPC_PARSE_NIBBLE, rx_kex);
+
+ nibble_ena = rvu_npc_get_tx_nibble_cfg(rvu, nibble_ena);
+ if (nibble_ena) {
+ tx_kex &= ~NPC_PARSE_NIBBLE;
+ tx_kex |= FIELD_PREP(NPC_PARSE_NIBBLE, nibble_ena);
+ npc_mkex_default.keyx_cfg[NIX_INTF_TX] = tx_kex;
+ }
+
+ /* Configure RX interfaces */
+ for (intf = 0; intf < hw->npc_intfs; intf++) {
+ if (is_npc_intf_tx(intf))
+ continue;
+
+ /* Set RX MCAM search key size. LA..LE (ltype only) + Channel */
+ rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(intf),
+ rx_kex);
+
+ /* If MCAM lookup doesn't result in a match, drop the received
+ * packet. And map this action to a counter to count dropped
+ * packets.
+ */
+ rvu_write64(rvu, blkaddr,
+ NPC_AF_INTFX_MISS_ACT(intf), NIX_RX_ACTIONOP_DROP);
+
+ /* NPC_AF_INTFX_MISS_STAT_ACT[14:12] - counter[11:9]
+ * NPC_AF_INTFX_MISS_STAT_ACT[8:0] - counter[8:0]
+ */
+ rvu_write64(rvu, blkaddr,
+ NPC_AF_INTFX_MISS_STAT_ACT(intf),
+ ((mcam->rx_miss_act_cntr >> 9) << 12) |
+ BIT_ULL(9) | mcam->rx_miss_act_cntr);
+ }
+
+ /* Configure TX interfaces */
+ for (intf = 0; intf < hw->npc_intfs; intf++) {
+ if (is_npc_intf_rx(intf))
+ continue;
+
+ /* Extract Ltypes LID_LA to LID_LE */
+ rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(intf),
+ tx_kex);
+
+ /* Set TX miss action to UCAST_DEFAULT i.e
+ * transmit the packet on NIX LF SQ's default channel.
+ */
+ rvu_write64(rvu, blkaddr,
+ NPC_AF_INTFX_MISS_ACT(intf),
+ NIX_TX_ACTIONOP_UCAST_DEFAULT);
+ }
+}
+
int rvu_npc_init(struct rvu *rvu)
{
struct npc_kpu_profile_adapter *kpu = &rvu->kpu;
struct npc_pkind *pkind = &rvu->hw->pkind;
struct npc_mcam *mcam = &rvu->hw->mcam;
- u64 cfg, nibble_ena, rx_kex, tx_kex;
int blkaddr, entry, bank, err;
blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
return -ENODEV;
}
+ rvu_npc_hw_init(rvu, blkaddr);
+
/* First disable all MCAM entries, to stop traffic towards NIXLFs */
- cfg = rvu_read64(rvu, blkaddr, NPC_AF_CONST);
- for (bank = 0; bank < ((cfg >> 44) & 0xF); bank++) {
- for (entry = 0; entry < ((cfg >> 28) & 0xFFFF); entry++)
+ for (bank = 0; bank < mcam->banks; bank++) {
+ for (entry = 0; entry < mcam->banksize; entry++)
rvu_write64(rvu, blkaddr,
NPC_AF_MCAMEX_BANKX_CFG(entry, bank), 0);
}
- /* Allocate resource bimap for pkind*/
- pkind->rsrc.max = (rvu_read64(rvu, blkaddr,
- NPC_AF_CONST1) >> 12) & 0xFF;
err = rvu_alloc_bitmap(&pkind->rsrc);
if (err)
return err;
BIT_ULL(32) | BIT_ULL(24) | BIT_ULL(6) |
BIT_ULL(2) | BIT_ULL(1));
- /* Set RX and TX side MCAM search key size.
- * LA..LD (ltype only) + Channel
- */
- rx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_RX];
- tx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_TX];
- nibble_ena = FIELD_GET(NPC_PARSE_NIBBLE, rx_kex);
- rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_RX), rx_kex);
- /* Due to an errata (35786) in A0 pass silicon, parse nibble enable
- * configuration has to be identical for both Rx and Tx interfaces.
- */
- if (is_rvu_96xx_B0(rvu)) {
- tx_kex &= ~NPC_PARSE_NIBBLE;
- tx_kex |= FIELD_PREP(NPC_PARSE_NIBBLE, nibble_ena);
- }
- rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_TX), tx_kex);
-
- err = npc_mcam_rsrcs_init(rvu, blkaddr);
- if (err)
- return err;
+ rvu_npc_setup_interfaces(rvu, blkaddr);
/* Configure MKEX profile */
npc_load_mkex_profile(rvu, blkaddr, rvu->mkex_pfl_name);
- /* Set TX miss action to UCAST_DEFAULT i.e
- * transmit the packet on NIX LF SQ's default channel.
- */
- rvu_write64(rvu, blkaddr, NPC_AF_INTFX_MISS_ACT(NIX_INTF_TX),
- NIX_TX_ACTIONOP_UCAST_DEFAULT);
+ err = npc_mcam_rsrcs_init(rvu, blkaddr);
+ if (err)
+ return err;
- /* If MCAM lookup doesn't result in a match, drop the received packet.
- * And map this action to a counter to count dropped pkts.
- */
- rvu_write64(rvu, blkaddr, NPC_AF_INTFX_MISS_ACT(NIX_INTF_RX),
- NIX_RX_ACTIONOP_DROP);
- rvu_write64(rvu, blkaddr, NPC_AF_INTFX_MISS_STAT_ACT(NIX_INTF_RX),
- BIT_ULL(9) | mcam->rx_miss_act_cntr);
+ err = npc_flow_steering_init(rvu, blkaddr);
+ if (err) {
+ dev_err(rvu->dev,
+ "Incorrect mkex profile loaded using default mkex\n");
+ npc_load_mkex_profile(rvu, blkaddr, def_pfl_name);
+ }
return 0;
}
/* Set mapping and increment counter's refcnt */
mcam->entry2cntr_map[entry] = cntr;
mcam->cntr_refcnt[cntr]++;
- /* Enable stats */
+ /* Enable stats
+ * NPC_AF_MCAMEX_BANKX_STAT_ACT[14:12] - counter[11:9]
+ * NPC_AF_MCAMEX_BANKX_STAT_ACT[8:0] - counter[8:0]
+ */
rvu_write64(rvu, blkaddr,
NPC_AF_MCAMEX_BANKX_STAT_ACT(index, bank),
- BIT_ULL(9) | cntr);
+ ((cntr >> 9) << 12) | BIT_ULL(9) | cntr);
}
static void npc_unmap_mcam_entry_and_cntr(struct rvu *rvu,
npc_unmap_mcam_entry_and_cntr(rvu, mcam,
blkaddr, index,
cntr);
+ mcam->entry2target_pffunc[index] = 0x0;
}
}
}
goto exit;
mcam->entry2pfvf_map[req->entry] = 0;
+ mcam->entry2target_pffunc[req->entry] = 0x0;
npc_mcam_clear_bit(mcam, req->entry);
npc_enable_mcam_entry(rvu, mcam, blkaddr, req->entry, false);
return rc;
}
+int rvu_mbox_handler_npc_mcam_read_entry(struct rvu *rvu,
+ struct npc_mcam_read_entry_req *req,
+ struct npc_mcam_read_entry_rsp *rsp)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ u16 pcifunc = req->hdr.pcifunc;
+ int blkaddr, rc;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+ if (blkaddr < 0)
+ return NPC_MCAM_INVALID_REQ;
+
+ mutex_lock(&mcam->lock);
+ rc = npc_mcam_verify_entry(mcam, pcifunc, req->entry);
+ if (!rc) {
+ npc_read_mcam_entry(rvu, mcam, blkaddr, req->entry,
+ &rsp->entry_data,
+ &rsp->intf, &rsp->enable);
+ }
+
+ mutex_unlock(&mcam->lock);
+ return rc;
+}
+
int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
struct npc_mcam_write_entry_req *req,
struct msg_rsp *rsp)
{
+ struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc);
struct npc_mcam *mcam = &rvu->hw->mcam;
u16 pcifunc = req->hdr.pcifunc;
+ u16 channel, chan_mask;
int blkaddr, rc;
+ u8 nix_intf;
blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
if (blkaddr < 0)
return NPC_MCAM_INVALID_REQ;
+ chan_mask = req->entry_data.kw_mask[0] & NPC_KEX_CHAN_MASK;
+ channel = req->entry_data.kw[0] & NPC_KEX_CHAN_MASK;
+ channel &= chan_mask;
+
mutex_lock(&mcam->lock);
rc = npc_mcam_verify_entry(mcam, pcifunc, req->entry);
if (rc)
goto exit;
}
- if (req->intf != NIX_INTF_RX && req->intf != NIX_INTF_TX) {
+ if (!is_npc_interface_valid(rvu, req->intf)) {
rc = NPC_MCAM_INVALID_REQ;
goto exit;
}
- npc_config_mcam_entry(rvu, mcam, blkaddr, req->entry, req->intf,
+ if (is_npc_intf_tx(req->intf))
+ nix_intf = pfvf->nix_tx_intf;
+ else
+ nix_intf = pfvf->nix_rx_intf;
+
+ if (npc_mcam_verify_channel(rvu, pcifunc, req->intf, channel)) {
+ rc = NPC_MCAM_INVALID_REQ;
+ goto exit;
+ }
+
+ if (npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf,
+ pcifunc)) {
+ rc = NPC_MCAM_INVALID_REQ;
+ goto exit;
+ }
+
+ npc_config_mcam_entry(rvu, mcam, blkaddr, req->entry, nix_intf,
&req->entry_data, req->enable_entry);
if (req->set_cntr)
struct npc_mcam_alloc_and_write_entry_req *req,
struct npc_mcam_alloc_and_write_entry_rsp *rsp)
{
+ struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc);
struct npc_mcam_alloc_counter_req cntr_req;
struct npc_mcam_alloc_counter_rsp cntr_rsp;
struct npc_mcam_alloc_entry_req entry_req;
struct npc_mcam *mcam = &rvu->hw->mcam;
u16 entry = NPC_MCAM_ENTRY_INVALID;
u16 cntr = NPC_MCAM_ENTRY_INVALID;
+ u16 channel, chan_mask;
int blkaddr, rc;
+ u8 nix_intf;
blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
if (blkaddr < 0)
return NPC_MCAM_INVALID_REQ;
- if (req->intf != NIX_INTF_RX && req->intf != NIX_INTF_TX)
+ if (!is_npc_interface_valid(rvu, req->intf))
+ return NPC_MCAM_INVALID_REQ;
+
+ chan_mask = req->entry_data.kw_mask[0] & NPC_KEX_CHAN_MASK;
+ channel = req->entry_data.kw[0] & NPC_KEX_CHAN_MASK;
+ channel &= chan_mask;
+
+ if (npc_mcam_verify_channel(rvu, req->hdr.pcifunc, req->intf, channel))
+ return NPC_MCAM_INVALID_REQ;
+
+ if (npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf,
+ req->hdr.pcifunc))
return NPC_MCAM_INVALID_REQ;
/* Try to allocate a MCAM entry */
write_entry:
mutex_lock(&mcam->lock);
- npc_config_mcam_entry(rvu, mcam, blkaddr, entry, req->intf,
+
+ if (is_npc_intf_tx(req->intf))
+ nix_intf = pfvf->nix_tx_intf;
+ else
+ nix_intf = pfvf->nix_rx_intf;
+
+ npc_config_mcam_entry(rvu, mcam, blkaddr, entry, nix_intf,
&req->entry_data, req->enable_entry);
if (req->alloc_cntr)
return 0;
}
-int rvu_npc_update_rxvlan(struct rvu *rvu, u16 pcifunc, int nixlf)
+bool rvu_npc_write_default_rule(struct rvu *rvu, int blkaddr, int nixlf,
+ u16 pcifunc, u8 intf, struct mcam_entry *entry,
+ int *index)
{
struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
struct npc_mcam *mcam = &rvu->hw->mcam;
- int blkaddr, index;
bool enable;
+ u8 nix_intf;
+
+ if (is_npc_intf_tx(intf))
+ nix_intf = pfvf->nix_tx_intf;
+ else
+ nix_intf = pfvf->nix_rx_intf;
+
+ *index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+ nixlf, NIXLF_UCAST_ENTRY);
+ /* dont force enable unicast entry */
+ enable = is_mcam_entry_enabled(rvu, mcam, blkaddr, *index);
+ npc_config_mcam_entry(rvu, mcam, blkaddr, *index, nix_intf,
+ entry, enable);
+
+ return enable;
+}
+
+int rvu_mbox_handler_npc_read_base_steer_rule(struct rvu *rvu,
+ struct msg_req *req,
+ struct npc_mcam_read_base_rule_rsp *rsp)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ int index, blkaddr, nixlf, rc = 0;
+ u16 pcifunc = req->hdr.pcifunc;
+ struct rvu_pfvf *pfvf;
+ u8 intf, enable;
blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
if (blkaddr < 0)
- return NIX_AF_ERR_AF_LF_INVALID;
+ return NPC_MCAM_INVALID_REQ;
- if (!pfvf->rxvlan)
- return 0;
+ /* Return the channel number in case of PF */
+ if (!(pcifunc & RVU_PFVF_FUNC_MASK)) {
+ pfvf = rvu_get_pfvf(rvu, pcifunc);
+ rsp->entry.kw[0] = pfvf->rx_chan_base;
+ rsp->entry.kw_mask[0] = 0xFFFULL;
+ goto out;
+ }
+ /* Find the pkt steering rule installed by PF to this VF */
+ mutex_lock(&mcam->lock);
+ for (index = 0; index < mcam->bmap_entries; index++) {
+ if (mcam->entry2target_pffunc[index] == pcifunc)
+ goto read_entry;
+ }
+
+ rc = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL);
+ if (rc < 0) {
+ mutex_unlock(&mcam->lock);
+ goto out;
+ }
+ /* Read the default ucast entry if there is no pkt steering rule */
index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf,
NIXLF_UCAST_ENTRY);
- pfvf->entry.action = npc_get_mcam_action(rvu, mcam, blkaddr, index);
- enable = is_mcam_entry_enabled(rvu, mcam, blkaddr, index);
- npc_config_mcam_entry(rvu, mcam, blkaddr, pfvf->rxvlan_index,
- NIX_INTF_RX, &pfvf->entry, enable);
-
- return 0;
+read_entry:
+ /* Read the mcam entry */
+ npc_read_mcam_entry(rvu, mcam, blkaddr, index, &rsp->entry, &intf,
+ &enable);
+ mutex_unlock(&mcam->lock);
+out:
+ return rc;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell OcteonTx2 RVU Admin Function driver
+ *
+ * Copyright (C) 2020 Marvell.
+ */
+
+#include <linux/bitfield.h>
+
+#include "rvu_struct.h"
+#include "rvu_reg.h"
+#include "rvu.h"
+#include "npc.h"
+
+#define NPC_BYTESM GENMASK_ULL(19, 16)
+#define NPC_HDR_OFFSET GENMASK_ULL(15, 8)
+#define NPC_KEY_OFFSET GENMASK_ULL(5, 0)
+#define NPC_LDATA_EN BIT_ULL(7)
+
+static const char * const npc_flow_names[] = {
+ [NPC_DMAC] = "dmac",
+ [NPC_SMAC] = "smac",
+ [NPC_ETYPE] = "ether type",
+ [NPC_OUTER_VID] = "outer vlan id",
+ [NPC_TOS] = "tos",
+ [NPC_SIP_IPV4] = "ipv4 source ip",
+ [NPC_DIP_IPV4] = "ipv4 destination ip",
+ [NPC_SIP_IPV6] = "ipv6 source ip",
+ [NPC_DIP_IPV6] = "ipv6 destination ip",
+ [NPC_SPORT_TCP] = "tcp source port",
+ [NPC_DPORT_TCP] = "tcp destination port",
+ [NPC_SPORT_UDP] = "udp source port",
+ [NPC_DPORT_UDP] = "udp destination port",
+ [NPC_SPORT_SCTP] = "sctp source port",
+ [NPC_DPORT_SCTP] = "sctp destination port",
+ [NPC_UNKNOWN] = "unknown",
+};
+
+const char *npc_get_field_name(u8 hdr)
+{
+ if (hdr >= ARRAY_SIZE(npc_flow_names))
+ return npc_flow_names[NPC_UNKNOWN];
+
+ return npc_flow_names[hdr];
+}
+
+/* Compute keyword masks and figure out the number of keywords a field
+ * spans in the key.
+ */
+static void npc_set_kw_masks(struct npc_mcam *mcam, u8 type,
+ u8 nr_bits, int start_kwi, int offset, u8 intf)
+{
+ struct npc_key_field *field = &mcam->rx_key_fields[type];
+ u8 bits_in_kw;
+ int max_kwi;
+
+ if (mcam->banks_per_entry == 1)
+ max_kwi = 1; /* NPC_MCAM_KEY_X1 */
+ else if (mcam->banks_per_entry == 2)
+ max_kwi = 3; /* NPC_MCAM_KEY_X2 */
+ else
+ max_kwi = 6; /* NPC_MCAM_KEY_X4 */
+
+ if (is_npc_intf_tx(intf))
+ field = &mcam->tx_key_fields[type];
+
+ if (offset + nr_bits <= 64) {
+ /* one KW only */
+ if (start_kwi > max_kwi)
+ return;
+ field->kw_mask[start_kwi] |= GENMASK_ULL(nr_bits - 1, 0)
+ << offset;
+ field->nr_kws = 1;
+ } else if (offset + nr_bits > 64 &&
+ offset + nr_bits <= 128) {
+ /* two KWs */
+ if (start_kwi + 1 > max_kwi)
+ return;
+ /* first KW mask */
+ bits_in_kw = 64 - offset;
+ field->kw_mask[start_kwi] |= GENMASK_ULL(bits_in_kw - 1, 0)
+ << offset;
+ /* second KW mask i.e. mask for rest of bits */
+ bits_in_kw = nr_bits + offset - 64;
+ field->kw_mask[start_kwi + 1] |= GENMASK_ULL(bits_in_kw - 1, 0);
+ field->nr_kws = 2;
+ } else {
+ /* three KWs */
+ if (start_kwi + 2 > max_kwi)
+ return;
+ /* first KW mask */
+ bits_in_kw = 64 - offset;
+ field->kw_mask[start_kwi] |= GENMASK_ULL(bits_in_kw - 1, 0)
+ << offset;
+ /* second KW mask */
+ field->kw_mask[start_kwi + 1] = ~0ULL;
+ /* third KW mask i.e. mask for rest of bits */
+ bits_in_kw = nr_bits + offset - 128;
+ field->kw_mask[start_kwi + 2] |= GENMASK_ULL(bits_in_kw - 1, 0);
+ field->nr_kws = 3;
+ }
+}
+
+/* Helper function to figure out whether field exists in the key */
+static bool npc_is_field_present(struct rvu *rvu, enum key_fields type, u8 intf)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct npc_key_field *input;
+
+ input = &mcam->rx_key_fields[type];
+ if (is_npc_intf_tx(intf))
+ input = &mcam->tx_key_fields[type];
+
+ return input->nr_kws > 0;
+}
+
+static bool npc_is_same(struct npc_key_field *input,
+ struct npc_key_field *field)
+{
+ int ret;
+
+ ret = memcmp(&input->layer_mdata, &field->layer_mdata,
+ sizeof(struct npc_layer_mdata));
+ return ret == 0;
+}
+
+static void npc_set_layer_mdata(struct npc_mcam *mcam, enum key_fields type,
+ u64 cfg, u8 lid, u8 lt, u8 intf)
+{
+ struct npc_key_field *input = &mcam->rx_key_fields[type];
+
+ if (is_npc_intf_tx(intf))
+ input = &mcam->tx_key_fields[type];
+
+ input->layer_mdata.hdr = FIELD_GET(NPC_HDR_OFFSET, cfg);
+ input->layer_mdata.key = FIELD_GET(NPC_KEY_OFFSET, cfg);
+ input->layer_mdata.len = FIELD_GET(NPC_BYTESM, cfg) + 1;
+ input->layer_mdata.ltype = lt;
+ input->layer_mdata.lid = lid;
+}
+
+static bool npc_check_overlap_fields(struct npc_key_field *input1,
+ struct npc_key_field *input2)
+{
+ int kwi;
+
+ /* Fields with same layer id and different ltypes are mutually
+ * exclusive hence they can be overlapped
+ */
+ if (input1->layer_mdata.lid == input2->layer_mdata.lid &&
+ input1->layer_mdata.ltype != input2->layer_mdata.ltype)
+ return false;
+
+ for (kwi = 0; kwi < NPC_MAX_KWS_IN_KEY; kwi++) {
+ if (input1->kw_mask[kwi] & input2->kw_mask[kwi])
+ return true;
+ }
+
+ return false;
+}
+
+/* Helper function to check whether given field overlaps with any other fields
+ * in the key. Due to limitations on key size and the key extraction profile in
+ * use higher layers can overwrite lower layer's header fields. Hence overlap
+ * needs to be checked.
+ */
+static bool npc_check_overlap(struct rvu *rvu, int blkaddr,
+ enum key_fields type, u8 start_lid, u8 intf)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct npc_key_field *dummy, *input;
+ int start_kwi, offset;
+ u8 nr_bits, lid, lt, ld;
+ u64 cfg;
+
+ dummy = &mcam->rx_key_fields[NPC_UNKNOWN];
+ input = &mcam->rx_key_fields[type];
+
+ if (is_npc_intf_tx(intf)) {
+ dummy = &mcam->tx_key_fields[NPC_UNKNOWN];
+ input = &mcam->tx_key_fields[type];
+ }
+
+ for (lid = start_lid; lid < NPC_MAX_LID; lid++) {
+ for (lt = 0; lt < NPC_MAX_LT; lt++) {
+ for (ld = 0; ld < NPC_MAX_LD; ld++) {
+ cfg = rvu_read64(rvu, blkaddr,
+ NPC_AF_INTFX_LIDX_LTX_LDX_CFG
+ (intf, lid, lt, ld));
+ if (!FIELD_GET(NPC_LDATA_EN, cfg))
+ continue;
+ memset(dummy, 0, sizeof(struct npc_key_field));
+ npc_set_layer_mdata(mcam, NPC_UNKNOWN, cfg,
+ lid, lt, intf);
+ /* exclude input */
+ if (npc_is_same(input, dummy))
+ continue;
+ start_kwi = dummy->layer_mdata.key / 8;
+ offset = (dummy->layer_mdata.key * 8) % 64;
+ nr_bits = dummy->layer_mdata.len * 8;
+ /* form KW masks */
+ npc_set_kw_masks(mcam, NPC_UNKNOWN, nr_bits,
+ start_kwi, offset, intf);
+ /* check any input field bits falls in any
+ * other field bits.
+ */
+ if (npc_check_overlap_fields(dummy, input))
+ return true;
+ }
+ }
+ }
+
+ return false;
+}
+
+static int npc_check_field(struct rvu *rvu, int blkaddr, enum key_fields type,
+ u8 intf)
+{
+ if (!npc_is_field_present(rvu, type, intf) ||
+ npc_check_overlap(rvu, blkaddr, type, 0, intf))
+ return -EOPNOTSUPP;
+ return 0;
+}
+
+static void npc_scan_parse_result(struct npc_mcam *mcam, u8 bit_number,
+ u8 key_nibble, u8 intf)
+{
+ u8 offset = (key_nibble * 4) % 64; /* offset within key word */
+ u8 kwi = (key_nibble * 4) / 64; /* which word in key */
+ u8 nr_bits = 4; /* bits in a nibble */
+ u8 type;
+
+ switch (bit_number) {
+ case 0 ... 2:
+ type = NPC_CHAN;
+ break;
+ case 3:
+ type = NPC_ERRLEV;
+ break;
+ case 4 ... 5:
+ type = NPC_ERRCODE;
+ break;
+ case 6:
+ type = NPC_LXMB;
+ break;
+ /* check for LTYPE only as of now */
+ case 9:
+ type = NPC_LA;
+ break;
+ case 12:
+ type = NPC_LB;
+ break;
+ case 15:
+ type = NPC_LC;
+ break;
+ case 18:
+ type = NPC_LD;
+ break;
+ case 21:
+ type = NPC_LE;
+ break;
+ case 24:
+ type = NPC_LF;
+ break;
+ case 27:
+ type = NPC_LG;
+ break;
+ case 30:
+ type = NPC_LH;
+ break;
+ default:
+ return;
+ };
+ npc_set_kw_masks(mcam, type, nr_bits, kwi, offset, intf);
+}
+
+static void npc_handle_multi_layer_fields(struct rvu *rvu, int blkaddr, u8 intf)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct npc_key_field *key_fields;
+ /* Ether type can come from three layers
+ * (ethernet, single tagged, double tagged)
+ */
+ struct npc_key_field *etype_ether;
+ struct npc_key_field *etype_tag1;
+ struct npc_key_field *etype_tag2;
+ /* Outer VLAN TCI can come from two layers
+ * (single tagged, double tagged)
+ */
+ struct npc_key_field *vlan_tag1;
+ struct npc_key_field *vlan_tag2;
+ u64 *features;
+ u8 start_lid;
+ int i;
+
+ key_fields = mcam->rx_key_fields;
+ features = &mcam->rx_features;
+
+ if (is_npc_intf_tx(intf)) {
+ key_fields = mcam->tx_key_fields;
+ features = &mcam->tx_features;
+ }
+
+ /* Handle header fields which can come from multiple layers like
+ * etype, outer vlan tci. These fields should have same position in
+ * the key otherwise to install a mcam rule more than one entry is
+ * needed which complicates mcam space management.
+ */
+ etype_ether = &key_fields[NPC_ETYPE_ETHER];
+ etype_tag1 = &key_fields[NPC_ETYPE_TAG1];
+ etype_tag2 = &key_fields[NPC_ETYPE_TAG2];
+ vlan_tag1 = &key_fields[NPC_VLAN_TAG1];
+ vlan_tag2 = &key_fields[NPC_VLAN_TAG2];
+
+ /* if key profile programmed does not extract Ethertype at all */
+ if (!etype_ether->nr_kws && !etype_tag1->nr_kws && !etype_tag2->nr_kws)
+ goto vlan_tci;
+
+ /* if key profile programmed extracts Ethertype from one layer */
+ if (etype_ether->nr_kws && !etype_tag1->nr_kws && !etype_tag2->nr_kws)
+ key_fields[NPC_ETYPE] = *etype_ether;
+ if (!etype_ether->nr_kws && etype_tag1->nr_kws && !etype_tag2->nr_kws)
+ key_fields[NPC_ETYPE] = *etype_tag1;
+ if (!etype_ether->nr_kws && !etype_tag1->nr_kws && etype_tag2->nr_kws)
+ key_fields[NPC_ETYPE] = *etype_tag2;
+
+ /* if key profile programmed extracts Ethertype from multiple layers */
+ if (etype_ether->nr_kws && etype_tag1->nr_kws) {
+ for (i = 0; i < NPC_MAX_KWS_IN_KEY; i++) {
+ if (etype_ether->kw_mask[i] != etype_tag1->kw_mask[i])
+ goto vlan_tci;
+ }
+ key_fields[NPC_ETYPE] = *etype_tag1;
+ }
+ if (etype_ether->nr_kws && etype_tag2->nr_kws) {
+ for (i = 0; i < NPC_MAX_KWS_IN_KEY; i++) {
+ if (etype_ether->kw_mask[i] != etype_tag2->kw_mask[i])
+ goto vlan_tci;
+ }
+ key_fields[NPC_ETYPE] = *etype_tag2;
+ }
+ if (etype_tag1->nr_kws && etype_tag2->nr_kws) {
+ for (i = 0; i < NPC_MAX_KWS_IN_KEY; i++) {
+ if (etype_tag1->kw_mask[i] != etype_tag2->kw_mask[i])
+ goto vlan_tci;
+ }
+ key_fields[NPC_ETYPE] = *etype_tag2;
+ }
+
+ /* check none of higher layers overwrite Ethertype */
+ start_lid = key_fields[NPC_ETYPE].layer_mdata.lid + 1;
+ if (npc_check_overlap(rvu, blkaddr, NPC_ETYPE, start_lid, intf))
+ goto vlan_tci;
+ *features |= BIT_ULL(NPC_ETYPE);
+vlan_tci:
+ /* if key profile does not extract outer vlan tci at all */
+ if (!vlan_tag1->nr_kws && !vlan_tag2->nr_kws)
+ goto done;
+
+ /* if key profile extracts outer vlan tci from one layer */
+ if (vlan_tag1->nr_kws && !vlan_tag2->nr_kws)
+ key_fields[NPC_OUTER_VID] = *vlan_tag1;
+ if (!vlan_tag1->nr_kws && vlan_tag2->nr_kws)
+ key_fields[NPC_OUTER_VID] = *vlan_tag2;
+
+ /* if key profile extracts outer vlan tci from multiple layers */
+ if (vlan_tag1->nr_kws && vlan_tag2->nr_kws) {
+ for (i = 0; i < NPC_MAX_KWS_IN_KEY; i++) {
+ if (vlan_tag1->kw_mask[i] != vlan_tag2->kw_mask[i])
+ goto done;
+ }
+ key_fields[NPC_OUTER_VID] = *vlan_tag2;
+ }
+ /* check none of higher layers overwrite outer vlan tci */
+ start_lid = key_fields[NPC_OUTER_VID].layer_mdata.lid + 1;
+ if (npc_check_overlap(rvu, blkaddr, NPC_OUTER_VID, start_lid, intf))
+ goto done;
+ *features |= BIT_ULL(NPC_OUTER_VID);
+done:
+ return;
+}
+
+static void npc_scan_ldata(struct rvu *rvu, int blkaddr, u8 lid,
+ u8 lt, u64 cfg, u8 intf)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ u8 hdr, key, nr_bytes, bit_offset;
+ u8 la_ltype, la_start;
+ /* starting KW index and starting bit position */
+ int start_kwi, offset;
+
+ nr_bytes = FIELD_GET(NPC_BYTESM, cfg) + 1;
+ hdr = FIELD_GET(NPC_HDR_OFFSET, cfg);
+ key = FIELD_GET(NPC_KEY_OFFSET, cfg);
+ start_kwi = key / 8;
+ offset = (key * 8) % 64;
+
+ /* For Tx, Layer A has NIX_INST_HDR_S(64 bytes) preceding
+ * ethernet header.
+ */
+ if (is_npc_intf_tx(intf)) {
+ la_ltype = NPC_LT_LA_IH_NIX_ETHER;
+ la_start = 8;
+ } else {
+ la_ltype = NPC_LT_LA_ETHER;
+ la_start = 0;
+ }
+
+#define NPC_SCAN_HDR(name, hlid, hlt, hstart, hlen) \
+do { \
+ if (lid == (hlid) && lt == (hlt)) { \
+ if ((hstart) >= hdr && \
+ ((hstart) + (hlen)) <= (hdr + nr_bytes)) { \
+ bit_offset = (hdr + nr_bytes - (hstart) - (hlen)) * 8; \
+ npc_set_layer_mdata(mcam, (name), cfg, lid, lt, intf); \
+ npc_set_kw_masks(mcam, (name), (hlen) * 8, \
+ start_kwi, offset + bit_offset, intf);\
+ } \
+ } \
+} while (0)
+
+ /* List LID, LTYPE, start offset from layer and length(in bytes) of
+ * packet header fields below.
+ * Example: Source IP is 4 bytes and starts at 12th byte of IP header
+ */
+ NPC_SCAN_HDR(NPC_SIP_IPV4, NPC_LID_LC, NPC_LT_LC_IP, 12, 4);
+ NPC_SCAN_HDR(NPC_DIP_IPV4, NPC_LID_LC, NPC_LT_LC_IP, 16, 4);
+ NPC_SCAN_HDR(NPC_SIP_IPV6, NPC_LID_LC, NPC_LT_LC_IP6, 8, 16);
+ NPC_SCAN_HDR(NPC_DIP_IPV6, NPC_LID_LC, NPC_LT_LC_IP6, 24, 16);
+ NPC_SCAN_HDR(NPC_SPORT_UDP, NPC_LID_LD, NPC_LT_LD_UDP, 0, 2);
+ NPC_SCAN_HDR(NPC_DPORT_UDP, NPC_LID_LD, NPC_LT_LD_UDP, 2, 2);
+ NPC_SCAN_HDR(NPC_SPORT_TCP, NPC_LID_LD, NPC_LT_LD_TCP, 0, 2);
+ NPC_SCAN_HDR(NPC_DPORT_TCP, NPC_LID_LD, NPC_LT_LD_TCP, 2, 2);
+ NPC_SCAN_HDR(NPC_SPORT_SCTP, NPC_LID_LD, NPC_LT_LD_SCTP, 0, 2);
+ NPC_SCAN_HDR(NPC_DPORT_SCTP, NPC_LID_LD, NPC_LT_LD_SCTP, 2, 2);
+ NPC_SCAN_HDR(NPC_ETYPE_ETHER, NPC_LID_LA, NPC_LT_LA_ETHER, 12, 2);
+ NPC_SCAN_HDR(NPC_ETYPE_TAG1, NPC_LID_LB, NPC_LT_LB_CTAG, 4, 2);
+ NPC_SCAN_HDR(NPC_ETYPE_TAG2, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 8, 2);
+ NPC_SCAN_HDR(NPC_VLAN_TAG1, NPC_LID_LB, NPC_LT_LB_CTAG, 2, 2);
+ NPC_SCAN_HDR(NPC_VLAN_TAG2, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 2, 2);
+ NPC_SCAN_HDR(NPC_DMAC, NPC_LID_LA, la_ltype, la_start, 6);
+ NPC_SCAN_HDR(NPC_SMAC, NPC_LID_LA, la_ltype, la_start, 6);
+ /* PF_FUNC is 2 bytes at 0th byte of NPC_LT_LA_IH_NIX_ETHER */
+ NPC_SCAN_HDR(NPC_PF_FUNC, NPC_LID_LA, NPC_LT_LA_IH_NIX_ETHER, 0, 2);
+}
+
+static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ u64 *features = &mcam->rx_features;
+ u64 tcp_udp_sctp;
+ int err, hdr;
+
+ if (is_npc_intf_tx(intf))
+ features = &mcam->tx_features;
+
+ for (hdr = NPC_DMAC; hdr < NPC_HEADER_FIELDS_MAX; hdr++) {
+ err = npc_check_field(rvu, blkaddr, hdr, intf);
+ if (!err)
+ *features |= BIT_ULL(hdr);
+ }
+
+ tcp_udp_sctp = BIT_ULL(NPC_SPORT_TCP) | BIT_ULL(NPC_SPORT_UDP) |
+ BIT_ULL(NPC_DPORT_TCP) | BIT_ULL(NPC_DPORT_UDP) |
+ BIT_ULL(NPC_SPORT_SCTP) | BIT_ULL(NPC_DPORT_SCTP);
+
+ /* for tcp/udp/sctp corresponding layer type should be in the key */
+ if (*features & tcp_udp_sctp)
+ if (npc_check_field(rvu, blkaddr, NPC_LD, intf))
+ *features &= ~tcp_udp_sctp;
+
+ /* for vlan corresponding layer type should be in the key */
+ if (*features & BIT_ULL(NPC_OUTER_VID))
+ if (npc_check_field(rvu, blkaddr, NPC_LB, intf))
+ *features &= ~BIT_ULL(NPC_OUTER_VID);
+}
+
+/* Scan key extraction profile and record how fields of our interest
+ * fill the key structure. Also verify Channel and DMAC exists in
+ * key and not overwritten by other header fields.
+ */
+static int npc_scan_kex(struct rvu *rvu, int blkaddr, u8 intf)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ u8 lid, lt, ld, bitnr;
+ u8 key_nibble = 0;
+ u64 cfg;
+
+ /* Scan and note how parse result is going to be in key.
+ * A bit set in PARSE_NIBBLE_ENA corresponds to a nibble from
+ * parse result in the key. The enabled nibbles from parse result
+ * will be concatenated in key.
+ */
+ cfg = rvu_read64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(intf));
+ cfg &= NPC_PARSE_NIBBLE;
+ for_each_set_bit(bitnr, (unsigned long *)&cfg, 31) {
+ npc_scan_parse_result(mcam, bitnr, key_nibble, intf);
+ key_nibble++;
+ }
+
+ /* Scan and note how layer data is going to be in key */
+ for (lid = 0; lid < NPC_MAX_LID; lid++) {
+ for (lt = 0; lt < NPC_MAX_LT; lt++) {
+ for (ld = 0; ld < NPC_MAX_LD; ld++) {
+ cfg = rvu_read64(rvu, blkaddr,
+ NPC_AF_INTFX_LIDX_LTX_LDX_CFG
+ (intf, lid, lt, ld));
+ if (!FIELD_GET(NPC_LDATA_EN, cfg))
+ continue;
+ npc_scan_ldata(rvu, blkaddr, lid, lt, cfg,
+ intf);
+ }
+ }
+ }
+
+ return 0;
+}
+
+static int npc_scan_verify_kex(struct rvu *rvu, int blkaddr)
+{
+ int err;
+
+ err = npc_scan_kex(rvu, blkaddr, NIX_INTF_RX);
+ if (err)
+ return err;
+
+ err = npc_scan_kex(rvu, blkaddr, NIX_INTF_TX);
+ if (err)
+ return err;
+
+ /* Channel is mandatory */
+ if (!npc_is_field_present(rvu, NPC_CHAN, NIX_INTF_RX)) {
+ dev_err(rvu->dev, "Channel not present in Key\n");
+ return -EINVAL;
+ }
+ /* check that none of the fields overwrite channel */
+ if (npc_check_overlap(rvu, blkaddr, NPC_CHAN, 0, NIX_INTF_RX)) {
+ dev_err(rvu->dev, "Channel cannot be overwritten\n");
+ return -EINVAL;
+ }
+ /* DMAC should be present in key for unicast filter to work */
+ if (!npc_is_field_present(rvu, NPC_DMAC, NIX_INTF_RX)) {
+ dev_err(rvu->dev, "DMAC not present in Key\n");
+ return -EINVAL;
+ }
+ /* check that none of the fields overwrite DMAC */
+ if (npc_check_overlap(rvu, blkaddr, NPC_DMAC, 0, NIX_INTF_RX)) {
+ dev_err(rvu->dev, "DMAC cannot be overwritten\n");
+ return -EINVAL;
+ }
+
+ npc_set_features(rvu, blkaddr, NIX_INTF_TX);
+ npc_set_features(rvu, blkaddr, NIX_INTF_RX);
+ npc_handle_multi_layer_fields(rvu, blkaddr, NIX_INTF_TX);
+ npc_handle_multi_layer_fields(rvu, blkaddr, NIX_INTF_RX);
+
+ return 0;
+}
+
+int npc_flow_steering_init(struct rvu *rvu, int blkaddr)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+
+ INIT_LIST_HEAD(&mcam->mcam_rules);
+
+ return npc_scan_verify_kex(rvu, blkaddr);
+}
+
+static int npc_check_unsupported_flows(struct rvu *rvu, u64 features, u8 intf)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ u64 *mcam_features = &mcam->rx_features;
+ u64 unsupported;
+ u8 bit;
+
+ if (is_npc_intf_tx(intf))
+ mcam_features = &mcam->tx_features;
+
+ unsupported = (*mcam_features ^ features) & ~(*mcam_features);
+ if (unsupported) {
+ dev_info(rvu->dev, "Unsupported flow(s):\n");
+ for_each_set_bit(bit, (unsigned long *)&unsupported, 64)
+ dev_info(rvu->dev, "%s ", npc_get_field_name(bit));
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+/* npc_update_entry - Based on the masks generated during
+ * the key scanning, updates the given entry with value and
+ * masks for the field of interest. Maximum 16 bytes of a packet
+ * header can be extracted by HW hence lo and hi are sufficient.
+ * When field bytes are less than or equal to 8 then hi should be
+ * 0 for value and mask.
+ *
+ * If exact match of value is required then mask should be all 1's.
+ * If any bits in mask are 0 then corresponding bits in value are
+ * dont care.
+ */
+static void npc_update_entry(struct rvu *rvu, enum key_fields type,
+ struct mcam_entry *entry, u64 val_lo,
+ u64 val_hi, u64 mask_lo, u64 mask_hi, u8 intf)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct mcam_entry dummy = { {0} };
+ struct npc_key_field *field;
+ u64 kw1, kw2, kw3;
+ u8 shift;
+ int i;
+
+ field = &mcam->rx_key_fields[type];
+ if (is_npc_intf_tx(intf))
+ field = &mcam->tx_key_fields[type];
+
+ if (!field->nr_kws)
+ return;
+
+ for (i = 0; i < NPC_MAX_KWS_IN_KEY; i++) {
+ if (!field->kw_mask[i])
+ continue;
+ /* place key value in kw[x] */
+ shift = __ffs64(field->kw_mask[i]);
+ /* update entry value */
+ kw1 = (val_lo << shift) & field->kw_mask[i];
+ dummy.kw[i] = kw1;
+ /* update entry mask */
+ kw1 = (mask_lo << shift) & field->kw_mask[i];
+ dummy.kw_mask[i] = kw1;
+
+ if (field->nr_kws == 1)
+ break;
+ /* place remaining bits of key value in kw[x + 1] */
+ if (field->nr_kws == 2) {
+ /* update entry value */
+ kw2 = shift ? val_lo >> (64 - shift) : 0;
+ kw2 |= (val_hi << shift);
+ kw2 &= field->kw_mask[i + 1];
+ dummy.kw[i + 1] = kw2;
+ /* update entry mask */
+ kw2 = shift ? mask_lo >> (64 - shift) : 0;
+ kw2 |= (mask_hi << shift);
+ kw2 &= field->kw_mask[i + 1];
+ dummy.kw_mask[i + 1] = kw2;
+ break;
+ }
+ /* place remaining bits of key value in kw[x + 1], kw[x + 2] */
+ if (field->nr_kws == 3) {
+ /* update entry value */
+ kw2 = shift ? val_lo >> (64 - shift) : 0;
+ kw2 |= (val_hi << shift);
+ kw2 &= field->kw_mask[i + 1];
+ kw3 = shift ? val_hi >> (64 - shift) : 0;
+ kw3 &= field->kw_mask[i + 2];
+ dummy.kw[i + 1] = kw2;
+ dummy.kw[i + 2] = kw3;
+ /* update entry mask */
+ kw2 = shift ? mask_lo >> (64 - shift) : 0;
+ kw2 |= (mask_hi << shift);
+ kw2 &= field->kw_mask[i + 1];
+ kw3 = shift ? mask_hi >> (64 - shift) : 0;
+ kw3 &= field->kw_mask[i + 2];
+ dummy.kw_mask[i + 1] = kw2;
+ dummy.kw_mask[i + 2] = kw3;
+ break;
+ }
+ }
+ /* dummy is ready with values and masks for given key
+ * field now clear and update input entry with those
+ */
+ for (i = 0; i < NPC_MAX_KWS_IN_KEY; i++) {
+ if (!field->kw_mask[i])
+ continue;
+ entry->kw[i] &= ~field->kw_mask[i];
+ entry->kw_mask[i] &= ~field->kw_mask[i];
+
+ entry->kw[i] |= dummy.kw[i];
+ entry->kw_mask[i] |= dummy.kw_mask[i];
+ }
+}
+
+#define IPV6_WORDS 4
+
+static void npc_update_ipv6_flow(struct rvu *rvu, struct mcam_entry *entry,
+ u64 features, struct flow_msg *pkt,
+ struct flow_msg *mask,
+ struct rvu_npc_mcam_rule *output, u8 intf)
+{
+ u32 src_ip[IPV6_WORDS], src_ip_mask[IPV6_WORDS];
+ u32 dst_ip[IPV6_WORDS], dst_ip_mask[IPV6_WORDS];
+ struct flow_msg *opkt = &output->packet;
+ struct flow_msg *omask = &output->mask;
+ u64 mask_lo, mask_hi;
+ u64 val_lo, val_hi;
+
+ /* For an ipv6 address fe80::2c68:63ff:fe5e:2d0a the packet
+ * values to be programmed in MCAM should as below:
+ * val_high: 0xfe80000000000000
+ * val_low: 0x2c6863fffe5e2d0a
+ */
+ if (features & BIT_ULL(NPC_SIP_IPV6)) {
+ be32_to_cpu_array(src_ip_mask, mask->ip6src, IPV6_WORDS);
+ be32_to_cpu_array(src_ip, pkt->ip6src, IPV6_WORDS);
+
+ mask_hi = (u64)src_ip_mask[0] << 32 | src_ip_mask[1];
+ mask_lo = (u64)src_ip_mask[2] << 32 | src_ip_mask[3];
+ val_hi = (u64)src_ip[0] << 32 | src_ip[1];
+ val_lo = (u64)src_ip[2] << 32 | src_ip[3];
+
+ npc_update_entry(rvu, NPC_SIP_IPV6, entry, val_lo, val_hi,
+ mask_lo, mask_hi, intf);
+ memcpy(opkt->ip6src, pkt->ip6src, sizeof(opkt->ip6src));
+ memcpy(omask->ip6src, mask->ip6src, sizeof(omask->ip6src));
+ }
+ if (features & BIT_ULL(NPC_DIP_IPV6)) {
+ be32_to_cpu_array(dst_ip_mask, mask->ip6dst, IPV6_WORDS);
+ be32_to_cpu_array(dst_ip, pkt->ip6dst, IPV6_WORDS);
+
+ mask_hi = (u64)dst_ip_mask[0] << 32 | dst_ip_mask[1];
+ mask_lo = (u64)dst_ip_mask[2] << 32 | dst_ip_mask[3];
+ val_hi = (u64)dst_ip[0] << 32 | dst_ip[1];
+ val_lo = (u64)dst_ip[2] << 32 | dst_ip[3];
+
+ npc_update_entry(rvu, NPC_DIP_IPV6, entry, val_lo, val_hi,
+ mask_lo, mask_hi, intf);
+ memcpy(opkt->ip6dst, pkt->ip6dst, sizeof(opkt->ip6dst));
+ memcpy(omask->ip6dst, mask->ip6dst, sizeof(omask->ip6dst));
+ }
+}
+
+static void npc_update_flow(struct rvu *rvu, struct mcam_entry *entry,
+ u64 features, struct flow_msg *pkt,
+ struct flow_msg *mask,
+ struct rvu_npc_mcam_rule *output, u8 intf)
+{
+ u64 dmac_mask = ether_addr_to_u64(mask->dmac);
+ u64 smac_mask = ether_addr_to_u64(mask->smac);
+ u64 dmac_val = ether_addr_to_u64(pkt->dmac);
+ u64 smac_val = ether_addr_to_u64(pkt->smac);
+ struct flow_msg *opkt = &output->packet;
+ struct flow_msg *omask = &output->mask;
+
+ if (!features)
+ return;
+
+ /* For tcp/udp/sctp LTYPE should be present in entry */
+ if (features & (BIT_ULL(NPC_SPORT_TCP) | BIT_ULL(NPC_DPORT_TCP)))
+ npc_update_entry(rvu, NPC_LD, entry, NPC_LT_LD_TCP,
+ 0, ~0ULL, 0, intf);
+ if (features & (BIT_ULL(NPC_SPORT_UDP) | BIT_ULL(NPC_DPORT_UDP)))
+ npc_update_entry(rvu, NPC_LD, entry, NPC_LT_LD_UDP,
+ 0, ~0ULL, 0, intf);
+ if (features & (BIT_ULL(NPC_SPORT_SCTP) | BIT_ULL(NPC_DPORT_SCTP)))
+ npc_update_entry(rvu, NPC_LD, entry, NPC_LT_LD_SCTP,
+ 0, ~0ULL, 0, intf);
+
+ if (features & BIT_ULL(NPC_OUTER_VID))
+ npc_update_entry(rvu, NPC_LB, entry,
+ NPC_LT_LB_STAG_QINQ | NPC_LT_LB_CTAG, 0,
+ NPC_LT_LB_STAG_QINQ & NPC_LT_LB_CTAG, 0, intf);
+
+#define NPC_WRITE_FLOW(field, member, val_lo, val_hi, mask_lo, mask_hi) \
+do { \
+ if (features & BIT_ULL((field))) { \
+ npc_update_entry(rvu, (field), entry, (val_lo), (val_hi), \
+ (mask_lo), (mask_hi), intf); \
+ memcpy(&opkt->member, &pkt->member, sizeof(pkt->member)); \
+ memcpy(&omask->member, &mask->member, sizeof(mask->member)); \
+ } \
+} while (0)
+
+ NPC_WRITE_FLOW(NPC_DMAC, dmac, dmac_val, 0, dmac_mask, 0);
+ NPC_WRITE_FLOW(NPC_SMAC, smac, smac_val, 0, smac_mask, 0);
+ NPC_WRITE_FLOW(NPC_ETYPE, etype, ntohs(pkt->etype), 0,
+ ntohs(mask->etype), 0);
+ NPC_WRITE_FLOW(NPC_SIP_IPV4, ip4src, ntohl(pkt->ip4src), 0,
+ ntohl(mask->ip4src), 0);
+ NPC_WRITE_FLOW(NPC_DIP_IPV4, ip4dst, ntohl(pkt->ip4dst), 0,
+ ntohl(mask->ip4dst), 0);
+ NPC_WRITE_FLOW(NPC_SPORT_TCP, sport, ntohs(pkt->sport), 0,
+ ntohs(mask->sport), 0);
+ NPC_WRITE_FLOW(NPC_SPORT_UDP, sport, ntohs(pkt->sport), 0,
+ ntohs(mask->sport), 0);
+ NPC_WRITE_FLOW(NPC_DPORT_TCP, dport, ntohs(pkt->dport), 0,
+ ntohs(mask->dport), 0);
+ NPC_WRITE_FLOW(NPC_DPORT_UDP, dport, ntohs(pkt->dport), 0,
+ ntohs(mask->dport), 0);
+ NPC_WRITE_FLOW(NPC_SPORT_SCTP, sport, ntohs(pkt->sport), 0,
+ ntohs(mask->sport), 0);
+ NPC_WRITE_FLOW(NPC_DPORT_SCTP, dport, ntohs(pkt->dport), 0,
+ ntohs(mask->dport), 0);
+
+ NPC_WRITE_FLOW(NPC_OUTER_VID, vlan_tci, ntohs(pkt->vlan_tci), 0,
+ ntohs(mask->vlan_tci), 0);
+
+ npc_update_ipv6_flow(rvu, entry, features, pkt, mask, output, intf);
+}
+
+static struct rvu_npc_mcam_rule *rvu_mcam_find_rule(struct npc_mcam *mcam,
+ u16 entry)
+{
+ struct rvu_npc_mcam_rule *iter;
+
+ mutex_lock(&mcam->lock);
+ list_for_each_entry(iter, &mcam->mcam_rules, list) {
+ if (iter->entry == entry) {
+ mutex_unlock(&mcam->lock);
+ return iter;
+ }
+ }
+ mutex_unlock(&mcam->lock);
+
+ return NULL;
+}
+
+static void rvu_mcam_add_rule(struct npc_mcam *mcam,
+ struct rvu_npc_mcam_rule *rule)
+{
+ struct list_head *head = &mcam->mcam_rules;
+ struct rvu_npc_mcam_rule *iter;
+
+ mutex_lock(&mcam->lock);
+ list_for_each_entry(iter, &mcam->mcam_rules, list) {
+ if (iter->entry > rule->entry)
+ break;
+ head = &iter->list;
+ }
+
+ list_add(&rule->list, head);
+ mutex_unlock(&mcam->lock);
+}
+
+static void rvu_mcam_remove_counter_from_rule(struct rvu *rvu, u16 pcifunc,
+ struct rvu_npc_mcam_rule *rule)
+{
+ struct npc_mcam_oper_counter_req free_req = { 0 };
+ struct msg_rsp free_rsp;
+
+ if (!rule->has_cntr)
+ return;
+
+ free_req.hdr.pcifunc = pcifunc;
+ free_req.cntr = rule->cntr;
+
+ rvu_mbox_handler_npc_mcam_free_counter(rvu, &free_req, &free_rsp);
+ rule->has_cntr = false;
+}
+
+static void rvu_mcam_add_counter_to_rule(struct rvu *rvu, u16 pcifunc,
+ struct rvu_npc_mcam_rule *rule,
+ struct npc_install_flow_rsp *rsp)
+{
+ struct npc_mcam_alloc_counter_req cntr_req = { 0 };
+ struct npc_mcam_alloc_counter_rsp cntr_rsp = { 0 };
+ int err;
+
+ cntr_req.hdr.pcifunc = pcifunc;
+ cntr_req.contig = true;
+ cntr_req.count = 1;
+
+ /* we try to allocate a counter to track the stats of this
+ * rule. If counter could not be allocated then proceed
+ * without counter because counters are limited than entries.
+ */
+ err = rvu_mbox_handler_npc_mcam_alloc_counter(rvu, &cntr_req,
+ &cntr_rsp);
+ if (!err && cntr_rsp.count) {
+ rule->cntr = cntr_rsp.cntr;
+ rule->has_cntr = true;
+ rsp->counter = rule->cntr;
+ } else {
+ rsp->counter = err;
+ }
+}
+
+static void npc_update_rx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
+ struct mcam_entry *entry,
+ struct npc_install_flow_req *req, u16 target)
+{
+ struct nix_rx_action action;
+
+ npc_update_entry(rvu, NPC_CHAN, entry, req->channel, 0,
+ ~0ULL, 0, NIX_INTF_RX);
+
+ *(u64 *)&action = 0x00;
+ action.pf_func = target;
+ action.op = req->op;
+ action.index = req->index;
+ action.match_id = req->match_id;
+ action.flow_key_alg = req->flow_key_alg;
+
+ if (req->op == NIX_RX_ACTION_DEFAULT && pfvf->def_ucast_rule)
+ action = pfvf->def_ucast_rule->rx_action;
+
+ entry->action = *(u64 *)&action;
+
+ /* VTAG0 starts at 0th byte of LID_B.
+ * VTAG1 starts at 4th byte of LID_B.
+ */
+ entry->vtag_action = FIELD_PREP(RX_VTAG0_VALID_BIT, req->vtag0_valid) |
+ FIELD_PREP(RX_VTAG0_TYPE_MASK, req->vtag0_type) |
+ FIELD_PREP(RX_VTAG0_LID_MASK, NPC_LID_LB) |
+ FIELD_PREP(RX_VTAG0_RELPTR_MASK, 0) |
+ FIELD_PREP(RX_VTAG1_VALID_BIT, req->vtag1_valid) |
+ FIELD_PREP(RX_VTAG1_TYPE_MASK, req->vtag1_type) |
+ FIELD_PREP(RX_VTAG1_LID_MASK, NPC_LID_LB) |
+ FIELD_PREP(RX_VTAG1_RELPTR_MASK, 4);
+}
+
+static void npc_update_tx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
+ struct mcam_entry *entry,
+ struct npc_install_flow_req *req, u16 target)
+{
+ struct nix_tx_action action;
+
+ npc_update_entry(rvu, NPC_PF_FUNC, entry, (__force u16)htons(target),
+ 0, ~0ULL, 0, NIX_INTF_TX);
+
+ *(u64 *)&action = 0x00;
+ action.op = req->op;
+ action.index = req->index;
+ action.match_id = req->match_id;
+
+ entry->action = *(u64 *)&action;
+
+ /* VTAG0 starts at 0th byte of LID_B.
+ * VTAG1 starts at 4th byte of LID_B.
+ */
+ entry->vtag_action = FIELD_PREP(TX_VTAG0_DEF_MASK, req->vtag0_def) |
+ FIELD_PREP(TX_VTAG0_OP_MASK, req->vtag0_op) |
+ FIELD_PREP(TX_VTAG0_LID_MASK, NPC_LID_LA) |
+ FIELD_PREP(TX_VTAG0_RELPTR_MASK, 20) |
+ FIELD_PREP(TX_VTAG1_DEF_MASK, req->vtag1_def) |
+ FIELD_PREP(TX_VTAG1_OP_MASK, req->vtag1_op) |
+ FIELD_PREP(TX_VTAG1_LID_MASK, NPC_LID_LA) |
+ FIELD_PREP(TX_VTAG1_RELPTR_MASK, 24);
+}
+
+static int npc_install_flow(struct rvu *rvu, int blkaddr, u16 target,
+ int nixlf, struct rvu_pfvf *pfvf,
+ struct npc_install_flow_req *req,
+ struct npc_install_flow_rsp *rsp, bool enable,
+ bool pf_set_vfs_mac)
+{
+ struct rvu_npc_mcam_rule *def_ucast_rule = pfvf->def_ucast_rule;
+ u64 features, installed_features, missing_features = 0;
+ struct npc_mcam_write_entry_req write_req = { 0 };
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct rvu_npc_mcam_rule dummy = { 0 };
+ struct rvu_npc_mcam_rule *rule;
+ bool new = false, msg_from_vf;
+ u16 owner = req->hdr.pcifunc;
+ struct msg_rsp write_rsp;
+ struct mcam_entry *entry;
+ int entry_index, err;
+
+ msg_from_vf = !!(owner & RVU_PFVF_FUNC_MASK);
+
+ installed_features = req->features;
+ features = req->features;
+ entry = &write_req.entry_data;
+ entry_index = req->entry;
+
+ npc_update_flow(rvu, entry, features, &req->packet, &req->mask, &dummy,
+ req->intf);
+
+ if (is_npc_intf_rx(req->intf))
+ npc_update_rx_entry(rvu, pfvf, entry, req, target);
+ else
+ npc_update_tx_entry(rvu, pfvf, entry, req, target);
+
+ /* Default unicast rules do not exist for TX */
+ if (is_npc_intf_tx(req->intf))
+ goto find_rule;
+
+ if (def_ucast_rule)
+ missing_features = (def_ucast_rule->features ^ features) &
+ def_ucast_rule->features;
+
+ if (req->default_rule && req->append) {
+ /* add to default rule */
+ if (missing_features)
+ npc_update_flow(rvu, entry, missing_features,
+ &def_ucast_rule->packet,
+ &def_ucast_rule->mask,
+ &dummy, req->intf);
+ enable = rvu_npc_write_default_rule(rvu, blkaddr,
+ nixlf, target,
+ pfvf->nix_rx_intf, entry,
+ &entry_index);
+ installed_features = req->features | missing_features;
+ } else if (req->default_rule && !req->append) {
+ /* overwrite default rule */
+ enable = rvu_npc_write_default_rule(rvu, blkaddr,
+ nixlf, target,
+ pfvf->nix_rx_intf, entry,
+ &entry_index);
+ } else if (msg_from_vf) {
+ /* normal rule - include default rule also to it for VF */
+ npc_update_flow(rvu, entry, missing_features,
+ &def_ucast_rule->packet, &def_ucast_rule->mask,
+ &dummy, req->intf);
+ installed_features = req->features | missing_features;
+ }
+
+find_rule:
+ rule = rvu_mcam_find_rule(mcam, entry_index);
+ if (!rule) {
+ rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+ if (!rule)
+ return -ENOMEM;
+ new = true;
+ }
+ /* no counter for default rule */
+ if (req->default_rule)
+ goto update_rule;
+
+ /* allocate new counter if rule has no counter */
+ if (req->set_cntr && !rule->has_cntr)
+ rvu_mcam_add_counter_to_rule(rvu, owner, rule, rsp);
+
+ /* if user wants to delete an existing counter for a rule then
+ * free the counter
+ */
+ if (!req->set_cntr && rule->has_cntr)
+ rvu_mcam_remove_counter_from_rule(rvu, owner, rule);
+
+ write_req.hdr.pcifunc = owner;
+ write_req.entry = req->entry;
+ write_req.intf = req->intf;
+ write_req.enable_entry = (u8)enable;
+ /* if counter is available then clear and use it */
+ if (req->set_cntr && rule->has_cntr) {
+ rvu_write64(rvu, blkaddr, NPC_AF_MATCH_STATX(rule->cntr), 0x00);
+ write_req.set_cntr = 1;
+ write_req.cntr = rule->cntr;
+ }
+
+ err = rvu_mbox_handler_npc_mcam_write_entry(rvu, &write_req,
+ &write_rsp);
+ if (err) {
+ rvu_mcam_remove_counter_from_rule(rvu, owner, rule);
+ if (new)
+ kfree(rule);
+ return err;
+ }
+update_rule:
+ memcpy(&rule->packet, &dummy.packet, sizeof(rule->packet));
+ memcpy(&rule->mask, &dummy.mask, sizeof(rule->mask));
+ rule->entry = entry_index;
+ memcpy(&rule->rx_action, &entry->action, sizeof(struct nix_rx_action));
+ if (is_npc_intf_tx(req->intf))
+ memcpy(&rule->tx_action, &entry->action,
+ sizeof(struct nix_tx_action));
+ rule->vtag_action = entry->vtag_action;
+ rule->features = installed_features;
+ rule->default_rule = req->default_rule;
+ rule->owner = owner;
+ rule->enable = enable;
+ if (is_npc_intf_tx(req->intf))
+ rule->intf = pfvf->nix_tx_intf;
+ else
+ rule->intf = pfvf->nix_rx_intf;
+
+ if (new)
+ rvu_mcam_add_rule(mcam, rule);
+ if (req->default_rule)
+ pfvf->def_ucast_rule = rule;
+
+ /* VF's MAC address is being changed via PF */
+ if (pf_set_vfs_mac) {
+ ether_addr_copy(pfvf->default_mac, req->packet.dmac);
+ ether_addr_copy(pfvf->mac_addr, req->packet.dmac);
+ }
+
+ if (pfvf->pf_set_vf_cfg && req->vtag0_type == NIX_AF_LFX_RX_VTAG_TYPE7)
+ rule->vfvlan_cfg = true;
+
+ return 0;
+}
+
+int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
+ struct npc_install_flow_req *req,
+ struct npc_install_flow_rsp *rsp)
+{
+ bool from_vf = !!(req->hdr.pcifunc & RVU_PFVF_FUNC_MASK);
+ int blkaddr, nixlf, err;
+ struct rvu_pfvf *pfvf;
+ bool pf_set_vfs_mac = false;
+ bool enable = true;
+ u16 target;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+ if (blkaddr < 0) {
+ dev_err(rvu->dev, "%s: NPC block not implemented\n", __func__);
+ return -ENODEV;
+ }
+
+ if (!is_npc_interface_valid(rvu, req->intf))
+ return -EINVAL;
+
+ if (from_vf && req->default_rule)
+ return NPC_MCAM_PERM_DENIED;
+
+ /* Each PF/VF info is maintained in struct rvu_pfvf.
+ * rvu_pfvf for the target PF/VF needs to be retrieved
+ * hence modify pcifunc accordingly.
+ */
+
+ /* AF installing for a PF/VF */
+ if (!req->hdr.pcifunc)
+ target = req->vf;
+ /* PF installing for its VF */
+ else if (!from_vf && req->vf) {
+ target = (req->hdr.pcifunc & ~RVU_PFVF_FUNC_MASK) | req->vf;
+ pf_set_vfs_mac = req->default_rule &&
+ (req->features & BIT_ULL(NPC_DMAC));
+ }
+ /* msg received from PF/VF */
+ else
+ target = req->hdr.pcifunc;
+
+ if (npc_check_unsupported_flows(rvu, req->features, req->intf))
+ return -EOPNOTSUPP;
+
+ if (npc_mcam_verify_channel(rvu, target, req->intf, req->channel))
+ return -EINVAL;
+
+ pfvf = rvu_get_pfvf(rvu, target);
+
+ /* PF installing for its VF */
+ if (req->hdr.pcifunc && !from_vf && req->vf)
+ pfvf->pf_set_vf_cfg = 1;
+
+ /* update req destination mac addr */
+ if ((req->features & BIT_ULL(NPC_DMAC)) && is_npc_intf_rx(req->intf) &&
+ is_zero_ether_addr(req->packet.dmac)) {
+ ether_addr_copy(req->packet.dmac, pfvf->mac_addr);
+ eth_broadcast_addr((u8 *)&req->mask.dmac);
+ }
+
+ err = nix_get_nixlf(rvu, target, &nixlf, NULL);
+
+ /* If interface is uninitialized then do not enable entry */
+ if (err || (!req->default_rule && !pfvf->def_ucast_rule))
+ enable = false;
+
+ /* Packets reaching NPC in Tx path implies that a
+ * NIXLF is properly setup and transmitting.
+ * Hence rules can be enabled for Tx.
+ */
+ if (is_npc_intf_tx(req->intf))
+ enable = true;
+
+ /* Do not allow requests from uninitialized VFs */
+ if (from_vf && !enable)
+ return -EINVAL;
+
+ /* If message is from VF then its flow should not overlap with
+ * reserved unicast flow.
+ */
+ if (from_vf && pfvf->def_ucast_rule && is_npc_intf_rx(req->intf) &&
+ pfvf->def_ucast_rule->features & req->features)
+ return -EINVAL;
+
+ return npc_install_flow(rvu, blkaddr, target, nixlf, pfvf, req, rsp,
+ enable, pf_set_vfs_mac);
+}
+
+static int npc_delete_flow(struct rvu *rvu, struct rvu_npc_mcam_rule *rule,
+ u16 pcifunc)
+{
+ struct npc_mcam_ena_dis_entry_req dis_req = { 0 };
+ struct msg_rsp dis_rsp;
+
+ if (rule->default_rule)
+ return 0;
+
+ if (rule->has_cntr)
+ rvu_mcam_remove_counter_from_rule(rvu, pcifunc, rule);
+
+ dis_req.hdr.pcifunc = pcifunc;
+ dis_req.entry = rule->entry;
+
+ list_del(&rule->list);
+ kfree(rule);
+
+ return rvu_mbox_handler_npc_mcam_dis_entry(rvu, &dis_req, &dis_rsp);
+}
+
+int rvu_mbox_handler_npc_delete_flow(struct rvu *rvu,
+ struct npc_delete_flow_req *req,
+ struct msg_rsp *rsp)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct rvu_npc_mcam_rule *iter, *tmp;
+ u16 pcifunc = req->hdr.pcifunc;
+ struct list_head del_list;
+
+ INIT_LIST_HEAD(&del_list);
+
+ mutex_lock(&mcam->lock);
+ list_for_each_entry_safe(iter, tmp, &mcam->mcam_rules, list) {
+ if (iter->owner == pcifunc) {
+ /* All rules */
+ if (req->all) {
+ list_move_tail(&iter->list, &del_list);
+ /* Range of rules */
+ } else if (req->end && iter->entry >= req->start &&
+ iter->entry <= req->end) {
+ list_move_tail(&iter->list, &del_list);
+ /* single rule */
+ } else if (req->entry == iter->entry) {
+ list_move_tail(&iter->list, &del_list);
+ break;
+ }
+ }
+ }
+ mutex_unlock(&mcam->lock);
+
+ list_for_each_entry_safe(iter, tmp, &del_list, list) {
+ u16 entry = iter->entry;
+
+ /* clear the mcam entry target pcifunc */
+ mcam->entry2target_pffunc[entry] = 0x0;
+ if (npc_delete_flow(rvu, iter, pcifunc))
+ dev_err(rvu->dev, "rule deletion failed for entry:%u",
+ entry);
+ }
+
+ return 0;
+}
+
+static int npc_update_dmac_value(struct rvu *rvu, int npcblkaddr,
+ struct rvu_npc_mcam_rule *rule,
+ struct rvu_pfvf *pfvf)
+{
+ struct npc_mcam_write_entry_req write_req = { 0 };
+ struct mcam_entry *entry = &write_req.entry_data;
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct msg_rsp rsp;
+ u8 intf, enable;
+ int err;
+
+ ether_addr_copy(rule->packet.dmac, pfvf->mac_addr);
+
+ npc_read_mcam_entry(rvu, mcam, npcblkaddr, rule->entry,
+ entry, &intf, &enable);
+
+ npc_update_entry(rvu, NPC_DMAC, entry,
+ ether_addr_to_u64(pfvf->mac_addr), 0,
+ 0xffffffffffffull, 0, intf);
+
+ write_req.hdr.pcifunc = rule->owner;
+ write_req.entry = rule->entry;
+
+ mutex_unlock(&mcam->lock);
+ err = rvu_mbox_handler_npc_mcam_write_entry(rvu, &write_req, &rsp);
+ mutex_lock(&mcam->lock);
+
+ return err;
+}
+
+void npc_mcam_enable_flows(struct rvu *rvu, u16 target)
+{
+ struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, target);
+ struct rvu_npc_mcam_rule *def_ucast_rule;
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct rvu_npc_mcam_rule *rule;
+ int blkaddr, bank, index;
+ u64 def_action;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+ if (blkaddr < 0)
+ return;
+
+ def_ucast_rule = pfvf->def_ucast_rule;
+
+ mutex_lock(&mcam->lock);
+ list_for_each_entry(rule, &mcam->mcam_rules, list) {
+ if (is_npc_intf_rx(rule->intf) &&
+ rule->rx_action.pf_func == target && !rule->enable) {
+ if (rule->default_rule) {
+ npc_enable_mcam_entry(rvu, mcam, blkaddr,
+ rule->entry, true);
+ rule->enable = true;
+ continue;
+ }
+
+ if (rule->vfvlan_cfg)
+ npc_update_dmac_value(rvu, blkaddr, rule, pfvf);
+
+ if (rule->rx_action.op == NIX_RX_ACTION_DEFAULT) {
+ if (!def_ucast_rule)
+ continue;
+ /* Use default unicast entry action */
+ rule->rx_action = def_ucast_rule->rx_action;
+ def_action = *(u64 *)&def_ucast_rule->rx_action;
+ bank = npc_get_bank(mcam, rule->entry);
+ rvu_write64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_ACTION
+ (rule->entry, bank), def_action);
+ }
+
+ npc_enable_mcam_entry(rvu, mcam, blkaddr,
+ rule->entry, true);
+ rule->enable = true;
+ }
+ }
+
+ /* Enable MCAM entries installed by PF with target as VF pcifunc */
+ for (index = 0; index < mcam->bmap_entries; index++) {
+ if (mcam->entry2target_pffunc[index] == target)
+ npc_enable_mcam_entry(rvu, mcam, blkaddr,
+ index, true);
+ }
+ mutex_unlock(&mcam->lock);
+}
+
+void npc_mcam_disable_flows(struct rvu *rvu, u16 target)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ int blkaddr, index;
+
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+ if (blkaddr < 0)
+ return;
+
+ mutex_lock(&mcam->lock);
+ /* Disable MCAM entries installed by PF with target as VF pcifunc */
+ for (index = 0; index < mcam->bmap_entries; index++) {
+ if (mcam->entry2target_pffunc[index] == target)
+ npc_enable_mcam_entry(rvu, mcam, blkaddr,
+ index, false);
+ }
+ mutex_unlock(&mcam->lock);
+}
{0x1200, 0x12E0} } },
{NIX_TXSCH_LVL_TL3, 3, 0xFFFF, {{0x1000, 0x10E0}, {0x1600, 0x1608},
{0x1610, 0x1618} } },
- {NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x1768} } },
+ {NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x17B0} } },
{NIX_TXSCH_LVL_TL1, 1, 0xFFFF, {{0x0C00, 0x0D98} } },
};
#define RVU_PRIV_PFX_MSIX_CFG(a) (0x8000110 | (a) << 16)
#define RVU_PRIV_PFX_ID_CFG(a) (0x8000120 | (a) << 16)
#define RVU_PRIV_PFX_INT_CFG(a) (0x8000200 | (a) << 16)
-#define RVU_PRIV_PFX_NIX0_CFG (0x8000300)
+#define RVU_PRIV_PFX_NIXX_CFG(a) (0x8000300 | (a) << 3)
#define RVU_PRIV_PFX_NPA_CFG (0x8000310)
#define RVU_PRIV_PFX_SSO_CFG (0x8000320)
#define RVU_PRIV_PFX_SSOW_CFG (0x8000330)
#define RVU_PRIV_PFX_TIM_CFG (0x8000340)
-#define RVU_PRIV_PFX_CPT0_CFG (0x8000350)
+#define RVU_PRIV_PFX_CPTX_CFG(a) (0x8000350 | (a) << 3)
#define RVU_PRIV_BLOCK_TYPEX_REV(a) (0x8000400 | (a) << 3)
#define RVU_PRIV_HWVFX_INT_CFG(a) (0x8001280 | (a) << 16)
-#define RVU_PRIV_HWVFX_NIX0_CFG (0x8001300)
+#define RVU_PRIV_HWVFX_NIXX_CFG(a) (0x8001300 | (a) << 3)
#define RVU_PRIV_HWVFX_NPA_CFG (0x8001310)
#define RVU_PRIV_HWVFX_SSO_CFG (0x8001320)
#define RVU_PRIV_HWVFX_SSOW_CFG (0x8001330)
#define RVU_PRIV_HWVFX_TIM_CFG (0x8001340)
-#define RVU_PRIV_HWVFX_CPT0_CFG (0x8001350)
+#define RVU_PRIV_HWVFX_CPTX_CFG(a) (0x8001350 | (a) << 3)
/* RVU PF registers */
#define RVU_PF_VFX_PFVF_MBOX0 (0x00000)
#define TIM_AF_LF_RST (0x20)
/* CPT */
-#define CPT_AF_CONSTANTS0 (0x0000)
-#define CPT_PRIV_LFX_CFG (0x41000)
-#define CPT_PRIV_LFX_INT_CFG (0x43000)
-#define CPT_AF_RVU_LF_CFG_DEBUG (0x45000)
-#define CPT_AF_LF_RST (0x44000)
-#define CPT_AF_BLK_RST (0x46000)
+#define CPT_AF_CONSTANTS0 (0x0000)
+#define CPT_AF_CONSTANTS1 (0x1000)
+#define CPT_AF_DIAG (0x3000)
+#define CPT_AF_ECO (0x4000)
+#define CPT_AF_FLTX_INT(a) (0xa000ull | (u64)(a) << 3)
+#define CPT_AF_FLTX_INT_W1S(a) (0xb000ull | (u64)(a) << 3)
+#define CPT_AF_FLTX_INT_ENA_W1C(a) (0xc000ull | (u64)(a) << 3)
+#define CPT_AF_FLTX_INT_ENA_W1S(a) (0xd000ull | (u64)(a) << 3)
+#define CPT_AF_PSNX_EXE(a) (0xe000ull | (u64)(a) << 3)
+#define CPT_AF_PSNX_EXE_W1S(a) (0xf000ull | (u64)(a) << 3)
+#define CPT_AF_PSNX_LF(a) (0x10000ull | (u64)(a) << 3)
+#define CPT_AF_PSNX_LF_W1S(a) (0x11000ull | (u64)(a) << 3)
+#define CPT_AF_EXEX_CTL2(a) (0x12000ull | (u64)(a) << 3)
+#define CPT_AF_EXEX_STS(a) (0x13000ull | (u64)(a) << 3)
+#define CPT_AF_EXE_ERR_INFO (0x14000)
+#define CPT_AF_EXEX_ACTIVE(a) (0x16000ull | (u64)(a) << 3)
+#define CPT_AF_INST_REQ_PC (0x17000)
+#define CPT_AF_INST_LATENCY_PC (0x18000)
+#define CPT_AF_RD_REQ_PC (0x19000)
+#define CPT_AF_RD_LATENCY_PC (0x1a000)
+#define CPT_AF_RD_UC_PC (0x1b000)
+#define CPT_AF_ACTIVE_CYCLES_PC (0x1c000)
+#define CPT_AF_EXE_DBG_CTL (0x1d000)
+#define CPT_AF_EXE_DBG_DATA (0x1e000)
+#define CPT_AF_EXE_REQ_TIMER (0x1f000)
+#define CPT_AF_EXEX_CTL(a) (0x20000ull | (u64)(a) << 3)
+#define CPT_AF_EXE_PERF_CTL (0x21000)
+#define CPT_AF_EXE_DBG_CNTX(a) (0x22000ull | (u64)(a) << 3)
+#define CPT_AF_EXE_PERF_EVENT_CNT (0x23000)
+#define CPT_AF_EXE_EPCI_INBX_CNT(a) (0x24000ull | (u64)(a) << 3)
+#define CPT_AF_EXE_EPCI_OUTBX_CNT(a) (0x25000ull | (u64)(a) << 3)
+#define CPT_AF_EXEX_UCODE_BASE(a) (0x26000ull | (u64)(a) << 3)
+#define CPT_AF_LFX_CTL(a) (0x27000ull | (u64)(a) << 3)
+#define CPT_AF_LFX_CTL2(a) (0x29000ull | (u64)(a) << 3)
+#define CPT_AF_CPTCLK_CNT (0x2a000)
+#define CPT_AF_PF_FUNC (0x2b000)
+#define CPT_AF_LFX_PTR_CTL(a) (0x2c000ull | (u64)(a) << 3)
+#define CPT_AF_GRPX_THR(a) (0x2d000ull | (u64)(a) << 3)
+#define CPT_AF_CTL (0x2e000ull)
+#define CPT_AF_XEX_THR(a) (0x2f000ull | (u64)(a) << 3)
+#define CPT_PRIV_LFX_CFG (0x41000)
+#define CPT_PRIV_AF_INT_CFG (0x42000)
+#define CPT_PRIV_LFX_INT_CFG (0x43000)
+#define CPT_AF_LF_RST (0x44000)
+#define CPT_AF_RVU_LF_CFG_DEBUG (0x45000)
+#define CPT_AF_BLK_RST (0x46000)
+#define CPT_AF_RVU_INT (0x47000)
+#define CPT_AF_RVU_INT_W1S (0x47008)
+#define CPT_AF_RVU_INT_ENA_W1S (0x47010)
+#define CPT_AF_RVU_INT_ENA_W1C (0x47018)
+#define CPT_AF_RAS_INT (0x47020)
+#define CPT_AF_RAS_INT_W1S (0x47028)
+#define CPT_AF_RAS_INT_ENA_W1S (0x47030)
+#define CPT_AF_RAS_INT_ENA_W1C (0x47038)
+
+#define CPT_AF_LF_CTL2_SHIFT 3
+#define CPT_AF_LF_SSO_PF_FUNC_SHIFT 32
#define NPC_AF_BLK_RST (0x00040)
#define NPC_AF_BLK_RST (0x00040)
#define NPC_AF_MCAM_SCRUB_CTL (0x000a0)
#define NPC_AF_KCAM_SCRUB_CTL (0x000b0)
+#define NPC_AF_CONST2 (0x00100)
+#define NPC_AF_CONST3 (0x00110)
#define NPC_AF_KPUX_CFG(a) (0x00500 | (a) << 3)
#define NPC_AF_PCK_CFG (0x00600)
#define NPC_AF_PCK_DEF_OL2 (0x00610)
(0x900000 | (a) << 16 | (b) << 12 | (c) << 5 | (d) << 3)
#define NPC_AF_INTFX_LDATAX_FLAGSX_CFG(a, b, c) \
(0x980000 | (a) << 16 | (b) << 12 | (c) << 3)
-#define NPC_AF_MCAMEX_BANKX_CAMX_INTF(a, b, c) \
- (0x1000000ull | (a) << 10 | (b) << 6 | (c) << 3)
-#define NPC_AF_MCAMEX_BANKX_CAMX_W0(a, b, c) \
- (0x1000010ull | (a) << 10 | (b) << 6 | (c) << 3)
-#define NPC_AF_MCAMEX_BANKX_CAMX_W1(a, b, c) \
- (0x1000020ull | (a) << 10 | (b) << 6 | (c) << 3)
-#define NPC_AF_MCAMEX_BANKX_CFG(a, b) (0x1800000ull | (a) << 8 | (b) << 4)
-#define NPC_AF_MCAMEX_BANKX_STAT_ACT(a, b) \
- (0x1880000 | (a) << 8 | (b) << 4)
-#define NPC_AF_MATCH_STATX(a) (0x1880008 | (a) << 8)
#define NPC_AF_INTFX_MISS_STAT_ACT(a) (0x1880040 + (a) * 0x8)
-#define NPC_AF_MCAMEX_BANKX_ACTION(a, b) (0x1900000ull | (a) << 8 | (b) << 4)
-#define NPC_AF_MCAMEX_BANKX_TAG_ACT(a, b) \
- (0x1900008 | (a) << 8 | (b) << 4)
#define NPC_AF_INTFX_MISS_ACT(a) (0x1a00000 | (a) << 4)
#define NPC_AF_INTFX_MISS_TAG_ACT(a) (0x1b00008 | (a) << 4)
#define NPC_AF_MCAM_BANKX_HITX(a, b) (0x1c80000 | (a) << 8 | (b) << 4)
#define NPC_AF_DBG_DATAX(a) (0x3001400 | (a) << 4)
#define NPC_AF_DBG_RESULTX(a) (0x3001800 | (a) << 4)
+#define NPC_AF_MCAMEX_BANKX_CAMX_INTF(a, b, c) ({ \
+ u64 offset; \
+ \
+ offset = (0x1000000ull | (a) << 10 | (b) << 6 | (c) << 3); \
+ if (rvu->hw->npc_ext_set) \
+ offset = (0x8000000ull | (a) << 8 | (b) << 22 | (c) << 3); \
+ offset; })
+
+#define NPC_AF_MCAMEX_BANKX_CAMX_W0(a, b, c) ({ \
+ u64 offset; \
+ \
+ offset = (0x1000010ull | (a) << 10 | (b) << 6 | (c) << 3); \
+ if (rvu->hw->npc_ext_set) \
+ offset = (0x8000010ull | (a) << 8 | (b) << 22 | (c) << 3); \
+ offset; })
+
+#define NPC_AF_MCAMEX_BANKX_CAMX_W1(a, b, c) ({ \
+ u64 offset; \
+ \
+ offset = (0x1000020ull | (a) << 10 | (b) << 6 | (c) << 3); \
+ if (rvu->hw->npc_ext_set) \
+ offset = (0x8000020ull | (a) << 8 | (b) << 22 | (c) << 3); \
+ offset; })
+
+#define NPC_AF_MCAMEX_BANKX_CFG(a, b) ({ \
+ u64 offset; \
+ \
+ offset = (0x1800000ull | (a) << 8 | (b) << 4); \
+ if (rvu->hw->npc_ext_set) \
+ offset = (0x8000038ull | (a) << 8 | (b) << 22); \
+ offset; })
+
+#define NPC_AF_MCAMEX_BANKX_ACTION(a, b) ({ \
+ u64 offset; \
+ \
+ offset = (0x1900000ull | (a) << 8 | (b) << 4); \
+ if (rvu->hw->npc_ext_set) \
+ offset = (0x8000040ull | (a) << 8 | (b) << 22); \
+ offset; }) \
+
+#define NPC_AF_MCAMEX_BANKX_TAG_ACT(a, b) ({ \
+ u64 offset; \
+ \
+ offset = (0x1900008ull | (a) << 8 | (b) << 4); \
+ if (rvu->hw->npc_ext_set) \
+ offset = (0x8000048ull | (a) << 8 | (b) << 22); \
+ offset; }) \
+
+#define NPC_AF_MCAMEX_BANKX_STAT_ACT(a, b) ({ \
+ u64 offset; \
+ \
+ offset = (0x1880000ull | (a) << 8 | (b) << 4); \
+ if (rvu->hw->npc_ext_set) \
+ offset = (0x8000050ull | (a) << 8 | (b) << 22); \
+ offset; }) \
+
+#define NPC_AF_MATCH_STATX(a) ({ \
+ u64 offset; \
+ \
+ offset = (0x1880008ull | (a) << 8); \
+ if (rvu->hw->npc_ext_set) \
+ offset = (0x8000078ull | (a) << 8); \
+ offset; }) \
+
/* NDC */
#define NDC_AF_CONST (0x00000)
#define NDC_AF_CLK_EN (0x00020)
/* RVU Block revision IDs */
#define RVU_BLK_RVUM_REVID 0x01
+#define RVU_MULTI_BLK_VER 0x7ULL
+
/* RVU Block Address Enumeration */
enum rvu_block_addr_e {
BLKADDR_RVUM = 0x0ULL,
BLKADDR_NDC_NIX0_RX = 0xcULL,
BLKADDR_NDC_NIX0_TX = 0xdULL,
BLKADDR_NDC_NPA0 = 0xeULL,
- BLK_COUNT = 0xfULL,
+ BLKADDR_NDC_NIX1_RX = 0x10ULL,
+ BLKADDR_NDC_NIX1_TX = 0x11ULL,
+ BLK_COUNT = 0x12ULL,
};
/* RVU Block Type Enumeration */
VTAGSIZE_T4 = 0x0,
VTAGSIZE_T8 = 0x1,
};
+
+enum nix_tx_vtag_op {
+ NOP = 0x0,
+ VTAG_INSERT = 0x1,
+ VTAG_REPLACE = 0x2,
+};
+
+/* NIX RX VTAG actions */
+#define VTAG_STRIP BIT_ULL(4)
+#define VTAG_CAPTURE BIT_ULL(5)
+
#endif /* RVU_STRUCT_H */
obj-$(CONFIG_OCTEONTX2_VF) += octeontx2_nicvf.o
octeontx2_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \
- otx2_ptp.o
+ otx2_ptp.o otx2_flows.o
octeontx2_nicvf-y := otx2_vf.o
ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
- if (!otx2_hw_set_mac_addr(pfvf, addr->sa_data))
+ if (!otx2_hw_set_mac_addr(pfvf, addr->sa_data)) {
memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
- else
+ /* update dmac field in vlan offload rule */
+ if (pfvf->flags & OTX2_FLAG_RX_VLAN_SUPPORT)
+ otx2_install_rxvlan_offload_flow(pfvf);
+ } else {
return -EPERM;
+ }
return 0;
}
rss->flowkey_cfg = rss->enable ? rss->flowkey_cfg :
NIX_FLOW_KEY_TYPE_IPV4 | NIX_FLOW_KEY_TYPE_IPV6 |
NIX_FLOW_KEY_TYPE_TCP | NIX_FLOW_KEY_TYPE_UDP |
- NIX_FLOW_KEY_TYPE_SCTP | NIX_FLOW_KEY_TYPE_VLAN;
+ NIX_FLOW_KEY_TYPE_SCTP | NIX_FLOW_KEY_TYPE_VLAN |
+ NIX_FLOW_KEY_TYPE_IPV4_PROTO;
ret = otx2_set_flowkey_cfg(pfvf);
if (ret)
link = 4 * ((map >> 8) & 0xF) + ((map >> 4) & 0xF);
}
/* LBK channel */
- if (pfvf->hw.tx_chan_base < SDP_CHAN_BASE)
- link = 12;
+ if (pfvf->hw.tx_chan_base < SDP_CHAN_BASE) {
+ map = pfvf->hw.tx_chan_base & 0x7FF;
+ link = pfvf->hw.cgx_links | ((map >> 8) & 0xF);
+ }
return link;
}
sq = &qset->sq[qidx];
sq->sqb_count = 0;
- sq->sqb_ptrs = kcalloc(num_sqbs, sizeof(u64 *), GFP_KERNEL);
+ sq->sqb_ptrs = kcalloc(num_sqbs, sizeof(*sq->sqb_ptrs), GFP_KERNEL);
if (!sq->sqb_ptrs)
return -ENOMEM;
pfvf->hw.tx_chan_base = rsp->tx_chan_base;
pfvf->hw.lso_tsov4_idx = rsp->lso_tsov4_idx;
pfvf->hw.lso_tsov6_idx = rsp->lso_tsov6_idx;
+ pfvf->hw.cgx_links = rsp->cgx_links;
+ pfvf->hw.lbk_links = rsp->lbk_links;
}
EXPORT_SYMBOL(mbox_handler_nix_lf_alloc);
#ifndef OTX2_COMMON_H
#define OTX2_COMMON_H
+#include <linux/ethtool.h>
#include <linux/pci.h>
#include <linux/iommu.h>
#include <linux/net_tstamp.h>
#include <linux/ptp_clock_kernel.h>
#include <linux/timecounter.h>
+#include <linux/soc/marvell/octeontx2/asm.h>
#include <mbox.h>
+#include <npc.h>
#include "otx2_reg.h"
#include "otx2_txrx.h"
#include <rvu_trace.h>
struct otx2_drv_stats drv_stats;
u64 cgx_rx_stats[CGX_RX_STATS_COUNT];
u64 cgx_tx_stats[CGX_TX_STATS_COUNT];
+ u8 cgx_links; /* No. of CGX links present in HW */
+ u8 lbk_links; /* No. of LBK links present in HW */
};
struct otx2_vf_config {
struct otx2_nic *pf;
struct delayed_work link_event_work;
bool intf_down; /* interface was either configured or not */
+ u8 mac[ETH_ALEN];
+ u16 vlan;
+ int tx_vtag_idx;
};
struct flr_work {
#define OTX2_HW_TIMESTAMP_LEN 8
+struct otx2_mac_table {
+ u8 addr[ETH_ALEN];
+ u16 mcam_entry;
+ bool inuse;
+};
+
+struct otx2_flow_config {
+ u16 entry[NPC_MAX_NONCONTIG_ENTRIES];
+ u32 nr_flows;
+#define OTX2_MAX_NTUPLE_FLOWS 32
+#define OTX2_MAX_UNICAST_FLOWS 8
+#define OTX2_MAX_VLAN_FLOWS 1
+#define OTX2_MCAM_COUNT (OTX2_MAX_NTUPLE_FLOWS + \
+ OTX2_MAX_UNICAST_FLOWS + \
+ OTX2_MAX_VLAN_FLOWS)
+ u32 ntuple_offset;
+ u32 unicast_offset;
+ u32 rx_vlan_offset;
+ u32 vf_vlan_offset;
+#define OTX2_PER_VF_VLAN_FLOWS 2 /* rx+tx per VF */
+#define OTX2_VF_VLAN_RX_INDEX 0
+#define OTX2_VF_VLAN_TX_INDEX 1
+ u32 ntuple_max_flows;
+ struct list_head flow_list;
+};
+
struct otx2_nic {
void __iomem *reg_base;
struct net_device *netdev;
#define OTX2_FLAG_RX_TSTAMP_ENABLED BIT_ULL(0)
#define OTX2_FLAG_TX_TSTAMP_ENABLED BIT_ULL(1)
#define OTX2_FLAG_INTF_DOWN BIT_ULL(2)
+#define OTX2_FLAG_MCAM_ENTRIES_ALLOC BIT_ULL(3)
+#define OTX2_FLAG_NTUPLE_SUPPORT BIT_ULL(4)
+#define OTX2_FLAG_UCAST_FLTR_SUPPORT BIT_ULL(5)
+#define OTX2_FLAG_RX_VLAN_SUPPORT BIT_ULL(6)
+#define OTX2_FLAG_VF_VLAN_SUPPORT BIT_ULL(7)
+#define OTX2_FLAG_PF_SHUTDOWN BIT_ULL(8)
#define OTX2_FLAG_RX_PAUSE_ENABLED BIT_ULL(9)
#define OTX2_FLAG_TX_PAUSE_ENABLED BIT_ULL(10)
u64 flags;
struct refill_work *refill_wrk;
struct workqueue_struct *otx2_wq;
struct work_struct rx_mode_work;
+ struct otx2_mac_table *mac_table;
/* Ethtool stuff */
u32 msg_enable;
struct otx2_ptp *ptp;
struct hwtstamp_config tstamp;
+
+ struct otx2_flow_config *flow_cfg;
};
static inline bool is_otx2_lbkvf(struct pci_dev *pdev)
return result;
}
-static inline u64 otx2_lmt_flush(uint64_t addr)
-{
- u64 result = 0;
-
- __asm__ volatile(".cpu generic+lse\n"
- "ldeor xzr,%x[rf],[%[rs]]"
- : [rf]"=r"(result)
- : [rs]"r"(addr));
- return result;
-}
-
#else
#define otx2_write128(lo, hi, addr)
#define otx2_atomic64_add(incr, ptr) ({ *ptr += incr; })
-#define otx2_lmt_flush(addr) ({ 0; })
#endif
/* Alloc pointer from pool/aura */
int otx2_stop(struct net_device *netdev);
int otx2_set_real_num_queues(struct net_device *netdev,
int tx_queues, int rx_queues);
+/* MCAM filter related APIs */
+int otx2_mcam_flow_init(struct otx2_nic *pf);
+int otx2_alloc_mcam_entries(struct otx2_nic *pfvf);
+void otx2_mcam_flow_del(struct otx2_nic *pf);
+int otx2_destroy_ntuple_flows(struct otx2_nic *pf);
+int otx2_destroy_mcam_flows(struct otx2_nic *pfvf);
+int otx2_get_flow(struct otx2_nic *pfvf,
+ struct ethtool_rxnfc *nfc, u32 location);
+int otx2_get_all_flows(struct otx2_nic *pfvf,
+ struct ethtool_rxnfc *nfc, u32 *rule_locs);
+int otx2_add_flow(struct otx2_nic *pfvf,
+ struct ethtool_rx_flow_spec *fsp);
+int otx2_remove_flow(struct otx2_nic *pfvf, u32 location);
+int otx2_prepare_flow_request(struct ethtool_rx_flow_spec *fsp,
+ struct npc_install_flow_req *req);
+int otx2_del_macfilter(struct net_device *netdev, const u8 *mac);
+int otx2_add_macfilter(struct net_device *netdev, const u8 *mac);
+int otx2_enable_rxvlan(struct otx2_nic *pf, bool enable);
+int otx2_install_rxvlan_offload_flow(struct otx2_nic *pfvf);
+
#endif /* OTX2_COMMON_H */
nfc->data = pfvf->hw.rx_queues;
ret = 0;
break;
+ case ETHTOOL_GRXCLSRLCNT:
+ nfc->rule_cnt = pfvf->flow_cfg->nr_flows;
+ ret = 0;
+ break;
+ case ETHTOOL_GRXCLSRULE:
+ ret = otx2_get_flow(pfvf, nfc, nfc->fs.location);
+ break;
+ case ETHTOOL_GRXCLSRLALL:
+ ret = otx2_get_all_flows(pfvf, nfc, rules);
+ break;
case ETHTOOL_GRXFH:
return otx2_get_rss_hash_opts(pfvf, nfc);
default:
}
static int otx2_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc)
+{
+ bool ntuple = !!(dev->features & NETIF_F_NTUPLE);
+ struct otx2_nic *pfvf = netdev_priv(dev);
+ int ret = -EOPNOTSUPP;
+
+ switch (nfc->cmd) {
+ case ETHTOOL_SRXFH:
+ ret = otx2_set_rss_hash_opts(pfvf, nfc);
+ break;
+ case ETHTOOL_SRXCLSRLINS:
+ if (netif_running(dev) && ntuple)
+ ret = otx2_add_flow(pfvf, &nfc->fs);
+ break;
+ case ETHTOOL_SRXCLSRLDEL:
+ if (netif_running(dev) && ntuple)
+ ret = otx2_remove_flow(pfvf, nfc->fs.location);
+ break;
+ default:
+ break;
+ }
+
+ return ret;
+}
+
+static int otx2vf_get_rxnfc(struct net_device *dev,
+ struct ethtool_rxnfc *nfc, u32 *rules)
+{
+ struct otx2_nic *pfvf = netdev_priv(dev);
+ int ret = -EOPNOTSUPP;
+
+ switch (nfc->cmd) {
+ case ETHTOOL_GRXRINGS:
+ nfc->data = pfvf->hw.rx_queues;
+ ret = 0;
+ break;
+ case ETHTOOL_GRXFH:
+ return otx2_get_rss_hash_opts(pfvf, nfc);
+ default:
+ break;
+ }
+ return ret;
+}
+
+static int otx2vf_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc)
{
struct otx2_nic *pfvf = netdev_priv(dev);
int ret = -EOPNOTSUPP;
.get_sset_count = otx2vf_get_sset_count,
.set_channels = otx2_set_channels,
.get_channels = otx2_get_channels,
- .get_rxnfc = otx2_get_rxnfc,
- .set_rxnfc = otx2_set_rxnfc,
+ .get_rxnfc = otx2vf_get_rxnfc,
+ .set_rxnfc = otx2vf_set_rxnfc,
.get_rxfh_key_size = otx2_get_rxfh_key_size,
.get_rxfh_indir_size = otx2_get_rxfh_indir_size,
.get_rxfh = otx2_get_rxfh,
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell OcteonTx2 RVU Physcial Function ethernet driver
+ *
+ * Copyright (C) 2020 Marvell.
+ */
+
+#include <net/ipv6.h>
+
+#include "otx2_common.h"
+
+#define OTX2_DEFAULT_ACTION 0x1
+
+struct otx2_flow {
+ struct ethtool_rx_flow_spec flow_spec;
+ struct list_head list;
+ u32 location;
+ u16 entry;
+ bool is_vf;
+ int vf;
+};
+
+int otx2_alloc_mcam_entries(struct otx2_nic *pfvf)
+{
+ struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
+ struct npc_mcam_alloc_entry_req *req;
+ struct npc_mcam_alloc_entry_rsp *rsp;
+ int vf_vlan_max_flows;
+ int i;
+
+ mutex_lock(&pfvf->mbox.lock);
+
+ req = otx2_mbox_alloc_msg_npc_mcam_alloc_entry(&pfvf->mbox);
+ if (!req) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ vf_vlan_max_flows = pfvf->total_vfs * OTX2_PER_VF_VLAN_FLOWS;
+ req->contig = false;
+ req->count = OTX2_MCAM_COUNT + vf_vlan_max_flows;
+
+ /* Send message to AF */
+ if (otx2_sync_mbox_msg(&pfvf->mbox)) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return -EINVAL;
+ }
+
+ rsp = (struct npc_mcam_alloc_entry_rsp *)otx2_mbox_get_rsp
+ (&pfvf->mbox.mbox, 0, &req->hdr);
+
+ if (rsp->count != req->count) {
+ netdev_info(pfvf->netdev,
+ "Unable to allocate %d MCAM entries, got %d\n",
+ req->count, rsp->count);
+ /* support only ntuples here */
+ flow_cfg->ntuple_max_flows = rsp->count;
+ flow_cfg->ntuple_offset = 0;
+ pfvf->flags |= OTX2_FLAG_NTUPLE_SUPPORT;
+ } else {
+ flow_cfg->vf_vlan_offset = 0;
+ flow_cfg->ntuple_offset = flow_cfg->vf_vlan_offset +
+ vf_vlan_max_flows;
+ flow_cfg->unicast_offset = flow_cfg->ntuple_offset +
+ OTX2_MAX_NTUPLE_FLOWS;
+ flow_cfg->rx_vlan_offset = flow_cfg->unicast_offset +
+ OTX2_MAX_UNICAST_FLOWS;
+ pfvf->flags |= OTX2_FLAG_NTUPLE_SUPPORT;
+ pfvf->flags |= OTX2_FLAG_UCAST_FLTR_SUPPORT;
+ pfvf->flags |= OTX2_FLAG_RX_VLAN_SUPPORT;
+ pfvf->flags |= OTX2_FLAG_VF_VLAN_SUPPORT;
+ }
+
+ for (i = 0; i < rsp->count; i++)
+ flow_cfg->entry[i] = rsp->entry_list[i];
+
+ pfvf->flags |= OTX2_FLAG_MCAM_ENTRIES_ALLOC;
+
+ mutex_unlock(&pfvf->mbox.lock);
+
+ return 0;
+}
+
+int otx2_mcam_flow_init(struct otx2_nic *pf)
+{
+ int err;
+
+ pf->flow_cfg = devm_kzalloc(pf->dev, sizeof(struct otx2_flow_config),
+ GFP_KERNEL);
+ if (!pf->flow_cfg)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&pf->flow_cfg->flow_list);
+
+ pf->flow_cfg->ntuple_max_flows = OTX2_MAX_NTUPLE_FLOWS;
+
+ err = otx2_alloc_mcam_entries(pf);
+ if (err)
+ return err;
+
+ pf->mac_table = devm_kzalloc(pf->dev, sizeof(struct otx2_mac_table)
+ * OTX2_MAX_UNICAST_FLOWS, GFP_KERNEL);
+ if (!pf->mac_table)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void otx2_mcam_flow_del(struct otx2_nic *pf)
+{
+ otx2_destroy_mcam_flows(pf);
+}
+
+/* On success adds mcam entry
+ * On failure enable promisous mode
+ */
+static int otx2_do_add_macfilter(struct otx2_nic *pf, const u8 *mac)
+{
+ struct otx2_flow_config *flow_cfg = pf->flow_cfg;
+ struct npc_install_flow_req *req;
+ int err, i;
+
+ if (!(pf->flags & OTX2_FLAG_UCAST_FLTR_SUPPORT))
+ return -ENOMEM;
+
+ /* dont have free mcam entries or uc list is greater than alloted */
+ if (netdev_uc_count(pf->netdev) > OTX2_MAX_UNICAST_FLOWS)
+ return -ENOMEM;
+
+ mutex_lock(&pf->mbox.lock);
+ req = otx2_mbox_alloc_msg_npc_install_flow(&pf->mbox);
+ if (!req) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ /* unicast offset starts with 32 0..31 for ntuple */
+ for (i = 0; i < OTX2_MAX_UNICAST_FLOWS; i++) {
+ if (pf->mac_table[i].inuse)
+ continue;
+ ether_addr_copy(pf->mac_table[i].addr, mac);
+ pf->mac_table[i].inuse = true;
+ pf->mac_table[i].mcam_entry =
+ flow_cfg->entry[i + flow_cfg->unicast_offset];
+ req->entry = pf->mac_table[i].mcam_entry;
+ break;
+ }
+
+ ether_addr_copy(req->packet.dmac, mac);
+ eth_broadcast_addr((u8 *)&req->mask.dmac);
+ req->features = BIT_ULL(NPC_DMAC);
+ req->channel = pf->hw.rx_chan_base;
+ req->intf = NIX_INTF_RX;
+ req->op = NIX_RX_ACTION_DEFAULT;
+ req->set_cntr = 1;
+
+ err = otx2_sync_mbox_msg(&pf->mbox);
+ mutex_unlock(&pf->mbox.lock);
+
+ return err;
+}
+
+int otx2_add_macfilter(struct net_device *netdev, const u8 *mac)
+{
+ struct otx2_nic *pf = netdev_priv(netdev);
+
+ return otx2_do_add_macfilter(pf, mac);
+}
+
+static bool otx2_get_mcamentry_for_mac(struct otx2_nic *pf, const u8 *mac,
+ int *mcam_entry)
+{
+ int i;
+
+ for (i = 0; i < OTX2_MAX_UNICAST_FLOWS; i++) {
+ if (!pf->mac_table[i].inuse)
+ continue;
+
+ if (ether_addr_equal(pf->mac_table[i].addr, mac)) {
+ *mcam_entry = pf->mac_table[i].mcam_entry;
+ pf->mac_table[i].inuse = false;
+ return true;
+ }
+ }
+ return false;
+}
+
+int otx2_del_macfilter(struct net_device *netdev, const u8 *mac)
+{
+ struct otx2_nic *pf = netdev_priv(netdev);
+ struct npc_delete_flow_req *req;
+ int err, mcam_entry;
+
+ /* check does mcam entry exists for given mac */
+ if (!otx2_get_mcamentry_for_mac(pf, mac, &mcam_entry))
+ return 0;
+
+ mutex_lock(&pf->mbox.lock);
+ req = otx2_mbox_alloc_msg_npc_delete_flow(&pf->mbox);
+ if (!req) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+ req->entry = mcam_entry;
+ /* Send message to AF */
+ err = otx2_sync_mbox_msg(&pf->mbox);
+ mutex_unlock(&pf->mbox.lock);
+
+ return err;
+}
+
+static struct otx2_flow *otx2_find_flow(struct otx2_nic *pfvf, u32 location)
+{
+ struct otx2_flow *iter;
+
+ list_for_each_entry(iter, &pfvf->flow_cfg->flow_list, list) {
+ if (iter->location == location)
+ return iter;
+ }
+
+ return NULL;
+}
+
+static void otx2_add_flow_to_list(struct otx2_nic *pfvf, struct otx2_flow *flow)
+{
+ struct list_head *head = &pfvf->flow_cfg->flow_list;
+ struct otx2_flow *iter;
+
+ list_for_each_entry(iter, &pfvf->flow_cfg->flow_list, list) {
+ if (iter->location > flow->location)
+ break;
+ head = &iter->list;
+ }
+
+ list_add(&flow->list, head);
+}
+
+int otx2_get_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc,
+ u32 location)
+{
+ struct otx2_flow *iter;
+
+ if (location >= pfvf->flow_cfg->ntuple_max_flows)
+ return -EINVAL;
+
+ list_for_each_entry(iter, &pfvf->flow_cfg->flow_list, list) {
+ if (iter->location == location) {
+ nfc->fs = iter->flow_spec;
+ return 0;
+ }
+ }
+
+ return -ENOENT;
+}
+
+int otx2_get_all_flows(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc,
+ u32 *rule_locs)
+{
+ u32 location = 0;
+ int idx = 0;
+ int err = 0;
+
+ nfc->data = pfvf->flow_cfg->ntuple_max_flows;
+ while ((!err || err == -ENOENT) && idx < nfc->rule_cnt) {
+ err = otx2_get_flow(pfvf, nfc, location);
+ if (!err)
+ rule_locs[idx++] = location;
+ location++;
+ }
+
+ return err;
+}
+
+static void otx2_prepare_ipv4_flow(struct ethtool_rx_flow_spec *fsp,
+ struct npc_install_flow_req *req,
+ u32 flow_type)
+{
+ struct ethtool_usrip4_spec *ipv4_usr_mask = &fsp->m_u.usr_ip4_spec;
+ struct ethtool_usrip4_spec *ipv4_usr_hdr = &fsp->h_u.usr_ip4_spec;
+ struct ethtool_tcpip4_spec *ipv4_l4_mask = &fsp->m_u.tcp_ip4_spec;
+ struct ethtool_tcpip4_spec *ipv4_l4_hdr = &fsp->h_u.tcp_ip4_spec;
+ struct flow_msg *pmask = &req->mask;
+ struct flow_msg *pkt = &req->packet;
+
+ switch (flow_type) {
+ case IP_USER_FLOW:
+ if (ipv4_usr_mask->ip4src) {
+ memcpy(&pkt->ip4src, &ipv4_usr_hdr->ip4src,
+ sizeof(pkt->ip4src));
+ memcpy(&pmask->ip4src, &ipv4_usr_mask->ip4src,
+ sizeof(pmask->ip4src));
+ req->features |= BIT_ULL(NPC_SIP_IPV4);
+ }
+ if (ipv4_usr_mask->ip4dst) {
+ memcpy(&pkt->ip4dst, &ipv4_usr_hdr->ip4dst,
+ sizeof(pkt->ip4dst));
+ memcpy(&pmask->ip4dst, &ipv4_usr_mask->ip4dst,
+ sizeof(pmask->ip4dst));
+ req->features |= BIT_ULL(NPC_DIP_IPV4);
+ }
+ break;
+ case TCP_V4_FLOW:
+ case UDP_V4_FLOW:
+ case SCTP_V4_FLOW:
+ if (ipv4_l4_mask->ip4src) {
+ memcpy(&pkt->ip4src, &ipv4_l4_hdr->ip4src,
+ sizeof(pkt->ip4src));
+ memcpy(&pmask->ip4src, &ipv4_l4_mask->ip4src,
+ sizeof(pmask->ip4src));
+ req->features |= BIT_ULL(NPC_SIP_IPV4);
+ }
+ if (ipv4_l4_mask->ip4dst) {
+ memcpy(&pkt->ip4dst, &ipv4_l4_hdr->ip4dst,
+ sizeof(pkt->ip4dst));
+ memcpy(&pmask->ip4dst, &ipv4_l4_mask->ip4dst,
+ sizeof(pmask->ip4dst));
+ req->features |= BIT_ULL(NPC_DIP_IPV4);
+ }
+ if (ipv4_l4_mask->psrc) {
+ memcpy(&pkt->sport, &ipv4_l4_hdr->psrc,
+ sizeof(pkt->sport));
+ memcpy(&pmask->sport, &ipv4_l4_mask->psrc,
+ sizeof(pmask->sport));
+ if (flow_type == UDP_V4_FLOW)
+ req->features |= BIT_ULL(NPC_SPORT_UDP);
+ else if (flow_type == TCP_V4_FLOW)
+ req->features |= BIT_ULL(NPC_SPORT_TCP);
+ else
+ req->features |= BIT_ULL(NPC_SPORT_SCTP);
+ }
+ if (ipv4_l4_mask->pdst) {
+ memcpy(&pkt->dport, &ipv4_l4_hdr->pdst,
+ sizeof(pkt->dport));
+ memcpy(&pmask->dport, &ipv4_l4_mask->pdst,
+ sizeof(pmask->dport));
+ if (flow_type == UDP_V4_FLOW)
+ req->features |= BIT_ULL(NPC_DPORT_UDP);
+ else if (flow_type == TCP_V4_FLOW)
+ req->features |= BIT_ULL(NPC_DPORT_TCP);
+ else
+ req->features |= BIT_ULL(NPC_DPORT_SCTP);
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+static void otx2_prepare_ipv6_flow(struct ethtool_rx_flow_spec *fsp,
+ struct npc_install_flow_req *req,
+ u32 flow_type)
+{
+ struct ethtool_usrip6_spec *ipv6_usr_mask = &fsp->m_u.usr_ip6_spec;
+ struct ethtool_usrip6_spec *ipv6_usr_hdr = &fsp->h_u.usr_ip6_spec;
+ struct ethtool_tcpip6_spec *ipv6_l4_mask = &fsp->m_u.tcp_ip6_spec;
+ struct ethtool_tcpip6_spec *ipv6_l4_hdr = &fsp->h_u.tcp_ip6_spec;
+ struct flow_msg *pmask = &req->mask;
+ struct flow_msg *pkt = &req->packet;
+
+ switch (flow_type) {
+ case IPV6_USER_FLOW:
+ if (!ipv6_addr_any((struct in6_addr *)ipv6_usr_mask->ip6src)) {
+ memcpy(&pkt->ip6src, &ipv6_usr_hdr->ip6src,
+ sizeof(pkt->ip6src));
+ memcpy(&pmask->ip6src, &ipv6_usr_mask->ip6src,
+ sizeof(pmask->ip6src));
+ req->features |= BIT_ULL(NPC_SIP_IPV6);
+ }
+ if (!ipv6_addr_any((struct in6_addr *)ipv6_usr_mask->ip6dst)) {
+ memcpy(&pkt->ip6dst, &ipv6_usr_hdr->ip6dst,
+ sizeof(pkt->ip6dst));
+ memcpy(&pmask->ip6dst, &ipv6_usr_mask->ip6dst,
+ sizeof(pmask->ip6dst));
+ req->features |= BIT_ULL(NPC_DIP_IPV6);
+ }
+ break;
+ case TCP_V6_FLOW:
+ case UDP_V6_FLOW:
+ case SCTP_V6_FLOW:
+ if (!ipv6_addr_any((struct in6_addr *)ipv6_l4_mask->ip6src)) {
+ memcpy(&pkt->ip6src, &ipv6_l4_hdr->ip6src,
+ sizeof(pkt->ip6src));
+ memcpy(&pmask->ip6src, &ipv6_l4_mask->ip6src,
+ sizeof(pmask->ip6src));
+ req->features |= BIT_ULL(NPC_SIP_IPV6);
+ }
+ if (!ipv6_addr_any((struct in6_addr *)ipv6_l4_mask->ip6dst)) {
+ memcpy(&pkt->ip6dst, &ipv6_l4_hdr->ip6dst,
+ sizeof(pkt->ip6dst));
+ memcpy(&pmask->ip6dst, &ipv6_l4_mask->ip6dst,
+ sizeof(pmask->ip6dst));
+ req->features |= BIT_ULL(NPC_DIP_IPV6);
+ }
+ if (ipv6_l4_mask->psrc) {
+ memcpy(&pkt->sport, &ipv6_l4_hdr->psrc,
+ sizeof(pkt->sport));
+ memcpy(&pmask->sport, &ipv6_l4_mask->psrc,
+ sizeof(pmask->sport));
+ if (flow_type == UDP_V6_FLOW)
+ req->features |= BIT_ULL(NPC_SPORT_UDP);
+ else if (flow_type == TCP_V6_FLOW)
+ req->features |= BIT_ULL(NPC_SPORT_TCP);
+ else
+ req->features |= BIT_ULL(NPC_SPORT_SCTP);
+ }
+ if (ipv6_l4_mask->pdst) {
+ memcpy(&pkt->dport, &ipv6_l4_hdr->pdst,
+ sizeof(pkt->dport));
+ memcpy(&pmask->dport, &ipv6_l4_mask->pdst,
+ sizeof(pmask->dport));
+ if (flow_type == UDP_V6_FLOW)
+ req->features |= BIT_ULL(NPC_DPORT_UDP);
+ else if (flow_type == TCP_V6_FLOW)
+ req->features |= BIT_ULL(NPC_DPORT_TCP);
+ else
+ req->features |= BIT_ULL(NPC_DPORT_SCTP);
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+int otx2_prepare_flow_request(struct ethtool_rx_flow_spec *fsp,
+ struct npc_install_flow_req *req)
+{
+ struct ethhdr *eth_mask = &fsp->m_u.ether_spec;
+ struct ethhdr *eth_hdr = &fsp->h_u.ether_spec;
+ struct flow_msg *pmask = &req->mask;
+ struct flow_msg *pkt = &req->packet;
+ u32 flow_type;
+
+ flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT);
+ switch (flow_type) {
+ /* bits not set in mask are don't care */
+ case ETHER_FLOW:
+ if (!is_zero_ether_addr(eth_mask->h_source)) {
+ ether_addr_copy(pkt->smac, eth_hdr->h_source);
+ ether_addr_copy(pmask->smac, eth_mask->h_source);
+ req->features |= BIT_ULL(NPC_SMAC);
+ }
+ if (!is_zero_ether_addr(eth_mask->h_dest)) {
+ ether_addr_copy(pkt->dmac, eth_hdr->h_dest);
+ ether_addr_copy(pmask->dmac, eth_mask->h_dest);
+ req->features |= BIT_ULL(NPC_DMAC);
+ }
+ if (eth_mask->h_proto) {
+ memcpy(&pkt->etype, ð_hdr->h_proto,
+ sizeof(pkt->etype));
+ memcpy(&pmask->etype, ð_mask->h_proto,
+ sizeof(pmask->etype));
+ req->features |= BIT_ULL(NPC_ETYPE);
+ }
+ break;
+ case IP_USER_FLOW:
+ case TCP_V4_FLOW:
+ case UDP_V4_FLOW:
+ case SCTP_V4_FLOW:
+ otx2_prepare_ipv4_flow(fsp, req, flow_type);
+ break;
+ case IPV6_USER_FLOW:
+ case TCP_V6_FLOW:
+ case UDP_V6_FLOW:
+ case SCTP_V6_FLOW:
+ otx2_prepare_ipv6_flow(fsp, req, flow_type);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+ if (fsp->flow_type & FLOW_EXT) {
+ if (fsp->m_ext.vlan_etype)
+ return -EINVAL;
+ if (fsp->m_ext.vlan_tci) {
+ if (fsp->m_ext.vlan_tci != cpu_to_be16(VLAN_VID_MASK))
+ return -EINVAL;
+ if (be16_to_cpu(fsp->h_ext.vlan_tci) >= VLAN_N_VID)
+ return -EINVAL;
+
+ memcpy(&pkt->vlan_tci, &fsp->h_ext.vlan_tci,
+ sizeof(pkt->vlan_tci));
+ memcpy(&pmask->vlan_tci, &fsp->m_ext.vlan_tci,
+ sizeof(pmask->vlan_tci));
+ req->features |= BIT_ULL(NPC_OUTER_VID);
+ }
+
+ /* Not Drop/Direct to queue but use action in default entry */
+ if (fsp->m_ext.data[1] &&
+ fsp->h_ext.data[1] == cpu_to_be32(OTX2_DEFAULT_ACTION))
+ req->op = NIX_RX_ACTION_DEFAULT;
+ }
+
+ if (fsp->flow_type & FLOW_MAC_EXT &&
+ !is_zero_ether_addr(fsp->m_ext.h_dest)) {
+ ether_addr_copy(pkt->dmac, fsp->h_ext.h_dest);
+ ether_addr_copy(pmask->dmac, fsp->m_ext.h_dest);
+ req->features |= BIT_ULL(NPC_DMAC);
+ }
+
+ if (!req->features)
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+static int otx2_add_flow_msg(struct otx2_nic *pfvf, struct otx2_flow *flow)
+{
+ u64 ring_cookie = flow->flow_spec.ring_cookie;
+ struct npc_install_flow_req *req;
+ int err, vf = 0;
+
+ mutex_lock(&pfvf->mbox.lock);
+ req = otx2_mbox_alloc_msg_npc_install_flow(&pfvf->mbox);
+ if (!req) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ err = otx2_prepare_flow_request(&flow->flow_spec, req);
+ if (err) {
+ /* free the allocated msg above */
+ otx2_mbox_reset(&pfvf->mbox.mbox, 0);
+ mutex_unlock(&pfvf->mbox.lock);
+ return err;
+ }
+
+ req->entry = flow->entry;
+ req->intf = NIX_INTF_RX;
+ req->set_cntr = 1;
+ req->channel = pfvf->hw.rx_chan_base;
+ if (ring_cookie == RX_CLS_FLOW_DISC) {
+ req->op = NIX_RX_ACTIONOP_DROP;
+ } else {
+ /* change to unicast only if action of default entry is not
+ * requested by user
+ */
+ if (req->op != NIX_RX_ACTION_DEFAULT)
+ req->op = NIX_RX_ACTIONOP_UCAST;
+ req->index = ethtool_get_flow_spec_ring(ring_cookie);
+ vf = ethtool_get_flow_spec_ring_vf(ring_cookie);
+ if (vf > pci_num_vf(pfvf->pdev)) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return -EINVAL;
+ }
+ }
+
+ /* ethtool ring_cookie has (VF + 1) for VF */
+ if (vf) {
+ req->vf = vf;
+ flow->is_vf = true;
+ flow->vf = vf;
+ }
+
+ /* Send message to AF */
+ err = otx2_sync_mbox_msg(&pfvf->mbox);
+ mutex_unlock(&pfvf->mbox.lock);
+ return err;
+}
+
+int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rx_flow_spec *fsp)
+{
+ struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
+ u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie);
+ struct otx2_flow *flow;
+ bool new = false;
+ int err;
+
+ if (!(pfvf->flags & OTX2_FLAG_NTUPLE_SUPPORT))
+ return -ENOMEM;
+
+ if (ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC)
+ return -EINVAL;
+
+ if (fsp->location >= flow_cfg->ntuple_max_flows)
+ return -EINVAL;
+
+ flow = otx2_find_flow(pfvf, fsp->location);
+ if (!flow) {
+ flow = kzalloc(sizeof(*flow), GFP_ATOMIC);
+ if (!flow)
+ return -ENOMEM;
+ flow->location = fsp->location;
+ flow->entry = flow_cfg->entry[flow_cfg->ntuple_offset +
+ flow->location];
+ new = true;
+ }
+ /* struct copy */
+ flow->flow_spec = *fsp;
+
+ err = otx2_add_flow_msg(pfvf, flow);
+ if (err) {
+ if (new)
+ kfree(flow);
+ return err;
+ }
+
+ /* add the new flow installed to list */
+ if (new) {
+ otx2_add_flow_to_list(pfvf, flow);
+ flow_cfg->nr_flows++;
+ }
+
+ return 0;
+}
+
+static int otx2_remove_flow_msg(struct otx2_nic *pfvf, u16 entry, bool all)
+{
+ struct npc_delete_flow_req *req;
+ int err;
+
+ mutex_lock(&pfvf->mbox.lock);
+ req = otx2_mbox_alloc_msg_npc_delete_flow(&pfvf->mbox);
+ if (!req) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ req->entry = entry;
+ if (all)
+ req->all = 1;
+
+ /* Send message to AF */
+ err = otx2_sync_mbox_msg(&pfvf->mbox);
+ mutex_unlock(&pfvf->mbox.lock);
+ return err;
+}
+
+int otx2_remove_flow(struct otx2_nic *pfvf, u32 location)
+{
+ struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
+ struct otx2_flow *flow;
+ int err;
+
+ if (location >= flow_cfg->ntuple_max_flows)
+ return -EINVAL;
+
+ flow = otx2_find_flow(pfvf, location);
+ if (!flow)
+ return -ENOENT;
+
+ err = otx2_remove_flow_msg(pfvf, flow->entry, false);
+ if (err)
+ return err;
+
+ list_del(&flow->list);
+ kfree(flow);
+ flow_cfg->nr_flows--;
+
+ return 0;
+}
+
+int otx2_destroy_ntuple_flows(struct otx2_nic *pfvf)
+{
+ struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
+ struct npc_delete_flow_req *req;
+ struct otx2_flow *iter, *tmp;
+ int err;
+
+ if (!(pfvf->flags & OTX2_FLAG_NTUPLE_SUPPORT))
+ return 0;
+
+ mutex_lock(&pfvf->mbox.lock);
+ req = otx2_mbox_alloc_msg_npc_delete_flow(&pfvf->mbox);
+ if (!req) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ req->start = flow_cfg->entry[flow_cfg->ntuple_offset];
+ req->end = flow_cfg->entry[flow_cfg->ntuple_offset +
+ flow_cfg->ntuple_max_flows - 1];
+ err = otx2_sync_mbox_msg(&pfvf->mbox);
+ mutex_unlock(&pfvf->mbox.lock);
+
+ list_for_each_entry_safe(iter, tmp, &flow_cfg->flow_list, list) {
+ list_del(&iter->list);
+ kfree(iter);
+ flow_cfg->nr_flows--;
+ }
+ return err;
+}
+
+int otx2_destroy_mcam_flows(struct otx2_nic *pfvf)
+{
+ struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
+ struct npc_mcam_free_entry_req *req;
+ struct otx2_flow *iter, *tmp;
+ int err;
+
+ if (!(pfvf->flags & OTX2_FLAG_MCAM_ENTRIES_ALLOC))
+ return 0;
+
+ /* remove all flows */
+ err = otx2_remove_flow_msg(pfvf, 0, true);
+ if (err)
+ return err;
+
+ list_for_each_entry_safe(iter, tmp, &flow_cfg->flow_list, list) {
+ list_del(&iter->list);
+ kfree(iter);
+ flow_cfg->nr_flows--;
+ }
+
+ mutex_lock(&pfvf->mbox.lock);
+ req = otx2_mbox_alloc_msg_npc_mcam_free_entry(&pfvf->mbox);
+ if (!req) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ req->all = 1;
+ /* Send message to AF to free MCAM entries */
+ err = otx2_sync_mbox_msg(&pfvf->mbox);
+ if (err) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return err;
+ }
+
+ pfvf->flags &= ~OTX2_FLAG_MCAM_ENTRIES_ALLOC;
+ mutex_unlock(&pfvf->mbox.lock);
+
+ return 0;
+}
+
+int otx2_install_rxvlan_offload_flow(struct otx2_nic *pfvf)
+{
+ struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
+ struct npc_install_flow_req *req;
+ int err;
+
+ mutex_lock(&pfvf->mbox.lock);
+ req = otx2_mbox_alloc_msg_npc_install_flow(&pfvf->mbox);
+ if (!req) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ req->entry = flow_cfg->entry[flow_cfg->rx_vlan_offset];
+ req->intf = NIX_INTF_RX;
+ ether_addr_copy(req->packet.dmac, pfvf->netdev->dev_addr);
+ eth_broadcast_addr((u8 *)&req->mask.dmac);
+ req->channel = pfvf->hw.rx_chan_base;
+ req->op = NIX_RX_ACTION_DEFAULT;
+ req->features = BIT_ULL(NPC_OUTER_VID) | BIT_ULL(NPC_DMAC);
+ req->vtag0_valid = true;
+ req->vtag0_type = NIX_AF_LFX_RX_VTAG_TYPE0;
+
+ /* Send message to AF */
+ err = otx2_sync_mbox_msg(&pfvf->mbox);
+ mutex_unlock(&pfvf->mbox.lock);
+ return err;
+}
+
+static int otx2_delete_rxvlan_offload_flow(struct otx2_nic *pfvf)
+{
+ struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
+ struct npc_delete_flow_req *req;
+ int err;
+
+ mutex_lock(&pfvf->mbox.lock);
+ req = otx2_mbox_alloc_msg_npc_delete_flow(&pfvf->mbox);
+ if (!req) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ req->entry = flow_cfg->entry[flow_cfg->rx_vlan_offset];
+ /* Send message to AF */
+ err = otx2_sync_mbox_msg(&pfvf->mbox);
+ mutex_unlock(&pfvf->mbox.lock);
+ return err;
+}
+
+int otx2_enable_rxvlan(struct otx2_nic *pf, bool enable)
+{
+ struct nix_vtag_config *req;
+ struct mbox_msghdr *rsp_hdr;
+ int err;
+
+ /* Dont have enough mcam entries */
+ if (!(pf->flags & OTX2_FLAG_RX_VLAN_SUPPORT))
+ return -ENOMEM;
+
+ if (enable) {
+ err = otx2_install_rxvlan_offload_flow(pf);
+ if (err)
+ return err;
+ } else {
+ err = otx2_delete_rxvlan_offload_flow(pf);
+ if (err)
+ return err;
+ }
+
+ mutex_lock(&pf->mbox.lock);
+ req = otx2_mbox_alloc_msg_nix_vtag_cfg(&pf->mbox);
+ if (!req) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ /* config strip, capture and size */
+ req->vtag_size = VTAGSIZE_T4;
+ req->cfg_type = 1; /* rx vlan cfg */
+ req->rx.vtag_type = NIX_AF_LFX_RX_VTAG_TYPE0;
+ req->rx.strip_vtag = enable;
+ req->rx.capture_vtag = enable;
+
+ err = otx2_sync_mbox_msg(&pf->mbox);
+ if (err) {
+ mutex_unlock(&pf->mbox.lock);
+ return err;
+ }
+
+ rsp_hdr = otx2_mbox_get_rsp(&pf->mbox.mbox, 0, &req->hdr);
+ if (IS_ERR(rsp_hdr)) {
+ mutex_unlock(&pf->mbox.lock);
+ return PTR_ERR(rsp_hdr);
+ }
+
+ mutex_unlock(&pf->mbox.lock);
+ return rsp_hdr->rc;
+}
static int otx2_init_hw_resources(struct otx2_nic *pf)
{
+ struct nix_lf_free_req *free_req;
struct mbox *mbox = &pf->mbox;
struct otx2_hw *hw = &pf->hw;
struct msg_req *req;
otx2_aura_pool_free(pf);
err_free_nix_lf:
mutex_lock(&mbox->lock);
- req = otx2_mbox_alloc_msg_nix_lf_free(mbox);
- if (req) {
+ free_req = otx2_mbox_alloc_msg_nix_lf_free(mbox);
+ if (free_req) {
+ free_req->flags = NIX_LF_DISABLE_FLOWS;
if (otx2_sync_mbox_msg(mbox))
dev_err(pf->dev, "%s failed to free nixlf\n", __func__);
}
static void otx2_free_hw_resources(struct otx2_nic *pf)
{
struct otx2_qset *qset = &pf->qset;
+ struct nix_lf_free_req *free_req;
struct mbox *mbox = &pf->mbox;
struct otx2_cq_queue *cq;
struct msg_req *req;
mutex_lock(&mbox->lock);
/* Reset NIX LF */
- req = otx2_mbox_alloc_msg_nix_lf_free(mbox);
- if (req) {
+ free_req = otx2_mbox_alloc_msg_nix_lf_free(mbox);
+ if (free_req) {
+ free_req->flags = NIX_LF_DISABLE_FLOWS;
+ if (!(pf->flags & OTX2_FLAG_PF_SHUTDOWN))
+ free_req->flags |= NIX_LF_DONT_FREE_TX_VTAG;
if (otx2_sync_mbox_msg(mbox))
dev_err(pf->dev, "%s failed to free nixlf\n", __func__);
}
otx2_set_cints_affinity(pf);
+ if (pf->flags & OTX2_FLAG_RX_VLAN_SUPPORT)
+ otx2_enable_rxvlan(pf, true);
+
/* When reinitializing enable time stamping if it is enabled before */
if (pf->flags & OTX2_FLAG_TX_TSTAMP_ENABLED) {
pf->flags &= ~OTX2_FLAG_TX_TSTAMP_ENABLED;
struct otx2_nic *pf = container_of(work, struct otx2_nic, rx_mode_work);
struct net_device *netdev = pf->netdev;
struct nix_rx_mode *req;
+ bool promisc = false;
if (!(netdev->flags & IFF_UP))
return;
+ if ((netdev->flags & IFF_PROMISC) ||
+ (netdev_uc_count(netdev) > OTX2_MAX_UNICAST_FLOWS)) {
+ promisc = true;
+ }
+
+ /* Write unicast address to mcam entries or del from mcam */
+ if (!promisc && netdev->priv_flags & IFF_UNICAST_FLT)
+ __dev_uc_sync(netdev, otx2_add_macfilter, otx2_del_macfilter);
+
mutex_lock(&pf->mbox.lock);
req = otx2_mbox_alloc_msg_nix_set_rx_mode(&pf->mbox);
if (!req) {
req->mode = NIX_RX_MODE_UCAST;
- /* We don't support MAC address filtering yet */
- if (netdev->flags & IFF_PROMISC)
+ if (promisc)
req->mode |= NIX_RX_MODE_PROMISC;
else if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST))
req->mode |= NIX_RX_MODE_ALLMULTI;
netdev_features_t features)
{
netdev_features_t changed = features ^ netdev->features;
+ bool ntuple = !!(features & NETIF_F_NTUPLE);
struct otx2_nic *pf = netdev_priv(netdev);
if ((changed & NETIF_F_LOOPBACK) && netif_running(netdev))
return otx2_cgx_config_loopback(pf,
features & NETIF_F_LOOPBACK);
+
+ if ((changed & NETIF_F_HW_VLAN_CTAG_RX) && netif_running(netdev))
+ return otx2_enable_rxvlan(pf,
+ features & NETIF_F_HW_VLAN_CTAG_RX);
+
+ if ((changed & NETIF_F_NTUPLE) && !ntuple)
+ otx2_destroy_ntuple_flows(pf);
+
return 0;
}
}
}
+static int otx2_do_set_vf_mac(struct otx2_nic *pf, int vf, const u8 *mac)
+{
+ struct npc_install_flow_req *req;
+ int err;
+
+ mutex_lock(&pf->mbox.lock);
+ req = otx2_mbox_alloc_msg_npc_install_flow(&pf->mbox);
+ if (!req) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ ether_addr_copy(req->packet.dmac, mac);
+ eth_broadcast_addr((u8 *)&req->mask.dmac);
+ req->features = BIT_ULL(NPC_DMAC);
+ req->channel = pf->hw.rx_chan_base;
+ req->intf = NIX_INTF_RX;
+ req->default_rule = 1;
+ req->append = 1;
+ req->vf = vf + 1;
+ req->op = NIX_RX_ACTION_DEFAULT;
+
+ err = otx2_sync_mbox_msg(&pf->mbox);
+out:
+ mutex_unlock(&pf->mbox.lock);
+ return err;
+}
+
+static int otx2_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
+{
+ struct otx2_nic *pf = netdev_priv(netdev);
+ struct pci_dev *pdev = pf->pdev;
+ struct otx2_vf_config *config;
+ int ret;
+
+ if (!netif_running(netdev))
+ return -EAGAIN;
+
+ if (vf >= pci_num_vf(pdev))
+ return -EINVAL;
+
+ if (!is_valid_ether_addr(mac))
+ return -EINVAL;
+
+ config = &pf->vf_configs[vf];
+ ether_addr_copy(config->mac, mac);
+
+ ret = otx2_do_set_vf_mac(pf, vf, mac);
+ if (ret == 0)
+ dev_info(&pdev->dev, "Reload VF driver to apply the changes\n");
+
+ return ret;
+}
+
+static int otx2_do_set_vf_vlan(struct otx2_nic *pf, int vf, u16 vlan, u8 qos,
+ __be16 proto)
+{
+ struct otx2_flow_config *flow_cfg = pf->flow_cfg;
+ struct nix_vtag_config_rsp *vtag_rsp;
+ struct npc_delete_flow_req *del_req;
+ struct nix_vtag_config *vtag_req;
+ struct npc_install_flow_req *req;
+ struct otx2_vf_config *config;
+ int err = 0;
+ u32 idx;
+
+ config = &pf->vf_configs[vf];
+
+ if (!vlan && !config->vlan)
+ goto out;
+
+ mutex_lock(&pf->mbox.lock);
+
+ /* free old tx vtag entry */
+ if (config->vlan) {
+ vtag_req = otx2_mbox_alloc_msg_nix_vtag_cfg(&pf->mbox);
+ if (!vtag_req) {
+ err = -ENOMEM;
+ goto out;
+ }
+ vtag_req->cfg_type = 0;
+ vtag_req->tx.free_vtag0 = 1;
+ vtag_req->tx.vtag0_idx = config->tx_vtag_idx;
+
+ err = otx2_sync_mbox_msg(&pf->mbox);
+ if (err)
+ goto out;
+ }
+
+ if (!vlan && config->vlan) {
+ /* rx */
+ del_req = otx2_mbox_alloc_msg_npc_delete_flow(&pf->mbox);
+ if (!del_req) {
+ err = -ENOMEM;
+ goto out;
+ }
+ idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_RX_INDEX);
+ del_req->entry =
+ flow_cfg->entry[flow_cfg->vf_vlan_offset + idx];
+ err = otx2_sync_mbox_msg(&pf->mbox);
+ if (err)
+ goto out;
+
+ /* tx */
+ del_req = otx2_mbox_alloc_msg_npc_delete_flow(&pf->mbox);
+ if (!del_req) {
+ err = -ENOMEM;
+ goto out;
+ }
+ idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_TX_INDEX);
+ del_req->entry =
+ flow_cfg->entry[flow_cfg->vf_vlan_offset + idx];
+ err = otx2_sync_mbox_msg(&pf->mbox);
+
+ goto out;
+ }
+
+ /* rx */
+ req = otx2_mbox_alloc_msg_npc_install_flow(&pf->mbox);
+ if (!req) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_RX_INDEX);
+ req->entry = flow_cfg->entry[flow_cfg->vf_vlan_offset + idx];
+ req->packet.vlan_tci = htons(vlan);
+ req->mask.vlan_tci = htons(VLAN_VID_MASK);
+ /* af fills the destination mac addr */
+ eth_broadcast_addr((u8 *)&req->mask.dmac);
+ req->features = BIT_ULL(NPC_OUTER_VID) | BIT_ULL(NPC_DMAC);
+ req->channel = pf->hw.rx_chan_base;
+ req->intf = NIX_INTF_RX;
+ req->vf = vf + 1;
+ req->op = NIX_RX_ACTION_DEFAULT;
+ req->vtag0_valid = true;
+ req->vtag0_type = NIX_AF_LFX_RX_VTAG_TYPE7;
+ req->set_cntr = 1;
+
+ err = otx2_sync_mbox_msg(&pf->mbox);
+ if (err)
+ goto out;
+
+ /* tx */
+ vtag_req = otx2_mbox_alloc_msg_nix_vtag_cfg(&pf->mbox);
+ if (!vtag_req) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ /* configure tx vtag params */
+ vtag_req->vtag_size = VTAGSIZE_T4;
+ vtag_req->cfg_type = 0; /* tx vlan cfg */
+ vtag_req->tx.cfg_vtag0 = 1;
+ vtag_req->tx.vtag0 = ((u64)ntohs(proto) << 16) | vlan;
+
+ err = otx2_sync_mbox_msg(&pf->mbox);
+ if (err)
+ goto out;
+
+ vtag_rsp = (struct nix_vtag_config_rsp *)otx2_mbox_get_rsp
+ (&pf->mbox.mbox, 0, &vtag_req->hdr);
+ if (IS_ERR(vtag_rsp)) {
+ err = PTR_ERR(vtag_rsp);
+ goto out;
+ }
+ config->tx_vtag_idx = vtag_rsp->vtag0_idx;
+
+ req = otx2_mbox_alloc_msg_npc_install_flow(&pf->mbox);
+ if (!req) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ eth_zero_addr((u8 *)&req->mask.dmac);
+ idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_TX_INDEX);
+ req->entry = flow_cfg->entry[flow_cfg->vf_vlan_offset + idx];
+ req->features = BIT_ULL(NPC_DMAC);
+ req->channel = pf->hw.tx_chan_base;
+ req->intf = NIX_INTF_TX;
+ req->vf = vf + 1;
+ req->op = NIX_TX_ACTIONOP_UCAST_DEFAULT;
+ req->vtag0_def = vtag_rsp->vtag0_idx;
+ req->vtag0_op = VTAG_INSERT;
+ req->set_cntr = 1;
+
+ err = otx2_sync_mbox_msg(&pf->mbox);
+out:
+ config->vlan = vlan;
+ mutex_unlock(&pf->mbox.lock);
+ return err;
+}
+
+static int otx2_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos,
+ __be16 proto)
+{
+ struct otx2_nic *pf = netdev_priv(netdev);
+ struct pci_dev *pdev = pf->pdev;
+
+ if (!netif_running(netdev))
+ return -EAGAIN;
+
+ if (vf >= pci_num_vf(pdev))
+ return -EINVAL;
+
+ /* qos is currently unsupported */
+ if (vlan >= VLAN_N_VID || qos)
+ return -EINVAL;
+
+ if (proto != htons(ETH_P_8021Q))
+ return -EPROTONOSUPPORT;
+
+ if (!(pf->flags & OTX2_FLAG_VF_VLAN_SUPPORT))
+ return -EOPNOTSUPP;
+
+ return otx2_do_set_vf_vlan(pf, vf, vlan, qos, proto);
+}
+
+static int otx2_get_vf_config(struct net_device *netdev, int vf,
+ struct ifla_vf_info *ivi)
+{
+ struct otx2_nic *pf = netdev_priv(netdev);
+ struct pci_dev *pdev = pf->pdev;
+ struct otx2_vf_config *config;
+
+ if (!netif_running(netdev))
+ return -EAGAIN;
+
+ if (vf >= pci_num_vf(pdev))
+ return -EINVAL;
+
+ config = &pf->vf_configs[vf];
+ ivi->vf = vf;
+ ether_addr_copy(ivi->mac, config->mac);
+ ivi->vlan = config->vlan;
+
+ return 0;
+}
+
static const struct net_device_ops otx2_netdev_ops = {
.ndo_open = otx2_open,
.ndo_stop = otx2_stop,
.ndo_tx_timeout = otx2_tx_timeout,
.ndo_get_stats64 = otx2_get_stats64,
.ndo_do_ioctl = otx2_ioctl,
+ .ndo_set_vf_mac = otx2_set_vf_mac,
+ .ndo_set_vf_vlan = otx2_set_vf_vlan,
+ .ndo_get_vf_config = otx2_get_vf_config,
};
static int otx2_wq_init(struct otx2_nic *pf)
netdev->hw_features |= NETIF_F_LOOPBACK | NETIF_F_RXALL;
+ err = otx2_mcam_flow_init(pf);
+ if (err)
+ goto err_ptp_destroy;
+
+ if (pf->flags & OTX2_FLAG_NTUPLE_SUPPORT)
+ netdev->hw_features |= NETIF_F_NTUPLE;
+
+ if (pf->flags & OTX2_FLAG_UCAST_FLTR_SUPPORT)
+ netdev->priv_flags |= IFF_UNICAST_FLT;
+
+ /* Support TSO on tag interface */
+ netdev->vlan_features |= netdev->features;
+ netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX;
+ if (pf->flags & OTX2_FLAG_RX_VLAN_SUPPORT)
+ netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_HW_VLAN_STAG_RX;
+ netdev->features |= netdev->hw_features;
+
netdev->gso_max_segs = OTX2_MAX_GSO_SEGS;
netdev->watchdog_timeo = OTX2_TX_TIMEOUT;
err = register_netdev(netdev);
if (err) {
dev_err(dev, "Failed to register netdevice\n");
- goto err_ptp_destroy;
+ goto err_del_mcam_entries;
}
err = otx2_wq_init(pf);
err_unreg_netdev:
unregister_netdev(netdev);
+err_del_mcam_entries:
+ otx2_mcam_flow_del(pf);
err_ptp_destroy:
otx2_ptp_destroy(pf);
err_detach_rsrc:
pf = netdev_priv(netdev);
+ pf->flags |= OTX2_FLAG_PF_SHUTDOWN;
+
if (pf->flags & OTX2_FLAG_TX_TSTAMP_ENABLED)
otx2_config_hw_tx_tstamp(pf, false);
if (pf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED)
destroy_workqueue(pf->otx2_wq);
otx2_ptp_destroy(pf);
+ otx2_mcam_flow_del(pf);
otx2_detach_resources(&pf->mbox);
otx2_disable_mbox_intr(pf);
otx2_pfaf_mbox_destroy(pf);
ext->tstmp = 1;
}
+#define OTX2_VLAN_PTR_OFFSET (ETH_HLEN - ETH_TLEN)
+ if (skb_vlan_tag_present(skb)) {
+ if (skb->vlan_proto == htons(ETH_P_8021Q)) {
+ ext->vlan1_ins_ena = 1;
+ ext->vlan1_ins_ptr = OTX2_VLAN_PTR_OFFSET;
+ ext->vlan1_ins_tci = skb_vlan_tag_get(skb);
+ } else if (skb->vlan_proto == htons(ETH_P_8021AD)) {
+ ext->vlan0_ins_ena = 1;
+ ext->vlan0_ins_ptr = OTX2_VLAN_PTR_OFFSET;
+ ext->vlan0_ins_tci = skb_vlan_tag_get(skb);
+ }
+ }
+
*offset += sizeof(*ext);
}
}
if (skb_shinfo(skb)->gso_size && !is_hw_tso_supported(pfvf, skb)) {
+ /* Insert vlan tag before giving pkt to tso */
+ if (skb_vlan_tag_present(skb))
+ skb = __vlan_hwaccel_push_inside(skb);
otx2_sq_append_tso(pfvf, sq, skb, qidx);
return true;
}
NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 |
NETIF_F_GSO_UDP_L4;
netdev->features = netdev->hw_features;
+ /* Support TSO on tag interface */
+ netdev->vlan_features |= netdev->features;
+ netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX;
+ netdev->features |= netdev->hw_features;
netdev->gso_max_segs = OTX2_MAX_GSO_SEGS;
netdev->watchdog_timeo = OTX2_TX_TIMEOUT;
};
if (chipid >= CHIP_ID_YUKON_XL && chipid <= CHIP_ID_YUKON_OP_2)
- strncpy(buf, name[chipid - CHIP_ID_YUKON_XL], sz);
+ snprintf(buf, sz, "%s", name[chipid - CHIP_ID_YUKON_XL]);
else
snprintf(buf, sz, "(chip %#x)", chipid);
return buf;
if (mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 1))
en_dbg(HW, priv, "Failed dumping statistics\n");
- memset(&priv->pstats, 0, sizeof(priv->pstats));
memset(&priv->pkstats, 0, sizeof(priv->pkstats));
memset(&priv->port_stats, 0, sizeof(priv->port_stats));
memset(&priv->rx_flowstats, 0, sizeof(priv->rx_flowstats));
xdp_prog = rcu_dereference(ring->xdp_prog);
xdp.rxq = &ring->xdp_rxq;
xdp.frame_sz = priv->frag_info[0].frag_stride;
- doorbell_pending = 0;
+ doorbell_pending = false;
/* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx
* descriptor offset can be deduced from the CQE index instead of
wmb(); /* ensure HW sees CQ consumer before we post new buffers */
ring->cons = cq->mcq.cons_index;
}
- AVG_PERF_COUNTER(priv->pstats.rx_coal_avg, polled);
mlx4_en_refill_rx_buffers(priv, ring);
/* in case we got here because of !clean_complete */
done = budget;
- INC_PERF_COUNTER(priv->pstats.napi_quota);
-
cpu_curr = smp_processor_id();
idata = irq_desc_get_irq_data(cq->irq_desc);
aff = irq_data_get_affinity_mask(idata);
if (unlikely(!priv->port_up))
goto tx_drop;
- /* fetch ring->cons far ahead before needing it to avoid stall */
- ring_cons = READ_ONCE(ring->cons);
-
real_size = get_real_size(skb, shinfo, dev, &lso_header_size,
&inline_ok, &fragptr);
if (unlikely(!real_size))
netdev_txq_bql_enqueue_prefetchw(ring->tx_queue);
- /* Track current inflight packets for performance analysis */
- AVG_PERF_COUNTER(priv->pstats.inflight_avg,
- (u32)(ring->prod - ring_cons - 1));
-
/* Packet is good - grab an index and transmit it */
index = ring->prod & ring->size_mask;
bf_index = ring->prod;
ring->packets++;
}
ring->bytes += tx_info->nr_bytes;
- AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, skb->len);
if (tx_info->inl)
build_inline_wqe(tx_desc, skb, shinfo, fragptr);
index = ring->prod & ring->size_mask;
tx_info = &ring->tx_info[index];
- /* Track current inflight packets for performance analysis */
- AVG_PERF_COUNTER(priv->pstats.inflight_avg,
- (u32)(ring->prod - READ_ONCE(ring->cons) - 1));
-
tx_desc = ring->buf + (index << LOG_TXBB_SIZE);
data = &tx_desc->data;
cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0);
rx_ring->xdp_tx++;
- AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, length);
ring->prod += MLX4_EN_XDP_TX_NRTXBB;
* @dev: mlx4_dev.
* @port: Physical port number.
* @vport: Vport id.
- * @out_param: Array of mlx4_vport_qos_param which holds the requested values.
+ * @in_param: Array of mlx4_vport_qos_param which holds the requested values.
*
* Returns 0 on success or a negative mlx4_core errno code.
**/
#include <linux/bitops.h>
#include <linux/compiler.h>
+#include <linux/ethtool.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/netdevice.h>
#define MLX4_EN_LOOPBACK_RETRIES 5
#define MLX4_EN_LOOPBACK_TIMEOUT 100
-#ifdef MLX4_EN_PERF_STAT
-/* Number of samples to 'average' */
-#define AVG_SIZE 128
-#define AVG_FACTOR 1024
-
-#define INC_PERF_COUNTER(cnt) (++(cnt))
-#define ADD_PERF_COUNTER(cnt, add) ((cnt) += (add))
-#define AVG_PERF_COUNTER(cnt, sample) \
- ((cnt) = ((cnt) * (AVG_SIZE - 1) + (sample) * AVG_FACTOR) / AVG_SIZE)
-#define GET_PERF_COUNTER(cnt) (cnt)
-#define GET_AVG_PERF_COUNTER(cnt) ((cnt) / AVG_FACTOR)
-
-#else
-
-#define INC_PERF_COUNTER(cnt) do {} while (0)
-#define ADD_PERF_COUNTER(cnt, add) do {} while (0)
-#define AVG_PERF_COUNTER(cnt, sample) do {} while (0)
-#define GET_PERF_COUNTER(cnt) (0)
-#define GET_AVG_PERF_COUNTER(cnt) (0)
-#endif /* MLX4_EN_PERF_STAT */
-
/* Constants for TX flow */
enum {
MAX_INLINE = 104, /* 128 - 16 - 4 - 4 */
struct work_struct linkstate_task;
struct delayed_work stats_task;
struct delayed_work service_task;
- struct mlx4_en_perf_stats pstats;
struct mlx4_en_pkt_stats pkstats;
struct mlx4_en_counter_stats pf_stats;
struct mlx4_en_flow_stats_rx rx_priority_flowstats[MLX4_NUM_PRIORITIES];
#ifndef _MLX4_STATS_
#define _MLX4_STATS_
-#ifdef MLX4_EN_PERF_STAT
-#define NUM_PERF_STATS NUM_PERF_COUNTERS
-#else
-#define NUM_PERF_STATS 0
-#endif
-
#define NUM_PRIORITIES 9
#define NUM_PRIORITY_STATS 2
#define NUM_PORT_STATS 10
};
-struct mlx4_en_perf_stats {
- u32 tx_poll;
- u64 tx_pktsz_avg;
- u32 inflight_avg;
- u16 tx_coal_avg;
- u16 rx_coal_avg;
- u32 napi_quota;
-#define NUM_PERF_COUNTERS 6
-};
-
struct mlx4_en_xdp_stats {
unsigned long rx_xdp_drop;
unsigned long rx_xdp_tx;
};
#define NUM_ALL_STATS (NUM_MAIN_STATS + NUM_PORT_STATS + NUM_PKT_STATS + \
- NUM_FLOW_STATS + NUM_PERF_STATS + NUM_PF_STATS + \
+ NUM_FLOW_STATS + NUM_PF_STATS + \
NUM_XDP_STATS + NUM_PHY_STATS)
#define MLX4_FIND_NETDEV_STAT(n) (offsetof(struct net_device_stats, n) / \
case RES_FS_RULE: return "RES_FS_RULE";
case RES_XRCD: return "RES_XRCD";
default: return "Unknown resource type !!!";
- };
+ }
}
static void rem_slave_vlans(struct mlx4_dev *dev, int slave);
mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o \
steering/dr_matcher.o steering/dr_rule.o \
- steering/dr_icm_pool.o \
+ steering/dr_icm_pool.o steering/dr_buddy.o \
steering/dr_ste.o steering/dr_send.o \
steering/dr_cmd.o steering/dr_fw.o \
steering/dr_action.o steering/fs_dr.o
kvfree(cmd->stats);
return err;
}
-EXPORT_SYMBOL(mlx5_cmd_init);
void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
{
dma_pool_destroy(cmd->pool);
kvfree(cmd->stats);
}
-EXPORT_SYMBOL(mlx5_cmd_cleanup);
void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
enum mlx5_cmdif_state cmdif_state)
{
dev->cmd.state = cmdif_state;
}
-EXPORT_SYMBOL(mlx5_cmd_set_state);
struct netlink_ext_ack *extack)
{
struct mlx5_core_dev *dev = devlink_priv(devlink);
- const struct firmware *fw;
- int err;
-
- err = request_firmware_direct(&fw, params->file_name, &dev->pdev->dev);
- if (err)
- return err;
-
- err = mlx5_firmware_flash(dev, fw, extack);
- release_firmware(fw);
- return err;
+ return mlx5_firmware_flash(dev, params->fw, extack);
}
static u8 mlx5_fw_ver_major(u32 version)
case MLX5_FLOW_DESTINATION_TYPE_TIR:
trace_seq_printf(p, "tir=%u\n", dst->tir_num);
break;
+ case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
+ trace_seq_printf(p, "sampler_id=%u\n", dst->sampler_id);
+ break;
case MLX5_FLOW_DESTINATION_TYPE_COUNTER:
trace_seq_printf(p, "counter_id=%u\n", counter_id);
break;
return (ioread32be(&dev->iseg->initializing) >> MLX5_ECPU_BIT_NUM) & 1;
}
-static int mlx5_peer_pf_init(struct mlx5_core_dev *dev)
+static bool mlx5_ecpf_esw_admins_host_pf(const struct mlx5_core_dev *dev)
{
- u32 in[MLX5_ST_SZ_DW(enable_hca_in)] = {};
- int err;
+ /* In separate host mode, PF enables itself.
+ * When ECPF is eswitch manager, eswitch enables host PF after
+ * eswitch is setup.
+ */
+ return mlx5_core_is_ecpf_esw_manager(dev);
+}
+
+int mlx5_cmd_host_pf_enable_hca(struct mlx5_core_dev *dev)
+{
+ u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(enable_hca_in)] = {};
MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA);
- err = mlx5_cmd_exec_in(dev, enable_hca, in);
+ MLX5_SET(enable_hca_in, in, function_id, 0);
+ MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0);
+ return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+}
+
+int mlx5_cmd_host_pf_disable_hca(struct mlx5_core_dev *dev)
+{
+ u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(disable_hca_in)] = {};
+
+ MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
+ MLX5_SET(disable_hca_in, in, function_id, 0);
+ MLX5_SET(disable_hca_in, in, embedded_cpu_function, 0);
+ return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_host_pf_init(struct mlx5_core_dev *dev)
+{
+ int err;
+
+ if (mlx5_ecpf_esw_admins_host_pf(dev))
+ return 0;
+
+ /* ECPF shall enable HCA for host PF in the same way a PF
+ * does this for its VFs when ECPF is not a eswitch manager.
+ */
+ err = mlx5_cmd_host_pf_enable_hca(dev);
if (err)
- mlx5_core_err(dev, "Failed to enable peer PF HCA err(%d)\n",
- err);
+ mlx5_core_err(dev, "Failed to enable external host PF HCA err(%d)\n", err);
return err;
}
-static void mlx5_peer_pf_cleanup(struct mlx5_core_dev *dev)
+static void mlx5_host_pf_cleanup(struct mlx5_core_dev *dev)
{
- u32 in[MLX5_ST_SZ_DW(disable_hca_in)] = {};
int err;
- MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
- err = mlx5_cmd_exec_in(dev, disable_hca, in);
+ if (mlx5_ecpf_esw_admins_host_pf(dev))
+ return;
+
+ err = mlx5_cmd_host_pf_disable_hca(dev);
if (err) {
- mlx5_core_err(dev, "Failed to disable peer PF HCA err(%d)\n",
- err);
+ mlx5_core_err(dev, "Failed to disable external host PF HCA err(%d)\n", err);
return;
}
-
- err = mlx5_wait_for_pages(dev, &dev->priv.peer_pf_pages);
- if (err)
- mlx5_core_warn(dev, "Timeout reclaiming peer PF pages err(%d)\n",
- err);
}
int mlx5_ec_init(struct mlx5_core_dev *dev)
if (!mlx5_core_is_ecpf(dev))
return 0;
- /* ECPF shall enable HCA for peer PF in the same way a PF
- * does this for its VFs.
- */
- return mlx5_peer_pf_init(dev);
+ return mlx5_host_pf_init(dev);
}
void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
{
+ int err;
+
if (!mlx5_core_is_ecpf(dev))
return;
- mlx5_peer_pf_cleanup(dev);
+ mlx5_host_pf_cleanup(dev);
+
+ err = mlx5_wait_for_pages(dev, &dev->priv.host_pf_pages);
+ if (err)
+ mlx5_core_warn(dev, "Timeout reclaiming external host PF pages err(%d)\n", err);
}
int mlx5_ec_init(struct mlx5_core_dev *dev);
void mlx5_ec_cleanup(struct mlx5_core_dev *dev);
+int mlx5_cmd_host_pf_enable_hca(struct mlx5_core_dev *dev);
+int mlx5_cmd_host_pf_disable_hca(struct mlx5_core_dev *dev);
+
#else /* CONFIG_MLX5_ESWITCH */
static inline bool
/* Copyright (c) 2019 Mellanox Technologies. */
#include "en/params.h"
+#include "en/txrx.h"
+#include "en_accel/tls_rxtx.h"
static inline bool mlx5e_rx_is_xdp(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk)
return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0;
}
+
+u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
+{
+ bool is_mpwqe = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE);
+ u16 stop_room;
+
+ stop_room = mlx5e_tls_get_stop_room(mdev, params);
+ stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS);
+ if (is_mpwqe)
+ /* A MPWQE can take up to the maximum-sized WQE + all the normal
+ * stop room can be taken if a new packet breaks the active
+ * MPWQE session and allocates its WQEs right away.
+ */
+ stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS);
+
+ return stop_room;
+}
+
+int mlx5e_validate_params(struct mlx5e_priv *priv, struct mlx5e_params *params)
+{
+ size_t sq_size = 1 << params->log_sq_size;
+ u16 stop_room;
+
+ stop_room = mlx5e_calc_sq_stop_room(priv->mdev, params);
+ if (stop_room >= sq_size) {
+ netdev_err(priv->netdev, "Stop room %hu is bigger than the SQ size %zu\n",
+ stop_room, sq_size);
+ return -EINVAL;
+ }
+
+ return 0;
+}
u32 sqc[MLX5_ST_SZ_DW(sqc)];
struct mlx5_wq_param wq;
bool is_mpw;
+ u16 stop_room;
};
struct mlx5e_channel_param {
struct mlx5e_params *params,
struct mlx5e_sq_param *param);
+u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
+int mlx5e_validate_params(struct mlx5e_priv *priv, struct mlx5e_params *params);
+
#endif /* __MLX5_EN_PARAMS_H__ */
static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
struct mlx5e_xdp_wqe_info *wi,
u32 *xsk_frames,
- bool recycle)
+ bool recycle,
+ struct xdp_frame_bulk *bq)
{
struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
u16 i;
/* XDP_TX from the XSK RQ and XDP_REDIRECT */
dma_unmap_single(sq->pdev, xdpi.frame.dma_addr,
xdpi.frame.xdpf->len, DMA_TO_DEVICE);
- xdp_return_frame(xdpi.frame.xdpf);
+ xdp_return_frame_bulk(xdpi.frame.xdpf, bq);
break;
case MLX5E_XDP_XMIT_MODE_PAGE:
/* XDP_TX from the regular RQ */
bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
{
+ struct xdp_frame_bulk bq;
struct mlx5e_xdpsq *sq;
struct mlx5_cqe64 *cqe;
u32 xsk_frames = 0;
u16 sqcc;
int i;
+ xdp_frame_bulk_init(&bq);
+
sq = container_of(cq, struct mlx5e_xdpsq, cq);
if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
sqcc += wi->num_wqebbs;
- mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true);
+ mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true, &bq);
} while (!last_wqe);
if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
}
} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
+ xdp_flush_frame_bulk(&bq);
+
if (xsk_frames)
xsk_tx_completed(sq->xsk_pool, xsk_frames);
void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
{
+ struct xdp_frame_bulk bq;
u32 xsk_frames = 0;
+ xdp_frame_bulk_init(&bq);
+
+ rcu_read_lock(); /* need for xdp_return_frame_bulk */
+
while (sq->cc != sq->pc) {
struct mlx5e_xdp_wqe_info *wi;
u16 ci;
sq->cc += wi->num_wqebbs;
- mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, false);
+ mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, false, &bq);
}
+ xdp_flush_frame_bulk(&bq);
+ rcu_read_unlock();
+
if (xsk_frames)
xsk_tx_completed(sq->xsk_pool, xsk_frames);
}
(DIV_ROUND_UP(sizeof(struct mlx5e_dump_wqe), MLX5_SEND_WQE_BB))
static u8
-mlx5e_ktls_dumps_num_wqes(struct mlx5e_txqsq *sq, unsigned int nfrags,
+mlx5e_ktls_dumps_num_wqes(struct mlx5e_params *params, unsigned int nfrags,
unsigned int sync_len)
{
/* Given the MTU and sync_len, calculates an upper bound for the
* number of DUMP WQEs needed for the TX resync of a record.
*/
- return nfrags + DIV_ROUND_UP(sync_len, sq->hw_mtu);
+ return nfrags + DIV_ROUND_UP(sync_len, MLX5E_SW2HW_MTU(params, params->sw_mtu));
}
-u16 mlx5e_ktls_get_stop_room(struct mlx5e_txqsq *sq)
+u16 mlx5e_ktls_get_stop_room(struct mlx5e_params *params)
{
u16 num_dumps, stop_room = 0;
- num_dumps = mlx5e_ktls_dumps_num_wqes(sq, MAX_SKB_FRAGS, TLS_MAX_PAYLOAD_SIZE);
+ num_dumps = mlx5e_ktls_dumps_num_wqes(params, MAX_SKB_FRAGS, TLS_MAX_PAYLOAD_SIZE);
stop_room += mlx5e_stop_room_for_wqe(MLX5E_TLS_SET_STATIC_PARAMS_WQEBBS);
stop_room += mlx5e_stop_room_for_wqe(MLX5E_TLS_SET_PROGRESS_PARAMS_WQEBBS);
u32 tls_tisn;
};
-u16 mlx5e_ktls_get_stop_room(struct mlx5e_txqsq *sq);
+u16 mlx5e_ktls_get_stop_room(struct mlx5e_params *params);
bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *sq,
struct sk_buff *skb, int datalen,
*cqe_bcnt -= MLX5E_METADATA_ETHER_LEN;
}
-u16 mlx5e_tls_get_stop_room(struct mlx5e_txqsq *sq)
+u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
{
- struct mlx5_core_dev *mdev = sq->channel->mdev;
-
if (!mlx5_accel_is_tls_device(mdev))
return 0;
if (mlx5_accel_is_ktls_device(mdev))
- return mlx5e_ktls_get_stop_room(sq);
+ return mlx5e_ktls_get_stop_room(params);
/* FPGA */
/* Resync SKB. */
#include "en.h"
#include "en/txrx.h"
-u16 mlx5e_tls_get_stop_room(struct mlx5e_txqsq *sq);
+u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
struct sk_buff *skb, struct mlx5e_accel_tx_tls_state *state);
static inline void
mlx5e_tls_handle_rx_skb(struct mlx5e_rq *rq, struct sk_buff *skb,
struct mlx5_cqe64 *cqe, u32 *cqe_bcnt) {}
-static inline u16 mlx5e_tls_get_stop_room(struct mlx5e_txqsq *sq)
+static inline u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
{
return 0;
}
#include "en.h"
#include "en/port.h"
+#include "en/params.h"
#include "en/xsk/pool.h"
#include "lib/clock.h"
new_channels.params.log_rq_mtu_frames = log_rq_size;
new_channels.params.log_sq_size = log_sq_size;
+ err = mlx5e_validate_params(priv, &new_channels.params);
+ if (err)
+ goto unlock;
+
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
priv->channels.params = new_channels.params;
goto unlock;
return 0;
}
-static int mlx5e_calc_sq_stop_room(struct mlx5e_txqsq *sq, u8 log_sq_size)
-{
- int sq_size = 1 << log_sq_size;
-
- sq->stop_room = mlx5e_tls_get_stop_room(sq);
- sq->stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS);
- if (test_bit(MLX5E_SQ_STATE_MPWQE, &sq->state))
- /* A MPWQE can take up to the maximum-sized WQE + all the normal
- * stop room can be taken if a new packet breaks the active
- * MPWQE session and allocates its WQEs right away.
- */
- sq->stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS);
-
- if (WARN_ON(sq->stop_room >= sq_size)) {
- netdev_err(sq->channel->netdev, "Stop room %hu is bigger than the SQ size %d\n",
- sq->stop_room, sq_size);
- return -ENOSPC;
- }
-
- return 0;
-}
-
static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work);
static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
int txq_ix,
set_bit(MLX5E_SQ_STATE_TLS, &sq->state);
if (param->is_mpw)
set_bit(MLX5E_SQ_STATE_MPWQE, &sq->state);
- err = mlx5e_calc_sq_stop_room(sq, params->log_sq_size);
- if (err)
- return err;
+ sq->stop_room = param->stop_room;
param->wq.db_numa_node = cpu_to_node(c->cpu);
err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl);
MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
MLX5_SET(sqc, sqc, allow_swp, allow_swp);
param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE);
+ param->stop_room = mlx5e_calc_sq_stop_room(priv->mdev, params);
mlx5e_build_tx_cq_param(priv, params, ¶m->cqp);
}
new_channels.params = *params;
new_channels.params.sw_mtu = new_mtu;
+ err = mlx5e_validate_params(priv, &new_channels.params);
+ if (err)
+ goto out;
if (params->xdp_prog &&
!mlx5e_rx_is_linear_skb(&new_channels.params, NULL)) {
return count_eqe;
}
-static void mlx5_eq_async_int_lock(struct mlx5_eq_async *eq, unsigned long *flags)
+static void mlx5_eq_async_int_lock(struct mlx5_eq_async *eq, bool recovery,
+ unsigned long *flags)
__acquires(&eq->lock)
{
- if (in_irq())
+ if (!recovery)
spin_lock(&eq->lock);
else
spin_lock_irqsave(&eq->lock, *flags);
}
-static void mlx5_eq_async_int_unlock(struct mlx5_eq_async *eq, unsigned long *flags)
+static void mlx5_eq_async_int_unlock(struct mlx5_eq_async *eq, bool recovery,
+ unsigned long *flags)
__releases(&eq->lock)
{
- if (in_irq())
+ if (!recovery)
spin_unlock(&eq->lock);
else
spin_unlock_irqrestore(&eq->lock, *flags);
struct mlx5_eqe *eqe;
unsigned long flags;
int num_eqes = 0;
+ bool recovery;
dev = eq->dev;
eqt = dev->priv.eq_table;
- mlx5_eq_async_int_lock(eq_async, &flags);
+ recovery = action == ASYNC_EQ_RECOVER;
+ mlx5_eq_async_int_lock(eq_async, recovery, &flags);
eqe = next_eqe_sw(eq);
if (!eqe)
out:
eq_update_ci(eq, 1);
- mlx5_eq_async_int_unlock(eq_async, &flags);
+ mlx5_eq_async_int_unlock(eq_async, recovery, &flags);
- return unlikely(action == ASYNC_EQ_RECOVER) ? num_eqes : 0;
+ return unlikely(recovery) ? num_eqes : 0;
}
void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev)
struct mlx5_flow_table *
esw_acl_table_create(struct mlx5_eswitch *esw, u16 vport_num, int ns, int size)
{
+ struct mlx5_flow_table_attr ft_attr = {};
struct mlx5_core_dev *dev = esw->dev;
struct mlx5_flow_namespace *root_ns;
struct mlx5_flow_table *acl;
return ERR_PTR(-EOPNOTSUPP);
}
- acl = mlx5_create_vport_flow_table(root_ns, 0, size, 0, vport_num);
+ ft_attr.max_fte = size;
+ ft_attr.flags = MLX5_FLOW_TABLE_OTHER_VPORT;
+ acl = mlx5_create_vport_flow_table(root_ns, &ft_attr, vport_num);
if (IS_ERR(acl)) {
err = PTR_ERR(acl);
esw_warn(dev, "vport[%d] create %s ACL table, err(%d)\n", vport_num,
return err;
}
+static int host_pf_enable_hca(struct mlx5_core_dev *dev)
+{
+ if (!mlx5_core_is_ecpf(dev))
+ return 0;
+
+ /* Once vport and representor are ready, take out the external host PF
+ * out of initializing state. Enabling HCA clears the iser->initializing
+ * bit and host PF driver loading can progress.
+ */
+ return mlx5_cmd_host_pf_enable_hca(dev);
+}
+
+static void host_pf_disable_hca(struct mlx5_core_dev *dev)
+{
+ if (!mlx5_core_is_ecpf(dev))
+ return;
+
+ mlx5_cmd_host_pf_disable_hca(dev);
+}
+
/* mlx5_eswitch_enable_pf_vf_vports() enables vports of PF, ECPF and VFs
* whichever are present on the eswitch.
*/
if (ret)
return ret;
+ /* Enable external host PF HCA */
+ ret = host_pf_enable_hca(esw->dev);
+ if (ret)
+ goto pf_hca_err;
+
/* Enable ECPF vport */
if (mlx5_ecpf_vport_exists(esw->dev)) {
ret = mlx5_eswitch_load_vport(esw, MLX5_VPORT_ECPF, enabled_events);
vf_err:
if (mlx5_ecpf_vport_exists(esw->dev))
mlx5_eswitch_unload_vport(esw, MLX5_VPORT_ECPF);
-
ecpf_err:
+ host_pf_disable_hca(esw->dev);
+pf_hca_err:
mlx5_eswitch_unload_vport(esw, MLX5_VPORT_PF);
return ret;
}
if (mlx5_ecpf_vport_exists(esw->dev))
mlx5_eswitch_unload_vport(esw, MLX5_VPORT_ECPF);
+ host_pf_disable_hca(esw->dev);
mlx5_eswitch_unload_vport(esw, MLX5_VPORT_PF);
}
/**
* enum mlx5_fpga_access_type - Enumerated the different methods possible for
* accessing the device memory address space
+ *
+ * @MLX5_FPGA_ACCESS_TYPE_I2C: Use the slow CX-FPGA I2C bus
+ * @MLX5_FPGA_ACCESS_TYPE_DONTCARE: Use the fastest available method
*/
enum mlx5_fpga_access_type {
- /** Use the slow CX-FPGA I2C bus */
MLX5_FPGA_ACCESS_TYPE_I2C = 0x0,
- /** Use the fastest available method */
MLX5_FPGA_ACCESS_TYPE_DONTCARE = 0x0,
};
* subsequent receives.
*/
void (*recv_cb)(void *cb_arg, struct mlx5_fpga_dma_buf *buf);
+ /** @cb_arg: A context to be passed to recv_cb callback */
void *cb_arg;
};
/**
* mlx5_fpga_sbu_conn_sendmsg() - Queue the transmission of a packet
- * @fdev: An FPGA SBU connection
+ * @conn: An FPGA SBU connection
* @buf: The packet buffer
*
* Queues a packet for transmission over an FPGA SBU connection.
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);
- MLX5_SET(set_flow_table_root_in, in, other_vport, 1);
- }
+ MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport);
+ MLX5_SET(set_flow_table_root_in, in, other_vport,
+ !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
return mlx5_cmd_exec_in(dev, set_flow_table_root, in);
}
MLX5_SET(create_flow_table_in, in, table_type, ft->type);
MLX5_SET(create_flow_table_in, in, flow_table_context.level, ft->level);
MLX5_SET(create_flow_table_in, in, flow_table_context.log_size, log_size);
- if (ft->vport) {
- MLX5_SET(create_flow_table_in, in, vport_number, ft->vport);
- MLX5_SET(create_flow_table_in, in, other_vport, 1);
- }
+ MLX5_SET(create_flow_table_in, in, vport_number, ft->vport);
+ MLX5_SET(create_flow_table_in, in, other_vport,
+ !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
MLX5_SET(create_flow_table_in, in, flow_table_context.decap_en,
en_decap);
MLX5_CMD_OP_DESTROY_FLOW_TABLE);
MLX5_SET(destroy_flow_table_in, in, table_type, ft->type);
MLX5_SET(destroy_flow_table_in, in, table_id, ft->id);
- if (ft->vport) {
- MLX5_SET(destroy_flow_table_in, in, vport_number, ft->vport);
- MLX5_SET(destroy_flow_table_in, in, other_vport, 1);
- }
+ MLX5_SET(destroy_flow_table_in, in, vport_number, ft->vport);
+ MLX5_SET(destroy_flow_table_in, in, other_vport,
+ !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
return mlx5_cmd_exec_in(dev, destroy_flow_table, in);
}
flow_table_context.lag_master_next_table_id, 0);
}
} else {
- if (ft->vport) {
- MLX5_SET(modify_flow_table_in, in, vport_number,
- ft->vport);
- MLX5_SET(modify_flow_table_in, in, other_vport, 1);
- }
+ MLX5_SET(modify_flow_table_in, in, vport_number, ft->vport);
+ MLX5_SET(modify_flow_table_in, in, other_vport,
+ !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
MLX5_SET(modify_flow_table_in, in, modify_field_select,
MLX5_MODIFY_FLOW_TABLE_MISS_TABLE_ID);
if (next_ft) {
MLX5_SET(create_flow_group_in, in, other_vport, 1);
}
+ MLX5_SET(create_flow_group_in, in, vport_number, ft->vport);
+ MLX5_SET(create_flow_group_in, in, other_vport,
+ !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
err = mlx5_cmd_exec_inout(dev, create_flow_group, in, out);
if (!err)
fg->id = MLX5_GET(create_flow_group_out, out,
MLX5_SET(destroy_flow_group_in, in, table_type, ft->type);
MLX5_SET(destroy_flow_group_in, in, table_id, ft->id);
MLX5_SET(destroy_flow_group_in, in, group_id, fg->id);
- if (ft->vport) {
- MLX5_SET(destroy_flow_group_in, in, vport_number, ft->vport);
- MLX5_SET(destroy_flow_group_in, in, other_vport, 1);
- }
-
+ MLX5_SET(destroy_flow_group_in, in, vport_number, ft->vport);
+ MLX5_SET(destroy_flow_group_in, in, other_vport,
+ !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
return mlx5_cmd_exec_in(dev, destroy_flow_group, in);
}
MLX5_SET(set_fte_in, in, ignore_flow_level,
!!(fte->action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL));
- if (ft->vport) {
- MLX5_SET(set_fte_in, in, vport_number, ft->vport);
- MLX5_SET(set_fte_in, in, other_vport, 1);
- }
+ MLX5_SET(set_fte_in, in, vport_number, ft->vport);
+ MLX5_SET(set_fte_in, in, other_vport,
+ !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context);
MLX5_SET(flow_context, in_flow_context, group_id, group_id);
dst->dest_attr.vport.pkt_reformat->id);
}
break;
+ case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
+ id = dst->dest_attr.sampler_id;
+ break;
default:
id = dst->dest_attr.tir_num;
}
MLX5_SET(delete_fte_in, in, table_type, ft->type);
MLX5_SET(delete_fte_in, in, table_id, ft->id);
MLX5_SET(delete_fte_in, in, flow_index, fte->index);
- if (ft->vport) {
- MLX5_SET(delete_fte_in, in, vport_number, ft->vport);
- MLX5_SET(delete_fte_in, in, other_vport, 1);
- }
+ MLX5_SET(delete_fte_in, in, vport_number, ft->vport);
+ MLX5_SET(delete_fte_in, in, other_vport,
+ !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
return mlx5_cmd_exec_in(dev, delete_fte, in);
}
{
return __mlx5_create_flow_table(ns, ft_attr, FS_FT_OP_MOD_NORMAL, 0);
}
+EXPORT_SYMBOL(mlx5_create_flow_table);
-struct mlx5_flow_table *mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
- int prio, int max_fte,
- u32 level, u16 vport)
+struct mlx5_flow_table *
+mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
+ struct mlx5_flow_table_attr *ft_attr, u16 vport)
{
- struct mlx5_flow_table_attr ft_attr = {};
-
- ft_attr.max_fte = max_fte;
- ft_attr.level = level;
- ft_attr.prio = prio;
-
- return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_NORMAL, vport);
+ return __mlx5_create_flow_table(ns, ft_attr, FS_FT_OP_MOD_NORMAL, vport);
}
struct mlx5_flow_table*
return fg;
}
+EXPORT_SYMBOL(mlx5_create_flow_group);
static struct mlx5_flow_rule *alloc_rule(struct mlx5_flow_destination *dest)
{
mlx5_core_warn(get_dev(&fg->node), "Flow group %d wasn't destroyed, refcount > 1\n",
fg->id);
}
+EXPORT_SYMBOL(mlx5_destroy_flow_group);
struct mlx5_flow_namespace *mlx5_get_fdb_sub_ns(struct mlx5_core_dev *dev,
int n)
u32 qpn;
};
-#define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_a00
+#define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_c00
/* Calculate the fte_match_param length and without the reserved length.
* Make sure the reserved field is the last.
*/
goto err_sriov;
}
- err = mlx5_sriov_attach(dev);
- if (err) {
- mlx5_core_err(dev, "sriov init failed %d\n", err);
- goto err_sriov;
- }
-
err = mlx5_ec_init(dev);
if (err) {
mlx5_core_err(dev, "Failed to init embedded CPU\n");
goto err_ec;
}
+ err = mlx5_sriov_attach(dev);
+ if (err) {
+ mlx5_core_err(dev, "sriov init failed %d\n", err);
+ goto err_sriov;
+ }
+
return 0;
-err_ec:
- mlx5_sriov_detach(dev);
err_sriov:
+ mlx5_ec_cleanup(dev);
+err_ec:
mlx5_cleanup_fs(dev);
err_fs:
mlx5_accel_tls_cleanup(dev);
static void mlx5_unload(struct mlx5_core_dev *dev)
{
- mlx5_ec_cleanup(dev);
mlx5_sriov_detach(dev);
+ mlx5_ec_cleanup(dev);
mlx5_cleanup_fs(dev);
mlx5_accel_ipsec_cleanup(dev);
mlx5_accel_tls_cleanup(dev);
{ PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */
{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */
{ PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */
+ { PCI_VDEVICE(MELLANOX, 0xa2dc) }, /* BlueField-3 integrated ConnectX-7 network controller */
{ 0, }
};
int mlx5_query_hca_caps(struct mlx5_core_dev *dev);
int mlx5_query_board_id(struct mlx5_core_dev *dev);
+int mlx5_cmd_init(struct mlx5_core_dev *dev);
+void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
+void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
+ enum mlx5_cmdif_state cmdif_state);
int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id);
int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev);
int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev);
if (func_id)
dev->priv.vfs_pages += npages;
else if (mlx5_core_is_ecpf(dev) && !ec_function)
- dev->priv.peer_pf_pages += npages;
+ dev->priv.host_pf_pages += npages;
mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n",
npages, ec_function, func_id, err);
if (func_id)
dev->priv.vfs_pages -= npages;
else if (mlx5_core_is_ecpf(dev) && !ec_function)
- dev->priv.peer_pf_pages -= npages;
+ dev->priv.host_pf_pages -= npages;
mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x\n",
npages, ec_function, func_id);
if (func_id)
dev->priv.vfs_pages -= num_claimed;
else if (mlx5_core_is_ecpf(dev) && !ec_function)
- dev->priv.peer_pf_pages -= num_claimed;
+ dev->priv.host_pf_pages -= num_claimed;
out_free:
kvfree(out);
WARN(dev->priv.vfs_pages,
"VFs FW pages counter is %d after reclaiming all pages\n",
dev->priv.vfs_pages);
- WARN(dev->priv.peer_pf_pages,
- "Peer PF FW pages counter is %d after reclaiming all pages\n",
- dev->priv.peer_pf_pages);
+ WARN(dev->priv.host_pf_pages,
+ "External host PF FW pages counter is %d after reclaiming all pages\n",
+ dev->priv.host_pf_pages);
return 0;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2004 Topspin Communications. All rights reserved.
+ * Copyright (c) 2005 - 2008 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2006 - 2007 Cisco Systems, Inc. All rights reserved.
+ * Copyright (c) 2020 NVIDIA CORPORATION. All rights reserved.
+ */
+
+#include "dr_types.h"
+
+int mlx5dr_buddy_init(struct mlx5dr_icm_buddy_mem *buddy,
+ unsigned int max_order)
+{
+ int i;
+
+ buddy->max_order = max_order;
+
+ INIT_LIST_HEAD(&buddy->list_node);
+ INIT_LIST_HEAD(&buddy->used_list);
+ INIT_LIST_HEAD(&buddy->hot_list);
+
+ buddy->bitmap = kcalloc(buddy->max_order + 1,
+ sizeof(*buddy->bitmap),
+ GFP_KERNEL);
+ buddy->num_free = kcalloc(buddy->max_order + 1,
+ sizeof(*buddy->num_free),
+ GFP_KERNEL);
+
+ if (!buddy->bitmap || !buddy->num_free)
+ goto err_free_all;
+
+ /* Allocating max_order bitmaps, one for each order */
+
+ for (i = 0; i <= buddy->max_order; ++i) {
+ unsigned int size = 1 << (buddy->max_order - i);
+
+ buddy->bitmap[i] = bitmap_zalloc(size, GFP_KERNEL);
+ if (!buddy->bitmap[i])
+ goto err_out_free_each_bit_per_order;
+ }
+
+ /* In the beginning, we have only one order that is available for
+ * use (the biggest one), so mark the first bit in both bitmaps.
+ */
+
+ bitmap_set(buddy->bitmap[buddy->max_order], 0, 1);
+
+ buddy->num_free[buddy->max_order] = 1;
+
+ return 0;
+
+err_out_free_each_bit_per_order:
+ for (i = 0; i <= buddy->max_order; ++i)
+ bitmap_free(buddy->bitmap[i]);
+
+err_free_all:
+ kfree(buddy->num_free);
+ kfree(buddy->bitmap);
+ return -ENOMEM;
+}
+
+void mlx5dr_buddy_cleanup(struct mlx5dr_icm_buddy_mem *buddy)
+{
+ int i;
+
+ list_del(&buddy->list_node);
+
+ for (i = 0; i <= buddy->max_order; ++i)
+ bitmap_free(buddy->bitmap[i]);
+
+ kfree(buddy->num_free);
+ kfree(buddy->bitmap);
+}
+
+static int dr_buddy_find_free_seg(struct mlx5dr_icm_buddy_mem *buddy,
+ unsigned int start_order,
+ unsigned int *segment,
+ unsigned int *order)
+{
+ unsigned int seg, order_iter, m;
+
+ for (order_iter = start_order;
+ order_iter <= buddy->max_order; ++order_iter) {
+ if (!buddy->num_free[order_iter])
+ continue;
+
+ m = 1 << (buddy->max_order - order_iter);
+ seg = find_first_bit(buddy->bitmap[order_iter], m);
+
+ if (WARN(seg >= m,
+ "ICM Buddy: failed finding free mem for order %d\n",
+ order_iter))
+ return -ENOMEM;
+
+ break;
+ }
+
+ if (order_iter > buddy->max_order)
+ return -ENOMEM;
+
+ *segment = seg;
+ *order = order_iter;
+ return 0;
+}
+
+/**
+ * mlx5dr_buddy_alloc_mem() - Update second level bitmap.
+ * @buddy: Buddy to update.
+ * @order: Order of the buddy to update.
+ * @segment: Segment number.
+ *
+ * This function finds the first area of the ICM memory managed by this buddy.
+ * It uses the data structures of the buddy system in order to find the first
+ * area of free place, starting from the current order till the maximum order
+ * in the system.
+ *
+ * Return: 0 when segment is set, non-zero error status otherwise.
+ *
+ * The function returns the location (segment) in the whole buddy ICM memory
+ * area - the index of the memory segment that is available for use.
+ */
+int mlx5dr_buddy_alloc_mem(struct mlx5dr_icm_buddy_mem *buddy,
+ unsigned int order,
+ unsigned int *segment)
+{
+ unsigned int seg, order_iter;
+ int err;
+
+ err = dr_buddy_find_free_seg(buddy, order, &seg, &order_iter);
+ if (err)
+ return err;
+
+ bitmap_clear(buddy->bitmap[order_iter], seg, 1);
+ --buddy->num_free[order_iter];
+
+ /* If we found free memory in some order that is bigger than the
+ * required order, we need to split every order between the required
+ * order and the order that we found into two parts, and mark accordingly.
+ */
+ while (order_iter > order) {
+ --order_iter;
+ seg <<= 1;
+ bitmap_set(buddy->bitmap[order_iter], seg ^ 1, 1);
+ ++buddy->num_free[order_iter];
+ }
+
+ seg <<= order;
+ *segment = seg;
+
+ return 0;
+}
+
+void mlx5dr_buddy_free_mem(struct mlx5dr_icm_buddy_mem *buddy,
+ unsigned int seg, unsigned int order)
+{
+ seg >>= order;
+
+ /* Whenever a segment is free,
+ * the mem is added to the buddy that gave it.
+ */
+ while (test_bit(seg ^ 1, buddy->bitmap[order])) {
+ bitmap_clear(buddy->bitmap[order], seg ^ 1, 1);
+ --buddy->num_free[order];
+ seg >>= 1;
+ ++order;
+ }
+ bitmap_set(buddy->bitmap[order], seg, 1);
+
+ ++buddy->num_free[order];
+}
+
caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols);
caps->sw_format_ver = MLX5_CAP_GEN(mdev, steering_format_version);
- if (mlx5dr_matcher_supp_flex_parser_icmp_v4(caps)) {
+ if (caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED) {
caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0);
caps->flex_parser_id_icmp_dw1 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw1);
}
- if (mlx5dr_matcher_supp_flex_parser_icmp_v6(caps)) {
+ if (caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED) {
caps->flex_parser_id_icmpv6_dw0 =
MLX5_CAP_GEN(mdev, flex_parser_id_icmpv6_dw0);
caps->flex_parser_id_icmpv6_dw1 =
#include "dr_types.h"
#define DR_ICM_MODIFY_HDR_ALIGN_BASE 64
-#define DR_ICM_SYNC_THRESHOLD (64 * 1024 * 1024)
-
-struct mlx5dr_icm_pool;
-
-struct mlx5dr_icm_bucket {
- struct mlx5dr_icm_pool *pool;
-
- /* Chunks that aren't visible to HW not directly and not in cache */
- struct list_head free_list;
- unsigned int free_list_count;
-
- /* Used chunks, HW may be accessing this memory */
- struct list_head used_list;
- unsigned int used_list_count;
-
- /* HW may be accessing this memory but at some future,
- * undetermined time, it might cease to do so. Before deciding to call
- * sync_ste, this list is moved to sync_list
- */
- struct list_head hot_list;
- unsigned int hot_list_count;
-
- /* Pending sync list, entries from the hot list are moved to this list.
- * sync_ste is executed and then sync_list is concatenated to the free list
- */
- struct list_head sync_list;
- unsigned int sync_list_count;
-
- u32 total_chunks;
- u32 num_of_entries;
- u32 entry_size;
- /* protect the ICM bucket */
- struct mutex mutex;
-};
+#define DR_ICM_SYNC_THRESHOLD_POOL (64 * 1024 * 1024)
struct mlx5dr_icm_pool {
- struct mlx5dr_icm_bucket *buckets;
enum mlx5dr_icm_type icm_type;
enum mlx5dr_icm_chunk_size max_log_chunk_sz;
- enum mlx5dr_icm_chunk_size num_of_buckets;
- struct list_head icm_mr_list;
- /* protect the ICM MR list */
- struct mutex mr_mutex;
struct mlx5dr_domain *dmn;
+ /* memory management */
+ struct mutex mutex; /* protect the ICM pool and ICM buddy */
+ struct list_head buddy_mem_list;
+ u64 hot_memory_size;
};
struct mlx5dr_icm_dm {
};
struct mlx5dr_icm_mr {
- struct mlx5dr_icm_pool *pool;
struct mlx5_core_mkey mkey;
struct mlx5dr_icm_dm dm;
- size_t used_length;
+ struct mlx5dr_domain *dmn;
size_t length;
u64 icm_start_addr;
- struct list_head mr_list;
};
static int dr_icm_create_dm_mkey(struct mlx5_core_dev *mdev,
if (!icm_mr)
return NULL;
- icm_mr->pool = pool;
- INIT_LIST_HEAD(&icm_mr->mr_list);
+ icm_mr->dmn = pool->dmn;
icm_mr->dm.length = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz,
pool->icm_type);
goto free_mkey;
}
- list_add_tail(&icm_mr->mr_list, &pool->icm_mr_list);
-
return icm_mr;
free_mkey:
static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr)
{
- struct mlx5_core_dev *mdev = icm_mr->pool->dmn->mdev;
+ struct mlx5_core_dev *mdev = icm_mr->dmn->mdev;
struct mlx5dr_icm_dm *dm = &icm_mr->dm;
- list_del(&icm_mr->mr_list);
mlx5_core_destroy_mkey(mdev, &icm_mr->mkey);
mlx5_dm_sw_icm_dealloc(mdev, dm->type, dm->length, 0,
dm->addr, dm->obj_id);
static int dr_icm_chunk_ste_init(struct mlx5dr_icm_chunk *chunk)
{
- struct mlx5dr_icm_bucket *bucket = chunk->bucket;
-
- chunk->ste_arr = kvzalloc(bucket->num_of_entries *
+ chunk->ste_arr = kvzalloc(chunk->num_of_entries *
sizeof(chunk->ste_arr[0]), GFP_KERNEL);
if (!chunk->ste_arr)
return -ENOMEM;
- chunk->hw_ste_arr = kvzalloc(bucket->num_of_entries *
+ chunk->hw_ste_arr = kvzalloc(chunk->num_of_entries *
DR_STE_SIZE_REDUCED, GFP_KERNEL);
if (!chunk->hw_ste_arr)
goto out_free_ste_arr;
- chunk->miss_list = kvmalloc(bucket->num_of_entries *
+ chunk->miss_list = kvmalloc(chunk->num_of_entries *
sizeof(chunk->miss_list[0]), GFP_KERNEL);
if (!chunk->miss_list)
goto out_free_hw_ste_arr;
return -ENOMEM;
}
-static int dr_icm_chunks_create(struct mlx5dr_icm_bucket *bucket)
-{
- size_t mr_free_size, mr_req_size, mr_row_size;
- struct mlx5dr_icm_pool *pool = bucket->pool;
- struct mlx5dr_icm_mr *icm_mr = NULL;
- struct mlx5dr_icm_chunk *chunk;
- int i, err = 0;
-
- mr_req_size = bucket->num_of_entries * bucket->entry_size;
- mr_row_size = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz,
- pool->icm_type);
- mutex_lock(&pool->mr_mutex);
- if (!list_empty(&pool->icm_mr_list)) {
- icm_mr = list_last_entry(&pool->icm_mr_list,
- struct mlx5dr_icm_mr, mr_list);
-
- if (icm_mr)
- mr_free_size = icm_mr->dm.length - icm_mr->used_length;
- }
-
- if (!icm_mr || mr_free_size < mr_row_size) {
- icm_mr = dr_icm_pool_mr_create(pool);
- if (!icm_mr) {
- err = -ENOMEM;
- goto out_err;
- }
- }
-
- /* Create memory aligned chunks */
- for (i = 0; i < mr_row_size / mr_req_size; i++) {
- chunk = kvzalloc(sizeof(*chunk), GFP_KERNEL);
- if (!chunk) {
- err = -ENOMEM;
- goto out_err;
- }
-
- chunk->bucket = bucket;
- chunk->rkey = icm_mr->mkey.key;
- /* mr start addr is zero based */
- chunk->mr_addr = icm_mr->used_length;
- chunk->icm_addr = (uintptr_t)icm_mr->icm_start_addr + icm_mr->used_length;
- icm_mr->used_length += mr_req_size;
- chunk->num_of_entries = bucket->num_of_entries;
- chunk->byte_size = chunk->num_of_entries * bucket->entry_size;
-
- if (pool->icm_type == DR_ICM_TYPE_STE) {
- err = dr_icm_chunk_ste_init(chunk);
- if (err)
- goto out_free_chunk;
- }
-
- INIT_LIST_HEAD(&chunk->chunk_list);
- list_add(&chunk->chunk_list, &bucket->free_list);
- bucket->free_list_count++;
- bucket->total_chunks++;
- }
- mutex_unlock(&pool->mr_mutex);
- return 0;
-
-out_free_chunk:
- kvfree(chunk);
-out_err:
- mutex_unlock(&pool->mr_mutex);
- return err;
-}
-
static void dr_icm_chunk_ste_cleanup(struct mlx5dr_icm_chunk *chunk)
{
kvfree(chunk->miss_list);
kvfree(chunk->ste_arr);
}
-static void dr_icm_chunk_destroy(struct mlx5dr_icm_chunk *chunk)
+static enum mlx5dr_icm_type
+get_chunk_icm_type(struct mlx5dr_icm_chunk *chunk)
+{
+ return chunk->buddy_mem->pool->icm_type;
+}
+
+static void dr_icm_chunk_destroy(struct mlx5dr_icm_chunk *chunk,
+ struct mlx5dr_icm_buddy_mem *buddy)
{
- struct mlx5dr_icm_bucket *bucket = chunk->bucket;
+ enum mlx5dr_icm_type icm_type = get_chunk_icm_type(chunk);
+ buddy->used_memory -= chunk->byte_size;
list_del(&chunk->chunk_list);
- bucket->total_chunks--;
- if (bucket->pool->icm_type == DR_ICM_TYPE_STE)
+ if (icm_type == DR_ICM_TYPE_STE)
dr_icm_chunk_ste_cleanup(chunk);
kvfree(chunk);
}
-static void dr_icm_bucket_init(struct mlx5dr_icm_pool *pool,
- struct mlx5dr_icm_bucket *bucket,
- enum mlx5dr_icm_chunk_size chunk_size)
+static int dr_icm_buddy_create(struct mlx5dr_icm_pool *pool)
{
- if (pool->icm_type == DR_ICM_TYPE_STE)
- bucket->entry_size = DR_STE_SIZE;
- else
- bucket->entry_size = DR_MODIFY_ACTION_SIZE;
-
- bucket->num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(chunk_size);
- bucket->pool = pool;
- mutex_init(&bucket->mutex);
- INIT_LIST_HEAD(&bucket->free_list);
- INIT_LIST_HEAD(&bucket->used_list);
- INIT_LIST_HEAD(&bucket->hot_list);
- INIT_LIST_HEAD(&bucket->sync_list);
+ struct mlx5dr_icm_buddy_mem *buddy;
+ struct mlx5dr_icm_mr *icm_mr;
+
+ icm_mr = dr_icm_pool_mr_create(pool);
+ if (!icm_mr)
+ return -ENOMEM;
+
+ buddy = kvzalloc(sizeof(*buddy), GFP_KERNEL);
+ if (!buddy)
+ goto free_mr;
+
+ if (mlx5dr_buddy_init(buddy, pool->max_log_chunk_sz))
+ goto err_free_buddy;
+
+ buddy->icm_mr = icm_mr;
+ buddy->pool = pool;
+
+ /* add it to the -start- of the list in order to search in it first */
+ list_add(&buddy->list_node, &pool->buddy_mem_list);
+
+ return 0;
+
+err_free_buddy:
+ kvfree(buddy);
+free_mr:
+ dr_icm_pool_mr_destroy(icm_mr);
+ return -ENOMEM;
}
-static void dr_icm_bucket_cleanup(struct mlx5dr_icm_bucket *bucket)
+static void dr_icm_buddy_destroy(struct mlx5dr_icm_buddy_mem *buddy)
{
struct mlx5dr_icm_chunk *chunk, *next;
- mutex_destroy(&bucket->mutex);
- list_splice_tail_init(&bucket->sync_list, &bucket->free_list);
- list_splice_tail_init(&bucket->hot_list, &bucket->free_list);
+ list_for_each_entry_safe(chunk, next, &buddy->hot_list, chunk_list)
+ dr_icm_chunk_destroy(chunk, buddy);
+
+ list_for_each_entry_safe(chunk, next, &buddy->used_list, chunk_list)
+ dr_icm_chunk_destroy(chunk, buddy);
- list_for_each_entry_safe(chunk, next, &bucket->free_list, chunk_list)
- dr_icm_chunk_destroy(chunk);
+ dr_icm_pool_mr_destroy(buddy->icm_mr);
- WARN_ON(bucket->total_chunks != 0);
+ mlx5dr_buddy_cleanup(buddy);
- /* Cleanup of unreturned chunks */
- list_for_each_entry_safe(chunk, next, &bucket->used_list, chunk_list)
- dr_icm_chunk_destroy(chunk);
+ kvfree(buddy);
}
-static u64 dr_icm_hot_mem_size(struct mlx5dr_icm_pool *pool)
+static struct mlx5dr_icm_chunk *
+dr_icm_chunk_create(struct mlx5dr_icm_pool *pool,
+ enum mlx5dr_icm_chunk_size chunk_size,
+ struct mlx5dr_icm_buddy_mem *buddy_mem_pool,
+ unsigned int seg)
{
- u64 hot_size = 0;
- int chunk_order;
+ struct mlx5dr_icm_chunk *chunk;
+ int offset;
- for (chunk_order = 0; chunk_order < pool->num_of_buckets; chunk_order++)
- hot_size += pool->buckets[chunk_order].hot_list_count *
- mlx5dr_icm_pool_chunk_size_to_byte(chunk_order, pool->icm_type);
+ chunk = kvzalloc(sizeof(*chunk), GFP_KERNEL);
+ if (!chunk)
+ return NULL;
- return hot_size;
-}
+ offset = mlx5dr_icm_pool_dm_type_to_entry_size(pool->icm_type) * seg;
+
+ chunk->rkey = buddy_mem_pool->icm_mr->mkey.key;
+ chunk->mr_addr = offset;
+ chunk->icm_addr =
+ (uintptr_t)buddy_mem_pool->icm_mr->icm_start_addr + offset;
+ chunk->num_of_entries =
+ mlx5dr_icm_pool_chunk_size_to_entries(chunk_size);
+ chunk->byte_size =
+ mlx5dr_icm_pool_chunk_size_to_byte(chunk_size, pool->icm_type);
+ chunk->seg = seg;
+
+ if (pool->icm_type == DR_ICM_TYPE_STE && dr_icm_chunk_ste_init(chunk)) {
+ mlx5dr_err(pool->dmn,
+ "Failed to init ste arrays (order: %d)\n",
+ chunk_size);
+ goto out_free_chunk;
+ }
-static bool dr_icm_reuse_hot_entries(struct mlx5dr_icm_pool *pool,
- struct mlx5dr_icm_bucket *bucket)
-{
- u64 bytes_for_sync;
+ buddy_mem_pool->used_memory += chunk->byte_size;
+ chunk->buddy_mem = buddy_mem_pool;
+ INIT_LIST_HEAD(&chunk->chunk_list);
- bytes_for_sync = dr_icm_hot_mem_size(pool);
- if (bytes_for_sync < DR_ICM_SYNC_THRESHOLD || !bucket->hot_list_count)
- return false;
+ /* chunk now is part of the used_list */
+ list_add_tail(&chunk->chunk_list, &buddy_mem_pool->used_list);
- return true;
-}
+ return chunk;
-static void dr_icm_chill_bucket_start(struct mlx5dr_icm_bucket *bucket)
-{
- list_splice_tail_init(&bucket->hot_list, &bucket->sync_list);
- bucket->sync_list_count += bucket->hot_list_count;
- bucket->hot_list_count = 0;
+out_free_chunk:
+ kvfree(chunk);
+ return NULL;
}
-static void dr_icm_chill_bucket_end(struct mlx5dr_icm_bucket *bucket)
+static bool dr_icm_pool_is_sync_required(struct mlx5dr_icm_pool *pool)
{
- list_splice_tail_init(&bucket->sync_list, &bucket->free_list);
- bucket->free_list_count += bucket->sync_list_count;
- bucket->sync_list_count = 0;
-}
+ if (pool->hot_memory_size > DR_ICM_SYNC_THRESHOLD_POOL)
+ return true;
-static void dr_icm_chill_bucket_abort(struct mlx5dr_icm_bucket *bucket)
-{
- list_splice_tail_init(&bucket->sync_list, &bucket->hot_list);
- bucket->hot_list_count += bucket->sync_list_count;
- bucket->sync_list_count = 0;
+ return false;
}
-static void dr_icm_chill_buckets_start(struct mlx5dr_icm_pool *pool,
- struct mlx5dr_icm_bucket *cb,
- bool buckets[DR_CHUNK_SIZE_MAX])
+static int dr_icm_pool_sync_all_buddy_pools(struct mlx5dr_icm_pool *pool)
{
- struct mlx5dr_icm_bucket *bucket;
- int i;
-
- for (i = 0; i < pool->num_of_buckets; i++) {
- bucket = &pool->buckets[i];
- if (bucket == cb) {
- dr_icm_chill_bucket_start(bucket);
- continue;
- }
+ struct mlx5dr_icm_buddy_mem *buddy, *tmp_buddy;
+ int err;
- /* Freeing the mutex is done at the end of that process, after
- * sync_ste was executed at dr_icm_chill_buckets_end func.
- */
- if (mutex_trylock(&bucket->mutex)) {
- dr_icm_chill_bucket_start(bucket);
- buckets[i] = true;
- }
+ err = mlx5dr_cmd_sync_steering(pool->dmn->mdev);
+ if (err) {
+ mlx5dr_err(pool->dmn, "Failed to sync to HW (err: %d)\n", err);
+ return err;
}
-}
-static void dr_icm_chill_buckets_end(struct mlx5dr_icm_pool *pool,
- struct mlx5dr_icm_bucket *cb,
- bool buckets[DR_CHUNK_SIZE_MAX])
-{
- struct mlx5dr_icm_bucket *bucket;
- int i;
-
- for (i = 0; i < pool->num_of_buckets; i++) {
- bucket = &pool->buckets[i];
- if (bucket == cb) {
- dr_icm_chill_bucket_end(bucket);
- continue;
- }
+ list_for_each_entry_safe(buddy, tmp_buddy, &pool->buddy_mem_list, list_node) {
+ struct mlx5dr_icm_chunk *chunk, *tmp_chunk;
- if (!buckets[i])
- continue;
+ list_for_each_entry_safe(chunk, tmp_chunk, &buddy->hot_list, chunk_list) {
+ mlx5dr_buddy_free_mem(buddy, chunk->seg,
+ ilog2(chunk->num_of_entries));
+ pool->hot_memory_size -= chunk->byte_size;
+ dr_icm_chunk_destroy(chunk, buddy);
+ }
- dr_icm_chill_bucket_end(bucket);
- mutex_unlock(&bucket->mutex);
+ if (!buddy->used_memory && pool->icm_type == DR_ICM_TYPE_STE)
+ dr_icm_buddy_destroy(buddy);
}
+
+ return 0;
}
-static void dr_icm_chill_buckets_abort(struct mlx5dr_icm_pool *pool,
- struct mlx5dr_icm_bucket *cb,
- bool buckets[DR_CHUNK_SIZE_MAX])
+static int dr_icm_handle_buddies_get_mem(struct mlx5dr_icm_pool *pool,
+ enum mlx5dr_icm_chunk_size chunk_size,
+ struct mlx5dr_icm_buddy_mem **buddy,
+ unsigned int *seg)
{
- struct mlx5dr_icm_bucket *bucket;
- int i;
-
- for (i = 0; i < pool->num_of_buckets; i++) {
- bucket = &pool->buckets[i];
- if (bucket == cb) {
- dr_icm_chill_bucket_abort(bucket);
- continue;
- }
+ struct mlx5dr_icm_buddy_mem *buddy_mem_pool;
+ bool new_mem = false;
+ int err;
- if (!buckets[i])
- continue;
+alloc_buddy_mem:
+ /* find the next free place from the buddy list */
+ list_for_each_entry(buddy_mem_pool, &pool->buddy_mem_list, list_node) {
+ err = mlx5dr_buddy_alloc_mem(buddy_mem_pool,
+ chunk_size, seg);
+ if (!err)
+ goto found;
+
+ if (WARN_ON(new_mem)) {
+ /* We have new memory pool, first in the list */
+ mlx5dr_err(pool->dmn,
+ "No memory for order: %d\n",
+ chunk_size);
+ goto out;
+ }
+ }
- dr_icm_chill_bucket_abort(bucket);
- mutex_unlock(&bucket->mutex);
+ /* no more available allocators in that pool, create new */
+ err = dr_icm_buddy_create(pool);
+ if (err) {
+ mlx5dr_err(pool->dmn,
+ "Failed creating buddy for order %d\n",
+ chunk_size);
+ goto out;
}
+
+ /* mark we have new memory, first in list */
+ new_mem = true;
+ goto alloc_buddy_mem;
+
+found:
+ *buddy = buddy_mem_pool;
+out:
+ return err;
}
/* Allocate an ICM chunk, each chunk holds a piece of ICM memory and
mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool,
enum mlx5dr_icm_chunk_size chunk_size)
{
- struct mlx5dr_icm_chunk *chunk = NULL; /* Fix compilation warning */
- bool buckets[DR_CHUNK_SIZE_MAX] = {};
- struct mlx5dr_icm_bucket *bucket;
- int err;
+ struct mlx5dr_icm_chunk *chunk = NULL;
+ struct mlx5dr_icm_buddy_mem *buddy;
+ unsigned int seg;
+ int ret;
if (chunk_size > pool->max_log_chunk_sz)
return NULL;
- bucket = &pool->buckets[chunk_size];
-
- mutex_lock(&bucket->mutex);
-
- /* Take chunk from pool if available, otherwise allocate new chunks */
- if (list_empty(&bucket->free_list)) {
- if (dr_icm_reuse_hot_entries(pool, bucket)) {
- dr_icm_chill_buckets_start(pool, bucket, buckets);
- err = mlx5dr_cmd_sync_steering(pool->dmn->mdev);
- if (err) {
- dr_icm_chill_buckets_abort(pool, bucket, buckets);
- mlx5dr_err(pool->dmn, "Sync_steering failed\n");
- chunk = NULL;
- goto out;
- }
- dr_icm_chill_buckets_end(pool, bucket, buckets);
- } else {
- dr_icm_chunks_create(bucket);
- }
- }
+ mutex_lock(&pool->mutex);
+ /* find mem, get back the relevant buddy pool and seg in that mem */
+ ret = dr_icm_handle_buddies_get_mem(pool, chunk_size, &buddy, &seg);
+ if (ret)
+ goto out;
- if (!list_empty(&bucket->free_list)) {
- chunk = list_last_entry(&bucket->free_list,
- struct mlx5dr_icm_chunk,
- chunk_list);
- if (chunk) {
- list_del_init(&chunk->chunk_list);
- list_add_tail(&chunk->chunk_list, &bucket->used_list);
- bucket->free_list_count--;
- bucket->used_list_count++;
- }
- }
+ chunk = dr_icm_chunk_create(pool, chunk_size, buddy, seg);
+ if (!chunk)
+ goto out_err;
+
+ goto out;
+
+out_err:
+ mlx5dr_buddy_free_mem(buddy, seg, chunk_size);
out:
- mutex_unlock(&bucket->mutex);
+ mutex_unlock(&pool->mutex);
return chunk;
}
void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk)
{
- struct mlx5dr_icm_bucket *bucket = chunk->bucket;
+ struct mlx5dr_icm_buddy_mem *buddy = chunk->buddy_mem;
+ struct mlx5dr_icm_pool *pool = buddy->pool;
- if (bucket->pool->icm_type == DR_ICM_TYPE_STE) {
- memset(chunk->ste_arr, 0,
- bucket->num_of_entries * sizeof(chunk->ste_arr[0]));
- memset(chunk->hw_ste_arr, 0,
- bucket->num_of_entries * DR_STE_SIZE_REDUCED);
- }
+ /* move the memory to the waiting list AKA "hot" */
+ mutex_lock(&pool->mutex);
+ list_move_tail(&chunk->chunk_list, &buddy->hot_list);
+ pool->hot_memory_size += chunk->byte_size;
+
+ /* Check if we have chunks that are waiting for sync-ste */
+ if (dr_icm_pool_is_sync_required(pool))
+ dr_icm_pool_sync_all_buddy_pools(pool);
- mutex_lock(&bucket->mutex);
- list_del_init(&chunk->chunk_list);
- list_add_tail(&chunk->chunk_list, &bucket->hot_list);
- bucket->hot_list_count++;
- bucket->used_list_count--;
- mutex_unlock(&bucket->mutex);
+ mutex_unlock(&pool->mutex);
}
struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn,
{
enum mlx5dr_icm_chunk_size max_log_chunk_sz;
struct mlx5dr_icm_pool *pool;
- int i;
if (icm_type == DR_ICM_TYPE_STE)
max_log_chunk_sz = dmn->info.max_log_sw_icm_sz;
if (!pool)
return NULL;
- pool->buckets = kcalloc(max_log_chunk_sz + 1,
- sizeof(pool->buckets[0]),
- GFP_KERNEL);
- if (!pool->buckets)
- goto free_pool;
-
pool->dmn = dmn;
pool->icm_type = icm_type;
pool->max_log_chunk_sz = max_log_chunk_sz;
- pool->num_of_buckets = max_log_chunk_sz + 1;
- INIT_LIST_HEAD(&pool->icm_mr_list);
- for (i = 0; i < pool->num_of_buckets; i++)
- dr_icm_bucket_init(pool, &pool->buckets[i], i);
+ INIT_LIST_HEAD(&pool->buddy_mem_list);
- mutex_init(&pool->mr_mutex);
+ mutex_init(&pool->mutex);
return pool;
-
-free_pool:
- kvfree(pool);
- return NULL;
}
void mlx5dr_icm_pool_destroy(struct mlx5dr_icm_pool *pool)
{
- struct mlx5dr_icm_mr *icm_mr, *next;
- int i;
-
- mutex_destroy(&pool->mr_mutex);
-
- list_for_each_entry_safe(icm_mr, next, &pool->icm_mr_list, mr_list)
- dr_icm_pool_mr_destroy(icm_mr);
+ struct mlx5dr_icm_buddy_mem *buddy, *tmp_buddy;
- for (i = 0; i < pool->num_of_buckets; i++)
- dr_icm_bucket_cleanup(&pool->buckets[i]);
+ list_for_each_entry_safe(buddy, tmp_buddy, &pool->buddy_mem_list, list_node)
+ dr_icm_buddy_destroy(buddy);
- kfree(pool->buckets);
+ mutex_destroy(&pool->mutex);
kvfree(pool);
}
(_misc2)._inner_outer##_first_mpls_s_bos || \
(_misc2)._inner_outer##_first_mpls_ttl)
-static bool dr_mask_is_gre_set(struct mlx5dr_match_misc *misc)
+static bool dr_mask_is_tnl_gre_set(struct mlx5dr_match_misc *misc)
{
return (misc->gre_key_h || misc->gre_key_l ||
misc->gre_protocol || misc->gre_c_present ||
(_misc2).outer_first_mpls_over_##gre_udp##_s_bos || \
(_misc2).outer_first_mpls_over_##gre_udp##_ttl)
-#define DR_MASK_IS_FLEX_PARSER_0_SET(_misc2) ( \
+#define DR_MASK_IS_TNL_MPLS_SET(_misc2) ( \
DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), gre) || \
DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), udp))
static bool
-dr_mask_is_misc3_vxlan_gpe_set(struct mlx5dr_match_misc3 *misc3)
+dr_mask_is_vxlan_gpe_set(struct mlx5dr_match_misc3 *misc3)
{
return (misc3->outer_vxlan_gpe_vni ||
misc3->outer_vxlan_gpe_next_protocol ||
}
static bool
-dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_cmd_caps *caps)
+dr_matcher_supp_vxlan_gpe(struct mlx5dr_cmd_caps *caps)
{
- return caps->flex_protocols &
- MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED;
+ return caps->flex_protocols & MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED;
}
static bool
-dr_mask_is_flex_parser_tnl_vxlan_gpe_set(struct mlx5dr_match_param *mask,
- struct mlx5dr_domain *dmn)
+dr_mask_is_tnl_vxlan_gpe(struct mlx5dr_match_param *mask,
+ struct mlx5dr_domain *dmn)
{
- return dr_mask_is_misc3_vxlan_gpe_set(&mask->misc3) &&
- dr_matcher_supp_flex_parser_vxlan_gpe(&dmn->info.caps);
+ return dr_mask_is_vxlan_gpe_set(&mask->misc3) &&
+ dr_matcher_supp_vxlan_gpe(&dmn->info.caps);
}
-static bool dr_mask_is_misc_geneve_set(struct mlx5dr_match_misc *misc)
+static bool dr_mask_is_tnl_geneve_set(struct mlx5dr_match_misc *misc)
{
return misc->geneve_vni ||
misc->geneve_oam ||
}
static bool
-dr_matcher_supp_flex_parser_geneve(struct mlx5dr_cmd_caps *caps)
+dr_matcher_supp_tnl_geneve(struct mlx5dr_cmd_caps *caps)
{
- return caps->flex_protocols &
- MLX5_FLEX_PARSER_GENEVE_ENABLED;
+ return caps->flex_protocols & MLX5_FLEX_PARSER_GENEVE_ENABLED;
}
static bool
-dr_mask_is_flex_parser_tnl_geneve_set(struct mlx5dr_match_param *mask,
- struct mlx5dr_domain *dmn)
+dr_mask_is_tnl_geneve(struct mlx5dr_match_param *mask,
+ struct mlx5dr_domain *dmn)
{
- return dr_mask_is_misc_geneve_set(&mask->misc) &&
- dr_matcher_supp_flex_parser_geneve(&dmn->info.caps);
+ return dr_mask_is_tnl_geneve_set(&mask->misc) &&
+ dr_matcher_supp_tnl_geneve(&dmn->info.caps);
}
-static bool dr_mask_is_flex_parser_icmpv6_set(struct mlx5dr_match_misc3 *misc3)
+static int dr_matcher_supp_icmp_v4(struct mlx5dr_cmd_caps *caps)
+{
+ return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED;
+}
+
+static int dr_matcher_supp_icmp_v6(struct mlx5dr_cmd_caps *caps)
+{
+ return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED;
+}
+
+static bool dr_mask_is_icmpv6_set(struct mlx5dr_match_misc3 *misc3)
{
return (misc3->icmpv6_type || misc3->icmpv6_code ||
misc3->icmpv6_header_data);
}
+static bool dr_mask_is_icmp(struct mlx5dr_match_param *mask,
+ struct mlx5dr_domain *dmn)
+{
+ if (DR_MASK_IS_ICMPV4_SET(&mask->misc3))
+ return dr_matcher_supp_icmp_v4(&dmn->info.caps);
+ else if (dr_mask_is_icmpv6_set(&mask->misc3))
+ return dr_matcher_supp_icmp_v6(&dmn->info.caps);
+
+ return false;
+}
+
static bool dr_mask_is_wqe_metadata_set(struct mlx5dr_match_misc2 *misc2)
{
return misc2->metadata_reg_a;
if (dr_mask_is_smac_set(&mask.outer) &&
dr_mask_is_dmac_set(&mask.outer)) {
- mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], &mask,
+ mlx5dr_ste_build_eth_l2_src_dst(&sb[idx++], &mask,
inner, rx);
}
inner, rx);
if (DR_MASK_IS_ETH_L4_SET(mask.outer, mask.misc, outer))
- mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask,
- inner, rx);
+ mlx5dr_ste_build_eth_ipv6_l3_l4(&sb[idx++], &mask,
+ inner, rx);
} else {
if (dr_mask_is_ipv4_5_tuple_set(&mask.outer))
mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask,
inner, rx);
}
- if (dr_mask_is_flex_parser_tnl_vxlan_gpe_set(&mask, dmn))
- mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(&sb[idx++],
- &mask,
- inner, rx);
- else if (dr_mask_is_flex_parser_tnl_geneve_set(&mask, dmn))
- mlx5dr_ste_build_flex_parser_tnl_geneve(&sb[idx++],
- &mask,
- inner, rx);
+ if (dr_mask_is_tnl_vxlan_gpe(&mask, dmn))
+ mlx5dr_ste_build_tnl_vxlan_gpe(&sb[idx++], &mask,
+ inner, rx);
+ else if (dr_mask_is_tnl_geneve(&mask, dmn))
+ mlx5dr_ste_build_tnl_geneve(&sb[idx++], &mask,
+ inner, rx);
if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, outer))
mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx);
if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, outer))
mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx);
- if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2))
- mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask,
- inner, rx);
+ if (DR_MASK_IS_TNL_MPLS_SET(mask.misc2))
+ mlx5dr_ste_build_tnl_mpls(&sb[idx++], &mask, inner, rx);
- if ((DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(&mask.misc3) &&
- mlx5dr_matcher_supp_flex_parser_icmp_v4(&dmn->info.caps)) ||
- (dr_mask_is_flex_parser_icmpv6_set(&mask.misc3) &&
- mlx5dr_matcher_supp_flex_parser_icmp_v6(&dmn->info.caps))) {
- ret = mlx5dr_ste_build_flex_parser_1(&sb[idx++],
- &mask, &dmn->info.caps,
- inner, rx);
+ if (dr_mask_is_icmp(&mask, dmn)) {
+ ret = mlx5dr_ste_build_icmp(&sb[idx++],
+ &mask, &dmn->info.caps,
+ inner, rx);
if (ret)
return ret;
}
- if (dr_mask_is_gre_set(&mask.misc))
- mlx5dr_ste_build_gre(&sb[idx++], &mask, inner, rx);
+ if (dr_mask_is_tnl_gre_set(&mask.misc))
+ mlx5dr_ste_build_tnl_gre(&sb[idx++], &mask, inner, rx);
}
/* Inner */
if (dr_mask_is_smac_set(&mask.inner) &&
dr_mask_is_dmac_set(&mask.inner)) {
- mlx5dr_ste_build_eth_l2_src_des(&sb[idx++],
+ mlx5dr_ste_build_eth_l2_src_dst(&sb[idx++],
&mask, inner, rx);
}
inner, rx);
if (DR_MASK_IS_ETH_L4_SET(mask.inner, mask.misc, inner))
- mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask,
- inner, rx);
+ mlx5dr_ste_build_eth_ipv6_l3_l4(&sb[idx++], &mask,
+ inner, rx);
} else {
if (dr_mask_is_ipv4_5_tuple_set(&mask.inner))
mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask,
if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, inner))
mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx);
- if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2))
- mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask, inner, rx);
+ if (DR_MASK_IS_TNL_MPLS_SET(mask.misc2))
+ mlx5dr_ste_build_tnl_mpls(&sb[idx++], &mask, inner, rx);
}
/* Empty matcher, takes all */
if (matcher->match_criteria == DR_MATCHER_CRITERIA_EMPTY)
}
if (mask) {
- if (mask->match_sz > sizeof(struct mlx5dr_match_param)) {
+ if (mask->match_sz > DR_SZ_MATCH_PARAM) {
mlx5dr_err(dmn, "Invalid match size attribute\n");
return -EINVAL;
}
u32 s_idx, e_idx;
if (!value_size ||
- (value_size > sizeof(struct mlx5dr_match_param) ||
- (value_size % sizeof(u32)))) {
+ (value_size > DR_SZ_MATCH_PARAM || (value_size % sizeof(u32)))) {
mlx5dr_err(matcher->tbl->dmn, "Rule parameters length is incorrect\n");
return false;
}
return 0;
}
-void mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *sb,
+void mlx5dr_ste_build_eth_l2_src_dst(struct mlx5dr_ste_build *sb,
struct mlx5dr_match_param *mask,
bool inner, bool rx)
{
return 0;
}
-void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb,
- struct mlx5dr_match_param *mask,
- bool inner, bool rx)
+void mlx5dr_ste_build_eth_ipv6_l3_l4(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
{
dr_ste_build_ipv6_l3_l4_bit_mask(mask, inner, sb->bit_mask);
return 0;
}
-void mlx5dr_ste_build_gre(struct mlx5dr_ste_build *sb,
- struct mlx5dr_match_param *mask, bool inner, bool rx)
+void mlx5dr_ste_build_tnl_gre(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask, bool inner, bool rx)
{
dr_ste_build_gre_bit_mask(mask, inner, sb->bit_mask);
return 0;
}
-void mlx5dr_ste_build_flex_parser_0(struct mlx5dr_ste_build *sb,
- struct mlx5dr_match_param *mask,
- bool inner, bool rx)
+void mlx5dr_ste_build_tnl_mpls(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
{
dr_ste_build_flex_parser_0_bit_mask(mask, inner, sb->bit_mask);
struct mlx5dr_cmd_caps *caps,
u8 *bit_mask)
{
+ bool is_ipv4_mask = DR_MASK_IS_ICMPV4_SET(&mask->misc3);
struct mlx5dr_match_misc3 *misc_3_mask = &mask->misc3;
- bool is_ipv4_mask = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3_mask);
u32 icmp_header_data_mask;
u32 icmp_type_mask;
u32 icmp_code_mask;
u32 icmp_code;
bool is_ipv4;
- is_ipv4 = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3);
+ is_ipv4 = DR_MASK_IS_ICMPV4_SET(misc_3);
if (is_ipv4) {
icmp_header_data = misc_3->icmpv4_header_data;
icmp_type = misc_3->icmpv4_type;
return 0;
}
-int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb,
- struct mlx5dr_match_param *mask,
- struct mlx5dr_cmd_caps *caps,
- bool inner, bool rx)
+int mlx5dr_ste_build_icmp(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ struct mlx5dr_cmd_caps *caps,
+ bool inner, bool rx)
{
int ret;
return 0;
}
-void mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb,
- struct mlx5dr_match_param *mask,
- bool inner, bool rx)
+void mlx5dr_ste_build_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
{
dr_ste_build_flex_parser_tnl_vxlan_gpe_bit_mask(mask, inner,
sb->bit_mask);
return 0;
}
-void mlx5dr_ste_build_flex_parser_tnl_geneve(struct mlx5dr_ste_build *sb,
- struct mlx5dr_match_param *mask,
- bool inner, bool rx)
+void mlx5dr_ste_build_tnl_geneve(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
{
dr_ste_build_flex_parser_tnl_geneve_bit_mask(mask, sb->bit_mask);
sb->rx = rx;
#define WIRE_PORT 0xFFFF
#define DR_STE_SVLAN 0x1
#define DR_STE_CVLAN 0x2
+#define DR_SZ_MATCH_PARAM (MLX5_ST_SZ_DW_MATCH_PARAM * 4)
#define mlx5dr_err(dmn, arg...) mlx5_core_err((dmn)->mdev, ##arg)
#define mlx5dr_info(dmn, arg...) mlx5_core_info((dmn)->mdev, ##arg)
struct mlx5dr_icm_pool;
struct mlx5dr_icm_chunk;
-struct mlx5dr_icm_bucket;
+struct mlx5dr_icm_buddy_mem;
struct mlx5dr_ste_htbl;
struct mlx5dr_match_param;
struct mlx5dr_cmd_caps;
struct mlx5dr_matcher_rx_tx *nic_matcher,
struct mlx5dr_match_param *value,
u8 *ste_arr);
-void mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *builder,
+void mlx5dr_ste_build_eth_l2_src_dst(struct mlx5dr_ste_build *builder,
struct mlx5dr_match_param *mask,
bool inner, bool rx);
void mlx5dr_ste_build_eth_l3_ipv4_5_tuple(struct mlx5dr_ste_build *sb,
void mlx5dr_ste_build_eth_l2_tnl(struct mlx5dr_ste_build *sb,
struct mlx5dr_match_param *mask,
bool inner, bool rx);
-void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb,
- struct mlx5dr_match_param *mask,
- bool inner, bool rx);
+void mlx5dr_ste_build_eth_ipv6_l3_l4(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx);
void mlx5dr_ste_build_eth_l4_misc(struct mlx5dr_ste_build *sb,
struct mlx5dr_match_param *mask,
bool inner, bool rx);
-void mlx5dr_ste_build_gre(struct mlx5dr_ste_build *sb,
- struct mlx5dr_match_param *mask,
- bool inner, bool rx);
+void mlx5dr_ste_build_tnl_gre(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx);
void mlx5dr_ste_build_mpls(struct mlx5dr_ste_build *sb,
struct mlx5dr_match_param *mask,
bool inner, bool rx);
-void mlx5dr_ste_build_flex_parser_0(struct mlx5dr_ste_build *sb,
+void mlx5dr_ste_build_tnl_mpls(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx);
+int mlx5dr_ste_build_icmp(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ struct mlx5dr_cmd_caps *caps,
+ bool inner, bool rx);
+void mlx5dr_ste_build_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb,
struct mlx5dr_match_param *mask,
bool inner, bool rx);
-int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb,
- struct mlx5dr_match_param *mask,
- struct mlx5dr_cmd_caps *caps,
- bool inner, bool rx);
-void mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb,
- struct mlx5dr_match_param *mask,
- bool inner, bool rx);
-void mlx5dr_ste_build_flex_parser_tnl_geneve(struct mlx5dr_ste_build *sb,
- struct mlx5dr_match_param *mask,
- bool inner, bool rx);
+void mlx5dr_ste_build_tnl_geneve(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx);
void mlx5dr_ste_build_general_purpose(struct mlx5dr_ste_build *sb,
struct mlx5dr_match_param *mask,
bool inner, bool rx);
struct mlx5dr_match_misc3 misc3;
};
-#define DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(_misc3) ((_misc3)->icmpv4_type || \
- (_misc3)->icmpv4_code || \
- (_misc3)->icmpv4_header_data)
+#define DR_MASK_IS_ICMPV4_SET(_misc3) ((_misc3)->icmpv4_type || \
+ (_misc3)->icmpv4_code || \
+ (_misc3)->icmpv4_header_data)
struct mlx5dr_esw_caps {
u64 drop_icm_address_rx;
struct mlx5dr_domain *dmn;
struct mlx5dr_icm_chunk *chunk;
u8 *data;
- u32 data_size;
u16 num_of_actions;
u32 index;
u8 allow_rx:1;
struct mlx5dr_ste *ste);
struct mlx5dr_icm_chunk {
- struct mlx5dr_icm_bucket *bucket;
+ struct mlx5dr_icm_buddy_mem *buddy_mem;
struct list_head chunk_list;
u32 rkey;
u32 num_of_entries;
u64 icm_addr;
u64 mr_addr;
+ /* indicates the index of this chunk in the whole memory,
+ * used for deleting the chunk from the buddy
+ */
+ unsigned int seg;
+
/* Memory optimisation */
struct mlx5dr_ste *ste_arr;
u8 *hw_ste_arr;
mlx5dr_domain_nic_unlock(&dmn->info.rx);
}
-static inline int
-mlx5dr_matcher_supp_flex_parser_icmp_v4(struct mlx5dr_cmd_caps *caps)
-{
- return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED;
-}
-
-static inline int
-mlx5dr_matcher_supp_flex_parser_icmp_v6(struct mlx5dr_cmd_caps *caps)
-{
- return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED;
-}
-
int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher,
struct mlx5dr_matcher_rx_tx *nic_matcher,
enum mlx5dr_ipv outer_ipv,
enum mlx5dr_ipv inner_ipv);
+static inline int
+mlx5dr_icm_pool_dm_type_to_entry_size(enum mlx5dr_icm_type icm_type)
+{
+ if (icm_type == DR_ICM_TYPE_STE)
+ return DR_STE_SIZE;
+
+ return DR_MODIFY_ACTION_SIZE;
+}
+
static inline u32
mlx5dr_icm_pool_chunk_size_to_entries(enum mlx5dr_icm_chunk_size chunk_size)
{
int num_of_entries;
int entry_size;
- if (icm_type == DR_ICM_TYPE_STE)
- entry_size = DR_STE_SIZE;
- else
- entry_size = DR_MODIFY_ACTION_SIZE;
-
+ entry_size = mlx5dr_icm_pool_dm_type_to_entry_size(icm_type);
num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(chunk_size);
return entry_size * num_of_entries;
return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner);
}
+/* buddy functions & structure */
+
+struct mlx5dr_icm_mr;
+
+struct mlx5dr_icm_buddy_mem {
+ unsigned long **bitmap;
+ unsigned int *num_free;
+ u32 max_order;
+ struct list_head list_node;
+ struct mlx5dr_icm_mr *icm_mr;
+ struct mlx5dr_icm_pool *pool;
+
+ /* This is the list of used chunks. HW may be accessing this memory */
+ struct list_head used_list;
+ u64 used_memory;
+
+ /* Hardware may be accessing this memory but at some future,
+ * undetermined time, it might cease to do so.
+ * sync_ste command sets them free.
+ */
+ struct list_head hot_list;
+};
+
+int mlx5dr_buddy_init(struct mlx5dr_icm_buddy_mem *buddy,
+ unsigned int max_order);
+void mlx5dr_buddy_cleanup(struct mlx5dr_icm_buddy_mem *buddy);
+int mlx5dr_buddy_alloc_mem(struct mlx5dr_icm_buddy_mem *buddy,
+ unsigned int order,
+ unsigned int *segment);
+void mlx5dr_buddy_free_mem(struct mlx5dr_icm_buddy_mem *buddy,
+ unsigned int seg, unsigned int order);
+
#endif /* _MLX5DR_H_ */
}
mlxfw_info(mlxfw_dev, "Initialize firmware flash process\n");
- devlink_flash_update_begin_notify(mlxfw_dev->devlink);
mlxfw_status_notify(mlxfw_dev, "Initializing firmware flash process",
NULL, 0, 0);
err = mlxfw_dev->ops->fsm_lock(mlxfw_dev, &fwhandle);
mlxfw_info(mlxfw_dev, "Firmware flash done\n");
mlxfw_status_notify(mlxfw_dev, "Firmware flash done", NULL, 0, 0);
mlxfw_mfa2_file_fini(mfa2_file);
- devlink_flash_update_end_notify(mlxfw_dev->devlink);
return 0;
err_state_wait_activate_to_locked:
mlxfw_dev->ops->fsm_release(mlxfw_dev, fwhandle);
err_fsm_lock:
mlxfw_mfa2_file_fini(mfa2_file);
- devlink_flash_update_end_notify(mlxfw_dev->devlink);
return err;
}
EXPORT_SYMBOL(mlxfw_firmware_flash);
struct devlink_flash_update_params *params,
struct netlink_ext_ack *extack)
{
- const struct firmware *firmware;
- int err;
-
- err = request_firmware_direct(&firmware, params->file_name, mlxsw_core->bus_info->dev);
- if (err)
- return err;
- err = mlxsw_core_fw_flash(mlxsw_core, firmware, extack);
- release_firmware(firmware);
-
- return err;
+ return mlxsw_core_fw_flash(mlxsw_core, params->fw, extack);
}
static int mlxsw_core_devlink_param_fw_load_policy_validate(struct devlink *devlink, u32 id,
#ifndef _MLXSW_CORE_ENV_H
#define _MLXSW_CORE_ENV_H
+struct ethtool_modinfo;
+struct ethtool_eeprom;
+
int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module,
int off, int *temp);
*/
MLXSW_ITEM32(reg, spvid, sub_port, 0x00, 8, 8);
+/* reg_spvid_et_vlan
+ * EtherType used for when VLAN is pushed at ingress (for untagged
+ * packets or for QinQ push mode).
+ * 0: ether_type0 - (default)
+ * 1: ether_type1
+ * 2: ether_type2 - Reserved when Spectrum-1, supported by Spectrum-2
+ * Ethertype IDs are configured by SVER.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spvid, et_vlan, 0x04, 16, 2);
+
/* reg_spvid_pvid
* Port default VID
* Access: RW
*/
MLXSW_ITEM32(reg, spvid, pvid, 0x04, 0, 12);
-static inline void mlxsw_reg_spvid_pack(char *payload, u8 local_port, u16 pvid)
+static inline void mlxsw_reg_spvid_pack(char *payload, u8 local_port, u16 pvid,
+ u8 et_vlan)
{
MLXSW_REG_ZERO(spvid, payload);
mlxsw_reg_spvid_local_port_set(payload, local_port);
mlxsw_reg_spvid_pvid_set(payload, pvid);
+ mlxsw_reg_spvid_et_vlan_set(payload, et_vlan);
}
/* SPVM - Switch Port VLAN Membership
}
}
+/* SPVC - Switch Port VLAN Classification Register
+ * -----------------------------------------------
+ * Configures the port to identify packets as untagged / single tagged /
+ * double packets based on the packet EtherTypes.
+ * Ethertype IDs are configured by SVER.
+ */
+#define MLXSW_REG_SPVC_ID 0x2026
+#define MLXSW_REG_SPVC_LEN 0x0C
+
+MLXSW_REG_DEFINE(spvc, MLXSW_REG_SPVC_ID, MLXSW_REG_SPVC_LEN);
+
+/* reg_spvc_local_port
+ * Local port.
+ * Access: Index
+ *
+ * Note: applies both to Rx port and Tx port, so if a packet traverses
+ * through Rx port i and a Tx port j then port i and port j must have the
+ * same configuration.
+ */
+MLXSW_ITEM32(reg, spvc, local_port, 0x00, 16, 8);
+
+/* reg_spvc_inner_et2
+ * Vlan Tag1 EtherType2 enable.
+ * Packet is initially classified as double VLAN Tag if in addition to
+ * being classified with a tag0 VLAN Tag its tag1 EtherType value is
+ * equal to ether_type2.
+ * 0: disable (default)
+ * 1: enable
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spvc, inner_et2, 0x08, 17, 1);
+
+/* reg_spvc_et2
+ * Vlan Tag0 EtherType2 enable.
+ * Packet is initially classified as VLAN Tag if its tag0 EtherType is
+ * equal to ether_type2.
+ * 0: disable (default)
+ * 1: enable
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spvc, et2, 0x08, 16, 1);
+
+/* reg_spvc_inner_et1
+ * Vlan Tag1 EtherType1 enable.
+ * Packet is initially classified as double VLAN Tag if in addition to
+ * being classified with a tag0 VLAN Tag its tag1 EtherType value is
+ * equal to ether_type1.
+ * 0: disable
+ * 1: enable (default)
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spvc, inner_et1, 0x08, 9, 1);
+
+/* reg_spvc_et1
+ * Vlan Tag0 EtherType1 enable.
+ * Packet is initially classified as VLAN Tag if its tag0 EtherType is
+ * equal to ether_type1.
+ * 0: disable
+ * 1: enable (default)
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spvc, et1, 0x08, 8, 1);
+
+/* reg_inner_et0
+ * Vlan Tag1 EtherType0 enable.
+ * Packet is initially classified as double VLAN Tag if in addition to
+ * being classified with a tag0 VLAN Tag its tag1 EtherType value is
+ * equal to ether_type0.
+ * 0: disable
+ * 1: enable (default)
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spvc, inner_et0, 0x08, 1, 1);
+
+/* reg_et0
+ * Vlan Tag0 EtherType0 enable.
+ * Packet is initially classified as VLAN Tag if its tag0 EtherType is
+ * equal to ether_type0.
+ * 0: disable
+ * 1: enable (default)
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spvc, et0, 0x08, 0, 1);
+
+static inline void mlxsw_reg_spvc_pack(char *payload, u8 local_port, bool et1,
+ bool et0)
+{
+ MLXSW_REG_ZERO(spvc, payload);
+ mlxsw_reg_spvc_local_port_set(payload, local_port);
+ /* Enable inner_et1 and inner_et0 to enable identification of double
+ * tagged packets.
+ */
+ mlxsw_reg_spvc_inner_et1_set(payload, 1);
+ mlxsw_reg_spvc_inner_et0_set(payload, 1);
+ mlxsw_reg_spvc_et1_set(payload, et1);
+ mlxsw_reg_spvc_et0_set(payload, et0);
+}
+
/* CWTP - Congetion WRED ECN TClass Profile
* ----------------------------------------
* Configures the profiles for queues of egress port and traffic class
enum mlxsw_reg_ralxx_protocol protocol,
enum mlxsw_reg_ralue_op op,
u16 virtual_router, u8 prefix_len,
- u32 dip)
+ u32 *dip)
{
mlxsw_reg_ralue_pack(payload, protocol, op, virtual_router, prefix_len);
- mlxsw_reg_ralue_dip4_set(payload, dip);
+ if (dip)
+ mlxsw_reg_ralue_dip4_set(payload, *dip);
}
static inline void mlxsw_reg_ralue_pack6(char *payload,
const void *dip)
{
mlxsw_reg_ralue_pack(payload, protocol, op, virtual_router, prefix_len);
- mlxsw_reg_ralue_dip6_memcpy_to(payload, dip);
+ if (dip)
+ mlxsw_reg_ralue_dip6_memcpy_to(payload, dip);
}
static inline void
mlxsw_reg_rmft2_sip6_mask_memcpy_to(payload, (void *)&sip6_mask);
}
+/* Note that XRALXX register position violates the rule of ordering register
+ * definition by the ID. However, XRALXX pack helpers are using RALXX pack
+ * helpers, RALXX registers have higher IDs.
+ */
+
+/* XRALTA - XM Router Algorithmic LPM Tree Allocation Register
+ * -----------------------------------------------------------
+ * The XRALTA is used to allocate the XLT LPM trees.
+ *
+ * This register embeds original RALTA register.
+ */
+#define MLXSW_REG_XRALTA_ID 0x7811
+#define MLXSW_REG_XRALTA_LEN 0x08
+#define MLXSW_REG_XRALTA_RALTA_OFFSET 0x04
+
+MLXSW_REG_DEFINE(xralta, MLXSW_REG_XRALTA_ID, MLXSW_REG_XRALTA_LEN);
+
+static inline void mlxsw_reg_xralta_pack(char *payload, bool alloc,
+ enum mlxsw_reg_ralxx_protocol protocol,
+ u8 tree_id)
+{
+ char *ralta_payload = payload + MLXSW_REG_XRALTA_RALTA_OFFSET;
+
+ MLXSW_REG_ZERO(xralta, payload);
+ mlxsw_reg_ralta_pack(ralta_payload, alloc, protocol, tree_id);
+}
+
+/* XRALST - XM Router Algorithmic LPM Structure Tree Register
+ * ----------------------------------------------------------
+ * The XRALST is used to set and query the structure of an XLT LPM tree.
+ *
+ * This register embeds original RALST register.
+ */
+#define MLXSW_REG_XRALST_ID 0x7812
+#define MLXSW_REG_XRALST_LEN 0x108
+#define MLXSW_REG_XRALST_RALST_OFFSET 0x04
+
+MLXSW_REG_DEFINE(xralst, MLXSW_REG_XRALST_ID, MLXSW_REG_XRALST_LEN);
+
+static inline void mlxsw_reg_xralst_pack(char *payload, u8 root_bin, u8 tree_id)
+{
+ char *ralst_payload = payload + MLXSW_REG_XRALST_RALST_OFFSET;
+
+ MLXSW_REG_ZERO(xralst, payload);
+ mlxsw_reg_ralst_pack(ralst_payload, root_bin, tree_id);
+}
+
+static inline void mlxsw_reg_xralst_bin_pack(char *payload, u8 bin_number,
+ u8 left_child_bin,
+ u8 right_child_bin)
+{
+ char *ralst_payload = payload + MLXSW_REG_XRALST_RALST_OFFSET;
+
+ mlxsw_reg_ralst_bin_pack(ralst_payload, bin_number, left_child_bin,
+ right_child_bin);
+}
+
+/* XRALTB - XM Router Algorithmic LPM Tree Binding Register
+ * --------------------------------------------------------
+ * The XRALTB register is used to bind virtual router and protocol
+ * to an allocated LPM tree.
+ *
+ * This register embeds original RALTB register.
+ */
+#define MLXSW_REG_XRALTB_ID 0x7813
+#define MLXSW_REG_XRALTB_LEN 0x08
+#define MLXSW_REG_XRALTB_RALTB_OFFSET 0x04
+
+MLXSW_REG_DEFINE(xraltb, MLXSW_REG_XRALTB_ID, MLXSW_REG_XRALTB_LEN);
+
+static inline void mlxsw_reg_xraltb_pack(char *payload, u16 virtual_router,
+ enum mlxsw_reg_ralxx_protocol protocol,
+ u8 tree_id)
+{
+ char *raltb_payload = payload + MLXSW_REG_XRALTB_RALTB_OFFSET;
+
+ MLXSW_REG_ZERO(xraltb, payload);
+ mlxsw_reg_raltb_pack(raltb_payload, virtual_router, protocol, tree_id);
+}
+
/* MFCR - Management Fan Control Register
* --------------------------------------
* This register controls the settings of the Fan Speed PWM mechanism.
MLXSW_REG(svpe),
MLXSW_REG(sfmr),
MLXSW_REG(spvmlr),
+ MLXSW_REG(spvc),
MLXSW_REG(cwtp),
MLXSW_REG(cwtpm),
MLXSW_REG(pgcr),
MLXSW_REG(rigr2),
MLXSW_REG(recr2),
MLXSW_REG(rmft2),
+ MLXSW_REG(xralta),
+ MLXSW_REG(xralst),
+ MLXSW_REG(xraltb),
MLXSW_REG(mfcr),
MLXSW_REG(mfsc),
MLXSW_REG(mfsm),
return err;
}
+static int mlxsw_sp_ethtype_to_sver_type(u16 ethtype, u8 *p_sver_type)
+{
+ switch (ethtype) {
+ case ETH_P_8021Q:
+ *p_sver_type = 0;
+ break;
+ case ETH_P_8021AD:
+ *p_sver_type = 1;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int __mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port,
- u16 vid)
+ u16 vid, u16 ethtype)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
char spvid_pl[MLXSW_REG_SPVID_LEN];
+ u8 sver_type;
+ int err;
+
+ err = mlxsw_sp_ethtype_to_sver_type(ethtype, &sver_type);
+ if (err)
+ return err;
+
+ mlxsw_reg_spvid_pack(spvid_pl, mlxsw_sp_port->local_port, vid,
+ sver_type);
- mlxsw_reg_spvid_pack(spvid_pl, mlxsw_sp_port->local_port, vid);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvid), spvid_pl);
}
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spaft), spaft_pl);
}
-int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
+int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid,
+ u16 ethtype)
{
int err;
if (err)
return err;
} else {
- err = __mlxsw_sp_port_pvid_set(mlxsw_sp_port, vid);
+ err = __mlxsw_sp_port_pvid_set(mlxsw_sp_port, vid, ethtype);
if (err)
return err;
err = mlxsw_sp_port_allow_untagged_set(mlxsw_sp_port, true);
return 0;
err_port_allow_untagged_set:
- __mlxsw_sp_port_pvid_set(mlxsw_sp_port, mlxsw_sp_port->pvid);
+ __mlxsw_sp_port_pvid_set(mlxsw_sp_port, mlxsw_sp_port->pvid, ethtype);
return err;
}
return 0;
}
+int
+mlxsw_sp_port_vlan_classification_set(struct mlxsw_sp_port *mlxsw_sp_port,
+ bool is_8021ad_tagged,
+ bool is_8021q_tagged)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ char spvc_pl[MLXSW_REG_SPVC_LEN];
+
+ mlxsw_reg_spvc_pack(spvc_pl, mlxsw_sp_port->local_port,
+ is_8021ad_tagged, is_8021q_tagged);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvc), spvc_pl);
+}
+
static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
u8 split_base_local_port,
struct mlxsw_sp_port_mapping *port_mapping)
goto err_port_nve_init;
}
- err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
+ err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID,
+ ETH_P_8021Q);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set PVID\n",
mlxsw_sp_port->local_port);
}
mlxsw_sp_port->default_vlan = mlxsw_sp_port_vlan;
+ /* Set SPVC.et0=true and SPVC.et1=false to make the local port to treat
+ * only packets with 802.1q header as tagged packets.
+ */
+ err = mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, false, true);
+ if (err) {
+ dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set default VLAN classification\n",
+ local_port);
+ goto err_port_vlan_classification_set;
+ }
+
INIT_DELAYED_WORK(&mlxsw_sp_port->ptp.shaper_dw,
mlxsw_sp->ptp_ops->shaper_work);
err_register_netdev:
err_port_overheat_init_val_set:
+ mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, true, true);
+err_port_vlan_classification_set:
mlxsw_sp->ports[local_port] = NULL;
mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
err_port_vlan_create:
mlxsw_sp_port_ptp_clear(mlxsw_sp_port);
mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp);
unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
+ mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, true, true);
mlxsw_sp->ports[local_port] = NULL;
mlxsw_sp_port_vlan_flush(mlxsw_sp_port, true);
mlxsw_sp_port_nve_fini(mlxsw_sp_port);
lag->ref_count--;
/* Make sure untagged frames are allowed to ingress */
- mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
+ mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID,
+ ETH_P_8021Q);
}
static int mlxsw_sp_lag_dist_port_add(struct mlxsw_sp_port *mlxsw_sp_port,
struct net_device *upper_dev;
struct mlxsw_sp *mlxsw_sp;
int err = 0;
+ u16 proto;
mlxsw_sp_port = netdev_priv(dev);
mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on an OVS port");
return -EINVAL;
}
+ if (netif_is_bridge_master(upper_dev)) {
+ br_vlan_get_proto(upper_dev, &proto);
+ if (br_vlan_enabled(upper_dev) &&
+ proto != ETH_P_8021Q && proto != ETH_P_8021AD) {
+ NL_SET_ERR_MSG_MOD(extack, "Enslaving a port to a bridge with unknown VLAN protocol is not supported");
+ return -EOPNOTSUPP;
+ }
+ if (vlan_uses_dev(lower_dev) &&
+ br_vlan_enabled(upper_dev) &&
+ proto == ETH_P_8021AD) {
+ NL_SET_ERR_MSG_MOD(extack, "Enslaving a port that already has a VLAN upper to an 802.1ad bridge is not supported");
+ return -EOPNOTSUPP;
+ }
+ }
+ if (netif_is_bridge_port(lower_dev) && is_vlan_dev(upper_dev)) {
+ struct net_device *br_dev = netdev_master_upper_dev_get(lower_dev);
+
+ if (br_vlan_enabled(br_dev)) {
+ br_vlan_get_proto(br_dev, &proto);
+ if (proto == ETH_P_8021AD) {
+ NL_SET_ERR_MSG_MOD(extack, "VLAN uppers are not supported on a port enslaved to an 802.1ad bridge");
+ return -EOPNOTSUPP;
+ }
+ }
+ }
+ if (is_vlan_dev(upper_dev) &&
+ ntohs(vlan_dev_vlan_proto(upper_dev)) != ETH_P_8021Q) {
+ NL_SET_ERR_MSG_MOD(extack, "VLAN uppers are only supported with 802.1q VLAN protocol");
+ return -EOPNOTSUPP;
+ }
break;
case NETDEV_CHANGEUPPER:
upper_dev = info->upper_dev;
struct netdev_notifier_changeupper_info *info = ptr;
struct netlink_ext_ack *extack;
struct net_device *upper_dev;
+ u16 proto;
if (!mlxsw_sp)
return 0;
}
if (!info->linking)
break;
+ if (br_vlan_enabled(br_dev)) {
+ br_vlan_get_proto(br_dev, &proto);
+ if (proto == ETH_P_8021AD) {
+ NL_SET_ERR_MSG_MOD(extack, "Uppers are not supported on top of an 802.1ad bridge");
+ return -EOPNOTSUPP;
+ }
+ }
+ if (is_vlan_dev(upper_dev) &&
+ ntohs(vlan_dev_vlan_proto(upper_dev)) != ETH_P_8021Q) {
+ NL_SET_ERR_MSG_MOD(extack, "VLAN uppers are only supported with 802.1q VLAN protocol");
+ return -EOPNOTSUPP;
+ }
if (netif_is_macvlan(upper_dev) &&
!mlxsw_sp_rif_exists(mlxsw_sp, br_dev)) {
NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
#ifndef _MLXSW_SPECTRUM_H
#define _MLXSW_SPECTRUM_H
+#include <linux/ethtool.h>
#include <linux/types.h>
#include <linux/netdevice.h>
#include <linux/rhashtable.h>
int prio, char *ppcnt_pl);
int mlxsw_sp_port_admin_status_set(struct mlxsw_sp_port *mlxsw_sp_port,
bool is_up);
+int
+mlxsw_sp_port_vlan_classification_set(struct mlxsw_sp_port *mlxsw_sp_port,
+ bool is_8021ad_tagged,
+ bool is_8021q_tagged);
/* spectrum_buffers.c */
struct mlxsw_sp_hdroom_prio {
int mlxsw_sp_port_vp_mode_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable);
int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid,
bool learn_enable);
-int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
+int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid,
+ u16 ethtype);
struct mlxsw_sp_port_vlan *
mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
void mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router)
if (mlxsw_sp_nexthop_offload(nh) &&
- !mlxsw_sp_nexthop_group_has_ipip(nh))
+ !mlxsw_sp_nexthop_group_has_ipip(nh) &&
+ !mlxsw_sp_nexthop_is_discard(nh))
size++;
return size;
}
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))
+ mlxsw_sp_nexthop_group_has_ipip(nh) ||
+ mlxsw_sp_nexthop_is_discard(nh))
continue;
if (nh_count < nh_skip)
mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) {
if (!mlxsw_sp_nexthop_offload(nh) ||
- mlxsw_sp_nexthop_group_has_ipip(nh))
+ mlxsw_sp_nexthop_group_has_ipip(nh) ||
+ mlxsw_sp_nexthop_is_discard(nh))
continue;
mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_size,
}
static int
-mlxsw_sp_ipip_fib_entry_op_gre4_ralue(struct mlxsw_sp *mlxsw_sp,
- u32 dip, u8 prefix_len, u16 ul_vr_id,
- enum mlxsw_reg_ralue_op op,
- u32 tunnel_index)
+mlxsw_sp_ipip_fib_entry_op_gre4_do(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp_router_ll_ops *ll_ops,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ u32 dip, u8 prefix_len, u16 ul_vr_id,
+ enum mlxsw_sp_fib_entry_op op,
+ u32 tunnel_index,
+ struct mlxsw_sp_fib_entry_priv *priv)
{
- char ralue_pl[MLXSW_REG_RALUE_LEN];
-
- mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_REG_RALXX_PROTOCOL_IPV4, op,
- ul_vr_id, prefix_len, dip);
- mlxsw_reg_ralue_act_ip2me_tun_pack(ralue_pl, tunnel_index);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+ ll_ops->fib_entry_pack(op_ctx, MLXSW_SP_L3_PROTO_IPV4, op, ul_vr_id,
+ prefix_len, (unsigned char *) &dip, priv);
+ ll_ops->fib_entry_act_ip2me_tun_pack(op_ctx, tunnel_index);
+ return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops);
}
static int mlxsw_sp_ipip_fib_entry_op_gre4(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_ipip_entry *ipip_entry,
- enum mlxsw_reg_ralue_op op,
- u32 tunnel_index)
+ const struct mlxsw_sp_router_ll_ops *ll_ops,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ struct mlxsw_sp_ipip_entry *ipip_entry,
+ enum mlxsw_sp_fib_entry_op op, u32 tunnel_index,
+ struct mlxsw_sp_fib_entry_priv *priv)
{
u16 ul_vr_id = mlxsw_sp_ipip_lb_ul_vr_id(ipip_entry->ol_lb);
__be32 dip;
dip = mlxsw_sp_ipip_netdev_saddr(MLXSW_SP_L3_PROTO_IPV4,
ipip_entry->ol_dev).addr4;
- return mlxsw_sp_ipip_fib_entry_op_gre4_ralue(mlxsw_sp, be32_to_cpu(dip),
- 32, ul_vr_id, op,
- tunnel_index);
+ return mlxsw_sp_ipip_fib_entry_op_gre4_do(mlxsw_sp, ll_ops, op_ctx, be32_to_cpu(dip),
+ 32, ul_vr_id, op, tunnel_index, priv);
}
static bool mlxsw_sp_ipip_tunnel_complete(enum mlxsw_sp_l3proto proto,
}
static bool mlxsw_sp_ipip_can_offload_gre4(const struct mlxsw_sp *mlxsw_sp,
- const struct net_device *ol_dev,
- enum mlxsw_sp_l3proto ol_proto)
+ const struct net_device *ol_dev)
{
struct ip_tunnel *tunnel = netdev_priv(ol_dev);
__be16 okflags = TUNNEL_KEY; /* We can't offload any other features. */
struct mlxsw_sp_ipip_entry *ipip_entry);
bool (*can_offload)(const struct mlxsw_sp *mlxsw_sp,
- const struct net_device *ol_dev,
- enum mlxsw_sp_l3proto ol_proto);
+ const struct net_device *ol_dev);
/* Return a configuration for creating an overlay loopback RIF. */
struct mlxsw_sp_rif_ipip_lb_config
const struct net_device *ol_dev);
int (*fib_entry_op)(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp_router_ll_ops *ll_ops,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_ipip_entry *ipip_entry,
- enum mlxsw_reg_ralue_op op,
- u32 tunnel_index);
+ enum mlxsw_sp_fib_entry_op op,
+ u32 tunnel_index,
+ struct mlxsw_sp_fib_entry_priv *priv);
int (*ol_netdev_change)(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_ipip_entry *ipip_entry,
goto err_hashtable_init;
/* Delive these message types as PTP0. */
- message_type = BIT(MLXSW_SP_PTP_MESSAGE_TYPE_SYNC) |
- BIT(MLXSW_SP_PTP_MESSAGE_TYPE_DELAY_REQ) |
- BIT(MLXSW_SP_PTP_MESSAGE_TYPE_PDELAY_REQ) |
- BIT(MLXSW_SP_PTP_MESSAGE_TYPE_PDELAY_RESP);
+ message_type = BIT(PTP_MSGTYPE_SYNC) |
+ BIT(PTP_MSGTYPE_DELAY_REQ) |
+ BIT(PTP_MSGTYPE_PDELAY_REQ) |
+ BIT(PTP_MSGTYPE_PDELAY_RESP);
err = mlxsw_sp_ptp_mtptpt_set(mlxsw_sp, MLXSW_REG_MTPTPT_TRAP_ID_PTP0,
message_type);
if (err)
struct mlxsw_sp_port;
struct mlxsw_sp_ptp_clock;
-enum {
- MLXSW_SP_PTP_MESSAGE_TYPE_SYNC,
- MLXSW_SP_PTP_MESSAGE_TYPE_DELAY_REQ,
- MLXSW_SP_PTP_MESSAGE_TYPE_PDELAY_REQ,
- MLXSW_SP_PTP_MESSAGE_TYPE_PDELAY_RESP,
-};
-
static inline int mlxsw_sp_ptp_get_ts_info_noptp(struct ethtool_ts_info *info)
{
info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP,
};
+struct mlxsw_sp_nexthop_group_info;
struct mlxsw_sp_nexthop_group;
struct mlxsw_sp_fib_entry;
u32 tunnel_index;
};
+static struct mlxsw_sp_fib_entry_priv *
+mlxsw_sp_fib_entry_priv_create(const struct mlxsw_sp_router_ll_ops *ll_ops)
+{
+ struct mlxsw_sp_fib_entry_priv *priv;
+
+ if (!ll_ops->fib_entry_priv_size)
+ /* No need to have priv */
+ return NULL;
+
+ priv = kzalloc(sizeof(*priv) + ll_ops->fib_entry_priv_size, GFP_KERNEL);
+ if (!priv)
+ return ERR_PTR(-ENOMEM);
+ refcount_set(&priv->refcnt, 1);
+ return priv;
+}
+
+static void
+mlxsw_sp_fib_entry_priv_destroy(struct mlxsw_sp_fib_entry_priv *priv)
+{
+ kfree(priv);
+}
+
+static void mlxsw_sp_fib_entry_priv_hold(struct mlxsw_sp_fib_entry_priv *priv)
+{
+ refcount_inc(&priv->refcnt);
+}
+
+static void mlxsw_sp_fib_entry_priv_put(struct mlxsw_sp_fib_entry_priv *priv)
+{
+ if (!priv || !refcount_dec_and_test(&priv->refcnt))
+ return;
+ mlxsw_sp_fib_entry_priv_destroy(priv);
+}
+
+static void mlxsw_sp_fib_entry_op_ctx_priv_hold(struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ struct mlxsw_sp_fib_entry_priv *priv)
+{
+ if (!priv)
+ return;
+ mlxsw_sp_fib_entry_priv_hold(priv);
+ list_add(&priv->list, &op_ctx->fib_entry_priv_list);
+}
+
+static void mlxsw_sp_fib_entry_op_ctx_priv_put_all(struct mlxsw_sp_fib_entry_op_ctx *op_ctx)
+{
+ struct mlxsw_sp_fib_entry_priv *priv, *tmp;
+
+ list_for_each_entry_safe(priv, tmp, &op_ctx->fib_entry_priv_list, list)
+ mlxsw_sp_fib_entry_priv_put(priv);
+ INIT_LIST_HEAD(&op_ctx->fib_entry_priv_list);
+}
+
struct mlxsw_sp_fib_entry {
struct mlxsw_sp_fib_node *fib_node;
enum mlxsw_sp_fib_entry_type type;
struct list_head nexthop_group_node;
struct mlxsw_sp_nexthop_group *nh_group;
struct mlxsw_sp_fib_entry_decap decap; /* Valid for decap entries. */
+ struct mlxsw_sp_fib_entry_priv *priv;
};
struct mlxsw_sp_fib4_entry {
struct mlxsw_sp_fib_entry common;
+ struct fib_info *fi;
u32 tb_id;
- u32 prio;
u8 tos;
u8 type;
};
struct mlxsw_sp_vr *vr;
struct mlxsw_sp_lpm_tree *lpm_tree;
enum mlxsw_sp_l3proto proto;
+ const struct mlxsw_sp_router_ll_ops *ll_ops;
};
struct mlxsw_sp_vr {
refcount_t ul_rif_refcnt;
};
+static int mlxsw_sp_router_ll_basic_ralta_write(struct mlxsw_sp *mlxsw_sp, char *xralta_pl)
+{
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta),
+ xralta_pl + MLXSW_REG_XRALTA_RALTA_OFFSET);
+}
+
+static int mlxsw_sp_router_ll_basic_ralst_write(struct mlxsw_sp *mlxsw_sp, char *xralst_pl)
+{
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst),
+ xralst_pl + MLXSW_REG_XRALST_RALST_OFFSET);
+}
+
+static int mlxsw_sp_router_ll_basic_raltb_write(struct mlxsw_sp *mlxsw_sp, char *xraltb_pl)
+{
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb),
+ xraltb_pl + MLXSW_REG_XRALTB_RALTB_OFFSET);
+}
+
static const struct rhashtable_params mlxsw_sp_fib_ht_params;
static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_vr *vr,
enum mlxsw_sp_l3proto proto)
{
+ const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto];
struct mlxsw_sp_lpm_tree *lpm_tree;
struct mlxsw_sp_fib *fib;
int err;
fib->proto = proto;
fib->vr = vr;
fib->lpm_tree = lpm_tree;
+ fib->ll_ops = ll_ops;
mlxsw_sp_lpm_tree_hold(lpm_tree);
err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib, lpm_tree->id);
if (err)
}
static int mlxsw_sp_lpm_tree_alloc(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp_router_ll_ops *ll_ops,
struct mlxsw_sp_lpm_tree *lpm_tree)
{
- char ralta_pl[MLXSW_REG_RALTA_LEN];
+ char xralta_pl[MLXSW_REG_XRALTA_LEN];
- mlxsw_reg_ralta_pack(ralta_pl, true,
- (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto,
- lpm_tree->id);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl);
+ mlxsw_reg_xralta_pack(xralta_pl, true,
+ (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto,
+ lpm_tree->id);
+ return ll_ops->ralta_write(mlxsw_sp, xralta_pl);
}
static void mlxsw_sp_lpm_tree_free(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp_router_ll_ops *ll_ops,
struct mlxsw_sp_lpm_tree *lpm_tree)
{
- char ralta_pl[MLXSW_REG_RALTA_LEN];
+ char xralta_pl[MLXSW_REG_XRALTA_LEN];
- mlxsw_reg_ralta_pack(ralta_pl, false,
- (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto,
- lpm_tree->id);
- mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl);
+ mlxsw_reg_xralta_pack(xralta_pl, false,
+ (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto,
+ lpm_tree->id);
+ ll_ops->ralta_write(mlxsw_sp, xralta_pl);
}
static int
mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp_router_ll_ops *ll_ops,
struct mlxsw_sp_prefix_usage *prefix_usage,
struct mlxsw_sp_lpm_tree *lpm_tree)
{
- char ralst_pl[MLXSW_REG_RALST_LEN];
+ char xralst_pl[MLXSW_REG_XRALST_LEN];
u8 root_bin = 0;
u8 prefix;
u8 last_prefix = MLXSW_REG_RALST_BIN_NO_CHILD;
mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage)
root_bin = prefix;
- mlxsw_reg_ralst_pack(ralst_pl, root_bin, lpm_tree->id);
+ mlxsw_reg_xralst_pack(xralst_pl, root_bin, lpm_tree->id);
mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) {
if (prefix == 0)
continue;
- mlxsw_reg_ralst_bin_pack(ralst_pl, prefix, last_prefix,
- MLXSW_REG_RALST_BIN_NO_CHILD);
+ mlxsw_reg_xralst_bin_pack(xralst_pl, prefix, last_prefix,
+ MLXSW_REG_RALST_BIN_NO_CHILD);
last_prefix = prefix;
}
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), ralst_pl);
+ return ll_ops->ralst_write(mlxsw_sp, xralst_pl);
}
static struct mlxsw_sp_lpm_tree *
mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp_router_ll_ops *ll_ops,
struct mlxsw_sp_prefix_usage *prefix_usage,
enum mlxsw_sp_l3proto proto)
{
if (!lpm_tree)
return ERR_PTR(-EBUSY);
lpm_tree->proto = proto;
- err = mlxsw_sp_lpm_tree_alloc(mlxsw_sp, lpm_tree);
+ err = mlxsw_sp_lpm_tree_alloc(mlxsw_sp, ll_ops, lpm_tree);
if (err)
return ERR_PTR(err);
- err = mlxsw_sp_lpm_tree_left_struct_set(mlxsw_sp, prefix_usage,
- lpm_tree);
+ err = mlxsw_sp_lpm_tree_left_struct_set(mlxsw_sp, ll_ops, prefix_usage, lpm_tree);
if (err)
goto err_left_struct_set;
memcpy(&lpm_tree->prefix_usage, prefix_usage,
return lpm_tree;
err_left_struct_set:
- mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree);
+ mlxsw_sp_lpm_tree_free(mlxsw_sp, ll_ops, lpm_tree);
return ERR_PTR(err);
}
static void mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp_router_ll_ops *ll_ops,
struct mlxsw_sp_lpm_tree *lpm_tree)
{
- mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree);
+ mlxsw_sp_lpm_tree_free(mlxsw_sp, ll_ops, lpm_tree);
}
static struct mlxsw_sp_lpm_tree *
struct mlxsw_sp_prefix_usage *prefix_usage,
enum mlxsw_sp_l3proto proto)
{
+ const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto];
struct mlxsw_sp_lpm_tree *lpm_tree;
int i;
return lpm_tree;
}
}
- return mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage, proto);
+ return mlxsw_sp_lpm_tree_create(mlxsw_sp, ll_ops, prefix_usage, proto);
}
static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree)
static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_lpm_tree *lpm_tree)
{
+ const struct mlxsw_sp_router_ll_ops *ll_ops =
+ mlxsw_sp->router->proto_ll_ops[lpm_tree->proto];
+
if (--lpm_tree->ref_count == 0)
- mlxsw_sp_lpm_tree_destroy(mlxsw_sp, lpm_tree);
+ mlxsw_sp_lpm_tree_destroy(mlxsw_sp, ll_ops, lpm_tree);
}
#define MLXSW_SP_LPM_TREE_MIN 1 /* tree 0 is reserved */
static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp,
const struct mlxsw_sp_fib *fib, u8 tree_id)
{
- char raltb_pl[MLXSW_REG_RALTB_LEN];
+ char xraltb_pl[MLXSW_REG_XRALTB_LEN];
- mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id,
- (enum mlxsw_reg_ralxx_protocol) fib->proto,
- tree_id);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
+ mlxsw_reg_xraltb_pack(xraltb_pl, fib->vr->id,
+ (enum mlxsw_reg_ralxx_protocol) fib->proto,
+ tree_id);
+ return fib->ll_ops->raltb_write(mlxsw_sp, xraltb_pl);
}
static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp,
const struct mlxsw_sp_fib *fib)
{
- char raltb_pl[MLXSW_REG_RALTB_LEN];
+ char xraltb_pl[MLXSW_REG_XRALTB_LEN];
/* Bind to tree 0 which is default */
- mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id,
- (enum mlxsw_reg_ralxx_protocol) fib->proto, 0);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
+ mlxsw_reg_xraltb_pack(xraltb_pl, fib->vr->id,
+ (enum mlxsw_reg_ralxx_protocol) fib->proto, 0);
+ return fib->ll_ops->raltb_write(mlxsw_sp, xraltb_pl);
}
static u32 mlxsw_sp_fix_tb_id(u32 tb_id)
/* Given decap parameters, find the corresponding IPIP entry. */
static struct mlxsw_sp_ipip_entry *
-mlxsw_sp_ipip_entry_find_by_decap(struct mlxsw_sp *mlxsw_sp,
- const struct net_device *ul_dev,
+mlxsw_sp_ipip_entry_find_by_decap(struct mlxsw_sp *mlxsw_sp, int ul_dev_ifindex,
enum mlxsw_sp_l3proto ul_proto,
union mlxsw_sp_l3addr ul_dip)
{
- struct mlxsw_sp_ipip_entry *ipip_entry;
+ struct mlxsw_sp_ipip_entry *ipip_entry = NULL;
+ struct net_device *ul_dev;
+
+ rcu_read_lock();
+
+ ul_dev = dev_get_by_index_rcu(mlxsw_sp_net(mlxsw_sp), ul_dev_ifindex);
+ if (!ul_dev)
+ goto out_unlock;
list_for_each_entry(ipip_entry, &mlxsw_sp->router->ipip_list,
ipip_list_node)
if (mlxsw_sp_ipip_entry_matches_decap(mlxsw_sp, ul_dev,
ul_proto, ul_dip,
ipip_entry))
- return ipip_entry;
+ goto out_unlock;
+
+ rcu_read_unlock();
return NULL;
+
+out_unlock:
+ rcu_read_unlock();
+ return ipip_entry;
}
static bool mlxsw_sp_netdev_ipip_type(const struct mlxsw_sp *mlxsw_sp,
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);
+ return ops->can_offload(mlxsw_sp, ol_dev);
}
static int mlxsw_sp_netdevice_ipip_ol_reg_event(struct mlxsw_sp *mlxsw_sp,
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
- */
+ struct mlxsw_sp_nexthop_group_info *nhgi; /* pointer back to the group
+ * this nexthop belongs to
+ */
struct rhash_head ht_node;
+ struct neigh_table *neigh_tbl;
struct mlxsw_sp_nexthop_key key;
unsigned char gw_addr[sizeof(struct in6_addr)];
int ifindex;
offloaded:1, /* set in case the neigh is actually put into
* KVD linear area of this group.
*/
- update:1; /* set indicates that MAC of this neigh should be
+ update:1, /* set indicates that MAC of this neigh should be
* updated in HW
*/
+ discard:1; /* nexthop is programmed to discard packets */
enum mlxsw_sp_nexthop_type type;
union {
struct mlxsw_sp_neigh_entry *neigh_entry;
bool counter_valid;
};
-struct mlxsw_sp_nexthop_group {
- void *priv;
- struct rhash_head ht_node;
- struct list_head fib_list; /* list of fib entries that use this group */
- struct neigh_table *neigh_tbl;
- u8 adj_index_valid:1,
- gateway:1; /* routes using the group use a gateway */
+enum mlxsw_sp_nexthop_group_type {
+ MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4,
+ MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6,
+ MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ,
+};
+
+struct mlxsw_sp_nexthop_group_info {
+ struct mlxsw_sp_nexthop_group *nh_grp;
u32 adj_index;
u16 ecmp_size;
u16 count;
int sum_norm_weight;
+ u8 adj_index_valid:1,
+ gateway:1; /* routes using the group use a gateway */
struct mlxsw_sp_nexthop nexthops[0];
#define nh_rif nexthops[0].rif
};
+struct mlxsw_sp_nexthop_group_vr_key {
+ u16 vr_id;
+ enum mlxsw_sp_l3proto proto;
+};
+
+struct mlxsw_sp_nexthop_group_vr_entry {
+ struct list_head list; /* member in vr_list */
+ struct rhash_head ht_node; /* member in vr_ht */
+ refcount_t ref_count;
+ struct mlxsw_sp_nexthop_group_vr_key key;
+};
+
+struct mlxsw_sp_nexthop_group {
+ struct rhash_head ht_node;
+ struct list_head fib_list; /* list of fib entries that use this group */
+ union {
+ struct {
+ struct fib_info *fi;
+ } ipv4;
+ struct {
+ u32 id;
+ } obj;
+ };
+ struct mlxsw_sp_nexthop_group_info *nhgi;
+ struct list_head vr_list;
+ struct rhashtable vr_ht;
+ enum mlxsw_sp_nexthop_group_type type;
+ bool can_destroy;
+};
+
void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp,
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_nexthop_group *nh_grp = nh->nh_grp;
+ struct mlxsw_sp_nexthop_group_info *nhgi = nh->nhgi;
u32 adj_hash_index = 0;
int i;
- if (!nh->offloaded || !nh_grp->adj_index_valid)
+ if (!nh->offloaded || !nhgi->adj_index_valid)
return -EINVAL;
- *p_adj_index = nh_grp->adj_index;
- *p_adj_size = nh_grp->ecmp_size;
+ *p_adj_index = nhgi->adj_index;
+ *p_adj_size = nhgi->ecmp_size;
- for (i = 0; i < nh_grp->count; i++) {
- struct mlxsw_sp_nexthop *nh_iter = &nh_grp->nexthops[i];
+ for (i = 0; i < nhgi->count; i++) {
+ struct mlxsw_sp_nexthop *nh_iter = &nhgi->nexthops[i];
if (nh_iter == nh)
break;
bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh)
{
- struct mlxsw_sp_nexthop_group *nh_grp = nh->nh_grp;
+ struct mlxsw_sp_nexthop_group_info *nhgi = nh->nhgi;
int i;
- for (i = 0; i < nh_grp->count; i++) {
- struct mlxsw_sp_nexthop *nh_iter = &nh_grp->nexthops[i];
+ for (i = 0; i < nhgi->count; i++) {
+ struct mlxsw_sp_nexthop *nh_iter = &nhgi->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)
+bool mlxsw_sp_nexthop_is_discard(const struct mlxsw_sp_nexthop *nh)
+{
+ return nh->discard;
+}
+
+static const struct rhashtable_params mlxsw_sp_nexthop_group_vr_ht_params = {
+ .key_offset = offsetof(struct mlxsw_sp_nexthop_group_vr_entry, key),
+ .head_offset = offsetof(struct mlxsw_sp_nexthop_group_vr_entry, ht_node),
+ .key_len = sizeof(struct mlxsw_sp_nexthop_group_vr_key),
+ .automatic_shrinking = true,
+};
+
+static struct mlxsw_sp_nexthop_group_vr_entry *
+mlxsw_sp_nexthop_group_vr_entry_lookup(struct mlxsw_sp_nexthop_group *nh_grp,
+ const struct mlxsw_sp_fib *fib)
+{
+ struct mlxsw_sp_nexthop_group_vr_key key;
+
+ memset(&key, 0, sizeof(key));
+ key.vr_id = fib->vr->id;
+ key.proto = fib->proto;
+ return rhashtable_lookup_fast(&nh_grp->vr_ht, &key,
+ mlxsw_sp_nexthop_group_vr_ht_params);
+}
+
+static int
+mlxsw_sp_nexthop_group_vr_entry_create(struct mlxsw_sp_nexthop_group *nh_grp,
+ const struct mlxsw_sp_fib *fib)
+{
+ struct mlxsw_sp_nexthop_group_vr_entry *vr_entry;
+ int err;
+
+ vr_entry = kzalloc(sizeof(*vr_entry), GFP_KERNEL);
+ if (!vr_entry)
+ return -ENOMEM;
+
+ vr_entry->key.vr_id = fib->vr->id;
+ vr_entry->key.proto = fib->proto;
+ refcount_set(&vr_entry->ref_count, 1);
+
+ err = rhashtable_insert_fast(&nh_grp->vr_ht, &vr_entry->ht_node,
+ mlxsw_sp_nexthop_group_vr_ht_params);
+ if (err)
+ goto err_hashtable_insert;
+
+ list_add(&vr_entry->list, &nh_grp->vr_list);
+
+ return 0;
+
+err_hashtable_insert:
+ kfree(vr_entry);
+ return err;
+}
+
+static void
+mlxsw_sp_nexthop_group_vr_entry_destroy(struct mlxsw_sp_nexthop_group *nh_grp,
+ struct mlxsw_sp_nexthop_group_vr_entry *vr_entry)
+{
+ list_del(&vr_entry->list);
+ rhashtable_remove_fast(&nh_grp->vr_ht, &vr_entry->ht_node,
+ mlxsw_sp_nexthop_group_vr_ht_params);
+ kfree(vr_entry);
+}
+
+static int
+mlxsw_sp_nexthop_group_vr_link(struct mlxsw_sp_nexthop_group *nh_grp,
+ const struct mlxsw_sp_fib *fib)
+{
+ struct mlxsw_sp_nexthop_group_vr_entry *vr_entry;
+
+ vr_entry = mlxsw_sp_nexthop_group_vr_entry_lookup(nh_grp, fib);
+ if (vr_entry) {
+ refcount_inc(&vr_entry->ref_count);
+ return 0;
+ }
+
+ return mlxsw_sp_nexthop_group_vr_entry_create(nh_grp, fib);
+}
+
+static void
+mlxsw_sp_nexthop_group_vr_unlink(struct mlxsw_sp_nexthop_group *nh_grp,
+ const struct mlxsw_sp_fib *fib)
{
- return nh_grp->priv;
+ struct mlxsw_sp_nexthop_group_vr_entry *vr_entry;
+
+ vr_entry = mlxsw_sp_nexthop_group_vr_entry_lookup(nh_grp, fib);
+ if (WARN_ON_ONCE(!vr_entry))
+ return;
+
+ if (!refcount_dec_and_test(&vr_entry->ref_count))
+ return;
+
+ mlxsw_sp_nexthop_group_vr_entry_destroy(nh_grp, vr_entry);
}
struct mlxsw_sp_nexthop_group_cmp_arg {
- enum mlxsw_sp_l3proto proto;
+ enum mlxsw_sp_nexthop_group_type type;
union {
struct fib_info *fi;
struct mlxsw_sp_fib6_entry *fib6_entry;
+ u32 id;
};
};
{
int i;
- for (i = 0; i < nh_grp->count; i++) {
+ for (i = 0; i < nh_grp->nhgi->count; i++) {
const struct mlxsw_sp_nexthop *nh;
- nh = &nh_grp->nexthops[i];
+ nh = &nh_grp->nhgi->nexthops[i];
if (nh->ifindex == ifindex && nh->nh_weight == weight &&
ipv6_addr_equal(gw, (struct in6_addr *) nh->gw_addr))
return true;
{
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
- if (nh_grp->count != fib6_entry->nrt6)
+ if (nh_grp->nhgi->count != fib6_entry->nrt6)
return false;
list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
const struct mlxsw_sp_nexthop_group_cmp_arg *cmp_arg = arg->key;
const struct mlxsw_sp_nexthop_group *nh_grp = ptr;
- switch (cmp_arg->proto) {
- case MLXSW_SP_L3_PROTO_IPV4:
- return cmp_arg->fi != mlxsw_sp_nexthop4_group_fi(nh_grp);
- case MLXSW_SP_L3_PROTO_IPV6:
+ if (nh_grp->type != cmp_arg->type)
+ return 1;
+
+ switch (cmp_arg->type) {
+ case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4:
+ return cmp_arg->fi != nh_grp->ipv4.fi;
+ case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6:
return !mlxsw_sp_nexthop6_group_cmp(nh_grp,
cmp_arg->fib6_entry);
+ case MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ:
+ return cmp_arg->id != nh_grp->obj.id;
default:
WARN_ON(1);
return 1;
}
}
-static int
-mlxsw_sp_nexthop_group_type(const struct mlxsw_sp_nexthop_group *nh_grp)
-{
- return nh_grp->neigh_tbl->family;
-}
-
static u32 mlxsw_sp_nexthop_group_hash_obj(const void *data, u32 len, u32 seed)
{
const struct mlxsw_sp_nexthop_group *nh_grp = data;
unsigned int val;
int i;
- switch (mlxsw_sp_nexthop_group_type(nh_grp)) {
- case AF_INET:
- fi = mlxsw_sp_nexthop4_group_fi(nh_grp);
+ switch (nh_grp->type) {
+ case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4:
+ fi = nh_grp->ipv4.fi;
return jhash(&fi, sizeof(fi), seed);
- case AF_INET6:
- val = nh_grp->count;
- for (i = 0; i < nh_grp->count; i++) {
- nh = &nh_grp->nexthops[i];
+ case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6:
+ val = nh_grp->nhgi->count;
+ for (i = 0; i < nh_grp->nhgi->count; i++) {
+ nh = &nh_grp->nhgi->nexthops[i];
val ^= jhash(&nh->ifindex, sizeof(nh->ifindex), seed);
val ^= jhash(&nh->gw_addr, sizeof(nh->gw_addr), seed);
}
return jhash(&val, sizeof(val), seed);
+ case MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ:
+ return jhash(&nh_grp->obj.id, sizeof(nh_grp->obj.id), seed);
default:
WARN_ON(1);
return 0;
{
const struct mlxsw_sp_nexthop_group_cmp_arg *cmp_arg = data;
- switch (cmp_arg->proto) {
- case MLXSW_SP_L3_PROTO_IPV4:
+ switch (cmp_arg->type) {
+ case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4:
return jhash(&cmp_arg->fi, sizeof(cmp_arg->fi), seed);
- case MLXSW_SP_L3_PROTO_IPV6:
+ case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6:
return mlxsw_sp_nexthop6_group_hash(cmp_arg->fib6_entry, seed);
+ case MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ:
+ return jhash(&cmp_arg->id, sizeof(cmp_arg->id), seed);
default:
WARN_ON(1);
return 0;
static int mlxsw_sp_nexthop_group_insert(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp)
{
- if (mlxsw_sp_nexthop_group_type(nh_grp) == AF_INET6 &&
- !nh_grp->gateway)
+ if (nh_grp->type == MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6 &&
+ !nh_grp->nhgi->gateway)
return 0;
return rhashtable_insert_fast(&mlxsw_sp->router->nexthop_group_ht,
static void mlxsw_sp_nexthop_group_remove(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp)
{
- if (mlxsw_sp_nexthop_group_type(nh_grp) == AF_INET6 &&
- !nh_grp->gateway)
+ if (nh_grp->type == MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6 &&
+ !nh_grp->nhgi->gateway)
return;
rhashtable_remove_fast(&mlxsw_sp->router->nexthop_group_ht,
{
struct mlxsw_sp_nexthop_group_cmp_arg cmp_arg;
- cmp_arg.proto = MLXSW_SP_L3_PROTO_IPV4;
+ cmp_arg.type = MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4;
cmp_arg.fi = fi;
return rhashtable_lookup_fast(&mlxsw_sp->router->nexthop_group_ht,
&cmp_arg,
{
struct mlxsw_sp_nexthop_group_cmp_arg cmp_arg;
- cmp_arg.proto = MLXSW_SP_L3_PROTO_IPV6;
+ cmp_arg.type = MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6;
cmp_arg.fib6_entry = fib6_entry;
return rhashtable_lookup_fast(&mlxsw_sp->router->nexthop_group_ht,
&cmp_arg,
}
static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp,
- const struct mlxsw_sp_fib *fib,
+ enum mlxsw_sp_l3proto proto,
+ u16 vr_id,
u32 adj_index, u16 ecmp_size,
u32 new_adj_index,
u16 new_ecmp_size)
char raleu_pl[MLXSW_REG_RALEU_LEN];
mlxsw_reg_raleu_pack(raleu_pl,
- (enum mlxsw_reg_ralxx_protocol) fib->proto,
- fib->vr->id, adj_index, ecmp_size, new_adj_index,
+ (enum mlxsw_reg_ralxx_protocol) proto, vr_id,
+ adj_index, ecmp_size, new_adj_index,
new_ecmp_size);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raleu), raleu_pl);
}
struct mlxsw_sp_nexthop_group *nh_grp,
u32 old_adj_index, u16 old_ecmp_size)
{
- struct mlxsw_sp_fib_entry *fib_entry;
- struct mlxsw_sp_fib *fib = NULL;
+ struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi;
+ struct mlxsw_sp_nexthop_group_vr_entry *vr_entry;
int err;
- list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) {
- if (fib == fib_entry->fib_node->fib)
- continue;
- fib = fib_entry->fib_node->fib;
- err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, fib,
+ list_for_each_entry(vr_entry, &nh_grp->vr_list, list) {
+ err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp,
+ vr_entry->key.proto,
+ vr_entry->key.vr_id,
old_adj_index,
old_ecmp_size,
- nh_grp->adj_index,
- nh_grp->ecmp_size);
+ nhgi->adj_index,
+ nhgi->ecmp_size);
if (err)
- return err;
+ goto err_mass_update_vr;
}
return 0;
+
+err_mass_update_vr:
+ list_for_each_entry_continue_reverse(vr_entry, &nh_grp->vr_list, list)
+ mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, vr_entry->key.proto,
+ vr_entry->key.vr_id,
+ nhgi->adj_index,
+ nhgi->ecmp_size,
+ old_adj_index, old_ecmp_size);
+ return err;
}
static int __mlxsw_sp_nexthop_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY,
true, MLXSW_REG_RATR_TYPE_ETHERNET,
- adj_index, neigh_entry->rif);
- mlxsw_reg_ratr_eth_entry_pack(ratr_pl, neigh_entry->ha);
+ adj_index, nh->rif->rif_index);
+ if (nh->discard)
+ mlxsw_reg_ratr_trap_action_set(ratr_pl,
+ MLXSW_REG_RATR_TRAP_ACTION_DISCARD_ERRORS);
+ else
+ 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
static int
mlxsw_sp_nexthop_group_update(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_nexthop_group *nh_grp,
+ struct mlxsw_sp_nexthop_group_info *nhgi,
bool reallocate)
{
- u32 adj_index = nh_grp->adj_index; /* base */
+ u32 adj_index = nhgi->adj_index; /* base */
struct mlxsw_sp_nexthop *nh;
int i;
- for (i = 0; i < nh_grp->count; i++) {
- nh = &nh_grp->nexthops[i];
+ for (i = 0; i < nhgi->count; i++) {
+ nh = &nhgi->nexthops[i];
if (!nh->should_offload) {
nh->offloaded = 0;
}
static void
-mlxsw_sp_nexthop_group_normalize(struct mlxsw_sp_nexthop_group *nh_grp)
+mlxsw_sp_nexthop_group_normalize(struct mlxsw_sp_nexthop_group_info *nhgi)
{
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];
+ for (i = 0; i < nhgi->count; i++) {
+ nh = &nhgi->nexthops[i];
if (!nh->should_offload)
continue;
g = nh->nh_weight;
}
- for (i = 0; i < nh_grp->count; i++) {
- nh = &nh_grp->nexthops[i];
+ for (i = 0; i < nhgi->count; i++) {
+ nh = &nhgi->nexthops[i];
if (!nh->should_offload)
continue;
sum_norm_weight += nh->norm_nh_weight;
}
- nh_grp->sum_norm_weight = sum_norm_weight;
+ nhgi->sum_norm_weight = sum_norm_weight;
}
static void
-mlxsw_sp_nexthop_group_rebalance(struct mlxsw_sp_nexthop_group *nh_grp)
+mlxsw_sp_nexthop_group_rebalance(struct mlxsw_sp_nexthop_group_info *nhgi)
{
- int total = nh_grp->sum_norm_weight;
- u16 ecmp_size = nh_grp->ecmp_size;
int i, weight = 0, lower_bound = 0;
+ int total = nhgi->sum_norm_weight;
+ u16 ecmp_size = nhgi->ecmp_size;
- for (i = 0; i < nh_grp->count; i++) {
- struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
+ for (i = 0; i < nhgi->count; i++) {
+ struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i];
int upper_bound;
if (!nh->should_offload)
{
int i;
- for (i = 0; i < nh_grp->count; i++) {
- struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
+ for (i = 0; i < nh_grp->nhgi->count; i++) {
+ struct mlxsw_sp_nexthop *nh = &nh_grp->nhgi->nexthops[i];
if (nh->offloaded)
nh->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
__mlxsw_sp_nexthop6_group_offload_refresh(nh_grp, fib6_entry);
}
+static void
+mlxsw_sp_nexthop_obj_group_offload_refresh(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ /* Do not update the flags if the nexthop group is being destroyed
+ * since:
+ * 1. The nexthop objects is being deleted, in which case the flags are
+ * irrelevant.
+ * 2. The nexthop group was replaced by a newer group, in which case
+ * the flags of the nexthop object were already updated based on the
+ * new group.
+ */
+ if (nh_grp->can_destroy)
+ return;
+
+ nexthop_set_hw_flags(mlxsw_sp_net(mlxsw_sp), nh_grp->obj.id,
+ nh_grp->nhgi->adj_index_valid, false);
+}
+
static void
mlxsw_sp_nexthop_group_offload_refresh(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp)
{
- switch (mlxsw_sp_nexthop_group_type(nh_grp)) {
- case AF_INET:
+ switch (nh_grp->type) {
+ case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4:
mlxsw_sp_nexthop4_group_offload_refresh(mlxsw_sp, nh_grp);
break;
- case AF_INET6:
+ case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6:
mlxsw_sp_nexthop6_group_offload_refresh(mlxsw_sp, nh_grp);
break;
+ case MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ:
+ mlxsw_sp_nexthop_obj_group_offload_refresh(mlxsw_sp, nh_grp);
+ break;
}
}
-static void
+static int
mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp)
{
+ struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi;
u16 ecmp_size, old_ecmp_size;
struct mlxsw_sp_nexthop *nh;
bool offload_change = false;
u32 adj_index;
bool old_adj_index_valid;
+ int i, err2, err = 0;
u32 old_adj_index;
- int i;
- int err;
- if (!nh_grp->gateway) {
- mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp);
- return;
- }
+ if (!nhgi->gateway)
+ return mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp);
- for (i = 0; i < nh_grp->count; i++) {
- nh = &nh_grp->nexthops[i];
+ for (i = 0; i < nhgi->count; i++) {
+ nh = &nhgi->nexthops[i];
if (nh->should_offload != nh->offloaded) {
offload_change = true;
/* Nothing was added or removed, so no need to reallocate. Just
* update MAC on existing adjacency indexes.
*/
- err = mlxsw_sp_nexthop_group_update(mlxsw_sp, nh_grp, false);
+ err = mlxsw_sp_nexthop_group_update(mlxsw_sp, nhgi, false);
if (err) {
dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
goto set_trap;
}
- return;
+ return 0;
}
- mlxsw_sp_nexthop_group_normalize(nh_grp);
- if (!nh_grp->sum_norm_weight)
+ mlxsw_sp_nexthop_group_normalize(nhgi);
+ if (!nhgi->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;
+ ecmp_size = nhgi->sum_norm_weight;
err = mlxsw_sp_fix_adj_grp_size(mlxsw_sp, &ecmp_size);
if (err)
/* No valid allocation size available. */
dev_warn(mlxsw_sp->bus_info->dev, "Failed to allocate KVD linear area for nexthop group.\n");
goto set_trap;
}
- old_adj_index_valid = nh_grp->adj_index_valid;
- old_adj_index = nh_grp->adj_index;
- old_ecmp_size = nh_grp->ecmp_size;
- 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);
+ old_adj_index_valid = nhgi->adj_index_valid;
+ old_adj_index = nhgi->adj_index;
+ old_ecmp_size = nhgi->ecmp_size;
+ nhgi->adj_index_valid = 1;
+ nhgi->adj_index = adj_index;
+ nhgi->ecmp_size = ecmp_size;
+ mlxsw_sp_nexthop_group_rebalance(nhgi);
+ err = mlxsw_sp_nexthop_group_update(mlxsw_sp, nhgi, true);
if (err) {
dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
goto set_trap;
dev_warn(mlxsw_sp->bus_info->dev, "Failed to add adjacency index to fib entries.\n");
goto set_trap;
}
- return;
+ return 0;
}
err = mlxsw_sp_adj_index_mass_update(mlxsw_sp, nh_grp,
goto set_trap;
}
- return;
+ return 0;
set_trap:
- old_adj_index_valid = nh_grp->adj_index_valid;
- nh_grp->adj_index_valid = 0;
- for (i = 0; i < nh_grp->count; i++) {
- nh = &nh_grp->nexthops[i];
+ old_adj_index_valid = nhgi->adj_index_valid;
+ nhgi->adj_index_valid = 0;
+ for (i = 0; i < nhgi->count; i++) {
+ nh = &nhgi->nexthops[i];
nh->offloaded = 0;
}
- err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp);
- if (err)
+ err2 = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp);
+ if (err2)
dev_warn(mlxsw_sp->bus_info->dev, "Failed to set traps for fib entries.\n");
mlxsw_sp_nexthop_group_offload_refresh(mlxsw_sp, nh_grp);
if (old_adj_index_valid)
mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
- nh_grp->ecmp_size, nh_grp->adj_index);
+ nhgi->ecmp_size, nhgi->adj_index);
+ return err;
}
static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh,
nh = list_first_entry(&neigh_entry->nexthop_list,
struct mlxsw_sp_nexthop, neigh_list_node);
- n = neigh_lookup(nh->nh_grp->neigh_tbl, &nh->gw_addr, nh->rif->dev);
+ n = neigh_lookup(nh->neigh_tbl, &nh->gw_addr, nh->rif->dev);
if (!n) {
- n = neigh_create(nh->nh_grp->neigh_tbl, &nh->gw_addr,
- nh->rif->dev);
+ n = neigh_create(nh->neigh_tbl, &nh->gw_addr, nh->rif->dev);
if (IS_ERR(n))
return PTR_ERR(n);
neigh_event_send(n, NULL);
neigh_release(old_n);
neigh_clone(n);
__mlxsw_sp_nexthop_neigh_update(nh, !entry_connected);
- mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
+ mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp);
}
neigh_release(n);
list_for_each_entry(nh, &neigh_entry->nexthop_list,
neigh_list_node) {
__mlxsw_sp_nexthop_neigh_update(nh, removing);
- mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
+ mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp);
}
}
u8 nud_state, dead;
int err;
- if (!nh->nh_grp->gateway || nh->neigh_entry)
+ if (!nh->nhgi->gateway || nh->neigh_entry)
return 0;
/* Take a reference of neigh here ensuring that neigh would
* The reference is taken either in neigh_lookup() or
* in neigh_create() in case n is not found.
*/
- n = neigh_lookup(nh->nh_grp->neigh_tbl, &nh->gw_addr, nh->rif->dev);
+ n = neigh_lookup(nh->neigh_tbl, &nh->gw_addr, nh->rif->dev);
if (!n) {
- n = neigh_create(nh->nh_grp->neigh_tbl, &nh->gw_addr,
- nh->rif->dev);
+ n = neigh_create(nh->neigh_tbl, &nh->gw_addr, nh->rif->dev);
if (IS_ERR(n))
return PTR_ERR(n);
neigh_event_send(n, NULL);
{
bool removing;
- if (!nh->nh_grp->gateway || nh->ipip_entry)
+ if (!nh->nhgi->gateway || nh->ipip_entry)
return;
nh->ipip_entry = ipip_entry;
mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, p_ipipt);
}
-static void mlxsw_sp_nexthop_type_fini(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_nexthop *nh)
-{
- switch (nh->type) {
- case MLXSW_SP_NEXTHOP_TYPE_ETH:
- mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
- mlxsw_sp_nexthop_rif_fini(nh);
- break;
- case MLXSW_SP_NEXTHOP_TYPE_IPIP:
- mlxsw_sp_nexthop_rif_fini(nh);
- mlxsw_sp_nexthop_ipip_fini(mlxsw_sp, nh);
- break;
- }
-}
-
-static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_nexthop *nh,
- struct fib_nh *fib_nh)
+static int mlxsw_sp_nexthop_type_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh,
+ const struct net_device *dev)
{
const struct mlxsw_sp_ipip_ops *ipip_ops;
- struct net_device *dev = fib_nh->fib_nh_dev;
struct mlxsw_sp_ipip_entry *ipip_entry;
struct mlxsw_sp_rif *rif;
int err;
ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, dev);
if (ipip_entry) {
ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt];
- if (ipip_ops->can_offload(mlxsw_sp, dev,
- MLXSW_SP_L3_PROTO_IPV4)) {
+ if (ipip_ops->can_offload(mlxsw_sp, dev)) {
nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP;
mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, ipip_entry);
return 0;
return err;
}
-static void mlxsw_sp_nexthop4_type_fini(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_nexthop *nh)
+static void mlxsw_sp_nexthop_type_fini(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh)
{
- mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh);
+ switch (nh->type) {
+ case MLXSW_SP_NEXTHOP_TYPE_ETH:
+ mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
+ mlxsw_sp_nexthop_rif_fini(nh);
+ break;
+ case MLXSW_SP_NEXTHOP_TYPE_IPIP:
+ mlxsw_sp_nexthop_rif_fini(nh);
+ mlxsw_sp_nexthop_ipip_fini(mlxsw_sp, nh);
+ break;
+ }
}
static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
struct in_device *in_dev;
int err;
- nh->nh_grp = nh_grp;
+ nh->nhgi = nh_grp->nhgi;
nh->key.fib_nh = fib_nh;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
nh->nh_weight = fib_nh->fib_nh_weight;
nh->nh_weight = 1;
#endif
memcpy(&nh->gw_addr, &fib_nh->fib_nh_gw4, sizeof(fib_nh->fib_nh_gw4));
+ nh->neigh_tbl = &arp_tbl;
err = mlxsw_sp_nexthop_insert(mlxsw_sp, nh);
if (err)
return err;
if (!dev)
return 0;
+ nh->ifindex = dev->ifindex;
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
}
rcu_read_unlock();
- err = mlxsw_sp_nexthop4_type_init(mlxsw_sp, nh, fib_nh);
+ err = mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, dev);
if (err)
goto err_nexthop_neigh_init;
static void mlxsw_sp_nexthop4_fini(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop *nh)
{
- mlxsw_sp_nexthop4_type_fini(mlxsw_sp, nh);
+ mlxsw_sp_nexthop_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);
switch (event) {
case FIB_EVENT_NH_ADD:
- mlxsw_sp_nexthop4_type_init(mlxsw_sp, nh, fib_nh);
+ mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, fib_nh->fib_nh_dev);
break;
case FIB_EVENT_NH_DEL:
- mlxsw_sp_nexthop4_type_fini(mlxsw_sp, nh);
+ mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh);
break;
}
- mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
+ mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp);
}
static void mlxsw_sp_nexthop_rif_update(struct mlxsw_sp *mlxsw_sp,
}
__mlxsw_sp_nexthop_neigh_update(nh, removing);
- mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
+ mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp);
}
}
list_for_each_entry_safe(nh, tmp, &rif->nexthop_list, rif_list_node) {
mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh);
- mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
+ mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp);
}
}
-static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp,
- struct fib_info *fi)
+static int
+mlxsw_sp_nexthop_obj_single_validate(struct mlxsw_sp *mlxsw_sp,
+ const struct nh_notifier_single_info *nh,
+ struct netlink_ext_ack *extack)
{
- const struct fib_nh *nh = fib_info_nh(fi, 0);
+ int err = -EINVAL;
- return nh->fib_nh_scope == RT_SCOPE_LINK ||
- mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, nh, NULL);
+ if (nh->is_fdb)
+ NL_SET_ERR_MSG_MOD(extack, "FDB nexthops are not supported");
+ else if (nh->has_encap)
+ NL_SET_ERR_MSG_MOD(extack, "Encapsulating nexthops are not supported");
+ else
+ err = 0;
+
+ return err;
}
-static struct mlxsw_sp_nexthop_group *
-mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi)
+static int
+mlxsw_sp_nexthop_obj_group_validate(struct mlxsw_sp *mlxsw_sp,
+ const struct nh_notifier_grp_info *nh_grp,
+ struct netlink_ext_ack *extack)
{
- unsigned int nhs = fib_info_num_path(fi);
- struct mlxsw_sp_nexthop_group *nh_grp;
- struct mlxsw_sp_nexthop *nh;
- struct fib_nh *fib_nh;
int i;
- int err;
- nh_grp = kzalloc(struct_size(nh_grp, nexthops, nhs), GFP_KERNEL);
- if (!nh_grp)
- return ERR_PTR(-ENOMEM);
- nh_grp->priv = fi;
- INIT_LIST_HEAD(&nh_grp->fib_list);
- nh_grp->neigh_tbl = &arp_tbl;
+ if (nh_grp->is_fdb) {
+ NL_SET_ERR_MSG_MOD(extack, "FDB nexthop groups are not supported");
+ return -EINVAL;
+ }
- nh_grp->gateway = mlxsw_sp_fi_is_gateway(mlxsw_sp, fi);
- nh_grp->count = nhs;
- fib_info_hold(fi);
- for (i = 0; i < nh_grp->count; i++) {
- nh = &nh_grp->nexthops[i];
- fib_nh = fib_info_nh(fi, i);
- err = mlxsw_sp_nexthop4_init(mlxsw_sp, nh_grp, nh, fib_nh);
+ for (i = 0; i < nh_grp->num_nh; i++) {
+ const struct nh_notifier_single_info *nh;
+ int err;
+
+ nh = &nh_grp->nh_entries[i].nh;
+ err = mlxsw_sp_nexthop_obj_single_validate(mlxsw_sp, nh,
+ extack);
if (err)
- goto err_nexthop4_init;
- }
- err = mlxsw_sp_nexthop_group_insert(mlxsw_sp, nh_grp);
- if (err)
- goto err_nexthop_group_insert;
- mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
- return nh_grp;
+ return err;
-err_nexthop_group_insert:
-err_nexthop4_init:
- for (i--; i >= 0; i--) {
- nh = &nh_grp->nexthops[i];
- mlxsw_sp_nexthop4_fini(mlxsw_sp, nh);
+ /* Device only nexthops with an IPIP device are programmed as
+ * encapsulating adjacency entries.
+ */
+ if (!nh->gw_family && !nh->is_reject &&
+ !mlxsw_sp_netdev_ipip_type(mlxsw_sp, nh->dev, NULL)) {
+ NL_SET_ERR_MSG_MOD(extack, "Nexthop group entry does not have a gateway");
+ return -EINVAL;
+ }
}
- fib_info_put(fi);
- kfree(nh_grp);
- return ERR_PTR(err);
+
+ return 0;
}
-static void
-mlxsw_sp_nexthop4_group_destroy(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_nexthop_group *nh_grp)
+static int mlxsw_sp_nexthop_obj_validate(struct mlxsw_sp *mlxsw_sp,
+ unsigned long event,
+ struct nh_notifier_info *info)
{
- struct mlxsw_sp_nexthop *nh;
- int i;
+ if (event != NEXTHOP_EVENT_REPLACE)
+ return 0;
- mlxsw_sp_nexthop_group_remove(mlxsw_sp, nh_grp);
- for (i = 0; i < nh_grp->count; i++) {
- nh = &nh_grp->nexthops[i];
- mlxsw_sp_nexthop4_fini(mlxsw_sp, nh);
- }
+ if (!info->is_grp)
+ return mlxsw_sp_nexthop_obj_single_validate(mlxsw_sp, info->nh,
+ info->extack);
+ return mlxsw_sp_nexthop_obj_group_validate(mlxsw_sp, info->nh_grp,
+ info->extack);
+}
+
+static bool mlxsw_sp_nexthop_obj_is_gateway(struct mlxsw_sp *mlxsw_sp,
+ const struct nh_notifier_info *info)
+{
+ const struct net_device *dev;
+
+ if (info->is_grp)
+ /* Already validated earlier. */
+ return true;
+
+ dev = info->nh->dev;
+ return info->nh->gw_family || info->nh->is_reject ||
+ mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, NULL);
+}
+
+static void mlxsw_sp_nexthop_obj_blackhole_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh)
+{
+ u16 lb_rif_index = mlxsw_sp->router->lb_rif_index;
+
+ nh->discard = 1;
+ nh->should_offload = 1;
+ /* While nexthops that discard packets do not forward packets
+ * via an egress RIF, they still need to be programmed using a
+ * valid RIF, so use the loopback RIF created during init.
+ */
+ nh->rif = mlxsw_sp->router->rifs[lb_rif_index];
+}
+
+static void mlxsw_sp_nexthop_obj_blackhole_fini(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh)
+{
+ nh->rif = NULL;
+ nh->should_offload = 0;
+}
+
+static int
+mlxsw_sp_nexthop_obj_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp,
+ struct mlxsw_sp_nexthop *nh,
+ struct nh_notifier_single_info *nh_obj, int weight)
+{
+ struct net_device *dev = nh_obj->dev;
+ int err;
+
+ nh->nhgi = nh_grp->nhgi;
+ nh->nh_weight = weight;
+
+ switch (nh_obj->gw_family) {
+ case AF_INET:
+ memcpy(&nh->gw_addr, &nh_obj->ipv4, sizeof(nh_obj->ipv4));
+ nh->neigh_tbl = &arp_tbl;
+ break;
+ case AF_INET6:
+ memcpy(&nh->gw_addr, &nh_obj->ipv6, sizeof(nh_obj->ipv6));
+#if IS_ENABLED(CONFIG_IPV6)
+ nh->neigh_tbl = &nd_tbl;
+#endif
+ break;
+ }
+
+ mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
+ list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list);
+ nh->ifindex = dev->ifindex;
+
+ err = mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, dev);
+ if (err)
+ goto err_type_init;
+
+ if (nh_obj->is_reject)
+ mlxsw_sp_nexthop_obj_blackhole_init(mlxsw_sp, nh);
+
+ return 0;
+
+err_type_init:
+ list_del(&nh->router_list_node);
+ mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
+ return err;
+}
+
+static void mlxsw_sp_nexthop_obj_fini(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh)
+{
+ if (nh->discard)
+ mlxsw_sp_nexthop_obj_blackhole_fini(mlxsw_sp, nh);
+ mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh);
+ list_del(&nh->router_list_node);
+ mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
+}
+
+static int
+mlxsw_sp_nexthop_obj_group_info_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp,
+ struct nh_notifier_info *info)
+{
+ unsigned int nhs = info->is_grp ? info->nh_grp->num_nh : 1;
+ struct mlxsw_sp_nexthop_group_info *nhgi;
+ struct mlxsw_sp_nexthop *nh;
+ int err, i;
+
+ nhgi = kzalloc(struct_size(nhgi, nexthops, nhs), GFP_KERNEL);
+ if (!nhgi)
+ return -ENOMEM;
+ nh_grp->nhgi = nhgi;
+ nhgi->nh_grp = nh_grp;
+ nhgi->gateway = mlxsw_sp_nexthop_obj_is_gateway(mlxsw_sp, info);
+ nhgi->count = nhs;
+ for (i = 0; i < nhgi->count; i++) {
+ struct nh_notifier_single_info *nh_obj;
+ int weight;
+
+ nh = &nhgi->nexthops[i];
+ if (info->is_grp) {
+ nh_obj = &info->nh_grp->nh_entries[i].nh;
+ weight = info->nh_grp->nh_entries[i].weight;
+ } else {
+ nh_obj = info->nh;
+ weight = 1;
+ }
+ err = mlxsw_sp_nexthop_obj_init(mlxsw_sp, nh_grp, nh, nh_obj,
+ weight);
+ if (err)
+ goto err_nexthop_obj_init;
+ }
+ err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(info->extack, "Failed to write adjacency entries to the device");
+ goto err_group_refresh;
+ }
+
+ return 0;
+
+err_group_refresh:
+ i = nhgi->count;
+err_nexthop_obj_init:
+ for (i--; i >= 0; i--) {
+ nh = &nhgi->nexthops[i];
+ mlxsw_sp_nexthop_obj_fini(mlxsw_sp, nh);
+ }
+ kfree(nhgi);
+ return err;
+}
+
+static void
+mlxsw_sp_nexthop_obj_group_info_fini(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi;
+ int i;
+
+ for (i = nhgi->count - 1; i >= 0; i--) {
+ struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i];
+
+ mlxsw_sp_nexthop_obj_fini(mlxsw_sp, nh);
+ }
+ mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
+ WARN_ON_ONCE(nhgi->adj_index_valid);
+ kfree(nhgi);
+}
+
+static struct mlxsw_sp_nexthop_group *
+mlxsw_sp_nexthop_obj_group_create(struct mlxsw_sp *mlxsw_sp,
+ struct nh_notifier_info *info)
+{
+ struct mlxsw_sp_nexthop_group *nh_grp;
+ int err;
+
+ nh_grp = kzalloc(sizeof(*nh_grp), GFP_KERNEL);
+ if (!nh_grp)
+ return ERR_PTR(-ENOMEM);
+ INIT_LIST_HEAD(&nh_grp->vr_list);
+ err = rhashtable_init(&nh_grp->vr_ht,
+ &mlxsw_sp_nexthop_group_vr_ht_params);
+ if (err)
+ goto err_nexthop_group_vr_ht_init;
+ INIT_LIST_HEAD(&nh_grp->fib_list);
+ nh_grp->type = MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ;
+ nh_grp->obj.id = info->id;
+
+ err = mlxsw_sp_nexthop_obj_group_info_init(mlxsw_sp, nh_grp, info);
+ if (err)
+ goto err_nexthop_group_info_init;
+
+ nh_grp->can_destroy = false;
+
+ return nh_grp;
+
+err_nexthop_group_info_init:
+ rhashtable_destroy(&nh_grp->vr_ht);
+err_nexthop_group_vr_ht_init:
+ kfree(nh_grp);
+ return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_nexthop_obj_group_destroy(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ if (!nh_grp->can_destroy)
+ return;
+ mlxsw_sp_nexthop_obj_group_info_fini(mlxsw_sp, nh_grp);
+ WARN_ON_ONCE(!list_empty(&nh_grp->fib_list));
+ WARN_ON_ONCE(!list_empty(&nh_grp->vr_list));
+ rhashtable_destroy(&nh_grp->vr_ht);
+ kfree(nh_grp);
+}
+
+static struct mlxsw_sp_nexthop_group *
+mlxsw_sp_nexthop_obj_group_lookup(struct mlxsw_sp *mlxsw_sp, u32 id)
+{
+ struct mlxsw_sp_nexthop_group_cmp_arg cmp_arg;
+
+ cmp_arg.type = MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ;
+ cmp_arg.id = id;
+ return rhashtable_lookup_fast(&mlxsw_sp->router->nexthop_group_ht,
+ &cmp_arg,
+ mlxsw_sp_nexthop_group_ht_params);
+}
+
+static int mlxsw_sp_nexthop_obj_group_add(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ return mlxsw_sp_nexthop_group_insert(mlxsw_sp, nh_grp);
+}
+
+static int
+mlxsw_sp_nexthop_obj_group_replace(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp,
+ struct mlxsw_sp_nexthop_group *old_nh_grp,
+ struct netlink_ext_ack *extack)
+{
+ struct mlxsw_sp_nexthop_group_info *old_nhgi = old_nh_grp->nhgi;
+ struct mlxsw_sp_nexthop_group_info *new_nhgi = nh_grp->nhgi;
+ int err;
+
+ old_nh_grp->nhgi = new_nhgi;
+ new_nhgi->nh_grp = old_nh_grp;
+ nh_grp->nhgi = old_nhgi;
+ old_nhgi->nh_grp = nh_grp;
+
+ if (old_nhgi->adj_index_valid && new_nhgi->adj_index_valid) {
+ /* Both the old adjacency index and the new one are valid.
+ * Routes are currently using the old one. Tell the device to
+ * replace the old adjacency index with the new one.
+ */
+ err = mlxsw_sp_adj_index_mass_update(mlxsw_sp, old_nh_grp,
+ old_nhgi->adj_index,
+ old_nhgi->ecmp_size);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to replace old adjacency index with new one");
+ goto err_out;
+ }
+ } else if (old_nhgi->adj_index_valid && !new_nhgi->adj_index_valid) {
+ /* The old adjacency index is valid, while the new one is not.
+ * Iterate over all the routes using the group and change them
+ * to trap packets to the CPU.
+ */
+ err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, old_nh_grp);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to update routes to trap packets");
+ goto err_out;
+ }
+ } else if (!old_nhgi->adj_index_valid && new_nhgi->adj_index_valid) {
+ /* The old adjacency index is invalid, while the new one is.
+ * Iterate over all the routes using the group and change them
+ * to forward packets using the new valid index.
+ */
+ err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, old_nh_grp);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to update routes to forward packets");
+ goto err_out;
+ }
+ }
+
+ /* Make sure the flags are set / cleared based on the new nexthop group
+ * information.
+ */
+ mlxsw_sp_nexthop_obj_group_offload_refresh(mlxsw_sp, old_nh_grp);
+
+ /* At this point 'nh_grp' is just a shell that is not used by anyone
+ * and its nexthop group info is the old info that was just replaced
+ * with the new one. Remove it.
+ */
+ nh_grp->can_destroy = true;
+ mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp);
+
+ return 0;
+
+err_out:
+ old_nhgi->nh_grp = old_nh_grp;
+ nh_grp->nhgi = new_nhgi;
+ new_nhgi->nh_grp = nh_grp;
+ old_nh_grp->nhgi = old_nhgi;
+ return err;
+}
+
+static int mlxsw_sp_nexthop_obj_new(struct mlxsw_sp *mlxsw_sp,
+ struct nh_notifier_info *info)
+{
+ struct mlxsw_sp_nexthop_group *nh_grp, *old_nh_grp;
+ struct netlink_ext_ack *extack = info->extack;
+ int err;
+
+ nh_grp = mlxsw_sp_nexthop_obj_group_create(mlxsw_sp, info);
+ if (IS_ERR(nh_grp))
+ return PTR_ERR(nh_grp);
+
+ old_nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, info->id);
+ if (!old_nh_grp)
+ err = mlxsw_sp_nexthop_obj_group_add(mlxsw_sp, nh_grp);
+ else
+ err = mlxsw_sp_nexthop_obj_group_replace(mlxsw_sp, nh_grp,
+ old_nh_grp, extack);
+
+ if (err) {
+ nh_grp->can_destroy = true;
+ mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp);
+ }
+
+ return err;
+}
+
+static void mlxsw_sp_nexthop_obj_del(struct mlxsw_sp *mlxsw_sp,
+ struct nh_notifier_info *info)
+{
+ struct mlxsw_sp_nexthop_group *nh_grp;
+
+ nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, info->id);
+ if (!nh_grp)
+ return;
+
+ nh_grp->can_destroy = true;
+ mlxsw_sp_nexthop_group_remove(mlxsw_sp, nh_grp);
+
+ /* If the group still has routes using it, then defer the delete
+ * operation until the last route using it is deleted.
+ */
+ if (!list_empty(&nh_grp->fib_list))
+ return;
+ mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp);
+}
+
+static int mlxsw_sp_nexthop_obj_event(struct notifier_block *nb,
+ unsigned long event, void *ptr)
+{
+ struct nh_notifier_info *info = ptr;
+ struct mlxsw_sp_router *router;
+ int err = 0;
+
+ router = container_of(nb, struct mlxsw_sp_router, nexthop_nb);
+ err = mlxsw_sp_nexthop_obj_validate(router->mlxsw_sp, event, info);
+ if (err)
+ goto out;
+
+ mutex_lock(&router->lock);
+
+ ASSERT_RTNL();
+
+ switch (event) {
+ case NEXTHOP_EVENT_REPLACE:
+ err = mlxsw_sp_nexthop_obj_new(router->mlxsw_sp, info);
+ break;
+ case NEXTHOP_EVENT_DEL:
+ mlxsw_sp_nexthop_obj_del(router->mlxsw_sp, info);
+ break;
+ default:
+ break;
+ }
+
+ mutex_unlock(&router->lock);
+
+out:
+ return notifier_from_errno(err);
+}
+
+static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp,
+ struct fib_info *fi)
+{
+ const struct fib_nh *nh = fib_info_nh(fi, 0);
+
+ return nh->fib_nh_scope == RT_SCOPE_LINK ||
+ mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, nh, NULL);
+}
+
+static int
+mlxsw_sp_nexthop4_group_info_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ unsigned int nhs = fib_info_num_path(nh_grp->ipv4.fi);
+ struct mlxsw_sp_nexthop_group_info *nhgi;
+ struct mlxsw_sp_nexthop *nh;
+ int err, i;
+
+ nhgi = kzalloc(struct_size(nhgi, nexthops, nhs), GFP_KERNEL);
+ if (!nhgi)
+ return -ENOMEM;
+ nh_grp->nhgi = nhgi;
+ nhgi->nh_grp = nh_grp;
+ nhgi->gateway = mlxsw_sp_fi_is_gateway(mlxsw_sp, nh_grp->ipv4.fi);
+ nhgi->count = nhs;
+ for (i = 0; i < nhgi->count; i++) {
+ struct fib_nh *fib_nh;
+
+ nh = &nhgi->nexthops[i];
+ fib_nh = fib_info_nh(nh_grp->ipv4.fi, i);
+ err = mlxsw_sp_nexthop4_init(mlxsw_sp, nh_grp, nh, fib_nh);
+ if (err)
+ goto err_nexthop4_init;
+ }
+ err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
+ if (err)
+ goto err_group_refresh;
+
+ return 0;
+
+err_group_refresh:
+ i = nhgi->count;
+err_nexthop4_init:
+ for (i--; i >= 0; i--) {
+ nh = &nhgi->nexthops[i];
+ mlxsw_sp_nexthop4_fini(mlxsw_sp, nh);
+ }
+ kfree(nhgi);
+ return err;
+}
+
+static void
+mlxsw_sp_nexthop4_group_info_fini(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi;
+ int i;
+
+ for (i = nhgi->count - 1; i >= 0; i--) {
+ struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i];
+
+ mlxsw_sp_nexthop4_fini(mlxsw_sp, nh);
+ }
mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
- WARN_ON_ONCE(nh_grp->adj_index_valid);
- fib_info_put(mlxsw_sp_nexthop4_group_fi(nh_grp));
+ WARN_ON_ONCE(nhgi->adj_index_valid);
+ kfree(nhgi);
+}
+
+static struct mlxsw_sp_nexthop_group *
+mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi)
+{
+ struct mlxsw_sp_nexthop_group *nh_grp;
+ int err;
+
+ nh_grp = kzalloc(sizeof(*nh_grp), GFP_KERNEL);
+ if (!nh_grp)
+ return ERR_PTR(-ENOMEM);
+ INIT_LIST_HEAD(&nh_grp->vr_list);
+ err = rhashtable_init(&nh_grp->vr_ht,
+ &mlxsw_sp_nexthop_group_vr_ht_params);
+ if (err)
+ goto err_nexthop_group_vr_ht_init;
+ INIT_LIST_HEAD(&nh_grp->fib_list);
+ nh_grp->type = MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4;
+ nh_grp->ipv4.fi = fi;
+ fib_info_hold(fi);
+
+ err = mlxsw_sp_nexthop4_group_info_init(mlxsw_sp, nh_grp);
+ if (err)
+ goto err_nexthop_group_info_init;
+
+ err = mlxsw_sp_nexthop_group_insert(mlxsw_sp, nh_grp);
+ if (err)
+ goto err_nexthop_group_insert;
+
+ nh_grp->can_destroy = true;
+
+ return nh_grp;
+
+err_nexthop_group_insert:
+ mlxsw_sp_nexthop4_group_info_fini(mlxsw_sp, nh_grp);
+err_nexthop_group_info_init:
+ fib_info_put(fi);
+ rhashtable_destroy(&nh_grp->vr_ht);
+err_nexthop_group_vr_ht_init:
+ kfree(nh_grp);
+ return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_nexthop4_group_destroy(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ if (!nh_grp->can_destroy)
+ return;
+ mlxsw_sp_nexthop_group_remove(mlxsw_sp, nh_grp);
+ mlxsw_sp_nexthop4_group_info_fini(mlxsw_sp, nh_grp);
+ fib_info_put(nh_grp->ipv4.fi);
+ WARN_ON_ONCE(!list_empty(&nh_grp->vr_list));
+ rhashtable_destroy(&nh_grp->vr_ht);
kfree(nh_grp);
}
{
struct mlxsw_sp_nexthop_group *nh_grp;
+ if (fi->nh) {
+ nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp,
+ fi->nh->id);
+ if (WARN_ON_ONCE(!nh_grp))
+ return -EINVAL;
+ goto out;
+ }
+
nh_grp = mlxsw_sp_nexthop4_group_lookup(mlxsw_sp, fi);
if (!nh_grp) {
nh_grp = mlxsw_sp_nexthop4_group_create(mlxsw_sp, fi);
if (IS_ERR(nh_grp))
return PTR_ERR(nh_grp);
}
+out:
list_add_tail(&fib_entry->nexthop_group_node, &nh_grp->fib_list);
fib_entry->nh_group = nh_grp;
return 0;
list_del(&fib_entry->nexthop_group_node);
if (!list_empty(&nh_grp->fib_list))
return;
+
+ if (nh_grp->type == MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ) {
+ mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp);
+ return;
+ }
+
mlxsw_sp_nexthop4_group_destroy(mlxsw_sp, nh_grp);
}
switch (fib_entry->type) {
case MLXSW_SP_FIB_ENTRY_TYPE_REMOTE:
- return !!nh_group->adj_index_valid;
+ return !!nh_group->nhgi->adj_index_valid;
case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL:
- return !!nh_group->nh_rif;
+ return !!nh_group->nhgi->nh_rif;
case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE:
case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP:
case MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP:
{
int i;
- for (i = 0; i < nh_grp->count; i++) {
- struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
+ for (i = 0; i < nh_grp->nhgi->count; i++) {
+ struct mlxsw_sp_nexthop *nh = &nh_grp->nhgi->nexthops[i];
struct fib6_info *rt = mlxsw_sp_rt6->rt;
if (nh->rif && nh->rif->dev == rt->fib6_nh->fib_nh_dev &&
mlxsw_sp_fib4_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_entry *fib_entry)
{
- struct fib_info *fi = mlxsw_sp_nexthop4_group_fi(fib_entry->nh_group);
u32 *p_dst = (u32 *) fib_entry->fib_node->key.addr;
int dst_len = fib_entry->fib_node->key.prefix_len;
struct mlxsw_sp_fib4_entry *fib4_entry;
should_offload = mlxsw_sp_fib_entry_should_offload(fib_entry);
fib4_entry = container_of(fib_entry, struct mlxsw_sp_fib4_entry,
common);
- fri.fi = fi;
+ fri.fi = fib4_entry->fi;
fri.tb_id = fib4_entry->tb_id;
fri.dst = cpu_to_be32(*p_dst);
fri.dst_len = dst_len;
mlxsw_sp_fib4_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_entry *fib_entry)
{
- struct fib_info *fi = mlxsw_sp_nexthop4_group_fi(fib_entry->nh_group);
u32 *p_dst = (u32 *) fib_entry->fib_node->key.addr;
int dst_len = fib_entry->fib_node->key.prefix_len;
struct mlxsw_sp_fib4_entry *fib4_entry;
fib4_entry = container_of(fib_entry, struct mlxsw_sp_fib4_entry,
common);
- fri.fi = fi;
+ fri.fi = fib4_entry->fi;
fri.tb_id = fib4_entry->tb_id;
fri.dst = cpu_to_be32(*p_dst);
fri.dst_len = dst_len;
static void
mlxsw_sp_fib_entry_hw_flags_refresh(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op)
+ enum mlxsw_sp_fib_entry_op op)
{
switch (op) {
- case MLXSW_REG_RALUE_OP_WRITE_WRITE:
+ case MLXSW_SP_FIB_ENTRY_OP_WRITE:
+ case MLXSW_SP_FIB_ENTRY_OP_UPDATE:
mlxsw_sp_fib_entry_hw_flags_set(mlxsw_sp, fib_entry);
break;
- case MLXSW_REG_RALUE_OP_WRITE_DELETE:
+ case MLXSW_SP_FIB_ENTRY_OP_DELETE:
mlxsw_sp_fib_entry_hw_flags_clear(mlxsw_sp, fib_entry);
break;
default:
}
}
+struct mlxsw_sp_fib_entry_op_ctx_basic {
+ char ralue_pl[MLXSW_REG_RALUE_LEN];
+};
+
static void
-mlxsw_sp_fib_entry_ralue_pack(char *ralue_pl,
- const struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op)
+mlxsw_sp_router_ll_basic_fib_entry_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ enum mlxsw_sp_l3proto proto,
+ enum mlxsw_sp_fib_entry_op op,
+ u16 virtual_router, u8 prefix_len,
+ unsigned char *addr,
+ struct mlxsw_sp_fib_entry_priv *priv)
{
- struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib;
- enum mlxsw_reg_ralxx_protocol proto;
- u32 *p_dip;
+ struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv;
+ enum mlxsw_reg_ralxx_protocol ralxx_proto;
+ char *ralue_pl = op_ctx_basic->ralue_pl;
+ enum mlxsw_reg_ralue_op ralue_op;
- proto = (enum mlxsw_reg_ralxx_protocol) fib->proto;
+ ralxx_proto = (enum mlxsw_reg_ralxx_protocol) proto;
- switch (fib->proto) {
+ switch (op) {
+ case MLXSW_SP_FIB_ENTRY_OP_WRITE:
+ case MLXSW_SP_FIB_ENTRY_OP_UPDATE:
+ ralue_op = MLXSW_REG_RALUE_OP_WRITE_WRITE;
+ break;
+ case MLXSW_SP_FIB_ENTRY_OP_DELETE:
+ ralue_op = MLXSW_REG_RALUE_OP_WRITE_DELETE;
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ return;
+ }
+
+ switch (proto) {
case MLXSW_SP_L3_PROTO_IPV4:
- p_dip = (u32 *) fib_entry->fib_node->key.addr;
- mlxsw_reg_ralue_pack4(ralue_pl, proto, op, fib->vr->id,
- fib_entry->fib_node->key.prefix_len,
- *p_dip);
+ mlxsw_reg_ralue_pack4(ralue_pl, ralxx_proto, ralue_op,
+ virtual_router, prefix_len, (u32 *) addr);
break;
case MLXSW_SP_L3_PROTO_IPV6:
- mlxsw_reg_ralue_pack6(ralue_pl, proto, op, fib->vr->id,
- fib_entry->fib_node->key.prefix_len,
- fib_entry->fib_node->key.addr);
+ mlxsw_reg_ralue_pack6(ralue_pl, ralxx_proto, ralue_op,
+ virtual_router, prefix_len, addr);
break;
}
}
-static int mlxsw_sp_adj_discard_write(struct mlxsw_sp *mlxsw_sp, u16 rif_index)
+static void
+mlxsw_sp_router_ll_basic_fib_entry_act_remote_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ enum mlxsw_reg_ralue_trap_action trap_action,
+ u16 trap_id, u32 adjacency_index, u16 ecmp_size)
+{
+ struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv;
+
+ mlxsw_reg_ralue_act_remote_pack(op_ctx_basic->ralue_pl, trap_action,
+ trap_id, adjacency_index, ecmp_size);
+}
+
+static void
+mlxsw_sp_router_ll_basic_fib_entry_act_local_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ enum mlxsw_reg_ralue_trap_action trap_action,
+ u16 trap_id, u16 local_erif)
+{
+ struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv;
+
+ mlxsw_reg_ralue_act_local_pack(op_ctx_basic->ralue_pl, trap_action,
+ trap_id, local_erif);
+}
+
+static void
+mlxsw_sp_router_ll_basic_fib_entry_act_ip2me_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx)
+{
+ struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv;
+
+ mlxsw_reg_ralue_act_ip2me_pack(op_ctx_basic->ralue_pl);
+}
+
+static void
+mlxsw_sp_router_ll_basic_fib_entry_act_ip2me_tun_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ u32 tunnel_ptr)
+{
+ struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv;
+
+ mlxsw_reg_ralue_act_ip2me_tun_pack(op_ctx_basic->ralue_pl, tunnel_ptr);
+}
+
+static int
+mlxsw_sp_router_ll_basic_fib_entry_commit(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ bool *postponed_for_bulk)
+{
+ struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv;
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue),
+ op_ctx_basic->ralue_pl);
+}
+
+static bool
+mlxsw_sp_router_ll_basic_fib_entry_is_committed(struct mlxsw_sp_fib_entry_priv *priv)
+{
+ return true;
+}
+
+static void mlxsw_sp_fib_entry_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ struct mlxsw_sp_fib_entry *fib_entry,
+ enum mlxsw_sp_fib_entry_op op)
+{
+ struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib;
+
+ mlxsw_sp_fib_entry_op_ctx_priv_hold(op_ctx, fib_entry->priv);
+ fib->ll_ops->fib_entry_pack(op_ctx, fib->proto, op, fib->vr->id,
+ fib_entry->fib_node->key.prefix_len,
+ fib_entry->fib_node->key.addr,
+ fib_entry->priv);
+}
+
+int mlxsw_sp_fib_entry_commit(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ const struct mlxsw_sp_router_ll_ops *ll_ops)
+{
+ bool postponed_for_bulk = false;
+ int err;
+
+ err = ll_ops->fib_entry_commit(mlxsw_sp, op_ctx, &postponed_for_bulk);
+ if (!postponed_for_bulk)
+ mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx);
+ return err;
+}
+
+static int mlxsw_sp_adj_discard_write(struct mlxsw_sp *mlxsw_sp)
{
enum mlxsw_reg_ratr_trap_action trap_action;
char ratr_pl[MLXSW_REG_RATR_LEN];
if (err)
return err;
- trap_action = MLXSW_REG_RATR_TRAP_ACTION_DISCARD_ERRORS;
+ trap_action = MLXSW_REG_RATR_TRAP_ACTION_TRAP;
mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, true,
MLXSW_REG_RATR_TYPE_ETHERNET,
- mlxsw_sp->router->adj_discard_index, rif_index);
+ mlxsw_sp->router->adj_discard_index,
+ mlxsw_sp->router->lb_rif_index);
mlxsw_reg_ratr_trap_action_set(ratr_pl, trap_action);
+ mlxsw_reg_ratr_trap_id_set(ratr_pl, MLXSW_TRAP_ID_RTR_EGRESS0);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl);
if (err)
goto err_ratr_write;
}
static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op)
+ enum mlxsw_sp_fib_entry_op op)
{
+ const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops;
struct mlxsw_sp_nexthop_group *nh_group = fib_entry->nh_group;
- char ralue_pl[MLXSW_REG_RALUE_LEN];
+ struct mlxsw_sp_nexthop_group_info *nhgi = nh_group->nhgi;
enum mlxsw_reg_ralue_trap_action trap_action;
u16 trap_id = 0;
u32 adjacency_index = 0;
*/
if (mlxsw_sp_fib_entry_should_offload(fib_entry)) {
trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP;
- adjacency_index = fib_entry->nh_group->adj_index;
- ecmp_size = fib_entry->nh_group->ecmp_size;
- } else if (!nh_group->adj_index_valid && nh_group->count &&
- nh_group->nh_rif) {
- err = mlxsw_sp_adj_discard_write(mlxsw_sp,
- nh_group->nh_rif->rif_index);
+ adjacency_index = nhgi->adj_index;
+ ecmp_size = nhgi->ecmp_size;
+ } else if (!nhgi->adj_index_valid && nhgi->count && nhgi->nh_rif) {
+ err = mlxsw_sp_adj_discard_write(mlxsw_sp);
if (err)
return err;
trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP;
trap_id = MLXSW_TRAP_ID_RTR_INGRESS0;
}
- mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op);
- mlxsw_reg_ralue_act_remote_pack(ralue_pl, trap_action, trap_id,
- adjacency_index, ecmp_size);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+ mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op);
+ ll_ops->fib_entry_act_remote_pack(op_ctx, trap_action, trap_id,
+ adjacency_index, ecmp_size);
+ return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops);
}
static int mlxsw_sp_fib_entry_op_local(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op)
+ enum mlxsw_sp_fib_entry_op op)
{
- struct mlxsw_sp_rif *rif = fib_entry->nh_group->nh_rif;
+ const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops;
+ struct mlxsw_sp_rif *rif = fib_entry->nh_group->nhgi->nh_rif;
enum mlxsw_reg_ralue_trap_action trap_action;
- char ralue_pl[MLXSW_REG_RALUE_LEN];
u16 trap_id = 0;
u16 rif_index = 0;
trap_id = MLXSW_TRAP_ID_RTR_INGRESS0;
}
- mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op);
- mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id,
- rif_index);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+ mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op);
+ ll_ops->fib_entry_act_local_pack(op_ctx, trap_action, trap_id, rif_index);
+ return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops);
}
static int mlxsw_sp_fib_entry_op_trap(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op)
+ enum mlxsw_sp_fib_entry_op op)
{
- char ralue_pl[MLXSW_REG_RALUE_LEN];
+ const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops;
- mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op);
- mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+ mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op);
+ ll_ops->fib_entry_act_ip2me_pack(op_ctx);
+ return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops);
}
static int mlxsw_sp_fib_entry_op_blackhole(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op)
+ enum mlxsw_sp_fib_entry_op op)
{
+ const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops;
enum mlxsw_reg_ralue_trap_action trap_action;
- char ralue_pl[MLXSW_REG_RALUE_LEN];
trap_action = MLXSW_REG_RALUE_TRAP_ACTION_DISCARD_ERROR;
- mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op);
- mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, 0, 0);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+ mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op);
+ ll_ops->fib_entry_act_local_pack(op_ctx, trap_action, 0, 0);
+ return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops);
}
static int
mlxsw_sp_fib_entry_op_unreachable(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op)
+ enum mlxsw_sp_fib_entry_op op)
{
+ const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops;
enum mlxsw_reg_ralue_trap_action trap_action;
- char ralue_pl[MLXSW_REG_RALUE_LEN];
u16 trap_id;
trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP;
trap_id = MLXSW_TRAP_ID_RTR_INGRESS1;
- mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op);
- mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, 0);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+ mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op);
+ ll_ops->fib_entry_act_local_pack(op_ctx, trap_action, trap_id, 0);
+ return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops);
}
static int
mlxsw_sp_fib_entry_op_ipip_decap(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op)
+ enum mlxsw_sp_fib_entry_op op)
{
+ const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops;
struct mlxsw_sp_ipip_entry *ipip_entry = fib_entry->decap.ipip_entry;
const struct mlxsw_sp_ipip_ops *ipip_ops;
return -EINVAL;
ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt];
- return ipip_ops->fib_entry_op(mlxsw_sp, ipip_entry, op,
- fib_entry->decap.tunnel_index);
+ return ipip_ops->fib_entry_op(mlxsw_sp, ll_ops, op_ctx, ipip_entry, op,
+ fib_entry->decap.tunnel_index, fib_entry->priv);
}
static int mlxsw_sp_fib_entry_op_nve_decap(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op)
+ enum mlxsw_sp_fib_entry_op op)
{
- char ralue_pl[MLXSW_REG_RALUE_LEN];
+ const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops;
- mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op);
- mlxsw_reg_ralue_act_ip2me_tun_pack(ralue_pl,
- fib_entry->decap.tunnel_index);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+ mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op);
+ ll_ops->fib_entry_act_ip2me_tun_pack(op_ctx,
+ fib_entry->decap.tunnel_index);
+ return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops);
}
static int __mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op)
+ enum mlxsw_sp_fib_entry_op op)
{
switch (fib_entry->type) {
case MLXSW_SP_FIB_ENTRY_TYPE_REMOTE:
- return mlxsw_sp_fib_entry_op_remote(mlxsw_sp, fib_entry, op);
+ return mlxsw_sp_fib_entry_op_remote(mlxsw_sp, op_ctx, fib_entry, op);
case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL:
- return mlxsw_sp_fib_entry_op_local(mlxsw_sp, fib_entry, op);
+ return mlxsw_sp_fib_entry_op_local(mlxsw_sp, op_ctx, fib_entry, op);
case MLXSW_SP_FIB_ENTRY_TYPE_TRAP:
- return mlxsw_sp_fib_entry_op_trap(mlxsw_sp, fib_entry, op);
+ return mlxsw_sp_fib_entry_op_trap(mlxsw_sp, op_ctx, fib_entry, op);
case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE:
- return mlxsw_sp_fib_entry_op_blackhole(mlxsw_sp, fib_entry, op);
+ return mlxsw_sp_fib_entry_op_blackhole(mlxsw_sp, op_ctx, fib_entry, op);
case MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE:
- return mlxsw_sp_fib_entry_op_unreachable(mlxsw_sp, fib_entry,
- op);
+ return mlxsw_sp_fib_entry_op_unreachable(mlxsw_sp, op_ctx, fib_entry, op);
case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP:
- return mlxsw_sp_fib_entry_op_ipip_decap(mlxsw_sp,
- fib_entry, op);
+ return mlxsw_sp_fib_entry_op_ipip_decap(mlxsw_sp, op_ctx, fib_entry, op);
case MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP:
- return mlxsw_sp_fib_entry_op_nve_decap(mlxsw_sp, fib_entry, op);
+ return mlxsw_sp_fib_entry_op_nve_decap(mlxsw_sp, op_ctx, fib_entry, op);
}
return -EINVAL;
}
static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op)
+ enum mlxsw_sp_fib_entry_op op)
{
- int err = __mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, op);
+ int err = __mlxsw_sp_fib_entry_op(mlxsw_sp, op_ctx, fib_entry, op);
if (err)
return err;
return err;
}
+static int __mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ struct mlxsw_sp_fib_entry *fib_entry,
+ bool is_new)
+{
+ return mlxsw_sp_fib_entry_op(mlxsw_sp, op_ctx, fib_entry,
+ is_new ? MLXSW_SP_FIB_ENTRY_OP_WRITE :
+ MLXSW_SP_FIB_ENTRY_OP_UPDATE);
+}
+
static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_entry *fib_entry)
{
- return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry,
- MLXSW_REG_RALUE_OP_WRITE_WRITE);
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx = mlxsw_sp->router->ll_op_ctx;
+
+ mlxsw_sp_fib_entry_op_ctx_clear(op_ctx);
+ return __mlxsw_sp_fib_entry_update(mlxsw_sp, op_ctx, fib_entry, false);
}
static int mlxsw_sp_fib_entry_del(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib_entry *fib_entry)
{
- return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry,
- MLXSW_REG_RALUE_OP_WRITE_DELETE);
+ const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops;
+
+ if (!ll_ops->fib_entry_is_committed(fib_entry->priv))
+ return 0;
+ return mlxsw_sp_fib_entry_op(mlxsw_sp, op_ctx, fib_entry,
+ MLXSW_SP_FIB_ENTRY_OP_DELETE);
}
static int
const struct fib_entry_notifier_info *fen_info,
struct mlxsw_sp_fib_entry *fib_entry)
{
- struct net_device *dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev;
+ struct mlxsw_sp_nexthop_group_info *nhgi = fib_entry->nh_group->nhgi;
union mlxsw_sp_l3addr dip = { .addr4 = htonl(fen_info->dst) };
struct mlxsw_sp_router *router = mlxsw_sp->router;
u32 tb_id = mlxsw_sp_fix_tb_id(fen_info->tb_id);
+ int ifindex = nhgi->nexthops[0].ifindex;
struct mlxsw_sp_ipip_entry *ipip_entry;
- struct fib_info *fi = fen_info->fi;
switch (fen_info->type) {
case RTN_LOCAL:
- ipip_entry = mlxsw_sp_ipip_entry_find_by_decap(mlxsw_sp, dev,
- MLXSW_SP_L3_PROTO_IPV4, dip);
+ ipip_entry = mlxsw_sp_ipip_entry_find_by_decap(mlxsw_sp, ifindex,
+ MLXSW_SP_L3_PROTO_IPV4, dip);
if (ipip_entry && ipip_entry->ol_dev->flags & IFF_UP) {
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP;
return mlxsw_sp_fib_entry_decap_init(mlxsw_sp,
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE;
return 0;
case RTN_UNICAST:
- if (mlxsw_sp_fi_is_gateway(mlxsw_sp, fi))
+ if (nhgi->gateway)
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE;
else
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
return ERR_PTR(-ENOMEM);
fib_entry = &fib4_entry->common;
- err = mlxsw_sp_fib4_entry_type_set(mlxsw_sp, fen_info, fib_entry);
- if (err)
- goto err_fib4_entry_type_set;
+ fib_entry->priv = mlxsw_sp_fib_entry_priv_create(fib_node->fib->ll_ops);
+ if (IS_ERR(fib_entry->priv)) {
+ err = PTR_ERR(fib_entry->priv);
+ goto err_fib_entry_priv_create;
+ }
err = mlxsw_sp_nexthop4_group_get(mlxsw_sp, fib_entry, fen_info->fi);
if (err)
goto err_nexthop4_group_get;
- fib4_entry->prio = fen_info->fi->fib_priority;
+ err = mlxsw_sp_nexthop_group_vr_link(fib_entry->nh_group,
+ fib_node->fib);
+ if (err)
+ goto err_nexthop_group_vr_link;
+
+ err = mlxsw_sp_fib4_entry_type_set(mlxsw_sp, fen_info, fib_entry);
+ if (err)
+ goto err_fib4_entry_type_set;
+
+ fib4_entry->fi = fen_info->fi;
+ fib_info_hold(fib4_entry->fi);
fib4_entry->tb_id = fen_info->tb_id;
fib4_entry->type = fen_info->type;
fib4_entry->tos = fen_info->tos;
return fib4_entry;
-err_nexthop4_group_get:
- mlxsw_sp_fib4_entry_type_unset(mlxsw_sp, fib_entry);
err_fib4_entry_type_set:
+ mlxsw_sp_nexthop_group_vr_unlink(fib_entry->nh_group, fib_node->fib);
+err_nexthop_group_vr_link:
+ mlxsw_sp_nexthop4_group_put(mlxsw_sp, &fib4_entry->common);
+err_nexthop4_group_get:
+ mlxsw_sp_fib_entry_priv_put(fib_entry->priv);
+err_fib_entry_priv_create:
kfree(fib4_entry);
return ERR_PTR(err);
}
static void mlxsw_sp_fib4_entry_destroy(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib4_entry *fib4_entry)
{
- mlxsw_sp_nexthop4_group_put(mlxsw_sp, &fib4_entry->common);
+ struct mlxsw_sp_fib_node *fib_node = fib4_entry->common.fib_node;
+
+ fib_info_put(fib4_entry->fi);
mlxsw_sp_fib4_entry_type_unset(mlxsw_sp, &fib4_entry->common);
+ mlxsw_sp_nexthop_group_vr_unlink(fib4_entry->common.nh_group,
+ fib_node->fib);
+ mlxsw_sp_nexthop4_group_put(mlxsw_sp, &fib4_entry->common);
+ mlxsw_sp_fib_entry_priv_put(fib4_entry->common.priv);
kfree(fib4_entry);
}
if (fib4_entry->tb_id == fen_info->tb_id &&
fib4_entry->tos == fen_info->tos &&
fib4_entry->type == fen_info->type &&
- mlxsw_sp_nexthop4_group_fi(fib4_entry->common.nh_group) ==
- fen_info->fi)
+ fib4_entry->fi == fen_info->fi)
return fib4_entry;
return NULL;
}
static int mlxsw_sp_fib_node_entry_link(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib_entry *fib_entry)
{
struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node;
+ bool is_new = !fib_node->fib_entry;
int err;
fib_node->fib_entry = fib_entry;
- err = mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry);
+ err = __mlxsw_sp_fib_entry_update(mlxsw_sp, op_ctx, fib_entry, is_new);
if (err)
goto err_fib_entry_update;
return err;
}
-static void
-mlxsw_sp_fib_node_entry_unlink(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_fib_entry *fib_entry)
+static int __mlxsw_sp_fib_node_entry_unlink(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ struct mlxsw_sp_fib_entry *fib_entry)
{
struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node;
+ int err;
- mlxsw_sp_fib_entry_del(mlxsw_sp, fib_entry);
+ err = mlxsw_sp_fib_entry_del(mlxsw_sp, op_ctx, fib_entry);
fib_node->fib_entry = NULL;
+ return err;
+}
+
+static void mlxsw_sp_fib_node_entry_unlink(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
+{
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx = mlxsw_sp->router->ll_op_ctx;
+
+ mlxsw_sp_fib_entry_op_ctx_clear(op_ctx);
+ __mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, op_ctx, fib_entry);
}
static bool mlxsw_sp_fib4_allow_replace(struct mlxsw_sp_fib4_entry *fib4_entry)
static int
mlxsw_sp_router_fib4_replace(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
const struct fib_entry_notifier_info *fen_info)
{
struct mlxsw_sp_fib4_entry *fib4_entry, *fib4_replaced;
}
replaced = fib_node->fib_entry;
- err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, &fib4_entry->common);
+ err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, op_ctx, &fib4_entry->common);
if (err) {
dev_warn(mlxsw_sp->bus_info->dev, "Failed to link FIB entry to node\n");
goto err_fib_node_entry_link;
return err;
}
-static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp,
- struct fib_entry_notifier_info *fen_info)
+static int mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ struct fib_entry_notifier_info *fen_info)
{
struct mlxsw_sp_fib4_entry *fib4_entry;
struct mlxsw_sp_fib_node *fib_node;
+ int err;
if (mlxsw_sp->router->aborted)
- return;
+ return 0;
fib4_entry = mlxsw_sp_fib4_entry_lookup(mlxsw_sp, fen_info);
if (!fib4_entry)
- return;
+ return 0;
fib_node = fib4_entry->common.fib_node;
- mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, &fib4_entry->common);
+ err = __mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, op_ctx, &fib4_entry->common);
mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib4_entry);
mlxsw_sp_fib_node_put(mlxsw_sp, fib_node);
+ return err;
}
static bool mlxsw_sp_fib6_rt_should_ignore(const struct fib6_info *rt)
{
struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh;
- fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
+ if (!mlxsw_sp_rt6->rt->nh)
+ fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
mlxsw_sp_rt6_release(mlxsw_sp_rt6->rt);
kfree(mlxsw_sp_rt6);
}
mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->fib6_nh->fib_nh_dev, ret);
}
-static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_nexthop_group *nh_grp,
- struct mlxsw_sp_nexthop *nh,
- const struct fib6_info *rt)
-{
- const struct mlxsw_sp_ipip_ops *ipip_ops;
- struct mlxsw_sp_ipip_entry *ipip_entry;
- struct net_device *dev = rt->fib6_nh->fib_nh_dev;
- struct mlxsw_sp_rif *rif;
- int err;
-
- ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, dev);
- if (ipip_entry) {
- ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt];
- if (ipip_ops->can_offload(mlxsw_sp, dev,
- MLXSW_SP_L3_PROTO_IPV6)) {
- nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP;
- mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, ipip_entry);
- return 0;
- }
- }
-
- nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH;
- rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
- if (!rif)
- return 0;
- mlxsw_sp_nexthop_rif_init(nh, rif);
-
- err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
- if (err)
- goto err_nexthop_neigh_init;
-
- return 0;
-
-err_nexthop_neigh_init:
- mlxsw_sp_nexthop_rif_fini(nh);
- return err;
-}
-
-static void mlxsw_sp_nexthop6_type_fini(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_nexthop *nh)
-{
- mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh);
-}
-
static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp,
struct mlxsw_sp_nexthop *nh,
{
struct net_device *dev = rt->fib6_nh->fib_nh_dev;
- nh->nh_grp = nh_grp;
+ nh->nhgi = nh_grp->nhgi;
nh->nh_weight = rt->fib6_nh->fib_nh_weight;
memcpy(&nh->gw_addr, &rt->fib6_nh->fib_nh_gw6, sizeof(nh->gw_addr));
+#if IS_ENABLED(CONFIG_IPV6)
+ nh->neigh_tbl = &nd_tbl;
+#endif
mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list);
return 0;
nh->ifindex = dev->ifindex;
- return mlxsw_sp_nexthop6_type_init(mlxsw_sp, nh_grp, nh, rt);
+ return mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, dev);
}
static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop *nh)
{
- mlxsw_sp_nexthop6_type_fini(mlxsw_sp, nh);
+ mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh);
list_del(&nh->router_list_node);
mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
}
mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, NULL);
}
-static struct mlxsw_sp_nexthop_group *
-mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_fib6_entry *fib6_entry)
+static int
+mlxsw_sp_nexthop6_group_info_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp,
+ struct mlxsw_sp_fib6_entry *fib6_entry)
{
- struct mlxsw_sp_nexthop_group *nh_grp;
+ struct mlxsw_sp_nexthop_group_info *nhgi;
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
struct mlxsw_sp_nexthop *nh;
- int i = 0;
- int err;
+ int err, i;
- nh_grp = kzalloc(struct_size(nh_grp, nexthops, fib6_entry->nrt6),
- GFP_KERNEL);
- if (!nh_grp)
- return ERR_PTR(-ENOMEM);
- INIT_LIST_HEAD(&nh_grp->fib_list);
-#if IS_ENABLED(CONFIG_IPV6)
- nh_grp->neigh_tbl = &nd_tbl;
-#endif
+ nhgi = kzalloc(struct_size(nhgi, nexthops, fib6_entry->nrt6),
+ GFP_KERNEL);
+ if (!nhgi)
+ return -ENOMEM;
+ nh_grp->nhgi = nhgi;
+ nhgi->nh_grp = nh_grp;
mlxsw_sp_rt6 = list_first_entry(&fib6_entry->rt6_list,
struct mlxsw_sp_rt6, list);
- nh_grp->gateway = mlxsw_sp_rt6_is_gateway(mlxsw_sp, mlxsw_sp_rt6->rt);
- nh_grp->count = fib6_entry->nrt6;
- for (i = 0; i < nh_grp->count; i++) {
+ nhgi->gateway = mlxsw_sp_rt6_is_gateway(mlxsw_sp, mlxsw_sp_rt6->rt);
+ nhgi->count = fib6_entry->nrt6;
+ for (i = 0; i < nhgi->count; i++) {
struct fib6_info *rt = mlxsw_sp_rt6->rt;
- nh = &nh_grp->nexthops[i];
+ nh = &nhgi->nexthops[i];
err = mlxsw_sp_nexthop6_init(mlxsw_sp, nh_grp, nh, rt);
if (err)
goto err_nexthop6_init;
mlxsw_sp_rt6 = list_next_entry(mlxsw_sp_rt6, list);
}
+ nh_grp->nhgi = nhgi;
+ err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
+ if (err)
+ goto err_group_refresh;
+
+ return 0;
+
+err_group_refresh:
+ i = nhgi->count;
+err_nexthop6_init:
+ for (i--; i >= 0; i--) {
+ nh = &nhgi->nexthops[i];
+ mlxsw_sp_nexthop6_fini(mlxsw_sp, nh);
+ }
+ kfree(nhgi);
+ return err;
+}
+
+static void
+mlxsw_sp_nexthop6_group_info_fini(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi;
+ int i;
+
+ for (i = nhgi->count - 1; i >= 0; i--) {
+ struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i];
+
+ mlxsw_sp_nexthop6_fini(mlxsw_sp, nh);
+ }
+ mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
+ WARN_ON_ONCE(nhgi->adj_index_valid);
+ kfree(nhgi);
+}
+
+static struct mlxsw_sp_nexthop_group *
+mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib6_entry *fib6_entry)
+{
+ struct mlxsw_sp_nexthop_group *nh_grp;
+ int err;
+
+ nh_grp = kzalloc(sizeof(*nh_grp), GFP_KERNEL);
+ if (!nh_grp)
+ return ERR_PTR(-ENOMEM);
+ INIT_LIST_HEAD(&nh_grp->vr_list);
+ err = rhashtable_init(&nh_grp->vr_ht,
+ &mlxsw_sp_nexthop_group_vr_ht_params);
+ if (err)
+ goto err_nexthop_group_vr_ht_init;
+ INIT_LIST_HEAD(&nh_grp->fib_list);
+ nh_grp->type = MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6;
+
+ err = mlxsw_sp_nexthop6_group_info_init(mlxsw_sp, nh_grp, fib6_entry);
+ if (err)
+ goto err_nexthop_group_info_init;
err = mlxsw_sp_nexthop_group_insert(mlxsw_sp, nh_grp);
if (err)
goto err_nexthop_group_insert;
- mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
+ nh_grp->can_destroy = true;
+
return nh_grp;
err_nexthop_group_insert:
-err_nexthop6_init:
- for (i--; i >= 0; i--) {
- nh = &nh_grp->nexthops[i];
- mlxsw_sp_nexthop6_fini(mlxsw_sp, nh);
- }
+ mlxsw_sp_nexthop6_group_info_fini(mlxsw_sp, nh_grp);
+err_nexthop_group_info_init:
+ rhashtable_destroy(&nh_grp->vr_ht);
+err_nexthop_group_vr_ht_init:
kfree(nh_grp);
return ERR_PTR(err);
}
mlxsw_sp_nexthop6_group_destroy(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp)
{
- struct mlxsw_sp_nexthop *nh;
- int i = nh_grp->count;
-
+ if (!nh_grp->can_destroy)
+ return;
mlxsw_sp_nexthop_group_remove(mlxsw_sp, nh_grp);
- for (i--; i >= 0; i--) {
- nh = &nh_grp->nexthops[i];
- mlxsw_sp_nexthop6_fini(mlxsw_sp, nh);
- }
- mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
- WARN_ON(nh_grp->adj_index_valid);
+ mlxsw_sp_nexthop6_group_info_fini(mlxsw_sp, nh_grp);
+ WARN_ON_ONCE(!list_empty(&nh_grp->vr_list));
+ rhashtable_destroy(&nh_grp->vr_ht);
kfree(nh_grp);
}
static int mlxsw_sp_nexthop6_group_get(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib6_entry *fib6_entry)
{
+ struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
struct mlxsw_sp_nexthop_group *nh_grp;
+ if (rt->nh) {
+ nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp,
+ rt->nh->id);
+ if (WARN_ON_ONCE(!nh_grp))
+ return -EINVAL;
+ goto out;
+ }
+
nh_grp = mlxsw_sp_nexthop6_group_lookup(mlxsw_sp, fib6_entry);
if (!nh_grp) {
nh_grp = mlxsw_sp_nexthop6_group_create(mlxsw_sp, fib6_entry);
return PTR_ERR(nh_grp);
}
- list_add_tail(&fib6_entry->common.nexthop_group_node,
- &nh_grp->fib_list);
- fib6_entry->common.nh_group = nh_grp;
-
/* The route and the nexthop are described by the same struct, so we
* need to the update the nexthop offload indication for the new route.
*/
__mlxsw_sp_nexthop6_group_offload_refresh(nh_grp, fib6_entry);
+out:
+ list_add_tail(&fib6_entry->common.nexthop_group_node,
+ &nh_grp->fib_list);
+ fib6_entry->common.nh_group = nh_grp;
+
return 0;
}
list_del(&fib_entry->nexthop_group_node);
if (!list_empty(&nh_grp->fib_list))
return;
+
+ if (nh_grp->type == MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ) {
+ mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp);
+ return;
+ }
+
mlxsw_sp_nexthop6_group_destroy(mlxsw_sp, nh_grp);
}
-static int
-mlxsw_sp_nexthop6_group_update(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_fib6_entry *fib6_entry)
+static int mlxsw_sp_nexthop6_group_update(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ struct mlxsw_sp_fib6_entry *fib6_entry)
{
struct mlxsw_sp_nexthop_group *old_nh_grp = fib6_entry->common.nh_group;
+ struct mlxsw_sp_fib_node *fib_node = fib6_entry->common.fib_node;
int err;
+ mlxsw_sp_nexthop_group_vr_unlink(old_nh_grp, fib_node->fib);
fib6_entry->common.nh_group = NULL;
list_del(&fib6_entry->common.nexthop_group_node);
if (err)
goto err_nexthop6_group_get;
+ err = mlxsw_sp_nexthop_group_vr_link(fib6_entry->common.nh_group,
+ fib_node->fib);
+ if (err)
+ goto err_nexthop_group_vr_link;
+
/* In case this entry is offloaded, then the adjacency index
* currently associated with it in the device's table is that
* of the old group. Start using the new one instead.
*/
- err = mlxsw_sp_fib_entry_update(mlxsw_sp, &fib6_entry->common);
+ err = __mlxsw_sp_fib_entry_update(mlxsw_sp, op_ctx,
+ &fib6_entry->common, false);
if (err)
goto err_fib_entry_update;
return 0;
err_fib_entry_update:
+ mlxsw_sp_nexthop_group_vr_unlink(fib6_entry->common.nh_group,
+ fib_node->fib);
+err_nexthop_group_vr_link:
mlxsw_sp_nexthop6_group_put(mlxsw_sp, &fib6_entry->common);
err_nexthop6_group_get:
list_add_tail(&fib6_entry->common.nexthop_group_node,
&old_nh_grp->fib_list);
fib6_entry->common.nh_group = old_nh_grp;
+ mlxsw_sp_nexthop_group_vr_link(old_nh_grp, fib_node->fib);
return err;
}
static int
mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib6_entry *fib6_entry,
struct fib6_info **rt_arr, unsigned int nrt6)
{
fib6_entry->nrt6++;
}
- err = mlxsw_sp_nexthop6_group_update(mlxsw_sp, fib6_entry);
+ err = mlxsw_sp_nexthop6_group_update(mlxsw_sp, op_ctx, fib6_entry);
if (err)
goto err_nexthop6_group_update;
static void
mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
struct mlxsw_sp_fib6_entry *fib6_entry,
struct fib6_info **rt_arr, unsigned int nrt6)
{
mlxsw_sp_rt6_destroy(mlxsw_sp_rt6);
}
- mlxsw_sp_nexthop6_group_update(mlxsw_sp, fib6_entry);
+ mlxsw_sp_nexthop6_group_update(mlxsw_sp, op_ctx, fib6_entry);
}
static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_entry *fib_entry,
const struct fib6_info *rt)
{
- /* Packets hitting RTF_REJECT routes need to be discarded by the
- * stack. We can rely on their destination device not having a
- * RIF (it's the loopback device) and can thus use action type
- * local, which will cause them to be trapped with a lower
- * priority than packets that need to be locally received.
- */
if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST))
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP;
else if (rt->fib6_type == RTN_BLACKHOLE)
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE;
else if (rt->fib6_flags & RTF_REJECT)
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE;
- else if (mlxsw_sp_rt6_is_gateway(mlxsw_sp, rt))
+ else if (fib_entry->nh_group->nhgi->gateway)
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE;
else
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
return ERR_PTR(-ENOMEM);
fib_entry = &fib6_entry->common;
+ fib_entry->priv = mlxsw_sp_fib_entry_priv_create(fib_node->fib->ll_ops);
+ if (IS_ERR(fib_entry->priv)) {
+ err = PTR_ERR(fib_entry->priv);
+ goto err_fib_entry_priv_create;
+ }
+
INIT_LIST_HEAD(&fib6_entry->rt6_list);
for (i = 0; i < nrt6; i++) {
fib6_entry->nrt6++;
}
- mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, rt_arr[0]);
-
err = mlxsw_sp_nexthop6_group_get(mlxsw_sp, fib6_entry);
if (err)
goto err_nexthop6_group_get;
+ err = mlxsw_sp_nexthop_group_vr_link(fib_entry->nh_group,
+ fib_node->fib);
+ if (err)
+ goto err_nexthop_group_vr_link;
+
+ mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, rt_arr[0]);
+
fib_entry->fib_node = fib_node;
return fib6_entry;
+err_nexthop_group_vr_link:
+ mlxsw_sp_nexthop6_group_put(mlxsw_sp, fib_entry);
err_nexthop6_group_get:
i = nrt6;
err_rt6_create:
list_del(&mlxsw_sp_rt6->list);
mlxsw_sp_rt6_destroy(mlxsw_sp_rt6);
}
+ mlxsw_sp_fib_entry_priv_put(fib_entry->priv);
+err_fib_entry_priv_create:
kfree(fib6_entry);
return ERR_PTR(err);
}
static void mlxsw_sp_fib6_entry_destroy(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib6_entry *fib6_entry)
{
+ struct mlxsw_sp_fib_node *fib_node = fib6_entry->common.fib_node;
+
+ mlxsw_sp_nexthop_group_vr_unlink(fib6_entry->common.nh_group,
+ fib_node->fib);
mlxsw_sp_nexthop6_group_put(mlxsw_sp, &fib6_entry->common);
mlxsw_sp_fib6_entry_rt_destroy_all(fib6_entry);
WARN_ON(fib6_entry->nrt6);
+ mlxsw_sp_fib_entry_priv_put(fib6_entry->common.priv);
kfree(fib6_entry);
}
}
static int mlxsw_sp_router_fib6_replace(struct mlxsw_sp *mlxsw_sp,
- struct fib6_info **rt_arr,
- unsigned int nrt6)
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ struct fib6_info **rt_arr, unsigned int nrt6)
{
struct mlxsw_sp_fib6_entry *fib6_entry, *fib6_replaced;
struct mlxsw_sp_fib_entry *replaced;
}
replaced = fib_node->fib_entry;
- err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, &fib6_entry->common);
+ err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, op_ctx, &fib6_entry->common);
if (err)
goto err_fib_node_entry_link;
}
static int mlxsw_sp_router_fib6_append(struct mlxsw_sp *mlxsw_sp,
- struct fib6_info **rt_arr,
- unsigned int nrt6)
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ struct fib6_info **rt_arr, unsigned int nrt6)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_fib_node *fib_node;
fib6_entry = container_of(fib_node->fib_entry,
struct mlxsw_sp_fib6_entry, common);
- err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry, rt_arr,
- nrt6);
+ err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, op_ctx, fib6_entry, rt_arr, nrt6);
if (err)
goto err_fib6_entry_nexthop_add;
return err;
}
-static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp,
- struct fib6_info **rt_arr,
- unsigned int nrt6)
+static int mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ struct fib6_info **rt_arr, unsigned int nrt6)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_fib_node *fib_node;
struct fib6_info *rt = rt_arr[0];
+ int err;
if (mlxsw_sp->router->aborted)
- return;
+ return 0;
if (mlxsw_sp_fib6_rt_should_ignore(rt))
- return;
+ return 0;
/* Multipath routes are first added to the FIB trie and only then
* notified. If we vetoed the addition, we will get a delete
*/
fib6_entry = mlxsw_sp_fib6_entry_lookup(mlxsw_sp, rt);
if (!fib6_entry)
- return;
+ return 0;
/* If not all the nexthops are deleted, then only reduce the nexthop
* group.
*/
if (nrt6 != fib6_entry->nrt6) {
- mlxsw_sp_fib6_entry_nexthop_del(mlxsw_sp, fib6_entry, rt_arr,
- nrt6);
- return;
+ mlxsw_sp_fib6_entry_nexthop_del(mlxsw_sp, op_ctx, fib6_entry, rt_arr, nrt6);
+ return 0;
}
fib_node = fib6_entry->common.fib_node;
- mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, &fib6_entry->common);
+ err = __mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, op_ctx, &fib6_entry->common);
mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_entry);
mlxsw_sp_fib_node_put(mlxsw_sp, fib_node);
+ return err;
}
static int __mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp,
- enum mlxsw_reg_ralxx_protocol proto,
+ enum mlxsw_sp_l3proto proto,
u8 tree_id)
{
- char ralta_pl[MLXSW_REG_RALTA_LEN];
- char ralst_pl[MLXSW_REG_RALST_LEN];
+ const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto];
+ enum mlxsw_reg_ralxx_protocol ralxx_proto =
+ (enum mlxsw_reg_ralxx_protocol) proto;
+ struct mlxsw_sp_fib_entry_priv *priv;
+ char xralta_pl[MLXSW_REG_XRALTA_LEN];
+ char xralst_pl[MLXSW_REG_XRALST_LEN];
int i, err;
- mlxsw_reg_ralta_pack(ralta_pl, true, proto, tree_id);
- err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl);
+ mlxsw_reg_xralta_pack(xralta_pl, true, ralxx_proto, tree_id);
+ err = ll_ops->ralta_write(mlxsw_sp, xralta_pl);
if (err)
return err;
- mlxsw_reg_ralst_pack(ralst_pl, 0xff, tree_id);
- err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), ralst_pl);
+ mlxsw_reg_xralst_pack(xralst_pl, 0xff, tree_id);
+ err = ll_ops->ralst_write(mlxsw_sp, xralst_pl);
if (err)
return err;
for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx = mlxsw_sp->router->ll_op_ctx;
struct mlxsw_sp_vr *vr = &mlxsw_sp->router->vrs[i];
- char raltb_pl[MLXSW_REG_RALTB_LEN];
- char ralue_pl[MLXSW_REG_RALUE_LEN];
+ char xraltb_pl[MLXSW_REG_XRALTB_LEN];
- mlxsw_reg_raltb_pack(raltb_pl, vr->id, proto, tree_id);
- err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb),
- raltb_pl);
+ mlxsw_sp_fib_entry_op_ctx_clear(op_ctx);
+ mlxsw_reg_xraltb_pack(xraltb_pl, vr->id, ralxx_proto, tree_id);
+ err = ll_ops->raltb_write(mlxsw_sp, xraltb_pl);
if (err)
return err;
- mlxsw_reg_ralue_pack(ralue_pl, proto,
- MLXSW_REG_RALUE_OP_WRITE_WRITE, vr->id, 0);
- mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
- err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue),
- ralue_pl);
+ priv = mlxsw_sp_fib_entry_priv_create(ll_ops);
+ if (IS_ERR(priv))
+ return PTR_ERR(priv);
+
+ ll_ops->fib_entry_pack(op_ctx, proto, MLXSW_SP_FIB_ENTRY_OP_WRITE,
+ vr->id, 0, NULL, priv);
+ ll_ops->fib_entry_act_ip2me_pack(op_ctx);
+ err = ll_ops->fib_entry_commit(mlxsw_sp, op_ctx, NULL);
+ mlxsw_sp_fib_entry_priv_put(priv);
if (err)
return err;
}
static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
{
- enum mlxsw_reg_ralxx_protocol proto = MLXSW_REG_RALXX_PROTOCOL_IPV4;
+ enum mlxsw_sp_l3proto proto = MLXSW_SP_L3_PROTO_IPV4;
int err;
err = __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto,
* packets that don't match any routes are trapped to the CPU.
*/
- proto = MLXSW_REG_RALXX_PROTOCOL_IPV6;
+ proto = MLXSW_SP_L3_PROTO_IPV6;
return __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto,
MLXSW_SP_LPM_TREE_MIN + 1);
}
dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n");
}
-struct mlxsw_sp_fib6_event_work {
+struct mlxsw_sp_fib6_event {
struct fib6_info **rt_arr;
unsigned int nrt6;
};
-struct mlxsw_sp_fib_event_work {
- struct work_struct work;
+struct mlxsw_sp_fib_event {
+ struct list_head list; /* node in fib queue */
union {
- struct mlxsw_sp_fib6_event_work fib6_work;
+ struct mlxsw_sp_fib6_event fib6_event;
struct fib_entry_notifier_info fen_info;
struct fib_rule_notifier_info fr_info;
struct fib_nh_notifier_info fnh_info;
};
struct mlxsw_sp *mlxsw_sp;
unsigned long event;
+ int family;
};
static int
-mlxsw_sp_router_fib6_work_init(struct mlxsw_sp_fib6_event_work *fib6_work,
- struct fib6_entry_notifier_info *fen6_info)
+mlxsw_sp_router_fib6_event_init(struct mlxsw_sp_fib6_event *fib6_event,
+ struct fib6_entry_notifier_info *fen6_info)
{
struct fib6_info *rt = fen6_info->rt;
struct fib6_info **rt_arr;
if (!rt_arr)
return -ENOMEM;
- fib6_work->rt_arr = rt_arr;
- fib6_work->nrt6 = nrt6;
+ fib6_event->rt_arr = rt_arr;
+ fib6_event->nrt6 = nrt6;
rt_arr[0] = rt;
fib6_info_hold(rt);
}
static void
-mlxsw_sp_router_fib6_work_fini(struct mlxsw_sp_fib6_event_work *fib6_work)
+mlxsw_sp_router_fib6_event_fini(struct mlxsw_sp_fib6_event *fib6_event)
{
int i;
- for (i = 0; i < fib6_work->nrt6; i++)
- mlxsw_sp_rt6_release(fib6_work->rt_arr[i]);
- kfree(fib6_work->rt_arr);
+ for (i = 0; i < fib6_event->nrt6; i++)
+ mlxsw_sp_rt6_release(fib6_event->rt_arr[i]);
+ kfree(fib6_event->rt_arr);
}
-static void mlxsw_sp_router_fib4_event_work(struct work_struct *work)
+static void mlxsw_sp_router_fib4_event_process(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ struct mlxsw_sp_fib_event *fib_event)
{
- 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;
int err;
- mutex_lock(&mlxsw_sp->router->lock);
mlxsw_sp_span_respin(mlxsw_sp);
- switch (fib_work->event) {
+ switch (fib_event->event) {
case FIB_EVENT_ENTRY_REPLACE:
- err = mlxsw_sp_router_fib4_replace(mlxsw_sp,
- &fib_work->fen_info);
- if (err)
+ err = mlxsw_sp_router_fib4_replace(mlxsw_sp, op_ctx, &fib_event->fen_info);
+ if (err) {
+ mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx);
mlxsw_sp_router_fib_abort(mlxsw_sp);
- fib_info_put(fib_work->fen_info.fi);
+ }
+ fib_info_put(fib_event->fen_info.fi);
break;
case FIB_EVENT_ENTRY_DEL:
- mlxsw_sp_router_fib4_del(mlxsw_sp, &fib_work->fen_info);
- fib_info_put(fib_work->fen_info.fi);
+ err = mlxsw_sp_router_fib4_del(mlxsw_sp, op_ctx, &fib_event->fen_info);
+ if (err)
+ mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx);
+ fib_info_put(fib_event->fen_info.fi);
break;
case FIB_EVENT_NH_ADD:
case FIB_EVENT_NH_DEL:
- mlxsw_sp_nexthop4_event(mlxsw_sp, fib_work->event,
- fib_work->fnh_info.fib_nh);
- fib_info_put(fib_work->fnh_info.fib_nh->nh_parent);
+ mlxsw_sp_nexthop4_event(mlxsw_sp, fib_event->event, fib_event->fnh_info.fib_nh);
+ fib_info_put(fib_event->fnh_info.fib_nh->nh_parent);
break;
}
- mutex_unlock(&mlxsw_sp->router->lock);
- kfree(fib_work);
}
-static void mlxsw_sp_router_fib6_event_work(struct work_struct *work)
+static void mlxsw_sp_router_fib6_event_process(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ struct mlxsw_sp_fib_event *fib_event)
{
- 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;
int err;
- mutex_lock(&mlxsw_sp->router->lock);
mlxsw_sp_span_respin(mlxsw_sp);
- switch (fib_work->event) {
+ switch (fib_event->event) {
case FIB_EVENT_ENTRY_REPLACE:
- err = mlxsw_sp_router_fib6_replace(mlxsw_sp,
- fib_work->fib6_work.rt_arr,
- fib_work->fib6_work.nrt6);
- if (err)
+ err = mlxsw_sp_router_fib6_replace(mlxsw_sp, op_ctx, fib_event->fib6_event.rt_arr,
+ fib_event->fib6_event.nrt6);
+ if (err) {
+ mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx);
mlxsw_sp_router_fib_abort(mlxsw_sp);
- mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work);
+ }
+ mlxsw_sp_router_fib6_event_fini(&fib_event->fib6_event);
break;
case FIB_EVENT_ENTRY_APPEND:
- err = mlxsw_sp_router_fib6_append(mlxsw_sp,
- fib_work->fib6_work.rt_arr,
- fib_work->fib6_work.nrt6);
- if (err)
+ err = mlxsw_sp_router_fib6_append(mlxsw_sp, op_ctx, fib_event->fib6_event.rt_arr,
+ fib_event->fib6_event.nrt6);
+ if (err) {
+ mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx);
mlxsw_sp_router_fib_abort(mlxsw_sp);
- mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work);
+ }
+ mlxsw_sp_router_fib6_event_fini(&fib_event->fib6_event);
break;
case FIB_EVENT_ENTRY_DEL:
- mlxsw_sp_router_fib6_del(mlxsw_sp,
- fib_work->fib6_work.rt_arr,
- fib_work->fib6_work.nrt6);
- mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work);
+ err = mlxsw_sp_router_fib6_del(mlxsw_sp, op_ctx, fib_event->fib6_event.rt_arr,
+ fib_event->fib6_event.nrt6);
+ if (err)
+ mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx);
+ mlxsw_sp_router_fib6_event_fini(&fib_event->fib6_event);
break;
}
- mutex_unlock(&mlxsw_sp->router->lock);
- kfree(fib_work);
}
-static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work)
+static void mlxsw_sp_router_fibmr_event_process(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_event *fib_event)
{
- 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();
mutex_lock(&mlxsw_sp->router->lock);
- switch (fib_work->event) {
+ switch (fib_event->event) {
case FIB_EVENT_ENTRY_REPLACE:
case FIB_EVENT_ENTRY_ADD:
- replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE;
+ replace = fib_event->event == FIB_EVENT_ENTRY_REPLACE;
- err = mlxsw_sp_router_fibmr_add(mlxsw_sp, &fib_work->men_info,
- replace);
+ err = mlxsw_sp_router_fibmr_add(mlxsw_sp, &fib_event->men_info, replace);
if (err)
mlxsw_sp_router_fib_abort(mlxsw_sp);
- mr_cache_put(fib_work->men_info.mfc);
+ mr_cache_put(fib_event->men_info.mfc);
break;
case FIB_EVENT_ENTRY_DEL:
- mlxsw_sp_router_fibmr_del(mlxsw_sp, &fib_work->men_info);
- mr_cache_put(fib_work->men_info.mfc);
+ mlxsw_sp_router_fibmr_del(mlxsw_sp, &fib_event->men_info);
+ mr_cache_put(fib_event->men_info.mfc);
break;
case FIB_EVENT_VIF_ADD:
err = mlxsw_sp_router_fibmr_vif_add(mlxsw_sp,
- &fib_work->ven_info);
+ &fib_event->ven_info);
if (err)
mlxsw_sp_router_fib_abort(mlxsw_sp);
- dev_put(fib_work->ven_info.dev);
+ dev_put(fib_event->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);
+ mlxsw_sp_router_fibmr_vif_del(mlxsw_sp, &fib_event->ven_info);
+ dev_put(fib_event->ven_info.dev);
break;
}
mutex_unlock(&mlxsw_sp->router->lock);
rtnl_unlock();
- kfree(fib_work);
}
-static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work,
+static void mlxsw_sp_router_fib_event_work(struct work_struct *work)
+{
+ struct mlxsw_sp_router *router = container_of(work, struct mlxsw_sp_router, fib_event_work);
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx = router->ll_op_ctx;
+ struct mlxsw_sp *mlxsw_sp = router->mlxsw_sp;
+ struct mlxsw_sp_fib_event *next_fib_event;
+ struct mlxsw_sp_fib_event *fib_event;
+ int last_family = AF_UNSPEC;
+ LIST_HEAD(fib_event_queue);
+
+ spin_lock_bh(&router->fib_event_queue_lock);
+ list_splice_init(&router->fib_event_queue, &fib_event_queue);
+ spin_unlock_bh(&router->fib_event_queue_lock);
+
+ /* Router lock is held here to make sure per-instance
+ * operation context is not used in between FIB4/6 events
+ * processing.
+ */
+ mutex_lock(&router->lock);
+ mlxsw_sp_fib_entry_op_ctx_clear(op_ctx);
+ list_for_each_entry_safe(fib_event, next_fib_event,
+ &fib_event_queue, list) {
+ /* Check if the next entry in the queue exists and it is
+ * of the same type (family and event) as the currect one.
+ * In that case it is permitted to do the bulking
+ * of multiple FIB entries to a single register write.
+ */
+ op_ctx->bulk_ok = !list_is_last(&fib_event->list, &fib_event_queue) &&
+ fib_event->family == next_fib_event->family &&
+ fib_event->event == next_fib_event->event;
+
+ /* In case family of this and the previous entry are different, context
+ * reinitialization is going to be needed now, indicate that.
+ * Note that since last_family is initialized to AF_UNSPEC, this is always
+ * going to happen for the first entry processed in the work.
+ */
+ if (fib_event->family != last_family)
+ op_ctx->initialized = false;
+
+ switch (fib_event->family) {
+ case AF_INET:
+ mlxsw_sp_router_fib4_event_process(mlxsw_sp, op_ctx,
+ fib_event);
+ break;
+ case AF_INET6:
+ mlxsw_sp_router_fib6_event_process(mlxsw_sp, op_ctx,
+ fib_event);
+ break;
+ case RTNL_FAMILY_IP6MR:
+ case RTNL_FAMILY_IPMR:
+ /* Unlock here as inside FIBMR the lock is taken again
+ * under RTNL. The per-instance operation context
+ * is not used by FIBMR.
+ */
+ mutex_unlock(&router->lock);
+ mlxsw_sp_router_fibmr_event_process(mlxsw_sp,
+ fib_event);
+ mutex_lock(&router->lock);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ }
+ last_family = fib_event->family;
+ kfree(fib_event);
+ cond_resched();
+ }
+ WARN_ON_ONCE(!list_empty(&router->ll_op_ctx->fib_entry_priv_list));
+ mutex_unlock(&router->lock);
+}
+
+static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event *fib_event,
struct fib_notifier_info *info)
{
struct fib_entry_notifier_info *fen_info;
struct fib_nh_notifier_info *fnh_info;
- switch (fib_work->event) {
+ switch (fib_event->event) {
case FIB_EVENT_ENTRY_REPLACE:
case FIB_EVENT_ENTRY_DEL:
fen_info = container_of(info, struct fib_entry_notifier_info,
info);
- fib_work->fen_info = *fen_info;
+ fib_event->fen_info = *fen_info;
/* Take reference on fib_info to prevent it from being
- * freed while work is queued. Release it afterwards.
+ * freed while event is queued. Release it afterwards.
*/
- fib_info_hold(fib_work->fen_info.fi);
+ fib_info_hold(fib_event->fen_info.fi);
break;
case FIB_EVENT_NH_ADD:
case FIB_EVENT_NH_DEL:
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);
+ fib_event->fnh_info = *fnh_info;
+ fib_info_hold(fib_event->fnh_info.fib_nh->nh_parent);
break;
}
}
-static int mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work,
+static int mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event *fib_event,
struct fib_notifier_info *info)
{
struct fib6_entry_notifier_info *fen6_info;
int err;
- switch (fib_work->event) {
+ switch (fib_event->event) {
case FIB_EVENT_ENTRY_REPLACE:
case FIB_EVENT_ENTRY_APPEND:
case FIB_EVENT_ENTRY_DEL:
fen6_info = container_of(info, struct fib6_entry_notifier_info,
info);
- err = mlxsw_sp_router_fib6_work_init(&fib_work->fib6_work,
- fen6_info);
+ err = mlxsw_sp_router_fib6_event_init(&fib_event->fib6_event,
+ fen6_info);
if (err)
return err;
break;
}
static void
-mlxsw_sp_router_fibmr_event(struct mlxsw_sp_fib_event_work *fib_work,
+mlxsw_sp_router_fibmr_event(struct mlxsw_sp_fib_event *fib_event,
struct fib_notifier_info *info)
{
- switch (fib_work->event) {
+ switch (fib_event->event) {
case FIB_EVENT_ENTRY_REPLACE:
case FIB_EVENT_ENTRY_ADD:
case FIB_EVENT_ENTRY_DEL:
- memcpy(&fib_work->men_info, info, sizeof(fib_work->men_info));
- mr_cache_hold(fib_work->men_info.mfc);
+ memcpy(&fib_event->men_info, info, sizeof(fib_event->men_info));
+ mr_cache_hold(fib_event->men_info.mfc);
break;
case FIB_EVENT_VIF_ADD:
case FIB_EVENT_VIF_DEL:
- memcpy(&fib_work->ven_info, info, sizeof(fib_work->ven_info));
- dev_hold(fib_work->ven_info.dev);
+ memcpy(&fib_event->ven_info, info, sizeof(fib_event->ven_info));
+ dev_hold(fib_event->ven_info.dev);
break;
}
}
static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
unsigned long event, void *ptr)
{
- struct mlxsw_sp_fib_event_work *fib_work;
+ struct mlxsw_sp_fib_event *fib_event;
struct fib_notifier_info *info = ptr;
struct mlxsw_sp_router *router;
int err;
NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported");
return notifier_from_errno(-EINVAL);
}
- if (fen_info->fi->nh) {
- NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported");
- return notifier_from_errno(-EINVAL);
- }
- } else if (info->family == AF_INET6) {
- struct fib6_entry_notifier_info *fen6_info;
-
- fen6_info = container_of(info,
- struct fib6_entry_notifier_info,
- info);
- if (fen6_info->rt->nh) {
- NL_SET_ERR_MSG_MOD(info->extack, "IPv6 route with nexthop objects is not supported");
- return notifier_from_errno(-EINVAL);
- }
}
break;
}
- fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
- if (!fib_work)
+ fib_event = kzalloc(sizeof(*fib_event), GFP_ATOMIC);
+ if (!fib_event)
return NOTIFY_BAD;
- fib_work->mlxsw_sp = router->mlxsw_sp;
- fib_work->event = event;
+ fib_event->mlxsw_sp = router->mlxsw_sp;
+ fib_event->event = event;
+ fib_event->family = info->family;
switch (info->family) {
case AF_INET:
- INIT_WORK(&fib_work->work, mlxsw_sp_router_fib4_event_work);
- mlxsw_sp_router_fib4_event(fib_work, info);
+ mlxsw_sp_router_fib4_event(fib_event, info);
break;
case AF_INET6:
- INIT_WORK(&fib_work->work, mlxsw_sp_router_fib6_event_work);
- err = mlxsw_sp_router_fib6_event(fib_work, info);
+ err = mlxsw_sp_router_fib6_event(fib_event, info);
if (err)
goto err_fib_event;
break;
case RTNL_FAMILY_IP6MR:
case RTNL_FAMILY_IPMR:
- INIT_WORK(&fib_work->work, mlxsw_sp_router_fibmr_event_work);
- mlxsw_sp_router_fibmr_event(fib_work, info);
+ mlxsw_sp_router_fibmr_event(fib_event, info);
break;
}
- mlxsw_core_schedule_work(&fib_work->work);
+ /* Enqueue the event and trigger the work */
+ spin_lock_bh(&router->fib_event_queue_lock);
+ list_add_tail(&fib_event->list, &router->fib_event_queue);
+ spin_unlock_bh(&router->fib_event_queue_lock);
+ mlxsw_core_schedule_work(&router->fib_event_work);
return NOTIFY_DONE;
err_fib_event:
- kfree(fib_work);
+ kfree(fib_event);
return NOTIFY_BAD;
}
switch (event) {
case NETDEV_UP:
+ if (netif_is_bridge_master(l3_dev) && br_vlan_enabled(l3_dev)) {
+ u16 proto;
+
+ br_vlan_get_proto(l3_dev, &proto);
+ if (proto == ETH_P_8021AD) {
+ NL_SET_ERR_MSG_MOD(extack, "Adding an IP address to 802.1ad bridge is not supported");
+ return -EOPNOTSUPP;
+ }
+ }
rif = mlxsw_sp_rif_create(mlxsw_sp, ¶ms, extack);
if (IS_ERR(rif))
return PTR_ERR(rif);
mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
}
+static const struct mlxsw_sp_router_ll_ops mlxsw_sp_router_ll_basic_ops = {
+ .ralta_write = mlxsw_sp_router_ll_basic_ralta_write,
+ .ralst_write = mlxsw_sp_router_ll_basic_ralst_write,
+ .raltb_write = mlxsw_sp_router_ll_basic_raltb_write,
+ .fib_entry_op_ctx_size = sizeof(struct mlxsw_sp_fib_entry_op_ctx_basic),
+ .fib_entry_pack = mlxsw_sp_router_ll_basic_fib_entry_pack,
+ .fib_entry_act_remote_pack = mlxsw_sp_router_ll_basic_fib_entry_act_remote_pack,
+ .fib_entry_act_local_pack = mlxsw_sp_router_ll_basic_fib_entry_act_local_pack,
+ .fib_entry_act_ip2me_pack = mlxsw_sp_router_ll_basic_fib_entry_act_ip2me_pack,
+ .fib_entry_act_ip2me_tun_pack = mlxsw_sp_router_ll_basic_fib_entry_act_ip2me_tun_pack,
+ .fib_entry_commit = mlxsw_sp_router_ll_basic_fib_entry_commit,
+ .fib_entry_is_committed = mlxsw_sp_router_ll_basic_fib_entry_is_committed,
+};
+
+static int mlxsw_sp_router_ll_op_ctx_init(struct mlxsw_sp_router *router)
+{
+ size_t max_size = 0;
+ int i;
+
+ for (i = 0; i < MLXSW_SP_L3_PROTO_MAX; i++) {
+ size_t size = router->proto_ll_ops[i]->fib_entry_op_ctx_size;
+
+ if (size > max_size)
+ max_size = size;
+ }
+ router->ll_op_ctx = kzalloc(sizeof(*router->ll_op_ctx) + max_size,
+ GFP_KERNEL);
+ if (!router->ll_op_ctx)
+ return -ENOMEM;
+ INIT_LIST_HEAD(&router->ll_op_ctx->fib_entry_priv_list);
+ return 0;
+}
+
+static void mlxsw_sp_router_ll_op_ctx_fini(struct mlxsw_sp_router *router)
+{
+ WARN_ON(!list_empty(&router->ll_op_ctx->fib_entry_priv_list));
+ kfree(router->ll_op_ctx);
+}
+
+static int mlxsw_sp_lb_rif_init(struct mlxsw_sp *mlxsw_sp)
+{
+ u16 lb_rif_index;
+ int err;
+
+ /* Create a generic loopback RIF associated with the main table
+ * (default VRF). Any table can be used, but the main table exists
+ * anyway, so we do not waste resources.
+ */
+ err = mlxsw_sp_router_ul_rif_get(mlxsw_sp, RT_TABLE_MAIN,
+ &lb_rif_index);
+ if (err)
+ return err;
+
+ mlxsw_sp->router->lb_rif_index = lb_rif_index;
+
+ return 0;
+}
+
+static void mlxsw_sp_lb_rif_fini(struct mlxsw_sp *mlxsw_sp)
+{
+ mlxsw_sp_router_ul_rif_put(mlxsw_sp, mlxsw_sp->router->lb_rif_index);
+}
+
int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp,
struct netlink_ext_ack *extack)
{
mlxsw_sp->router = router;
router->mlxsw_sp = mlxsw_sp;
+ router->proto_ll_ops[MLXSW_SP_L3_PROTO_IPV4] = &mlxsw_sp_router_ll_basic_ops;
+ router->proto_ll_ops[MLXSW_SP_L3_PROTO_IPV6] = &mlxsw_sp_router_ll_basic_ops;
+
+ err = mlxsw_sp_router_ll_op_ctx_init(router);
+ if (err)
+ goto err_ll_op_ctx_init;
+
INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_neighs_list);
err = __mlxsw_sp_router_init(mlxsw_sp);
if (err)
if (err)
goto err_vrs_init;
+ err = mlxsw_sp_lb_rif_init(mlxsw_sp);
+ if (err)
+ goto err_lb_rif_init;
+
err = mlxsw_sp_neigh_init(mlxsw_sp);
if (err)
goto err_neigh_init;
if (err)
goto err_dscp_init;
+ INIT_WORK(&router->fib_event_work, mlxsw_sp_router_fib_event_work);
+ INIT_LIST_HEAD(&router->fib_event_queue);
+ spin_lock_init(&router->fib_event_queue_lock);
+
router->inetaddr_nb.notifier_call = mlxsw_sp_inetaddr_event;
err = register_inetaddr_notifier(&router->inetaddr_nb);
if (err)
if (err)
goto err_register_netevent_notifier;
+ mlxsw_sp->router->nexthop_nb.notifier_call =
+ mlxsw_sp_nexthop_obj_event;
+ err = register_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
+ &mlxsw_sp->router->nexthop_nb,
+ extack);
+ if (err)
+ goto err_register_nexthop_notifier;
+
mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event;
err = register_fib_notifier(mlxsw_sp_net(mlxsw_sp),
&mlxsw_sp->router->fib_nb,
return 0;
err_register_fib_notifier:
+ unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
+ &mlxsw_sp->router->nexthop_nb);
+err_register_nexthop_notifier:
unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb);
err_register_netevent_notifier:
unregister_inet6addr_notifier(&router->inet6addr_nb);
unregister_inetaddr_notifier(&router->inetaddr_nb);
err_register_inetaddr_notifier:
mlxsw_core_flush_owq();
+ WARN_ON(!list_empty(&router->fib_event_queue));
err_dscp_init:
err_mp_hash_init:
mlxsw_sp_neigh_fini(mlxsw_sp);
err_neigh_init:
+ mlxsw_sp_lb_rif_fini(mlxsw_sp);
+err_lb_rif_init:
mlxsw_sp_vrs_fini(mlxsw_sp);
err_vrs_init:
mlxsw_sp_mr_fini(mlxsw_sp);
err_rifs_init:
__mlxsw_sp_router_fini(mlxsw_sp);
err_router_init:
+ mlxsw_sp_router_ll_op_ctx_fini(router);
+err_ll_op_ctx_init:
mutex_destroy(&mlxsw_sp->router->lock);
kfree(mlxsw_sp->router);
return err;
{
unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp),
&mlxsw_sp->router->fib_nb);
+ unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
+ &mlxsw_sp->router->nexthop_nb);
unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb);
unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb);
unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb);
mlxsw_core_flush_owq();
+ WARN_ON(!list_empty(&mlxsw_sp->router->fib_event_queue));
mlxsw_sp_neigh_fini(mlxsw_sp);
+ mlxsw_sp_lb_rif_fini(mlxsw_sp);
mlxsw_sp_vrs_fini(mlxsw_sp);
mlxsw_sp_mr_fini(mlxsw_sp);
mlxsw_sp_lpm_fini(mlxsw_sp);
mlxsw_sp_ipips_fini(mlxsw_sp);
mlxsw_sp_rifs_fini(mlxsw_sp);
__mlxsw_sp_router_fini(mlxsw_sp);
+ mlxsw_sp_router_ll_op_ctx_fini(mlxsw_sp->router);
mutex_destroy(&mlxsw_sp->router->lock);
kfree(mlxsw_sp->router);
}
u8 valid:1;
};
+struct mlxsw_sp_fib_entry_op_ctx {
+ u8 bulk_ok:1, /* Indicate to the low-level op it is ok to bulk
+ * the actual entry with the one that is the next
+ * in queue.
+ */
+ initialized:1; /* Bit that the low-level op sets in case
+ * the context priv is initialized.
+ */
+ struct list_head fib_entry_priv_list;
+ unsigned long ll_priv[];
+};
+
+static inline void
+mlxsw_sp_fib_entry_op_ctx_clear(struct mlxsw_sp_fib_entry_op_ctx *op_ctx)
+{
+ WARN_ON_ONCE(!list_empty(&op_ctx->fib_entry_priv_list));
+ memset(op_ctx, 0, sizeof(*op_ctx));
+ INIT_LIST_HEAD(&op_ctx->fib_entry_priv_list);
+}
+
struct mlxsw_sp_router {
struct mlxsw_sp *mlxsw_sp;
struct mlxsw_sp_rif **rifs;
struct list_head nexthop_neighs_list;
struct list_head ipip_list;
bool aborted;
+ struct notifier_block nexthop_nb;
struct notifier_block fib_nb;
struct notifier_block netevent_nb;
struct notifier_block inetaddr_nb;
bool adj_discard_index_valid;
struct mlxsw_sp_router_nve_decap nve_decap_config;
struct mutex lock; /* Protects shared router resources */
+ struct work_struct fib_event_work;
+ struct list_head fib_event_queue;
+ spinlock_t fib_event_queue_lock; /* Protects fib event queue list */
+ /* One set of ops for each protocol: IPv4 and IPv6 */
+ const struct mlxsw_sp_router_ll_ops *proto_ll_ops[MLXSW_SP_L3_PROTO_MAX];
+ struct mlxsw_sp_fib_entry_op_ctx *ll_op_ctx;
+ u16 lb_rif_index;
+};
+
+struct mlxsw_sp_fib_entry_priv {
+ refcount_t refcnt;
+ struct list_head list; /* Member in op_ctx->fib_entry_priv_list */
+ unsigned long priv[];
+};
+
+enum mlxsw_sp_fib_entry_op {
+ MLXSW_SP_FIB_ENTRY_OP_WRITE,
+ MLXSW_SP_FIB_ENTRY_OP_UPDATE,
+ MLXSW_SP_FIB_ENTRY_OP_DELETE,
};
+/* Low-level router ops. Basically this is to handle the different
+ * register sets to work with ordinary and XM trees and FIB entries.
+ */
+struct mlxsw_sp_router_ll_ops {
+ int (*ralta_write)(struct mlxsw_sp *mlxsw_sp, char *xralta_pl);
+ int (*ralst_write)(struct mlxsw_sp *mlxsw_sp, char *xralst_pl);
+ int (*raltb_write)(struct mlxsw_sp *mlxsw_sp, char *xraltb_pl);
+ size_t fib_entry_op_ctx_size;
+ size_t fib_entry_priv_size;
+ void (*fib_entry_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ enum mlxsw_sp_l3proto proto, enum mlxsw_sp_fib_entry_op op,
+ u16 virtual_router, u8 prefix_len, unsigned char *addr,
+ struct mlxsw_sp_fib_entry_priv *priv);
+ void (*fib_entry_act_remote_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ enum mlxsw_reg_ralue_trap_action trap_action,
+ u16 trap_id, u32 adjacency_index, u16 ecmp_size);
+ void (*fib_entry_act_local_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ enum mlxsw_reg_ralue_trap_action trap_action,
+ u16 trap_id, u16 local_erif);
+ void (*fib_entry_act_ip2me_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx);
+ void (*fib_entry_act_ip2me_tun_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ u32 tunnel_ptr);
+ int (*fib_entry_commit)(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ bool *postponed_for_bulk);
+ bool (*fib_entry_is_committed)(struct mlxsw_sp_fib_entry_priv *priv);
+};
+
+int mlxsw_sp_fib_entry_commit(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry_op_ctx *op_ctx,
+ const struct mlxsw_sp_router_ll_ops *ll_ops);
+
struct mlxsw_sp_rif_ipip_lb;
struct mlxsw_sp_rif_ipip_lb_config {
enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt;
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);
+bool mlxsw_sp_nexthop_is_discard(const 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))
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;
+ const struct mlxsw_sp_bridge_ops *bridge_8021ad_ops;
};
struct mlxsw_sp_bridge_device {
bridge_device->mrouter = br_multicast_router(br_dev);
INIT_LIST_HEAD(&bridge_device->ports_list);
if (vlan_enabled) {
+ u16 proto;
+
bridge->vlan_enabled_exists = true;
- bridge_device->ops = bridge->bridge_8021q_ops;
+ br_vlan_get_proto(br_dev, &proto);
+ if (proto == ETH_P_8021AD)
+ bridge_device->ops = bridge->bridge_8021ad_ops;
+ else
+ bridge_device->ops = bridge->bridge_8021q_ops;
} else {
bridge_device->ops = bridge->bridge_8021d_ops;
}
return -EINVAL;
}
+static int mlxsw_sp_port_attr_br_vlan_proto_set(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct switchdev_trans *trans,
+ struct net_device *orig_dev,
+ u16 vlan_proto)
+{
+ 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;
+
+ bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, orig_dev);
+ if (WARN_ON(!bridge_device))
+ return -EINVAL;
+
+ netdev_err(bridge_device->dev, "VLAN protocol can't be changed on existing bridge\n");
+ return -EINVAL;
+}
+
static int mlxsw_sp_port_attr_mrouter_set(struct mlxsw_sp_port *mlxsw_sp_port,
struct switchdev_trans *trans,
struct net_device *orig_dev,
attr->orig_dev,
attr->u.vlan_filtering);
break;
+ case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL:
+ err = mlxsw_sp_port_attr_br_vlan_proto_set(mlxsw_sp_port, trans,
+ attr->orig_dev,
+ attr->u.vlan_protocol);
+ break;
case SWITCHDEV_ATTR_ID_PORT_MROUTER:
err = mlxsw_sp_port_attr_mrouter_set(mlxsw_sp_port, trans,
attr->orig_dev,
u16 pvid = mlxsw_sp_port_pvid_determine(mlxsw_sp_port, vid, is_pvid);
struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
u16 old_pvid = mlxsw_sp_port->pvid;
+ u16 proto;
int err;
/* The only valid scenario in which a port-vlan already exists, is if
if (err)
goto err_port_vlan_set;
- err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, pvid);
+ br_vlan_get_proto(bridge_port->bridge_device->dev, &proto);
+ err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, pvid, proto);
if (err)
goto err_port_pvid_set;
return 0;
err_port_vlan_bridge_join:
- mlxsw_sp_port_pvid_set(mlxsw_sp_port, old_pvid);
+ mlxsw_sp_port_pvid_set(mlxsw_sp_port, old_pvid, proto);
err_port_pvid_set:
mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
err_port_vlan_set:
{
u16 pvid = mlxsw_sp_port->pvid == vid ? 0 : mlxsw_sp_port->pvid;
struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
+ u16 proto;
mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
if (WARN_ON(!mlxsw_sp_port_vlan))
return;
mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
- mlxsw_sp_port_pvid_set(mlxsw_sp_port, pvid);
+ br_vlan_get_proto(bridge_port->bridge_device->dev, &proto);
+ mlxsw_sp_port_pvid_set(mlxsw_sp_port, pvid, proto);
mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
}
}
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 netlink_ext_ack *extack)
+mlxsw_sp_bridge_vlan_aware_port_join(struct mlxsw_sp_bridge_port *bridge_port,
+ struct mlxsw_sp_port *mlxsw_sp_port,
+ struct netlink_ext_ack *extack)
{
if (is_vlan_dev(bridge_port->dev)) {
NL_SET_ERR_MSG_MOD(extack, "Can not enslave a VLAN device to a VLAN-aware bridge");
return 0;
}
+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 netlink_ext_ack *extack)
+{
+ return mlxsw_sp_bridge_vlan_aware_port_join(bridge_port, mlxsw_sp_port,
+ extack);
+}
+
+static void
+mlxsw_sp_bridge_vlan_aware_port_leave(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ /* Make sure untagged frames are allowed to ingress */
+ mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID,
+ ETH_P_8021Q);
+}
+
static void
mlxsw_sp_bridge_8021q_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
struct mlxsw_sp_bridge_port *bridge_port,
struct mlxsw_sp_port *mlxsw_sp_port)
{
- /* Make sure untagged frames are allowed to ingress */
- mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
+ mlxsw_sp_bridge_vlan_aware_port_leave(mlxsw_sp_port);
}
static int
.fid_vid = mlxsw_sp_bridge_8021d_fid_vid,
};
+static int
+mlxsw_sp_bridge_8021ad_port_join(struct mlxsw_sp_bridge_device *bridge_device,
+ struct mlxsw_sp_bridge_port *bridge_port,
+ struct mlxsw_sp_port *mlxsw_sp_port,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ err = mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, true, false);
+ if (err)
+ return err;
+
+ err = mlxsw_sp_bridge_vlan_aware_port_join(bridge_port, mlxsw_sp_port,
+ extack);
+ if (err)
+ goto err_bridge_vlan_aware_port_join;
+
+ return 0;
+
+err_bridge_vlan_aware_port_join:
+ mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, false, true);
+ return err;
+}
+
+static void
+mlxsw_sp_bridge_8021ad_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
+ struct mlxsw_sp_bridge_port *bridge_port,
+ struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ mlxsw_sp_bridge_vlan_aware_port_leave(mlxsw_sp_port);
+ mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, false, true);
+}
+
+static int
+mlxsw_sp_bridge_8021ad_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device,
+ const struct net_device *vxlan_dev, u16 vid,
+ struct netlink_ext_ack *extack)
+{
+ NL_SET_ERR_MSG_MOD(extack, "VXLAN is not supported with 802.1ad");
+ return -EOPNOTSUPP;
+}
+
+static const struct mlxsw_sp_bridge_ops mlxsw_sp_bridge_8021ad_ops = {
+ .port_join = mlxsw_sp_bridge_8021ad_port_join,
+ .port_leave = mlxsw_sp_bridge_8021ad_port_leave,
+ .vxlan_join = mlxsw_sp_bridge_8021ad_vxlan_join,
+ .fid_get = mlxsw_sp_bridge_8021q_fid_get,
+ .fid_lookup = mlxsw_sp_bridge_8021q_fid_lookup,
+ .fid_vid = mlxsw_sp_bridge_8021q_fid_vid,
+};
+
int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port,
struct net_device *brport_dev,
struct net_device *br_dev,
bridge->bridge_8021q_ops = &mlxsw_sp_bridge_8021q_ops;
bridge->bridge_8021d_ops = &mlxsw_sp_bridge_8021d_ops;
+ bridge->bridge_8021ad_ops = &mlxsw_sp_bridge_8021ad_ops;
return mlxsw_sp_fdb_init(mlxsw_sp);
}
TRAP_TO_CPU),
MLXSW_SP_RXL_EXCEPTION(HOST_MISS_IPV6, L3_EXCEPTIONS,
TRAP_TO_CPU),
- MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER3, L3_EXCEPTIONS,
+ MLXSW_SP_RXL_EXCEPTION(RTR_EGRESS0, L3_EXCEPTIONS,
TRAP_EXCEPTION_TO_CPU),
},
},
false),
},
},
+ {
+ .trap = MLXSW_SP_TRAP_DROP(BLACKHOLE_NEXTHOP, L3_DROPS),
+ .listeners_arr = {
+ MLXSW_SP_RXL_DISCARD(ROUTER3, L3_DISCARDS),
+ },
+ },
};
static struct mlxsw_sp_trap_policer_item *
#include <linux/types.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
+#include <linux/ethtool.h>
#include <linux/etherdevice.h>
#include <linux/slab.h>
#include <linux/device.h>
MLXSW_TRAP_ID_RTR_INGRESS1 = 0x71,
MLXSW_TRAP_ID_IPV6_PIM = 0x79,
MLXSW_TRAP_ID_IPV6_VRRP = 0x7A,
+ MLXSW_TRAP_ID_RTR_EGRESS0 = 0x80,
MLXSW_TRAP_ID_IPV4_BGP = 0x88,
MLXSW_TRAP_ID_IPV6_BGP = 0x89,
MLXSW_TRAP_ID_L3_IPV6_ROUTER_SOLICITATION = 0x8A,
wol->supported = 0;
wol->wolopts = 0;
- phy_ethtool_get_wol(netdev->phydev, wol);
+
+ if (netdev->phydev)
+ phy_ethtool_get_wol(netdev->phydev, wol);
wol->supported |= WAKE_BCAST | WAKE_UCAST | WAKE_MCAST |
WAKE_MAGIC | WAKE_PHY | WAKE_ARP;
device_set_wakeup_enable(&adapter->pdev->dev, (bool)wol->wolopts);
- phy_ethtool_set_wol(netdev->phydev, wol);
-
- return 0;
+ return netdev->phydev ? phy_ethtool_set_wol(netdev->phydev, wol)
+ : -ENETDOWN;
}
#endif /* CONFIG_PM */
return result;
}
-static void lan743x_intr_software_isr(void *context)
+static void lan743x_intr_software_isr(struct lan743x_adapter *adapter)
{
- struct lan743x_adapter *adapter = context;
struct lan743x_intr *intr = &adapter->intr;
- u32 int_sts;
- int_sts = lan743x_csr_read(adapter, INT_STS);
- if (int_sts & INT_BIT_SW_GP_) {
- /* disable the interrupt to prevent repeated re-triggering */
- lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_SW_GP_);
- intr->software_isr_flag = 1;
- }
+ /* disable the interrupt to prevent repeated re-triggering */
+ lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_SW_GP_);
+ intr->software_isr_flag = true;
+ wake_up(&intr->software_isr_wq);
}
static void lan743x_tx_isr(void *context, u32 int_sts, u32 flags)
static int lan743x_intr_test_isr(struct lan743x_adapter *adapter)
{
struct lan743x_intr *intr = &adapter->intr;
- int result = -ENODEV;
- int timeout = 10;
+ int ret;
- intr->software_isr_flag = 0;
+ intr->software_isr_flag = false;
- /* enable interrupt */
+ /* enable and activate test interrupt */
lan743x_csr_write(adapter, INT_EN_SET, INT_BIT_SW_GP_);
-
- /* activate interrupt here */
lan743x_csr_write(adapter, INT_SET, INT_BIT_SW_GP_);
- while ((timeout > 0) && (!(intr->software_isr_flag))) {
- usleep_range(1000, 20000);
- timeout--;
- }
- if (intr->software_isr_flag)
- result = 0;
+ ret = wait_event_timeout(intr->software_isr_wq,
+ intr->software_isr_flag,
+ msecs_to_jiffies(200));
- /* disable interrupts */
+ /* disable test interrupt */
lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_SW_GP_);
- return result;
+
+ return ret > 0 ? 0 : -ENODEV;
}
static int lan743x_intr_register_isr(struct lan743x_adapter *adapter,
flags |= LAN743X_VECTOR_FLAG_SOURCE_ENABLE_R2C;
}
+ init_waitqueue_head(&intr->software_isr_wq);
+
ret = lan743x_intr_register_isr(adapter, 0, flags,
INT_BIT_ALL_RX_ | INT_BIT_ALL_TX_ |
INT_BIT_ALL_OTHER_,
static int lan743x_mac_open(struct lan743x_adapter *adapter)
{
- int ret = 0;
u32 temp;
temp = lan743x_csr_read(adapter, MAC_RX);
lan743x_csr_write(adapter, MAC_RX, temp | MAC_RX_RXEN_);
temp = lan743x_csr_read(adapter, MAC_TX);
lan743x_csr_write(adapter, MAC_TX, temp | MAC_TX_TXEN_);
- return ret;
+ return 0;
}
static void lan743x_mac_close(struct lan743x_adapter *adapter)
data = lan743x_csr_read(adapter, MAC_CR);
/* set interface mode */
- if (phy_interface_mode_is_rgmii(adapter->phy_mode))
+ if (phy_interface_is_rgmii(phydev))
/* RGMII */
data &= ~MAC_CR_MII_EN_;
else
static int lan743x_phy_open(struct lan743x_adapter *adapter)
{
+ struct net_device *netdev = adapter->netdev;
struct lan743x_phy *phy = &adapter->phy;
- struct phy_device *phydev = NULL;
- struct device_node *phynode;
- struct net_device *netdev;
+ struct phy_device *phydev;
int ret = -EIO;
- netdev = adapter->netdev;
- phynode = of_node_get(adapter->pdev->dev.of_node);
-
- if (phynode) {
- /* try devicetree phy, or fixed link */
- of_get_phy_mode(phynode, &adapter->phy_mode);
-
- if (of_phy_is_fixed_link(phynode)) {
- ret = of_phy_register_fixed_link(phynode);
- if (ret) {
- netdev_err(netdev,
- "cannot register fixed PHY\n");
- of_node_put(phynode);
- goto return_error;
- }
- }
- phydev = of_phy_connect(netdev, phynode,
- lan743x_phy_link_status_change, 0,
- adapter->phy_mode);
- of_node_put(phynode);
- }
+ /* try devicetree phy, or fixed link */
+ phydev = of_phy_get_and_connect(netdev, adapter->pdev->dev.of_node,
+ lan743x_phy_link_status_change);
if (!phydev) {
/* try internal phy */
if (!phydev)
goto return_error;
- adapter->phy_mode = PHY_INTERFACE_MODE_GMII;
ret = phy_connect_direct(netdev, phydev,
lan743x_phy_link_status_change,
- adapter->phy_mode);
+ PHY_INTERFACE_MODE_GMII);
if (ret)
goto return_error;
}
phy_start(phydev);
phy_start_aneg(phydev);
+ phy_attached_info(phydev);
return 0;
return_error:
int number_of_vectors;
bool using_vectors;
- int software_isr_flag;
+ bool software_isr_flag;
+ wait_queue_head_t software_isr_wq;
};
#define LAN743X_MAX_FRAME_SIZE (9 * 1024)
struct lan743x_adapter {
struct net_device *netdev;
struct mii_bus *mdiobus;
- phy_interface_t phy_mode;
int msg_enable;
#ifdef CONFIG_PM
u32 wolopts;
return ocelot_vlant_wait_for_completion(ocelot);
}
-static int ocelot_port_set_native_vlan(struct ocelot *ocelot, int port,
- u16 vid)
+static void ocelot_port_set_native_vlan(struct ocelot *ocelot, int port,
+ struct ocelot_vlan native_vlan)
{
struct ocelot_port *ocelot_port = ocelot->ports[port];
u32 val = 0;
- if (ocelot_port->vid != vid) {
- /* Always permit deleting the native VLAN (vid = 0) */
- if (ocelot_port->vid && vid) {
- dev_err(ocelot->dev,
- "Port already has a native VLAN: %d\n",
- ocelot_port->vid);
- return -EBUSY;
- }
- ocelot_port->vid = vid;
- }
+ ocelot_port->native_vlan = native_vlan;
- ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(vid),
+ ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(native_vlan.vid),
REW_PORT_VLAN_CFG_PORT_VID_M,
REW_PORT_VLAN_CFG, port);
- if (ocelot_port->vlan_aware && !ocelot_port->vid)
- /* If port is vlan-aware and tagged, drop untagged and priority
- * tagged frames.
- */
- val = ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA |
- ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
- ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA;
- ocelot_rmw_gix(ocelot, val,
- ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA |
- ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
- ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA,
- ANA_PORT_DROP_CFG, port);
-
if (ocelot_port->vlan_aware) {
- if (ocelot_port->vid)
+ if (native_vlan.valid)
/* Tag all frames except when VID == DEFAULT_VLAN */
val = REW_TAG_CFG_TAG_CFG(1);
else
ocelot_rmw_gix(ocelot, val,
REW_TAG_CFG_TAG_CFG_M,
REW_TAG_CFG, port);
+}
- return 0;
+/* Default vlan to clasify for untagged frames (may be zero) */
+static void ocelot_port_set_pvid(struct ocelot *ocelot, int port,
+ struct ocelot_vlan pvid_vlan)
+{
+ struct ocelot_port *ocelot_port = ocelot->ports[port];
+ u32 val = 0;
+
+ ocelot_port->pvid_vlan = pvid_vlan;
+
+ if (!ocelot_port->vlan_aware)
+ pvid_vlan.vid = 0;
+
+ ocelot_rmw_gix(ocelot,
+ ANA_PORT_VLAN_CFG_VLAN_VID(pvid_vlan.vid),
+ ANA_PORT_VLAN_CFG_VLAN_VID_M,
+ ANA_PORT_VLAN_CFG, port);
+
+ /* If there's no pvid, we should drop not only untagged traffic (which
+ * happens automatically), but also 802.1p traffic which gets
+ * classified to VLAN 0, but that is always in our RX filter, so it
+ * would get accepted were it not for this setting.
+ */
+ if (!pvid_vlan.valid && ocelot_port->vlan_aware)
+ val = ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
+ ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA;
+
+ ocelot_rmw_gix(ocelot, val,
+ ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
+ ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA,
+ ANA_PORT_DROP_CFG, port);
}
int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M,
ANA_PORT_VLAN_CFG, port);
- ocelot_port_set_native_vlan(ocelot, port, ocelot_port->vid);
+ ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan);
+ ocelot_port_set_native_vlan(ocelot, port, ocelot_port->native_vlan);
return 0;
}
EXPORT_SYMBOL(ocelot_port_vlan_filtering);
-/* Default vlan to clasify for untagged frames (may be zero) */
-static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, u16 pvid)
+int ocelot_vlan_prepare(struct ocelot *ocelot, int port, u16 vid, bool pvid,
+ bool untagged)
{
struct ocelot_port *ocelot_port = ocelot->ports[port];
- ocelot_rmw_gix(ocelot,
- ANA_PORT_VLAN_CFG_VLAN_VID(pvid),
- ANA_PORT_VLAN_CFG_VLAN_VID_M,
- ANA_PORT_VLAN_CFG, port);
+ /* Deny changing the native VLAN, but always permit deleting it */
+ if (untagged && ocelot_port->native_vlan.vid != vid &&
+ ocelot_port->native_vlan.valid) {
+ dev_err(ocelot->dev,
+ "Port already has a native VLAN: %d\n",
+ ocelot_port->native_vlan.vid);
+ return -EBUSY;
+ }
- ocelot_port->pvid = pvid;
+ return 0;
}
+EXPORT_SYMBOL(ocelot_vlan_prepare);
int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
bool untagged)
return ret;
/* Default ingress vlan classification */
- if (pvid)
- ocelot_port_set_pvid(ocelot, port, vid);
+ if (pvid) {
+ struct ocelot_vlan pvid_vlan;
+
+ pvid_vlan.vid = vid;
+ pvid_vlan.valid = true;
+ ocelot_port_set_pvid(ocelot, port, pvid_vlan);
+ }
/* Untagged egress vlan clasification */
if (untagged) {
- ret = ocelot_port_set_native_vlan(ocelot, port, vid);
- if (ret)
- return ret;
+ struct ocelot_vlan native_vlan;
+
+ native_vlan.vid = vid;
+ native_vlan.valid = true;
+ ocelot_port_set_native_vlan(ocelot, port, native_vlan);
}
return 0;
return ret;
/* Ingress */
- if (ocelot_port->pvid == vid)
- ocelot_port_set_pvid(ocelot, port, 0);
+ if (ocelot_port->pvid_vlan.vid == vid) {
+ struct ocelot_vlan pvid_vlan = {0};
+
+ ocelot_port_set_pvid(ocelot, port, pvid_vlan);
+ }
/* Egress */
- if (ocelot_port->vid == vid)
- ocelot_port_set_native_vlan(ocelot, port, 0);
+ if (ocelot_port->native_vlan.vid == vid) {
+ struct ocelot_vlan native_vlan = {0};
+
+ ocelot_port_set_native_vlan(ocelot, port, native_vlan);
+ }
return 0;
}
int ocelot_fdb_add(struct ocelot *ocelot, int port,
const unsigned char *addr, u16 vid)
{
- struct ocelot_port *ocelot_port = ocelot->ports[port];
int pgid = port;
if (port == ocelot->npi)
pgid = PGID_CPU;
- if (!vid) {
- if (!ocelot_port->vlan_aware)
- /* If the bridge is not VLAN aware and no VID was
- * provided, set it to pvid to ensure the MAC entry
- * matches incoming untagged packets
- */
- vid = ocelot_port->pvid;
- else
- /* If the bridge is VLAN aware a VID must be provided as
- * otherwise the learnt entry wouldn't match any frame.
- */
- return -EINVAL;
- }
-
return ocelot_mact_learn(ocelot, pgid, addr, vid, ENTRYTYPE_LOCKED);
}
EXPORT_SYMBOL(ocelot_fdb_add);
return ENTRYTYPE_MACv4;
if (addr[0] == 0x33 && addr[1] == 0x33)
return ENTRYTYPE_MACv6;
- return ENTRYTYPE_NORMAL;
+ return ENTRYTYPE_LOCKED;
+}
+
+static struct ocelot_pgid *ocelot_pgid_alloc(struct ocelot *ocelot, int index,
+ unsigned long ports)
+{
+ struct ocelot_pgid *pgid;
+
+ pgid = kzalloc(sizeof(*pgid), GFP_KERNEL);
+ if (!pgid)
+ return ERR_PTR(-ENOMEM);
+
+ pgid->ports = ports;
+ pgid->index = index;
+ refcount_set(&pgid->refcount, 1);
+ list_add_tail(&pgid->list, &ocelot->pgids);
+
+ return pgid;
+}
+
+static void ocelot_pgid_free(struct ocelot *ocelot, struct ocelot_pgid *pgid)
+{
+ if (!refcount_dec_and_test(&pgid->refcount))
+ return;
+
+ list_del(&pgid->list);
+ kfree(pgid);
}
-static int ocelot_mdb_get_pgid(struct ocelot *ocelot,
- enum macaccess_entry_type entry_type)
+static struct ocelot_pgid *ocelot_mdb_get_pgid(struct ocelot *ocelot,
+ const struct ocelot_multicast *mc)
{
- int pgid;
+ struct ocelot_pgid *pgid;
+ int index;
/* According to VSC7514 datasheet 3.9.1.5 IPv4 Multicast Entries and
* 3.9.1.6 IPv6 Multicast Entries, "Instead of a lookup in the
* destination mask table (PGID), the destination set is programmed as
* part of the entry MAC address.", and the DEST_IDX is set to 0.
*/
- if (entry_type == ENTRYTYPE_MACv4 ||
- entry_type == ENTRYTYPE_MACv6)
- return 0;
+ if (mc->entry_type == ENTRYTYPE_MACv4 ||
+ mc->entry_type == ENTRYTYPE_MACv6)
+ return ocelot_pgid_alloc(ocelot, 0, mc->ports);
- for_each_nonreserved_multicast_dest_pgid(ocelot, pgid) {
- struct ocelot_multicast *mc;
+ list_for_each_entry(pgid, &ocelot->pgids, list) {
+ /* When searching for a nonreserved multicast PGID, ignore the
+ * dummy PGID of zero that we have for MACv4/MACv6 entries
+ */
+ if (pgid->index && pgid->ports == mc->ports) {
+ refcount_inc(&pgid->refcount);
+ return pgid;
+ }
+ }
+
+ /* Search for a free index in the nonreserved multicast PGID area */
+ for_each_nonreserved_multicast_dest_pgid(ocelot, index) {
bool used = false;
- list_for_each_entry(mc, &ocelot->multicast, list) {
- if (mc->pgid == pgid) {
+ list_for_each_entry(pgid, &ocelot->pgids, list) {
+ if (pgid->index == index) {
used = true;
break;
}
}
if (!used)
- return pgid;
+ return ocelot_pgid_alloc(ocelot, index, mc->ports);
}
- return -1;
+ return ERR_PTR(-ENOSPC);
}
static void ocelot_encode_ports_to_mdb(unsigned char *addr,
- struct ocelot_multicast *mc,
- enum macaccess_entry_type entry_type)
+ struct ocelot_multicast *mc)
{
- memcpy(addr, mc->addr, ETH_ALEN);
+ ether_addr_copy(addr, mc->addr);
- if (entry_type == ENTRYTYPE_MACv4) {
+ if (mc->entry_type == ENTRYTYPE_MACv4) {
addr[0] = 0;
addr[1] = mc->ports >> 8;
addr[2] = mc->ports & 0xff;
- } else if (entry_type == ENTRYTYPE_MACv6) {
+ } else if (mc->entry_type == ENTRYTYPE_MACv6) {
addr[0] = mc->ports >> 8;
addr[1] = mc->ports & 0xff;
}
int ocelot_port_mdb_add(struct ocelot *ocelot, int port,
const struct switchdev_obj_port_mdb *mdb)
{
- struct ocelot_port *ocelot_port = ocelot->ports[port];
- enum macaccess_entry_type entry_type;
unsigned char addr[ETH_ALEN];
struct ocelot_multicast *mc;
+ struct ocelot_pgid *pgid;
u16 vid = mdb->vid;
- bool new = false;
if (port == ocelot->npi)
port = ocelot->num_phys_ports;
- if (!vid)
- vid = ocelot_port->pvid;
-
- entry_type = ocelot_classify_mdb(mdb->addr);
-
mc = ocelot_multicast_get(ocelot, mdb->addr, vid);
if (!mc) {
- int pgid = ocelot_mdb_get_pgid(ocelot, entry_type);
-
- if (pgid < 0) {
- dev_err(ocelot->dev,
- "No more PGIDs available for mdb %pM vid %d\n",
- mdb->addr, vid);
- return -ENOSPC;
- }
-
+ /* New entry */
mc = devm_kzalloc(ocelot->dev, sizeof(*mc), GFP_KERNEL);
if (!mc)
return -ENOMEM;
- memcpy(mc->addr, mdb->addr, ETH_ALEN);
+ mc->entry_type = ocelot_classify_mdb(mdb->addr);
+ ether_addr_copy(mc->addr, mdb->addr);
mc->vid = vid;
- mc->pgid = pgid;
list_add_tail(&mc->list, &ocelot->multicast);
- new = true;
- }
-
- if (!new) {
- ocelot_encode_ports_to_mdb(addr, mc, entry_type);
+ } else {
+ /* Existing entry. Clean up the current port mask from
+ * hardware now, because we'll be modifying it.
+ */
+ ocelot_pgid_free(ocelot, mc->pgid);
+ ocelot_encode_ports_to_mdb(addr, mc);
ocelot_mact_forget(ocelot, addr, vid);
}
mc->ports |= BIT(port);
- ocelot_encode_ports_to_mdb(addr, mc, entry_type);
- return ocelot_mact_learn(ocelot, mc->pgid, addr, vid, entry_type);
+ pgid = ocelot_mdb_get_pgid(ocelot, mc);
+ if (IS_ERR(pgid)) {
+ dev_err(ocelot->dev,
+ "Cannot allocate PGID for mdb %pM vid %d\n",
+ mc->addr, mc->vid);
+ devm_kfree(ocelot->dev, mc);
+ return PTR_ERR(pgid);
+ }
+ mc->pgid = pgid;
+
+ ocelot_encode_ports_to_mdb(addr, mc);
+
+ if (mc->entry_type != ENTRYTYPE_MACv4 &&
+ mc->entry_type != ENTRYTYPE_MACv6)
+ ocelot_write_rix(ocelot, pgid->ports, ANA_PGID_PGID,
+ pgid->index);
+
+ return ocelot_mact_learn(ocelot, pgid->index, addr, vid,
+ mc->entry_type);
}
EXPORT_SYMBOL(ocelot_port_mdb_add);
int ocelot_port_mdb_del(struct ocelot *ocelot, int port,
const struct switchdev_obj_port_mdb *mdb)
{
- struct ocelot_port *ocelot_port = ocelot->ports[port];
- enum macaccess_entry_type entry_type;
unsigned char addr[ETH_ALEN];
struct ocelot_multicast *mc;
+ struct ocelot_pgid *pgid;
u16 vid = mdb->vid;
if (port == ocelot->npi)
port = ocelot->num_phys_ports;
- if (!vid)
- vid = ocelot_port->pvid;
-
mc = ocelot_multicast_get(ocelot, mdb->addr, vid);
if (!mc)
return -ENOENT;
- entry_type = ocelot_classify_mdb(mdb->addr);
-
- ocelot_encode_ports_to_mdb(addr, mc, entry_type);
+ ocelot_encode_ports_to_mdb(addr, mc);
ocelot_mact_forget(ocelot, addr, vid);
+ ocelot_pgid_free(ocelot, mc->pgid);
mc->ports &= ~BIT(port);
if (!mc->ports) {
list_del(&mc->list);
return 0;
}
- ocelot_encode_ports_to_mdb(addr, mc, entry_type);
+ /* We have a PGID with fewer ports now */
+ pgid = ocelot_mdb_get_pgid(ocelot, mc);
+ if (IS_ERR(pgid))
+ return PTR_ERR(pgid);
+ mc->pgid = pgid;
+
+ ocelot_encode_ports_to_mdb(addr, mc);
+
+ if (mc->entry_type != ENTRYTYPE_MACv4 &&
+ mc->entry_type != ENTRYTYPE_MACv6)
+ ocelot_write_rix(ocelot, pgid->ports, ANA_PGID_PGID,
+ pgid->index);
- return ocelot_mact_learn(ocelot, mc->pgid, addr, vid, entry_type);
+ return ocelot_mact_learn(ocelot, pgid->index, addr, vid,
+ mc->entry_type);
}
EXPORT_SYMBOL(ocelot_port_mdb_del);
int ocelot_port_bridge_leave(struct ocelot *ocelot, int port,
struct net_device *bridge)
{
+ struct ocelot_vlan pvid = {0}, native_vlan = {0};
struct switchdev_trans trans;
int ret;
if (ret)
return ret;
- ocelot_port_set_pvid(ocelot, port, 0);
- return ocelot_port_set_native_vlan(ocelot, port, 0);
+ ocelot_port_set_pvid(ocelot, port, pvid);
+ ocelot_port_set_native_vlan(ocelot, port, native_vlan);
+
+ return 0;
}
EXPORT_SYMBOL(ocelot_port_bridge_leave);
return -ENOMEM;
INIT_LIST_HEAD(&ocelot->multicast);
+ INIT_LIST_HEAD(&ocelot->pgids);
ocelot_mact_init(ocelot);
ocelot_vlan_init(ocelot);
ocelot_vcap_init(ocelot);
u32 timestamp; /* rew_val */
};
-struct ocelot_multicast {
- struct list_head list;
- unsigned char addr[ETH_ALEN];
- u16 vid;
- u16 ports;
- int pgid;
-};
-
struct ocelot_port_tc {
bool block_shared;
unsigned long offload_cnt;
ENTRYTYPE_MACv6,
};
+/* A (PGID) port mask structure, encoding the 2^ocelot->num_phys_ports
+ * possibilities of egress port masks for L2 multicast traffic.
+ * For a switch with 9 user ports, there are 512 possible port masks, but the
+ * hardware only has 46 individual PGIDs that it can forward multicast traffic
+ * to. So we need a structure that maps the limited PGID indices to the port
+ * destinations requested by the user for L2 multicast.
+ */
+struct ocelot_pgid {
+ unsigned long ports;
+ int index;
+ refcount_t refcount;
+ struct list_head list;
+};
+
+struct ocelot_multicast {
+ struct list_head list;
+ enum macaccess_entry_type entry_type;
+ unsigned char addr[ETH_ALEN];
+ u16 vid;
+ u16 ports;
+ struct ocelot_pgid *pgid;
+};
+
int ocelot_port_fdb_do_dump(const unsigned char *addr, u16 vid,
bool is_static, void *data);
int ocelot_mact_learn(struct ocelot *ocelot, int port,
ocelot_adjust_link(ocelot, port, dev->phydev);
}
+static int ocelot_vlan_vid_prepare(struct net_device *dev, u16 vid, bool pvid,
+ bool untagged)
+{
+ struct ocelot_port_private *priv = netdev_priv(dev);
+ struct ocelot_port *ocelot_port = &priv->port;
+ struct ocelot *ocelot = ocelot_port->ocelot;
+ int port = priv->chip_port;
+
+ return ocelot_vlan_prepare(ocelot, port, vid, pvid, untagged);
+}
+
static int ocelot_vlan_vid_add(struct net_device *dev, u16 vid, bool pvid,
bool untagged)
{
struct ocelot_port *ocelot_port = &priv->port;
struct ocelot *ocelot = ocelot_port->ocelot;
- return ocelot_mact_forget(ocelot, addr, ocelot_port->pvid);
+ return ocelot_mact_forget(ocelot, addr, ocelot_port->pvid_vlan.vid);
}
static int ocelot_mc_sync(struct net_device *dev, const unsigned char *addr)
struct ocelot_port *ocelot_port = &priv->port;
struct ocelot *ocelot = ocelot_port->ocelot;
- return ocelot_mact_learn(ocelot, PGID_CPU, addr, ocelot_port->pvid,
- ENTRYTYPE_LOCKED);
+ return ocelot_mact_learn(ocelot, PGID_CPU, addr,
+ ocelot_port->pvid_vlan.vid, ENTRYTYPE_LOCKED);
}
static void ocelot_set_rx_mode(struct net_device *dev)
const struct sockaddr *addr = p;
/* Learn the new net device MAC address in the mac table. */
- ocelot_mact_learn(ocelot, PGID_CPU, addr->sa_data, ocelot_port->pvid,
- ENTRYTYPE_LOCKED);
+ ocelot_mact_learn(ocelot, PGID_CPU, addr->sa_data,
+ ocelot_port->pvid_vlan.vid, ENTRYTYPE_LOCKED);
/* Then forget the previous one. */
- ocelot_mact_forget(ocelot, dev->dev_addr, ocelot_port->pvid);
+ ocelot_mact_forget(ocelot, dev->dev_addr, ocelot_port->pvid_vlan.vid);
ether_addr_copy(dev->dev_addr, addr->sa_data);
return 0;
u16 vid;
for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
- ret = ocelot_vlan_vid_add(dev, vid,
- vlan->flags & BRIDGE_VLAN_INFO_PVID,
- vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED);
+ bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+ bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+
+ if (switchdev_trans_ph_prepare(trans))
+ ret = ocelot_vlan_vid_prepare(dev, vid, pvid,
+ untagged);
+ else
+ ret = ocelot_vlan_vid_add(dev, vid, pvid, untagged);
if (ret)
return ret;
}
memcpy(dev->dev_addr, ocelot->base_mac, ETH_ALEN);
dev->dev_addr[ETH_ALEN - 1] += port;
- ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, ocelot_port->pvid,
- ENTRYTYPE_LOCKED);
+ ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr,
+ ocelot_port->pvid_vlan.vid, ENTRYTYPE_LOCKED);
ocelot_init_port(ocelot, port);
* '-1' on failure
*/
-static int init_tti(struct s2io_nic *nic, int link)
+static int init_tti(struct s2io_nic *nic, int link, bool may_sleep)
{
struct XENA_dev_config __iomem *bar0 = nic->bar0;
register u64 val64 = 0;
if (wait_for_cmd_complete(&bar0->tti_command_mem,
TTI_CMD_MEM_STROBE_NEW_CMD,
- S2IO_BIT_RESET) != SUCCESS)
+ S2IO_BIT_RESET, may_sleep) != SUCCESS)
return FAILURE;
}
*/
/* Initialize TTI */
- if (SUCCESS != init_tti(nic, nic->last_link_state))
+ if (SUCCESS != init_tti(nic, nic->last_link_state, true))
return -ENODEV;
/* RTI Initialization */
*/
static int wait_for_cmd_complete(void __iomem *addr, u64 busy_bit,
- int bit_state)
+ int bit_state, bool may_sleep)
{
int ret = FAILURE, cnt = 0, delay = 1;
u64 val64;
}
}
- if (in_interrupt())
+ if (!may_sleep)
mdelay(delay);
else
msleep(delay);
* Return value:
* void.
*/
-
-static void s2io_set_multicast(struct net_device *dev)
+static void s2io_set_multicast(struct net_device *dev, bool may_sleep)
{
int i, j, prev_cnt;
struct netdev_hw_addr *ha;
/* Wait till command completes */
wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING,
- S2IO_BIT_RESET);
+ S2IO_BIT_RESET, may_sleep);
sp->m_cast_flg = 1;
sp->all_multi_pos = config->max_mc_addr - 1;
/* Wait till command completes */
wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING,
- S2IO_BIT_RESET);
+ S2IO_BIT_RESET, may_sleep);
sp->m_cast_flg = 0;
sp->all_multi_pos = 0;
/* Wait for command completes */
if (wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING,
- S2IO_BIT_RESET)) {
+ S2IO_BIT_RESET, may_sleep)) {
DBG_PRINT(ERR_DBG,
"%s: Adding Multicasts failed\n",
dev->name);
/* Wait for command completes */
if (wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING,
- S2IO_BIT_RESET)) {
+ S2IO_BIT_RESET, may_sleep)) {
DBG_PRINT(ERR_DBG,
"%s: Adding Multicasts failed\n",
dev->name);
}
}
+/* NDO wrapper for s2io_set_multicast */
+static void s2io_ndo_set_multicast(struct net_device *dev)
+{
+ s2io_set_multicast(dev, false);
+}
+
/* read from CAM unicast & multicast addresses and store it in
* def_mac_addr structure
*/
/* Wait till command completes */
if (wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING,
- S2IO_BIT_RESET)) {
+ S2IO_BIT_RESET, true)) {
DBG_PRINT(INFO_DBG, "do_s2io_add_mac failed\n");
return FAILURE;
}
/* Wait till command completes */
if (wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING,
- S2IO_BIT_RESET)) {
+ S2IO_BIT_RESET, true)) {
DBG_PRINT(INFO_DBG, "do_s2io_read_unicast_mc failed\n");
return FAILURE;
}
}
/* Setting its receive mode */
- s2io_set_multicast(dev);
+ s2io_set_multicast(dev, true);
if (dev->features & NETIF_F_LRO) {
/* Initialize max aggregatable pkts per session based on MTU */
struct swStat *swstats = &sp->mac_control.stats_info->sw_stat;
if (link != sp->last_link_state) {
- init_tti(sp, link);
+ init_tti(sp, link, false);
if (link == LINK_DOWN) {
DBG_PRINT(ERR_DBG, "%s: Link down\n", dev->name);
s2io_stop_all_tx_queue(sp);
return wait_for_cmd_complete(&bar0->rts_ds_mem_ctrl,
RTS_DS_MEM_CTRL_STROBE_CMD_BEING_EXECUTED,
- S2IO_BIT_RESET);
+ S2IO_BIT_RESET, true);
}
static const struct net_device_ops s2io_netdev_ops = {
.ndo_get_stats = s2io_get_stats,
.ndo_start_xmit = s2io_xmit,
.ndo_validate_addr = eth_validate_addr,
- .ndo_set_rx_mode = s2io_set_multicast,
+ .ndo_set_rx_mode = s2io_ndo_set_multicast,
.ndo_do_ioctl = s2io_ioctl,
.ndo_set_mac_address = s2io_set_mac_addr,
.ndo_change_mtu = s2io_change_mtu,
writeq(val64, &bar0->rmac_addr_cmd_mem);
wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING,
- S2IO_BIT_RESET);
+ S2IO_BIT_RESET, true);
tmp64 = readq(&bar0->rmac_addr_data0_mem);
mac_down = (u32)tmp64;
mac_up = (u32) (tmp64 >> 32);
static void s2io_handle_errors(void * dev_id);
static void s2io_tx_watchdog(struct net_device *dev, unsigned int txqueue);
-static void s2io_set_multicast(struct net_device *dev);
+static void s2io_set_multicast(struct net_device *dev, bool may_sleep);
static int rx_osm_handler(struct ring_info *ring_data, struct RxD_t * rxdp);
static void s2io_link(struct s2io_nic * sp, int link);
static void s2io_reset(struct s2io_nic * sp);
static void s2io_card_down(struct s2io_nic *nic);
static int s2io_card_up(struct s2io_nic *nic);
static int wait_for_cmd_complete(void __iomem *addr, u64 busy_bit,
- int bit_state);
+ int bit_state, bool may_sleep);
static int s2io_add_isr(struct s2io_nic * sp);
static void s2io_rem_isr(struct s2io_nic * sp);
list_for_each_safe(p, n, &blockpool->free_entry_list) {
list_del(&((struct __vxge_hw_blockpool_entry *)p)->item);
- kfree((void *)p);
+ kfree(p);
}
return;
ipv6 = true;
break;
}
-#endif
fallthrough;
+#endif
case AF_INET:
req_sz = sizeof(struct nfp_crypto_req_add_v4);
ipv6 = false;
struct devlink_flash_update_params *params,
struct netlink_ext_ack *extack)
{
- return nfp_flash_update_common(devlink_priv(devlink), params->file_name, extack);
+ return nfp_flash_update_common(devlink_priv(devlink), params->fw, extack);
}
const struct devlink_ops nfp_devlink_ops = {
return nfp_pcie_sriov_enable(pdev, num_vfs);
}
-int nfp_flash_update_common(struct nfp_pf *pf, const char *path,
+int nfp_flash_update_common(struct nfp_pf *pf, const struct firmware *fw,
struct netlink_ext_ack *extack)
{
struct device *dev = &pf->pdev->dev;
- const struct firmware *fw;
struct nfp_nsp *nsp;
int err;
return err;
}
- err = request_firmware_direct(&fw, path, dev);
- if (err) {
- NL_SET_ERR_MSG_MOD(extack,
- "unable to read flash file from disk");
- goto exit_close_nsp;
- }
-
- dev_info(dev, "Please be patient while writing flash image: %s\n",
- path);
-
err = nfp_nsp_write_flash(nsp, fw);
if (err < 0)
- goto exit_release_fw;
+ goto exit_close_nsp;
dev_info(dev, "Finished writing flash image\n");
err = 0;
-exit_release_fw:
- release_firmware(fw);
exit_close_nsp:
nfp_nsp_close(nsp);
return err;
}
pf->cpp = nfp_cpp_from_nfp6000_pcie(pdev);
- if (IS_ERR_OR_NULL(pf->cpp)) {
+ if (IS_ERR(pf->cpp)) {
err = PTR_ERR(pf->cpp);
- if (err >= 0)
- err = -ENOMEM;
goto err_disable_msix;
}
unsigned int min_size, struct nfp_cpp_area **area);
int nfp_mbox_cmd(struct nfp_pf *pf, u32 cmd, void *in_data, u64 in_length,
void *out_data, u64 out_length);
-int nfp_flash_update_common(struct nfp_pf *pf, const char *path,
+int nfp_flash_update_common(struct nfp_pf *pf, const struct firmware *fw,
struct netlink_ext_ack *extack);
enum nfp_dump_diag {
struct fe_priv *np = get_nvpriv(dev);
if (!(np->msi_flags & NV_MSI_X_ENABLED) ||
- ((np->msi_flags & NV_MSI_X_ENABLED) &&
- ((np->msi_flags & NV_MSI_X_VECTORS_MASK) == 0x1)))
+ ((np->msi_flags & NV_MSI_X_VECTORS_MASK) == 0x1))
return 0;
else
return 1;
struct fe_priv *np = netdev_priv(dev);
u8 __iomem *base = get_hwbase(dev);
- /* If it happens that this is run in top-half context, then
- * replace the spin_lock of hwstats_lock with
- * spin_lock_irqsave() in calling functions. */
- WARN_ONCE(in_irq(), "forcedeth: estats spin_lock(_bh) from top-half");
- assert_spin_locked(&np->hwstats_lock);
+ lockdep_assert_held(&np->hwstats_lock);
/* query hardware */
np->estats.tx_bytes += readl(base + NvRegTxCnt);
pch_gbe_clean_tx_ring(adapter, tx_ring);
vfree(tx_ring->buffer_info);
tx_ring->buffer_info = NULL;
- pci_free_consistent(pdev, tx_ring->size, tx_ring->desc, tx_ring->dma);
+ dma_free_coherent(&pdev->dev, tx_ring->size, tx_ring->desc,
+ tx_ring->dma);
tx_ring->desc = NULL;
}
pch_gbe_clean_rx_ring(adapter, rx_ring);
vfree(rx_ring->buffer_info);
rx_ring->buffer_info = NULL;
- pci_free_consistent(pdev, rx_ring->size, rx_ring->desc, rx_ring->dma);
+ dma_free_coherent(&pdev->dev, rx_ring->size, rx_ring->desc,
+ rx_ring->dma);
rx_ring->desc = NULL;
}
pch_gbe_clean_tx_ring(adapter, adapter->tx_ring);
pch_gbe_clean_rx_ring(adapter, adapter->rx_ring);
- pci_free_consistent(adapter->pdev, rx_ring->rx_buff_pool_size,
- rx_ring->rx_buff_pool, rx_ring->rx_buff_pool_logic);
+ dma_free_coherent(&adapter->pdev->dev, rx_ring->rx_buff_pool_size,
+ rx_ring->rx_buff_pool, rx_ring->rx_buff_pool_logic);
rx_ring->rx_buff_pool_logic = 0;
rx_ring->rx_buff_pool_size = 0;
rx_ring->rx_buff_pool = NULL;
struct pch_gbe_adapter *adapter = netdev_priv(netdev);
struct pch_gbe_hw *hw = &adapter->hw;
u32 wufc = adapter->wake_up_evt;
- int retval = 0;
netif_device_detach(netdev);
if (netif_running(netdev))
pch_gbe_mac_set_wol_event(hw, wufc);
pci_disable_device(pdev);
}
- return retval;
+ return 0;
}
#ifdef CONFIG_PM
if (ret)
return ret;
- if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64))
- || pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) {
- ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+ if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
+ ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
if (ret) {
- ret = pci_set_consistent_dma_mask(pdev,
- DMA_BIT_MASK(32));
- if (ret) {
- dev_err(&pdev->dev, "ERR: No usable DMA "
- "configuration, aborting\n");
- return ret;
- }
+ dev_err(&pdev->dev, "ERR: No usable DMA configuration, aborting\n");
+ return ret;
}
}
hb = ionic_heartbeat_check(ionic);
if (hb >= 0)
- ionic_link_status_check_request(ionic->lif, false);
+ ionic_link_status_check_request(ionic->lif, CAN_NOT_SLEEP);
}
void ionic_init_devinfo(struct ionic *ionic)
work = kzalloc(sizeof(*work), GFP_ATOMIC);
if (!work) {
- dev_err(ionic->dev, "%s OOM\n", __func__);
+ dev_err(ionic->dev, "LIF reset trigger dropped\n");
} else {
work->type = IONIC_DW_TYPE_LIF_RESET;
if (fw_status & IONIC_FW_STS_F_RUNNING &&
#define IONIC_MAX_TX_DESC 8192
#define IONIC_MAX_RX_DESC 16384
-#define IONIC_MIN_TXRX_DESC 16
+#define IONIC_MIN_TXRX_DESC 64
#define IONIC_DEF_TXRX_DESC 4096
+#define IONIC_RX_FILL_THRESHOLD 16
+#define IONIC_RX_FILL_DIV 8
#define IONIC_LIFS_MAX 1024
#define IONIC_WATCHDOG_SECS 5
#define IONIC_ITR_COAL_USEC_DEFAULT 64
{
struct ionic *ionic = devlink_priv(dl);
- return ionic_firmware_update(ionic->lif, params->file_name, extack);
+ return ionic_firmware_update(ionic->lif, params->fw, extack);
}
static int ionic_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
#include <net/devlink.h>
-int ionic_firmware_update(struct ionic_lif *lif, const char *fw_name,
+int ionic_firmware_update(struct ionic_lif *lif, const struct firmware *fw,
struct netlink_ext_ack *extack);
struct ionic *ionic_devlink_alloc(struct device *dev);
return err;
}
-int ionic_firmware_update(struct ionic_lif *lif, const char *fw_name,
+int ionic_firmware_update(struct ionic_lif *lif, const struct firmware *fw,
struct netlink_ext_ack *extack)
{
struct ionic_dev *idev = &lif->ionic->idev;
struct ionic *ionic = lif->ionic;
union ionic_dev_cmd_comp comp;
u32 buf_sz, copy_sz, offset;
- const struct firmware *fw;
struct devlink *dl;
int next_interval;
int err = 0;
u8 fw_slot;
- netdev_info(netdev, "Installing firmware %s\n", fw_name);
+ netdev_info(netdev, "Installing firmware\n");
dl = priv_to_devlink(ionic);
- devlink_flash_update_begin_notify(dl);
devlink_flash_update_status_notify(dl, "Preparing to flash", NULL, 0, 0);
- err = request_firmware(&fw, fw_name, ionic->dev);
- if (err) {
- NL_SET_ERR_MSG_MOD(extack, "Unable to find firmware file");
- goto err_out;
- }
-
buf_sz = sizeof(idev->dev_cmd_regs->data);
netdev_dbg(netdev,
devlink_flash_update_status_notify(dl, "Flash failed", NULL, 0, 0);
else
devlink_flash_update_status_notify(dl, "Flash done", NULL, 0, 0);
- release_firmware(fw);
- devlink_flash_update_end_notify(dl);
return err;
}
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */
+#include <linux/ethtool.h>
#include <linux/printk.h>
#include <linux/dynamic_debug.h>
#include <linux/netdevice.h>
link_up = link_status == IONIC_PORT_OPER_STATUS_UP;
if (link_up) {
+ if (lif->netdev->flags & IFF_UP && netif_running(lif->netdev)) {
+ mutex_lock(&lif->queue_lock);
+ ionic_start_queues(lif);
+ mutex_unlock(&lif->queue_lock);
+ }
+
if (!netif_carrier_ok(netdev)) {
u32 link_speed;
link_speed / 1000);
netif_carrier_on(netdev);
}
-
- if (lif->netdev->flags & IFF_UP && netif_running(lif->netdev)) {
- mutex_lock(&lif->queue_lock);
- ionic_start_queues(lif);
- mutex_unlock(&lif->queue_lock);
- }
} else {
if (netif_carrier_ok(netdev)) {
netdev_info(netdev, "Link down\n");
case IONIC_EVENT_RESET:
work = kzalloc(sizeof(*work), GFP_ATOMIC);
if (!work) {
- netdev_err(lif->netdev, "%s OOM\n", __func__);
+ netdev_err(lif->netdev, "Reset event dropped\n");
} else {
work->type = IONIC_DW_TYPE_LIF_RESET;
ionic_lif_deferred_enqueue(&lif->deferred, work);
if (!can_sleep) {
work = kzalloc(sizeof(*work), GFP_ATOMIC);
- if (!work) {
- netdev_err(lif->netdev, "%s OOM\n", __func__);
+ if (!work)
return -ENOMEM;
- }
work->type = add ? IONIC_DW_TYPE_RX_ADDR_ADD :
IONIC_DW_TYPE_RX_ADDR_DEL;
memcpy(work->addr, addr, ETH_ALEN);
static int ionic_addr_add(struct net_device *netdev, const u8 *addr)
{
- return ionic_lif_addr(netdev_priv(netdev), addr, true, true);
+ return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR, CAN_SLEEP);
}
static int ionic_ndo_addr_add(struct net_device *netdev, const u8 *addr)
{
- return ionic_lif_addr(netdev_priv(netdev), addr, true, false);
+ return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR, CAN_NOT_SLEEP);
}
static int ionic_addr_del(struct net_device *netdev, const u8 *addr)
{
- return ionic_lif_addr(netdev_priv(netdev), addr, false, true);
+ return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR, CAN_SLEEP);
}
static int ionic_ndo_addr_del(struct net_device *netdev, const u8 *addr)
{
- return ionic_lif_addr(netdev_priv(netdev), addr, false, false);
+ return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR, CAN_NOT_SLEEP);
}
static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode)
lif->rx_mode = rx_mode;
}
-static void _ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode,
- bool from_ndo)
-{
- struct ionic_deferred_work *work;
-
- if (from_ndo) {
- work = kzalloc(sizeof(*work), GFP_ATOMIC);
- if (!work) {
- netdev_err(lif->netdev, "%s OOM\n", __func__);
- return;
- }
- work->type = IONIC_DW_TYPE_RX_MODE;
- work->rx_mode = rx_mode;
- netdev_dbg(lif->netdev, "deferred: rx_mode\n");
- ionic_lif_deferred_enqueue(&lif->deferred, work);
- } else {
- ionic_lif_rx_mode(lif, rx_mode);
- }
-}
-
-static void ionic_dev_uc_sync(struct net_device *netdev, bool from_ndo)
-{
- if (from_ndo)
- __dev_uc_sync(netdev, ionic_ndo_addr_add, ionic_ndo_addr_del);
- else
- __dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del);
-
-}
-
-static void ionic_set_rx_mode(struct net_device *netdev, bool from_ndo)
+static void ionic_set_rx_mode(struct net_device *netdev, bool can_sleep)
{
struct ionic_lif *lif = netdev_priv(netdev);
+ struct ionic_deferred_work *work;
unsigned int nfilters;
unsigned int rx_mode;
* we remove our overflow flag and check the netdev flags
* to see if we can disable NIC PROMISC
*/
- ionic_dev_uc_sync(netdev, from_ndo);
+ if (can_sleep)
+ __dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del);
+ else
+ __dev_uc_sync(netdev, ionic_ndo_addr_add, ionic_ndo_addr_del);
nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters);
if (netdev_uc_count(netdev) + 1 > nfilters) {
rx_mode |= IONIC_RX_MODE_F_PROMISC;
}
/* same for multicast */
- ionic_dev_uc_sync(netdev, from_ndo);
+ if (can_sleep)
+ __dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del);
+ else
+ __dev_mc_sync(netdev, ionic_ndo_addr_add, ionic_ndo_addr_del);
nfilters = le32_to_cpu(lif->identity->eth.max_mcast_filters);
if (netdev_mc_count(netdev) > nfilters) {
rx_mode |= IONIC_RX_MODE_F_ALLMULTI;
rx_mode &= ~IONIC_RX_MODE_F_ALLMULTI;
}
- if (lif->rx_mode != rx_mode)
- _ionic_lif_rx_mode(lif, rx_mode, from_ndo);
+ if (lif->rx_mode != rx_mode) {
+ if (!can_sleep) {
+ work = kzalloc(sizeof(*work), GFP_ATOMIC);
+ if (!work) {
+ netdev_err(lif->netdev, "rxmode change dropped\n");
+ return;
+ }
+ work->type = IONIC_DW_TYPE_RX_MODE;
+ work->rx_mode = rx_mode;
+ netdev_dbg(lif->netdev, "deferred: rx_mode\n");
+ ionic_lif_deferred_enqueue(&lif->deferred, work);
+ } else {
+ ionic_lif_rx_mode(lif, rx_mode);
+ }
+ }
}
static void ionic_ndo_set_rx_mode(struct net_device *netdev)
{
- ionic_set_rx_mode(netdev, true);
+ ionic_set_rx_mode(netdev, CAN_NOT_SLEEP);
}
static __le64 ionic_netdev_features_to_nic(netdev_features_t features)
if (err)
return err;
- netdev->mtu = new_mtu;
/* if we're not running, nothing more to do */
- if (!netif_running(netdev))
+ if (!netif_running(netdev)) {
+ netdev->mtu = new_mtu;
return 0;
+ }
ionic_stop_queues_reconfig(lif);
+ netdev->mtu = new_mtu;
return ionic_start_queues_reconfig(lif);
}
ionic_lif_rss_config(lif, 0x0, NULL, NULL);
}
+static void ionic_lif_quiesce(struct ionic_lif *lif)
+{
+ struct ionic_admin_ctx ctx = {
+ .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
+ .cmd.lif_setattr = {
+ .opcode = IONIC_CMD_LIF_SETATTR,
+ .index = cpu_to_le16(lif->index),
+ .attr = IONIC_LIF_ATTR_STATE,
+ .state = IONIC_LIF_QUIESCE,
+ },
+ };
+ int err;
+
+ err = ionic_adminq_post_wait(lif, &ctx);
+ if (err)
+ netdev_err(lif->netdev, "lif quiesce failed %d\n", err);
+}
+
static void ionic_txrx_disable(struct ionic_lif *lif)
{
unsigned int i;
for (i = 0; i < lif->nxqs; i++)
err = ionic_qcq_disable(lif->rxqcqs[i], (err != -ETIMEDOUT));
}
+
+ ionic_lif_quiesce(lif);
}
static void ionic_txrx_deinit(struct ionic_lif *lif)
if (lif->netdev->features & NETIF_F_RXHASH)
ionic_lif_rss_init(lif);
- ionic_set_rx_mode(lif->netdev, false);
+ ionic_set_rx_mode(lif->netdev, CAN_SLEEP);
return 0;
*/
if (!ether_addr_equal(ctx.comp.lif_getattr.mac,
netdev->dev_addr))
- ionic_lif_addr(lif, netdev->dev_addr, true, true);
+ ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR, CAN_SLEEP);
} else {
/* Update the netdev mac with the device's mac */
memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len);
netdev_dbg(lif->netdev, "adding station MAC addr %pM\n",
netdev->dev_addr);
- ionic_lif_addr(lif, netdev->dev_addr, true, true);
+ ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR, CAN_SLEEP);
return 0;
}
dev_err(lif->ionic->dev, "Cannot register net device, aborting\n");
return err;
}
+
+ ionic_link_status_check_request(lif, true);
lif->registered = true;
ionic_lif_set_netdev_info(lif);
#define IONIC_MAX_NUM_NAPI_CNTR (NAPI_POLL_WEIGHT + 1)
#define IONIC_MAX_NUM_SG_CNTR (IONIC_TX_MAX_SG_ELEMS + 1)
+
+#define ADD_ADDR true
+#define DEL_ADDR false
+#define CAN_SLEEP true
+#define CAN_NOT_SLEEP false
+
#define IONIC_RX_COPYBREAK_DEFAULT 256
#define IONIC_TX_BUDGET_DEFAULT 256
idev->port_info_sz,
&idev->port_info_pa,
GFP_KERNEL);
- if (!idev->port_info) {
- dev_err(ionic->dev, "Failed to allocate port info\n");
+ if (!idev->port_info)
return -ENOMEM;
- }
}
sz = min(sizeof(ident->port.config), sizeof(idev->dev_cmd_regs->data));
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */
+#include <linux/ethtool.h>
#include <linux/kernel.h>
#include <linux/mutex.h>
#include <linux/netdevice.h>
q->dbval | q->head_idx);
}
-static void ionic_rx_fill_cb(void *arg)
-{
- ionic_rx_fill(arg);
-}
-
void ionic_rx_empty(struct ionic_queue *q)
{
struct ionic_desc_info *desc_info;
struct ionic_cq *cq = napi_to_cq(napi);
struct ionic_dev *idev;
struct ionic_lif *lif;
+ u16 rx_fill_threshold;
u32 work_done = 0;
u32 flags = 0;
work_done = ionic_cq_service(cq, budget,
ionic_rx_service, NULL, NULL);
- if (work_done)
+ rx_fill_threshold = min_t(u16, IONIC_RX_FILL_THRESHOLD,
+ cq->num_descs / IONIC_RX_FILL_DIV);
+ if (work_done && ionic_q_space_avail(cq->bound_q) >= rx_fill_threshold)
ionic_rx_fill(cq->bound_q);
if (work_done < budget && napi_complete_done(napi, work_done)) {
struct ionic_dev *idev;
struct ionic_lif *lif;
struct ionic_cq *txcq;
+ u16 rx_fill_threshold;
u32 rx_work_done = 0;
u32 tx_work_done = 0;
u32 flags = 0;
rx_work_done = ionic_cq_service(rxcq, budget,
ionic_rx_service, NULL, NULL);
- if (rx_work_done)
- ionic_rx_fill_cb(rxcq->bound_q);
+
+ rx_fill_threshold = min_t(u16, IONIC_RX_FILL_THRESHOLD,
+ rxcq->num_descs / IONIC_RX_FILL_DIV);
+ if (rx_work_done && ionic_q_space_avail(rxcq->bound_q) >= rx_fill_threshold)
+ ionic_rx_fill(rxcq->bound_q);
if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) {
ionic_dim_update(qcq);
*/
#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
#include <linux/if_arp.h>
#include <net/pkt_sched.h>
#include "rmnet_config.h"
#define R8169_REGS_SIZE 256
#define R8169_RX_BUF_SIZE (SZ_16K - 1)
-#define NUM_TX_DESC 64 /* Number of Tx descriptor registers */
+#define NUM_TX_DESC 256 /* Number of Tx descriptor registers */
#define NUM_RX_DESC 256U /* Number of Rx descriptor registers */
#define R8169_TX_RING_BYTES (NUM_TX_DESC * sizeof(struct TxDesc))
#define R8169_RX_RING_BYTES (NUM_RX_DESC * sizeof(struct RxDesc))
RTL_FLAG_MAX
};
-struct rtl8169_stats {
- u64 packets;
- u64 bytes;
- struct u64_stats_sync syncp;
-};
-
struct rtl8169_private {
void __iomem *mmio_addr; /* memory map physical address */
struct pci_dev *pci_dev;
u32 cur_rx; /* Index into the Rx descriptor buffer of next Rx pkt. */
u32 cur_tx; /* Index into the Tx descriptor buffer of next Rx pkt. */
u32 dirty_tx;
- struct rtl8169_stats rx_stats;
- struct rtl8169_stats tx_stats;
struct TxDesc *TxDescArray; /* 256-aligned Tx descriptor ring */
struct RxDesc *RxDescArray; /* 256-aligned Rx descriptor ring */
dma_addr_t TxPhyAddr;
tp->mac_version != RTL_GIGA_MAC_VER_39;
}
-static void rtl_get_priv_stats(struct rtl8169_stats *stats,
- u64 *pkts, u64 *bytes)
-{
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_irq(&stats->syncp);
- *pkts = stats->packets;
- *bytes = stats->bytes;
- } while (u64_stats_fetch_retry_irq(&stats->syncp, start));
-}
-
-static void rtl_inc_priv_stats(struct rtl8169_stats *stats,
- u64 pkts, u64 bytes)
-{
- u64_stats_update_begin(&stats->syncp);
- stats->packets += pkts;
- stats->bytes += bytes;
- u64_stats_update_end(&stats->syncp);
-}
-
static void rtl_read_mac_from_reg(struct rtl8169_private *tp, u8 *mac, int reg)
{
int i;
rtl_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
}
-static void rtl8169_reset_counters(struct rtl8169_private *tp)
-{
- /*
- * Versions prior to RTL_GIGA_MAC_VER_19 don't support resetting the
- * tally counters.
- */
- if (tp->mac_version >= RTL_GIGA_MAC_VER_19)
- rtl8169_do_counters(tp, CounterReset);
-}
-
static void rtl8169_update_counters(struct rtl8169_private *tp)
{
u8 val = RTL_R8(tp, ChipCmd);
if (tp->tc_offset.inited)
return;
- rtl8169_reset_counters(tp);
- rtl8169_update_counters(tp);
+ if (tp->mac_version >= RTL_GIGA_MAC_VER_19) {
+ rtl8169_do_counters(tp, CounterReset);
+ } else {
+ rtl8169_update_counters(tp);
+ tp->tc_offset.tx_errors = counters->tx_errors;
+ tp->tc_offset.tx_multi_collision = counters->tx_multi_collision;
+ tp->tc_offset.tx_aborted = counters->tx_aborted;
+ tp->tc_offset.rx_missed = counters->rx_missed;
+ }
- tp->tc_offset.tx_errors = counters->tx_errors;
- tp->tc_offset.tx_multi_collision = counters->tx_multi_collision;
- tp->tc_offset.tx_aborted = counters->tx_aborted;
- tp->tc_offset.rx_missed = counters->rx_missed;
tp->tc_offset.inited = true;
}
return true;
}
-static bool rtl_tx_slots_avail(struct rtl8169_private *tp,
- unsigned int nr_frags)
+static bool rtl_tx_slots_avail(struct rtl8169_private *tp)
{
- unsigned int slots_avail = tp->dirty_tx + NUM_TX_DESC - tp->cur_tx;
+ unsigned int slots_avail = READ_ONCE(tp->dirty_tx) + NUM_TX_DESC
+ - READ_ONCE(tp->cur_tx);
/* A skbuff with nr_frags needs nr_frags+1 entries in the tx queue */
- return slots_avail > nr_frags;
+ return slots_avail > MAX_SKB_FRAGS;
}
/* Versions RTL8102e and from RTL8168c onwards support csum_v2 */
bool stop_queue, door_bell;
u32 opts[2];
- txd_first = tp->TxDescArray + entry;
-
- if (unlikely(!rtl_tx_slots_avail(tp, frags))) {
+ if (unlikely(!rtl_tx_slots_avail(tp))) {
if (net_ratelimit())
netdev_err(dev, "BUG! Tx Ring full when queue awake!\n");
goto err_stop_0;
}
- if (unlikely(le32_to_cpu(txd_first->opts1) & DescOwn))
- goto err_stop_0;
-
opts[1] = rtl8169_tx_vlan_tag(skb);
opts[0] = 0;
entry, false)))
goto err_dma_0;
+ txd_first = tp->TxDescArray + entry;
+
if (frags) {
if (rtl8169_xmit_frags(tp, skb, opts, entry))
goto err_dma_1;
/* rtl_tx needs to see descriptor changes before updated tp->cur_tx */
smp_wmb();
- tp->cur_tx += frags + 1;
+ WRITE_ONCE(tp->cur_tx, tp->cur_tx + frags + 1);
- stop_queue = !rtl_tx_slots_avail(tp, MAX_SKB_FRAGS);
+ stop_queue = !rtl_tx_slots_avail(tp);
if (unlikely(stop_queue)) {
/* Avoid wrongly optimistic queue wake-up: rtl_tx thread must
* not miss a ring update when it notices a stopped queue.
*/
smp_wmb();
netif_stop_queue(dev);
- door_bell = true;
- }
-
- if (door_bell)
- rtl8169_doorbell(tp);
-
- if (unlikely(stop_queue)) {
/* Sync with rtl_tx:
* - publish queue status and cur_tx ring index (write barrier)
* - refresh dirty_tx ring index (read barrier).
* status and forget to wake up queue, a racing rtl_tx thread
* can't.
*/
- smp_mb();
- if (rtl_tx_slots_avail(tp, MAX_SKB_FRAGS))
+ smp_mb__after_atomic();
+ if (rtl_tx_slots_avail(tp))
netif_start_queue(dev);
+ door_bell = true;
}
+ if (door_bell)
+ rtl8169_doorbell(tp);
+
return NETDEV_TX_OK;
err_dma_1:
static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp,
int budget)
{
- unsigned int dirty_tx, tx_left, bytes_compl = 0, pkts_compl = 0;
+ unsigned int dirty_tx, bytes_compl = 0, pkts_compl = 0;
+ struct sk_buff *skb;
dirty_tx = tp->dirty_tx;
- smp_rmb();
- for (tx_left = tp->cur_tx - dirty_tx; tx_left > 0; tx_left--) {
+ while (READ_ONCE(tp->cur_tx) != dirty_tx) {
unsigned int entry = dirty_tx % NUM_TX_DESC;
- struct sk_buff *skb = tp->tx_skb[entry].skb;
u32 status;
status = le32_to_cpu(tp->TxDescArray[entry].opts1);
if (status & DescOwn)
break;
+ skb = tp->tx_skb[entry].skb;
rtl8169_unmap_tx_skb(tp, entry);
if (skb) {
if (tp->dirty_tx != dirty_tx) {
netdev_completed_queue(dev, pkts_compl, bytes_compl);
+ dev_sw_netstats_tx_add(dev, pkts_compl, bytes_compl);
- rtl_inc_priv_stats(&tp->tx_stats, pkts_compl, bytes_compl);
-
- tp->dirty_tx = dirty_tx;
/* Sync with rtl8169_start_xmit:
* - publish dirty_tx ring index (write barrier)
* - refresh cur_tx ring index and queue status (read barrier)
* a racing xmit thread can only have a right view of the
* ring status.
*/
- smp_mb();
- if (netif_queue_stopped(dev) &&
- rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) {
+ smp_store_mb(tp->dirty_tx, dirty_tx);
+ if (netif_queue_stopped(dev) && rtl_tx_slots_avail(tp))
netif_wake_queue(dev);
- }
/*
* 8168 hack: TxPoll requests are lost when the Tx packets are
* too close. Let's kick an extra TxPoll request when a burst
* of start_xmit activity is detected (if it is not detected,
* it is slow enough). -- FR
+ * If skb is NULL then we come here again once a tx irq is
+ * triggered after the last fragment is marked transmitted.
*/
- if (tp->cur_tx != dirty_tx)
+ if (tp->cur_tx != dirty_tx && skb)
rtl8169_doorbell(tp);
}
}
napi_gro_receive(&tp->napi, skb);
- rtl_inc_priv_stats(&tp->rx_stats, 1, pkt_size);
+ dev_sw_netstats_rx_add(dev, pkt_size);
release_descriptor:
rtl8169_mark_to_asic(desc);
}
{
struct rtl8169_private *tp = netdev_priv(dev);
struct pci_dev *pdev = tp->pci_dev;
+ unsigned long irqflags;
int retval = -ENOMEM;
pm_runtime_get_sync(&pdev->dev);
tp->TxDescArray = dma_alloc_coherent(&pdev->dev, R8169_TX_RING_BYTES,
&tp->TxPhyAddr, GFP_KERNEL);
if (!tp->TxDescArray)
- goto err_pm_runtime_put;
+ goto out;
tp->RxDescArray = dma_alloc_coherent(&pdev->dev, R8169_RX_RING_BYTES,
&tp->RxPhyAddr, GFP_KERNEL);
rtl_request_firmware(tp);
+ irqflags = pci_dev_msi_enabled(pdev) ? IRQF_NO_THREAD : IRQF_SHARED;
retval = request_irq(pci_irq_vector(pdev, 0), rtl8169_interrupt,
- IRQF_SHARED, dev->name, tp);
+ irqflags, dev->name, tp);
if (retval < 0)
goto err_release_fw_2;
rtl8169_up(tp);
rtl8169_init_counter_offsets(tp);
netif_start_queue(dev);
-
- pm_runtime_put_sync(&pdev->dev);
out:
+ pm_runtime_put_sync(&pdev->dev);
+
return retval;
err_free_irq:
dma_free_coherent(&pdev->dev, R8169_TX_RING_BYTES, tp->TxDescArray,
tp->TxPhyAddr);
tp->TxDescArray = NULL;
-err_pm_runtime_put:
- pm_runtime_put_noidle(&pdev->dev);
goto out;
}
pm_runtime_get_noresume(&pdev->dev);
netdev_stats_to_stats64(stats, &dev->stats);
-
- rtl_get_priv_stats(&tp->rx_stats, &stats->rx_packets, &stats->rx_bytes);
- rtl_get_priv_stats(&tp->tx_stats, &stats->tx_packets, &stats->tx_bytes);
+ dev_fetch_sw_netstats(stats, dev->tstats);
/*
* Fetch additional counter values missing in stats collected by driver
if (rc == -ENOENT)
/* clk-core allows NULL (for suspend / resume) */
rc = 0;
- else if (rc != -EPROBE_DEFER)
- dev_err(d, "failed to get clk: %d\n", rc);
+ else
+ dev_err_probe(d, rc, "failed to get clk\n");
} else {
tp->clk = clk;
rc = clk_prepare_enable(clk);
tp->eee_adv = -1;
tp->ocp_base = OCP_STD_PHY_BASE;
+ dev->tstats = devm_netdev_alloc_pcpu_stats(&pdev->dev,
+ struct pcpu_sw_netstats);
+ if (!dev->tstats)
+ return -ENOMEM;
+
/* Get the *optional* external "ether_clk" used on some boards */
rc = rtl_get_ether_clk(tp);
if (rc)
}
INIT_WORK(&tp->wk.work, rtl_task);
- u64_stats_init(&tp->rx_stats.syncp);
- u64_stats_init(&tp->tx_stats.syncp);
rtl_init_mac_address(tp);
field10, value10, \
field11, value11, \
field12, value12, \
- field13, value13) \
+ field13, value13, \
+ field14, value14, \
+ field15, value15, \
+ field16, value16, \
+ field17, value17, \
+ field18, value18, \
+ field19, value19) \
(EFX_INSERT_FIELD_NATIVE((min), (max), field1, (value1)) | \
EFX_INSERT_FIELD_NATIVE((min), (max), field2, (value2)) | \
EFX_INSERT_FIELD_NATIVE((min), (max), field3, (value3)) | \
EFX_INSERT_FIELD_NATIVE((min), (max), field10, (value10)) | \
EFX_INSERT_FIELD_NATIVE((min), (max), field11, (value11)) | \
EFX_INSERT_FIELD_NATIVE((min), (max), field12, (value12)) | \
- EFX_INSERT_FIELD_NATIVE((min), (max), field13, (value13)))
+ EFX_INSERT_FIELD_NATIVE((min), (max), field13, (value13)) | \
+ EFX_INSERT_FIELD_NATIVE((min), (max), field14, (value14)) | \
+ EFX_INSERT_FIELD_NATIVE((min), (max), field15, (value15)) | \
+ EFX_INSERT_FIELD_NATIVE((min), (max), field16, (value16)) | \
+ EFX_INSERT_FIELD_NATIVE((min), (max), field17, (value17)) | \
+ EFX_INSERT_FIELD_NATIVE((min), (max), field18, (value18)) | \
+ EFX_INSERT_FIELD_NATIVE((min), (max), field19, (value19)))
#define EFX_INSERT_FIELDS64(...) \
cpu_to_le64(EFX_INSERT_FIELDS_NATIVE(__VA_ARGS__))
#endif
/* Populate an octword field with various numbers of arguments */
-#define EFX_POPULATE_OWORD_13 EFX_POPULATE_OWORD
+#define EFX_POPULATE_OWORD_19 EFX_POPULATE_OWORD
+#define EFX_POPULATE_OWORD_18(oword, ...) \
+ EFX_POPULATE_OWORD_19(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_OWORD_17(oword, ...) \
+ EFX_POPULATE_OWORD_18(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_OWORD_16(oword, ...) \
+ EFX_POPULATE_OWORD_17(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_OWORD_15(oword, ...) \
+ EFX_POPULATE_OWORD_16(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_OWORD_14(oword, ...) \
+ EFX_POPULATE_OWORD_15(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_OWORD_13(oword, ...) \
+ EFX_POPULATE_OWORD_14(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
#define EFX_POPULATE_OWORD_12(oword, ...) \
EFX_POPULATE_OWORD_13(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
#define EFX_POPULATE_OWORD_11(oword, ...) \
EFX_DWORD_3, 0xffffffff)
/* Populate a quadword field with various numbers of arguments */
-#define EFX_POPULATE_QWORD_13 EFX_POPULATE_QWORD
+#define EFX_POPULATE_QWORD_19 EFX_POPULATE_QWORD
+#define EFX_POPULATE_QWORD_18(qword, ...) \
+ EFX_POPULATE_QWORD_19(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_QWORD_17(qword, ...) \
+ EFX_POPULATE_QWORD_18(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_QWORD_16(qword, ...) \
+ EFX_POPULATE_QWORD_17(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_QWORD_15(qword, ...) \
+ EFX_POPULATE_QWORD_16(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_QWORD_14(qword, ...) \
+ EFX_POPULATE_QWORD_15(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_QWORD_13(qword, ...) \
+ EFX_POPULATE_QWORD_14(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
#define EFX_POPULATE_QWORD_12(qword, ...) \
EFX_POPULATE_QWORD_13(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
#define EFX_POPULATE_QWORD_11(qword, ...) \
EFX_DWORD_1, 0xffffffff)
/* Populate a dword field with various numbers of arguments */
-#define EFX_POPULATE_DWORD_13 EFX_POPULATE_DWORD
+#define EFX_POPULATE_DWORD_19 EFX_POPULATE_DWORD
+#define EFX_POPULATE_DWORD_18(dword, ...) \
+ EFX_POPULATE_DWORD_19(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_DWORD_17(dword, ...) \
+ EFX_POPULATE_DWORD_18(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_DWORD_16(dword, ...) \
+ EFX_POPULATE_DWORD_17(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_DWORD_15(dword, ...) \
+ EFX_POPULATE_DWORD_16(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_DWORD_14(dword, ...) \
+ EFX_POPULATE_DWORD_15(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
+#define EFX_POPULATE_DWORD_13(dword, ...) \
+ EFX_POPULATE_DWORD_14(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
#define EFX_POPULATE_DWORD_12(dword, ...) \
EFX_POPULATE_DWORD_13(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__)
#define EFX_POPULATE_DWORD_11(dword, ...) \
if (rc)
return rc;
- if (efx_ef100_has_cap(nic_data->datapath_caps2, TX_TSO_V3))
- efx->net_dev->features |= NETIF_F_TSO | NETIF_F_TSO6;
+ if (efx_ef100_has_cap(nic_data->datapath_caps2, TX_TSO_V3)) {
+ struct net_device *net_dev = efx->net_dev;
+ netdev_features_t tso = NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_PARTIAL |
+ NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM |
+ NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM;
+
+ net_dev->features |= tso;
+ net_dev->hw_features |= tso;
+ net_dev->hw_enc_features |= tso;
+ /* EF100 HW can only offload outer checksums if they are UDP,
+ * so for GRE_CSUM we have to use GSO_PARTIAL.
+ */
+ net_dev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
+ }
efx->num_mac_stats = MCDI_WORD(outbuf,
GET_CAPABILITIES_V4_OUT_MAC_STATS_NUM_STATS);
netif_dbg(efx, probe, efx->net_dev,
#define EF100_OFFLOAD_FEATURES (NETIF_F_HW_CSUM | NETIF_F_RXCSUM | \
NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_NTUPLE | \
NETIF_F_RXHASH | NETIF_F_RXFCS | NETIF_F_TSO_ECN | NETIF_F_RXALL | \
- NETIF_F_TSO_MANGLEID | NETIF_F_HW_VLAN_CTAG_TX)
+ NETIF_F_HW_VLAN_CTAG_TX)
const struct efx_nic_type ef100_pf_nic_type = {
.revision = EFX_REV_EF100,
nic_data->efx = efx;
net_dev->features |= efx->type->offload_features;
net_dev->hw_features |= efx->type->offload_features;
+ net_dev->hw_enc_features |= efx->type->offload_features;
+ net_dev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_SG |
+ NETIF_F_HIGHDMA | NETIF_F_ALL_TSO;
/* Populate design-parameter defaults */
nic_data->tso_max_hdr_len = ESE_EF100_DP_GZ_TSO_MAX_HDR_LEN_DEFAULT;
struct efx_nic *efx = tx_queue->efx;
struct ef100_nic_data *nic_data;
struct efx_tx_buffer *buffer;
- struct tcphdr *tcphdr;
- struct iphdr *iphdr;
size_t header_len;
u32 mss;
buffer->unmap_len = 0;
buffer->skb = skb;
++tx_queue->insert_count;
-
- /* Adjust the TCP checksum to exclude the total length, since we set
- * ED_INNER_IP_LEN in the descriptor.
- */
- tcphdr = tcp_hdr(skb);
- if (skb_is_gso_v6(skb)) {
- tcphdr->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
- &ipv6_hdr(skb)->daddr,
- 0, IPPROTO_TCP, 0);
- } else {
- iphdr = ip_hdr(skb);
- tcphdr->check = ~csum_tcpudp_magic(iphdr->saddr, iphdr->daddr,
- 0, IPPROTO_TCP, 0);
- }
return true;
}
struct efx_tx_buffer *buffer, efx_oword_t *txd,
unsigned int segment_count)
{
- u32 mangleid = (efx->net_dev->features & NETIF_F_TSO_MANGLEID) ||
- skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID ?
- ESE_GZ_TX_DESC_IP4_ID_NO_OP :
- ESE_GZ_TX_DESC_IP4_ID_INC_MOD16;
- u16 vlan_enable = efx->net_dev->features & NETIF_F_HW_VLAN_CTAG_TX ?
- skb_vlan_tag_present(skb) : 0;
+ bool gso_partial = skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL;
unsigned int len, ip_offset, tcp_offset, payload_segs;
+ u32 mangleid = ESE_GZ_TX_DESC_IP4_ID_INC_MOD16;
+ unsigned int outer_ip_offset, outer_l4_offset;
u16 vlan_tci = skb_vlan_tag_get(skb);
u32 mss = skb_shinfo(skb)->gso_size;
+ bool encap = skb->encapsulation;
+ bool udp_encap = false;
+ u16 vlan_enable = 0;
+ struct tcphdr *tcp;
+ bool outer_csum;
+ u32 paylen;
+
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID)
+ mangleid = ESE_GZ_TX_DESC_IP4_ID_NO_OP;
+ if (efx->net_dev->features & NETIF_F_HW_VLAN_CTAG_TX)
+ vlan_enable = skb_vlan_tag_present(skb);
len = skb->len - buffer->len;
/* We use 1 for the TSO descriptor and 1 for the header */
payload_segs = segment_count - 2;
- ip_offset = skb_network_offset(skb);
- tcp_offset = skb_transport_offset(skb);
+ if (encap) {
+ outer_ip_offset = skb_network_offset(skb);
+ outer_l4_offset = skb_transport_offset(skb);
+ ip_offset = skb_inner_network_offset(skb);
+ tcp_offset = skb_inner_transport_offset(skb);
+ if (skb_shinfo(skb)->gso_type &
+ (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))
+ udp_encap = true;
+ } else {
+ ip_offset = skb_network_offset(skb);
+ tcp_offset = skb_transport_offset(skb);
+ outer_ip_offset = outer_l4_offset = 0;
+ }
+ outer_csum = skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM;
+
+ /* subtract TCP payload length from inner checksum */
+ tcp = (void *)skb->data + tcp_offset;
+ paylen = skb->len - tcp_offset;
+ csum_replace_by_diff(&tcp->check, (__force __wsum)htonl(paylen));
- EFX_POPULATE_OWORD_13(*txd,
+ EFX_POPULATE_OWORD_19(*txd,
ESF_GZ_TX_DESC_TYPE, ESE_GZ_TX_DESC_TYPE_TSO,
ESF_GZ_TX_TSO_MSS, mss,
ESF_GZ_TX_TSO_HDR_NUM_SEGS, 1,
ESF_GZ_TX_TSO_PAYLOAD_NUM_SEGS, payload_segs,
ESF_GZ_TX_TSO_HDR_LEN_W, buffer->len >> 1,
ESF_GZ_TX_TSO_PAYLOAD_LEN, len,
+ ESF_GZ_TX_TSO_CSO_OUTER_L4, outer_csum,
ESF_GZ_TX_TSO_CSO_INNER_L4, 1,
ESF_GZ_TX_TSO_INNER_L3_OFF_W, ip_offset >> 1,
ESF_GZ_TX_TSO_INNER_L4_OFF_W, tcp_offset >> 1,
ESF_GZ_TX_TSO_ED_INNER_IP4_ID, mangleid,
ESF_GZ_TX_TSO_ED_INNER_IP_LEN, 1,
+ ESF_GZ_TX_TSO_OUTER_L3_OFF_W, outer_ip_offset >> 1,
+ ESF_GZ_TX_TSO_OUTER_L4_OFF_W, outer_l4_offset >> 1,
+ ESF_GZ_TX_TSO_ED_OUTER_UDP_LEN, udp_encap && !gso_partial,
+ ESF_GZ_TX_TSO_ED_OUTER_IP_LEN, encap && !gso_partial,
+ ESF_GZ_TX_TSO_ED_OUTER_IP4_ID, encap ? mangleid :
+ ESE_GZ_TX_DESC_IP4_ID_NO_OP,
ESF_GZ_TX_TSO_VLAN_INSERT_EN, vlan_enable,
ESF_GZ_TX_TSO_VLAN_INSERT_TCI, vlan_tci
);
default y
depends on ARM || ARM64 || ATARI_ETHERNAT || COLDFIRE || \
ISA || MAC || MIPS || NIOS2 || PCI || \
- PCMCIA || SUPERH || XTENSA || H8300
+ PCMCIA || SUPERH || XTENSA || H8300 || COMPILE_TEST
help
If you have a network (Ethernet) card belonging to this class, say Y.
select MII
depends on !OF || GPIOLIB
depends on ARM || ARM64 || ATARI_ETHERNAT || COLDFIRE || \
- MIPS || NIOS2 || SUPERH || XTENSA || H8300
+ MIPS || NIOS2 || SUPERH || XTENSA || H8300 || COMPILE_TEST
help
This is a driver for SMC's 91x series of Ethernet chipsets,
including the SMC91C94 and the SMC91C111. Say Y if you want it
tristate "SMSC LAN911[5678] support"
select CRC32
select MII
- depends on (ARM || SUPERH)
+ depends on (ARM || SUPERH || COMPILE_TEST)
help
This is a driver for SMSC's LAN911x series of Ethernet chipsets
including the new LAN9115, LAN9116, LAN9117, and LAN9118.
#define PRINTK(dev, args...) netdev_info(dev, args)
#else
-#define DBG(n, dev, args...) do { } while (0)
+#define DBG(n, dev, args...) \
+ while (0) { \
+ netdev_dbg(dev, args); \
+ }
#define PRINTK(dev, args...) netdev_dbg(dev, args)
#endif
TX_CMD_A_INT_FIRST_SEG_ | TX_CMD_A_INT_LAST_SEG_ |
skb->len;
#else
- buf = (char*)((u32)skb->data & ~0x3);
- len = (skb->len + 3 + ((u32)skb->data & 3)) & ~0x3;
- cmdA = (((u32)skb->data & 0x3) << 16) |
+ buf = (char *)((uintptr_t)skb->data & ~0x3);
+ len = (skb->len + 3 + ((uintptr_t)skb->data & 3)) & ~0x3;
+ cmdA = (((uintptr_t)skb->data & 0x3) << 16) |
TX_CMD_A_INT_FIRST_SEG_ | TX_CMD_A_INT_LAST_SEG_ |
skb->len;
#endif
int phyaddr = lp->mii.phy_id;
int my_phy_caps; /* My PHY capabilities */
int my_ad_caps; /* My Advertised capabilities */
- int status;
+ int status __always_unused;
unsigned long flags;
DBG(SMC_DEBUG_FUNC, dev, "--> %s()\n", __func__);
{
struct smc911x_local *lp = netdev_priv(dev);
int phyaddr = lp->mii.phy_id;
- int status;
+ int status __always_unused;
DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__);
void __iomem *addr;
int ret;
- /* ndev is not valid yet, so avoid passing it in. */
- DBG(SMC_DEBUG_FUNC, "--> %s\n", __func__);
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!res) {
ret = -ENODEV;
{
struct smc_local *lp = netdev_priv(dev);
void __iomem *ioaddr = lp->base;
- unsigned int saved_packet, packet_no, tx_status, pkt_len;
+ unsigned int saved_packet, packet_no, tx_status;
+ unsigned int pkt_len __always_unused;
DBG(3, dev, "%s\n", __func__);
/**
* of_try_set_control_gpio - configure a gpio if it exists
+ * @dev: net device
+ * @desc: where to store the GPIO descriptor, if it exists
+ * @name: name of the GPIO in DT
+ * @index: index of the GPIO in DT
+ * @value: set the GPIO to this value
+ * @nsdelay: delay before setting the GPIO
*/
static int try_toggle_control_gpio(struct device *dev,
struct gpio_desc **desc,
static bool netsec_clean_tx_dring(struct netsec_priv *priv)
{
struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_TX];
+ struct xdp_frame_bulk bq;
struct netsec_de *entry;
int tail = dring->tail;
unsigned int bytes;
spin_lock(&dring->lock);
bytes = 0;
+ xdp_frame_bulk_init(&bq);
entry = dring->vaddr + DESC_SZ * tail;
+ rcu_read_lock(); /* need for xdp_return_frame_bulk */
+
while (!(entry->attr & (1U << NETSEC_TX_SHIFT_OWN_FIELD)) &&
cnt < DESC_NUM) {
struct netsec_desc *desc;
dev_kfree_skb(desc->skb);
} else {
bytes += desc->xdpf->len;
- xdp_return_frame(desc->xdpf);
+ if (desc->buf_type == TYPE_NETSEC_XDP_TX)
+ xdp_return_frame_rx_napi(desc->xdpf);
+ else
+ xdp_return_frame_bulk(desc->xdpf, &bq);
}
next:
/* clean up so netsec_uninit_pkt_dring() won't free the skb
entry = dring->vaddr + DESC_SZ * tail;
cnt++;
}
+ xdp_flush_frame_bulk(&bq);
+
+ rcu_read_unlock();
spin_unlock(&dring->lock);
/* Default LPI timers */
#define STMMAC_DEFAULT_LIT_LS 0x3E8
#define STMMAC_DEFAULT_TWT_LS 0x1E
+#define STMMAC_ET_MAX 0xFFFFF
#define STMMAC_CHAIN_MODE 0x1
#define STMMAC_RING_MODE 0x2
return 0;
}
-static void *dwc_qos_probe(struct platform_device *pdev,
- struct plat_stmmacenet_data *plat_dat,
- struct stmmac_resources *stmmac_res)
+static int dwc_qos_probe(struct platform_device *pdev,
+ struct plat_stmmacenet_data *plat_dat,
+ struct stmmac_resources *stmmac_res)
{
int err;
plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk");
if (IS_ERR(plat_dat->stmmac_clk)) {
dev_err(&pdev->dev, "apb_pclk clock not found.\n");
- return ERR_CAST(plat_dat->stmmac_clk);
+ return PTR_ERR(plat_dat->stmmac_clk);
}
err = clk_prepare_enable(plat_dat->stmmac_clk);
if (err < 0) {
dev_err(&pdev->dev, "failed to enable apb_pclk clock: %d\n",
err);
- return ERR_PTR(err);
+ return err;
}
plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk");
goto disable;
}
- return NULL;
+ return 0;
disable:
clk_disable_unprepare(plat_dat->stmmac_clk);
- return ERR_PTR(err);
+ return err;
}
static int dwc_qos_remove(struct platform_device *pdev)
return 0;
}
-static void *tegra_eqos_probe(struct platform_device *pdev,
- struct plat_stmmacenet_data *data,
- struct stmmac_resources *res)
+static int tegra_eqos_probe(struct platform_device *pdev,
+ struct plat_stmmacenet_data *data,
+ struct stmmac_resources *res)
{
struct device *dev = &pdev->dev;
struct tegra_eqos *eqos;
int err;
eqos = devm_kzalloc(&pdev->dev, sizeof(*eqos), GFP_KERNEL);
- if (!eqos) {
- err = -ENOMEM;
- goto error;
- }
+ if (!eqos)
+ return -ENOMEM;
eqos->dev = &pdev->dev;
eqos->regs = res->addr;
if (err < 0)
goto reset;
-out:
- return eqos;
-
+ return 0;
reset:
reset_control_assert(eqos->rst);
reset_phy:
disable_master:
clk_disable_unprepare(eqos->clk_master);
error:
- eqos = ERR_PTR(err);
- goto out;
+ return err;
}
static int tegra_eqos_remove(struct platform_device *pdev)
}
struct dwc_eth_dwmac_data {
- void *(*probe)(struct platform_device *pdev,
- struct plat_stmmacenet_data *data,
- struct stmmac_resources *res);
+ int (*probe)(struct platform_device *pdev,
+ struct plat_stmmacenet_data *data,
+ struct stmmac_resources *res);
int (*remove)(struct platform_device *pdev);
};
const struct dwc_eth_dwmac_data *data;
struct plat_stmmacenet_data *plat_dat;
struct stmmac_resources stmmac_res;
- void *priv;
int ret;
data = device_get_match_data(&pdev->dev);
if (IS_ERR(plat_dat))
return PTR_ERR(plat_dat);
- priv = data->probe(pdev, plat_dat, &stmmac_res);
- if (IS_ERR(priv)) {
- ret = PTR_ERR(priv);
-
+ ret = data->probe(pdev, plat_dat, &stmmac_res);
+ if (ret < 0) {
if (ret != -EPROBE_DEFER)
dev_err(&pdev->dev, "failed to probe subdriver: %d\n",
ret);
int ret;
int i;
+ plat->phy_addr = -1;
plat->clk_csr = 5;
plat->has_gmac = 0;
plat->has_gmac4 = 1;
struct plat_stmmacenet_data *plat)
{
plat->bus_id = 1;
- plat->phy_addr = 0;
plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
plat->serdes_powerup = intel_serdes_powerup;
struct plat_stmmacenet_data *plat)
{
plat->bus_id = 1;
- plat->phy_addr = 0;
plat->phy_interface = PHY_INTERFACE_MODE_RGMII;
return ehl_common_data(pdev, plat);
struct plat_stmmacenet_data *plat)
{
plat->bus_id = 2;
- plat->phy_addr = 1;
return ehl_common_data(pdev, plat);
}
struct plat_stmmacenet_data *plat)
{
plat->bus_id = 3;
- plat->phy_addr = 1;
return ehl_common_data(pdev, plat);
}
struct plat_stmmacenet_data *plat)
{
plat->bus_id = 1;
- plat->phy_addr = 0;
plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
plat->serdes_powerup = intel_serdes_powerup;
plat->serdes_powerdown = intel_serdes_powerdown;
dev_err(dwmac->dev, "unsupported phy-mode %s\n",
phy_modes(dwmac->phy_mode));
return -EINVAL;
- };
+ }
if (rx_dly_config & PRG_ETH0_ADJ_ENABLE) {
if (!dwmac->timing_adj_clk) {
*/
#define GMAC4_LPI_CTRL_STATUS 0xd0
#define GMAC4_LPI_TIMER_CTRL 0xd4
+#define GMAC4_LPI_ENTRY_TIMER 0xd8
/* LPI control and status defines */
#define GMAC4_LPI_CTRL_STATUS_LPITCSE BIT(21) /* LPI Tx Clock Stop Enable */
+#define GMAC4_LPI_CTRL_STATUS_LPIATE BIT(20) /* LPI Timer Enable */
#define GMAC4_LPI_CTRL_STATUS_LPITXA BIT(19) /* Enable LPI TX Automate */
#define GMAC4_LPI_CTRL_STATUS_PLS BIT(17) /* PHY Link Status */
#define GMAC4_LPI_CTRL_STATUS_LPIEN BIT(16) /* LPI Enable */
writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);
}
+static void dwmac4_set_eee_lpi_entry_timer(struct mac_device_info *hw, int et)
+{
+ void __iomem *ioaddr = hw->pcsr;
+ int value = et & STMMAC_ET_MAX;
+ int regval;
+
+ /* Program LPI entry timer value into register */
+ writel(value, ioaddr + GMAC4_LPI_ENTRY_TIMER);
+
+ /* Enable/disable LPI entry timer */
+ regval = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
+ regval |= GMAC4_LPI_CTRL_STATUS_LPIEN | GMAC4_LPI_CTRL_STATUS_LPITXA;
+
+ if (et)
+ regval |= GMAC4_LPI_CTRL_STATUS_LPIATE;
+ else
+ regval &= ~GMAC4_LPI_CTRL_STATUS_LPIATE;
+
+ writel(regval, ioaddr + GMAC4_LPI_CTRL_STATUS);
+}
+
static void dwmac4_set_eee_timer(struct mac_device_info *hw, int ls, int tw)
{
void __iomem *ioaddr = hw->pcsr;
.get_umac_addr = dwmac4_get_umac_addr,
.set_eee_mode = dwmac4_set_eee_mode,
.reset_eee_mode = dwmac4_reset_eee_mode,
+ .set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer,
.set_eee_timer = dwmac4_set_eee_timer,
.set_eee_pls = dwmac4_set_eee_pls,
.pcs_ctrl_ane = dwmac4_ctrl_ane,
.get_umac_addr = dwmac4_get_umac_addr,
.set_eee_mode = dwmac4_set_eee_mode,
.reset_eee_mode = dwmac4_reset_eee_mode,
+ .set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer,
.set_eee_timer = dwmac4_set_eee_timer,
.set_eee_pls = dwmac4_set_eee_pls,
.pcs_ctrl_ane = dwmac4_ctrl_ane,
.get_umac_addr = dwmac4_get_umac_addr,
.set_eee_mode = dwmac4_set_eee_mode,
.reset_eee_mode = dwmac4_reset_eee_mode,
+ .set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer,
.set_eee_timer = dwmac4_set_eee_timer,
.set_eee_pls = dwmac4_set_eee_pls,
.pcs_ctrl_ane = dwmac4_ctrl_ane,
void (*set_eee_mode)(struct mac_device_info *hw,
bool en_tx_lpi_clockgating);
void (*reset_eee_mode)(struct mac_device_info *hw);
+ void (*set_eee_lpi_entry_timer)(struct mac_device_info *hw, int et);
void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw);
void (*set_eee_pls)(struct mac_device_info *hw, int link);
void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x,
stmmac_do_void_callback(__priv, mac, set_eee_mode, __args)
#define stmmac_reset_eee_mode(__priv, __args...) \
stmmac_do_void_callback(__priv, mac, reset_eee_mode, __args)
+#define stmmac_set_eee_lpi_timer(__priv, __args...) \
+ stmmac_do_void_callback(__priv, mac, set_eee_lpi_entry_timer, __args)
#define stmmac_set_eee_timer(__priv, __args...) \
stmmac_do_void_callback(__priv, mac, set_eee_timer, __args)
#define stmmac_set_eee_pls(__priv, __args...) \
#define DRV_MODULE_VERSION "Jan_2016"
#include <linux/clk.h>
+#include <linux/hrtimer.h>
#include <linux/if_vlan.h>
#include <linux/stmmac.h>
#include <linux/phylink.h>
struct stmmac_tx_queue {
u32 tx_count_frames;
int tbs;
- struct timer_list txtimer;
+ struct hrtimer txtimer;
u32 queue_index;
struct stmmac_priv *priv_data;
struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp;
int tx_lpi_timer;
int tx_lpi_enabled;
int eee_tw_timer;
+ bool eee_sw_timer_en;
unsigned int mode;
unsigned int chain_mode;
int extend_desc;
static void stmmac_exit_fs(struct net_device *dev);
#endif
-#define STMMAC_COAL_TIMER(x) (jiffies + usecs_to_jiffies(x))
+#define STMMAC_COAL_TIMER(x) (ns_to_ktime((x) * NSEC_PER_USEC))
/**
* stmmac_verify_args - verify the driver parameters.
return dirty;
}
+static void stmmac_lpi_entry_timer_config(struct stmmac_priv *priv, bool en)
+{
+ int tx_lpi_timer;
+
+ /* Clear/set the SW EEE timer flag based on LPI ET enablement */
+ priv->eee_sw_timer_en = en ? 0 : 1;
+ tx_lpi_timer = en ? priv->tx_lpi_timer : 0;
+ stmmac_set_eee_lpi_timer(priv, priv->hw, tx_lpi_timer);
+}
+
/**
* stmmac_enable_eee_mode - check and enter in LPI mode
* @priv: driver private structure
*/
void stmmac_disable_eee_mode(struct stmmac_priv *priv)
{
+ if (!priv->eee_sw_timer_en) {
+ stmmac_lpi_entry_timer_config(priv, 0);
+ return;
+ }
+
stmmac_reset_eee_mode(priv, priv->hw);
del_timer_sync(&priv->eee_ctrl_timer);
priv->tx_path_in_lpi_mode = false;
if (!priv->eee_active) {
if (priv->eee_enabled) {
netdev_dbg(priv->dev, "disable EEE\n");
+ stmmac_lpi_entry_timer_config(priv, 0);
del_timer_sync(&priv->eee_ctrl_timer);
stmmac_set_eee_timer(priv, priv->hw, 0, eee_tw_timer);
}
eee_tw_timer);
}
- mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer));
+ if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) {
+ del_timer_sync(&priv->eee_ctrl_timer);
+ priv->tx_path_in_lpi_mode = false;
+ stmmac_lpi_entry_timer_config(priv, 1);
+ } else {
+ stmmac_lpi_entry_timer_config(priv, 0);
+ mod_timer(&priv->eee_ctrl_timer,
+ STMMAC_LPI_T(priv->tx_lpi_timer));
+ }
mutex_unlock(&priv->lock);
netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n");
netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, queue));
}
- if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) {
+ if (priv->eee_enabled && !priv->tx_path_in_lpi_mode &&
+ priv->eee_sw_timer_en) {
stmmac_enable_eee_mode(priv);
mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer));
}
/* We still have pending packets, let's call for a new scheduling */
if (tx_q->dirty_tx != tx_q->cur_tx)
- mod_timer(&tx_q->txtimer, STMMAC_COAL_TIMER(priv->tx_coal_timer));
+ hrtimer_start(&tx_q->txtimer, STMMAC_COAL_TIMER(priv->tx_coal_timer),
+ HRTIMER_MODE_REL);
__netif_tx_unlock_bh(netdev_get_tx_queue(priv->dev, queue));
{
struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
- mod_timer(&tx_q->txtimer, STMMAC_COAL_TIMER(priv->tx_coal_timer));
+ hrtimer_start(&tx_q->txtimer, STMMAC_COAL_TIMER(priv->tx_coal_timer),
+ HRTIMER_MODE_REL);
}
/**
* Description:
* This is the timer handler to directly invoke the stmmac_tx_clean.
*/
-static void stmmac_tx_timer(struct timer_list *t)
+static enum hrtimer_restart stmmac_tx_timer(struct hrtimer *t)
{
- struct stmmac_tx_queue *tx_q = from_timer(tx_q, t, txtimer);
+ struct stmmac_tx_queue *tx_q = container_of(t, struct stmmac_tx_queue, txtimer);
struct stmmac_priv *priv = tx_q->priv_data;
struct stmmac_channel *ch;
spin_unlock_irqrestore(&ch->lock, flags);
__napi_schedule(&ch->tx_napi);
}
+
+ return HRTIMER_NORESTART;
}
/**
for (chan = 0; chan < tx_channel_count; chan++) {
struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan];
- timer_setup(&tx_q->txtimer, stmmac_tx_timer, 0);
+ hrtimer_init(&tx_q->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ tx_q->txtimer.function = stmmac_tx_timer;
}
}
phylink_stop(priv->phylink);
for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++)
- del_timer_sync(&priv->tx_queue[chan].txtimer);
+ hrtimer_cancel(&priv->tx_queue[chan].txtimer);
stmmac_hw_teardown(dev);
init_error:
stmmac_disable_all_queues(priv);
for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++)
- del_timer_sync(&priv->tx_queue[chan].txtimer);
+ hrtimer_cancel(&priv->tx_queue[chan].txtimer);
/* Free the IRQ lines */
free_irq(dev->irq, dev);
tx_q = &priv->tx_queue[queue];
first_tx = tx_q->cur_tx;
- if (priv->tx_path_in_lpi_mode)
+ if (priv->tx_path_in_lpi_mode && priv->eee_sw_timer_en)
stmmac_disable_eee_mode(priv);
/* Manage oversized TCP frames for GMAC4 device */
stmmac_disable_all_queues(priv);
for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++)
- del_timer_sync(&priv->tx_queue[chan].txtimer);
+ hrtimer_cancel(&priv->tx_queue[chan].txtimer);
/* Stop TX/RX DMA */
stmmac_stop_all_dma(priv);
struct device_node *np = pdev->dev.of_node;
struct plat_stmmacenet_data *plat;
struct stmmac_dma_cfg *dma_cfg;
+ void *ret;
int rc;
plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
clk_prepare_enable(plat->stmmac_clk);
}
- plat->pclk = devm_clk_get(&pdev->dev, "pclk");
+ plat->pclk = devm_clk_get_optional(&pdev->dev, "pclk");
if (IS_ERR(plat->pclk)) {
- if (PTR_ERR(plat->pclk) == -EPROBE_DEFER)
- goto error_pclk_get;
-
- plat->pclk = NULL;
+ ret = plat->pclk;
+ goto error_pclk_get;
}
clk_prepare_enable(plat->pclk);
dev_dbg(&pdev->dev, "PTP rate %d\n", plat->clk_ptp_rate);
}
- plat->stmmac_rst = devm_reset_control_get(&pdev->dev,
- STMMAC_RESOURCE_NAME);
+ plat->stmmac_rst = devm_reset_control_get_optional(&pdev->dev,
+ STMMAC_RESOURCE_NAME);
if (IS_ERR(plat->stmmac_rst)) {
- if (PTR_ERR(plat->stmmac_rst) == -EPROBE_DEFER)
- goto error_hw_init;
-
- dev_info(&pdev->dev, "no reset control found\n");
- plat->stmmac_rst = NULL;
+ ret = plat->stmmac_rst;
+ goto error_hw_init;
}
return plat;
error_pclk_get:
clk_disable_unprepare(plat->stmmac_clk);
- return ERR_PTR(-EPROBE_DEFER);
+ return ret;
}
/**
if (!vid)
unreg_mcast = port_mask;
dev_info(common->dev, "Adding vlan %d to vlan filter\n", vid);
- ret = cpsw_ale_add_vlan(common->ale, vid, port_mask,
- unreg_mcast, port_mask, 0);
+ ret = cpsw_ale_vlan_add_modify(common->ale, vid, port_mask,
+ unreg_mcast, port_mask, 0);
pm_runtime_put(common->dev);
return ret;
__be16 proto, u16 vid)
{
struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+ struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
int ret;
if (!netif_running(ndev) || !vid)
}
dev_info(common->dev, "Removing vlan %d from vlan filter\n", vid);
- ret = cpsw_ale_del_vlan(common->ale, vid, 0);
+ ret = cpsw_ale_del_vlan(common->ale, vid,
+ BIT(port->port_id) | ALE_PORT_HOST);
pm_runtime_put(common->dev);
return ret;
}
-static void am65_cpsw_slave_set_promisc_2g(struct am65_cpsw_port *port,
- bool promisc)
+static void am65_cpsw_slave_set_promisc(struct am65_cpsw_port *port,
+ bool promisc)
{
struct am65_cpsw_common *common = port->common;
bool promisc;
promisc = !!(ndev->flags & IFF_PROMISC);
- am65_cpsw_slave_set_promisc_2g(port, promisc);
+ am65_cpsw_slave_set_promisc(port, promisc);
if (promisc)
return;
cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT,
AM65_CPSW_NAV_PS_DATA_SIZE);
- cppi5_hdesc_attach_buf(desc_rx, 0, 0, buf_dma, skb_tailroom(skb));
+ cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb));
swdata = cppi5_hdesc_get_swdata(desc_rx);
*((void **)swdata) = skb;
writel(common->rx_flow_id_base,
host_p->port_base + AM65_CPSW_PORT0_REG_FLOW_ID_OFFSET);
/* en tx crc offload */
- if (features & NETIF_F_HW_CSUM)
- writel(AM65_CPSW_P0_REG_CTL_RX_CHECKSUM_EN,
- host_p->port_base + AM65_CPSW_P0_REG_CTL);
+ writel(AM65_CPSW_P0_REG_CTL_RX_CHECKSUM_EN, host_p->port_base + AM65_CPSW_P0_REG_CTL);
am65_cpsw_nuss_set_p0_ptype(common);
am65_cpsw_port_set_sl_mac(port, ndev->dev_addr);
- if (port->slave.mac_only)
+ if (port->slave.mac_only) {
/* enable mac-only mode on port */
cpsw_ale_control_set(common->ale, port->port_id,
ALE_PORT_MACONLY, 1);
- if (AM65_CPSW_IS_CPSW2G(common))
cpsw_ale_control_set(common->ale, port->port_id,
ALE_PORT_NOLEARN, 1);
+ }
port_mask = BIT(port->port_id) | ALE_PORT_HOST;
cpsw_ale_add_ucast(common->ale, ndev->dev_addr,
return ret;
}
- if (desc_dma & 0x1) {
+ if (cppi5_desc_is_tdcm(desc_dma)) {
dev_dbg(dev, "%s RX tdown flow: %u\n", __func__, flow_idx);
return 0;
}
dev_kfree_skb_any(skb);
}
+static struct sk_buff *
+am65_cpsw_nuss_tx_compl_packet(struct am65_cpsw_tx_chn *tx_chn,
+ dma_addr_t desc_dma)
+{
+ struct am65_cpsw_ndev_priv *ndev_priv;
+ struct am65_cpsw_ndev_stats *stats;
+ struct cppi5_host_desc_t *desc_tx;
+ struct net_device *ndev;
+ struct sk_buff *skb;
+ void **swdata;
+
+ desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
+ desc_dma);
+ swdata = cppi5_hdesc_get_swdata(desc_tx);
+ skb = *(swdata);
+ am65_cpsw_nuss_xmit_free(tx_chn, tx_chn->common->dev, desc_tx);
+
+ ndev = skb->dev;
+
+ am65_cpts_tx_timestamp(tx_chn->common->cpts, skb);
+
+ ndev_priv = netdev_priv(ndev);
+ stats = this_cpu_ptr(ndev_priv->stats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->tx_packets++;
+ stats->tx_bytes += skb->len;
+ u64_stats_update_end(&stats->syncp);
+
+ return skb;
+}
+
+static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_device *ndev,
+ struct netdev_queue *netif_txq)
+{
+ if (netif_tx_queue_stopped(netif_txq)) {
+ /* Check whether the queue is stopped due to stalled
+ * tx dma, if the queue is stopped then wake the queue
+ * as we have free desc for tx
+ */
+ __netif_tx_lock(netif_txq, smp_processor_id());
+ if (netif_running(ndev) &&
+ (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >= MAX_SKB_FRAGS))
+ netif_tx_wake_queue(netif_txq);
+
+ __netif_tx_unlock(netif_txq);
+ }
+}
+
static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
int chn, unsigned int budget)
{
- struct cppi5_host_desc_t *desc_tx;
struct device *dev = common->dev;
struct am65_cpsw_tx_chn *tx_chn;
struct netdev_queue *netif_txq;
struct sk_buff *skb;
dma_addr_t desc_dma;
int res, num_tx = 0;
- void **swdata;
tx_chn = &common->tx_chns[chn];
while (true) {
- struct am65_cpsw_ndev_priv *ndev_priv;
- struct am65_cpsw_ndev_stats *stats;
-
+ spin_lock(&tx_chn->lock);
res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma);
+ spin_unlock(&tx_chn->lock);
if (res == -ENODATA)
break;
- if (desc_dma & 0x1) {
+ if (cppi5_desc_is_tdcm(desc_dma)) {
if (atomic_dec_and_test(&common->tdown_cnt))
complete(&common->tdown_complete);
break;
}
- desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
- desc_dma);
- swdata = cppi5_hdesc_get_swdata(desc_tx);
- skb = *(swdata);
- am65_cpsw_nuss_xmit_free(tx_chn, dev, desc_tx);
-
+ skb = am65_cpsw_nuss_tx_compl_packet(tx_chn, desc_dma);
+ total_bytes = skb->len;
ndev = skb->dev;
+ napi_consume_skb(skb, budget);
+ num_tx++;
- am65_cpts_tx_timestamp(common->cpts, skb);
+ netif_txq = netdev_get_tx_queue(ndev, chn);
- ndev_priv = netdev_priv(ndev);
- stats = this_cpu_ptr(ndev_priv->stats);
- u64_stats_update_begin(&stats->syncp);
- stats->tx_packets++;
- stats->tx_bytes += skb->len;
- u64_stats_update_end(&stats->syncp);
+ netdev_tx_completed_queue(netif_txq, num_tx, total_bytes);
+ am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq);
+ }
+
+ dev_dbg(dev, "%s:%u pkt:%d\n", __func__, chn, num_tx);
+
+ return num_tx;
+}
+
+static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common,
+ int chn, unsigned int budget)
+{
+ struct device *dev = common->dev;
+ struct am65_cpsw_tx_chn *tx_chn;
+ struct netdev_queue *netif_txq;
+ unsigned int total_bytes = 0;
+ struct net_device *ndev;
+ struct sk_buff *skb;
+ dma_addr_t desc_dma;
+ int res, num_tx = 0;
+
+ tx_chn = &common->tx_chns[chn];
+
+ while (true) {
+ res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma);
+ if (res == -ENODATA)
+ break;
+
+ if (cppi5_desc_is_tdcm(desc_dma)) {
+ if (atomic_dec_and_test(&common->tdown_cnt))
+ complete(&common->tdown_complete);
+ break;
+ }
+
+ skb = am65_cpsw_nuss_tx_compl_packet(tx_chn, desc_dma);
+
+ ndev = skb->dev;
total_bytes += skb->len;
napi_consume_skb(skb, budget);
num_tx++;
netdev_tx_completed_queue(netif_txq, num_tx, total_bytes);
- if (netif_tx_queue_stopped(netif_txq)) {
- /* Check whether the queue is stopped due to stalled tx dma,
- * if the queue is stopped then wake the queue as
- * we have free desc for tx
- */
- __netif_tx_lock(netif_txq, smp_processor_id());
- if (netif_running(ndev) &&
- (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >=
- MAX_SKB_FRAGS))
- netif_tx_wake_queue(netif_txq);
+ am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq);
- __netif_tx_unlock(netif_txq);
- }
dev_dbg(dev, "%s:%u pkt:%d\n", __func__, chn, num_tx);
return num_tx;
struct am65_cpsw_tx_chn *tx_chn = am65_cpsw_napi_to_tx_chn(napi_tx);
int num_tx;
- num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common, tx_chn->id,
- budget);
+ if (AM65_CPSW_IS_CPSW2G(tx_chn->common))
+ num_tx = am65_cpsw_nuss_tx_compl_packets_2g(tx_chn->common, tx_chn->id, budget);
+ else
+ num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common, tx_chn->id, budget);
+
num_tx = min(num_tx, budget);
if (num_tx < budget) {
napi_complete(napi_tx);
cppi5_hdesc_set_pktlen(first_desc, pkt_len);
desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
- ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
+ if (AM65_CPSW_IS_CPSW2G(common)) {
+ ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
+ } else {
+ spin_lock_bh(&tx_chn->lock);
+ ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
+ spin_unlock_bh(&tx_chn->lock);
+ }
if (ret) {
dev_err(dev, "can't push desc %d\n", ret);
/* inform bql */
stats->tx_dropped = dev->stats.tx_dropped;
}
-static int am65_cpsw_nuss_ndo_slave_set_features(struct net_device *ndev,
- netdev_features_t features)
-{
- struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
- netdev_features_t changes = features ^ ndev->features;
- struct am65_cpsw_host *host_p;
-
- host_p = am65_common_get_host(common);
-
- if (changes & NETIF_F_HW_CSUM) {
- bool enable = !!(features & NETIF_F_HW_CSUM);
-
- dev_info(common->dev, "Turn %s tx-checksum-ip-generic\n",
- enable ? "ON" : "OFF");
- if (enable)
- writel(AM65_CPSW_P0_REG_CTL_RX_CHECKSUM_EN,
- host_p->port_base + AM65_CPSW_P0_REG_CTL);
- else
- writel(0,
- host_p->port_base + AM65_CPSW_P0_REG_CTL);
- }
-
- return 0;
-}
-
-static const struct net_device_ops am65_cpsw_nuss_netdev_ops_2g = {
+static const struct net_device_ops am65_cpsw_nuss_netdev_ops = {
.ndo_open = am65_cpsw_nuss_ndo_slave_open,
.ndo_stop = am65_cpsw_nuss_ndo_slave_stop,
.ndo_start_xmit = am65_cpsw_nuss_ndo_slave_xmit,
.ndo_vlan_rx_add_vid = am65_cpsw_nuss_ndo_slave_add_vid,
.ndo_vlan_rx_kill_vid = am65_cpsw_nuss_ndo_slave_kill_vid,
.ndo_do_ioctl = am65_cpsw_nuss_ndo_slave_ioctl,
- .ndo_set_features = am65_cpsw_nuss_ndo_slave_set_features,
.ndo_setup_tc = am65_cpsw_qos_ndo_setup_tc,
};
if (!port->disabled)
return;
- common->disabled_ports_mask |= BIT(port->port_id);
cpsw_ale_control_set(common->ale, port->port_id,
ALE_PORT_STATE, ALE_PORT_STATE_DISABLE);
snprintf(tx_chn->tx_chn_name,
sizeof(tx_chn->tx_chn_name), "tx%d", i);
+ spin_lock_init(&tx_chn->lock);
tx_chn->common = common;
tx_chn->id = i;
tx_chn->descs_num = max_desc_num;
tx_chn->tx_chn_name,
&tx_cfg);
if (IS_ERR(tx_chn->tx_chn)) {
- ret = PTR_ERR(tx_chn->tx_chn);
- dev_err(dev, "Failed to request tx dma channel %d\n",
- ret);
+ ret = dev_err_probe(dev, PTR_ERR(tx_chn->tx_chn),
+ "Failed to request tx dma channel\n");
goto err;
}
rx_chn->rx_chn = k3_udma_glue_request_rx_chn(dev, "rx", &rx_cfg);
if (IS_ERR(rx_chn->rx_chn)) {
- ret = PTR_ERR(rx_chn->rx_chn);
- dev_err(dev, "Failed to request rx dma channel %d\n", ret);
+ ret = dev_err_probe(dev, PTR_ERR(rx_chn->rx_chn),
+ "Failed to request rx dma channel\n");
goto err;
}
};
struct k3_ring_cfg fdqring_cfg = {
.elm_size = K3_RINGACC_RING_ELSIZE_8,
- .mode = K3_RINGACC_RING_MODE_MESSAGE,
.flags = K3_RINGACC_RING_SHARED,
};
struct k3_udma_glue_rx_flow_cfg rx_flow_cfg = {
rx_flow_cfg.ring_rxfdq0_id = fdqring_id;
rx_flow_cfg.rx_cfg.size = max_desc_num;
rx_flow_cfg.rxfdq_cfg.size = max_desc_num;
+ rx_flow_cfg.rxfdq_cfg.mode = common->pdata.fdqring_mode;
ret = k3_udma_glue_rx_flow_init(rx_chn->rx_chn,
i, &rx_flow_cfg);
return ret;
}
common->cpts = cpts;
+ /* Forbid PM runtime if CPTS is running.
+ * K3 CPSWxG modules may completely lose context during ON->OFF
+ * transitions depending on integration.
+ * AM65x/J721E MCU CPSW2G: false
+ * J721E MAIN_CPSW9G: true
+ */
+ pm_runtime_forbid(dev);
return 0;
}
return PTR_ERR(port->slave.mac_sl);
port->disabled = !of_device_is_available(port_np);
- if (port->disabled)
+ if (port->disabled) {
+ common->disabled_ports_mask |= BIT(port->port_id);
continue;
+ }
port->slave.ifphy = devm_of_phy_get(dev, port_np, NULL);
if (IS_ERR(port->slave.ifphy)) {
/* get phy/link info */
if (of_phy_is_fixed_link(port_np)) {
ret = of_phy_register_fixed_link(port_np);
- if (ret) {
- if (ret != -EPROBE_DEFER)
- dev_err(dev, "%pOF failed to register fixed-link phy: %d\n",
- port_np, ret);
- return ret;
- }
+ if (ret)
+ return dev_err_probe(dev, ret,
+ "failed to register fixed-link phy %pOF\n",
+ port_np);
port->slave.phy_node = of_node_get(port_np);
} else {
port->slave.phy_node =
}
of_node_put(node);
+ /* is there at least one ext.port */
+ if (!(~common->disabled_ports_mask & GENMASK(common->port_num, 1))) {
+ dev_err(dev, "No Ext. port are available\n");
+ return -ENODEV;
+ }
+
return 0;
}
free_percpu(stats);
}
-static int am65_cpsw_nuss_init_ndev_2g(struct am65_cpsw_common *common)
+static int
+am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
{
struct am65_cpsw_ndev_priv *ndev_priv;
struct device *dev = common->dev;
struct am65_cpsw_port *port;
int ret;
- port = am65_common_get_port(common, 1);
+ port = &common->ports[port_idx];
+
+ if (port->disabled)
+ return 0;
/* alloc netdev */
port->ndev = devm_alloc_etherdev_mqs(common->dev,
port->ndev->features = port->ndev->hw_features |
NETIF_F_HW_VLAN_CTAG_FILTER;
port->ndev->vlan_features |= NETIF_F_SG;
- port->ndev->netdev_ops = &am65_cpsw_nuss_netdev_ops_2g;
+ port->ndev->netdev_ops = &am65_cpsw_nuss_netdev_ops;
port->ndev->ethtool_ops = &am65_cpsw_ethtool_ops_slave;
/* Disable TX checksum offload by default due to HW bug */
ret = devm_add_action_or_reset(dev, am65_cpsw_pcpu_stats_free,
ndev_priv->stats);
- if (ret) {
- dev_err(dev, "Failed to add percpu stat free action %d\n", ret);
- return ret;
+ if (ret)
+ dev_err(dev, "failed to add percpu stat free action %d\n", ret);
+
+ if (!common->dma_ndev)
+ common->dma_ndev = port->ndev;
+
+ return ret;
+}
+
+static int am65_cpsw_nuss_init_ndevs(struct am65_cpsw_common *common)
+{
+ int ret;
+ int i;
+
+ for (i = 0; i < common->port_num; i++) {
+ ret = am65_cpsw_nuss_init_port_ndev(common, i);
+ if (ret)
+ return ret;
}
- netif_napi_add(port->ndev, &common->napi_rx,
+ netif_napi_add(common->dma_ndev, &common->napi_rx,
am65_cpsw_nuss_rx_poll, NAPI_POLL_WEIGHT);
return ret;
}
-static int am65_cpsw_nuss_ndev_add_napi_2g(struct am65_cpsw_common *common)
+static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common)
{
struct device *dev = common->dev;
- struct am65_cpsw_port *port;
int i, ret = 0;
- port = am65_common_get_port(common, 1);
-
for (i = 0; i < common->tx_ch_num; i++) {
struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i];
- netif_tx_napi_add(port->ndev, &tx_chn->napi_tx,
+ netif_tx_napi_add(common->dma_ndev, &tx_chn->napi_tx,
am65_cpsw_nuss_tx_poll, NAPI_POLL_WEIGHT);
ret = devm_request_irq(dev, tx_chn->irq,
return ret;
}
-static int am65_cpsw_nuss_ndev_reg_2g(struct am65_cpsw_common *common)
+static void am65_cpsw_nuss_cleanup_ndev(struct am65_cpsw_common *common)
+{
+ struct am65_cpsw_port *port;
+ int i;
+
+ for (i = 0; i < common->port_num; i++) {
+ port = &common->ports[i];
+ if (port->ndev)
+ unregister_netdev(port->ndev);
+ }
+}
+
+static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
{
struct device *dev = common->dev;
struct am65_cpsw_port *port;
- int ret = 0;
+ int ret = 0, i;
- port = am65_common_get_port(common, 1);
- ret = am65_cpsw_nuss_ndev_add_napi_2g(common);
+ ret = am65_cpsw_nuss_ndev_add_tx_napi(common);
if (ret)
- goto err;
+ return ret;
ret = devm_request_irq(dev, common->rx_chns.irq,
am65_cpsw_nuss_rx_irq,
if (ret) {
dev_err(dev, "failure requesting rx irq %u, %d\n",
common->rx_chns.irq, ret);
- goto err;
+ return ret;
+ }
+
+ for (i = 0; i < common->port_num; i++) {
+ port = &common->ports[i];
+
+ if (!port->ndev)
+ continue;
+
+ ret = register_netdev(port->ndev);
+ if (ret) {
+ dev_err(dev, "error registering slave net device%i %d\n",
+ i, ret);
+ goto err_cleanup_ndev;
+ }
}
- ret = register_netdev(port->ndev);
- if (ret)
- dev_err(dev, "error registering slave net device %d\n", ret);
/* can't auto unregister ndev using devm_add_action() due to
* devres release sequence in DD core for DMA
*/
-err:
+ return 0;
+
+err_cleanup_ndev:
+ am65_cpsw_nuss_cleanup_ndev(common);
return ret;
}
if (ret)
return ret;
- return am65_cpsw_nuss_ndev_add_napi_2g(common);
-}
-
-static void am65_cpsw_nuss_cleanup_ndev(struct am65_cpsw_common *common)
-{
- struct am65_cpsw_port *port;
- int i;
-
- for (i = 0; i < common->port_num; i++) {
- port = &common->ports[i];
- if (port->ndev)
- unregister_netdev(port->ndev);
- }
+ return am65_cpsw_nuss_ndev_add_tx_napi(common);
}
struct am65_cpsw_soc_pdata {
static const struct am65_cpsw_pdata am65x_sr1_0 = {
.quirks = AM65_CPSW_QUIRK_I2027_NO_TX_CSUM,
+ .ale_dev_id = "am65x-cpsw2g",
+ .fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE,
};
static const struct am65_cpsw_pdata j721e_pdata = {
.quirks = 0,
+ .ale_dev_id = "am65x-cpsw2g",
+ .fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE,
};
static const struct of_device_id am65_cpsw_nuss_of_mtable[] = {
return -ENOENT;
of_node_put(node);
- if (common->port_num != 1)
- return -EOPNOTSUPP;
-
common->rx_flow_id_base = -1;
init_completion(&common->tdown_complete);
common->tx_ch_num = 1;
return -ENOMEM;
clk = devm_clk_get(dev, "fck");
- if (IS_ERR(clk)) {
- ret = PTR_ERR(clk);
-
- if (ret != -EPROBE_DEFER)
- dev_err(dev, "error getting fck clock %d\n", ret);
- return ret;
- }
+ if (IS_ERR(clk))
+ return dev_err_probe(dev, PTR_ERR(clk), "getting fck clock\n");
common->bus_freq = clk_get_rate(clk);
pm_runtime_enable(dev);
ale_params.ale_ageout = AM65_CPSW_ALE_AGEOUT_DEFAULT;
ale_params.ale_ports = common->port_num + 1;
ale_params.ale_regs = common->cpsw_base + AM65_CPSW_NU_ALE_BASE;
- ale_params.dev_id = "am65x-cpsw2g";
+ ale_params.dev_id = common->pdata.ale_dev_id;
ale_params.bus_freq = common->bus_freq;
common->ale = cpsw_ale_create(&ale_params);
dev_set_drvdata(dev, common);
- ret = am65_cpsw_nuss_init_ndev_2g(common);
+ ret = am65_cpsw_nuss_init_ndevs(common);
if (ret)
goto err_of_clear;
- ret = am65_cpsw_nuss_ndev_reg_2g(common);
+ ret = am65_cpsw_nuss_register_ndevs(common);
if (ret)
goto err_of_clear;
#include <linux/netdevice.h>
#include <linux/phy.h>
#include <linux/platform_device.h>
+#include <linux/soc/ti/k3-ringacc.h>
#include "am65-cpsw-qos.h"
struct am65_cpts;
struct am65_cpsw_common *common;
struct k3_cppi_desc_pool *desc_pool;
struct k3_udma_glue_tx_channel *tx_chn;
+ spinlock_t lock; /* protect TX rings in multi-port mode */
int irq;
u32 id;
u32 descs_num;
struct am65_cpsw_pdata {
u32 quirks;
+ enum k3_ring_mode fdqring_mode;
+ const char *ale_dev_id;
};
struct am65_cpsw_common {
struct am65_cpsw_host host;
struct am65_cpsw_port *ports;
u32 disabled_ports_mask;
+ struct net_device *dma_ndev;
int usage_count; /* number of opened ports */
struct cpsw_ale *ale;
return 0;
}
-static void cpsw_ale_del_vlan_modify(struct cpsw_ale *ale, u32 *ale_entry,
- u16 vid, int port_mask)
+static void cpsw_ale_vlan_del_modify_int(struct cpsw_ale *ale, u32 *ale_entry,
+ u16 vid, int port_mask)
{
int reg_mcast, unreg_mcast;
int members, untag;
ALE_ENT_VID_MEMBER_LIST);
members &= ~port_mask;
if (!members) {
+ cpsw_ale_set_vlan_untag(ale, ale_entry, vid, 0);
cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
return;
}
ALE_ENT_VID_MEMBER_LIST, members);
}
-int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask)
+int cpsw_ale_vlan_del_modify(struct cpsw_ale *ale, u16 vid, int port_mask)
{
u32 ale_entry[ALE_ENTRY_WORDS] = {0, 0, 0};
int idx;
cpsw_ale_read(ale, idx, ale_entry);
- if (port_mask) {
- cpsw_ale_del_vlan_modify(ale, ale_entry, vid, port_mask);
- } else {
+ cpsw_ale_vlan_del_modify_int(ale, ale_entry, vid, port_mask);
+ cpsw_ale_write(ale, idx, ale_entry);
+
+ return 0;
+}
+
+int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask)
+{
+ u32 ale_entry[ALE_ENTRY_WORDS] = {0, 0, 0};
+ int members, idx;
+
+ idx = cpsw_ale_match_vlan(ale, vid);
+ if (idx < 0)
+ return -ENOENT;
+
+ cpsw_ale_read(ale, idx, ale_entry);
+
+ /* if !port_mask - force remove VLAN (legacy).
+ * Check if there are other VLAN members ports
+ * if no - remove VLAN.
+ * if yes it means same VLAN was added to >1 port in multi port mode, so
+ * remove port_mask ports from VLAN ALE entry excluding Host port.
+ */
+ members = cpsw_ale_vlan_get_fld(ale, ale_entry, ALE_ENT_VID_MEMBER_LIST);
+ members &= ~port_mask;
+
+ if (!port_mask || !members) {
+ /* last port or force remove - remove VLAN */
cpsw_ale_set_vlan_untag(ale, ale_entry, vid, 0);
cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
+ } else {
+ port_mask &= ~ALE_PORT_HOST;
+ cpsw_ale_vlan_del_modify_int(ale, ale_entry, vid, port_mask);
}
cpsw_ale_write(ale, idx, ale_entry);
int cpsw_ale_vlan_add_modify(struct cpsw_ale *ale, u16 vid, int port_mask,
int untag_mask, int reg_mcast, int unreg_mcast);
+int cpsw_ale_vlan_del_modify(struct cpsw_ale *ale, u16 vid, int port_mask);
void cpsw_ale_set_unreg_mcast(struct cpsw_ale *ale, int unreg_mcast_mask,
bool add);
else
port_mask = BIT(priv->emac_port);
- ret = cpsw_ale_del_vlan(cpsw->ale, vid, port_mask);
+ ret = cpsw_ale_vlan_del_modify(cpsw->ale, vid, port_mask);
if (ret != 0)
return ret;
static void tlan_finish_reset(struct net_device *);
static void tlan_set_mac(struct net_device *, int areg, char *mac);
+static void __tlan_phy_print(struct net_device *);
static void tlan_phy_print(struct net_device *);
static void tlan_phy_detect(struct net_device *);
static void tlan_phy_power_down(struct net_device *);
static int tlan_phy_dp83840a_check(struct net_device *);
*/
-static bool tlan_mii_read_reg(struct net_device *, u16, u16, u16 *);
+static bool __tlan_mii_read_reg(struct net_device *, u16, u16, u16 *);
+static void tlan_mii_read_reg(struct net_device *, u16, u16, u16 *);
static void tlan_mii_send_data(u16, u32, unsigned);
static void tlan_mii_sync(u16);
+static void __tlan_mii_write_reg(struct net_device *, u16, u16, u16);
static void tlan_mii_write_reg(struct net_device *, u16, u16, u16);
static void tlan_ee_send_start(u16);
tlan_handle_rx_eoc
};
-static inline void
+static void
tlan_set_timer(struct net_device *dev, u32 ticks, u32 type)
{
struct tlan_priv *priv = netdev_priv(dev);
unsigned long flags = 0;
- if (!in_irq())
- spin_lock_irqsave(&priv->lock, flags);
+ spin_lock_irqsave(&priv->lock, flags);
if (priv->timer.function != NULL &&
priv->timer_type != TLAN_TIMER_ACTIVITY) {
- if (!in_irq())
- spin_unlock_irqrestore(&priv->lock, flags);
+ spin_unlock_irqrestore(&priv->lock, flags);
return;
}
priv->timer.function = tlan_timer;
- if (!in_irq())
- spin_unlock_irqrestore(&priv->lock, flags);
+ spin_unlock_irqrestore(&priv->lock, flags);
priv->timer_set_at = jiffies;
priv->timer_type = type;
dev->name, (unsigned) net_sts);
}
if ((net_sts & TLAN_NET_STS_MIRQ) && (priv->phy_num == 0)) {
- tlan_mii_read_reg(dev, phy, TLAN_TLPHY_STS, &tlphy_sts);
- tlan_mii_read_reg(dev, phy, TLAN_TLPHY_CTL, &tlphy_ctl);
+ __tlan_mii_read_reg(dev, phy, TLAN_TLPHY_STS, &tlphy_sts);
+ __tlan_mii_read_reg(dev, phy, TLAN_TLPHY_CTL, &tlphy_ctl);
if (!(tlphy_sts & TLAN_TS_POLOK) &&
!(tlphy_ctl & TLAN_TC_SWAPOL)) {
tlphy_ctl |= TLAN_TC_SWAPOL;
- tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL,
- tlphy_ctl);
+ __tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL,
+ tlphy_ctl);
} else if ((tlphy_sts & TLAN_TS_POLOK) &&
(tlphy_ctl & TLAN_TC_SWAPOL)) {
tlphy_ctl &= ~TLAN_TC_SWAPOL;
- tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL,
- tlphy_ctl);
+ __tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL,
+ tlphy_ctl);
}
if (debug)
- tlan_phy_print(dev);
+ __tlan_phy_print(dev);
}
}
/*********************************************************************
- * tlan_phy_print
+ * __tlan_phy_print
*
* Returns:
* Nothing
*
********************************************************************/
-static void tlan_phy_print(struct net_device *dev)
+static void __tlan_phy_print(struct net_device *dev)
{
struct tlan_priv *priv = netdev_priv(dev);
u16 i, data0, data1, data2, data3, phy;
+ lockdep_assert_held(&priv->lock);
+
phy = priv->phy[priv->phy_num];
if (priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY) {
netdev_info(dev, "PHY 0x%02x\n", phy);
pr_info(" Off. +0 +1 +2 +3\n");
for (i = 0; i < 0x20; i += 4) {
- tlan_mii_read_reg(dev, phy, i, &data0);
- tlan_mii_read_reg(dev, phy, i + 1, &data1);
- tlan_mii_read_reg(dev, phy, i + 2, &data2);
- tlan_mii_read_reg(dev, phy, i + 3, &data3);
+ __tlan_mii_read_reg(dev, phy, i, &data0);
+ __tlan_mii_read_reg(dev, phy, i + 1, &data1);
+ __tlan_mii_read_reg(dev, phy, i + 2, &data2);
+ __tlan_mii_read_reg(dev, phy, i + 3, &data3);
pr_info(" 0x%02x 0x%04hx 0x%04hx 0x%04hx 0x%04hx\n",
i, data0, data1, data2, data3);
}
}
+static void tlan_phy_print(struct net_device *dev)
+{
+ struct tlan_priv *priv = netdev_priv(dev);
+ unsigned long flags;
+ spin_lock_irqsave(&priv->lock, flags);
+ __tlan_phy_print(dev);
+ spin_unlock_irqrestore(&priv->lock, flags);
+}
/*********************************************************************
/***************************************************************
- * tlan_mii_read_reg
+ * __tlan_mii_read_reg
*
* Returns:
* false if ack received ok
**************************************************************/
static bool
-tlan_mii_read_reg(struct net_device *dev, u16 phy, u16 reg, u16 *val)
+__tlan_mii_read_reg(struct net_device *dev, u16 phy, u16 reg, u16 *val)
{
u8 nack;
u16 sio, tmp;
bool err;
int minten;
struct tlan_priv *priv = netdev_priv(dev);
- unsigned long flags = 0;
+
+ lockdep_assert_held(&priv->lock);
err = false;
outw(TLAN_NET_SIO, dev->base_addr + TLAN_DIO_ADR);
sio = dev->base_addr + TLAN_DIO_DATA + TLAN_NET_SIO;
- if (!in_irq())
- spin_lock_irqsave(&priv->lock, flags);
-
tlan_mii_sync(dev->base_addr);
minten = tlan_get_bit(TLAN_NET_SIO_MINTEN, sio);
*val = tmp;
- if (!in_irq())
- spin_unlock_irqrestore(&priv->lock, flags);
-
return err;
-
}
+static void tlan_mii_read_reg(struct net_device *dev, u16 phy, u16 reg,
+ u16 *val)
+{
+ struct tlan_priv *priv = netdev_priv(dev);
+ unsigned long flags;
-
+ spin_lock_irqsave(&priv->lock, flags);
+ __tlan_mii_read_reg(dev, phy, reg, val);
+ spin_unlock_irqrestore(&priv->lock, flags);
+}
/***************************************************************
* tlan_mii_send_data
/***************************************************************
- * tlan_mii_write_reg
+ * __tlan_mii_write_reg
*
* Returns:
* Nothing
**************************************************************/
static void
-tlan_mii_write_reg(struct net_device *dev, u16 phy, u16 reg, u16 val)
+__tlan_mii_write_reg(struct net_device *dev, u16 phy, u16 reg, u16 val)
{
u16 sio;
int minten;
- unsigned long flags = 0;
struct tlan_priv *priv = netdev_priv(dev);
+ lockdep_assert_held(&priv->lock);
+
outw(TLAN_NET_SIO, dev->base_addr + TLAN_DIO_ADR);
sio = dev->base_addr + TLAN_DIO_DATA + TLAN_NET_SIO;
- if (!in_irq())
- spin_lock_irqsave(&priv->lock, flags);
-
tlan_mii_sync(dev->base_addr);
minten = tlan_get_bit(TLAN_NET_SIO_MINTEN, sio);
if (minten)
tlan_set_bit(TLAN_NET_SIO_MINTEN, sio);
- if (!in_irq())
- spin_unlock_irqrestore(&priv->lock, flags);
-
}
+static void
+tlan_mii_write_reg(struct net_device *dev, u16 phy, u16 reg, u16 val)
+{
+ struct tlan_priv *priv = netdev_priv(dev);
+ unsigned long flags;
+ spin_lock_irqsave(&priv->lock, flags);
+ __tlan_mii_write_reg(dev, phy, reg, val);
+ spin_unlock_irqrestore(&priv->lock, flags);
+}
/*****************************************************************************
config XILINX_EMACLITE
tristate "Xilinx 10/100 Ethernet Lite support"
- depends on PPC32 || MICROBLAZE || ARCH_ZYNQ || MIPS
+ depends on PPC32 || MICROBLAZE || ARCH_ZYNQ || MIPS || COMPILE_TEST
select PHYLIB
help
This driver supports the 10/100 Ethernet Lite from Xilinx.
* @dev: Pointer to device structure
* @phy_node: Pointer to device node structure
* @mii_bus: Pointer to MII bus structure
+ * @mii_clk_div: MII bus clock divider value
* @regs_start: Resource start for axienet device addresses
* @regs: Base address for the axienet_local device address space
* @dma_regs: Base address for the axidma device address space
struct phylink *phylink;
struct phylink_config phylink_config;
+ /* Reference to PCS/PMA PHY if used */
+ struct mdio_device *pcs_phy;
+
/* Clock for AXI bus */
struct clk *clk;
/* MDIO bus data */
struct mii_bus *mii_bus; /* MII bus reference */
+ u8 mii_clk_div; /* MII bus clock divider value */
/* IO registers, dma functions and IRQs */
resource_size_t regs_start;
dev_dbg(&ndev->dev, "axienet_open()\n");
- /* Disable the MDIO interface till Axi Ethernet Reset is completed.
- * When we do an Axi Ethernet reset, it resets the complete core
- * including the MDIO. MDIO must be disabled before resetting
- * and re-enabled afterwards.
+ /* When we do an Axi Ethernet reset, it resets the complete core
+ * including the MDIO. MDIO must be disabled before resetting.
* Hold MDIO bus lock to avoid MDIO accesses during the reset.
*/
mutex_lock(&lp->mii_bus->mdio_lock);
- axienet_mdio_disable(lp);
ret = axienet_device_reset(ndev);
- if (ret == 0)
- ret = axienet_mdio_enable(lp);
mutex_unlock(&lp->mii_bus->mdio_lock);
- if (ret < 0)
- return ret;
ret = phylink_of_phy_connect(lp->phylink, lp->dev->of_node, 0);
if (ret) {
/* Do a reset to ensure DMA is really stopped */
mutex_lock(&lp->mii_bus->mdio_lock);
- axienet_mdio_disable(lp);
__axienet_device_reset(lp);
- axienet_mdio_enable(lp);
mutex_unlock(&lp->mii_bus->mdio_lock);
cancel_work_sync(&lp->dma_err_task);
phylink_set(mask, Asym_Pause);
phylink_set(mask, Pause);
- phylink_set(mask, 1000baseX_Full);
- phylink_set(mask, 10baseT_Full);
- phylink_set(mask, 100baseT_Full);
- phylink_set(mask, 1000baseT_Full);
+
+ switch (state->interface) {
+ case PHY_INTERFACE_MODE_NA:
+ case PHY_INTERFACE_MODE_1000BASEX:
+ case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_GMII:
+ case PHY_INTERFACE_MODE_RGMII:
+ case PHY_INTERFACE_MODE_RGMII_ID:
+ case PHY_INTERFACE_MODE_RGMII_RXID:
+ case PHY_INTERFACE_MODE_RGMII_TXID:
+ phylink_set(mask, 1000baseX_Full);
+ phylink_set(mask, 1000baseT_Full);
+ if (state->interface == PHY_INTERFACE_MODE_1000BASEX)
+ break;
+ fallthrough;
+ case PHY_INTERFACE_MODE_MII:
+ phylink_set(mask, 100baseT_Full);
+ phylink_set(mask, 10baseT_Full);
+ default:
+ break;
+ }
bitmap_and(supported, supported, mask,
__ETHTOOL_LINK_MODE_MASK_NBITS);
{
struct net_device *ndev = to_net_dev(config->dev);
struct axienet_local *lp = netdev_priv(ndev);
- u32 emmc_reg, fcc_reg;
-
- state->interface = lp->phy_mode;
- emmc_reg = axienet_ior(lp, XAE_EMMC_OFFSET);
- if (emmc_reg & XAE_EMMC_LINKSPD_1000)
- state->speed = SPEED_1000;
- else if (emmc_reg & XAE_EMMC_LINKSPD_100)
- state->speed = SPEED_100;
- else
- state->speed = SPEED_10;
-
- state->pause = 0;
- fcc_reg = axienet_ior(lp, XAE_FCC_OFFSET);
- if (fcc_reg & XAE_FCC_FCTX_MASK)
- state->pause |= MLO_PAUSE_TX;
- if (fcc_reg & XAE_FCC_FCRX_MASK)
- state->pause |= MLO_PAUSE_RX;
-
- state->an_complete = 0;
- state->duplex = 1;
+ switch (state->interface) {
+ case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_1000BASEX:
+ phylink_mii_c22_pcs_get_state(lp->pcs_phy, state);
+ break;
+ default:
+ break;
+ }
}
static void axienet_mac_an_restart(struct phylink_config *config)
{
- /* Unsupported, do nothing */
+ struct net_device *ndev = to_net_dev(config->dev);
+ struct axienet_local *lp = netdev_priv(ndev);
+
+ phylink_mii_c22_pcs_an_restart(lp->pcs_phy);
}
static void axienet_mac_config(struct phylink_config *config, unsigned int mode,
const struct phylink_link_state *state)
{
- /* nothing meaningful to do */
+ struct net_device *ndev = to_net_dev(config->dev);
+ struct axienet_local *lp = netdev_priv(ndev);
+ int ret;
+
+ switch (state->interface) {
+ case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_1000BASEX:
+ ret = phylink_mii_c22_pcs_config(lp->pcs_phy, mode,
+ state->interface,
+ state->advertising);
+ if (ret < 0)
+ netdev_warn(ndev, "Failed to configure PCS: %d\n",
+ ret);
+ break;
+
+ default:
+ break;
+ }
}
static void axienet_mac_link_down(struct phylink_config *config,
axienet_setoptions(ndev, lp->options &
~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
- /* Disable the MDIO interface till Axi Ethernet Reset is completed.
- * When we do an Axi Ethernet reset, it resets the complete core
- * including the MDIO. MDIO must be disabled before resetting
- * and re-enabled afterwards.
+ /* When we do an Axi Ethernet reset, it resets the complete core
+ * including the MDIO. MDIO must be disabled before resetting.
* Hold MDIO bus lock to avoid MDIO accesses during the reset.
*/
mutex_lock(&lp->mii_bus->mdio_lock);
- axienet_mdio_disable(lp);
__axienet_device_reset(lp);
- axienet_mdio_enable(lp);
mutex_unlock(&lp->mii_bus->mdio_lock);
for (i = 0; i < lp->tx_bd_num; i++) {
dev_warn(&pdev->dev,
"error registering MDIO bus: %d\n", ret);
}
+ if (lp->phy_mode == PHY_INTERFACE_MODE_SGMII ||
+ lp->phy_mode == PHY_INTERFACE_MODE_1000BASEX) {
+ if (!lp->phy_node) {
+ dev_err(&pdev->dev, "phy-handle required for 1000BaseX/SGMII\n");
+ ret = -EINVAL;
+ goto free_netdev;
+ }
+ lp->pcs_phy = of_mdio_find_device(lp->phy_node);
+ if (!lp->pcs_phy) {
+ ret = -EPROBE_DEFER;
+ goto free_netdev;
+ }
+ lp->phylink_config.pcs_poll = true;
+ }
lp->phylink_config.dev = &ndev->dev;
lp->phylink_config.type = PHYLINK_NETDEV;
if (lp->phylink)
phylink_destroy(lp->phylink);
+ if (lp->pcs_phy)
+ put_device(&lp->pcs_phy->dev);
+
axienet_mdio_teardown(lp);
clk_disable_unprepare(lp->clk);
1, 20000);
}
+/* Enable the MDIO MDC. Called prior to a read/write operation */
+static void axienet_mdio_mdc_enable(struct axienet_local *lp)
+{
+ axienet_iow(lp, XAE_MDIO_MC_OFFSET,
+ ((u32)lp->mii_clk_div | XAE_MDIO_MC_MDIOEN_MASK));
+}
+
+/* Disable the MDIO MDC. Called after a read/write operation*/
+static void axienet_mdio_mdc_disable(struct axienet_local *lp)
+{
+ u32 mc_reg;
+
+ mc_reg = axienet_ior(lp, XAE_MDIO_MC_OFFSET);
+ axienet_iow(lp, XAE_MDIO_MC_OFFSET,
+ (mc_reg & ~XAE_MDIO_MC_MDIOEN_MASK));
+}
+
/**
* axienet_mdio_read - MDIO interface read function
* @bus: Pointer to mii bus structure
int ret;
struct axienet_local *lp = bus->priv;
+ axienet_mdio_mdc_enable(lp);
+
ret = axienet_mdio_wait_until_ready(lp);
- if (ret < 0)
+ if (ret < 0) {
+ axienet_mdio_mdc_disable(lp);
return ret;
+ }
axienet_iow(lp, XAE_MDIO_MCR_OFFSET,
(((phy_id << XAE_MDIO_MCR_PHYAD_SHIFT) &
XAE_MDIO_MCR_OP_READ_MASK));
ret = axienet_mdio_wait_until_ready(lp);
- if (ret < 0)
+ if (ret < 0) {
+ axienet_mdio_mdc_disable(lp);
return ret;
+ }
rc = axienet_ior(lp, XAE_MDIO_MRD_OFFSET) & 0x0000FFFF;
dev_dbg(lp->dev, "axienet_mdio_read(phy_id=%i, reg=%x) == %x\n",
phy_id, reg, rc);
+ axienet_mdio_mdc_disable(lp);
return rc;
}
dev_dbg(lp->dev, "axienet_mdio_write(phy_id=%i, reg=%x, val=%x)\n",
phy_id, reg, val);
+ axienet_mdio_mdc_enable(lp);
+
ret = axienet_mdio_wait_until_ready(lp);
- if (ret < 0)
+ if (ret < 0) {
+ axienet_mdio_mdc_disable(lp);
return ret;
+ }
axienet_iow(lp, XAE_MDIO_MWD_OFFSET, (u32) val);
axienet_iow(lp, XAE_MDIO_MCR_OFFSET,
XAE_MDIO_MCR_OP_WRITE_MASK));
ret = axienet_mdio_wait_until_ready(lp);
- if (ret < 0)
+ if (ret < 0) {
+ axienet_mdio_mdc_disable(lp);
return ret;
+ }
+ axienet_mdio_mdc_disable(lp);
return 0;
}
**/
int axienet_mdio_enable(struct axienet_local *lp)
{
- u32 clk_div, host_clock;
+ u32 host_clock;
+
+ lp->mii_clk_div = 0;
if (lp->clk) {
host_clock = clk_get_rate(lp->clk);
* "clock-frequency" from the CPU
*/
- clk_div = (host_clock / (MAX_MDIO_FREQ * 2)) - 1;
+ lp->mii_clk_div = (host_clock / (MAX_MDIO_FREQ * 2)) - 1;
/* If there is any remainder from the division of
* fHOST / (MAX_MDIO_FREQ * 2), then we need to add
* 1 to the clock divisor or we will surely be above 2.5 MHz
*/
if (host_clock % (MAX_MDIO_FREQ * 2))
- clk_div++;
+ lp->mii_clk_div++;
netdev_dbg(lp->ndev,
"Setting MDIO clock divisor to %u/%u Hz host clock.\n",
- clk_div, host_clock);
+ lp->mii_clk_div, host_clock);
- axienet_iow(lp, XAE_MDIO_MC_OFFSET, clk_div | XAE_MDIO_MC_MDIOEN_MASK);
+ axienet_iow(lp, XAE_MDIO_MC_OFFSET, lp->mii_clk_div | XAE_MDIO_MC_MDIOEN_MASK);
return axienet_mdio_wait_until_ready(lp);
}
* Return: 0 on success, -ETIMEDOUT on a timeout, -ENOMEM when
* mdiobus_alloc (to allocate memory for mii bus structure) fails.
*
- * Sets up the MDIO interface by initializing the MDIO clock and enabling the
- * MDIO interface in hardware. Register the MDIO interface.
+ * Sets up the MDIO interface by initializing the MDIO clock.
+ * Register the MDIO interface.
**/
int axienet_mdio_setup(struct axienet_local *lp)
{
lp->mii_bus = NULL;
return ret;
}
+ axienet_mdio_mdc_disable(lp);
return 0;
}
#define ALIGNMENT 4
/* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */
-#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32)adr)) % ALIGNMENT)
+#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((uintptr_t)adr)) % ALIGNMENT)
#ifdef __BIG_ENDIAN
#define xemaclite_readl ioread32be
* if it is configured in HW
*/
- addr = (void __iomem __force *)((u32 __force)addr ^
+ addr = (void __iomem __force *)((uintptr_t __force)addr ^
XEL_BUFFER_OFFSET);
reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
* will correct on subsequent calls
*/
if (drvdata->rx_ping_pong != 0)
- addr = (void __iomem __force *)((u32 __force)addr ^
- XEL_BUFFER_OFFSET);
+ addr = (void __iomem __force *)
+ ((uintptr_t __force)addr ^
+ XEL_BUFFER_OFFSET);
else
return 0; /* No data was available */
/**
* xemaclite_tx_timeout - Callback for Tx Timeout
* @dev: Pointer to the network device
+ * @txqueue: Unused
*
* This function is called when Tx time out occurs for Emaclite device.
*/
}
dev_info(dev,
- "Xilinx EmacLite at 0x%08X mapped to 0x%08X, irq=%d\n",
+ "Xilinx EmacLite at 0x%08X mapped to 0x%08lX, irq=%d\n",
(unsigned int __force)ndev->mem_start,
- (unsigned int __force)lp->base_addr, ndev->irq);
+ (unsigned long __force)lp->base_addr, ndev->irq);
return 0;
error:
#include <linux/bitrev.h>
#include <linux/pci.h>
-#ifndef lint
-static const char ID_sccs[] = "@(#)drvfbi.c 1.63 99/02/11 (C) SK " ;
-#endif
-
/*
* PCM active state
*/
#define KERNEL
#include "h/smtstate.h"
-#ifndef lint
-static const char ID_sccs[] = "@(#)ecm.c 2.7 99/08/05 (C) SK " ;
-#endif
-
/*
* FSM Macros
*/
/* For AIX event notification: */
/* Is a disconnect command remotely issued ? */
if (cmd == EC_DISCONNECT &&
- smc->mib.fddiSMTRemoteDisconnectFlag == TRUE)
+ smc->mib.fddiSMTRemoteDisconnectFlag == TRUE) {
AIX_EVENT (smc, (u_long) CIO_HARD_FAIL, (u_long)
FDDI_REMOTE_DISCONNECT, smt_get_event_word(smc),
smt_get_error_word(smc) );
+ }
/*jd 05-Aug-1999 Bug #10419 "Port Disconnect fails at Dup MAc Cond."*/
if (cmd == EC_CONNECT) {
#ifdef ESS
#ifndef lint
-static const char ID_sccs[] = "@(#)ess.c 1.10 96/02/23 (C) SK" ;
#define LINT_USE(x)
#else
#define LINT_USE(x) (x)=(x)
#include "h/fddi.h"
#include "h/smc.h"
-#ifndef lint
-static const char ID_sccs[] = "@(#)hwt.c 1.13 97/04/23 (C) SK " ;
-#endif
-
/*
* Prototypes of local functions.
*/
#define KERNEL
#include "h/smtstate.h"
-#ifndef lint
-static const char ID_sccs[] = "@(#)pcmplc.c 2.55 99/08/05 (C) SK " ;
-#endif
-
#ifdef FDDI_MIB
extern int snmp_fddi_trap(
#ifdef ANSIC
#ifndef SLIM_SMT
-#ifndef lint
-static const char ID_sccs[] = "@(#)pmf.c 1.37 97/08/04 (C) SK " ;
-#endif
-
static int smt_authorize(struct s_smc *smc, struct smt_header *sm);
static int smt_check_set_count(struct s_smc *smc, struct smt_header *sm);
static const struct s_p_tab* smt_get_ptab(u_short para);
#include "h/fddi.h"
#include "h/smc.h"
-#ifndef lint
-static const char ID_sccs[] = "@(#)queue.c 2.9 97/08/04 (C) SK " ;
-#endif
-
#define PRINTF(a,b,c)
/*
#define KERNEL
#include "h/smtstate.h"
-#ifndef lint
-static const char ID_sccs[] = "@(#)rmt.c 2.13 99/07/02 (C) SK " ;
-#endif
-
/*
* FSM Macros
*/
#define OEM_USER_DATA "SK-NET FDDI V2.0 Userdata"
#endif
-#ifndef lint
-static const char ID_sccs[] = "@(#)smtdef.c 2.53 99/08/11 (C) SK " ;
-#endif
-
/*
* defaults
*/
#include "h/fddi.h"
#include "h/smc.h"
-#ifndef lint
-static const char ID_sccs[] = "@(#)smtinit.c 1.15 97/05/06 (C) SK " ;
-#endif
-
void init_fddi_driver(struct s_smc *smc, u_char *mac_addr);
/* define global debug variable */
#include "h/fddi.h"
#include "h/smc.h"
-#ifndef lint
-static const char ID_sccs[] = "@(#)smttimer.c 2.4 97/08/04 (C) SK " ;
-#endif
-
static void timer_done(struct s_smc *smc, int restart);
void smt_timer_init(struct s_smc *smc)
#ifndef SLIM_SMT
#ifndef BOOT
-#ifndef lint
-static const char ID_sccs[] = "@(#)srf.c 1.18 97/08/04 (C) SK " ;
-#endif
-
-
/*
* function declarations
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/ethtool.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/etherdevice.h>
.ndo_open = geneve_open,
.ndo_stop = geneve_stop,
.ndo_start_xmit = geneve_xmit,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_change_mtu = geneve_change_mtu,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
.ndo_init = gtp_dev_init,
.ndo_uninit = gtp_dev_uninit,
.ndo_start_xmit = gtp_dev_xmit,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
};
static void gtp_link_setup(struct net_device *dev)
case HDLCDRVCTL_DRIVERNAME:
if (s->ops && s->ops->drvname) {
- strncpy(bi.data.drivername, s->ops->drvname,
+ strlcpy(bi.data.drivername, s->ops->drvname,
sizeof(bi.data.drivername));
break;
}
#include <linux/init.h>
#include <linux/atomic.h>
+#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/device.h>
* Haiyang Zhang <haiyangz@microsoft.com>
* Hank Janssen <hjanssen@microsoft.com>
*/
+#include <linux/ethtool.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/wait.h>
* struct ca8210_test - ca8210 test interface structure
* @ca8210_dfs_spi_int: pointer to the entry in the debug fs for this device
* @up_fifo: fifo for upstream messages
+ * @readq: read wait queue
*
* This structure stores all the data pertaining to the debug interface
*/
* @ca8210_is_awake: nonzero if ca8210 is initialised, ready for comms
* @sync_down: counts number of downstream synchronous commands
* @sync_up: counts number of upstream synchronous commands
- * @spi_transfer_complete completion object for a single spi_transfer
- * @sync_exchange_complete completion object for a complete synchronous API
- * exchange
- * @promiscuous whether the ca8210 is in promiscuous mode or not
+ * @spi_transfer_complete: completion object for a single spi_transfer
+ * @sync_exchange_complete: completion object for a complete synchronous API
+ * exchange
+ * @promiscuous: whether the ca8210 is in promiscuous mode or not
* @retries: records how many times the current pending spi
- * transfer has been retried
+ * transfer has been retried
*/
struct ca8210_priv {
struct spi_device *spi;
/**
* union macaddr: generic MAC address container
- * @short_addr: 16-bit short address
- * @ieee_address: 64-bit extended address as LE byte array
+ * @short_address: 16-bit short address
+ * @ieee_address: 64-bit extended address as LE byte array
*
*/
union macaddr {
/**
* ca8210_rx_done() - Calls various message dispatches responding to a received
* command
- * @arg: Pointer to the cas_control object for the relevant spi transfer
+ * @cas_ctl: Pointer to the cas_control object for the relevant spi transfer
*
* Presents a received SAP command from the ca8210 to the Cascoda EVBME, test
* interface and network driver.
* @pib_attribute: Attribute Number
* @pib_attribute_length: Attribute length
* @pib_attribute_value: Pointer to Attribute Value
- * @device_ref: Nondescript pointer to target device
*
* Return: 802.15.4 status code of checks
*/
/**
* ca8210_remove() - Shut down a ca8210 upon being disconnected
- * @priv: Pointer to private data structure
+ * @spi_device: Pointer to spi device data structure
*
* Return: 0 or linux error code
*/
/**
* ca8210_probe() - Set up a connected ca8210 upon being detected by the system
- * @priv: Pointer to private data structure
+ * @spi_device: Pointer to spi device data structure
*
* Return: 0 or linux error code
*/
};
#define IFB_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_FRAGLIST | \
- NETIF_F_TSO_ECN | NETIF_F_TSO | NETIF_F_TSO6 | \
- NETIF_F_GSO_ENCAP_ALL | \
+ NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | \
NETIF_F_HIGHDMA | NETIF_F_HW_VLAN_CTAG_TX | \
NETIF_F_HW_VLAN_STAG_TX)
#include "gsi_trans.h"
#include "ipa_gsi.h"
#include "ipa_data.h"
+#include "ipa_version.h"
/**
* DOC: The IPA Generic Software Interface
#define GSI_CMD_TIMEOUT 5 /* seconds */
#define GSI_CHANNEL_STOP_RX_RETRIES 10
+#define GSI_CHANNEL_MODEM_HALT_RETRIES 10
#define GSI_MHI_EVENT_ID_START 10 /* 1st reserved event id */
#define GSI_MHI_EVENT_ID_END 16 /* Last reserved event id */
u8 chid;
};
-/* Hardware values from the error log register error code field */
-enum gsi_err_code {
- GSI_INVALID_TRE_ERR = 0x1,
- GSI_OUT_OF_BUFFERS_ERR = 0x2,
- GSI_OUT_OF_RESOURCES_ERR = 0x3,
- GSI_UNSUPPORTED_INTER_EE_OP_ERR = 0x4,
- GSI_EVT_RING_EMPTY_ERR = 0x5,
- GSI_NON_ALLOCATED_EVT_ACCESS_ERR = 0x6,
- GSI_HWO_1_ERR = 0x8,
-};
-
-/* Hardware values from the error log register error type field */
-enum gsi_err_type {
- GSI_ERR_TYPE_GLOB = 0x1,
- GSI_ERR_TYPE_CHAN = 0x2,
- GSI_ERR_TYPE_EVT = 0x3,
-};
-
-/* Hardware values used when programming an event ring */
-enum gsi_evt_chtype {
- GSI_EVT_CHTYPE_MHI_EV = 0x0,
- GSI_EVT_CHTYPE_XHCI_EV = 0x1,
- GSI_EVT_CHTYPE_GPI_EV = 0x2,
- GSI_EVT_CHTYPE_XDCI_EV = 0x3,
-};
-
-/* Hardware values used when programming a channel */
-enum gsi_channel_protocol {
- GSI_CHANNEL_PROTOCOL_MHI = 0x0,
- GSI_CHANNEL_PROTOCOL_XHCI = 0x1,
- GSI_CHANNEL_PROTOCOL_GPI = 0x2,
- GSI_CHANNEL_PROTOCOL_XDCI = 0x3,
-};
-
-/* Hardware values representing an event ring immediate command opcode */
-enum gsi_evt_cmd_opcode {
- GSI_EVT_ALLOCATE = 0x0,
- GSI_EVT_RESET = 0x9,
- GSI_EVT_DE_ALLOC = 0xa,
-};
-
-/* Hardware values representing a generic immediate command opcode */
-enum gsi_generic_cmd_opcode {
- GSI_GENERIC_HALT_CHANNEL = 0x1,
- GSI_GENERIC_ALLOCATE_CHANNEL = 0x2,
-};
-
-/* Hardware values representing a channel immediate command opcode */
-enum gsi_ch_cmd_opcode {
- GSI_CH_ALLOCATE = 0x0,
- GSI_CH_START = 0x1,
- GSI_CH_STOP = 0x2,
- GSI_CH_RESET = 0x9,
- GSI_CH_DE_ALLOC = 0xa,
-};
-
/** gsi_channel_scratch_gpi - GPI protocol scratch register
* @max_outstanding_tre:
* Defines the maximum number of TREs allowed in a single transaction
return channel - &channel->gsi->channel[0];
}
+/* Update the GSI IRQ type register with the cached value */
+static void gsi_irq_type_update(struct gsi *gsi, u32 val)
+{
+ gsi->type_enabled_bitmap = val;
+ iowrite32(val, gsi->virt + GSI_CNTXT_TYPE_IRQ_MSK_OFFSET);
+}
+
+static void gsi_irq_type_enable(struct gsi *gsi, enum gsi_irq_type_id type_id)
+{
+ gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | BIT(type_id));
+}
+
+static void gsi_irq_type_disable(struct gsi *gsi, enum gsi_irq_type_id type_id)
+{
+ gsi_irq_type_update(gsi, gsi->type_enabled_bitmap & ~BIT(type_id));
+}
+
+/* Turn off all GSI interrupts initially */
+static void gsi_irq_setup(struct gsi *gsi)
+{
+ u32 adjust;
+
+ /* Disable all interrupt types */
+ gsi_irq_type_update(gsi, 0);
+
+ /* Clear all type-specific interrupt masks */
+ iowrite32(0, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_MSK_OFFSET);
+ iowrite32(0, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_MSK_OFFSET);
+ iowrite32(0, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET);
+ iowrite32(0, gsi->virt + GSI_CNTXT_SRC_IEOB_IRQ_MSK_OFFSET);
+
+ /* Reverse the offset adjustment for inter-EE register offsets */
+ adjust = gsi->version < IPA_VERSION_4_5 ? 0 : GSI_EE_REG_ADJUST;
+ iowrite32(0, gsi->virt + adjust + GSI_INTER_EE_SRC_CH_IRQ_OFFSET);
+ iowrite32(0, gsi->virt + adjust + GSI_INTER_EE_SRC_EV_CH_IRQ_OFFSET);
+
+ iowrite32(0, gsi->virt + GSI_CNTXT_GSI_IRQ_EN_OFFSET);
+}
+
+/* Turn off all GSI interrupts when we're all done */
+static void gsi_irq_teardown(struct gsi *gsi)
+{
+ /* Nothing to do */
+}
+
static void gsi_irq_ieob_enable(struct gsi *gsi, u32 evt_ring_id)
{
+ bool enable_ieob = !gsi->ieob_enabled_bitmap;
u32 val;
- gsi->event_enable_bitmap |= BIT(evt_ring_id);
- val = gsi->event_enable_bitmap;
+ gsi->ieob_enabled_bitmap |= BIT(evt_ring_id);
+ val = gsi->ieob_enabled_bitmap;
iowrite32(val, gsi->virt + GSI_CNTXT_SRC_IEOB_IRQ_MSK_OFFSET);
+
+ /* Enable the interrupt type if this is the first channel enabled */
+ if (enable_ieob)
+ gsi_irq_type_enable(gsi, GSI_IEOB);
}
static void gsi_irq_ieob_disable(struct gsi *gsi, u32 evt_ring_id)
{
u32 val;
- gsi->event_enable_bitmap &= ~BIT(evt_ring_id);
- val = gsi->event_enable_bitmap;
+ gsi->ieob_enabled_bitmap &= ~BIT(evt_ring_id);
+
+ /* Disable the interrupt type if this was the last enabled channel */
+ if (!gsi->ieob_enabled_bitmap)
+ gsi_irq_type_disable(gsi, GSI_IEOB);
+
+ val = gsi->ieob_enabled_bitmap;
iowrite32(val, gsi->virt + GSI_CNTXT_SRC_IEOB_IRQ_MSK_OFFSET);
}
{
u32 val;
- /* We don't use inter-EE channel or event interrupts */
- val = GSI_CNTXT_TYPE_IRQ_MSK_ALL;
- val &= ~INTER_EE_CH_CTRL_FMASK;
- val &= ~INTER_EE_EV_CTRL_FMASK;
- iowrite32(val, gsi->virt + GSI_CNTXT_TYPE_IRQ_MSK_OFFSET);
-
- val = GENMASK(gsi->channel_count - 1, 0);
- iowrite32(val, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_MSK_OFFSET);
-
- val = GENMASK(gsi->evt_ring_count - 1, 0);
- iowrite32(val, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_MSK_OFFSET);
-
- /* Each IEOB interrupt is enabled (later) as needed by channels */
- iowrite32(0, gsi->virt + GSI_CNTXT_SRC_IEOB_IRQ_MSK_OFFSET);
-
- val = GSI_CNTXT_GLOB_IRQ_ALL;
- iowrite32(val, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET);
+ /* Global interrupts include hardware error reports. Enable
+ * that so we can at least report the error should it occur.
+ */
+ iowrite32(BIT(ERROR_INT), gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET);
+ gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | BIT(GSI_GLOB_EE));
- /* Never enable GSI_BREAK_POINT */
- val = GSI_CNTXT_GSI_IRQ_ALL & ~BREAK_POINT_FMASK;
+ /* General GSI interrupts are reported to all EEs; if they occur
+ * they are unrecoverable (without reset). A breakpoint interrupt
+ * also exists, but we don't support that. We want to be notified
+ * of errors so we can report them, even if they can't be handled.
+ */
+ val = BIT(BUS_ERROR);
+ val |= BIT(CMD_FIFO_OVRFLOW);
+ val |= BIT(MCS_STACK_OVRFLOW);
iowrite32(val, gsi->virt + GSI_CNTXT_GSI_IRQ_EN_OFFSET);
+ gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | BIT(GSI_GENERAL));
}
-/* Disable all GSI_interrupt types */
+/* Disable all GSI interrupt types */
static void gsi_irq_disable(struct gsi *gsi)
{
+ gsi_irq_type_update(gsi, 0);
+
+ /* Clear the type-specific interrupt masks set by gsi_irq_enable() */
iowrite32(0, gsi->virt + GSI_CNTXT_GSI_IRQ_EN_OFFSET);
iowrite32(0, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET);
- iowrite32(0, gsi->virt + GSI_CNTXT_SRC_IEOB_IRQ_MSK_OFFSET);
- iowrite32(0, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_MSK_OFFSET);
- iowrite32(0, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_MSK_OFFSET);
- iowrite32(0, gsi->virt + GSI_CNTXT_TYPE_IRQ_MSK_OFFSET);
}
/* Return the virtual address associated with a ring index */
struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id];
struct completion *completion = &evt_ring->completion;
struct device *dev = gsi->dev;
+ bool success;
u32 val;
+ /* We only perform one event ring command at a time, and event
+ * control interrupts should only occur when such a command
+ * is issued here. Only permit *this* event ring to trigger
+ * an interrupt, and only enable the event control IRQ type
+ * when we expect it to occur.
+ */
+ val = BIT(evt_ring_id);
+ iowrite32(val, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_MSK_OFFSET);
+ gsi_irq_type_enable(gsi, GSI_EV_CTRL);
+
val = u32_encode_bits(evt_ring_id, EV_CHID_FMASK);
val |= u32_encode_bits(opcode, EV_OPCODE_FMASK);
- if (gsi_command(gsi, GSI_EV_CH_CMD_OFFSET, val, completion))
- return 0; /* Success! */
+ success = gsi_command(gsi, GSI_EV_CH_CMD_OFFSET, val, completion);
+
+ /* Disable the interrupt again */
+ gsi_irq_type_disable(gsi, GSI_EV_CTRL);
+ iowrite32(0, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_MSK_OFFSET);
+
+ if (success)
+ return 0;
dev_err(dev, "GSI command %u for event ring %u timed out, state %u\n",
opcode, evt_ring_id, evt_ring->state);
/* Get initial event ring state */
evt_ring->state = gsi_evt_ring_state(gsi, evt_ring_id);
if (evt_ring->state != GSI_EVT_RING_STATE_NOT_ALLOCATED) {
- dev_err(gsi->dev, "bad event ring state %u before alloc\n",
- evt_ring->state);
+ dev_err(gsi->dev, "event ring %u bad state %u before alloc\n",
+ evt_ring_id, evt_ring->state);
return -EINVAL;
}
ret = evt_ring_command(gsi, evt_ring_id, GSI_EVT_ALLOCATE);
if (!ret && evt_ring->state != GSI_EVT_RING_STATE_ALLOCATED) {
- dev_err(gsi->dev, "bad event ring state %u after alloc\n",
- evt_ring->state);
+ dev_err(gsi->dev, "event ring %u bad state %u after alloc\n",
+ evt_ring_id, evt_ring->state);
ret = -EIO;
}
if (state != GSI_EVT_RING_STATE_ALLOCATED &&
state != GSI_EVT_RING_STATE_ERROR) {
- dev_err(gsi->dev, "bad event ring state %u before reset\n",
- evt_ring->state);
+ dev_err(gsi->dev, "event ring %u bad state %u before reset\n",
+ evt_ring_id, evt_ring->state);
return;
}
ret = evt_ring_command(gsi, evt_ring_id, GSI_EVT_RESET);
if (!ret && evt_ring->state != GSI_EVT_RING_STATE_ALLOCATED)
- dev_err(gsi->dev, "bad event ring state %u after reset\n",
- evt_ring->state);
+ dev_err(gsi->dev, "event ring %u bad state %u after reset\n",
+ evt_ring_id, evt_ring->state);
}
/* Issue a hardware de-allocation request for an allocated event ring */
int ret;
if (evt_ring->state != GSI_EVT_RING_STATE_ALLOCATED) {
- dev_err(gsi->dev, "bad event ring state %u before dealloc\n",
- evt_ring->state);
+ dev_err(gsi->dev, "event ring %u state %u before dealloc\n",
+ evt_ring_id, evt_ring->state);
return;
}
ret = evt_ring_command(gsi, evt_ring_id, GSI_EVT_DE_ALLOC);
if (!ret && evt_ring->state != GSI_EVT_RING_STATE_NOT_ALLOCATED)
- dev_err(gsi->dev, "bad event ring state %u after dealloc\n",
- evt_ring->state);
+ dev_err(gsi->dev, "event ring %u bad state %u after dealloc\n",
+ evt_ring_id, evt_ring->state);
}
/* Fetch the current state of a channel from hardware */
u32 channel_id = gsi_channel_id(channel);
struct gsi *gsi = channel->gsi;
struct device *dev = gsi->dev;
+ bool success;
u32 val;
+ /* We only perform one channel command at a time, and channel
+ * control interrupts should only occur when such a command is
+ * issued here. So we only permit *this* channel to trigger
+ * an interrupt and only enable the channel control IRQ type
+ * when we expect it to occur.
+ */
+ val = BIT(channel_id);
+ iowrite32(val, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_MSK_OFFSET);
+ gsi_irq_type_enable(gsi, GSI_CH_CTRL);
+
val = u32_encode_bits(channel_id, CH_CHID_FMASK);
val |= u32_encode_bits(opcode, CH_OPCODE_FMASK);
+ success = gsi_command(gsi, GSI_CH_CMD_OFFSET, val, completion);
- if (gsi_command(gsi, GSI_CH_CMD_OFFSET, val, completion))
- return 0; /* Success! */
+ /* Disable the interrupt again */
+ gsi_irq_type_disable(gsi, GSI_CH_CTRL);
+ iowrite32(0, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_MSK_OFFSET);
+
+ if (success)
+ return 0;
dev_err(dev, "GSI command %u for channel %u timed out, state %u\n",
opcode, channel_id, gsi_channel_state(channel));
/* Get initial channel state */
state = gsi_channel_state(channel);
if (state != GSI_CHANNEL_STATE_NOT_ALLOCATED) {
- dev_err(dev, "bad channel state %u before alloc\n", state);
+ dev_err(dev, "channel %u bad state %u before alloc\n",
+ channel_id, state);
return -EINVAL;
}
/* Channel state will normally have been updated */
state = gsi_channel_state(channel);
if (!ret && state != GSI_CHANNEL_STATE_ALLOCATED) {
- dev_err(dev, "bad channel state %u after alloc\n", state);
+ dev_err(dev, "channel %u bad state %u after alloc\n",
+ channel_id, state);
ret = -EIO;
}
state = gsi_channel_state(channel);
if (state != GSI_CHANNEL_STATE_ALLOCATED &&
state != GSI_CHANNEL_STATE_STOPPED) {
- dev_err(dev, "bad channel state %u before start\n", state);
+ dev_err(dev, "channel %u bad state %u before start\n",
+ gsi_channel_id(channel), state);
return -EINVAL;
}
/* Channel state will normally have been updated */
state = gsi_channel_state(channel);
if (!ret && state != GSI_CHANNEL_STATE_STARTED) {
- dev_err(dev, "bad channel state %u after start\n", state);
+ dev_err(dev, "channel %u bad state %u after start\n",
+ gsi_channel_id(channel), state);
ret = -EIO;
}
if (state != GSI_CHANNEL_STATE_STARTED &&
state != GSI_CHANNEL_STATE_STOP_IN_PROC) {
- dev_err(dev, "bad channel state %u before stop\n", state);
+ dev_err(dev, "channel %u bad state %u before stop\n",
+ gsi_channel_id(channel), state);
return -EINVAL;
}
if (state == GSI_CHANNEL_STATE_STOP_IN_PROC)
return -EAGAIN;
- dev_err(dev, "bad channel state %u after stop\n", state);
+ dev_err(dev, "channel %u bad state %u after stop\n",
+ gsi_channel_id(channel), state);
return -EIO;
}
state = gsi_channel_state(channel);
if (state != GSI_CHANNEL_STATE_STOPPED &&
state != GSI_CHANNEL_STATE_ERROR) {
- dev_err(dev, "bad channel state %u before reset\n", state);
+ /* No need to reset a channel already in ALLOCATED state */
+ if (state != GSI_CHANNEL_STATE_ALLOCATED)
+ dev_err(dev, "channel %u bad state %u before reset\n",
+ gsi_channel_id(channel), state);
return;
}
/* Channel state will normally have been updated */
state = gsi_channel_state(channel);
if (!ret && state != GSI_CHANNEL_STATE_ALLOCATED)
- dev_err(dev, "bad channel state %u after reset\n", state);
+ dev_err(dev, "channel %u bad state %u after reset\n",
+ gsi_channel_id(channel), state);
}
/* Deallocate an ALLOCATED GSI channel */
state = gsi_channel_state(channel);
if (state != GSI_CHANNEL_STATE_ALLOCATED) {
- dev_err(dev, "bad channel state %u before dealloc\n", state);
+ dev_err(dev, "channel %u bad state %u before dealloc\n",
+ channel_id, state);
return;
}
/* Channel state will normally have been updated */
state = gsi_channel_state(channel);
if (!ret && state != GSI_CHANNEL_STATE_NOT_ALLOCATED)
- dev_err(dev, "bad channel state %u after dealloc\n", state);
+ dev_err(dev, "channel %u bad state %u after dealloc\n",
+ channel_id, state);
}
/* Ring an event ring doorbell, reporting the last entry processed by the AP.
size_t size = evt_ring->ring.count * GSI_RING_ELEMENT_SIZE;
u32 val;
- val = u32_encode_bits(GSI_EVT_CHTYPE_GPI_EV, EV_CHTYPE_FMASK);
+ /* We program all event rings as GPI type/protocol */
+ val = u32_encode_bits(GSI_CHANNEL_TYPE_GPI, EV_CHTYPE_FMASK);
val |= EV_INTYPE_FMASK;
val |= u32_encode_bits(GSI_RING_ELEMENT_SIZE, EV_ELEMENT_SIZE_FMASK);
iowrite32(val, gsi->virt + GSI_EV_CH_E_CNTXT_0_OFFSET(evt_ring_id));
/* Arbitrarily pick TRE 0 as the first channel element to use */
channel->tre_ring.index = 0;
- /* We program all channels to use GPI protocol */
- val = u32_encode_bits(GSI_CHANNEL_PROTOCOL_GPI, CHTYPE_PROTOCOL_FMASK);
+ /* We program all channels as GPI type/protocol */
+ val = u32_encode_bits(GSI_CHANNEL_TYPE_GPI, CHTYPE_PROTOCOL_FMASK);
if (channel->toward_ipa)
val |= CHTYPE_DIR_FMASK;
val |= u32_encode_bits(channel->evt_ring_id, ERINDEX_FMASK);
/* Max prefetch is 1 segment (do not set MAX_PREFETCH_FMASK) */
- /* Enable the doorbell engine if requested */
- if (doorbell)
+ /* We enable the doorbell engine for IPA v3.5.1 */
+ if (gsi->version == IPA_VERSION_3_5_1 && doorbell)
val |= USE_DB_ENG_FMASK;
- if (!channel->use_prefetch)
- val |= USE_ESCAPE_BUF_ONLY_FMASK;
+ /* v4.0 introduces an escape buffer for prefetch. We use it
+ * on all but the AP command channel.
+ */
+ if (gsi->version != IPA_VERSION_3_5_1 && !channel->command) {
+ /* If not otherwise set, prefetch buffers are used */
+ if (gsi->version < IPA_VERSION_4_5)
+ val |= USE_ESCAPE_BUF_ONLY_FMASK;
+ else
+ val |= u32_encode_bits(GSI_ESCAPE_BUF_ONLY,
+ PREFETCH_MODE_FMASK);
+ }
iowrite32(val, gsi->virt + GSI_CH_C_QOS_OFFSET(channel_id));
return ret;
}
-/* Reset and reconfigure a channel (possibly leaving doorbell disabled) */
-void gsi_channel_reset(struct gsi *gsi, u32 channel_id, bool legacy)
+/* Reset and reconfigure a channel, (possibly) enabling the doorbell engine */
+void gsi_channel_reset(struct gsi *gsi, u32 channel_id, bool doorbell)
{
struct gsi_channel *channel = &gsi->channel[channel_id];
gsi_channel_reset_command(channel);
/* Due to a hardware quirk we may need to reset RX channels twice. */
- if (legacy && !channel->toward_ipa)
+ if (gsi->version == IPA_VERSION_3_5_1 && !channel->toward_ipa)
gsi_channel_reset_command(channel);
- gsi_channel_program(channel, legacy);
+ gsi_channel_program(channel, doorbell);
gsi_channel_trans_cancel_pending(channel);
mutex_unlock(&gsi->mutex);
static void
gsi_isr_glob_chan_err(struct gsi *gsi, u32 err_ee, u32 channel_id, u32 code)
{
- if (code == GSI_OUT_OF_RESOURCES_ERR) {
+ if (code == GSI_OUT_OF_RESOURCES) {
dev_err(gsi->dev, "channel %u out of resources\n", channel_id);
complete(&gsi->channel[channel_id].completion);
return;
static void
gsi_isr_glob_evt_err(struct gsi *gsi, u32 err_ee, u32 evt_ring_id, u32 code)
{
- if (code == GSI_OUT_OF_RESOURCES_ERR) {
+ if (code == GSI_OUT_OF_RESOURCES) {
struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id];
u32 channel_id = gsi_channel_id(evt_ring->channel);
iowrite32(~0, gsi->virt + GSI_ERROR_LOG_CLR_OFFSET);
ee = u32_get_bits(val, ERR_EE_FMASK);
- which = u32_get_bits(val, ERR_VIRT_IDX_FMASK);
type = u32_get_bits(val, ERR_TYPE_FMASK);
+ which = u32_get_bits(val, ERR_VIRT_IDX_FMASK);
code = u32_get_bits(val, ERR_CODE_FMASK);
if (type == GSI_ERR_TYPE_CHAN)
u32 result;
u32 val;
+ /* This interrupt is used to handle completions of the two GENERIC
+ * GSI commands. We use these to allocate and halt channels on
+ * the modem's behalf due to a hardware quirk on IPA v4.2. Once
+ * allocated, the modem "owns" these channels, and as a result we
+ * have no way of knowing the channel's state at any given time.
+ *
+ * It is recommended that we halt the modem channels we allocated
+ * when shutting down, but it's possible the channel isn't running
+ * at the time we issue the HALT command. We'll get an error in
+ * that case, but it's harmless (the channel is already halted).
+ *
+ * For this reason, we silently ignore a CHANNEL_NOT_RUNNING error
+ * if we receive it.
+ */
val = ioread32(gsi->virt + GSI_CNTXT_SCRATCH_0_OFFSET);
result = u32_get_bits(val, GENERIC_EE_RESULT_FMASK);
- if (result != GENERIC_EE_SUCCESS_FVAL)
+
+ switch (result) {
+ case GENERIC_EE_SUCCESS:
+ case GENERIC_EE_CHANNEL_NOT_RUNNING:
+ gsi->result = 0;
+ break;
+
+ case GENERIC_EE_RETRY:
+ gsi->result = -EAGAIN;
+ break;
+
+ default:
dev_err(gsi->dev, "global INT1 generic result %u\n", result);
+ gsi->result = -EIO;
+ break;
+ }
complete(&gsi->completion);
}
val = ioread32(gsi->virt + GSI_CNTXT_GLOB_IRQ_STTS_OFFSET);
- if (val & ERROR_INT_FMASK)
+ if (val & BIT(ERROR_INT))
gsi_isr_glob_err(gsi);
iowrite32(val, gsi->virt + GSI_CNTXT_GLOB_IRQ_CLR_OFFSET);
- val &= ~ERROR_INT_FMASK;
+ val &= ~BIT(ERROR_INT);
- if (val & GP_INT1_FMASK) {
- val ^= GP_INT1_FMASK;
+ if (val & BIT(GP_INT1)) {
+ val ^= BIT(GP_INT1);
gsi_isr_gp_int1(gsi);
}
val = ioread32(gsi->virt + GSI_CNTXT_GSI_IRQ_STTS_OFFSET);
iowrite32(val, gsi->virt + GSI_CNTXT_GSI_IRQ_CLR_OFFSET);
- if (val)
- dev_err(dev, "unexpected general interrupt 0x%08x\n", val);
+ dev_err(dev, "unexpected general interrupt 0x%08x\n", val);
}
/**
u32 intr_mask;
u32 cnt = 0;
+ /* enum gsi_irq_type_id defines GSI interrupt types */
while ((intr_mask = ioread32(gsi->virt + GSI_CNTXT_TYPE_IRQ_OFFSET))) {
/* intr_mask contains bitmask of pending GSI interrupts */
do {
intr_mask ^= gsi_intr;
switch (gsi_intr) {
- case CH_CTRL_FMASK:
+ case BIT(GSI_CH_CTRL):
gsi_isr_chan_ctrl(gsi);
break;
- case EV_CTRL_FMASK:
+ case BIT(GSI_EV_CTRL):
gsi_isr_evt_ctrl(gsi);
break;
- case GLOB_EE_FMASK:
+ case BIT(GSI_GLOB_EE):
gsi_isr_glob_ee(gsi);
break;
- case IEOB_FMASK:
+ case BIT(GSI_IEOB):
gsi_isr_ieob(gsi);
break;
- case GENERAL_FMASK:
+ case BIT(GSI_GENERAL):
gsi_isr_general(gsi);
break;
default:
return IRQ_HANDLED;
}
+static int gsi_irq_init(struct gsi *gsi, struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ unsigned int irq;
+ int ret;
+
+ ret = platform_get_irq_byname(pdev, "gsi");
+ if (ret <= 0) {
+ dev_err(dev, "DT error %d getting \"gsi\" IRQ property\n", ret);
+ return ret ? : -EINVAL;
+ }
+ irq = ret;
+
+ ret = request_irq(irq, gsi_isr, 0, "gsi", gsi);
+ if (ret) {
+ dev_err(dev, "error %d requesting \"gsi\" IRQ\n", ret);
+ return ret;
+ }
+ gsi->irq = irq;
+
+ return 0;
+}
+
+static void gsi_irq_exit(struct gsi *gsi)
+{
+ free_irq(gsi->irq, gsi);
+}
+
/* Return the transaction associated with a transfer completion event */
static struct gsi_trans *gsi_event_trans(struct gsi_channel *channel,
struct gsi_event *event)
}
/* Setup function for a single channel */
-static int gsi_channel_setup_one(struct gsi *gsi, u32 channel_id,
- bool legacy)
+static int gsi_channel_setup_one(struct gsi *gsi, u32 channel_id)
{
struct gsi_channel *channel = &gsi->channel[channel_id];
u32 evt_ring_id = channel->evt_ring_id;
if (ret)
goto err_evt_ring_de_alloc;
- gsi_channel_program(channel, legacy);
+ gsi_channel_program(channel, true);
if (channel->toward_ipa)
netif_tx_napi_add(&gsi->dummy_dev, &channel->napi,
enum gsi_generic_cmd_opcode opcode)
{
struct completion *completion = &gsi->completion;
+ bool success;
u32 val;
+ /* The error global interrupt type is always enabled (until we
+ * teardown), so we won't change that. A generic EE command
+ * completes with a GSI global interrupt of type GP_INT1. We
+ * only perform one generic command at a time (to allocate or
+ * halt a modem channel) and only from this function. So we
+ * enable the GP_INT1 IRQ type here while we're expecting it.
+ */
+ val = BIT(ERROR_INT) | BIT(GP_INT1);
+ iowrite32(val, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET);
+
/* First zero the result code field */
val = ioread32(gsi->virt + GSI_CNTXT_SCRATCH_0_OFFSET);
val &= ~GENERIC_EE_RESULT_FMASK;
val |= u32_encode_bits(channel_id, GENERIC_CHID_FMASK);
val |= u32_encode_bits(GSI_EE_MODEM, GENERIC_EE_FMASK);
- if (gsi_command(gsi, GSI_GENERIC_CMD_OFFSET, val, completion))
- return 0; /* Success! */
+ success = gsi_command(gsi, GSI_GENERIC_CMD_OFFSET, val, completion);
+
+ /* Disable the GP_INT1 IRQ type again */
+ iowrite32(BIT(ERROR_INT), gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET);
+
+ if (success)
+ return gsi->result;
dev_err(gsi->dev, "GSI generic command %u to channel %u timed out\n",
opcode, channel_id);
static void gsi_modem_channel_halt(struct gsi *gsi, u32 channel_id)
{
+ u32 retries = GSI_CHANNEL_MODEM_HALT_RETRIES;
int ret;
- ret = gsi_generic_command(gsi, channel_id, GSI_GENERIC_HALT_CHANNEL);
+ do
+ ret = gsi_generic_command(gsi, channel_id,
+ GSI_GENERIC_HALT_CHANNEL);
+ while (ret == -EAGAIN && retries--);
+
if (ret)
dev_err(gsi->dev, "error %d halting modem channel %u\n",
ret, channel_id);
}
/* Setup function for channels */
-static int gsi_channel_setup(struct gsi *gsi, bool legacy)
+static int gsi_channel_setup(struct gsi *gsi)
{
u32 channel_id = 0;
u32 mask;
mutex_lock(&gsi->mutex);
do {
- ret = gsi_channel_setup_one(gsi, channel_id, legacy);
+ ret = gsi_channel_setup_one(gsi, channel_id);
if (ret)
goto err_unwind;
} while (++channel_id < gsi->channel_count);
}
/* Setup function for GSI. GSI firmware must be loaded and initialized */
-int gsi_setup(struct gsi *gsi, bool legacy)
+int gsi_setup(struct gsi *gsi)
{
struct device *dev = gsi->dev;
u32 val;
+ int ret;
/* Here is where we first touch the GSI hardware */
val = ioread32(gsi->virt + GSI_GSI_STATUS_OFFSET);
return -EIO;
}
+ gsi_irq_setup(gsi);
+
val = ioread32(gsi->virt + GSI_GSI_HW_PARAM_2_OFFSET);
gsi->channel_count = u32_get_bits(val, NUM_CH_PER_EE_FMASK);
/* Writing 1 indicates IRQ interrupts; 0 would be MSI */
iowrite32(1, gsi->virt + GSI_CNTXT_INTSET_OFFSET);
- return gsi_channel_setup(gsi, legacy);
+ ret = gsi_channel_setup(gsi);
+ if (ret)
+ gsi_irq_teardown(gsi);
+
+ return ret;
}
/* Inverse of gsi_setup() */
void gsi_teardown(struct gsi *gsi)
{
gsi_channel_teardown(gsi);
+ gsi_irq_teardown(gsi);
}
/* Initialize a channel's event ring */
u32 evt_ring_id = 0;
gsi->event_bitmap = gsi_event_bitmap_init(GSI_EVT_RING_COUNT_MAX);
- gsi->event_enable_bitmap = 0;
+ gsi->ieob_enabled_bitmap = 0;
do
init_completion(&gsi->evt_ring[evt_ring_id].completion);
while (++evt_ring_id < GSI_EVT_RING_COUNT_MAX);
/* Init function for a single channel */
static int gsi_channel_init_one(struct gsi *gsi,
const struct ipa_gsi_endpoint_data *data,
- bool command, bool prefetch)
+ bool command)
{
struct gsi_channel *channel;
u32 tre_count;
channel->gsi = gsi;
channel->toward_ipa = data->toward_ipa;
channel->command = command;
- channel->use_prefetch = command && prefetch;
channel->tlv_count = data->channel.tlv_count;
channel->tre_count = tre_count;
channel->event_count = data->channel.event_count;
}
/* Init function for channels */
-static int gsi_channel_init(struct gsi *gsi, bool prefetch, u32 count,
- const struct ipa_gsi_endpoint_data *data,
- bool modem_alloc)
+static int gsi_channel_init(struct gsi *gsi, u32 count,
+ const struct ipa_gsi_endpoint_data *data)
{
+ bool modem_alloc;
int ret = 0;
u32 i;
+ /* IPA v4.2 requires the AP to allocate channels for the modem */
+ modem_alloc = gsi->version == IPA_VERSION_4_2;
+
gsi_evt_ring_init(gsi);
/* The endpoint data array is indexed by endpoint name */
continue;
}
- ret = gsi_channel_init_one(gsi, &data[i], command, prefetch);
+ ret = gsi_channel_init_one(gsi, &data[i], command);
if (ret)
goto err_unwind;
}
}
/* Init function for GSI. GSI hardware does not need to be "ready" */
-int gsi_init(struct gsi *gsi, struct platform_device *pdev, bool prefetch,
- u32 count, const struct ipa_gsi_endpoint_data *data,
- bool modem_alloc)
+int gsi_init(struct gsi *gsi, struct platform_device *pdev,
+ enum ipa_version version, u32 count,
+ const struct ipa_gsi_endpoint_data *data)
{
struct device *dev = &pdev->dev;
struct resource *res;
resource_size_t size;
- unsigned int irq;
+ u32 adjust;
int ret;
gsi_validate_build();
gsi->dev = dev;
+ gsi->version = version;
/* The GSI layer performs NAPI on all endpoints. NAPI requires a
* network device structure, but the GSI layer does not have one,
*/
init_dummy_netdev(&gsi->dummy_dev);
- ret = platform_get_irq_byname(pdev, "gsi");
- if (ret <= 0) {
- dev_err(dev, "DT error %d getting \"gsi\" IRQ property\n", ret);
- return ret ? : -EINVAL;
- }
- irq = ret;
-
- ret = request_irq(irq, gsi_isr, 0, "gsi", gsi);
- if (ret) {
- dev_err(dev, "error %d requesting \"gsi\" IRQ\n", ret);
- return ret;
- }
- gsi->irq = irq;
-
/* Get GSI memory range and map it */
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "gsi");
if (!res) {
dev_err(dev, "DT error getting \"gsi\" memory property\n");
- ret = -ENODEV;
- goto err_free_irq;
+ return -ENODEV;
}
size = resource_size(res);
if (res->start > U32_MAX || size > U32_MAX - res->start) {
dev_err(dev, "DT memory resource \"gsi\" out of range\n");
- ret = -EINVAL;
- goto err_free_irq;
+ return -EINVAL;
+ }
+
+ /* Make sure we can make our pointer adjustment if necessary */
+ adjust = gsi->version < IPA_VERSION_4_5 ? 0 : GSI_EE_REG_ADJUST;
+ if (res->start < adjust) {
+ dev_err(dev, "DT memory resource \"gsi\" too low (< %u)\n",
+ adjust);
+ return -EINVAL;
}
gsi->virt = ioremap(res->start, size);
if (!gsi->virt) {
dev_err(dev, "unable to remap \"gsi\" memory\n");
- ret = -ENOMEM;
- goto err_free_irq;
+ return -ENOMEM;
}
+ /* Adjust register range pointer downward for newer IPA versions */
+ gsi->virt -= adjust;
- ret = gsi_channel_init(gsi, prefetch, count, data, modem_alloc);
+ init_completion(&gsi->completion);
+
+ ret = gsi_irq_init(gsi, pdev);
if (ret)
goto err_iounmap;
+ ret = gsi_channel_init(gsi, count, data);
+ if (ret)
+ goto err_irq_exit;
+
mutex_init(&gsi->mutex);
- init_completion(&gsi->completion);
return 0;
+err_irq_exit:
+ gsi_irq_exit(gsi);
err_iounmap:
iounmap(gsi->virt);
-err_free_irq:
- free_irq(gsi->irq, gsi);
return ret;
}
{
mutex_destroy(&gsi->mutex);
gsi_channel_exit(gsi);
- free_irq(gsi->irq, gsi);
+ gsi_irq_exit(gsi);
iounmap(gsi->virt);
}
#include <linux/platform_device.h>
#include <linux/netdevice.h>
+#include "ipa_version.h"
+
/* Maximum number of channels and event rings supported by the driver */
#define GSI_CHANNEL_COUNT_MAX 17
#define GSI_EVT_RING_COUNT_MAX 13
/* Execution environment IDs */
enum gsi_ee_id {
- GSI_EE_AP = 0,
- GSI_EE_MODEM = 1,
- GSI_EE_UC = 2,
- GSI_EE_TZ = 3,
+ GSI_EE_AP = 0x0,
+ GSI_EE_MODEM = 0x1,
+ GSI_EE_UC = 0x2,
+ GSI_EE_TZ = 0x3,
};
struct gsi_ring {
/* Hardware values signifying the state of a channel */
enum gsi_channel_state {
- GSI_CHANNEL_STATE_NOT_ALLOCATED = 0x0,
- GSI_CHANNEL_STATE_ALLOCATED = 0x1,
- GSI_CHANNEL_STATE_STARTED = 0x2,
- GSI_CHANNEL_STATE_STOPPED = 0x3,
- GSI_CHANNEL_STATE_STOP_IN_PROC = 0x4,
- GSI_CHANNEL_STATE_ERROR = 0xf,
+ GSI_CHANNEL_STATE_NOT_ALLOCATED = 0x0,
+ GSI_CHANNEL_STATE_ALLOCATED = 0x1,
+ GSI_CHANNEL_STATE_STARTED = 0x2,
+ GSI_CHANNEL_STATE_STOPPED = 0x3,
+ GSI_CHANNEL_STATE_STOP_IN_PROC = 0x4,
+ GSI_CHANNEL_STATE_ERROR = 0xf,
};
/* We only care about channels between IPA and AP */
struct gsi *gsi;
bool toward_ipa;
bool command; /* AP command TX channel or not */
- bool use_prefetch; /* use prefetch (else escape buf) */
u8 tlv_count; /* # entries in TLV FIFO */
u16 tre_count;
struct gsi {
struct device *dev; /* Same as IPA device */
+ enum ipa_version version;
struct net_device dummy_dev; /* needed for NAPI */
void __iomem *virt;
u32 irq;
u32 evt_ring_count;
struct gsi_channel channel[GSI_CHANNEL_COUNT_MAX];
struct gsi_evt_ring evt_ring[GSI_EVT_RING_COUNT_MAX];
- u32 event_bitmap;
- u32 event_enable_bitmap;
- u32 modem_channel_bitmap;
+ u32 event_bitmap; /* allocated event rings */
+ u32 modem_channel_bitmap; /* modem channels to allocate */
+ u32 type_enabled_bitmap; /* GSI IRQ types enabled */
+ u32 ieob_enabled_bitmap; /* IEOB IRQ enabled (event rings) */
struct completion completion; /* for global EE commands */
+ int result; /* Negative errno (generic commands) */
struct mutex mutex; /* protects commands, programming */
};
/**
* gsi_setup() - Set up the GSI subsystem
* @gsi: Address of GSI structure embedded in an IPA structure
- * @legacy: Set up for legacy hardware
*
* Return: 0 if successful, or a negative error code
*
* Performs initialization that must wait until the GSI hardware is
* ready (including firmware loaded).
*/
-int gsi_setup(struct gsi *gsi, bool legacy);
+int gsi_setup(struct gsi *gsi);
/**
* gsi_teardown() - Tear down GSI subsystem
* gsi_channel_reset() - Reset an allocated GSI channel
* @gsi: GSI pointer
* @channel_id: Channel to be reset
- * @legacy: Legacy behavior
+ * @doorbell: Whether to (possibly) enable the doorbell engine
*
- * Reset a channel and reconfigure it. The @legacy flag indicates
- * that some steps should be done differently for legacy hardware.
+ * Reset a channel and reconfigure it. The @doorbell flag indicates
+ * that the doorbell engine should be enabled if needed.
*
* GSI hardware relinquishes ownership of all pending receive buffer
* transactions and they will complete with their cancelled flag set.
*/
-void gsi_channel_reset(struct gsi *gsi, u32 channel_id, bool legacy);
+void gsi_channel_reset(struct gsi *gsi, u32 channel_id, bool doorbell);
int gsi_channel_suspend(struct gsi *gsi, u32 channel_id, bool stop);
int gsi_channel_resume(struct gsi *gsi, u32 channel_id, bool start);
* gsi_init() - Initialize the GSI subsystem
* @gsi: Address of GSI structure embedded in an IPA structure
* @pdev: IPA platform device
+ * @version: IPA hardware version (implies GSI version)
+ * @count: Number of entries in the configuration data array
+ * @data: Endpoint and channel configuration data
*
* Return: 0 if successful, or a negative error code
*
* Early stage initialization of the GSI subsystem, performing tasks
* that can be done before the GSI hardware is ready to use.
*/
-int gsi_init(struct gsi *gsi, struct platform_device *pdev, bool prefetch,
- u32 count, const struct ipa_gsi_endpoint_data *data,
- bool modem_alloc);
+int gsi_init(struct gsi *gsi, struct platform_device *pdev,
+ enum ipa_version version, u32 count,
+ const struct ipa_gsi_endpoint_data *data);
/**
* gsi_exit() - Exit the GSI subsystem
* (though the actual limit is hardware-dependent).
*/
+/* GSI EE registers as a group are shifted downward by a fixed
+ * constant amount for IPA versions 4.5 and beyond. This applies
+ * to all GSI registers we use *except* the ones that disable
+ * inter-EE interrupts for channels and event channels.
+ *
+ * We handle this by adjusting the pointer to the mapped GSI memory
+ * region downward. Then in the one place we use them (gsi_irq_setup())
+ * we undo that adjustment for the inter-EE interrupt registers.
+ */
+#define GSI_EE_REG_ADJUST 0x0000d000 /* IPA v4.5+ */
+
#define GSI_INTER_EE_SRC_CH_IRQ_OFFSET \
GSI_INTER_EE_N_SRC_CH_IRQ_OFFSET(GSI_EE_AP)
#define GSI_INTER_EE_N_SRC_CH_IRQ_OFFSET(ee) \
#define CHTYPE_DIR_FMASK GENMASK(3, 3)
#define EE_FMASK GENMASK(7, 4)
#define CHID_FMASK GENMASK(12, 8)
-/* The next field is present for GSI v2.0 and above */
+/* The next field is present for IPA v4.5 and above */
#define CHTYPE_PROTOCOL_MSB_FMASK GENMASK(13, 13)
#define ERINDEX_FMASK GENMASK(18, 14)
#define CHSTATE_FMASK GENMASK(23, 20)
#define ELEMENT_SIZE_FMASK GENMASK(31, 24)
+/** enum gsi_channel_type - CHTYPE_PROTOCOL field values in CH_C_CNTXT_0 */
+enum gsi_channel_type {
+ GSI_CHANNEL_TYPE_MHI = 0x0,
+ GSI_CHANNEL_TYPE_XHCI = 0x1,
+ GSI_CHANNEL_TYPE_GPI = 0x2,
+ GSI_CHANNEL_TYPE_XDCI = 0x3,
+};
+
#define GSI_CH_C_CNTXT_1_OFFSET(ch) \
GSI_EE_N_CH_C_CNTXT_1_OFFSET((ch), GSI_EE_AP)
#define GSI_EE_N_CH_C_CNTXT_1_OFFSET(ch, ee) \
#define WRR_WEIGHT_FMASK GENMASK(3, 0)
#define MAX_PREFETCH_FMASK GENMASK(8, 8)
#define USE_DB_ENG_FMASK GENMASK(9, 9)
-/* The next field is present for GSI v2.0 and above */
+/* The next field is only present for IPA v4.0, v4.1, and v4.2 */
#define USE_ESCAPE_BUF_ONLY_FMASK GENMASK(10, 10)
+/* The next two fields are present for IPA v4.5 and above */
+#define PREFETCH_MODE_FMASK GENMASK(13, 10)
+#define EMPTY_LVL_THRSHOLD_FMASK GENMASK(23, 16)
+/** enum gsi_prefetch_mode - PREFETCH_MODE field in CH_C_QOS */
+enum gsi_prefetch_mode {
+ GSI_USE_PREFETCH_BUFS = 0x0,
+ GSI_ESCAPE_BUF_ONLY = 0x1,
+ GSI_SMART_PREFETCH = 0x2,
+ GSI_FREE_PREFETCH = 0x3,
+};
#define GSI_CH_C_SCRATCH_0_OFFSET(ch) \
GSI_EE_N_CH_C_SCRATCH_0_OFFSET((ch), GSI_EE_AP)
#define EV_INTYPE_FMASK GENMASK(16, 16)
#define EV_CHSTATE_FMASK GENMASK(23, 20)
#define EV_ELEMENT_SIZE_FMASK GENMASK(31, 24)
+/* enum gsi_channel_type defines EV_CHTYPE field values in EV_CH_E_CNTXT_0 */
#define GSI_EV_CH_E_CNTXT_1_OFFSET(ev) \
GSI_EE_N_EV_CH_E_CNTXT_1_OFFSET((ev), GSI_EE_AP)
#define CH_CHID_FMASK GENMASK(7, 0)
#define CH_OPCODE_FMASK GENMASK(31, 24)
+/** enum gsi_ch_cmd_opcode - CH_OPCODE field values in CH_CMD */
+enum gsi_ch_cmd_opcode {
+ GSI_CH_ALLOCATE = 0x0,
+ GSI_CH_START = 0x1,
+ GSI_CH_STOP = 0x2,
+ GSI_CH_RESET = 0x9,
+ GSI_CH_DE_ALLOC = 0xa,
+};
+
#define GSI_EV_CH_CMD_OFFSET \
GSI_EE_N_EV_CH_CMD_OFFSET(GSI_EE_AP)
#define GSI_EE_N_EV_CH_CMD_OFFSET(ee) \
#define EV_CHID_FMASK GENMASK(7, 0)
#define EV_OPCODE_FMASK GENMASK(31, 24)
+/** enum gsi_evt_cmd_opcode - EV_OPCODE field values in EV_CH_CMD */
+enum gsi_evt_cmd_opcode {
+ GSI_EVT_ALLOCATE = 0x0,
+ GSI_EVT_RESET = 0x9,
+ GSI_EVT_DE_ALLOC = 0xa,
+};
+
#define GSI_GENERIC_CMD_OFFSET \
GSI_EE_N_GENERIC_CMD_OFFSET(GSI_EE_AP)
#define GSI_EE_N_GENERIC_CMD_OFFSET(ee) \
#define GENERIC_CHID_FMASK GENMASK(9, 5)
#define GENERIC_EE_FMASK GENMASK(13, 10)
+/** enum gsi_generic_cmd_opcode - GENERIC_OPCODE field values in GENERIC_CMD */
+enum gsi_generic_cmd_opcode {
+ GSI_GENERIC_HALT_CHANNEL = 0x1,
+ GSI_GENERIC_ALLOCATE_CHANNEL = 0x2,
+};
+
#define GSI_GSI_HW_PARAM_2_OFFSET \
GSI_EE_N_GSI_HW_PARAM_2_OFFSET(GSI_EE_AP)
#define GSI_EE_N_GSI_HW_PARAM_2_OFFSET(ee) \
(0x0001f040 + 0x4000 * (ee))
#define IRAM_SIZE_FMASK GENMASK(2, 0)
-#define IRAM_SIZE_ONE_KB_FVAL 0
-#define IRAM_SIZE_TWO_KB_FVAL 1
-/* The next two values are available for GSI v2.0 and above */
-#define IRAM_SIZE_TWO_N_HALF_KB_FVAL 2
-#define IRAM_SIZE_THREE_KB_FVAL 3
#define NUM_CH_PER_EE_FMASK GENMASK(7, 3)
#define NUM_EV_PER_EE_FMASK GENMASK(12, 8)
#define GSI_CH_PEND_TRANSLATE_FMASK GENMASK(13, 13)
#define GSI_CH_FULL_LOGIC_FMASK GENMASK(14, 14)
-/* Fields below are present for GSI v2.0 and above */
+/* Fields below are present for IPA v4.0 and above */
#define GSI_USE_SDMA_FMASK GENMASK(15, 15)
#define GSI_SDMA_N_INT_FMASK GENMASK(18, 16)
#define GSI_SDMA_MAX_BURST_FMASK GENMASK(26, 19)
#define GSI_SDMA_N_IOVEC_FMASK GENMASK(29, 27)
-/* Fields below are present for GSI v2.2 and above */
+/* Fields below are present for IPA v4.2 and above */
#define GSI_USE_RD_WR_ENG_FMASK GENMASK(30, 30)
#define GSI_USE_INTER_EE_FMASK GENMASK(31, 31)
+/** enum gsi_iram_size - IRAM_SIZE field values in HW_PARAM_2 */
+enum gsi_iram_size {
+ IRAM_SIZE_ONE_KB = 0x0,
+ IRAM_SIZE_TWO_KB = 0x1,
+/* The next two values are available for IPA v4.0 and above */
+ IRAM_SIZE_TWO_N_HALF_KB = 0x2,
+ IRAM_SIZE_THREE_KB = 0x3,
+ /* The next two values are available for IPA v4.5 and above */
+ IRAM_SIZE_THREE_N_HALF_KB = 0x4,
+ IRAM_SIZE_FOUR_KB = 0x5,
+};
+
+/* IRQ condition for each type is cleared by writing type-specific register */
#define GSI_CNTXT_TYPE_IRQ_OFFSET \
GSI_EE_N_CNTXT_TYPE_IRQ_OFFSET(GSI_EE_AP)
#define GSI_EE_N_CNTXT_TYPE_IRQ_OFFSET(ee) \
GSI_EE_N_CNTXT_TYPE_IRQ_MSK_OFFSET(GSI_EE_AP)
#define GSI_EE_N_CNTXT_TYPE_IRQ_MSK_OFFSET(ee) \
(0x0001f088 + 0x4000 * (ee))
-/* The masks below are used for the TYPE_IRQ and TYPE_IRQ_MASK registers */
-#define CH_CTRL_FMASK GENMASK(0, 0)
-#define EV_CTRL_FMASK GENMASK(1, 1)
-#define GLOB_EE_FMASK GENMASK(2, 2)
-#define IEOB_FMASK GENMASK(3, 3)
-#define INTER_EE_CH_CTRL_FMASK GENMASK(4, 4)
-#define INTER_EE_EV_CTRL_FMASK GENMASK(5, 5)
-#define GENERAL_FMASK GENMASK(6, 6)
-#define GSI_CNTXT_TYPE_IRQ_MSK_ALL GENMASK(6, 0)
+
+/* Values here are bit positions in the TYPE_IRQ and TYPE_IRQ_MSK registers */
+enum gsi_irq_type_id {
+ GSI_CH_CTRL = 0x0, /* channel allocation, etc. */
+ GSI_EV_CTRL = 0x1, /* event ring allocation, etc. */
+ GSI_GLOB_EE = 0x2, /* global/general event */
+ GSI_IEOB = 0x3, /* TRE completion */
+ GSI_INTER_EE_CH_CTRL = 0x4, /* remote-issued stop/reset (unused) */
+ GSI_INTER_EE_EV_CTRL = 0x5, /* remote-issued event reset (unused) */
+ GSI_GENERAL = 0x6, /* general-purpose event */
+};
#define GSI_CNTXT_SRC_CH_IRQ_OFFSET \
GSI_EE_N_CNTXT_SRC_CH_IRQ_OFFSET(GSI_EE_AP)
GSI_EE_N_CNTXT_GLOB_IRQ_CLR_OFFSET(GSI_EE_AP)
#define GSI_EE_N_CNTXT_GLOB_IRQ_CLR_OFFSET(ee) \
(0x0001f110 + 0x4000 * (ee))
-/* The masks below are used for the general IRQ STTS, EN, and CLR registers */
-#define ERROR_INT_FMASK GENMASK(0, 0)
-#define GP_INT1_FMASK GENMASK(1, 1)
-#define GP_INT2_FMASK GENMASK(2, 2)
-#define GP_INT3_FMASK GENMASK(3, 3)
-#define GSI_CNTXT_GLOB_IRQ_ALL GENMASK(3, 0)
+/* Values here are bit positions in the GLOB_IRQ_* registers */
+enum gsi_global_irq_id {
+ ERROR_INT = 0x0,
+ GP_INT1 = 0x1,
+ GP_INT2 = 0x2,
+ GP_INT3 = 0x3,
+};
#define GSI_CNTXT_GSI_IRQ_STTS_OFFSET \
GSI_EE_N_CNTXT_GSI_IRQ_STTS_OFFSET(GSI_EE_AP)
GSI_EE_N_CNTXT_GSI_IRQ_CLR_OFFSET(GSI_EE_AP)
#define GSI_EE_N_CNTXT_GSI_IRQ_CLR_OFFSET(ee) \
(0x0001f128 + 0x4000 * (ee))
-/* The masks below are used for the general IRQ STTS, EN, and CLR registers */
-#define BREAK_POINT_FMASK GENMASK(0, 0)
-#define BUS_ERROR_FMASK GENMASK(1, 1)
-#define CMD_FIFO_OVRFLOW_FMASK GENMASK(2, 2)
-#define MCS_STACK_OVRFLOW_FMASK GENMASK(3, 3)
-#define GSI_CNTXT_GSI_IRQ_ALL GENMASK(3, 0)
+/* Values here are bit positions in the (general) GSI_IRQ_* registers */
+enum gsi_general_id {
+ BREAK_POINT = 0x0,
+ BUS_ERROR = 0x1,
+ CMD_FIFO_OVRFLOW = 0x2,
+ MCS_STACK_OVRFLOW = 0x3,
+};
#define GSI_CNTXT_INTSET_OFFSET \
GSI_EE_N_CNTXT_INTSET_OFFSET(GSI_EE_AP)
#define ERR_TYPE_FMASK GENMASK(27, 24)
#define ERR_EE_FMASK GENMASK(31, 28)
+/** enum gsi_err_code - ERR_CODE field values in EE_ERR_LOG */
+enum gsi_err_code {
+ GSI_INVALID_TRE = 0x1,
+ GSI_OUT_OF_BUFFERS = 0x2,
+ GSI_OUT_OF_RESOURCES = 0x3,
+ GSI_UNSUPPORTED_INTER_EE_OP = 0x4,
+ GSI_EVT_RING_EMPTY = 0x5,
+ GSI_NON_ALLOCATED_EVT_ACCESS = 0x6,
+ /* 7 is not assigned */
+ GSI_HWO_1 = 0x8,
+};
+
+/** enum gsi_err_type - ERR_TYPE field values in EE_ERR_LOG */
+enum gsi_err_type {
+ GSI_ERR_TYPE_GLOB = 0x1,
+ GSI_ERR_TYPE_CHAN = 0x2,
+ GSI_ERR_TYPE_EVT = 0x3,
+};
+
#define GSI_ERROR_LOG_CLR_OFFSET \
GSI_EE_N_ERROR_LOG_CLR_OFFSET(GSI_EE_AP)
#define GSI_EE_N_ERROR_LOG_CLR_OFFSET(ee) \
(0x0001f400 + 0x4000 * (ee))
#define INTER_EE_RESULT_FMASK GENMASK(2, 0)
#define GENERIC_EE_RESULT_FMASK GENMASK(7, 5)
-#define GENERIC_EE_SUCCESS_FVAL 1
-#define GENERIC_EE_INCORRECT_DIRECTION_FVAL 3
-#define GENERIC_EE_INCORRECT_CHANNEL_FVAL 5
-#define GENERIC_EE_NO_RESOURCES_FVAL 7
+
+/** enum gsi_generic_ee_result - GENERIC_EE_RESULT field values in SCRATCH_0 */
+enum gsi_generic_ee_result {
+ GENERIC_EE_SUCCESS = 0x1,
+ GENERIC_EE_CHANNEL_NOT_RUNNING = 0x2,
+ GENERIC_EE_INCORRECT_DIRECTION = 0x3,
+ GENERIC_EE_INCORRECT_CHANNEL_TYPE = 0x4,
+ GENERIC_EE_INCORRECT_CHANNEL = 0x5,
+ GENERIC_EE_RETRY = 0x6,
+ GENERIC_EE_NO_RESOURCES = 0x7,
+};
+
#define USB_MAX_PACKET_FMASK GENMASK(15, 15) /* 0: HS; 1: SS */
#define MHI_BASE_CHANNEL_FMASK GENMASK(31, 24)
#include "ipa.h"
#include "ipa_clock.h"
#include "ipa_modem.h"
+#include "ipa_data.h"
/**
* DOC: IPA Clocking
* An IPA clock reference must be held for any access to IPA hardware.
*/
-#define IPA_CORE_CLOCK_RATE (75UL * 1000 * 1000) /* Hz */
-
-/* Interconnect path bandwidths (each times 1000 bytes per second) */
-#define IPA_MEMORY_AVG (80 * 1000) /* 80 MBps */
-#define IPA_MEMORY_PEAK (600 * 1000)
-
-#define IPA_IMEM_AVG (80 * 1000)
-#define IPA_IMEM_PEAK (350 * 1000)
-
-#define IPA_CONFIG_AVG (40 * 1000)
-#define IPA_CONFIG_PEAK (40 * 1000)
-
/**
* struct ipa_clock - IPA clocking information
* @count: Clocking reference count
* @memory_path: Memory interconnect
* @imem_path: Internal memory interconnect
* @config_path: Configuration space interconnect
+ * @interconnect_data: Interconnect configuration data
*/
struct ipa_clock {
refcount_t count;
struct icc_path *memory_path;
struct icc_path *imem_path;
struct icc_path *config_path;
+ const struct ipa_interconnect_data *interconnect_data;
};
static struct icc_path *
/* Currently we only use one bandwidth level, so just "enable" interconnects */
static int ipa_interconnect_enable(struct ipa *ipa)
{
+ const struct ipa_interconnect_data *data;
struct ipa_clock *clock = ipa->clock;
int ret;
- ret = icc_set_bw(clock->memory_path, IPA_MEMORY_AVG, IPA_MEMORY_PEAK);
+ data = &clock->interconnect_data[IPA_INTERCONNECT_MEMORY];
+ ret = icc_set_bw(clock->memory_path, data->average_rate,
+ data->peak_rate);
if (ret)
return ret;
- ret = icc_set_bw(clock->imem_path, IPA_IMEM_AVG, IPA_IMEM_PEAK);
+ data = &clock->interconnect_data[IPA_INTERCONNECT_IMEM];
+ ret = icc_set_bw(clock->memory_path, data->average_rate,
+ data->peak_rate);
if (ret)
goto err_memory_path_disable;
- ret = icc_set_bw(clock->config_path, IPA_CONFIG_AVG, IPA_CONFIG_PEAK);
+ data = &clock->interconnect_data[IPA_INTERCONNECT_CONFIG];
+ ret = icc_set_bw(clock->memory_path, data->average_rate,
+ data->peak_rate);
if (ret)
goto err_imem_path_disable;
/* To disable an interconnect, we just its bandwidth to 0 */
static int ipa_interconnect_disable(struct ipa *ipa)
{
+ const struct ipa_interconnect_data *data;
struct ipa_clock *clock = ipa->clock;
int ret;
return 0;
err_imem_path_reenable:
- (void)icc_set_bw(clock->imem_path, IPA_IMEM_AVG, IPA_IMEM_PEAK);
+ data = &clock->interconnect_data[IPA_INTERCONNECT_IMEM];
+ (void)icc_set_bw(clock->imem_path, data->average_rate,
+ data->peak_rate);
err_memory_path_reenable:
- (void)icc_set_bw(clock->memory_path, IPA_MEMORY_AVG, IPA_MEMORY_PEAK);
+ data = &clock->interconnect_data[IPA_INTERCONNECT_MEMORY];
+ (void)icc_set_bw(clock->memory_path, data->average_rate,
+ data->peak_rate);
return ret;
}
}
/* Initialize IPA clocking */
-struct ipa_clock *ipa_clock_init(struct device *dev)
+struct ipa_clock *
+ipa_clock_init(struct device *dev, const struct ipa_clock_data *data)
{
struct ipa_clock *clock;
struct clk *clk;
return ERR_CAST(clk);
}
- ret = clk_set_rate(clk, IPA_CORE_CLOCK_RATE);
+ ret = clk_set_rate(clk, data->core_clock_rate);
if (ret) {
- dev_err(dev, "error %d setting core clock rate to %lu\n",
- ret, IPA_CORE_CLOCK_RATE);
+ dev_err(dev, "error %d setting core clock rate to %u\n",
+ ret, data->core_clock_rate);
goto err_clk_put;
}
goto err_clk_put;
}
clock->core = clk;
+ clock->interconnect_data = data->interconnect;
ret = ipa_interconnect_init(clock, dev);
if (ret)
struct device;
struct ipa;
+struct ipa_clock_data;
/**
* ipa_clock_rate() - Return the current IPA core clock rate
/**
* ipa_clock_init() - Initialize IPA clocking
* @dev: IPA device
+ * @data: Clock configuration data
*
* Return: A pointer to an ipa_clock structure, or a pointer-coded error
*/
-struct ipa_clock *ipa_clock_init(struct device *dev);
+struct ipa_clock *ipa_clock_init(struct device *dev,
+ const struct ipa_clock_data *data);
/**
* ipa_clock_exit() - Inverse of ipa_clock_init()
/* Some commands can wait until indicated pipeline stages are clear */
enum pipeline_clear_options {
- pipeline_clear_hps = 0,
- pipeline_clear_src_grp = 1,
- pipeline_clear_full = 2,
+ pipeline_clear_hps = 0x0,
+ pipeline_clear_src_grp = 0x1,
+ pipeline_clear_full = 0x2,
};
/* IPA_CMD_IP_V{4,6}_{FILTER,ROUTING}_INIT */
* a request is *not* an immediate command.
*/
enum ipa_cmd_opcode {
- IPA_CMD_NONE = 0,
- IPA_CMD_IP_V4_FILTER_INIT = 3,
- IPA_CMD_IP_V6_FILTER_INIT = 4,
- IPA_CMD_IP_V4_ROUTING_INIT = 7,
- IPA_CMD_IP_V6_ROUTING_INIT = 8,
- IPA_CMD_HDR_INIT_LOCAL = 9,
- IPA_CMD_REGISTER_WRITE = 12,
- IPA_CMD_IP_PACKET_INIT = 16,
- IPA_CMD_DMA_SHARED_MEM = 19,
- IPA_CMD_IP_PACKET_TAG_STATUS = 20,
+ IPA_CMD_NONE = 0x0,
+ IPA_CMD_IP_V4_FILTER_INIT = 0x3,
+ IPA_CMD_IP_V6_FILTER_INIT = 0x4,
+ IPA_CMD_IP_V4_ROUTING_INIT = 0x7,
+ IPA_CMD_IP_V6_ROUTING_INIT = 0x8,
+ IPA_CMD_HDR_INIT_LOCAL = 0x9,
+ IPA_CMD_REGISTER_WRITE = 0xc,
+ IPA_CMD_IP_PACKET_INIT = 0x10,
+ IPA_CMD_DMA_SHARED_MEM = 0x13,
+ IPA_CMD_IP_PACKET_TAG_STATUS = 0x14,
};
/**
enum dma_data_direction direction;
};
-
#ifdef IPA_VALIDATE
/**
.endpoint = {
.seq_type = IPA_SEQ_DMA_ONLY,
.config = {
+ .resource_group = 0,
.dma_mode = true,
.dma_endpoint = IPA_ENDPOINT_AP_LAN_RX,
},
.endpoint = {
.seq_type = IPA_SEQ_INVALID,
.config = {
+ .resource_group = 0,
.aggregation = true,
.status_enable = true,
.rx = {
.seq_type =
IPA_SEQ_PKT_PROCESS_NO_DEC_NO_UCP_DMAP,
.config = {
+ .resource_group = 0,
.checksum = true,
.qmap = true,
.status_enable = true,
.endpoint = {
.seq_type = IPA_SEQ_INVALID,
.config = {
+ .resource_group = 0,
.checksum = true,
.qmap = true,
.aggregation = true,
.smem_size = 0x00002000,
};
+static struct ipa_clock_data ipa_clock_data = {
+ .core_clock_rate = 100 * 1000 * 1000, /* Hz */
+ /* Interconnect rates are in 1000 byte/second units */
+ .interconnect = {
+ [IPA_INTERCONNECT_MEMORY] = {
+ .peak_rate = 465000, /* 465 MBps */
+ .average_rate = 80000, /* 80 MBps */
+ },
+ /* Average rate is unused for the next two interconnects */
+ [IPA_INTERCONNECT_IMEM] = {
+ .peak_rate = 68570, /* 68.570 MBps */
+ .average_rate = 0, /* unused */
+ },
+ [IPA_INTERCONNECT_CONFIG] = {
+ .peak_rate = 30000, /* 30 MBps */
+ .average_rate = 0, /* unused */
+ },
+ },
+};
+
/* Configuration data for the SC7180 SoC. */
const struct ipa_data ipa_data_sc7180 = {
.version = IPA_VERSION_4_2,
.endpoint_data = ipa_gsi_endpoint_data,
.resource_data = &ipa_resource_data,
.mem_data = &ipa_mem_data,
+ .clock_data = &ipa_clock_data,
};
.endpoint = {
.seq_type = IPA_SEQ_DMA_ONLY,
.config = {
+ .resource_group = 1,
.dma_mode = true,
.dma_endpoint = IPA_ENDPOINT_AP_LAN_RX,
},
.endpoint = {
.seq_type = IPA_SEQ_INVALID,
.config = {
+ .resource_group = 1,
.aggregation = true,
.status_enable = true,
.rx = {
.seq_type =
IPA_SEQ_2ND_PKT_PROCESS_PASS_NO_DEC_UCP,
.config = {
+ .resource_group = 1,
.checksum = true,
.qmap = true,
.status_enable = true,
.endpoint = {
.seq_type = IPA_SEQ_INVALID,
.config = {
+ .resource_group = 1,
.checksum = true,
.qmap = true,
.aggregation = true,
.type = IPA_RESOURCE_TYPE_SRC_PKT_CONTEXTS,
.limits[0] = {
.min = 1,
- .max = 63,
+ .max = 255,
},
.limits[1] = {
.min = 1,
- .max = 63,
+ .max = 255,
},
},
{
.smem_size = 0x00002000,
};
+static struct ipa_clock_data ipa_clock_data = {
+ .core_clock_rate = 75 * 1000 * 1000, /* Hz */
+ /* Interconnect rates are in 1000 byte/second units */
+ .interconnect = {
+ [IPA_INTERCONNECT_MEMORY] = {
+ .peak_rate = 600000, /* 600 MBps */
+ .average_rate = 80000, /* 80 MBps */
+ },
+ /* Average rate is unused for the next two interconnects */
+ [IPA_INTERCONNECT_IMEM] = {
+ .peak_rate = 350000, /* 350 MBps */
+ .average_rate = 0, /* unused */
+ },
+ [IPA_INTERCONNECT_CONFIG] = {
+ .peak_rate = 40000, /* 40 MBps */
+ .average_rate = 0, /* unused */
+ },
+ },
+};
+
/* Configuration data for the SDM845 SoC. */
const struct ipa_data ipa_data_sdm845 = {
.version = IPA_VERSION_3_5_1,
.endpoint_data = ipa_gsi_endpoint_data,
.resource_data = &ipa_resource_data,
.mem_data = &ipa_mem_data,
+ .clock_data = &ipa_clock_data,
};
* the IPA endpoint.
*/
-/* The maximum value returned by ipa_resource_group_count() */
-#define IPA_RESOURCE_GROUP_COUNT 4
+/* The maximum value returned by ipa_resource_group_{src,dst}_count() */
+#define IPA_RESOURCE_GROUP_SRC_MAX 5
+#define IPA_RESOURCE_GROUP_DST_MAX 5
-/** enum ipa_resource_type_src - source resource types */
/**
* struct gsi_channel_data - GSI channel configuration data
* @tre_count: number of TREs in the channel ring
/**
* struct ipa_endpoint_config_data - IPA endpoint hardware configuration
+ * @resource_group: resource group to assign endpoint to
* @checksum: whether checksum offload is enabled
* @qmap: whether endpoint uses QMAP protocol
* @aggregation: whether endpoint supports aggregation
* @rx: RX-specific endpoint information (see above)
*/
struct ipa_endpoint_config_data {
+ u32 resource_group;
bool checksum;
bool qmap;
bool aggregation;
*/
struct ipa_resource_src {
enum ipa_resource_type_src type;
- struct ipa_resource_limits limits[IPA_RESOURCE_GROUP_COUNT];
+ struct ipa_resource_limits limits[IPA_RESOURCE_GROUP_SRC_MAX];
};
/**
*/
struct ipa_resource_dst {
enum ipa_resource_type_dst type;
- struct ipa_resource_limits limits[IPA_RESOURCE_GROUP_COUNT];
+ struct ipa_resource_limits limits[IPA_RESOURCE_GROUP_DST_MAX];
};
/**
};
/**
- * struct ipa_mem - description of IPA memory regions
+ * struct ipa_mem_data - description of IPA memory regions
* @local_count: number of regions defined in the local[] array
* @local: array of IPA-local memory region descriptors
* @imem_addr: physical address of IPA region within IMEM
u32 smem_size;
};
+/** enum ipa_interconnect_id - IPA interconnect identifier */
+enum ipa_interconnect_id {
+ IPA_INTERCONNECT_MEMORY,
+ IPA_INTERCONNECT_IMEM,
+ IPA_INTERCONNECT_CONFIG,
+ IPA_INTERCONNECT_COUNT, /* Last; not an interconnect */
+};
+
+/**
+ * struct ipa_interconnect_data - description of IPA interconnect rates
+ * @peak_rate: Peak interconnect bandwidth (in 1000 byte/sec units)
+ * @average_rate: Average interconnect bandwidth (in 1000 byte/sec units)
+ */
+struct ipa_interconnect_data {
+ u32 peak_rate;
+ u32 average_rate;
+};
+
+/**
+ * struct ipa_clock_data - description of IPA clock and interconnect rates
+ * @core_clock_rate: Core clock rate (Hz)
+ * @interconnect: Array of interconnect bandwidth parameters
+ */
+struct ipa_clock_data {
+ u32 core_clock_rate;
+ struct ipa_interconnect_data interconnect[IPA_INTERCONNECT_COUNT];
+};
+
/**
* struct ipa_data - combined IPA/GSI configuration data
* @version: IPA hardware version
const struct ipa_gsi_endpoint_data *endpoint_data;
const struct ipa_resource_data *resource_data;
const struct ipa_mem_data *mem_data;
+ const struct ipa_clock_data *clock_data;
};
extern const struct ipa_data ipa_data_sdm845;
#define IPA_ENDPOINT_QMAP_METADATA_MASK 0x000000ff /* host byte order */
#define IPA_ENDPOINT_RESET_AGGR_RETRY_MAX 3
-#define IPA_AGGR_TIME_LIMIT_DEFAULT 500 /* microseconds */
+#define IPA_AGGR_TIME_LIMIT 500 /* microseconds */
/** enum ipa_status_opcode - status element opcode hardware values */
enum ipa_status_opcode {
#ifdef IPA_VALIDATE
-static void ipa_endpoint_validate_build(void)
-{
- /* The aggregation byte limit defines the point at which an
- * aggregation window will close. It is programmed into the
- * IPA hardware as a number of KB. We don't use "hard byte
- * limit" aggregation, which means that we need to supply
- * enough space in a receive buffer to hold a complete MTU
- * plus normal skb overhead *after* that aggregation byte
- * limit has been crossed.
- *
- * This check just ensures we don't define a receive buffer
- * size that would exceed what we can represent in the field
- * that is used to program its size.
- */
- BUILD_BUG_ON(IPA_RX_BUFFER_SIZE >
- field_max(AGGR_BYTE_LIMIT_FMASK) * SZ_1K +
- IPA_MTU + IPA_RX_BUFFER_OVERHEAD);
-
- /* I honestly don't know where this requirement comes from. But
- * it holds, and if we someday need to loosen the constraint we
- * can try to track it down.
- */
- BUILD_BUG_ON(sizeof(struct ipa_status) % 4);
-}
-
static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count,
const struct ipa_gsi_endpoint_data *all_data,
const struct ipa_gsi_endpoint_data *data)
return true;
}
+static u32 aggr_byte_limit_max(enum ipa_version version)
+{
+ if (version < IPA_VERSION_4_5)
+ return field_max(aggr_byte_limit_fmask(true));
+
+ return field_max(aggr_byte_limit_fmask(false));
+}
+
static bool ipa_endpoint_data_valid(struct ipa *ipa, u32 count,
const struct ipa_gsi_endpoint_data *data)
{
const struct ipa_gsi_endpoint_data *dp = data;
struct device *dev = &ipa->pdev->dev;
enum ipa_endpoint_name name;
+ u32 limit;
- ipa_endpoint_validate_build();
+ /* Not sure where this constraint come from... */
+ BUILD_BUG_ON(sizeof(struct ipa_status) % 4);
if (count > IPA_ENDPOINT_COUNT) {
dev_err(dev, "too many endpoints specified (%u > %u)\n",
return false;
}
+ /* The aggregation byte limit defines the point at which an
+ * aggregation window will close. It is programmed into the
+ * IPA hardware as a number of KB. We don't use "hard byte
+ * limit" aggregation, which means that we need to supply
+ * enough space in a receive buffer to hold a complete MTU
+ * plus normal skb overhead *after* that aggregation byte
+ * limit has been crossed.
+ *
+ * This check ensures we don't define a receive buffer size
+ * that would exceed what we can represent in the field that
+ * is used to program its size.
+ */
+ limit = aggr_byte_limit_max(ipa->version) * SZ_1K;
+ limit += IPA_MTU + IPA_RX_BUFFER_OVERHEAD;
+ if (limit < IPA_RX_BUFFER_SIZE) {
+ dev_err(dev, "buffer size too big for aggregation (%u > %u)\n",
+ IPA_RX_BUFFER_SIZE, limit);
+ return false;
+ }
+
/* Make sure needed endpoints have defined data */
if (ipa_gsi_endpoint_data_empty(&data[IPA_ENDPOINT_AP_COMMAND_TX])) {
dev_err(dev, "command TX endpoint not defined\n");
static void ipa_endpoint_init_hdr(struct ipa_endpoint *endpoint)
{
u32 offset = IPA_REG_ENDP_INIT_HDR_N_OFFSET(endpoint->endpoint_id);
+ struct ipa *ipa = endpoint->ipa;
u32 val = 0;
if (endpoint->data->qmap) {
size_t header_size = sizeof(struct rmnet_map_header);
+ enum ipa_version version = ipa->version;
/* We might supply a checksum header after the QMAP header */
if (endpoint->toward_ipa && endpoint->data->checksum)
header_size += sizeof(struct rmnet_map_ul_csum_header);
- val |= u32_encode_bits(header_size, HDR_LEN_FMASK);
+ val |= ipa_header_size_encoded(version, header_size);
/* Define how to fill fields in a received QMAP header */
if (!endpoint->toward_ipa) {
- u32 off; /* Field offset within header */
+ u32 offset; /* Field offset within header */
/* Where IPA will write the metadata value */
- off = offsetof(struct rmnet_map_header, mux_id);
- val |= u32_encode_bits(off, HDR_OFST_METADATA_FMASK);
+ offset = offsetof(struct rmnet_map_header, mux_id);
+ val |= ipa_metadata_offset_encoded(version, offset);
/* Where IPA will write the length */
- off = offsetof(struct rmnet_map_header, pkt_len);
+ offset = offsetof(struct rmnet_map_header, pkt_len);
+ /* Upper bits are stored in HDR_EXT with IPA v4.5 */
+ if (version == IPA_VERSION_4_5)
+ offset &= field_mask(HDR_OFST_PKT_SIZE_FMASK);
+
val |= HDR_OFST_PKT_SIZE_VALID_FMASK;
- val |= u32_encode_bits(off, HDR_OFST_PKT_SIZE_FMASK);
+ val |= u32_encode_bits(offset, HDR_OFST_PKT_SIZE_FMASK);
}
/* For QMAP TX, metadata offset is 0 (modem assumes this) */
val |= HDR_OFST_METADATA_VALID_FMASK;
/* HDR_ADDITIONAL_CONST_LEN is 0; (RX only) */
/* HDR_A5_MUX is 0 */
/* HDR_LEN_INC_DEAGG_HDR is 0 */
- /* HDR_METADATA_REG_VALID is 0 (TX only) */
+ /* HDR_METADATA_REG_VALID is 0 (TX only, version < v4.5) */
}
- iowrite32(val, endpoint->ipa->reg_virt + offset);
+ iowrite32(val, ipa->reg_virt + offset);
}
static void ipa_endpoint_init_hdr_ext(struct ipa_endpoint *endpoint)
{
u32 offset = IPA_REG_ENDP_INIT_HDR_EXT_N_OFFSET(endpoint->endpoint_id);
u32 pad_align = endpoint->data->rx.pad_align;
+ struct ipa *ipa = endpoint->ipa;
u32 val = 0;
val |= HDR_ENDIANNESS_FMASK; /* big endian */
if (!endpoint->toward_ipa)
val |= u32_encode_bits(pad_align, HDR_PAD_TO_ALIGNMENT_FMASK);
- iowrite32(val, endpoint->ipa->reg_virt + offset);
+ /* IPA v4.5 adds some most-significant bits to a few fields,
+ * two of which are defined in the HDR (not HDR_EXT) register.
+ */
+ if (ipa->version == IPA_VERSION_4_5) {
+ /* HDR_TOTAL_LEN_OR_PAD_OFFSET is 0, so MSB is 0 */
+ if (endpoint->data->qmap && !endpoint->toward_ipa) {
+ u32 offset;
+
+ offset = offsetof(struct rmnet_map_header, pkt_len);
+ offset >>= hweight32(HDR_OFST_PKT_SIZE_FMASK);
+ val |= u32_encode_bits(offset,
+ HDR_OFST_PKT_SIZE_MSB_FMASK);
+ /* HDR_ADDITIONAL_CONST_LEN is 0 so MSB is 0 */
+ }
+ }
+ iowrite32(val, ipa->reg_virt + offset);
}
-
static void ipa_endpoint_init_hdr_metadata_mask(struct ipa_endpoint *endpoint)
{
u32 endpoint_id = endpoint->endpoint_id;
return rx_buffer_size / SZ_1K;
}
+/* Encoded values for AGGR endpoint register fields */
+static u32 aggr_byte_limit_encoded(enum ipa_version version, u32 limit)
+{
+ if (version < IPA_VERSION_4_5)
+ return u32_encode_bits(limit, aggr_byte_limit_fmask(true));
+
+ return u32_encode_bits(limit, aggr_byte_limit_fmask(false));
+}
+
+/* Encode the aggregation timer limit (microseconds) based on IPA version */
+static u32 aggr_time_limit_encoded(enum ipa_version version, u32 limit)
+{
+ u32 gran_sel;
+ u32 fmask;
+ u32 val;
+
+ if (version < IPA_VERSION_4_5) {
+ /* We set aggregation granularity in ipa_hardware_config() */
+ limit = DIV_ROUND_CLOSEST(limit, IPA_AGGR_GRANULARITY);
+
+ return u32_encode_bits(limit, aggr_time_limit_fmask(true));
+ }
+
+ /* IPA v4.5 expresses the time limit using Qtime. The AP has
+ * pulse generators 0 and 1 available, which were configured
+ * in ipa_qtime_config() to have granularity 100 usec and
+ * 1 msec, respectively. Use pulse generator 0 if possible,
+ * otherwise fall back to pulse generator 1.
+ */
+ fmask = aggr_time_limit_fmask(false);
+ val = DIV_ROUND_CLOSEST(limit, 100);
+ if (val > field_max(fmask)) {
+ /* Have to use pulse generator 1 (millisecond granularity) */
+ gran_sel = AGGR_GRAN_SEL_FMASK;
+ val = DIV_ROUND_CLOSEST(limit, 1000);
+ } else {
+ /* We can use pulse generator 0 (100 usec granularity) */
+ gran_sel = 0;
+ }
+
+ return gran_sel | u32_encode_bits(val, fmask);
+}
+
+static u32 aggr_sw_eof_active_encoded(enum ipa_version version, bool enabled)
+{
+ u32 val = enabled ? 1 : 0;
+
+ if (version < IPA_VERSION_4_5)
+ return u32_encode_bits(val, aggr_sw_eof_active_fmask(true));
+
+ return u32_encode_bits(val, aggr_sw_eof_active_fmask(false));
+}
+
static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint)
{
u32 offset = IPA_REG_ENDP_INIT_AGGR_N_OFFSET(endpoint->endpoint_id);
+ enum ipa_version version = endpoint->ipa->version;
u32 val = 0;
if (endpoint->data->aggregation) {
if (!endpoint->toward_ipa) {
+ bool close_eof;
u32 limit;
val |= u32_encode_bits(IPA_ENABLE_AGGR, AGGR_EN_FMASK);
val |= u32_encode_bits(IPA_GENERIC, AGGR_TYPE_FMASK);
limit = ipa_aggr_size_kb(IPA_RX_BUFFER_SIZE);
- val |= u32_encode_bits(limit, AGGR_BYTE_LIMIT_FMASK);
+ val |= aggr_byte_limit_encoded(version, limit);
- limit = IPA_AGGR_TIME_LIMIT_DEFAULT;
- limit = DIV_ROUND_CLOSEST(limit, IPA_AGGR_GRANULARITY);
- val |= u32_encode_bits(limit, AGGR_TIME_LIMIT_FMASK);
+ limit = IPA_AGGR_TIME_LIMIT;
+ val |= aggr_time_limit_encoded(version, limit);
/* AGGR_PKT_LIMIT is 0 (unlimited) */
- if (endpoint->data->rx.aggr_close_eof)
- val |= AGGR_SW_EOF_ACTIVE_FMASK;
+ close_eof = endpoint->data->rx.aggr_close_eof;
+ val |= aggr_sw_eof_active_encoded(version, close_eof);
+
/* AGGR_HARD_BYTE_LIMIT_ENABLE is 0 */
} else {
val |= u32_encode_bits(IPA_ENABLE_DEAGGR,
/* other fields ignored */
}
/* AGGR_FORCE_CLOSE is 0 */
+ /* AGGR_GRAN_SEL is 0 for IPA v4.5 */
} else {
val |= u32_encode_bits(IPA_BYPASS_AGGR, AGGR_EN_FMASK);
/* other fields ignored */
iowrite32(val, endpoint->ipa->reg_virt + offset);
}
-/* The head-of-line blocking timer is defined as a tick count, where each
- * tick represents 128 cycles of the IPA core clock. Return the value
- * that should be written to that register that represents the timeout
- * period provided.
+/* Return the Qtime-based head-of-line blocking timer value that
+ * represents the given number of microseconds. The result
+ * includes both the timer value and the selected timer granularity.
*/
-static u32 ipa_reg_init_hol_block_timer_val(struct ipa *ipa, u32 microseconds)
+static u32 hol_block_timer_qtime_val(struct ipa *ipa, u32 microseconds)
+{
+ u32 gran_sel;
+ u32 val;
+
+ /* IPA v4.5 expresses time limits using Qtime. The AP has
+ * pulse generators 0 and 1 available, which were configured
+ * in ipa_qtime_config() to have granularity 100 usec and
+ * 1 msec, respectively. Use pulse generator 0 if possible,
+ * otherwise fall back to pulse generator 1.
+ */
+ val = DIV_ROUND_CLOSEST(microseconds, 100);
+ if (val > field_max(TIME_LIMIT_FMASK)) {
+ /* Have to use pulse generator 1 (millisecond granularity) */
+ gran_sel = GRAN_SEL_FMASK;
+ val = DIV_ROUND_CLOSEST(microseconds, 1000);
+ } else {
+ /* We can use pulse generator 0 (100 usec granularity) */
+ gran_sel = 0;
+ }
+
+ return gran_sel | u32_encode_bits(val, TIME_LIMIT_FMASK);
+}
+
+/* The head-of-line blocking timer is defined as a tick count. For
+ * IPA version 4.5 the tick count is based on the Qtimer, which is
+ * derived from the 19.2 MHz SoC XO clock. For older IPA versions
+ * each tick represents 128 cycles of the IPA core clock.
+ *
+ * Return the encoded value that should be written to that register
+ * that represents the timeout period provided. For IPA v4.2 this
+ * encodes a base and scale value, while for earlier versions the
+ * value is a simple tick count.
+ */
+static u32 hol_block_timer_val(struct ipa *ipa, u32 microseconds)
{
u32 width;
u32 scale;
if (!microseconds)
return 0; /* Nothing to compute if timer period is 0 */
+ if (ipa->version == IPA_VERSION_4_5)
+ return hol_block_timer_qtime_val(ipa, microseconds);
+
/* Use 64 bit arithmetic to avoid overflow... */
rate = ipa_clock_rate(ipa);
ticks = DIV_ROUND_CLOSEST(microseconds * rate, 128 * USEC_PER_SEC);
/* ...but we still need to fit into a 32-bit register */
WARN_ON(ticks > U32_MAX);
- /* IPA v3.5.1 just records the tick count */
- if (ipa->version == IPA_VERSION_3_5_1)
+ /* IPA v3.5.1 through v4.1 just record the tick count */
+ if (ipa->version < IPA_VERSION_4_2)
return (u32)ticks;
/* For IPA v4.2, the tick count is represented by base and
u32 val;
offset = IPA_REG_ENDP_INIT_HOL_BLOCK_TIMER_N_OFFSET(endpoint_id);
- val = ipa_reg_init_hol_block_timer_val(ipa, microseconds);
+ val = hol_block_timer_val(ipa, microseconds);
iowrite32(val, ipa->reg_virt + offset);
}
iowrite32(val, endpoint->ipa->reg_virt + offset);
}
+static void ipa_endpoint_init_rsrc_grp(struct ipa_endpoint *endpoint)
+{
+ u32 offset = IPA_REG_ENDP_INIT_RSRC_GRP_N_OFFSET(endpoint->endpoint_id);
+ struct ipa *ipa = endpoint->ipa;
+ u32 val;
+
+ val = rsrc_grp_encoded(ipa->version, endpoint->data->resource_group);
+ iowrite32(val, ipa->reg_virt + offset);
+}
+
static void ipa_endpoint_init_seq(struct ipa_endpoint *endpoint)
{
u32 offset = IPA_REG_ENDP_INIT_SEQ_N_OFFSET(endpoint->endpoint_id);
val |= u32_encode_bits(status_endpoint_id,
STATUS_ENDP_FMASK);
}
- /* STATUS_LOCATION is 0 (status element precedes packet) */
- /* The next field is present for IPA v4.0 and above */
- /* STATUS_PKT_SUPPRESS_FMASK is 0 */
+ /* STATUS_LOCATION is 0, meaning status element precedes
+ * packet (not present for IPA v4.5)
+ */
+ /* STATUS_PKT_SUPPRESS_FMASK is 0 (not present for v3.5.1) */
}
iowrite32(val, ipa->reg_virt + offset);
struct gsi *gsi = &ipa->gsi;
bool suspended = false;
dma_addr_t addr;
- bool legacy;
u32 retries;
u32 len = 1;
void *virt;
* complete the channel reset sequence. Finish by suspending the
* channel again (if necessary).
*/
- legacy = ipa->version == IPA_VERSION_3_5_1;
- gsi_channel_reset(gsi, endpoint->channel_id, legacy);
+ gsi_channel_reset(gsi, endpoint->channel_id, true);
msleep(1);
u32 channel_id = endpoint->channel_id;
struct ipa *ipa = endpoint->ipa;
bool special;
- bool legacy;
int ret = 0;
/* On IPA v3.5.1, if an RX endpoint is reset while aggregation
* is active, we need to handle things specially to recover.
* All other cases just need to reset the underlying GSI channel.
- *
- * IPA v3.5.1 enables the doorbell engine. Newer versions do not.
*/
- legacy = ipa->version == IPA_VERSION_3_5_1;
- special = !endpoint->toward_ipa && endpoint->data->aggregation;
+ special = ipa->version == IPA_VERSION_3_5_1 &&
+ !endpoint->toward_ipa &&
+ endpoint->data->aggregation;
if (special && ipa_endpoint_aggr_active(endpoint))
ret = ipa_endpoint_reset_rx_aggr(endpoint);
else
- gsi_channel_reset(&ipa->gsi, channel_id, legacy);
+ gsi_channel_reset(&ipa->gsi, channel_id, true);
if (ret)
dev_err(&ipa->pdev->dev,
ipa_endpoint_init_mode(endpoint);
ipa_endpoint_init_aggr(endpoint);
ipa_endpoint_init_deaggr(endpoint);
+ ipa_endpoint_init_rsrc_grp(endpoint);
ipa_endpoint_init_seq(endpoint);
ipa_endpoint_status(endpoint);
}
val = ioread32(ipa->reg_virt + IPA_REG_FLAVOR_0_OFFSET);
/* Our RX is an IPA producer */
- rx_base = u32_get_bits(val, BAM_PROD_LOWEST_FMASK);
- max = rx_base + u32_get_bits(val, BAM_MAX_PROD_PIPES_FMASK);
+ rx_base = u32_get_bits(val, IPA_PROD_LOWEST_FMASK);
+ max = rx_base + u32_get_bits(val, IPA_MAX_PROD_PIPES_FMASK);
if (max > IPA_ENDPOINT_MAX) {
dev_err(dev, "too many endpoints (%u > %u)\n",
max, IPA_ENDPOINT_MAX);
rx_mask = GENMASK(max - 1, rx_base);
/* Our TX is an IPA consumer */
- max = u32_get_bits(val, BAM_MAX_CONS_PIPES_FMASK);
+ max = u32_get_bits(val, IPA_MAX_CONS_PIPES_FMASK);
tx_mask = GENMASK(max - 1, 0);
ipa->available = rx_mask | tx_mask;
#define IPA_MTU ETH_DATA_LEN
enum ipa_endpoint_name {
- IPA_ENDPOINT_AP_MODEM_TX = 0,
+ IPA_ENDPOINT_AP_MODEM_TX,
IPA_ENDPOINT_MODEM_LAN_TX,
IPA_ENDPOINT_MODEM_COMMAND_TX,
IPA_ENDPOINT_AP_COMMAND_TX,
u32 val;
/* assert(mask & ipa->available); */
- val = ioread32(ipa->reg_virt + IPA_REG_SUSPEND_IRQ_EN_OFFSET);
+ val = ioread32(ipa->reg_virt + IPA_REG_IRQ_SUSPEND_EN_OFFSET);
if (enable)
val |= mask;
else
val &= ~mask;
- iowrite32(val, ipa->reg_virt + IPA_REG_SUSPEND_IRQ_EN_OFFSET);
+ iowrite32(val, ipa->reg_virt + IPA_REG_IRQ_SUSPEND_EN_OFFSET);
}
/* Enable TX_SUSPEND for an endpoint */
u32 val;
val = ioread32(ipa->reg_virt + IPA_REG_IRQ_SUSPEND_INFO_OFFSET);
- iowrite32(val, ipa->reg_virt + IPA_REG_SUSPEND_IRQ_CLR_OFFSET);
+ iowrite32(val, ipa->reg_virt + IPA_REG_IRQ_SUSPEND_CLR_OFFSET);
}
/* Simulate arrival of an IPA TX_SUSPEND interrupt */
struct ipa;
struct ipa_interrupt;
-/**
- * enum ipa_irq_id - IPA interrupt type
- * @IPA_IRQ_UC_0: Microcontroller event interrupt
- * @IPA_IRQ_UC_1: Microcontroller response interrupt
- * @IPA_IRQ_TX_SUSPEND: Data ready interrupt
- *
- * The data ready interrupt is signaled if data has arrived that is destined
- * for an AP RX endpoint whose underlying GSI channel is suspended/stopped.
- */
-enum ipa_irq_id {
- IPA_IRQ_UC_0 = 2,
- IPA_IRQ_UC_1 = 3,
- IPA_IRQ_TX_SUSPEND = 14,
- IPA_IRQ_COUNT, /* Number of interrupt types (not an index) */
-};
-
/**
* typedef ipa_irq_handler_t - IPA interrupt handler function type
* @ipa: IPA pointer
#define IPA_FWS_PATH "ipa_fws.mdt"
#define IPA_PAS_ID 15
+/* Shift of 19.2 MHz timestamp to achieve lower resolution timestamps */
+#define DPL_TIMESTAMP_SHIFT 14 /* ~1.172 kHz, ~853 usec per tick */
+#define TAG_TIMESTAMP_SHIFT 14
+#define NAT_TIMESTAMP_SHIFT 24 /* ~1.144 Hz, ~874 msec per tick */
+
+/* Divider for 19.2 MHz crystal oscillator clock to get common timer clock */
+#define IPA_XO_CLOCK_DIVIDER 192 /* 1 is subtracted where used */
+
/**
* ipa_suspend_handler() - Handle the suspend IPA interrupt
* @ipa: IPA pointer
struct device *dev = &ipa->pdev->dev;
int ret;
- /* Setup for IPA v3.5.1 has some slight differences */
- ret = gsi_setup(&ipa->gsi, ipa->version == IPA_VERSION_3_5_1);
+ ret = gsi_setup(&ipa->gsi);
if (ret)
return ret;
val &= ~IPA_QMB_SELECT_CONS_EN_FMASK;
val &= ~IPA_QMB_SELECT_PROD_EN_FMASK;
val &= ~IPA_QMB_SELECT_GLOBAL_EN_FMASK;
- } else {
+ } else if (ipa->version < IPA_VERSION_4_5) {
val |= GSI_MULTI_AXI_MASTERS_DIS_FMASK;
+ } else {
+ /* For IPA v4.5 IPA_FULL_FLUSH_WAIT_RSC_CLOSE_EN is 0 */
}
val |= GSI_MULTI_INORDER_RD_DIS_FMASK;
/* Configure DDR and PCIe max read/write QSB values */
static void ipa_hardware_config_qsb(struct ipa *ipa)
{
+ enum ipa_version version = ipa->version;
+ u32 max0;
+ u32 max1;
u32 val;
- /* QMB_0 represents DDR; QMB_1 represents PCIe (not present in 4.2) */
+ /* QMB_0 represents DDR; QMB_1 represents PCIe */
val = u32_encode_bits(8, GEN_QMB_0_MAX_WRITES_FMASK);
- if (ipa->version == IPA_VERSION_4_2)
- val |= u32_encode_bits(0, GEN_QMB_1_MAX_WRITES_FMASK);
- else
- val |= u32_encode_bits(4, GEN_QMB_1_MAX_WRITES_FMASK);
+ switch (version) {
+ case IPA_VERSION_4_2:
+ max1 = 0; /* PCIe not present */
+ break;
+ case IPA_VERSION_4_5:
+ max1 = 8;
+ break;
+ default:
+ max1 = 4;
+ break;
+ }
+ val |= u32_encode_bits(max1, GEN_QMB_1_MAX_WRITES_FMASK);
iowrite32(val, ipa->reg_virt + IPA_REG_QSB_MAX_WRITES_OFFSET);
- if (ipa->version == IPA_VERSION_3_5_1) {
- val = u32_encode_bits(8, GEN_QMB_0_MAX_READS_FMASK);
- val |= u32_encode_bits(12, GEN_QMB_1_MAX_READS_FMASK);
- } else {
- val = u32_encode_bits(12, GEN_QMB_0_MAX_READS_FMASK);
- if (ipa->version == IPA_VERSION_4_2)
- val |= u32_encode_bits(0, GEN_QMB_1_MAX_READS_FMASK);
- else
- val |= u32_encode_bits(12, GEN_QMB_1_MAX_READS_FMASK);
+ max1 = 12;
+ switch (version) {
+ case IPA_VERSION_3_5_1:
+ max0 = 8;
+ break;
+ case IPA_VERSION_4_0:
+ case IPA_VERSION_4_1:
+ max0 = 12;
+ break;
+ case IPA_VERSION_4_2:
+ max0 = 12;
+ max1 = 0; /* PCIe not present */
+ break;
+ case IPA_VERSION_4_5:
+ max0 = 0; /* No limit (hardware maximum) */
+ break;
+ }
+ val = u32_encode_bits(max0, GEN_QMB_0_MAX_READS_FMASK);
+ val |= u32_encode_bits(max1, GEN_QMB_1_MAX_READS_FMASK);
+ if (version != IPA_VERSION_3_5_1) {
/* GEN_QMB_0_MAX_READS_BEATS is 0 */
/* GEN_QMB_1_MAX_READS_BEATS is 0 */
}
iowrite32(val, ipa->reg_virt + IPA_REG_QSB_MAX_READS_OFFSET);
}
+/* IPA uses unified Qtime starting at IPA v4.5, implementing various
+ * timestamps and timers independent of the IPA core clock rate. The
+ * Qtimer is based on a 56-bit timestamp incremented at each tick of
+ * a 19.2 MHz SoC crystal oscillator (XO clock).
+ *
+ * For IPA timestamps (tag, NAT, data path logging) a lower resolution
+ * timestamp is achieved by shifting the Qtimer timestamp value right
+ * some number of bits to produce the low-order bits of the coarser
+ * granularity timestamp.
+ *
+ * For timers, a common timer clock is derived from the XO clock using
+ * a divider (we use 192, to produce a 100kHz timer clock). From
+ * this common clock, three "pulse generators" are used to produce
+ * timer ticks at a configurable frequency. IPA timers (such as
+ * those used for aggregation or head-of-line block handling) now
+ * define their period based on one of these pulse generators.
+ */
+static void ipa_qtime_config(struct ipa *ipa)
+{
+ u32 val;
+
+ /* Timer clock divider must be disabled when we change the rate */
+ iowrite32(0, ipa->reg_virt + IPA_REG_TIMERS_XO_CLK_DIV_CFG_OFFSET);
+
+ /* Set DPL time stamp resolution to use Qtime (instead of 1 msec) */
+ val = u32_encode_bits(DPL_TIMESTAMP_SHIFT, DPL_TIMESTAMP_LSB_FMASK);
+ val |= u32_encode_bits(1, DPL_TIMESTAMP_SEL_FMASK);
+ /* Configure tag and NAT Qtime timestamp resolution as well */
+ val |= u32_encode_bits(TAG_TIMESTAMP_SHIFT, TAG_TIMESTAMP_LSB_FMASK);
+ val |= u32_encode_bits(NAT_TIMESTAMP_SHIFT, NAT_TIMESTAMP_LSB_FMASK);
+ iowrite32(val, ipa->reg_virt + IPA_REG_QTIME_TIMESTAMP_CFG_OFFSET);
+
+ /* Set granularity of pulse generators used for other timers */
+ val = u32_encode_bits(IPA_GRAN_100_US, GRAN_0_FMASK);
+ val |= u32_encode_bits(IPA_GRAN_1_MS, GRAN_1_FMASK);
+ val |= u32_encode_bits(IPA_GRAN_1_MS, GRAN_2_FMASK);
+ iowrite32(val, ipa->reg_virt + IPA_REG_TIMERS_PULSE_GRAN_CFG_OFFSET);
+
+ /* Actual divider is 1 more than value supplied here */
+ val = u32_encode_bits(IPA_XO_CLOCK_DIVIDER - 1, DIV_VALUE_FMASK);
+ iowrite32(val, ipa->reg_virt + IPA_REG_TIMERS_XO_CLK_DIV_CFG_OFFSET);
+
+ /* Divider value is set; re-enable the common timer clock divider */
+ val |= u32_encode_bits(1, DIV_ENABLE_FMASK);
+ iowrite32(val, ipa->reg_virt + IPA_REG_TIMERS_XO_CLK_DIV_CFG_OFFSET);
+}
+
static void ipa_idle_indication_cfg(struct ipa *ipa,
u32 enter_idle_debounce_thresh,
bool const_non_idle_enable)
*/
static void ipa_hardware_dcd_config(struct ipa *ipa)
{
- /* Recommended values for IPA 3.5 according to IPA HPG */
+ /* Recommended values for IPA 3.5 and later according to IPA HPG */
ipa_idle_indication_cfg(ipa, 256, false);
}
*/
static void ipa_hardware_config(struct ipa *ipa)
{
+ enum ipa_version version = ipa->version;
u32 granularity;
u32 val;
- /* Fill in backward-compatibility register, based on version */
- val = ipa_reg_bcr_val(ipa->version);
- iowrite32(val, ipa->reg_virt + IPA_REG_BCR_OFFSET);
+ /* IPA v4.5 has no backward compatibility register */
+ if (version < IPA_VERSION_4_5) {
+ val = ipa_reg_bcr_val(version);
+ iowrite32(val, ipa->reg_virt + IPA_REG_BCR_OFFSET);
+ }
- if (ipa->version != IPA_VERSION_3_5_1) {
- /* Enable open global clocks (hardware workaround) */
+ /* Implement some hardware workarounds */
+ if (version != IPA_VERSION_3_5_1 && version < IPA_VERSION_4_5) {
+ /* Enable open global clocks (not needed for IPA v4.5) */
val = GLOBAL_FMASK;
val |= GLOBAL_2X_CLK_FMASK;
iowrite32(val, ipa->reg_virt + IPA_REG_CLKON_CFG_OFFSET);
- /* Disable PA mask to allow HOLB drop (hardware workaround) */
+ /* Disable PA mask to allow HOLB drop */
val = ioread32(ipa->reg_virt + IPA_REG_TX_CFG_OFFSET);
- val &= ~PA_MASK_EN;
+ val &= ~PA_MASK_EN_FMASK;
iowrite32(val, ipa->reg_virt + IPA_REG_TX_CFG_OFFSET);
}
/* Configure system bus limits */
ipa_hardware_config_qsb(ipa);
- /* Configure aggregation granularity */
- val = ioread32(ipa->reg_virt + IPA_REG_COUNTER_CFG_OFFSET);
- granularity = ipa_aggr_granularity_val(IPA_AGGR_GRANULARITY);
- val = u32_encode_bits(granularity, AGGR_GRANULARITY);
- iowrite32(val, ipa->reg_virt + IPA_REG_COUNTER_CFG_OFFSET);
+ if (version < IPA_VERSION_4_5) {
+ /* Configure aggregation timer granularity */
+ granularity = ipa_aggr_granularity_val(IPA_AGGR_GRANULARITY);
+ val = u32_encode_bits(granularity, AGGR_GRANULARITY_FMASK);
+ iowrite32(val, ipa->reg_virt + IPA_REG_COUNTER_CFG_OFFSET);
+ } else {
+ ipa_qtime_config(ipa);
+ }
- /* Disable hashed IPv4 and IPv6 routing and filtering for IPA v4.2 */
- if (ipa->version == IPA_VERSION_4_2)
- iowrite32(0, ipa->reg_virt + IPA_REG_FILT_ROUT_HASH_EN_OFFSET);
+ /* IPA v4.2 does not support hashed tables, so disable them */
+ if (version == IPA_VERSION_4_2) {
+ u32 offset = ipa_reg_filt_rout_hash_en_offset(version);
+
+ iowrite32(0, ipa->reg_virt + offset);
+ }
/* Enable dynamic clock division */
ipa_hardware_dcd_config(ipa);
#ifdef IPA_VALIDATION
-/* # IPA resources used based on version (see IPA_RESOURCE_GROUP_COUNT) */
-static int ipa_resource_group_count(struct ipa *ipa)
-{
- switch (ipa->version) {
- case IPA_VERSION_3_5_1:
- return 3;
-
- case IPA_VERSION_4_0:
- case IPA_VERSION_4_1:
- return 4;
-
- case IPA_VERSION_4_2:
- return 1;
-
- default:
- return 0;
- }
-}
-
static bool ipa_resource_limits_valid(struct ipa *ipa,
const struct ipa_resource_data *data)
{
- u32 group_count = ipa_resource_group_count(ipa);
+ u32 group_count;
u32 i;
u32 j;
- if (!group_count)
+ /* We program at most 6 source or destination resource group limits */
+ BUILD_BUG_ON(IPA_RESOURCE_GROUP_SRC_MAX > 6);
+
+ group_count = ipa_resource_group_src_count(ipa->version);
+ if (!group_count || group_count > IPA_RESOURCE_GROUP_SRC_MAX)
return false;
- /* Return an error if a non-zero resource group limit is specified
- * for a resource not supported by hardware.
+ /* Return an error if a non-zero resource limit is specified
+ * for a resource group not supported by hardware.
*/
for (i = 0; i < data->resource_src_count; i++) {
const struct ipa_resource_src *resource;
resource = &data->resource_src[i];
- for (j = group_count; j < IPA_RESOURCE_GROUP_COUNT; j++)
+ for (j = group_count; j < IPA_RESOURCE_GROUP_SRC_MAX; j++)
if (resource->limits[j].min || resource->limits[j].max)
return false;
}
+ group_count = ipa_resource_group_dst_count(ipa->version);
+ if (!group_count || group_count > IPA_RESOURCE_GROUP_DST_MAX)
+ return false;
+
for (i = 0; i < data->resource_dst_count; i++) {
const struct ipa_resource_dst *resource;
resource = &data->resource_dst[i];
- for (j = group_count; j < IPA_RESOURCE_GROUP_COUNT; j++)
+ for (j = group_count; j < IPA_RESOURCE_GROUP_DST_MAX; j++)
if (resource->limits[j].min || resource->limits[j].max)
return false;
}
val = u32_encode_bits(xlimits->min, X_MIN_LIM_FMASK);
val |= u32_encode_bits(xlimits->max, X_MAX_LIM_FMASK);
- val |= u32_encode_bits(ylimits->min, Y_MIN_LIM_FMASK);
- val |= u32_encode_bits(ylimits->max, Y_MAX_LIM_FMASK);
+ if (ylimits) {
+ val |= u32_encode_bits(ylimits->min, Y_MIN_LIM_FMASK);
+ val |= u32_encode_bits(ylimits->max, Y_MAX_LIM_FMASK);
+ }
iowrite32(val, ipa->reg_virt + offset);
}
-static void ipa_resource_config_src_01(struct ipa *ipa,
- const struct ipa_resource_src *resource)
+static void ipa_resource_config_src(struct ipa *ipa,
+ const struct ipa_resource_src *resource)
{
- u32 offset = IPA_REG_SRC_RSRC_GRP_01_RSRC_TYPE_N_OFFSET(resource->type);
+ u32 group_count = ipa_resource_group_src_count(ipa->version);
+ const struct ipa_resource_limits *ylimits;
+ u32 offset;
- ipa_resource_config_common(ipa, offset,
- &resource->limits[0], &resource->limits[1]);
-}
+ offset = IPA_REG_SRC_RSRC_GRP_01_RSRC_TYPE_N_OFFSET(resource->type);
+ ylimits = group_count == 1 ? NULL : &resource->limits[1];
+ ipa_resource_config_common(ipa, offset, &resource->limits[0], ylimits);
-static void ipa_resource_config_src_23(struct ipa *ipa,
- const struct ipa_resource_src *resource)
-{
- u32 offset = IPA_REG_SRC_RSRC_GRP_23_RSRC_TYPE_N_OFFSET(resource->type);
+ if (group_count < 2)
+ return;
- ipa_resource_config_common(ipa, offset,
- &resource->limits[2], &resource->limits[3]);
-}
+ offset = IPA_REG_SRC_RSRC_GRP_23_RSRC_TYPE_N_OFFSET(resource->type);
+ ylimits = group_count == 3 ? NULL : &resource->limits[3];
+ ipa_resource_config_common(ipa, offset, &resource->limits[2], ylimits);
-static void ipa_resource_config_dst_01(struct ipa *ipa,
- const struct ipa_resource_dst *resource)
-{
- u32 offset = IPA_REG_DST_RSRC_GRP_01_RSRC_TYPE_N_OFFSET(resource->type);
+ if (group_count < 4)
+ return;
- ipa_resource_config_common(ipa, offset,
- &resource->limits[0], &resource->limits[1]);
+ offset = IPA_REG_SRC_RSRC_GRP_45_RSRC_TYPE_N_OFFSET(resource->type);
+ ylimits = group_count == 5 ? NULL : &resource->limits[5];
+ ipa_resource_config_common(ipa, offset, &resource->limits[4], ylimits);
}
-static void ipa_resource_config_dst_23(struct ipa *ipa,
- const struct ipa_resource_dst *resource)
+static void ipa_resource_config_dst(struct ipa *ipa,
+ const struct ipa_resource_dst *resource)
{
- u32 offset = IPA_REG_DST_RSRC_GRP_23_RSRC_TYPE_N_OFFSET(resource->type);
+ u32 group_count = ipa_resource_group_dst_count(ipa->version);
+ const struct ipa_resource_limits *ylimits;
+ u32 offset;
+
+ offset = IPA_REG_DST_RSRC_GRP_01_RSRC_TYPE_N_OFFSET(resource->type);
+ ylimits = group_count == 1 ? NULL : &resource->limits[1];
+ ipa_resource_config_common(ipa, offset, &resource->limits[0], ylimits);
- ipa_resource_config_common(ipa, offset,
- &resource->limits[2], &resource->limits[3]);
+ if (group_count < 2)
+ return;
+
+ offset = IPA_REG_DST_RSRC_GRP_23_RSRC_TYPE_N_OFFSET(resource->type);
+ ylimits = group_count == 3 ? NULL : &resource->limits[3];
+ ipa_resource_config_common(ipa, offset, &resource->limits[2], ylimits);
+
+ if (group_count < 4)
+ return;
+
+ offset = IPA_REG_DST_RSRC_GRP_45_RSRC_TYPE_N_OFFSET(resource->type);
+ ylimits = group_count == 5 ? NULL : &resource->limits[5];
+ ipa_resource_config_common(ipa, offset, &resource->limits[4], ylimits);
}
static int
if (!ipa_resource_limits_valid(ipa, data))
return -EINVAL;
- for (i = 0; i < data->resource_src_count; i++) {
- ipa_resource_config_src_01(ipa, &data->resource_src[i]);
- ipa_resource_config_src_23(ipa, &data->resource_src[i]);
- }
+ for (i = 0; i < data->resource_src_count; i++)
+ ipa_resource_config_src(ipa, data->resource_src);
- for (i = 0; i < data->resource_dst_count; i++) {
- ipa_resource_config_dst_01(ipa, &data->resource_dst[i]);
- ipa_resource_config_dst_23(ipa, &data->resource_dst[i]);
- }
+ for (i = 0; i < data->resource_dst_count; i++)
+ ipa_resource_config_dst(ipa, data->resource_dst);
return 0;
}
*/
BUILD_BUG_ON(GSI_TLV_MAX > U8_MAX);
- /* Exceeding 128 bytes makes the transaction pool *much* larger */
- BUILD_BUG_ON(sizeof(struct gsi_trans) > 128);
-
/* This is used as a divisor */
BUILD_BUG_ON(!IPA_AGGR_GRANULARITY);
/* Aggregation granularity value can't be 0, and must fit */
BUILD_BUG_ON(!ipa_aggr_granularity_val(IPA_AGGR_GRANULARITY));
BUILD_BUG_ON(ipa_aggr_granularity_val(IPA_AGGR_GRANULARITY) >
- field_max(AGGR_GRANULARITY));
+ field_max(AGGR_GRANULARITY_FMASK));
#endif /* IPA_VALIDATE */
}
const struct ipa_data *data;
struct ipa_clock *clock;
struct rproc *rproc;
- bool modem_alloc;
bool modem_init;
struct ipa *ipa;
- bool prefetch;
phandle ph;
int ret;
ipa_validate_build();
+ /* Get configuration data early; needed for clock initialization */
+ data = of_device_get_match_data(dev);
+ if (!data) {
+ /* This is really IPA_VALIDATE (should never happen) */
+ dev_err(dev, "matched hardware not supported\n");
+ return -ENODEV;
+ }
+
/* If we need Trust Zone, make sure it's available */
modem_init = of_property_read_bool(dev->of_node, "modem-init");
if (!modem_init)
/* The clock and interconnects might not be ready when we're
* probed, so might return -EPROBE_DEFER.
*/
- clock = ipa_clock_init(dev);
+ clock = ipa_clock_init(dev, data->clock_data);
if (IS_ERR(clock)) {
ret = PTR_ERR(clock);
goto err_rproc_put;
}
- /* No more EPROBE_DEFER. Get our configuration data */
- data = of_device_get_match_data(dev);
- if (!data) {
- /* This is really IPA_VALIDATE (should never happen) */
- dev_err(dev, "matched hardware not supported\n");
- ret = -ENOTSUPP;
- goto err_clock_exit;
- }
-
- /* Allocate and initialize the IPA structure */
+ /* No more EPROBE_DEFER. Allocate and initialize the IPA structure */
ipa = kzalloc(sizeof(*ipa), GFP_KERNEL);
if (!ipa) {
ret = -ENOMEM;
if (ret)
goto err_reg_exit;
- /* GSI v2.0+ (IPA v4.0+) uses prefetch for the command channel */
- prefetch = ipa->version != IPA_VERSION_3_5_1;
- /* IPA v4.2 requires the AP to allocate channels for the modem */
- modem_alloc = ipa->version == IPA_VERSION_4_2;
-
- ret = gsi_init(&ipa->gsi, pdev, prefetch, data->endpoint_count,
- data->endpoint_data, modem_alloc);
+ ret = gsi_init(&ipa->gsi, pdev, ipa->version, data->endpoint_count,
+ data->endpoint_data);
if (ret)
goto err_mem_exit;
- /* Result is a non-zero mask endpoints that support filtering */
+ /* Result is a non-zero mask of endpoints that support filtering */
ipa->filter_map = ipa_endpoint_init(ipa, data->endpoint_count,
data->endpoint_data);
if (!ipa->filter_map) {
if (ipa->setup_complete) {
ret = ipa_modem_stop(ipa);
+ /* If starting or stopping is in progress, try once more */
+ if (ret == -EBUSY) {
+ usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC);
+ ret = ipa_modem_stop(ipa);
+ }
if (ret)
return ret;
return 0;
}
+static void ipa_shutdown(struct platform_device *pdev)
+{
+ int ret;
+
+ ret = ipa_remove(pdev);
+ if (ret)
+ dev_err(&pdev->dev, "shutdown: remove returned %d\n", ret);
+}
+
/**
* ipa_suspend() - Power management system suspend callback
* @dev: IPA device structure
};
static struct platform_driver ipa_driver = {
- .probe = ipa_probe,
- .remove = ipa_remove,
+ .probe = ipa_probe,
+ .remove = ipa_remove,
+ .shutdown = ipa_shutdown,
.driver = {
.name = "ipa",
.pm = &ipa_pm_ops,
gsi_trans_commit_wait(trans);
/* Tell the hardware where the processing context area is located */
- iowrite32(ipa->mem_offset + offset,
+ iowrite32(ipa->mem_offset + ipa->mem[IPA_MEM_MODEM_PROC_CTX].offset,
ipa->reg_virt + IPA_REG_LOCAL_PKT_PROC_CNTXT_BASE_OFFSET);
return 0;
mem_size = 8 * u32_get_bits(val, SHARED_MEM_SIZE_FMASK);
/* If the sizes don't match, issue a warning */
- if (ipa->mem_offset + mem_size > ipa->mem_size) {
- dev_warn(dev, "ignoring larger reported memory size: 0x%08x\n",
- mem_size);
- } else if (ipa->mem_offset + mem_size < ipa->mem_size) {
+ if (ipa->mem_offset + mem_size < ipa->mem_size) {
dev_warn(dev, "limiting IPA memory size to 0x%08x\n",
mem_size);
ipa->mem_size = mem_size;
+ } else if (ipa->mem_offset + mem_size > ipa->mem_size) {
+ dev_dbg(dev, "ignoring larger reported memory size: 0x%08x\n",
+ mem_size);
}
/* Prealloc DMA memory for zeroing regions */
ipa_qmi->indication_sent = false;
}
-static struct qmi_ops ipa_server_ops = {
+static const struct qmi_ops ipa_server_ops = {
.bye = ipa_server_bye,
};
}
/* The server handles two request message types sent by the modem. */
-static struct qmi_msg_handler ipa_server_msg_handlers[] = {
+static const struct qmi_msg_handler ipa_server_msg_handlers[] = {
{
.type = QMI_REQUEST,
.msg_id = IPA_QMI_INDICATION_REGISTER,
}
/* The client handles one response message type sent by the modem. */
-static struct qmi_msg_handler ipa_client_msg_handlers[] = {
+static const struct qmi_msg_handler ipa_client_msg_handlers[] = {
{
.type = QMI_RESPONSE,
.msg_id = IPA_QMI_INIT_DRIVER,
return 0;
}
-static struct qmi_ops ipa_client_ops = {
+static const struct qmi_ops ipa_client_ops = {
.new_server = ipa_client_new_server,
};
/* The AP tells the modem its platform type. We assume Android. */
enum ipa_platform_type {
- IPA_QMI_PLATFORM_TYPE_INVALID = 0, /* Invalid */
- IPA_QMI_PLATFORM_TYPE_TN = 1, /* Data card */
- IPA_QMI_PLATFORM_TYPE_LE = 2, /* Data router */
- IPA_QMI_PLATFORM_TYPE_MSM_ANDROID = 3, /* Android MSM */
- IPA_QMI_PLATFORM_TYPE_MSM_WINDOWS = 4, /* Windows MSM */
- IPA_QMI_PLATFORM_TYPE_MSM_QNX_V01 = 5, /* QNX MSM */
+ IPA_QMI_PLATFORM_TYPE_INVALID = 0x0, /* Invalid */
+ IPA_QMI_PLATFORM_TYPE_TN = 0x1, /* Data card */
+ IPA_QMI_PLATFORM_TYPE_LE = 0x2, /* Data router */
+ IPA_QMI_PLATFORM_TYPE_MSM_ANDROID = 0x3, /* Android MSM */
+ IPA_QMI_PLATFORM_TYPE_MSM_WINDOWS = 0x4, /* Windows MSM */
+ IPA_QMI_PLATFORM_TYPE_MSM_QNX_V01 = 0x5, /* QNX MSM */
};
/* This defines the start and end offset of a range of memory. Both
* of valid bits for the register.
*/
-#define IPA_REG_ENABLED_PIPES_OFFSET 0x00000038
-
#define IPA_REG_COMP_CFG_OFFSET 0x0000003c
+/* The next field is not supported for IPA v4.1 */
#define ENABLE_FMASK GENMASK(0, 0)
#define GSI_SNOC_BYPASS_DIS_FMASK GENMASK(1, 1)
#define GEN_QMB_0_SNOC_BYPASS_DIS_FMASK GENMASK(2, 2)
#define GEN_QMB_1_SNOC_BYPASS_DIS_FMASK GENMASK(3, 3)
+/* The next field is not present for IPA v4.5 */
#define IPA_DCMP_FAST_CLK_EN_FMASK GENMASK(4, 4)
+/* The remaining fields are not present for IPA v3.5.1 */
#define IPA_QMB_SELECT_CONS_EN_FMASK GENMASK(5, 5)
#define IPA_QMB_SELECT_PROD_EN_FMASK GENMASK(6, 6)
#define GSI_MULTI_INORDER_RD_DIS_FMASK GENMASK(7, 7)
#define GSI_MULTI_AXI_MASTERS_DIS_FMASK GENMASK(15, 15)
#define IPA_QMB_SELECT_GLOBAL_EN_FMASK GENMASK(16, 16)
#define IPA_ATOMIC_FETCHER_ARB_LOCK_DIS_FMASK GENMASK(20, 17)
+/* The next field is present for IPA v4.5 */
+#define IPA_FULL_FLUSH_WAIT_RSC_CLOSE_EN_FMASK GENMASK(21, 21)
#define IPA_REG_CLKON_CFG_OFFSET 0x00000044
#define RX_FMASK GENMASK(0, 0)
#define ACK_MNGR_FMASK GENMASK(14, 14)
#define D_DCPH_FMASK GENMASK(15, 15)
#define H_DCPH_FMASK GENMASK(16, 16)
+/* The next field is not present for IPA v4.5 */
#define DCMP_FMASK GENMASK(17, 17)
#define NTF_TX_CMDQS_FMASK GENMASK(18, 18)
#define TX_0_FMASK GENMASK(19, 19)
#define TX_1_FMASK GENMASK(20, 20)
#define FNR_FMASK GENMASK(21, 21)
+/* The remaining fields are not present for IPA v3.5.1 */
#define QSB2AXI_CMDQ_L_FMASK GENMASK(22, 22)
#define AGGR_WRAPPER_FMASK GENMASK(23, 23)
#define RAM_SLAVEWAY_FMASK GENMASK(24, 24)
#define GSI_IF_FMASK GENMASK(27, 27)
#define GLOBAL_FMASK GENMASK(28, 28)
#define GLOBAL_2X_CLK_FMASK GENMASK(29, 29)
+/* The next field is present for IPA v4.5 */
+#define DPL_FIFO_FMASK GENMASK(30, 30)
#define IPA_REG_ROUTE_OFFSET 0x00000048
#define ROUTE_DIS_FMASK GENMASK(0, 0)
#define IPA_REG_QSB_MAX_READS_OFFSET 0x00000078
#define GEN_QMB_0_MAX_READS_FMASK GENMASK(3, 0)
#define GEN_QMB_1_MAX_READS_FMASK GENMASK(7, 4)
-/* The next two fields are present for IPA v4.0 and above */
+/* The next two fields are not present for IPA v3.5.1 */
#define GEN_QMB_0_MAX_READS_BEATS_FMASK GENMASK(23, 16)
#define GEN_QMB_1_MAX_READS_BEATS_FMASK GENMASK(31, 24)
-static inline u32 ipa_reg_state_aggr_active_offset(enum ipa_version version)
+static inline u32 ipa_reg_filt_rout_hash_en_offset(enum ipa_version version)
{
if (version == IPA_VERSION_3_5_1)
- return 0x0000010c;
+ return 0x000008c;
- return 0x000000b4;
+ return 0x0000148;
}
-/* ipa->available defines the valid bits in the STATE_AGGR_ACTIVE register */
-
-/* The next register is present for IPA v4.2 and above */
-#define IPA_REG_FILT_ROUT_HASH_EN_OFFSET 0x00000148
-#define IPV6_ROUTER_HASH_EN GENMASK(0, 0)
-#define IPV6_FILTER_HASH_EN GENMASK(4, 4)
-#define IPV4_ROUTER_HASH_EN GENMASK(8, 8)
-#define IPV4_FILTER_HASH_EN GENMASK(12, 12)
static inline u32 ipa_reg_filt_rout_hash_flush_offset(enum ipa_version version)
{
return 0x000014c;
}
-#define IPV6_ROUTER_HASH_FLUSH GENMASK(0, 0)
-#define IPV6_FILTER_HASH_FLUSH GENMASK(4, 4)
-#define IPV4_ROUTER_HASH_FLUSH GENMASK(8, 8)
-#define IPV4_FILTER_HASH_FLUSH GENMASK(12, 12)
+/* The next four fields are used for the hash enable and flush registers */
+#define IPV6_ROUTER_HASH_FMASK GENMASK(0, 0)
+#define IPV6_FILTER_HASH_FMASK GENMASK(4, 4)
+#define IPV4_ROUTER_HASH_FMASK GENMASK(8, 8)
+#define IPV4_FILTER_HASH_FMASK GENMASK(12, 12)
+
+/* ipa->available defines the valid bits in the STATE_AGGR_ACTIVE register */
+static inline u32 ipa_reg_state_aggr_active_offset(enum ipa_version version)
+{
+ if (version == IPA_VERSION_3_5_1)
+ return 0x0000010c;
+
+ return 0x000000b4;
+}
+/* The next register is not present for IPA v4.5 */
#define IPA_REG_BCR_OFFSET 0x000001d0
-#define BCR_CMDQ_L_LACK_ONE_ENTRY BIT(0)
-#define BCR_TX_NOT_USING_BRESP BIT(1)
-#define BCR_SUSPEND_L2_IRQ BIT(3)
-#define BCR_HOLB_DROP_L2_IRQ BIT(4)
-#define BCR_DUAL_TX BIT(5)
+/* The next two fields are not present for IPA v4.2 */
+#define BCR_CMDQ_L_LACK_ONE_ENTRY_FMASK GENMASK(0, 0)
+#define BCR_TX_NOT_USING_BRESP_FMASK GENMASK(1, 1)
+/* The next field is invalid for IPA v4.1 */
+#define BCR_TX_SUSPEND_IRQ_ASSERT_ONCE_FMASK GENMASK(2, 2)
+/* The next two fields are not present for IPA v4.2 */
+#define BCR_SUSPEND_L2_IRQ_FMASK GENMASK(3, 3)
+#define BCR_HOLB_DROP_L2_IRQ_FMASK GENMASK(4, 4)
+#define BCR_DUAL_TX_FMASK GENMASK(5, 5)
+#define BCR_ENABLE_FILTER_DATA_CACHE_FMASK GENMASK(6, 6)
+#define BCR_NOTIF_PRIORITY_OVER_ZLT_FMASK GENMASK(7, 7)
+#define BCR_FILTER_PREFETCH_EN_FMASK GENMASK(8, 8)
+#define BCR_ROUTER_PREFETCH_EN_FMASK GENMASK(9, 9)
/* Backward compatibility register value to use for each version */
static inline u32 ipa_reg_bcr_val(enum ipa_version version)
{
if (version == IPA_VERSION_3_5_1)
- return BCR_CMDQ_L_LACK_ONE_ENTRY | BCR_TX_NOT_USING_BRESP |
- BCR_SUSPEND_L2_IRQ | BCR_HOLB_DROP_L2_IRQ | BCR_DUAL_TX;
+ return BCR_CMDQ_L_LACK_ONE_ENTRY_FMASK |
+ BCR_TX_NOT_USING_BRESP_FMASK |
+ BCR_SUSPEND_L2_IRQ_FMASK |
+ BCR_HOLB_DROP_L2_IRQ_FMASK |
+ BCR_DUAL_TX_FMASK;
if (version == IPA_VERSION_4_0 || version == IPA_VERSION_4_1)
- return BCR_CMDQ_L_LACK_ONE_ENTRY | BCR_SUSPEND_L2_IRQ |
- BCR_HOLB_DROP_L2_IRQ | BCR_DUAL_TX;
+ return BCR_CMDQ_L_LACK_ONE_ENTRY_FMASK |
+ BCR_SUSPEND_L2_IRQ_FMASK |
+ BCR_HOLB_DROP_L2_IRQ_FMASK |
+ BCR_DUAL_TX_FMASK;
+
+ /* assert(version != IPA_VERSION_4_5); */
return 0x00000000;
}
+/* The value of the next register must be a multiple of 8 */
#define IPA_REG_LOCAL_PKT_PROC_CNTXT_BASE_OFFSET 0x000001e8
-#define IPA_REG_AGGR_FORCE_CLOSE_OFFSET 0x000001ec
/* ipa->available defines the valid bits in the AGGR_FORCE_CLOSE register */
+#define IPA_REG_AGGR_FORCE_CLOSE_OFFSET 0x000001ec
+
+/* The next register is not present for IPA v4.5 */
+#define IPA_REG_COUNTER_CFG_OFFSET 0x000001f0
+#define AGGR_GRANULARITY_FMASK GENMASK(8, 4)
/* The internal inactivity timer clock is used for the aggregation timer */
-#define TIMER_FREQUENCY 32000 /* 32 KHz inactivity timer clock */
+#define TIMER_FREQUENCY 32000 /* 32 KHz inactivity timer clock */
-#define IPA_REG_COUNTER_CFG_OFFSET 0x000001f0
-#define AGGR_GRANULARITY GENMASK(8, 4)
/* Compute the value to use in the AGGR_GRANULARITY field representing the
* given number of microseconds. The value is one less than the number of
- * timer ticks in the requested period. Zero not a valid granularity value.
+ * timer ticks in the requested period. 0 not a valid granularity value.
*/
static inline u32 ipa_aggr_granularity_val(u32 usec)
{
return DIV_ROUND_CLOSEST(usec * TIMER_FREQUENCY, USEC_PER_SEC) - 1;
}
+/* The next register is not present for IPA v4.5 */
#define IPA_REG_TX_CFG_OFFSET 0x000001fc
/* The first three fields are present for IPA v3.5.1 only */
-#define TX0_PREFETCH_DISABLE GENMASK(0, 0)
-#define TX1_PREFETCH_DISABLE GENMASK(1, 1)
-#define PREFETCH_ALMOST_EMPTY_SIZE GENMASK(4, 2)
-/* The next fields are present for IPA v4.0 and above */
-#define PREFETCH_ALMOST_EMPTY_SIZE_TX0 GENMASK(5, 2)
-#define DMAW_SCND_OUTSD_PRED_THRESHOLD GENMASK(9, 6)
-#define DMAW_SCND_OUTSD_PRED_EN GENMASK(10, 10)
-#define DMAW_MAX_BEATS_256_DIS GENMASK(11, 11)
-#define PA_MASK_EN GENMASK(12, 12)
-#define PREFETCH_ALMOST_EMPTY_SIZE_TX1 GENMASK(16, 13)
-/* The last two fields are present for IPA v4.2 and above */
-#define SSPND_PA_NO_START_STATE GENMASK(18, 18)
-#define SSPND_PA_NO_BQ_STATE GENMASK(19, 19)
+#define TX0_PREFETCH_DISABLE_FMASK GENMASK(0, 0)
+#define TX1_PREFETCH_DISABLE_FMASK GENMASK(1, 1)
+#define PREFETCH_ALMOST_EMPTY_SIZE_FMASK GENMASK(4, 2)
+/* The next six fields are present for IPA v4.0 and above */
+#define PREFETCH_ALMOST_EMPTY_SIZE_TX0_FMASK GENMASK(5, 2)
+#define DMAW_SCND_OUTSD_PRED_THRESHOLD_FMASK GENMASK(9, 6)
+#define DMAW_SCND_OUTSD_PRED_EN_FMASK GENMASK(10, 10)
+#define DMAW_MAX_BEATS_256_DIS_FMASK GENMASK(11, 11)
+#define PA_MASK_EN_FMASK GENMASK(12, 12)
+#define PREFETCH_ALMOST_EMPTY_SIZE_TX1_FMASK GENMASK(16, 13)
+/* The next field is present for IPA v4.5 */
+#define DUAL_TX_ENABLE_FMASK GENMASK(17, 17)
+/* The next two fields are present for IPA v4.2 only */
+#define SSPND_PA_NO_START_STATE_FMASK GENMASK(18, 18)
+#define SSPND_PA_NO_BQ_STATE_FMASK GENMASK(19, 19)
#define IPA_REG_FLAVOR_0_OFFSET 0x00000210
-#define BAM_MAX_PIPES_FMASK GENMASK(4, 0)
-#define BAM_MAX_CONS_PIPES_FMASK GENMASK(12, 8)
-#define BAM_MAX_PROD_PIPES_FMASK GENMASK(20, 16)
-#define BAM_PROD_LOWEST_FMASK GENMASK(27, 24)
+#define IPA_MAX_PIPES_FMASK GENMASK(3, 0)
+#define IPA_MAX_CONS_PIPES_FMASK GENMASK(12, 8)
+#define IPA_MAX_PROD_PIPES_FMASK GENMASK(20, 16)
+#define IPA_PROD_LOWEST_FMASK GENMASK(27, 24)
static inline u32 ipa_reg_idle_indication_cfg_offset(enum ipa_version version)
{
- if (version == IPA_VERSION_4_2)
+ if (version >= IPA_VERSION_4_2)
return 0x00000240;
return 0x00000220;
#define ENTER_IDLE_DEBOUNCE_THRESH_FMASK GENMASK(15, 0)
#define CONST_NON_IDLE_ENABLE_FMASK GENMASK(16, 16)
+/* The next register is present for IPA v4.5 */
+#define IPA_REG_QTIME_TIMESTAMP_CFG_OFFSET 0x0000024c
+#define DPL_TIMESTAMP_LSB_FMASK GENMASK(4, 0)
+#define DPL_TIMESTAMP_SEL_FMASK GENMASK(7, 7)
+#define TAG_TIMESTAMP_LSB_FMASK GENMASK(12, 8)
+#define NAT_TIMESTAMP_LSB_FMASK GENMASK(20, 16)
+
+/* The next register is present for IPA v4.5 */
+#define IPA_REG_TIMERS_XO_CLK_DIV_CFG_OFFSET 0x00000250
+#define DIV_VALUE_FMASK GENMASK(8, 0)
+#define DIV_ENABLE_FMASK GENMASK(31, 31)
+
+/* The next register is present for IPA v4.5 */
+#define IPA_REG_TIMERS_PULSE_GRAN_CFG_OFFSET 0x00000254
+#define GRAN_0_FMASK GENMASK(2, 0)
+#define GRAN_1_FMASK GENMASK(5, 3)
+#define GRAN_2_FMASK GENMASK(8, 6)
+/* Values for GRAN_x fields of TIMERS_PULSE_GRAN_CFG */
+enum ipa_pulse_gran {
+ IPA_GRAN_10_US = 0x0,
+ IPA_GRAN_20_US = 0x1,
+ IPA_GRAN_50_US = 0x2,
+ IPA_GRAN_100_US = 0x3,
+ IPA_GRAN_1_MS = 0x4,
+ IPA_GRAN_10_MS = 0x5,
+ IPA_GRAN_100_MS = 0x6,
+ IPA_GRAN_655350_US = 0x7,
+};
+
+/* # IPA source resource groups available based on version */
+static inline u32 ipa_resource_group_src_count(enum ipa_version version)
+{
+ switch (version) {
+ case IPA_VERSION_3_5_1:
+ case IPA_VERSION_4_0:
+ case IPA_VERSION_4_1:
+ return 4;
+
+ case IPA_VERSION_4_2:
+ return 1;
+
+ case IPA_VERSION_4_5:
+ return 5;
+
+ default:
+ return 0;
+ }
+}
+
+/* # IPA destination resource groups available based on version */
+static inline u32 ipa_resource_group_dst_count(enum ipa_version version)
+{
+ switch (version) {
+ case IPA_VERSION_3_5_1:
+ return 3;
+
+ case IPA_VERSION_4_0:
+ case IPA_VERSION_4_1:
+ return 4;
+
+ case IPA_VERSION_4_2:
+ return 1;
+
+ case IPA_VERSION_4_5:
+ return 5;
+
+ default:
+ return 0;
+ }
+}
+
+/* Not all of the following are valid (depends on the count, above) */
#define IPA_REG_SRC_RSRC_GRP_01_RSRC_TYPE_N_OFFSET(rt) \
(0x00000400 + 0x0020 * (rt))
#define IPA_REG_SRC_RSRC_GRP_23_RSRC_TYPE_N_OFFSET(rt) \
(0x00000404 + 0x0020 * (rt))
+/* The next register is only present for IPA v4.5 */
#define IPA_REG_SRC_RSRC_GRP_45_RSRC_TYPE_N_OFFSET(rt) \
(0x00000408 + 0x0020 * (rt))
#define IPA_REG_DST_RSRC_GRP_01_RSRC_TYPE_N_OFFSET(rt) \
(0x00000500 + 0x0020 * (rt))
#define IPA_REG_DST_RSRC_GRP_23_RSRC_TYPE_N_OFFSET(rt) \
(0x00000504 + 0x0020 * (rt))
+/* The next register is only present for IPA v4.5 */
#define IPA_REG_DST_RSRC_GRP_45_RSRC_TYPE_N_OFFSET(rt) \
(0x00000508 + 0x0020 * (rt))
+/* The next four fields are used for all resource group registers */
#define X_MIN_LIM_FMASK GENMASK(5, 0)
#define X_MAX_LIM_FMASK GENMASK(13, 8)
+/* The next two fields are not always present (if resource count is odd) */
#define Y_MIN_LIM_FMASK GENMASK(21, 16)
#define Y_MAX_LIM_FMASK GENMASK(29, 24)
#define IPA_REG_ENDP_INIT_CTRL_N_OFFSET(ep) \
(0x00000800 + 0x0070 * (ep))
+/* The next field should only used for IPA v3.5.1 */
#define ENDP_SUSPEND_FMASK GENMASK(0, 0)
#define ENDP_DELAY_FMASK GENMASK(1, 1)
#define CS_METADATA_HDR_OFFSET_FMASK GENMASK(6, 3)
#define CS_GEN_QMB_MASTER_SEL_FMASK GENMASK(8, 8)
+/** enum ipa_cs_offload_en - checksum offload field in ENDP_INIT_CFG_N */
+enum ipa_cs_offload_en {
+ IPA_CS_OFFLOAD_NONE = 0x0,
+ IPA_CS_OFFLOAD_UL = 0x1,
+ IPA_CS_OFFLOAD_DL = 0x2,
+};
+
#define IPA_REG_ENDP_INIT_HDR_N_OFFSET(ep) \
(0x00000810 + 0x0070 * (ep))
#define HDR_LEN_FMASK GENMASK(5, 0)
#define HDR_OFST_PKT_SIZE_FMASK GENMASK(25, 20)
#define HDR_A5_MUX_FMASK GENMASK(26, 26)
#define HDR_LEN_INC_DEAGG_HDR_FMASK GENMASK(27, 27)
+/* The next field is not present for IPA v4.5 */
#define HDR_METADATA_REG_VALID_FMASK GENMASK(28, 28)
+/* The next two fields are present for IPA v4.5 */
+#define HDR_LEN_MSB_FMASK GENMASK(29, 28)
+#define HDR_OFST_METADATA_MSB_FMASK GENMASK(31, 30)
+
+/* Encoded value for ENDP_INIT_HDR register HDR_LEN* field(s) */
+static inline u32 ipa_header_size_encoded(enum ipa_version version,
+ u32 header_size)
+{
+ u32 val;
+
+ val = u32_encode_bits(header_size, HDR_LEN_FMASK);
+ if (version < IPA_VERSION_4_5)
+ return val;
+
+ /* IPA v4.5 adds a few more most-significant bits */
+ header_size >>= hweight32(HDR_LEN_FMASK);
+ val |= u32_encode_bits(header_size, HDR_LEN_MSB_FMASK);
+
+ return val;
+}
+
+/* Encoded value for ENDP_INIT_HDR register OFST_METADATA* field(s) */
+static inline u32 ipa_metadata_offset_encoded(enum ipa_version version,
+ u32 offset)
+{
+ u32 val;
+
+ val = u32_encode_bits(offset, HDR_OFST_METADATA_FMASK);
+ if (version < IPA_VERSION_4_5)
+ return val;
+
+ /* IPA v4.5 adds a few more most-significant bits */
+ offset >>= hweight32(HDR_OFST_METADATA_FMASK);
+ val |= u32_encode_bits(offset, HDR_OFST_METADATA_MSB_FMASK);
+
+ return val;
+}
#define IPA_REG_ENDP_INIT_HDR_EXT_N_OFFSET(ep) \
(0x00000814 + 0x0070 * (ep))
#define HDR_PAYLOAD_LEN_INC_PADDING_FMASK GENMASK(3, 3)
#define HDR_TOTAL_LEN_OR_PAD_OFFSET_FMASK GENMASK(9, 4)
#define HDR_PAD_TO_ALIGNMENT_FMASK GENMASK(13, 10)
+/* The next three fields are present for IPA v4.5 */
+#define HDR_TOTAL_LEN_OR_PAD_OFFSET_MSB_FMASK GENMASK(17, 16)
+#define HDR_OFST_PKT_SIZE_MSB_FMASK GENMASK(19, 18)
+#define HDR_ADDITIONAL_CONST_LEN_MSB_FMASK GENMASK(21, 20)
/* Valid only for RX (IPA producer) endpoints */
#define IPA_REG_ENDP_INIT_HDR_METADATA_MASK_N_OFFSET(rxep) \
#define IPA_REG_ENDP_INIT_MODE_N_OFFSET(txep) \
(0x00000820 + 0x0070 * (txep))
#define MODE_FMASK GENMASK(2, 0)
+/* The next field is present for IPA v4.5 */
+#define DCPH_ENABLE_FMASK GENMASK(3, 3)
#define DEST_PIPE_INDEX_FMASK GENMASK(8, 4)
#define BYTE_THRESHOLD_FMASK GENMASK(27, 12)
#define PIPE_REPLICATION_EN_FMASK GENMASK(28, 28)
#define PAD_EN_FMASK GENMASK(29, 29)
+/* The next register is not present for IPA v4.5 */
#define HDR_FTCH_DISABLE_FMASK GENMASK(30, 30)
+/** enum ipa_mode - mode field in ENDP_INIT_MODE_N */
+enum ipa_mode {
+ IPA_BASIC = 0x0,
+ IPA_ENABLE_FRAMING_HDLC = 0x1,
+ IPA_ENABLE_DEFRAMING_HDLC = 0x2,
+ IPA_DMA = 0x3,
+};
+
#define IPA_REG_ENDP_INIT_AGGR_N_OFFSET(ep) \
(0x00000824 + 0x0070 * (ep))
#define AGGR_EN_FMASK GENMASK(1, 0)
#define AGGR_TYPE_FMASK GENMASK(4, 2)
-#define AGGR_BYTE_LIMIT_FMASK GENMASK(9, 5)
-#define AGGR_TIME_LIMIT_FMASK GENMASK(14, 10)
-#define AGGR_PKT_LIMIT_FMASK GENMASK(20, 15)
-#define AGGR_SW_EOF_ACTIVE_FMASK GENMASK(21, 21)
-#define AGGR_FORCE_CLOSE_FMASK GENMASK(22, 22)
-#define AGGR_HARD_BYTE_LIMIT_ENABLE_FMASK GENMASK(24, 24)
+static inline u32 aggr_byte_limit_fmask(bool legacy)
+{
+ return legacy ? GENMASK(9, 5) : GENMASK(10, 5);
+}
+
+static inline u32 aggr_time_limit_fmask(bool legacy)
+{
+ return legacy ? GENMASK(14, 10) : GENMASK(16, 12);
+}
+
+static inline u32 aggr_pkt_limit_fmask(bool legacy)
+{
+ return legacy ? GENMASK(20, 15) : GENMASK(22, 17);
+}
+
+static inline u32 aggr_sw_eof_active_fmask(bool legacy)
+{
+ return legacy ? GENMASK(21, 21) : GENMASK(23, 23);
+}
+
+static inline u32 aggr_force_close_fmask(bool legacy)
+{
+ return legacy ? GENMASK(22, 22) : GENMASK(24, 24);
+}
+
+static inline u32 aggr_hard_byte_limit_enable_fmask(bool legacy)
+{
+ return legacy ? GENMASK(24, 24) : GENMASK(26, 26);
+}
+
+/* The next field is present for IPA v4.5 */
+#define AGGR_GRAN_SEL_FMASK GENMASK(27, 27)
+
+/** enum ipa_aggr_en - aggregation enable field in ENDP_INIT_AGGR_N */
+enum ipa_aggr_en {
+ IPA_BYPASS_AGGR = 0x0,
+ IPA_ENABLE_AGGR = 0x1,
+ IPA_ENABLE_DEAGGR = 0x2,
+};
+
+/** enum ipa_aggr_type - aggregation type field in ENDP_INIT_AGGR_N */
+enum ipa_aggr_type {
+ IPA_MBIM_16 = 0x0,
+ IPA_HDLC = 0x1,
+ IPA_TLP = 0x2,
+ IPA_RNDIS = 0x3,
+ IPA_GENERIC = 0x4,
+ IPA_COALESCE = 0x5,
+ IPA_QCMAP = 0x6,
+};
/* Valid only for RX (IPA producer) endpoints */
#define IPA_REG_ENDP_INIT_HOL_BLOCK_EN_N_OFFSET(rxep) \
/* Valid only for RX (IPA producer) endpoints */
#define IPA_REG_ENDP_INIT_HOL_BLOCK_TIMER_N_OFFSET(rxep) \
(0x00000830 + 0x0070 * (rxep))
-/* The next fields are present for IPA v4.2 only */
+/* The next two fields are present for IPA v4.2 only */
#define BASE_VALUE_FMASK GENMASK(4, 0)
#define SCALE_FMASK GENMASK(12, 8)
+/* The next two fields are present for IPA v4.5 */
+#define TIME_LIMIT_FMASK GENMASK(4, 0)
+#define GRAN_SEL_FMASK GENMASK(8, 8)
/* Valid only for TX (IPA consumer) endpoints */
#define IPA_REG_ENDP_INIT_DEAGGR_N_OFFSET(txep) \
(0x00000834 + 0x0070 * (txep))
#define DEAGGR_HDR_LEN_FMASK GENMASK(5, 0)
+#define SYSPIPE_ERR_DETECTION_FMASK GENMASK(6, 6)
#define PACKET_OFFSET_VALID_FMASK GENMASK(7, 7)
#define PACKET_OFFSET_LOCATION_FMASK GENMASK(13, 8)
+#define IGNORE_MIN_PKT_ERR_FMASK GENMASK(14, 14)
#define MAX_PACKET_LEN_FMASK GENMASK(31, 16)
#define IPA_REG_ENDP_INIT_RSRC_GRP_N_OFFSET(ep) \
(0x00000838 + 0x0070 * (ep))
-#define RSRC_GRP_FMASK GENMASK(1, 0)
+/* Encoded value for ENDP_INIT_RSRC_GRP register RSRC_GRP field */
+static inline u32 rsrc_grp_encoded(enum ipa_version version, u32 rsrc_grp)
+{
+ switch (version) {
+ case IPA_VERSION_4_2:
+ return u32_encode_bits(rsrc_grp, GENMASK(0, 0));
+ case IPA_VERSION_4_5:
+ return u32_encode_bits(rsrc_grp, GENMASK(2, 0));
+ default:
+ return u32_encode_bits(rsrc_grp, GENMASK(1, 0));
+ }
+}
/* Valid only for TX (IPA consumer) endpoints */
#define IPA_REG_ENDP_INIT_SEQ_N_OFFSET(txep) \
#define HPS_REP_SEQ_TYPE_FMASK GENMASK(11, 8)
#define DPS_REP_SEQ_TYPE_FMASK GENMASK(15, 12)
+/**
+ * enum ipa_seq_type - HPS and DPS sequencer type fields in ENDP_INIT_SEQ_N
+ * @IPA_SEQ_DMA_ONLY: only DMA is performed
+ * @IPA_SEQ_2ND_PKT_PROCESS_PASS_NO_DEC_UCP:
+ * second packet processing pass + no decipher + microcontroller
+ * @IPA_SEQ_PKT_PROCESS_NO_DEC_NO_UCP_DMAP:
+ * packet processing + no decipher + no uCP + HPS REP DMA parser
+ * @IPA_SEQ_INVALID: invalid sequencer type
+ *
+ * The values defined here are broken into 4-bit nibbles that are written
+ * into fields of the ENDP_INIT_SEQ registers.
+ */
+enum ipa_seq_type {
+ IPA_SEQ_DMA_ONLY = 0x0000,
+ IPA_SEQ_2ND_PKT_PROCESS_PASS_NO_DEC_UCP = 0x0004,
+ IPA_SEQ_PKT_PROCESS_NO_DEC_NO_UCP_DMAP = 0x0806,
+ IPA_SEQ_INVALID = 0xffff,
+};
+
#define IPA_REG_ENDP_STATUS_N_OFFSET(ep) \
(0x00000840 + 0x0070 * (ep))
#define STATUS_EN_FMASK GENMASK(0, 0)
#define STATUS_ENDP_FMASK GENMASK(5, 1)
+/* The next field is not present for IPA v4.5 */
#define STATUS_LOCATION_FMASK GENMASK(8, 8)
-/* The next field is present for IPA v4.0 and above */
+/* The next field is not present for IPA v3.5.1 */
#define STATUS_PKT_SUPPRESS_FMASK GENMASK(9, 9)
-/* "er" is either an endpoint ID (for filters) or a route ID (for routes) */
+/* The next register is only present for IPA versions that support hashing */
#define IPA_REG_ENDP_FILTER_ROUTER_HSH_CFG_N_OFFSET(er) \
(0x0000085c + 0x0070 * (er))
#define FILTER_HASH_MSK_SRC_ID_FMASK GENMASK(0, 0)
IPA_REG_IRQ_CLR_EE_N_OFFSET(GSI_EE_AP)
#define IPA_REG_IRQ_CLR_EE_N_OFFSET(ee) \
(0x00003010 + 0x1000 * (ee))
+/**
+ * enum ipa_irq_id - Bit positions representing type of IPA IRQ
+ * @IPA_IRQ_UC_0: Microcontroller event interrupt
+ * @IPA_IRQ_UC_1: Microcontroller response interrupt
+ * @IPA_IRQ_TX_SUSPEND: Data ready interrupt
+ *
+ * IRQ types not described above are not currently used.
+ */
+enum ipa_irq_id {
+ IPA_IRQ_BAD_SNOC_ACCESS = 0x0,
+ /* Type (bit) 0x1 is not defined */
+ IPA_IRQ_UC_0 = 0x2,
+ IPA_IRQ_UC_1 = 0x3,
+ IPA_IRQ_UC_2 = 0x4,
+ IPA_IRQ_UC_3 = 0x5,
+ IPA_IRQ_UC_IN_Q_NOT_EMPTY = 0x6,
+ IPA_IRQ_UC_RX_CMD_Q_NOT_FULL = 0x7,
+ IPA_IRQ_PROC_UC_ACK_Q_NOT_EMPTY = 0x8,
+ IPA_IRQ_RX_ERR = 0x9,
+ IPA_IRQ_DEAGGR_ERR = 0xa,
+ IPA_IRQ_TX_ERR = 0xb,
+ IPA_IRQ_STEP_MODE = 0xc,
+ IPA_IRQ_PROC_ERR = 0xd,
+ IPA_IRQ_TX_SUSPEND = 0xe,
+ IPA_IRQ_TX_HOLB_DROP = 0xf,
+ IPA_IRQ_BAM_GSI_IDLE = 0x10,
+ IPA_IRQ_PIPE_YELLOW_BELOW = 0x11,
+ IPA_IRQ_PIPE_RED_BELOW = 0x12,
+ IPA_IRQ_PIPE_YELLOW_ABOVE = 0x13,
+ IPA_IRQ_PIPE_RED_ABOVE = 0x14,
+ IPA_IRQ_UCP = 0x15,
+ IPA_IRQ_DCMP = 0x16,
+ IPA_IRQ_GSI_EE = 0x17,
+ IPA_IRQ_GSI_IPA_IF_TLV_RCVD = 0x18,
+ IPA_IRQ_GSI_UC = 0x19,
+ /* The next bit is present for IPA v4.5 */
+ IPA_IRQ_TLV_LEN_MIN_DSM = 0x1a,
+ IPA_IRQ_COUNT, /* Last; not an id */
+};
#define IPA_REG_IRQ_UC_OFFSET \
IPA_REG_IRQ_UC_EE_N_OFFSET(GSI_EE_AP)
#define IPA_REG_IRQ_UC_EE_N_OFFSET(ee) \
(0x0000301c + 0x1000 * (ee))
+#define UC_INTR_FMASK GENMASK(0, 0)
+/* ipa->available defines the valid bits in the SUSPEND_INFO register */
#define IPA_REG_IRQ_SUSPEND_INFO_OFFSET \
IPA_REG_IRQ_SUSPEND_INFO_EE_N_OFFSET(GSI_EE_AP)
#define IPA_REG_IRQ_SUSPEND_INFO_EE_N_OFFSET(ee) \
(0x00003030 + 0x1000 * (ee))
-/* ipa->available defines the valid bits in the SUSPEND_INFO register */
-#define IPA_REG_SUSPEND_IRQ_EN_OFFSET \
- IPA_REG_SUSPEND_IRQ_EN_EE_N_OFFSET(GSI_EE_AP)
-#define IPA_REG_SUSPEND_IRQ_EN_EE_N_OFFSET(ee) \
+/* ipa->available defines the valid bits in the IRQ_SUSPEND_EN register */
+#define IPA_REG_IRQ_SUSPEND_EN_OFFSET \
+ IPA_REG_IRQ_SUSPEND_EN_EE_N_OFFSET(GSI_EE_AP)
+#define IPA_REG_IRQ_SUSPEND_EN_EE_N_OFFSET(ee) \
(0x00003034 + 0x1000 * (ee))
-/* ipa->available defines the valid bits in the SUSPEND_IRQ_EN register */
-#define IPA_REG_SUSPEND_IRQ_CLR_OFFSET \
- IPA_REG_SUSPEND_IRQ_CLR_EE_N_OFFSET(GSI_EE_AP)
-#define IPA_REG_SUSPEND_IRQ_CLR_EE_N_OFFSET(ee) \
+/* ipa->available defines the valid bits in the IRQ_SUSPEND_CLR register */
+#define IPA_REG_IRQ_SUSPEND_CLR_OFFSET \
+ IPA_REG_IRQ_SUSPEND_CLR_EE_N_OFFSET(GSI_EE_AP)
+#define IPA_REG_IRQ_SUSPEND_CLR_EE_N_OFFSET(ee) \
(0x00003038 + 0x1000 * (ee))
-/* ipa->available defines the valid bits in the SUSPEND_IRQ_CLR register */
-
-/** enum ipa_cs_offload_en - checksum offload field in ENDP_INIT_CFG_N */
-enum ipa_cs_offload_en {
- IPA_CS_OFFLOAD_NONE = 0,
- IPA_CS_OFFLOAD_UL = 1,
- IPA_CS_OFFLOAD_DL = 2,
- IPA_CS_RSVD
-};
-
-/** enum ipa_aggr_en - aggregation enable field in ENDP_INIT_AGGR_N */
-enum ipa_aggr_en {
- IPA_BYPASS_AGGR = 0,
- IPA_ENABLE_AGGR = 1,
- IPA_ENABLE_DEAGGR = 2,
-};
-
-/** enum ipa_aggr_type - aggregation type field in in_ENDP_INIT_AGGR_N */
-enum ipa_aggr_type {
- IPA_MBIM_16 = 0,
- IPA_HDLC = 1,
- IPA_TLP = 2,
- IPA_RNDIS = 3,
- IPA_GENERIC = 4,
- IPA_COALESCE = 5,
- IPA_QCMAP = 6,
-};
-
-/** enum ipa_mode - mode field in ENDP_INIT_MODE_N */
-enum ipa_mode {
- IPA_BASIC = 0,
- IPA_ENABLE_FRAMING_HDLC = 1,
- IPA_ENABLE_DEFRAMING_HDLC = 2,
- IPA_DMA = 3,
-};
-
-/**
- * enum ipa_seq_type - HPS and DPS sequencer type fields in in ENDP_INIT_SEQ_N
- * @IPA_SEQ_DMA_ONLY: only DMA is performed
- * @IPA_SEQ_PKT_PROCESS_NO_DEC_UCP:
- * packet processing + no decipher + microcontroller (Ethernet Bridging)
- * @IPA_SEQ_2ND_PKT_PROCESS_PASS_NO_DEC_UCP:
- * second packet processing pass + no decipher + microcontroller
- * @IPA_SEQ_DMA_DEC: DMA + cipher/decipher
- * @IPA_SEQ_DMA_COMP_DECOMP: DMA + compression/decompression
- * @IPA_SEQ_PKT_PROCESS_NO_DEC_NO_UCP_DMAP:
- * packet processing + no decipher + no uCP + HPS REP DMA parser
- * @IPA_SEQ_INVALID: invalid sequencer type
- *
- * The values defined here are broken into 4-bit nibbles that are written
- * into fields of the INIT_SEQ_N endpoint registers.
- */
-enum ipa_seq_type {
- IPA_SEQ_DMA_ONLY = 0x0000,
- IPA_SEQ_PKT_PROCESS_NO_DEC_UCP = 0x0002,
- IPA_SEQ_2ND_PKT_PROCESS_PASS_NO_DEC_UCP = 0x0004,
- IPA_SEQ_DMA_DEC = 0x0011,
- IPA_SEQ_DMA_COMP_DECOMP = 0x0020,
- IPA_SEQ_PKT_PROCESS_NO_DEC_NO_UCP_DMAP = 0x0806,
- IPA_SEQ_INVALID = 0xffff,
-};
int ipa_reg_init(struct ipa *ipa);
void ipa_reg_exit(struct ipa *ipa);
return -EBUSY;
}
- val = IPV4_FILTER_HASH_FLUSH | IPV6_FILTER_HASH_FLUSH;
- val |= IPV6_ROUTER_HASH_FLUSH | IPV4_ROUTER_HASH_FLUSH;
+ val = IPV4_FILTER_HASH_FMASK | IPV6_FILTER_HASH_FMASK;
+ val |= IPV6_ROUTER_HASH_FMASK | IPV4_ROUTER_HASH_FMASK;
ipa_cmd_register_write_add(trans, offset, val, val, false);
/** enum ipa_uc_command - commands from the AP to the microcontroller */
enum ipa_uc_command {
- IPA_UC_COMMAND_NO_OP = 0,
- IPA_UC_COMMAND_UPDATE_FLAGS = 1,
- IPA_UC_COMMAND_DEBUG_RUN_TEST = 2,
- IPA_UC_COMMAND_DEBUG_GET_INFO = 3,
- IPA_UC_COMMAND_ERR_FATAL = 4,
- IPA_UC_COMMAND_CLK_GATE = 5,
- IPA_UC_COMMAND_CLK_UNGATE = 6,
- IPA_UC_COMMAND_MEMCPY = 7,
- IPA_UC_COMMAND_RESET_PIPE = 8,
- IPA_UC_COMMAND_REG_WRITE = 9,
- IPA_UC_COMMAND_GSI_CH_EMPTY = 10,
+ IPA_UC_COMMAND_NO_OP = 0x0,
+ IPA_UC_COMMAND_UPDATE_FLAGS = 0x1,
+ IPA_UC_COMMAND_DEBUG_RUN_TEST = 0x2,
+ IPA_UC_COMMAND_DEBUG_GET_INFO = 0x3,
+ IPA_UC_COMMAND_ERR_FATAL = 0x4,
+ IPA_UC_COMMAND_CLK_GATE = 0x5,
+ IPA_UC_COMMAND_CLK_UNGATE = 0x6,
+ IPA_UC_COMMAND_MEMCPY = 0x7,
+ IPA_UC_COMMAND_RESET_PIPE = 0x8,
+ IPA_UC_COMMAND_REG_WRITE = 0x9,
+ IPA_UC_COMMAND_GSI_CH_EMPTY = 0xa,
};
/** enum ipa_uc_response - microcontroller response codes */
enum ipa_uc_response {
- IPA_UC_RESPONSE_NO_OP = 0,
- IPA_UC_RESPONSE_INIT_COMPLETED = 1,
- IPA_UC_RESPONSE_CMD_COMPLETED = 2,
- IPA_UC_RESPONSE_DEBUG_GET_INFO = 3,
+ IPA_UC_RESPONSE_NO_OP = 0x0,
+ IPA_UC_RESPONSE_INIT_COMPLETED = 0x1,
+ IPA_UC_RESPONSE_CMD_COMPLETED = 0x2,
+ IPA_UC_RESPONSE_DEBUG_GET_INFO = 0x3,
};
/** enum ipa_uc_event - common cpu events reported by the microcontroller */
enum ipa_uc_event {
- IPA_UC_EVENT_NO_OP = 0,
- IPA_UC_EVENT_ERROR = 1,
- IPA_UC_EVENT_LOG_INFO = 2,
+ IPA_UC_EVENT_NO_OP = 0x0,
+ IPA_UC_EVENT_ERROR = 0x1,
+ IPA_UC_EVENT_LOG_INFO = 0x2,
};
static struct ipa_uc_mem_area *ipa_uc_shared(struct ipa *ipa)
if (shared->event == IPA_UC_EVENT_ERROR)
dev_err(dev, "microcontroller error event\n");
- else
+ else if (shared->event != IPA_UC_EVENT_LOG_INFO)
dev_err(dev, "unsupported microcontroller event %hhu\n",
shared->event);
+ /* The LOG_INFO event can be safely ignored */
}
/* Microcontroller response IPA interrupt handler */
static void send_uc_command(struct ipa *ipa, u32 command, u32 command_param)
{
struct ipa_uc_mem_area *shared = ipa_uc_shared(ipa);
+ u32 val;
+ /* Fill in the command data */
shared->command = command;
shared->command_param = cpu_to_le32(command_param);
shared->command_param_hi = 0;
shared->response = 0;
shared->response_param = 0;
- iowrite32(1, ipa->reg_virt + IPA_REG_IRQ_UC_OFFSET);
+ /* Use an interrupt to tell the microcontroller the command is ready */
+ val = u32_encode_bits(1, UC_INTR_FMASK);
+
+ iowrite32(val, ipa->reg_virt + IPA_REG_IRQ_UC_OFFSET);
}
/* Tell the microcontroller the AP is shutting down */
IPA_VERSION_4_0, /* GSI version 2.0 */
IPA_VERSION_4_1, /* GSI version 2.1 */
IPA_VERSION_4_2, /* GSI version 2.2 */
+ IPA_VERSION_4_5, /* GSI version 2.5 */
};
#endif /* _IPA_VERSION_H_ */
/* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
*/
+#include <linux/ethtool.h>
+
#include "ipvlan.h"
static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval,
* @real_dev: pointer to underlying netdevice
* @stats: MACsec device stats
* @secys: linked list of SecY's on the underlying device
+ * @gro_cells: pointer to the Generic Receive Offload cell
* @offload: status of offloading on the MACsec device
*/
struct macsec_dev {
#define MACVLAN_HASH_BITS 8
#define MACVLAN_HASH_SIZE (1<<MACVLAN_HASH_BITS)
-#define MACVLAN_BC_QUEUE_LEN 1000
+#define MACVLAN_DEFAULT_BC_QUEUE_LEN 1000
#define MACVLAN_F_PASSTHRU 1
#define MACVLAN_F_ADDRCHANGE 2
struct list_head vlans;
struct sk_buff_head bc_queue;
struct work_struct bc_work;
+ u32 bc_queue_len_used;
u32 flags;
int count;
struct hlist_head vlan_source_hash[MACVLAN_HASH_SIZE];
#define MACVLAN_SKB_CB(__skb) ((struct macvlan_skb_cb *)&((__skb)->cb[0]))
static void macvlan_port_destroy(struct net_device *dev);
+static void update_port_bc_queue_len(struct macvlan_port *port);
static inline bool macvlan_passthru(const struct macvlan_port *port)
{
MACVLAN_SKB_CB(nskb)->src = src;
spin_lock(&port->bc_queue.lock);
- if (skb_queue_len(&port->bc_queue) < MACVLAN_BC_QUEUE_LEN) {
+ if (skb_queue_len(&port->bc_queue) < port->bc_queue_len_used) {
if (src)
dev_hold(src->dev);
__skb_queue_tail(&port->bc_queue, nskb);
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *real_dev = vlan->lowerdev;
struct netpoll *netpoll;
- int err = 0;
+ int err;
netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
err = -ENOMEM;
for (i = 0; i < MACVLAN_HASH_SIZE; i++)
INIT_HLIST_HEAD(&port->vlan_source_hash[i]);
+ port->bc_queue_len_used = 0;
skb_queue_head_init(&port->bc_queue);
INIT_WORK(&port->bc_work, macvlan_process_broadcast);
return 0;
}
-/**
+/*
* reconfigure list of remote source mac address
* (only for macvlan devices in source mode)
* Note regarding alignment: all netlink data is aligned to 4 Byte, which
goto destroy_macvlan_port;
}
+ vlan->bc_queue_len_req = MACVLAN_DEFAULT_BC_QUEUE_LEN;
+ if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN])
+ vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]);
+
err = register_netdevice(dev);
if (err < 0)
goto destroy_macvlan_port;
goto unregister_netdev;
list_add_tail_rcu(&vlan->list, &port->vlans);
+ update_port_bc_queue_len(vlan->port);
netif_stacked_transfer_operstate(lowerdev, dev);
linkwatch_fire_event(dev);
if (vlan->mode == MACVLAN_MODE_SOURCE)
macvlan_flush_sources(vlan->port, vlan);
list_del_rcu(&vlan->list);
+ update_port_bc_queue_len(vlan->port);
unregister_netdevice_queue(dev, head);
netdev_upper_dev_unlink(vlan->lowerdev, dev);
}
}
vlan->flags = flags;
}
+
+ if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) {
+ vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]);
+ update_port_bc_queue_len(vlan->port);
+ }
+
if (set_mode)
vlan->mode = mode;
if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
+ nla_total_size(2) /* IFLA_MACVLAN_FLAGS */
+ nla_total_size(4) /* IFLA_MACVLAN_MACADDR_COUNT */
+ macvlan_get_size_mac(vlan) /* IFLA_MACVLAN_MACADDR */
+ + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN */
+ + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN_USED */
);
}
const struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
+ struct macvlan_port *port = vlan->port;
int i;
struct nlattr *nest;
}
nla_nest_end(skb, nest);
}
+ if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN, vlan->bc_queue_len_req))
+ goto nla_put_failure;
+ if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN_USED, port->bc_queue_len_used))
+ goto nla_put_failure;
return 0;
nla_put_failure:
[IFLA_MACVLAN_MACADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
[IFLA_MACVLAN_MACADDR_DATA] = { .type = NLA_NESTED },
[IFLA_MACVLAN_MACADDR_COUNT] = { .type = NLA_U32 },
+ [IFLA_MACVLAN_BC_QUEUE_LEN] = { .type = NLA_U32 },
+ [IFLA_MACVLAN_BC_QUEUE_LEN_USED] = { .type = NLA_REJECT },
};
int macvlan_link_register(struct rtnl_link_ops *ops)
.priv_size = sizeof(struct macvlan_dev),
};
+static void update_port_bc_queue_len(struct macvlan_port *port)
+{
+ u32 max_bc_queue_len_req = 0;
+ struct macvlan_dev *vlan;
+
+ list_for_each_entry(vlan, &port->vlans, list) {
+ if (vlan->bc_queue_len_req > max_bc_queue_len_req)
+ max_bc_queue_len_req = vlan->bc_queue_len_req;
+ }
+ port->bc_queue_len_used = max_bc_queue_len_req;
+}
+
static int macvlan_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* MHI Network driver - Network over MHI bus
+ *
+ * Copyright (C) 2020 Linaro Ltd <loic.poulain@linaro.org>
+ */
+
+#include <linux/if_arp.h>
+#include <linux/mhi.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/u64_stats_sync.h>
+
+#define MHI_NET_MIN_MTU ETH_MIN_MTU
+#define MHI_NET_MAX_MTU 0xffff
+#define MHI_NET_DEFAULT_MTU 0x4000
+
+struct mhi_net_stats {
+ u64_stats_t rx_packets;
+ u64_stats_t rx_bytes;
+ u64_stats_t rx_errors;
+ u64_stats_t rx_dropped;
+ u64_stats_t tx_packets;
+ u64_stats_t tx_bytes;
+ u64_stats_t tx_errors;
+ u64_stats_t tx_dropped;
+ atomic_t rx_queued;
+ struct u64_stats_sync tx_syncp;
+ struct u64_stats_sync rx_syncp;
+};
+
+struct mhi_net_dev {
+ struct mhi_device *mdev;
+ struct net_device *ndev;
+ struct delayed_work rx_refill;
+ struct mhi_net_stats stats;
+ u32 rx_queue_sz;
+};
+
+static int mhi_ndo_open(struct net_device *ndev)
+{
+ struct mhi_net_dev *mhi_netdev = netdev_priv(ndev);
+
+ /* Feed the rx buffer pool */
+ schedule_delayed_work(&mhi_netdev->rx_refill, 0);
+
+ /* Carrier is established via out-of-band channel (e.g. qmi) */
+ netif_carrier_on(ndev);
+
+ netif_start_queue(ndev);
+
+ return 0;
+}
+
+static int mhi_ndo_stop(struct net_device *ndev)
+{
+ struct mhi_net_dev *mhi_netdev = netdev_priv(ndev);
+
+ netif_stop_queue(ndev);
+ netif_carrier_off(ndev);
+ cancel_delayed_work_sync(&mhi_netdev->rx_refill);
+
+ return 0;
+}
+
+static int mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+ struct mhi_net_dev *mhi_netdev = netdev_priv(ndev);
+ struct mhi_device *mdev = mhi_netdev->mdev;
+ int err;
+
+ err = mhi_queue_skb(mdev, DMA_TO_DEVICE, skb, skb->len, MHI_EOT);
+ if (unlikely(err)) {
+ net_err_ratelimited("%s: Failed to queue TX buf (%d)\n",
+ ndev->name, err);
+
+ u64_stats_update_begin(&mhi_netdev->stats.tx_syncp);
+ u64_stats_inc(&mhi_netdev->stats.tx_dropped);
+ u64_stats_update_end(&mhi_netdev->stats.tx_syncp);
+
+ /* drop the packet */
+ dev_kfree_skb_any(skb);
+ }
+
+ if (mhi_queue_is_full(mdev, DMA_TO_DEVICE))
+ netif_stop_queue(ndev);
+
+ return NETDEV_TX_OK;
+}
+
+static void mhi_ndo_get_stats64(struct net_device *ndev,
+ struct rtnl_link_stats64 *stats)
+{
+ struct mhi_net_dev *mhi_netdev = netdev_priv(ndev);
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin_irq(&mhi_netdev->stats.rx_syncp);
+ stats->rx_packets = u64_stats_read(&mhi_netdev->stats.rx_packets);
+ stats->rx_bytes = u64_stats_read(&mhi_netdev->stats.rx_bytes);
+ stats->rx_errors = u64_stats_read(&mhi_netdev->stats.rx_errors);
+ stats->rx_dropped = u64_stats_read(&mhi_netdev->stats.rx_dropped);
+ } while (u64_stats_fetch_retry_irq(&mhi_netdev->stats.rx_syncp, start));
+
+ do {
+ start = u64_stats_fetch_begin_irq(&mhi_netdev->stats.tx_syncp);
+ stats->tx_packets = u64_stats_read(&mhi_netdev->stats.tx_packets);
+ stats->tx_bytes = u64_stats_read(&mhi_netdev->stats.tx_bytes);
+ stats->tx_errors = u64_stats_read(&mhi_netdev->stats.tx_errors);
+ stats->tx_dropped = u64_stats_read(&mhi_netdev->stats.tx_dropped);
+ } while (u64_stats_fetch_retry_irq(&mhi_netdev->stats.tx_syncp, start));
+}
+
+static const struct net_device_ops mhi_netdev_ops = {
+ .ndo_open = mhi_ndo_open,
+ .ndo_stop = mhi_ndo_stop,
+ .ndo_start_xmit = mhi_ndo_xmit,
+ .ndo_get_stats64 = mhi_ndo_get_stats64,
+};
+
+static void mhi_net_setup(struct net_device *ndev)
+{
+ ndev->header_ops = NULL; /* No header */
+ ndev->type = ARPHRD_NONE; /* QMAP... */
+ ndev->hard_header_len = 0;
+ ndev->addr_len = 0;
+ ndev->flags = IFF_POINTOPOINT | IFF_NOARP;
+ ndev->netdev_ops = &mhi_netdev_ops;
+ ndev->mtu = MHI_NET_DEFAULT_MTU;
+ ndev->min_mtu = MHI_NET_MIN_MTU;
+ ndev->max_mtu = MHI_NET_MAX_MTU;
+ ndev->tx_queue_len = 1000;
+}
+
+static void mhi_net_dl_callback(struct mhi_device *mhi_dev,
+ struct mhi_result *mhi_res)
+{
+ struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev);
+ struct sk_buff *skb = mhi_res->buf_addr;
+ int remaining;
+
+ remaining = atomic_dec_return(&mhi_netdev->stats.rx_queued);
+
+ if (unlikely(mhi_res->transaction_status)) {
+ dev_kfree_skb_any(skb);
+
+ /* MHI layer stopping/resetting the DL channel */
+ if (mhi_res->transaction_status == -ENOTCONN)
+ return;
+
+ u64_stats_update_begin(&mhi_netdev->stats.rx_syncp);
+ u64_stats_inc(&mhi_netdev->stats.rx_errors);
+ u64_stats_update_end(&mhi_netdev->stats.rx_syncp);
+ } else {
+ u64_stats_update_begin(&mhi_netdev->stats.rx_syncp);
+ u64_stats_inc(&mhi_netdev->stats.rx_packets);
+ u64_stats_add(&mhi_netdev->stats.rx_bytes, mhi_res->bytes_xferd);
+ u64_stats_update_end(&mhi_netdev->stats.rx_syncp);
+
+ skb->protocol = htons(ETH_P_MAP);
+ skb_put(skb, mhi_res->bytes_xferd);
+ netif_rx(skb);
+ }
+
+ /* Refill if RX buffers queue becomes low */
+ if (remaining <= mhi_netdev->rx_queue_sz / 2)
+ schedule_delayed_work(&mhi_netdev->rx_refill, 0);
+}
+
+static void mhi_net_ul_callback(struct mhi_device *mhi_dev,
+ struct mhi_result *mhi_res)
+{
+ struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev);
+ struct net_device *ndev = mhi_netdev->ndev;
+ struct sk_buff *skb = mhi_res->buf_addr;
+
+ /* Hardware has consumed the buffer, so free the skb (which is not
+ * freed by the MHI stack) and perform accounting.
+ */
+ dev_consume_skb_any(skb);
+
+ u64_stats_update_begin(&mhi_netdev->stats.tx_syncp);
+ if (unlikely(mhi_res->transaction_status)) {
+
+ /* MHI layer stopping/resetting the UL channel */
+ if (mhi_res->transaction_status == -ENOTCONN) {
+ u64_stats_update_end(&mhi_netdev->stats.tx_syncp);
+ return;
+ }
+
+ u64_stats_inc(&mhi_netdev->stats.tx_errors);
+ } else {
+ u64_stats_inc(&mhi_netdev->stats.tx_packets);
+ u64_stats_add(&mhi_netdev->stats.tx_bytes, mhi_res->bytes_xferd);
+ }
+ u64_stats_update_end(&mhi_netdev->stats.tx_syncp);
+
+ if (netif_queue_stopped(ndev))
+ netif_wake_queue(ndev);
+}
+
+static void mhi_net_rx_refill_work(struct work_struct *work)
+{
+ struct mhi_net_dev *mhi_netdev = container_of(work, struct mhi_net_dev,
+ rx_refill.work);
+ struct net_device *ndev = mhi_netdev->ndev;
+ struct mhi_device *mdev = mhi_netdev->mdev;
+ int size = READ_ONCE(ndev->mtu);
+ struct sk_buff *skb;
+ int err;
+
+ while (atomic_read(&mhi_netdev->stats.rx_queued) < mhi_netdev->rx_queue_sz) {
+ skb = netdev_alloc_skb(ndev, size);
+ if (unlikely(!skb))
+ break;
+
+ err = mhi_queue_skb(mdev, DMA_FROM_DEVICE, skb, size, MHI_EOT);
+ if (unlikely(err)) {
+ net_err_ratelimited("%s: Failed to queue RX buf (%d)\n",
+ ndev->name, err);
+ kfree_skb(skb);
+ break;
+ }
+
+ atomic_inc(&mhi_netdev->stats.rx_queued);
+
+ /* Do not hog the CPU if rx buffers are consumed faster than
+ * queued (unlikely).
+ */
+ cond_resched();
+ }
+
+ /* If we're still starved of rx buffers, reschedule later */
+ if (unlikely(!atomic_read(&mhi_netdev->stats.rx_queued)))
+ schedule_delayed_work(&mhi_netdev->rx_refill, HZ / 2);
+}
+
+static int mhi_net_probe(struct mhi_device *mhi_dev,
+ const struct mhi_device_id *id)
+{
+ const char *netname = (char *)id->driver_data;
+ struct device *dev = &mhi_dev->dev;
+ struct mhi_net_dev *mhi_netdev;
+ struct net_device *ndev;
+ int err;
+
+ ndev = alloc_netdev(sizeof(*mhi_netdev), netname, NET_NAME_PREDICTABLE,
+ mhi_net_setup);
+ if (!ndev)
+ return -ENOMEM;
+
+ mhi_netdev = netdev_priv(ndev);
+ dev_set_drvdata(dev, mhi_netdev);
+ mhi_netdev->ndev = ndev;
+ mhi_netdev->mdev = mhi_dev;
+ SET_NETDEV_DEV(ndev, &mhi_dev->dev);
+
+ /* All MHI net channels have 128 ring elements (at least for now) */
+ mhi_netdev->rx_queue_sz = 128;
+
+ INIT_DELAYED_WORK(&mhi_netdev->rx_refill, mhi_net_rx_refill_work);
+ u64_stats_init(&mhi_netdev->stats.rx_syncp);
+ u64_stats_init(&mhi_netdev->stats.tx_syncp);
+
+ /* Start MHI channels */
+ err = mhi_prepare_for_transfer(mhi_dev);
+ if (err)
+ goto out_err;
+
+ err = register_netdev(ndev);
+ if (err)
+ goto out_err;
+
+ return 0;
+
+out_err:
+ free_netdev(ndev);
+ return err;
+}
+
+static void mhi_net_remove(struct mhi_device *mhi_dev)
+{
+ struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev);
+
+ unregister_netdev(mhi_netdev->ndev);
+
+ mhi_unprepare_from_transfer(mhi_netdev->mdev);
+
+ free_netdev(mhi_netdev->ndev);
+}
+
+static const struct mhi_device_id mhi_net_id_table[] = {
+ { .chan = "IP_HW0", .driver_data = (kernel_ulong_t)"mhi_hwip%d" },
+ { .chan = "IP_SW0", .driver_data = (kernel_ulong_t)"mhi_swip%d" },
+ {}
+};
+MODULE_DEVICE_TABLE(mhi, mhi_net_id_table);
+
+static struct mhi_driver mhi_net_driver = {
+ .probe = mhi_net_probe,
+ .remove = mhi_net_remove,
+ .dl_xfer_cb = mhi_net_dl_callback,
+ .ul_xfer_cb = mhi_net_ul_callback,
+ .id_table = mhi_net_id_table,
+ .driver = {
+ .name = "mhi_net",
+ .owner = THIS_MODULE,
+ },
+};
+
+module_mhi_driver(mhi_net_driver);
+
+MODULE_AUTHOR("Loic Poulain <loic.poulain@linaro.org>");
+MODULE_DESCRIPTION("Network over MHI");
+MODULE_LICENSE("GPL v2");
ctrl1000 = mii->mdio_read(dev, mii->phy_id, MII_CTRL1000);
stat1000 = mii->mdio_read(dev, mii->phy_id, MII_STAT1000);
}
+
+ ecmd->advertising |= mii_get_an(mii, MII_ADVERTISE);
+ if (mii->supports_gmii)
+ ecmd->advertising |=
+ mii_ctrl1000_to_ethtool_adv_t(ctrl1000);
+
if (bmcr & BMCR_ANENABLE) {
ecmd->advertising |= ADVERTISED_Autoneg;
ecmd->autoneg = AUTONEG_ENABLE;
- ecmd->advertising |= mii_get_an(mii, MII_ADVERTISE);
- if (mii->supports_gmii)
- ecmd->advertising |=
- mii_ctrl1000_to_ethtool_adv_t(ctrl1000);
-
if (bmsr & BMSR_ANEGCOMPLETE) {
ecmd->lp_advertising = mii_get_an(mii, MII_LPA);
ecmd->lp_advertising |=
ctrl1000 = mii->mdio_read(dev, mii->phy_id, MII_CTRL1000);
stat1000 = mii->mdio_read(dev, mii->phy_id, MII_STAT1000);
}
+
+ advertising |= mii_get_an(mii, MII_ADVERTISE);
+ if (mii->supports_gmii)
+ advertising |= mii_ctrl1000_to_ethtool_adv_t(ctrl1000);
+
if (bmcr & BMCR_ANENABLE) {
advertising |= ADVERTISED_Autoneg;
cmd->base.autoneg = AUTONEG_ENABLE;
- advertising |= mii_get_an(mii, MII_ADVERTISE);
- if (mii->supports_gmii)
- advertising |= mii_ctrl1000_to_ethtool_adv_t(ctrl1000);
-
if (bmsr & BMSR_ANEGCOMPLETE) {
lp_advertising = mii_get_an(mii, MII_LPA);
lp_advertising |=
/**
* net_failover_create - Create and register a failover instance
*
- * @dev: standby netdev
+ * @standby_dev: standby netdev
*
* Creates a failover netdev and registers a failover instance for a standby
* netdev. Used by paravirtual drivers that use 3-netdev model.
* whether the corresponding netpoll is active or inactive.
* Also, other parameters of a target may be modified at
* runtime only when it is disabled (enabled == 0).
+ * @extended: Denotes whether console is extended or not.
* @np: The netpoll structure for this target.
* Contains the other userspace visible parameters:
* dev_name (read-write)
return err;
}
+ /* Resources for nexthops */
+ err = devlink_resource_register(devlink, "nexthops", (u64)-1,
+ NSIM_RESOURCE_NEXTHOPS,
+ DEVLINK_RESOURCE_ID_PARENT_TOP,
+ ¶ms);
+
out:
return err;
}
return -EOPNOTSUPP;
if (nsim_dev->fw_update_status) {
- devlink_flash_update_begin_notify(devlink);
devlink_flash_update_status_notify(devlink,
"Preparing to flash",
params->component, 0, 0);
params->component, 81);
devlink_flash_update_status_notify(devlink, "Flashing done",
params->component, 0, 0);
- devlink_flash_update_end_notify(devlink);
}
return 0;
{
struct netdevsim *ns = netdev_priv(dev);
- if (ns->ethtool.report_stats_rx)
+ if (ns->ethtool.pauseparam.report_stats_rx)
pause_stats->rx_pause_frames = 1;
- if (ns->ethtool.report_stats_tx)
+ if (ns->ethtool.pauseparam.report_stats_tx)
pause_stats->tx_pause_frames = 2;
}
struct netdevsim *ns = netdev_priv(dev);
pause->autoneg = 0; /* We don't support ksettings, so can't pretend */
- pause->rx_pause = ns->ethtool.rx;
- pause->tx_pause = ns->ethtool.tx;
+ pause->rx_pause = ns->ethtool.pauseparam.rx;
+ pause->tx_pause = ns->ethtool.pauseparam.tx;
}
static int
if (pause->autoneg)
return -EINVAL;
- ns->ethtool.rx = pause->rx_pause;
- ns->ethtool.tx = pause->tx_pause;
+ ns->ethtool.pauseparam.rx = pause->rx_pause;
+ ns->ethtool.pauseparam.tx = pause->tx_pause;
+ return 0;
+}
+
+static int nsim_get_coalesce(struct net_device *dev,
+ struct ethtool_coalesce *coal)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ memcpy(coal, &ns->ethtool.coalesce, sizeof(ns->ethtool.coalesce));
+ return 0;
+}
+
+static int nsim_set_coalesce(struct net_device *dev,
+ struct ethtool_coalesce *coal)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ memcpy(&ns->ethtool.coalesce, coal, sizeof(ns->ethtool.coalesce));
+ return 0;
+}
+
+static void nsim_get_ringparam(struct net_device *dev,
+ struct ethtool_ringparam *ring)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ memcpy(ring, &ns->ethtool.ring, sizeof(ns->ethtool.ring));
+}
+
+static int nsim_set_ringparam(struct net_device *dev,
+ struct ethtool_ringparam *ring)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ memcpy(&ns->ethtool.ring, ring, sizeof(ns->ethtool.ring));
return 0;
}
static const struct ethtool_ops nsim_ethtool_ops = {
- .get_pause_stats = nsim_get_pause_stats,
- .get_pauseparam = nsim_get_pauseparam,
- .set_pauseparam = nsim_set_pauseparam,
+ .supported_coalesce_params = ETHTOOL_COALESCE_ALL_PARAMS,
+ .get_pause_stats = nsim_get_pause_stats,
+ .get_pauseparam = nsim_get_pauseparam,
+ .set_pauseparam = nsim_set_pauseparam,
+ .set_coalesce = nsim_set_coalesce,
+ .get_coalesce = nsim_get_coalesce,
+ .get_ringparam = nsim_get_ringparam,
+ .set_ringparam = nsim_set_ringparam,
};
+static void nsim_ethtool_ring_init(struct netdevsim *ns)
+{
+ ns->ethtool.ring.rx_max_pending = 4096;
+ ns->ethtool.ring.rx_jumbo_max_pending = 4096;
+ ns->ethtool.ring.rx_mini_max_pending = 4096;
+ ns->ethtool.ring.tx_max_pending = 4096;
+}
+
void nsim_ethtool_init(struct netdevsim *ns)
{
struct dentry *ethtool, *dir;
ns->netdev->ethtool_ops = &nsim_ethtool_ops;
+ nsim_ethtool_ring_init(ns);
+
ethtool = debugfs_create_dir("ethtool", ns->nsim_dev_port->ddir);
dir = debugfs_create_dir("pause", ethtool);
debugfs_create_bool("report_stats_rx", 0600, dir,
- &ns->ethtool.report_stats_rx);
+ &ns->ethtool.pauseparam.report_stats_rx);
debugfs_create_bool("report_stats_tx", 0600, dir,
- &ns->ethtool.report_stats_tx);
+ &ns->ethtool.pauseparam.report_stats_tx);
+
+ dir = debugfs_create_dir("ring", ethtool);
+ debugfs_create_u32("rx_max_pending", 0600, dir,
+ &ns->ethtool.ring.rx_max_pending);
+ debugfs_create_u32("rx_jumbo_max_pending", 0600, dir,
+ &ns->ethtool.ring.rx_jumbo_max_pending);
+ debugfs_create_u32("rx_mini_max_pending", 0600, dir,
+ &ns->ethtool.ring.rx_mini_max_pending);
+ debugfs_create_u32("tx_max_pending", 0600, dir,
+ &ns->ethtool.ring.tx_max_pending);
}
#include <net/ip6_fib.h>
#include <net/fib_rules.h>
#include <net/net_namespace.h>
+#include <net/nexthop.h>
#include "netdevsim.h"
struct notifier_block fib_nb;
struct nsim_per_fib_data ipv4;
struct nsim_per_fib_data ipv6;
+ struct nsim_fib_entry nexthops;
struct rhashtable fib_rt_ht;
struct list_head fib_rt_list;
spinlock_t fib_lock; /* Protects hashtable, list and accounting */
+ struct notifier_block nexthop_nb;
+ struct rhashtable nexthop_ht;
struct devlink *devlink;
};
.automatic_shrinking = true,
};
+struct nsim_nexthop {
+ struct rhash_head ht_node;
+ u64 occ;
+ u32 id;
+};
+
+static const struct rhashtable_params nsim_nexthop_ht_params = {
+ .key_offset = offsetof(struct nsim_nexthop, id),
+ .head_offset = offsetof(struct nsim_nexthop, ht_node),
+ .key_len = sizeof(u32),
+ .automatic_shrinking = true,
+};
+
u64 nsim_fib_get_val(struct nsim_fib_data *fib_data,
enum nsim_resource_id res_id, bool max)
{
case NSIM_RESOURCE_IPV6_FIB_RULES:
entry = &fib_data->ipv6.rules;
break;
+ case NSIM_RESOURCE_NEXTHOPS:
+ entry = &fib_data->nexthops;
+ break;
default:
return 0;
}
case NSIM_RESOURCE_IPV6_FIB_RULES:
entry = &fib_data->ipv6.rules;
break;
+ case NSIM_RESOURCE_NEXTHOPS:
+ entry = &fib_data->nexthops;
+ break;
default:
WARN_ON(1);
return;
fen_info = container_of(info, struct fib_entry_notifier_info, info);
- if (fen_info->fi->nh) {
- NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported");
- return 0;
- }
-
switch (event) {
case FIB_EVENT_ENTRY_REPLACE:
err = nsim_fib4_rt_insert(data, fen_info);
fen6_info = container_of(info, struct fib6_entry_notifier_info, info);
- if (fen6_info->rt->nh) {
- NL_SET_ERR_MSG_MOD(info->extack, "IPv6 route with nexthop objects is not supported");
- return 0;
- }
-
if (fen6_info->rt->fib6_src.plen) {
NL_SET_ERR_MSG_MOD(info->extack, "IPv6 source-specific route is not supported");
return 0;
data->ipv6.rules.num = 0ULL;
}
+static struct nsim_nexthop *nsim_nexthop_create(struct nsim_fib_data *data,
+ struct nh_notifier_info *info)
+{
+ struct nsim_nexthop *nexthop;
+ u64 occ = 0;
+ int i;
+
+ nexthop = kzalloc(sizeof(*nexthop), GFP_KERNEL);
+ if (!nexthop)
+ return NULL;
+
+ nexthop->id = info->id;
+
+ /* Determine the number of nexthop entries the new nexthop will
+ * occupy.
+ */
+
+ if (!info->is_grp) {
+ occ = 1;
+ goto out;
+ }
+
+ for (i = 0; i < info->nh_grp->num_nh; i++)
+ occ += info->nh_grp->nh_entries[i].weight;
+
+out:
+ nexthop->occ = occ;
+ return nexthop;
+}
+
+static void nsim_nexthop_destroy(struct nsim_nexthop *nexthop)
+{
+ kfree(nexthop);
+}
+
+static int nsim_nexthop_account(struct nsim_fib_data *data, u64 occ,
+ bool add, struct netlink_ext_ack *extack)
+{
+ int err = 0;
+
+ if (add) {
+ if (data->nexthops.num + occ <= data->nexthops.max) {
+ data->nexthops.num += occ;
+ } else {
+ err = -ENOSPC;
+ NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported nexthops");
+ }
+ } else {
+ if (WARN_ON(occ > data->nexthops.num))
+ return -EINVAL;
+ data->nexthops.num -= occ;
+ }
+
+ return err;
+}
+
+static int nsim_nexthop_add(struct nsim_fib_data *data,
+ struct nsim_nexthop *nexthop,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = devlink_net(data->devlink);
+ int err;
+
+ err = nsim_nexthop_account(data, nexthop->occ, true, extack);
+ if (err)
+ return err;
+
+ err = rhashtable_insert_fast(&data->nexthop_ht, &nexthop->ht_node,
+ nsim_nexthop_ht_params);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to insert nexthop");
+ goto err_nexthop_dismiss;
+ }
+
+ nexthop_set_hw_flags(net, nexthop->id, false, true);
+
+ return 0;
+
+err_nexthop_dismiss:
+ nsim_nexthop_account(data, nexthop->occ, false, extack);
+ return err;
+}
+
+static int nsim_nexthop_replace(struct nsim_fib_data *data,
+ struct nsim_nexthop *nexthop,
+ struct nsim_nexthop *nexthop_old,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = devlink_net(data->devlink);
+ int err;
+
+ err = nsim_nexthop_account(data, nexthop->occ, true, extack);
+ if (err)
+ return err;
+
+ err = rhashtable_replace_fast(&data->nexthop_ht,
+ &nexthop_old->ht_node, &nexthop->ht_node,
+ nsim_nexthop_ht_params);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to replace nexthop");
+ goto err_nexthop_dismiss;
+ }
+
+ nexthop_set_hw_flags(net, nexthop->id, false, true);
+ nsim_nexthop_account(data, nexthop_old->occ, false, extack);
+ nsim_nexthop_destroy(nexthop_old);
+
+ return 0;
+
+err_nexthop_dismiss:
+ nsim_nexthop_account(data, nexthop->occ, false, extack);
+ return err;
+}
+
+static int nsim_nexthop_insert(struct nsim_fib_data *data,
+ struct nh_notifier_info *info)
+{
+ struct nsim_nexthop *nexthop, *nexthop_old;
+ int err;
+
+ nexthop = nsim_nexthop_create(data, info);
+ if (!nexthop)
+ return -ENOMEM;
+
+ nexthop_old = rhashtable_lookup_fast(&data->nexthop_ht, &info->id,
+ nsim_nexthop_ht_params);
+ if (!nexthop_old)
+ err = nsim_nexthop_add(data, nexthop, info->extack);
+ else
+ err = nsim_nexthop_replace(data, nexthop, nexthop_old,
+ info->extack);
+
+ if (err)
+ nsim_nexthop_destroy(nexthop);
+
+ return err;
+}
+
+static void nsim_nexthop_remove(struct nsim_fib_data *data,
+ struct nh_notifier_info *info)
+{
+ struct nsim_nexthop *nexthop;
+
+ nexthop = rhashtable_lookup_fast(&data->nexthop_ht, &info->id,
+ nsim_nexthop_ht_params);
+ if (!nexthop)
+ return;
+
+ rhashtable_remove_fast(&data->nexthop_ht, &nexthop->ht_node,
+ nsim_nexthop_ht_params);
+ nsim_nexthop_account(data, nexthop->occ, false, info->extack);
+ nsim_nexthop_destroy(nexthop);
+}
+
+static int nsim_nexthop_event_nb(struct notifier_block *nb, unsigned long event,
+ void *ptr)
+{
+ struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data,
+ nexthop_nb);
+ struct nh_notifier_info *info = ptr;
+ int err = 0;
+
+ ASSERT_RTNL();
+
+ switch (event) {
+ case NEXTHOP_EVENT_REPLACE:
+ err = nsim_nexthop_insert(data, info);
+ break;
+ case NEXTHOP_EVENT_DEL:
+ nsim_nexthop_remove(data, info);
+ break;
+ default:
+ break;
+ }
+
+ return notifier_from_errno(err);
+}
+
+static void nsim_nexthop_free(void *ptr, void *arg)
+{
+ struct nsim_nexthop *nexthop = ptr;
+ struct nsim_fib_data *data = arg;
+ struct net *net;
+
+ net = devlink_net(data->devlink);
+ nexthop_set_hw_flags(net, nexthop->id, false, false);
+ nsim_nexthop_account(data, nexthop->occ, false, NULL);
+ nsim_nexthop_destroy(nexthop);
+}
+
static u64 nsim_fib_ipv4_resource_occ_get(void *priv)
{
struct nsim_fib_data *data = priv;
return nsim_fib_get_val(data, NSIM_RESOURCE_IPV6_FIB_RULES, false);
}
+static u64 nsim_fib_nexthops_res_occ_get(void *priv)
+{
+ struct nsim_fib_data *data = priv;
+
+ return nsim_fib_get_val(data, NSIM_RESOURCE_NEXTHOPS, false);
+}
+
static void nsim_fib_set_max_all(struct nsim_fib_data *data,
struct devlink *devlink)
{
enum nsim_resource_id res_ids[] = {
NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES,
- NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES
+ NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES,
+ NSIM_RESOURCE_NEXTHOPS,
};
int i;
return ERR_PTR(-ENOMEM);
data->devlink = devlink;
+ err = rhashtable_init(&data->nexthop_ht, &nsim_nexthop_ht_params);
+ if (err)
+ goto err_data_free;
+
spin_lock_init(&data->fib_lock);
INIT_LIST_HEAD(&data->fib_rt_list);
err = rhashtable_init(&data->fib_rt_ht, &nsim_fib_rt_ht_params);
if (err)
- goto err_data_free;
+ goto err_rhashtable_nexthop_destroy;
nsim_fib_set_max_all(data, devlink);
+ data->nexthop_nb.notifier_call = nsim_nexthop_event_nb;
+ err = register_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb,
+ extack);
+ if (err) {
+ pr_err("Failed to register nexthop notifier\n");
+ goto err_rhashtable_fib_destroy;
+ }
+
data->fib_nb.notifier_call = nsim_fib_event_nb;
err = register_fib_notifier(devlink_net(devlink), &data->fib_nb,
nsim_fib_dump_inconsistent, extack);
if (err) {
pr_err("Failed to register fib notifier\n");
- goto err_rhashtable_destroy;
+ goto err_nexthop_nb_unregister;
}
devlink_resource_occ_get_register(devlink,
NSIM_RESOURCE_IPV6_FIB_RULES,
nsim_fib_ipv6_rules_res_occ_get,
data);
+ devlink_resource_occ_get_register(devlink,
+ NSIM_RESOURCE_NEXTHOPS,
+ nsim_fib_nexthops_res_occ_get,
+ data);
return data;
-err_rhashtable_destroy:
+err_nexthop_nb_unregister:
+ unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb);
+err_rhashtable_fib_destroy:
rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free,
data);
+err_rhashtable_nexthop_destroy:
+ rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free,
+ data);
err_data_free:
kfree(data);
return ERR_PTR(err);
void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data)
{
+ devlink_resource_occ_get_unregister(devlink,
+ NSIM_RESOURCE_NEXTHOPS);
devlink_resource_occ_get_unregister(devlink,
NSIM_RESOURCE_IPV6_FIB_RULES);
devlink_resource_occ_get_unregister(devlink,
devlink_resource_occ_get_unregister(devlink,
NSIM_RESOURCE_IPV4_FIB);
unregister_fib_notifier(devlink_net(devlink), &data->fib_nb);
+ unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb);
rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free,
data);
+ rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free,
+ data);
WARN_ON_ONCE(!list_empty(&data->fib_rt_list));
kfree(data);
}
#include <linux/debugfs.h>
#include <linux/device.h>
+#include <linux/ethtool.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/netdevice.h>
u32 ok;
};
-struct nsim_ethtool {
+struct nsim_ethtool_pauseparam {
bool rx;
bool tx;
bool report_stats_rx;
bool report_stats_tx;
};
+struct nsim_ethtool {
+ struct nsim_ethtool_pauseparam pauseparam;
+ struct ethtool_coalesce coalesce;
+ struct ethtool_ringparam ring;
+};
+
struct netdevsim {
struct net_device *netdev;
struct nsim_dev *nsim_dev;
NSIM_RESOURCE_IPV6,
NSIM_RESOURCE_IPV6_FIB,
NSIM_RESOURCE_IPV6_FIB_RULES,
+ NSIM_RESOURCE_NEXTHOPS,
};
struct nsim_dev_health {
// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/bitfield.h>
#include <linux/delay.h>
#include <linux/errno.h>
+#include <linux/ethtool_netlink.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mii.h>
#define ADIN1300_PHY_CTRL1 0x0012
#define ADIN1300_AUTO_MDI_EN BIT(10)
#define ADIN1300_MAN_MDIX_EN BIT(9)
+#define ADIN1300_DIAG_CLK_EN BIT(2)
#define ADIN1300_RX_ERR_CNT 0x0014
#define ADIN1300_CLOCK_STOP_REG 0x9400
#define ADIN1300_LPI_WAKE_ERR_CNT_REG 0xa000
+#define ADIN1300_CDIAG_RUN 0xba1b
+#define ADIN1300_CDIAG_RUN_EN BIT(0)
+
+/*
+ * The XSIM3/2/1 and XSHRT3/2/1 are actually relative.
+ * For CDIAG_DTLD_RSLTS(0) it's ADIN1300_CDIAG_RSLT_XSIM3/2/1
+ * For CDIAG_DTLD_RSLTS(1) it's ADIN1300_CDIAG_RSLT_XSIM3/2/0
+ * For CDIAG_DTLD_RSLTS(2) it's ADIN1300_CDIAG_RSLT_XSIM3/1/0
+ * For CDIAG_DTLD_RSLTS(3) it's ADIN1300_CDIAG_RSLT_XSIM2/1/0
+ */
+#define ADIN1300_CDIAG_DTLD_RSLTS(x) (0xba1d + (x))
+#define ADIN1300_CDIAG_RSLT_BUSY BIT(10)
+#define ADIN1300_CDIAG_RSLT_XSIM3 BIT(9)
+#define ADIN1300_CDIAG_RSLT_XSIM2 BIT(8)
+#define ADIN1300_CDIAG_RSLT_XSIM1 BIT(7)
+#define ADIN1300_CDIAG_RSLT_SIM BIT(6)
+#define ADIN1300_CDIAG_RSLT_XSHRT3 BIT(5)
+#define ADIN1300_CDIAG_RSLT_XSHRT2 BIT(4)
+#define ADIN1300_CDIAG_RSLT_XSHRT1 BIT(3)
+#define ADIN1300_CDIAG_RSLT_SHRT BIT(2)
+#define ADIN1300_CDIAG_RSLT_OPEN BIT(1)
+#define ADIN1300_CDIAG_RSLT_GOOD BIT(0)
+
+#define ADIN1300_CDIAG_FLT_DIST(x) (0xba21 + (x))
+
#define ADIN1300_GE_SOFT_RESET_REG 0xff0c
#define ADIN1300_GE_SOFT_RESET BIT(0)
return -E2BIG;
val = FIELD_PREP(ADIN1300_DOWNSPEED_RETRIES_MSK, cnt);
- val |= ADIN1300_LINKING_EN;
rc = phy_modify(phydev, ADIN1300_PHY_CTRL3,
- ADIN1300_LINKING_EN | ADIN1300_DOWNSPEED_RETRIES_MSK,
+ ADIN1300_DOWNSPEED_RETRIES_MSK,
val);
if (rc < 0)
return rc;
static int adin_phy_config_intr(struct phy_device *phydev)
{
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
- return phy_set_bits(phydev, ADIN1300_INT_MASK_REG,
- ADIN1300_INT_MASK_EN);
+ int err;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = adin_phy_ack_intr(phydev);
+ if (err)
+ return err;
+
+ err = phy_set_bits(phydev, ADIN1300_INT_MASK_REG,
+ ADIN1300_INT_MASK_EN);
+ } else {
+ err = phy_clear_bits(phydev, ADIN1300_INT_MASK_REG,
+ ADIN1300_INT_MASK_EN);
+ if (err)
+ return err;
+
+ err = adin_phy_ack_intr(phydev);
+ }
+
+ return err;
+}
+
+static irqreturn_t adin_phy_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, ADIN1300_INT_STATUS_REG);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
- return phy_clear_bits(phydev, ADIN1300_INT_MASK_REG,
- ADIN1300_INT_MASK_EN);
+ if (!(irq_status & ADIN1300_INT_LINK_STAT_CHNG_EN))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
static int adin_cl45_to_adin_reg(struct phy_device *phydev, int devad,
{
int ret;
+ ret = phy_clear_bits(phydev, ADIN1300_PHY_CTRL1, ADIN1300_DIAG_CLK_EN);
+ if (ret < 0)
+ return ret;
+
+ ret = phy_set_bits(phydev, ADIN1300_PHY_CTRL3, ADIN1300_LINKING_EN);
+ if (ret < 0)
+ return ret;
+
ret = adin_config_mdix(phydev);
if (ret)
return ret;
return 0;
}
+static int adin_cable_test_start(struct phy_device *phydev)
+{
+ int ret;
+
+ ret = phy_clear_bits(phydev, ADIN1300_PHY_CTRL3, ADIN1300_LINKING_EN);
+ if (ret < 0)
+ return ret;
+
+ ret = phy_clear_bits(phydev, ADIN1300_PHY_CTRL1, ADIN1300_DIAG_CLK_EN);
+ if (ret < 0)
+ return ret;
+
+ /* wait a bit for the clock to stabilize */
+ msleep(50);
+
+ return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, ADIN1300_CDIAG_RUN,
+ ADIN1300_CDIAG_RUN_EN);
+}
+
+static int adin_cable_test_report_trans(int result)
+{
+ int mask;
+
+ if (result & ADIN1300_CDIAG_RSLT_GOOD)
+ return ETHTOOL_A_CABLE_RESULT_CODE_OK;
+ if (result & ADIN1300_CDIAG_RSLT_OPEN)
+ return ETHTOOL_A_CABLE_RESULT_CODE_OPEN;
+
+ /* short with other pairs */
+ mask = ADIN1300_CDIAG_RSLT_XSHRT3 |
+ ADIN1300_CDIAG_RSLT_XSHRT2 |
+ ADIN1300_CDIAG_RSLT_XSHRT1;
+ if (result & mask)
+ return ETHTOOL_A_CABLE_RESULT_CODE_CROSS_SHORT;
+
+ if (result & ADIN1300_CDIAG_RSLT_SHRT)
+ return ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT;
+
+ return ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC;
+}
+
+static int adin_cable_test_report_pair(struct phy_device *phydev,
+ unsigned int pair)
+{
+ int fault_rslt;
+ int ret;
+
+ ret = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+ ADIN1300_CDIAG_DTLD_RSLTS(pair));
+ if (ret < 0)
+ return ret;
+
+ fault_rslt = adin_cable_test_report_trans(ret);
+
+ ret = ethnl_cable_test_result(phydev, pair, fault_rslt);
+ if (ret < 0)
+ return ret;
+
+ ret = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+ ADIN1300_CDIAG_FLT_DIST(pair));
+ if (ret < 0)
+ return ret;
+
+ switch (fault_rslt) {
+ case ETHTOOL_A_CABLE_RESULT_CODE_OPEN:
+ case ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT:
+ case ETHTOOL_A_CABLE_RESULT_CODE_CROSS_SHORT:
+ return ethnl_cable_test_fault_length(phydev, pair, ret * 100);
+ default:
+ return 0;
+ }
+}
+
+static int adin_cable_test_report(struct phy_device *phydev)
+{
+ unsigned int pair;
+ int ret;
+
+ for (pair = ETHTOOL_A_CABLE_PAIR_A; pair <= ETHTOOL_A_CABLE_PAIR_D; pair++) {
+ ret = adin_cable_test_report_pair(phydev, pair);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int adin_cable_test_get_status(struct phy_device *phydev,
+ bool *finished)
+{
+ int ret;
+
+ *finished = false;
+
+ ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, ADIN1300_CDIAG_RUN);
+ if (ret < 0)
+ return ret;
+
+ if (ret & ADIN1300_CDIAG_RUN_EN)
+ return 0;
+
+ *finished = true;
+
+ return adin_cable_test_report(phydev);
+}
+
static struct phy_driver adin_driver[] = {
{
PHY_ID_MATCH_MODEL(PHY_ID_ADIN1200),
.name = "ADIN1200",
+ .flags = PHY_POLL_CABLE_TEST,
.probe = adin_probe,
.config_init = adin_config_init,
.soft_reset = adin_soft_reset,
.read_status = adin_read_status,
.get_tunable = adin_get_tunable,
.set_tunable = adin_set_tunable,
- .ack_interrupt = adin_phy_ack_intr,
.config_intr = adin_phy_config_intr,
+ .handle_interrupt = adin_phy_handle_interrupt,
.get_sset_count = adin_get_sset_count,
.get_strings = adin_get_strings,
.get_stats = adin_get_stats,
.suspend = genphy_suspend,
.read_mmd = adin_read_mmd,
.write_mmd = adin_write_mmd,
+ .cable_test_start = adin_cable_test_start,
+ .cable_test_get_status = adin_cable_test_get_status,
},
{
PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300),
.name = "ADIN1300",
+ .flags = PHY_POLL_CABLE_TEST,
.probe = adin_probe,
.config_init = adin_config_init,
.soft_reset = adin_soft_reset,
.read_status = adin_read_status,
.get_tunable = adin_get_tunable,
.set_tunable = adin_set_tunable,
- .ack_interrupt = adin_phy_ack_intr,
.config_intr = adin_phy_config_intr,
+ .handle_interrupt = adin_phy_handle_interrupt,
.get_sset_count = adin_get_sset_count,
.get_strings = adin_get_strings,
.get_stats = adin_get_stats,
.suspend = genphy_suspend,
.read_mmd = adin_read_mmd,
.write_mmd = adin_write_mmd,
+ .cable_test_start = adin_cable_test_start,
+ .cable_test_get_status = adin_cable_test_get_status,
},
};
#define MII_AM79C_IR_EN_ANEG 0x0100 /* IR enable Aneg Complete */
#define MII_AM79C_IR_IMASK_INIT (MII_AM79C_IR_EN_LINK | MII_AM79C_IR_EN_ANEG)
+#define MII_AM79C_IR_LINK_DOWN BIT(2)
+#define MII_AM79C_IR_ANEG_DONE BIT(0)
+#define MII_AM79C_IR_IMASK_STAT (MII_AM79C_IR_LINK_DOWN | MII_AM79C_IR_ANEG_DONE)
+
MODULE_DESCRIPTION("AMD PHY driver");
MODULE_AUTHOR("Heiko Schocher <hs@denx.de>");
MODULE_LICENSE("GPL");
{
int err;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = am79c_ack_interrupt(phydev);
+ if (err)
+ return err;
+
err = phy_write(phydev, MII_AM79C_IR, MII_AM79C_IR_IMASK_INIT);
- else
+ } else {
err = phy_write(phydev, MII_AM79C_IR, 0);
+ if (err)
+ return err;
+
+ err = am79c_ack_interrupt(phydev);
+ }
return err;
}
+static irqreturn_t am79c_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, MII_AM79C_IR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & MII_AM79C_IR_IMASK_STAT))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
static struct phy_driver am79c_driver[] = { {
.phy_id = PHY_ID_AM79C874,
.name = "AM79C874",
.phy_id_mask = 0xfffffff0,
/* PHY_BASIC_FEATURES */
.config_init = am79c_config_init,
- .ack_interrupt = am79c_ack_interrupt,
.config_intr = am79c_config_intr,
+ .handle_interrupt = am79c_handle_interrupt,
} };
module_phy_driver(am79c_driver);
#define MDIO_AN_TX_VEND_INT_STATUS1_DOWNSHIFT BIT(1)
#define MDIO_AN_TX_VEND_INT_STATUS2 0xcc01
+#define MDIO_AN_TX_VEND_INT_STATUS2_MASK BIT(0)
#define MDIO_AN_TX_VEND_INT_MASK2 0xd401
#define MDIO_AN_TX_VEND_INT_MASK2_LINK BIT(0)
bool en = phydev->interrupts == PHY_INTERRUPT_ENABLED;
int err;
+ if (en) {
+ /* Clear any pending interrupts before enabling them */
+ err = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_TX_VEND_INT_STATUS2);
+ if (err < 0)
+ return err;
+ }
+
err = phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_TX_VEND_INT_MASK2,
en ? MDIO_AN_TX_VEND_INT_MASK2_LINK : 0);
if (err < 0)
if (err < 0)
return err;
- return phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_INT_VEND_MASK,
- en ? VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3 |
- VEND1_GLOBAL_INT_VEND_MASK_AN : 0);
+ err = phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_INT_VEND_MASK,
+ en ? VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3 |
+ VEND1_GLOBAL_INT_VEND_MASK_AN : 0);
+ if (err < 0)
+ return err;
+
+ if (!en) {
+ /* Clear any pending interrupts after we have disabled them */
+ err = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_TX_VEND_INT_STATUS2);
+ if (err < 0)
+ return err;
+ }
+
+ return 0;
}
-static int aqr_ack_interrupt(struct phy_device *phydev)
+static irqreturn_t aqr_handle_interrupt(struct phy_device *phydev)
{
- int reg;
+ int irq_status;
+
+ irq_status = phy_read_mmd(phydev, MDIO_MMD_AN,
+ MDIO_AN_TX_VEND_INT_STATUS2);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & MDIO_AN_TX_VEND_INT_STATUS2_MASK))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
- reg = phy_read_mmd(phydev, MDIO_MMD_AN,
- MDIO_AN_TX_VEND_INT_STATUS2);
- return (reg < 0) ? reg : 0;
+ return IRQ_HANDLED;
}
static int aqr_read_status(struct phy_device *phydev)
.name = "Aquantia AQ1202",
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
- .ack_interrupt = aqr_ack_interrupt,
+ .handle_interrupt = aqr_handle_interrupt,
.read_status = aqr_read_status,
},
{
.name = "Aquantia AQ2104",
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
- .ack_interrupt = aqr_ack_interrupt,
+ .handle_interrupt = aqr_handle_interrupt,
.read_status = aqr_read_status,
},
{
.name = "Aquantia AQR105",
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
- .ack_interrupt = aqr_ack_interrupt,
+ .handle_interrupt = aqr_handle_interrupt,
.read_status = aqr_read_status,
.suspend = aqr107_suspend,
.resume = aqr107_resume,
.name = "Aquantia AQR106",
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
- .ack_interrupt = aqr_ack_interrupt,
+ .handle_interrupt = aqr_handle_interrupt,
.read_status = aqr_read_status,
},
{
.config_init = aqr107_config_init,
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
- .ack_interrupt = aqr_ack_interrupt,
+ .handle_interrupt = aqr_handle_interrupt,
.read_status = aqr107_read_status,
.get_tunable = aqr107_get_tunable,
.set_tunable = aqr107_set_tunable,
.config_init = aqcs109_config_init,
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
- .ack_interrupt = aqr_ack_interrupt,
+ .handle_interrupt = aqr_handle_interrupt,
.read_status = aqr107_read_status,
.get_tunable = aqr107_get_tunable,
.set_tunable = aqr107_set_tunable,
.name = "Aquantia AQR405",
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
- .ack_interrupt = aqr_ack_interrupt,
+ .handle_interrupt = aqr_handle_interrupt,
.read_status = aqr_read_status,
},
};
value = phy_read(phydev, AT803X_INTR_ENABLE);
if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ /* Clear any pending interrupts */
+ err = at803x_ack_interrupt(phydev);
+ if (err)
+ return err;
+
value |= AT803X_INTR_ENABLE_AUTONEG_ERR;
value |= AT803X_INTR_ENABLE_SPEED_CHANGED;
value |= AT803X_INTR_ENABLE_DUPLEX_CHANGED;
value |= AT803X_INTR_ENABLE_LINK_SUCCESS;
err = phy_write(phydev, AT803X_INTR_ENABLE, value);
- }
- else
+ } else {
err = phy_write(phydev, AT803X_INTR_ENABLE, 0);
+ if (err)
+ return err;
+
+ /* Clear any pending interrupts */
+ err = at803x_ack_interrupt(phydev);
+ }
return err;
}
+static irqreturn_t at803x_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status, int_enabled;
+
+ irq_status = phy_read(phydev, AT803X_INTR_STATUS);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ /* Read the current enabled interrupts */
+ int_enabled = phy_read(phydev, AT803X_INTR_ENABLE);
+ if (int_enabled < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ /* See if this was one of our enabled interrupts */
+ if (!(irq_status & int_enabled))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
static void at803x_link_change_notify(struct phy_device *phydev)
{
/*
.resume = at803x_resume,
/* PHY_GBIT_FEATURES */
.read_status = at803x_read_status,
- .ack_interrupt = at803x_ack_interrupt,
.config_intr = at803x_config_intr,
+ .handle_interrupt = at803x_handle_interrupt,
.get_tunable = at803x_get_tunable,
.set_tunable = at803x_set_tunable,
.cable_test_start = at803x_cable_test_start,
.suspend = at803x_suspend,
.resume = at803x_resume,
/* PHY_BASIC_FEATURES */
- .ack_interrupt = at803x_ack_interrupt,
.config_intr = at803x_config_intr,
+ .handle_interrupt = at803x_handle_interrupt,
}, {
/* Qualcomm Atheros AR8031/AR8033 */
PHY_ID_MATCH_EXACT(ATH8031_PHY_ID),
/* PHY_GBIT_FEATURES */
.read_status = at803x_read_status,
.aneg_done = at803x_aneg_done,
- .ack_interrupt = &at803x_ack_interrupt,
.config_intr = &at803x_config_intr,
+ .handle_interrupt = at803x_handle_interrupt,
.get_tunable = at803x_get_tunable,
.set_tunable = at803x_set_tunable,
.cable_test_start = at803x_cable_test_start,
.suspend = at803x_suspend,
.resume = at803x_resume,
/* PHY_BASIC_FEATURES */
- .ack_interrupt = at803x_ack_interrupt,
.config_intr = at803x_config_intr,
+ .handle_interrupt = at803x_handle_interrupt,
.cable_test_start = at803x_cable_test_start,
.cable_test_get_status = at803x_cable_test_get_status,
}, {
.resume = at803x_resume,
.flags = PHY_POLL_CABLE_TEST,
/* PHY_BASIC_FEATURES */
- .ack_interrupt = &at803x_ack_interrupt,
.config_intr = &at803x_config_intr,
+ .handle_interrupt = at803x_handle_interrupt,
.cable_test_start = at803x_cable_test_start,
.cable_test_get_status = at803x_cable_test_get_status,
.read_status = at803x_read_status,
.name = "Broadcom Cygnus PHY",
/* PHY_GBIT_FEATURES */
.config_init = bcm_cygnus_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
.suspend = genphy_suspend,
.resume = bcm_cygnus_resume,
}, {
int bcm_phy_config_intr(struct phy_device *phydev)
{
- int reg;
+ int reg, err;
reg = phy_read(phydev, MII_BCM54XX_ECR);
if (reg < 0)
return reg;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = bcm_phy_ack_intr(phydev);
+ if (err)
+ return err;
+
reg &= ~MII_BCM54XX_ECR_IM;
- else
+ err = phy_write(phydev, MII_BCM54XX_ECR, reg);
+ } else {
reg |= MII_BCM54XX_ECR_IM;
+ err = phy_write(phydev, MII_BCM54XX_ECR, reg);
+ if (err)
+ return err;
- return phy_write(phydev, MII_BCM54XX_ECR, reg);
+ err = bcm_phy_ack_intr(phydev);
+ }
+ return err;
}
EXPORT_SYMBOL_GPL(bcm_phy_config_intr);
+irqreturn_t bcm_phy_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status, irq_mask;
+
+ irq_status = phy_read(phydev, MII_BCM54XX_ISR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ /* If a bit from the Interrupt Mask register is set, the corresponding
+ * bit from the Interrupt Status register is masked. So read the IMR
+ * and then flip the bits to get the list of possible interrupt
+ * sources.
+ */
+ irq_mask = phy_read(phydev, MII_BCM54XX_IMR);
+ if (irq_mask < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+ irq_mask = ~irq_mask;
+
+ if (!(irq_status & irq_mask))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+EXPORT_SYMBOL_GPL(bcm_phy_handle_interrupt);
+
int bcm_phy_read_shadow(struct phy_device *phydev, u16 shadow)
{
phy_write(phydev, MII_BCM54XX_SHD, MII_BCM54XX_SHD_VAL(shadow));
int bcm_phy_ack_intr(struct phy_device *phydev);
int bcm_phy_config_intr(struct phy_device *phydev);
+irqreturn_t bcm_phy_handle_interrupt(struct phy_device *phydev);
int bcm_phy_enable_apd(struct phy_device *phydev, bool dll_pwr_down);
BCM54140_RDB_C_PWR_ISOLATE, 0);
}
-static int bcm54140_did_interrupt(struct phy_device *phydev)
+static irqreturn_t bcm54140_handle_interrupt(struct phy_device *phydev)
{
- int ret;
+ int irq_status, irq_mask;
+
+ irq_status = bcm_phy_read_rdb(phydev, BCM54140_RDB_ISR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ irq_mask = bcm_phy_read_rdb(phydev, BCM54140_RDB_IMR);
+ if (irq_mask < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+ irq_mask = ~irq_mask;
+
+ if (!(irq_status & irq_mask))
+ return IRQ_NONE;
- ret = bcm_phy_read_rdb(phydev, BCM54140_RDB_ISR);
+ phy_trigger_machine(phydev);
- return (ret < 0) ? 0 : ret;
+ return IRQ_HANDLED;
}
static int bcm54140_ack_intr(struct phy_device *phydev)
BCM54140_RDB_TOP_IMR_PORT0, BCM54140_RDB_TOP_IMR_PORT1,
BCM54140_RDB_TOP_IMR_PORT2, BCM54140_RDB_TOP_IMR_PORT3,
};
- int reg;
+ int reg, err;
if (priv->port >= ARRAY_SIZE(port_to_imr_bit))
return -EINVAL;
if (reg < 0)
return reg;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = bcm54140_ack_intr(phydev);
+ if (err)
+ return err;
+
reg &= ~port_to_imr_bit[priv->port];
- else
+ err = bcm54140_base_write_rdb(phydev, BCM54140_RDB_TOP_IMR, reg);
+ } else {
reg |= port_to_imr_bit[priv->port];
+ err = bcm54140_base_write_rdb(phydev, BCM54140_RDB_TOP_IMR, reg);
+ if (err)
+ return err;
+
+ err = bcm54140_ack_intr(phydev);
+ }
- return bcm54140_base_write_rdb(phydev, BCM54140_RDB_TOP_IMR, reg);
+ return err;
}
static int bcm54140_get_downshift(struct phy_device *phydev, u8 *data)
.flags = PHY_POLL_CABLE_TEST,
.features = PHY_GBIT_FEATURES,
.config_init = bcm54140_config_init,
- .did_interrupt = bcm54140_did_interrupt,
- .ack_interrupt = bcm54140_ack_intr,
+ .handle_interrupt = bcm54140_handle_interrupt,
.config_intr = bcm54140_config_intr,
.probe = bcm54140_probe,
.suspend = genphy_suspend,
if (reg < 0)
return reg;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = bcm_phy_ack_intr(phydev);
+ if (err)
+ return err;
+
reg &= ~MII_BCM63XX_IR_GMASK;
- else
+ err = phy_write(phydev, MII_BCM63XX_IR, reg);
+ } else {
reg |= MII_BCM63XX_IR_GMASK;
+ err = phy_write(phydev, MII_BCM63XX_IR, reg);
+ if (err)
+ return err;
+
+ err = bcm_phy_ack_intr(phydev);
+ }
- err = phy_write(phydev, MII_BCM63XX_IR, reg);
return err;
}
/* PHY_BASIC_FEATURES */
.flags = PHY_IS_INTERNAL,
.config_init = bcm63xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm63xx_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
}, {
/* same phy as above, with just a different OUI */
.phy_id = 0x002bdc00,
/* PHY_BASIC_FEATURES */
.flags = PHY_IS_INTERNAL,
.config_init = bcm63xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm63xx_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
} };
module_phy_driver(bcm63xx_driver);
if (reg < 0)
return reg;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = phy_read(phydev, BCM87XX_LASI_STATUS);
+ if (err)
+ return err;
+
reg |= 1;
- else
+ err = phy_write(phydev, BCM87XX_LASI_CONTROL, reg);
+ } else {
reg &= ~1;
+ err = phy_write(phydev, BCM87XX_LASI_CONTROL, reg);
+ if (err)
+ return err;
+
+ err = phy_read(phydev, BCM87XX_LASI_STATUS);
+ }
- err = phy_write(phydev, BCM87XX_LASI_CONTROL, reg);
return err;
}
-static int bcm87xx_did_interrupt(struct phy_device *phydev)
+static irqreturn_t bcm87xx_handle_interrupt(struct phy_device *phydev)
{
- int reg;
+ int irq_status;
- reg = phy_read(phydev, BCM87XX_LASI_STATUS);
-
- if (reg < 0) {
- phydev_err(phydev,
- "Error: Read of BCM87XX_LASI_STATUS failed: %d\n",
- reg);
- return 0;
+ irq_status = phy_read(phydev, BCM87XX_LASI_STATUS);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
}
- return (reg & 1) != 0;
-}
-static int bcm87xx_ack_interrupt(struct phy_device *phydev)
-{
- /* Reading the LASI status clears it. */
- bcm87xx_did_interrupt(phydev);
- return 0;
+ if (irq_status == 0)
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
static int bcm8706_match_phy_device(struct phy_device *phydev)
.config_init = bcm87xx_config_init,
.config_aneg = bcm87xx_config_aneg,
.read_status = bcm87xx_read_status,
- .ack_interrupt = bcm87xx_ack_interrupt,
.config_intr = bcm87xx_config_intr,
- .did_interrupt = bcm87xx_did_interrupt,
+ .handle_interrupt = bcm87xx_handle_interrupt,
.match_phy_device = bcm8706_match_phy_device,
}, {
.phy_id = PHY_ID_BCM8727,
.config_init = bcm87xx_config_init,
.config_aneg = bcm87xx_config_aneg,
.read_status = bcm87xx_read_status,
- .ack_interrupt = bcm87xx_ack_interrupt,
.config_intr = bcm87xx_config_intr,
- .did_interrupt = bcm87xx_did_interrupt,
+ .handle_interrupt = bcm87xx_handle_interrupt,
.match_phy_device = bcm8727_match_phy_device,
} };
if (reg < 0)
return reg;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = brcm_fet_ack_interrupt(phydev);
+ if (err)
+ return err;
+
reg &= ~MII_BRCM_FET_IR_MASK;
- else
+ err = phy_write(phydev, MII_BRCM_FET_INTREG, reg);
+ } else {
reg |= MII_BRCM_FET_IR_MASK;
+ err = phy_write(phydev, MII_BRCM_FET_INTREG, reg);
+ if (err)
+ return err;
+
+ err = brcm_fet_ack_interrupt(phydev);
+ }
- err = phy_write(phydev, MII_BRCM_FET_INTREG, reg);
return err;
}
+static irqreturn_t brcm_fet_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, MII_BRCM_FET_INTREG);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (irq_status == 0)
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
struct bcm53xx_phy_priv {
u64 *stats;
};
.name = "Broadcom BCM5411",
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
}, {
.phy_id = PHY_ID_BCM5421,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM5421",
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
}, {
.phy_id = PHY_ID_BCM54210E,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM54210E",
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
}, {
.phy_id = PHY_ID_BCM5461,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM5461",
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
}, {
.phy_id = PHY_ID_BCM54612E,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM54612E",
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
}, {
.phy_id = PHY_ID_BCM54616S,
.phy_id_mask = 0xfffffff0,
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.config_aneg = bcm54616s_config_aneg,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
.read_status = bcm54616s_read_status,
.probe = bcm54616s_probe,
}, {
.name = "Broadcom BCM5464",
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
}, {
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.config_aneg = bcm5481_config_aneg,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
}, {
.phy_id = PHY_ID_BCM54810,
.phy_id_mask = 0xfffffff0,
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.config_aneg = bcm5481_config_aneg,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
.suspend = genphy_suspend,
.resume = bcm54xx_resume,
}, {
/* PHY_GBIT_FEATURES */
.config_init = bcm54811_config_init,
.config_aneg = bcm5481_config_aneg,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
.suspend = genphy_suspend,
.resume = bcm54xx_resume,
}, {
/* PHY_GBIT_FEATURES */
.config_init = bcm5482_config_init,
.read_status = bcm5482_read_status,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
}, {
.phy_id = PHY_ID_BCM50610,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM50610",
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
}, {
.phy_id = PHY_ID_BCM50610M,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM50610M",
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
}, {
.phy_id = PHY_ID_BCM57780,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM57780",
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
}, {
.phy_id = PHY_ID_BCMAC131,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCMAC131",
/* PHY_BASIC_FEATURES */
.config_init = brcm_fet_config_init,
- .ack_interrupt = brcm_fet_ack_interrupt,
.config_intr = brcm_fet_config_intr,
+ .handle_interrupt = brcm_fet_handle_interrupt,
}, {
.phy_id = PHY_ID_BCM5241,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM5241",
/* PHY_BASIC_FEATURES */
.config_init = brcm_fet_config_init,
- .ack_interrupt = brcm_fet_ack_interrupt,
.config_intr = brcm_fet_config_intr,
+ .handle_interrupt = brcm_fet_handle_interrupt,
}, {
.phy_id = PHY_ID_BCM5395,
.phy_id_mask = 0xfffffff0,
.get_stats = bcm53xx_phy_get_stats,
.probe = bcm53xx_phy_probe,
.config_init = bcm54xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
}, {
.phy_id = PHY_ID_BCM89610,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM89610",
/* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
- .ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
+ .handle_interrupt = bcm_phy_handle_interrupt,
} };
module_phy_driver(broadcom_drivers);
{
int err;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = cis820x_ack_interrupt(phydev);
+ if (err)
+ return err;
+
err = phy_write(phydev, MII_CIS8201_IMASK,
MII_CIS8201_IMASK_MASK);
- else
+ } else {
err = phy_write(phydev, MII_CIS8201_IMASK, 0);
+ if (err)
+ return err;
+
+ err = cis820x_ack_interrupt(phydev);
+ }
return err;
}
+static irqreturn_t cis820x_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, MII_CIS8201_ISTAT);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & MII_CIS8201_IMASK_MASK))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
/* Cicada 8201, a.k.a Vitesse VSC8201 */
static struct phy_driver cis820x_driver[] = {
{
.phy_id_mask = 0x000ffff0,
/* PHY_GBIT_FEATURES */
.config_init = &cis820x_config_init,
- .ack_interrupt = &cis820x_ack_interrupt,
.config_intr = &cis820x_config_intr,
+ .handle_interrupt = &cis820x_handle_interrupt,
}, {
.phy_id = 0x000fc440,
.name = "Cicada Cis8204",
.phy_id_mask = 0x000fffc0,
/* PHY_GBIT_FEATURES */
.config_init = &cis820x_config_init,
- .ack_interrupt = &cis820x_ack_interrupt,
.config_intr = &cis820x_config_intr,
+ .handle_interrupt = &cis820x_handle_interrupt,
} };
module_phy_driver(cis820x_driver);
#define MII_DM9161_INTR_STOP \
(MII_DM9161_INTR_DPLX_MASK | MII_DM9161_INTR_SPD_MASK \
| MII_DM9161_INTR_LINK_MASK | MII_DM9161_INTR_MASK)
+#define MII_DM9161_INTR_CHANGE \
+ (MII_DM9161_INTR_DPLX_CHANGE | \
+ MII_DM9161_INTR_SPD_CHANGE | \
+ MII_DM9161_INTR_LINK_CHANGE)
/* DM9161 10BT Configuration/Status */
#define MII_DM9161_10BTCSR 0x12
MODULE_LICENSE("GPL");
+static int dm9161_ack_interrupt(struct phy_device *phydev)
+{
+ int err = phy_read(phydev, MII_DM9161_INTR);
+
+ return (err < 0) ? err : 0;
+}
+
#define DM9161_DELAY 1
static int dm9161_config_intr(struct phy_device *phydev)
{
- int temp;
+ int temp, err;
temp = phy_read(phydev, MII_DM9161_INTR);
if (temp < 0)
return temp;
- if (PHY_INTERRUPT_ENABLED == phydev->interrupts)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = dm9161_ack_interrupt(phydev);
+ if (err)
+ return err;
+
temp &= ~(MII_DM9161_INTR_STOP);
- else
+ err = phy_write(phydev, MII_DM9161_INTR, temp);
+ } else {
temp |= MII_DM9161_INTR_STOP;
+ err = phy_write(phydev, MII_DM9161_INTR, temp);
+ if (err)
+ return err;
+
+ err = dm9161_ack_interrupt(phydev);
+ }
+
+ return err;
+}
- temp = phy_write(phydev, MII_DM9161_INTR, temp);
+static irqreturn_t dm9161_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, MII_DM9161_INTR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
- return temp;
+ if (!(irq_status & MII_DM9161_INTR_CHANGE))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
static int dm9161_config_aneg(struct phy_device *phydev)
return phy_write(phydev, MII_BMCR, BMCR_ANENABLE);
}
-static int dm9161_ack_interrupt(struct phy_device *phydev)
-{
- int err = phy_read(phydev, MII_DM9161_INTR);
-
- return (err < 0) ? err : 0;
-}
-
static struct phy_driver dm91xx_driver[] = {
{
.phy_id = 0x0181b880,
/* PHY_BASIC_FEATURES */
.config_init = dm9161_config_init,
.config_aneg = dm9161_config_aneg,
- .ack_interrupt = dm9161_ack_interrupt,
.config_intr = dm9161_config_intr,
+ .handle_interrupt = dm9161_handle_interrupt,
}, {
.phy_id = 0x0181b8b0,
.name = "Davicom DM9161B/C",
/* PHY_BASIC_FEATURES */
.config_init = dm9161_config_init,
.config_aneg = dm9161_config_aneg,
- .ack_interrupt = dm9161_ack_interrupt,
.config_intr = dm9161_config_intr,
+ .handle_interrupt = dm9161_handle_interrupt,
}, {
.phy_id = 0x0181b8a0,
.name = "Davicom DM9161A",
/* PHY_BASIC_FEATURES */
.config_init = dm9161_config_init,
.config_aneg = dm9161_config_aneg,
- .ack_interrupt = dm9161_ack_interrupt,
.config_intr = dm9161_config_intr,
+ .handle_interrupt = dm9161_handle_interrupt,
}, {
.phy_id = 0x00181b80,
.name = "Davicom DM9131",
.phy_id_mask = 0x0ffffff0,
/* PHY_BASIC_FEATURES */
- .ack_interrupt = dm9161_ack_interrupt,
.config_intr = dm9161_config_intr,
+ .handle_interrupt = dm9161_handle_interrupt,
} };
module_phy_driver(dm91xx_driver);
#define MII_DP83640_MISR_LINK_INT_EN 0x20
#define MII_DP83640_MISR_ED_INT_EN 0x40
#define MII_DP83640_MISR_LQ_INT_EN 0x80
+#define MII_DP83640_MISR_ANC_INT 0x400
+#define MII_DP83640_MISR_DUP_INT 0x800
+#define MII_DP83640_MISR_SPD_INT 0x1000
+#define MII_DP83640_MISR_LINK_INT 0x2000
+#define MII_DP83640_MISR_INT_MASK (MII_DP83640_MISR_ANC_INT |\
+ MII_DP83640_MISR_DUP_INT |\
+ MII_DP83640_MISR_SPD_INT |\
+ MII_DP83640_MISR_LINK_INT)
/* phyter seems to miss the mark by 16 ns */
#define ADJTIME_FIX 16
static int is_sync(struct sk_buff *skb, int type)
{
struct ptp_header *hdr;
- u8 msgtype;
hdr = ptp_parse_header(skb, type);
if (!hdr)
return 0;
- msgtype = ptp_get_msgtype(hdr, type);
-
- return (msgtype & 0xf) == 0;
+ return ptp_get_msgtype(hdr, type) == PTP_MSGTYPE_SYNC;
}
static void dp83640_free_clocks(void)
int err;
if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = dp83640_ack_interrupt(phydev);
+ if (err)
+ return err;
+
misr = phy_read(phydev, MII_DP83640_MISR);
if (misr < 0)
return misr;
MII_DP83640_MISR_DUP_INT_EN |
MII_DP83640_MISR_SPD_INT_EN |
MII_DP83640_MISR_LINK_INT_EN);
- return phy_write(phydev, MII_DP83640_MISR, misr);
+ err = phy_write(phydev, MII_DP83640_MISR, misr);
+ if (err)
+ return err;
+
+ return dp83640_ack_interrupt(phydev);
}
}
+static irqreturn_t dp83640_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, MII_DP83640_MISR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & MII_DP83640_MISR_INT_MASK))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
{
struct dp83640_private *dp83640 =
.remove = dp83640_remove,
.soft_reset = dp83640_soft_reset,
.config_init = dp83640_config_init,
- .ack_interrupt = dp83640_ack_interrupt,
.config_intr = dp83640_config_intr,
+ .handle_interrupt = dp83640_handle_interrupt,
};
static int __init dp83640_init(void)
u16 fx_sd_enable;
};
-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)
{
return phy_write(phydev, MII_DP83822_PHYSCR, physcr_status);
}
+static irqreturn_t dp83822_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ /* The MISR1 and MISR2 registers are holding the interrupt status in
+ * the upper half (15:8), while the lower half (7:0) is used for
+ * controlling the interrupt enable state of those individual interrupt
+ * sources. To determine the possible interrupt sources, just read the
+ * MISR* register and use it directly to know which interrupts have
+ * been enabled previously or not.
+ */
+ irq_status = phy_read(phydev, MII_DP83822_MISR1);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+ if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
+ goto trigger_machine;
+
+ irq_status = phy_read(phydev, MII_DP83822_MISR2);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+ if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
+ goto trigger_machine;
+
+ return IRQ_NONE;
+
+trigger_machine:
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
static int dp8382x_disable_wol(struct phy_device *phydev)
{
int value = DP83822_WOL_EN | DP83822_WOL_MAGIC_EN |
.read_status = dp83822_read_status, \
.get_wol = dp83822_get_wol, \
.set_wol = dp83822_set_wol, \
- .ack_interrupt = dp83822_ack_interrupt, \
.config_intr = dp83822_config_intr, \
+ .handle_interrupt = dp83822_handle_interrupt, \
.suspend = dp83822_suspend, \
.resume = dp83822_resume, \
}
.config_init = dp8382x_config_init, \
.get_wol = dp83822_get_wol, \
.set_wol = dp83822_set_wol, \
- .ack_interrupt = dp83822_ack_interrupt, \
.config_intr = dp83822_config_intr, \
+ .handle_interrupt = dp83822_handle_interrupt, \
.suspend = dp83822_suspend, \
.resume = dp83822_resume, \
}
DP83848_MISR_SPD_INT_EN | \
DP83848_MISR_LINK_INT_EN)
+#define DP83848_MISR_RHF_INT BIT(8)
+#define DP83848_MISR_FHF_INT BIT(9)
+#define DP83848_MISR_ANC_INT BIT(10)
+#define DP83848_MISR_DUP_INT BIT(11)
+#define DP83848_MISR_SPD_INT BIT(12)
+#define DP83848_MISR_LINK_INT BIT(13)
+#define DP83848_MISR_ED_INT BIT(14)
+
+#define DP83848_INT_MASK \
+ (DP83848_MISR_ANC_INT | \
+ DP83848_MISR_DUP_INT | \
+ DP83848_MISR_SPD_INT | \
+ DP83848_MISR_LINK_INT)
+
static int dp83848_ack_interrupt(struct phy_device *phydev)
{
int err = phy_read(phydev, DP83848_MISR);
return control;
if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ ret = dp83848_ack_interrupt(phydev);
+ if (ret)
+ return ret;
+
control |= DP83848_MICR_INT_OE;
control |= DP83848_MICR_INTEN;
ret = phy_write(phydev, DP83848_MISR, DP83848_INT_EN_MASK);
if (ret < 0)
return ret;
+
+ ret = phy_write(phydev, DP83848_MICR, control);
} else {
control &= ~DP83848_MICR_INTEN;
+ ret = phy_write(phydev, DP83848_MICR, control);
+ if (ret)
+ return ret;
+
+ ret = dp83848_ack_interrupt(phydev);
+ }
+
+ return ret;
+}
+
+static irqreturn_t dp83848_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, DP83848_MISR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
}
- return phy_write(phydev, DP83848_MICR, control);
+ if (!(irq_status & DP83848_INT_MASK))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
static int dp83848_config_init(struct phy_device *phydev)
.resume = genphy_resume, \
\
/* IRQ related */ \
- .ack_interrupt = dp83848_ack_interrupt, \
.config_intr = dp83848_config_intr, \
+ .handle_interrupt = dp83848_handle_interrupt, \
}
static struct phy_driver dp83848_driver[] = {
static int dp83867_config_intr(struct phy_device *phydev)
{
- int micr_status;
+ int micr_status, err;
if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = dp83867_ack_interrupt(phydev);
+ if (err)
+ return err;
+
micr_status = phy_read(phydev, MII_DP83867_MICR);
if (micr_status < 0)
return micr_status;
MII_DP83867_MICR_DUP_MODE_CHNG_INT_EN |
MII_DP83867_MICR_SLEEP_MODE_CHNG_INT_EN);
- return phy_write(phydev, MII_DP83867_MICR, micr_status);
+ err = phy_write(phydev, MII_DP83867_MICR, micr_status);
+ } else {
+ micr_status = 0x0;
+ err = phy_write(phydev, MII_DP83867_MICR, micr_status);
+ if (err)
+ return err;
+
+ err = dp83867_ack_interrupt(phydev);
}
- micr_status = 0x0;
- return phy_write(phydev, MII_DP83867_MICR, micr_status);
+ return err;
+}
+
+static irqreturn_t dp83867_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status, irq_enabled;
+
+ irq_status = phy_read(phydev, MII_DP83867_ISR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ irq_enabled = phy_read(phydev, MII_DP83867_MICR);
+ if (irq_enabled < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & irq_enabled))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
static int dp83867_read_status(struct phy_device *phydev)
.set_wol = dp83867_set_wol,
/* IRQ related */
- .ack_interrupt = dp83867_ack_interrupt,
.config_intr = dp83867_config_intr,
+ .handle_interrupt = dp83867_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
static int dp83869_config_intr(struct phy_device *phydev)
{
- int micr_status = 0;
+ int micr_status = 0, err;
if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = dp83869_ack_interrupt(phydev);
+ if (err)
+ return err;
+
micr_status = phy_read(phydev, MII_DP83869_MICR);
if (micr_status < 0)
return micr_status;
MII_DP83869_MICR_DUP_MODE_CHNG_INT_EN |
MII_DP83869_MICR_SLEEP_MODE_CHNG_INT_EN);
- return phy_write(phydev, MII_DP83869_MICR, micr_status);
+ err = phy_write(phydev, MII_DP83869_MICR, micr_status);
+ } else {
+ err = phy_write(phydev, MII_DP83869_MICR, micr_status);
+ if (err)
+ return err;
+
+ err = dp83869_ack_interrupt(phydev);
}
- return phy_write(phydev, MII_DP83869_MICR, micr_status);
+ return err;
+}
+
+static irqreturn_t dp83869_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status, irq_enabled;
+
+ irq_status = phy_read(phydev, MII_DP83869_ISR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ irq_enabled = phy_read(phydev, MII_DP83869_MICR);
+ if (irq_enabled < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & irq_enabled))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
static int dp83869_set_wol(struct phy_device *phydev,
.soft_reset = dp83869_phy_reset,
/* IRQ related */
- .ack_interrupt = dp83869_ack_interrupt,
.config_intr = dp83869_config_intr,
+ .handle_interrupt = dp83869_handle_interrupt,
.read_status = dp83869_read_status,
.get_tunable = dp83869_get_tunable,
int misr_status, err;
if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = dp83811_ack_interrupt(phydev);
+ if (err)
+ return err;
+
misr_status = phy_read(phydev, MII_DP83811_INT_STAT1);
if (misr_status < 0)
return misr_status;
return err;
err = phy_write(phydev, MII_DP83811_INT_STAT3, 0);
+ if (err < 0)
+ return err;
+
+ err = dp83811_ack_interrupt(phydev);
}
return err;
}
+static irqreturn_t dp83811_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ /* The INT_STAT registers 1, 2 and 3 are holding the interrupt status
+ * in the upper half (15:8), while the lower half (7:0) is used for
+ * controlling the interrupt enable state of those individual interrupt
+ * sources. To determine the possible interrupt sources, just read the
+ * INT_STAT* register and use it directly to know which interrupts have
+ * been enabled previously or not.
+ */
+ irq_status = phy_read(phydev, MII_DP83811_INT_STAT1);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+ if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
+ goto trigger_machine;
+
+ irq_status = phy_read(phydev, MII_DP83811_INT_STAT2);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+ if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
+ goto trigger_machine;
+
+ irq_status = phy_read(phydev, MII_DP83811_INT_STAT3);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+ if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
+ goto trigger_machine;
+
+ return IRQ_NONE;
+
+trigger_machine:
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
static int dp83811_config_aneg(struct phy_device *phydev)
{
int value, err;
.soft_reset = dp83811_phy_reset,
.get_wol = dp83811_get_wol,
.set_wol = dp83811_set_wol,
- .ack_interrupt = dp83811_ack_interrupt,
.config_intr = dp83811_config_intr,
+ .handle_interrupt = dp83811_handle_interrupt,
.suspend = dp83811_suspend,
.resume = dp83811_resume,
},
return phy_write(phydev, IP10XX_SPEC_CTRL_STATUS, c);
}
+static int ip101a_g_ack_interrupt(struct phy_device *phydev)
+{
+ int err = phy_read(phydev, IP101A_G_IRQ_CONF_STATUS);
+
+ if (err < 0)
+ return err;
+
+ return 0;
+}
+
static int ip101a_g_config_intr(struct phy_device *phydev)
{
u16 val;
+ int err;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = ip101a_g_ack_interrupt(phydev);
+ if (err)
+ return err;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
/* INTR pin used: Speed/link/duplex will cause an interrupt */
val = IP101A_G_IRQ_PIN_USED;
- else
+ err = phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, val);
+ } else {
val = IP101A_G_IRQ_ALL_MASK;
+ err = phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, val);
+ if (err)
+ return err;
+
+ err = ip101a_g_ack_interrupt(phydev);
+ }
- return phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, val);
+ return err;
}
-static int ip101a_g_did_interrupt(struct phy_device *phydev)
+static irqreturn_t ip101a_g_handle_interrupt(struct phy_device *phydev)
{
- int val = phy_read(phydev, IP101A_G_IRQ_CONF_STATUS);
+ int irq_status;
- if (val < 0)
- return 0;
+ irq_status = phy_read(phydev, IP101A_G_IRQ_CONF_STATUS);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
- return val & (IP101A_G_IRQ_SPEED_CHANGE |
- IP101A_G_IRQ_DUPLEX_CHANGE |
- IP101A_G_IRQ_LINK_CHANGE);
-}
+ if (!(irq_status & (IP101A_G_IRQ_SPEED_CHANGE |
+ IP101A_G_IRQ_DUPLEX_CHANGE |
+ IP101A_G_IRQ_LINK_CHANGE)))
+ return IRQ_NONE;
-static int ip101a_g_ack_interrupt(struct phy_device *phydev)
-{
- int err = phy_read(phydev, IP101A_G_IRQ_CONF_STATUS);
- if (err < 0)
- return err;
+ phy_trigger_machine(phydev);
- return 0;
+ return IRQ_HANDLED;
}
static struct phy_driver icplus_driver[] = {
/* PHY_BASIC_FEATURES */
.probe = ip101a_g_probe,
.config_intr = ip101a_g_config_intr,
- .did_interrupt = ip101a_g_did_interrupt,
- .ack_interrupt = ip101a_g_ack_interrupt,
+ .handle_interrupt = ip101a_g_handle_interrupt,
.config_init = &ip101a_g_config_init,
.suspend = genphy_suspend,
.resume = genphy_resume,
return (reg < 0) ? reg : 0;
}
-static int xway_gphy_did_interrupt(struct phy_device *phydev)
+static int xway_gphy_config_intr(struct phy_device *phydev)
{
- int reg;
+ u16 mask = 0;
+ int err;
- reg = phy_read(phydev, XWAY_MDIO_ISTAT);
- return reg & XWAY_MDIO_INIT_MASK;
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = xway_gphy_ack_interrupt(phydev);
+ if (err)
+ return err;
+
+ mask = XWAY_MDIO_INIT_MASK;
+ err = phy_write(phydev, XWAY_MDIO_IMASK, mask);
+ } else {
+ err = phy_write(phydev, XWAY_MDIO_IMASK, mask);
+ if (err)
+ return err;
+
+ err = xway_gphy_ack_interrupt(phydev);
+ }
+
+ return err;
}
-static int xway_gphy_config_intr(struct phy_device *phydev)
+static irqreturn_t xway_gphy_handle_interrupt(struct phy_device *phydev)
{
- u16 mask = 0;
+ int irq_status;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
- mask = XWAY_MDIO_INIT_MASK;
+ irq_status = phy_read(phydev, XWAY_MDIO_ISTAT);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & XWAY_MDIO_INIT_MASK))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
- return phy_write(phydev, XWAY_MDIO_IMASK, mask);
+ return IRQ_HANDLED;
}
static struct phy_driver xway_gphy[] = {
/* PHY_GBIT_FEATURES */
.config_init = xway_gphy_config_init,
.config_aneg = xway_gphy14_config_aneg,
- .ack_interrupt = xway_gphy_ack_interrupt,
- .did_interrupt = xway_gphy_did_interrupt,
+ .handle_interrupt = xway_gphy_handle_interrupt,
.config_intr = xway_gphy_config_intr,
.suspend = genphy_suspend,
.resume = genphy_resume,
/* PHY_BASIC_FEATURES */
.config_init = xway_gphy_config_init,
.config_aneg = xway_gphy14_config_aneg,
- .ack_interrupt = xway_gphy_ack_interrupt,
- .did_interrupt = xway_gphy_did_interrupt,
+ .handle_interrupt = xway_gphy_handle_interrupt,
.config_intr = xway_gphy_config_intr,
.suspend = genphy_suspend,
.resume = genphy_resume,
/* PHY_GBIT_FEATURES */
.config_init = xway_gphy_config_init,
.config_aneg = xway_gphy14_config_aneg,
- .ack_interrupt = xway_gphy_ack_interrupt,
- .did_interrupt = xway_gphy_did_interrupt,
+ .handle_interrupt = xway_gphy_handle_interrupt,
.config_intr = xway_gphy_config_intr,
.suspend = genphy_suspend,
.resume = genphy_resume,
/* PHY_BASIC_FEATURES */
.config_init = xway_gphy_config_init,
.config_aneg = xway_gphy14_config_aneg,
- .ack_interrupt = xway_gphy_ack_interrupt,
- .did_interrupt = xway_gphy_did_interrupt,
+ .handle_interrupt = xway_gphy_handle_interrupt,
.config_intr = xway_gphy_config_intr,
.suspend = genphy_suspend,
.resume = genphy_resume,
.name = "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.5 / v1.6",
/* PHY_GBIT_FEATURES */
.config_init = xway_gphy_config_init,
- .ack_interrupt = xway_gphy_ack_interrupt,
- .did_interrupt = xway_gphy_did_interrupt,
+ .handle_interrupt = xway_gphy_handle_interrupt,
.config_intr = xway_gphy_config_intr,
.suspend = genphy_suspend,
.resume = genphy_resume,
.name = "Intel XWAY PHY22F (PEF 7061) v1.5 / v1.6",
/* PHY_BASIC_FEATURES */
.config_init = xway_gphy_config_init,
- .ack_interrupt = xway_gphy_ack_interrupt,
- .did_interrupt = xway_gphy_did_interrupt,
+ .handle_interrupt = xway_gphy_handle_interrupt,
.config_intr = xway_gphy_config_intr,
.suspend = genphy_suspend,
.resume = genphy_resume,
.name = "Intel XWAY PHY11G (xRX v1.1 integrated)",
/* PHY_GBIT_FEATURES */
.config_init = xway_gphy_config_init,
- .ack_interrupt = xway_gphy_ack_interrupt,
- .did_interrupt = xway_gphy_did_interrupt,
+ .handle_interrupt = xway_gphy_handle_interrupt,
.config_intr = xway_gphy_config_intr,
.suspend = genphy_suspend,
.resume = genphy_resume,
.name = "Intel XWAY PHY22F (xRX v1.1 integrated)",
/* PHY_BASIC_FEATURES */
.config_init = xway_gphy_config_init,
- .ack_interrupt = xway_gphy_ack_interrupt,
- .did_interrupt = xway_gphy_did_interrupt,
+ .handle_interrupt = xway_gphy_handle_interrupt,
.config_intr = xway_gphy_config_intr,
.suspend = genphy_suspend,
.resume = genphy_resume,
.name = "Intel XWAY PHY11G (xRX v1.2 integrated)",
/* PHY_GBIT_FEATURES */
.config_init = xway_gphy_config_init,
- .ack_interrupt = xway_gphy_ack_interrupt,
- .did_interrupt = xway_gphy_did_interrupt,
+ .handle_interrupt = xway_gphy_handle_interrupt,
.config_intr = xway_gphy_config_intr,
.suspend = genphy_suspend,
.resume = genphy_resume,
.name = "Intel XWAY PHY22F (xRX v1.2 integrated)",
/* PHY_BASIC_FEATURES */
.config_init = xway_gphy_config_init,
- .ack_interrupt = xway_gphy_ack_interrupt,
- .did_interrupt = xway_gphy_did_interrupt,
+ .handle_interrupt = xway_gphy_handle_interrupt,
.config_intr = xway_gphy_config_intr,
.suspend = genphy_suspend,
.resume = genphy_resume,
#define MII_LXT970_ISR 18 /* Interrupt Status Register */
+#define MII_LXT970_IRS_MINT BIT(15)
+
#define MII_LXT970_CONFIG 19 /* Configuration Register */
/* ------------------------------------------------------------------------- */
#define MII_LXT971_IER_IEN 0x00f2
#define MII_LXT971_ISR 19 /* Interrupt Status Register */
+#define MII_LXT971_ISR_MASK 0x00f0
/* register definitions for the 973 */
#define MII_LXT973_PCR 16 /* Port Configuration Register */
static int lxt970_config_intr(struct phy_device *phydev)
{
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
- return phy_write(phydev, MII_LXT970_IER, MII_LXT970_IER_IEN);
- else
- return phy_write(phydev, MII_LXT970_IER, 0);
+ int err;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = lxt970_ack_interrupt(phydev);
+ if (err)
+ return err;
+
+ err = phy_write(phydev, MII_LXT970_IER, MII_LXT970_IER_IEN);
+ } else {
+ err = phy_write(phydev, MII_LXT970_IER, 0);
+ if (err)
+ return err;
+
+ err = lxt970_ack_interrupt(phydev);
+ }
+
+ return err;
+}
+
+static irqreturn_t lxt970_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ /* The interrupt status register is cleared by reading BMSR
+ * followed by MII_LXT970_ISR
+ */
+ irq_status = phy_read(phydev, MII_BMSR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ irq_status = phy_read(phydev, MII_LXT970_ISR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & MII_LXT970_IRS_MINT))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
static int lxt970_config_init(struct phy_device *phydev)
static int lxt971_config_intr(struct phy_device *phydev)
{
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
- return phy_write(phydev, MII_LXT971_IER, MII_LXT971_IER_IEN);
- else
- return phy_write(phydev, MII_LXT971_IER, 0);
+ int err;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = lxt971_ack_interrupt(phydev);
+ if (err)
+ return err;
+
+ err = phy_write(phydev, MII_LXT971_IER, MII_LXT971_IER_IEN);
+ } else {
+ err = phy_write(phydev, MII_LXT971_IER, 0);
+ if (err)
+ return err;
+
+ err = lxt971_ack_interrupt(phydev);
+ }
+
+ return err;
+}
+
+static irqreturn_t lxt971_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, MII_LXT971_ISR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & MII_LXT971_ISR_MASK))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
/*
.phy_id_mask = 0xfffffff0,
/* PHY_BASIC_FEATURES */
.config_init = lxt970_config_init,
- .ack_interrupt = lxt970_ack_interrupt,
.config_intr = lxt970_config_intr,
+ .handle_interrupt = lxt970_handle_interrupt,
}, {
.phy_id = 0x001378e0,
.name = "LXT971",
.phy_id_mask = 0xfffffff0,
/* PHY_BASIC_FEATURES */
- .ack_interrupt = lxt971_ack_interrupt,
.config_intr = lxt971_config_intr,
+ .handle_interrupt = lxt971_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
}, {
#define MII_M1111_HWCFG_MODE_FIBER_RGMII 0x3
#define MII_M1111_HWCFG_MODE_SGMII_NO_CLK 0x4
#define MII_M1111_HWCFG_MODE_RTBI 0x7
+#define MII_M1111_HWCFG_MODE_COPPER_1000X_AN 0x8
#define MII_M1111_HWCFG_MODE_COPPER_RTBI 0x9
#define MII_M1111_HWCFG_MODE_COPPER_RGMII 0xb
+#define MII_M1111_HWCFG_MODE_COPPER_1000X_NOAN 0xc
+#define MII_M1111_HWCFG_SERIAL_AN_BYPASS BIT(12)
#define MII_M1111_HWCFG_FIBER_COPPER_RES BIT(13)
#define MII_M1111_HWCFG_FIBER_COPPER_AUTO BIT(15)
{
int err;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = marvell_ack_interrupt(phydev);
+ if (err)
+ return err;
+
err = phy_write(phydev, MII_M1011_IMASK,
MII_M1011_IMASK_INIT);
- else
+ } else {
err = phy_write(phydev, MII_M1011_IMASK,
MII_M1011_IMASK_CLEAR);
+ if (err)
+ return err;
+
+ err = marvell_ack_interrupt(phydev);
+ }
return err;
}
+static irqreturn_t marvell_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, MII_M1011_IEVENT);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & MII_M1011_IMASK_INIT))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
static int marvell_set_polarity(struct phy_device *phydev, int polarity)
{
int reg;
return genphy_check_and_restart_aneg(phydev, changed);
}
+static int m88e1111_config_aneg(struct phy_device *phydev)
+{
+ int extsr = phy_read(phydev, MII_M1111_PHY_EXT_SR);
+ int err;
+
+ if (extsr < 0)
+ return extsr;
+
+ /* If not using SGMII or copper 1000BaseX modes, use normal process.
+ * Steps below are only required for these modes.
+ */
+ if (phydev->interface != PHY_INTERFACE_MODE_SGMII &&
+ (extsr & MII_M1111_HWCFG_MODE_MASK) !=
+ MII_M1111_HWCFG_MODE_COPPER_1000X_AN)
+ return marvell_config_aneg(phydev);
+
+ err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE);
+ if (err < 0)
+ goto error;
+
+ /* Configure the copper link first */
+ err = marvell_config_aneg(phydev);
+ if (err < 0)
+ goto error;
+
+ /* Do not touch the fiber page if we're in copper->sgmii mode */
+ if (phydev->interface == PHY_INTERFACE_MODE_SGMII)
+ return 0;
+
+ /* Then the fiber link */
+ err = marvell_set_page(phydev, MII_MARVELL_FIBER_PAGE);
+ if (err < 0)
+ goto error;
+
+ err = marvell_config_aneg_fiber(phydev);
+ if (err < 0)
+ goto error;
+
+ return marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE);
+
+error:
+ marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE);
+ return err;
+}
+
static int m88e1510_config_aneg(struct phy_device *phydev)
{
int err;
static int marvell_config_init(struct phy_device *phydev)
{
- /* Set defalut LED */
+ /* Set default LED */
marvell_config_led(phydev);
/* Set registers from marvell,reg-init DT property */
MII_M1111_HWCFG_FIBER_COPPER_AUTO);
}
+static int m88e1111_config_init_1000basex(struct phy_device *phydev)
+{
+ int extsr = phy_read(phydev, MII_M1111_PHY_EXT_SR);
+ int err, mode;
+
+ if (extsr < 0)
+ return extsr;
+
+ /* If using copper mode, ensure 1000BaseX auto-negotiation is enabled */
+ mode = extsr & MII_M1111_HWCFG_MODE_MASK;
+ if (mode == MII_M1111_HWCFG_MODE_COPPER_1000X_NOAN) {
+ err = phy_modify(phydev, MII_M1111_PHY_EXT_SR,
+ MII_M1111_HWCFG_MODE_MASK |
+ MII_M1111_HWCFG_SERIAL_AN_BYPASS,
+ MII_M1111_HWCFG_MODE_COPPER_1000X_AN |
+ MII_M1111_HWCFG_SERIAL_AN_BYPASS);
+ if (err < 0)
+ return err;
+ }
+ return 0;
+}
+
static int m88e1111_config_init(struct phy_device *phydev)
{
int err;
return err;
}
+ if (phydev->interface == PHY_INTERFACE_MODE_1000BASEX) {
+ err = m88e1111_config_init_1000basex(phydev);
+ if (err < 0)
+ return err;
+ }
+
err = marvell_of_reg_init(phydev);
if (err < 0)
return err;
return err;
/* PHY reset is necessary after changing MODE[2:0] */
- err = phy_modify(phydev, MII_88E1510_GEN_CTRL_REG_1, 0,
- MII_88E1510_GEN_CTRL_REG_1_RESET);
+ err = phy_set_bits(phydev, MII_88E1510_GEN_CTRL_REG_1,
+ MII_88E1510_GEN_CTRL_REG_1_RESET);
if (err < 0)
return err;
return (retval < 0) ? retval : (retval & MII_M1011_PHY_STATUS_RESOLVED);
}
-static int m88e1121_did_interrupt(struct phy_device *phydev)
-{
- int imask;
-
- imask = phy_read(phydev, MII_M1011_IEVENT);
-
- if (imask & MII_M1011_IMASK_INIT)
- return 1;
-
- return 0;
-}
-
static void m88e1318_get_wol(struct phy_device *phydev,
struct ethtool_wolinfo *wol)
{
__phy_read(phydev, MII_M1011_IEVENT);
/* Enable the WOL interrupt */
- err = __phy_modify(phydev, MII_88E1318S_PHY_CSIER, 0,
- MII_88E1318S_PHY_CSIER_WOL_EIE);
+ err = __phy_set_bits(phydev, MII_88E1318S_PHY_CSIER,
+ MII_88E1318S_PHY_CSIER_WOL_EIE);
if (err < 0)
goto error;
goto error;
/* Clear WOL status and enable magic packet matching */
- err = __phy_modify(phydev, MII_88E1318S_PHY_WOL_CTRL, 0,
- MII_88E1318S_PHY_WOL_CTRL_CLEAR_WOL_STATUS |
- MII_88E1318S_PHY_WOL_CTRL_MAGIC_PACKET_MATCH_ENABLE);
+ err = __phy_set_bits(phydev, MII_88E1318S_PHY_WOL_CTRL,
+ MII_88E1318S_PHY_WOL_CTRL_CLEAR_WOL_STATUS |
+ MII_88E1318S_PHY_WOL_CTRL_MAGIC_PACKET_MATCH_ENABLE);
if (err < 0)
goto error;
} else {
return bmsr;
if (bmcr & BMCR_ANENABLE) {
- ret = phy_modify(phydev, MII_BMCR, BMCR_ANENABLE, 0);
+ ret = phy_clear_bits(phydev, MII_BMCR, BMCR_ANENABLE);
if (ret < 0)
return ret;
ret = genphy_soft_reset(phydev);
.probe = marvell_probe,
.config_init = marvell_config_init,
.config_aneg = m88e1101_config_aneg,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
.probe = marvell_probe,
.config_init = m88e1111_config_init,
.config_aneg = marvell_config_aneg,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
/* PHY_GBIT_FEATURES */
.probe = marvell_probe,
.config_init = m88e1111_config_init,
- .config_aneg = marvell_config_aneg,
+ .config_aneg = m88e1111_config_aneg,
+ .read_status = marvell_read_status,
+ .config_intr = marvell_config_intr,
+ .handle_interrupt = marvell_handle_interrupt,
+ .resume = genphy_resume,
+ .suspend = genphy_suspend,
+ .read_page = marvell_read_page,
+ .write_page = marvell_write_page,
+ .get_sset_count = marvell_get_sset_count,
+ .get_strings = marvell_get_strings,
+ .get_stats = marvell_get_stats,
+ .get_tunable = m88e1111_get_tunable,
+ .set_tunable = m88e1111_set_tunable,
+ },
+ {
+ .phy_id = MARVELL_PHY_ID_88E1111_FINISAR,
+ .phy_id_mask = MARVELL_PHY_ID_MASK,
+ .name = "Marvell 88E1111 (Finisar)",
+ /* PHY_GBIT_FEATURES */
+ .probe = marvell_probe,
+ .config_init = m88e1111_config_init,
+ .config_aneg = m88e1111_config_aneg,
.read_status = marvell_read_status,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
.probe = marvell_probe,
.config_init = m88e1118_config_init,
.config_aneg = m88e1118_config_aneg,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
.config_init = marvell_config_init,
.config_aneg = m88e1121_config_aneg,
.read_status = marvell_read_status,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
- .did_interrupt = m88e1121_did_interrupt,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
.config_init = m88e1318_config_init,
.config_aneg = m88e1318_config_aneg,
.read_status = marvell_read_status,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
- .did_interrupt = m88e1121_did_interrupt,
+ .handle_interrupt = marvell_handle_interrupt,
.get_wol = m88e1318_get_wol,
.set_wol = m88e1318_set_wol,
.resume = genphy_resume,
.config_init = m88e1145_config_init,
.config_aneg = m88e1101_config_aneg,
.read_status = genphy_read_status,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
.probe = marvell_probe,
.config_init = m88e1149_config_init,
.config_aneg = m88e1118_config_aneg,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
.probe = marvell_probe,
.config_init = m88e1111_config_init,
.config_aneg = marvell_config_aneg,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
/* PHY_GBIT_FEATURES */
.probe = marvell_probe,
.config_init = m88e1116r_config_init,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
.config_init = m88e1510_config_init,
.config_aneg = m88e1510_config_aneg,
.read_status = marvell_read_status,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
- .did_interrupt = m88e1121_did_interrupt,
+ .handle_interrupt = marvell_handle_interrupt,
.get_wol = m88e1318_get_wol,
.set_wol = m88e1318_set_wol,
.resume = marvell_resume,
.config_init = marvell_config_init,
.config_aneg = m88e1510_config_aneg,
.read_status = marvell_read_status,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
- .did_interrupt = m88e1121_did_interrupt,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
.config_init = marvell_config_init,
.config_aneg = m88e1510_config_aneg,
.read_status = marvell_read_status,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
- .did_interrupt = m88e1121_did_interrupt,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
.config_init = m88e3016_config_init,
.aneg_done = marvell_aneg_done,
.read_status = marvell_read_status,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
- .did_interrupt = m88e1121_did_interrupt,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
.config_init = marvell_config_init,
.config_aneg = m88e6390_config_aneg,
.read_status = marvell_read_status,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
- .did_interrupt = m88e1121_did_interrupt,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
.config_init = marvell_config_init,
.config_aneg = m88e1510_config_aneg,
.read_status = marvell_read_status,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
- .did_interrupt = m88e1121_did_interrupt,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
.config_init = marvell_config_init,
.config_aneg = m88e1510_config_aneg,
.read_status = marvell_read_status,
- .ack_interrupt = marvell_ack_interrupt,
.config_intr = marvell_config_intr,
- .did_interrupt = m88e1121_did_interrupt,
+ .handle_interrupt = marvell_handle_interrupt,
.resume = genphy_resume,
.suspend = genphy_suspend,
.read_page = marvell_read_page,
{ MARVELL_PHY_ID_88E1101, MARVELL_PHY_ID_MASK },
{ MARVELL_PHY_ID_88E1112, MARVELL_PHY_ID_MASK },
{ MARVELL_PHY_ID_88E1111, MARVELL_PHY_ID_MASK },
+ { MARVELL_PHY_ID_88E1111_FINISAR, MARVELL_PHY_ID_MASK },
{ MARVELL_PHY_ID_88E1118, MARVELL_PHY_ID_MASK },
{ MARVELL_PHY_ID_88E1121R, MARVELL_PHY_ID_MASK },
{ MARVELL_PHY_ID_88E1145, MARVELL_PHY_ID_MASK },
#endif
/**
- * mdiobus_create_device_from_board_info - create a full MDIO device given
+ * mdiobus_create_device - create a full MDIO device given
* a mdio_board_info structure
* @bus: MDIO bus to create the devices on
* @bi: mdio_board_info structure describing the devices
/* de-assert bus level PHY GPIO reset */
gpiod = devm_gpiod_get_optional(&bus->dev, "reset", GPIOD_OUT_LOW);
if (IS_ERR(gpiod)) {
- dev_err(&bus->dev, "mii_bus %s couldn't get reset GPIO\n",
- bus->id);
+ err = dev_err_probe(&bus->dev, PTR_ERR(gpiod),
+ "mii_bus %s couldn't get reset GPIO\n",
+ bus->id);
device_del(&bus->dev);
- return PTR_ERR(gpiod);
+ return err;
} else if (gpiod) {
bus->reset_gpiod = gpiod;
int ret;
if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ /* Ack any pending IRQ */
+ ret = meson_gxl_ack_interrupt(phydev);
+ if (ret)
+ return ret;
+
val = INTSRC_ANEG_PR
| INTSRC_PARALLEL_FAULT
| INTSRC_ANEG_LP_ACK
| INTSRC_LINK_DOWN
| INTSRC_REMOTE_FAULT
| INTSRC_ANEG_COMPLETE;
+ ret = phy_write(phydev, INTSRC_MASK, val);
} else {
val = 0;
+ ret = phy_write(phydev, INTSRC_MASK, val);
+
+ /* Ack any pending IRQ */
+ ret = meson_gxl_ack_interrupt(phydev);
}
- /* Ack any pending IRQ */
- ret = meson_gxl_ack_interrupt(phydev);
- if (ret)
- return ret;
+ return ret;
+}
+
+static irqreturn_t meson_gxl_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, INTSRC_FLAG);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (irq_status == 0)
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
- return phy_write(phydev, INTSRC_MASK, val);
+ return IRQ_HANDLED;
}
static struct phy_driver meson_gxl_phy[] = {
.soft_reset = genphy_soft_reset,
.config_init = meson_gxl_config_init,
.read_status = meson_gxl_read_status,
- .ack_interrupt = meson_gxl_ack_interrupt,
.config_intr = meson_gxl_config_intr,
+ .handle_interrupt = meson_gxl_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
}, {
/* PHY_BASIC_FEATURES */
.flags = PHY_IS_INTERNAL,
.soft_reset = genphy_soft_reset,
- .ack_interrupt = meson_gxl_ack_interrupt,
.config_intr = meson_gxl_config_intr,
+ .handle_interrupt = meson_gxl_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
},
#define KSZPHY_INTCS_LINK_UP BIT(8)
#define KSZPHY_INTCS_ALL (KSZPHY_INTCS_LINK_UP |\
KSZPHY_INTCS_LINK_DOWN)
+#define KSZPHY_INTCS_LINK_DOWN_STATUS BIT(2)
+#define KSZPHY_INTCS_LINK_UP_STATUS BIT(0)
+#define KSZPHY_INTCS_STATUS (KSZPHY_INTCS_LINK_DOWN_STATUS |\
+ KSZPHY_INTCS_LINK_UP_STATUS)
/* PHY Control 1 */
#define MII_KSZPHY_CTRL_1 0x1e
static int kszphy_config_intr(struct phy_device *phydev)
{
const struct kszphy_type *type = phydev->drv->driver_data;
- int temp;
+ int temp, err;
u16 mask;
if (type && type->interrupt_level_mask)
phy_write(phydev, MII_KSZPHY_CTRL, temp);
/* enable / disable interrupts */
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = kszphy_ack_interrupt(phydev);
+ if (err)
+ return err;
+
temp = KSZPHY_INTCS_ALL;
- else
+ err = phy_write(phydev, MII_KSZPHY_INTCS, temp);
+ } else {
temp = 0;
+ err = phy_write(phydev, MII_KSZPHY_INTCS, temp);
+ if (err)
+ return err;
+
+ err = kszphy_ack_interrupt(phydev);
+ }
+
+ return err;
+}
+
+static irqreturn_t kszphy_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, MII_KSZPHY_INTCS);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & KSZPHY_INTCS_STATUS))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
- return phy_write(phydev, MII_KSZPHY_INTCS, temp);
+ return IRQ_HANDLED;
}
static int kszphy_rmii_clk_sel(struct phy_device *phydev, bool val)
/* PHY_BASIC_FEATURES */
.driver_data = &ks8737_type,
.config_init = kszphy_config_init,
- .ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
+ .handle_interrupt = kszphy_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
}, {
.driver_data = &ksz8021_type,
.probe = kszphy_probe,
.config_init = kszphy_config_init,
- .ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
+ .handle_interrupt = kszphy_handle_interrupt,
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
.driver_data = &ksz8021_type,
.probe = kszphy_probe,
.config_init = kszphy_config_init,
- .ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
+ .handle_interrupt = kszphy_handle_interrupt,
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
.probe = kszphy_probe,
.config_init = ksz8041_config_init,
.config_aneg = ksz8041_config_aneg,
- .ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
+ .handle_interrupt = kszphy_handle_interrupt,
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
.driver_data = &ksz8041_type,
.probe = kszphy_probe,
.config_init = kszphy_config_init,
- .ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
+ .handle_interrupt = kszphy_handle_interrupt,
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
.driver_data = &ksz8051_type,
.probe = kszphy_probe,
.config_init = kszphy_config_init,
- .ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
+ .handle_interrupt = kszphy_handle_interrupt,
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
.driver_data = &ksz8041_type,
.probe = kszphy_probe,
.config_init = kszphy_config_init,
- .ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
+ .handle_interrupt = kszphy_handle_interrupt,
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
.driver_data = &ksz8081_type,
.probe = kszphy_probe,
.config_init = ksz8081_config_init,
- .ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
+ .handle_interrupt = kszphy_handle_interrupt,
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
.phy_id_mask = MICREL_PHY_ID_MASK,
/* PHY_BASIC_FEATURES */
.config_init = ksz8061_config_init,
- .ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
+ .handle_interrupt = kszphy_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
}, {
.probe = kszphy_probe,
.get_features = ksz9031_get_features,
.config_init = ksz9021_config_init,
- .ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
+ .handle_interrupt = kszphy_handle_interrupt,
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
.config_init = ksz9031_config_init,
.soft_reset = genphy_soft_reset,
.read_status = ksz9031_read_status,
- .ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
+ .handle_interrupt = kszphy_handle_interrupt,
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
.probe = kszphy_probe,
.config_init = ksz9131_config_init,
.read_status = genphy_read_status,
- .ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
+ .handle_interrupt = kszphy_handle_interrupt,
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
LAN88XX_INT_MASK_LINK_CHANGE_);
} else {
rc = phy_write(phydev, LAN88XX_INT_MASK, 0);
+ if (rc)
+ return rc;
+
+ /* Ack interrupts after they have been disabled */
+ rc = phy_read(phydev, LAN88XX_INT_STS);
}
return rc < 0 ? rc : 0;
}
-static int lan88xx_phy_ack_interrupt(struct phy_device *phydev)
+static irqreturn_t lan88xx_handle_interrupt(struct phy_device *phydev)
{
- int rc = phy_read(phydev, LAN88XX_INT_STS);
+ int irq_status;
- return rc < 0 ? rc : 0;
+ irq_status = phy_read(phydev, LAN88XX_INT_STS);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & LAN88XX_INT_STS_LINK_CHANGE_))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
static int lan88xx_suspend(struct phy_device *phydev)
.config_init = lan88xx_config_init,
.config_aneg = lan88xx_config_aneg,
- .ack_interrupt = lan88xx_phy_ack_interrupt,
.config_intr = lan88xx_phy_config_intr,
+ .handle_interrupt = lan88xx_handle_interrupt,
.suspend = lan88xx_suspend,
.resume = genphy_resume,
rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, 0x7FFF);
rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE);
val = LAN87XX_MASK_LINK_UP | LAN87XX_MASK_LINK_DOWN;
- }
+ rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, val);
+ } else {
+ rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, val);
+ if (rc)
+ return rc;
- rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, val);
+ rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE);
+ }
return rc < 0 ? rc : 0;
}
-static int lan87xx_phy_ack_interrupt(struct phy_device *phydev)
+static irqreturn_t lan87xx_handle_interrupt(struct phy_device *phydev)
{
- int rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE);
+ int irq_status;
- return rc < 0 ? rc : 0;
+ irq_status = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (irq_status == 0)
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
static int lan87xx_config_init(struct phy_device *phydev)
.features = PHY_BASIC_T1_FEATURES,
.config_init = lan87xx_config_init,
- .config_aneg = genphy_config_aneg,
- .ack_interrupt = lan87xx_phy_ack_interrupt,
.config_intr = lan87xx_phy_config_intr,
+ .handle_interrupt = lan87xx_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
vsc8584_handle_macsec_interrupt(phydev);
if (irq_status & MII_VSC85XX_INT_MASK_LINK_CHG)
- phy_mac_interrupt(phydev);
+ phy_trigger_machine(phydev);
return IRQ_HANDLED;
}
return 0;
}
-static int vsc8584_did_interrupt(struct phy_device *phydev)
-{
- int rc = 0;
-
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
- rc = phy_read(phydev, MII_VSC85XX_INT_STATUS);
-
- return (rc < 0) ? 0 : rc & MII_VSC85XX_INT_MASK_MASK;
-}
-
static int vsc8514_config_pre_init(struct phy_device *phydev)
{
/* These are the settings to override the silicon default
int rc;
if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ rc = vsc85xx_ack_interrupt(phydev);
+ if (rc)
+ return rc;
+
vsc8584_config_macsec_intr(phydev);
vsc8584_config_ts_intr(phydev);
if (rc < 0)
return rc;
rc = phy_read(phydev, MII_VSC85XX_INT_STATUS);
+ if (rc < 0)
+ return rc;
+
+ rc = vsc85xx_ack_interrupt(phydev);
}
return rc;
}
+static irqreturn_t vsc85xx_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, MII_VSC85XX_INT_STATUS);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & MII_VSC85XX_INT_MASK_MASK))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
static int vsc85xx_config_aneg(struct phy_device *phydev)
{
int rc;
.config_init = &vsc85xx_config_init,
.config_aneg = &vsc85xx_config_aneg,
.read_status = &vsc85xx_read_status,
- .ack_interrupt = &vsc85xx_ack_interrupt,
+ .handle_interrupt = vsc85xx_handle_interrupt,
.config_intr = &vsc85xx_config_intr,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.config_aneg = &vsc85xx_config_aneg,
.aneg_done = &genphy_aneg_done,
.read_status = &vsc85xx_read_status,
- .ack_interrupt = &vsc85xx_ack_interrupt,
+ .handle_interrupt = vsc85xx_handle_interrupt,
.config_intr = &vsc85xx_config_intr,
- .did_interrupt = &vsc8584_did_interrupt,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.probe = &vsc8574_probe,
.config_init = &vsc8514_config_init,
.config_aneg = &vsc85xx_config_aneg,
.read_status = &vsc85xx_read_status,
- .ack_interrupt = &vsc85xx_ack_interrupt,
+ .handle_interrupt = vsc85xx_handle_interrupt,
.config_intr = &vsc85xx_config_intr,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.config_init = &vsc85xx_config_init,
.config_aneg = &vsc85xx_config_aneg,
.read_status = &vsc85xx_read_status,
- .ack_interrupt = &vsc85xx_ack_interrupt,
+ .handle_interrupt = vsc85xx_handle_interrupt,
.config_intr = &vsc85xx_config_intr,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.config_init = &vsc85xx_config_init,
.config_aneg = &vsc85xx_config_aneg,
.read_status = &vsc85xx_read_status,
- .ack_interrupt = &vsc85xx_ack_interrupt,
+ .handle_interrupt = vsc85xx_handle_interrupt,
.config_intr = &vsc85xx_config_intr,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.config_init = &vsc85xx_config_init,
.config_aneg = &vsc85xx_config_aneg,
.read_status = &vsc85xx_read_status,
- .ack_interrupt = &vsc85xx_ack_interrupt,
+ .handle_interrupt = vsc85xx_handle_interrupt,
.config_intr = &vsc85xx_config_intr,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.config_init = &vsc85xx_config_init,
.config_aneg = &vsc85xx_config_aneg,
.read_status = &vsc85xx_read_status,
- .ack_interrupt = &vsc85xx_ack_interrupt,
+ .handle_interrupt = vsc85xx_handle_interrupt,
.config_intr = &vsc85xx_config_intr,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.config_init = &vsc8584_config_init,
.config_aneg = &vsc85xx_config_aneg,
.read_status = &vsc85xx_read_status,
- .ack_interrupt = &vsc85xx_ack_interrupt,
+ .handle_interrupt = vsc85xx_handle_interrupt,
.config_intr = &vsc85xx_config_intr,
- .did_interrupt = &vsc8584_did_interrupt,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.probe = &vsc8574_probe,
.config_init = &vsc8584_config_init,
.config_aneg = &vsc85xx_config_aneg,
.read_status = &vsc85xx_read_status,
- .ack_interrupt = &vsc85xx_ack_interrupt,
+ .handle_interrupt = vsc85xx_handle_interrupt,
.config_intr = &vsc85xx_config_intr,
- .did_interrupt = &vsc8584_did_interrupt,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.probe = &vsc8584_probe,
.aneg_done = &genphy_aneg_done,
.read_status = &vsc85xx_read_status,
.handle_interrupt = &vsc8584_handle_interrupt,
- .ack_interrupt = &vsc85xx_ack_interrupt,
.config_intr = &vsc85xx_config_intr,
- .did_interrupt = &vsc8584_did_interrupt,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.probe = &vsc8574_probe,
.config_aneg = &vsc85xx_config_aneg,
.aneg_done = &genphy_aneg_done,
.read_status = &vsc85xx_read_status,
- .ack_interrupt = &vsc85xx_ack_interrupt,
+ .handle_interrupt = vsc85xx_handle_interrupt,
.config_intr = &vsc85xx_config_intr,
- .did_interrupt = &vsc8584_did_interrupt,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.probe = &vsc8574_probe,
.aneg_done = &genphy_aneg_done,
.read_status = &vsc85xx_read_status,
.handle_interrupt = &vsc8584_handle_interrupt,
- .ack_interrupt = &vsc85xx_ack_interrupt,
.config_intr = &vsc85xx_config_intr,
- .did_interrupt = &vsc8584_did_interrupt,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.probe = &vsc8584_probe,
.aneg_done = &genphy_aneg_done,
.read_status = &vsc85xx_read_status,
.handle_interrupt = &vsc8584_handle_interrupt,
- .ack_interrupt = &vsc85xx_ack_interrupt,
.config_intr = &vsc85xx_config_intr,
- .did_interrupt = &vsc8584_did_interrupt,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.probe = &vsc8584_probe,
.aneg_done = &genphy_aneg_done,
.read_status = &vsc85xx_read_status,
.handle_interrupt = &vsc8584_handle_interrupt,
- .ack_interrupt = &vsc85xx_ack_interrupt,
.config_intr = &vsc85xx_config_intr,
- .did_interrupt = &vsc8584_did_interrupt,
.suspend = &genphy_suspend,
.resume = &genphy_resume,
.probe = &vsc8584_probe,
phy_ts_base_write(phydev, MSCC_EXT_PAGE_ACCESS, MSCC_PHY_PAGE_1588);
- if (!cond || (cond && upper))
+ if (!cond || upper)
phy_ts_base_write(phydev, MSCC_PHY_TS_CSR_DATA_MSB, upper);
phy_ts_base_write(phydev, MSCC_PHY_TS_CSR_DATA_LSB, lower);
{
struct vsc8531_private *vsc8531 = phydev->priv;
bool base = phydev->mdio.addr == vsc8531->ts_base_addr;
- enum vsc85xx_ptp_msg_type msgs[] = {
- PTP_MSG_TYPE_SYNC,
- PTP_MSG_TYPE_DELAY_REQ
+ u8 msgs[] = {
+ PTP_MSGTYPE_SYNC,
+ PTP_MSGTYPE_DELAY_REQ
};
u32 val;
u8 i;
static int vsc85xx_ptp_conf(struct phy_device *phydev, enum ts_blk blk,
bool one_step, bool enable)
{
- enum vsc85xx_ptp_msg_type msgs[] = {
- PTP_MSG_TYPE_SYNC,
- PTP_MSG_TYPE_DELAY_REQ
+ u8 msgs[] = {
+ PTP_MSGTYPE_SYNC,
+ PTP_MSGTYPE_DELAY_REQ
};
u32 val;
u8 i;
if (blk == INGRESS)
vsc85xx_ts_ptp_action_flow(phydev, blk, msgs[i],
PTP_WRITE_NS);
- else if (msgs[i] == PTP_MSG_TYPE_SYNC && one_step)
+ else if (msgs[i] == PTP_MSGTYPE_SYNC && one_step)
/* no need to know Sync t when sending in one_step */
vsc85xx_ts_ptp_action_flow(phydev, blk, msgs[i],
PTP_WRITE_1588);
int vsc8584_ptp_init(struct phy_device *phydev)
{
switch (phydev->phy_id & phydev->drv->phy_id_mask) {
+ case PHY_ID_VSC8572:
+ case PHY_ID_VSC8574:
case PHY_ID_VSC8575:
case PHY_ID_VSC8582:
case PHY_ID_VSC8584:
PTP_SAVE_IN_TS_FIFO = 11, /* invalid when writing in reg */
};
-enum vsc85xx_ptp_msg_type {
- PTP_MSG_TYPE_SYNC,
- PTP_MSG_TYPE_DELAY_REQ,
-};
-
struct vsc85xx_ptphdr {
u8 tsmt; /* transportSpecific | messageType */
u8 ver; /* reserved0 | versionPTP */
phy_write(phydev, NS_EXP_MEM_DATA, data);
}
-static int ns_config_intr(struct phy_device *phydev)
-{
- int err;
-
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
- err = phy_write(phydev, DP83865_INT_MASK,
- DP83865_INT_MASK_DEFAULT);
- else
- err = phy_write(phydev, DP83865_INT_MASK, 0);
-
- return err;
-}
-
static int ns_ack_interrupt(struct phy_device *phydev)
{
int ret = phy_read(phydev, DP83865_INT_STATUS);
return ret;
}
+static irqreturn_t ns_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, DP83865_INT_STATUS);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & DP83865_INT_MASK_DEFAULT))
+ return IRQ_NONE;
+
+ /* clear the interrupt */
+ phy_write(phydev, DP83865_INT_CLEAR, irq_status & ~0x7);
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
+static int ns_config_intr(struct phy_device *phydev)
+{
+ int err;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = ns_ack_interrupt(phydev);
+ if (err)
+ return err;
+
+ err = phy_write(phydev, DP83865_INT_MASK,
+ DP83865_INT_MASK_DEFAULT);
+ } else {
+ err = phy_write(phydev, DP83865_INT_MASK, 0);
+ if (err)
+ return err;
+
+ err = ns_ack_interrupt(phydev);
+ }
+
+ return err;
+}
+
static void ns_giga_speed_fallback(struct phy_device *phydev, int mode)
{
int bmcr = phy_read(phydev, MII_BMCR);
.name = "NatSemi DP83865",
/* PHY_GBIT_FEATURES */
.config_init = ns_config_init,
- .ack_interrupt = ns_ack_interrupt,
.config_intr = ns_config_intr,
+ .handle_interrupt = ns_handle_interrupt,
} };
module_phy_driver(dp83865_driver);
#define MII_CFG2_SLEEP_REQUEST_TO_16MS 0x3
#define MII_INTSRC 21
+#define MII_INTSRC_LINK_FAIL BIT(10)
+#define MII_INTSRC_LINK_UP BIT(9)
+#define MII_INTSRC_MASK (MII_INTSRC_LINK_FAIL | MII_INTSRC_LINK_UP)
#define MII_INTSRC_TEMP_ERR BIT(1)
#define MII_INTSRC_UV_ERR BIT(3)
static int tja11xx_config_intr(struct phy_device *phydev)
{
int value = 0;
+ int err;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = tja11xx_ack_interrupt(phydev);
+ if (err)
+ return err;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
value = MII_INTEN_LINK_FAIL | MII_INTEN_LINK_UP;
+ err = phy_write(phydev, MII_INTEN, value);
+ } else {
+ err = phy_write(phydev, MII_INTEN, value);
+ if (err)
+ return err;
+
+ err = tja11xx_ack_interrupt(phydev);
+ }
+
+ return err;
+}
+
+static irqreturn_t tja11xx_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, MII_INTSRC);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & MII_INTSRC_MASK))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
- return phy_write(phydev, MII_INTEN, value);
+ return IRQ_HANDLED;
}
static int tja11xx_cable_test_start(struct phy_device *phydev)
.get_sset_count = tja11xx_get_sset_count,
.get_strings = tja11xx_get_strings,
.get_stats = tja11xx_get_stats,
- .ack_interrupt = tja11xx_ack_interrupt,
.config_intr = tja11xx_config_intr,
+ .handle_interrupt = tja11xx_handle_interrupt,
.cable_test_start = tja11xx_cable_test_start,
.cable_test_get_status = tja11xx_cable_test_get_status,
}, {
.get_sset_count = tja11xx_get_sset_count,
.get_strings = tja11xx_get_strings,
.get_stats = tja11xx_get_stats,
- .ack_interrupt = tja11xx_ack_interrupt,
.config_intr = tja11xx_config_intr,
+ .handle_interrupt = tja11xx_handle_interrupt,
.cable_test_start = tja11xx_cable_test_start,
.cable_test_get_status = tja11xx_cable_test_get_status,
}
#include <linux/phy.h>
/**
- * genphy_c45_setup_forced - configures a forced speed
+ * genphy_c45_pma_setup_forced - configures a forced speed
* @phydev: target phy_device struct
*/
int genphy_c45_pma_setup_forced(struct phy_device *phydev)
}
EXPORT_SYMBOL(phy_print_status);
-/**
- * phy_clear_interrupt - Ack the phy device's interrupt
- * @phydev: the phy_device struct
- *
- * If the @phydev driver has an ack_interrupt function, call it to
- * ack and clear the phy device's interrupt.
- *
- * Returns 0 on success or < 0 on error.
- */
-static int phy_clear_interrupt(struct phy_device *phydev)
-{
- if (phydev->drv->ack_interrupt)
- return phydev->drv->ack_interrupt(phydev);
-
- return 0;
-}
-
/**
* phy_config_interrupt - configure the PHY device for the requested interrupts
* @phydev: the phy_device struct
EXPORT_SYMBOL(phy_queue_state_machine);
/**
- * phy_queue_state_machine - Trigger the state machine to run now
+ * phy_trigger_machine - Trigger the state machine to run now
*
* @phydev: the phy_device struct
*/
-static void phy_trigger_machine(struct phy_device *phydev)
+void phy_trigger_machine(struct phy_device *phydev)
{
phy_queue_state_machine(phydev, 0);
}
+EXPORT_SYMBOL(phy_trigger_machine);
static void phy_abort_cable_test(struct phy_device *phydev)
{
* Must not be called from interrupt context, or while the
* phydev->lock is held.
*/
-static void phy_error(struct phy_device *phydev)
+void phy_error(struct phy_device *phydev)
{
WARN_ON(1);
phy_trigger_machine(phydev);
}
+EXPORT_SYMBOL(phy_error);
/**
* phy_disable_interrupts - Disable the PHY interrupts from the PHY side
*/
int phy_disable_interrupts(struct phy_device *phydev)
{
- int err;
-
/* Disable PHY interrupts */
- err = phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED);
- if (err)
- return err;
-
- /* Clear the interrupt */
- return phy_clear_interrupt(phydev);
+ return phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED);
}
/**
struct phy_device *phydev = phy_dat;
struct phy_driver *drv = phydev->drv;
- if (drv->handle_interrupt)
- return drv->handle_interrupt(phydev);
-
- if (drv->did_interrupt && !drv->did_interrupt(phydev))
- return IRQ_NONE;
-
- /* reschedule state queue work to run as soon as possible */
- phy_trigger_machine(phydev);
-
- /* did_interrupt() may have cleared the interrupt already */
- if (!drv->did_interrupt && phy_clear_interrupt(phydev)) {
- phy_error(phydev);
- return IRQ_NONE;
- }
-
- return IRQ_HANDLED;
+ return drv->handle_interrupt(phydev);
}
/**
*/
static int phy_enable_interrupts(struct phy_device *phydev)
{
- int err = phy_clear_interrupt(phydev);
-
- if (err < 0)
- return err;
-
return phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED);
}
}
EXPORT_SYMBOL(phy_attached_info);
-#define ATTACHED_FMT "attached PHY driver [%s] (mii_bus:phy_addr=%s, irq=%s)"
+#define ATTACHED_FMT "attached PHY driver %s(mii_bus:phy_addr=%s, irq=%s)"
char *phy_attached_info_irq(struct phy_device *phydev)
{
char *irq_str;
void phy_attached_print(struct phy_device *phydev, const char *fmt, ...)
{
- const char *drv_name = phydev->drv ? phydev->drv->name : "unbound";
+ const char *unbound = phydev->drv ? "" : "[unbound] ";
char *irq_str = phy_attached_info_irq(phydev);
if (!fmt) {
- phydev_info(phydev, ATTACHED_FMT "\n",
- drv_name, phydev_name(phydev),
- irq_str);
+ phydev_info(phydev, ATTACHED_FMT "\n", unbound,
+ phydev_name(phydev), irq_str);
} else {
va_list ap;
- phydev_info(phydev, ATTACHED_FMT,
- drv_name, phydev_name(phydev),
- irq_str);
+ phydev_info(phydev, ATTACHED_FMT, unbound,
+ phydev_name(phydev), irq_str);
va_start(ap, fmt);
vprintk(fmt, ap);
}
EXPORT_SYMBOL(genphy_soft_reset);
+irqreturn_t genphy_handle_interrupt_no_ack(struct phy_device *phydev)
+{
+ /* It seems there are cases where the interrupts are handled by another
+ * entity (ie an IRQ controller embedded inside the PHY) and do not
+ * need any other interraction from phylib. In this case, just trigger
+ * the state machine directly.
+ */
+ phy_trigger_machine(phydev);
+
+ return 0;
+}
+EXPORT_SYMBOL(genphy_handle_interrupt_no_ack);
+
/**
* genphy_read_abilities - read PHY abilities from Clause 22 registers
* @phydev: target phy_device struct
#endif
/**
- * phy_get_delay_index - returns the index of the internal delay
+ * phy_get_internal_delay - returns the index of the internal delay
* @phydev: phy_device struct
* @dev: pointer to the devices device struct
* @delay_values: array of delays the PHY supports
static bool phy_drv_supports_irq(struct phy_driver *phydrv)
{
- return phydrv->config_intr && phydrv->ack_interrupt;
+ return phydrv->config_intr && phydrv->handle_interrupt;
}
/**
return 0;
}
+static void phy_shutdown(struct device *dev)
+{
+ struct phy_device *phydev = to_phy_device(dev);
+
+ phy_disable_interrupts(phydev);
+}
+
/**
* phy_driver_register - register a phy_driver with the PHY layer
* @new_driver: new phy_driver to register
new_driver->mdiodrv.driver.bus = &mdio_bus_type;
new_driver->mdiodrv.driver.probe = phy_probe;
new_driver->mdiodrv.driver.remove = phy_remove;
+ new_driver->mdiodrv.driver.shutdown = phy_shutdown;
new_driver->mdiodrv.driver.owner = owner;
new_driver->mdiodrv.driver.probe_type = PROBE_FORCE_SYNCHRONOUS;
static int phy_led_trigger_register(struct phy_device *phy,
struct phy_led_trigger *plt,
- unsigned int speed)
+ unsigned int speed,
+ const char *suffix)
{
plt->speed = speed;
- phy_led_trigger_format_name(phy, plt->name, sizeof(plt->name),
- phy_speed_to_str(speed));
+ phy_led_trigger_format_name(phy, plt->name, sizeof(plt->name), suffix);
plt->trigger.name = plt->name;
return led_trigger_register(&plt->trigger);
goto out_clear;
}
- phy_led_trigger_format_name(phy, phy->led_link_trigger->name,
- sizeof(phy->led_link_trigger->name),
- "link");
- phy->led_link_trigger->trigger.name = phy->led_link_trigger->name;
-
- err = led_trigger_register(&phy->led_link_trigger->trigger);
+ err = phy_led_trigger_register(phy, phy->led_link_trigger, 0, "link");
if (err)
goto out_free_link;
for (i = 0; i < phy->phy_num_led_triggers; i++) {
err = phy_led_trigger_register(phy, &phy->phy_led_triggers[i],
- speeds[i]);
+ speeds[i],
+ phy_speed_to_str(speeds[i]));
if (err)
goto out_unreg;
}
EXPORT_SYMBOL_GPL(phylink_ethtool_set_pauseparam);
/**
- * phylink_ethtool_get_eee_err() - read the energy efficient ethernet error
+ * phylink_get_eee_err() - read the energy efficient ethernet error
* counter
* @pl: a pointer to a &struct phylink returned from phylink_create().
*
changed = ret > 0;
+ /* Ensure ISOLATE bit is disabled */
bmcr = mode == MLO_AN_INBAND ? BMCR_ANENABLE : 0;
ret = mdiobus_modify(pcs->bus, pcs->addr, MII_BMCR,
- BMCR_ANENABLE, bmcr);
+ BMCR_ANENABLE | BMCR_ISOLATE, bmcr);
if (ret < 0)
return ret;
{
int err;
+ /* The Interrupt Source register is not self-clearing, bits 4 and 5 are
+ * cleared when MII_BMSR is read and bits 1 and 3 are cleared when
+ * MII_EXPANSION is read
+ */
err = phy_read(phydev, MII_QS6612_ISR);
if (err < 0)
static int qs6612_config_intr(struct phy_device *phydev)
{
int err;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ /* clear any interrupts before enabling them */
+ err = qs6612_ack_interrupt(phydev);
+ if (err)
+ return err;
+
err = phy_write(phydev, MII_QS6612_IMR,
MII_QS6612_IMR_INIT);
- else
+ } else {
err = phy_write(phydev, MII_QS6612_IMR, 0);
+ if (err)
+ return err;
+
+ /* clear any leftover interrupts */
+ err = qs6612_ack_interrupt(phydev);
+ }
return err;
}
+static irqreturn_t qs6612_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, MII_QS6612_ISR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & MII_QS6612_IMR_INIT))
+ return IRQ_NONE;
+
+ /* the interrupt source register is not self-clearing */
+ qs6612_ack_interrupt(phydev);
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
static struct phy_driver qs6612_driver[] = { {
.phy_id = 0x00181440,
.name = "QS6612",
.phy_id_mask = 0xfffffff0,
/* PHY_BASIC_FEATURES */
.config_init = qs6612_config_init,
- .ack_interrupt = qs6612_ack_interrupt,
.config_intr = qs6612_config_intr,
+ .handle_interrupt = qs6612_handle_interrupt,
} };
module_phy_driver(qs6612_driver);
#define RTL8211E_RX_DELAY BIT(11)
#define RTL8201F_ISR 0x1e
+#define RTL8201F_ISR_ANERR BIT(15)
+#define RTL8201F_ISR_DUPLEX BIT(13)
+#define RTL8201F_ISR_LINK BIT(11)
+#define RTL8201F_ISR_MASK (RTL8201F_ISR_ANERR | \
+ RTL8201F_ISR_DUPLEX | \
+ RTL8201F_ISR_LINK)
#define RTL8201F_IER 0x13
#define RTL8366RB_POWER_SAVE 0x15
static int rtl8201_config_intr(struct phy_device *phydev)
{
u16 val;
+ int err;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = rtl8201_ack_interrupt(phydev);
+ if (err)
+ return err;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
val = BIT(13) | BIT(12) | BIT(11);
- else
+ err = phy_write_paged(phydev, 0x7, RTL8201F_IER, val);
+ } else {
val = 0;
+ err = phy_write_paged(phydev, 0x7, RTL8201F_IER, val);
+ if (err)
+ return err;
- return phy_write_paged(phydev, 0x7, RTL8201F_IER, val);
+ err = rtl8201_ack_interrupt(phydev);
+ }
+
+ return err;
}
static int rtl8211b_config_intr(struct phy_device *phydev)
{
int err;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = rtl821x_ack_interrupt(phydev);
+ if (err)
+ return err;
+
err = phy_write(phydev, RTL821x_INER,
RTL8211B_INER_INIT);
- else
+ } else {
err = phy_write(phydev, RTL821x_INER, 0);
+ if (err)
+ return err;
+
+ err = rtl821x_ack_interrupt(phydev);
+ }
return err;
}
{
int err;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = rtl821x_ack_interrupt(phydev);
+ if (err)
+ return err;
+
err = phy_write(phydev, RTL821x_INER,
RTL8211E_INER_LINK_STATUS);
- else
+ } else {
err = phy_write(phydev, RTL821x_INER, 0);
+ if (err)
+ return err;
+
+ err = rtl821x_ack_interrupt(phydev);
+ }
return err;
}
static int rtl8211f_config_intr(struct phy_device *phydev)
{
u16 val;
+ int err;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ err = rtl8211f_ack_interrupt(phydev);
+ if (err)
+ return err;
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
val = RTL8211F_INER_LINK_STATUS;
- else
+ err = phy_write_paged(phydev, 0xa42, RTL821x_INER, val);
+ } else {
val = 0;
+ err = phy_write_paged(phydev, 0xa42, RTL821x_INER, val);
+ if (err)
+ return err;
- return phy_write_paged(phydev, 0xa42, RTL821x_INER, val);
+ err = rtl8211f_ack_interrupt(phydev);
+ }
+
+ return err;
+}
+
+static irqreturn_t rtl8201_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read(phydev, RTL8201F_ISR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & RTL8201F_ISR_MASK))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t rtl821x_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status, irq_enabled;
+
+ irq_status = phy_read(phydev, RTL821x_INSR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ irq_enabled = phy_read(phydev, RTL821x_INER);
+ if (irq_enabled < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & irq_enabled))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t rtl8211f_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status;
+
+ irq_status = phy_read_paged(phydev, 0xa43, RTL8211F_INSR);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & RTL8211F_INER_LINK_STATUS))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
static int rtl8211_config_aneg(struct phy_device *phydev)
}, {
PHY_ID_MATCH_EXACT(0x001cc816),
.name = "RTL8201F Fast Ethernet",
- .ack_interrupt = &rtl8201_ack_interrupt,
.config_intr = &rtl8201_config_intr,
+ .handle_interrupt = rtl8201_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
.read_page = rtl821x_read_page,
}, {
PHY_ID_MATCH_EXACT(0x001cc912),
.name = "RTL8211B Gigabit Ethernet",
- .ack_interrupt = &rtl821x_ack_interrupt,
.config_intr = &rtl8211b_config_intr,
+ .handle_interrupt = rtl821x_handle_interrupt,
.read_mmd = &genphy_read_mmd_unsupported,
.write_mmd = &genphy_write_mmd_unsupported,
.suspend = rtl8211b_suspend,
}, {
PHY_ID_MATCH_EXACT(0x001cc914),
.name = "RTL8211DN Gigabit Ethernet",
- .ack_interrupt = rtl821x_ack_interrupt,
.config_intr = rtl8211e_config_intr,
+ .handle_interrupt = rtl821x_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
.read_page = rtl821x_read_page,
PHY_ID_MATCH_EXACT(0x001cc915),
.name = "RTL8211E Gigabit Ethernet",
.config_init = &rtl8211e_config_init,
- .ack_interrupt = &rtl821x_ack_interrupt,
.config_intr = &rtl8211e_config_intr,
+ .handle_interrupt = rtl821x_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
.read_page = rtl821x_read_page,
PHY_ID_MATCH_EXACT(0x001cc916),
.name = "RTL8211F Gigabit Ethernet",
.config_init = &rtl8211f_config_init,
- .ack_interrupt = &rtl8211f_ack_interrupt,
+ .read_status = rtlgen_read_status,
.config_intr = &rtl8211f_config_intr,
+ .handle_interrupt = rtl8211f_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
.read_page = rtl821x_read_page,
.write_page = rtl821x_write_page,
.read_mmd = rtl822x_read_mmd,
.write_mmd = rtl822x_write_mmd,
+ }, {
+ PHY_ID_MATCH_EXACT(0x001cc838),
+ .name = "RTL8226-CG 2.5Gbps PHY",
+ .get_features = rtl822x_get_features,
+ .config_aneg = rtl822x_config_aneg,
+ .read_status = rtl822x_read_status,
+ .suspend = genphy_suspend,
+ .resume = rtlgen_resume,
+ .read_page = rtl821x_read_page,
+ .write_page = rtl821x_write_page,
+ }, {
+ PHY_ID_MATCH_EXACT(0x001cc848),
+ .name = "RTL8226B-CG_RTL8221B-CG 2.5Gbps PHY",
+ .get_features = rtl822x_get_features,
+ .config_aneg = rtl822x_config_aneg,
+ .read_status = rtl822x_read_status,
+ .suspend = genphy_suspend,
+ .resume = rtlgen_resume,
+ .read_page = rtl821x_read_page,
+ .write_page = rtl821x_write_page,
+ }, {
+ PHY_ID_MATCH_EXACT(0x001cc849),
+ .name = "RTL8221B-VB-CG 2.5Gbps PHY",
+ .get_features = rtl822x_get_features,
+ .config_aneg = rtl822x_config_aneg,
+ .read_status = rtl822x_read_status,
+ .suspend = genphy_suspend,
+ .resume = rtlgen_resume,
+ .read_page = rtl821x_read_page,
+ .write_page = rtl821x_write_page,
+ }, {
+ PHY_ID_MATCH_EXACT(0x001cc84a),
+ .name = "RTL8221B-VM-CG 2.5Gbps PHY",
+ .get_features = rtl822x_get_features,
+ .config_aneg = rtl822x_config_aneg,
+ .read_status = rtl822x_read_status,
+ .suspend = genphy_suspend,
+ .resume = rtlgen_resume,
+ .read_page = rtl821x_read_page,
+ .write_page = rtl821x_write_page,
}, {
PHY_ID_MATCH_EXACT(0x001cc961),
.name = "RTL8366RB Gigabit Ethernet",
* irq is requested and ACKed by reading the status register,
* which is done by the irqchip code.
*/
- .ack_interrupt = genphy_no_ack_interrupt,
.config_intr = genphy_no_config_intr,
+ .handle_interrupt = genphy_handle_interrupt_no_ack,
.suspend = genphy_suspend,
.resume = genphy_resume,
},
struct clk *refclk;
};
+static int smsc_phy_ack_interrupt(struct phy_device *phydev)
+{
+ int rc = phy_read(phydev, MII_LAN83C185_ISF);
+
+ return rc < 0 ? rc : 0;
+}
+
static int smsc_phy_config_intr(struct phy_device *phydev)
{
struct smsc_phy_priv *priv = phydev->priv;
int rc;
if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ rc = smsc_phy_ack_interrupt(phydev);
+ if (rc)
+ return rc;
+
intmask = MII_LAN83C185_ISF_INT4 | MII_LAN83C185_ISF_INT6;
if (priv->energy_enable)
intmask |= MII_LAN83C185_ISF_INT7;
- }
+ rc = phy_write(phydev, MII_LAN83C185_IM, intmask);
+ } else {
+ rc = phy_write(phydev, MII_LAN83C185_IM, intmask);
+ if (rc)
+ return rc;
- rc = phy_write(phydev, MII_LAN83C185_IM, intmask);
+ rc = smsc_phy_ack_interrupt(phydev);
+ }
return rc < 0 ? rc : 0;
}
-static int smsc_phy_ack_interrupt(struct phy_device *phydev)
+static irqreturn_t smsc_phy_handle_interrupt(struct phy_device *phydev)
{
- int rc = phy_read (phydev, MII_LAN83C185_ISF);
+ int irq_status, irq_enabled;
- return rc < 0 ? rc : 0;
+ irq_enabled = phy_read(phydev, MII_LAN83C185_IM);
+ if (irq_enabled < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ irq_status = phy_read(phydev, MII_LAN83C185_ISF);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & irq_enabled))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
static int smsc_phy_config_init(struct phy_device *phydev)
.soft_reset = smsc_phy_reset,
/* IRQ related */
- .ack_interrupt = smsc_phy_ack_interrupt,
.config_intr = smsc_phy_config_intr,
+ .handle_interrupt = smsc_phy_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
.soft_reset = smsc_phy_reset,
/* IRQ related */
- .ack_interrupt = smsc_phy_ack_interrupt,
.config_intr = smsc_phy_config_intr,
+ .handle_interrupt = smsc_phy_handle_interrupt,
/* Statistics */
.get_sset_count = smsc_get_sset_count,
.config_aneg = lan87xx_config_aneg,
/* IRQ related */
- .ack_interrupt = smsc_phy_ack_interrupt,
.config_intr = smsc_phy_config_intr,
+ .handle_interrupt = smsc_phy_handle_interrupt,
/* Statistics */
.get_sset_count = smsc_get_sset_count,
.config_init = lan911x_config_init,
/* IRQ related */
- .ack_interrupt = smsc_phy_ack_interrupt,
.config_intr = smsc_phy_config_intr,
+ .handle_interrupt = smsc_phy_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
.config_aneg = lan87xx_config_aneg_ext,
/* IRQ related */
- .ack_interrupt = smsc_phy_ack_interrupt,
.config_intr = smsc_phy_config_intr,
+ .handle_interrupt = smsc_phy_handle_interrupt,
/* Statistics */
.get_sset_count = smsc_get_sset_count,
.soft_reset = smsc_phy_reset,
/* IRQ related */
- .ack_interrupt = smsc_phy_ack_interrupt,
.config_intr = smsc_phy_config_intr,
+ .handle_interrupt = smsc_phy_handle_interrupt,
/* Statistics */
.get_sset_count = smsc_get_sset_count,
return 0;
}
+static int ste10Xp_ack_interrupt(struct phy_device *phydev)
+{
+ int err = phy_read(phydev, MII_XCIIS);
+
+ if (err < 0)
+ return err;
+
+ return 0;
+}
+
static int ste10Xp_config_intr(struct phy_device *phydev)
{
- int err, value;
+ int err;
if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ /* clear any pending interrupts */
+ err = ste10Xp_ack_interrupt(phydev);
+ if (err)
+ return err;
+
/* Enable all STe101P interrupts (PR12) */
err = phy_write(phydev, MII_XIE, MII_XIE_DEFAULT_MASK);
- /* clear any pending interrupts */
- if (err == 0) {
- value = phy_read(phydev, MII_XCIIS);
- if (value < 0)
- err = value;
- }
- } else
+ } else {
err = phy_write(phydev, MII_XIE, 0);
+ if (err)
+ return err;
+
+ err = ste10Xp_ack_interrupt(phydev);
+ }
return err;
}
-static int ste10Xp_ack_interrupt(struct phy_device *phydev)
+static irqreturn_t ste10Xp_handle_interrupt(struct phy_device *phydev)
{
- int err = phy_read(phydev, MII_XCIIS);
- if (err < 0)
- return err;
+ int irq_status;
- return 0;
+ irq_status = phy_read(phydev, MII_XCIIS);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & MII_XIE_DEFAULT_MASK))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
}
static struct phy_driver ste10xp_pdriver[] = {
.name = "STe101p",
/* PHY_BASIC_FEATURES */
.config_init = ste10Xp_config_init,
- .ack_interrupt = ste10Xp_ack_interrupt,
.config_intr = ste10Xp_config_intr,
+ .handle_interrupt = ste10Xp_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
}, {
.name = "STe100p",
/* PHY_BASIC_FEATURES */
.config_init = ste10Xp_config_init,
- .ack_interrupt = ste10Xp_ack_interrupt,
.config_intr = ste10Xp_config_intr,
+ .handle_interrupt = ste10Xp_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
} };
#define MII_VSC8244_ISTAT_SPEED 0x4000
#define MII_VSC8244_ISTAT_LINK 0x2000
#define MII_VSC8244_ISTAT_DUPLEX 0x1000
+#define MII_VSC8244_ISTAT_MASK (MII_VSC8244_ISTAT_SPEED | \
+ MII_VSC8244_ISTAT_LINK | \
+ MII_VSC8244_ISTAT_DUPLEX)
+
+#define MII_VSC8221_ISTAT_MASK MII_VSC8244_ISTAT_LINK
/* Vitesse Auxiliary Control/Status Register */
#define MII_VSC8244_AUX_CONSTAT 0x1c
return 0;
}
-static int vsc824x_ack_interrupt(struct phy_device *phydev)
-{
- int err = 0;
-
- /* Don't bother to ACK the interrupts if interrupts
- * are disabled. The 824x cannot clear the interrupts
- * if they are disabled.
- */
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
- err = phy_read(phydev, MII_VSC8244_ISTAT);
-
- return (err < 0) ? err : 0;
-}
-
static int vsc82xx_config_intr(struct phy_device *phydev)
{
int err;
if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ /* Don't bother to ACK the interrupts since the 824x cannot
+ * clear the interrupts if they are disabled.
+ */
err = phy_write(phydev, MII_VSC8244_IMASK,
(phydev->drv->phy_id == PHY_ID_VSC8234 ||
phydev->drv->phy_id == PHY_ID_VSC8244 ||
return err;
}
+static irqreturn_t vsc82xx_handle_interrupt(struct phy_device *phydev)
+{
+ int irq_status, irq_mask;
+
+ if (phydev->drv->phy_id == PHY_ID_VSC8244 ||
+ phydev->drv->phy_id == PHY_ID_VSC8572 ||
+ phydev->drv->phy_id == PHY_ID_VSC8601)
+ irq_mask = MII_VSC8244_ISTAT_MASK;
+ else
+ irq_mask = MII_VSC8221_ISTAT_MASK;
+
+ irq_status = phy_read(phydev, MII_VSC8244_ISTAT);
+ if (irq_status < 0) {
+ phy_error(phydev);
+ return IRQ_NONE;
+ }
+
+ if (!(irq_status & irq_mask))
+ return IRQ_NONE;
+
+ phy_trigger_machine(phydev);
+
+ return IRQ_HANDLED;
+}
+
static int vsc8221_config_init(struct phy_device *phydev)
{
int err;
/* PHY_GBIT_FEATURES */
.config_init = &vsc824x_config_init,
.config_aneg = &vsc82x4_config_aneg,
- .ack_interrupt = &vsc824x_ack_interrupt,
.config_intr = &vsc82xx_config_intr,
+ .handle_interrupt = &vsc82xx_handle_interrupt,
}, {
.phy_id = PHY_ID_VSC8244,
.name = "Vitesse VSC8244",
/* PHY_GBIT_FEATURES */
.config_init = &vsc824x_config_init,
.config_aneg = &vsc82x4_config_aneg,
- .ack_interrupt = &vsc824x_ack_interrupt,
.config_intr = &vsc82xx_config_intr,
+ .handle_interrupt = &vsc82xx_handle_interrupt,
}, {
.phy_id = PHY_ID_VSC8572,
.name = "Vitesse VSC8572",
/* PHY_GBIT_FEATURES */
.config_init = &vsc824x_config_init,
.config_aneg = &vsc82x4_config_aneg,
- .ack_interrupt = &vsc824x_ack_interrupt,
.config_intr = &vsc82xx_config_intr,
+ .handle_interrupt = &vsc82xx_handle_interrupt,
}, {
.phy_id = PHY_ID_VSC8601,
.name = "Vitesse VSC8601",
.phy_id_mask = 0x000ffff0,
/* PHY_GBIT_FEATURES */
.config_init = &vsc8601_config_init,
- .ack_interrupt = &vsc824x_ack_interrupt,
.config_intr = &vsc82xx_config_intr,
+ .handle_interrupt = &vsc82xx_handle_interrupt,
}, {
.phy_id = PHY_ID_VSC7385,
.name = "Vitesse VSC7385",
/* PHY_GBIT_FEATURES */
.config_init = &vsc824x_config_init,
.config_aneg = &vsc82x4_config_aneg,
- .ack_interrupt = &vsc824x_ack_interrupt,
.config_intr = &vsc82xx_config_intr,
+ .handle_interrupt = &vsc82xx_handle_interrupt,
}, {
/* Vitesse 8221 */
.phy_id = PHY_ID_VSC8221,
.name = "Vitesse VSC8221",
/* PHY_GBIT_FEATURES */
.config_init = &vsc8221_config_init,
- .ack_interrupt = &vsc824x_ack_interrupt,
.config_intr = &vsc82xx_config_intr,
+ .handle_interrupt = &vsc82xx_handle_interrupt,
}, {
/* Vitesse 8211 */
.phy_id = PHY_ID_VSC8211,
.name = "Vitesse VSC8211",
/* PHY_GBIT_FEATURES */
.config_init = &vsc8221_config_init,
- .ack_interrupt = &vsc824x_ack_interrupt,
.config_intr = &vsc82xx_config_intr,
+ .handle_interrupt = &vsc82xx_handle_interrupt,
} };
module_phy_driver(vsc82xx_driver);
* Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com>
*/
+#include <linux/ethtool.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/module.h>
}
#define TEAM_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
- NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
+ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \
NETIF_F_HIGHDMA | NETIF_F_LRO)
#define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
- NETIF_F_RXCSUM | NETIF_F_ALL_TSO)
+ NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE)
static void __team_compute_features(struct team *team)
{
team->dev->vlan_features = vlan_features;
team->dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
NETIF_F_HW_VLAN_CTAG_TX |
- NETIF_F_HW_VLAN_STAG_TX |
- NETIF_F_GSO_UDP_L4;
+ NETIF_F_HW_VLAN_STAG_TX;
team->dev->hard_header_len = max_hard_header_len;
team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_CTAG_FILTER;
- dev->hw_features |= NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4;
+ dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
dev->features |= dev->hw_features;
dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
}
#define TUN_FLOW_EXPIRE (3 * HZ)
-struct tun_pcpu_stats {
- u64_stats_t rx_packets;
- u64_stats_t rx_bytes;
- u64_stats_t tx_packets;
- u64_stats_t tx_bytes;
- struct u64_stats_sync syncp;
- u32 rx_dropped;
- u32 tx_dropped;
- u32 rx_frame_errors;
-};
-
/* A tun_file connects an open character device to a tuntap netdevice. It
* also contains all socket related structures (except sock_fprog and tap_filter)
* to serve as one transmit queue for tuntap device. The sock_fprog and
void *security;
u32 flow_count;
u32 rx_batched;
- struct tun_pcpu_stats __percpu *pcpu_stats;
+ atomic_long_t rx_frame_errors;
struct bpf_prog __rcu *xdp_prog;
struct tun_prog __rcu *steering_prog;
struct tun_prog __rcu *filter_prog;
return NETDEV_TX_OK;
drop:
- this_cpu_inc(tun->pcpu_stats->tx_dropped);
+ atomic_long_inc(&dev->tx_dropped);
skb_tx_error(skb);
kfree_skb(skb);
rcu_read_unlock();
static void
tun_net_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
{
- u32 rx_dropped = 0, tx_dropped = 0, rx_frame_errors = 0;
struct tun_struct *tun = netdev_priv(dev);
- struct tun_pcpu_stats *p;
- int i;
-
- for_each_possible_cpu(i) {
- u64 rxpackets, rxbytes, txpackets, txbytes;
- unsigned int start;
-
- p = per_cpu_ptr(tun->pcpu_stats, i);
- do {
- start = u64_stats_fetch_begin(&p->syncp);
- rxpackets = u64_stats_read(&p->rx_packets);
- rxbytes = u64_stats_read(&p->rx_bytes);
- txpackets = u64_stats_read(&p->tx_packets);
- txbytes = u64_stats_read(&p->tx_bytes);
- } while (u64_stats_fetch_retry(&p->syncp, start));
- stats->rx_packets += rxpackets;
- stats->rx_bytes += rxbytes;
- stats->tx_packets += txpackets;
- stats->tx_bytes += txbytes;
+ dev_get_tstats64(dev, stats);
- /* u32 counters */
- rx_dropped += p->rx_dropped;
- rx_frame_errors += p->rx_frame_errors;
- tx_dropped += p->tx_dropped;
- }
- stats->rx_dropped = rx_dropped;
- stats->rx_frame_errors = rx_frame_errors;
- stats->tx_dropped = tx_dropped;
+ stats->rx_frame_errors +=
+ (unsigned long)atomic_long_read(&tun->rx_frame_errors);
}
static int tun_xdp_set(struct net_device *dev, struct bpf_prog *prog,
void *frame = tun_xdp_to_ptr(xdp);
if (__ptr_ring_produce(&tfile->tx_ring, frame)) {
- this_cpu_inc(tun->pcpu_stats->tx_dropped);
+ atomic_long_inc(&dev->tx_dropped);
xdp_return_frame_rx_napi(xdp);
drops++;
}
.ndo_select_queue = tun_select_queue,
.ndo_features_check = passthru_features_check,
.ndo_set_rx_headroom = tun_set_headroom,
- .ndo_get_stats64 = tun_net_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_bpf = tun_xdp,
.ndo_xdp_xmit = tun_xdp_xmit,
.ndo_change_carrier = tun_net_change_carrier,
trace_xdp_exception(tun->dev, xdp_prog, act);
fallthrough;
case XDP_DROP:
- this_cpu_inc(tun->pcpu_stats->rx_dropped);
+ atomic_long_inc(&tun->dev->rx_dropped);
break;
}
size_t total_len = iov_iter_count(from);
size_t len = total_len, align = tun->align, linear;
struct virtio_net_hdr gso = { 0 };
- struct tun_pcpu_stats *stats;
int good_linear;
int copylen;
bool zerocopy = false;
*/
skb = tun_build_skb(tun, tfile, from, &gso, len, &skb_xdp);
if (IS_ERR(skb)) {
- this_cpu_inc(tun->pcpu_stats->rx_dropped);
+ atomic_long_inc(&tun->dev->rx_dropped);
return PTR_ERR(skb);
}
if (!skb)
if (IS_ERR(skb)) {
if (PTR_ERR(skb) != -EAGAIN)
- this_cpu_inc(tun->pcpu_stats->rx_dropped);
+ atomic_long_inc(&tun->dev->rx_dropped);
if (frags)
mutex_unlock(&tfile->napi_mutex);
return PTR_ERR(skb);
if (err) {
err = -EFAULT;
drop:
- this_cpu_inc(tun->pcpu_stats->rx_dropped);
+ atomic_long_inc(&tun->dev->rx_dropped);
kfree_skb(skb);
if (frags) {
tfile->napi.skb = NULL;
}
if (virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun))) {
- this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
+ atomic_long_inc(&tun->rx_frame_errors);
kfree_skb(skb);
if (frags) {
tfile->napi.skb = NULL;
pi.proto = htons(ETH_P_IPV6);
break;
default:
- this_cpu_inc(tun->pcpu_stats->rx_dropped);
+ atomic_long_inc(&tun->dev->rx_dropped);
kfree_skb(skb);
return -EINVAL;
}
skb_headlen(skb));
if (unlikely(headlen > skb_headlen(skb))) {
- this_cpu_inc(tun->pcpu_stats->rx_dropped);
+ atomic_long_inc(&tun->dev->rx_dropped);
napi_free_frags(&tfile->napi);
rcu_read_unlock();
mutex_unlock(&tfile->napi_mutex);
}
rcu_read_unlock();
- stats = get_cpu_ptr(tun->pcpu_stats);
- u64_stats_update_begin(&stats->syncp);
- u64_stats_inc(&stats->rx_packets);
- u64_stats_add(&stats->rx_bytes, len);
- u64_stats_update_end(&stats->syncp);
- put_cpu_ptr(stats);
+ preempt_disable();
+ dev_sw_netstats_rx_add(tun->dev, len);
+ preempt_enable();
if (rxhash)
tun_flow_update(tun, rxhash, tfile);
{
int vnet_hdr_sz = 0;
size_t size = xdp_frame->len;
- struct tun_pcpu_stats *stats;
size_t ret;
if (tun->flags & IFF_VNET_HDR) {
ret = copy_to_iter(xdp_frame->data, size, iter) + vnet_hdr_sz;
- stats = get_cpu_ptr(tun->pcpu_stats);
- u64_stats_update_begin(&stats->syncp);
- u64_stats_inc(&stats->tx_packets);
- u64_stats_add(&stats->tx_bytes, ret);
- u64_stats_update_end(&stats->syncp);
- put_cpu_ptr(tun->pcpu_stats);
+ preempt_disable();
+ dev_sw_netstats_tx_add(tun->dev, 1, ret);
+ preempt_enable();
return ret;
}
struct iov_iter *iter)
{
struct tun_pi pi = { 0, skb->protocol };
- struct tun_pcpu_stats *stats;
ssize_t total;
int vlan_offset = 0;
int vlan_hlen = 0;
done:
/* caller is in process context, */
- stats = get_cpu_ptr(tun->pcpu_stats);
- u64_stats_update_begin(&stats->syncp);
- u64_stats_inc(&stats->tx_packets);
- u64_stats_add(&stats->tx_bytes, skb->len + vlan_hlen);
- u64_stats_update_end(&stats->syncp);
- put_cpu_ptr(tun->pcpu_stats);
+ preempt_disable();
+ dev_sw_netstats_tx_add(tun->dev, 1, skb->len + vlan_hlen);
+ preempt_enable();
return total;
}
BUG_ON(!(list_empty(&tun->disabled)));
- free_percpu(tun->pcpu_stats);
- /* We clear pcpu_stats so that tun_set_iff() can tell if
+ free_percpu(dev->tstats);
+ /* We clear tstats so that tun_set_iff() can tell if
* tun_free_netdev() has been called from register_netdevice().
*/
- tun->pcpu_stats = NULL;
+ dev->tstats = NULL;
tun_flow_uninit(tun);
security_tun_dev_free_security(tun->security);
unsigned int datasize = xdp->data_end - xdp->data;
struct tun_xdp_hdr *hdr = xdp->data_hard_start;
struct virtio_net_hdr *gso = &hdr->gso;
- struct tun_pcpu_stats *stats;
struct bpf_prog *xdp_prog;
struct sk_buff *skb = NULL;
u32 rxhash = 0, act;
skb_put(skb, xdp->data_end - xdp->data);
if (virtio_net_hdr_to_skb(skb, gso, tun_is_little_endian(tun))) {
- this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
+ atomic_long_inc(&tun->rx_frame_errors);
kfree_skb(skb);
err = -EINVAL;
goto out;
netif_receive_skb(skb);
- /* No need for get_cpu_ptr() here since this function is
+ /* No need to disable preemption here since this function is
* always called with bh disabled
*/
- stats = this_cpu_ptr(tun->pcpu_stats);
- u64_stats_update_begin(&stats->syncp);
- u64_stats_inc(&stats->rx_packets);
- u64_stats_add(&stats->rx_bytes, datasize);
- u64_stats_update_end(&stats->syncp);
+ dev_sw_netstats_rx_add(tun->dev, datasize);
if (rxhash)
tun_flow_update(tun, rxhash, tfile);
tun->rx_batched = 0;
RCU_INIT_POINTER(tun->steering_prog, NULL);
- tun->pcpu_stats = netdev_alloc_pcpu_stats(struct tun_pcpu_stats);
- if (!tun->pcpu_stats) {
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ if (!dev->tstats) {
err = -ENOMEM;
goto err_free_dev;
}
tun_detach_all(dev);
/* We are here because register_netdevice() has failed.
* If register_netdevice() already called tun_free_netdev()
- * while dealing with the error, tun->pcpu_stats has been cleared.
+ * while dealing with the error, dev->stats has been cleared.
*/
- if (!tun->pcpu_stats)
+ if (!dev->tstats)
goto err_free_dev;
err_free_flow:
tun_flow_uninit(tun);
security_tun_dev_free_security(tun->security);
err_free_stat:
- free_percpu(tun->pcpu_stats);
+ free_percpu(dev->tstats);
err_free_dev:
free_netdev(dev);
return err;
"Linktype set failed because interface is up\n");
ret = -EBUSY;
} else {
+ ret = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE,
+ tun->dev);
+ ret = notifier_to_errno(ret);
+ if (ret) {
+ netif_info(tun, drv, tun->dev,
+ "Refused to change device type\n");
+ break;
+ }
tun->dev->type = (int) arg;
netif_info(tun, drv, tun->dev, "linktype set to %d\n",
tun->dev->type);
- ret = 0;
+ call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE,
+ tun->dev);
}
break;
This driver should work with at least the following devices:
* Aquantia AQtion USB to 5GbE
+config USB_RTL8153_ECM
+ tristate "RTL8153 ECM support"
+ depends on USB_NET_CDCETHER && (USB_RTL8152 || USB_RTL8152=n)
+ default y
+ help
+ This option supports ECM mode for RTL8153 ethernet adapter, when
+ CONFIG_USB_RTL8152 is not set, or the RTL8153 device is not
+ supported by r8152 driver.
+
endif # USB_NET_DRIVERS
obj-$(CONFIG_USB_NET_CDC_MBIM) += cdc_mbim.o
obj-$(CONFIG_USB_NET_CH9200) += ch9200.o
obj-$(CONFIG_USB_NET_AQC111) += aqc111.o
+obj-$(CONFIG_USB_RTL8153_ECM) += r8153_ecm.o
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_change_mtu = aqc111_change_mtu,
.ndo_set_mac_address = aqc111_set_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = asix_ioctl,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = asix_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = asix_ioctl,
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = asix_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_rx_mode = asix_set_multicast,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = asix_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = phy_do_ioctl_running,
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_change_mtu = ax88179_change_mtu,
.ndo_set_mac_address = ax88179_set_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_change_mtu = cdc_ncm_change_mtu,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_set_rx_mode = usbnet_set_rx_mode,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_change_mtu = cdc_ncm_change_mtu,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
break;
}
- /* calculate frame number withing this NDP */
+ /* calculate frame number within this NDP */
if (ctx->is_ndp16) {
ndplen = le16_to_cpu(ndp.ndp16->wLength);
index = (ndplen - sizeof(struct usb_cdc_ncm_ndp16)) / sizeof(struct usb_cdc_ncm_dpe16) - 1;
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = dm9601_ioctl,
.ndo_set_rx_mode = dm9601_set_multicast,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_rx_mode = int51x1_set_multicast,
u32 length, u8 *data)
{
int i;
- int ret;
u32 buf;
unsigned long timeout;
- ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf);
+ lan78xx_read_reg(dev, OTP_PWR_DN, &buf);
if (buf & OTP_PWR_DN_PWRDN_N_) {
/* clear it and wait to be cleared */
- ret = lan78xx_write_reg(dev, OTP_PWR_DN, 0);
+ lan78xx_write_reg(dev, OTP_PWR_DN, 0);
timeout = jiffies + HZ;
do {
usleep_range(1, 10);
- ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf);
+ lan78xx_read_reg(dev, OTP_PWR_DN, &buf);
if (time_after(jiffies, timeout)) {
netdev_warn(dev->net,
"timeout on OTP_PWR_DN");
}
for (i = 0; i < length; i++) {
- ret = lan78xx_write_reg(dev, OTP_ADDR1,
+ lan78xx_write_reg(dev, OTP_ADDR1,
((offset + i) >> 8) & OTP_ADDR1_15_11);
- ret = lan78xx_write_reg(dev, OTP_ADDR2,
+ lan78xx_write_reg(dev, OTP_ADDR2,
((offset + i) & OTP_ADDR2_10_3));
- ret = lan78xx_write_reg(dev, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_);
- ret = lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_);
+ lan78xx_write_reg(dev, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_);
+ lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_);
timeout = jiffies + HZ;
do {
udelay(1);
- ret = lan78xx_read_reg(dev, OTP_STATUS, &buf);
+ lan78xx_read_reg(dev, OTP_STATUS, &buf);
if (time_after(jiffies, timeout)) {
netdev_warn(dev->net,
"timeout on OTP_STATUS");
}
} while (buf & OTP_STATUS_BUSY_);
- ret = lan78xx_read_reg(dev, OTP_RD_DATA, &buf);
+ lan78xx_read_reg(dev, OTP_RD_DATA, &buf);
data[i] = (u8)(buf & 0xFF);
}
u32 length, u8 *data)
{
int i;
- int ret;
u32 buf;
unsigned long timeout;
- ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf);
+ lan78xx_read_reg(dev, OTP_PWR_DN, &buf);
if (buf & OTP_PWR_DN_PWRDN_N_) {
/* clear it and wait to be cleared */
- ret = lan78xx_write_reg(dev, OTP_PWR_DN, 0);
+ lan78xx_write_reg(dev, OTP_PWR_DN, 0);
timeout = jiffies + HZ;
do {
udelay(1);
- ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf);
+ lan78xx_read_reg(dev, OTP_PWR_DN, &buf);
if (time_after(jiffies, timeout)) {
netdev_warn(dev->net,
"timeout on OTP_PWR_DN completion");
}
/* set to BYTE program mode */
- ret = lan78xx_write_reg(dev, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_);
+ lan78xx_write_reg(dev, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_);
for (i = 0; i < length; i++) {
- ret = lan78xx_write_reg(dev, OTP_ADDR1,
+ lan78xx_write_reg(dev, OTP_ADDR1,
((offset + i) >> 8) & OTP_ADDR1_15_11);
- ret = lan78xx_write_reg(dev, OTP_ADDR2,
+ lan78xx_write_reg(dev, OTP_ADDR2,
((offset + i) & OTP_ADDR2_10_3));
- ret = lan78xx_write_reg(dev, OTP_PRGM_DATA, data[i]);
- ret = lan78xx_write_reg(dev, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_);
- ret = lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_);
+ lan78xx_write_reg(dev, OTP_PRGM_DATA, data[i]);
+ lan78xx_write_reg(dev, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_);
+ lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_);
timeout = jiffies + HZ;
do {
udelay(1);
- ret = lan78xx_read_reg(dev, OTP_STATUS, &buf);
+ lan78xx_read_reg(dev, OTP_STATUS, &buf);
if (time_after(jiffies, timeout)) {
netdev_warn(dev->net,
"Timeout on OTP_STATUS completion");
container_of(param, struct lan78xx_priv, set_multicast);
struct lan78xx_net *dev = pdata->dev;
int i;
- int ret;
netif_dbg(dev, drv, dev->net, "deferred multicast write 0x%08x\n",
pdata->rfe_ctl);
DP_SEL_VHF_HASH_LEN, pdata->mchash_table);
for (i = 1; i < NUM_OF_MAF; i++) {
- ret = lan78xx_write_reg(dev, MAF_HI(i), 0);
- ret = lan78xx_write_reg(dev, MAF_LO(i),
+ lan78xx_write_reg(dev, MAF_HI(i), 0);
+ lan78xx_write_reg(dev, MAF_LO(i),
pdata->pfilter_table[i][1]);
- ret = lan78xx_write_reg(dev, MAF_HI(i),
+ lan78xx_write_reg(dev, MAF_HI(i),
pdata->pfilter_table[i][0]);
}
- ret = lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl);
+ lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl);
}
static void lan78xx_set_multicast(struct net_device *netdev)
u16 lcladv, u16 rmtadv)
{
u32 flow = 0, fct_flow = 0;
- int ret;
u8 cap;
if (dev->fc_autoneg)
(cap & FLOW_CTRL_RX ? "enabled" : "disabled"),
(cap & FLOW_CTRL_TX ? "enabled" : "disabled"));
- ret = lan78xx_write_reg(dev, FCT_FLOW, fct_flow);
+ lan78xx_write_reg(dev, FCT_FLOW, fct_flow);
/* threshold value should be set before enabling flow */
- ret = lan78xx_write_reg(dev, FLOW, flow);
+ lan78xx_write_reg(dev, FLOW, flow);
return 0;
}
static void lan78xx_init_mac_address(struct lan78xx_net *dev)
{
u32 addr_lo, addr_hi;
- int ret;
u8 addr[6];
- ret = lan78xx_read_reg(dev, RX_ADDRL, &addr_lo);
- ret = lan78xx_read_reg(dev, RX_ADDRH, &addr_hi);
+ lan78xx_read_reg(dev, RX_ADDRL, &addr_lo);
+ lan78xx_read_reg(dev, RX_ADDRH, &addr_hi);
addr[0] = addr_lo & 0xFF;
addr[1] = (addr_lo >> 8) & 0xFF;
(addr[2] << 16) | (addr[3] << 24);
addr_hi = addr[4] | (addr[5] << 8);
- ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo);
- ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi);
+ lan78xx_write_reg(dev, RX_ADDRL, addr_lo);
+ lan78xx_write_reg(dev, RX_ADDRH, addr_hi);
}
- ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo);
- ret = lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_);
+ lan78xx_write_reg(dev, MAF_LO(0), addr_lo);
+ lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_);
ether_addr_copy(dev->net->dev_addr, addr);
}
static void lan78xx_link_status_change(struct net_device *net)
{
struct phy_device *phydev = net->phydev;
- int ret, temp;
+ int temp;
/* At forced 100 F/H mode, chip may fail to set mode correctly
* when cable is switched between long(~50+m) and short one.
/* disable phy interrupt */
temp = phy_read(phydev, LAN88XX_INT_MASK);
temp &= ~LAN88XX_INT_MASK_MDINTPIN_EN_;
- ret = phy_write(phydev, LAN88XX_INT_MASK, temp);
+ phy_write(phydev, LAN88XX_INT_MASK, temp);
temp = phy_read(phydev, MII_BMCR);
temp &= ~(BMCR_SPEED100 | BMCR_SPEED1000);
/* enable phy interrupt back */
temp = phy_read(phydev, LAN88XX_INT_MASK);
temp |= LAN88XX_INT_MASK_MDINTPIN_EN_;
- ret = phy_write(phydev, LAN88XX_INT_MASK, temp);
+ phy_write(phydev, LAN88XX_INT_MASK, temp);
}
}
struct lan78xx_net *dev =
container_of(data, struct lan78xx_net, domain_data);
u32 buf;
- int ret;
/* call register access here because irq_bus_lock & irq_bus_sync_unlock
* are only two callbacks executed in non-atomic contex.
*/
- ret = lan78xx_read_reg(dev, INT_EP_CTL, &buf);
+ lan78xx_read_reg(dev, INT_EP_CTL, &buf);
if (buf != data->irqenable)
- ret = lan78xx_write_reg(dev, INT_EP_CTL, data->irqenable);
+ lan78xx_write_reg(dev, INT_EP_CTL, data->irqenable);
mutex_unlock(&data->irq_lock);
}
static int lan8835_fixup(struct phy_device *phydev)
{
int buf;
- int ret;
struct lan78xx_net *dev = netdev_priv(phydev->attached_dev);
/* LED2/PME_N/IRQ_N/RGMII_ID pin to IRQ_N mode */
phy_write_mmd(phydev, MDIO_MMD_PCS, 0x8010, buf);
/* RGMII MAC TXC Delay Enable */
- ret = lan78xx_write_reg(dev, MAC_RGMII_ID,
+ lan78xx_write_reg(dev, MAC_RGMII_ID,
MAC_RGMII_ID_TXC_DELAY_EN_);
/* RGMII TX DLL Tune Adjust */
- ret = lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00);
+ lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00);
dev->interface = PHY_INTERFACE_MODE_RGMII_TXID;
static int lan78xx_set_rx_max_frame_length(struct lan78xx_net *dev, int size)
{
- int ret = 0;
u32 buf;
bool rxenabled;
- ret = lan78xx_read_reg(dev, MAC_RX, &buf);
+ lan78xx_read_reg(dev, MAC_RX, &buf);
rxenabled = ((buf & MAC_RX_RXEN_) != 0);
if (rxenabled) {
buf &= ~MAC_RX_RXEN_;
- ret = lan78xx_write_reg(dev, MAC_RX, buf);
+ lan78xx_write_reg(dev, MAC_RX, buf);
}
/* add 4 to size for FCS */
buf &= ~MAC_RX_MAX_SIZE_MASK_;
buf |= (((size + 4) << MAC_RX_MAX_SIZE_SHIFT_) & MAC_RX_MAX_SIZE_MASK_);
- ret = lan78xx_write_reg(dev, MAC_RX, buf);
+ lan78xx_write_reg(dev, MAC_RX, buf);
if (rxenabled) {
buf |= MAC_RX_RXEN_;
- ret = lan78xx_write_reg(dev, MAC_RX, buf);
+ lan78xx_write_reg(dev, MAC_RX, buf);
}
return 0;
int ll_mtu = new_mtu + netdev->hard_header_len;
int old_hard_mtu = dev->hard_mtu;
int old_rx_urb_size = dev->rx_urb_size;
- int ret;
/* no second zero-length packet read wanted after mtu-sized packets */
if ((ll_mtu % dev->maxpacket) == 0)
return -EDOM;
- ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN);
+ lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN);
netdev->mtu = new_mtu;
struct lan78xx_net *dev = netdev_priv(netdev);
struct sockaddr *addr = p;
u32 addr_lo, addr_hi;
- int ret;
if (netif_running(netdev))
return -EBUSY;
addr_hi = netdev->dev_addr[4] |
netdev->dev_addr[5] << 8;
- ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo);
- ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi);
+ lan78xx_write_reg(dev, RX_ADDRL, addr_lo);
+ lan78xx_write_reg(dev, RX_ADDRH, addr_hi);
/* Added to support MAC address changes */
- ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo);
- ret = lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_);
+ lan78xx_write_reg(dev, MAF_LO(0), addr_lo);
+ lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_);
return 0;
}
struct lan78xx_net *dev = netdev_priv(netdev);
struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]);
unsigned long flags;
- int ret;
spin_lock_irqsave(&pdata->rfe_ctl_lock, flags);
spin_unlock_irqrestore(&pdata->rfe_ctl_lock, flags);
- ret = lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl);
+ lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl);
return 0;
}
static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol)
{
u32 buf;
- int ret;
int mask_index;
u16 crc;
u32 temp_wucsr;
const u8 ipv6_multicast[3] = { 0x33, 0x33 };
const u8 arp_type[2] = { 0x08, 0x06 };
- ret = lan78xx_read_reg(dev, MAC_TX, &buf);
+ lan78xx_read_reg(dev, MAC_TX, &buf);
buf &= ~MAC_TX_TXEN_;
- ret = lan78xx_write_reg(dev, MAC_TX, buf);
- ret = lan78xx_read_reg(dev, MAC_RX, &buf);
+ lan78xx_write_reg(dev, MAC_TX, buf);
+ lan78xx_read_reg(dev, MAC_RX, &buf);
buf &= ~MAC_RX_RXEN_;
- ret = lan78xx_write_reg(dev, MAC_RX, buf);
+ lan78xx_write_reg(dev, MAC_RX, buf);
- ret = lan78xx_write_reg(dev, WUCSR, 0);
- ret = lan78xx_write_reg(dev, WUCSR2, 0);
- ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL);
+ lan78xx_write_reg(dev, WUCSR, 0);
+ lan78xx_write_reg(dev, WUCSR2, 0);
+ lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL);
temp_wucsr = 0;
temp_pmt_ctl = 0;
- ret = lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl);
+ lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl);
temp_pmt_ctl &= ~PMT_CTL_RES_CLR_WKP_EN_;
temp_pmt_ctl |= PMT_CTL_RES_CLR_WKP_STS_;
for (mask_index = 0; mask_index < NUM_OF_WUF_CFG; mask_index++)
- ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), 0);
+ lan78xx_write_reg(dev, WUF_CFG(mask_index), 0);
mask_index = 0;
if (wol & WAKE_PHY) {
/* set WUF_CFG & WUF_MASK for IPv4 Multicast */
crc = lan78xx_wakeframe_crc16(ipv4_multicast, 3);
- ret = lan78xx_write_reg(dev, WUF_CFG(mask_index),
+ lan78xx_write_reg(dev, WUF_CFG(mask_index),
WUF_CFGX_EN_ |
WUF_CFGX_TYPE_MCAST_ |
(0 << WUF_CFGX_OFFSET_SHIFT_) |
(crc & WUF_CFGX_CRC16_MASK_));
- ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7);
- ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0);
- ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0);
- ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0);
+ lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7);
+ lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0);
+ lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0);
+ lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0);
mask_index++;
/* for IPv6 Multicast */
crc = lan78xx_wakeframe_crc16(ipv6_multicast, 2);
- ret = lan78xx_write_reg(dev, WUF_CFG(mask_index),
+ lan78xx_write_reg(dev, WUF_CFG(mask_index),
WUF_CFGX_EN_ |
WUF_CFGX_TYPE_MCAST_ |
(0 << WUF_CFGX_OFFSET_SHIFT_) |
(crc & WUF_CFGX_CRC16_MASK_));
- ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3);
- ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0);
- ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0);
- ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0);
+ lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3);
+ lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0);
+ lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0);
+ lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0);
mask_index++;
temp_pmt_ctl |= PMT_CTL_WOL_EN_;
* for packettype (offset 12,13) = ARP (0x0806)
*/
crc = lan78xx_wakeframe_crc16(arp_type, 2);
- ret = lan78xx_write_reg(dev, WUF_CFG(mask_index),
+ lan78xx_write_reg(dev, WUF_CFG(mask_index),
WUF_CFGX_EN_ |
WUF_CFGX_TYPE_ALL_ |
(0 << WUF_CFGX_OFFSET_SHIFT_) |
(crc & WUF_CFGX_CRC16_MASK_));
- ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000);
- ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0);
- ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0);
- ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0);
+ lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000);
+ lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0);
+ lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0);
+ lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0);
mask_index++;
temp_pmt_ctl |= PMT_CTL_WOL_EN_;
temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_;
}
- ret = lan78xx_write_reg(dev, WUCSR, temp_wucsr);
+ lan78xx_write_reg(dev, WUCSR, temp_wucsr);
/* when multiple WOL bits are set */
if (hweight_long((unsigned long)wol) > 1) {
temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_;
temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_;
}
- ret = lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl);
+ lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl);
/* clear WUPS */
- ret = lan78xx_read_reg(dev, PMT_CTL, &buf);
+ lan78xx_read_reg(dev, PMT_CTL, &buf);
buf |= PMT_CTL_WUPS_MASK_;
- ret = lan78xx_write_reg(dev, PMT_CTL, buf);
+ lan78xx_write_reg(dev, PMT_CTL, buf);
- ret = lan78xx_read_reg(dev, MAC_RX, &buf);
+ lan78xx_read_reg(dev, MAC_RX, &buf);
buf |= MAC_RX_RXEN_;
- ret = lan78xx_write_reg(dev, MAC_RX, buf);
+ lan78xx_write_reg(dev, MAC_RX, buf);
return 0;
}
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = mcs7830_ioctl,
.ndo_set_rx_mode = mcs7830_set_multicast,
struct qmimux_priv {
struct net_device *real_dev;
u8 mux_id;
- struct pcpu_sw_netstats __percpu *stats64;
};
static int qmimux_open(struct net_device *dev)
skb->dev = priv->real_dev;
ret = dev_queue_xmit(skb);
- if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
- struct pcpu_sw_netstats *stats64 = this_cpu_ptr(priv->stats64);
-
- u64_stats_update_begin(&stats64->syncp);
- stats64->tx_packets++;
- stats64->tx_bytes += len;
- u64_stats_update_end(&stats64->syncp);
- } else {
+ if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN))
+ dev_sw_netstats_tx_add(dev, 1, len);
+ else
dev->stats.tx_dropped++;
- }
return ret;
}
-static void qmimux_get_stats64(struct net_device *net,
- struct rtnl_link_stats64 *stats)
-{
- struct qmimux_priv *priv = netdev_priv(net);
-
- netdev_stats_to_stats64(stats, &net->stats);
- dev_fetch_sw_netstats(stats, priv->stats64);
-}
-
static const struct net_device_ops qmimux_netdev_ops = {
.ndo_open = qmimux_open,
.ndo_stop = qmimux_stop,
.ndo_start_xmit = qmimux_start_xmit,
- .ndo_get_stats64 = qmimux_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
};
static void qmimux_setup(struct net_device *dev)
net->stats.rx_errors++;
return 0;
} else {
- struct pcpu_sw_netstats *stats64;
- struct qmimux_priv *priv = netdev_priv(net);
-
- stats64 = this_cpu_ptr(priv->stats64);
- u64_stats_update_begin(&stats64->syncp);
- stats64->rx_packets++;
- stats64->rx_bytes += pkt_len;
- u64_stats_update_end(&stats64->syncp);
+ dev_sw_netstats_rx_add(net, pkt_len);
}
skip:
priv->mux_id = mux_id;
priv->real_dev = real_dev;
- priv->stats64 = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
- if (!priv->stats64) {
+ new_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ if (!new_dev->tstats) {
err = -ENOBUFS;
goto out_free_newdev;
}
struct qmimux_priv *priv = netdev_priv(dev);
struct net_device *real_dev = priv->real_dev;
- free_percpu(priv->stats64);
+ free_percpu(dev->tstats);
netdev_upper_dev_unlink(real_dev, dev);
unregister_netdevice_queue(dev, head);
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = qmi_wwan_mac_addr,
.ndo_validate_addr = eth_validate_addr,
};
#include <linux/acpi.h>
#include <linux/firmware.h>
#include <crypto/hash.h>
+#include <linux/usb/r8152.h>
/* Information for net-next */
#define NETNEXT_VERSION "11"
#define INTR_LINK 0x0004
-#define RTL8152_REQT_READ 0xc0
-#define RTL8152_REQT_WRITE 0x40
-#define RTL8152_REQ_GET_REGS 0x05
-#define RTL8152_REQ_SET_REGS 0x05
-
-#define BYTE_EN_DWORD 0xff
-#define BYTE_EN_WORD 0x33
-#define BYTE_EN_BYTE 0x11
-#define BYTE_EN_SIX_BYTES 0x3f
-#define BYTE_EN_START_MASK 0x0f
-#define BYTE_EN_END_MASK 0xf0
-
#define RTL8153_MAX_PACKET 9216 /* 9K */
#define RTL8153_MAX_MTU (RTL8153_MAX_PACKET - VLAN_ETH_HLEN - \
ETH_FCS_LEN)
LENOVO_MACPASSTHRU,
};
-/* Define these values to match your device */
-#define VENDOR_ID_REALTEK 0x0bda
-#define VENDOR_ID_MICROSOFT 0x045e
-#define VENDOR_ID_SAMSUNG 0x04e8
-#define VENDOR_ID_LENOVO 0x17ef
-#define VENDOR_ID_LINKSYS 0x13b1
-#define VENDOR_ID_NVIDIA 0x0955
-#define VENDOR_ID_TPLINK 0x2357
-
#define DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2 0x3082
#define DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2 0xa387
-#define MCU_TYPE_PLA 0x0100
-#define MCU_TYPE_USB 0x0000
-
struct tally_counter {
__le64 tx_packets;
__le64 rx_packets;
* struct fw_mac - a firmware block used by RTL_FW_PLA and RTL_FW_USB.
* The layout of the firmware block is:
* <struct fw_mac> + <info> + <firmware data>.
+ * @blk_hdr: firmware descriptor (type, length)
* @fw_offset: offset of the firmware binary data. The start address of
* the data would be the address of struct fw_mac + @fw_offset.
* @fw_reg: the register to load the firmware. Depends on chip.
* @bp_num: the break point number which needs to be set for this firmware.
* Depends on the firmware.
* @bp: break points. Depends on firmware.
+ * @reserved: reserved space (unused)
* @fw_ver_reg: the register to store the fw version.
* @fw_ver_data: the firmware version of the current type.
* @info: additional information for debugging, and is followed by the
/**
* struct fw_phy_patch_key - a firmware block used by RTL_FW_PHY_START.
* This is used to set patch key when loading the firmware of PHY.
+ * @blk_hdr: firmware descriptor (type, length)
* @key_reg: the register to write the patch key.
* @key_data: patch key.
+ * @reserved: reserved space (unused)
*/
struct fw_phy_patch_key {
struct fw_block blk_hdr;
* struct fw_phy_nc - a firmware block used by RTL_FW_PHY_NC.
* The layout of the firmware block is:
* <struct fw_phy_nc> + <info> + <firmware data>.
+ * @blk_hdr: firmware descriptor (type, length)
* @fw_offset: offset of the firmware binary data. The start address of
* the data would be the address of struct fw_phy_nc + @fw_offset.
* @fw_reg: the register to load the firmware. Depends on chip.
* @patch_en_addr: the register of enabling patch mode. Depends on chip.
* @patch_en_value: patch mode enabled mask. Depends on the firmware.
* @mode_reg: the regitster of switching the mode.
- * @mod_pre: the mode needing to be set before loading the firmware.
- * @mod_post: the mode to be set when finishing to load the firmware.
+ * @mode_pre: the mode needing to be set before loading the firmware.
+ * @mode_post: the mode to be set when finishing to load the firmware.
+ * @reserved: reserved space (unused)
* @bp_start: the start register of break points. Depends on chip.
* @bp_num: the break point number which needs to be set for this firmware.
* Depends on the firmware.
return 0;
}
-static u8 rtl_get_version(struct usb_interface *intf)
+u8 rtl8152_get_version(struct usb_interface *intf)
{
struct usb_device *udev = interface_to_usbdev(intf);
u32 ocp_data = 0;
return version;
}
+EXPORT_SYMBOL_GPL(rtl8152_get_version);
static int rtl8152_probe(struct usb_interface *intf,
const struct usb_device_id *id)
{
struct usb_device *udev = interface_to_usbdev(intf);
- u8 version = rtl_get_version(intf);
+ u8 version = rtl8152_get_version(intf);
struct r8152 *tp;
struct net_device *netdev;
int ret;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/mii.h>
+#include <linux/usb.h>
+#include <linux/usb/cdc.h>
+#include <linux/usb/usbnet.h>
+#include <linux/usb/r8152.h>
+
+#define OCP_BASE 0xe86c
+
+static int pla_read_word(struct usbnet *dev, u16 index)
+{
+ u16 byen = BYTE_EN_WORD;
+ u8 shift = index & 2;
+ __le32 tmp;
+ int ret;
+
+ if (shift)
+ byen <<= shift;
+
+ index &= ~3;
+
+ ret = usbnet_read_cmd(dev, RTL8152_REQ_GET_REGS, RTL8152_REQT_READ, index,
+ MCU_TYPE_PLA | byen, &tmp, sizeof(tmp));
+ if (ret < 0)
+ goto out;
+
+ ret = __le32_to_cpu(tmp);
+ ret >>= (shift * 8);
+ ret &= 0xffff;
+
+out:
+ return ret;
+}
+
+static int pla_write_word(struct usbnet *dev, u16 index, u32 data)
+{
+ u32 mask = 0xffff;
+ u16 byen = BYTE_EN_WORD;
+ u8 shift = index & 2;
+ __le32 tmp;
+ int ret;
+
+ data &= mask;
+
+ if (shift) {
+ byen <<= shift;
+ mask <<= (shift * 8);
+ data <<= (shift * 8);
+ }
+
+ index &= ~3;
+
+ ret = usbnet_read_cmd(dev, RTL8152_REQ_GET_REGS, RTL8152_REQT_READ, index,
+ MCU_TYPE_PLA | byen, &tmp, sizeof(tmp));
+
+ if (ret < 0)
+ goto out;
+
+ data |= __le32_to_cpu(tmp) & ~mask;
+ tmp = __cpu_to_le32(data);
+
+ ret = usbnet_write_cmd(dev, RTL8152_REQ_SET_REGS, RTL8152_REQT_WRITE, index,
+ MCU_TYPE_PLA | byen, &tmp, sizeof(tmp));
+
+out:
+ return ret;
+}
+
+static int r8153_ecm_mdio_read(struct net_device *netdev, int phy_id, int reg)
+{
+ struct usbnet *dev = netdev_priv(netdev);
+ int ret;
+
+ ret = pla_write_word(dev, OCP_BASE, 0xa000);
+ if (ret < 0)
+ goto out;
+
+ ret = pla_read_word(dev, 0xb400 + reg * 2);
+
+out:
+ return ret;
+}
+
+static void r8153_ecm_mdio_write(struct net_device *netdev, int phy_id, int reg, int val)
+{
+ struct usbnet *dev = netdev_priv(netdev);
+ int ret;
+
+ ret = pla_write_word(dev, OCP_BASE, 0xa000);
+ if (ret < 0)
+ return;
+
+ ret = pla_write_word(dev, 0xb400 + reg * 2, val);
+}
+
+static int r8153_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+ int status;
+
+ status = usbnet_cdc_bind(dev, intf);
+ if (status < 0)
+ return status;
+
+ dev->mii.dev = dev->net;
+ dev->mii.mdio_read = r8153_ecm_mdio_read;
+ dev->mii.mdio_write = r8153_ecm_mdio_write;
+ dev->mii.reg_num_mask = 0x1f;
+ dev->mii.supports_gmii = 1;
+
+ return status;
+}
+
+static const struct driver_info r8153_info = {
+ .description = "RTL8153 ECM Device",
+ .flags = FLAG_ETHER,
+ .bind = r8153_bind,
+ .unbind = usbnet_cdc_unbind,
+ .status = usbnet_cdc_status,
+ .manage_power = usbnet_manage_power,
+};
+
+static const struct usb_device_id products[] = {
+{
+ USB_DEVICE_AND_INTERFACE_INFO(VENDOR_ID_REALTEK, 0x8153, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+ .driver_info = (unsigned long)&r8153_info,
+},
+
+ { }, /* END */
+};
+MODULE_DEVICE_TABLE(usb, products);
+
+static int rtl8153_ecm_probe(struct usb_interface *intf,
+ const struct usb_device_id *id)
+{
+#if IS_REACHABLE(CONFIG_USB_RTL8152)
+ if (rtl8152_get_version(intf))
+ return -ENODEV;
+#endif
+
+ return usbnet_probe(intf, id);
+}
+
+static struct usb_driver r8153_ecm_driver = {
+ .name = "r8153_ecm",
+ .id_table = products,
+ .probe = rtl8153_ecm_probe,
+ .disconnect = usbnet_disconnect,
+ .suspend = usbnet_suspend,
+ .resume = usbnet_resume,
+ .reset_resume = usbnet_resume,
+ .supports_autosuspend = 1,
+ .disable_hub_initiated_lpm = 1,
+};
+
+module_usb_driver(r8153_ecm_driver);
+
+MODULE_AUTHOR("Hayes Wang");
+MODULE_DESCRIPTION("Realtek USB ECM device");
+MODULE_LICENSE("GPL");
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
};
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
};
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_change_mtu = smsc75xx_change_mtu,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = smsc95xx_ioctl,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = sr9700_ioctl,
.ndo_set_rx_mode = sr9700_set_multicast,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = sr_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = sr_ioctl,
*/
void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb)
{
- struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->stats64);
+ struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->net->tstats);
unsigned long flags;
int status;
}
EXPORT_SYMBOL_GPL(usbnet_set_link_ksettings);
-void usbnet_get_stats64(struct net_device *net, struct rtnl_link_stats64 *stats)
-{
- struct usbnet *dev = netdev_priv(net);
-
- netdev_stats_to_stats64(stats, &net->stats);
- dev_fetch_sw_netstats(stats, dev->stats64);
-}
-EXPORT_SYMBOL_GPL(usbnet_get_stats64);
-
u32 usbnet_get_link (struct net_device *net)
{
struct usbnet *dev = netdev_priv(net);
struct usbnet *dev = entry->dev;
if (urb->status == 0) {
- struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->stats64);
+ struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->net->tstats);
unsigned long flags;
flags = u64_stats_update_begin_irqsave(&stats64->syncp);
usb_free_urb(dev->interrupt);
kfree(dev->padding_pkt);
- free_percpu(dev->stats64);
+ free_percpu(net->tstats);
free_netdev(net);
}
EXPORT_SYMBOL_GPL(usbnet_disconnect);
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_set_rx_mode = usbnet_set_rx_mode,
.ndo_change_mtu = usbnet_change_mtu,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
};
dev->driver_info = info;
dev->driver_name = name;
- dev->stats64 = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
- if (!dev->stats64)
+ net->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ if (!net->tstats)
goto out0;
dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV
*/
cancel_work_sync(&dev->kevent);
del_timer_sync(&dev->delay);
- free_percpu(dev->stats64);
+ free_percpu(net->tstats);
out0:
free_netdev(net);
out:
}
if (ifmp && tbp[IFLA_IFNAME]) {
- nla_strlcpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
+ nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
name_assign_type = NET_NAME_USER;
} else {
snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
eth_hw_addr_random(dev);
if (tb[IFLA_IFNAME])
- nla_strlcpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
+ nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
else
snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d");
* Based on dummy, team and ipvlan drivers
*/
+#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/if_arp.h>
struct list_head vxlan_list;
struct hlist_head sock_list[PORT_HASH_SIZE];
spinlock_t sock_lock;
+ struct notifier_block nexthop_notifier_block;
};
/* Forwarding table entry */
.ndo_open = vxlan_open,
.ndo_stop = vxlan_stop,
.ndo_start_xmit = vxlan_xmit,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_rx_mode = vxlan_set_multicast_list,
.ndo_change_mtu = vxlan_change_mtu,
.ndo_validate_addr = eth_validate_addr,
.ndo_open = vxlan_open,
.ndo_stop = vxlan_stop,
.ndo_start_xmit = vxlan_xmit,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_change_mtu = vxlan_change_mtu,
.ndo_fill_metadata_dst = vxlan_fill_metadata_dst,
};
static int vxlan_nexthop_event(struct notifier_block *nb,
unsigned long event, void *ptr)
{
- struct nexthop *nh = ptr;
+ struct nh_notifier_info *info = ptr;
+ struct nexthop *nh;
+
+ if (event != NEXTHOP_EVENT_DEL)
+ return NOTIFY_DONE;
- if (!nh || event != NEXTHOP_EVENT_DEL)
+ nh = nexthop_find_by_id(info->net, info->id);
+ if (!nh)
return NOTIFY_DONE;
vxlan_fdb_nh_flush(nh);
return NOTIFY_DONE;
}
-static struct notifier_block vxlan_nexthop_notifier_block __read_mostly = {
- .notifier_call = vxlan_nexthop_event,
-};
-
static __net_init int vxlan_init_net(struct net *net)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
INIT_LIST_HEAD(&vn->vxlan_list);
spin_lock_init(&vn->sock_lock);
+ vn->nexthop_notifier_block.notifier_call = vxlan_nexthop_event;
for (h = 0; h < PORT_HASH_SIZE; ++h)
INIT_HLIST_HEAD(&vn->sock_list[h]);
- return register_nexthop_notifier(net, &vxlan_nexthop_notifier_block);
+ return register_nexthop_notifier(net, &vn->nexthop_notifier_block,
+ NULL);
}
static void vxlan_destroy_tunnels(struct net *net, struct list_head *head)
LIST_HEAD(list);
rtnl_lock();
- list_for_each_entry(net, net_list, exit_list)
- unregister_nexthop_notifier(net, &vxlan_nexthop_notifier_block);
+ list_for_each_entry(net, net_list, exit_list) {
+ struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+
+ unregister_nexthop_notifier(net, &vn->nexthop_notifier_block);
+ }
list_for_each_entry(net, net_list, exit_list)
vxlan_destroy_tunnels(net, &list);
Say Y here if you want to use built-in HSS ports
on IXP4xx processor.
-config DLCI
- tristate "Frame Relay DLCI support"
- help
- Support for the Frame Relay protocol.
-
- Frame Relay is a fast low-cost way to connect to a remote Internet
- access provider or to form a private wide area network. The one
- physical line from your box to the local "switch" (i.e. the entry
- point to the Frame Relay network, usually at the phone company) can
- carry several logical point-to-point connections to other computers
- connected to the Frame Relay network. For a general explanation of
- the protocol, check out <http://www.mplsforum.org/>.
-
- To use frame relay, you need supporting hardware (called FRAD) and
- certain programs from the net-tools package as explained in
- <file:Documentation/networking/framerelay.rst>.
-
- To compile this driver as a module, choose M here: the
- module will be called dlci.
-
-config DLCI_MAX
- int "Max DLCI per device"
- depends on DLCI
- default "8"
- help
- How many logical point-to-point frame relay connections (the
- identifiers of which are called DCLIs) should be handled by each
- of your hardware frame relay access devices.
-
- Go with the default.
-
-config SDLA
- tristate "SDLA (Sangoma S502/S508) support"
- depends on DLCI && ISA
- help
- Driver for the Sangoma S502A, S502E, and S508 Frame Relay Access
- Devices.
-
- These are multi-protocol cards, but only Frame Relay is supported
- by the driver at this time. Please read
- <file:Documentation/networking/framerelay.rst>.
-
- To compile this driver as a module, choose M here: the
- module will be called sdla.
-
# X.25 network drivers
config LAPBETHER
tristate "LAPB over Ethernet driver"
If unsure, say N.
-config X25_ASY
- tristate "X.25 async driver"
- depends on LAPB && X25 && TTY
- help
- Send and receive X.25 frames over regular asynchronous serial
- lines such as telephone lines equipped with ordinary modems.
-
- Experts should note that this driver doesn't currently comply with
- the asynchronous HDLS framing protocols in CCITT recommendation X.25.
-
- To compile this driver as a module, choose M here: the
- module will be called x25_asy.
-
- If unsure, say N.
-
config SBNI
tristate "Granch SBNI12 Leased Line adapter support"
depends on X86
obj-$(CONFIG_SEALEVEL_4021) += z85230.o sealevel.o
obj-$(CONFIG_COSA) += cosa.o
obj-$(CONFIG_FARSYNC) += farsync.o
-obj-$(CONFIG_X25_ASY) += x25_asy.o
obj-$(CONFIG_LANMEDIA) += lmc/
-obj-$(CONFIG_DLCI) += dlci.o
-obj-$(CONFIG_SDLA) += sdla.o
obj-$(CONFIG_LAPBETHER) += lapbether.o
obj-$(CONFIG_SBNI) += sbni.o
obj-$(CONFIG_N2) += n2.o
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * DLCI Implementation of Frame Relay protocol for Linux, according to
- * RFC 1490. This generic device provides en/decapsulation for an
- * underlying hardware driver. Routes & IPs are assigned to these
- * interfaces. Requires 'dlcicfg' program to create usable
- * interfaces, the initial one, 'dlci' is for IOCTL use only.
- *
- * Version: @(#)dlci.c 0.35 4 Jan 1997
- *
- * Author: Mike McLagan <mike.mclagan@linux.org>
- *
- * Changes:
- *
- * 0.15 Mike Mclagan Packet freeing, bug in kmalloc call
- * DLCI_RET handling
- * 0.20 Mike McLagan More conservative on which packets
- * are returned for retry and which are
- * are dropped. If DLCI_RET_DROP is
- * returned from the FRAD, the packet is
- * sent back to Linux for re-transmission
- * 0.25 Mike McLagan Converted to use SIOC IOCTL calls
- * 0.30 Jim Freeman Fixed to allow IPX traffic
- * 0.35 Michael Elizabeth Fixed incorrect memcpy_fromfs
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/fcntl.h>
-#include <linux/interrupt.h>
-#include <linux/ptrace.h>
-#include <linux/ioport.h>
-#include <linux/in.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/if_frad.h>
-#include <linux/bitops.h>
-
-#include <net/sock.h>
-
-#include <asm/io.h>
-#include <asm/dma.h>
-#include <linux/uaccess.h>
-
-static const char version[] = "DLCI driver v0.35, 4 Jan 1997, mike.mclagan@linux.org";
-
-static LIST_HEAD(dlci_devs);
-
-static void dlci_setup(struct net_device *);
-
-/*
- * these encapsulate the RFC 1490 requirements as well as
- * deal with packet transmission and reception, working with
- * the upper network layers
- */
-
-static int dlci_header(struct sk_buff *skb, struct net_device *dev,
- unsigned short type, const void *daddr,
- const void *saddr, unsigned len)
-{
- struct frhdr hdr;
- unsigned int hlen;
- char *dest;
-
- hdr.control = FRAD_I_UI;
- switch (type)
- {
- case ETH_P_IP:
- hdr.IP_NLPID = FRAD_P_IP;
- hlen = sizeof(hdr.control) + sizeof(hdr.IP_NLPID);
- break;
-
- /* feel free to add other types, if necessary */
-
- default:
- hdr.pad = FRAD_P_PADDING;
- hdr.NLPID = FRAD_P_SNAP;
- memset(hdr.OUI, 0, sizeof(hdr.OUI));
- hdr.PID = htons(type);
- hlen = sizeof(hdr);
- break;
- }
-
- dest = skb_push(skb, hlen);
- if (!dest)
- return 0;
-
- memcpy(dest, &hdr, hlen);
-
- return hlen;
-}
-
-static void dlci_receive(struct sk_buff *skb, struct net_device *dev)
-{
- struct frhdr *hdr;
- int process, header;
-
- if (!pskb_may_pull(skb, sizeof(*hdr))) {
- netdev_notice(dev, "invalid data no header\n");
- dev->stats.rx_errors++;
- kfree_skb(skb);
- return;
- }
-
- hdr = (struct frhdr *) skb->data;
- process = 0;
- header = 0;
- skb->dev = dev;
-
- if (hdr->control != FRAD_I_UI)
- {
- netdev_notice(dev, "Invalid header flag 0x%02X\n",
- hdr->control);
- dev->stats.rx_errors++;
- }
- else
- switch (hdr->IP_NLPID)
- {
- case FRAD_P_PADDING:
- if (hdr->NLPID != FRAD_P_SNAP)
- {
- netdev_notice(dev, "Unsupported NLPID 0x%02X\n",
- hdr->NLPID);
- dev->stats.rx_errors++;
- break;
- }
-
- if (hdr->OUI[0] + hdr->OUI[1] + hdr->OUI[2] != 0)
- {
- netdev_notice(dev, "Unsupported organizationally unique identifier 0x%02X-%02X-%02X\n",
- hdr->OUI[0],
- hdr->OUI[1],
- hdr->OUI[2]);
- dev->stats.rx_errors++;
- break;
- }
-
- /* at this point, it's an EtherType frame */
- header = sizeof(struct frhdr);
- /* Already in network order ! */
- skb->protocol = hdr->PID;
- process = 1;
- break;
-
- case FRAD_P_IP:
- header = sizeof(hdr->control) + sizeof(hdr->IP_NLPID);
- skb->protocol = htons(ETH_P_IP);
- process = 1;
- break;
-
- case FRAD_P_SNAP:
- case FRAD_P_Q933:
- case FRAD_P_CLNP:
- netdev_notice(dev, "Unsupported NLPID 0x%02X\n",
- hdr->pad);
- dev->stats.rx_errors++;
- break;
-
- default:
- netdev_notice(dev, "Invalid pad byte 0x%02X\n",
- hdr->pad);
- dev->stats.rx_errors++;
- break;
- }
-
- if (process)
- {
- /* we've set up the protocol, so discard the header */
- skb_reset_mac_header(skb);
- skb_pull(skb, header);
- dev->stats.rx_bytes += skb->len;
- netif_rx(skb);
- dev->stats.rx_packets++;
- }
- else
- dev_kfree_skb(skb);
-}
-
-static netdev_tx_t dlci_transmit(struct sk_buff *skb, struct net_device *dev)
-{
- struct dlci_local *dlp = netdev_priv(dev);
-
- if (skb) {
- struct netdev_queue *txq = skb_get_tx_queue(dev, skb);
- netdev_start_xmit(skb, dlp->slave, txq, false);
- }
- return NETDEV_TX_OK;
-}
-
-static int dlci_config(struct net_device *dev, struct dlci_conf __user *conf, int get)
-{
- struct dlci_conf config;
- struct dlci_local *dlp;
- struct frad_local *flp;
- int err;
-
- dlp = netdev_priv(dev);
-
- flp = netdev_priv(dlp->slave);
-
- if (!get)
- {
- if (copy_from_user(&config, conf, sizeof(struct dlci_conf)))
- return -EFAULT;
- if (config.flags & ~DLCI_VALID_FLAGS)
- return -EINVAL;
- memcpy(&dlp->config, &config, sizeof(struct dlci_conf));
- dlp->configured = 1;
- }
-
- err = (*flp->dlci_conf)(dlp->slave, dev, get);
- if (err)
- return err;
-
- if (get)
- {
- if (copy_to_user(conf, &dlp->config, sizeof(struct dlci_conf)))
- return -EFAULT;
- }
-
- return 0;
-}
-
-static int dlci_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
- struct dlci_local *dlp;
-
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
-
- dlp = netdev_priv(dev);
-
- switch (cmd)
- {
- case DLCI_GET_SLAVE:
- if (!*(short *)(dev->dev_addr))
- return -EINVAL;
-
- strncpy(ifr->ifr_slave, dlp->slave->name, sizeof(ifr->ifr_slave));
- break;
-
- case DLCI_GET_CONF:
- case DLCI_SET_CONF:
- if (!*(short *)(dev->dev_addr))
- return -EINVAL;
-
- return dlci_config(dev, ifr->ifr_data, cmd == DLCI_GET_CONF);
-
- default:
- return -EOPNOTSUPP;
- }
- return 0;
-}
-
-static int dlci_change_mtu(struct net_device *dev, int new_mtu)
-{
- struct dlci_local *dlp = netdev_priv(dev);
-
- return dev_set_mtu(dlp->slave, new_mtu);
-}
-
-static int dlci_open(struct net_device *dev)
-{
- struct dlci_local *dlp;
- struct frad_local *flp;
- int err;
-
- dlp = netdev_priv(dev);
-
- if (!*(short *)(dev->dev_addr))
- return -EINVAL;
-
- if (!netif_running(dlp->slave))
- return -ENOTCONN;
-
- flp = netdev_priv(dlp->slave);
- err = (*flp->activate)(dlp->slave, dev);
- if (err)
- return err;
-
- netif_start_queue(dev);
-
- return 0;
-}
-
-static int dlci_close(struct net_device *dev)
-{
- struct dlci_local *dlp;
- struct frad_local *flp;
-
- netif_stop_queue(dev);
-
- dlp = netdev_priv(dev);
-
- flp = netdev_priv(dlp->slave);
- (*flp->deactivate)(dlp->slave, dev);
-
- return 0;
-}
-
-static int dlci_add(struct dlci_add *dlci)
-{
- struct net_device *master, *slave;
- struct dlci_local *dlp;
- struct frad_local *flp;
- int err = -EINVAL;
-
-
- /* validate slave device */
- slave = dev_get_by_name(&init_net, dlci->devname);
- if (!slave)
- return -ENODEV;
-
- if (slave->type != ARPHRD_FRAD || netdev_priv(slave) == NULL)
- goto err1;
-
- /* create device name */
- master = alloc_netdev(sizeof(struct dlci_local), "dlci%d",
- NET_NAME_UNKNOWN, dlci_setup);
- if (!master) {
- err = -ENOMEM;
- goto err1;
- }
-
- /* make sure same slave not already registered */
- rtnl_lock();
- list_for_each_entry(dlp, &dlci_devs, list) {
- if (dlp->slave == slave) {
- err = -EBUSY;
- goto err2;
- }
- }
-
- *(short *)(master->dev_addr) = dlci->dlci;
-
- dlp = netdev_priv(master);
- dlp->slave = slave;
- dlp->master = master;
-
- flp = netdev_priv(slave);
- err = (*flp->assoc)(slave, master);
- if (err < 0)
- goto err2;
-
- err = register_netdevice(master);
- if (err < 0)
- goto err2;
-
- strcpy(dlci->devname, master->name);
-
- list_add(&dlp->list, &dlci_devs);
- rtnl_unlock();
-
- return 0;
-
- err2:
- rtnl_unlock();
- free_netdev(master);
- err1:
- dev_put(slave);
- return err;
-}
-
-static int dlci_del(struct dlci_add *dlci)
-{
- struct dlci_local *dlp;
- struct frad_local *flp;
- struct net_device *master, *slave;
- int err;
- bool found = false;
-
- rtnl_lock();
-
- /* validate slave device */
- master = __dev_get_by_name(&init_net, dlci->devname);
- if (!master) {
- err = -ENODEV;
- goto out;
- }
-
- list_for_each_entry(dlp, &dlci_devs, list) {
- if (dlp->master == master) {
- found = true;
- break;
- }
- }
- if (!found) {
- err = -ENODEV;
- goto out;
- }
-
- if (netif_running(master)) {
- err = -EBUSY;
- goto out;
- }
-
- dlp = netdev_priv(master);
- slave = dlp->slave;
- flp = netdev_priv(slave);
-
- err = (*flp->deassoc)(slave, master);
- if (!err) {
- list_del(&dlp->list);
-
- unregister_netdevice(master);
-
- dev_put(slave);
- }
-out:
- rtnl_unlock();
- return err;
-}
-
-static int dlci_ioctl(unsigned int cmd, void __user *arg)
-{
- struct dlci_add add;
- int err;
-
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
-
- if (copy_from_user(&add, arg, sizeof(struct dlci_add)))
- return -EFAULT;
-
- switch (cmd)
- {
- case SIOCADDDLCI:
- err = dlci_add(&add);
-
- if (!err)
- if (copy_to_user(arg, &add, sizeof(struct dlci_add)))
- return -EFAULT;
- break;
-
- case SIOCDELDLCI:
- err = dlci_del(&add);
- break;
-
- default:
- err = -EINVAL;
- }
-
- return err;
-}
-
-static const struct header_ops dlci_header_ops = {
- .create = dlci_header,
-};
-
-static const struct net_device_ops dlci_netdev_ops = {
- .ndo_open = dlci_open,
- .ndo_stop = dlci_close,
- .ndo_do_ioctl = dlci_dev_ioctl,
- .ndo_start_xmit = dlci_transmit,
- .ndo_change_mtu = dlci_change_mtu,
-};
-
-static void dlci_setup(struct net_device *dev)
-{
- struct dlci_local *dlp = netdev_priv(dev);
-
- dev->flags = 0;
- dev->header_ops = &dlci_header_ops;
- dev->netdev_ops = &dlci_netdev_ops;
- dev->needs_free_netdev = true;
-
- dlp->receive = dlci_receive;
-
- dev->type = ARPHRD_DLCI;
- dev->hard_header_len = sizeof(struct frhdr);
- dev->addr_len = sizeof(short);
-
-}
-
-/* if slave is unregistering, then cleanup master */
-static int dlci_dev_event(struct notifier_block *unused,
- unsigned long event, void *ptr)
-{
- struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-
- if (dev_net(dev) != &init_net)
- return NOTIFY_DONE;
-
- if (event == NETDEV_UNREGISTER) {
- struct dlci_local *dlp;
-
- list_for_each_entry(dlp, &dlci_devs, list) {
- if (dlp->slave == dev) {
- list_del(&dlp->list);
- unregister_netdevice(dlp->master);
- dev_put(dlp->slave);
- break;
- }
- }
- }
- return NOTIFY_DONE;
-}
-
-static struct notifier_block dlci_notifier = {
- .notifier_call = dlci_dev_event,
-};
-
-static int __init init_dlci(void)
-{
- dlci_ioctl_set(dlci_ioctl);
- register_netdevice_notifier(&dlci_notifier);
-
- printk("%s.\n", version);
-
- return 0;
-}
-
-static void __exit dlci_exit(void)
-{
- struct dlci_local *dlp, *nxt;
-
- dlci_ioctl_set(NULL);
- unregister_netdevice_notifier(&dlci_notifier);
-
- rtnl_lock();
- list_for_each_entry_safe(dlp, nxt, &dlci_devs, list) {
- unregister_netdevice(dlp->master);
- dev_put(dlp->slave);
- }
- rtnl_unlock();
-}
-
-module_init(init_dlci);
-module_exit(dlci_exit);
-
-MODULE_AUTHOR("Mike McLagan");
-MODULE_DESCRIPTION("Frame Relay DLCI layer");
-MODULE_LICENSE("GPL");
return 0;
}
+static int fr_snap_parse(struct sk_buff *skb, struct pvc_device *pvc)
+{
+ /* OUI 00-00-00 indicates an Ethertype follows */
+ if (skb->data[0] == 0x00 &&
+ skb->data[1] == 0x00 &&
+ skb->data[2] == 0x00) {
+ if (!pvc->main)
+ return -1;
+ skb->dev = pvc->main;
+ skb->protocol = *(__be16 *)(skb->data + 3); /* Ethertype */
+ skb_pull(skb, 5);
+ skb_reset_mac_header(skb);
+ return 0;
+
+ /* OUI 00-80-C2 stands for the 802.1 organization */
+ } else if (skb->data[0] == 0x00 &&
+ skb->data[1] == 0x80 &&
+ skb->data[2] == 0xC2) {
+ /* PID 00-07 stands for Ethernet frames without FCS */
+ if (skb->data[3] == 0x00 &&
+ skb->data[4] == 0x07) {
+ if (!pvc->ether)
+ return -1;
+ skb_pull(skb, 5);
+ if (skb->len < ETH_HLEN)
+ return -1;
+ skb->protocol = eth_type_trans(skb, pvc->ether);
+ return 0;
+
+ /* PID unsupported */
+ } else {
+ return -1;
+ }
+
+ /* OUI unsupported */
+ } else {
+ return -1;
+ }
+}
static int fr_rx(struct sk_buff *skb)
{
u8 *data = skb->data;
u16 dlci;
struct pvc_device *pvc;
- struct net_device *dev = NULL;
+ struct net_device *dev;
- if (skb->len <= 4 || fh->ea1 || data[2] != FR_UI)
+ if (skb->len < 4 || fh->ea1 || !fh->ea2 || data[2] != FR_UI)
goto rx_error;
dlci = q922_to_dlci(skb->data);
netdev_info(frad, "No PVC for received frame's DLCI %d\n",
dlci);
#endif
- dev_kfree_skb_any(skb);
- return NET_RX_DROP;
+ goto rx_drop;
}
if (pvc->state.fecn != fh->fecn) {
}
if (data[3] == NLPID_IP) {
+ if (!pvc->main)
+ goto rx_drop;
skb_pull(skb, 4); /* Remove 4-byte header (hdr, UI, NLPID) */
- dev = pvc->main;
+ skb->dev = pvc->main;
skb->protocol = htons(ETH_P_IP);
+ skb_reset_mac_header(skb);
} else if (data[3] == NLPID_IPV6) {
+ if (!pvc->main)
+ goto rx_drop;
skb_pull(skb, 4); /* Remove 4-byte header (hdr, UI, NLPID) */
- dev = pvc->main;
+ skb->dev = pvc->main;
skb->protocol = htons(ETH_P_IPV6);
+ skb_reset_mac_header(skb);
- } else if (skb->len > 10 && data[3] == FR_PAD &&
- data[4] == NLPID_SNAP && data[5] == FR_PAD) {
- u16 oui = ntohs(*(__be16*)(data + 6));
- u16 pid = ntohs(*(__be16*)(data + 8));
- skb_pull(skb, 10);
-
- switch ((((u32)oui) << 16) | pid) {
- case ETH_P_ARP: /* routed frame with SNAP */
- case ETH_P_IPX:
- case ETH_P_IP: /* a long variant */
- case ETH_P_IPV6:
- dev = pvc->main;
- skb->protocol = htons(pid);
- break;
-
- case 0x80C20007: /* bridged Ethernet frame */
- if ((dev = pvc->ether) != NULL)
- skb->protocol = eth_type_trans(skb, dev);
- break;
-
- default:
- netdev_info(frad, "Unsupported protocol, OUI=%x PID=%x\n",
- oui, pid);
- dev_kfree_skb_any(skb);
- return NET_RX_DROP;
+ } else if (data[3] == FR_PAD) {
+ if (skb->len < 5)
+ goto rx_error;
+ if (data[4] == NLPID_SNAP) { /* A SNAP header follows */
+ skb_pull(skb, 5);
+ if (skb->len < 5) /* Incomplete SNAP header */
+ goto rx_error;
+ if (fr_snap_parse(skb, pvc))
+ goto rx_drop;
+ } else {
+ goto rx_drop;
}
+
} else {
netdev_info(frad, "Unsupported protocol, NLPID=%x length=%i\n",
data[3], skb->len);
- dev_kfree_skb_any(skb);
- return NET_RX_DROP;
+ goto rx_drop;
}
- if (dev) {
- dev->stats.rx_packets++; /* PVC traffic */
- dev->stats.rx_bytes += skb->len;
- if (pvc->state.becn)
- dev->stats.rx_compressed++;
- skb->dev = dev;
- netif_rx(skb);
- return NET_RX_SUCCESS;
- } else {
- dev_kfree_skb_any(skb);
- return NET_RX_DROP;
- }
+ dev = skb->dev;
+ dev->stats.rx_packets++; /* PVC traffic */
+ dev->stats.rx_bytes += skb->len;
+ if (pvc->state.becn)
+ dev->stats.rx_compressed++;
+ netif_rx(skb);
+ return NET_RX_SUCCESS;
- rx_error:
+rx_error:
frad->stats.rx_errors++; /* Mark error */
+rx_drop:
dev_kfree_skb_any(skb);
return NET_RX_DROP;
}
switch(xc.command){
case lmc_xilinx_reset: /*fold02*/
{
- u16 mii;
spin_lock_irqsave(&sc->lmc_lock, flags);
- mii = lmc_mii_readreg (sc, 0, 16);
+ lmc_mii_readreg (sc, 0, 16);
/*
* Make all of them 0 and make input
break;
case lmc_xilinx_load_prom: /*fold02*/
{
- u16 mii;
int timeout = 500000;
spin_lock_irqsave(&sc->lmc_lock, flags);
- mii = lmc_mii_readreg (sc, 0, 16);
+ lmc_mii_readreg (sc, 0, 16);
/*
* Make all of them 0 and make input
int i;
s32 stat;
unsigned int badtx;
- u32 firstcsr;
int max_work = LMC_RXDESCS;
int handled = 0;
goto lmc_int_fail_out;
}
- firstcsr = csr;
-
/* always go through this loop at least once */
while (csr & sc->lmc_intrmask) {
handled = 1;
#define get_port(card, port) (&card->ports[port])
-#define sca_flush(card) (sca_in(IER0, card));
+#define sca_flush(card) (sca_in(IER0, card))
static inline void new_memcpy_toio(char __iomem *dest, char *src, int length)
{
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * SDLA An implementation of a driver for the Sangoma S502/S508 series
- * multi-protocol PC interface card. Initial offering is with
- * the DLCI driver, providing Frame Relay support for linux.
- *
- * Global definitions for the Frame relay interface.
- *
- * Version: @(#)sdla.c 0.30 12 Sep 1996
- *
- * Credits: Sangoma Technologies, for the use of 2 cards for an extended
- * period of time.
- * David Mandelstam <dm@sangoma.com> for getting me started on
- * this project, and incentive to complete it.
- * Gene Kozen <74604.152@compuserve.com> for providing me with
- * important information about the cards.
- *
- * Author: Mike McLagan <mike.mclagan@linux.org>
- *
- * Changes:
- * 0.15 Mike McLagan Improved error handling, packet dropping
- * 0.20 Mike McLagan New transmit/receive flags for config
- * If in FR mode, don't accept packets from
- * non DLCI devices.
- * 0.25 Mike McLagan Fixed problem with rejecting packets
- * from non DLCI devices.
- * 0.30 Mike McLagan Fixed kernel panic when used with modified
- * ifconfig
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/fcntl.h>
-#include <linux/interrupt.h>
-#include <linux/ptrace.h>
-#include <linux/ioport.h>
-#include <linux/in.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/timer.h>
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/if_frad.h>
-#include <linux/sdla.h>
-#include <linux/bitops.h>
-
-#include <asm/io.h>
-#include <asm/dma.h>
-#include <linux/uaccess.h>
-
-static const char* version = "SDLA driver v0.30, 12 Sep 1996, mike.mclagan@linux.org";
-
-static unsigned int valid_port[] = { 0x250, 0x270, 0x280, 0x300, 0x350, 0x360, 0x380, 0x390};
-
-static unsigned int valid_mem[] = {
- 0xA0000, 0xA2000, 0xA4000, 0xA6000, 0xA8000, 0xAA000, 0xAC000, 0xAE000,
- 0xB0000, 0xB2000, 0xB4000, 0xB6000, 0xB8000, 0xBA000, 0xBC000, 0xBE000,
- 0xC0000, 0xC2000, 0xC4000, 0xC6000, 0xC8000, 0xCA000, 0xCC000, 0xCE000,
- 0xD0000, 0xD2000, 0xD4000, 0xD6000, 0xD8000, 0xDA000, 0xDC000, 0xDE000,
- 0xE0000, 0xE2000, 0xE4000, 0xE6000, 0xE8000, 0xEA000, 0xEC000, 0xEE000};
-
-static DEFINE_SPINLOCK(sdla_lock);
-
-/*********************************************************
- *
- * these are the core routines that access the card itself
- *
- *********************************************************/
-
-#define SDLA_WINDOW(dev,addr) outb((((addr) >> 13) & 0x1F), (dev)->base_addr + SDLA_REG_Z80_WINDOW)
-
-static void __sdla_read(struct net_device *dev, int addr, void *buf, short len)
-{
- char *temp;
- const void *base;
- int offset, bytes;
-
- temp = buf;
- while(len)
- {
- offset = addr & SDLA_ADDR_MASK;
- bytes = offset + len > SDLA_WINDOW_SIZE ? SDLA_WINDOW_SIZE - offset : len;
- base = (const void *) (dev->mem_start + offset);
-
- SDLA_WINDOW(dev, addr);
- memcpy(temp, base, bytes);
-
- addr += bytes;
- temp += bytes;
- len -= bytes;
- }
-}
-
-static void sdla_read(struct net_device *dev, int addr, void *buf, short len)
-{
- unsigned long flags;
- spin_lock_irqsave(&sdla_lock, flags);
- __sdla_read(dev, addr, buf, len);
- spin_unlock_irqrestore(&sdla_lock, flags);
-}
-
-static void __sdla_write(struct net_device *dev, int addr,
- const void *buf, short len)
-{
- const char *temp;
- void *base;
- int offset, bytes;
-
- temp = buf;
- while(len)
- {
- offset = addr & SDLA_ADDR_MASK;
- bytes = offset + len > SDLA_WINDOW_SIZE ? SDLA_WINDOW_SIZE - offset : len;
- base = (void *) (dev->mem_start + offset);
-
- SDLA_WINDOW(dev, addr);
- memcpy(base, temp, bytes);
-
- addr += bytes;
- temp += bytes;
- len -= bytes;
- }
-}
-
-static void sdla_write(struct net_device *dev, int addr,
- const void *buf, short len)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&sdla_lock, flags);
- __sdla_write(dev, addr, buf, len);
- spin_unlock_irqrestore(&sdla_lock, flags);
-}
-
-
-static void sdla_clear(struct net_device *dev)
-{
- unsigned long flags;
- char *base;
- int len, addr, bytes;
-
- len = 65536;
- addr = 0;
- bytes = SDLA_WINDOW_SIZE;
- base = (void *) dev->mem_start;
-
- spin_lock_irqsave(&sdla_lock, flags);
- while(len)
- {
- SDLA_WINDOW(dev, addr);
- memset(base, 0, bytes);
-
- addr += bytes;
- len -= bytes;
- }
- spin_unlock_irqrestore(&sdla_lock, flags);
-
-}
-
-static char sdla_byte(struct net_device *dev, int addr)
-{
- unsigned long flags;
- char byte, *temp;
-
- temp = (void *) (dev->mem_start + (addr & SDLA_ADDR_MASK));
-
- spin_lock_irqsave(&sdla_lock, flags);
- SDLA_WINDOW(dev, addr);
- byte = *temp;
- spin_unlock_irqrestore(&sdla_lock, flags);
-
- return byte;
-}
-
-static void sdla_stop(struct net_device *dev)
-{
- struct frad_local *flp;
-
- flp = netdev_priv(dev);
- switch(flp->type)
- {
- case SDLA_S502A:
- outb(SDLA_S502A_HALT, dev->base_addr + SDLA_REG_CONTROL);
- flp->state = SDLA_HALT;
- break;
- case SDLA_S502E:
- outb(SDLA_HALT, dev->base_addr + SDLA_REG_Z80_CONTROL);
- outb(SDLA_S502E_ENABLE, dev->base_addr + SDLA_REG_CONTROL);
- flp->state = SDLA_S502E_ENABLE;
- break;
- case SDLA_S507:
- flp->state &= ~SDLA_CPUEN;
- outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
- break;
- case SDLA_S508:
- flp->state &= ~SDLA_CPUEN;
- outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
- break;
- }
-}
-
-static void sdla_start(struct net_device *dev)
-{
- struct frad_local *flp;
-
- flp = netdev_priv(dev);
- switch(flp->type)
- {
- case SDLA_S502A:
- outb(SDLA_S502A_NMI, dev->base_addr + SDLA_REG_CONTROL);
- outb(SDLA_S502A_START, dev->base_addr + SDLA_REG_CONTROL);
- flp->state = SDLA_S502A_START;
- break;
- case SDLA_S502E:
- outb(SDLA_S502E_CPUEN, dev->base_addr + SDLA_REG_Z80_CONTROL);
- outb(0x00, dev->base_addr + SDLA_REG_CONTROL);
- flp->state = 0;
- break;
- case SDLA_S507:
- flp->state |= SDLA_CPUEN;
- outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
- break;
- case SDLA_S508:
- flp->state |= SDLA_CPUEN;
- outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
- break;
- }
-}
-
-/****************************************************
- *
- * this is used for the S502A/E cards to determine
- * the speed of the onboard CPU. Calibration is
- * necessary for the Frame Relay code uploaded
- * later. Incorrect results cause timing problems
- * with link checks & status messages
- *
- ***************************************************/
-
-static int sdla_z80_poll(struct net_device *dev, int z80_addr, int jiffs, char resp1, char resp2)
-{
- unsigned long start, done, now;
- char resp, *temp;
-
- start = now = jiffies;
- done = jiffies + jiffs;
-
- temp = (void *)dev->mem_start;
- temp += z80_addr & SDLA_ADDR_MASK;
-
- resp = ~resp1;
- while (time_before(jiffies, done) && (resp != resp1) && (!resp2 || (resp != resp2)))
- {
- if (jiffies != now)
- {
- SDLA_WINDOW(dev, z80_addr);
- now = jiffies;
- resp = *temp;
- }
- }
- return time_before(jiffies, done) ? jiffies - start : -1;
-}
-
-/* constants for Z80 CPU speed */
-#define Z80_READY '1' /* Z80 is ready to begin */
-#define LOADER_READY '2' /* driver is ready to begin */
-#define Z80_SCC_OK '3' /* SCC is on board */
-#define Z80_SCC_BAD '4' /* SCC was not found */
-
-static int sdla_cpuspeed(struct net_device *dev, struct ifreq *ifr)
-{
- int jiffs;
- char data;
-
- sdla_start(dev);
- if (sdla_z80_poll(dev, 0, 3*HZ, Z80_READY, 0) < 0)
- return -EIO;
-
- data = LOADER_READY;
- sdla_write(dev, 0, &data, 1);
-
- if ((jiffs = sdla_z80_poll(dev, 0, 8*HZ, Z80_SCC_OK, Z80_SCC_BAD)) < 0)
- return -EIO;
-
- sdla_stop(dev);
- sdla_read(dev, 0, &data, 1);
-
- if (data == Z80_SCC_BAD)
- {
- printk("%s: SCC bad\n", dev->name);
- return -EIO;
- }
-
- if (data != Z80_SCC_OK)
- return -EINVAL;
-
- if (jiffs < 165)
- ifr->ifr_mtu = SDLA_CPU_16M;
- else if (jiffs < 220)
- ifr->ifr_mtu = SDLA_CPU_10M;
- else if (jiffs < 258)
- ifr->ifr_mtu = SDLA_CPU_8M;
- else if (jiffs < 357)
- ifr->ifr_mtu = SDLA_CPU_7M;
- else if (jiffs < 467)
- ifr->ifr_mtu = SDLA_CPU_5M;
- else
- ifr->ifr_mtu = SDLA_CPU_3M;
-
- return 0;
-}
-
-/************************************************
- *
- * Direct interaction with the Frame Relay code
- * starts here.
- *
- ************************************************/
-
-struct _dlci_stat
-{
- short dlci;
- char flags;
-} __packed;
-
-struct _frad_stat
-{
- char flags;
- struct _dlci_stat dlcis[SDLA_MAX_DLCI];
-};
-
-static void sdla_errors(struct net_device *dev, int cmd, int dlci, int ret, int len, void *data)
-{
- struct _dlci_stat *pstatus;
- short *pdlci;
- int i;
- char *state, line[30];
-
- switch (ret)
- {
- case SDLA_RET_MODEM:
- state = data;
- if (*state & SDLA_MODEM_DCD_LOW)
- netdev_info(dev, "Modem DCD unexpectedly low!\n");
- if (*state & SDLA_MODEM_CTS_LOW)
- netdev_info(dev, "Modem CTS unexpectedly low!\n");
- /* I should probably do something about this! */
- break;
-
- case SDLA_RET_CHANNEL_OFF:
- netdev_info(dev, "Channel became inoperative!\n");
- /* same here */
- break;
-
- case SDLA_RET_CHANNEL_ON:
- netdev_info(dev, "Channel became operative!\n");
- /* same here */
- break;
-
- case SDLA_RET_DLCI_STATUS:
- netdev_info(dev, "Status change reported by Access Node\n");
- len /= sizeof(struct _dlci_stat);
- for(pstatus = data, i=0;i < len;i++,pstatus++)
- {
- if (pstatus->flags & SDLA_DLCI_NEW)
- state = "new";
- else if (pstatus->flags & SDLA_DLCI_DELETED)
- state = "deleted";
- else if (pstatus->flags & SDLA_DLCI_ACTIVE)
- state = "active";
- else
- {
- sprintf(line, "unknown status: %02X", pstatus->flags);
- state = line;
- }
- netdev_info(dev, "DLCI %i: %s\n",
- pstatus->dlci, state);
- /* same here */
- }
- break;
-
- case SDLA_RET_DLCI_UNKNOWN:
- netdev_info(dev, "Received unknown DLCIs:");
- len /= sizeof(short);
- for(pdlci = data,i=0;i < len;i++,pdlci++)
- pr_cont(" %i", *pdlci);
- pr_cont("\n");
- break;
-
- case SDLA_RET_TIMEOUT:
- netdev_err(dev, "Command timed out!\n");
- break;
-
- case SDLA_RET_BUF_OVERSIZE:
- netdev_info(dev, "Bc/CIR overflow, acceptable size is %i\n",
- len);
- break;
-
- case SDLA_RET_BUF_TOO_BIG:
- netdev_info(dev, "Buffer size over specified max of %i\n",
- len);
- break;
-
- case SDLA_RET_CHANNEL_INACTIVE:
- case SDLA_RET_DLCI_INACTIVE:
- case SDLA_RET_CIR_OVERFLOW:
- case SDLA_RET_NO_BUFS:
- if (cmd == SDLA_INFORMATION_WRITE)
- break;
- fallthrough;
-
- default:
- netdev_dbg(dev, "Cmd 0x%02X generated return code 0x%02X\n",
- cmd, ret);
- /* Further processing could be done here */
- break;
- }
-}
-
-static int sdla_cmd(struct net_device *dev, int cmd, short dlci, short flags,
- void *inbuf, short inlen, void *outbuf, short *outlen)
-{
- static struct _frad_stat status;
- struct frad_local *flp;
- struct sdla_cmd *cmd_buf;
- unsigned long pflags;
- unsigned long jiffs;
- int ret, waiting, len;
- long window;
-
- flp = netdev_priv(dev);
- window = flp->type == SDLA_S508 ? SDLA_508_CMD_BUF : SDLA_502_CMD_BUF;
- cmd_buf = (struct sdla_cmd *)(dev->mem_start + (window & SDLA_ADDR_MASK));
- ret = 0;
- len = 0;
- jiffs = jiffies + HZ; /* 1 second is plenty */
-
- spin_lock_irqsave(&sdla_lock, pflags);
- SDLA_WINDOW(dev, window);
- cmd_buf->cmd = cmd;
- cmd_buf->dlci = dlci;
- cmd_buf->flags = flags;
-
- if (inbuf)
- memcpy(cmd_buf->data, inbuf, inlen);
-
- cmd_buf->length = inlen;
-
- cmd_buf->opp_flag = 1;
- spin_unlock_irqrestore(&sdla_lock, pflags);
-
- waiting = 1;
- len = 0;
- while (waiting && time_before_eq(jiffies, jiffs))
- {
- if (waiting++ % 3)
- {
- spin_lock_irqsave(&sdla_lock, pflags);
- SDLA_WINDOW(dev, window);
- waiting = ((volatile int)(cmd_buf->opp_flag));
- spin_unlock_irqrestore(&sdla_lock, pflags);
- }
- }
-
- if (!waiting)
- {
-
- spin_lock_irqsave(&sdla_lock, pflags);
- SDLA_WINDOW(dev, window);
- ret = cmd_buf->retval;
- len = cmd_buf->length;
- if (outbuf && outlen)
- {
- *outlen = *outlen >= len ? len : *outlen;
-
- if (*outlen)
- memcpy(outbuf, cmd_buf->data, *outlen);
- }
-
- /* This is a local copy that's used for error handling */
- if (ret)
- memcpy(&status, cmd_buf->data, len > sizeof(status) ? sizeof(status) : len);
-
- spin_unlock_irqrestore(&sdla_lock, pflags);
- }
- else
- ret = SDLA_RET_TIMEOUT;
-
- if (ret != SDLA_RET_OK)
- sdla_errors(dev, cmd, dlci, ret, len, &status);
-
- return ret;
-}
-
-/***********************************************
- *
- * these functions are called by the DLCI driver
- *
- ***********************************************/
-
-static int sdla_reconfig(struct net_device *dev);
-
-static int sdla_activate(struct net_device *slave, struct net_device *master)
-{
- struct frad_local *flp;
- int i;
-
- flp = netdev_priv(slave);
-
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- if (flp->master[i] == master)
- break;
-
- if (i == CONFIG_DLCI_MAX)
- return -ENODEV;
-
- flp->dlci[i] = abs(flp->dlci[i]);
-
- if (netif_running(slave) && (flp->config.station == FRAD_STATION_NODE))
- sdla_cmd(slave, SDLA_ACTIVATE_DLCI, 0, 0, &flp->dlci[i], sizeof(short), NULL, NULL);
-
- return 0;
-}
-
-static int sdla_deactivate(struct net_device *slave, struct net_device *master)
-{
- struct frad_local *flp;
- int i;
-
- flp = netdev_priv(slave);
-
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- if (flp->master[i] == master)
- break;
-
- if (i == CONFIG_DLCI_MAX)
- return -ENODEV;
-
- flp->dlci[i] = -abs(flp->dlci[i]);
-
- if (netif_running(slave) && (flp->config.station == FRAD_STATION_NODE))
- sdla_cmd(slave, SDLA_DEACTIVATE_DLCI, 0, 0, &flp->dlci[i], sizeof(short), NULL, NULL);
-
- return 0;
-}
-
-static int sdla_assoc(struct net_device *slave, struct net_device *master)
-{
- struct frad_local *flp;
- int i;
-
- if (master->type != ARPHRD_DLCI)
- return -EINVAL;
-
- flp = netdev_priv(slave);
-
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- {
- if (!flp->master[i])
- break;
- if (abs(flp->dlci[i]) == *(short *)(master->dev_addr))
- return -EADDRINUSE;
- }
-
- if (i == CONFIG_DLCI_MAX)
- return -EMLINK; /* #### Alan: Comments on this ?? */
-
-
- flp->master[i] = master;
- flp->dlci[i] = -*(short *)(master->dev_addr);
- master->mtu = slave->mtu;
-
- if (netif_running(slave)) {
- if (flp->config.station == FRAD_STATION_CPE)
- sdla_reconfig(slave);
- else
- sdla_cmd(slave, SDLA_ADD_DLCI, 0, 0, master->dev_addr, sizeof(short), NULL, NULL);
- }
-
- return 0;
-}
-
-static int sdla_deassoc(struct net_device *slave, struct net_device *master)
-{
- struct frad_local *flp;
- int i;
-
- flp = netdev_priv(slave);
-
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- if (flp->master[i] == master)
- break;
-
- if (i == CONFIG_DLCI_MAX)
- return -ENODEV;
-
- flp->master[i] = NULL;
- flp->dlci[i] = 0;
-
-
- if (netif_running(slave)) {
- if (flp->config.station == FRAD_STATION_CPE)
- sdla_reconfig(slave);
- else
- sdla_cmd(slave, SDLA_DELETE_DLCI, 0, 0, master->dev_addr, sizeof(short), NULL, NULL);
- }
-
- return 0;
-}
-
-static int sdla_dlci_conf(struct net_device *slave, struct net_device *master, int get)
-{
- struct frad_local *flp;
- struct dlci_local *dlp;
- int i;
- short len, ret;
-
- flp = netdev_priv(slave);
-
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- if (flp->master[i] == master)
- break;
-
- if (i == CONFIG_DLCI_MAX)
- return -ENODEV;
-
- dlp = netdev_priv(master);
-
- ret = SDLA_RET_OK;
- len = sizeof(struct dlci_conf);
- if (netif_running(slave)) {
- if (get)
- ret = sdla_cmd(slave, SDLA_READ_DLCI_CONFIGURATION, abs(flp->dlci[i]), 0,
- NULL, 0, &dlp->config, &len);
- else
- ret = sdla_cmd(slave, SDLA_SET_DLCI_CONFIGURATION, abs(flp->dlci[i]), 0,
- &dlp->config, sizeof(struct dlci_conf) - 4 * sizeof(short), NULL, NULL);
- }
-
- return ret == SDLA_RET_OK ? 0 : -EIO;
-}
-
-/**************************
- *
- * now for the Linux driver
- *
- **************************/
-
-/* NOTE: the DLCI driver deals with freeing the SKB!! */
-static netdev_tx_t sdla_transmit(struct sk_buff *skb,
- struct net_device *dev)
-{
- struct frad_local *flp;
- int ret, addr, accept, i;
- short size;
- unsigned long flags;
- struct buf_entry *pbuf;
-
- flp = netdev_priv(dev);
- ret = 0;
- accept = 1;
-
- netif_stop_queue(dev);
-
- /*
- * stupid GateD insists on setting up the multicast router thru us
- * and we're ill equipped to handle a non Frame Relay packet at this
- * time!
- */
-
- accept = 1;
- switch (dev->type)
- {
- case ARPHRD_FRAD:
- if (skb->dev->type != ARPHRD_DLCI)
- {
- netdev_warn(dev, "Non DLCI device, type %i, tried to send on FRAD module\n",
- skb->dev->type);
- accept = 0;
- }
- break;
- default:
- netdev_warn(dev, "unknown firmware type 0x%04X\n",
- dev->type);
- accept = 0;
- break;
- }
- if (accept)
- {
- /* this is frame specific, but till there's a PPP module, it's the default */
- switch (flp->type)
- {
- case SDLA_S502A:
- case SDLA_S502E:
- ret = sdla_cmd(dev, SDLA_INFORMATION_WRITE, *(short *)(skb->dev->dev_addr), 0, skb->data, skb->len, NULL, NULL);
- break;
- case SDLA_S508:
- size = sizeof(addr);
- ret = sdla_cmd(dev, SDLA_INFORMATION_WRITE, *(short *)(skb->dev->dev_addr), 0, NULL, skb->len, &addr, &size);
- if (ret == SDLA_RET_OK)
- {
-
- spin_lock_irqsave(&sdla_lock, flags);
- SDLA_WINDOW(dev, addr);
- pbuf = (void *)(dev->mem_start + (addr & SDLA_ADDR_MASK));
- __sdla_write(dev, pbuf->buf_addr, skb->data, skb->len);
- SDLA_WINDOW(dev, addr);
- pbuf->opp_flag = 1;
- spin_unlock_irqrestore(&sdla_lock, flags);
- }
- break;
- }
-
- switch (ret)
- {
- case SDLA_RET_OK:
- dev->stats.tx_packets++;
- break;
-
- case SDLA_RET_CIR_OVERFLOW:
- case SDLA_RET_BUF_OVERSIZE:
- case SDLA_RET_NO_BUFS:
- dev->stats.tx_dropped++;
- break;
-
- default:
- dev->stats.tx_errors++;
- break;
- }
- }
- netif_wake_queue(dev);
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- {
- if(flp->master[i]!=NULL)
- netif_wake_queue(flp->master[i]);
- }
-
- dev_kfree_skb(skb);
- return NETDEV_TX_OK;
-}
-
-static void sdla_receive(struct net_device *dev)
-{
- struct net_device *master;
- struct frad_local *flp;
- struct dlci_local *dlp;
- struct sk_buff *skb;
-
- struct sdla_cmd *cmd;
- struct buf_info *pbufi;
- struct buf_entry *pbuf;
-
- unsigned long flags;
- int i=0, received, success, addr, buf_base, buf_top;
- short dlci, len, len2, split;
-
- flp = netdev_priv(dev);
- success = 1;
- received = addr = buf_top = buf_base = 0;
- len = dlci = 0;
- skb = NULL;
- master = NULL;
- cmd = NULL;
- pbufi = NULL;
- pbuf = NULL;
-
- spin_lock_irqsave(&sdla_lock, flags);
-
- switch (flp->type)
- {
- case SDLA_S502A:
- case SDLA_S502E:
- cmd = (void *) (dev->mem_start + (SDLA_502_RCV_BUF & SDLA_ADDR_MASK));
- SDLA_WINDOW(dev, SDLA_502_RCV_BUF);
- success = cmd->opp_flag;
- if (!success)
- break;
-
- dlci = cmd->dlci;
- len = cmd->length;
- break;
-
- case SDLA_S508:
- pbufi = (void *) (dev->mem_start + (SDLA_508_RXBUF_INFO & SDLA_ADDR_MASK));
- SDLA_WINDOW(dev, SDLA_508_RXBUF_INFO);
- pbuf = (void *) (dev->mem_start + ((pbufi->rse_base + flp->buffer * sizeof(struct buf_entry)) & SDLA_ADDR_MASK));
- success = pbuf->opp_flag;
- if (!success)
- break;
-
- buf_top = pbufi->buf_top;
- buf_base = pbufi->buf_base;
- dlci = pbuf->dlci;
- len = pbuf->length;
- addr = pbuf->buf_addr;
- break;
- }
-
- /* common code, find the DLCI and get the SKB */
- if (success)
- {
- for (i=0;i<CONFIG_DLCI_MAX;i++)
- if (flp->dlci[i] == dlci)
- break;
-
- if (i == CONFIG_DLCI_MAX)
- {
- netdev_notice(dev, "Received packet from invalid DLCI %i, ignoring\n",
- dlci);
- dev->stats.rx_errors++;
- success = 0;
- }
- }
-
- if (success)
- {
- master = flp->master[i];
- skb = dev_alloc_skb(len + sizeof(struct frhdr));
- if (skb == NULL)
- {
- netdev_notice(dev, "Memory squeeze, dropping packet\n");
- dev->stats.rx_dropped++;
- success = 0;
- }
- else
- skb_reserve(skb, sizeof(struct frhdr));
- }
-
- /* pick up the data */
- switch (flp->type)
- {
- case SDLA_S502A:
- case SDLA_S502E:
- if (success)
- __sdla_read(dev, SDLA_502_RCV_BUF + SDLA_502_DATA_OFS, skb_put(skb,len), len);
-
- SDLA_WINDOW(dev, SDLA_502_RCV_BUF);
- cmd->opp_flag = 0;
- break;
-
- case SDLA_S508:
- if (success)
- {
- /* is this buffer split off the end of the internal ring buffer */
- split = addr + len > buf_top + 1 ? len - (buf_top - addr + 1) : 0;
- len2 = len - split;
-
- __sdla_read(dev, addr, skb_put(skb, len2), len2);
- if (split)
- __sdla_read(dev, buf_base, skb_put(skb, split), split);
- }
-
- /* increment the buffer we're looking at */
- SDLA_WINDOW(dev, SDLA_508_RXBUF_INFO);
- flp->buffer = (flp->buffer + 1) % pbufi->rse_num;
- pbuf->opp_flag = 0;
- break;
- }
-
- if (success)
- {
- dev->stats.rx_packets++;
- dlp = netdev_priv(master);
- (*dlp->receive)(skb, master);
- }
-
- spin_unlock_irqrestore(&sdla_lock, flags);
-}
-
-static irqreturn_t sdla_isr(int dummy, void *dev_id)
-{
- struct net_device *dev;
- struct frad_local *flp;
- char byte;
-
- dev = dev_id;
-
- flp = netdev_priv(dev);
-
- if (!flp->initialized)
- {
- netdev_warn(dev, "irq %d for uninitialized device\n", dev->irq);
- return IRQ_NONE;
- }
-
- byte = sdla_byte(dev, flp->type == SDLA_S508 ? SDLA_508_IRQ_INTERFACE : SDLA_502_IRQ_INTERFACE);
- switch (byte)
- {
- case SDLA_INTR_RX:
- sdla_receive(dev);
- break;
-
- /* the command will get an error return, which is processed above */
- case SDLA_INTR_MODEM:
- case SDLA_INTR_STATUS:
- sdla_cmd(dev, SDLA_READ_DLC_STATUS, 0, 0, NULL, 0, NULL, NULL);
- break;
-
- case SDLA_INTR_TX:
- case SDLA_INTR_COMPLETE:
- case SDLA_INTR_TIMER:
- netdev_warn(dev, "invalid irq flag 0x%02X\n", byte);
- break;
- }
-
- /* the S502E requires a manual acknowledgement of the interrupt */
- if (flp->type == SDLA_S502E)
- {
- flp->state &= ~SDLA_S502E_INTACK;
- outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
- flp->state |= SDLA_S502E_INTACK;
- outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
- }
-
- /* this clears the byte, informing the Z80 we're done */
- byte = 0;
- sdla_write(dev, flp->type == SDLA_S508 ? SDLA_508_IRQ_INTERFACE : SDLA_502_IRQ_INTERFACE, &byte, sizeof(byte));
- return IRQ_HANDLED;
-}
-
-static void sdla_poll(struct timer_list *t)
-{
- 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);
-
- flp->timer.expires = 1;
- add_timer(&flp->timer);
-}
-
-static int sdla_close(struct net_device *dev)
-{
- struct frad_local *flp;
- struct intr_info intr;
- int len, i;
- short dlcis[CONFIG_DLCI_MAX];
-
- flp = netdev_priv(dev);
-
- len = 0;
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- if (flp->dlci[i])
- dlcis[len++] = abs(flp->dlci[i]);
- len *= 2;
-
- if (flp->config.station == FRAD_STATION_NODE)
- {
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- if (flp->dlci[i] > 0)
- sdla_cmd(dev, SDLA_DEACTIVATE_DLCI, 0, 0, dlcis, len, NULL, NULL);
- sdla_cmd(dev, SDLA_DELETE_DLCI, 0, 0, &flp->dlci[i], sizeof(flp->dlci[i]), NULL, NULL);
- }
-
- memset(&intr, 0, sizeof(intr));
- /* let's start up the reception */
- switch(flp->type)
- {
- case SDLA_S502A:
- del_timer(&flp->timer);
- break;
-
- case SDLA_S502E:
- sdla_cmd(dev, SDLA_SET_IRQ_TRIGGER, 0, 0, &intr, sizeof(char) + sizeof(short), NULL, NULL);
- flp->state &= ~SDLA_S502E_INTACK;
- outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
- break;
-
- case SDLA_S507:
- break;
-
- case SDLA_S508:
- sdla_cmd(dev, SDLA_SET_IRQ_TRIGGER, 0, 0, &intr, sizeof(struct intr_info), NULL, NULL);
- flp->state &= ~SDLA_S508_INTEN;
- outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
- break;
- }
-
- sdla_cmd(dev, SDLA_DISABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL);
-
- netif_stop_queue(dev);
-
- return 0;
-}
-
-struct conf_data {
- struct frad_conf config;
- short dlci[CONFIG_DLCI_MAX];
-};
-
-static int sdla_open(struct net_device *dev)
-{
- struct frad_local *flp;
- struct dlci_local *dlp;
- struct conf_data data;
- struct intr_info intr;
- int len, i;
- char byte;
-
- flp = netdev_priv(dev);
-
- if (!flp->initialized)
- return -EPERM;
-
- if (!flp->configured)
- return -EPERM;
-
- /* time to send in the configuration */
- len = 0;
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- if (flp->dlci[i])
- data.dlci[len++] = abs(flp->dlci[i]);
- len *= 2;
-
- memcpy(&data.config, &flp->config, sizeof(struct frad_conf));
- len += sizeof(struct frad_conf);
-
- sdla_cmd(dev, SDLA_DISABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL);
- sdla_cmd(dev, SDLA_SET_DLCI_CONFIGURATION, 0, 0, &data, len, NULL, NULL);
-
- if (flp->type == SDLA_S508)
- flp->buffer = 0;
-
- sdla_cmd(dev, SDLA_ENABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL);
-
- /* let's start up the reception */
- memset(&intr, 0, sizeof(intr));
- switch(flp->type)
- {
- case SDLA_S502A:
- flp->timer.expires = 1;
- add_timer(&flp->timer);
- break;
-
- case SDLA_S502E:
- flp->state |= SDLA_S502E_ENABLE;
- outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
- flp->state |= SDLA_S502E_INTACK;
- outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
- byte = 0;
- sdla_write(dev, SDLA_502_IRQ_INTERFACE, &byte, sizeof(byte));
- intr.flags = SDLA_INTR_RX | SDLA_INTR_STATUS | SDLA_INTR_MODEM;
- sdla_cmd(dev, SDLA_SET_IRQ_TRIGGER, 0, 0, &intr, sizeof(char) + sizeof(short), NULL, NULL);
- break;
-
- case SDLA_S507:
- break;
-
- case SDLA_S508:
- flp->state |= SDLA_S508_INTEN;
- outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
- byte = 0;
- sdla_write(dev, SDLA_508_IRQ_INTERFACE, &byte, sizeof(byte));
- intr.flags = SDLA_INTR_RX | SDLA_INTR_STATUS | SDLA_INTR_MODEM;
- intr.irq = dev->irq;
- sdla_cmd(dev, SDLA_SET_IRQ_TRIGGER, 0, 0, &intr, sizeof(struct intr_info), NULL, NULL);
- break;
- }
-
- if (flp->config.station == FRAD_STATION_CPE)
- {
- byte = SDLA_ICS_STATUS_ENQ;
- sdla_cmd(dev, SDLA_ISSUE_IN_CHANNEL_SIGNAL, 0, 0, &byte, sizeof(byte), NULL, NULL);
- }
- else
- {
- sdla_cmd(dev, SDLA_ADD_DLCI, 0, 0, data.dlci, len - sizeof(struct frad_conf), NULL, NULL);
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- if (flp->dlci[i] > 0)
- sdla_cmd(dev, SDLA_ACTIVATE_DLCI, 0, 0, &flp->dlci[i], 2*sizeof(flp->dlci[i]), NULL, NULL);
- }
-
- /* configure any specific DLCI settings */
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- if (flp->dlci[i])
- {
- dlp = netdev_priv(flp->master[i]);
- if (dlp->configured)
- sdla_cmd(dev, SDLA_SET_DLCI_CONFIGURATION, abs(flp->dlci[i]), 0, &dlp->config, sizeof(struct dlci_conf), NULL, NULL);
- }
-
- netif_start_queue(dev);
-
- return 0;
-}
-
-static int sdla_config(struct net_device *dev, struct frad_conf __user *conf, int get)
-{
- struct frad_local *flp;
- struct conf_data data;
- int i;
- short size;
-
- if (dev->type == 0xFFFF)
- return -EUNATCH;
-
- flp = netdev_priv(dev);
-
- if (!get)
- {
- if (netif_running(dev))
- return -EBUSY;
-
- if(copy_from_user(&data.config, conf, sizeof(struct frad_conf)))
- return -EFAULT;
-
- if (data.config.station & ~FRAD_STATION_NODE)
- return -EINVAL;
-
- if (data.config.flags & ~FRAD_VALID_FLAGS)
- return -EINVAL;
-
- if ((data.config.kbaud < 0) ||
- ((data.config.kbaud > 128) && (flp->type != SDLA_S508)))
- return -EINVAL;
-
- if (data.config.clocking & ~(FRAD_CLOCK_INT | SDLA_S508_PORT_RS232))
- return -EINVAL;
-
- if ((data.config.mtu < 0) || (data.config.mtu > SDLA_MAX_MTU))
- return -EINVAL;
-
- if ((data.config.T391 < 5) || (data.config.T391 > 30))
- return -EINVAL;
-
- if ((data.config.T392 < 5) || (data.config.T392 > 30))
- return -EINVAL;
-
- if ((data.config.N391 < 1) || (data.config.N391 > 255))
- return -EINVAL;
-
- if ((data.config.N392 < 1) || (data.config.N392 > 10))
- return -EINVAL;
-
- if ((data.config.N393 < 1) || (data.config.N393 > 10))
- return -EINVAL;
-
- memcpy(&flp->config, &data.config, sizeof(struct frad_conf));
- flp->config.flags |= SDLA_DIRECT_RECV;
-
- if (flp->type == SDLA_S508)
- flp->config.flags |= SDLA_TX70_RX30;
-
- if (dev->mtu != flp->config.mtu)
- {
- /* this is required to change the MTU */
- dev->mtu = flp->config.mtu;
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- if (flp->master[i])
- flp->master[i]->mtu = flp->config.mtu;
- }
-
- flp->config.mtu += sizeof(struct frhdr);
-
- /* off to the races! */
- if (!flp->configured)
- sdla_start(dev);
-
- flp->configured = 1;
- }
- else
- {
- /* no sense reading if the CPU isn't started */
- if (netif_running(dev))
- {
- size = sizeof(data);
- if (sdla_cmd(dev, SDLA_READ_DLCI_CONFIGURATION, 0, 0, NULL, 0, &data, &size) != SDLA_RET_OK)
- return -EIO;
- }
- else
- if (flp->configured)
- memcpy(&data.config, &flp->config, sizeof(struct frad_conf));
- else
- memset(&data.config, 0, sizeof(struct frad_conf));
-
- memcpy(&flp->config, &data.config, sizeof(struct frad_conf));
- data.config.flags &= FRAD_VALID_FLAGS;
- data.config.mtu -= data.config.mtu > sizeof(struct frhdr) ? sizeof(struct frhdr) : data.config.mtu;
- return copy_to_user(conf, &data.config, sizeof(struct frad_conf))?-EFAULT:0;
- }
-
- return 0;
-}
-
-static int sdla_xfer(struct net_device *dev, struct sdla_mem __user *info, int read)
-{
- struct sdla_mem mem;
- char *temp;
-
- if(copy_from_user(&mem, info, sizeof(mem)))
- return -EFAULT;
-
- if (read)
- {
- temp = kzalloc(mem.len, GFP_KERNEL);
- if (!temp)
- return -ENOMEM;
- sdla_read(dev, mem.addr, temp, mem.len);
- if(copy_to_user(mem.data, temp, mem.len))
- {
- kfree(temp);
- return -EFAULT;
- }
- kfree(temp);
- }
- else
- {
- temp = memdup_user(mem.data, mem.len);
- if (IS_ERR(temp))
- return PTR_ERR(temp);
- sdla_write(dev, mem.addr, temp, mem.len);
- kfree(temp);
- }
- return 0;
-}
-
-static int sdla_reconfig(struct net_device *dev)
-{
- struct frad_local *flp;
- struct conf_data data;
- int i, len;
-
- flp = netdev_priv(dev);
-
- len = 0;
- for(i=0;i<CONFIG_DLCI_MAX;i++)
- if (flp->dlci[i])
- data.dlci[len++] = flp->dlci[i];
- len *= 2;
-
- memcpy(&data, &flp->config, sizeof(struct frad_conf));
- len += sizeof(struct frad_conf);
-
- sdla_cmd(dev, SDLA_DISABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL);
- sdla_cmd(dev, SDLA_SET_DLCI_CONFIGURATION, 0, 0, &data, len, NULL, NULL);
- sdla_cmd(dev, SDLA_ENABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL);
-
- return 0;
-}
-
-static int sdla_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
- struct frad_local *flp;
-
- if(!capable(CAP_NET_ADMIN))
- return -EPERM;
-
- flp = netdev_priv(dev);
-
- if (!flp->initialized)
- return -EINVAL;
-
- switch (cmd)
- {
- case FRAD_GET_CONF:
- case FRAD_SET_CONF:
- return sdla_config(dev, ifr->ifr_data, cmd == FRAD_GET_CONF);
-
- case SDLA_IDENTIFY:
- ifr->ifr_flags = flp->type;
- break;
-
- case SDLA_CPUSPEED:
- return sdla_cpuspeed(dev, ifr);
-
-/* ==========================================================
-NOTE: This is rather a useless action right now, as the
- current driver does not support protocols other than
- FR. However, Sangoma has modules for a number of
- other protocols in the works.
-============================================================*/
- case SDLA_PROTOCOL:
- if (flp->configured)
- return -EALREADY;
-
- switch (ifr->ifr_flags)
- {
- case ARPHRD_FRAD:
- dev->type = ifr->ifr_flags;
- break;
- default:
- return -ENOPROTOOPT;
- }
- break;
-
- case SDLA_CLEARMEM:
- sdla_clear(dev);
- break;
-
- case SDLA_WRITEMEM:
- case SDLA_READMEM:
- if(!capable(CAP_SYS_RAWIO))
- return -EPERM;
- return sdla_xfer(dev, ifr->ifr_data, cmd == SDLA_READMEM);
-
- case SDLA_START:
- sdla_start(dev);
- break;
-
- case SDLA_STOP:
- sdla_stop(dev);
- break;
-
- default:
- return -EOPNOTSUPP;
- }
- return 0;
-}
-
-static int sdla_change_mtu(struct net_device *dev, int new_mtu)
-{
- if (netif_running(dev))
- return -EBUSY;
-
- /* for now, you can't change the MTU! */
- return -EOPNOTSUPP;
-}
-
-static int sdla_set_config(struct net_device *dev, struct ifmap *map)
-{
- struct frad_local *flp;
- int i;
- char byte;
- unsigned base;
- int err = -EINVAL;
-
- flp = netdev_priv(dev);
-
- if (flp->initialized)
- return -EINVAL;
-
- for(i=0; i < ARRAY_SIZE(valid_port); i++)
- if (valid_port[i] == map->base_addr)
- break;
-
- if (i == ARRAY_SIZE(valid_port))
- return -EINVAL;
-
- if (!request_region(map->base_addr, SDLA_IO_EXTENTS, dev->name)){
- pr_warn("io-port 0x%04lx in use\n", dev->base_addr);
- return -EINVAL;
- }
- base = map->base_addr;
-
- /* test for card types, S502A, S502E, S507, S508 */
- /* these tests shut down the card completely, so clear the state */
- flp->type = SDLA_UNKNOWN;
- flp->state = 0;
-
- for(i=1;i<SDLA_IO_EXTENTS;i++)
- if (inb(base + i) != 0xFF)
- break;
-
- if (i == SDLA_IO_EXTENTS) {
- outb(SDLA_HALT, base + SDLA_REG_Z80_CONTROL);
- if ((inb(base + SDLA_S502_STS) & 0x0F) == 0x08) {
- outb(SDLA_S502E_INTACK, base + SDLA_REG_CONTROL);
- if ((inb(base + SDLA_S502_STS) & 0x0F) == 0x0C) {
- outb(SDLA_HALT, base + SDLA_REG_CONTROL);
- flp->type = SDLA_S502E;
- goto got_type;
- }
- }
- }
-
- for(byte=inb(base),i=0;i<SDLA_IO_EXTENTS;i++)
- if (inb(base + i) != byte)
- break;
-
- if (i == SDLA_IO_EXTENTS) {
- outb(SDLA_HALT, base + SDLA_REG_CONTROL);
- if ((inb(base + SDLA_S502_STS) & 0x7E) == 0x30) {
- outb(SDLA_S507_ENABLE, base + SDLA_REG_CONTROL);
- if ((inb(base + SDLA_S502_STS) & 0x7E) == 0x32) {
- outb(SDLA_HALT, base + SDLA_REG_CONTROL);
- flp->type = SDLA_S507;
- goto got_type;
- }
- }
- }
-
- outb(SDLA_HALT, base + SDLA_REG_CONTROL);
- if ((inb(base + SDLA_S508_STS) & 0x3F) == 0x00) {
- outb(SDLA_S508_INTEN, base + SDLA_REG_CONTROL);
- if ((inb(base + SDLA_S508_STS) & 0x3F) == 0x10) {
- outb(SDLA_HALT, base + SDLA_REG_CONTROL);
- flp->type = SDLA_S508;
- goto got_type;
- }
- }
-
- outb(SDLA_S502A_HALT, base + SDLA_REG_CONTROL);
- if (inb(base + SDLA_S502_STS) == 0x40) {
- outb(SDLA_S502A_START, base + SDLA_REG_CONTROL);
- if (inb(base + SDLA_S502_STS) == 0x40) {
- outb(SDLA_S502A_INTEN, base + SDLA_REG_CONTROL);
- if (inb(base + SDLA_S502_STS) == 0x44) {
- outb(SDLA_S502A_START, base + SDLA_REG_CONTROL);
- flp->type = SDLA_S502A;
- goto got_type;
- }
- }
- }
-
- netdev_notice(dev, "Unknown card type\n");
- err = -ENODEV;
- goto fail;
-
-got_type:
- switch(base) {
- case 0x270:
- case 0x280:
- case 0x380:
- case 0x390:
- if (flp->type != SDLA_S508 && flp->type != SDLA_S507)
- goto fail;
- }
-
- switch (map->irq) {
- case 2:
- if (flp->type != SDLA_S502E)
- goto fail;
- break;
-
- case 10:
- case 11:
- case 12:
- case 15:
- case 4:
- if (flp->type != SDLA_S508 && flp->type != SDLA_S507)
- goto fail;
- break;
- case 3:
- case 5:
- case 7:
- if (flp->type == SDLA_S502A)
- goto fail;
- break;
-
- default:
- goto fail;
- }
-
- err = -EAGAIN;
- if (request_irq(dev->irq, sdla_isr, 0, dev->name, dev))
- goto fail;
-
- if (flp->type == SDLA_S507) {
- switch(dev->irq) {
- case 3:
- flp->state = SDLA_S507_IRQ3;
- break;
- case 4:
- flp->state = SDLA_S507_IRQ4;
- break;
- case 5:
- flp->state = SDLA_S507_IRQ5;
- break;
- case 7:
- flp->state = SDLA_S507_IRQ7;
- break;
- case 10:
- flp->state = SDLA_S507_IRQ10;
- break;
- case 11:
- flp->state = SDLA_S507_IRQ11;
- break;
- case 12:
- flp->state = SDLA_S507_IRQ12;
- break;
- case 15:
- flp->state = SDLA_S507_IRQ15;
- break;
- }
- }
-
- for(i=0; i < ARRAY_SIZE(valid_mem); i++)
- if (valid_mem[i] == map->mem_start)
- break;
-
- err = -EINVAL;
- if (i == ARRAY_SIZE(valid_mem))
- goto fail2;
-
- if (flp->type == SDLA_S502A && (map->mem_start & 0xF000) >> 12 == 0x0E)
- goto fail2;
-
- if (flp->type != SDLA_S507 && map->mem_start >> 16 == 0x0B)
- goto fail2;
-
- if (flp->type == SDLA_S507 && map->mem_start >> 16 == 0x0D)
- goto fail2;
-
- byte = flp->type != SDLA_S508 ? SDLA_8K_WINDOW : 0;
- byte |= (map->mem_start & 0xF000) >> (12 + (flp->type == SDLA_S508 ? 1 : 0));
- switch(flp->type) {
- case SDLA_S502A:
- case SDLA_S502E:
- switch (map->mem_start >> 16) {
- case 0x0A:
- byte |= SDLA_S502_SEG_A;
- break;
- case 0x0C:
- byte |= SDLA_S502_SEG_C;
- break;
- case 0x0D:
- byte |= SDLA_S502_SEG_D;
- break;
- case 0x0E:
- byte |= SDLA_S502_SEG_E;
- break;
- }
- break;
- case SDLA_S507:
- switch (map->mem_start >> 16) {
- case 0x0A:
- byte |= SDLA_S507_SEG_A;
- break;
- case 0x0B:
- byte |= SDLA_S507_SEG_B;
- break;
- case 0x0C:
- byte |= SDLA_S507_SEG_C;
- break;
- case 0x0E:
- byte |= SDLA_S507_SEG_E;
- break;
- }
- break;
- case SDLA_S508:
- switch (map->mem_start >> 16) {
- case 0x0A:
- byte |= SDLA_S508_SEG_A;
- break;
- case 0x0C:
- byte |= SDLA_S508_SEG_C;
- break;
- case 0x0D:
- byte |= SDLA_S508_SEG_D;
- break;
- case 0x0E:
- byte |= SDLA_S508_SEG_E;
- break;
- }
- break;
- }
-
- /* set the memory bits, and enable access */
- outb(byte, base + SDLA_REG_PC_WINDOW);
-
- switch(flp->type)
- {
- case SDLA_S502E:
- flp->state = SDLA_S502E_ENABLE;
- break;
- case SDLA_S507:
- flp->state |= SDLA_MEMEN;
- break;
- case SDLA_S508:
- flp->state = SDLA_MEMEN;
- break;
- }
- outb(flp->state, base + SDLA_REG_CONTROL);
-
- dev->irq = map->irq;
- dev->base_addr = base;
- dev->mem_start = map->mem_start;
- dev->mem_end = dev->mem_start + 0x2000;
- flp->initialized = 1;
- return 0;
-
-fail2:
- free_irq(map->irq, dev);
-fail:
- release_region(base, SDLA_IO_EXTENTS);
- return err;
-}
-
-static const struct net_device_ops sdla_netdev_ops = {
- .ndo_open = sdla_open,
- .ndo_stop = sdla_close,
- .ndo_do_ioctl = sdla_ioctl,
- .ndo_set_config = sdla_set_config,
- .ndo_start_xmit = sdla_transmit,
- .ndo_change_mtu = sdla_change_mtu,
-};
-
-static void setup_sdla(struct net_device *dev)
-{
- struct frad_local *flp = netdev_priv(dev);
-
- netdev_boot_setup_check(dev);
-
- dev->netdev_ops = &sdla_netdev_ops;
- dev->flags = 0;
- dev->type = 0xFFFF;
- dev->hard_header_len = 0;
- dev->addr_len = 0;
- dev->mtu = SDLA_MAX_MTU;
-
- flp->activate = sdla_activate;
- flp->deactivate = sdla_deactivate;
- flp->assoc = sdla_assoc;
- flp->deassoc = sdla_deassoc;
- flp->dlci_conf = sdla_dlci_conf;
- flp->dev = dev;
-
- timer_setup(&flp->timer, sdla_poll, 0);
- flp->timer.expires = 1;
-}
-
-static struct net_device *sdla;
-
-static int __init init_sdla(void)
-{
- int err;
-
- printk("%s.\n", version);
-
- sdla = alloc_netdev(sizeof(struct frad_local), "sdla0",
- NET_NAME_UNKNOWN, setup_sdla);
- if (!sdla)
- return -ENOMEM;
-
- err = register_netdev(sdla);
- if (err)
- free_netdev(sdla);
-
- return err;
-}
-
-static void __exit exit_sdla(void)
-{
- struct frad_local *flp = netdev_priv(sdla);
-
- unregister_netdev(sdla);
- if (flp->initialized) {
- free_irq(sdla->irq, sdla);
- release_region(sdla->base_addr, SDLA_IO_EXTENTS);
- }
- del_timer_sync(&flp->timer);
- free_netdev(sdla);
-}
-
-MODULE_LICENSE("GPL");
-
-module_init(init_sdla);
-module_exit(exit_sdla);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Things to sort out:
- *
- * o tbusy handling
- * o allow users to set the parameters
- * o sync/async switching ?
- *
- * Note: This does _not_ implement CCITT X.25 asynchronous framing
- * recommendations. Its primarily for testing purposes. If you wanted
- * to do CCITT then in theory all you need is to nick the HDLC async
- * checksum routines from ppp.c
- * Changes:
- *
- * 2000-10-29 Henner Eisen lapb_data_indication() return status.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-
-#include <linux/uaccess.h>
-#include <linux/bitops.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/interrupt.h>
-#include <linux/in.h>
-#include <linux/tty.h>
-#include <linux/errno.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/lapb.h>
-#include <linux/init.h>
-#include <linux/rtnetlink.h>
-#include <linux/slab.h>
-#include <net/x25device.h>
-#include "x25_asy.h"
-
-static struct net_device **x25_asy_devs;
-static int x25_asy_maxdev = SL_NRUNIT;
-
-module_param(x25_asy_maxdev, int, 0);
-MODULE_LICENSE("GPL");
-
-static int x25_asy_esc(unsigned char *p, unsigned char *d, int len);
-static void x25_asy_unesc(struct x25_asy *sl, unsigned char c);
-static void x25_asy_setup(struct net_device *dev);
-
-/* Find a free X.25 channel, and link in this `tty' line. */
-static struct x25_asy *x25_asy_alloc(void)
-{
- struct net_device *dev = NULL;
- struct x25_asy *sl;
- int i;
-
- if (x25_asy_devs == NULL)
- return NULL; /* Master array missing ! */
-
- for (i = 0; i < x25_asy_maxdev; i++) {
- dev = x25_asy_devs[i];
-
- /* Not allocated ? */
- if (dev == NULL)
- break;
-
- sl = netdev_priv(dev);
- /* Not in use ? */
- if (!test_and_set_bit(SLF_INUSE, &sl->flags))
- return sl;
- }
-
-
- /* Sorry, too many, all slots in use */
- if (i >= x25_asy_maxdev)
- return NULL;
-
- /* If no channels are available, allocate one */
- if (!dev) {
- char name[IFNAMSIZ];
- sprintf(name, "x25asy%d", i);
-
- dev = alloc_netdev(sizeof(struct x25_asy), name,
- NET_NAME_UNKNOWN, x25_asy_setup);
- if (!dev)
- return NULL;
-
- /* Initialize channel control data */
- sl = netdev_priv(dev);
- dev->base_addr = i;
-
- /* register device so that it can be ifconfig'ed */
- if (register_netdev(dev) == 0) {
- /* (Re-)Set the INUSE bit. Very Important! */
- set_bit(SLF_INUSE, &sl->flags);
- x25_asy_devs[i] = dev;
- return sl;
- } else {
- pr_warn("%s(): register_netdev() failure\n", __func__);
- free_netdev(dev);
- }
- }
- return NULL;
-}
-
-
-/* Free an X.25 channel. */
-static void x25_asy_free(struct x25_asy *sl)
-{
- /* Free all X.25 frame buffers. */
- kfree(sl->rbuff);
- sl->rbuff = NULL;
- kfree(sl->xbuff);
- sl->xbuff = NULL;
-
- if (!test_and_clear_bit(SLF_INUSE, &sl->flags))
- netdev_err(sl->dev, "x25_asy_free for already free unit\n");
-}
-
-static int x25_asy_change_mtu(struct net_device *dev, int newmtu)
-{
- struct x25_asy *sl = netdev_priv(dev);
- unsigned char *xbuff, *rbuff;
- int len;
-
- len = 2 * newmtu;
- xbuff = kmalloc(len + 4, GFP_ATOMIC);
- rbuff = kmalloc(len + 4, GFP_ATOMIC);
-
- if (xbuff == NULL || rbuff == NULL) {
- kfree(xbuff);
- kfree(rbuff);
- return -ENOMEM;
- }
-
- spin_lock_bh(&sl->lock);
- xbuff = xchg(&sl->xbuff, xbuff);
- if (sl->xleft) {
- if (sl->xleft <= len) {
- memcpy(sl->xbuff, sl->xhead, sl->xleft);
- } else {
- sl->xleft = 0;
- dev->stats.tx_dropped++;
- }
- }
- sl->xhead = sl->xbuff;
-
- rbuff = xchg(&sl->rbuff, rbuff);
- if (sl->rcount) {
- if (sl->rcount <= len) {
- memcpy(sl->rbuff, rbuff, sl->rcount);
- } else {
- sl->rcount = 0;
- dev->stats.rx_over_errors++;
- set_bit(SLF_ERROR, &sl->flags);
- }
- }
-
- dev->mtu = newmtu;
- sl->buffsize = len;
-
- spin_unlock_bh(&sl->lock);
-
- kfree(xbuff);
- kfree(rbuff);
- return 0;
-}
-
-
-/* Set the "sending" flag. This must be atomic, hence the ASM. */
-
-static inline void x25_asy_lock(struct x25_asy *sl)
-{
- netif_stop_queue(sl->dev);
-}
-
-
-/* Clear the "sending" flag. This must be atomic, hence the ASM. */
-
-static inline void x25_asy_unlock(struct x25_asy *sl)
-{
- netif_wake_queue(sl->dev);
-}
-
-/* Send an LAPB frame to the LAPB module to process. */
-
-static void x25_asy_bump(struct x25_asy *sl)
-{
- struct net_device *dev = sl->dev;
- struct sk_buff *skb;
- int count;
- int err;
-
- count = sl->rcount;
- dev->stats.rx_bytes += count;
-
- skb = dev_alloc_skb(count);
- if (skb == NULL) {
- netdev_warn(sl->dev, "memory squeeze, dropping packet\n");
- dev->stats.rx_dropped++;
- return;
- }
- skb_put_data(skb, sl->rbuff, count);
- err = lapb_data_received(sl->dev, skb);
- if (err != LAPB_OK) {
- kfree_skb(skb);
- printk(KERN_DEBUG "x25_asy: data received err - %d\n", err);
- } else {
- dev->stats.rx_packets++;
- }
-}
-
-/* Encapsulate one IP datagram and stuff into a TTY queue. */
-static void x25_asy_encaps(struct x25_asy *sl, unsigned char *icp, int len)
-{
- unsigned char *p;
- int actual, count, mtu = sl->dev->mtu;
-
- if (len > mtu) {
- /* Sigh, shouldn't occur BUT ... */
- len = mtu;
- printk(KERN_DEBUG "%s: truncating oversized transmit packet!\n",
- sl->dev->name);
- sl->dev->stats.tx_dropped++;
- x25_asy_unlock(sl);
- return;
- }
-
- p = icp;
- count = x25_asy_esc(p, sl->xbuff, len);
-
- /* Order of next two lines is *very* important.
- * When we are sending a little amount of data,
- * the transfer may be completed inside driver.write()
- * routine, because it's running with interrupts enabled.
- * In this case we *never* got WRITE_WAKEUP event,
- * if we did not request it before write operation.
- * 14 Oct 1994 Dmitry Gorodchanin.
- */
- set_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags);
- actual = sl->tty->ops->write(sl->tty, sl->xbuff, count);
- sl->xleft = count - actual;
- sl->xhead = sl->xbuff + actual;
-}
-
-/*
- * Called by the driver when there's room for more data. If we have
- * more packets to send, we send them here.
- */
-static void x25_asy_write_wakeup(struct tty_struct *tty)
-{
- int actual;
- struct x25_asy *sl = tty->disc_data;
-
- /* First make sure we're connected. */
- if (!sl || sl->magic != X25_ASY_MAGIC || !netif_running(sl->dev))
- return;
-
- if (sl->xleft <= 0) {
- /* Now serial buffer is almost free & we can start
- * transmission of another packet */
- sl->dev->stats.tx_packets++;
- clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
- x25_asy_unlock(sl);
- return;
- }
-
- actual = tty->ops->write(tty, sl->xhead, sl->xleft);
- sl->xleft -= actual;
- sl->xhead += actual;
-}
-
-static void x25_asy_timeout(struct net_device *dev, unsigned int txqueue)
-{
- struct x25_asy *sl = netdev_priv(dev);
-
- spin_lock(&sl->lock);
- if (netif_queue_stopped(dev)) {
- /* May be we must check transmitter timeout here ?
- * 14 Oct 1994 Dmitry Gorodchanin.
- */
- netdev_warn(dev, "transmit timed out, %s?\n",
- (tty_chars_in_buffer(sl->tty) || sl->xleft) ?
- "bad line quality" : "driver error");
- sl->xleft = 0;
- clear_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags);
- x25_asy_unlock(sl);
- }
- spin_unlock(&sl->lock);
-}
-
-/* Encapsulate an IP datagram and kick it into a TTY queue. */
-
-static netdev_tx_t x25_asy_xmit(struct sk_buff *skb,
- struct net_device *dev)
-{
- struct x25_asy *sl = netdev_priv(dev);
- int err;
-
- if (!netif_running(sl->dev)) {
- netdev_err(dev, "xmit call when iface is down\n");
- kfree_skb(skb);
- return NETDEV_TX_OK;
- }
-
- /* There should be a pseudo header of 1 byte added by upper layers.
- * Check to make sure it is there before reading it.
- */
- if (skb->len < 1) {
- kfree_skb(skb);
- return NETDEV_TX_OK;
- }
-
- switch (skb->data[0]) {
- case X25_IFACE_DATA:
- break;
- case X25_IFACE_CONNECT: /* Connection request .. do nothing */
- err = lapb_connect_request(dev);
- if (err != LAPB_OK)
- netdev_err(dev, "lapb_connect_request error: %d\n",
- err);
- kfree_skb(skb);
- return NETDEV_TX_OK;
- case X25_IFACE_DISCONNECT: /* do nothing - hang up ?? */
- err = lapb_disconnect_request(dev);
- if (err != LAPB_OK)
- netdev_err(dev, "lapb_disconnect_request error: %d\n",
- err);
- fallthrough;
- default:
- kfree_skb(skb);
- return NETDEV_TX_OK;
- }
- skb_pull(skb, 1); /* Remove control byte */
- /*
- * If we are busy already- too bad. We ought to be able
- * to queue things at this point, to allow for a little
- * frame buffer. Oh well...
- * -----------------------------------------------------
- * I hate queues in X.25 driver. May be it's efficient,
- * but for me latency is more important. ;)
- * So, no queues !
- * 14 Oct 1994 Dmitry Gorodchanin.
- */
-
- err = lapb_data_request(dev, skb);
- if (err != LAPB_OK) {
- netdev_err(dev, "lapb_data_request error: %d\n", err);
- kfree_skb(skb);
- return NETDEV_TX_OK;
- }
- return NETDEV_TX_OK;
-}
-
-
-/*
- * LAPB interface boilerplate
- */
-
-/*
- * Called when I frame data arrive. We add a pseudo header for upper
- * layers and pass it to upper layers.
- */
-
-static int x25_asy_data_indication(struct net_device *dev, struct sk_buff *skb)
-{
- if (skb_cow(skb, 1)) {
- kfree_skb(skb);
- return NET_RX_DROP;
- }
- skb_push(skb, 1);
- skb->data[0] = X25_IFACE_DATA;
-
- skb->protocol = x25_type_trans(skb, dev);
-
- return netif_rx(skb);
-}
-
-/*
- * Data has emerged from the LAPB protocol machine. We don't handle
- * busy cases too well. Its tricky to see how to do this nicely -
- * perhaps lapb should allow us to bounce this ?
- */
-
-static void x25_asy_data_transmit(struct net_device *dev, struct sk_buff *skb)
-{
- struct x25_asy *sl = netdev_priv(dev);
-
- spin_lock(&sl->lock);
- if (netif_queue_stopped(sl->dev) || sl->tty == NULL) {
- spin_unlock(&sl->lock);
- netdev_err(dev, "tbusy drop\n");
- kfree_skb(skb);
- return;
- }
- /* We were not busy, so we are now... :-) */
- if (skb != NULL) {
- x25_asy_lock(sl);
- dev->stats.tx_bytes += skb->len;
- x25_asy_encaps(sl, skb->data, skb->len);
- dev_kfree_skb(skb);
- }
- spin_unlock(&sl->lock);
-}
-
-/*
- * LAPB connection establish/down information.
- */
-
-static void x25_asy_connected(struct net_device *dev, int reason)
-{
- struct x25_asy *sl = netdev_priv(dev);
- struct sk_buff *skb;
- unsigned char *ptr;
-
- skb = dev_alloc_skb(1);
- if (skb == NULL) {
- netdev_err(dev, "out of memory\n");
- return;
- }
-
- ptr = skb_put(skb, 1);
- *ptr = X25_IFACE_CONNECT;
-
- skb->protocol = x25_type_trans(skb, sl->dev);
- netif_rx(skb);
-}
-
-static void x25_asy_disconnected(struct net_device *dev, int reason)
-{
- struct x25_asy *sl = netdev_priv(dev);
- struct sk_buff *skb;
- unsigned char *ptr;
-
- skb = dev_alloc_skb(1);
- if (skb == NULL) {
- netdev_err(dev, "out of memory\n");
- return;
- }
-
- ptr = skb_put(skb, 1);
- *ptr = X25_IFACE_DISCONNECT;
-
- skb->protocol = x25_type_trans(skb, sl->dev);
- netif_rx(skb);
-}
-
-static const struct lapb_register_struct x25_asy_callbacks = {
- .connect_confirmation = x25_asy_connected,
- .connect_indication = x25_asy_connected,
- .disconnect_confirmation = x25_asy_disconnected,
- .disconnect_indication = x25_asy_disconnected,
- .data_indication = x25_asy_data_indication,
- .data_transmit = x25_asy_data_transmit,
-};
-
-
-/* Open the low-level part of the X.25 channel. Easy! */
-static int x25_asy_open(struct net_device *dev)
-{
- struct x25_asy *sl = netdev_priv(dev);
- unsigned long len;
-
- if (sl->tty == NULL)
- return -ENODEV;
-
- /*
- * Allocate the X.25 frame buffers:
- *
- * rbuff Receive buffer.
- * xbuff Transmit buffer.
- */
-
- len = dev->mtu * 2;
-
- sl->rbuff = kmalloc(len + 4, GFP_KERNEL);
- if (sl->rbuff == NULL)
- goto norbuff;
- sl->xbuff = kmalloc(len + 4, GFP_KERNEL);
- if (sl->xbuff == NULL)
- goto noxbuff;
-
- sl->buffsize = len;
- sl->rcount = 0;
- sl->xleft = 0;
- sl->flags &= (1 << SLF_INUSE); /* Clear ESCAPE & ERROR flags */
-
- return 0;
-
- /* Cleanup */
- kfree(sl->xbuff);
- sl->xbuff = NULL;
-noxbuff:
- kfree(sl->rbuff);
- sl->rbuff = NULL;
-norbuff:
- return -ENOMEM;
-}
-
-
-/* Close the low-level part of the X.25 channel. Easy! */
-static int x25_asy_close(struct net_device *dev)
-{
- struct x25_asy *sl = netdev_priv(dev);
-
- spin_lock(&sl->lock);
- if (sl->tty)
- clear_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags);
-
- sl->rcount = 0;
- sl->xleft = 0;
- spin_unlock(&sl->lock);
- return 0;
-}
-
-/*
- * Handle the 'receiver data ready' interrupt.
- * This function is called by the 'tty_io' module in the kernel when
- * a block of X.25 data has been received, which can now be decapsulated
- * and sent on to some IP layer for further processing.
- */
-
-static void x25_asy_receive_buf(struct tty_struct *tty,
- const unsigned char *cp, char *fp, int count)
-{
- struct x25_asy *sl = tty->disc_data;
-
- if (!sl || sl->magic != X25_ASY_MAGIC || !netif_running(sl->dev))
- return;
-
-
- /* Read the characters out of the buffer */
- while (count--) {
- if (fp && *fp++) {
- if (!test_and_set_bit(SLF_ERROR, &sl->flags))
- sl->dev->stats.rx_errors++;
- cp++;
- continue;
- }
- x25_asy_unesc(sl, *cp++);
- }
-}
-
-/*
- * Open the high-level part of the X.25 channel.
- * This function is called by the TTY module when the
- * X.25 line discipline is called for. Because we are
- * sure the tty line exists, we only have to link it to
- * a free X.25 channel...
- */
-
-static int x25_asy_open_tty(struct tty_struct *tty)
-{
- struct x25_asy *sl;
- int err;
-
- if (tty->ops->write == NULL)
- return -EOPNOTSUPP;
-
- /* OK. Find a free X.25 channel to use. */
- sl = x25_asy_alloc();
- if (sl == NULL)
- return -ENFILE;
-
- sl->tty = tty;
- tty->disc_data = sl;
- tty->receive_room = 65536;
- tty_driver_flush_buffer(tty);
- tty_ldisc_flush(tty);
-
- /* Restore default settings */
- sl->dev->type = ARPHRD_X25;
-
- /* Perform the low-level X.25 async init */
- err = x25_asy_open(sl->dev);
- if (err) {
- x25_asy_free(sl);
- return err;
- }
- /* Done. We have linked the TTY line to a channel. */
- return 0;
-}
-
-
-/*
- * Close down an X.25 channel.
- * This means flushing out any pending queues, and then restoring the
- * TTY line discipline to what it was before it got hooked to X.25
- * (which usually is TTY again).
- */
-static void x25_asy_close_tty(struct tty_struct *tty)
-{
- struct x25_asy *sl = tty->disc_data;
-
- /* First make sure we're connected. */
- if (!sl || sl->magic != X25_ASY_MAGIC)
- return;
-
- rtnl_lock();
- if (sl->dev->flags & IFF_UP)
- dev_close(sl->dev);
- rtnl_unlock();
-
- tty->disc_data = NULL;
- sl->tty = NULL;
- x25_asy_free(sl);
-}
-
- /************************************************************************
- * STANDARD X.25 ENCAPSULATION *
- ************************************************************************/
-
-static int x25_asy_esc(unsigned char *s, unsigned char *d, int len)
-{
- unsigned char *ptr = d;
- unsigned char c;
-
- /*
- * Send an initial END character to flush out any
- * data that may have accumulated in the receiver
- * due to line noise.
- */
-
- *ptr++ = X25_END; /* Send 10111110 bit seq */
-
- /*
- * For each byte in the packet, send the appropriate
- * character sequence, according to the X.25 protocol.
- */
-
- while (len-- > 0) {
- switch (c = *s++) {
- case X25_END:
- *ptr++ = X25_ESC;
- *ptr++ = X25_ESCAPE(X25_END);
- break;
- case X25_ESC:
- *ptr++ = X25_ESC;
- *ptr++ = X25_ESCAPE(X25_ESC);
- break;
- default:
- *ptr++ = c;
- break;
- }
- }
- *ptr++ = X25_END;
- return ptr - d;
-}
-
-static void x25_asy_unesc(struct x25_asy *sl, unsigned char s)
-{
-
- switch (s) {
- case X25_END:
- if (!test_and_clear_bit(SLF_ERROR, &sl->flags) &&
- sl->rcount >= 2)
- x25_asy_bump(sl);
- clear_bit(SLF_ESCAPE, &sl->flags);
- sl->rcount = 0;
- return;
- case X25_ESC:
- set_bit(SLF_ESCAPE, &sl->flags);
- return;
- case X25_ESCAPE(X25_ESC):
- case X25_ESCAPE(X25_END):
- if (test_and_clear_bit(SLF_ESCAPE, &sl->flags))
- s = X25_UNESCAPE(s);
- break;
- }
- if (!test_bit(SLF_ERROR, &sl->flags)) {
- if (sl->rcount < sl->buffsize) {
- sl->rbuff[sl->rcount++] = s;
- return;
- }
- sl->dev->stats.rx_over_errors++;
- set_bit(SLF_ERROR, &sl->flags);
- }
-}
-
-
-/* Perform I/O control on an active X.25 channel. */
-static int x25_asy_ioctl(struct tty_struct *tty, struct file *file,
- unsigned int cmd, unsigned long arg)
-{
- struct x25_asy *sl = tty->disc_data;
-
- /* First make sure we're connected. */
- if (!sl || sl->magic != X25_ASY_MAGIC)
- return -EINVAL;
-
- switch (cmd) {
- case SIOCGIFNAME:
- if (copy_to_user((void __user *)arg, sl->dev->name,
- strlen(sl->dev->name) + 1))
- return -EFAULT;
- return 0;
- case SIOCSIFHWADDR:
- return -EINVAL;
- default:
- return tty_mode_ioctl(tty, file, cmd, arg);
- }
-}
-
-static int x25_asy_open_dev(struct net_device *dev)
-{
- int err;
- struct x25_asy *sl = netdev_priv(dev);
- if (sl->tty == NULL)
- return -ENODEV;
-
- err = lapb_register(dev, &x25_asy_callbacks);
- if (err != LAPB_OK)
- return -ENOMEM;
-
- netif_start_queue(dev);
-
- return 0;
-}
-
-static int x25_asy_close_dev(struct net_device *dev)
-{
- int err;
-
- netif_stop_queue(dev);
-
- err = lapb_unregister(dev);
- if (err != LAPB_OK)
- pr_err("%s: lapb_unregister error: %d\n",
- __func__, err);
-
- x25_asy_close(dev);
-
- return 0;
-}
-
-static const struct net_device_ops x25_asy_netdev_ops = {
- .ndo_open = x25_asy_open_dev,
- .ndo_stop = x25_asy_close_dev,
- .ndo_start_xmit = x25_asy_xmit,
- .ndo_tx_timeout = x25_asy_timeout,
- .ndo_change_mtu = x25_asy_change_mtu,
-};
-
-/* Initialise the X.25 driver. Called by the device init code */
-static void x25_asy_setup(struct net_device *dev)
-{
- struct x25_asy *sl = netdev_priv(dev);
-
- sl->magic = X25_ASY_MAGIC;
- sl->dev = dev;
- spin_lock_init(&sl->lock);
- set_bit(SLF_INUSE, &sl->flags);
-
- /*
- * Finish setting up the DEVICE info.
- */
-
- dev->mtu = SL_MTU;
- dev->min_mtu = 0;
- dev->max_mtu = 65534;
- dev->netdev_ops = &x25_asy_netdev_ops;
- dev->watchdog_timeo = HZ*20;
- dev->hard_header_len = 0;
- dev->addr_len = 0;
- dev->type = ARPHRD_X25;
- dev->tx_queue_len = 10;
-
- /* When transmitting data:
- * first this driver removes a pseudo header of 1 byte,
- * then the lapb module prepends an LAPB header of at most 3 bytes.
- */
- dev->needed_headroom = 3 - 1;
-
- /* New-style flags. */
- dev->flags = IFF_NOARP;
-}
-
-static struct tty_ldisc_ops x25_ldisc = {
- .owner = THIS_MODULE,
- .magic = TTY_LDISC_MAGIC,
- .name = "X.25",
- .open = x25_asy_open_tty,
- .close = x25_asy_close_tty,
- .ioctl = x25_asy_ioctl,
- .receive_buf = x25_asy_receive_buf,
- .write_wakeup = x25_asy_write_wakeup,
-};
-
-static int __init init_x25_asy(void)
-{
- if (x25_asy_maxdev < 4)
- x25_asy_maxdev = 4; /* Sanity */
-
- pr_info("X.25 async: version 0.00 ALPHA (dynamic channels, max=%d)\n",
- x25_asy_maxdev);
-
- x25_asy_devs = kcalloc(x25_asy_maxdev, sizeof(struct net_device *),
- GFP_KERNEL);
- if (!x25_asy_devs)
- return -ENOMEM;
-
- return tty_register_ldisc(N_X25, &x25_ldisc);
-}
-
-
-static void __exit exit_x25_asy(void)
-{
- struct net_device *dev;
- int i;
-
- for (i = 0; i < x25_asy_maxdev; i++) {
- dev = x25_asy_devs[i];
- if (dev) {
- struct x25_asy *sl = netdev_priv(dev);
-
- spin_lock_bh(&sl->lock);
- if (sl->tty)
- tty_hangup(sl->tty);
-
- spin_unlock_bh(&sl->lock);
- /*
- * VSV = if dev->start==0, then device
- * unregistered while close proc.
- */
- unregister_netdev(dev);
- free_netdev(dev);
- }
- }
-
- kfree(x25_asy_devs);
- tty_unregister_ldisc(N_X25);
-}
-
-module_init(init_x25_asy);
-module_exit(exit_x25_asy);
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_X25_ASY_H
-#define _LINUX_X25_ASY_H
-
-/* X.25 asy configuration. */
-#define SL_NRUNIT 256 /* MAX number of X.25 channels;
- This can be overridden with
- insmod -ox25_asy_maxdev=nnn */
-#define SL_MTU 256
-
-/* X25 async protocol characters. */
-#define X25_END 0x7E /* indicates end of frame */
-#define X25_ESC 0x7D /* indicates byte stuffing */
-#define X25_ESCAPE(x) ((x)^0x20)
-#define X25_UNESCAPE(x) ((x)^0x20)
-
-
-struct x25_asy {
- int magic;
-
- /* Various fields. */
- spinlock_t lock;
- struct tty_struct *tty; /* ptr to TTY structure */
- struct net_device *dev; /* easy for intr handling */
-
- /* These are pointers to the malloc()ed frame buffers. */
- unsigned char *rbuff; /* receiver buffer */
- int rcount; /* received chars counter */
- unsigned char *xbuff; /* transmitter buffer */
- unsigned char *xhead; /* pointer to next byte to XMIT */
- int xleft; /* bytes left in XMIT queue */
- int buffsize; /* Max buffers sizes */
-
- unsigned long flags; /* Flag values/ mode etc */
-#define SLF_INUSE 0 /* Channel in use */
-#define SLF_ESCAPE 1 /* ESC received */
-#define SLF_ERROR 2 /* Parity, etc. error */
-};
-
-
-
-#define X25_ASY_MAGIC 0x5303
-
-int x25_asy_init(struct net_device *dev);
-
-#endif /* _LINUX_X25_ASY.H */
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# WiMAX LAN device drivers configuration
-#
-
-
-comment "Enable WiMAX (Networking options) to see the WiMAX drivers"
- depends on WIMAX = n
-
-if WIMAX
-
-menu "WiMAX Wireless Broadband devices"
-
-source "drivers/net/wimax/i2400m/Kconfig"
-
-endmenu
-
-endif
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_WIMAX_I2400M) += i2400m/
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0-only
-
-config WIMAX_I2400M
- tristate
- depends on WIMAX
- select FW_LOADER
-
-comment "Enable USB support to see WiMAX USB drivers"
- depends on USB = n
-
-config WIMAX_I2400M_USB
- tristate "Intel Wireless WiMAX Connection 2400 over USB (including 5x50)"
- depends on WIMAX && USB
- select WIMAX_I2400M
- help
- Select if you have a device based on the Intel WiMAX
- Connection 2400 over USB (like any of the Intel Wireless
- WiMAX/WiFi Link 5x50 series).
-
- If unsure, it is safe to select M (module).
-
-config WIMAX_I2400M_DEBUG_LEVEL
- int "WiMAX i2400m debug level"
- depends on WIMAX_I2400M
- default 8
- help
-
- Select the maximum debug verbosity level to be compiled into
- the WiMAX i2400m driver code.
-
- By default, this is disabled at runtime and can be
- selectively enabled at runtime for different parts of the
- code using the sysfs debug-levels file.
-
- If set at zero, this will compile out all the debug code.
-
- It is recommended that it is left at 8.
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0
-
-obj-$(CONFIG_WIMAX_I2400M) += i2400m.o
-obj-$(CONFIG_WIMAX_I2400M_USB) += i2400m-usb.o
-
-i2400m-y := \
- control.o \
- driver.o \
- fw.o \
- op-rfkill.o \
- sysfs.o \
- netdev.o \
- tx.o \
- rx.o
-
-i2400m-$(CONFIG_DEBUG_FS) += debugfs.o
-
-i2400m-usb-y := \
- usb-fw.o \
- usb-notif.o \
- usb-tx.o \
- usb-rx.o \
- usb.o
+++ /dev/null
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Miscellaneous control functions for managing the device
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * - Initial implementation
- *
- * This is a collection of functions used to control the device (plus
- * a few helpers).
- *
- * There are utilities for handling TLV buffers, hooks on the device's
- * reports to act on device changes of state [i2400m_report_hook()],
- * on acks to commands [i2400m_msg_ack_hook()], a helper for sending
- * commands to the device and blocking until a reply arrives
- * [i2400m_msg_to_dev()], a few high level commands for manipulating
- * the device state, powersving mode and configuration plus the
- * routines to setup the device once communication is stablished with
- * it [i2400m_dev_initialize()].
- *
- * ROADMAP
- *
- * i2400m_dev_initialize() Called by i2400m_dev_start()
- * i2400m_set_init_config()
- * i2400m_cmd_get_state()
- * i2400m_dev_shutdown() Called by i2400m_dev_stop()
- * i2400m_reset()
- *
- * i2400m_{cmd,get,set}_*()
- * i2400m_msg_to_dev()
- * i2400m_msg_check_status()
- *
- * i2400m_report_hook() Called on reception of an event
- * i2400m_report_state_hook()
- * i2400m_tlv_buffer_walk()
- * i2400m_tlv_match()
- * i2400m_report_tlv_system_state()
- * i2400m_report_tlv_rf_switches_status()
- * i2400m_report_tlv_media_status()
- * i2400m_cmd_enter_powersave()
- *
- * i2400m_msg_ack_hook() Called on reception of a reply to a
- * command, get or set
- */
-
-#include <stdarg.h>
-#include "i2400m.h"
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/wimax/i2400m.h>
-#include <linux/export.h>
-#include <linux/moduleparam.h>
-
-
-#define D_SUBMODULE control
-#include "debug-levels.h"
-
-static int i2400m_idle_mode_disabled;/* 0 (idle mode enabled) by default */
-module_param_named(idle_mode_disabled, i2400m_idle_mode_disabled, int, 0644);
-MODULE_PARM_DESC(idle_mode_disabled,
- "If true, the device will not enable idle mode negotiation "
- "with the base station (when connected) to save power.");
-
-/* 0 (power saving enabled) by default */
-static int i2400m_power_save_disabled;
-module_param_named(power_save_disabled, i2400m_power_save_disabled, int, 0644);
-MODULE_PARM_DESC(power_save_disabled,
- "If true, the driver will not tell the device to enter "
- "power saving mode when it reports it is ready for it. "
- "False by default (so the device is told to do power "
- "saving).");
-
-static int i2400m_passive_mode; /* 0 (passive mode disabled) by default */
-module_param_named(passive_mode, i2400m_passive_mode, int, 0644);
-MODULE_PARM_DESC(passive_mode,
- "If true, the driver will not do any device setup "
- "and leave it up to user space, who must be properly "
- "setup.");
-
-
-/*
- * Return if a TLV is of a give type and size
- *
- * @tlv_hdr: pointer to the TLV
- * @tlv_type: type of the TLV we are looking for
- * @tlv_size: expected size of the TLV we are looking for (if -1,
- * don't check the size). This includes the header
- * Returns: 0 if the TLV matches
- * < 0 if it doesn't match at all
- * > 0 total TLV + payload size, if the type matches, but not
- * the size
- */
-static
-ssize_t i2400m_tlv_match(const struct i2400m_tlv_hdr *tlv,
- enum i2400m_tlv tlv_type, ssize_t tlv_size)
-{
- if (le16_to_cpu(tlv->type) != tlv_type) /* Not our type? skip */
- return -1;
- if (tlv_size != -1
- && le16_to_cpu(tlv->length) + sizeof(*tlv) != tlv_size) {
- size_t size = le16_to_cpu(tlv->length) + sizeof(*tlv);
- printk(KERN_WARNING "W: tlv type 0x%x mismatched because of "
- "size (got %zu vs %zd expected)\n",
- tlv_type, size, tlv_size);
- return size;
- }
- return 0;
-}
-
-
-/*
- * Given a buffer of TLVs, iterate over them
- *
- * @i2400m: device instance
- * @tlv_buf: pointer to the beginning of the TLV buffer
- * @buf_size: buffer size in bytes
- * @tlv_pos: seek position; this is assumed to be a pointer returned
- * by i2400m_tlv_buffer_walk() [and thus, validated]. The
- * TLV returned will be the one following this one.
- *
- * Usage:
- *
- * tlv_itr = NULL;
- * while (tlv_itr = i2400m_tlv_buffer_walk(i2400m, buf, size, tlv_itr)) {
- * ...
- * // Do stuff with tlv_itr, DON'T MODIFY IT
- * ...
- * }
- */
-static
-const struct i2400m_tlv_hdr *i2400m_tlv_buffer_walk(
- struct i2400m *i2400m,
- const void *tlv_buf, size_t buf_size,
- const struct i2400m_tlv_hdr *tlv_pos)
-{
- struct device *dev = i2400m_dev(i2400m);
- const struct i2400m_tlv_hdr *tlv_top = tlv_buf + buf_size;
- size_t offset, length, avail_size;
- unsigned type;
-
- if (tlv_pos == NULL) /* Take the first one? */
- tlv_pos = tlv_buf;
- else /* Nope, the next one */
- tlv_pos = (void *) tlv_pos
- + le16_to_cpu(tlv_pos->length) + sizeof(*tlv_pos);
- if (tlv_pos == tlv_top) { /* buffer done */
- tlv_pos = NULL;
- goto error_beyond_end;
- }
- if (tlv_pos > tlv_top) {
- tlv_pos = NULL;
- WARN_ON(1);
- goto error_beyond_end;
- }
- offset = (void *) tlv_pos - (void *) tlv_buf;
- avail_size = buf_size - offset;
- if (avail_size < sizeof(*tlv_pos)) {
- dev_err(dev, "HW BUG? tlv_buf %p [%zu bytes], tlv @%zu: "
- "short header\n", tlv_buf, buf_size, offset);
- goto error_short_header;
- }
- type = le16_to_cpu(tlv_pos->type);
- length = le16_to_cpu(tlv_pos->length);
- if (avail_size < sizeof(*tlv_pos) + length) {
- dev_err(dev, "HW BUG? tlv_buf %p [%zu bytes], "
- "tlv type 0x%04x @%zu: "
- "short data (%zu bytes vs %zu needed)\n",
- tlv_buf, buf_size, type, offset, avail_size,
- sizeof(*tlv_pos) + length);
- goto error_short_header;
- }
-error_short_header:
-error_beyond_end:
- return tlv_pos;
-}
-
-
-/*
- * Find a TLV in a buffer of sequential TLVs
- *
- * @i2400m: device descriptor
- * @tlv_hdr: pointer to the first TLV in the sequence
- * @size: size of the buffer in bytes; all TLVs are assumed to fit
- * fully in the buffer (otherwise we'll complain).
- * @tlv_type: type of the TLV we are looking for
- * @tlv_size: expected size of the TLV we are looking for (if -1,
- * don't check the size). This includes the header
- *
- * Returns: NULL if the TLV is not found, otherwise a pointer to
- * it. If the sizes don't match, an error is printed and NULL
- * returned.
- */
-static
-const struct i2400m_tlv_hdr *i2400m_tlv_find(
- struct i2400m *i2400m,
- const struct i2400m_tlv_hdr *tlv_hdr, size_t size,
- enum i2400m_tlv tlv_type, ssize_t tlv_size)
-{
- ssize_t match;
- struct device *dev = i2400m_dev(i2400m);
- const struct i2400m_tlv_hdr *tlv = NULL;
- while ((tlv = i2400m_tlv_buffer_walk(i2400m, tlv_hdr, size, tlv))) {
- match = i2400m_tlv_match(tlv, tlv_type, tlv_size);
- if (match == 0) /* found it :) */
- break;
- if (match > 0)
- dev_warn(dev, "TLV type 0x%04x found with size "
- "mismatch (%zu vs %zd needed)\n",
- tlv_type, match, tlv_size);
- }
- return tlv;
-}
-
-
-static const struct
-{
- char *msg;
- int errno;
-} ms_to_errno[I2400M_MS_MAX] = {
- [I2400M_MS_DONE_OK] = { "", 0 },
- [I2400M_MS_DONE_IN_PROGRESS] = { "", 0 },
- [I2400M_MS_INVALID_OP] = { "invalid opcode", -ENOSYS },
- [I2400M_MS_BAD_STATE] = { "invalid state", -EILSEQ },
- [I2400M_MS_ILLEGAL_VALUE] = { "illegal value", -EINVAL },
- [I2400M_MS_MISSING_PARAMS] = { "missing parameters", -ENOMSG },
- [I2400M_MS_VERSION_ERROR] = { "bad version", -EIO },
- [I2400M_MS_ACCESSIBILITY_ERROR] = { "accesibility error", -EIO },
- [I2400M_MS_BUSY] = { "busy", -EBUSY },
- [I2400M_MS_CORRUPTED_TLV] = { "corrupted TLV", -EILSEQ },
- [I2400M_MS_UNINITIALIZED] = { "uninitialized", -EILSEQ },
- [I2400M_MS_UNKNOWN_ERROR] = { "unknown error", -EIO },
- [I2400M_MS_PRODUCTION_ERROR] = { "production error", -EIO },
- [I2400M_MS_NO_RF] = { "no RF", -EIO },
- [I2400M_MS_NOT_READY_FOR_POWERSAVE] =
- { "not ready for powersave", -EACCES },
- [I2400M_MS_THERMAL_CRITICAL] = { "thermal critical", -EL3HLT },
-};
-
-
-/*
- * i2400m_msg_check_status - translate a message's status code
- *
- * @i2400m: device descriptor
- * @l3l4_hdr: message header
- * @strbuf: buffer to place a formatted error message (unless NULL).
- * @strbuf_size: max amount of available space; larger messages will
- * be truncated.
- *
- * Returns: errno code corresponding to the status code in @l3l4_hdr
- * and a message in @strbuf describing the error.
- */
-int i2400m_msg_check_status(const struct i2400m_l3l4_hdr *l3l4_hdr,
- char *strbuf, size_t strbuf_size)
-{
- int result;
- enum i2400m_ms status = le16_to_cpu(l3l4_hdr->status);
- const char *str;
-
- if (status == 0)
- return 0;
- if (status >= ARRAY_SIZE(ms_to_errno)) {
- str = "unknown status code";
- result = -EBADR;
- } else {
- str = ms_to_errno[status].msg;
- result = ms_to_errno[status].errno;
- }
- if (strbuf)
- snprintf(strbuf, strbuf_size, "%s (%d)", str, status);
- return result;
-}
-
-
-/*
- * Act on a TLV System State reported by the device
- *
- * @i2400m: device descriptor
- * @ss: validated System State TLV
- */
-static
-void i2400m_report_tlv_system_state(struct i2400m *i2400m,
- const struct i2400m_tlv_system_state *ss)
-{
- struct device *dev = i2400m_dev(i2400m);
- struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
- enum i2400m_system_state i2400m_state = le32_to_cpu(ss->state);
-
- d_fnstart(3, dev, "(i2400m %p ss %p [%u])\n", i2400m, ss, i2400m_state);
-
- if (i2400m->state != i2400m_state) {
- i2400m->state = i2400m_state;
- wake_up_all(&i2400m->state_wq);
- }
- switch (i2400m_state) {
- case I2400M_SS_UNINITIALIZED:
- case I2400M_SS_INIT:
- case I2400M_SS_CONFIG:
- case I2400M_SS_PRODUCTION:
- wimax_state_change(wimax_dev, WIMAX_ST_UNINITIALIZED);
- break;
-
- case I2400M_SS_RF_OFF:
- case I2400M_SS_RF_SHUTDOWN:
- wimax_state_change(wimax_dev, WIMAX_ST_RADIO_OFF);
- break;
-
- case I2400M_SS_READY:
- case I2400M_SS_STANDBY:
- case I2400M_SS_SLEEPACTIVE:
- wimax_state_change(wimax_dev, WIMAX_ST_READY);
- break;
-
- case I2400M_SS_CONNECTING:
- case I2400M_SS_WIMAX_CONNECTED:
- wimax_state_change(wimax_dev, WIMAX_ST_READY);
- break;
-
- case I2400M_SS_SCAN:
- case I2400M_SS_OUT_OF_ZONE:
- wimax_state_change(wimax_dev, WIMAX_ST_SCANNING);
- break;
-
- case I2400M_SS_IDLE:
- d_printf(1, dev, "entering BS-negotiated idle mode\n");
- fallthrough;
- case I2400M_SS_DISCONNECTING:
- case I2400M_SS_DATA_PATH_CONNECTED:
- wimax_state_change(wimax_dev, WIMAX_ST_CONNECTED);
- break;
-
- default:
- /* Huh? just in case, shut it down */
- dev_err(dev, "HW BUG? unknown state %u: shutting down\n",
- i2400m_state);
- i2400m_reset(i2400m, I2400M_RT_WARM);
- break;
- }
- d_fnend(3, dev, "(i2400m %p ss %p [%u]) = void\n",
- i2400m, ss, i2400m_state);
-}
-
-
-/*
- * Parse and act on a TLV Media Status sent by the device
- *
- * @i2400m: device descriptor
- * @ms: validated Media Status TLV
- *
- * This will set the carrier up on down based on the device's link
- * report. This is done asides of what the WiMAX stack does based on
- * the device's state as sometimes we need to do a link-renew (the BS
- * wants us to renew a DHCP lease, for example).
- *
- * In fact, doc says that every time we get a link-up, we should do a
- * DHCP negotiation...
- */
-static
-void i2400m_report_tlv_media_status(struct i2400m *i2400m,
- const struct i2400m_tlv_media_status *ms)
-{
- struct device *dev = i2400m_dev(i2400m);
- struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
- struct net_device *net_dev = wimax_dev->net_dev;
- enum i2400m_media_status status = le32_to_cpu(ms->media_status);
-
- d_fnstart(3, dev, "(i2400m %p ms %p [%u])\n", i2400m, ms, status);
-
- switch (status) {
- case I2400M_MEDIA_STATUS_LINK_UP:
- netif_carrier_on(net_dev);
- break;
- case I2400M_MEDIA_STATUS_LINK_DOWN:
- netif_carrier_off(net_dev);
- break;
- /*
- * This is the network telling us we need to retrain the DHCP
- * lease -- so far, we are trusting the WiMAX Network Service
- * in user space to pick this up and poke the DHCP client.
- */
- case I2400M_MEDIA_STATUS_LINK_RENEW:
- netif_carrier_on(net_dev);
- break;
- default:
- dev_err(dev, "HW BUG? unknown media status %u\n",
- status);
- }
- d_fnend(3, dev, "(i2400m %p ms %p [%u]) = void\n",
- i2400m, ms, status);
-}
-
-
-/*
- * Process a TLV from a 'state report'
- *
- * @i2400m: device descriptor
- * @tlv: pointer to the TLV header; it has been already validated for
- * consistent size.
- * @tag: for error messages
- *
- * Act on the TLVs from a 'state report'.
- */
-static
-void i2400m_report_state_parse_tlv(struct i2400m *i2400m,
- const struct i2400m_tlv_hdr *tlv,
- const char *tag)
-{
- struct device *dev = i2400m_dev(i2400m);
- const struct i2400m_tlv_media_status *ms;
- const struct i2400m_tlv_system_state *ss;
- const struct i2400m_tlv_rf_switches_status *rfss;
-
- if (0 == i2400m_tlv_match(tlv, I2400M_TLV_SYSTEM_STATE, sizeof(*ss))) {
- ss = container_of(tlv, typeof(*ss), hdr);
- d_printf(2, dev, "%s: system state TLV "
- "found (0x%04x), state 0x%08x\n",
- tag, I2400M_TLV_SYSTEM_STATE,
- le32_to_cpu(ss->state));
- i2400m_report_tlv_system_state(i2400m, ss);
- }
- if (0 == i2400m_tlv_match(tlv, I2400M_TLV_RF_STATUS, sizeof(*rfss))) {
- rfss = container_of(tlv, typeof(*rfss), hdr);
- d_printf(2, dev, "%s: RF status TLV "
- "found (0x%04x), sw 0x%02x hw 0x%02x\n",
- tag, I2400M_TLV_RF_STATUS,
- le32_to_cpu(rfss->sw_rf_switch),
- le32_to_cpu(rfss->hw_rf_switch));
- i2400m_report_tlv_rf_switches_status(i2400m, rfss);
- }
- if (0 == i2400m_tlv_match(tlv, I2400M_TLV_MEDIA_STATUS, sizeof(*ms))) {
- ms = container_of(tlv, typeof(*ms), hdr);
- d_printf(2, dev, "%s: Media Status TLV: %u\n",
- tag, le32_to_cpu(ms->media_status));
- i2400m_report_tlv_media_status(i2400m, ms);
- }
-}
-
-
-/*
- * Parse a 'state report' and extract information
- *
- * @i2400m: device descriptor
- * @l3l4_hdr: pointer to message; it has been already validated for
- * consistent size.
- * @size: size of the message (header + payload). The header length
- * declaration is assumed to be congruent with @size (as in
- * sizeof(*l3l4_hdr) + l3l4_hdr->length == size)
- *
- * Walk over the TLVs in a report state and act on them.
- */
-static
-void i2400m_report_state_hook(struct i2400m *i2400m,
- const struct i2400m_l3l4_hdr *l3l4_hdr,
- size_t size, const char *tag)
-{
- struct device *dev = i2400m_dev(i2400m);
- const struct i2400m_tlv_hdr *tlv;
- size_t tlv_size = le16_to_cpu(l3l4_hdr->length);
-
- d_fnstart(4, dev, "(i2400m %p, l3l4_hdr %p, size %zu, %s)\n",
- i2400m, l3l4_hdr, size, tag);
- tlv = NULL;
-
- while ((tlv = i2400m_tlv_buffer_walk(i2400m, &l3l4_hdr->pl,
- tlv_size, tlv)))
- i2400m_report_state_parse_tlv(i2400m, tlv, tag);
- d_fnend(4, dev, "(i2400m %p, l3l4_hdr %p, size %zu, %s) = void\n",
- i2400m, l3l4_hdr, size, tag);
-}
-
-
-/*
- * i2400m_report_hook - (maybe) act on a report
- *
- * @i2400m: device descriptor
- * @l3l4_hdr: pointer to message; it has been already validated for
- * consistent size.
- * @size: size of the message (header + payload). The header length
- * declaration is assumed to be congruent with @size (as in
- * sizeof(*l3l4_hdr) + l3l4_hdr->length == size)
- *
- * Extract information we might need (like carrien on/off) from a
- * device report.
- */
-void i2400m_report_hook(struct i2400m *i2400m,
- const struct i2400m_l3l4_hdr *l3l4_hdr, size_t size)
-{
- struct device *dev = i2400m_dev(i2400m);
- unsigned msg_type;
-
- d_fnstart(3, dev, "(i2400m %p l3l4_hdr %p size %zu)\n",
- i2400m, l3l4_hdr, size);
- /* Chew on the message, we might need some information from
- * here */
- msg_type = le16_to_cpu(l3l4_hdr->type);
- switch (msg_type) {
- case I2400M_MT_REPORT_STATE: /* carrier detection... */
- i2400m_report_state_hook(i2400m,
- l3l4_hdr, size, "REPORT STATE");
- break;
- /* If the device is ready for power save, then ask it to do
- * it. */
- case I2400M_MT_REPORT_POWERSAVE_READY: /* zzzzz */
- if (l3l4_hdr->status == cpu_to_le16(I2400M_MS_DONE_OK)) {
- if (i2400m_power_save_disabled)
- d_printf(1, dev, "ready for powersave, "
- "not requesting (disabled by module "
- "parameter)\n");
- else {
- d_printf(1, dev, "ready for powersave, "
- "requesting\n");
- i2400m_cmd_enter_powersave(i2400m);
- }
- }
- break;
- }
- d_fnend(3, dev, "(i2400m %p l3l4_hdr %p size %zu) = void\n",
- i2400m, l3l4_hdr, size);
-}
-
-
-/*
- * i2400m_msg_ack_hook - process cmd/set/get ack for internal status
- *
- * @i2400m: device descriptor
- * @l3l4_hdr: pointer to message; it has been already validated for
- * consistent size.
- * @size: size of the message
- *
- * Extract information we might need from acks to commands and act on
- * it. This is akin to i2400m_report_hook(). Note most of this
- * processing should be done in the function that calls the
- * command. This is here for some cases where it can't happen...
- */
-static void i2400m_msg_ack_hook(struct i2400m *i2400m,
- const struct i2400m_l3l4_hdr *l3l4_hdr,
- size_t size)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- unsigned int ack_type;
- char strerr[32];
-
- /* Chew on the message, we might need some information from
- * here */
- ack_type = le16_to_cpu(l3l4_hdr->type);
- switch (ack_type) {
- case I2400M_MT_CMD_ENTER_POWERSAVE:
- /* This is just left here for the sake of example, as
- * the processing is done somewhere else. */
- if (0) {
- result = i2400m_msg_check_status(
- l3l4_hdr, strerr, sizeof(strerr));
- if (result >= 0)
- d_printf(1, dev, "ready for power save: %zd\n",
- size);
- }
- break;
- }
-}
-
-
-/*
- * i2400m_msg_size_check() - verify message size and header are congruent
- *
- * It is ok if the total message size is larger than the expected
- * size, as there can be padding.
- */
-int i2400m_msg_size_check(struct i2400m *i2400m,
- const struct i2400m_l3l4_hdr *l3l4_hdr,
- size_t msg_size)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- size_t expected_size;
- d_fnstart(4, dev, "(i2400m %p l3l4_hdr %p msg_size %zu)\n",
- i2400m, l3l4_hdr, msg_size);
- if (msg_size < sizeof(*l3l4_hdr)) {
- dev_err(dev, "bad size for message header "
- "(expected at least %zu, got %zu)\n",
- (size_t) sizeof(*l3l4_hdr), msg_size);
- result = -EIO;
- goto error_hdr_size;
- }
- expected_size = le16_to_cpu(l3l4_hdr->length) + sizeof(*l3l4_hdr);
- if (msg_size < expected_size) {
- dev_err(dev, "bad size for message code 0x%04x (expected %zu, "
- "got %zu)\n", le16_to_cpu(l3l4_hdr->type),
- expected_size, msg_size);
- result = -EIO;
- } else
- result = 0;
-error_hdr_size:
- d_fnend(4, dev,
- "(i2400m %p l3l4_hdr %p msg_size %zu) = %d\n",
- i2400m, l3l4_hdr, msg_size, result);
- return result;
-}
-
-
-
-/*
- * Cancel a wait for a command ACK
- *
- * @i2400m: device descriptor
- * @code: [negative] errno code to cancel with (don't use
- * -EINPROGRESS)
- *
- * If there is an ack already filled out, free it.
- */
-void i2400m_msg_to_dev_cancel_wait(struct i2400m *i2400m, int code)
-{
- struct sk_buff *ack_skb;
- unsigned long flags;
-
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- ack_skb = i2400m->ack_skb;
- if (ack_skb && !IS_ERR(ack_skb))
- kfree_skb(ack_skb);
- i2400m->ack_skb = ERR_PTR(code);
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-}
-
-
-/**
- * i2400m_msg_to_dev - Send a control message to the device and get a response
- *
- * @i2400m: device descriptor
- *
- * @buf: pointer to the buffer containing the message to be sent; it
- * has to start with a &struct i2400M_l3l4_hdr and then
- * followed by the payload. Once this function returns, the
- * buffer can be reused.
- *
- * @buf_len: buffer size
- *
- * Returns:
- *
- * Pointer to skb containing the ack message. You need to check the
- * pointer with IS_ERR(), as it might be an error code. Error codes
- * could happen because:
- *
- * - the message wasn't formatted correctly
- * - couldn't send the message
- * - failed waiting for a response
- * - the ack message wasn't formatted correctly
- *
- * The returned skb has been allocated with wimax_msg_to_user_alloc(),
- * it contains the response in a netlink attribute and is ready to be
- * passed up to user space with wimax_msg_to_user_send(). To access
- * the payload and its length, use wimax_msg_{data,len}() on the skb.
- *
- * The skb has to be freed with kfree_skb() once done.
- *
- * Description:
- *
- * This function delivers a message/command to the device and waits
- * for an ack to be received. The format is described in
- * linux/wimax/i2400m.h. In summary, a command/get/set is followed by an
- * ack.
- *
- * This function will not check the ack status, that's left up to the
- * caller. Once done with the ack skb, it has to be kfree_skb()ed.
- *
- * The i2400m handles only one message at the same time, thus we need
- * the mutex to exclude other players.
- *
- * We write the message and then wait for an answer to come back. The
- * RX path intercepts control messages and handles them in
- * i2400m_rx_ctl(). Reports (notifications) are (maybe) processed
- * locally and then forwarded (as needed) to user space on the WiMAX
- * stack message pipe. Acks are saved and passed back to us through an
- * skb in i2400m->ack_skb which is ready to be given to generic
- * netlink if need be.
- */
-struct sk_buff *i2400m_msg_to_dev(struct i2400m *i2400m,
- const void *buf, size_t buf_len)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- const struct i2400m_l3l4_hdr *msg_l3l4_hdr;
- struct sk_buff *ack_skb;
- const struct i2400m_l3l4_hdr *ack_l3l4_hdr;
- size_t ack_len;
- int ack_timeout;
- unsigned msg_type;
- unsigned long flags;
-
- d_fnstart(3, dev, "(i2400m %p buf %p len %zu)\n",
- i2400m, buf, buf_len);
-
- rmb(); /* Make sure we see what i2400m_dev_reset_handle() */
- if (i2400m->boot_mode)
- return ERR_PTR(-EL3RST);
-
- msg_l3l4_hdr = buf;
- /* Check msg & payload consistency */
- result = i2400m_msg_size_check(i2400m, msg_l3l4_hdr, buf_len);
- if (result < 0)
- goto error_bad_msg;
- msg_type = le16_to_cpu(msg_l3l4_hdr->type);
- d_printf(1, dev, "CMD/GET/SET 0x%04x %zu bytes\n",
- msg_type, buf_len);
- d_dump(2, dev, buf, buf_len);
-
- /* Setup the completion, ack_skb ("we are waiting") and send
- * the message to the device */
- mutex_lock(&i2400m->msg_mutex);
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- i2400m->ack_skb = ERR_PTR(-EINPROGRESS);
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- init_completion(&i2400m->msg_completion);
- result = i2400m_tx(i2400m, buf, buf_len, I2400M_PT_CTRL);
- if (result < 0) {
- dev_err(dev, "can't send message 0x%04x: %d\n",
- le16_to_cpu(msg_l3l4_hdr->type), result);
- goto error_tx;
- }
-
- /* Some commands take longer to execute because of crypto ops,
- * so we give them some more leeway on timeout */
- switch (msg_type) {
- case I2400M_MT_GET_TLS_OPERATION_RESULT:
- case I2400M_MT_CMD_SEND_EAP_RESPONSE:
- ack_timeout = 5 * HZ;
- break;
- default:
- ack_timeout = HZ;
- }
-
- if (unlikely(i2400m->trace_msg_from_user))
- wimax_msg(&i2400m->wimax_dev, "echo", buf, buf_len, GFP_KERNEL);
- /* The RX path in rx.c will put any response for this message
- * in i2400m->ack_skb and wake us up. If we cancel the wait,
- * we need to change the value of i2400m->ack_skb to something
- * not -EINPROGRESS so RX knows there is no one waiting. */
- result = wait_for_completion_interruptible_timeout(
- &i2400m->msg_completion, ack_timeout);
- if (result == 0) {
- dev_err(dev, "timeout waiting for reply to message 0x%04x\n",
- msg_type);
- result = -ETIMEDOUT;
- i2400m_msg_to_dev_cancel_wait(i2400m, result);
- goto error_wait_for_completion;
- } else if (result < 0) {
- dev_err(dev, "error waiting for reply to message 0x%04x: %d\n",
- msg_type, result);
- i2400m_msg_to_dev_cancel_wait(i2400m, result);
- goto error_wait_for_completion;
- }
-
- /* Pull out the ack data from i2400m->ack_skb -- see if it is
- * an error and act accordingly */
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- ack_skb = i2400m->ack_skb;
- if (IS_ERR(ack_skb))
- result = PTR_ERR(ack_skb);
- else
- result = 0;
- i2400m->ack_skb = NULL;
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- if (result < 0)
- goto error_ack_status;
- ack_l3l4_hdr = wimax_msg_data_len(ack_skb, &ack_len);
-
- /* Check the ack and deliver it if it is ok */
- if (unlikely(i2400m->trace_msg_from_user))
- wimax_msg(&i2400m->wimax_dev, "echo",
- ack_l3l4_hdr, ack_len, GFP_KERNEL);
- result = i2400m_msg_size_check(i2400m, ack_l3l4_hdr, ack_len);
- if (result < 0) {
- dev_err(dev, "HW BUG? reply to message 0x%04x: %d\n",
- msg_type, result);
- goto error_bad_ack_len;
- }
- if (msg_type != le16_to_cpu(ack_l3l4_hdr->type)) {
- dev_err(dev, "HW BUG? bad reply 0x%04x to message 0x%04x\n",
- le16_to_cpu(ack_l3l4_hdr->type), msg_type);
- result = -EIO;
- goto error_bad_ack_type;
- }
- i2400m_msg_ack_hook(i2400m, ack_l3l4_hdr, ack_len);
- mutex_unlock(&i2400m->msg_mutex);
- d_fnend(3, dev, "(i2400m %p buf %p len %zu) = %p\n",
- i2400m, buf, buf_len, ack_skb);
- return ack_skb;
-
-error_bad_ack_type:
-error_bad_ack_len:
- kfree_skb(ack_skb);
-error_ack_status:
-error_wait_for_completion:
-error_tx:
- mutex_unlock(&i2400m->msg_mutex);
-error_bad_msg:
- d_fnend(3, dev, "(i2400m %p buf %p len %zu) = %d\n",
- i2400m, buf, buf_len, result);
- return ERR_PTR(result);
-}
-
-
-/*
- * Definitions for the Enter Power Save command
- *
- * The Enter Power Save command requests the device to go into power
- * saving mode. The device will ack or nak the command depending on it
- * being ready for it. If it acks, we tell the USB subsystem to
- *
- * As well, the device might request to go into power saving mode by
- * sending a report (REPORT_POWERSAVE_READY), in which case, we issue
- * this command. The hookups in the RX coder allow
- */
-enum {
- I2400M_WAKEUP_ENABLED = 0x01,
- I2400M_WAKEUP_DISABLED = 0x02,
- I2400M_TLV_TYPE_WAKEUP_MODE = 144,
-};
-
-struct i2400m_cmd_enter_power_save {
- struct i2400m_l3l4_hdr hdr;
- struct i2400m_tlv_hdr tlv;
- __le32 val;
-} __packed;
-
-
-/*
- * Request entering power save
- *
- * This command is (mainly) executed when the device indicates that it
- * is ready to go into powersave mode via a REPORT_POWERSAVE_READY.
- */
-int i2400m_cmd_enter_powersave(struct i2400m *i2400m)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *ack_skb;
- struct i2400m_cmd_enter_power_save *cmd;
- char strerr[32];
-
- result = -ENOMEM;
- cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
- if (cmd == NULL)
- goto error_alloc;
- cmd->hdr.type = cpu_to_le16(I2400M_MT_CMD_ENTER_POWERSAVE);
- cmd->hdr.length = cpu_to_le16(sizeof(*cmd) - sizeof(cmd->hdr));
- cmd->hdr.version = cpu_to_le16(I2400M_L3L4_VERSION);
- cmd->tlv.type = cpu_to_le16(I2400M_TLV_TYPE_WAKEUP_MODE);
- cmd->tlv.length = cpu_to_le16(sizeof(cmd->val));
- cmd->val = cpu_to_le32(I2400M_WAKEUP_ENABLED);
-
- ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
- result = PTR_ERR(ack_skb);
- if (IS_ERR(ack_skb)) {
- dev_err(dev, "Failed to issue 'Enter power save' command: %d\n",
- result);
- goto error_msg_to_dev;
- }
- result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
- strerr, sizeof(strerr));
- if (result == -EACCES)
- d_printf(1, dev, "Cannot enter power save mode\n");
- else if (result < 0)
- dev_err(dev, "'Enter power save' (0x%04x) command failed: "
- "%d - %s\n", I2400M_MT_CMD_ENTER_POWERSAVE,
- result, strerr);
- else
- d_printf(1, dev, "device ready to power save\n");
- kfree_skb(ack_skb);
-error_msg_to_dev:
- kfree(cmd);
-error_alloc:
- return result;
-}
-EXPORT_SYMBOL_GPL(i2400m_cmd_enter_powersave);
-
-
-/*
- * Definitions for getting device information
- */
-enum {
- I2400M_TLV_DETAILED_DEVICE_INFO = 140
-};
-
-/**
- * i2400m_get_device_info - Query the device for detailed device information
- *
- * @i2400m: device descriptor
- *
- * Returns: an skb whose skb->data points to a 'struct
- * i2400m_tlv_detailed_device_info'. When done, kfree_skb() it. The
- * skb is *guaranteed* to contain the whole TLV data structure.
- *
- * On error, IS_ERR(skb) is true and ERR_PTR(skb) is the error
- * code.
- */
-struct sk_buff *i2400m_get_device_info(struct i2400m *i2400m)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *ack_skb;
- struct i2400m_l3l4_hdr *cmd;
- const struct i2400m_l3l4_hdr *ack;
- size_t ack_len;
- const struct i2400m_tlv_hdr *tlv;
- const struct i2400m_tlv_detailed_device_info *ddi;
- char strerr[32];
-
- ack_skb = ERR_PTR(-ENOMEM);
- cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
- if (cmd == NULL)
- goto error_alloc;
- cmd->type = cpu_to_le16(I2400M_MT_GET_DEVICE_INFO);
- cmd->length = 0;
- cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
-
- ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
- if (IS_ERR(ack_skb)) {
- dev_err(dev, "Failed to issue 'get device info' command: %ld\n",
- PTR_ERR(ack_skb));
- goto error_msg_to_dev;
- }
- ack = wimax_msg_data_len(ack_skb, &ack_len);
- result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
- if (result < 0) {
- dev_err(dev, "'get device info' (0x%04x) command failed: "
- "%d - %s\n", I2400M_MT_GET_DEVICE_INFO, result,
- strerr);
- goto error_cmd_failed;
- }
- tlv = i2400m_tlv_find(i2400m, ack->pl, ack_len - sizeof(*ack),
- I2400M_TLV_DETAILED_DEVICE_INFO, sizeof(*ddi));
- if (tlv == NULL) {
- dev_err(dev, "GET DEVICE INFO: "
- "detailed device info TLV not found (0x%04x)\n",
- I2400M_TLV_DETAILED_DEVICE_INFO);
- result = -EIO;
- goto error_no_tlv;
- }
- skb_pull(ack_skb, (void *) tlv - (void *) ack_skb->data);
-error_msg_to_dev:
- kfree(cmd);
-error_alloc:
- return ack_skb;
-
-error_no_tlv:
-error_cmd_failed:
- kfree_skb(ack_skb);
- kfree(cmd);
- return ERR_PTR(result);
-}
-
-
-/* Firmware interface versions we support */
-enum {
- I2400M_HDIv_MAJOR = 9,
- I2400M_HDIv_MINOR = 1,
- I2400M_HDIv_MINOR_2 = 2,
-};
-
-
-/**
- * i2400m_firmware_check - check firmware versions are compatible with
- * the driver
- *
- * @i2400m: device descriptor
- *
- * Returns: 0 if ok, < 0 errno code an error and a message in the
- * kernel log.
- *
- * Long function, but quite simple; first chunk launches the command
- * and double checks the reply for the right TLV. Then we process the
- * TLV (where the meat is).
- *
- * Once we process the TLV that gives us the firmware's interface
- * version, we encode it and save it in i2400m->fw_version for future
- * reference.
- */
-int i2400m_firmware_check(struct i2400m *i2400m)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *ack_skb;
- struct i2400m_l3l4_hdr *cmd;
- const struct i2400m_l3l4_hdr *ack;
- size_t ack_len;
- const struct i2400m_tlv_hdr *tlv;
- const struct i2400m_tlv_l4_message_versions *l4mv;
- char strerr[32];
- unsigned major, minor, branch;
-
- result = -ENOMEM;
- cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
- if (cmd == NULL)
- goto error_alloc;
- cmd->type = cpu_to_le16(I2400M_MT_GET_LM_VERSION);
- cmd->length = 0;
- cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
-
- ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
- if (IS_ERR(ack_skb)) {
- result = PTR_ERR(ack_skb);
- dev_err(dev, "Failed to issue 'get lm version' command: %-d\n",
- result);
- goto error_msg_to_dev;
- }
- ack = wimax_msg_data_len(ack_skb, &ack_len);
- result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
- if (result < 0) {
- dev_err(dev, "'get lm version' (0x%04x) command failed: "
- "%d - %s\n", I2400M_MT_GET_LM_VERSION, result,
- strerr);
- goto error_cmd_failed;
- }
- tlv = i2400m_tlv_find(i2400m, ack->pl, ack_len - sizeof(*ack),
- I2400M_TLV_L4_MESSAGE_VERSIONS, sizeof(*l4mv));
- if (tlv == NULL) {
- dev_err(dev, "get lm version: TLV not found (0x%04x)\n",
- I2400M_TLV_L4_MESSAGE_VERSIONS);
- result = -EIO;
- goto error_no_tlv;
- }
- l4mv = container_of(tlv, typeof(*l4mv), hdr);
- major = le16_to_cpu(l4mv->major);
- minor = le16_to_cpu(l4mv->minor);
- branch = le16_to_cpu(l4mv->branch);
- result = -EINVAL;
- if (major != I2400M_HDIv_MAJOR) {
- dev_err(dev, "unsupported major fw version "
- "%u.%u.%u\n", major, minor, branch);
- goto error_bad_major;
- }
- result = 0;
- if (minor > I2400M_HDIv_MINOR_2 || minor < I2400M_HDIv_MINOR)
- dev_warn(dev, "untested minor fw version %u.%u.%u\n",
- major, minor, branch);
- /* Yes, we ignore the branch -- we don't have to track it */
- i2400m->fw_version = major << 16 | minor;
- dev_info(dev, "firmware interface version %u.%u.%u\n",
- major, minor, branch);
-error_bad_major:
-error_no_tlv:
-error_cmd_failed:
- kfree_skb(ack_skb);
-error_msg_to_dev:
- kfree(cmd);
-error_alloc:
- return result;
-}
-
-
-/*
- * Send an DoExitIdle command to the device to ask it to go out of
- * basestation-idle mode.
- *
- * @i2400m: device descriptor
- *
- * This starts a renegotiation with the basestation that might involve
- * another crypto handshake with user space.
- *
- * Returns: 0 if ok, < 0 errno code on error.
- */
-int i2400m_cmd_exit_idle(struct i2400m *i2400m)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *ack_skb;
- struct i2400m_l3l4_hdr *cmd;
- char strerr[32];
-
- result = -ENOMEM;
- cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
- if (cmd == NULL)
- goto error_alloc;
- cmd->type = cpu_to_le16(I2400M_MT_CMD_EXIT_IDLE);
- cmd->length = 0;
- cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
-
- ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
- result = PTR_ERR(ack_skb);
- if (IS_ERR(ack_skb)) {
- dev_err(dev, "Failed to issue 'exit idle' command: %d\n",
- result);
- goto error_msg_to_dev;
- }
- result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
- strerr, sizeof(strerr));
- kfree_skb(ack_skb);
-error_msg_to_dev:
- kfree(cmd);
-error_alloc:
- return result;
-
-}
-
-
-/*
- * Query the device for its state, update the WiMAX stack's idea of it
- *
- * @i2400m: device descriptor
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * Executes a 'Get State' command and parses the returned
- * TLVs.
- *
- * Because this is almost identical to a 'Report State', we use
- * i2400m_report_state_hook() to parse the answer. This will set the
- * carrier state, as well as the RF Kill switches state.
- */
-static int i2400m_cmd_get_state(struct i2400m *i2400m)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *ack_skb;
- struct i2400m_l3l4_hdr *cmd;
- const struct i2400m_l3l4_hdr *ack;
- size_t ack_len;
- char strerr[32];
-
- result = -ENOMEM;
- cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
- if (cmd == NULL)
- goto error_alloc;
- cmd->type = cpu_to_le16(I2400M_MT_GET_STATE);
- cmd->length = 0;
- cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
-
- ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
- if (IS_ERR(ack_skb)) {
- dev_err(dev, "Failed to issue 'get state' command: %ld\n",
- PTR_ERR(ack_skb));
- result = PTR_ERR(ack_skb);
- goto error_msg_to_dev;
- }
- ack = wimax_msg_data_len(ack_skb, &ack_len);
- result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
- if (result < 0) {
- dev_err(dev, "'get state' (0x%04x) command failed: "
- "%d - %s\n", I2400M_MT_GET_STATE, result, strerr);
- goto error_cmd_failed;
- }
- i2400m_report_state_hook(i2400m, ack, ack_len - sizeof(*ack),
- "GET STATE");
- result = 0;
- kfree_skb(ack_skb);
-error_cmd_failed:
-error_msg_to_dev:
- kfree(cmd);
-error_alloc:
- return result;
-}
-
-/**
- * Set basic configuration settings
- *
- * @i2400m: device descriptor
- * @args: array of pointers to the TLV headers to send for
- * configuration (each followed by its payload).
- * TLV headers and payloads must be properly initialized, with the
- * right endianess (LE).
- * @arg_size: number of pointers in the @args array
- */
-static int i2400m_set_init_config(struct i2400m *i2400m,
- const struct i2400m_tlv_hdr **arg,
- size_t args)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *ack_skb;
- struct i2400m_l3l4_hdr *cmd;
- char strerr[32];
- unsigned argc, argsize, tlv_size;
- const struct i2400m_tlv_hdr *tlv_hdr;
- void *buf, *itr;
-
- d_fnstart(3, dev, "(i2400m %p arg %p args %zu)\n", i2400m, arg, args);
- result = 0;
- if (args == 0)
- goto none;
- /* Compute the size of all the TLVs, so we can alloc a
- * contiguous command block to copy them. */
- argsize = 0;
- for (argc = 0; argc < args; argc++) {
- tlv_hdr = arg[argc];
- argsize += sizeof(*tlv_hdr) + le16_to_cpu(tlv_hdr->length);
- }
- WARN_ON(argc >= 9); /* As per hw spec */
-
- /* Alloc the space for the command and TLVs*/
- result = -ENOMEM;
- buf = kzalloc(sizeof(*cmd) + argsize, GFP_KERNEL);
- if (buf == NULL)
- goto error_alloc;
- cmd = buf;
- cmd->type = cpu_to_le16(I2400M_MT_SET_INIT_CONFIG);
- cmd->length = cpu_to_le16(argsize);
- cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
-
- /* Copy the TLVs */
- itr = buf + sizeof(*cmd);
- for (argc = 0; argc < args; argc++) {
- tlv_hdr = arg[argc];
- tlv_size = sizeof(*tlv_hdr) + le16_to_cpu(tlv_hdr->length);
- memcpy(itr, tlv_hdr, tlv_size);
- itr += tlv_size;
- }
-
- /* Send the message! */
- ack_skb = i2400m_msg_to_dev(i2400m, buf, sizeof(*cmd) + argsize);
- result = PTR_ERR(ack_skb);
- if (IS_ERR(ack_skb)) {
- dev_err(dev, "Failed to issue 'init config' command: %d\n",
- result);
-
- goto error_msg_to_dev;
- }
- result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
- strerr, sizeof(strerr));
- if (result < 0)
- dev_err(dev, "'init config' (0x%04x) command failed: %d - %s\n",
- I2400M_MT_SET_INIT_CONFIG, result, strerr);
- kfree_skb(ack_skb);
-error_msg_to_dev:
- kfree(buf);
-error_alloc:
-none:
- d_fnend(3, dev, "(i2400m %p arg %p args %zu) = %d\n",
- i2400m, arg, args, result);
- return result;
-
-}
-
-/**
- * i2400m_set_idle_timeout - Set the device's idle mode timeout
- *
- * @i2400m: i2400m device descriptor
- *
- * @msecs: milliseconds for the timeout to enter idle mode. Between
- * 100 to 300000 (5m); 0 to disable. In increments of 100.
- *
- * After this @msecs of the link being idle (no data being sent or
- * received), the device will negotiate with the basestation entering
- * idle mode for saving power. The connection is maintained, but
- * getting out of it (done in tx.c) will require some negotiation,
- * possible crypto re-handshake and a possible DHCP re-lease.
- *
- * Only available if fw_version >= 0x00090002.
- *
- * Returns: 0 if ok, < 0 errno code on error.
- */
-int i2400m_set_idle_timeout(struct i2400m *i2400m, unsigned msecs)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *ack_skb;
- struct {
- struct i2400m_l3l4_hdr hdr;
- struct i2400m_tlv_config_idle_timeout cit;
- } *cmd;
- const struct i2400m_l3l4_hdr *ack;
- size_t ack_len;
- char strerr[32];
-
- result = -ENOSYS;
- if (i2400m_le_v1_3(i2400m))
- goto error_alloc;
- result = -ENOMEM;
- cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
- if (cmd == NULL)
- goto error_alloc;
- cmd->hdr.type = cpu_to_le16(I2400M_MT_GET_STATE);
- cmd->hdr.length = cpu_to_le16(sizeof(*cmd) - sizeof(cmd->hdr));
- cmd->hdr.version = cpu_to_le16(I2400M_L3L4_VERSION);
-
- cmd->cit.hdr.type =
- cpu_to_le16(I2400M_TLV_CONFIG_IDLE_TIMEOUT);
- cmd->cit.hdr.length = cpu_to_le16(sizeof(cmd->cit.timeout));
- cmd->cit.timeout = cpu_to_le32(msecs);
-
- ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
- if (IS_ERR(ack_skb)) {
- dev_err(dev, "Failed to issue 'set idle timeout' command: "
- "%ld\n", PTR_ERR(ack_skb));
- result = PTR_ERR(ack_skb);
- goto error_msg_to_dev;
- }
- ack = wimax_msg_data_len(ack_skb, &ack_len);
- result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
- if (result < 0) {
- dev_err(dev, "'set idle timeout' (0x%04x) command failed: "
- "%d - %s\n", I2400M_MT_GET_STATE, result, strerr);
- goto error_cmd_failed;
- }
- result = 0;
- kfree_skb(ack_skb);
-error_cmd_failed:
-error_msg_to_dev:
- kfree(cmd);
-error_alloc:
- return result;
-}
-
-
-/**
- * i2400m_dev_initialize - Initialize the device once communications are ready
- *
- * @i2400m: device descriptor
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * Configures the device to work the way we like it.
- *
- * At the point of this call, the device is registered with the WiMAX
- * and netdev stacks, firmware is uploaded and we can talk to the
- * device normally.
- */
-int i2400m_dev_initialize(struct i2400m *i2400m)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct i2400m_tlv_config_idle_parameters idle_params;
- struct i2400m_tlv_config_idle_timeout idle_timeout;
- struct i2400m_tlv_config_d2h_data_format df;
- struct i2400m_tlv_config_dl_host_reorder dlhr;
- const struct i2400m_tlv_hdr *args[9];
- unsigned argc = 0;
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
- if (i2400m_passive_mode)
- goto out_passive;
- /* Disable idle mode? (enabled by default) */
- if (i2400m_idle_mode_disabled) {
- if (i2400m_le_v1_3(i2400m)) {
- idle_params.hdr.type =
- cpu_to_le16(I2400M_TLV_CONFIG_IDLE_PARAMETERS);
- idle_params.hdr.length = cpu_to_le16(
- sizeof(idle_params) - sizeof(idle_params.hdr));
- idle_params.idle_timeout = 0;
- idle_params.idle_paging_interval = 0;
- args[argc++] = &idle_params.hdr;
- } else {
- idle_timeout.hdr.type =
- cpu_to_le16(I2400M_TLV_CONFIG_IDLE_TIMEOUT);
- idle_timeout.hdr.length = cpu_to_le16(
- sizeof(idle_timeout) - sizeof(idle_timeout.hdr));
- idle_timeout.timeout = 0;
- args[argc++] = &idle_timeout.hdr;
- }
- }
- if (i2400m_ge_v1_4(i2400m)) {
- /* Enable extended RX data format? */
- df.hdr.type =
- cpu_to_le16(I2400M_TLV_CONFIG_D2H_DATA_FORMAT);
- df.hdr.length = cpu_to_le16(
- sizeof(df) - sizeof(df.hdr));
- df.format = 1;
- args[argc++] = &df.hdr;
-
- /* Enable RX data reordering?
- * (switch flipped in rx.c:i2400m_rx_setup() after fw upload) */
- if (i2400m->rx_reorder) {
- dlhr.hdr.type =
- cpu_to_le16(I2400M_TLV_CONFIG_DL_HOST_REORDER);
- dlhr.hdr.length = cpu_to_le16(
- sizeof(dlhr) - sizeof(dlhr.hdr));
- dlhr.reorder = 1;
- args[argc++] = &dlhr.hdr;
- }
- }
- result = i2400m_set_init_config(i2400m, args, argc);
- if (result < 0)
- goto error;
-out_passive:
- /*
- * Update state: Here it just calls a get state; parsing the
- * result (System State TLV and RF Status TLV [done in the rx
- * path hooks]) will set the hardware and software RF-Kill
- * status.
- */
- result = i2400m_cmd_get_state(i2400m);
-error:
- if (result < 0)
- dev_err(dev, "failed to initialize the device: %d\n", result);
- d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
- return result;
-}
-
-
-/**
- * i2400m_dev_shutdown - Shutdown a running device
- *
- * @i2400m: device descriptor
- *
- * Release resources acquired during the running of the device; in
- * theory, should also tell the device to go to sleep, switch off the
- * radio, all that, but at this point, in most cases (driver
- * disconnection, reset handling) we can't even talk to the device.
- */
-void i2400m_dev_shutdown(struct i2400m *i2400m)
-{
- struct device *dev = i2400m_dev(i2400m);
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
- d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Debug levels control file for the i2400m module
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-#ifndef __debug_levels__h__
-#define __debug_levels__h__
-
-/* Maximum compile and run time debug level for all submodules */
-#define D_MODULENAME i2400m
-#define D_MASTER CONFIG_WIMAX_I2400M_DEBUG_LEVEL
-
-#include <linux/wimax/debug.h>
-
-/* List of all the enabled modules */
-enum d_module {
- D_SUBMODULE_DECLARE(control),
- D_SUBMODULE_DECLARE(driver),
- D_SUBMODULE_DECLARE(debugfs),
- D_SUBMODULE_DECLARE(fw),
- D_SUBMODULE_DECLARE(netdev),
- D_SUBMODULE_DECLARE(rfkill),
- D_SUBMODULE_DECLARE(rx),
- D_SUBMODULE_DECLARE(sysfs),
- D_SUBMODULE_DECLARE(tx),
-};
-
-
-#endif /* #ifndef __debug_levels__h__ */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Debugfs interfaces to manipulate driver and device information
- *
- * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-
-#include <linux/debugfs.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/spinlock.h>
-#include <linux/device.h>
-#include <linux/export.h>
-#include "i2400m.h"
-
-
-#define D_SUBMODULE debugfs
-#include "debug-levels.h"
-
-static
-int debugfs_netdev_queue_stopped_get(void *data, u64 *val)
-{
- struct i2400m *i2400m = data;
- *val = netif_queue_stopped(i2400m->wimax_dev.net_dev);
- return 0;
-}
-DEFINE_DEBUGFS_ATTRIBUTE(fops_netdev_queue_stopped,
- debugfs_netdev_queue_stopped_get,
- NULL, "%llu\n");
-
-/*
- * We don't allow partial reads of this file, as then the reader would
- * get weirdly confused data as it is updated.
- *
- * So or you read it all or nothing; if you try to read with an offset
- * != 0, we consider you are done reading.
- */
-static
-ssize_t i2400m_rx_stats_read(struct file *filp, char __user *buffer,
- size_t count, loff_t *ppos)
-{
- struct i2400m *i2400m = filp->private_data;
- char buf[128];
- unsigned long flags;
-
- if (*ppos != 0)
- return 0;
- if (count < sizeof(buf))
- return -ENOSPC;
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- snprintf(buf, sizeof(buf), "%u %u %u %u %u %u %u\n",
- i2400m->rx_pl_num, i2400m->rx_pl_min,
- i2400m->rx_pl_max, i2400m->rx_num,
- i2400m->rx_size_acc,
- i2400m->rx_size_min, i2400m->rx_size_max);
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
-}
-
-
-/* Any write clears the stats */
-static
-ssize_t i2400m_rx_stats_write(struct file *filp, const char __user *buffer,
- size_t count, loff_t *ppos)
-{
- struct i2400m *i2400m = filp->private_data;
- unsigned long flags;
-
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- i2400m->rx_pl_num = 0;
- i2400m->rx_pl_max = 0;
- i2400m->rx_pl_min = UINT_MAX;
- i2400m->rx_num = 0;
- i2400m->rx_size_acc = 0;
- i2400m->rx_size_min = UINT_MAX;
- i2400m->rx_size_max = 0;
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- return count;
-}
-
-static
-const struct file_operations i2400m_rx_stats_fops = {
- .owner = THIS_MODULE,
- .open = simple_open,
- .read = i2400m_rx_stats_read,
- .write = i2400m_rx_stats_write,
- .llseek = default_llseek,
-};
-
-
-/* See i2400m_rx_stats_read() */
-static
-ssize_t i2400m_tx_stats_read(struct file *filp, char __user *buffer,
- size_t count, loff_t *ppos)
-{
- struct i2400m *i2400m = filp->private_data;
- char buf[128];
- unsigned long flags;
-
- if (*ppos != 0)
- return 0;
- if (count < sizeof(buf))
- return -ENOSPC;
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- snprintf(buf, sizeof(buf), "%u %u %u %u %u %u %u\n",
- i2400m->tx_pl_num, i2400m->tx_pl_min,
- i2400m->tx_pl_max, i2400m->tx_num,
- i2400m->tx_size_acc,
- i2400m->tx_size_min, i2400m->tx_size_max);
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
- return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
-}
-
-/* Any write clears the stats */
-static
-ssize_t i2400m_tx_stats_write(struct file *filp, const char __user *buffer,
- size_t count, loff_t *ppos)
-{
- struct i2400m *i2400m = filp->private_data;
- unsigned long flags;
-
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- i2400m->tx_pl_num = 0;
- i2400m->tx_pl_max = 0;
- i2400m->tx_pl_min = UINT_MAX;
- i2400m->tx_num = 0;
- i2400m->tx_size_acc = 0;
- i2400m->tx_size_min = UINT_MAX;
- i2400m->tx_size_max = 0;
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
- return count;
-}
-
-static
-const struct file_operations i2400m_tx_stats_fops = {
- .owner = THIS_MODULE,
- .open = simple_open,
- .read = i2400m_tx_stats_read,
- .write = i2400m_tx_stats_write,
- .llseek = default_llseek,
-};
-
-
-/* Write 1 to ask the device to go into suspend */
-static
-int debugfs_i2400m_suspend_set(void *data, u64 val)
-{
- int result;
- struct i2400m *i2400m = data;
- result = i2400m_cmd_enter_powersave(i2400m);
- if (result >= 0)
- result = 0;
- return result;
-}
-DEFINE_DEBUGFS_ATTRIBUTE(fops_i2400m_suspend,
- NULL, debugfs_i2400m_suspend_set,
- "%llu\n");
-
-/*
- * Reset the device
- *
- * Write 0 to ask the device to soft reset, 1 to cold reset, 2 to bus
- * reset (as defined by enum i2400m_reset_type).
- */
-static
-int debugfs_i2400m_reset_set(void *data, u64 val)
-{
- int result;
- struct i2400m *i2400m = data;
- enum i2400m_reset_type rt = val;
- switch(rt) {
- case I2400M_RT_WARM:
- case I2400M_RT_COLD:
- case I2400M_RT_BUS:
- result = i2400m_reset(i2400m, rt);
- if (result >= 0)
- result = 0;
- break;
- default:
- result = -EINVAL;
- }
- return result;
-}
-DEFINE_DEBUGFS_ATTRIBUTE(fops_i2400m_reset,
- NULL, debugfs_i2400m_reset_set,
- "%llu\n");
-
-void i2400m_debugfs_add(struct i2400m *i2400m)
-{
- struct dentry *dentry = i2400m->wimax_dev.debugfs_dentry;
-
- dentry = debugfs_create_dir("i2400m", dentry);
- i2400m->debugfs_dentry = dentry;
-
- d_level_register_debugfs("dl_", control, dentry);
- d_level_register_debugfs("dl_", driver, dentry);
- d_level_register_debugfs("dl_", debugfs, dentry);
- d_level_register_debugfs("dl_", fw, dentry);
- d_level_register_debugfs("dl_", netdev, dentry);
- d_level_register_debugfs("dl_", rfkill, dentry);
- d_level_register_debugfs("dl_", rx, dentry);
- d_level_register_debugfs("dl_", tx, dentry);
-
- debugfs_create_size_t("tx_in", 0400, dentry, &i2400m->tx_in);
- debugfs_create_size_t("tx_out", 0400, dentry, &i2400m->tx_out);
- debugfs_create_u32("state", 0600, dentry, &i2400m->state);
-
- /*
- * Trace received messages from user space
- *
- * In order to tap the bidirectional message stream in the
- * 'msg' pipe, user space can read from the 'msg' pipe;
- * however, due to limitations in libnl, we can't know what
- * the different applications are sending down to the kernel.
- *
- * So we have this hack where the driver will echo any message
- * received on the msg pipe from user space [through a call to
- * wimax_dev->op_msg_from_user() into
- * i2400m_op_msg_from_user()] into the 'trace' pipe that this
- * driver creates.
- *
- * So then, reading from both the 'trace' and 'msg' pipes in
- * user space will provide a full dump of the traffic.
- *
- * Write 1 to activate, 0 to clear.
- *
- * It is not really very atomic, but it is also not too
- * critical.
- */
- debugfs_create_u8("trace_msg_from_user", 0600, dentry,
- &i2400m->trace_msg_from_user);
-
- debugfs_create_file("netdev_queue_stopped", 0400, dentry, i2400m,
- &fops_netdev_queue_stopped);
-
- debugfs_create_file("rx_stats", 0600, dentry, i2400m,
- &i2400m_rx_stats_fops);
-
- debugfs_create_file("tx_stats", 0600, dentry, i2400m,
- &i2400m_tx_stats_fops);
-
- debugfs_create_file("suspend", 0200, dentry, i2400m,
- &fops_i2400m_suspend);
-
- debugfs_create_file("reset", 0200, dentry, i2400m, &fops_i2400m_reset);
-}
-
-void i2400m_debugfs_rm(struct i2400m *i2400m)
-{
- debugfs_remove_recursive(i2400m->debugfs_dentry);
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Generic probe/disconnect, reset and message passing
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * See i2400m.h for driver documentation. This contains helpers for
- * the driver model glue [_setup()/_release()], handling device resets
- * [_dev_reset_handle()], and the backends for the WiMAX stack ops
- * reset [_op_reset()] and message from user [_op_msg_from_user()].
- *
- * ROADMAP:
- *
- * i2400m_op_msg_from_user()
- * i2400m_msg_to_dev()
- * wimax_msg_to_user_send()
- *
- * i2400m_op_reset()
- * i240m->bus_reset()
- *
- * i2400m_dev_reset_handle()
- * __i2400m_dev_reset_handle()
- * __i2400m_dev_stop()
- * __i2400m_dev_start()
- *
- * i2400m_setup()
- * i2400m->bus_setup()
- * i2400m_bootrom_init()
- * register_netdev()
- * wimax_dev_add()
- * i2400m_dev_start()
- * __i2400m_dev_start()
- * i2400m_dev_bootstrap()
- * i2400m_tx_setup()
- * i2400m->bus_dev_start()
- * i2400m_firmware_check()
- * i2400m_check_mac_addr()
- *
- * i2400m_release()
- * i2400m_dev_stop()
- * __i2400m_dev_stop()
- * i2400m_dev_shutdown()
- * i2400m->bus_dev_stop()
- * i2400m_tx_release()
- * i2400m->bus_release()
- * wimax_dev_rm()
- * unregister_netdev()
- */
-#include "i2400m.h"
-#include <linux/etherdevice.h>
-#include <linux/wimax/i2400m.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/suspend.h>
-#include <linux/slab.h>
-
-#define D_SUBMODULE driver
-#include "debug-levels.h"
-
-
-static char i2400m_debug_params[128];
-module_param_string(debug, i2400m_debug_params, sizeof(i2400m_debug_params),
- 0644);
-MODULE_PARM_DESC(debug,
- "String of space-separated NAME:VALUE pairs, where NAMEs "
- "are the different debug submodules and VALUE are the "
- "initial debug value to set.");
-
-static char i2400m_barkers_params[128];
-module_param_string(barkers, i2400m_barkers_params,
- sizeof(i2400m_barkers_params), 0644);
-MODULE_PARM_DESC(barkers,
- "String of comma-separated 32-bit values; each is "
- "recognized as the value the device sends as a reboot "
- "signal; values are appended to a list--setting one value "
- "as zero cleans the existing list and starts a new one.");
-
-/*
- * WiMAX stack operation: relay a message from user space
- *
- * @wimax_dev: device descriptor
- * @pipe_name: named pipe the message is for
- * @msg_buf: pointer to the message bytes
- * @msg_len: length of the buffer
- * @genl_info: passed by the generic netlink layer
- *
- * The WiMAX stack will call this function when a message was received
- * from user space.
- *
- * For the i2400m, this is an L3L4 message, as specified in
- * include/linux/wimax/i2400m.h, and thus prefixed with a 'struct
- * i2400m_l3l4_hdr'. Driver (and device) expect the messages to be
- * coded in Little Endian.
- *
- * This function just verifies that the header declaration and the
- * payload are consistent and then deals with it, either forwarding it
- * to the device or procesing it locally.
- *
- * In the i2400m, messages are basically commands that will carry an
- * ack, so we use i2400m_msg_to_dev() and then deliver the ack back to
- * user space. The rx.c code might intercept the response and use it
- * to update the driver's state, but then it will pass it on so it can
- * be relayed back to user space.
- *
- * Note that asynchronous events from the device are processed and
- * sent to user space in rx.c.
- */
-static
-int i2400m_op_msg_from_user(struct wimax_dev *wimax_dev,
- const char *pipe_name,
- const void *msg_buf, size_t msg_len,
- const struct genl_info *genl_info)
-{
- int result;
- struct i2400m *i2400m = wimax_dev_to_i2400m(wimax_dev);
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *ack_skb;
-
- d_fnstart(4, dev, "(wimax_dev %p [i2400m %p] msg_buf %p "
- "msg_len %zu genl_info %p)\n", wimax_dev, i2400m,
- msg_buf, msg_len, genl_info);
- ack_skb = i2400m_msg_to_dev(i2400m, msg_buf, msg_len);
- result = PTR_ERR(ack_skb);
- if (IS_ERR(ack_skb))
- goto error_msg_to_dev;
- result = wimax_msg_send(&i2400m->wimax_dev, ack_skb);
-error_msg_to_dev:
- d_fnend(4, dev, "(wimax_dev %p [i2400m %p] msg_buf %p msg_len %zu "
- "genl_info %p) = %d\n", wimax_dev, i2400m, msg_buf, msg_len,
- genl_info, result);
- return result;
-}
-
-
-/*
- * Context to wait for a reset to finalize
- */
-struct i2400m_reset_ctx {
- struct completion completion;
- int result;
-};
-
-
-/*
- * WiMAX stack operation: reset a device
- *
- * @wimax_dev: device descriptor
- *
- * See the documentation for wimax_reset() and wimax_dev->op_reset for
- * the requirements of this function. The WiMAX stack guarantees
- * serialization on calls to this function.
- *
- * Do a warm reset on the device; if it fails, resort to a cold reset
- * and return -ENODEV. On successful warm reset, we need to block
- * until it is complete.
- *
- * The bus-driver implementation of reset takes care of falling back
- * to cold reset if warm fails.
- */
-static
-int i2400m_op_reset(struct wimax_dev *wimax_dev)
-{
- int result;
- struct i2400m *i2400m = wimax_dev_to_i2400m(wimax_dev);
- struct device *dev = i2400m_dev(i2400m);
- struct i2400m_reset_ctx ctx = {
- .completion = COMPLETION_INITIALIZER_ONSTACK(ctx.completion),
- .result = 0,
- };
-
- d_fnstart(4, dev, "(wimax_dev %p)\n", wimax_dev);
- mutex_lock(&i2400m->init_mutex);
- i2400m->reset_ctx = &ctx;
- mutex_unlock(&i2400m->init_mutex);
- result = i2400m_reset(i2400m, I2400M_RT_WARM);
- if (result < 0)
- goto out;
- result = wait_for_completion_timeout(&ctx.completion, 4*HZ);
- if (result == 0)
- result = -ETIMEDOUT;
- else if (result > 0)
- result = ctx.result;
- /* if result < 0, pass it on */
- mutex_lock(&i2400m->init_mutex);
- i2400m->reset_ctx = NULL;
- mutex_unlock(&i2400m->init_mutex);
-out:
- d_fnend(4, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
- return result;
-}
-
-
-/*
- * Check the MAC address we got from boot mode is ok
- *
- * @i2400m: device descriptor
- *
- * Returns: 0 if ok, < 0 errno code on error.
- */
-static
-int i2400m_check_mac_addr(struct i2400m *i2400m)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *skb;
- const struct i2400m_tlv_detailed_device_info *ddi;
- struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
- skb = i2400m_get_device_info(i2400m);
- if (IS_ERR(skb)) {
- result = PTR_ERR(skb);
- dev_err(dev, "Cannot verify MAC address, error reading: %d\n",
- result);
- goto error;
- }
- /* Extract MAC address */
- ddi = (void *) skb->data;
- BUILD_BUG_ON(ETH_ALEN != sizeof(ddi->mac_address));
- d_printf(2, dev, "GET DEVICE INFO: mac addr %pM\n",
- ddi->mac_address);
- if (!memcmp(net_dev->perm_addr, ddi->mac_address,
- sizeof(ddi->mac_address)))
- goto ok;
- dev_warn(dev, "warning: device reports a different MAC address "
- "to that of boot mode's\n");
- dev_warn(dev, "device reports %pM\n", ddi->mac_address);
- dev_warn(dev, "boot mode reported %pM\n", net_dev->perm_addr);
- if (is_zero_ether_addr(ddi->mac_address))
- dev_err(dev, "device reports an invalid MAC address, "
- "not updating\n");
- else {
- dev_warn(dev, "updating MAC address\n");
- net_dev->addr_len = ETH_ALEN;
- memcpy(net_dev->perm_addr, ddi->mac_address, ETH_ALEN);
- memcpy(net_dev->dev_addr, ddi->mac_address, ETH_ALEN);
- }
-ok:
- result = 0;
- kfree_skb(skb);
-error:
- d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
- return result;
-}
-
-
-/**
- * __i2400m_dev_start - Bring up driver communication with the device
- *
- * @i2400m: device descriptor
- * @flags: boot mode flags
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * Uploads firmware and brings up all the resources needed to be able
- * to communicate with the device.
- *
- * The workqueue has to be setup early, at least before RX handling
- * (it's only real user for now) so it can process reports as they
- * arrive. We also want to destroy it if we retry, to make sure it is
- * flushed...easier like this.
- *
- * TX needs to be setup before the bus-specific code (otherwise on
- * shutdown, the bus-tx code could try to access it).
- */
-static
-int __i2400m_dev_start(struct i2400m *i2400m, enum i2400m_bri flags)
-{
- int result;
- struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
- struct net_device *net_dev = wimax_dev->net_dev;
- struct device *dev = i2400m_dev(i2400m);
- int times = i2400m->bus_bm_retries;
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-retry:
- result = i2400m_dev_bootstrap(i2400m, flags);
- if (result < 0) {
- dev_err(dev, "cannot bootstrap device: %d\n", result);
- goto error_bootstrap;
- }
- result = i2400m_tx_setup(i2400m);
- if (result < 0)
- goto error_tx_setup;
- result = i2400m_rx_setup(i2400m);
- if (result < 0)
- goto error_rx_setup;
- i2400m->work_queue = create_singlethread_workqueue(wimax_dev->name);
- if (i2400m->work_queue == NULL) {
- result = -ENOMEM;
- dev_err(dev, "cannot create workqueue\n");
- goto error_create_workqueue;
- }
- if (i2400m->bus_dev_start) {
- result = i2400m->bus_dev_start(i2400m);
- if (result < 0)
- goto error_bus_dev_start;
- }
- i2400m->ready = 1;
- wmb(); /* see i2400m->ready's documentation */
- /* process pending reports from the device */
- queue_work(i2400m->work_queue, &i2400m->rx_report_ws);
- result = i2400m_firmware_check(i2400m); /* fw versions ok? */
- if (result < 0)
- goto error_fw_check;
- /* At this point is ok to send commands to the device */
- result = i2400m_check_mac_addr(i2400m);
- if (result < 0)
- goto error_check_mac_addr;
- result = i2400m_dev_initialize(i2400m);
- if (result < 0)
- goto error_dev_initialize;
-
- /* We don't want any additional unwanted error recovery triggered
- * from any other context so if anything went wrong before we come
- * here, let's keep i2400m->error_recovery untouched and leave it to
- * dev_reset_handle(). See dev_reset_handle(). */
-
- atomic_dec(&i2400m->error_recovery);
- /* Every thing works so far, ok, now we are ready to
- * take error recovery if it's required. */
-
- /* At this point, reports will come for the device and set it
- * to the right state if it is different than UNINITIALIZED */
- d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
- net_dev, i2400m, result);
- return result;
-
-error_dev_initialize:
-error_check_mac_addr:
-error_fw_check:
- i2400m->ready = 0;
- wmb(); /* see i2400m->ready's documentation */
- flush_workqueue(i2400m->work_queue);
- if (i2400m->bus_dev_stop)
- i2400m->bus_dev_stop(i2400m);
-error_bus_dev_start:
- destroy_workqueue(i2400m->work_queue);
-error_create_workqueue:
- i2400m_rx_release(i2400m);
-error_rx_setup:
- i2400m_tx_release(i2400m);
-error_tx_setup:
-error_bootstrap:
- if (result == -EL3RST && times-- > 0) {
- flags = I2400M_BRI_SOFT|I2400M_BRI_MAC_REINIT;
- goto retry;
- }
- d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
- net_dev, i2400m, result);
- return result;
-}
-
-
-static
-int i2400m_dev_start(struct i2400m *i2400m, enum i2400m_bri bm_flags)
-{
- int result = 0;
- mutex_lock(&i2400m->init_mutex); /* Well, start the device */
- if (i2400m->updown == 0) {
- result = __i2400m_dev_start(i2400m, bm_flags);
- if (result >= 0) {
- i2400m->updown = 1;
- i2400m->alive = 1;
- wmb();/* see i2400m->updown and i2400m->alive's doc */
- }
- }
- mutex_unlock(&i2400m->init_mutex);
- return result;
-}
-
-
-/**
- * i2400m_dev_stop - Tear down driver communication with the device
- *
- * @i2400m: device descriptor
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * Releases all the resources allocated to communicate with the
- * device. Note we cannot destroy the workqueue earlier as until RX is
- * fully destroyed, it could still try to schedule jobs.
- */
-static
-void __i2400m_dev_stop(struct i2400m *i2400m)
-{
- struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
- struct device *dev = i2400m_dev(i2400m);
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
- wimax_state_change(wimax_dev, __WIMAX_ST_QUIESCING);
- i2400m_msg_to_dev_cancel_wait(i2400m, -EL3RST);
- complete(&i2400m->msg_completion);
- i2400m_net_wake_stop(i2400m);
- i2400m_dev_shutdown(i2400m);
- /*
- * Make sure no report hooks are running *before* we stop the
- * communication infrastructure with the device.
- */
- i2400m->ready = 0; /* nobody can queue work anymore */
- wmb(); /* see i2400m->ready's documentation */
- flush_workqueue(i2400m->work_queue);
-
- if (i2400m->bus_dev_stop)
- i2400m->bus_dev_stop(i2400m);
- destroy_workqueue(i2400m->work_queue);
- i2400m_rx_release(i2400m);
- i2400m_tx_release(i2400m);
- wimax_state_change(wimax_dev, WIMAX_ST_DOWN);
- d_fnend(3, dev, "(i2400m %p) = 0\n", i2400m);
-}
-
-
-/*
- * Watch out -- we only need to stop if there is a need for it. The
- * device could have reset itself and failed to come up again (see
- * _i2400m_dev_reset_handle()).
- */
-static
-void i2400m_dev_stop(struct i2400m *i2400m)
-{
- mutex_lock(&i2400m->init_mutex);
- if (i2400m->updown) {
- __i2400m_dev_stop(i2400m);
- i2400m->updown = 0;
- i2400m->alive = 0;
- wmb(); /* see i2400m->updown and i2400m->alive's doc */
- }
- mutex_unlock(&i2400m->init_mutex);
-}
-
-
-/*
- * Listen to PM events to cache the firmware before suspend/hibernation
- *
- * When the device comes out of suspend, it might go into reset and
- * firmware has to be uploaded again. At resume, most of the times, we
- * can't load firmware images from disk, so we need to cache it.
- *
- * i2400m_fw_cache() will allocate a kobject and attach the firmware
- * to it; that way we don't have to worry too much about the fw loader
- * hitting a race condition.
- *
- * Note: modus operandi stolen from the Orinoco driver; thx.
- */
-static
-int i2400m_pm_notifier(struct notifier_block *notifier,
- unsigned long pm_event,
- void *unused)
-{
- struct i2400m *i2400m =
- container_of(notifier, struct i2400m, pm_notifier);
- struct device *dev = i2400m_dev(i2400m);
-
- d_fnstart(3, dev, "(i2400m %p pm_event %lx)\n", i2400m, pm_event);
- switch (pm_event) {
- case PM_HIBERNATION_PREPARE:
- case PM_SUSPEND_PREPARE:
- i2400m_fw_cache(i2400m);
- break;
- case PM_POST_RESTORE:
- /* Restore from hibernation failed. We need to clean
- * up in exactly the same way, so fall through. */
- case PM_POST_HIBERNATION:
- case PM_POST_SUSPEND:
- i2400m_fw_uncache(i2400m);
- break;
-
- case PM_RESTORE_PREPARE:
- default:
- break;
- }
- d_fnend(3, dev, "(i2400m %p pm_event %lx) = void\n", i2400m, pm_event);
- return NOTIFY_DONE;
-}
-
-
-/*
- * pre-reset is called before a device is going on reset
- *
- * This has to be followed by a call to i2400m_post_reset(), otherwise
- * bad things might happen.
- */
-int i2400m_pre_reset(struct i2400m *i2400m)
-{
- struct device *dev = i2400m_dev(i2400m);
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
- d_printf(1, dev, "pre-reset shut down\n");
-
- mutex_lock(&i2400m->init_mutex);
- if (i2400m->updown) {
- netif_tx_disable(i2400m->wimax_dev.net_dev);
- __i2400m_dev_stop(i2400m);
- /* down't set updown to zero -- this way
- * post_reset can restore properly */
- }
- mutex_unlock(&i2400m->init_mutex);
- if (i2400m->bus_release)
- i2400m->bus_release(i2400m);
- d_fnend(3, dev, "(i2400m %p) = 0\n", i2400m);
- return 0;
-}
-EXPORT_SYMBOL_GPL(i2400m_pre_reset);
-
-
-/*
- * Restore device state after a reset
- *
- * Do the work needed after a device reset to bring it up to the same
- * state as it was before the reset.
- *
- * NOTE: this requires i2400m->init_mutex taken
- */
-int i2400m_post_reset(struct i2400m *i2400m)
-{
- int result = 0;
- struct device *dev = i2400m_dev(i2400m);
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
- d_printf(1, dev, "post-reset start\n");
- if (i2400m->bus_setup) {
- result = i2400m->bus_setup(i2400m);
- if (result < 0) {
- dev_err(dev, "bus-specific setup failed: %d\n",
- result);
- goto error_bus_setup;
- }
- }
- mutex_lock(&i2400m->init_mutex);
- if (i2400m->updown) {
- result = __i2400m_dev_start(
- i2400m, I2400M_BRI_SOFT | I2400M_BRI_MAC_REINIT);
- if (result < 0)
- goto error_dev_start;
- }
- mutex_unlock(&i2400m->init_mutex);
- d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
- return result;
-
-error_dev_start:
- if (i2400m->bus_release)
- i2400m->bus_release(i2400m);
- /* even if the device was up, it could not be recovered, so we
- * mark it as down. */
- i2400m->updown = 0;
- wmb(); /* see i2400m->updown's documentation */
- mutex_unlock(&i2400m->init_mutex);
-error_bus_setup:
- d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
- return result;
-}
-EXPORT_SYMBOL_GPL(i2400m_post_reset);
-
-
-/*
- * The device has rebooted; fix up the device and the driver
- *
- * Tear down the driver communication with the device, reload the
- * firmware and reinitialize the communication with the device.
- *
- * If someone calls a reset when the device's firmware is down, in
- * theory we won't see it because we are not listening. However, just
- * in case, leave the code to handle it.
- *
- * If there is a reset context, use it; this means someone is waiting
- * for us to tell him when the reset operation is complete and the
- * device is ready to rock again.
- *
- * NOTE: if we are in the process of bringing up or down the
- * communication with the device [running i2400m_dev_start() or
- * _stop()], don't do anything, let it fail and handle it.
- *
- * This function is ran always in a thread context
- *
- * This function gets passed, as payload to i2400m_work() a 'const
- * char *' ptr with a "reason" why the reset happened (for messages).
- */
-static
-void __i2400m_dev_reset_handle(struct work_struct *ws)
-{
- struct i2400m *i2400m = container_of(ws, struct i2400m, reset_ws);
- const char *reason = i2400m->reset_reason;
- struct device *dev = i2400m_dev(i2400m);
- struct i2400m_reset_ctx *ctx = i2400m->reset_ctx;
- int result;
-
- d_fnstart(3, dev, "(ws %p i2400m %p reason %s)\n", ws, i2400m, reason);
-
- i2400m->boot_mode = 1;
- wmb(); /* Make sure i2400m_msg_to_dev() sees boot_mode */
-
- result = 0;
- if (mutex_trylock(&i2400m->init_mutex) == 0) {
- /* We are still in i2400m_dev_start() [let it fail] or
- * i2400m_dev_stop() [we are shutting down anyway, so
- * ignore it] or we are resetting somewhere else. */
- dev_err(dev, "device rebooted somewhere else?\n");
- i2400m_msg_to_dev_cancel_wait(i2400m, -EL3RST);
- complete(&i2400m->msg_completion);
- goto out;
- }
-
- dev_err(dev, "%s: reinitializing driver\n", reason);
- rmb();
- if (i2400m->updown) {
- __i2400m_dev_stop(i2400m);
- i2400m->updown = 0;
- wmb(); /* see i2400m->updown's documentation */
- }
-
- if (i2400m->alive) {
- result = __i2400m_dev_start(i2400m,
- I2400M_BRI_SOFT | I2400M_BRI_MAC_REINIT);
- if (result < 0) {
- dev_err(dev, "%s: cannot start the device: %d\n",
- reason, result);
- result = -EUCLEAN;
- if (atomic_read(&i2400m->bus_reset_retries)
- >= I2400M_BUS_RESET_RETRIES) {
- result = -ENODEV;
- dev_err(dev, "tried too many times to "
- "reset the device, giving up\n");
- }
- }
- }
-
- if (i2400m->reset_ctx) {
- ctx->result = result;
- complete(&ctx->completion);
- }
- mutex_unlock(&i2400m->init_mutex);
- if (result == -EUCLEAN) {
- /*
- * We come here because the reset during operational mode
- * wasn't successfully done and need to proceed to a bus
- * reset. For the dev_reset_handle() to be able to handle
- * the reset event later properly, we restore boot_mode back
- * to the state before previous reset. ie: just like we are
- * issuing the bus reset for the first time
- */
- i2400m->boot_mode = 0;
- wmb();
-
- atomic_inc(&i2400m->bus_reset_retries);
- /* ops, need to clean up [w/ init_mutex not held] */
- result = i2400m_reset(i2400m, I2400M_RT_BUS);
- if (result >= 0)
- result = -ENODEV;
- } else {
- rmb();
- if (i2400m->alive) {
- /* great, we expect the device state up and
- * dev_start() actually brings the device state up */
- i2400m->updown = 1;
- wmb();
- atomic_set(&i2400m->bus_reset_retries, 0);
- }
- }
-out:
- d_fnend(3, dev, "(ws %p i2400m %p reason %s) = void\n",
- ws, i2400m, reason);
-}
-
-
-/**
- * i2400m_dev_reset_handle - Handle a device's reset in a thread context
- *
- * Schedule a device reset handling out on a thread context, so it
- * is safe to call from atomic context. We can't use the i2400m's
- * queue as we are going to destroy it and reinitialize it as part of
- * the driver bringup/bringup process.
- *
- * See __i2400m_dev_reset_handle() for details; that takes care of
- * reinitializing the driver to handle the reset, calling into the
- * bus-specific functions ops as needed.
- */
-int i2400m_dev_reset_handle(struct i2400m *i2400m, const char *reason)
-{
- i2400m->reset_reason = reason;
- return schedule_work(&i2400m->reset_ws);
-}
-EXPORT_SYMBOL_GPL(i2400m_dev_reset_handle);
-
-
- /*
- * The actual work of error recovery.
- *
- * The current implementation of error recovery is to trigger a bus reset.
- */
-static
-void __i2400m_error_recovery(struct work_struct *ws)
-{
- struct i2400m *i2400m = container_of(ws, struct i2400m, recovery_ws);
-
- i2400m_reset(i2400m, I2400M_RT_BUS);
-}
-
-/*
- * Schedule a work struct for error recovery.
- *
- * The intention of error recovery is to bring back the device to some
- * known state whenever TX sees -110 (-ETIMEOUT) on copying the data to
- * the device. The TX failure could mean a device bus stuck, so the current
- * error recovery implementation is to trigger a bus reset to the device
- * and hopefully it can bring back the device.
- *
- * The actual work of error recovery has to be in a thread context because
- * it is kicked off in the TX thread (i2400ms->tx_workqueue) which is to be
- * destroyed by the error recovery mechanism (currently a bus reset).
- *
- * Also, there may be already a queue of TX works that all hit
- * the -ETIMEOUT error condition because the device is stuck already.
- * Since bus reset is used as the error recovery mechanism and we don't
- * want consecutive bus resets simply because the multiple TX works
- * in the queue all hit the same device erratum, the flag "error_recovery"
- * is introduced for preventing unwanted consecutive bus resets.
- *
- * Error recovery shall only be invoked again if previous one was completed.
- * The flag error_recovery is set when error recovery mechanism is scheduled,
- * and is checked when we need to schedule another error recovery. If it is
- * in place already, then we shouldn't schedule another one.
- */
-void i2400m_error_recovery(struct i2400m *i2400m)
-{
- if (atomic_add_return(1, &i2400m->error_recovery) == 1)
- schedule_work(&i2400m->recovery_ws);
- else
- atomic_dec(&i2400m->error_recovery);
-}
-EXPORT_SYMBOL_GPL(i2400m_error_recovery);
-
-/*
- * Alloc the command and ack buffers for boot mode
- *
- * Get the buffers needed to deal with boot mode messages.
- */
-static
-int i2400m_bm_buf_alloc(struct i2400m *i2400m)
-{
- i2400m->bm_cmd_buf = kzalloc(I2400M_BM_CMD_BUF_SIZE, GFP_KERNEL);
- if (i2400m->bm_cmd_buf == NULL)
- goto error_bm_cmd_kzalloc;
- i2400m->bm_ack_buf = kzalloc(I2400M_BM_ACK_BUF_SIZE, GFP_KERNEL);
- if (i2400m->bm_ack_buf == NULL)
- goto error_bm_ack_buf_kzalloc;
- return 0;
-
-error_bm_ack_buf_kzalloc:
- kfree(i2400m->bm_cmd_buf);
-error_bm_cmd_kzalloc:
- return -ENOMEM;
-}
-
-
-/*
- * Free boot mode command and ack buffers.
- */
-static
-void i2400m_bm_buf_free(struct i2400m *i2400m)
-{
- kfree(i2400m->bm_ack_buf);
- kfree(i2400m->bm_cmd_buf);
-}
-
-
-/**
- * i2400m_init - Initialize a 'struct i2400m' from all zeroes
- *
- * This is a bus-generic API call.
- */
-void i2400m_init(struct i2400m *i2400m)
-{
- wimax_dev_init(&i2400m->wimax_dev);
-
- i2400m->boot_mode = 1;
- i2400m->rx_reorder = 1;
- init_waitqueue_head(&i2400m->state_wq);
-
- spin_lock_init(&i2400m->tx_lock);
- i2400m->tx_pl_min = UINT_MAX;
- i2400m->tx_size_min = UINT_MAX;
-
- spin_lock_init(&i2400m->rx_lock);
- i2400m->rx_pl_min = UINT_MAX;
- i2400m->rx_size_min = UINT_MAX;
- INIT_LIST_HEAD(&i2400m->rx_reports);
- INIT_WORK(&i2400m->rx_report_ws, i2400m_report_hook_work);
-
- mutex_init(&i2400m->msg_mutex);
- init_completion(&i2400m->msg_completion);
-
- mutex_init(&i2400m->init_mutex);
- /* wake_tx_ws is initialized in i2400m_tx_setup() */
-
- INIT_WORK(&i2400m->reset_ws, __i2400m_dev_reset_handle);
- INIT_WORK(&i2400m->recovery_ws, __i2400m_error_recovery);
-
- atomic_set(&i2400m->bus_reset_retries, 0);
-
- i2400m->alive = 0;
-
- /* initialize error_recovery to 1 for denoting we
- * are not yet ready to take any error recovery */
- atomic_set(&i2400m->error_recovery, 1);
-}
-EXPORT_SYMBOL_GPL(i2400m_init);
-
-
-int i2400m_reset(struct i2400m *i2400m, enum i2400m_reset_type rt)
-{
- struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-
- /*
- * Make sure we stop TXs and down the carrier before
- * resetting; this is needed to avoid things like
- * i2400m_wake_tx() scheduling stuff in parallel.
- */
- if (net_dev->reg_state == NETREG_REGISTERED) {
- netif_tx_disable(net_dev);
- netif_carrier_off(net_dev);
- }
- return i2400m->bus_reset(i2400m, rt);
-}
-EXPORT_SYMBOL_GPL(i2400m_reset);
-
-
-/**
- * i2400m_setup - bus-generic setup function for the i2400m device
- *
- * @i2400m: device descriptor (bus-specific parts have been initialized)
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * Sets up basic device comunication infrastructure, boots the ROM to
- * read the MAC address, registers with the WiMAX and network stacks
- * and then brings up the device.
- */
-int i2400m_setup(struct i2400m *i2400m, enum i2400m_bri bm_flags)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
- struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-
- snprintf(wimax_dev->name, sizeof(wimax_dev->name),
- "i2400m-%s:%s", dev->bus->name, dev_name(dev));
-
- result = i2400m_bm_buf_alloc(i2400m);
- if (result < 0) {
- dev_err(dev, "cannot allocate bootmode scratch buffers\n");
- goto error_bm_buf_alloc;
- }
-
- if (i2400m->bus_setup) {
- result = i2400m->bus_setup(i2400m);
- if (result < 0) {
- dev_err(dev, "bus-specific setup failed: %d\n",
- result);
- goto error_bus_setup;
- }
- }
-
- result = i2400m_bootrom_init(i2400m, bm_flags);
- if (result < 0) {
- dev_err(dev, "read mac addr: bootrom init "
- "failed: %d\n", result);
- goto error_bootrom_init;
- }
- result = i2400m_read_mac_addr(i2400m);
- if (result < 0)
- goto error_read_mac_addr;
- eth_random_addr(i2400m->src_mac_addr);
-
- i2400m->pm_notifier.notifier_call = i2400m_pm_notifier;
- register_pm_notifier(&i2400m->pm_notifier);
-
- result = register_netdev(net_dev); /* Okey dokey, bring it up */
- if (result < 0) {
- dev_err(dev, "cannot register i2400m network device: %d\n",
- result);
- goto error_register_netdev;
- }
- netif_carrier_off(net_dev);
-
- i2400m->wimax_dev.op_msg_from_user = i2400m_op_msg_from_user;
- i2400m->wimax_dev.op_rfkill_sw_toggle = i2400m_op_rfkill_sw_toggle;
- i2400m->wimax_dev.op_reset = i2400m_op_reset;
-
- result = wimax_dev_add(&i2400m->wimax_dev, net_dev);
- if (result < 0)
- goto error_wimax_dev_add;
-
- /* Now setup all that requires a registered net and wimax device. */
- result = sysfs_create_group(&net_dev->dev.kobj, &i2400m_dev_attr_group);
- if (result < 0) {
- dev_err(dev, "cannot setup i2400m's sysfs: %d\n", result);
- goto error_sysfs_setup;
- }
-
- i2400m_debugfs_add(i2400m);
-
- result = i2400m_dev_start(i2400m, bm_flags);
- if (result < 0)
- goto error_dev_start;
- d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
- return result;
-
-error_dev_start:
- i2400m_debugfs_rm(i2400m);
- sysfs_remove_group(&i2400m->wimax_dev.net_dev->dev.kobj,
- &i2400m_dev_attr_group);
-error_sysfs_setup:
- wimax_dev_rm(&i2400m->wimax_dev);
-error_wimax_dev_add:
- unregister_netdev(net_dev);
-error_register_netdev:
- unregister_pm_notifier(&i2400m->pm_notifier);
-error_read_mac_addr:
-error_bootrom_init:
- if (i2400m->bus_release)
- i2400m->bus_release(i2400m);
-error_bus_setup:
- i2400m_bm_buf_free(i2400m);
-error_bm_buf_alloc:
- d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
- return result;
-}
-EXPORT_SYMBOL_GPL(i2400m_setup);
-
-
-/**
- * i2400m_release - release the bus-generic driver resources
- *
- * Sends a disconnect message and undoes any setup done by i2400m_setup()
- */
-void i2400m_release(struct i2400m *i2400m)
-{
- struct device *dev = i2400m_dev(i2400m);
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
- netif_stop_queue(i2400m->wimax_dev.net_dev);
-
- i2400m_dev_stop(i2400m);
-
- cancel_work_sync(&i2400m->reset_ws);
- cancel_work_sync(&i2400m->recovery_ws);
-
- i2400m_debugfs_rm(i2400m);
- sysfs_remove_group(&i2400m->wimax_dev.net_dev->dev.kobj,
- &i2400m_dev_attr_group);
- wimax_dev_rm(&i2400m->wimax_dev);
- unregister_netdev(i2400m->wimax_dev.net_dev);
- unregister_pm_notifier(&i2400m->pm_notifier);
- if (i2400m->bus_release)
- i2400m->bus_release(i2400m);
- i2400m_bm_buf_free(i2400m);
- d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
-EXPORT_SYMBOL_GPL(i2400m_release);
-
-
-/*
- * Debug levels control; see debug.h
- */
-struct d_level D_LEVEL[] = {
- D_SUBMODULE_DEFINE(control),
- D_SUBMODULE_DEFINE(driver),
- D_SUBMODULE_DEFINE(debugfs),
- D_SUBMODULE_DEFINE(fw),
- D_SUBMODULE_DEFINE(netdev),
- D_SUBMODULE_DEFINE(rfkill),
- D_SUBMODULE_DEFINE(rx),
- D_SUBMODULE_DEFINE(sysfs),
- D_SUBMODULE_DEFINE(tx),
-};
-size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
-
-
-static
-int __init i2400m_driver_init(void)
-{
- d_parse_params(D_LEVEL, D_LEVEL_SIZE, i2400m_debug_params,
- "i2400m.debug");
- return i2400m_barker_db_init(i2400m_barkers_params);
-}
-module_init(i2400m_driver_init);
-
-static
-void __exit i2400m_driver_exit(void)
-{
- i2400m_barker_db_exit();
-}
-module_exit(i2400m_driver_exit);
-
-MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
-MODULE_DESCRIPTION("Intel 2400M WiMAX networking bus-generic driver");
-MODULE_LICENSE("GPL");
+++ /dev/null
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Firmware uploader
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * - Initial implementation
- *
- *
- * THE PROCEDURE
- *
- * The 2400m and derived devices work in two modes: boot-mode or
- * normal mode. In boot mode we can execute only a handful of commands
- * targeted at uploading the firmware and launching it.
- *
- * The 2400m enters boot mode when it is first connected to the
- * system, when it crashes and when you ask it to reboot. There are
- * two submodes of the boot mode: signed and non-signed. Signed takes
- * firmwares signed with a certain private key, non-signed takes any
- * firmware. Normal hardware takes only signed firmware.
- *
- * On boot mode, in USB, we write to the device using the bulk out
- * endpoint and read from it in the notification endpoint.
- *
- * Upon entrance to boot mode, the device sends (preceded with a few
- * zero length packets (ZLPs) on the notification endpoint in USB) a
- * reboot barker (4 le32 words with the same value). We ack it by
- * sending the same barker to the device. The device acks with a
- * reboot ack barker (4 le32 words with value I2400M_ACK_BARKER) and
- * then is fully booted. At this point we can upload the firmware.
- *
- * Note that different iterations of the device and EEPROM
- * configurations will send different [re]boot barkers; these are
- * collected in i2400m_barker_db along with the firmware
- * characteristics they require.
- *
- * This process is accomplished by the i2400m_bootrom_init()
- * function. All the device interaction happens through the
- * i2400m_bm_cmd() [boot mode command]. Special return values will
- * indicate if the device did reset during the process.
- *
- * After this, we read the MAC address and then (if needed)
- * reinitialize the device. We need to read it ahead of time because
- * in the future, we might not upload the firmware until userspace
- * 'ifconfig up's the device.
- *
- * We can then upload the firmware file. The file is composed of a BCF
- * header (basic data, keys and signatures) and a list of write
- * commands and payloads. Optionally more BCF headers might follow the
- * main payload. We first upload the header [i2400m_dnload_init()] and
- * then pass the commands and payloads verbatim to the i2400m_bm_cmd()
- * function [i2400m_dnload_bcf()]. Then we tell the device to jump to
- * the new firmware [i2400m_dnload_finalize()].
- *
- * Once firmware is uploaded, we are good to go :)
- *
- * When we don't know in which mode we are, we first try by sending a
- * warm reset request that will take us to boot-mode. If we time out
- * waiting for a reboot barker, that means maybe we are already in
- * boot mode, so we send a reboot barker.
- *
- * COMMAND EXECUTION
- *
- * This code (and process) is single threaded; for executing commands,
- * we post a URB to the notification endpoint, post the command, wait
- * for data on the notification buffer. We don't need to worry about
- * others as we know we are the only ones in there.
- *
- * BACKEND IMPLEMENTATION
- *
- * This code is bus-generic; the bus-specific driver provides back end
- * implementations to send a boot mode command to the device and to
- * read an acknolwedgement from it (or an asynchronous notification)
- * from it.
- *
- * FIRMWARE LOADING
- *
- * Note that in some cases, we can't just load a firmware file (for
- * example, when resuming). For that, we might cache the firmware
- * file. Thus, when doing the bootstrap, if there is a cache firmware
- * file, it is used; if not, loading from disk is attempted.
- *
- * ROADMAP
- *
- * i2400m_barker_db_init Called by i2400m_driver_init()
- * i2400m_barker_db_add
- *
- * i2400m_barker_db_exit Called by i2400m_driver_exit()
- *
- * i2400m_dev_bootstrap Called by __i2400m_dev_start()
- * request_firmware
- * i2400m_fw_bootstrap
- * i2400m_fw_check
- * i2400m_fw_hdr_check
- * i2400m_fw_dnload
- * release_firmware
- *
- * i2400m_fw_dnload
- * i2400m_bootrom_init
- * i2400m_bm_cmd
- * i2400m_reset
- * i2400m_dnload_init
- * i2400m_dnload_init_signed
- * i2400m_dnload_init_nonsigned
- * i2400m_download_chunk
- * i2400m_bm_cmd
- * i2400m_dnload_bcf
- * i2400m_bm_cmd
- * i2400m_dnload_finalize
- * i2400m_bm_cmd
- *
- * i2400m_bm_cmd
- * i2400m->bus_bm_cmd_send()
- * i2400m->bus_bm_wait_for_ack
- * __i2400m_bm_ack_verify
- * i2400m_is_boot_barker
- *
- * i2400m_bm_cmd_prepare Used by bus-drivers to prep
- * commands before sending
- *
- * i2400m_pm_notifier Called on Power Management events
- * i2400m_fw_cache
- * i2400m_fw_uncache
- */
-#include <linux/firmware.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/usb.h>
-#include <linux/export.h>
-#include "i2400m.h"
-
-
-#define D_SUBMODULE fw
-#include "debug-levels.h"
-
-
-static const __le32 i2400m_ACK_BARKER[4] = {
- cpu_to_le32(I2400M_ACK_BARKER),
- cpu_to_le32(I2400M_ACK_BARKER),
- cpu_to_le32(I2400M_ACK_BARKER),
- cpu_to_le32(I2400M_ACK_BARKER)
-};
-
-
-/**
- * Prepare a boot-mode command for delivery
- *
- * @cmd: pointer to bootrom header to prepare
- *
- * Computes checksum if so needed. After calling this function, DO NOT
- * modify the command or header as the checksum won't work anymore.
- *
- * We do it from here because some times we cannot do it in the
- * original context the command was sent (it is a const), so when we
- * copy it to our staging buffer, we add the checksum there.
- */
-void i2400m_bm_cmd_prepare(struct i2400m_bootrom_header *cmd)
-{
- if (i2400m_brh_get_use_checksum(cmd)) {
- int i;
- u32 checksum = 0;
- const u32 *checksum_ptr = (void *) cmd->payload;
- for (i = 0; i < cmd->data_size / 4; i++)
- checksum += cpu_to_le32(*checksum_ptr++);
- checksum += cmd->command + cmd->target_addr + cmd->data_size;
- cmd->block_checksum = cpu_to_le32(checksum);
- }
-}
-EXPORT_SYMBOL_GPL(i2400m_bm_cmd_prepare);
-
-
-/*
- * Database of known barkers.
- *
- * A barker is what the device sends indicating he is ready to be
- * bootloaded. Different versions of the device will send different
- * barkers. Depending on the barker, it might mean the device wants
- * some kind of firmware or the other.
- */
-static struct i2400m_barker_db {
- __le32 data[4];
-} *i2400m_barker_db;
-static size_t i2400m_barker_db_used, i2400m_barker_db_size;
-
-
-static
-int i2400m_zrealloc_2x(void **ptr, size_t *_count, size_t el_size,
- gfp_t gfp_flags)
-{
- size_t old_count = *_count,
- new_count = old_count ? 2 * old_count : 2,
- old_size = el_size * old_count,
- new_size = el_size * new_count;
- void *nptr = krealloc(*ptr, new_size, gfp_flags);
- if (nptr) {
- /* zero the other half or the whole thing if old_count
- * was zero */
- if (old_size == 0)
- memset(nptr, 0, new_size);
- else
- memset(nptr + old_size, 0, old_size);
- *_count = new_count;
- *ptr = nptr;
- return 0;
- } else
- return -ENOMEM;
-}
-
-
-/*
- * Add a barker to the database
- *
- * This cannot used outside of this module and only at at module_init
- * time. This is to avoid the need to do locking.
- */
-static
-int i2400m_barker_db_add(u32 barker_id)
-{
- int result;
-
- struct i2400m_barker_db *barker;
- if (i2400m_barker_db_used >= i2400m_barker_db_size) {
- result = i2400m_zrealloc_2x(
- (void **) &i2400m_barker_db, &i2400m_barker_db_size,
- sizeof(i2400m_barker_db[0]), GFP_KERNEL);
- if (result < 0)
- return result;
- }
- barker = i2400m_barker_db + i2400m_barker_db_used++;
- barker->data[0] = le32_to_cpu(barker_id);
- barker->data[1] = le32_to_cpu(barker_id);
- barker->data[2] = le32_to_cpu(barker_id);
- barker->data[3] = le32_to_cpu(barker_id);
- return 0;
-}
-
-
-void i2400m_barker_db_exit(void)
-{
- kfree(i2400m_barker_db);
- i2400m_barker_db = NULL;
- i2400m_barker_db_size = 0;
- i2400m_barker_db_used = 0;
-}
-
-
-/*
- * Helper function to add all the known stable barkers to the barker
- * database.
- */
-static
-int i2400m_barker_db_known_barkers(void)
-{
- int result;
-
- result = i2400m_barker_db_add(I2400M_NBOOT_BARKER);
- if (result < 0)
- goto error_add;
- result = i2400m_barker_db_add(I2400M_SBOOT_BARKER);
- if (result < 0)
- goto error_add;
- result = i2400m_barker_db_add(I2400M_SBOOT_BARKER_6050);
- if (result < 0)
- goto error_add;
-error_add:
- return result;
-}
-
-
-/*
- * Initialize the barker database
- *
- * This can only be used from the module_init function for this
- * module; this is to avoid the need to do locking.
- *
- * @options: command line argument with extra barkers to
- * recognize. This is a comma-separated list of 32-bit hex
- * numbers. They are appended to the existing list. Setting 0
- * cleans the existing list and starts a new one.
- */
-int i2400m_barker_db_init(const char *_options)
-{
- int result;
- char *options = NULL, *options_orig, *token;
-
- i2400m_barker_db = NULL;
- i2400m_barker_db_size = 0;
- i2400m_barker_db_used = 0;
-
- result = i2400m_barker_db_known_barkers();
- if (result < 0)
- goto error_add;
- /* parse command line options from i2400m.barkers */
- if (_options != NULL) {
- unsigned barker;
-
- options_orig = kstrdup(_options, GFP_KERNEL);
- if (options_orig == NULL) {
- result = -ENOMEM;
- goto error_parse;
- }
- options = options_orig;
-
- while ((token = strsep(&options, ",")) != NULL) {
- if (*token == '\0') /* eat joint commas */
- continue;
- if (sscanf(token, "%x", &barker) != 1
- || barker > 0xffffffff) {
- printk(KERN_ERR "%s: can't recognize "
- "i2400m.barkers value '%s' as "
- "a 32-bit number\n",
- __func__, token);
- result = -EINVAL;
- goto error_parse;
- }
- if (barker == 0) {
- /* clean list and start new */
- i2400m_barker_db_exit();
- continue;
- }
- result = i2400m_barker_db_add(barker);
- if (result < 0)
- goto error_parse_add;
- }
- kfree(options_orig);
- }
- return 0;
-
-error_parse_add:
-error_parse:
- kfree(options_orig);
-error_add:
- kfree(i2400m_barker_db);
- return result;
-}
-
-
-/*
- * Recognize a boot barker
- *
- * @buf: buffer where the boot barker.
- * @buf_size: size of the buffer (has to be 16 bytes). It is passed
- * here so the function can check it for the caller.
- *
- * Note that as a side effect, upon identifying the obtained boot
- * barker, this function will set i2400m->barker to point to the right
- * barker database entry. Subsequent calls to the function will result
- * in verifying that the same type of boot barker is returned when the
- * device [re]boots (as long as the same device instance is used).
- *
- * Return: 0 if @buf matches a known boot barker. -ENOENT if the
- * buffer in @buf doesn't match any boot barker in the database or
- * -EILSEQ if the buffer doesn't have the right size.
- */
-int i2400m_is_boot_barker(struct i2400m *i2400m,
- const void *buf, size_t buf_size)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct i2400m_barker_db *barker;
- int i;
-
- result = -ENOENT;
- if (buf_size != sizeof(i2400m_barker_db[i].data))
- return result;
-
- /* Short circuit if we have already discovered the barker
- * associated with the device. */
- if (i2400m->barker &&
- !memcmp(buf, i2400m->barker, sizeof(i2400m->barker->data)))
- return 0;
-
- for (i = 0; i < i2400m_barker_db_used; i++) {
- barker = &i2400m_barker_db[i];
- BUILD_BUG_ON(sizeof(barker->data) != 16);
- if (memcmp(buf, barker->data, sizeof(barker->data)))
- continue;
-
- if (i2400m->barker == NULL) {
- i2400m->barker = barker;
- d_printf(1, dev, "boot barker set to #%u/%08x\n",
- i, le32_to_cpu(barker->data[0]));
- if (barker->data[0] == le32_to_cpu(I2400M_NBOOT_BARKER))
- i2400m->sboot = 0;
- else
- i2400m->sboot = 1;
- } else if (i2400m->barker != barker) {
- dev_err(dev, "HW inconsistency: device "
- "reports a different boot barker "
- "than set (from %08x to %08x)\n",
- le32_to_cpu(i2400m->barker->data[0]),
- le32_to_cpu(barker->data[0]));
- result = -EIO;
- } else
- d_printf(2, dev, "boot barker confirmed #%u/%08x\n",
- i, le32_to_cpu(barker->data[0]));
- result = 0;
- break;
- }
- return result;
-}
-EXPORT_SYMBOL_GPL(i2400m_is_boot_barker);
-
-
-/*
- * Verify the ack data received
- *
- * Given a reply to a boot mode command, chew it and verify everything
- * is ok.
- *
- * @opcode: opcode which generated this ack. For error messages.
- * @ack: pointer to ack data we received
- * @ack_size: size of that data buffer
- * @flags: I2400M_BM_CMD_* flags we called the command with.
- *
- * Way too long function -- maybe it should be further split
- */
-static
-ssize_t __i2400m_bm_ack_verify(struct i2400m *i2400m, int opcode,
- struct i2400m_bootrom_header *ack,
- size_t ack_size, int flags)
-{
- ssize_t result = -ENOMEM;
- struct device *dev = i2400m_dev(i2400m);
-
- d_fnstart(8, dev, "(i2400m %p opcode %d ack %p size %zu)\n",
- i2400m, opcode, ack, ack_size);
- if (ack_size < sizeof(*ack)) {
- result = -EIO;
- dev_err(dev, "boot-mode cmd %d: HW BUG? notification didn't "
- "return enough data (%zu bytes vs %zu expected)\n",
- opcode, ack_size, sizeof(*ack));
- goto error_ack_short;
- }
- result = i2400m_is_boot_barker(i2400m, ack, ack_size);
- if (result >= 0) {
- result = -ERESTARTSYS;
- d_printf(6, dev, "boot-mode cmd %d: HW boot barker\n", opcode);
- goto error_reboot;
- }
- if (ack_size == sizeof(i2400m_ACK_BARKER)
- && memcmp(ack, i2400m_ACK_BARKER, sizeof(*ack)) == 0) {
- result = -EISCONN;
- d_printf(3, dev, "boot-mode cmd %d: HW reboot ack barker\n",
- opcode);
- goto error_reboot_ack;
- }
- result = 0;
- if (flags & I2400M_BM_CMD_RAW)
- goto out_raw;
- ack->data_size = le32_to_cpu(ack->data_size);
- ack->target_addr = le32_to_cpu(ack->target_addr);
- ack->block_checksum = le32_to_cpu(ack->block_checksum);
- d_printf(5, dev, "boot-mode cmd %d: notification for opcode %u "
- "response %u csum %u rr %u da %u\n",
- opcode, i2400m_brh_get_opcode(ack),
- i2400m_brh_get_response(ack),
- i2400m_brh_get_use_checksum(ack),
- i2400m_brh_get_response_required(ack),
- i2400m_brh_get_direct_access(ack));
- result = -EIO;
- if (i2400m_brh_get_signature(ack) != 0xcbbc) {
- dev_err(dev, "boot-mode cmd %d: HW BUG? wrong signature "
- "0x%04x\n", opcode, i2400m_brh_get_signature(ack));
- goto error_ack_signature;
- }
- if (opcode != -1 && opcode != i2400m_brh_get_opcode(ack)) {
- dev_err(dev, "boot-mode cmd %d: HW BUG? "
- "received response for opcode %u, expected %u\n",
- opcode, i2400m_brh_get_opcode(ack), opcode);
- goto error_ack_opcode;
- }
- if (i2400m_brh_get_response(ack) != 0) { /* failed? */
- dev_err(dev, "boot-mode cmd %d: error; hw response %u\n",
- opcode, i2400m_brh_get_response(ack));
- goto error_ack_failed;
- }
- if (ack_size < ack->data_size + sizeof(*ack)) {
- dev_err(dev, "boot-mode cmd %d: SW BUG "
- "driver provided only %zu bytes for %zu bytes "
- "of data\n", opcode, ack_size,
- (size_t) le32_to_cpu(ack->data_size) + sizeof(*ack));
- goto error_ack_short_buffer;
- }
- result = ack_size;
- /* Don't you love this stack of empty targets? Well, I don't
- * either, but it helps track exactly who comes in here and
- * why :) */
-error_ack_short_buffer:
-error_ack_failed:
-error_ack_opcode:
-error_ack_signature:
-out_raw:
-error_reboot_ack:
-error_reboot:
-error_ack_short:
- d_fnend(8, dev, "(i2400m %p opcode %d ack %p size %zu) = %d\n",
- i2400m, opcode, ack, ack_size, (int) result);
- return result;
-}
-
-
-/**
- * i2400m_bm_cmd - Execute a boot mode command
- *
- * @cmd: buffer containing the command data (pointing at the header).
- * This data can be ANYWHERE (for USB, we will copy it to an
- * specific buffer). Make sure everything is in proper little
- * endian.
- *
- * A raw buffer can be also sent, just cast it and set flags to
- * I2400M_BM_CMD_RAW.
- *
- * This function will generate a checksum for you if the
- * checksum bit in the command is set (unless I2400M_BM_CMD_RAW
- * is set).
- *
- * You can use the i2400m->bm_cmd_buf to stage your commands and
- * send them.
- *
- * If NULL, no command is sent (we just wait for an ack).
- *
- * @cmd_size: size of the command. Will be auto padded to the
- * bus-specific drivers padding requirements.
- *
- * @ack: buffer where to place the acknowledgement. If it is a regular
- * command response, all fields will be returned with the right,
- * native endianess.
- *
- * You *cannot* use i2400m->bm_ack_buf for this buffer.
- *
- * @ack_size: size of @ack, 16 aligned; you need to provide at least
- * sizeof(*ack) bytes and then enough to contain the return data
- * from the command
- *
- * @flags: see I2400M_BM_CMD_* above.
- *
- * @returns: bytes received by the notification; if < 0, an errno code
- * denoting an error or:
- *
- * -ERESTARTSYS The device has rebooted
- *
- * Executes a boot-mode command and waits for a response, doing basic
- * validation on it; if a zero length response is received, it retries
- * waiting for a response until a non-zero one is received (timing out
- * after %I2400M_BOOT_RETRIES retries).
- */
-static
-ssize_t i2400m_bm_cmd(struct i2400m *i2400m,
- const struct i2400m_bootrom_header *cmd, size_t cmd_size,
- struct i2400m_bootrom_header *ack, size_t ack_size,
- int flags)
-{
- ssize_t result = -ENOMEM, rx_bytes;
- struct device *dev = i2400m_dev(i2400m);
- int opcode = cmd == NULL ? -1 : i2400m_brh_get_opcode(cmd);
-
- d_fnstart(6, dev, "(i2400m %p cmd %p size %zu ack %p size %zu)\n",
- i2400m, cmd, cmd_size, ack, ack_size);
- BUG_ON(ack_size < sizeof(*ack));
- BUG_ON(i2400m->boot_mode == 0);
-
- if (cmd != NULL) { /* send the command */
- result = i2400m->bus_bm_cmd_send(i2400m, cmd, cmd_size, flags);
- if (result < 0)
- goto error_cmd_send;
- if ((flags & I2400M_BM_CMD_RAW) == 0)
- d_printf(5, dev,
- "boot-mode cmd %d csum %u rr %u da %u: "
- "addr 0x%04x size %u block csum 0x%04x\n",
- opcode, i2400m_brh_get_use_checksum(cmd),
- i2400m_brh_get_response_required(cmd),
- i2400m_brh_get_direct_access(cmd),
- cmd->target_addr, cmd->data_size,
- cmd->block_checksum);
- }
- result = i2400m->bus_bm_wait_for_ack(i2400m, ack, ack_size);
- if (result < 0) {
- dev_err(dev, "boot-mode cmd %d: error waiting for an ack: %d\n",
- opcode, (int) result); /* bah, %zd doesn't work */
- goto error_wait_for_ack;
- }
- rx_bytes = result;
- /* verify the ack and read more if necessary [result is the
- * final amount of bytes we get in the ack] */
- result = __i2400m_bm_ack_verify(i2400m, opcode, ack, ack_size, flags);
- if (result < 0)
- goto error_bad_ack;
- /* Don't you love this stack of empty targets? Well, I don't
- * either, but it helps track exactly who comes in here and
- * why :) */
- result = rx_bytes;
-error_bad_ack:
-error_wait_for_ack:
-error_cmd_send:
- d_fnend(6, dev, "(i2400m %p cmd %p size %zu ack %p size %zu) = %d\n",
- i2400m, cmd, cmd_size, ack, ack_size, (int) result);
- return result;
-}
-
-
-/**
- * i2400m_download_chunk - write a single chunk of data to the device's memory
- *
- * @i2400m: device descriptor
- * @buf: the buffer to write
- * @buf_len: length of the buffer to write
- * @addr: address in the device memory space
- * @direct: bootrom write mode
- * @do_csum: should a checksum validation be performed
- */
-static int i2400m_download_chunk(struct i2400m *i2400m, const void *chunk,
- size_t __chunk_len, unsigned long addr,
- unsigned int direct, unsigned int do_csum)
-{
- int ret;
- size_t chunk_len = ALIGN(__chunk_len, I2400M_PL_ALIGN);
- struct device *dev = i2400m_dev(i2400m);
- struct {
- struct i2400m_bootrom_header cmd;
- u8 cmd_payload[];
- } __packed *buf;
- struct i2400m_bootrom_header ack;
-
- d_fnstart(5, dev, "(i2400m %p chunk %p __chunk_len %zu addr 0x%08lx "
- "direct %u do_csum %u)\n", i2400m, chunk, __chunk_len,
- addr, direct, do_csum);
- buf = i2400m->bm_cmd_buf;
- memcpy(buf->cmd_payload, chunk, __chunk_len);
- memset(buf->cmd_payload + __chunk_len, 0xad, chunk_len - __chunk_len);
-
- buf->cmd.command = i2400m_brh_command(I2400M_BRH_WRITE,
- __chunk_len & 0x3 ? 0 : do_csum,
- __chunk_len & 0xf ? 0 : direct);
- buf->cmd.target_addr = cpu_to_le32(addr);
- buf->cmd.data_size = cpu_to_le32(__chunk_len);
- ret = i2400m_bm_cmd(i2400m, &buf->cmd, sizeof(buf->cmd) + chunk_len,
- &ack, sizeof(ack), 0);
- if (ret >= 0)
- ret = 0;
- d_fnend(5, dev, "(i2400m %p chunk %p __chunk_len %zu addr 0x%08lx "
- "direct %u do_csum %u) = %d\n", i2400m, chunk, __chunk_len,
- addr, direct, do_csum, ret);
- return ret;
-}
-
-
-/*
- * Download a BCF file's sections to the device
- *
- * @i2400m: device descriptor
- * @bcf: pointer to firmware data (first header followed by the
- * payloads). Assumed verified and consistent.
- * @bcf_len: length (in bytes) of the @bcf buffer.
- *
- * Returns: < 0 errno code on error or the offset to the jump instruction.
- *
- * Given a BCF file, downloads each section (a command and a payload)
- * to the device's address space. Actually, it just executes each
- * command i the BCF file.
- *
- * The section size has to be aligned to 4 bytes AND the padding has
- * to be taken from the firmware file, as the signature takes it into
- * account.
- */
-static
-ssize_t i2400m_dnload_bcf(struct i2400m *i2400m,
- const struct i2400m_bcf_hdr *bcf, size_t bcf_len)
-{
- ssize_t ret;
- struct device *dev = i2400m_dev(i2400m);
- size_t offset, /* iterator offset */
- data_size, /* Size of the data payload */
- section_size, /* Size of the whole section (cmd + payload) */
- section = 1;
- const struct i2400m_bootrom_header *bh;
- struct i2400m_bootrom_header ack;
-
- d_fnstart(3, dev, "(i2400m %p bcf %p bcf_len %zu)\n",
- i2400m, bcf, bcf_len);
- /* Iterate over the command blocks in the BCF file that start
- * after the header */
- offset = le32_to_cpu(bcf->header_len) * sizeof(u32);
- while (1) { /* start sending the file */
- bh = (void *) bcf + offset;
- data_size = le32_to_cpu(bh->data_size);
- section_size = ALIGN(sizeof(*bh) + data_size, 4);
- d_printf(7, dev,
- "downloading section #%zu (@%zu %zu B) to 0x%08x\n",
- section, offset, sizeof(*bh) + data_size,
- le32_to_cpu(bh->target_addr));
- /*
- * We look for JUMP cmd from the bootmode header,
- * either I2400M_BRH_SIGNED_JUMP for secure boot
- * or I2400M_BRH_JUMP for unsecure boot, the last chunk
- * should be the bootmode header with JUMP cmd.
- */
- if (i2400m_brh_get_opcode(bh) == I2400M_BRH_SIGNED_JUMP ||
- i2400m_brh_get_opcode(bh) == I2400M_BRH_JUMP) {
- d_printf(5, dev, "jump found @%zu\n", offset);
- break;
- }
- if (offset + section_size > bcf_len) {
- dev_err(dev, "fw %s: bad section #%zu, "
- "end (@%zu) beyond EOF (@%zu)\n",
- i2400m->fw_name, section,
- offset + section_size, bcf_len);
- ret = -EINVAL;
- goto error_section_beyond_eof;
- }
- __i2400m_msleep(20);
- ret = i2400m_bm_cmd(i2400m, bh, section_size,
- &ack, sizeof(ack), I2400M_BM_CMD_RAW);
- if (ret < 0) {
- dev_err(dev, "fw %s: section #%zu (@%zu %zu B) "
- "failed %d\n", i2400m->fw_name, section,
- offset, sizeof(*bh) + data_size, (int) ret);
- goto error_send;
- }
- offset += section_size;
- section++;
- }
- ret = offset;
-error_section_beyond_eof:
-error_send:
- d_fnend(3, dev, "(i2400m %p bcf %p bcf_len %zu) = %d\n",
- i2400m, bcf, bcf_len, (int) ret);
- return ret;
-}
-
-
-/*
- * Indicate if the device emitted a reboot barker that indicates
- * "signed boot"
- */
-static
-unsigned i2400m_boot_is_signed(struct i2400m *i2400m)
-{
- return likely(i2400m->sboot);
-}
-
-
-/*
- * Do the final steps of uploading firmware
- *
- * @bcf_hdr: BCF header we are actually using
- * @bcf: pointer to the firmware image (which matches the first header
- * that is followed by the actual payloads).
- * @offset: [byte] offset into @bcf for the command we need to send.
- *
- * Depending on the boot mode (signed vs non-signed), different
- * actions need to be taken.
- */
-static
-int i2400m_dnload_finalize(struct i2400m *i2400m,
- const struct i2400m_bcf_hdr *bcf_hdr,
- const struct i2400m_bcf_hdr *bcf, size_t offset)
-{
- int ret = 0;
- struct device *dev = i2400m_dev(i2400m);
- struct i2400m_bootrom_header *cmd, ack;
- struct {
- struct i2400m_bootrom_header cmd;
- u8 cmd_pl[0];
- } __packed *cmd_buf;
- size_t signature_block_offset, signature_block_size;
-
- d_fnstart(3, dev, "offset %zu\n", offset);
- cmd = (void *) bcf + offset;
- if (i2400m_boot_is_signed(i2400m) == 0) {
- struct i2400m_bootrom_header jump_ack;
- d_printf(1, dev, "unsecure boot, jumping to 0x%08x\n",
- le32_to_cpu(cmd->target_addr));
- cmd_buf = i2400m->bm_cmd_buf;
- memcpy(&cmd_buf->cmd, cmd, sizeof(*cmd));
- cmd = &cmd_buf->cmd;
- /* now cmd points to the actual bootrom_header in cmd_buf */
- i2400m_brh_set_opcode(cmd, I2400M_BRH_JUMP);
- cmd->data_size = 0;
- ret = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
- &jump_ack, sizeof(jump_ack), 0);
- } else {
- d_printf(1, dev, "secure boot, jumping to 0x%08x\n",
- le32_to_cpu(cmd->target_addr));
- cmd_buf = i2400m->bm_cmd_buf;
- memcpy(&cmd_buf->cmd, cmd, sizeof(*cmd));
- signature_block_offset =
- sizeof(*bcf_hdr)
- + le32_to_cpu(bcf_hdr->key_size) * sizeof(u32)
- + le32_to_cpu(bcf_hdr->exponent_size) * sizeof(u32);
- signature_block_size =
- le32_to_cpu(bcf_hdr->modulus_size) * sizeof(u32);
- memcpy(cmd_buf->cmd_pl,
- (void *) bcf_hdr + signature_block_offset,
- signature_block_size);
- ret = i2400m_bm_cmd(i2400m, &cmd_buf->cmd,
- sizeof(cmd_buf->cmd) + signature_block_size,
- &ack, sizeof(ack), I2400M_BM_CMD_RAW);
- }
- d_fnend(3, dev, "returning %d\n", ret);
- return ret;
-}
-
-
-/**
- * i2400m_bootrom_init - Reboots a powered device into boot mode
- *
- * @i2400m: device descriptor
- * @flags:
- * I2400M_BRI_SOFT: a reboot barker has been seen
- * already, so don't wait for it.
- *
- * I2400M_BRI_NO_REBOOT: Don't send a reboot command, but wait
- * for a reboot barker notification. This is a one shot; if
- * the state machine needs to send a reboot command it will.
- *
- * Returns:
- *
- * < 0 errno code on error, 0 if ok.
- *
- * Description:
- *
- * Tries hard enough to put the device in boot-mode. There are two
- * main phases to this:
- *
- * a. (1) send a reboot command and (2) get a reboot barker
- *
- * b. (1) echo/ack the reboot sending the reboot barker back and (2)
- * getting an ack barker in return
- *
- * We want to skip (a) in some cases [soft]. The state machine is
- * horrible, but it is basically: on each phase, send what has to be
- * sent (if any), wait for the answer and act on the answer. We might
- * have to backtrack and retry, so we keep a max tries counter for
- * that.
- *
- * It sucks because we don't know ahead of time which is going to be
- * the reboot barker (the device might send different ones depending
- * on its EEPROM config) and once the device reboots and waits for the
- * echo/ack reboot barker being sent back, it doesn't understand
- * anything else. So we can be left at the point where we don't know
- * what to send to it -- cold reset and bus reset seem to have little
- * effect. So the function iterates (in this case) through all the
- * known barkers and tries them all until an ACK is
- * received. Otherwise, it gives up.
- *
- * If we get a timeout after sending a warm reset, we do it again.
- */
-int i2400m_bootrom_init(struct i2400m *i2400m, enum i2400m_bri flags)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct i2400m_bootrom_header *cmd;
- struct i2400m_bootrom_header ack;
- int count = i2400m->bus_bm_retries;
- int ack_timeout_cnt = 1;
- unsigned i;
-
- BUILD_BUG_ON(sizeof(*cmd) != sizeof(i2400m_barker_db[0].data));
- BUILD_BUG_ON(sizeof(ack) != sizeof(i2400m_ACK_BARKER));
-
- d_fnstart(4, dev, "(i2400m %p flags 0x%08x)\n", i2400m, flags);
- result = -ENOMEM;
- cmd = i2400m->bm_cmd_buf;
- if (flags & I2400M_BRI_SOFT)
- goto do_reboot_ack;
-do_reboot:
- ack_timeout_cnt = 1;
- if (--count < 0)
- goto error_timeout;
- d_printf(4, dev, "device reboot: reboot command [%d # left]\n",
- count);
- if ((flags & I2400M_BRI_NO_REBOOT) == 0)
- i2400m_reset(i2400m, I2400M_RT_WARM);
- result = i2400m_bm_cmd(i2400m, NULL, 0, &ack, sizeof(ack),
- I2400M_BM_CMD_RAW);
- flags &= ~I2400M_BRI_NO_REBOOT;
- switch (result) {
- case -ERESTARTSYS:
- /*
- * at this point, i2400m_bm_cmd(), through
- * __i2400m_bm_ack_process(), has updated
- * i2400m->barker and we are good to go.
- */
- d_printf(4, dev, "device reboot: got reboot barker\n");
- break;
- case -EISCONN: /* we don't know how it got here...but we follow it */
- d_printf(4, dev, "device reboot: got ack barker - whatever\n");
- goto do_reboot;
- case -ETIMEDOUT:
- /*
- * Device has timed out, we might be in boot mode
- * already and expecting an ack; if we don't know what
- * the barker is, we just send them all. Cold reset
- * and bus reset don't work. Beats me.
- */
- if (i2400m->barker != NULL) {
- dev_err(dev, "device boot: reboot barker timed out, "
- "trying (set) %08x echo/ack\n",
- le32_to_cpu(i2400m->barker->data[0]));
- goto do_reboot_ack;
- }
- for (i = 0; i < i2400m_barker_db_used; i++) {
- struct i2400m_barker_db *barker = &i2400m_barker_db[i];
- memcpy(cmd, barker->data, sizeof(barker->data));
- result = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
- &ack, sizeof(ack),
- I2400M_BM_CMD_RAW);
- if (result == -EISCONN) {
- dev_warn(dev, "device boot: got ack barker "
- "after sending echo/ack barker "
- "#%d/%08x; rebooting j.i.c.\n",
- i, le32_to_cpu(barker->data[0]));
- flags &= ~I2400M_BRI_NO_REBOOT;
- goto do_reboot;
- }
- }
- dev_err(dev, "device boot: tried all the echo/acks, could "
- "not get device to respond; giving up");
- result = -ESHUTDOWN;
- case -EPROTO:
- case -ESHUTDOWN: /* dev is gone */
- case -EINTR: /* user cancelled */
- goto error_dev_gone;
- default:
- dev_err(dev, "device reboot: error %d while waiting "
- "for reboot barker - rebooting\n", result);
- d_dump(1, dev, &ack, result);
- goto do_reboot;
- }
- /* At this point we ack back with 4 REBOOT barkers and expect
- * 4 ACK barkers. This is ugly, as we send a raw command --
- * hence the cast. _bm_cmd() will catch the reboot ack
- * notification and report it as -EISCONN. */
-do_reboot_ack:
- d_printf(4, dev, "device reboot ack: sending ack [%d # left]\n", count);
- memcpy(cmd, i2400m->barker->data, sizeof(i2400m->barker->data));
- result = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
- &ack, sizeof(ack), I2400M_BM_CMD_RAW);
- switch (result) {
- case -ERESTARTSYS:
- d_printf(4, dev, "reboot ack: got reboot barker - retrying\n");
- if (--count < 0)
- goto error_timeout;
- goto do_reboot_ack;
- case -EISCONN:
- d_printf(4, dev, "reboot ack: got ack barker - good\n");
- break;
- case -ETIMEDOUT: /* no response, maybe it is the other type? */
- if (ack_timeout_cnt-- < 0) {
- d_printf(4, dev, "reboot ack timedout: retrying\n");
- goto do_reboot_ack;
- } else {
- dev_err(dev, "reboot ack timedout too long: "
- "trying reboot\n");
- goto do_reboot;
- }
- break;
- case -EPROTO:
- case -ESHUTDOWN: /* dev is gone */
- goto error_dev_gone;
- default:
- dev_err(dev, "device reboot ack: error %d while waiting for "
- "reboot ack barker - rebooting\n", result);
- goto do_reboot;
- }
- d_printf(2, dev, "device reboot ack: got ack barker - boot done\n");
- result = 0;
-exit_timeout:
-error_dev_gone:
- d_fnend(4, dev, "(i2400m %p flags 0x%08x) = %d\n",
- i2400m, flags, result);
- return result;
-
-error_timeout:
- dev_err(dev, "Timed out waiting for reboot ack\n");
- result = -ETIMEDOUT;
- goto exit_timeout;
-}
-
-
-/*
- * Read the MAC addr
- *
- * The position this function reads is fixed in device memory and
- * always available, even without firmware.
- *
- * Note we specify we want to read only six bytes, but provide space
- * for 16, as we always get it rounded up.
- */
-int i2400m_read_mac_addr(struct i2400m *i2400m)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct net_device *net_dev = i2400m->wimax_dev.net_dev;
- struct i2400m_bootrom_header *cmd;
- struct {
- struct i2400m_bootrom_header ack;
- u8 ack_pl[16];
- } __packed ack_buf;
-
- d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
- cmd = i2400m->bm_cmd_buf;
- cmd->command = i2400m_brh_command(I2400M_BRH_READ, 0, 1);
- cmd->target_addr = cpu_to_le32(0x00203fe8);
- cmd->data_size = cpu_to_le32(6);
- result = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
- &ack_buf.ack, sizeof(ack_buf), 0);
- if (result < 0) {
- dev_err(dev, "BM: read mac addr failed: %d\n", result);
- goto error_read_mac;
- }
- d_printf(2, dev, "mac addr is %pM\n", ack_buf.ack_pl);
- if (i2400m->bus_bm_mac_addr_impaired == 1) {
- ack_buf.ack_pl[0] = 0x00;
- ack_buf.ack_pl[1] = 0x16;
- ack_buf.ack_pl[2] = 0xd3;
- get_random_bytes(&ack_buf.ack_pl[3], 3);
- dev_err(dev, "BM is MAC addr impaired, faking MAC addr to "
- "mac addr is %pM\n", ack_buf.ack_pl);
- result = 0;
- }
- net_dev->addr_len = ETH_ALEN;
- memcpy(net_dev->dev_addr, ack_buf.ack_pl, ETH_ALEN);
-error_read_mac:
- d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, result);
- return result;
-}
-
-
-/*
- * Initialize a non signed boot
- *
- * This implies sending some magic values to the device's memory. Note
- * we convert the values to little endian in the same array
- * declaration.
- */
-static
-int i2400m_dnload_init_nonsigned(struct i2400m *i2400m)
-{
- unsigned i = 0;
- int ret = 0;
- struct device *dev = i2400m_dev(i2400m);
- d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
- if (i2400m->bus_bm_pokes_table) {
- while (i2400m->bus_bm_pokes_table[i].address) {
- ret = i2400m_download_chunk(
- i2400m,
- &i2400m->bus_bm_pokes_table[i].data,
- sizeof(i2400m->bus_bm_pokes_table[i].data),
- i2400m->bus_bm_pokes_table[i].address, 1, 1);
- if (ret < 0)
- break;
- i++;
- }
- }
- d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, ret);
- return ret;
-}
-
-
-/*
- * Initialize the signed boot process
- *
- * @i2400m: device descriptor
- *
- * @bcf_hdr: pointer to the firmware header; assumes it is fully in
- * memory (it has gone through basic validation).
- *
- * Returns: 0 if ok, < 0 errno code on error, -ERESTARTSYS if the hw
- * rebooted.
- *
- * This writes the firmware BCF header to the device using the
- * HASH_PAYLOAD_ONLY command.
- */
-static
-int i2400m_dnload_init_signed(struct i2400m *i2400m,
- const struct i2400m_bcf_hdr *bcf_hdr)
-{
- int ret;
- struct device *dev = i2400m_dev(i2400m);
- struct {
- struct i2400m_bootrom_header cmd;
- struct i2400m_bcf_hdr cmd_pl;
- } __packed *cmd_buf;
- struct i2400m_bootrom_header ack;
-
- d_fnstart(5, dev, "(i2400m %p bcf_hdr %p)\n", i2400m, bcf_hdr);
- cmd_buf = i2400m->bm_cmd_buf;
- cmd_buf->cmd.command =
- i2400m_brh_command(I2400M_BRH_HASH_PAYLOAD_ONLY, 0, 0);
- cmd_buf->cmd.target_addr = 0;
- cmd_buf->cmd.data_size = cpu_to_le32(sizeof(cmd_buf->cmd_pl));
- memcpy(&cmd_buf->cmd_pl, bcf_hdr, sizeof(*bcf_hdr));
- ret = i2400m_bm_cmd(i2400m, &cmd_buf->cmd, sizeof(*cmd_buf),
- &ack, sizeof(ack), 0);
- if (ret >= 0)
- ret = 0;
- d_fnend(5, dev, "(i2400m %p bcf_hdr %p) = %d\n", i2400m, bcf_hdr, ret);
- return ret;
-}
-
-
-/*
- * Initialize the firmware download at the device size
- *
- * Multiplex to the one that matters based on the device's mode
- * (signed or non-signed).
- */
-static
-int i2400m_dnload_init(struct i2400m *i2400m,
- const struct i2400m_bcf_hdr *bcf_hdr)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
-
- if (i2400m_boot_is_signed(i2400m)) {
- d_printf(1, dev, "signed boot\n");
- result = i2400m_dnload_init_signed(i2400m, bcf_hdr);
- if (result == -ERESTARTSYS)
- return result;
- if (result < 0)
- dev_err(dev, "firmware %s: signed boot download "
- "initialization failed: %d\n",
- i2400m->fw_name, result);
- } else {
- /* non-signed boot process without pokes */
- d_printf(1, dev, "non-signed boot\n");
- result = i2400m_dnload_init_nonsigned(i2400m);
- if (result == -ERESTARTSYS)
- return result;
- if (result < 0)
- dev_err(dev, "firmware %s: non-signed download "
- "initialization failed: %d\n",
- i2400m->fw_name, result);
- }
- return result;
-}
-
-
-/*
- * Run consistency tests on the firmware file and load up headers
- *
- * Check for the firmware being made for the i2400m device,
- * etc...These checks are mostly informative, as the device will make
- * them too; but the driver's response is more informative on what
- * went wrong.
- *
- * This will also look at all the headers present on the firmware
- * file, and update i2400m->fw_bcf_hdr to point to them.
- */
-static
-int i2400m_fw_hdr_check(struct i2400m *i2400m,
- const struct i2400m_bcf_hdr *bcf_hdr,
- size_t index, size_t offset)
-{
- struct device *dev = i2400m_dev(i2400m);
-
- unsigned module_type, header_len, major_version, minor_version,
- module_id, module_vendor, date, size;
-
- module_type = le32_to_cpu(bcf_hdr->module_type);
- header_len = sizeof(u32) * le32_to_cpu(bcf_hdr->header_len);
- major_version = (le32_to_cpu(bcf_hdr->header_version) & 0xffff0000)
- >> 16;
- minor_version = le32_to_cpu(bcf_hdr->header_version) & 0x0000ffff;
- module_id = le32_to_cpu(bcf_hdr->module_id);
- module_vendor = le32_to_cpu(bcf_hdr->module_vendor);
- date = le32_to_cpu(bcf_hdr->date);
- size = sizeof(u32) * le32_to_cpu(bcf_hdr->size);
-
- d_printf(1, dev, "firmware %s #%zd@%08zx: BCF header "
- "type:vendor:id 0x%x:%x:%x v%u.%u (%u/%u B) built %08x\n",
- i2400m->fw_name, index, offset,
- module_type, module_vendor, module_id,
- major_version, minor_version, header_len, size, date);
-
- /* Hard errors */
- if (major_version != 1) {
- dev_err(dev, "firmware %s #%zd@%08zx: major header version "
- "v%u.%u not supported\n",
- i2400m->fw_name, index, offset,
- major_version, minor_version);
- return -EBADF;
- }
-
- if (module_type != 6) { /* built for the right hardware? */
- dev_err(dev, "firmware %s #%zd@%08zx: unexpected module "
- "type 0x%x; aborting\n",
- i2400m->fw_name, index, offset,
- module_type);
- return -EBADF;
- }
-
- if (module_vendor != 0x8086) {
- dev_err(dev, "firmware %s #%zd@%08zx: unexpected module "
- "vendor 0x%x; aborting\n",
- i2400m->fw_name, index, offset, module_vendor);
- return -EBADF;
- }
-
- if (date < 0x20080300)
- dev_warn(dev, "firmware %s #%zd@%08zx: build date %08x "
- "too old; unsupported\n",
- i2400m->fw_name, index, offset, date);
- return 0;
-}
-
-
-/*
- * Run consistency tests on the firmware file and load up headers
- *
- * Check for the firmware being made for the i2400m device,
- * etc...These checks are mostly informative, as the device will make
- * them too; but the driver's response is more informative on what
- * went wrong.
- *
- * This will also look at all the headers present on the firmware
- * file, and update i2400m->fw_hdrs to point to them.
- */
-static
-int i2400m_fw_check(struct i2400m *i2400m, const void *bcf, size_t bcf_size)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- size_t headers = 0;
- const struct i2400m_bcf_hdr *bcf_hdr;
- const void *itr, *next, *top;
- size_t slots = 0, used_slots = 0;
-
- for (itr = bcf, top = itr + bcf_size;
- itr < top;
- headers++, itr = next) {
- size_t leftover, offset, header_len, size;
-
- leftover = top - itr;
- offset = itr - bcf;
- if (leftover <= sizeof(*bcf_hdr)) {
- dev_err(dev, "firmware %s: %zu B left at @%zx, "
- "not enough for BCF header\n",
- i2400m->fw_name, leftover, offset);
- break;
- }
- bcf_hdr = itr;
- /* Only the first header is supposed to be followed by
- * payload */
- header_len = sizeof(u32) * le32_to_cpu(bcf_hdr->header_len);
- size = sizeof(u32) * le32_to_cpu(bcf_hdr->size);
- if (headers == 0)
- next = itr + size;
- else
- next = itr + header_len;
-
- result = i2400m_fw_hdr_check(i2400m, bcf_hdr, headers, offset);
- if (result < 0)
- continue;
- if (used_slots + 1 >= slots) {
- /* +1 -> we need to account for the one we'll
- * occupy and at least an extra one for
- * always being NULL */
- result = i2400m_zrealloc_2x(
- (void **) &i2400m->fw_hdrs, &slots,
- sizeof(i2400m->fw_hdrs[0]),
- GFP_KERNEL);
- if (result < 0)
- goto error_zrealloc;
- }
- i2400m->fw_hdrs[used_slots] = bcf_hdr;
- used_slots++;
- }
- if (headers == 0) {
- dev_err(dev, "firmware %s: no usable headers found\n",
- i2400m->fw_name);
- result = -EBADF;
- } else
- result = 0;
-error_zrealloc:
- return result;
-}
-
-
-/*
- * Match a barker to a BCF header module ID
- *
- * The device sends a barker which tells the firmware loader which
- * header in the BCF file has to be used. This does the matching.
- */
-static
-unsigned i2400m_bcf_hdr_match(struct i2400m *i2400m,
- const struct i2400m_bcf_hdr *bcf_hdr)
-{
- u32 barker = le32_to_cpu(i2400m->barker->data[0])
- & 0x7fffffff;
- u32 module_id = le32_to_cpu(bcf_hdr->module_id)
- & 0x7fffffff; /* high bit used for something else */
-
- /* special case for 5x50 */
- if (barker == I2400M_SBOOT_BARKER && module_id == 0)
- return 1;
- if (module_id == barker)
- return 1;
- return 0;
-}
-
-static
-const struct i2400m_bcf_hdr *i2400m_bcf_hdr_find(struct i2400m *i2400m)
-{
- struct device *dev = i2400m_dev(i2400m);
- const struct i2400m_bcf_hdr **bcf_itr, *bcf_hdr;
- unsigned i = 0;
- u32 barker = le32_to_cpu(i2400m->barker->data[0]);
-
- d_printf(2, dev, "finding BCF header for barker %08x\n", barker);
- if (barker == I2400M_NBOOT_BARKER) {
- bcf_hdr = i2400m->fw_hdrs[0];
- d_printf(1, dev, "using BCF header #%u/%08x for non-signed "
- "barker\n", 0, le32_to_cpu(bcf_hdr->module_id));
- return bcf_hdr;
- }
- for (bcf_itr = i2400m->fw_hdrs; *bcf_itr != NULL; bcf_itr++, i++) {
- bcf_hdr = *bcf_itr;
- if (i2400m_bcf_hdr_match(i2400m, bcf_hdr)) {
- d_printf(1, dev, "hit on BCF hdr #%u/%08x\n",
- i, le32_to_cpu(bcf_hdr->module_id));
- return bcf_hdr;
- } else
- d_printf(1, dev, "miss on BCF hdr #%u/%08x\n",
- i, le32_to_cpu(bcf_hdr->module_id));
- }
- dev_err(dev, "cannot find a matching BCF header for barker %08x\n",
- barker);
- return NULL;
-}
-
-
-/*
- * Download the firmware to the device
- *
- * @i2400m: device descriptor
- * @bcf: pointer to loaded (and minimally verified for consistency)
- * firmware
- * @bcf_size: size of the @bcf buffer (header plus payloads)
- *
- * The process for doing this is described in this file's header.
- *
- * Note we only reinitialize boot-mode if the flags say so. Some hw
- * iterations need it, some don't. In any case, if we loop, we always
- * need to reinitialize the boot room, hence the flags modification.
- */
-static
-int i2400m_fw_dnload(struct i2400m *i2400m, const struct i2400m_bcf_hdr *bcf,
- size_t fw_size, enum i2400m_bri flags)
-{
- int ret = 0;
- struct device *dev = i2400m_dev(i2400m);
- int count = i2400m->bus_bm_retries;
- const struct i2400m_bcf_hdr *bcf_hdr;
- size_t bcf_size;
-
- d_fnstart(5, dev, "(i2400m %p bcf %p fw size %zu)\n",
- i2400m, bcf, fw_size);
- i2400m->boot_mode = 1;
- wmb(); /* Make sure other readers see it */
-hw_reboot:
- if (count-- == 0) {
- ret = -ERESTARTSYS;
- dev_err(dev, "device rebooted too many times, aborting\n");
- goto error_too_many_reboots;
- }
- if (flags & I2400M_BRI_MAC_REINIT) {
- ret = i2400m_bootrom_init(i2400m, flags);
- if (ret < 0) {
- dev_err(dev, "bootrom init failed: %d\n", ret);
- goto error_bootrom_init;
- }
- }
- flags |= I2400M_BRI_MAC_REINIT;
-
- /*
- * Initialize the download, push the bytes to the device and
- * then jump to the new firmware. Note @ret is passed with the
- * offset of the jump instruction to _dnload_finalize()
- *
- * Note we need to use the BCF header in the firmware image
- * that matches the barker that the device sent when it
- * rebooted, so it has to be passed along.
- */
- ret = -EBADF;
- bcf_hdr = i2400m_bcf_hdr_find(i2400m);
- if (bcf_hdr == NULL)
- goto error_bcf_hdr_find;
-
- ret = i2400m_dnload_init(i2400m, bcf_hdr);
- if (ret == -ERESTARTSYS)
- goto error_dev_rebooted;
- if (ret < 0)
- goto error_dnload_init;
-
- /*
- * bcf_size refers to one header size plus the fw sections size
- * indicated by the header,ie. if there are other extended headers
- * at the tail, they are not counted
- */
- bcf_size = sizeof(u32) * le32_to_cpu(bcf_hdr->size);
- ret = i2400m_dnload_bcf(i2400m, bcf, bcf_size);
- if (ret == -ERESTARTSYS)
- goto error_dev_rebooted;
- if (ret < 0) {
- dev_err(dev, "fw %s: download failed: %d\n",
- i2400m->fw_name, ret);
- goto error_dnload_bcf;
- }
-
- ret = i2400m_dnload_finalize(i2400m, bcf_hdr, bcf, ret);
- if (ret == -ERESTARTSYS)
- goto error_dev_rebooted;
- if (ret < 0) {
- dev_err(dev, "fw %s: "
- "download finalization failed: %d\n",
- i2400m->fw_name, ret);
- goto error_dnload_finalize;
- }
-
- d_printf(2, dev, "fw %s successfully uploaded\n",
- i2400m->fw_name);
- i2400m->boot_mode = 0;
- wmb(); /* Make sure i2400m_msg_to_dev() sees boot_mode */
-error_dnload_finalize:
-error_dnload_bcf:
-error_dnload_init:
-error_bcf_hdr_find:
-error_bootrom_init:
-error_too_many_reboots:
- d_fnend(5, dev, "(i2400m %p bcf %p size %zu) = %d\n",
- i2400m, bcf, fw_size, ret);
- return ret;
-
-error_dev_rebooted:
- dev_err(dev, "device rebooted, %d tries left\n", count);
- /* we got the notification already, no need to wait for it again */
- flags |= I2400M_BRI_SOFT;
- goto hw_reboot;
-}
-
-static
-int i2400m_fw_bootstrap(struct i2400m *i2400m, const struct firmware *fw,
- enum i2400m_bri flags)
-{
- int ret;
- struct device *dev = i2400m_dev(i2400m);
- const struct i2400m_bcf_hdr *bcf; /* Firmware data */
-
- d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
- bcf = (void *) fw->data;
- ret = i2400m_fw_check(i2400m, bcf, fw->size);
- if (ret >= 0)
- ret = i2400m_fw_dnload(i2400m, bcf, fw->size, flags);
- if (ret < 0)
- dev_err(dev, "%s: cannot use: %d, skipping\n",
- i2400m->fw_name, ret);
- kfree(i2400m->fw_hdrs);
- i2400m->fw_hdrs = NULL;
- d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, ret);
- return ret;
-}
-
-
-/* Refcounted container for firmware data */
-struct i2400m_fw {
- struct kref kref;
- const struct firmware *fw;
-};
-
-
-static
-void i2400m_fw_destroy(struct kref *kref)
-{
- struct i2400m_fw *i2400m_fw =
- container_of(kref, struct i2400m_fw, kref);
- release_firmware(i2400m_fw->fw);
- kfree(i2400m_fw);
-}
-
-
-static
-struct i2400m_fw *i2400m_fw_get(struct i2400m_fw *i2400m_fw)
-{
- if (i2400m_fw != NULL && i2400m_fw != (void *) ~0)
- kref_get(&i2400m_fw->kref);
- return i2400m_fw;
-}
-
-
-static
-void i2400m_fw_put(struct i2400m_fw *i2400m_fw)
-{
- kref_put(&i2400m_fw->kref, i2400m_fw_destroy);
-}
-
-
-/**
- * i2400m_dev_bootstrap - Bring the device to a known state and upload firmware
- *
- * @i2400m: device descriptor
- *
- * Returns: >= 0 if ok, < 0 errno code on error.
- *
- * This sets up the firmware upload environment, loads the firmware
- * file from disk, verifies and then calls the firmware upload process
- * per se.
- *
- * Can be called either from probe, or after a warm reset. Can not be
- * called from within an interrupt. All the flow in this code is
- * single-threade; all I/Os are synchronous.
- */
-int i2400m_dev_bootstrap(struct i2400m *i2400m, enum i2400m_bri flags)
-{
- int ret, itr;
- struct device *dev = i2400m_dev(i2400m);
- struct i2400m_fw *i2400m_fw;
- const struct firmware *fw;
- const char *fw_name;
-
- d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
-
- ret = -ENODEV;
- spin_lock(&i2400m->rx_lock);
- i2400m_fw = i2400m_fw_get(i2400m->fw_cached);
- spin_unlock(&i2400m->rx_lock);
- if (i2400m_fw == (void *) ~0) {
- dev_err(dev, "can't load firmware now!");
- goto out;
- } else if (i2400m_fw != NULL) {
- dev_info(dev, "firmware %s: loading from cache\n",
- i2400m->fw_name);
- ret = i2400m_fw_bootstrap(i2400m, i2400m_fw->fw, flags);
- i2400m_fw_put(i2400m_fw);
- goto out;
- }
-
- /* Load firmware files to memory. */
- for (itr = 0, ret = -ENOENT; ; itr++) {
- fw_name = i2400m->bus_fw_names[itr];
- if (fw_name == NULL) {
- dev_err(dev, "Could not find a usable firmware image\n");
- break;
- }
- d_printf(1, dev, "trying firmware %s (%d)\n", fw_name, itr);
- ret = request_firmware(&fw, fw_name, dev);
- if (ret < 0) {
- dev_err(dev, "fw %s: cannot load file: %d\n",
- fw_name, ret);
- continue;
- }
- i2400m->fw_name = fw_name;
- ret = i2400m_fw_bootstrap(i2400m, fw, flags);
- release_firmware(fw);
- if (ret >= 0) /* firmware loaded successfully */
- break;
- i2400m->fw_name = NULL;
- }
-out:
- d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, ret);
- return ret;
-}
-EXPORT_SYMBOL_GPL(i2400m_dev_bootstrap);
-
-
-void i2400m_fw_cache(struct i2400m *i2400m)
-{
- int result;
- struct i2400m_fw *i2400m_fw;
- struct device *dev = i2400m_dev(i2400m);
-
- /* if there is anything there, free it -- now, this'd be weird */
- spin_lock(&i2400m->rx_lock);
- i2400m_fw = i2400m->fw_cached;
- spin_unlock(&i2400m->rx_lock);
- if (i2400m_fw != NULL && i2400m_fw != (void *) ~0) {
- i2400m_fw_put(i2400m_fw);
- WARN(1, "%s:%u: still cached fw still present?\n",
- __func__, __LINE__);
- }
-
- if (i2400m->fw_name == NULL) {
- dev_err(dev, "firmware n/a: can't cache\n");
- i2400m_fw = (void *) ~0;
- goto out;
- }
-
- i2400m_fw = kzalloc(sizeof(*i2400m_fw), GFP_ATOMIC);
- if (i2400m_fw == NULL)
- goto out;
- kref_init(&i2400m_fw->kref);
- result = request_firmware(&i2400m_fw->fw, i2400m->fw_name, dev);
- if (result < 0) {
- dev_err(dev, "firmware %s: failed to cache: %d\n",
- i2400m->fw_name, result);
- kfree(i2400m_fw);
- i2400m_fw = (void *) ~0;
- } else
- dev_info(dev, "firmware %s: cached\n", i2400m->fw_name);
-out:
- spin_lock(&i2400m->rx_lock);
- i2400m->fw_cached = i2400m_fw;
- spin_unlock(&i2400m->rx_lock);
-}
-
-
-void i2400m_fw_uncache(struct i2400m *i2400m)
-{
- struct i2400m_fw *i2400m_fw;
-
- spin_lock(&i2400m->rx_lock);
- i2400m_fw = i2400m->fw_cached;
- i2400m->fw_cached = NULL;
- spin_unlock(&i2400m->rx_lock);
-
- if (i2400m_fw != NULL && i2400m_fw != (void *) ~0)
- i2400m_fw_put(i2400m_fw);
-}
-
+++ /dev/null
-/*
- * Intel Wireless WiMAX Connection 2400m
- * USB-specific i2400m driver definitions
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * - Initial implementation
- *
- *
- * This driver implements the bus-specific part of the i2400m for
- * USB. Check i2400m.h for a generic driver description.
- *
- * ARCHITECTURE
- *
- * This driver listens to notifications sent from the notification
- * endpoint (in usb-notif.c); when data is ready to read, the code in
- * there schedules a read from the device (usb-rx.c) and then passes
- * the data to the generic RX code (rx.c).
- *
- * When the generic driver needs to send data (network or control), it
- * queues up in the TX FIFO (tx.c) and that will notify the driver
- * through the i2400m->bus_tx_kick() callback
- * (usb-tx.c:i2400mu_bus_tx_kick) which will send the items in the
- * FIFO queue.
- *
- * This driver, as well, implements the USB-specific ops for the generic
- * driver to be able to setup/teardown communication with the device
- * [i2400m_bus_dev_start() and i2400m_bus_dev_stop()], reseting the
- * device [i2400m_bus_reset()] and performing firmware upload
- * [i2400m_bus_bm_cmd() and i2400_bus_bm_wait_for_ack()].
- */
-
-#ifndef __I2400M_USB_H__
-#define __I2400M_USB_H__
-
-#include "i2400m.h"
-#include <linux/kthread.h>
-
-
-/*
- * Error Density Count: cheapo error density (over time) counter
- *
- * Originally by Reinette Chatre <reinette.chatre@intel.com>
- *
- * Embed an 'struct edc' somewhere. Each time there is a soft or
- * retryable error, call edc_inc() and check if the error top
- * watermark has been reached.
- */
-enum {
- EDC_MAX_ERRORS = 10,
- EDC_ERROR_TIMEFRAME = HZ,
-};
-
-/* error density counter */
-struct edc {
- unsigned long timestart;
- u16 errorcount;
-};
-
-struct i2400m_endpoint_cfg {
- unsigned char bulk_out;
- unsigned char notification;
- unsigned char reset_cold;
- unsigned char bulk_in;
-};
-
-static inline void edc_init(struct edc *edc)
-{
- edc->timestart = jiffies;
-}
-
-/**
- * edc_inc - report a soft error and check if we are over the watermark
- *
- * @edc: pointer to error density counter.
- * @max_err: maximum number of errors we can accept over the timeframe
- * @timeframe: length of the timeframe (in jiffies).
- *
- * Returns: !0 1 if maximum acceptable errors per timeframe has been
- * exceeded. 0 otherwise.
- *
- * This is way to determine if the number of acceptable errors per time
- * period has been exceeded. It is not accurate as there are cases in which
- * this scheme will not work, for example if there are periodic occurrences
- * of errors that straddle updates to the start time. This scheme is
- * sufficient for our usage.
- *
- * To use, embed a 'struct edc' somewhere, initialize it with
- * edc_init() and when an error hits:
- *
- * if (do_something_fails_with_a_soft_error) {
- * if (edc_inc(&my->edc, MAX_ERRORS, MAX_TIMEFRAME))
- * Ops, hard error, do something about it
- * else
- * Retry or ignore, depending on whatever
- * }
- */
-static inline int edc_inc(struct edc *edc, u16 max_err, u16 timeframe)
-{
- unsigned long now;
-
- now = jiffies;
- if (time_after(now, edc->timestart + timeframe)) {
- edc->errorcount = 1;
- edc->timestart = now;
- } else if (++edc->errorcount > max_err) {
- edc->errorcount = 0;
- edc->timestart = now;
- return 1;
- }
- return 0;
-}
-
-/* Host-Device interface for USB */
-enum {
- I2400M_USB_BOOT_RETRIES = 3,
- I2400MU_MAX_NOTIFICATION_LEN = 256,
- I2400MU_BLK_SIZE = 16,
- I2400MU_PL_SIZE_MAX = 0x3EFF,
-
- /* Device IDs */
- USB_DEVICE_ID_I6050 = 0x0186,
- USB_DEVICE_ID_I6050_2 = 0x0188,
- USB_DEVICE_ID_I6150 = 0x07d6,
- USB_DEVICE_ID_I6150_2 = 0x07d7,
- USB_DEVICE_ID_I6150_3 = 0x07d9,
- USB_DEVICE_ID_I6250 = 0x0187,
-};
-
-
-/**
- * struct i2400mu - descriptor for a USB connected i2400m
- *
- * @i2400m: bus-generic i2400m implementation; has to be first (see
- * it's documentation in i2400m.h).
- *
- * @usb_dev: pointer to our USB device
- *
- * @usb_iface: pointer to our USB interface
- *
- * @urb_edc: error density counter; used to keep a density-on-time tab
- * on how many soft (retryable or ignorable) errors we get. If we
- * go over the threshold, we consider the bus transport is failing
- * too much and reset.
- *
- * @notif_urb: URB for receiving notifications from the device.
- *
- * @tx_kthread: thread we use for data TX. We use a thread because in
- * order to do deep power saving and put the device to sleep, we
- * need to call usb_autopm_*() [blocking functions].
- *
- * @tx_wq: waitqueue for the TX kthread to sleep when there is no data
- * to be sent; when more data is available, it is woken up by
- * i2400mu_bus_tx_kick().
- *
- * @rx_kthread: thread we use for data RX. We use a thread because in
- * order to do deep power saving and put the device to sleep, we
- * need to call usb_autopm_*() [blocking functions].
- *
- * @rx_wq: waitqueue for the RX kthread to sleep when there is no data
- * to receive. When data is available, it is woken up by
- * usb-notif.c:i2400mu_notification_grok().
- *
- * @rx_pending_count: number of rx-data-ready notifications that were
- * still not handled by the RX kthread.
- *
- * @rx_size: current RX buffer size that is being used.
- *
- * @rx_size_acc: accumulator of the sizes of the previous read
- * transactions.
- *
- * @rx_size_cnt: number of read transactions accumulated in
- * @rx_size_acc.
- *
- * @do_autopm: disable(0)/enable(>0) calling the
- * usb_autopm_get/put_interface() barriers when executing
- * commands. See doc in i2400mu_suspend() for more information.
- *
- * @rx_size_auto_shrink: if true, the rx_size is shrunk
- * automatically based on the average size of the received
- * transactions. This allows the receive code to allocate smaller
- * chunks of memory and thus reduce pressure on the memory
- * allocator by not wasting so much space. By default it is
- * enabled.
- *
- * @debugfs_dentry: hookup for debugfs files.
- * These have to be in a separate directory, a child of
- * (wimax_dev->debugfs_dentry) so they can be removed when the
- * module unloads, as we don't keep each dentry.
- */
-struct i2400mu {
- struct i2400m i2400m; /* FIRST! See doc */
-
- struct usb_device *usb_dev;
- struct usb_interface *usb_iface;
- struct edc urb_edc; /* Error density counter */
- struct i2400m_endpoint_cfg endpoint_cfg;
-
- struct urb *notif_urb;
- struct task_struct *tx_kthread;
- wait_queue_head_t tx_wq;
-
- struct task_struct *rx_kthread;
- wait_queue_head_t rx_wq;
- atomic_t rx_pending_count;
- size_t rx_size, rx_size_acc, rx_size_cnt;
- atomic_t do_autopm;
- u8 rx_size_auto_shrink;
-
- struct dentry *debugfs_dentry;
- unsigned i6050:1; /* 1 if this is a 6050 based SKU */
-};
-
-
-static inline
-void i2400mu_init(struct i2400mu *i2400mu)
-{
- i2400m_init(&i2400mu->i2400m);
- edc_init(&i2400mu->urb_edc);
- init_waitqueue_head(&i2400mu->tx_wq);
- atomic_set(&i2400mu->rx_pending_count, 0);
- init_waitqueue_head(&i2400mu->rx_wq);
- i2400mu->rx_size = PAGE_SIZE - sizeof(struct skb_shared_info);
- atomic_set(&i2400mu->do_autopm, 1);
- i2400mu->rx_size_auto_shrink = 1;
-}
-
-int i2400mu_notification_setup(struct i2400mu *);
-void i2400mu_notification_release(struct i2400mu *);
-
-int i2400mu_rx_setup(struct i2400mu *);
-void i2400mu_rx_release(struct i2400mu *);
-void i2400mu_rx_kick(struct i2400mu *);
-
-int i2400mu_tx_setup(struct i2400mu *);
-void i2400mu_tx_release(struct i2400mu *);
-void i2400mu_bus_tx_kick(struct i2400m *);
-
-ssize_t i2400mu_bus_bm_cmd_send(struct i2400m *,
- const struct i2400m_bootrom_header *, size_t,
- int);
-ssize_t i2400mu_bus_bm_wait_for_ack(struct i2400m *,
- struct i2400m_bootrom_header *, size_t);
-#endif /* #ifndef __I2400M_USB_H__ */
+++ /dev/null
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Declarations for bus-generic internal APIs
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * - Initial implementation
- *
- *
- * GENERAL DRIVER ARCHITECTURE
- *
- * The i2400m driver is split in the following two major parts:
- *
- * - bus specific driver
- * - bus generic driver (this part)
- *
- * The bus specific driver sets up stuff specific to the bus the
- * device is connected to (USB, PCI, tam-tam...non-authoritative
- * nor binding list) which is basically the device-model management
- * (probe/disconnect, etc), moving data from device to kernel and
- * back, doing the power saving details and reseting the device.
- *
- * For details on each bus-specific driver, see it's include file,
- * i2400m-BUSNAME.h
- *
- * The bus-generic functionality break up is:
- *
- * - Firmware upload: fw.c - takes care of uploading firmware to the
- * device. bus-specific driver just needs to provides a way to
- * execute boot-mode commands and to reset the device.
- *
- * - RX handling: rx.c - receives data from the bus-specific code and
- * feeds it to the network or WiMAX stack or uses it to modify
- * the driver state. bus-specific driver only has to receive
- * frames and pass them to this module.
- *
- * - TX handling: tx.c - manages the TX FIFO queue and provides means
- * for the bus-specific TX code to pull data from the FIFO
- * queue. bus-specific code just pulls frames from this module
- * to sends them to the device.
- *
- * - netdev glue: netdev.c - interface with Linux networking
- * stack. Pass around data frames, and configure when the
- * device is up and running or shutdown (through ifconfig up /
- * down). Bus-generic only.
- *
- * - control ops: control.c - implements various commands for
- * controlling the device. bus-generic only.
- *
- * - device model glue: driver.c - implements helpers for the
- * device-model glue done by the bus-specific layer
- * (setup/release the driver resources), turning the device on
- * and off, handling the device reboots/resets and a few simple
- * WiMAX stack ops.
- *
- * Code is also broken up in linux-glue / device-glue.
- *
- * Linux glue contains functions that deal mostly with gluing with the
- * rest of the Linux kernel.
- *
- * Device-glue are functions that deal mostly with the way the device
- * does things and talk the device's language.
- *
- * device-glue code is licensed BSD so other open source OSes can take
- * it to implement their drivers.
- *
- *
- * APIs AND HEADER FILES
- *
- * This bus generic code exports three APIs:
- *
- * - HDI (host-device interface) definitions common to all busses
- * (include/linux/wimax/i2400m.h); these can be also used by user
- * space code.
- * - internal API for the bus-generic code
- * - external API for the bus-specific drivers
- *
- *
- * LIFE CYCLE:
- *
- * When the bus-specific driver probes, it allocates a network device
- * with enough space for it's data structue, that must contain a
- * &struct i2400m at the top.
- *
- * On probe, it needs to fill the i2400m members marked as [fill], as
- * well as i2400m->wimax_dev.net_dev and call i2400m_setup(). The
- * i2400m driver will only register with the WiMAX and network stacks;
- * the only access done to the device is to read the MAC address so we
- * can register a network device.
- *
- * The high-level call flow is:
- *
- * bus_probe()
- * i2400m_setup()
- * i2400m->bus_setup()
- * boot rom initialization / read mac addr
- * network / WiMAX stacks registration
- * i2400m_dev_start()
- * i2400m->bus_dev_start()
- * i2400m_dev_initialize()
- *
- * The reverse applies for a disconnect() call:
- *
- * bus_disconnect()
- * i2400m_release()
- * i2400m_dev_stop()
- * i2400m_dev_shutdown()
- * i2400m->bus_dev_stop()
- * network / WiMAX stack unregistration
- * i2400m->bus_release()
- *
- * At this point, control and data communications are possible.
- *
- * While the device is up, it might reset. The bus-specific driver has
- * to catch that situation and call i2400m_dev_reset_handle() to deal
- * with it (reset the internal driver structures and go back to square
- * one).
- */
-
-#ifndef __I2400M_H__
-#define __I2400M_H__
-
-#include <linux/usb.h>
-#include <linux/netdevice.h>
-#include <linux/completion.h>
-#include <linux/rwsem.h>
-#include <linux/atomic.h>
-#include <net/wimax.h>
-#include <linux/wimax/i2400m.h>
-#include <asm/byteorder.h>
-
-enum {
-/* netdev interface */
- /*
- * Out of NWG spec (R1_v1.2.2), 3.3.3 ASN Bearer Plane MTU Size
- *
- * The MTU is 1400 or less
- */
- I2400M_MAX_MTU = 1400,
-};
-
-/* Misc constants */
-enum {
- /* Size of the Boot Mode Command buffer */
- I2400M_BM_CMD_BUF_SIZE = 16 * 1024,
- I2400M_BM_ACK_BUF_SIZE = 256,
-};
-
-enum {
- /* Maximum number of bus reset can be retried */
- I2400M_BUS_RESET_RETRIES = 3,
-};
-
-/**
- * struct i2400m_poke_table - Hardware poke table for the Intel 2400m
- *
- * This structure will be used to create a device specific poke table
- * to put the device in a consistent state at boot time.
- *
- * @address: The device address to poke
- *
- * @data: The data value to poke to the device address
- *
- */
-struct i2400m_poke_table{
- __le32 address;
- __le32 data;
-};
-
-#define I2400M_FW_POKE(a, d) { \
- .address = cpu_to_le32(a), \
- .data = cpu_to_le32(d) \
-}
-
-
-/**
- * i2400m_reset_type - methods to reset a device
- *
- * @I2400M_RT_WARM: Reset without device disconnection, device handles
- * are kept valid but state is back to power on, with firmware
- * re-uploaded.
- * @I2400M_RT_COLD: Tell the device to disconnect itself from the bus
- * and reconnect. Renders all device handles invalid.
- * @I2400M_RT_BUS: Tells the bus to reset the device; last measure
- * used when both types above don't work.
- */
-enum i2400m_reset_type {
- I2400M_RT_WARM, /* first measure */
- I2400M_RT_COLD, /* second measure */
- I2400M_RT_BUS, /* call in artillery */
-};
-
-struct i2400m_reset_ctx;
-struct i2400m_roq;
-struct i2400m_barker_db;
-
-/**
- * struct i2400m - descriptor for an Intel 2400m
- *
- * Members marked with [fill] must be filled out/initialized before
- * calling i2400m_setup().
- *
- * Note the @bus_setup/@bus_release, @bus_dev_start/@bus_dev_release
- * call pairs are very much doing almost the same, and depending on
- * the underlying bus, some stuff has to be put in one or the
- * other. The idea of setup/release is that they setup the minimal
- * amount needed for loading firmware, where us dev_start/stop setup
- * the rest needed to do full data/control traffic.
- *
- * @bus_tx_block_size: [fill] USB imposes a 16 block size, but other
- * busses will differ. So we have a tx_blk_size variable that the
- * bus layer sets to tell the engine how much of that we need.
- *
- * @bus_tx_room_min: [fill] Minimum room required while allocating
- * TX queue's buffer space for message header. USB requires
- * 16 bytes. Refer to bus specific driver code for details.
- *
- * @bus_pl_size_max: [fill] Maximum payload size.
- *
- * @bus_setup: [optional fill] Function called by the bus-generic code
- * [i2400m_setup()] to setup the basic bus-specific communications
- * to the the device needed to load firmware. See LIFE CYCLE above.
- *
- * NOTE: Doesn't need to upload the firmware, as that is taken
- * care of by the bus-generic code.
- *
- * @bus_release: [optional fill] Function called by the bus-generic
- * code [i2400m_release()] to shutdown the basic bus-specific
- * communications to the the device needed to load firmware. See
- * LIFE CYCLE above.
- *
- * This function does not need to reset the device, just tear down
- * all the host resources created to handle communication with
- * the device.
- *
- * @bus_dev_start: [optional fill] Function called by the bus-generic
- * code [i2400m_dev_start()] to do things needed to start the
- * device. See LIFE CYCLE above.
- *
- * NOTE: Doesn't need to upload the firmware, as that is taken
- * care of by the bus-generic code.
- *
- * @bus_dev_stop: [optional fill] Function called by the bus-generic
- * code [i2400m_dev_stop()] to do things needed for stopping the
- * device. See LIFE CYCLE above.
- *
- * This function does not need to reset the device, just tear down
- * all the host resources created to handle communication with
- * the device.
- *
- * @bus_tx_kick: [fill] Function called by the bus-generic code to let
- * the bus-specific code know that there is data available in the
- * TX FIFO for transmission to the device.
- *
- * This function cannot sleep.
- *
- * @bus_reset: [fill] Function called by the bus-generic code to reset
- * the device in in various ways. Doesn't need to wait for the
- * reset to finish.
- *
- * If warm or cold reset fail, this function is expected to do a
- * bus-specific reset (eg: USB reset) to get the device to a
- * working state (even if it implies device disconecction).
- *
- * Note the warm reset is used by the firmware uploader to
- * reinitialize the device.
- *
- * IMPORTANT: this is called very early in the device setup
- * process, so it cannot rely on common infrastructure being laid
- * out.
- *
- * IMPORTANT: don't call reset on RT_BUS with i2400m->init_mutex
- * held, as the .pre/.post reset handlers will deadlock.
- *
- * @bus_bm_retries: [fill] How many times shall a firmware upload /
- * device initialization be retried? Different models of the same
- * device might need different values, hence it is set by the
- * bus-specific driver. Note this value is used in two places,
- * i2400m_fw_dnload() and __i2400m_dev_start(); they won't become
- * multiplicative (__i2400m_dev_start() calling N times
- * i2400m_fw_dnload() and this trying N times to download the
- * firmware), as if __i2400m_dev_start() only retries if the
- * firmware crashed while initializing the device (not in a
- * general case).
- *
- * @bus_bm_cmd_send: [fill] Function called to send a boot-mode
- * command. Flags are defined in 'enum i2400m_bm_cmd_flags'. This
- * is synchronous and has to return 0 if ok or < 0 errno code in
- * any error condition.
- *
- * @bus_bm_wait_for_ack: [fill] Function called to wait for a
- * boot-mode notification (that can be a response to a previously
- * issued command or an asynchronous one). Will read until all the
- * indicated size is read or timeout. Reading more or less data
- * than asked for is an error condition. Return 0 if ok, < 0 errno
- * code on error.
- *
- * The caller to this function will check if the response is a
- * barker that indicates the device going into reset mode.
- *
- * @bus_fw_names: [fill] a NULL-terminated array with the names of the
- * firmware images to try loading. This is made a list so we can
- * support backward compatibility of firmware releases (eg: if we
- * can't find the default v1.4, we try v1.3). In general, the name
- * should be i2400m-fw-X-VERSION.sbcf, where X is the bus name.
- * The list is tried in order and the first one that loads is
- * used. The fw loader will set i2400m->fw_name to point to the
- * active firmware image.
- *
- * @bus_bm_mac_addr_impaired: [fill] Set to true if the device's MAC
- * address provided in boot mode is kind of broken and needs to
- * be re-read later on.
- *
- * @bus_bm_pokes_table: [fill/optional] A table of device addresses
- * and values that will be poked at device init time to move the
- * device to the correct state for the type of boot/firmware being
- * used. This table MUST be terminated with (0x000000,
- * 0x00000000) or bad things will happen.
- *
- *
- * @wimax_dev: WiMAX generic device for linkage into the kernel WiMAX
- * stack. Due to the way a net_device is allocated, we need to
- * force this to be the first field so that we can get from
- * netdev_priv() the right pointer.
- *
- * @updown: the device is up and ready for transmitting control and
- * data packets. This implies @ready (communication infrastructure
- * with the device is ready) and the device's firmware has been
- * loaded and the device initialized.
- *
- * Write to it only inside a i2400m->init_mutex protected area
- * followed with a wmb(); rmb() before accesing (unless locked
- * inside i2400m->init_mutex). Read access can be loose like that
- * [just using rmb()] because the paths that use this also do
- * other error checks later on.
- *
- * @ready: Communication infrastructure with the device is ready, data
- * frames can start to be passed around (this is lighter than
- * using the WiMAX state for certain hot paths).
- *
- * Write to it only inside a i2400m->init_mutex protected area
- * followed with a wmb(); rmb() before accesing (unless locked
- * inside i2400m->init_mutex). Read access can be loose like that
- * [just using rmb()] because the paths that use this also do
- * other error checks later on.
- *
- * @rx_reorder: 1 if RX reordering is enabled; this can only be
- * set at probe time.
- *
- * @state: device's state (as reported by it)
- *
- * @state_wq: waitqueue that is woken up whenever the state changes
- *
- * @tx_lock: spinlock to protect TX members
- *
- * @tx_buf: FIFO buffer for TX; we queue data here
- *
- * @tx_in: FIFO index for incoming data. Note this doesn't wrap around
- * and it is always greater than @tx_out.
- *
- * @tx_out: FIFO index for outgoing data
- *
- * @tx_msg: current TX message that is active in the FIFO for
- * appending payloads.
- *
- * @tx_sequence: current sequence number for TX messages from the
- * device to the host.
- *
- * @tx_msg_size: size of the current message being transmitted by the
- * bus-specific code.
- *
- * @tx_pl_num: total number of payloads sent
- *
- * @tx_pl_max: maximum number of payloads sent in a TX message
- *
- * @tx_pl_min: minimum number of payloads sent in a TX message
- *
- * @tx_num: number of TX messages sent
- *
- * @tx_size_acc: number of bytes in all TX messages sent
- * (this is different to net_dev's statistics as it also counts
- * control messages).
- *
- * @tx_size_min: smallest TX message sent.
- *
- * @tx_size_max: biggest TX message sent.
- *
- * @rx_lock: spinlock to protect RX members and rx_roq_refcount.
- *
- * @rx_pl_num: total number of payloads received
- *
- * @rx_pl_max: maximum number of payloads received in a RX message
- *
- * @rx_pl_min: minimum number of payloads received in a RX message
- *
- * @rx_num: number of RX messages received
- *
- * @rx_size_acc: number of bytes in all RX messages received
- * (this is different to net_dev's statistics as it also counts
- * control messages).
- *
- * @rx_size_min: smallest RX message received.
- *
- * @rx_size_max: buggest RX message received.
- *
- * @rx_roq: RX ReOrder queues. (fw >= v1.4) When packets are received
- * out of order, the device will ask the driver to hold certain
- * packets until the ones that are received out of order can be
- * delivered. Then the driver can release them to the host. See
- * drivers/net/i2400m/rx.c for details.
- *
- * @rx_roq_refcount: refcount rx_roq. This refcounts any access to
- * rx_roq thus preventing rx_roq being destroyed when rx_roq
- * is being accessed. rx_roq_refcount is protected by rx_lock.
- *
- * @rx_reports: reports received from the device that couldn't be
- * processed because the driver wasn't still ready; when ready,
- * they are pulled from here and chewed.
- *
- * @rx_reports_ws: Work struct used to kick a scan of the RX reports
- * list and to process each.
- *
- * @src_mac_addr: MAC address used to make ethernet packets be coming
- * from. This is generated at i2400m_setup() time and used during
- * the life cycle of the instance. See i2400m_fake_eth_header().
- *
- * @init_mutex: Mutex used for serializing the device bringup
- * sequence; this way if the device reboots in the middle, we
- * don't try to do a bringup again while we are tearing down the
- * one that failed.
- *
- * Can't reuse @msg_mutex because from within the bringup sequence
- * we need to send messages to the device and thus use @msg_mutex.
- *
- * @msg_mutex: mutex used to send control commands to the device (we
- * only allow one at a time, per host-device interface design).
- *
- * @msg_completion: used to wait for an ack to a control command sent
- * to the device.
- *
- * @ack_skb: used to store the actual ack to a control command if the
- * reception of the command was successful. Otherwise, a ERR_PTR()
- * errno code that indicates what failed with the ack reception.
- *
- * Only valid after @msg_completion is woken up. Only updateable
- * if @msg_completion is armed. Only touched by
- * i2400m_msg_to_dev().
- *
- * Protected by @rx_lock. In theory the command execution flow is
- * sequential, but in case the device sends an out-of-phase or
- * very delayed response, we need to avoid it trampling current
- * execution.
- *
- * @bm_cmd_buf: boot mode command buffer for composing firmware upload
- * commands.
- *
- * USB can't r/w to stack, vmalloc, etc...as well, we end up
- * having to alloc/free a lot to compose commands, so we use these
- * for stagging and not having to realloc all the time.
- *
- * This assumes the code always runs serialized. Only one thread
- * can call i2400m_bm_cmd() at the same time.
- *
- * @bm_ack_buf: boot mode acknoledge buffer for staging reception of
- * responses to commands.
- *
- * See @bm_cmd_buf.
- *
- * @work_queue: work queue for processing device reports. This
- * workqueue cannot be used for processing TX or RX to the device,
- * as from it we'll process device reports, which might require
- * further communication with the device.
- *
- * @debugfs_dentry: hookup for debugfs files.
- * These have to be in a separate directory, a child of
- * (wimax_dev->debugfs_dentry) so they can be removed when the
- * module unloads, as we don't keep each dentry.
- *
- * @fw_name: name of the firmware image that is currently being used.
- *
- * @fw_version: version of the firmware interface, Major.minor,
- * encoded in the high word and low word (major << 16 | minor).
- *
- * @fw_hdrs: NULL terminated array of pointers to the firmware
- * headers. This is only available during firmware load time.
- *
- * @fw_cached: Used to cache firmware when the system goes to
- * suspend/standby/hibernation (as on resume we can't read it). If
- * NULL, no firmware was cached, read it. If ~0, you can't read
- * any firmware files (the system still didn't come out of suspend
- * and failed to cache one), so abort; otherwise, a valid cached
- * firmware to be used. Access to this variable is protected by
- * the spinlock i2400m->rx_lock.
- *
- * @barker: barker type that the device uses; this is initialized by
- * i2400m_is_boot_barker() the first time it is called. Then it
- * won't change during the life cycle of the device and every time
- * a boot barker is received, it is just verified for it being the
- * same.
- *
- * @pm_notifier: used to register for PM events
- *
- * @bus_reset_retries: counter for the number of bus resets attempted for
- * this boot. It's not for tracking the number of bus resets during
- * the whole driver life cycle (from insmod to rmmod) but for the
- * number of dev_start() executed until dev_start() returns a success
- * (ie: a good boot means a dev_stop() followed by a successful
- * dev_start()). dev_reset_handler() increments this counter whenever
- * it is triggering a bus reset. It checks this counter to decide if a
- * subsequent bus reset should be retried. dev_reset_handler() retries
- * the bus reset until dev_start() succeeds or the counter reaches
- * I2400M_BUS_RESET_RETRIES. The counter is cleared to 0 in
- * dev_reset_handle() when dev_start() returns a success,
- * ie: a successul boot is completed.
- *
- * @alive: flag to denote if the device *should* be alive. This flag is
- * everything like @updown (see doc for @updown) except reflecting
- * the device state *we expect* rather than the actual state as denoted
- * by @updown. It is set 1 whenever @updown is set 1 in dev_start().
- * Then the device is expected to be alive all the time
- * (i2400m->alive remains 1) until the driver is removed. Therefore
- * all the device reboot events detected can be still handled properly
- * by either dev_reset_handle() or .pre_reset/.post_reset as long as
- * the driver presents. It is set 0 along with @updown in dev_stop().
- *
- * @error_recovery: flag to denote if we are ready to take an error recovery.
- * 0 for ready to take an error recovery; 1 for not ready. It is
- * initialized to 1 while probe() since we don't tend to take any error
- * recovery during probe(). It is decremented by 1 whenever dev_start()
- * succeeds to indicate we are ready to take error recovery from now on.
- * It is checked every time we wanna schedule an error recovery. If an
- * error recovery is already in place (error_recovery was set 1), we
- * should not schedule another one until the last one is done.
- */
-struct i2400m {
- struct wimax_dev wimax_dev; /* FIRST! See doc */
-
- unsigned updown:1; /* Network device is up or down */
- unsigned boot_mode:1; /* is the device in boot mode? */
- unsigned sboot:1; /* signed or unsigned fw boot */
- unsigned ready:1; /* Device comm infrastructure ready */
- unsigned rx_reorder:1; /* RX reorder is enabled */
- u8 trace_msg_from_user; /* echo rx msgs to 'trace' pipe */
- /* typed u8 so /sys/kernel/debug/u8 can tweak */
- enum i2400m_system_state state;
- wait_queue_head_t state_wq; /* Woken up when on state updates */
-
- size_t bus_tx_block_size;
- size_t bus_tx_room_min;
- size_t bus_pl_size_max;
- unsigned bus_bm_retries;
-
- int (*bus_setup)(struct i2400m *);
- int (*bus_dev_start)(struct i2400m *);
- void (*bus_dev_stop)(struct i2400m *);
- void (*bus_release)(struct i2400m *);
- void (*bus_tx_kick)(struct i2400m *);
- int (*bus_reset)(struct i2400m *, enum i2400m_reset_type);
- ssize_t (*bus_bm_cmd_send)(struct i2400m *,
- const struct i2400m_bootrom_header *,
- size_t, int flags);
- ssize_t (*bus_bm_wait_for_ack)(struct i2400m *,
- struct i2400m_bootrom_header *, size_t);
- const char **bus_fw_names;
- unsigned bus_bm_mac_addr_impaired:1;
- const struct i2400m_poke_table *bus_bm_pokes_table;
-
- spinlock_t tx_lock; /* protect TX state */
- void *tx_buf;
- size_t tx_in, tx_out;
- struct i2400m_msg_hdr *tx_msg;
- size_t tx_sequence, tx_msg_size;
- /* TX stats */
- unsigned tx_pl_num, tx_pl_max, tx_pl_min,
- tx_num, tx_size_acc, tx_size_min, tx_size_max;
-
- /* RX stuff */
- /* protect RX state and rx_roq_refcount */
- spinlock_t rx_lock;
- unsigned rx_pl_num, rx_pl_max, rx_pl_min,
- rx_num, rx_size_acc, rx_size_min, rx_size_max;
- struct i2400m_roq *rx_roq; /* access is refcounted */
- struct kref rx_roq_refcount; /* refcount access to rx_roq */
- u8 src_mac_addr[ETH_HLEN];
- struct list_head rx_reports; /* under rx_lock! */
- struct work_struct rx_report_ws;
-
- struct mutex msg_mutex; /* serialize command execution */
- struct completion msg_completion;
- struct sk_buff *ack_skb; /* protected by rx_lock */
-
- void *bm_ack_buf; /* for receiving acks over USB */
- void *bm_cmd_buf; /* for issuing commands over USB */
-
- struct workqueue_struct *work_queue;
-
- struct mutex init_mutex; /* protect bringup seq */
- struct i2400m_reset_ctx *reset_ctx; /* protected by init_mutex */
-
- struct work_struct wake_tx_ws;
- struct sk_buff *wake_tx_skb;
-
- struct work_struct reset_ws;
- const char *reset_reason;
-
- struct work_struct recovery_ws;
-
- struct dentry *debugfs_dentry;
- const char *fw_name; /* name of the current firmware image */
- unsigned long fw_version; /* version of the firmware interface */
- const struct i2400m_bcf_hdr **fw_hdrs;
- struct i2400m_fw *fw_cached; /* protected by rx_lock */
- struct i2400m_barker_db *barker;
-
- struct notifier_block pm_notifier;
-
- /* counting bus reset retries in this boot */
- atomic_t bus_reset_retries;
-
- /* if the device is expected to be alive */
- unsigned alive;
-
- /* 0 if we are ready for error recovery; 1 if not ready */
- atomic_t error_recovery;
-
-};
-
-
-/*
- * Bus-generic internal APIs
- * -------------------------
- */
-
-static inline
-struct i2400m *wimax_dev_to_i2400m(struct wimax_dev *wimax_dev)
-{
- return container_of(wimax_dev, struct i2400m, wimax_dev);
-}
-
-static inline
-struct i2400m *net_dev_to_i2400m(struct net_device *net_dev)
-{
- return wimax_dev_to_i2400m(netdev_priv(net_dev));
-}
-
-/*
- * Boot mode support
- */
-
-/**
- * i2400m_bm_cmd_flags - flags to i2400m_bm_cmd()
- *
- * @I2400M_BM_CMD_RAW: send the command block as-is, without doing any
- * extra processing for adding CRC.
- */
-enum i2400m_bm_cmd_flags {
- I2400M_BM_CMD_RAW = 1 << 2,
-};
-
-/**
- * i2400m_bri - Boot-ROM indicators
- *
- * Flags for i2400m_bootrom_init() and i2400m_dev_bootstrap() [which
- * are passed from things like i2400m_setup()]. Can be combined with
- * |.
- *
- * @I2400M_BRI_SOFT: The device rebooted already and a reboot
- * barker received, proceed directly to ack the boot sequence.
- * @I2400M_BRI_NO_REBOOT: Do not reboot the device and proceed
- * directly to wait for a reboot barker from the device.
- * @I2400M_BRI_MAC_REINIT: We need to reinitialize the boot
- * rom after reading the MAC address. This is quite a dirty hack,
- * if you ask me -- the device requires the bootrom to be
- * initialized after reading the MAC address.
- */
-enum i2400m_bri {
- I2400M_BRI_SOFT = 1 << 1,
- I2400M_BRI_NO_REBOOT = 1 << 2,
- I2400M_BRI_MAC_REINIT = 1 << 3,
-};
-
-void i2400m_bm_cmd_prepare(struct i2400m_bootrom_header *);
-int i2400m_dev_bootstrap(struct i2400m *, enum i2400m_bri);
-int i2400m_read_mac_addr(struct i2400m *);
-int i2400m_bootrom_init(struct i2400m *, enum i2400m_bri);
-int i2400m_is_boot_barker(struct i2400m *, const void *, size_t);
-static inline
-int i2400m_is_d2h_barker(const void *buf)
-{
- const __le32 *barker = buf;
- return le32_to_cpu(*barker) == I2400M_D2H_MSG_BARKER;
-}
-void i2400m_unknown_barker(struct i2400m *, const void *, size_t);
-
-/* Make/grok boot-rom header commands */
-
-static inline
-__le32 i2400m_brh_command(enum i2400m_brh_opcode opcode, unsigned use_checksum,
- unsigned direct_access)
-{
- return cpu_to_le32(
- I2400M_BRH_SIGNATURE
- | (direct_access ? I2400M_BRH_DIRECT_ACCESS : 0)
- | I2400M_BRH_RESPONSE_REQUIRED /* response always required */
- | (use_checksum ? I2400M_BRH_USE_CHECKSUM : 0)
- | (opcode & I2400M_BRH_OPCODE_MASK));
-}
-
-static inline
-void i2400m_brh_set_opcode(struct i2400m_bootrom_header *hdr,
- enum i2400m_brh_opcode opcode)
-{
- hdr->command = cpu_to_le32(
- (le32_to_cpu(hdr->command) & ~I2400M_BRH_OPCODE_MASK)
- | (opcode & I2400M_BRH_OPCODE_MASK));
-}
-
-static inline
-unsigned i2400m_brh_get_opcode(const struct i2400m_bootrom_header *hdr)
-{
- return le32_to_cpu(hdr->command) & I2400M_BRH_OPCODE_MASK;
-}
-
-static inline
-unsigned i2400m_brh_get_response(const struct i2400m_bootrom_header *hdr)
-{
- return (le32_to_cpu(hdr->command) & I2400M_BRH_RESPONSE_MASK)
- >> I2400M_BRH_RESPONSE_SHIFT;
-}
-
-static inline
-unsigned i2400m_brh_get_use_checksum(const struct i2400m_bootrom_header *hdr)
-{
- return le32_to_cpu(hdr->command) & I2400M_BRH_USE_CHECKSUM;
-}
-
-static inline
-unsigned i2400m_brh_get_response_required(
- const struct i2400m_bootrom_header *hdr)
-{
- return le32_to_cpu(hdr->command) & I2400M_BRH_RESPONSE_REQUIRED;
-}
-
-static inline
-unsigned i2400m_brh_get_direct_access(const struct i2400m_bootrom_header *hdr)
-{
- return le32_to_cpu(hdr->command) & I2400M_BRH_DIRECT_ACCESS;
-}
-
-static inline
-unsigned i2400m_brh_get_signature(const struct i2400m_bootrom_header *hdr)
-{
- return (le32_to_cpu(hdr->command) & I2400M_BRH_SIGNATURE_MASK)
- >> I2400M_BRH_SIGNATURE_SHIFT;
-}
-
-
-/*
- * Driver / device setup and internal functions
- */
-void i2400m_init(struct i2400m *);
-int i2400m_reset(struct i2400m *, enum i2400m_reset_type);
-void i2400m_netdev_setup(struct net_device *net_dev);
-int i2400m_sysfs_setup(struct device_driver *);
-void i2400m_sysfs_release(struct device_driver *);
-int i2400m_tx_setup(struct i2400m *);
-void i2400m_wake_tx_work(struct work_struct *);
-void i2400m_tx_release(struct i2400m *);
-
-int i2400m_rx_setup(struct i2400m *);
-void i2400m_rx_release(struct i2400m *);
-
-void i2400m_fw_cache(struct i2400m *);
-void i2400m_fw_uncache(struct i2400m *);
-
-void i2400m_net_rx(struct i2400m *, struct sk_buff *, unsigned, const void *,
- int);
-void i2400m_net_erx(struct i2400m *, struct sk_buff *, enum i2400m_cs);
-void i2400m_net_wake_stop(struct i2400m *);
-enum i2400m_pt;
-int i2400m_tx(struct i2400m *, const void *, size_t, enum i2400m_pt);
-
-#ifdef CONFIG_DEBUG_FS
-void i2400m_debugfs_add(struct i2400m *);
-void i2400m_debugfs_rm(struct i2400m *);
-#else
-static inline void i2400m_debugfs_add(struct i2400m *i2400m) {}
-static inline void i2400m_debugfs_rm(struct i2400m *i2400m) {}
-#endif
-
-/* Initialize/shutdown the device */
-int i2400m_dev_initialize(struct i2400m *);
-void i2400m_dev_shutdown(struct i2400m *);
-
-extern struct attribute_group i2400m_dev_attr_group;
-
-
-/* HDI message's payload description handling */
-
-static inline
-size_t i2400m_pld_size(const struct i2400m_pld *pld)
-{
- return I2400M_PLD_SIZE_MASK & le32_to_cpu(pld->val);
-}
-
-static inline
-enum i2400m_pt i2400m_pld_type(const struct i2400m_pld *pld)
-{
- return (I2400M_PLD_TYPE_MASK & le32_to_cpu(pld->val))
- >> I2400M_PLD_TYPE_SHIFT;
-}
-
-static inline
-void i2400m_pld_set(struct i2400m_pld *pld, size_t size,
- enum i2400m_pt type)
-{
- pld->val = cpu_to_le32(
- ((type << I2400M_PLD_TYPE_SHIFT) & I2400M_PLD_TYPE_MASK)
- | (size & I2400M_PLD_SIZE_MASK));
-}
-
-
-/*
- * API for the bus-specific drivers
- * --------------------------------
- */
-
-static inline
-struct i2400m *i2400m_get(struct i2400m *i2400m)
-{
- dev_hold(i2400m->wimax_dev.net_dev);
- return i2400m;
-}
-
-static inline
-void i2400m_put(struct i2400m *i2400m)
-{
- dev_put(i2400m->wimax_dev.net_dev);
-}
-
-int i2400m_dev_reset_handle(struct i2400m *, const char *);
-int i2400m_pre_reset(struct i2400m *);
-int i2400m_post_reset(struct i2400m *);
-void i2400m_error_recovery(struct i2400m *);
-
-/*
- * _setup()/_release() are called by the probe/disconnect functions of
- * the bus-specific drivers.
- */
-int i2400m_setup(struct i2400m *, enum i2400m_bri bm_flags);
-void i2400m_release(struct i2400m *);
-
-int i2400m_rx(struct i2400m *, struct sk_buff *);
-struct i2400m_msg_hdr *i2400m_tx_msg_get(struct i2400m *, size_t *);
-void i2400m_tx_msg_sent(struct i2400m *);
-
-
-/*
- * Utility functions
- */
-
-static inline
-struct device *i2400m_dev(struct i2400m *i2400m)
-{
- return i2400m->wimax_dev.net_dev->dev.parent;
-}
-
-int i2400m_msg_check_status(const struct i2400m_l3l4_hdr *, char *, size_t);
-int i2400m_msg_size_check(struct i2400m *, const struct i2400m_l3l4_hdr *,
- size_t);
-struct sk_buff *i2400m_msg_to_dev(struct i2400m *, const void *, size_t);
-void i2400m_msg_to_dev_cancel_wait(struct i2400m *, int);
-void i2400m_report_hook(struct i2400m *, const struct i2400m_l3l4_hdr *,
- size_t);
-void i2400m_report_hook_work(struct work_struct *);
-int i2400m_cmd_enter_powersave(struct i2400m *);
-int i2400m_cmd_exit_idle(struct i2400m *);
-struct sk_buff *i2400m_get_device_info(struct i2400m *);
-int i2400m_firmware_check(struct i2400m *);
-int i2400m_set_idle_timeout(struct i2400m *, unsigned);
-
-static inline
-struct usb_endpoint_descriptor *usb_get_epd(struct usb_interface *iface, int ep)
-{
- return &iface->cur_altsetting->endpoint[ep].desc;
-}
-
-int i2400m_op_rfkill_sw_toggle(struct wimax_dev *, enum wimax_rf_state);
-void i2400m_report_tlv_rf_switches_status(struct i2400m *,
- const struct i2400m_tlv_rf_switches_status *);
-
-/*
- * Helpers for firmware backwards compatibility
- *
- * As we aim to support at least the firmware version that was
- * released with the previous kernel/driver release, some code will be
- * conditionally executed depending on the firmware version. On each
- * release, the code to support fw releases past the last two ones
- * will be purged.
- *
- * By making it depend on this macros, it is easier to keep it a tab
- * on what has to go and what not.
- */
-static inline
-unsigned i2400m_le_v1_3(struct i2400m *i2400m)
-{
- /* running fw is lower or v1.3 */
- return i2400m->fw_version <= 0x00090001;
-}
-
-static inline
-unsigned i2400m_ge_v1_4(struct i2400m *i2400m)
-{
- /* running fw is higher or v1.4 */
- return i2400m->fw_version >= 0x00090002;
-}
-
-
-/*
- * Do a millisecond-sleep for allowing wireshark to dump all the data
- * packets. Used only for debugging.
- */
-static inline
-void __i2400m_msleep(unsigned ms)
-{
-#if 1
-#else
- msleep(ms);
-#endif
-}
-
-
-/* module initialization helpers */
-int i2400m_barker_db_init(const char *);
-void i2400m_barker_db_exit(void);
-
-
-
-#endif /* #ifndef __I2400M_H__ */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Glue with the networking stack
- *
- * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements an ethernet device for the i2400m.
- *
- * We fake being an ethernet device to simplify the support from user
- * space and from the other side. The world is (sadly) configured to
- * take in only Ethernet devices...
- *
- * Because of this, when using firmwares <= v1.3, there is an
- * copy-each-rxed-packet overhead on the RX path. Each IP packet has
- * to be reallocated to add an ethernet header (as there is no space
- * in what we get from the device). This is a known drawback and
- * firmwares >= 1.4 add header space that can be used to insert the
- * ethernet header without having to reallocate and copy.
- *
- * TX error handling is tricky; because we have to FIFO/queue the
- * buffers for transmission (as the hardware likes it aggregated), we
- * just give the skb to the TX subsystem and by the time it is
- * transmitted, we have long forgotten about it. So we just don't care
- * too much about it.
- *
- * Note that when the device is in idle mode with the basestation, we
- * need to negotiate coming back up online. That involves negotiation
- * and possible user space interaction. Thus, we defer to a workqueue
- * to do all that. By default, we only queue a single packet and drop
- * the rest, as potentially the time to go back from idle to normal is
- * long.
- *
- * ROADMAP
- *
- * i2400m_open Called on ifconfig up
- * i2400m_stop Called on ifconfig down
- *
- * i2400m_hard_start_xmit Called by the network stack to send a packet
- * i2400m_net_wake_tx Wake up device from basestation-IDLE & TX
- * i2400m_wake_tx_work
- * i2400m_cmd_exit_idle
- * i2400m_tx
- * i2400m_net_tx TX a data frame
- * i2400m_tx
- *
- * i2400m_change_mtu Called on ifconfig mtu XXX
- *
- * i2400m_tx_timeout Called when the device times out
- *
- * i2400m_net_rx Called by the RX code when a data frame is
- * available (firmware <= 1.3)
- * i2400m_net_erx Called by the RX code when a data frame is
- * available (firmware >= 1.4).
- * i2400m_netdev_setup Called to setup all the netdev stuff from
- * alloc_netdev.
- */
-#include <linux/if_arp.h>
-#include <linux/slab.h>
-#include <linux/netdevice.h>
-#include <linux/ethtool.h>
-#include <linux/export.h>
-#include "i2400m.h"
-
-
-#define D_SUBMODULE netdev
-#include "debug-levels.h"
-
-enum {
-/* netdev interface */
- /* 20 secs? yep, this is the maximum timeout that the device
- * might take to get out of IDLE / negotiate it with the base
- * station. We add 1sec for good measure. */
- I2400M_TX_TIMEOUT = 21 * HZ,
- /*
- * Experimentation has determined that, 20 to be a good value
- * for minimizing the jitter in the throughput.
- */
- I2400M_TX_QLEN = 20,
-};
-
-
-static
-int i2400m_open(struct net_device *net_dev)
-{
- int result;
- struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
- struct device *dev = i2400m_dev(i2400m);
-
- d_fnstart(3, dev, "(net_dev %p [i2400m %p])\n", net_dev, i2400m);
- /* Make sure we wait until init is complete... */
- mutex_lock(&i2400m->init_mutex);
- if (i2400m->updown)
- result = 0;
- else
- result = -EBUSY;
- mutex_unlock(&i2400m->init_mutex);
- d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
- net_dev, i2400m, result);
- return result;
-}
-
-
-static
-int i2400m_stop(struct net_device *net_dev)
-{
- struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
- struct device *dev = i2400m_dev(i2400m);
-
- d_fnstart(3, dev, "(net_dev %p [i2400m %p])\n", net_dev, i2400m);
- i2400m_net_wake_stop(i2400m);
- d_fnend(3, dev, "(net_dev %p [i2400m %p]) = 0\n", net_dev, i2400m);
- return 0;
-}
-
-
-/*
- * Wake up the device and transmit a held SKB, then restart the net queue
- *
- * When the device goes into basestation-idle mode, we need to tell it
- * to exit that mode; it will negotiate with the base station, user
- * space may have to intervene to rehandshake crypto and then tell us
- * when it is ready to transmit the packet we have "queued". Still we
- * need to give it sometime after it reports being ok.
- *
- * On error, there is not much we can do. If the error was on TX, we
- * still wake the queue up to see if the next packet will be luckier.
- *
- * If _cmd_exit_idle() fails...well, it could be many things; most
- * commonly it is that something else took the device out of IDLE mode
- * (for example, the base station). In that case we get an -EILSEQ and
- * we are just going to ignore that one. If the device is back to
- * connected, then fine -- if it is someother state, the packet will
- * be dropped anyway.
- */
-void i2400m_wake_tx_work(struct work_struct *ws)
-{
- int result;
- struct i2400m *i2400m = container_of(ws, struct i2400m, wake_tx_ws);
- struct net_device *net_dev = i2400m->wimax_dev.net_dev;
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *skb;
- unsigned long flags;
-
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- skb = i2400m->wake_tx_skb;
- i2400m->wake_tx_skb = NULL;
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-
- d_fnstart(3, dev, "(ws %p i2400m %p skb %p)\n", ws, i2400m, skb);
- result = -EINVAL;
- if (skb == NULL) {
- dev_err(dev, "WAKE&TX: skb disappeared!\n");
- goto out_put;
- }
- /* If we have, somehow, lost the connection after this was
- * queued, don't do anything; this might be the device got
- * reset or just disconnected. */
- if (unlikely(!netif_carrier_ok(net_dev)))
- goto out_kfree;
- result = i2400m_cmd_exit_idle(i2400m);
- if (result == -EILSEQ)
- result = 0;
- if (result < 0) {
- dev_err(dev, "WAKE&TX: device didn't get out of idle: "
- "%d - resetting\n", result);
- i2400m_reset(i2400m, I2400M_RT_BUS);
- goto error;
- }
- result = wait_event_timeout(i2400m->state_wq,
- i2400m->state != I2400M_SS_IDLE,
- net_dev->watchdog_timeo - HZ/2);
- if (result == 0)
- result = -ETIMEDOUT;
- if (result < 0) {
- dev_err(dev, "WAKE&TX: error waiting for device to exit IDLE: "
- "%d - resetting\n", result);
- i2400m_reset(i2400m, I2400M_RT_BUS);
- goto error;
- }
- msleep(20); /* device still needs some time or it drops it */
- result = i2400m_tx(i2400m, skb->data, skb->len, I2400M_PT_DATA);
-error:
- netif_wake_queue(net_dev);
-out_kfree:
- kfree_skb(skb); /* refcount transferred by _hard_start_xmit() */
-out_put:
- i2400m_put(i2400m);
- d_fnend(3, dev, "(ws %p i2400m %p skb %p) = void [%d]\n",
- ws, i2400m, skb, result);
-}
-
-
-/*
- * Prepare the data payload TX header
- *
- * The i2400m expects a 4 byte header in front of a data packet.
- *
- * Because we pretend to be an ethernet device, this packet comes with
- * an ethernet header. Pull it and push our header.
- */
-static
-void i2400m_tx_prep_header(struct sk_buff *skb)
-{
- struct i2400m_pl_data_hdr *pl_hdr;
- skb_pull(skb, ETH_HLEN);
- pl_hdr = skb_push(skb, sizeof(*pl_hdr));
- pl_hdr->reserved = 0;
-}
-
-
-
-/*
- * Cleanup resources acquired during i2400m_net_wake_tx()
- *
- * This is called by __i2400m_dev_stop and means we have to make sure
- * the workqueue is flushed from any pending work.
- */
-void i2400m_net_wake_stop(struct i2400m *i2400m)
-{
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *wake_tx_skb;
- unsigned long flags;
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
- /*
- * See i2400m_hard_start_xmit(), references are taken there and
- * here we release them if the packet was still pending.
- */
- cancel_work_sync(&i2400m->wake_tx_ws);
-
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- wake_tx_skb = i2400m->wake_tx_skb;
- i2400m->wake_tx_skb = NULL;
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-
- if (wake_tx_skb) {
- i2400m_put(i2400m);
- kfree_skb(wake_tx_skb);
- }
-
- d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
-
-
-/*
- * TX an skb to an idle device
- *
- * When the device is in basestation-idle mode, we need to wake it up
- * and then TX. So we queue a work_struct for doing so.
- *
- * We need to get an extra ref for the skb (so it is not dropped), as
- * well as be careful not to queue more than one request (won't help
- * at all). If more than one request comes or there are errors, we
- * just drop the packets (see i2400m_hard_start_xmit()).
- */
-static
-int i2400m_net_wake_tx(struct i2400m *i2400m, struct net_device *net_dev,
- struct sk_buff *skb)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- unsigned long flags;
-
- d_fnstart(3, dev, "(skb %p net_dev %p)\n", skb, net_dev);
- if (net_ratelimit()) {
- d_printf(3, dev, "WAKE&NETTX: "
- "skb %p sending %d bytes to radio\n",
- skb, skb->len);
- d_dump(4, dev, skb->data, skb->len);
- }
- /* We hold a ref count for i2400m and skb, so when
- * stopping() the device, we need to cancel that work
- * and if pending, release those resources. */
- result = 0;
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- if (!i2400m->wake_tx_skb) {
- netif_stop_queue(net_dev);
- i2400m_get(i2400m);
- i2400m->wake_tx_skb = skb_get(skb); /* transfer ref count */
- i2400m_tx_prep_header(skb);
- result = schedule_work(&i2400m->wake_tx_ws);
- WARN_ON(result == 0);
- }
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
- if (result == 0) {
- /* Yes, this happens even if we stopped the
- * queue -- blame the queue disciplines that
- * queue without looking -- I guess there is a reason
- * for that. */
- if (net_ratelimit())
- d_printf(1, dev, "NETTX: device exiting idle, "
- "dropping skb %p, queue running %d\n",
- skb, netif_queue_stopped(net_dev));
- result = -EBUSY;
- }
- d_fnend(3, dev, "(skb %p net_dev %p) = %d\n", skb, net_dev, result);
- return result;
-}
-
-
-/*
- * Transmit a packet to the base station on behalf of the network stack.
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * We need to pull the ethernet header and add the hardware header,
- * which is currently set to all zeroes and reserved.
- */
-static
-int i2400m_net_tx(struct i2400m *i2400m, struct net_device *net_dev,
- struct sk_buff *skb)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
-
- d_fnstart(3, dev, "(i2400m %p net_dev %p skb %p)\n",
- i2400m, net_dev, skb);
- /* FIXME: check eth hdr, only IPv4 is routed by the device as of now */
- netif_trans_update(net_dev);
- i2400m_tx_prep_header(skb);
- d_printf(3, dev, "NETTX: skb %p sending %d bytes to radio\n",
- skb, skb->len);
- d_dump(4, dev, skb->data, skb->len);
- result = i2400m_tx(i2400m, skb->data, skb->len, I2400M_PT_DATA);
- d_fnend(3, dev, "(i2400m %p net_dev %p skb %p) = %d\n",
- i2400m, net_dev, skb, result);
- return result;
-}
-
-
-/*
- * Transmit a packet to the base station on behalf of the network stack
- *
- *
- * Returns: NETDEV_TX_OK (always, even in case of error)
- *
- * In case of error, we just drop it. Reasons:
- *
- * - we add a hw header to each skb, and if the network stack
- * retries, we have no way to know if that skb has it or not.
- *
- * - network protocols have their own drop-recovery mechanisms
- *
- * - there is not much else we can do
- *
- * If the device is idle, we need to wake it up; that is an operation
- * that will sleep. See i2400m_net_wake_tx() for details.
- */
-static
-netdev_tx_t i2400m_hard_start_xmit(struct sk_buff *skb,
- struct net_device *net_dev)
-{
- struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
- struct device *dev = i2400m_dev(i2400m);
- int result = -1;
-
- d_fnstart(3, dev, "(skb %p net_dev %p)\n", skb, net_dev);
-
- if (skb_cow_head(skb, 0))
- goto drop;
-
- if (i2400m->state == I2400M_SS_IDLE)
- result = i2400m_net_wake_tx(i2400m, net_dev, skb);
- else
- result = i2400m_net_tx(i2400m, net_dev, skb);
- if (result < 0) {
-drop:
- net_dev->stats.tx_dropped++;
- } else {
- net_dev->stats.tx_packets++;
- net_dev->stats.tx_bytes += skb->len;
- }
- dev_kfree_skb(skb);
- d_fnend(3, dev, "(skb %p net_dev %p) = %d\n", skb, net_dev, result);
- return NETDEV_TX_OK;
-}
-
-
-static
-void i2400m_tx_timeout(struct net_device *net_dev, unsigned int txqueue)
-{
- /*
- * We might want to kick the device
- *
- * There is not much we can do though, as the device requires
- * that we send the data aggregated. By the time we receive
- * this, there might be data pending to be sent or not...
- */
- net_dev->stats.tx_errors++;
-}
-
-
-/*
- * Create a fake ethernet header
- *
- * For emulating an ethernet device, every received IP header has to
- * be prefixed with an ethernet header. Fake it with the given
- * protocol.
- */
-static
-void i2400m_rx_fake_eth_header(struct net_device *net_dev,
- void *_eth_hdr, __be16 protocol)
-{
- struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
- struct ethhdr *eth_hdr = _eth_hdr;
-
- memcpy(eth_hdr->h_dest, net_dev->dev_addr, sizeof(eth_hdr->h_dest));
- memcpy(eth_hdr->h_source, i2400m->src_mac_addr,
- sizeof(eth_hdr->h_source));
- eth_hdr->h_proto = protocol;
-}
-
-
-/*
- * i2400m_net_rx - pass a network packet to the stack
- *
- * @i2400m: device instance
- * @skb_rx: the skb where the buffer pointed to by @buf is
- * @i: 1 if payload is the only one
- * @buf: pointer to the buffer containing the data
- * @len: buffer's length
- *
- * This is only used now for the v1.3 firmware. It will be deprecated
- * in >= 2.6.31.
- *
- * Note that due to firmware limitations, we don't have space to add
- * an ethernet header, so we need to copy each packet. Firmware
- * versions >= v1.4 fix this [see i2400m_net_erx()].
- *
- * We just clone the skb and set it up so that it's skb->data pointer
- * points to "buf" and it's length.
- *
- * Note that if the payload is the last (or the only one) in a
- * multi-payload message, we don't clone the SKB but just reuse it.
- *
- * This function is normally run from a thread context. However, we
- * still use netif_rx() instead of netif_receive_skb() as was
- * recommended in the mailing list. Reason is in some stress tests
- * when sending/receiving a lot of data we seem to hit a softlock in
- * the kernel's TCP implementation [aroudn tcp_delay_timer()]. Using
- * netif_rx() took care of the issue.
- *
- * This is, of course, still open to do more research on why running
- * with netif_receive_skb() hits this softlock. FIXME.
- *
- * FIXME: currently we don't do any efforts at distinguishing if what
- * we got was an IPv4 or IPv6 header, to setup the protocol field
- * correctly.
- */
-void i2400m_net_rx(struct i2400m *i2400m, struct sk_buff *skb_rx,
- unsigned i, const void *buf, int buf_len)
-{
- struct net_device *net_dev = i2400m->wimax_dev.net_dev;
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *skb;
-
- d_fnstart(2, dev, "(i2400m %p buf %p buf_len %d)\n",
- i2400m, buf, buf_len);
- if (i) {
- skb = skb_get(skb_rx);
- d_printf(2, dev, "RX: reusing first payload skb %p\n", skb);
- skb_pull(skb, buf - (void *) skb->data);
- skb_trim(skb, (void *) skb_end_pointer(skb) - buf);
- } else {
- /* Yes, this is bad -- a lot of overhead -- see
- * comments at the top of the file */
- skb = __netdev_alloc_skb(net_dev, buf_len, GFP_KERNEL);
- if (skb == NULL) {
- dev_err(dev, "NETRX: no memory to realloc skb\n");
- net_dev->stats.rx_dropped++;
- goto error_skb_realloc;
- }
- skb_put_data(skb, buf, buf_len);
- }
- i2400m_rx_fake_eth_header(i2400m->wimax_dev.net_dev,
- skb->data - ETH_HLEN,
- cpu_to_be16(ETH_P_IP));
- skb_set_mac_header(skb, -ETH_HLEN);
- skb->dev = i2400m->wimax_dev.net_dev;
- skb->protocol = htons(ETH_P_IP);
- net_dev->stats.rx_packets++;
- net_dev->stats.rx_bytes += buf_len;
- d_printf(3, dev, "NETRX: receiving %d bytes to network stack\n",
- buf_len);
- d_dump(4, dev, buf, buf_len);
- netif_rx_ni(skb); /* see notes in function header */
-error_skb_realloc:
- d_fnend(2, dev, "(i2400m %p buf %p buf_len %d) = void\n",
- i2400m, buf, buf_len);
-}
-
-
-/*
- * i2400m_net_erx - pass a network packet to the stack (extended version)
- *
- * @i2400m: device descriptor
- * @skb: the skb where the packet is - the skb should be set to point
- * at the IP packet; this function will add ethernet headers if
- * needed.
- * @cs: packet type
- *
- * This is only used now for firmware >= v1.4. Note it is quite
- * similar to i2400m_net_rx() (used only for v1.3 firmware).
- *
- * This function is normally run from a thread context. However, we
- * still use netif_rx() instead of netif_receive_skb() as was
- * recommended in the mailing list. Reason is in some stress tests
- * when sending/receiving a lot of data we seem to hit a softlock in
- * the kernel's TCP implementation [aroudn tcp_delay_timer()]. Using
- * netif_rx() took care of the issue.
- *
- * This is, of course, still open to do more research on why running
- * with netif_receive_skb() hits this softlock. FIXME.
- */
-void i2400m_net_erx(struct i2400m *i2400m, struct sk_buff *skb,
- enum i2400m_cs cs)
-{
- struct net_device *net_dev = i2400m->wimax_dev.net_dev;
- struct device *dev = i2400m_dev(i2400m);
-
- d_fnstart(2, dev, "(i2400m %p skb %p [%u] cs %d)\n",
- i2400m, skb, skb->len, cs);
- switch(cs) {
- case I2400M_CS_IPV4_0:
- case I2400M_CS_IPV4:
- i2400m_rx_fake_eth_header(i2400m->wimax_dev.net_dev,
- skb->data - ETH_HLEN,
- cpu_to_be16(ETH_P_IP));
- skb_set_mac_header(skb, -ETH_HLEN);
- skb->dev = i2400m->wimax_dev.net_dev;
- skb->protocol = htons(ETH_P_IP);
- net_dev->stats.rx_packets++;
- net_dev->stats.rx_bytes += skb->len;
- break;
- default:
- dev_err(dev, "ERX: BUG? CS type %u unsupported\n", cs);
- goto error;
-
- }
- d_printf(3, dev, "ERX: receiving %d bytes to the network stack\n",
- skb->len);
- d_dump(4, dev, skb->data, skb->len);
- netif_rx_ni(skb); /* see notes in function header */
-error:
- d_fnend(2, dev, "(i2400m %p skb %p [%u] cs %d) = void\n",
- i2400m, skb, skb->len, cs);
-}
-
-static const struct net_device_ops i2400m_netdev_ops = {
- .ndo_open = i2400m_open,
- .ndo_stop = i2400m_stop,
- .ndo_start_xmit = i2400m_hard_start_xmit,
- .ndo_tx_timeout = i2400m_tx_timeout,
-};
-
-static void i2400m_get_drvinfo(struct net_device *net_dev,
- struct ethtool_drvinfo *info)
-{
- struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
-
- strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
- strlcpy(info->fw_version, i2400m->fw_name ? : "",
- sizeof(info->fw_version));
- if (net_dev->dev.parent)
- strlcpy(info->bus_info, dev_name(net_dev->dev.parent),
- sizeof(info->bus_info));
-}
-
-static const struct ethtool_ops i2400m_ethtool_ops = {
- .get_drvinfo = i2400m_get_drvinfo,
- .get_link = ethtool_op_get_link,
-};
-
-/**
- * i2400m_netdev_setup - Setup setup @net_dev's i2400m private data
- *
- * Called by alloc_netdev()
- */
-void i2400m_netdev_setup(struct net_device *net_dev)
-{
- d_fnstart(3, NULL, "(net_dev %p)\n", net_dev);
- ether_setup(net_dev);
- net_dev->mtu = I2400M_MAX_MTU;
- net_dev->min_mtu = 0;
- net_dev->max_mtu = I2400M_MAX_MTU;
- net_dev->tx_queue_len = I2400M_TX_QLEN;
- net_dev->features =
- NETIF_F_VLAN_CHALLENGED
- | NETIF_F_HIGHDMA;
- net_dev->flags =
- IFF_NOARP /* i2400m is apure IP device */
- & (~IFF_BROADCAST /* i2400m is P2P */
- & ~IFF_MULTICAST);
- net_dev->watchdog_timeo = I2400M_TX_TIMEOUT;
- net_dev->netdev_ops = &i2400m_netdev_ops;
- net_dev->ethtool_ops = &i2400m_ethtool_ops;
- d_fnend(3, NULL, "(net_dev %p) = void\n", net_dev);
-}
-EXPORT_SYMBOL_GPL(i2400m_netdev_setup);
-
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Implement backend for the WiMAX stack rfkill support
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * The WiMAX kernel stack integrates into RF-Kill and keeps the
- * switches's status. We just need to:
- *
- * - report changes in the HW RF Kill switch [with
- * wimax_rfkill_{sw,hw}_report(), which happens when we detect those
- * indications coming through hardware reports]. We also do it on
- * initialization to let the stack know the initial HW state.
- *
- * - implement indications from the stack to change the SW RF Kill
- * switch (coming from sysfs, the wimax stack or user space).
- */
-#include "i2400m.h"
-#include <linux/wimax/i2400m.h>
-#include <linux/slab.h>
-
-
-
-#define D_SUBMODULE rfkill
-#include "debug-levels.h"
-
-/*
- * Return true if the i2400m radio is in the requested wimax_rf_state state
- *
- */
-static
-int i2400m_radio_is(struct i2400m *i2400m, enum wimax_rf_state state)
-{
- if (state == WIMAX_RF_OFF)
- return i2400m->state == I2400M_SS_RF_OFF
- || i2400m->state == I2400M_SS_RF_SHUTDOWN;
- else if (state == WIMAX_RF_ON)
- /* state == WIMAX_RF_ON */
- return i2400m->state != I2400M_SS_RF_OFF
- && i2400m->state != I2400M_SS_RF_SHUTDOWN;
- else {
- BUG();
- return -EINVAL; /* shut gcc warnings on certain arches */
- }
-}
-
-
-/*
- * WiMAX stack operation: implement SW RFKill toggling
- *
- * @wimax_dev: device descriptor
- * @skb: skb where the message has been received; skb->data is
- * expected to point to the message payload.
- * @genl_info: passed by the generic netlink layer
- *
- * Generic Netlink will call this function when a message is sent from
- * userspace to change the software RF-Kill switch status.
- *
- * This function will set the device's software RF-Kill switch state to
- * match what is requested.
- *
- * NOTE: the i2400m has a strict state machine; we can only set the
- * RF-Kill switch when it is on, the HW RF-Kill is on and the
- * device is initialized. So we ignore errors steaming from not
- * being in the right state (-EILSEQ).
- */
-int i2400m_op_rfkill_sw_toggle(struct wimax_dev *wimax_dev,
- enum wimax_rf_state state)
-{
- int result;
- struct i2400m *i2400m = wimax_dev_to_i2400m(wimax_dev);
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *ack_skb;
- struct {
- struct i2400m_l3l4_hdr hdr;
- struct i2400m_tlv_rf_operation sw_rf;
- } __packed *cmd;
- char strerr[32];
-
- d_fnstart(4, dev, "(wimax_dev %p state %d)\n", wimax_dev, state);
-
- result = -ENOMEM;
- cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
- if (cmd == NULL)
- goto error_alloc;
- cmd->hdr.type = cpu_to_le16(I2400M_MT_CMD_RF_CONTROL);
- cmd->hdr.length = sizeof(cmd->sw_rf);
- cmd->hdr.version = cpu_to_le16(I2400M_L3L4_VERSION);
- cmd->sw_rf.hdr.type = cpu_to_le16(I2400M_TLV_RF_OPERATION);
- cmd->sw_rf.hdr.length = cpu_to_le16(sizeof(cmd->sw_rf.status));
- switch (state) {
- case WIMAX_RF_OFF: /* RFKILL ON, radio OFF */
- cmd->sw_rf.status = cpu_to_le32(2);
- break;
- case WIMAX_RF_ON: /* RFKILL OFF, radio ON */
- cmd->sw_rf.status = cpu_to_le32(1);
- break;
- default:
- BUG();
- }
-
- ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
- result = PTR_ERR(ack_skb);
- if (IS_ERR(ack_skb)) {
- dev_err(dev, "Failed to issue 'RF Control' command: %d\n",
- result);
- goto error_msg_to_dev;
- }
- result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
- strerr, sizeof(strerr));
- if (result < 0) {
- dev_err(dev, "'RF Control' (0x%04x) command failed: %d - %s\n",
- I2400M_MT_CMD_RF_CONTROL, result, strerr);
- goto error_cmd;
- }
-
- /* Now we wait for the state to change to RADIO_OFF or RADIO_ON */
- result = wait_event_timeout(
- i2400m->state_wq, i2400m_radio_is(i2400m, state),
- 5 * HZ);
- if (result == 0)
- result = -ETIMEDOUT;
- if (result < 0)
- dev_err(dev, "Error waiting for device to toggle RF state: "
- "%d\n", result);
- result = 0;
-error_cmd:
- kfree_skb(ack_skb);
-error_msg_to_dev:
-error_alloc:
- d_fnend(4, dev, "(wimax_dev %p state %d) = %d\n",
- wimax_dev, state, result);
- kfree(cmd);
- return result;
-}
-
-
-/*
- * Inform the WiMAX stack of changes in the RF Kill switches reported
- * by the device
- *
- * @i2400m: device descriptor
- * @rfss: TLV for RF Switches status; already validated
- *
- * NOTE: the reports on RF switch status cannot be trusted
- * or used until the device is in a state of RADIO_OFF
- * or greater.
- */
-void i2400m_report_tlv_rf_switches_status(
- struct i2400m *i2400m,
- const struct i2400m_tlv_rf_switches_status *rfss)
-{
- struct device *dev = i2400m_dev(i2400m);
- enum i2400m_rf_switch_status hw, sw;
- enum wimax_st wimax_state;
-
- sw = le32_to_cpu(rfss->sw_rf_switch);
- hw = le32_to_cpu(rfss->hw_rf_switch);
-
- d_fnstart(3, dev, "(i2400m %p rfss %p [hw %u sw %u])\n",
- i2400m, rfss, hw, sw);
- /* We only process rw switch evens when the device has been
- * fully initialized */
- wimax_state = wimax_state_get(&i2400m->wimax_dev);
- if (wimax_state < WIMAX_ST_RADIO_OFF) {
- d_printf(3, dev, "ignoring RF switches report, state %u\n",
- wimax_state);
- goto out;
- }
- switch (sw) {
- case I2400M_RF_SWITCH_ON: /* RF Kill disabled (radio on) */
- wimax_report_rfkill_sw(&i2400m->wimax_dev, WIMAX_RF_ON);
- break;
- case I2400M_RF_SWITCH_OFF: /* RF Kill enabled (radio off) */
- wimax_report_rfkill_sw(&i2400m->wimax_dev, WIMAX_RF_OFF);
- break;
- default:
- dev_err(dev, "HW BUG? Unknown RF SW state 0x%x\n", sw);
- }
-
- switch (hw) {
- case I2400M_RF_SWITCH_ON: /* RF Kill disabled (radio on) */
- wimax_report_rfkill_hw(&i2400m->wimax_dev, WIMAX_RF_ON);
- break;
- case I2400M_RF_SWITCH_OFF: /* RF Kill enabled (radio off) */
- wimax_report_rfkill_hw(&i2400m->wimax_dev, WIMAX_RF_OFF);
- break;
- default:
- dev_err(dev, "HW BUG? Unknown RF HW state 0x%x\n", hw);
- }
-out:
- d_fnend(3, dev, "(i2400m %p rfss %p [hw %u sw %u]) = void\n",
- i2400m, rfss, hw, sw);
-}
+++ /dev/null
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Handle incoming traffic and deliver it to the control or data planes
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * - Initial implementation
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * - Use skb_clone(), break up processing in chunks
- * - Split transport/device specific
- * - Make buffer size dynamic to exert less memory pressure
- * - RX reorder support
- *
- * This handles the RX path.
- *
- * We receive an RX message from the bus-specific driver, which
- * contains one or more payloads that have potentially different
- * destinataries (data or control paths).
- *
- * So we just take that payload from the transport specific code in
- * the form of an skb, break it up in chunks (a cloned skb each in the
- * case of network packets) and pass it to netdev or to the
- * command/ack handler (and from there to the WiMAX stack).
- *
- * PROTOCOL FORMAT
- *
- * The format of the buffer is:
- *
- * HEADER (struct i2400m_msg_hdr)
- * PAYLOAD DESCRIPTOR 0 (struct i2400m_pld)
- * PAYLOAD DESCRIPTOR 1
- * ...
- * PAYLOAD DESCRIPTOR N
- * PAYLOAD 0 (raw bytes)
- * PAYLOAD 1
- * ...
- * PAYLOAD N
- *
- * See tx.c for a deeper description on alignment requirements and
- * other fun facts of it.
- *
- * DATA PACKETS
- *
- * In firmwares <= v1.3, data packets have no header for RX, but they
- * do for TX (currently unused).
- *
- * In firmware >= 1.4, RX packets have an extended header (16
- * bytes). This header conveys information for management of host
- * reordering of packets (the device offloads storage of the packets
- * for reordering to the host). Read below for more information.
- *
- * The header is used as dummy space to emulate an ethernet header and
- * thus be able to act as an ethernet device without having to reallocate.
- *
- * DATA RX REORDERING
- *
- * Starting in firmware v1.4, the device can deliver packets for
- * delivery with special reordering information; this allows it to
- * more effectively do packet management when some frames were lost in
- * the radio traffic.
- *
- * Thus, for RX packets that come out of order, the device gives the
- * driver enough information to queue them properly and then at some
- * point, the signal to deliver the whole (or part) of the queued
- * packets to the networking stack. There are 16 such queues.
- *
- * This only happens when a packet comes in with the "need reorder"
- * flag set in the RX header. When such bit is set, the following
- * operations might be indicated:
- *
- * - reset queue: send all queued packets to the OS
- *
- * - queue: queue a packet
- *
- * - update ws: update the queue's window start and deliver queued
- * packets that meet the criteria
- *
- * - queue & update ws: queue a packet, update the window start and
- * deliver queued packets that meet the criteria
- *
- * (delivery criteria: the packet's [normalized] sequence number is
- * lower than the new [normalized] window start).
- *
- * See the i2400m_roq_*() functions for details.
- *
- * ROADMAP
- *
- * i2400m_rx
- * i2400m_rx_msg_hdr_check
- * i2400m_rx_pl_descr_check
- * i2400m_rx_payload
- * i2400m_net_rx
- * i2400m_rx_edata
- * i2400m_net_erx
- * i2400m_roq_reset
- * i2400m_net_erx
- * i2400m_roq_queue
- * __i2400m_roq_queue
- * i2400m_roq_update_ws
- * __i2400m_roq_update_ws
- * i2400m_net_erx
- * i2400m_roq_queue_update_ws
- * __i2400m_roq_queue
- * __i2400m_roq_update_ws
- * i2400m_net_erx
- * i2400m_rx_ctl
- * i2400m_msg_size_check
- * i2400m_report_hook_work [in a workqueue]
- * i2400m_report_hook
- * wimax_msg_to_user
- * i2400m_rx_ctl_ack
- * wimax_msg_to_user_alloc
- * i2400m_rx_trace
- * i2400m_msg_size_check
- * wimax_msg
- */
-#include <linux/slab.h>
-#include <linux/kernel.h>
-#include <linux/if_arp.h>
-#include <linux/netdevice.h>
-#include <linux/workqueue.h>
-#include <linux/export.h>
-#include <linux/moduleparam.h>
-#include "i2400m.h"
-
-
-#define D_SUBMODULE rx
-#include "debug-levels.h"
-
-static int i2400m_rx_reorder_disabled; /* 0 (rx reorder enabled) by default */
-module_param_named(rx_reorder_disabled, i2400m_rx_reorder_disabled, int, 0644);
-MODULE_PARM_DESC(rx_reorder_disabled,
- "If true, RX reordering will be disabled.");
-
-struct i2400m_report_hook_args {
- struct sk_buff *skb_rx;
- const struct i2400m_l3l4_hdr *l3l4_hdr;
- size_t size;
- struct list_head list_node;
-};
-
-
-/*
- * Execute i2400m_report_hook in a workqueue
- *
- * Goes over the list of queued reports in i2400m->rx_reports and
- * processes them.
- *
- * NOTE: refcounts on i2400m are not needed because we flush the
- * workqueue this runs on (i2400m->work_queue) before destroying
- * i2400m.
- */
-void i2400m_report_hook_work(struct work_struct *ws)
-{
- struct i2400m *i2400m = container_of(ws, struct i2400m, rx_report_ws);
- struct device *dev = i2400m_dev(i2400m);
- struct i2400m_report_hook_args *args, *args_next;
- LIST_HEAD(list);
- unsigned long flags;
-
- while (1) {
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- list_splice_init(&i2400m->rx_reports, &list);
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- if (list_empty(&list))
- break;
- else
- d_printf(1, dev, "processing queued reports\n");
- list_for_each_entry_safe(args, args_next, &list, list_node) {
- d_printf(2, dev, "processing queued report %p\n", args);
- i2400m_report_hook(i2400m, args->l3l4_hdr, args->size);
- kfree_skb(args->skb_rx);
- list_del(&args->list_node);
- kfree(args);
- }
- }
-}
-
-
-/*
- * Flush the list of queued reports
- */
-static
-void i2400m_report_hook_flush(struct i2400m *i2400m)
-{
- struct device *dev = i2400m_dev(i2400m);
- struct i2400m_report_hook_args *args, *args_next;
- LIST_HEAD(list);
- unsigned long flags;
-
- d_printf(1, dev, "flushing queued reports\n");
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- list_splice_init(&i2400m->rx_reports, &list);
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- list_for_each_entry_safe(args, args_next, &list, list_node) {
- d_printf(2, dev, "flushing queued report %p\n", args);
- kfree_skb(args->skb_rx);
- list_del(&args->list_node);
- kfree(args);
- }
-}
-
-
-/*
- * Queue a report for later processing
- *
- * @i2400m: device descriptor
- * @skb_rx: skb that contains the payload (for reference counting)
- * @l3l4_hdr: pointer to the control
- * @size: size of the message
- */
-static
-void i2400m_report_hook_queue(struct i2400m *i2400m, struct sk_buff *skb_rx,
- const void *l3l4_hdr, size_t size)
-{
- struct device *dev = i2400m_dev(i2400m);
- unsigned long flags;
- struct i2400m_report_hook_args *args;
-
- args = kzalloc(sizeof(*args), GFP_NOIO);
- if (args) {
- args->skb_rx = skb_get(skb_rx);
- args->l3l4_hdr = l3l4_hdr;
- args->size = size;
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- list_add_tail(&args->list_node, &i2400m->rx_reports);
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- d_printf(2, dev, "queued report %p\n", args);
- rmb(); /* see i2400m->ready's documentation */
- if (likely(i2400m->ready)) /* only send if up */
- queue_work(i2400m->work_queue, &i2400m->rx_report_ws);
- } else {
- if (printk_ratelimit())
- dev_err(dev, "%s:%u: Can't allocate %zu B\n",
- __func__, __LINE__, sizeof(*args));
- }
-}
-
-
-/*
- * Process an ack to a command
- *
- * @i2400m: device descriptor
- * @payload: pointer to message
- * @size: size of the message
- *
- * Pass the acknodledgment (in an skb) to the thread that is waiting
- * for it in i2400m->msg_completion.
- *
- * We need to coordinate properly with the thread waiting for the
- * ack. Check if it is waiting or if it is gone. We loose the spinlock
- * to avoid allocating on atomic contexts (yeah, could use GFP_ATOMIC,
- * but this is not so speed critical).
- */
-static
-void i2400m_rx_ctl_ack(struct i2400m *i2400m,
- const void *payload, size_t size)
-{
- struct device *dev = i2400m_dev(i2400m);
- struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
- unsigned long flags;
- struct sk_buff *ack_skb;
-
- /* Anyone waiting for an answer? */
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- if (i2400m->ack_skb != ERR_PTR(-EINPROGRESS)) {
- dev_err(dev, "Huh? reply to command with no waiters\n");
- goto error_no_waiter;
- }
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-
- ack_skb = wimax_msg_alloc(wimax_dev, NULL, payload, size, GFP_KERNEL);
-
- /* Check waiter didn't time out waiting for the answer... */
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- if (i2400m->ack_skb != ERR_PTR(-EINPROGRESS)) {
- d_printf(1, dev, "Huh? waiter for command reply cancelled\n");
- goto error_waiter_cancelled;
- }
- if (IS_ERR(ack_skb))
- dev_err(dev, "CMD/GET/SET ack: cannot allocate SKB\n");
- i2400m->ack_skb = ack_skb;
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- complete(&i2400m->msg_completion);
- return;
-
-error_waiter_cancelled:
- if (!IS_ERR(ack_skb))
- kfree_skb(ack_skb);
-error_no_waiter:
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-}
-
-
-/*
- * Receive and process a control payload
- *
- * @i2400m: device descriptor
- * @skb_rx: skb that contains the payload (for reference counting)
- * @payload: pointer to message
- * @size: size of the message
- *
- * There are two types of control RX messages: reports (asynchronous,
- * like your every day interrupts) and 'acks' (reponses to a command,
- * get or set request).
- *
- * If it is a report, we run hooks on it (to extract information for
- * things we need to do in the driver) and then pass it over to the
- * WiMAX stack to send it to user space.
- *
- * NOTE: report processing is done in a workqueue specific to the
- * generic driver, to avoid deadlocks in the system.
- *
- * If it is not a report, it is an ack to a previously executed
- * command, set or get, so wake up whoever is waiting for it from
- * i2400m_msg_to_dev(). i2400m_rx_ctl_ack() takes care of that.
- *
- * Note that the sizes we pass to other functions from here are the
- * sizes of the _l3l4_hdr + payload, not full buffer sizes, as we have
- * verified in _msg_size_check() that they are congruent.
- *
- * For reports: We can't clone the original skb where the data is
- * because we need to send this up via netlink; netlink has to add
- * headers and we can't overwrite what's preceding the payload...as
- * it is another message. So we just dup them.
- */
-static
-void i2400m_rx_ctl(struct i2400m *i2400m, struct sk_buff *skb_rx,
- const void *payload, size_t size)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- const struct i2400m_l3l4_hdr *l3l4_hdr = payload;
- unsigned msg_type;
-
- result = i2400m_msg_size_check(i2400m, l3l4_hdr, size);
- if (result < 0) {
- dev_err(dev, "HW BUG? device sent a bad message: %d\n",
- result);
- goto error_check;
- }
- msg_type = le16_to_cpu(l3l4_hdr->type);
- d_printf(1, dev, "%s 0x%04x: %zu bytes\n",
- msg_type & I2400M_MT_REPORT_MASK ? "REPORT" : "CMD/SET/GET",
- msg_type, size);
- d_dump(2, dev, l3l4_hdr, size);
- if (msg_type & I2400M_MT_REPORT_MASK) {
- /*
- * Process each report
- *
- * - has to be ran serialized as well
- *
- * - the handling might force the execution of
- * commands. That might cause reentrancy issues with
- * bus-specific subdrivers and workqueues, so the we
- * run it in a separate workqueue.
- *
- * - when the driver is not yet ready to handle them,
- * they are queued and at some point the queue is
- * restarted [NOTE: we can't queue SKBs directly, as
- * this might be a piece of a SKB, not the whole
- * thing, and this is cheaper than cloning the
- * SKB].
- *
- * Note we don't do refcounting for the device
- * structure; this is because before destroying
- * 'i2400m', we make sure to flush the
- * i2400m->work_queue, so there are no issues.
- */
- i2400m_report_hook_queue(i2400m, skb_rx, l3l4_hdr, size);
- if (unlikely(i2400m->trace_msg_from_user))
- wimax_msg(&i2400m->wimax_dev, "echo",
- l3l4_hdr, size, GFP_KERNEL);
- result = wimax_msg(&i2400m->wimax_dev, NULL, l3l4_hdr, size,
- GFP_KERNEL);
- if (result < 0)
- dev_err(dev, "error sending report to userspace: %d\n",
- result);
- } else /* an ack to a CMD, GET or SET */
- i2400m_rx_ctl_ack(i2400m, payload, size);
-error_check:
- return;
-}
-
-
-/*
- * Receive and send up a trace
- *
- * @i2400m: device descriptor
- * @skb_rx: skb that contains the trace (for reference counting)
- * @payload: pointer to trace message inside the skb
- * @size: size of the message
- *
- * THe i2400m might produce trace information (diagnostics) and we
- * send them through a different kernel-to-user pipe (to avoid
- * clogging it).
- *
- * As in i2400m_rx_ctl(), we can't clone the original skb where the
- * data is because we need to send this up via netlink; netlink has to
- * add headers and we can't overwrite what's preceding the
- * payload...as it is another message. So we just dup them.
- */
-static
-void i2400m_rx_trace(struct i2400m *i2400m,
- const void *payload, size_t size)
-{
- int result;
- struct device *dev = i2400m_dev(i2400m);
- struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
- const struct i2400m_l3l4_hdr *l3l4_hdr = payload;
- unsigned msg_type;
-
- result = i2400m_msg_size_check(i2400m, l3l4_hdr, size);
- if (result < 0) {
- dev_err(dev, "HW BUG? device sent a bad trace message: %d\n",
- result);
- goto error_check;
- }
- msg_type = le16_to_cpu(l3l4_hdr->type);
- d_printf(1, dev, "Trace %s 0x%04x: %zu bytes\n",
- msg_type & I2400M_MT_REPORT_MASK ? "REPORT" : "CMD/SET/GET",
- msg_type, size);
- d_dump(2, dev, l3l4_hdr, size);
- result = wimax_msg(wimax_dev, "trace", l3l4_hdr, size, GFP_KERNEL);
- if (result < 0)
- dev_err(dev, "error sending trace to userspace: %d\n",
- result);
-error_check:
- return;
-}
-
-
-/*
- * Reorder queue data stored on skb->cb while the skb is queued in the
- * reorder queues.
- */
-struct i2400m_roq_data {
- unsigned sn; /* Serial number for the skb */
- enum i2400m_cs cs; /* packet type for the skb */
-};
-
-
-/*
- * ReOrder Queue
- *
- * @ws: Window Start; sequence number where the current window start
- * is for this queue
- * @queue: the skb queue itself
- * @log: circular ring buffer used to log information about the
- * reorder process in this queue that can be displayed in case of
- * error to help diagnose it.
- *
- * This is the head for a list of skbs. In the skb->cb member of the
- * skb when queued here contains a 'struct i2400m_roq_data' were we
- * store the sequence number (sn) and the cs (packet type) coming from
- * the RX payload header from the device.
- */
-struct i2400m_roq
-{
- unsigned ws;
- struct sk_buff_head queue;
- struct i2400m_roq_log *log;
-};
-
-
-static
-void __i2400m_roq_init(struct i2400m_roq *roq)
-{
- roq->ws = 0;
- skb_queue_head_init(&roq->queue);
-}
-
-
-static
-unsigned __i2400m_roq_index(struct i2400m *i2400m, struct i2400m_roq *roq)
-{
- return ((unsigned long) roq - (unsigned long) i2400m->rx_roq)
- / sizeof(*roq);
-}
-
-
-/*
- * Normalize a sequence number based on the queue's window start
- *
- * nsn = (sn - ws) % 2048
- *
- * Note that if @sn < @roq->ws, we still need a positive number; %'s
- * sign is implementation specific, so we normalize it by adding 2048
- * to bring it to be positive.
- */
-static
-unsigned __i2400m_roq_nsn(struct i2400m_roq *roq, unsigned sn)
-{
- int r;
- r = ((int) sn - (int) roq->ws) % 2048;
- if (r < 0)
- r += 2048;
- return r;
-}
-
-
-/*
- * Circular buffer to keep the last N reorder operations
- *
- * In case something fails, dumb then to try to come up with what
- * happened.
- */
-enum {
- I2400M_ROQ_LOG_LENGTH = 32,
-};
-
-struct i2400m_roq_log {
- struct i2400m_roq_log_entry {
- enum i2400m_ro_type type;
- unsigned ws, count, sn, nsn, new_ws;
- } entry[I2400M_ROQ_LOG_LENGTH];
- unsigned in, out;
-};
-
-
-/* Print a log entry */
-static
-void i2400m_roq_log_entry_print(struct i2400m *i2400m, unsigned index,
- unsigned e_index,
- struct i2400m_roq_log_entry *e)
-{
- struct device *dev = i2400m_dev(i2400m);
-
- switch(e->type) {
- case I2400M_RO_TYPE_RESET:
- dev_err(dev, "q#%d reset ws %u cnt %u sn %u/%u"
- " - new nws %u\n",
- index, e->ws, e->count, e->sn, e->nsn, e->new_ws);
- break;
- case I2400M_RO_TYPE_PACKET:
- dev_err(dev, "q#%d queue ws %u cnt %u sn %u/%u\n",
- index, e->ws, e->count, e->sn, e->nsn);
- break;
- case I2400M_RO_TYPE_WS:
- dev_err(dev, "q#%d update_ws ws %u cnt %u sn %u/%u"
- " - new nws %u\n",
- index, e->ws, e->count, e->sn, e->nsn, e->new_ws);
- break;
- case I2400M_RO_TYPE_PACKET_WS:
- dev_err(dev, "q#%d queue_update_ws ws %u cnt %u sn %u/%u"
- " - new nws %u\n",
- index, e->ws, e->count, e->sn, e->nsn, e->new_ws);
- break;
- default:
- dev_err(dev, "q#%d BUG? entry %u - unknown type %u\n",
- index, e_index, e->type);
- break;
- }
-}
-
-
-static
-void i2400m_roq_log_add(struct i2400m *i2400m,
- struct i2400m_roq *roq, enum i2400m_ro_type type,
- unsigned ws, unsigned count, unsigned sn,
- unsigned nsn, unsigned new_ws)
-{
- struct i2400m_roq_log_entry *e;
- unsigned cnt_idx;
- int index = __i2400m_roq_index(i2400m, roq);
-
- /* if we run out of space, we eat from the end */
- if (roq->log->in - roq->log->out == I2400M_ROQ_LOG_LENGTH)
- roq->log->out++;
- cnt_idx = roq->log->in++ % I2400M_ROQ_LOG_LENGTH;
- e = &roq->log->entry[cnt_idx];
-
- e->type = type;
- e->ws = ws;
- e->count = count;
- e->sn = sn;
- e->nsn = nsn;
- e->new_ws = new_ws;
-
- if (d_test(1))
- i2400m_roq_log_entry_print(i2400m, index, cnt_idx, e);
-}
-
-
-/* Dump all the entries in the FIFO and reinitialize it */
-static
-void i2400m_roq_log_dump(struct i2400m *i2400m, struct i2400m_roq *roq)
-{
- unsigned cnt, cnt_idx;
- struct i2400m_roq_log_entry *e;
- int index = __i2400m_roq_index(i2400m, roq);
-
- BUG_ON(roq->log->out > roq->log->in);
- for (cnt = roq->log->out; cnt < roq->log->in; cnt++) {
- cnt_idx = cnt % I2400M_ROQ_LOG_LENGTH;
- e = &roq->log->entry[cnt_idx];
- i2400m_roq_log_entry_print(i2400m, index, cnt_idx, e);
- memset(e, 0, sizeof(*e));
- }
- roq->log->in = roq->log->out = 0;
-}
-
-
-/*
- * Backbone for the queuing of an skb (by normalized sequence number)
- *
- * @i2400m: device descriptor
- * @roq: reorder queue where to add
- * @skb: the skb to add
- * @sn: the sequence number of the skb
- * @nsn: the normalized sequence number of the skb (pre-computed by the
- * caller from the @sn and @roq->ws).
- *
- * We try first a couple of quick cases:
- *
- * - the queue is empty
- * - the skb would be appended to the queue
- *
- * These will be the most common operations.
- *
- * If these fail, then we have to do a sorted insertion in the queue,
- * which is the slowest path.
- *
- * We don't have to acquire a reference count as we are going to own it.
- */
-static
-void __i2400m_roq_queue(struct i2400m *i2400m, struct i2400m_roq *roq,
- struct sk_buff *skb, unsigned sn, unsigned nsn)
-{
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *skb_itr;
- struct i2400m_roq_data *roq_data_itr, *roq_data;
- unsigned nsn_itr;
-
- d_fnstart(4, dev, "(i2400m %p roq %p skb %p sn %u nsn %u)\n",
- i2400m, roq, skb, sn, nsn);
-
- roq_data = (struct i2400m_roq_data *) &skb->cb;
- BUILD_BUG_ON(sizeof(*roq_data) > sizeof(skb->cb));
- roq_data->sn = sn;
- d_printf(3, dev, "ERX: roq %p [ws %u] nsn %d sn %u\n",
- roq, roq->ws, nsn, roq_data->sn);
-
- /* Queues will be empty on not-so-bad environments, so try
- * that first */
- if (skb_queue_empty(&roq->queue)) {
- d_printf(2, dev, "ERX: roq %p - first one\n", roq);
- __skb_queue_head(&roq->queue, skb);
- goto out;
- }
- /* Now try append, as most of the operations will be that */
- skb_itr = skb_peek_tail(&roq->queue);
- roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
- nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
- /* NSN bounds assumed correct (checked when it was queued) */
- if (nsn >= nsn_itr) {
- d_printf(2, dev, "ERX: roq %p - appended after %p (nsn %d sn %u)\n",
- roq, skb_itr, nsn_itr, roq_data_itr->sn);
- __skb_queue_tail(&roq->queue, skb);
- goto out;
- }
- /* None of the fast paths option worked. Iterate to find the
- * right spot where to insert the packet; we know the queue is
- * not empty, so we are not the first ones; we also know we
- * are not going to be the last ones. The list is sorted, so
- * we have to insert before the the first guy with an nsn_itr
- * greater that our nsn. */
- skb_queue_walk(&roq->queue, skb_itr) {
- roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
- nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
- /* NSN bounds assumed correct (checked when it was queued) */
- if (nsn_itr > nsn) {
- d_printf(2, dev, "ERX: roq %p - queued before %p "
- "(nsn %d sn %u)\n", roq, skb_itr, nsn_itr,
- roq_data_itr->sn);
- __skb_queue_before(&roq->queue, skb_itr, skb);
- goto out;
- }
- }
- /* If we get here, that is VERY bad -- print info to help
- * diagnose and crash it */
- dev_err(dev, "SW BUG? failed to insert packet\n");
- dev_err(dev, "ERX: roq %p [ws %u] skb %p nsn %d sn %u\n",
- roq, roq->ws, skb, nsn, roq_data->sn);
- skb_queue_walk(&roq->queue, skb_itr) {
- roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
- nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
- /* NSN bounds assumed correct (checked when it was queued) */
- dev_err(dev, "ERX: roq %p skb_itr %p nsn %d sn %u\n",
- roq, skb_itr, nsn_itr, roq_data_itr->sn);
- }
- BUG();
-out:
- d_fnend(4, dev, "(i2400m %p roq %p skb %p sn %u nsn %d) = void\n",
- i2400m, roq, skb, sn, nsn);
-}
-
-
-/*
- * Backbone for the update window start operation
- *
- * @i2400m: device descriptor
- * @roq: Reorder queue
- * @sn: New sequence number
- *
- * Updates the window start of a queue; when doing so, it must deliver
- * to the networking stack all the queued skb's whose normalized
- * sequence number is lower than the new normalized window start.
- */
-static
-unsigned __i2400m_roq_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
- unsigned sn)
-{
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *skb_itr, *tmp_itr;
- struct i2400m_roq_data *roq_data_itr;
- unsigned new_nws, nsn_itr;
-
- new_nws = __i2400m_roq_nsn(roq, sn);
- /*
- * For type 2(update_window_start) rx messages, there is no
- * need to check if the normalized sequence number is greater 1023.
- * Simply insert and deliver all packets to the host up to the
- * window start.
- */
- skb_queue_walk_safe(&roq->queue, skb_itr, tmp_itr) {
- roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
- nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
- /* NSN bounds assumed correct (checked when it was queued) */
- if (nsn_itr < new_nws) {
- d_printf(2, dev, "ERX: roq %p - release skb %p "
- "(nsn %u/%u new nws %u)\n",
- roq, skb_itr, nsn_itr, roq_data_itr->sn,
- new_nws);
- __skb_unlink(skb_itr, &roq->queue);
- i2400m_net_erx(i2400m, skb_itr, roq_data_itr->cs);
- }
- else
- break; /* rest of packets all nsn_itr > nws */
- }
- roq->ws = sn;
- return new_nws;
-}
-
-
-/*
- * Reset a queue
- *
- * @i2400m: device descriptor
- * @cin: Queue Index
- *
- * Deliver all the packets and reset the window-start to zero. Name is
- * kind of misleading.
- */
-static
-void i2400m_roq_reset(struct i2400m *i2400m, struct i2400m_roq *roq)
-{
- struct device *dev = i2400m_dev(i2400m);
- struct sk_buff *skb_itr, *tmp_itr;
- struct i2400m_roq_data *roq_data_itr;
-
- d_fnstart(2, dev, "(i2400m %p roq %p)\n", i2400m, roq);
- i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_RESET,
- roq->ws, skb_queue_len(&roq->queue),
- ~0, ~0, 0);
- skb_queue_walk_safe(&roq->queue, skb_itr, tmp_itr) {
- roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
- d_printf(2, dev, "ERX: roq %p - release skb %p (sn %u)\n",
- roq, skb_itr, roq_data_itr->sn);
- __skb_unlink(skb_itr, &roq->queue);
- i2400m_net_erx(i2400m, skb_itr, roq_data_itr->cs);
- }
- roq->ws = 0;
- d_fnend(2, dev, "(i2400m %p roq %p) = void\n", i2400m, roq);
-}
-
-
-/*
- * Queue a packet
- *
- * @i2400m: device descriptor
- * @cin: Queue Index
- * @skb: containing the packet data
- * @fbn: First block number of the packet in @skb
- * @lbn: Last block number of the packet in @skb
- *
- * The hardware is asking the driver to queue a packet for later
- * delivery to the networking stack.
- */
-static
-void i2400m_roq_queue(struct i2400m *i2400m, struct i2400m_roq *roq,
- struct sk_buff * skb, unsigned lbn)
-{
- struct device *dev = i2400m_dev(i2400m);
- unsigned nsn, len;
-
- d_fnstart(2, dev, "(i2400m %p roq %p skb %p lbn %u) = void\n",
- i2400m, roq, skb, lbn);
- len = skb_queue_len(&roq->queue);
- nsn = __i2400m_roq_nsn(roq, lbn);
- if (unlikely(nsn >= 1024)) {
- dev_err(dev, "SW BUG? queue nsn %d (lbn %u ws %u)\n",
- nsn, lbn, roq->ws);
- i2400m_roq_log_dump(i2400m, roq);
- i2400m_reset(i2400m, I2400M_RT_WARM);
- } else {
- __i2400m_roq_queue(i2400m, roq, skb, lbn, nsn);
- i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_PACKET,
- roq->ws, len, lbn, nsn, ~0);
- }
- d_fnend(2, dev, "(i2400m %p roq %p skb %p lbn %u) = void\n",
- i2400m, roq, skb, lbn);
-}
-
-
-/*
- * Update the window start in a reorder queue and deliver all skbs
- * with a lower window start
- *
- * @i2400m: device descriptor
- * @roq: Reorder queue
- * @sn: New sequence number
- */
-static
-void i2400m_roq_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
- unsigned sn)
-{
- struct device *dev = i2400m_dev(i2400m);
- unsigned old_ws, nsn, len;
-
- d_fnstart(2, dev, "(i2400m %p roq %p sn %u)\n", i2400m, roq, sn);
- old_ws = roq->ws;
- len = skb_queue_len(&roq->queue);
- nsn = __i2400m_roq_update_ws(i2400m, roq, sn);
- i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_WS,
- old_ws, len, sn, nsn, roq->ws);
- d_fnstart(2, dev, "(i2400m %p roq %p sn %u) = void\n", i2400m, roq, sn);
-}
-
-
-/*
- * Queue a packet and update the window start
- *
- * @i2400m: device descriptor
- * @cin: Queue Index
- * @skb: containing the packet data
- * @fbn: First block number of the packet in @skb
- * @sn: Last block number of the packet in @skb
- *
- * Note that unlike i2400m_roq_update_ws(), which sets the new window
- * start to @sn, in here we'll set it to @sn + 1.
- */
-static
-void i2400m_roq_queue_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
- struct sk_buff * skb, unsigned sn)
-{
- struct device *dev = i2400m_dev(i2400m);
- unsigned nsn, old_ws, len;
-
- d_fnstart(2, dev, "(i2400m %p roq %p skb %p sn %u)\n",
- i2400m, roq, skb, sn);
- len = skb_queue_len(&roq->queue);
- nsn = __i2400m_roq_nsn(roq, sn);
- /*
- * For type 3(queue_update_window_start) rx messages, there is no
- * need to check if the normalized sequence number is greater 1023.
- * Simply insert and deliver all packets to the host up to the
- * window start.
- */
- old_ws = roq->ws;
- /* If the queue is empty, don't bother as we'd queue
- * it and immediately unqueue it -- just deliver it.
- */
- if (len == 0) {
- struct i2400m_roq_data *roq_data;
- roq_data = (struct i2400m_roq_data *) &skb->cb;
- i2400m_net_erx(i2400m, skb, roq_data->cs);
- } else
- __i2400m_roq_queue(i2400m, roq, skb, sn, nsn);
-
- __i2400m_roq_update_ws(i2400m, roq, sn + 1);
- i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_PACKET_WS,
- old_ws, len, sn, nsn, roq->ws);
-
- d_fnend(2, dev, "(i2400m %p roq %p skb %p sn %u) = void\n",
- i2400m, roq, skb, sn);
-}
-
-
-/*
- * This routine destroys the memory allocated for rx_roq, when no
- * other thread is accessing it. Access to rx_roq is refcounted by
- * rx_roq_refcount, hence memory allocated must be destroyed when
- * rx_roq_refcount becomes zero. This routine gets executed when
- * rx_roq_refcount becomes zero.
- */
-static void i2400m_rx_roq_destroy(struct kref *ref)
-{
- unsigned itr;
- struct i2400m *i2400m
- = container_of(ref, struct i2400m, rx_roq_refcount);
- for (itr = 0; itr < I2400M_RO_CIN + 1; itr++)
- __skb_queue_purge(&i2400m->rx_roq[itr].queue);
- kfree(i2400m->rx_roq[0].log);
- kfree(i2400m->rx_roq);
- i2400m->rx_roq = NULL;
-}
-
-/*
- * Receive and send up an extended data packet
- *
- * @i2400m: device descriptor
- * @skb_rx: skb that contains the extended data packet
- * @single_last: 1 if the payload is the only one or the last one of
- * the skb.
- * @payload: pointer to the packet's data inside the skb
- * @size: size of the payload
- *
- * Starting in v1.4 of the i2400m's firmware, the device can send data
- * packets to the host in an extended format that; this incudes a 16
- * byte header (struct i2400m_pl_edata_hdr). Using this header's space
- * we can fake ethernet headers for ethernet device emulation without
- * having to copy packets around.
- *
- * This function handles said path.
- *
- *
- * Receive and send up an extended data packet that requires no reordering
- *
- * @i2400m: device descriptor
- * @skb_rx: skb that contains the extended data packet
- * @single_last: 1 if the payload is the only one or the last one of
- * the skb.
- * @payload: pointer to the packet's data (past the actual extended
- * data payload header).
- * @size: size of the payload
- *
- * Pass over to the networking stack a data packet that might have
- * reordering requirements.
- *
- * This needs to the decide if the skb in which the packet is
- * contained can be reused or if it needs to be cloned. Then it has to
- * be trimmed in the edges so that the beginning is the space for eth
- * header and then pass it to i2400m_net_erx() for the stack
- *
- * Assumes the caller has verified the sanity of the payload (size,
- * etc) already.
- */
-static
-void i2400m_rx_edata(struct i2400m *i2400m, struct sk_buff *skb_rx,
- unsigned single_last, const void *payload, size_t size)
-{
- struct device *dev = i2400m_dev(i2400m);
- const struct i2400m_pl_edata_hdr *hdr = payload;
- struct net_device *net_dev = i2400m->wimax_dev.net_dev;
- struct sk_buff *skb;
- enum i2400m_cs cs;
- u32 reorder;
- unsigned ro_needed, ro_type, ro_cin, ro_sn;
- struct i2400m_roq *roq;
- struct i2400m_roq_data *roq_data;
- unsigned long flags;
-
- BUILD_BUG_ON(ETH_HLEN > sizeof(*hdr));
-
- d_fnstart(2, dev, "(i2400m %p skb_rx %p single %u payload %p "
- "size %zu)\n", i2400m, skb_rx, single_last, payload, size);
- if (size < sizeof(*hdr)) {
- dev_err(dev, "ERX: HW BUG? message with short header (%zu "
- "vs %zu bytes expected)\n", size, sizeof(*hdr));
- goto error;
- }
-
- if (single_last) {
- skb = skb_get(skb_rx);
- d_printf(3, dev, "ERX: skb %p reusing\n", skb);
- } else {
- skb = skb_clone(skb_rx, GFP_KERNEL);
- if (skb == NULL) {
- dev_err(dev, "ERX: no memory to clone skb\n");
- net_dev->stats.rx_dropped++;
- goto error_skb_clone;
- }
- d_printf(3, dev, "ERX: skb %p cloned from %p\n", skb, skb_rx);
- }
- /* now we have to pull and trim so that the skb points to the
- * beginning of the IP packet; the netdev part will add the
- * ethernet header as needed - we know there is enough space
- * because we checked in i2400m_rx_edata(). */
- skb_pull(skb, payload + sizeof(*hdr) - (void *) skb->data);
- skb_trim(skb, (void *) skb_end_pointer(skb) - payload - sizeof(*hdr));
-
- reorder = le32_to_cpu(hdr->reorder);
- ro_needed = reorder & I2400M_RO_NEEDED;
- cs = hdr->cs;
- if (ro_needed) {
- ro_type = (reorder >> I2400M_RO_TYPE_SHIFT) & I2400M_RO_TYPE;
- ro_cin = (reorder >> I2400M_RO_CIN_SHIFT) & I2400M_RO_CIN;
- ro_sn = (reorder >> I2400M_RO_SN_SHIFT) & I2400M_RO_SN;
-
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- if (i2400m->rx_roq == NULL) {
- kfree_skb(skb); /* rx_roq is already destroyed */
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- goto error;
- }
- roq = &i2400m->rx_roq[ro_cin];
- kref_get(&i2400m->rx_roq_refcount);
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-
- roq_data = (struct i2400m_roq_data *) &skb->cb;
- roq_data->sn = ro_sn;
- roq_data->cs = cs;
- d_printf(2, dev, "ERX: reorder needed: "
- "type %u cin %u [ws %u] sn %u/%u len %zuB\n",
- ro_type, ro_cin, roq->ws, ro_sn,
- __i2400m_roq_nsn(roq, ro_sn), size);
- d_dump(2, dev, payload, size);
- switch(ro_type) {
- case I2400M_RO_TYPE_RESET:
- i2400m_roq_reset(i2400m, roq);
- kfree_skb(skb); /* no data here */
- break;
- case I2400M_RO_TYPE_PACKET:
- i2400m_roq_queue(i2400m, roq, skb, ro_sn);
- break;
- case I2400M_RO_TYPE_WS:
- i2400m_roq_update_ws(i2400m, roq, ro_sn);
- kfree_skb(skb); /* no data here */
- break;
- case I2400M_RO_TYPE_PACKET_WS:
- i2400m_roq_queue_update_ws(i2400m, roq, skb, ro_sn);
- break;
- default:
- dev_err(dev, "HW BUG? unknown reorder type %u\n", ro_type);
- }
-
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- kref_put(&i2400m->rx_roq_refcount, i2400m_rx_roq_destroy);
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- }
- else
- i2400m_net_erx(i2400m, skb, cs);
-error_skb_clone:
-error:
- d_fnend(2, dev, "(i2400m %p skb_rx %p single %u payload %p "
- "size %zu) = void\n", i2400m, skb_rx, single_last, payload, size);
-}
-
-
-/*
- * Act on a received payload
- *
- * @i2400m: device instance
- * @skb_rx: skb where the transaction was received
- * @single_last: 1 this is the only payload or the last one (so the
- * skb can be reused instead of cloned).
- * @pld: payload descriptor
- * @payload: payload data
- *
- * Upon reception of a payload, look at its guts in the payload
- * descriptor and decide what to do with it. If it is a single payload
- * skb or if the last skb is a data packet, the skb will be referenced
- * and modified (so it doesn't have to be cloned).
- */
-static
-void i2400m_rx_payload(struct i2400m *i2400m, struct sk_buff *skb_rx,
- unsigned single_last, const struct i2400m_pld *pld,
- const void *payload)
-{
- struct device *dev = i2400m_dev(i2400m);
- size_t pl_size = i2400m_pld_size(pld);
- enum i2400m_pt pl_type = i2400m_pld_type(pld);
-
- d_printf(7, dev, "RX: received payload type %u, %zu bytes\n",
- pl_type, pl_size);
- d_dump(8, dev, payload, pl_size);
-
- switch (pl_type) {
- case I2400M_PT_DATA:
- d_printf(3, dev, "RX: data payload %zu bytes\n", pl_size);
- i2400m_net_rx(i2400m, skb_rx, single_last, payload, pl_size);
- break;
- case I2400M_PT_CTRL:
- i2400m_rx_ctl(i2400m, skb_rx, payload, pl_size);
- break;
- case I2400M_PT_TRACE:
- i2400m_rx_trace(i2400m, payload, pl_size);
- break;
- case I2400M_PT_EDATA:
- d_printf(3, dev, "ERX: data payload %zu bytes\n", pl_size);
- i2400m_rx_edata(i2400m, skb_rx, single_last, payload, pl_size);
- break;
- default: /* Anything else shouldn't come to the host */
- if (printk_ratelimit())
- dev_err(dev, "RX: HW BUG? unexpected payload type %u\n",
- pl_type);
- }
-}
-
-
-/*
- * Check a received transaction's message header
- *
- * @i2400m: device descriptor
- * @msg_hdr: message header
- * @buf_size: size of the received buffer
- *
- * Check that the declarations done by a RX buffer message header are
- * sane and consistent with the amount of data that was received.
- */
-static
-int i2400m_rx_msg_hdr_check(struct i2400m *i2400m,
- const struct i2400m_msg_hdr *msg_hdr,
- size_t buf_size)
-{
- int result = -EIO;
- struct device *dev = i2400m_dev(i2400m);
- if (buf_size < sizeof(*msg_hdr)) {
- dev_err(dev, "RX: HW BUG? message with short header (%zu "
- "vs %zu bytes expected)\n", buf_size, sizeof(*msg_hdr));
- goto error;
- }
- if (msg_hdr->barker != cpu_to_le32(I2400M_D2H_MSG_BARKER)) {
- dev_err(dev, "RX: HW BUG? message received with unknown "
- "barker 0x%08x (buf_size %zu bytes)\n",
- le32_to_cpu(msg_hdr->barker), buf_size);
- goto error;
- }
- if (msg_hdr->num_pls == 0) {
- dev_err(dev, "RX: HW BUG? zero payload packets in message\n");
- goto error;
- }
- if (le16_to_cpu(msg_hdr->num_pls) > I2400M_MAX_PLS_IN_MSG) {
- dev_err(dev, "RX: HW BUG? message contains more payload "
- "than maximum; ignoring.\n");
- goto error;
- }
- result = 0;
-error:
- return result;
-}
-
-
-/*
- * Check a payload descriptor against the received data
- *
- * @i2400m: device descriptor
- * @pld: payload descriptor
- * @pl_itr: offset (in bytes) in the received buffer the payload is
- * located
- * @buf_size: size of the received buffer
- *
- * Given a payload descriptor (part of a RX buffer), check it is sane
- * and that the data it declares fits in the buffer.
- */
-static
-int i2400m_rx_pl_descr_check(struct i2400m *i2400m,
- const struct i2400m_pld *pld,
- size_t pl_itr, size_t buf_size)
-{
- int result = -EIO;
- struct device *dev = i2400m_dev(i2400m);
- size_t pl_size = i2400m_pld_size(pld);
- enum i2400m_pt pl_type = i2400m_pld_type(pld);
-
- if (pl_size > i2400m->bus_pl_size_max) {
- dev_err(dev, "RX: HW BUG? payload @%zu: size %zu is "
- "bigger than maximum %zu; ignoring message\n",
- pl_itr, pl_size, i2400m->bus_pl_size_max);
- goto error;
- }
- if (pl_itr + pl_size > buf_size) { /* enough? */
- dev_err(dev, "RX: HW BUG? payload @%zu: size %zu "
- "goes beyond the received buffer "
- "size (%zu bytes); ignoring message\n",
- pl_itr, pl_size, buf_size);
- goto error;
- }
- if (pl_type >= I2400M_PT_ILLEGAL) {
- dev_err(dev, "RX: HW BUG? illegal payload type %u; "
- "ignoring message\n", pl_type);
- goto error;
- }
- result = 0;
-error:
- return result;
-}
-
-
-/**
- * i2400m_rx - Receive a buffer of data from the device
- *
- * @i2400m: device descriptor
- * @skb: skbuff where the data has been received
- *
- * Parse in a buffer of data that contains an RX message sent from the
- * device. See the file header for the format. Run all checks on the
- * buffer header, then run over each payload's descriptors, verify
- * their consistency and act on each payload's contents. If
- * everything is successful, update the device's statistics.
- *
- * Note: You need to set the skb to contain only the length of the
- * received buffer; for that, use skb_trim(skb, RECEIVED_SIZE).
- *
- * Returns:
- *
- * 0 if ok, < 0 errno on error
- *
- * If ok, this function owns now the skb and the caller DOESN'T have
- * to run kfree_skb() on it. However, on error, the caller still owns
- * the skb and it is responsible for releasing it.
- */
-int i2400m_rx(struct i2400m *i2400m, struct sk_buff *skb)
-{
- int i, result;
- struct device *dev = i2400m_dev(i2400m);
- const struct i2400m_msg_hdr *msg_hdr;
- size_t pl_itr, pl_size;
- unsigned long flags;
- unsigned num_pls, single_last, skb_len;
-
- skb_len = skb->len;
- d_fnstart(4, dev, "(i2400m %p skb %p [size %u])\n",
- i2400m, skb, skb_len);
- msg_hdr = (void *) skb->data;
- result = i2400m_rx_msg_hdr_check(i2400m, msg_hdr, skb_len);
- if (result < 0)
- goto error_msg_hdr_check;
- result = -EIO;
- num_pls = le16_to_cpu(msg_hdr->num_pls);
- /* Check payload descriptor(s) */
- pl_itr = struct_size(msg_hdr, pld, num_pls);
- pl_itr = ALIGN(pl_itr, I2400M_PL_ALIGN);
- if (pl_itr > skb_len) { /* got all the payload descriptors? */
- dev_err(dev, "RX: HW BUG? message too short (%u bytes) for "
- "%u payload descriptors (%zu each, total %zu)\n",
- skb_len, num_pls, sizeof(msg_hdr->pld[0]), pl_itr);
- goto error_pl_descr_short;
- }
- /* Walk each payload payload--check we really got it */
- for (i = 0; i < num_pls; i++) {
- /* work around old gcc warnings */
- pl_size = i2400m_pld_size(&msg_hdr->pld[i]);
- result = i2400m_rx_pl_descr_check(i2400m, &msg_hdr->pld[i],
- pl_itr, skb_len);
- if (result < 0)
- goto error_pl_descr_check;
- single_last = num_pls == 1 || i == num_pls - 1;
- i2400m_rx_payload(i2400m, skb, single_last, &msg_hdr->pld[i],
- skb->data + pl_itr);
- pl_itr += ALIGN(pl_size, I2400M_PL_ALIGN);
- cond_resched(); /* Don't monopolize */
- }
- kfree_skb(skb);
- /* Update device statistics */
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- i2400m->rx_pl_num += i;
- if (i > i2400m->rx_pl_max)
- i2400m->rx_pl_max = i;
- if (i < i2400m->rx_pl_min)
- i2400m->rx_pl_min = i;
- i2400m->rx_num++;
- i2400m->rx_size_acc += skb_len;
- if (skb_len < i2400m->rx_size_min)
- i2400m->rx_size_min = skb_len;
- if (skb_len > i2400m->rx_size_max)
- i2400m->rx_size_max = skb_len;
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-error_pl_descr_check:
-error_pl_descr_short:
-error_msg_hdr_check:
- d_fnend(4, dev, "(i2400m %p skb %p [size %u]) = %d\n",
- i2400m, skb, skb_len, result);
- return result;
-}
-EXPORT_SYMBOL_GPL(i2400m_rx);
-
-
-void i2400m_unknown_barker(struct i2400m *i2400m,
- const void *buf, size_t size)
-{
- struct device *dev = i2400m_dev(i2400m);
- char prefix[64];
- const __le32 *barker = buf;
- dev_err(dev, "RX: HW BUG? unknown barker %08x, "
- "dropping %zu bytes\n", le32_to_cpu(*barker), size);
- snprintf(prefix, sizeof(prefix), "%s %s: ",
- dev_driver_string(dev), dev_name(dev));
- if (size > 64) {
- print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET,
- 8, 4, buf, 64, 0);
- printk(KERN_ERR "%s... (only first 64 bytes "
- "dumped)\n", prefix);
- } else
- print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET,
- 8, 4, buf, size, 0);
-}
-EXPORT_SYMBOL(i2400m_unknown_barker);
-
-
-/*
- * Initialize the RX queue and infrastructure
- *
- * This sets up all the RX reordering infrastructures, which will not
- * be used if reordering is not enabled or if the firmware does not
- * support it. The device is told to do reordering in
- * i2400m_dev_initialize(), where it also looks at the value of the
- * i2400m->rx_reorder switch before taking a decission.
- *
- * Note we allocate the roq queues in one chunk and the actual logging
- * support for it (logging) in another one and then we setup the
- * pointers from the first to the last.
- */
-int i2400m_rx_setup(struct i2400m *i2400m)
-{
- int result = 0;
-
- i2400m->rx_reorder = i2400m_rx_reorder_disabled? 0 : 1;
- if (i2400m->rx_reorder) {
- unsigned itr;
- struct i2400m_roq_log *rd;
-
- result = -ENOMEM;
-
- i2400m->rx_roq = kcalloc(I2400M_RO_CIN + 1,
- sizeof(i2400m->rx_roq[0]), GFP_KERNEL);
- if (i2400m->rx_roq == NULL)
- goto error_roq_alloc;
-
- rd = kcalloc(I2400M_RO_CIN + 1, sizeof(*i2400m->rx_roq[0].log),
- GFP_KERNEL);
- if (rd == NULL) {
- result = -ENOMEM;
- goto error_roq_log_alloc;
- }
-
- for(itr = 0; itr < I2400M_RO_CIN + 1; itr++) {
- __i2400m_roq_init(&i2400m->rx_roq[itr]);
- i2400m->rx_roq[itr].log = &rd[itr];
- }
- kref_init(&i2400m->rx_roq_refcount);
- }
- return 0;
-
-error_roq_log_alloc:
- kfree(i2400m->rx_roq);
-error_roq_alloc:
- return result;
-}
-
-
-/* Tear down the RX queue and infrastructure */
-void i2400m_rx_release(struct i2400m *i2400m)
-{
- unsigned long flags;
-
- if (i2400m->rx_reorder) {
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- kref_put(&i2400m->rx_roq_refcount, i2400m_rx_roq_destroy);
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- }
- /* at this point, nothing can be received... */
- i2400m_report_hook_flush(i2400m);
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Sysfs interfaces to show driver and device information
- *
- * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/spinlock.h>
-#include <linux/device.h>
-#include "i2400m.h"
-
-
-#define D_SUBMODULE sysfs
-#include "debug-levels.h"
-
-
-/*
- * Set the idle timeout (msecs)
- *
- * FIXME: eventually this should be a common WiMAX stack method, but
- * would like to wait to see how other devices manage it.
- */
-static
-ssize_t i2400m_idle_timeout_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t size)
-{
- ssize_t result;
- struct i2400m *i2400m = net_dev_to_i2400m(to_net_dev(dev));
- unsigned val;
-
- result = -EINVAL;
- if (sscanf(buf, "%u\n", &val) != 1)
- goto error_no_unsigned;
- if (val != 0 && (val < 100 || val > 300000 || val % 100 != 0)) {
- dev_err(dev, "idle_timeout: %u: invalid msecs specification; "
- "valid values are 0, 100-300000 in 100 increments\n",
- val);
- goto error_bad_value;
- }
- result = i2400m_set_idle_timeout(i2400m, val);
- if (result >= 0)
- result = size;
-error_no_unsigned:
-error_bad_value:
- return result;
-}
-
-static
-DEVICE_ATTR_WO(i2400m_idle_timeout);
-
-static
-struct attribute *i2400m_dev_attrs[] = {
- &dev_attr_i2400m_idle_timeout.attr,
- NULL,
-};
-
-struct attribute_group i2400m_dev_attr_group = {
- .name = NULL, /* we want them in the same directory */
- .attrs = i2400m_dev_attrs,
-};
+++ /dev/null
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Generic (non-bus specific) TX handling
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * - Initial implementation
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * - Rewritten to use a single FIFO to lower the memory allocation
- * pressure and optimize cache hits when copying to the queue, as
- * well as splitting out bus-specific code.
- *
- *
- * Implements data transmission to the device; this is done through a
- * software FIFO, as data/control frames can be coalesced (while the
- * device is reading the previous tx transaction, others accumulate).
- *
- * A FIFO is used because at the end it is resource-cheaper that trying
- * to implement scatter/gather over USB. As well, most traffic is going
- * to be download (vs upload).
- *
- * The format for sending/receiving data to/from the i2400m is
- * described in detail in rx.c:PROTOCOL FORMAT. In here we implement
- * the transmission of that. This is split between a bus-independent
- * part that just prepares everything and a bus-specific part that
- * does the actual transmission over the bus to the device (in the
- * bus-specific driver).
- *
- *
- * The general format of a device-host transaction is MSG-HDR, PLD1,
- * PLD2...PLDN, PL1, PL2,...PLN, PADDING.
- *
- * Because we need the send payload descriptors and then payloads and
- * because it is kind of expensive to do scatterlists in USB (one URB
- * per node), it becomes cheaper to append all the data to a FIFO
- * (copying to a FIFO potentially in cache is cheaper).
- *
- * Then the bus-specific code takes the parts of that FIFO that are
- * written and passes them to the device.
- *
- * So the concepts to keep in mind there are:
- *
- * We use a FIFO to queue the data in a linear buffer. We first append
- * a MSG-HDR, space for I2400M_TX_PLD_MAX payload descriptors and then
- * go appending payloads until we run out of space or of payload
- * descriptors. Then we append padding to make the whole transaction a
- * multiple of i2400m->bus_tx_block_size (as defined by the bus layer).
- *
- * - A TX message: a combination of a message header, payload
- * descriptors and payloads.
- *
- * Open: it is marked as active (i2400m->tx_msg is valid) and we
- * can keep adding payloads to it.
- *
- * Closed: we are not appending more payloads to this TX message
- * (exahusted space in the queue, too many payloads or
- * whichever). We have appended padding so the whole message
- * length is aligned to i2400m->bus_tx_block_size (as set by the
- * bus/transport layer).
- *
- * - Most of the time we keep a TX message open to which we append
- * payloads.
- *
- * - If we are going to append and there is no more space (we are at
- * the end of the FIFO), we close the message, mark the rest of the
- * FIFO space unusable (skip_tail), create a new message at the
- * beginning of the FIFO (if there is space) and append the message
- * there.
- *
- * This is because we need to give linear TX messages to the bus
- * engine. So we don't write a message to the remaining FIFO space
- * until the tail and continue at the head of it.
- *
- * - We overload one of the fields in the message header to use it as
- * 'size' of the TX message, so we can iterate over them. It also
- * contains a flag that indicates if we have to skip it or not.
- * When we send the buffer, we update that to its real on-the-wire
- * value.
- *
- * - The MSG-HDR PLD1...PLD2 stuff has to be a size multiple of 16.
- *
- * It follows that if MSG-HDR says we have N messages, the whole
- * header + descriptors is 16 + 4*N; for those to be a multiple of
- * 16, it follows that N can be 4, 8, 12, ... (32, 48, 64, 80...
- * bytes).
- *
- * So if we have only 1 payload, we have to submit a header that in
- * all truth has space for 4.
- *
- * The implication is that we reserve space for 12 (64 bytes); but
- * if we fill up only (eg) 2, our header becomes 32 bytes only. So
- * the TX engine has to shift those 32 bytes of msg header and 2
- * payloads and padding so that right after it the payloads start
- * and the TX engine has to know about that.
- *
- * It is cheaper to move the header up than the whole payloads down.
- *
- * We do this in i2400m_tx_close(). See 'i2400m_msg_hdr->offset'.
- *
- * - Each payload has to be size-padded to 16 bytes; before appending
- * it, we just do it.
- *
- * - The whole message has to be padded to i2400m->bus_tx_block_size;
- * we do this at close time. Thus, when reserving space for the
- * payload, we always make sure there is also free space for this
- * padding that sooner or later will happen.
- *
- * When we append a message, we tell the bus specific code to kick in
- * TXs. It will TX (in parallel) until the buffer is exhausted--hence
- * the lockin we do. The TX code will only send a TX message at the
- * time (which remember, might contain more than one payload). Of
- * course, when the bus-specific driver attempts to TX a message that
- * is still open, it gets closed first.
- *
- * Gee, this is messy; well a picture. In the example below we have a
- * partially full FIFO, with a closed message ready to be delivered
- * (with a moved message header to make sure it is size-aligned to
- * 16), TAIL room that was unusable (and thus is marked with a message
- * header that says 'skip this') and at the head of the buffer, an
- * incomplete message with a couple of payloads.
- *
- * N ___________________________________________________
- * | |
- * | TAIL room |
- * | |
- * | msg_hdr to skip (size |= 0x80000) |
- * |---------------------------------------------------|-------
- * | | /|\
- * | | |
- * | TX message padding | |
- * | | |
- * | | |
- * |- - - - - - - - - - - - - - - - - - - - - - - - - -| |
- * | | |
- * | payload 1 | |
- * | | N * tx_block_size
- * | | |
- * |- - - - - - - - - - - - - - - - - - - - - - - - - -| |
- * | | |
- * | payload 1 | |
- * | | |
- * | | |
- * |- - - - - - - - - - - - - - - - - - - - - - - - - -|- -|- - - -
- * | padding 3 /|\ | | /|\
- * | padding 2 | | | |
- * | pld 1 32 bytes (2 * 16) | | |
- * | pld 0 | | | |
- * | moved msg_hdr \|/ | \|/ |
- * |- - - - - - - - - - - - - - - - - - - - - - - - - -|- - - |
- * | | _PLD_SIZE
- * | unused | |
- * | | |
- * |- - - - - - - - - - - - - - - - - - - - - - - - - -| |
- * | msg_hdr (size X) [this message is closed] | \|/
- * |===================================================|========== <=== OUT
- * | |
- * | |
- * | |
- * | Free rooom |
- * | |
- * | |
- * | |
- * | |
- * | |
- * | |
- * | |
- * | |
- * | |
- * |===================================================|========== <=== IN
- * | |
- * | |
- * | |
- * | |
- * | payload 1 |
- * | |
- * | |
- * |- - - - - - - - - - - - - - - - - - - - - - - - - -|
- * | |
- * | payload 0 |
- * | |
- * | |
- * |- - - - - - - - - - - - - - - - - - - - - - - - - -|
- * | pld 11 /|\ |
- * | ... | |
- * | pld 1 64 bytes (2 * 16) |
- * | pld 0 | |
- * | msg_hdr (size X) \|/ [message is open] |
- * 0 ---------------------------------------------------
- *
- *
- * ROADMAP
- *
- * i2400m_tx_setup() Called by i2400m_setup
- * i2400m_tx_release() Called by i2400m_release()
- *
- * i2400m_tx() Called to send data or control frames
- * i2400m_tx_fifo_push() Allocates append-space in the FIFO
- * i2400m_tx_new() Opens a new message in the FIFO
- * i2400m_tx_fits() Checks if a new payload fits in the message
- * i2400m_tx_close() Closes an open message in the FIFO
- * i2400m_tx_skip_tail() Marks unusable FIFO tail space
- * i2400m->bus_tx_kick()
- *
- * Now i2400m->bus_tx_kick() is the the bus-specific driver backend
- * implementation; that would do:
- *
- * i2400m->bus_tx_kick()
- * i2400m_tx_msg_get() Gets first message ready to go
- * ...sends it...
- * i2400m_tx_msg_sent() Ack the message is sent; repeat from
- * _tx_msg_get() until it returns NULL
- * (FIFO empty).
- */
-#include <linux/netdevice.h>
-#include <linux/slab.h>
-#include <linux/export.h>
-#include "i2400m.h"
-
-
-#define D_SUBMODULE tx
-#include "debug-levels.h"
-
-enum {
- /**
- * TX Buffer size
- *
- * Doc says maximum transaction is 16KiB. If we had 16KiB en
- * route and 16KiB being queued, it boils down to needing
- * 32KiB.
- * 32KiB is insufficient for 1400 MTU, hence increasing
- * tx buffer size to 64KiB.
- */
- I2400M_TX_BUF_SIZE = 65536,
- /**
- * Message header and payload descriptors have to be 16
- * aligned (16 + 4 * N = 16 * M). If we take that average sent
- * packets are MTU size (~1400-~1500) it follows that we could
- * fit at most 10-11 payloads in one transaction. To meet the
- * alignment requirement, that means we need to leave space
- * for 12 (64 bytes). To simplify, we leave space for that. If
- * at the end there are less, we pad up to the nearest
- * multiple of 16.
- */
- /*
- * According to Intel Wimax i3200, i5x50 and i6x50 specification
- * documents, the maximum number of payloads per message can be
- * up to 60. Increasing the number of payloads to 60 per message
- * helps to accommodate smaller payloads in a single transaction.
- */
- I2400M_TX_PLD_MAX = 60,
- I2400M_TX_PLD_SIZE = sizeof(struct i2400m_msg_hdr)
- + I2400M_TX_PLD_MAX * sizeof(struct i2400m_pld),
- I2400M_TX_SKIP = 0x80000000,
- /*
- * According to Intel Wimax i3200, i5x50 and i6x50 specification
- * documents, the maximum size of each message can be up to 16KiB.
- */
- I2400M_TX_MSG_SIZE = 16384,
-};
-
-#define TAIL_FULL ((void *)~(unsigned long)NULL)
-
-/*
- * Calculate how much tail room is available
- *
- * Note the trick here. This path is ONLY caleed for Case A (see
- * i2400m_tx_fifo_push() below), where we have:
- *
- * Case A
- * N ___________
- * | tail room |
- * | |
- * |<- IN ->|
- * | |
- * | data |
- * | |
- * |<- OUT ->|
- * | |
- * | head room |
- * 0 -----------
- *
- * When calculating the tail_room, tx_in might get to be zero if
- * i2400m->tx_in is right at the end of the buffer (really full
- * buffer) if there is no head room. In this case, tail_room would be
- * I2400M_TX_BUF_SIZE, although it is actually zero. Hence the final
- * mod (%) operation. However, when doing this kind of optimization,
- * i2400m->tx_in being zero would fail, so we treat is an a special
- * case.
- */
-static inline
-size_t __i2400m_tx_tail_room(struct i2400m *i2400m)
-{
- size_t tail_room;
- size_t tx_in;
-
- if (unlikely(i2400m->tx_in == 0))
- return I2400M_TX_BUF_SIZE;
- tx_in = i2400m->tx_in % I2400M_TX_BUF_SIZE;
- tail_room = I2400M_TX_BUF_SIZE - tx_in;
- tail_room %= I2400M_TX_BUF_SIZE;
- return tail_room;
-}
-
-
-/*
- * Allocate @size bytes in the TX fifo, return a pointer to it
- *
- * @i2400m: device descriptor
- * @size: size of the buffer we need to allocate
- * @padding: ensure that there is at least this many bytes of free
- * contiguous space in the fifo. This is needed because later on
- * we might need to add padding.
- * @try_head: specify either to allocate head room or tail room space
- * in the TX FIFO. This boolean is required to avoids a system hang
- * due to an infinite loop caused by i2400m_tx_fifo_push().
- * The caller must always try to allocate tail room space first by
- * calling this routine with try_head = 0. In case if there
- * is not enough tail room space but there is enough head room space,
- * (i2400m_tx_fifo_push() returns TAIL_FULL) try to allocate head
- * room space, by calling this routine again with try_head = 1.
- *
- * Returns:
- *
- * Pointer to the allocated space. NULL if there is no
- * space. TAIL_FULL if there is no space at the tail but there is at
- * the head (Case B below).
- *
- * These are the two basic cases we need to keep an eye for -- it is
- * much better explained in linux/kernel/kfifo.c, but this code
- * basically does the same. No rocket science here.
- *
- * Case A Case B
- * N ___________ ___________
- * | tail room | | data |
- * | | | |
- * |<- IN ->| |<- OUT ->|
- * | | | |
- * | data | | room |
- * | | | |
- * |<- OUT ->| |<- IN ->|
- * | | | |
- * | head room | | data |
- * 0 ----------- -----------
- *
- * We allocate only *contiguous* space.
- *
- * We can allocate only from 'room'. In Case B, it is simple; in case
- * A, we only try from the tail room; if it is not enough, we just
- * fail and return TAIL_FULL and let the caller figure out if we wants to
- * skip the tail room and try to allocate from the head.
- *
- * There is a corner case, wherein i2400m_tx_new() can get into
- * an infinite loop calling i2400m_tx_fifo_push().
- * In certain situations, tx_in would have reached on the top of TX FIFO
- * and i2400m_tx_tail_room() returns 0, as described below:
- *
- * N ___________ tail room is zero
- * |<- IN ->|
- * | |
- * | |
- * | |
- * | data |
- * |<- OUT ->|
- * | |
- * | |
- * | head room |
- * 0 -----------
- * During such a time, where tail room is zero in the TX FIFO and if there
- * is a request to add a payload to TX FIFO, which calls:
- * i2400m_tx()
- * ->calls i2400m_tx_close()
- * ->calls i2400m_tx_skip_tail()
- * goto try_new;
- * ->calls i2400m_tx_new()
- * |----> [try_head:]
- * infinite loop | ->calls i2400m_tx_fifo_push()
- * | if (tail_room < needed)
- * | if (head_room => needed)
- * | return TAIL_FULL;
- * |<---- goto try_head;
- *
- * i2400m_tx() calls i2400m_tx_close() to close the message, since there
- * is no tail room to accommodate the payload and calls
- * i2400m_tx_skip_tail() to skip the tail space. Now i2400m_tx() calls
- * i2400m_tx_new() to allocate space for new message header calling
- * i2400m_tx_fifo_push() that returns TAIL_FULL, since there is no tail space
- * to accommodate the message header, but there is enough head space.
- * The i2400m_tx_new() keeps re-retrying by calling i2400m_tx_fifo_push()
- * ending up in a loop causing system freeze.
- *
- * This corner case is avoided by using a try_head boolean,
- * as an argument to i2400m_tx_fifo_push().
- *
- * Note:
- *
- * Assumes i2400m->tx_lock is taken, and we use that as a barrier
- *
- * The indexes keep increasing and we reset them to zero when we
- * pop data off the queue
- */
-static
-void *i2400m_tx_fifo_push(struct i2400m *i2400m, size_t size,
- size_t padding, bool try_head)
-{
- struct device *dev = i2400m_dev(i2400m);
- size_t room, tail_room, needed_size;
- void *ptr;
-
- needed_size = size + padding;
- room = I2400M_TX_BUF_SIZE - (i2400m->tx_in - i2400m->tx_out);
- if (room < needed_size) { /* this takes care of Case B */
- d_printf(2, dev, "fifo push %zu/%zu: no space\n",
- size, padding);
- return NULL;
- }
- /* Is there space at the tail? */
- tail_room = __i2400m_tx_tail_room(i2400m);
- if (!try_head && tail_room < needed_size) {
- /*
- * If the tail room space is not enough to push the message
- * in the TX FIFO, then there are two possibilities:
- * 1. There is enough head room space to accommodate
- * this message in the TX FIFO.
- * 2. There is not enough space in the head room and
- * in tail room of the TX FIFO to accommodate the message.
- * In the case (1), return TAIL_FULL so that the caller
- * can figure out, if the caller wants to push the message
- * into the head room space.
- * In the case (2), return NULL, indicating that the TX FIFO
- * cannot accommodate the message.
- */
- if (room - tail_room >= needed_size) {
- d_printf(2, dev, "fifo push %zu/%zu: tail full\n",
- size, padding);
- return TAIL_FULL; /* There might be head space */
- } else {
- d_printf(2, dev, "fifo push %zu/%zu: no head space\n",
- size, padding);
- return NULL; /* There is no space */
- }
- }
- ptr = i2400m->tx_buf + i2400m->tx_in % I2400M_TX_BUF_SIZE;
- d_printf(2, dev, "fifo push %zu/%zu: at @%zu\n", size, padding,
- i2400m->tx_in % I2400M_TX_BUF_SIZE);
- i2400m->tx_in += size;
- return ptr;
-}
-
-
-/*
- * Mark the tail of the FIFO buffer as 'to-skip'
- *
- * We should never hit the BUG_ON() because all the sizes we push to
- * the FIFO are padded to be a multiple of 16 -- the size of *msg
- * (I2400M_PL_PAD for the payloads, I2400M_TX_PLD_SIZE for the
- * header).
- *
- * Tail room can get to be zero if a message was opened when there was
- * space only for a header. _tx_close() will mark it as to-skip (as it
- * will have no payloads) and there will be no more space to flush, so
- * nothing has to be done here. This is probably cheaper than ensuring
- * in _tx_new() that there is some space for payloads...as we could
- * always possibly hit the same problem if the payload wouldn't fit.
- *
- * Note:
- *
- * Assumes i2400m->tx_lock is taken, and we use that as a barrier
- *
- * This path is only taken for Case A FIFO situations [see
- * i2400m_tx_fifo_push()]
- */
-static
-void i2400m_tx_skip_tail(struct i2400m *i2400m)
-{
- struct device *dev = i2400m_dev(i2400m);
- size_t tx_in = i2400m->tx_in % I2400M_TX_BUF_SIZE;
- size_t tail_room = __i2400m_tx_tail_room(i2400m);
- struct i2400m_msg_hdr *msg = i2400m->tx_buf + tx_in;
- if (unlikely(tail_room == 0))
- return;
- BUG_ON(tail_room < sizeof(*msg));
- msg->size = tail_room | I2400M_TX_SKIP;
- d_printf(2, dev, "skip tail: skipping %zu bytes @%zu\n",
- tail_room, tx_in);
- i2400m->tx_in += tail_room;
-}
-
-
-/*
- * Check if a skb will fit in the TX queue's current active TX
- * message (if there are still descriptors left unused).
- *
- * Returns:
- * 0 if the message won't fit, 1 if it will.
- *
- * Note:
- *
- * Assumes a TX message is active (i2400m->tx_msg).
- *
- * Assumes i2400m->tx_lock is taken, and we use that as a barrier
- */
-static
-unsigned i2400m_tx_fits(struct i2400m *i2400m)
-{
- struct i2400m_msg_hdr *msg_hdr = i2400m->tx_msg;
- return le16_to_cpu(msg_hdr->num_pls) < I2400M_TX_PLD_MAX;
-
-}
-
-
-/*
- * Start a new TX message header in the queue.
- *
- * Reserve memory from the base FIFO engine and then just initialize
- * the message header.
- *
- * We allocate the biggest TX message header we might need (one that'd
- * fit I2400M_TX_PLD_MAX payloads) -- when it is closed it will be
- * 'ironed it out' and the unneeded parts removed.
- *
- * NOTE:
- *
- * Assumes that the previous message is CLOSED (eg: either
- * there was none or 'i2400m_tx_close()' was called on it).
- *
- * Assumes i2400m->tx_lock is taken, and we use that as a barrier
- */
-static
-void i2400m_tx_new(struct i2400m *i2400m)
-{
- struct device *dev = i2400m_dev(i2400m);
- struct i2400m_msg_hdr *tx_msg;
- bool try_head = false;
- BUG_ON(i2400m->tx_msg != NULL);
- /*
- * In certain situations, TX queue might have enough space to
- * accommodate the new message header I2400M_TX_PLD_SIZE, but
- * might not have enough space to accommodate the payloads.
- * Adding bus_tx_room_min padding while allocating a new TX message
- * increases the possibilities of including at least one payload of the
- * size <= bus_tx_room_min.
- */
-try_head:
- tx_msg = i2400m_tx_fifo_push(i2400m, I2400M_TX_PLD_SIZE,
- i2400m->bus_tx_room_min, try_head);
- if (tx_msg == NULL)
- goto out;
- else if (tx_msg == TAIL_FULL) {
- i2400m_tx_skip_tail(i2400m);
- d_printf(2, dev, "new TX message: tail full, trying head\n");
- try_head = true;
- goto try_head;
- }
- memset(tx_msg, 0, I2400M_TX_PLD_SIZE);
- tx_msg->size = I2400M_TX_PLD_SIZE;
-out:
- i2400m->tx_msg = tx_msg;
- d_printf(2, dev, "new TX message: %p @%zu\n",
- tx_msg, (void *) tx_msg - i2400m->tx_buf);
-}
-
-
-/*
- * Finalize the current TX message header
- *
- * Sets the message header to be at the proper location depending on
- * how many descriptors we have (check documentation at the file's
- * header for more info on that).
- *
- * Appends padding bytes to make sure the whole TX message (counting
- * from the 'relocated' message header) is aligned to
- * tx_block_size. We assume the _append() code has left enough space
- * in the FIFO for that. If there are no payloads, just pass, as it
- * won't be transferred.
- *
- * The amount of padding bytes depends on how many payloads are in the
- * TX message, as the "msg header and payload descriptors" will be
- * shifted up in the buffer.
- */
-static
-void i2400m_tx_close(struct i2400m *i2400m)
-{
- struct device *dev = i2400m_dev(i2400m);
- struct i2400m_msg_hdr *tx_msg = i2400m->tx_msg;
- struct i2400m_msg_hdr *tx_msg_moved;
- size_t aligned_size, padding, hdr_size;
- void *pad_buf;
- unsigned num_pls;
-
- if (tx_msg->size & I2400M_TX_SKIP) /* a skipper? nothing to do */
- goto out;
- num_pls = le16_to_cpu(tx_msg->num_pls);
- /* We can get this situation when a new message was started
- * and there was no space to add payloads before hitting the
- tail (and taking padding into consideration). */
- if (num_pls == 0) {
- tx_msg->size |= I2400M_TX_SKIP;
- goto out;
- }
- /* Relocate the message header
- *
- * Find the current header size, align it to 16 and if we need
- * to move it so the tail is next to the payloads, move it and
- * set the offset.
- *
- * If it moved, this header is good only for transmission; the
- * original one (it is kept if we moved) is still used to
- * figure out where the next TX message starts (and where the
- * offset to the moved header is).
- */
- hdr_size = struct_size(tx_msg, pld, le16_to_cpu(tx_msg->num_pls));
- hdr_size = ALIGN(hdr_size, I2400M_PL_ALIGN);
- tx_msg->offset = I2400M_TX_PLD_SIZE - hdr_size;
- tx_msg_moved = (void *) tx_msg + tx_msg->offset;
- memmove(tx_msg_moved, tx_msg, hdr_size);
- tx_msg_moved->size -= tx_msg->offset;
- /*
- * Now figure out how much we have to add to the (moved!)
- * message so the size is a multiple of i2400m->bus_tx_block_size.
- */
- aligned_size = ALIGN(tx_msg_moved->size, i2400m->bus_tx_block_size);
- padding = aligned_size - tx_msg_moved->size;
- if (padding > 0) {
- pad_buf = i2400m_tx_fifo_push(i2400m, padding, 0, 0);
- if (WARN_ON(pad_buf == NULL || pad_buf == TAIL_FULL)) {
- /* This should not happen -- append should verify
- * there is always space left at least to append
- * tx_block_size */
- dev_err(dev,
- "SW BUG! Possible data leakage from memory the "
- "device should not read for padding - "
- "size %lu aligned_size %zu tx_buf %p in "
- "%zu out %zu\n",
- (unsigned long) tx_msg_moved->size,
- aligned_size, i2400m->tx_buf, i2400m->tx_in,
- i2400m->tx_out);
- } else
- memset(pad_buf, 0xad, padding);
- }
- tx_msg_moved->padding = cpu_to_le16(padding);
- tx_msg_moved->size += padding;
- if (tx_msg != tx_msg_moved)
- tx_msg->size += padding;
-out:
- i2400m->tx_msg = NULL;
-}
-
-
-/**
- * i2400m_tx - send the data in a buffer to the device
- *
- * @buf: pointer to the buffer to transmit
- *
- * @buf_len: buffer size
- *
- * @pl_type: type of the payload we are sending.
- *
- * Returns:
- * 0 if ok, < 0 errno code on error (-ENOSPC, if there is no more
- * room for the message in the queue).
- *
- * Appends the buffer to the TX FIFO and notifies the bus-specific
- * part of the driver that there is new data ready to transmit.
- * Once this function returns, the buffer has been copied, so it can
- * be reused.
- *
- * The steps followed to append are explained in detail in the file
- * header.
- *
- * Whenever we write to a message, we increase msg->size, so it
- * reflects exactly how big the message is. This is needed so that if
- * we concatenate two messages before they can be sent, the code that
- * sends the messages can find the boundaries (and it will replace the
- * size with the real barker before sending).
- *
- * Note:
- *
- * Cold and warm reset payloads need to be sent as a single
- * payload, so we handle that.
- */
-int i2400m_tx(struct i2400m *i2400m, const void *buf, size_t buf_len,
- enum i2400m_pt pl_type)
-{
- int result = -ENOSPC;
- struct device *dev = i2400m_dev(i2400m);
- unsigned long flags;
- size_t padded_len;
- void *ptr;
- bool try_head = false;
- unsigned is_singleton = pl_type == I2400M_PT_RESET_WARM
- || pl_type == I2400M_PT_RESET_COLD;
-
- d_fnstart(3, dev, "(i2400m %p skb %p [%zu bytes] pt %u)\n",
- i2400m, buf, buf_len, pl_type);
- padded_len = ALIGN(buf_len, I2400M_PL_ALIGN);
- d_printf(5, dev, "padded_len %zd buf_len %zd\n", padded_len, buf_len);
- /* If there is no current TX message, create one; if the
- * current one is out of payload slots or we have a singleton,
- * close it and start a new one */
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- /* If tx_buf is NULL, device is shutdown */
- if (i2400m->tx_buf == NULL) {
- result = -ESHUTDOWN;
- goto error_tx_new;
- }
-try_new:
- if (unlikely(i2400m->tx_msg == NULL))
- i2400m_tx_new(i2400m);
- else if (unlikely(!i2400m_tx_fits(i2400m)
- || (is_singleton && i2400m->tx_msg->num_pls != 0))) {
- d_printf(2, dev, "closing TX message (fits %u singleton "
- "%u num_pls %u)\n", i2400m_tx_fits(i2400m),
- is_singleton, i2400m->tx_msg->num_pls);
- i2400m_tx_close(i2400m);
- i2400m_tx_new(i2400m);
- }
- if (i2400m->tx_msg == NULL)
- goto error_tx_new;
- /*
- * Check if this skb will fit in the TX queue's current active
- * TX message. The total message size must not exceed the maximum
- * size of each message I2400M_TX_MSG_SIZE. If it exceeds,
- * close the current message and push this skb into the new message.
- */
- if (i2400m->tx_msg->size + padded_len > I2400M_TX_MSG_SIZE) {
- d_printf(2, dev, "TX: message too big, going new\n");
- i2400m_tx_close(i2400m);
- i2400m_tx_new(i2400m);
- }
- if (i2400m->tx_msg == NULL)
- goto error_tx_new;
- /* So we have a current message header; now append space for
- * the message -- if there is not enough, try the head */
- ptr = i2400m_tx_fifo_push(i2400m, padded_len,
- i2400m->bus_tx_block_size, try_head);
- if (ptr == TAIL_FULL) { /* Tail is full, try head */
- d_printf(2, dev, "pl append: tail full\n");
- i2400m_tx_close(i2400m);
- i2400m_tx_skip_tail(i2400m);
- try_head = true;
- goto try_new;
- } else if (ptr == NULL) { /* All full */
- result = -ENOSPC;
- d_printf(2, dev, "pl append: all full\n");
- } else { /* Got space, copy it, set padding */
- struct i2400m_msg_hdr *tx_msg = i2400m->tx_msg;
- unsigned num_pls = le16_to_cpu(tx_msg->num_pls);
- memcpy(ptr, buf, buf_len);
- memset(ptr + buf_len, 0xad, padded_len - buf_len);
- i2400m_pld_set(&tx_msg->pld[num_pls], buf_len, pl_type);
- d_printf(3, dev, "pld 0x%08x (type 0x%1x len 0x%04zx\n",
- le32_to_cpu(tx_msg->pld[num_pls].val),
- pl_type, buf_len);
- tx_msg->num_pls = le16_to_cpu(num_pls+1);
- tx_msg->size += padded_len;
- d_printf(2, dev, "TX: appended %zu b (up to %u b) pl #%u\n",
- padded_len, tx_msg->size, num_pls+1);
- d_printf(2, dev,
- "TX: appended hdr @%zu %zu b pl #%u @%zu %zu/%zu b\n",
- (void *)tx_msg - i2400m->tx_buf, (size_t)tx_msg->size,
- num_pls+1, ptr - i2400m->tx_buf, buf_len, padded_len);
- result = 0;
- if (is_singleton)
- i2400m_tx_close(i2400m);
- }
-error_tx_new:
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
- /* kick in most cases, except when the TX subsys is down, as
- * it might free space */
- if (likely(result != -ESHUTDOWN))
- i2400m->bus_tx_kick(i2400m);
- d_fnend(3, dev, "(i2400m %p skb %p [%zu bytes] pt %u) = %d\n",
- i2400m, buf, buf_len, pl_type, result);
- return result;
-}
-EXPORT_SYMBOL_GPL(i2400m_tx);
-
-
-/**
- * i2400m_tx_msg_get - Get the first TX message in the FIFO to start sending it
- *
- * @i2400m: device descriptors
- * @bus_size: where to place the size of the TX message
- *
- * Called by the bus-specific driver to get the first TX message at
- * the FIF that is ready for transmission.
- *
- * It sets the state in @i2400m to indicate the bus-specific driver is
- * transferring that message (i2400m->tx_msg_size).
- *
- * Once the transfer is completed, call i2400m_tx_msg_sent().
- *
- * Notes:
- *
- * The size of the TX message to be transmitted might be smaller than
- * that of the TX message in the FIFO (in case the header was
- * shorter). Hence, we copy it in @bus_size, for the bus layer to
- * use. We keep the message's size in i2400m->tx_msg_size so that
- * when the bus later is done transferring we know how much to
- * advance the fifo.
- *
- * We collect statistics here as all the data is available and we
- * assume it is going to work [see i2400m_tx_msg_sent()].
- */
-struct i2400m_msg_hdr *i2400m_tx_msg_get(struct i2400m *i2400m,
- size_t *bus_size)
-{
- struct device *dev = i2400m_dev(i2400m);
- struct i2400m_msg_hdr *tx_msg, *tx_msg_moved;
- unsigned long flags, pls;
-
- d_fnstart(3, dev, "(i2400m %p bus_size %p)\n", i2400m, bus_size);
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- tx_msg_moved = NULL;
- if (i2400m->tx_buf == NULL)
- goto out_unlock;
-skip:
- tx_msg_moved = NULL;
- if (i2400m->tx_in == i2400m->tx_out) { /* Empty FIFO? */
- i2400m->tx_in = 0;
- i2400m->tx_out = 0;
- d_printf(2, dev, "TX: FIFO empty: resetting\n");
- goto out_unlock;
- }
- tx_msg = i2400m->tx_buf + i2400m->tx_out % I2400M_TX_BUF_SIZE;
- if (tx_msg->size & I2400M_TX_SKIP) { /* skip? */
- d_printf(2, dev, "TX: skip: msg @%zu (%zu b)\n",
- i2400m->tx_out % I2400M_TX_BUF_SIZE,
- (size_t) tx_msg->size & ~I2400M_TX_SKIP);
- i2400m->tx_out += tx_msg->size & ~I2400M_TX_SKIP;
- goto skip;
- }
-
- if (tx_msg->num_pls == 0) { /* No payloads? */
- if (tx_msg == i2400m->tx_msg) { /* open, we are done */
- d_printf(2, dev,
- "TX: FIFO empty: open msg w/o payloads @%zu\n",
- (void *) tx_msg - i2400m->tx_buf);
- tx_msg = NULL;
- goto out_unlock;
- } else { /* closed, skip it */
- d_printf(2, dev,
- "TX: skip msg w/o payloads @%zu (%zu b)\n",
- (void *) tx_msg - i2400m->tx_buf,
- (size_t) tx_msg->size);
- i2400m->tx_out += tx_msg->size & ~I2400M_TX_SKIP;
- goto skip;
- }
- }
- if (tx_msg == i2400m->tx_msg) /* open msg? */
- i2400m_tx_close(i2400m);
-
- /* Now we have a valid TX message (with payloads) to TX */
- tx_msg_moved = (void *) tx_msg + tx_msg->offset;
- i2400m->tx_msg_size = tx_msg->size;
- *bus_size = tx_msg_moved->size;
- d_printf(2, dev, "TX: pid %d msg hdr at @%zu offset +@%zu "
- "size %zu bus_size %zu\n",
- current->pid, (void *) tx_msg - i2400m->tx_buf,
- (size_t) tx_msg->offset, (size_t) tx_msg->size,
- (size_t) tx_msg_moved->size);
- tx_msg_moved->barker = le32_to_cpu(I2400M_H2D_PREVIEW_BARKER);
- tx_msg_moved->sequence = le32_to_cpu(i2400m->tx_sequence++);
-
- pls = le32_to_cpu(tx_msg_moved->num_pls);
- i2400m->tx_pl_num += pls; /* Update stats */
- if (pls > i2400m->tx_pl_max)
- i2400m->tx_pl_max = pls;
- if (pls < i2400m->tx_pl_min)
- i2400m->tx_pl_min = pls;
- i2400m->tx_num++;
- i2400m->tx_size_acc += *bus_size;
- if (*bus_size < i2400m->tx_size_min)
- i2400m->tx_size_min = *bus_size;
- if (*bus_size > i2400m->tx_size_max)
- i2400m->tx_size_max = *bus_size;
-out_unlock:
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
- d_fnstart(3, dev, "(i2400m %p bus_size %p [%zu]) = %p\n",
- i2400m, bus_size, *bus_size, tx_msg_moved);
- return tx_msg_moved;
-}
-EXPORT_SYMBOL_GPL(i2400m_tx_msg_get);
-
-
-/**
- * i2400m_tx_msg_sent - indicate the transmission of a TX message
- *
- * @i2400m: device descriptor
- *
- * Called by the bus-specific driver when a message has been sent;
- * this pops it from the FIFO; and as there is space, start the queue
- * in case it was stopped.
- *
- * Should be called even if the message send failed and we are
- * dropping this TX message.
- */
-void i2400m_tx_msg_sent(struct i2400m *i2400m)
-{
- unsigned n;
- unsigned long flags;
- struct device *dev = i2400m_dev(i2400m);
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- if (i2400m->tx_buf == NULL)
- goto out_unlock;
- i2400m->tx_out += i2400m->tx_msg_size;
- d_printf(2, dev, "TX: sent %zu b\n", (size_t) i2400m->tx_msg_size);
- i2400m->tx_msg_size = 0;
- BUG_ON(i2400m->tx_out > i2400m->tx_in);
- /* level them FIFO markers off */
- n = i2400m->tx_out / I2400M_TX_BUF_SIZE;
- i2400m->tx_out %= I2400M_TX_BUF_SIZE;
- i2400m->tx_in -= n * I2400M_TX_BUF_SIZE;
-out_unlock:
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
- d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
-EXPORT_SYMBOL_GPL(i2400m_tx_msg_sent);
-
-
-/**
- * i2400m_tx_setup - Initialize the TX queue and infrastructure
- *
- * Make sure we reset the TX sequence to zero, as when this function
- * is called, the firmware has been just restarted. Same rational
- * for tx_in, tx_out, tx_msg_size and tx_msg. We reset them since
- * the memory for TX queue is reallocated.
- */
-int i2400m_tx_setup(struct i2400m *i2400m)
-{
- int result = 0;
- void *tx_buf;
- unsigned long flags;
-
- /* Do this here only once -- can't do on
- * i2400m_hard_start_xmit() as we'll cause race conditions if
- * the WS was scheduled on another CPU */
- INIT_WORK(&i2400m->wake_tx_ws, i2400m_wake_tx_work);
-
- tx_buf = kmalloc(I2400M_TX_BUF_SIZE, GFP_ATOMIC);
- if (tx_buf == NULL) {
- result = -ENOMEM;
- goto error_kmalloc;
- }
-
- /*
- * Fail the build if we can't fit at least two maximum size messages
- * on the TX FIFO [one being delivered while one is constructed].
- */
- BUILD_BUG_ON(2 * I2400M_TX_MSG_SIZE > I2400M_TX_BUF_SIZE);
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- i2400m->tx_sequence = 0;
- i2400m->tx_in = 0;
- i2400m->tx_out = 0;
- i2400m->tx_msg_size = 0;
- i2400m->tx_msg = NULL;
- i2400m->tx_buf = tx_buf;
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
- /* Huh? the bus layer has to define this... */
- BUG_ON(i2400m->bus_tx_block_size == 0);
-error_kmalloc:
- return result;
-
-}
-
-
-/**
- * i2400m_tx_release - Tear down the TX queue and infrastructure
- */
-void i2400m_tx_release(struct i2400m *i2400m)
-{
- unsigned long flags;
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- kfree(i2400m->tx_buf);
- i2400m->tx_buf = NULL;
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Debug levels control file for the i2400m-usb module
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-#ifndef __debug_levels__h__
-#define __debug_levels__h__
-
-/* Maximum compile and run time debug level for all submodules */
-#define D_MODULENAME i2400m_usb
-#define D_MASTER CONFIG_WIMAX_I2400M_DEBUG_LEVEL
-
-#include <linux/wimax/debug.h>
-
-/* List of all the enabled modules */
-enum d_module {
- D_SUBMODULE_DECLARE(usb),
- D_SUBMODULE_DECLARE(fw),
- D_SUBMODULE_DECLARE(notif),
- D_SUBMODULE_DECLARE(rx),
- D_SUBMODULE_DECLARE(tx),
-};
-
-
-#endif /* #ifndef __debug_levels__h__ */
+++ /dev/null
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Firmware uploader's USB specifics
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * - Initial implementation
- *
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * - bus generic/specific split
- *
- * THE PROCEDURE
- *
- * See fw.c for the generic description of this procedure.
- *
- * This file implements only the USB specifics. It boils down to how
- * to send a command and waiting for an acknowledgement from the
- * device.
- *
- * This code (and process) is single threaded. It assumes it is the
- * only thread poking around (guaranteed by fw.c).
- *
- * COMMAND EXECUTION
- *
- * A write URB is posted with the buffer to the bulk output endpoint.
- *
- * ACK RECEPTION
- *
- * We just post a URB to the notification endpoint and wait for
- * data. We repeat until we get all the data we expect (as indicated
- * by the call from the bus generic code).
- *
- * The data is not read from the bulk in endpoint for boot mode.
- *
- * ROADMAP
- *
- * i2400mu_bus_bm_cmd_send
- * i2400m_bm_cmd_prepare...
- * i2400mu_tx_bulk_out
- *
- * i2400mu_bus_bm_wait_for_ack
- * i2400m_notif_submit
- */
-#include <linux/usb.h>
-#include <linux/gfp.h>
-#include "i2400m-usb.h"
-
-
-#define D_SUBMODULE fw
-#include "usb-debug-levels.h"
-
-
-/*
- * Synchronous write to the device
- *
- * Takes care of updating EDC counts and thus, handle device errors.
- */
-static
-ssize_t i2400mu_tx_bulk_out(struct i2400mu *i2400mu, void *buf, size_t buf_size)
-{
- int result;
- struct device *dev = &i2400mu->usb_iface->dev;
- int len;
- struct usb_endpoint_descriptor *epd;
- int pipe, do_autopm = 1;
-
- result = usb_autopm_get_interface(i2400mu->usb_iface);
- if (result < 0) {
- dev_err(dev, "BM-CMD: can't get autopm: %d\n", result);
- do_autopm = 0;
- }
- epd = usb_get_epd(i2400mu->usb_iface, i2400mu->endpoint_cfg.bulk_out);
- pipe = usb_sndbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
-retry:
- result = usb_bulk_msg(i2400mu->usb_dev, pipe, buf, buf_size, &len, 200);
- switch (result) {
- case 0:
- if (len != buf_size) {
- dev_err(dev, "BM-CMD: short write (%u B vs %zu "
- "expected)\n", len, buf_size);
- result = -EIO;
- break;
- }
- result = len;
- break;
- case -EPIPE:
- /*
- * Stall -- maybe the device is choking with our
- * requests. Clear it and give it some time. If they
- * happen to often, it might be another symptom, so we
- * reset.
- *
- * No error handling for usb_clear_halt(0; if it
- * works, the retry works; if it fails, this switch
- * does the error handling for us.
- */
- if (edc_inc(&i2400mu->urb_edc,
- 10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
- dev_err(dev, "BM-CMD: too many stalls in "
- "URB; resetting device\n");
- usb_queue_reset_device(i2400mu->usb_iface);
- } else {
- usb_clear_halt(i2400mu->usb_dev, pipe);
- msleep(10); /* give the device some time */
- goto retry;
- }
- fallthrough;
- case -EINVAL: /* while removing driver */
- case -ENODEV: /* dev disconnect ... */
- case -ENOENT: /* just ignore it */
- case -ESHUTDOWN: /* and exit */
- case -ECONNRESET:
- result = -ESHUTDOWN;
- break;
- case -ETIMEDOUT: /* bah... */
- break;
- default: /* any other? */
- if (edc_inc(&i2400mu->urb_edc,
- EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
- dev_err(dev, "BM-CMD: maximum errors in "
- "URB exceeded; resetting device\n");
- usb_queue_reset_device(i2400mu->usb_iface);
- result = -ENODEV;
- break;
- }
- dev_err(dev, "BM-CMD: URB error %d, retrying\n",
- result);
- goto retry;
- }
- if (do_autopm)
- usb_autopm_put_interface(i2400mu->usb_iface);
- return result;
-}
-
-
-/*
- * Send a boot-mode command over the bulk-out pipe
- *
- * Command can be a raw command, which requires no preparation (and
- * which might not even be following the command format). Checks that
- * the right amount of data was transferred.
- *
- * To satisfy USB requirements (no onstack, vmalloc or in data segment
- * buffers), we copy the command to i2400m->bm_cmd_buf and send it from
- * there.
- *
- * @flags: pass thru from i2400m_bm_cmd()
- * @return: cmd_size if ok, < 0 errno code on error.
- */
-ssize_t i2400mu_bus_bm_cmd_send(struct i2400m *i2400m,
- const struct i2400m_bootrom_header *_cmd,
- size_t cmd_size, int flags)
-{
- ssize_t result;
- struct device *dev = i2400m_dev(i2400m);
- struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
- int opcode = _cmd == NULL ? -1 : i2400m_brh_get_opcode(_cmd);
- struct i2400m_bootrom_header *cmd;
- size_t cmd_size_a = ALIGN(cmd_size, 16); /* USB restriction */
-
- d_fnstart(8, dev, "(i2400m %p cmd %p size %zu)\n",
- i2400m, _cmd, cmd_size);
- result = -E2BIG;
- if (cmd_size > I2400M_BM_CMD_BUF_SIZE)
- goto error_too_big;
- if (_cmd != i2400m->bm_cmd_buf)
- memmove(i2400m->bm_cmd_buf, _cmd, cmd_size);
- cmd = i2400m->bm_cmd_buf;
- if (cmd_size_a > cmd_size) /* Zero pad space */
- memset(i2400m->bm_cmd_buf + cmd_size, 0, cmd_size_a - cmd_size);
- if ((flags & I2400M_BM_CMD_RAW) == 0) {
- if (WARN_ON(i2400m_brh_get_response_required(cmd) == 0))
- dev_warn(dev, "SW BUG: response_required == 0\n");
- i2400m_bm_cmd_prepare(cmd);
- }
- result = i2400mu_tx_bulk_out(i2400mu, i2400m->bm_cmd_buf, cmd_size);
- if (result < 0) {
- dev_err(dev, "boot-mode cmd %d: cannot send: %zd\n",
- opcode, result);
- goto error_cmd_send;
- }
- if (result != cmd_size) { /* all was transferred? */
- dev_err(dev, "boot-mode cmd %d: incomplete transfer "
- "(%zd vs %zu submitted)\n", opcode, result, cmd_size);
- result = -EIO;
- goto error_cmd_size;
- }
-error_cmd_size:
-error_cmd_send:
-error_too_big:
- d_fnend(8, dev, "(i2400m %p cmd %p size %zu) = %zd\n",
- i2400m, _cmd, cmd_size, result);
- return result;
-}
-
-
-static
-void __i2400mu_bm_notif_cb(struct urb *urb)
-{
- complete(urb->context);
-}
-
-
-/*
- * submit a read to the notification endpoint
- *
- * @i2400m: device descriptor
- * @urb: urb to use
- * @completion: completion variable to complete when done
- *
- * Data is always read to i2400m->bm_ack_buf
- */
-static
-int i2400mu_notif_submit(struct i2400mu *i2400mu, struct urb *urb,
- struct completion *completion)
-{
- struct i2400m *i2400m = &i2400mu->i2400m;
- struct usb_endpoint_descriptor *epd;
- int pipe;
-
- epd = usb_get_epd(i2400mu->usb_iface,
- i2400mu->endpoint_cfg.notification);
- pipe = usb_rcvintpipe(i2400mu->usb_dev, epd->bEndpointAddress);
- usb_fill_int_urb(urb, i2400mu->usb_dev, pipe,
- i2400m->bm_ack_buf, I2400M_BM_ACK_BUF_SIZE,
- __i2400mu_bm_notif_cb, completion,
- epd->bInterval);
- return usb_submit_urb(urb, GFP_KERNEL);
-}
-
-
-/*
- * Read an ack from the notification endpoint
- *
- * @i2400m:
- * @_ack: pointer to where to store the read data
- * @ack_size: how many bytes we should read
- *
- * Returns: < 0 errno code on error; otherwise, amount of received bytes.
- *
- * Submits a notification read, appends the read data to the given ack
- * buffer and then repeats (until @ack_size bytes have been
- * received).
- */
-ssize_t i2400mu_bus_bm_wait_for_ack(struct i2400m *i2400m,
- struct i2400m_bootrom_header *_ack,
- size_t ack_size)
-{
- ssize_t result = -ENOMEM;
- struct device *dev = i2400m_dev(i2400m);
- struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
- struct urb notif_urb;
- void *ack = _ack;
- size_t offset, len;
- long val;
- int do_autopm = 1;
- DECLARE_COMPLETION_ONSTACK(notif_completion);
-
- d_fnstart(8, dev, "(i2400m %p ack %p size %zu)\n",
- i2400m, ack, ack_size);
- BUG_ON(_ack == i2400m->bm_ack_buf);
- result = usb_autopm_get_interface(i2400mu->usb_iface);
- if (result < 0) {
- dev_err(dev, "BM-ACK: can't get autopm: %d\n", (int) result);
- do_autopm = 0;
- }
- usb_init_urb(¬if_urb); /* ready notifications */
- usb_get_urb(¬if_urb);
- offset = 0;
- while (offset < ack_size) {
- init_completion(¬if_completion);
- result = i2400mu_notif_submit(i2400mu, ¬if_urb,
- ¬if_completion);
- if (result < 0)
- goto error_notif_urb_submit;
- val = wait_for_completion_interruptible_timeout(
- ¬if_completion, HZ);
- if (val == 0) {
- result = -ETIMEDOUT;
- usb_kill_urb(¬if_urb); /* Timedout */
- goto error_notif_wait;
- }
- if (val == -ERESTARTSYS) {
- result = -EINTR; /* Interrupted */
- usb_kill_urb(¬if_urb);
- goto error_notif_wait;
- }
- result = notif_urb.status; /* How was the ack? */
- switch (result) {
- case 0:
- break;
- case -EINVAL: /* while removing driver */
- case -ENODEV: /* dev disconnect ... */
- case -ENOENT: /* just ignore it */
- case -ESHUTDOWN: /* and exit */
- case -ECONNRESET:
- result = -ESHUTDOWN;
- goto error_dev_gone;
- default: /* any other? */
- usb_kill_urb(¬if_urb); /* Timedout */
- if (edc_inc(&i2400mu->urb_edc,
- EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME))
- goto error_exceeded;
- dev_err(dev, "BM-ACK: URB error %d, "
- "retrying\n", notif_urb.status);
- continue; /* retry */
- }
- if (notif_urb.actual_length == 0) {
- d_printf(6, dev, "ZLP received, retrying\n");
- continue;
- }
- /* Got data, append it to the buffer */
- len = min(ack_size - offset, (size_t) notif_urb.actual_length);
- memcpy(ack + offset, i2400m->bm_ack_buf, len);
- offset += len;
- }
- result = offset;
-error_notif_urb_submit:
-error_notif_wait:
-error_dev_gone:
-out:
- if (do_autopm)
- usb_autopm_put_interface(i2400mu->usb_iface);
- d_fnend(8, dev, "(i2400m %p ack %p size %zu) = %ld\n",
- i2400m, ack, ack_size, (long) result);
- usb_put_urb(¬if_urb);
- return result;
-
-error_exceeded:
- dev_err(dev, "bm: maximum errors in notification URB exceeded; "
- "resetting device\n");
- usb_queue_reset_device(i2400mu->usb_iface);
- goto out;
-}
+++ /dev/null
-/*
- * Intel Wireless WiMAX Connection 2400m over USB
- * Notification handling
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * - Initial implementation
- *
- *
- * The notification endpoint is active when the device is not in boot
- * mode; in here we just read and get notifications; based on those,
- * we act to either reinitialize the device after a reboot or to
- * submit a RX request.
- *
- * ROADMAP
- *
- * i2400mu_usb_notification_setup()
- *
- * i2400mu_usb_notification_release()
- *
- * i2400mu_usb_notification_cb() Called when a URB is ready
- * i2400mu_notif_grok()
- * i2400m_is_boot_barker()
- * i2400m_dev_reset_handle()
- * i2400mu_rx_kick()
- */
-#include <linux/usb.h>
-#include <linux/slab.h>
-#include "i2400m-usb.h"
-
-
-#define D_SUBMODULE notif
-#include "usb-debug-levels.h"
-
-
-static const
-__le32 i2400m_ZERO_BARKER[4] = { 0, 0, 0, 0 };
-
-
-/*
- * Process a received notification
- *
- * In normal operation mode, we can only receive two types of payloads
- * on the notification endpoint:
- *
- * - a reboot barker, we do a bootstrap (the device has reseted).
- *
- * - a block of zeroes: there is pending data in the IN endpoint
- */
-static
-int i2400mu_notification_grok(struct i2400mu *i2400mu, const void *buf,
- size_t buf_len)
-{
- int ret;
- struct device *dev = &i2400mu->usb_iface->dev;
- struct i2400m *i2400m = &i2400mu->i2400m;
-
- d_fnstart(4, dev, "(i2400m %p buf %p buf_len %zu)\n",
- i2400mu, buf, buf_len);
- ret = -EIO;
- if (buf_len < sizeof(i2400m_ZERO_BARKER))
- /* Not a bug, just ignore */
- goto error_bad_size;
- ret = 0;
- if (!memcmp(i2400m_ZERO_BARKER, buf, sizeof(i2400m_ZERO_BARKER))) {
- i2400mu_rx_kick(i2400mu);
- goto out;
- }
- ret = i2400m_is_boot_barker(i2400m, buf, buf_len);
- if (unlikely(ret >= 0))
- ret = i2400m_dev_reset_handle(i2400m, "device rebooted");
- else /* Unknown or unexpected data in the notif message */
- i2400m_unknown_barker(i2400m, buf, buf_len);
-error_bad_size:
-out:
- d_fnend(4, dev, "(i2400m %p buf %p buf_len %zu) = %d\n",
- i2400mu, buf, buf_len, ret);
- return ret;
-}
-
-
-/*
- * URB callback for the notification endpoint
- *
- * @urb: the urb received from the notification endpoint
- *
- * This function will just process the USB side of the transaction,
- * checking everything is fine, pass the processing to
- * i2400m_notification_grok() and resubmit the URB.
- */
-static
-void i2400mu_notification_cb(struct urb *urb)
-{
- int ret;
- struct i2400mu *i2400mu = urb->context;
- struct device *dev = &i2400mu->usb_iface->dev;
-
- d_fnstart(4, dev, "(urb %p status %d actual_length %d)\n",
- urb, urb->status, urb->actual_length);
- ret = urb->status;
- switch (ret) {
- case 0:
- ret = i2400mu_notification_grok(i2400mu, urb->transfer_buffer,
- urb->actual_length);
- if (ret == -EIO && edc_inc(&i2400mu->urb_edc, EDC_MAX_ERRORS,
- EDC_ERROR_TIMEFRAME))
- goto error_exceeded;
- if (ret == -ENOMEM) /* uff...power cycle? shutdown? */
- goto error_exceeded;
- break;
- case -EINVAL: /* while removing driver */
- case -ENODEV: /* dev disconnect ... */
- case -ENOENT: /* ditto */
- case -ESHUTDOWN: /* URB killed */
- case -ECONNRESET: /* disconnection */
- goto out; /* Notify around */
- default: /* Some error? */
- if (edc_inc(&i2400mu->urb_edc,
- EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME))
- goto error_exceeded;
- dev_err(dev, "notification: URB error %d, retrying\n",
- urb->status);
- }
- usb_mark_last_busy(i2400mu->usb_dev);
- ret = usb_submit_urb(i2400mu->notif_urb, GFP_ATOMIC);
- switch (ret) {
- case 0:
- case -EINVAL: /* while removing driver */
- case -ENODEV: /* dev disconnect ... */
- case -ENOENT: /* ditto */
- case -ESHUTDOWN: /* URB killed */
- case -ECONNRESET: /* disconnection */
- break; /* just ignore */
- default: /* Some error? */
- dev_err(dev, "notification: cannot submit URB: %d\n", ret);
- goto error_submit;
- }
- d_fnend(4, dev, "(urb %p status %d actual_length %d) = void\n",
- urb, urb->status, urb->actual_length);
- return;
-
-error_exceeded:
- dev_err(dev, "maximum errors in notification URB exceeded; "
- "resetting device\n");
-error_submit:
- usb_queue_reset_device(i2400mu->usb_iface);
-out:
- d_fnend(4, dev, "(urb %p status %d actual_length %d) = void\n",
- urb, urb->status, urb->actual_length);
-}
-
-
-/*
- * setup the notification endpoint
- *
- * @i2400m: device descriptor
- *
- * This procedure prepares the notification urb and handler for receiving
- * unsolicited barkers from the device.
- */
-int i2400mu_notification_setup(struct i2400mu *i2400mu)
-{
- struct device *dev = &i2400mu->usb_iface->dev;
- int usb_pipe, ret = 0;
- struct usb_endpoint_descriptor *epd;
- char *buf;
-
- d_fnstart(4, dev, "(i2400m %p)\n", i2400mu);
- buf = kmalloc(I2400MU_MAX_NOTIFICATION_LEN, GFP_KERNEL | GFP_DMA);
- if (buf == NULL) {
- ret = -ENOMEM;
- goto error_buf_alloc;
- }
-
- i2400mu->notif_urb = usb_alloc_urb(0, GFP_KERNEL);
- if (!i2400mu->notif_urb) {
- ret = -ENOMEM;
- goto error_alloc_urb;
- }
- epd = usb_get_epd(i2400mu->usb_iface,
- i2400mu->endpoint_cfg.notification);
- usb_pipe = usb_rcvintpipe(i2400mu->usb_dev, epd->bEndpointAddress);
- usb_fill_int_urb(i2400mu->notif_urb, i2400mu->usb_dev, usb_pipe,
- buf, I2400MU_MAX_NOTIFICATION_LEN,
- i2400mu_notification_cb, i2400mu, epd->bInterval);
- ret = usb_submit_urb(i2400mu->notif_urb, GFP_KERNEL);
- if (ret != 0) {
- dev_err(dev, "notification: cannot submit URB: %d\n", ret);
- goto error_submit;
- }
- d_fnend(4, dev, "(i2400m %p) = %d\n", i2400mu, ret);
- return ret;
-
-error_submit:
- usb_free_urb(i2400mu->notif_urb);
-error_alloc_urb:
- kfree(buf);
-error_buf_alloc:
- d_fnend(4, dev, "(i2400m %p) = %d\n", i2400mu, ret);
- return ret;
-}
-
-
-/*
- * Tear down of the notification mechanism
- *
- * @i2400m: device descriptor
- *
- * Kill the interrupt endpoint urb, free any allocated resources.
- *
- * We need to check if we have done it before as for example,
- * _suspend() call this; if after a suspend() we get a _disconnect()
- * (as the case is when hibernating), nothing bad happens.
- */
-void i2400mu_notification_release(struct i2400mu *i2400mu)
-{
- struct device *dev = &i2400mu->usb_iface->dev;
-
- d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
- if (i2400mu->notif_urb != NULL) {
- usb_kill_urb(i2400mu->notif_urb);
- kfree(i2400mu->notif_urb->transfer_buffer);
- usb_free_urb(i2400mu->notif_urb);
- i2400mu->notif_urb = NULL;
- }
- d_fnend(4, dev, "(i2400mu %p)\n", i2400mu);
-}
+++ /dev/null
-/*
- * Intel Wireless WiMAX Connection 2400m
- * USB RX handling
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * - Initial implementation
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * - Use skb_clone(), break up processing in chunks
- * - Split transport/device specific
- * - Make buffer size dynamic to exert less memory pressure
- *
- *
- * This handles the RX path on USB.
- *
- * When a notification is received that says 'there is RX data ready',
- * we call i2400mu_rx_kick(); that wakes up the RX kthread, which
- * reads a buffer from USB and passes it to i2400m_rx() in the generic
- * handling code. The RX buffer has an specific format that is
- * described in rx.c.
- *
- * We use a kernel thread in a loop because:
- *
- * - we want to be able to call the USB power management get/put
- * functions (blocking) before each transaction.
- *
- * - We might get a lot of notifications and we don't want to submit
- * a zillion reads; by serializing, we are throttling.
- *
- * - RX data processing can get heavy enough so that it is not
- * appropriate for doing it in the USB callback; thus we run it in a
- * process context.
- *
- * We provide a read buffer of an arbitrary size (short of a page); if
- * the callback reports -EOVERFLOW, it means it was too small, so we
- * just double the size and retry (being careful to append, as
- * sometimes the device provided some data). Every now and then we
- * check if the average packet size is smaller than the current packet
- * size and if so, we halve it. At the end, the size of the
- * preallocated buffer should be following the average received
- * transaction size, adapting dynamically to it.
- *
- * ROADMAP
- *
- * i2400mu_rx_kick() Called from notif.c when we get a
- * 'data ready' notification
- * i2400mu_rxd() Kernel RX daemon
- * i2400mu_rx() Receive USB data
- * i2400m_rx() Send data to generic i2400m RX handling
- *
- * i2400mu_rx_setup() called from i2400mu_bus_dev_start()
- *
- * i2400mu_rx_release() called from i2400mu_bus_dev_stop()
- */
-#include <linux/workqueue.h>
-#include <linux/slab.h>
-#include <linux/usb.h>
-#include "i2400m-usb.h"
-
-
-#define D_SUBMODULE rx
-#include "usb-debug-levels.h"
-
-/*
- * Dynamic RX size
- *
- * We can't let the rx_size be a multiple of 512 bytes (the RX
- * endpoint's max packet size). On some USB host controllers (we
- * haven't been able to fully characterize which), if the device is
- * about to send (for example) X bytes and we only post a buffer to
- * receive n*512, it will fail to mark that as babble (so that
- * i2400mu_rx() [case -EOVERFLOW] can resize the buffer and get the
- * rest).
- *
- * So on growing or shrinking, if it is a multiple of the
- * maxpacketsize, we remove some (instead of incresing some, so in a
- * buddy allocator we try to waste less space).
- *
- * Note we also need a hook for this on i2400mu_rx() -- when we do the
- * first read, we are sure we won't hit this spot because
- * i240mm->rx_size has been set properly. However, if we have to
- * double because of -EOVERFLOW, when we launch the read to get the
- * rest of the data, we *have* to make sure that also is not a
- * multiple of the max_pkt_size.
- */
-
-static
-size_t i2400mu_rx_size_grow(struct i2400mu *i2400mu)
-{
- struct device *dev = &i2400mu->usb_iface->dev;
- size_t rx_size;
- const size_t max_pkt_size = 512;
-
- rx_size = 2 * i2400mu->rx_size;
- if (rx_size % max_pkt_size == 0) {
- rx_size -= 8;
- d_printf(1, dev,
- "RX: expected size grew to %zu [adjusted -8] "
- "from %zu\n",
- rx_size, i2400mu->rx_size);
- } else
- d_printf(1, dev,
- "RX: expected size grew to %zu from %zu\n",
- rx_size, i2400mu->rx_size);
- return rx_size;
-}
-
-
-static
-void i2400mu_rx_size_maybe_shrink(struct i2400mu *i2400mu)
-{
- const size_t max_pkt_size = 512;
- struct device *dev = &i2400mu->usb_iface->dev;
-
- if (unlikely(i2400mu->rx_size_cnt >= 100
- && i2400mu->rx_size_auto_shrink)) {
- size_t avg_rx_size =
- i2400mu->rx_size_acc / i2400mu->rx_size_cnt;
- size_t new_rx_size = i2400mu->rx_size / 2;
- if (avg_rx_size < new_rx_size) {
- if (new_rx_size % max_pkt_size == 0) {
- new_rx_size -= 8;
- d_printf(1, dev,
- "RX: expected size shrank to %zu "
- "[adjusted -8] from %zu\n",
- new_rx_size, i2400mu->rx_size);
- } else
- d_printf(1, dev,
- "RX: expected size shrank to %zu "
- "from %zu\n",
- new_rx_size, i2400mu->rx_size);
- i2400mu->rx_size = new_rx_size;
- i2400mu->rx_size_cnt = 0;
- i2400mu->rx_size_acc = i2400mu->rx_size;
- }
- }
-}
-
-/*
- * Receive a message with payloads from the USB bus into an skb
- *
- * @i2400mu: USB device descriptor
- * @rx_skb: skb where to place the received message
- *
- * Deals with all the USB-specifics of receiving, dynamically
- * increasing the buffer size if so needed. Returns the payload in the
- * skb, ready to process. On a zero-length packet, we retry.
- *
- * On soft USB errors, we retry (until they become too frequent and
- * then are promoted to hard); on hard USB errors, we reset the
- * device. On other errors (skb realloacation, we just drop it and
- * hope for the next invocation to solve it).
- *
- * Returns: pointer to the skb if ok, ERR_PTR on error.
- * NOTE: this function might realloc the skb (if it is too small),
- * so always update with the one returned.
- * ERR_PTR() is < 0 on error.
- * Will return NULL if it cannot reallocate -- this can be
- * considered a transient retryable error.
- */
-static
-struct sk_buff *i2400mu_rx(struct i2400mu *i2400mu, struct sk_buff *rx_skb)
-{
- int result = 0;
- struct device *dev = &i2400mu->usb_iface->dev;
- int usb_pipe, read_size, rx_size, do_autopm;
- struct usb_endpoint_descriptor *epd;
- const size_t max_pkt_size = 512;
-
- d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
- do_autopm = atomic_read(&i2400mu->do_autopm);
- result = do_autopm ?
- usb_autopm_get_interface(i2400mu->usb_iface) : 0;
- if (result < 0) {
- dev_err(dev, "RX: can't get autopm: %d\n", result);
- do_autopm = 0;
- }
- epd = usb_get_epd(i2400mu->usb_iface, i2400mu->endpoint_cfg.bulk_in);
- usb_pipe = usb_rcvbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
-retry:
- rx_size = skb_end_pointer(rx_skb) - rx_skb->data - rx_skb->len;
- if (unlikely(rx_size % max_pkt_size == 0)) {
- rx_size -= 8;
- d_printf(1, dev, "RX: rx_size adapted to %d [-8]\n", rx_size);
- }
- result = usb_bulk_msg(
- i2400mu->usb_dev, usb_pipe, rx_skb->data + rx_skb->len,
- rx_size, &read_size, 200);
- usb_mark_last_busy(i2400mu->usb_dev);
- switch (result) {
- case 0:
- if (read_size == 0)
- goto retry; /* ZLP, just resubmit */
- skb_put(rx_skb, read_size);
- break;
- case -EPIPE:
- /*
- * Stall -- maybe the device is choking with our
- * requests. Clear it and give it some time. If they
- * happen to often, it might be another symptom, so we
- * reset.
- *
- * No error handling for usb_clear_halt(0; if it
- * works, the retry works; if it fails, this switch
- * does the error handling for us.
- */
- if (edc_inc(&i2400mu->urb_edc,
- 10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
- dev_err(dev, "BM-CMD: too many stalls in "
- "URB; resetting device\n");
- goto do_reset;
- }
- usb_clear_halt(i2400mu->usb_dev, usb_pipe);
- msleep(10); /* give the device some time */
- goto retry;
- case -EINVAL: /* while removing driver */
- case -ENODEV: /* dev disconnect ... */
- case -ENOENT: /* just ignore it */
- case -ESHUTDOWN:
- case -ECONNRESET:
- break;
- case -EOVERFLOW: { /* too small, reallocate */
- struct sk_buff *new_skb;
- rx_size = i2400mu_rx_size_grow(i2400mu);
- if (rx_size <= (1 << 16)) /* cap it */
- i2400mu->rx_size = rx_size;
- else if (printk_ratelimit()) {
- dev_err(dev, "BUG? rx_size up to %d\n", rx_size);
- result = -EINVAL;
- goto out;
- }
- skb_put(rx_skb, read_size);
- new_skb = skb_copy_expand(rx_skb, 0, rx_size - rx_skb->len,
- GFP_KERNEL);
- if (new_skb == NULL) {
- kfree_skb(rx_skb);
- rx_skb = NULL;
- goto out; /* drop it...*/
- }
- kfree_skb(rx_skb);
- rx_skb = new_skb;
- i2400mu->rx_size_cnt = 0;
- i2400mu->rx_size_acc = i2400mu->rx_size;
- d_printf(1, dev, "RX: size changed to %d, received %d, "
- "copied %d, capacity %ld\n",
- rx_size, read_size, rx_skb->len,
- (long) skb_end_offset(new_skb));
- goto retry;
- }
- /* In most cases, it happens due to the hardware scheduling a
- * read when there was no data - unfortunately, we have no way
- * to tell this timeout from a USB timeout. So we just ignore
- * it. */
- case -ETIMEDOUT:
- dev_err(dev, "RX: timeout: %d\n", result);
- result = 0;
- break;
- default: /* Any error */
- if (edc_inc(&i2400mu->urb_edc,
- EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME))
- goto error_reset;
- dev_err(dev, "RX: error receiving URB: %d, retrying\n", result);
- goto retry;
- }
-out:
- if (do_autopm)
- usb_autopm_put_interface(i2400mu->usb_iface);
- d_fnend(4, dev, "(i2400mu %p) = %p\n", i2400mu, rx_skb);
- return rx_skb;
-
-error_reset:
- dev_err(dev, "RX: maximum errors in URB exceeded; "
- "resetting device\n");
-do_reset:
- usb_queue_reset_device(i2400mu->usb_iface);
- rx_skb = ERR_PTR(result);
- goto out;
-}
-
-
-/*
- * Kernel thread for USB reception of data
- *
- * This thread waits for a kick; once kicked, it will allocate an skb
- * and receive a single message to it from USB (using
- * i2400mu_rx()). Once received, it is passed to the generic i2400m RX
- * code for processing.
- *
- * When done processing, it runs some dirty statistics to verify if
- * the last 100 messages received were smaller than half of the
- * current RX buffer size. In that case, the RX buffer size is
- * halved. This will helps lowering the pressure on the memory
- * allocator.
- *
- * Hard errors force the thread to exit.
- */
-static
-int i2400mu_rxd(void *_i2400mu)
-{
- int result = 0;
- struct i2400mu *i2400mu = _i2400mu;
- struct i2400m *i2400m = &i2400mu->i2400m;
- struct device *dev = &i2400mu->usb_iface->dev;
- struct net_device *net_dev = i2400m->wimax_dev.net_dev;
- size_t pending;
- int rx_size;
- struct sk_buff *rx_skb;
- unsigned long flags;
-
- d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- BUG_ON(i2400mu->rx_kthread != NULL);
- i2400mu->rx_kthread = current;
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- while (1) {
- d_printf(2, dev, "RX: waiting for messages\n");
- pending = 0;
- wait_event_interruptible(
- i2400mu->rx_wq,
- (kthread_should_stop() /* check this first! */
- || (pending = atomic_read(&i2400mu->rx_pending_count)))
- );
- if (kthread_should_stop())
- break;
- if (pending == 0)
- continue;
- rx_size = i2400mu->rx_size;
- d_printf(2, dev, "RX: reading up to %d bytes\n", rx_size);
- rx_skb = __netdev_alloc_skb(net_dev, rx_size, GFP_KERNEL);
- if (rx_skb == NULL) {
- dev_err(dev, "RX: can't allocate skb [%d bytes]\n",
- rx_size);
- msleep(50); /* give it some time? */
- continue;
- }
-
- /* Receive the message with the payloads */
- rx_skb = i2400mu_rx(i2400mu, rx_skb);
- result = PTR_ERR(rx_skb);
- if (IS_ERR(rx_skb))
- goto out;
- atomic_dec(&i2400mu->rx_pending_count);
- if (rx_skb == NULL || rx_skb->len == 0) {
- /* some "ignorable" condition */
- kfree_skb(rx_skb);
- continue;
- }
-
- /* Deliver the message to the generic i2400m code */
- i2400mu->rx_size_cnt++;
- i2400mu->rx_size_acc += rx_skb->len;
- result = i2400m_rx(i2400m, rx_skb);
- if (result == -EIO
- && edc_inc(&i2400mu->urb_edc,
- EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
- goto error_reset;
- }
-
- /* Maybe adjust RX buffer size */
- i2400mu_rx_size_maybe_shrink(i2400mu);
- }
- result = 0;
-out:
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- i2400mu->rx_kthread = NULL;
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- d_fnend(4, dev, "(i2400mu %p) = %d\n", i2400mu, result);
- return result;
-
-error_reset:
- dev_err(dev, "RX: maximum errors in received buffer exceeded; "
- "resetting device\n");
- usb_queue_reset_device(i2400mu->usb_iface);
- goto out;
-}
-
-
-/*
- * Start reading from the device
- *
- * @i2400m: device instance
- *
- * Notify the RX thread that there is data pending.
- */
-void i2400mu_rx_kick(struct i2400mu *i2400mu)
-{
- struct i2400m *i2400m = &i2400mu->i2400m;
- struct device *dev = &i2400mu->usb_iface->dev;
-
- d_fnstart(3, dev, "(i2400mu %p)\n", i2400m);
- atomic_inc(&i2400mu->rx_pending_count);
- wake_up_all(&i2400mu->rx_wq);
- d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
-
-
-int i2400mu_rx_setup(struct i2400mu *i2400mu)
-{
- int result = 0;
- struct i2400m *i2400m = &i2400mu->i2400m;
- struct device *dev = &i2400mu->usb_iface->dev;
- struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
- struct task_struct *kthread;
-
- kthread = kthread_run(i2400mu_rxd, i2400mu, "%s-rx",
- wimax_dev->name);
- /* the kthread function sets i2400mu->rx_thread */
- if (IS_ERR(kthread)) {
- result = PTR_ERR(kthread);
- dev_err(dev, "RX: cannot start thread: %d\n", result);
- }
- return result;
-}
-
-
-void i2400mu_rx_release(struct i2400mu *i2400mu)
-{
- unsigned long flags;
- struct i2400m *i2400m = &i2400mu->i2400m;
- struct device *dev = i2400m_dev(i2400m);
- struct task_struct *kthread;
-
- spin_lock_irqsave(&i2400m->rx_lock, flags);
- kthread = i2400mu->rx_kthread;
- i2400mu->rx_kthread = NULL;
- spin_unlock_irqrestore(&i2400m->rx_lock, flags);
- if (kthread)
- kthread_stop(kthread);
- else
- d_printf(1, dev, "RX: kthread had already exited\n");
-}
-
+++ /dev/null
-/*
- * Intel Wireless WiMAX Connection 2400m
- * USB specific TX handling
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * - Initial implementation
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * - Split transport/device specific
- *
- *
- * Takes the TX messages in the i2400m's driver TX FIFO and sends them
- * to the device until there are no more.
- *
- * If we fail sending the message, we just drop it. There isn't much
- * we can do at this point. We could also retry, but the USB stack has
- * already retried and still failed, so there is not much of a
- * point. As well, most of the traffic is network, which has recovery
- * methods for dropped packets.
- *
- * For sending we just obtain a FIFO buffer to send, send it to the
- * USB bulk out, tell the TX FIFO code we have sent it; query for
- * another one, etc... until done.
- *
- * We use a thread so we can call usb_autopm_enable() and
- * usb_autopm_disable() for each transaction; this way when the device
- * goes idle, it will suspend. It also has less overhead than a
- * dedicated workqueue, as it is being used for a single task.
- *
- * ROADMAP
- *
- * i2400mu_tx_setup()
- * i2400mu_tx_release()
- *
- * i2400mu_bus_tx_kick() - Called by the tx.c code when there
- * is new data in the FIFO.
- * i2400mu_txd()
- * i2400m_tx_msg_get()
- * i2400m_tx_msg_sent()
- */
-#include "i2400m-usb.h"
-
-
-#define D_SUBMODULE tx
-#include "usb-debug-levels.h"
-
-
-/*
- * Get the next TX message in the TX FIFO and send it to the device
- *
- * Note that any iteration consumes a message to be sent, no matter if
- * it succeeds or fails (we have no real way to retry or complain).
- *
- * Return: 0 if ok, < 0 errno code on hard error.
- */
-static
-int i2400mu_tx(struct i2400mu *i2400mu, struct i2400m_msg_hdr *tx_msg,
- size_t tx_msg_size)
-{
- int result = 0;
- struct i2400m *i2400m = &i2400mu->i2400m;
- struct device *dev = &i2400mu->usb_iface->dev;
- int usb_pipe, sent_size, do_autopm;
- struct usb_endpoint_descriptor *epd;
-
- d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
- do_autopm = atomic_read(&i2400mu->do_autopm);
- result = do_autopm ?
- usb_autopm_get_interface(i2400mu->usb_iface) : 0;
- if (result < 0) {
- dev_err(dev, "TX: can't get autopm: %d\n", result);
- do_autopm = 0;
- }
- epd = usb_get_epd(i2400mu->usb_iface, i2400mu->endpoint_cfg.bulk_out);
- usb_pipe = usb_sndbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
-retry:
- result = usb_bulk_msg(i2400mu->usb_dev, usb_pipe,
- tx_msg, tx_msg_size, &sent_size, 200);
- usb_mark_last_busy(i2400mu->usb_dev);
- switch (result) {
- case 0:
- if (sent_size != tx_msg_size) { /* Too short? drop it */
- dev_err(dev, "TX: short write (%d B vs %zu "
- "expected)\n", sent_size, tx_msg_size);
- result = -EIO;
- }
- break;
- case -EPIPE:
- /*
- * Stall -- maybe the device is choking with our
- * requests. Clear it and give it some time. If they
- * happen to often, it might be another symptom, so we
- * reset.
- *
- * No error handling for usb_clear_halt(0; if it
- * works, the retry works; if it fails, this switch
- * does the error handling for us.
- */
- if (edc_inc(&i2400mu->urb_edc,
- 10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
- dev_err(dev, "BM-CMD: too many stalls in "
- "URB; resetting device\n");
- usb_queue_reset_device(i2400mu->usb_iface);
- } else {
- usb_clear_halt(i2400mu->usb_dev, usb_pipe);
- msleep(10); /* give the device some time */
- goto retry;
- }
- fallthrough;
- case -EINVAL: /* while removing driver */
- case -ENODEV: /* dev disconnect ... */
- case -ENOENT: /* just ignore it */
- case -ESHUTDOWN: /* and exit */
- case -ECONNRESET:
- result = -ESHUTDOWN;
- break;
- default: /* Some error? */
- if (edc_inc(&i2400mu->urb_edc,
- EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
- dev_err(dev, "TX: maximum errors in URB "
- "exceeded; resetting device\n");
- usb_queue_reset_device(i2400mu->usb_iface);
- } else {
- dev_err(dev, "TX: cannot send URB; retrying. "
- "tx_msg @%zu %zu B [%d sent]: %d\n",
- (void *) tx_msg - i2400m->tx_buf,
- tx_msg_size, sent_size, result);
- goto retry;
- }
- }
- if (do_autopm)
- usb_autopm_put_interface(i2400mu->usb_iface);
- d_fnend(4, dev, "(i2400mu %p) = result\n", i2400mu);
- return result;
-}
-
-
-/*
- * Get the next TX message in the TX FIFO and send it to the device
- *
- * Note we exit the loop if i2400mu_tx() fails; that function only
- * fails on hard error (failing to tx a buffer not being one of them,
- * see its doc).
- *
- * Return: 0
- */
-static
-int i2400mu_txd(void *_i2400mu)
-{
- struct i2400mu *i2400mu = _i2400mu;
- struct i2400m *i2400m = &i2400mu->i2400m;
- struct device *dev = &i2400mu->usb_iface->dev;
- struct i2400m_msg_hdr *tx_msg;
- size_t tx_msg_size;
- unsigned long flags;
-
- d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
-
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- BUG_ON(i2400mu->tx_kthread != NULL);
- i2400mu->tx_kthread = current;
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-
- while (1) {
- d_printf(2, dev, "TX: waiting for messages\n");
- tx_msg = NULL;
- wait_event_interruptible(
- i2400mu->tx_wq,
- (kthread_should_stop() /* check this first! */
- || (tx_msg = i2400m_tx_msg_get(i2400m, &tx_msg_size)))
- );
- if (kthread_should_stop())
- break;
- WARN_ON(tx_msg == NULL); /* should not happen...*/
- d_printf(2, dev, "TX: submitting %zu bytes\n", tx_msg_size);
- d_dump(5, dev, tx_msg, tx_msg_size);
- /* Yeah, we ignore errors ... not much we can do */
- i2400mu_tx(i2400mu, tx_msg, tx_msg_size);
- i2400m_tx_msg_sent(i2400m); /* ack it, advance the FIFO */
- }
-
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- i2400mu->tx_kthread = NULL;
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-
- d_fnend(4, dev, "(i2400mu %p)\n", i2400mu);
- return 0;
-}
-
-
-/*
- * i2400m TX engine notifies us that there is data in the FIFO ready
- * for TX
- *
- * If there is a URB in flight, don't do anything; when it finishes,
- * it will see there is data in the FIFO and send it. Else, just
- * submit a write.
- */
-void i2400mu_bus_tx_kick(struct i2400m *i2400m)
-{
- struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
- struct device *dev = &i2400mu->usb_iface->dev;
-
- d_fnstart(3, dev, "(i2400m %p) = void\n", i2400m);
- wake_up_all(&i2400mu->tx_wq);
- d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
-
-
-int i2400mu_tx_setup(struct i2400mu *i2400mu)
-{
- int result = 0;
- struct i2400m *i2400m = &i2400mu->i2400m;
- struct device *dev = &i2400mu->usb_iface->dev;
- struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
- struct task_struct *kthread;
-
- kthread = kthread_run(i2400mu_txd, i2400mu, "%s-tx",
- wimax_dev->name);
- /* the kthread function sets i2400mu->tx_thread */
- if (IS_ERR(kthread)) {
- result = PTR_ERR(kthread);
- dev_err(dev, "TX: cannot start thread: %d\n", result);
- }
- return result;
-}
-
-void i2400mu_tx_release(struct i2400mu *i2400mu)
-{
- unsigned long flags;
- struct i2400m *i2400m = &i2400mu->i2400m;
- struct device *dev = i2400m_dev(i2400m);
- struct task_struct *kthread;
-
- spin_lock_irqsave(&i2400m->tx_lock, flags);
- kthread = i2400mu->tx_kthread;
- i2400mu->tx_kthread = NULL;
- spin_unlock_irqrestore(&i2400m->tx_lock, flags);
- if (kthread)
- kthread_stop(kthread);
- else
- d_printf(1, dev, "TX: kthread had already exited\n");
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Linux driver model glue for USB device, reset & fw upload
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- *
- * See i2400m-usb.h for a general description of this driver.
- *
- * This file implements driver model glue, and hook ups for the
- * generic driver to implement the bus-specific functions (device
- * communication setup/tear down, firmware upload and resetting).
- *
- * ROADMAP
- *
- * i2400mu_probe()
- * alloc_netdev()...
- * i2400mu_netdev_setup()
- * i2400mu_init()
- * i2400m_netdev_setup()
- * i2400m_setup()...
- *
- * i2400mu_disconnect
- * i2400m_release()
- * free_netdev()
- *
- * i2400mu_suspend()
- * i2400m_cmd_enter_powersave()
- * i2400mu_notification_release()
- *
- * i2400mu_resume()
- * i2400mu_notification_setup()
- *
- * i2400mu_bus_dev_start() Called by i2400m_dev_start() [who is
- * i2400mu_tx_setup() called by i2400m_setup()]
- * i2400mu_rx_setup()
- * i2400mu_notification_setup()
- *
- * i2400mu_bus_dev_stop() Called by i2400m_dev_stop() [who is
- * i2400mu_notification_release() called by i2400m_release()]
- * i2400mu_rx_release()
- * i2400mu_tx_release()
- *
- * i2400mu_bus_reset() Called by i2400m_reset
- * __i2400mu_reset()
- * __i2400mu_send_barker()
- * usb_reset_device()
- */
-#include "i2400m-usb.h"
-#include <linux/wimax/i2400m.h>
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-
-
-#define D_SUBMODULE usb
-#include "usb-debug-levels.h"
-
-static char i2400mu_debug_params[128];
-module_param_string(debug, i2400mu_debug_params, sizeof(i2400mu_debug_params),
- 0644);
-MODULE_PARM_DESC(debug,
- "String of space-separated NAME:VALUE pairs, where NAMEs "
- "are the different debug submodules and VALUE are the "
- "initial debug value to set.");
-
-/* Our firmware file name */
-static const char *i2400mu_bus_fw_names_5x50[] = {
-#define I2400MU_FW_FILE_NAME_v1_5 "i2400m-fw-usb-1.5.sbcf"
- I2400MU_FW_FILE_NAME_v1_5,
-#define I2400MU_FW_FILE_NAME_v1_4 "i2400m-fw-usb-1.4.sbcf"
- I2400MU_FW_FILE_NAME_v1_4,
- NULL,
-};
-
-
-static const char *i2400mu_bus_fw_names_6050[] = {
-#define I6050U_FW_FILE_NAME_v1_5 "i6050-fw-usb-1.5.sbcf"
- I6050U_FW_FILE_NAME_v1_5,
- NULL,
-};
-
-
-static
-int i2400mu_bus_dev_start(struct i2400m *i2400m)
-{
- int result;
- struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
- struct device *dev = &i2400mu->usb_iface->dev;
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
- result = i2400mu_tx_setup(i2400mu);
- if (result < 0)
- goto error_usb_tx_setup;
- result = i2400mu_rx_setup(i2400mu);
- if (result < 0)
- goto error_usb_rx_setup;
- result = i2400mu_notification_setup(i2400mu);
- if (result < 0)
- goto error_notif_setup;
- d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
- return result;
-
-error_notif_setup:
- i2400mu_rx_release(i2400mu);
-error_usb_rx_setup:
- i2400mu_tx_release(i2400mu);
-error_usb_tx_setup:
- d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
- return result;
-}
-
-
-static
-void i2400mu_bus_dev_stop(struct i2400m *i2400m)
-{
- struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
- struct device *dev = &i2400mu->usb_iface->dev;
-
- d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
- i2400mu_notification_release(i2400mu);
- i2400mu_rx_release(i2400mu);
- i2400mu_tx_release(i2400mu);
- d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
-
-
-/*
- * Sends a barker buffer to the device
- *
- * This helper will allocate a kmalloced buffer and use it to transmit
- * (then free it). Reason for this is that other arches cannot use
- * stack/vmalloc/text areas for DMA transfers.
- *
- * Error recovery here is simpler: anything is considered a hard error
- * and will move the reset code to use a last-resort bus-based reset.
- */
-static
-int __i2400mu_send_barker(struct i2400mu *i2400mu,
- const __le32 *barker,
- size_t barker_size,
- unsigned endpoint)
-{
- struct usb_endpoint_descriptor *epd = NULL;
- int pipe, actual_len, ret;
- struct device *dev = &i2400mu->usb_iface->dev;
- void *buffer;
- int do_autopm = 1;
-
- ret = usb_autopm_get_interface(i2400mu->usb_iface);
- if (ret < 0) {
- dev_err(dev, "RESET: can't get autopm: %d\n", ret);
- do_autopm = 0;
- }
- ret = -ENOMEM;
- buffer = kmalloc(barker_size, GFP_KERNEL);
- if (buffer == NULL)
- goto error_kzalloc;
- epd = usb_get_epd(i2400mu->usb_iface, endpoint);
- pipe = usb_sndbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
- memcpy(buffer, barker, barker_size);
-retry:
- ret = usb_bulk_msg(i2400mu->usb_dev, pipe, buffer, barker_size,
- &actual_len, 200);
- switch (ret) {
- case 0:
- if (actual_len != barker_size) { /* Too short? drop it */
- dev_err(dev, "E: %s: short write (%d B vs %zu "
- "expected)\n",
- __func__, actual_len, barker_size);
- ret = -EIO;
- }
- break;
- case -EPIPE:
- /*
- * Stall -- maybe the device is choking with our
- * requests. Clear it and give it some time. If they
- * happen to often, it might be another symptom, so we
- * reset.
- *
- * No error handling for usb_clear_halt(0; if it
- * works, the retry works; if it fails, this switch
- * does the error handling for us.
- */
- if (edc_inc(&i2400mu->urb_edc,
- 10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
- dev_err(dev, "E: %s: too many stalls in "
- "URB; resetting device\n", __func__);
- usb_queue_reset_device(i2400mu->usb_iface);
- /* fallthrough */
- } else {
- usb_clear_halt(i2400mu->usb_dev, pipe);
- msleep(10); /* give the device some time */
- goto retry;
- }
- fallthrough;
- case -EINVAL: /* while removing driver */
- case -ENODEV: /* dev disconnect ... */
- case -ENOENT: /* just ignore it */
- case -ESHUTDOWN: /* and exit */
- case -ECONNRESET:
- ret = -ESHUTDOWN;
- break;
- default: /* Some error? */
- if (edc_inc(&i2400mu->urb_edc,
- EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
- dev_err(dev, "E: %s: maximum errors in URB "
- "exceeded; resetting device\n",
- __func__);
- usb_queue_reset_device(i2400mu->usb_iface);
- } else {
- dev_warn(dev, "W: %s: cannot send URB: %d\n",
- __func__, ret);
- goto retry;
- }
- }
- kfree(buffer);
-error_kzalloc:
- if (do_autopm)
- usb_autopm_put_interface(i2400mu->usb_iface);
- return ret;
-}
-
-
-/*
- * Reset a device at different levels (warm, cold or bus)
- *
- * @i2400m: device descriptor
- * @reset_type: soft, warm or bus reset (I2400M_RT_WARM/SOFT/BUS)
- *
- * Warm and cold resets get a USB reset if they fail.
- *
- * Warm reset:
- *
- * The device will be fully reset internally, but won't be
- * disconnected from the USB bus (so no reenumeration will
- * happen). Firmware upload will be necessary.
- *
- * The device will send a reboot barker in the notification endpoint
- * that will trigger the driver to reinitialize the state
- * automatically from notif.c:i2400m_notification_grok() into
- * i2400m_dev_bootstrap_delayed().
- *
- * Cold and bus (USB) reset:
- *
- * The device will be fully reset internally, disconnected from the
- * USB bus an a reenumeration will happen. Firmware upload will be
- * necessary. Thus, we don't do any locking or struct
- * reinitialization, as we are going to be fully disconnected and
- * reenumerated.
- *
- * Note we need to return -ENODEV if a warm reset was requested and we
- * had to resort to a bus reset. See i2400m_op_reset(), wimax_reset()
- * and wimax_dev->op_reset.
- *
- * WARNING: no driver state saved/fixed
- */
-static
-int i2400mu_bus_reset(struct i2400m *i2400m, enum i2400m_reset_type rt)
-{
- int result;
- struct i2400mu *i2400mu =
- container_of(i2400m, struct i2400mu, i2400m);
- struct device *dev = i2400m_dev(i2400m);
- static const __le32 i2400m_WARM_BOOT_BARKER[4] = {
- cpu_to_le32(I2400M_WARM_RESET_BARKER),
- cpu_to_le32(I2400M_WARM_RESET_BARKER),
- cpu_to_le32(I2400M_WARM_RESET_BARKER),
- cpu_to_le32(I2400M_WARM_RESET_BARKER),
- };
- static const __le32 i2400m_COLD_BOOT_BARKER[4] = {
- cpu_to_le32(I2400M_COLD_RESET_BARKER),
- cpu_to_le32(I2400M_COLD_RESET_BARKER),
- cpu_to_le32(I2400M_COLD_RESET_BARKER),
- cpu_to_le32(I2400M_COLD_RESET_BARKER),
- };
-
- d_fnstart(3, dev, "(i2400m %p rt %u)\n", i2400m, rt);
- if (rt == I2400M_RT_WARM)
- result = __i2400mu_send_barker(
- i2400mu, i2400m_WARM_BOOT_BARKER,
- sizeof(i2400m_WARM_BOOT_BARKER),
- i2400mu->endpoint_cfg.bulk_out);
- else if (rt == I2400M_RT_COLD)
- result = __i2400mu_send_barker(
- i2400mu, i2400m_COLD_BOOT_BARKER,
- sizeof(i2400m_COLD_BOOT_BARKER),
- i2400mu->endpoint_cfg.reset_cold);
- else if (rt == I2400M_RT_BUS) {
- result = usb_reset_device(i2400mu->usb_dev);
- switch (result) {
- case 0:
- case -EINVAL: /* device is gone */
- case -ENODEV:
- case -ENOENT:
- case -ESHUTDOWN:
- result = 0;
- break; /* We assume the device is disconnected */
- default:
- dev_err(dev, "USB reset failed (%d), giving up!\n",
- result);
- }
- } else {
- result = -EINVAL; /* shut gcc up in certain arches */
- BUG();
- }
- if (result < 0
- && result != -EINVAL /* device is gone */
- && rt != I2400M_RT_BUS) {
- /*
- * Things failed -- resort to lower level reset, that
- * we queue in another context; the reason for this is
- * that the pre and post reset functionality requires
- * the i2400m->init_mutex; RT_WARM and RT_COLD can
- * come from areas where i2400m->init_mutex is taken.
- */
- dev_err(dev, "%s reset failed (%d); trying USB reset\n",
- rt == I2400M_RT_WARM ? "warm" : "cold", result);
- usb_queue_reset_device(i2400mu->usb_iface);
- result = -ENODEV;
- }
- d_fnend(3, dev, "(i2400m %p rt %u) = %d\n", i2400m, rt, result);
- return result;
-}
-
-static void i2400mu_get_drvinfo(struct net_device *net_dev,
- struct ethtool_drvinfo *info)
-{
- struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
- struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
- struct usb_device *udev = i2400mu->usb_dev;
-
- strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
- strlcpy(info->fw_version, i2400m->fw_name ? : "",
- sizeof(info->fw_version));
- usb_make_path(udev, info->bus_info, sizeof(info->bus_info));
-}
-
-static const struct ethtool_ops i2400mu_ethtool_ops = {
- .get_drvinfo = i2400mu_get_drvinfo,
- .get_link = ethtool_op_get_link,
-};
-
-static
-void i2400mu_netdev_setup(struct net_device *net_dev)
-{
- struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
- struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
- i2400mu_init(i2400mu);
- i2400m_netdev_setup(net_dev);
- net_dev->ethtool_ops = &i2400mu_ethtool_ops;
-}
-
-
-/*
- * Debug levels control; see debug.h
- */
-struct d_level D_LEVEL[] = {
- D_SUBMODULE_DEFINE(usb),
- D_SUBMODULE_DEFINE(fw),
- D_SUBMODULE_DEFINE(notif),
- D_SUBMODULE_DEFINE(rx),
- D_SUBMODULE_DEFINE(tx),
-};
-size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
-
-static
-void i2400mu_debugfs_add(struct i2400mu *i2400mu)
-{
- struct dentry *dentry = i2400mu->i2400m.wimax_dev.debugfs_dentry;
-
- dentry = debugfs_create_dir("i2400m-usb", dentry);
- i2400mu->debugfs_dentry = dentry;
-
- d_level_register_debugfs("dl_", usb, dentry);
- d_level_register_debugfs("dl_", fw, dentry);
- d_level_register_debugfs("dl_", notif, dentry);
- d_level_register_debugfs("dl_", rx, dentry);
- d_level_register_debugfs("dl_", tx, dentry);
-
- /* Don't touch these if you don't know what you are doing */
- debugfs_create_u8("rx_size_auto_shrink", 0600, dentry,
- &i2400mu->rx_size_auto_shrink);
-
- debugfs_create_size_t("rx_size", 0600, dentry, &i2400mu->rx_size);
-}
-
-
-static struct device_type i2400mu_type = {
- .name = "wimax",
-};
-
-/*
- * Probe a i2400m interface and register it
- *
- * @iface: USB interface to link to
- * @id: USB class/subclass/protocol id
- * @returns: 0 if ok, < 0 errno code on error.
- *
- * Alloc a net device, initialize the bus-specific details and then
- * calls the bus-generic initialization routine. That will register
- * the wimax and netdev devices, upload the firmware [using
- * _bus_bm_*()], call _bus_dev_start() to finalize the setup of the
- * communication with the device and then will start to talk to it to
- * finnish setting it up.
- */
-static
-int i2400mu_probe(struct usb_interface *iface,
- const struct usb_device_id *id)
-{
- int result;
- struct net_device *net_dev;
- struct device *dev = &iface->dev;
- struct i2400m *i2400m;
- struct i2400mu *i2400mu;
- struct usb_device *usb_dev = interface_to_usbdev(iface);
-
- if (iface->cur_altsetting->desc.bNumEndpoints < 4)
- return -ENODEV;
-
- if (usb_dev->speed != USB_SPEED_HIGH)
- dev_err(dev, "device not connected as high speed\n");
-
- /* Allocate instance [calls i2400m_netdev_setup() on it]. */
- result = -ENOMEM;
- net_dev = alloc_netdev(sizeof(*i2400mu), "wmx%d", NET_NAME_UNKNOWN,
- i2400mu_netdev_setup);
- if (net_dev == NULL) {
- dev_err(dev, "no memory for network device instance\n");
- goto error_alloc_netdev;
- }
- SET_NETDEV_DEV(net_dev, dev);
- SET_NETDEV_DEVTYPE(net_dev, &i2400mu_type);
- i2400m = net_dev_to_i2400m(net_dev);
- i2400mu = container_of(i2400m, struct i2400mu, i2400m);
- i2400m->wimax_dev.net_dev = net_dev;
- i2400mu->usb_dev = usb_get_dev(usb_dev);
- i2400mu->usb_iface = iface;
- usb_set_intfdata(iface, i2400mu);
-
- i2400m->bus_tx_block_size = I2400MU_BLK_SIZE;
- /*
- * Room required in the Tx queue for USB message to accommodate
- * a smallest payload while allocating header space is 16 bytes.
- * Adding this room for the new tx message increases the
- * possibilities of including any payload with size <= 16 bytes.
- */
- i2400m->bus_tx_room_min = I2400MU_BLK_SIZE;
- i2400m->bus_pl_size_max = I2400MU_PL_SIZE_MAX;
- i2400m->bus_setup = NULL;
- i2400m->bus_dev_start = i2400mu_bus_dev_start;
- i2400m->bus_dev_stop = i2400mu_bus_dev_stop;
- i2400m->bus_release = NULL;
- i2400m->bus_tx_kick = i2400mu_bus_tx_kick;
- i2400m->bus_reset = i2400mu_bus_reset;
- i2400m->bus_bm_retries = I2400M_USB_BOOT_RETRIES;
- i2400m->bus_bm_cmd_send = i2400mu_bus_bm_cmd_send;
- i2400m->bus_bm_wait_for_ack = i2400mu_bus_bm_wait_for_ack;
- i2400m->bus_bm_mac_addr_impaired = 0;
-
- switch (id->idProduct) {
- case USB_DEVICE_ID_I6050:
- case USB_DEVICE_ID_I6050_2:
- case USB_DEVICE_ID_I6150:
- case USB_DEVICE_ID_I6150_2:
- case USB_DEVICE_ID_I6150_3:
- case USB_DEVICE_ID_I6250:
- i2400mu->i6050 = 1;
- break;
- default:
- break;
- }
-
- if (i2400mu->i6050) {
- i2400m->bus_fw_names = i2400mu_bus_fw_names_6050;
- i2400mu->endpoint_cfg.bulk_out = 0;
- i2400mu->endpoint_cfg.notification = 3;
- i2400mu->endpoint_cfg.reset_cold = 2;
- i2400mu->endpoint_cfg.bulk_in = 1;
- } else {
- i2400m->bus_fw_names = i2400mu_bus_fw_names_5x50;
- i2400mu->endpoint_cfg.bulk_out = 0;
- i2400mu->endpoint_cfg.notification = 1;
- i2400mu->endpoint_cfg.reset_cold = 2;
- i2400mu->endpoint_cfg.bulk_in = 3;
- }
-#ifdef CONFIG_PM
- iface->needs_remote_wakeup = 1; /* autosuspend (15s delay) */
- device_init_wakeup(dev, 1);
- pm_runtime_set_autosuspend_delay(&usb_dev->dev, 15000);
- usb_enable_autosuspend(usb_dev);
-#endif
-
- result = i2400m_setup(i2400m, I2400M_BRI_MAC_REINIT);
- if (result < 0) {
- dev_err(dev, "cannot setup device: %d\n", result);
- goto error_setup;
- }
- i2400mu_debugfs_add(i2400mu);
- return 0;
-
-error_setup:
- usb_set_intfdata(iface, NULL);
- usb_put_dev(i2400mu->usb_dev);
- free_netdev(net_dev);
-error_alloc_netdev:
- return result;
-}
-
-
-/*
- * Disconnect a i2400m from the system.
- *
- * i2400m_stop() has been called before, so al the rx and tx contexts
- * have been taken down already. Make sure the queue is stopped,
- * unregister netdev and i2400m, free and kill.
- */
-static
-void i2400mu_disconnect(struct usb_interface *iface)
-{
- struct i2400mu *i2400mu = usb_get_intfdata(iface);
- struct i2400m *i2400m = &i2400mu->i2400m;
- struct net_device *net_dev = i2400m->wimax_dev.net_dev;
- struct device *dev = &iface->dev;
-
- d_fnstart(3, dev, "(iface %p i2400m %p)\n", iface, i2400m);
-
- debugfs_remove_recursive(i2400mu->debugfs_dentry);
- i2400m_release(i2400m);
- usb_set_intfdata(iface, NULL);
- usb_put_dev(i2400mu->usb_dev);
- free_netdev(net_dev);
- d_fnend(3, dev, "(iface %p i2400m %p) = void\n", iface, i2400m);
-}
-
-
-/*
- * Get the device ready for USB port or system standby and hibernation
- *
- * USB port and system standby are handled the same.
- *
- * When the system hibernates, the USB device is powered down and then
- * up, so we don't really have to do much here, as it will be seen as
- * a reconnect. Still for simplicity we consider this case the same as
- * suspend, so that the device has a chance to do notify the base
- * station (if connected).
- *
- * So at the end, the three cases require common handling.
- *
- * If at the time of this call the device's firmware is not loaded,
- * nothing has to be done. Note we can be "loose" about not reading
- * i2400m->updown under i2400m->init_mutex. If it happens to change
- * inmediately, other parts of the call flow will fail and effectively
- * catch it.
- *
- * If the firmware is loaded, we need to:
- *
- * - tell the device to go into host interface power save mode, wait
- * for it to ack
- *
- * This is quite more interesting than it is; we need to execute a
- * command, but this time, we don't want the code in usb-{tx,rx}.c
- * to call the usb_autopm_get/put_interface() barriers as it'd
- * deadlock, so we need to decrement i2400mu->do_autopm, that acts
- * as a poor man's semaphore. Ugly, but it works.
- *
- * As well, the device might refuse going to sleep for whichever
- * reason. In this case we just fail. For system suspend/hibernate,
- * we *can't* fail. We check PMSG_IS_AUTO to see if the
- * suspend call comes from the USB stack or from the system and act
- * in consequence.
- *
- * - stop the notification endpoint polling
- */
-static
-int i2400mu_suspend(struct usb_interface *iface, pm_message_t pm_msg)
-{
- int result = 0;
- struct device *dev = &iface->dev;
- struct i2400mu *i2400mu = usb_get_intfdata(iface);
- unsigned is_autosuspend = 0;
- struct i2400m *i2400m = &i2400mu->i2400m;
-
-#ifdef CONFIG_PM
- if (PMSG_IS_AUTO(pm_msg))
- is_autosuspend = 1;
-#endif
-
- d_fnstart(3, dev, "(iface %p pm_msg %u)\n", iface, pm_msg.event);
- rmb(); /* see i2400m->updown's documentation */
- if (i2400m->updown == 0)
- goto no_firmware;
- if (i2400m->state == I2400M_SS_DATA_PATH_CONNECTED && is_autosuspend) {
- /* ugh -- the device is connected and this suspend
- * request is an autosuspend one (not a system standby
- * / hibernate).
- *
- * The only way the device can go to standby is if the
- * link with the base station is in IDLE mode; that
- * were the case, we'd be in status
- * I2400M_SS_CONNECTED_IDLE. But we are not.
- *
- * If we *tell* him to go power save now, it'll reset
- * as a precautionary measure, so if this is an
- * autosuspend thing, say no and it'll come back
- * later, when the link is IDLE
- */
- result = -EBADF;
- d_printf(1, dev, "fw up, link up, not-idle, autosuspend: "
- "not entering powersave\n");
- goto error_not_now;
- }
- d_printf(1, dev, "fw up: entering powersave\n");
- atomic_dec(&i2400mu->do_autopm);
- result = i2400m_cmd_enter_powersave(i2400m);
- atomic_inc(&i2400mu->do_autopm);
- if (result < 0 && !is_autosuspend) {
- /* System suspend, can't fail */
- dev_err(dev, "failed to suspend, will reset on resume\n");
- result = 0;
- }
- if (result < 0)
- goto error_enter_powersave;
- i2400mu_notification_release(i2400mu);
- d_printf(1, dev, "powersave requested\n");
-error_enter_powersave:
-error_not_now:
-no_firmware:
- d_fnend(3, dev, "(iface %p pm_msg %u) = %d\n",
- iface, pm_msg.event, result);
- return result;
-}
-
-
-static
-int i2400mu_resume(struct usb_interface *iface)
-{
- int ret = 0;
- struct device *dev = &iface->dev;
- struct i2400mu *i2400mu = usb_get_intfdata(iface);
- struct i2400m *i2400m = &i2400mu->i2400m;
-
- d_fnstart(3, dev, "(iface %p)\n", iface);
- rmb(); /* see i2400m->updown's documentation */
- if (i2400m->updown == 0) {
- d_printf(1, dev, "fw was down, no resume needed\n");
- goto out;
- }
- d_printf(1, dev, "fw was up, resuming\n");
- i2400mu_notification_setup(i2400mu);
- /* USB has flow control, so we don't need to give it time to
- * come back; otherwise, we'd use something like a get-state
- * command... */
-out:
- d_fnend(3, dev, "(iface %p) = %d\n", iface, ret);
- return ret;
-}
-
-
-static
-int i2400mu_reset_resume(struct usb_interface *iface)
-{
- int result;
- struct device *dev = &iface->dev;
- struct i2400mu *i2400mu = usb_get_intfdata(iface);
- struct i2400m *i2400m = &i2400mu->i2400m;
-
- d_fnstart(3, dev, "(iface %p)\n", iface);
- result = i2400m_dev_reset_handle(i2400m, "device reset on resume");
- d_fnend(3, dev, "(iface %p) = %d\n", iface, result);
- return result < 0 ? result : 0;
-}
-
-
-/*
- * Another driver or user space is triggering a reset on the device
- * which contains the interface passed as an argument. Cease IO and
- * save any device state you need to restore.
- *
- * If you need to allocate memory here, use GFP_NOIO or GFP_ATOMIC, if
- * you are in atomic context.
- */
-static
-int i2400mu_pre_reset(struct usb_interface *iface)
-{
- struct i2400mu *i2400mu = usb_get_intfdata(iface);
- return i2400m_pre_reset(&i2400mu->i2400m);
-}
-
-
-/*
- * The reset has completed. Restore any saved device state and begin
- * using the device again.
- *
- * If you need to allocate memory here, use GFP_NOIO or GFP_ATOMIC, if
- * you are in atomic context.
- */
-static
-int i2400mu_post_reset(struct usb_interface *iface)
-{
- struct i2400mu *i2400mu = usb_get_intfdata(iface);
- return i2400m_post_reset(&i2400mu->i2400m);
-}
-
-
-static
-struct usb_device_id i2400mu_id_table[] = {
- { USB_DEVICE(0x8086, USB_DEVICE_ID_I6050) },
- { USB_DEVICE(0x8086, USB_DEVICE_ID_I6050_2) },
- { USB_DEVICE(0x8087, USB_DEVICE_ID_I6150) },
- { USB_DEVICE(0x8087, USB_DEVICE_ID_I6150_2) },
- { USB_DEVICE(0x8087, USB_DEVICE_ID_I6150_3) },
- { USB_DEVICE(0x8086, USB_DEVICE_ID_I6250) },
- { USB_DEVICE(0x8086, 0x0181) },
- { USB_DEVICE(0x8086, 0x1403) },
- { USB_DEVICE(0x8086, 0x1405) },
- { USB_DEVICE(0x8086, 0x0180) },
- { USB_DEVICE(0x8086, 0x0182) },
- { USB_DEVICE(0x8086, 0x1406) },
- { USB_DEVICE(0x8086, 0x1403) },
- { },
-};
-MODULE_DEVICE_TABLE(usb, i2400mu_id_table);
-
-
-static
-struct usb_driver i2400mu_driver = {
- .name = KBUILD_MODNAME,
- .suspend = i2400mu_suspend,
- .resume = i2400mu_resume,
- .reset_resume = i2400mu_reset_resume,
- .probe = i2400mu_probe,
- .disconnect = i2400mu_disconnect,
- .pre_reset = i2400mu_pre_reset,
- .post_reset = i2400mu_post_reset,
- .id_table = i2400mu_id_table,
- .supports_autosuspend = 1,
-};
-
-static
-int __init i2400mu_driver_init(void)
-{
- d_parse_params(D_LEVEL, D_LEVEL_SIZE, i2400mu_debug_params,
- "i2400m_usb.debug");
- return usb_register(&i2400mu_driver);
-}
-module_init(i2400mu_driver_init);
-
-
-static
-void __exit i2400mu_driver_exit(void)
-{
- usb_deregister(&i2400mu_driver);
-}
-module_exit(i2400mu_driver_exit);
-
-MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
-MODULE_DESCRIPTION("Driver for USB based Intel Wireless WiMAX Connection 2400M "
- "(5x50 & 6050)");
-MODULE_LICENSE("GPL");
-MODULE_FIRMWARE(I2400MU_FW_FILE_NAME_v1_5);
-MODULE_FIRMWARE(I6050U_FW_FILE_NAME_v1_5);
.ndo_open = wg_open,
.ndo_stop = wg_stop,
.ndo_start_xmit = wg_xmit,
- .ndo_get_stats64 = ip_tunnel_get_stats64
+ .ndo_get_stats64 = dev_get_tstats64
};
static void wg_destruct(struct net_device *dev)
if WLAN
-config WIRELESS_WDS
- bool "mac80211-based legacy WDS support" if EXPERT
- help
- This option enables the deprecated WDS support, the newer
- mac80211-based 4-addr AP/client support supersedes it with
- a much better feature set (HT, VHT, ...)
-
- We plan to remove this option and code, so if you find
- that you have to enable it, please let us know on the
- linux-wireless@vger.kernel.org mailing list, so we can
- help you migrate to 4-addr AP/client (or, if it's really
- necessary, give up on our plan of removing it).
-
source "drivers/net/wireless/admtek/Kconfig"
source "drivers/net/wireless/ath/Kconfig"
source "drivers/net/wireless/atmel/Kconfig"
int naps; /* number of AP vifs */
int nmeshes; /* number of mesh vifs */
int nstations; /* number of station vifs */
- int nwds; /* number of WDS vifs */
int nadhocs; /* number of adhoc vifs */
int nocbs; /* number of OCB vifs */
int nbcnvifs; /* number of beaconing vifs */
ath9k_calculate_iter_data(sc, ctx, &iter_data);
seq_printf(file,
- "VIFS: CTX %i(%i) AP: %i STA: %i MESH: %i WDS: %i",
+ "VIFS: CTX %i(%i) AP: %i STA: %i MESH: %i",
i++, (int)(ctx->assigned), iter_data.naps,
iter_data.nstations,
- iter_data.nmeshes, iter_data.nwds);
+ iter_data.nmeshes);
seq_printf(file, " ADHOC: %i OCB: %i TOTAL: %hi BEACON-VIF: %hi\n",
iter_data.nadhocs, iter_data.nocbs, sc->cur_chan->nvifs,
sc->nbcnvifs);
BIT(NL80211_IFTYPE_P2P_GO) },
};
-#ifdef CONFIG_WIRELESS_WDS
-static const struct ieee80211_iface_limit wds_limits[] = {
- { .max = 2048, .types = BIT(NL80211_IFTYPE_WDS) },
-};
-#endif
-
#ifdef CONFIG_ATH9K_CHANNEL_CONTEXT
static const struct ieee80211_iface_limit if_limits_multi[] = {
BIT(NL80211_CHAN_WIDTH_40),
#endif
},
-#ifdef CONFIG_WIRELESS_WDS
- {
- .limits = wds_limits,
- .n_limits = ARRAY_SIZE(wds_limits),
- .max_interfaces = 2048,
- .num_different_channels = 1,
- .beacon_int_infra_match = true,
- },
-#endif
};
#ifdef CONFIG_ATH9K_CHANNEL_CONTEXT
ieee80211_hw_set(hw, QUEUE_CONTROL);
hw->queues = ATH9K_NUM_TX_QUEUES;
hw->offchannel_tx_hw_queue = hw->queues - 1;
- hw->wiphy->interface_modes &= ~ BIT(NL80211_IFTYPE_WDS);
hw->wiphy->iface_combinations = if_comb_multi;
hw->wiphy->n_iface_combinations = ARRAY_SIZE(if_comb_multi);
hw->wiphy->max_scan_ssids = 255;
BIT(NL80211_IFTYPE_STATION) |
BIT(NL80211_IFTYPE_ADHOC) |
BIT(NL80211_IFTYPE_MESH_POINT) |
-#ifdef CONFIG_WIRELESS_WDS
- BIT(NL80211_IFTYPE_WDS) |
-#endif
BIT(NL80211_IFTYPE_OCB);
if (ath9k_is_chanctx_enabled())
if (vif->bss_conf.enable_beacon)
ath9k_vif_iter_set_beacon(iter_data, vif);
break;
- case NL80211_IFTYPE_WDS:
- iter_data->nwds++;
- break;
default:
break;
}
ah->opmode = NL80211_IFTYPE_MESH_POINT;
else if (iter_data.nocbs)
ah->opmode = NL80211_IFTYPE_OCB;
- else if (iter_data.nwds)
- ah->opmode = NL80211_IFTYPE_AP;
else if (iter_data.nadhocs)
ah->opmode = NL80211_IFTYPE_ADHOC;
else
/* iwlagn 802.11n STA Workaround */
rx_ctrl |= AR9170_MAC_RX_CTRL_PASS_TO_HOST;
break;
- case NL80211_IFTYPE_WDS:
- cam_mode |= AR9170_MAC_CAM_AP_WDS;
- rx_ctrl |= AR9170_MAC_RX_CTRL_PASS_TO_HOST;
- break;
case NL80211_IFTYPE_STATION:
cam_mode |= AR9170_MAC_CAM_STA;
rx_ctrl |= AR9170_MAC_RX_CTRL_PASS_TO_HOST;
case NL80211_IFTYPE_MESH_POINT:
case NL80211_IFTYPE_AP:
if ((vif->type == NL80211_IFTYPE_STATION) ||
- (vif->type == NL80211_IFTYPE_WDS) ||
(vif->type == NL80211_IFTYPE_AP) ||
(vif->type == NL80211_IFTYPE_MESH_POINT))
break;
struct b43_wldev *dev;
int err = -EOPNOTSUPP;
- /* TODO: allow WDS/AP devices to coexist */
+ /* TODO: allow AP devices to coexist */
if (vif->type != NL80211_IFTYPE_AP &&
vif->type != NL80211_IFTYPE_MESH_POINT &&
vif->type != NL80211_IFTYPE_STATION &&
- vif->type != NL80211_IFTYPE_WDS &&
vif->type != NL80211_IFTYPE_ADHOC)
return -EOPNOTSUPP;
BIT(NL80211_IFTYPE_AP) |
BIT(NL80211_IFTYPE_MESH_POINT) |
BIT(NL80211_IFTYPE_STATION) |
-#ifdef CONFIG_WIRELESS_WDS
- BIT(NL80211_IFTYPE_WDS) |
-#endif
BIT(NL80211_IFTYPE_ADHOC);
hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
unsigned long flags;
int err = -EOPNOTSUPP;
- /* TODO: allow WDS/AP devices to coexist */
+ /* TODO: allow AP devices to coexist */
if (vif->type != NL80211_IFTYPE_AP &&
vif->type != NL80211_IFTYPE_STATION &&
- vif->type != NL80211_IFTYPE_WDS &&
vif->type != NL80211_IFTYPE_ADHOC)
return -EOPNOTSUPP;
hw->wiphy->interface_modes =
BIT(NL80211_IFTYPE_AP) |
BIT(NL80211_IFTYPE_STATION) |
-#ifdef CONFIG_WIRELESS_WDS
- BIT(NL80211_IFTYPE_WDS) |
-#endif
BIT(NL80211_IFTYPE_ADHOC);
hw->queues = 1; /* FIXME: hardware has more queues */
hw->max_rates = 2;
if (unlikely(skb->protocol == htons(ETH_P_PAE))) {
qtnf_packet_send_hi_pri(skb);
- qtnf_update_tx_stats(ndev, skb);
+ dev_sw_netstats_tx_add(ndev, 1, skb->len);
return NETDEV_TX_OK;
}
return qtnf_bus_data_tx(mac->bus, skb, mac->macid, vif->vifid);
}
-/* Netdev handler for getting stats.
- */
-static void qtnf_netdev_get_stats64(struct net_device *ndev,
- struct rtnl_link_stats64 *stats)
-{
- struct qtnf_vif *vif = qtnf_netdev_get_priv(ndev);
-
- netdev_stats_to_stats64(stats, &ndev->stats);
-
- if (!vif->stats64)
- return;
-
- dev_fetch_sw_netstats(stats, vif->stats64);
-}
-
/* Netdev handler for transmission timeout.
*/
static void qtnf_netdev_tx_timeout(struct net_device *ndev, unsigned int txqueue)
return 0;
}
+static int qtnf_netdev_alloc_pcpu_stats(struct net_device *dev)
+{
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+
+ return dev->tstats ? 0 : -ENOMEM;
+}
+
+static void qtnf_netdev_free_pcpu_stats(struct net_device *dev)
+{
+ free_percpu(dev->tstats);
+}
+
/* Network device ops handlers */
const struct net_device_ops qtnf_netdev_ops = {
+ .ndo_init = qtnf_netdev_alloc_pcpu_stats,
+ .ndo_uninit = qtnf_netdev_free_pcpu_stats,
.ndo_open = qtnf_netdev_open,
.ndo_stop = qtnf_netdev_close,
.ndo_start_xmit = qtnf_netdev_hard_start_xmit,
.ndo_tx_timeout = qtnf_netdev_tx_timeout,
- .ndo_get_stats64 = qtnf_netdev_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = qtnf_netdev_set_mac_address,
.ndo_get_port_parent_id = qtnf_netdev_port_parent_id,
};
qtnf_sta_list_init(&vif->sta_list);
INIT_WORK(&vif->high_pri_tx_work, qtnf_vif_send_data_high_pri);
skb_queue_head_init(&vif->high_pri_tx_queue);
- vif->stats64 = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
- if (!vif->stats64)
- pr_warn("VIF%u.%u: per cpu stats allocation failed\n",
- macid, i);
}
qtnf_mac_init_primary_intf(mac);
}
rtnl_unlock();
qtnf_sta_list_free(&vif->sta_list);
- free_percpu(vif->stats64);
}
if (mac->wiphy_registered)
}
EXPORT_SYMBOL_GPL(qtnf_wake_all_queues);
-void qtnf_update_rx_stats(struct net_device *ndev, const struct sk_buff *skb)
-{
- struct qtnf_vif *vif = qtnf_netdev_get_priv(ndev);
- struct pcpu_sw_netstats *stats64;
-
- if (unlikely(!vif || !vif->stats64)) {
- ndev->stats.rx_packets++;
- ndev->stats.rx_bytes += skb->len;
- return;
- }
-
- stats64 = this_cpu_ptr(vif->stats64);
-
- u64_stats_update_begin(&stats64->syncp);
- stats64->rx_packets++;
- stats64->rx_bytes += skb->len;
- u64_stats_update_end(&stats64->syncp);
-}
-EXPORT_SYMBOL_GPL(qtnf_update_rx_stats);
-
-void qtnf_update_tx_stats(struct net_device *ndev, const struct sk_buff *skb)
-{
- struct qtnf_vif *vif = qtnf_netdev_get_priv(ndev);
- struct pcpu_sw_netstats *stats64;
-
- if (unlikely(!vif || !vif->stats64)) {
- ndev->stats.tx_packets++;
- ndev->stats.tx_bytes += skb->len;
- return;
- }
-
- stats64 = this_cpu_ptr(vif->stats64);
-
- u64_stats_update_begin(&stats64->syncp);
- stats64->tx_packets++;
- stats64->tx_bytes += skb->len;
- u64_stats_update_end(&stats64->syncp);
-}
-EXPORT_SYMBOL_GPL(qtnf_update_tx_stats);
-
struct dentry *qtnf_get_debugfs_dir(void)
{
return qtnf_debugfs_dir;
struct qtnf_sta_list sta_list;
unsigned long cons_tx_timeout_cnt;
int generation;
-
- struct pcpu_sw_netstats __percpu *stats64;
};
struct qtnf_mac_info {
struct qtnf_wmac *qtnf_core_get_mac(const struct qtnf_bus *bus, u8 macid);
struct net_device *qtnf_classify_skb(struct qtnf_bus *bus, struct sk_buff *skb);
void qtnf_wake_all_queues(struct net_device *ndev);
-void qtnf_update_rx_stats(struct net_device *ndev, const struct sk_buff *skb);
-void qtnf_update_tx_stats(struct net_device *ndev, const struct sk_buff *skb);
void qtnf_virtual_intf_cleanup(struct net_device *ndev);
PCI_DMA_TODEVICE);
if (skb->dev) {
- qtnf_update_tx_stats(skb->dev, skb);
+ dev_sw_netstats_tx_add(skb->dev, 1, skb->len);
if (unlikely(priv->tx_stopped)) {
qtnf_wake_all_queues(skb->dev);
priv->tx_stopped = 0;
skb_put(skb, psize);
ndev = qtnf_classify_skb(bus, skb);
if (likely(ndev)) {
- qtnf_update_rx_stats(ndev, skb);
+ dev_sw_netstats_rx_add(ndev, skb->len);
skb->protocol = eth_type_trans(skb, ndev);
napi_gro_receive(napi, skb);
} else {
PCI_DMA_TODEVICE);
if (skb->dev) {
- qtnf_update_tx_stats(skb->dev, skb);
+ dev_sw_netstats_tx_add(skb->dev, 1, skb->len);
if (unlikely(priv->tx_stopped)) {
qtnf_wake_all_queues(skb->dev);
priv->tx_stopped = 0;
skb_put(skb, psize);
ndev = qtnf_classify_skb(bus, skb);
if (likely(ndev)) {
- qtnf_update_rx_stats(ndev, skb);
+ dev_sw_netstats_rx_add(ndev, skb->len);
skb->protocol = eth_type_trans(skb, ndev);
netif_receive_skb(skb);
} else {
break;
case NL80211_IFTYPE_AP:
case NL80211_IFTYPE_MESH_POINT:
- case NL80211_IFTYPE_WDS:
conf.sync = TSF_SYNC_AP_NONE;
break;
case NL80211_IFTYPE_STATION:
if (vif->type != NL80211_IFTYPE_AP &&
vif->type != NL80211_IFTYPE_ADHOC &&
- vif->type != NL80211_IFTYPE_MESH_POINT &&
- vif->type != NL80211_IFTYPE_WDS)
+ vif->type != NL80211_IFTYPE_MESH_POINT)
return;
/*
BIT(NL80211_IFTYPE_ADHOC) |
#ifdef CONFIG_MAC80211_MESH
BIT(NL80211_IFTYPE_MESH_POINT) |
-#endif
-#ifdef CONFIG_WIRELESS_WDS
- BIT(NL80211_IFTYPE_WDS) |
#endif
BIT(NL80211_IFTYPE_AP);
if (vif->type != NL80211_IFTYPE_AP &&
vif->type != NL80211_IFTYPE_ADHOC &&
- vif->type != NL80211_IFTYPE_MESH_POINT &&
- vif->type != NL80211_IFTYPE_WDS)
+ vif->type != NL80211_IFTYPE_MESH_POINT)
return;
set_bit(DELAYED_UPDATE_BEACON, &intf->delayed_flags);
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
- .ndo_get_stats64 = usbnet_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_rx_mode = rndis_wlan_set_multicast_list,
const char *buf, size_t len)
{
char *endp;
- unsigned long target;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
- target = simple_strtoul(buf, &endp, 0);
+ simple_strtoul(buf, &endp, 0);
if (endp == buf)
return -EBADMSG;
return PTR_ERR(phy->gpiod_en);
}
- phy->gpiod_fw = devm_gpiod_get(dev, "firmware", GPIOD_OUT_LOW);
+ phy->gpiod_fw = devm_gpiod_get_optional(dev, "firmware", GPIOD_OUT_LOW);
if (IS_ERR(phy->gpiod_fw)) {
nfc_err(dev, "Failed to get FW gpio\n");
return PTR_ERR(phy->gpiod_fw);
To compile this driver as a module, choose m here. The module will
be called s3fwrn5_i2c.ko.
Say N if unsure.
+
+config NFC_S3FWRN82_UART
+ tristate "Samsung S3FWRN82 UART support"
+ depends on NFC_NCI && SERIAL_DEV_BUS
+ select NFC_S3FWRN5
+ help
+ This module adds support for a UART interface to the S3FWRN82 chip.
+ Select this if your platform is using the UART bus.
+
+ To compile this driver as a module, choose m here. The module will
+ be called s3fwrn82_uart.ko.
+ Say N if unsure.
# Makefile for Samsung S3FWRN5 NFC driver
#
-s3fwrn5-objs = core.o firmware.o nci.o
+s3fwrn5-objs = core.o firmware.o nci.o phy_common.o
s3fwrn5_i2c-objs = i2c.o
+s3fwrn82_uart-objs = uart.o
obj-$(CONFIG_NFC_S3FWRN5) += s3fwrn5.o
obj-$(CONFIG_NFC_S3FWRN5_I2C) += s3fwrn5_i2c.o
+obj-$(CONFIG_NFC_S3FWRN82_UART) += s3fwrn82_uart.o
};
int s3fwrn5_probe(struct nci_dev **ndev, void *phy_id, struct device *pdev,
- const struct s3fwrn5_phy_ops *phy_ops, unsigned int max_payload)
+ const struct s3fwrn5_phy_ops *phy_ops)
{
struct s3fwrn5_info *info;
int ret;
info->phy_id = phy_id;
info->pdev = pdev;
info->phy_ops = phy_ops;
- info->max_payload = max_payload;
mutex_init(&info->mutex);
s3fwrn5_set_mode(info, S3FWRN5_MODE_COLD);
}
/*
- * Firmware header stucture:
+ * Firmware header structure:
*
* 0x00 - 0x0B : Date and time string (w/o NUL termination)
* 0x10 - 0x13 : Firmware version
#include <net/nfc/nfc.h>
-#include "s3fwrn5.h"
+#include "phy_common.h"
#define S3FWRN5_I2C_DRIVER_NAME "s3fwrn5_i2c"
-#define S3FWRN5_I2C_MAX_PAYLOAD 32
-#define S3FWRN5_EN_WAIT_TIME 150
-
struct s3fwrn5_i2c_phy {
+ struct phy_common common;
struct i2c_client *i2c_dev;
- struct nci_dev *ndev;
-
- int gpio_en;
- int gpio_fw_wake;
-
- struct mutex mutex;
- enum s3fwrn5_mode mode;
unsigned int irq_skip:1;
};
-static void s3fwrn5_i2c_set_wake(void *phy_id, bool wake)
-{
- struct s3fwrn5_i2c_phy *phy = phy_id;
-
- mutex_lock(&phy->mutex);
- gpio_set_value(phy->gpio_fw_wake, wake);
- msleep(S3FWRN5_EN_WAIT_TIME/2);
- mutex_unlock(&phy->mutex);
-}
-
static void s3fwrn5_i2c_set_mode(void *phy_id, enum s3fwrn5_mode mode)
{
struct s3fwrn5_i2c_phy *phy = phy_id;
- mutex_lock(&phy->mutex);
+ mutex_lock(&phy->common.mutex);
- if (phy->mode == mode)
+ if (s3fwrn5_phy_power_ctrl(&phy->common, mode) == false)
goto out;
- phy->mode = mode;
-
- gpio_set_value(phy->gpio_en, 1);
- gpio_set_value(phy->gpio_fw_wake, 0);
- if (mode == S3FWRN5_MODE_FW)
- gpio_set_value(phy->gpio_fw_wake, 1);
-
- if (mode != S3FWRN5_MODE_COLD) {
- msleep(S3FWRN5_EN_WAIT_TIME);
- gpio_set_value(phy->gpio_en, 0);
- msleep(S3FWRN5_EN_WAIT_TIME/2);
- }
-
phy->irq_skip = true;
out:
- mutex_unlock(&phy->mutex);
-}
-
-static enum s3fwrn5_mode s3fwrn5_i2c_get_mode(void *phy_id)
-{
- struct s3fwrn5_i2c_phy *phy = phy_id;
- enum s3fwrn5_mode mode;
-
- mutex_lock(&phy->mutex);
-
- mode = phy->mode;
-
- mutex_unlock(&phy->mutex);
-
- return mode;
+ mutex_unlock(&phy->common.mutex);
}
static int s3fwrn5_i2c_write(void *phy_id, struct sk_buff *skb)
struct s3fwrn5_i2c_phy *phy = phy_id;
int ret;
- mutex_lock(&phy->mutex);
+ mutex_lock(&phy->common.mutex);
phy->irq_skip = false;
ret = i2c_master_send(phy->i2c_dev, skb->data, skb->len);
}
- mutex_unlock(&phy->mutex);
+ mutex_unlock(&phy->common.mutex);
if (ret < 0)
return ret;
}
static const struct s3fwrn5_phy_ops i2c_phy_ops = {
- .set_wake = s3fwrn5_i2c_set_wake,
+ .set_wake = s3fwrn5_phy_set_wake,
.set_mode = s3fwrn5_i2c_set_mode,
- .get_mode = s3fwrn5_i2c_get_mode,
+ .get_mode = s3fwrn5_phy_get_mode,
.write = s3fwrn5_i2c_write,
};
char hdr[4];
int ret;
- hdr_size = (phy->mode == S3FWRN5_MODE_NCI) ?
+ hdr_size = (phy->common.mode == S3FWRN5_MODE_NCI) ?
NCI_CTRL_HDR_SIZE : S3FWRN5_FW_HDR_SIZE;
ret = i2c_master_recv(phy->i2c_dev, hdr, hdr_size);
if (ret < 0)
if (ret < hdr_size)
return -EBADMSG;
- data_len = (phy->mode == S3FWRN5_MODE_NCI) ?
+ data_len = (phy->common.mode == S3FWRN5_MODE_NCI) ?
((struct nci_ctrl_hdr *)hdr)->plen :
((struct s3fwrn5_fw_header *)hdr)->len;
}
out:
- return s3fwrn5_recv_frame(phy->ndev, skb, phy->mode);
+ return s3fwrn5_recv_frame(phy->common.ndev, skb, phy->common.mode);
}
static irqreturn_t s3fwrn5_i2c_irq_thread_fn(int irq, void *phy_id)
{
struct s3fwrn5_i2c_phy *phy = phy_id;
- if (!phy || !phy->ndev) {
+ if (!phy || !phy->common.ndev) {
WARN_ON_ONCE(1);
return IRQ_NONE;
}
- mutex_lock(&phy->mutex);
+ mutex_lock(&phy->common.mutex);
if (phy->irq_skip)
goto out;
- switch (phy->mode) {
+ switch (phy->common.mode) {
case S3FWRN5_MODE_NCI:
case S3FWRN5_MODE_FW:
s3fwrn5_i2c_read(phy);
}
out:
- mutex_unlock(&phy->mutex);
+ mutex_unlock(&phy->common.mutex);
return IRQ_HANDLED;
}
if (!np)
return -ENODEV;
- phy->gpio_en = of_get_named_gpio(np, "en-gpios", 0);
- if (!gpio_is_valid(phy->gpio_en)) {
+ phy->common.gpio_en = of_get_named_gpio(np, "en-gpios", 0);
+ if (!gpio_is_valid(phy->common.gpio_en)) {
/* Support also deprecated property */
- phy->gpio_en = of_get_named_gpio(np, "s3fwrn5,en-gpios", 0);
- if (!gpio_is_valid(phy->gpio_en))
+ phy->common.gpio_en = of_get_named_gpio(np,
+ "s3fwrn5,en-gpios",
+ 0);
+ if (!gpio_is_valid(phy->common.gpio_en))
return -ENODEV;
}
- phy->gpio_fw_wake = of_get_named_gpio(np, "wake-gpios", 0);
- if (!gpio_is_valid(phy->gpio_fw_wake)) {
+ phy->common.gpio_fw_wake = of_get_named_gpio(np, "wake-gpios", 0);
+ if (!gpio_is_valid(phy->common.gpio_fw_wake)) {
/* Support also deprecated property */
- phy->gpio_fw_wake = of_get_named_gpio(np, "s3fwrn5,fw-gpios", 0);
- if (!gpio_is_valid(phy->gpio_fw_wake))
+ phy->common.gpio_fw_wake = of_get_named_gpio(np,
+ "s3fwrn5,fw-gpios",
+ 0);
+ if (!gpio_is_valid(phy->common.gpio_fw_wake))
return -ENODEV;
}
if (!phy)
return -ENOMEM;
- mutex_init(&phy->mutex);
- phy->mode = S3FWRN5_MODE_COLD;
+ mutex_init(&phy->common.mutex);
+ phy->common.mode = S3FWRN5_MODE_COLD;
phy->irq_skip = true;
phy->i2c_dev = client;
if (ret < 0)
return ret;
- ret = devm_gpio_request_one(&phy->i2c_dev->dev, phy->gpio_en,
- GPIOF_OUT_INIT_HIGH, "s3fwrn5_en");
+ ret = devm_gpio_request_one(&phy->i2c_dev->dev, phy->common.gpio_en,
+ GPIOF_OUT_INIT_HIGH, "s3fwrn5_en");
if (ret < 0)
return ret;
- ret = devm_gpio_request_one(&phy->i2c_dev->dev, phy->gpio_fw_wake,
- GPIOF_OUT_INIT_LOW, "s3fwrn5_fw_wake");
+ ret = devm_gpio_request_one(&phy->i2c_dev->dev,
+ phy->common.gpio_fw_wake,
+ GPIOF_OUT_INIT_LOW, "s3fwrn5_fw_wake");
if (ret < 0)
return ret;
- ret = s3fwrn5_probe(&phy->ndev, phy, &phy->i2c_dev->dev, &i2c_phy_ops,
- S3FWRN5_I2C_MAX_PAYLOAD);
+ ret = s3fwrn5_probe(&phy->common.ndev, phy, &phy->i2c_dev->dev,
+ &i2c_phy_ops);
if (ret < 0)
return ret;
s3fwrn5_i2c_irq_thread_fn, IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
S3FWRN5_I2C_DRIVER_NAME, phy);
if (ret)
- s3fwrn5_remove(phy->ndev);
+ s3fwrn5_remove(phy->common.ndev);
return ret;
}
{
struct s3fwrn5_i2c_phy *phy = i2c_get_clientdata(client);
- s3fwrn5_remove(phy->ndev);
+ s3fwrn5_remove(phy->common.ndev);
return 0;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Link Layer for Samsung S3FWRN5 NCI based Driver
+ *
+ * Copyright (C) 2015 Samsung Electrnoics
+ * Robert Baldyga <r.baldyga@samsung.com>
+ * Copyright (C) 2020 Samsung Electrnoics
+ * Bongsu Jeon <bongsu.jeon@samsung.com>
+ */
+
+#include <linux/gpio.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+
+#include "phy_common.h"
+
+void s3fwrn5_phy_set_wake(void *phy_id, bool wake)
+{
+ struct phy_common *phy = phy_id;
+
+ mutex_lock(&phy->mutex);
+ gpio_set_value(phy->gpio_fw_wake, wake);
+ msleep(S3FWRN5_EN_WAIT_TIME);
+ mutex_unlock(&phy->mutex);
+}
+EXPORT_SYMBOL(s3fwrn5_phy_set_wake);
+
+bool s3fwrn5_phy_power_ctrl(struct phy_common *phy, enum s3fwrn5_mode mode)
+{
+ if (phy->mode == mode)
+ return false;
+
+ phy->mode = mode;
+
+ gpio_set_value(phy->gpio_en, 1);
+ gpio_set_value(phy->gpio_fw_wake, 0);
+ if (mode == S3FWRN5_MODE_FW)
+ gpio_set_value(phy->gpio_fw_wake, 1);
+
+ if (mode != S3FWRN5_MODE_COLD) {
+ msleep(S3FWRN5_EN_WAIT_TIME);
+ gpio_set_value(phy->gpio_en, 0);
+ msleep(S3FWRN5_EN_WAIT_TIME);
+ }
+
+ return true;
+}
+EXPORT_SYMBOL(s3fwrn5_phy_power_ctrl);
+
+void s3fwrn5_phy_set_mode(void *phy_id, enum s3fwrn5_mode mode)
+{
+ struct phy_common *phy = phy_id;
+
+ mutex_lock(&phy->mutex);
+
+ s3fwrn5_phy_power_ctrl(phy, mode);
+
+ mutex_unlock(&phy->mutex);
+}
+EXPORT_SYMBOL(s3fwrn5_phy_set_mode);
+
+enum s3fwrn5_mode s3fwrn5_phy_get_mode(void *phy_id)
+{
+ struct phy_common *phy = phy_id;
+ enum s3fwrn5_mode mode;
+
+ mutex_lock(&phy->mutex);
+
+ mode = phy->mode;
+
+ mutex_unlock(&phy->mutex);
+
+ return mode;
+}
+EXPORT_SYMBOL(s3fwrn5_phy_get_mode);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * Link Layer for Samsung S3FWRN5 NCI based Driver
+ *
+ * Copyright (C) 2015 Samsung Electrnoics
+ * Robert Baldyga <r.baldyga@samsung.com>
+ * Copyright (C) 2020 Samsung Electrnoics
+ * Bongsu Jeon <bongsu.jeon@samsung.com>
+ */
+
+#ifndef __NFC_S3FWRN5_PHY_COMMON_H
+#define __NFC_S3FWRN5_PHY_COMMON_H
+
+#include <linux/mutex.h>
+#include <net/nfc/nci_core.h>
+
+#include "s3fwrn5.h"
+
+#define S3FWRN5_EN_WAIT_TIME 20
+
+struct phy_common {
+ struct nci_dev *ndev;
+
+ int gpio_en;
+ int gpio_fw_wake;
+
+ struct mutex mutex;
+
+ enum s3fwrn5_mode mode;
+};
+
+void s3fwrn5_phy_set_wake(void *phy_id, bool wake);
+bool s3fwrn5_phy_power_ctrl(struct phy_common *phy, enum s3fwrn5_mode mode);
+void s3fwrn5_phy_set_mode(void *phy_id, enum s3fwrn5_mode mode);
+enum s3fwrn5_mode s3fwrn5_phy_get_mode(void *phy_id);
+
+#endif /* __NFC_S3FWRN5_PHY_COMMON_H */
struct device *pdev;
const struct s3fwrn5_phy_ops *phy_ops;
- unsigned int max_payload;
struct s3fwrn5_fw_info fw_info;
enum s3fwrn5_mode mode)
{
if (!info->phy_ops->set_mode)
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
info->phy_ops->set_mode(info->phy_id, mode);
static inline enum s3fwrn5_mode s3fwrn5_get_mode(struct s3fwrn5_info *info)
{
if (!info->phy_ops->get_mode)
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
return info->phy_ops->get_mode(info->phy_id);
}
static inline int s3fwrn5_set_wake(struct s3fwrn5_info *info, bool wake)
{
if (!info->phy_ops->set_wake)
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
info->phy_ops->set_wake(info->phy_id, wake);
static inline int s3fwrn5_write(struct s3fwrn5_info *info, struct sk_buff *skb)
{
if (!info->phy_ops->write)
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
return info->phy_ops->write(info->phy_id, skb);
}
int s3fwrn5_probe(struct nci_dev **ndev, void *phy_id, struct device *pdev,
- const struct s3fwrn5_phy_ops *phy_ops, unsigned int max_payload);
+ const struct s3fwrn5_phy_ops *phy_ops);
void s3fwrn5_remove(struct nci_dev *ndev);
int s3fwrn5_recv_frame(struct nci_dev *ndev, struct sk_buff *skb,
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * UART Link Layer for S3FWRN82 NCI based Driver
+ *
+ * Copyright (C) 2015 Samsung Electronics
+ * Robert Baldyga <r.baldyga@samsung.com>
+ * Copyright (C) 2020 Samsung Electronics
+ * Bongsu Jeon <bongsu.jeon@samsung.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/nfc.h>
+#include <linux/netdevice.h>
+#include <linux/of.h>
+#include <linux/serdev.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+
+#include "phy_common.h"
+
+#define S3FWRN82_NCI_HEADER 3
+#define S3FWRN82_NCI_IDX 2
+#define NCI_SKB_BUFF_LEN 258
+
+struct s3fwrn82_uart_phy {
+ struct phy_common common;
+ struct serdev_device *ser_dev;
+ struct sk_buff *recv_skb;
+};
+
+static int s3fwrn82_uart_write(void *phy_id, struct sk_buff *out)
+{
+ struct s3fwrn82_uart_phy *phy = phy_id;
+ int err;
+
+ err = serdev_device_write(phy->ser_dev,
+ out->data, out->len,
+ MAX_SCHEDULE_TIMEOUT);
+ if (err < 0)
+ return err;
+
+ return 0;
+}
+
+static const struct s3fwrn5_phy_ops uart_phy_ops = {
+ .set_wake = s3fwrn5_phy_set_wake,
+ .set_mode = s3fwrn5_phy_set_mode,
+ .get_mode = s3fwrn5_phy_get_mode,
+ .write = s3fwrn82_uart_write,
+};
+
+static int s3fwrn82_uart_read(struct serdev_device *serdev,
+ const unsigned char *data,
+ size_t count)
+{
+ struct s3fwrn82_uart_phy *phy = serdev_device_get_drvdata(serdev);
+ size_t i;
+
+ for (i = 0; i < count; i++) {
+ skb_put_u8(phy->recv_skb, *data++);
+
+ if (phy->recv_skb->len < S3FWRN82_NCI_HEADER)
+ continue;
+
+ if ((phy->recv_skb->len - S3FWRN82_NCI_HEADER)
+ < phy->recv_skb->data[S3FWRN82_NCI_IDX])
+ continue;
+
+ s3fwrn5_recv_frame(phy->common.ndev, phy->recv_skb,
+ phy->common.mode);
+ phy->recv_skb = alloc_skb(NCI_SKB_BUFF_LEN, GFP_KERNEL);
+ if (!phy->recv_skb)
+ return 0;
+ }
+
+ return i;
+}
+
+static const struct serdev_device_ops s3fwrn82_serdev_ops = {
+ .receive_buf = s3fwrn82_uart_read,
+ .write_wakeup = serdev_device_write_wakeup,
+};
+
+static const struct of_device_id s3fwrn82_uart_of_match[] = {
+ { .compatible = "samsung,s3fwrn82", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, s3fwrn82_uart_of_match);
+
+static int s3fwrn82_uart_parse_dt(struct serdev_device *serdev)
+{
+ struct s3fwrn82_uart_phy *phy = serdev_device_get_drvdata(serdev);
+ struct device_node *np = serdev->dev.of_node;
+
+ if (!np)
+ return -ENODEV;
+
+ phy->common.gpio_en = of_get_named_gpio(np, "en-gpios", 0);
+ if (!gpio_is_valid(phy->common.gpio_en))
+ return -ENODEV;
+
+ phy->common.gpio_fw_wake = of_get_named_gpio(np, "wake-gpios", 0);
+ if (!gpio_is_valid(phy->common.gpio_fw_wake))
+ return -ENODEV;
+
+ return 0;
+}
+
+static int s3fwrn82_uart_probe(struct serdev_device *serdev)
+{
+ struct s3fwrn82_uart_phy *phy;
+ int ret = -ENOMEM;
+
+ phy = devm_kzalloc(&serdev->dev, sizeof(*phy), GFP_KERNEL);
+ if (!phy)
+ goto err_exit;
+
+ phy->recv_skb = alloc_skb(NCI_SKB_BUFF_LEN, GFP_KERNEL);
+ if (!phy->recv_skb)
+ goto err_exit;
+
+ mutex_init(&phy->common.mutex);
+ phy->common.mode = S3FWRN5_MODE_COLD;
+
+ phy->ser_dev = serdev;
+ serdev_device_set_drvdata(serdev, phy);
+ serdev_device_set_client_ops(serdev, &s3fwrn82_serdev_ops);
+ ret = serdev_device_open(serdev);
+ if (ret) {
+ dev_err(&serdev->dev, "Unable to open device\n");
+ goto err_skb;
+ }
+
+ ret = serdev_device_set_baudrate(serdev, 115200);
+ if (ret != 115200) {
+ ret = -EINVAL;
+ goto err_serdev;
+ }
+
+ serdev_device_set_flow_control(serdev, false);
+
+ ret = s3fwrn82_uart_parse_dt(serdev);
+ if (ret < 0)
+ goto err_serdev;
+
+ ret = devm_gpio_request_one(&phy->ser_dev->dev, phy->common.gpio_en,
+ GPIOF_OUT_INIT_HIGH, "s3fwrn82_en");
+ if (ret < 0)
+ goto err_serdev;
+
+ ret = devm_gpio_request_one(&phy->ser_dev->dev,
+ phy->common.gpio_fw_wake,
+ GPIOF_OUT_INIT_LOW, "s3fwrn82_fw_wake");
+ if (ret < 0)
+ goto err_serdev;
+
+ ret = s3fwrn5_probe(&phy->common.ndev, phy, &phy->ser_dev->dev,
+ &uart_phy_ops);
+ if (ret < 0)
+ goto err_serdev;
+
+ return ret;
+
+err_serdev:
+ serdev_device_close(serdev);
+err_skb:
+ kfree_skb(phy->recv_skb);
+err_exit:
+ return ret;
+}
+
+static void s3fwrn82_uart_remove(struct serdev_device *serdev)
+{
+ struct s3fwrn82_uart_phy *phy = serdev_device_get_drvdata(serdev);
+
+ s3fwrn5_remove(phy->common.ndev);
+ serdev_device_close(serdev);
+ kfree_skb(phy->recv_skb);
+}
+
+static struct serdev_device_driver s3fwrn82_uart_driver = {
+ .probe = s3fwrn82_uart_probe,
+ .remove = s3fwrn82_uart_remove,
+ .driver = {
+ .name = "s3fwrn82_uart",
+ .of_match_table = s3fwrn82_uart_of_match,
+ },
+};
+
+module_serdev_device_driver(s3fwrn82_uart_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("UART driver for Samsung NFC");
+MODULE_AUTHOR("Bongsu Jeon <bongsu.jeon@samsung.com>");
MODULE_AUTHOR("IDT support-1588 <IDT-support-1588@lm.renesas.com>");
MODULE_VERSION("1.0");
MODULE_LICENSE("GPL");
+MODULE_FIRMWARE(FW_FILENAME);
/* Module Parameters */
static u32 sync_tod_timeout = SYNC_TOD_TIMEOUT_SEC;
}
}
-static int idt82p33_xfer(struct idt82p33 *idt82p33,
- unsigned char regaddr,
- unsigned char *buf,
- unsigned int count,
- int write)
+static int idt82p33_xfer_read(struct idt82p33 *idt82p33,
+ unsigned char regaddr,
+ unsigned char *buf,
+ unsigned int count)
{
struct i2c_client *client = idt82p33->client;
struct i2c_msg msg[2];
msg[0].buf = ®addr;
msg[1].addr = client->addr;
- msg[1].flags = write ? 0 : I2C_M_RD;
+ msg[1].flags = I2C_M_RD;
msg[1].len = count;
msg[1].buf = buf;
return 0;
}
+static int idt82p33_xfer_write(struct idt82p33 *idt82p33,
+ u8 regaddr,
+ u8 *buf,
+ u16 count)
+{
+ struct i2c_client *client = idt82p33->client;
+ /* we add 1 byte for device register */
+ u8 msg[IDT82P33_MAX_WRITE_COUNT + 1];
+ int err;
+
+ if (count > IDT82P33_MAX_WRITE_COUNT)
+ return -EINVAL;
+
+ msg[0] = regaddr;
+ memcpy(&msg[1], buf, count);
+
+ err = i2c_master_send(client, msg, count + 1);
+ if (err < 0) {
+ dev_err(&client->dev, "i2c_master_send returned %d\n", err);
+ return err;
+ }
+
+ return 0;
+}
+
static int idt82p33_page_offset(struct idt82p33 *idt82p33, unsigned char val)
{
int err;
if (idt82p33->page_offset == val)
return 0;
- err = idt82p33_xfer(idt82p33, PAGE_ADDR, &val, sizeof(val), 1);
+ err = idt82p33_xfer_write(idt82p33, PAGE_ADDR, &val, sizeof(val));
if (err)
dev_err(&idt82p33->client->dev,
"failed to set page offset %d\n", val);
err = idt82p33_page_offset(idt82p33, page);
if (err)
- goto out;
+ return err;
- err = idt82p33_xfer(idt82p33, offset, buf, count, write);
-out:
- return err;
+ if (write)
+ return idt82p33_xfer_write(idt82p33, offset, buf, count);
+
+ return idt82p33_xfer_read(idt82p33, offset, buf, count);
}
static int idt82p33_read(struct idt82p33 *idt82p33, unsigned int regaddr,
{
struct idt82p33 *idt82p33 = channel->idt82p33;
unsigned char buf[5] = {0};
- int neg_adj = 0;
int err, i;
s64 fcw;
* FCW = -------------
* 168 * 2^4
*/
- if (scaled_ppm < 0) {
- neg_adj = 1;
- scaled_ppm = -scaled_ppm;
- }
fcw = scaled_ppm * 244140625ULL;
- fcw = div_u64(fcw, 2688);
-
- if (neg_adj)
- fcw = -fcw;
+ fcw = div_s64(fcw, 2688);
for (i = 0; i < 5; i++) {
buf[i] = fcw & 0xff;
err = idt82p33_measure_settime_gettime_gap_overhead(channel, &gap_ns);
- if (err)
+ if (err) {
+ dev_err(&idt82p33->client->dev,
+ "Failed in %s with err %d!\n", __func__, err);
return err;
+ }
err = idt82p33_measure_one_byte_write_overhead(channel,
&one_byte_write_ns);
u8 sync_cnfg;
int err;
- if (enable == channel->sync_tod_on) {
- if (enable && sync_tod_timeout) {
- mod_delayed_work(system_wq, &channel->sync_tod_work,
- sync_tod_timeout * HZ);
- }
- return 0;
- }
+ /* Turn it off after sync_tod_timeout seconds */
+ if (enable && sync_tod_timeout)
+ ptp_schedule_worker(channel->ptp_clock,
+ sync_tod_timeout * HZ);
err = idt82p33_read(idt82p33, channel->dpll_sync_cnfg,
&sync_cnfg, sizeof(sync_cnfg));
return err;
sync_cnfg &= ~SYNC_TOD;
-
if (enable)
sync_cnfg |= SYNC_TOD;
- err = idt82p33_write(idt82p33, channel->dpll_sync_cnfg,
- &sync_cnfg, sizeof(sync_cnfg));
- if (err)
- return err;
-
- channel->sync_tod_on = enable;
-
- if (enable && sync_tod_timeout) {
- mod_delayed_work(system_wq, &channel->sync_tod_work,
- sync_tod_timeout * HZ);
- }
-
- return 0;
+ return idt82p33_write(idt82p33, channel->dpll_sync_cnfg,
+ &sync_cnfg, sizeof(sync_cnfg));
}
-static void idt82p33_sync_tod_work_handler(struct work_struct *work)
+static long idt82p33_sync_tod_work_handler(struct ptp_clock_info *ptp)
{
struct idt82p33_channel *channel =
- container_of(work, struct idt82p33_channel, sync_tod_work.work);
+ container_of(ptp, struct idt82p33_channel, caps);
struct idt82p33 *idt82p33 = channel->idt82p33;
mutex_lock(&idt82p33->reg_lock);
(void)idt82p33_sync_tod(channel, false);
mutex_unlock(&idt82p33->reg_lock);
+
+ /* Return a negative value here to not reschedule */
+ return -1;
}
-static int idt82p33_pps_enable(struct idt82p33_channel *channel, bool enable)
+static int idt82p33_output_enable(struct idt82p33_channel *channel,
+ bool enable, unsigned int outn)
{
struct idt82p33 *idt82p33 = channel->idt82p33;
- u8 mask, outn, val;
int err;
+ u8 val;
+
+ err = idt82p33_read(idt82p33, OUT_MUX_CNFG(outn), &val, sizeof(val));
+ if (err)
+ return err;
+ if (enable)
+ val &= ~SQUELCH_ENABLE;
+ else
+ val |= SQUELCH_ENABLE;
+
+ return idt82p33_write(idt82p33, OUT_MUX_CNFG(outn), &val, sizeof(val));
+}
+
+static int idt82p33_output_mask_enable(struct idt82p33_channel *channel,
+ bool enable)
+{
+ u16 mask;
+ int err;
+ u8 outn;
mask = channel->output_mask;
outn = 0;
while (mask) {
if (mask & 0x1) {
- err = idt82p33_read(idt82p33, OUT_MUX_CNFG(outn),
- &val, sizeof(val));
- if (err)
- return err;
-
- if (enable)
- val &= ~SQUELCH_ENABLE;
- else
- val |= SQUELCH_ENABLE;
-
- err = idt82p33_write(idt82p33, OUT_MUX_CNFG(outn),
- &val, sizeof(val));
-
+ err = idt82p33_output_enable(channel, enable, outn);
if (err)
return err;
}
+
mask >>= 0x1;
outn++;
}
return 0;
}
+static int idt82p33_perout_enable(struct idt82p33_channel *channel,
+ bool enable,
+ struct ptp_perout_request *perout)
+{
+ unsigned int flags = perout->flags;
+
+ /* Enable/disable output based on output_mask */
+ if (flags == PEROUT_ENABLE_OUTPUT_MASK)
+ return idt82p33_output_mask_enable(channel, enable);
+
+ /* Enable/disable individual output instead */
+ return idt82p33_output_enable(channel, enable, perout->index);
+}
+
static int idt82p33_enable_tod(struct idt82p33_channel *channel)
{
struct idt82p33 *idt82p33 = channel->idt82p33;
if (err)
return err;
- err = idt82p33_pps_enable(channel, false);
-
- if (err)
- return err;
-
err = idt82p33_measure_tod_write_overhead(channel);
- if (err)
+ if (err) {
+ dev_err(&idt82p33->client->dev,
+ "Failed in %s with err %d!\n", __func__, err);
return err;
+ }
err = _idt82p33_settime(channel, &ts);
channel = &idt82p33->channel[i];
- if (channel->ptp_clock) {
+ if (channel->ptp_clock)
ptp_clock_unregister(channel->ptp_clock);
- cancel_delayed_work_sync(&channel->sync_tod_work);
- }
}
}
if (rq->type == PTP_CLK_REQ_PEROUT) {
if (!on)
- err = idt82p33_pps_enable(channel, false);
-
+ err = idt82p33_perout_enable(channel, false,
+ &rq->perout);
/* Only accept a 1-PPS aligned to the second. */
else if (rq->perout.start.nsec || rq->perout.period.sec != 1 ||
rq->perout.period.nsec) {
err = -ERANGE;
} else
- err = idt82p33_pps_enable(channel, true);
+ err = idt82p33_perout_enable(channel, true,
+ &rq->perout);
}
mutex_unlock(&idt82p33->reg_lock);
return err;
}
+static int idt82p33_adjwritephase(struct ptp_clock_info *ptp, s32 offset_ns)
+{
+ struct idt82p33_channel *channel =
+ container_of(ptp, struct idt82p33_channel, caps);
+ struct idt82p33 *idt82p33 = channel->idt82p33;
+ s64 offset_regval, offset_fs;
+ u8 val[4] = {0};
+ int err;
+
+ offset_fs = (s64)(-offset_ns) * 1000000;
+
+ if (offset_fs > WRITE_PHASE_OFFSET_LIMIT)
+ offset_fs = WRITE_PHASE_OFFSET_LIMIT;
+ else if (offset_fs < -WRITE_PHASE_OFFSET_LIMIT)
+ offset_fs = -WRITE_PHASE_OFFSET_LIMIT;
+
+ /* Convert from phaseoffset_fs to register value */
+ offset_regval = div_s64(offset_fs * 1000, IDT_T0DPLL_PHASE_RESOL);
+
+ val[0] = offset_regval & 0xFF;
+ val[1] = (offset_regval >> 8) & 0xFF;
+ val[2] = (offset_regval >> 16) & 0xFF;
+ val[3] = (offset_regval >> 24) & 0x1F;
+ val[3] |= PH_OFFSET_EN;
+
+ mutex_lock(&idt82p33->reg_lock);
+
+ err = idt82p33_dpll_set_mode(channel, PLL_MODE_WPH);
+ if (err) {
+ dev_err(&idt82p33->client->dev,
+ "Failed in %s with err %d!\n", __func__, err);
+ goto out;
+ }
+
+ err = idt82p33_write(idt82p33, channel->dpll_phase_cnfg, val,
+ sizeof(val));
+
+out:
+ mutex_unlock(&idt82p33->reg_lock);
+ return err;
+}
+
static int idt82p33_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
{
struct idt82p33_channel *channel =
mutex_lock(&idt82p33->reg_lock);
err = _idt82p33_adjfine(channel, scaled_ppm);
+ if (err)
+ dev_err(&idt82p33->client->dev,
+ "Failed in %s with err %d!\n", __func__, err);
mutex_unlock(&idt82p33->reg_lock);
return err;
if (err) {
mutex_unlock(&idt82p33->reg_lock);
+ dev_err(&idt82p33->client->dev,
+ "Adjtime failed in %s with err %d!\n", __func__, err);
return err;
}
err = idt82p33_sync_tod(channel, true);
+ if (err)
+ dev_err(&idt82p33->client->dev,
+ "Sync_tod failed in %s with err %d!\n", __func__, err);
mutex_unlock(&idt82p33->reg_lock);
mutex_lock(&idt82p33->reg_lock);
err = _idt82p33_gettime(channel, ts);
+ if (err)
+ dev_err(&idt82p33->client->dev,
+ "Failed in %s with err %d!\n", __func__, err);
mutex_unlock(&idt82p33->reg_lock);
return err;
mutex_lock(&idt82p33->reg_lock);
err = _idt82p33_settime(channel, ts);
+ if (err)
+ dev_err(&idt82p33->client->dev,
+ "Failed in %s with err %d!\n", __func__, err);
mutex_unlock(&idt82p33->reg_lock);
return err;
return -EINVAL;
}
- INIT_DELAYED_WORK(&channel->sync_tod_work,
- idt82p33_sync_tod_work_handler);
- channel->sync_tod_on = false;
channel->current_freq_ppb = 0;
return 0;
{
caps->owner = THIS_MODULE;
caps->max_adj = 92000;
+ caps->n_per_out = 11;
+ caps->adjphase = idt82p33_adjwritephase;
caps->adjfine = idt82p33_adjfine;
caps->adjtime = idt82p33_adjtime;
caps->gettime64 = idt82p33_gettime;
caps->settime64 = idt82p33_settime;
caps->enable = idt82p33_enable;
+ caps->do_aux_work = idt82p33_sync_tod_work_handler;
}
static int idt82p33_enable_channel(struct idt82p33 *idt82p33, u32 index)
channel = &idt82p33->channel[index];
err = idt82p33_channel_init(channel, index);
- if (err)
+ if (err) {
+ dev_err(&idt82p33->client->dev,
+ "Channel_init failed in %s with err %d!\n",
+ __func__, err);
return err;
+ }
channel->idt82p33 = idt82p33;
idt82p33_caps_init(&channel->caps);
snprintf(channel->caps.name, sizeof(channel->caps.name),
"IDT 82P33 PLL%u", index);
- channel->caps.n_per_out = hweight8(channel->output_mask);
-
- err = idt82p33_dpll_set_mode(channel, PLL_MODE_DCO);
- if (err)
- return err;
-
- err = idt82p33_enable_tod(channel);
- if (err)
- return err;
channel->ptp_clock = ptp_clock_register(&channel->caps, NULL);
if (!channel->ptp_clock)
return -ENOTSUPP;
+ err = idt82p33_dpll_set_mode(channel, PLL_MODE_DCO);
+ if (err) {
+ dev_err(&idt82p33->client->dev,
+ "Dpll_set_mode failed in %s with err %d!\n",
+ __func__, err);
+ return err;
+ }
+
+ err = idt82p33_enable_tod(channel);
+ if (err) {
+ dev_err(&idt82p33->client->dev,
+ "Enable_tod failed in %s with err %d!\n",
+ __func__, err);
+ return err;
+ }
+
dev_info(&idt82p33->client->dev, "PLL%d registered as ptp%d\n",
index, channel->ptp_clock->index);
err = request_firmware(&fw, FW_FILENAME, &idt82p33->client->dev);
- if (err)
+ if (err) {
+ dev_err(&idt82p33->client->dev,
+ "Failed in %s with err %d!\n", __func__, err);
return err;
+ }
dev_dbg(&idt82p33->client->dev, "firmware size %zu bytes\n", fw->size);
for (i = 0; i < MAX_PHC_PLL; i++) {
if (idt82p33->pll_mask & (1 << i)) {
err = idt82p33_enable_channel(idt82p33, i);
- if (err)
+ if (err) {
+ dev_err(&idt82p33->client->dev,
+ "Failed in %s with err %d!\n",
+ __func__, err);
break;
+ }
}
}
} else {
#define PLL_MODE_SHIFT (0)
#define PLL_MODE_MASK (0x1F)
+#define PEROUT_ENABLE_OUTPUT_MASK (0xdeadbeef)
+
enum pll_mode {
PLL_MODE_MIN = 0,
PLL_MODE_AUTOMATIC = PLL_MODE_MIN,
#define MAX_MEASURMENT_COUNT (5)
#define SNAP_THRESHOLD_NS (150000)
#define SYNC_TOD_TIMEOUT_SEC (5)
+#define IDT82P33_MAX_WRITE_COUNT (512)
#define PLLMASK_ADDR_HI 0xFF
#define PLLMASK_ADDR_LO 0xA5
#define MESSAGE_TYPE_P_DELAY_RESP 3
#define MESSAGE_TYPE_DELAY_REQ 4
-#define SYNC 0x0
-#define DELAY_REQ 0x1
-#define PDELAY_REQ 0x2
-#define PDELAY_RESP 0x3
-
static LIST_HEAD(ines_clocks);
static DEFINE_MUTEX(ines_clocks_lock);
msgtype = ptp_get_msgtype(hdr, type);
- switch ((msgtype & 0xf)) {
- case SYNC:
- case PDELAY_RESP:
+ switch (msgtype) {
+ case PTP_MSGTYPE_SYNC:
+ case PTP_MSGTYPE_PDELAY_RESP:
return true;
default:
return false;
{
switch (tag) {
case MESSAGE_TYPE_SYNC:
- return SYNC;
+ return PTP_MSGTYPE_SYNC;
case MESSAGE_TYPE_P_DELAY_REQ:
- return PDELAY_REQ;
+ return PTP_MSGTYPE_PDELAY_REQ;
case MESSAGE_TYPE_P_DELAY_RESP:
- return PDELAY_RESP;
+ return PTP_MSGTYPE_PDELAY_RESP;
case MESSAGE_TYPE_DELAY_REQ:
- return DELAY_REQ;
+ return PTP_MSGTYPE_DELAY_REQ;
}
return 0xf;
}
/* p_header points to the last one we handled */
if (p_header)
p_header->pdu_flag |= PDU_LAST; /*Say it's the last one*/
- header = kzalloc(TH_HEADER_LENGTH, gfp_type());
- if (!header) {
- spin_unlock(&ch->collect_lock);
- fsm_event(priv->mpcg->fsm, MPCG_EVENT_INOP, dev);
- goto done;
- }
+
+ header = skb_push(ch->trans_skb, TH_HEADER_LENGTH);
+ memset(header, 0, TH_HEADER_LENGTH);
+
header->th_ch_flag = TH_HAS_PDU; /* Normal data */
ch->th_seq_num++;
header->th_seq_num = ch->th_seq_num;
CTCM_PR_DBGDATA("%s: ToVTAM_th_seq= %08x\n" ,
__func__, ch->th_seq_num);
- memcpy(skb_push(ch->trans_skb, TH_HEADER_LENGTH), header,
- TH_HEADER_LENGTH); /* put the TH on the packet */
-
- kfree(header);
-
CTCM_PR_DBGDATA("%s: trans_skb len:%04x \n",
__func__, ch->trans_skb->len);
CTCM_PR_DBGDATA("%s: up-to-50 bytes of trans_skb "
goto nomem;
}
- header = kmalloc(TH_SWEEP_LENGTH, gfp_type());
-
- if (!header) {
- dev_kfree_skb_any(sweep_skb);
- /* rc = -ENOMEM; */
- goto nomem;
- }
-
- header->th.th_seg = 0x00 ;
+ header = skb_put_zero(sweep_skb, TH_SWEEP_LENGTH);
header->th.th_ch_flag = TH_SWEEP_REQ; /* 0x0f */
- header->th.th_blk_flag = 0x00;
- header->th.th_is_xid = 0x00;
- header->th.th_seq_num = 0x00;
header->sw.th_last_seq = ch->th_seq_num;
- skb_put_data(sweep_skb, header, TH_SWEEP_LENGTH);
-
- kfree(header);
-
netif_trans_update(dev);
skb_queue_tail(&ch->sweep_queue, sweep_skb);
if ((fsm_getstate(ch->fsm) != CTC_STATE_TXIDLE) || grp->in_sweep) {
spin_lock_irqsave(&ch->collect_lock, saveflags);
refcount_inc(&skb->users);
- p_header = kmalloc(PDU_HEADER_LENGTH, gfp_type());
-
- if (!p_header) {
- spin_unlock_irqrestore(&ch->collect_lock, saveflags);
- goto nomem_exit;
- }
- p_header->pdu_offset = skb->len;
+ p_header = skb_push(skb, PDU_HEADER_LENGTH);
+ p_header->pdu_offset = skb->len - PDU_HEADER_LENGTH;
p_header->pdu_proto = 0x01;
- p_header->pdu_flag = 0x00;
if (be16_to_cpu(skb->protocol) == ETH_P_SNAP) {
- p_header->pdu_flag |= PDU_FIRST | PDU_CNTL;
+ p_header->pdu_flag = PDU_FIRST | PDU_CNTL;
} else {
- p_header->pdu_flag |= PDU_FIRST;
+ p_header->pdu_flag = PDU_FIRST;
}
p_header->pdu_seq = 0;
- memcpy(skb_push(skb, PDU_HEADER_LENGTH), p_header,
- PDU_HEADER_LENGTH);
CTCM_PR_DEBUG("%s(%s): Put on collect_q - skb len: %04x \n"
"pdu header and data for up to 32 bytes:\n",
skb_queue_tail(&ch->collect_queue, skb);
ch->collect_len += skb->len;
- kfree(p_header);
spin_unlock_irqrestore(&ch->collect_lock, saveflags);
goto done;
}
}
- p_header = kmalloc(PDU_HEADER_LENGTH, gfp_type());
-
- if (!p_header)
- goto nomem_exit;
-
- p_header->pdu_offset = skb->len;
+ p_header = skb_push(skb, PDU_HEADER_LENGTH);
+ p_header->pdu_offset = skb->len - PDU_HEADER_LENGTH;
p_header->pdu_proto = 0x01;
- p_header->pdu_flag = 0x00;
p_header->pdu_seq = 0;
if (be16_to_cpu(skb->protocol) == ETH_P_SNAP) {
- p_header->pdu_flag |= PDU_FIRST | PDU_CNTL;
+ p_header->pdu_flag = PDU_FIRST | PDU_CNTL;
} else {
- p_header->pdu_flag |= PDU_FIRST;
+ p_header->pdu_flag = PDU_FIRST;
}
- memcpy(skb_push(skb, PDU_HEADER_LENGTH), p_header, PDU_HEADER_LENGTH);
-
- kfree(p_header);
if (ch->collect_len > 0) {
spin_lock_irqsave(&ch->collect_lock, saveflags);
ch->prof.txlen += skb->len - PDU_HEADER_LENGTH;
- header = kmalloc(TH_HEADER_LENGTH, gfp_type());
- if (!header)
- goto nomem_exit;
+ /* put the TH on the packet */
+ header = skb_push(skb, TH_HEADER_LENGTH);
+ memset(header, 0, TH_HEADER_LENGTH);
- header->th_seg = 0x00;
header->th_ch_flag = TH_HAS_PDU; /* Normal data */
- header->th_blk_flag = 0x00;
- header->th_is_xid = 0x00; /* Just data here */
ch->th_seq_num++;
header->th_seq_num = ch->th_seq_num;
CTCM_PR_DBGDATA("%s(%s) ToVTAM_th_seq= %08x\n" ,
__func__, dev->name, ch->th_seq_num);
- /* put the TH on the packet */
- memcpy(skb_push(skb, TH_HEADER_LENGTH), header, TH_HEADER_LENGTH);
-
- kfree(header);
-
CTCM_PR_DBGDATA("%s(%s): skb len: %04x\n - pdu header and data for "
"up to 32 bytes sent to vtam:\n",
__func__, dev->name, skb->len);
CTCM_D3_DUMP((char *)skb->data, min_t(int, 32, skb->len));
len = skb->len + TH_HEADER_LENGTH + PDU_HEADER_LENGTH;
- newskb = __dev_alloc_skb(len, gfp_type() | GFP_DMA);
+ newskb = __dev_alloc_skb(len, GFP_ATOMIC | GFP_DMA);
if (!newskb) {
CTCM_DBF_TEXT_(MPC_TRACE, CTC_DBF_ERROR,
ch->protocol = priv->protocol;
if (IS_MPC(priv)) {
- ch->discontact_th = kzalloc(TH_HEADER_LENGTH, gfp_type());
+ ch->discontact_th = kzalloc(TH_HEADER_LENGTH, GFP_KERNEL);
if (ch->discontact_th == NULL)
goto nomem_return;
/* test if struct ctcm_priv of struct net_device has MPC protocol setting */
#define IS_MPCDEV(dev) IS_MPC((struct ctcm_priv *)dev->ml_priv)
-static inline gfp_t gfp_type(void)
-{
- return in_interrupt() ? GFP_ATOMIC : GFP_KERNEL;
-}
-
/*
* Definition of our link level header.
*/
goto done;
}
- header = kmalloc(sizeof(struct th_sweep), gfp_type());
-
- if (!header) {
- dev_kfree_skb_any(sweep_skb);
- goto done;
- }
-
- header->th.th_seg = 0x00 ;
+ header = skb_put_zero(sweep_skb, TH_SWEEP_LENGTH);
header->th.th_ch_flag = TH_SWEEP_RESP;
- header->th.th_blk_flag = 0x00;
- header->th.th_is_xid = 0x00;
- header->th.th_seq_num = 0x00;
header->sw.th_last_seq = ch->th_seq_num;
- skb_put_data(sweep_skb, header, TH_SWEEP_LENGTH);
-
- kfree(header);
-
netif_trans_update(dev);
skb_queue_tail(&ch->sweep_queue, sweep_skb);
skb_pull(pskb, new_len); /* point to next PDU */
}
} else {
- mpcginfo = kmalloc(sizeof(struct mpcg_info), gfp_type());
+ mpcginfo = kmalloc(sizeof(struct mpcg_info), GFP_ATOMIC);
if (mpcginfo == NULL)
goto done;
*/
static int mpc_send_qllc_discontact(struct net_device *dev)
{
- __u32 new_len = 0;
struct sk_buff *skb;
struct qllc *qllcptr;
struct ctcm_priv *priv = dev->ml_priv;
case MPCG_STATE_FLOWC:
case MPCG_STATE_READY:
grp->send_qllc_disc = 2;
- new_len = sizeof(struct qllc);
- qllcptr = kzalloc(new_len, gfp_type() | GFP_DMA);
- if (qllcptr == NULL) {
- CTCM_DBF_TEXT_(MPC_ERROR, CTC_DBF_ERROR,
- "%s(%s): qllcptr allocation error",
- CTCM_FUNTAIL, dev->name);
- return -ENOMEM;
- }
-
- qllcptr->qllc_address = 0xcc;
- qllcptr->qllc_commands = 0x03;
-
- skb = __dev_alloc_skb(new_len, GFP_ATOMIC);
+ skb = __dev_alloc_skb(sizeof(struct qllc), GFP_ATOMIC);
if (skb == NULL) {
CTCM_DBF_TEXT_(MPC_ERROR, CTC_DBF_ERROR,
"%s(%s): skb allocation error",
CTCM_FUNTAIL, dev->name);
priv->stats.rx_dropped++;
- kfree(qllcptr);
return -ENOMEM;
}
- skb_put_data(skb, qllcptr, new_len);
- kfree(qllcptr);
+ qllcptr = skb_put(skb, sizeof(struct qllc));
+ qllcptr->qllc_address = 0xcc;
+ qllcptr->qllc_commands = 0x03;
if (skb_headroom(skb) < 4) {
CTCM_DBF_TEXT_(MPC_ERROR, CTC_DBF_ERROR,
QETH_PNSO_ADDR_INFO,
};
+enum qeth_link_mode {
+ QETH_LINK_MODE_UNKNOWN,
+ QETH_LINK_MODE_FIBRE_SHORT,
+ QETH_LINK_MODE_FIBRE_LONG,
+};
+
+struct qeth_link_info {
+ u32 speed;
+ u8 duplex;
+ u8 port;
+ enum qeth_link_mode link_mode;
+};
+
#define QETH_BROADCAST_WITH_ECHO 0x01
#define QETH_BROADCAST_WITHOUT_ECHO 0x02
struct qeth_card_info {
struct qeth_card_blkt blkt;
__u32 diagass_support;
__u32 hwtrap;
+ struct qeth_link_info link_info;
};
enum qeth_discipline_id {
u8 bufs_refill;
};
-struct carrier_info {
- __u8 card_type;
- __u16 port_mode;
- __u32 port_speed;
-};
-
struct qeth_switch_info {
__u32 capabilities;
__u32 settings;
int qeth_query_switch_attributes(struct qeth_card *card,
struct qeth_switch_info *sw_info);
int qeth_query_card_info(struct qeth_card *card,
- struct carrier_info *carrier_info);
+ struct qeth_link_info *link_info);
int qeth_setadpparms_set_access_ctrl(struct qeth_card *card,
enum qeth_ipa_isolation_modes mode);
static int qeth_query_card_info_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct carrier_info *carrier_info = (struct carrier_info *)reply->param;
struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
+ struct qeth_link_info *link_info = reply->param;
struct qeth_query_card_info *card_info;
QETH_CARD_TEXT(card, 2, "qcrdincb");
return -EIO;
card_info = &cmd->data.setadapterparms.data.card_info;
- carrier_info->card_type = card_info->card_type;
- carrier_info->port_mode = card_info->port_mode;
- carrier_info->port_speed = card_info->port_speed;
+ netdev_dbg(card->dev,
+ "card info: card_type=0x%02x, port_mode=0x%04x, port_speed=0x%08x\n",
+ card_info->card_type, card_info->port_mode,
+ card_info->port_speed);
+
+ switch (card_info->port_mode) {
+ case CARD_INFO_PORTM_FULLDUPLEX:
+ link_info->duplex = DUPLEX_FULL;
+ break;
+ case CARD_INFO_PORTM_HALFDUPLEX:
+ link_info->duplex = DUPLEX_HALF;
+ break;
+ default:
+ link_info->duplex = DUPLEX_UNKNOWN;
+ }
+
+ switch (card_info->card_type) {
+ case CARD_INFO_TYPE_1G_COPPER_A:
+ case CARD_INFO_TYPE_1G_COPPER_B:
+ link_info->speed = SPEED_1000;
+ link_info->port = PORT_TP;
+ break;
+ case CARD_INFO_TYPE_1G_FIBRE_A:
+ case CARD_INFO_TYPE_1G_FIBRE_B:
+ link_info->speed = SPEED_1000;
+ link_info->port = PORT_FIBRE;
+ break;
+ case CARD_INFO_TYPE_10G_FIBRE_A:
+ case CARD_INFO_TYPE_10G_FIBRE_B:
+ link_info->speed = SPEED_10000;
+ link_info->port = PORT_FIBRE;
+ break;
+ default:
+ switch (card_info->port_speed) {
+ case CARD_INFO_PORTS_10M:
+ link_info->speed = SPEED_10;
+ break;
+ case CARD_INFO_PORTS_100M:
+ link_info->speed = SPEED_100;
+ break;
+ case CARD_INFO_PORTS_1G:
+ link_info->speed = SPEED_1000;
+ break;
+ case CARD_INFO_PORTS_10G:
+ link_info->speed = SPEED_10000;
+ break;
+ case CARD_INFO_PORTS_25G:
+ link_info->speed = SPEED_25000;
+ break;
+ default:
+ link_info->speed = SPEED_UNKNOWN;
+ }
+
+ link_info->port = PORT_OTHER;
+ }
+
return 0;
}
int qeth_query_card_info(struct qeth_card *card,
- struct carrier_info *carrier_info)
+ struct qeth_link_info *link_info)
{
struct qeth_cmd_buffer *iob;
iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_CARD_INFO, 0);
if (!iob)
return -ENOMEM;
- return qeth_send_ipa_cmd(card, iob, qeth_query_card_info_cb,
- (void *)carrier_info);
+
+ return qeth_send_ipa_cmd(card, iob, qeth_query_card_info_cb, link_info);
+}
+
+static int qeth_init_link_info_oat_cb(struct qeth_card *card,
+ struct qeth_reply *reply_priv,
+ unsigned long data)
+{
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
+ struct qeth_link_info *link_info = reply_priv->param;
+ struct qeth_query_oat_physical_if *phys_if;
+ struct qeth_query_oat_reply *reply;
+
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return -EIO;
+
+ /* Multi-part reply is unexpected, don't bother: */
+ if (cmd->data.setadapterparms.hdr.used_total > 1)
+ return -EINVAL;
+
+ /* Expect the reply to start with phys_if data: */
+ reply = &cmd->data.setadapterparms.data.query_oat.reply[0];
+ if (reply->type != QETH_QOAT_REPLY_TYPE_PHYS_IF ||
+ reply->length < sizeof(*reply))
+ return -EINVAL;
+
+ phys_if = &reply->phys_if;
+
+ switch (phys_if->speed_duplex) {
+ case QETH_QOAT_PHYS_SPEED_10M_HALF:
+ link_info->speed = SPEED_10;
+ link_info->duplex = DUPLEX_HALF;
+ break;
+ case QETH_QOAT_PHYS_SPEED_10M_FULL:
+ link_info->speed = SPEED_10;
+ link_info->duplex = DUPLEX_FULL;
+ break;
+ case QETH_QOAT_PHYS_SPEED_100M_HALF:
+ link_info->speed = SPEED_100;
+ link_info->duplex = DUPLEX_HALF;
+ break;
+ case QETH_QOAT_PHYS_SPEED_100M_FULL:
+ link_info->speed = SPEED_100;
+ link_info->duplex = DUPLEX_FULL;
+ break;
+ case QETH_QOAT_PHYS_SPEED_1000M_HALF:
+ link_info->speed = SPEED_1000;
+ link_info->duplex = DUPLEX_HALF;
+ break;
+ case QETH_QOAT_PHYS_SPEED_1000M_FULL:
+ link_info->speed = SPEED_1000;
+ link_info->duplex = DUPLEX_FULL;
+ break;
+ case QETH_QOAT_PHYS_SPEED_10G_FULL:
+ link_info->speed = SPEED_10000;
+ link_info->duplex = DUPLEX_FULL;
+ break;
+ case QETH_QOAT_PHYS_SPEED_25G_FULL:
+ link_info->speed = SPEED_25000;
+ link_info->duplex = DUPLEX_FULL;
+ break;
+ case QETH_QOAT_PHYS_SPEED_UNKNOWN:
+ default:
+ link_info->speed = SPEED_UNKNOWN;
+ link_info->duplex = DUPLEX_UNKNOWN;
+ break;
+ }
+
+ switch (phys_if->media_type) {
+ case QETH_QOAT_PHYS_MEDIA_COPPER:
+ link_info->port = PORT_TP;
+ link_info->link_mode = QETH_LINK_MODE_UNKNOWN;
+ break;
+ case QETH_QOAT_PHYS_MEDIA_FIBRE_SHORT:
+ link_info->port = PORT_FIBRE;
+ link_info->link_mode = QETH_LINK_MODE_FIBRE_SHORT;
+ break;
+ case QETH_QOAT_PHYS_MEDIA_FIBRE_LONG:
+ link_info->port = PORT_FIBRE;
+ link_info->link_mode = QETH_LINK_MODE_FIBRE_LONG;
+ break;
+ default:
+ link_info->port = PORT_OTHER;
+ link_info->link_mode = QETH_LINK_MODE_UNKNOWN;
+ break;
+ }
+
+ return 0;
+}
+
+static void qeth_init_link_info(struct qeth_card *card)
+{
+ card->info.link_info.duplex = DUPLEX_FULL;
+
+ if (IS_IQD(card) || IS_VM_NIC(card)) {
+ card->info.link_info.speed = SPEED_10000;
+ card->info.link_info.port = PORT_FIBRE;
+ card->info.link_info.link_mode = QETH_LINK_MODE_FIBRE_SHORT;
+ } else {
+ switch (card->info.link_type) {
+ case QETH_LINK_TYPE_FAST_ETH:
+ case QETH_LINK_TYPE_LANE_ETH100:
+ card->info.link_info.speed = SPEED_100;
+ card->info.link_info.port = PORT_TP;
+ break;
+ case QETH_LINK_TYPE_GBIT_ETH:
+ case QETH_LINK_TYPE_LANE_ETH1000:
+ card->info.link_info.speed = SPEED_1000;
+ card->info.link_info.port = PORT_FIBRE;
+ break;
+ case QETH_LINK_TYPE_10GBIT_ETH:
+ card->info.link_info.speed = SPEED_10000;
+ card->info.link_info.port = PORT_FIBRE;
+ break;
+ case QETH_LINK_TYPE_25GBIT_ETH:
+ card->info.link_info.speed = SPEED_25000;
+ card->info.link_info.port = PORT_FIBRE;
+ break;
+ default:
+ dev_info(&card->gdev->dev, "Unknown link type %x\n",
+ card->info.link_type);
+ card->info.link_info.speed = SPEED_UNKNOWN;
+ card->info.link_info.port = PORT_OTHER;
+ }
+
+ card->info.link_info.link_mode = QETH_LINK_MODE_UNKNOWN;
+ }
+
+ /* Get more accurate data via QUERY OAT: */
+ if (qeth_adp_supported(card, IPA_SETADP_QUERY_OAT)) {
+ struct qeth_link_info link_info;
+ struct qeth_cmd_buffer *iob;
+
+ iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_OAT,
+ SETADP_DATA_SIZEOF(query_oat));
+ if (iob) {
+ struct qeth_ipa_cmd *cmd = __ipa_cmd(iob);
+ struct qeth_query_oat *oat_req;
+
+ oat_req = &cmd->data.setadapterparms.data.query_oat;
+ oat_req->subcmd_code = QETH_QOAT_SCOPE_INTERFACE;
+
+ if (!qeth_send_ipa_cmd(card, iob,
+ qeth_init_link_info_oat_cb,
+ &link_info)) {
+ if (link_info.speed != SPEED_UNKNOWN)
+ card->info.link_info.speed = link_info.speed;
+ if (link_info.duplex != DUPLEX_UNKNOWN)
+ card->info.link_info.duplex = link_info.duplex;
+ if (link_info.port != PORT_OTHER)
+ card->info.link_info.port = link_info.port;
+ if (link_info.link_mode != QETH_LINK_MODE_UNKNOWN)
+ card->info.link_info.link_mode = link_info.link_mode;
+ }
+ }
+ }
}
/**
goto out;
}
+ qeth_init_link_info(card);
+
rc = qeth_init_qdio_queues(card);
if (rc) {
QETH_CARD_TEXT_(card, 2, "9err%d", rc);
__u8 reserved[8];
} __attribute__((packed));
+#define QETH_QOAT_PHYS_SPEED_UNKNOWN 0x00
+#define QETH_QOAT_PHYS_SPEED_10M_HALF 0x01
+#define QETH_QOAT_PHYS_SPEED_10M_FULL 0x02
+#define QETH_QOAT_PHYS_SPEED_100M_HALF 0x03
+#define QETH_QOAT_PHYS_SPEED_100M_FULL 0x04
+#define QETH_QOAT_PHYS_SPEED_1000M_HALF 0x05
+#define QETH_QOAT_PHYS_SPEED_1000M_FULL 0x06
+// n/a 0x07
+#define QETH_QOAT_PHYS_SPEED_10G_FULL 0x08
+// n/a 0x09
+#define QETH_QOAT_PHYS_SPEED_25G_FULL 0x0A
+
+#define QETH_QOAT_PHYS_MEDIA_COPPER 0x01
+#define QETH_QOAT_PHYS_MEDIA_FIBRE_SHORT 0x02
+#define QETH_QOAT_PHYS_MEDIA_FIBRE_LONG 0x04
+
+struct qeth_query_oat_physical_if {
+ u8 res_head[33];
+ u8 speed_duplex;
+ u8 media_type;
+ u8 res_tail[29];
+};
+
+#define QETH_QOAT_REPLY_TYPE_PHYS_IF 0x0004
+
+struct qeth_query_oat_reply {
+ u16 type;
+ u16 length;
+ u16 version;
+ u8 res[10];
+ struct qeth_query_oat_physical_if phys_if;
+};
+
+#define QETH_QOAT_SCOPE_INTERFACE 0x00000001
+
struct qeth_query_oat {
- __u32 subcmd_code;
- __u8 reserved[12];
+ u32 subcmd_code;
+ u8 reserved[12];
+ struct qeth_query_oat_reply reply[];
} __packed;
struct qeth_qoat_priv {
/* Autoneg and full-duplex are supported and advertised unconditionally. */
/* Always advertise and support all speeds up to specified, and only one */
/* specified port type. */
-static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd,
- int maxspeed, int porttype)
+static void qeth_set_ethtool_link_modes(struct ethtool_link_ksettings *cmd,
+ enum qeth_link_mode link_mode)
{
ethtool_link_ksettings_zero_link_mode(cmd, supported);
ethtool_link_ksettings_zero_link_mode(cmd, advertising);
ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg);
ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg);
- switch (porttype) {
+ switch (cmd->base.port) {
case PORT_TP:
ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
+
+ switch (cmd->base.speed) {
+ case SPEED_10000:
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ 10000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ 10000baseT_Full);
+ fallthrough;
+ case SPEED_1000:
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ 1000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ 1000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ 1000baseT_Half);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ 1000baseT_Half);
+ fallthrough;
+ case SPEED_100:
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ 100baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ 100baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ 100baseT_Half);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ 100baseT_Half);
+ fallthrough;
+ case SPEED_10:
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ 10baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ 10baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ 10baseT_Half);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ 10baseT_Half);
+ break;
+ default:
+ break;
+ }
+
break;
case PORT_FIBRE:
ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
- break;
- default:
- ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
- ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
- WARN_ON_ONCE(1);
- }
- /* partially does fall through, to also select lower speeds */
- switch (maxspeed) {
- case SPEED_25000:
- ethtool_link_ksettings_add_link_mode(cmd, supported,
- 25000baseSR_Full);
- ethtool_link_ksettings_add_link_mode(cmd, advertising,
- 25000baseSR_Full);
- break;
- case SPEED_10000:
- ethtool_link_ksettings_add_link_mode(cmd, supported,
- 10000baseT_Full);
- ethtool_link_ksettings_add_link_mode(cmd, advertising,
- 10000baseT_Full);
- fallthrough;
- case SPEED_1000:
- ethtool_link_ksettings_add_link_mode(cmd, supported,
- 1000baseT_Full);
- ethtool_link_ksettings_add_link_mode(cmd, advertising,
- 1000baseT_Full);
- ethtool_link_ksettings_add_link_mode(cmd, supported,
- 1000baseT_Half);
- ethtool_link_ksettings_add_link_mode(cmd, advertising,
- 1000baseT_Half);
- fallthrough;
- case SPEED_100:
- ethtool_link_ksettings_add_link_mode(cmd, supported,
- 100baseT_Full);
- ethtool_link_ksettings_add_link_mode(cmd, advertising,
- 100baseT_Full);
- ethtool_link_ksettings_add_link_mode(cmd, supported,
- 100baseT_Half);
- ethtool_link_ksettings_add_link_mode(cmd, advertising,
- 100baseT_Half);
- fallthrough;
- case SPEED_10:
- ethtool_link_ksettings_add_link_mode(cmd, supported,
- 10baseT_Full);
- ethtool_link_ksettings_add_link_mode(cmd, advertising,
- 10baseT_Full);
- ethtool_link_ksettings_add_link_mode(cmd, supported,
- 10baseT_Half);
- ethtool_link_ksettings_add_link_mode(cmd, advertising,
- 10baseT_Half);
+ switch (cmd->base.speed) {
+ case SPEED_25000:
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ 25000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ 25000baseSR_Full);
+ break;
+ case SPEED_10000:
+ if (link_mode == QETH_LINK_MODE_FIBRE_LONG) {
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ 10000baseLR_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ 10000baseLR_Full);
+ } else if (link_mode == QETH_LINK_MODE_FIBRE_SHORT) {
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ 10000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ 10000baseSR_Full);
+ }
+ break;
+ case SPEED_1000:
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ 1000baseX_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ 1000baseX_Full);
+ break;
+ default:
+ break;
+ }
+
break;
default:
- ethtool_link_ksettings_add_link_mode(cmd, supported,
- 10baseT_Full);
- ethtool_link_ksettings_add_link_mode(cmd, advertising,
- 10baseT_Full);
- ethtool_link_ksettings_add_link_mode(cmd, supported,
- 10baseT_Half);
- ethtool_link_ksettings_add_link_mode(cmd, advertising,
- 10baseT_Half);
- WARN_ON_ONCE(1);
+ break;
}
}
-
static int qeth_get_link_ksettings(struct net_device *netdev,
struct ethtool_link_ksettings *cmd)
{
struct qeth_card *card = netdev->ml_priv;
- enum qeth_link_types link_type;
- struct carrier_info carrier_info;
- int rc;
+ struct qeth_link_info link_info;
- if (IS_IQD(card) || IS_VM_NIC(card))
- link_type = QETH_LINK_TYPE_10GBIT_ETH;
- else
- link_type = card->info.link_type;
-
- cmd->base.duplex = DUPLEX_FULL;
+ cmd->base.speed = card->info.link_info.speed;
+ cmd->base.duplex = card->info.link_info.duplex;
+ cmd->base.port = card->info.link_info.port;
cmd->base.autoneg = AUTONEG_ENABLE;
cmd->base.phy_address = 0;
cmd->base.mdio_support = 0;
cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID;
- switch (link_type) {
- case QETH_LINK_TYPE_FAST_ETH:
- case QETH_LINK_TYPE_LANE_ETH100:
- cmd->base.speed = SPEED_100;
- cmd->base.port = PORT_TP;
- break;
- case QETH_LINK_TYPE_GBIT_ETH:
- case QETH_LINK_TYPE_LANE_ETH1000:
- cmd->base.speed = SPEED_1000;
- cmd->base.port = PORT_FIBRE;
- break;
- case QETH_LINK_TYPE_10GBIT_ETH:
- cmd->base.speed = SPEED_10000;
- cmd->base.port = PORT_FIBRE;
- break;
- case QETH_LINK_TYPE_25GBIT_ETH:
- cmd->base.speed = SPEED_25000;
- cmd->base.port = PORT_FIBRE;
- break;
- default:
- cmd->base.speed = SPEED_10;
- cmd->base.port = PORT_TP;
- }
- qeth_set_cmd_adv_sup(cmd, cmd->base.speed, cmd->base.port);
-
/* Check if we can obtain more accurate information. */
- /* If QUERY_CARD_INFO command is not supported or fails, */
- /* just return the heuristics that was filled above. */
- rc = qeth_query_card_info(card, &carrier_info);
- if (rc == -EOPNOTSUPP) /* for old hardware, return heuristic */
- return 0;
- if (rc) /* report error from the hardware operation */
- return rc;
- /* on success, fill in the information got from the hardware */
-
- netdev_dbg(netdev,
- "card info: card_type=0x%02x, port_mode=0x%04x, port_speed=0x%08x\n",
- carrier_info.card_type,
- carrier_info.port_mode,
- carrier_info.port_speed);
-
- /* Update attributes for which we've obtained more authoritative */
- /* information, leave the rest the way they where filled above. */
- switch (carrier_info.card_type) {
- case CARD_INFO_TYPE_1G_COPPER_A:
- case CARD_INFO_TYPE_1G_COPPER_B:
- cmd->base.port = PORT_TP;
- qeth_set_cmd_adv_sup(cmd, SPEED_1000, cmd->base.port);
- break;
- case CARD_INFO_TYPE_1G_FIBRE_A:
- case CARD_INFO_TYPE_1G_FIBRE_B:
- cmd->base.port = PORT_FIBRE;
- qeth_set_cmd_adv_sup(cmd, SPEED_1000, cmd->base.port);
- break;
- case CARD_INFO_TYPE_10G_FIBRE_A:
- case CARD_INFO_TYPE_10G_FIBRE_B:
- cmd->base.port = PORT_FIBRE;
- qeth_set_cmd_adv_sup(cmd, SPEED_10000, cmd->base.port);
- break;
- }
-
- switch (carrier_info.port_mode) {
- case CARD_INFO_PORTM_FULLDUPLEX:
- cmd->base.duplex = DUPLEX_FULL;
- break;
- case CARD_INFO_PORTM_HALFDUPLEX:
- cmd->base.duplex = DUPLEX_HALF;
- break;
+ if (!qeth_query_card_info(card, &link_info)) {
+ if (link_info.speed != SPEED_UNKNOWN)
+ cmd->base.speed = link_info.speed;
+ if (link_info.duplex != DUPLEX_UNKNOWN)
+ cmd->base.duplex = link_info.duplex;
+ if (link_info.port != PORT_OTHER)
+ cmd->base.port = link_info.port;
}
- switch (carrier_info.port_speed) {
- case CARD_INFO_PORTS_10M:
- cmd->base.speed = SPEED_10;
- break;
- case CARD_INFO_PORTS_100M:
- cmd->base.speed = SPEED_100;
- break;
- case CARD_INFO_PORTS_1G:
- cmd->base.speed = SPEED_1000;
- break;
- case CARD_INFO_PORTS_10G:
- cmd->base.speed = SPEED_10000;
- break;
- case CARD_INFO_PORTS_25G:
- cmd->base.speed = SPEED_25000;
- break;
- }
+ qeth_set_ethtool_link_modes(cmd, card->info.link_info.link_mode);
return 0;
}
*
* On enable, emits a series of address notifications for all
* currently registered hosts.
- *
- * Must be called under rtnl_lock
*/
static int qeth_l2_dev2br_an_set(struct qeth_card *card, bool enable)
{
if (READ_ONCE(card->info.pnso_mode) == QETH_PNSO_NONE)
goto free;
- /* Potential re-config in progress, try again later: */
- if (!rtnl_trylock()) {
- queue_delayed_work(card->event_wq, dwork,
- msecs_to_jiffies(100));
- return;
- }
- if (!netif_device_present(card->dev))
- goto out_unlock;
-
if (data->ac_event.lost_event_mask) {
+ /* Potential re-config in progress, try again later: */
+ if (!rtnl_trylock()) {
+ queue_delayed_work(card->event_wq, dwork,
+ msecs_to_jiffies(100));
+ return;
+ }
+
+ if (!netif_device_present(card->dev)) {
+ rtnl_unlock();
+ goto free;
+ }
+
QETH_DBF_MESSAGE(3,
"Address change notification overflow on device %x\n",
CARD_DEVID(card));
"Address Notification resynced on device %x\n",
CARD_DEVID(card));
}
+
+ rtnl_unlock();
} else {
for (i = 0; i < data->ac_event.num_entries; i++) {
struct qeth_ipacmd_addr_change_entry *entry =
}
}
-out_unlock:
- rtnl_unlock();
-
free:
kfree(data);
}
card->state = CARD_STATE_DOWN;
qeth_l2_set_pnso_mode(card, QETH_PNSO_NONE);
- if (priv->brport_features & BR_LEARNING_SYNC) {
- rtnl_lock();
+ if (priv->brport_features & BR_LEARNING_SYNC)
qeth_l2_dev2br_fdb_flush(card);
- rtnl_unlock();
- }
}
/* Returns zero if the command is successfully "consumed" */
qeth_l3_convert_addr_to_bits(ipatoe->addr, ipatoe_bits,
(ipatoe->proto == QETH_PROT_IPV4) ?
4 : 16);
- if (addr->proto == QETH_PROT_IPV4)
- rc = !memcmp(addr_bits, ipatoe_bits, ipatoe->mask_bits);
- else
- rc = !memcmp(addr_bits, ipatoe_bits, ipatoe->mask_bits);
+ rc = !memcmp(addr_bits, ipatoe_bits, ipatoe->mask_bits);
if (rc)
break;
}
#include "bnx2fc.h"
+#include <linux/ethtool.h>
+
static struct list_head adapter_list;
static struct list_head if_list;
static u32 adapter_count;
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/netdevice.h>
+#include <linux/ethtool.h>
#include <linux/errno.h>
#include <linux/crc32.h>
#include <scsi/libfcoe.h>
static u32 __poll_portal_slow(struct qman_portal *p, u32 is);
static inline unsigned int __poll_portal_fast(struct qman_portal *p,
- unsigned int poll_limit);
+ unsigned int poll_limit, bool sched_napi);
static void qm_congestion_task(struct work_struct *work);
static void qm_mr_process_task(struct work_struct *work);
/* DQRR-handling if it's interrupt-driven */
if (is & QM_PIRQ_DQRI) {
- __poll_portal_fast(p, QMAN_POLL_LIMIT);
+ __poll_portal_fast(p, QMAN_POLL_LIMIT, true);
clear = QM_DQAVAIL_MASK | QM_PIRQ_DQRI;
}
/* Handling of anything else that's interrupt-driven */
* user callbacks to call into any QMan API.
*/
static inline unsigned int __poll_portal_fast(struct qman_portal *p,
- unsigned int poll_limit)
+ unsigned int poll_limit, bool sched_napi)
{
const struct qm_dqrr_entry *dq;
struct qman_fq *fq;
* and we don't want multiple if()s in the critical
* path (SDQCR).
*/
- res = fq->cb.dqrr(p, fq, dq);
+ res = fq->cb.dqrr(p, fq, dq, sched_napi);
if (res == qman_cb_dqrr_stop)
break;
/* Check for VDQCR completion */
/* SDQCR: context_b points to the FQ */
fq = tag_to_fq(be32_to_cpu(dq->context_b));
/* Now let the callback do its stuff */
- res = fq->cb.dqrr(p, fq, dq);
+ res = fq->cb.dqrr(p, fq, dq, sched_napi);
/*
* The callback can request that we exit without
* consuming this entry nor advancing;
int qman_p_poll_dqrr(struct qman_portal *p, unsigned int limit)
{
- return __poll_portal_fast(p, limit);
+ return __poll_portal_fast(p, limit, false);
}
EXPORT_SYMBOL(qman_p_poll_dqrr);
static enum qman_cb_dqrr_result cb_dqrr(struct qman_portal *,
struct qman_fq *,
- const struct qm_dqrr_entry *);
+ const struct qm_dqrr_entry *,
+ bool sched_napi);
static void cb_ern(struct qman_portal *, struct qman_fq *,
const union qm_mr_entry *);
static void cb_fqs(struct qman_portal *, struct qman_fq *,
static enum qman_cb_dqrr_result cb_dqrr(struct qman_portal *p,
struct qman_fq *fq,
- const struct qm_dqrr_entry *dq)
+ const struct qm_dqrr_entry *dq,
+ bool sched_napi)
{
if (WARN_ON(fd_neq(&fd_dq, &dq->fd))) {
pr_err("BADNESS: dequeued frame doesn't match;\n");
static enum qman_cb_dqrr_result normal_dqrr(struct qman_portal *portal,
struct qman_fq *fq,
- const struct qm_dqrr_entry *dqrr)
+ const struct qm_dqrr_entry *dqrr,
+ bool sched_napi)
{
struct hp_handler *handler = (struct hp_handler *)fq;
static enum qman_cb_dqrr_result special_dqrr(struct qman_portal *portal,
struct qman_fq *fq,
- const struct qm_dqrr_entry *dqrr)
+ const struct qm_dqrr_entry *dqrr,
+ bool sched_napi)
{
struct hp_handler *handler = (struct hp_handler *)fq;
source "drivers/staging/qlge/Kconfig"
+source "drivers/staging/wimax/Kconfig"
+
source "drivers/staging/wfx/Kconfig"
source "drivers/staging/hikey9xx/Kconfig"
obj-$(CONFIG_FIELDBUS_DEV) += fieldbus/
obj-$(CONFIG_KPC2000) += kpc2000/
obj-$(CONFIG_QLGE) += qlge/
+obj-$(CONFIG_WIMAX) += wimax/
obj-$(CONFIG_WFX) += wfx/
obj-y += hikey9xx/
*
*/
+#include <linux/ethtool.h>
+
#include "ethsw.h"
static struct {
--- /dev/null
+.. include:: <isonum.txt>
+
+====================================================
+Driver for the Intel Wireless Wimax Connection 2400m
+====================================================
+
+:Copyright: |copy| 2008 Intel Corporation < linux-wimax@intel.com >
+
+ This provides a driver for the Intel Wireless WiMAX Connection 2400m
+ and a basic Linux kernel WiMAX stack.
+
+1. Requirements
+===============
+
+ * Linux installation with Linux kernel 2.6.22 or newer (if building
+ from a separate tree)
+ * Intel i2400m Echo Peak or Baxter Peak; this includes the Intel
+ Wireless WiMAX/WiFi Link 5x50 series.
+ * build tools:
+
+ + Linux kernel development package for the target kernel; to
+ build against your currently running kernel, you need to have
+ the kernel development package corresponding to the running
+ image installed (usually if your kernel is named
+ linux-VERSION, the development package is called
+ linux-dev-VERSION or linux-headers-VERSION).
+ + GNU C Compiler, make
+
+2. Compilation and installation
+===============================
+
+2.1. Compilation of the drivers included in the kernel
+------------------------------------------------------
+
+ Configure the kernel; to enable the WiMAX drivers select Drivers >
+ Networking Drivers > WiMAX device support. Enable all of them as
+ modules (easier).
+
+ If USB or SDIO are not enabled in the kernel configuration, the options
+ to build the i2400m USB or SDIO drivers will not show. Enable said
+ subsystems and go back to the WiMAX menu to enable the drivers.
+
+ Compile and install your kernel as usual.
+
+2.2. Compilation of the drivers distributed as an standalone module
+-------------------------------------------------------------------
+
+ To compile::
+
+ $ cd source/directory
+ $ make
+
+ Once built you can load and unload using the provided load.sh script;
+ load.sh will load the modules, load.sh u will unload them.
+
+ To install in the default kernel directories (and enable auto loading
+ when the device is plugged)::
+
+ $ make install
+ $ depmod -a
+
+ If your kernel development files are located in a non standard
+ directory or if you want to build for a kernel that is not the
+ currently running one, set KDIR to the right location::
+
+ $ make KDIR=/path/to/kernel/dev/tree
+
+ For more information, please contact linux-wimax@intel.com.
+
+3. Installing the firmware
+--------------------------
+
+ The firmware can be obtained from http://linuxwimax.org or might have
+ been supplied with your hardware.
+
+ It has to be installed in the target system::
+
+ $ cp FIRMWAREFILE.sbcf /lib/firmware/i2400m-fw-BUSTYPE-1.3.sbcf
+
+ * NOTE: if your firmware came in an .rpm or .deb file, just install
+ it as normal, with the rpm (rpm -i FIRMWARE.rpm) or dpkg
+ (dpkg -i FIRMWARE.deb) commands. No further action is needed.
+ * BUSTYPE will be usb or sdio, depending on the hardware you have.
+ Each hardware type comes with its own firmware and will not work
+ with other types.
+
+4. Design
+=========
+
+ This package contains two major parts: a WiMAX kernel stack and a
+ driver for the Intel i2400m.
+
+ The WiMAX stack is designed to provide for common WiMAX control
+ services to current and future WiMAX devices from any vendor; please
+ see README.wimax for details.
+
+ The i2400m kernel driver is broken up in two main parts: the bus
+ generic driver and the bus-specific drivers. The bus generic driver
+ forms the drivercore and contain no knowledge of the actual method we
+ use to connect to the device. The bus specific drivers are just the
+ glue to connect the bus-generic driver and the device. Currently only
+ USB and SDIO are supported. See drivers/net/wimax/i2400m/i2400m.h for
+ more information.
+
+ The bus generic driver is logically broken up in two parts: OS-glue and
+ hardware-glue. The OS-glue interfaces with Linux. The hardware-glue
+ interfaces with the device on using an interface provided by the
+ bus-specific driver. The reason for this breakup is to be able to
+ easily reuse the hardware-glue to write drivers for other OSes; note
+ the hardware glue part is written as a native Linux driver; no
+ abstraction layers are used, so to port to another OS, the Linux kernel
+ API calls should be replaced with the target OS's.
+
+5. Usage
+========
+
+ To load the driver, follow the instructions in the install section;
+ once the driver is loaded, plug in the device (unless it is permanently
+ plugged in). The driver will enumerate the device, upload the firmware
+ and output messages in the kernel log (dmesg, /var/log/messages or
+ /var/log/kern.log) such as::
+
+ ...
+ i2400m_usb 5-4:1.0: firmware interface version 8.0.0
+ i2400m_usb 5-4:1.0: WiMAX interface wmx0 (00:1d:e1:01:94:2c) ready
+
+ At this point the device is ready to work.
+
+ Current versions require the Intel WiMAX Network Service in userspace
+ to make things work. See the network service's README for instructions
+ on how to scan, connect and disconnect.
+
+5.1. Module parameters
+----------------------
+
+ Module parameters can be set at kernel or module load time or by
+ echoing values::
+
+ $ echo VALUE > /sys/module/MODULENAME/parameters/PARAMETERNAME
+
+ To make changes permanent, for example, for the i2400m module, you can
+ also create a file named /etc/modprobe.d/i2400m containing::
+
+ options i2400m idle_mode_disabled=1
+
+ To find which parameters are supported by a module, run::
+
+ $ modinfo path/to/module.ko
+
+ During kernel bootup (if the driver is linked in the kernel), specify
+ the following to the kernel command line::
+
+ i2400m.PARAMETER=VALUE
+
+5.1.1. i2400m: idle_mode_disabled
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ The i2400m module supports a parameter to disable idle mode. This
+ parameter, once set, will take effect only when the device is
+ reinitialized by the driver (eg: following a reset or a reconnect).
+
+5.2. Debug operations: debugfs entries
+--------------------------------------
+
+ The driver will register debugfs entries that allow the user to tweak
+ debug settings. There are three main container directories where
+ entries are placed, which correspond to the three blocks a i2400m WiMAX
+ driver has:
+
+ * /sys/kernel/debug/wimax:DEVNAME/ for the generic WiMAX stack
+ controls
+ * /sys/kernel/debug/wimax:DEVNAME/i2400m for the i2400m generic
+ driver controls
+ * /sys/kernel/debug/wimax:DEVNAME/i2400m-usb (or -sdio) for the
+ bus-specific i2400m-usb or i2400m-sdio controls).
+
+ Of course, if debugfs is mounted in a directory other than
+ /sys/kernel/debug, those paths will change.
+
+5.2.1. Increasing debug output
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ The files named *dl_* indicate knobs for controlling the debug output
+ of different submodules::
+
+ # find /sys/kernel/debug/wimax\:wmx0 -name \*dl_\*
+ /sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_tx
+ /sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_rx
+ /sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_notif
+ /sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_fw
+ /sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_usb
+ /sys/kernel/debug/wimax:wmx0/i2400m/dl_tx
+ /sys/kernel/debug/wimax:wmx0/i2400m/dl_rx
+ /sys/kernel/debug/wimax:wmx0/i2400m/dl_rfkill
+ /sys/kernel/debug/wimax:wmx0/i2400m/dl_netdev
+ /sys/kernel/debug/wimax:wmx0/i2400m/dl_fw
+ /sys/kernel/debug/wimax:wmx0/i2400m/dl_debugfs
+ /sys/kernel/debug/wimax:wmx0/i2400m/dl_driver
+ /sys/kernel/debug/wimax:wmx0/i2400m/dl_control
+ /sys/kernel/debug/wimax:wmx0/wimax_dl_stack
+ /sys/kernel/debug/wimax:wmx0/wimax_dl_op_rfkill
+ /sys/kernel/debug/wimax:wmx0/wimax_dl_op_reset
+ /sys/kernel/debug/wimax:wmx0/wimax_dl_op_msg
+ /sys/kernel/debug/wimax:wmx0/wimax_dl_id_table
+ /sys/kernel/debug/wimax:wmx0/wimax_dl_debugfs
+
+ By reading the file you can obtain the current value of said debug
+ level; by writing to it, you can set it.
+
+ To increase the debug level of, for example, the i2400m's generic TX
+ engine, just write::
+
+ $ echo 3 > /sys/kernel/debug/wimax:wmx0/i2400m/dl_tx
+
+ Increasing numbers yield increasing debug information; for details of
+ what is printed and the available levels, check the source. The code
+ uses 0 for disabled and increasing values until 8.
+
+5.2.2. RX and TX statistics
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ The i2400m/rx_stats and i2400m/tx_stats provide statistics about the
+ data reception/delivery from the device::
+
+ $ cat /sys/kernel/debug/wimax:wmx0/i2400m/rx_stats
+ 45 1 3 34 3104 48 480
+
+ The numbers reported are:
+
+ * packets/RX-buffer: total, min, max
+ * RX-buffers: total RX buffers received, accumulated RX buffer size
+ in bytes, min size received, max size received
+
+ Thus, to find the average buffer size received, divide accumulated
+ RX-buffer / total RX-buffers.
+
+ To clear the statistics back to 0, write anything to the rx_stats file::
+
+ $ echo 1 > /sys/kernel/debug/wimax:wmx0/i2400m_rx_stats
+
+ Likewise for TX.
+
+ Note the packets this debug file refers to are not network packet, but
+ packets in the sense of the device-specific protocol for communication
+ to the host. See drivers/net/wimax/i2400m/tx.c.
+
+5.2.3. Tracing messages received from user space
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ To echo messages received from user space into the trace pipe that the
+ i2400m driver creates, set the debug file i2400m/trace_msg_from_user to
+ 1::
+
+ $ echo 1 > /sys/kernel/debug/wimax:wmx0/i2400m/trace_msg_from_user
+
+5.2.4. Performing a device reset
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ By writing a 0, a 1 or a 2 to the file
+ /sys/kernel/debug/wimax:wmx0/reset, the driver performs a warm (without
+ disconnecting from the bus), cold (disconnecting from the bus) or bus
+ (bus specific) reset on the device.
+
+5.2.5. Asking the device to enter power saving mode
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ By writing any value to the /sys/kernel/debug/wimax:wmx0 file, the
+ device will attempt to enter power saving mode.
+
+6. Troubleshooting
+==================
+
+6.1. Driver complains about ``i2400m-fw-usb-1.2.sbcf: request failed``
+----------------------------------------------------------------------
+
+ If upon connecting the device, the following is output in the kernel
+ log::
+
+ i2400m_usb 5-4:1.0: fw i2400m-fw-usb-1.3.sbcf: request failed: -2
+
+ This means that the driver cannot locate the firmware file named
+ /lib/firmware/i2400m-fw-usb-1.2.sbcf. Check that the file is present in
+ the right location.
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+WiMAX subsystem
+===============
+
+.. toctree::
+ :maxdepth: 2
+
+ wimax
+
+ i2400m
+
+.. only:: subproject and html
+
+ Indices
+ =======
+
+ * :ref:`genindex`
--- /dev/null
+.. include:: <isonum.txt>
+
+========================
+Linux kernel WiMAX stack
+========================
+
+:Copyright: |copy| 2008 Intel Corporation < linux-wimax@intel.com >
+
+ This provides a basic Linux kernel WiMAX stack to provide a common
+ control API for WiMAX devices, usable from kernel and user space.
+
+1. Design
+=========
+
+ The WiMAX stack is designed to provide for common WiMAX control
+ services to current and future WiMAX devices from any vendor.
+
+ Because currently there is only one and we don't know what would be the
+ common services, the APIs it currently provides are very minimal.
+ However, it is done in such a way that it is easily extensible to
+ accommodate future requirements.
+
+ The stack works by embedding a struct wimax_dev in your device's
+ control structures. This provides a set of callbacks that the WiMAX
+ stack will call in order to implement control operations requested by
+ the user. As well, the stack provides API functions that the driver
+ calls to notify about changes of state in the device.
+
+ The stack exports the API calls needed to control the device to user
+ space using generic netlink as a marshalling mechanism. You can access
+ them using your own code or use the wrappers provided for your
+ convenience in libwimax (in the wimax-tools package).
+
+ For detailed information on the stack, please see
+ include/linux/wimax.h.
+
+2. Usage
+========
+
+ For usage in a driver (registration, API, etc) please refer to the
+ instructions in the header file include/linux/wimax.h.
+
+ When a device is registered with the WiMAX stack, a set of debugfs
+ files will appear in /sys/kernel/debug/wimax:wmxX can tweak for
+ control.
+
+2.1. Obtaining debug information: debugfs entries
+-------------------------------------------------
+
+ The WiMAX stack is compiled, by default, with debug messages that can
+ be used to diagnose issues. By default, said messages are disabled.
+
+ The drivers will register debugfs entries that allow the user to tweak
+ debug settings.
+
+ Each driver, when registering with the stack, will cause a debugfs
+ directory named wimax:DEVICENAME to be created; optionally, it might
+ create more subentries below it.
+
+2.1.1. Increasing debug output
+------------------------------
+
+ The files named *dl_* indicate knobs for controlling the debug output
+ of different submodules of the WiMAX stack::
+
+ # find /sys/kernel/debug/wimax\:wmx0 -name \*dl_\*
+ /sys/kernel/debug/wimax:wmx0/wimax_dl_stack
+ /sys/kernel/debug/wimax:wmx0/wimax_dl_op_rfkill
+ /sys/kernel/debug/wimax:wmx0/wimax_dl_op_reset
+ /sys/kernel/debug/wimax:wmx0/wimax_dl_op_msg
+ /sys/kernel/debug/wimax:wmx0/wimax_dl_id_table
+ /sys/kernel/debug/wimax:wmx0/wimax_dl_debugfs
+ /sys/kernel/debug/wimax:wmx0/.... # other driver specific files
+
+ NOTE:
+ Of course, if debugfs is mounted in a directory other than
+ /sys/kernel/debug, those paths will change.
+
+ By reading the file you can obtain the current value of said debug
+ level; by writing to it, you can set it.
+
+ To increase the debug level of, for example, the id-table submodule,
+ just write:
+
+ $ echo 3 > /sys/kernel/debug/wimax:wmx0/wimax_dl_id_table
+
+ Increasing numbers yield increasing debug information; for details of
+ what is printed and the available levels, check the source. The code
+ uses 0 for disabled and increasing values until 8.
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# WiMAX LAN device configuration
+#
+
+menuconfig WIMAX
+ tristate "WiMAX Wireless Broadband support"
+ depends on RFKILL || !RFKILL
+ help
+
+ Select to configure support for devices that provide
+ wireless broadband connectivity using the WiMAX protocol
+ (IEEE 802.16).
+
+ Please note that most of these devices require signing up
+ for a service plan with a provider.
+
+ The different WiMAX drivers can be enabled in the menu entry
+
+ Device Drivers > Network device support > WiMAX Wireless
+ Broadband devices
+
+ If unsure, it is safe to select M (module).
+
+if WIMAX
+
+config WIMAX_DEBUG_LEVEL
+ int "WiMAX debug level"
+ depends on WIMAX
+ default 8
+ help
+
+ Select the maximum debug verbosity level to be compiled into
+ the WiMAX stack code.
+
+ By default, debug messages are disabled at runtime and can
+ be selectively enabled for different parts of the code using
+ the sysfs debug-levels file.
+
+ If set at zero, this will compile out all the debug code.
+
+ It is recommended that it is left at 8.
+
+source "drivers/staging/wimax/i2400m/Kconfig"
+
+endif
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_WIMAX) += wimax.o
+
+wimax-y := \
+ id-table.o \
+ op-msg.o \
+ op-reset.o \
+ op-rfkill.o \
+ op-state-get.o \
+ stack.o
+
+wimax-$(CONFIG_DEBUG_FS) += debugfs.o
+
+obj-$(CONFIG_WIMAX_I2400M) += i2400m/
--- /dev/null
+There are no known users of this driver as of October 2020, and it will
+be removed unless someone turns out to still need it in future releases.
+
+According to https://en.wikipedia.org/wiki/List_of_WiMAX_networks, there
+have been many public wimax networks, but it appears that many of these
+have migrated to LTE or discontinued their service altogether. As most
+PCs and phones lack WiMAX hardware support, the remaining networks tend
+to use standalone routers. These almost certainly run Linux, but not a
+modern kernel or the mainline wimax driver stack.
+
+NetworkManager appears to have dropped userspace support in 2015
+https://bugzilla.gnome.org/show_bug.cgi?id=747846, the www.linuxwimax.org
+site had already shut down earlier.
+
+WiMax is apparently still being deployed on airport campus networks
+("AeroMACS"), but in a frequency band that was not supported by the old
+Intel 2400m (used in Sandy Bridge laptops and earlier), which is the
+only driver using the kernel's wimax stack.
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Linux WiMAX Stack
+ * Debug levels control file for the wimax module
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+#ifndef __debug_levels__h__
+#define __debug_levels__h__
+
+/* Maximum compile and run time debug level for all submodules */
+#define D_MODULENAME wimax
+#define D_MASTER CONFIG_WIMAX_DEBUG_LEVEL
+
+#include "linux-wimax-debug.h"
+
+/* List of all the enabled modules */
+enum d_module {
+ D_SUBMODULE_DECLARE(debugfs),
+ D_SUBMODULE_DECLARE(id_table),
+ D_SUBMODULE_DECLARE(op_msg),
+ D_SUBMODULE_DECLARE(op_reset),
+ D_SUBMODULE_DECLARE(op_rfkill),
+ D_SUBMODULE_DECLARE(op_state_get),
+ D_SUBMODULE_DECLARE(stack),
+};
+
+#endif /* #ifndef __debug_levels__h__ */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * Debugfs support
+ *
+ * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+#include <linux/debugfs.h>
+#include "linux-wimax.h"
+#include "wimax-internal.h"
+
+#define D_SUBMODULE debugfs
+#include "debug-levels.h"
+
+void wimax_debugfs_add(struct wimax_dev *wimax_dev)
+{
+ struct net_device *net_dev = wimax_dev->net_dev;
+ struct dentry *dentry;
+ char buf[128];
+
+ snprintf(buf, sizeof(buf), "wimax:%s", net_dev->name);
+ dentry = debugfs_create_dir(buf, NULL);
+ wimax_dev->debugfs_dentry = dentry;
+
+ d_level_register_debugfs("wimax_dl_", debugfs, dentry);
+ d_level_register_debugfs("wimax_dl_", id_table, dentry);
+ d_level_register_debugfs("wimax_dl_", op_msg, dentry);
+ d_level_register_debugfs("wimax_dl_", op_reset, dentry);
+ d_level_register_debugfs("wimax_dl_", op_rfkill, dentry);
+ d_level_register_debugfs("wimax_dl_", op_state_get, dentry);
+ d_level_register_debugfs("wimax_dl_", stack, dentry);
+}
+
+void wimax_debugfs_rm(struct wimax_dev *wimax_dev)
+{
+ debugfs_remove_recursive(wimax_dev->debugfs_dentry);
+}
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0-only
+
+config WIMAX_I2400M
+ tristate
+ depends on WIMAX
+ select FW_LOADER
+
+comment "Enable USB support to see WiMAX USB drivers"
+ depends on USB = n
+
+config WIMAX_I2400M_USB
+ tristate "Intel Wireless WiMAX Connection 2400 over USB (including 5x50)"
+ depends on WIMAX && USB
+ select WIMAX_I2400M
+ help
+ Select if you have a device based on the Intel WiMAX
+ Connection 2400 over USB (like any of the Intel Wireless
+ WiMAX/WiFi Link 5x50 series).
+
+ If unsure, it is safe to select M (module).
+
+config WIMAX_I2400M_DEBUG_LEVEL
+ int "WiMAX i2400m debug level"
+ depends on WIMAX_I2400M
+ default 8
+ help
+
+ Select the maximum debug verbosity level to be compiled into
+ the WiMAX i2400m driver code.
+
+ By default, this is disabled at runtime and can be
+ selectively enabled at runtime for different parts of the
+ code using the sysfs debug-levels file.
+
+ If set at zero, this will compile out all the debug code.
+
+ It is recommended that it is left at 8.
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_WIMAX_I2400M) += i2400m.o
+obj-$(CONFIG_WIMAX_I2400M_USB) += i2400m-usb.o
+
+i2400m-y := \
+ control.o \
+ driver.o \
+ fw.o \
+ op-rfkill.o \
+ sysfs.o \
+ netdev.o \
+ tx.o \
+ rx.o
+
+i2400m-$(CONFIG_DEBUG_FS) += debugfs.o
+
+i2400m-usb-y := \
+ usb-fw.o \
+ usb-notif.o \
+ usb-tx.o \
+ usb-rx.o \
+ usb.o
--- /dev/null
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Miscellaneous control functions for managing the device
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * - Initial implementation
+ *
+ * This is a collection of functions used to control the device (plus
+ * a few helpers).
+ *
+ * There are utilities for handling TLV buffers, hooks on the device's
+ * reports to act on device changes of state [i2400m_report_hook()],
+ * on acks to commands [i2400m_msg_ack_hook()], a helper for sending
+ * commands to the device and blocking until a reply arrives
+ * [i2400m_msg_to_dev()], a few high level commands for manipulating
+ * the device state, powersving mode and configuration plus the
+ * routines to setup the device once communication is stablished with
+ * it [i2400m_dev_initialize()].
+ *
+ * ROADMAP
+ *
+ * i2400m_dev_initialize() Called by i2400m_dev_start()
+ * i2400m_set_init_config()
+ * i2400m_cmd_get_state()
+ * i2400m_dev_shutdown() Called by i2400m_dev_stop()
+ * i2400m_reset()
+ *
+ * i2400m_{cmd,get,set}_*()
+ * i2400m_msg_to_dev()
+ * i2400m_msg_check_status()
+ *
+ * i2400m_report_hook() Called on reception of an event
+ * i2400m_report_state_hook()
+ * i2400m_tlv_buffer_walk()
+ * i2400m_tlv_match()
+ * i2400m_report_tlv_system_state()
+ * i2400m_report_tlv_rf_switches_status()
+ * i2400m_report_tlv_media_status()
+ * i2400m_cmd_enter_powersave()
+ *
+ * i2400m_msg_ack_hook() Called on reception of a reply to a
+ * command, get or set
+ */
+
+#include <stdarg.h>
+#include "i2400m.h"
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include "linux-wimax-i2400m.h"
+#include <linux/export.h>
+#include <linux/moduleparam.h>
+
+
+#define D_SUBMODULE control
+#include "debug-levels.h"
+
+static int i2400m_idle_mode_disabled;/* 0 (idle mode enabled) by default */
+module_param_named(idle_mode_disabled, i2400m_idle_mode_disabled, int, 0644);
+MODULE_PARM_DESC(idle_mode_disabled,
+ "If true, the device will not enable idle mode negotiation "
+ "with the base station (when connected) to save power.");
+
+/* 0 (power saving enabled) by default */
+static int i2400m_power_save_disabled;
+module_param_named(power_save_disabled, i2400m_power_save_disabled, int, 0644);
+MODULE_PARM_DESC(power_save_disabled,
+ "If true, the driver will not tell the device to enter "
+ "power saving mode when it reports it is ready for it. "
+ "False by default (so the device is told to do power "
+ "saving).");
+
+static int i2400m_passive_mode; /* 0 (passive mode disabled) by default */
+module_param_named(passive_mode, i2400m_passive_mode, int, 0644);
+MODULE_PARM_DESC(passive_mode,
+ "If true, the driver will not do any device setup "
+ "and leave it up to user space, who must be properly "
+ "setup.");
+
+
+/*
+ * Return if a TLV is of a give type and size
+ *
+ * @tlv_hdr: pointer to the TLV
+ * @tlv_type: type of the TLV we are looking for
+ * @tlv_size: expected size of the TLV we are looking for (if -1,
+ * don't check the size). This includes the header
+ * Returns: 0 if the TLV matches
+ * < 0 if it doesn't match at all
+ * > 0 total TLV + payload size, if the type matches, but not
+ * the size
+ */
+static
+ssize_t i2400m_tlv_match(const struct i2400m_tlv_hdr *tlv,
+ enum i2400m_tlv tlv_type, ssize_t tlv_size)
+{
+ if (le16_to_cpu(tlv->type) != tlv_type) /* Not our type? skip */
+ return -1;
+ if (tlv_size != -1
+ && le16_to_cpu(tlv->length) + sizeof(*tlv) != tlv_size) {
+ size_t size = le16_to_cpu(tlv->length) + sizeof(*tlv);
+ printk(KERN_WARNING "W: tlv type 0x%x mismatched because of "
+ "size (got %zu vs %zd expected)\n",
+ tlv_type, size, tlv_size);
+ return size;
+ }
+ return 0;
+}
+
+
+/*
+ * Given a buffer of TLVs, iterate over them
+ *
+ * @i2400m: device instance
+ * @tlv_buf: pointer to the beginning of the TLV buffer
+ * @buf_size: buffer size in bytes
+ * @tlv_pos: seek position; this is assumed to be a pointer returned
+ * by i2400m_tlv_buffer_walk() [and thus, validated]. The
+ * TLV returned will be the one following this one.
+ *
+ * Usage:
+ *
+ * tlv_itr = NULL;
+ * while (tlv_itr = i2400m_tlv_buffer_walk(i2400m, buf, size, tlv_itr)) {
+ * ...
+ * // Do stuff with tlv_itr, DON'T MODIFY IT
+ * ...
+ * }
+ */
+static
+const struct i2400m_tlv_hdr *i2400m_tlv_buffer_walk(
+ struct i2400m *i2400m,
+ const void *tlv_buf, size_t buf_size,
+ const struct i2400m_tlv_hdr *tlv_pos)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ const struct i2400m_tlv_hdr *tlv_top = tlv_buf + buf_size;
+ size_t offset, length, avail_size;
+ unsigned type;
+
+ if (tlv_pos == NULL) /* Take the first one? */
+ tlv_pos = tlv_buf;
+ else /* Nope, the next one */
+ tlv_pos = (void *) tlv_pos
+ + le16_to_cpu(tlv_pos->length) + sizeof(*tlv_pos);
+ if (tlv_pos == tlv_top) { /* buffer done */
+ tlv_pos = NULL;
+ goto error_beyond_end;
+ }
+ if (tlv_pos > tlv_top) {
+ tlv_pos = NULL;
+ WARN_ON(1);
+ goto error_beyond_end;
+ }
+ offset = (void *) tlv_pos - (void *) tlv_buf;
+ avail_size = buf_size - offset;
+ if (avail_size < sizeof(*tlv_pos)) {
+ dev_err(dev, "HW BUG? tlv_buf %p [%zu bytes], tlv @%zu: "
+ "short header\n", tlv_buf, buf_size, offset);
+ goto error_short_header;
+ }
+ type = le16_to_cpu(tlv_pos->type);
+ length = le16_to_cpu(tlv_pos->length);
+ if (avail_size < sizeof(*tlv_pos) + length) {
+ dev_err(dev, "HW BUG? tlv_buf %p [%zu bytes], "
+ "tlv type 0x%04x @%zu: "
+ "short data (%zu bytes vs %zu needed)\n",
+ tlv_buf, buf_size, type, offset, avail_size,
+ sizeof(*tlv_pos) + length);
+ goto error_short_header;
+ }
+error_short_header:
+error_beyond_end:
+ return tlv_pos;
+}
+
+
+/*
+ * Find a TLV in a buffer of sequential TLVs
+ *
+ * @i2400m: device descriptor
+ * @tlv_hdr: pointer to the first TLV in the sequence
+ * @size: size of the buffer in bytes; all TLVs are assumed to fit
+ * fully in the buffer (otherwise we'll complain).
+ * @tlv_type: type of the TLV we are looking for
+ * @tlv_size: expected size of the TLV we are looking for (if -1,
+ * don't check the size). This includes the header
+ *
+ * Returns: NULL if the TLV is not found, otherwise a pointer to
+ * it. If the sizes don't match, an error is printed and NULL
+ * returned.
+ */
+static
+const struct i2400m_tlv_hdr *i2400m_tlv_find(
+ struct i2400m *i2400m,
+ const struct i2400m_tlv_hdr *tlv_hdr, size_t size,
+ enum i2400m_tlv tlv_type, ssize_t tlv_size)
+{
+ ssize_t match;
+ struct device *dev = i2400m_dev(i2400m);
+ const struct i2400m_tlv_hdr *tlv = NULL;
+ while ((tlv = i2400m_tlv_buffer_walk(i2400m, tlv_hdr, size, tlv))) {
+ match = i2400m_tlv_match(tlv, tlv_type, tlv_size);
+ if (match == 0) /* found it :) */
+ break;
+ if (match > 0)
+ dev_warn(dev, "TLV type 0x%04x found with size "
+ "mismatch (%zu vs %zd needed)\n",
+ tlv_type, match, tlv_size);
+ }
+ return tlv;
+}
+
+
+static const struct
+{
+ char *msg;
+ int errno;
+} ms_to_errno[I2400M_MS_MAX] = {
+ [I2400M_MS_DONE_OK] = { "", 0 },
+ [I2400M_MS_DONE_IN_PROGRESS] = { "", 0 },
+ [I2400M_MS_INVALID_OP] = { "invalid opcode", -ENOSYS },
+ [I2400M_MS_BAD_STATE] = { "invalid state", -EILSEQ },
+ [I2400M_MS_ILLEGAL_VALUE] = { "illegal value", -EINVAL },
+ [I2400M_MS_MISSING_PARAMS] = { "missing parameters", -ENOMSG },
+ [I2400M_MS_VERSION_ERROR] = { "bad version", -EIO },
+ [I2400M_MS_ACCESSIBILITY_ERROR] = { "accesibility error", -EIO },
+ [I2400M_MS_BUSY] = { "busy", -EBUSY },
+ [I2400M_MS_CORRUPTED_TLV] = { "corrupted TLV", -EILSEQ },
+ [I2400M_MS_UNINITIALIZED] = { "uninitialized", -EILSEQ },
+ [I2400M_MS_UNKNOWN_ERROR] = { "unknown error", -EIO },
+ [I2400M_MS_PRODUCTION_ERROR] = { "production error", -EIO },
+ [I2400M_MS_NO_RF] = { "no RF", -EIO },
+ [I2400M_MS_NOT_READY_FOR_POWERSAVE] =
+ { "not ready for powersave", -EACCES },
+ [I2400M_MS_THERMAL_CRITICAL] = { "thermal critical", -EL3HLT },
+};
+
+
+/*
+ * i2400m_msg_check_status - translate a message's status code
+ *
+ * @i2400m: device descriptor
+ * @l3l4_hdr: message header
+ * @strbuf: buffer to place a formatted error message (unless NULL).
+ * @strbuf_size: max amount of available space; larger messages will
+ * be truncated.
+ *
+ * Returns: errno code corresponding to the status code in @l3l4_hdr
+ * and a message in @strbuf describing the error.
+ */
+int i2400m_msg_check_status(const struct i2400m_l3l4_hdr *l3l4_hdr,
+ char *strbuf, size_t strbuf_size)
+{
+ int result;
+ enum i2400m_ms status = le16_to_cpu(l3l4_hdr->status);
+ const char *str;
+
+ if (status == 0)
+ return 0;
+ if (status >= ARRAY_SIZE(ms_to_errno)) {
+ str = "unknown status code";
+ result = -EBADR;
+ } else {
+ str = ms_to_errno[status].msg;
+ result = ms_to_errno[status].errno;
+ }
+ if (strbuf)
+ snprintf(strbuf, strbuf_size, "%s (%d)", str, status);
+ return result;
+}
+
+
+/*
+ * Act on a TLV System State reported by the device
+ *
+ * @i2400m: device descriptor
+ * @ss: validated System State TLV
+ */
+static
+void i2400m_report_tlv_system_state(struct i2400m *i2400m,
+ const struct i2400m_tlv_system_state *ss)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+ enum i2400m_system_state i2400m_state = le32_to_cpu(ss->state);
+
+ d_fnstart(3, dev, "(i2400m %p ss %p [%u])\n", i2400m, ss, i2400m_state);
+
+ if (i2400m->state != i2400m_state) {
+ i2400m->state = i2400m_state;
+ wake_up_all(&i2400m->state_wq);
+ }
+ switch (i2400m_state) {
+ case I2400M_SS_UNINITIALIZED:
+ case I2400M_SS_INIT:
+ case I2400M_SS_CONFIG:
+ case I2400M_SS_PRODUCTION:
+ wimax_state_change(wimax_dev, WIMAX_ST_UNINITIALIZED);
+ break;
+
+ case I2400M_SS_RF_OFF:
+ case I2400M_SS_RF_SHUTDOWN:
+ wimax_state_change(wimax_dev, WIMAX_ST_RADIO_OFF);
+ break;
+
+ case I2400M_SS_READY:
+ case I2400M_SS_STANDBY:
+ case I2400M_SS_SLEEPACTIVE:
+ wimax_state_change(wimax_dev, WIMAX_ST_READY);
+ break;
+
+ case I2400M_SS_CONNECTING:
+ case I2400M_SS_WIMAX_CONNECTED:
+ wimax_state_change(wimax_dev, WIMAX_ST_READY);
+ break;
+
+ case I2400M_SS_SCAN:
+ case I2400M_SS_OUT_OF_ZONE:
+ wimax_state_change(wimax_dev, WIMAX_ST_SCANNING);
+ break;
+
+ case I2400M_SS_IDLE:
+ d_printf(1, dev, "entering BS-negotiated idle mode\n");
+ fallthrough;
+ case I2400M_SS_DISCONNECTING:
+ case I2400M_SS_DATA_PATH_CONNECTED:
+ wimax_state_change(wimax_dev, WIMAX_ST_CONNECTED);
+ break;
+
+ default:
+ /* Huh? just in case, shut it down */
+ dev_err(dev, "HW BUG? unknown state %u: shutting down\n",
+ i2400m_state);
+ i2400m_reset(i2400m, I2400M_RT_WARM);
+ break;
+ }
+ d_fnend(3, dev, "(i2400m %p ss %p [%u]) = void\n",
+ i2400m, ss, i2400m_state);
+}
+
+
+/*
+ * Parse and act on a TLV Media Status sent by the device
+ *
+ * @i2400m: device descriptor
+ * @ms: validated Media Status TLV
+ *
+ * This will set the carrier up on down based on the device's link
+ * report. This is done asides of what the WiMAX stack does based on
+ * the device's state as sometimes we need to do a link-renew (the BS
+ * wants us to renew a DHCP lease, for example).
+ *
+ * In fact, doc says that every time we get a link-up, we should do a
+ * DHCP negotiation...
+ */
+static
+void i2400m_report_tlv_media_status(struct i2400m *i2400m,
+ const struct i2400m_tlv_media_status *ms)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+ struct net_device *net_dev = wimax_dev->net_dev;
+ enum i2400m_media_status status = le32_to_cpu(ms->media_status);
+
+ d_fnstart(3, dev, "(i2400m %p ms %p [%u])\n", i2400m, ms, status);
+
+ switch (status) {
+ case I2400M_MEDIA_STATUS_LINK_UP:
+ netif_carrier_on(net_dev);
+ break;
+ case I2400M_MEDIA_STATUS_LINK_DOWN:
+ netif_carrier_off(net_dev);
+ break;
+ /*
+ * This is the network telling us we need to retrain the DHCP
+ * lease -- so far, we are trusting the WiMAX Network Service
+ * in user space to pick this up and poke the DHCP client.
+ */
+ case I2400M_MEDIA_STATUS_LINK_RENEW:
+ netif_carrier_on(net_dev);
+ break;
+ default:
+ dev_err(dev, "HW BUG? unknown media status %u\n",
+ status);
+ }
+ d_fnend(3, dev, "(i2400m %p ms %p [%u]) = void\n",
+ i2400m, ms, status);
+}
+
+
+/*
+ * Process a TLV from a 'state report'
+ *
+ * @i2400m: device descriptor
+ * @tlv: pointer to the TLV header; it has been already validated for
+ * consistent size.
+ * @tag: for error messages
+ *
+ * Act on the TLVs from a 'state report'.
+ */
+static
+void i2400m_report_state_parse_tlv(struct i2400m *i2400m,
+ const struct i2400m_tlv_hdr *tlv,
+ const char *tag)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ const struct i2400m_tlv_media_status *ms;
+ const struct i2400m_tlv_system_state *ss;
+ const struct i2400m_tlv_rf_switches_status *rfss;
+
+ if (0 == i2400m_tlv_match(tlv, I2400M_TLV_SYSTEM_STATE, sizeof(*ss))) {
+ ss = container_of(tlv, typeof(*ss), hdr);
+ d_printf(2, dev, "%s: system state TLV "
+ "found (0x%04x), state 0x%08x\n",
+ tag, I2400M_TLV_SYSTEM_STATE,
+ le32_to_cpu(ss->state));
+ i2400m_report_tlv_system_state(i2400m, ss);
+ }
+ if (0 == i2400m_tlv_match(tlv, I2400M_TLV_RF_STATUS, sizeof(*rfss))) {
+ rfss = container_of(tlv, typeof(*rfss), hdr);
+ d_printf(2, dev, "%s: RF status TLV "
+ "found (0x%04x), sw 0x%02x hw 0x%02x\n",
+ tag, I2400M_TLV_RF_STATUS,
+ le32_to_cpu(rfss->sw_rf_switch),
+ le32_to_cpu(rfss->hw_rf_switch));
+ i2400m_report_tlv_rf_switches_status(i2400m, rfss);
+ }
+ if (0 == i2400m_tlv_match(tlv, I2400M_TLV_MEDIA_STATUS, sizeof(*ms))) {
+ ms = container_of(tlv, typeof(*ms), hdr);
+ d_printf(2, dev, "%s: Media Status TLV: %u\n",
+ tag, le32_to_cpu(ms->media_status));
+ i2400m_report_tlv_media_status(i2400m, ms);
+ }
+}
+
+
+/*
+ * Parse a 'state report' and extract information
+ *
+ * @i2400m: device descriptor
+ * @l3l4_hdr: pointer to message; it has been already validated for
+ * consistent size.
+ * @size: size of the message (header + payload). The header length
+ * declaration is assumed to be congruent with @size (as in
+ * sizeof(*l3l4_hdr) + l3l4_hdr->length == size)
+ *
+ * Walk over the TLVs in a report state and act on them.
+ */
+static
+void i2400m_report_state_hook(struct i2400m *i2400m,
+ const struct i2400m_l3l4_hdr *l3l4_hdr,
+ size_t size, const char *tag)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ const struct i2400m_tlv_hdr *tlv;
+ size_t tlv_size = le16_to_cpu(l3l4_hdr->length);
+
+ d_fnstart(4, dev, "(i2400m %p, l3l4_hdr %p, size %zu, %s)\n",
+ i2400m, l3l4_hdr, size, tag);
+ tlv = NULL;
+
+ while ((tlv = i2400m_tlv_buffer_walk(i2400m, &l3l4_hdr->pl,
+ tlv_size, tlv)))
+ i2400m_report_state_parse_tlv(i2400m, tlv, tag);
+ d_fnend(4, dev, "(i2400m %p, l3l4_hdr %p, size %zu, %s) = void\n",
+ i2400m, l3l4_hdr, size, tag);
+}
+
+
+/*
+ * i2400m_report_hook - (maybe) act on a report
+ *
+ * @i2400m: device descriptor
+ * @l3l4_hdr: pointer to message; it has been already validated for
+ * consistent size.
+ * @size: size of the message (header + payload). The header length
+ * declaration is assumed to be congruent with @size (as in
+ * sizeof(*l3l4_hdr) + l3l4_hdr->length == size)
+ *
+ * Extract information we might need (like carrien on/off) from a
+ * device report.
+ */
+void i2400m_report_hook(struct i2400m *i2400m,
+ const struct i2400m_l3l4_hdr *l3l4_hdr, size_t size)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ unsigned msg_type;
+
+ d_fnstart(3, dev, "(i2400m %p l3l4_hdr %p size %zu)\n",
+ i2400m, l3l4_hdr, size);
+ /* Chew on the message, we might need some information from
+ * here */
+ msg_type = le16_to_cpu(l3l4_hdr->type);
+ switch (msg_type) {
+ case I2400M_MT_REPORT_STATE: /* carrier detection... */
+ i2400m_report_state_hook(i2400m,
+ l3l4_hdr, size, "REPORT STATE");
+ break;
+ /* If the device is ready for power save, then ask it to do
+ * it. */
+ case I2400M_MT_REPORT_POWERSAVE_READY: /* zzzzz */
+ if (l3l4_hdr->status == cpu_to_le16(I2400M_MS_DONE_OK)) {
+ if (i2400m_power_save_disabled)
+ d_printf(1, dev, "ready for powersave, "
+ "not requesting (disabled by module "
+ "parameter)\n");
+ else {
+ d_printf(1, dev, "ready for powersave, "
+ "requesting\n");
+ i2400m_cmd_enter_powersave(i2400m);
+ }
+ }
+ break;
+ }
+ d_fnend(3, dev, "(i2400m %p l3l4_hdr %p size %zu) = void\n",
+ i2400m, l3l4_hdr, size);
+}
+
+
+/*
+ * i2400m_msg_ack_hook - process cmd/set/get ack for internal status
+ *
+ * @i2400m: device descriptor
+ * @l3l4_hdr: pointer to message; it has been already validated for
+ * consistent size.
+ * @size: size of the message
+ *
+ * Extract information we might need from acks to commands and act on
+ * it. This is akin to i2400m_report_hook(). Note most of this
+ * processing should be done in the function that calls the
+ * command. This is here for some cases where it can't happen...
+ */
+static void i2400m_msg_ack_hook(struct i2400m *i2400m,
+ const struct i2400m_l3l4_hdr *l3l4_hdr,
+ size_t size)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ unsigned int ack_type;
+ char strerr[32];
+
+ /* Chew on the message, we might need some information from
+ * here */
+ ack_type = le16_to_cpu(l3l4_hdr->type);
+ switch (ack_type) {
+ case I2400M_MT_CMD_ENTER_POWERSAVE:
+ /* This is just left here for the sake of example, as
+ * the processing is done somewhere else. */
+ if (0) {
+ result = i2400m_msg_check_status(
+ l3l4_hdr, strerr, sizeof(strerr));
+ if (result >= 0)
+ d_printf(1, dev, "ready for power save: %zd\n",
+ size);
+ }
+ break;
+ }
+}
+
+
+/*
+ * i2400m_msg_size_check() - verify message size and header are congruent
+ *
+ * It is ok if the total message size is larger than the expected
+ * size, as there can be padding.
+ */
+int i2400m_msg_size_check(struct i2400m *i2400m,
+ const struct i2400m_l3l4_hdr *l3l4_hdr,
+ size_t msg_size)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ size_t expected_size;
+ d_fnstart(4, dev, "(i2400m %p l3l4_hdr %p msg_size %zu)\n",
+ i2400m, l3l4_hdr, msg_size);
+ if (msg_size < sizeof(*l3l4_hdr)) {
+ dev_err(dev, "bad size for message header "
+ "(expected at least %zu, got %zu)\n",
+ (size_t) sizeof(*l3l4_hdr), msg_size);
+ result = -EIO;
+ goto error_hdr_size;
+ }
+ expected_size = le16_to_cpu(l3l4_hdr->length) + sizeof(*l3l4_hdr);
+ if (msg_size < expected_size) {
+ dev_err(dev, "bad size for message code 0x%04x (expected %zu, "
+ "got %zu)\n", le16_to_cpu(l3l4_hdr->type),
+ expected_size, msg_size);
+ result = -EIO;
+ } else
+ result = 0;
+error_hdr_size:
+ d_fnend(4, dev,
+ "(i2400m %p l3l4_hdr %p msg_size %zu) = %d\n",
+ i2400m, l3l4_hdr, msg_size, result);
+ return result;
+}
+
+
+
+/*
+ * Cancel a wait for a command ACK
+ *
+ * @i2400m: device descriptor
+ * @code: [negative] errno code to cancel with (don't use
+ * -EINPROGRESS)
+ *
+ * If there is an ack already filled out, free it.
+ */
+void i2400m_msg_to_dev_cancel_wait(struct i2400m *i2400m, int code)
+{
+ struct sk_buff *ack_skb;
+ unsigned long flags;
+
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ ack_skb = i2400m->ack_skb;
+ if (ack_skb && !IS_ERR(ack_skb))
+ kfree_skb(ack_skb);
+ i2400m->ack_skb = ERR_PTR(code);
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+}
+
+
+/**
+ * i2400m_msg_to_dev - Send a control message to the device and get a response
+ *
+ * @i2400m: device descriptor
+ *
+ * @buf: pointer to the buffer containing the message to be sent; it
+ * has to start with a &struct i2400M_l3l4_hdr and then
+ * followed by the payload. Once this function returns, the
+ * buffer can be reused.
+ *
+ * @buf_len: buffer size
+ *
+ * Returns:
+ *
+ * Pointer to skb containing the ack message. You need to check the
+ * pointer with IS_ERR(), as it might be an error code. Error codes
+ * could happen because:
+ *
+ * - the message wasn't formatted correctly
+ * - couldn't send the message
+ * - failed waiting for a response
+ * - the ack message wasn't formatted correctly
+ *
+ * The returned skb has been allocated with wimax_msg_to_user_alloc(),
+ * it contains the response in a netlink attribute and is ready to be
+ * passed up to user space with wimax_msg_to_user_send(). To access
+ * the payload and its length, use wimax_msg_{data,len}() on the skb.
+ *
+ * The skb has to be freed with kfree_skb() once done.
+ *
+ * Description:
+ *
+ * This function delivers a message/command to the device and waits
+ * for an ack to be received. The format is described in
+ * linux/wimax/i2400m.h. In summary, a command/get/set is followed by an
+ * ack.
+ *
+ * This function will not check the ack status, that's left up to the
+ * caller. Once done with the ack skb, it has to be kfree_skb()ed.
+ *
+ * The i2400m handles only one message at the same time, thus we need
+ * the mutex to exclude other players.
+ *
+ * We write the message and then wait for an answer to come back. The
+ * RX path intercepts control messages and handles them in
+ * i2400m_rx_ctl(). Reports (notifications) are (maybe) processed
+ * locally and then forwarded (as needed) to user space on the WiMAX
+ * stack message pipe. Acks are saved and passed back to us through an
+ * skb in i2400m->ack_skb which is ready to be given to generic
+ * netlink if need be.
+ */
+struct sk_buff *i2400m_msg_to_dev(struct i2400m *i2400m,
+ const void *buf, size_t buf_len)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ const struct i2400m_l3l4_hdr *msg_l3l4_hdr;
+ struct sk_buff *ack_skb;
+ const struct i2400m_l3l4_hdr *ack_l3l4_hdr;
+ size_t ack_len;
+ int ack_timeout;
+ unsigned msg_type;
+ unsigned long flags;
+
+ d_fnstart(3, dev, "(i2400m %p buf %p len %zu)\n",
+ i2400m, buf, buf_len);
+
+ rmb(); /* Make sure we see what i2400m_dev_reset_handle() */
+ if (i2400m->boot_mode)
+ return ERR_PTR(-EL3RST);
+
+ msg_l3l4_hdr = buf;
+ /* Check msg & payload consistency */
+ result = i2400m_msg_size_check(i2400m, msg_l3l4_hdr, buf_len);
+ if (result < 0)
+ goto error_bad_msg;
+ msg_type = le16_to_cpu(msg_l3l4_hdr->type);
+ d_printf(1, dev, "CMD/GET/SET 0x%04x %zu bytes\n",
+ msg_type, buf_len);
+ d_dump(2, dev, buf, buf_len);
+
+ /* Setup the completion, ack_skb ("we are waiting") and send
+ * the message to the device */
+ mutex_lock(&i2400m->msg_mutex);
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ i2400m->ack_skb = ERR_PTR(-EINPROGRESS);
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ init_completion(&i2400m->msg_completion);
+ result = i2400m_tx(i2400m, buf, buf_len, I2400M_PT_CTRL);
+ if (result < 0) {
+ dev_err(dev, "can't send message 0x%04x: %d\n",
+ le16_to_cpu(msg_l3l4_hdr->type), result);
+ goto error_tx;
+ }
+
+ /* Some commands take longer to execute because of crypto ops,
+ * so we give them some more leeway on timeout */
+ switch (msg_type) {
+ case I2400M_MT_GET_TLS_OPERATION_RESULT:
+ case I2400M_MT_CMD_SEND_EAP_RESPONSE:
+ ack_timeout = 5 * HZ;
+ break;
+ default:
+ ack_timeout = HZ;
+ }
+
+ if (unlikely(i2400m->trace_msg_from_user))
+ wimax_msg(&i2400m->wimax_dev, "echo", buf, buf_len, GFP_KERNEL);
+ /* The RX path in rx.c will put any response for this message
+ * in i2400m->ack_skb and wake us up. If we cancel the wait,
+ * we need to change the value of i2400m->ack_skb to something
+ * not -EINPROGRESS so RX knows there is no one waiting. */
+ result = wait_for_completion_interruptible_timeout(
+ &i2400m->msg_completion, ack_timeout);
+ if (result == 0) {
+ dev_err(dev, "timeout waiting for reply to message 0x%04x\n",
+ msg_type);
+ result = -ETIMEDOUT;
+ i2400m_msg_to_dev_cancel_wait(i2400m, result);
+ goto error_wait_for_completion;
+ } else if (result < 0) {
+ dev_err(dev, "error waiting for reply to message 0x%04x: %d\n",
+ msg_type, result);
+ i2400m_msg_to_dev_cancel_wait(i2400m, result);
+ goto error_wait_for_completion;
+ }
+
+ /* Pull out the ack data from i2400m->ack_skb -- see if it is
+ * an error and act accordingly */
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ ack_skb = i2400m->ack_skb;
+ if (IS_ERR(ack_skb))
+ result = PTR_ERR(ack_skb);
+ else
+ result = 0;
+ i2400m->ack_skb = NULL;
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ if (result < 0)
+ goto error_ack_status;
+ ack_l3l4_hdr = wimax_msg_data_len(ack_skb, &ack_len);
+
+ /* Check the ack and deliver it if it is ok */
+ if (unlikely(i2400m->trace_msg_from_user))
+ wimax_msg(&i2400m->wimax_dev, "echo",
+ ack_l3l4_hdr, ack_len, GFP_KERNEL);
+ result = i2400m_msg_size_check(i2400m, ack_l3l4_hdr, ack_len);
+ if (result < 0) {
+ dev_err(dev, "HW BUG? reply to message 0x%04x: %d\n",
+ msg_type, result);
+ goto error_bad_ack_len;
+ }
+ if (msg_type != le16_to_cpu(ack_l3l4_hdr->type)) {
+ dev_err(dev, "HW BUG? bad reply 0x%04x to message 0x%04x\n",
+ le16_to_cpu(ack_l3l4_hdr->type), msg_type);
+ result = -EIO;
+ goto error_bad_ack_type;
+ }
+ i2400m_msg_ack_hook(i2400m, ack_l3l4_hdr, ack_len);
+ mutex_unlock(&i2400m->msg_mutex);
+ d_fnend(3, dev, "(i2400m %p buf %p len %zu) = %p\n",
+ i2400m, buf, buf_len, ack_skb);
+ return ack_skb;
+
+error_bad_ack_type:
+error_bad_ack_len:
+ kfree_skb(ack_skb);
+error_ack_status:
+error_wait_for_completion:
+error_tx:
+ mutex_unlock(&i2400m->msg_mutex);
+error_bad_msg:
+ d_fnend(3, dev, "(i2400m %p buf %p len %zu) = %d\n",
+ i2400m, buf, buf_len, result);
+ return ERR_PTR(result);
+}
+
+
+/*
+ * Definitions for the Enter Power Save command
+ *
+ * The Enter Power Save command requests the device to go into power
+ * saving mode. The device will ack or nak the command depending on it
+ * being ready for it. If it acks, we tell the USB subsystem to
+ *
+ * As well, the device might request to go into power saving mode by
+ * sending a report (REPORT_POWERSAVE_READY), in which case, we issue
+ * this command. The hookups in the RX coder allow
+ */
+enum {
+ I2400M_WAKEUP_ENABLED = 0x01,
+ I2400M_WAKEUP_DISABLED = 0x02,
+ I2400M_TLV_TYPE_WAKEUP_MODE = 144,
+};
+
+struct i2400m_cmd_enter_power_save {
+ struct i2400m_l3l4_hdr hdr;
+ struct i2400m_tlv_hdr tlv;
+ __le32 val;
+} __packed;
+
+
+/*
+ * Request entering power save
+ *
+ * This command is (mainly) executed when the device indicates that it
+ * is ready to go into powersave mode via a REPORT_POWERSAVE_READY.
+ */
+int i2400m_cmd_enter_powersave(struct i2400m *i2400m)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *ack_skb;
+ struct i2400m_cmd_enter_power_save *cmd;
+ char strerr[32];
+
+ result = -ENOMEM;
+ cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+ if (cmd == NULL)
+ goto error_alloc;
+ cmd->hdr.type = cpu_to_le16(I2400M_MT_CMD_ENTER_POWERSAVE);
+ cmd->hdr.length = cpu_to_le16(sizeof(*cmd) - sizeof(cmd->hdr));
+ cmd->hdr.version = cpu_to_le16(I2400M_L3L4_VERSION);
+ cmd->tlv.type = cpu_to_le16(I2400M_TLV_TYPE_WAKEUP_MODE);
+ cmd->tlv.length = cpu_to_le16(sizeof(cmd->val));
+ cmd->val = cpu_to_le32(I2400M_WAKEUP_ENABLED);
+
+ ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+ result = PTR_ERR(ack_skb);
+ if (IS_ERR(ack_skb)) {
+ dev_err(dev, "Failed to issue 'Enter power save' command: %d\n",
+ result);
+ goto error_msg_to_dev;
+ }
+ result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
+ strerr, sizeof(strerr));
+ if (result == -EACCES)
+ d_printf(1, dev, "Cannot enter power save mode\n");
+ else if (result < 0)
+ dev_err(dev, "'Enter power save' (0x%04x) command failed: "
+ "%d - %s\n", I2400M_MT_CMD_ENTER_POWERSAVE,
+ result, strerr);
+ else
+ d_printf(1, dev, "device ready to power save\n");
+ kfree_skb(ack_skb);
+error_msg_to_dev:
+ kfree(cmd);
+error_alloc:
+ return result;
+}
+EXPORT_SYMBOL_GPL(i2400m_cmd_enter_powersave);
+
+
+/*
+ * Definitions for getting device information
+ */
+enum {
+ I2400M_TLV_DETAILED_DEVICE_INFO = 140
+};
+
+/**
+ * i2400m_get_device_info - Query the device for detailed device information
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: an skb whose skb->data points to a 'struct
+ * i2400m_tlv_detailed_device_info'. When done, kfree_skb() it. The
+ * skb is *guaranteed* to contain the whole TLV data structure.
+ *
+ * On error, IS_ERR(skb) is true and ERR_PTR(skb) is the error
+ * code.
+ */
+struct sk_buff *i2400m_get_device_info(struct i2400m *i2400m)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *ack_skb;
+ struct i2400m_l3l4_hdr *cmd;
+ const struct i2400m_l3l4_hdr *ack;
+ size_t ack_len;
+ const struct i2400m_tlv_hdr *tlv;
+ const struct i2400m_tlv_detailed_device_info *ddi;
+ char strerr[32];
+
+ ack_skb = ERR_PTR(-ENOMEM);
+ cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+ if (cmd == NULL)
+ goto error_alloc;
+ cmd->type = cpu_to_le16(I2400M_MT_GET_DEVICE_INFO);
+ cmd->length = 0;
+ cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
+
+ ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+ if (IS_ERR(ack_skb)) {
+ dev_err(dev, "Failed to issue 'get device info' command: %ld\n",
+ PTR_ERR(ack_skb));
+ goto error_msg_to_dev;
+ }
+ ack = wimax_msg_data_len(ack_skb, &ack_len);
+ result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
+ if (result < 0) {
+ dev_err(dev, "'get device info' (0x%04x) command failed: "
+ "%d - %s\n", I2400M_MT_GET_DEVICE_INFO, result,
+ strerr);
+ goto error_cmd_failed;
+ }
+ tlv = i2400m_tlv_find(i2400m, ack->pl, ack_len - sizeof(*ack),
+ I2400M_TLV_DETAILED_DEVICE_INFO, sizeof(*ddi));
+ if (tlv == NULL) {
+ dev_err(dev, "GET DEVICE INFO: "
+ "detailed device info TLV not found (0x%04x)\n",
+ I2400M_TLV_DETAILED_DEVICE_INFO);
+ result = -EIO;
+ goto error_no_tlv;
+ }
+ skb_pull(ack_skb, (void *) tlv - (void *) ack_skb->data);
+error_msg_to_dev:
+ kfree(cmd);
+error_alloc:
+ return ack_skb;
+
+error_no_tlv:
+error_cmd_failed:
+ kfree_skb(ack_skb);
+ kfree(cmd);
+ return ERR_PTR(result);
+}
+
+
+/* Firmware interface versions we support */
+enum {
+ I2400M_HDIv_MAJOR = 9,
+ I2400M_HDIv_MINOR = 1,
+ I2400M_HDIv_MINOR_2 = 2,
+};
+
+
+/**
+ * i2400m_firmware_check - check firmware versions are compatible with
+ * the driver
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: 0 if ok, < 0 errno code an error and a message in the
+ * kernel log.
+ *
+ * Long function, but quite simple; first chunk launches the command
+ * and double checks the reply for the right TLV. Then we process the
+ * TLV (where the meat is).
+ *
+ * Once we process the TLV that gives us the firmware's interface
+ * version, we encode it and save it in i2400m->fw_version for future
+ * reference.
+ */
+int i2400m_firmware_check(struct i2400m *i2400m)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *ack_skb;
+ struct i2400m_l3l4_hdr *cmd;
+ const struct i2400m_l3l4_hdr *ack;
+ size_t ack_len;
+ const struct i2400m_tlv_hdr *tlv;
+ const struct i2400m_tlv_l4_message_versions *l4mv;
+ char strerr[32];
+ unsigned major, minor, branch;
+
+ result = -ENOMEM;
+ cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+ if (cmd == NULL)
+ goto error_alloc;
+ cmd->type = cpu_to_le16(I2400M_MT_GET_LM_VERSION);
+ cmd->length = 0;
+ cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
+
+ ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+ if (IS_ERR(ack_skb)) {
+ result = PTR_ERR(ack_skb);
+ dev_err(dev, "Failed to issue 'get lm version' command: %-d\n",
+ result);
+ goto error_msg_to_dev;
+ }
+ ack = wimax_msg_data_len(ack_skb, &ack_len);
+ result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
+ if (result < 0) {
+ dev_err(dev, "'get lm version' (0x%04x) command failed: "
+ "%d - %s\n", I2400M_MT_GET_LM_VERSION, result,
+ strerr);
+ goto error_cmd_failed;
+ }
+ tlv = i2400m_tlv_find(i2400m, ack->pl, ack_len - sizeof(*ack),
+ I2400M_TLV_L4_MESSAGE_VERSIONS, sizeof(*l4mv));
+ if (tlv == NULL) {
+ dev_err(dev, "get lm version: TLV not found (0x%04x)\n",
+ I2400M_TLV_L4_MESSAGE_VERSIONS);
+ result = -EIO;
+ goto error_no_tlv;
+ }
+ l4mv = container_of(tlv, typeof(*l4mv), hdr);
+ major = le16_to_cpu(l4mv->major);
+ minor = le16_to_cpu(l4mv->minor);
+ branch = le16_to_cpu(l4mv->branch);
+ result = -EINVAL;
+ if (major != I2400M_HDIv_MAJOR) {
+ dev_err(dev, "unsupported major fw version "
+ "%u.%u.%u\n", major, minor, branch);
+ goto error_bad_major;
+ }
+ result = 0;
+ if (minor > I2400M_HDIv_MINOR_2 || minor < I2400M_HDIv_MINOR)
+ dev_warn(dev, "untested minor fw version %u.%u.%u\n",
+ major, minor, branch);
+ /* Yes, we ignore the branch -- we don't have to track it */
+ i2400m->fw_version = major << 16 | minor;
+ dev_info(dev, "firmware interface version %u.%u.%u\n",
+ major, minor, branch);
+error_bad_major:
+error_no_tlv:
+error_cmd_failed:
+ kfree_skb(ack_skb);
+error_msg_to_dev:
+ kfree(cmd);
+error_alloc:
+ return result;
+}
+
+
+/*
+ * Send an DoExitIdle command to the device to ask it to go out of
+ * basestation-idle mode.
+ *
+ * @i2400m: device descriptor
+ *
+ * This starts a renegotiation with the basestation that might involve
+ * another crypto handshake with user space.
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ */
+int i2400m_cmd_exit_idle(struct i2400m *i2400m)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *ack_skb;
+ struct i2400m_l3l4_hdr *cmd;
+ char strerr[32];
+
+ result = -ENOMEM;
+ cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+ if (cmd == NULL)
+ goto error_alloc;
+ cmd->type = cpu_to_le16(I2400M_MT_CMD_EXIT_IDLE);
+ cmd->length = 0;
+ cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
+
+ ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+ result = PTR_ERR(ack_skb);
+ if (IS_ERR(ack_skb)) {
+ dev_err(dev, "Failed to issue 'exit idle' command: %d\n",
+ result);
+ goto error_msg_to_dev;
+ }
+ result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
+ strerr, sizeof(strerr));
+ kfree_skb(ack_skb);
+error_msg_to_dev:
+ kfree(cmd);
+error_alloc:
+ return result;
+
+}
+
+
+/*
+ * Query the device for its state, update the WiMAX stack's idea of it
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * Executes a 'Get State' command and parses the returned
+ * TLVs.
+ *
+ * Because this is almost identical to a 'Report State', we use
+ * i2400m_report_state_hook() to parse the answer. This will set the
+ * carrier state, as well as the RF Kill switches state.
+ */
+static int i2400m_cmd_get_state(struct i2400m *i2400m)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *ack_skb;
+ struct i2400m_l3l4_hdr *cmd;
+ const struct i2400m_l3l4_hdr *ack;
+ size_t ack_len;
+ char strerr[32];
+
+ result = -ENOMEM;
+ cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+ if (cmd == NULL)
+ goto error_alloc;
+ cmd->type = cpu_to_le16(I2400M_MT_GET_STATE);
+ cmd->length = 0;
+ cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
+
+ ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+ if (IS_ERR(ack_skb)) {
+ dev_err(dev, "Failed to issue 'get state' command: %ld\n",
+ PTR_ERR(ack_skb));
+ result = PTR_ERR(ack_skb);
+ goto error_msg_to_dev;
+ }
+ ack = wimax_msg_data_len(ack_skb, &ack_len);
+ result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
+ if (result < 0) {
+ dev_err(dev, "'get state' (0x%04x) command failed: "
+ "%d - %s\n", I2400M_MT_GET_STATE, result, strerr);
+ goto error_cmd_failed;
+ }
+ i2400m_report_state_hook(i2400m, ack, ack_len - sizeof(*ack),
+ "GET STATE");
+ result = 0;
+ kfree_skb(ack_skb);
+error_cmd_failed:
+error_msg_to_dev:
+ kfree(cmd);
+error_alloc:
+ return result;
+}
+
+/**
+ * Set basic configuration settings
+ *
+ * @i2400m: device descriptor
+ * @args: array of pointers to the TLV headers to send for
+ * configuration (each followed by its payload).
+ * TLV headers and payloads must be properly initialized, with the
+ * right endianess (LE).
+ * @arg_size: number of pointers in the @args array
+ */
+static int i2400m_set_init_config(struct i2400m *i2400m,
+ const struct i2400m_tlv_hdr **arg,
+ size_t args)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *ack_skb;
+ struct i2400m_l3l4_hdr *cmd;
+ char strerr[32];
+ unsigned argc, argsize, tlv_size;
+ const struct i2400m_tlv_hdr *tlv_hdr;
+ void *buf, *itr;
+
+ d_fnstart(3, dev, "(i2400m %p arg %p args %zu)\n", i2400m, arg, args);
+ result = 0;
+ if (args == 0)
+ goto none;
+ /* Compute the size of all the TLVs, so we can alloc a
+ * contiguous command block to copy them. */
+ argsize = 0;
+ for (argc = 0; argc < args; argc++) {
+ tlv_hdr = arg[argc];
+ argsize += sizeof(*tlv_hdr) + le16_to_cpu(tlv_hdr->length);
+ }
+ WARN_ON(argc >= 9); /* As per hw spec */
+
+ /* Alloc the space for the command and TLVs*/
+ result = -ENOMEM;
+ buf = kzalloc(sizeof(*cmd) + argsize, GFP_KERNEL);
+ if (buf == NULL)
+ goto error_alloc;
+ cmd = buf;
+ cmd->type = cpu_to_le16(I2400M_MT_SET_INIT_CONFIG);
+ cmd->length = cpu_to_le16(argsize);
+ cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
+
+ /* Copy the TLVs */
+ itr = buf + sizeof(*cmd);
+ for (argc = 0; argc < args; argc++) {
+ tlv_hdr = arg[argc];
+ tlv_size = sizeof(*tlv_hdr) + le16_to_cpu(tlv_hdr->length);
+ memcpy(itr, tlv_hdr, tlv_size);
+ itr += tlv_size;
+ }
+
+ /* Send the message! */
+ ack_skb = i2400m_msg_to_dev(i2400m, buf, sizeof(*cmd) + argsize);
+ result = PTR_ERR(ack_skb);
+ if (IS_ERR(ack_skb)) {
+ dev_err(dev, "Failed to issue 'init config' command: %d\n",
+ result);
+
+ goto error_msg_to_dev;
+ }
+ result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
+ strerr, sizeof(strerr));
+ if (result < 0)
+ dev_err(dev, "'init config' (0x%04x) command failed: %d - %s\n",
+ I2400M_MT_SET_INIT_CONFIG, result, strerr);
+ kfree_skb(ack_skb);
+error_msg_to_dev:
+ kfree(buf);
+error_alloc:
+none:
+ d_fnend(3, dev, "(i2400m %p arg %p args %zu) = %d\n",
+ i2400m, arg, args, result);
+ return result;
+
+}
+
+/**
+ * i2400m_set_idle_timeout - Set the device's idle mode timeout
+ *
+ * @i2400m: i2400m device descriptor
+ *
+ * @msecs: milliseconds for the timeout to enter idle mode. Between
+ * 100 to 300000 (5m); 0 to disable. In increments of 100.
+ *
+ * After this @msecs of the link being idle (no data being sent or
+ * received), the device will negotiate with the basestation entering
+ * idle mode for saving power. The connection is maintained, but
+ * getting out of it (done in tx.c) will require some negotiation,
+ * possible crypto re-handshake and a possible DHCP re-lease.
+ *
+ * Only available if fw_version >= 0x00090002.
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ */
+int i2400m_set_idle_timeout(struct i2400m *i2400m, unsigned msecs)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *ack_skb;
+ struct {
+ struct i2400m_l3l4_hdr hdr;
+ struct i2400m_tlv_config_idle_timeout cit;
+ } *cmd;
+ const struct i2400m_l3l4_hdr *ack;
+ size_t ack_len;
+ char strerr[32];
+
+ result = -ENOSYS;
+ if (i2400m_le_v1_3(i2400m))
+ goto error_alloc;
+ result = -ENOMEM;
+ cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+ if (cmd == NULL)
+ goto error_alloc;
+ cmd->hdr.type = cpu_to_le16(I2400M_MT_GET_STATE);
+ cmd->hdr.length = cpu_to_le16(sizeof(*cmd) - sizeof(cmd->hdr));
+ cmd->hdr.version = cpu_to_le16(I2400M_L3L4_VERSION);
+
+ cmd->cit.hdr.type =
+ cpu_to_le16(I2400M_TLV_CONFIG_IDLE_TIMEOUT);
+ cmd->cit.hdr.length = cpu_to_le16(sizeof(cmd->cit.timeout));
+ cmd->cit.timeout = cpu_to_le32(msecs);
+
+ ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+ if (IS_ERR(ack_skb)) {
+ dev_err(dev, "Failed to issue 'set idle timeout' command: "
+ "%ld\n", PTR_ERR(ack_skb));
+ result = PTR_ERR(ack_skb);
+ goto error_msg_to_dev;
+ }
+ ack = wimax_msg_data_len(ack_skb, &ack_len);
+ result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
+ if (result < 0) {
+ dev_err(dev, "'set idle timeout' (0x%04x) command failed: "
+ "%d - %s\n", I2400M_MT_GET_STATE, result, strerr);
+ goto error_cmd_failed;
+ }
+ result = 0;
+ kfree_skb(ack_skb);
+error_cmd_failed:
+error_msg_to_dev:
+ kfree(cmd);
+error_alloc:
+ return result;
+}
+
+
+/**
+ * i2400m_dev_initialize - Initialize the device once communications are ready
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * Configures the device to work the way we like it.
+ *
+ * At the point of this call, the device is registered with the WiMAX
+ * and netdev stacks, firmware is uploaded and we can talk to the
+ * device normally.
+ */
+int i2400m_dev_initialize(struct i2400m *i2400m)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400m_tlv_config_idle_parameters idle_params;
+ struct i2400m_tlv_config_idle_timeout idle_timeout;
+ struct i2400m_tlv_config_d2h_data_format df;
+ struct i2400m_tlv_config_dl_host_reorder dlhr;
+ const struct i2400m_tlv_hdr *args[9];
+ unsigned argc = 0;
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+ if (i2400m_passive_mode)
+ goto out_passive;
+ /* Disable idle mode? (enabled by default) */
+ if (i2400m_idle_mode_disabled) {
+ if (i2400m_le_v1_3(i2400m)) {
+ idle_params.hdr.type =
+ cpu_to_le16(I2400M_TLV_CONFIG_IDLE_PARAMETERS);
+ idle_params.hdr.length = cpu_to_le16(
+ sizeof(idle_params) - sizeof(idle_params.hdr));
+ idle_params.idle_timeout = 0;
+ idle_params.idle_paging_interval = 0;
+ args[argc++] = &idle_params.hdr;
+ } else {
+ idle_timeout.hdr.type =
+ cpu_to_le16(I2400M_TLV_CONFIG_IDLE_TIMEOUT);
+ idle_timeout.hdr.length = cpu_to_le16(
+ sizeof(idle_timeout) - sizeof(idle_timeout.hdr));
+ idle_timeout.timeout = 0;
+ args[argc++] = &idle_timeout.hdr;
+ }
+ }
+ if (i2400m_ge_v1_4(i2400m)) {
+ /* Enable extended RX data format? */
+ df.hdr.type =
+ cpu_to_le16(I2400M_TLV_CONFIG_D2H_DATA_FORMAT);
+ df.hdr.length = cpu_to_le16(
+ sizeof(df) - sizeof(df.hdr));
+ df.format = 1;
+ args[argc++] = &df.hdr;
+
+ /* Enable RX data reordering?
+ * (switch flipped in rx.c:i2400m_rx_setup() after fw upload) */
+ if (i2400m->rx_reorder) {
+ dlhr.hdr.type =
+ cpu_to_le16(I2400M_TLV_CONFIG_DL_HOST_REORDER);
+ dlhr.hdr.length = cpu_to_le16(
+ sizeof(dlhr) - sizeof(dlhr.hdr));
+ dlhr.reorder = 1;
+ args[argc++] = &dlhr.hdr;
+ }
+ }
+ result = i2400m_set_init_config(i2400m, args, argc);
+ if (result < 0)
+ goto error;
+out_passive:
+ /*
+ * Update state: Here it just calls a get state; parsing the
+ * result (System State TLV and RF Status TLV [done in the rx
+ * path hooks]) will set the hardware and software RF-Kill
+ * status.
+ */
+ result = i2400m_cmd_get_state(i2400m);
+error:
+ if (result < 0)
+ dev_err(dev, "failed to initialize the device: %d\n", result);
+ d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+ return result;
+}
+
+
+/**
+ * i2400m_dev_shutdown - Shutdown a running device
+ *
+ * @i2400m: device descriptor
+ *
+ * Release resources acquired during the running of the device; in
+ * theory, should also tell the device to go to sleep, switch off the
+ * radio, all that, but at this point, in most cases (driver
+ * disconnection, reset handling) we can't even talk to the device.
+ */
+void i2400m_dev_shutdown(struct i2400m *i2400m)
+{
+ struct device *dev = i2400m_dev(i2400m);
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+ d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Debug levels control file for the i2400m module
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+#ifndef __debug_levels__h__
+#define __debug_levels__h__
+
+/* Maximum compile and run time debug level for all submodules */
+#define D_MODULENAME i2400m
+#define D_MASTER CONFIG_WIMAX_I2400M_DEBUG_LEVEL
+
+#include "../linux-wimax-debug.h"
+
+/* List of all the enabled modules */
+enum d_module {
+ D_SUBMODULE_DECLARE(control),
+ D_SUBMODULE_DECLARE(driver),
+ D_SUBMODULE_DECLARE(debugfs),
+ D_SUBMODULE_DECLARE(fw),
+ D_SUBMODULE_DECLARE(netdev),
+ D_SUBMODULE_DECLARE(rfkill),
+ D_SUBMODULE_DECLARE(rx),
+ D_SUBMODULE_DECLARE(sysfs),
+ D_SUBMODULE_DECLARE(tx),
+};
+
+
+#endif /* #ifndef __debug_levels__h__ */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Debugfs interfaces to manipulate driver and device information
+ *
+ * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/spinlock.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include "i2400m.h"
+
+
+#define D_SUBMODULE debugfs
+#include "debug-levels.h"
+
+static
+int debugfs_netdev_queue_stopped_get(void *data, u64 *val)
+{
+ struct i2400m *i2400m = data;
+ *val = netif_queue_stopped(i2400m->wimax_dev.net_dev);
+ return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_netdev_queue_stopped,
+ debugfs_netdev_queue_stopped_get,
+ NULL, "%llu\n");
+
+/*
+ * We don't allow partial reads of this file, as then the reader would
+ * get weirdly confused data as it is updated.
+ *
+ * So or you read it all or nothing; if you try to read with an offset
+ * != 0, we consider you are done reading.
+ */
+static
+ssize_t i2400m_rx_stats_read(struct file *filp, char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct i2400m *i2400m = filp->private_data;
+ char buf[128];
+ unsigned long flags;
+
+ if (*ppos != 0)
+ return 0;
+ if (count < sizeof(buf))
+ return -ENOSPC;
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ snprintf(buf, sizeof(buf), "%u %u %u %u %u %u %u\n",
+ i2400m->rx_pl_num, i2400m->rx_pl_min,
+ i2400m->rx_pl_max, i2400m->rx_num,
+ i2400m->rx_size_acc,
+ i2400m->rx_size_min, i2400m->rx_size_max);
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
+}
+
+
+/* Any write clears the stats */
+static
+ssize_t i2400m_rx_stats_write(struct file *filp, const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct i2400m *i2400m = filp->private_data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ i2400m->rx_pl_num = 0;
+ i2400m->rx_pl_max = 0;
+ i2400m->rx_pl_min = UINT_MAX;
+ i2400m->rx_num = 0;
+ i2400m->rx_size_acc = 0;
+ i2400m->rx_size_min = UINT_MAX;
+ i2400m->rx_size_max = 0;
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ return count;
+}
+
+static
+const struct file_operations i2400m_rx_stats_fops = {
+ .owner = THIS_MODULE,
+ .open = simple_open,
+ .read = i2400m_rx_stats_read,
+ .write = i2400m_rx_stats_write,
+ .llseek = default_llseek,
+};
+
+
+/* See i2400m_rx_stats_read() */
+static
+ssize_t i2400m_tx_stats_read(struct file *filp, char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct i2400m *i2400m = filp->private_data;
+ char buf[128];
+ unsigned long flags;
+
+ if (*ppos != 0)
+ return 0;
+ if (count < sizeof(buf))
+ return -ENOSPC;
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ snprintf(buf, sizeof(buf), "%u %u %u %u %u %u %u\n",
+ i2400m->tx_pl_num, i2400m->tx_pl_min,
+ i2400m->tx_pl_max, i2400m->tx_num,
+ i2400m->tx_size_acc,
+ i2400m->tx_size_min, i2400m->tx_size_max);
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+ return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
+}
+
+/* Any write clears the stats */
+static
+ssize_t i2400m_tx_stats_write(struct file *filp, const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct i2400m *i2400m = filp->private_data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ i2400m->tx_pl_num = 0;
+ i2400m->tx_pl_max = 0;
+ i2400m->tx_pl_min = UINT_MAX;
+ i2400m->tx_num = 0;
+ i2400m->tx_size_acc = 0;
+ i2400m->tx_size_min = UINT_MAX;
+ i2400m->tx_size_max = 0;
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+ return count;
+}
+
+static
+const struct file_operations i2400m_tx_stats_fops = {
+ .owner = THIS_MODULE,
+ .open = simple_open,
+ .read = i2400m_tx_stats_read,
+ .write = i2400m_tx_stats_write,
+ .llseek = default_llseek,
+};
+
+
+/* Write 1 to ask the device to go into suspend */
+static
+int debugfs_i2400m_suspend_set(void *data, u64 val)
+{
+ int result;
+ struct i2400m *i2400m = data;
+ result = i2400m_cmd_enter_powersave(i2400m);
+ if (result >= 0)
+ result = 0;
+ return result;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_i2400m_suspend,
+ NULL, debugfs_i2400m_suspend_set,
+ "%llu\n");
+
+/*
+ * Reset the device
+ *
+ * Write 0 to ask the device to soft reset, 1 to cold reset, 2 to bus
+ * reset (as defined by enum i2400m_reset_type).
+ */
+static
+int debugfs_i2400m_reset_set(void *data, u64 val)
+{
+ int result;
+ struct i2400m *i2400m = data;
+ enum i2400m_reset_type rt = val;
+ switch(rt) {
+ case I2400M_RT_WARM:
+ case I2400M_RT_COLD:
+ case I2400M_RT_BUS:
+ result = i2400m_reset(i2400m, rt);
+ if (result >= 0)
+ result = 0;
+ break;
+ default:
+ result = -EINVAL;
+ }
+ return result;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_i2400m_reset,
+ NULL, debugfs_i2400m_reset_set,
+ "%llu\n");
+
+void i2400m_debugfs_add(struct i2400m *i2400m)
+{
+ struct dentry *dentry = i2400m->wimax_dev.debugfs_dentry;
+
+ dentry = debugfs_create_dir("i2400m", dentry);
+ i2400m->debugfs_dentry = dentry;
+
+ d_level_register_debugfs("dl_", control, dentry);
+ d_level_register_debugfs("dl_", driver, dentry);
+ d_level_register_debugfs("dl_", debugfs, dentry);
+ d_level_register_debugfs("dl_", fw, dentry);
+ d_level_register_debugfs("dl_", netdev, dentry);
+ d_level_register_debugfs("dl_", rfkill, dentry);
+ d_level_register_debugfs("dl_", rx, dentry);
+ d_level_register_debugfs("dl_", tx, dentry);
+
+ debugfs_create_size_t("tx_in", 0400, dentry, &i2400m->tx_in);
+ debugfs_create_size_t("tx_out", 0400, dentry, &i2400m->tx_out);
+ debugfs_create_u32("state", 0600, dentry, &i2400m->state);
+
+ /*
+ * Trace received messages from user space
+ *
+ * In order to tap the bidirectional message stream in the
+ * 'msg' pipe, user space can read from the 'msg' pipe;
+ * however, due to limitations in libnl, we can't know what
+ * the different applications are sending down to the kernel.
+ *
+ * So we have this hack where the driver will echo any message
+ * received on the msg pipe from user space [through a call to
+ * wimax_dev->op_msg_from_user() into
+ * i2400m_op_msg_from_user()] into the 'trace' pipe that this
+ * driver creates.
+ *
+ * So then, reading from both the 'trace' and 'msg' pipes in
+ * user space will provide a full dump of the traffic.
+ *
+ * Write 1 to activate, 0 to clear.
+ *
+ * It is not really very atomic, but it is also not too
+ * critical.
+ */
+ debugfs_create_u8("trace_msg_from_user", 0600, dentry,
+ &i2400m->trace_msg_from_user);
+
+ debugfs_create_file("netdev_queue_stopped", 0400, dentry, i2400m,
+ &fops_netdev_queue_stopped);
+
+ debugfs_create_file("rx_stats", 0600, dentry, i2400m,
+ &i2400m_rx_stats_fops);
+
+ debugfs_create_file("tx_stats", 0600, dentry, i2400m,
+ &i2400m_tx_stats_fops);
+
+ debugfs_create_file("suspend", 0200, dentry, i2400m,
+ &fops_i2400m_suspend);
+
+ debugfs_create_file("reset", 0200, dentry, i2400m, &fops_i2400m_reset);
+}
+
+void i2400m_debugfs_rm(struct i2400m *i2400m)
+{
+ debugfs_remove_recursive(i2400m->debugfs_dentry);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Generic probe/disconnect, reset and message passing
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * See i2400m.h for driver documentation. This contains helpers for
+ * the driver model glue [_setup()/_release()], handling device resets
+ * [_dev_reset_handle()], and the backends for the WiMAX stack ops
+ * reset [_op_reset()] and message from user [_op_msg_from_user()].
+ *
+ * ROADMAP:
+ *
+ * i2400m_op_msg_from_user()
+ * i2400m_msg_to_dev()
+ * wimax_msg_to_user_send()
+ *
+ * i2400m_op_reset()
+ * i240m->bus_reset()
+ *
+ * i2400m_dev_reset_handle()
+ * __i2400m_dev_reset_handle()
+ * __i2400m_dev_stop()
+ * __i2400m_dev_start()
+ *
+ * i2400m_setup()
+ * i2400m->bus_setup()
+ * i2400m_bootrom_init()
+ * register_netdev()
+ * wimax_dev_add()
+ * i2400m_dev_start()
+ * __i2400m_dev_start()
+ * i2400m_dev_bootstrap()
+ * i2400m_tx_setup()
+ * i2400m->bus_dev_start()
+ * i2400m_firmware_check()
+ * i2400m_check_mac_addr()
+ *
+ * i2400m_release()
+ * i2400m_dev_stop()
+ * __i2400m_dev_stop()
+ * i2400m_dev_shutdown()
+ * i2400m->bus_dev_stop()
+ * i2400m_tx_release()
+ * i2400m->bus_release()
+ * wimax_dev_rm()
+ * unregister_netdev()
+ */
+#include "i2400m.h"
+#include <linux/etherdevice.h>
+#include "linux-wimax-i2400m.h"
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/suspend.h>
+#include <linux/slab.h>
+
+#define D_SUBMODULE driver
+#include "debug-levels.h"
+
+
+static char i2400m_debug_params[128];
+module_param_string(debug, i2400m_debug_params, sizeof(i2400m_debug_params),
+ 0644);
+MODULE_PARM_DESC(debug,
+ "String of space-separated NAME:VALUE pairs, where NAMEs "
+ "are the different debug submodules and VALUE are the "
+ "initial debug value to set.");
+
+static char i2400m_barkers_params[128];
+module_param_string(barkers, i2400m_barkers_params,
+ sizeof(i2400m_barkers_params), 0644);
+MODULE_PARM_DESC(barkers,
+ "String of comma-separated 32-bit values; each is "
+ "recognized as the value the device sends as a reboot "
+ "signal; values are appended to a list--setting one value "
+ "as zero cleans the existing list and starts a new one.");
+
+/*
+ * WiMAX stack operation: relay a message from user space
+ *
+ * @wimax_dev: device descriptor
+ * @pipe_name: named pipe the message is for
+ * @msg_buf: pointer to the message bytes
+ * @msg_len: length of the buffer
+ * @genl_info: passed by the generic netlink layer
+ *
+ * The WiMAX stack will call this function when a message was received
+ * from user space.
+ *
+ * For the i2400m, this is an L3L4 message, as specified in
+ * include/linux/wimax/i2400m.h, and thus prefixed with a 'struct
+ * i2400m_l3l4_hdr'. Driver (and device) expect the messages to be
+ * coded in Little Endian.
+ *
+ * This function just verifies that the header declaration and the
+ * payload are consistent and then deals with it, either forwarding it
+ * to the device or procesing it locally.
+ *
+ * In the i2400m, messages are basically commands that will carry an
+ * ack, so we use i2400m_msg_to_dev() and then deliver the ack back to
+ * user space. The rx.c code might intercept the response and use it
+ * to update the driver's state, but then it will pass it on so it can
+ * be relayed back to user space.
+ *
+ * Note that asynchronous events from the device are processed and
+ * sent to user space in rx.c.
+ */
+static
+int i2400m_op_msg_from_user(struct wimax_dev *wimax_dev,
+ const char *pipe_name,
+ const void *msg_buf, size_t msg_len,
+ const struct genl_info *genl_info)
+{
+ int result;
+ struct i2400m *i2400m = wimax_dev_to_i2400m(wimax_dev);
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *ack_skb;
+
+ d_fnstart(4, dev, "(wimax_dev %p [i2400m %p] msg_buf %p "
+ "msg_len %zu genl_info %p)\n", wimax_dev, i2400m,
+ msg_buf, msg_len, genl_info);
+ ack_skb = i2400m_msg_to_dev(i2400m, msg_buf, msg_len);
+ result = PTR_ERR(ack_skb);
+ if (IS_ERR(ack_skb))
+ goto error_msg_to_dev;
+ result = wimax_msg_send(&i2400m->wimax_dev, ack_skb);
+error_msg_to_dev:
+ d_fnend(4, dev, "(wimax_dev %p [i2400m %p] msg_buf %p msg_len %zu "
+ "genl_info %p) = %d\n", wimax_dev, i2400m, msg_buf, msg_len,
+ genl_info, result);
+ return result;
+}
+
+
+/*
+ * Context to wait for a reset to finalize
+ */
+struct i2400m_reset_ctx {
+ struct completion completion;
+ int result;
+};
+
+
+/*
+ * WiMAX stack operation: reset a device
+ *
+ * @wimax_dev: device descriptor
+ *
+ * See the documentation for wimax_reset() and wimax_dev->op_reset for
+ * the requirements of this function. The WiMAX stack guarantees
+ * serialization on calls to this function.
+ *
+ * Do a warm reset on the device; if it fails, resort to a cold reset
+ * and return -ENODEV. On successful warm reset, we need to block
+ * until it is complete.
+ *
+ * The bus-driver implementation of reset takes care of falling back
+ * to cold reset if warm fails.
+ */
+static
+int i2400m_op_reset(struct wimax_dev *wimax_dev)
+{
+ int result;
+ struct i2400m *i2400m = wimax_dev_to_i2400m(wimax_dev);
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400m_reset_ctx ctx = {
+ .completion = COMPLETION_INITIALIZER_ONSTACK(ctx.completion),
+ .result = 0,
+ };
+
+ d_fnstart(4, dev, "(wimax_dev %p)\n", wimax_dev);
+ mutex_lock(&i2400m->init_mutex);
+ i2400m->reset_ctx = &ctx;
+ mutex_unlock(&i2400m->init_mutex);
+ result = i2400m_reset(i2400m, I2400M_RT_WARM);
+ if (result < 0)
+ goto out;
+ result = wait_for_completion_timeout(&ctx.completion, 4*HZ);
+ if (result == 0)
+ result = -ETIMEDOUT;
+ else if (result > 0)
+ result = ctx.result;
+ /* if result < 0, pass it on */
+ mutex_lock(&i2400m->init_mutex);
+ i2400m->reset_ctx = NULL;
+ mutex_unlock(&i2400m->init_mutex);
+out:
+ d_fnend(4, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
+ return result;
+}
+
+
+/*
+ * Check the MAC address we got from boot mode is ok
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ */
+static
+int i2400m_check_mac_addr(struct i2400m *i2400m)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *skb;
+ const struct i2400m_tlv_detailed_device_info *ddi;
+ struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+ skb = i2400m_get_device_info(i2400m);
+ if (IS_ERR(skb)) {
+ result = PTR_ERR(skb);
+ dev_err(dev, "Cannot verify MAC address, error reading: %d\n",
+ result);
+ goto error;
+ }
+ /* Extract MAC address */
+ ddi = (void *) skb->data;
+ BUILD_BUG_ON(ETH_ALEN != sizeof(ddi->mac_address));
+ d_printf(2, dev, "GET DEVICE INFO: mac addr %pM\n",
+ ddi->mac_address);
+ if (!memcmp(net_dev->perm_addr, ddi->mac_address,
+ sizeof(ddi->mac_address)))
+ goto ok;
+ dev_warn(dev, "warning: device reports a different MAC address "
+ "to that of boot mode's\n");
+ dev_warn(dev, "device reports %pM\n", ddi->mac_address);
+ dev_warn(dev, "boot mode reported %pM\n", net_dev->perm_addr);
+ if (is_zero_ether_addr(ddi->mac_address))
+ dev_err(dev, "device reports an invalid MAC address, "
+ "not updating\n");
+ else {
+ dev_warn(dev, "updating MAC address\n");
+ net_dev->addr_len = ETH_ALEN;
+ memcpy(net_dev->perm_addr, ddi->mac_address, ETH_ALEN);
+ memcpy(net_dev->dev_addr, ddi->mac_address, ETH_ALEN);
+ }
+ok:
+ result = 0;
+ kfree_skb(skb);
+error:
+ d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+ return result;
+}
+
+
+/**
+ * __i2400m_dev_start - Bring up driver communication with the device
+ *
+ * @i2400m: device descriptor
+ * @flags: boot mode flags
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * Uploads firmware and brings up all the resources needed to be able
+ * to communicate with the device.
+ *
+ * The workqueue has to be setup early, at least before RX handling
+ * (it's only real user for now) so it can process reports as they
+ * arrive. We also want to destroy it if we retry, to make sure it is
+ * flushed...easier like this.
+ *
+ * TX needs to be setup before the bus-specific code (otherwise on
+ * shutdown, the bus-tx code could try to access it).
+ */
+static
+int __i2400m_dev_start(struct i2400m *i2400m, enum i2400m_bri flags)
+{
+ int result;
+ struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+ struct net_device *net_dev = wimax_dev->net_dev;
+ struct device *dev = i2400m_dev(i2400m);
+ int times = i2400m->bus_bm_retries;
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+retry:
+ result = i2400m_dev_bootstrap(i2400m, flags);
+ if (result < 0) {
+ dev_err(dev, "cannot bootstrap device: %d\n", result);
+ goto error_bootstrap;
+ }
+ result = i2400m_tx_setup(i2400m);
+ if (result < 0)
+ goto error_tx_setup;
+ result = i2400m_rx_setup(i2400m);
+ if (result < 0)
+ goto error_rx_setup;
+ i2400m->work_queue = create_singlethread_workqueue(wimax_dev->name);
+ if (i2400m->work_queue == NULL) {
+ result = -ENOMEM;
+ dev_err(dev, "cannot create workqueue\n");
+ goto error_create_workqueue;
+ }
+ if (i2400m->bus_dev_start) {
+ result = i2400m->bus_dev_start(i2400m);
+ if (result < 0)
+ goto error_bus_dev_start;
+ }
+ i2400m->ready = 1;
+ wmb(); /* see i2400m->ready's documentation */
+ /* process pending reports from the device */
+ queue_work(i2400m->work_queue, &i2400m->rx_report_ws);
+ result = i2400m_firmware_check(i2400m); /* fw versions ok? */
+ if (result < 0)
+ goto error_fw_check;
+ /* At this point is ok to send commands to the device */
+ result = i2400m_check_mac_addr(i2400m);
+ if (result < 0)
+ goto error_check_mac_addr;
+ result = i2400m_dev_initialize(i2400m);
+ if (result < 0)
+ goto error_dev_initialize;
+
+ /* We don't want any additional unwanted error recovery triggered
+ * from any other context so if anything went wrong before we come
+ * here, let's keep i2400m->error_recovery untouched and leave it to
+ * dev_reset_handle(). See dev_reset_handle(). */
+
+ atomic_dec(&i2400m->error_recovery);
+ /* Every thing works so far, ok, now we are ready to
+ * take error recovery if it's required. */
+
+ /* At this point, reports will come for the device and set it
+ * to the right state if it is different than UNINITIALIZED */
+ d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
+ net_dev, i2400m, result);
+ return result;
+
+error_dev_initialize:
+error_check_mac_addr:
+error_fw_check:
+ i2400m->ready = 0;
+ wmb(); /* see i2400m->ready's documentation */
+ flush_workqueue(i2400m->work_queue);
+ if (i2400m->bus_dev_stop)
+ i2400m->bus_dev_stop(i2400m);
+error_bus_dev_start:
+ destroy_workqueue(i2400m->work_queue);
+error_create_workqueue:
+ i2400m_rx_release(i2400m);
+error_rx_setup:
+ i2400m_tx_release(i2400m);
+error_tx_setup:
+error_bootstrap:
+ if (result == -EL3RST && times-- > 0) {
+ flags = I2400M_BRI_SOFT|I2400M_BRI_MAC_REINIT;
+ goto retry;
+ }
+ d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
+ net_dev, i2400m, result);
+ return result;
+}
+
+
+static
+int i2400m_dev_start(struct i2400m *i2400m, enum i2400m_bri bm_flags)
+{
+ int result = 0;
+ mutex_lock(&i2400m->init_mutex); /* Well, start the device */
+ if (i2400m->updown == 0) {
+ result = __i2400m_dev_start(i2400m, bm_flags);
+ if (result >= 0) {
+ i2400m->updown = 1;
+ i2400m->alive = 1;
+ wmb();/* see i2400m->updown and i2400m->alive's doc */
+ }
+ }
+ mutex_unlock(&i2400m->init_mutex);
+ return result;
+}
+
+
+/**
+ * i2400m_dev_stop - Tear down driver communication with the device
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * Releases all the resources allocated to communicate with the
+ * device. Note we cannot destroy the workqueue earlier as until RX is
+ * fully destroyed, it could still try to schedule jobs.
+ */
+static
+void __i2400m_dev_stop(struct i2400m *i2400m)
+{
+ struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+ struct device *dev = i2400m_dev(i2400m);
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+ wimax_state_change(wimax_dev, __WIMAX_ST_QUIESCING);
+ i2400m_msg_to_dev_cancel_wait(i2400m, -EL3RST);
+ complete(&i2400m->msg_completion);
+ i2400m_net_wake_stop(i2400m);
+ i2400m_dev_shutdown(i2400m);
+ /*
+ * Make sure no report hooks are running *before* we stop the
+ * communication infrastructure with the device.
+ */
+ i2400m->ready = 0; /* nobody can queue work anymore */
+ wmb(); /* see i2400m->ready's documentation */
+ flush_workqueue(i2400m->work_queue);
+
+ if (i2400m->bus_dev_stop)
+ i2400m->bus_dev_stop(i2400m);
+ destroy_workqueue(i2400m->work_queue);
+ i2400m_rx_release(i2400m);
+ i2400m_tx_release(i2400m);
+ wimax_state_change(wimax_dev, WIMAX_ST_DOWN);
+ d_fnend(3, dev, "(i2400m %p) = 0\n", i2400m);
+}
+
+
+/*
+ * Watch out -- we only need to stop if there is a need for it. The
+ * device could have reset itself and failed to come up again (see
+ * _i2400m_dev_reset_handle()).
+ */
+static
+void i2400m_dev_stop(struct i2400m *i2400m)
+{
+ mutex_lock(&i2400m->init_mutex);
+ if (i2400m->updown) {
+ __i2400m_dev_stop(i2400m);
+ i2400m->updown = 0;
+ i2400m->alive = 0;
+ wmb(); /* see i2400m->updown and i2400m->alive's doc */
+ }
+ mutex_unlock(&i2400m->init_mutex);
+}
+
+
+/*
+ * Listen to PM events to cache the firmware before suspend/hibernation
+ *
+ * When the device comes out of suspend, it might go into reset and
+ * firmware has to be uploaded again. At resume, most of the times, we
+ * can't load firmware images from disk, so we need to cache it.
+ *
+ * i2400m_fw_cache() will allocate a kobject and attach the firmware
+ * to it; that way we don't have to worry too much about the fw loader
+ * hitting a race condition.
+ *
+ * Note: modus operandi stolen from the Orinoco driver; thx.
+ */
+static
+int i2400m_pm_notifier(struct notifier_block *notifier,
+ unsigned long pm_event,
+ void *unused)
+{
+ struct i2400m *i2400m =
+ container_of(notifier, struct i2400m, pm_notifier);
+ struct device *dev = i2400m_dev(i2400m);
+
+ d_fnstart(3, dev, "(i2400m %p pm_event %lx)\n", i2400m, pm_event);
+ switch (pm_event) {
+ case PM_HIBERNATION_PREPARE:
+ case PM_SUSPEND_PREPARE:
+ i2400m_fw_cache(i2400m);
+ break;
+ case PM_POST_RESTORE:
+ /* Restore from hibernation failed. We need to clean
+ * up in exactly the same way, so fall through. */
+ case PM_POST_HIBERNATION:
+ case PM_POST_SUSPEND:
+ i2400m_fw_uncache(i2400m);
+ break;
+
+ case PM_RESTORE_PREPARE:
+ default:
+ break;
+ }
+ d_fnend(3, dev, "(i2400m %p pm_event %lx) = void\n", i2400m, pm_event);
+ return NOTIFY_DONE;
+}
+
+
+/*
+ * pre-reset is called before a device is going on reset
+ *
+ * This has to be followed by a call to i2400m_post_reset(), otherwise
+ * bad things might happen.
+ */
+int i2400m_pre_reset(struct i2400m *i2400m)
+{
+ struct device *dev = i2400m_dev(i2400m);
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+ d_printf(1, dev, "pre-reset shut down\n");
+
+ mutex_lock(&i2400m->init_mutex);
+ if (i2400m->updown) {
+ netif_tx_disable(i2400m->wimax_dev.net_dev);
+ __i2400m_dev_stop(i2400m);
+ /* down't set updown to zero -- this way
+ * post_reset can restore properly */
+ }
+ mutex_unlock(&i2400m->init_mutex);
+ if (i2400m->bus_release)
+ i2400m->bus_release(i2400m);
+ d_fnend(3, dev, "(i2400m %p) = 0\n", i2400m);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(i2400m_pre_reset);
+
+
+/*
+ * Restore device state after a reset
+ *
+ * Do the work needed after a device reset to bring it up to the same
+ * state as it was before the reset.
+ *
+ * NOTE: this requires i2400m->init_mutex taken
+ */
+int i2400m_post_reset(struct i2400m *i2400m)
+{
+ int result = 0;
+ struct device *dev = i2400m_dev(i2400m);
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+ d_printf(1, dev, "post-reset start\n");
+ if (i2400m->bus_setup) {
+ result = i2400m->bus_setup(i2400m);
+ if (result < 0) {
+ dev_err(dev, "bus-specific setup failed: %d\n",
+ result);
+ goto error_bus_setup;
+ }
+ }
+ mutex_lock(&i2400m->init_mutex);
+ if (i2400m->updown) {
+ result = __i2400m_dev_start(
+ i2400m, I2400M_BRI_SOFT | I2400M_BRI_MAC_REINIT);
+ if (result < 0)
+ goto error_dev_start;
+ }
+ mutex_unlock(&i2400m->init_mutex);
+ d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+ return result;
+
+error_dev_start:
+ if (i2400m->bus_release)
+ i2400m->bus_release(i2400m);
+ /* even if the device was up, it could not be recovered, so we
+ * mark it as down. */
+ i2400m->updown = 0;
+ wmb(); /* see i2400m->updown's documentation */
+ mutex_unlock(&i2400m->init_mutex);
+error_bus_setup:
+ d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+ return result;
+}
+EXPORT_SYMBOL_GPL(i2400m_post_reset);
+
+
+/*
+ * The device has rebooted; fix up the device and the driver
+ *
+ * Tear down the driver communication with the device, reload the
+ * firmware and reinitialize the communication with the device.
+ *
+ * If someone calls a reset when the device's firmware is down, in
+ * theory we won't see it because we are not listening. However, just
+ * in case, leave the code to handle it.
+ *
+ * If there is a reset context, use it; this means someone is waiting
+ * for us to tell him when the reset operation is complete and the
+ * device is ready to rock again.
+ *
+ * NOTE: if we are in the process of bringing up or down the
+ * communication with the device [running i2400m_dev_start() or
+ * _stop()], don't do anything, let it fail and handle it.
+ *
+ * This function is ran always in a thread context
+ *
+ * This function gets passed, as payload to i2400m_work() a 'const
+ * char *' ptr with a "reason" why the reset happened (for messages).
+ */
+static
+void __i2400m_dev_reset_handle(struct work_struct *ws)
+{
+ struct i2400m *i2400m = container_of(ws, struct i2400m, reset_ws);
+ const char *reason = i2400m->reset_reason;
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400m_reset_ctx *ctx = i2400m->reset_ctx;
+ int result;
+
+ d_fnstart(3, dev, "(ws %p i2400m %p reason %s)\n", ws, i2400m, reason);
+
+ i2400m->boot_mode = 1;
+ wmb(); /* Make sure i2400m_msg_to_dev() sees boot_mode */
+
+ result = 0;
+ if (mutex_trylock(&i2400m->init_mutex) == 0) {
+ /* We are still in i2400m_dev_start() [let it fail] or
+ * i2400m_dev_stop() [we are shutting down anyway, so
+ * ignore it] or we are resetting somewhere else. */
+ dev_err(dev, "device rebooted somewhere else?\n");
+ i2400m_msg_to_dev_cancel_wait(i2400m, -EL3RST);
+ complete(&i2400m->msg_completion);
+ goto out;
+ }
+
+ dev_err(dev, "%s: reinitializing driver\n", reason);
+ rmb();
+ if (i2400m->updown) {
+ __i2400m_dev_stop(i2400m);
+ i2400m->updown = 0;
+ wmb(); /* see i2400m->updown's documentation */
+ }
+
+ if (i2400m->alive) {
+ result = __i2400m_dev_start(i2400m,
+ I2400M_BRI_SOFT | I2400M_BRI_MAC_REINIT);
+ if (result < 0) {
+ dev_err(dev, "%s: cannot start the device: %d\n",
+ reason, result);
+ result = -EUCLEAN;
+ if (atomic_read(&i2400m->bus_reset_retries)
+ >= I2400M_BUS_RESET_RETRIES) {
+ result = -ENODEV;
+ dev_err(dev, "tried too many times to "
+ "reset the device, giving up\n");
+ }
+ }
+ }
+
+ if (i2400m->reset_ctx) {
+ ctx->result = result;
+ complete(&ctx->completion);
+ }
+ mutex_unlock(&i2400m->init_mutex);
+ if (result == -EUCLEAN) {
+ /*
+ * We come here because the reset during operational mode
+ * wasn't successfully done and need to proceed to a bus
+ * reset. For the dev_reset_handle() to be able to handle
+ * the reset event later properly, we restore boot_mode back
+ * to the state before previous reset. ie: just like we are
+ * issuing the bus reset for the first time
+ */
+ i2400m->boot_mode = 0;
+ wmb();
+
+ atomic_inc(&i2400m->bus_reset_retries);
+ /* ops, need to clean up [w/ init_mutex not held] */
+ result = i2400m_reset(i2400m, I2400M_RT_BUS);
+ if (result >= 0)
+ result = -ENODEV;
+ } else {
+ rmb();
+ if (i2400m->alive) {
+ /* great, we expect the device state up and
+ * dev_start() actually brings the device state up */
+ i2400m->updown = 1;
+ wmb();
+ atomic_set(&i2400m->bus_reset_retries, 0);
+ }
+ }
+out:
+ d_fnend(3, dev, "(ws %p i2400m %p reason %s) = void\n",
+ ws, i2400m, reason);
+}
+
+
+/**
+ * i2400m_dev_reset_handle - Handle a device's reset in a thread context
+ *
+ * Schedule a device reset handling out on a thread context, so it
+ * is safe to call from atomic context. We can't use the i2400m's
+ * queue as we are going to destroy it and reinitialize it as part of
+ * the driver bringup/bringup process.
+ *
+ * See __i2400m_dev_reset_handle() for details; that takes care of
+ * reinitializing the driver to handle the reset, calling into the
+ * bus-specific functions ops as needed.
+ */
+int i2400m_dev_reset_handle(struct i2400m *i2400m, const char *reason)
+{
+ i2400m->reset_reason = reason;
+ return schedule_work(&i2400m->reset_ws);
+}
+EXPORT_SYMBOL_GPL(i2400m_dev_reset_handle);
+
+
+ /*
+ * The actual work of error recovery.
+ *
+ * The current implementation of error recovery is to trigger a bus reset.
+ */
+static
+void __i2400m_error_recovery(struct work_struct *ws)
+{
+ struct i2400m *i2400m = container_of(ws, struct i2400m, recovery_ws);
+
+ i2400m_reset(i2400m, I2400M_RT_BUS);
+}
+
+/*
+ * Schedule a work struct for error recovery.
+ *
+ * The intention of error recovery is to bring back the device to some
+ * known state whenever TX sees -110 (-ETIMEOUT) on copying the data to
+ * the device. The TX failure could mean a device bus stuck, so the current
+ * error recovery implementation is to trigger a bus reset to the device
+ * and hopefully it can bring back the device.
+ *
+ * The actual work of error recovery has to be in a thread context because
+ * it is kicked off in the TX thread (i2400ms->tx_workqueue) which is to be
+ * destroyed by the error recovery mechanism (currently a bus reset).
+ *
+ * Also, there may be already a queue of TX works that all hit
+ * the -ETIMEOUT error condition because the device is stuck already.
+ * Since bus reset is used as the error recovery mechanism and we don't
+ * want consecutive bus resets simply because the multiple TX works
+ * in the queue all hit the same device erratum, the flag "error_recovery"
+ * is introduced for preventing unwanted consecutive bus resets.
+ *
+ * Error recovery shall only be invoked again if previous one was completed.
+ * The flag error_recovery is set when error recovery mechanism is scheduled,
+ * and is checked when we need to schedule another error recovery. If it is
+ * in place already, then we shouldn't schedule another one.
+ */
+void i2400m_error_recovery(struct i2400m *i2400m)
+{
+ if (atomic_add_return(1, &i2400m->error_recovery) == 1)
+ schedule_work(&i2400m->recovery_ws);
+ else
+ atomic_dec(&i2400m->error_recovery);
+}
+EXPORT_SYMBOL_GPL(i2400m_error_recovery);
+
+/*
+ * Alloc the command and ack buffers for boot mode
+ *
+ * Get the buffers needed to deal with boot mode messages.
+ */
+static
+int i2400m_bm_buf_alloc(struct i2400m *i2400m)
+{
+ i2400m->bm_cmd_buf = kzalloc(I2400M_BM_CMD_BUF_SIZE, GFP_KERNEL);
+ if (i2400m->bm_cmd_buf == NULL)
+ goto error_bm_cmd_kzalloc;
+ i2400m->bm_ack_buf = kzalloc(I2400M_BM_ACK_BUF_SIZE, GFP_KERNEL);
+ if (i2400m->bm_ack_buf == NULL)
+ goto error_bm_ack_buf_kzalloc;
+ return 0;
+
+error_bm_ack_buf_kzalloc:
+ kfree(i2400m->bm_cmd_buf);
+error_bm_cmd_kzalloc:
+ return -ENOMEM;
+}
+
+
+/*
+ * Free boot mode command and ack buffers.
+ */
+static
+void i2400m_bm_buf_free(struct i2400m *i2400m)
+{
+ kfree(i2400m->bm_ack_buf);
+ kfree(i2400m->bm_cmd_buf);
+}
+
+
+/**
+ * i2400m_init - Initialize a 'struct i2400m' from all zeroes
+ *
+ * This is a bus-generic API call.
+ */
+void i2400m_init(struct i2400m *i2400m)
+{
+ wimax_dev_init(&i2400m->wimax_dev);
+
+ i2400m->boot_mode = 1;
+ i2400m->rx_reorder = 1;
+ init_waitqueue_head(&i2400m->state_wq);
+
+ spin_lock_init(&i2400m->tx_lock);
+ i2400m->tx_pl_min = UINT_MAX;
+ i2400m->tx_size_min = UINT_MAX;
+
+ spin_lock_init(&i2400m->rx_lock);
+ i2400m->rx_pl_min = UINT_MAX;
+ i2400m->rx_size_min = UINT_MAX;
+ INIT_LIST_HEAD(&i2400m->rx_reports);
+ INIT_WORK(&i2400m->rx_report_ws, i2400m_report_hook_work);
+
+ mutex_init(&i2400m->msg_mutex);
+ init_completion(&i2400m->msg_completion);
+
+ mutex_init(&i2400m->init_mutex);
+ /* wake_tx_ws is initialized in i2400m_tx_setup() */
+
+ INIT_WORK(&i2400m->reset_ws, __i2400m_dev_reset_handle);
+ INIT_WORK(&i2400m->recovery_ws, __i2400m_error_recovery);
+
+ atomic_set(&i2400m->bus_reset_retries, 0);
+
+ i2400m->alive = 0;
+
+ /* initialize error_recovery to 1 for denoting we
+ * are not yet ready to take any error recovery */
+ atomic_set(&i2400m->error_recovery, 1);
+}
+EXPORT_SYMBOL_GPL(i2400m_init);
+
+
+int i2400m_reset(struct i2400m *i2400m, enum i2400m_reset_type rt)
+{
+ struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+
+ /*
+ * Make sure we stop TXs and down the carrier before
+ * resetting; this is needed to avoid things like
+ * i2400m_wake_tx() scheduling stuff in parallel.
+ */
+ if (net_dev->reg_state == NETREG_REGISTERED) {
+ netif_tx_disable(net_dev);
+ netif_carrier_off(net_dev);
+ }
+ return i2400m->bus_reset(i2400m, rt);
+}
+EXPORT_SYMBOL_GPL(i2400m_reset);
+
+
+/**
+ * i2400m_setup - bus-generic setup function for the i2400m device
+ *
+ * @i2400m: device descriptor (bus-specific parts have been initialized)
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * Sets up basic device comunication infrastructure, boots the ROM to
+ * read the MAC address, registers with the WiMAX and network stacks
+ * and then brings up the device.
+ */
+int i2400m_setup(struct i2400m *i2400m, enum i2400m_bri bm_flags)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+ struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+
+ snprintf(wimax_dev->name, sizeof(wimax_dev->name),
+ "i2400m-%s:%s", dev->bus->name, dev_name(dev));
+
+ result = i2400m_bm_buf_alloc(i2400m);
+ if (result < 0) {
+ dev_err(dev, "cannot allocate bootmode scratch buffers\n");
+ goto error_bm_buf_alloc;
+ }
+
+ if (i2400m->bus_setup) {
+ result = i2400m->bus_setup(i2400m);
+ if (result < 0) {
+ dev_err(dev, "bus-specific setup failed: %d\n",
+ result);
+ goto error_bus_setup;
+ }
+ }
+
+ result = i2400m_bootrom_init(i2400m, bm_flags);
+ if (result < 0) {
+ dev_err(dev, "read mac addr: bootrom init "
+ "failed: %d\n", result);
+ goto error_bootrom_init;
+ }
+ result = i2400m_read_mac_addr(i2400m);
+ if (result < 0)
+ goto error_read_mac_addr;
+ eth_random_addr(i2400m->src_mac_addr);
+
+ i2400m->pm_notifier.notifier_call = i2400m_pm_notifier;
+ register_pm_notifier(&i2400m->pm_notifier);
+
+ result = register_netdev(net_dev); /* Okey dokey, bring it up */
+ if (result < 0) {
+ dev_err(dev, "cannot register i2400m network device: %d\n",
+ result);
+ goto error_register_netdev;
+ }
+ netif_carrier_off(net_dev);
+
+ i2400m->wimax_dev.op_msg_from_user = i2400m_op_msg_from_user;
+ i2400m->wimax_dev.op_rfkill_sw_toggle = i2400m_op_rfkill_sw_toggle;
+ i2400m->wimax_dev.op_reset = i2400m_op_reset;
+
+ result = wimax_dev_add(&i2400m->wimax_dev, net_dev);
+ if (result < 0)
+ goto error_wimax_dev_add;
+
+ /* Now setup all that requires a registered net and wimax device. */
+ result = sysfs_create_group(&net_dev->dev.kobj, &i2400m_dev_attr_group);
+ if (result < 0) {
+ dev_err(dev, "cannot setup i2400m's sysfs: %d\n", result);
+ goto error_sysfs_setup;
+ }
+
+ i2400m_debugfs_add(i2400m);
+
+ result = i2400m_dev_start(i2400m, bm_flags);
+ if (result < 0)
+ goto error_dev_start;
+ d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+ return result;
+
+error_dev_start:
+ i2400m_debugfs_rm(i2400m);
+ sysfs_remove_group(&i2400m->wimax_dev.net_dev->dev.kobj,
+ &i2400m_dev_attr_group);
+error_sysfs_setup:
+ wimax_dev_rm(&i2400m->wimax_dev);
+error_wimax_dev_add:
+ unregister_netdev(net_dev);
+error_register_netdev:
+ unregister_pm_notifier(&i2400m->pm_notifier);
+error_read_mac_addr:
+error_bootrom_init:
+ if (i2400m->bus_release)
+ i2400m->bus_release(i2400m);
+error_bus_setup:
+ i2400m_bm_buf_free(i2400m);
+error_bm_buf_alloc:
+ d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+ return result;
+}
+EXPORT_SYMBOL_GPL(i2400m_setup);
+
+
+/**
+ * i2400m_release - release the bus-generic driver resources
+ *
+ * Sends a disconnect message and undoes any setup done by i2400m_setup()
+ */
+void i2400m_release(struct i2400m *i2400m)
+{
+ struct device *dev = i2400m_dev(i2400m);
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+ netif_stop_queue(i2400m->wimax_dev.net_dev);
+
+ i2400m_dev_stop(i2400m);
+
+ cancel_work_sync(&i2400m->reset_ws);
+ cancel_work_sync(&i2400m->recovery_ws);
+
+ i2400m_debugfs_rm(i2400m);
+ sysfs_remove_group(&i2400m->wimax_dev.net_dev->dev.kobj,
+ &i2400m_dev_attr_group);
+ wimax_dev_rm(&i2400m->wimax_dev);
+ unregister_netdev(i2400m->wimax_dev.net_dev);
+ unregister_pm_notifier(&i2400m->pm_notifier);
+ if (i2400m->bus_release)
+ i2400m->bus_release(i2400m);
+ i2400m_bm_buf_free(i2400m);
+ d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
+EXPORT_SYMBOL_GPL(i2400m_release);
+
+
+/*
+ * Debug levels control; see debug.h
+ */
+struct d_level D_LEVEL[] = {
+ D_SUBMODULE_DEFINE(control),
+ D_SUBMODULE_DEFINE(driver),
+ D_SUBMODULE_DEFINE(debugfs),
+ D_SUBMODULE_DEFINE(fw),
+ D_SUBMODULE_DEFINE(netdev),
+ D_SUBMODULE_DEFINE(rfkill),
+ D_SUBMODULE_DEFINE(rx),
+ D_SUBMODULE_DEFINE(sysfs),
+ D_SUBMODULE_DEFINE(tx),
+};
+size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
+
+
+static
+int __init i2400m_driver_init(void)
+{
+ d_parse_params(D_LEVEL, D_LEVEL_SIZE, i2400m_debug_params,
+ "i2400m.debug");
+ return i2400m_barker_db_init(i2400m_barkers_params);
+}
+module_init(i2400m_driver_init);
+
+static
+void __exit i2400m_driver_exit(void)
+{
+ i2400m_barker_db_exit();
+}
+module_exit(i2400m_driver_exit);
+
+MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
+MODULE_DESCRIPTION("Intel 2400M WiMAX networking bus-generic driver");
+MODULE_LICENSE("GPL");
--- /dev/null
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Firmware uploader
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * - Initial implementation
+ *
+ *
+ * THE PROCEDURE
+ *
+ * The 2400m and derived devices work in two modes: boot-mode or
+ * normal mode. In boot mode we can execute only a handful of commands
+ * targeted at uploading the firmware and launching it.
+ *
+ * The 2400m enters boot mode when it is first connected to the
+ * system, when it crashes and when you ask it to reboot. There are
+ * two submodes of the boot mode: signed and non-signed. Signed takes
+ * firmwares signed with a certain private key, non-signed takes any
+ * firmware. Normal hardware takes only signed firmware.
+ *
+ * On boot mode, in USB, we write to the device using the bulk out
+ * endpoint and read from it in the notification endpoint.
+ *
+ * Upon entrance to boot mode, the device sends (preceded with a few
+ * zero length packets (ZLPs) on the notification endpoint in USB) a
+ * reboot barker (4 le32 words with the same value). We ack it by
+ * sending the same barker to the device. The device acks with a
+ * reboot ack barker (4 le32 words with value I2400M_ACK_BARKER) and
+ * then is fully booted. At this point we can upload the firmware.
+ *
+ * Note that different iterations of the device and EEPROM
+ * configurations will send different [re]boot barkers; these are
+ * collected in i2400m_barker_db along with the firmware
+ * characteristics they require.
+ *
+ * This process is accomplished by the i2400m_bootrom_init()
+ * function. All the device interaction happens through the
+ * i2400m_bm_cmd() [boot mode command]. Special return values will
+ * indicate if the device did reset during the process.
+ *
+ * After this, we read the MAC address and then (if needed)
+ * reinitialize the device. We need to read it ahead of time because
+ * in the future, we might not upload the firmware until userspace
+ * 'ifconfig up's the device.
+ *
+ * We can then upload the firmware file. The file is composed of a BCF
+ * header (basic data, keys and signatures) and a list of write
+ * commands and payloads. Optionally more BCF headers might follow the
+ * main payload. We first upload the header [i2400m_dnload_init()] and
+ * then pass the commands and payloads verbatim to the i2400m_bm_cmd()
+ * function [i2400m_dnload_bcf()]. Then we tell the device to jump to
+ * the new firmware [i2400m_dnload_finalize()].
+ *
+ * Once firmware is uploaded, we are good to go :)
+ *
+ * When we don't know in which mode we are, we first try by sending a
+ * warm reset request that will take us to boot-mode. If we time out
+ * waiting for a reboot barker, that means maybe we are already in
+ * boot mode, so we send a reboot barker.
+ *
+ * COMMAND EXECUTION
+ *
+ * This code (and process) is single threaded; for executing commands,
+ * we post a URB to the notification endpoint, post the command, wait
+ * for data on the notification buffer. We don't need to worry about
+ * others as we know we are the only ones in there.
+ *
+ * BACKEND IMPLEMENTATION
+ *
+ * This code is bus-generic; the bus-specific driver provides back end
+ * implementations to send a boot mode command to the device and to
+ * read an acknolwedgement from it (or an asynchronous notification)
+ * from it.
+ *
+ * FIRMWARE LOADING
+ *
+ * Note that in some cases, we can't just load a firmware file (for
+ * example, when resuming). For that, we might cache the firmware
+ * file. Thus, when doing the bootstrap, if there is a cache firmware
+ * file, it is used; if not, loading from disk is attempted.
+ *
+ * ROADMAP
+ *
+ * i2400m_barker_db_init Called by i2400m_driver_init()
+ * i2400m_barker_db_add
+ *
+ * i2400m_barker_db_exit Called by i2400m_driver_exit()
+ *
+ * i2400m_dev_bootstrap Called by __i2400m_dev_start()
+ * request_firmware
+ * i2400m_fw_bootstrap
+ * i2400m_fw_check
+ * i2400m_fw_hdr_check
+ * i2400m_fw_dnload
+ * release_firmware
+ *
+ * i2400m_fw_dnload
+ * i2400m_bootrom_init
+ * i2400m_bm_cmd
+ * i2400m_reset
+ * i2400m_dnload_init
+ * i2400m_dnload_init_signed
+ * i2400m_dnload_init_nonsigned
+ * i2400m_download_chunk
+ * i2400m_bm_cmd
+ * i2400m_dnload_bcf
+ * i2400m_bm_cmd
+ * i2400m_dnload_finalize
+ * i2400m_bm_cmd
+ *
+ * i2400m_bm_cmd
+ * i2400m->bus_bm_cmd_send()
+ * i2400m->bus_bm_wait_for_ack
+ * __i2400m_bm_ack_verify
+ * i2400m_is_boot_barker
+ *
+ * i2400m_bm_cmd_prepare Used by bus-drivers to prep
+ * commands before sending
+ *
+ * i2400m_pm_notifier Called on Power Management events
+ * i2400m_fw_cache
+ * i2400m_fw_uncache
+ */
+#include <linux/firmware.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/usb.h>
+#include <linux/export.h>
+#include "i2400m.h"
+
+
+#define D_SUBMODULE fw
+#include "debug-levels.h"
+
+
+static const __le32 i2400m_ACK_BARKER[4] = {
+ cpu_to_le32(I2400M_ACK_BARKER),
+ cpu_to_le32(I2400M_ACK_BARKER),
+ cpu_to_le32(I2400M_ACK_BARKER),
+ cpu_to_le32(I2400M_ACK_BARKER)
+};
+
+
+/**
+ * Prepare a boot-mode command for delivery
+ *
+ * @cmd: pointer to bootrom header to prepare
+ *
+ * Computes checksum if so needed. After calling this function, DO NOT
+ * modify the command or header as the checksum won't work anymore.
+ *
+ * We do it from here because some times we cannot do it in the
+ * original context the command was sent (it is a const), so when we
+ * copy it to our staging buffer, we add the checksum there.
+ */
+void i2400m_bm_cmd_prepare(struct i2400m_bootrom_header *cmd)
+{
+ if (i2400m_brh_get_use_checksum(cmd)) {
+ int i;
+ u32 checksum = 0;
+ const u32 *checksum_ptr = (void *) cmd->payload;
+ for (i = 0; i < cmd->data_size / 4; i++)
+ checksum += cpu_to_le32(*checksum_ptr++);
+ checksum += cmd->command + cmd->target_addr + cmd->data_size;
+ cmd->block_checksum = cpu_to_le32(checksum);
+ }
+}
+EXPORT_SYMBOL_GPL(i2400m_bm_cmd_prepare);
+
+
+/*
+ * Database of known barkers.
+ *
+ * A barker is what the device sends indicating he is ready to be
+ * bootloaded. Different versions of the device will send different
+ * barkers. Depending on the barker, it might mean the device wants
+ * some kind of firmware or the other.
+ */
+static struct i2400m_barker_db {
+ __le32 data[4];
+} *i2400m_barker_db;
+static size_t i2400m_barker_db_used, i2400m_barker_db_size;
+
+
+static
+int i2400m_zrealloc_2x(void **ptr, size_t *_count, size_t el_size,
+ gfp_t gfp_flags)
+{
+ size_t old_count = *_count,
+ new_count = old_count ? 2 * old_count : 2,
+ old_size = el_size * old_count,
+ new_size = el_size * new_count;
+ void *nptr = krealloc(*ptr, new_size, gfp_flags);
+ if (nptr) {
+ /* zero the other half or the whole thing if old_count
+ * was zero */
+ if (old_size == 0)
+ memset(nptr, 0, new_size);
+ else
+ memset(nptr + old_size, 0, old_size);
+ *_count = new_count;
+ *ptr = nptr;
+ return 0;
+ } else
+ return -ENOMEM;
+}
+
+
+/*
+ * Add a barker to the database
+ *
+ * This cannot used outside of this module and only at at module_init
+ * time. This is to avoid the need to do locking.
+ */
+static
+int i2400m_barker_db_add(u32 barker_id)
+{
+ int result;
+
+ struct i2400m_barker_db *barker;
+ if (i2400m_barker_db_used >= i2400m_barker_db_size) {
+ result = i2400m_zrealloc_2x(
+ (void **) &i2400m_barker_db, &i2400m_barker_db_size,
+ sizeof(i2400m_barker_db[0]), GFP_KERNEL);
+ if (result < 0)
+ return result;
+ }
+ barker = i2400m_barker_db + i2400m_barker_db_used++;
+ barker->data[0] = le32_to_cpu(barker_id);
+ barker->data[1] = le32_to_cpu(barker_id);
+ barker->data[2] = le32_to_cpu(barker_id);
+ barker->data[3] = le32_to_cpu(barker_id);
+ return 0;
+}
+
+
+void i2400m_barker_db_exit(void)
+{
+ kfree(i2400m_barker_db);
+ i2400m_barker_db = NULL;
+ i2400m_barker_db_size = 0;
+ i2400m_barker_db_used = 0;
+}
+
+
+/*
+ * Helper function to add all the known stable barkers to the barker
+ * database.
+ */
+static
+int i2400m_barker_db_known_barkers(void)
+{
+ int result;
+
+ result = i2400m_barker_db_add(I2400M_NBOOT_BARKER);
+ if (result < 0)
+ goto error_add;
+ result = i2400m_barker_db_add(I2400M_SBOOT_BARKER);
+ if (result < 0)
+ goto error_add;
+ result = i2400m_barker_db_add(I2400M_SBOOT_BARKER_6050);
+ if (result < 0)
+ goto error_add;
+error_add:
+ return result;
+}
+
+
+/*
+ * Initialize the barker database
+ *
+ * This can only be used from the module_init function for this
+ * module; this is to avoid the need to do locking.
+ *
+ * @options: command line argument with extra barkers to
+ * recognize. This is a comma-separated list of 32-bit hex
+ * numbers. They are appended to the existing list. Setting 0
+ * cleans the existing list and starts a new one.
+ */
+int i2400m_barker_db_init(const char *_options)
+{
+ int result;
+ char *options = NULL, *options_orig, *token;
+
+ i2400m_barker_db = NULL;
+ i2400m_barker_db_size = 0;
+ i2400m_barker_db_used = 0;
+
+ result = i2400m_barker_db_known_barkers();
+ if (result < 0)
+ goto error_add;
+ /* parse command line options from i2400m.barkers */
+ if (_options != NULL) {
+ unsigned barker;
+
+ options_orig = kstrdup(_options, GFP_KERNEL);
+ if (options_orig == NULL) {
+ result = -ENOMEM;
+ goto error_parse;
+ }
+ options = options_orig;
+
+ while ((token = strsep(&options, ",")) != NULL) {
+ if (*token == '\0') /* eat joint commas */
+ continue;
+ if (sscanf(token, "%x", &barker) != 1
+ || barker > 0xffffffff) {
+ printk(KERN_ERR "%s: can't recognize "
+ "i2400m.barkers value '%s' as "
+ "a 32-bit number\n",
+ __func__, token);
+ result = -EINVAL;
+ goto error_parse;
+ }
+ if (barker == 0) {
+ /* clean list and start new */
+ i2400m_barker_db_exit();
+ continue;
+ }
+ result = i2400m_barker_db_add(barker);
+ if (result < 0)
+ goto error_parse_add;
+ }
+ kfree(options_orig);
+ }
+ return 0;
+
+error_parse_add:
+error_parse:
+ kfree(options_orig);
+error_add:
+ kfree(i2400m_barker_db);
+ return result;
+}
+
+
+/*
+ * Recognize a boot barker
+ *
+ * @buf: buffer where the boot barker.
+ * @buf_size: size of the buffer (has to be 16 bytes). It is passed
+ * here so the function can check it for the caller.
+ *
+ * Note that as a side effect, upon identifying the obtained boot
+ * barker, this function will set i2400m->barker to point to the right
+ * barker database entry. Subsequent calls to the function will result
+ * in verifying that the same type of boot barker is returned when the
+ * device [re]boots (as long as the same device instance is used).
+ *
+ * Return: 0 if @buf matches a known boot barker. -ENOENT if the
+ * buffer in @buf doesn't match any boot barker in the database or
+ * -EILSEQ if the buffer doesn't have the right size.
+ */
+int i2400m_is_boot_barker(struct i2400m *i2400m,
+ const void *buf, size_t buf_size)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400m_barker_db *barker;
+ int i;
+
+ result = -ENOENT;
+ if (buf_size != sizeof(i2400m_barker_db[i].data))
+ return result;
+
+ /* Short circuit if we have already discovered the barker
+ * associated with the device. */
+ if (i2400m->barker &&
+ !memcmp(buf, i2400m->barker, sizeof(i2400m->barker->data)))
+ return 0;
+
+ for (i = 0; i < i2400m_barker_db_used; i++) {
+ barker = &i2400m_barker_db[i];
+ BUILD_BUG_ON(sizeof(barker->data) != 16);
+ if (memcmp(buf, barker->data, sizeof(barker->data)))
+ continue;
+
+ if (i2400m->barker == NULL) {
+ i2400m->barker = barker;
+ d_printf(1, dev, "boot barker set to #%u/%08x\n",
+ i, le32_to_cpu(barker->data[0]));
+ if (barker->data[0] == le32_to_cpu(I2400M_NBOOT_BARKER))
+ i2400m->sboot = 0;
+ else
+ i2400m->sboot = 1;
+ } else if (i2400m->barker != barker) {
+ dev_err(dev, "HW inconsistency: device "
+ "reports a different boot barker "
+ "than set (from %08x to %08x)\n",
+ le32_to_cpu(i2400m->barker->data[0]),
+ le32_to_cpu(barker->data[0]));
+ result = -EIO;
+ } else
+ d_printf(2, dev, "boot barker confirmed #%u/%08x\n",
+ i, le32_to_cpu(barker->data[0]));
+ result = 0;
+ break;
+ }
+ return result;
+}
+EXPORT_SYMBOL_GPL(i2400m_is_boot_barker);
+
+
+/*
+ * Verify the ack data received
+ *
+ * Given a reply to a boot mode command, chew it and verify everything
+ * is ok.
+ *
+ * @opcode: opcode which generated this ack. For error messages.
+ * @ack: pointer to ack data we received
+ * @ack_size: size of that data buffer
+ * @flags: I2400M_BM_CMD_* flags we called the command with.
+ *
+ * Way too long function -- maybe it should be further split
+ */
+static
+ssize_t __i2400m_bm_ack_verify(struct i2400m *i2400m, int opcode,
+ struct i2400m_bootrom_header *ack,
+ size_t ack_size, int flags)
+{
+ ssize_t result = -ENOMEM;
+ struct device *dev = i2400m_dev(i2400m);
+
+ d_fnstart(8, dev, "(i2400m %p opcode %d ack %p size %zu)\n",
+ i2400m, opcode, ack, ack_size);
+ if (ack_size < sizeof(*ack)) {
+ result = -EIO;
+ dev_err(dev, "boot-mode cmd %d: HW BUG? notification didn't "
+ "return enough data (%zu bytes vs %zu expected)\n",
+ opcode, ack_size, sizeof(*ack));
+ goto error_ack_short;
+ }
+ result = i2400m_is_boot_barker(i2400m, ack, ack_size);
+ if (result >= 0) {
+ result = -ERESTARTSYS;
+ d_printf(6, dev, "boot-mode cmd %d: HW boot barker\n", opcode);
+ goto error_reboot;
+ }
+ if (ack_size == sizeof(i2400m_ACK_BARKER)
+ && memcmp(ack, i2400m_ACK_BARKER, sizeof(*ack)) == 0) {
+ result = -EISCONN;
+ d_printf(3, dev, "boot-mode cmd %d: HW reboot ack barker\n",
+ opcode);
+ goto error_reboot_ack;
+ }
+ result = 0;
+ if (flags & I2400M_BM_CMD_RAW)
+ goto out_raw;
+ ack->data_size = le32_to_cpu(ack->data_size);
+ ack->target_addr = le32_to_cpu(ack->target_addr);
+ ack->block_checksum = le32_to_cpu(ack->block_checksum);
+ d_printf(5, dev, "boot-mode cmd %d: notification for opcode %u "
+ "response %u csum %u rr %u da %u\n",
+ opcode, i2400m_brh_get_opcode(ack),
+ i2400m_brh_get_response(ack),
+ i2400m_brh_get_use_checksum(ack),
+ i2400m_brh_get_response_required(ack),
+ i2400m_brh_get_direct_access(ack));
+ result = -EIO;
+ if (i2400m_brh_get_signature(ack) != 0xcbbc) {
+ dev_err(dev, "boot-mode cmd %d: HW BUG? wrong signature "
+ "0x%04x\n", opcode, i2400m_brh_get_signature(ack));
+ goto error_ack_signature;
+ }
+ if (opcode != -1 && opcode != i2400m_brh_get_opcode(ack)) {
+ dev_err(dev, "boot-mode cmd %d: HW BUG? "
+ "received response for opcode %u, expected %u\n",
+ opcode, i2400m_brh_get_opcode(ack), opcode);
+ goto error_ack_opcode;
+ }
+ if (i2400m_brh_get_response(ack) != 0) { /* failed? */
+ dev_err(dev, "boot-mode cmd %d: error; hw response %u\n",
+ opcode, i2400m_brh_get_response(ack));
+ goto error_ack_failed;
+ }
+ if (ack_size < ack->data_size + sizeof(*ack)) {
+ dev_err(dev, "boot-mode cmd %d: SW BUG "
+ "driver provided only %zu bytes for %zu bytes "
+ "of data\n", opcode, ack_size,
+ (size_t) le32_to_cpu(ack->data_size) + sizeof(*ack));
+ goto error_ack_short_buffer;
+ }
+ result = ack_size;
+ /* Don't you love this stack of empty targets? Well, I don't
+ * either, but it helps track exactly who comes in here and
+ * why :) */
+error_ack_short_buffer:
+error_ack_failed:
+error_ack_opcode:
+error_ack_signature:
+out_raw:
+error_reboot_ack:
+error_reboot:
+error_ack_short:
+ d_fnend(8, dev, "(i2400m %p opcode %d ack %p size %zu) = %d\n",
+ i2400m, opcode, ack, ack_size, (int) result);
+ return result;
+}
+
+
+/**
+ * i2400m_bm_cmd - Execute a boot mode command
+ *
+ * @cmd: buffer containing the command data (pointing at the header).
+ * This data can be ANYWHERE (for USB, we will copy it to an
+ * specific buffer). Make sure everything is in proper little
+ * endian.
+ *
+ * A raw buffer can be also sent, just cast it and set flags to
+ * I2400M_BM_CMD_RAW.
+ *
+ * This function will generate a checksum for you if the
+ * checksum bit in the command is set (unless I2400M_BM_CMD_RAW
+ * is set).
+ *
+ * You can use the i2400m->bm_cmd_buf to stage your commands and
+ * send them.
+ *
+ * If NULL, no command is sent (we just wait for an ack).
+ *
+ * @cmd_size: size of the command. Will be auto padded to the
+ * bus-specific drivers padding requirements.
+ *
+ * @ack: buffer where to place the acknowledgement. If it is a regular
+ * command response, all fields will be returned with the right,
+ * native endianess.
+ *
+ * You *cannot* use i2400m->bm_ack_buf for this buffer.
+ *
+ * @ack_size: size of @ack, 16 aligned; you need to provide at least
+ * sizeof(*ack) bytes and then enough to contain the return data
+ * from the command
+ *
+ * @flags: see I2400M_BM_CMD_* above.
+ *
+ * @returns: bytes received by the notification; if < 0, an errno code
+ * denoting an error or:
+ *
+ * -ERESTARTSYS The device has rebooted
+ *
+ * Executes a boot-mode command and waits for a response, doing basic
+ * validation on it; if a zero length response is received, it retries
+ * waiting for a response until a non-zero one is received (timing out
+ * after %I2400M_BOOT_RETRIES retries).
+ */
+static
+ssize_t i2400m_bm_cmd(struct i2400m *i2400m,
+ const struct i2400m_bootrom_header *cmd, size_t cmd_size,
+ struct i2400m_bootrom_header *ack, size_t ack_size,
+ int flags)
+{
+ ssize_t result = -ENOMEM, rx_bytes;
+ struct device *dev = i2400m_dev(i2400m);
+ int opcode = cmd == NULL ? -1 : i2400m_brh_get_opcode(cmd);
+
+ d_fnstart(6, dev, "(i2400m %p cmd %p size %zu ack %p size %zu)\n",
+ i2400m, cmd, cmd_size, ack, ack_size);
+ BUG_ON(ack_size < sizeof(*ack));
+ BUG_ON(i2400m->boot_mode == 0);
+
+ if (cmd != NULL) { /* send the command */
+ result = i2400m->bus_bm_cmd_send(i2400m, cmd, cmd_size, flags);
+ if (result < 0)
+ goto error_cmd_send;
+ if ((flags & I2400M_BM_CMD_RAW) == 0)
+ d_printf(5, dev,
+ "boot-mode cmd %d csum %u rr %u da %u: "
+ "addr 0x%04x size %u block csum 0x%04x\n",
+ opcode, i2400m_brh_get_use_checksum(cmd),
+ i2400m_brh_get_response_required(cmd),
+ i2400m_brh_get_direct_access(cmd),
+ cmd->target_addr, cmd->data_size,
+ cmd->block_checksum);
+ }
+ result = i2400m->bus_bm_wait_for_ack(i2400m, ack, ack_size);
+ if (result < 0) {
+ dev_err(dev, "boot-mode cmd %d: error waiting for an ack: %d\n",
+ opcode, (int) result); /* bah, %zd doesn't work */
+ goto error_wait_for_ack;
+ }
+ rx_bytes = result;
+ /* verify the ack and read more if necessary [result is the
+ * final amount of bytes we get in the ack] */
+ result = __i2400m_bm_ack_verify(i2400m, opcode, ack, ack_size, flags);
+ if (result < 0)
+ goto error_bad_ack;
+ /* Don't you love this stack of empty targets? Well, I don't
+ * either, but it helps track exactly who comes in here and
+ * why :) */
+ result = rx_bytes;
+error_bad_ack:
+error_wait_for_ack:
+error_cmd_send:
+ d_fnend(6, dev, "(i2400m %p cmd %p size %zu ack %p size %zu) = %d\n",
+ i2400m, cmd, cmd_size, ack, ack_size, (int) result);
+ return result;
+}
+
+
+/**
+ * i2400m_download_chunk - write a single chunk of data to the device's memory
+ *
+ * @i2400m: device descriptor
+ * @buf: the buffer to write
+ * @buf_len: length of the buffer to write
+ * @addr: address in the device memory space
+ * @direct: bootrom write mode
+ * @do_csum: should a checksum validation be performed
+ */
+static int i2400m_download_chunk(struct i2400m *i2400m, const void *chunk,
+ size_t __chunk_len, unsigned long addr,
+ unsigned int direct, unsigned int do_csum)
+{
+ int ret;
+ size_t chunk_len = ALIGN(__chunk_len, I2400M_PL_ALIGN);
+ struct device *dev = i2400m_dev(i2400m);
+ struct {
+ struct i2400m_bootrom_header cmd;
+ u8 cmd_payload[];
+ } __packed *buf;
+ struct i2400m_bootrom_header ack;
+
+ d_fnstart(5, dev, "(i2400m %p chunk %p __chunk_len %zu addr 0x%08lx "
+ "direct %u do_csum %u)\n", i2400m, chunk, __chunk_len,
+ addr, direct, do_csum);
+ buf = i2400m->bm_cmd_buf;
+ memcpy(buf->cmd_payload, chunk, __chunk_len);
+ memset(buf->cmd_payload + __chunk_len, 0xad, chunk_len - __chunk_len);
+
+ buf->cmd.command = i2400m_brh_command(I2400M_BRH_WRITE,
+ __chunk_len & 0x3 ? 0 : do_csum,
+ __chunk_len & 0xf ? 0 : direct);
+ buf->cmd.target_addr = cpu_to_le32(addr);
+ buf->cmd.data_size = cpu_to_le32(__chunk_len);
+ ret = i2400m_bm_cmd(i2400m, &buf->cmd, sizeof(buf->cmd) + chunk_len,
+ &ack, sizeof(ack), 0);
+ if (ret >= 0)
+ ret = 0;
+ d_fnend(5, dev, "(i2400m %p chunk %p __chunk_len %zu addr 0x%08lx "
+ "direct %u do_csum %u) = %d\n", i2400m, chunk, __chunk_len,
+ addr, direct, do_csum, ret);
+ return ret;
+}
+
+
+/*
+ * Download a BCF file's sections to the device
+ *
+ * @i2400m: device descriptor
+ * @bcf: pointer to firmware data (first header followed by the
+ * payloads). Assumed verified and consistent.
+ * @bcf_len: length (in bytes) of the @bcf buffer.
+ *
+ * Returns: < 0 errno code on error or the offset to the jump instruction.
+ *
+ * Given a BCF file, downloads each section (a command and a payload)
+ * to the device's address space. Actually, it just executes each
+ * command i the BCF file.
+ *
+ * The section size has to be aligned to 4 bytes AND the padding has
+ * to be taken from the firmware file, as the signature takes it into
+ * account.
+ */
+static
+ssize_t i2400m_dnload_bcf(struct i2400m *i2400m,
+ const struct i2400m_bcf_hdr *bcf, size_t bcf_len)
+{
+ ssize_t ret;
+ struct device *dev = i2400m_dev(i2400m);
+ size_t offset, /* iterator offset */
+ data_size, /* Size of the data payload */
+ section_size, /* Size of the whole section (cmd + payload) */
+ section = 1;
+ const struct i2400m_bootrom_header *bh;
+ struct i2400m_bootrom_header ack;
+
+ d_fnstart(3, dev, "(i2400m %p bcf %p bcf_len %zu)\n",
+ i2400m, bcf, bcf_len);
+ /* Iterate over the command blocks in the BCF file that start
+ * after the header */
+ offset = le32_to_cpu(bcf->header_len) * sizeof(u32);
+ while (1) { /* start sending the file */
+ bh = (void *) bcf + offset;
+ data_size = le32_to_cpu(bh->data_size);
+ section_size = ALIGN(sizeof(*bh) + data_size, 4);
+ d_printf(7, dev,
+ "downloading section #%zu (@%zu %zu B) to 0x%08x\n",
+ section, offset, sizeof(*bh) + data_size,
+ le32_to_cpu(bh->target_addr));
+ /*
+ * We look for JUMP cmd from the bootmode header,
+ * either I2400M_BRH_SIGNED_JUMP for secure boot
+ * or I2400M_BRH_JUMP for unsecure boot, the last chunk
+ * should be the bootmode header with JUMP cmd.
+ */
+ if (i2400m_brh_get_opcode(bh) == I2400M_BRH_SIGNED_JUMP ||
+ i2400m_brh_get_opcode(bh) == I2400M_BRH_JUMP) {
+ d_printf(5, dev, "jump found @%zu\n", offset);
+ break;
+ }
+ if (offset + section_size > bcf_len) {
+ dev_err(dev, "fw %s: bad section #%zu, "
+ "end (@%zu) beyond EOF (@%zu)\n",
+ i2400m->fw_name, section,
+ offset + section_size, bcf_len);
+ ret = -EINVAL;
+ goto error_section_beyond_eof;
+ }
+ __i2400m_msleep(20);
+ ret = i2400m_bm_cmd(i2400m, bh, section_size,
+ &ack, sizeof(ack), I2400M_BM_CMD_RAW);
+ if (ret < 0) {
+ dev_err(dev, "fw %s: section #%zu (@%zu %zu B) "
+ "failed %d\n", i2400m->fw_name, section,
+ offset, sizeof(*bh) + data_size, (int) ret);
+ goto error_send;
+ }
+ offset += section_size;
+ section++;
+ }
+ ret = offset;
+error_section_beyond_eof:
+error_send:
+ d_fnend(3, dev, "(i2400m %p bcf %p bcf_len %zu) = %d\n",
+ i2400m, bcf, bcf_len, (int) ret);
+ return ret;
+}
+
+
+/*
+ * Indicate if the device emitted a reboot barker that indicates
+ * "signed boot"
+ */
+static
+unsigned i2400m_boot_is_signed(struct i2400m *i2400m)
+{
+ return likely(i2400m->sboot);
+}
+
+
+/*
+ * Do the final steps of uploading firmware
+ *
+ * @bcf_hdr: BCF header we are actually using
+ * @bcf: pointer to the firmware image (which matches the first header
+ * that is followed by the actual payloads).
+ * @offset: [byte] offset into @bcf for the command we need to send.
+ *
+ * Depending on the boot mode (signed vs non-signed), different
+ * actions need to be taken.
+ */
+static
+int i2400m_dnload_finalize(struct i2400m *i2400m,
+ const struct i2400m_bcf_hdr *bcf_hdr,
+ const struct i2400m_bcf_hdr *bcf, size_t offset)
+{
+ int ret = 0;
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400m_bootrom_header *cmd, ack;
+ struct {
+ struct i2400m_bootrom_header cmd;
+ u8 cmd_pl[0];
+ } __packed *cmd_buf;
+ size_t signature_block_offset, signature_block_size;
+
+ d_fnstart(3, dev, "offset %zu\n", offset);
+ cmd = (void *) bcf + offset;
+ if (i2400m_boot_is_signed(i2400m) == 0) {
+ struct i2400m_bootrom_header jump_ack;
+ d_printf(1, dev, "unsecure boot, jumping to 0x%08x\n",
+ le32_to_cpu(cmd->target_addr));
+ cmd_buf = i2400m->bm_cmd_buf;
+ memcpy(&cmd_buf->cmd, cmd, sizeof(*cmd));
+ cmd = &cmd_buf->cmd;
+ /* now cmd points to the actual bootrom_header in cmd_buf */
+ i2400m_brh_set_opcode(cmd, I2400M_BRH_JUMP);
+ cmd->data_size = 0;
+ ret = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
+ &jump_ack, sizeof(jump_ack), 0);
+ } else {
+ d_printf(1, dev, "secure boot, jumping to 0x%08x\n",
+ le32_to_cpu(cmd->target_addr));
+ cmd_buf = i2400m->bm_cmd_buf;
+ memcpy(&cmd_buf->cmd, cmd, sizeof(*cmd));
+ signature_block_offset =
+ sizeof(*bcf_hdr)
+ + le32_to_cpu(bcf_hdr->key_size) * sizeof(u32)
+ + le32_to_cpu(bcf_hdr->exponent_size) * sizeof(u32);
+ signature_block_size =
+ le32_to_cpu(bcf_hdr->modulus_size) * sizeof(u32);
+ memcpy(cmd_buf->cmd_pl,
+ (void *) bcf_hdr + signature_block_offset,
+ signature_block_size);
+ ret = i2400m_bm_cmd(i2400m, &cmd_buf->cmd,
+ sizeof(cmd_buf->cmd) + signature_block_size,
+ &ack, sizeof(ack), I2400M_BM_CMD_RAW);
+ }
+ d_fnend(3, dev, "returning %d\n", ret);
+ return ret;
+}
+
+
+/**
+ * i2400m_bootrom_init - Reboots a powered device into boot mode
+ *
+ * @i2400m: device descriptor
+ * @flags:
+ * I2400M_BRI_SOFT: a reboot barker has been seen
+ * already, so don't wait for it.
+ *
+ * I2400M_BRI_NO_REBOOT: Don't send a reboot command, but wait
+ * for a reboot barker notification. This is a one shot; if
+ * the state machine needs to send a reboot command it will.
+ *
+ * Returns:
+ *
+ * < 0 errno code on error, 0 if ok.
+ *
+ * Description:
+ *
+ * Tries hard enough to put the device in boot-mode. There are two
+ * main phases to this:
+ *
+ * a. (1) send a reboot command and (2) get a reboot barker
+ *
+ * b. (1) echo/ack the reboot sending the reboot barker back and (2)
+ * getting an ack barker in return
+ *
+ * We want to skip (a) in some cases [soft]. The state machine is
+ * horrible, but it is basically: on each phase, send what has to be
+ * sent (if any), wait for the answer and act on the answer. We might
+ * have to backtrack and retry, so we keep a max tries counter for
+ * that.
+ *
+ * It sucks because we don't know ahead of time which is going to be
+ * the reboot barker (the device might send different ones depending
+ * on its EEPROM config) and once the device reboots and waits for the
+ * echo/ack reboot barker being sent back, it doesn't understand
+ * anything else. So we can be left at the point where we don't know
+ * what to send to it -- cold reset and bus reset seem to have little
+ * effect. So the function iterates (in this case) through all the
+ * known barkers and tries them all until an ACK is
+ * received. Otherwise, it gives up.
+ *
+ * If we get a timeout after sending a warm reset, we do it again.
+ */
+int i2400m_bootrom_init(struct i2400m *i2400m, enum i2400m_bri flags)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400m_bootrom_header *cmd;
+ struct i2400m_bootrom_header ack;
+ int count = i2400m->bus_bm_retries;
+ int ack_timeout_cnt = 1;
+ unsigned i;
+
+ BUILD_BUG_ON(sizeof(*cmd) != sizeof(i2400m_barker_db[0].data));
+ BUILD_BUG_ON(sizeof(ack) != sizeof(i2400m_ACK_BARKER));
+
+ d_fnstart(4, dev, "(i2400m %p flags 0x%08x)\n", i2400m, flags);
+ result = -ENOMEM;
+ cmd = i2400m->bm_cmd_buf;
+ if (flags & I2400M_BRI_SOFT)
+ goto do_reboot_ack;
+do_reboot:
+ ack_timeout_cnt = 1;
+ if (--count < 0)
+ goto error_timeout;
+ d_printf(4, dev, "device reboot: reboot command [%d # left]\n",
+ count);
+ if ((flags & I2400M_BRI_NO_REBOOT) == 0)
+ i2400m_reset(i2400m, I2400M_RT_WARM);
+ result = i2400m_bm_cmd(i2400m, NULL, 0, &ack, sizeof(ack),
+ I2400M_BM_CMD_RAW);
+ flags &= ~I2400M_BRI_NO_REBOOT;
+ switch (result) {
+ case -ERESTARTSYS:
+ /*
+ * at this point, i2400m_bm_cmd(), through
+ * __i2400m_bm_ack_process(), has updated
+ * i2400m->barker and we are good to go.
+ */
+ d_printf(4, dev, "device reboot: got reboot barker\n");
+ break;
+ case -EISCONN: /* we don't know how it got here...but we follow it */
+ d_printf(4, dev, "device reboot: got ack barker - whatever\n");
+ goto do_reboot;
+ case -ETIMEDOUT:
+ /*
+ * Device has timed out, we might be in boot mode
+ * already and expecting an ack; if we don't know what
+ * the barker is, we just send them all. Cold reset
+ * and bus reset don't work. Beats me.
+ */
+ if (i2400m->barker != NULL) {
+ dev_err(dev, "device boot: reboot barker timed out, "
+ "trying (set) %08x echo/ack\n",
+ le32_to_cpu(i2400m->barker->data[0]));
+ goto do_reboot_ack;
+ }
+ for (i = 0; i < i2400m_barker_db_used; i++) {
+ struct i2400m_barker_db *barker = &i2400m_barker_db[i];
+ memcpy(cmd, barker->data, sizeof(barker->data));
+ result = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
+ &ack, sizeof(ack),
+ I2400M_BM_CMD_RAW);
+ if (result == -EISCONN) {
+ dev_warn(dev, "device boot: got ack barker "
+ "after sending echo/ack barker "
+ "#%d/%08x; rebooting j.i.c.\n",
+ i, le32_to_cpu(barker->data[0]));
+ flags &= ~I2400M_BRI_NO_REBOOT;
+ goto do_reboot;
+ }
+ }
+ dev_err(dev, "device boot: tried all the echo/acks, could "
+ "not get device to respond; giving up");
+ result = -ESHUTDOWN;
+ case -EPROTO:
+ case -ESHUTDOWN: /* dev is gone */
+ case -EINTR: /* user cancelled */
+ goto error_dev_gone;
+ default:
+ dev_err(dev, "device reboot: error %d while waiting "
+ "for reboot barker - rebooting\n", result);
+ d_dump(1, dev, &ack, result);
+ goto do_reboot;
+ }
+ /* At this point we ack back with 4 REBOOT barkers and expect
+ * 4 ACK barkers. This is ugly, as we send a raw command --
+ * hence the cast. _bm_cmd() will catch the reboot ack
+ * notification and report it as -EISCONN. */
+do_reboot_ack:
+ d_printf(4, dev, "device reboot ack: sending ack [%d # left]\n", count);
+ memcpy(cmd, i2400m->barker->data, sizeof(i2400m->barker->data));
+ result = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
+ &ack, sizeof(ack), I2400M_BM_CMD_RAW);
+ switch (result) {
+ case -ERESTARTSYS:
+ d_printf(4, dev, "reboot ack: got reboot barker - retrying\n");
+ if (--count < 0)
+ goto error_timeout;
+ goto do_reboot_ack;
+ case -EISCONN:
+ d_printf(4, dev, "reboot ack: got ack barker - good\n");
+ break;
+ case -ETIMEDOUT: /* no response, maybe it is the other type? */
+ if (ack_timeout_cnt-- < 0) {
+ d_printf(4, dev, "reboot ack timedout: retrying\n");
+ goto do_reboot_ack;
+ } else {
+ dev_err(dev, "reboot ack timedout too long: "
+ "trying reboot\n");
+ goto do_reboot;
+ }
+ break;
+ case -EPROTO:
+ case -ESHUTDOWN: /* dev is gone */
+ goto error_dev_gone;
+ default:
+ dev_err(dev, "device reboot ack: error %d while waiting for "
+ "reboot ack barker - rebooting\n", result);
+ goto do_reboot;
+ }
+ d_printf(2, dev, "device reboot ack: got ack barker - boot done\n");
+ result = 0;
+exit_timeout:
+error_dev_gone:
+ d_fnend(4, dev, "(i2400m %p flags 0x%08x) = %d\n",
+ i2400m, flags, result);
+ return result;
+
+error_timeout:
+ dev_err(dev, "Timed out waiting for reboot ack\n");
+ result = -ETIMEDOUT;
+ goto exit_timeout;
+}
+
+
+/*
+ * Read the MAC addr
+ *
+ * The position this function reads is fixed in device memory and
+ * always available, even without firmware.
+ *
+ * Note we specify we want to read only six bytes, but provide space
+ * for 16, as we always get it rounded up.
+ */
+int i2400m_read_mac_addr(struct i2400m *i2400m)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+ struct i2400m_bootrom_header *cmd;
+ struct {
+ struct i2400m_bootrom_header ack;
+ u8 ack_pl[16];
+ } __packed ack_buf;
+
+ d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
+ cmd = i2400m->bm_cmd_buf;
+ cmd->command = i2400m_brh_command(I2400M_BRH_READ, 0, 1);
+ cmd->target_addr = cpu_to_le32(0x00203fe8);
+ cmd->data_size = cpu_to_le32(6);
+ result = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
+ &ack_buf.ack, sizeof(ack_buf), 0);
+ if (result < 0) {
+ dev_err(dev, "BM: read mac addr failed: %d\n", result);
+ goto error_read_mac;
+ }
+ d_printf(2, dev, "mac addr is %pM\n", ack_buf.ack_pl);
+ if (i2400m->bus_bm_mac_addr_impaired == 1) {
+ ack_buf.ack_pl[0] = 0x00;
+ ack_buf.ack_pl[1] = 0x16;
+ ack_buf.ack_pl[2] = 0xd3;
+ get_random_bytes(&ack_buf.ack_pl[3], 3);
+ dev_err(dev, "BM is MAC addr impaired, faking MAC addr to "
+ "mac addr is %pM\n", ack_buf.ack_pl);
+ result = 0;
+ }
+ net_dev->addr_len = ETH_ALEN;
+ memcpy(net_dev->dev_addr, ack_buf.ack_pl, ETH_ALEN);
+error_read_mac:
+ d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, result);
+ return result;
+}
+
+
+/*
+ * Initialize a non signed boot
+ *
+ * This implies sending some magic values to the device's memory. Note
+ * we convert the values to little endian in the same array
+ * declaration.
+ */
+static
+int i2400m_dnload_init_nonsigned(struct i2400m *i2400m)
+{
+ unsigned i = 0;
+ int ret = 0;
+ struct device *dev = i2400m_dev(i2400m);
+ d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
+ if (i2400m->bus_bm_pokes_table) {
+ while (i2400m->bus_bm_pokes_table[i].address) {
+ ret = i2400m_download_chunk(
+ i2400m,
+ &i2400m->bus_bm_pokes_table[i].data,
+ sizeof(i2400m->bus_bm_pokes_table[i].data),
+ i2400m->bus_bm_pokes_table[i].address, 1, 1);
+ if (ret < 0)
+ break;
+ i++;
+ }
+ }
+ d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, ret);
+ return ret;
+}
+
+
+/*
+ * Initialize the signed boot process
+ *
+ * @i2400m: device descriptor
+ *
+ * @bcf_hdr: pointer to the firmware header; assumes it is fully in
+ * memory (it has gone through basic validation).
+ *
+ * Returns: 0 if ok, < 0 errno code on error, -ERESTARTSYS if the hw
+ * rebooted.
+ *
+ * This writes the firmware BCF header to the device using the
+ * HASH_PAYLOAD_ONLY command.
+ */
+static
+int i2400m_dnload_init_signed(struct i2400m *i2400m,
+ const struct i2400m_bcf_hdr *bcf_hdr)
+{
+ int ret;
+ struct device *dev = i2400m_dev(i2400m);
+ struct {
+ struct i2400m_bootrom_header cmd;
+ struct i2400m_bcf_hdr cmd_pl;
+ } __packed *cmd_buf;
+ struct i2400m_bootrom_header ack;
+
+ d_fnstart(5, dev, "(i2400m %p bcf_hdr %p)\n", i2400m, bcf_hdr);
+ cmd_buf = i2400m->bm_cmd_buf;
+ cmd_buf->cmd.command =
+ i2400m_brh_command(I2400M_BRH_HASH_PAYLOAD_ONLY, 0, 0);
+ cmd_buf->cmd.target_addr = 0;
+ cmd_buf->cmd.data_size = cpu_to_le32(sizeof(cmd_buf->cmd_pl));
+ memcpy(&cmd_buf->cmd_pl, bcf_hdr, sizeof(*bcf_hdr));
+ ret = i2400m_bm_cmd(i2400m, &cmd_buf->cmd, sizeof(*cmd_buf),
+ &ack, sizeof(ack), 0);
+ if (ret >= 0)
+ ret = 0;
+ d_fnend(5, dev, "(i2400m %p bcf_hdr %p) = %d\n", i2400m, bcf_hdr, ret);
+ return ret;
+}
+
+
+/*
+ * Initialize the firmware download at the device size
+ *
+ * Multiplex to the one that matters based on the device's mode
+ * (signed or non-signed).
+ */
+static
+int i2400m_dnload_init(struct i2400m *i2400m,
+ const struct i2400m_bcf_hdr *bcf_hdr)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+
+ if (i2400m_boot_is_signed(i2400m)) {
+ d_printf(1, dev, "signed boot\n");
+ result = i2400m_dnload_init_signed(i2400m, bcf_hdr);
+ if (result == -ERESTARTSYS)
+ return result;
+ if (result < 0)
+ dev_err(dev, "firmware %s: signed boot download "
+ "initialization failed: %d\n",
+ i2400m->fw_name, result);
+ } else {
+ /* non-signed boot process without pokes */
+ d_printf(1, dev, "non-signed boot\n");
+ result = i2400m_dnload_init_nonsigned(i2400m);
+ if (result == -ERESTARTSYS)
+ return result;
+ if (result < 0)
+ dev_err(dev, "firmware %s: non-signed download "
+ "initialization failed: %d\n",
+ i2400m->fw_name, result);
+ }
+ return result;
+}
+
+
+/*
+ * Run consistency tests on the firmware file and load up headers
+ *
+ * Check for the firmware being made for the i2400m device,
+ * etc...These checks are mostly informative, as the device will make
+ * them too; but the driver's response is more informative on what
+ * went wrong.
+ *
+ * This will also look at all the headers present on the firmware
+ * file, and update i2400m->fw_bcf_hdr to point to them.
+ */
+static
+int i2400m_fw_hdr_check(struct i2400m *i2400m,
+ const struct i2400m_bcf_hdr *bcf_hdr,
+ size_t index, size_t offset)
+{
+ struct device *dev = i2400m_dev(i2400m);
+
+ unsigned module_type, header_len, major_version, minor_version,
+ module_id, module_vendor, date, size;
+
+ module_type = le32_to_cpu(bcf_hdr->module_type);
+ header_len = sizeof(u32) * le32_to_cpu(bcf_hdr->header_len);
+ major_version = (le32_to_cpu(bcf_hdr->header_version) & 0xffff0000)
+ >> 16;
+ minor_version = le32_to_cpu(bcf_hdr->header_version) & 0x0000ffff;
+ module_id = le32_to_cpu(bcf_hdr->module_id);
+ module_vendor = le32_to_cpu(bcf_hdr->module_vendor);
+ date = le32_to_cpu(bcf_hdr->date);
+ size = sizeof(u32) * le32_to_cpu(bcf_hdr->size);
+
+ d_printf(1, dev, "firmware %s #%zd@%08zx: BCF header "
+ "type:vendor:id 0x%x:%x:%x v%u.%u (%u/%u B) built %08x\n",
+ i2400m->fw_name, index, offset,
+ module_type, module_vendor, module_id,
+ major_version, minor_version, header_len, size, date);
+
+ /* Hard errors */
+ if (major_version != 1) {
+ dev_err(dev, "firmware %s #%zd@%08zx: major header version "
+ "v%u.%u not supported\n",
+ i2400m->fw_name, index, offset,
+ major_version, minor_version);
+ return -EBADF;
+ }
+
+ if (module_type != 6) { /* built for the right hardware? */
+ dev_err(dev, "firmware %s #%zd@%08zx: unexpected module "
+ "type 0x%x; aborting\n",
+ i2400m->fw_name, index, offset,
+ module_type);
+ return -EBADF;
+ }
+
+ if (module_vendor != 0x8086) {
+ dev_err(dev, "firmware %s #%zd@%08zx: unexpected module "
+ "vendor 0x%x; aborting\n",
+ i2400m->fw_name, index, offset, module_vendor);
+ return -EBADF;
+ }
+
+ if (date < 0x20080300)
+ dev_warn(dev, "firmware %s #%zd@%08zx: build date %08x "
+ "too old; unsupported\n",
+ i2400m->fw_name, index, offset, date);
+ return 0;
+}
+
+
+/*
+ * Run consistency tests on the firmware file and load up headers
+ *
+ * Check for the firmware being made for the i2400m device,
+ * etc...These checks are mostly informative, as the device will make
+ * them too; but the driver's response is more informative on what
+ * went wrong.
+ *
+ * This will also look at all the headers present on the firmware
+ * file, and update i2400m->fw_hdrs to point to them.
+ */
+static
+int i2400m_fw_check(struct i2400m *i2400m, const void *bcf, size_t bcf_size)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ size_t headers = 0;
+ const struct i2400m_bcf_hdr *bcf_hdr;
+ const void *itr, *next, *top;
+ size_t slots = 0, used_slots = 0;
+
+ for (itr = bcf, top = itr + bcf_size;
+ itr < top;
+ headers++, itr = next) {
+ size_t leftover, offset, header_len, size;
+
+ leftover = top - itr;
+ offset = itr - bcf;
+ if (leftover <= sizeof(*bcf_hdr)) {
+ dev_err(dev, "firmware %s: %zu B left at @%zx, "
+ "not enough for BCF header\n",
+ i2400m->fw_name, leftover, offset);
+ break;
+ }
+ bcf_hdr = itr;
+ /* Only the first header is supposed to be followed by
+ * payload */
+ header_len = sizeof(u32) * le32_to_cpu(bcf_hdr->header_len);
+ size = sizeof(u32) * le32_to_cpu(bcf_hdr->size);
+ if (headers == 0)
+ next = itr + size;
+ else
+ next = itr + header_len;
+
+ result = i2400m_fw_hdr_check(i2400m, bcf_hdr, headers, offset);
+ if (result < 0)
+ continue;
+ if (used_slots + 1 >= slots) {
+ /* +1 -> we need to account for the one we'll
+ * occupy and at least an extra one for
+ * always being NULL */
+ result = i2400m_zrealloc_2x(
+ (void **) &i2400m->fw_hdrs, &slots,
+ sizeof(i2400m->fw_hdrs[0]),
+ GFP_KERNEL);
+ if (result < 0)
+ goto error_zrealloc;
+ }
+ i2400m->fw_hdrs[used_slots] = bcf_hdr;
+ used_slots++;
+ }
+ if (headers == 0) {
+ dev_err(dev, "firmware %s: no usable headers found\n",
+ i2400m->fw_name);
+ result = -EBADF;
+ } else
+ result = 0;
+error_zrealloc:
+ return result;
+}
+
+
+/*
+ * Match a barker to a BCF header module ID
+ *
+ * The device sends a barker which tells the firmware loader which
+ * header in the BCF file has to be used. This does the matching.
+ */
+static
+unsigned i2400m_bcf_hdr_match(struct i2400m *i2400m,
+ const struct i2400m_bcf_hdr *bcf_hdr)
+{
+ u32 barker = le32_to_cpu(i2400m->barker->data[0])
+ & 0x7fffffff;
+ u32 module_id = le32_to_cpu(bcf_hdr->module_id)
+ & 0x7fffffff; /* high bit used for something else */
+
+ /* special case for 5x50 */
+ if (barker == I2400M_SBOOT_BARKER && module_id == 0)
+ return 1;
+ if (module_id == barker)
+ return 1;
+ return 0;
+}
+
+static
+const struct i2400m_bcf_hdr *i2400m_bcf_hdr_find(struct i2400m *i2400m)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ const struct i2400m_bcf_hdr **bcf_itr, *bcf_hdr;
+ unsigned i = 0;
+ u32 barker = le32_to_cpu(i2400m->barker->data[0]);
+
+ d_printf(2, dev, "finding BCF header for barker %08x\n", barker);
+ if (barker == I2400M_NBOOT_BARKER) {
+ bcf_hdr = i2400m->fw_hdrs[0];
+ d_printf(1, dev, "using BCF header #%u/%08x for non-signed "
+ "barker\n", 0, le32_to_cpu(bcf_hdr->module_id));
+ return bcf_hdr;
+ }
+ for (bcf_itr = i2400m->fw_hdrs; *bcf_itr != NULL; bcf_itr++, i++) {
+ bcf_hdr = *bcf_itr;
+ if (i2400m_bcf_hdr_match(i2400m, bcf_hdr)) {
+ d_printf(1, dev, "hit on BCF hdr #%u/%08x\n",
+ i, le32_to_cpu(bcf_hdr->module_id));
+ return bcf_hdr;
+ } else
+ d_printf(1, dev, "miss on BCF hdr #%u/%08x\n",
+ i, le32_to_cpu(bcf_hdr->module_id));
+ }
+ dev_err(dev, "cannot find a matching BCF header for barker %08x\n",
+ barker);
+ return NULL;
+}
+
+
+/*
+ * Download the firmware to the device
+ *
+ * @i2400m: device descriptor
+ * @bcf: pointer to loaded (and minimally verified for consistency)
+ * firmware
+ * @bcf_size: size of the @bcf buffer (header plus payloads)
+ *
+ * The process for doing this is described in this file's header.
+ *
+ * Note we only reinitialize boot-mode if the flags say so. Some hw
+ * iterations need it, some don't. In any case, if we loop, we always
+ * need to reinitialize the boot room, hence the flags modification.
+ */
+static
+int i2400m_fw_dnload(struct i2400m *i2400m, const struct i2400m_bcf_hdr *bcf,
+ size_t fw_size, enum i2400m_bri flags)
+{
+ int ret = 0;
+ struct device *dev = i2400m_dev(i2400m);
+ int count = i2400m->bus_bm_retries;
+ const struct i2400m_bcf_hdr *bcf_hdr;
+ size_t bcf_size;
+
+ d_fnstart(5, dev, "(i2400m %p bcf %p fw size %zu)\n",
+ i2400m, bcf, fw_size);
+ i2400m->boot_mode = 1;
+ wmb(); /* Make sure other readers see it */
+hw_reboot:
+ if (count-- == 0) {
+ ret = -ERESTARTSYS;
+ dev_err(dev, "device rebooted too many times, aborting\n");
+ goto error_too_many_reboots;
+ }
+ if (flags & I2400M_BRI_MAC_REINIT) {
+ ret = i2400m_bootrom_init(i2400m, flags);
+ if (ret < 0) {
+ dev_err(dev, "bootrom init failed: %d\n", ret);
+ goto error_bootrom_init;
+ }
+ }
+ flags |= I2400M_BRI_MAC_REINIT;
+
+ /*
+ * Initialize the download, push the bytes to the device and
+ * then jump to the new firmware. Note @ret is passed with the
+ * offset of the jump instruction to _dnload_finalize()
+ *
+ * Note we need to use the BCF header in the firmware image
+ * that matches the barker that the device sent when it
+ * rebooted, so it has to be passed along.
+ */
+ ret = -EBADF;
+ bcf_hdr = i2400m_bcf_hdr_find(i2400m);
+ if (bcf_hdr == NULL)
+ goto error_bcf_hdr_find;
+
+ ret = i2400m_dnload_init(i2400m, bcf_hdr);
+ if (ret == -ERESTARTSYS)
+ goto error_dev_rebooted;
+ if (ret < 0)
+ goto error_dnload_init;
+
+ /*
+ * bcf_size refers to one header size plus the fw sections size
+ * indicated by the header,ie. if there are other extended headers
+ * at the tail, they are not counted
+ */
+ bcf_size = sizeof(u32) * le32_to_cpu(bcf_hdr->size);
+ ret = i2400m_dnload_bcf(i2400m, bcf, bcf_size);
+ if (ret == -ERESTARTSYS)
+ goto error_dev_rebooted;
+ if (ret < 0) {
+ dev_err(dev, "fw %s: download failed: %d\n",
+ i2400m->fw_name, ret);
+ goto error_dnload_bcf;
+ }
+
+ ret = i2400m_dnload_finalize(i2400m, bcf_hdr, bcf, ret);
+ if (ret == -ERESTARTSYS)
+ goto error_dev_rebooted;
+ if (ret < 0) {
+ dev_err(dev, "fw %s: "
+ "download finalization failed: %d\n",
+ i2400m->fw_name, ret);
+ goto error_dnload_finalize;
+ }
+
+ d_printf(2, dev, "fw %s successfully uploaded\n",
+ i2400m->fw_name);
+ i2400m->boot_mode = 0;
+ wmb(); /* Make sure i2400m_msg_to_dev() sees boot_mode */
+error_dnload_finalize:
+error_dnload_bcf:
+error_dnload_init:
+error_bcf_hdr_find:
+error_bootrom_init:
+error_too_many_reboots:
+ d_fnend(5, dev, "(i2400m %p bcf %p size %zu) = %d\n",
+ i2400m, bcf, fw_size, ret);
+ return ret;
+
+error_dev_rebooted:
+ dev_err(dev, "device rebooted, %d tries left\n", count);
+ /* we got the notification already, no need to wait for it again */
+ flags |= I2400M_BRI_SOFT;
+ goto hw_reboot;
+}
+
+static
+int i2400m_fw_bootstrap(struct i2400m *i2400m, const struct firmware *fw,
+ enum i2400m_bri flags)
+{
+ int ret;
+ struct device *dev = i2400m_dev(i2400m);
+ const struct i2400m_bcf_hdr *bcf; /* Firmware data */
+
+ d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
+ bcf = (void *) fw->data;
+ ret = i2400m_fw_check(i2400m, bcf, fw->size);
+ if (ret >= 0)
+ ret = i2400m_fw_dnload(i2400m, bcf, fw->size, flags);
+ if (ret < 0)
+ dev_err(dev, "%s: cannot use: %d, skipping\n",
+ i2400m->fw_name, ret);
+ kfree(i2400m->fw_hdrs);
+ i2400m->fw_hdrs = NULL;
+ d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, ret);
+ return ret;
+}
+
+
+/* Refcounted container for firmware data */
+struct i2400m_fw {
+ struct kref kref;
+ const struct firmware *fw;
+};
+
+
+static
+void i2400m_fw_destroy(struct kref *kref)
+{
+ struct i2400m_fw *i2400m_fw =
+ container_of(kref, struct i2400m_fw, kref);
+ release_firmware(i2400m_fw->fw);
+ kfree(i2400m_fw);
+}
+
+
+static
+struct i2400m_fw *i2400m_fw_get(struct i2400m_fw *i2400m_fw)
+{
+ if (i2400m_fw != NULL && i2400m_fw != (void *) ~0)
+ kref_get(&i2400m_fw->kref);
+ return i2400m_fw;
+}
+
+
+static
+void i2400m_fw_put(struct i2400m_fw *i2400m_fw)
+{
+ kref_put(&i2400m_fw->kref, i2400m_fw_destroy);
+}
+
+
+/**
+ * i2400m_dev_bootstrap - Bring the device to a known state and upload firmware
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: >= 0 if ok, < 0 errno code on error.
+ *
+ * This sets up the firmware upload environment, loads the firmware
+ * file from disk, verifies and then calls the firmware upload process
+ * per se.
+ *
+ * Can be called either from probe, or after a warm reset. Can not be
+ * called from within an interrupt. All the flow in this code is
+ * single-threade; all I/Os are synchronous.
+ */
+int i2400m_dev_bootstrap(struct i2400m *i2400m, enum i2400m_bri flags)
+{
+ int ret, itr;
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400m_fw *i2400m_fw;
+ const struct firmware *fw;
+ const char *fw_name;
+
+ d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
+
+ ret = -ENODEV;
+ spin_lock(&i2400m->rx_lock);
+ i2400m_fw = i2400m_fw_get(i2400m->fw_cached);
+ spin_unlock(&i2400m->rx_lock);
+ if (i2400m_fw == (void *) ~0) {
+ dev_err(dev, "can't load firmware now!");
+ goto out;
+ } else if (i2400m_fw != NULL) {
+ dev_info(dev, "firmware %s: loading from cache\n",
+ i2400m->fw_name);
+ ret = i2400m_fw_bootstrap(i2400m, i2400m_fw->fw, flags);
+ i2400m_fw_put(i2400m_fw);
+ goto out;
+ }
+
+ /* Load firmware files to memory. */
+ for (itr = 0, ret = -ENOENT; ; itr++) {
+ fw_name = i2400m->bus_fw_names[itr];
+ if (fw_name == NULL) {
+ dev_err(dev, "Could not find a usable firmware image\n");
+ break;
+ }
+ d_printf(1, dev, "trying firmware %s (%d)\n", fw_name, itr);
+ ret = request_firmware(&fw, fw_name, dev);
+ if (ret < 0) {
+ dev_err(dev, "fw %s: cannot load file: %d\n",
+ fw_name, ret);
+ continue;
+ }
+ i2400m->fw_name = fw_name;
+ ret = i2400m_fw_bootstrap(i2400m, fw, flags);
+ release_firmware(fw);
+ if (ret >= 0) /* firmware loaded successfully */
+ break;
+ i2400m->fw_name = NULL;
+ }
+out:
+ d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, ret);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(i2400m_dev_bootstrap);
+
+
+void i2400m_fw_cache(struct i2400m *i2400m)
+{
+ int result;
+ struct i2400m_fw *i2400m_fw;
+ struct device *dev = i2400m_dev(i2400m);
+
+ /* if there is anything there, free it -- now, this'd be weird */
+ spin_lock(&i2400m->rx_lock);
+ i2400m_fw = i2400m->fw_cached;
+ spin_unlock(&i2400m->rx_lock);
+ if (i2400m_fw != NULL && i2400m_fw != (void *) ~0) {
+ i2400m_fw_put(i2400m_fw);
+ WARN(1, "%s:%u: still cached fw still present?\n",
+ __func__, __LINE__);
+ }
+
+ if (i2400m->fw_name == NULL) {
+ dev_err(dev, "firmware n/a: can't cache\n");
+ i2400m_fw = (void *) ~0;
+ goto out;
+ }
+
+ i2400m_fw = kzalloc(sizeof(*i2400m_fw), GFP_ATOMIC);
+ if (i2400m_fw == NULL)
+ goto out;
+ kref_init(&i2400m_fw->kref);
+ result = request_firmware(&i2400m_fw->fw, i2400m->fw_name, dev);
+ if (result < 0) {
+ dev_err(dev, "firmware %s: failed to cache: %d\n",
+ i2400m->fw_name, result);
+ kfree(i2400m_fw);
+ i2400m_fw = (void *) ~0;
+ } else
+ dev_info(dev, "firmware %s: cached\n", i2400m->fw_name);
+out:
+ spin_lock(&i2400m->rx_lock);
+ i2400m->fw_cached = i2400m_fw;
+ spin_unlock(&i2400m->rx_lock);
+}
+
+
+void i2400m_fw_uncache(struct i2400m *i2400m)
+{
+ struct i2400m_fw *i2400m_fw;
+
+ spin_lock(&i2400m->rx_lock);
+ i2400m_fw = i2400m->fw_cached;
+ i2400m->fw_cached = NULL;
+ spin_unlock(&i2400m->rx_lock);
+
+ if (i2400m_fw != NULL && i2400m_fw != (void *) ~0)
+ i2400m_fw_put(i2400m_fw);
+}
+
--- /dev/null
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * USB-specific i2400m driver definitions
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * - Initial implementation
+ *
+ *
+ * This driver implements the bus-specific part of the i2400m for
+ * USB. Check i2400m.h for a generic driver description.
+ *
+ * ARCHITECTURE
+ *
+ * This driver listens to notifications sent from the notification
+ * endpoint (in usb-notif.c); when data is ready to read, the code in
+ * there schedules a read from the device (usb-rx.c) and then passes
+ * the data to the generic RX code (rx.c).
+ *
+ * When the generic driver needs to send data (network or control), it
+ * queues up in the TX FIFO (tx.c) and that will notify the driver
+ * through the i2400m->bus_tx_kick() callback
+ * (usb-tx.c:i2400mu_bus_tx_kick) which will send the items in the
+ * FIFO queue.
+ *
+ * This driver, as well, implements the USB-specific ops for the generic
+ * driver to be able to setup/teardown communication with the device
+ * [i2400m_bus_dev_start() and i2400m_bus_dev_stop()], reseting the
+ * device [i2400m_bus_reset()] and performing firmware upload
+ * [i2400m_bus_bm_cmd() and i2400_bus_bm_wait_for_ack()].
+ */
+
+#ifndef __I2400M_USB_H__
+#define __I2400M_USB_H__
+
+#include "i2400m.h"
+#include <linux/kthread.h>
+
+
+/*
+ * Error Density Count: cheapo error density (over time) counter
+ *
+ * Originally by Reinette Chatre <reinette.chatre@intel.com>
+ *
+ * Embed an 'struct edc' somewhere. Each time there is a soft or
+ * retryable error, call edc_inc() and check if the error top
+ * watermark has been reached.
+ */
+enum {
+ EDC_MAX_ERRORS = 10,
+ EDC_ERROR_TIMEFRAME = HZ,
+};
+
+/* error density counter */
+struct edc {
+ unsigned long timestart;
+ u16 errorcount;
+};
+
+struct i2400m_endpoint_cfg {
+ unsigned char bulk_out;
+ unsigned char notification;
+ unsigned char reset_cold;
+ unsigned char bulk_in;
+};
+
+static inline void edc_init(struct edc *edc)
+{
+ edc->timestart = jiffies;
+}
+
+/**
+ * edc_inc - report a soft error and check if we are over the watermark
+ *
+ * @edc: pointer to error density counter.
+ * @max_err: maximum number of errors we can accept over the timeframe
+ * @timeframe: length of the timeframe (in jiffies).
+ *
+ * Returns: !0 1 if maximum acceptable errors per timeframe has been
+ * exceeded. 0 otherwise.
+ *
+ * This is way to determine if the number of acceptable errors per time
+ * period has been exceeded. It is not accurate as there are cases in which
+ * this scheme will not work, for example if there are periodic occurrences
+ * of errors that straddle updates to the start time. This scheme is
+ * sufficient for our usage.
+ *
+ * To use, embed a 'struct edc' somewhere, initialize it with
+ * edc_init() and when an error hits:
+ *
+ * if (do_something_fails_with_a_soft_error) {
+ * if (edc_inc(&my->edc, MAX_ERRORS, MAX_TIMEFRAME))
+ * Ops, hard error, do something about it
+ * else
+ * Retry or ignore, depending on whatever
+ * }
+ */
+static inline int edc_inc(struct edc *edc, u16 max_err, u16 timeframe)
+{
+ unsigned long now;
+
+ now = jiffies;
+ if (time_after(now, edc->timestart + timeframe)) {
+ edc->errorcount = 1;
+ edc->timestart = now;
+ } else if (++edc->errorcount > max_err) {
+ edc->errorcount = 0;
+ edc->timestart = now;
+ return 1;
+ }
+ return 0;
+}
+
+/* Host-Device interface for USB */
+enum {
+ I2400M_USB_BOOT_RETRIES = 3,
+ I2400MU_MAX_NOTIFICATION_LEN = 256,
+ I2400MU_BLK_SIZE = 16,
+ I2400MU_PL_SIZE_MAX = 0x3EFF,
+
+ /* Device IDs */
+ USB_DEVICE_ID_I6050 = 0x0186,
+ USB_DEVICE_ID_I6050_2 = 0x0188,
+ USB_DEVICE_ID_I6150 = 0x07d6,
+ USB_DEVICE_ID_I6150_2 = 0x07d7,
+ USB_DEVICE_ID_I6150_3 = 0x07d9,
+ USB_DEVICE_ID_I6250 = 0x0187,
+};
+
+
+/**
+ * struct i2400mu - descriptor for a USB connected i2400m
+ *
+ * @i2400m: bus-generic i2400m implementation; has to be first (see
+ * it's documentation in i2400m.h).
+ *
+ * @usb_dev: pointer to our USB device
+ *
+ * @usb_iface: pointer to our USB interface
+ *
+ * @urb_edc: error density counter; used to keep a density-on-time tab
+ * on how many soft (retryable or ignorable) errors we get. If we
+ * go over the threshold, we consider the bus transport is failing
+ * too much and reset.
+ *
+ * @notif_urb: URB for receiving notifications from the device.
+ *
+ * @tx_kthread: thread we use for data TX. We use a thread because in
+ * order to do deep power saving and put the device to sleep, we
+ * need to call usb_autopm_*() [blocking functions].
+ *
+ * @tx_wq: waitqueue for the TX kthread to sleep when there is no data
+ * to be sent; when more data is available, it is woken up by
+ * i2400mu_bus_tx_kick().
+ *
+ * @rx_kthread: thread we use for data RX. We use a thread because in
+ * order to do deep power saving and put the device to sleep, we
+ * need to call usb_autopm_*() [blocking functions].
+ *
+ * @rx_wq: waitqueue for the RX kthread to sleep when there is no data
+ * to receive. When data is available, it is woken up by
+ * usb-notif.c:i2400mu_notification_grok().
+ *
+ * @rx_pending_count: number of rx-data-ready notifications that were
+ * still not handled by the RX kthread.
+ *
+ * @rx_size: current RX buffer size that is being used.
+ *
+ * @rx_size_acc: accumulator of the sizes of the previous read
+ * transactions.
+ *
+ * @rx_size_cnt: number of read transactions accumulated in
+ * @rx_size_acc.
+ *
+ * @do_autopm: disable(0)/enable(>0) calling the
+ * usb_autopm_get/put_interface() barriers when executing
+ * commands. See doc in i2400mu_suspend() for more information.
+ *
+ * @rx_size_auto_shrink: if true, the rx_size is shrunk
+ * automatically based on the average size of the received
+ * transactions. This allows the receive code to allocate smaller
+ * chunks of memory and thus reduce pressure on the memory
+ * allocator by not wasting so much space. By default it is
+ * enabled.
+ *
+ * @debugfs_dentry: hookup for debugfs files.
+ * These have to be in a separate directory, a child of
+ * (wimax_dev->debugfs_dentry) so they can be removed when the
+ * module unloads, as we don't keep each dentry.
+ */
+struct i2400mu {
+ struct i2400m i2400m; /* FIRST! See doc */
+
+ struct usb_device *usb_dev;
+ struct usb_interface *usb_iface;
+ struct edc urb_edc; /* Error density counter */
+ struct i2400m_endpoint_cfg endpoint_cfg;
+
+ struct urb *notif_urb;
+ struct task_struct *tx_kthread;
+ wait_queue_head_t tx_wq;
+
+ struct task_struct *rx_kthread;
+ wait_queue_head_t rx_wq;
+ atomic_t rx_pending_count;
+ size_t rx_size, rx_size_acc, rx_size_cnt;
+ atomic_t do_autopm;
+ u8 rx_size_auto_shrink;
+
+ struct dentry *debugfs_dentry;
+ unsigned i6050:1; /* 1 if this is a 6050 based SKU */
+};
+
+
+static inline
+void i2400mu_init(struct i2400mu *i2400mu)
+{
+ i2400m_init(&i2400mu->i2400m);
+ edc_init(&i2400mu->urb_edc);
+ init_waitqueue_head(&i2400mu->tx_wq);
+ atomic_set(&i2400mu->rx_pending_count, 0);
+ init_waitqueue_head(&i2400mu->rx_wq);
+ i2400mu->rx_size = PAGE_SIZE - sizeof(struct skb_shared_info);
+ atomic_set(&i2400mu->do_autopm, 1);
+ i2400mu->rx_size_auto_shrink = 1;
+}
+
+int i2400mu_notification_setup(struct i2400mu *);
+void i2400mu_notification_release(struct i2400mu *);
+
+int i2400mu_rx_setup(struct i2400mu *);
+void i2400mu_rx_release(struct i2400mu *);
+void i2400mu_rx_kick(struct i2400mu *);
+
+int i2400mu_tx_setup(struct i2400mu *);
+void i2400mu_tx_release(struct i2400mu *);
+void i2400mu_bus_tx_kick(struct i2400m *);
+
+ssize_t i2400mu_bus_bm_cmd_send(struct i2400m *,
+ const struct i2400m_bootrom_header *, size_t,
+ int);
+ssize_t i2400mu_bus_bm_wait_for_ack(struct i2400m *,
+ struct i2400m_bootrom_header *, size_t);
+#endif /* #ifndef __I2400M_USB_H__ */
--- /dev/null
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Declarations for bus-generic internal APIs
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * - Initial implementation
+ *
+ *
+ * GENERAL DRIVER ARCHITECTURE
+ *
+ * The i2400m driver is split in the following two major parts:
+ *
+ * - bus specific driver
+ * - bus generic driver (this part)
+ *
+ * The bus specific driver sets up stuff specific to the bus the
+ * device is connected to (USB, PCI, tam-tam...non-authoritative
+ * nor binding list) which is basically the device-model management
+ * (probe/disconnect, etc), moving data from device to kernel and
+ * back, doing the power saving details and reseting the device.
+ *
+ * For details on each bus-specific driver, see it's include file,
+ * i2400m-BUSNAME.h
+ *
+ * The bus-generic functionality break up is:
+ *
+ * - Firmware upload: fw.c - takes care of uploading firmware to the
+ * device. bus-specific driver just needs to provides a way to
+ * execute boot-mode commands and to reset the device.
+ *
+ * - RX handling: rx.c - receives data from the bus-specific code and
+ * feeds it to the network or WiMAX stack or uses it to modify
+ * the driver state. bus-specific driver only has to receive
+ * frames and pass them to this module.
+ *
+ * - TX handling: tx.c - manages the TX FIFO queue and provides means
+ * for the bus-specific TX code to pull data from the FIFO
+ * queue. bus-specific code just pulls frames from this module
+ * to sends them to the device.
+ *
+ * - netdev glue: netdev.c - interface with Linux networking
+ * stack. Pass around data frames, and configure when the
+ * device is up and running or shutdown (through ifconfig up /
+ * down). Bus-generic only.
+ *
+ * - control ops: control.c - implements various commands for
+ * controlling the device. bus-generic only.
+ *
+ * - device model glue: driver.c - implements helpers for the
+ * device-model glue done by the bus-specific layer
+ * (setup/release the driver resources), turning the device on
+ * and off, handling the device reboots/resets and a few simple
+ * WiMAX stack ops.
+ *
+ * Code is also broken up in linux-glue / device-glue.
+ *
+ * Linux glue contains functions that deal mostly with gluing with the
+ * rest of the Linux kernel.
+ *
+ * Device-glue are functions that deal mostly with the way the device
+ * does things and talk the device's language.
+ *
+ * device-glue code is licensed BSD so other open source OSes can take
+ * it to implement their drivers.
+ *
+ *
+ * APIs AND HEADER FILES
+ *
+ * This bus generic code exports three APIs:
+ *
+ * - HDI (host-device interface) definitions common to all busses
+ * (include/linux/wimax/i2400m.h); these can be also used by user
+ * space code.
+ * - internal API for the bus-generic code
+ * - external API for the bus-specific drivers
+ *
+ *
+ * LIFE CYCLE:
+ *
+ * When the bus-specific driver probes, it allocates a network device
+ * with enough space for it's data structue, that must contain a
+ * &struct i2400m at the top.
+ *
+ * On probe, it needs to fill the i2400m members marked as [fill], as
+ * well as i2400m->wimax_dev.net_dev and call i2400m_setup(). The
+ * i2400m driver will only register with the WiMAX and network stacks;
+ * the only access done to the device is to read the MAC address so we
+ * can register a network device.
+ *
+ * The high-level call flow is:
+ *
+ * bus_probe()
+ * i2400m_setup()
+ * i2400m->bus_setup()
+ * boot rom initialization / read mac addr
+ * network / WiMAX stacks registration
+ * i2400m_dev_start()
+ * i2400m->bus_dev_start()
+ * i2400m_dev_initialize()
+ *
+ * The reverse applies for a disconnect() call:
+ *
+ * bus_disconnect()
+ * i2400m_release()
+ * i2400m_dev_stop()
+ * i2400m_dev_shutdown()
+ * i2400m->bus_dev_stop()
+ * network / WiMAX stack unregistration
+ * i2400m->bus_release()
+ *
+ * At this point, control and data communications are possible.
+ *
+ * While the device is up, it might reset. The bus-specific driver has
+ * to catch that situation and call i2400m_dev_reset_handle() to deal
+ * with it (reset the internal driver structures and go back to square
+ * one).
+ */
+
+#ifndef __I2400M_H__
+#define __I2400M_H__
+
+#include <linux/usb.h>
+#include <linux/netdevice.h>
+#include <linux/completion.h>
+#include <linux/rwsem.h>
+#include <linux/atomic.h>
+#include "../net-wimax.h"
+#include "linux-wimax-i2400m.h"
+#include <asm/byteorder.h>
+
+enum {
+/* netdev interface */
+ /*
+ * Out of NWG spec (R1_v1.2.2), 3.3.3 ASN Bearer Plane MTU Size
+ *
+ * The MTU is 1400 or less
+ */
+ I2400M_MAX_MTU = 1400,
+};
+
+/* Misc constants */
+enum {
+ /* Size of the Boot Mode Command buffer */
+ I2400M_BM_CMD_BUF_SIZE = 16 * 1024,
+ I2400M_BM_ACK_BUF_SIZE = 256,
+};
+
+enum {
+ /* Maximum number of bus reset can be retried */
+ I2400M_BUS_RESET_RETRIES = 3,
+};
+
+/**
+ * struct i2400m_poke_table - Hardware poke table for the Intel 2400m
+ *
+ * This structure will be used to create a device specific poke table
+ * to put the device in a consistent state at boot time.
+ *
+ * @address: The device address to poke
+ *
+ * @data: The data value to poke to the device address
+ *
+ */
+struct i2400m_poke_table{
+ __le32 address;
+ __le32 data;
+};
+
+#define I2400M_FW_POKE(a, d) { \
+ .address = cpu_to_le32(a), \
+ .data = cpu_to_le32(d) \
+}
+
+
+/**
+ * i2400m_reset_type - methods to reset a device
+ *
+ * @I2400M_RT_WARM: Reset without device disconnection, device handles
+ * are kept valid but state is back to power on, with firmware
+ * re-uploaded.
+ * @I2400M_RT_COLD: Tell the device to disconnect itself from the bus
+ * and reconnect. Renders all device handles invalid.
+ * @I2400M_RT_BUS: Tells the bus to reset the device; last measure
+ * used when both types above don't work.
+ */
+enum i2400m_reset_type {
+ I2400M_RT_WARM, /* first measure */
+ I2400M_RT_COLD, /* second measure */
+ I2400M_RT_BUS, /* call in artillery */
+};
+
+struct i2400m_reset_ctx;
+struct i2400m_roq;
+struct i2400m_barker_db;
+
+/**
+ * struct i2400m - descriptor for an Intel 2400m
+ *
+ * Members marked with [fill] must be filled out/initialized before
+ * calling i2400m_setup().
+ *
+ * Note the @bus_setup/@bus_release, @bus_dev_start/@bus_dev_release
+ * call pairs are very much doing almost the same, and depending on
+ * the underlying bus, some stuff has to be put in one or the
+ * other. The idea of setup/release is that they setup the minimal
+ * amount needed for loading firmware, where us dev_start/stop setup
+ * the rest needed to do full data/control traffic.
+ *
+ * @bus_tx_block_size: [fill] USB imposes a 16 block size, but other
+ * busses will differ. So we have a tx_blk_size variable that the
+ * bus layer sets to tell the engine how much of that we need.
+ *
+ * @bus_tx_room_min: [fill] Minimum room required while allocating
+ * TX queue's buffer space for message header. USB requires
+ * 16 bytes. Refer to bus specific driver code for details.
+ *
+ * @bus_pl_size_max: [fill] Maximum payload size.
+ *
+ * @bus_setup: [optional fill] Function called by the bus-generic code
+ * [i2400m_setup()] to setup the basic bus-specific communications
+ * to the the device needed to load firmware. See LIFE CYCLE above.
+ *
+ * NOTE: Doesn't need to upload the firmware, as that is taken
+ * care of by the bus-generic code.
+ *
+ * @bus_release: [optional fill] Function called by the bus-generic
+ * code [i2400m_release()] to shutdown the basic bus-specific
+ * communications to the the device needed to load firmware. See
+ * LIFE CYCLE above.
+ *
+ * This function does not need to reset the device, just tear down
+ * all the host resources created to handle communication with
+ * the device.
+ *
+ * @bus_dev_start: [optional fill] Function called by the bus-generic
+ * code [i2400m_dev_start()] to do things needed to start the
+ * device. See LIFE CYCLE above.
+ *
+ * NOTE: Doesn't need to upload the firmware, as that is taken
+ * care of by the bus-generic code.
+ *
+ * @bus_dev_stop: [optional fill] Function called by the bus-generic
+ * code [i2400m_dev_stop()] to do things needed for stopping the
+ * device. See LIFE CYCLE above.
+ *
+ * This function does not need to reset the device, just tear down
+ * all the host resources created to handle communication with
+ * the device.
+ *
+ * @bus_tx_kick: [fill] Function called by the bus-generic code to let
+ * the bus-specific code know that there is data available in the
+ * TX FIFO for transmission to the device.
+ *
+ * This function cannot sleep.
+ *
+ * @bus_reset: [fill] Function called by the bus-generic code to reset
+ * the device in in various ways. Doesn't need to wait for the
+ * reset to finish.
+ *
+ * If warm or cold reset fail, this function is expected to do a
+ * bus-specific reset (eg: USB reset) to get the device to a
+ * working state (even if it implies device disconecction).
+ *
+ * Note the warm reset is used by the firmware uploader to
+ * reinitialize the device.
+ *
+ * IMPORTANT: this is called very early in the device setup
+ * process, so it cannot rely on common infrastructure being laid
+ * out.
+ *
+ * IMPORTANT: don't call reset on RT_BUS with i2400m->init_mutex
+ * held, as the .pre/.post reset handlers will deadlock.
+ *
+ * @bus_bm_retries: [fill] How many times shall a firmware upload /
+ * device initialization be retried? Different models of the same
+ * device might need different values, hence it is set by the
+ * bus-specific driver. Note this value is used in two places,
+ * i2400m_fw_dnload() and __i2400m_dev_start(); they won't become
+ * multiplicative (__i2400m_dev_start() calling N times
+ * i2400m_fw_dnload() and this trying N times to download the
+ * firmware), as if __i2400m_dev_start() only retries if the
+ * firmware crashed while initializing the device (not in a
+ * general case).
+ *
+ * @bus_bm_cmd_send: [fill] Function called to send a boot-mode
+ * command. Flags are defined in 'enum i2400m_bm_cmd_flags'. This
+ * is synchronous and has to return 0 if ok or < 0 errno code in
+ * any error condition.
+ *
+ * @bus_bm_wait_for_ack: [fill] Function called to wait for a
+ * boot-mode notification (that can be a response to a previously
+ * issued command or an asynchronous one). Will read until all the
+ * indicated size is read or timeout. Reading more or less data
+ * than asked for is an error condition. Return 0 if ok, < 0 errno
+ * code on error.
+ *
+ * The caller to this function will check if the response is a
+ * barker that indicates the device going into reset mode.
+ *
+ * @bus_fw_names: [fill] a NULL-terminated array with the names of the
+ * firmware images to try loading. This is made a list so we can
+ * support backward compatibility of firmware releases (eg: if we
+ * can't find the default v1.4, we try v1.3). In general, the name
+ * should be i2400m-fw-X-VERSION.sbcf, where X is the bus name.
+ * The list is tried in order and the first one that loads is
+ * used. The fw loader will set i2400m->fw_name to point to the
+ * active firmware image.
+ *
+ * @bus_bm_mac_addr_impaired: [fill] Set to true if the device's MAC
+ * address provided in boot mode is kind of broken and needs to
+ * be re-read later on.
+ *
+ * @bus_bm_pokes_table: [fill/optional] A table of device addresses
+ * and values that will be poked at device init time to move the
+ * device to the correct state for the type of boot/firmware being
+ * used. This table MUST be terminated with (0x000000,
+ * 0x00000000) or bad things will happen.
+ *
+ *
+ * @wimax_dev: WiMAX generic device for linkage into the kernel WiMAX
+ * stack. Due to the way a net_device is allocated, we need to
+ * force this to be the first field so that we can get from
+ * netdev_priv() the right pointer.
+ *
+ * @updown: the device is up and ready for transmitting control and
+ * data packets. This implies @ready (communication infrastructure
+ * with the device is ready) and the device's firmware has been
+ * loaded and the device initialized.
+ *
+ * Write to it only inside a i2400m->init_mutex protected area
+ * followed with a wmb(); rmb() before accesing (unless locked
+ * inside i2400m->init_mutex). Read access can be loose like that
+ * [just using rmb()] because the paths that use this also do
+ * other error checks later on.
+ *
+ * @ready: Communication infrastructure with the device is ready, data
+ * frames can start to be passed around (this is lighter than
+ * using the WiMAX state for certain hot paths).
+ *
+ * Write to it only inside a i2400m->init_mutex protected area
+ * followed with a wmb(); rmb() before accesing (unless locked
+ * inside i2400m->init_mutex). Read access can be loose like that
+ * [just using rmb()] because the paths that use this also do
+ * other error checks later on.
+ *
+ * @rx_reorder: 1 if RX reordering is enabled; this can only be
+ * set at probe time.
+ *
+ * @state: device's state (as reported by it)
+ *
+ * @state_wq: waitqueue that is woken up whenever the state changes
+ *
+ * @tx_lock: spinlock to protect TX members
+ *
+ * @tx_buf: FIFO buffer for TX; we queue data here
+ *
+ * @tx_in: FIFO index for incoming data. Note this doesn't wrap around
+ * and it is always greater than @tx_out.
+ *
+ * @tx_out: FIFO index for outgoing data
+ *
+ * @tx_msg: current TX message that is active in the FIFO for
+ * appending payloads.
+ *
+ * @tx_sequence: current sequence number for TX messages from the
+ * device to the host.
+ *
+ * @tx_msg_size: size of the current message being transmitted by the
+ * bus-specific code.
+ *
+ * @tx_pl_num: total number of payloads sent
+ *
+ * @tx_pl_max: maximum number of payloads sent in a TX message
+ *
+ * @tx_pl_min: minimum number of payloads sent in a TX message
+ *
+ * @tx_num: number of TX messages sent
+ *
+ * @tx_size_acc: number of bytes in all TX messages sent
+ * (this is different to net_dev's statistics as it also counts
+ * control messages).
+ *
+ * @tx_size_min: smallest TX message sent.
+ *
+ * @tx_size_max: biggest TX message sent.
+ *
+ * @rx_lock: spinlock to protect RX members and rx_roq_refcount.
+ *
+ * @rx_pl_num: total number of payloads received
+ *
+ * @rx_pl_max: maximum number of payloads received in a RX message
+ *
+ * @rx_pl_min: minimum number of payloads received in a RX message
+ *
+ * @rx_num: number of RX messages received
+ *
+ * @rx_size_acc: number of bytes in all RX messages received
+ * (this is different to net_dev's statistics as it also counts
+ * control messages).
+ *
+ * @rx_size_min: smallest RX message received.
+ *
+ * @rx_size_max: buggest RX message received.
+ *
+ * @rx_roq: RX ReOrder queues. (fw >= v1.4) When packets are received
+ * out of order, the device will ask the driver to hold certain
+ * packets until the ones that are received out of order can be
+ * delivered. Then the driver can release them to the host. See
+ * drivers/net/i2400m/rx.c for details.
+ *
+ * @rx_roq_refcount: refcount rx_roq. This refcounts any access to
+ * rx_roq thus preventing rx_roq being destroyed when rx_roq
+ * is being accessed. rx_roq_refcount is protected by rx_lock.
+ *
+ * @rx_reports: reports received from the device that couldn't be
+ * processed because the driver wasn't still ready; when ready,
+ * they are pulled from here and chewed.
+ *
+ * @rx_reports_ws: Work struct used to kick a scan of the RX reports
+ * list and to process each.
+ *
+ * @src_mac_addr: MAC address used to make ethernet packets be coming
+ * from. This is generated at i2400m_setup() time and used during
+ * the life cycle of the instance. See i2400m_fake_eth_header().
+ *
+ * @init_mutex: Mutex used for serializing the device bringup
+ * sequence; this way if the device reboots in the middle, we
+ * don't try to do a bringup again while we are tearing down the
+ * one that failed.
+ *
+ * Can't reuse @msg_mutex because from within the bringup sequence
+ * we need to send messages to the device and thus use @msg_mutex.
+ *
+ * @msg_mutex: mutex used to send control commands to the device (we
+ * only allow one at a time, per host-device interface design).
+ *
+ * @msg_completion: used to wait for an ack to a control command sent
+ * to the device.
+ *
+ * @ack_skb: used to store the actual ack to a control command if the
+ * reception of the command was successful. Otherwise, a ERR_PTR()
+ * errno code that indicates what failed with the ack reception.
+ *
+ * Only valid after @msg_completion is woken up. Only updateable
+ * if @msg_completion is armed. Only touched by
+ * i2400m_msg_to_dev().
+ *
+ * Protected by @rx_lock. In theory the command execution flow is
+ * sequential, but in case the device sends an out-of-phase or
+ * very delayed response, we need to avoid it trampling current
+ * execution.
+ *
+ * @bm_cmd_buf: boot mode command buffer for composing firmware upload
+ * commands.
+ *
+ * USB can't r/w to stack, vmalloc, etc...as well, we end up
+ * having to alloc/free a lot to compose commands, so we use these
+ * for stagging and not having to realloc all the time.
+ *
+ * This assumes the code always runs serialized. Only one thread
+ * can call i2400m_bm_cmd() at the same time.
+ *
+ * @bm_ack_buf: boot mode acknoledge buffer for staging reception of
+ * responses to commands.
+ *
+ * See @bm_cmd_buf.
+ *
+ * @work_queue: work queue for processing device reports. This
+ * workqueue cannot be used for processing TX or RX to the device,
+ * as from it we'll process device reports, which might require
+ * further communication with the device.
+ *
+ * @debugfs_dentry: hookup for debugfs files.
+ * These have to be in a separate directory, a child of
+ * (wimax_dev->debugfs_dentry) so they can be removed when the
+ * module unloads, as we don't keep each dentry.
+ *
+ * @fw_name: name of the firmware image that is currently being used.
+ *
+ * @fw_version: version of the firmware interface, Major.minor,
+ * encoded in the high word and low word (major << 16 | minor).
+ *
+ * @fw_hdrs: NULL terminated array of pointers to the firmware
+ * headers. This is only available during firmware load time.
+ *
+ * @fw_cached: Used to cache firmware when the system goes to
+ * suspend/standby/hibernation (as on resume we can't read it). If
+ * NULL, no firmware was cached, read it. If ~0, you can't read
+ * any firmware files (the system still didn't come out of suspend
+ * and failed to cache one), so abort; otherwise, a valid cached
+ * firmware to be used. Access to this variable is protected by
+ * the spinlock i2400m->rx_lock.
+ *
+ * @barker: barker type that the device uses; this is initialized by
+ * i2400m_is_boot_barker() the first time it is called. Then it
+ * won't change during the life cycle of the device and every time
+ * a boot barker is received, it is just verified for it being the
+ * same.
+ *
+ * @pm_notifier: used to register for PM events
+ *
+ * @bus_reset_retries: counter for the number of bus resets attempted for
+ * this boot. It's not for tracking the number of bus resets during
+ * the whole driver life cycle (from insmod to rmmod) but for the
+ * number of dev_start() executed until dev_start() returns a success
+ * (ie: a good boot means a dev_stop() followed by a successful
+ * dev_start()). dev_reset_handler() increments this counter whenever
+ * it is triggering a bus reset. It checks this counter to decide if a
+ * subsequent bus reset should be retried. dev_reset_handler() retries
+ * the bus reset until dev_start() succeeds or the counter reaches
+ * I2400M_BUS_RESET_RETRIES. The counter is cleared to 0 in
+ * dev_reset_handle() when dev_start() returns a success,
+ * ie: a successul boot is completed.
+ *
+ * @alive: flag to denote if the device *should* be alive. This flag is
+ * everything like @updown (see doc for @updown) except reflecting
+ * the device state *we expect* rather than the actual state as denoted
+ * by @updown. It is set 1 whenever @updown is set 1 in dev_start().
+ * Then the device is expected to be alive all the time
+ * (i2400m->alive remains 1) until the driver is removed. Therefore
+ * all the device reboot events detected can be still handled properly
+ * by either dev_reset_handle() or .pre_reset/.post_reset as long as
+ * the driver presents. It is set 0 along with @updown in dev_stop().
+ *
+ * @error_recovery: flag to denote if we are ready to take an error recovery.
+ * 0 for ready to take an error recovery; 1 for not ready. It is
+ * initialized to 1 while probe() since we don't tend to take any error
+ * recovery during probe(). It is decremented by 1 whenever dev_start()
+ * succeeds to indicate we are ready to take error recovery from now on.
+ * It is checked every time we wanna schedule an error recovery. If an
+ * error recovery is already in place (error_recovery was set 1), we
+ * should not schedule another one until the last one is done.
+ */
+struct i2400m {
+ struct wimax_dev wimax_dev; /* FIRST! See doc */
+
+ unsigned updown:1; /* Network device is up or down */
+ unsigned boot_mode:1; /* is the device in boot mode? */
+ unsigned sboot:1; /* signed or unsigned fw boot */
+ unsigned ready:1; /* Device comm infrastructure ready */
+ unsigned rx_reorder:1; /* RX reorder is enabled */
+ u8 trace_msg_from_user; /* echo rx msgs to 'trace' pipe */
+ /* typed u8 so /sys/kernel/debug/u8 can tweak */
+ enum i2400m_system_state state;
+ wait_queue_head_t state_wq; /* Woken up when on state updates */
+
+ size_t bus_tx_block_size;
+ size_t bus_tx_room_min;
+ size_t bus_pl_size_max;
+ unsigned bus_bm_retries;
+
+ int (*bus_setup)(struct i2400m *);
+ int (*bus_dev_start)(struct i2400m *);
+ void (*bus_dev_stop)(struct i2400m *);
+ void (*bus_release)(struct i2400m *);
+ void (*bus_tx_kick)(struct i2400m *);
+ int (*bus_reset)(struct i2400m *, enum i2400m_reset_type);
+ ssize_t (*bus_bm_cmd_send)(struct i2400m *,
+ const struct i2400m_bootrom_header *,
+ size_t, int flags);
+ ssize_t (*bus_bm_wait_for_ack)(struct i2400m *,
+ struct i2400m_bootrom_header *, size_t);
+ const char **bus_fw_names;
+ unsigned bus_bm_mac_addr_impaired:1;
+ const struct i2400m_poke_table *bus_bm_pokes_table;
+
+ spinlock_t tx_lock; /* protect TX state */
+ void *tx_buf;
+ size_t tx_in, tx_out;
+ struct i2400m_msg_hdr *tx_msg;
+ size_t tx_sequence, tx_msg_size;
+ /* TX stats */
+ unsigned tx_pl_num, tx_pl_max, tx_pl_min,
+ tx_num, tx_size_acc, tx_size_min, tx_size_max;
+
+ /* RX stuff */
+ /* protect RX state and rx_roq_refcount */
+ spinlock_t rx_lock;
+ unsigned rx_pl_num, rx_pl_max, rx_pl_min,
+ rx_num, rx_size_acc, rx_size_min, rx_size_max;
+ struct i2400m_roq *rx_roq; /* access is refcounted */
+ struct kref rx_roq_refcount; /* refcount access to rx_roq */
+ u8 src_mac_addr[ETH_HLEN];
+ struct list_head rx_reports; /* under rx_lock! */
+ struct work_struct rx_report_ws;
+
+ struct mutex msg_mutex; /* serialize command execution */
+ struct completion msg_completion;
+ struct sk_buff *ack_skb; /* protected by rx_lock */
+
+ void *bm_ack_buf; /* for receiving acks over USB */
+ void *bm_cmd_buf; /* for issuing commands over USB */
+
+ struct workqueue_struct *work_queue;
+
+ struct mutex init_mutex; /* protect bringup seq */
+ struct i2400m_reset_ctx *reset_ctx; /* protected by init_mutex */
+
+ struct work_struct wake_tx_ws;
+ struct sk_buff *wake_tx_skb;
+
+ struct work_struct reset_ws;
+ const char *reset_reason;
+
+ struct work_struct recovery_ws;
+
+ struct dentry *debugfs_dentry;
+ const char *fw_name; /* name of the current firmware image */
+ unsigned long fw_version; /* version of the firmware interface */
+ const struct i2400m_bcf_hdr **fw_hdrs;
+ struct i2400m_fw *fw_cached; /* protected by rx_lock */
+ struct i2400m_barker_db *barker;
+
+ struct notifier_block pm_notifier;
+
+ /* counting bus reset retries in this boot */
+ atomic_t bus_reset_retries;
+
+ /* if the device is expected to be alive */
+ unsigned alive;
+
+ /* 0 if we are ready for error recovery; 1 if not ready */
+ atomic_t error_recovery;
+
+};
+
+
+/*
+ * Bus-generic internal APIs
+ * -------------------------
+ */
+
+static inline
+struct i2400m *wimax_dev_to_i2400m(struct wimax_dev *wimax_dev)
+{
+ return container_of(wimax_dev, struct i2400m, wimax_dev);
+}
+
+static inline
+struct i2400m *net_dev_to_i2400m(struct net_device *net_dev)
+{
+ return wimax_dev_to_i2400m(netdev_priv(net_dev));
+}
+
+/*
+ * Boot mode support
+ */
+
+/**
+ * i2400m_bm_cmd_flags - flags to i2400m_bm_cmd()
+ *
+ * @I2400M_BM_CMD_RAW: send the command block as-is, without doing any
+ * extra processing for adding CRC.
+ */
+enum i2400m_bm_cmd_flags {
+ I2400M_BM_CMD_RAW = 1 << 2,
+};
+
+/**
+ * i2400m_bri - Boot-ROM indicators
+ *
+ * Flags for i2400m_bootrom_init() and i2400m_dev_bootstrap() [which
+ * are passed from things like i2400m_setup()]. Can be combined with
+ * |.
+ *
+ * @I2400M_BRI_SOFT: The device rebooted already and a reboot
+ * barker received, proceed directly to ack the boot sequence.
+ * @I2400M_BRI_NO_REBOOT: Do not reboot the device and proceed
+ * directly to wait for a reboot barker from the device.
+ * @I2400M_BRI_MAC_REINIT: We need to reinitialize the boot
+ * rom after reading the MAC address. This is quite a dirty hack,
+ * if you ask me -- the device requires the bootrom to be
+ * initialized after reading the MAC address.
+ */
+enum i2400m_bri {
+ I2400M_BRI_SOFT = 1 << 1,
+ I2400M_BRI_NO_REBOOT = 1 << 2,
+ I2400M_BRI_MAC_REINIT = 1 << 3,
+};
+
+void i2400m_bm_cmd_prepare(struct i2400m_bootrom_header *);
+int i2400m_dev_bootstrap(struct i2400m *, enum i2400m_bri);
+int i2400m_read_mac_addr(struct i2400m *);
+int i2400m_bootrom_init(struct i2400m *, enum i2400m_bri);
+int i2400m_is_boot_barker(struct i2400m *, const void *, size_t);
+static inline
+int i2400m_is_d2h_barker(const void *buf)
+{
+ const __le32 *barker = buf;
+ return le32_to_cpu(*barker) == I2400M_D2H_MSG_BARKER;
+}
+void i2400m_unknown_barker(struct i2400m *, const void *, size_t);
+
+/* Make/grok boot-rom header commands */
+
+static inline
+__le32 i2400m_brh_command(enum i2400m_brh_opcode opcode, unsigned use_checksum,
+ unsigned direct_access)
+{
+ return cpu_to_le32(
+ I2400M_BRH_SIGNATURE
+ | (direct_access ? I2400M_BRH_DIRECT_ACCESS : 0)
+ | I2400M_BRH_RESPONSE_REQUIRED /* response always required */
+ | (use_checksum ? I2400M_BRH_USE_CHECKSUM : 0)
+ | (opcode & I2400M_BRH_OPCODE_MASK));
+}
+
+static inline
+void i2400m_brh_set_opcode(struct i2400m_bootrom_header *hdr,
+ enum i2400m_brh_opcode opcode)
+{
+ hdr->command = cpu_to_le32(
+ (le32_to_cpu(hdr->command) & ~I2400M_BRH_OPCODE_MASK)
+ | (opcode & I2400M_BRH_OPCODE_MASK));
+}
+
+static inline
+unsigned i2400m_brh_get_opcode(const struct i2400m_bootrom_header *hdr)
+{
+ return le32_to_cpu(hdr->command) & I2400M_BRH_OPCODE_MASK;
+}
+
+static inline
+unsigned i2400m_brh_get_response(const struct i2400m_bootrom_header *hdr)
+{
+ return (le32_to_cpu(hdr->command) & I2400M_BRH_RESPONSE_MASK)
+ >> I2400M_BRH_RESPONSE_SHIFT;
+}
+
+static inline
+unsigned i2400m_brh_get_use_checksum(const struct i2400m_bootrom_header *hdr)
+{
+ return le32_to_cpu(hdr->command) & I2400M_BRH_USE_CHECKSUM;
+}
+
+static inline
+unsigned i2400m_brh_get_response_required(
+ const struct i2400m_bootrom_header *hdr)
+{
+ return le32_to_cpu(hdr->command) & I2400M_BRH_RESPONSE_REQUIRED;
+}
+
+static inline
+unsigned i2400m_brh_get_direct_access(const struct i2400m_bootrom_header *hdr)
+{
+ return le32_to_cpu(hdr->command) & I2400M_BRH_DIRECT_ACCESS;
+}
+
+static inline
+unsigned i2400m_brh_get_signature(const struct i2400m_bootrom_header *hdr)
+{
+ return (le32_to_cpu(hdr->command) & I2400M_BRH_SIGNATURE_MASK)
+ >> I2400M_BRH_SIGNATURE_SHIFT;
+}
+
+
+/*
+ * Driver / device setup and internal functions
+ */
+void i2400m_init(struct i2400m *);
+int i2400m_reset(struct i2400m *, enum i2400m_reset_type);
+void i2400m_netdev_setup(struct net_device *net_dev);
+int i2400m_sysfs_setup(struct device_driver *);
+void i2400m_sysfs_release(struct device_driver *);
+int i2400m_tx_setup(struct i2400m *);
+void i2400m_wake_tx_work(struct work_struct *);
+void i2400m_tx_release(struct i2400m *);
+
+int i2400m_rx_setup(struct i2400m *);
+void i2400m_rx_release(struct i2400m *);
+
+void i2400m_fw_cache(struct i2400m *);
+void i2400m_fw_uncache(struct i2400m *);
+
+void i2400m_net_rx(struct i2400m *, struct sk_buff *, unsigned, const void *,
+ int);
+void i2400m_net_erx(struct i2400m *, struct sk_buff *, enum i2400m_cs);
+void i2400m_net_wake_stop(struct i2400m *);
+enum i2400m_pt;
+int i2400m_tx(struct i2400m *, const void *, size_t, enum i2400m_pt);
+
+#ifdef CONFIG_DEBUG_FS
+void i2400m_debugfs_add(struct i2400m *);
+void i2400m_debugfs_rm(struct i2400m *);
+#else
+static inline void i2400m_debugfs_add(struct i2400m *i2400m) {}
+static inline void i2400m_debugfs_rm(struct i2400m *i2400m) {}
+#endif
+
+/* Initialize/shutdown the device */
+int i2400m_dev_initialize(struct i2400m *);
+void i2400m_dev_shutdown(struct i2400m *);
+
+extern struct attribute_group i2400m_dev_attr_group;
+
+
+/* HDI message's payload description handling */
+
+static inline
+size_t i2400m_pld_size(const struct i2400m_pld *pld)
+{
+ return I2400M_PLD_SIZE_MASK & le32_to_cpu(pld->val);
+}
+
+static inline
+enum i2400m_pt i2400m_pld_type(const struct i2400m_pld *pld)
+{
+ return (I2400M_PLD_TYPE_MASK & le32_to_cpu(pld->val))
+ >> I2400M_PLD_TYPE_SHIFT;
+}
+
+static inline
+void i2400m_pld_set(struct i2400m_pld *pld, size_t size,
+ enum i2400m_pt type)
+{
+ pld->val = cpu_to_le32(
+ ((type << I2400M_PLD_TYPE_SHIFT) & I2400M_PLD_TYPE_MASK)
+ | (size & I2400M_PLD_SIZE_MASK));
+}
+
+
+/*
+ * API for the bus-specific drivers
+ * --------------------------------
+ */
+
+static inline
+struct i2400m *i2400m_get(struct i2400m *i2400m)
+{
+ dev_hold(i2400m->wimax_dev.net_dev);
+ return i2400m;
+}
+
+static inline
+void i2400m_put(struct i2400m *i2400m)
+{
+ dev_put(i2400m->wimax_dev.net_dev);
+}
+
+int i2400m_dev_reset_handle(struct i2400m *, const char *);
+int i2400m_pre_reset(struct i2400m *);
+int i2400m_post_reset(struct i2400m *);
+void i2400m_error_recovery(struct i2400m *);
+
+/*
+ * _setup()/_release() are called by the probe/disconnect functions of
+ * the bus-specific drivers.
+ */
+int i2400m_setup(struct i2400m *, enum i2400m_bri bm_flags);
+void i2400m_release(struct i2400m *);
+
+int i2400m_rx(struct i2400m *, struct sk_buff *);
+struct i2400m_msg_hdr *i2400m_tx_msg_get(struct i2400m *, size_t *);
+void i2400m_tx_msg_sent(struct i2400m *);
+
+
+/*
+ * Utility functions
+ */
+
+static inline
+struct device *i2400m_dev(struct i2400m *i2400m)
+{
+ return i2400m->wimax_dev.net_dev->dev.parent;
+}
+
+int i2400m_msg_check_status(const struct i2400m_l3l4_hdr *, char *, size_t);
+int i2400m_msg_size_check(struct i2400m *, const struct i2400m_l3l4_hdr *,
+ size_t);
+struct sk_buff *i2400m_msg_to_dev(struct i2400m *, const void *, size_t);
+void i2400m_msg_to_dev_cancel_wait(struct i2400m *, int);
+void i2400m_report_hook(struct i2400m *, const struct i2400m_l3l4_hdr *,
+ size_t);
+void i2400m_report_hook_work(struct work_struct *);
+int i2400m_cmd_enter_powersave(struct i2400m *);
+int i2400m_cmd_exit_idle(struct i2400m *);
+struct sk_buff *i2400m_get_device_info(struct i2400m *);
+int i2400m_firmware_check(struct i2400m *);
+int i2400m_set_idle_timeout(struct i2400m *, unsigned);
+
+static inline
+struct usb_endpoint_descriptor *usb_get_epd(struct usb_interface *iface, int ep)
+{
+ return &iface->cur_altsetting->endpoint[ep].desc;
+}
+
+int i2400m_op_rfkill_sw_toggle(struct wimax_dev *, enum wimax_rf_state);
+void i2400m_report_tlv_rf_switches_status(struct i2400m *,
+ const struct i2400m_tlv_rf_switches_status *);
+
+/*
+ * Helpers for firmware backwards compatibility
+ *
+ * As we aim to support at least the firmware version that was
+ * released with the previous kernel/driver release, some code will be
+ * conditionally executed depending on the firmware version. On each
+ * release, the code to support fw releases past the last two ones
+ * will be purged.
+ *
+ * By making it depend on this macros, it is easier to keep it a tab
+ * on what has to go and what not.
+ */
+static inline
+unsigned i2400m_le_v1_3(struct i2400m *i2400m)
+{
+ /* running fw is lower or v1.3 */
+ return i2400m->fw_version <= 0x00090001;
+}
+
+static inline
+unsigned i2400m_ge_v1_4(struct i2400m *i2400m)
+{
+ /* running fw is higher or v1.4 */
+ return i2400m->fw_version >= 0x00090002;
+}
+
+
+/*
+ * Do a millisecond-sleep for allowing wireshark to dump all the data
+ * packets. Used only for debugging.
+ */
+static inline
+void __i2400m_msleep(unsigned ms)
+{
+#if 1
+#else
+ msleep(ms);
+#endif
+}
+
+
+/* module initialization helpers */
+int i2400m_barker_db_init(const char *);
+void i2400m_barker_db_exit(void);
+
+
+
+#endif /* #ifndef __I2400M_H__ */
--- /dev/null
+/*
+ * Intel Wireless WiMax Connection 2400m
+ * Host-Device protocol interface definitions
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * - Initial implementation
+ *
+ *
+ * This header defines the data structures and constants used to
+ * communicate with the device.
+ *
+ * BOOTMODE/BOOTROM/FIRMWARE UPLOAD PROTOCOL
+ *
+ * The firmware upload protocol is quite simple and only requires a
+ * handful of commands. See drivers/net/wimax/i2400m/fw.c for more
+ * details.
+ *
+ * The BCF data structure is for the firmware file header.
+ *
+ *
+ * THE DATA / CONTROL PROTOCOL
+ *
+ * This is the normal protocol spoken with the device once the
+ * firmware is uploaded. It transports data payloads and control
+ * messages back and forth.
+ *
+ * It consists 'messages' that pack one or more payloads each. The
+ * format is described in detail in drivers/net/wimax/i2400m/rx.c and
+ * tx.c.
+ *
+ *
+ * THE L3L4 PROTOCOL
+ *
+ * The term L3L4 refers to Layer 3 (the device), Layer 4 (the
+ * driver/host software).
+ *
+ * This is the control protocol used by the host to control the i2400m
+ * device (scan, connect, disconnect...). This is sent to / received
+ * as control frames. These frames consist of a header and zero or
+ * more TLVs with information. We call each control frame a "message".
+ *
+ * Each message is composed of:
+ *
+ * HEADER
+ * [TLV0 + PAYLOAD0]
+ * [TLV1 + PAYLOAD1]
+ * [...]
+ * [TLVN + PAYLOADN]
+ *
+ * The HEADER is defined by 'struct i2400m_l3l4_hdr'. The payloads are
+ * defined by a TLV structure (Type Length Value) which is a 'header'
+ * (struct i2400m_tlv_hdr) and then the payload.
+ *
+ * All integers are represented as Little Endian.
+ *
+ * - REQUESTS AND EVENTS
+ *
+ * The requests can be clasified as follows:
+ *
+ * COMMAND: implies a request from the host to the device requesting
+ * an action being performed. The device will reply with a
+ * message (with the same type as the command), status and
+ * no (TLV) payload. Execution of a command might cause
+ * events (of different type) to be sent later on as
+ * device's state changes.
+ *
+ * GET/SET: similar to COMMAND, but will not cause other
+ * EVENTs. The reply, in the case of GET, will contain
+ * TLVs with the requested information.
+ *
+ * EVENT: asynchronous messages sent from the device, maybe as a
+ * consequence of previous COMMANDs but disassociated from
+ * them.
+ *
+ * Only one request might be pending at the same time (ie: don't
+ * parallelize nor post another GET request before the previous
+ * COMMAND has been acknowledged with it's corresponding reply by the
+ * device).
+ *
+ * The different requests and their formats are described below:
+ *
+ * I2400M_MT_* Message types
+ * I2400M_MS_* Message status (for replies, events)
+ * i2400m_tlv_* TLVs
+ *
+ * data types are named 'struct i2400m_msg_OPNAME', OPNAME matching the
+ * operation.
+ */
+
+#ifndef __LINUX__WIMAX__I2400M_H__
+#define __LINUX__WIMAX__I2400M_H__
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+/*
+ * Host Device Interface (HDI) common to all busses
+ */
+
+/* Boot-mode (firmware upload mode) commands */
+
+/* Header for the firmware file */
+struct i2400m_bcf_hdr {
+ __le32 module_type;
+ __le32 header_len;
+ __le32 header_version;
+ __le32 module_id;
+ __le32 module_vendor;
+ __le32 date; /* BCD YYYMMDD */
+ __le32 size; /* in dwords */
+ __le32 key_size; /* in dwords */
+ __le32 modulus_size; /* in dwords */
+ __le32 exponent_size; /* in dwords */
+ __u8 reserved[88];
+} __attribute__ ((packed));
+
+/* Boot mode opcodes */
+enum i2400m_brh_opcode {
+ I2400M_BRH_READ = 1,
+ I2400M_BRH_WRITE = 2,
+ I2400M_BRH_JUMP = 3,
+ I2400M_BRH_SIGNED_JUMP = 8,
+ I2400M_BRH_HASH_PAYLOAD_ONLY = 9,
+};
+
+/* Boot mode command masks and stuff */
+enum i2400m_brh {
+ I2400M_BRH_SIGNATURE = 0xcbbc0000,
+ I2400M_BRH_SIGNATURE_MASK = 0xffff0000,
+ I2400M_BRH_SIGNATURE_SHIFT = 16,
+ I2400M_BRH_OPCODE_MASK = 0x0000000f,
+ I2400M_BRH_RESPONSE_MASK = 0x000000f0,
+ I2400M_BRH_RESPONSE_SHIFT = 4,
+ I2400M_BRH_DIRECT_ACCESS = 0x00000400,
+ I2400M_BRH_RESPONSE_REQUIRED = 0x00000200,
+ I2400M_BRH_USE_CHECKSUM = 0x00000100,
+};
+
+
+/**
+ * i2400m_bootrom_header - Header for a boot-mode command
+ *
+ * @cmd: the above command descriptor
+ * @target_addr: where on the device memory should the action be performed.
+ * @data_size: for read/write, amount of data to be read/written
+ * @block_checksum: checksum value (if applicable)
+ * @payload: the beginning of data attached to this header
+ */
+struct i2400m_bootrom_header {
+ __le32 command; /* Compose with enum i2400_brh */
+ __le32 target_addr;
+ __le32 data_size;
+ __le32 block_checksum;
+ char payload[0];
+} __attribute__ ((packed));
+
+
+/*
+ * Data / control protocol
+ */
+
+/* Packet types for the host-device interface */
+enum i2400m_pt {
+ I2400M_PT_DATA = 0,
+ I2400M_PT_CTRL,
+ I2400M_PT_TRACE, /* For device debug */
+ I2400M_PT_RESET_WARM, /* device reset */
+ I2400M_PT_RESET_COLD, /* USB[transport] reset, like reconnect */
+ I2400M_PT_EDATA, /* Extended RX data */
+ I2400M_PT_ILLEGAL
+};
+
+
+/*
+ * Payload for a data packet
+ *
+ * This is prefixed to each and every outgoing DATA type.
+ */
+struct i2400m_pl_data_hdr {
+ __le32 reserved;
+} __attribute__((packed));
+
+
+/*
+ * Payload for an extended data packet
+ *
+ * New in fw v1.4
+ *
+ * @reorder: if this payload has to be reorder or not (and how)
+ * @cs: the type of data in the packet, as defined per (802.16e
+ * T11.13.19.1). Currently only 2 (IPv4 packet) supported.
+ *
+ * This is prefixed to each and every INCOMING DATA packet.
+ */
+struct i2400m_pl_edata_hdr {
+ __le32 reorder; /* bits defined in i2400m_ro */
+ __u8 cs;
+ __u8 reserved[11];
+} __attribute__((packed));
+
+enum i2400m_cs {
+ I2400M_CS_IPV4_0 = 0,
+ I2400M_CS_IPV4 = 2,
+};
+
+enum i2400m_ro {
+ I2400M_RO_NEEDED = 0x01,
+ I2400M_RO_TYPE = 0x03,
+ I2400M_RO_TYPE_SHIFT = 1,
+ I2400M_RO_CIN = 0x0f,
+ I2400M_RO_CIN_SHIFT = 4,
+ I2400M_RO_FBN = 0x07ff,
+ I2400M_RO_FBN_SHIFT = 8,
+ I2400M_RO_SN = 0x07ff,
+ I2400M_RO_SN_SHIFT = 21,
+};
+
+enum i2400m_ro_type {
+ I2400M_RO_TYPE_RESET = 0,
+ I2400M_RO_TYPE_PACKET,
+ I2400M_RO_TYPE_WS,
+ I2400M_RO_TYPE_PACKET_WS,
+};
+
+
+/* Misc constants */
+enum {
+ I2400M_PL_ALIGN = 16, /* Payload data size alignment */
+ I2400M_PL_SIZE_MAX = 0x3EFF,
+ I2400M_MAX_PLS_IN_MSG = 60,
+ /* protocol barkers: sync sequences; for notifications they
+ * are sent in groups of four. */
+ I2400M_H2D_PREVIEW_BARKER = 0xcafe900d,
+ I2400M_COLD_RESET_BARKER = 0xc01dc01d,
+ I2400M_WARM_RESET_BARKER = 0x50f750f7,
+ I2400M_NBOOT_BARKER = 0xdeadbeef,
+ I2400M_SBOOT_BARKER = 0x0ff1c1a1,
+ I2400M_SBOOT_BARKER_6050 = 0x80000001,
+ I2400M_ACK_BARKER = 0xfeedbabe,
+ I2400M_D2H_MSG_BARKER = 0xbeefbabe,
+};
+
+
+/*
+ * Hardware payload descriptor
+ *
+ * Bitfields encoded in a struct to enforce typing semantics.
+ *
+ * Look in rx.c and tx.c for a full description of the format.
+ */
+struct i2400m_pld {
+ __le32 val;
+} __attribute__ ((packed));
+
+#define I2400M_PLD_SIZE_MASK 0x00003fff
+#define I2400M_PLD_TYPE_SHIFT 16
+#define I2400M_PLD_TYPE_MASK 0x000f0000
+
+/*
+ * Header for a TX message or RX message
+ *
+ * @barker: preamble
+ * @size: used for management of the FIFO queue buffer; before
+ * sending, this is converted to be a real preamble. This
+ * indicates the real size of the TX message that starts at this
+ * point. If the highest bit is set, then this message is to be
+ * skipped.
+ * @sequence: sequence number of this message
+ * @offset: offset where the message itself starts -- see the comments
+ * in the file header about message header and payload descriptor
+ * alignment.
+ * @num_pls: number of payloads in this message
+ * @padding: amount of padding bytes at the end of the message to make
+ * it be of block-size aligned
+ *
+ * Look in rx.c and tx.c for a full description of the format.
+ */
+struct i2400m_msg_hdr {
+ union {
+ __le32 barker;
+ __u32 size; /* same size type as barker!! */
+ };
+ union {
+ __le32 sequence;
+ __u32 offset; /* same size type as barker!! */
+ };
+ __le16 num_pls;
+ __le16 rsv1;
+ __le16 padding;
+ __le16 rsv2;
+ struct i2400m_pld pld[0];
+} __attribute__ ((packed));
+
+
+
+/*
+ * L3/L4 control protocol
+ */
+
+enum {
+ /* Interface version */
+ I2400M_L3L4_VERSION = 0x0100,
+};
+
+/* Message types */
+enum i2400m_mt {
+ I2400M_MT_RESERVED = 0x0000,
+ I2400M_MT_INVALID = 0xffff,
+ I2400M_MT_REPORT_MASK = 0x8000,
+
+ I2400M_MT_GET_SCAN_RESULT = 0x4202,
+ I2400M_MT_SET_SCAN_PARAM = 0x4402,
+ I2400M_MT_CMD_RF_CONTROL = 0x4602,
+ I2400M_MT_CMD_SCAN = 0x4603,
+ I2400M_MT_CMD_CONNECT = 0x4604,
+ I2400M_MT_CMD_DISCONNECT = 0x4605,
+ I2400M_MT_CMD_EXIT_IDLE = 0x4606,
+ I2400M_MT_GET_LM_VERSION = 0x5201,
+ I2400M_MT_GET_DEVICE_INFO = 0x5202,
+ I2400M_MT_GET_LINK_STATUS = 0x5203,
+ I2400M_MT_GET_STATISTICS = 0x5204,
+ I2400M_MT_GET_STATE = 0x5205,
+ I2400M_MT_GET_MEDIA_STATUS = 0x5206,
+ I2400M_MT_SET_INIT_CONFIG = 0x5404,
+ I2400M_MT_CMD_INIT = 0x5601,
+ I2400M_MT_CMD_TERMINATE = 0x5602,
+ I2400M_MT_CMD_MODE_OF_OP = 0x5603,
+ I2400M_MT_CMD_RESET_DEVICE = 0x5604,
+ I2400M_MT_CMD_MONITOR_CONTROL = 0x5605,
+ I2400M_MT_CMD_ENTER_POWERSAVE = 0x5606,
+ I2400M_MT_GET_TLS_OPERATION_RESULT = 0x6201,
+ I2400M_MT_SET_EAP_SUCCESS = 0x6402,
+ I2400M_MT_SET_EAP_FAIL = 0x6403,
+ I2400M_MT_SET_EAP_KEY = 0x6404,
+ I2400M_MT_CMD_SEND_EAP_RESPONSE = 0x6602,
+ I2400M_MT_REPORT_SCAN_RESULT = 0xc002,
+ I2400M_MT_REPORT_STATE = 0xd002,
+ I2400M_MT_REPORT_POWERSAVE_READY = 0xd005,
+ I2400M_MT_REPORT_EAP_REQUEST = 0xe002,
+ I2400M_MT_REPORT_EAP_RESTART = 0xe003,
+ I2400M_MT_REPORT_ALT_ACCEPT = 0xe004,
+ I2400M_MT_REPORT_KEY_REQUEST = 0xe005,
+};
+
+
+/*
+ * Message Ack Status codes
+ *
+ * When a message is replied-to, this status is reported.
+ */
+enum i2400m_ms {
+ I2400M_MS_DONE_OK = 0,
+ I2400M_MS_DONE_IN_PROGRESS = 1,
+ I2400M_MS_INVALID_OP = 2,
+ I2400M_MS_BAD_STATE = 3,
+ I2400M_MS_ILLEGAL_VALUE = 4,
+ I2400M_MS_MISSING_PARAMS = 5,
+ I2400M_MS_VERSION_ERROR = 6,
+ I2400M_MS_ACCESSIBILITY_ERROR = 7,
+ I2400M_MS_BUSY = 8,
+ I2400M_MS_CORRUPTED_TLV = 9,
+ I2400M_MS_UNINITIALIZED = 10,
+ I2400M_MS_UNKNOWN_ERROR = 11,
+ I2400M_MS_PRODUCTION_ERROR = 12,
+ I2400M_MS_NO_RF = 13,
+ I2400M_MS_NOT_READY_FOR_POWERSAVE = 14,
+ I2400M_MS_THERMAL_CRITICAL = 15,
+ I2400M_MS_MAX
+};
+
+
+/**
+ * i2400m_tlv - enumeration of the different types of TLVs
+ *
+ * TLVs stand for type-length-value and are the header for a payload
+ * composed of almost anything. Each payload has a type assigned
+ * and a length.
+ */
+enum i2400m_tlv {
+ I2400M_TLV_L4_MESSAGE_VERSIONS = 129,
+ I2400M_TLV_SYSTEM_STATE = 141,
+ I2400M_TLV_MEDIA_STATUS = 161,
+ I2400M_TLV_RF_OPERATION = 162,
+ I2400M_TLV_RF_STATUS = 163,
+ I2400M_TLV_DEVICE_RESET_TYPE = 132,
+ I2400M_TLV_CONFIG_IDLE_PARAMETERS = 601,
+ I2400M_TLV_CONFIG_IDLE_TIMEOUT = 611,
+ I2400M_TLV_CONFIG_D2H_DATA_FORMAT = 614,
+ I2400M_TLV_CONFIG_DL_HOST_REORDER = 615,
+};
+
+
+struct i2400m_tlv_hdr {
+ __le16 type;
+ __le16 length; /* payload's */
+ __u8 pl[0];
+} __attribute__((packed));
+
+
+struct i2400m_l3l4_hdr {
+ __le16 type;
+ __le16 length; /* payload's */
+ __le16 version;
+ __le16 resv1;
+ __le16 status;
+ __le16 resv2;
+ struct i2400m_tlv_hdr pl[0];
+} __attribute__((packed));
+
+
+/**
+ * i2400m_system_state - different states of the device
+ */
+enum i2400m_system_state {
+ I2400M_SS_UNINITIALIZED = 1,
+ I2400M_SS_INIT,
+ I2400M_SS_READY,
+ I2400M_SS_SCAN,
+ I2400M_SS_STANDBY,
+ I2400M_SS_CONNECTING,
+ I2400M_SS_WIMAX_CONNECTED,
+ I2400M_SS_DATA_PATH_CONNECTED,
+ I2400M_SS_IDLE,
+ I2400M_SS_DISCONNECTING,
+ I2400M_SS_OUT_OF_ZONE,
+ I2400M_SS_SLEEPACTIVE,
+ I2400M_SS_PRODUCTION,
+ I2400M_SS_CONFIG,
+ I2400M_SS_RF_OFF,
+ I2400M_SS_RF_SHUTDOWN,
+ I2400M_SS_DEVICE_DISCONNECT,
+ I2400M_SS_MAX,
+};
+
+
+/**
+ * i2400m_tlv_system_state - report on the state of the system
+ *
+ * @state: see enum i2400m_system_state
+ */
+struct i2400m_tlv_system_state {
+ struct i2400m_tlv_hdr hdr;
+ __le32 state;
+} __attribute__((packed));
+
+
+struct i2400m_tlv_l4_message_versions {
+ struct i2400m_tlv_hdr hdr;
+ __le16 major;
+ __le16 minor;
+ __le16 branch;
+ __le16 reserved;
+} __attribute__((packed));
+
+
+struct i2400m_tlv_detailed_device_info {
+ struct i2400m_tlv_hdr hdr;
+ __u8 reserved1[400];
+ __u8 mac_address[ETH_ALEN];
+ __u8 reserved2[2];
+} __attribute__((packed));
+
+
+enum i2400m_rf_switch_status {
+ I2400M_RF_SWITCH_ON = 1,
+ I2400M_RF_SWITCH_OFF = 2,
+};
+
+struct i2400m_tlv_rf_switches_status {
+ struct i2400m_tlv_hdr hdr;
+ __u8 sw_rf_switch; /* 1 ON, 2 OFF */
+ __u8 hw_rf_switch; /* 1 ON, 2 OFF */
+ __u8 reserved[2];
+} __attribute__((packed));
+
+
+enum {
+ i2400m_rf_operation_on = 1,
+ i2400m_rf_operation_off = 2
+};
+
+struct i2400m_tlv_rf_operation {
+ struct i2400m_tlv_hdr hdr;
+ __le32 status; /* 1 ON, 2 OFF */
+} __attribute__((packed));
+
+
+enum i2400m_tlv_reset_type {
+ I2400M_RESET_TYPE_COLD = 1,
+ I2400M_RESET_TYPE_WARM
+};
+
+struct i2400m_tlv_device_reset_type {
+ struct i2400m_tlv_hdr hdr;
+ __le32 reset_type;
+} __attribute__((packed));
+
+
+struct i2400m_tlv_config_idle_parameters {
+ struct i2400m_tlv_hdr hdr;
+ __le32 idle_timeout; /* 100 to 300000 ms [5min], 100 increments
+ * 0 disabled */
+ __le32 idle_paging_interval; /* frames */
+} __attribute__((packed));
+
+
+enum i2400m_media_status {
+ I2400M_MEDIA_STATUS_LINK_UP = 1,
+ I2400M_MEDIA_STATUS_LINK_DOWN,
+ I2400M_MEDIA_STATUS_LINK_RENEW,
+};
+
+struct i2400m_tlv_media_status {
+ struct i2400m_tlv_hdr hdr;
+ __le32 media_status;
+} __attribute__((packed));
+
+
+/* New in v1.4 */
+struct i2400m_tlv_config_idle_timeout {
+ struct i2400m_tlv_hdr hdr;
+ __le32 timeout; /* 100 to 300000 ms [5min], 100 increments
+ * 0 disabled */
+} __attribute__((packed));
+
+/* New in v1.4 -- for backward compat, will be removed */
+struct i2400m_tlv_config_d2h_data_format {
+ struct i2400m_tlv_hdr hdr;
+ __u8 format; /* 0 old format, 1 enhanced */
+ __u8 reserved[3];
+} __attribute__((packed));
+
+/* New in v1.4 */
+struct i2400m_tlv_config_dl_host_reorder {
+ struct i2400m_tlv_hdr hdr;
+ __u8 reorder; /* 0 disabled, 1 enabled */
+ __u8 reserved[3];
+} __attribute__((packed));
+
+
+#endif /* #ifndef __LINUX__WIMAX__I2400M_H__ */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Glue with the networking stack
+ *
+ * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This implements an ethernet device for the i2400m.
+ *
+ * We fake being an ethernet device to simplify the support from user
+ * space and from the other side. The world is (sadly) configured to
+ * take in only Ethernet devices...
+ *
+ * Because of this, when using firmwares <= v1.3, there is an
+ * copy-each-rxed-packet overhead on the RX path. Each IP packet has
+ * to be reallocated to add an ethernet header (as there is no space
+ * in what we get from the device). This is a known drawback and
+ * firmwares >= 1.4 add header space that can be used to insert the
+ * ethernet header without having to reallocate and copy.
+ *
+ * TX error handling is tricky; because we have to FIFO/queue the
+ * buffers for transmission (as the hardware likes it aggregated), we
+ * just give the skb to the TX subsystem and by the time it is
+ * transmitted, we have long forgotten about it. So we just don't care
+ * too much about it.
+ *
+ * Note that when the device is in idle mode with the basestation, we
+ * need to negotiate coming back up online. That involves negotiation
+ * and possible user space interaction. Thus, we defer to a workqueue
+ * to do all that. By default, we only queue a single packet and drop
+ * the rest, as potentially the time to go back from idle to normal is
+ * long.
+ *
+ * ROADMAP
+ *
+ * i2400m_open Called on ifconfig up
+ * i2400m_stop Called on ifconfig down
+ *
+ * i2400m_hard_start_xmit Called by the network stack to send a packet
+ * i2400m_net_wake_tx Wake up device from basestation-IDLE & TX
+ * i2400m_wake_tx_work
+ * i2400m_cmd_exit_idle
+ * i2400m_tx
+ * i2400m_net_tx TX a data frame
+ * i2400m_tx
+ *
+ * i2400m_change_mtu Called on ifconfig mtu XXX
+ *
+ * i2400m_tx_timeout Called when the device times out
+ *
+ * i2400m_net_rx Called by the RX code when a data frame is
+ * available (firmware <= 1.3)
+ * i2400m_net_erx Called by the RX code when a data frame is
+ * available (firmware >= 1.4).
+ * i2400m_netdev_setup Called to setup all the netdev stuff from
+ * alloc_netdev.
+ */
+#include <linux/if_arp.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#include <linux/ethtool.h>
+#include <linux/export.h>
+#include "i2400m.h"
+
+
+#define D_SUBMODULE netdev
+#include "debug-levels.h"
+
+enum {
+/* netdev interface */
+ /* 20 secs? yep, this is the maximum timeout that the device
+ * might take to get out of IDLE / negotiate it with the base
+ * station. We add 1sec for good measure. */
+ I2400M_TX_TIMEOUT = 21 * HZ,
+ /*
+ * Experimentation has determined that, 20 to be a good value
+ * for minimizing the jitter in the throughput.
+ */
+ I2400M_TX_QLEN = 20,
+};
+
+
+static
+int i2400m_open(struct net_device *net_dev)
+{
+ int result;
+ struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+ struct device *dev = i2400m_dev(i2400m);
+
+ d_fnstart(3, dev, "(net_dev %p [i2400m %p])\n", net_dev, i2400m);
+ /* Make sure we wait until init is complete... */
+ mutex_lock(&i2400m->init_mutex);
+ if (i2400m->updown)
+ result = 0;
+ else
+ result = -EBUSY;
+ mutex_unlock(&i2400m->init_mutex);
+ d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
+ net_dev, i2400m, result);
+ return result;
+}
+
+
+static
+int i2400m_stop(struct net_device *net_dev)
+{
+ struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+ struct device *dev = i2400m_dev(i2400m);
+
+ d_fnstart(3, dev, "(net_dev %p [i2400m %p])\n", net_dev, i2400m);
+ i2400m_net_wake_stop(i2400m);
+ d_fnend(3, dev, "(net_dev %p [i2400m %p]) = 0\n", net_dev, i2400m);
+ return 0;
+}
+
+
+/*
+ * Wake up the device and transmit a held SKB, then restart the net queue
+ *
+ * When the device goes into basestation-idle mode, we need to tell it
+ * to exit that mode; it will negotiate with the base station, user
+ * space may have to intervene to rehandshake crypto and then tell us
+ * when it is ready to transmit the packet we have "queued". Still we
+ * need to give it sometime after it reports being ok.
+ *
+ * On error, there is not much we can do. If the error was on TX, we
+ * still wake the queue up to see if the next packet will be luckier.
+ *
+ * If _cmd_exit_idle() fails...well, it could be many things; most
+ * commonly it is that something else took the device out of IDLE mode
+ * (for example, the base station). In that case we get an -EILSEQ and
+ * we are just going to ignore that one. If the device is back to
+ * connected, then fine -- if it is someother state, the packet will
+ * be dropped anyway.
+ */
+void i2400m_wake_tx_work(struct work_struct *ws)
+{
+ int result;
+ struct i2400m *i2400m = container_of(ws, struct i2400m, wake_tx_ws);
+ struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *skb;
+ unsigned long flags;
+
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ skb = i2400m->wake_tx_skb;
+ i2400m->wake_tx_skb = NULL;
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+
+ d_fnstart(3, dev, "(ws %p i2400m %p skb %p)\n", ws, i2400m, skb);
+ result = -EINVAL;
+ if (skb == NULL) {
+ dev_err(dev, "WAKE&TX: skb disappeared!\n");
+ goto out_put;
+ }
+ /* If we have, somehow, lost the connection after this was
+ * queued, don't do anything; this might be the device got
+ * reset or just disconnected. */
+ if (unlikely(!netif_carrier_ok(net_dev)))
+ goto out_kfree;
+ result = i2400m_cmd_exit_idle(i2400m);
+ if (result == -EILSEQ)
+ result = 0;
+ if (result < 0) {
+ dev_err(dev, "WAKE&TX: device didn't get out of idle: "
+ "%d - resetting\n", result);
+ i2400m_reset(i2400m, I2400M_RT_BUS);
+ goto error;
+ }
+ result = wait_event_timeout(i2400m->state_wq,
+ i2400m->state != I2400M_SS_IDLE,
+ net_dev->watchdog_timeo - HZ/2);
+ if (result == 0)
+ result = -ETIMEDOUT;
+ if (result < 0) {
+ dev_err(dev, "WAKE&TX: error waiting for device to exit IDLE: "
+ "%d - resetting\n", result);
+ i2400m_reset(i2400m, I2400M_RT_BUS);
+ goto error;
+ }
+ msleep(20); /* device still needs some time or it drops it */
+ result = i2400m_tx(i2400m, skb->data, skb->len, I2400M_PT_DATA);
+error:
+ netif_wake_queue(net_dev);
+out_kfree:
+ kfree_skb(skb); /* refcount transferred by _hard_start_xmit() */
+out_put:
+ i2400m_put(i2400m);
+ d_fnend(3, dev, "(ws %p i2400m %p skb %p) = void [%d]\n",
+ ws, i2400m, skb, result);
+}
+
+
+/*
+ * Prepare the data payload TX header
+ *
+ * The i2400m expects a 4 byte header in front of a data packet.
+ *
+ * Because we pretend to be an ethernet device, this packet comes with
+ * an ethernet header. Pull it and push our header.
+ */
+static
+void i2400m_tx_prep_header(struct sk_buff *skb)
+{
+ struct i2400m_pl_data_hdr *pl_hdr;
+ skb_pull(skb, ETH_HLEN);
+ pl_hdr = skb_push(skb, sizeof(*pl_hdr));
+ pl_hdr->reserved = 0;
+}
+
+
+
+/*
+ * Cleanup resources acquired during i2400m_net_wake_tx()
+ *
+ * This is called by __i2400m_dev_stop and means we have to make sure
+ * the workqueue is flushed from any pending work.
+ */
+void i2400m_net_wake_stop(struct i2400m *i2400m)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *wake_tx_skb;
+ unsigned long flags;
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+ /*
+ * See i2400m_hard_start_xmit(), references are taken there and
+ * here we release them if the packet was still pending.
+ */
+ cancel_work_sync(&i2400m->wake_tx_ws);
+
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ wake_tx_skb = i2400m->wake_tx_skb;
+ i2400m->wake_tx_skb = NULL;
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+
+ if (wake_tx_skb) {
+ i2400m_put(i2400m);
+ kfree_skb(wake_tx_skb);
+ }
+
+ d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
+
+
+/*
+ * TX an skb to an idle device
+ *
+ * When the device is in basestation-idle mode, we need to wake it up
+ * and then TX. So we queue a work_struct for doing so.
+ *
+ * We need to get an extra ref for the skb (so it is not dropped), as
+ * well as be careful not to queue more than one request (won't help
+ * at all). If more than one request comes or there are errors, we
+ * just drop the packets (see i2400m_hard_start_xmit()).
+ */
+static
+int i2400m_net_wake_tx(struct i2400m *i2400m, struct net_device *net_dev,
+ struct sk_buff *skb)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ unsigned long flags;
+
+ d_fnstart(3, dev, "(skb %p net_dev %p)\n", skb, net_dev);
+ if (net_ratelimit()) {
+ d_printf(3, dev, "WAKE&NETTX: "
+ "skb %p sending %d bytes to radio\n",
+ skb, skb->len);
+ d_dump(4, dev, skb->data, skb->len);
+ }
+ /* We hold a ref count for i2400m and skb, so when
+ * stopping() the device, we need to cancel that work
+ * and if pending, release those resources. */
+ result = 0;
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ if (!i2400m->wake_tx_skb) {
+ netif_stop_queue(net_dev);
+ i2400m_get(i2400m);
+ i2400m->wake_tx_skb = skb_get(skb); /* transfer ref count */
+ i2400m_tx_prep_header(skb);
+ result = schedule_work(&i2400m->wake_tx_ws);
+ WARN_ON(result == 0);
+ }
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+ if (result == 0) {
+ /* Yes, this happens even if we stopped the
+ * queue -- blame the queue disciplines that
+ * queue without looking -- I guess there is a reason
+ * for that. */
+ if (net_ratelimit())
+ d_printf(1, dev, "NETTX: device exiting idle, "
+ "dropping skb %p, queue running %d\n",
+ skb, netif_queue_stopped(net_dev));
+ result = -EBUSY;
+ }
+ d_fnend(3, dev, "(skb %p net_dev %p) = %d\n", skb, net_dev, result);
+ return result;
+}
+
+
+/*
+ * Transmit a packet to the base station on behalf of the network stack.
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * We need to pull the ethernet header and add the hardware header,
+ * which is currently set to all zeroes and reserved.
+ */
+static
+int i2400m_net_tx(struct i2400m *i2400m, struct net_device *net_dev,
+ struct sk_buff *skb)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+
+ d_fnstart(3, dev, "(i2400m %p net_dev %p skb %p)\n",
+ i2400m, net_dev, skb);
+ /* FIXME: check eth hdr, only IPv4 is routed by the device as of now */
+ netif_trans_update(net_dev);
+ i2400m_tx_prep_header(skb);
+ d_printf(3, dev, "NETTX: skb %p sending %d bytes to radio\n",
+ skb, skb->len);
+ d_dump(4, dev, skb->data, skb->len);
+ result = i2400m_tx(i2400m, skb->data, skb->len, I2400M_PT_DATA);
+ d_fnend(3, dev, "(i2400m %p net_dev %p skb %p) = %d\n",
+ i2400m, net_dev, skb, result);
+ return result;
+}
+
+
+/*
+ * Transmit a packet to the base station on behalf of the network stack
+ *
+ *
+ * Returns: NETDEV_TX_OK (always, even in case of error)
+ *
+ * In case of error, we just drop it. Reasons:
+ *
+ * - we add a hw header to each skb, and if the network stack
+ * retries, we have no way to know if that skb has it or not.
+ *
+ * - network protocols have their own drop-recovery mechanisms
+ *
+ * - there is not much else we can do
+ *
+ * If the device is idle, we need to wake it up; that is an operation
+ * that will sleep. See i2400m_net_wake_tx() for details.
+ */
+static
+netdev_tx_t i2400m_hard_start_xmit(struct sk_buff *skb,
+ struct net_device *net_dev)
+{
+ struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+ struct device *dev = i2400m_dev(i2400m);
+ int result = -1;
+
+ d_fnstart(3, dev, "(skb %p net_dev %p)\n", skb, net_dev);
+
+ if (skb_cow_head(skb, 0))
+ goto drop;
+
+ if (i2400m->state == I2400M_SS_IDLE)
+ result = i2400m_net_wake_tx(i2400m, net_dev, skb);
+ else
+ result = i2400m_net_tx(i2400m, net_dev, skb);
+ if (result < 0) {
+drop:
+ net_dev->stats.tx_dropped++;
+ } else {
+ net_dev->stats.tx_packets++;
+ net_dev->stats.tx_bytes += skb->len;
+ }
+ dev_kfree_skb(skb);
+ d_fnend(3, dev, "(skb %p net_dev %p) = %d\n", skb, net_dev, result);
+ return NETDEV_TX_OK;
+}
+
+
+static
+void i2400m_tx_timeout(struct net_device *net_dev, unsigned int txqueue)
+{
+ /*
+ * We might want to kick the device
+ *
+ * There is not much we can do though, as the device requires
+ * that we send the data aggregated. By the time we receive
+ * this, there might be data pending to be sent or not...
+ */
+ net_dev->stats.tx_errors++;
+}
+
+
+/*
+ * Create a fake ethernet header
+ *
+ * For emulating an ethernet device, every received IP header has to
+ * be prefixed with an ethernet header. Fake it with the given
+ * protocol.
+ */
+static
+void i2400m_rx_fake_eth_header(struct net_device *net_dev,
+ void *_eth_hdr, __be16 protocol)
+{
+ struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+ struct ethhdr *eth_hdr = _eth_hdr;
+
+ memcpy(eth_hdr->h_dest, net_dev->dev_addr, sizeof(eth_hdr->h_dest));
+ memcpy(eth_hdr->h_source, i2400m->src_mac_addr,
+ sizeof(eth_hdr->h_source));
+ eth_hdr->h_proto = protocol;
+}
+
+
+/*
+ * i2400m_net_rx - pass a network packet to the stack
+ *
+ * @i2400m: device instance
+ * @skb_rx: the skb where the buffer pointed to by @buf is
+ * @i: 1 if payload is the only one
+ * @buf: pointer to the buffer containing the data
+ * @len: buffer's length
+ *
+ * This is only used now for the v1.3 firmware. It will be deprecated
+ * in >= 2.6.31.
+ *
+ * Note that due to firmware limitations, we don't have space to add
+ * an ethernet header, so we need to copy each packet. Firmware
+ * versions >= v1.4 fix this [see i2400m_net_erx()].
+ *
+ * We just clone the skb and set it up so that it's skb->data pointer
+ * points to "buf" and it's length.
+ *
+ * Note that if the payload is the last (or the only one) in a
+ * multi-payload message, we don't clone the SKB but just reuse it.
+ *
+ * This function is normally run from a thread context. However, we
+ * still use netif_rx() instead of netif_receive_skb() as was
+ * recommended in the mailing list. Reason is in some stress tests
+ * when sending/receiving a lot of data we seem to hit a softlock in
+ * the kernel's TCP implementation [aroudn tcp_delay_timer()]. Using
+ * netif_rx() took care of the issue.
+ *
+ * This is, of course, still open to do more research on why running
+ * with netif_receive_skb() hits this softlock. FIXME.
+ *
+ * FIXME: currently we don't do any efforts at distinguishing if what
+ * we got was an IPv4 or IPv6 header, to setup the protocol field
+ * correctly.
+ */
+void i2400m_net_rx(struct i2400m *i2400m, struct sk_buff *skb_rx,
+ unsigned i, const void *buf, int buf_len)
+{
+ struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *skb;
+
+ d_fnstart(2, dev, "(i2400m %p buf %p buf_len %d)\n",
+ i2400m, buf, buf_len);
+ if (i) {
+ skb = skb_get(skb_rx);
+ d_printf(2, dev, "RX: reusing first payload skb %p\n", skb);
+ skb_pull(skb, buf - (void *) skb->data);
+ skb_trim(skb, (void *) skb_end_pointer(skb) - buf);
+ } else {
+ /* Yes, this is bad -- a lot of overhead -- see
+ * comments at the top of the file */
+ skb = __netdev_alloc_skb(net_dev, buf_len, GFP_KERNEL);
+ if (skb == NULL) {
+ dev_err(dev, "NETRX: no memory to realloc skb\n");
+ net_dev->stats.rx_dropped++;
+ goto error_skb_realloc;
+ }
+ skb_put_data(skb, buf, buf_len);
+ }
+ i2400m_rx_fake_eth_header(i2400m->wimax_dev.net_dev,
+ skb->data - ETH_HLEN,
+ cpu_to_be16(ETH_P_IP));
+ skb_set_mac_header(skb, -ETH_HLEN);
+ skb->dev = i2400m->wimax_dev.net_dev;
+ skb->protocol = htons(ETH_P_IP);
+ net_dev->stats.rx_packets++;
+ net_dev->stats.rx_bytes += buf_len;
+ d_printf(3, dev, "NETRX: receiving %d bytes to network stack\n",
+ buf_len);
+ d_dump(4, dev, buf, buf_len);
+ netif_rx_ni(skb); /* see notes in function header */
+error_skb_realloc:
+ d_fnend(2, dev, "(i2400m %p buf %p buf_len %d) = void\n",
+ i2400m, buf, buf_len);
+}
+
+
+/*
+ * i2400m_net_erx - pass a network packet to the stack (extended version)
+ *
+ * @i2400m: device descriptor
+ * @skb: the skb where the packet is - the skb should be set to point
+ * at the IP packet; this function will add ethernet headers if
+ * needed.
+ * @cs: packet type
+ *
+ * This is only used now for firmware >= v1.4. Note it is quite
+ * similar to i2400m_net_rx() (used only for v1.3 firmware).
+ *
+ * This function is normally run from a thread context. However, we
+ * still use netif_rx() instead of netif_receive_skb() as was
+ * recommended in the mailing list. Reason is in some stress tests
+ * when sending/receiving a lot of data we seem to hit a softlock in
+ * the kernel's TCP implementation [aroudn tcp_delay_timer()]. Using
+ * netif_rx() took care of the issue.
+ *
+ * This is, of course, still open to do more research on why running
+ * with netif_receive_skb() hits this softlock. FIXME.
+ */
+void i2400m_net_erx(struct i2400m *i2400m, struct sk_buff *skb,
+ enum i2400m_cs cs)
+{
+ struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+ struct device *dev = i2400m_dev(i2400m);
+
+ d_fnstart(2, dev, "(i2400m %p skb %p [%u] cs %d)\n",
+ i2400m, skb, skb->len, cs);
+ switch(cs) {
+ case I2400M_CS_IPV4_0:
+ case I2400M_CS_IPV4:
+ i2400m_rx_fake_eth_header(i2400m->wimax_dev.net_dev,
+ skb->data - ETH_HLEN,
+ cpu_to_be16(ETH_P_IP));
+ skb_set_mac_header(skb, -ETH_HLEN);
+ skb->dev = i2400m->wimax_dev.net_dev;
+ skb->protocol = htons(ETH_P_IP);
+ net_dev->stats.rx_packets++;
+ net_dev->stats.rx_bytes += skb->len;
+ break;
+ default:
+ dev_err(dev, "ERX: BUG? CS type %u unsupported\n", cs);
+ goto error;
+
+ }
+ d_printf(3, dev, "ERX: receiving %d bytes to the network stack\n",
+ skb->len);
+ d_dump(4, dev, skb->data, skb->len);
+ netif_rx_ni(skb); /* see notes in function header */
+error:
+ d_fnend(2, dev, "(i2400m %p skb %p [%u] cs %d) = void\n",
+ i2400m, skb, skb->len, cs);
+}
+
+static const struct net_device_ops i2400m_netdev_ops = {
+ .ndo_open = i2400m_open,
+ .ndo_stop = i2400m_stop,
+ .ndo_start_xmit = i2400m_hard_start_xmit,
+ .ndo_tx_timeout = i2400m_tx_timeout,
+};
+
+static void i2400m_get_drvinfo(struct net_device *net_dev,
+ struct ethtool_drvinfo *info)
+{
+ struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+
+ strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+ strlcpy(info->fw_version, i2400m->fw_name ? : "",
+ sizeof(info->fw_version));
+ if (net_dev->dev.parent)
+ strlcpy(info->bus_info, dev_name(net_dev->dev.parent),
+ sizeof(info->bus_info));
+}
+
+static const struct ethtool_ops i2400m_ethtool_ops = {
+ .get_drvinfo = i2400m_get_drvinfo,
+ .get_link = ethtool_op_get_link,
+};
+
+/**
+ * i2400m_netdev_setup - Setup setup @net_dev's i2400m private data
+ *
+ * Called by alloc_netdev()
+ */
+void i2400m_netdev_setup(struct net_device *net_dev)
+{
+ d_fnstart(3, NULL, "(net_dev %p)\n", net_dev);
+ ether_setup(net_dev);
+ net_dev->mtu = I2400M_MAX_MTU;
+ net_dev->min_mtu = 0;
+ net_dev->max_mtu = I2400M_MAX_MTU;
+ net_dev->tx_queue_len = I2400M_TX_QLEN;
+ net_dev->features =
+ NETIF_F_VLAN_CHALLENGED
+ | NETIF_F_HIGHDMA;
+ net_dev->flags =
+ IFF_NOARP /* i2400m is apure IP device */
+ & (~IFF_BROADCAST /* i2400m is P2P */
+ & ~IFF_MULTICAST);
+ net_dev->watchdog_timeo = I2400M_TX_TIMEOUT;
+ net_dev->netdev_ops = &i2400m_netdev_ops;
+ net_dev->ethtool_ops = &i2400m_ethtool_ops;
+ d_fnend(3, NULL, "(net_dev %p) = void\n", net_dev);
+}
+EXPORT_SYMBOL_GPL(i2400m_netdev_setup);
+
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Implement backend for the WiMAX stack rfkill support
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * The WiMAX kernel stack integrates into RF-Kill and keeps the
+ * switches's status. We just need to:
+ *
+ * - report changes in the HW RF Kill switch [with
+ * wimax_rfkill_{sw,hw}_report(), which happens when we detect those
+ * indications coming through hardware reports]. We also do it on
+ * initialization to let the stack know the initial HW state.
+ *
+ * - implement indications from the stack to change the SW RF Kill
+ * switch (coming from sysfs, the wimax stack or user space).
+ */
+#include "i2400m.h"
+#include "linux-wimax-i2400m.h"
+#include <linux/slab.h>
+
+
+
+#define D_SUBMODULE rfkill
+#include "debug-levels.h"
+
+/*
+ * Return true if the i2400m radio is in the requested wimax_rf_state state
+ *
+ */
+static
+int i2400m_radio_is(struct i2400m *i2400m, enum wimax_rf_state state)
+{
+ if (state == WIMAX_RF_OFF)
+ return i2400m->state == I2400M_SS_RF_OFF
+ || i2400m->state == I2400M_SS_RF_SHUTDOWN;
+ else if (state == WIMAX_RF_ON)
+ /* state == WIMAX_RF_ON */
+ return i2400m->state != I2400M_SS_RF_OFF
+ && i2400m->state != I2400M_SS_RF_SHUTDOWN;
+ else {
+ BUG();
+ return -EINVAL; /* shut gcc warnings on certain arches */
+ }
+}
+
+
+/*
+ * WiMAX stack operation: implement SW RFKill toggling
+ *
+ * @wimax_dev: device descriptor
+ * @skb: skb where the message has been received; skb->data is
+ * expected to point to the message payload.
+ * @genl_info: passed by the generic netlink layer
+ *
+ * Generic Netlink will call this function when a message is sent from
+ * userspace to change the software RF-Kill switch status.
+ *
+ * This function will set the device's software RF-Kill switch state to
+ * match what is requested.
+ *
+ * NOTE: the i2400m has a strict state machine; we can only set the
+ * RF-Kill switch when it is on, the HW RF-Kill is on and the
+ * device is initialized. So we ignore errors steaming from not
+ * being in the right state (-EILSEQ).
+ */
+int i2400m_op_rfkill_sw_toggle(struct wimax_dev *wimax_dev,
+ enum wimax_rf_state state)
+{
+ int result;
+ struct i2400m *i2400m = wimax_dev_to_i2400m(wimax_dev);
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *ack_skb;
+ struct {
+ struct i2400m_l3l4_hdr hdr;
+ struct i2400m_tlv_rf_operation sw_rf;
+ } __packed *cmd;
+ char strerr[32];
+
+ d_fnstart(4, dev, "(wimax_dev %p state %d)\n", wimax_dev, state);
+
+ result = -ENOMEM;
+ cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+ if (cmd == NULL)
+ goto error_alloc;
+ cmd->hdr.type = cpu_to_le16(I2400M_MT_CMD_RF_CONTROL);
+ cmd->hdr.length = sizeof(cmd->sw_rf);
+ cmd->hdr.version = cpu_to_le16(I2400M_L3L4_VERSION);
+ cmd->sw_rf.hdr.type = cpu_to_le16(I2400M_TLV_RF_OPERATION);
+ cmd->sw_rf.hdr.length = cpu_to_le16(sizeof(cmd->sw_rf.status));
+ switch (state) {
+ case WIMAX_RF_OFF: /* RFKILL ON, radio OFF */
+ cmd->sw_rf.status = cpu_to_le32(2);
+ break;
+ case WIMAX_RF_ON: /* RFKILL OFF, radio ON */
+ cmd->sw_rf.status = cpu_to_le32(1);
+ break;
+ default:
+ BUG();
+ }
+
+ ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+ result = PTR_ERR(ack_skb);
+ if (IS_ERR(ack_skb)) {
+ dev_err(dev, "Failed to issue 'RF Control' command: %d\n",
+ result);
+ goto error_msg_to_dev;
+ }
+ result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
+ strerr, sizeof(strerr));
+ if (result < 0) {
+ dev_err(dev, "'RF Control' (0x%04x) command failed: %d - %s\n",
+ I2400M_MT_CMD_RF_CONTROL, result, strerr);
+ goto error_cmd;
+ }
+
+ /* Now we wait for the state to change to RADIO_OFF or RADIO_ON */
+ result = wait_event_timeout(
+ i2400m->state_wq, i2400m_radio_is(i2400m, state),
+ 5 * HZ);
+ if (result == 0)
+ result = -ETIMEDOUT;
+ if (result < 0)
+ dev_err(dev, "Error waiting for device to toggle RF state: "
+ "%d\n", result);
+ result = 0;
+error_cmd:
+ kfree_skb(ack_skb);
+error_msg_to_dev:
+error_alloc:
+ d_fnend(4, dev, "(wimax_dev %p state %d) = %d\n",
+ wimax_dev, state, result);
+ kfree(cmd);
+ return result;
+}
+
+
+/*
+ * Inform the WiMAX stack of changes in the RF Kill switches reported
+ * by the device
+ *
+ * @i2400m: device descriptor
+ * @rfss: TLV for RF Switches status; already validated
+ *
+ * NOTE: the reports on RF switch status cannot be trusted
+ * or used until the device is in a state of RADIO_OFF
+ * or greater.
+ */
+void i2400m_report_tlv_rf_switches_status(
+ struct i2400m *i2400m,
+ const struct i2400m_tlv_rf_switches_status *rfss)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ enum i2400m_rf_switch_status hw, sw;
+ enum wimax_st wimax_state;
+
+ sw = le32_to_cpu(rfss->sw_rf_switch);
+ hw = le32_to_cpu(rfss->hw_rf_switch);
+
+ d_fnstart(3, dev, "(i2400m %p rfss %p [hw %u sw %u])\n",
+ i2400m, rfss, hw, sw);
+ /* We only process rw switch evens when the device has been
+ * fully initialized */
+ wimax_state = wimax_state_get(&i2400m->wimax_dev);
+ if (wimax_state < WIMAX_ST_RADIO_OFF) {
+ d_printf(3, dev, "ignoring RF switches report, state %u\n",
+ wimax_state);
+ goto out;
+ }
+ switch (sw) {
+ case I2400M_RF_SWITCH_ON: /* RF Kill disabled (radio on) */
+ wimax_report_rfkill_sw(&i2400m->wimax_dev, WIMAX_RF_ON);
+ break;
+ case I2400M_RF_SWITCH_OFF: /* RF Kill enabled (radio off) */
+ wimax_report_rfkill_sw(&i2400m->wimax_dev, WIMAX_RF_OFF);
+ break;
+ default:
+ dev_err(dev, "HW BUG? Unknown RF SW state 0x%x\n", sw);
+ }
+
+ switch (hw) {
+ case I2400M_RF_SWITCH_ON: /* RF Kill disabled (radio on) */
+ wimax_report_rfkill_hw(&i2400m->wimax_dev, WIMAX_RF_ON);
+ break;
+ case I2400M_RF_SWITCH_OFF: /* RF Kill enabled (radio off) */
+ wimax_report_rfkill_hw(&i2400m->wimax_dev, WIMAX_RF_OFF);
+ break;
+ default:
+ dev_err(dev, "HW BUG? Unknown RF HW state 0x%x\n", hw);
+ }
+out:
+ d_fnend(3, dev, "(i2400m %p rfss %p [hw %u sw %u]) = void\n",
+ i2400m, rfss, hw, sw);
+}
--- /dev/null
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Handle incoming traffic and deliver it to the control or data planes
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * - Initial implementation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * - Use skb_clone(), break up processing in chunks
+ * - Split transport/device specific
+ * - Make buffer size dynamic to exert less memory pressure
+ * - RX reorder support
+ *
+ * This handles the RX path.
+ *
+ * We receive an RX message from the bus-specific driver, which
+ * contains one or more payloads that have potentially different
+ * destinataries (data or control paths).
+ *
+ * So we just take that payload from the transport specific code in
+ * the form of an skb, break it up in chunks (a cloned skb each in the
+ * case of network packets) and pass it to netdev or to the
+ * command/ack handler (and from there to the WiMAX stack).
+ *
+ * PROTOCOL FORMAT
+ *
+ * The format of the buffer is:
+ *
+ * HEADER (struct i2400m_msg_hdr)
+ * PAYLOAD DESCRIPTOR 0 (struct i2400m_pld)
+ * PAYLOAD DESCRIPTOR 1
+ * ...
+ * PAYLOAD DESCRIPTOR N
+ * PAYLOAD 0 (raw bytes)
+ * PAYLOAD 1
+ * ...
+ * PAYLOAD N
+ *
+ * See tx.c for a deeper description on alignment requirements and
+ * other fun facts of it.
+ *
+ * DATA PACKETS
+ *
+ * In firmwares <= v1.3, data packets have no header for RX, but they
+ * do for TX (currently unused).
+ *
+ * In firmware >= 1.4, RX packets have an extended header (16
+ * bytes). This header conveys information for management of host
+ * reordering of packets (the device offloads storage of the packets
+ * for reordering to the host). Read below for more information.
+ *
+ * The header is used as dummy space to emulate an ethernet header and
+ * thus be able to act as an ethernet device without having to reallocate.
+ *
+ * DATA RX REORDERING
+ *
+ * Starting in firmware v1.4, the device can deliver packets for
+ * delivery with special reordering information; this allows it to
+ * more effectively do packet management when some frames were lost in
+ * the radio traffic.
+ *
+ * Thus, for RX packets that come out of order, the device gives the
+ * driver enough information to queue them properly and then at some
+ * point, the signal to deliver the whole (or part) of the queued
+ * packets to the networking stack. There are 16 such queues.
+ *
+ * This only happens when a packet comes in with the "need reorder"
+ * flag set in the RX header. When such bit is set, the following
+ * operations might be indicated:
+ *
+ * - reset queue: send all queued packets to the OS
+ *
+ * - queue: queue a packet
+ *
+ * - update ws: update the queue's window start and deliver queued
+ * packets that meet the criteria
+ *
+ * - queue & update ws: queue a packet, update the window start and
+ * deliver queued packets that meet the criteria
+ *
+ * (delivery criteria: the packet's [normalized] sequence number is
+ * lower than the new [normalized] window start).
+ *
+ * See the i2400m_roq_*() functions for details.
+ *
+ * ROADMAP
+ *
+ * i2400m_rx
+ * i2400m_rx_msg_hdr_check
+ * i2400m_rx_pl_descr_check
+ * i2400m_rx_payload
+ * i2400m_net_rx
+ * i2400m_rx_edata
+ * i2400m_net_erx
+ * i2400m_roq_reset
+ * i2400m_net_erx
+ * i2400m_roq_queue
+ * __i2400m_roq_queue
+ * i2400m_roq_update_ws
+ * __i2400m_roq_update_ws
+ * i2400m_net_erx
+ * i2400m_roq_queue_update_ws
+ * __i2400m_roq_queue
+ * __i2400m_roq_update_ws
+ * i2400m_net_erx
+ * i2400m_rx_ctl
+ * i2400m_msg_size_check
+ * i2400m_report_hook_work [in a workqueue]
+ * i2400m_report_hook
+ * wimax_msg_to_user
+ * i2400m_rx_ctl_ack
+ * wimax_msg_to_user_alloc
+ * i2400m_rx_trace
+ * i2400m_msg_size_check
+ * wimax_msg
+ */
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/if_arp.h>
+#include <linux/netdevice.h>
+#include <linux/workqueue.h>
+#include <linux/export.h>
+#include <linux/moduleparam.h>
+#include "i2400m.h"
+
+
+#define D_SUBMODULE rx
+#include "debug-levels.h"
+
+static int i2400m_rx_reorder_disabled; /* 0 (rx reorder enabled) by default */
+module_param_named(rx_reorder_disabled, i2400m_rx_reorder_disabled, int, 0644);
+MODULE_PARM_DESC(rx_reorder_disabled,
+ "If true, RX reordering will be disabled.");
+
+struct i2400m_report_hook_args {
+ struct sk_buff *skb_rx;
+ const struct i2400m_l3l4_hdr *l3l4_hdr;
+ size_t size;
+ struct list_head list_node;
+};
+
+
+/*
+ * Execute i2400m_report_hook in a workqueue
+ *
+ * Goes over the list of queued reports in i2400m->rx_reports and
+ * processes them.
+ *
+ * NOTE: refcounts on i2400m are not needed because we flush the
+ * workqueue this runs on (i2400m->work_queue) before destroying
+ * i2400m.
+ */
+void i2400m_report_hook_work(struct work_struct *ws)
+{
+ struct i2400m *i2400m = container_of(ws, struct i2400m, rx_report_ws);
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400m_report_hook_args *args, *args_next;
+ LIST_HEAD(list);
+ unsigned long flags;
+
+ while (1) {
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ list_splice_init(&i2400m->rx_reports, &list);
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ if (list_empty(&list))
+ break;
+ else
+ d_printf(1, dev, "processing queued reports\n");
+ list_for_each_entry_safe(args, args_next, &list, list_node) {
+ d_printf(2, dev, "processing queued report %p\n", args);
+ i2400m_report_hook(i2400m, args->l3l4_hdr, args->size);
+ kfree_skb(args->skb_rx);
+ list_del(&args->list_node);
+ kfree(args);
+ }
+ }
+}
+
+
+/*
+ * Flush the list of queued reports
+ */
+static
+void i2400m_report_hook_flush(struct i2400m *i2400m)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400m_report_hook_args *args, *args_next;
+ LIST_HEAD(list);
+ unsigned long flags;
+
+ d_printf(1, dev, "flushing queued reports\n");
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ list_splice_init(&i2400m->rx_reports, &list);
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ list_for_each_entry_safe(args, args_next, &list, list_node) {
+ d_printf(2, dev, "flushing queued report %p\n", args);
+ kfree_skb(args->skb_rx);
+ list_del(&args->list_node);
+ kfree(args);
+ }
+}
+
+
+/*
+ * Queue a report for later processing
+ *
+ * @i2400m: device descriptor
+ * @skb_rx: skb that contains the payload (for reference counting)
+ * @l3l4_hdr: pointer to the control
+ * @size: size of the message
+ */
+static
+void i2400m_report_hook_queue(struct i2400m *i2400m, struct sk_buff *skb_rx,
+ const void *l3l4_hdr, size_t size)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ unsigned long flags;
+ struct i2400m_report_hook_args *args;
+
+ args = kzalloc(sizeof(*args), GFP_NOIO);
+ if (args) {
+ args->skb_rx = skb_get(skb_rx);
+ args->l3l4_hdr = l3l4_hdr;
+ args->size = size;
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ list_add_tail(&args->list_node, &i2400m->rx_reports);
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ d_printf(2, dev, "queued report %p\n", args);
+ rmb(); /* see i2400m->ready's documentation */
+ if (likely(i2400m->ready)) /* only send if up */
+ queue_work(i2400m->work_queue, &i2400m->rx_report_ws);
+ } else {
+ if (printk_ratelimit())
+ dev_err(dev, "%s:%u: Can't allocate %zu B\n",
+ __func__, __LINE__, sizeof(*args));
+ }
+}
+
+
+/*
+ * Process an ack to a command
+ *
+ * @i2400m: device descriptor
+ * @payload: pointer to message
+ * @size: size of the message
+ *
+ * Pass the acknodledgment (in an skb) to the thread that is waiting
+ * for it in i2400m->msg_completion.
+ *
+ * We need to coordinate properly with the thread waiting for the
+ * ack. Check if it is waiting or if it is gone. We loose the spinlock
+ * to avoid allocating on atomic contexts (yeah, could use GFP_ATOMIC,
+ * but this is not so speed critical).
+ */
+static
+void i2400m_rx_ctl_ack(struct i2400m *i2400m,
+ const void *payload, size_t size)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+ unsigned long flags;
+ struct sk_buff *ack_skb;
+
+ /* Anyone waiting for an answer? */
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ if (i2400m->ack_skb != ERR_PTR(-EINPROGRESS)) {
+ dev_err(dev, "Huh? reply to command with no waiters\n");
+ goto error_no_waiter;
+ }
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+
+ ack_skb = wimax_msg_alloc(wimax_dev, NULL, payload, size, GFP_KERNEL);
+
+ /* Check waiter didn't time out waiting for the answer... */
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ if (i2400m->ack_skb != ERR_PTR(-EINPROGRESS)) {
+ d_printf(1, dev, "Huh? waiter for command reply cancelled\n");
+ goto error_waiter_cancelled;
+ }
+ if (IS_ERR(ack_skb))
+ dev_err(dev, "CMD/GET/SET ack: cannot allocate SKB\n");
+ i2400m->ack_skb = ack_skb;
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ complete(&i2400m->msg_completion);
+ return;
+
+error_waiter_cancelled:
+ if (!IS_ERR(ack_skb))
+ kfree_skb(ack_skb);
+error_no_waiter:
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+}
+
+
+/*
+ * Receive and process a control payload
+ *
+ * @i2400m: device descriptor
+ * @skb_rx: skb that contains the payload (for reference counting)
+ * @payload: pointer to message
+ * @size: size of the message
+ *
+ * There are two types of control RX messages: reports (asynchronous,
+ * like your every day interrupts) and 'acks' (reponses to a command,
+ * get or set request).
+ *
+ * If it is a report, we run hooks on it (to extract information for
+ * things we need to do in the driver) and then pass it over to the
+ * WiMAX stack to send it to user space.
+ *
+ * NOTE: report processing is done in a workqueue specific to the
+ * generic driver, to avoid deadlocks in the system.
+ *
+ * If it is not a report, it is an ack to a previously executed
+ * command, set or get, so wake up whoever is waiting for it from
+ * i2400m_msg_to_dev(). i2400m_rx_ctl_ack() takes care of that.
+ *
+ * Note that the sizes we pass to other functions from here are the
+ * sizes of the _l3l4_hdr + payload, not full buffer sizes, as we have
+ * verified in _msg_size_check() that they are congruent.
+ *
+ * For reports: We can't clone the original skb where the data is
+ * because we need to send this up via netlink; netlink has to add
+ * headers and we can't overwrite what's preceding the payload...as
+ * it is another message. So we just dup them.
+ */
+static
+void i2400m_rx_ctl(struct i2400m *i2400m, struct sk_buff *skb_rx,
+ const void *payload, size_t size)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ const struct i2400m_l3l4_hdr *l3l4_hdr = payload;
+ unsigned msg_type;
+
+ result = i2400m_msg_size_check(i2400m, l3l4_hdr, size);
+ if (result < 0) {
+ dev_err(dev, "HW BUG? device sent a bad message: %d\n",
+ result);
+ goto error_check;
+ }
+ msg_type = le16_to_cpu(l3l4_hdr->type);
+ d_printf(1, dev, "%s 0x%04x: %zu bytes\n",
+ msg_type & I2400M_MT_REPORT_MASK ? "REPORT" : "CMD/SET/GET",
+ msg_type, size);
+ d_dump(2, dev, l3l4_hdr, size);
+ if (msg_type & I2400M_MT_REPORT_MASK) {
+ /*
+ * Process each report
+ *
+ * - has to be ran serialized as well
+ *
+ * - the handling might force the execution of
+ * commands. That might cause reentrancy issues with
+ * bus-specific subdrivers and workqueues, so the we
+ * run it in a separate workqueue.
+ *
+ * - when the driver is not yet ready to handle them,
+ * they are queued and at some point the queue is
+ * restarted [NOTE: we can't queue SKBs directly, as
+ * this might be a piece of a SKB, not the whole
+ * thing, and this is cheaper than cloning the
+ * SKB].
+ *
+ * Note we don't do refcounting for the device
+ * structure; this is because before destroying
+ * 'i2400m', we make sure to flush the
+ * i2400m->work_queue, so there are no issues.
+ */
+ i2400m_report_hook_queue(i2400m, skb_rx, l3l4_hdr, size);
+ if (unlikely(i2400m->trace_msg_from_user))
+ wimax_msg(&i2400m->wimax_dev, "echo",
+ l3l4_hdr, size, GFP_KERNEL);
+ result = wimax_msg(&i2400m->wimax_dev, NULL, l3l4_hdr, size,
+ GFP_KERNEL);
+ if (result < 0)
+ dev_err(dev, "error sending report to userspace: %d\n",
+ result);
+ } else /* an ack to a CMD, GET or SET */
+ i2400m_rx_ctl_ack(i2400m, payload, size);
+error_check:
+ return;
+}
+
+
+/*
+ * Receive and send up a trace
+ *
+ * @i2400m: device descriptor
+ * @skb_rx: skb that contains the trace (for reference counting)
+ * @payload: pointer to trace message inside the skb
+ * @size: size of the message
+ *
+ * THe i2400m might produce trace information (diagnostics) and we
+ * send them through a different kernel-to-user pipe (to avoid
+ * clogging it).
+ *
+ * As in i2400m_rx_ctl(), we can't clone the original skb where the
+ * data is because we need to send this up via netlink; netlink has to
+ * add headers and we can't overwrite what's preceding the
+ * payload...as it is another message. So we just dup them.
+ */
+static
+void i2400m_rx_trace(struct i2400m *i2400m,
+ const void *payload, size_t size)
+{
+ int result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+ const struct i2400m_l3l4_hdr *l3l4_hdr = payload;
+ unsigned msg_type;
+
+ result = i2400m_msg_size_check(i2400m, l3l4_hdr, size);
+ if (result < 0) {
+ dev_err(dev, "HW BUG? device sent a bad trace message: %d\n",
+ result);
+ goto error_check;
+ }
+ msg_type = le16_to_cpu(l3l4_hdr->type);
+ d_printf(1, dev, "Trace %s 0x%04x: %zu bytes\n",
+ msg_type & I2400M_MT_REPORT_MASK ? "REPORT" : "CMD/SET/GET",
+ msg_type, size);
+ d_dump(2, dev, l3l4_hdr, size);
+ result = wimax_msg(wimax_dev, "trace", l3l4_hdr, size, GFP_KERNEL);
+ if (result < 0)
+ dev_err(dev, "error sending trace to userspace: %d\n",
+ result);
+error_check:
+ return;
+}
+
+
+/*
+ * Reorder queue data stored on skb->cb while the skb is queued in the
+ * reorder queues.
+ */
+struct i2400m_roq_data {
+ unsigned sn; /* Serial number for the skb */
+ enum i2400m_cs cs; /* packet type for the skb */
+};
+
+
+/*
+ * ReOrder Queue
+ *
+ * @ws: Window Start; sequence number where the current window start
+ * is for this queue
+ * @queue: the skb queue itself
+ * @log: circular ring buffer used to log information about the
+ * reorder process in this queue that can be displayed in case of
+ * error to help diagnose it.
+ *
+ * This is the head for a list of skbs. In the skb->cb member of the
+ * skb when queued here contains a 'struct i2400m_roq_data' were we
+ * store the sequence number (sn) and the cs (packet type) coming from
+ * the RX payload header from the device.
+ */
+struct i2400m_roq
+{
+ unsigned ws;
+ struct sk_buff_head queue;
+ struct i2400m_roq_log *log;
+};
+
+
+static
+void __i2400m_roq_init(struct i2400m_roq *roq)
+{
+ roq->ws = 0;
+ skb_queue_head_init(&roq->queue);
+}
+
+
+static
+unsigned __i2400m_roq_index(struct i2400m *i2400m, struct i2400m_roq *roq)
+{
+ return ((unsigned long) roq - (unsigned long) i2400m->rx_roq)
+ / sizeof(*roq);
+}
+
+
+/*
+ * Normalize a sequence number based on the queue's window start
+ *
+ * nsn = (sn - ws) % 2048
+ *
+ * Note that if @sn < @roq->ws, we still need a positive number; %'s
+ * sign is implementation specific, so we normalize it by adding 2048
+ * to bring it to be positive.
+ */
+static
+unsigned __i2400m_roq_nsn(struct i2400m_roq *roq, unsigned sn)
+{
+ int r;
+ r = ((int) sn - (int) roq->ws) % 2048;
+ if (r < 0)
+ r += 2048;
+ return r;
+}
+
+
+/*
+ * Circular buffer to keep the last N reorder operations
+ *
+ * In case something fails, dumb then to try to come up with what
+ * happened.
+ */
+enum {
+ I2400M_ROQ_LOG_LENGTH = 32,
+};
+
+struct i2400m_roq_log {
+ struct i2400m_roq_log_entry {
+ enum i2400m_ro_type type;
+ unsigned ws, count, sn, nsn, new_ws;
+ } entry[I2400M_ROQ_LOG_LENGTH];
+ unsigned in, out;
+};
+
+
+/* Print a log entry */
+static
+void i2400m_roq_log_entry_print(struct i2400m *i2400m, unsigned index,
+ unsigned e_index,
+ struct i2400m_roq_log_entry *e)
+{
+ struct device *dev = i2400m_dev(i2400m);
+
+ switch(e->type) {
+ case I2400M_RO_TYPE_RESET:
+ dev_err(dev, "q#%d reset ws %u cnt %u sn %u/%u"
+ " - new nws %u\n",
+ index, e->ws, e->count, e->sn, e->nsn, e->new_ws);
+ break;
+ case I2400M_RO_TYPE_PACKET:
+ dev_err(dev, "q#%d queue ws %u cnt %u sn %u/%u\n",
+ index, e->ws, e->count, e->sn, e->nsn);
+ break;
+ case I2400M_RO_TYPE_WS:
+ dev_err(dev, "q#%d update_ws ws %u cnt %u sn %u/%u"
+ " - new nws %u\n",
+ index, e->ws, e->count, e->sn, e->nsn, e->new_ws);
+ break;
+ case I2400M_RO_TYPE_PACKET_WS:
+ dev_err(dev, "q#%d queue_update_ws ws %u cnt %u sn %u/%u"
+ " - new nws %u\n",
+ index, e->ws, e->count, e->sn, e->nsn, e->new_ws);
+ break;
+ default:
+ dev_err(dev, "q#%d BUG? entry %u - unknown type %u\n",
+ index, e_index, e->type);
+ break;
+ }
+}
+
+
+static
+void i2400m_roq_log_add(struct i2400m *i2400m,
+ struct i2400m_roq *roq, enum i2400m_ro_type type,
+ unsigned ws, unsigned count, unsigned sn,
+ unsigned nsn, unsigned new_ws)
+{
+ struct i2400m_roq_log_entry *e;
+ unsigned cnt_idx;
+ int index = __i2400m_roq_index(i2400m, roq);
+
+ /* if we run out of space, we eat from the end */
+ if (roq->log->in - roq->log->out == I2400M_ROQ_LOG_LENGTH)
+ roq->log->out++;
+ cnt_idx = roq->log->in++ % I2400M_ROQ_LOG_LENGTH;
+ e = &roq->log->entry[cnt_idx];
+
+ e->type = type;
+ e->ws = ws;
+ e->count = count;
+ e->sn = sn;
+ e->nsn = nsn;
+ e->new_ws = new_ws;
+
+ if (d_test(1))
+ i2400m_roq_log_entry_print(i2400m, index, cnt_idx, e);
+}
+
+
+/* Dump all the entries in the FIFO and reinitialize it */
+static
+void i2400m_roq_log_dump(struct i2400m *i2400m, struct i2400m_roq *roq)
+{
+ unsigned cnt, cnt_idx;
+ struct i2400m_roq_log_entry *e;
+ int index = __i2400m_roq_index(i2400m, roq);
+
+ BUG_ON(roq->log->out > roq->log->in);
+ for (cnt = roq->log->out; cnt < roq->log->in; cnt++) {
+ cnt_idx = cnt % I2400M_ROQ_LOG_LENGTH;
+ e = &roq->log->entry[cnt_idx];
+ i2400m_roq_log_entry_print(i2400m, index, cnt_idx, e);
+ memset(e, 0, sizeof(*e));
+ }
+ roq->log->in = roq->log->out = 0;
+}
+
+
+/*
+ * Backbone for the queuing of an skb (by normalized sequence number)
+ *
+ * @i2400m: device descriptor
+ * @roq: reorder queue where to add
+ * @skb: the skb to add
+ * @sn: the sequence number of the skb
+ * @nsn: the normalized sequence number of the skb (pre-computed by the
+ * caller from the @sn and @roq->ws).
+ *
+ * We try first a couple of quick cases:
+ *
+ * - the queue is empty
+ * - the skb would be appended to the queue
+ *
+ * These will be the most common operations.
+ *
+ * If these fail, then we have to do a sorted insertion in the queue,
+ * which is the slowest path.
+ *
+ * We don't have to acquire a reference count as we are going to own it.
+ */
+static
+void __i2400m_roq_queue(struct i2400m *i2400m, struct i2400m_roq *roq,
+ struct sk_buff *skb, unsigned sn, unsigned nsn)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *skb_itr;
+ struct i2400m_roq_data *roq_data_itr, *roq_data;
+ unsigned nsn_itr;
+
+ d_fnstart(4, dev, "(i2400m %p roq %p skb %p sn %u nsn %u)\n",
+ i2400m, roq, skb, sn, nsn);
+
+ roq_data = (struct i2400m_roq_data *) &skb->cb;
+ BUILD_BUG_ON(sizeof(*roq_data) > sizeof(skb->cb));
+ roq_data->sn = sn;
+ d_printf(3, dev, "ERX: roq %p [ws %u] nsn %d sn %u\n",
+ roq, roq->ws, nsn, roq_data->sn);
+
+ /* Queues will be empty on not-so-bad environments, so try
+ * that first */
+ if (skb_queue_empty(&roq->queue)) {
+ d_printf(2, dev, "ERX: roq %p - first one\n", roq);
+ __skb_queue_head(&roq->queue, skb);
+ goto out;
+ }
+ /* Now try append, as most of the operations will be that */
+ skb_itr = skb_peek_tail(&roq->queue);
+ roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
+ nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
+ /* NSN bounds assumed correct (checked when it was queued) */
+ if (nsn >= nsn_itr) {
+ d_printf(2, dev, "ERX: roq %p - appended after %p (nsn %d sn %u)\n",
+ roq, skb_itr, nsn_itr, roq_data_itr->sn);
+ __skb_queue_tail(&roq->queue, skb);
+ goto out;
+ }
+ /* None of the fast paths option worked. Iterate to find the
+ * right spot where to insert the packet; we know the queue is
+ * not empty, so we are not the first ones; we also know we
+ * are not going to be the last ones. The list is sorted, so
+ * we have to insert before the the first guy with an nsn_itr
+ * greater that our nsn. */
+ skb_queue_walk(&roq->queue, skb_itr) {
+ roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
+ nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
+ /* NSN bounds assumed correct (checked when it was queued) */
+ if (nsn_itr > nsn) {
+ d_printf(2, dev, "ERX: roq %p - queued before %p "
+ "(nsn %d sn %u)\n", roq, skb_itr, nsn_itr,
+ roq_data_itr->sn);
+ __skb_queue_before(&roq->queue, skb_itr, skb);
+ goto out;
+ }
+ }
+ /* If we get here, that is VERY bad -- print info to help
+ * diagnose and crash it */
+ dev_err(dev, "SW BUG? failed to insert packet\n");
+ dev_err(dev, "ERX: roq %p [ws %u] skb %p nsn %d sn %u\n",
+ roq, roq->ws, skb, nsn, roq_data->sn);
+ skb_queue_walk(&roq->queue, skb_itr) {
+ roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
+ nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
+ /* NSN bounds assumed correct (checked when it was queued) */
+ dev_err(dev, "ERX: roq %p skb_itr %p nsn %d sn %u\n",
+ roq, skb_itr, nsn_itr, roq_data_itr->sn);
+ }
+ BUG();
+out:
+ d_fnend(4, dev, "(i2400m %p roq %p skb %p sn %u nsn %d) = void\n",
+ i2400m, roq, skb, sn, nsn);
+}
+
+
+/*
+ * Backbone for the update window start operation
+ *
+ * @i2400m: device descriptor
+ * @roq: Reorder queue
+ * @sn: New sequence number
+ *
+ * Updates the window start of a queue; when doing so, it must deliver
+ * to the networking stack all the queued skb's whose normalized
+ * sequence number is lower than the new normalized window start.
+ */
+static
+unsigned __i2400m_roq_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
+ unsigned sn)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *skb_itr, *tmp_itr;
+ struct i2400m_roq_data *roq_data_itr;
+ unsigned new_nws, nsn_itr;
+
+ new_nws = __i2400m_roq_nsn(roq, sn);
+ /*
+ * For type 2(update_window_start) rx messages, there is no
+ * need to check if the normalized sequence number is greater 1023.
+ * Simply insert and deliver all packets to the host up to the
+ * window start.
+ */
+ skb_queue_walk_safe(&roq->queue, skb_itr, tmp_itr) {
+ roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
+ nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
+ /* NSN bounds assumed correct (checked when it was queued) */
+ if (nsn_itr < new_nws) {
+ d_printf(2, dev, "ERX: roq %p - release skb %p "
+ "(nsn %u/%u new nws %u)\n",
+ roq, skb_itr, nsn_itr, roq_data_itr->sn,
+ new_nws);
+ __skb_unlink(skb_itr, &roq->queue);
+ i2400m_net_erx(i2400m, skb_itr, roq_data_itr->cs);
+ }
+ else
+ break; /* rest of packets all nsn_itr > nws */
+ }
+ roq->ws = sn;
+ return new_nws;
+}
+
+
+/*
+ * Reset a queue
+ *
+ * @i2400m: device descriptor
+ * @cin: Queue Index
+ *
+ * Deliver all the packets and reset the window-start to zero. Name is
+ * kind of misleading.
+ */
+static
+void i2400m_roq_reset(struct i2400m *i2400m, struct i2400m_roq *roq)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ struct sk_buff *skb_itr, *tmp_itr;
+ struct i2400m_roq_data *roq_data_itr;
+
+ d_fnstart(2, dev, "(i2400m %p roq %p)\n", i2400m, roq);
+ i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_RESET,
+ roq->ws, skb_queue_len(&roq->queue),
+ ~0, ~0, 0);
+ skb_queue_walk_safe(&roq->queue, skb_itr, tmp_itr) {
+ roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
+ d_printf(2, dev, "ERX: roq %p - release skb %p (sn %u)\n",
+ roq, skb_itr, roq_data_itr->sn);
+ __skb_unlink(skb_itr, &roq->queue);
+ i2400m_net_erx(i2400m, skb_itr, roq_data_itr->cs);
+ }
+ roq->ws = 0;
+ d_fnend(2, dev, "(i2400m %p roq %p) = void\n", i2400m, roq);
+}
+
+
+/*
+ * Queue a packet
+ *
+ * @i2400m: device descriptor
+ * @cin: Queue Index
+ * @skb: containing the packet data
+ * @fbn: First block number of the packet in @skb
+ * @lbn: Last block number of the packet in @skb
+ *
+ * The hardware is asking the driver to queue a packet for later
+ * delivery to the networking stack.
+ */
+static
+void i2400m_roq_queue(struct i2400m *i2400m, struct i2400m_roq *roq,
+ struct sk_buff * skb, unsigned lbn)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ unsigned nsn, len;
+
+ d_fnstart(2, dev, "(i2400m %p roq %p skb %p lbn %u) = void\n",
+ i2400m, roq, skb, lbn);
+ len = skb_queue_len(&roq->queue);
+ nsn = __i2400m_roq_nsn(roq, lbn);
+ if (unlikely(nsn >= 1024)) {
+ dev_err(dev, "SW BUG? queue nsn %d (lbn %u ws %u)\n",
+ nsn, lbn, roq->ws);
+ i2400m_roq_log_dump(i2400m, roq);
+ i2400m_reset(i2400m, I2400M_RT_WARM);
+ } else {
+ __i2400m_roq_queue(i2400m, roq, skb, lbn, nsn);
+ i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_PACKET,
+ roq->ws, len, lbn, nsn, ~0);
+ }
+ d_fnend(2, dev, "(i2400m %p roq %p skb %p lbn %u) = void\n",
+ i2400m, roq, skb, lbn);
+}
+
+
+/*
+ * Update the window start in a reorder queue and deliver all skbs
+ * with a lower window start
+ *
+ * @i2400m: device descriptor
+ * @roq: Reorder queue
+ * @sn: New sequence number
+ */
+static
+void i2400m_roq_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
+ unsigned sn)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ unsigned old_ws, nsn, len;
+
+ d_fnstart(2, dev, "(i2400m %p roq %p sn %u)\n", i2400m, roq, sn);
+ old_ws = roq->ws;
+ len = skb_queue_len(&roq->queue);
+ nsn = __i2400m_roq_update_ws(i2400m, roq, sn);
+ i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_WS,
+ old_ws, len, sn, nsn, roq->ws);
+ d_fnstart(2, dev, "(i2400m %p roq %p sn %u) = void\n", i2400m, roq, sn);
+}
+
+
+/*
+ * Queue a packet and update the window start
+ *
+ * @i2400m: device descriptor
+ * @cin: Queue Index
+ * @skb: containing the packet data
+ * @fbn: First block number of the packet in @skb
+ * @sn: Last block number of the packet in @skb
+ *
+ * Note that unlike i2400m_roq_update_ws(), which sets the new window
+ * start to @sn, in here we'll set it to @sn + 1.
+ */
+static
+void i2400m_roq_queue_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
+ struct sk_buff * skb, unsigned sn)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ unsigned nsn, old_ws, len;
+
+ d_fnstart(2, dev, "(i2400m %p roq %p skb %p sn %u)\n",
+ i2400m, roq, skb, sn);
+ len = skb_queue_len(&roq->queue);
+ nsn = __i2400m_roq_nsn(roq, sn);
+ /*
+ * For type 3(queue_update_window_start) rx messages, there is no
+ * need to check if the normalized sequence number is greater 1023.
+ * Simply insert and deliver all packets to the host up to the
+ * window start.
+ */
+ old_ws = roq->ws;
+ /* If the queue is empty, don't bother as we'd queue
+ * it and immediately unqueue it -- just deliver it.
+ */
+ if (len == 0) {
+ struct i2400m_roq_data *roq_data;
+ roq_data = (struct i2400m_roq_data *) &skb->cb;
+ i2400m_net_erx(i2400m, skb, roq_data->cs);
+ } else
+ __i2400m_roq_queue(i2400m, roq, skb, sn, nsn);
+
+ __i2400m_roq_update_ws(i2400m, roq, sn + 1);
+ i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_PACKET_WS,
+ old_ws, len, sn, nsn, roq->ws);
+
+ d_fnend(2, dev, "(i2400m %p roq %p skb %p sn %u) = void\n",
+ i2400m, roq, skb, sn);
+}
+
+
+/*
+ * This routine destroys the memory allocated for rx_roq, when no
+ * other thread is accessing it. Access to rx_roq is refcounted by
+ * rx_roq_refcount, hence memory allocated must be destroyed when
+ * rx_roq_refcount becomes zero. This routine gets executed when
+ * rx_roq_refcount becomes zero.
+ */
+static void i2400m_rx_roq_destroy(struct kref *ref)
+{
+ unsigned itr;
+ struct i2400m *i2400m
+ = container_of(ref, struct i2400m, rx_roq_refcount);
+ for (itr = 0; itr < I2400M_RO_CIN + 1; itr++)
+ __skb_queue_purge(&i2400m->rx_roq[itr].queue);
+ kfree(i2400m->rx_roq[0].log);
+ kfree(i2400m->rx_roq);
+ i2400m->rx_roq = NULL;
+}
+
+/*
+ * Receive and send up an extended data packet
+ *
+ * @i2400m: device descriptor
+ * @skb_rx: skb that contains the extended data packet
+ * @single_last: 1 if the payload is the only one or the last one of
+ * the skb.
+ * @payload: pointer to the packet's data inside the skb
+ * @size: size of the payload
+ *
+ * Starting in v1.4 of the i2400m's firmware, the device can send data
+ * packets to the host in an extended format that; this incudes a 16
+ * byte header (struct i2400m_pl_edata_hdr). Using this header's space
+ * we can fake ethernet headers for ethernet device emulation without
+ * having to copy packets around.
+ *
+ * This function handles said path.
+ *
+ *
+ * Receive and send up an extended data packet that requires no reordering
+ *
+ * @i2400m: device descriptor
+ * @skb_rx: skb that contains the extended data packet
+ * @single_last: 1 if the payload is the only one or the last one of
+ * the skb.
+ * @payload: pointer to the packet's data (past the actual extended
+ * data payload header).
+ * @size: size of the payload
+ *
+ * Pass over to the networking stack a data packet that might have
+ * reordering requirements.
+ *
+ * This needs to the decide if the skb in which the packet is
+ * contained can be reused or if it needs to be cloned. Then it has to
+ * be trimmed in the edges so that the beginning is the space for eth
+ * header and then pass it to i2400m_net_erx() for the stack
+ *
+ * Assumes the caller has verified the sanity of the payload (size,
+ * etc) already.
+ */
+static
+void i2400m_rx_edata(struct i2400m *i2400m, struct sk_buff *skb_rx,
+ unsigned single_last, const void *payload, size_t size)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ const struct i2400m_pl_edata_hdr *hdr = payload;
+ struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+ struct sk_buff *skb;
+ enum i2400m_cs cs;
+ u32 reorder;
+ unsigned ro_needed, ro_type, ro_cin, ro_sn;
+ struct i2400m_roq *roq;
+ struct i2400m_roq_data *roq_data;
+ unsigned long flags;
+
+ BUILD_BUG_ON(ETH_HLEN > sizeof(*hdr));
+
+ d_fnstart(2, dev, "(i2400m %p skb_rx %p single %u payload %p "
+ "size %zu)\n", i2400m, skb_rx, single_last, payload, size);
+ if (size < sizeof(*hdr)) {
+ dev_err(dev, "ERX: HW BUG? message with short header (%zu "
+ "vs %zu bytes expected)\n", size, sizeof(*hdr));
+ goto error;
+ }
+
+ if (single_last) {
+ skb = skb_get(skb_rx);
+ d_printf(3, dev, "ERX: skb %p reusing\n", skb);
+ } else {
+ skb = skb_clone(skb_rx, GFP_KERNEL);
+ if (skb == NULL) {
+ dev_err(dev, "ERX: no memory to clone skb\n");
+ net_dev->stats.rx_dropped++;
+ goto error_skb_clone;
+ }
+ d_printf(3, dev, "ERX: skb %p cloned from %p\n", skb, skb_rx);
+ }
+ /* now we have to pull and trim so that the skb points to the
+ * beginning of the IP packet; the netdev part will add the
+ * ethernet header as needed - we know there is enough space
+ * because we checked in i2400m_rx_edata(). */
+ skb_pull(skb, payload + sizeof(*hdr) - (void *) skb->data);
+ skb_trim(skb, (void *) skb_end_pointer(skb) - payload - sizeof(*hdr));
+
+ reorder = le32_to_cpu(hdr->reorder);
+ ro_needed = reorder & I2400M_RO_NEEDED;
+ cs = hdr->cs;
+ if (ro_needed) {
+ ro_type = (reorder >> I2400M_RO_TYPE_SHIFT) & I2400M_RO_TYPE;
+ ro_cin = (reorder >> I2400M_RO_CIN_SHIFT) & I2400M_RO_CIN;
+ ro_sn = (reorder >> I2400M_RO_SN_SHIFT) & I2400M_RO_SN;
+
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ if (i2400m->rx_roq == NULL) {
+ kfree_skb(skb); /* rx_roq is already destroyed */
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ goto error;
+ }
+ roq = &i2400m->rx_roq[ro_cin];
+ kref_get(&i2400m->rx_roq_refcount);
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+
+ roq_data = (struct i2400m_roq_data *) &skb->cb;
+ roq_data->sn = ro_sn;
+ roq_data->cs = cs;
+ d_printf(2, dev, "ERX: reorder needed: "
+ "type %u cin %u [ws %u] sn %u/%u len %zuB\n",
+ ro_type, ro_cin, roq->ws, ro_sn,
+ __i2400m_roq_nsn(roq, ro_sn), size);
+ d_dump(2, dev, payload, size);
+ switch(ro_type) {
+ case I2400M_RO_TYPE_RESET:
+ i2400m_roq_reset(i2400m, roq);
+ kfree_skb(skb); /* no data here */
+ break;
+ case I2400M_RO_TYPE_PACKET:
+ i2400m_roq_queue(i2400m, roq, skb, ro_sn);
+ break;
+ case I2400M_RO_TYPE_WS:
+ i2400m_roq_update_ws(i2400m, roq, ro_sn);
+ kfree_skb(skb); /* no data here */
+ break;
+ case I2400M_RO_TYPE_PACKET_WS:
+ i2400m_roq_queue_update_ws(i2400m, roq, skb, ro_sn);
+ break;
+ default:
+ dev_err(dev, "HW BUG? unknown reorder type %u\n", ro_type);
+ }
+
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ kref_put(&i2400m->rx_roq_refcount, i2400m_rx_roq_destroy);
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ }
+ else
+ i2400m_net_erx(i2400m, skb, cs);
+error_skb_clone:
+error:
+ d_fnend(2, dev, "(i2400m %p skb_rx %p single %u payload %p "
+ "size %zu) = void\n", i2400m, skb_rx, single_last, payload, size);
+}
+
+
+/*
+ * Act on a received payload
+ *
+ * @i2400m: device instance
+ * @skb_rx: skb where the transaction was received
+ * @single_last: 1 this is the only payload or the last one (so the
+ * skb can be reused instead of cloned).
+ * @pld: payload descriptor
+ * @payload: payload data
+ *
+ * Upon reception of a payload, look at its guts in the payload
+ * descriptor and decide what to do with it. If it is a single payload
+ * skb or if the last skb is a data packet, the skb will be referenced
+ * and modified (so it doesn't have to be cloned).
+ */
+static
+void i2400m_rx_payload(struct i2400m *i2400m, struct sk_buff *skb_rx,
+ unsigned single_last, const struct i2400m_pld *pld,
+ const void *payload)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ size_t pl_size = i2400m_pld_size(pld);
+ enum i2400m_pt pl_type = i2400m_pld_type(pld);
+
+ d_printf(7, dev, "RX: received payload type %u, %zu bytes\n",
+ pl_type, pl_size);
+ d_dump(8, dev, payload, pl_size);
+
+ switch (pl_type) {
+ case I2400M_PT_DATA:
+ d_printf(3, dev, "RX: data payload %zu bytes\n", pl_size);
+ i2400m_net_rx(i2400m, skb_rx, single_last, payload, pl_size);
+ break;
+ case I2400M_PT_CTRL:
+ i2400m_rx_ctl(i2400m, skb_rx, payload, pl_size);
+ break;
+ case I2400M_PT_TRACE:
+ i2400m_rx_trace(i2400m, payload, pl_size);
+ break;
+ case I2400M_PT_EDATA:
+ d_printf(3, dev, "ERX: data payload %zu bytes\n", pl_size);
+ i2400m_rx_edata(i2400m, skb_rx, single_last, payload, pl_size);
+ break;
+ default: /* Anything else shouldn't come to the host */
+ if (printk_ratelimit())
+ dev_err(dev, "RX: HW BUG? unexpected payload type %u\n",
+ pl_type);
+ }
+}
+
+
+/*
+ * Check a received transaction's message header
+ *
+ * @i2400m: device descriptor
+ * @msg_hdr: message header
+ * @buf_size: size of the received buffer
+ *
+ * Check that the declarations done by a RX buffer message header are
+ * sane and consistent with the amount of data that was received.
+ */
+static
+int i2400m_rx_msg_hdr_check(struct i2400m *i2400m,
+ const struct i2400m_msg_hdr *msg_hdr,
+ size_t buf_size)
+{
+ int result = -EIO;
+ struct device *dev = i2400m_dev(i2400m);
+ if (buf_size < sizeof(*msg_hdr)) {
+ dev_err(dev, "RX: HW BUG? message with short header (%zu "
+ "vs %zu bytes expected)\n", buf_size, sizeof(*msg_hdr));
+ goto error;
+ }
+ if (msg_hdr->barker != cpu_to_le32(I2400M_D2H_MSG_BARKER)) {
+ dev_err(dev, "RX: HW BUG? message received with unknown "
+ "barker 0x%08x (buf_size %zu bytes)\n",
+ le32_to_cpu(msg_hdr->barker), buf_size);
+ goto error;
+ }
+ if (msg_hdr->num_pls == 0) {
+ dev_err(dev, "RX: HW BUG? zero payload packets in message\n");
+ goto error;
+ }
+ if (le16_to_cpu(msg_hdr->num_pls) > I2400M_MAX_PLS_IN_MSG) {
+ dev_err(dev, "RX: HW BUG? message contains more payload "
+ "than maximum; ignoring.\n");
+ goto error;
+ }
+ result = 0;
+error:
+ return result;
+}
+
+
+/*
+ * Check a payload descriptor against the received data
+ *
+ * @i2400m: device descriptor
+ * @pld: payload descriptor
+ * @pl_itr: offset (in bytes) in the received buffer the payload is
+ * located
+ * @buf_size: size of the received buffer
+ *
+ * Given a payload descriptor (part of a RX buffer), check it is sane
+ * and that the data it declares fits in the buffer.
+ */
+static
+int i2400m_rx_pl_descr_check(struct i2400m *i2400m,
+ const struct i2400m_pld *pld,
+ size_t pl_itr, size_t buf_size)
+{
+ int result = -EIO;
+ struct device *dev = i2400m_dev(i2400m);
+ size_t pl_size = i2400m_pld_size(pld);
+ enum i2400m_pt pl_type = i2400m_pld_type(pld);
+
+ if (pl_size > i2400m->bus_pl_size_max) {
+ dev_err(dev, "RX: HW BUG? payload @%zu: size %zu is "
+ "bigger than maximum %zu; ignoring message\n",
+ pl_itr, pl_size, i2400m->bus_pl_size_max);
+ goto error;
+ }
+ if (pl_itr + pl_size > buf_size) { /* enough? */
+ dev_err(dev, "RX: HW BUG? payload @%zu: size %zu "
+ "goes beyond the received buffer "
+ "size (%zu bytes); ignoring message\n",
+ pl_itr, pl_size, buf_size);
+ goto error;
+ }
+ if (pl_type >= I2400M_PT_ILLEGAL) {
+ dev_err(dev, "RX: HW BUG? illegal payload type %u; "
+ "ignoring message\n", pl_type);
+ goto error;
+ }
+ result = 0;
+error:
+ return result;
+}
+
+
+/**
+ * i2400m_rx - Receive a buffer of data from the device
+ *
+ * @i2400m: device descriptor
+ * @skb: skbuff where the data has been received
+ *
+ * Parse in a buffer of data that contains an RX message sent from the
+ * device. See the file header for the format. Run all checks on the
+ * buffer header, then run over each payload's descriptors, verify
+ * their consistency and act on each payload's contents. If
+ * everything is successful, update the device's statistics.
+ *
+ * Note: You need to set the skb to contain only the length of the
+ * received buffer; for that, use skb_trim(skb, RECEIVED_SIZE).
+ *
+ * Returns:
+ *
+ * 0 if ok, < 0 errno on error
+ *
+ * If ok, this function owns now the skb and the caller DOESN'T have
+ * to run kfree_skb() on it. However, on error, the caller still owns
+ * the skb and it is responsible for releasing it.
+ */
+int i2400m_rx(struct i2400m *i2400m, struct sk_buff *skb)
+{
+ int i, result;
+ struct device *dev = i2400m_dev(i2400m);
+ const struct i2400m_msg_hdr *msg_hdr;
+ size_t pl_itr, pl_size;
+ unsigned long flags;
+ unsigned num_pls, single_last, skb_len;
+
+ skb_len = skb->len;
+ d_fnstart(4, dev, "(i2400m %p skb %p [size %u])\n",
+ i2400m, skb, skb_len);
+ msg_hdr = (void *) skb->data;
+ result = i2400m_rx_msg_hdr_check(i2400m, msg_hdr, skb_len);
+ if (result < 0)
+ goto error_msg_hdr_check;
+ result = -EIO;
+ num_pls = le16_to_cpu(msg_hdr->num_pls);
+ /* Check payload descriptor(s) */
+ pl_itr = struct_size(msg_hdr, pld, num_pls);
+ pl_itr = ALIGN(pl_itr, I2400M_PL_ALIGN);
+ if (pl_itr > skb_len) { /* got all the payload descriptors? */
+ dev_err(dev, "RX: HW BUG? message too short (%u bytes) for "
+ "%u payload descriptors (%zu each, total %zu)\n",
+ skb_len, num_pls, sizeof(msg_hdr->pld[0]), pl_itr);
+ goto error_pl_descr_short;
+ }
+ /* Walk each payload payload--check we really got it */
+ for (i = 0; i < num_pls; i++) {
+ /* work around old gcc warnings */
+ pl_size = i2400m_pld_size(&msg_hdr->pld[i]);
+ result = i2400m_rx_pl_descr_check(i2400m, &msg_hdr->pld[i],
+ pl_itr, skb_len);
+ if (result < 0)
+ goto error_pl_descr_check;
+ single_last = num_pls == 1 || i == num_pls - 1;
+ i2400m_rx_payload(i2400m, skb, single_last, &msg_hdr->pld[i],
+ skb->data + pl_itr);
+ pl_itr += ALIGN(pl_size, I2400M_PL_ALIGN);
+ cond_resched(); /* Don't monopolize */
+ }
+ kfree_skb(skb);
+ /* Update device statistics */
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ i2400m->rx_pl_num += i;
+ if (i > i2400m->rx_pl_max)
+ i2400m->rx_pl_max = i;
+ if (i < i2400m->rx_pl_min)
+ i2400m->rx_pl_min = i;
+ i2400m->rx_num++;
+ i2400m->rx_size_acc += skb_len;
+ if (skb_len < i2400m->rx_size_min)
+ i2400m->rx_size_min = skb_len;
+ if (skb_len > i2400m->rx_size_max)
+ i2400m->rx_size_max = skb_len;
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+error_pl_descr_check:
+error_pl_descr_short:
+error_msg_hdr_check:
+ d_fnend(4, dev, "(i2400m %p skb %p [size %u]) = %d\n",
+ i2400m, skb, skb_len, result);
+ return result;
+}
+EXPORT_SYMBOL_GPL(i2400m_rx);
+
+
+void i2400m_unknown_barker(struct i2400m *i2400m,
+ const void *buf, size_t size)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ char prefix[64];
+ const __le32 *barker = buf;
+ dev_err(dev, "RX: HW BUG? unknown barker %08x, "
+ "dropping %zu bytes\n", le32_to_cpu(*barker), size);
+ snprintf(prefix, sizeof(prefix), "%s %s: ",
+ dev_driver_string(dev), dev_name(dev));
+ if (size > 64) {
+ print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET,
+ 8, 4, buf, 64, 0);
+ printk(KERN_ERR "%s... (only first 64 bytes "
+ "dumped)\n", prefix);
+ } else
+ print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET,
+ 8, 4, buf, size, 0);
+}
+EXPORT_SYMBOL(i2400m_unknown_barker);
+
+
+/*
+ * Initialize the RX queue and infrastructure
+ *
+ * This sets up all the RX reordering infrastructures, which will not
+ * be used if reordering is not enabled or if the firmware does not
+ * support it. The device is told to do reordering in
+ * i2400m_dev_initialize(), where it also looks at the value of the
+ * i2400m->rx_reorder switch before taking a decission.
+ *
+ * Note we allocate the roq queues in one chunk and the actual logging
+ * support for it (logging) in another one and then we setup the
+ * pointers from the first to the last.
+ */
+int i2400m_rx_setup(struct i2400m *i2400m)
+{
+ int result = 0;
+
+ i2400m->rx_reorder = i2400m_rx_reorder_disabled? 0 : 1;
+ if (i2400m->rx_reorder) {
+ unsigned itr;
+ struct i2400m_roq_log *rd;
+
+ result = -ENOMEM;
+
+ i2400m->rx_roq = kcalloc(I2400M_RO_CIN + 1,
+ sizeof(i2400m->rx_roq[0]), GFP_KERNEL);
+ if (i2400m->rx_roq == NULL)
+ goto error_roq_alloc;
+
+ rd = kcalloc(I2400M_RO_CIN + 1, sizeof(*i2400m->rx_roq[0].log),
+ GFP_KERNEL);
+ if (rd == NULL) {
+ result = -ENOMEM;
+ goto error_roq_log_alloc;
+ }
+
+ for(itr = 0; itr < I2400M_RO_CIN + 1; itr++) {
+ __i2400m_roq_init(&i2400m->rx_roq[itr]);
+ i2400m->rx_roq[itr].log = &rd[itr];
+ }
+ kref_init(&i2400m->rx_roq_refcount);
+ }
+ return 0;
+
+error_roq_log_alloc:
+ kfree(i2400m->rx_roq);
+error_roq_alloc:
+ return result;
+}
+
+
+/* Tear down the RX queue and infrastructure */
+void i2400m_rx_release(struct i2400m *i2400m)
+{
+ unsigned long flags;
+
+ if (i2400m->rx_reorder) {
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ kref_put(&i2400m->rx_roq_refcount, i2400m_rx_roq_destroy);
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ }
+ /* at this point, nothing can be received... */
+ i2400m_report_hook_flush(i2400m);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Sysfs interfaces to show driver and device information
+ *
+ * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/spinlock.h>
+#include <linux/device.h>
+#include "i2400m.h"
+
+
+#define D_SUBMODULE sysfs
+#include "debug-levels.h"
+
+
+/*
+ * Set the idle timeout (msecs)
+ *
+ * FIXME: eventually this should be a common WiMAX stack method, but
+ * would like to wait to see how other devices manage it.
+ */
+static
+ssize_t i2400m_idle_timeout_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ ssize_t result;
+ struct i2400m *i2400m = net_dev_to_i2400m(to_net_dev(dev));
+ unsigned val;
+
+ result = -EINVAL;
+ if (sscanf(buf, "%u\n", &val) != 1)
+ goto error_no_unsigned;
+ if (val != 0 && (val < 100 || val > 300000 || val % 100 != 0)) {
+ dev_err(dev, "idle_timeout: %u: invalid msecs specification; "
+ "valid values are 0, 100-300000 in 100 increments\n",
+ val);
+ goto error_bad_value;
+ }
+ result = i2400m_set_idle_timeout(i2400m, val);
+ if (result >= 0)
+ result = size;
+error_no_unsigned:
+error_bad_value:
+ return result;
+}
+
+static
+DEVICE_ATTR_WO(i2400m_idle_timeout);
+
+static
+struct attribute *i2400m_dev_attrs[] = {
+ &dev_attr_i2400m_idle_timeout.attr,
+ NULL,
+};
+
+struct attribute_group i2400m_dev_attr_group = {
+ .name = NULL, /* we want them in the same directory */
+ .attrs = i2400m_dev_attrs,
+};
--- /dev/null
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Generic (non-bus specific) TX handling
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * - Initial implementation
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * - Rewritten to use a single FIFO to lower the memory allocation
+ * pressure and optimize cache hits when copying to the queue, as
+ * well as splitting out bus-specific code.
+ *
+ *
+ * Implements data transmission to the device; this is done through a
+ * software FIFO, as data/control frames can be coalesced (while the
+ * device is reading the previous tx transaction, others accumulate).
+ *
+ * A FIFO is used because at the end it is resource-cheaper that trying
+ * to implement scatter/gather over USB. As well, most traffic is going
+ * to be download (vs upload).
+ *
+ * The format for sending/receiving data to/from the i2400m is
+ * described in detail in rx.c:PROTOCOL FORMAT. In here we implement
+ * the transmission of that. This is split between a bus-independent
+ * part that just prepares everything and a bus-specific part that
+ * does the actual transmission over the bus to the device (in the
+ * bus-specific driver).
+ *
+ *
+ * The general format of a device-host transaction is MSG-HDR, PLD1,
+ * PLD2...PLDN, PL1, PL2,...PLN, PADDING.
+ *
+ * Because we need the send payload descriptors and then payloads and
+ * because it is kind of expensive to do scatterlists in USB (one URB
+ * per node), it becomes cheaper to append all the data to a FIFO
+ * (copying to a FIFO potentially in cache is cheaper).
+ *
+ * Then the bus-specific code takes the parts of that FIFO that are
+ * written and passes them to the device.
+ *
+ * So the concepts to keep in mind there are:
+ *
+ * We use a FIFO to queue the data in a linear buffer. We first append
+ * a MSG-HDR, space for I2400M_TX_PLD_MAX payload descriptors and then
+ * go appending payloads until we run out of space or of payload
+ * descriptors. Then we append padding to make the whole transaction a
+ * multiple of i2400m->bus_tx_block_size (as defined by the bus layer).
+ *
+ * - A TX message: a combination of a message header, payload
+ * descriptors and payloads.
+ *
+ * Open: it is marked as active (i2400m->tx_msg is valid) and we
+ * can keep adding payloads to it.
+ *
+ * Closed: we are not appending more payloads to this TX message
+ * (exahusted space in the queue, too many payloads or
+ * whichever). We have appended padding so the whole message
+ * length is aligned to i2400m->bus_tx_block_size (as set by the
+ * bus/transport layer).
+ *
+ * - Most of the time we keep a TX message open to which we append
+ * payloads.
+ *
+ * - If we are going to append and there is no more space (we are at
+ * the end of the FIFO), we close the message, mark the rest of the
+ * FIFO space unusable (skip_tail), create a new message at the
+ * beginning of the FIFO (if there is space) and append the message
+ * there.
+ *
+ * This is because we need to give linear TX messages to the bus
+ * engine. So we don't write a message to the remaining FIFO space
+ * until the tail and continue at the head of it.
+ *
+ * - We overload one of the fields in the message header to use it as
+ * 'size' of the TX message, so we can iterate over them. It also
+ * contains a flag that indicates if we have to skip it or not.
+ * When we send the buffer, we update that to its real on-the-wire
+ * value.
+ *
+ * - The MSG-HDR PLD1...PLD2 stuff has to be a size multiple of 16.
+ *
+ * It follows that if MSG-HDR says we have N messages, the whole
+ * header + descriptors is 16 + 4*N; for those to be a multiple of
+ * 16, it follows that N can be 4, 8, 12, ... (32, 48, 64, 80...
+ * bytes).
+ *
+ * So if we have only 1 payload, we have to submit a header that in
+ * all truth has space for 4.
+ *
+ * The implication is that we reserve space for 12 (64 bytes); but
+ * if we fill up only (eg) 2, our header becomes 32 bytes only. So
+ * the TX engine has to shift those 32 bytes of msg header and 2
+ * payloads and padding so that right after it the payloads start
+ * and the TX engine has to know about that.
+ *
+ * It is cheaper to move the header up than the whole payloads down.
+ *
+ * We do this in i2400m_tx_close(). See 'i2400m_msg_hdr->offset'.
+ *
+ * - Each payload has to be size-padded to 16 bytes; before appending
+ * it, we just do it.
+ *
+ * - The whole message has to be padded to i2400m->bus_tx_block_size;
+ * we do this at close time. Thus, when reserving space for the
+ * payload, we always make sure there is also free space for this
+ * padding that sooner or later will happen.
+ *
+ * When we append a message, we tell the bus specific code to kick in
+ * TXs. It will TX (in parallel) until the buffer is exhausted--hence
+ * the lockin we do. The TX code will only send a TX message at the
+ * time (which remember, might contain more than one payload). Of
+ * course, when the bus-specific driver attempts to TX a message that
+ * is still open, it gets closed first.
+ *
+ * Gee, this is messy; well a picture. In the example below we have a
+ * partially full FIFO, with a closed message ready to be delivered
+ * (with a moved message header to make sure it is size-aligned to
+ * 16), TAIL room that was unusable (and thus is marked with a message
+ * header that says 'skip this') and at the head of the buffer, an
+ * incomplete message with a couple of payloads.
+ *
+ * N ___________________________________________________
+ * | |
+ * | TAIL room |
+ * | |
+ * | msg_hdr to skip (size |= 0x80000) |
+ * |---------------------------------------------------|-------
+ * | | /|\
+ * | | |
+ * | TX message padding | |
+ * | | |
+ * | | |
+ * |- - - - - - - - - - - - - - - - - - - - - - - - - -| |
+ * | | |
+ * | payload 1 | |
+ * | | N * tx_block_size
+ * | | |
+ * |- - - - - - - - - - - - - - - - - - - - - - - - - -| |
+ * | | |
+ * | payload 1 | |
+ * | | |
+ * | | |
+ * |- - - - - - - - - - - - - - - - - - - - - - - - - -|- -|- - - -
+ * | padding 3 /|\ | | /|\
+ * | padding 2 | | | |
+ * | pld 1 32 bytes (2 * 16) | | |
+ * | pld 0 | | | |
+ * | moved msg_hdr \|/ | \|/ |
+ * |- - - - - - - - - - - - - - - - - - - - - - - - - -|- - - |
+ * | | _PLD_SIZE
+ * | unused | |
+ * | | |
+ * |- - - - - - - - - - - - - - - - - - - - - - - - - -| |
+ * | msg_hdr (size X) [this message is closed] | \|/
+ * |===================================================|========== <=== OUT
+ * | |
+ * | |
+ * | |
+ * | Free rooom |
+ * | |
+ * | |
+ * | |
+ * | |
+ * | |
+ * | |
+ * | |
+ * | |
+ * | |
+ * |===================================================|========== <=== IN
+ * | |
+ * | |
+ * | |
+ * | |
+ * | payload 1 |
+ * | |
+ * | |
+ * |- - - - - - - - - - - - - - - - - - - - - - - - - -|
+ * | |
+ * | payload 0 |
+ * | |
+ * | |
+ * |- - - - - - - - - - - - - - - - - - - - - - - - - -|
+ * | pld 11 /|\ |
+ * | ... | |
+ * | pld 1 64 bytes (2 * 16) |
+ * | pld 0 | |
+ * | msg_hdr (size X) \|/ [message is open] |
+ * 0 ---------------------------------------------------
+ *
+ *
+ * ROADMAP
+ *
+ * i2400m_tx_setup() Called by i2400m_setup
+ * i2400m_tx_release() Called by i2400m_release()
+ *
+ * i2400m_tx() Called to send data or control frames
+ * i2400m_tx_fifo_push() Allocates append-space in the FIFO
+ * i2400m_tx_new() Opens a new message in the FIFO
+ * i2400m_tx_fits() Checks if a new payload fits in the message
+ * i2400m_tx_close() Closes an open message in the FIFO
+ * i2400m_tx_skip_tail() Marks unusable FIFO tail space
+ * i2400m->bus_tx_kick()
+ *
+ * Now i2400m->bus_tx_kick() is the the bus-specific driver backend
+ * implementation; that would do:
+ *
+ * i2400m->bus_tx_kick()
+ * i2400m_tx_msg_get() Gets first message ready to go
+ * ...sends it...
+ * i2400m_tx_msg_sent() Ack the message is sent; repeat from
+ * _tx_msg_get() until it returns NULL
+ * (FIFO empty).
+ */
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include "i2400m.h"
+
+
+#define D_SUBMODULE tx
+#include "debug-levels.h"
+
+enum {
+ /**
+ * TX Buffer size
+ *
+ * Doc says maximum transaction is 16KiB. If we had 16KiB en
+ * route and 16KiB being queued, it boils down to needing
+ * 32KiB.
+ * 32KiB is insufficient for 1400 MTU, hence increasing
+ * tx buffer size to 64KiB.
+ */
+ I2400M_TX_BUF_SIZE = 65536,
+ /**
+ * Message header and payload descriptors have to be 16
+ * aligned (16 + 4 * N = 16 * M). If we take that average sent
+ * packets are MTU size (~1400-~1500) it follows that we could
+ * fit at most 10-11 payloads in one transaction. To meet the
+ * alignment requirement, that means we need to leave space
+ * for 12 (64 bytes). To simplify, we leave space for that. If
+ * at the end there are less, we pad up to the nearest
+ * multiple of 16.
+ */
+ /*
+ * According to Intel Wimax i3200, i5x50 and i6x50 specification
+ * documents, the maximum number of payloads per message can be
+ * up to 60. Increasing the number of payloads to 60 per message
+ * helps to accommodate smaller payloads in a single transaction.
+ */
+ I2400M_TX_PLD_MAX = 60,
+ I2400M_TX_PLD_SIZE = sizeof(struct i2400m_msg_hdr)
+ + I2400M_TX_PLD_MAX * sizeof(struct i2400m_pld),
+ I2400M_TX_SKIP = 0x80000000,
+ /*
+ * According to Intel Wimax i3200, i5x50 and i6x50 specification
+ * documents, the maximum size of each message can be up to 16KiB.
+ */
+ I2400M_TX_MSG_SIZE = 16384,
+};
+
+#define TAIL_FULL ((void *)~(unsigned long)NULL)
+
+/*
+ * Calculate how much tail room is available
+ *
+ * Note the trick here. This path is ONLY caleed for Case A (see
+ * i2400m_tx_fifo_push() below), where we have:
+ *
+ * Case A
+ * N ___________
+ * | tail room |
+ * | |
+ * |<- IN ->|
+ * | |
+ * | data |
+ * | |
+ * |<- OUT ->|
+ * | |
+ * | head room |
+ * 0 -----------
+ *
+ * When calculating the tail_room, tx_in might get to be zero if
+ * i2400m->tx_in is right at the end of the buffer (really full
+ * buffer) if there is no head room. In this case, tail_room would be
+ * I2400M_TX_BUF_SIZE, although it is actually zero. Hence the final
+ * mod (%) operation. However, when doing this kind of optimization,
+ * i2400m->tx_in being zero would fail, so we treat is an a special
+ * case.
+ */
+static inline
+size_t __i2400m_tx_tail_room(struct i2400m *i2400m)
+{
+ size_t tail_room;
+ size_t tx_in;
+
+ if (unlikely(i2400m->tx_in == 0))
+ return I2400M_TX_BUF_SIZE;
+ tx_in = i2400m->tx_in % I2400M_TX_BUF_SIZE;
+ tail_room = I2400M_TX_BUF_SIZE - tx_in;
+ tail_room %= I2400M_TX_BUF_SIZE;
+ return tail_room;
+}
+
+
+/*
+ * Allocate @size bytes in the TX fifo, return a pointer to it
+ *
+ * @i2400m: device descriptor
+ * @size: size of the buffer we need to allocate
+ * @padding: ensure that there is at least this many bytes of free
+ * contiguous space in the fifo. This is needed because later on
+ * we might need to add padding.
+ * @try_head: specify either to allocate head room or tail room space
+ * in the TX FIFO. This boolean is required to avoids a system hang
+ * due to an infinite loop caused by i2400m_tx_fifo_push().
+ * The caller must always try to allocate tail room space first by
+ * calling this routine with try_head = 0. In case if there
+ * is not enough tail room space but there is enough head room space,
+ * (i2400m_tx_fifo_push() returns TAIL_FULL) try to allocate head
+ * room space, by calling this routine again with try_head = 1.
+ *
+ * Returns:
+ *
+ * Pointer to the allocated space. NULL if there is no
+ * space. TAIL_FULL if there is no space at the tail but there is at
+ * the head (Case B below).
+ *
+ * These are the two basic cases we need to keep an eye for -- it is
+ * much better explained in linux/kernel/kfifo.c, but this code
+ * basically does the same. No rocket science here.
+ *
+ * Case A Case B
+ * N ___________ ___________
+ * | tail room | | data |
+ * | | | |
+ * |<- IN ->| |<- OUT ->|
+ * | | | |
+ * | data | | room |
+ * | | | |
+ * |<- OUT ->| |<- IN ->|
+ * | | | |
+ * | head room | | data |
+ * 0 ----------- -----------
+ *
+ * We allocate only *contiguous* space.
+ *
+ * We can allocate only from 'room'. In Case B, it is simple; in case
+ * A, we only try from the tail room; if it is not enough, we just
+ * fail and return TAIL_FULL and let the caller figure out if we wants to
+ * skip the tail room and try to allocate from the head.
+ *
+ * There is a corner case, wherein i2400m_tx_new() can get into
+ * an infinite loop calling i2400m_tx_fifo_push().
+ * In certain situations, tx_in would have reached on the top of TX FIFO
+ * and i2400m_tx_tail_room() returns 0, as described below:
+ *
+ * N ___________ tail room is zero
+ * |<- IN ->|
+ * | |
+ * | |
+ * | |
+ * | data |
+ * |<- OUT ->|
+ * | |
+ * | |
+ * | head room |
+ * 0 -----------
+ * During such a time, where tail room is zero in the TX FIFO and if there
+ * is a request to add a payload to TX FIFO, which calls:
+ * i2400m_tx()
+ * ->calls i2400m_tx_close()
+ * ->calls i2400m_tx_skip_tail()
+ * goto try_new;
+ * ->calls i2400m_tx_new()
+ * |----> [try_head:]
+ * infinite loop | ->calls i2400m_tx_fifo_push()
+ * | if (tail_room < needed)
+ * | if (head_room => needed)
+ * | return TAIL_FULL;
+ * |<---- goto try_head;
+ *
+ * i2400m_tx() calls i2400m_tx_close() to close the message, since there
+ * is no tail room to accommodate the payload and calls
+ * i2400m_tx_skip_tail() to skip the tail space. Now i2400m_tx() calls
+ * i2400m_tx_new() to allocate space for new message header calling
+ * i2400m_tx_fifo_push() that returns TAIL_FULL, since there is no tail space
+ * to accommodate the message header, but there is enough head space.
+ * The i2400m_tx_new() keeps re-retrying by calling i2400m_tx_fifo_push()
+ * ending up in a loop causing system freeze.
+ *
+ * This corner case is avoided by using a try_head boolean,
+ * as an argument to i2400m_tx_fifo_push().
+ *
+ * Note:
+ *
+ * Assumes i2400m->tx_lock is taken, and we use that as a barrier
+ *
+ * The indexes keep increasing and we reset them to zero when we
+ * pop data off the queue
+ */
+static
+void *i2400m_tx_fifo_push(struct i2400m *i2400m, size_t size,
+ size_t padding, bool try_head)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ size_t room, tail_room, needed_size;
+ void *ptr;
+
+ needed_size = size + padding;
+ room = I2400M_TX_BUF_SIZE - (i2400m->tx_in - i2400m->tx_out);
+ if (room < needed_size) { /* this takes care of Case B */
+ d_printf(2, dev, "fifo push %zu/%zu: no space\n",
+ size, padding);
+ return NULL;
+ }
+ /* Is there space at the tail? */
+ tail_room = __i2400m_tx_tail_room(i2400m);
+ if (!try_head && tail_room < needed_size) {
+ /*
+ * If the tail room space is not enough to push the message
+ * in the TX FIFO, then there are two possibilities:
+ * 1. There is enough head room space to accommodate
+ * this message in the TX FIFO.
+ * 2. There is not enough space in the head room and
+ * in tail room of the TX FIFO to accommodate the message.
+ * In the case (1), return TAIL_FULL so that the caller
+ * can figure out, if the caller wants to push the message
+ * into the head room space.
+ * In the case (2), return NULL, indicating that the TX FIFO
+ * cannot accommodate the message.
+ */
+ if (room - tail_room >= needed_size) {
+ d_printf(2, dev, "fifo push %zu/%zu: tail full\n",
+ size, padding);
+ return TAIL_FULL; /* There might be head space */
+ } else {
+ d_printf(2, dev, "fifo push %zu/%zu: no head space\n",
+ size, padding);
+ return NULL; /* There is no space */
+ }
+ }
+ ptr = i2400m->tx_buf + i2400m->tx_in % I2400M_TX_BUF_SIZE;
+ d_printf(2, dev, "fifo push %zu/%zu: at @%zu\n", size, padding,
+ i2400m->tx_in % I2400M_TX_BUF_SIZE);
+ i2400m->tx_in += size;
+ return ptr;
+}
+
+
+/*
+ * Mark the tail of the FIFO buffer as 'to-skip'
+ *
+ * We should never hit the BUG_ON() because all the sizes we push to
+ * the FIFO are padded to be a multiple of 16 -- the size of *msg
+ * (I2400M_PL_PAD for the payloads, I2400M_TX_PLD_SIZE for the
+ * header).
+ *
+ * Tail room can get to be zero if a message was opened when there was
+ * space only for a header. _tx_close() will mark it as to-skip (as it
+ * will have no payloads) and there will be no more space to flush, so
+ * nothing has to be done here. This is probably cheaper than ensuring
+ * in _tx_new() that there is some space for payloads...as we could
+ * always possibly hit the same problem if the payload wouldn't fit.
+ *
+ * Note:
+ *
+ * Assumes i2400m->tx_lock is taken, and we use that as a barrier
+ *
+ * This path is only taken for Case A FIFO situations [see
+ * i2400m_tx_fifo_push()]
+ */
+static
+void i2400m_tx_skip_tail(struct i2400m *i2400m)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ size_t tx_in = i2400m->tx_in % I2400M_TX_BUF_SIZE;
+ size_t tail_room = __i2400m_tx_tail_room(i2400m);
+ struct i2400m_msg_hdr *msg = i2400m->tx_buf + tx_in;
+ if (unlikely(tail_room == 0))
+ return;
+ BUG_ON(tail_room < sizeof(*msg));
+ msg->size = tail_room | I2400M_TX_SKIP;
+ d_printf(2, dev, "skip tail: skipping %zu bytes @%zu\n",
+ tail_room, tx_in);
+ i2400m->tx_in += tail_room;
+}
+
+
+/*
+ * Check if a skb will fit in the TX queue's current active TX
+ * message (if there are still descriptors left unused).
+ *
+ * Returns:
+ * 0 if the message won't fit, 1 if it will.
+ *
+ * Note:
+ *
+ * Assumes a TX message is active (i2400m->tx_msg).
+ *
+ * Assumes i2400m->tx_lock is taken, and we use that as a barrier
+ */
+static
+unsigned i2400m_tx_fits(struct i2400m *i2400m)
+{
+ struct i2400m_msg_hdr *msg_hdr = i2400m->tx_msg;
+ return le16_to_cpu(msg_hdr->num_pls) < I2400M_TX_PLD_MAX;
+
+}
+
+
+/*
+ * Start a new TX message header in the queue.
+ *
+ * Reserve memory from the base FIFO engine and then just initialize
+ * the message header.
+ *
+ * We allocate the biggest TX message header we might need (one that'd
+ * fit I2400M_TX_PLD_MAX payloads) -- when it is closed it will be
+ * 'ironed it out' and the unneeded parts removed.
+ *
+ * NOTE:
+ *
+ * Assumes that the previous message is CLOSED (eg: either
+ * there was none or 'i2400m_tx_close()' was called on it).
+ *
+ * Assumes i2400m->tx_lock is taken, and we use that as a barrier
+ */
+static
+void i2400m_tx_new(struct i2400m *i2400m)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400m_msg_hdr *tx_msg;
+ bool try_head = false;
+ BUG_ON(i2400m->tx_msg != NULL);
+ /*
+ * In certain situations, TX queue might have enough space to
+ * accommodate the new message header I2400M_TX_PLD_SIZE, but
+ * might not have enough space to accommodate the payloads.
+ * Adding bus_tx_room_min padding while allocating a new TX message
+ * increases the possibilities of including at least one payload of the
+ * size <= bus_tx_room_min.
+ */
+try_head:
+ tx_msg = i2400m_tx_fifo_push(i2400m, I2400M_TX_PLD_SIZE,
+ i2400m->bus_tx_room_min, try_head);
+ if (tx_msg == NULL)
+ goto out;
+ else if (tx_msg == TAIL_FULL) {
+ i2400m_tx_skip_tail(i2400m);
+ d_printf(2, dev, "new TX message: tail full, trying head\n");
+ try_head = true;
+ goto try_head;
+ }
+ memset(tx_msg, 0, I2400M_TX_PLD_SIZE);
+ tx_msg->size = I2400M_TX_PLD_SIZE;
+out:
+ i2400m->tx_msg = tx_msg;
+ d_printf(2, dev, "new TX message: %p @%zu\n",
+ tx_msg, (void *) tx_msg - i2400m->tx_buf);
+}
+
+
+/*
+ * Finalize the current TX message header
+ *
+ * Sets the message header to be at the proper location depending on
+ * how many descriptors we have (check documentation at the file's
+ * header for more info on that).
+ *
+ * Appends padding bytes to make sure the whole TX message (counting
+ * from the 'relocated' message header) is aligned to
+ * tx_block_size. We assume the _append() code has left enough space
+ * in the FIFO for that. If there are no payloads, just pass, as it
+ * won't be transferred.
+ *
+ * The amount of padding bytes depends on how many payloads are in the
+ * TX message, as the "msg header and payload descriptors" will be
+ * shifted up in the buffer.
+ */
+static
+void i2400m_tx_close(struct i2400m *i2400m)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400m_msg_hdr *tx_msg = i2400m->tx_msg;
+ struct i2400m_msg_hdr *tx_msg_moved;
+ size_t aligned_size, padding, hdr_size;
+ void *pad_buf;
+ unsigned num_pls;
+
+ if (tx_msg->size & I2400M_TX_SKIP) /* a skipper? nothing to do */
+ goto out;
+ num_pls = le16_to_cpu(tx_msg->num_pls);
+ /* We can get this situation when a new message was started
+ * and there was no space to add payloads before hitting the
+ tail (and taking padding into consideration). */
+ if (num_pls == 0) {
+ tx_msg->size |= I2400M_TX_SKIP;
+ goto out;
+ }
+ /* Relocate the message header
+ *
+ * Find the current header size, align it to 16 and if we need
+ * to move it so the tail is next to the payloads, move it and
+ * set the offset.
+ *
+ * If it moved, this header is good only for transmission; the
+ * original one (it is kept if we moved) is still used to
+ * figure out where the next TX message starts (and where the
+ * offset to the moved header is).
+ */
+ hdr_size = struct_size(tx_msg, pld, le16_to_cpu(tx_msg->num_pls));
+ hdr_size = ALIGN(hdr_size, I2400M_PL_ALIGN);
+ tx_msg->offset = I2400M_TX_PLD_SIZE - hdr_size;
+ tx_msg_moved = (void *) tx_msg + tx_msg->offset;
+ memmove(tx_msg_moved, tx_msg, hdr_size);
+ tx_msg_moved->size -= tx_msg->offset;
+ /*
+ * Now figure out how much we have to add to the (moved!)
+ * message so the size is a multiple of i2400m->bus_tx_block_size.
+ */
+ aligned_size = ALIGN(tx_msg_moved->size, i2400m->bus_tx_block_size);
+ padding = aligned_size - tx_msg_moved->size;
+ if (padding > 0) {
+ pad_buf = i2400m_tx_fifo_push(i2400m, padding, 0, 0);
+ if (WARN_ON(pad_buf == NULL || pad_buf == TAIL_FULL)) {
+ /* This should not happen -- append should verify
+ * there is always space left at least to append
+ * tx_block_size */
+ dev_err(dev,
+ "SW BUG! Possible data leakage from memory the "
+ "device should not read for padding - "
+ "size %lu aligned_size %zu tx_buf %p in "
+ "%zu out %zu\n",
+ (unsigned long) tx_msg_moved->size,
+ aligned_size, i2400m->tx_buf, i2400m->tx_in,
+ i2400m->tx_out);
+ } else
+ memset(pad_buf, 0xad, padding);
+ }
+ tx_msg_moved->padding = cpu_to_le16(padding);
+ tx_msg_moved->size += padding;
+ if (tx_msg != tx_msg_moved)
+ tx_msg->size += padding;
+out:
+ i2400m->tx_msg = NULL;
+}
+
+
+/**
+ * i2400m_tx - send the data in a buffer to the device
+ *
+ * @buf: pointer to the buffer to transmit
+ *
+ * @buf_len: buffer size
+ *
+ * @pl_type: type of the payload we are sending.
+ *
+ * Returns:
+ * 0 if ok, < 0 errno code on error (-ENOSPC, if there is no more
+ * room for the message in the queue).
+ *
+ * Appends the buffer to the TX FIFO and notifies the bus-specific
+ * part of the driver that there is new data ready to transmit.
+ * Once this function returns, the buffer has been copied, so it can
+ * be reused.
+ *
+ * The steps followed to append are explained in detail in the file
+ * header.
+ *
+ * Whenever we write to a message, we increase msg->size, so it
+ * reflects exactly how big the message is. This is needed so that if
+ * we concatenate two messages before they can be sent, the code that
+ * sends the messages can find the boundaries (and it will replace the
+ * size with the real barker before sending).
+ *
+ * Note:
+ *
+ * Cold and warm reset payloads need to be sent as a single
+ * payload, so we handle that.
+ */
+int i2400m_tx(struct i2400m *i2400m, const void *buf, size_t buf_len,
+ enum i2400m_pt pl_type)
+{
+ int result = -ENOSPC;
+ struct device *dev = i2400m_dev(i2400m);
+ unsigned long flags;
+ size_t padded_len;
+ void *ptr;
+ bool try_head = false;
+ unsigned is_singleton = pl_type == I2400M_PT_RESET_WARM
+ || pl_type == I2400M_PT_RESET_COLD;
+
+ d_fnstart(3, dev, "(i2400m %p skb %p [%zu bytes] pt %u)\n",
+ i2400m, buf, buf_len, pl_type);
+ padded_len = ALIGN(buf_len, I2400M_PL_ALIGN);
+ d_printf(5, dev, "padded_len %zd buf_len %zd\n", padded_len, buf_len);
+ /* If there is no current TX message, create one; if the
+ * current one is out of payload slots or we have a singleton,
+ * close it and start a new one */
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ /* If tx_buf is NULL, device is shutdown */
+ if (i2400m->tx_buf == NULL) {
+ result = -ESHUTDOWN;
+ goto error_tx_new;
+ }
+try_new:
+ if (unlikely(i2400m->tx_msg == NULL))
+ i2400m_tx_new(i2400m);
+ else if (unlikely(!i2400m_tx_fits(i2400m)
+ || (is_singleton && i2400m->tx_msg->num_pls != 0))) {
+ d_printf(2, dev, "closing TX message (fits %u singleton "
+ "%u num_pls %u)\n", i2400m_tx_fits(i2400m),
+ is_singleton, i2400m->tx_msg->num_pls);
+ i2400m_tx_close(i2400m);
+ i2400m_tx_new(i2400m);
+ }
+ if (i2400m->tx_msg == NULL)
+ goto error_tx_new;
+ /*
+ * Check if this skb will fit in the TX queue's current active
+ * TX message. The total message size must not exceed the maximum
+ * size of each message I2400M_TX_MSG_SIZE. If it exceeds,
+ * close the current message and push this skb into the new message.
+ */
+ if (i2400m->tx_msg->size + padded_len > I2400M_TX_MSG_SIZE) {
+ d_printf(2, dev, "TX: message too big, going new\n");
+ i2400m_tx_close(i2400m);
+ i2400m_tx_new(i2400m);
+ }
+ if (i2400m->tx_msg == NULL)
+ goto error_tx_new;
+ /* So we have a current message header; now append space for
+ * the message -- if there is not enough, try the head */
+ ptr = i2400m_tx_fifo_push(i2400m, padded_len,
+ i2400m->bus_tx_block_size, try_head);
+ if (ptr == TAIL_FULL) { /* Tail is full, try head */
+ d_printf(2, dev, "pl append: tail full\n");
+ i2400m_tx_close(i2400m);
+ i2400m_tx_skip_tail(i2400m);
+ try_head = true;
+ goto try_new;
+ } else if (ptr == NULL) { /* All full */
+ result = -ENOSPC;
+ d_printf(2, dev, "pl append: all full\n");
+ } else { /* Got space, copy it, set padding */
+ struct i2400m_msg_hdr *tx_msg = i2400m->tx_msg;
+ unsigned num_pls = le16_to_cpu(tx_msg->num_pls);
+ memcpy(ptr, buf, buf_len);
+ memset(ptr + buf_len, 0xad, padded_len - buf_len);
+ i2400m_pld_set(&tx_msg->pld[num_pls], buf_len, pl_type);
+ d_printf(3, dev, "pld 0x%08x (type 0x%1x len 0x%04zx\n",
+ le32_to_cpu(tx_msg->pld[num_pls].val),
+ pl_type, buf_len);
+ tx_msg->num_pls = le16_to_cpu(num_pls+1);
+ tx_msg->size += padded_len;
+ d_printf(2, dev, "TX: appended %zu b (up to %u b) pl #%u\n",
+ padded_len, tx_msg->size, num_pls+1);
+ d_printf(2, dev,
+ "TX: appended hdr @%zu %zu b pl #%u @%zu %zu/%zu b\n",
+ (void *)tx_msg - i2400m->tx_buf, (size_t)tx_msg->size,
+ num_pls+1, ptr - i2400m->tx_buf, buf_len, padded_len);
+ result = 0;
+ if (is_singleton)
+ i2400m_tx_close(i2400m);
+ }
+error_tx_new:
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+ /* kick in most cases, except when the TX subsys is down, as
+ * it might free space */
+ if (likely(result != -ESHUTDOWN))
+ i2400m->bus_tx_kick(i2400m);
+ d_fnend(3, dev, "(i2400m %p skb %p [%zu bytes] pt %u) = %d\n",
+ i2400m, buf, buf_len, pl_type, result);
+ return result;
+}
+EXPORT_SYMBOL_GPL(i2400m_tx);
+
+
+/**
+ * i2400m_tx_msg_get - Get the first TX message in the FIFO to start sending it
+ *
+ * @i2400m: device descriptors
+ * @bus_size: where to place the size of the TX message
+ *
+ * Called by the bus-specific driver to get the first TX message at
+ * the FIF that is ready for transmission.
+ *
+ * It sets the state in @i2400m to indicate the bus-specific driver is
+ * transferring that message (i2400m->tx_msg_size).
+ *
+ * Once the transfer is completed, call i2400m_tx_msg_sent().
+ *
+ * Notes:
+ *
+ * The size of the TX message to be transmitted might be smaller than
+ * that of the TX message in the FIFO (in case the header was
+ * shorter). Hence, we copy it in @bus_size, for the bus layer to
+ * use. We keep the message's size in i2400m->tx_msg_size so that
+ * when the bus later is done transferring we know how much to
+ * advance the fifo.
+ *
+ * We collect statistics here as all the data is available and we
+ * assume it is going to work [see i2400m_tx_msg_sent()].
+ */
+struct i2400m_msg_hdr *i2400m_tx_msg_get(struct i2400m *i2400m,
+ size_t *bus_size)
+{
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400m_msg_hdr *tx_msg, *tx_msg_moved;
+ unsigned long flags, pls;
+
+ d_fnstart(3, dev, "(i2400m %p bus_size %p)\n", i2400m, bus_size);
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ tx_msg_moved = NULL;
+ if (i2400m->tx_buf == NULL)
+ goto out_unlock;
+skip:
+ tx_msg_moved = NULL;
+ if (i2400m->tx_in == i2400m->tx_out) { /* Empty FIFO? */
+ i2400m->tx_in = 0;
+ i2400m->tx_out = 0;
+ d_printf(2, dev, "TX: FIFO empty: resetting\n");
+ goto out_unlock;
+ }
+ tx_msg = i2400m->tx_buf + i2400m->tx_out % I2400M_TX_BUF_SIZE;
+ if (tx_msg->size & I2400M_TX_SKIP) { /* skip? */
+ d_printf(2, dev, "TX: skip: msg @%zu (%zu b)\n",
+ i2400m->tx_out % I2400M_TX_BUF_SIZE,
+ (size_t) tx_msg->size & ~I2400M_TX_SKIP);
+ i2400m->tx_out += tx_msg->size & ~I2400M_TX_SKIP;
+ goto skip;
+ }
+
+ if (tx_msg->num_pls == 0) { /* No payloads? */
+ if (tx_msg == i2400m->tx_msg) { /* open, we are done */
+ d_printf(2, dev,
+ "TX: FIFO empty: open msg w/o payloads @%zu\n",
+ (void *) tx_msg - i2400m->tx_buf);
+ tx_msg = NULL;
+ goto out_unlock;
+ } else { /* closed, skip it */
+ d_printf(2, dev,
+ "TX: skip msg w/o payloads @%zu (%zu b)\n",
+ (void *) tx_msg - i2400m->tx_buf,
+ (size_t) tx_msg->size);
+ i2400m->tx_out += tx_msg->size & ~I2400M_TX_SKIP;
+ goto skip;
+ }
+ }
+ if (tx_msg == i2400m->tx_msg) /* open msg? */
+ i2400m_tx_close(i2400m);
+
+ /* Now we have a valid TX message (with payloads) to TX */
+ tx_msg_moved = (void *) tx_msg + tx_msg->offset;
+ i2400m->tx_msg_size = tx_msg->size;
+ *bus_size = tx_msg_moved->size;
+ d_printf(2, dev, "TX: pid %d msg hdr at @%zu offset +@%zu "
+ "size %zu bus_size %zu\n",
+ current->pid, (void *) tx_msg - i2400m->tx_buf,
+ (size_t) tx_msg->offset, (size_t) tx_msg->size,
+ (size_t) tx_msg_moved->size);
+ tx_msg_moved->barker = le32_to_cpu(I2400M_H2D_PREVIEW_BARKER);
+ tx_msg_moved->sequence = le32_to_cpu(i2400m->tx_sequence++);
+
+ pls = le32_to_cpu(tx_msg_moved->num_pls);
+ i2400m->tx_pl_num += pls; /* Update stats */
+ if (pls > i2400m->tx_pl_max)
+ i2400m->tx_pl_max = pls;
+ if (pls < i2400m->tx_pl_min)
+ i2400m->tx_pl_min = pls;
+ i2400m->tx_num++;
+ i2400m->tx_size_acc += *bus_size;
+ if (*bus_size < i2400m->tx_size_min)
+ i2400m->tx_size_min = *bus_size;
+ if (*bus_size > i2400m->tx_size_max)
+ i2400m->tx_size_max = *bus_size;
+out_unlock:
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+ d_fnstart(3, dev, "(i2400m %p bus_size %p [%zu]) = %p\n",
+ i2400m, bus_size, *bus_size, tx_msg_moved);
+ return tx_msg_moved;
+}
+EXPORT_SYMBOL_GPL(i2400m_tx_msg_get);
+
+
+/**
+ * i2400m_tx_msg_sent - indicate the transmission of a TX message
+ *
+ * @i2400m: device descriptor
+ *
+ * Called by the bus-specific driver when a message has been sent;
+ * this pops it from the FIFO; and as there is space, start the queue
+ * in case it was stopped.
+ *
+ * Should be called even if the message send failed and we are
+ * dropping this TX message.
+ */
+void i2400m_tx_msg_sent(struct i2400m *i2400m)
+{
+ unsigned n;
+ unsigned long flags;
+ struct device *dev = i2400m_dev(i2400m);
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ if (i2400m->tx_buf == NULL)
+ goto out_unlock;
+ i2400m->tx_out += i2400m->tx_msg_size;
+ d_printf(2, dev, "TX: sent %zu b\n", (size_t) i2400m->tx_msg_size);
+ i2400m->tx_msg_size = 0;
+ BUG_ON(i2400m->tx_out > i2400m->tx_in);
+ /* level them FIFO markers off */
+ n = i2400m->tx_out / I2400M_TX_BUF_SIZE;
+ i2400m->tx_out %= I2400M_TX_BUF_SIZE;
+ i2400m->tx_in -= n * I2400M_TX_BUF_SIZE;
+out_unlock:
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+ d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
+EXPORT_SYMBOL_GPL(i2400m_tx_msg_sent);
+
+
+/**
+ * i2400m_tx_setup - Initialize the TX queue and infrastructure
+ *
+ * Make sure we reset the TX sequence to zero, as when this function
+ * is called, the firmware has been just restarted. Same rational
+ * for tx_in, tx_out, tx_msg_size and tx_msg. We reset them since
+ * the memory for TX queue is reallocated.
+ */
+int i2400m_tx_setup(struct i2400m *i2400m)
+{
+ int result = 0;
+ void *tx_buf;
+ unsigned long flags;
+
+ /* Do this here only once -- can't do on
+ * i2400m_hard_start_xmit() as we'll cause race conditions if
+ * the WS was scheduled on another CPU */
+ INIT_WORK(&i2400m->wake_tx_ws, i2400m_wake_tx_work);
+
+ tx_buf = kmalloc(I2400M_TX_BUF_SIZE, GFP_ATOMIC);
+ if (tx_buf == NULL) {
+ result = -ENOMEM;
+ goto error_kmalloc;
+ }
+
+ /*
+ * Fail the build if we can't fit at least two maximum size messages
+ * on the TX FIFO [one being delivered while one is constructed].
+ */
+ BUILD_BUG_ON(2 * I2400M_TX_MSG_SIZE > I2400M_TX_BUF_SIZE);
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ i2400m->tx_sequence = 0;
+ i2400m->tx_in = 0;
+ i2400m->tx_out = 0;
+ i2400m->tx_msg_size = 0;
+ i2400m->tx_msg = NULL;
+ i2400m->tx_buf = tx_buf;
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+ /* Huh? the bus layer has to define this... */
+ BUG_ON(i2400m->bus_tx_block_size == 0);
+error_kmalloc:
+ return result;
+
+}
+
+
+/**
+ * i2400m_tx_release - Tear down the TX queue and infrastructure
+ */
+void i2400m_tx_release(struct i2400m *i2400m)
+{
+ unsigned long flags;
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ kfree(i2400m->tx_buf);
+ i2400m->tx_buf = NULL;
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Debug levels control file for the i2400m-usb module
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+#ifndef __debug_levels__h__
+#define __debug_levels__h__
+
+/* Maximum compile and run time debug level for all submodules */
+#define D_MODULENAME i2400m_usb
+#define D_MASTER CONFIG_WIMAX_I2400M_DEBUG_LEVEL
+
+#include "../linux-wimax-debug.h"
+
+/* List of all the enabled modules */
+enum d_module {
+ D_SUBMODULE_DECLARE(usb),
+ D_SUBMODULE_DECLARE(fw),
+ D_SUBMODULE_DECLARE(notif),
+ D_SUBMODULE_DECLARE(rx),
+ D_SUBMODULE_DECLARE(tx),
+};
+
+
+#endif /* #ifndef __debug_levels__h__ */
--- /dev/null
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Firmware uploader's USB specifics
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * - Initial implementation
+ *
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * - bus generic/specific split
+ *
+ * THE PROCEDURE
+ *
+ * See fw.c for the generic description of this procedure.
+ *
+ * This file implements only the USB specifics. It boils down to how
+ * to send a command and waiting for an acknowledgement from the
+ * device.
+ *
+ * This code (and process) is single threaded. It assumes it is the
+ * only thread poking around (guaranteed by fw.c).
+ *
+ * COMMAND EXECUTION
+ *
+ * A write URB is posted with the buffer to the bulk output endpoint.
+ *
+ * ACK RECEPTION
+ *
+ * We just post a URB to the notification endpoint and wait for
+ * data. We repeat until we get all the data we expect (as indicated
+ * by the call from the bus generic code).
+ *
+ * The data is not read from the bulk in endpoint for boot mode.
+ *
+ * ROADMAP
+ *
+ * i2400mu_bus_bm_cmd_send
+ * i2400m_bm_cmd_prepare...
+ * i2400mu_tx_bulk_out
+ *
+ * i2400mu_bus_bm_wait_for_ack
+ * i2400m_notif_submit
+ */
+#include <linux/usb.h>
+#include <linux/gfp.h>
+#include "i2400m-usb.h"
+
+
+#define D_SUBMODULE fw
+#include "usb-debug-levels.h"
+
+
+/*
+ * Synchronous write to the device
+ *
+ * Takes care of updating EDC counts and thus, handle device errors.
+ */
+static
+ssize_t i2400mu_tx_bulk_out(struct i2400mu *i2400mu, void *buf, size_t buf_size)
+{
+ int result;
+ struct device *dev = &i2400mu->usb_iface->dev;
+ int len;
+ struct usb_endpoint_descriptor *epd;
+ int pipe, do_autopm = 1;
+
+ result = usb_autopm_get_interface(i2400mu->usb_iface);
+ if (result < 0) {
+ dev_err(dev, "BM-CMD: can't get autopm: %d\n", result);
+ do_autopm = 0;
+ }
+ epd = usb_get_epd(i2400mu->usb_iface, i2400mu->endpoint_cfg.bulk_out);
+ pipe = usb_sndbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
+retry:
+ result = usb_bulk_msg(i2400mu->usb_dev, pipe, buf, buf_size, &len, 200);
+ switch (result) {
+ case 0:
+ if (len != buf_size) {
+ dev_err(dev, "BM-CMD: short write (%u B vs %zu "
+ "expected)\n", len, buf_size);
+ result = -EIO;
+ break;
+ }
+ result = len;
+ break;
+ case -EPIPE:
+ /*
+ * Stall -- maybe the device is choking with our
+ * requests. Clear it and give it some time. If they
+ * happen to often, it might be another symptom, so we
+ * reset.
+ *
+ * No error handling for usb_clear_halt(0; if it
+ * works, the retry works; if it fails, this switch
+ * does the error handling for us.
+ */
+ if (edc_inc(&i2400mu->urb_edc,
+ 10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+ dev_err(dev, "BM-CMD: too many stalls in "
+ "URB; resetting device\n");
+ usb_queue_reset_device(i2400mu->usb_iface);
+ } else {
+ usb_clear_halt(i2400mu->usb_dev, pipe);
+ msleep(10); /* give the device some time */
+ goto retry;
+ }
+ fallthrough;
+ case -EINVAL: /* while removing driver */
+ case -ENODEV: /* dev disconnect ... */
+ case -ENOENT: /* just ignore it */
+ case -ESHUTDOWN: /* and exit */
+ case -ECONNRESET:
+ result = -ESHUTDOWN;
+ break;
+ case -ETIMEDOUT: /* bah... */
+ break;
+ default: /* any other? */
+ if (edc_inc(&i2400mu->urb_edc,
+ EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+ dev_err(dev, "BM-CMD: maximum errors in "
+ "URB exceeded; resetting device\n");
+ usb_queue_reset_device(i2400mu->usb_iface);
+ result = -ENODEV;
+ break;
+ }
+ dev_err(dev, "BM-CMD: URB error %d, retrying\n",
+ result);
+ goto retry;
+ }
+ if (do_autopm)
+ usb_autopm_put_interface(i2400mu->usb_iface);
+ return result;
+}
+
+
+/*
+ * Send a boot-mode command over the bulk-out pipe
+ *
+ * Command can be a raw command, which requires no preparation (and
+ * which might not even be following the command format). Checks that
+ * the right amount of data was transferred.
+ *
+ * To satisfy USB requirements (no onstack, vmalloc or in data segment
+ * buffers), we copy the command to i2400m->bm_cmd_buf and send it from
+ * there.
+ *
+ * @flags: pass thru from i2400m_bm_cmd()
+ * @return: cmd_size if ok, < 0 errno code on error.
+ */
+ssize_t i2400mu_bus_bm_cmd_send(struct i2400m *i2400m,
+ const struct i2400m_bootrom_header *_cmd,
+ size_t cmd_size, int flags)
+{
+ ssize_t result;
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+ int opcode = _cmd == NULL ? -1 : i2400m_brh_get_opcode(_cmd);
+ struct i2400m_bootrom_header *cmd;
+ size_t cmd_size_a = ALIGN(cmd_size, 16); /* USB restriction */
+
+ d_fnstart(8, dev, "(i2400m %p cmd %p size %zu)\n",
+ i2400m, _cmd, cmd_size);
+ result = -E2BIG;
+ if (cmd_size > I2400M_BM_CMD_BUF_SIZE)
+ goto error_too_big;
+ if (_cmd != i2400m->bm_cmd_buf)
+ memmove(i2400m->bm_cmd_buf, _cmd, cmd_size);
+ cmd = i2400m->bm_cmd_buf;
+ if (cmd_size_a > cmd_size) /* Zero pad space */
+ memset(i2400m->bm_cmd_buf + cmd_size, 0, cmd_size_a - cmd_size);
+ if ((flags & I2400M_BM_CMD_RAW) == 0) {
+ if (WARN_ON(i2400m_brh_get_response_required(cmd) == 0))
+ dev_warn(dev, "SW BUG: response_required == 0\n");
+ i2400m_bm_cmd_prepare(cmd);
+ }
+ result = i2400mu_tx_bulk_out(i2400mu, i2400m->bm_cmd_buf, cmd_size);
+ if (result < 0) {
+ dev_err(dev, "boot-mode cmd %d: cannot send: %zd\n",
+ opcode, result);
+ goto error_cmd_send;
+ }
+ if (result != cmd_size) { /* all was transferred? */
+ dev_err(dev, "boot-mode cmd %d: incomplete transfer "
+ "(%zd vs %zu submitted)\n", opcode, result, cmd_size);
+ result = -EIO;
+ goto error_cmd_size;
+ }
+error_cmd_size:
+error_cmd_send:
+error_too_big:
+ d_fnend(8, dev, "(i2400m %p cmd %p size %zu) = %zd\n",
+ i2400m, _cmd, cmd_size, result);
+ return result;
+}
+
+
+static
+void __i2400mu_bm_notif_cb(struct urb *urb)
+{
+ complete(urb->context);
+}
+
+
+/*
+ * submit a read to the notification endpoint
+ *
+ * @i2400m: device descriptor
+ * @urb: urb to use
+ * @completion: completion variable to complete when done
+ *
+ * Data is always read to i2400m->bm_ack_buf
+ */
+static
+int i2400mu_notif_submit(struct i2400mu *i2400mu, struct urb *urb,
+ struct completion *completion)
+{
+ struct i2400m *i2400m = &i2400mu->i2400m;
+ struct usb_endpoint_descriptor *epd;
+ int pipe;
+
+ epd = usb_get_epd(i2400mu->usb_iface,
+ i2400mu->endpoint_cfg.notification);
+ pipe = usb_rcvintpipe(i2400mu->usb_dev, epd->bEndpointAddress);
+ usb_fill_int_urb(urb, i2400mu->usb_dev, pipe,
+ i2400m->bm_ack_buf, I2400M_BM_ACK_BUF_SIZE,
+ __i2400mu_bm_notif_cb, completion,
+ epd->bInterval);
+ return usb_submit_urb(urb, GFP_KERNEL);
+}
+
+
+/*
+ * Read an ack from the notification endpoint
+ *
+ * @i2400m:
+ * @_ack: pointer to where to store the read data
+ * @ack_size: how many bytes we should read
+ *
+ * Returns: < 0 errno code on error; otherwise, amount of received bytes.
+ *
+ * Submits a notification read, appends the read data to the given ack
+ * buffer and then repeats (until @ack_size bytes have been
+ * received).
+ */
+ssize_t i2400mu_bus_bm_wait_for_ack(struct i2400m *i2400m,
+ struct i2400m_bootrom_header *_ack,
+ size_t ack_size)
+{
+ ssize_t result = -ENOMEM;
+ struct device *dev = i2400m_dev(i2400m);
+ struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+ struct urb notif_urb;
+ void *ack = _ack;
+ size_t offset, len;
+ long val;
+ int do_autopm = 1;
+ DECLARE_COMPLETION_ONSTACK(notif_completion);
+
+ d_fnstart(8, dev, "(i2400m %p ack %p size %zu)\n",
+ i2400m, ack, ack_size);
+ BUG_ON(_ack == i2400m->bm_ack_buf);
+ result = usb_autopm_get_interface(i2400mu->usb_iface);
+ if (result < 0) {
+ dev_err(dev, "BM-ACK: can't get autopm: %d\n", (int) result);
+ do_autopm = 0;
+ }
+ usb_init_urb(¬if_urb); /* ready notifications */
+ usb_get_urb(¬if_urb);
+ offset = 0;
+ while (offset < ack_size) {
+ init_completion(¬if_completion);
+ result = i2400mu_notif_submit(i2400mu, ¬if_urb,
+ ¬if_completion);
+ if (result < 0)
+ goto error_notif_urb_submit;
+ val = wait_for_completion_interruptible_timeout(
+ ¬if_completion, HZ);
+ if (val == 0) {
+ result = -ETIMEDOUT;
+ usb_kill_urb(¬if_urb); /* Timedout */
+ goto error_notif_wait;
+ }
+ if (val == -ERESTARTSYS) {
+ result = -EINTR; /* Interrupted */
+ usb_kill_urb(¬if_urb);
+ goto error_notif_wait;
+ }
+ result = notif_urb.status; /* How was the ack? */
+ switch (result) {
+ case 0:
+ break;
+ case -EINVAL: /* while removing driver */
+ case -ENODEV: /* dev disconnect ... */
+ case -ENOENT: /* just ignore it */
+ case -ESHUTDOWN: /* and exit */
+ case -ECONNRESET:
+ result = -ESHUTDOWN;
+ goto error_dev_gone;
+ default: /* any other? */
+ usb_kill_urb(¬if_urb); /* Timedout */
+ if (edc_inc(&i2400mu->urb_edc,
+ EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME))
+ goto error_exceeded;
+ dev_err(dev, "BM-ACK: URB error %d, "
+ "retrying\n", notif_urb.status);
+ continue; /* retry */
+ }
+ if (notif_urb.actual_length == 0) {
+ d_printf(6, dev, "ZLP received, retrying\n");
+ continue;
+ }
+ /* Got data, append it to the buffer */
+ len = min(ack_size - offset, (size_t) notif_urb.actual_length);
+ memcpy(ack + offset, i2400m->bm_ack_buf, len);
+ offset += len;
+ }
+ result = offset;
+error_notif_urb_submit:
+error_notif_wait:
+error_dev_gone:
+out:
+ if (do_autopm)
+ usb_autopm_put_interface(i2400mu->usb_iface);
+ d_fnend(8, dev, "(i2400m %p ack %p size %zu) = %ld\n",
+ i2400m, ack, ack_size, (long) result);
+ usb_put_urb(¬if_urb);
+ return result;
+
+error_exceeded:
+ dev_err(dev, "bm: maximum errors in notification URB exceeded; "
+ "resetting device\n");
+ usb_queue_reset_device(i2400mu->usb_iface);
+ goto out;
+}
--- /dev/null
+/*
+ * Intel Wireless WiMAX Connection 2400m over USB
+ * Notification handling
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * - Initial implementation
+ *
+ *
+ * The notification endpoint is active when the device is not in boot
+ * mode; in here we just read and get notifications; based on those,
+ * we act to either reinitialize the device after a reboot or to
+ * submit a RX request.
+ *
+ * ROADMAP
+ *
+ * i2400mu_usb_notification_setup()
+ *
+ * i2400mu_usb_notification_release()
+ *
+ * i2400mu_usb_notification_cb() Called when a URB is ready
+ * i2400mu_notif_grok()
+ * i2400m_is_boot_barker()
+ * i2400m_dev_reset_handle()
+ * i2400mu_rx_kick()
+ */
+#include <linux/usb.h>
+#include <linux/slab.h>
+#include "i2400m-usb.h"
+
+
+#define D_SUBMODULE notif
+#include "usb-debug-levels.h"
+
+
+static const
+__le32 i2400m_ZERO_BARKER[4] = { 0, 0, 0, 0 };
+
+
+/*
+ * Process a received notification
+ *
+ * In normal operation mode, we can only receive two types of payloads
+ * on the notification endpoint:
+ *
+ * - a reboot barker, we do a bootstrap (the device has reseted).
+ *
+ * - a block of zeroes: there is pending data in the IN endpoint
+ */
+static
+int i2400mu_notification_grok(struct i2400mu *i2400mu, const void *buf,
+ size_t buf_len)
+{
+ int ret;
+ struct device *dev = &i2400mu->usb_iface->dev;
+ struct i2400m *i2400m = &i2400mu->i2400m;
+
+ d_fnstart(4, dev, "(i2400m %p buf %p buf_len %zu)\n",
+ i2400mu, buf, buf_len);
+ ret = -EIO;
+ if (buf_len < sizeof(i2400m_ZERO_BARKER))
+ /* Not a bug, just ignore */
+ goto error_bad_size;
+ ret = 0;
+ if (!memcmp(i2400m_ZERO_BARKER, buf, sizeof(i2400m_ZERO_BARKER))) {
+ i2400mu_rx_kick(i2400mu);
+ goto out;
+ }
+ ret = i2400m_is_boot_barker(i2400m, buf, buf_len);
+ if (unlikely(ret >= 0))
+ ret = i2400m_dev_reset_handle(i2400m, "device rebooted");
+ else /* Unknown or unexpected data in the notif message */
+ i2400m_unknown_barker(i2400m, buf, buf_len);
+error_bad_size:
+out:
+ d_fnend(4, dev, "(i2400m %p buf %p buf_len %zu) = %d\n",
+ i2400mu, buf, buf_len, ret);
+ return ret;
+}
+
+
+/*
+ * URB callback for the notification endpoint
+ *
+ * @urb: the urb received from the notification endpoint
+ *
+ * This function will just process the USB side of the transaction,
+ * checking everything is fine, pass the processing to
+ * i2400m_notification_grok() and resubmit the URB.
+ */
+static
+void i2400mu_notification_cb(struct urb *urb)
+{
+ int ret;
+ struct i2400mu *i2400mu = urb->context;
+ struct device *dev = &i2400mu->usb_iface->dev;
+
+ d_fnstart(4, dev, "(urb %p status %d actual_length %d)\n",
+ urb, urb->status, urb->actual_length);
+ ret = urb->status;
+ switch (ret) {
+ case 0:
+ ret = i2400mu_notification_grok(i2400mu, urb->transfer_buffer,
+ urb->actual_length);
+ if (ret == -EIO && edc_inc(&i2400mu->urb_edc, EDC_MAX_ERRORS,
+ EDC_ERROR_TIMEFRAME))
+ goto error_exceeded;
+ if (ret == -ENOMEM) /* uff...power cycle? shutdown? */
+ goto error_exceeded;
+ break;
+ case -EINVAL: /* while removing driver */
+ case -ENODEV: /* dev disconnect ... */
+ case -ENOENT: /* ditto */
+ case -ESHUTDOWN: /* URB killed */
+ case -ECONNRESET: /* disconnection */
+ goto out; /* Notify around */
+ default: /* Some error? */
+ if (edc_inc(&i2400mu->urb_edc,
+ EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME))
+ goto error_exceeded;
+ dev_err(dev, "notification: URB error %d, retrying\n",
+ urb->status);
+ }
+ usb_mark_last_busy(i2400mu->usb_dev);
+ ret = usb_submit_urb(i2400mu->notif_urb, GFP_ATOMIC);
+ switch (ret) {
+ case 0:
+ case -EINVAL: /* while removing driver */
+ case -ENODEV: /* dev disconnect ... */
+ case -ENOENT: /* ditto */
+ case -ESHUTDOWN: /* URB killed */
+ case -ECONNRESET: /* disconnection */
+ break; /* just ignore */
+ default: /* Some error? */
+ dev_err(dev, "notification: cannot submit URB: %d\n", ret);
+ goto error_submit;
+ }
+ d_fnend(4, dev, "(urb %p status %d actual_length %d) = void\n",
+ urb, urb->status, urb->actual_length);
+ return;
+
+error_exceeded:
+ dev_err(dev, "maximum errors in notification URB exceeded; "
+ "resetting device\n");
+error_submit:
+ usb_queue_reset_device(i2400mu->usb_iface);
+out:
+ d_fnend(4, dev, "(urb %p status %d actual_length %d) = void\n",
+ urb, urb->status, urb->actual_length);
+}
+
+
+/*
+ * setup the notification endpoint
+ *
+ * @i2400m: device descriptor
+ *
+ * This procedure prepares the notification urb and handler for receiving
+ * unsolicited barkers from the device.
+ */
+int i2400mu_notification_setup(struct i2400mu *i2400mu)
+{
+ struct device *dev = &i2400mu->usb_iface->dev;
+ int usb_pipe, ret = 0;
+ struct usb_endpoint_descriptor *epd;
+ char *buf;
+
+ d_fnstart(4, dev, "(i2400m %p)\n", i2400mu);
+ buf = kmalloc(I2400MU_MAX_NOTIFICATION_LEN, GFP_KERNEL | GFP_DMA);
+ if (buf == NULL) {
+ ret = -ENOMEM;
+ goto error_buf_alloc;
+ }
+
+ i2400mu->notif_urb = usb_alloc_urb(0, GFP_KERNEL);
+ if (!i2400mu->notif_urb) {
+ ret = -ENOMEM;
+ goto error_alloc_urb;
+ }
+ epd = usb_get_epd(i2400mu->usb_iface,
+ i2400mu->endpoint_cfg.notification);
+ usb_pipe = usb_rcvintpipe(i2400mu->usb_dev, epd->bEndpointAddress);
+ usb_fill_int_urb(i2400mu->notif_urb, i2400mu->usb_dev, usb_pipe,
+ buf, I2400MU_MAX_NOTIFICATION_LEN,
+ i2400mu_notification_cb, i2400mu, epd->bInterval);
+ ret = usb_submit_urb(i2400mu->notif_urb, GFP_KERNEL);
+ if (ret != 0) {
+ dev_err(dev, "notification: cannot submit URB: %d\n", ret);
+ goto error_submit;
+ }
+ d_fnend(4, dev, "(i2400m %p) = %d\n", i2400mu, ret);
+ return ret;
+
+error_submit:
+ usb_free_urb(i2400mu->notif_urb);
+error_alloc_urb:
+ kfree(buf);
+error_buf_alloc:
+ d_fnend(4, dev, "(i2400m %p) = %d\n", i2400mu, ret);
+ return ret;
+}
+
+
+/*
+ * Tear down of the notification mechanism
+ *
+ * @i2400m: device descriptor
+ *
+ * Kill the interrupt endpoint urb, free any allocated resources.
+ *
+ * We need to check if we have done it before as for example,
+ * _suspend() call this; if after a suspend() we get a _disconnect()
+ * (as the case is when hibernating), nothing bad happens.
+ */
+void i2400mu_notification_release(struct i2400mu *i2400mu)
+{
+ struct device *dev = &i2400mu->usb_iface->dev;
+
+ d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
+ if (i2400mu->notif_urb != NULL) {
+ usb_kill_urb(i2400mu->notif_urb);
+ kfree(i2400mu->notif_urb->transfer_buffer);
+ usb_free_urb(i2400mu->notif_urb);
+ i2400mu->notif_urb = NULL;
+ }
+ d_fnend(4, dev, "(i2400mu %p)\n", i2400mu);
+}
--- /dev/null
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * USB RX handling
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * - Initial implementation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * - Use skb_clone(), break up processing in chunks
+ * - Split transport/device specific
+ * - Make buffer size dynamic to exert less memory pressure
+ *
+ *
+ * This handles the RX path on USB.
+ *
+ * When a notification is received that says 'there is RX data ready',
+ * we call i2400mu_rx_kick(); that wakes up the RX kthread, which
+ * reads a buffer from USB and passes it to i2400m_rx() in the generic
+ * handling code. The RX buffer has an specific format that is
+ * described in rx.c.
+ *
+ * We use a kernel thread in a loop because:
+ *
+ * - we want to be able to call the USB power management get/put
+ * functions (blocking) before each transaction.
+ *
+ * - We might get a lot of notifications and we don't want to submit
+ * a zillion reads; by serializing, we are throttling.
+ *
+ * - RX data processing can get heavy enough so that it is not
+ * appropriate for doing it in the USB callback; thus we run it in a
+ * process context.
+ *
+ * We provide a read buffer of an arbitrary size (short of a page); if
+ * the callback reports -EOVERFLOW, it means it was too small, so we
+ * just double the size and retry (being careful to append, as
+ * sometimes the device provided some data). Every now and then we
+ * check if the average packet size is smaller than the current packet
+ * size and if so, we halve it. At the end, the size of the
+ * preallocated buffer should be following the average received
+ * transaction size, adapting dynamically to it.
+ *
+ * ROADMAP
+ *
+ * i2400mu_rx_kick() Called from notif.c when we get a
+ * 'data ready' notification
+ * i2400mu_rxd() Kernel RX daemon
+ * i2400mu_rx() Receive USB data
+ * i2400m_rx() Send data to generic i2400m RX handling
+ *
+ * i2400mu_rx_setup() called from i2400mu_bus_dev_start()
+ *
+ * i2400mu_rx_release() called from i2400mu_bus_dev_stop()
+ */
+#include <linux/workqueue.h>
+#include <linux/slab.h>
+#include <linux/usb.h>
+#include "i2400m-usb.h"
+
+
+#define D_SUBMODULE rx
+#include "usb-debug-levels.h"
+
+/*
+ * Dynamic RX size
+ *
+ * We can't let the rx_size be a multiple of 512 bytes (the RX
+ * endpoint's max packet size). On some USB host controllers (we
+ * haven't been able to fully characterize which), if the device is
+ * about to send (for example) X bytes and we only post a buffer to
+ * receive n*512, it will fail to mark that as babble (so that
+ * i2400mu_rx() [case -EOVERFLOW] can resize the buffer and get the
+ * rest).
+ *
+ * So on growing or shrinking, if it is a multiple of the
+ * maxpacketsize, we remove some (instead of incresing some, so in a
+ * buddy allocator we try to waste less space).
+ *
+ * Note we also need a hook for this on i2400mu_rx() -- when we do the
+ * first read, we are sure we won't hit this spot because
+ * i240mm->rx_size has been set properly. However, if we have to
+ * double because of -EOVERFLOW, when we launch the read to get the
+ * rest of the data, we *have* to make sure that also is not a
+ * multiple of the max_pkt_size.
+ */
+
+static
+size_t i2400mu_rx_size_grow(struct i2400mu *i2400mu)
+{
+ struct device *dev = &i2400mu->usb_iface->dev;
+ size_t rx_size;
+ const size_t max_pkt_size = 512;
+
+ rx_size = 2 * i2400mu->rx_size;
+ if (rx_size % max_pkt_size == 0) {
+ rx_size -= 8;
+ d_printf(1, dev,
+ "RX: expected size grew to %zu [adjusted -8] "
+ "from %zu\n",
+ rx_size, i2400mu->rx_size);
+ } else
+ d_printf(1, dev,
+ "RX: expected size grew to %zu from %zu\n",
+ rx_size, i2400mu->rx_size);
+ return rx_size;
+}
+
+
+static
+void i2400mu_rx_size_maybe_shrink(struct i2400mu *i2400mu)
+{
+ const size_t max_pkt_size = 512;
+ struct device *dev = &i2400mu->usb_iface->dev;
+
+ if (unlikely(i2400mu->rx_size_cnt >= 100
+ && i2400mu->rx_size_auto_shrink)) {
+ size_t avg_rx_size =
+ i2400mu->rx_size_acc / i2400mu->rx_size_cnt;
+ size_t new_rx_size = i2400mu->rx_size / 2;
+ if (avg_rx_size < new_rx_size) {
+ if (new_rx_size % max_pkt_size == 0) {
+ new_rx_size -= 8;
+ d_printf(1, dev,
+ "RX: expected size shrank to %zu "
+ "[adjusted -8] from %zu\n",
+ new_rx_size, i2400mu->rx_size);
+ } else
+ d_printf(1, dev,
+ "RX: expected size shrank to %zu "
+ "from %zu\n",
+ new_rx_size, i2400mu->rx_size);
+ i2400mu->rx_size = new_rx_size;
+ i2400mu->rx_size_cnt = 0;
+ i2400mu->rx_size_acc = i2400mu->rx_size;
+ }
+ }
+}
+
+/*
+ * Receive a message with payloads from the USB bus into an skb
+ *
+ * @i2400mu: USB device descriptor
+ * @rx_skb: skb where to place the received message
+ *
+ * Deals with all the USB-specifics of receiving, dynamically
+ * increasing the buffer size if so needed. Returns the payload in the
+ * skb, ready to process. On a zero-length packet, we retry.
+ *
+ * On soft USB errors, we retry (until they become too frequent and
+ * then are promoted to hard); on hard USB errors, we reset the
+ * device. On other errors (skb realloacation, we just drop it and
+ * hope for the next invocation to solve it).
+ *
+ * Returns: pointer to the skb if ok, ERR_PTR on error.
+ * NOTE: this function might realloc the skb (if it is too small),
+ * so always update with the one returned.
+ * ERR_PTR() is < 0 on error.
+ * Will return NULL if it cannot reallocate -- this can be
+ * considered a transient retryable error.
+ */
+static
+struct sk_buff *i2400mu_rx(struct i2400mu *i2400mu, struct sk_buff *rx_skb)
+{
+ int result = 0;
+ struct device *dev = &i2400mu->usb_iface->dev;
+ int usb_pipe, read_size, rx_size, do_autopm;
+ struct usb_endpoint_descriptor *epd;
+ const size_t max_pkt_size = 512;
+
+ d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
+ do_autopm = atomic_read(&i2400mu->do_autopm);
+ result = do_autopm ?
+ usb_autopm_get_interface(i2400mu->usb_iface) : 0;
+ if (result < 0) {
+ dev_err(dev, "RX: can't get autopm: %d\n", result);
+ do_autopm = 0;
+ }
+ epd = usb_get_epd(i2400mu->usb_iface, i2400mu->endpoint_cfg.bulk_in);
+ usb_pipe = usb_rcvbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
+retry:
+ rx_size = skb_end_pointer(rx_skb) - rx_skb->data - rx_skb->len;
+ if (unlikely(rx_size % max_pkt_size == 0)) {
+ rx_size -= 8;
+ d_printf(1, dev, "RX: rx_size adapted to %d [-8]\n", rx_size);
+ }
+ result = usb_bulk_msg(
+ i2400mu->usb_dev, usb_pipe, rx_skb->data + rx_skb->len,
+ rx_size, &read_size, 200);
+ usb_mark_last_busy(i2400mu->usb_dev);
+ switch (result) {
+ case 0:
+ if (read_size == 0)
+ goto retry; /* ZLP, just resubmit */
+ skb_put(rx_skb, read_size);
+ break;
+ case -EPIPE:
+ /*
+ * Stall -- maybe the device is choking with our
+ * requests. Clear it and give it some time. If they
+ * happen to often, it might be another symptom, so we
+ * reset.
+ *
+ * No error handling for usb_clear_halt(0; if it
+ * works, the retry works; if it fails, this switch
+ * does the error handling for us.
+ */
+ if (edc_inc(&i2400mu->urb_edc,
+ 10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+ dev_err(dev, "BM-CMD: too many stalls in "
+ "URB; resetting device\n");
+ goto do_reset;
+ }
+ usb_clear_halt(i2400mu->usb_dev, usb_pipe);
+ msleep(10); /* give the device some time */
+ goto retry;
+ case -EINVAL: /* while removing driver */
+ case -ENODEV: /* dev disconnect ... */
+ case -ENOENT: /* just ignore it */
+ case -ESHUTDOWN:
+ case -ECONNRESET:
+ break;
+ case -EOVERFLOW: { /* too small, reallocate */
+ struct sk_buff *new_skb;
+ rx_size = i2400mu_rx_size_grow(i2400mu);
+ if (rx_size <= (1 << 16)) /* cap it */
+ i2400mu->rx_size = rx_size;
+ else if (printk_ratelimit()) {
+ dev_err(dev, "BUG? rx_size up to %d\n", rx_size);
+ result = -EINVAL;
+ goto out;
+ }
+ skb_put(rx_skb, read_size);
+ new_skb = skb_copy_expand(rx_skb, 0, rx_size - rx_skb->len,
+ GFP_KERNEL);
+ if (new_skb == NULL) {
+ kfree_skb(rx_skb);
+ rx_skb = NULL;
+ goto out; /* drop it...*/
+ }
+ kfree_skb(rx_skb);
+ rx_skb = new_skb;
+ i2400mu->rx_size_cnt = 0;
+ i2400mu->rx_size_acc = i2400mu->rx_size;
+ d_printf(1, dev, "RX: size changed to %d, received %d, "
+ "copied %d, capacity %ld\n",
+ rx_size, read_size, rx_skb->len,
+ (long) skb_end_offset(new_skb));
+ goto retry;
+ }
+ /* In most cases, it happens due to the hardware scheduling a
+ * read when there was no data - unfortunately, we have no way
+ * to tell this timeout from a USB timeout. So we just ignore
+ * it. */
+ case -ETIMEDOUT:
+ dev_err(dev, "RX: timeout: %d\n", result);
+ result = 0;
+ break;
+ default: /* Any error */
+ if (edc_inc(&i2400mu->urb_edc,
+ EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME))
+ goto error_reset;
+ dev_err(dev, "RX: error receiving URB: %d, retrying\n", result);
+ goto retry;
+ }
+out:
+ if (do_autopm)
+ usb_autopm_put_interface(i2400mu->usb_iface);
+ d_fnend(4, dev, "(i2400mu %p) = %p\n", i2400mu, rx_skb);
+ return rx_skb;
+
+error_reset:
+ dev_err(dev, "RX: maximum errors in URB exceeded; "
+ "resetting device\n");
+do_reset:
+ usb_queue_reset_device(i2400mu->usb_iface);
+ rx_skb = ERR_PTR(result);
+ goto out;
+}
+
+
+/*
+ * Kernel thread for USB reception of data
+ *
+ * This thread waits for a kick; once kicked, it will allocate an skb
+ * and receive a single message to it from USB (using
+ * i2400mu_rx()). Once received, it is passed to the generic i2400m RX
+ * code for processing.
+ *
+ * When done processing, it runs some dirty statistics to verify if
+ * the last 100 messages received were smaller than half of the
+ * current RX buffer size. In that case, the RX buffer size is
+ * halved. This will helps lowering the pressure on the memory
+ * allocator.
+ *
+ * Hard errors force the thread to exit.
+ */
+static
+int i2400mu_rxd(void *_i2400mu)
+{
+ int result = 0;
+ struct i2400mu *i2400mu = _i2400mu;
+ struct i2400m *i2400m = &i2400mu->i2400m;
+ struct device *dev = &i2400mu->usb_iface->dev;
+ struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+ size_t pending;
+ int rx_size;
+ struct sk_buff *rx_skb;
+ unsigned long flags;
+
+ d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ BUG_ON(i2400mu->rx_kthread != NULL);
+ i2400mu->rx_kthread = current;
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ while (1) {
+ d_printf(2, dev, "RX: waiting for messages\n");
+ pending = 0;
+ wait_event_interruptible(
+ i2400mu->rx_wq,
+ (kthread_should_stop() /* check this first! */
+ || (pending = atomic_read(&i2400mu->rx_pending_count)))
+ );
+ if (kthread_should_stop())
+ break;
+ if (pending == 0)
+ continue;
+ rx_size = i2400mu->rx_size;
+ d_printf(2, dev, "RX: reading up to %d bytes\n", rx_size);
+ rx_skb = __netdev_alloc_skb(net_dev, rx_size, GFP_KERNEL);
+ if (rx_skb == NULL) {
+ dev_err(dev, "RX: can't allocate skb [%d bytes]\n",
+ rx_size);
+ msleep(50); /* give it some time? */
+ continue;
+ }
+
+ /* Receive the message with the payloads */
+ rx_skb = i2400mu_rx(i2400mu, rx_skb);
+ result = PTR_ERR(rx_skb);
+ if (IS_ERR(rx_skb))
+ goto out;
+ atomic_dec(&i2400mu->rx_pending_count);
+ if (rx_skb == NULL || rx_skb->len == 0) {
+ /* some "ignorable" condition */
+ kfree_skb(rx_skb);
+ continue;
+ }
+
+ /* Deliver the message to the generic i2400m code */
+ i2400mu->rx_size_cnt++;
+ i2400mu->rx_size_acc += rx_skb->len;
+ result = i2400m_rx(i2400m, rx_skb);
+ if (result == -EIO
+ && edc_inc(&i2400mu->urb_edc,
+ EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+ goto error_reset;
+ }
+
+ /* Maybe adjust RX buffer size */
+ i2400mu_rx_size_maybe_shrink(i2400mu);
+ }
+ result = 0;
+out:
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ i2400mu->rx_kthread = NULL;
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ d_fnend(4, dev, "(i2400mu %p) = %d\n", i2400mu, result);
+ return result;
+
+error_reset:
+ dev_err(dev, "RX: maximum errors in received buffer exceeded; "
+ "resetting device\n");
+ usb_queue_reset_device(i2400mu->usb_iface);
+ goto out;
+}
+
+
+/*
+ * Start reading from the device
+ *
+ * @i2400m: device instance
+ *
+ * Notify the RX thread that there is data pending.
+ */
+void i2400mu_rx_kick(struct i2400mu *i2400mu)
+{
+ struct i2400m *i2400m = &i2400mu->i2400m;
+ struct device *dev = &i2400mu->usb_iface->dev;
+
+ d_fnstart(3, dev, "(i2400mu %p)\n", i2400m);
+ atomic_inc(&i2400mu->rx_pending_count);
+ wake_up_all(&i2400mu->rx_wq);
+ d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
+
+
+int i2400mu_rx_setup(struct i2400mu *i2400mu)
+{
+ int result = 0;
+ struct i2400m *i2400m = &i2400mu->i2400m;
+ struct device *dev = &i2400mu->usb_iface->dev;
+ struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+ struct task_struct *kthread;
+
+ kthread = kthread_run(i2400mu_rxd, i2400mu, "%s-rx",
+ wimax_dev->name);
+ /* the kthread function sets i2400mu->rx_thread */
+ if (IS_ERR(kthread)) {
+ result = PTR_ERR(kthread);
+ dev_err(dev, "RX: cannot start thread: %d\n", result);
+ }
+ return result;
+}
+
+
+void i2400mu_rx_release(struct i2400mu *i2400mu)
+{
+ unsigned long flags;
+ struct i2400m *i2400m = &i2400mu->i2400m;
+ struct device *dev = i2400m_dev(i2400m);
+ struct task_struct *kthread;
+
+ spin_lock_irqsave(&i2400m->rx_lock, flags);
+ kthread = i2400mu->rx_kthread;
+ i2400mu->rx_kthread = NULL;
+ spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+ if (kthread)
+ kthread_stop(kthread);
+ else
+ d_printf(1, dev, "RX: kthread had already exited\n");
+}
+
--- /dev/null
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * USB specific TX handling
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * - Initial implementation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * - Split transport/device specific
+ *
+ *
+ * Takes the TX messages in the i2400m's driver TX FIFO and sends them
+ * to the device until there are no more.
+ *
+ * If we fail sending the message, we just drop it. There isn't much
+ * we can do at this point. We could also retry, but the USB stack has
+ * already retried and still failed, so there is not much of a
+ * point. As well, most of the traffic is network, which has recovery
+ * methods for dropped packets.
+ *
+ * For sending we just obtain a FIFO buffer to send, send it to the
+ * USB bulk out, tell the TX FIFO code we have sent it; query for
+ * another one, etc... until done.
+ *
+ * We use a thread so we can call usb_autopm_enable() and
+ * usb_autopm_disable() for each transaction; this way when the device
+ * goes idle, it will suspend. It also has less overhead than a
+ * dedicated workqueue, as it is being used for a single task.
+ *
+ * ROADMAP
+ *
+ * i2400mu_tx_setup()
+ * i2400mu_tx_release()
+ *
+ * i2400mu_bus_tx_kick() - Called by the tx.c code when there
+ * is new data in the FIFO.
+ * i2400mu_txd()
+ * i2400m_tx_msg_get()
+ * i2400m_tx_msg_sent()
+ */
+#include "i2400m-usb.h"
+
+
+#define D_SUBMODULE tx
+#include "usb-debug-levels.h"
+
+
+/*
+ * Get the next TX message in the TX FIFO and send it to the device
+ *
+ * Note that any iteration consumes a message to be sent, no matter if
+ * it succeeds or fails (we have no real way to retry or complain).
+ *
+ * Return: 0 if ok, < 0 errno code on hard error.
+ */
+static
+int i2400mu_tx(struct i2400mu *i2400mu, struct i2400m_msg_hdr *tx_msg,
+ size_t tx_msg_size)
+{
+ int result = 0;
+ struct i2400m *i2400m = &i2400mu->i2400m;
+ struct device *dev = &i2400mu->usb_iface->dev;
+ int usb_pipe, sent_size, do_autopm;
+ struct usb_endpoint_descriptor *epd;
+
+ d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
+ do_autopm = atomic_read(&i2400mu->do_autopm);
+ result = do_autopm ?
+ usb_autopm_get_interface(i2400mu->usb_iface) : 0;
+ if (result < 0) {
+ dev_err(dev, "TX: can't get autopm: %d\n", result);
+ do_autopm = 0;
+ }
+ epd = usb_get_epd(i2400mu->usb_iface, i2400mu->endpoint_cfg.bulk_out);
+ usb_pipe = usb_sndbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
+retry:
+ result = usb_bulk_msg(i2400mu->usb_dev, usb_pipe,
+ tx_msg, tx_msg_size, &sent_size, 200);
+ usb_mark_last_busy(i2400mu->usb_dev);
+ switch (result) {
+ case 0:
+ if (sent_size != tx_msg_size) { /* Too short? drop it */
+ dev_err(dev, "TX: short write (%d B vs %zu "
+ "expected)\n", sent_size, tx_msg_size);
+ result = -EIO;
+ }
+ break;
+ case -EPIPE:
+ /*
+ * Stall -- maybe the device is choking with our
+ * requests. Clear it and give it some time. If they
+ * happen to often, it might be another symptom, so we
+ * reset.
+ *
+ * No error handling for usb_clear_halt(0; if it
+ * works, the retry works; if it fails, this switch
+ * does the error handling for us.
+ */
+ if (edc_inc(&i2400mu->urb_edc,
+ 10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+ dev_err(dev, "BM-CMD: too many stalls in "
+ "URB; resetting device\n");
+ usb_queue_reset_device(i2400mu->usb_iface);
+ } else {
+ usb_clear_halt(i2400mu->usb_dev, usb_pipe);
+ msleep(10); /* give the device some time */
+ goto retry;
+ }
+ fallthrough;
+ case -EINVAL: /* while removing driver */
+ case -ENODEV: /* dev disconnect ... */
+ case -ENOENT: /* just ignore it */
+ case -ESHUTDOWN: /* and exit */
+ case -ECONNRESET:
+ result = -ESHUTDOWN;
+ break;
+ default: /* Some error? */
+ if (edc_inc(&i2400mu->urb_edc,
+ EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+ dev_err(dev, "TX: maximum errors in URB "
+ "exceeded; resetting device\n");
+ usb_queue_reset_device(i2400mu->usb_iface);
+ } else {
+ dev_err(dev, "TX: cannot send URB; retrying. "
+ "tx_msg @%zu %zu B [%d sent]: %d\n",
+ (void *) tx_msg - i2400m->tx_buf,
+ tx_msg_size, sent_size, result);
+ goto retry;
+ }
+ }
+ if (do_autopm)
+ usb_autopm_put_interface(i2400mu->usb_iface);
+ d_fnend(4, dev, "(i2400mu %p) = result\n", i2400mu);
+ return result;
+}
+
+
+/*
+ * Get the next TX message in the TX FIFO and send it to the device
+ *
+ * Note we exit the loop if i2400mu_tx() fails; that function only
+ * fails on hard error (failing to tx a buffer not being one of them,
+ * see its doc).
+ *
+ * Return: 0
+ */
+static
+int i2400mu_txd(void *_i2400mu)
+{
+ struct i2400mu *i2400mu = _i2400mu;
+ struct i2400m *i2400m = &i2400mu->i2400m;
+ struct device *dev = &i2400mu->usb_iface->dev;
+ struct i2400m_msg_hdr *tx_msg;
+ size_t tx_msg_size;
+ unsigned long flags;
+
+ d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
+
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ BUG_ON(i2400mu->tx_kthread != NULL);
+ i2400mu->tx_kthread = current;
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+
+ while (1) {
+ d_printf(2, dev, "TX: waiting for messages\n");
+ tx_msg = NULL;
+ wait_event_interruptible(
+ i2400mu->tx_wq,
+ (kthread_should_stop() /* check this first! */
+ || (tx_msg = i2400m_tx_msg_get(i2400m, &tx_msg_size)))
+ );
+ if (kthread_should_stop())
+ break;
+ WARN_ON(tx_msg == NULL); /* should not happen...*/
+ d_printf(2, dev, "TX: submitting %zu bytes\n", tx_msg_size);
+ d_dump(5, dev, tx_msg, tx_msg_size);
+ /* Yeah, we ignore errors ... not much we can do */
+ i2400mu_tx(i2400mu, tx_msg, tx_msg_size);
+ i2400m_tx_msg_sent(i2400m); /* ack it, advance the FIFO */
+ }
+
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ i2400mu->tx_kthread = NULL;
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+
+ d_fnend(4, dev, "(i2400mu %p)\n", i2400mu);
+ return 0;
+}
+
+
+/*
+ * i2400m TX engine notifies us that there is data in the FIFO ready
+ * for TX
+ *
+ * If there is a URB in flight, don't do anything; when it finishes,
+ * it will see there is data in the FIFO and send it. Else, just
+ * submit a write.
+ */
+void i2400mu_bus_tx_kick(struct i2400m *i2400m)
+{
+ struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+ struct device *dev = &i2400mu->usb_iface->dev;
+
+ d_fnstart(3, dev, "(i2400m %p) = void\n", i2400m);
+ wake_up_all(&i2400mu->tx_wq);
+ d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
+
+
+int i2400mu_tx_setup(struct i2400mu *i2400mu)
+{
+ int result = 0;
+ struct i2400m *i2400m = &i2400mu->i2400m;
+ struct device *dev = &i2400mu->usb_iface->dev;
+ struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+ struct task_struct *kthread;
+
+ kthread = kthread_run(i2400mu_txd, i2400mu, "%s-tx",
+ wimax_dev->name);
+ /* the kthread function sets i2400mu->tx_thread */
+ if (IS_ERR(kthread)) {
+ result = PTR_ERR(kthread);
+ dev_err(dev, "TX: cannot start thread: %d\n", result);
+ }
+ return result;
+}
+
+void i2400mu_tx_release(struct i2400mu *i2400mu)
+{
+ unsigned long flags;
+ struct i2400m *i2400m = &i2400mu->i2400m;
+ struct device *dev = i2400m_dev(i2400m);
+ struct task_struct *kthread;
+
+ spin_lock_irqsave(&i2400m->tx_lock, flags);
+ kthread = i2400mu->tx_kthread;
+ i2400mu->tx_kthread = NULL;
+ spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+ if (kthread)
+ kthread_stop(kthread);
+ else
+ d_printf(1, dev, "TX: kthread had already exited\n");
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Linux driver model glue for USB device, reset & fw upload
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ *
+ * See i2400m-usb.h for a general description of this driver.
+ *
+ * This file implements driver model glue, and hook ups for the
+ * generic driver to implement the bus-specific functions (device
+ * communication setup/tear down, firmware upload and resetting).
+ *
+ * ROADMAP
+ *
+ * i2400mu_probe()
+ * alloc_netdev()...
+ * i2400mu_netdev_setup()
+ * i2400mu_init()
+ * i2400m_netdev_setup()
+ * i2400m_setup()...
+ *
+ * i2400mu_disconnect
+ * i2400m_release()
+ * free_netdev()
+ *
+ * i2400mu_suspend()
+ * i2400m_cmd_enter_powersave()
+ * i2400mu_notification_release()
+ *
+ * i2400mu_resume()
+ * i2400mu_notification_setup()
+ *
+ * i2400mu_bus_dev_start() Called by i2400m_dev_start() [who is
+ * i2400mu_tx_setup() called by i2400m_setup()]
+ * i2400mu_rx_setup()
+ * i2400mu_notification_setup()
+ *
+ * i2400mu_bus_dev_stop() Called by i2400m_dev_stop() [who is
+ * i2400mu_notification_release() called by i2400m_release()]
+ * i2400mu_rx_release()
+ * i2400mu_tx_release()
+ *
+ * i2400mu_bus_reset() Called by i2400m_reset
+ * __i2400mu_reset()
+ * __i2400mu_send_barker()
+ * usb_reset_device()
+ */
+#include "i2400m-usb.h"
+#include "linux-wimax-i2400m.h"
+#include <linux/debugfs.h>
+#include <linux/ethtool.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+
+
+#define D_SUBMODULE usb
+#include "usb-debug-levels.h"
+
+static char i2400mu_debug_params[128];
+module_param_string(debug, i2400mu_debug_params, sizeof(i2400mu_debug_params),
+ 0644);
+MODULE_PARM_DESC(debug,
+ "String of space-separated NAME:VALUE pairs, where NAMEs "
+ "are the different debug submodules and VALUE are the "
+ "initial debug value to set.");
+
+/* Our firmware file name */
+static const char *i2400mu_bus_fw_names_5x50[] = {
+#define I2400MU_FW_FILE_NAME_v1_5 "i2400m-fw-usb-1.5.sbcf"
+ I2400MU_FW_FILE_NAME_v1_5,
+#define I2400MU_FW_FILE_NAME_v1_4 "i2400m-fw-usb-1.4.sbcf"
+ I2400MU_FW_FILE_NAME_v1_4,
+ NULL,
+};
+
+
+static const char *i2400mu_bus_fw_names_6050[] = {
+#define I6050U_FW_FILE_NAME_v1_5 "i6050-fw-usb-1.5.sbcf"
+ I6050U_FW_FILE_NAME_v1_5,
+ NULL,
+};
+
+
+static
+int i2400mu_bus_dev_start(struct i2400m *i2400m)
+{
+ int result;
+ struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+ struct device *dev = &i2400mu->usb_iface->dev;
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+ result = i2400mu_tx_setup(i2400mu);
+ if (result < 0)
+ goto error_usb_tx_setup;
+ result = i2400mu_rx_setup(i2400mu);
+ if (result < 0)
+ goto error_usb_rx_setup;
+ result = i2400mu_notification_setup(i2400mu);
+ if (result < 0)
+ goto error_notif_setup;
+ d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+ return result;
+
+error_notif_setup:
+ i2400mu_rx_release(i2400mu);
+error_usb_rx_setup:
+ i2400mu_tx_release(i2400mu);
+error_usb_tx_setup:
+ d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+ return result;
+}
+
+
+static
+void i2400mu_bus_dev_stop(struct i2400m *i2400m)
+{
+ struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+ struct device *dev = &i2400mu->usb_iface->dev;
+
+ d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+ i2400mu_notification_release(i2400mu);
+ i2400mu_rx_release(i2400mu);
+ i2400mu_tx_release(i2400mu);
+ d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
+
+
+/*
+ * Sends a barker buffer to the device
+ *
+ * This helper will allocate a kmalloced buffer and use it to transmit
+ * (then free it). Reason for this is that other arches cannot use
+ * stack/vmalloc/text areas for DMA transfers.
+ *
+ * Error recovery here is simpler: anything is considered a hard error
+ * and will move the reset code to use a last-resort bus-based reset.
+ */
+static
+int __i2400mu_send_barker(struct i2400mu *i2400mu,
+ const __le32 *barker,
+ size_t barker_size,
+ unsigned endpoint)
+{
+ struct usb_endpoint_descriptor *epd = NULL;
+ int pipe, actual_len, ret;
+ struct device *dev = &i2400mu->usb_iface->dev;
+ void *buffer;
+ int do_autopm = 1;
+
+ ret = usb_autopm_get_interface(i2400mu->usb_iface);
+ if (ret < 0) {
+ dev_err(dev, "RESET: can't get autopm: %d\n", ret);
+ do_autopm = 0;
+ }
+ ret = -ENOMEM;
+ buffer = kmalloc(barker_size, GFP_KERNEL);
+ if (buffer == NULL)
+ goto error_kzalloc;
+ epd = usb_get_epd(i2400mu->usb_iface, endpoint);
+ pipe = usb_sndbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
+ memcpy(buffer, barker, barker_size);
+retry:
+ ret = usb_bulk_msg(i2400mu->usb_dev, pipe, buffer, barker_size,
+ &actual_len, 200);
+ switch (ret) {
+ case 0:
+ if (actual_len != barker_size) { /* Too short? drop it */
+ dev_err(dev, "E: %s: short write (%d B vs %zu "
+ "expected)\n",
+ __func__, actual_len, barker_size);
+ ret = -EIO;
+ }
+ break;
+ case -EPIPE:
+ /*
+ * Stall -- maybe the device is choking with our
+ * requests. Clear it and give it some time. If they
+ * happen to often, it might be another symptom, so we
+ * reset.
+ *
+ * No error handling for usb_clear_halt(0; if it
+ * works, the retry works; if it fails, this switch
+ * does the error handling for us.
+ */
+ if (edc_inc(&i2400mu->urb_edc,
+ 10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+ dev_err(dev, "E: %s: too many stalls in "
+ "URB; resetting device\n", __func__);
+ usb_queue_reset_device(i2400mu->usb_iface);
+ /* fallthrough */
+ } else {
+ usb_clear_halt(i2400mu->usb_dev, pipe);
+ msleep(10); /* give the device some time */
+ goto retry;
+ }
+ fallthrough;
+ case -EINVAL: /* while removing driver */
+ case -ENODEV: /* dev disconnect ... */
+ case -ENOENT: /* just ignore it */
+ case -ESHUTDOWN: /* and exit */
+ case -ECONNRESET:
+ ret = -ESHUTDOWN;
+ break;
+ default: /* Some error? */
+ if (edc_inc(&i2400mu->urb_edc,
+ EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+ dev_err(dev, "E: %s: maximum errors in URB "
+ "exceeded; resetting device\n",
+ __func__);
+ usb_queue_reset_device(i2400mu->usb_iface);
+ } else {
+ dev_warn(dev, "W: %s: cannot send URB: %d\n",
+ __func__, ret);
+ goto retry;
+ }
+ }
+ kfree(buffer);
+error_kzalloc:
+ if (do_autopm)
+ usb_autopm_put_interface(i2400mu->usb_iface);
+ return ret;
+}
+
+
+/*
+ * Reset a device at different levels (warm, cold or bus)
+ *
+ * @i2400m: device descriptor
+ * @reset_type: soft, warm or bus reset (I2400M_RT_WARM/SOFT/BUS)
+ *
+ * Warm and cold resets get a USB reset if they fail.
+ *
+ * Warm reset:
+ *
+ * The device will be fully reset internally, but won't be
+ * disconnected from the USB bus (so no reenumeration will
+ * happen). Firmware upload will be necessary.
+ *
+ * The device will send a reboot barker in the notification endpoint
+ * that will trigger the driver to reinitialize the state
+ * automatically from notif.c:i2400m_notification_grok() into
+ * i2400m_dev_bootstrap_delayed().
+ *
+ * Cold and bus (USB) reset:
+ *
+ * The device will be fully reset internally, disconnected from the
+ * USB bus an a reenumeration will happen. Firmware upload will be
+ * necessary. Thus, we don't do any locking or struct
+ * reinitialization, as we are going to be fully disconnected and
+ * reenumerated.
+ *
+ * Note we need to return -ENODEV if a warm reset was requested and we
+ * had to resort to a bus reset. See i2400m_op_reset(), wimax_reset()
+ * and wimax_dev->op_reset.
+ *
+ * WARNING: no driver state saved/fixed
+ */
+static
+int i2400mu_bus_reset(struct i2400m *i2400m, enum i2400m_reset_type rt)
+{
+ int result;
+ struct i2400mu *i2400mu =
+ container_of(i2400m, struct i2400mu, i2400m);
+ struct device *dev = i2400m_dev(i2400m);
+ static const __le32 i2400m_WARM_BOOT_BARKER[4] = {
+ cpu_to_le32(I2400M_WARM_RESET_BARKER),
+ cpu_to_le32(I2400M_WARM_RESET_BARKER),
+ cpu_to_le32(I2400M_WARM_RESET_BARKER),
+ cpu_to_le32(I2400M_WARM_RESET_BARKER),
+ };
+ static const __le32 i2400m_COLD_BOOT_BARKER[4] = {
+ cpu_to_le32(I2400M_COLD_RESET_BARKER),
+ cpu_to_le32(I2400M_COLD_RESET_BARKER),
+ cpu_to_le32(I2400M_COLD_RESET_BARKER),
+ cpu_to_le32(I2400M_COLD_RESET_BARKER),
+ };
+
+ d_fnstart(3, dev, "(i2400m %p rt %u)\n", i2400m, rt);
+ if (rt == I2400M_RT_WARM)
+ result = __i2400mu_send_barker(
+ i2400mu, i2400m_WARM_BOOT_BARKER,
+ sizeof(i2400m_WARM_BOOT_BARKER),
+ i2400mu->endpoint_cfg.bulk_out);
+ else if (rt == I2400M_RT_COLD)
+ result = __i2400mu_send_barker(
+ i2400mu, i2400m_COLD_BOOT_BARKER,
+ sizeof(i2400m_COLD_BOOT_BARKER),
+ i2400mu->endpoint_cfg.reset_cold);
+ else if (rt == I2400M_RT_BUS) {
+ result = usb_reset_device(i2400mu->usb_dev);
+ switch (result) {
+ case 0:
+ case -EINVAL: /* device is gone */
+ case -ENODEV:
+ case -ENOENT:
+ case -ESHUTDOWN:
+ result = 0;
+ break; /* We assume the device is disconnected */
+ default:
+ dev_err(dev, "USB reset failed (%d), giving up!\n",
+ result);
+ }
+ } else {
+ result = -EINVAL; /* shut gcc up in certain arches */
+ BUG();
+ }
+ if (result < 0
+ && result != -EINVAL /* device is gone */
+ && rt != I2400M_RT_BUS) {
+ /*
+ * Things failed -- resort to lower level reset, that
+ * we queue in another context; the reason for this is
+ * that the pre and post reset functionality requires
+ * the i2400m->init_mutex; RT_WARM and RT_COLD can
+ * come from areas where i2400m->init_mutex is taken.
+ */
+ dev_err(dev, "%s reset failed (%d); trying USB reset\n",
+ rt == I2400M_RT_WARM ? "warm" : "cold", result);
+ usb_queue_reset_device(i2400mu->usb_iface);
+ result = -ENODEV;
+ }
+ d_fnend(3, dev, "(i2400m %p rt %u) = %d\n", i2400m, rt, result);
+ return result;
+}
+
+static void i2400mu_get_drvinfo(struct net_device *net_dev,
+ struct ethtool_drvinfo *info)
+{
+ struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+ struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+ struct usb_device *udev = i2400mu->usb_dev;
+
+ strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+ strlcpy(info->fw_version, i2400m->fw_name ? : "",
+ sizeof(info->fw_version));
+ usb_make_path(udev, info->bus_info, sizeof(info->bus_info));
+}
+
+static const struct ethtool_ops i2400mu_ethtool_ops = {
+ .get_drvinfo = i2400mu_get_drvinfo,
+ .get_link = ethtool_op_get_link,
+};
+
+static
+void i2400mu_netdev_setup(struct net_device *net_dev)
+{
+ struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+ struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+ i2400mu_init(i2400mu);
+ i2400m_netdev_setup(net_dev);
+ net_dev->ethtool_ops = &i2400mu_ethtool_ops;
+}
+
+
+/*
+ * Debug levels control; see debug.h
+ */
+struct d_level D_LEVEL[] = {
+ D_SUBMODULE_DEFINE(usb),
+ D_SUBMODULE_DEFINE(fw),
+ D_SUBMODULE_DEFINE(notif),
+ D_SUBMODULE_DEFINE(rx),
+ D_SUBMODULE_DEFINE(tx),
+};
+size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
+
+static
+void i2400mu_debugfs_add(struct i2400mu *i2400mu)
+{
+ struct dentry *dentry = i2400mu->i2400m.wimax_dev.debugfs_dentry;
+
+ dentry = debugfs_create_dir("i2400m-usb", dentry);
+ i2400mu->debugfs_dentry = dentry;
+
+ d_level_register_debugfs("dl_", usb, dentry);
+ d_level_register_debugfs("dl_", fw, dentry);
+ d_level_register_debugfs("dl_", notif, dentry);
+ d_level_register_debugfs("dl_", rx, dentry);
+ d_level_register_debugfs("dl_", tx, dentry);
+
+ /* Don't touch these if you don't know what you are doing */
+ debugfs_create_u8("rx_size_auto_shrink", 0600, dentry,
+ &i2400mu->rx_size_auto_shrink);
+
+ debugfs_create_size_t("rx_size", 0600, dentry, &i2400mu->rx_size);
+}
+
+
+static struct device_type i2400mu_type = {
+ .name = "wimax",
+};
+
+/*
+ * Probe a i2400m interface and register it
+ *
+ * @iface: USB interface to link to
+ * @id: USB class/subclass/protocol id
+ * @returns: 0 if ok, < 0 errno code on error.
+ *
+ * Alloc a net device, initialize the bus-specific details and then
+ * calls the bus-generic initialization routine. That will register
+ * the wimax and netdev devices, upload the firmware [using
+ * _bus_bm_*()], call _bus_dev_start() to finalize the setup of the
+ * communication with the device and then will start to talk to it to
+ * finnish setting it up.
+ */
+static
+int i2400mu_probe(struct usb_interface *iface,
+ const struct usb_device_id *id)
+{
+ int result;
+ struct net_device *net_dev;
+ struct device *dev = &iface->dev;
+ struct i2400m *i2400m;
+ struct i2400mu *i2400mu;
+ struct usb_device *usb_dev = interface_to_usbdev(iface);
+
+ if (iface->cur_altsetting->desc.bNumEndpoints < 4)
+ return -ENODEV;
+
+ if (usb_dev->speed != USB_SPEED_HIGH)
+ dev_err(dev, "device not connected as high speed\n");
+
+ /* Allocate instance [calls i2400m_netdev_setup() on it]. */
+ result = -ENOMEM;
+ net_dev = alloc_netdev(sizeof(*i2400mu), "wmx%d", NET_NAME_UNKNOWN,
+ i2400mu_netdev_setup);
+ if (net_dev == NULL) {
+ dev_err(dev, "no memory for network device instance\n");
+ goto error_alloc_netdev;
+ }
+ SET_NETDEV_DEV(net_dev, dev);
+ SET_NETDEV_DEVTYPE(net_dev, &i2400mu_type);
+ i2400m = net_dev_to_i2400m(net_dev);
+ i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+ i2400m->wimax_dev.net_dev = net_dev;
+ i2400mu->usb_dev = usb_get_dev(usb_dev);
+ i2400mu->usb_iface = iface;
+ usb_set_intfdata(iface, i2400mu);
+
+ i2400m->bus_tx_block_size = I2400MU_BLK_SIZE;
+ /*
+ * Room required in the Tx queue for USB message to accommodate
+ * a smallest payload while allocating header space is 16 bytes.
+ * Adding this room for the new tx message increases the
+ * possibilities of including any payload with size <= 16 bytes.
+ */
+ i2400m->bus_tx_room_min = I2400MU_BLK_SIZE;
+ i2400m->bus_pl_size_max = I2400MU_PL_SIZE_MAX;
+ i2400m->bus_setup = NULL;
+ i2400m->bus_dev_start = i2400mu_bus_dev_start;
+ i2400m->bus_dev_stop = i2400mu_bus_dev_stop;
+ i2400m->bus_release = NULL;
+ i2400m->bus_tx_kick = i2400mu_bus_tx_kick;
+ i2400m->bus_reset = i2400mu_bus_reset;
+ i2400m->bus_bm_retries = I2400M_USB_BOOT_RETRIES;
+ i2400m->bus_bm_cmd_send = i2400mu_bus_bm_cmd_send;
+ i2400m->bus_bm_wait_for_ack = i2400mu_bus_bm_wait_for_ack;
+ i2400m->bus_bm_mac_addr_impaired = 0;
+
+ switch (id->idProduct) {
+ case USB_DEVICE_ID_I6050:
+ case USB_DEVICE_ID_I6050_2:
+ case USB_DEVICE_ID_I6150:
+ case USB_DEVICE_ID_I6150_2:
+ case USB_DEVICE_ID_I6150_3:
+ case USB_DEVICE_ID_I6250:
+ i2400mu->i6050 = 1;
+ break;
+ default:
+ break;
+ }
+
+ if (i2400mu->i6050) {
+ i2400m->bus_fw_names = i2400mu_bus_fw_names_6050;
+ i2400mu->endpoint_cfg.bulk_out = 0;
+ i2400mu->endpoint_cfg.notification = 3;
+ i2400mu->endpoint_cfg.reset_cold = 2;
+ i2400mu->endpoint_cfg.bulk_in = 1;
+ } else {
+ i2400m->bus_fw_names = i2400mu_bus_fw_names_5x50;
+ i2400mu->endpoint_cfg.bulk_out = 0;
+ i2400mu->endpoint_cfg.notification = 1;
+ i2400mu->endpoint_cfg.reset_cold = 2;
+ i2400mu->endpoint_cfg.bulk_in = 3;
+ }
+#ifdef CONFIG_PM
+ iface->needs_remote_wakeup = 1; /* autosuspend (15s delay) */
+ device_init_wakeup(dev, 1);
+ pm_runtime_set_autosuspend_delay(&usb_dev->dev, 15000);
+ usb_enable_autosuspend(usb_dev);
+#endif
+
+ result = i2400m_setup(i2400m, I2400M_BRI_MAC_REINIT);
+ if (result < 0) {
+ dev_err(dev, "cannot setup device: %d\n", result);
+ goto error_setup;
+ }
+ i2400mu_debugfs_add(i2400mu);
+ return 0;
+
+error_setup:
+ usb_set_intfdata(iface, NULL);
+ usb_put_dev(i2400mu->usb_dev);
+ free_netdev(net_dev);
+error_alloc_netdev:
+ return result;
+}
+
+
+/*
+ * Disconnect a i2400m from the system.
+ *
+ * i2400m_stop() has been called before, so al the rx and tx contexts
+ * have been taken down already. Make sure the queue is stopped,
+ * unregister netdev and i2400m, free and kill.
+ */
+static
+void i2400mu_disconnect(struct usb_interface *iface)
+{
+ struct i2400mu *i2400mu = usb_get_intfdata(iface);
+ struct i2400m *i2400m = &i2400mu->i2400m;
+ struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+ struct device *dev = &iface->dev;
+
+ d_fnstart(3, dev, "(iface %p i2400m %p)\n", iface, i2400m);
+
+ debugfs_remove_recursive(i2400mu->debugfs_dentry);
+ i2400m_release(i2400m);
+ usb_set_intfdata(iface, NULL);
+ usb_put_dev(i2400mu->usb_dev);
+ free_netdev(net_dev);
+ d_fnend(3, dev, "(iface %p i2400m %p) = void\n", iface, i2400m);
+}
+
+
+/*
+ * Get the device ready for USB port or system standby and hibernation
+ *
+ * USB port and system standby are handled the same.
+ *
+ * When the system hibernates, the USB device is powered down and then
+ * up, so we don't really have to do much here, as it will be seen as
+ * a reconnect. Still for simplicity we consider this case the same as
+ * suspend, so that the device has a chance to do notify the base
+ * station (if connected).
+ *
+ * So at the end, the three cases require common handling.
+ *
+ * If at the time of this call the device's firmware is not loaded,
+ * nothing has to be done. Note we can be "loose" about not reading
+ * i2400m->updown under i2400m->init_mutex. If it happens to change
+ * inmediately, other parts of the call flow will fail and effectively
+ * catch it.
+ *
+ * If the firmware is loaded, we need to:
+ *
+ * - tell the device to go into host interface power save mode, wait
+ * for it to ack
+ *
+ * This is quite more interesting than it is; we need to execute a
+ * command, but this time, we don't want the code in usb-{tx,rx}.c
+ * to call the usb_autopm_get/put_interface() barriers as it'd
+ * deadlock, so we need to decrement i2400mu->do_autopm, that acts
+ * as a poor man's semaphore. Ugly, but it works.
+ *
+ * As well, the device might refuse going to sleep for whichever
+ * reason. In this case we just fail. For system suspend/hibernate,
+ * we *can't* fail. We check PMSG_IS_AUTO to see if the
+ * suspend call comes from the USB stack or from the system and act
+ * in consequence.
+ *
+ * - stop the notification endpoint polling
+ */
+static
+int i2400mu_suspend(struct usb_interface *iface, pm_message_t pm_msg)
+{
+ int result = 0;
+ struct device *dev = &iface->dev;
+ struct i2400mu *i2400mu = usb_get_intfdata(iface);
+ unsigned is_autosuspend = 0;
+ struct i2400m *i2400m = &i2400mu->i2400m;
+
+#ifdef CONFIG_PM
+ if (PMSG_IS_AUTO(pm_msg))
+ is_autosuspend = 1;
+#endif
+
+ d_fnstart(3, dev, "(iface %p pm_msg %u)\n", iface, pm_msg.event);
+ rmb(); /* see i2400m->updown's documentation */
+ if (i2400m->updown == 0)
+ goto no_firmware;
+ if (i2400m->state == I2400M_SS_DATA_PATH_CONNECTED && is_autosuspend) {
+ /* ugh -- the device is connected and this suspend
+ * request is an autosuspend one (not a system standby
+ * / hibernate).
+ *
+ * The only way the device can go to standby is if the
+ * link with the base station is in IDLE mode; that
+ * were the case, we'd be in status
+ * I2400M_SS_CONNECTED_IDLE. But we are not.
+ *
+ * If we *tell* him to go power save now, it'll reset
+ * as a precautionary measure, so if this is an
+ * autosuspend thing, say no and it'll come back
+ * later, when the link is IDLE
+ */
+ result = -EBADF;
+ d_printf(1, dev, "fw up, link up, not-idle, autosuspend: "
+ "not entering powersave\n");
+ goto error_not_now;
+ }
+ d_printf(1, dev, "fw up: entering powersave\n");
+ atomic_dec(&i2400mu->do_autopm);
+ result = i2400m_cmd_enter_powersave(i2400m);
+ atomic_inc(&i2400mu->do_autopm);
+ if (result < 0 && !is_autosuspend) {
+ /* System suspend, can't fail */
+ dev_err(dev, "failed to suspend, will reset on resume\n");
+ result = 0;
+ }
+ if (result < 0)
+ goto error_enter_powersave;
+ i2400mu_notification_release(i2400mu);
+ d_printf(1, dev, "powersave requested\n");
+error_enter_powersave:
+error_not_now:
+no_firmware:
+ d_fnend(3, dev, "(iface %p pm_msg %u) = %d\n",
+ iface, pm_msg.event, result);
+ return result;
+}
+
+
+static
+int i2400mu_resume(struct usb_interface *iface)
+{
+ int ret = 0;
+ struct device *dev = &iface->dev;
+ struct i2400mu *i2400mu = usb_get_intfdata(iface);
+ struct i2400m *i2400m = &i2400mu->i2400m;
+
+ d_fnstart(3, dev, "(iface %p)\n", iface);
+ rmb(); /* see i2400m->updown's documentation */
+ if (i2400m->updown == 0) {
+ d_printf(1, dev, "fw was down, no resume needed\n");
+ goto out;
+ }
+ d_printf(1, dev, "fw was up, resuming\n");
+ i2400mu_notification_setup(i2400mu);
+ /* USB has flow control, so we don't need to give it time to
+ * come back; otherwise, we'd use something like a get-state
+ * command... */
+out:
+ d_fnend(3, dev, "(iface %p) = %d\n", iface, ret);
+ return ret;
+}
+
+
+static
+int i2400mu_reset_resume(struct usb_interface *iface)
+{
+ int result;
+ struct device *dev = &iface->dev;
+ struct i2400mu *i2400mu = usb_get_intfdata(iface);
+ struct i2400m *i2400m = &i2400mu->i2400m;
+
+ d_fnstart(3, dev, "(iface %p)\n", iface);
+ result = i2400m_dev_reset_handle(i2400m, "device reset on resume");
+ d_fnend(3, dev, "(iface %p) = %d\n", iface, result);
+ return result < 0 ? result : 0;
+}
+
+
+/*
+ * Another driver or user space is triggering a reset on the device
+ * which contains the interface passed as an argument. Cease IO and
+ * save any device state you need to restore.
+ *
+ * If you need to allocate memory here, use GFP_NOIO or GFP_ATOMIC, if
+ * you are in atomic context.
+ */
+static
+int i2400mu_pre_reset(struct usb_interface *iface)
+{
+ struct i2400mu *i2400mu = usb_get_intfdata(iface);
+ return i2400m_pre_reset(&i2400mu->i2400m);
+}
+
+
+/*
+ * The reset has completed. Restore any saved device state and begin
+ * using the device again.
+ *
+ * If you need to allocate memory here, use GFP_NOIO or GFP_ATOMIC, if
+ * you are in atomic context.
+ */
+static
+int i2400mu_post_reset(struct usb_interface *iface)
+{
+ struct i2400mu *i2400mu = usb_get_intfdata(iface);
+ return i2400m_post_reset(&i2400mu->i2400m);
+}
+
+
+static
+struct usb_device_id i2400mu_id_table[] = {
+ { USB_DEVICE(0x8086, USB_DEVICE_ID_I6050) },
+ { USB_DEVICE(0x8086, USB_DEVICE_ID_I6050_2) },
+ { USB_DEVICE(0x8087, USB_DEVICE_ID_I6150) },
+ { USB_DEVICE(0x8087, USB_DEVICE_ID_I6150_2) },
+ { USB_DEVICE(0x8087, USB_DEVICE_ID_I6150_3) },
+ { USB_DEVICE(0x8086, USB_DEVICE_ID_I6250) },
+ { USB_DEVICE(0x8086, 0x0181) },
+ { USB_DEVICE(0x8086, 0x1403) },
+ { USB_DEVICE(0x8086, 0x1405) },
+ { USB_DEVICE(0x8086, 0x0180) },
+ { USB_DEVICE(0x8086, 0x0182) },
+ { USB_DEVICE(0x8086, 0x1406) },
+ { USB_DEVICE(0x8086, 0x1403) },
+ { },
+};
+MODULE_DEVICE_TABLE(usb, i2400mu_id_table);
+
+
+static
+struct usb_driver i2400mu_driver = {
+ .name = KBUILD_MODNAME,
+ .suspend = i2400mu_suspend,
+ .resume = i2400mu_resume,
+ .reset_resume = i2400mu_reset_resume,
+ .probe = i2400mu_probe,
+ .disconnect = i2400mu_disconnect,
+ .pre_reset = i2400mu_pre_reset,
+ .post_reset = i2400mu_post_reset,
+ .id_table = i2400mu_id_table,
+ .supports_autosuspend = 1,
+};
+
+static
+int __init i2400mu_driver_init(void)
+{
+ d_parse_params(D_LEVEL, D_LEVEL_SIZE, i2400mu_debug_params,
+ "i2400m_usb.debug");
+ return usb_register(&i2400mu_driver);
+}
+module_init(i2400mu_driver_init);
+
+
+static
+void __exit i2400mu_driver_exit(void)
+{
+ usb_deregister(&i2400mu_driver);
+}
+module_exit(i2400mu_driver_exit);
+
+MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
+MODULE_DESCRIPTION("Driver for USB based Intel Wireless WiMAX Connection 2400M "
+ "(5x50 & 6050)");
+MODULE_LICENSE("GPL");
+MODULE_FIRMWARE(I2400MU_FW_FILE_NAME_v1_5);
+MODULE_FIRMWARE(I6050U_FW_FILE_NAME_v1_5);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * Mappping of generic netlink family IDs to net devices
+ *
+ * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * We assign a single generic netlink family ID to each device (to
+ * simplify lookup).
+ *
+ * We need a way to map family ID to a wimax_dev pointer.
+ *
+ * The idea is to use a very simple lookup. Using a netlink attribute
+ * with (for example) the interface name implies a heavier search over
+ * all the network devices; seemed kind of a waste given that we know
+ * we are looking for a WiMAX device and that most systems will have
+ * just a single WiMAX adapter.
+ *
+ * We put all the WiMAX devices in the system in a linked list and
+ * match the generic link family ID against the list.
+ *
+ * By using a linked list, the case of a single adapter in the system
+ * becomes (almost) no overhead, while still working for many more. If
+ * it ever goes beyond two, I'll be surprised.
+ */
+#include <linux/device.h>
+#include <net/genetlink.h>
+#include <linux/netdevice.h>
+#include <linux/list.h>
+#include "linux-wimax.h"
+#include "wimax-internal.h"
+
+
+#define D_SUBMODULE id_table
+#include "debug-levels.h"
+
+
+static DEFINE_SPINLOCK(wimax_id_table_lock);
+static struct list_head wimax_id_table = LIST_HEAD_INIT(wimax_id_table);
+
+
+/*
+ * wimax_id_table_add - add a gennetlink familiy ID / wimax_dev mapping
+ *
+ * @wimax_dev: WiMAX device descriptor to associate to the Generic
+ * Netlink family ID.
+ *
+ * Look for an empty spot in the ID table; if none found, double the
+ * table's size and get the first spot.
+ */
+void wimax_id_table_add(struct wimax_dev *wimax_dev)
+{
+ d_fnstart(3, NULL, "(wimax_dev %p)\n", wimax_dev);
+ spin_lock(&wimax_id_table_lock);
+ list_add(&wimax_dev->id_table_node, &wimax_id_table);
+ spin_unlock(&wimax_id_table_lock);
+ d_fnend(3, NULL, "(wimax_dev %p)\n", wimax_dev);
+}
+
+
+/*
+ * wimax_get_netdev_by_info - lookup a wimax_dev from the gennetlink info
+ *
+ * The generic netlink family ID has been filled out in the
+ * nlmsghdr->nlmsg_type field, so we pull it from there, look it up in
+ * the mapping table and reference the wimax_dev.
+ *
+ * When done, the reference should be dropped with
+ * 'dev_put(wimax_dev->net_dev)'.
+ */
+struct wimax_dev *wimax_dev_get_by_genl_info(
+ struct genl_info *info, int ifindex)
+{
+ struct wimax_dev *wimax_dev = NULL;
+
+ d_fnstart(3, NULL, "(info %p ifindex %d)\n", info, ifindex);
+ spin_lock(&wimax_id_table_lock);
+ list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) {
+ if (wimax_dev->net_dev->ifindex == ifindex) {
+ dev_hold(wimax_dev->net_dev);
+ goto found;
+ }
+ }
+ wimax_dev = NULL;
+ d_printf(1, NULL, "wimax: no devices found with ifindex %d\n",
+ ifindex);
+found:
+ spin_unlock(&wimax_id_table_lock);
+ d_fnend(3, NULL, "(info %p ifindex %d) = %p\n",
+ info, ifindex, wimax_dev);
+ return wimax_dev;
+}
+
+
+/*
+ * wimax_id_table_rm - Remove a gennetlink familiy ID / wimax_dev mapping
+ *
+ * @id: family ID to remove from the table
+ */
+void wimax_id_table_rm(struct wimax_dev *wimax_dev)
+{
+ spin_lock(&wimax_id_table_lock);
+ list_del_init(&wimax_dev->id_table_node);
+ spin_unlock(&wimax_id_table_lock);
+}
+
+
+/*
+ * Release the gennetlink family id / mapping table
+ *
+ * On debug, verify that the table is empty upon removal. We want the
+ * code always compiled, to ensure it doesn't bit rot. It will be
+ * compiled out if CONFIG_BUG is disabled.
+ */
+void wimax_id_table_release(void)
+{
+ struct wimax_dev *wimax_dev;
+
+#ifndef CONFIG_BUG
+ return;
+#endif
+ spin_lock(&wimax_id_table_lock);
+ list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) {
+ pr_err("BUG: %s wimax_dev %p ifindex %d not cleared\n",
+ __func__, wimax_dev, wimax_dev->net_dev->ifindex);
+ WARN_ON(1);
+ }
+ spin_unlock(&wimax_id_table_lock);
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Linux WiMAX
+ * Collection of tools to manage debug operations.
+ *
+ * Copyright (C) 2005-2007 Intel Corporation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * Don't #include this file directly, read on!
+ *
+ * EXECUTING DEBUGGING ACTIONS OR NOT
+ *
+ * The main thing this framework provides is decission power to take a
+ * debug action (like printing a message) if the current debug level
+ * allows it.
+ *
+ * The decission power is at two levels: at compile-time (what does
+ * not make it is compiled out) and at run-time. The run-time
+ * selection is done per-submodule (as they are declared by the user
+ * of the framework).
+ *
+ * A call to d_test(L) (L being the target debug level) returns true
+ * if the action should be taken because the current debug levels
+ * allow it (both compile and run time).
+ *
+ * It follows that a call to d_test() that can be determined to be
+ * always false at compile time will get the code depending on it
+ * compiled out by optimization.
+ *
+ * DEBUG LEVELS
+ *
+ * It is up to the caller to define how much a debugging level is.
+ *
+ * Convention sets 0 as "no debug" (so an action marked as debug level 0
+ * will always be taken). The increasing debug levels are used for
+ * increased verbosity.
+ *
+ * USAGE
+ *
+ * Group the code in modules and submodules inside each module [which
+ * in most cases maps to Linux modules and .c files that compose
+ * those].
+ *
+ * For each module, there is:
+ *
+ * - a MODULENAME (single word, legal C identifier)
+ *
+ * - a debug-levels.h header file that declares the list of
+ * submodules and that is included by all .c files that use
+ * the debugging tools. The file name can be anything.
+ *
+ * - some (optional) .c code to manipulate the runtime debug levels
+ * through debugfs.
+ *
+ * The debug-levels.h file would look like:
+ *
+ * #ifndef __debug_levels__h__
+ * #define __debug_levels__h__
+ *
+ * #define D_MODULENAME modulename
+ * #define D_MASTER 10
+ *
+ * #include "linux-wimax-debug.h"
+ *
+ * enum d_module {
+ * D_SUBMODULE_DECLARE(submodule_1),
+ * D_SUBMODULE_DECLARE(submodule_2),
+ * ...
+ * D_SUBMODULE_DECLARE(submodule_N)
+ * };
+ *
+ * #endif
+ *
+ * D_MASTER is the maximum compile-time debug level; any debug actions
+ * above this will be out. D_MODULENAME is the module name (legal C
+ * identifier), which has to be unique for each module (to avoid
+ * namespace collisions during linkage). Note those #defines need to
+ * be done before #including debug.h
+ *
+ * We declare N different submodules whose debug level can be
+ * independently controlled during runtime.
+ *
+ * In a .c file of the module (and only in one of them), define the
+ * following code:
+ *
+ * struct d_level D_LEVEL[] = {
+ * D_SUBMODULE_DEFINE(submodule_1),
+ * D_SUBMODULE_DEFINE(submodule_2),
+ * ...
+ * D_SUBMODULE_DEFINE(submodule_N),
+ * };
+ * size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
+ *
+ * Externs for d_level_MODULENAME and d_level_size_MODULENAME are used
+ * and declared in this file using the D_LEVEL and D_LEVEL_SIZE macros
+ * #defined also in this file.
+ *
+ * To manipulate from user space the levels, create a debugfs dentry
+ * and then register each submodule with:
+ *
+ * d_level_register_debugfs("PREFIX_", submodule_X, parent);
+ *
+ * Where PREFIX_ is a name of your chosing. This will create debugfs
+ * file with a single numeric value that can be use to tweak it. To
+ * remove the entires, just use debugfs_remove_recursive() on 'parent'.
+ *
+ * NOTE: remember that even if this will show attached to some
+ * particular instance of a device, the settings are *global*.
+ *
+ * On each submodule (for example, .c files), the debug infrastructure
+ * should be included like this:
+ *
+ * #define D_SUBMODULE submodule_x // matches one in debug-levels.h
+ * #include "debug-levels.h"
+ *
+ * after #including all your include files.
+ *
+ * Now you can use the d_*() macros below [d_test(), d_fnstart(),
+ * d_fnend(), d_printf(), d_dump()].
+ *
+ * If their debug level is greater than D_MASTER, they will be
+ * compiled out.
+ *
+ * If their debug level is lower or equal than D_MASTER but greater
+ * than the current debug level of their submodule, they'll be
+ * ignored.
+ *
+ * Otherwise, the action will be performed.
+ */
+#ifndef __debug__h__
+#define __debug__h__
+
+#include <linux/types.h>
+#include <linux/slab.h>
+
+struct device;
+
+/* Backend stuff */
+
+/*
+ * Debug backend: generate a message header from a 'struct device'
+ *
+ * @head: buffer where to place the header
+ * @head_size: length of @head
+ * @dev: pointer to device used to generate a header from. If NULL,
+ * an empty ("") header is generated.
+ */
+static inline
+void __d_head(char *head, size_t head_size,
+ struct device *dev)
+{
+ if (dev == NULL)
+ head[0] = 0;
+ else if ((unsigned long)dev < 4096) {
+ printk(KERN_ERR "E: Corrupt dev %p\n", dev);
+ WARN_ON(1);
+ } else
+ snprintf(head, head_size, "%s %s: ",
+ dev_driver_string(dev), dev_name(dev));
+}
+
+
+/*
+ * Debug backend: log some message if debugging is enabled
+ *
+ * @l: intended debug level
+ * @tag: tag to prefix the message with
+ * @dev: 'struct device' associated to this message
+ * @f: printf-like format and arguments
+ *
+ * Note this is optimized out if it doesn't pass the compile-time
+ * check; however, it is *always* compiled. This is useful to make
+ * sure the printf-like formats and variables are always checked and
+ * they don't get bit rot if you have all the debugging disabled.
+ */
+#define _d_printf(l, tag, dev, f, a...) \
+do { \
+ char head[64]; \
+ if (!d_test(l)) \
+ break; \
+ __d_head(head, sizeof(head), dev); \
+ printk(KERN_ERR "%s%s%s: " f, head, __func__, tag, ##a); \
+} while (0)
+
+
+/*
+ * CPP syntactic sugar to generate A_B like symbol names when one of
+ * the arguments is a preprocessor #define.
+ */
+#define __D_PASTE__(varname, modulename) varname##_##modulename
+#define __D_PASTE(varname, modulename) (__D_PASTE__(varname, modulename))
+#define _D_SUBMODULE_INDEX(_name) (D_SUBMODULE_DECLARE(_name))
+
+
+/*
+ * Store a submodule's runtime debug level and name
+ */
+struct d_level {
+ u8 level;
+ const char *name;
+};
+
+
+/*
+ * List of available submodules and their debug levels
+ *
+ * We call them d_level_MODULENAME and d_level_size_MODULENAME; the
+ * macros D_LEVEL and D_LEVEL_SIZE contain the name already for
+ * convenience.
+ *
+ * This array and the size are defined on some .c file that is part of
+ * the current module.
+ */
+#define D_LEVEL __D_PASTE(d_level, D_MODULENAME)
+#define D_LEVEL_SIZE __D_PASTE(d_level_size, D_MODULENAME)
+
+extern struct d_level D_LEVEL[];
+extern size_t D_LEVEL_SIZE;
+
+
+/*
+ * Frontend stuff
+ *
+ *
+ * Stuff you need to declare prior to using the actual "debug" actions
+ * (defined below).
+ */
+
+#ifndef D_MODULENAME
+#error D_MODULENAME is not defined in your debug-levels.h file
+/**
+ * D_MODULE - Name of the current module
+ *
+ * #define in your module's debug-levels.h, making sure it is
+ * unique. This has to be a legal C identifier.
+ */
+#define D_MODULENAME undefined_modulename
+#endif
+
+
+#ifndef D_MASTER
+#warning D_MASTER not defined, but debug.h included! [see docs]
+/**
+ * D_MASTER - Compile time maximum debug level
+ *
+ * #define in your debug-levels.h file to the maximum debug level the
+ * runtime code will be allowed to have. This allows you to provide a
+ * main knob.
+ *
+ * Anything above that level will be optimized out of the compile.
+ *
+ * Defaults to zero (no debug code compiled in).
+ *
+ * Maximum one definition per module (at the debug-levels.h file).
+ */
+#define D_MASTER 0
+#endif
+
+#ifndef D_SUBMODULE
+#error D_SUBMODULE not defined, but debug.h included! [see docs]
+/**
+ * D_SUBMODULE - Name of the current submodule
+ *
+ * #define in your submodule .c file before #including debug-levels.h
+ * to the name of the current submodule as previously declared and
+ * defined with D_SUBMODULE_DECLARE() (in your module's
+ * debug-levels.h) and D_SUBMODULE_DEFINE().
+ *
+ * This is used to provide runtime-control over the debug levels.
+ *
+ * Maximum one per .c file! Can be shared among different .c files
+ * (meaning they belong to the same submodule categorization).
+ */
+#define D_SUBMODULE undefined_module
+#endif
+
+
+/**
+ * D_SUBMODULE_DECLARE - Declare a submodule for runtime debug level control
+ *
+ * @_name: name of the submodule, restricted to the chars that make up a
+ * valid C identifier ([a-zA-Z0-9_]).
+ *
+ * Declare in the module's debug-levels.h header file as:
+ *
+ * enum d_module {
+ * D_SUBMODULE_DECLARE(submodule_1),
+ * D_SUBMODULE_DECLARE(submodule_2),
+ * D_SUBMODULE_DECLARE(submodule_3),
+ * };
+ *
+ * Some corresponding .c file needs to have a matching
+ * D_SUBMODULE_DEFINE().
+ */
+#define D_SUBMODULE_DECLARE(_name) __D_SUBMODULE_##_name
+
+
+/**
+ * D_SUBMODULE_DEFINE - Define a submodule for runtime debug level control
+ *
+ * @_name: name of the submodule, restricted to the chars that make up a
+ * valid C identifier ([a-zA-Z0-9_]).
+ *
+ * Use once per module (in some .c file) as:
+ *
+ * static
+ * struct d_level d_level_SUBMODULENAME[] = {
+ * D_SUBMODULE_DEFINE(submodule_1),
+ * D_SUBMODULE_DEFINE(submodule_2),
+ * D_SUBMODULE_DEFINE(submodule_3),
+ * };
+ * size_t d_level_size_SUBDMODULENAME = ARRAY_SIZE(d_level_SUBDMODULENAME);
+ *
+ * Matching D_SUBMODULE_DECLARE()s have to be present in a
+ * debug-levels.h header file.
+ */
+#define D_SUBMODULE_DEFINE(_name) \
+[__D_SUBMODULE_##_name] = { \
+ .level = 0, \
+ .name = #_name \
+}
+
+
+
+/* The actual "debug" operations */
+
+
+/**
+ * d_test - Returns true if debugging should be enabled
+ *
+ * @l: intended debug level (unsigned)
+ *
+ * If the master debug switch is enabled and the current settings are
+ * higher or equal to the requested level, then debugging
+ * output/actions should be enabled.
+ *
+ * NOTE:
+ *
+ * This needs to be coded so that it can be evaluated in compile
+ * time; this is why the ugly BUG_ON() is placed in there, so the
+ * D_MASTER evaluation compiles all out if it is compile-time false.
+ */
+#define d_test(l) \
+({ \
+ unsigned __l = l; /* type enforcer */ \
+ (D_MASTER) >= __l \
+ && ({ \
+ BUG_ON(_D_SUBMODULE_INDEX(D_SUBMODULE) >= D_LEVEL_SIZE);\
+ D_LEVEL[_D_SUBMODULE_INDEX(D_SUBMODULE)].level >= __l; \
+ }); \
+})
+
+
+/**
+ * d_fnstart - log message at function start if debugging enabled
+ *
+ * @l: intended debug level
+ * @_dev: 'struct device' pointer, NULL if none (for context)
+ * @f: printf-like format and arguments
+ */
+#define d_fnstart(l, _dev, f, a...) _d_printf(l, " FNSTART", _dev, f, ## a)
+
+
+/**
+ * d_fnend - log message at function end if debugging enabled
+ *
+ * @l: intended debug level
+ * @_dev: 'struct device' pointer, NULL if none (for context)
+ * @f: printf-like format and arguments
+ */
+#define d_fnend(l, _dev, f, a...) _d_printf(l, " FNEND", _dev, f, ## a)
+
+
+/**
+ * d_printf - log message if debugging enabled
+ *
+ * @l: intended debug level
+ * @_dev: 'struct device' pointer, NULL if none (for context)
+ * @f: printf-like format and arguments
+ */
+#define d_printf(l, _dev, f, a...) _d_printf(l, "", _dev, f, ## a)
+
+
+/**
+ * d_dump - log buffer hex dump if debugging enabled
+ *
+ * @l: intended debug level
+ * @_dev: 'struct device' pointer, NULL if none (for context)
+ * @f: printf-like format and arguments
+ */
+#define d_dump(l, dev, ptr, size) \
+do { \
+ char head[64]; \
+ if (!d_test(l)) \
+ break; \
+ __d_head(head, sizeof(head), dev); \
+ print_hex_dump(KERN_ERR, head, 0, 16, 1, \
+ ((void *) ptr), (size), 0); \
+} while (0)
+
+
+/**
+ * Export a submodule's debug level over debugfs as PREFIXSUBMODULE
+ *
+ * @prefix: string to prefix the name with
+ * @submodule: name of submodule (not a string, just the name)
+ * @dentry: debugfs parent dentry
+ *
+ * For removing, just use debugfs_remove_recursive() on the parent.
+ */
+#define d_level_register_debugfs(prefix, name, parent) \
+({ \
+ debugfs_create_u8( \
+ prefix #name, 0600, parent, \
+ &(D_LEVEL[__D_SUBMODULE_ ## name].level)); \
+})
+
+
+static inline
+void d_submodule_set(struct d_level *d_level, size_t d_level_size,
+ const char *submodule, u8 level, const char *tag)
+{
+ struct d_level *itr, *top;
+ int index = -1;
+
+ for (itr = d_level, top = itr + d_level_size; itr < top; itr++) {
+ index++;
+ if (itr->name == NULL) {
+ printk(KERN_ERR "%s: itr->name NULL?? (%p, #%d)\n",
+ tag, itr, index);
+ continue;
+ }
+ if (!strcmp(itr->name, submodule)) {
+ itr->level = level;
+ return;
+ }
+ }
+ printk(KERN_ERR "%s: unknown submodule %s\n", tag, submodule);
+}
+
+
+/**
+ * d_parse_params - Parse a string with debug parameters from the
+ * command line
+ *
+ * @d_level: level structure (D_LEVEL)
+ * @d_level_size: number of items in the level structure
+ * (D_LEVEL_SIZE).
+ * @_params: string with the parameters; this is a space (not tab!)
+ * separated list of NAME:VALUE, where value is the debug level
+ * and NAME is the name of the submodule.
+ * @tag: string for error messages (example: MODULE.ARGNAME).
+ */
+static inline
+void d_parse_params(struct d_level *d_level, size_t d_level_size,
+ const char *_params, const char *tag)
+{
+ char submodule[130], *params, *params_orig, *token, *colon;
+ unsigned level, tokens;
+
+ if (_params == NULL)
+ return;
+ params_orig = kstrdup(_params, GFP_KERNEL);
+ params = params_orig;
+ while (1) {
+ token = strsep(¶ms, " ");
+ if (token == NULL)
+ break;
+ if (*token == '\0') /* eat joint spaces */
+ continue;
+ /* kernel's sscanf %s eats until whitespace, so we
+ * replace : by \n so it doesn't get eaten later by
+ * strsep */
+ colon = strchr(token, ':');
+ if (colon != NULL)
+ *colon = '\n';
+ tokens = sscanf(token, "%s\n%u", submodule, &level);
+ if (colon != NULL)
+ *colon = ':'; /* set back, for error messages */
+ if (tokens == 2)
+ d_submodule_set(d_level, d_level_size,
+ submodule, level, tag);
+ else
+ printk(KERN_ERR "%s: can't parse '%s' as a "
+ "SUBMODULE:LEVEL (%d tokens)\n",
+ tag, token, tokens);
+ }
+ kfree(params_orig);
+}
+
+#endif /* #ifndef __debug__h__ */
--- /dev/null
+/*
+ * Linux WiMax
+ * API for user space
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * - Initial implementation
+ *
+ *
+ * This file declares the user/kernel protocol that is spoken over
+ * Generic Netlink, as well as any type declaration that is to be used
+ * by kernel and user space.
+ *
+ * It is intended for user space to clone it verbatim to use it as a
+ * primary reference for definitions.
+ *
+ * Stuff intended for kernel usage as well as full protocol and stack
+ * documentation is rooted in include/net/wimax.h.
+ */
+
+#ifndef __LINUX__WIMAX_H__
+#define __LINUX__WIMAX_H__
+
+#include <linux/types.h>
+
+enum {
+ /**
+ * Version of the interface (unsigned decimal, MMm, max 25.5)
+ * M - Major: change if removing or modifying an existing call.
+ * m - minor: change when adding a new call
+ */
+ WIMAX_GNL_VERSION = 01,
+ /* Generic NetLink attributes */
+ WIMAX_GNL_ATTR_INVALID = 0x00,
+ WIMAX_GNL_ATTR_MAX = 10,
+};
+
+
+/*
+ * Generic NetLink operations
+ *
+ * Most of these map to an API call; _OP_ stands for operation, _RP_
+ * for reply and _RE_ for report (aka: signal).
+ */
+enum {
+ WIMAX_GNL_OP_MSG_FROM_USER, /* User to kernel message */
+ WIMAX_GNL_OP_MSG_TO_USER, /* Kernel to user message */
+ WIMAX_GNL_OP_RFKILL, /* Run wimax_rfkill() */
+ WIMAX_GNL_OP_RESET, /* Run wimax_rfkill() */
+ WIMAX_GNL_RE_STATE_CHANGE, /* Report: status change */
+ WIMAX_GNL_OP_STATE_GET, /* Request for current state */
+};
+
+
+/* Message from user / to user */
+enum {
+ WIMAX_GNL_MSG_IFIDX = 1,
+ WIMAX_GNL_MSG_PIPE_NAME,
+ WIMAX_GNL_MSG_DATA,
+};
+
+
+/*
+ * wimax_rfkill()
+ *
+ * The state of the radio (ON/OFF) is mapped to the rfkill subsystem's
+ * switch state (DISABLED/ENABLED).
+ */
+enum wimax_rf_state {
+ WIMAX_RF_OFF = 0, /* Radio is off, rfkill on/enabled */
+ WIMAX_RF_ON = 1, /* Radio is on, rfkill off/disabled */
+ WIMAX_RF_QUERY = 2,
+};
+
+/* Attributes */
+enum {
+ WIMAX_GNL_RFKILL_IFIDX = 1,
+ WIMAX_GNL_RFKILL_STATE,
+};
+
+
+/* Attributes for wimax_reset() */
+enum {
+ WIMAX_GNL_RESET_IFIDX = 1,
+};
+
+/* Attributes for wimax_state_get() */
+enum {
+ WIMAX_GNL_STGET_IFIDX = 1,
+};
+
+/*
+ * Attributes for the Report State Change
+ *
+ * For now we just have the old and new states; new attributes might
+ * be added later on.
+ */
+enum {
+ WIMAX_GNL_STCH_IFIDX = 1,
+ WIMAX_GNL_STCH_STATE_OLD,
+ WIMAX_GNL_STCH_STATE_NEW,
+};
+
+
+/**
+ * enum wimax_st - The different states of a WiMAX device
+ * @__WIMAX_ST_NULL: The device structure has been allocated and zeroed,
+ * but still wimax_dev_add() hasn't been called. There is no state.
+ *
+ * @WIMAX_ST_DOWN: The device has been registered with the WiMAX and
+ * networking stacks, but it is not initialized (normally that is
+ * done with 'ifconfig DEV up' [or equivalent], which can upload
+ * firmware and enable communications with the device).
+ * In this state, the device is powered down and using as less
+ * power as possible.
+ * This state is the default after a call to wimax_dev_add(). It
+ * is ok to have drivers move directly to %WIMAX_ST_UNINITIALIZED
+ * or %WIMAX_ST_RADIO_OFF in _probe() after the call to
+ * wimax_dev_add().
+ * It is recommended that the driver leaves this state when
+ * calling 'ifconfig DEV up' and enters it back on 'ifconfig DEV
+ * down'.
+ *
+ * @__WIMAX_ST_QUIESCING: The device is being torn down, so no API
+ * operations are allowed to proceed except the ones needed to
+ * complete the device clean up process.
+ *
+ * @WIMAX_ST_UNINITIALIZED: [optional] Communication with the device
+ * is setup, but the device still requires some configuration
+ * before being operational.
+ * Some WiMAX API calls might work.
+ *
+ * @WIMAX_ST_RADIO_OFF: The device is fully up; radio is off (wether
+ * by hardware or software switches).
+ * It is recommended to always leave the device in this state
+ * after initialization.
+ *
+ * @WIMAX_ST_READY: The device is fully up and radio is on.
+ *
+ * @WIMAX_ST_SCANNING: [optional] The device has been instructed to
+ * scan. In this state, the device cannot be actively connected to
+ * a network.
+ *
+ * @WIMAX_ST_CONNECTING: The device is connecting to a network. This
+ * state exists because in some devices, the connect process can
+ * include a number of negotiations between user space, kernel
+ * space and the device. User space needs to know what the device
+ * is doing. If the connect sequence in a device is atomic and
+ * fast, the device can transition directly to CONNECTED
+ *
+ * @WIMAX_ST_CONNECTED: The device is connected to a network.
+ *
+ * @__WIMAX_ST_INVALID: This is an invalid state used to mark the
+ * maximum numeric value of states.
+ *
+ * Description:
+ *
+ * Transitions from one state to another one are atomic and can only
+ * be caused in kernel space with wimax_state_change(). To read the
+ * state, use wimax_state_get().
+ *
+ * States starting with __ are internal and shall not be used or
+ * referred to by drivers or userspace. They look ugly, but that's the
+ * point -- if any use is made non-internal to the stack, it is easier
+ * to catch on review.
+ *
+ * All API operations [with well defined exceptions] will take the
+ * device mutex before starting and then check the state. If the state
+ * is %__WIMAX_ST_NULL, %WIMAX_ST_DOWN, %WIMAX_ST_UNINITIALIZED or
+ * %__WIMAX_ST_QUIESCING, it will drop the lock and quit with
+ * -%EINVAL, -%ENOMEDIUM, -%ENOTCONN or -%ESHUTDOWN.
+ *
+ * The order of the definitions is important, so we can do numerical
+ * comparisons (eg: < %WIMAX_ST_RADIO_OFF means the device is not ready
+ * to operate).
+ */
+/*
+ * The allowed state transitions are described in the table below
+ * (states in rows can go to states in columns where there is an X):
+ *
+ * UNINI RADIO READY SCAN CONNEC CONNEC
+ * NULL DOWN QUIESCING TIALIZED OFF NING TING TED
+ * NULL - x
+ * DOWN - x x x
+ * QUIESCING x -
+ * UNINITIALIZED x - x
+ * RADIO_OFF x - x
+ * READY x x - x x x
+ * SCANNING x x x - x x
+ * CONNECTING x x x x - x
+ * CONNECTED x x x -
+ *
+ * This table not available in kernel-doc because the formatting messes it up.
+ */
+ enum wimax_st {
+ __WIMAX_ST_NULL = 0,
+ WIMAX_ST_DOWN,
+ __WIMAX_ST_QUIESCING,
+ WIMAX_ST_UNINITIALIZED,
+ WIMAX_ST_RADIO_OFF,
+ WIMAX_ST_READY,
+ WIMAX_ST_SCANNING,
+ WIMAX_ST_CONNECTING,
+ WIMAX_ST_CONNECTED,
+ __WIMAX_ST_INVALID /* Always keep last */
+};
+
+
+#endif /* #ifndef __LINUX__WIMAX_H__ */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Linux WiMAX
+ * Kernel space API for accessing WiMAX devices
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * The WiMAX stack provides an API for controlling and managing the
+ * system's WiMAX devices. This API affects the control plane; the
+ * data plane is accessed via the network stack (netdev).
+ *
+ * Parts of the WiMAX stack API and notifications are exported to
+ * user space via Generic Netlink. In user space, libwimax (part of
+ * the wimax-tools package) provides a shim layer for accessing those
+ * calls.
+ *
+ * The API is standarized for all WiMAX devices and different drivers
+ * implement the backend support for it. However, device-specific
+ * messaging pipes are provided that can be used to issue commands and
+ * receive notifications in free form.
+ *
+ * Currently the messaging pipes are the only means of control as it
+ * is not known (due to the lack of more devices in the market) what
+ * will be a good abstraction layer. Expect this to change as more
+ * devices show in the market. This API is designed to be growable in
+ * order to address this problem.
+ *
+ * USAGE
+ *
+ * Embed a `struct wimax_dev` at the beginning of the device's
+ * private structure, initialize and register it. For details, see
+ * `struct wimax_dev`s documentation.
+ *
+ * Once this is done, wimax-tools's libwimaxll can be used to
+ * communicate with the driver from user space. You user space
+ * application does not have to forcibily use libwimaxll and can talk
+ * the generic netlink protocol directly if desired.
+ *
+ * Remember this is a very low level API that will to provide all of
+ * WiMAX features. Other daemons and services running in user space
+ * are the expected clients of it. They offer a higher level API that
+ * applications should use (an example of this is the Intel's WiMAX
+ * Network Service for the i2400m).
+ *
+ * DESIGN
+ *
+ * Although not set on final stone, this very basic interface is
+ * mostly completed. Remember this is meant to grow as new common
+ * operations are decided upon. New operations will be added to the
+ * interface, intent being on keeping backwards compatibility as much
+ * as possible.
+ *
+ * This layer implements a set of calls to control a WiMAX device,
+ * exposing a frontend to the rest of the kernel and user space (via
+ * generic netlink) and a backend implementation in the driver through
+ * function pointers.
+ *
+ * WiMAX devices have a state, and a kernel-only API allows the
+ * drivers to manipulate that state. State transitions are atomic, and
+ * only some of them are allowed (see `enum wimax_st`).
+ *
+ * Most API calls will set the state automatically; in most cases
+ * drivers have to only report state changes due to external
+ * conditions.
+ *
+ * All API operations are 'atomic', serialized through a mutex in the
+ * `struct wimax_dev`.
+ *
+ * EXPORTING TO USER SPACE THROUGH GENERIC NETLINK
+ *
+ * The API is exported to user space using generic netlink (other
+ * methods can be added as needed).
+ *
+ * There is a Generic Netlink Family named "WiMAX", where interfaces
+ * supporting the WiMAX interface receive commands and broadcast their
+ * signals over a multicast group named "msg".
+ *
+ * Mapping to the source/destination interface is done by an interface
+ * index attribute.
+ *
+ * For user-to-kernel traffic (commands) we use a function call
+ * marshalling mechanism, where a message X with attributes A, B, C
+ * sent from user space to kernel space means executing the WiMAX API
+ * call wimax_X(A, B, C), sending the results back as a message.
+ *
+ * Kernel-to-user (notifications or signals) communication is sent
+ * over multicast groups. This allows to have multiple applications
+ * monitoring them.
+ *
+ * Each command/signal gets assigned it's own attribute policy. This
+ * way the validator will verify that all the attributes in there are
+ * only the ones that should be for each command/signal. Thing of an
+ * attribute mapping to a type+argumentname for each command/signal.
+ *
+ * If we had a single policy for *all* commands/signals, after running
+ * the validator we'd have to check "does this attribute belong in
+ * here"? for each one. It can be done manually, but it's just easier
+ * to have the validator do that job with multiple policies. As well,
+ * it makes it easier to later expand each command/signal signature
+ * without affecting others and keeping the namespace more or less
+ * sane. Not that it is too complicated, but it makes it even easier.
+ *
+ * No state information is maintained in the kernel for each user
+ * space connection (the connection is stateless).
+ *
+ * TESTING FOR THE INTERFACE AND VERSIONING
+ *
+ * If network interface X is a WiMAX device, there will be a Generic
+ * Netlink family named "WiMAX X" and the device will present a
+ * "wimax" directory in it's network sysfs directory
+ * (/sys/class/net/DEVICE/wimax) [used by HAL].
+ *
+ * The inexistence of any of these means the device does not support
+ * this WiMAX API.
+ *
+ * By querying the generic netlink controller, versioning information
+ * and the multicast groups available can be found. Applications using
+ * the interface can either rely on that or use the generic netlink
+ * controller to figure out which generic netlink commands/signals are
+ * supported.
+ *
+ * NOTE: this versioning is a last resort to avoid hard
+ * incompatibilities. It is the intention of the design of this
+ * stack not to introduce backward incompatible changes.
+ *
+ * The version code has to fit in one byte (restrictions imposed by
+ * generic netlink); we use `version / 10` for the major version and
+ * `version % 10` for the minor. This gives 9 minors for each major
+ * and 25 majors.
+ *
+ * The version change protocol is as follow:
+ *
+ * - Major versions: needs to be increased if an existing message/API
+ * call is changed or removed. Doesn't need to be changed if a new
+ * message is added.
+ *
+ * - Minor version: needs to be increased if new messages/API calls are
+ * being added or some other consideration that doesn't impact the
+ * user-kernel interface too much (like some kind of bug fix) and
+ * that is kind of left up in the air to common sense.
+ *
+ * User space code should not try to work if the major version it was
+ * compiled for differs from what the kernel offers. As well, if the
+ * minor version of the kernel interface is lower than the one user
+ * space is expecting (the one it was compiled for), the kernel
+ * might be missing API calls; user space shall be ready to handle
+ * said condition. Use the generic netlink controller operations to
+ * find which ones are supported and which not.
+ *
+ * libwimaxll:wimaxll_open() takes care of checking versions.
+ *
+ * THE OPERATIONS:
+ *
+ * Each operation is defined in its on file (drivers/net/wimax/op-*.c)
+ * for clarity. The parts needed for an operation are:
+ *
+ * - a function pointer in `struct wimax_dev`: optional, as the
+ * operation might be implemented by the stack and not by the
+ * driver.
+ *
+ * All function pointers are named wimax_dev->op_*(), and drivers
+ * must implement them except where noted otherwise.
+ *
+ * - When exported to user space, a `struct nla_policy` to define the
+ * attributes of the generic netlink command and a `struct genl_ops`
+ * to define the operation.
+ *
+ * All the declarations for the operation codes (WIMAX_GNL_OP_<NAME>)
+ * and generic netlink attributes (WIMAX_GNL_<NAME>_*) are declared in
+ * include/linux/wimax.h; this file is intended to be cloned by user
+ * space to gain access to those declarations.
+ *
+ * A few caveats to remember:
+ *
+ * - Need to define attribute numbers starting in 1; otherwise it
+ * fails.
+ *
+ * - the `struct genl_family` requires a maximum attribute id; when
+ * defining the `struct nla_policy` for each message, it has to have
+ * an array size of WIMAX_GNL_ATTR_MAX+1.
+ *
+ * The op_*() function pointers will not be called if the wimax_dev is
+ * in a state <= %WIMAX_ST_UNINITIALIZED. The exception is:
+ *
+ * - op_reset: can be called at any time after wimax_dev_add() has
+ * been called.
+ *
+ * THE PIPE INTERFACE:
+ *
+ * This interface is kept intentionally simple. The driver can send
+ * and receive free-form messages to/from user space through a
+ * pipe. See drivers/net/wimax/op-msg.c for details.
+ *
+ * The kernel-to-user messages are sent with
+ * wimax_msg(). user-to-kernel messages are delivered via
+ * wimax_dev->op_msg_from_user().
+ *
+ * RFKILL:
+ *
+ * RFKILL support is built into the wimax_dev layer; the driver just
+ * needs to call wimax_report_rfkill_{hw,sw}() to inform of changes in
+ * the hardware or software RF kill switches. When the stack wants to
+ * turn the radio off, it will call wimax_dev->op_rfkill_sw_toggle(),
+ * which the driver implements.
+ *
+ * User space can set the software RF Kill switch by calling
+ * wimax_rfkill().
+ *
+ * The code for now only supports devices that don't require polling;
+ * If the device needs to be polled, create a self-rearming delayed
+ * work struct for polling or look into adding polled support to the
+ * WiMAX stack.
+ *
+ * When initializing the hardware (_probe), after calling
+ * wimax_dev_add(), query the device for it's RF Kill switches status
+ * and feed it back to the WiMAX stack using
+ * wimax_report_rfkill_{hw,sw}(). If any switch is missing, always
+ * report it as ON.
+ *
+ * NOTE: the wimax stack uses an inverted terminology to that of the
+ * RFKILL subsystem:
+ *
+ * - ON: radio is ON, RFKILL is DISABLED or OFF.
+ * - OFF: radio is OFF, RFKILL is ENABLED or ON.
+ *
+ * MISCELLANEOUS OPS:
+ *
+ * wimax_reset() can be used to reset the device to power on state; by
+ * default it issues a warm reset that maintains the same device
+ * node. If that is not possible, it falls back to a cold reset
+ * (device reconnect). The driver implements the backend to this
+ * through wimax_dev->op_reset().
+ */
+
+#ifndef __NET__WIMAX_H__
+#define __NET__WIMAX_H__
+
+#include "linux-wimax.h"
+#include <net/genetlink.h>
+#include <linux/netdevice.h>
+
+struct net_device;
+struct genl_info;
+struct wimax_dev;
+
+/**
+ * struct wimax_dev - Generic WiMAX device
+ *
+ * @net_dev: [fill] Pointer to the &struct net_device this WiMAX
+ * device implements.
+ *
+ * @op_msg_from_user: [fill] Driver-specific operation to
+ * handle a raw message from user space to the driver. The
+ * driver can send messages to user space using with
+ * wimax_msg_to_user().
+ *
+ * @op_rfkill_sw_toggle: [fill] Driver-specific operation to act on
+ * userspace (or any other agent) requesting the WiMAX device to
+ * change the RF Kill software switch (WIMAX_RF_ON or
+ * WIMAX_RF_OFF).
+ * If such hardware support is not present, it is assumed the
+ * radio cannot be switched off and it is always on (and the stack
+ * will error out when trying to switch it off). In such case,
+ * this function pointer can be left as NULL.
+ *
+ * @op_reset: [fill] Driver specific operation to reset the
+ * device.
+ * This operation should always attempt first a warm reset that
+ * does not disconnect the device from the bus and return 0.
+ * If that fails, it should resort to some sort of cold or bus
+ * reset (even if it implies a bus disconnection and device
+ * disappearance). In that case, -ENODEV should be returned to
+ * indicate the device is gone.
+ * This operation has to be synchronous, and return only when the
+ * reset is complete. In case of having had to resort to bus/cold
+ * reset implying a device disconnection, the call is allowed to
+ * return immediately.
+ * NOTE: wimax_dev->mutex is NOT locked when this op is being
+ * called; however, wimax_dev->mutex_reset IS locked to ensure
+ * serialization of calls to wimax_reset().
+ * See wimax_reset()'s documentation.
+ *
+ * @name: [fill] A way to identify this device. We need to register a
+ * name with many subsystems (rfkill, workqueue creation, etc).
+ * We can't use the network device name as that
+ * might change and in some instances we don't know it yet (until
+ * we don't call register_netdev()). So we generate an unique one
+ * using the driver name and device bus id, place it here and use
+ * it across the board. Recommended naming:
+ * DRIVERNAME-BUSNAME:BUSID (dev->bus->name, dev->bus_id).
+ *
+ * @id_table_node: [private] link to the list of wimax devices kept by
+ * id-table.c. Protected by it's own spinlock.
+ *
+ * @mutex: [private] Serializes all concurrent access and execution of
+ * operations.
+ *
+ * @mutex_reset: [private] Serializes reset operations. Needs to be a
+ * different mutex because as part of the reset operation, the
+ * driver has to call back into the stack to do things such as
+ * state change, that require wimax_dev->mutex.
+ *
+ * @state: [private] Current state of the WiMAX device.
+ *
+ * @rfkill: [private] integration into the RF-Kill infrastructure.
+ *
+ * @rf_sw: [private] State of the software radio switch (OFF/ON)
+ *
+ * @rf_hw: [private] State of the hardware radio switch (OFF/ON)
+ *
+ * @debugfs_dentry: [private] Used to hook up a debugfs entry. This
+ * shows up in the debugfs root as wimax\:DEVICENAME.
+ *
+ * Description:
+ * This structure defines a common interface to access all WiMAX
+ * devices from different vendors and provides a common API as well as
+ * a free-form device-specific messaging channel.
+ *
+ * Usage:
+ * 1. Embed a &struct wimax_dev at *the beginning* the network
+ * device structure so that netdev_priv() points to it.
+ *
+ * 2. memset() it to zero
+ *
+ * 3. Initialize with wimax_dev_init(). This will leave the WiMAX
+ * device in the %__WIMAX_ST_NULL state.
+ *
+ * 4. Fill all the fields marked with [fill]; once called
+ * wimax_dev_add(), those fields CANNOT be modified.
+ *
+ * 5. Call wimax_dev_add() *after* registering the network
+ * device. This will leave the WiMAX device in the %WIMAX_ST_DOWN
+ * state.
+ * Protect the driver's net_device->open() against succeeding if
+ * the wimax device state is lower than %WIMAX_ST_DOWN.
+ *
+ * 6. Select when the device is going to be turned on/initialized;
+ * for example, it could be initialized on 'ifconfig up' (when the
+ * netdev op 'open()' is called on the driver).
+ *
+ * When the device is initialized (at `ifconfig up` time, or right
+ * after calling wimax_dev_add() from _probe(), make sure the
+ * following steps are taken
+ *
+ * a. Move the device to %WIMAX_ST_UNINITIALIZED. This is needed so
+ * some API calls that shouldn't work until the device is ready
+ * can be blocked.
+ *
+ * b. Initialize the device. Make sure to turn the SW radio switch
+ * off and move the device to state %WIMAX_ST_RADIO_OFF when
+ * done. When just initialized, a device should be left in RADIO
+ * OFF state until user space devices to turn it on.
+ *
+ * c. Query the device for the state of the hardware rfkill switch
+ * and call wimax_rfkill_report_hw() and wimax_rfkill_report_sw()
+ * as needed. See below.
+ *
+ * wimax_dev_rm() undoes before unregistering the network device. Once
+ * wimax_dev_add() is called, the driver can get called on the
+ * wimax_dev->op_* function pointers
+ *
+ * CONCURRENCY:
+ *
+ * The stack provides a mutex for each device that will disallow API
+ * calls happening concurrently; thus, op calls into the driver
+ * through the wimax_dev->op*() function pointers will always be
+ * serialized and *never* concurrent.
+ *
+ * For locking, take wimax_dev->mutex is taken; (most) operations in
+ * the API have to check for wimax_dev_is_ready() to return 0 before
+ * continuing (this is done internally).
+ *
+ * REFERENCE COUNTING:
+ *
+ * The WiMAX device is reference counted by the associated network
+ * device. The only operation that can be used to reference the device
+ * is wimax_dev_get_by_genl_info(), and the reference it acquires has
+ * to be released with dev_put(wimax_dev->net_dev).
+ *
+ * RFKILL:
+ *
+ * At startup, both HW and SW radio switchess are assumed to be off.
+ *
+ * At initialization time [after calling wimax_dev_add()], have the
+ * driver query the device for the status of the software and hardware
+ * RF kill switches and call wimax_report_rfkill_hw() and
+ * wimax_rfkill_report_sw() to indicate their state. If any is
+ * missing, just call it to indicate it is ON (radio always on).
+ *
+ * Whenever the driver detects a change in the state of the RF kill
+ * switches, it should call wimax_report_rfkill_hw() or
+ * wimax_report_rfkill_sw() to report it to the stack.
+ */
+struct wimax_dev {
+ struct net_device *net_dev;
+ struct list_head id_table_node;
+ struct mutex mutex; /* Protects all members and API calls */
+ struct mutex mutex_reset;
+ enum wimax_st state;
+
+ int (*op_msg_from_user)(struct wimax_dev *wimax_dev,
+ const char *,
+ const void *, size_t,
+ const struct genl_info *info);
+ int (*op_rfkill_sw_toggle)(struct wimax_dev *wimax_dev,
+ enum wimax_rf_state);
+ int (*op_reset)(struct wimax_dev *wimax_dev);
+
+ struct rfkill *rfkill;
+ unsigned int rf_hw;
+ unsigned int rf_sw;
+ char name[32];
+
+ struct dentry *debugfs_dentry;
+};
+
+
+
+/*
+ * WiMAX stack public API for device drivers
+ * -----------------------------------------
+ *
+ * These functions are not exported to user space.
+ */
+void wimax_dev_init(struct wimax_dev *);
+int wimax_dev_add(struct wimax_dev *, struct net_device *);
+void wimax_dev_rm(struct wimax_dev *);
+
+static inline
+struct wimax_dev *net_dev_to_wimax(struct net_device *net_dev)
+{
+ return netdev_priv(net_dev);
+}
+
+static inline
+struct device *wimax_dev_to_dev(struct wimax_dev *wimax_dev)
+{
+ return wimax_dev->net_dev->dev.parent;
+}
+
+void wimax_state_change(struct wimax_dev *, enum wimax_st);
+enum wimax_st wimax_state_get(struct wimax_dev *);
+
+/*
+ * Radio Switch state reporting.
+ *
+ * enum wimax_rf_state is declared in linux/wimax.h so the exports
+ * to user space can use it.
+ */
+void wimax_report_rfkill_hw(struct wimax_dev *, enum wimax_rf_state);
+void wimax_report_rfkill_sw(struct wimax_dev *, enum wimax_rf_state);
+
+
+/*
+ * Free-form messaging to/from user space
+ *
+ * Sending a message:
+ *
+ * wimax_msg(wimax_dev, pipe_name, buf, buf_size, GFP_KERNEL);
+ *
+ * Broken up:
+ *
+ * skb = wimax_msg_alloc(wimax_dev, pipe_name, buf_size, GFP_KERNEL);
+ * ...fill up skb...
+ * wimax_msg_send(wimax_dev, pipe_name, skb);
+ *
+ * Be sure not to modify skb->data in the middle (ie: don't use
+ * skb_push()/skb_pull()/skb_reserve() on the skb).
+ *
+ * "pipe_name" is any string, that can be interpreted as the name of
+ * the pipe or recipient; the interpretation of it is driver
+ * specific, so the recipient can multiplex it as wished. It can be
+ * NULL, it won't be used - an example is using a "diagnostics" tag to
+ * send diagnostics information that a device-specific diagnostics
+ * tool would be interested in.
+ */
+struct sk_buff *wimax_msg_alloc(struct wimax_dev *, const char *, const void *,
+ size_t, gfp_t);
+int wimax_msg_send(struct wimax_dev *, struct sk_buff *);
+int wimax_msg(struct wimax_dev *, const char *, const void *, size_t, gfp_t);
+
+const void *wimax_msg_data_len(struct sk_buff *, size_t *);
+const void *wimax_msg_data(struct sk_buff *);
+ssize_t wimax_msg_len(struct sk_buff *);
+
+
+/*
+ * WiMAX stack user space API
+ * --------------------------
+ *
+ * This API is what gets exported to user space for general
+ * operations. As well, they can be called from within the kernel,
+ * (with a properly referenced `struct wimax_dev`).
+ *
+ * Properly referenced means: the 'struct net_device' that embeds the
+ * device's control structure and (as such) the 'struct wimax_dev' is
+ * referenced by the caller.
+ */
+int wimax_rfkill(struct wimax_dev *, enum wimax_rf_state);
+int wimax_reset(struct wimax_dev *);
+
+#endif /* #ifndef __NET__WIMAX_H__ */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * Generic messaging interface between userspace and driver/device
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This implements a direct communication channel between user space and
+ * the driver/device, by which free form messages can be sent back and
+ * forth.
+ *
+ * This is intended for device-specific features, vendor quirks, etc.
+ *
+ * See include/net/wimax.h
+ *
+ * GENERIC NETLINK ENCODING AND CAPACITY
+ *
+ * A destination "pipe name" is added to each message; it is up to the
+ * drivers to assign or use those names (if using them at all).
+ *
+ * Messages are encoded as a binary netlink attribute using nla_put()
+ * using type NLA_UNSPEC (as some versions of libnl still in
+ * deployment don't yet understand NLA_BINARY).
+ *
+ * The maximum capacity of this transport is PAGESIZE per message (so
+ * the actual payload will be bit smaller depending on the
+ * netlink/generic netlink attributes and headers).
+ *
+ * RECEPTION OF MESSAGES
+ *
+ * When a message is received from user space, it is passed verbatim
+ * to the driver calling wimax_dev->op_msg_from_user(). The return
+ * value from this function is passed back to user space as an ack
+ * over the generic netlink protocol.
+ *
+ * The stack doesn't do any processing or interpretation of these
+ * messages.
+ *
+ * SENDING MESSAGES
+ *
+ * Messages can be sent with wimax_msg().
+ *
+ * If the message delivery needs to happen on a different context to
+ * that of its creation, wimax_msg_alloc() can be used to get a
+ * pointer to the message that can be delivered later on with
+ * wimax_msg_send().
+ *
+ * ROADMAP
+ *
+ * wimax_gnl_doit_msg_from_user() Process a message from user space
+ * wimax_dev_get_by_genl_info()
+ * wimax_dev->op_msg_from_user() Delivery of message to the driver
+ *
+ * wimax_msg() Send a message to user space
+ * wimax_msg_alloc()
+ * wimax_msg_send()
+ */
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <net/genetlink.h>
+#include <linux/netdevice.h>
+#include "linux-wimax.h"
+#include <linux/security.h>
+#include <linux/export.h>
+#include "wimax-internal.h"
+
+
+#define D_SUBMODULE op_msg
+#include "debug-levels.h"
+
+
+/**
+ * wimax_msg_alloc - Create a new skb for sending a message to userspace
+ *
+ * @wimax_dev: WiMAX device descriptor
+ * @pipe_name: "named pipe" the message will be sent to
+ * @msg: pointer to the message data to send
+ * @size: size of the message to send (in bytes), including the header.
+ * @gfp_flags: flags for memory allocation.
+ *
+ * Returns: %0 if ok, negative errno code on error
+ *
+ * Description:
+ *
+ * Allocates an skb that will contain the message to send to user
+ * space over the messaging pipe and initializes it, copying the
+ * payload.
+ *
+ * Once this call is done, you can deliver it with
+ * wimax_msg_send().
+ *
+ * IMPORTANT:
+ *
+ * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as
+ * wimax_msg_send() depends on skb->data being placed at the
+ * beginning of the user message.
+ *
+ * Unlike other WiMAX stack calls, this call can be used way early,
+ * even before wimax_dev_add() is called, as long as the
+ * wimax_dev->net_dev pointer is set to point to a proper
+ * net_dev. This is so that drivers can use it early in case they need
+ * to send stuff around or communicate with user space.
+ */
+struct sk_buff *wimax_msg_alloc(struct wimax_dev *wimax_dev,
+ const char *pipe_name,
+ const void *msg, size_t size,
+ gfp_t gfp_flags)
+{
+ int result;
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+ size_t msg_size;
+ void *genl_msg;
+ struct sk_buff *skb;
+
+ msg_size = nla_total_size(size)
+ + nla_total_size(sizeof(u32))
+ + (pipe_name ? nla_total_size(strlen(pipe_name)) : 0);
+ result = -ENOMEM;
+ skb = genlmsg_new(msg_size, gfp_flags);
+ if (skb == NULL)
+ goto error_new;
+ genl_msg = genlmsg_put(skb, 0, 0, &wimax_gnl_family,
+ 0, WIMAX_GNL_OP_MSG_TO_USER);
+ if (genl_msg == NULL) {
+ dev_err(dev, "no memory to create generic netlink message\n");
+ goto error_genlmsg_put;
+ }
+ result = nla_put_u32(skb, WIMAX_GNL_MSG_IFIDX,
+ wimax_dev->net_dev->ifindex);
+ if (result < 0) {
+ dev_err(dev, "no memory to add ifindex attribute\n");
+ goto error_nla_put;
+ }
+ if (pipe_name) {
+ result = nla_put_string(skb, WIMAX_GNL_MSG_PIPE_NAME,
+ pipe_name);
+ if (result < 0) {
+ dev_err(dev, "no memory to add pipe_name attribute\n");
+ goto error_nla_put;
+ }
+ }
+ result = nla_put(skb, WIMAX_GNL_MSG_DATA, size, msg);
+ if (result < 0) {
+ dev_err(dev, "no memory to add payload (msg %p size %zu) in "
+ "attribute: %d\n", msg, size, result);
+ goto error_nla_put;
+ }
+ genlmsg_end(skb, genl_msg);
+ return skb;
+
+error_nla_put:
+error_genlmsg_put:
+error_new:
+ nlmsg_free(skb);
+ return ERR_PTR(result);
+}
+EXPORT_SYMBOL_GPL(wimax_msg_alloc);
+
+
+/**
+ * wimax_msg_data_len - Return a pointer and size of a message's payload
+ *
+ * @msg: Pointer to a message created with wimax_msg_alloc()
+ * @size: Pointer to where to store the message's size
+ *
+ * Returns the pointer to the message data.
+ */
+const void *wimax_msg_data_len(struct sk_buff *msg, size_t *size)
+{
+ struct nlmsghdr *nlh = (void *) msg->head;
+ struct nlattr *nla;
+
+ nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
+ WIMAX_GNL_MSG_DATA);
+ if (nla == NULL) {
+ pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
+ return NULL;
+ }
+ *size = nla_len(nla);
+ return nla_data(nla);
+}
+EXPORT_SYMBOL_GPL(wimax_msg_data_len);
+
+
+/**
+ * wimax_msg_data - Return a pointer to a message's payload
+ *
+ * @msg: Pointer to a message created with wimax_msg_alloc()
+ */
+const void *wimax_msg_data(struct sk_buff *msg)
+{
+ struct nlmsghdr *nlh = (void *) msg->head;
+ struct nlattr *nla;
+
+ nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
+ WIMAX_GNL_MSG_DATA);
+ if (nla == NULL) {
+ pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
+ return NULL;
+ }
+ return nla_data(nla);
+}
+EXPORT_SYMBOL_GPL(wimax_msg_data);
+
+
+/**
+ * wimax_msg_len - Return a message's payload length
+ *
+ * @msg: Pointer to a message created with wimax_msg_alloc()
+ */
+ssize_t wimax_msg_len(struct sk_buff *msg)
+{
+ struct nlmsghdr *nlh = (void *) msg->head;
+ struct nlattr *nla;
+
+ nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
+ WIMAX_GNL_MSG_DATA);
+ if (nla == NULL) {
+ pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
+ return -EINVAL;
+ }
+ return nla_len(nla);
+}
+EXPORT_SYMBOL_GPL(wimax_msg_len);
+
+
+/**
+ * wimax_msg_send - Send a pre-allocated message to user space
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * @skb: &struct sk_buff returned by wimax_msg_alloc(). Note the
+ * ownership of @skb is transferred to this function.
+ *
+ * Returns: 0 if ok, < 0 errno code on error
+ *
+ * Description:
+ *
+ * Sends a free-form message that was preallocated with
+ * wimax_msg_alloc() and filled up.
+ *
+ * Assumes that once you pass an skb to this function for sending, it
+ * owns it and will release it when done (on success).
+ *
+ * IMPORTANT:
+ *
+ * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as
+ * wimax_msg_send() depends on skb->data being placed at the
+ * beginning of the user message.
+ *
+ * Unlike other WiMAX stack calls, this call can be used way early,
+ * even before wimax_dev_add() is called, as long as the
+ * wimax_dev->net_dev pointer is set to point to a proper
+ * net_dev. This is so that drivers can use it early in case they need
+ * to send stuff around or communicate with user space.
+ */
+int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb)
+{
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+ void *msg = skb->data;
+ size_t size = skb->len;
+ might_sleep();
+
+ d_printf(1, dev, "CTX: wimax msg, %zu bytes\n", size);
+ d_dump(2, dev, msg, size);
+ genlmsg_multicast(&wimax_gnl_family, skb, 0, 0, GFP_KERNEL);
+ d_printf(1, dev, "CTX: genl multicast done\n");
+ return 0;
+}
+EXPORT_SYMBOL_GPL(wimax_msg_send);
+
+
+/**
+ * wimax_msg - Send a message to user space
+ *
+ * @wimax_dev: WiMAX device descriptor (properly referenced)
+ * @pipe_name: "named pipe" the message will be sent to
+ * @buf: pointer to the message to send.
+ * @size: size of the buffer pointed to by @buf (in bytes).
+ * @gfp_flags: flags for memory allocation.
+ *
+ * Returns: %0 if ok, negative errno code on error.
+ *
+ * Description:
+ *
+ * Sends a free-form message to user space on the device @wimax_dev.
+ *
+ * NOTES:
+ *
+ * Once the @skb is given to this function, who will own it and will
+ * release it when done (unless it returns error).
+ */
+int wimax_msg(struct wimax_dev *wimax_dev, const char *pipe_name,
+ const void *buf, size_t size, gfp_t gfp_flags)
+{
+ int result = -ENOMEM;
+ struct sk_buff *skb;
+
+ skb = wimax_msg_alloc(wimax_dev, pipe_name, buf, size, gfp_flags);
+ if (IS_ERR(skb))
+ result = PTR_ERR(skb);
+ else
+ result = wimax_msg_send(wimax_dev, skb);
+ return result;
+}
+EXPORT_SYMBOL_GPL(wimax_msg);
+
+/*
+ * Relays a message from user space to the driver
+ *
+ * The skb is passed to the driver-specific function with the netlink
+ * and generic netlink headers already stripped.
+ *
+ * This call will block while handling/relaying the message.
+ */
+int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info)
+{
+ int result, ifindex;
+ struct wimax_dev *wimax_dev;
+ struct device *dev;
+ struct nlmsghdr *nlh = info->nlhdr;
+ char *pipe_name;
+ void *msg_buf;
+ size_t msg_len;
+
+ might_sleep();
+ d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
+ result = -ENODEV;
+ if (info->attrs[WIMAX_GNL_MSG_IFIDX] == NULL) {
+ pr_err("WIMAX_GNL_MSG_FROM_USER: can't find IFIDX attribute\n");
+ goto error_no_wimax_dev;
+ }
+ ifindex = nla_get_u32(info->attrs[WIMAX_GNL_MSG_IFIDX]);
+ wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
+ if (wimax_dev == NULL)
+ goto error_no_wimax_dev;
+ dev = wimax_dev_to_dev(wimax_dev);
+
+ /* Unpack arguments */
+ result = -EINVAL;
+ if (info->attrs[WIMAX_GNL_MSG_DATA] == NULL) {
+ dev_err(dev, "WIMAX_GNL_MSG_FROM_USER: can't find MSG_DATA "
+ "attribute\n");
+ goto error_no_data;
+ }
+ msg_buf = nla_data(info->attrs[WIMAX_GNL_MSG_DATA]);
+ msg_len = nla_len(info->attrs[WIMAX_GNL_MSG_DATA]);
+
+ if (info->attrs[WIMAX_GNL_MSG_PIPE_NAME] == NULL)
+ pipe_name = NULL;
+ else {
+ struct nlattr *attr = info->attrs[WIMAX_GNL_MSG_PIPE_NAME];
+ size_t attr_len = nla_len(attr);
+ /* libnl-1.1 does not yet support NLA_NUL_STRING */
+ result = -ENOMEM;
+ pipe_name = kstrndup(nla_data(attr), attr_len + 1, GFP_KERNEL);
+ if (pipe_name == NULL)
+ goto error_alloc;
+ pipe_name[attr_len] = 0;
+ }
+ mutex_lock(&wimax_dev->mutex);
+ result = wimax_dev_is_ready(wimax_dev);
+ if (result == -ENOMEDIUM)
+ result = 0;
+ if (result < 0)
+ goto error_not_ready;
+ result = -ENOSYS;
+ if (wimax_dev->op_msg_from_user == NULL)
+ goto error_noop;
+
+ d_printf(1, dev,
+ "CRX: nlmsghdr len %u type %u flags 0x%04x seq 0x%x pid %u\n",
+ nlh->nlmsg_len, nlh->nlmsg_type, nlh->nlmsg_flags,
+ nlh->nlmsg_seq, nlh->nlmsg_pid);
+ d_printf(1, dev, "CRX: wimax message %zu bytes\n", msg_len);
+ d_dump(2, dev, msg_buf, msg_len);
+
+ result = wimax_dev->op_msg_from_user(wimax_dev, pipe_name,
+ msg_buf, msg_len, info);
+error_noop:
+error_not_ready:
+ mutex_unlock(&wimax_dev->mutex);
+error_alloc:
+ kfree(pipe_name);
+error_no_data:
+ dev_put(wimax_dev->net_dev);
+error_no_wimax_dev:
+ d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
+ return result;
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * Implement and export a method for resetting a WiMAX device
+ *
+ * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This implements a simple synchronous call to reset a WiMAX device.
+ *
+ * Resets aim at being warm, keeping the device handles active;
+ * however, when that fails, it falls back to a cold reset (that will
+ * disconnect and reconnect the device).
+ */
+
+#include "net-wimax.h"
+#include <net/genetlink.h>
+#include "linux-wimax.h"
+#include <linux/security.h>
+#include <linux/export.h>
+#include "wimax-internal.h"
+
+#define D_SUBMODULE op_reset
+#include "debug-levels.h"
+
+
+/**
+ * wimax_reset - Reset a WiMAX device
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * Returns:
+ *
+ * %0 if ok and a warm reset was done (the device still exists in
+ * the system).
+ *
+ * -%ENODEV if a cold/bus reset had to be done (device has
+ * disconnected and reconnected, so current handle is not valid
+ * any more).
+ *
+ * -%EINVAL if the device is not even registered.
+ *
+ * Any other negative error code shall be considered as
+ * non-recoverable.
+ *
+ * Description:
+ *
+ * Called when wanting to reset the device for any reason. Device is
+ * taken back to power on status.
+ *
+ * This call blocks; on successful return, the device has completed the
+ * reset process and is ready to operate.
+ */
+int wimax_reset(struct wimax_dev *wimax_dev)
+{
+ int result = -EINVAL;
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+ enum wimax_st state;
+
+ might_sleep();
+ d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
+ mutex_lock(&wimax_dev->mutex);
+ dev_hold(wimax_dev->net_dev);
+ state = wimax_dev->state;
+ mutex_unlock(&wimax_dev->mutex);
+
+ if (state >= WIMAX_ST_DOWN) {
+ mutex_lock(&wimax_dev->mutex_reset);
+ result = wimax_dev->op_reset(wimax_dev);
+ mutex_unlock(&wimax_dev->mutex_reset);
+ }
+ dev_put(wimax_dev->net_dev);
+
+ d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
+ return result;
+}
+EXPORT_SYMBOL(wimax_reset);
+
+
+/*
+ * Exporting to user space over generic netlink
+ *
+ * Parse the reset command from user space, return error code.
+ *
+ * No attributes.
+ */
+int wimax_gnl_doit_reset(struct sk_buff *skb, struct genl_info *info)
+{
+ int result, ifindex;
+ struct wimax_dev *wimax_dev;
+
+ d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
+ result = -ENODEV;
+ if (info->attrs[WIMAX_GNL_RESET_IFIDX] == NULL) {
+ pr_err("WIMAX_GNL_OP_RFKILL: can't find IFIDX attribute\n");
+ goto error_no_wimax_dev;
+ }
+ ifindex = nla_get_u32(info->attrs[WIMAX_GNL_RESET_IFIDX]);
+ wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
+ if (wimax_dev == NULL)
+ goto error_no_wimax_dev;
+ /* Execute the operation and send the result back to user space */
+ result = wimax_reset(wimax_dev);
+ dev_put(wimax_dev->net_dev);
+error_no_wimax_dev:
+ d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
+ return result;
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * RF-kill framework integration
+ *
+ * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This integrates into the Linux Kernel rfkill susbystem so that the
+ * drivers just have to do the bare minimal work, which is providing a
+ * method to set the software RF-Kill switch and to report changes in
+ * the software and hardware switch status.
+ *
+ * A non-polled generic rfkill device is embedded into the WiMAX
+ * subsystem's representation of a device.
+ *
+ * FIXME: Need polled support? Let drivers provide a poll routine
+ * and hand it to rfkill ops then?
+ *
+ * All device drivers have to do is after wimax_dev_init(), call
+ * wimax_report_rfkill_hw() and wimax_report_rfkill_sw() to update
+ * initial state and then every time it changes. See wimax.h:struct
+ * wimax_dev for more information.
+ *
+ * ROADMAP
+ *
+ * wimax_gnl_doit_rfkill() User space calling wimax_rfkill()
+ * wimax_rfkill() Kernel calling wimax_rfkill()
+ * __wimax_rf_toggle_radio()
+ *
+ * wimax_rfkill_set_radio_block() RF-Kill subsystem calling
+ * __wimax_rf_toggle_radio()
+ *
+ * __wimax_rf_toggle_radio()
+ * wimax_dev->op_rfkill_sw_toggle() Driver backend
+ * __wimax_state_change()
+ *
+ * wimax_report_rfkill_sw() Driver reports state change
+ * __wimax_state_change()
+ *
+ * wimax_report_rfkill_hw() Driver reports state change
+ * __wimax_state_change()
+ *
+ * wimax_rfkill_add() Initialize/shutdown rfkill support
+ * wimax_rfkill_rm() [called by wimax_dev_add/rm()]
+ */
+
+#include "net-wimax.h"
+#include <net/genetlink.h>
+#include "linux-wimax.h"
+#include <linux/security.h>
+#include <linux/rfkill.h>
+#include <linux/export.h>
+#include "wimax-internal.h"
+
+#define D_SUBMODULE op_rfkill
+#include "debug-levels.h"
+
+/**
+ * wimax_report_rfkill_hw - Reports changes in the hardware RF switch
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * @state: New state of the RF Kill switch. %WIMAX_RF_ON radio on,
+ * %WIMAX_RF_OFF radio off.
+ *
+ * When the device detects a change in the state of thehardware RF
+ * switch, it must call this function to let the WiMAX kernel stack
+ * know that the state has changed so it can be properly propagated.
+ *
+ * The WiMAX stack caches the state (the driver doesn't need to). As
+ * well, as the change is propagated it will come back as a request to
+ * change the software state to mirror the hardware state.
+ *
+ * If the device doesn't have a hardware kill switch, just report
+ * it on initialization as always on (%WIMAX_RF_ON, radio on).
+ */
+void wimax_report_rfkill_hw(struct wimax_dev *wimax_dev,
+ enum wimax_rf_state state)
+{
+ int result;
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+ enum wimax_st wimax_state;
+
+ d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
+ BUG_ON(state == WIMAX_RF_QUERY);
+ BUG_ON(state != WIMAX_RF_ON && state != WIMAX_RF_OFF);
+
+ mutex_lock(&wimax_dev->mutex);
+ result = wimax_dev_is_ready(wimax_dev);
+ if (result < 0)
+ goto error_not_ready;
+
+ if (state != wimax_dev->rf_hw) {
+ wimax_dev->rf_hw = state;
+ if (wimax_dev->rf_hw == WIMAX_RF_ON &&
+ wimax_dev->rf_sw == WIMAX_RF_ON)
+ wimax_state = WIMAX_ST_READY;
+ else
+ wimax_state = WIMAX_ST_RADIO_OFF;
+
+ result = rfkill_set_hw_state(wimax_dev->rfkill,
+ state == WIMAX_RF_OFF);
+
+ __wimax_state_change(wimax_dev, wimax_state);
+ }
+error_not_ready:
+ mutex_unlock(&wimax_dev->mutex);
+ d_fnend(3, dev, "(wimax_dev %p state %u) = void [%d]\n",
+ wimax_dev, state, result);
+}
+EXPORT_SYMBOL_GPL(wimax_report_rfkill_hw);
+
+
+/**
+ * wimax_report_rfkill_sw - Reports changes in the software RF switch
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * @state: New state of the RF kill switch. %WIMAX_RF_ON radio on,
+ * %WIMAX_RF_OFF radio off.
+ *
+ * Reports changes in the software RF switch state to the WiMAX stack.
+ *
+ * The main use is during initialization, so the driver can query the
+ * device for its current software radio kill switch state and feed it
+ * to the system.
+ *
+ * On the side, the device does not change the software state by
+ * itself. In practice, this can happen, as the device might decide to
+ * switch (in software) the radio off for different reasons.
+ */
+void wimax_report_rfkill_sw(struct wimax_dev *wimax_dev,
+ enum wimax_rf_state state)
+{
+ int result;
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+ enum wimax_st wimax_state;
+
+ d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
+ BUG_ON(state == WIMAX_RF_QUERY);
+ BUG_ON(state != WIMAX_RF_ON && state != WIMAX_RF_OFF);
+
+ mutex_lock(&wimax_dev->mutex);
+ result = wimax_dev_is_ready(wimax_dev);
+ if (result < 0)
+ goto error_not_ready;
+
+ if (state != wimax_dev->rf_sw) {
+ wimax_dev->rf_sw = state;
+ if (wimax_dev->rf_hw == WIMAX_RF_ON &&
+ wimax_dev->rf_sw == WIMAX_RF_ON)
+ wimax_state = WIMAX_ST_READY;
+ else
+ wimax_state = WIMAX_ST_RADIO_OFF;
+ __wimax_state_change(wimax_dev, wimax_state);
+ rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF);
+ }
+error_not_ready:
+ mutex_unlock(&wimax_dev->mutex);
+ d_fnend(3, dev, "(wimax_dev %p state %u) = void [%d]\n",
+ wimax_dev, state, result);
+}
+EXPORT_SYMBOL_GPL(wimax_report_rfkill_sw);
+
+
+/*
+ * Callback for the RF Kill toggle operation
+ *
+ * This function is called by:
+ *
+ * - The rfkill subsystem when the RF-Kill key is pressed in the
+ * hardware and the driver notifies through
+ * wimax_report_rfkill_hw(). The rfkill subsystem ends up calling back
+ * here so the software RF Kill switch state is changed to reflect
+ * the hardware switch state.
+ *
+ * - When the user sets the state through sysfs' rfkill/state file
+ *
+ * - When the user calls wimax_rfkill().
+ *
+ * This call blocks!
+ *
+ * WARNING! When we call rfkill_unregister(), this will be called with
+ * state 0!
+ *
+ * WARNING: wimax_dev must be locked
+ */
+static
+int __wimax_rf_toggle_radio(struct wimax_dev *wimax_dev,
+ enum wimax_rf_state state)
+{
+ int result = 0;
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+ enum wimax_st wimax_state;
+
+ might_sleep();
+ d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
+ if (wimax_dev->rf_sw == state)
+ goto out_no_change;
+ if (wimax_dev->op_rfkill_sw_toggle != NULL)
+ result = wimax_dev->op_rfkill_sw_toggle(wimax_dev, state);
+ else if (state == WIMAX_RF_OFF) /* No op? can't turn off */
+ result = -ENXIO;
+ else /* No op? can turn on */
+ result = 0; /* should never happen tho */
+ if (result >= 0) {
+ result = 0;
+ wimax_dev->rf_sw = state;
+ wimax_state = state == WIMAX_RF_ON ?
+ WIMAX_ST_READY : WIMAX_ST_RADIO_OFF;
+ __wimax_state_change(wimax_dev, wimax_state);
+ }
+out_no_change:
+ d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n",
+ wimax_dev, state, result);
+ return result;
+}
+
+
+/*
+ * Translate from rfkill state to wimax state
+ *
+ * NOTE: Special state handling rules here
+ *
+ * Just pretend the call didn't happen if we are in a state where
+ * we know for sure it cannot be handled (WIMAX_ST_DOWN or
+ * __WIMAX_ST_QUIESCING). rfkill() needs it to register and
+ * unregister, as it will run this path.
+ *
+ * NOTE: This call will block until the operation is completed.
+ */
+static int wimax_rfkill_set_radio_block(void *data, bool blocked)
+{
+ int result;
+ struct wimax_dev *wimax_dev = data;
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+ enum wimax_rf_state rf_state;
+
+ d_fnstart(3, dev, "(wimax_dev %p blocked %u)\n", wimax_dev, blocked);
+ rf_state = WIMAX_RF_ON;
+ if (blocked)
+ rf_state = WIMAX_RF_OFF;
+ mutex_lock(&wimax_dev->mutex);
+ if (wimax_dev->state <= __WIMAX_ST_QUIESCING)
+ result = 0;
+ else
+ result = __wimax_rf_toggle_radio(wimax_dev, rf_state);
+ mutex_unlock(&wimax_dev->mutex);
+ d_fnend(3, dev, "(wimax_dev %p blocked %u) = %d\n",
+ wimax_dev, blocked, result);
+ return result;
+}
+
+static const struct rfkill_ops wimax_rfkill_ops = {
+ .set_block = wimax_rfkill_set_radio_block,
+};
+
+/**
+ * wimax_rfkill - Set the software RF switch state for a WiMAX device
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * @state: New RF state.
+ *
+ * Returns:
+ *
+ * >= 0 toggle state if ok, < 0 errno code on error. The toggle state
+ * is returned as a bitmap, bit 0 being the hardware RF state, bit 1
+ * the software RF state.
+ *
+ * 0 means disabled (%WIMAX_RF_ON, radio on), 1 means enabled radio
+ * off (%WIMAX_RF_OFF).
+ *
+ * Description:
+ *
+ * Called by the user when he wants to request the WiMAX radio to be
+ * switched on (%WIMAX_RF_ON) or off (%WIMAX_RF_OFF). With
+ * %WIMAX_RF_QUERY, just the current state is returned.
+ *
+ * NOTE:
+ *
+ * This call will block until the operation is complete.
+ */
+int wimax_rfkill(struct wimax_dev *wimax_dev, enum wimax_rf_state state)
+{
+ int result;
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+
+ d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
+ mutex_lock(&wimax_dev->mutex);
+ result = wimax_dev_is_ready(wimax_dev);
+ if (result < 0) {
+ /* While initializing, < 1.4.3 wimax-tools versions use
+ * this call to check if the device is a valid WiMAX
+ * device; so we allow it to proceed always,
+ * considering the radios are all off. */
+ if (result == -ENOMEDIUM && state == WIMAX_RF_QUERY)
+ result = WIMAX_RF_OFF << 1 | WIMAX_RF_OFF;
+ goto error_not_ready;
+ }
+ switch (state) {
+ case WIMAX_RF_ON:
+ case WIMAX_RF_OFF:
+ result = __wimax_rf_toggle_radio(wimax_dev, state);
+ if (result < 0)
+ goto error;
+ rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF);
+ break;
+ case WIMAX_RF_QUERY:
+ break;
+ default:
+ result = -EINVAL;
+ goto error;
+ }
+ result = wimax_dev->rf_sw << 1 | wimax_dev->rf_hw;
+error:
+error_not_ready:
+ mutex_unlock(&wimax_dev->mutex);
+ d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n",
+ wimax_dev, state, result);
+ return result;
+}
+EXPORT_SYMBOL(wimax_rfkill);
+
+
+/*
+ * Register a new WiMAX device's RF Kill support
+ *
+ * WARNING: wimax_dev->mutex must be unlocked
+ */
+int wimax_rfkill_add(struct wimax_dev *wimax_dev)
+{
+ int result;
+ struct rfkill *rfkill;
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+
+ d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
+ /* Initialize RF Kill */
+ result = -ENOMEM;
+ rfkill = rfkill_alloc(wimax_dev->name, dev, RFKILL_TYPE_WIMAX,
+ &wimax_rfkill_ops, wimax_dev);
+ if (rfkill == NULL)
+ goto error_rfkill_allocate;
+
+ d_printf(1, dev, "rfkill %p\n", rfkill);
+
+ wimax_dev->rfkill = rfkill;
+
+ rfkill_init_sw_state(rfkill, 1);
+ result = rfkill_register(wimax_dev->rfkill);
+ if (result < 0)
+ goto error_rfkill_register;
+
+ /* If there is no SW toggle op, SW RFKill is always on */
+ if (wimax_dev->op_rfkill_sw_toggle == NULL)
+ wimax_dev->rf_sw = WIMAX_RF_ON;
+
+ d_fnend(3, dev, "(wimax_dev %p) = 0\n", wimax_dev);
+ return 0;
+
+error_rfkill_register:
+ rfkill_destroy(wimax_dev->rfkill);
+error_rfkill_allocate:
+ d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
+ return result;
+}
+
+
+/*
+ * Deregister a WiMAX device's RF Kill support
+ *
+ * Ick, we can't call rfkill_free() after rfkill_unregister()...oh
+ * well.
+ *
+ * WARNING: wimax_dev->mutex must be unlocked
+ */
+void wimax_rfkill_rm(struct wimax_dev *wimax_dev)
+{
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+ d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
+ rfkill_unregister(wimax_dev->rfkill);
+ rfkill_destroy(wimax_dev->rfkill);
+ d_fnend(3, dev, "(wimax_dev %p)\n", wimax_dev);
+}
+
+
+/*
+ * Exporting to user space over generic netlink
+ *
+ * Parse the rfkill command from user space, return a combination
+ * value that describe the states of the different toggles.
+ *
+ * Only one attribute: the new state requested (on, off or no change,
+ * just query).
+ */
+
+int wimax_gnl_doit_rfkill(struct sk_buff *skb, struct genl_info *info)
+{
+ int result, ifindex;
+ struct wimax_dev *wimax_dev;
+ struct device *dev;
+ enum wimax_rf_state new_state;
+
+ d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
+ result = -ENODEV;
+ if (info->attrs[WIMAX_GNL_RFKILL_IFIDX] == NULL) {
+ pr_err("WIMAX_GNL_OP_RFKILL: can't find IFIDX attribute\n");
+ goto error_no_wimax_dev;
+ }
+ ifindex = nla_get_u32(info->attrs[WIMAX_GNL_RFKILL_IFIDX]);
+ wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
+ if (wimax_dev == NULL)
+ goto error_no_wimax_dev;
+ dev = wimax_dev_to_dev(wimax_dev);
+ result = -EINVAL;
+ if (info->attrs[WIMAX_GNL_RFKILL_STATE] == NULL) {
+ dev_err(dev, "WIMAX_GNL_RFKILL: can't find RFKILL_STATE "
+ "attribute\n");
+ goto error_no_pid;
+ }
+ new_state = nla_get_u32(info->attrs[WIMAX_GNL_RFKILL_STATE]);
+
+ /* Execute the operation and send the result back to user space */
+ result = wimax_rfkill(wimax_dev, new_state);
+error_no_pid:
+ dev_put(wimax_dev->net_dev);
+error_no_wimax_dev:
+ d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
+ return result;
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * Implement and export a method for getting a WiMAX device current state
+ *
+ * Copyright (C) 2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
+ *
+ * Based on previous WiMAX core work by:
+ * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+
+#include "net-wimax.h"
+#include <net/genetlink.h>
+#include "linux-wimax.h"
+#include <linux/security.h>
+#include "wimax-internal.h"
+
+#define D_SUBMODULE op_state_get
+#include "debug-levels.h"
+
+
+/*
+ * Exporting to user space over generic netlink
+ *
+ * Parse the state get command from user space, return a combination
+ * value that describe the current state.
+ *
+ * No attributes.
+ */
+int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info)
+{
+ int result, ifindex;
+ struct wimax_dev *wimax_dev;
+
+ d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
+ result = -ENODEV;
+ if (info->attrs[WIMAX_GNL_STGET_IFIDX] == NULL) {
+ pr_err("WIMAX_GNL_OP_STATE_GET: can't find IFIDX attribute\n");
+ goto error_no_wimax_dev;
+ }
+ ifindex = nla_get_u32(info->attrs[WIMAX_GNL_STGET_IFIDX]);
+ wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
+ if (wimax_dev == NULL)
+ goto error_no_wimax_dev;
+ /* Execute the operation and send the result back to user space */
+ result = wimax_state_get(wimax_dev);
+ dev_put(wimax_dev->net_dev);
+error_no_wimax_dev:
+ d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
+ return result;
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * Initialization, addition and removal of wimax devices
+ *
+ * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This implements:
+ *
+ * - basic life cycle of 'struct wimax_dev' [wimax_dev_*()]; on
+ * addition/registration initialize all subfields and allocate
+ * generic netlink resources for user space communication. On
+ * removal/unregistration, undo all that.
+ *
+ * - device state machine [wimax_state_change()] and support to send
+ * reports to user space when the state changes
+ * [wimax_gnl_re_state_change*()].
+ *
+ * See include/net/wimax.h for rationales and design.
+ *
+ * ROADMAP
+ *
+ * [__]wimax_state_change() Called by drivers to update device's state
+ * wimax_gnl_re_state_change_alloc()
+ * wimax_gnl_re_state_change_send()
+ *
+ * wimax_dev_init() Init a device
+ * wimax_dev_add() Register
+ * wimax_rfkill_add()
+ * wimax_gnl_add() Register all the generic netlink resources.
+ * wimax_id_table_add()
+ * wimax_dev_rm() Unregister
+ * wimax_id_table_rm()
+ * wimax_gnl_rm()
+ * wimax_rfkill_rm()
+ */
+#include <linux/device.h>
+#include <linux/gfp.h>
+#include <net/genetlink.h>
+#include <linux/netdevice.h>
+#include "linux-wimax.h"
+#include <linux/module.h>
+#include "wimax-internal.h"
+
+
+#define D_SUBMODULE stack
+#include "debug-levels.h"
+
+static char wimax_debug_params[128];
+module_param_string(debug, wimax_debug_params, sizeof(wimax_debug_params),
+ 0644);
+MODULE_PARM_DESC(debug,
+ "String of space-separated NAME:VALUE pairs, where NAMEs "
+ "are the different debug submodules and VALUE are the "
+ "initial debug value to set.");
+
+/*
+ * Authoritative source for the RE_STATE_CHANGE attribute policy
+ *
+ * We don't really use it here, but /me likes to keep the definition
+ * close to where the data is generated.
+ */
+/*
+static const struct nla_policy wimax_gnl_re_status_change[WIMAX_GNL_ATTR_MAX + 1] = {
+ [WIMAX_GNL_STCH_STATE_OLD] = { .type = NLA_U8 },
+ [WIMAX_GNL_STCH_STATE_NEW] = { .type = NLA_U8 },
+};
+*/
+
+
+/*
+ * Allocate a Report State Change message
+ *
+ * @header: save it, you need it for _send()
+ *
+ * Creates and fills a basic state change message; different code
+ * paths can then add more attributes to the message as needed.
+ *
+ * Use wimax_gnl_re_state_change_send() to send the returned skb.
+ *
+ * Returns: skb with the genl message if ok, IS_ERR() ptr on error
+ * with an errno code.
+ */
+static
+struct sk_buff *wimax_gnl_re_state_change_alloc(
+ struct wimax_dev *wimax_dev,
+ enum wimax_st new_state, enum wimax_st old_state,
+ void **header)
+{
+ int result;
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+ void *data;
+ struct sk_buff *report_skb;
+
+ d_fnstart(3, dev, "(wimax_dev %p new_state %u old_state %u)\n",
+ wimax_dev, new_state, old_state);
+ result = -ENOMEM;
+ report_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (report_skb == NULL) {
+ dev_err(dev, "RE_STCH: can't create message\n");
+ goto error_new;
+ }
+ /* FIXME: sending a group ID as the seq is wrong */
+ data = genlmsg_put(report_skb, 0, wimax_gnl_family.mcgrp_offset,
+ &wimax_gnl_family, 0, WIMAX_GNL_RE_STATE_CHANGE);
+ if (data == NULL) {
+ dev_err(dev, "RE_STCH: can't put data into message\n");
+ goto error_put;
+ }
+ *header = data;
+
+ result = nla_put_u8(report_skb, WIMAX_GNL_STCH_STATE_OLD, old_state);
+ if (result < 0) {
+ dev_err(dev, "RE_STCH: Error adding OLD attr: %d\n", result);
+ goto error_put;
+ }
+ result = nla_put_u8(report_skb, WIMAX_GNL_STCH_STATE_NEW, new_state);
+ if (result < 0) {
+ dev_err(dev, "RE_STCH: Error adding NEW attr: %d\n", result);
+ goto error_put;
+ }
+ result = nla_put_u32(report_skb, WIMAX_GNL_STCH_IFIDX,
+ wimax_dev->net_dev->ifindex);
+ if (result < 0) {
+ dev_err(dev, "RE_STCH: Error adding IFINDEX attribute\n");
+ goto error_put;
+ }
+ d_fnend(3, dev, "(wimax_dev %p new_state %u old_state %u) = %p\n",
+ wimax_dev, new_state, old_state, report_skb);
+ return report_skb;
+
+error_put:
+ nlmsg_free(report_skb);
+error_new:
+ d_fnend(3, dev, "(wimax_dev %p new_state %u old_state %u) = %d\n",
+ wimax_dev, new_state, old_state, result);
+ return ERR_PTR(result);
+}
+
+
+/*
+ * Send a Report State Change message (as created with _alloc).
+ *
+ * @report_skb: as returned by wimax_gnl_re_state_change_alloc()
+ * @header: as returned by wimax_gnl_re_state_change_alloc()
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * If the message is NULL, pretend it didn't happen.
+ */
+static
+int wimax_gnl_re_state_change_send(
+ struct wimax_dev *wimax_dev, struct sk_buff *report_skb,
+ void *header)
+{
+ int result = 0;
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+ d_fnstart(3, dev, "(wimax_dev %p report_skb %p)\n",
+ wimax_dev, report_skb);
+ if (report_skb == NULL) {
+ result = -ENOMEM;
+ goto out;
+ }
+ genlmsg_end(report_skb, header);
+ genlmsg_multicast(&wimax_gnl_family, report_skb, 0, 0, GFP_KERNEL);
+out:
+ d_fnend(3, dev, "(wimax_dev %p report_skb %p) = %d\n",
+ wimax_dev, report_skb, result);
+ return result;
+}
+
+
+static
+void __check_new_state(enum wimax_st old_state, enum wimax_st new_state,
+ unsigned int allowed_states_bm)
+{
+ if (WARN_ON(((1 << new_state) & allowed_states_bm) == 0)) {
+ pr_err("SW BUG! Forbidden state change %u -> %u\n",
+ old_state, new_state);
+ }
+}
+
+
+/*
+ * Set the current state of a WiMAX device [unlocking version of
+ * wimax_state_change().
+ */
+void __wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
+{
+ struct device *dev = wimax_dev_to_dev(wimax_dev);
+ enum wimax_st old_state = wimax_dev->state;
+ struct sk_buff *stch_skb;
+ void *header;
+
+ d_fnstart(3, dev, "(wimax_dev %p new_state %u [old %u])\n",
+ wimax_dev, new_state, old_state);
+
+ if (WARN_ON(new_state >= __WIMAX_ST_INVALID)) {
+ dev_err(dev, "SW BUG: requesting invalid state %u\n",
+ new_state);
+ goto out;
+ }
+ if (old_state == new_state)
+ goto out;
+ header = NULL; /* gcc complains? can't grok why */
+ stch_skb = wimax_gnl_re_state_change_alloc(
+ wimax_dev, new_state, old_state, &header);
+
+ /* Verify the state transition and do exit-from-state actions */
+ switch (old_state) {
+ case __WIMAX_ST_NULL:
+ __check_new_state(old_state, new_state,
+ 1 << WIMAX_ST_DOWN);
+ break;
+ case WIMAX_ST_DOWN:
+ __check_new_state(old_state, new_state,
+ 1 << __WIMAX_ST_QUIESCING
+ | 1 << WIMAX_ST_UNINITIALIZED
+ | 1 << WIMAX_ST_RADIO_OFF);
+ break;
+ case __WIMAX_ST_QUIESCING:
+ __check_new_state(old_state, new_state, 1 << WIMAX_ST_DOWN);
+ break;
+ case WIMAX_ST_UNINITIALIZED:
+ __check_new_state(old_state, new_state,
+ 1 << __WIMAX_ST_QUIESCING
+ | 1 << WIMAX_ST_RADIO_OFF);
+ break;
+ case WIMAX_ST_RADIO_OFF:
+ __check_new_state(old_state, new_state,
+ 1 << __WIMAX_ST_QUIESCING
+ | 1 << WIMAX_ST_READY);
+ break;
+ case WIMAX_ST_READY:
+ __check_new_state(old_state, new_state,
+ 1 << __WIMAX_ST_QUIESCING
+ | 1 << WIMAX_ST_RADIO_OFF
+ | 1 << WIMAX_ST_SCANNING
+ | 1 << WIMAX_ST_CONNECTING
+ | 1 << WIMAX_ST_CONNECTED);
+ break;
+ case WIMAX_ST_SCANNING:
+ __check_new_state(old_state, new_state,
+ 1 << __WIMAX_ST_QUIESCING
+ | 1 << WIMAX_ST_RADIO_OFF
+ | 1 << WIMAX_ST_READY
+ | 1 << WIMAX_ST_CONNECTING
+ | 1 << WIMAX_ST_CONNECTED);
+ break;
+ case WIMAX_ST_CONNECTING:
+ __check_new_state(old_state, new_state,
+ 1 << __WIMAX_ST_QUIESCING
+ | 1 << WIMAX_ST_RADIO_OFF
+ | 1 << WIMAX_ST_READY
+ | 1 << WIMAX_ST_SCANNING
+ | 1 << WIMAX_ST_CONNECTED);
+ break;
+ case WIMAX_ST_CONNECTED:
+ __check_new_state(old_state, new_state,
+ 1 << __WIMAX_ST_QUIESCING
+ | 1 << WIMAX_ST_RADIO_OFF
+ | 1 << WIMAX_ST_READY);
+ netif_tx_disable(wimax_dev->net_dev);
+ netif_carrier_off(wimax_dev->net_dev);
+ break;
+ case __WIMAX_ST_INVALID:
+ default:
+ dev_err(dev, "SW BUG: wimax_dev %p is in unknown state %u\n",
+ wimax_dev, wimax_dev->state);
+ WARN_ON(1);
+ goto out;
+ }
+
+ /* Execute the actions of entry to the new state */
+ switch (new_state) {
+ case __WIMAX_ST_NULL:
+ dev_err(dev, "SW BUG: wimax_dev %p entering NULL state "
+ "from %u\n", wimax_dev, wimax_dev->state);
+ WARN_ON(1); /* Nobody can enter this state */
+ break;
+ case WIMAX_ST_DOWN:
+ break;
+ case __WIMAX_ST_QUIESCING:
+ break;
+ case WIMAX_ST_UNINITIALIZED:
+ break;
+ case WIMAX_ST_RADIO_OFF:
+ break;
+ case WIMAX_ST_READY:
+ break;
+ case WIMAX_ST_SCANNING:
+ break;
+ case WIMAX_ST_CONNECTING:
+ break;
+ case WIMAX_ST_CONNECTED:
+ netif_carrier_on(wimax_dev->net_dev);
+ netif_wake_queue(wimax_dev->net_dev);
+ break;
+ case __WIMAX_ST_INVALID:
+ default:
+ BUG();
+ }
+ __wimax_state_set(wimax_dev, new_state);
+ if (!IS_ERR(stch_skb))
+ wimax_gnl_re_state_change_send(wimax_dev, stch_skb, header);
+out:
+ d_fnend(3, dev, "(wimax_dev %p new_state %u [old %u]) = void\n",
+ wimax_dev, new_state, old_state);
+}
+
+
+/**
+ * wimax_state_change - Set the current state of a WiMAX device
+ *
+ * @wimax_dev: WiMAX device descriptor (properly referenced)
+ * @new_state: New state to switch to
+ *
+ * This implements the state changes for the wimax devices. It will
+ *
+ * - verify that the state transition is legal (for now it'll just
+ * print a warning if not) according to the table in
+ * linux/wimax.h's documentation for 'enum wimax_st'.
+ *
+ * - perform the actions needed for leaving the current state and
+ * whichever are needed for entering the new state.
+ *
+ * - issue a report to user space indicating the new state (and an
+ * optional payload with information about the new state).
+ *
+ * NOTE: @wimax_dev must be locked
+ */
+void wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
+{
+ /*
+ * A driver cannot take the wimax_dev out of the
+ * __WIMAX_ST_NULL state unless by calling wimax_dev_add(). If
+ * the wimax_dev's state is still NULL, we ignore any request
+ * to change its state because it means it hasn't been yet
+ * registered.
+ *
+ * There is no need to complain about it, as routines that
+ * call this might be shared from different code paths that
+ * are called before or after wimax_dev_add() has done its
+ * job.
+ */
+ mutex_lock(&wimax_dev->mutex);
+ if (wimax_dev->state > __WIMAX_ST_NULL)
+ __wimax_state_change(wimax_dev, new_state);
+ mutex_unlock(&wimax_dev->mutex);
+}
+EXPORT_SYMBOL_GPL(wimax_state_change);
+
+
+/**
+ * wimax_state_get() - Return the current state of a WiMAX device
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * Returns: Current state of the device according to its driver.
+ */
+enum wimax_st wimax_state_get(struct wimax_dev *wimax_dev)
+{
+ enum wimax_st state;
+ mutex_lock(&wimax_dev->mutex);
+ state = wimax_dev->state;
+ mutex_unlock(&wimax_dev->mutex);
+ return state;
+}
+EXPORT_SYMBOL_GPL(wimax_state_get);
+
+
+/**
+ * wimax_dev_init - initialize a newly allocated instance
+ *
+ * @wimax_dev: WiMAX device descriptor to initialize.
+ *
+ * Initializes fields of a freshly allocated @wimax_dev instance. This
+ * function assumes that after allocation, the memory occupied by
+ * @wimax_dev was zeroed.
+ */
+void wimax_dev_init(struct wimax_dev *wimax_dev)
+{
+ INIT_LIST_HEAD(&wimax_dev->id_table_node);
+ __wimax_state_set(wimax_dev, __WIMAX_ST_NULL);
+ mutex_init(&wimax_dev->mutex);
+ mutex_init(&wimax_dev->mutex_reset);
+}
+EXPORT_SYMBOL_GPL(wimax_dev_init);
+
+/*
+ * There are multiple enums reusing the same values, adding
+ * others is only possible if they use a compatible policy.
+ */
+static const struct nla_policy wimax_gnl_policy[WIMAX_GNL_ATTR_MAX + 1] = {
+ /*
+ * WIMAX_GNL_RESET_IFIDX, WIMAX_GNL_RFKILL_IFIDX,
+ * WIMAX_GNL_STGET_IFIDX, WIMAX_GNL_MSG_IFIDX
+ */
+ [1] = { .type = NLA_U32, },
+ /*
+ * WIMAX_GNL_RFKILL_STATE, WIMAX_GNL_MSG_PIPE_NAME
+ */
+ [2] = { .type = NLA_U32, }, /* enum wimax_rf_state */
+ /*
+ * WIMAX_GNL_MSG_DATA
+ */
+ [3] = { .type = NLA_UNSPEC, }, /* libnl doesn't grok BINARY yet */
+};
+
+static const struct genl_small_ops wimax_gnl_ops[] = {
+ {
+ .cmd = WIMAX_GNL_OP_MSG_FROM_USER,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .flags = GENL_ADMIN_PERM,
+ .doit = wimax_gnl_doit_msg_from_user,
+ },
+ {
+ .cmd = WIMAX_GNL_OP_RESET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .flags = GENL_ADMIN_PERM,
+ .doit = wimax_gnl_doit_reset,
+ },
+ {
+ .cmd = WIMAX_GNL_OP_RFKILL,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .flags = GENL_ADMIN_PERM,
+ .doit = wimax_gnl_doit_rfkill,
+ },
+ {
+ .cmd = WIMAX_GNL_OP_STATE_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .flags = GENL_ADMIN_PERM,
+ .doit = wimax_gnl_doit_state_get,
+ },
+};
+
+
+static
+size_t wimax_addr_scnprint(char *addr_str, size_t addr_str_size,
+ unsigned char *addr, size_t addr_len)
+{
+ unsigned int cnt, total;
+
+ for (total = cnt = 0; cnt < addr_len; cnt++)
+ total += scnprintf(addr_str + total, addr_str_size - total,
+ "%02x%c", addr[cnt],
+ cnt == addr_len - 1 ? '\0' : ':');
+ return total;
+}
+
+
+/**
+ * wimax_dev_add - Register a new WiMAX device
+ *
+ * @wimax_dev: WiMAX device descriptor (as embedded in your @net_dev's
+ * priv data). You must have called wimax_dev_init() on it before.
+ *
+ * @net_dev: net device the @wimax_dev is associated with. The
+ * function expects SET_NETDEV_DEV() and register_netdev() were
+ * already called on it.
+ *
+ * Registers the new WiMAX device, sets up the user-kernel control
+ * interface (generic netlink) and common WiMAX infrastructure.
+ *
+ * Note that the parts that will allow interaction with user space are
+ * setup at the very end, when the rest is in place, as once that
+ * happens, the driver might get user space control requests via
+ * netlink or from debugfs that might translate into calls into
+ * wimax_dev->op_*().
+ */
+int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev)
+{
+ int result;
+ struct device *dev = net_dev->dev.parent;
+ char addr_str[32];
+
+ d_fnstart(3, dev, "(wimax_dev %p net_dev %p)\n", wimax_dev, net_dev);
+
+ /* Do the RFKILL setup before locking, as RFKILL will call
+ * into our functions.
+ */
+ wimax_dev->net_dev = net_dev;
+ result = wimax_rfkill_add(wimax_dev);
+ if (result < 0)
+ goto error_rfkill_add;
+
+ /* Set up user-space interaction */
+ mutex_lock(&wimax_dev->mutex);
+ wimax_id_table_add(wimax_dev);
+ wimax_debugfs_add(wimax_dev);
+
+ __wimax_state_set(wimax_dev, WIMAX_ST_DOWN);
+ mutex_unlock(&wimax_dev->mutex);
+
+ wimax_addr_scnprint(addr_str, sizeof(addr_str),
+ net_dev->dev_addr, net_dev->addr_len);
+ dev_err(dev, "WiMAX interface %s (%s) ready\n",
+ net_dev->name, addr_str);
+ d_fnend(3, dev, "(wimax_dev %p net_dev %p) = 0\n", wimax_dev, net_dev);
+ return 0;
+
+error_rfkill_add:
+ d_fnend(3, dev, "(wimax_dev %p net_dev %p) = %d\n",
+ wimax_dev, net_dev, result);
+ return result;
+}
+EXPORT_SYMBOL_GPL(wimax_dev_add);
+
+
+/**
+ * wimax_dev_rm - Unregister an existing WiMAX device
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * Unregisters a WiMAX device previously registered for use with
+ * wimax_add_rm().
+ *
+ * IMPORTANT! Must call before calling unregister_netdev().
+ *
+ * After this function returns, you will not get any more user space
+ * control requests (via netlink or debugfs) and thus to wimax_dev->ops.
+ *
+ * Reentrancy control is ensured by setting the state to
+ * %__WIMAX_ST_QUIESCING. rfkill operations coming through
+ * wimax_*rfkill*() will be stopped by the quiescing state; ops coming
+ * from the rfkill subsystem will be stopped by the support being
+ * removed by wimax_rfkill_rm().
+ */
+void wimax_dev_rm(struct wimax_dev *wimax_dev)
+{
+ d_fnstart(3, NULL, "(wimax_dev %p)\n", wimax_dev);
+
+ mutex_lock(&wimax_dev->mutex);
+ __wimax_state_change(wimax_dev, __WIMAX_ST_QUIESCING);
+ wimax_debugfs_rm(wimax_dev);
+ wimax_id_table_rm(wimax_dev);
+ __wimax_state_change(wimax_dev, WIMAX_ST_DOWN);
+ mutex_unlock(&wimax_dev->mutex);
+ wimax_rfkill_rm(wimax_dev);
+ d_fnend(3, NULL, "(wimax_dev %p) = void\n", wimax_dev);
+}
+EXPORT_SYMBOL_GPL(wimax_dev_rm);
+
+
+/* Debug framework control of debug levels */
+struct d_level D_LEVEL[] = {
+ D_SUBMODULE_DEFINE(debugfs),
+ D_SUBMODULE_DEFINE(id_table),
+ D_SUBMODULE_DEFINE(op_msg),
+ D_SUBMODULE_DEFINE(op_reset),
+ D_SUBMODULE_DEFINE(op_rfkill),
+ D_SUBMODULE_DEFINE(op_state_get),
+ D_SUBMODULE_DEFINE(stack),
+};
+size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
+
+
+static const struct genl_multicast_group wimax_gnl_mcgrps[] = {
+ { .name = "msg", },
+};
+
+struct genl_family wimax_gnl_family __ro_after_init = {
+ .name = "WiMAX",
+ .version = WIMAX_GNL_VERSION,
+ .hdrsize = 0,
+ .maxattr = WIMAX_GNL_ATTR_MAX,
+ .policy = wimax_gnl_policy,
+ .module = THIS_MODULE,
+ .small_ops = wimax_gnl_ops,
+ .n_small_ops = ARRAY_SIZE(wimax_gnl_ops),
+ .mcgrps = wimax_gnl_mcgrps,
+ .n_mcgrps = ARRAY_SIZE(wimax_gnl_mcgrps),
+};
+
+
+
+/* Shutdown the wimax stack */
+static
+int __init wimax_subsys_init(void)
+{
+ int result;
+
+ d_fnstart(4, NULL, "()\n");
+ d_parse_params(D_LEVEL, D_LEVEL_SIZE, wimax_debug_params,
+ "wimax.debug");
+
+ result = genl_register_family(&wimax_gnl_family);
+ if (unlikely(result < 0)) {
+ pr_err("cannot register generic netlink family: %d\n", result);
+ goto error_register_family;
+ }
+
+ d_fnend(4, NULL, "() = 0\n");
+ return 0;
+
+error_register_family:
+ d_fnend(4, NULL, "() = %d\n", result);
+ return result;
+
+}
+module_init(wimax_subsys_init);
+
+
+/* Shutdown the wimax stack */
+static
+void __exit wimax_subsys_exit(void)
+{
+ wimax_id_table_release();
+ genl_unregister_family(&wimax_gnl_family);
+}
+module_exit(wimax_subsys_exit);
+
+MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
+MODULE_DESCRIPTION("Linux WiMAX stack");
+MODULE_LICENSE("GPL");
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Linux WiMAX
+ * Internal API for kernel space WiMAX stack
+ *
+ * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This header file is for declarations and definitions internal to
+ * the WiMAX stack. For public APIs and documentation, see
+ * include/net/wimax.h and include/linux/wimax.h.
+ */
+
+#ifndef __WIMAX_INTERNAL_H__
+#define __WIMAX_INTERNAL_H__
+#ifdef __KERNEL__
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/device.h>
+#include "net-wimax.h"
+
+
+/*
+ * Decide if a (locked) device is ready for use
+ *
+ * Before using the device structure, it must be locked
+ * (wimax_dev->mutex). As well, most operations need to call this
+ * function to check if the state is the right one.
+ *
+ * An error value will be returned if the state is not the right
+ * one. In that case, the caller should not attempt to use the device
+ * and just unlock it.
+ */
+static inline __must_check
+int wimax_dev_is_ready(struct wimax_dev *wimax_dev)
+{
+ if (wimax_dev->state == __WIMAX_ST_NULL)
+ return -EINVAL; /* Device is not even registered! */
+ if (wimax_dev->state == WIMAX_ST_DOWN)
+ return -ENOMEDIUM;
+ if (wimax_dev->state == __WIMAX_ST_QUIESCING)
+ return -ESHUTDOWN;
+ return 0;
+}
+
+
+static inline
+void __wimax_state_set(struct wimax_dev *wimax_dev, enum wimax_st state)
+{
+ wimax_dev->state = state;
+}
+void __wimax_state_change(struct wimax_dev *, enum wimax_st);
+
+#ifdef CONFIG_DEBUG_FS
+void wimax_debugfs_add(struct wimax_dev *);
+void wimax_debugfs_rm(struct wimax_dev *);
+#else
+static inline void wimax_debugfs_add(struct wimax_dev *wimax_dev) {}
+static inline void wimax_debugfs_rm(struct wimax_dev *wimax_dev) {}
+#endif
+
+void wimax_id_table_add(struct wimax_dev *);
+struct wimax_dev *wimax_dev_get_by_genl_info(struct genl_info *, int);
+void wimax_id_table_rm(struct wimax_dev *);
+void wimax_id_table_release(void);
+
+int wimax_rfkill_add(struct wimax_dev *);
+void wimax_rfkill_rm(struct wimax_dev *);
+
+/* generic netlink */
+extern struct genl_family wimax_gnl_family;
+
+/* ops */
+int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info);
+int wimax_gnl_doit_reset(struct sk_buff *skb, struct genl_info *info);
+int wimax_gnl_doit_rfkill(struct sk_buff *skb, struct genl_info *info);
+int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info);
+
+#endif /* #ifdef __KERNEL__ */
+#endif /* #ifndef __WIMAX_INTERNAL_H__ */
#define IMX_SC_R_CAN_0 105
#define IMX_SC_R_CAN_1 106
#define IMX_SC_R_CAN_2 107
+#define IMX_SC_R_CAN(x) (IMX_SC_R_CAN_0 + (x))
#define IMX_SC_R_DMA_1_CH0 108
#define IMX_SC_R_DMA_1_CH1 109
#define IMX_SC_R_DMA_1_CH2 110
u8 ticket[]; /* the encrypted ticket */
};
-/*
- * Kerberos 5 principal
- * name/name/name@realm
- */
-struct krb5_principal {
- u8 n_name_parts; /* N of parts of the name part of the principal */
- char **name_parts; /* parts of the name part of the principal */
- char *realm; /* parts of the realm part of the principal */
-};
-
-/*
- * Kerberos 5 tagged data
- */
-struct krb5_tagged_data {
- /* for tag value, see /usr/include/krb5/krb5.h
- * - KRB5_AUTHDATA_* for auth data
- * -
- */
- s32 tag;
- u32 data_len;
- u8 *data;
-};
-
-/*
- * RxRPC key for Kerberos V (type-5 security)
- */
-struct rxk5_key {
- u64 authtime; /* time at which auth token generated */
- u64 starttime; /* time at which auth token starts */
- u64 endtime; /* time at which auth token expired */
- u64 renew_till; /* time to which auth token can be renewed */
- s32 is_skey; /* T if ticket is encrypted in another ticket's
- * skey */
- s32 flags; /* mask of TKT_FLG_* bits (krb5/krb5.h) */
- struct krb5_principal client; /* client principal name */
- struct krb5_principal server; /* server principal name */
- u16 ticket_len; /* length of ticket */
- u16 ticket2_len; /* length of second ticket */
- u8 n_authdata; /* number of authorisation data elements */
- u8 n_addresses; /* number of addresses */
- struct krb5_tagged_data session; /* session data; tag is enctype */
- struct krb5_tagged_data *addresses; /* addresses */
- u8 *ticket; /* krb5 ticket */
- u8 *ticket2; /* second krb5 ticket, if related to ticket (via
- * DUPLICATE-SKEY or ENC-TKT-IN-SKEY) */
- struct krb5_tagged_data *authdata; /* authorisation data */
-};
-
/*
* list of tokens attached to an rxrpc key
*/
struct rxrpc_key_token {
u16 security_index; /* RxRPC header security index */
+ bool no_leak_key; /* Don't copy the key to userspace */
struct rxrpc_key_token *next; /* the next token in the list */
union {
struct rxkad_key *kad;
- struct rxk5_key *k5;
};
};
#define AFSTOKEN_RK_TIX_MAX 12000 /* max RxKAD ticket size */
#define AFSTOKEN_GK_KEY_MAX 64 /* max GSSAPI key size */
#define AFSTOKEN_GK_TOKEN_MAX 16384 /* max GSSAPI token size */
-#define AFSTOKEN_K5_COMPONENTS_MAX 16 /* max K5 components */
-#define AFSTOKEN_K5_NAME_MAX 128 /* max K5 name length */
-#define AFSTOKEN_K5_REALM_MAX 64 /* max K5 realm name length */
-#define AFSTOKEN_K5_TIX_MAX 16384 /* max K5 ticket size */
-#define AFSTOKEN_K5_ADDRESSES_MAX 16 /* max K5 addresses */
-#define AFSTOKEN_K5_AUTHDATA_MAX 16 /* max K5 pieces of auth data */
/*
* Truncate a time64_t to the range from 1970 to 2106 as in the network
void __user *arg);
#endif
int (*send)(struct atm_vcc *vcc,struct sk_buff *skb);
+ int (*send_bh)(struct atm_vcc *vcc, struct sk_buff *skb);
int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags);
void (*phy_put)(struct atm_dev *dev,unsigned char value,
unsigned long addr);
struct bpf_iter_aux_info;
struct bpf_local_storage;
struct bpf_local_storage_map;
+struct kobject;
extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
+extern struct kobject *btf_kobj;
typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
struct bpf_iter_aux_info *aux);
RET_PTR_TO_BTF_ID_OR_NULL, /* returns a pointer to a btf_id or NULL */
RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */
RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */
+ RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */
};
/* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux,
struct bpf_link_info *info);
+enum bpf_iter_feature {
+ BPF_ITER_RESCHED = BIT(0),
+};
+
#define BPF_ITER_CTX_ARG_MAX 2
struct bpf_iter_reg {
const char *target;
bpf_iter_show_fdinfo_t show_fdinfo;
bpf_iter_fill_link_info_t fill_link_info;
u32 ctx_arg_info_size;
+ u32 feature;
struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
const struct bpf_iter_seq_info *seq_info;
};
#ifndef _LINUX_BPF_LSM_H
#define _LINUX_BPF_LSM_H
+#include <linux/sched.h>
#include <linux/bpf.h>
#include <linux/lsm_hooks.h>
int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
const struct bpf_prog *prog);
+bool bpf_lsm_is_sleepable_hook(u32 btf_id);
+
static inline struct bpf_storage_blob *bpf_inode(
const struct inode *inode)
{
return inode->i_security + bpf_lsm_blob_sizes.lbs_inode;
}
+static inline struct bpf_storage_blob *bpf_task(
+ const struct task_struct *task)
+{
+ if (unlikely(!task->security))
+ return NULL;
+
+ return task->security + bpf_lsm_blob_sizes.lbs_task;
+}
+
extern const struct bpf_func_proto bpf_inode_storage_get_proto;
extern const struct bpf_func_proto bpf_inode_storage_delete_proto;
+extern const struct bpf_func_proto bpf_task_storage_get_proto;
+extern const struct bpf_func_proto bpf_task_storage_delete_proto;
void bpf_inode_storage_free(struct inode *inode);
+void bpf_task_storage_free(struct task_struct *task);
#else /* !CONFIG_BPF_LSM */
+static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id)
+{
+ return false;
+}
+
static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
const struct bpf_prog *prog)
{
return NULL;
}
+static inline struct bpf_storage_blob *bpf_task(
+ const struct task_struct *task)
+{
+ return NULL;
+}
+
static inline void bpf_inode_storage_free(struct inode *inode)
{
}
+static inline void bpf_task_storage_free(struct task_struct *task)
+{
+}
+
#endif /* CONFIG_BPF_LSM */
#endif /* _LINUX_BPF_LSM_H */
#endif
#ifdef CONFIG_BPF_LSM
BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
#if defined(CONFIG_XDP_SOCKETS)
enum bpf_reg_type type;
union {
/* valid when type == PTR_TO_PACKET */
- u16 range;
+ int range;
/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
* PTR_TO_MAP_VALUE_OR_NULL
}
/*
- * get_can_dlc(value) - helper macro to cast a given data length code (dlc)
- * to u8 and ensure the dlc value to be max. 8 bytes.
+ * can_cc_dlc2len(value) - convert a given data length code (dlc) of a
+ * Classical CAN frame into a valid data length of max. 8 bytes.
*
* To be used in the CAN netdriver receive path to ensure conformance with
* ISO 11898-1 Chapter 8.4.2.3 (DLC field)
*/
-#define get_can_dlc(i) (min_t(u8, (i), CAN_MAX_DLC))
-#define get_canfd_dlc(i) (min_t(u8, (i), CANFD_MAX_DLC))
+#define can_cc_dlc2len(dlc) (min_t(u8, (dlc), CAN_MAX_DLEN))
/* Check for outgoing skbs that have not been created by the CAN subsystem */
static inline bool can_skb_headroom_valid(struct net_device *dev,
return skb->len == CANFD_MTU;
}
+/* helper to get the data length code (DLC) for Classical CAN raw DLC access */
+static inline u8 can_get_cc_dlc(const struct can_frame *cf, const u32 ctrlmode)
+{
+ /* return len8_dlc as dlc value only if all conditions apply */
+ if ((ctrlmode & CAN_CTRLMODE_CC_LEN8_DLC) &&
+ (cf->len == CAN_MAX_DLEN) &&
+ (cf->len8_dlc > CAN_MAX_DLEN && cf->len8_dlc <= CAN_MAX_RAW_DLC))
+ return cf->len8_dlc;
+
+ /* return the payload length as dlc value */
+ return cf->len;
+}
+
+/* helper to set len and len8_dlc value for Classical CAN raw DLC access */
+static inline void can_frame_set_cc_len(struct can_frame *cf, const u8 dlc,
+ const u32 ctrlmode)
+{
+ /* the caller already ensured that dlc is a value from 0 .. 15 */
+ if (ctrlmode & CAN_CTRLMODE_CC_LEN8_DLC && dlc > CAN_MAX_DLEN)
+ cf->len8_dlc = dlc;
+
+ /* limit the payload length 'len' to CAN_MAX_DLEN */
+ cf->len = can_cc_dlc2len(dlc);
+}
+
/* helper to define static CAN controller features at device creation time */
static inline void can_set_static_ctrlmode(struct net_device *dev,
u32 static_mode)
dev->mtu = CANFD_MTU;
}
-/* get data length from can_dlc with sanitized can_dlc */
-u8 can_dlc2len(u8 can_dlc);
+/* get data length from raw data length code (DLC) */
+u8 can_fd_dlc2len(u8 dlc);
/* map the sanitized data length to an appropriate data length code */
-u8 can_len2dlc(u8 len);
+u8 can_fd_len2dlc(u8 len);
struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max,
unsigned int txqs, unsigned int rxqs);
}
/* return the dlc value from any received message channel_dlc field */
-static inline int pucan_msg_get_dlc(const struct pucan_rx_msg *msg)
+static inline u8 pucan_msg_get_dlc(const struct pucan_rx_msg *msg)
{
return msg->channel_dlc >> 4;
}
#define ETHTOOL_COALESCE_TX_USECS_HIGH BIT(19)
#define ETHTOOL_COALESCE_TX_MAX_FRAMES_HIGH BIT(20)
#define ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL BIT(21)
+#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(21, 0)
#define ETHTOOL_COALESCE_USECS \
(ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS)
nla_get_u64, nla_put_u64_0pad, false)
#define __str_field(attr_nr, attr_flag, name, maxlen) \
__array(attr_nr, attr_flag, name, NLA_NUL_STRING, char, maxlen, \
- nla_strlcpy, nla_put, false)
+ nla_strscpy, nla_put, false)
#define __bin_field(attr_nr, attr_flag, name, maxlen) \
__array(attr_nr, attr_flag, name, NLA_BINARY, char, maxlen, \
nla_memcpy, nla_put, false)
#define WLAN_AKM_SUITE_FT_PSK_SHA384 SUITE(0x000FAC, 19)
#define WLAN_AKM_SUITE_PSK_SHA384 SUITE(0x000FAC, 20)
+#define WLAN_AKM_SUITE_WFA_DPP SUITE(WLAN_OUI_WFA, 2)
+
#define WLAN_MAX_KEY_LEN 32
#define WLAN_PMK_NAME_LEN 16
#define WLAN_OUI_WFA 0x506f9a
#define WLAN_OUI_TYPE_WFA_P2P 9
+#define WLAN_OUI_TYPE_WFA_DPP 0x1A
#define WLAN_OUI_MICROSOFT 0x0050f2
#define WLAN_OUI_TYPE_MICROSOFT_WPA 1
#define WLAN_OUI_TYPE_MICROSOFT_WMM 2
#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr ip6;
#endif
+ unsigned char mac_addr[ETH_ALEN];
} dst;
__be16 proto;
__u16 vid;
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * DLCI/FRAD Definitions for Frame Relay Access Devices. DLCI devices are
- * created for each DLCI associated with a FRAD. The FRAD driver
- * is not truly a network device, but the lower level device
- * handler. This allows other FRAD manufacturers to use the DLCI
- * code, including its RFC1490 encapsulation alongside the current
- * implementation for the Sangoma cards.
- *
- * Version: @(#)if_ifrad.h 0.15 31 Mar 96
- *
- * Author: Mike McLagan <mike.mclagan@linux.org>
- *
- * Changes:
- * 0.15 Mike McLagan changed structure defs (packed)
- * re-arranged flags
- * added DLCI_RET vars
- */
-#ifndef _FRAD_H_
-#define _FRAD_H_
-
-#include <uapi/linux/if_frad.h>
-
-
-#if defined(CONFIG_DLCI) || defined(CONFIG_DLCI_MODULE)
-
-/* these are the fields of an RFC 1490 header */
-struct frhdr
-{
- unsigned char control;
-
- /* for IP packets, this can be the NLPID */
- unsigned char pad;
-
- unsigned char NLPID;
- unsigned char OUI[3];
- __be16 PID;
-
-#define IP_NLPID pad
-} __packed;
-
-/* see RFC 1490 for the definition of the following */
-#define FRAD_I_UI 0x03
-
-#define FRAD_P_PADDING 0x00
-#define FRAD_P_Q933 0x08
-#define FRAD_P_SNAP 0x80
-#define FRAD_P_CLNP 0x81
-#define FRAD_P_IP 0xCC
-
-struct dlci_local
-{
- struct net_device *master;
- struct net_device *slave;
- struct dlci_conf config;
- int configured;
- struct list_head list;
-
- /* callback function */
- void (*receive)(struct sk_buff *skb, struct net_device *);
-};
-
-struct frad_local
-{
- /* devices which this FRAD is slaved to */
- struct net_device *master[CONFIG_DLCI_MAX];
- short dlci[CONFIG_DLCI_MAX];
-
- struct frad_conf config;
- int configured; /* has this device been configured */
- int initialized; /* mem_start, port, irq set ? */
-
- /* callback functions */
- int (*activate)(struct net_device *, struct net_device *);
- int (*deactivate)(struct net_device *, struct net_device *);
- int (*assoc)(struct net_device *, struct net_device *);
- int (*deassoc)(struct net_device *, struct net_device *);
- int (*dlci_conf)(struct net_device *, struct net_device *, int get);
-
- /* 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 */
-};
-
-#endif /* CONFIG_DLCI || CONFIG_DLCI_MODULE */
-
-extern void dlci_ioctl_set(int (*hook)(unsigned int, void __user *));
-
-#endif
enum macvlan_mode mode;
u16 flags;
unsigned int macaddr_count;
+ u32 bc_queue_len_req;
#ifdef CONFIG_NET_POLL_CONTROLLER
struct netpoll *netpoll;
#endif
#define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS)
#define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP)
-#define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_CONF_GET(in_dev, PROXY_ARP_PVLAN)
+#define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN)
#define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA)
#define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS)
#define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \
IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS)))
#define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \
- IN_DEV_CONF_GET((in_dev), IGNORE_ROUTES_WITH_LINKDOWN)
+ IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN)
#define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER)
#define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_ORCONF((in_dev), ARP_ACCEPT)
* clear the contents.
*/
struct key_preparsed_payload {
+ const char *orig_description; /* Actual or proposed description (maybe NULL) */
char *description; /* Proposed key description (or NULL) */
union key_payload payload; /* Proposed payload */
const void *data; /* Raw data */
this_cpu_read(hardirqs_enabled))); \
} while (0)
+/*
+ * Acceptable for protecting per-CPU resources accessed from BH.
+ * Much like in_softirq() - semantics are ambiguous, use carefully.
+ */
+#define lockdep_assert_in_softirq() \
+do { \
+ WARN_ON_ONCE(__lockdep_enabled && \
+ (!in_softirq() || in_irq() || in_nmi())); \
+} while (0)
+
#else
# define might_lock(lock) do { } while (0)
# define might_lock_read(lock) do { } while (0)
# define lockdep_assert_preemption_enabled() do { } while (0)
# define lockdep_assert_preemption_disabled() do { } while (0)
+# define lockdep_assert_in_softirq() do { } while (0)
#endif
#ifdef CONFIG_PROVE_RAW_LOCK_NESTING
struct lsm_network_audit {
int netif;
- struct sock *sk;
+ const struct sock *sk;
u16 family;
__be16 dport;
__be16 sport;
struct sock *newsk)
LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, struct sock *sk, u32 *secid)
LSM_HOOK(void, LSM_RET_VOID, sock_graft, struct sock *sk, struct socket *parent)
-LSM_HOOK(int, 0, inet_conn_request, struct sock *sk, struct sk_buff *skb,
+LSM_HOOK(int, 0, inet_conn_request, const struct sock *sk, struct sk_buff *skb,
struct request_sock *req)
LSM_HOOK(void, LSM_RET_VOID, inet_csk_clone, struct sock *newsk,
const struct request_sock *req)
#define MARVELL_PHY_ID_88X3310 0x002b09a0
#define MARVELL_PHY_ID_88E2110 0x002b09b0
+/* Marvel 88E1111 in Finisar SFP module with modified PHY ID */
+#define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0
+
/* The MV88e6390 Ethernet switch contains embedded PHYs. These PHYs do
* not have a model ID. So the switch driver traps reads to the ID2
* register and returns the switch family ID
int mhi_queue_skb(struct mhi_device *mhi_dev, enum dma_data_direction dir,
struct sk_buff *skb, size_t len, enum mhi_flags mflags);
+/**
+ * mhi_queue_is_full - Determine whether queueing new elements is possible
+ * @mhi_dev: Device associated with the channels
+ * @dir: DMA direction for the channel
+ */
+bool mhi_queue_is_full(struct mhi_device *mhi_dev, enum dma_data_direction dir);
+
#endif /* _MHI_H_ */
MLX5_EVENT_TYPE_NIC_VPORT_CHANGE = 0xd,
MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED = 0xe,
+ MLX5_EVENT_TYPE_VHCA_STATE_CHANGE = 0xf,
MLX5_EVENT_TYPE_DCT_DRAINED = 0x1c,
MLX5_EVENT_TYPE_DCT_KEY_VIOLATION = 0x1d,
u8 sync_rst_state;
};
+struct mlx5_eqe_vhca_state {
+ __be16 ec_function;
+ __be16 function_id;
+} __packed;
+
union ev_data {
__be32 raw[7];
struct mlx5_eqe_cmd cmd;
struct mlx5_eqe_temp_warning temp_warning;
struct mlx5_eqe_xrq_err xrq_err;
struct mlx5_eqe_sync_fw_update sync_fw_update;
+ struct mlx5_eqe_vhca_state vhca_state;
} __packed;
struct mlx5_eqe {
MLX5_MATCH_INNER_HEADERS = 1 << 2,
MLX5_MATCH_MISC_PARAMETERS_2 = 1 << 3,
MLX5_MATCH_MISC_PARAMETERS_3 = 1 << 4,
+ MLX5_MATCH_MISC_PARAMETERS_4 = 1 << 5,
};
enum {
atomic_t reg_pages;
struct list_head free_list;
int vfs_pages;
- int peer_pf_pages;
+ int host_pf_pages;
struct mlx5_core_health health;
CMD_ALLOWED_OPCODE_ALL,
};
-int mlx5_cmd_init(struct mlx5_core_dev *dev);
-void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
-void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
- enum mlx5_cmdif_state cmdif_state);
void mlx5_cmd_use_events(struct mlx5_core_dev *dev);
void mlx5_cmd_use_polling(struct mlx5_core_dev *dev);
void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode);
return dev->coredev_type == MLX5_COREDEV_VF;
}
-static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev)
+static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev)
{
return dev->caps.embedded_cpu;
}
MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1),
MLX5_FLOW_TABLE_TERMINATION = BIT(2),
MLX5_FLOW_TABLE_UNMANAGED = BIT(3),
+ MLX5_FLOW_TABLE_OTHER_VPORT = BIT(4),
};
#define LEFTOVERS_RULE_NUM 2
struct mlx5_pkt_reformat *pkt_reformat;
u8 flags;
} vport;
+ u32 sampler_id;
};
};
struct mlx5_flow_table *
mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
- int prio,
- int num_flow_table_entries,
- u32 level, u16 vport);
+ struct mlx5_flow_table_attr *ft_attr, u16 vport);
struct mlx5_flow_table *mlx5_create_lag_demux_flow_table(
struct mlx5_flow_namespace *ns,
int prio, u32 level);
MLX5_CMD_OP_CREATE_UMEM = 0xa08,
MLX5_CMD_OP_DESTROY_UMEM = 0xa0a,
MLX5_CMD_OP_SYNC_STEERING = 0xb00,
+ MLX5_CMD_OP_QUERY_VHCA_STATE = 0xb0d,
+ MLX5_CMD_OP_MODIFY_VHCA_STATE = 0xb0e,
MLX5_CMD_OP_MAX
};
u8 reserved_at_140[0xc0];
};
+struct mlx5_ifc_fte_match_set_misc4_bits {
+ u8 prog_sample_field_value_0[0x20];
+
+ u8 prog_sample_field_id_0[0x20];
+
+ u8 prog_sample_field_value_1[0x20];
+
+ u8 prog_sample_field_id_1[0x20];
+
+ u8 prog_sample_field_value_2[0x20];
+
+ u8 prog_sample_field_id_2[0x20];
+
+ u8 prog_sample_field_value_3[0x20];
+
+ u8 prog_sample_field_id_3[0x20];
+
+ u8 reserved_at_100[0x100];
+};
+
struct mlx5_ifc_cmd_pas_bits {
u8 pa_h[0x20];
u8 tunnel_stateless_ipv4_over_vxlan[0x1];
u8 tunnel_stateless_ip_over_ip[0x1];
u8 insert_trailer[0x1];
- u8 reserved_at_2b[0x5];
+ u8 reserved_at_2b[0x1];
+ u8 tunnel_stateless_ip_over_ip_rx[0x1];
+ u8 tunnel_stateless_ip_over_ip_tx[0x1];
+ u8 reserved_at_2e[0x2];
u8 max_vxlan_udp_ports[0x8];
u8 reserved_at_38[0x6];
u8 max_geneve_opt_len[0x1];
};
struct mlx5_ifc_cmd_hca_cap_bits {
- u8 reserved_at_0[0x30];
+ u8 reserved_at_0[0x1f];
+ u8 vhca_resource_manager[0x1];
+
+ u8 reserved_at_20[0x3];
+ u8 event_on_vhca_state_teardown_request[0x1];
+ u8 event_on_vhca_state_in_use[0x1];
+ u8 event_on_vhca_state_active[0x1];
+ u8 event_on_vhca_state_allocated[0x1];
+ u8 event_on_vhca_state_invalid[0x1];
+ u8 reserved_at_28[0x8];
u8 vhca_id[0x10];
u8 reserved_at_40[0x40];
u8 ece_support[0x1];
u8 reserved_at_a4[0x7];
u8 log_max_srq[0x5];
- u8 reserved_at_b0[0x10];
+ u8 reserved_at_b0[0x2];
+ u8 ts_cqe_to_dest_cqn[0x1];
+ u8 reserved_at_b3[0xd];
u8 max_sgl_for_optimized_performance[0x8];
u8 log_max_cq_sz[0x8];
u8 disable_local_lb_uc[0x1];
u8 disable_local_lb_mc[0x1];
u8 log_min_hairpin_wq_data_sz[0x5];
- u8 reserved_at_3e8[0x3];
+ u8 reserved_at_3e8[0x2];
+ u8 vhca_state[0x1];
u8 log_max_vlan_list[0x5];
u8 reserved_at_3f0[0x3];
u8 log_max_current_mc_list[0x5];
u8 max_num_of_monitor_counters[0x10];
u8 num_ppcnt_monitor_counters[0x10];
- u8 reserved_at_640[0x10];
+ u8 max_num_sf[0x10];
u8 num_q_monitor_counters[0x10];
u8 reserved_at_660[0x20];
MLX5_FLOW_DESTINATION_TYPE_VPORT = 0x0,
MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1,
MLX5_FLOW_DESTINATION_TYPE_TIR = 0x2,
+ MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6,
MLX5_FLOW_DESTINATION_TYPE_PORT = 0x99,
MLX5_FLOW_DESTINATION_TYPE_COUNTER = 0x100,
struct mlx5_ifc_fte_match_set_misc3_bits misc_parameters_3;
- u8 reserved_at_a00[0x600];
+ struct mlx5_ifc_fte_match_set_misc4_bits misc_parameters_4;
+
+ u8 reserved_at_c00[0x400];
};
enum {
u8 reserved_at_80[0x10];
u8 hairpin_peer_vhca[0x10];
- u8 reserved_at_a0[0x50];
+ u8 reserved_at_a0[0x20];
+ u8 reserved_at_c0[0x8];
+ u8 ts_cqe_to_dest_cqn[0x18];
+
+ u8 reserved_at_e0[0x10];
u8 packet_pacing_rate_limit_index[0x10];
u8 tis_lst_sz[0x10];
u8 reserved_at_110[0x10];
u8 reserved_at_20[0x10];
u8 op_mod[0x10];
- u8 reserved_at_40[0x40];
+ u8 other_function[0x1];
+ u8 reserved_at_41[0xf];
+ u8 function_id[0x10];
+
+ u8 reserved_at_60[0x20];
union mlx5_ifc_hca_cap_union_bits capability;
};
MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_INNER_HEADERS = 0x2,
MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0x3,
MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_3 = 0x4,
+ MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_4 = 0x5,
};
struct mlx5_ifc_query_flow_group_out_bits {
enum {
MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT(0xc),
MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT(0x13),
+ MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER = BIT(0x20),
};
enum {
MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc,
MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13,
+ MLX5_GENERAL_OBJECT_TYPES_SAMPLER = 0x20,
};
enum {
struct mlx5_ifc_encryption_key_obj_bits encryption_key_object;
};
+struct mlx5_ifc_sampler_obj_bits {
+ u8 modify_field_select[0x40];
+
+ u8 table_type[0x8];
+ u8 level[0x8];
+ u8 reserved_at_50[0xf];
+ u8 ignore_flow_level[0x1];
+
+ u8 sample_ratio[0x20];
+
+ u8 reserved_at_80[0x8];
+ u8 sample_table_id[0x18];
+
+ u8 reserved_at_a0[0x8];
+ u8 default_table_id[0x18];
+
+ u8 sw_steering_icm_address_rx[0x40];
+ u8 sw_steering_icm_address_tx[0x40];
+
+ u8 reserved_at_140[0xa0];
+};
+
+struct mlx5_ifc_create_sampler_obj_in_bits {
+ struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+ struct mlx5_ifc_sampler_obj_bits sampler_object;
+};
+
enum {
MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128 = 0x0,
MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_256 = 0x1,
unsigned int num_bpf_raw_events;
struct bpf_raw_event_map *bpf_raw_events;
#endif
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+ unsigned int btf_data_size;
+ void *btf_data;
+#endif
#ifdef CONFIG_JUMP_LABEL
struct jump_entry *jump_entries;
unsigned int num_jump_entries;
NETIF_F_FSO)
/* List of features with software fallbacks. */
-#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | \
- NETIF_F_GSO_SCTP)
+#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP | \
+ NETIF_F_GSO_UDP_L4 | NETIF_F_GSO_FRAGLIST)
/*
* If one device supports one of these features, then enable them
#include <linux/workqueue.h>
#include <linux/dynamic_queue_limits.h>
-#include <linux/ethtool.h>
#include <net/net_namespace.h>
#ifdef CONFIG_DCB
#include <net/dcbnl.h>
struct netpoll_info;
struct device;
+struct ethtool_ops;
struct phy_device;
struct dsa_port;
struct ip_tunnel_parm;
};
/**
- * enum net_device_priv_flags - &struct net_device priv_flags
+ * enum netdev_priv_flags - &struct net_device priv_flags
*
* These are the &struct net_device, they are only set internally
* by drivers and used in the kernel. These flags are invisible to
u64_stats_update_end(&tstats->syncp);
}
+static inline void dev_sw_netstats_tx_add(struct net_device *dev,
+ unsigned int packets,
+ unsigned int len)
+{
+ struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->tx_bytes += len;
+ tstats->tx_packets += packets;
+ u64_stats_update_end(&tstats->syncp);
+}
+
static inline void dev_lstats_add(struct net_device *dev, unsigned int len)
{
struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats);
#define netdev_alloc_pcpu_stats(type) \
__netdev_alloc_pcpu_stats(type, GFP_KERNEL)
+#define devm_netdev_alloc_pcpu_stats(dev, type) \
+({ \
+ typeof(type) __percpu *pcpu_stats = devm_alloc_percpu(dev, type);\
+ if (pcpu_stats) { \
+ int __cpu; \
+ for_each_possible_cpu(__cpu) { \
+ typeof(type) *stat; \
+ stat = per_cpu_ptr(pcpu_stats, __cpu); \
+ u64_stats_init(&stat->syncp); \
+ } \
+ } \
+ pcpu_stats; \
+})
+
enum netdev_lag_tx_type {
NETDEV_LAG_TX_TYPE_UNKNOWN,
NETDEV_LAG_TX_TYPE_RANDOM,
struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
const char *hwaddr);
struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
-struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type);
void dev_add_pack(struct packet_type *pt);
void dev_remove_pack(struct packet_type *pt);
void __dev_remove_pack(struct packet_type *pt);
}
/**
- * netif_subqueue_stopped - test status of subqueue
+ * __netif_subqueue_stopped - test status of subqueue
* @dev: network device
* @queue_index: sub queue index
*
return netif_tx_queue_stopped(txq);
}
+/**
+ * netif_subqueue_stopped - test status of subqueue
+ * @dev: network device
+ * @skb: sub queue buffer pointer
+ *
+ * Check individual transmit queue of a device with multiple transmit queues.
+ */
static inline bool netif_subqueue_stopped(const struct net_device *dev,
struct sk_buff *skb)
{
const struct net_device_stats *netdev_stats);
void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
const struct pcpu_sw_netstats __percpu *netstats);
+void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s);
extern int netdev_max_backlog;
extern int netdev_tstamp_prequeue;
u32 elements; /* Number of elements vs timeout */
};
+/* The max revision number supported by any set type + 1 */
+#define IPSET_REVISION_MAX 9
+
/* The core set type structure */
struct ip_set_type {
struct list_head list;
u8 family;
/* Type revisions */
u8 revision_min, revision_max;
+ /* Revision-specific supported (create) flags */
+ u8 create_flags[IPSET_REVISION_MAX+1];
/* Set features to control swapping */
u16 features;
/** @read_status: Determines the negotiated speed and duplex */
int (*read_status)(struct phy_device *phydev);
- /** @ack_interrupt: Clears any pending interrupts */
- int (*ack_interrupt)(struct phy_device *phydev);
-
- /** @config_intr: Enables or disables interrupts */
- int (*config_intr)(struct phy_device *phydev);
-
- /**
- * @did_interrupt: Checks if the PHY generated an interrupt.
- * For multi-PHY devices with shared PHY interrupt pin
- * Set interrupt bits have to be cleared.
+ /** @config_intr: Enables or disables interrupts.
+ * It should also clear any pending interrupts prior to enabling the
+ * IRQs and after disabling them.
*/
- int (*did_interrupt)(struct phy_device *phydev);
+ int (*config_intr)(struct phy_device *phydev);
/** @handle_interrupt: Override default interrupt handling */
irqreturn_t (*handle_interrupt)(struct phy_device *phydev);
int genphy_resume(struct phy_device *phydev);
int genphy_loopback(struct phy_device *phydev, bool enable);
int genphy_soft_reset(struct phy_device *phydev);
+irqreturn_t genphy_handle_interrupt_no_ack(struct phy_device *phydev);
static inline int genphy_config_aneg(struct phy_device *phydev)
{
return __genphy_config_aneg(phydev, false);
}
-static inline int genphy_no_ack_interrupt(struct phy_device *phydev)
-{
- return 0;
-}
static inline int genphy_no_config_intr(struct phy_device *phydev)
{
return 0;
int phy_driver_register(struct phy_driver *new_driver, struct module *owner);
int phy_drivers_register(struct phy_driver *new_driver, int n,
struct module *owner);
+void phy_error(struct phy_device *phydev);
void phy_state_machine(struct work_struct *work);
void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies);
+void phy_trigger_machine(struct phy_device *phydev);
void phy_mac_interrupt(struct phy_device *phydev);
void phy_start_machine(struct phy_device *phydev);
void phy_stop_machine(struct phy_device *phydev);
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 or MIT) */
+/*
+ * Hirschmann Hellcreek TSN switch platform data.
+ *
+ * Copyright (C) 2020 Linutronix GmbH
+ * Author Kurt Kanzenbach <kurt@linutronix.de>
+ */
+
+#ifndef _HIRSCHMANN_HELLCREEK_H_
+#define _HIRSCHMANN_HELLCREEK_H_
+
+#include <linux/types.h>
+
+struct hellcreek_platform_data {
+ int num_ports; /* Amount of switch ports */
+ int is_100_mbits; /* Is it configured to 100 or 1000 mbit/s */
+ int qbv_support; /* Qbv support on front TSN ports */
+ int qbv_on_cpu_port; /* Qbv support on the CPU port */
+ int qbu_support; /* Qbu support on front TSN ports */
+ u16 module_id; /* Module identificaton */
+};
+
+#endif /* _HIRSCHMANN_HELLCREEK_H_ */
#define PTP_CLASS_V2_VLAN (PTP_CLASS_V2 | PTP_CLASS_VLAN)
#define PTP_CLASS_L4 (PTP_CLASS_IPV4 | PTP_CLASS_IPV6)
+#define PTP_MSGTYPE_SYNC 0x0
+#define PTP_MSGTYPE_DELAY_REQ 0x1
+#define PTP_MSGTYPE_PDELAY_REQ 0x2
+#define PTP_MSGTYPE_PDELAY_RESP 0x3
+
#define PTP_EV_PORT 319
#define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */
/* The return is meaningless. The stub function would not be
* executed since no available header from ptp_parse_header.
*/
- return 0;
+ return PTP_MSGTYPE_SYNC;
}
#endif
#endif /* _PTP_CLASSIFY_H_ */
#include <linux/pps_kernel.h>
#include <linux/ptp_clock.h>
+/**
+ * struct ptp_clock_request - request PTP clock event
+ *
+ * @type: The type of the request.
+ * EXTTS: Configure external trigger timestamping
+ * PEROUT: Configure periodic output signal (e.g. PPS)
+ * PPS: trigger internal PPS event for input
+ * into kernel PPS subsystem
+ * @extts: describes configuration for external trigger timestamping.
+ * This is only valid when event == PTP_CLK_REQ_EXTTS.
+ * @perout: describes configuration for periodic output.
+ * This is only valid when event == PTP_CLK_REQ_PEROUT.
+ */
struct ptp_clock_request {
enum {
#ifndef _QED_IF_H
#define _QED_IF_H
+#include <linux/ethtool.h>
#include <linux/types.h>
#include <linux/interrupt.h>
#include <linux/netdevice.h>
* 11 Restart of an association with new addresses
* 12 User Initiated Abort
* 13 Protocol Violation
+ * 14 Restart of an Association with New Encapsulation Port
*/
SCTP_ERROR_RESTART = cpu_to_be16(0x0b),
SCTP_ERROR_USER_ABORT = cpu_to_be16(0x0c),
SCTP_ERROR_PROTO_VIOLATION = cpu_to_be16(0x0d),
+ SCTP_ERROR_NEW_ENCAP_PORT = cpu_to_be16(0x0e),
/* ADDIP Section 3.3 New Error Causes
*
SCTP_FLOWLABEL_VAL_MASK = 0xfffff
};
+/* UDP Encapsulation
+ * draft-tuexen-tsvwg-sctp-udp-encaps-cons-03.html#section-4-4
+ *
+ * The error cause indicating an "Restart of an Association with
+ * New Encapsulation Port"
+ *
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Cause Code = 14 | Cause Length = 8 |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Current Encapsulation Port | New Encapsulation Port |
+ * +-------------------------------+-------------------------------+
+ */
+struct sctp_new_encap_port_hdr {
+ __be16 cur_port;
+ __be16 new_port;
+};
+
#endif /* __LINUX_SCTP_H__ */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * INET An implementation of the TCP/IP protocol suite for the LINUX
- * operating system. INET is implemented using the BSD Socket
- * interface as the means of communication with the user level.
- *
- * Global definitions for the Frame relay interface.
- *
- * Version: @(#)if_ifrad.h 0.20 13 Apr 96
- *
- * Author: Mike McLagan <mike.mclagan@linux.org>
- *
- * Changes:
- * 0.15 Mike McLagan Structure packing
- *
- * 0.20 Mike McLagan New flags for S508 buffer handling
- */
-#ifndef SDLA_H
-#define SDLA_H
-
-#include <uapi/linux/sdla.h>
-
-
-/* important Z80 window addresses */
-#define SDLA_CONTROL_WND 0xE000
-
-#define SDLA_502_CMD_BUF 0xEF60
-#define SDLA_502_RCV_BUF 0xA900
-#define SDLA_502_TXN_AVAIL 0xFFF1
-#define SDLA_502_RCV_AVAIL 0xFFF2
-#define SDLA_502_EVENT_FLAGS 0xFFF3
-#define SDLA_502_MDM_STATUS 0xFFF4
-#define SDLA_502_IRQ_INTERFACE 0xFFFD
-#define SDLA_502_IRQ_PERMISSION 0xFFFE
-#define SDLA_502_DATA_OFS 0x0010
-
-#define SDLA_508_CMD_BUF 0xE000
-#define SDLA_508_TXBUF_INFO 0xF100
-#define SDLA_508_RXBUF_INFO 0xF120
-#define SDLA_508_EVENT_FLAGS 0xF003
-#define SDLA_508_MDM_STATUS 0xF004
-#define SDLA_508_IRQ_INTERFACE 0xF010
-#define SDLA_508_IRQ_PERMISSION 0xF011
-#define SDLA_508_TSE_OFFSET 0xF012
-
-/* Event flags */
-#define SDLA_EVENT_STATUS 0x01
-#define SDLA_EVENT_DLCI_STATUS 0x02
-#define SDLA_EVENT_BAD_DLCI 0x04
-#define SDLA_EVENT_LINK_DOWN 0x40
-
-/* IRQ Trigger flags */
-#define SDLA_INTR_RX 0x01
-#define SDLA_INTR_TX 0x02
-#define SDLA_INTR_MODEM 0x04
-#define SDLA_INTR_COMPLETE 0x08
-#define SDLA_INTR_STATUS 0x10
-#define SDLA_INTR_TIMER 0x20
-
-/* DLCI status bits */
-#define SDLA_DLCI_DELETED 0x01
-#define SDLA_DLCI_ACTIVE 0x02
-#define SDLA_DLCI_WAITING 0x04
-#define SDLA_DLCI_NEW 0x08
-#define SDLA_DLCI_INCLUDED 0x40
-
-/* valid command codes */
-#define SDLA_INFORMATION_WRITE 0x01
-#define SDLA_INFORMATION_READ 0x02
-#define SDLA_ISSUE_IN_CHANNEL_SIGNAL 0x03
-#define SDLA_SET_DLCI_CONFIGURATION 0x10
-#define SDLA_READ_DLCI_CONFIGURATION 0x11
-#define SDLA_DISABLE_COMMUNICATIONS 0x12
-#define SDLA_ENABLE_COMMUNICATIONS 0x13
-#define SDLA_READ_DLC_STATUS 0x14
-#define SDLA_READ_DLC_STATISTICS 0x15
-#define SDLA_FLUSH_DLC_STATISTICS 0x16
-#define SDLA_LIST_ACTIVE_DLCI 0x17
-#define SDLA_FLUSH_INFORMATION_BUFFERS 0x18
-#define SDLA_ADD_DLCI 0x20
-#define SDLA_DELETE_DLCI 0x21
-#define SDLA_ACTIVATE_DLCI 0x22
-#define SDLA_DEACTIVATE_DLCI 0x23
-#define SDLA_READ_MODEM_STATUS 0x30
-#define SDLA_SET_MODEM_STATUS 0x31
-#define SDLA_READ_COMMS_ERR_STATS 0x32
-#define SDLA_FLUSH_COMMS_ERR_STATS 0x33
-#define SDLA_READ_CODE_VERSION 0x40
-#define SDLA_SET_IRQ_TRIGGER 0x50
-#define SDLA_GET_IRQ_TRIGGER 0x51
-
-/* In channel signal types */
-#define SDLA_ICS_LINK_VERIFY 0x02
-#define SDLA_ICS_STATUS_ENQ 0x03
-
-/* modem status flags */
-#define SDLA_MODEM_DTR_HIGH 0x01
-#define SDLA_MODEM_RTS_HIGH 0x02
-#define SDLA_MODEM_DCD_HIGH 0x08
-#define SDLA_MODEM_CTS_HIGH 0x20
-
-/* used for RET_MODEM interpretation */
-#define SDLA_MODEM_DCD_LOW 0x01
-#define SDLA_MODEM_CTS_LOW 0x02
-
-/* return codes */
-#define SDLA_RET_OK 0x00
-#define SDLA_RET_COMMUNICATIONS 0x01
-#define SDLA_RET_CHANNEL_INACTIVE 0x02
-#define SDLA_RET_DLCI_INACTIVE 0x03
-#define SDLA_RET_DLCI_CONFIG 0x04
-#define SDLA_RET_BUF_TOO_BIG 0x05
-#define SDLA_RET_NO_DATA 0x05
-#define SDLA_RET_BUF_OVERSIZE 0x06
-#define SDLA_RET_CIR_OVERFLOW 0x07
-#define SDLA_RET_NO_BUFS 0x08
-#define SDLA_RET_TIMEOUT 0x0A
-#define SDLA_RET_MODEM 0x10
-#define SDLA_RET_CHANNEL_OFF 0x11
-#define SDLA_RET_CHANNEL_ON 0x12
-#define SDLA_RET_DLCI_STATUS 0x13
-#define SDLA_RET_DLCI_UNKNOWN 0x14
-#define SDLA_RET_COMMAND_INVALID 0x1F
-
-/* Configuration flags */
-#define SDLA_DIRECT_RECV 0x0080
-#define SDLA_TX_NO_EXCEPT 0x0020
-#define SDLA_NO_ICF_MSGS 0x1000
-#define SDLA_TX50_RX50 0x0000
-#define SDLA_TX70_RX30 0x2000
-#define SDLA_TX30_RX70 0x4000
-
-/* IRQ selection flags */
-#define SDLA_IRQ_RECEIVE 0x01
-#define SDLA_IRQ_TRANSMIT 0x02
-#define SDLA_IRQ_MODEM_STAT 0x04
-#define SDLA_IRQ_COMMAND 0x08
-#define SDLA_IRQ_CHANNEL 0x10
-#define SDLA_IRQ_TIMER 0x20
-
-/* definitions for PC memory mapping */
-#define SDLA_8K_WINDOW 0x01
-#define SDLA_S502_SEG_A 0x10
-#define SDLA_S502_SEG_C 0x20
-#define SDLA_S502_SEG_D 0x00
-#define SDLA_S502_SEG_E 0x30
-#define SDLA_S507_SEG_A 0x00
-#define SDLA_S507_SEG_B 0x40
-#define SDLA_S507_SEG_C 0x80
-#define SDLA_S507_SEG_E 0xC0
-#define SDLA_S508_SEG_A 0x00
-#define SDLA_S508_SEG_C 0x10
-#define SDLA_S508_SEG_D 0x08
-#define SDLA_S508_SEG_E 0x18
-
-/* SDLA adapter port constants */
-#define SDLA_IO_EXTENTS 0x04
-
-#define SDLA_REG_CONTROL 0x00
-#define SDLA_REG_PC_WINDOW 0x01 /* offset for PC window select latch */
-#define SDLA_REG_Z80_WINDOW 0x02 /* offset for Z80 window select latch */
-#define SDLA_REG_Z80_CONTROL 0x03 /* offset for Z80 control latch */
-
-#define SDLA_S502_STS 0x00 /* status reg for 502, 502E, 507 */
-#define SDLA_S508_GNRL 0x00 /* general purp. reg for 508 */
-#define SDLA_S508_STS 0x01 /* status reg for 508 */
-#define SDLA_S508_IDR 0x02 /* ID reg for 508 */
-
-/* control register flags */
-#define SDLA_S502A_START 0x00 /* start the CPU */
-#define SDLA_S502A_INTREQ 0x02
-#define SDLA_S502A_INTEN 0x04
-#define SDLA_S502A_HALT 0x08 /* halt the CPU */
-#define SDLA_S502A_NMI 0x10 /* issue an NMI to the CPU */
-
-#define SDLA_S502E_CPUEN 0x01
-#define SDLA_S502E_ENABLE 0x02
-#define SDLA_S502E_INTACK 0x04
-
-#define SDLA_S507_ENABLE 0x01
-#define SDLA_S507_IRQ3 0x00
-#define SDLA_S507_IRQ4 0x20
-#define SDLA_S507_IRQ5 0x40
-#define SDLA_S507_IRQ7 0x60
-#define SDLA_S507_IRQ10 0x80
-#define SDLA_S507_IRQ11 0xA0
-#define SDLA_S507_IRQ12 0xC0
-#define SDLA_S507_IRQ15 0xE0
-
-#define SDLA_HALT 0x00
-#define SDLA_CPUEN 0x02
-#define SDLA_MEMEN 0x04
-#define SDLA_S507_EPROMWR 0x08
-#define SDLA_S507_EPROMCLK 0x10
-#define SDLA_S508_INTRQ 0x08
-#define SDLA_S508_INTEN 0x10
-
-struct sdla_cmd {
- char opp_flag;
- char cmd;
- short length;
- char retval;
- short dlci;
- char flags;
- short rxlost_int;
- long rxlost_app;
- char reserve[2];
- char data[SDLA_MAX_DATA]; /* transfer data buffer */
-} __attribute__((packed));
-
-struct intr_info {
- char flags;
- short txlen;
- char irq;
- char flags2;
- short timeout;
-} __attribute__((packed));
-
-/* found in the 508's control window at RXBUF_INFO */
-struct buf_info {
- unsigned short rse_num;
- unsigned long rse_base;
- unsigned long rse_next;
- unsigned long buf_base;
- unsigned short reserved;
- unsigned long buf_top;
-} __attribute__((packed));
-
-/* structure pointed to by rse_base in RXBUF_INFO struct */
-struct buf_entry {
- char opp_flag;
- short length;
- short dlci;
- char flags;
- short timestamp;
- short reserved[2];
- long buf_addr;
-} __attribute__((packed));
-
-#endif
void security_sk_classify_flow(struct sock *sk, struct flowi *fl);
void security_req_classify_flow(const struct request_sock *req, struct flowi *fl);
void security_sock_graft(struct sock*sk, struct socket *parent);
-int security_inet_conn_request(struct sock *sk,
+int security_inet_conn_request(const struct sock *sk,
struct sk_buff *skb, struct request_sock *req);
void security_inet_csk_clone(struct sock *newsk,
const struct request_sock *req);
{
}
-static inline int security_inet_conn_request(struct sock *sk,
+static inline int security_inet_conn_request(const struct sock *sk,
struct sk_buff *skb, struct request_sock *req)
{
return 0;
* @transport_header: Transport layer header
* @network_header: Network layer header
* @mac_header: Link layer header
+ * @kcov_handle: KCOV remote handle for remote coverage collection
* @tail: Tail pointer
* @end: End pointer
* @head: Head of buffer
__u16 network_header;
__u16 mac_header;
+#ifdef CONFIG_KCOV
+ u64 kcov_handle;
+#endif
+
/* private: */
__u32 headers_end[0];
/* public: */
#endif
}
+static inline void skb_set_kcov_handle(struct sk_buff *skb,
+ const u64 kcov_handle)
+{
+#ifdef CONFIG_KCOV
+ skb->kcov_handle = kcov_handle;
+#endif
+}
+
+static inline u64 skb_get_kcov_handle(struct sk_buff *skb)
+{
+#ifdef CONFIG_KCOV
+ return skb->kcov_handle;
+#else
+ return 0;
+#endif
+}
+
#endif /* __KERNEL__ */
#endif /* _LINUX_SKBUFF_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __SOC_OTX2_ASM_H
+#define __SOC_OTX2_ASM_H
+
+#if defined(CONFIG_ARM64)
+/*
+ * otx2_lmt_flush is used for LMT store operation.
+ * On octeontx2 platform CPT instruction enqueue and
+ * NIX packet send are only possible via LMTST
+ * operations and it uses LDEOR instruction targeting
+ * the coprocessor address.
+ */
+#define otx2_lmt_flush(ioaddr) \
+({ \
+ u64 result = 0; \
+ __asm__ volatile(".cpu generic+lse\n" \
+ "ldeor xzr, %x[rf], [%[rs]]" \
+ : [rf]"=r" (result) \
+ : [rs]"r" (ioaddr)); \
+ (result); \
+})
+#else
+#define otx2_lmt_flush(ioaddr) ({ 0; })
+#endif
+
+#endif /* __SOC_OTX2_ASM_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2020 Realtek Semiconductor Corp. All rights reserved.
+ */
+
+#ifndef __LINUX_R8152_H
+#define __LINUX_R8152_H
+
+#define RTL8152_REQT_READ 0xc0
+#define RTL8152_REQT_WRITE 0x40
+#define RTL8152_REQ_GET_REGS 0x05
+#define RTL8152_REQ_SET_REGS 0x05
+
+#define BYTE_EN_DWORD 0xff
+#define BYTE_EN_WORD 0x33
+#define BYTE_EN_BYTE 0x11
+#define BYTE_EN_SIX_BYTES 0x3f
+#define BYTE_EN_START_MASK 0x0f
+#define BYTE_EN_END_MASK 0xf0
+
+#define MCU_TYPE_PLA 0x0100
+#define MCU_TYPE_USB 0x0000
+
+/* Define these values to match your device */
+#define VENDOR_ID_REALTEK 0x0bda
+#define VENDOR_ID_MICROSOFT 0x045e
+#define VENDOR_ID_SAMSUNG 0x04e8
+#define VENDOR_ID_LENOVO 0x17ef
+#define VENDOR_ID_LINKSYS 0x13b1
+#define VENDOR_ID_NVIDIA 0x0955
+#define VENDOR_ID_TPLINK 0x2357
+
+#if IS_REACHABLE(CONFIG_USB_RTL8152)
+extern u8 rtl8152_get_version(struct usb_interface *intf);
+#endif
+
+#endif /* __LINUX_R8152_H */
struct usb_anchor deferred;
struct tasklet_struct bh;
- struct pcpu_sw_netstats __percpu *stats64;
-
struct work_struct kevent;
unsigned long flags;
# define EVENT_TX_HALT 0
extern void usbnet_status_stop(struct usbnet *dev);
extern void usbnet_update_max_qlen(struct usbnet *dev);
-extern void usbnet_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *stats);
#endif /* __LINUX_USB_USBNET_H */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Linux WiMAX
- * Collection of tools to manage debug operations.
- *
- * Copyright (C) 2005-2007 Intel Corporation
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * Don't #include this file directly, read on!
- *
- * EXECUTING DEBUGGING ACTIONS OR NOT
- *
- * The main thing this framework provides is decission power to take a
- * debug action (like printing a message) if the current debug level
- * allows it.
- *
- * The decission power is at two levels: at compile-time (what does
- * not make it is compiled out) and at run-time. The run-time
- * selection is done per-submodule (as they are declared by the user
- * of the framework).
- *
- * A call to d_test(L) (L being the target debug level) returns true
- * if the action should be taken because the current debug levels
- * allow it (both compile and run time).
- *
- * It follows that a call to d_test() that can be determined to be
- * always false at compile time will get the code depending on it
- * compiled out by optimization.
- *
- * DEBUG LEVELS
- *
- * It is up to the caller to define how much a debugging level is.
- *
- * Convention sets 0 as "no debug" (so an action marked as debug level 0
- * will always be taken). The increasing debug levels are used for
- * increased verbosity.
- *
- * USAGE
- *
- * Group the code in modules and submodules inside each module [which
- * in most cases maps to Linux modules and .c files that compose
- * those].
- *
- * For each module, there is:
- *
- * - a MODULENAME (single word, legal C identifier)
- *
- * - a debug-levels.h header file that declares the list of
- * submodules and that is included by all .c files that use
- * the debugging tools. The file name can be anything.
- *
- * - some (optional) .c code to manipulate the runtime debug levels
- * through debugfs.
- *
- * The debug-levels.h file would look like:
- *
- * #ifndef __debug_levels__h__
- * #define __debug_levels__h__
- *
- * #define D_MODULENAME modulename
- * #define D_MASTER 10
- *
- * #include <linux/wimax/debug.h>
- *
- * enum d_module {
- * D_SUBMODULE_DECLARE(submodule_1),
- * D_SUBMODULE_DECLARE(submodule_2),
- * ...
- * D_SUBMODULE_DECLARE(submodule_N)
- * };
- *
- * #endif
- *
- * D_MASTER is the maximum compile-time debug level; any debug actions
- * above this will be out. D_MODULENAME is the module name (legal C
- * identifier), which has to be unique for each module (to avoid
- * namespace collisions during linkage). Note those #defines need to
- * be done before #including debug.h
- *
- * We declare N different submodules whose debug level can be
- * independently controlled during runtime.
- *
- * In a .c file of the module (and only in one of them), define the
- * following code:
- *
- * struct d_level D_LEVEL[] = {
- * D_SUBMODULE_DEFINE(submodule_1),
- * D_SUBMODULE_DEFINE(submodule_2),
- * ...
- * D_SUBMODULE_DEFINE(submodule_N),
- * };
- * size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
- *
- * Externs for d_level_MODULENAME and d_level_size_MODULENAME are used
- * and declared in this file using the D_LEVEL and D_LEVEL_SIZE macros
- * #defined also in this file.
- *
- * To manipulate from user space the levels, create a debugfs dentry
- * and then register each submodule with:
- *
- * d_level_register_debugfs("PREFIX_", submodule_X, parent);
- *
- * Where PREFIX_ is a name of your chosing. This will create debugfs
- * file with a single numeric value that can be use to tweak it. To
- * remove the entires, just use debugfs_remove_recursive() on 'parent'.
- *
- * NOTE: remember that even if this will show attached to some
- * particular instance of a device, the settings are *global*.
- *
- * On each submodule (for example, .c files), the debug infrastructure
- * should be included like this:
- *
- * #define D_SUBMODULE submodule_x // matches one in debug-levels.h
- * #include "debug-levels.h"
- *
- * after #including all your include files.
- *
- * Now you can use the d_*() macros below [d_test(), d_fnstart(),
- * d_fnend(), d_printf(), d_dump()].
- *
- * If their debug level is greater than D_MASTER, they will be
- * compiled out.
- *
- * If their debug level is lower or equal than D_MASTER but greater
- * than the current debug level of their submodule, they'll be
- * ignored.
- *
- * Otherwise, the action will be performed.
- */
-#ifndef __debug__h__
-#define __debug__h__
-
-#include <linux/types.h>
-#include <linux/slab.h>
-
-struct device;
-
-/* Backend stuff */
-
-/*
- * Debug backend: generate a message header from a 'struct device'
- *
- * @head: buffer where to place the header
- * @head_size: length of @head
- * @dev: pointer to device used to generate a header from. If NULL,
- * an empty ("") header is generated.
- */
-static inline
-void __d_head(char *head, size_t head_size,
- struct device *dev)
-{
- if (dev == NULL)
- head[0] = 0;
- else if ((unsigned long)dev < 4096) {
- printk(KERN_ERR "E: Corrupt dev %p\n", dev);
- WARN_ON(1);
- } else
- snprintf(head, head_size, "%s %s: ",
- dev_driver_string(dev), dev_name(dev));
-}
-
-
-/*
- * Debug backend: log some message if debugging is enabled
- *
- * @l: intended debug level
- * @tag: tag to prefix the message with
- * @dev: 'struct device' associated to this message
- * @f: printf-like format and arguments
- *
- * Note this is optimized out if it doesn't pass the compile-time
- * check; however, it is *always* compiled. This is useful to make
- * sure the printf-like formats and variables are always checked and
- * they don't get bit rot if you have all the debugging disabled.
- */
-#define _d_printf(l, tag, dev, f, a...) \
-do { \
- char head[64]; \
- if (!d_test(l)) \
- break; \
- __d_head(head, sizeof(head), dev); \
- printk(KERN_ERR "%s%s%s: " f, head, __func__, tag, ##a); \
-} while (0)
-
-
-/*
- * CPP syntactic sugar to generate A_B like symbol names when one of
- * the arguments is a preprocessor #define.
- */
-#define __D_PASTE__(varname, modulename) varname##_##modulename
-#define __D_PASTE(varname, modulename) (__D_PASTE__(varname, modulename))
-#define _D_SUBMODULE_INDEX(_name) (D_SUBMODULE_DECLARE(_name))
-
-
-/*
- * Store a submodule's runtime debug level and name
- */
-struct d_level {
- u8 level;
- const char *name;
-};
-
-
-/*
- * List of available submodules and their debug levels
- *
- * We call them d_level_MODULENAME and d_level_size_MODULENAME; the
- * macros D_LEVEL and D_LEVEL_SIZE contain the name already for
- * convenience.
- *
- * This array and the size are defined on some .c file that is part of
- * the current module.
- */
-#define D_LEVEL __D_PASTE(d_level, D_MODULENAME)
-#define D_LEVEL_SIZE __D_PASTE(d_level_size, D_MODULENAME)
-
-extern struct d_level D_LEVEL[];
-extern size_t D_LEVEL_SIZE;
-
-
-/*
- * Frontend stuff
- *
- *
- * Stuff you need to declare prior to using the actual "debug" actions
- * (defined below).
- */
-
-#ifndef D_MODULENAME
-#error D_MODULENAME is not defined in your debug-levels.h file
-/**
- * D_MODULE - Name of the current module
- *
- * #define in your module's debug-levels.h, making sure it is
- * unique. This has to be a legal C identifier.
- */
-#define D_MODULENAME undefined_modulename
-#endif
-
-
-#ifndef D_MASTER
-#warning D_MASTER not defined, but debug.h included! [see docs]
-/**
- * D_MASTER - Compile time maximum debug level
- *
- * #define in your debug-levels.h file to the maximum debug level the
- * runtime code will be allowed to have. This allows you to provide a
- * main knob.
- *
- * Anything above that level will be optimized out of the compile.
- *
- * Defaults to zero (no debug code compiled in).
- *
- * Maximum one definition per module (at the debug-levels.h file).
- */
-#define D_MASTER 0
-#endif
-
-#ifndef D_SUBMODULE
-#error D_SUBMODULE not defined, but debug.h included! [see docs]
-/**
- * D_SUBMODULE - Name of the current submodule
- *
- * #define in your submodule .c file before #including debug-levels.h
- * to the name of the current submodule as previously declared and
- * defined with D_SUBMODULE_DECLARE() (in your module's
- * debug-levels.h) and D_SUBMODULE_DEFINE().
- *
- * This is used to provide runtime-control over the debug levels.
- *
- * Maximum one per .c file! Can be shared among different .c files
- * (meaning they belong to the same submodule categorization).
- */
-#define D_SUBMODULE undefined_module
-#endif
-
-
-/**
- * D_SUBMODULE_DECLARE - Declare a submodule for runtime debug level control
- *
- * @_name: name of the submodule, restricted to the chars that make up a
- * valid C identifier ([a-zA-Z0-9_]).
- *
- * Declare in the module's debug-levels.h header file as:
- *
- * enum d_module {
- * D_SUBMODULE_DECLARE(submodule_1),
- * D_SUBMODULE_DECLARE(submodule_2),
- * D_SUBMODULE_DECLARE(submodule_3),
- * };
- *
- * Some corresponding .c file needs to have a matching
- * D_SUBMODULE_DEFINE().
- */
-#define D_SUBMODULE_DECLARE(_name) __D_SUBMODULE_##_name
-
-
-/**
- * D_SUBMODULE_DEFINE - Define a submodule for runtime debug level control
- *
- * @_name: name of the submodule, restricted to the chars that make up a
- * valid C identifier ([a-zA-Z0-9_]).
- *
- * Use once per module (in some .c file) as:
- *
- * static
- * struct d_level d_level_SUBMODULENAME[] = {
- * D_SUBMODULE_DEFINE(submodule_1),
- * D_SUBMODULE_DEFINE(submodule_2),
- * D_SUBMODULE_DEFINE(submodule_3),
- * };
- * size_t d_level_size_SUBDMODULENAME = ARRAY_SIZE(d_level_SUBDMODULENAME);
- *
- * Matching D_SUBMODULE_DECLARE()s have to be present in a
- * debug-levels.h header file.
- */
-#define D_SUBMODULE_DEFINE(_name) \
-[__D_SUBMODULE_##_name] = { \
- .level = 0, \
- .name = #_name \
-}
-
-
-
-/* The actual "debug" operations */
-
-
-/**
- * d_test - Returns true if debugging should be enabled
- *
- * @l: intended debug level (unsigned)
- *
- * If the master debug switch is enabled and the current settings are
- * higher or equal to the requested level, then debugging
- * output/actions should be enabled.
- *
- * NOTE:
- *
- * This needs to be coded so that it can be evaluated in compile
- * time; this is why the ugly BUG_ON() is placed in there, so the
- * D_MASTER evaluation compiles all out if it is compile-time false.
- */
-#define d_test(l) \
-({ \
- unsigned __l = l; /* type enforcer */ \
- (D_MASTER) >= __l \
- && ({ \
- BUG_ON(_D_SUBMODULE_INDEX(D_SUBMODULE) >= D_LEVEL_SIZE);\
- D_LEVEL[_D_SUBMODULE_INDEX(D_SUBMODULE)].level >= __l; \
- }); \
-})
-
-
-/**
- * d_fnstart - log message at function start if debugging enabled
- *
- * @l: intended debug level
- * @_dev: 'struct device' pointer, NULL if none (for context)
- * @f: printf-like format and arguments
- */
-#define d_fnstart(l, _dev, f, a...) _d_printf(l, " FNSTART", _dev, f, ## a)
-
-
-/**
- * d_fnend - log message at function end if debugging enabled
- *
- * @l: intended debug level
- * @_dev: 'struct device' pointer, NULL if none (for context)
- * @f: printf-like format and arguments
- */
-#define d_fnend(l, _dev, f, a...) _d_printf(l, " FNEND", _dev, f, ## a)
-
-
-/**
- * d_printf - log message if debugging enabled
- *
- * @l: intended debug level
- * @_dev: 'struct device' pointer, NULL if none (for context)
- * @f: printf-like format and arguments
- */
-#define d_printf(l, _dev, f, a...) _d_printf(l, "", _dev, f, ## a)
-
-
-/**
- * d_dump - log buffer hex dump if debugging enabled
- *
- * @l: intended debug level
- * @_dev: 'struct device' pointer, NULL if none (for context)
- * @f: printf-like format and arguments
- */
-#define d_dump(l, dev, ptr, size) \
-do { \
- char head[64]; \
- if (!d_test(l)) \
- break; \
- __d_head(head, sizeof(head), dev); \
- print_hex_dump(KERN_ERR, head, 0, 16, 1, \
- ((void *) ptr), (size), 0); \
-} while (0)
-
-
-/**
- * Export a submodule's debug level over debugfs as PREFIXSUBMODULE
- *
- * @prefix: string to prefix the name with
- * @submodule: name of submodule (not a string, just the name)
- * @dentry: debugfs parent dentry
- *
- * For removing, just use debugfs_remove_recursive() on the parent.
- */
-#define d_level_register_debugfs(prefix, name, parent) \
-({ \
- debugfs_create_u8( \
- prefix #name, 0600, parent, \
- &(D_LEVEL[__D_SUBMODULE_ ## name].level)); \
-})
-
-
-static inline
-void d_submodule_set(struct d_level *d_level, size_t d_level_size,
- const char *submodule, u8 level, const char *tag)
-{
- struct d_level *itr, *top;
- int index = -1;
-
- for (itr = d_level, top = itr + d_level_size; itr < top; itr++) {
- index++;
- if (itr->name == NULL) {
- printk(KERN_ERR "%s: itr->name NULL?? (%p, #%d)\n",
- tag, itr, index);
- continue;
- }
- if (!strcmp(itr->name, submodule)) {
- itr->level = level;
- return;
- }
- }
- printk(KERN_ERR "%s: unknown submodule %s\n", tag, submodule);
-}
-
-
-/**
- * d_parse_params - Parse a string with debug parameters from the
- * command line
- *
- * @d_level: level structure (D_LEVEL)
- * @d_level_size: number of items in the level structure
- * (D_LEVEL_SIZE).
- * @_params: string with the parameters; this is a space (not tab!)
- * separated list of NAME:VALUE, where value is the debug level
- * and NAME is the name of the submodule.
- * @tag: string for error messages (example: MODULE.ARGNAME).
- */
-static inline
-void d_parse_params(struct d_level *d_level, size_t d_level_size,
- const char *_params, const char *tag)
-{
- char submodule[130], *params, *params_orig, *token, *colon;
- unsigned level, tokens;
-
- if (_params == NULL)
- return;
- params_orig = kstrdup(_params, GFP_KERNEL);
- params = params_orig;
- while (1) {
- token = strsep(¶ms, " ");
- if (token == NULL)
- break;
- if (*token == '\0') /* eat joint spaces */
- continue;
- /* kernel's sscanf %s eats until whitespace, so we
- * replace : by \n so it doesn't get eaten later by
- * strsep */
- colon = strchr(token, ':');
- if (colon != NULL)
- *colon = '\n';
- tokens = sscanf(token, "%s\n%u", submodule, &level);
- if (colon != NULL)
- *colon = ':'; /* set back, for error messages */
- if (tokens == 2)
- d_submodule_set(d_level, d_level_size,
- submodule, level, tag);
- else
- printk(KERN_ERR "%s: can't parse '%s' as a "
- "SUBMODULE:LEVEL (%d tokens)\n",
- tag, token, tokens);
- }
- kfree(params_orig);
-}
-
-#endif /* #ifndef __debug__h__ */
struct netlink_ext_ack *newchain);
struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action,
struct tcf_chain *newchain);
+
+#ifdef CONFIG_INET
+DECLARE_STATIC_KEY_FALSE(tcf_frag_xmit_count);
+#endif
+
+int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb));
#endif /* CONFIG_NET_CLS_ACT */
static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
extern const struct bpf_func_proto bpf_sk_storage_get_proto;
extern const struct bpf_func_proto bpf_sk_storage_delete_proto;
+extern const struct bpf_func_proto bpf_sk_storage_get_tracing_proto;
+extern const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto;
struct bpf_local_storage_elem;
struct bpf_sk_storage_diag;
* Copyright (C) 2018-2020 Intel Corporation
*/
+#include <linux/ethtool.h>
#include <linux/netdevice.h>
#include <linux/debugfs.h>
#include <linux/list.h>
* @sae_pwd: password for SAE authentication (for devices supporting SAE
* offload)
* @sae_pwd_len: length of SAE password (for devices supporting SAE offload)
+ * @sae_pwe: The mechanisms allowed for SAE PWE derivation:
+ *
+ * NL80211_SAE_PWE_UNSPECIFIED
+ * Not-specified, used to indicate userspace did not specify any
+ * preference. The driver should follow its internal policy in
+ * such a scenario.
+ *
+ * NL80211_SAE_PWE_HUNT_AND_PECK
+ * Allow hunting-and-pecking loop only
+ *
+ * NL80211_SAE_PWE_HASH_TO_ELEMENT
+ * Allow hash-to-element only
+ *
+ * NL80211_SAE_PWE_BOTH
+ * Allow either hunting-and-pecking loop or hash-to-element
*/
struct cfg80211_crypto_settings {
u32 wpa_versions;
const u8 *psk;
const u8 *sae_pwd;
u8 sae_pwd_len;
+ enum nl80211_sae_pwe_mechanism sae_pwe;
};
/**
* @get_tx_power: store the current TX power into the dbm variable;
* return 0 if successful
*
- * @set_wds_peer: set the WDS peer for a WDS interface
- *
* @rfkill_poll: polls the hw rfkill line, use cfg80211 reporting
* functions to adjust rfkill hw state
*
int (*get_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev,
int *dbm);
- int (*set_wds_peer)(struct wiphy *wiphy, struct net_device *dev,
- const u8 *addr);
-
void (*rfkill_poll)(struct wiphy *wiphy);
#ifdef CONFIG_NL80211_TESTMODE
struct sock;
-#if defined(CONFIG_COMPAT)
-
#include <linux/compat.h>
struct compat_msghdr {
unsigned short rt_irtt; /* Initial RTT */
};
-#else /* defined(CONFIG_COMPAT) */
-/*
- * To avoid compiler warnings:
- */
-#define compat_msghdr msghdr
-#define compat_mmsghdr mmsghdr
-#endif /* defined(CONFIG_COMPAT) */
-
int __get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg,
struct sockaddr __user **save_addr, compat_uptr_t *ptr,
compat_size_t *len);
#include <net/flow_offload.h>
#include <uapi/linux/devlink.h>
#include <linux/xarray.h>
+#include <linux/firmware.h>
#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \
(__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX)
/**
* struct devlink_flash_update_params - Flash Update parameters
- * @file_name: the name of the flash firmware file to update from
+ * @fw: pointer to the firmware data to update from
* @component: the flash component to update
*
- * With the exception of file_name, drivers must opt-in to parameters by
+ * With the exception of fw, drivers must opt-in to parameters by
* setting the appropriate bit in the supported_flash_update_params field in
* their devlink_ops structure.
*/
struct devlink_flash_update_params {
- const char *file_name;
+ const struct firmware *fw;
const char *component;
u32 overwrite_mask;
};
DEVLINK_TRAP_GENERIC_ID_DCCP_PARSING,
DEVLINK_TRAP_GENERIC_ID_GTP_PARSING,
DEVLINK_TRAP_GENERIC_ID_ESP_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_NEXTHOP,
/* Add new generic trap IDs above */
__DEVLINK_TRAP_GENERIC_ID_MAX,
"gtp_parsing"
#define DEVLINK_TRAP_GENERIC_NAME_ESP_PARSING \
"esp_parsing"
-
+#define DEVLINK_TRAP_GENERIC_NAME_BLACKHOLE_NEXTHOP \
+ "blackhole_nexthop"
#define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \
"l2_drops"
enum devlink_reload_limit limit,
u32 actions_performed);
-void devlink_flash_update_begin_notify(struct devlink *devlink);
-void devlink_flash_update_end_notify(struct devlink *devlink);
void devlink_flash_update_status_notify(struct devlink *devlink,
const char *status_msg,
const char *component,
#define DSA_TAG_PROTO_OCELOT_VALUE 15
#define DSA_TAG_PROTO_AR9331_VALUE 16
#define DSA_TAG_PROTO_RTL4_A_VALUE 17
+#define DSA_TAG_PROTO_HELLCREEK_VALUE 18
enum dsa_tag_protocol {
DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE,
DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE,
DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE,
DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE,
+ DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE,
};
struct packet_type;
void (*get_regs)(struct dsa_switch *ds, int port,
struct ethtool_regs *regs, void *p);
+ /*
+ * Upper device tracking.
+ */
+ int (*port_prechangeupper)(struct dsa_switch *ds, int port,
+ struct netdev_notifier_changeupper_info *info);
+
/*
* Bridge integration
*/
static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst,
struct sk_buff *skb)
{
- struct neighbour *n = NULL;
+ struct neighbour *n;
- /* The packets from tunnel devices (eg bareudp) may have only
- * metadata in the dst pointer of skb. Hence a pointer check of
- * neigh_lookup is needed.
- */
- if (dst->ops->neigh_lookup)
- n = dst->ops->neigh_lookup(dst, skb, NULL);
+ if (WARN_ON_ONCE(!dst->ops->neigh_lookup))
+ return NULL;
+
+ n = dst->ops->neigh_lookup(dst, skb, NULL);
return IS_ERR(n) ? NULL : n;
}
IEEE80211_RADIOTAP_F_TX_RTS = 0x0004,
IEEE80211_RADIOTAP_F_TX_NOACK = 0x0008,
IEEE80211_RADIOTAP_F_TX_NOSEQNO = 0x0010,
+ IEEE80211_RADIOTAP_F_TX_ORDER = 0x0020,
};
/* for IEEE80211_RADIOTAP_MCS "have" flags */
#define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb))
/* return enslaved device index if relevant */
-static inline int inet_sdif(struct sk_buff *skb)
+static inline int inet_sdif(const struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
if (skb && ipv4_l3mdev_skb(IPCB(skb)->flags))
int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict);
int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
-void ip_tunnel_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot);
struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
int link, __be16 flags,
__be32 remote, __be32 local,
* nontransmitted BSSIDs
* @profile_periodicity: the least number of beacon frames need to be received
* in order to discover all the nontransmitted BSSIDs in the set.
- * @he_oper: HE operation information of the AP we are connected to
+ * @he_oper: HE operation information of the BSS (AP/Mesh) or of the AP we are
+ * connected to (STA)
* @he_obss_pd: OBSS Packet Detection parameters.
* @he_bss_color: BSS coloring settings, if BSS supports HE
* @fils_discovery: FILS discovery configuration
* it can be sent out.
* @IEEE80211_TX_CTRL_NO_SEQNO: Do not overwrite the sequence number that
* has already been assigned to this frame.
+ * @IEEE80211_TX_CTRL_DONT_REORDER: This frame should not be reordered
+ * relative to other frames that have this flag set, independent
+ * of their QoS TID or other priority field values.
*
* These flags are used in tx_info->control.flags.
*/
IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP = BIT(5),
IEEE80211_TX_INTCFL_NEED_TXPROCESSING = BIT(6),
IEEE80211_TX_CTRL_NO_SEQNO = BIT(7),
+ IEEE80211_TX_CTRL_DONT_REORDER = BIT(8),
};
/*
use_ack:1,
ack64:1,
mpc_map:1,
- __unused:2;
+ frozen:1,
+ __unused:1;
/* one byte hole */
};
struct mptcp_out_options *opts);
void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
-void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts);
+void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
+ struct mptcp_out_options *opts);
/* move the skb extension owership, with the assumption that 'to' is
* newly allocated
from->active_extensions = 0;
}
+static inline void mptcp_skb_ext_copy(struct sk_buff *to,
+ struct sk_buff *from)
+{
+ struct mptcp_ext *from_ext;
+
+ from_ext = skb_ext_find(from, SKB_EXT_MPTCP);
+ if (!from_ext)
+ return;
+
+ from_ext->frozen = 1;
+ skb_ext_copy(to, from);
+}
+
static inline bool mptcp_ext_matches(const struct mptcp_ext *to_ext,
const struct mptcp_ext *from_ext)
{
{
}
+static inline void mptcp_skb_ext_copy(struct sk_buff *to,
+ struct sk_buff *from)
+{
+}
+
static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
const struct sk_buff *from)
{
void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb,
const struct tcphdr *oth);
+struct sk_buff *nf_reject_skb_v4_unreach(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook, u8 code);
+struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook);
+
+
#endif /* _IPV4_NF_REJECT_H */
const struct sk_buff *oldskb,
const struct tcphdr *oth, unsigned int otcplen);
+struct sk_buff *nf_reject_skb_v6_tcp_reset(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook);
+struct sk_buff *nf_reject_skb_v6_unreach(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook, u8 code);
+
#endif /* _IPV6_NF_REJECT_H */
{
return &net->ct.nf_ct_proto.icmpv6;
}
+
+/* Caller must check nf_ct_protonum(ct) is IPPROTO_TCP before calling. */
+static inline void nf_ct_set_tcp_be_liberal(struct nf_conn *ct)
+{
+ ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
+ ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
+}
+
+/* Caller must check nf_ct_protonum(ct) is IPPROTO_TCP before calling. */
+static inline bool nf_conntrack_tcp_established(const struct nf_conn *ct)
+{
+ return ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED &&
+ test_bit(IPS_ASSURED_BIT, &ct->status);
+}
#endif
#ifdef CONFIG_NF_CT_PROTO_DCCP
* Attribute Misc:
* nla_memcpy(dest, nla, count) copy attribute into memory
* nla_memcmp(nla, data, size) compare attribute with memory area
- * nla_strlcpy(dst, nla, size) copy attribute to a sized string
+ * nla_strscpy(dst, nla, size) copy attribute to a sized string
* nla_strcmp(nla, str) compare attribute with string
*
* Attribute Parsing:
struct netlink_ext_ack *extack);
int nla_policy_len(const struct nla_policy *, int);
struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype);
-size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize);
+ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize);
char *nla_strdup(const struct nlattr *nla, gfp_t flags);
int nla_memcpy(void *dest, const struct nlattr *src, int count);
int nla_memcmp(const struct nlattr *nla, const void *data, size_t size);
*/
struct sock *ctl_sock;
+ /* UDP tunneling listening sock. */
+ struct sock *udp4_sock;
+ struct sock *udp6_sock;
+ /* UDP tunneling listening port. */
+ int udp_port;
+ /* UDP tunneling remote encap port. */
+ int encap_port;
+
/* This is the global local address list.
* We actively maintain this complete list of addresses on
* the system by catching address add/delete events.
};
enum nexthop_event_type {
- NEXTHOP_EVENT_DEL
+ NEXTHOP_EVENT_DEL,
+ NEXTHOP_EVENT_REPLACE,
};
-int register_nexthop_notifier(struct net *net, struct notifier_block *nb);
+struct nh_notifier_single_info {
+ struct net_device *dev;
+ u8 gw_family;
+ union {
+ __be32 ipv4;
+ struct in6_addr ipv6;
+ };
+ u8 is_reject:1,
+ is_fdb:1,
+ has_encap:1;
+};
+
+struct nh_notifier_grp_entry_info {
+ u8 weight;
+ u32 id;
+ struct nh_notifier_single_info nh;
+};
+
+struct nh_notifier_grp_info {
+ u16 num_nh;
+ bool is_fdb;
+ struct nh_notifier_grp_entry_info nh_entries[];
+};
+
+struct nh_notifier_info {
+ struct net *net;
+ struct netlink_ext_ack *extack;
+ u32 id;
+ bool is_grp;
+ union {
+ struct nh_notifier_single_info *nh;
+ struct nh_notifier_grp_info *nh_grp;
+ };
+};
+
+int register_nexthop_notifier(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack);
int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb);
+void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap);
/* caller is holding rcu or rtnl; no reference taken to nexthop */
struct nexthop *nexthop_find_by_id(struct net *net, u32 id);
void page_pool_destroy(struct page_pool *pool);
void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *));
void page_pool_release_page(struct page_pool *pool, struct page *page);
+void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+ int count);
#else
static inline void page_pool_destroy(struct page_pool *pool)
{
struct page *page)
{
}
+
+static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+ int count)
+{
+}
#endif
void page_pool_put_page(struct page_pool *pool, struct page *page,
if (unlikely(pool->p.nid != new_nid))
page_pool_update_nid(pool, new_nid);
}
+
+static inline void page_pool_ring_lock(struct page_pool *pool)
+ __acquires(&pool->ring.producer_lock)
+{
+ if (in_serving_softirq())
+ spin_lock(&pool->ring.producer_lock);
+ else
+ spin_lock_bh(&pool->ring.producer_lock);
+}
+
+static inline void page_pool_ring_unlock(struct page_pool *pool)
+ __releases(&pool->ring.producer_lock)
+{
+ if (in_serving_softirq())
+ spin_unlock(&pool->ring.producer_lock);
+ else
+ spin_unlock_bh(&pool->ring.producer_lock);
+}
+
#endif /* _NET_PAGE_POOL_H */
struct tcf_chain *tcf_get_next_chain(struct tcf_block *block,
struct tcf_chain *chain);
struct tcf_proto *tcf_get_next_proto(struct tcf_chain *chain,
- struct tcf_proto *tp, bool rtnl_held);
+ struct tcf_proto *tp);
void tcf_block_netif_keep_dst(struct tcf_block *block);
int tcf_block_get(struct tcf_block **p_block,
struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
char indev[IFNAMSIZ];
struct net_device *dev;
- if (nla_strlcpy(indev, indev_tlv, IFNAMSIZ) >= IFNAMSIZ) {
+ if (nla_strscpy(indev, indev_tlv, IFNAMSIZ) < 0) {
NL_SET_ERR_MSG_ATTR(extack, indev_tlv,
"Interface name too long");
return -EINVAL;
return &q->privdata;
}
+static inline struct Qdisc *qdisc_from_priv(void *priv)
+{
+ return container_of(priv, struct Qdisc, privdata);
+}
+
/*
Timer resolution MUST BE < 10% of min_schedulable_packet_size/bandwidth
void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp,
struct tcf_block *block);
-static inline int skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res)
-{
- return res->ingress ? netif_receive_skb(skb) : dev_queue_xmit(skb);
-}
+int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb));
#endif
* functions simpler to write.
*/
+#define SCTP_DEFAULT_UDP_PORT 9899 /* default UDP tunneling port */
+
/* These are the values for pf exposure, UNUSED is to keep compatible with old
* applications by default.
*/
struct sctp_pf *sctp_get_pf_specific(sa_family_t family);
int sctp_register_pf(struct sctp_pf *, sa_family_t);
void sctp_addr_wq_mgmt(struct net *, struct sctp_sockaddr_entry *, int);
+int sctp_udp_sock_start(struct net *net);
+void sctp_udp_sock_stop(struct net *net);
/*
* sctp/socket.c
{
__u32 overhead = sizeof(struct sctphdr) + extra;
- if (sp)
+ if (sp) {
overhead += sp->pf->af->net_header_len;
- else
+ if (sp->udp_port)
+ overhead += sizeof(struct udphdr);
+ } else {
overhead += sizeof(struct ipv6hdr);
+ }
if (WARN_ON_ONCE(mtu && mtu <= overhead))
mtu = overhead;
struct sctp_chunk *sctp_make_violation_max_retrans(
const struct sctp_association *asoc,
const struct sctp_chunk *chunk);
+struct sctp_chunk *sctp_make_new_encap_port(
+ const struct sctp_association *asoc,
+ const struct sctp_chunk *chunk);
struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc,
const struct sctp_transport *transport);
struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc,
if (ntohl(chunk->sctp_hdr->vtag) == asoc->c.my_vtag)
return 1;
+ chunk->transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port;
return 0;
}
*/
__u32 hbinterval;
+ __be16 udp_port;
+ __be16 encap_port;
+
/* This is the max_retrans value for new associations. */
__u16 pathmaxrxt;
*/
unsigned long last_time_ecne_reduced;
+ __be16 encap_port;
+
/* This is the max_retrans value for the transport and will
* be initialized from the assocs value. This can be changed
* using the SCTP_SET_PEER_ADDR_PARAMS socket option.
*/
struct sctp_input_cb {
union {
- struct inet_skb_parm h4;
+ struct inet_skb_parm h4;
#if IS_ENABLED(CONFIG_IPV6)
- struct inet6_skb_parm h6;
+ struct inet6_skb_parm h6;
#endif
} header;
struct sctp_chunk *chunk;
struct sctp_af *af;
+ __be16 encap_port;
};
#define SCTP_INPUT_CB(__skb) ((struct sctp_input_cb *)&((__skb)->cb[0]))
*/
unsigned long hbinterval;
+ __be16 encap_port;
+
/* This is the max_retrans value for new transports in the
* association.
*/
#include <linux/rculist_nulls.h>
#include <linux/poll.h>
#include <linux/sockptr.h>
-
+#include <linux/indirect_call_wrapper.h>
#include <linux/atomic.h>
#include <linux/refcount.h>
#include <net/dst.h>
#define sk_refcnt_debug_release(sk) do { } while (0)
#endif /* SOCK_REFCNT_DEBUG */
+INDIRECT_CALLABLE_DECLARE(bool tcp_stream_memory_free(const struct sock *sk, int wake));
+
static inline bool __sk_stream_memory_free(const struct sock *sk, int wake)
{
if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf))
return false;
+#ifdef CONFIG_INET
+ return sk->sk_prot->stream_memory_free ?
+ INDIRECT_CALL_1(sk->sk_prot->stream_memory_free,
+ tcp_stream_memory_free,
+ sk, wake) : true;
+#else
return sk->sk_prot->stream_memory_free ?
sk->sk_prot->stream_memory_free(sk, wake) : true;
+#endif
}
static inline bool sk_stream_memory_free(const struct sock *sk)
lock_sock_nested(sk, 0);
}
+void __lock_sock(struct sock *sk);
void __release_sock(struct sock *sk);
void release_sock(struct sock *sk);
SINGLE_DEPTH_NESTING)
#define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock))
-bool lock_sock_fast(struct sock *sk);
+bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock);
+
/**
* unlock_sock_fast - complement of lock_sock_fast
* @sk: socket
* If slow mode is on, we call regular release_sock()
*/
static inline void unlock_sock_fast(struct sock *sk, bool slow)
+ __releases(&sk->sk_lock.slock)
{
- if (slow)
+ if (slow) {
release_sock(sk);
- else
+ __release(&sk->sk_lock.slock);
+ } else {
spin_unlock_bh(&sk->sk_lock.slock);
+ }
}
/* Used by processes to "lock" a socket state, so that
SWITCHDEV_ATTR_ID_PORT_MROUTER,
SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME,
SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING,
+ SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL,
SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED,
SWITCHDEV_ATTR_ID_BRIDGE_MROUTER,
#if IS_ENABLED(CONFIG_BRIDGE_MRP)
bool mrouter; /* PORT_MROUTER */
clock_t ageing_time; /* BRIDGE_AGEING_TIME */
bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */
+ u16 vlan_protocol; /* BRIDGE_VLAN_PROTOCOL */
bool mc_disabled; /* MC_DISABLED */
#if IS_ENABLED(CONFIG_BRIDGE_MRP)
u8 mrp_port_state; /* MRP_PORT_STATE */
int tcp_v4_early_demux(struct sk_buff *skb);
int tcp_v4_rcv(struct sk_buff *skb);
+void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb);
int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size);
int flags);
int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,
size_t size, int flags);
+struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags,
+ struct page *page, int offset, size_t *size);
ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
size_t size, int flags);
int tcp_send_mss(struct sock *sk, int *size_goal, int flags);
int tcp_child_process(struct sock *parent, struct sock *child,
struct sk_buff *skb);
void tcp_enter_loss(struct sock *sk);
-void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag);
+void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag);
void tcp_clear_retrans(struct tcp_sock *tp);
void tcp_update_metrics(struct sock *sk);
void tcp_init_metrics(struct sock *sk);
void tcp_metrics_init(void);
bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
+void __tcp_close(struct sock *sk, long timeout);
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, struct sk_buff *skb);
return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat;
}
-/* @wake is one when sk_stream_write_space() calls us.
- * This sends EPOLLOUT only if notsent_bytes is half the limit.
- * This mimics the strategy used in sock_def_write_space().
- */
-static inline bool tcp_stream_memory_free(const struct sock *sk, int wake)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
- u32 notsent_bytes = READ_ONCE(tp->write_seq) -
- READ_ONCE(tp->snd_nxt);
-
- return (notsent_bytes << wake) < tcp_notsent_lowat(tp);
-}
+bool tcp_stream_memory_free(const struct sock *sk, int wake);
#ifdef CONFIG_PROC_FS
int tcp4_proc_init(void);
const struct sock *sk,
const struct sk_buff *skb);
#endif
- void (*init_req)(struct request_sock *req,
- const struct sock *sk_listener,
- struct sk_buff *skb);
#ifdef CONFIG_SYN_COOKIES
__u32 (*cookie_init_seq)(const struct sk_buff *skb,
__u16 *mss);
#endif
- struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl,
- const struct request_sock *req);
+ struct dst_entry *(*route_req)(const struct sock *sk,
+ struct sk_buff *skb,
+ struct flowi *fl,
+ struct request_sock *req);
u32 (*init_seq)(const struct sk_buff *skb);
u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb);
int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
union {
struct tls12_crypto_info_aes_gcm_128 aes_gcm_128;
struct tls12_crypto_info_aes_gcm_256 aes_gcm_256;
+ struct tls12_crypto_info_chacha20_poly1305 chacha20_poly1305;
};
};
if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size))
tls_err_abort(sk, EBADMSG);
- if (prot->version != TLS_1_3_VERSION)
- tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+ if (prot->version != TLS_1_3_VERSION &&
+ prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305)
+ tls_bigint_increment(ctx->iv + prot->salt_size,
prot->iv_size);
}
static inline void tls_fill_prepend(struct tls_context *ctx,
char *buf,
size_t plaintext_len,
- unsigned char record_type,
- int version)
+ unsigned char record_type)
{
struct tls_prot_info *prot = &ctx->prot_info;
size_t pkt_len, iv_size = prot->iv_size;
pkt_len = plaintext_len + prot->tag_size;
- if (version != TLS_1_3_VERSION) {
+ if (prot->version != TLS_1_3_VERSION &&
+ prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) {
pkt_len += iv_size;
memcpy(buf + TLS_NONCE_OFFSET,
- ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size);
+ ctx->tx.iv + prot->salt_size, iv_size);
}
/* we cover nonce explicit here as well, so buf should be of
* size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE
*/
- buf[0] = version == TLS_1_3_VERSION ?
+ buf[0] = prot->version == TLS_1_3_VERSION ?
TLS_RECORD_TYPE_DATA : record_type;
/* Note that VERSION must be TLS_1_2 for both TLS1.2 and TLS1.3 */
buf[1] = TLS_1_2_VERSION_MINOR;
static inline void tls_make_aad(char *buf,
size_t size,
char *record_sequence,
- int record_sequence_size,
unsigned char record_type,
- int version)
+ struct tls_prot_info *prot)
{
- if (version != TLS_1_3_VERSION) {
- memcpy(buf, record_sequence, record_sequence_size);
+ if (prot->version != TLS_1_3_VERSION) {
+ memcpy(buf, record_sequence, prot->rec_seq_size);
buf += 8;
} else {
- size += TLS_CIPHER_AES_GCM_128_TAG_SIZE;
+ size += prot->tag_size;
}
- buf[0] = version == TLS_1_3_VERSION ?
+ buf[0] = prot->version == TLS_1_3_VERSION ?
TLS_RECORD_TYPE_DATA : record_type;
buf[1] = TLS_1_2_VERSION_MAJOR;
buf[2] = TLS_1_2_VERSION_MINOR;
buf[4] = size & 0xFF;
}
-static inline void xor_iv_with_seq(int version, char *iv, char *seq)
+static inline void xor_iv_with_seq(struct tls_prot_info *prot, char *iv, char *seq)
{
int i;
- if (version == TLS_1_3_VERSION) {
+ if (prot->version == TLS_1_3_VERSION ||
+ prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305) {
for (i = 0; i < 8; i++)
iv[i + 4] ^= seq[i];
}
UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr);
}
-typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport,
+typedef struct sock *(*udp_lookup_t)(const struct sk_buff *skb, __be16 sport,
__be16 dport);
INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *,
struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
__be32 daddr, __be16 dport, int dif, int sdif,
struct udp_table *tbl, struct sk_buff *skb);
-struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
+struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport);
struct sock *udp6_lib_lookup(struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport,
int dif, int sdif, struct udp_table *tbl,
struct sk_buff *skb);
-struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
+struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport);
/* UDP uses skb->dev_scratch to cache as much information as possible and avoid
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Linux WiMAX
- * Kernel space API for accessing WiMAX devices
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * The WiMAX stack provides an API for controlling and managing the
- * system's WiMAX devices. This API affects the control plane; the
- * data plane is accessed via the network stack (netdev).
- *
- * Parts of the WiMAX stack API and notifications are exported to
- * user space via Generic Netlink. In user space, libwimax (part of
- * the wimax-tools package) provides a shim layer for accessing those
- * calls.
- *
- * The API is standarized for all WiMAX devices and different drivers
- * implement the backend support for it. However, device-specific
- * messaging pipes are provided that can be used to issue commands and
- * receive notifications in free form.
- *
- * Currently the messaging pipes are the only means of control as it
- * is not known (due to the lack of more devices in the market) what
- * will be a good abstraction layer. Expect this to change as more
- * devices show in the market. This API is designed to be growable in
- * order to address this problem.
- *
- * USAGE
- *
- * Embed a `struct wimax_dev` at the beginning of the device's
- * private structure, initialize and register it. For details, see
- * `struct wimax_dev`s documentation.
- *
- * Once this is done, wimax-tools's libwimaxll can be used to
- * communicate with the driver from user space. You user space
- * application does not have to forcibily use libwimaxll and can talk
- * the generic netlink protocol directly if desired.
- *
- * Remember this is a very low level API that will to provide all of
- * WiMAX features. Other daemons and services running in user space
- * are the expected clients of it. They offer a higher level API that
- * applications should use (an example of this is the Intel's WiMAX
- * Network Service for the i2400m).
- *
- * DESIGN
- *
- * Although not set on final stone, this very basic interface is
- * mostly completed. Remember this is meant to grow as new common
- * operations are decided upon. New operations will be added to the
- * interface, intent being on keeping backwards compatibility as much
- * as possible.
- *
- * This layer implements a set of calls to control a WiMAX device,
- * exposing a frontend to the rest of the kernel and user space (via
- * generic netlink) and a backend implementation in the driver through
- * function pointers.
- *
- * WiMAX devices have a state, and a kernel-only API allows the
- * drivers to manipulate that state. State transitions are atomic, and
- * only some of them are allowed (see `enum wimax_st`).
- *
- * Most API calls will set the state automatically; in most cases
- * drivers have to only report state changes due to external
- * conditions.
- *
- * All API operations are 'atomic', serialized through a mutex in the
- * `struct wimax_dev`.
- *
- * EXPORTING TO USER SPACE THROUGH GENERIC NETLINK
- *
- * The API is exported to user space using generic netlink (other
- * methods can be added as needed).
- *
- * There is a Generic Netlink Family named "WiMAX", where interfaces
- * supporting the WiMAX interface receive commands and broadcast their
- * signals over a multicast group named "msg".
- *
- * Mapping to the source/destination interface is done by an interface
- * index attribute.
- *
- * For user-to-kernel traffic (commands) we use a function call
- * marshalling mechanism, where a message X with attributes A, B, C
- * sent from user space to kernel space means executing the WiMAX API
- * call wimax_X(A, B, C), sending the results back as a message.
- *
- * Kernel-to-user (notifications or signals) communication is sent
- * over multicast groups. This allows to have multiple applications
- * monitoring them.
- *
- * Each command/signal gets assigned it's own attribute policy. This
- * way the validator will verify that all the attributes in there are
- * only the ones that should be for each command/signal. Thing of an
- * attribute mapping to a type+argumentname for each command/signal.
- *
- * If we had a single policy for *all* commands/signals, after running
- * the validator we'd have to check "does this attribute belong in
- * here"? for each one. It can be done manually, but it's just easier
- * to have the validator do that job with multiple policies. As well,
- * it makes it easier to later expand each command/signal signature
- * without affecting others and keeping the namespace more or less
- * sane. Not that it is too complicated, but it makes it even easier.
- *
- * No state information is maintained in the kernel for each user
- * space connection (the connection is stateless).
- *
- * TESTING FOR THE INTERFACE AND VERSIONING
- *
- * If network interface X is a WiMAX device, there will be a Generic
- * Netlink family named "WiMAX X" and the device will present a
- * "wimax" directory in it's network sysfs directory
- * (/sys/class/net/DEVICE/wimax) [used by HAL].
- *
- * The inexistence of any of these means the device does not support
- * this WiMAX API.
- *
- * By querying the generic netlink controller, versioning information
- * and the multicast groups available can be found. Applications using
- * the interface can either rely on that or use the generic netlink
- * controller to figure out which generic netlink commands/signals are
- * supported.
- *
- * NOTE: this versioning is a last resort to avoid hard
- * incompatibilities. It is the intention of the design of this
- * stack not to introduce backward incompatible changes.
- *
- * The version code has to fit in one byte (restrictions imposed by
- * generic netlink); we use `version / 10` for the major version and
- * `version % 10` for the minor. This gives 9 minors for each major
- * and 25 majors.
- *
- * The version change protocol is as follow:
- *
- * - Major versions: needs to be increased if an existing message/API
- * call is changed or removed. Doesn't need to be changed if a new
- * message is added.
- *
- * - Minor version: needs to be increased if new messages/API calls are
- * being added or some other consideration that doesn't impact the
- * user-kernel interface too much (like some kind of bug fix) and
- * that is kind of left up in the air to common sense.
- *
- * User space code should not try to work if the major version it was
- * compiled for differs from what the kernel offers. As well, if the
- * minor version of the kernel interface is lower than the one user
- * space is expecting (the one it was compiled for), the kernel
- * might be missing API calls; user space shall be ready to handle
- * said condition. Use the generic netlink controller operations to
- * find which ones are supported and which not.
- *
- * libwimaxll:wimaxll_open() takes care of checking versions.
- *
- * THE OPERATIONS:
- *
- * Each operation is defined in its on file (drivers/net/wimax/op-*.c)
- * for clarity. The parts needed for an operation are:
- *
- * - a function pointer in `struct wimax_dev`: optional, as the
- * operation might be implemented by the stack and not by the
- * driver.
- *
- * All function pointers are named wimax_dev->op_*(), and drivers
- * must implement them except where noted otherwise.
- *
- * - When exported to user space, a `struct nla_policy` to define the
- * attributes of the generic netlink command and a `struct genl_ops`
- * to define the operation.
- *
- * All the declarations for the operation codes (WIMAX_GNL_OP_<NAME>)
- * and generic netlink attributes (WIMAX_GNL_<NAME>_*) are declared in
- * include/linux/wimax.h; this file is intended to be cloned by user
- * space to gain access to those declarations.
- *
- * A few caveats to remember:
- *
- * - Need to define attribute numbers starting in 1; otherwise it
- * fails.
- *
- * - the `struct genl_family` requires a maximum attribute id; when
- * defining the `struct nla_policy` for each message, it has to have
- * an array size of WIMAX_GNL_ATTR_MAX+1.
- *
- * The op_*() function pointers will not be called if the wimax_dev is
- * in a state <= %WIMAX_ST_UNINITIALIZED. The exception is:
- *
- * - op_reset: can be called at any time after wimax_dev_add() has
- * been called.
- *
- * THE PIPE INTERFACE:
- *
- * This interface is kept intentionally simple. The driver can send
- * and receive free-form messages to/from user space through a
- * pipe. See drivers/net/wimax/op-msg.c for details.
- *
- * The kernel-to-user messages are sent with
- * wimax_msg(). user-to-kernel messages are delivered via
- * wimax_dev->op_msg_from_user().
- *
- * RFKILL:
- *
- * RFKILL support is built into the wimax_dev layer; the driver just
- * needs to call wimax_report_rfkill_{hw,sw}() to inform of changes in
- * the hardware or software RF kill switches. When the stack wants to
- * turn the radio off, it will call wimax_dev->op_rfkill_sw_toggle(),
- * which the driver implements.
- *
- * User space can set the software RF Kill switch by calling
- * wimax_rfkill().
- *
- * The code for now only supports devices that don't require polling;
- * If the device needs to be polled, create a self-rearming delayed
- * work struct for polling or look into adding polled support to the
- * WiMAX stack.
- *
- * When initializing the hardware (_probe), after calling
- * wimax_dev_add(), query the device for it's RF Kill switches status
- * and feed it back to the WiMAX stack using
- * wimax_report_rfkill_{hw,sw}(). If any switch is missing, always
- * report it as ON.
- *
- * NOTE: the wimax stack uses an inverted terminology to that of the
- * RFKILL subsystem:
- *
- * - ON: radio is ON, RFKILL is DISABLED or OFF.
- * - OFF: radio is OFF, RFKILL is ENABLED or ON.
- *
- * MISCELLANEOUS OPS:
- *
- * wimax_reset() can be used to reset the device to power on state; by
- * default it issues a warm reset that maintains the same device
- * node. If that is not possible, it falls back to a cold reset
- * (device reconnect). The driver implements the backend to this
- * through wimax_dev->op_reset().
- */
-
-#ifndef __NET__WIMAX_H__
-#define __NET__WIMAX_H__
-
-#include <linux/wimax.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-
-struct net_device;
-struct genl_info;
-struct wimax_dev;
-
-/**
- * struct wimax_dev - Generic WiMAX device
- *
- * @net_dev: [fill] Pointer to the &struct net_device this WiMAX
- * device implements.
- *
- * @op_msg_from_user: [fill] Driver-specific operation to
- * handle a raw message from user space to the driver. The
- * driver can send messages to user space using with
- * wimax_msg_to_user().
- *
- * @op_rfkill_sw_toggle: [fill] Driver-specific operation to act on
- * userspace (or any other agent) requesting the WiMAX device to
- * change the RF Kill software switch (WIMAX_RF_ON or
- * WIMAX_RF_OFF).
- * If such hardware support is not present, it is assumed the
- * radio cannot be switched off and it is always on (and the stack
- * will error out when trying to switch it off). In such case,
- * this function pointer can be left as NULL.
- *
- * @op_reset: [fill] Driver specific operation to reset the
- * device.
- * This operation should always attempt first a warm reset that
- * does not disconnect the device from the bus and return 0.
- * If that fails, it should resort to some sort of cold or bus
- * reset (even if it implies a bus disconnection and device
- * disappearance). In that case, -ENODEV should be returned to
- * indicate the device is gone.
- * This operation has to be synchronous, and return only when the
- * reset is complete. In case of having had to resort to bus/cold
- * reset implying a device disconnection, the call is allowed to
- * return immediately.
- * NOTE: wimax_dev->mutex is NOT locked when this op is being
- * called; however, wimax_dev->mutex_reset IS locked to ensure
- * serialization of calls to wimax_reset().
- * See wimax_reset()'s documentation.
- *
- * @name: [fill] A way to identify this device. We need to register a
- * name with many subsystems (rfkill, workqueue creation, etc).
- * We can't use the network device name as that
- * might change and in some instances we don't know it yet (until
- * we don't call register_netdev()). So we generate an unique one
- * using the driver name and device bus id, place it here and use
- * it across the board. Recommended naming:
- * DRIVERNAME-BUSNAME:BUSID (dev->bus->name, dev->bus_id).
- *
- * @id_table_node: [private] link to the list of wimax devices kept by
- * id-table.c. Protected by it's own spinlock.
- *
- * @mutex: [private] Serializes all concurrent access and execution of
- * operations.
- *
- * @mutex_reset: [private] Serializes reset operations. Needs to be a
- * different mutex because as part of the reset operation, the
- * driver has to call back into the stack to do things such as
- * state change, that require wimax_dev->mutex.
- *
- * @state: [private] Current state of the WiMAX device.
- *
- * @rfkill: [private] integration into the RF-Kill infrastructure.
- *
- * @rf_sw: [private] State of the software radio switch (OFF/ON)
- *
- * @rf_hw: [private] State of the hardware radio switch (OFF/ON)
- *
- * @debugfs_dentry: [private] Used to hook up a debugfs entry. This
- * shows up in the debugfs root as wimax\:DEVICENAME.
- *
- * Description:
- * This structure defines a common interface to access all WiMAX
- * devices from different vendors and provides a common API as well as
- * a free-form device-specific messaging channel.
- *
- * Usage:
- * 1. Embed a &struct wimax_dev at *the beginning* the network
- * device structure so that netdev_priv() points to it.
- *
- * 2. memset() it to zero
- *
- * 3. Initialize with wimax_dev_init(). This will leave the WiMAX
- * device in the %__WIMAX_ST_NULL state.
- *
- * 4. Fill all the fields marked with [fill]; once called
- * wimax_dev_add(), those fields CANNOT be modified.
- *
- * 5. Call wimax_dev_add() *after* registering the network
- * device. This will leave the WiMAX device in the %WIMAX_ST_DOWN
- * state.
- * Protect the driver's net_device->open() against succeeding if
- * the wimax device state is lower than %WIMAX_ST_DOWN.
- *
- * 6. Select when the device is going to be turned on/initialized;
- * for example, it could be initialized on 'ifconfig up' (when the
- * netdev op 'open()' is called on the driver).
- *
- * When the device is initialized (at `ifconfig up` time, or right
- * after calling wimax_dev_add() from _probe(), make sure the
- * following steps are taken
- *
- * a. Move the device to %WIMAX_ST_UNINITIALIZED. This is needed so
- * some API calls that shouldn't work until the device is ready
- * can be blocked.
- *
- * b. Initialize the device. Make sure to turn the SW radio switch
- * off and move the device to state %WIMAX_ST_RADIO_OFF when
- * done. When just initialized, a device should be left in RADIO
- * OFF state until user space devices to turn it on.
- *
- * c. Query the device for the state of the hardware rfkill switch
- * and call wimax_rfkill_report_hw() and wimax_rfkill_report_sw()
- * as needed. See below.
- *
- * wimax_dev_rm() undoes before unregistering the network device. Once
- * wimax_dev_add() is called, the driver can get called on the
- * wimax_dev->op_* function pointers
- *
- * CONCURRENCY:
- *
- * The stack provides a mutex for each device that will disallow API
- * calls happening concurrently; thus, op calls into the driver
- * through the wimax_dev->op*() function pointers will always be
- * serialized and *never* concurrent.
- *
- * For locking, take wimax_dev->mutex is taken; (most) operations in
- * the API have to check for wimax_dev_is_ready() to return 0 before
- * continuing (this is done internally).
- *
- * REFERENCE COUNTING:
- *
- * The WiMAX device is reference counted by the associated network
- * device. The only operation that can be used to reference the device
- * is wimax_dev_get_by_genl_info(), and the reference it acquires has
- * to be released with dev_put(wimax_dev->net_dev).
- *
- * RFKILL:
- *
- * At startup, both HW and SW radio switchess are assumed to be off.
- *
- * At initialization time [after calling wimax_dev_add()], have the
- * driver query the device for the status of the software and hardware
- * RF kill switches and call wimax_report_rfkill_hw() and
- * wimax_rfkill_report_sw() to indicate their state. If any is
- * missing, just call it to indicate it is ON (radio always on).
- *
- * Whenever the driver detects a change in the state of the RF kill
- * switches, it should call wimax_report_rfkill_hw() or
- * wimax_report_rfkill_sw() to report it to the stack.
- */
-struct wimax_dev {
- struct net_device *net_dev;
- struct list_head id_table_node;
- struct mutex mutex; /* Protects all members and API calls */
- struct mutex mutex_reset;
- enum wimax_st state;
-
- int (*op_msg_from_user)(struct wimax_dev *wimax_dev,
- const char *,
- const void *, size_t,
- const struct genl_info *info);
- int (*op_rfkill_sw_toggle)(struct wimax_dev *wimax_dev,
- enum wimax_rf_state);
- int (*op_reset)(struct wimax_dev *wimax_dev);
-
- struct rfkill *rfkill;
- unsigned int rf_hw;
- unsigned int rf_sw;
- char name[32];
-
- struct dentry *debugfs_dentry;
-};
-
-
-
-/*
- * WiMAX stack public API for device drivers
- * -----------------------------------------
- *
- * These functions are not exported to user space.
- */
-void wimax_dev_init(struct wimax_dev *);
-int wimax_dev_add(struct wimax_dev *, struct net_device *);
-void wimax_dev_rm(struct wimax_dev *);
-
-static inline
-struct wimax_dev *net_dev_to_wimax(struct net_device *net_dev)
-{
- return netdev_priv(net_dev);
-}
-
-static inline
-struct device *wimax_dev_to_dev(struct wimax_dev *wimax_dev)
-{
- return wimax_dev->net_dev->dev.parent;
-}
-
-void wimax_state_change(struct wimax_dev *, enum wimax_st);
-enum wimax_st wimax_state_get(struct wimax_dev *);
-
-/*
- * Radio Switch state reporting.
- *
- * enum wimax_rf_state is declared in linux/wimax.h so the exports
- * to user space can use it.
- */
-void wimax_report_rfkill_hw(struct wimax_dev *, enum wimax_rf_state);
-void wimax_report_rfkill_sw(struct wimax_dev *, enum wimax_rf_state);
-
-
-/*
- * Free-form messaging to/from user space
- *
- * Sending a message:
- *
- * wimax_msg(wimax_dev, pipe_name, buf, buf_size, GFP_KERNEL);
- *
- * Broken up:
- *
- * skb = wimax_msg_alloc(wimax_dev, pipe_name, buf_size, GFP_KERNEL);
- * ...fill up skb...
- * wimax_msg_send(wimax_dev, pipe_name, skb);
- *
- * Be sure not to modify skb->data in the middle (ie: don't use
- * skb_push()/skb_pull()/skb_reserve() on the skb).
- *
- * "pipe_name" is any string, that can be interpreted as the name of
- * the pipe or recipient; the interpretation of it is driver
- * specific, so the recipient can multiplex it as wished. It can be
- * NULL, it won't be used - an example is using a "diagnostics" tag to
- * send diagnostics information that a device-specific diagnostics
- * tool would be interested in.
- */
-struct sk_buff *wimax_msg_alloc(struct wimax_dev *, const char *, const void *,
- size_t, gfp_t);
-int wimax_msg_send(struct wimax_dev *, struct sk_buff *);
-int wimax_msg(struct wimax_dev *, const char *, const void *, size_t, gfp_t);
-
-const void *wimax_msg_data_len(struct sk_buff *, size_t *);
-const void *wimax_msg_data(struct sk_buff *);
-ssize_t wimax_msg_len(struct sk_buff *);
-
-
-/*
- * WiMAX stack user space API
- * --------------------------
- *
- * This API is what gets exported to user space for general
- * operations. As well, they can be called from within the kernel,
- * (with a properly referenced `struct wimax_dev`).
- *
- * Properly referenced means: the 'struct net_device' that embeds the
- * device's control structure and (as such) the 'struct wimax_dev' is
- * referenced by the caller.
- */
-int wimax_rfkill(struct wimax_dev *, enum wimax_rf_state);
-int wimax_reset(struct wimax_dev *);
-
-#endif /* #ifndef __NET__WIMAX_H__ */
struct net_device *dev_rx; /* used by cpumap */
};
+#define XDP_BULK_QUEUE_SIZE 16
+struct xdp_frame_bulk {
+ int count;
+ void *xa;
+ void *q[XDP_BULK_QUEUE_SIZE];
+};
+
+static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq)
+{
+ /* bq->count will be zero'ed when bq->xa gets updated */
+ bq->xa = NULL;
+}
static inline struct skb_shared_info *
xdp_get_shared_info_from_frame(struct xdp_frame *frame)
void xdp_return_frame(struct xdp_frame *xdpf);
void xdp_return_frame_rx_napi(struct xdp_frame *xdpf);
void xdp_return_buff(struct xdp_buff *xdp);
+void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq);
+void xdp_return_frame_bulk(struct xdp_frame *xdpf,
+ struct xdp_frame_bulk *bq);
/* When sending xdp_frame into the network stack, then there is no
* return point callback, which is needed to release e.g. DMA-mapping
void xdp_attachment_setup(struct xdp_attachment_info *info,
struct netdev_bpf *bpf);
-#define DEV_MAP_BULK_SIZE 16
+#define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE
#endif /* __LINUX_NET_XDP_H__ */
#ifndef IB_ADDR_H
#define IB_ADDR_H
+#include <linux/ethtool.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/if_arp.h>
#ifndef IB_VERBS_H
#define IB_VERBS_H
+#include <linux/ethtool.h>
#include <linux/types.h>
#include <linux/device.h>
#include <linux/dma-mapping.h>
};
typedef enum qman_cb_dqrr_result (*qman_cb_dqrr)(struct qman_portal *qm,
struct qman_fq *fq,
- const struct qm_dqrr_entry *dqrr);
+ const struct qm_dqrr_entry *dqrr,
+ bool sched_napi);
/*
* This callback type is used when handling ERNs, FQRNs and FQRLs via MR. They
int pol_lpr;
};
+struct ocelot_vlan {
+ bool valid;
+ u16 vid;
+};
+
struct ocelot_port {
struct ocelot *ocelot;
struct regmap *target;
bool vlan_aware;
-
- /* Ingress default VLAN (pvid) */
- u16 pvid;
-
- /* Egress default VLAN (vid) */
- u16 vid;
+ /* VLAN that untagged frames are classified to, on ingress */
+ struct ocelot_vlan pvid_vlan;
+ /* The VLAN ID that will be transmitted as untagged, on egress */
+ struct ocelot_vlan native_vlan;
u8 ptp_cmd;
struct sk_buff_head tx_skbs;
u32 *lags;
struct list_head multicast;
+ struct list_head pgids;
struct list_head dummy_rules;
struct ocelot_vcap_block block[3];
const unsigned char *addr, u16 vid);
int ocelot_fdb_del(struct ocelot *ocelot, int port,
const unsigned char *addr, u16 vid);
+int ocelot_vlan_prepare(struct ocelot *ocelot, int port, u16 vid, bool pvid,
+ bool untagged);
int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
bool untagged);
int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid);
BPF_MAP_TYPE_STRUCT_OPS,
BPF_MAP_TYPE_RINGBUF,
BPF_MAP_TYPE_INODE_STORAGE,
+ BPF_MAP_TYPE_TASK_STORAGE,
};
/* Note that tracing related programs such as
* Return
* The helper returns **TC_ACT_REDIRECT** on success or
* **TC_ACT_SHOT** on error.
+ *
+ * void *bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from the *task*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *task* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
+ * helper enforces the key must be an task_struct and the map must also
+ * be a **BPF_MAP_TYPE_TASK_STORAGE**.
+ *
+ * Underneath, the value is stored locally at *task* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf_local_storage residing at *task*.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * long bpf_task_storage_delete(struct bpf_map *map, struct task_struct *task)
+ * Description
+ * Delete a bpf_local_storage from a *task*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * struct task_struct *bpf_get_current_task_btf(void)
+ * Description
+ * Return a BTF pointer to the "current" task.
+ * This pointer can also be used in helpers that accept an
+ * *ARG_PTR_TO_BTF_ID* of type *task_struct*.
+ * Return
+ * Pointer to the current task.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
FN(bpf_per_cpu_ptr), \
FN(bpf_this_cpu_ptr), \
FN(redirect_peer), \
+ FN(task_storage_get), \
+ FN(task_storage_delete), \
+ FN(get_current_task_btf), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
__aligned_u64 btf;
__u32 btf_size;
__u32 id;
+ __aligned_u64 name;
+ __u32 name_len;
+ __u32 kernel_btf;
} __attribute__((aligned(8)));
struct bpf_link_info {
/* CAN payload length and DLC definitions according to ISO 11898-1 */
#define CAN_MAX_DLC 8
+#define CAN_MAX_RAW_DLC 15
#define CAN_MAX_DLEN 8
/* CAN FD payload length and DLC definitions according to ISO 11898-7 */
#define CANFD_MAX_DLEN 64
/**
- * struct can_frame - basic CAN frame structure
- * @can_id: CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition
- * @can_dlc: frame payload length in byte (0 .. 8) aka data length code
- * N.B. the DLC field from ISO 11898-1 Chapter 8.4.2.3 has a 1:1
- * mapping of the 'data length code' to the real payload length
- * @__pad: padding
- * @__res0: reserved / padding
- * @__res1: reserved / padding
- * @data: CAN frame payload (up to 8 byte)
+ * struct can_frame - Classical CAN frame structure (aka CAN 2.0B)
+ * @can_id: CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition
+ * @len: CAN frame payload length in byte (0 .. 8)
+ * @can_dlc: deprecated name for CAN frame payload length in byte (0 .. 8)
+ * @__pad: padding
+ * @__res0: reserved / padding
+ * @len8_dlc: optional DLC value (9 .. 15) at 8 byte payload length
+ * len8_dlc contains values from 9 .. 15 when the payload length is
+ * 8 bytes but the DLC value (see ISO 11898-1) is greater then 8.
+ * CAN_CTRLMODE_CC_LEN8_DLC flag has to be enabled in CAN driver.
+ * @data: CAN frame payload (up to 8 byte)
*/
struct can_frame {
canid_t can_id; /* 32 bit CAN_ID + EFF/RTR/ERR flags */
- __u8 can_dlc; /* frame payload length in byte (0 .. CAN_MAX_DLEN) */
- __u8 __pad; /* padding */
- __u8 __res0; /* reserved / padding */
- __u8 __res1; /* reserved / padding */
- __u8 data[CAN_MAX_DLEN] __attribute__((aligned(8)));
+ union {
+ /* CAN frame payload length in byte (0 .. CAN_MAX_DLEN)
+ * was previously named can_dlc so we need to carry that
+ * name for legacy support
+ */
+ __u8 len;
+ __u8 can_dlc; /* deprecated */
+ };
+ __u8 __pad; /* padding */
+ __u8 __res0; /* reserved / padding */
+ __u8 len8_dlc; /* optional DLC for 8 byte payload length (9 .. 15) */
+ __u8 data[CAN_MAX_DLEN] __attribute__((aligned(8)));
};
/*
/* CAN frame elements that are affected by curr. 3 CAN frame modifications */
#define CGW_MOD_ID 0x01
-#define CGW_MOD_DLC 0x02 /* contains the data length in bytes */
-#define CGW_MOD_LEN CGW_MOD_DLC /* CAN FD length representation */
+#define CGW_MOD_DLC 0x02 /* Classical CAN data length code */
+#define CGW_MOD_LEN CGW_MOD_DLC /* CAN FD (plain) data length */
#define CGW_MOD_DATA 0x04
#define CGW_MOD_FLAGS 0x08 /* CAN FD flags */
#define CAN_CTRLMODE_FD 0x20 /* CAN FD mode */
#define CAN_CTRLMODE_PRESUME_ACK 0x40 /* Ignore missing CAN ACKs */
#define CAN_CTRLMODE_FD_NON_ISO 0x80 /* CAN FD in non-ISO mode */
+#define CAN_CTRLMODE_CC_LEN8_DLC 0x100 /* Classic CAN DLC option */
/*
* CAN device statistics
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+
+#ifndef _UAPI_LINUX_CFM_BRIDGE_H_
+#define _UAPI_LINUX_CFM_BRIDGE_H_
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+#define ETHER_HEADER_LENGTH (6+6+4+2)
+#define CFM_MAID_LENGTH 48
+#define CFM_CCM_PDU_LENGTH 75
+#define CFM_PORT_STATUS_TLV_LENGTH 4
+#define CFM_IF_STATUS_TLV_LENGTH 4
+#define CFM_IF_STATUS_TLV_TYPE 4
+#define CFM_PORT_STATUS_TLV_TYPE 2
+#define CFM_ENDE_TLV_TYPE 0
+#define CFM_CCM_MAX_FRAME_LENGTH (ETHER_HEADER_LENGTH+\
+ CFM_CCM_PDU_LENGTH+\
+ CFM_PORT_STATUS_TLV_LENGTH+\
+ CFM_IF_STATUS_TLV_LENGTH)
+#define CFM_FRAME_PRIO 7
+#define CFM_CCM_TLV_OFFSET 70
+#define CFM_CCM_PDU_MAID_OFFSET 10
+#define CFM_CCM_PDU_MEPID_OFFSET 8
+#define CFM_CCM_PDU_SEQNR_OFFSET 4
+#define CFM_CCM_PDU_TLV_OFFSET 74
+#define CFM_CCM_ITU_RESERVED_SIZE 16
+
+struct br_cfm_common_hdr {
+ __u8 mdlevel_version;
+ __u8 opcode;
+ __u8 flags;
+ __u8 tlv_offset;
+};
+
+enum br_cfm_opcodes {
+ BR_CFM_OPCODE_CCM = 0x1,
+};
+
+/* MEP domain */
+enum br_cfm_domain {
+ BR_CFM_PORT,
+ BR_CFM_VLAN,
+};
+
+/* MEP direction */
+enum br_cfm_mep_direction {
+ BR_CFM_MEP_DIRECTION_DOWN,
+ BR_CFM_MEP_DIRECTION_UP,
+};
+
+/* CCM interval supported. */
+enum br_cfm_ccm_interval {
+ BR_CFM_CCM_INTERVAL_NONE,
+ BR_CFM_CCM_INTERVAL_3_3_MS,
+ BR_CFM_CCM_INTERVAL_10_MS,
+ BR_CFM_CCM_INTERVAL_100_MS,
+ BR_CFM_CCM_INTERVAL_1_SEC,
+ BR_CFM_CCM_INTERVAL_10_SEC,
+ BR_CFM_CCM_INTERVAL_1_MIN,
+ BR_CFM_CCM_INTERVAL_10_MIN,
+};
+
+#endif
IFLA_BRIDGE_VLAN_INFO,
IFLA_BRIDGE_VLAN_TUNNEL_INFO,
IFLA_BRIDGE_MRP,
+ IFLA_BRIDGE_CFM,
__IFLA_BRIDGE_MAX,
};
#define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1)
__u16 in_id;
};
+enum {
+ IFLA_BRIDGE_CFM_UNSPEC,
+ IFLA_BRIDGE_CFM_MEP_CREATE,
+ IFLA_BRIDGE_CFM_MEP_DELETE,
+ IFLA_BRIDGE_CFM_MEP_CONFIG,
+ IFLA_BRIDGE_CFM_CC_CONFIG,
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD,
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE,
+ IFLA_BRIDGE_CFM_CC_RDI,
+ IFLA_BRIDGE_CFM_CC_CCM_TX,
+ IFLA_BRIDGE_CFM_MEP_CREATE_INFO,
+ IFLA_BRIDGE_CFM_MEP_CONFIG_INFO,
+ IFLA_BRIDGE_CFM_CC_CONFIG_INFO,
+ IFLA_BRIDGE_CFM_CC_RDI_INFO,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_INFO,
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_INFO,
+ IFLA_BRIDGE_CFM_MEP_STATUS_INFO,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO,
+ __IFLA_BRIDGE_CFM_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MAX (__IFLA_BRIDGE_CFM_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_MEP_CREATE_UNSPEC,
+ IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE,
+ IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN,
+ IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION,
+ IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX,
+ __IFLA_BRIDGE_CFM_MEP_CREATE_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MEP_CREATE_MAX (__IFLA_BRIDGE_CFM_MEP_CREATE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_MEP_DELETE_UNSPEC,
+ IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE,
+ __IFLA_BRIDGE_CFM_MEP_DELETE_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MEP_DELETE_MAX (__IFLA_BRIDGE_CFM_MEP_DELETE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_MEP_CONFIG_UNSPEC,
+ IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE,
+ IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC,
+ IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL,
+ IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID,
+ __IFLA_BRIDGE_CFM_MEP_CONFIG_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MEP_CONFIG_MAX (__IFLA_BRIDGE_CFM_MEP_CONFIG_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_CC_CONFIG_UNSPEC,
+ IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE,
+ IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE,
+ IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL,
+ IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID,
+ __IFLA_BRIDGE_CFM_CC_CONFIG_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_CONFIG_MAX (__IFLA_BRIDGE_CFM_CC_CONFIG_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_UNSPEC,
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE,
+ IFLA_BRIDGE_CFM_CC_PEER_MEPID,
+ __IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX (__IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_CC_RDI_UNSPEC,
+ IFLA_BRIDGE_CFM_CC_RDI_INSTANCE,
+ IFLA_BRIDGE_CFM_CC_RDI_RDI,
+ __IFLA_BRIDGE_CFM_CC_RDI_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_RDI_MAX (__IFLA_BRIDGE_CFM_CC_RDI_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_CC_CCM_TX_UNSPEC,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE,
+ __IFLA_BRIDGE_CFM_CC_CCM_TX_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_CCM_TX_MAX (__IFLA_BRIDGE_CFM_CC_CCM_TX_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_MEP_STATUS_UNSPEC,
+ IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE,
+ IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN,
+ IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN,
+ IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN,
+ __IFLA_BRIDGE_CFM_MEP_STATUS_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MEP_STATUS_MAX (__IFLA_BRIDGE_CFM_MEP_STATUS_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_UNSPEC,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN,
+ __IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX (__IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX - 1)
+
struct bridge_stp_xstats {
__u64 transition_blk;
__u64 transition_fwd;
union {
__be32 ip4;
struct in6_addr ip6;
+ unsigned char mac_addr[ETH_ALEN];
} u;
__be16 proto;
} addr;
#define ETH_P_1588 0x88F7 /* IEEE 1588 Timesync */
#define ETH_P_NCSI 0x88F8 /* NCSI protocol */
#define ETH_P_PRP 0x88FB /* IEC 62439-3 PRP/HSRv0 */
+#define ETH_P_CFM 0x8902 /* Connectivity Fault Management */
#define ETH_P_FCOE 0x8906 /* Fibre Channel over Ethernet */
#define ETH_P_IBOE 0x8915 /* Infiniband over Ethernet */
#define ETH_P_TDLS 0x890D /* TDLS */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
-/*
- * DLCI/FRAD Definitions for Frame Relay Access Devices. DLCI devices are
- * created for each DLCI associated with a FRAD. The FRAD driver
- * is not truly a network device, but the lower level device
- * handler. This allows other FRAD manufacturers to use the DLCI
- * code, including its RFC1490 encapsulation alongside the current
- * implementation for the Sangoma cards.
- *
- * Version: @(#)if_ifrad.h 0.15 31 Mar 96
- *
- * Author: Mike McLagan <mike.mclagan@linux.org>
- *
- * Changes:
- * 0.15 Mike McLagan changed structure defs (packed)
- * re-arranged flags
- * added DLCI_RET vars
- *
- * 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 _UAPI_FRAD_H_
-#define _UAPI_FRAD_H_
-
-#include <linux/if.h>
-
-/* Structures and constants associated with the DLCI device driver */
-
-struct dlci_add
-{
- char devname[IFNAMSIZ];
- short dlci;
-};
-
-#define DLCI_GET_CONF (SIOCDEVPRIVATE + 2)
-#define DLCI_SET_CONF (SIOCDEVPRIVATE + 3)
-
-/*
- * These are related to the Sangoma SDLA and should remain in order.
- * Code within the SDLA module is based on the specifics of this
- * structure. Change at your own peril.
- */
-struct dlci_conf {
- short flags;
- short CIR_fwd;
- short Bc_fwd;
- short Be_fwd;
- short CIR_bwd;
- short Bc_bwd;
- short Be_bwd;
-
-/* these are part of the status read */
- short Tc_fwd;
- short Tc_bwd;
- short Tf_max;
- short Tb_max;
-
-/* add any new fields here above is a mirror of sdla_dlci_conf */
-};
-
-#define DLCI_GET_SLAVE (SIOCDEVPRIVATE + 4)
-
-/* configuration flags for DLCI */
-#define DLCI_IGNORE_CIR_OUT 0x0001
-#define DLCI_ACCOUNT_CIR_IN 0x0002
-#define DLCI_BUFFER_IF 0x0008
-
-#define DLCI_VALID_FLAGS 0x000B
-
-/* defines for the actual Frame Relay hardware */
-#define FRAD_GET_CONF (SIOCDEVPRIVATE)
-#define FRAD_SET_CONF (SIOCDEVPRIVATE + 1)
-
-#define FRAD_LAST_IOCTL FRAD_SET_CONF
-
-/*
- * Based on the setup for the Sangoma SDLA. If changes are
- * necessary to this structure, a routine will need to be
- * added to that module to copy fields.
- */
-struct frad_conf
-{
- short station;
- short flags;
- short kbaud;
- short clocking;
- short mtu;
- short T391;
- short T392;
- short N391;
- short N392;
- short N393;
- short CIR_fwd;
- short Bc_fwd;
- short Be_fwd;
- short CIR_bwd;
- short Bc_bwd;
- short Be_bwd;
-
-/* Add new fields here, above is a mirror of the sdla_conf */
-
-};
-
-#define FRAD_STATION_CPE 0x0000
-#define FRAD_STATION_NODE 0x0001
-
-#define FRAD_TX_IGNORE_CIR 0x0001
-#define FRAD_RX_ACCOUNT_CIR 0x0002
-#define FRAD_DROP_ABORTED 0x0004
-#define FRAD_BUFFERIF 0x0008
-#define FRAD_STATS 0x0010
-#define FRAD_MCI 0x0100
-#define FRAD_AUTODLCI 0x8000
-#define FRAD_VALID_FLAGS 0x811F
-
-#define FRAD_CLOCK_INT 0x0001
-#define FRAD_CLOCK_EXT 0x0000
-
-
-#endif /* _UAPI_FRAD_H_ */
IFLA_MACVLAN_MACADDR,
IFLA_MACVLAN_MACADDR_DATA,
IFLA_MACVLAN_MACADDR_COUNT,
+ IFLA_MACVLAN_BC_QUEUE_LEN,
+ IFLA_MACVLAN_BC_QUEUE_LEN_USED,
__IFLA_MACVLAN_MAX,
};
#ifndef __LINUX_IF_PACKET_H
#define __LINUX_IF_PACKET_H
+#include <asm/byteorder.h>
#include <linux/types.h>
struct sockaddr_pkt {
unsigned char mr_address[8];
};
+struct fanout_args {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u16 id;
+ __u16 type_flags;
+#else
+ __u16 type_flags;
+ __u16 id;
+#endif
+ __u32 max_num_members;
+};
+
#define PACKET_MR_MULTICAST 0
#define PACKET_MR_PROMISC 1
#define PACKET_MR_ALLMULTI 2
BR_MRP_TLV_HEADER_IN_TOPO = 0x7,
BR_MRP_TLV_HEADER_IN_LINK_DOWN = 0x8,
BR_MRP_TLV_HEADER_IN_LINK_UP = 0x9,
+ BR_MRP_TLV_HEADER_IN_LINK_STATUS = 0xa,
BR_MRP_TLV_HEADER_OPTION = 0x7f,
};
/* Reserve empty slots */
IPSET_ATTR_CADT_MAX = 16,
/* Create-only specific attributes */
- IPSET_ATTR_GC,
+ IPSET_ATTR_INITVAL, /* was unused IPSET_ATTR_GC */
IPSET_ATTR_HASHSIZE,
IPSET_ATTR_MAXELEM,
IPSET_ATTR_NETMASK,
- IPSET_ATTR_PROBES,
+ IPSET_ATTR_BUCKETSIZE, /* was unused IPSET_ATTR_PROBES */
IPSET_ATTR_RESIZE,
IPSET_ATTR_SIZE,
/* Kernel-only */
enum ipset_create_flags {
IPSET_CREATE_FLAG_BIT_FORCEADD = 0,
IPSET_CREATE_FLAG_FORCEADD = (1 << IPSET_CREATE_FLAG_BIT_FORCEADD),
+ IPSET_CREATE_FLAG_BIT_BUCKETSIZE = 1,
+ IPSET_CREATE_FLAG_BUCKETSIZE = (1 << IPSET_CREATE_FLAG_BIT_BUCKETSIZE),
IPSET_CREATE_FLAG_BIT_MAX = 7,
};
* of any other interfaces, and other interfaces will again take
* precedence when they are used.
*
- * @NL80211_CMD_SET_WDS_PEER: Set the MAC address of the peer on a WDS interface.
+ * @NL80211_CMD_SET_WDS_PEER: Set the MAC address of the peer on a WDS interface
+ * (no longer supported).
*
* @NL80211_CMD_SET_MULTICAST_TO_UNICAST: Configure if this AP should perform
* multicast to unicast conversion. When enabled, all multicast packets
* specify just a single bitrate, which is to be used for the beacon.
* The driver must also specify support for this with the extended
* features NL80211_EXT_FEATURE_BEACON_RATE_LEGACY,
- * NL80211_EXT_FEATURE_BEACON_RATE_HT and
- * NL80211_EXT_FEATURE_BEACON_RATE_VHT.
+ * NL80211_EXT_FEATURE_BEACON_RATE_HT,
+ * NL80211_EXT_FEATURE_BEACON_RATE_VHT and
+ * NL80211_EXT_FEATURE_BEACON_RATE_HE.
*
* @NL80211_ATTR_FRAME_MATCH: A binary attribute which typically must contain
* at least one byte, currently used with @NL80211_CMD_REGISTER_FRAME.
* override mask. Used with NL80211_ATTR_S1G_CAPABILITY in
* NL80211_CMD_ASSOCIATE or NL80211_CMD_CONNECT.
*
+ * @NL80211_ATTR_SAE_PWE: Indicates the mechanism(s) allowed for SAE PWE
+ * derivation in WPA3-Personal networks which are using SAE authentication.
+ * This is a u8 attribute that encapsulates one of the values from
+ * &enum nl80211_sae_pwe_mechanism.
+ *
* @NUM_NL80211_ATTR: total number of nl80211_attrs available
* @NL80211_ATTR_MAX: highest attribute number currently defined
* @__NL80211_ATTR_AFTER_LAST: internal use
NL80211_ATTR_S1G_CAPABILITY,
NL80211_ATTR_S1G_CAPABILITY_MASK,
+ NL80211_ATTR_SAE_PWE,
+
/* add attributes here, update the policy in nl80211.c */
__NL80211_ATTR_AFTER_LAST,
* @NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP: Driver/device supports
* unsolicited broadcast probe response transmission
*
+ * @NL80211_EXT_FEATURE_BEACON_RATE_HE: Driver supports beacon rate
+ * configuration (AP/mesh) with HE rates.
+ *
* @NUM_NL80211_EXT_FEATURES: number of extended features.
* @MAX_NL80211_EXT_FEATURES: highest extended feature index.
*/
NL80211_EXT_FEATURE_SAE_OFFLOAD_AP,
NL80211_EXT_FEATURE_FILS_DISCOVERY,
NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP,
+ NL80211_EXT_FEATURE_BEACON_RATE_HE,
/* add new features before the definition below */
NUM_NL80211_EXT_FEATURES,
NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX =
__NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_LAST - 1
};
+
+/**
+ * enum nl80211_sae_pwe_mechanism - The mechanism(s) allowed for SAE PWE
+ * derivation. Applicable only when WPA3-Personal SAE authentication is
+ * used.
+ *
+ * @NL80211_SAE_PWE_UNSPECIFIED: not specified, used internally to indicate that
+ * attribute is not present from userspace.
+ * @NL80211_SAE_PWE_HUNT_AND_PECK: hunting-and-pecking loop only
+ * @NL80211_SAE_PWE_HASH_TO_ELEMENT: hash-to-element only
+ * @NL80211_SAE_PWE_BOTH: both hunting-and-pecking loop and hash-to-element
+ * can be used.
+ */
+enum nl80211_sae_pwe_mechanism {
+ NL80211_SAE_PWE_UNSPECIFIED,
+ NL80211_SAE_PWE_HUNT_AND_PECK,
+ NL80211_SAE_PWE_HASH_TO_ELEMENT,
+ NL80211_SAE_PWE_BOTH,
+};
#endif /* __LINUX_NL80211_H */
#define RTNH_F_DEAD 1 /* Nexthop is dead (used by multipath) */
#define RTNH_F_PERVASIVE 2 /* Do recursive gateway lookup */
#define RTNH_F_ONLINK 4 /* Gateway is forced on link */
-#define RTNH_F_OFFLOAD 8 /* offloaded route */
+#define RTNH_F_OFFLOAD 8 /* Nexthop is offloaded */
#define RTNH_F_LINKDOWN 16 /* carrier-down on nexthop */
#define RTNH_F_UNRESOLVED 32 /* The entry is unresolved (ipmr) */
+#define RTNH_F_TRAP 64 /* Nexthop is trapping packets */
-#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD)
+#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | \
+ RTNH_F_OFFLOAD | RTNH_F_TRAP)
/* Macros to handle hexthops */
#define TA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcamsg))
/* tcamsg flags stored in attribute TCA_ROOT_FLAGS
*
- * TCA_FLAG_LARGE_DUMP_ON user->kernel to request for larger than TCA_ACT_MAX_PRIO
- * actions in a dump. All dump responses will contain the number of actions
- * being dumped stored in for user app's consumption in TCA_ROOT_COUNT
+ * TCA_ACT_FLAG_LARGE_DUMP_ON user->kernel to request for larger than
+ * TCA_ACT_MAX_PRIO actions in a dump. All dump responses will contain the
+ * number of actions being dumped stored in for user app's consumption in
+ * TCA_ROOT_COUNT
+ *
+ * TCA_ACT_FLAG_TERSE_DUMP user->kernel to request terse (brief) dump that only
+ * includes essential action info (kind, index, etc.)
*
*/
#define TCA_FLAG_LARGE_DUMP_ON (1 << 0)
+#define TCA_ACT_FLAG_LARGE_DUMP_ON TCA_FLAG_LARGE_DUMP_ON
+#define TCA_ACT_FLAG_TERSE_DUMP (1 << 1)
/* New extended info filters for IFLA_EXT_MASK */
#define RTEXT_FILTER_VF (1 << 0)
#define RTEXT_FILTER_BRVLAN_COMPRESSED (1 << 2)
#define RTEXT_FILTER_SKIP_STATS (1 << 3)
#define RTEXT_FILTER_MRP (1 << 4)
+#define RTEXT_FILTER_CFM_CONFIG (1 << 5)
+#define RTEXT_FILTER_CFM_STATUS (1 << 6)
/* End of information exported to user level */
#define SCTP_ECN_SUPPORTED 130
#define SCTP_EXPOSE_POTENTIALLY_FAILED_STATE 131
#define SCTP_EXPOSE_PF_STATE SCTP_EXPOSE_POTENTIALLY_FAILED_STATE
+#define SCTP_REMOTE_UDP_ENCAPS_PORT 132
/* PR-SCTP policies */
#define SCTP_PR_SCTP_NONE 0x0000
uint8_t se_on;
};
+struct sctp_udpencaps {
+ sctp_assoc_t sue_assoc_id;
+ struct sockaddr_storage sue_address;
+ uint16_t sue_port;
+};
+
/* SCTP Stream schedulers */
enum sctp_sched_type {
SCTP_SS_FCFS,
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
-/*
- * INET An implementation of the TCP/IP protocol suite for the LINUX
- * operating system. INET is implemented using the BSD Socket
- * interface as the means of communication with the user level.
- *
- * Global definitions for the Frame relay interface.
- *
- * Version: @(#)if_ifrad.h 0.20 13 Apr 96
- *
- * Author: Mike McLagan <mike.mclagan@linux.org>
- *
- * Changes:
- * 0.15 Mike McLagan Structure packing
- *
- * 0.20 Mike McLagan New flags for S508 buffer handling
- *
- * 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 _UAPISDLA_H
-#define _UAPISDLA_H
-
-/* adapter type */
-#define SDLA_TYPES
-#define SDLA_S502A 5020
-#define SDLA_S502E 5021
-#define SDLA_S503 5030
-#define SDLA_S507 5070
-#define SDLA_S508 5080
-#define SDLA_S509 5090
-#define SDLA_UNKNOWN -1
-
-/* port selection flags for the S508 */
-#define SDLA_S508_PORT_V35 0x00
-#define SDLA_S508_PORT_RS232 0x02
-
-/* Z80 CPU speeds */
-#define SDLA_CPU_3M 0x00
-#define SDLA_CPU_5M 0x01
-#define SDLA_CPU_7M 0x02
-#define SDLA_CPU_8M 0x03
-#define SDLA_CPU_10M 0x04
-#define SDLA_CPU_16M 0x05
-#define SDLA_CPU_12M 0x06
-
-/* some private IOCTLs */
-#define SDLA_IDENTIFY (FRAD_LAST_IOCTL + 1)
-#define SDLA_CPUSPEED (FRAD_LAST_IOCTL + 2)
-#define SDLA_PROTOCOL (FRAD_LAST_IOCTL + 3)
-
-#define SDLA_CLEARMEM (FRAD_LAST_IOCTL + 4)
-#define SDLA_WRITEMEM (FRAD_LAST_IOCTL + 5)
-#define SDLA_READMEM (FRAD_LAST_IOCTL + 6)
-
-struct sdla_mem {
- int addr;
- int len;
- void __user *data;
-};
-
-#define SDLA_START (FRAD_LAST_IOCTL + 7)
-#define SDLA_STOP (FRAD_LAST_IOCTL + 8)
-
-/* some offsets in the Z80's memory space */
-#define SDLA_NMIADDR 0x0000
-#define SDLA_CONF_ADDR 0x0010
-#define SDLA_S502A_NMIADDR 0x0066
-#define SDLA_CODE_BASEADDR 0x0100
-#define SDLA_WINDOW_SIZE 0x2000
-#define SDLA_ADDR_MASK 0x1FFF
-
-/* largest handleable block of data */
-#define SDLA_MAX_DATA 4080
-#define SDLA_MAX_MTU 4072 /* MAX_DATA - sizeof(fradhdr) */
-#define SDLA_MAX_DLCI 24
-
-/* this should be the same as frad_conf */
-struct sdla_conf {
- short station;
- short config;
- short kbaud;
- short clocking;
- short max_frm;
- short T391;
- short T392;
- short N391;
- short N392;
- short N393;
- short CIR_fwd;
- short Bc_fwd;
- short Be_fwd;
- short CIR_bwd;
- short Bc_bwd;
- short Be_bwd;
-};
-
-/* this should be the same as dlci_conf */
-struct sdla_dlci_conf {
- short config;
- short CIR_fwd;
- short Bc_fwd;
- short Be_fwd;
- short CIR_bwd;
- short Bc_bwd;
- short Be_bwd;
- short Tc_fwd;
- short Tc_bwd;
- short Tf_max;
- short Tb_max;
-};
-
-
-#endif /* _UAPISDLA_H */
#define SMCR_GENL_FAMILY_NAME "SMC_PNETID"
#define SMCR_GENL_FAMILY_VERSION 1
+/* gennetlink interface to access non-socket information from SMC module */
+#define SMC_GENL_FAMILY_NAME "SMC_GEN_NETLINK"
+#define SMC_GENL_FAMILY_VERSION 1
+
+#define SMC_PCI_ID_STR_LEN 16 /* Max length of pci id string */
+
+/* SMC_GENL_FAMILY commands */
+enum {
+ SMC_NETLINK_GET_SYS_INFO = 1,
+ SMC_NETLINK_GET_LGR_SMCR,
+ SMC_NETLINK_GET_LINK_SMCR,
+ SMC_NETLINK_GET_LGR_SMCD,
+ SMC_NETLINK_GET_DEV_SMCD,
+ SMC_NETLINK_GET_DEV_SMCR,
+};
+
+/* SMC_GENL_FAMILY top level attributes */
+enum {
+ SMC_GEN_UNSPEC,
+ SMC_GEN_SYS_INFO, /* nest */
+ SMC_GEN_LGR_SMCR, /* nest */
+ SMC_GEN_LINK_SMCR, /* nest */
+ SMC_GEN_LGR_SMCD, /* nest */
+ SMC_GEN_DEV_SMCD, /* nest */
+ SMC_GEN_DEV_SMCR, /* nest */
+ __SMC_GEN_MAX,
+ SMC_GEN_MAX = __SMC_GEN_MAX - 1
+};
+
+/* SMC_GEN_SYS_INFO attributes */
+enum {
+ SMC_NLA_SYS_UNSPEC,
+ SMC_NLA_SYS_VER, /* u8 */
+ SMC_NLA_SYS_REL, /* u8 */
+ SMC_NLA_SYS_IS_ISM_V2, /* u8 */
+ SMC_NLA_SYS_LOCAL_HOST, /* string */
+ SMC_NLA_SYS_SEID, /* string */
+ __SMC_NLA_SYS_MAX,
+ SMC_NLA_SYS_MAX = __SMC_NLA_SYS_MAX - 1
+};
+
+/* SMC_NLA_LGR_V2 nested attributes */
+enum {
+ SMC_NLA_LGR_V2_VER, /* u8 */
+ SMC_NLA_LGR_V2_REL, /* u8 */
+ SMC_NLA_LGR_V2_OS, /* u8 */
+ SMC_NLA_LGR_V2_NEG_EID, /* string */
+ SMC_NLA_LGR_V2_PEER_HOST, /* string */
+};
+
+/* SMC_GEN_LGR_SMCR attributes */
+enum {
+ SMC_NLA_LGR_R_UNSPEC,
+ SMC_NLA_LGR_R_ID, /* u32 */
+ SMC_NLA_LGR_R_ROLE, /* u8 */
+ SMC_NLA_LGR_R_TYPE, /* u8 */
+ SMC_NLA_LGR_R_PNETID, /* string */
+ SMC_NLA_LGR_R_VLAN_ID, /* u8 */
+ SMC_NLA_LGR_R_CONNS_NUM, /* u32 */
+ __SMC_NLA_LGR_R_MAX,
+ SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1
+};
+
+/* SMC_GEN_LINK_SMCR attributes */
+enum {
+ SMC_NLA_LINK_UNSPEC,
+ SMC_NLA_LINK_ID, /* u8 */
+ SMC_NLA_LINK_IB_DEV, /* string */
+ SMC_NLA_LINK_IB_PORT, /* u8 */
+ SMC_NLA_LINK_GID, /* string */
+ SMC_NLA_LINK_PEER_GID, /* string */
+ SMC_NLA_LINK_CONN_CNT, /* u32 */
+ SMC_NLA_LINK_NET_DEV, /* u32 */
+ SMC_NLA_LINK_UID, /* u32 */
+ SMC_NLA_LINK_PEER_UID, /* u32 */
+ SMC_NLA_LINK_STATE, /* u32 */
+ __SMC_NLA_LINK_MAX,
+ SMC_NLA_LINK_MAX = __SMC_NLA_LINK_MAX - 1
+};
+
+/* SMC_GEN_LGR_SMCD attributes */
+enum {
+ SMC_NLA_LGR_D_UNSPEC,
+ SMC_NLA_LGR_D_ID, /* u32 */
+ SMC_NLA_LGR_D_GID, /* u64 */
+ SMC_NLA_LGR_D_PEER_GID, /* u64 */
+ SMC_NLA_LGR_D_VLAN_ID, /* u8 */
+ SMC_NLA_LGR_D_CONNS_NUM, /* u32 */
+ SMC_NLA_LGR_D_PNETID, /* string */
+ SMC_NLA_LGR_D_CHID, /* u16 */
+ SMC_NLA_LGR_D_PAD, /* flag */
+ SMC_NLA_LGR_V2, /* nest */
+ __SMC_NLA_LGR_D_MAX,
+ SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1
+};
+
+/* SMC_NLA_DEV_PORT nested attributes */
+enum {
+ SMC_NLA_DEV_PORT_UNSPEC,
+ SMC_NLA_DEV_PORT_PNET_USR, /* u8 */
+ SMC_NLA_DEV_PORT_PNETID, /* string */
+ SMC_NLA_DEV_PORT_NETDEV, /* u32 */
+ SMC_NLA_DEV_PORT_STATE, /* u8 */
+ SMC_NLA_DEV_PORT_VALID, /* u8 */
+ SMC_NLA_DEV_PORT_LNK_CNT, /* u32 */
+ __SMC_NLA_DEV_PORT_MAX,
+ SMC_NLA_DEV_PORT_MAX = __SMC_NLA_DEV_PORT_MAX - 1
+};
+
+/* SMC_GEN_DEV_SMCD and SMC_GEN_DEV_SMCR attributes */
+enum {
+ SMC_NLA_DEV_UNSPEC,
+ SMC_NLA_DEV_USE_CNT, /* u32 */
+ SMC_NLA_DEV_IS_CRIT, /* u8 */
+ SMC_NLA_DEV_PCI_FID, /* u32 */
+ SMC_NLA_DEV_PCI_CHID, /* u16 */
+ SMC_NLA_DEV_PCI_VENDOR, /* u16 */
+ SMC_NLA_DEV_PCI_DEVICE, /* u16 */
+ SMC_NLA_DEV_PCI_ID, /* string */
+ SMC_NLA_DEV_PORT, /* nest */
+ SMC_NLA_DEV_PORT2, /* nest */
+ SMC_NLA_DEV_IB_NAME, /* string */
+ __SMC_NLA_DEV_MAX,
+ SMC_NLA_DEV_MAX = __SMC_NLA_DEV_MAX - 1
+};
+
#endif /* _UAPI_LINUX_SMC_H */
UDP_MIB_SNDBUFERRORS, /* SndbufErrors */
UDP_MIB_CSUMERRORS, /* InCsumErrors */
UDP_MIB_IGNOREDMULTI, /* IgnoredMulti */
+ UDP_MIB_MEMERRORS, /* MemErrors */
__UDP_MIB_MAX
};
#define TLS_CIPHER_AES_CCM_128_TAG_SIZE 16
#define TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE 8
+#define TLS_CIPHER_CHACHA20_POLY1305 54
+#define TLS_CIPHER_CHACHA20_POLY1305_IV_SIZE 12
+#define TLS_CIPHER_CHACHA20_POLY1305_KEY_SIZE 32
+#define TLS_CIPHER_CHACHA20_POLY1305_SALT_SIZE 0
+#define TLS_CIPHER_CHACHA20_POLY1305_TAG_SIZE 16
+#define TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE 8
+
#define TLS_SET_RECORD_TYPE 1
#define TLS_GET_RECORD_TYPE 2
unsigned char rec_seq[TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE];
};
+struct tls12_crypto_info_chacha20_poly1305 {
+ struct tls_crypto_info info;
+ unsigned char iv[TLS_CIPHER_CHACHA20_POLY1305_IV_SIZE];
+ unsigned char key[TLS_CIPHER_CHACHA20_POLY1305_KEY_SIZE];
+ unsigned char salt[TLS_CIPHER_CHACHA20_POLY1305_SALT_SIZE];
+ unsigned char rec_seq[TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE];
+};
+
enum {
TLS_INFO_UNSPEC,
TLS_INFO_VERSION,
+++ /dev/null
-/*
- * Linux WiMax
- * API for user space
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * - Initial implementation
- *
- *
- * This file declares the user/kernel protocol that is spoken over
- * Generic Netlink, as well as any type declaration that is to be used
- * by kernel and user space.
- *
- * It is intended for user space to clone it verbatim to use it as a
- * primary reference for definitions.
- *
- * Stuff intended for kernel usage as well as full protocol and stack
- * documentation is rooted in include/net/wimax.h.
- */
-
-#ifndef __LINUX__WIMAX_H__
-#define __LINUX__WIMAX_H__
-
-#include <linux/types.h>
-
-enum {
- /**
- * Version of the interface (unsigned decimal, MMm, max 25.5)
- * M - Major: change if removing or modifying an existing call.
- * m - minor: change when adding a new call
- */
- WIMAX_GNL_VERSION = 01,
- /* Generic NetLink attributes */
- WIMAX_GNL_ATTR_INVALID = 0x00,
- WIMAX_GNL_ATTR_MAX = 10,
-};
-
-
-/*
- * Generic NetLink operations
- *
- * Most of these map to an API call; _OP_ stands for operation, _RP_
- * for reply and _RE_ for report (aka: signal).
- */
-enum {
- WIMAX_GNL_OP_MSG_FROM_USER, /* User to kernel message */
- WIMAX_GNL_OP_MSG_TO_USER, /* Kernel to user message */
- WIMAX_GNL_OP_RFKILL, /* Run wimax_rfkill() */
- WIMAX_GNL_OP_RESET, /* Run wimax_rfkill() */
- WIMAX_GNL_RE_STATE_CHANGE, /* Report: status change */
- WIMAX_GNL_OP_STATE_GET, /* Request for current state */
-};
-
-
-/* Message from user / to user */
-enum {
- WIMAX_GNL_MSG_IFIDX = 1,
- WIMAX_GNL_MSG_PIPE_NAME,
- WIMAX_GNL_MSG_DATA,
-};
-
-
-/*
- * wimax_rfkill()
- *
- * The state of the radio (ON/OFF) is mapped to the rfkill subsystem's
- * switch state (DISABLED/ENABLED).
- */
-enum wimax_rf_state {
- WIMAX_RF_OFF = 0, /* Radio is off, rfkill on/enabled */
- WIMAX_RF_ON = 1, /* Radio is on, rfkill off/disabled */
- WIMAX_RF_QUERY = 2,
-};
-
-/* Attributes */
-enum {
- WIMAX_GNL_RFKILL_IFIDX = 1,
- WIMAX_GNL_RFKILL_STATE,
-};
-
-
-/* Attributes for wimax_reset() */
-enum {
- WIMAX_GNL_RESET_IFIDX = 1,
-};
-
-/* Attributes for wimax_state_get() */
-enum {
- WIMAX_GNL_STGET_IFIDX = 1,
-};
-
-/*
- * Attributes for the Report State Change
- *
- * For now we just have the old and new states; new attributes might
- * be added later on.
- */
-enum {
- WIMAX_GNL_STCH_IFIDX = 1,
- WIMAX_GNL_STCH_STATE_OLD,
- WIMAX_GNL_STCH_STATE_NEW,
-};
-
-
-/**
- * enum wimax_st - The different states of a WiMAX device
- * @__WIMAX_ST_NULL: The device structure has been allocated and zeroed,
- * but still wimax_dev_add() hasn't been called. There is no state.
- *
- * @WIMAX_ST_DOWN: The device has been registered with the WiMAX and
- * networking stacks, but it is not initialized (normally that is
- * done with 'ifconfig DEV up' [or equivalent], which can upload
- * firmware and enable communications with the device).
- * In this state, the device is powered down and using as less
- * power as possible.
- * This state is the default after a call to wimax_dev_add(). It
- * is ok to have drivers move directly to %WIMAX_ST_UNINITIALIZED
- * or %WIMAX_ST_RADIO_OFF in _probe() after the call to
- * wimax_dev_add().
- * It is recommended that the driver leaves this state when
- * calling 'ifconfig DEV up' and enters it back on 'ifconfig DEV
- * down'.
- *
- * @__WIMAX_ST_QUIESCING: The device is being torn down, so no API
- * operations are allowed to proceed except the ones needed to
- * complete the device clean up process.
- *
- * @WIMAX_ST_UNINITIALIZED: [optional] Communication with the device
- * is setup, but the device still requires some configuration
- * before being operational.
- * Some WiMAX API calls might work.
- *
- * @WIMAX_ST_RADIO_OFF: The device is fully up; radio is off (wether
- * by hardware or software switches).
- * It is recommended to always leave the device in this state
- * after initialization.
- *
- * @WIMAX_ST_READY: The device is fully up and radio is on.
- *
- * @WIMAX_ST_SCANNING: [optional] The device has been instructed to
- * scan. In this state, the device cannot be actively connected to
- * a network.
- *
- * @WIMAX_ST_CONNECTING: The device is connecting to a network. This
- * state exists because in some devices, the connect process can
- * include a number of negotiations between user space, kernel
- * space and the device. User space needs to know what the device
- * is doing. If the connect sequence in a device is atomic and
- * fast, the device can transition directly to CONNECTED
- *
- * @WIMAX_ST_CONNECTED: The device is connected to a network.
- *
- * @__WIMAX_ST_INVALID: This is an invalid state used to mark the
- * maximum numeric value of states.
- *
- * Description:
- *
- * Transitions from one state to another one are atomic and can only
- * be caused in kernel space with wimax_state_change(). To read the
- * state, use wimax_state_get().
- *
- * States starting with __ are internal and shall not be used or
- * referred to by drivers or userspace. They look ugly, but that's the
- * point -- if any use is made non-internal to the stack, it is easier
- * to catch on review.
- *
- * All API operations [with well defined exceptions] will take the
- * device mutex before starting and then check the state. If the state
- * is %__WIMAX_ST_NULL, %WIMAX_ST_DOWN, %WIMAX_ST_UNINITIALIZED or
- * %__WIMAX_ST_QUIESCING, it will drop the lock and quit with
- * -%EINVAL, -%ENOMEDIUM, -%ENOTCONN or -%ESHUTDOWN.
- *
- * The order of the definitions is important, so we can do numerical
- * comparisons (eg: < %WIMAX_ST_RADIO_OFF means the device is not ready
- * to operate).
- */
-/*
- * The allowed state transitions are described in the table below
- * (states in rows can go to states in columns where there is an X):
- *
- * UNINI RADIO READY SCAN CONNEC CONNEC
- * NULL DOWN QUIESCING TIALIZED OFF NING TING TED
- * NULL - x
- * DOWN - x x x
- * QUIESCING x -
- * UNINITIALIZED x - x
- * RADIO_OFF x - x
- * READY x x - x x x
- * SCANNING x x x - x x
- * CONNECTING x x x x - x
- * CONNECTED x x x -
- *
- * This table not available in kernel-doc because the formatting messes it up.
- */
- enum wimax_st {
- __WIMAX_ST_NULL = 0,
- WIMAX_ST_DOWN,
- __WIMAX_ST_QUIESCING,
- WIMAX_ST_UNINITIALIZED,
- WIMAX_ST_RADIO_OFF,
- WIMAX_ST_READY,
- WIMAX_ST_SCANNING,
- WIMAX_ST_CONNECTING,
- WIMAX_ST_CONNECTED,
- __WIMAX_ST_INVALID /* Always keep last */
-};
-
-
-#endif /* #ifndef __LINUX__WIMAX_H__ */
+++ /dev/null
-/*
- * Intel Wireless WiMax Connection 2400m
- * Host-Device protocol interface definitions
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. 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 of 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.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * - Initial implementation
- *
- *
- * This header defines the data structures and constants used to
- * communicate with the device.
- *
- * BOOTMODE/BOOTROM/FIRMWARE UPLOAD PROTOCOL
- *
- * The firmware upload protocol is quite simple and only requires a
- * handful of commands. See drivers/net/wimax/i2400m/fw.c for more
- * details.
- *
- * The BCF data structure is for the firmware file header.
- *
- *
- * THE DATA / CONTROL PROTOCOL
- *
- * This is the normal protocol spoken with the device once the
- * firmware is uploaded. It transports data payloads and control
- * messages back and forth.
- *
- * It consists 'messages' that pack one or more payloads each. The
- * format is described in detail in drivers/net/wimax/i2400m/rx.c and
- * tx.c.
- *
- *
- * THE L3L4 PROTOCOL
- *
- * The term L3L4 refers to Layer 3 (the device), Layer 4 (the
- * driver/host software).
- *
- * This is the control protocol used by the host to control the i2400m
- * device (scan, connect, disconnect...). This is sent to / received
- * as control frames. These frames consist of a header and zero or
- * more TLVs with information. We call each control frame a "message".
- *
- * Each message is composed of:
- *
- * HEADER
- * [TLV0 + PAYLOAD0]
- * [TLV1 + PAYLOAD1]
- * [...]
- * [TLVN + PAYLOADN]
- *
- * The HEADER is defined by 'struct i2400m_l3l4_hdr'. The payloads are
- * defined by a TLV structure (Type Length Value) which is a 'header'
- * (struct i2400m_tlv_hdr) and then the payload.
- *
- * All integers are represented as Little Endian.
- *
- * - REQUESTS AND EVENTS
- *
- * The requests can be clasified as follows:
- *
- * COMMAND: implies a request from the host to the device requesting
- * an action being performed. The device will reply with a
- * message (with the same type as the command), status and
- * no (TLV) payload. Execution of a command might cause
- * events (of different type) to be sent later on as
- * device's state changes.
- *
- * GET/SET: similar to COMMAND, but will not cause other
- * EVENTs. The reply, in the case of GET, will contain
- * TLVs with the requested information.
- *
- * EVENT: asynchronous messages sent from the device, maybe as a
- * consequence of previous COMMANDs but disassociated from
- * them.
- *
- * Only one request might be pending at the same time (ie: don't
- * parallelize nor post another GET request before the previous
- * COMMAND has been acknowledged with it's corresponding reply by the
- * device).
- *
- * The different requests and their formats are described below:
- *
- * I2400M_MT_* Message types
- * I2400M_MS_* Message status (for replies, events)
- * i2400m_tlv_* TLVs
- *
- * data types are named 'struct i2400m_msg_OPNAME', OPNAME matching the
- * operation.
- */
-
-#ifndef __LINUX__WIMAX__I2400M_H__
-#define __LINUX__WIMAX__I2400M_H__
-
-#include <linux/types.h>
-#include <linux/if_ether.h>
-
-/*
- * Host Device Interface (HDI) common to all busses
- */
-
-/* Boot-mode (firmware upload mode) commands */
-
-/* Header for the firmware file */
-struct i2400m_bcf_hdr {
- __le32 module_type;
- __le32 header_len;
- __le32 header_version;
- __le32 module_id;
- __le32 module_vendor;
- __le32 date; /* BCD YYYMMDD */
- __le32 size; /* in dwords */
- __le32 key_size; /* in dwords */
- __le32 modulus_size; /* in dwords */
- __le32 exponent_size; /* in dwords */
- __u8 reserved[88];
-} __attribute__ ((packed));
-
-/* Boot mode opcodes */
-enum i2400m_brh_opcode {
- I2400M_BRH_READ = 1,
- I2400M_BRH_WRITE = 2,
- I2400M_BRH_JUMP = 3,
- I2400M_BRH_SIGNED_JUMP = 8,
- I2400M_BRH_HASH_PAYLOAD_ONLY = 9,
-};
-
-/* Boot mode command masks and stuff */
-enum i2400m_brh {
- I2400M_BRH_SIGNATURE = 0xcbbc0000,
- I2400M_BRH_SIGNATURE_MASK = 0xffff0000,
- I2400M_BRH_SIGNATURE_SHIFT = 16,
- I2400M_BRH_OPCODE_MASK = 0x0000000f,
- I2400M_BRH_RESPONSE_MASK = 0x000000f0,
- I2400M_BRH_RESPONSE_SHIFT = 4,
- I2400M_BRH_DIRECT_ACCESS = 0x00000400,
- I2400M_BRH_RESPONSE_REQUIRED = 0x00000200,
- I2400M_BRH_USE_CHECKSUM = 0x00000100,
-};
-
-
-/**
- * i2400m_bootrom_header - Header for a boot-mode command
- *
- * @cmd: the above command descriptor
- * @target_addr: where on the device memory should the action be performed.
- * @data_size: for read/write, amount of data to be read/written
- * @block_checksum: checksum value (if applicable)
- * @payload: the beginning of data attached to this header
- */
-struct i2400m_bootrom_header {
- __le32 command; /* Compose with enum i2400_brh */
- __le32 target_addr;
- __le32 data_size;
- __le32 block_checksum;
- char payload[0];
-} __attribute__ ((packed));
-
-
-/*
- * Data / control protocol
- */
-
-/* Packet types for the host-device interface */
-enum i2400m_pt {
- I2400M_PT_DATA = 0,
- I2400M_PT_CTRL,
- I2400M_PT_TRACE, /* For device debug */
- I2400M_PT_RESET_WARM, /* device reset */
- I2400M_PT_RESET_COLD, /* USB[transport] reset, like reconnect */
- I2400M_PT_EDATA, /* Extended RX data */
- I2400M_PT_ILLEGAL
-};
-
-
-/*
- * Payload for a data packet
- *
- * This is prefixed to each and every outgoing DATA type.
- */
-struct i2400m_pl_data_hdr {
- __le32 reserved;
-} __attribute__((packed));
-
-
-/*
- * Payload for an extended data packet
- *
- * New in fw v1.4
- *
- * @reorder: if this payload has to be reorder or not (and how)
- * @cs: the type of data in the packet, as defined per (802.16e
- * T11.13.19.1). Currently only 2 (IPv4 packet) supported.
- *
- * This is prefixed to each and every INCOMING DATA packet.
- */
-struct i2400m_pl_edata_hdr {
- __le32 reorder; /* bits defined in i2400m_ro */
- __u8 cs;
- __u8 reserved[11];
-} __attribute__((packed));
-
-enum i2400m_cs {
- I2400M_CS_IPV4_0 = 0,
- I2400M_CS_IPV4 = 2,
-};
-
-enum i2400m_ro {
- I2400M_RO_NEEDED = 0x01,
- I2400M_RO_TYPE = 0x03,
- I2400M_RO_TYPE_SHIFT = 1,
- I2400M_RO_CIN = 0x0f,
- I2400M_RO_CIN_SHIFT = 4,
- I2400M_RO_FBN = 0x07ff,
- I2400M_RO_FBN_SHIFT = 8,
- I2400M_RO_SN = 0x07ff,
- I2400M_RO_SN_SHIFT = 21,
-};
-
-enum i2400m_ro_type {
- I2400M_RO_TYPE_RESET = 0,
- I2400M_RO_TYPE_PACKET,
- I2400M_RO_TYPE_WS,
- I2400M_RO_TYPE_PACKET_WS,
-};
-
-
-/* Misc constants */
-enum {
- I2400M_PL_ALIGN = 16, /* Payload data size alignment */
- I2400M_PL_SIZE_MAX = 0x3EFF,
- I2400M_MAX_PLS_IN_MSG = 60,
- /* protocol barkers: sync sequences; for notifications they
- * are sent in groups of four. */
- I2400M_H2D_PREVIEW_BARKER = 0xcafe900d,
- I2400M_COLD_RESET_BARKER = 0xc01dc01d,
- I2400M_WARM_RESET_BARKER = 0x50f750f7,
- I2400M_NBOOT_BARKER = 0xdeadbeef,
- I2400M_SBOOT_BARKER = 0x0ff1c1a1,
- I2400M_SBOOT_BARKER_6050 = 0x80000001,
- I2400M_ACK_BARKER = 0xfeedbabe,
- I2400M_D2H_MSG_BARKER = 0xbeefbabe,
-};
-
-
-/*
- * Hardware payload descriptor
- *
- * Bitfields encoded in a struct to enforce typing semantics.
- *
- * Look in rx.c and tx.c for a full description of the format.
- */
-struct i2400m_pld {
- __le32 val;
-} __attribute__ ((packed));
-
-#define I2400M_PLD_SIZE_MASK 0x00003fff
-#define I2400M_PLD_TYPE_SHIFT 16
-#define I2400M_PLD_TYPE_MASK 0x000f0000
-
-/*
- * Header for a TX message or RX message
- *
- * @barker: preamble
- * @size: used for management of the FIFO queue buffer; before
- * sending, this is converted to be a real preamble. This
- * indicates the real size of the TX message that starts at this
- * point. If the highest bit is set, then this message is to be
- * skipped.
- * @sequence: sequence number of this message
- * @offset: offset where the message itself starts -- see the comments
- * in the file header about message header and payload descriptor
- * alignment.
- * @num_pls: number of payloads in this message
- * @padding: amount of padding bytes at the end of the message to make
- * it be of block-size aligned
- *
- * Look in rx.c and tx.c for a full description of the format.
- */
-struct i2400m_msg_hdr {
- union {
- __le32 barker;
- __u32 size; /* same size type as barker!! */
- };
- union {
- __le32 sequence;
- __u32 offset; /* same size type as barker!! */
- };
- __le16 num_pls;
- __le16 rsv1;
- __le16 padding;
- __le16 rsv2;
- struct i2400m_pld pld[0];
-} __attribute__ ((packed));
-
-
-
-/*
- * L3/L4 control protocol
- */
-
-enum {
- /* Interface version */
- I2400M_L3L4_VERSION = 0x0100,
-};
-
-/* Message types */
-enum i2400m_mt {
- I2400M_MT_RESERVED = 0x0000,
- I2400M_MT_INVALID = 0xffff,
- I2400M_MT_REPORT_MASK = 0x8000,
-
- I2400M_MT_GET_SCAN_RESULT = 0x4202,
- I2400M_MT_SET_SCAN_PARAM = 0x4402,
- I2400M_MT_CMD_RF_CONTROL = 0x4602,
- I2400M_MT_CMD_SCAN = 0x4603,
- I2400M_MT_CMD_CONNECT = 0x4604,
- I2400M_MT_CMD_DISCONNECT = 0x4605,
- I2400M_MT_CMD_EXIT_IDLE = 0x4606,
- I2400M_MT_GET_LM_VERSION = 0x5201,
- I2400M_MT_GET_DEVICE_INFO = 0x5202,
- I2400M_MT_GET_LINK_STATUS = 0x5203,
- I2400M_MT_GET_STATISTICS = 0x5204,
- I2400M_MT_GET_STATE = 0x5205,
- I2400M_MT_GET_MEDIA_STATUS = 0x5206,
- I2400M_MT_SET_INIT_CONFIG = 0x5404,
- I2400M_MT_CMD_INIT = 0x5601,
- I2400M_MT_CMD_TERMINATE = 0x5602,
- I2400M_MT_CMD_MODE_OF_OP = 0x5603,
- I2400M_MT_CMD_RESET_DEVICE = 0x5604,
- I2400M_MT_CMD_MONITOR_CONTROL = 0x5605,
- I2400M_MT_CMD_ENTER_POWERSAVE = 0x5606,
- I2400M_MT_GET_TLS_OPERATION_RESULT = 0x6201,
- I2400M_MT_SET_EAP_SUCCESS = 0x6402,
- I2400M_MT_SET_EAP_FAIL = 0x6403,
- I2400M_MT_SET_EAP_KEY = 0x6404,
- I2400M_MT_CMD_SEND_EAP_RESPONSE = 0x6602,
- I2400M_MT_REPORT_SCAN_RESULT = 0xc002,
- I2400M_MT_REPORT_STATE = 0xd002,
- I2400M_MT_REPORT_POWERSAVE_READY = 0xd005,
- I2400M_MT_REPORT_EAP_REQUEST = 0xe002,
- I2400M_MT_REPORT_EAP_RESTART = 0xe003,
- I2400M_MT_REPORT_ALT_ACCEPT = 0xe004,
- I2400M_MT_REPORT_KEY_REQUEST = 0xe005,
-};
-
-
-/*
- * Message Ack Status codes
- *
- * When a message is replied-to, this status is reported.
- */
-enum i2400m_ms {
- I2400M_MS_DONE_OK = 0,
- I2400M_MS_DONE_IN_PROGRESS = 1,
- I2400M_MS_INVALID_OP = 2,
- I2400M_MS_BAD_STATE = 3,
- I2400M_MS_ILLEGAL_VALUE = 4,
- I2400M_MS_MISSING_PARAMS = 5,
- I2400M_MS_VERSION_ERROR = 6,
- I2400M_MS_ACCESSIBILITY_ERROR = 7,
- I2400M_MS_BUSY = 8,
- I2400M_MS_CORRUPTED_TLV = 9,
- I2400M_MS_UNINITIALIZED = 10,
- I2400M_MS_UNKNOWN_ERROR = 11,
- I2400M_MS_PRODUCTION_ERROR = 12,
- I2400M_MS_NO_RF = 13,
- I2400M_MS_NOT_READY_FOR_POWERSAVE = 14,
- I2400M_MS_THERMAL_CRITICAL = 15,
- I2400M_MS_MAX
-};
-
-
-/**
- * i2400m_tlv - enumeration of the different types of TLVs
- *
- * TLVs stand for type-length-value and are the header for a payload
- * composed of almost anything. Each payload has a type assigned
- * and a length.
- */
-enum i2400m_tlv {
- I2400M_TLV_L4_MESSAGE_VERSIONS = 129,
- I2400M_TLV_SYSTEM_STATE = 141,
- I2400M_TLV_MEDIA_STATUS = 161,
- I2400M_TLV_RF_OPERATION = 162,
- I2400M_TLV_RF_STATUS = 163,
- I2400M_TLV_DEVICE_RESET_TYPE = 132,
- I2400M_TLV_CONFIG_IDLE_PARAMETERS = 601,
- I2400M_TLV_CONFIG_IDLE_TIMEOUT = 611,
- I2400M_TLV_CONFIG_D2H_DATA_FORMAT = 614,
- I2400M_TLV_CONFIG_DL_HOST_REORDER = 615,
-};
-
-
-struct i2400m_tlv_hdr {
- __le16 type;
- __le16 length; /* payload's */
- __u8 pl[0];
-} __attribute__((packed));
-
-
-struct i2400m_l3l4_hdr {
- __le16 type;
- __le16 length; /* payload's */
- __le16 version;
- __le16 resv1;
- __le16 status;
- __le16 resv2;
- struct i2400m_tlv_hdr pl[0];
-} __attribute__((packed));
-
-
-/**
- * i2400m_system_state - different states of the device
- */
-enum i2400m_system_state {
- I2400M_SS_UNINITIALIZED = 1,
- I2400M_SS_INIT,
- I2400M_SS_READY,
- I2400M_SS_SCAN,
- I2400M_SS_STANDBY,
- I2400M_SS_CONNECTING,
- I2400M_SS_WIMAX_CONNECTED,
- I2400M_SS_DATA_PATH_CONNECTED,
- I2400M_SS_IDLE,
- I2400M_SS_DISCONNECTING,
- I2400M_SS_OUT_OF_ZONE,
- I2400M_SS_SLEEPACTIVE,
- I2400M_SS_PRODUCTION,
- I2400M_SS_CONFIG,
- I2400M_SS_RF_OFF,
- I2400M_SS_RF_SHUTDOWN,
- I2400M_SS_DEVICE_DISCONNECT,
- I2400M_SS_MAX,
-};
-
-
-/**
- * i2400m_tlv_system_state - report on the state of the system
- *
- * @state: see enum i2400m_system_state
- */
-struct i2400m_tlv_system_state {
- struct i2400m_tlv_hdr hdr;
- __le32 state;
-} __attribute__((packed));
-
-
-struct i2400m_tlv_l4_message_versions {
- struct i2400m_tlv_hdr hdr;
- __le16 major;
- __le16 minor;
- __le16 branch;
- __le16 reserved;
-} __attribute__((packed));
-
-
-struct i2400m_tlv_detailed_device_info {
- struct i2400m_tlv_hdr hdr;
- __u8 reserved1[400];
- __u8 mac_address[ETH_ALEN];
- __u8 reserved2[2];
-} __attribute__((packed));
-
-
-enum i2400m_rf_switch_status {
- I2400M_RF_SWITCH_ON = 1,
- I2400M_RF_SWITCH_OFF = 2,
-};
-
-struct i2400m_tlv_rf_switches_status {
- struct i2400m_tlv_hdr hdr;
- __u8 sw_rf_switch; /* 1 ON, 2 OFF */
- __u8 hw_rf_switch; /* 1 ON, 2 OFF */
- __u8 reserved[2];
-} __attribute__((packed));
-
-
-enum {
- i2400m_rf_operation_on = 1,
- i2400m_rf_operation_off = 2
-};
-
-struct i2400m_tlv_rf_operation {
- struct i2400m_tlv_hdr hdr;
- __le32 status; /* 1 ON, 2 OFF */
-} __attribute__((packed));
-
-
-enum i2400m_tlv_reset_type {
- I2400M_RESET_TYPE_COLD = 1,
- I2400M_RESET_TYPE_WARM
-};
-
-struct i2400m_tlv_device_reset_type {
- struct i2400m_tlv_hdr hdr;
- __le32 reset_type;
-} __attribute__((packed));
-
-
-struct i2400m_tlv_config_idle_parameters {
- struct i2400m_tlv_hdr hdr;
- __le32 idle_timeout; /* 100 to 300000 ms [5min], 100 increments
- * 0 disabled */
- __le32 idle_paging_interval; /* frames */
-} __attribute__((packed));
-
-
-enum i2400m_media_status {
- I2400M_MEDIA_STATUS_LINK_UP = 1,
- I2400M_MEDIA_STATUS_LINK_DOWN,
- I2400M_MEDIA_STATUS_LINK_RENEW,
-};
-
-struct i2400m_tlv_media_status {
- struct i2400m_tlv_hdr hdr;
- __le32 media_status;
-} __attribute__((packed));
-
-
-/* New in v1.4 */
-struct i2400m_tlv_config_idle_timeout {
- struct i2400m_tlv_hdr hdr;
- __le32 timeout; /* 100 to 300000 ms [5min], 100 increments
- * 0 disabled */
-} __attribute__((packed));
-
-/* New in v1.4 -- for backward compat, will be removed */
-struct i2400m_tlv_config_d2h_data_format {
- struct i2400m_tlv_hdr hdr;
- __u8 format; /* 0 old format, 1 enhanced */
- __u8 reserved[3];
-} __attribute__((packed));
-
-/* New in v1.4 */
-struct i2400m_tlv_config_dl_host_reorder {
- struct i2400m_tlv_hdr hdr;
- __u8 reorder; /* 0 disabled, 1 enabled */
- __u8 reserved[3];
-} __attribute__((packed));
-
-
-#endif /* #ifndef __LINUX__WIMAX__I2400M_H__ */
MLX5_IB_ATTR_QUERY_CONTEXT_RESP_UCTX = (1U << UVERBS_ID_NS_SHIFT),
};
-#define MLX5_IB_DW_MATCH_PARAM 0x80
+#define MLX5_IB_DW_MATCH_PARAM 0x90
struct mlx5_ib_match_params {
__u32 match_params[MLX5_IB_DW_MATCH_PARAM];
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) += local_storage.o queue_stack_maps.o ringbuf.o
obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o
+obj-${CONFIG_BPF_LSM} += bpf_task_storage.o
obj-$(CONFIG_BPF_SYSCALL) += disasm.o
obj-$(CONFIG_BPF_JIT) += trampoline.o
obj-$(CONFIG_BPF_SYSCALL) += btf.o
iter_priv->done_stop = true;
}
+static bool bpf_iter_support_resched(struct seq_file *seq)
+{
+ struct bpf_iter_priv_data *iter_priv;
+
+ iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
+ target_private);
+ return iter_priv->tinfo->reg_info->feature & BPF_ITER_RESCHED;
+}
+
/* maximum visited objects before bailing out */
#define MAX_ITER_OBJECTS 1000000
struct seq_file *seq = file->private_data;
size_t n, offs, copied = 0;
int err = 0, num_objs = 0;
+ bool can_resched;
void *p;
mutex_lock(&seq->lock);
goto done;
}
+ can_resched = bpf_iter_support_resched(seq);
while (1) {
loff_t pos = seq->index;
}
break;
}
+
+ if (can_resched)
+ cond_resched();
}
stop:
offs = seq->count;
return &bpf_sk_storage_get_proto;
case BPF_FUNC_sk_storage_delete:
return &bpf_sk_storage_delete_proto;
+ case BPF_FUNC_spin_lock:
+ return &bpf_spin_lock_proto;
+ case BPF_FUNC_spin_unlock:
+ return &bpf_spin_unlock_proto;
+ case BPF_FUNC_task_storage_get:
+ return &bpf_task_storage_get_proto;
+ case BPF_FUNC_task_storage_delete:
+ return &bpf_task_storage_delete_proto;
default:
return tracing_prog_func_proto(func_id, prog);
}
}
+/* The set of hooks which are called without pagefaults disabled and are allowed
+ * to "sleep" and thus can be used for sleeable BPF programs.
+ */
+BTF_SET_START(sleepable_lsm_hooks)
+BTF_ID(func, bpf_lsm_bpf)
+BTF_ID(func, bpf_lsm_bpf_map)
+BTF_ID(func, bpf_lsm_bpf_map_alloc_security)
+BTF_ID(func, bpf_lsm_bpf_map_free_security)
+BTF_ID(func, bpf_lsm_bpf_prog)
+BTF_ID(func, bpf_lsm_bprm_check_security)
+BTF_ID(func, bpf_lsm_bprm_committed_creds)
+BTF_ID(func, bpf_lsm_bprm_committing_creds)
+BTF_ID(func, bpf_lsm_bprm_creds_for_exec)
+BTF_ID(func, bpf_lsm_bprm_creds_from_file)
+BTF_ID(func, bpf_lsm_capget)
+BTF_ID(func, bpf_lsm_capset)
+BTF_ID(func, bpf_lsm_cred_prepare)
+BTF_ID(func, bpf_lsm_file_ioctl)
+BTF_ID(func, bpf_lsm_file_lock)
+BTF_ID(func, bpf_lsm_file_open)
+BTF_ID(func, bpf_lsm_file_receive)
+BTF_ID(func, bpf_lsm_inet_conn_established)
+BTF_ID(func, bpf_lsm_inode_create)
+BTF_ID(func, bpf_lsm_inode_free_security)
+BTF_ID(func, bpf_lsm_inode_getattr)
+BTF_ID(func, bpf_lsm_inode_getxattr)
+BTF_ID(func, bpf_lsm_inode_mknod)
+BTF_ID(func, bpf_lsm_inode_need_killpriv)
+BTF_ID(func, bpf_lsm_inode_post_setxattr)
+BTF_ID(func, bpf_lsm_inode_readlink)
+BTF_ID(func, bpf_lsm_inode_rename)
+BTF_ID(func, bpf_lsm_inode_rmdir)
+BTF_ID(func, bpf_lsm_inode_setattr)
+BTF_ID(func, bpf_lsm_inode_setxattr)
+BTF_ID(func, bpf_lsm_inode_symlink)
+BTF_ID(func, bpf_lsm_inode_unlink)
+BTF_ID(func, bpf_lsm_kernel_module_request)
+BTF_ID(func, bpf_lsm_kernfs_init_security)
+BTF_ID(func, bpf_lsm_key_free)
+BTF_ID(func, bpf_lsm_mmap_file)
+BTF_ID(func, bpf_lsm_netlink_send)
+BTF_ID(func, bpf_lsm_path_notify)
+BTF_ID(func, bpf_lsm_release_secctx)
+BTF_ID(func, bpf_lsm_sb_alloc_security)
+BTF_ID(func, bpf_lsm_sb_eat_lsm_opts)
+BTF_ID(func, bpf_lsm_sb_kern_mount)
+BTF_ID(func, bpf_lsm_sb_mount)
+BTF_ID(func, bpf_lsm_sb_remount)
+BTF_ID(func, bpf_lsm_sb_set_mnt_opts)
+BTF_ID(func, bpf_lsm_sb_show_options)
+BTF_ID(func, bpf_lsm_sb_statfs)
+BTF_ID(func, bpf_lsm_sb_umount)
+BTF_ID(func, bpf_lsm_settime)
+BTF_ID(func, bpf_lsm_socket_accept)
+BTF_ID(func, bpf_lsm_socket_bind)
+BTF_ID(func, bpf_lsm_socket_connect)
+BTF_ID(func, bpf_lsm_socket_create)
+BTF_ID(func, bpf_lsm_socket_getpeername)
+BTF_ID(func, bpf_lsm_socket_getpeersec_dgram)
+BTF_ID(func, bpf_lsm_socket_getsockname)
+BTF_ID(func, bpf_lsm_socket_getsockopt)
+BTF_ID(func, bpf_lsm_socket_listen)
+BTF_ID(func, bpf_lsm_socket_post_create)
+BTF_ID(func, bpf_lsm_socket_recvmsg)
+BTF_ID(func, bpf_lsm_socket_sendmsg)
+BTF_ID(func, bpf_lsm_socket_shutdown)
+BTF_ID(func, bpf_lsm_socket_socketpair)
+BTF_ID(func, bpf_lsm_syslog)
+BTF_ID(func, bpf_lsm_task_alloc)
+BTF_ID(func, bpf_lsm_task_getsecid)
+BTF_ID(func, bpf_lsm_task_prctl)
+BTF_ID(func, bpf_lsm_task_setscheduler)
+BTF_ID(func, bpf_lsm_task_to_inode)
+BTF_SET_END(sleepable_lsm_hooks)
+
+bool bpf_lsm_is_sleepable_hook(u32 btf_id)
+{
+ return btf_id_set_contains(&sleepable_lsm_hooks, btf_id);
+}
+
const struct bpf_prog_ops lsm_prog_ops = {
};
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020 Facebook
+ * Copyright 2020 Google LLC.
+ */
+
+#include <linux/pid.h>
+#include <linux/sched.h>
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <linux/bpf_local_storage.h>
+#include <linux/filter.h>
+#include <uapi/linux/btf.h>
+#include <linux/bpf_lsm.h>
+#include <linux/btf_ids.h>
+#include <linux/fdtable.h>
+
+DEFINE_BPF_STORAGE_CACHE(task_cache);
+
+static struct bpf_local_storage __rcu **task_storage_ptr(void *owner)
+{
+ struct task_struct *task = owner;
+ struct bpf_storage_blob *bsb;
+
+ bsb = bpf_task(task);
+ if (!bsb)
+ return NULL;
+ return &bsb->storage;
+}
+
+static struct bpf_local_storage_data *
+task_storage_lookup(struct task_struct *task, struct bpf_map *map,
+ bool cacheit_lockit)
+{
+ struct bpf_local_storage *task_storage;
+ struct bpf_local_storage_map *smap;
+ struct bpf_storage_blob *bsb;
+
+ bsb = bpf_task(task);
+ if (!bsb)
+ return NULL;
+
+ task_storage = rcu_dereference(bsb->storage);
+ if (!task_storage)
+ return NULL;
+
+ smap = (struct bpf_local_storage_map *)map;
+ return bpf_local_storage_lookup(task_storage, smap, cacheit_lockit);
+}
+
+void bpf_task_storage_free(struct task_struct *task)
+{
+ struct bpf_local_storage_elem *selem;
+ struct bpf_local_storage *local_storage;
+ bool free_task_storage = false;
+ struct bpf_storage_blob *bsb;
+ struct hlist_node *n;
+
+ bsb = bpf_task(task);
+ if (!bsb)
+ return;
+
+ rcu_read_lock();
+
+ local_storage = rcu_dereference(bsb->storage);
+ if (!local_storage) {
+ rcu_read_unlock();
+ return;
+ }
+
+ /* Neither the bpf_prog nor the bpf-map's syscall
+ * could be modifying the local_storage->list now.
+ * Thus, no elem can be added-to or deleted-from the
+ * local_storage->list by the bpf_prog or by the bpf-map's syscall.
+ *
+ * It is racing with bpf_local_storage_map_free() alone
+ * when unlinking elem from the local_storage->list and
+ * the map's bucket->list.
+ */
+ raw_spin_lock_bh(&local_storage->lock);
+ hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) {
+ /* Always unlink from map before unlinking from
+ * local_storage.
+ */
+ bpf_selem_unlink_map(selem);
+ free_task_storage = bpf_selem_unlink_storage_nolock(
+ local_storage, selem, false);
+ }
+ raw_spin_unlock_bh(&local_storage->lock);
+ rcu_read_unlock();
+
+ /* free_task_storage should always be true as long as
+ * local_storage->list was non-empty.
+ */
+ if (free_task_storage)
+ kfree_rcu(local_storage, rcu);
+}
+
+static void *bpf_pid_task_storage_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_local_storage_data *sdata;
+ struct task_struct *task;
+ unsigned int f_flags;
+ struct pid *pid;
+ int fd, err;
+
+ fd = *(int *)key;
+ pid = pidfd_get_pid(fd, &f_flags);
+ if (IS_ERR(pid))
+ return ERR_CAST(pid);
+
+ /* We should be in an RCU read side critical section, it should be safe
+ * to call pid_task.
+ */
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ task = pid_task(pid, PIDTYPE_PID);
+ if (!task) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ sdata = task_storage_lookup(task, map, true);
+ put_pid(pid);
+ return sdata ? sdata->data : NULL;
+out:
+ put_pid(pid);
+ return ERR_PTR(err);
+}
+
+static int bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags)
+{
+ struct bpf_local_storage_data *sdata;
+ struct task_struct *task;
+ unsigned int f_flags;
+ struct pid *pid;
+ int fd, err;
+
+ fd = *(int *)key;
+ pid = pidfd_get_pid(fd, &f_flags);
+ if (IS_ERR(pid))
+ return PTR_ERR(pid);
+
+ /* We should be in an RCU read side critical section, it should be safe
+ * to call pid_task.
+ */
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ task = pid_task(pid, PIDTYPE_PID);
+ if (!task || !task_storage_ptr(task)) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ sdata = bpf_local_storage_update(
+ task, (struct bpf_local_storage_map *)map, value, map_flags);
+
+ err = PTR_ERR_OR_ZERO(sdata);
+out:
+ put_pid(pid);
+ return err;
+}
+
+static int task_storage_delete(struct task_struct *task, struct bpf_map *map)
+{
+ struct bpf_local_storage_data *sdata;
+
+ sdata = task_storage_lookup(task, map, false);
+ if (!sdata)
+ return -ENOENT;
+
+ bpf_selem_unlink(SELEM(sdata));
+
+ return 0;
+}
+
+static int bpf_pid_task_storage_delete_elem(struct bpf_map *map, void *key)
+{
+ struct task_struct *task;
+ unsigned int f_flags;
+ struct pid *pid;
+ int fd, err;
+
+ fd = *(int *)key;
+ pid = pidfd_get_pid(fd, &f_flags);
+ if (IS_ERR(pid))
+ return PTR_ERR(pid);
+
+ /* We should be in an RCU read side critical section, it should be safe
+ * to call pid_task.
+ */
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ task = pid_task(pid, PIDTYPE_PID);
+ if (!task) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ err = task_storage_delete(task, map);
+out:
+ put_pid(pid);
+ return err;
+}
+
+BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *,
+ task, void *, value, u64, flags)
+{
+ struct bpf_local_storage_data *sdata;
+
+ if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
+ return (unsigned long)NULL;
+
+ /* explicitly check that the task_storage_ptr is not
+ * NULL as task_storage_lookup returns NULL in this case and
+ * bpf_local_storage_update expects the owner to have a
+ * valid storage pointer.
+ */
+ if (!task_storage_ptr(task))
+ return (unsigned long)NULL;
+
+ sdata = task_storage_lookup(task, map, true);
+ if (sdata)
+ return (unsigned long)sdata->data;
+
+ /* This helper must only be called from places where the lifetime of the task
+ * is guaranteed. Either by being refcounted or by being protected
+ * by an RCU read-side critical section.
+ */
+ if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) {
+ sdata = bpf_local_storage_update(
+ task, (struct bpf_local_storage_map *)map, value,
+ BPF_NOEXIST);
+ return IS_ERR(sdata) ? (unsigned long)NULL :
+ (unsigned long)sdata->data;
+ }
+
+ return (unsigned long)NULL;
+}
+
+BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *,
+ task)
+{
+ /* This helper must only be called from places where the lifetime of the task
+ * is guaranteed. Either by being refcounted or by being protected
+ * by an RCU read-side critical section.
+ */
+ return task_storage_delete(task, map);
+}
+
+static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+ return -ENOTSUPP;
+}
+
+static struct bpf_map *task_storage_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_local_storage_map *smap;
+
+ smap = bpf_local_storage_map_alloc(attr);
+ if (IS_ERR(smap))
+ return ERR_CAST(smap);
+
+ smap->cache_idx = bpf_local_storage_cache_idx_get(&task_cache);
+ return &smap->map;
+}
+
+static void task_storage_map_free(struct bpf_map *map)
+{
+ struct bpf_local_storage_map *smap;
+
+ smap = (struct bpf_local_storage_map *)map;
+ bpf_local_storage_cache_idx_free(&task_cache, smap->cache_idx);
+ bpf_local_storage_map_free(smap);
+}
+
+static int task_storage_map_btf_id;
+const struct bpf_map_ops task_storage_map_ops = {
+ .map_meta_equal = bpf_map_meta_equal,
+ .map_alloc_check = bpf_local_storage_map_alloc_check,
+ .map_alloc = task_storage_map_alloc,
+ .map_free = task_storage_map_free,
+ .map_get_next_key = notsupp_get_next_key,
+ .map_lookup_elem = bpf_pid_task_storage_lookup_elem,
+ .map_update_elem = bpf_pid_task_storage_update_elem,
+ .map_delete_elem = bpf_pid_task_storage_delete_elem,
+ .map_check_btf = bpf_local_storage_map_check_btf,
+ .map_btf_name = "bpf_local_storage_map",
+ .map_btf_id = &task_storage_map_btf_id,
+ .map_owner_storage_ptr = task_storage_ptr,
+};
+
+BTF_ID_LIST_SINGLE(bpf_task_storage_btf_ids, struct, task_struct)
+
+const struct bpf_func_proto bpf_task_storage_get_proto = {
+ .func = bpf_task_storage_get,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg2_btf_id = &bpf_task_storage_btf_ids[0],
+ .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg4_type = ARG_ANYTHING,
+};
+
+const struct bpf_func_proto bpf_task_storage_delete_proto = {
+ .func = bpf_task_storage_delete,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg2_btf_id = &bpf_task_storage_btf_ids[0],
+};
#include <linux/skmsg.h>
#include <linux/perf_event.h>
#include <linux/bsearch.h>
-#include <linux/btf_ids.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
#include <net/sock.h>
/* BTF (BPF Type Format) is the meta data format which describes
const char *strings;
void *nohdr_data;
struct btf_header hdr;
- u32 nr_types;
+ u32 nr_types; /* includes VOID for base BTF */
u32 types_size;
u32 data_size;
refcount_t refcnt;
u32 id;
struct rcu_head rcu;
+
+ /* split BTF support */
+ struct btf *base_btf;
+ u32 start_id; /* first type ID in this BTF (0 for base BTF) */
+ u32 start_str_off; /* first string offset (0 for base BTF) */
+ char name[MODULE_NAME_LEN];
+ bool kernel_btf;
};
enum verifier_phase {
return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
}
+static u32 btf_nr_types_total(const struct btf *btf)
+{
+ u32 total = 0;
+
+ while (btf) {
+ total += btf->nr_types;
+ btf = btf->base_btf;
+ }
+
+ return total;
+}
+
s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind)
{
const struct btf_type *t;
const char *tname;
- u32 i;
+ u32 i, total;
- for (i = 1; i <= btf->nr_types; i++) {
- t = btf->types[i];
+ total = btf_nr_types_total(btf);
+ for (i = 1; i < total; i++) {
+ t = btf_type_by_id(btf, i);
if (BTF_INFO_KIND(t->info) != kind)
continue;
static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
{
- return BTF_STR_OFFSET_VALID(offset) &&
- offset < btf->hdr.str_len;
+ if (!BTF_STR_OFFSET_VALID(offset))
+ return false;
+
+ while (offset < btf->start_str_off)
+ btf = btf->base_btf;
+
+ offset -= btf->start_str_off;
+ return offset < btf->hdr.str_len;
}
static bool __btf_name_char_ok(char c, bool first, bool dot_ok)
return true;
}
+static const char *btf_str_by_offset(const struct btf *btf, u32 offset)
+{
+ while (offset < btf->start_str_off)
+ btf = btf->base_btf;
+
+ offset -= btf->start_str_off;
+ if (offset < btf->hdr.str_len)
+ return &btf->strings[offset];
+
+ return NULL;
+}
+
static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok)
{
/* offset must be valid */
- const char *src = &btf->strings[offset];
+ const char *src = btf_str_by_offset(btf, offset);
const char *src_limit;
if (!__btf_name_char_ok(*src, true, dot_ok))
static const char *__btf_name_by_offset(const struct btf *btf, u32 offset)
{
+ const char *name;
+
if (!offset)
return "(anon)";
- else if (offset < btf->hdr.str_len)
- return &btf->strings[offset];
- else
- return "(invalid-name-offset)";
+
+ name = btf_str_by_offset(btf, offset);
+ return name ?: "(invalid-name-offset)";
}
const char *btf_name_by_offset(const struct btf *btf, u32 offset)
{
- if (offset < btf->hdr.str_len)
- return &btf->strings[offset];
-
- return NULL;
+ return btf_str_by_offset(btf, offset);
}
const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
{
- if (type_id > btf->nr_types)
- return NULL;
+ while (type_id < btf->start_id)
+ btf = btf->base_btf;
+ type_id -= btf->start_id;
+ if (type_id >= btf->nr_types)
+ return NULL;
return btf->types[type_id];
}
{
struct btf *btf = env->btf;
- /* < 2 because +1 for btf_void which is always in btf->types[0].
- * btf_void is not accounted in btf->nr_types because btf_void
- * does not come from the BTF file.
- */
- if (btf->types_size - btf->nr_types < 2) {
+ if (btf->types_size == btf->nr_types) {
/* Expand 'types' array */
struct btf_type **new_types;
u32 expand_by, new_size;
- if (btf->types_size == BTF_MAX_TYPE) {
+ if (btf->start_id + btf->types_size == BTF_MAX_TYPE) {
btf_verifier_log(env, "Exceeded max num of types");
return -E2BIG;
}
if (!new_types)
return -ENOMEM;
- if (btf->nr_types == 0)
- new_types[0] = &btf_void;
- else
+ if (btf->nr_types == 0) {
+ if (!btf->base_btf) {
+ /* lazily init VOID type */
+ new_types[0] = &btf_void;
+ btf->nr_types++;
+ }
+ } else {
memcpy(new_types, btf->types,
- sizeof(*btf->types) * (btf->nr_types + 1));
+ sizeof(*btf->types) * btf->nr_types);
+ }
kvfree(btf->types);
btf->types = new_types;
btf->types_size = new_size;
}
- btf->types[++(btf->nr_types)] = t;
+ btf->types[btf->nr_types++] = t;
return 0;
}
u32 *resolved_ids = NULL;
u8 *visit_states = NULL;
- /* +1 for btf_void */
- resolved_sizes = kvcalloc(nr_types + 1, sizeof(*resolved_sizes),
+ resolved_sizes = kvcalloc(nr_types, sizeof(*resolved_sizes),
GFP_KERNEL | __GFP_NOWARN);
if (!resolved_sizes)
goto nomem;
- resolved_ids = kvcalloc(nr_types + 1, sizeof(*resolved_ids),
+ resolved_ids = kvcalloc(nr_types, sizeof(*resolved_ids),
GFP_KERNEL | __GFP_NOWARN);
if (!resolved_ids)
goto nomem;
- visit_states = kvcalloc(nr_types + 1, sizeof(*visit_states),
+ visit_states = kvcalloc(nr_types, sizeof(*visit_states),
GFP_KERNEL | __GFP_NOWARN);
if (!visit_states)
goto nomem;
static bool env_type_is_resolved(const struct btf_verifier_env *env,
u32 type_id)
{
- return env->visit_states[type_id] == RESOLVED;
+ /* base BTF types should be resolved by now */
+ if (type_id < env->btf->start_id)
+ return true;
+
+ return env->visit_states[type_id - env->btf->start_id] == RESOLVED;
}
static int env_stack_push(struct btf_verifier_env *env,
const struct btf_type *t, u32 type_id)
{
+ const struct btf *btf = env->btf;
struct resolve_vertex *v;
if (env->top_stack == MAX_RESOLVE_DEPTH)
return -E2BIG;
- if (env->visit_states[type_id] != NOT_VISITED)
+ if (type_id < btf->start_id
+ || env->visit_states[type_id - btf->start_id] != NOT_VISITED)
return -EEXIST;
- env->visit_states[type_id] = VISITED;
+ env->visit_states[type_id - btf->start_id] = VISITED;
v = &env->stack[env->top_stack++];
v->t = t;
u32 type_id = env->stack[--(env->top_stack)].type_id;
struct btf *btf = env->btf;
+ type_id -= btf->start_id; /* adjust to local type id */
btf->resolved_sizes[type_id] = resolved_size;
btf->resolved_ids[type_id] = resolved_type_id;
env->visit_states[type_id] = RESOLVED;
return __btf_resolve_size(btf, type, type_size, NULL, NULL, NULL, NULL);
}
+static u32 btf_resolved_type_id(const struct btf *btf, u32 type_id)
+{
+ while (type_id < btf->start_id)
+ btf = btf->base_btf;
+
+ return btf->resolved_ids[type_id - btf->start_id];
+}
+
/* The input param "type_id" must point to a needs_resolve type */
static const struct btf_type *btf_type_id_resolve(const struct btf *btf,
u32 *type_id)
{
- *type_id = btf->resolved_ids[*type_id];
+ *type_id = btf_resolved_type_id(btf, *type_id);
return btf_type_by_id(btf, *type_id);
}
+static u32 btf_resolved_type_size(const struct btf *btf, u32 type_id)
+{
+ while (type_id < btf->start_id)
+ btf = btf->base_btf;
+
+ return btf->resolved_sizes[type_id - btf->start_id];
+}
+
const struct btf_type *btf_type_id_size(const struct btf *btf,
u32 *type_id, u32 *ret_size)
{
if (btf_type_has_size(size_type)) {
size = size_type->size;
} else if (btf_type_is_array(size_type)) {
- size = btf->resolved_sizes[size_type_id];
+ size = btf_resolved_type_size(btf, size_type_id);
} else if (btf_type_is_ptr(size_type)) {
size = sizeof(void *);
} else {
!btf_type_is_var(size_type)))
return NULL;
- size_type_id = btf->resolved_ids[size_type_id];
+ size_type_id = btf_resolved_type_id(btf, size_type_id);
size_type = btf_type_by_id(btf, size_type_id);
if (btf_type_nosize_or_null(size_type))
return NULL;
else if (btf_type_has_size(size_type))
size = size_type->size;
else if (btf_type_is_array(size_type))
- size = btf->resolved_sizes[size_type_id];
+ size = btf_resolved_type_size(btf, size_type_id);
else if (btf_type_is_ptr(size_type))
size = sizeof(void *);
else
cur = btf->nohdr_data + hdr->type_off;
end = cur + hdr->type_len;
- env->log_type_id = 1;
+ env->log_type_id = btf->base_btf ? btf->start_id : 1;
while (cur < end) {
struct btf_type *t = cur;
s32 meta_size;
return false;
if (btf_type_is_struct(t) || btf_type_is_datasec(t))
- return !btf->resolved_ids[type_id] &&
- !btf->resolved_sizes[type_id];
+ return !btf_resolved_type_id(btf, type_id) &&
+ !btf_resolved_type_size(btf, type_id);
if (btf_type_is_modifier(t) || btf_type_is_ptr(t) ||
btf_type_is_var(t)) {
elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
return elem_type && !btf_type_is_modifier(elem_type) &&
(array->nelems * elem_size ==
- btf->resolved_sizes[type_id]);
+ btf_resolved_type_size(btf, type_id));
}
return false;
static int btf_check_all_types(struct btf_verifier_env *env)
{
struct btf *btf = env->btf;
- u32 type_id;
+ const struct btf_type *t;
+ u32 type_id, i;
int err;
err = env_resolve_init(env);
return err;
env->phase++;
- for (type_id = 1; type_id <= btf->nr_types; type_id++) {
- const struct btf_type *t = btf_type_by_id(btf, type_id);
+ for (i = btf->base_btf ? 0 : 1; i < btf->nr_types; i++) {
+ type_id = btf->start_id + i;
+ t = btf_type_by_id(btf, type_id);
env->log_type_id = type_id;
if (btf_type_needs_resolve(t) &&
return -EINVAL;
}
- if (!hdr->type_len) {
+ if (!env->btf->base_btf && !hdr->type_len) {
btf_verifier_log(env, "No type found");
return -EINVAL;
}
return -EINVAL;
}
- if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET ||
- start[0] || end[-1]) {
+ btf->strings = start;
+
+ if (btf->base_btf && !hdr->str_len)
+ return 0;
+ if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || end[-1]) {
+ btf_verifier_log(env, "Invalid string section");
+ return -EINVAL;
+ }
+ if (!btf->base_btf && start[0]) {
btf_verifier_log(env, "Invalid string section");
return -EINVAL;
}
-
- btf->strings = start;
return 0;
}
btf->data = __start_BTF;
btf->data_size = __stop_BTF - __start_BTF;
+ btf->kernel_btf = true;
+ snprintf(btf->name, sizeof(btf->name), "vmlinux");
err = btf_parse_hdr(env);
if (err)
bpf_struct_ops_init(btf, log);
+ refcount_set(&btf->refcnt, 1);
+
+ err = btf_alloc_id(btf);
+ if (err)
+ goto errout;
+
+ btf_verifier_env_free(env);
+ return btf;
+
+errout:
+ btf_verifier_env_free(env);
+ if (btf) {
+ kvfree(btf->types);
+ kfree(btf);
+ }
+ return ERR_PTR(err);
+}
+
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+
+static struct btf *btf_parse_module(const char *module_name, const void *data, unsigned int data_size)
+{
+ struct btf_verifier_env *env = NULL;
+ struct bpf_verifier_log *log;
+ struct btf *btf = NULL, *base_btf;
+ int err;
+
+ base_btf = bpf_get_btf_vmlinux();
+ if (IS_ERR(base_btf))
+ return base_btf;
+ if (!base_btf)
+ return ERR_PTR(-EINVAL);
+
+ env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
+ if (!env)
+ return ERR_PTR(-ENOMEM);
+
+ log = &env->log;
+ log->level = BPF_LOG_KERNEL;
+
+ btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN);
+ if (!btf) {
+ err = -ENOMEM;
+ goto errout;
+ }
+ env->btf = btf;
+
+ btf->base_btf = base_btf;
+ btf->start_id = base_btf->nr_types;
+ btf->start_str_off = base_btf->hdr.str_len;
+ btf->kernel_btf = true;
+ snprintf(btf->name, sizeof(btf->name), "%s", module_name);
+
+ btf->data = kvmalloc(data_size, GFP_KERNEL | __GFP_NOWARN);
+ if (!btf->data) {
+ err = -ENOMEM;
+ goto errout;
+ }
+ memcpy(btf->data, data, data_size);
+ btf->data_size = data_size;
+
+ err = btf_parse_hdr(env);
+ if (err)
+ goto errout;
+
+ btf->nohdr_data = btf->data + btf->hdr.hdr_len;
+
+ err = btf_parse_str_sec(env);
+ if (err)
+ goto errout;
+
+ err = btf_check_all_metas(env);
+ if (err)
+ goto errout;
+
btf_verifier_env_free(env);
refcount_set(&btf->refcnt, 1);
return btf;
errout:
btf_verifier_env_free(env);
if (btf) {
+ kvfree(btf->data);
kvfree(btf->types);
kfree(btf);
}
return ERR_PTR(err);
}
+#endif /* CONFIG_DEBUG_INFO_BTF_MODULES */
+
struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
{
struct bpf_prog *tgt_prog = prog->aux->dst_prog;
while (t && btf_type_is_modifier(t))
t = btf_type_by_id(btf, t->type);
if (!t) {
- *bad_type = btf->types[0];
+ *bad_type = btf_type_by_id(btf, 0);
return -EINVAL;
}
if (btf_type_is_ptr(t))
struct bpf_btf_info info;
u32 info_copy, btf_copy;
void __user *ubtf;
- u32 uinfo_len;
+ char __user *uname;
+ u32 uinfo_len, uname_len, name_len;
+ int ret = 0;
uinfo = u64_to_user_ptr(attr->info.info);
uinfo_len = attr->info.info_len;
return -EFAULT;
info.btf_size = btf->data_size;
+ info.kernel_btf = btf->kernel_btf;
+
+ uname = u64_to_user_ptr(info.name);
+ uname_len = info.name_len;
+ if (!uname ^ !uname_len)
+ return -EINVAL;
+
+ name_len = strlen(btf->name);
+ info.name_len = name_len;
+
+ if (uname) {
+ if (uname_len >= name_len + 1) {
+ if (copy_to_user(uname, btf->name, name_len + 1))
+ return -EFAULT;
+ } else {
+ char zero = '\0';
+
+ if (copy_to_user(uname, btf->name, uname_len - 1))
+ return -EFAULT;
+ if (put_user(zero, uname + uname_len - 1))
+ return -EFAULT;
+ /* let user-space know about too short buffer */
+ ret = -ENOSPC;
+ }
+ }
+
if (copy_to_user(uinfo, &info, info_copy) ||
put_user(info_copy, &uattr->info.info_len))
return -EFAULT;
- return 0;
+ return ret;
}
int btf_get_fd_by_id(u32 id)
{
return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
}
+
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+struct btf_module {
+ struct list_head list;
+ struct module *module;
+ struct btf *btf;
+ struct bin_attribute *sysfs_attr;
+};
+
+static LIST_HEAD(btf_modules);
+static DEFINE_MUTEX(btf_module_mutex);
+
+static ssize_t
+btf_module_read(struct file *file, struct kobject *kobj,
+ struct bin_attribute *bin_attr,
+ char *buf, loff_t off, size_t len)
+{
+ const struct btf *btf = bin_attr->private;
+
+ memcpy(buf, btf->data + off, len);
+ return len;
+}
+
+static int btf_module_notify(struct notifier_block *nb, unsigned long op,
+ void *module)
+{
+ struct btf_module *btf_mod, *tmp;
+ struct module *mod = module;
+ struct btf *btf;
+ int err = 0;
+
+ if (mod->btf_data_size == 0 ||
+ (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING))
+ goto out;
+
+ switch (op) {
+ case MODULE_STATE_COMING:
+ btf_mod = kzalloc(sizeof(*btf_mod), GFP_KERNEL);
+ if (!btf_mod) {
+ err = -ENOMEM;
+ goto out;
+ }
+ btf = btf_parse_module(mod->name, mod->btf_data, mod->btf_data_size);
+ if (IS_ERR(btf)) {
+ pr_warn("failed to validate module [%s] BTF: %ld\n",
+ mod->name, PTR_ERR(btf));
+ kfree(btf_mod);
+ err = PTR_ERR(btf);
+ goto out;
+ }
+ err = btf_alloc_id(btf);
+ if (err) {
+ btf_free(btf);
+ kfree(btf_mod);
+ goto out;
+ }
+
+ mutex_lock(&btf_module_mutex);
+ btf_mod->module = module;
+ btf_mod->btf = btf;
+ list_add(&btf_mod->list, &btf_modules);
+ mutex_unlock(&btf_module_mutex);
+
+ if (IS_ENABLED(CONFIG_SYSFS)) {
+ struct bin_attribute *attr;
+
+ attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+ if (!attr)
+ goto out;
+
+ sysfs_bin_attr_init(attr);
+ attr->attr.name = btf->name;
+ attr->attr.mode = 0444;
+ attr->size = btf->data_size;
+ attr->private = btf;
+ attr->read = btf_module_read;
+
+ err = sysfs_create_bin_file(btf_kobj, attr);
+ if (err) {
+ pr_warn("failed to register module [%s] BTF in sysfs: %d\n",
+ mod->name, err);
+ kfree(attr);
+ err = 0;
+ goto out;
+ }
+
+ btf_mod->sysfs_attr = attr;
+ }
+
+ break;
+ case MODULE_STATE_GOING:
+ mutex_lock(&btf_module_mutex);
+ list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) {
+ if (btf_mod->module != module)
+ continue;
+
+ list_del(&btf_mod->list);
+ if (btf_mod->sysfs_attr)
+ sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr);
+ btf_put(btf_mod->btf);
+ kfree(btf_mod->sysfs_attr);
+ kfree(btf_mod);
+ break;
+ }
+ mutex_unlock(&btf_module_mutex);
+ break;
+ }
+out:
+ return notifier_from_errno(err);
+}
+
+static struct notifier_block btf_module_nb = {
+ .notifier_call = btf_module_notify,
+};
+
+static int __init btf_module_init(void)
+{
+ register_module_notifier(&btf_module_nb);
+ return 0;
+}
+
+fs_initcall(btf_module_init);
+#endif /* CONFIG_DEBUG_INFO_BTF_MODULES */
};
};
+#define HASHTAB_MAP_LOCK_COUNT 8
+#define HASHTAB_MAP_LOCK_MASK (HASHTAB_MAP_LOCK_COUNT - 1)
+
struct bpf_htab {
struct bpf_map map;
struct bucket *buckets;
u32 n_buckets; /* number of hash buckets */
u32 elem_size; /* size of each element in bytes */
u32 hashrnd;
+ struct lock_class_key lockdep_key;
+ int __percpu *map_locked[HASHTAB_MAP_LOCK_COUNT];
};
/* each htab element is struct htab_elem + key + value */
for (i = 0; i < htab->n_buckets; i++) {
INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
- if (htab_use_raw_lock(htab))
+ if (htab_use_raw_lock(htab)) {
raw_spin_lock_init(&htab->buckets[i].raw_lock);
- else
+ lockdep_set_class(&htab->buckets[i].raw_lock,
+ &htab->lockdep_key);
+ } else {
spin_lock_init(&htab->buckets[i].lock);
+ lockdep_set_class(&htab->buckets[i].lock,
+ &htab->lockdep_key);
+ }
}
}
-static inline unsigned long htab_lock_bucket(const struct bpf_htab *htab,
- struct bucket *b)
+static inline int htab_lock_bucket(const struct bpf_htab *htab,
+ struct bucket *b, u32 hash,
+ unsigned long *pflags)
{
unsigned long flags;
+ hash = hash & HASHTAB_MAP_LOCK_MASK;
+
+ migrate_disable();
+ if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
+ __this_cpu_dec(*(htab->map_locked[hash]));
+ migrate_enable();
+ return -EBUSY;
+ }
+
if (htab_use_raw_lock(htab))
raw_spin_lock_irqsave(&b->raw_lock, flags);
else
spin_lock_irqsave(&b->lock, flags);
- return flags;
+ *pflags = flags;
+
+ return 0;
}
static inline void htab_unlock_bucket(const struct bpf_htab *htab,
- struct bucket *b,
+ struct bucket *b, u32 hash,
unsigned long flags)
{
+ hash = hash & HASHTAB_MAP_LOCK_MASK;
if (htab_use_raw_lock(htab))
raw_spin_unlock_irqrestore(&b->raw_lock, flags);
else
spin_unlock_irqrestore(&b->lock, flags);
+ __this_cpu_dec(*(htab->map_locked[hash]));
+ migrate_enable();
}
static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node);
attr->value_size == 0)
return -EINVAL;
- if (attr->key_size > MAX_BPF_STACK)
- /* eBPF programs initialize keys on stack, so they cannot be
- * larger than max stack size
- */
- return -E2BIG;
-
- if (attr->value_size >= KMALLOC_MAX_SIZE -
- MAX_BPF_STACK - sizeof(struct htab_elem))
- /* if value_size is bigger, the user space won't be able to
- * access the elements via bpf syscall. This check also makes
- * sure that the elem_size doesn't overflow and it's
+ if ((u64)attr->key_size + attr->value_size >= KMALLOC_MAX_SIZE -
+ sizeof(struct htab_elem))
+ /* if key_size + value_size is bigger, the user space won't be
+ * able to access the elements via bpf syscall. This check
+ * also makes sure that the elem_size doesn't overflow and it's
* kmalloc-able later in htab_map_update_elem()
*/
return -E2BIG;
bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
struct bpf_htab *htab;
+ int err, i;
u64 cost;
- int err;
htab = kzalloc(sizeof(*htab), GFP_USER);
if (!htab)
return ERR_PTR(-ENOMEM);
+ lockdep_register_key(&htab->lockdep_key);
+
bpf_map_init_from_attr(&htab->map, attr);
if (percpu_lru) {
if (!htab->buckets)
goto free_charge;
+ for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) {
+ htab->map_locked[i] = __alloc_percpu_gfp(sizeof(int),
+ sizeof(int), GFP_USER);
+ if (!htab->map_locked[i])
+ goto free_map_locked;
+ }
+
if (htab->map.map_flags & BPF_F_ZERO_SEED)
htab->hashrnd = 0;
else
if (prealloc) {
err = prealloc_init(htab);
if (err)
- goto free_buckets;
+ goto free_map_locked;
if (!percpu && !lru) {
/* lru itself can remove the least used element, so
free_prealloc:
prealloc_destroy(htab);
-free_buckets:
+free_map_locked:
+ for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
+ free_percpu(htab->map_locked[i]);
bpf_map_area_free(htab->buckets);
free_charge:
bpf_map_charge_finish(&htab->map.memory);
free_htab:
+ lockdep_unregister_key(&htab->lockdep_key);
kfree(htab);
return ERR_PTR(err);
}
struct hlist_nulls_node *n;
unsigned long flags;
struct bucket *b;
+ int ret;
tgt_l = container_of(node, struct htab_elem, lru_node);
b = __select_bucket(htab, tgt_l->hash);
head = &b->head;
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, tgt_l->hash, &flags);
+ if (ret)
+ return false;
hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
if (l == tgt_l) {
break;
}
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, tgt_l->hash, flags);
return l == tgt_l;
}
*/
}
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, hash, &flags);
+ if (ret)
+ return ret;
l_old = lookup_elem_raw(head, hash, key, key_size);
}
ret = 0;
err:
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, hash, flags);
return ret;
}
return -ENOMEM;
memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size);
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, hash, &flags);
+ if (ret)
+ return ret;
l_old = lookup_elem_raw(head, hash, key, key_size);
ret = 0;
err:
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, hash, flags);
if (ret)
bpf_lru_push_free(&htab->lru, &l_new->lru_node);
b = __select_bucket(htab, hash);
head = &b->head;
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, hash, &flags);
+ if (ret)
+ return ret;
l_old = lookup_elem_raw(head, hash, key, key_size);
}
ret = 0;
err:
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, hash, flags);
return ret;
}
return -ENOMEM;
}
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, hash, &flags);
+ if (ret)
+ return ret;
l_old = lookup_elem_raw(head, hash, key, key_size);
}
ret = 0;
err:
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, hash, flags);
if (l_new)
bpf_lru_push_free(&htab->lru, &l_new->lru_node);
return ret;
struct htab_elem *l;
unsigned long flags;
u32 hash, key_size;
- int ret = -ENOENT;
+ int ret;
WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
b = __select_bucket(htab, hash);
head = &b->head;
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, hash, &flags);
+ if (ret)
+ return ret;
l = lookup_elem_raw(head, hash, key, key_size);
if (l) {
hlist_nulls_del_rcu(&l->hash_node);
free_htab_elem(htab, l);
- ret = 0;
+ } else {
+ ret = -ENOENT;
}
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, hash, flags);
return ret;
}
struct htab_elem *l;
unsigned long flags;
u32 hash, key_size;
- int ret = -ENOENT;
+ int ret;
WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
b = __select_bucket(htab, hash);
head = &b->head;
- flags = htab_lock_bucket(htab, b);
+ ret = htab_lock_bucket(htab, b, hash, &flags);
+ if (ret)
+ return ret;
l = lookup_elem_raw(head, hash, key, key_size);
- if (l) {
+ if (l)
hlist_nulls_del_rcu(&l->hash_node);
- ret = 0;
- }
+ else
+ ret = -ENOENT;
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, hash, flags);
if (l)
bpf_lru_push_free(&htab->lru, &l->lru_node);
return ret;
static void htab_map_free(struct bpf_map *map)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ int i;
/* bpf_free_used_maps() or close(map_fd) will trigger this map_free callback.
* bpf_free_used_maps() is called after bpf prog is no longer executing.
free_percpu(htab->extra_elems);
bpf_map_area_free(htab->buckets);
+ for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
+ free_percpu(htab->map_locked[i]);
+ lockdep_unregister_key(&htab->lockdep_key);
kfree(htab);
}
b = &htab->buckets[batch];
head = &b->head;
/* do not grab the lock unless need it (bucket_cnt > 0). */
- if (locked)
- flags = htab_lock_bucket(htab, b);
+ if (locked) {
+ ret = htab_lock_bucket(htab, b, batch, &flags);
+ if (ret)
+ goto next_batch;
+ }
bucket_cnt = 0;
hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
/* Note that since bucket_cnt > 0 here, it is implicit
* that the locked was grabbed, so release it.
*/
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, batch, flags);
rcu_read_unlock();
bpf_enable_instrumentation();
goto after_loop;
/* Note that since bucket_cnt > 0 here, it is implicit
* that the locked was grabbed, so release it.
*/
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, batch, flags);
rcu_read_unlock();
bpf_enable_instrumentation();
kvfree(keys);
dst_val += value_size;
}
- htab_unlock_bucket(htab, b, flags);
+ htab_unlock_bucket(htab, b, batch, flags);
locked = false;
while (node_to_free) {
map->map_type != BPF_MAP_TYPE_ARRAY &&
map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
map->map_type != BPF_MAP_TYPE_SK_STORAGE &&
- map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
+ map->map_type != BPF_MAP_TYPE_INODE_STORAGE &&
+ map->map_type != BPF_MAP_TYPE_TASK_STORAGE)
return -ENOTSUPP;
if (map->spin_lock_off + sizeof(struct bpf_spin_lock) >
map->value_size) {
.read = btf_vmlinux_read,
};
-static struct kobject *btf_kobj;
+struct kobject *btf_kobj;
static int __init btf_vmlinux_init(void)
{
static struct bpf_iter_reg task_reg_info = {
.target = "task",
+ .feature = BPF_ITER_RESCHED,
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__task, task),
static struct bpf_iter_reg task_file_reg_info = {
.target = "task_file",
+ .feature = BPF_ITER_RESCHED,
.ctx_arg_info_size = 2,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__task_file, task),
regno);
return -EACCES;
}
- err = __check_mem_access(env, regno, off, size, reg->range,
+
+ err = reg->range < 0 ? -EINVAL :
+ __check_mem_access(env, regno, off, size, reg->range,
zero_size_allowed);
if (err) {
verbose(env, "R%d offset is outside of the packet\n", regno);
func_id != BPF_FUNC_inode_storage_delete)
goto error;
break;
+ case BPF_MAP_TYPE_TASK_STORAGE:
+ if (func_id != BPF_FUNC_task_storage_get &&
+ func_id != BPF_FUNC_task_storage_delete)
+ goto error;
+ break;
default:
break;
}
if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
goto error;
break;
+ case BPF_FUNC_task_storage_get:
+ case BPF_FUNC_task_storage_delete:
+ if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE)
+ goto error;
+ break;
default:
break;
}
__clear_all_pkt_pointers(env, vstate->frame[i]);
}
+enum {
+ AT_PKT_END = -1,
+ BEYOND_PKT_END = -2,
+};
+
+static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range_open)
+{
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ struct bpf_reg_state *reg = &state->regs[regn];
+
+ if (reg->type != PTR_TO_PACKET)
+ /* PTR_TO_PACKET_META is not supported yet */
+ return;
+
+ /* The 'reg' is pkt > pkt_end or pkt >= pkt_end.
+ * How far beyond pkt_end it goes is unknown.
+ * if (!range_open) it's the case of pkt >= pkt_end
+ * if (range_open) it's the case of pkt > pkt_end
+ * hence this pointer is at least 1 byte bigger than pkt_end
+ */
+ if (range_open)
+ reg->range = BEYOND_PKT_END;
+ else
+ reg->range = AT_PKT_END;
+}
+
static void release_reg_references(struct bpf_verifier_env *env,
struct bpf_func_state *state,
int ref_obj_id)
PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL;
regs[BPF_REG_0].btf_id = meta.ret_btf_id;
}
- } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) {
+ } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL ||
+ fn->ret_type == RET_PTR_TO_BTF_ID) {
int ret_btf_id;
mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL;
+ regs[BPF_REG_0].type = fn->ret_type == RET_PTR_TO_BTF_ID ?
+ PTR_TO_BTF_ID :
+ PTR_TO_BTF_ID_OR_NULL;
ret_btf_id = *fn->ret_btf_id;
if (ret_btf_id == 0) {
verbose(env, "invalid return type %d of func %s#%d\n",
static void __find_good_pkt_pointers(struct bpf_func_state *state,
struct bpf_reg_state *dst_reg,
- enum bpf_reg_type type, u16 new_range)
+ enum bpf_reg_type type, int new_range)
{
struct bpf_reg_state *reg;
int i;
enum bpf_reg_type type,
bool range_right_open)
{
- u16 new_range;
- int i;
+ int new_range, i;
if (dst_reg->off < 0 ||
(dst_reg->off == 0 && range_right_open))
return is_branch64_taken(reg, val, opcode);
}
+static int flip_opcode(u32 opcode)
+{
+ /* How can we transform "a <op> b" into "b <op> a"? */
+ static const u8 opcode_flip[16] = {
+ /* these stay the same */
+ [BPF_JEQ >> 4] = BPF_JEQ,
+ [BPF_JNE >> 4] = BPF_JNE,
+ [BPF_JSET >> 4] = BPF_JSET,
+ /* these swap "lesser" and "greater" (L and G in the opcodes) */
+ [BPF_JGE >> 4] = BPF_JLE,
+ [BPF_JGT >> 4] = BPF_JLT,
+ [BPF_JLE >> 4] = BPF_JGE,
+ [BPF_JLT >> 4] = BPF_JGT,
+ [BPF_JSGE >> 4] = BPF_JSLE,
+ [BPF_JSGT >> 4] = BPF_JSLT,
+ [BPF_JSLE >> 4] = BPF_JSGE,
+ [BPF_JSLT >> 4] = BPF_JSGT
+ };
+ return opcode_flip[opcode >> 4];
+}
+
+static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg,
+ u8 opcode)
+{
+ struct bpf_reg_state *pkt;
+
+ if (src_reg->type == PTR_TO_PACKET_END) {
+ pkt = dst_reg;
+ } else if (dst_reg->type == PTR_TO_PACKET_END) {
+ pkt = src_reg;
+ opcode = flip_opcode(opcode);
+ } else {
+ return -1;
+ }
+
+ if (pkt->range >= 0)
+ return -1;
+
+ switch (opcode) {
+ case BPF_JLE:
+ /* pkt <= pkt_end */
+ fallthrough;
+ case BPF_JGT:
+ /* pkt > pkt_end */
+ if (pkt->range == BEYOND_PKT_END)
+ /* pkt has at last one extra byte beyond pkt_end */
+ return opcode == BPF_JGT;
+ break;
+ case BPF_JLT:
+ /* pkt < pkt_end */
+ fallthrough;
+ case BPF_JGE:
+ /* pkt >= pkt_end */
+ if (pkt->range == BEYOND_PKT_END || pkt->range == AT_PKT_END)
+ return opcode == BPF_JGE;
+ break;
+ }
+ return -1;
+}
+
/* Adjusts the register min/max values in the case that the dst_reg is the
* variable register that we are working on, and src_reg is a constant or we're
* simply doing a BPF_K check.
u64 val, u32 val32,
u8 opcode, bool is_jmp32)
{
- /* How can we transform "a <op> b" into "b <op> a"? */
- static const u8 opcode_flip[16] = {
- /* these stay the same */
- [BPF_JEQ >> 4] = BPF_JEQ,
- [BPF_JNE >> 4] = BPF_JNE,
- [BPF_JSET >> 4] = BPF_JSET,
- /* these swap "lesser" and "greater" (L and G in the opcodes) */
- [BPF_JGE >> 4] = BPF_JLE,
- [BPF_JGT >> 4] = BPF_JLT,
- [BPF_JLE >> 4] = BPF_JGE,
- [BPF_JLT >> 4] = BPF_JGT,
- [BPF_JSGE >> 4] = BPF_JSLE,
- [BPF_JSGT >> 4] = BPF_JSLT,
- [BPF_JSLE >> 4] = BPF_JSGE,
- [BPF_JSLT >> 4] = BPF_JSGT
- };
- opcode = opcode_flip[opcode >> 4];
+ opcode = flip_opcode(opcode);
/* This uses zero as "not present in table"; luckily the zero opcode,
* BPF_JA, can't get here.
*/
/* pkt_data' > pkt_end, pkt_meta' > pkt_data */
find_good_pkt_pointers(this_branch, dst_reg,
dst_reg->type, false);
+ mark_pkt_end(other_branch, insn->dst_reg, 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) &&
/* pkt_end > pkt_data', pkt_data > pkt_meta' */
find_good_pkt_pointers(other_branch, src_reg,
src_reg->type, true);
+ mark_pkt_end(this_branch, insn->src_reg, false);
} else {
return false;
}
/* pkt_data' < pkt_end, pkt_meta' < pkt_data */
find_good_pkt_pointers(other_branch, dst_reg,
dst_reg->type, true);
+ mark_pkt_end(this_branch, insn->dst_reg, 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) &&
/* pkt_end < pkt_data', pkt_data > pkt_meta' */
find_good_pkt_pointers(this_branch, src_reg,
src_reg->type, false);
+ mark_pkt_end(other_branch, insn->src_reg, true);
} else {
return false;
}
/* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */
find_good_pkt_pointers(this_branch, dst_reg,
dst_reg->type, true);
+ mark_pkt_end(other_branch, insn->dst_reg, 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) &&
/* pkt_end >= pkt_data', pkt_data >= pkt_meta' */
find_good_pkt_pointers(other_branch, src_reg,
src_reg->type, false);
+ mark_pkt_end(this_branch, insn->src_reg, true);
} else {
return false;
}
/* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */
find_good_pkt_pointers(other_branch, dst_reg,
dst_reg->type, false);
+ mark_pkt_end(this_branch, insn->dst_reg, 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) &&
/* pkt_end <= pkt_data', pkt_data <= pkt_meta' */
find_good_pkt_pointers(this_branch, src_reg,
src_reg->type, true);
+ mark_pkt_end(other_branch, insn->src_reg, false);
} else {
return false;
}
src_reg->var_off.value,
opcode,
is_jmp32);
+ } else if (reg_is_pkt_pointer_any(dst_reg) &&
+ reg_is_pkt_pointer_any(src_reg) &&
+ !is_jmp32) {
+ pred = is_pkt_ptr_branch_taken(dst_reg, src_reg, opcode);
}
if (pred >= 0) {
*/
if (!__is_pointer_value(false, dst_reg))
err = mark_chain_precision(env, insn->dst_reg);
- if (BPF_SRC(insn->code) == BPF_X && !err)
+ if (BPF_SRC(insn->code) == BPF_X && !err &&
+ !__is_pointer_value(false, src_reg))
err = mark_chain_precision(env, insn->src_reg);
if (err)
return err;
verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n");
}
- if ((is_tracing_prog_type(prog_type) ||
- prog_type == BPF_PROG_TYPE_SOCKET_FILTER) &&
- map_value_has_spin_lock(map)) {
- verbose(env, "tracing progs cannot use bpf_spin_lock yet\n");
- return -EINVAL;
+ if (map_value_has_spin_lock(map)) {
+ if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) {
+ verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n");
+ return -EINVAL;
+ }
+
+ if (is_tracing_prog_type(prog_type)) {
+ verbose(env, "tracing progs cannot use bpf_spin_lock yet\n");
+ return -EINVAL;
+ }
+
+ if (prog->aux->sleepable) {
+ verbose(env, "sleepable progs cannot use bpf_spin_lock yet\n");
+ return -EINVAL;
+ }
}
if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
return -EINVAL;
}
-/* non exhaustive list of sleepable bpf_lsm_*() functions */
-BTF_SET_START(btf_sleepable_lsm_hooks)
-#ifdef CONFIG_BPF_LSM
-BTF_ID(func, bpf_lsm_bprm_committed_creds)
-#else
-BTF_ID_UNUSED
-#endif
-BTF_SET_END(btf_sleepable_lsm_hooks)
-
-static int check_sleepable_lsm_hook(u32 btf_id)
-{
- return btf_id_set_contains(&btf_sleepable_lsm_hooks, btf_id);
-}
-
/* list of non-sleepable functions that are otherwise on
* ALLOW_ERROR_INJECTION list
*/
/* LSM progs check that they are attached to bpf_lsm_*() funcs.
* Only some of them are sleepable.
*/
- if (check_sleepable_lsm_hook(btf_id))
+ if (bpf_lsm_is_sleepable_hook(btf_id))
ret = 0;
break;
default:
/* See the comment before kcov_remote_start() for usage details. */
u64 kcov_common_handle(void)
{
+ if (!in_task())
+ return 0;
return current->kcov_handle;
}
EXPORT_SYMBOL(kcov_common_handle);
return (void *)info->sechdrs[sec].sh_addr;
}
+/* Find a module section: 0 means not found. Ignores SHF_ALLOC flag. */
+static unsigned int find_any_sec(const struct load_info *info, const char *name)
+{
+ unsigned int i;
+
+ for (i = 1; i < info->hdr->e_shnum; i++) {
+ Elf_Shdr *shdr = &info->sechdrs[i];
+ if (strcmp(info->secstrings + shdr->sh_name, name) == 0)
+ return i;
+ }
+ return 0;
+}
+
+/*
+ * Find a module section, or NULL. Fill in number of "objects" in section.
+ * Ignores SHF_ALLOC flag.
+ */
+static __maybe_unused void *any_section_objs(const struct load_info *info,
+ const char *name,
+ size_t object_size,
+ unsigned int *num)
+{
+ unsigned int sec = find_any_sec(info, name);
+
+ /* Section 0 has sh_addr 0 and sh_size 0. */
+ *num = info->sechdrs[sec].sh_size / object_size;
+ return (void *)info->sechdrs[sec].sh_addr;
+}
+
/* Provided by the linker */
extern const struct kernel_symbol __start___ksymtab[];
extern const struct kernel_symbol __stop___ksymtab[];
sizeof(*mod->bpf_raw_events),
&mod->num_bpf_raw_events);
#endif
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+ mod->btf_data = any_section_objs(info, ".BTF", 1, &mod->btf_data_size);
+#endif
#ifdef CONFIG_JUMP_LABEL
mod->jump_entries = section_objs(info, "__jump_table",
sizeof(*mod->jump_entries),
data = kmalloc(len, GFP_KERNEL);
if (!data)
return -ENOMEM;
- nla_strlcpy(data, na, len);
+ nla_strscpy(data, na, len);
ret = cpulist_parse(data, mask);
kfree(data);
return ret;
#include <linux/syscalls.h>
#include <linux/error-injection.h>
#include <linux/btf_ids.h>
+#include <linux/bpf_lsm.h>
+
+#include <net/bpf_sk_storage.h>
#include <uapi/linux/bpf.h>
#include <uapi/linux/btf.h>
.ret_type = RET_INTEGER,
};
+BPF_CALL_0(bpf_get_current_task_btf)
+{
+ return (unsigned long) current;
+}
+
+BTF_ID_LIST_SINGLE(bpf_get_current_btf_ids, struct, task_struct)
+
+static const struct bpf_func_proto bpf_get_current_task_btf_proto = {
+ .func = bpf_get_current_task_btf,
+ .gpl_only = true,
+ .ret_type = RET_PTR_TO_BTF_ID,
+ .ret_btf_id = &bpf_get_current_btf_ids[0],
+};
+
BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
static bool bpf_d_path_allowed(const struct bpf_prog *prog)
{
- return btf_id_set_contains(&btf_allowlist_d_path, prog->aux->attach_btf_id);
+ if (prog->type == BPF_PROG_TYPE_LSM)
+ return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id);
+
+ return btf_id_set_contains(&btf_allowlist_d_path,
+ prog->aux->attach_btf_id);
}
BTF_ID_LIST_SINGLE(bpf_d_path_btf_ids, struct, path)
return &bpf_get_current_pid_tgid_proto;
case BPF_FUNC_get_current_task:
return &bpf_get_current_task_proto;
+ case BPF_FUNC_get_current_task_btf:
+ return &bpf_get_current_task_btf_proto;
case BPF_FUNC_get_current_uid_gid:
return &bpf_get_current_uid_gid_proto;
case BPF_FUNC_get_current_comm:
return &bpf_skc_to_tcp_request_sock_proto;
case BPF_FUNC_skc_to_udp6_sock:
return &bpf_skc_to_udp6_sock_proto;
+ case BPF_FUNC_sk_storage_get:
+ return &bpf_sk_storage_get_tracing_proto;
+ case BPF_FUNC_sk_storage_delete:
+ return &bpf_sk_storage_delete_tracing_proto;
#endif
case BPF_FUNC_seq_printf:
return prog->expected_attach_type == BPF_TRACE_ITER ?
Turning this on expects presence of pahole tool, which will convert
DWARF type info into equivalent deduplicated BTF type info.
+config PAHOLE_HAS_SPLIT_BTF
+ def_bool $(success, test `$(PAHOLE) --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/'` -ge "119")
+
+config DEBUG_INFO_BTF_MODULES
+ def_bool y
+ depends on DEBUG_INFO_BTF && MODULES && PAHOLE_HAS_SPLIT_BTF
+ help
+ Generate compact split BTF type information for kernel modules.
+
config GDB_SCRIPTS
bool "Provide GDB scripts for kernel debugging"
help
EXPORT_SYMBOL(nla_find);
/**
- * nla_strlcpy - Copy string attribute payload into a sized buffer
- * @dst: where to copy the string to
- * @nla: attribute to copy the string from
- * @dstsize: size of destination buffer
+ * nla_strscpy - Copy string attribute payload into a sized buffer
+ * @dst: Where to copy the string to.
+ * @nla: Attribute to copy the string from.
+ * @dstsize: Size of destination buffer.
*
* Copies at most dstsize - 1 bytes into the destination buffer.
- * The result is always a valid NUL-terminated string. Unlike
- * strlcpy the destination buffer is always padded out.
+ * Unlike strlcpy the destination buffer is always padded out.
*
- * Returns the length of the source buffer.
+ * Return:
+ * * srclen - Returns @nla length (not including the trailing %NUL).
+ * * -E2BIG - If @dstsize is 0 or greater than U16_MAX or @nla length greater
+ * than @dstsize.
*/
-size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize)
+ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize)
{
size_t srclen = nla_len(nla);
char *src = nla_data(nla);
+ ssize_t ret;
+ size_t len;
+
+ if (dstsize == 0 || WARN_ON_ONCE(dstsize > U16_MAX))
+ return -E2BIG;
if (srclen > 0 && src[srclen - 1] == '\0')
srclen--;
- if (dstsize > 0) {
- size_t len = (srclen >= dstsize) ? dstsize - 1 : srclen;
-
- memset(dst, 0, dstsize);
- memcpy(dst, src, len);
+ if (srclen >= dstsize) {
+ len = dstsize - 1;
+ ret = -E2BIG;
+ } else {
+ len = srclen;
+ ret = len;
}
- return srclen;
+ memcpy(dst, src, len);
+ /* Zero pad end of dst. */
+ memset(dst + len, 0, dstsize - len);
+
+ return ret;
}
-EXPORT_SYMBOL(nla_strlcpy);
+EXPORT_SYMBOL(nla_strscpy);
/**
* nla_strdup - Copy string attribute payload into a newly allocated buffer
/**
* p9_client_cb - call back from transport to client
- * c: client state
- * req: request received
+ * @c: client state
+ * @req: request received
+ * @status: request status, one of REQ_STATUS_*
*
*/
void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
* p9_check_zc_errors - check 9p packet for error return and process it
* @c: current client instance
* @req: request to parse and check for error conditions
+ * @uidata: external buffer containing error
* @in_hdrlen: Size of response protocol buffer.
*
* returns error code if one is discovered, otherwise returns 0
#include "trans_common.h"
/**
- * p9_release_pages - Release pages after the transaction.
+ * p9_release_pages - Release pages after the transaction.
+ * @pages: array of pages to be put
+ * @nr_pages: size of array
*/
void p9_release_pages(struct page **pages, int nr_pages)
{
* @rfd: file descriptor for reading (trans=fd)
* @wfd: file descriptor for writing (trans=fd)
* @port: port to connect to (trans=tcp)
- *
+ * @privport: port is privileged
*/
struct p9_fd_opts {
* @err: error state
* @req_list: accounting for requests which have been sent
* @unsent_req_list: accounting for requests that haven't been sent
+ * @rreq: read request
+ * @wreq: write request
* @req: current request being processed (if any)
* @tmp_buf: temporary buffer to read in header
* @rc: temporary fcall for reading current frame
/**
* struct p9_rdma_context - Keeps track of in-process WR
*
+ * @cqe: completion queue entry
* @busa: Bus address to unmap when the WR completes
* @req: Keeps track of requests (send)
* @rc: Keepts track of replies (receive)
/**
* struct p9_rdma_opts - Collection of mount options
* @port: port of connection
+ * @privport: Whether a privileged port may be used
* @sq_depth: The requested depth of the SQ. This really doesn't need
* to be any deeper than the number of threads used in the client
* @rq_depth: The depth of the RQ. Should be greater than or equal to SQ depth
* @client: client instance
* @vdev: virtio dev associated with this channel
* @vq: virtio queue associated with this channel
+ * @ring_bufs_avail: flag to indicate there is some available in the ring buf
+ * @vc_wq: wait queue for waiting for thing to be added to ring buf
+ * @p9_max_pages: maximum number of pinned pages
* @sg: scatter gather list which is used to pack a request (protected?)
+ * @chan_list: linked list of channels
*
* We keep all per-channel information in a structure.
* This structure is allocated within the devices dev->mem space.
unsigned long p9_max_pages;
/* Scatterlist: can be too big for stack. */
struct scatterlist sg[VIRTQUEUE_NUM];
- /*
- * tag name to identify a mount null terminated
+ /**
+ * @tag: name to identify a mount null terminated
*/
char *tag;
* this takes a list of pages.
* @sg: scatter/gather list to pack into
* @start: which segment of the sg_list to start at
+ * @limit: maximum number of pages in sg list.
* @pdata: a list of pages to add into sg.
* @nr_pages: number of pages to pack into the scatter/gather list
* @offs: amount of data in the beginning of first page _not_ to pack
endif # WIRELESS
-source "net/wimax/Kconfig"
-
source "net/rfkill/Kconfig"
source "net/9p/Kconfig"
source "net/caif/Kconfig"
ifeq ($(CONFIG_NET),y)
obj-$(CONFIG_SYSCTL) += sysctl_net.o
endif
-obj-$(CONFIG_WIMAX) += wimax/
obj-$(CONFIG_DNS_RESOLVER) += dns_resolver/
obj-$(CONFIG_CEPH_LIB) += ceph/
obj-$(CONFIG_BATMAN_ADV) += batman-adv/
/* Lists of aarp entries */
/**
* struct aarp_entry - AARP entry
- * @last_sent - Last time we xmitted the aarp request
- * @packet_queue - Queue of frames wait for resolution
- * @status - Used for proxy AARP
- * expires_at - Entry expiry time
- * target_addr - DDP Address
- * dev - Device to use
- * hwaddr - Physical i/f address of target/router
- * xmit_count - When this hits 10 we give up
- * next - Next entry in chain
+ * @last_sent: Last time we xmitted the aarp request
+ * @packet_queue: Queue of frames wait for resolution
+ * @status: Used for proxy AARP
+ * @expires_at: Entry expiry time
+ * @target_addr: DDP Address
+ * @dev: Device to use
+ * @hwaddr: Physical i/f address of target/router
+ * @xmit_count: When this hits 10 we give up
+ * @next: Next entry in chain
*/
struct aarp_entry {
/* These first two are only used for unresolved entries */
/**
* atalk_rcv - Receive a packet (in skb) from device dev
- * @skb - packet received
- * @dev - network device where the packet comes from
- * @pt - packet type
+ * @skb: packet received
+ * @dev: network device where the packet comes from
+ * @pt: packet type
+ * @orig_dev: the original receive net device
*
* Receive a packet (in skb) from device dev. This has come from the SNAP
* decoder, and on entry skb->transport_header is the DDP header, skb->len
kfree_skb(skb);
return -EADDRNOTAVAIL;
}
+ if (vcc->dev->ops->send_bh)
+ return vcc->dev->ops->send_bh(vcc, skb);
return vcc->dev->ops->send(vcc, skb);
}
vcc->push = atm_push_raw;
vcc->pop = atm_pop_raw;
vcc->push_oam = NULL;
- vcc->send = vcc->dev->ops->send;
+ if (vcc->dev->ops->send_bh)
+ vcc->send = vcc->dev->ops->send_bh;
+ else
+ vcc->send = vcc->dev->ops->send;
return 0;
}
vcc->push = atm_push_raw;
vcc->pop = atm_pop_raw;
vcc->push_oam = NULL;
- vcc->send = vcc->dev->ops->send;
+ if (vcc->dev->ops->send_bh)
+ vcc->send = vcc->dev->ops->send_bh;
+ else
+ vcc->send = vcc->dev->ops->send;
return 0;
}
EXPORT_SYMBOL(atm_init_aal5);
Say N to exclude this support and reduce the binary size.
If unsure, say N.
+
+config BRIDGE_CFM
+ bool "CFM protocol"
+ depends on BRIDGE
+ help
+ If you say Y here, then the Ethernet bridge will be able to run CFM
+ protocol according to 802.1Q section 12.14
+
+ Say N to exclude this support and reduce the binary size.
+
+ If unsure, say N.
obj-$(CONFIG_NETFILTER) += netfilter/
bridge-$(CONFIG_BRIDGE_MRP) += br_mrp_switchdev.o br_mrp.o br_mrp_netlink.o
+
+bridge-$(CONFIG_BRIDGE_CFM) += br_cfm.o br_cfm_netlink.o
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/cfm_bridge.h>
+#include <uapi/linux/cfm_bridge.h>
+#include "br_private_cfm.h"
+
+static struct br_cfm_mep *br_mep_find(struct net_bridge *br, u32 instance)
+{
+ struct br_cfm_mep *mep;
+
+ hlist_for_each_entry(mep, &br->mep_list, head)
+ if (mep->instance == instance)
+ return mep;
+
+ return NULL;
+}
+
+static struct br_cfm_mep *br_mep_find_ifindex(struct net_bridge *br,
+ u32 ifindex)
+{
+ struct br_cfm_mep *mep;
+
+ hlist_for_each_entry_rcu(mep, &br->mep_list, head,
+ lockdep_rtnl_is_held())
+ if (mep->create.ifindex == ifindex)
+ return mep;
+
+ return NULL;
+}
+
+static struct br_cfm_peer_mep *br_peer_mep_find(struct br_cfm_mep *mep,
+ u32 mepid)
+{
+ struct br_cfm_peer_mep *peer_mep;
+
+ hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head,
+ lockdep_rtnl_is_held())
+ if (peer_mep->mepid == mepid)
+ return peer_mep;
+
+ return NULL;
+}
+
+static struct net_bridge_port *br_mep_get_port(struct net_bridge *br,
+ u32 ifindex)
+{
+ struct net_bridge_port *port;
+
+ list_for_each_entry(port, &br->port_list, list)
+ if (port->dev->ifindex == ifindex)
+ return port;
+
+ return NULL;
+}
+
+/* Calculate the CCM interval in us. */
+static u32 interval_to_us(enum br_cfm_ccm_interval interval)
+{
+ switch (interval) {
+ case BR_CFM_CCM_INTERVAL_NONE:
+ return 0;
+ case BR_CFM_CCM_INTERVAL_3_3_MS:
+ return 3300;
+ case BR_CFM_CCM_INTERVAL_10_MS:
+ return 10 * 1000;
+ case BR_CFM_CCM_INTERVAL_100_MS:
+ return 100 * 1000;
+ case BR_CFM_CCM_INTERVAL_1_SEC:
+ return 1000 * 1000;
+ case BR_CFM_CCM_INTERVAL_10_SEC:
+ return 10 * 1000 * 1000;
+ case BR_CFM_CCM_INTERVAL_1_MIN:
+ return 60 * 1000 * 1000;
+ case BR_CFM_CCM_INTERVAL_10_MIN:
+ return 10 * 60 * 1000 * 1000;
+ }
+ return 0;
+}
+
+/* Convert the interface interval to CCM PDU value. */
+static u32 interval_to_pdu(enum br_cfm_ccm_interval interval)
+{
+ switch (interval) {
+ case BR_CFM_CCM_INTERVAL_NONE:
+ return 0;
+ case BR_CFM_CCM_INTERVAL_3_3_MS:
+ return 1;
+ case BR_CFM_CCM_INTERVAL_10_MS:
+ return 2;
+ case BR_CFM_CCM_INTERVAL_100_MS:
+ return 3;
+ case BR_CFM_CCM_INTERVAL_1_SEC:
+ return 4;
+ case BR_CFM_CCM_INTERVAL_10_SEC:
+ return 5;
+ case BR_CFM_CCM_INTERVAL_1_MIN:
+ return 6;
+ case BR_CFM_CCM_INTERVAL_10_MIN:
+ return 7;
+ }
+ return 0;
+}
+
+/* Convert the CCM PDU value to interval on interface. */
+static u32 pdu_to_interval(u32 value)
+{
+ switch (value) {
+ case 0:
+ return BR_CFM_CCM_INTERVAL_NONE;
+ case 1:
+ return BR_CFM_CCM_INTERVAL_3_3_MS;
+ case 2:
+ return BR_CFM_CCM_INTERVAL_10_MS;
+ case 3:
+ return BR_CFM_CCM_INTERVAL_100_MS;
+ case 4:
+ return BR_CFM_CCM_INTERVAL_1_SEC;
+ case 5:
+ return BR_CFM_CCM_INTERVAL_10_SEC;
+ case 6:
+ return BR_CFM_CCM_INTERVAL_1_MIN;
+ case 7:
+ return BR_CFM_CCM_INTERVAL_10_MIN;
+ }
+ return BR_CFM_CCM_INTERVAL_NONE;
+}
+
+static void ccm_rx_timer_start(struct br_cfm_peer_mep *peer_mep)
+{
+ u32 interval_us;
+
+ interval_us = interval_to_us(peer_mep->mep->cc_config.exp_interval);
+ /* Function ccm_rx_dwork must be called with 1/4
+ * of the configured CC 'expected_interval'
+ * in order to detect CCM defect after 3.25 interval.
+ */
+ queue_delayed_work(system_wq, &peer_mep->ccm_rx_dwork,
+ usecs_to_jiffies(interval_us / 4));
+}
+
+static void br_cfm_notify(int event, const struct net_bridge_port *port)
+{
+ u32 filter = RTEXT_FILTER_CFM_STATUS;
+
+ return br_info_notify(event, port->br, NULL, filter);
+}
+
+static void cc_peer_enable(struct br_cfm_peer_mep *peer_mep)
+{
+ memset(&peer_mep->cc_status, 0, sizeof(peer_mep->cc_status));
+ peer_mep->ccm_rx_count_miss = 0;
+
+ ccm_rx_timer_start(peer_mep);
+}
+
+static void cc_peer_disable(struct br_cfm_peer_mep *peer_mep)
+{
+ cancel_delayed_work_sync(&peer_mep->ccm_rx_dwork);
+}
+
+static struct sk_buff *ccm_frame_build(struct br_cfm_mep *mep,
+ const struct br_cfm_cc_ccm_tx_info *const tx_info)
+
+{
+ struct br_cfm_common_hdr *common_hdr;
+ struct net_bridge_port *b_port;
+ struct br_cfm_maid *maid;
+ u8 *itu_reserved, *e_tlv;
+ struct ethhdr *eth_hdr;
+ struct sk_buff *skb;
+ __be32 *status_tlv;
+ __be32 *snumber;
+ __be16 *mepid;
+
+ skb = dev_alloc_skb(CFM_CCM_MAX_FRAME_LENGTH);
+ if (!skb)
+ return NULL;
+
+ rcu_read_lock();
+ b_port = rcu_dereference(mep->b_port);
+ if (!b_port) {
+ kfree_skb(skb);
+ rcu_read_unlock();
+ return NULL;
+ }
+ skb->dev = b_port->dev;
+ rcu_read_unlock();
+ /* The device cannot be deleted until the work_queue functions has
+ * completed. This function is called from ccm_tx_work_expired()
+ * that is a work_queue functions.
+ */
+
+ skb->protocol = htons(ETH_P_CFM);
+ skb->priority = CFM_FRAME_PRIO;
+
+ /* Ethernet header */
+ eth_hdr = skb_put(skb, sizeof(*eth_hdr));
+ ether_addr_copy(eth_hdr->h_dest, tx_info->dmac.addr);
+ ether_addr_copy(eth_hdr->h_source, mep->config.unicast_mac.addr);
+ eth_hdr->h_proto = htons(ETH_P_CFM);
+
+ /* Common CFM Header */
+ common_hdr = skb_put(skb, sizeof(*common_hdr));
+ common_hdr->mdlevel_version = mep->config.mdlevel << 5;
+ common_hdr->opcode = BR_CFM_OPCODE_CCM;
+ common_hdr->flags = (mep->rdi << 7) |
+ interval_to_pdu(mep->cc_config.exp_interval);
+ common_hdr->tlv_offset = CFM_CCM_TLV_OFFSET;
+
+ /* Sequence number */
+ snumber = skb_put(skb, sizeof(*snumber));
+ if (tx_info->seq_no_update) {
+ *snumber = cpu_to_be32(mep->ccm_tx_snumber);
+ mep->ccm_tx_snumber += 1;
+ } else {
+ *snumber = 0;
+ }
+
+ mepid = skb_put(skb, sizeof(*mepid));
+ *mepid = cpu_to_be16((u16)mep->config.mepid);
+
+ maid = skb_put(skb, sizeof(*maid));
+ memcpy(maid->data, mep->cc_config.exp_maid.data, sizeof(maid->data));
+
+ /* ITU reserved (CFM_CCM_ITU_RESERVED_SIZE octets) */
+ itu_reserved = skb_put(skb, CFM_CCM_ITU_RESERVED_SIZE);
+ memset(itu_reserved, 0, CFM_CCM_ITU_RESERVED_SIZE);
+
+ /* Generel CFM TLV format:
+ * TLV type: one byte
+ * TLV value length: two bytes
+ * TLV value: 'TLV value length' bytes
+ */
+
+ /* Port status TLV. The value length is 1. Total of 4 bytes. */
+ if (tx_info->port_tlv) {
+ status_tlv = skb_put(skb, sizeof(*status_tlv));
+ *status_tlv = cpu_to_be32((CFM_PORT_STATUS_TLV_TYPE << 24) |
+ (1 << 8) | /* Value length */
+ (tx_info->port_tlv_value & 0xFF));
+ }
+
+ /* Interface status TLV. The value length is 1. Total of 4 bytes. */
+ if (tx_info->if_tlv) {
+ status_tlv = skb_put(skb, sizeof(*status_tlv));
+ *status_tlv = cpu_to_be32((CFM_IF_STATUS_TLV_TYPE << 24) |
+ (1 << 8) | /* Value length */
+ (tx_info->if_tlv_value & 0xFF));
+ }
+
+ /* End TLV */
+ e_tlv = skb_put(skb, sizeof(*e_tlv));
+ *e_tlv = CFM_ENDE_TLV_TYPE;
+
+ return skb;
+}
+
+static void ccm_frame_tx(struct sk_buff *skb)
+{
+ skb_reset_network_header(skb);
+ dev_queue_xmit(skb);
+}
+
+/* This function is called with the configured CC 'expected_interval'
+ * in order to drive CCM transmission when enabled.
+ */
+static void ccm_tx_work_expired(struct work_struct *work)
+{
+ struct delayed_work *del_work;
+ struct br_cfm_mep *mep;
+ struct sk_buff *skb;
+ u32 interval_us;
+
+ del_work = to_delayed_work(work);
+ mep = container_of(del_work, struct br_cfm_mep, ccm_tx_dwork);
+
+ if (time_before_eq(mep->ccm_tx_end, jiffies)) {
+ /* Transmission period has ended */
+ mep->cc_ccm_tx_info.period = 0;
+ return;
+ }
+
+ skb = ccm_frame_build(mep, &mep->cc_ccm_tx_info);
+ if (skb)
+ ccm_frame_tx(skb);
+
+ interval_us = interval_to_us(mep->cc_config.exp_interval);
+ queue_delayed_work(system_wq, &mep->ccm_tx_dwork,
+ usecs_to_jiffies(interval_us));
+}
+
+/* This function is called with 1/4 of the configured CC 'expected_interval'
+ * in order to detect CCM defect after 3.25 interval.
+ */
+static void ccm_rx_work_expired(struct work_struct *work)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct net_bridge_port *b_port;
+ struct delayed_work *del_work;
+
+ del_work = to_delayed_work(work);
+ peer_mep = container_of(del_work, struct br_cfm_peer_mep, ccm_rx_dwork);
+
+ /* After 13 counts (4 * 3,25) then 3.25 intervals are expired */
+ if (peer_mep->ccm_rx_count_miss < 13) {
+ /* 3.25 intervals are NOT expired without CCM reception */
+ peer_mep->ccm_rx_count_miss++;
+
+ /* Start timer again */
+ ccm_rx_timer_start(peer_mep);
+ } else {
+ /* 3.25 intervals are expired without CCM reception.
+ * CCM defect detected
+ */
+ peer_mep->cc_status.ccm_defect = true;
+
+ /* Change in CCM defect status - notify */
+ rcu_read_lock();
+ b_port = rcu_dereference(peer_mep->mep->b_port);
+ if (b_port)
+ br_cfm_notify(RTM_NEWLINK, b_port);
+ rcu_read_unlock();
+ }
+}
+
+static u32 ccm_tlv_extract(struct sk_buff *skb, u32 index,
+ struct br_cfm_peer_mep *peer_mep)
+{
+ __be32 *s_tlv;
+ __be32 _s_tlv;
+ u32 h_s_tlv;
+ u8 *e_tlv;
+ u8 _e_tlv;
+
+ e_tlv = skb_header_pointer(skb, index, sizeof(_e_tlv), &_e_tlv);
+ if (!e_tlv)
+ return 0;
+
+ /* TLV is present - get the status TLV */
+ s_tlv = skb_header_pointer(skb,
+ index,
+ sizeof(_s_tlv), &_s_tlv);
+ if (!s_tlv)
+ return 0;
+
+ h_s_tlv = ntohl(*s_tlv);
+ if ((h_s_tlv >> 24) == CFM_IF_STATUS_TLV_TYPE) {
+ /* Interface status TLV */
+ peer_mep->cc_status.tlv_seen = true;
+ peer_mep->cc_status.if_tlv_value = (h_s_tlv & 0xFF);
+ }
+
+ if ((h_s_tlv >> 24) == CFM_PORT_STATUS_TLV_TYPE) {
+ /* Port status TLV */
+ peer_mep->cc_status.tlv_seen = true;
+ peer_mep->cc_status.port_tlv_value = (h_s_tlv & 0xFF);
+ }
+
+ /* The Sender ID TLV is not handled */
+ /* The Organization-Specific TLV is not handled */
+
+ /* Return the length of this tlv.
+ * This is the length of the value field plus 3 bytes for size of type
+ * field and length field
+ */
+ return ((h_s_tlv >> 8) & 0xFFFF) + 3;
+}
+
+/* note: already called with rcu_read_lock */
+static int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb)
+{
+ u32 mdlevel, interval, size, index, max;
+ const struct br_cfm_common_hdr *hdr;
+ struct br_cfm_peer_mep *peer_mep;
+ const struct br_cfm_maid *maid;
+ struct br_cfm_common_hdr _hdr;
+ struct br_cfm_maid _maid;
+ struct br_cfm_mep *mep;
+ struct net_bridge *br;
+ __be32 *snumber;
+ __be32 _snumber;
+ __be16 *mepid;
+ __be16 _mepid;
+
+ if (port->state == BR_STATE_DISABLED)
+ return 0;
+
+ hdr = skb_header_pointer(skb, 0, sizeof(_hdr), &_hdr);
+ if (!hdr)
+ return 1;
+
+ br = port->br;
+ mep = br_mep_find_ifindex(br, port->dev->ifindex);
+ if (unlikely(!mep))
+ /* No MEP on this port - must be forwarded */
+ return 0;
+
+ mdlevel = hdr->mdlevel_version >> 5;
+ if (mdlevel > mep->config.mdlevel)
+ /* The level is above this MEP level - must be forwarded */
+ return 0;
+
+ if ((hdr->mdlevel_version & 0x1F) != 0) {
+ /* Invalid version */
+ mep->status.version_unexp_seen = true;
+ return 1;
+ }
+
+ if (mdlevel < mep->config.mdlevel) {
+ /* The level is below this MEP level */
+ mep->status.rx_level_low_seen = true;
+ return 1;
+ }
+
+ if (hdr->opcode == BR_CFM_OPCODE_CCM) {
+ /* CCM PDU received. */
+ /* MA ID is after common header + sequence number + MEP ID */
+ maid = skb_header_pointer(skb,
+ CFM_CCM_PDU_MAID_OFFSET,
+ sizeof(_maid), &_maid);
+ if (!maid)
+ return 1;
+ if (memcmp(maid->data, mep->cc_config.exp_maid.data,
+ sizeof(maid->data)))
+ /* MA ID not as expected */
+ return 1;
+
+ /* MEP ID is after common header + sequence number */
+ mepid = skb_header_pointer(skb,
+ CFM_CCM_PDU_MEPID_OFFSET,
+ sizeof(_mepid), &_mepid);
+ if (!mepid)
+ return 1;
+ peer_mep = br_peer_mep_find(mep, (u32)ntohs(*mepid));
+ if (!peer_mep)
+ return 1;
+
+ /* Interval is in common header flags */
+ interval = hdr->flags & 0x07;
+ if (mep->cc_config.exp_interval != pdu_to_interval(interval))
+ /* Interval not as expected */
+ return 1;
+
+ /* A valid CCM frame is received */
+ if (peer_mep->cc_status.ccm_defect) {
+ peer_mep->cc_status.ccm_defect = false;
+
+ /* Change in CCM defect status - notify */
+ br_cfm_notify(RTM_NEWLINK, port);
+
+ /* Start CCM RX timer */
+ ccm_rx_timer_start(peer_mep);
+ }
+
+ peer_mep->cc_status.seen = true;
+ peer_mep->ccm_rx_count_miss = 0;
+
+ /* RDI is in common header flags */
+ peer_mep->cc_status.rdi = (hdr->flags & 0x80) ? true : false;
+
+ /* Sequence number is after common header */
+ snumber = skb_header_pointer(skb,
+ CFM_CCM_PDU_SEQNR_OFFSET,
+ sizeof(_snumber), &_snumber);
+ if (!snumber)
+ return 1;
+ if (ntohl(*snumber) != (mep->ccm_rx_snumber + 1))
+ /* Unexpected sequence number */
+ peer_mep->cc_status.seq_unexp_seen = true;
+
+ mep->ccm_rx_snumber = ntohl(*snumber);
+
+ /* TLV end is after common header + sequence number + MEP ID +
+ * MA ID + ITU reserved
+ */
+ index = CFM_CCM_PDU_TLV_OFFSET;
+ max = 0;
+ do { /* Handle all TLVs */
+ size = ccm_tlv_extract(skb, index, peer_mep);
+ index += size;
+ max += 1;
+ } while (size != 0 && max < 4); /* Max four TLVs possible */
+
+ return 1;
+ }
+
+ mep->status.opcode_unexp_seen = true;
+
+ return 1;
+}
+
+static struct br_frame_type cfm_frame_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_CFM),
+ .frame_handler = br_cfm_frame_rx,
+};
+
+int br_cfm_mep_create(struct net_bridge *br,
+ const u32 instance,
+ struct br_cfm_mep_create *const create,
+ struct netlink_ext_ack *extack)
+{
+ struct net_bridge_port *p;
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ if (create->domain == BR_CFM_VLAN) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "VLAN domain not supported");
+ return -EINVAL;
+ }
+ if (create->domain != BR_CFM_PORT) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Invalid domain value");
+ return -EINVAL;
+ }
+ if (create->direction == BR_CFM_MEP_DIRECTION_UP) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Up-MEP not supported");
+ return -EINVAL;
+ }
+ if (create->direction != BR_CFM_MEP_DIRECTION_DOWN) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Invalid direction value");
+ return -EINVAL;
+ }
+ p = br_mep_get_port(br, create->ifindex);
+ if (!p) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Port is not related to bridge");
+ return -EINVAL;
+ }
+ mep = br_mep_find(br, instance);
+ if (mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance already exists");
+ return -EEXIST;
+ }
+
+ /* In PORT domain only one instance can be created per port */
+ if (create->domain == BR_CFM_PORT) {
+ mep = br_mep_find_ifindex(br, create->ifindex);
+ if (mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Only one Port MEP on a port allowed");
+ return -EINVAL;
+ }
+ }
+
+ mep = kzalloc(sizeof(*mep), GFP_KERNEL);
+ if (!mep)
+ return -ENOMEM;
+
+ mep->create = *create;
+ mep->instance = instance;
+ rcu_assign_pointer(mep->b_port, p);
+
+ INIT_HLIST_HEAD(&mep->peer_mep_list);
+ INIT_DELAYED_WORK(&mep->ccm_tx_dwork, ccm_tx_work_expired);
+
+ if (hlist_empty(&br->mep_list))
+ br_add_frame(br, &cfm_frame_type);
+
+ hlist_add_tail_rcu(&mep->head, &br->mep_list);
+
+ return 0;
+}
+
+static void mep_delete_implementation(struct net_bridge *br,
+ struct br_cfm_mep *mep)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct hlist_node *n_store;
+
+ ASSERT_RTNL();
+
+ /* Empty and free peer MEP list */
+ hlist_for_each_entry_safe(peer_mep, n_store, &mep->peer_mep_list, head) {
+ cancel_delayed_work_sync(&peer_mep->ccm_rx_dwork);
+ hlist_del_rcu(&peer_mep->head);
+ kfree_rcu(peer_mep, rcu);
+ }
+
+ cancel_delayed_work_sync(&mep->ccm_tx_dwork);
+
+ RCU_INIT_POINTER(mep->b_port, NULL);
+ hlist_del_rcu(&mep->head);
+ kfree_rcu(mep, rcu);
+
+ if (hlist_empty(&br->mep_list))
+ br_del_frame(br, &cfm_frame_type);
+}
+
+int br_cfm_mep_delete(struct net_bridge *br,
+ const u32 instance,
+ struct netlink_ext_ack *extack)
+{
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ mep_delete_implementation(br, mep);
+
+ return 0;
+}
+
+int br_cfm_mep_config_set(struct net_bridge *br,
+ const u32 instance,
+ const struct br_cfm_mep_config *const config,
+ struct netlink_ext_ack *extack)
+{
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ mep->config = *config;
+
+ return 0;
+}
+
+int br_cfm_cc_config_set(struct net_bridge *br,
+ const u32 instance,
+ const struct br_cfm_cc_config *const config,
+ struct netlink_ext_ack *extack)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ /* Check for no change in configuration */
+ if (memcmp(config, &mep->cc_config, sizeof(*config)) == 0)
+ return 0;
+
+ if (config->enable && !mep->cc_config.enable)
+ /* CC is enabled */
+ hlist_for_each_entry(peer_mep, &mep->peer_mep_list, head)
+ cc_peer_enable(peer_mep);
+
+ if (!config->enable && mep->cc_config.enable)
+ /* CC is disabled */
+ hlist_for_each_entry(peer_mep, &mep->peer_mep_list, head)
+ cc_peer_disable(peer_mep);
+
+ mep->cc_config = *config;
+ mep->ccm_rx_snumber = 0;
+ mep->ccm_tx_snumber = 1;
+
+ return 0;
+}
+
+int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance,
+ u32 mepid,
+ struct netlink_ext_ack *extack)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ peer_mep = br_peer_mep_find(mep, mepid);
+ if (peer_mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Peer MEP-ID already exists");
+ return -EEXIST;
+ }
+
+ peer_mep = kzalloc(sizeof(*peer_mep), GFP_KERNEL);
+ if (!peer_mep)
+ return -ENOMEM;
+
+ peer_mep->mepid = mepid;
+ peer_mep->mep = mep;
+ INIT_DELAYED_WORK(&peer_mep->ccm_rx_dwork, ccm_rx_work_expired);
+
+ if (mep->cc_config.enable)
+ cc_peer_enable(peer_mep);
+
+ hlist_add_tail_rcu(&peer_mep->head, &mep->peer_mep_list);
+
+ return 0;
+}
+
+int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance,
+ u32 mepid,
+ struct netlink_ext_ack *extack)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ peer_mep = br_peer_mep_find(mep, mepid);
+ if (!peer_mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Peer MEP-ID does not exists");
+ return -ENOENT;
+ }
+
+ cc_peer_disable(peer_mep);
+
+ hlist_del_rcu(&peer_mep->head);
+ kfree_rcu(peer_mep, rcu);
+
+ return 0;
+}
+
+int br_cfm_cc_rdi_set(struct net_bridge *br, const u32 instance,
+ const bool rdi, struct netlink_ext_ack *extack)
+{
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ mep->rdi = rdi;
+
+ return 0;
+}
+
+int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance,
+ const struct br_cfm_cc_ccm_tx_info *const tx_info,
+ struct netlink_ext_ack *extack)
+{
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ if (memcmp(tx_info, &mep->cc_ccm_tx_info, sizeof(*tx_info)) == 0) {
+ /* No change in tx_info. */
+ if (mep->cc_ccm_tx_info.period == 0)
+ /* Transmission is not enabled - just return */
+ return 0;
+
+ /* Transmission is ongoing, the end time is recalculated */
+ mep->ccm_tx_end = jiffies +
+ usecs_to_jiffies(tx_info->period * 1000000);
+ return 0;
+ }
+
+ if (tx_info->period == 0 && mep->cc_ccm_tx_info.period == 0)
+ /* Some change in info and transmission is not ongoing */
+ goto save;
+
+ if (tx_info->period != 0 && mep->cc_ccm_tx_info.period != 0) {
+ /* Some change in info and transmission is ongoing
+ * The end time is recalculated
+ */
+ mep->ccm_tx_end = jiffies +
+ usecs_to_jiffies(tx_info->period * 1000000);
+
+ goto save;
+ }
+
+ if (tx_info->period == 0 && mep->cc_ccm_tx_info.period != 0) {
+ cancel_delayed_work_sync(&mep->ccm_tx_dwork);
+ goto save;
+ }
+
+ /* Start delayed work to transmit CCM frames. It is done with zero delay
+ * to send first frame immediately
+ */
+ mep->ccm_tx_end = jiffies + usecs_to_jiffies(tx_info->period * 1000000);
+ queue_delayed_work(system_wq, &mep->ccm_tx_dwork, 0);
+
+save:
+ mep->cc_ccm_tx_info = *tx_info;
+
+ return 0;
+}
+
+int br_cfm_mep_count(struct net_bridge *br, u32 *count)
+{
+ struct br_cfm_mep *mep;
+
+ *count = 0;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(mep, &br->mep_list, head)
+ *count += 1;
+ rcu_read_unlock();
+
+ return 0;
+}
+
+int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct br_cfm_mep *mep;
+
+ *count = 0;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(mep, &br->mep_list, head)
+ hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head)
+ *count += 1;
+ rcu_read_unlock();
+
+ return 0;
+}
+
+bool br_cfm_created(struct net_bridge *br)
+{
+ return !hlist_empty(&br->mep_list);
+}
+
+/* Deletes the CFM instances on a specific bridge port
+ */
+void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *port)
+{
+ struct hlist_node *n_store;
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ hlist_for_each_entry_safe(mep, n_store, &br->mep_list, head)
+ if (mep->create.ifindex == port->dev->ifindex)
+ mep_delete_implementation(br, mep);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <net/genetlink.h>
+
+#include "br_private.h"
+#include "br_private_cfm.h"
+
+static const struct nla_policy
+br_cfm_mep_create_policy[IFLA_BRIDGE_CFM_MEP_CREATE_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_MEP_CREATE_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX] = { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+br_cfm_mep_delete_policy[IFLA_BRIDGE_CFM_MEP_DELETE_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_MEP_DELETE_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE] = { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+br_cfm_mep_config_policy[IFLA_BRIDGE_CFM_MEP_CONFIG_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_MEP_CONFIG_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC] = NLA_POLICY_ETH_ADDR,
+ [IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL] = NLA_POLICY_MAX(NLA_U32, 7),
+ [IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID] = NLA_POLICY_MAX(NLA_U32, 0x1FFF),
+};
+
+static const struct nla_policy
+br_cfm_cc_config_policy[IFLA_BRIDGE_CFM_CC_CONFIG_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_CC_CONFIG_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID] = {
+ .type = NLA_BINARY, .len = CFM_MAID_LENGTH },
+};
+
+static const struct nla_policy
+br_cfm_cc_peer_mep_policy[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_CC_PEER_MEP_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_PEER_MEPID] = NLA_POLICY_MAX(NLA_U32, 0x1FFF),
+};
+
+static const struct nla_policy
+br_cfm_cc_rdi_policy[IFLA_BRIDGE_CFM_CC_RDI_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_CC_RDI_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_CC_RDI_INSTANCE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_RDI_RDI] = { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+br_cfm_cc_ccm_tx_policy[IFLA_BRIDGE_CFM_CC_CCM_TX_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC] = NLA_POLICY_ETH_ADDR,
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE] = { .type = NLA_U8 },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE] = { .type = NLA_U8 },
+};
+
+static const struct nla_policy
+br_cfm_policy[IFLA_BRIDGE_CFM_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_MEP_CREATE] =
+ NLA_POLICY_NESTED(br_cfm_mep_create_policy),
+ [IFLA_BRIDGE_CFM_MEP_DELETE] =
+ NLA_POLICY_NESTED(br_cfm_mep_delete_policy),
+ [IFLA_BRIDGE_CFM_MEP_CONFIG] =
+ NLA_POLICY_NESTED(br_cfm_mep_config_policy),
+ [IFLA_BRIDGE_CFM_CC_CONFIG] =
+ NLA_POLICY_NESTED(br_cfm_cc_config_policy),
+ [IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD] =
+ NLA_POLICY_NESTED(br_cfm_cc_peer_mep_policy),
+ [IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE] =
+ NLA_POLICY_NESTED(br_cfm_cc_peer_mep_policy),
+ [IFLA_BRIDGE_CFM_CC_RDI] =
+ NLA_POLICY_NESTED(br_cfm_cc_rdi_policy),
+ [IFLA_BRIDGE_CFM_CC_CCM_TX] =
+ NLA_POLICY_NESTED(br_cfm_cc_ccm_tx_policy),
+};
+
+static int br_mep_create_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_CREATE_MAX + 1];
+ struct br_cfm_mep_create create;
+ u32 instance;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_CREATE_MAX, attr,
+ br_cfm_mep_create_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing DOMAIN attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing DIRECTION attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing IFINDEX attribute");
+ return -EINVAL;
+ }
+
+ memset(&create, 0, sizeof(create));
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE]);
+ create.domain = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN]);
+ create.direction = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION]);
+ create.ifindex = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX]);
+
+ return br_cfm_mep_create(br, instance, &create, extack);
+}
+
+static int br_mep_delete_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_DELETE_MAX + 1];
+ u32 instance;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_DELETE_MAX, attr,
+ br_cfm_mep_delete_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE]);
+
+ return br_cfm_mep_delete(br, instance, extack);
+}
+
+static int br_mep_config_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MAX + 1];
+ struct br_cfm_mep_config config;
+ u32 instance;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_CONFIG_MAX, attr,
+ br_cfm_mep_config_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing UNICAST_MAC attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing MDLEVEL attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing MEPID attribute");
+ return -EINVAL;
+ }
+
+ memset(&config, 0, sizeof(config));
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE]);
+ nla_memcpy(&config.unicast_mac.addr,
+ tb[IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC],
+ sizeof(config.unicast_mac.addr));
+ config.mdlevel = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL]);
+ config.mepid = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID]);
+
+ return br_cfm_mep_config_set(br, instance, &config, extack);
+}
+
+static int br_cc_config_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_CC_CONFIG_MAX + 1];
+ struct br_cfm_cc_config config;
+ u32 instance;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_CONFIG_MAX, attr,
+ br_cfm_cc_config_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing ENABLE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INTERVAL attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing MAID attribute");
+ return -EINVAL;
+ }
+
+ memset(&config, 0, sizeof(config));
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE]);
+ config.enable = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE]);
+ config.exp_interval = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL]);
+ nla_memcpy(&config.exp_maid.data, tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID],
+ sizeof(config.exp_maid.data));
+
+ return br_cfm_cc_config_set(br, instance, &config, extack);
+}
+
+static int br_cc_peer_mep_add_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1];
+ u32 instance, peer_mep_id;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX, attr,
+ br_cfm_cc_peer_mep_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing PEER_MEP_ID attribute");
+ return -EINVAL;
+ }
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]);
+ peer_mep_id = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]);
+
+ return br_cfm_cc_peer_mep_add(br, instance, peer_mep_id, extack);
+}
+
+static int br_cc_peer_mep_remove_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1];
+ u32 instance, peer_mep_id;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX, attr,
+ br_cfm_cc_peer_mep_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing PEER_MEP_ID attribute");
+ return -EINVAL;
+ }
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]);
+ peer_mep_id = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]);
+
+ return br_cfm_cc_peer_mep_remove(br, instance, peer_mep_id, extack);
+}
+
+static int br_cc_rdi_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_CC_RDI_MAX + 1];
+ u32 instance, rdi;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_RDI_MAX, attr,
+ br_cfm_cc_rdi_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_RDI_RDI]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing RDI attribute");
+ return -EINVAL;
+ }
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]);
+ rdi = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_RDI]);
+
+ return br_cfm_cc_rdi_set(br, instance, rdi, extack);
+}
+
+static int br_cc_ccm_tx_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_CC_CCM_TX_MAX + 1];
+ struct br_cfm_cc_ccm_tx_info tx_info;
+ u32 instance;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_CCM_TX_MAX, attr,
+ br_cfm_cc_ccm_tx_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing DMAC attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing SEQ_NO_UPDATE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing PERIOD attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing IF_TLV attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing IF_TLV_VALUE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing PORT_TLV attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing PORT_TLV_VALUE attribute");
+ return -EINVAL;
+ }
+
+ memset(&tx_info, 0, sizeof(tx_info));
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]);
+ nla_memcpy(&tx_info.dmac.addr,
+ tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC],
+ sizeof(tx_info.dmac.addr));
+ tx_info.seq_no_update = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE]);
+ tx_info.period = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD]);
+ tx_info.if_tlv = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV]);
+ tx_info.if_tlv_value = nla_get_u8(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE]);
+ tx_info.port_tlv = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV]);
+ tx_info.port_tlv_value = nla_get_u8(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE]);
+
+ return br_cfm_cc_ccm_tx(br, instance, &tx_info, extack);
+}
+
+int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p,
+ struct nlattr *attr, int cmd, struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_MAX + 1];
+ int err;
+
+ /* When this function is called for a port then the br pointer is
+ * invalid, therefor set the br to point correctly
+ */
+ if (p)
+ br = p->br;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MAX, attr,
+ br_cfm_policy, extack);
+ if (err)
+ return err;
+
+ if (tb[IFLA_BRIDGE_CFM_MEP_CREATE]) {
+ err = br_mep_create_parse(br, tb[IFLA_BRIDGE_CFM_MEP_CREATE],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_MEP_DELETE]) {
+ err = br_mep_delete_parse(br, tb[IFLA_BRIDGE_CFM_MEP_DELETE],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_MEP_CONFIG]) {
+ err = br_mep_config_parse(br, tb[IFLA_BRIDGE_CFM_MEP_CONFIG],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_CC_CONFIG]) {
+ err = br_cc_config_parse(br, tb[IFLA_BRIDGE_CFM_CC_CONFIG],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD]) {
+ err = br_cc_peer_mep_add_parse(br, tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE]) {
+ err = br_cc_peer_mep_remove_parse(br, tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_CC_RDI]) {
+ err = br_cc_rdi_parse(br, tb[IFLA_BRIDGE_CFM_CC_RDI],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_CC_CCM_TX]) {
+ err = br_cc_ccm_tx_parse(br, tb[IFLA_BRIDGE_CFM_CC_CCM_TX],
+ extack);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct br_cfm_mep *mep;
+ struct nlattr *tb;
+
+ hlist_for_each_entry_rcu(mep, &br->mep_list, head) {
+ tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_CREATE_INFO);
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN,
+ mep->create.domain))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION,
+ mep->create.direction))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX,
+ mep->create.ifindex))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, tb);
+
+ tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_INFO);
+
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC,
+ sizeof(mep->config.unicast_mac.addr),
+ mep->config.unicast_mac.addr))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL,
+ mep->config.mdlevel))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID,
+ mep->config.mepid))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, tb);
+
+ tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_CONFIG_INFO);
+
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE,
+ mep->cc_config.enable))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL,
+ mep->cc_config.exp_interval))
+ goto nla_put_failure;
+
+ if (nla_put(skb, IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID,
+ sizeof(mep->cc_config.exp_maid.data),
+ mep->cc_config.exp_maid.data))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, tb);
+
+ tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_RDI_INFO);
+
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_RDI_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_RDI_RDI,
+ mep->rdi))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, tb);
+
+ tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_INFO);
+
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC,
+ sizeof(mep->cc_ccm_tx_info.dmac),
+ mep->cc_ccm_tx_info.dmac.addr))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE,
+ mep->cc_ccm_tx_info.seq_no_update))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD,
+ mep->cc_ccm_tx_info.period))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV,
+ mep->cc_ccm_tx_info.if_tlv))
+ goto nla_put_failure;
+
+ if (nla_put_u8(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE,
+ mep->cc_ccm_tx_info.if_tlv_value))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV,
+ mep->cc_ccm_tx_info.port_tlv))
+ goto nla_put_failure;
+
+ if (nla_put_u8(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE,
+ mep->cc_ccm_tx_info.port_tlv_value))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, tb);
+
+ hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head) {
+ tb = nla_nest_start(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_INFO);
+
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_PEER_MEPID,
+ peer_mep->mepid))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, tb);
+ }
+ }
+
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, tb);
+
+nla_info_failure:
+ return -EMSGSIZE;
+}
+
+int br_cfm_status_fill_info(struct sk_buff *skb,
+ struct net_bridge *br,
+ bool getlink)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct br_cfm_mep *mep;
+ struct nlattr *tb;
+
+ hlist_for_each_entry_rcu(mep, &br->mep_list, head) {
+ tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_STATUS_INFO);
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN,
+ mep->status.opcode_unexp_seen))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN,
+ mep->status.version_unexp_seen))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN,
+ mep->status.rx_level_low_seen))
+ goto nla_put_failure;
+
+ /* Only clear if this is a GETLINK */
+ if (getlink) {
+ /* Clear all 'seen' indications */
+ mep->status.opcode_unexp_seen = false;
+ mep->status.version_unexp_seen = false;
+ mep->status.rx_level_low_seen = false;
+ }
+
+ nla_nest_end(skb, tb);
+
+ hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head) {
+ tb = nla_nest_start(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO);
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID,
+ peer_mep->mepid))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT,
+ peer_mep->cc_status.ccm_defect))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI,
+ peer_mep->cc_status.rdi))
+ goto nla_put_failure;
+
+ if (nla_put_u8(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE,
+ peer_mep->cc_status.port_tlv_value))
+ goto nla_put_failure;
+
+ if (nla_put_u8(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE,
+ peer_mep->cc_status.if_tlv_value))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN,
+ peer_mep->cc_status.seen))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN,
+ peer_mep->cc_status.tlv_seen))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN,
+ peer_mep->cc_status.seq_unexp_seen))
+ goto nla_put_failure;
+
+ if (getlink) { /* Only clear if this is a GETLINK */
+ /* Clear all 'seen' indications */
+ peer_mep->cc_status.seen = false;
+ peer_mep->cc_status.tlv_seen = false;
+ peer_mep->cc_status.seq_unexp_seen = false;
+ }
+
+ nla_nest_end(skb, tb);
+ }
+ }
+
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, tb);
+
+nla_info_failure:
+ return -EMSGSIZE;
+}
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_fdb_entry *dst;
struct net_bridge_mdb_entry *mdst;
- struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
const struct nf_br_ops *nf_ops;
u8 state = BR_STATE_FORWARDING;
const unsigned char *dest;
return NETDEV_TX_OK;
}
- u64_stats_update_begin(&brstats->syncp);
- brstats->tx_packets++;
- brstats->tx_bytes += skb->len;
- u64_stats_update_end(&brstats->syncp);
+ dev_sw_netstats_tx_add(dev, 1, skb->len);
br_switchdev_frame_unmark(skb);
BR_INPUT_SKB_CB(skb)->brdev = dev;
mdst = br_mdb_get(br, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
- br_multicast_querier_exists(br, eth_hdr(skb)))
+ br_multicast_querier_exists(br, eth_hdr(skb), mdst))
br_multicast_flood(mdst, skb, false, true);
else
br_flood(br, skb, BR_PKT_MULTICAST, false, true);
struct net_bridge *br = netdev_priv(dev);
int err;
- br->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
- if (!br->stats)
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ if (!dev->tstats)
return -ENOMEM;
err = br_fdb_hash_init(br);
if (err) {
- free_percpu(br->stats);
+ free_percpu(dev->tstats);
return err;
}
err = br_mdb_hash_init(br);
if (err) {
- free_percpu(br->stats);
+ free_percpu(dev->tstats);
br_fdb_hash_fini(br);
return err;
}
err = br_vlan_init(br);
if (err) {
- free_percpu(br->stats);
+ free_percpu(dev->tstats);
br_mdb_hash_fini(br);
br_fdb_hash_fini(br);
return err;
err = br_multicast_init_stats(br);
if (err) {
- free_percpu(br->stats);
+ free_percpu(dev->tstats);
br_vlan_flush(br);
br_mdb_hash_fini(br);
br_fdb_hash_fini(br);
br_vlan_flush(br);
br_mdb_hash_fini(br);
br_fdb_hash_fini(br);
- free_percpu(br->stats);
+ free_percpu(dev->tstats);
}
static int br_dev_open(struct net_device *dev)
return 0;
}
-static void br_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *stats)
-{
- struct net_bridge *br = netdev_priv(dev);
-
- netdev_stats_to_stats64(stats, &dev->stats);
- dev_fetch_sw_netstats(stats, br->stats);
-}
-
static int br_change_mtu(struct net_device *dev, int new_mtu)
{
struct net_bridge *br = netdev_priv(dev);
.ndo_init = br_dev_init,
.ndo_uninit = br_dev_uninit,
.ndo_start_xmit = br_dev_xmit,
- .ndo_get_stats64 = br_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_set_mac_address = br_set_mac_address,
.ndo_set_rx_mode = br_dev_set_multicast_list,
.ndo_change_rx_flags = br_dev_change_rx_flags,
spin_lock_init(&br->lock);
INIT_LIST_HEAD(&br->port_list);
INIT_HLIST_HEAD(&br->fdb_list);
+ INIT_HLIST_HEAD(&br->frame_type_list);
#if IS_ENABLED(CONFIG_BRIDGE_MRP)
- INIT_LIST_HEAD(&br->mrp_list);
+ INIT_HLIST_HEAD(&br->mrp_list);
+#endif
+#if IS_ENABLED(CONFIG_BRIDGE_CFM)
+ INIT_HLIST_HEAD(&br->mep_list);
#endif
spin_lock_init(&br->hash_lock);
spin_unlock_bh(&br->lock);
br_mrp_port_del(br, p);
+ br_cfm_port_del(br, p);
br_ifinfo_notify(RTM_DELLINK, NULL, p);
struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
struct net_bridge *br = netdev_priv(brdev);
struct net_bridge_vlan_group *vg;
- struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
- u64_stats_update_begin(&brstats->syncp);
- brstats->rx_packets++;
- brstats->rx_bytes += skb->len;
- u64_stats_update_end(&brstats->syncp);
+ dev_sw_netstats_rx_add(brdev, skb->len);
vg = br_vlan_group_rcu(br);
/* Bridge is just like any other port. Make sure the
case BR_PKT_MULTICAST:
mdst = br_mdb_get(br, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
- br_multicast_querier_exists(br, eth_hdr(skb))) {
+ br_multicast_querier_exists(br, eth_hdr(skb), mdst)) {
if ((mdst && mdst->host_joined) ||
br_multicast_is_router(br)) {
local_rcv = true;
return RX_HANDLER_CONSUMED;
}
+/* Return 0 if the frame was not processed otherwise 1
+ * note: already called with rcu_read_lock
+ */
+static int br_process_frame_type(struct net_bridge_port *p,
+ struct sk_buff *skb)
+{
+ struct br_frame_type *tmp;
+
+ hlist_for_each_entry_rcu(tmp, &p->br->frame_type_list, list)
+ if (unlikely(tmp->type == skb->protocol))
+ return tmp->frame_handler(p, skb);
+
+ return 0;
+}
+
/*
* Return NULL if skb is handled
* note: already called with rcu_read_lock
}
}
- if (unlikely(br_mrp_process(p, skb)))
+ if (unlikely(br_process_frame_type(p, skb)))
return RX_HANDLER_PASS;
forward:
return br_handle_frame;
}
+
+void br_add_frame(struct net_bridge *br, struct br_frame_type *ft)
+{
+ hlist_add_head_rcu(&ft->list, &br->frame_type_list);
+}
+
+void br_del_frame(struct net_bridge *br, struct br_frame_type *ft)
+{
+ struct br_frame_type *tmp;
+
+ hlist_for_each_entry(tmp, &br->frame_type_list, list)
+ if (ft == tmp) {
+ hlist_del_rcu(&ft->list);
+ return;
+ }
+}
ip->src.ip6 = nla_get_in6_addr(mdb_attrs[MDBE_ATTR_SOURCE]);
break;
#endif
+ default:
+ ether_addr_copy(ip->dst.mac_addr, entry->addr.u.mac_addr);
}
}
if (mp->addr.proto == htons(ETH_P_IP))
e.addr.u.ip4 = mp->addr.dst.ip4;
#if IS_ENABLED(CONFIG_IPV6)
- if (mp->addr.proto == htons(ETH_P_IPV6))
+ else if (mp->addr.proto == htons(ETH_P_IPV6))
e.addr.u.ip6 = mp->addr.dst.ip6;
#endif
+ else
+ ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr);
e.addr.proto = mp->addr.proto;
nest_ent = nla_nest_start_noflag(skb,
MDBA_MDB_ENTRY_INFO);
}
break;
#endif
+ default:
+ ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr);
}
if (p) {
if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, p->rt_protocol))
if (mp->addr.proto == htons(ETH_P_IP))
ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
#if IS_ENABLED(CONFIG_IPV6)
- else
+ else if (mp->addr.proto == htons(ETH_P_IPV6))
ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
#endif
+ else
+ ether_addr_copy(mdb.addr, mp->addr.dst.mac_addr);
+
mdb.obj.orig_dev = pg->key.port->dev;
switch (type) {
case RTM_NEWMDB:
return false;
}
#endif
+ } else if (entry->addr.proto == 0) {
+ /* L2 mdb */
+ if (!is_multicast_ether_addr(entry->addr.u.mac_addr)) {
+ NL_SET_ERR_MSG_MOD(extack, "L2 entry group is not multicast");
+ return false;
+ }
} else {
NL_SET_ERR_MSG_MOD(extack, "Unknown entry protocol");
return false;
struct net_bridge_port_group __rcu **pp;
struct br_ip group, star_group;
unsigned long now = jiffies;
+ unsigned char flags = 0;
u8 filter_mode;
int err;
}
}
+ if (br_group_is_l2(&group) && entry->state != MDB_PERMANENT) {
+ NL_SET_ERR_MSG_MOD(extack, "Only permanent L2 entries allowed");
+ return -EINVAL;
+ }
+
mp = br_mdb_ip_get(br, &group);
if (!mp) {
mp = br_multicast_new_group(br, &group);
filter_mode = br_multicast_is_star_g(&group) ? MCAST_EXCLUDE :
MCAST_INCLUDE;
- p = br_multicast_new_port_group(port, &group, *pp, entry->state, NULL,
+ if (entry->state == MDB_PERMANENT)
+ flags |= MDB_PG_FLAGS_PERMANENT;
+
+ p = br_multicast_new_port_group(port, &group, *pp, flags, NULL,
filter_mode, RTPROT_STATIC);
if (unlikely(!p)) {
NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group");
static const u8 mrp_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x1 };
static const u8 mrp_in_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x3 };
+static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb);
+
+static struct br_frame_type mrp_frame_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_MRP),
+ .frame_handler = br_mrp_process,
+};
+
static bool br_mrp_is_ring_port(struct net_bridge_port *p_port,
struct net_bridge_port *s_port,
struct net_bridge_port *port)
struct br_mrp *res = NULL;
struct br_mrp *mrp;
- list_for_each_entry_rcu(mrp, &br->mrp_list, list,
- lockdep_rtnl_is_held()) {
+ hlist_for_each_entry_rcu(mrp, &br->mrp_list, list,
+ lockdep_rtnl_is_held()) {
if (mrp->ring_id == ring_id) {
res = mrp;
break;
struct br_mrp *res = NULL;
struct br_mrp *mrp;
- list_for_each_entry_rcu(mrp, &br->mrp_list, list,
- lockdep_rtnl_is_held()) {
+ hlist_for_each_entry_rcu(mrp, &br->mrp_list, list,
+ lockdep_rtnl_is_held()) {
if (mrp->in_id == in_id) {
res = mrp;
break;
{
struct br_mrp *mrp;
- list_for_each_entry_rcu(mrp, &br->mrp_list, list,
- lockdep_rtnl_is_held()) {
+ hlist_for_each_entry_rcu(mrp, &br->mrp_list, list,
+ lockdep_rtnl_is_held()) {
struct net_bridge_port *p;
p = rtnl_dereference(mrp->p_port);
struct br_mrp *res = NULL;
struct br_mrp *mrp;
- list_for_each_entry_rcu(mrp, &br->mrp_list, list,
- lockdep_rtnl_is_held()) {
+ hlist_for_each_entry_rcu(mrp, &br->mrp_list, list,
+ lockdep_rtnl_is_held()) {
if (rcu_access_pointer(mrp->p_port) == p ||
rcu_access_pointer(mrp->s_port) == p ||
rcu_access_pointer(mrp->i_port) == p) {
rcu_assign_pointer(mrp->i_port, NULL);
}
- list_del_rcu(&mrp->list);
+ hlist_del_rcu(&mrp->list);
kfree_rcu(mrp, rcu);
+
+ if (hlist_empty(&br->mrp_list))
+ br_del_frame(br, &mrp_frame_type);
}
/* Adds a new MRP instance.
spin_unlock_bh(&br->lock);
rcu_assign_pointer(mrp->s_port, p);
+ if (hlist_empty(&br->mrp_list))
+ br_add_frame(br, &mrp_frame_type);
+
INIT_DELAYED_WORK(&mrp->test_work, br_mrp_test_work_expired);
INIT_DELAYED_WORK(&mrp->in_test_work, br_mrp_in_test_work_expired);
- list_add_tail_rcu(&mrp->list, &br->mrp_list);
+ hlist_add_tail_rcu(&mrp->list, &br->mrp_list);
err = br_mrp_switchdev_add(br, mrp);
if (err)
if (hdr->type == BR_MRP_TLV_HEADER_IN_TEST ||
hdr->type == BR_MRP_TLV_HEADER_IN_TOPO ||
hdr->type == BR_MRP_TLV_HEADER_IN_LINK_DOWN ||
- hdr->type == BR_MRP_TLV_HEADER_IN_LINK_UP)
+ hdr->type == BR_MRP_TLV_HEADER_IN_LINK_UP ||
+ hdr->type == BR_MRP_TLV_HEADER_IN_LINK_STATUS)
return true;
return false;
goto no_forward;
}
} else {
- /* MIM should forward IntLinkChange and
+ /* MIM should forward IntLinkChange/Status and
* IntTopoChange between ring ports but MIM
- * should not forward IntLinkChange and
+ * should not forward IntLinkChange/Status and
* IntTopoChange if the frame was received at
* the interconnect port
*/
in_type == BR_MRP_TLV_HEADER_IN_LINK_DOWN))
goto forward;
+ /* MIC should forward IntLinkStatus frames only to
+ * interconnect port if it was received on a ring port.
+ * If it is received on interconnect port then, it
+ * should be forward on both ring ports
+ */
+ if (br_mrp_is_ring_port(p_port, s_port, p) &&
+ in_type == BR_MRP_TLV_HEADER_IN_LINK_STATUS) {
+ p_dst = NULL;
+ s_dst = NULL;
+ }
+
/* Should forward the InTopo frames only between the
* ring ports
*/
* normal forwarding.
* note: already called with rcu_read_lock
*/
-int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb)
+static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb)
{
/* If there is no MRP instance do normal forwarding */
if (likely(!(p->flags & BR_MRP_AWARE)))
goto out;
- if (unlikely(skb->protocol == htons(ETH_P_MRP)))
- return br_mrp_rcv(p, skb, p->dev);
-
+ return br_mrp_rcv(p, skb, p->dev);
out:
return 0;
}
bool br_mrp_enabled(struct net_bridge *br)
{
- return !list_empty(&br->mrp_list);
+ return !hlist_empty(&br->mrp_list);
}
if (!mrp_tb)
return -EMSGSIZE;
- list_for_each_entry_rcu(mrp, &br->mrp_list, list) {
+ hlist_for_each_entry_rcu(mrp, &br->mrp_list, list) {
struct net_bridge_port *p;
tb = nla_nest_start_noflag(skb, IFLA_BRIDGE_MRP_INFO);
break;
#endif
default:
- return NULL;
+ ip.proto = 0;
+ ether_addr_copy(ip.dst.mac_addr, eth_hdr(skb)->h_dest);
}
return br_mdb_ip_get_rcu(br, &ip);
if (notify)
br_mdb_notify(mp->br->dev, mp, NULL, RTM_NEWMDB);
}
+
+ if (br_group_is_l2(&mp->addr))
+ return;
+
mod_timer(&mp->timer, jiffies + mp->br->multicast_membership_interval);
}
break;
}
- p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode,
- RTPROT_KERNEL);
+ p = br_multicast_new_port_group(port, group, *pp, 0, src,
+ filter_mode, RTPROT_KERNEL);
if (unlikely(!p)) {
p = ERR_PTR(-ENOMEM);
goto out;
memset(ð, 0, sizeof(eth));
eth.h_proto = htons(proto);
- ret = br_multicast_querier_exists(br, ð);
+ ret = br_multicast_querier_exists(br, ð, NULL);
unlock:
rcu_read_unlock();
#include "br_private.h"
#include "br_private_stp.h"
+#include "br_private_cfm.h"
#include "br_private_tunnel.h"
static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg,
{
struct net_bridge_vlan_group *vg = NULL;
struct net_bridge_port *p = NULL;
- struct net_bridge *br;
- int num_vlan_infos;
+ struct net_bridge *br = NULL;
+ u32 num_cfm_peer_mep_infos;
+ u32 num_cfm_mep_infos;
size_t vinfo_sz = 0;
+ int num_vlan_infos;
rcu_read_lock();
if (netif_is_bridge_port(dev)) {
/* Each VLAN is returned in bridge_vlan_info along with flags */
vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info));
+ if (!(filter_mask & RTEXT_FILTER_CFM_STATUS))
+ return vinfo_sz;
+
+ if (!br)
+ return vinfo_sz;
+
+ /* CFM status info must be added */
+ br_cfm_mep_count(br, &num_cfm_mep_infos);
+ br_cfm_peer_mep_count(br, &num_cfm_peer_mep_infos);
+
+ vinfo_sz += nla_total_size(0); /* IFLA_BRIDGE_CFM */
+ /* For each status struct the MEP instance (u32) is added */
+ /* MEP instance (u32) + br_cfm_mep_status */
+ vinfo_sz += num_cfm_mep_infos *
+ /*IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE */
+ (nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN */
+ + nla_total_size(sizeof(u32)));
+ /* MEP instance (u32) + br_cfm_cc_peer_status */
+ vinfo_sz += num_cfm_peer_mep_infos *
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE */
+ (nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE */
+ + nla_total_size(sizeof(u8))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE */
+ + nla_total_size(sizeof(u8))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN */
+ + nla_total_size(sizeof(u32)));
+
return vinfo_sz;
}
static int br_fill_ifinfo(struct sk_buff *skb,
const struct net_bridge_port *port,
u32 pid, u32 seq, int event, unsigned int flags,
- u32 filter_mask, const struct net_device *dev)
+ u32 filter_mask, const struct net_device *dev,
+ bool getlink)
{
u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
struct nlattr *af = NULL;
if (filter_mask & (RTEXT_FILTER_BRVLAN |
RTEXT_FILTER_BRVLAN_COMPRESSED |
- RTEXT_FILTER_MRP)) {
+ RTEXT_FILTER_MRP |
+ RTEXT_FILTER_CFM_CONFIG |
+ RTEXT_FILTER_CFM_STATUS)) {
af = nla_nest_start_noflag(skb, IFLA_AF_SPEC);
if (!af)
goto nla_put_failure;
goto nla_put_failure;
}
+ if (filter_mask & (RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS)) {
+ struct nlattr *cfm_nest = NULL;
+ int err;
+
+ if (!br_cfm_created(br) || port)
+ goto done;
+
+ cfm_nest = nla_nest_start(skb, IFLA_BRIDGE_CFM);
+ if (!cfm_nest)
+ goto nla_put_failure;
+
+ if (filter_mask & RTEXT_FILTER_CFM_CONFIG) {
+ rcu_read_lock();
+ err = br_cfm_config_fill_info(skb, br);
+ rcu_read_unlock();
+ if (err)
+ goto nla_put_failure;
+ }
+
+ if (filter_mask & RTEXT_FILTER_CFM_STATUS) {
+ rcu_read_lock();
+ err = br_cfm_status_fill_info(skb, br, getlink);
+ rcu_read_unlock();
+ if (err)
+ goto nla_put_failure;
+ }
+
+ nla_nest_end(skb, cfm_nest);
+ }
+
done:
if (af)
nla_nest_end(skb, af);
return -EMSGSIZE;
}
-/* 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)
+void br_info_notify(int event, const struct net_bridge *br,
+ const struct net_bridge_port *port, u32 filter)
{
- u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
struct net_device *dev;
struct sk_buff *skb;
int err = -ENOBUFS;
if (skb == NULL)
goto errout;
- err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev);
+ err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev, false);
if (err < 0) {
/* -EMSGSIZE implies BUG in br_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
rtnl_set_sk_err(net, RTNLGRP_LINK, err);
}
+/* 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)
+{
+ u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
+
+ return br_info_notify(event, br, port, filter);
+}
+
/*
* Dump information about all ports, in response to GETLINK
*/
if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) &&
!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) &&
- !(filter_mask & RTEXT_FILTER_MRP))
+ !(filter_mask & RTEXT_FILTER_MRP) &&
+ !(filter_mask & RTEXT_FILTER_CFM_CONFIG) &&
+ !(filter_mask & RTEXT_FILTER_CFM_STATUS))
return 0;
return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags,
- filter_mask, dev);
+ filter_mask, dev, true);
}
static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
if (err)
return err;
break;
+ case IFLA_BRIDGE_CFM:
+ err = br_cfm_parse(br, p, attr, cmd, extack);
+ if (err)
+ return err;
+ break;
}
}
pvid = br_get_pvid(vg);
list_for_each_entry(v, &vg->vlan_list, vlist) {
struct bridge_vlan_xstats vxi;
- struct br_vlan_stats stats;
+ struct pcpu_sw_netstats stats;
if (++vl_idx < *prividx)
continue;
};
#endif
-struct br_vlan_stats {
- u64 rx_bytes;
- u64 rx_packets;
- u64 tx_bytes;
- u64 tx_packets;
- struct u64_stats_sync syncp;
-};
-
struct br_tunnel_info {
__be64 tunnel_id;
struct metadata_dst *tunnel_dst;
u16 flags;
u16 priv_flags;
u8 state;
- struct br_vlan_stats __percpu *stats;
+ struct pcpu_sw_netstats __percpu *stats;
union {
struct net_bridge *br;
struct net_bridge_port *port;
struct net_bridge {
spinlock_t lock;
spinlock_t hash_lock;
- struct list_head port_list;
+ struct hlist_head frame_type_list;
struct net_device *dev;
- struct pcpu_sw_netstats __percpu *stats;
unsigned long options;
/* These fields are accessed on each packet */
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
#endif
struct rhashtable fdb_hash_tbl;
+ struct list_head port_list;
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
union {
struct rtable fake_rtable;
struct hlist_head fdb_list;
#if IS_ENABLED(CONFIG_BRIDGE_MRP)
- struct list_head mrp_list;
+ struct hlist_head mrp_list;
+#endif
+#if IS_ENABLED(CONFIG_BRIDGE_CFM)
+ struct hlist_head mep_list;
#endif
};
int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
rx_handler_func_t *br_get_rx_handler(const struct net_device *dev);
+struct br_frame_type {
+ __be16 type;
+ int (*frame_handler)(struct net_bridge_port *port,
+ struct sk_buff *skb);
+ struct hlist_node list;
+};
+
+void br_add_frame(struct net_bridge *br, struct br_frame_type *ft);
+void br_del_frame(struct net_bridge *br, struct br_frame_type *ft);
+
static inline bool br_rx_handler_check_rcu(const struct net_device *dev)
{
return rcu_dereference(dev->rx_handler) == br_get_rx_handler(dev);
void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
struct net_bridge_port_group *sg);
+static inline bool br_group_is_l2(const struct br_ip *group)
+{
+ return group->proto == 0;
+}
+
#define mlock_dereference(X, br) \
rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
}
static inline bool br_multicast_querier_exists(struct net_bridge *br,
- struct ethhdr *eth)
+ struct ethhdr *eth,
+ const struct net_bridge_mdb_entry *mdb)
{
switch (eth->h_proto) {
case (htons(ETH_P_IP)):
&br->ip6_other_query, true);
#endif
default:
- return false;
+ return !!mdb && br_group_is_l2(&mdb->addr);
}
}
}
static inline bool br_multicast_querier_exists(struct net_bridge *br,
- struct ethhdr *eth)
+ struct ethhdr *eth,
+ const struct net_bridge_mdb_entry *mdb)
{
return false;
}
int nbp_vlan_init(struct net_bridge_port *port, struct netlink_ext_ack *extack);
int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask);
void br_vlan_get_stats(const struct net_bridge_vlan *v,
- struct br_vlan_stats *stats);
+ struct pcpu_sw_netstats *stats);
void br_vlan_port_event(struct net_bridge_port *p, unsigned long event);
int br_vlan_bridge_event(struct net_device *dev, unsigned long event,
void *ptr);
}
static inline void br_vlan_get_stats(const struct net_bridge_vlan *v,
- struct br_vlan_stats *stats)
+ struct pcpu_sw_netstats *stats)
{
}
#if IS_ENABLED(CONFIG_BRIDGE_MRP)
int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p,
struct nlattr *attr, int cmd, struct netlink_ext_ack *extack);
-int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb);
bool br_mrp_enabled(struct net_bridge *br);
void br_mrp_port_del(struct net_bridge *br, struct net_bridge_port *p);
int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br);
return -EOPNOTSUPP;
}
-static inline int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb)
-{
- return 0;
-}
-
static inline bool br_mrp_enabled(struct net_bridge *br)
{
return false;
#endif
+/* br_cfm.c */
+#if IS_ENABLED(CONFIG_BRIDGE_CFM)
+int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p,
+ struct nlattr *attr, int cmd, struct netlink_ext_ack *extack);
+bool br_cfm_created(struct net_bridge *br);
+void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *p);
+int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br);
+int br_cfm_status_fill_info(struct sk_buff *skb,
+ struct net_bridge *br,
+ bool getlink);
+int br_cfm_mep_count(struct net_bridge *br, u32 *count);
+int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count);
+#else
+static inline int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p,
+ struct nlattr *attr, int cmd,
+ struct netlink_ext_ack *extack)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline bool br_cfm_created(struct net_bridge *br)
+{
+ return false;
+}
+
+static inline void br_cfm_port_del(struct net_bridge *br,
+ struct net_bridge_port *p)
+{
+}
+
+static inline int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int br_cfm_status_fill_info(struct sk_buff *skb,
+ struct net_bridge *br,
+ bool getlink)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int br_cfm_mep_count(struct net_bridge *br, u32 *count)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
/* br_netlink.c */
extern struct rtnl_link_ops br_link_ops;
int br_netlink_init(void);
void br_netlink_fini(void);
void br_ifinfo_notify(int event, const struct net_bridge *br,
const struct net_bridge_port *port);
+void br_info_notify(int event, const struct net_bridge *br,
+ const struct net_bridge_port *port, u32 filter);
int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags,
struct netlink_ext_ack *extack);
int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _BR_PRIVATE_CFM_H_
+#define _BR_PRIVATE_CFM_H_
+
+#include "br_private.h"
+#include <uapi/linux/cfm_bridge.h>
+
+struct br_cfm_mep_create {
+ enum br_cfm_domain domain; /* Domain for this MEP */
+ enum br_cfm_mep_direction direction; /* Up or Down MEP direction */
+ u32 ifindex; /* Residence port */
+};
+
+int br_cfm_mep_create(struct net_bridge *br,
+ const u32 instance,
+ struct br_cfm_mep_create *const create,
+ struct netlink_ext_ack *extack);
+
+int br_cfm_mep_delete(struct net_bridge *br,
+ const u32 instance,
+ struct netlink_ext_ack *extack);
+
+struct br_cfm_mep_config {
+ u32 mdlevel;
+ u32 mepid; /* MEPID for this MEP */
+ struct mac_addr unicast_mac; /* The MEP unicast MAC */
+};
+
+int br_cfm_mep_config_set(struct net_bridge *br,
+ const u32 instance,
+ const struct br_cfm_mep_config *const config,
+ struct netlink_ext_ack *extack);
+
+struct br_cfm_maid {
+ u8 data[CFM_MAID_LENGTH];
+};
+
+struct br_cfm_cc_config {
+ /* Expected received CCM PDU MAID. */
+ struct br_cfm_maid exp_maid;
+
+ /* Expected received CCM PDU interval. */
+ /* Transmitting CCM PDU interval when CCM tx is enabled. */
+ enum br_cfm_ccm_interval exp_interval;
+
+ bool enable; /* Enable/disable CCM PDU handling */
+};
+
+int br_cfm_cc_config_set(struct net_bridge *br,
+ const u32 instance,
+ const struct br_cfm_cc_config *const config,
+ struct netlink_ext_ack *extack);
+
+int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance,
+ u32 peer_mep_id,
+ struct netlink_ext_ack *extack);
+int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance,
+ u32 peer_mep_id,
+ struct netlink_ext_ack *extack);
+
+/* Transmitted CCM Remote Defect Indication status set.
+ * This RDI is inserted in transmitted CCM PDUs if CCM transmission is enabled.
+ * See br_cfm_cc_ccm_tx() with interval != BR_CFM_CCM_INTERVAL_NONE
+ */
+int br_cfm_cc_rdi_set(struct net_bridge *br, const u32 instance,
+ const bool rdi, struct netlink_ext_ack *extack);
+
+/* OAM PDU Tx information */
+struct br_cfm_cc_ccm_tx_info {
+ struct mac_addr dmac;
+ /* The CCM will be transmitted for this period in seconds.
+ * Call br_cfm_cc_ccm_tx before timeout to keep transmission alive.
+ * When period is zero any ongoing transmission will be stopped.
+ */
+ u32 period;
+
+ bool seq_no_update; /* Update Tx CCM sequence number */
+ bool if_tlv; /* Insert Interface Status TLV */
+ u8 if_tlv_value; /* Interface Status TLV value */
+ bool port_tlv; /* Insert Port Status TLV */
+ u8 port_tlv_value; /* Port Status TLV value */
+ /* Sender ID TLV ??
+ * Organization-Specific TLV ??
+ */
+};
+
+int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance,
+ const struct br_cfm_cc_ccm_tx_info *const tx_info,
+ struct netlink_ext_ack *extack);
+
+struct br_cfm_mep_status {
+ /* Indications that an OAM PDU has been seen. */
+ bool opcode_unexp_seen; /* RX of OAM PDU with unexpected opcode */
+ bool version_unexp_seen; /* RX of OAM PDU with unexpected version */
+ bool rx_level_low_seen; /* Rx of OAM PDU with level low */
+};
+
+struct br_cfm_cc_peer_status {
+ /* This CCM related status is based on the latest received CCM PDU. */
+ u8 port_tlv_value; /* Port Status TLV value */
+ u8 if_tlv_value; /* Interface Status TLV value */
+
+ /* CCM has not been received for 3.25 intervals */
+ u8 ccm_defect:1;
+
+ /* (RDI == 1) for last received CCM PDU */
+ u8 rdi:1;
+
+ /* Indications that a CCM PDU has been seen. */
+ u8 seen:1; /* CCM PDU received */
+ u8 tlv_seen:1; /* CCM PDU with TLV received */
+ /* CCM PDU with unexpected sequence number received */
+ u8 seq_unexp_seen:1;
+};
+
+struct br_cfm_mep {
+ /* list header of MEP instances */
+ struct hlist_node head;
+ u32 instance;
+ struct br_cfm_mep_create create;
+ struct br_cfm_mep_config config;
+ struct br_cfm_cc_config cc_config;
+ struct br_cfm_cc_ccm_tx_info cc_ccm_tx_info;
+ /* List of multiple peer MEPs */
+ struct hlist_head peer_mep_list;
+ struct net_bridge_port __rcu *b_port;
+ unsigned long ccm_tx_end;
+ struct delayed_work ccm_tx_dwork;
+ u32 ccm_tx_snumber;
+ u32 ccm_rx_snumber;
+ struct br_cfm_mep_status status;
+ bool rdi;
+ struct rcu_head rcu;
+};
+
+struct br_cfm_peer_mep {
+ struct hlist_node head;
+ struct br_cfm_mep *mep;
+ struct delayed_work ccm_rx_dwork;
+ u32 mepid;
+ struct br_cfm_cc_peer_status cc_status;
+ u32 ccm_rx_count_miss;
+ struct rcu_head rcu;
+};
+
+#endif /* _BR_PRIVATE_CFM_H_ */
struct br_mrp {
/* list of mrp instances */
- struct list_head list;
+ struct hlist_node list;
struct net_bridge_port __rcu *p_port;
struct net_bridge_port __rcu *s_port;
goto out_filt;
v->brvlan = masterv;
if (br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)) {
- v->stats = netdev_alloc_pcpu_stats(struct br_vlan_stats);
+ v->stats =
+ netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!v->stats) {
err = -ENOMEM;
goto out_filt;
struct net_bridge_vlan_group *vg,
struct sk_buff *skb)
{
- struct br_vlan_stats *stats;
+ struct pcpu_sw_netstats *stats;
struct net_bridge_vlan *v;
u16 vid;
struct sk_buff *skb, u16 *vid,
u8 *state)
{
- struct br_vlan_stats *stats;
+ struct pcpu_sw_netstats *stats;
struct net_bridge_vlan *v;
bool tagged;
if (!vlan)
return -ENOMEM;
- vlan->stats = netdev_alloc_pcpu_stats(struct br_vlan_stats);
+ vlan->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!vlan->stats) {
kfree(vlan);
return -ENOMEM;
int __br_vlan_set_proto(struct net_bridge *br, __be16 proto)
{
+ struct switchdev_attr attr = {
+ .orig_dev = br->dev,
+ .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL,
+ .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP,
+ .u.vlan_protocol = ntohs(proto),
+ };
int err = 0;
struct net_bridge_port *p;
struct net_bridge_vlan *vlan;
struct net_bridge_vlan_group *vg;
- __be16 oldproto;
+ __be16 oldproto = br->vlan_proto;
if (br->vlan_proto == proto)
return 0;
+ err = switchdev_port_attr_set(br->dev, &attr);
+ if (err && err != -EOPNOTSUPP)
+ return err;
+
/* Add VLANs for the new proto to the device filter. */
list_for_each_entry(p, &br->port_list, list) {
vg = nbp_vlan_group(p);
}
}
- oldproto = br->vlan_proto;
br->vlan_proto = proto;
recalculate_group_addr(br);
return 0;
err_filt:
+ attr.u.vlan_protocol = ntohs(oldproto);
+ switchdev_port_attr_set(br->dev, &attr);
+
list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist)
vlan_vid_del(p->dev, proto, vlan->vid);
}
void br_vlan_get_stats(const struct net_bridge_vlan *v,
- struct br_vlan_stats *stats)
+ struct pcpu_sw_netstats *stats)
{
int i;
memset(stats, 0, sizeof(*stats));
for_each_possible_cpu(i) {
u64 rxpackets, rxbytes, txpackets, txbytes;
- struct br_vlan_stats *cpu_stats;
+ struct pcpu_sw_netstats *cpu_stats;
unsigned int start;
cpu_stats = per_cpu_ptr(v->stats, i);
static bool br_vlan_stats_fill(struct sk_buff *skb,
const struct net_bridge_vlan *v)
{
- struct br_vlan_stats stats;
+ struct pcpu_sw_netstats stats;
struct nlattr *nest;
nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY_STATS);
config NFT_BRIDGE_REJECT
tristate "Netfilter nf_tables bridge reject support"
- depends on NFT_REJECT && NFT_REJECT_IPV4 && NFT_REJECT_IPV6
+ depends on NFT_REJECT
help
Add support to reject packets.
}
}
-static int nft_bridge_iphdr_validate(struct sk_buff *skb)
-{
- struct iphdr *iph;
- u32 len;
-
- if (!pskb_may_pull(skb, sizeof(struct iphdr)))
- return 0;
-
- iph = ip_hdr(skb);
- if (iph->ihl < 5 || iph->version != 4)
- return 0;
-
- len = ntohs(iph->tot_len);
- if (skb->len < len)
- return 0;
- else if (len < (iph->ihl*4))
- return 0;
-
- if (!pskb_may_pull(skb, iph->ihl*4))
- return 0;
-
- return 1;
-}
-
/* We cannot use oldskb->dev, it can be either bridge device (NF_BRIDGE INPUT)
* or the bridge port (NF_BRIDGE PREROUTING).
*/
int hook)
{
struct sk_buff *nskb;
- struct iphdr *niph;
- const struct tcphdr *oth;
- struct tcphdr _oth;
- if (!nft_bridge_iphdr_validate(oldskb))
- return;
-
- oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook);
- if (!oth)
- return;
-
- nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
- LL_MAX_HEADER, GFP_ATOMIC);
+ nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook);
if (!nskb)
return;
- skb_reserve(nskb, LL_MAX_HEADER);
- niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
- net->ipv4.sysctl_ip_default_ttl);
- nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
- niph->tot_len = htons(nskb->len);
- ip_send_check(niph);
-
nft_reject_br_push_etherhdr(oldskb, nskb);
br_forward(br_port_get_rcu(dev), nskb, false, true);
int hook, u8 code)
{
struct sk_buff *nskb;
- struct iphdr *niph;
- struct icmphdr *icmph;
- unsigned int len;
- __wsum csum;
- u8 proto;
-
- if (!nft_bridge_iphdr_validate(oldskb))
- return;
-
- /* IP header checks: fragment. */
- if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
- return;
-
- /* RFC says return as much as we can without exceeding 576 bytes. */
- len = min_t(unsigned int, 536, oldskb->len);
-
- if (!pskb_may_pull(oldskb, len))
- return;
-
- if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len)))
- return;
-
- proto = ip_hdr(oldskb)->protocol;
-
- if (!skb_csum_unnecessary(oldskb) &&
- nf_reject_verify_csum(proto) &&
- nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto))
- return;
- nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) +
- LL_MAX_HEADER + len, GFP_ATOMIC);
+ nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code);
if (!nskb)
return;
- skb_reserve(nskb, LL_MAX_HEADER);
- niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP,
- net->ipv4.sysctl_ip_default_ttl);
-
- skb_reset_transport_header(nskb);
- icmph = skb_put_zero(nskb, sizeof(struct icmphdr));
- icmph->type = ICMP_DEST_UNREACH;
- icmph->code = code;
-
- skb_put_data(nskb, skb_network_header(oldskb), len);
-
- csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0);
- icmph->checksum = csum_fold(csum);
-
- niph->tot_len = htons(nskb->len);
- ip_send_check(niph);
-
nft_reject_br_push_etherhdr(oldskb, nskb);
br_forward(br_port_get_rcu(dev), nskb, false, true);
}
-static int nft_bridge_ip6hdr_validate(struct sk_buff *skb)
-{
- struct ipv6hdr *hdr;
- u32 pkt_len;
-
- if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
- return 0;
-
- hdr = ipv6_hdr(skb);
- if (hdr->version != 6)
- return 0;
-
- pkt_len = ntohs(hdr->payload_len);
- if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
- return 0;
-
- return 1;
-}
-
static void nft_reject_br_send_v6_tcp_reset(struct net *net,
struct sk_buff *oldskb,
const struct net_device *dev,
int hook)
{
struct sk_buff *nskb;
- const struct tcphdr *oth;
- struct tcphdr _oth;
- unsigned int otcplen;
- struct ipv6hdr *nip6h;
- if (!nft_bridge_ip6hdr_validate(oldskb))
- return;
-
- oth = nf_reject_ip6_tcphdr_get(oldskb, &_oth, &otcplen, hook);
- if (!oth)
- return;
-
- nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct tcphdr) +
- LL_MAX_HEADER, GFP_ATOMIC);
+ nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook);
if (!nskb)
return;
- skb_reserve(nskb, LL_MAX_HEADER);
- nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
- net->ipv6.devconf_all->hop_limit);
- nf_reject_ip6_tcphdr_put(nskb, oldskb, oth, otcplen);
- nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr));
-
nft_reject_br_push_etherhdr(oldskb, nskb);
br_forward(br_port_get_rcu(dev), nskb, false, true);
}
-static bool reject6_br_csum_ok(struct sk_buff *skb, int hook)
-{
- const struct ipv6hdr *ip6h = ipv6_hdr(skb);
- int thoff;
- __be16 fo;
- u8 proto = ip6h->nexthdr;
-
- if (skb_csum_unnecessary(skb))
- return true;
-
- if (ip6h->payload_len &&
- pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h)))
- return false;
-
- ip6h = ipv6_hdr(skb);
- thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo);
- if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
- return false;
-
- if (!nf_reject_verify_csum(proto))
- return true;
-
- return nf_ip6_checksum(skb, hook, thoff, proto) == 0;
-}
static void nft_reject_br_send_v6_unreach(struct net *net,
struct sk_buff *oldskb,
int hook, u8 code)
{
struct sk_buff *nskb;
- struct ipv6hdr *nip6h;
- struct icmp6hdr *icmp6h;
- unsigned int len;
-
- if (!nft_bridge_ip6hdr_validate(oldskb))
- return;
- /* Include "As much of invoking packet as possible without the ICMPv6
- * packet exceeding the minimum IPv6 MTU" in the ICMP payload.
- */
- len = min_t(unsigned int, 1220, oldskb->len);
-
- if (!pskb_may_pull(oldskb, len))
- return;
-
- if (!reject6_br_csum_ok(oldskb, hook))
- return;
-
- nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) +
- LL_MAX_HEADER + len, GFP_ATOMIC);
+ nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code);
if (!nskb)
return;
- skb_reserve(nskb, LL_MAX_HEADER);
- nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_ICMPV6,
- net->ipv6.devconf_all->hop_limit);
-
- skb_reset_transport_header(nskb);
- icmp6h = skb_put_zero(nskb, sizeof(struct icmp6hdr));
- icmp6h->icmp6_type = ICMPV6_DEST_UNREACH;
- icmp6h->icmp6_code = code;
-
- skb_put_data(nskb, skb_network_header(oldskb), len);
- nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr));
-
- icmp6h->icmp6_cksum =
- csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr,
- nskb->len - sizeof(struct ipv6hdr),
- IPPROTO_ICMPV6,
- csum_partial(icmp6h,
- nskb->len - sizeof(struct ipv6hdr),
- 0));
-
nft_reject_br_push_etherhdr(oldskb, nskb);
br_forward(br_port_get_rcu(dev), nskb, false, true);
(1 << NF_BR_LOCAL_IN));
}
-static int nft_reject_bridge_init(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nlattr * const tb[])
-{
- struct nft_reject *priv = nft_expr_priv(expr);
- int icmp_code;
-
- if (tb[NFTA_REJECT_TYPE] == NULL)
- return -EINVAL;
-
- priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
- switch (priv->type) {
- case NFT_REJECT_ICMP_UNREACH:
- case NFT_REJECT_ICMPX_UNREACH:
- if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
- return -EINVAL;
-
- icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
- if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
- icmp_code > NFT_REJECT_ICMPX_MAX)
- return -EINVAL;
-
- priv->icmp_code = icmp_code;
- break;
- case NFT_REJECT_TCP_RST:
- break;
- default:
- return -EINVAL;
- }
- return 0;
-}
-
-static int nft_reject_bridge_dump(struct sk_buff *skb,
- const struct nft_expr *expr)
-{
- const struct nft_reject *priv = nft_expr_priv(expr);
-
- if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
- goto nla_put_failure;
-
- switch (priv->type) {
- case NFT_REJECT_ICMP_UNREACH:
- case NFT_REJECT_ICMPX_UNREACH:
- if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
- goto nla_put_failure;
- break;
- default:
- break;
- }
-
- return 0;
-
-nla_put_failure:
- return -1;
-}
-
static struct nft_expr_type nft_reject_bridge_type;
static const struct nft_expr_ops nft_reject_bridge_ops = {
.type = &nft_reject_bridge_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
.eval = nft_reject_bridge_eval,
- .init = nft_reject_bridge_init,
- .dump = nft_reject_bridge_dump,
+ .init = nft_reject_init,
+ .dump = nft_reject_dump,
.validate = nft_reject_bridge_validate,
};
int err;
/* check for correct padding to be able to use the structs similarly */
- BUILD_BUG_ON(offsetof(struct can_frame, can_dlc) !=
+ BUILD_BUG_ON(offsetof(struct can_frame, len) !=
offsetof(struct canfd_frame, len) ||
offsetof(struct can_frame, data) !=
offsetof(struct canfd_frame, data));
memcpy(cf->data, mod->modframe.set.data, CANFD_MAX_DLEN);
}
+/* retrieve valid CC DLC value and store it into 'len' */
+static void mod_retrieve_ccdlc(struct canfd_frame *cf)
+{
+ struct can_frame *ccf = (struct can_frame *)cf;
+
+ /* len8_dlc is only valid if len == CAN_MAX_DLEN */
+ if (ccf->len != CAN_MAX_DLEN)
+ return;
+
+ /* do we have a valid len8_dlc value from 9 .. 15 ? */
+ if (ccf->len8_dlc > CAN_MAX_DLEN && ccf->len8_dlc <= CAN_MAX_RAW_DLC)
+ ccf->len = ccf->len8_dlc;
+}
+
+/* convert valid CC DLC value in 'len' into struct can_frame elements */
+static void mod_store_ccdlc(struct canfd_frame *cf)
+{
+ struct can_frame *ccf = (struct can_frame *)cf;
+
+ /* clear potential leftovers */
+ ccf->len8_dlc = 0;
+
+ /* plain data length 0 .. 8 - that was easy */
+ if (ccf->len <= CAN_MAX_DLEN)
+ return;
+
+ /* potentially broken values are catched in can_can_gw_rcv() */
+ if (ccf->len > CAN_MAX_RAW_DLC)
+ return;
+
+ /* we have a valid dlc value from 9 .. 15 in ccf->len */
+ ccf->len8_dlc = ccf->len;
+ ccf->len = CAN_MAX_DLEN;
+}
+
+static void mod_and_ccdlc(struct canfd_frame *cf, struct cf_mod *mod)
+{
+ mod_retrieve_ccdlc(cf);
+ mod_and_len(cf, mod);
+ mod_store_ccdlc(cf);
+}
+
+static void mod_or_ccdlc(struct canfd_frame *cf, struct cf_mod *mod)
+{
+ mod_retrieve_ccdlc(cf);
+ mod_or_len(cf, mod);
+ mod_store_ccdlc(cf);
+}
+
+static void mod_xor_ccdlc(struct canfd_frame *cf, struct cf_mod *mod)
+{
+ mod_retrieve_ccdlc(cf);
+ mod_xor_len(cf, mod);
+ mod_store_ccdlc(cf);
+}
+
+static void mod_set_ccdlc(struct canfd_frame *cf, struct cf_mod *mod)
+{
+ mod_set_len(cf, mod);
+ mod_store_ccdlc(cf);
+}
+
static void canframecpy(struct canfd_frame *dst, struct can_frame *src)
{
/* Copy the struct members separately to ensure that no uninitialized
*/
dst->can_id = src->can_id;
- dst->len = src->can_dlc;
+ dst->len = src->len;
*(u64 *)dst->data = *(u64 *)src->data;
}
if (mb.modtype & CGW_MOD_ID)
mod->modfunc[modidx++] = mod_and_id;
- if (mb.modtype & CGW_MOD_LEN)
- mod->modfunc[modidx++] = mod_and_len;
+ if (mb.modtype & CGW_MOD_DLC)
+ mod->modfunc[modidx++] = mod_and_ccdlc;
if (mb.modtype & CGW_MOD_DATA)
mod->modfunc[modidx++] = mod_and_data;
if (mb.modtype & CGW_MOD_ID)
mod->modfunc[modidx++] = mod_or_id;
- if (mb.modtype & CGW_MOD_LEN)
- mod->modfunc[modidx++] = mod_or_len;
+ if (mb.modtype & CGW_MOD_DLC)
+ mod->modfunc[modidx++] = mod_or_ccdlc;
if (mb.modtype & CGW_MOD_DATA)
mod->modfunc[modidx++] = mod_or_data;
if (mb.modtype & CGW_MOD_ID)
mod->modfunc[modidx++] = mod_xor_id;
- if (mb.modtype & CGW_MOD_LEN)
- mod->modfunc[modidx++] = mod_xor_len;
+ if (mb.modtype & CGW_MOD_DLC)
+ mod->modfunc[modidx++] = mod_xor_ccdlc;
if (mb.modtype & CGW_MOD_DATA)
mod->modfunc[modidx++] = mod_xor_data;
if (mb.modtype & CGW_MOD_ID)
mod->modfunc[modidx++] = mod_set_id;
- if (mb.modtype & CGW_MOD_LEN)
- mod->modfunc[modidx++] = mod_set_len;
+ if (mb.modtype & CGW_MOD_DLC)
+ mod->modfunc[modidx++] = mod_set_ccdlc;
if (mb.modtype & CGW_MOD_DATA)
mod->modfunc[modidx++] = mod_set_data;
skb_pull(skb, J1939_CAN_HDR);
/* fix length, set to dlc, with 8 maximum */
- skb_trim(skb, min_t(uint8_t, cf->can_dlc, 8));
+ skb_trim(skb, min_t(uint8_t, cf->len, 8));
/* set addr */
skcb = j1939_skb_to_cb(skb);
canid |= skcb->addr.da << 8;
cf->can_id = canid;
- cf->can_dlc = dlc;
+ cf->len = dlc;
return can_send(skb, 1);
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/bpf.h>
+#include <linux/btf.h>
#include <linux/btf_ids.h>
#include <linux/bpf_local_storage.h>
#include <net/bpf_sk_storage.h>
DEFINE_BPF_STORAGE_CACHE(sk_cache);
-static int omem_charge(struct sock *sk, unsigned int size)
-{
- /* same check as in sock_kmalloc() */
- if (size <= sysctl_optmem_max &&
- atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
- atomic_add(size, &sk->sk_omem_alloc);
- return 0;
- }
-
- return -ENOMEM;
-}
-
static struct bpf_local_storage_data *
-sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
+bpf_sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
{
struct bpf_local_storage *sk_storage;
struct bpf_local_storage_map *smap;
return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit);
}
-static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
+static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map)
{
struct bpf_local_storage_data *sdata;
- sdata = sk_storage_lookup(sk, map, false);
+ sdata = bpf_sk_storage_lookup(sk, map, false);
if (!sdata)
return -ENOENT;
kfree_rcu(sk_storage, rcu);
}
-static void sk_storage_map_free(struct bpf_map *map)
+static void bpf_sk_storage_map_free(struct bpf_map *map)
{
struct bpf_local_storage_map *smap;
bpf_local_storage_map_free(smap);
}
-static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr)
+static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
{
struct bpf_local_storage_map *smap;
fd = *(int *)key;
sock = sockfd_lookup(fd, &err);
if (sock) {
- sdata = sk_storage_lookup(sock->sk, map, true);
+ sdata = bpf_sk_storage_lookup(sock->sk, map, true);
sockfd_put(sock);
return sdata ? sdata->data : NULL;
}
fd = *(int *)key;
sock = sockfd_lookup(fd, &err);
if (sock) {
- err = sk_storage_delete(sock->sk, map);
+ err = bpf_sk_storage_del(sock->sk, map);
sockfd_put(sock);
return err;
}
if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE)
return (unsigned long)NULL;
- sdata = sk_storage_lookup(sk, map, true);
+ sdata = bpf_sk_storage_lookup(sk, map, true);
if (sdata)
return (unsigned long)sdata->data;
if (refcount_inc_not_zero(&sk->sk_refcnt)) {
int err;
- err = sk_storage_delete(sk, map);
+ err = bpf_sk_storage_del(sk, map);
sock_put(sk);
return err;
}
return -ENOENT;
}
-static int sk_storage_charge(struct bpf_local_storage_map *smap,
- void *owner, u32 size)
+static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
+ void *owner, u32 size)
{
- return omem_charge(owner, size);
+ struct sock *sk = (struct sock *)owner;
+
+ /* same check as in sock_kmalloc() */
+ if (size <= sysctl_optmem_max &&
+ atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+ atomic_add(size, &sk->sk_omem_alloc);
+ return 0;
+ }
+
+ return -ENOMEM;
}
-static void sk_storage_uncharge(struct bpf_local_storage_map *smap,
- void *owner, u32 size)
+static void bpf_sk_storage_uncharge(struct bpf_local_storage_map *smap,
+ void *owner, u32 size)
{
struct sock *sk = owner;
}
static struct bpf_local_storage __rcu **
-sk_storage_ptr(void *owner)
+bpf_sk_storage_ptr(void *owner)
{
struct sock *sk = owner;
const struct bpf_map_ops sk_storage_map_ops = {
.map_meta_equal = bpf_map_meta_equal,
.map_alloc_check = bpf_local_storage_map_alloc_check,
- .map_alloc = sk_storage_map_alloc,
- .map_free = sk_storage_map_free,
+ .map_alloc = bpf_sk_storage_map_alloc,
+ .map_free = bpf_sk_storage_map_free,
.map_get_next_key = notsupp_get_next_key,
.map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
.map_update_elem = bpf_fd_sk_storage_update_elem,
.map_check_btf = bpf_local_storage_map_check_btf,
.map_btf_name = "bpf_local_storage_map",
.map_btf_id = &sk_storage_map_btf_id,
- .map_local_storage_charge = sk_storage_charge,
- .map_local_storage_uncharge = sk_storage_uncharge,
- .map_owner_storage_ptr = sk_storage_ptr,
+ .map_local_storage_charge = bpf_sk_storage_charge,
+ .map_local_storage_uncharge = bpf_sk_storage_uncharge,
+ .map_owner_storage_ptr = bpf_sk_storage_ptr,
};
const struct bpf_func_proto bpf_sk_storage_get_proto = {
.arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
};
+static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog)
+{
+ const struct btf *btf_vmlinux;
+ const struct btf_type *t;
+ const char *tname;
+ u32 btf_id;
+
+ if (prog->aux->dst_prog)
+ return false;
+
+ /* Ensure the tracing program is not tracing
+ * any bpf_sk_storage*() function and also
+ * use the bpf_sk_storage_(get|delete) helper.
+ */
+ switch (prog->expected_attach_type) {
+ case BPF_TRACE_RAW_TP:
+ /* bpf_sk_storage has no trace point */
+ return true;
+ case BPF_TRACE_FENTRY:
+ case BPF_TRACE_FEXIT:
+ btf_vmlinux = bpf_get_btf_vmlinux();
+ btf_id = prog->aux->attach_btf_id;
+ t = btf_type_by_id(btf_vmlinux, btf_id);
+ tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+ return !!strncmp(tname, "bpf_sk_storage",
+ strlen("bpf_sk_storage"));
+ default:
+ return false;
+ }
+
+ return false;
+}
+
+BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk,
+ void *, value, u64, flags)
+{
+ if (!in_serving_softirq() && !in_task())
+ return (unsigned long)NULL;
+
+ return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags);
+}
+
+BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map,
+ struct sock *, sk)
+{
+ if (!in_serving_softirq() && !in_task())
+ return -EPERM;
+
+ return ____bpf_sk_storage_delete(map, sk);
+}
+
+const struct bpf_func_proto bpf_sk_storage_get_tracing_proto = {
+ .func = bpf_sk_storage_get_tracing,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+ .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg4_type = ARG_ANYTHING,
+ .allowed = bpf_sk_storage_tracing_allowed,
+};
+
+const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto = {
+ .func = bpf_sk_storage_delete_tracing,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+ .allowed = bpf_sk_storage_tracing_allowed,
+};
+
struct bpf_sk_storage_diag {
u32 nr_maps;
struct bpf_map *maps[];
EXPORT_SYMBOL(zerocopy_sg_from_iter);
/**
- * skb_copy_and_csum_datagram_iter - Copy datagram to an iovec iterator
+ * skb_copy_and_csum_datagram - Copy datagram to an iovec iterator
* and update a checksum.
* @skb: buffer to copy
* @offset: offset in the buffer to start copying from
}
EXPORT_SYMBOL(dev_getbyhwaddr_rcu);
-struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
-{
- struct net_device *dev;
-
- ASSERT_RTNL();
- for_each_netdev(net, dev)
- if (dev->type == type)
- return dev;
-
- return NULL;
-}
-EXPORT_SYMBOL(__dev_getfirstbyhwtype);
-
struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
{
struct net_device *dev, *ret = NULL;
if (skb->ip_summed == CHECKSUM_COMPLETE)
goto out_set_summed;
- if (unlikely(skb_shinfo(skb)->gso_size)) {
+ if (unlikely(skb_is_gso(skb))) {
skb_warn_bad_offload(skb);
return -EINVAL;
}
if (gso_segs > dev->gso_max_segs)
return features & ~NETIF_F_GSO_MASK;
+ if (!skb_shinfo(skb)->gso_type) {
+ skb_warn_bad_offload(skb);
+ return features & ~NETIF_F_GSO_MASK;
+ }
+
/* Support for GSO partial features requires software
* intervention before we can actually process the packets
* so we need to strip support for any partial features now
return skb;
/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
+ qdisc_skb_cb(skb)->mru = 0;
mini_qdisc_bstats_cpu_update(miniq, skb);
switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
}
qdisc_skb_cb(skb)->pkt_len = skb->len;
+ qdisc_skb_cb(skb)->mru = 0;
skb->tc_at_ingress = 1;
mini_qdisc_bstats_cpu_update(miniq, skb);
EXPORT_SYMBOL(netdev_has_upper_dev);
/**
- * netdev_has_upper_dev_all - Check if device is linked to an upper device
+ * netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device
* @dev: device
* @upper_dev: upper device to check
*
/**
- * netdev_lower_change - Dispatch event about lower device state change
+ * netdev_lower_state_changed - Dispatch event about lower device state change
* @lower_dev: device
* @lower_state_info: state to dispatch
*
return dev->netdev_ops->ndo_bpf;
default:
return NULL;
- };
+ }
}
static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev,
}
EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats);
+/**
+ * dev_get_tstats64 - ndo_get_stats64 implementation
+ * @dev: device to get statistics from
+ * @s: place to store stats
+ *
+ * Populate @s from dev->stats and dev->tstats. Can be used as
+ * ndo_get_stats64() callback.
+ */
+void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s)
+{
+ netdev_stats_to_stats64(s, &dev->stats);
+ dev_fetch_sw_netstats(s, dev->tstats);
+}
+EXPORT_SYMBOL_GPL(dev_get_tstats64);
+
struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
{
struct netdev_queue *queue = dev_ingress_queue(dev);
struct ifreq *ifr, unsigned int cmd)
{
const struct net_device_ops *ops = dev->netdev_ops;
- int err = -EOPNOTSUPP;
+ int err;
err = dsa_ndo_do_ioctl(dev, ifr, cmd);
if (err == 0 || err != -EOPNOTSUPP)
nlmsg_free(msg);
}
-void devlink_flash_update_begin_notify(struct devlink *devlink)
+static void devlink_flash_update_begin_notify(struct devlink *devlink)
{
struct devlink_flash_notify params = { 0 };
DEVLINK_CMD_FLASH_UPDATE,
¶ms);
}
-EXPORT_SYMBOL_GPL(devlink_flash_update_begin_notify);
-void devlink_flash_update_end_notify(struct devlink *devlink)
+static void devlink_flash_update_end_notify(struct devlink *devlink)
{
struct devlink_flash_notify params = { 0 };
DEVLINK_CMD_FLASH_UPDATE_END,
¶ms);
}
-EXPORT_SYMBOL_GPL(devlink_flash_update_end_notify);
void devlink_flash_update_status_notify(struct devlink *devlink,
const char *status_msg,
static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
struct genl_info *info)
{
- struct nlattr *nla_component, *nla_overwrite_mask;
+ struct nlattr *nla_component, *nla_overwrite_mask, *nla_file_name;
struct devlink_flash_update_params params = {};
struct devlink *devlink = info->user_ptr[0];
+ const char *file_name;
u32 supported_params;
+ int ret;
if (!devlink->ops->flash_update)
return -EOPNOTSUPP;
supported_params = devlink->ops->supported_flash_update_params;
- params.file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]);
-
nla_component = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT];
if (nla_component) {
if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT)) {
params.overwrite_mask = sections.value & sections.selector;
}
- return devlink->ops->flash_update(devlink, ¶ms, info->extack);
+ nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME];
+ file_name = nla_data(nla_file_name);
+ ret = request_firmware(¶ms.fw, file_name, devlink->dev);
+ if (ret) {
+ NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, "failed to locate the requested firmware file");
+ return ret;
+ }
+
+ devlink_flash_update_begin_notify(devlink);
+ ret = devlink->ops->flash_update(devlink, ¶ms, info->extack);
+ devlink_flash_update_end_notify(devlink);
+
+ release_firmware(params.fw);
+
+ return ret;
}
static const struct devlink_param devlink_param_generic[] = {
DEVLINK_TRAP(DCCP_PARSING, DROP),
DEVLINK_TRAP(GTP_PARSING, DROP),
DEVLINK_TRAP(ESP_PARSING, DROP),
+ DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP),
};
#define DEVLINK_TRAP_GROUP(_id) \
goto out;
}
- params.file_name = file_name;
+ ret = request_firmware(¶ms.fw, file_name, devlink->dev);
+ if (ret)
+ goto out;
mutex_lock(&devlink->lock);
+ devlink_flash_update_begin_notify(devlink);
ret = devlink->ops->flash_update(devlink, ¶ms, NULL);
+ devlink_flash_update_end_notify(devlink);
mutex_unlock(&devlink->lock);
+ release_firmware(params.fw);
+
out:
rtnl_lock();
dev_put(dev);
struct net_device *dev;
nlrule->iifindex = -1;
- nla_strlcpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
+ nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
dev = __dev_get_by_name(net, nlrule->iifname);
if (dev)
nlrule->iifindex = dev->ifindex;
struct net_device *dev;
nlrule->oifindex = -1;
- nla_strlcpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
+ nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
dev = __dev_get_by_name(net, nlrule->oifname);
if (dev)
nlrule->oifindex = dev->ifindex;
memset(flow_dissector, 0, sizeof(*flow_dissector));
for (i = 0; i < key_count; i++, key++) {
- /* User should make sure that every key target offset is withing
+ /* User should make sure that every key target offset is within
* boundaries of unsigned short.
*/
BUG_ON(key->offset > USHRT_MAX);
#include <linux/device.h>
#include <net/page_pool.h>
+#include <net/xdp.h>
+
#include <linux/dma-direction.h>
#include <linux/dma-mapping.h>
#include <linux/page-flags.h>
* If the page refcnt != 1, then the page will be returned to memory
* subsystem.
*/
-void page_pool_put_page(struct page_pool *pool, struct page *page,
- unsigned int dma_sync_size, bool allow_direct)
+static __always_inline struct page *
+__page_pool_put_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size, bool allow_direct)
{
/* This allocator is optimized for the XDP mode that uses
* one-frame-per-page, but have fallbacks that act like the
page_pool_dma_sync_for_device(pool, page,
dma_sync_size);
- if (allow_direct && in_serving_softirq())
- if (page_pool_recycle_in_cache(page, pool))
- return;
+ if (allow_direct && in_serving_softirq() &&
+ page_pool_recycle_in_cache(page, pool))
+ return NULL;
- if (!page_pool_recycle_in_ring(pool, page)) {
- /* Cache full, fallback to free pages */
- page_pool_return_page(pool, page);
- }
- return;
+ /* Page found as candidate for recycling */
+ return page;
}
/* Fallback/non-XDP mode: API user have elevated refcnt.
*
/* Do not replace this with page_pool_return_page() */
page_pool_release_page(pool, page);
put_page(page);
+
+ return NULL;
+}
+
+void page_pool_put_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size, bool allow_direct)
+{
+ page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct);
+ if (page && !page_pool_recycle_in_ring(pool, page)) {
+ /* Cache full, fallback to free pages */
+ page_pool_return_page(pool, page);
+ }
}
EXPORT_SYMBOL(page_pool_put_page);
+/* Caller must not use data area after call, as this function overwrites it */
+void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+ int count)
+{
+ int i, bulk_len = 0;
+
+ for (i = 0; i < count; i++) {
+ struct page *page = virt_to_head_page(data[i]);
+
+ page = __page_pool_put_page(pool, page, -1, false);
+ /* Approved for bulk recycling in ptr_ring cache */
+ if (page)
+ data[bulk_len++] = page;
+ }
+
+ if (unlikely(!bulk_len))
+ return;
+
+ /* Bulk producer into ptr_ring page_pool cache */
+ page_pool_ring_lock(pool);
+ for (i = 0; i < bulk_len; i++) {
+ if (__ptr_ring_produce(&pool->ring, data[i]))
+ break; /* ring full */
+ }
+ page_pool_ring_unlock(pool);
+
+ /* Hopefully all pages was return into ptr_ring */
+ if (likely(i == bulk_len))
+ return;
+
+ /* ptr_ring cache full, free remaining pages outside producer lock
+ * since put_page() with refcnt == 1 can be an expensive operation
+ */
+ for (; i < bulk_len; i++)
+ page_pool_return_page(pool, data[i]);
+}
+EXPORT_SYMBOL(page_pool_put_page_bulk);
+
static void page_pool_empty_ring(struct page_pool *pool)
{
struct page *page;
if (linfo[IFLA_INFO_KIND]) {
char kind[MODULE_NAME_LEN];
- nla_strlcpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
+ nla_strscpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
ops = rtnl_link_ops_get(kind);
}
if (!ifname) {
ifname = buffer;
if (ifname_attr)
- nla_strlcpy(ifname, ifname_attr, IFNAMSIZ);
+ nla_strscpy(ifname, ifname_attr, IFNAMSIZ);
else if (altifname_attr)
- nla_strlcpy(ifname, altifname_attr, ALTIFNAMSIZ);
+ nla_strscpy(ifname, altifname_attr, ALTIFNAMSIZ);
else
return NULL;
}
goto errout;
if (tb[IFLA_IFNAME])
- nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+ nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
ifname[0] = '\0';
return err;
if (tb[IFLA_IFNAME])
- nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+ nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
ifname[0] = '\0';
memset(linkinfo, 0, sizeof(linkinfo));
if (linkinfo[IFLA_INFO_KIND]) {
- nla_strlcpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
+ nla_strscpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
ops = rtnl_link_ops_get(kind);
} else {
kind[0] = '\0';
fclones->skb2.fclone = SKB_FCLONE_CLONE;
}
+
+ skb_set_kcov_handle(skb, kcov_common_handle());
+
out:
return skb;
nodata:
memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
atomic_set(&shinfo->dataref, 1);
+ skb_set_kcov_handle(skb, kcov_common_handle());
+
return skb;
}
#endif
/**
- * consume_stateless_skb - free an skbuff, assuming it is stateless
+ * __consume_stateless_skb - free an skbuff, assuming it is stateless
* @skb: buffer to free
*
* Alike consume_skb(), but this variant assumes that this is the last
return;
}
+ lockdep_assert_in_softirq();
+
if (!skb_unref(skb))
return;
goto err_free;
skb_reset_network_header(skb);
- skb_reset_transport_header(skb);
+ if (!skb_transport_header_was_set(skb))
+ skb_reset_transport_header(skb);
skb_reset_mac_len(skb);
return skb;
}
EXPORT_SYMBOL(sk_page_frag_refill);
-static void __lock_sock(struct sock *sk)
+void __lock_sock(struct sock *sk)
__releases(&sk->sk_lock.slock)
__acquires(&sk->sk_lock.slock)
{
*
* sk_lock.slock unlocked, owned = 1, BH enabled
*/
-bool lock_sock_fast(struct sock *sk)
+bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock)
{
might_sleep();
spin_lock_bh(&sk->sk_lock.slock);
* The sk_lock has mutex_lock() semantics here:
*/
mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
+ __acquire(&sk->sk_lock.slock);
local_bh_enable();
return true;
}
}
EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
+/* XDP bulk APIs introduce a defer/flush mechanism to return
+ * pages belonging to the same xdp_mem_allocator object
+ * (identified via the mem.id field) in bulk to optimize
+ * I-cache and D-cache.
+ * The bulk queue size is set to 16 to be aligned to how
+ * XDP_REDIRECT bulking works. The bulk is flushed when
+ * it is full or when mem.id changes.
+ * xdp_frame_bulk is usually stored/allocated on the function
+ * call-stack to avoid locking penalties.
+ */
+void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq)
+{
+ struct xdp_mem_allocator *xa = bq->xa;
+
+ if (unlikely(!xa || !bq->count))
+ return;
+
+ page_pool_put_page_bulk(xa->page_pool, bq->q, bq->count);
+ /* bq->xa is not cleared to save lookup, if mem.id same in next bulk */
+ bq->count = 0;
+}
+EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk);
+
+/* Must be called with rcu_read_lock held */
+void xdp_return_frame_bulk(struct xdp_frame *xdpf,
+ struct xdp_frame_bulk *bq)
+{
+ struct xdp_mem_info *mem = &xdpf->mem;
+ struct xdp_mem_allocator *xa;
+
+ if (mem->type != MEM_TYPE_PAGE_POOL) {
+ __xdp_return(xdpf->data, &xdpf->mem, false);
+ return;
+ }
+
+ xa = bq->xa;
+ if (unlikely(!xa)) {
+ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+ bq->count = 0;
+ bq->xa = xa;
+ }
+
+ if (bq->count == XDP_BULK_QUEUE_SIZE)
+ xdp_flush_frame_bulk(bq);
+
+ if (unlikely(mem->id != xa->mem.id)) {
+ xdp_flush_frame_bulk(bq);
+ bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+ }
+
+ bq->q[bq->count++] = xdpf->data;
+}
+EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
+
void xdp_return_buff(struct xdp_buff *xdp)
{
__xdp_return(xdp->data, &xdp->rxq->mem, true);
/**
* dcb_getapp - retrieve the DCBX application user priority
+ * @dev: network interface
+ * @app: application to get user priority of
*
* On success returns a non-zero 802.1p user priority bitmap
* otherwise returns 0 as the invalid user priority bitmap to
/**
* dcb_setapp - add CEE dcb application data to app list
+ * @dev: network interface
+ * @new: application data to add
*
* Priority 0 is an invalid priority in CEE spec. This routine
* removes applications from the app list if the priority is
/**
* dcb_ieee_getapp_mask - retrieve the IEEE DCB application priority
+ * @dev: network interface
+ * @app: where to store the retrieve application data
*
* Helper routine which on success returns a non-zero 802.1Qaz user
* priority bitmap otherwise returns 0 to indicate the dcb_app was
/**
* dcb_ieee_setapp - add IEEE dcb application data to app list
+ * @dev: network interface
+ * @new: application data to add
*
* This adds Application data to the list. Multiple application
* entries may exists for the same selector and protocol as long
/**
* dcb_ieee_delapp - delete IEEE dcb application data from list
+ * @dev: network interface
+ * @del: application data to delete
*
* This removes a matching APP data from the APP list
*/
}
EXPORT_SYMBOL(dcb_ieee_delapp);
-/**
+/*
* dcb_ieee_getapp_prio_dscp_mask_map - For a given device, find mapping from
* priorities to the DSCP values assigned to that priority. Initialize p_map
* such that each map element holds a bit mask of DSCP values configured for
}
EXPORT_SYMBOL(dcb_ieee_getapp_prio_dscp_mask_map);
-/**
+/*
* dcb_ieee_getapp_dscp_prio_mask_map - For a given device, find mapping from
* DSCP values to the priorities assigned to that DSCP value. Initialize p_map
* such that each map element holds a bit mask of priorities configured for a
}
EXPORT_SYMBOL(dcb_ieee_getapp_dscp_prio_mask_map);
-/**
+/*
* Per 802.1Q-2014, the selector value of 1 is used for matching on Ethernet
* type, with valid PID values >= 1536. A special meaning is then assigned to
* protocol value of 0: "default priority. For use when priority is not
/**
* dccp_ackvec_input - Register incoming packet in the buffer
+ * @av: Ack Vector to register packet to
+ * @skb: Packet to register
*/
void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb)
{
/**
* dccp_ackvec_clear_state - Perform house-keeping / garbage-collection
+ * @av: Ack Vector record to clean
+ * @ackno: last Ack Vector which has been acknowledged
+ *
* This routine is called when the peer acknowledges the receipt of Ack Vectors
* up to and including @ackno. While based on section A.3 of RFC 4340, here
* are additional precautions to prevent corrupted buffer state. In particular,
return err;
}
-static struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...)
+static __printf(3, 4) struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...)
{
struct kmem_cache *slab;
va_list args;
/**
* ccid2_update_used_window - Track how much of cwnd is actually used
+ * @hc: socket to update window
+ * @new_wnd: new window values to add into the filter
+ *
* This is done in addition to CWV. The sender needs to have an idea of how many
* packets may be in flight, to set the local Sequence Window value accordingly
* (RFC 4340, 7.5.2). The CWV mechanism is exploited to keep track of the
/**
* ccid2_rtt_estimator - Sample RTT and compute RTO using RFC2988 algorithm
+ * @sk: socket to perform estimator on
+ *
* This code is almost identical with TCP's tcp_rtt_estimator(), since
* - it has a higher sampling frequency (recommended by RFC 1323),
* - the RTO does not collapse into RTT due to RTTVAR going towards zero,
/**
* ccid3_update_send_interval - Calculate new t_ipi = s / X_inst
+ * @hc: socket to have the send interval updated
+ *
* This respects the granularity of X_inst (64 * bytes/second).
*/
static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc)
/**
* ccid3_hc_tx_update_x - Update allowed sending rate X
+ * @sk: socket to be updated
* @stamp: most recent time if available - can be left NULL.
*
* This function tracks draft rfc3448bis, check there for latest details.
/**
* ccid3_hc_tx_update_s - Track the mean packet size `s'
+ * @hc: socket to be updated
* @len: DCCP packet payload size in bytes
*
* cf. RFC 4342, 5.3 and RFC 3448, 4.1
/**
* ccid3_hc_tx_send_packet - Delay-based dequeueing of TX packets
+ * @sk: socket to send packet from
* @skb: next packet candidate to send on @sk
*
* This function uses the convention of ccid_packet_dequeue_eval() and
/**
* ccid3_first_li - Implements [RFC 5348, 6.3.1]
+ * @sk: socket to calculate loss interval for
*
* Determine the length of the first loss interval via inverse lookup.
* Assume that X_recv can be computed by the throughput equation
/**
* tfrc_lh_update_i_mean - Update the `open' loss interval I_0
+ * @lh: histogram to update
+ * @skb: received socket triggering loss interval update
+ *
* For recomputing p: returns `true' if p > p_prev <=> 1/p < 1/p_prev
*/
u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *skb)
/**
* tfrc_rx_hist_sample_rtt - Sample RTT from timestamp / CCVal
+ * @h: receive histogram
+ * @skb: packet containing timestamp.
+ *
* Based on ideas presented in RFC 4342, 8.1. Returns 0 if it was not able
* to compute a sample with given data - calling function should check this.
*/
/**
* dccp_feat_server_ccid_dependencies - Resolve CCID-dependent features
+ * @dreq: server socket to resolve
+ *
* It is the server which resolves the dependencies once the CCID has been
* fully negotiated. If no CCID has been negotiated, it uses the default CCID.
*/
/**
* dccp_feat_prefer - Move preferred entry to the start of array
+ * @preferred_value: entry to move to start of array
+ * @array: array of preferred entries
+ * @array_len: size of the array
+ *
* Reorder the @array_len elements in @array so that @preferred_value comes
* first. Returns >0 to indicate that @preferred_value does occur in @array.
*/
/**
* dccp_determine_ccmps - Find out about CCID-specific packet-size limits
+ * @dp: socket to find packet size limits of
+ *
* We only consider the HC-sender CCID for setting the CCMPS (RFC 4340, 14.),
* since the RX CCID is restricted to feedback packets (Acks), which are small
* in comparison with the data traffic. A value of 0 means "no current CCMPS".
/**
* dccp_xmit_packet - Send data packet under control of CCID
+ * @sk: socket to send data packet on
+ *
* Transmits next-queued payload and informs CCID to account for the packet.
*/
static void dccp_xmit_packet(struct sock *sk)
/**
* dccp_flush_write_queue - Drain queue at end of connection
+ * @sk: socket to be drained
+ * @time_budget: time allowed to drain the queue
+ *
* Since dccp_sendmsg queues packets without waiting for them to be sent, it may
* happen that the TX queue is not empty at the end of a connection. We give the
* HC-sender CCID a grace period of up to @time_budget jiffies. If this function
/**
* dccp_retransmit_skb - Retransmit Request, Close, or CloseReq packets
+ * @sk: socket to perform retransmit on
+ *
* There are only four retransmittable packet types in DCCP:
* - Request in client-REQUEST state (sec. 8.1.1),
* - CloseReq in server-CLOSEREQ state (sec. 8.3),
* @push: add a new @skb to the write queue
* @full: indicates that no more packets will be admitted
* @top: peeks at whatever the queueing policy defines as its `top'
+ * @params: parameter passed to policy operation
*/
-static struct dccp_qpolicy_operations {
+struct dccp_qpolicy_operations {
void (*push) (struct sock *sk, struct sk_buff *skb);
bool (*full) (struct sock *sk);
struct sk_buff* (*top) (struct sock *sk);
__be32 params;
+};
-} qpol_table[DCCPQ_POLICY_MAX] = {
+static struct dccp_qpolicy_operations qpol_table[DCCPQ_POLICY_MAX] = {
[DCCPQ_POLICY_SIMPLE] = {
.push = qpolicy_simple_push,
.full = qpolicy_simple_full,
/**
* dccp_write_xmitlet - Workhorse for CCID packet dequeueing interface
- * @data: Socket to act on
+ * @t: pointer to the tasklet associated with this handler
*
* See the comments above %ccid_dequeueing_decision for supported modes.
*/
-static void dccp_write_xmitlet(unsigned long data)
+static void dccp_write_xmitlet(struct tasklet_struct *t)
{
- struct sock *sk = (struct sock *)data;
+ struct dccp_sock *dp = from_tasklet(dp, t, dccps_xmitlet);
+ struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
static void dccp_write_xmit_timer(struct timer_list *t)
{
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);
+ dccp_write_xmitlet(&dp->dccps_xmitlet);
}
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);
+ tasklet_setup(&dp->dccps_xmitlet, dccp_write_xmitlet);
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);
ifa->ifa_dev = dn_db;
if (tb[IFA_LABEL])
- nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
+ nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
Broadcom switches which places the tag before the Ethernet header
(prepended).
+config NET_DSA_TAG_HELLCREEK
+ tristate "Tag driver for Hirschmann Hellcreek TSN switches"
+ help
+ Say Y or M if you want to enable support for tagging frames
+ for the Hirschmann Hellcreek TSN switches.
+
config NET_DSA_TAG_GSWIP
tristate "Tag driver for Lantiq / Intel GSWIP switches"
help
Say Y or M if you want to enable support for tagging frames for the
Lantiq / Intel GSWIP switches.
+config NET_DSA_TAG_DSA_COMMON
+ tristate
+
config NET_DSA_TAG_DSA
tristate "Tag driver for Marvell switches using DSA headers"
+ select NET_DSA_TAG_DSA_COMMON
help
Say Y or M if you want to enable support for tagging frames for the
Marvell switches which use DSA headers.
config NET_DSA_TAG_EDSA
tristate "Tag driver for Marvell switches using EtherType DSA headers"
+ select NET_DSA_TAG_DSA_COMMON
help
Say Y or M if you want to enable support for tagging frames for the
Marvell switches which use EtherType DSA headers.
obj-$(CONFIG_NET_DSA_TAG_8021Q) += tag_8021q.o
obj-$(CONFIG_NET_DSA_TAG_AR9331) += tag_ar9331.o
obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o
-obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o
-obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
+obj-$(CONFIG_NET_DSA_TAG_DSA_COMMON) += tag_dsa.o
obj-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o
+obj-$(CONFIG_NET_DSA_TAG_HELLCREEK) += tag_hellcreek.o
obj-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o
obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o
obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o
{
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(!cpu_dp)) {
skb = nskb;
}
- s = this_cpu_ptr(p->stats64);
- u64_stats_update_begin(&s->syncp);
- s->rx_packets++;
- s->rx_bytes += skb->len;
- u64_stats_update_end(&s->syncp);
+ dev_sw_netstats_rx_add(skb->dev, skb->len);
if (dsa_skb_defer_rx_timestamp(p, skb))
return 0;
struct sk_buff * (*xmit)(struct sk_buff *skb,
struct net_device *dev);
- struct pcpu_sw_netstats __percpu *stats64;
-
struct gro_cells gcells;
/* DSA port data, such as switch, port index, etc. */
if (!clone)
return;
- DSA_SKB_CB(skb)->clone = clone;
-
- if (ds->ops->port_txtstamp(ds, p->dp->index, clone, type))
+ if (ds->ops->port_txtstamp(ds, p->dp->index, clone, type)) {
+ DSA_SKB_CB(skb)->clone = clone;
return;
+ }
kfree_skb(clone);
}
}
EXPORT_SYMBOL_GPL(dsa_enqueue_skb);
+static int dsa_realloc_skb(struct sk_buff *skb, struct net_device *dev)
+{
+ int needed_headroom = dev->needed_headroom;
+ int needed_tailroom = dev->needed_tailroom;
+
+ /* For tail taggers, we need to pad short frames ourselves, to ensure
+ * that the tail tag does not fail at its role of being at the end of
+ * the packet, once the master interface pads the frame. Account for
+ * that pad length here, and pad later.
+ */
+ if (unlikely(needed_tailroom && skb->len < ETH_ZLEN))
+ needed_tailroom += ETH_ZLEN - skb->len;
+ /* skb_headroom() returns unsigned int... */
+ needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0);
+ needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0);
+
+ if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb)))
+ /* No reallocation needed, yay! */
+ return 0;
+
+ return pskb_expand_head(skb, needed_headroom, needed_tailroom,
+ GFP_ATOMIC);
+}
+
static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dsa_slave_priv *p = netdev_priv(dev);
- struct pcpu_sw_netstats *s;
struct sk_buff *nskb;
- s = this_cpu_ptr(p->stats64);
- u64_stats_update_begin(&s->syncp);
- s->tx_packets++;
- s->tx_bytes += skb->len;
- u64_stats_update_end(&s->syncp);
+ dev_sw_netstats_tx_add(dev, 1, skb->len);
DSA_SKB_CB(skb)->clone = NULL;
*/
dsa_skb_tx_timestamp(p, skb);
+ if (dsa_realloc_skb(skb, dev)) {
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+ }
+
+ /* needed_tailroom should still be 'warm' in the cache line from
+ * dsa_realloc_skb(), which has also ensured that padding is safe.
+ */
+ if (dev->needed_tailroom)
+ eth_skb_pad(skb);
+
/* Transmit function may have to reallocate the original SKB,
* in which case it must have freed it. Only free it here on error.
*/
uint64_t *data)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- struct dsa_slave_priv *p = netdev_priv(dev);
struct dsa_switch *ds = dp->ds;
struct pcpu_sw_netstats *s;
unsigned int start;
for_each_possible_cpu(i) {
u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
- s = per_cpu_ptr(p->stats64, i);
+ s = per_cpu_ptr(dev->tstats, i);
do {
start = u64_stats_fetch_begin_irq(&s->syncp);
tx_packets = s->tx_packets;
return ds->ops->port_setup_tc(ds, dp->index, type, type_data);
}
-static void dsa_slave_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *stats)
-{
- struct dsa_slave_priv *p = netdev_priv(dev);
-
- netdev_stats_to_stats64(stats, &dev->stats);
- dev_fetch_sw_netstats(stats, p->stats64);
-}
-
static int dsa_slave_get_rxnfc(struct net_device *dev,
struct ethtool_rxnfc *nfc, u32 *rule_locs)
{
#endif
.ndo_get_phys_port_name = dsa_slave_get_phys_port_name,
.ndo_setup_tc = dsa_slave_setup_tc,
- .ndo_get_stats64 = dsa_slave_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_port_parent_id = dsa_slave_get_port_parent_id,
.ndo_vlan_rx_add_vid = dsa_slave_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = dsa_slave_vlan_rx_kill_vid,
slave_dev->netdev_ops = &dsa_slave_netdev_ops;
if (ds->ops->port_max_mtu)
slave_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index);
+ if (cpu_dp->tag_ops->tail_tag)
+ slave_dev->needed_tailroom = cpu_dp->tag_ops->overhead;
+ else
+ slave_dev->needed_headroom = cpu_dp->tag_ops->overhead;
+ /* Try to save one extra realloc later in the TX path (in the master)
+ * by also inheriting the master's needed headroom and tailroom.
+ * The 8021q driver also does this.
+ */
+ slave_dev->needed_headroom += master->needed_headroom;
+ slave_dev->needed_tailroom += master->needed_tailroom;
SET_NETDEV_DEVTYPE(slave_dev, &dsa_type);
netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one,
slave_dev->vlan_features = master->vlan_features;
p = netdev_priv(slave_dev);
- p->stats64 = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
- if (!p->stats64) {
+ slave_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ if (!slave_dev->tstats) {
free_netdev(slave_dev);
return -ENOMEM;
}
out_gcells:
gro_cells_destroy(&p->gcells);
out_free:
- free_percpu(p->stats64);
+ free_percpu(slave_dev->tstats);
free_netdev(slave_dev);
port->slave = NULL;
return ret;
dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER);
phylink_destroy(dp->pl);
gro_cells_destroy(&p->gcells);
- free_percpu(p->stats64);
+ free_percpu(slave_dev->tstats);
free_netdev(slave_dev);
}
switch (event) {
case NETDEV_PRECHANGEUPPER: {
struct netdev_notifier_changeupper_info *info = ptr;
+ struct dsa_switch *ds;
+ struct dsa_port *dp;
+ int err;
if (!dsa_slave_dev_check(dev))
return dsa_prevent_bridging_8021q_upper(dev, ptr);
+ dp = dsa_slave_to_port(dev);
+ ds = dp->ds;
+
+ if (ds->ops->port_prechangeupper) {
+ err = ds->ops->port_prechangeupper(ds, dp->index, info);
+ if (err)
+ return notifier_from_errno(err);
+ }
+
if (is_vlan_dev(info->upper_dev))
return dsa_slave_check_8021q_upper(dev, ptr);
break;
__le16 *phdr;
u16 hdr;
- if (skb_cow_head(skb, AR9331_HDR_LEN) < 0)
- return NULL;
-
phdr = skb_push(skb, AR9331_HDR_LEN);
hdr = FIELD_PREP(AR9331_HDR_VERSION_MASK, AR9331_HDR_VERSION);
u16 queue = skb_get_queue_mapping(skb);
u8 *brcm_tag;
- if (skb_cow_head(skb, BRCM_TAG_LEN) < 0)
- return NULL;
-
/* The Ethernet switch we are interfaced with needs packets to be at
* least 64 bytes (including FCS) otherwise they will be discarded when
* they enter the switch port logic. When Broadcom tags are enabled, we
// SPDX-License-Identifier: GPL-2.0+
/*
- * net/dsa/tag_dsa.c - (Non-ethertype) DSA tagging
+ * Regular and Ethertype DSA tagging
* Copyright (c) 2008-2009 Marvell Semiconductor
+ *
+ * Regular DSA
+ * -----------
+
+ * For untagged (in 802.1Q terms) packets, the switch will splice in
+ * the tag between the SA and the ethertype of the original
+ * packet. Tagged frames will instead have their outermost .1Q tag
+ * converted to a DSA tag. It expects the same layout when receiving
+ * packets from the CPU.
+ *
+ * Example:
+ *
+ * .----.----.----.---------
+ * Pu: | DA | SA | ET | Payload ...
+ * '----'----'----'---------
+ * 6 6 2 N
+ * .----.----.--------.-----.----.---------
+ * Pt: | DA | SA | 0x8100 | TCI | ET | Payload ...
+ * '----'----'--------'-----'----'---------
+ * 6 6 2 2 2 N
+ * .----.----.-----.----.---------
+ * Pd: | DA | SA | DSA | ET | Payload ...
+ * '----'----'-----'----'---------
+ * 6 6 4 2 N
+ *
+ * No matter if a packet is received untagged (Pu) or tagged (Pt),
+ * they will both have the same layout (Pd) when they are sent to the
+ * CPU. This is done by ignoring 802.3, replacing the ethertype field
+ * with more metadata, among which is a bit to signal if the original
+ * packet was tagged or not.
+ *
+ * Ethertype DSA
+ * -------------
+ * Uses the exact same tag format as regular DSA, but also includes a
+ * proper ethertype field (which the mv88e6xxx driver sets to
+ * ETH_P_EDSA/0xdada) followed by two zero bytes:
+ *
+ * .----.----.--------.--------.-----.----.---------
+ * | DA | SA | 0xdada | 0x0000 | DSA | ET | Payload ...
+ * '----'----'--------'--------'-----'----'---------
+ * 6 6 2 2 4 2 N
*/
#include <linux/etherdevice.h>
#define DSA_HLEN 4
-static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
+/**
+ * enum dsa_cmd - DSA Command
+ * @DSA_CMD_TO_CPU: Set on packets that were trapped or mirrored to
+ * the CPU port. This is needed to implement control protocols,
+ * e.g. STP and LLDP, that must not allow those control packets to
+ * be switched according to the normal rules.
+ * @DSA_CMD_FROM_CPU: Used by the CPU to send a packet to a specific
+ * port, ignoring all the barriers that the switch normally
+ * enforces (VLANs, STP port states etc.). No source address
+ * learning takes place. "sudo send packet"
+ * @DSA_CMD_TO_SNIFFER: Set on the copies of packets that matched some
+ * user configured ingress or egress monitor criteria. These are
+ * forwarded by the switch tree to the user configured ingress or
+ * egress monitor port, which can be set to the CPU port or a
+ * regular port. If the destination is a regular port, the tag
+ * will be removed before egressing the port. If the destination
+ * is the CPU port, the tag will not be removed.
+ * @DSA_CMD_FORWARD: This tag is used on all bulk traffic passing
+ * through the switch tree, including the flows that are directed
+ * towards the CPU. Its device/port tuple encodes the original
+ * source port on which the packet ingressed. It can also be used
+ * on transmit by the CPU to defer the forwarding decision to the
+ * hardware, based on the current config of PVT/VTU/ATU
+ * etc. Source address learning takes places if enabled on the
+ * receiving DSA/CPU port.
+ */
+enum dsa_cmd {
+ DSA_CMD_TO_CPU = 0,
+ DSA_CMD_FROM_CPU = 1,
+ DSA_CMD_TO_SNIFFER = 2,
+ DSA_CMD_FORWARD = 3
+};
+
+/**
+ * enum dsa_code - TO_CPU Code
+ *
+ * @DSA_CODE_MGMT_TRAP: DA was classified as a management
+ * address. Typical examples include STP BPDUs and LLDP.
+ * @DSA_CODE_FRAME2REG: Response to a "remote management" request.
+ * @DSA_CODE_IGMP_MLD_TRAP: IGMP/MLD signaling.
+ * @DSA_CODE_POLICY_TRAP: Frame matched some policy configuration on
+ * the device. Typical examples are matching on DA/SA/VID and DHCP
+ * snooping.
+ * @DSA_CODE_ARP_MIRROR: The name says it all really.
+ * @DSA_CODE_POLICY_MIRROR: Same as @DSA_CODE_POLICY_TRAP, but the
+ * particular policy was set to trigger a mirror instead of a
+ * trap.
+ * @DSA_CODE_RESERVED_6: Unused on all devices up to at least 6393X.
+ * @DSA_CODE_RESERVED_7: Unused on all devices up to at least 6393X.
+ *
+ * A 3-bit code is used to relay why a particular frame was sent to
+ * the CPU. We only use this to determine if the packet was mirrored
+ * or trapped, i.e. whether the packet has been forwarded by hardware
+ * or not.
+ *
+ * This is the superset of all possible codes. Any particular device
+ * may only implement a subset.
+ */
+enum dsa_code {
+ DSA_CODE_MGMT_TRAP = 0,
+ DSA_CODE_FRAME2REG = 1,
+ DSA_CODE_IGMP_MLD_TRAP = 2,
+ DSA_CODE_POLICY_TRAP = 3,
+ DSA_CODE_ARP_MIRROR = 4,
+ DSA_CODE_POLICY_MIRROR = 5,
+ DSA_CODE_RESERVED_6 = 6,
+ DSA_CODE_RESERVED_7 = 7
+};
+
+static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev,
+ u8 extra)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
u8 *dsa_header;
- /*
- * Convert the outermost 802.1q tag to a DSA tag for tagged
- * packets, or insert a DSA tag between the addresses and
- * the ethertype field for untagged packets.
- */
if (skb->protocol == htons(ETH_P_8021Q)) {
- if (skb_cow_head(skb, 0) < 0)
- return NULL;
+ if (extra) {
+ skb_push(skb, extra);
+ memmove(skb->data, skb->data + extra, 2 * ETH_ALEN);
+ }
- /*
- * Construct tagged FROM_CPU DSA tag from 802.1q tag.
- */
- dsa_header = skb->data + 2 * ETH_ALEN;
- dsa_header[0] = 0x60 | dp->ds->index;
+ /* Construct tagged FROM_CPU DSA tag from 802.1Q tag. */
+ dsa_header = skb->data + 2 * ETH_ALEN + extra;
+ dsa_header[0] = (DSA_CMD_FROM_CPU << 6) | 0x20 | dp->ds->index;
dsa_header[1] = dp->index << 3;
- /*
- * Move CFI field from byte 2 to byte 1.
- */
+ /* Move CFI field from byte 2 to byte 1. */
if (dsa_header[2] & 0x10) {
dsa_header[1] |= 0x01;
dsa_header[2] &= ~0x10;
}
} else {
- if (skb_cow_head(skb, DSA_HLEN) < 0)
- return NULL;
- skb_push(skb, DSA_HLEN);
+ skb_push(skb, DSA_HLEN + extra);
+ memmove(skb->data, skb->data + DSA_HLEN + extra, 2 * ETH_ALEN);
- memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN);
-
- /*
- * Construct untagged FROM_CPU DSA tag.
- */
- dsa_header = skb->data + 2 * ETH_ALEN;
- dsa_header[0] = 0x40 | dp->ds->index;
+ /* Construct untagged FROM_CPU DSA tag. */
+ dsa_header = skb->data + 2 * ETH_ALEN + extra;
+ dsa_header[0] = (DSA_CMD_FROM_CPU << 6) | dp->ds->index;
dsa_header[1] = dp->index << 3;
dsa_header[2] = 0x00;
dsa_header[3] = 0x00;
return skb;
}
-static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *pt)
+static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev,
+ u8 extra)
{
+ int source_device, source_port;
+ enum dsa_code code;
+ enum dsa_cmd cmd;
u8 *dsa_header;
- int source_device;
- int source_port;
- if (unlikely(!pskb_may_pull(skb, DSA_HLEN)))
- return NULL;
-
- /*
- * The ethertype field is part of the DSA header.
- */
+ /* The ethertype field is part of the DSA header. */
dsa_header = skb->data - 2;
- /*
- * Check that frame type is either TO_CPU or FORWARD.
- */
- if ((dsa_header[0] & 0xc0) != 0x00 && (dsa_header[0] & 0xc0) != 0xc0)
+ cmd = dsa_header[0] >> 6;
+ switch (cmd) {
+ case DSA_CMD_FORWARD:
+ skb->offload_fwd_mark = 1;
+ break;
+
+ case DSA_CMD_TO_CPU:
+ code = (dsa_header[1] & 0x6) | ((dsa_header[2] >> 4) & 1);
+
+ switch (code) {
+ case DSA_CODE_FRAME2REG:
+ /* Remote management is not implemented yet,
+ * drop.
+ */
+ return NULL;
+ case DSA_CODE_ARP_MIRROR:
+ case DSA_CODE_POLICY_MIRROR:
+ /* Mark mirrored packets to notify any upper
+ * device (like a bridge) that forwarding has
+ * already been done by hardware.
+ */
+ skb->offload_fwd_mark = 1;
+ break;
+ case DSA_CODE_MGMT_TRAP:
+ case DSA_CODE_IGMP_MLD_TRAP:
+ case DSA_CODE_POLICY_TRAP:
+ /* Traps have, by definition, not been
+ * forwarded by hardware, so don't mark them.
+ */
+ break;
+ default:
+ /* Reserved code, this could be anything. Drop
+ * seems like the safest option.
+ */
+ return NULL;
+ }
+
+ break;
+
+ default:
return NULL;
+ }
- /*
- * Determine source device and port.
- */
source_device = dsa_header[0] & 0x1f;
source_port = (dsa_header[1] >> 3) & 0x1f;
if (!skb->dev)
return NULL;
- /*
- * Convert the DSA header to an 802.1q header if the 'tagged'
- * bit in the DSA header is set. If the 'tagged' bit is clear,
- * delete the DSA header entirely.
+ /* If the 'tagged' bit is set; convert the DSA tag to a 802.1Q
+ * tag, and delete the ethertype (extra) if applicable. If the
+ * 'tagged' bit is cleared; delete the DSA tag, and ethertype
+ * if applicable.
*/
if (dsa_header[0] & 0x20) {
u8 new_header[4];
- /*
- * Insert 802.1q ethertype and copy the VLAN-related
+ /* Insert 802.1Q ethertype and copy the VLAN-related
* fields, but clear the bit that will hold CFI (since
* DSA uses that bit location for another purpose).
*/
new_header[2] = dsa_header[2] & ~0x10;
new_header[3] = dsa_header[3];
- /*
- * Move CFI bit from its place in the DSA header to
- * its 802.1q-designated place.
+ /* Move CFI bit from its place in the DSA header to
+ * its 802.1Q-designated place.
*/
if (dsa_header[1] & 0x01)
new_header[2] |= 0x10;
- /*
- * Update packet checksum if skb is CHECKSUM_COMPLETE.
- */
+ /* Update packet checksum if skb is CHECKSUM_COMPLETE. */
if (skb->ip_summed == CHECKSUM_COMPLETE) {
__wsum c = skb->csum;
c = csum_add(c, csum_partial(new_header + 2, 2, 0));
}
memcpy(dsa_header, new_header, DSA_HLEN);
+
+ if (extra)
+ memmove(skb->data - ETH_HLEN,
+ skb->data - ETH_HLEN - extra,
+ 2 * ETH_ALEN);
} else {
- /*
- * Remove DSA tag and update checksum.
- */
skb_pull_rcsum(skb, DSA_HLEN);
memmove(skb->data - ETH_HLEN,
- skb->data - ETH_HLEN - DSA_HLEN,
+ skb->data - ETH_HLEN - DSA_HLEN - extra,
2 * ETH_ALEN);
}
- skb->offload_fwd_mark = 1;
-
return skb;
}
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_DSA)
+
+static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ return dsa_xmit_ll(skb, dev, 0);
+}
+
+static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt)
+{
+ if (unlikely(!pskb_may_pull(skb, DSA_HLEN)))
+ return NULL;
+
+ return dsa_rcv_ll(skb, dev, 0);
+}
+
static const struct dsa_device_ops dsa_netdev_ops = {
- .name = "dsa",
- .proto = DSA_TAG_PROTO_DSA,
- .xmit = dsa_xmit,
- .rcv = dsa_rcv,
+ .name = "dsa",
+ .proto = DSA_TAG_PROTO_DSA,
+ .xmit = dsa_xmit,
+ .rcv = dsa_rcv,
.overhead = DSA_HLEN,
};
-MODULE_LICENSE("GPL");
+DSA_TAG_DRIVER(dsa_netdev_ops);
MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_DSA);
+#endif /* CONFIG_NET_DSA_TAG_DSA */
+
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_EDSA)
+
+#define EDSA_HLEN 8
+
+static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ u8 *edsa_header;
-module_dsa_tag_driver(dsa_netdev_ops);
+ skb = dsa_xmit_ll(skb, dev, EDSA_HLEN - DSA_HLEN);
+ if (!skb)
+ return NULL;
+
+ edsa_header = skb->data + 2 * ETH_ALEN;
+ edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff;
+ edsa_header[1] = ETH_P_EDSA & 0xff;
+ edsa_header[2] = 0x00;
+ edsa_header[3] = 0x00;
+ return skb;
+}
+
+static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt)
+{
+ if (unlikely(!pskb_may_pull(skb, EDSA_HLEN)))
+ return NULL;
+
+ skb_pull_rcsum(skb, EDSA_HLEN - DSA_HLEN);
+
+ return dsa_rcv_ll(skb, dev, EDSA_HLEN - DSA_HLEN);
+}
+
+static const struct dsa_device_ops edsa_netdev_ops = {
+ .name = "edsa",
+ .proto = DSA_TAG_PROTO_EDSA,
+ .xmit = edsa_xmit,
+ .rcv = edsa_rcv,
+ .overhead = EDSA_HLEN,
+};
+
+DSA_TAG_DRIVER(edsa_netdev_ops);
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA);
+#endif /* CONFIG_NET_DSA_TAG_EDSA */
+
+static struct dsa_tag_driver *dsa_tag_drivers[] = {
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_DSA)
+ &DSA_TAG_DRIVER_NAME(dsa_netdev_ops),
+#endif
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_EDSA)
+ &DSA_TAG_DRIVER_NAME(edsa_netdev_ops),
+#endif
+};
+
+module_dsa_tag_drivers(dsa_tag_drivers);
+
+MODULE_LICENSE("GPL");
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * net/dsa/tag_edsa.c - Ethertype DSA tagging
- * Copyright (c) 2008-2009 Marvell Semiconductor
- */
-
-#include <linux/etherdevice.h>
-#include <linux/list.h>
-#include <linux/slab.h>
-
-#include "dsa_priv.h"
-
-#define DSA_HLEN 4
-#define EDSA_HLEN 8
-
-#define FRAME_TYPE_TO_CPU 0x00
-#define FRAME_TYPE_FORWARD 0x03
-
-#define TO_CPU_CODE_MGMT_TRAP 0x00
-#define TO_CPU_CODE_FRAME2REG 0x01
-#define TO_CPU_CODE_IGMP_MLD_TRAP 0x02
-#define TO_CPU_CODE_POLICY_TRAP 0x03
-#define TO_CPU_CODE_ARP_MIRROR 0x04
-#define TO_CPU_CODE_POLICY_MIRROR 0x05
-
-static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
-{
- struct dsa_port *dp = dsa_slave_to_port(dev);
- u8 *edsa_header;
-
- /*
- * Convert the outermost 802.1q tag to a DSA tag and prepend
- * a DSA ethertype field is the packet is tagged, or insert
- * a DSA ethertype plus DSA tag between the addresses and the
- * current ethertype field if the packet is untagged.
- */
- if (skb->protocol == htons(ETH_P_8021Q)) {
- if (skb_cow_head(skb, DSA_HLEN) < 0)
- return NULL;
- skb_push(skb, DSA_HLEN);
-
- memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN);
-
- /*
- * Construct tagged FROM_CPU DSA tag from 802.1q tag.
- */
- edsa_header = skb->data + 2 * ETH_ALEN;
- edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff;
- edsa_header[1] = ETH_P_EDSA & 0xff;
- edsa_header[2] = 0x00;
- edsa_header[3] = 0x00;
- edsa_header[4] = 0x60 | dp->ds->index;
- edsa_header[5] = dp->index << 3;
-
- /*
- * Move CFI field from byte 6 to byte 5.
- */
- if (edsa_header[6] & 0x10) {
- edsa_header[5] |= 0x01;
- edsa_header[6] &= ~0x10;
- }
- } else {
- if (skb_cow_head(skb, EDSA_HLEN) < 0)
- return NULL;
- skb_push(skb, EDSA_HLEN);
-
- memmove(skb->data, skb->data + EDSA_HLEN, 2 * ETH_ALEN);
-
- /*
- * Construct untagged FROM_CPU DSA tag.
- */
- edsa_header = skb->data + 2 * ETH_ALEN;
- edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff;
- edsa_header[1] = ETH_P_EDSA & 0xff;
- edsa_header[2] = 0x00;
- edsa_header[3] = 0x00;
- edsa_header[4] = 0x40 | dp->ds->index;
- edsa_header[5] = dp->index << 3;
- edsa_header[6] = 0x00;
- edsa_header[7] = 0x00;
- }
-
- return skb;
-}
-
-static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *pt)
-{
- u8 *edsa_header;
- int frame_type;
- int code;
- int source_device;
- int source_port;
-
- if (unlikely(!pskb_may_pull(skb, EDSA_HLEN)))
- return NULL;
-
- /*
- * Skip the two null bytes after the ethertype.
- */
- edsa_header = skb->data + 2;
-
- /*
- * Check that frame type is either TO_CPU or FORWARD.
- */
- frame_type = edsa_header[0] >> 6;
-
- switch (frame_type) {
- case FRAME_TYPE_TO_CPU:
- code = (edsa_header[1] & 0x6) | ((edsa_header[2] >> 4) & 1);
-
- /*
- * Mark the frame to never egress on any port of the same switch
- * unless it's a trapped IGMP/MLD packet, in which case the
- * bridge might want to forward it.
- */
- if (code != TO_CPU_CODE_IGMP_MLD_TRAP)
- skb->offload_fwd_mark = 1;
-
- break;
-
- case FRAME_TYPE_FORWARD:
- skb->offload_fwd_mark = 1;
- break;
-
- default:
- return NULL;
- }
-
- /*
- * Determine source device and port.
- */
- source_device = edsa_header[0] & 0x1f;
- source_port = (edsa_header[1] >> 3) & 0x1f;
-
- skb->dev = dsa_master_find_slave(dev, source_device, source_port);
- if (!skb->dev)
- return NULL;
-
- /*
- * If the 'tagged' bit is set, convert the DSA tag to a 802.1q
- * tag and delete the ethertype part. If the 'tagged' bit is
- * clear, delete the ethertype and the DSA tag parts.
- */
- if (edsa_header[0] & 0x20) {
- u8 new_header[4];
-
- /*
- * Insert 802.1q ethertype and copy the VLAN-related
- * fields, but clear the bit that will hold CFI (since
- * DSA uses that bit location for another purpose).
- */
- new_header[0] = (ETH_P_8021Q >> 8) & 0xff;
- new_header[1] = ETH_P_8021Q & 0xff;
- new_header[2] = edsa_header[2] & ~0x10;
- new_header[3] = edsa_header[3];
-
- /*
- * Move CFI bit from its place in the DSA header to
- * its 802.1q-designated place.
- */
- if (edsa_header[1] & 0x01)
- new_header[2] |= 0x10;
-
- skb_pull_rcsum(skb, DSA_HLEN);
-
- /*
- * Update packet checksum if skb is CHECKSUM_COMPLETE.
- */
- if (skb->ip_summed == CHECKSUM_COMPLETE) {
- __wsum c = skb->csum;
- c = csum_add(c, csum_partial(new_header + 2, 2, 0));
- c = csum_sub(c, csum_partial(edsa_header + 2, 2, 0));
- skb->csum = c;
- }
-
- memcpy(edsa_header, new_header, DSA_HLEN);
-
- memmove(skb->data - ETH_HLEN,
- skb->data - ETH_HLEN - DSA_HLEN,
- 2 * ETH_ALEN);
- } else {
- /*
- * Remove DSA tag and update checksum.
- */
- skb_pull_rcsum(skb, EDSA_HLEN);
- memmove(skb->data - ETH_HLEN,
- skb->data - ETH_HLEN - EDSA_HLEN,
- 2 * ETH_ALEN);
- }
-
- return skb;
-}
-
-static const struct dsa_device_ops edsa_netdev_ops = {
- .name = "edsa",
- .proto = DSA_TAG_PROTO_EDSA,
- .xmit = edsa_xmit,
- .rcv = edsa_rcv,
- .overhead = EDSA_HLEN,
-};
-
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA);
-
-module_dsa_tag_driver(edsa_netdev_ops);
struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- int err;
u8 *gswip_tag;
- err = skb_cow_head(skb, GSWIP_TX_HEADER_LEN);
- if (err)
- return NULL;
-
skb_push(skb, GSWIP_TX_HEADER_LEN);
gswip_tag = skb->data;
--- /dev/null
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * net/dsa/tag_hellcreek.c - Hirschmann Hellcreek switch tag format handling
+ *
+ * Copyright (C) 2019,2020 Linutronix GmbH
+ * Author Kurt Kanzenbach <kurt@linutronix.de>
+ *
+ * Based on tag_ksz.c.
+ */
+
+#include <linux/skbuff.h>
+#include <net/dsa.h>
+
+#include "dsa_priv.h"
+
+#define HELLCREEK_TAG_LEN 1
+
+static struct sk_buff *hellcreek_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ u8 *tag;
+
+ /* Tag encoding */
+ tag = skb_put(skb, HELLCREEK_TAG_LEN);
+ *tag = BIT(dp->index);
+
+ return skb;
+}
+
+static struct sk_buff *hellcreek_rcv(struct sk_buff *skb,
+ struct net_device *dev,
+ struct packet_type *pt)
+{
+ /* Tag decoding */
+ u8 *tag = skb_tail_pointer(skb) - HELLCREEK_TAG_LEN;
+ unsigned int port = tag[0] & 0x03;
+
+ skb->dev = dsa_master_find_slave(dev, 0, port);
+ if (!skb->dev) {
+ netdev_warn(dev, "Failed to get source port: %d\n", port);
+ return NULL;
+ }
+
+ pskb_trim_rcsum(skb, skb->len - HELLCREEK_TAG_LEN);
+
+ skb->offload_fwd_mark = true;
+
+ return skb;
+}
+
+static const struct dsa_device_ops hellcreek_netdev_ops = {
+ .name = "hellcreek",
+ .proto = DSA_TAG_PROTO_HELLCREEK,
+ .xmit = hellcreek_xmit,
+ .rcv = hellcreek_rcv,
+ .overhead = HELLCREEK_TAG_LEN,
+ .tail_tag = true,
+};
+
+MODULE_LICENSE("Dual MIT/GPL");
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_HELLCREEK);
+
+module_dsa_tag_driver(hellcreek_netdev_ops);
#define KSZ_EGRESS_TAG_LEN 1
#define KSZ_INGRESS_TAG_LEN 1
-static struct sk_buff *ksz_common_xmit(struct sk_buff *skb,
- struct net_device *dev, int len)
-{
- struct sk_buff *nskb;
- int padlen;
-
- padlen = (skb->len >= ETH_ZLEN) ? 0 : ETH_ZLEN - skb->len;
-
- if (skb_tailroom(skb) >= padlen + len) {
- /* Let dsa_slave_xmit() free skb */
- if (__skb_put_padto(skb, skb->len + padlen, false))
- return NULL;
-
- nskb = skb;
- } else {
- nskb = alloc_skb(NET_IP_ALIGN + skb->len +
- padlen + len, GFP_ATOMIC);
- if (!nskb)
- return NULL;
- skb_reserve(nskb, NET_IP_ALIGN);
-
- skb_reset_mac_header(nskb);
- skb_set_network_header(nskb,
- skb_network_header(skb) - skb->head);
- skb_set_transport_header(nskb,
- skb_transport_header(skb) - skb->head);
- skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len));
-
- /* Let skb_put_padto() free nskb, and let dsa_slave_xmit() free
- * skb
- */
- if (skb_put_padto(nskb, nskb->len + padlen))
- return NULL;
-
- consume_skb(skb);
- }
-
- return nskb;
-}
-
static struct sk_buff *ksz_common_rcv(struct sk_buff *skb,
struct net_device *dev,
unsigned int port, unsigned int len)
static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- struct sk_buff *nskb;
u8 *tag;
u8 *addr;
- nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN);
- if (!nskb)
- return NULL;
-
/* Tag encoding */
- tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN);
- addr = skb_mac_header(nskb);
+ tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
+ addr = skb_mac_header(skb);
*tag = 1 << dp->index;
if (is_link_local_ether_addr(addr))
*tag |= KSZ8795_TAIL_TAG_OVERRIDE;
- return nskb;
+ return skb;
}
static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev,
struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- struct sk_buff *nskb;
__be16 *tag;
u8 *addr;
u16 val;
- nskb = ksz_common_xmit(skb, dev, KSZ9477_INGRESS_TAG_LEN);
- if (!nskb)
- return NULL;
-
/* Tag encoding */
- tag = skb_put(nskb, KSZ9477_INGRESS_TAG_LEN);
- addr = skb_mac_header(nskb);
+ tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN);
+ addr = skb_mac_header(skb);
val = BIT(dp->index);
*tag = cpu_to_be16(val);
- return nskb;
+ return skb;
}
static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev,
struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- struct sk_buff *nskb;
u8 *addr;
u8 *tag;
- nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN);
- if (!nskb)
- return NULL;
-
/* Tag encoding */
- tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN);
- addr = skb_mac_header(nskb);
+ tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
+ addr = skb_mac_header(skb);
*tag = BIT(dp->index);
if (is_link_local_ether_addr(addr))
*tag |= KSZ9893_TAIL_TAG_OVERRIDE;
- return nskb;
+ return skb;
}
static const struct dsa_device_ops ksz9893_netdev_ops = {
__be16 *lan9303_tag;
u16 tag;
- /* insert a special VLAN tag between the MAC addresses
- * and the current ethertype field.
- */
- if (skb_cow_head(skb, LAN9303_TAG_LEN) < 0) {
- dev_dbg(&dev->dev,
- "Cannot make room for the special tag. Dropping packet\n");
- return NULL;
- }
-
/* provide 'LAN9303_TAG_LEN' bytes additional space */
skb_push(skb, LAN9303_TAG_LEN);
* table with VID.
*/
if (!skb_vlan_tagged(skb)) {
- if (skb_cow_head(skb, MTK_HDR_LEN) < 0)
- return NULL;
-
skb_push(skb, MTK_HDR_LEN);
memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN);
is_vlan_skb = false;
struct ocelot_port *ocelot_port;
u8 *prefix, *injection;
u64 qos_class, rew_op;
- int err;
-
- err = skb_cow_head(skb, OCELOT_TOTAL_TAG_LEN);
- if (unlikely(err < 0)) {
- netdev_err(netdev, "Cannot make room for tag.\n");
- return NULL;
- }
ocelot_port = ocelot->ports[dp->index];
__be16 *phdr;
u16 hdr;
- if (skb_cow_head(skb, QCA_HDR_LEN) < 0)
- return NULL;
-
skb_push(skb, QCA_HDR_LEN);
memmove(skb->data, skb->data + QCA_HDR_LEN, 2 * ETH_ALEN);
static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- struct sk_buff *nskb;
- int padlen;
u8 *trailer;
- /*
- * We have to make sure that the trailer ends up as the very
- * last 4 bytes of the packet. This means that we have to pad
- * the packet to the minimum ethernet frame size, if necessary,
- * before adding the trailer.
- */
- padlen = 0;
- if (skb->len < 60)
- padlen = 60 - skb->len;
-
- nskb = alloc_skb(NET_IP_ALIGN + skb->len + padlen + 4, GFP_ATOMIC);
- if (!nskb)
- return NULL;
- skb_reserve(nskb, NET_IP_ALIGN);
-
- skb_reset_mac_header(nskb);
- skb_set_network_header(nskb, skb_network_header(skb) - skb->head);
- skb_set_transport_header(nskb, skb_transport_header(skb) - skb->head);
- skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len));
- consume_skb(skb);
-
- if (padlen) {
- skb_put_zero(nskb, padlen);
- }
-
- trailer = skb_put(nskb, 4);
+ trailer = skb_put(skb, 4);
trailer[0] = 0x80;
trailer[1] = 1 << dp->index;
trailer[2] = 0x10;
trailer[3] = 0x00;
- return nskb;
+ return skb;
}
static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
EXPORT_SYMBOL(eth_header_cache_update);
/**
- * eth_header_parser_protocol - extract protocol from L2 header
+ * eth_header_parse_protocol - extract protocol from L2 header
* @skb: packet to extract protocol from
*/
__be16 eth_header_parse_protocol(const struct sk_buff *skb)
EXPORT_SYMBOL(eth_platform_get_mac_address);
/**
- * Obtain the MAC address from an nvmem cell named 'mac-address' associated
- * with given device.
+ * nvmem_get_mac_address - Obtain the MAC address from an nvmem cell named
+ * 'mac-address' associated with given device.
*
* @dev: Device with which the mac-address cell is associated.
* @addrbuf: Buffer to which the MAC address will be copied on success.
return ethtool_set_per_queue_coalesce(dev, useraddr, &per_queue_opt);
default:
return -EOPNOTSUPP;
- };
+ }
}
static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna)
if (info->attrs[IEEE802154_ATTR_DEV_NAME]) {
char name[IFNAMSIZ + 1];
- nla_strlcpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME],
+ nla_strscpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME],
sizeof(name));
dev = dev_get_by_name(&init_net, name);
} else if (info->attrs[IEEE802154_ATTR_DEV_INDEX]) {
struct in_device *in_dev;
struct ifaddrmsg *ifm;
struct in_ifaddr *ifa;
-
- int err = -EINVAL;
+ int err;
ASSERT_RTNL();
ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]);
if (tb[IFA_LABEL])
- nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
+ nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
char tmp[TCP_CA_NAME_MAX];
bool ecn_ca = false;
- nla_strlcpy(tmp, nla, sizeof(tmp));
+ nla_strscpy(tmp, nla, sizeof(tmp));
val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
} else {
if (nla_len(nla) != sizeof(u32))
break;
}
- *flags |= (nhc->nhc_flags & RTNH_F_ONLINK);
- if (nhc->nhc_flags & RTNH_F_OFFLOAD)
- *flags |= RTNH_F_OFFLOAD;
+ *flags |= (nhc->nhc_flags &
+ (RTNH_F_ONLINK | RTNH_F_OFFLOAD | RTNH_F_TRAP));
if (!skip_oif && nhc->nhc_dev &&
nla_put_u32(skb, RTA_OIF, nhc->nhc_dev->ifindex))
rtmsg_fib(RTM_NEWROUTE, htonl(n->key), fa,
KEYLENGTH - fa->fa_slen, tb->tb_id,
info, NLM_F_REPLACE);
-
- /* call_fib_entry_notifiers will be removed when
- * in-kernel notifier is implemented and supported
- * for nexthop objects
- */
- call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE,
- n->key,
- KEYLENGTH - fa->fa_slen, fa,
- NULL);
}
}
}
.ndo_start_xmit = ipgre_xmit,
.ndo_do_ioctl = ip_tunnel_ioctl,
.ndo_change_mtu = ip_tunnel_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_tunnel_ctl = ipgre_tunnel_ctl,
};
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ip_tunnel_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_fill_metadata_dst = gre_fill_metadata_dst,
};
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ip_tunnel_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_fill_metadata_dst = gre_fill_metadata_dst,
};
}
EXPORT_SYMBOL(skb_tunnel_check_pmtu);
-/* Often modified stats are per cpu, other are shared (netdev->stats) */
-void ip_tunnel_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- netdev_stats_to_stats64(tot, &dev->stats);
- dev_fetch_sw_netstats(tot, dev->tstats);
-}
-EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
-
static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = {
[LWTUNNEL_IP_UNSPEC] = { .strict_start_type = LWTUNNEL_IP_OPTS },
[LWTUNNEL_IP_ID] = { .type = NLA_U64 },
.ndo_start_xmit = vti_tunnel_xmit,
.ndo_do_ioctl = ip_tunnel_ioctl,
.ndo_change_mtu = ip_tunnel_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_tunnel_ctl = vti_tunnel_ctl,
};
int retries = CONF_OPEN_RETRIES;
#endif
int err;
- unsigned int i;
+ unsigned int i, count;
/* Initialise all name servers and NTP servers to NONE (but only if the
* "ip=" or "nfsaddrs=" kernel command line parameters weren't decoded,
if (ic_dev_mtu)
pr_cont(", mtu=%d", ic_dev_mtu);
/* Name servers (if any): */
- for (i = 0; i < CONF_NAMESERVERS_MAX; i++) {
+ for (i = 0, count = 0; i < CONF_NAMESERVERS_MAX; i++) {
if (ic_nameservers[i] != NONE) {
if (i == 0)
pr_info(" nameserver%u=%pI4",
else
pr_cont(", nameserver%u=%pI4",
i, &ic_nameservers[i]);
+
+ count++;
}
- if (i + 1 == CONF_NAMESERVERS_MAX)
+ if ((i + 1 == CONF_NAMESERVERS_MAX) && count > 0)
pr_cont("\n");
}
/* NTP servers (if any): */
- for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) {
+ for (i = 0, count = 0; i < CONF_NTP_SERVERS_MAX; i++) {
if (ic_ntp_servers[i] != NONE) {
if (i == 0)
pr_info(" ntpserver%u=%pI4",
else
pr_cont(", ntpserver%u=%pI4",
i, &ic_ntp_servers[i]);
+
+ count++;
}
- if (i + 1 == CONF_NTP_SERVERS_MAX)
+ if ((i + 1 == CONF_NTP_SERVERS_MAX) && count > 0)
pr_cont("\n");
}
#endif /* !SILENT */
.ndo_start_xmit = ipip_tunnel_xmit,
.ndo_do_ioctl = ip_tunnel_ioctl,
.ndo_change_mtu = ip_tunnel_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_tunnel_ctl = ipip_tunnel_ctl,
};
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
- nla_strlcpy(tmp, nla, sizeof(tmp));
+ nla_strscpy(tmp, nla, sizeof(tmp));
val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
if (val == TCP_CA_UNSPEC) {
NL_SET_ERR_MSG(extack, "Unknown tcp congestion algorithm");
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_bridge.h>
+static int nf_reject_iphdr_validate(struct sk_buff *skb)
+{
+ struct iphdr *iph;
+ u32 len;
+
+ if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+ return 0;
+
+ iph = ip_hdr(skb);
+ if (iph->ihl < 5 || iph->version != 4)
+ return 0;
+
+ len = ntohs(iph->tot_len);
+ if (skb->len < len)
+ return 0;
+ else if (len < (iph->ihl*4))
+ return 0;
+
+ if (!pskb_may_pull(skb, iph->ihl*4))
+ return 0;
+
+ return 1;
+}
+
+struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook)
+{
+ const struct tcphdr *oth;
+ struct sk_buff *nskb;
+ struct iphdr *niph;
+ struct tcphdr _oth;
+
+ if (!nf_reject_iphdr_validate(oldskb))
+ return NULL;
+
+ oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook);
+ if (!oth)
+ return NULL;
+
+ nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
+ LL_MAX_HEADER, GFP_ATOMIC);
+ if (!nskb)
+ return NULL;
+
+ nskb->dev = (struct net_device *)dev;
+
+ skb_reserve(nskb, LL_MAX_HEADER);
+ niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
+ net->ipv4.sysctl_ip_default_ttl);
+ nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
+ niph->tot_len = htons(nskb->len);
+ ip_send_check(niph);
+
+ return nskb;
+}
+EXPORT_SYMBOL_GPL(nf_reject_skb_v4_tcp_reset);
+
+struct sk_buff *nf_reject_skb_v4_unreach(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook, u8 code)
+{
+ struct sk_buff *nskb;
+ struct iphdr *niph;
+ struct icmphdr *icmph;
+ unsigned int len;
+ __wsum csum;
+ u8 proto;
+
+ if (!nf_reject_iphdr_validate(oldskb))
+ return NULL;
+
+ /* IP header checks: fragment. */
+ if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
+ return NULL;
+
+ /* RFC says return as much as we can without exceeding 576 bytes. */
+ len = min_t(unsigned int, 536, oldskb->len);
+
+ if (!pskb_may_pull(oldskb, len))
+ return NULL;
+
+ if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len)))
+ return NULL;
+
+ proto = ip_hdr(oldskb)->protocol;
+
+ if (!skb_csum_unnecessary(oldskb) &&
+ nf_reject_verify_csum(proto) &&
+ nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto))
+ return NULL;
+
+ nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) +
+ LL_MAX_HEADER + len, GFP_ATOMIC);
+ if (!nskb)
+ return NULL;
+
+ nskb->dev = (struct net_device *)dev;
+
+ skb_reserve(nskb, LL_MAX_HEADER);
+ niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP,
+ net->ipv4.sysctl_ip_default_ttl);
+
+ skb_reset_transport_header(nskb);
+ icmph = skb_put_zero(nskb, sizeof(struct icmphdr));
+ icmph->type = ICMP_DEST_UNREACH;
+ icmph->code = code;
+
+ skb_put_data(nskb, skb_network_header(oldskb), len);
+
+ csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0);
+ icmph->checksum = csum_fold(csum);
+
+ niph->tot_len = htons(nskb->len);
+ ip_send_check(niph);
+
+ return nskb;
+}
+EXPORT_SYMBOL_GPL(nf_reject_skb_v4_unreach);
+
const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb,
struct tcphdr *_oth, int hook)
{
if (!oth)
return;
- if (hook == NF_INET_PRE_ROUTING && nf_reject_fill_skb_dst(oldskb))
+ if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) &&
+ nf_reject_fill_skb_dst(oldskb) < 0)
return;
if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
if (iph->frag_off & htons(IP_OFFSET))
return;
- if (hook == NF_INET_PRE_ROUTING && nf_reject_fill_skb_dst(skb_in))
+ if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) &&
+ nf_reject_fill_skb_dst(skb_in) < 0)
return;
if (skb_csum_unnecessary(skb_in) || !nf_reject_verify_csum(proto)) {
[NHA_FDB] = { .type = NLA_FLAG },
};
+static bool nexthop_notifiers_is_empty(struct net *net)
+{
+ return !net->nexthop.notifier_chain.head;
+}
+
+static void
+__nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info,
+ const struct nexthop *nh)
+{
+ struct nh_info *nhi = rtnl_dereference(nh->nh_info);
+
+ nh_info->dev = nhi->fib_nhc.nhc_dev;
+ nh_info->gw_family = nhi->fib_nhc.nhc_gw_family;
+ if (nh_info->gw_family == AF_INET)
+ nh_info->ipv4 = nhi->fib_nhc.nhc_gw.ipv4;
+ else if (nh_info->gw_family == AF_INET6)
+ nh_info->ipv6 = nhi->fib_nhc.nhc_gw.ipv6;
+
+ nh_info->is_reject = nhi->reject_nh;
+ nh_info->is_fdb = nhi->fdb_nh;
+ nh_info->has_encap = !!nhi->fib_nhc.nhc_lwtstate;
+}
+
+static int nh_notifier_single_info_init(struct nh_notifier_info *info,
+ const struct nexthop *nh)
+{
+ info->nh = kzalloc(sizeof(*info->nh), GFP_KERNEL);
+ if (!info->nh)
+ return -ENOMEM;
+
+ __nh_notifier_single_info_init(info->nh, nh);
+
+ return 0;
+}
+
+static void nh_notifier_single_info_fini(struct nh_notifier_info *info)
+{
+ kfree(info->nh);
+}
+
+static int nh_notifier_grp_info_init(struct nh_notifier_info *info,
+ const struct nexthop *nh)
+{
+ struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
+ u16 num_nh = nhg->num_nh;
+ int i;
+
+ info->nh_grp = kzalloc(struct_size(info->nh_grp, nh_entries, num_nh),
+ GFP_KERNEL);
+ if (!info->nh_grp)
+ return -ENOMEM;
+
+ info->nh_grp->num_nh = num_nh;
+ info->nh_grp->is_fdb = nhg->fdb_nh;
+
+ for (i = 0; i < num_nh; i++) {
+ struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+
+ info->nh_grp->nh_entries[i].id = nhge->nh->id;
+ info->nh_grp->nh_entries[i].weight = nhge->weight;
+ __nh_notifier_single_info_init(&info->nh_grp->nh_entries[i].nh,
+ nhge->nh);
+ }
+
+ return 0;
+}
+
+static void nh_notifier_grp_info_fini(struct nh_notifier_info *info)
+{
+ kfree(info->nh_grp);
+}
+
+static int nh_notifier_info_init(struct nh_notifier_info *info,
+ const struct nexthop *nh)
+{
+ info->id = nh->id;
+ info->is_grp = nh->is_group;
+
+ if (info->is_grp)
+ return nh_notifier_grp_info_init(info, nh);
+ else
+ return nh_notifier_single_info_init(info, nh);
+}
+
+static void nh_notifier_info_fini(struct nh_notifier_info *info)
+{
+ if (info->is_grp)
+ nh_notifier_grp_info_fini(info);
+ else
+ nh_notifier_single_info_fini(info);
+}
+
static int call_nexthop_notifiers(struct net *net,
enum nexthop_event_type event_type,
- struct nexthop *nh)
+ struct nexthop *nh,
+ struct netlink_ext_ack *extack)
{
+ struct nh_notifier_info info = {
+ .net = net,
+ .extack = extack,
+ };
int err;
+ ASSERT_RTNL();
+
+ if (nexthop_notifiers_is_empty(net))
+ return 0;
+
+ err = nh_notifier_info_init(&info, nh);
+ if (err) {
+ NL_SET_ERR_MSG(extack, "Failed to initialize nexthop notifier info");
+ return err;
+ }
+
err = blocking_notifier_call_chain(&net->nexthop.notifier_chain,
- event_type, nh);
+ event_type, &info);
+ nh_notifier_info_fini(&info);
+
+ return notifier_to_errno(err);
+}
+
+static int call_nexthop_notifier(struct notifier_block *nb, struct net *net,
+ enum nexthop_event_type event_type,
+ struct nexthop *nh,
+ struct netlink_ext_ack *extack)
+{
+ struct nh_notifier_info info = {
+ .net = net,
+ .extack = extack,
+ };
+ int err;
+
+ err = nh_notifier_info_init(&info, nh);
+ if (err)
+ return err;
+
+ err = nb->notifier_call(nb, event_type, &info);
+ nh_notifier_info_fini(&info);
+
return notifier_to_errno(err);
}
{
struct nh_grp_entry *nhges, *new_nhges;
struct nexthop *nhp = nhge->nh_parent;
+ struct netlink_ext_ack extack;
struct nexthop *nh = nhge->nh;
struct nh_group *nhg, *newg;
- int i, j;
+ int i, j, err;
WARN_ON(!nh);
list_del(&nhge->nh_list);
nexthop_put(nhge->nh);
+ err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, &extack);
+ if (err)
+ pr_err("%s\n", extack._msg);
+
if (nlinfo)
nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo);
}
static void remove_nexthop(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo)
{
- call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh);
+ call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh, NULL);
/* remove from the tree */
rb_erase(&nh->rb_node, &net->nexthop.rb_root);
struct netlink_ext_ack *extack)
{
struct nh_group *oldg, *newg;
- int i;
+ int i, err;
if (!new->is_group) {
NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with a nexthop.");
return -EINVAL;
}
+ err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack);
+ if (err)
+ return err;
+
oldg = rtnl_dereference(old->nh_grp);
newg = rtnl_dereference(new->nh_grp);
struct nexthop *new,
struct netlink_ext_ack *extack)
{
+ u8 old_protocol, old_nh_flags;
struct nh_info *oldi, *newi;
+ struct nh_grp_entry *nhge;
+ int err;
if (new->is_group) {
NL_SET_ERR_MSG(extack, "Can not replace a nexthop with a nexthop group.");
return -EINVAL;
}
+ err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack);
+ if (err)
+ return err;
+
+ /* Hardware flags were set on 'old' as 'new' is not in the red-black
+ * tree. Therefore, inherit the flags from 'old' to 'new'.
+ */
+ new->nh_flags |= old->nh_flags & (RTNH_F_OFFLOAD | RTNH_F_TRAP);
+
oldi = rtnl_dereference(old->nh_info);
newi = rtnl_dereference(new->nh_info);
newi->nh_parent = old;
oldi->nh_parent = new;
+ old_protocol = old->protocol;
+ old_nh_flags = old->nh_flags;
+
old->protocol = new->protocol;
old->nh_flags = new->nh_flags;
rcu_assign_pointer(old->nh_info, newi);
rcu_assign_pointer(new->nh_info, oldi);
+ /* Send a replace notification for all the groups using the nexthop. */
+ list_for_each_entry(nhge, &old->grp_list, nh_list) {
+ struct nexthop *nhp = nhge->nh_parent;
+
+ err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp,
+ extack);
+ if (err)
+ goto err_notify;
+ }
+
/* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially
* update IPv4 indication in all the groups using the nexthop.
*/
if (oldi->family == AF_INET && newi->family == AF_INET6) {
- struct nh_grp_entry *nhge;
-
list_for_each_entry(nhge, &old->grp_list, nh_list) {
struct nexthop *nhp = nhge->nh_parent;
struct nh_group *nhg;
}
return 0;
+
+err_notify:
+ rcu_assign_pointer(new->nh_info, newi);
+ rcu_assign_pointer(old->nh_info, oldi);
+ old->nh_flags = old_nh_flags;
+ old->protocol = old_protocol;
+ oldi->nh_parent = old;
+ newi->nh_parent = new;
+ list_for_each_entry_continue_reverse(nhge, &old->grp_list, nh_list) {
+ struct nexthop *nhp = nhge->nh_parent;
+
+ call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, extack);
+ }
+ call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, old, extack);
+ return err;
}
static void __nexthop_replace_notify(struct net *net, struct nexthop *nh,
rb_link_node_rcu(&new_nh->rb_node, parent, pp);
rb_insert_color(&new_nh->rb_node, root);
- rc = 0;
+
+ rc = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new_nh, extack);
+ if (rc)
+ rb_erase(&new_nh->rb_node, &net->nexthop.rb_root);
+
out:
if (!rc) {
nh_base_seq_inc(net);
.notifier_call = nh_netdev_event,
};
-int register_nexthop_notifier(struct net *net, struct notifier_block *nb)
+static int nexthops_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
+{
+ struct rb_root *root = &net->nexthop.rb_root;
+ struct rb_node *node;
+ int err = 0;
+
+ for (node = rb_first(root); node; node = rb_next(node)) {
+ struct nexthop *nh;
+
+ nh = rb_entry(node, struct nexthop, rb_node);
+ err = call_nexthop_notifier(nb, net, NEXTHOP_EVENT_REPLACE, nh,
+ extack);
+ if (err)
+ break;
+ }
+
+ return err;
+}
+
+int register_nexthop_notifier(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
- return blocking_notifier_chain_register(&net->nexthop.notifier_chain,
- nb);
+ int err;
+
+ rtnl_lock();
+ err = nexthops_dump(net, nb, extack);
+ if (err)
+ goto unlock;
+ err = blocking_notifier_chain_register(&net->nexthop.notifier_chain,
+ nb);
+unlock:
+ rtnl_unlock();
+ return err;
}
EXPORT_SYMBOL(register_nexthop_notifier);
}
EXPORT_SYMBOL(unregister_nexthop_notifier);
+void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap)
+{
+ struct nexthop *nexthop;
+
+ rcu_read_lock();
+
+ nexthop = nexthop_find_by_id(net, id);
+ if (!nexthop)
+ goto out;
+
+ nexthop->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP);
+ if (offload)
+ nexthop->nh_flags |= RTNH_F_OFFLOAD;
+ if (trap)
+ nexthop->nh_flags |= RTNH_F_TRAP;
+
+out:
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL(nexthop_set_hw_flags);
+
static void __net_exit nexthop_net_exit(struct net *net)
{
rtnl_lock();
SNMP_MIB_ITEM("SndbufErrors", UDP_MIB_SNDBUFERRORS),
SNMP_MIB_ITEM("InCsumErrors", UDP_MIB_CSUMERRORS),
SNMP_MIB_ITEM("IgnoredMulti", UDP_MIB_IGNOREDMULTI),
+ SNMP_MIB_ITEM("MemErrors", UDP_MIB_MEMERRORS),
SNMP_MIB_SENTINEL
};
flags |= RTCF_LOCAL;
rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
- IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+ IN_DEV_ORCONF(in_dev, NOPOLICY), false);
if (!rth)
return -ENOBUFS;
}
rth = rt_dst_alloc(out_dev->dev, 0, res->type,
- IN_DEV_CONF_GET(in_dev, NOPOLICY),
- IN_DEV_CONF_GET(out_dev, NOXFRM));
+ IN_DEV_ORCONF(in_dev, NOPOLICY),
+ IN_DEV_ORCONF(out_dev, NOXFRM));
if (!rth) {
err = -ENOBUFS;
goto cleanup;
rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev,
flags | RTCF_LOCAL, res->type,
- IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+ IN_DEV_ORCONF(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
add:
rth = rt_dst_alloc(dev_out, flags, type,
- IN_DEV_CONF_GET(in_dev, NOPOLICY),
- IN_DEV_CONF_GET(in_dev, NOXFRM));
+ IN_DEV_ORCONF(in_dev, NOPOLICY),
+ IN_DEV_ORCONF(in_dev, NOXFRM));
if (!rth)
return ERR_PTR(-ENOBUFS);
if (rt->dst.dev &&
nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
goto nla_put_failure;
+ if (rt->dst.lwtstate &&
+ lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
+ goto nla_put_failure;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (rt->dst.tclassid &&
nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid))
* importantly be able to generate EPOLLOUT for Edge Trigger epoll()
* users.
*/
-static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
+void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
{
if (skb && !skb->len) {
tcp_unlink_write_queue(skb, sk);
}
}
+struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags,
+ struct page *page, int offset, size_t *size)
+{
+ struct sk_buff *skb = tcp_write_queue_tail(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ bool can_coalesce;
+ int copy, i;
+
+ if (!skb || (copy = size_goal - skb->len) <= 0 ||
+ !tcp_skb_can_collapse_to(skb)) {
+new_segment:
+ if (!sk_stream_memory_free(sk))
+ return NULL;
+
+ skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
+ tcp_rtx_and_write_queues_empty(sk));
+ if (!skb)
+ return NULL;
+
+#ifdef CONFIG_TLS_DEVICE
+ skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
+#endif
+ skb_entail(sk, skb);
+ copy = size_goal;
+ }
+
+ if (copy > *size)
+ copy = *size;
+
+ i = skb_shinfo(skb)->nr_frags;
+ can_coalesce = skb_can_coalesce(skb, i, page, offset);
+ if (!can_coalesce && i >= sysctl_max_skb_frags) {
+ tcp_mark_push(tp, skb);
+ goto new_segment;
+ }
+ if (!sk_wmem_schedule(sk, copy))
+ return NULL;
+
+ if (can_coalesce) {
+ skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+ } else {
+ get_page(page);
+ skb_fill_page_desc(skb, i, page, offset, copy);
+ }
+
+ if (!(flags & MSG_NO_SHARED_FRAGS))
+ skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
+
+ skb->len += copy;
+ skb->data_len += copy;
+ skb->truesize += copy;
+ sk_wmem_queued_add(sk, copy);
+ sk_mem_charge(sk, copy);
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
+ TCP_SKB_CB(skb)->end_seq += copy;
+ tcp_skb_pcount_set(skb, 0);
+
+ *size = copy;
+ return skb;
+}
+
ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
size_t size, int flags)
{
goto out_err;
while (size > 0) {
- struct sk_buff *skb = tcp_write_queue_tail(sk);
- int copy, i;
- bool can_coalesce;
+ struct sk_buff *skb;
+ size_t copy = size;
- 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_space;
-
- skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
- tcp_rtx_and_write_queues_empty(sk));
- if (!skb)
- goto wait_for_space;
-
-#ifdef CONFIG_TLS_DEVICE
- skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
-#endif
- skb_entail(sk, skb);
- copy = size_goal;
- }
-
- if (copy > size)
- copy = size;
-
- i = skb_shinfo(skb)->nr_frags;
- can_coalesce = skb_can_coalesce(skb, i, page, offset);
- if (!can_coalesce && i >= sysctl_max_skb_frags) {
- tcp_mark_push(tp, skb);
- goto new_segment;
- }
- if (!sk_wmem_schedule(sk, copy))
+ skb = tcp_build_frag(sk, size_goal, flags, page, offset, ©);
+ if (!skb)
goto wait_for_space;
- if (can_coalesce) {
- skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
- } else {
- get_page(page);
- skb_fill_page_desc(skb, i, page, offset, copy);
- }
-
- if (!(flags & MSG_NO_SHARED_FRAGS))
- skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
-
- skb->len += copy;
- skb->data_len += copy;
- skb->truesize += copy;
- sk_wmem_queued_add(sk, copy);
- sk_mem_charge(sk, copy);
- skb->ip_summed = CHECKSUM_PARTIAL;
- WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
- TCP_SKB_CB(skb)->end_seq += copy;
- tcp_skb_pcount_set(skb, 0);
-
if (!copied)
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
return too_many_orphans || out_of_socket_memory;
}
-void tcp_close(struct sock *sk, long timeout)
+void __tcp_close(struct sock *sk, long timeout)
{
struct sk_buff *skb;
int data_was_unread = 0;
int state;
- lock_sock(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
if (sk->sk_state == TCP_LISTEN) {
out:
bh_unlock_sock(sk);
local_bh_enable();
+}
+
+void tcp_close(struct sock *sk, long timeout)
+{
+ lock_sock(sk);
+ __tcp_close(sk, timeout);
release_sock(sk);
sock_put(sk);
}
* 1) If the packets in flight is larger than ssthresh, PRR spreads the
* cwnd reductions across a full RTT.
* 2) Otherwise PRR uses packet conservation to send as much as delivered.
- * But when the retransmits are acked without further losses, PRR
+ * But when SND_UNA is acked without further losses,
* slow starts cwnd up to ssthresh to speed up the recovery.
*/
static void tcp_init_cwnd_reduction(struct sock *sk)
tcp_ecn_queue_cwr(tp);
}
-void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag)
+void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
int sndcnt = 0;
u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +
tp->prior_cwnd - 1;
sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out;
- } else if ((flag & (FLAG_RETRANS_DATA_ACKED | FLAG_LOST_RETRANS)) ==
- FLAG_RETRANS_DATA_ACKED) {
+ } else if (flag & FLAG_SND_UNA_ADVANCED && !newly_lost) {
sndcnt = min_t(int, delta,
max_t(int, tp->prr_delivered - tp->prr_out,
newly_acked_sacked) + 1);
if (tcp_in_cwnd_reduction(sk)) {
/* Reduce cwnd if state mandates */
- tcp_cwnd_reduction(sk, acked_sacked, flag);
+ tcp_cwnd_reduction(sk, acked_sacked, rs->losses, flag);
} else if (tcp_may_raise_cwnd(sk, flag)) {
/* Advance cwnd if state allows */
tcp_cong_avoid(sk, ack, acked_sacked);
/* Note: tcp_v6_init_req() might override ir_iif for link locals */
inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb);
- af_ops->init_req(req, sk, skb);
-
- if (security_inet_conn_request(sk, skb, req))
+ dst = af_ops->route_req(sk, skb, &fl, req);
+ if (!dst)
goto drop_and_free;
if (tmp_opt.tstamp_ok)
tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb);
- dst = af_ops->route_req(sk, &fl, req);
- if (!dst)
- goto drop_and_free;
-
if (!want_cookie && !isn) {
/* Kill the following clause, if you dislike this way. */
if (!net->ipv4.sysctl_tcp_syncookies &&
}
static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
+ struct sk_buff *skb,
struct flowi *fl,
- const struct request_sock *req)
+ struct request_sock *req)
{
+ tcp_v4_init_req(req, sk, skb);
+
+ if (security_inet_conn_request(sk, skb, req))
+ return NULL;
+
return inet_csk_route_req(sk, &fl->u.ip4, req);
}
.req_md5_lookup = tcp_v4_md5_lookup,
.calc_md5_hash = tcp_v4_md5_hash_skb,
#endif
- .init_req = tcp_v4_init_req,
#ifdef CONFIG_SYN_COOKIES
.cookie_init_seq = cookie_v4_init_sequence,
#endif
}
#endif /* CONFIG_PROC_FS */
+/* @wake is one when sk_stream_write_space() calls us.
+ * This sends EPOLLOUT only if notsent_bytes is half the limit.
+ * This mimics the strategy used in sock_def_write_space().
+ */
+bool tcp_stream_memory_free(const struct sock *sk, int wake)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ u32 notsent_bytes = READ_ONCE(tp->write_seq) -
+ READ_ONCE(tp->snd_nxt);
+
+ return (notsent_bytes << wake) < tcp_notsent_lowat(tp);
+}
+EXPORT_SYMBOL(tcp_stream_memory_free);
+
struct proto tcp_prot = {
.name = "TCP",
.owner = THIS_MODULE,
/**
* tcp_lp_init
+ * @sk: socket to initialize congestion control algorithm for
*
* Init all required variables.
* Clone the handling from Vegas module implementation.
/**
* tcp_lp_cong_avoid
+ * @sk: socket to avoid congesting
*
* Implementation of cong_avoid.
* Will only call newReno CA when away from inference.
/**
* tcp_lp_remote_hz_estimator
+ * @sk: socket which needs an estimate for the remote HZs
*
* Estimate remote HZ.
* We keep on updating the estimated value, where original TCP-LP
/**
* tcp_lp_owd_calculator
+ * @sk: socket to calculate one way delay for
*
* Calculate one way delay (in relative format).
* Original implement OWD as minus of remote time difference to local time
/**
* tcp_lp_rtt_sample
+ * @sk: socket to add a rtt sample to
+ * @rtt: round trip time, which is ignored!
*
* Implementation or rtt_sample.
* Will take the following action,
/**
* tcp_lp_pkts_acked
+ * @sk: socket requiring congestion avoidance calculations
*
* Implementation of pkts_acked.
* Deal with active drop under Early Congestion Indication.
struct mptcp_out_options mptcp;
};
-static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts)
+static void mptcp_options_write(__be32 *ptr, const struct tcp_sock *tp,
+ struct tcp_out_options *opts)
{
#if IS_ENABLED(CONFIG_MPTCP)
if (unlikely(OPTION_MPTCP & opts->options))
- mptcp_write_options(ptr, &opts->mptcp);
+ mptcp_write_options(ptr, tp, &opts->mptcp);
#endif
}
smc_options_write(ptr, &options);
- mptcp_options_write(ptr, opts);
+ mptcp_options_write(ptr, tp, opts);
}
static void smc_set_option(const struct tcp_sock *tp,
* transferring tsq->head because tcp_wfree() might
* interrupt us (non NAPI drivers)
*/
-static void tcp_tasklet_func(unsigned long data)
+static void tcp_tasklet_func(struct tasklet_struct *t)
{
- struct tsq_tasklet *tsq = (struct tsq_tasklet *)data;
+ struct tsq_tasklet *tsq = from_tasklet(tsq, t, tasklet);
LIST_HEAD(list);
unsigned long flags;
struct list_head *q, *n;
struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i);
INIT_LIST_HEAD(&tsq->head);
- tasklet_init(&tsq->tasklet,
- tcp_tasklet_func,
- (unsigned long)tsq);
+ tasklet_setup(&tsq->tasklet, tcp_tasklet_func);
}
}
}
}
- tcp_options_write((__be32 *)(th + 1), tp, &opts);
skb_shinfo(skb)->gso_type = sk->sk_gso_type;
if (likely(!(tcb->tcp_flags & TCPHDR_SYN))) {
th->window = htons(tcp_select_window(sk));
*/
th->window = htons(min(tp->rcv_wnd, 65535U));
}
+
+ tcp_options_write((__be32 *)(th + 1), tp, &opts);
+
#ifdef CONFIG_TCP_MD5SIG
/* Calculate the MD5 hash, as we have all we need now */
if (md5) {
if (!buff)
return -ENOMEM; /* We'll just try again later. */
skb_copy_decrypted(buff, skb);
+ mptcp_skb_ext_copy(buff, skb);
sk_wmem_queued_add(sk, buff->truesize);
sk_mem_charge(sk, buff->truesize);
if (unlikely(!buff))
return -ENOMEM;
skb_copy_decrypted(buff, skb);
+ mptcp_skb_ext_copy(buff, skb);
sk_wmem_queued_add(sk, buff->truesize);
sk_mem_charge(sk, buff->truesize);
skb = tcp_send_head(sk);
skb_copy_decrypted(nskb, skb);
+ mptcp_skb_ext_copy(nskb, skb);
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
{
struct tcp_sock *tp = tcp_sk(sk);
u32 timeout, prior_inflight;
+ u32 lost = tp->lost;
prior_inflight = tcp_packets_in_flight(tp);
tcp_rack_detect_loss(sk, &timeout);
if (inet_csk(sk)->icsk_ca_state != TCP_CA_Recovery) {
tcp_enter_recovery(sk, false);
if (!inet_csk(sk)->icsk_ca_ops->cong_control)
- tcp_cwnd_reduction(sk, 1, 0);
+ tcp_cwnd_reduction(sk, 1, tp->lost - lost, 0);
}
tcp_xmit_retransmit_queue(sk);
}
inet_sdif(skb), udptable, skb);
}
-struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
+struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
const struct iphdr *iph = ip_hdr(skb);
iph->daddr, dport, inet_iif(skb),
inet_sdif(skb), &udp_table, NULL);
}
-EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb);
/* Must be called under rcu_read_lock().
* Does increment socket refcount.
sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
iph->saddr, uh->source, skb->dev->ifindex,
inet_sdif(skb), udptable, NULL);
- if (!sk) {
+ if (!sk || udp_sk(sk)->encap_type) {
/* No socket for error: try tunnels before discarding */
sk = ERR_PTR(-ENOENT);
if (static_branch_unlikely(&udp_encap_needed_key)) {
struct sock *sk = skb->sk;
struct inet_sock *inet = inet_sk(sk);
struct udphdr *uh;
- int err = 0;
+ int err;
int is_udplite = IS_UDPLITE(sk);
int offset = skb_transport_offset(skb);
int len = skb->len - offset;
if (rc == -ENOMEM)
UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS,
is_udplite);
+ else
+ UDP_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS,
+ is_udplite);
UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
kfree_skb(skb);
trace_udp_fail_queue_rcv_skb(rc, sk);
const struct inet_diag_req_v2 *req)
{
struct sk_buff *in_skb = cb->skb;
- int err = -EINVAL;
+ int err;
struct sock *sk = NULL;
struct sk_buff *rep;
struct net *net = sock_net(in_skb->sk);
__skb_pull(skb, tnl_hlen);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb_inner_network_offset(skb));
+ skb_set_transport_header(skb, skb_inner_transport_offset(skb));
skb->mac_len = skb_inner_network_offset(skb);
skb->protocol = new_protocol;
(NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));
features &= skb->dev->hw_enc_features;
+ /* CRC checksum can't be handled by HW when it's a UDP tunneling packet. */
+ features &= ~NETIF_F_SCTP_CRC;
/* The only checksum offload we care about from here on out is the
* outer one so strip the existing checksum feature flags and
{
__be16 newlen = htons(skb->len - nhoff);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
- int err = -ENOSYS;
struct sock *sk;
+ int err;
uh->len = newlen;
* ipv6_dev_find - find the first device with a given source address.
* @net: the net namespace
* @addr: the source address
+ * @dev: used to find the L3 domain of interest
*
* The caller should be protected by RCU, or RTNL.
*/
/**
* calipso_doi_remove - Remove an existing DOI from the CALIPSO protocol engine
* @doi: the DOI value
- * @audit_secid: the LSM secid to use in the audit message
+ * @audit_info: NetLabel audit information
*
* Description:
* Removes a DOI definition from the CALIPSO engine. The NetLabel routines will
/**
* calipso_req_delattr - Delete the CALIPSO option from a request socket
- * @reg: the request socket
+ * @req: the request socket
*
* Description:
* Removes the CALIPSO option from a request socket, if present.
/*
* Note: we cannot rely on skb_dst(skb) before we assign it in ip6_route_input().
*/
-static inline struct inet6_dev *ipv6_skb_idev(struct sk_buff *skb)
-{
- return skb_dst(skb) ? ip6_dst_idev(skb_dst(skb)) : __in6_dev_get(skb->dev);
-}
-
static inline struct net *ipv6_skb_net(struct sk_buff *skb)
{
return skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev);
.ndo_start_xmit = ip6gre_tunnel_xmit,
.ndo_do_ioctl = ip6gre_tunnel_ioctl,
.ndo_change_mtu = ip6_tnl_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ip6_tnl_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ip6_tnl_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
return IS_ENABLED(CONFIG_MPLS);
}
-static struct net_device_stats *ip6_get_stats(struct net_device *dev)
-{
- struct pcpu_sw_netstats tmp, sum = { 0 };
- int i;
-
- for_each_possible_cpu(i) {
- unsigned int start;
- const struct pcpu_sw_netstats *tstats =
- per_cpu_ptr(dev->tstats, i);
-
- do {
- start = u64_stats_fetch_begin_irq(&tstats->syncp);
- tmp.rx_packets = tstats->rx_packets;
- tmp.rx_bytes = tstats->rx_bytes;
- tmp.tx_packets = tstats->tx_packets;
- tmp.tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
-
- sum.rx_packets += tmp.rx_packets;
- sum.rx_bytes += tmp.rx_bytes;
- sum.tx_packets += tmp.tx_packets;
- sum.tx_bytes += tmp.tx_bytes;
- }
- dev->stats.rx_packets = sum.rx_packets;
- dev->stats.rx_bytes = sum.rx_bytes;
- dev->stats.tx_packets = sum.tx_packets;
- dev->stats.tx_bytes = sum.tx_bytes;
- return &dev->stats;
-}
-
#define for_each_ip6_tunnel_rcu(start) \
for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
/**
* ip6_tnl_bucket - get head of list matching given tunnel parameters
+ * @ip6n: the private data for ip6_vti in the netns
* @p: parameters containing tunnel end-points
*
* Description:
/**
* ip6_tnl_link - add tunnel to hash table
+ * @ip6n: the private data for ip6_vti in the netns
* @t: tunnel to be added
**/
/**
* ip6_tnl_unlink - remove tunnel from hash table
+ * @ip6n: the private data for ip6_vti in the netns
* @t: tunnel to be removed
**/
/**
* parse_tvl_tnl_enc_lim - handle encapsulation limit option
* @skb: received socket buffer
+ * @raw: the ICMPv6 error message data
*
* Return:
* 0 if none was found,
}
EXPORT_SYMBOL(ip6_tnl_parse_tlv_enc_lim);
-/**
- * ip6_tnl_err - tunnel error handler
- *
- * Description:
- * ip6_tnl_err() should handle errors in the tunnel according
- * to the specifications in RFC 2473.
- **/
-
+/* ip6_tnl_err() should handle errors in the tunnel according to the
+ * specifications in RFC 2473.
+ */
static int
ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
u8 *type, u8 *code, int *msg, __u32 *info, int offset)
.ndo_start_xmit = ip6_tnl_start_xmit,
.ndo_do_ioctl = ip6_tnl_ioctl,
.ndo_change_mtu = ip6_tnl_change_mtu,
- .ndo_get_stats = ip6_get_stats,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
/**
* vti6_tnl_bucket - get head of list matching given tunnel parameters
+ * @ip6n: the private data for ip6_vti in the netns
* @p: parameters containing tunnel end-points
*
* Description:
.ndo_uninit = vti6_dev_uninit,
.ndo_start_xmit = vti6_tnl_xmit,
.ndo_do_ioctl = vti6_ioctl,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
if (sk->sk_type != SOCK_STREAM)
return -ENOPROTOOPT;
- msg.msg_control = optval;
+ msg.msg_control_user = optval;
msg.msg_controllen = len;
msg.msg_flags = flags;
msg.msg_control_is_user = true;
}
int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
- struct sockaddr_storage *p)
+ struct sockaddr_storage __user *p)
{
int err, i, count, copycount;
const struct in6_addr *group;
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_bridge.h>
+static bool nf_reject_v6_csum_ok(struct sk_buff *skb, int hook)
+{
+ const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ int thoff;
+ __be16 fo;
+ u8 proto = ip6h->nexthdr;
+
+ if (skb_csum_unnecessary(skb))
+ return true;
+
+ if (ip6h->payload_len &&
+ pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h)))
+ return false;
+
+ ip6h = ipv6_hdr(skb);
+ thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo);
+ if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
+ return false;
+
+ if (!nf_reject_verify_csum(proto))
+ return true;
+
+ return nf_ip6_checksum(skb, hook, thoff, proto) == 0;
+}
+
+static int nf_reject_ip6hdr_validate(struct sk_buff *skb)
+{
+ struct ipv6hdr *hdr;
+ u32 pkt_len;
+
+ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+ return 0;
+
+ hdr = ipv6_hdr(skb);
+ if (hdr->version != 6)
+ return 0;
+
+ pkt_len = ntohs(hdr->payload_len);
+ if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
+ return 0;
+
+ return 1;
+}
+
+struct sk_buff *nf_reject_skb_v6_tcp_reset(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook)
+{
+ struct sk_buff *nskb;
+ const struct tcphdr *oth;
+ struct tcphdr _oth;
+ unsigned int otcplen;
+ struct ipv6hdr *nip6h;
+
+ if (!nf_reject_ip6hdr_validate(oldskb))
+ return NULL;
+
+ oth = nf_reject_ip6_tcphdr_get(oldskb, &_oth, &otcplen, hook);
+ if (!oth)
+ return NULL;
+
+ nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct tcphdr) +
+ LL_MAX_HEADER, GFP_ATOMIC);
+ if (!nskb)
+ return NULL;
+
+ nskb->dev = (struct net_device *)dev;
+
+ skb_reserve(nskb, LL_MAX_HEADER);
+ nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
+ net->ipv6.devconf_all->hop_limit);
+ nf_reject_ip6_tcphdr_put(nskb, oldskb, oth, otcplen);
+ nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr));
+
+ return nskb;
+}
+EXPORT_SYMBOL_GPL(nf_reject_skb_v6_tcp_reset);
+
+struct sk_buff *nf_reject_skb_v6_unreach(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook, u8 code)
+{
+ struct sk_buff *nskb;
+ struct ipv6hdr *nip6h;
+ struct icmp6hdr *icmp6h;
+ unsigned int len;
+
+ if (!nf_reject_ip6hdr_validate(oldskb))
+ return NULL;
+
+ /* Include "As much of invoking packet as possible without the ICMPv6
+ * packet exceeding the minimum IPv6 MTU" in the ICMP payload.
+ */
+ len = min_t(unsigned int, 1220, oldskb->len);
+
+ if (!pskb_may_pull(oldskb, len))
+ return NULL;
+
+ if (!nf_reject_v6_csum_ok(oldskb, hook))
+ return NULL;
+
+ nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) +
+ LL_MAX_HEADER + len, GFP_ATOMIC);
+ if (!nskb)
+ return NULL;
+
+ nskb->dev = (struct net_device *)dev;
+
+ skb_reserve(nskb, LL_MAX_HEADER);
+ nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_ICMPV6,
+ net->ipv6.devconf_all->hop_limit);
+
+ skb_reset_transport_header(nskb);
+ icmp6h = skb_put_zero(nskb, sizeof(struct icmp6hdr));
+ icmp6h->icmp6_type = ICMPV6_DEST_UNREACH;
+ icmp6h->icmp6_code = code;
+
+ skb_put_data(nskb, skb_network_header(oldskb), len);
+ nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr));
+
+ icmp6h->icmp6_cksum =
+ csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr,
+ nskb->len - sizeof(struct ipv6hdr),
+ IPPROTO_ICMPV6,
+ csum_partial(icmp6h,
+ nskb->len - sizeof(struct ipv6hdr),
+ 0));
+
+ return nskb;
+}
+EXPORT_SYMBOL_GPL(nf_reject_skb_v6_unreach);
+
const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb,
struct tcphdr *otcph,
unsigned int *otcplen, int hook)
fl6.fl6_sport = otcph->dest;
fl6.fl6_dport = otcph->source;
- if (hook == NF_INET_PRE_ROUTING) {
+ if (hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) {
nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false);
if (!dst)
return;
if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL)
skb_in->dev = net->loopback_dev;
- if (hooknum == NF_INET_PRE_ROUTING && nf_reject6_fill_skb_dst(skb_in))
+ if ((hooknum == NF_INET_PRE_ROUTING || hooknum == NF_INET_INGRESS) &&
+ nf_reject6_fill_skb_dst(skb_in) < 0)
return;
icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);
SNMP_MIB_ITEM("Udp6SndbufErrors", UDP_MIB_SNDBUFERRORS),
SNMP_MIB_ITEM("Udp6InCsumErrors", UDP_MIB_CSUMERRORS),
SNMP_MIB_ITEM("Udp6IgnoredMulti", UDP_MIB_IGNOREDMULTI),
+ SNMP_MIB_ITEM("Udp6MemErrors", UDP_MIB_MEMERRORS),
SNMP_MIB_SENTINEL
};
SNMP_MIB_ITEM("UdpLite6RcvbufErrors", UDP_MIB_RCVBUFERRORS),
SNMP_MIB_ITEM("UdpLite6SndbufErrors", UDP_MIB_SNDBUFERRORS),
SNMP_MIB_ITEM("UdpLite6InCsumErrors", UDP_MIB_CSUMERRORS),
+ SNMP_MIB_ITEM("UdpLite6MemErrors", UDP_MIB_MEMERRORS),
SNMP_MIB_SENTINEL
};
if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex))
goto nla_put_failure;
+
+ if (dst->lwtstate &&
+ lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
+ goto nla_put_failure;
} else if (rt->fib6_nsiblings) {
struct fib6_info *sibling, *next_sibling;
struct nlattr *mp;
struct sk_buff *skb;
int err = -ENOBUFS;
- /* call_fib6_entry_notifiers will be removed when in-kernel notifier
- * is implemented and supported for nexthop objects
- */
- call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, rt, NULL);
-
skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
if (!skb)
goto errout;
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* Authors:
* (C) 2020 Alexander Aring <alex.aring@gmail.com>
*/
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* Authors:
* (C) 2020 Alexander Aring <alex.aring@gmail.com>
*/
.ndo_uninit = ipip6_tunnel_uninit,
.ndo_start_xmit = sit_tunnel_xmit,
.ndo_do_ioctl = ipip6_tunnel_ioctl,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_tunnel_ctl = ipip6_tunnel_ctl,
};
}
static struct dst_entry *tcp_v6_route_req(const struct sock *sk,
+ struct sk_buff *skb,
struct flowi *fl,
- const struct request_sock *req)
+ struct request_sock *req)
{
+ tcp_v6_init_req(req, sk, skb);
+
+ if (security_inet_conn_request(sk, skb, req))
+ return NULL;
+
return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP);
}
.req_md5_lookup = tcp_v6_md5_lookup,
.calc_md5_hash = tcp_v6_md5_hash_skb,
#endif
- .init_req = tcp_v6_init_req,
#ifdef CONFIG_SYN_COOKIES
.cookie_init_seq = cookie_v6_init_sequence,
#endif
inet6_sdif(skb), udptable, skb);
}
-struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
+struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
&iph->daddr, dport, inet6_iif(skb),
inet6_sdif(skb), &udp_table, NULL);
}
-EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb);
/* Must be called under rcu_read_lock().
* Does increment socket refcount.
sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
inet6_iif(skb), inet6_sdif(skb), udptable, NULL);
- if (!sk) {
+ if (!sk || udp_sk(sk)->encap_type) {
/* No socket for error: try tunnels before discarding */
sk = ERR_PTR(-ENOENT);
if (static_branch_unlikely(&udpv6_encap_needed_key)) {
if (rc == -ENOMEM)
UDP6_INC_STATS(sock_net(sk),
UDP_MIB_RCVBUFERRORS, is_udplite);
+ else
+ UDP6_INC_STATS(sock_net(sk),
+ UDP_MIB_MEMERRORS, is_udplite);
UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
kfree_skb(skb);
return -1;
int tnl_hlen;
int err;
- mss = skb_shinfo(skb)->gso_size;
- if (unlikely(skb->len <= mss))
- goto out;
-
if (skb->encapsulation && skb_shinfo(skb)->gso_type &
(SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
segs = skb_udp_tunnel_segment(skb, features, true);
if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
return __udp_gso_segment(skb, features);
+ mss = skb_shinfo(skb)->gso_size;
+ if (unlikely(skb->len <= mss))
+ goto out;
+
/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
* do checksum of UDP packets sent as multiple IP fragments.
*/
* L3 master device
* @net: network namespace for device index lookup
* @fl: flow struct
+ * @arg: store the table the rule matched with here
*/
int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
return used;
}
+/* Handle device status changes. */
+static int lapb_device_event(struct notifier_block *this, unsigned long event,
+ void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct lapb_cb *lapb;
+
+ if (!net_eq(dev_net(dev), &init_net))
+ return NOTIFY_DONE;
+
+ if (dev->type != ARPHRD_X25)
+ return NOTIFY_DONE;
+
+ lapb = lapb_devtostruct(dev);
+ if (!lapb)
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_UP:
+ lapb_dbg(0, "(%p) Interface up: %s\n", dev, dev->name);
+
+ if (netif_carrier_ok(dev)) {
+ lapb_dbg(0, "(%p): Carrier is already up: %s\n", dev,
+ dev->name);
+ if (lapb->mode & LAPB_DCE) {
+ lapb_start_t1timer(lapb);
+ } else {
+ if (lapb->state == LAPB_STATE_0) {
+ lapb->state = LAPB_STATE_1;
+ lapb_establish_data_link(lapb);
+ }
+ }
+ }
+ break;
+ case NETDEV_GOING_DOWN:
+ if (netif_carrier_ok(dev))
+ lapb_disconnect_request(dev);
+ break;
+ case NETDEV_DOWN:
+ lapb_dbg(0, "(%p) Interface down: %s\n", dev, dev->name);
+ lapb_dbg(0, "(%p) S%d -> S0\n", dev, lapb->state);
+ lapb_clear_queues(lapb);
+ lapb->state = LAPB_STATE_0;
+ lapb->n2count = 0;
+ lapb_stop_t1timer(lapb);
+ lapb_stop_t2timer(lapb);
+ break;
+ case NETDEV_CHANGE:
+ if (netif_carrier_ok(dev)) {
+ lapb_dbg(0, "(%p): Carrier detected: %s\n", dev,
+ dev->name);
+ if (lapb->mode & LAPB_DCE) {
+ lapb_start_t1timer(lapb);
+ } else {
+ if (lapb->state == LAPB_STATE_0) {
+ lapb->state = LAPB_STATE_1;
+ lapb_establish_data_link(lapb);
+ }
+ }
+ } else {
+ lapb_dbg(0, "(%p) Carrier lost: %s\n", dev, dev->name);
+ lapb_dbg(0, "(%p) S%d -> S0\n", dev, lapb->state);
+ lapb_clear_queues(lapb);
+ lapb->state = LAPB_STATE_0;
+ lapb->n2count = 0;
+ lapb_stop_t1timer(lapb);
+ lapb_stop_t2timer(lapb);
+ }
+ break;
+ }
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block lapb_dev_notifier = {
+ .notifier_call = lapb_device_event,
+};
+
static int __init lapb_init(void)
{
- return 0;
+ return register_netdevice_notifier(&lapb_dev_notifier);
}
static void __exit lapb_exit(void)
{
WARN_ON(!list_empty(&lapb_list));
+
+ unregister_netdevice_notifier(&lapb_dev_notifier);
}
MODULE_AUTHOR("Jonathan Naylor <g4klx@g4klx.demon.co.uk>");
switch (lapb->state) {
/*
- * If we are a DCE, keep going DM .. DM .. DM
+ * If we are a DCE, send DM up to N2 times, then switch to
+ * STATE_1 and send SABM(E).
*/
case LAPB_STATE_0:
- if (lapb->mode & LAPB_DCE)
+ if (lapb->mode & LAPB_DCE &&
+ lapb->n2count != lapb->n2) {
+ lapb->n2count++;
lapb_send_control(lapb, LAPB_DM, LAPB_POLLOFF, LAPB_RESPONSE);
+ } else {
+ lapb->state = LAPB_STATE_1;
+ lapb_establish_data_link(lapb);
+ }
break;
/*
* @net: network namespace
* @family: upper layer protocol family
* @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
+ * @prot: struct proto associated with this new sock instance
+ * @kern: is this to be a kernel socket?
*
* Allocates a LLC sock and initializes it. Returns the new LLC sock
* or %NULL if there's no memory available for one
return 0;
}
-static int ieee80211_set_wds_peer(struct wiphy *wiphy, struct net_device *dev,
- const u8 *addr)
-{
- struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-
- memcpy(&sdata->u.wds.remote_addr, addr, ETH_ALEN);
-
- return 0;
-}
-
static void ieee80211_rfkill_poll(struct wiphy *wiphy)
{
struct ieee80211_local *local = wiphy_priv(wiphy);
.set_wiphy_params = ieee80211_set_wiphy_params,
.set_tx_power = ieee80211_set_tx_power,
.get_tx_power = ieee80211_get_tx_power,
- .set_wds_peer = ieee80211_set_wds_peer,
.rfkill_poll = ieee80211_rfkill_poll,
CFG80211_TESTMODE_CMD(ieee80211_testmode_cmd)
CFG80211_TESTMODE_DUMP(ieee80211_testmode_dump)
case NL80211_IFTYPE_NAN:
continue;
case NL80211_IFTYPE_ADHOC:
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_MESH_POINT:
case NL80211_IFTYPE_OCB:
width = vif->bss_conf.chandef.width;
break;
+ case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_UNSPECIFIED:
case NUM_NL80211_IFTYPES:
case NL80211_IFTYPE_MONITOR:
continue;
case NL80211_IFTYPE_AP:
case NL80211_IFTYPE_ADHOC:
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_MESH_POINT:
case NL80211_IFTYPE_OCB:
break;
IEEE80211_IF_FILE_RW(tsf);
-/* WDS attributes */
-IEEE80211_IF_FILE(peer, u.wds.remote_addr, MAC);
-
#ifdef CONFIG_MAC80211_MESH
IEEE80211_IF_FILE(estab_plinks, u.mesh.estab_plinks, ATOMIC);
DEBUGFS_ADD_MODE(tsf, 0600);
}
-static void add_wds_files(struct ieee80211_sub_if_data *sdata)
-{
- DEBUGFS_ADD(peer);
-}
-
#ifdef CONFIG_MAC80211_MESH
static void add_mesh_files(struct ieee80211_sub_if_data *sdata)
case NL80211_IFTYPE_AP_VLAN:
add_vlan_files(sdata);
break;
- case NL80211_IFTYPE_WDS:
- add_wds_files(sdata);
- break;
default:
break;
}
"Q limit[low/high]: VO: %u/%u VI: %u/%u BE: %u/%u BK: %u/%u\n",
q_depth[0], q_depth[1], q_depth[2], q_depth[3],
q_limit_l[0], q_limit_h[0], q_limit_l[1], q_limit_h[1],
- q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]),
+ q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]);
rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
kfree(buf);
bool multicast_to_unicast;
};
-struct ieee80211_if_wds {
- struct sta_info *sta;
- u8 remote_addr[ETH_ALEN];
-};
-
struct ieee80211_if_vlan {
struct list_head list; /* write-protected with RTNL and local->mtx */
union {
struct ieee80211_if_ap ap;
- struct ieee80211_if_wds wds;
struct ieee80211_if_vlan vlan;
struct ieee80211_if_managed mgd;
struct ieee80211_if_ibss ibss;
/* tx handling */
void ieee80211_clear_tx_pending(struct ieee80211_local *local);
-void ieee80211_tx_pending(unsigned long data);
+void ieee80211_tx_pending(struct tasklet_struct *t);
netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
struct net_device *dev);
netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
struct ieee80211_sub_if_data *sdata);
void ieee80211_fill_txq_stats(struct cfg80211_txq_stats *txqstats,
struct txq_info *txqi);
-void ieee80211_wake_txqs(unsigned long data);
+void ieee80211_wake_txqs(struct tasklet_struct *t);
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,
type2 == NL80211_IFTYPE_MONITOR ||
type1 == NL80211_IFTYPE_P2P_DEVICE ||
type2 == NL80211_IFTYPE_P2P_DEVICE ||
- (type1 == NL80211_IFTYPE_AP && type2 == NL80211_IFTYPE_WDS) ||
- (type1 == NL80211_IFTYPE_WDS &&
- (type2 == NL80211_IFTYPE_WDS ||
- type2 == NL80211_IFTYPE_AP)) ||
(type1 == NL80211_IFTYPE_AP && type2 == NL80211_IFTYPE_AP_VLAN) ||
(type1 == NL80211_IFTYPE_AP_VLAN &&
(type2 == NL80211_IFTYPE_AP ||
* (because if we remove a STA after ops->remove_interface()
* the driver will have removed the vif info already!)
*
- * In WDS mode a station must exist here and be flushed, for
- * AP_VLANs stations may exist since there's nothing else that
+ * For AP_VLANs stations may exist since there's nothing else that
* would have removed them, but in other modes there shouldn't
* be any stations.
*/
flushed = sta_info_flush(sdata);
- WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP_VLAN &&
- ((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) ||
- (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1)));
+ WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP_VLAN && flushed > 0);
/* don't count this interface for allmulti while it is down */
if (sdata->flags & IEEE80211_SDATA_ALLMULTI)
* When we get here, the interface is marked down.
* Free the remaining keys, if there are any
* (which can happen in AP mode if userspace sets
- * keys before the interface is operating, and maybe
- * also in WDS mode)
+ * keys before the interface is operating)
*
* Force the key freeing to always synchronize_net()
* to wait for the RX path in case it is using this
struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
struct net_device *dev = wdev->netdev;
struct ieee80211_local *local = sdata->local;
- struct sta_info *sta;
u32 changed = 0;
int res;
u32 hw_reconf_flags = 0;
switch (sdata->vif.type) {
- case NL80211_IFTYPE_WDS:
- if (!is_valid_ether_addr(sdata->u.wds.remote_addr))
- return -ENOLINK;
- break;
case NL80211_IFTYPE_AP_VLAN: {
struct ieee80211_sub_if_data *master;
case NUM_NL80211_IFTYPES:
case NL80211_IFTYPE_P2P_CLIENT:
case NL80211_IFTYPE_P2P_GO:
+ case NL80211_IFTYPE_WDS:
/* cannot happen */
WARN_ON(1);
break;
case NL80211_IFTYPE_OCB:
netif_carrier_off(dev);
break;
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_P2P_DEVICE:
case NL80211_IFTYPE_NAN:
break;
set_bit(SDATA_STATE_RUNNING, &sdata->state);
switch (sdata->vif.type) {
- case NL80211_IFTYPE_WDS:
- /* Create STA entry for the WDS peer */
- sta = sta_info_alloc(sdata, sdata->u.wds.remote_addr,
- GFP_KERNEL);
- if (!sta) {
- res = -ENOMEM;
- goto err_del_interface;
- }
-
- sta_info_pre_move_state(sta, IEEE80211_STA_AUTH);
- sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC);
- sta_info_pre_move_state(sta, IEEE80211_STA_AUTHORIZED);
-
- res = sta_info_insert(sta);
- if (res) {
- /* STA has been freed */
- goto err_del_interface;
- }
-
- rate_control_rate_init(sta);
- netif_carrier_on(dev);
- break;
case NL80211_IFTYPE_P2P_DEVICE:
rcu_assign_pointer(local->p2p_sdata, sdata);
break;
while ((skb = skb_dequeue(&sdata->skb_queue))) {
struct ieee80211_mgmt *mgmt = (void *)skb->data;
+ kcov_remote_start_common(skb_get_kcov_handle(skb));
if (ieee80211_is_action(mgmt->frame_control) &&
mgmt->u.action.category == WLAN_CATEGORY_BACK) {
int len = skb->len;
}
kfree_skb(skb);
+ kcov_remote_stop();
}
/* then other type-dependent work */
sdata->u.mntr.flags = MONITOR_FLAG_CONTROL |
MONITOR_FLAG_OTHER_BSS;
break;
- case NL80211_IFTYPE_WDS:
- sdata->vif.bss_conf.bssid = NULL;
- break;
case NL80211_IFTYPE_NAN:
idr_init(&sdata->u.nan.function_inst_ids);
spin_lock_init(&sdata->u.nan.func_lock);
sdata->vif.bss_conf.bssid = sdata->vif.addr;
break;
case NL80211_IFTYPE_UNSPECIFIED:
+ case NL80211_IFTYPE_WDS:
case NUM_NL80211_IFTYPES:
WARN_ON(1);
break;
case NL80211_IFTYPE_OCB:
/*
* Could probably support everything
- * but WDS here (WDS do_open can fail
- * under memory pressure, which this
- * code isn't prepared to handle).
+ * but here.
*/
break;
case NL80211_IFTYPE_P2P_CLIENT:
case NL80211_IFTYPE_MONITOR:
/* doesn't matter */
break;
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_AP_VLAN:
/* match up with an AP interface */
list_for_each_entry(sdata, &local->interfaces, list) {
BSS_CHANGED_ERP_SLOT;
}
-static void ieee80211_tasklet_handler(unsigned long data)
+static void ieee80211_tasklet_handler(struct tasklet_struct *t)
{
- struct ieee80211_local *local = (struct ieee80211_local *) data;
+ struct ieee80211_local *local = from_tasklet(local, t, tasklet);
struct sk_buff *skb;
while ((skb = skb_dequeue(&local->skb_queue)) ||
skb_queue_head_init(&local->pending[i]);
atomic_set(&local->agg_queue_stop[i], 0);
}
- tasklet_init(&local->tx_pending_tasklet, ieee80211_tx_pending,
- (unsigned long)local);
+ tasklet_setup(&local->tx_pending_tasklet, ieee80211_tx_pending);
if (ops->wake_tx_queue)
- tasklet_init(&local->wake_txqs_tasklet, ieee80211_wake_txqs,
- (unsigned long)local);
+ tasklet_setup(&local->wake_txqs_tasklet, ieee80211_wake_txqs);
- tasklet_init(&local->tasklet,
- ieee80211_tasklet_handler,
- (unsigned long) local);
+ tasklet_setup(&local->tasklet, ieee80211_tasklet_handler);
skb_queue_head_init(&local->skb_queue);
skb_queue_head_init(&local->skb_queue_unreliable);
return -EINVAL;
}
} else {
- /*
- * WDS is currently prohibited when channel contexts are used
- * because there's no clear definition of which channel WDS
- * type interfaces use
- */
- if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_WDS))
- return -EINVAL;
-
/* DFS is not supported with multi-channel combinations yet */
for (i = 0; i < local->hw.wiphy->n_iface_combinations; i++) {
const struct ieee80211_iface_combination *comb;
}
}
+static void
+ieee80211_mesh_update_bss_params(struct ieee80211_sub_if_data *sdata,
+ u8 *ie, u8 ie_len)
+{
+ struct ieee80211_supported_band *sband;
+ const u8 *cap;
+ const struct ieee80211_he_operation *he_oper = NULL;
+
+ sband = ieee80211_get_sband(sdata);
+ if (!sband)
+ return;
+
+ if (!ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT) ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10)
+ return;
+
+ sdata->vif.bss_conf.he_support = true;
+
+ cap = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, ie, ie_len);
+ if (cap && cap[1] >= ieee80211_he_oper_size(&cap[3]))
+ he_oper = (void *)(cap + 3);
+
+ if (he_oper)
+ sdata->vif.bss_conf.he_oper.params =
+ __le32_to_cpu(he_oper->he_oper_params);
+}
+
/**
* ieee80211_fill_mesh_addresses - fill addresses of a locally originated mesh frame
* @hdr: 802.11 frame header
bcn->tail_len = skb->len;
memcpy(bcn->tail, skb->data, bcn->tail_len);
+ ieee80211_mesh_update_bss_params(sdata, bcn->tail, bcn->tail_len);
bcn->meshconf = (struct ieee80211_meshconf_ie *)
(bcn->tail + ifmsh->meshconf_offset);
case NL80211_IFTYPE_STATION:
ieee80211_mgd_quiesce(sdata);
break;
- case NL80211_IFTYPE_WDS:
- /* tear down aggregation sessions and remove STAs */
- mutex_lock(&local->sta_mtx);
- sta = sdata->u.wds.sta;
- if (sta && sta->uploaded) {
- enum ieee80211_sta_state state;
-
- state = sta->sta_state;
- for (; state > IEEE80211_STA_NOTEXIST; state--)
- WARN_ON(drv_sta_state(local, sta->sdata,
- sta, state,
- state - 1));
- }
- mutex_unlock(&local->sta_mtx);
- break;
default:
break;
}
if (unlikely((ieee80211_is_data(hdr->frame_control) ||
ieee80211_is_pspoll(hdr->frame_control)) &&
rx->sdata->vif.type != NL80211_IFTYPE_ADHOC &&
- rx->sdata->vif.type != NL80211_IFTYPE_WDS &&
rx->sdata->vif.type != NL80211_IFTYPE_OCB &&
(!rx->sta || !test_sta_flag(rx->sta, WLAN_STA_ASSOC)))) {
/*
return false;
return true;
- case NL80211_IFTYPE_WDS:
- if (bssid || !ieee80211_is_data(hdr->frame_control))
- return false;
- return ether_addr_equal(sdata->u.wds.remote_addr, hdr->addr2);
case NL80211_IFTYPE_P2P_DEVICE:
return ieee80211_is_public_action(hdr, skb->len) ||
ieee80211_is_probe_req(hdr->frame_control) ||
status->rx_flags = 0;
+ kcov_remote_start_common(skb_get_kcov_handle(skb));
+
/*
* Frames with failed FCS/PLCP checksum are not returned,
* all other frames are returned without radiotap header
* Also, frames with less than 16 bytes are dropped.
*/
skb = ieee80211_rx_monitor(local, skb, rate);
- if (!skb)
- return;
-
- ieee80211_tpt_led_trig_rx(local,
- ((struct ieee80211_hdr *)skb->data)->frame_control,
- skb->len);
+ if (skb) {
+ ieee80211_tpt_led_trig_rx(local,
+ ((struct ieee80211_hdr *)skb->data)->frame_control,
+ skb->len);
- __ieee80211_rx_handle_packet(hw, pubsta, skb, list);
+ __ieee80211_rx_handle_packet(hw, pubsta, skb, list);
+ }
+ kcov_remote_stop();
return;
drop:
kfree_skb(skb);
if (tx->sdata->vif.type == NL80211_IFTYPE_OCB)
return TX_CONTINUE;
- if (tx->sdata->vif.type == NL80211_IFTYPE_WDS)
- return TX_CONTINUE;
-
if (tx->flags & IEEE80211_TX_PS_BUFFERED)
return TX_CONTINUE;
info->flags |= IEEE80211_TX_CTL_NO_ACK;
if (txflags & IEEE80211_RADIOTAP_F_TX_NOSEQNO)
info->control.flags |= IEEE80211_TX_CTRL_NO_SEQNO;
+ if (txflags & IEEE80211_RADIOTAP_F_TX_ORDER)
+ info->control.flags |=
+ IEEE80211_TX_CTRL_DONT_REORDER;
break;
case IEEE80211_RADIOTAP_RATE:
payload[7]);
}
- /*
- * Initialize skb->priority for QoS frames. This is put in the TID field
- * of the frame before passing it to the driver.
+ /* Initialize skb->priority for QoS frames. If the DONT_REORDER flag
+ * is set, stick to the default value for skb->priority to assure
+ * frames injected with this flag are not reordered relative to each
+ * other.
*/
- if (ieee80211_is_data_qos(hdr->frame_control)) {
+ if (ieee80211_is_data_qos(hdr->frame_control) &&
+ !(info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER)) {
u8 *p = ieee80211_get_qos_ctl(hdr);
skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK;
}
* we handle as though they are non-injected frames.
* This code here isn't entirely correct, the local MAC address
* isn't always enough to find the interface to use; for proper
- * VLAN/WDS support we will need a different mechanism (which
- * likely isn't going to be monitor interfaces).
+ * VLAN support we have an nl80211-based mechanism.
*
* This is necessary, for example, for old hostapd versions that
* don't use nl80211-based management TX/RX.
if (!ieee80211_sdata_running(tmp_sdata))
continue;
if (tmp_sdata->vif.type == NL80211_IFTYPE_MONITOR ||
- tmp_sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
- tmp_sdata->vif.type == NL80211_IFTYPE_WDS)
+ tmp_sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
continue;
if (ether_addr_equal(tmp_sdata->vif.addr, hdr->addr2)) {
sdata = tmp_sdata;
}
sta = sta_info_get_bss(sdata, skb->data);
break;
- case NL80211_IFTYPE_WDS:
- sta = sta_info_get(sdata, sdata->u.wds.remote_addr);
- break;
#ifdef CONFIG_MAC80211_MESH
case NL80211_IFTYPE_MESH_POINT:
/* determined much later */
hdrlen = 24;
band = chanctx_conf->def.chan->band;
break;
- case NL80211_IFTYPE_WDS:
- fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS);
- /* RA TA DA SA */
- memcpy(hdr.addr1, sdata->u.wds.remote_addr, ETH_ALEN);
- memcpy(hdr.addr2, sdata->vif.addr, ETH_ALEN);
- memcpy(hdr.addr3, skb->data, ETH_ALEN);
- memcpy(hdr.addr4, skb->data + ETH_ALEN, ETH_ALEN);
- hdrlen = 30;
- /*
- * This is the exception! WDS style interfaces are prohibited
- * when channel contexts are in used so this must be valid
- */
- band = local->hw.conf.chandef.chan->band;
- break;
#ifdef CONFIG_MAC80211_MESH
case NL80211_IFTYPE_MESH_POINT:
if (!is_multicast_ether_addr(skb->data)) {
/*
* Transmit all pending packets. Called from tasklet.
*/
-void ieee80211_tx_pending(unsigned long data)
+void ieee80211_tx_pending(struct tasklet_struct *t)
{
- struct ieee80211_local *local = (struct ieee80211_local *)data;
+ struct ieee80211_local *local = from_tasklet(local, t,
+ tx_pending_tasklet);
unsigned long flags;
int i;
bool txok;
rcu_read_unlock();
}
-void ieee80211_wake_txqs(unsigned long data)
+void ieee80211_wake_txqs(struct tasklet_struct *t)
{
- struct ieee80211_local *local = (struct ieee80211_local *)data;
+ struct ieee80211_local *local = from_tasklet(local, t,
+ wake_txqs_tasklet);
unsigned long flags;
spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
return res;
}
break;
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_AP_VLAN:
case NL80211_IFTYPE_MONITOR:
case NL80211_IFTYPE_P2P_DEVICE:
case NUM_NL80211_IFTYPES:
case NL80211_IFTYPE_P2P_CLIENT:
case NL80211_IFTYPE_P2P_GO:
+ case NL80211_IFTYPE_WDS:
WARN_ON(1);
break;
}
struct ieee80211_hdr *hdr)
{
struct ieee80211_local *local = sdata->local;
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
u8 *p;
- if (local->hw.queues < IEEE80211_NUM_ACS)
+ if ((info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER) ||
+ local->hw.queues < IEEE80211_NUM_ACS)
return 0;
if (!ieee80211_is_data(hdr->frame_control)) {
u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta, struct sk_buff *skb)
{
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
struct mac80211_qos_map *qos_map;
bool qos;
else
qos = false;
- if (!qos) {
+ if (!qos || (info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER)) {
skb->priority = 0; /* required for correct WPA/11i MIC */
return IEEE80211_AC_BE;
}
case NL80211_IFTYPE_AP:
ra = skb->data;
break;
- case NL80211_IFTYPE_WDS:
- ra = sdata->u.wds.remote_addr;
- break;
case NL80211_IFTYPE_STATION:
/* might be a TDLS station */
sta = sta_info_get(sdata, skb->data);
p = ieee80211_get_qos_ctl(hdr);
+ /* don't overwrite the QoS field of injected frames */
+ if (info->flags & IEEE80211_TX_CTL_INJECTED) {
+ /* do take into account Ack policy of injected frames */
+ if (*p & IEEE80211_QOS_CTL_ACK_POLICY_NOACK)
+ info->flags |= IEEE80211_TX_CTL_NO_ACK;
+ return;
+ }
+
/* set up the first byte */
/*
#include "ieee802154_i.h"
#include "cfg.h"
-static void ieee802154_tasklet_handler(unsigned long data)
+static void ieee802154_tasklet_handler(struct tasklet_struct *t)
{
- struct ieee802154_local *local = (struct ieee802154_local *)data;
+ struct ieee802154_local *local = from_tasklet(local, t, tasklet);
struct sk_buff *skb;
while ((skb = skb_dequeue(&local->skb_queue))) {
INIT_LIST_HEAD(&local->interfaces);
mutex_init(&local->iflist_mtx);
- tasklet_init(&local->tasklet,
- ieee802154_tasklet_handler,
- (unsigned long)local);
+ tasklet_setup(&local->tasklet, ieee802154_tasklet_handler);
skb_queue_head_init(&local->skb_queue);
if (!pskb_may_pull(skb, sizeof(*hdr)))
goto err;
+ skb_dst_drop(skb);
+
/* Read and decode the label */
hdr = mpls_hdr(skb);
dec = mpls_entry_decode(hdr);
struct ctl_table_header *ctl_table_hdr;
int mptcp_enabled;
+ unsigned int add_addr_timeout;
};
static struct mptcp_pernet *mptcp_get_pernet(struct net *net)
return mptcp_get_pernet(net)->mptcp_enabled;
}
+unsigned int mptcp_get_add_addr_timeout(struct net *net)
+{
+ return mptcp_get_pernet(net)->add_addr_timeout;
+}
+
static struct ctl_table mptcp_sysctl_table[] = {
{
.procname = "enabled",
*/
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "add_addr_timeout",
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
{}
};
static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
{
pernet->mptcp_enabled = 1;
+ pernet->add_addr_timeout = TCP_RTO_MAX;
}
static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
}
table[0].data = &pernet->mptcp_enabled;
+ table[1].data = &pernet->add_addr_timeout;
hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
if (!hdr)
info->mptcpi_flags = flags;
info->mptcpi_token = READ_ONCE(msk->token);
info->mptcpi_write_seq = READ_ONCE(msk->write_seq);
- info->mptcpi_snd_una = atomic64_read(&msk->snd_una);
+ info->mptcpi_snd_una = READ_ONCE(msk->snd_una);
info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq);
unlock_sock_fast(sk, slow);
}
mp_opt->add_addr = 1;
mp_opt->addr_id = *ptr++;
- pr_debug("ADD_ADDR: id=%d, echo=%d", mp_opt->addr_id, mp_opt->echo);
+ pr_debug("ADD_ADDR%s: id=%d, echo=%d",
+ (mp_opt->family == MPTCP_ADDR_IPVERSION_6) ? "6" : "",
+ mp_opt->addr_id, mp_opt->echo);
if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) {
memcpy((u8 *)&mp_opt->addr.s_addr, (u8 *)ptr, 4);
ptr += 4;
bool ret = false;
mpext = skb ? mptcp_get_ext(skb) : NULL;
- snd_data_fin_enable = READ_ONCE(msk->snd_data_fin_enable);
+ snd_data_fin_enable = mptcp_data_fin_enabled(msk);
if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
unsigned int map_size;
opts->ext_copy.ack64 = 0;
}
opts->ext_copy.use_ack = 1;
+ WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk));
/* Add kind/length/subtype/flag overhead if mapping is not populated */
if (dss_size == 0)
}
#endif
-static bool mptcp_established_options_add_addr(struct sock *sk,
+static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *skb,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+ bool drop_other_suboptions = false;
+ unsigned int opt_size = *size;
struct mptcp_addr_info saddr;
bool echo;
int len;
+ if (mptcp_pm_should_add_signal_ipv6(msk) &&
+ skb && skb_is_tcp_pure_ack(skb)) {
+ pr_debug("drop other suboptions");
+ opts->suboptions = 0;
+ remaining += opt_size;
+ drop_other_suboptions = true;
+ }
+
if (!mptcp_pm_should_add_signal(msk) ||
!(mptcp_pm_add_addr_signal(msk, remaining, &saddr, &echo)))
return false;
return false;
*size = len;
+ if (drop_other_suboptions)
+ *size -= opt_size;
opts->addr_id = saddr.id;
if (saddr.family == AF_INET) {
opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
*size += opt_size;
remaining -= opt_size;
- if (mptcp_established_options_add_addr(sk, &opt_size, remaining, opts)) {
+ if (mptcp_established_options_add_addr(sk, skb, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
ret = true;
goto fully_established;
}
+ if (mp_opt->add_addr) {
+ WRITE_ONCE(msk->fully_established, true);
+ return true;
+ }
+
/* If the first established packet does not contain MP_CAPABLE + data
* then fallback to TCP. Fallback scenarios requires a reset for
* MP_JOIN subflows.
return cur_ack;
}
-static void update_una(struct mptcp_sock *msk,
- struct mptcp_options_received *mp_opt)
+static void ack_update_msk(struct mptcp_sock *msk,
+ struct sock *ssk,
+ struct mptcp_options_received *mp_opt)
{
- u64 new_snd_una, snd_una, old_snd_una = atomic64_read(&msk->snd_una);
- u64 write_seq = READ_ONCE(msk->write_seq);
+ u64 new_wnd_end, new_snd_una, snd_nxt = READ_ONCE(msk->snd_nxt);
+ struct sock *sk = (struct sock *)msk;
+ u64 old_snd_una;
+
+ mptcp_data_lock(sk);
/* avoid ack expansion on update conflict, to reduce the risk of
* wrongly expanding to a future ack sequence number, which is way
* more dangerous than missing an ack
*/
+ old_snd_una = msk->snd_una;
new_snd_una = expand_ack(old_snd_una, mp_opt->data_ack, mp_opt->ack64);
/* ACK for data not even sent yet? Ignore. */
- if (after64(new_snd_una, write_seq))
+ if (after64(new_snd_una, snd_nxt))
new_snd_una = old_snd_una;
- while (after64(new_snd_una, old_snd_una)) {
- snd_una = old_snd_una;
- old_snd_una = atomic64_cmpxchg(&msk->snd_una, snd_una,
- new_snd_una);
- if (old_snd_una == snd_una) {
- mptcp_data_acked((struct sock *)msk);
- break;
- }
+ new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd;
+
+ if (after64(new_wnd_end, msk->wnd_end)) {
+ msk->wnd_end = new_wnd_end;
+ __mptcp_wnd_updated(sk, ssk);
}
+
+ if (after64(new_snd_una, old_snd_una)) {
+ msk->snd_una = new_snd_una;
+ __mptcp_data_acked(sk);
+ }
+ mptcp_data_unlock(sk);
}
bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit)
struct mptcp_options_received mp_opt;
struct mptcp_ext *mpext;
- if (__mptcp_check_fallback(msk))
+ if (__mptcp_check_fallback(msk)) {
+ /* Keep it simple and unconditionally trigger send data cleanup and
+ * pending queue spooling. We will need to acquire the data lock
+ * for more accurate checks, and once the lock is acquired, such
+ * helpers are cheap.
+ */
+ mptcp_data_lock(subflow->conn);
+ if (mptcp_send_head(subflow->conn))
+ __mptcp_wnd_updated(subflow->conn, sk);
+ __mptcp_data_acked(subflow->conn);
+ mptcp_data_unlock(subflow->conn);
return;
+ }
mptcp_get_options(skb, &mp_opt);
if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
* monodirectional flows will stuck
*/
if (mp_opt.use_ack)
- update_una(msk, &mp_opt);
+ ack_update_msk(msk, sk, &mp_opt);
/* Zero-data-length packets are dropped by the caller and not
* propagated to the MPTCP layer, so the skb extension does not
}
}
-void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
+static void mptcp_set_rwin(const struct tcp_sock *tp)
+{
+ const struct sock *ssk = (const struct sock *)tp;
+ const struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk;
+ u64 ack_seq;
+
+ subflow = mptcp_subflow_ctx(ssk);
+ msk = mptcp_sk(subflow->conn);
+
+ ack_seq = READ_ONCE(msk->ack_seq) + tp->rcv_wnd;
+
+ if (after64(ack_seq, READ_ONCE(msk->rcv_wnd_sent)))
+ WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
+}
+
+void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
+ struct mptcp_out_options *opts)
{
if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
}
}
+
+ if (tp)
+ mptcp_set_rwin(tp);
}
const struct mptcp_addr_info *addr,
bool echo)
{
+ u8 add_addr = READ_ONCE(msk->pm.add_addr_signal);
+
pr_debug("msk=%p, local_id=%d", msk, addr->id);
msk->pm.local = *addr;
- WRITE_ONCE(msk->pm.add_addr_echo, echo);
- WRITE_ONCE(msk->pm.add_addr_signal, true);
+ add_addr |= BIT(MPTCP_ADD_ADDR_SIGNAL);
+ if (echo)
+ add_addr |= BIT(MPTCP_ADD_ADDR_ECHO);
+ if (addr->family == AF_INET6)
+ add_addr |= BIT(MPTCP_ADD_ADDR_IPV6);
+ WRITE_ONCE(msk->pm.add_addr_signal, add_addr);
return 0;
}
return false;
msk->pm.status |= BIT(new_status);
- if (schedule_work(&msk->work))
- sock_hold((struct sock *)msk);
+ mptcp_schedule_work((struct sock *)msk);
return true;
}
spin_lock_bh(&pm->lock);
- if (!READ_ONCE(pm->accept_addr))
+ if (!READ_ONCE(pm->accept_addr)) {
mptcp_pm_announce_addr(msk, addr, true);
- else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED))
+ mptcp_pm_add_addr_send_ack(msk);
+ } else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) {
pm->remote = *addr;
+ }
spin_unlock_bh(&pm->lock);
}
+void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk)
+{
+ if (!mptcp_pm_should_add_signal_ipv6(msk))
+ return;
+
+ mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_SEND_ACK);
+}
+
void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id)
{
struct mptcp_pm_data *pm = &msk->pm;
if (!mptcp_pm_should_add_signal(msk))
goto out_unlock;
- *echo = READ_ONCE(msk->pm.add_addr_echo);
+ *echo = mptcp_pm_should_add_signal_echo(msk);
if (remaining < mptcp_add_addr_len(msk->pm.local.family, *echo))
goto out_unlock;
*saddr = msk->pm.local;
- WRITE_ONCE(msk->pm.add_addr_signal, false);
+ WRITE_ONCE(msk->pm.add_addr_signal, 0);
ret = true;
out_unlock:
msk->pm.subflows = 0;
msk->pm.rm_id = 0;
WRITE_ONCE(msk->pm.work_pending, false);
- WRITE_ONCE(msk->pm.add_addr_signal, false);
+ WRITE_ONCE(msk->pm.add_addr_signal, 0);
WRITE_ONCE(msk->pm.rm_addr_signal, false);
WRITE_ONCE(msk->pm.accept_addr, false);
WRITE_ONCE(msk->pm.accept_subflow, false);
- WRITE_ONCE(msk->pm.add_addr_echo, false);
msk->pm.status = 0;
spin_lock_init(&msk->pm.lock);
if (!mptcp_pm_should_add_signal(msk)) {
pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id);
mptcp_pm_announce_addr(msk, &entry->addr, false);
+ mptcp_pm_add_addr_send_ack(msk);
entry->retrans_times++;
}
if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
- sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX);
+ sk_reset_timer(sk, timer,
+ jiffies + mptcp_get_add_addr_timeout(sock_net(sk)));
spin_unlock_bh(&msk->pm.lock);
{
struct mptcp_pm_add_entry *add_entry = NULL;
struct sock *sk = (struct sock *)msk;
+ struct net *net = sock_net(sk);
if (lookup_anno_list_by_saddr(msk, &entry->addr))
return false;
add_entry->retrans_times = 0;
timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
- sk_reset_timer(sk, &add_entry->add_timer, jiffies + TCP_RTO_MAX);
+ sk_reset_timer(sk, &add_entry->add_timer,
+ jiffies + mptcp_get_add_addr_timeout(net));
return true;
}
if (mptcp_pm_alloc_anno_list(msk, local)) {
msk->pm.add_addr_signaled++;
mptcp_pm_announce_addr(msk, &local->addr, false);
+ mptcp_pm_nl_add_addr_send_ack(msk);
}
} else {
/* pick failed, avoid fourther attempts later */
spin_lock_bh(&msk->pm.lock);
mptcp_pm_announce_addr(msk, &remote, true);
+ mptcp_pm_nl_add_addr_send_ack(msk);
+}
+
+void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk)
+{
+ struct mptcp_subflow_context *subflow;
+
+ if (!mptcp_pm_should_add_signal_ipv6(msk))
+ return;
+
+ __mptcp_flush_join_list(msk);
+ subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);
+ if (subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ u8 add_addr;
+
+ spin_unlock_bh(&msk->pm.lock);
+ pr_debug("send ack for add_addr6");
+ lock_sock(ssk);
+ tcp_send_ack(ssk);
+ release_sock(ssk);
+ spin_lock_bh(&msk->pm.lock);
+
+ add_addr = READ_ONCE(msk->pm.add_addr_signal);
+ add_addr &= ~BIT(MPTCP_ADD_ADDR_IPV6);
+ WRITE_ONCE(msk->pm.add_addr_signal, add_addr);
+ }
}
void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
- long timeout = 0;
if (msk->pm.rm_id != subflow->remote_id)
continue;
spin_unlock_bh(&msk->pm.lock);
mptcp_subflow_shutdown(sk, ssk, how);
- __mptcp_close_ssk(sk, ssk, subflow, timeout);
+ __mptcp_close_ssk(sk, ssk, subflow);
spin_lock_bh(&msk->pm.lock);
msk->pm.add_addr_accepted--;
list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
- long timeout = 0;
if (rm_id != subflow->local_id)
continue;
spin_unlock_bh(&msk->pm.lock);
mptcp_subflow_shutdown(sk, ssk, how);
- __mptcp_close_ssk(sk, ssk, subflow, timeout);
+ __mptcp_close_ssk(sk, ssk, subflow);
spin_lock_bh(&msk->pm.lock);
msk->pm.local_addr_used--;
#include <net/transp_v6.h>
#endif
#include <net/mptcp.h>
+#include <net/xfrm.h>
#include "protocol.h"
#include "mib.h"
static struct percpu_counter mptcp_sockets_allocated;
+static void __mptcp_destroy_sock(struct sock *sk);
+static void __mptcp_check_send_data_fin(struct sock *sk);
+
/* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not
* completed yet or has failed, return the subflow socket.
* Otherwise return NULL.
return msk->subflow;
}
+/* Returns end sequence number of the receiver's advertised window */
+static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
+{
+ return READ_ONCE(msk->wnd_end);
+}
+
static bool mptcp_is_tcpsk(struct sock *sk)
{
struct socket *sock = sk->sk_socket;
msk->subflow = ssock;
subflow = mptcp_subflow_ctx(ssock->sk);
list_add(&subflow->node, &msk->conn_list);
+ sock_hold(ssock->sk);
subflow->request_mptcp = 1;
/* accept() will wait on first subflow sk_wq, and we always wakes up
struct rb_node **p, *parent;
u64 seq, end_seq, max_seq;
struct sk_buff *skb1;
- int space;
seq = MPTCP_SKB_CB(skb)->map_seq;
end_seq = MPTCP_SKB_CB(skb)->end_seq;
- space = tcp_space(sk);
- max_seq = space > 0 ? space + msk->ack_seq : msk->ack_seq;
+ max_seq = READ_ONCE(msk->rcv_wnd_sent);
pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq,
RB_EMPTY_ROOT(&msk->out_of_order_queue));
- if (after64(seq, max_seq)) {
+ if (after64(end_seq, max_seq)) {
/* out of window */
mptcp_drop(sk, skb);
+ pr_debug("oow by %lld, rcv_wnd_sent %llu\n",
+ (unsigned long long)end_seq - (unsigned long)max_seq,
+ (unsigned long long)msk->rcv_wnd_sent);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW);
return;
}
mptcp_sk(sk)->timer_ival = 0;
}
-static void mptcp_check_data_fin_ack(struct sock *sk)
+static void mptcp_close_wake_up(struct sock *sk)
+{
+ if (sock_flag(sk, SOCK_DEAD))
+ return;
+
+ sk->sk_state_change(sk);
+ if (sk->sk_shutdown == SHUTDOWN_MASK ||
+ sk->sk_state == TCP_CLOSE)
+ sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
+ else
+ sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+}
+
+static bool mptcp_pending_data_fin_ack(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- if (__mptcp_check_fallback(msk))
- return;
+ return !__mptcp_check_fallback(msk) &&
+ ((1 << sk->sk_state) &
+ (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
+ msk->write_seq == READ_ONCE(msk->snd_una);
+}
+
+static void mptcp_check_data_fin_ack(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
/* Look for an acknowledged DATA_FIN */
- if (((1 << sk->sk_state) &
- (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
- msk->write_seq == atomic64_read(&msk->snd_una)) {
+ if (mptcp_pending_data_fin_ack(sk)) {
mptcp_stop_timer(sk);
WRITE_ONCE(msk->snd_data_fin_enable, 0);
switch (sk->sk_state) {
case TCP_FIN_WAIT1:
inet_sk_state_store(sk, TCP_FIN_WAIT2);
- sk->sk_state_change(sk);
break;
case TCP_CLOSING:
case TCP_LAST_ACK:
inet_sk_state_store(sk, TCP_CLOSE);
- sk->sk_state_change(sk);
break;
}
- if (sk->sk_shutdown == SHUTDOWN_MASK ||
- sk->sk_state == TCP_CLOSE)
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
- else
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+ mptcp_close_wake_up(sk);
}
}
mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN;
}
-static void mptcp_check_data_fin(struct sock *sk)
+static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
+{
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ /* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
+ if (subflow->request_join && !subflow->fully_established)
+ return false;
+
+ /* only send if our side has not closed yet */
+ return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
+}
+
+static bool tcp_can_send_ack(const struct sock *ssk)
+{
+ return !((1 << inet_sk_state_load(ssk)) &
+ (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE));
+}
+
+static void mptcp_send_ack(struct mptcp_sock *msk)
+{
+ struct mptcp_subflow_context *subflow;
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ lock_sock(ssk);
+ if (tcp_can_send_ack(ssk))
+ tcp_send_ack(ssk);
+ release_sock(ssk);
+ }
+}
+
+static bool mptcp_subflow_cleanup_rbuf(struct sock *ssk)
+{
+ int ret;
+
+ lock_sock(ssk);
+ ret = tcp_can_send_ack(ssk);
+ if (ret)
+ tcp_cleanup_rbuf(ssk, 1);
+ release_sock(ssk);
+ return ret;
+}
+
+static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)
+{
+ struct sock *ack_hint = READ_ONCE(msk->ack_hint);
+ struct mptcp_subflow_context *subflow;
+
+ /* if the hinted ssk is still active, try to use it */
+ if (likely(ack_hint)) {
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ if (ack_hint == ssk && mptcp_subflow_cleanup_rbuf(ssk))
+ return;
+ }
+ }
+
+ /* otherwise pick the first active subflow */
+ mptcp_for_each_subflow(msk, subflow)
+ if (mptcp_subflow_cleanup_rbuf(mptcp_subflow_tcp_sock(subflow)))
+ return;
+}
+
+static bool mptcp_check_data_fin(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
u64 rcv_data_fin_seq;
+ bool ret = false;
if (__mptcp_check_fallback(msk) || !msk->first)
- return;
+ return ret;
/* Need to ack a DATA_FIN received from a peer while this side
* of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2.
*/
if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) {
- struct mptcp_subflow_context *subflow;
-
WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1);
WRITE_ONCE(msk->rcv_data_fin, 0);
break;
case TCP_FIN_WAIT2:
inet_sk_state_store(sk, TCP_CLOSE);
- // @@ Close subflows now?
break;
default:
/* Other states not expected */
break;
}
+ ret = true;
mptcp_set_timeout(sk, NULL);
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
- lock_sock(ssk);
- tcp_send_ack(ssk);
- release_sock(ssk);
- }
-
- sk->sk_state_change(sk);
-
- if (sk->sk_shutdown == SHUTDOWN_MASK ||
- sk->sk_state == TCP_CLOSE)
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
- else
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+ mptcp_send_ack(msk);
+ mptcp_close_wake_up(sk);
}
+ return ret;
}
static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
unsigned int moved = 0;
bool more_data_avail;
struct tcp_sock *tp;
- u32 old_copied_seq;
bool done = false;
+ int sk_rbuf;
+
+ sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
+
+ if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+ int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
+
+ if (unlikely(ssk_rbuf > sk_rbuf)) {
+ WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf);
+ sk_rbuf = ssk_rbuf;
+ }
+ }
pr_debug("msk=%p ssk=%p", msk, ssk);
tp = tcp_sk(ssk);
- old_copied_seq = tp->copied_seq;
do {
u32 map_remaining, offset;
u32 seq = tp->copied_seq;
WRITE_ONCE(tp->copied_seq, seq);
more_data_avail = mptcp_subflow_data_available(ssk);
- if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) {
+ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) {
done = true;
break;
}
} while (more_data_avail);
+ WRITE_ONCE(msk->ack_hint, ssk);
*bytes += moved;
- if (tp->copied_seq != old_copied_seq)
- tcp_cleanup_rbuf(ssk, 1);
-
return done;
}
-static bool mptcp_ofo_queue(struct mptcp_sock *msk)
+static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
{
struct sock *sk = (struct sock *)msk;
struct sk_buff *skb, *tail;
/* In most cases we will be able to lock the mptcp socket. If its already
* owned, we need to defer to the work queue to avoid ABBA deadlock.
*/
-static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
+static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
{
struct sock *sk = (struct sock *)msk;
unsigned int moved = 0;
- if (READ_ONCE(sk->sk_lock.owned))
- return false;
-
- if (unlikely(!spin_trylock_bh(&sk->sk_lock.slock)))
- return false;
-
- /* must re-check after taking the lock */
- if (!READ_ONCE(sk->sk_lock.owned)) {
- __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
- mptcp_ofo_queue(msk);
+ if (inet_sk_state_load(sk) == TCP_CLOSE)
+ return;
- /* If the moves have caught up with the DATA_FIN sequence number
- * it's time to ack the DATA_FIN and change socket state, but
- * this is not a good place to change state. Let the workqueue
- * do it.
- */
- if (mptcp_pending_data_fin(sk, NULL) &&
- schedule_work(&msk->work))
- sock_hold(sk);
- }
+ mptcp_data_lock(sk);
- spin_unlock_bh(&sk->sk_lock.slock);
+ __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
+ __mptcp_ofo_queue(msk);
- return moved > 0;
+ /* If the moves have caught up with the DATA_FIN sequence number
+ * it's time to ack the DATA_FIN and change socket state, but
+ * this is not a good place to change state. Let the workqueue
+ * do it.
+ */
+ if (mptcp_pending_data_fin(sk, NULL))
+ mptcp_schedule_work(sk);
+ mptcp_data_unlock(sk);
}
void mptcp_data_ready(struct sock *sk, struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct mptcp_sock *msk = mptcp_sk(sk);
+ int sk_rbuf, ssk_rbuf;
bool wake;
/* move_skbs_to_msk below can legitly clear the data_avail flag,
if (wake)
set_bit(MPTCP_DATA_READY, &msk->flags);
- if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) &&
- move_skbs_to_msk(msk, ssk))
- goto wake;
+ ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
+ sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
+ if (unlikely(ssk_rbuf > sk_rbuf))
+ sk_rbuf = ssk_rbuf;
- /* don't schedule if mptcp sk is (still) over limit */
- if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf))
+ /* over limit? can't append more skbs to msk */
+ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
goto wake;
- /* mptcp socket is owned, release_cb should retry */
- if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED,
- &sk->sk_tsq_flags)) {
- sock_hold(sk);
+ move_skbs_to_msk(msk, ssk);
- /* need to try again, its possible release_cb() has already
- * been called after the test_and_set_bit() above.
- */
- move_skbs_to_msk(msk, ssk);
- }
wake:
if (wake)
sk->sk_data_ready(sk);
}
-static void __mptcp_flush_join_list(struct mptcp_sock *msk)
+void __mptcp_flush_join_list(struct mptcp_sock *msk)
{
if (likely(list_empty(&msk->join_list)))
return;
struct inet_connection_sock *icsk = inet_csk(sk);
unsigned long tout;
+ /* prevent rescheduling on close */
+ if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE))
+ return;
+
/* should never be called with mptcp level timer cleared */
tout = READ_ONCE(mptcp_sk(sk)->timer_ival);
if (WARN_ON_ONCE(!tout))
sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + tout);
}
-void mptcp_data_acked(struct sock *sk)
+bool mptcp_schedule_work(struct sock *sk)
{
- mptcp_reset_timer(sk);
-
- if ((!test_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags) ||
- (inet_sk_state_load(sk) != TCP_ESTABLISHED)) &&
- schedule_work(&mptcp_sk(sk)->work))
+ if (inet_sk_state_load(sk) != TCP_CLOSE &&
+ schedule_work(&mptcp_sk(sk)->work)) {
+ /* each subflow already holds a reference to the sk, and the
+ * workqueue is invoked by a subflow, so sk can't go away here.
+ */
sock_hold(sk);
+ return true;
+ }
+ return false;
}
void mptcp_subflow_eof(struct sock *sk)
{
- struct mptcp_sock *msk = mptcp_sk(sk);
-
- if (!test_and_set_bit(MPTCP_WORK_EOF, &msk->flags) &&
- schedule_work(&msk->work))
- sock_hold(sk);
+ if (!test_and_set_bit(MPTCP_WORK_EOF, &mptcp_sk(sk)->flags))
+ mptcp_schedule_work(sk);
}
static void mptcp_check_for_eof(struct mptcp_sock *msk)
mptcp_for_each_subflow(msk, subflow)
receivers += !subflow->rx_eof;
+ if (receivers)
+ return;
- if (!receivers && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
+ if (!(sk->sk_shutdown & RCV_SHUTDOWN)) {
/* hopefully temporary hack: propagate shutdown status
* to msk, when all subflows agree on it
*/
set_bit(MPTCP_DATA_READY, &msk->flags);
sk->sk_data_ready(sk);
}
-}
-static bool mptcp_ext_cache_refill(struct mptcp_sock *msk)
-{
- const struct sock *sk = (const struct sock *)msk;
-
- if (!msk->cached_ext)
- msk->cached_ext = __skb_ext_alloc(sk->sk_allocation);
-
- return !!msk->cached_ext;
+ switch (sk->sk_state) {
+ case TCP_ESTABLISHED:
+ inet_sk_state_store(sk, TCP_CLOSE_WAIT);
+ break;
+ case TCP_FIN_WAIT1:
+ inet_sk_state_store(sk, TCP_CLOSING);
+ break;
+ case TCP_FIN_WAIT2:
+ inet_sk_state_store(sk, TCP_CLOSE);
+ break;
+ default:
+ return;
+ }
+ mptcp_close_wake_up(sk);
}
static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk)
if (!tcp_skb_can_collapse_to(skb))
return false;
- /* can collapse only if MPTCP level sequence is in order */
- return mpext && mpext->data_seq + mpext->data_len == write_seq;
+ /* can collapse only if MPTCP level sequence is in order and this
+ * mapping has not been xmitted yet
+ */
+ return mpext && mpext->data_seq + mpext->data_len == write_seq &&
+ !mpext->frozen;
}
static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
const struct mptcp_data_frag *df)
{
return df && pfrag->page == df->page &&
+ pfrag->size - pfrag->offset > 0 &&
df->data_seq + df->data_len == msk->write_seq;
}
+static int mptcp_wmem_with_overhead(struct sock *sk, int size)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ int ret, skbs;
+
+ ret = size + ((sizeof(struct mptcp_data_frag) * size) >> PAGE_SHIFT);
+ skbs = (msk->tx_pending_data + size) / msk->size_goal_cache;
+ if (skbs < msk->skb_tx_cache.qlen)
+ return ret;
+
+ return ret + (skbs - msk->skb_tx_cache.qlen) * SKB_TRUESIZE(MAX_TCP_HEADER);
+}
+
+static void __mptcp_wmem_reserve(struct sock *sk, int size)
+{
+ int amount = mptcp_wmem_with_overhead(sk, size);
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ WARN_ON_ONCE(msk->wmem_reserved);
+ if (amount <= sk->sk_forward_alloc)
+ goto reserve;
+
+ /* under memory pressure try to reserve at most a single page
+ * otherwise try to reserve the full estimate and fallback
+ * to a single page before entering the error path
+ */
+ if ((tcp_under_memory_pressure(sk) && amount > PAGE_SIZE) ||
+ !sk_wmem_schedule(sk, amount)) {
+ if (amount <= PAGE_SIZE)
+ goto nomem;
+
+ amount = PAGE_SIZE;
+ if (!sk_wmem_schedule(sk, amount))
+ goto nomem;
+ }
+
+reserve:
+ msk->wmem_reserved = amount;
+ sk->sk_forward_alloc -= amount;
+ return;
+
+nomem:
+ /* we will wait for memory on next allocation */
+ msk->wmem_reserved = -1;
+}
+
+static void __mptcp_update_wmem(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ if (!msk->wmem_reserved)
+ return;
+
+ if (msk->wmem_reserved < 0)
+ msk->wmem_reserved = 0;
+ if (msk->wmem_reserved > 0) {
+ sk->sk_forward_alloc += msk->wmem_reserved;
+ msk->wmem_reserved = 0;
+ }
+}
+
+static bool mptcp_wmem_alloc(struct sock *sk, int size)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ /* check for pre-existing error condition */
+ if (msk->wmem_reserved < 0)
+ return false;
+
+ if (msk->wmem_reserved >= size)
+ goto account;
+
+ mptcp_data_lock(sk);
+ if (!sk_wmem_schedule(sk, size)) {
+ mptcp_data_unlock(sk);
+ return false;
+ }
+
+ sk->sk_forward_alloc -= size;
+ msk->wmem_reserved += size;
+ mptcp_data_unlock(sk);
+
+account:
+ msk->wmem_reserved -= size;
+ return true;
+}
+
+static void mptcp_wmem_uncharge(struct sock *sk, int size)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ if (msk->wmem_reserved < 0)
+ msk->wmem_reserved = 0;
+ msk->wmem_reserved += size;
+}
+
+static void mptcp_mem_reclaim_partial(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ /* if we are experiencing a transint allocation error,
+ * the forward allocation memory has been already
+ * released
+ */
+ if (msk->wmem_reserved < 0)
+ return;
+
+ mptcp_data_lock(sk);
+ sk->sk_forward_alloc += msk->wmem_reserved;
+ sk_mem_reclaim_partial(sk);
+ msk->wmem_reserved = sk->sk_forward_alloc;
+ sk->sk_forward_alloc = 0;
+ mptcp_data_unlock(sk);
+}
+
static void dfrag_uncharge(struct sock *sk, int len)
{
sk_mem_uncharge(sk, len);
put_page(dfrag->page);
}
-static bool mptcp_is_writeable(struct mptcp_sock *msk)
-{
- struct mptcp_subflow_context *subflow;
-
- if (!sk_stream_is_writeable((struct sock *)msk))
- return false;
-
- mptcp_for_each_subflow(msk, subflow) {
- if (sk_stream_is_writeable(subflow->tcp_sock))
- return true;
- }
- return false;
-}
-
-static void mptcp_clean_una(struct sock *sk)
+static void __mptcp_clean_una(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
struct mptcp_data_frag *dtmp, *dfrag;
* plain TCP
*/
if (__mptcp_check_fallback(msk))
- atomic64_set(&msk->snd_una, msk->write_seq);
- snd_una = atomic64_read(&msk->snd_una);
+ msk->snd_una = READ_ONCE(msk->snd_nxt);
+ snd_una = msk->snd_una;
list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) {
if (after64(dfrag->data_seq + dfrag->data_len, snd_una))
break;
+ if (WARN_ON_ONCE(dfrag == msk->first_pending))
+ break;
dfrag_clear(sk, dfrag);
cleaned = true;
}
if (dfrag && after64(snd_una, dfrag->data_seq)) {
u64 delta = snd_una - dfrag->data_seq;
- if (WARN_ON_ONCE(delta > dfrag->data_len))
+ if (WARN_ON_ONCE(delta > dfrag->already_sent))
goto out;
dfrag->data_seq += delta;
dfrag->offset += delta;
dfrag->data_len -= delta;
+ dfrag->already_sent -= delta;
dfrag_uncharge(sk, delta);
cleaned = true;
out:
if (cleaned) {
- sk_mem_reclaim_partial(sk);
-
- /* Only wake up writers if a subflow is ready */
- if (mptcp_is_writeable(msk)) {
- set_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags);
- smp_mb__after_atomic();
+ if (tcp_under_memory_pressure(sk)) {
+ __mptcp_update_wmem(sk);
+ sk_mem_reclaim_partial(sk);
+ }
- /* set SEND_SPACE before sk_stream_write_space clears
- * NOSPACE
- */
- sk_stream_write_space(sk);
+ if (sk_stream_is_writeable(sk)) {
+ /* pairs with memory barrier in mptcp_poll */
+ smp_mb();
+ if (test_and_clear_bit(MPTCP_NOSPACE, &msk->flags))
+ sk_stream_write_space(sk);
}
}
+
+ if (snd_una == READ_ONCE(msk->snd_nxt)) {
+ if (msk->timer_ival)
+ mptcp_stop_timer(sk);
+ } else {
+ mptcp_reset_timer(sk);
+ }
+}
+
+static void mptcp_enter_memory_pressure(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ bool first = true;
+
+ sk_stream_moderate_sndbuf(sk);
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ if (first)
+ tcp_enter_memory_pressure(ssk);
+ sk_stream_moderate_sndbuf(ssk);
+ first = false;
+ }
}
/* ensure we get enough memory for the frag hdr, beyond some minimal amount of
pfrag, sk->sk_allocation)))
return true;
- sk->sk_prot->enter_memory_pressure(sk);
- sk_stream_moderate_sndbuf(sk);
+ mptcp_enter_memory_pressure(sk);
return false;
}
dfrag->data_seq = msk->write_seq;
dfrag->overhead = offset - orig_offset + sizeof(struct mptcp_data_frag);
dfrag->offset = offset + sizeof(struct mptcp_data_frag);
+ dfrag->already_sent = 0;
dfrag->page = pfrag->page;
return dfrag;
}
+struct mptcp_sendmsg_info {
+ int mss_now;
+ int size_goal;
+ u16 limit;
+ u16 sent;
+ unsigned int flags;
+};
+
+static int mptcp_check_allowed_size(struct mptcp_sock *msk, u64 data_seq,
+ int avail_size)
+{
+ u64 window_end = mptcp_wnd_end(msk);
+
+ if (__mptcp_check_fallback(msk))
+ return avail_size;
+
+ if (!before64(data_seq + avail_size, window_end)) {
+ u64 allowed_size = window_end - data_seq;
+
+ return min_t(unsigned int, allowed_size, avail_size);
+ }
+
+ return avail_size;
+}
+
+static bool __mptcp_add_ext(struct sk_buff *skb, gfp_t gfp)
+{
+ struct skb_ext *mpext = __skb_ext_alloc(gfp);
+
+ if (!mpext)
+ return false;
+ __skb_ext_set(skb, SKB_EXT_MPTCP, mpext);
+ return true;
+}
+
+static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp)
+{
+ struct sk_buff *skb;
+
+ skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp);
+ if (likely(skb)) {
+ if (likely(__mptcp_add_ext(skb, gfp))) {
+ skb_reserve(skb, MAX_TCP_HEADER);
+ skb->reserved_tailroom = skb->end - skb->tail;
+ return skb;
+ }
+ __kfree_skb(skb);
+ } else {
+ mptcp_enter_memory_pressure(sk);
+ }
+ return NULL;
+}
+
+static bool mptcp_tx_cache_refill(struct sock *sk, int size,
+ struct sk_buff_head *skbs, int *total_ts)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct sk_buff *skb;
+ int space_needed;
+
+ if (unlikely(tcp_under_memory_pressure(sk))) {
+ mptcp_mem_reclaim_partial(sk);
+
+ /* under pressure pre-allocate at most a single skb */
+ if (msk->skb_tx_cache.qlen)
+ return true;
+ space_needed = msk->size_goal_cache;
+ } else {
+ space_needed = msk->tx_pending_data + size -
+ msk->skb_tx_cache.qlen * msk->size_goal_cache;
+ }
+
+ while (space_needed > 0) {
+ skb = __mptcp_do_alloc_tx_skb(sk, sk->sk_allocation);
+ if (unlikely(!skb)) {
+ /* under memory pressure, try to pass the caller a
+ * single skb to allow forward progress
+ */
+ while (skbs->qlen > 1) {
+ skb = __skb_dequeue_tail(skbs);
+ __kfree_skb(skb);
+ }
+ return skbs->qlen > 0;
+ }
+
+ *total_ts += skb->truesize;
+ __skb_queue_tail(skbs, skb);
+ space_needed -= msk->size_goal_cache;
+ }
+ return true;
+}
+
+static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct sk_buff *skb;
+
+ if (ssk->sk_tx_skb_cache) {
+ skb = ssk->sk_tx_skb_cache;
+ if (unlikely(!skb_ext_find(skb, SKB_EXT_MPTCP) &&
+ !__mptcp_add_ext(skb, gfp)))
+ return false;
+ return true;
+ }
+
+ skb = skb_peek(&msk->skb_tx_cache);
+ if (skb) {
+ if (likely(sk_wmem_schedule(ssk, skb->truesize))) {
+ skb = __skb_dequeue(&msk->skb_tx_cache);
+ if (WARN_ON_ONCE(!skb))
+ return false;
+
+ mptcp_wmem_uncharge(sk, skb->truesize);
+ ssk->sk_tx_skb_cache = skb;
+ return true;
+ }
+
+ /* over memory limit, no point to try to allocate a new skb */
+ return false;
+ }
+
+ skb = __mptcp_do_alloc_tx_skb(sk, gfp);
+ if (!skb)
+ return false;
+
+ if (likely(sk_wmem_schedule(ssk, skb->truesize))) {
+ ssk->sk_tx_skb_cache = skb;
+ return true;
+ }
+ kfree_skb(skb);
+ return false;
+}
+
+static bool mptcp_must_reclaim_memory(struct sock *sk, struct sock *ssk)
+{
+ return !ssk->sk_tx_skb_cache &&
+ !skb_peek(&mptcp_sk(sk)->skb_tx_cache) &&
+ tcp_under_memory_pressure(sk);
+}
+
+static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk)
+{
+ if (unlikely(mptcp_must_reclaim_memory(sk, ssk)))
+ mptcp_mem_reclaim_partial(sk);
+ return __mptcp_alloc_tx_skb(sk, ssk, sk->sk_allocation);
+}
+
static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
- struct msghdr *msg, struct mptcp_data_frag *dfrag,
- long *timeo, int *pmss_now,
- int *ps_goal)
+ struct mptcp_data_frag *dfrag,
+ struct mptcp_sendmsg_info *info)
{
- int mss_now, avail_size, size_goal, offset, ret, frag_truesize = 0;
- bool dfrag_collapsed, can_collapse = false;
+ u64 data_seq = dfrag->data_seq + info->sent;
struct mptcp_sock *msk = mptcp_sk(sk);
+ bool zero_window_probe = false;
struct mptcp_ext *mpext = NULL;
- bool retransmission = !!dfrag;
struct sk_buff *skb, *tail;
- struct page_frag *pfrag;
- struct page *page;
- u64 *write_seq;
- size_t psize;
-
- /* use the mptcp page cache so that we can easily move the data
- * from one substream to another, but do per subflow memory accounting
- * Note: pfrag is used only !retransmission, but the compiler if
- * fooled into a warning if we don't init here
- */
- pfrag = sk_page_frag(sk);
- if (!retransmission) {
- write_seq = &msk->write_seq;
- page = pfrag->page;
- } else {
- write_seq = &dfrag->data_seq;
- page = dfrag->page;
- }
+ bool can_collapse = false;
+ int avail_size;
+ size_t ret = 0;
- /* compute copy limit */
- mss_now = tcp_send_mss(ssk, &size_goal, msg->msg_flags);
- *pmss_now = mss_now;
- *ps_goal = size_goal;
- avail_size = size_goal;
+ pr_debug("msk=%p ssk=%p sending dfrag at seq=%lld len=%d already sent=%d",
+ msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent);
+
+ /* compute send limit */
+ info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
+ avail_size = info->size_goal;
+ msk->size_goal_cache = info->size_goal;
skb = tcp_write_queue_tail(ssk);
if (skb) {
- mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
-
/* Limit the write to the size available in the
* current skb, if any, so that we create at most a new skb.
* Explicitly tells TCP internals to avoid collapsing on later
* queue management operation, to avoid breaking the ext <->
* SSN association set here
*/
- can_collapse = (size_goal - skb->len > 0) &&
- mptcp_skb_can_collapse_to(*write_seq, skb, mpext);
+ mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
+ can_collapse = (info->size_goal - skb->len > 0) &&
+ mptcp_skb_can_collapse_to(data_seq, skb, mpext);
if (!can_collapse)
TCP_SKB_CB(skb)->eor = 1;
else
- avail_size = size_goal - skb->len;
+ avail_size = info->size_goal - skb->len;
}
- if (!retransmission) {
- /* reuse tail pfrag, if possible, or carve a new one from the
- * page allocator
- */
- dfrag = mptcp_rtx_tail(sk);
- offset = pfrag->offset;
- dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
- if (!dfrag_collapsed) {
- dfrag = mptcp_carve_data_frag(msk, pfrag, offset);
- offset = dfrag->offset;
- frag_truesize = dfrag->overhead;
- }
- psize = min_t(size_t, pfrag->size - offset, avail_size);
-
- /* Copy to page */
- pr_debug("left=%zu", msg_data_left(msg));
- psize = copy_page_from_iter(pfrag->page, offset,
- min_t(size_t, msg_data_left(msg),
- psize),
- &msg->msg_iter);
- pr_debug("left=%zu", msg_data_left(msg));
- if (!psize)
- return -EINVAL;
-
- if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) {
- iov_iter_revert(&msg->msg_iter, psize);
- return -ENOMEM;
- }
- } else {
- offset = dfrag->offset;
- psize = min_t(size_t, dfrag->data_len, avail_size);
- }
+ /* Zero window and all data acked? Probe. */
+ avail_size = mptcp_check_allowed_size(msk, data_seq, avail_size);
+ if (avail_size == 0) {
+ u64 snd_una = READ_ONCE(msk->snd_una);
- /* tell the TCP stack to delay the push so that we can safely
- * access the skb after the sendpages call
- */
- ret = do_tcp_sendpages(ssk, page, offset, psize,
- msg->msg_flags | MSG_SENDPAGE_NOTLAST | MSG_DONTWAIT);
- if (ret <= 0) {
- if (!retransmission)
- iov_iter_revert(&msg->msg_iter, psize);
- return ret;
+ if (skb || snd_una != msk->snd_nxt)
+ return 0;
+ zero_window_probe = true;
+ data_seq = snd_una - 1;
+ avail_size = 1;
}
- frag_truesize += ret;
- if (!retransmission) {
- if (unlikely(ret < psize))
- iov_iter_revert(&msg->msg_iter, psize - ret);
+ if (WARN_ON_ONCE(info->sent > info->limit ||
+ info->limit > dfrag->data_len))
+ return 0;
- /* send successful, keep track of sent data for mptcp-level
- * retransmission
- */
- dfrag->data_len += ret;
- if (!dfrag_collapsed) {
- get_page(dfrag->page);
- list_add_tail(&dfrag->list, &msk->rtx_queue);
- sk_wmem_queued_add(sk, frag_truesize);
- } else {
- sk_wmem_queued_add(sk, ret);
- }
-
- /* charge data on mptcp rtx queue to the master socket
- * Note: we charge such data both to sk and ssk
- */
- sk->sk_forward_alloc -= frag_truesize;
+ ret = info->limit - info->sent;
+ tail = tcp_build_frag(ssk, avail_size, info->flags, dfrag->page,
+ dfrag->offset + info->sent, &ret);
+ if (!tail) {
+ tcp_remove_empty_skb(sk, tcp_write_queue_tail(ssk));
+ return -ENOMEM;
}
- /* if the tail skb extension is still the cached one, collapsing
- * really happened. Note: we can't check for 'same skb' as the sk_buff
- * hdr on tail can be transmitted, freed and re-allocated by the
- * do_tcp_sendpages() call
+ /* if the tail skb is still the cached one, collapsing really happened.
*/
- tail = tcp_write_queue_tail(ssk);
- if (mpext && tail && mpext == skb_ext_find(tail, SKB_EXT_MPTCP)) {
+ if (skb == tail) {
WARN_ON_ONCE(!can_collapse);
mpext->data_len += ret;
+ WARN_ON_ONCE(zero_window_probe);
goto out;
}
- skb = tcp_write_queue_tail(ssk);
- mpext = __skb_ext_set(skb, SKB_EXT_MPTCP, msk->cached_ext);
- msk->cached_ext = NULL;
+ mpext = skb_ext_find(tail, SKB_EXT_MPTCP);
+ if (WARN_ON_ONCE(!mpext)) {
+ /* should never reach here, stream corrupted */
+ return -EINVAL;
+ }
memset(mpext, 0, sizeof(*mpext));
- mpext->data_seq = *write_seq;
+ mpext->data_seq = data_seq;
mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq;
mpext->data_len = ret;
mpext->use_map = 1;
mpext->data_seq, mpext->subflow_seq, mpext->data_len,
mpext->dsn64);
+ if (zero_window_probe) {
+ mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
+ mpext->frozen = 1;
+ ret = 0;
+ tcp_push_pending_frames(ssk);
+ }
out:
- if (!retransmission)
- pfrag->offset += frag_truesize;
- WRITE_ONCE(*write_seq, *write_seq + ret);
mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
-
return ret;
}
-static void mptcp_nospace(struct mptcp_sock *msk)
-{
- struct mptcp_subflow_context *subflow;
-
- clear_bit(MPTCP_SEND_SPACE, &msk->flags);
- smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */
-
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- struct socket *sock = READ_ONCE(ssk->sk_socket);
-
- /* enables ssk->write_space() callbacks */
- if (sock)
- set_bit(SOCK_NOSPACE, &sock->flags);
- }
-}
-
-static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
-{
- struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
- /* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
- if (subflow->request_join && !subflow->fully_established)
- return false;
-
- /* only send if our side has not closed yet */
- return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
-}
-
#define MPTCP_SEND_BURST_SIZE ((1 << 16) - \
sizeof(struct tcphdr) - \
MAX_TCP_OPTION_SPACE - \
sock_owned_by_me((struct sock *)msk);
*sndbuf = 0;
- if (!mptcp_ext_cache_refill(msk))
- return NULL;
-
if (__mptcp_check_fallback(msk)) {
if (!msk->first)
return NULL;
return NULL;
}
-static void ssk_check_wmem(struct mptcp_sock *msk)
+static void mptcp_push_release(struct sock *sk, struct sock *ssk,
+ struct mptcp_sendmsg_info *info)
+{
+ mptcp_set_timeout(sk, ssk);
+ tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal);
+ release_sock(ssk);
+}
+
+static void mptcp_push_pending(struct sock *sk, unsigned int flags)
+{
+ struct sock *prev_ssk = NULL, *ssk = NULL;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct mptcp_sendmsg_info info = {
+ .flags = flags,
+ };
+ struct mptcp_data_frag *dfrag;
+ int len, copied = 0;
+ u32 sndbuf;
+
+ while ((dfrag = mptcp_send_head(sk))) {
+ info.sent = dfrag->already_sent;
+ info.limit = dfrag->data_len;
+ len = dfrag->data_len - dfrag->already_sent;
+ while (len > 0) {
+ int ret = 0;
+
+ prev_ssk = ssk;
+ __mptcp_flush_join_list(msk);
+ ssk = mptcp_subflow_get_send(msk, &sndbuf);
+
+ /* do auto tuning */
+ if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
+ sndbuf > READ_ONCE(sk->sk_sndbuf))
+ WRITE_ONCE(sk->sk_sndbuf, sndbuf);
+
+ /* try to keep the subflow socket lock across
+ * consecutive xmit on the same socket
+ */
+ if (ssk != prev_ssk && prev_ssk)
+ mptcp_push_release(sk, prev_ssk, &info);
+ if (!ssk)
+ goto out;
+
+ if (ssk != prev_ssk || !prev_ssk)
+ lock_sock(ssk);
+
+ /* keep it simple and always provide a new skb for the
+ * subflow, even if we will not use it when collapsing
+ * on the pending one
+ */
+ if (!mptcp_alloc_tx_skb(sk, ssk)) {
+ mptcp_push_release(sk, ssk, &info);
+ goto out;
+ }
+
+ ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+ if (ret <= 0) {
+ mptcp_push_release(sk, ssk, &info);
+ goto out;
+ }
+
+ info.sent += ret;
+ dfrag->already_sent += ret;
+ msk->snd_nxt += ret;
+ msk->snd_burst -= ret;
+ msk->tx_pending_data -= ret;
+ copied += ret;
+ len -= ret;
+ }
+ WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+ }
+
+ /* at this point we held the socket lock for the last subflow we used */
+ if (ssk)
+ mptcp_push_release(sk, ssk, &info);
+
+out:
+ if (copied) {
+ /* start the timer, if it's not pending */
+ if (!mptcp_timer_pending(sk))
+ mptcp_reset_timer(sk);
+ __mptcp_check_send_data_fin(sk);
+ }
+}
+
+static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
{
- if (unlikely(!mptcp_is_writeable(msk)))
- mptcp_nospace(msk);
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct mptcp_sendmsg_info info;
+ struct mptcp_data_frag *dfrag;
+ int len, copied = 0;
+
+ info.flags = 0;
+ while ((dfrag = mptcp_send_head(sk))) {
+ info.sent = dfrag->already_sent;
+ info.limit = dfrag->data_len;
+ len = dfrag->data_len - dfrag->already_sent;
+ while (len > 0) {
+ int ret = 0;
+
+ /* do auto tuning */
+ if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
+ ssk->sk_sndbuf > READ_ONCE(sk->sk_sndbuf))
+ WRITE_ONCE(sk->sk_sndbuf, ssk->sk_sndbuf);
+
+ if (unlikely(mptcp_must_reclaim_memory(sk, ssk))) {
+ __mptcp_update_wmem(sk);
+ sk_mem_reclaim_partial(sk);
+ }
+ if (!__mptcp_alloc_tx_skb(sk, ssk, GFP_ATOMIC))
+ goto out;
+
+ ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+ if (ret <= 0)
+ goto out;
+
+ info.sent += ret;
+ dfrag->already_sent += ret;
+ msk->snd_nxt += ret;
+ msk->snd_burst -= ret;
+ msk->tx_pending_data -= ret;
+ copied += ret;
+ len -= ret;
+ }
+ WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+ }
+
+out:
+ /* __mptcp_alloc_tx_skb could have released some wmem and we are
+ * not going to flush it via release_sock()
+ */
+ __mptcp_update_wmem(sk);
+ if (copied) {
+ mptcp_set_timeout(sk, ssk);
+ tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+ info.size_goal);
+ if (msk->snd_data_fin_enable &&
+ msk->snd_nxt + 1 == msk->write_seq)
+ mptcp_schedule_work(sk);
+ }
}
static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
- int mss_now = 0, size_goal = 0, ret = 0;
struct mptcp_sock *msk = mptcp_sk(sk);
struct page_frag *pfrag;
size_t copied = 0;
- struct sock *ssk;
- u32 sndbuf;
- bool tx_ok;
+ int ret = 0;
long timeo;
if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
return -EOPNOTSUPP;
- lock_sock(sk);
+ mptcp_lock_sock(sk, __mptcp_wmem_reserve(sk, len));
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
}
pfrag = sk_page_frag(sk);
-restart:
- mptcp_clean_una(sk);
- if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) {
- ret = -EPIPE;
- goto out;
- }
+ while (msg_data_left(msg)) {
+ int total_ts, frag_truesize = 0;
+ struct mptcp_data_frag *dfrag;
+ struct sk_buff_head skbs;
+ bool dfrag_collapsed;
+ size_t psize, offset;
- __mptcp_flush_join_list(msk);
- ssk = mptcp_subflow_get_send(msk, &sndbuf);
- while (!sk_stream_memory_free(sk) ||
- !ssk ||
- !mptcp_page_frag_refill(ssk, pfrag)) {
- if (ssk) {
- /* make sure retransmit timer is
- * running before we wait for memory.
- *
- * The retransmit timer might be needed
- * to make the peer send an up-to-date
- * MPTCP Ack.
- */
- mptcp_set_timeout(sk, ssk);
- if (!mptcp_timer_pending(sk))
- mptcp_reset_timer(sk);
- }
-
- mptcp_nospace(msk);
- ret = sk_stream_wait_memory(sk, &timeo);
- if (ret)
- goto out;
-
- mptcp_clean_una(sk);
-
- ssk = mptcp_subflow_get_send(msk, &sndbuf);
- if (list_empty(&msk->conn_list)) {
- ret = -ENOTCONN;
+ if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) {
+ ret = -EPIPE;
goto out;
}
- }
- /* do auto tuning */
- if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
- sndbuf > READ_ONCE(sk->sk_sndbuf))
- WRITE_ONCE(sk->sk_sndbuf, sndbuf);
+ /* reuse tail pfrag, if possible, or carve a new one from the
+ * page allocator
+ */
+ dfrag = mptcp_pending_tail(sk);
+ dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
+ if (!dfrag_collapsed) {
+ if (!sk_stream_memory_free(sk))
+ goto wait_for_memory;
- pr_debug("conn_list->subflow=%p", ssk);
+ if (!mptcp_page_frag_refill(sk, pfrag))
+ goto wait_for_memory;
- lock_sock(ssk);
- tx_ok = msg_data_left(msg);
- while (tx_ok) {
- ret = mptcp_sendmsg_frag(sk, ssk, msg, NULL, &timeo, &mss_now,
- &size_goal);
- if (ret < 0) {
- if (ret == -EAGAIN && timeo > 0) {
- mptcp_set_timeout(sk, ssk);
- release_sock(ssk);
- goto restart;
- }
- break;
+ dfrag = mptcp_carve_data_frag(msk, pfrag, pfrag->offset);
+ frag_truesize = dfrag->overhead;
}
- /* burst can be negative, we will try move to the next subflow
- * at selection time, if possible.
+ /* we do not bound vs wspace, to allow a single packet.
+ * memory accounting will prevent execessive memory usage
+ * anyway
*/
- msk->snd_burst -= ret;
- copied += ret;
-
- tx_ok = msg_data_left(msg);
- if (!tx_ok)
- break;
+ offset = dfrag->offset + dfrag->data_len;
+ psize = pfrag->size - offset;
+ psize = min_t(size_t, psize, msg_data_left(msg));
+ total_ts = psize + frag_truesize;
+ __skb_queue_head_init(&skbs);
+ if (!mptcp_tx_cache_refill(sk, psize, &skbs, &total_ts))
+ goto wait_for_memory;
+
+ if (!mptcp_wmem_alloc(sk, total_ts)) {
+ __skb_queue_purge(&skbs);
+ goto wait_for_memory;
+ }
- if (!sk_stream_memory_free(ssk) ||
- !mptcp_page_frag_refill(ssk, pfrag) ||
- !mptcp_ext_cache_refill(msk)) {
- tcp_push(ssk, msg->msg_flags, mss_now,
- tcp_sk(ssk)->nonagle, size_goal);
- mptcp_set_timeout(sk, ssk);
- release_sock(ssk);
- goto restart;
+ skb_queue_splice_tail(&skbs, &msk->skb_tx_cache);
+ if (copy_page_from_iter(dfrag->page, offset, psize,
+ &msg->msg_iter) != psize) {
+ mptcp_wmem_uncharge(sk, psize + frag_truesize);
+ ret = -EFAULT;
+ goto out;
}
- /* memory is charged to mptcp level socket as well, i.e.
- * if msg is very large, mptcp socket may run out of buffer
- * space. mptcp_clean_una() will release data that has
- * been acked at mptcp level in the mean time, so there is
- * a good chance we can continue sending data right away.
- *
- * Normally, when the tcp subflow can accept more data, then
- * so can the MPTCP socket. However, we need to cope with
- * peers that might lag behind in their MPTCP-level
- * acknowledgements, i.e. data might have been acked at
- * tcp level only. So, we must also check the MPTCP socket
- * limits before we send more data.
+ /* data successfully copied into the write queue */
+ copied += psize;
+ dfrag->data_len += psize;
+ frag_truesize += psize;
+ pfrag->offset += frag_truesize;
+ WRITE_ONCE(msk->write_seq, msk->write_seq + psize);
+
+ /* charge data on mptcp pending queue to the msk socket
+ * Note: we charge such data both to sk and ssk
*/
- if (unlikely(!sk_stream_memory_free(sk))) {
- tcp_push(ssk, msg->msg_flags, mss_now,
- tcp_sk(ssk)->nonagle, size_goal);
- mptcp_clean_una(sk);
- if (!sk_stream_memory_free(sk)) {
- /* can't send more for now, need to wait for
- * MPTCP-level ACKs from peer.
- *
- * Wakeup will happen via mptcp_clean_una().
- */
- mptcp_set_timeout(sk, ssk);
- release_sock(ssk);
- goto restart;
- }
+ sk_wmem_queued_add(sk, frag_truesize);
+ if (!dfrag_collapsed) {
+ get_page(dfrag->page);
+ list_add_tail(&dfrag->list, &msk->rtx_queue);
+ if (!msk->first_pending)
+ WRITE_ONCE(msk->first_pending, dfrag);
}
+ pr_debug("msk=%p dfrag at seq=%lld len=%d sent=%d new=%d", msk,
+ dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
+ !dfrag_collapsed);
+
+ continue;
+
+wait_for_memory:
+ set_bit(MPTCP_NOSPACE, &msk->flags);
+ mptcp_push_pending(sk, msg->msg_flags);
+ ret = sk_stream_wait_memory(sk, &timeo);
+ if (ret)
+ goto out;
}
- mptcp_set_timeout(sk, ssk);
if (copied) {
- tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle,
- size_goal);
-
- /* start the timer, if it's not pending */
- if (!mptcp_timer_pending(sk))
- mptcp_reset_timer(sk);
+ msk->tx_pending_data += copied;
+ mptcp_push_pending(sk, msg->msg_flags);
}
- release_sock(ssk);
out:
- ssk_check_wmem(msk);
release_sock(sk);
return copied ? : ret;
}
struct msghdr *msg,
size_t len)
{
- struct sock *sk = (struct sock *)msk;
struct sk_buff *skb;
int copied = 0;
- while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
+ while ((skb = skb_peek(&msk->receive_queue)) != NULL) {
u32 offset = MPTCP_SKB_CB(skb)->offset;
u32 data_len = skb->len - offset;
u32 count = min_t(size_t, len - copied, data_len);
break;
}
- __skb_unlink(skb, &sk->sk_receive_queue);
+ /* we will bulk release the skb memory later */
+ skb->destructor = NULL;
+ msk->rmem_released += skb->truesize;
+ __skb_unlink(skb, &msk->receive_queue);
__kfree_skb(skb);
if (copied >= len)
msk->rcvq_space.time = mstamp;
}
-static bool __mptcp_move_skbs(struct mptcp_sock *msk)
+static void __mptcp_update_rmem(struct sock *sk)
{
- unsigned int moved = 0;
- bool done;
+ struct mptcp_sock *msk = mptcp_sk(sk);
- /* avoid looping forever below on racing close */
- if (((struct sock *)msk)->sk_state == TCP_CLOSE)
- return false;
+ if (!msk->rmem_released)
+ return;
+
+ atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc);
+ sk_mem_uncharge(sk, msk->rmem_released);
+ msk->rmem_released = 0;
+}
+
+static void __mptcp_splice_receive_queue(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ skb_queue_splice_tail_init(&sk->sk_receive_queue, &msk->receive_queue);
+}
+
+static bool __mptcp_move_skbs(struct mptcp_sock *msk, unsigned int rcv)
+{
+ struct sock *sk = (struct sock *)msk;
+ unsigned int moved = 0;
+ bool ret, done;
__mptcp_flush_join_list(msk);
do {
struct sock *ssk = mptcp_subflow_recv_lookup(msk);
+ bool slowpath;
- if (!ssk)
+ /* we can have data pending in the subflows only if the msk
+ * receive buffer was full at subflow_data_ready() time,
+ * that is an unlikely slow path.
+ */
+ if (likely(!ssk))
break;
- lock_sock(ssk);
+ slowpath = lock_sock_fast(ssk);
+ mptcp_data_lock(sk);
done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
- release_sock(ssk);
+ mptcp_data_unlock(sk);
+ if (moved && rcv) {
+ WRITE_ONCE(msk->rmem_pending, min(rcv, moved));
+ tcp_cleanup_rbuf(ssk, 1);
+ WRITE_ONCE(msk->rmem_pending, 0);
+ }
+ unlock_sock_fast(ssk, slowpath);
} while (!done);
- if (mptcp_ofo_queue(msk) || moved > 0) {
- mptcp_check_data_fin((struct sock *)msk);
- return true;
+ /* acquire the data lock only if some input data is pending */
+ ret = moved > 0;
+ if (!RB_EMPTY_ROOT(&msk->out_of_order_queue) ||
+ !skb_queue_empty_lockless(&sk->sk_receive_queue)) {
+ mptcp_data_lock(sk);
+ __mptcp_update_rmem(sk);
+ ret |= __mptcp_ofo_queue(msk);
+ __mptcp_splice_receive_queue(sk);
+ mptcp_data_unlock(sk);
}
- return false;
+ if (ret)
+ mptcp_check_data_fin((struct sock *)msk);
+ return !skb_queue_empty(&msk->receive_queue);
}
static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
if (msg->msg_flags & ~(MSG_WAITALL | MSG_DONTWAIT))
return -EOPNOTSUPP;
- lock_sock(sk);
+ mptcp_lock_sock(sk, __mptcp_splice_receive_queue(sk));
+ if (unlikely(sk->sk_state == TCP_LISTEN)) {
+ copied = -ENOTCONN;
+ goto out_err;
+ }
+
timeo = sock_rcvtimeo(sk, nonblock);
len = min_t(size_t, len, INT_MAX);
target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
- __mptcp_flush_join_list(msk);
- while (len > (size_t)copied) {
- int bytes_read;
+ while (copied < len) {
+ int bytes_read, old_space;
bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied);
if (unlikely(bytes_read < 0)) {
copied += bytes_read;
- if (skb_queue_empty(&sk->sk_receive_queue) &&
- __mptcp_move_skbs(msk))
+ if (skb_queue_empty(&msk->receive_queue) &&
+ __mptcp_move_skbs(msk, len - copied))
continue;
+ /* be sure to advertise window change */
+ old_space = READ_ONCE(msk->old_wspace);
+ if ((tcp_space(sk) - old_space) >= old_space)
+ mptcp_cleanup_rbuf(msk);
+
/* only the master socket status is relevant here. The exit
* conditions mirror closely tcp_recvmsg()
*/
if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
mptcp_check_for_eof(msk);
- if (sk->sk_shutdown & RCV_SHUTDOWN)
+ if (sk->sk_shutdown & RCV_SHUTDOWN) {
+ /* race breaker: the shutdown could be after the
+ * previous receive queue check
+ */
+ if (__mptcp_move_skbs(msk, len - copied))
+ continue;
break;
+ }
if (sk->sk_state == TCP_CLOSE) {
copied = -ENOTCONN;
mptcp_wait_data(sk, &timeo);
}
- if (skb_queue_empty(&sk->sk_receive_queue)) {
+ if (skb_queue_empty_lockless(&sk->sk_receive_queue) &&
+ skb_queue_empty(&msk->receive_queue)) {
/* entire backlog drained, clear DATA_READY. */
clear_bit(MPTCP_DATA_READY, &msk->flags);
/* .. race-breaker: ssk might have gotten new data
* after last __mptcp_move_skbs() returned false.
*/
- if (unlikely(__mptcp_move_skbs(msk)))
+ if (unlikely(__mptcp_move_skbs(msk, 0)))
set_bit(MPTCP_DATA_READY, &msk->flags);
} else if (unlikely(!test_bit(MPTCP_DATA_READY, &msk->flags))) {
/* data to read but mptcp_wait_data() cleared DATA_READY */
out_err:
pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d",
msk, test_bit(MPTCP_DATA_READY, &msk->flags),
- skb_queue_empty(&sk->sk_receive_queue), copied);
+ skb_queue_empty_lockless(&sk->sk_receive_queue), copied);
mptcp_rcv_space_adjust(msk, copied);
release_sock(sk);
{
struct mptcp_sock *msk = mptcp_sk(sk);
- if (atomic64_read(&msk->snd_una) == READ_ONCE(msk->write_seq)) {
- mptcp_stop_timer(sk);
- } else {
- set_bit(MPTCP_WORK_RTX, &msk->flags);
- if (schedule_work(&msk->work))
- sock_hold(sk);
- }
+ set_bit(MPTCP_WORK_RTX, &msk->flags);
+ mptcp_schedule_work(sk);
}
static void mptcp_retransmit_timer(struct timer_list *t)
sock_put(sk);
}
+static void mptcp_timeout_timer(struct timer_list *t)
+{
+ struct sock *sk = from_timer(sk, t, sk_timer);
+
+ mptcp_schedule_work(sk);
+ sock_put(sk);
+}
+
/* Find an idle subflow. Return NULL if there is unacked data at tcp
* level.
*
sock_owned_by_me((const struct sock *)msk);
if (__mptcp_check_fallback(msk))
- return msk->first;
+ return NULL;
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
continue;
/* still data outstanding at TCP level? Don't retransmit. */
- if (!tcp_write_queue_empty(ssk))
+ if (!tcp_write_queue_empty(ssk)) {
+ if (inet_csk(ssk)->icsk_ca_state >= TCP_CA_Loss)
+ continue;
return NULL;
+ }
if (subflow->backup) {
if (!backup)
* parent socket.
*/
void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
- struct mptcp_subflow_context *subflow,
- long timeout)
+ struct mptcp_subflow_context *subflow)
{
- struct socket *sock = READ_ONCE(ssk->sk_socket);
+ bool dispose_socket = false;
+ struct socket *sock;
list_del(&subflow->node);
- if (sock && sock != sk->sk_socket) {
- /* outgoing subflow */
- sock_release(sock);
+ lock_sock(ssk);
+
+ /* if we are invoked by the msk cleanup code, the subflow is
+ * already orphaned
+ */
+ sock = ssk->sk_socket;
+ if (sock) {
+ dispose_socket = sock != sk->sk_socket;
+ sock_orphan(ssk);
+ }
+
+ /* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops
+ * the ssk has been already destroyed, we just need to release the
+ * reference owned by msk;
+ */
+ if (!inet_csk(ssk)->icsk_ulp_ops) {
+ kfree_rcu(subflow, rcu);
} else {
- /* incoming subflow */
- tcp_close(ssk, timeout);
+ /* otherwise ask tcp do dispose of ssk and subflow ctx */
+ subflow->disposable = 1;
+ __tcp_close(ssk, 0);
+
+ /* close acquired an extra ref */
+ __sock_put(ssk);
}
+ release_sock(ssk);
+ if (dispose_socket)
+ iput(SOCK_INODE(sock));
+
+ sock_put(ssk);
}
static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
mptcp_pm_nl_add_addr_received(msk);
}
+ if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) {
+ pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK);
+ mptcp_pm_nl_add_addr_send_ack(msk);
+ }
if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {
pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);
mptcp_pm_nl_rm_addr_received(msk);
if (inet_sk_state_load(ssk) != TCP_CLOSE)
continue;
- __mptcp_close_ssk((struct sock *)msk, ssk, subflow, 0);
+ __mptcp_close_ssk((struct sock *)msk, ssk, subflow);
+ }
+}
+
+static bool mptcp_check_close_timeout(const struct sock *sk)
+{
+ s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp;
+ struct mptcp_subflow_context *subflow;
+
+ if (delta >= TCP_TIMEWAIT_LEN)
+ return true;
+
+ /* if all subflows are in closed status don't bother with additional
+ * timeout
+ */
+ mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
+ if (inet_sk_state_load(mptcp_subflow_tcp_sock(subflow)) !=
+ TCP_CLOSE)
+ return false;
}
+ return true;
}
static void mptcp_worker(struct work_struct *work)
{
struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
struct sock *ssk, *sk = &msk->sk.icsk_inet.sk;
- int orig_len, orig_offset, mss_now = 0, size_goal = 0;
+ struct mptcp_sendmsg_info info = {};
struct mptcp_data_frag *dfrag;
- u64 orig_write_seq;
size_t copied = 0;
- struct msghdr msg = {
- .msg_flags = MSG_DONTWAIT,
- };
- long timeo = 0;
+ int state, ret;
lock_sock(sk);
- mptcp_clean_una(sk);
+ state = sk->sk_state;
+ if (unlikely(state == TCP_CLOSE))
+ goto unlock;
+
mptcp_check_data_fin_ack(sk);
__mptcp_flush_join_list(msk);
if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
__mptcp_close_subflow(msk);
- __mptcp_move_skbs(msk);
-
if (msk->pm.status)
pm_work(msk);
if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
mptcp_check_for_eof(msk);
+ __mptcp_check_send_data_fin(sk);
mptcp_check_data_fin(sk);
+ /* if the msk data is completely acked, or the socket timedout,
+ * there is no point in keeping around an orphaned sk
+ */
+ if (sock_flag(sk, SOCK_DEAD) &&
+ (mptcp_check_close_timeout(sk) ||
+ (state != sk->sk_state &&
+ ((1 << inet_sk_state_load(sk)) & (TCPF_CLOSE | TCPF_FIN_WAIT2))))) {
+ inet_sk_state_store(sk, TCP_CLOSE);
+ __mptcp_destroy_sock(sk);
+ goto unlock;
+ }
+
if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
goto unlock;
if (!dfrag)
goto unlock;
- if (!mptcp_ext_cache_refill(msk))
- goto reset_unlock;
-
ssk = mptcp_subflow_get_retrans(msk);
if (!ssk)
goto reset_unlock;
lock_sock(ssk);
- orig_len = dfrag->data_len;
- orig_offset = dfrag->offset;
- orig_write_seq = dfrag->data_seq;
- while (dfrag->data_len > 0) {
- int ret = mptcp_sendmsg_frag(sk, ssk, &msg, dfrag, &timeo,
- &mss_now, &size_goal);
- if (ret < 0)
+ /* limit retransmission to the bytes already sent on some subflows */
+ info.sent = 0;
+ info.limit = dfrag->already_sent;
+ while (info.sent < dfrag->already_sent) {
+ if (!mptcp_alloc_tx_skb(sk, ssk))
+ break;
+
+ ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+ if (ret <= 0)
break;
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
copied += ret;
- dfrag->data_len -= ret;
- dfrag->offset += ret;
-
- if (!mptcp_ext_cache_refill(msk))
- break;
+ info.sent += ret;
}
if (copied)
- tcp_push(ssk, msg.msg_flags, mss_now, tcp_sk(ssk)->nonagle,
- size_goal);
-
- dfrag->data_seq = orig_write_seq;
- dfrag->offset = orig_offset;
- dfrag->data_len = orig_len;
+ tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+ info.size_goal);
mptcp_set_timeout(sk, ssk);
release_sock(ssk);
INIT_LIST_HEAD(&msk->conn_list);
INIT_LIST_HEAD(&msk->join_list);
INIT_LIST_HEAD(&msk->rtx_queue);
- __set_bit(MPTCP_SEND_SPACE, &msk->flags);
INIT_WORK(&msk->work, mptcp_worker);
+ __skb_queue_head_init(&msk->receive_queue);
+ __skb_queue_head_init(&msk->skb_tx_cache);
msk->out_of_order_queue = RB_ROOT;
+ msk->first_pending = NULL;
+ msk->wmem_reserved = 0;
+ msk->rmem_released = 0;
+ msk->tx_pending_data = 0;
+ msk->size_goal_cache = TCP_BASE_MSS;
+ msk->ack_hint = NULL;
msk->first = NULL;
inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
/* re-use the csk retrans timer for MPTCP-level retrans */
timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
-
+ timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
return 0;
}
{
struct mptcp_sock *msk = mptcp_sk(sk);
struct mptcp_data_frag *dtmp, *dfrag;
+ struct sk_buff *skb;
- sk_stop_timer(sk, &msk->sk.icsk_retransmit_timer);
-
+ WRITE_ONCE(msk->first_pending, NULL);
list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list)
dfrag_clear(sk, dfrag);
+ while ((skb = __skb_dequeue(&msk->skb_tx_cache)) != NULL) {
+ sk->sk_forward_alloc += skb->truesize;
+ kfree_skb(skb);
+ }
}
static void mptcp_cancel_work(struct sock *sk)
struct mptcp_sock *msk = mptcp_sk(sk);
if (cancel_work_sync(&msk->work))
- sock_put(sk);
+ __sock_put(sk);
}
void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
return next & TCP_ACTION_FIN;
}
-static void mptcp_close(struct sock *sk, long timeout)
+static void __mptcp_check_send_data_fin(struct sock *sk)
{
- struct mptcp_subflow_context *subflow, *tmp;
+ struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
- LIST_HEAD(conn_list);
- lock_sock(sk);
- sk->sk_shutdown = SHUTDOWN_MASK;
+ pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu",
+ msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk),
+ msk->snd_nxt, msk->write_seq);
- if (sk->sk_state == TCP_LISTEN) {
- inet_sk_state_store(sk, TCP_CLOSE);
- goto cleanup;
- } else if (sk->sk_state == TCP_CLOSE) {
- goto cleanup;
- }
+ /* we still need to enqueue subflows or not really shutting down,
+ * skip this
+ */
+ if (!msk->snd_data_fin_enable || msk->snd_nxt + 1 != msk->write_seq ||
+ mptcp_send_head(sk))
+ return;
+ WRITE_ONCE(msk->snd_nxt, msk->write_seq);
+
+ /* fallback socket will not get data_fin/ack, can move to the next
+ * state now
+ */
if (__mptcp_check_fallback(msk)) {
- goto update_state;
- } else if (mptcp_close_state(sk)) {
- pr_debug("Sending DATA_FIN sk=%p", sk);
- WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
- WRITE_ONCE(msk->snd_data_fin_enable, 1);
+ if ((1 << sk->sk_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) {
+ inet_sk_state_store(sk, TCP_CLOSE);
+ mptcp_close_wake_up(sk);
+ } else if (sk->sk_state == TCP_FIN_WAIT1) {
+ inet_sk_state_store(sk, TCP_FIN_WAIT2);
+ }
+ }
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
+ __mptcp_flush_join_list(msk);
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
- mptcp_subflow_shutdown(sk, tcp_sk, SHUTDOWN_MASK);
- }
+ mptcp_subflow_shutdown(sk, tcp_sk, SEND_SHUTDOWN);
}
+}
- sk_stream_wait_close(sk, timeout);
+static void __mptcp_wr_shutdown(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
-update_state:
- inet_sk_state_store(sk, TCP_CLOSE);
+ pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d",
+ msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state,
+ !!mptcp_send_head(sk));
+
+ /* will be ignored by fallback sockets */
+ WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
+ WRITE_ONCE(msk->snd_data_fin_enable, 1);
+
+ __mptcp_check_send_data_fin(sk);
+}
+
+static void __mptcp_destroy_sock(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow, *tmp;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ LIST_HEAD(conn_list);
+
+ pr_debug("msk=%p", msk);
-cleanup:
/* be sure to always acquire the join list lock, to sync vs
* mptcp_finish_join().
*/
spin_unlock_bh(&msk->join_list_lock);
list_splice_init(&msk->conn_list, &conn_list);
- __mptcp_clear_xmit(sk);
-
- release_sock(sk);
+ sk_stop_timer(sk, &msk->sk.icsk_retransmit_timer);
+ sk_stop_timer(sk, &sk->sk_timer);
+ msk->pm.status = 0;
list_for_each_entry_safe(subflow, tmp, &conn_list, node) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- __mptcp_close_ssk(sk, ssk, subflow, timeout);
+ __mptcp_close_ssk(sk, ssk, subflow);
+ }
+
+ sk->sk_prot->destroy(sk);
+
+ WARN_ON_ONCE(msk->wmem_reserved);
+ WARN_ON_ONCE(msk->rmem_released);
+ sk_stream_kill_queues(sk);
+ xfrm_sk_free_policy(sk);
+ sk_refcnt_debug_release(sk);
+ sock_put(sk);
+}
+
+static void mptcp_close(struct sock *sk, long timeout)
+{
+ struct mptcp_subflow_context *subflow;
+ bool do_cancel_work = false;
+
+ lock_sock(sk);
+ sk->sk_shutdown = SHUTDOWN_MASK;
+
+ if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
+ inet_sk_state_store(sk, TCP_CLOSE);
+ goto cleanup;
}
- mptcp_cancel_work(sk);
+ if (mptcp_close_state(sk))
+ __mptcp_wr_shutdown(sk);
+
+ sk_stream_wait_close(sk, timeout);
+
+cleanup:
+ /* orphan all the subflows */
+ inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
+ list_for_each_entry(subflow, &mptcp_sk(sk)->conn_list, node) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow, dispose_socket;
+ struct socket *sock;
+
+ slow = lock_sock_fast(ssk);
+ sock = ssk->sk_socket;
+ dispose_socket = sock && sock != sk->sk_socket;
+ sock_orphan(ssk);
+ unlock_sock_fast(ssk, slow);
- __skb_queue_purge(&sk->sk_receive_queue);
+ /* for the outgoing subflows we additionally need to free
+ * the associated socket
+ */
+ if (dispose_socket)
+ iput(SOCK_INODE(sock));
+ }
+ sock_orphan(sk);
- sk_common_release(sk);
+ sock_hold(sk);
+ pr_debug("msk=%p state=%d", sk, sk->sk_state);
+ if (sk->sk_state == TCP_CLOSE) {
+ __mptcp_destroy_sock(sk);
+ do_cancel_work = true;
+ } else {
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + TCP_TIMEWAIT_LEN);
+ }
+ release_sock(sk);
+ if (do_cancel_work)
+ mptcp_cancel_work(sk);
+ sock_put(sk);
}
static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
WRITE_ONCE(msk->fully_established, false);
msk->write_seq = subflow_req->idsn + 1;
- atomic64_set(&msk->snd_una, msk->write_seq);
+ msk->snd_nxt = msk->write_seq;
+ msk->snd_una = msk->write_seq;
+ msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
+
if (mp_opt->mp_capable) {
msk->can_ack = true;
msk->remote_key = mp_opt->sndr_key;
mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq);
ack_seq++;
WRITE_ONCE(msk->ack_seq, ack_seq);
+ WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
}
sock_reset_flag(nsk, SOCK_RCU_FREE);
TCP_INIT_CWND * tp->advmss);
if (msk->rcvq_space.space == 0)
msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
+
+ WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
}
static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
if (sk_is_mptcp(newsk)) {
struct mptcp_subflow_context *subflow;
struct sock *new_mptcp_sock;
- struct sock *ssk = newsk;
subflow = mptcp_subflow_ctx(newsk);
new_mptcp_sock = subflow->conn;
/* acquire the 2nd reference for the owning socket */
sock_hold(new_mptcp_sock);
-
- local_bh_disable();
- bh_lock_sock(new_mptcp_sock);
- msk = mptcp_sk(new_mptcp_sock);
- msk->first = newsk;
-
newsk = new_mptcp_sock;
- mptcp_copy_inaddrs(newsk, ssk);
- list_add(&subflow->node, &msk->conn_list);
-
- mptcp_rcv_space_init(msk, ssk);
- bh_unlock_sock(new_mptcp_sock);
-
- __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
- local_bh_enable();
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
} else {
MPTCP_INC_STATS(sock_net(sk),
MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
void mptcp_destroy_common(struct mptcp_sock *msk)
{
+ struct sock *sk = (struct sock *)msk;
+
+ __mptcp_clear_xmit(sk);
+
+ /* move to sk_receive_queue, sk_stream_kill_queues will purge it */
+ skb_queue_splice_tail_init(&msk->receive_queue, &sk->sk_receive_queue);
+
skb_rbtree_purge(&msk->out_of_order_queue);
mptcp_token_destroy(msk);
mptcp_pm_free_anno_list(msk);
{
struct mptcp_sock *msk = mptcp_sk(sk);
- if (msk->cached_ext)
- __skb_ext_put(msk->cached_ext);
-
mptcp_destroy_common(msk);
sk_sockets_allocated_dec(sk);
}
return -EOPNOTSUPP;
}
-#define MPTCP_DEFERRED_ALL (TCPF_DELACK_TIMER_DEFERRED | \
- TCPF_WRITE_TIMER_DEFERRED)
+void __mptcp_data_acked(struct sock *sk)
+{
+ if (!sock_owned_by_user(sk))
+ __mptcp_clean_una(sk);
+ else
+ set_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags);
+
+ if (mptcp_pending_data_fin_ack(sk))
+ mptcp_schedule_work(sk);
+}
+
+void __mptcp_wnd_updated(struct sock *sk, struct sock *ssk)
+{
+ if (!mptcp_send_head(sk))
+ return;
-/* this is very alike tcp_release_cb() but we must handle differently a
- * different set of events
- */
+ if (!sock_owned_by_user(sk))
+ __mptcp_subflow_push_pending(sk, ssk);
+ else
+ set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags);
+}
+
+#define MPTCP_DEFERRED_ALL (TCPF_WRITE_TIMER_DEFERRED)
+
+/* processes deferred events and flush wmem */
static void mptcp_release_cb(struct sock *sk)
{
unsigned long flags, nflags;
+ /* push_pending may touch wmem_reserved, do it before the later
+ * cleanup
+ */
+ if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags))
+ __mptcp_clean_una(sk);
+ if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags)) {
+ /* mptcp_push_pending() acquires the subflow socket lock
+ *
+ * 1) can't be invoked in atomic scope
+ * 2) must avoid ABBA deadlock with msk socket spinlock: the RX
+ * datapath acquires the msk socket spinlock while helding
+ * the subflow socket lock
+ */
+
+ spin_unlock_bh(&sk->sk_lock.slock);
+ mptcp_push_pending(sk, 0);
+ spin_lock_bh(&sk->sk_lock.slock);
+ }
+
+ /* clear any wmem reservation and errors */
+ __mptcp_update_wmem(sk);
+ __mptcp_update_rmem(sk);
+
do {
flags = sk->sk_tsq_flags;
if (!(flags & MPTCP_DEFERRED_ALL))
sock_release_ownership(sk);
- if (flags & TCPF_DELACK_TIMER_DEFERRED) {
- struct mptcp_sock *msk = mptcp_sk(sk);
- struct sock *ssk;
-
- ssk = mptcp_subflow_recv_lookup(msk);
- if (!ssk || !schedule_work(&msk->work))
- __sock_put(sk);
- }
-
if (flags & TCPF_WRITE_TIMER_DEFERRED) {
mptcp_retransmit_handler(sk);
__sock_put(sk);
WRITE_ONCE(msk->remote_key, subflow->remote_key);
WRITE_ONCE(msk->local_key, subflow->local_key);
WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
+ WRITE_ONCE(msk->snd_nxt, msk->write_seq);
WRITE_ONCE(msk->ack_seq, ack_seq);
+ WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
WRITE_ONCE(msk->can_ack, 1);
- atomic64_set(&msk->snd_una, msk->write_seq);
+ WRITE_ONCE(msk->snd_una, msk->write_seq);
mptcp_pm_new_connection(msk, 0);
write_unlock_bh(&sk->sk_callback_lock);
}
-bool mptcp_finish_join(struct sock *sk)
+bool mptcp_finish_join(struct sock *ssk)
{
- struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
struct sock *parent = (void *)msk;
struct socket *parent_sock;
/* active connections are already on conn_list, and we can't acquire
* msk lock here.
* use the join list lock as synchronization point and double-check
- * msk status to avoid racing with mptcp_close()
+ * msk status to avoid racing with __mptcp_destroy_sock()
*/
spin_lock_bh(&msk->join_list_lock);
ret = inet_sk_state_load(parent) == TCP_ESTABLISHED;
- if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node)))
+ if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node))) {
list_add_tail(&subflow->node, &msk->join_list);
+ sock_hold(ssk);
+ }
spin_unlock_bh(&msk->join_list_lock);
if (!ret)
return false;
* at close time
*/
parent_sock = READ_ONCE(parent->sk_socket);
- if (parent_sock && !sk->sk_socket)
- mptcp_sock_graft(sk, parent_sock);
+ if (parent_sock && !ssk->sk_socket)
+ mptcp_sock_graft(ssk, parent_sock);
subflow->map_seq = READ_ONCE(msk->ack_seq);
return true;
}
-static bool mptcp_memory_free(const struct sock *sk, int wake)
-{
- struct mptcp_sock *msk = mptcp_sk(sk);
-
- return wake ? test_bit(MPTCP_SEND_SPACE, &msk->flags) : true;
-}
-
static struct proto mptcp_prot = {
.name = "MPTCP",
.owner = THIS_MODULE,
.sockets_allocated = &mptcp_sockets_allocated,
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
- .stream_memory_free = mptcp_memory_free,
.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem),
.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem),
.sysctl_mem = sysctl_tcp_mem,
if (err == 0 && !mptcp_is_tcpsk(newsock->sk)) {
struct mptcp_sock *msk = mptcp_sk(newsock->sk);
struct mptcp_subflow_context *subflow;
+ struct sock *newsk = newsock->sk;
+ bool slowpath;
+
+ slowpath = lock_sock_fast(newsk);
+ mptcp_copy_inaddrs(newsk, msk->first);
+ mptcp_rcv_space_init(msk, msk->first);
/* set ssk->sk_socket of accept()ed flows to mptcp socket.
* This is needed so NOSPACE flag can be set from tcp stack.
if (!ssk->sk_socket)
mptcp_sock_graft(ssk, newsock);
}
+ unlock_sock_fast(newsk, slowpath);
}
if (inet_csk_listen_poll(ssock->sk))
0;
}
+static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
+{
+ struct sock *sk = (struct sock *)msk;
+
+ if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN))
+ return 0;
+
+ if (sk_stream_is_writeable(sk))
+ return EPOLLOUT | EPOLLWRNORM;
+
+ set_bit(MPTCP_NOSPACE, &msk->flags);
+ smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */
+ if (sk_stream_is_writeable(sk))
+ return EPOLLOUT | EPOLLWRNORM;
+
+ return 0;
+}
+
static __poll_t mptcp_poll(struct file *file, struct socket *sock,
struct poll_table_struct *wait)
{
if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
mask |= mptcp_check_readable(msk);
- if (test_bit(MPTCP_SEND_SPACE, &msk->flags))
- mask |= EPOLLOUT | EPOLLWRNORM;
+ mask |= mptcp_check_writeable(msk);
}
if (sk->sk_shutdown & RCV_SHUTDOWN)
mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
static int mptcp_shutdown(struct socket *sock, int how)
{
struct mptcp_sock *msk = mptcp_sk(sock->sk);
- struct mptcp_subflow_context *subflow;
+ struct sock *sk = sock->sk;
int ret = 0;
pr_debug("sk=%p, how=%d", msk, how);
- lock_sock(sock->sk);
+ lock_sock(sk);
how++;
if ((how & ~SHUTDOWN_MASK) || !how) {
}
if (sock->state == SS_CONNECTING) {
- if ((1 << sock->sk->sk_state) &
+ if ((1 << sk->sk_state) &
(TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
sock->state = SS_DISCONNECTING;
else
sock->state = SS_CONNECTED;
}
- /* If we've already sent a FIN, or it's a closed state, skip this. */
- if (__mptcp_check_fallback(msk)) {
- if (how == SHUT_WR || how == SHUT_RDWR)
- inet_sk_state_store(sock->sk, TCP_FIN_WAIT1);
-
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
-
- mptcp_subflow_shutdown(sock->sk, tcp_sk, how);
- }
- } else if ((how & SEND_SHUTDOWN) &&
- ((1 << sock->sk->sk_state) &
- (TCPF_ESTABLISHED | TCPF_SYN_SENT |
- TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) &&
- mptcp_close_state(sock->sk)) {
- __mptcp_flush_join_list(msk);
-
- WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
- WRITE_ONCE(msk->snd_data_fin_enable, 1);
-
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
-
- mptcp_subflow_shutdown(sock->sk, tcp_sk, how);
- }
- }
+ sk->sk_shutdown |= how;
+ if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
+ __mptcp_wr_shutdown(sk);
/* Wake up anyone sleeping in poll. */
- sock->sk->sk_state_change(sock->sk);
+ sk->sk_state_change(sk);
out_unlock:
- release_sock(sock->sk);
+ release_sock(sk);
return ret;
}
/* MPTCP socket flags */
#define MPTCP_DATA_READY 0
-#define MPTCP_SEND_SPACE 1
+#define MPTCP_NOSPACE 1
#define MPTCP_WORK_RTX 2
#define MPTCP_WORK_EOF 3
#define MPTCP_FALLBACK_DONE 4
#define MPTCP_WORK_CLOSE_SUBFLOW 5
+#define MPTCP_PUSH_PENDING 6
+#define MPTCP_CLEAN_UNA 7
+
+static inline bool before64(__u64 seq1, __u64 seq2)
+{
+ return (__s64)(seq1 - seq2) < 0;
+}
+
+#define after64(seq2, seq1) before64(seq1, seq2)
struct mptcp_options_received {
u64 sndr_key;
enum mptcp_pm_status {
MPTCP_PM_ADD_ADDR_RECEIVED,
+ MPTCP_PM_ADD_ADDR_SEND_ACK,
MPTCP_PM_RM_ADDR_RECEIVED,
MPTCP_PM_ESTABLISHED,
MPTCP_PM_SUBFLOW_ESTABLISHED,
};
+enum mptcp_add_addr_status {
+ MPTCP_ADD_ADDR_SIGNAL,
+ MPTCP_ADD_ADDR_ECHO,
+ MPTCP_ADD_ADDR_IPV6,
+};
+
struct mptcp_pm_data {
struct mptcp_addr_info local;
struct mptcp_addr_info remote;
spinlock_t lock; /*protects the whole PM data */
- bool add_addr_signal;
+ u8 add_addr_signal;
bool rm_addr_signal;
bool server_side;
bool work_pending;
bool accept_addr;
bool accept_subflow;
- bool add_addr_echo;
u8 add_addr_signaled;
u8 add_addr_accepted;
u8 local_addr_used;
struct mptcp_data_frag {
struct list_head list;
u64 data_seq;
- int data_len;
- int offset;
- int overhead;
+ u16 data_len;
+ u16 offset;
+ u16 overhead;
+ u16 already_sent;
struct page *page;
};
u64 local_key;
u64 remote_key;
u64 write_seq;
+ u64 snd_nxt;
u64 ack_seq;
+ u64 rcv_wnd_sent;
u64 rcv_data_fin_seq;
+ int wmem_reserved;
struct sock *last_snd;
int snd_burst;
- atomic64_t snd_una;
+ int old_wspace;
+ u64 snd_una;
+ u64 wnd_end;
unsigned long timer_ival;
u32 token;
+ int rmem_pending;
+ int rmem_released;
unsigned long flags;
bool can_ack;
bool fully_established;
bool snd_data_fin_enable;
bool use_64bit_ack; /* Set when we received a 64-bit DSN */
spinlock_t join_list_lock;
+ struct sock *ack_hint;
struct work_struct work;
struct sk_buff *ooo_last_skb;
struct rb_root out_of_order_queue;
+ struct sk_buff_head receive_queue;
+ struct sk_buff_head skb_tx_cache; /* this is wmem accounted */
+ int tx_pending_data;
+ int size_goal_cache;
struct list_head conn_list;
struct list_head rtx_queue;
+ struct mptcp_data_frag *first_pending;
struct list_head join_list;
- struct skb_ext *cached_ext; /* for the next sendmsg */
struct socket *subflow; /* outgoing connect/listener/!mp_capable */
struct sock *first;
struct mptcp_pm_data pm;
} rcvq_space;
};
+#define mptcp_lock_sock(___sk, cb) do { \
+ struct sock *__sk = (___sk); /* silence macro reuse warning */ \
+ might_sleep(); \
+ spin_lock_bh(&__sk->sk_lock.slock); \
+ if (__sk->sk_lock.owned) \
+ __lock_sock(__sk); \
+ cb; \
+ __sk->sk_lock.owned = 1; \
+ spin_unlock(&__sk->sk_lock.slock); \
+ mutex_acquire(&__sk->sk_lock.dep_map, 0, 0, _RET_IP_); \
+ local_bh_enable(); \
+} while (0)
+
+#define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock)
+#define mptcp_data_unlock(sk) spin_unlock_bh(&(sk)->sk_lock.slock)
+
#define mptcp_for_each_subflow(__msk, __subflow) \
list_for_each_entry(__subflow, &((__msk)->conn_list), node)
return (struct mptcp_sock *)sk;
}
+static inline int __mptcp_space(const struct sock *sk)
+{
+ return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_pending);
+}
+
+static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
+{
+ const struct mptcp_sock *msk = mptcp_sk(sk);
+
+ return READ_ONCE(msk->first_pending);
+}
+
+static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct mptcp_data_frag *cur;
+
+ cur = msk->first_pending;
+ return list_is_last(&cur->list, &msk->rtx_queue) ? NULL :
+ list_next_entry(cur, list);
+}
+
+static inline struct mptcp_data_frag *mptcp_pending_tail(const struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ if (!msk->first_pending)
+ return NULL;
+
+ if (WARN_ON_ONCE(list_empty(&msk->rtx_queue)))
+ return NULL;
+
+ return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
+}
+
static inline struct mptcp_data_frag *mptcp_rtx_tail(const struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- if (list_empty(&msk->rtx_queue))
+ if (!before64(msk->snd_nxt, READ_ONCE(msk->snd_una)))
return NULL;
return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
mpc_map : 1,
backup : 1,
rx_eof : 1,
- can_ack : 1; /* only after processing the remote a key */
+ can_ack : 1, /* only after processing the remote a key */
+ disposable : 1; /* ctx can be free at ulp release time */
enum mptcp_data_avail data_avail;
u32 remote_nonce;
u64 thmac;
return subflow->map_seq + mptcp_subflow_get_map_offset(subflow);
}
+static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk,
+ struct mptcp_subflow_context *subflow)
+{
+ sock_hold(mptcp_subflow_tcp_sock(subflow));
+ spin_lock_bh(&msk->join_list_lock);
+ list_add_tail(&subflow->node, &msk->join_list);
+ spin_unlock_bh(&msk->join_list_lock);
+}
+
int mptcp_is_enabled(struct net *net);
+unsigned int mptcp_get_add_addr_timeout(struct net *net);
void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
struct mptcp_options_received *mp_opt);
bool mptcp_subflow_data_available(struct sock *sk);
void __init mptcp_subflow_init(void);
void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
- struct mptcp_subflow_context *subflow,
- long timeout);
+ struct mptcp_subflow_context *subflow);
void mptcp_subflow_reset(struct sock *ssk);
/* called with sk socket lock held */
void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk);
void mptcp_data_ready(struct sock *sk, struct sock *ssk);
bool mptcp_finish_join(struct sock *sk);
-void mptcp_data_acked(struct sock *sk);
+bool mptcp_schedule_work(struct sock *sk);
+void __mptcp_wnd_updated(struct sock *sk, struct sock *ssk);
+void __mptcp_data_acked(struct sock *sk);
void mptcp_subflow_eof(struct sock *sk);
bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);
+void __mptcp_flush_join_list(struct mptcp_sock *msk);
+static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
+{
+ return READ_ONCE(msk->snd_data_fin_enable) &&
+ READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt);
+}
+
void mptcp_destroy_common(struct mptcp_sock *msk);
void __init mptcp_token_init(void);
void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id);
void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr);
+void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id);
void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
struct mptcp_pm_add_entry *
static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
{
- return READ_ONCE(msk->pm.add_addr_signal);
+ return READ_ONCE(msk->pm.add_addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL);
+}
+
+static inline bool mptcp_pm_should_add_signal_echo(struct mptcp_sock *msk)
+{
+ return READ_ONCE(msk->pm.add_addr_signal) & BIT(MPTCP_ADD_ADDR_ECHO);
+}
+
+static inline bool mptcp_pm_should_add_signal_ipv6(struct mptcp_sock *msk)
+{
+ return READ_ONCE(msk->pm.add_addr_signal) & BIT(MPTCP_ADD_ADDR_IPV6);
}
static inline bool mptcp_pm_should_rm_signal(struct mptcp_sock *msk)
void mptcp_pm_nl_fully_established(struct mptcp_sock *msk);
void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk);
void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk);
+void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk);
void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk);
void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id);
int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP);
}
-static inline bool before64(__u64 seq1, __u64 seq2)
-{
- return (__s64)(seq1 - seq2) < 0;
-}
-
-#define after64(seq2, seq1) before64(seq1, seq2)
-
void mptcp_diag_subflow_init(struct tcp_ulp_ops *ops);
static inline bool __mptcp_check_fallback(const struct mptcp_sock *msk)
return 0;
}
-static void subflow_init_req(struct request_sock *req,
- const struct sock *sk_listener,
- struct sk_buff *skb)
+/* Init mptcp request socket.
+ *
+ * Returns an error code if a JOIN has failed and a TCP reset
+ * should be sent.
+ */
+static int subflow_init_req(struct request_sock *req,
+ const struct sock *sk_listener,
+ struct sk_buff *skb)
{
struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener);
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
ret = __subflow_init_req(req, sk_listener);
if (ret)
- return;
+ return 0;
mptcp_get_options(skb, &mp_opt);
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
if (mp_opt.mp_join)
- return;
+ return 0;
} else if (mp_opt.mp_join) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
}
} else {
subflow_req->mp_capable = 1;
}
- return;
+ return 0;
}
err = mptcp_token_new_request(req);
subflow_req->remote_nonce = mp_opt.nonce;
subflow_req->msk = subflow_token_join_request(req, skb);
- if (unlikely(req->syncookie) && subflow_req->msk) {
+ /* Can't fall back to TCP in this case. */
+ if (!subflow_req->msk)
+ return -EPERM;
+
+ if (unlikely(req->syncookie)) {
if (mptcp_can_accept_new_subflow(subflow_req->msk))
subflow_init_req_cookie_join_save(subflow_req, skb);
}
pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
subflow_req->remote_nonce, subflow_req->msk);
}
+
+ return 0;
}
int mptcp_subflow_init_cookie_req(struct request_sock *req,
}
EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req);
-static void subflow_v4_init_req(struct request_sock *req,
- const struct sock *sk_listener,
- struct sk_buff *skb)
+static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
+ struct sk_buff *skb,
+ struct flowi *fl,
+ struct request_sock *req)
{
+ struct dst_entry *dst;
+ int err;
+
tcp_rsk(req)->is_mptcp = 1;
- tcp_request_sock_ipv4_ops.init_req(req, sk_listener, skb);
+ dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req);
+ if (!dst)
+ return NULL;
+
+ err = subflow_init_req(req, sk, skb);
+ if (err == 0)
+ return dst;
- subflow_init_req(req, sk_listener, skb);
+ dst_release(dst);
+ if (!req->syncookie)
+ tcp_request_sock_ops.send_reset(sk, skb);
+ return NULL;
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-static void subflow_v6_init_req(struct request_sock *req,
- const struct sock *sk_listener,
- struct sk_buff *skb)
+static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
+ struct sk_buff *skb,
+ struct flowi *fl,
+ struct request_sock *req)
{
+ struct dst_entry *dst;
+ int err;
+
tcp_rsk(req)->is_mptcp = 1;
- tcp_request_sock_ipv6_ops.init_req(req, sk_listener, skb);
+ dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req);
+ if (!dst)
+ return NULL;
+
+ err = subflow_init_req(req, sk, skb);
+ if (err == 0)
+ return dst;
- subflow_init_req(req, sk_listener, skb);
+ dst_release(dst);
+ if (!req->syncookie)
+ tcp6_request_sock_ops.send_reset(sk, skb);
+ return NULL;
}
#endif
*/
inet_sk_state_store((void *)new_msk, TCP_ESTABLISHED);
+ /* link the newly created socket to the msk */
+ mptcp_add_pending_subflow(mptcp_sk(new_msk), ctx);
+ WRITE_ONCE(mptcp_sk(new_msk)->first, child);
+
/* new mpc subflow takes ownership of the newly
* created mptcp socket
*/
sk_eat_skb(ssk, skb);
if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
subflow->map_valid = 0;
- if (incr)
- tcp_cleanup_rbuf(ssk, incr);
}
static bool subflow_check_data_avail(struct sock *ssk)
const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
const struct sock *sk = subflow->conn;
- *space = tcp_space(sk);
+ *space = __mptcp_space(sk);
*full_space = tcp_full_space(sk);
}
mptcp_data_ready(parent, sk);
}
-static void subflow_write_space(struct sock *sk)
+static void subflow_write_space(struct sock *ssk)
{
- struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
- struct sock *parent = subflow->conn;
-
- if (!sk_stream_is_writeable(sk))
- return;
-
- if (sk_stream_is_writeable(parent)) {
- set_bit(MPTCP_SEND_SPACE, &mptcp_sk(parent)->flags);
- smp_mb__after_atomic();
- /* set SEND_SPACE before sk_stream_write_space clears NOSPACE */
- sk_stream_write_space(parent);
- }
+ /* we take action in __mptcp_clean_una() */
}
static struct inet_connection_sock_af_ops *
if (err && err != -EINPROGRESS)
goto failed;
- spin_lock_bh(&msk->join_list_lock);
- list_add_tail(&subflow->node, &msk->join_list);
- spin_unlock_bh(&msk->join_list_lock);
-
+ mptcp_add_pending_subflow(msk, subflow);
return err;
failed:
+ subflow->disposable = 1;
sock_release(sf);
return err;
}
mptcp_data_ready(parent, sk);
if (__mptcp_check_fallback(mptcp_sk(parent)) &&
- !(parent->sk_shutdown & RCV_SHUTDOWN) &&
!subflow->rx_eof && subflow_is_done(sk)) {
subflow->rx_eof = 1;
mptcp_subflow_eof(parent);
return err;
}
-static void subflow_ulp_release(struct sock *sk)
+static void subflow_ulp_release(struct sock *ssk)
{
- struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(sk);
+ struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk);
+ bool release = true;
+ struct sock *sk;
if (!ctx)
return;
- if (ctx->conn)
- sock_put(ctx->conn);
+ sk = ctx->conn;
+ if (sk) {
+ /* if the msk has been orphaned, keep the ctx
+ * alive, will be freed by mptcp_done()
+ */
+ release = ctx->disposable;
+ sock_put(sk);
+ }
- kfree_rcu(ctx, rcu);
+ if (release)
+ kfree_rcu(ctx, rcu);
}
static void subflow_ulp_clone(const struct request_sock *req,
panic("MPTCP: failed to init subflow request sock ops\n");
subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops;
- subflow_request_sock_ipv4_ops.init_req = subflow_v4_init_req;
+ subflow_request_sock_ipv4_ops.route_req = subflow_v4_route_req;
subflow_specific = ipv4_specific;
subflow_specific.conn_request = subflow_v4_conn_request;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops;
- subflow_request_sock_ipv6_ops.init_req = subflow_v6_init_req;
+ subflow_request_sock_ipv6_ops.route_req = subflow_v6_route_req;
subflow_v6_specific = ipv6_specific;
subflow_v6_specific.conn_request = subflow_v6_conn_request;
The lookup will be delegated to the IPv4 or IPv6 FIB depending
on the protocol of the packet.
+config NFT_REJECT_NETDEV
+ depends on NFT_REJECT_IPV4
+ depends on NFT_REJECT_IPV6
+ tristate "Netfilter nf_tables netdev REJECT support"
+ help
+ This option enables the REJECT support from the netdev table.
+ The return packet generation will be delegated to the IPv4
+ or IPv6 ICMP or TCP RST implementation depending on the
+ protocol of the packet.
+
endif # NF_TABLES_NETDEV
endif # NF_TABLES
obj-$(CONFIG_NFT_QUOTA) += nft_quota.o
obj-$(CONFIG_NFT_REJECT) += nft_reject.o
obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o
+obj-$(CONFIG_NFT_REJECT_NETDEV) += nft_reject_netdev.o
obj-$(CONFIG_NFT_TUNNEL) += nft_tunnel.o
obj-$(CONFIG_NFT_COUNTER) += nft_counter.o
obj-$(CONFIG_NFT_LOG) += nft_log.o
ret = -IPSET_ERR_PROTOCOL;
goto put_out;
}
+ /* Set create flags depending on the type revision */
+ set->flags |= set->type->create_flags[revision];
ret = set->type->create(net, set, tb, flags);
if (ret != 0)
/* Modified by ip_set_destroy() only, which is serialized */
inst->is_destroyed = false;
} else {
+ u32 flags = flag_exist(nlh);
s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
&i);
if (!s) {
- ret = -ENOENT;
+ if (!(flags & IPSET_FLAG_EXIST))
+ ret = -ENOENT;
goto out;
} else if (s->ref || s->ref_netlink) {
ret = -IPSET_ERR_BUSY;
*/
/* Number of elements to store in an initial array block */
-#define AHASH_INIT_SIZE 4
+#define AHASH_INIT_SIZE 2
/* Max number of elements to store in an array block */
-#define AHASH_MAX_SIZE (3 * AHASH_INIT_SIZE)
+#define AHASH_MAX_SIZE (6 * AHASH_INIT_SIZE)
/* Max muber of elements in the array block when tuned */
#define AHASH_MAX_TUNED 64
+#define AHASH_MAX(h) ((h)->bucketsize)
+
/* Max number of elements can be tuned */
#ifdef IP_SET_HASH_WITH_MULTI
-#define AHASH_MAX(h) ((h)->ahash_max)
-
static u8
-tune_ahash_max(u8 curr, u32 multi)
+tune_bucketsize(u8 curr, u32 multi)
{
u32 n;
*/
return n > curr && n <= AHASH_MAX_TUNED ? n : curr;
}
-
-#define TUNE_AHASH_MAX(h, multi) \
- ((h)->ahash_max = tune_ahash_max((h)->ahash_max, multi))
+#define TUNE_BUCKETSIZE(h, multi) \
+ ((h)->bucketsize = tune_bucketsize((h)->bucketsize, multi))
#else
-#define AHASH_MAX(h) AHASH_MAX_SIZE
-#define TUNE_AHASH_MAX(h, multi)
+#define TUNE_BUCKETSIZE(h, multi)
#endif
/* A hash bucket */
#ifdef IP_SET_HASH_WITH_MARKMASK
u32 markmask; /* markmask value for mark mask to store */
#endif
-#ifdef IP_SET_HASH_WITH_MULTI
- u8 ahash_max; /* max elements in an array block */
-#endif
+ u8 bucketsize; /* max elements in an array block */
#ifdef IP_SET_HASH_WITH_NETMASK
u8 netmask; /* netmask value for subnets to store */
#endif
goto set_full;
/* Create a new slot */
if (n->pos >= n->size) {
- TUNE_AHASH_MAX(h, multi);
+ TUNE_BUCKETSIZE(h, multi);
if (n->size >= AHASH_MAX(h)) {
/* Trigger rehashing */
mtype_data_next(&h->next, d);
if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask))
goto nla_put_failure;
#endif
+ if (set->flags & IPSET_CREATE_FLAG_BUCKETSIZE) {
+ if (nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, h->bucketsize) ||
+ nla_put_net32(skb, IPSET_ATTR_INITVAL, htonl(h->initval)))
+ goto nla_put_failure;
+ }
if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) ||
nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) ||
nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements)))
#ifdef IP_SET_HASH_WITH_MARKMASK
h->markmask = markmask;
#endif
- get_random_bytes(&h->initval, sizeof(h->initval));
-
+ if (tb[IPSET_ATTR_INITVAL])
+ h->initval = ntohl(nla_get_be32(tb[IPSET_ATTR_INITVAL]));
+ else
+ get_random_bytes(&h->initval, sizeof(h->initval));
+ h->bucketsize = AHASH_MAX_SIZE;
+ if (tb[IPSET_ATTR_BUCKETSIZE]) {
+ h->bucketsize = nla_get_u8(tb[IPSET_ATTR_BUCKETSIZE]);
+ if (h->bucketsize < AHASH_INIT_SIZE)
+ h->bucketsize = AHASH_INIT_SIZE;
+ else if (h->bucketsize > AHASH_MAX_SIZE)
+ h->bucketsize = AHASH_MAX_SIZE;
+ else if (h->bucketsize % 2)
+ h->bucketsize += 1;
+ }
t->htable_bits = hbits;
t->maxelem = h->maxelem / ahash_numof_locks(hbits);
RCU_INIT_POINTER(h->table, t);
/* 1 Counters support */
/* 2 Comments support */
/* 3 Forceadd support */
-#define IPSET_TYPE_REV_MAX 4 /* skbinfo support */
+/* 4 skbinfo support */
+#define IPSET_TYPE_REV_MAX 5 /* bucketsize, initval support */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_ip_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_NETMASK] = { .type = NLA_U8 },
#include <linux/netfilter/ipset/ip_set_hash.h>
#define IPSET_TYPE_REV_MIN 0
-#define IPSET_TYPE_REV_MAX 0
+#define IPSET_TYPE_REV_MAX 1 /* bucketsize, initval support */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Tomasz Chilinski <tomasz.chilinski@chilan.com>");
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_ipmac_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
#define IPSET_TYPE_REV_MIN 0
/* 1 Forceadd support */
-#define IPSET_TYPE_REV_MAX 2 /* skbinfo support */
+/* 2 skbinfo support */
+#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Vytas Dauksa <vytas.dauksa@smoothwall.net>");
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_ipmark_create,
.create_policy = {
[IPSET_ATTR_MARKMASK] = { .type = NLA_U32 },
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
/* 2 Counters support added */
/* 3 Comments support added */
/* 4 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 5 /* skbinfo support added */
+/* 5 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 6 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_ipport_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_PROTO] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
/* 2 Counters support added */
/* 3 Comments support added */
/* 4 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 5 /* skbinfo support added */
+/* 5 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 6 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_ipportip_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
/* 4 Counters support added */
/* 5 Comments support added */
/* 6 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 7 /* skbinfo support added */
+/* 7 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_ipportnet_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
#include <linux/netfilter/ipset/ip_set_hash.h>
#define IPSET_TYPE_REV_MIN 0
-#define IPSET_TYPE_REV_MAX 0
+#define IPSET_TYPE_REV_MAX 1 /* bucketsize, initval support */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_mac_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
/* 3 Counters support added */
/* 4 Comments support added */
/* 5 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 6 /* skbinfo mapping support added */
+/* 6 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 7 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_net_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
/* 4 Comments support added */
/* 5 Forceadd support added */
/* 6 skbinfo support added */
-#define IPSET_TYPE_REV_MAX 7 /* interface wildcard support added */
+/* 7 interface wildcard support added */
+#define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
if (e.cidr > HOST_MASK)
return -IPSET_ERR_INVALID_CIDR;
}
- nla_strlcpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
+ nla_strscpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
ip6_netmask(&e.ip, e.cidr);
- nla_strlcpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
+ nla_strscpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_netiface_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_PROTO] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
#define IPSET_TYPE_REV_MIN 0
/* 1 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 2 /* skbinfo support added */
+/* 2 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_netnet_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
/* 4 Counters support added */
/* 5 Comments support added */
/* 6 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 7 /* skbinfo support added */
+/* 7 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_netport_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_PROTO] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
#define IPSET_TYPE_REV_MIN 0
/* 0 Comments support added */
/* 1 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 2 /* skbinfo support added */
+/* 2 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_netportnet_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
return true;
}
-static bool nf_conntrack_tcp_established(const struct nf_conn *ct)
-{
- return ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED &&
- test_bit(IPS_ASSURED_BIT, &ct->status);
-}
-
/* Returns verdict for packet, or -1 for invalid. */
int nf_conntrack_tcp_packet(struct nf_conn *ct,
struct sk_buff *skb,
};
#ifdef CONFIG_MODULES
-static int nft_request_module(struct net *net, const char *fmt, ...)
+static __printf(2, 3) int nft_request_module(struct net *net, const char *fmt,
+ ...)
{
char module_name[MODULE_NAME_LEN];
struct nft_module_request *req;
if (nla == NULL)
return ERR_PTR(-EINVAL);
- nla_strlcpy(search, nla, sizeof(search));
+ nla_strscpy(search, nla, sizeof(search));
WARN_ON(!rcu_read_lock_held() &&
!lockdep_commit_lock_is_held(net));
goto err_hook_alloc;
}
- nla_strlcpy(ifname, attr, IFNAMSIZ);
+ nla_strscpy(ifname, attr, IFNAMSIZ);
dev = __dev_get_by_name(net, ifname);
if (!dev) {
err = -ENOENT;
struct rhlist_head *tmp, *list;
struct nft_object *obj;
- nla_strlcpy(search, nla, sizeof(search));
+ nla_strscpy(search, nla, sizeof(search));
k.name = search;
WARN_ON_ONCE(!rcu_read_lock_held() &&
nfacct->flags = flags;
}
- nla_strlcpy(nfacct->name, tb[NFACCT_NAME], NFACCT_NAME_MAX);
+ nla_strscpy(nfacct->name, tb[NFACCT_NAME], NFACCT_NAME_MAX);
if (tb[NFACCT_BYTES]) {
atomic64_set(&nfacct->bytes,
!tb[NFCTH_POLICY_EXPECT_TIMEOUT])
return -EINVAL;
- nla_strlcpy(expect_policy->name,
+ nla_strscpy(expect_policy->name,
tb[NFCTH_POLICY_NAME], NF_CT_HELPER_NAME_LEN);
expect_policy->max_expected =
ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
if (ret < 0)
goto err1;
- nla_strlcpy(helper->name,
+ nla_strscpy(helper->name,
tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN);
size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
if (size > sizeof_field(struct nf_conn_help, data)) {
if (!priv->l4proto)
return -ENOENT;
- nla_strlcpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name));
+ nla_strscpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name));
if (tb[NFTA_CT_HELPER_L3PROTO])
family = ntohs(nla_get_be16(tb[NFTA_CT_HELPER_L3PROTO]));
priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);
if (priv->prefix == NULL)
return -ENOMEM;
- nla_strlcpy(priv->prefix, nla, nla_len(nla) + 1);
+ nla_strscpy(priv->prefix, nla, nla_len(nla) + 1);
} else {
priv->prefix = (char *)nft_log_null_prefix;
}
const struct nlattr * const tb[])
{
struct nft_reject *priv = nft_expr_priv(expr);
+ int icmp_code;
if (tb[NFTA_REJECT_TYPE] == NULL)
return -EINVAL;
priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
+ case NFT_REJECT_ICMPX_UNREACH:
if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
return -EINVAL;
- priv->icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+
+ icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+ if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
+ icmp_code > NFT_REJECT_ICMPX_MAX)
+ return -EINVAL;
+
+ priv->icmp_code = icmp_code;
+ break;
case NFT_REJECT_TCP_RST:
break;
default:
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
+ case NFT_REJECT_ICMPX_UNREACH:
if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
goto nla_put_failure;
break;
regs->verdict.code = NF_DROP;
}
-static int nft_reject_inet_init(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nlattr * const tb[])
+static int nft_reject_inet_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
{
- struct nft_reject *priv = nft_expr_priv(expr);
- int icmp_code;
-
- if (tb[NFTA_REJECT_TYPE] == NULL)
- return -EINVAL;
-
- priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
- switch (priv->type) {
- case NFT_REJECT_ICMP_UNREACH:
- case NFT_REJECT_ICMPX_UNREACH:
- if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
- return -EINVAL;
-
- icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
- if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
- icmp_code > NFT_REJECT_ICMPX_MAX)
- return -EINVAL;
-
- priv->icmp_code = icmp_code;
- break;
- case NFT_REJECT_TCP_RST:
- break;
- default:
- return -EINVAL;
- }
- return 0;
-}
-
-static int nft_reject_inet_dump(struct sk_buff *skb,
- const struct nft_expr *expr)
-{
- const struct nft_reject *priv = nft_expr_priv(expr);
-
- if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
- goto nla_put_failure;
-
- switch (priv->type) {
- case NFT_REJECT_ICMP_UNREACH:
- case NFT_REJECT_ICMPX_UNREACH:
- if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
- goto nla_put_failure;
- break;
- default:
- break;
- }
-
- return 0;
-
-nla_put_failure:
- return -1;
+ return nft_chain_validate_hooks(ctx->chain,
+ (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_FORWARD) |
+ (1 << NF_INET_LOCAL_OUT) |
+ (1 << NF_INET_PRE_ROUTING) |
+ (1 << NF_INET_INGRESS));
}
static struct nft_expr_type nft_reject_inet_type;
.type = &nft_reject_inet_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
.eval = nft_reject_inet_eval,
- .init = nft_reject_inet_init,
- .dump = nft_reject_inet_dump,
- .validate = nft_reject_validate,
+ .init = nft_reject_init,
+ .dump = nft_reject_dump,
+ .validate = nft_reject_inet_validate,
};
static struct nft_expr_type nft_reject_inet_type __read_mostly = {
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Laura Garcia Liebana <nevola@gmail.com>
+ * Copyright (c) 2020 Jose M. Guisado <guigom@riseup.net>
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/ipv6/nf_reject.h>
+
+static void nft_reject_queue_xmit(struct sk_buff *nskb, struct sk_buff *oldskb)
+{
+ dev_hard_header(nskb, nskb->dev, ntohs(oldskb->protocol),
+ eth_hdr(oldskb)->h_source, eth_hdr(oldskb)->h_dest,
+ nskb->len);
+ dev_queue_xmit(nskb);
+}
+
+static void nft_reject_netdev_send_v4_tcp_reset(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook)
+{
+ struct sk_buff *nskb;
+
+ nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook);
+ if (!nskb)
+ return;
+
+ nft_reject_queue_xmit(nskb, oldskb);
+}
+
+static void nft_reject_netdev_send_v4_unreach(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook, u8 code)
+{
+ struct sk_buff *nskb;
+
+ nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code);
+ if (!nskb)
+ return;
+
+ nft_reject_queue_xmit(nskb, oldskb);
+}
+
+static void nft_reject_netdev_send_v6_tcp_reset(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook)
+{
+ struct sk_buff *nskb;
+
+ nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook);
+ if (!nskb)
+ return;
+
+ nft_reject_queue_xmit(nskb, oldskb);
+}
+
+
+static void nft_reject_netdev_send_v6_unreach(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook, u8 code)
+{
+ struct sk_buff *nskb;
+
+ nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code);
+ if (!nskb)
+ return;
+
+ nft_reject_queue_xmit(nskb, oldskb);
+}
+
+static void nft_reject_netdev_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct ethhdr *eth = eth_hdr(pkt->skb);
+ struct nft_reject *priv = nft_expr_priv(expr);
+ const unsigned char *dest = eth->h_dest;
+
+ if (is_broadcast_ether_addr(dest) ||
+ is_multicast_ether_addr(dest))
+ goto out;
+
+ switch (eth->h_proto) {
+ case htons(ETH_P_IP):
+ switch (priv->type) {
+ case NFT_REJECT_ICMP_UNREACH:
+ nft_reject_netdev_send_v4_unreach(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt),
+ priv->icmp_code);
+ break;
+ case NFT_REJECT_TCP_RST:
+ nft_reject_netdev_send_v4_tcp_reset(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt));
+ break;
+ case NFT_REJECT_ICMPX_UNREACH:
+ nft_reject_netdev_send_v4_unreach(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt),
+ nft_reject_icmp_code(priv->icmp_code));
+ break;
+ }
+ break;
+ case htons(ETH_P_IPV6):
+ switch (priv->type) {
+ case NFT_REJECT_ICMP_UNREACH:
+ nft_reject_netdev_send_v6_unreach(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt),
+ priv->icmp_code);
+ break;
+ case NFT_REJECT_TCP_RST:
+ nft_reject_netdev_send_v6_tcp_reset(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt));
+ break;
+ case NFT_REJECT_ICMPX_UNREACH:
+ nft_reject_netdev_send_v6_unreach(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt),
+ nft_reject_icmpv6_code(priv->icmp_code));
+ break;
+ }
+ break;
+ default:
+ /* No explicit way to reject this protocol, drop it. */
+ break;
+ }
+out:
+ regs->verdict.code = NF_DROP;
+}
+
+static int nft_reject_netdev_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
+{
+ return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS));
+}
+
+static struct nft_expr_type nft_reject_netdev_type;
+static const struct nft_expr_ops nft_reject_netdev_ops = {
+ .type = &nft_reject_netdev_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+ .eval = nft_reject_netdev_eval,
+ .init = nft_reject_init,
+ .dump = nft_reject_dump,
+ .validate = nft_reject_netdev_validate,
+};
+
+static struct nft_expr_type nft_reject_netdev_type __read_mostly = {
+ .family = NFPROTO_NETDEV,
+ .name = "reject",
+ .ops = &nft_reject_netdev_ops,
+ .policy = nft_reject_policy,
+ .maxattr = NFTA_REJECT_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_reject_netdev_module_init(void)
+{
+ return nft_register_expr(&nft_reject_netdev_type);
+}
+
+static void __exit nft_reject_netdev_module_exit(void)
+{
+ nft_unregister_expr(&nft_reject_netdev_type);
+}
+
+module_init(nft_reject_netdev_module_init);
+module_exit(nft_reject_netdev_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Laura Garcia Liebana <nevola@gmail.com>");
+MODULE_AUTHOR("Jose M. Guisado <guigom@riseup.net>");
+MODULE_DESCRIPTION("Reject packets from netdev via nftables");
+MODULE_ALIAS_NFT_AF_EXPR(5, "reject");
/**
* netlbl_calipso_ops_register - Register the CALIPSO operations
+ * @ops: ops to register
*
* Description:
* Register the CALIPSO packet engine operations.
ret_val = -ENOMEM;
goto add_free_entry;
}
- nla_strlcpy(entry->domain,
+ nla_strscpy(entry->domain,
info->attrs[NLBL_MGMT_A_DOMAIN], tmp_size);
}
* nfc_start_poll - start polling for nfc targets
*
* @dev: The nfc device that must start polling
- * @protocols: bitset of nfc protocols that must be used for polling
+ * @im_protocols: bitset of nfc initiator protocols to be used for polling
+ * @tm_protocols: bitset of nfc transport protocols to be used for polling
*
* The device remains polling for targets until a target is found or
* the nfc_stop_poll function is called.
*
* @dev: The nfc device that found the target
* @target_idx: index of the target that must be deactivated
+ * @mode: idle or sleep?
*/
int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx, u8 mode)
{
/**
* nfc_alloc_send_skb - allocate a skb for data exchange responses
*
+ * @dev: device sending the response
+ * @sk: socket sending the response
+ * @flags: MSG_DONTWAIT flag
* @size: size to allocate
+ * @err: pointer to memory to store the error code
*/
struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk,
unsigned int flags, unsigned int size,
*
* @ops: device operations
* @supported_protocols: NFC protocols supported by the device
+ * @tx_headroom: reserved space at beginning of skb
+ * @tx_tailroom: reserved space at end of skb
*/
struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops,
u32 supported_protocols,
/**
* start_poll operation
+ * @nfc_dev: device to be polled
+ * @im_protocols: bitset of nfc initiator protocols to be used for polling
+ * @tm_protocols: bitset of nfc transport protocols to be used for polling
*
* For every supported protocol, the corresponding polling function is added
* to the table of polling technologies (ddev->poll_techs[]) using
*
* @ops: device operations
* @supported_protocols: NFC protocols supported by the device
+ * @tx_headroom: Reserved space at beginning of skb
+ * @tx_tailroom: Reserved space at end of skb
*/
struct nci_dev *nci_allocate_device(struct nci_ops *ops,
__u32 supported_protocols,
}
static void nci_hci_resp_received(struct nci_dev *ndev, u8 pipe,
- u8 result, struct sk_buff *skb)
+ struct sk_buff *skb)
{
struct nci_conn_info *conn_info;
- u8 status = result;
conn_info = ndev->hci_dev->conn_info;
- if (!conn_info) {
- status = NCI_STATUS_REJECTED;
+ if (!conn_info)
goto exit;
- }
conn_info->rx_skb = skb;
{
switch (type) {
case NCI_HCI_HCP_RESPONSE:
- nci_hci_resp_received(ndev, pipe, instruction, skb);
+ nci_hci_resp_received(ndev, pipe, skb);
break;
case NCI_HCI_HCP_COMMAND:
nci_hci_cmd_received(ndev, pipe, instruction, skb);
if (!dev)
return -ENODEV;
- nla_strlcpy(firmware_name, info->attrs[NFC_ATTR_FIRMWARE_NAME],
+ nla_strscpy(firmware_name, info->attrs[NFC_ATTR_FIRMWARE_NAME],
sizeof(firmware_name));
rc = nfc_fw_download(dev, firmware_name);
ovs_ct_helper(skb, info->family) != NF_ACCEPT) {
return -EINVAL;
}
+
+ if (nf_ct_protonum(ct) == IPPROTO_TCP &&
+ nf_ct_is_confirmed(ct) && nf_conntrack_tcp_established(ct)) {
+ /* Be liberal for tcp packets so that out-of-window
+ * packets are not marked invalid.
+ */
+ nf_ct_set_tcp_be_liberal(ct);
+ }
}
return 0;
/**
* Parse vlan tag from vlan header.
+ * @skb: skb containing frame to parse
+ * @key_vh: pointer to parsed vlan tag
+ * @untag_vlan: should the vlan header be removed from the frame
+ *
* Returns ERROR on memory error.
* Returns 0 if it encounters a non-vlan or incomplete packet.
* Returns 1 after successfully parsing vlan tag.
return -EINVAL;
meter = dp_meter_create(a);
- if (IS_ERR_OR_NULL(meter))
+ if (IS_ERR(meter))
return PTR_ERR(meter);
reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_SET,
{
int len, err;
+ /* store len value because skb can be freed inside ovs_vport_receive() */
len = skb->len;
+
rcu_read_lock();
err = ovs_vport_receive(internal_dev_priv(netdev)->vport, skb, NULL);
rcu_read_unlock();
- if (likely(!err)) {
- struct pcpu_sw_netstats *tstats = this_cpu_ptr(netdev->tstats);
-
- u64_stats_update_begin(&tstats->syncp);
- tstats->tx_bytes += len;
- tstats->tx_packets++;
- u64_stats_update_end(&tstats->syncp);
- } else {
+ if (likely(!err))
+ dev_sw_netstats_tx_add(netdev, 1, len);
+ else
netdev->stats.tx_errors++;
- }
+
return NETDEV_TX_OK;
}
ovs_vport_free(vport);
}
-static void
-internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
-{
- memset(stats, 0, sizeof(*stats));
- stats->rx_errors = dev->stats.rx_errors;
- stats->tx_errors = dev->stats.tx_errors;
- stats->tx_dropped = dev->stats.tx_dropped;
- stats->rx_dropped = dev->stats.rx_dropped;
-
- dev_fetch_sw_netstats(stats, dev->tstats);
-}
-
static const struct net_device_ops internal_dev_netdev_ops = {
.ndo_open = internal_dev_open,
.ndo_stop = internal_dev_stop,
.ndo_start_xmit = internal_dev_xmit,
.ndo_set_mac_address = eth_mac_addr,
- .ndo_get_stats64 = internal_get_stats,
+ .ndo_get_stats64 = dev_get_tstats64,
};
static struct rtnl_link_ops internal_dev_link_ops __read_mostly = {
*
* @priv_size: Size of private data area to allocate.
* @ops: vport device ops
+ * @parms: information about new vport.
*
* Allocate and initialize a new vport defined by @ops. The vport will contain
* a private data area of size @priv_size that can be accessed using
- * vport_priv(). vports that are no longer needed should be released with
+ * vport_priv(). Some parameters of the vport will be initialized from @parms.
+ * @vports that are no longer needed should be released with
* vport_free().
*/
struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
* Copyright (C) 2011, <lokec@ccs.neu.edu>
*/
+#include <linux/ethtool.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/capability.h>
return false;
}
-static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
+static int fanout_add(struct sock *sk, struct fanout_args *args)
{
struct packet_rollover *rollover = NULL;
struct packet_sock *po = pkt_sk(sk);
+ u16 type_flags = args->type_flags;
struct packet_fanout *f, *match;
u8 type = type_flags & 0xff;
u8 flags = type_flags >> 8;
+ u16 id = args->id;
int err;
switch (type) {
}
}
err = -EINVAL;
- if (match && match->flags != flags)
- goto out;
- if (!match) {
+ if (match) {
+ if (match->flags != flags)
+ goto out;
+ if (args->max_num_members &&
+ args->max_num_members != match->max_num_members)
+ goto out;
+ } else {
+ if (args->max_num_members > PACKET_FANOUT_MAX)
+ goto out;
+ if (!args->max_num_members)
+ /* legacy PACKET_FANOUT_MAX */
+ args->max_num_members = 256;
err = -ENOMEM;
- match = kzalloc(sizeof(*match), GFP_KERNEL);
+ match = kvzalloc(struct_size(match, arr, args->max_num_members),
+ GFP_KERNEL);
if (!match)
goto out;
write_pnet(&match->net, sock_net(sk));
match->prot_hook.func = packet_rcv_fanout;
match->prot_hook.af_packet_priv = match;
match->prot_hook.id_match = match_fanout_group;
+ match->max_num_members = args->max_num_members;
list_add(&match->list, &fanout_list);
}
err = -EINVAL;
match->prot_hook.type == po->prot_hook.type &&
match->prot_hook.dev == po->prot_hook.dev) {
err = -ENOSPC;
- if (refcount_read(&match->sk_ref) < PACKET_FANOUT_MAX) {
+ if (refcount_read(&match->sk_ref) < match->max_num_members) {
__dev_remove_pack(&po->prot_hook);
po->fanout = match;
po->rollover = rollover;
if (err && !refcount_read(&match->sk_ref)) {
list_del(&match->list);
- kfree(match);
+ kvfree(match);
}
out:
kfree(po->rollover);
if (f) {
fanout_release_data(f);
- kfree(f);
+ kvfree(f);
}
/*
* Now the socket is dead. No more input will appear.
}
case PACKET_FANOUT:
{
- int val;
+ struct fanout_args args = { 0 };
- if (optlen != sizeof(val))
+ if (optlen != sizeof(int) && optlen != sizeof(args))
return -EINVAL;
- if (copy_from_sockptr(&val, optval, sizeof(val)))
+ if (copy_from_sockptr(&args, optval, optlen))
return -EFAULT;
- return fanout_add(sk, val & 0xffff, val >> 16);
+ return fanout_add(sk, &args);
}
case PACKET_FANOUT_DATA:
{
};
extern struct mutex fanout_mutex;
-#define PACKET_FANOUT_MAX 256
+#define PACKET_FANOUT_MAX (1 << 16)
struct packet_fanout {
possible_net_t net;
unsigned int num_members;
+ u32 max_num_members;
u16 id;
u8 type;
u8 flags;
struct bpf_prog __rcu *bpf_prog;
};
struct list_head list;
- struct sock *arr[PACKET_FANOUT_MAX];
spinlock_t lock;
refcount_t sk_ref;
struct packet_type prot_hook ____cacheline_aligned_in_smp;
+ struct sock *arr[];
};
struct packet_rollover {
port = from->sq_port;
}
- /* Don't accept spoofed messages */
- if (from->sq_node != node_id)
- return -EINVAL;
-
srv = server_add(service, instance, node_id, port);
if (!srv)
return -EINVAL;
port = from->sq_port;
}
- /* Don't accept spoofed messages */
- if (from->sq_node != node_id)
- return -EINVAL;
-
/* Local servers may only unregister themselves */
if (from->sq_node == qrtr_ns.local_node && from->sq_port != port)
return -EINVAL;
void __rcu **slot;
spin_lock_irqsave(&qrtr_nodes_lock, flags);
- if (node->nid != QRTR_EP_NID_AUTO)
- radix_tree_delete(&qrtr_nodes, node->nid);
+ /* If the node is a bridge for other nodes, there are possibly
+ * multiple entries pointing to our released node, delete them all.
+ */
+ radix_tree_for_each_slot(slot, &qrtr_nodes, &iter, 0) {
+ if (*slot == node)
+ radix_tree_iter_delete(&qrtr_nodes, &iter, slot);
+ }
spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
list_del(&node->item);
hdr->src_port_id = cpu_to_le32(from->sq_port);
if (to->sq_port == QRTR_PORT_CTRL) {
hdr->dst_node_id = cpu_to_le32(node->nid);
- hdr->dst_port_id = cpu_to_le32(QRTR_NODE_BCAST);
+ hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL);
} else {
hdr->dst_node_id = cpu_to_le32(to->sq_node);
hdr->dst_port_id = cpu_to_le32(to->sq_port);
{
unsigned long flags;
- if (node->nid != QRTR_EP_NID_AUTO || nid == QRTR_EP_NID_AUTO)
+ if (nid == QRTR_EP_NID_AUTO)
return;
spin_lock_irqsave(&qrtr_nodes_lock, flags);
radix_tree_insert(&qrtr_nodes, nid, node);
- node->nid = nid;
+ if (node->nid == QRTR_EP_NID_AUTO)
+ node->nid = nid;
spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
}
qrtr_node_assign(node, cb->src_node);
+ if (cb->type == QRTR_TYPE_NEW_SERVER) {
+ /* Remote node endpoint can bridge other distant nodes */
+ const struct qrtr_ctrl_pkt *pkt = data + hdrlen;
+
+ qrtr_node_assign(node, le32_to_cpu(pkt->server.node));
+ }
+
if (cb->type == QRTR_TYPE_RESUME_TX) {
qrtr_tx_resume(node, skb);
} else {
/**
* qrtr_alloc_ctrl_packet() - allocate control packet skb
* @pkt: reference to qrtr_ctrl_pkt pointer
+ * @flags: the type of memory to allocate
*
* 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)
+static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt,
+ gfp_t flags)
{
const int pkt_len = sizeof(struct qrtr_ctrl_pkt);
struct sk_buff *skb;
- skb = alloc_skb(QRTR_HDR_MAX_SIZE + pkt_len, GFP_KERNEL);
+ skb = alloc_skb(QRTR_HDR_MAX_SIZE + pkt_len, flags);
if (!skb)
return NULL;
struct qrtr_ctrl_pkt *pkt;
struct qrtr_tx_flow *flow;
struct sk_buff *skb;
+ unsigned long flags;
void __rcu **slot;
mutex_lock(&node->ep_lock);
mutex_unlock(&node->ep_lock);
/* Notify the local controller about the event */
- 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);
+ spin_lock_irqsave(&qrtr_nodes_lock, flags);
+ radix_tree_for_each_slot(slot, &qrtr_nodes, &iter, 0) {
+ if (*slot != node)
+ continue;
+ src.sq_node = iter.index;
+ skb = qrtr_alloc_ctrl_packet(&pkt, GFP_ATOMIC);
+ if (skb) {
+ pkt->cmd = cpu_to_le32(QRTR_TYPE_BYE);
+ qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst);
+ }
}
+ spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
/* Wake up any transmitters waiting for resume-tx from the node */
mutex_lock(&node->qrtr_tx_lock);
to.sq_node = QRTR_NODE_BCAST;
to.sq_port = QRTR_PORT_CTRL;
- skb = qrtr_alloc_ctrl_packet(&pkt);
+ skb = qrtr_alloc_ctrl_packet(&pkt, GFP_KERNEL);
if (skb) {
pkt->cmd = cpu_to_le32(QRTR_TYPE_DEL_CLIENT);
pkt->client.node = cpu_to_le32(ipc->us.sq_node);
if (!node)
return -EINVAL;
- skb = qrtr_alloc_ctrl_packet(&pkt);
+ skb = qrtr_alloc_ctrl_packet(&pkt, GFP_KERNEL);
if (!skb)
return -ENOMEM;
rtt.o \
security.o \
sendmsg.o \
+ server_key.o \
skbuff.o \
utils.o
#include <net/netns/generic.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
+#include <keys/rxrpc-type.h>
#include "protocol.h"
#if 0
#define rxrpc_queue_delayed_work(WS,D) \
queue_delayed_work(rxrpc_workqueue, (WS), (D))
+struct key_preparsed_payload;
struct rxrpc_connection;
/*
/* Clean up a security service */
void (*exit)(void);
+ /* Parse the information from a server key */
+ int (*preparse_server_key)(struct key_preparsed_payload *);
+
+ /* Clean up the preparse buffer after parsing a server key */
+ void (*free_preparse_server_key)(struct key_preparsed_payload *);
+
+ /* Destroy the payload of a server key */
+ void (*destroy_server_key)(struct key *);
+
+ /* Describe a server key */
+ void (*describe_server_key)(const struct key *, struct seq_file *);
+
/* initialise a connection's security */
- int (*init_connection_security)(struct rxrpc_connection *);
+ int (*init_connection_security)(struct rxrpc_connection *,
+ struct rxrpc_key_token *);
- /* prime a connection's packet security */
- int (*prime_packet_security)(struct rxrpc_connection *);
+ /* Work out how much data we can store in a packet, given an estimate
+ * of the amount of data remaining.
+ */
+ int (*how_much_data)(struct rxrpc_call *, size_t,
+ size_t *, size_t *, size_t *);
/* impose security on a packet */
- int (*secure_packet)(struct rxrpc_call *,
- struct sk_buff *,
- size_t,
- void *);
+ int (*secure_packet)(struct rxrpc_call *, struct sk_buff *, size_t);
/* verify the security on a received packet */
int (*verify_packet)(struct rxrpc_call *, struct sk_buff *,
struct list_head proc_link; /* link in procfs list */
struct list_head link; /* link in master connection list */
struct sk_buff_head rx_queue; /* received conn-level packets */
+
const struct rxrpc_security *security; /* applied security module */
- struct key *server_key; /* security for this service */
- struct crypto_sync_skcipher *cipher; /* encryption handle */
- struct rxrpc_crypt csum_iv; /* packet checksum base */
+ union {
+ struct {
+ struct crypto_sync_skcipher *cipher; /* encryption handle */
+ struct rxrpc_crypt csum_iv; /* packet checksum base */
+ u32 nonce; /* response re-use preventer */
+ } rxkad;
+ };
unsigned long flags;
unsigned long events;
unsigned long idle_timestamp; /* Time at which last became idle */
int debug_id; /* debug ID for printks */
atomic_t serial; /* packet serial number counter */
unsigned int hi_serial; /* highest serial number received */
- u32 security_nonce; /* response re-use preventer */
u32 service_id; /* Service ID, possibly upgraded */
- u8 size_align; /* data size alignment (for security) */
- u8 security_size; /* security header size */
u8 security_ix; /* security type */
u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */
u8 bundle_shift; /* Index into bundle->avail_chans */
struct sk_buff *);
struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *, gfp_t);
void rxrpc_new_incoming_connection(struct rxrpc_sock *, struct rxrpc_connection *,
- const struct rxrpc_security *, struct key *,
- struct sk_buff *);
+ const struct rxrpc_security *, struct sk_buff *);
void rxrpc_unpublish_service_conn(struct rxrpc_connection *);
/*
* key.c
*/
extern struct key_type key_type_rxrpc;
-extern struct key_type key_type_rxrpc_s;
int rxrpc_request_key(struct rxrpc_sock *, sockptr_t , int);
-int rxrpc_server_keyring(struct rxrpc_sock *, sockptr_t, int);
int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t,
u32);
* security.c
*/
int __init rxrpc_init_security(void);
+const struct rxrpc_security *rxrpc_security_lookup(u8);
void rxrpc_exit_security(void);
int rxrpc_init_client_conn_security(struct rxrpc_connection *);
-bool rxrpc_look_up_server_security(struct rxrpc_local *, struct rxrpc_sock *,
- const struct rxrpc_security **, struct key **,
- struct sk_buff *);
+const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *,
+ struct sk_buff *);
+struct key *rxrpc_look_up_server_security(struct rxrpc_connection *,
+ struct sk_buff *, u32, u32);
/*
* sendmsg.c
*/
int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
+/*
+ * server_key.c
+ */
+extern struct key_type key_type_rxrpc_s;
+
+int rxrpc_server_keyring(struct rxrpc_sock *, sockptr_t, int);
+
/*
* skbuff.c
*/
struct rxrpc_peer *peer,
struct rxrpc_connection *conn,
const struct rxrpc_security *sec,
- struct key *key,
struct sk_buff *skb)
{
struct rxrpc_backlog *b = rx->backlog;
conn->params.local = rxrpc_get_local(local);
conn->params.peer = peer;
rxrpc_see_connection(conn);
- rxrpc_new_incoming_connection(rx, conn, sec, key, skb);
+ rxrpc_new_incoming_connection(rx, conn, sec, skb);
} else {
rxrpc_get_connection(conn);
}
struct rxrpc_connection *conn;
struct rxrpc_peer *peer = NULL;
struct rxrpc_call *call = NULL;
- struct key *key = NULL;
_enter("");
*/
conn = rxrpc_find_connection_rcu(local, skb, &peer);
- if (!conn && !rxrpc_look_up_server_security(local, rx, &sec, &key, skb))
- goto no_call;
+ if (!conn) {
+ sec = rxrpc_get_incoming_security(rx, skb);
+ if (!sec)
+ goto no_call;
+ }
- call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, key, skb);
- key_put(key);
+ call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, skb);
if (!call) {
skb->mark = RXRPC_SKB_MARK_REJECT_BUSY;
goto no_call;
if (ret < 0)
goto error_1;
- ret = conn->security->prime_packet_security(conn);
- if (ret < 0)
- goto error_2;
-
atomic_inc(&rxnet->nr_conns);
write_lock(&rxnet->conn_lock);
list_add_tail(&conn->proc_link, &rxnet->conn_proc_list);
_leave(" = %p", conn);
return conn;
-error_2:
- conn->security->clear(conn);
error_1:
rxrpc_put_client_connection_id(conn);
error_0:
if (ret < 0)
return ret;
- ret = conn->security->init_connection_security(conn);
- if (ret < 0)
- return ret;
-
- ret = conn->security->prime_packet_security(conn);
+ ret = conn->security->init_connection_security(
+ conn, conn->params.key->payload.data[0]);
if (ret < 0)
return ret;
_enter("{%d}", conn->debug_id);
ASSERT(conn->security_ix != 0);
- ASSERT(conn->server_key);
if (conn->security->issue_challenge(conn) < 0) {
abort_code = RX_CALL_DEAD;
conn->security = &rxrpc_no_security;
spin_lock_init(&conn->state_lock);
conn->debug_id = atomic_inc_return(&rxrpc_debug_id);
- conn->size_align = 4;
conn->idle_timestamp = jiffies;
}
conn->security->clear(conn);
key_put(conn->params.key);
- key_put(conn->server_key);
rxrpc_put_bundle(conn->bundle);
rxrpc_put_peer(conn->params.peer);
void rxrpc_new_incoming_connection(struct rxrpc_sock *rx,
struct rxrpc_connection *conn,
const struct rxrpc_security *sec,
- struct key *key,
struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
conn->security_ix = sp->hdr.securityIndex;
conn->out_clientflag = 0;
conn->security = sec;
- conn->server_key = key_get(key);
if (conn->security_ix)
conn->state = RXRPC_CONN_SERVICE_UNSECURED;
else
#include <net/af_rxrpc.h>
#include "ar-internal.h"
-static int none_init_connection_security(struct rxrpc_connection *conn)
+static int none_init_connection_security(struct rxrpc_connection *conn,
+ struct rxrpc_key_token *token)
{
return 0;
}
-static int none_prime_packet_security(struct rxrpc_connection *conn)
+/*
+ * Work out how much data we can put in an unsecured packet.
+ */
+static int none_how_much_data(struct rxrpc_call *call, size_t remain,
+ size_t *_buf_size, size_t *_data_size, size_t *_offset)
{
+ *_buf_size = *_data_size = min_t(size_t, remain, RXRPC_JUMBO_DATALEN);
+ *_offset = 0;
return 0;
}
-static int none_secure_packet(struct rxrpc_call *call,
- struct sk_buff *skb,
- size_t data_size,
- void *sechdr)
+static int none_secure_packet(struct rxrpc_call *call, struct sk_buff *skb,
+ size_t data_size)
{
return 0;
}
.init = none_init,
.exit = none_exit,
.init_connection_security = none_init_connection_security,
- .prime_packet_security = none_prime_packet_security,
.free_call_crypto = none_free_call_crypto,
+ .how_much_data = none_how_much_data,
.secure_packet = none_secure_packet,
.verify_packet = none_verify_packet,
.locate_data = none_locate_data,
* Written by David Howells (dhowells@redhat.com)
*
* RxRPC keys should have a description of describing their purpose:
- * "afs@CAMBRIDGE.REDHAT.COM>
+ * "afs@example.com"
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <keys/user-type.h>
#include "ar-internal.h"
-static int rxrpc_vet_description_s(const char *);
static int rxrpc_preparse(struct key_preparsed_payload *);
-static int rxrpc_preparse_s(struct key_preparsed_payload *);
static void rxrpc_free_preparse(struct key_preparsed_payload *);
-static void rxrpc_free_preparse_s(struct key_preparsed_payload *);
static void rxrpc_destroy(struct key *);
-static void rxrpc_destroy_s(struct key *);
static void rxrpc_describe(const struct key *, struct seq_file *);
static long rxrpc_read(const struct key *, char *, size_t);
};
EXPORT_SYMBOL(key_type_rxrpc);
-/*
- * rxrpc server defined keys take "<serviceId>:<securityIndex>" as the
- * description and an 8-byte decryption key as the payload
- */
-struct key_type key_type_rxrpc_s = {
- .name = "rxrpc_s",
- .flags = KEY_TYPE_NET_DOMAIN,
- .vet_description = rxrpc_vet_description_s,
- .preparse = rxrpc_preparse_s,
- .free_preparse = rxrpc_free_preparse_s,
- .instantiate = generic_key_instantiate,
- .destroy = rxrpc_destroy_s,
- .describe = rxrpc_describe,
-};
-
-/*
- * Vet the description for an RxRPC server key
- */
-static int rxrpc_vet_description_s(const char *desc)
-{
- unsigned long num;
- char *p;
-
- num = simple_strtoul(desc, &p, 10);
- if (*p != ':' || num > 65535)
- return -EINVAL;
- num = simple_strtoul(p + 1, &p, 10);
- if (*p || num < 1 || num > 255)
- return -EINVAL;
- return 0;
-}
-
/*
* parse an RxKAD type XDR format token
* - the caller guarantees we have at least 4 words
return 0;
}
-static void rxrpc_free_krb5_principal(struct krb5_principal *princ)
-{
- int loop;
-
- if (princ->name_parts) {
- for (loop = princ->n_name_parts - 1; loop >= 0; loop--)
- kfree(princ->name_parts[loop]);
- kfree(princ->name_parts);
- }
- kfree(princ->realm);
-}
-
-static void rxrpc_free_krb5_tagged(struct krb5_tagged_data *td)
-{
- kfree(td->data);
-}
-
-/*
- * free up an RxK5 token
- */
-static void rxrpc_rxk5_free(struct rxk5_key *rxk5)
-{
- int loop;
-
- rxrpc_free_krb5_principal(&rxk5->client);
- rxrpc_free_krb5_principal(&rxk5->server);
- rxrpc_free_krb5_tagged(&rxk5->session);
-
- if (rxk5->addresses) {
- for (loop = rxk5->n_addresses - 1; loop >= 0; loop--)
- rxrpc_free_krb5_tagged(&rxk5->addresses[loop]);
- kfree(rxk5->addresses);
- }
- if (rxk5->authdata) {
- for (loop = rxk5->n_authdata - 1; loop >= 0; loop--)
- rxrpc_free_krb5_tagged(&rxk5->authdata[loop]);
- kfree(rxk5->authdata);
- }
-
- kfree(rxk5->ticket);
- kfree(rxk5->ticket2);
- kfree(rxk5);
-}
-
-/*
- * extract a krb5 principal
- */
-static int rxrpc_krb5_decode_principal(struct krb5_principal *princ,
- const __be32 **_xdr,
- unsigned int *_toklen)
-{
- const __be32 *xdr = *_xdr;
- unsigned int toklen = *_toklen, n_parts, loop, tmp, paddedlen;
-
- /* there must be at least one name, and at least #names+1 length
- * words */
- if (toklen <= 12)
- return -EINVAL;
-
- _enter(",{%x,%x,%x},%u",
- ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), toklen);
-
- n_parts = ntohl(*xdr++);
- toklen -= 4;
- if (n_parts <= 0 || n_parts > AFSTOKEN_K5_COMPONENTS_MAX)
- return -EINVAL;
- princ->n_name_parts = n_parts;
-
- if (toklen <= (n_parts + 1) * 4)
- return -EINVAL;
-
- princ->name_parts = kcalloc(n_parts, sizeof(char *), GFP_KERNEL);
- if (!princ->name_parts)
- return -ENOMEM;
-
- for (loop = 0; loop < n_parts; loop++) {
- if (toklen < 4)
- return -EINVAL;
- tmp = ntohl(*xdr++);
- toklen -= 4;
- if (tmp <= 0 || tmp > AFSTOKEN_STRING_MAX)
- return -EINVAL;
- paddedlen = (tmp + 3) & ~3;
- if (paddedlen > toklen)
- return -EINVAL;
- princ->name_parts[loop] = kmalloc(tmp + 1, GFP_KERNEL);
- if (!princ->name_parts[loop])
- return -ENOMEM;
- memcpy(princ->name_parts[loop], xdr, tmp);
- princ->name_parts[loop][tmp] = 0;
- toklen -= paddedlen;
- xdr += paddedlen >> 2;
- }
-
- if (toklen < 4)
- return -EINVAL;
- tmp = ntohl(*xdr++);
- toklen -= 4;
- if (tmp <= 0 || tmp > AFSTOKEN_K5_REALM_MAX)
- return -EINVAL;
- paddedlen = (tmp + 3) & ~3;
- if (paddedlen > toklen)
- return -EINVAL;
- princ->realm = kmalloc(tmp + 1, GFP_KERNEL);
- if (!princ->realm)
- return -ENOMEM;
- memcpy(princ->realm, xdr, tmp);
- princ->realm[tmp] = 0;
- toklen -= paddedlen;
- xdr += paddedlen >> 2;
-
- _debug("%s/...@%s", princ->name_parts[0], princ->realm);
-
- *_xdr = xdr;
- *_toklen = toklen;
- _leave(" = 0 [toklen=%u]", toklen);
- return 0;
-}
-
-/*
- * extract a piece of krb5 tagged data
- */
-static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td,
- size_t max_data_size,
- const __be32 **_xdr,
- unsigned int *_toklen)
-{
- const __be32 *xdr = *_xdr;
- unsigned int toklen = *_toklen, len, paddedlen;
-
- /* there must be at least one tag and one length word */
- if (toklen <= 8)
- return -EINVAL;
-
- _enter(",%zu,{%x,%x},%u",
- max_data_size, ntohl(xdr[0]), ntohl(xdr[1]), toklen);
-
- td->tag = ntohl(*xdr++);
- len = ntohl(*xdr++);
- toklen -= 8;
- if (len > max_data_size)
- return -EINVAL;
- paddedlen = (len + 3) & ~3;
- if (paddedlen > toklen)
- return -EINVAL;
- td->data_len = len;
-
- if (len > 0) {
- td->data = kmemdup(xdr, len, GFP_KERNEL);
- if (!td->data)
- return -ENOMEM;
- toklen -= paddedlen;
- xdr += paddedlen >> 2;
- }
-
- _debug("tag %x len %x", td->tag, td->data_len);
-
- *_xdr = xdr;
- *_toklen = toklen;
- _leave(" = 0 [toklen=%u]", toklen);
- return 0;
-}
-
-/*
- * extract an array of tagged data
- */
-static int rxrpc_krb5_decode_tagged_array(struct krb5_tagged_data **_td,
- u8 *_n_elem,
- u8 max_n_elem,
- size_t max_elem_size,
- const __be32 **_xdr,
- unsigned int *_toklen)
-{
- struct krb5_tagged_data *td;
- const __be32 *xdr = *_xdr;
- unsigned int toklen = *_toklen, n_elem, loop;
- int ret;
-
- /* there must be at least one count */
- if (toklen < 4)
- return -EINVAL;
-
- _enter(",,%u,%zu,{%x},%u",
- max_n_elem, max_elem_size, ntohl(xdr[0]), toklen);
-
- n_elem = ntohl(*xdr++);
- toklen -= 4;
- if (n_elem > max_n_elem)
- return -EINVAL;
- *_n_elem = n_elem;
- if (n_elem > 0) {
- if (toklen <= (n_elem + 1) * 4)
- return -EINVAL;
-
- _debug("n_elem %d", n_elem);
-
- td = kcalloc(n_elem, sizeof(struct krb5_tagged_data),
- GFP_KERNEL);
- if (!td)
- return -ENOMEM;
- *_td = td;
-
- for (loop = 0; loop < n_elem; loop++) {
- ret = rxrpc_krb5_decode_tagged_data(&td[loop],
- max_elem_size,
- &xdr, &toklen);
- if (ret < 0)
- return ret;
- }
- }
-
- *_xdr = xdr;
- *_toklen = toklen;
- _leave(" = 0 [toklen=%u]", toklen);
- return 0;
-}
-
-/*
- * extract a krb5 ticket
- */
-static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen,
- const __be32 **_xdr, unsigned int *_toklen)
-{
- const __be32 *xdr = *_xdr;
- unsigned int toklen = *_toklen, len, paddedlen;
-
- /* there must be at least one length word */
- if (toklen <= 4)
- return -EINVAL;
-
- _enter(",{%x},%u", ntohl(xdr[0]), toklen);
-
- len = ntohl(*xdr++);
- toklen -= 4;
- if (len > AFSTOKEN_K5_TIX_MAX)
- return -EINVAL;
- paddedlen = (len + 3) & ~3;
- if (paddedlen > toklen)
- return -EINVAL;
- *_tktlen = len;
-
- _debug("ticket len %u", len);
-
- if (len > 0) {
- *_ticket = kmemdup(xdr, len, GFP_KERNEL);
- if (!*_ticket)
- return -ENOMEM;
- toklen -= paddedlen;
- xdr += paddedlen >> 2;
- }
-
- *_xdr = xdr;
- *_toklen = toklen;
- _leave(" = 0 [toklen=%u]", toklen);
- return 0;
-}
-
-/*
- * parse an RxK5 type XDR format token
- * - the caller guarantees we have at least 4 words
- */
-static int rxrpc_preparse_xdr_rxk5(struct key_preparsed_payload *prep,
- size_t datalen,
- const __be32 *xdr, unsigned int toklen)
-{
- struct rxrpc_key_token *token, **pptoken;
- struct rxk5_key *rxk5;
- const __be32 *end_xdr = xdr + (toklen >> 2);
- time64_t expiry;
- int ret;
-
- _enter(",{%x,%x,%x,%x},%u",
- ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]),
- toklen);
-
- /* reserve some payload space for this subkey - the length of the token
- * is a reasonable approximation */
- prep->quotalen = datalen + toklen;
-
- token = kzalloc(sizeof(*token), GFP_KERNEL);
- if (!token)
- return -ENOMEM;
-
- rxk5 = kzalloc(sizeof(*rxk5), GFP_KERNEL);
- if (!rxk5) {
- kfree(token);
- return -ENOMEM;
- }
-
- token->security_index = RXRPC_SECURITY_RXK5;
- token->k5 = rxk5;
-
- /* extract the principals */
- ret = rxrpc_krb5_decode_principal(&rxk5->client, &xdr, &toklen);
- if (ret < 0)
- goto error;
- ret = rxrpc_krb5_decode_principal(&rxk5->server, &xdr, &toklen);
- if (ret < 0)
- goto error;
-
- /* extract the session key and the encoding type (the tag field ->
- * ENCTYPE_xxx) */
- ret = rxrpc_krb5_decode_tagged_data(&rxk5->session, AFSTOKEN_DATA_MAX,
- &xdr, &toklen);
- if (ret < 0)
- goto error;
-
- if (toklen < 4 * 8 + 2 * 4)
- goto inval;
- rxk5->authtime = be64_to_cpup((const __be64 *) xdr);
- xdr += 2;
- rxk5->starttime = be64_to_cpup((const __be64 *) xdr);
- xdr += 2;
- rxk5->endtime = be64_to_cpup((const __be64 *) xdr);
- xdr += 2;
- rxk5->renew_till = be64_to_cpup((const __be64 *) xdr);
- xdr += 2;
- rxk5->is_skey = ntohl(*xdr++);
- rxk5->flags = ntohl(*xdr++);
- toklen -= 4 * 8 + 2 * 4;
-
- _debug("times: a=%llx s=%llx e=%llx rt=%llx",
- rxk5->authtime, rxk5->starttime, rxk5->endtime,
- rxk5->renew_till);
- _debug("is_skey=%x flags=%x", rxk5->is_skey, rxk5->flags);
-
- /* extract the permitted client addresses */
- ret = rxrpc_krb5_decode_tagged_array(&rxk5->addresses,
- &rxk5->n_addresses,
- AFSTOKEN_K5_ADDRESSES_MAX,
- AFSTOKEN_DATA_MAX,
- &xdr, &toklen);
- if (ret < 0)
- goto error;
-
- ASSERTCMP((end_xdr - xdr) << 2, ==, toklen);
-
- /* extract the tickets */
- ret = rxrpc_krb5_decode_ticket(&rxk5->ticket, &rxk5->ticket_len,
- &xdr, &toklen);
- if (ret < 0)
- goto error;
- ret = rxrpc_krb5_decode_ticket(&rxk5->ticket2, &rxk5->ticket2_len,
- &xdr, &toklen);
- if (ret < 0)
- goto error;
-
- ASSERTCMP((end_xdr - xdr) << 2, ==, toklen);
-
- /* extract the typed auth data */
- ret = rxrpc_krb5_decode_tagged_array(&rxk5->authdata,
- &rxk5->n_authdata,
- AFSTOKEN_K5_AUTHDATA_MAX,
- AFSTOKEN_BDATALN_MAX,
- &xdr, &toklen);
- if (ret < 0)
- goto error;
-
- ASSERTCMP((end_xdr - xdr) << 2, ==, toklen);
-
- if (toklen != 0)
- goto inval;
-
- /* attach the payload */
- for (pptoken = (struct rxrpc_key_token **)&prep->payload.data[0];
- *pptoken;
- pptoken = &(*pptoken)->next)
- continue;
- *pptoken = token;
- expiry = rxrpc_u32_to_time64(token->k5->endtime);
- if (expiry < prep->expiry)
- prep->expiry = expiry;
-
- _leave(" = 0");
- return 0;
-
-inval:
- ret = -EINVAL;
-error:
- rxrpc_rxk5_free(rxk5);
- kfree(token);
- _leave(" = %d", ret);
- return ret;
-}
-
/*
* attempt to parse the data as the XDR format
* - the caller guarantees we have more than 7 words
*/
static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep)
{
- const __be32 *xdr = prep->data, *token;
+ const __be32 *xdr = prep->data, *token, *p;
const char *cp;
unsigned int len, paddedlen, loop, ntoken, toklen, sec_ix;
size_t datalen = prep->datalen;
- int ret;
+ int ret, ret2;
_enter(",{%x,%x,%x,%x},%zu",
ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]),
goto not_xdr;
/* check each token wrapper */
- token = xdr;
+ p = xdr;
loop = ntoken;
do {
if (datalen < 8)
goto not_xdr;
- toklen = ntohl(*xdr++);
- sec_ix = ntohl(*xdr);
+ toklen = ntohl(*p++);
+ sec_ix = ntohl(*p);
datalen -= 4;
_debug("token: [%x/%zx] %x", toklen, datalen, sec_ix);
paddedlen = (toklen + 3) & ~3;
if (toklen < 20 || toklen > datalen || paddedlen > datalen)
goto not_xdr;
datalen -= paddedlen;
- xdr += paddedlen >> 2;
+ p += paddedlen >> 2;
} while (--loop > 0);
/* okay: we're going to assume it's valid XDR format
* - we ignore the cellname, relying on the key to be correctly named
*/
+ ret = -EPROTONOSUPPORT;
do {
- xdr = token;
toklen = ntohl(*xdr++);
- token = xdr + ((toklen + 3) >> 2);
- sec_ix = ntohl(*xdr++);
+ token = xdr;
+ xdr += (toklen + 3) / 4;
+
+ sec_ix = ntohl(*token++);
toklen -= 4;
- _debug("TOKEN type=%u [%p-%p]", sec_ix, xdr, token);
+ _debug("TOKEN type=%x len=%x", sec_ix, toklen);
switch (sec_ix) {
case RXRPC_SECURITY_RXKAD:
- ret = rxrpc_preparse_xdr_rxkad(prep, datalen, xdr, toklen);
- if (ret != 0)
- goto error;
+ ret2 = rxrpc_preparse_xdr_rxkad(prep, datalen, token, toklen);
break;
+ default:
+ ret2 = -EPROTONOSUPPORT;
+ break;
+ }
- case RXRPC_SECURITY_RXK5:
- ret = rxrpc_preparse_xdr_rxk5(prep, datalen, xdr, toklen);
+ switch (ret2) {
+ case 0:
+ ret = 0;
+ break;
+ case -EPROTONOSUPPORT:
+ break;
+ case -ENOPKG:
if (ret != 0)
- goto error;
+ ret = -ENOPKG;
break;
-
default:
- ret = -EPROTONOSUPPORT;
+ ret = ret2;
goto error;
}
} while (--ntoken > 0);
- _leave(" = 0");
- return 0;
+error:
+ _leave(" = %d", ret);
+ return ret;
not_xdr:
_leave(" = -EPROTO");
return -EPROTO;
-error:
- _leave(" = %d", ret);
- return ret;
}
/*
case RXRPC_SECURITY_RXKAD:
kfree(token->kad);
break;
- case RXRPC_SECURITY_RXK5:
- if (token->k5)
- rxrpc_rxk5_free(token->k5);
- break;
default:
pr_err("Unknown token type %x on rxrpc key\n",
token->security_index);
rxrpc_free_token_list(prep->payload.data[0]);
}
-/*
- * Preparse a server secret key.
- *
- * The data should be the 8-byte secret key.
- */
-static int rxrpc_preparse_s(struct key_preparsed_payload *prep)
-{
- struct crypto_skcipher *ci;
-
- _enter("%zu", prep->datalen);
-
- if (prep->datalen != 8)
- return -EINVAL;
-
- memcpy(&prep->payload.data[2], prep->data, 8);
-
- ci = crypto_alloc_skcipher("pcbc(des)", 0, CRYPTO_ALG_ASYNC);
- if (IS_ERR(ci)) {
- _leave(" = %ld", PTR_ERR(ci));
- return PTR_ERR(ci);
- }
-
- if (crypto_skcipher_setkey(ci, prep->data, 8) < 0)
- BUG();
-
- prep->payload.data[0] = ci;
- _leave(" = 0");
- return 0;
-}
-
-/*
- * Clean up preparse data.
- */
-static void rxrpc_free_preparse_s(struct key_preparsed_payload *prep)
-{
- if (prep->payload.data[0])
- crypto_free_skcipher(prep->payload.data[0]);
-}
-
/*
* dispose of the data dangling from the corpse of a rxrpc key
*/
rxrpc_free_token_list(key->payload.data[0]);
}
-/*
- * dispose of the data dangling from the corpse of a rxrpc key
- */
-static void rxrpc_destroy_s(struct key *key)
-{
- if (key->payload.data[0]) {
- crypto_free_skcipher(key->payload.data[0]);
- key->payload.data[0] = NULL;
- }
-}
-
/*
* describe the rxrpc key
*/
static void rxrpc_describe(const struct key *key, struct seq_file *m)
{
+ const struct rxrpc_key_token *token;
+ const char *sep = ": ";
+
seq_puts(m, key->description);
+
+ for (token = key->payload.data[0]; token; token = token->next) {
+ seq_puts(m, sep);
+
+ switch (token->security_index) {
+ case RXRPC_SECURITY_RXKAD:
+ seq_puts(m, "ka");
+ break;
+ default: /* we have a ticket we can't encode */
+ seq_printf(m, "%u", token->security_index);
+ break;
+ }
+
+ sep = " ";
+ }
}
/*
return 0;
}
-/*
- * grab the security keyring for a server socket
- */
-int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen)
-{
- struct key *key;
- char *description;
-
- _enter("");
-
- if (optlen <= 0 || optlen > PAGE_SIZE - 1)
- return -EINVAL;
-
- description = memdup_sockptr_nul(optval, optlen);
- if (IS_ERR(description))
- return PTR_ERR(description);
-
- key = request_key(&key_type_keyring, description, NULL);
- if (IS_ERR(key)) {
- kfree(description);
- _leave(" = %ld", PTR_ERR(key));
- return PTR_ERR(key);
- }
-
- rx->securities = key;
- kfree(description);
- _leave(" = 0 [key %x]", key->serial);
- return 0;
-}
-
/*
* generate a server data key
*/
char *buffer, size_t buflen)
{
const struct rxrpc_key_token *token;
- const struct krb5_principal *princ;
size_t size;
__be32 *xdr, *oldxdr;
u32 cnlen, toksize, ntoks, tok, zero;
u16 toksizes[AFSTOKEN_MAX];
- int loop;
_enter("");
case RXRPC_SECURITY_RXKAD:
toksize += 8 * 4; /* viceid, kvno, key*2, begin,
* end, primary, tktlen */
- toksize += RND(token->kad->ticket_len);
- break;
-
- case RXRPC_SECURITY_RXK5:
- princ = &token->k5->client;
- toksize += 4 + princ->n_name_parts * 4;
- for (loop = 0; loop < princ->n_name_parts; loop++)
- toksize += RND(strlen(princ->name_parts[loop]));
- toksize += 4 + RND(strlen(princ->realm));
-
- princ = &token->k5->server;
- toksize += 4 + princ->n_name_parts * 4;
- for (loop = 0; loop < princ->n_name_parts; loop++)
- toksize += RND(strlen(princ->name_parts[loop]));
- toksize += 4 + RND(strlen(princ->realm));
-
- toksize += 8 + RND(token->k5->session.data_len);
-
- toksize += 4 * 8 + 2 * 4;
-
- toksize += 4 + token->k5->n_addresses * 8;
- for (loop = 0; loop < token->k5->n_addresses; loop++)
- toksize += RND(token->k5->addresses[loop].data_len);
-
- toksize += 4 + RND(token->k5->ticket_len);
- toksize += 4 + RND(token->k5->ticket2_len);
-
- toksize += 4 + token->k5->n_authdata * 8;
- for (loop = 0; loop < token->k5->n_authdata; loop++)
- toksize += RND(token->k5->authdata[loop].data_len);
+ if (!token->no_leak_key)
+ toksize += RND(token->kad->ticket_len);
break;
default: /* we have a ticket we can't encode */
ENCODE(token->kad->start);
ENCODE(token->kad->expiry);
ENCODE(token->kad->primary_flag);
- ENCODE_DATA(token->kad->ticket_len, token->kad->ticket);
- break;
-
- case RXRPC_SECURITY_RXK5:
- princ = &token->k5->client;
- ENCODE(princ->n_name_parts);
- for (loop = 0; loop < princ->n_name_parts; loop++)
- ENCODE_STR(princ->name_parts[loop]);
- ENCODE_STR(princ->realm);
-
- princ = &token->k5->server;
- ENCODE(princ->n_name_parts);
- for (loop = 0; loop < princ->n_name_parts; loop++)
- ENCODE_STR(princ->name_parts[loop]);
- ENCODE_STR(princ->realm);
-
- ENCODE(token->k5->session.tag);
- ENCODE_DATA(token->k5->session.data_len,
- token->k5->session.data);
-
- ENCODE64(token->k5->authtime);
- ENCODE64(token->k5->starttime);
- ENCODE64(token->k5->endtime);
- ENCODE64(token->k5->renew_till);
- ENCODE(token->k5->is_skey);
- ENCODE(token->k5->flags);
-
- ENCODE(token->k5->n_addresses);
- for (loop = 0; loop < token->k5->n_addresses; loop++) {
- ENCODE(token->k5->addresses[loop].tag);
- ENCODE_DATA(token->k5->addresses[loop].data_len,
- token->k5->addresses[loop].data);
- }
-
- ENCODE_DATA(token->k5->ticket_len, token->k5->ticket);
- ENCODE_DATA(token->k5->ticket2_len, token->k5->ticket2);
-
- ENCODE(token->k5->n_authdata);
- for (loop = 0; loop < token->k5->n_authdata; loop++) {
- ENCODE(token->k5->authdata[loop].tag);
- ENCODE_DATA(token->k5->authdata[loop].data_len,
- token->k5->authdata[loop].data);
- }
+ if (token->no_leak_key)
+ ENCODE(0);
+ else
+ ENCODE_DATA(token->kad->ticket_len, token->kad->ticket);
break;
default:
#include <linux/scatterlist.h>
#include <linux/ctype.h>
#include <linux/slab.h>
+#include <linux/key-type.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include <keys/rxrpc-type.h>
#define INST_SZ 40 /* size of principal's instance */
#define REALM_SZ 40 /* size of principal's auth domain */
#define SNAME_SZ 40 /* size of service name */
+#define RXKAD_ALIGN 8
struct rxkad_level1_hdr {
__be32 data_size; /* true data size (excluding padding) */
__be32 checksum; /* decrypted data checksum */
};
+static int rxkad_prime_packet_security(struct rxrpc_connection *conn,
+ struct crypto_sync_skcipher *ci);
+
/*
* this holds a pinned cipher so that keventd doesn't get called by the cipher
* alloc routine, but since we have it to hand, we use it to decrypt RESPONSE
static struct skcipher_request *rxkad_ci_req;
static DEFINE_MUTEX(rxkad_ci_mutex);
+/*
+ * Parse the information from a server key
+ *
+ * The data should be the 8-byte secret key.
+ */
+static int rxkad_preparse_server_key(struct key_preparsed_payload *prep)
+{
+ struct crypto_skcipher *ci;
+
+ if (prep->datalen != 8)
+ return -EINVAL;
+
+ memcpy(&prep->payload.data[2], prep->data, 8);
+
+ ci = crypto_alloc_skcipher("pcbc(des)", 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(ci)) {
+ _leave(" = %ld", PTR_ERR(ci));
+ return PTR_ERR(ci);
+ }
+
+ if (crypto_skcipher_setkey(ci, prep->data, 8) < 0)
+ BUG();
+
+ prep->payload.data[0] = ci;
+ _leave(" = 0");
+ return 0;
+}
+
+static void rxkad_free_preparse_server_key(struct key_preparsed_payload *prep)
+{
+
+ if (prep->payload.data[0])
+ crypto_free_skcipher(prep->payload.data[0]);
+}
+
+static void rxkad_destroy_server_key(struct key *key)
+{
+ if (key->payload.data[0]) {
+ crypto_free_skcipher(key->payload.data[0]);
+ key->payload.data[0] = NULL;
+ }
+}
+
/*
* initialise connection security
*/
-static int rxkad_init_connection_security(struct rxrpc_connection *conn)
+static int rxkad_init_connection_security(struct rxrpc_connection *conn,
+ struct rxrpc_key_token *token)
{
struct crypto_sync_skcipher *ci;
- struct rxrpc_key_token *token;
int ret;
_enter("{%d},{%x}", conn->debug_id, key_serial(conn->params.key));
- token = conn->params.key->payload.data[0];
conn->security_ix = token->security_index;
ci = crypto_alloc_sync_skcipher("pcbc(fcrypt)", 0, 0);
switch (conn->params.security_level) {
case RXRPC_SECURITY_PLAIN:
- break;
case RXRPC_SECURITY_AUTH:
- conn->size_align = 8;
- conn->security_size = sizeof(struct rxkad_level1_hdr);
- break;
case RXRPC_SECURITY_ENCRYPT:
- conn->size_align = 8;
- conn->security_size = sizeof(struct rxkad_level2_hdr);
break;
default:
ret = -EKEYREJECTED;
goto error;
}
- conn->cipher = ci;
- ret = 0;
+ ret = rxkad_prime_packet_security(conn, ci);
+ if (ret < 0)
+ goto error_ci;
+
+ conn->rxkad.cipher = ci;
+ return 0;
+
+error_ci:
+ crypto_free_sync_skcipher(ci);
error:
_leave(" = %d", ret);
return ret;
}
+/*
+ * Work out how much data we can put in a packet.
+ */
+static int rxkad_how_much_data(struct rxrpc_call *call, size_t remain,
+ size_t *_buf_size, size_t *_data_size, size_t *_offset)
+{
+ size_t shdr, buf_size, chunk;
+
+ switch (call->conn->params.security_level) {
+ default:
+ buf_size = chunk = min_t(size_t, remain, RXRPC_JUMBO_DATALEN);
+ shdr = 0;
+ goto out;
+ case RXRPC_SECURITY_AUTH:
+ shdr = sizeof(struct rxkad_level1_hdr);
+ break;
+ case RXRPC_SECURITY_ENCRYPT:
+ shdr = sizeof(struct rxkad_level2_hdr);
+ break;
+ }
+
+ buf_size = round_down(RXRPC_JUMBO_DATALEN, RXKAD_ALIGN);
+
+ chunk = buf_size - shdr;
+ if (remain < chunk)
+ buf_size = round_up(shdr + remain, RXKAD_ALIGN);
+
+out:
+ *_buf_size = buf_size;
+ *_data_size = chunk;
+ *_offset = shdr;
+ return 0;
+}
+
/*
* prime the encryption state with the invariant parts of a connection's
* description
*/
-static int rxkad_prime_packet_security(struct rxrpc_connection *conn)
+static int rxkad_prime_packet_security(struct rxrpc_connection *conn,
+ struct crypto_sync_skcipher *ci)
{
struct skcipher_request *req;
struct rxrpc_key_token *token;
if (!tmpbuf)
return -ENOMEM;
- req = skcipher_request_alloc(&conn->cipher->base, GFP_NOFS);
+ req = skcipher_request_alloc(&ci->base, GFP_NOFS);
if (!req) {
kfree(tmpbuf);
return -ENOMEM;
tmpbuf[3] = htonl(conn->security_ix);
sg_init_one(&sg, tmpbuf, tmpsize);
- skcipher_request_set_sync_tfm(req, conn->cipher);
+ skcipher_request_set_sync_tfm(req, ci);
skcipher_request_set_callback(req, 0, NULL, NULL);
skcipher_request_set_crypt(req, &sg, &sg, tmpsize, iv.x);
crypto_skcipher_encrypt(req);
skcipher_request_free(req);
- memcpy(&conn->csum_iv, tmpbuf + 2, sizeof(conn->csum_iv));
+ memcpy(&conn->rxkad.csum_iv, tmpbuf + 2, sizeof(conn->rxkad.csum_iv));
kfree(tmpbuf);
_leave(" = 0");
return 0;
*/
static struct skcipher_request *rxkad_get_call_crypto(struct rxrpc_call *call)
{
- struct crypto_skcipher *tfm = &call->conn->cipher->base;
+ struct crypto_skcipher *tfm = &call->conn->rxkad.cipher->base;
struct skcipher_request *cipher_req = call->cipher_req;
if (!cipher_req) {
* partially encrypt a packet (level 1 security)
*/
static int rxkad_secure_packet_auth(const struct rxrpc_call *call,
- struct sk_buff *skb,
- u32 data_size,
- void *sechdr,
+ struct sk_buff *skb, u32 data_size,
struct skcipher_request *req)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxkad_level1_hdr hdr;
struct rxrpc_crypt iv;
struct scatterlist sg;
+ size_t pad;
u16 check;
_enter("");
data_size |= (u32)check << 16;
hdr.data_size = htonl(data_size);
- memcpy(sechdr, &hdr, sizeof(hdr));
+ memcpy(skb->head, &hdr, sizeof(hdr));
+
+ pad = sizeof(struct rxkad_level1_hdr) + data_size;
+ pad = RXKAD_ALIGN - pad;
+ pad &= RXKAD_ALIGN - 1;
+ if (pad)
+ skb_put_zero(skb, pad);
/* start the encryption afresh */
memset(&iv, 0, sizeof(iv));
- sg_init_one(&sg, sechdr, 8);
- skcipher_request_set_sync_tfm(req, call->conn->cipher);
+ sg_init_one(&sg, skb->head, 8);
+ skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
skcipher_request_set_callback(req, 0, NULL, NULL);
skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x);
crypto_skcipher_encrypt(req);
static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call,
struct sk_buff *skb,
u32 data_size,
- void *sechdr,
struct skcipher_request *req)
{
const struct rxrpc_key_token *token;
struct rxrpc_crypt iv;
struct scatterlist sg[16];
unsigned int len;
+ size_t pad;
u16 check;
int err;
rxkhdr.data_size = htonl(data_size | (u32)check << 16);
rxkhdr.checksum = 0;
- memcpy(sechdr, &rxkhdr, sizeof(rxkhdr));
+ memcpy(skb->head, &rxkhdr, sizeof(rxkhdr));
+
+ pad = sizeof(struct rxkad_level2_hdr) + data_size;
+ pad = RXKAD_ALIGN - pad;
+ pad &= RXKAD_ALIGN - 1;
+ if (pad)
+ skb_put_zero(skb, pad);
/* encrypt from the session key */
token = call->conn->params.key->payload.data[0];
memcpy(&iv, token->kad->session_key, sizeof(iv));
- sg_init_one(&sg[0], sechdr, sizeof(rxkhdr));
- skcipher_request_set_sync_tfm(req, call->conn->cipher);
+ sg_init_one(&sg[0], skb->head, sizeof(rxkhdr));
+ skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
skcipher_request_set_callback(req, 0, NULL, NULL);
skcipher_request_set_crypt(req, &sg[0], &sg[0], sizeof(rxkhdr), iv.x);
crypto_skcipher_encrypt(req);
if (skb_shinfo(skb)->nr_frags > 16)
goto out;
- len = data_size + call->conn->size_align - 1;
- len &= ~(call->conn->size_align - 1);
+ len = round_up(data_size, RXKAD_ALIGN);
sg_init_table(sg, ARRAY_SIZE(sg));
- err = skb_to_sgvec(skb, sg, 0, len);
+ err = skb_to_sgvec(skb, sg, 8, len);
if (unlikely(err < 0))
goto out;
skcipher_request_set_crypt(req, sg, sg, len, iv.x);
*/
static int rxkad_secure_packet(struct rxrpc_call *call,
struct sk_buff *skb,
- size_t data_size,
- void *sechdr)
+ size_t data_size)
{
struct rxrpc_skb_priv *sp;
struct skcipher_request *req;
call->debug_id, key_serial(call->conn->params.key),
sp->hdr.seq, data_size);
- if (!call->conn->cipher)
+ if (!call->conn->rxkad.cipher)
return 0;
ret = key_validate(call->conn->params.key);
return -ENOMEM;
/* continue encrypting from where we left off */
- memcpy(&iv, call->conn->csum_iv.x, sizeof(iv));
+ memcpy(&iv, call->conn->rxkad.csum_iv.x, sizeof(iv));
/* calculate the security checksum */
x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT);
call->crypto_buf[1] = htonl(x);
sg_init_one(&sg, call->crypto_buf, 8);
- skcipher_request_set_sync_tfm(req, call->conn->cipher);
+ skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
skcipher_request_set_callback(req, 0, NULL, NULL);
skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x);
crypto_skcipher_encrypt(req);
ret = 0;
break;
case RXRPC_SECURITY_AUTH:
- ret = rxkad_secure_packet_auth(call, skb, data_size, sechdr,
- req);
+ ret = rxkad_secure_packet_auth(call, skb, data_size, req);
break;
case RXRPC_SECURITY_ENCRYPT:
- ret = rxkad_secure_packet_encrypt(call, skb, data_size,
- sechdr, req);
+ ret = rxkad_secure_packet_encrypt(call, skb, data_size, req);
break;
default:
ret = -EPERM;
/* start the decryption afresh */
memset(&iv, 0, sizeof(iv));
- skcipher_request_set_sync_tfm(req, call->conn->cipher);
+ skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
skcipher_request_set_callback(req, 0, NULL, NULL);
skcipher_request_set_crypt(req, sg, sg, 8, iv.x);
crypto_skcipher_decrypt(req);
token = call->conn->params.key->payload.data[0];
memcpy(&iv, token->kad->session_key, sizeof(iv));
- skcipher_request_set_sync_tfm(req, call->conn->cipher);
+ skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
skcipher_request_set_callback(req, 0, NULL, NULL);
skcipher_request_set_crypt(req, sg, sg, len, iv.x);
crypto_skcipher_decrypt(req);
_enter("{%d{%x}},{#%u}",
call->debug_id, key_serial(call->conn->params.key), seq);
- if (!call->conn->cipher)
+ if (!call->conn->rxkad.cipher)
return 0;
req = rxkad_get_call_crypto(call);
return -ENOMEM;
/* continue encrypting from where we left off */
- memcpy(&iv, call->conn->csum_iv.x, sizeof(iv));
+ memcpy(&iv, call->conn->rxkad.csum_iv.x, sizeof(iv));
/* validate the security checksum */
x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT);
call->crypto_buf[1] = htonl(x);
sg_init_one(&sg, call->crypto_buf, 8);
- skcipher_request_set_sync_tfm(req, call->conn->cipher);
+ skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
skcipher_request_set_callback(req, 0, NULL, NULL);
skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x);
crypto_skcipher_encrypt(req);
u32 serial;
int ret;
- _enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key));
+ _enter("{%d}", conn->debug_id);
- ret = key_validate(conn->server_key);
- if (ret < 0)
- return ret;
-
- get_random_bytes(&conn->security_nonce, sizeof(conn->security_nonce));
+ get_random_bytes(&conn->rxkad.nonce, sizeof(conn->rxkad.nonce));
challenge.version = htonl(2);
- challenge.nonce = htonl(conn->security_nonce);
+ challenge.nonce = htonl(conn->rxkad.nonce);
challenge.min_level = htonl(0);
challenge.__padding = 0;
struct rxrpc_crypt iv;
struct scatterlist sg[1];
- req = skcipher_request_alloc(&conn->cipher->base, GFP_NOFS);
+ req = skcipher_request_alloc(&conn->rxkad.cipher->base, GFP_NOFS);
if (!req)
return -ENOMEM;
sg_init_table(sg, 1);
sg_set_buf(sg, &resp->encrypted, sizeof(resp->encrypted));
- skcipher_request_set_sync_tfm(req, conn->cipher);
+ skcipher_request_set_sync_tfm(req, conn->rxkad.cipher);
skcipher_request_set_callback(req, 0, NULL, NULL);
skcipher_request_set_crypt(req, sg, sg, sizeof(resp->encrypted), iv.x);
crypto_skcipher_encrypt(req);
* decrypt the kerberos IV ticket in the response
*/
static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
+ struct key *server_key,
struct sk_buff *skb,
void *ticket, size_t ticket_len,
struct rxrpc_crypt *_session_key,
u32 abort_code;
u8 *p, *q, *name, *end;
- _enter("{%d},{%x}", conn->debug_id, key_serial(conn->server_key));
+ _enter("{%d},{%x}", conn->debug_id, key_serial(server_key));
*_expiry = 0;
- ret = key_validate(conn->server_key);
- if (ret < 0) {
- switch (ret) {
- case -EKEYEXPIRED:
- abort_code = RXKADEXPIRED;
- goto other_error;
- default:
- abort_code = RXKADNOAUTH;
- goto other_error;
- }
- }
-
- ASSERT(conn->server_key->payload.data[0] != NULL);
+ ASSERT(server_key->payload.data[0] != NULL);
ASSERTCMP((unsigned long) ticket & 7UL, ==, 0);
- memcpy(&iv, &conn->server_key->payload.data[2], sizeof(iv));
+ memcpy(&iv, &server_key->payload.data[2], sizeof(iv));
ret = -ENOMEM;
- req = skcipher_request_alloc(conn->server_key->payload.data[0],
- GFP_NOFS);
+ req = skcipher_request_alloc(server_key->payload.data[0], GFP_NOFS);
if (!req)
goto temporary_error;
struct rxkad_response *response;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt session_key;
+ struct key *server_key;
const char *eproto;
time64_t expiry;
void *ticket;
__be32 csum;
int ret, i;
- _enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key));
+ _enter("{%d}", conn->debug_id);
+
+ server_key = rxrpc_look_up_server_security(conn, skb, 0, 0);
+ if (IS_ERR(server_key)) {
+ switch (PTR_ERR(server_key)) {
+ case -ENOKEY:
+ abort_code = RXKADUNKNOWNKEY;
+ break;
+ case -EKEYEXPIRED:
+ abort_code = RXKADEXPIRED;
+ break;
+ default:
+ abort_code = RXKADNOAUTH;
+ break;
+ }
+ trace_rxrpc_abort(0, "SVK",
+ sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ abort_code, PTR_ERR(server_key));
+ *_abort_code = abort_code;
+ return -EPROTO;
+ }
ret = -ENOMEM;
response = kzalloc(sizeof(struct rxkad_response), GFP_NOFS);
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
response, sizeof(*response)) < 0)
goto protocol_error;
- if (!pskb_pull(skb, sizeof(*response)))
- BUG();
version = ntohl(response->version);
ticket_len = ntohl(response->ticket_len);
eproto = tracepoint_string("rxkad_tkt_short");
abort_code = RXKADPACKETSHORT;
- if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
+ if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response),
ticket, ticket_len) < 0)
goto protocol_error_free;
- ret = rxkad_decrypt_ticket(conn, skb, ticket, ticket_len, &session_key,
- &expiry, _abort_code);
+ ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len,
+ &session_key, &expiry, _abort_code);
if (ret < 0)
goto temporary_error_free_ticket;
eproto = tracepoint_string("rxkad_rsp_seq");
abort_code = RXKADOUTOFSEQUENCE;
- if (ntohl(response->encrypted.inc_nonce) != conn->security_nonce + 1)
+ if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1)
goto protocol_error_free;
eproto = tracepoint_string("rxkad_rsp_level");
protocol_error:
kfree(response);
trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
+ key_put(server_key);
*_abort_code = abort_code;
return -EPROTO;
* ENOMEM. We just want to send the challenge again. Note that we
* also come out this way if the ticket decryption fails.
*/
+ key_put(server_key);
return ret;
}
{
_enter("");
- if (conn->cipher)
- crypto_free_sync_skcipher(conn->cipher);
+ if (conn->rxkad.cipher)
+ crypto_free_sync_skcipher(conn->rxkad.cipher);
}
/*
.no_key_abort = RXKADUNKNOWNKEY,
.init = rxkad_init,
.exit = rxkad_exit,
+ .preparse_server_key = rxkad_preparse_server_key,
+ .free_preparse_server_key = rxkad_free_preparse_server_key,
+ .destroy_server_key = rxkad_destroy_server_key,
.init_connection_security = rxkad_init_connection_security,
- .prime_packet_security = rxkad_prime_packet_security,
+ .how_much_data = rxkad_how_much_data,
.secure_packet = rxkad_secure_packet,
.verify_packet = rxkad_verify_packet,
.free_call_crypto = rxkad_free_call_crypto,
/*
* look up an rxrpc security module
*/
-static const struct rxrpc_security *rxrpc_security_lookup(u8 security_index)
+const struct rxrpc_security *rxrpc_security_lookup(u8 security_index)
{
if (security_index >= ARRAY_SIZE(rxrpc_security_types))
return NULL;
if (ret < 0)
return ret;
- token = key->payload.data[0];
- if (!token)
- return -EKEYREJECTED;
+ for (token = key->payload.data[0]; token; token = token->next) {
+ sec = rxrpc_security_lookup(token->security_index);
+ if (sec)
+ goto found;
+ }
+ return -EKEYREJECTED;
- sec = rxrpc_security_lookup(token->security_index);
- if (!sec)
- return -EKEYREJECTED;
+found:
conn->security = sec;
- ret = conn->security->init_connection_security(conn);
+ ret = conn->security->init_connection_security(conn, token);
if (ret < 0) {
conn->security = &rxrpc_no_security;
return ret;
}
/*
- * Find the security key for a server connection.
+ * Set the ops a server connection.
*/
-bool rxrpc_look_up_server_security(struct rxrpc_local *local, struct rxrpc_sock *rx,
- const struct rxrpc_security **_sec,
- struct key **_key,
- struct sk_buff *skb)
+const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *rx,
+ struct sk_buff *skb)
{
const struct rxrpc_security *sec;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- key_ref_t kref = NULL;
- char kdesc[5 + 1 + 3 + 1];
_enter("");
- sprintf(kdesc, "%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex);
-
sec = rxrpc_security_lookup(sp->hdr.securityIndex);
if (!sec) {
trace_rxrpc_abort(0, "SVS",
RX_INVALID_OPERATION, EKEYREJECTED);
skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
skb->priority = RX_INVALID_OPERATION;
- return false;
+ return NULL;
}
- if (sp->hdr.securityIndex == RXRPC_SECURITY_NONE)
- goto out;
-
- if (!rx->securities) {
+ if (sp->hdr.securityIndex != RXRPC_SECURITY_NONE &&
+ !rx->securities) {
trace_rxrpc_abort(0, "SVR",
sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
RX_INVALID_OPERATION, EKEYREJECTED);
skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
- skb->priority = RX_INVALID_OPERATION;
- return false;
+ skb->priority = sec->no_key_abort;
+ return NULL;
}
+ return sec;
+}
+
+/*
+ * Find the security key for a server connection.
+ */
+struct key *rxrpc_look_up_server_security(struct rxrpc_connection *conn,
+ struct sk_buff *skb,
+ u32 kvno, u32 enctype)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ struct rxrpc_sock *rx;
+ struct key *key = ERR_PTR(-EKEYREJECTED);
+ key_ref_t kref = NULL;
+ char kdesc[5 + 1 + 3 + 1 + 12 + 1 + 12 + 1];
+ int ret;
+
+ _enter("");
+
+ if (enctype)
+ sprintf(kdesc, "%u:%u:%u:%u",
+ sp->hdr.serviceId, sp->hdr.securityIndex, kvno, enctype);
+ else if (kvno)
+ sprintf(kdesc, "%u:%u:%u",
+ sp->hdr.serviceId, sp->hdr.securityIndex, kvno);
+ else
+ sprintf(kdesc, "%u:%u",
+ sp->hdr.serviceId, sp->hdr.securityIndex);
+
+ rcu_read_lock();
+
+ rx = rcu_dereference(conn->params.local->service);
+ if (!rx)
+ goto out;
+
/* look through the service's keyring */
kref = keyring_search(make_key_ref(rx->securities, 1UL),
&key_type_rxrpc_s, kdesc, true);
if (IS_ERR(kref)) {
- trace_rxrpc_abort(0, "SVK",
- sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- sec->no_key_abort, EKEYREJECTED);
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
- skb->priority = sec->no_key_abort;
- return false;
+ key = ERR_CAST(kref);
+ goto out;
+ }
+
+ key = key_ref_to_ptr(kref);
+
+ ret = key_validate(key);
+ if (ret < 0) {
+ key_put(key);
+ key = ERR_PTR(ret);
+ goto out;
}
out:
- *_sec = sec;
- *_key = key_ref_to_ptr(kref);
- return true;
+ rcu_read_unlock();
+ return key;
}
rxrpc_send_ack_packet(call, false, NULL);
if (!skb) {
- size_t size, chunk, max, space;
+ size_t remain, bufsize, chunk, offset;
_debug("alloc");
goto maybe_error;
}
- max = RXRPC_JUMBO_DATALEN;
- max -= call->conn->security_size;
- max &= ~(call->conn->size_align - 1UL);
-
- chunk = max;
- if (chunk > msg_data_left(msg) && !more)
- chunk = msg_data_left(msg);
-
- space = chunk + call->conn->size_align;
- space &= ~(call->conn->size_align - 1UL);
-
- size = space + call->conn->security_size;
+ /* Work out the maximum size of a packet. Assume that
+ * the security header is going to be in the padded
+ * region (enc blocksize), but the trailer is not.
+ */
+ remain = more ? INT_MAX : msg_data_left(msg);
+ ret = call->conn->security->how_much_data(call, remain,
+ &bufsize, &chunk, &offset);
+ if (ret < 0)
+ goto maybe_error;
- _debug("SIZE: %zu/%zu/%zu", chunk, space, size);
+ _debug("SIZE: %zu/%zu @%zu", chunk, bufsize, offset);
/* create a buffer that we can retain until it's ACK'd */
skb = sock_alloc_send_skb(
- sk, size, msg->msg_flags & MSG_DONTWAIT, &ret);
+ sk, bufsize, msg->msg_flags & MSG_DONTWAIT, &ret);
if (!skb)
goto maybe_error;
ASSERTCMP(skb->mark, ==, 0);
- _debug("HS: %u", call->conn->security_size);
- skb_reserve(skb, call->conn->security_size);
- skb->len += call->conn->security_size;
+ __skb_put(skb, offset);
sp->remain = chunk;
if (sp->remain > skb_tailroom(skb))
(msg_data_left(msg) == 0 && !more)) {
struct rxrpc_connection *conn = call->conn;
uint32_t seq;
- size_t pad;
-
- /* pad out if we're using security */
- if (conn->security_ix) {
- pad = conn->security_size + skb->mark;
- pad = conn->size_align - pad;
- pad &= conn->size_align - 1;
- _debug("pad %zu", pad);
- if (pad)
- skb_put_zero(skb, pad);
- }
seq = call->tx_top + 1;
call->tx_winsize)
sp->hdr.flags |= RXRPC_MORE_PACKETS;
- ret = call->security->secure_packet(
- call, skb, skb->mark, skb->head);
+ ret = call->security->secure_packet(call, skb, skb->mark);
if (ret < 0)
goto out;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* RxRPC key management
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * RxRPC keys should have a description of describing their purpose:
+ * "afs@CAMBRIDGE.REDHAT.COM>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <crypto/skcipher.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/key-type.h>
+#include <linux/ctype.h>
+#include <linux/slab.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <keys/rxrpc-type.h>
+#include <keys/user-type.h>
+#include "ar-internal.h"
+
+static int rxrpc_vet_description_s(const char *);
+static int rxrpc_preparse_s(struct key_preparsed_payload *);
+static void rxrpc_free_preparse_s(struct key_preparsed_payload *);
+static void rxrpc_destroy_s(struct key *);
+static void rxrpc_describe_s(const struct key *, struct seq_file *);
+
+/*
+ * rxrpc server keys take "<serviceId>:<securityIndex>[:<sec-specific>]" as the
+ * description and the key material as the payload.
+ */
+struct key_type key_type_rxrpc_s = {
+ .name = "rxrpc_s",
+ .flags = KEY_TYPE_NET_DOMAIN,
+ .vet_description = rxrpc_vet_description_s,
+ .preparse = rxrpc_preparse_s,
+ .free_preparse = rxrpc_free_preparse_s,
+ .instantiate = generic_key_instantiate,
+ .destroy = rxrpc_destroy_s,
+ .describe = rxrpc_describe_s,
+};
+
+/*
+ * Vet the description for an RxRPC server key.
+ */
+static int rxrpc_vet_description_s(const char *desc)
+{
+ unsigned long service, sec_class;
+ char *p;
+
+ service = simple_strtoul(desc, &p, 10);
+ if (*p != ':' || service > 65535)
+ return -EINVAL;
+ sec_class = simple_strtoul(p + 1, &p, 10);
+ if ((*p && *p != ':') || sec_class < 1 || sec_class > 255)
+ return -EINVAL;
+ return 0;
+}
+
+/*
+ * Preparse a server secret key.
+ */
+static int rxrpc_preparse_s(struct key_preparsed_payload *prep)
+{
+ const struct rxrpc_security *sec;
+ unsigned int service, sec_class;
+ int n;
+
+ _enter("%zu", prep->datalen);
+
+ if (!prep->orig_description)
+ return -EINVAL;
+
+ if (sscanf(prep->orig_description, "%u:%u%n", &service, &sec_class, &n) != 2)
+ return -EINVAL;
+
+ sec = rxrpc_security_lookup(sec_class);
+ if (!sec)
+ return -ENOPKG;
+
+ prep->payload.data[1] = (struct rxrpc_security *)sec;
+
+ return sec->preparse_server_key(prep);
+}
+
+static void rxrpc_free_preparse_s(struct key_preparsed_payload *prep)
+{
+ const struct rxrpc_security *sec = prep->payload.data[1];
+
+ if (sec)
+ sec->free_preparse_server_key(prep);
+}
+
+static void rxrpc_destroy_s(struct key *key)
+{
+ const struct rxrpc_security *sec = key->payload.data[1];
+
+ if (sec)
+ sec->destroy_server_key(key);
+}
+
+static void rxrpc_describe_s(const struct key *key, struct seq_file *m)
+{
+ const struct rxrpc_security *sec = key->payload.data[1];
+
+ seq_puts(m, key->description);
+ if (sec && sec->describe_server_key)
+ sec->describe_server_key(key, m);
+}
+
+/*
+ * grab the security keyring for a server socket
+ */
+int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen)
+{
+ struct key *key;
+ char *description;
+
+ _enter("");
+
+ if (optlen <= 0 || optlen > PAGE_SIZE - 1)
+ return -EINVAL;
+
+ description = memdup_sockptr_nul(optval, optlen);
+ if (IS_ERR(description))
+ return PTR_ERR(description);
+
+ key = request_key(&key_type_keyring, description, NULL);
+ if (IS_ERR(key)) {
+ kfree(description);
+ _leave(" = %ld", PTR_ERR(key));
+ return PTR_ERR(key);
+ }
+
+ rx->securities = key;
+ kfree(description);
+ _leave(" = 0 [key %x]", key->serial);
+ return 0;
+}
obj-y := sch_generic.o sch_mq.o
+obj-$(CONFIG_INET) += sch_frag.o
obj-$(CONFIG_NET_SCHED) += sch_api.o sch_blackhole.o
obj-$(CONFIG_NET_CLS) += cls_api.o
obj-$(CONFIG_NET_CLS_ACT) += act_api.o
#include <net/act_api.h>
#include <net/netlink.h>
+#ifdef CONFIG_INET
+DEFINE_STATIC_KEY_FALSE(tcf_frag_xmit_count);
+EXPORT_SYMBOL_GPL(tcf_frag_xmit_count);
+#endif
+
+int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
+{
+#ifdef CONFIG_INET
+ if (static_branch_unlikely(&tcf_frag_xmit_count))
+ return sch_frag_xmit_hook(skb, xmit);
+#endif
+
+ return xmit(skb);
+}
+EXPORT_SYMBOL_GPL(tcf_dev_queue_xmit);
+
static void tcf_action_goto_chain_exec(const struct tc_action *a,
struct tcf_result *res)
{
return sz;
}
+static int
+tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a, bool from_act)
+{
+ unsigned char *b = skb_tail_pointer(skb);
+ struct tc_cookie *cookie;
+
+ if (nla_put_string(skb, TCA_KIND, a->ops->kind))
+ goto nla_put_failure;
+ if (tcf_action_copy_stats(skb, a, 0))
+ goto nla_put_failure;
+ if (from_act && nla_put_u32(skb, TCA_ACT_INDEX, a->tcfa_index))
+ goto nla_put_failure;
+
+ rcu_read_lock();
+ cookie = rcu_dereference(a->act_cookie);
+ if (cookie) {
+ if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) {
+ rcu_read_unlock();
+ goto nla_put_failure;
+ }
+ }
+ rcu_read_unlock();
+
+ return 0;
+
+nla_put_failure:
+ nlmsg_trim(skb, b);
+ return -1;
+}
+
static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
struct netlink_callback *cb)
{
index--;
goto nla_put_failure;
}
- err = tcf_action_dump_1(skb, p, 0, 0);
+ err = (act_flags & TCA_ACT_FLAG_TERSE_DUMP) ?
+ tcf_action_dump_terse(skb, p, true) :
+ tcf_action_dump_1(skb, p, 0, 0);
if (err < 0) {
index--;
nlmsg_trim(skb, nest);
}
nla_nest_end(skb, nest);
n_i++;
- if (!(act_flags & TCA_FLAG_LARGE_DUMP_ON) &&
+ if (!(act_flags & TCA_ACT_FLAG_LARGE_DUMP_ON) &&
n_i >= TCA_ACT_MAX_PRIO)
goto done;
}
mutex_unlock(&idrinfo->lock);
if (n_i) {
- if (act_flags & TCA_FLAG_LARGE_DUMP_ON)
+ if (act_flags & TCA_ACT_FLAG_LARGE_DUMP_ON)
cb->args[1] = n_i;
}
return n_i;
return res;
}
-/*TCA_ACT_MAX_PRIO is 32, there count upto 32 */
+/*TCA_ACT_MAX_PRIO is 32, there count up to 32 */
#define TCA_ACT_MAX_PRIO_MASK 0x1FF
int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
int nr_actions, struct tcf_result *res)
return a->ops->dump(skb, a, bind, ref);
}
-static int
-tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a)
-{
- unsigned char *b = skb_tail_pointer(skb);
- struct tc_cookie *cookie;
-
- if (nla_put_string(skb, TCA_KIND, a->ops->kind))
- goto nla_put_failure;
- if (tcf_action_copy_stats(skb, a, 0))
- goto nla_put_failure;
-
- rcu_read_lock();
- cookie = rcu_dereference(a->act_cookie);
- if (cookie) {
- if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) {
- rcu_read_unlock();
- goto nla_put_failure;
- }
- }
- rcu_read_unlock();
-
- return 0;
-
-nla_put_failure:
- nlmsg_trim(skb, b);
- return -1;
-}
-
int
tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
- if (tcf_action_dump_terse(skb, a))
+ if (tcf_action_dump_terse(skb, a, false))
goto nla_put_failure;
if (a->hw_stats != TCA_ACT_HW_STATS_ANY &&
nest = nla_nest_start_noflag(skb, i + 1);
if (nest == NULL)
goto nla_put_failure;
- err = terse ? tcf_action_dump_terse(skb, a) :
+ err = terse ? tcf_action_dump_terse(skb, a, false) :
tcf_action_dump_1(skb, a, bind, ref);
if (err < 0)
goto errout;
NL_SET_ERR_MSG(extack, "TC action kind must be specified");
goto err_out;
}
- if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) {
+ if (nla_strscpy(act_name, kind, IFNAMSIZ) < 0) {
NL_SET_ERR_MSG(extack, "TC action name too long");
goto err_out;
}
}
static const struct nla_policy tcaa_policy[TCA_ROOT_MAX + 1] = {
- [TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_FLAG_LARGE_DUMP_ON),
+ [TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_ACT_FLAG_LARGE_DUMP_ON |
+ TCA_ACT_FLAG_TERSE_DUMP),
[TCA_ROOT_TIME_DELTA] = { .type = NLA_U32 },
};
* In case a different well-known TC_ACT opcode has been
* returned, it will overwrite the default one.
*
- * For everything else that is unkown, TC_ACT_UNSPEC is
+ * For everything else that is unknown, TC_ACT_UNSPEC is
* returned.
*/
switch (filter_res) {
goto err_insert;
ct_ft->nf_ft.type = &flowtable_ct;
- ct_ft->nf_ft.flags |= NF_FLOWTABLE_HW_OFFLOAD;
+ ct_ft->nf_ft.flags |= NF_FLOWTABLE_HW_OFFLOAD |
+ NF_FLOWTABLE_COUNTER;
err = nf_flow_table_init(&ct_ft->nf_ft);
if (err)
goto err_init;
flow_offload_refresh(nf_ft, flow);
nf_conntrack_get(&ct->ct_general);
nf_ct_set(skb, ct, ctinfo);
- nf_ct_acct_update(ct, dir, skb->len);
+ if (nf_ft->flags & NF_FLOWTABLE_COUNTER)
+ nf_ct_acct_update(ct, dir, skb->len);
return true;
}
if (err)
goto err_register;
+ static_branch_inc(&tcf_frag_xmit_count);
+
return 0;
err_register:
static void __exit ct_cleanup_module(void)
{
+ static_branch_dec(&tcf_frag_xmit_count);
tcf_unregister_action(&act_ct_ops, &ct_net_ops);
tcf_ct_flow_tables_uninit();
destroy_workqueue(act_ct_wq);
if (unlikely(!tname))
goto err1;
if (tb[TCA_IPT_TABLE] == NULL ||
- nla_strlcpy(tname, tb[TCA_IPT_TABLE], IFNAMSIZ) >= IFNAMSIZ)
+ nla_strscpy(tname, tb[TCA_IPT_TABLE], IFNAMSIZ) >= IFNAMSIZ)
strcpy(tname, "mangle");
t = kmemdup(td, td->u.target_size, GFP_KERNEL);
return err;
}
+static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb)
+{
+ int err;
+
+ if (!want_ingress)
+ err = tcf_dev_queue_xmit(skb, dev_queue_xmit);
+ else
+ err = netif_receive_skb(skb);
+
+ return err;
+}
+
static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
/* let's the caller reinsert the packet, if possible */
if (use_reinsert) {
res->ingress = want_ingress;
- if (skb_tc_reinsert(skb, res))
+ err = tcf_mirred_forward(res->ingress, skb);
+ if (err)
tcf_action_inc_overlimit_qstats(&m->common);
__this_cpu_dec(mirred_rec_level);
return TC_ACT_CONSUMED;
}
}
- if (!want_ingress)
- err = dev_queue_xmit(skb2);
- else
- err = netif_receive_skb(skb2);
-
+ err = tcf_mirred_forward(want_ingress, skb2);
if (err) {
out:
tcf_action_inc_overlimit_qstats(&m->common);
d->tcfd_defdata = kzalloc(SIMP_MAX_DATA, GFP_KERNEL);
if (unlikely(!d->tcfd_defdata))
return -ENOMEM;
- nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+ nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
return 0;
}
spin_lock_bh(&d->tcf_lock);
goto_ch = tcf_action_set_ctrlact(a, p->action, goto_ch);
memset(d->tcfd_defdata, 0, SIMP_MAX_DATA);
- nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+ nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
spin_unlock_bh(&d->tcf_lock);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
static bool tcf_proto_check_kind(struct nlattr *kind, char *name)
{
if (kind)
- return nla_strlcpy(name, kind, IFNAMSIZ) >= IFNAMSIZ;
+ return nla_strscpy(name, kind, IFNAMSIZ) < 0;
memset(name, 0, IFNAMSIZ);
return false;
}
*/
struct tcf_proto *
-tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp,
- bool rtnl_held)
+tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp)
{
struct tcf_proto *tp_next = __tcf_get_next_proto(chain, tp);
if (tp)
- tcf_proto_put(tp, rtnl_held, NULL);
+ tcf_proto_put(tp, true, NULL);
return tp_next;
}
static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
struct tcf_block *block, struct Qdisc *q,
u32 parent, struct nlmsghdr *n,
- struct tcf_chain *chain, int event,
- bool rtnl_held)
+ struct tcf_chain *chain, int event)
{
struct tcf_proto *tp;
- for (tp = tcf_get_next_proto(chain, NULL, rtnl_held);
- tp; tp = tcf_get_next_proto(chain, tp, rtnl_held))
+ for (tp = tcf_get_next_proto(chain, NULL);
+ tp; tp = tcf_get_next_proto(chain, tp))
tfilter_notify(net, oskb, n, tp, block,
- q, parent, NULL, event, false, rtnl_held);
+ q, parent, NULL, event, false, true);
}
static void tfilter_put(struct tcf_proto *tp, void *fh)
if (prio == 0) {
tfilter_notify_chain(net, skb, block, q, parent, n,
- chain, RTM_DELTFILTER, rtnl_held);
+ chain, RTM_DELTFILTER);
tcf_chain_flush(chain, rtnl_held);
err = 0;
goto errout;
break;
case RTM_DELCHAIN:
tfilter_notify_chain(net, skb, block, q, parent, n,
- chain, RTM_DELTFILTER, true);
+ chain, RTM_DELTFILTER);
/* Flush the chain first as the user requested chain removal. */
tcf_chain_flush(chain, true);
/* In case the chain was successfully deleted, put a reference
struct tcf_chain *chain;
long index_start;
long index;
- u32 parent;
int err;
if (nlmsg_len(cb->nlh) < sizeof(*tcm))
block = tcf_block_refcnt_get(net, tcm->tcm_block_index);
if (!block)
goto out;
- /* If we work with block index, q is NULL and parent value
- * will never be used in the following code. The check
- * in tcf_fill_node prevents it. However, compiler does not
- * see that far, so set parent to zero to silence the warning
- * about parent being uninitialized.
- */
- parent = 0;
} else {
const struct Qdisc_class_ops *cops;
struct net_device *dev;
if (!dev)
return skb->len;
- parent = tcm->tcm_parent;
- if (!parent) {
+ if (!tcm->tcm_parent)
q = dev->qdisc;
- parent = q->handle;
- } else {
+ else
q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
- }
+
if (!q)
goto out;
cops = q->ops->cl_ops;
}
}
- /* Something went wrong if we are trying to replace a non-existant
+ /* Something went wrong if we are trying to replace a non-existent
* node. Mind as well halt instead of silently failing.
*/
BUG_ON(1);
break;
case TCF_EM_ALIGN_U32:
- /* Worth checking boundries? The branching seems
+ /* Worth checking boundaries? The branching seems
* to get worse. Visit again.
*/
val = get_unaligned_be32(ptr);
#ifdef CONFIG_MODULES
if (ops == NULL && kind != NULL) {
char name[IFNAMSIZ];
- if (nla_strlcpy(name, kind, IFNAMSIZ) < IFNAMSIZ) {
+ if (nla_strscpy(name, kind, IFNAMSIZ) >= 0) {
/* We dropped the RTNL semaphore in order to
* perform the module load. So, even if we
* succeeded in loading the module we have to
chain = tcf_get_next_chain(block, chain)) {
struct tcf_proto *tp;
- for (tp = tcf_get_next_proto(chain, NULL, true);
- tp; tp = tcf_get_next_proto(chain, tp, true)) {
+ for (tp = tcf_get_next_proto(chain, NULL);
+ tp; tp = tcf_get_next_proto(chain, tp)) {
struct tcf_bind_args arg = {};
arg.w.fn = tcf_node_bind;
* non-ATM interfaces.
*/
-static void sch_atm_dequeue(unsigned long data)
+static void sch_atm_dequeue(struct tasklet_struct *t)
{
- struct Qdisc *sch = (struct Qdisc *)data;
- struct atm_qdisc_data *p = qdisc_priv(sch);
+ struct atm_qdisc_data *p = from_tasklet(p, t, task);
+ struct Qdisc *sch = qdisc_from_priv(p);
struct atm_flow_data *flow;
struct sk_buff *skb;
if (err)
return err;
- tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch);
+ tasklet_setup(&p->task, sch_atm_dequeue);
return 0;
}
* locredit = max_frame_size * (sendslope / port_transmit_rate)
*/
+#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+#include <net/netlink.h>
+#include <net/sch_generic.h>
+#include <net/dst.h>
+#include <net/ip.h>
+#include <net/ip6_fib.h>
+
+struct sch_frag_data {
+ unsigned long dst;
+ struct qdisc_skb_cb cb;
+ __be16 inner_protocol;
+ u16 vlan_tci;
+ __be16 vlan_proto;
+ unsigned int l2_len;
+ u8 l2_data[VLAN_ETH_HLEN];
+ int (*xmit)(struct sk_buff *skb);
+};
+
+static DEFINE_PER_CPU(struct sch_frag_data, sch_frag_data_storage);
+
+static int sch_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ struct sch_frag_data *data = this_cpu_ptr(&sch_frag_data_storage);
+
+ if (skb_cow_head(skb, data->l2_len) < 0) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+
+ __skb_dst_copy(skb, data->dst);
+ *qdisc_skb_cb(skb) = data->cb;
+ skb->inner_protocol = data->inner_protocol;
+ if (data->vlan_tci & VLAN_CFI_MASK)
+ __vlan_hwaccel_put_tag(skb, data->vlan_proto,
+ data->vlan_tci & ~VLAN_CFI_MASK);
+ else
+ __vlan_hwaccel_clear_tag(skb);
+
+ /* Reconstruct the MAC header. */
+ skb_push(skb, data->l2_len);
+ memcpy(skb->data, &data->l2_data, data->l2_len);
+ skb_postpush_rcsum(skb, skb->data, data->l2_len);
+ skb_reset_mac_header(skb);
+
+ return data->xmit(skb);
+}
+
+static void sch_frag_prepare_frag(struct sk_buff *skb,
+ int (*xmit)(struct sk_buff *skb))
+{
+ unsigned int hlen = skb_network_offset(skb);
+ struct sch_frag_data *data;
+
+ data = this_cpu_ptr(&sch_frag_data_storage);
+ data->dst = skb->_skb_refdst;
+ data->cb = *qdisc_skb_cb(skb);
+ data->xmit = xmit;
+ data->inner_protocol = skb->inner_protocol;
+ if (skb_vlan_tag_present(skb))
+ data->vlan_tci = skb_vlan_tag_get(skb) | VLAN_CFI_MASK;
+ else
+ data->vlan_tci = 0;
+ data->vlan_proto = skb->vlan_proto;
+ data->l2_len = hlen;
+ memcpy(&data->l2_data, skb->data, hlen);
+
+ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+ skb_pull(skb, hlen);
+}
+
+static unsigned int
+sch_frag_dst_get_mtu(const struct dst_entry *dst)
+{
+ return dst->dev->mtu;
+}
+
+static struct dst_ops sch_frag_dst_ops = {
+ .family = AF_UNSPEC,
+ .mtu = sch_frag_dst_get_mtu,
+};
+
+static int sch_fragment(struct net *net, struct sk_buff *skb,
+ u16 mru, int (*xmit)(struct sk_buff *skb))
+{
+ int ret = -1;
+
+ if (skb_network_offset(skb) > VLAN_ETH_HLEN) {
+ net_warn_ratelimited("L2 header too long to fragment\n");
+ goto err;
+ }
+
+ if (skb_protocol(skb, true) == htons(ETH_P_IP)) {
+ struct dst_entry sch_frag_dst;
+ unsigned long orig_dst;
+
+ sch_frag_prepare_frag(skb, xmit);
+ dst_init(&sch_frag_dst, &sch_frag_dst_ops, NULL, 1,
+ DST_OBSOLETE_NONE, DST_NOCOUNT);
+ sch_frag_dst.dev = skb->dev;
+
+ orig_dst = skb->_skb_refdst;
+ skb_dst_set_noref(skb, &sch_frag_dst);
+ IPCB(skb)->frag_max_size = mru;
+
+ ret = ip_do_fragment(net, skb->sk, skb, sch_frag_xmit);
+ refdst_drop(orig_dst);
+ } else if (skb_protocol(skb, true) == htons(ETH_P_IPV6)) {
+ unsigned long orig_dst;
+ struct rt6_info sch_frag_rt;
+
+ sch_frag_prepare_frag(skb, xmit);
+ memset(&sch_frag_rt, 0, sizeof(sch_frag_rt));
+ dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL, 1,
+ DST_OBSOLETE_NONE, DST_NOCOUNT);
+ sch_frag_rt.dst.dev = skb->dev;
+
+ orig_dst = skb->_skb_refdst;
+ skb_dst_set_noref(skb, &sch_frag_rt.dst);
+ IP6CB(skb)->frag_max_size = mru;
+
+ ret = ipv6_stub->ipv6_fragment(net, skb->sk, skb,
+ sch_frag_xmit);
+ refdst_drop(orig_dst);
+ } else {
+ net_warn_ratelimited("Fail frag %s: eth=%x, MRU=%d, MTU=%d\n",
+ netdev_name(skb->dev),
+ ntohs(skb_protocol(skb, true)), mru,
+ skb->dev->mtu);
+ goto err;
+ }
+
+ return ret;
+err:
+ kfree_skb(skb);
+ return ret;
+}
+
+int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
+{
+ u16 mru = qdisc_skb_cb(skb)->mru;
+ int err;
+
+ if (mru && skb->len > mru + skb->dev->hard_header_len)
+ err = sch_fragment(dev_net(skb->dev), skb, mru, xmit);
+ else
+ err = xmit(skb);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(sch_frag_xmit_hook);
/* We restart the measurement cycle if the following conditions are met
* 1. If the delay has been low for 2 consecutive Tupdate periods
* 2. Calculated drop probability is zero
- * 3. If average dq_rate_estimator is enabled, we have atleast one
+ * 3. If average dq_rate_estimator is enabled, we have at least one
* estimate for the avg_dq_rate ie., is a non-zero value
*/
if ((vars->qdelay < params->target / 2) &&
*
*/
+#include <linux/ethtool.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/kernel.h>
select CRYPTO_HMAC
select CRYPTO_SHA1
select LIBCRC32C
+ select NET_UDP_TUNNEL
help
Stream Control Transmission Protocol
*/
asoc->hbinterval = msecs_to_jiffies(sp->hbinterval);
+ asoc->encap_port = sp->encap_port;
+
/* Initialize path max retrans value. */
asoc->pathmaxrxt = sp->pathmaxrxt;
*/
peer->hbinterval = asoc->hbinterval;
+ peer->encap_port = asoc->encap_port;
+
/* Set the path max_retrans. */
peer->pathmaxrxt = asoc->pathmaxrxt;
#include <net/inet_common.h>
#include <net/inet_ecn.h>
#include <net/sctp/sctp.h>
+#include <net/udp_tunnel.h>
#include <linux/uaccess.h>
return ret;
}
-static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
+static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t)
{
+ struct dst_entry *dst = dst_clone(t->dst);
+ struct flowi6 *fl6 = &t->fl.u.ip6;
struct sock *sk = skb->sk;
struct ipv6_pinfo *np = inet6_sk(sk);
- struct flowi6 *fl6 = &transport->fl.u.ip6;
__u8 tclass = np->tclass;
- int res;
+ __be32 label;
pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb,
skb->len, &fl6->saddr, &fl6->daddr);
- if (transport->dscp & SCTP_DSCP_SET_MASK)
- tclass = transport->dscp & SCTP_DSCP_VAL_MASK;
+ if (t->dscp & SCTP_DSCP_SET_MASK)
+ tclass = t->dscp & SCTP_DSCP_VAL_MASK;
if (INET_ECN_is_capable(tclass))
IP6_ECN_flow_xmit(sk, fl6->flowlabel);
- if (!(transport->param_flags & SPP_PMTUD_ENABLE))
+ if (!(t->param_flags & SPP_PMTUD_ENABLE))
skb->ignore_df = 1;
SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
- rcu_read_lock();
- res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt),
- tclass, sk->sk_priority);
- rcu_read_unlock();
- return res;
+ if (!t->encap_port || !sctp_sk(sk)->udp_port) {
+ int res;
+
+ skb_dst_set(skb, dst);
+ rcu_read_lock();
+ res = ip6_xmit(sk, skb, fl6, sk->sk_mark,
+ rcu_dereference(np->opt),
+ tclass, sk->sk_priority);
+ rcu_read_unlock();
+ return res;
+ }
+
+ if (skb_is_gso(skb))
+ skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+
+ skb->encapsulation = 1;
+ skb_reset_inner_mac_header(skb);
+ skb_reset_inner_transport_header(skb);
+ skb_set_inner_ipproto(skb, IPPROTO_SCTP);
+ label = ip6_make_flowlabel(sock_net(sk), skb, fl6->flowlabel, true, fl6);
+
+ return udp_tunnel6_xmit_skb(dst, sk, skb, NULL, &fl6->saddr,
+ &fl6->daddr, tclass, ip6_dst_hoplimit(dst),
+ label, sctp_sk(sk)->udp_port, t->encap_port, false);
}
/* Returns the dst cache entry for the given source and destination ip
static int sctp6_rcv(struct sk_buff *skb)
{
+ SCTP_INPUT_CB(skb)->encap_port = 0;
return sctp_rcv(skb) ? -1 : 0;
}
{
skb->ip_summed = CHECKSUM_NONE;
skb->csum_not_inet = 0;
- gso_reset_checksum(skb, ~0);
+ /* csum and csum_start in GSO CB may be needed to do the UDP
+ * checksum when it's a UDP tunneling packet.
+ */
+ SKB_GSO_CB(skb)->csum = (__force __wsum)~0;
+ SKB_GSO_CB(skb)->csum_start = skb_headroom(skb) + skb->len;
return sctp_compute_cksum(skb, skb_transport_offset(skb));
}
sizeof(struct inet6_skb_parm)));
skb_shinfo(head)->gso_segs = pkt_count;
skb_shinfo(head)->gso_size = GSO_BY_FRAGS;
- rcu_read_lock();
- if (skb_dst(head) != tp->dst) {
- dst_hold(tp->dst);
- sk_setup_caps(sk, tp->dst);
- }
- rcu_read_unlock();
goto chksum;
}
if (sctp_checksum_disable)
return 1;
- if (!(skb_dst(head)->dev->features & NETIF_F_SCTP_CRC) ||
- dst_xfrm(skb_dst(head)) || packet->ipfragok) {
+ if (!(tp->dst->dev->features & NETIF_F_SCTP_CRC) ||
+ dst_xfrm(tp->dst) || packet->ipfragok || tp->encap_port) {
struct sctphdr *sh =
(struct sctphdr *)skb_transport_header(head);
struct sctp_association *asoc = tp->asoc;
struct sctp_chunk *chunk, *tmp;
int pkt_count, gso = 0;
- struct dst_entry *dst;
struct sk_buff *head;
struct sctphdr *sh;
struct sock *sk;
sh->checksum = 0;
/* drop packet if no dst */
- dst = dst_clone(tp->dst);
- if (!dst) {
+ if (!tp->dst) {
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(head);
goto out;
}
- skb_dst_set(head, dst);
+
+ rcu_read_lock();
+ if (__sk_dst_get(sk) != tp->dst) {
+ dst_hold(tp->dst);
+ sk_setup_caps(sk, tp->dst);
+ }
+ rcu_read_unlock();
/* pack up chunks */
pkt_count = sctp_packet_pack(packet, head, gso, gfp);
#include <net/addrconf.h>
#include <net/inet_common.h>
#include <net/inet_ecn.h>
+#include <net/udp_tunnel.h>
#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
return 0;
}
+static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb)
+{
+ SCTP_INPUT_CB(skb)->encap_port = udp_hdr(skb)->source;
+
+ skb_set_transport_header(skb, sizeof(struct udphdr));
+ sctp_rcv(skb);
+ return 0;
+}
+
+static int sctp_udp_err_lookup(struct sock *sk, struct sk_buff *skb)
+{
+ struct sctp_association *asoc;
+ struct sctp_transport *t;
+ int family;
+
+ skb->transport_header += sizeof(struct udphdr);
+ family = (ip_hdr(skb)->version == 4) ? AF_INET : AF_INET6;
+ sk = sctp_err_lookup(dev_net(skb->dev), family, skb, sctp_hdr(skb),
+ &asoc, &t);
+ if (!sk)
+ return -ENOENT;
+
+ sctp_err_finish(sk, t);
+ return 0;
+}
+
+int sctp_udp_sock_start(struct net *net)
+{
+ struct udp_tunnel_sock_cfg tuncfg = {NULL};
+ struct udp_port_cfg udp_conf = {0};
+ struct socket *sock;
+ int err;
+
+ udp_conf.family = AF_INET;
+ udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
+ udp_conf.local_udp_port = htons(net->sctp.udp_port);
+ err = udp_sock_create(net, &udp_conf, &sock);
+ if (err) {
+ pr_err("Failed to create the SCTP UDP tunneling v4 sock\n");
+ return err;
+ }
+
+ tuncfg.encap_type = 1;
+ tuncfg.encap_rcv = sctp_udp_rcv;
+ tuncfg.encap_err_lookup = sctp_udp_err_lookup;
+ setup_udp_tunnel_sock(net, sock, &tuncfg);
+ net->sctp.udp4_sock = sock->sk;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ memset(&udp_conf, 0, sizeof(udp_conf));
+
+ udp_conf.family = AF_INET6;
+ udp_conf.local_ip6 = in6addr_any;
+ udp_conf.local_udp_port = htons(net->sctp.udp_port);
+ udp_conf.use_udp6_rx_checksums = true;
+ udp_conf.ipv6_v6only = true;
+ err = udp_sock_create(net, &udp_conf, &sock);
+ if (err) {
+ pr_err("Failed to create the SCTP UDP tunneling v6 sock\n");
+ udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
+ net->sctp.udp4_sock = NULL;
+ return err;
+ }
+
+ tuncfg.encap_type = 1;
+ tuncfg.encap_rcv = sctp_udp_rcv;
+ tuncfg.encap_err_lookup = sctp_udp_err_lookup;
+ setup_udp_tunnel_sock(net, sock, &tuncfg);
+ net->sctp.udp6_sock = sock->sk;
+#endif
+
+ return 0;
+}
+
+void sctp_udp_sock_stop(struct net *net)
+{
+ if (net->sctp.udp4_sock) {
+ udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
+ net->sctp.udp4_sock = NULL;
+ }
+ if (net->sctp.udp6_sock) {
+ udp_tunnel_sock_release(net->sctp.udp6_sock->sk_socket);
+ net->sctp.udp6_sock = NULL;
+ }
+}
+
/* Register address family specific functions. */
int sctp_register_af(struct sctp_af *af)
{
}
/* Wrapper routine that calls the ip transmit routine. */
-static inline int sctp_v4_xmit(struct sk_buff *skb,
- struct sctp_transport *transport)
+static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t)
{
- struct inet_sock *inet = inet_sk(skb->sk);
+ struct dst_entry *dst = dst_clone(t->dst);
+ struct flowi4 *fl4 = &t->fl.u.ip4;
+ struct sock *sk = skb->sk;
+ struct inet_sock *inet = inet_sk(sk);
__u8 dscp = inet->tos;
+ __be16 df = 0;
pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb,
- skb->len, &transport->fl.u.ip4.saddr,
- &transport->fl.u.ip4.daddr);
+ skb->len, &fl4->saddr, &fl4->daddr);
- if (transport->dscp & SCTP_DSCP_SET_MASK)
- dscp = transport->dscp & SCTP_DSCP_VAL_MASK;
+ if (t->dscp & SCTP_DSCP_SET_MASK)
+ dscp = t->dscp & SCTP_DSCP_VAL_MASK;
+
+ inet->pmtudisc = t->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO
+ : IP_PMTUDISC_DONT;
+ SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
- inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ?
- IP_PMTUDISC_DO : IP_PMTUDISC_DONT;
+ if (!t->encap_port || !sctp_sk(sk)->udp_port) {
+ skb_dst_set(skb, dst);
+ return __ip_queue_xmit(sk, skb, &t->fl, dscp);
+ }
- SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS);
+ if (skb_is_gso(skb))
+ skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
- return __ip_queue_xmit(&inet->sk, skb, &transport->fl, dscp);
+ if (ip_dont_fragment(sk, dst) && !skb->ignore_df)
+ df = htons(IP_DF);
+
+ skb->encapsulation = 1;
+ skb_reset_inner_mac_header(skb);
+ skb_reset_inner_transport_header(skb);
+ skb_set_inner_ipproto(skb, IPPROTO_SCTP);
+ udp_tunnel_xmit_skb((struct rtable *)dst, sk, skb, fl4->saddr,
+ fl4->daddr, dscp, ip4_dst_hoplimit(dst), df,
+ sctp_sk(sk)->udp_port, t->encap_port, false, false);
+ return 0;
}
static struct sctp_af sctp_af_inet;
.flags = SCTP_PROTOSW_FLAG
};
+static int sctp4_rcv(struct sk_buff *skb)
+{
+ SCTP_INPUT_CB(skb)->encap_port = 0;
+ return sctp_rcv(skb);
+}
+
/* Register with IP layer. */
static const struct net_protocol sctp_protocol = {
- .handler = sctp_rcv,
+ .handler = sctp4_rcv,
.err_handler = sctp_v4_err,
.no_policy = 1,
.netns_ok = 1,
/* Enable ECN by default. */
net->sctp.ecn_enable = 1;
+ /* Set UDP tunneling listening port to 0 by default */
+ net->sctp.udp_port = 0;
+
+ /* Set remote encap port to 0 by default */
+ net->sctp.encap_port = 0;
+
/* Set SCOPE policy to enabled */
net->sctp.scope_policy = SCTP_SCOPE_POLICY_ENABLE;
return retval;
}
+struct sctp_chunk *sctp_make_new_encap_port(const struct sctp_association *asoc,
+ const struct sctp_chunk *chunk)
+{
+ struct sctp_new_encap_port_hdr nep;
+ struct sctp_chunk *retval;
+
+ retval = sctp_make_abort(asoc, chunk,
+ sizeof(struct sctp_errhdr) + sizeof(nep));
+ if (!retval)
+ goto nodata;
+
+ sctp_init_cause(retval, SCTP_ERROR_NEW_ENCAP_PORT, sizeof(nep));
+ nep.cur_port = SCTP_INPUT_CB(chunk->skb)->encap_port;
+ nep.new_port = chunk->transport->encap_port;
+ sctp_addto_chunk(retval, sizeof(nep), &nep);
+
+nodata:
+ return retval;
+}
+
/* Make a HEARTBEAT chunk. */
struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc,
const struct sctp_transport *transport)
* added as the primary transport. The source address seems to
* be a better choice than any of the embedded addresses.
*/
+ asoc->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port;
if (!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE))
goto nomem;
const union sctp_subtype type,
void *arg,
struct sctp_cmd_seq *commands);
+static enum sctp_disposition sctp_sf_new_encap_port(
+ struct net *net,
+ const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type,
+ void *arg,
+ struct sctp_cmd_seq *commands);
static struct sctp_sackhdr *sctp_sm_pull_sack(struct sctp_chunk *chunk);
static enum sctp_disposition sctp_stop_t1_and_abort(
if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
commands);
+
+ if (SCTP_INPUT_CB(chunk->skb)->encap_port != chunk->transport->encap_port)
+ return sctp_sf_new_encap_port(net, ep, asoc, type, arg, commands);
+
/* Grab the INIT header. */
chunk->subh.init_hdr = (struct sctp_inithdr *)chunk->skb->data;
sctp_packet_append_chunk(packet, abort);
+ sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet));
+
+ SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS);
+
+ sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ return SCTP_DISPOSITION_CONSUME;
+}
+
+/* Handling of SCTP Packets Containing an INIT Chunk Matching an
+ * Existing Associations when the UDP encap port is incorrect.
+ *
+ * From Section 4 at draft-tuexen-tsvwg-sctp-udp-encaps-cons-03.
+ */
+static enum sctp_disposition sctp_sf_new_encap_port(
+ struct net *net,
+ const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type,
+ void *arg,
+ struct sctp_cmd_seq *commands)
+{
+ struct sctp_packet *packet = NULL;
+ struct sctp_chunk *chunk = arg;
+ struct sctp_chunk *abort;
+
+ packet = sctp_ootb_pkt_new(net, asoc, chunk);
+ if (!packet)
+ return SCTP_DISPOSITION_NOMEM;
+
+ abort = sctp_make_new_encap_port(asoc, chunk);
+ if (!abort) {
+ sctp_ootb_pkt_free(packet);
+ return SCTP_DISPOSITION_NOMEM;
+ }
+
+ abort->skb->sk = ep->base.sk;
+
+ sctp_packet_append_chunk(packet, abort);
+
sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT,
SCTP_PACKET(packet));
if (!transport)
goto nomem;
+ transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port;
+
/* Cache a route for the transport with the chunk's destination as
* the source address.
*/
return retval;
}
+static int sctp_setsockopt_encap_port(struct sock *sk,
+ struct sctp_udpencaps *encap,
+ unsigned int optlen)
+{
+ struct sctp_association *asoc;
+ struct sctp_transport *t;
+ __be16 encap_port;
+
+ if (optlen != sizeof(*encap))
+ return -EINVAL;
+
+ /* If an address other than INADDR_ANY is specified, and
+ * no transport is found, then the request is invalid.
+ */
+ encap_port = (__force __be16)encap->sue_port;
+ if (!sctp_is_any(sk, (union sctp_addr *)&encap->sue_address)) {
+ t = sctp_addr_id2transport(sk, &encap->sue_address,
+ encap->sue_assoc_id);
+ if (!t)
+ return -EINVAL;
+
+ t->encap_port = encap_port;
+ return 0;
+ }
+
+ /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the
+ * socket is a one to many style socket, and an association
+ * was not found, then the id was invalid.
+ */
+ asoc = sctp_id2assoc(sk, encap->sue_assoc_id);
+ if (!asoc && encap->sue_assoc_id != SCTP_FUTURE_ASSOC &&
+ sctp_style(sk, UDP))
+ return -EINVAL;
+
+ /* If changes are for association, also apply encap_port to
+ * each transport.
+ */
+ if (asoc) {
+ list_for_each_entry(t, &asoc->peer.transport_addr_list,
+ transports)
+ t->encap_port = encap_port;
+
+ return 0;
+ }
+
+ sctp_sk(sk)->encap_port = encap_port;
+ return 0;
+}
+
/* API 6.2 setsockopt(), getsockopt()
*
* Applications use setsockopt() and getsockopt() to set or retrieve
case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE:
retval = sctp_setsockopt_pf_expose(sk, kopt, optlen);
break;
+ case SCTP_REMOTE_UDP_ENCAPS_PORT:
+ retval = sctp_setsockopt_encap_port(sk, kopt, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
* be modified via SCTP_PEER_ADDR_PARAMS
*/
sp->hbinterval = net->sctp.hb_interval;
+ sp->udp_port = htons(net->sctp.udp_port);
+ sp->encap_port = htons(net->sctp.encap_port);
sp->pathmaxrxt = net->sctp.max_retrans_path;
sp->pf_retrans = net->sctp.pf_retrans;
sp->ps_retrans = net->sctp.ps_retrans;
return retval;
}
+static int sctp_getsockopt_encap_port(struct sock *sk, int len,
+ char __user *optval, int __user *optlen)
+{
+ struct sctp_association *asoc;
+ struct sctp_udpencaps encap;
+ struct sctp_transport *t;
+ __be16 encap_port;
+
+ if (len < sizeof(encap))
+ return -EINVAL;
+
+ len = sizeof(encap);
+ if (copy_from_user(&encap, optval, len))
+ return -EFAULT;
+
+ /* If an address other than INADDR_ANY is specified, and
+ * no transport is found, then the request is invalid.
+ */
+ if (!sctp_is_any(sk, (union sctp_addr *)&encap.sue_address)) {
+ t = sctp_addr_id2transport(sk, &encap.sue_address,
+ encap.sue_assoc_id);
+ if (!t) {
+ pr_debug("%s: failed no transport\n", __func__);
+ return -EINVAL;
+ }
+
+ encap_port = t->encap_port;
+ goto out;
+ }
+
+ /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the
+ * socket is a one to many style socket, and an association
+ * was not found, then the id was invalid.
+ */
+ asoc = sctp_id2assoc(sk, encap.sue_assoc_id);
+ if (!asoc && encap.sue_assoc_id != SCTP_FUTURE_ASSOC &&
+ sctp_style(sk, UDP)) {
+ pr_debug("%s: failed no association\n", __func__);
+ return -EINVAL;
+ }
+
+ if (asoc) {
+ encap_port = asoc->encap_port;
+ goto out;
+ }
+
+ encap_port = sctp_sk(sk)->encap_port;
+
+out:
+ encap.sue_port = (__force uint16_t)encap_port;
+ if (copy_to_user(optval, &encap, len))
+ return -EFAULT;
+
+ if (put_user(len, optlen))
+ return -EFAULT;
+
+ return 0;
+}
+
static int sctp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE:
retval = sctp_getsockopt_pf_expose(sk, len, optval, optlen);
break;
+ case SCTP_REMOTE_UDP_ENCAPS_PORT:
+ retval = sctp_getsockopt_encap_port(sk, len, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
static int rto_beta_max = 1000;
static int pf_expose_max = SCTP_PF_EXPOSE_MAX;
static int ps_retrans_max = SCTP_PS_RETRANS_MAX;
+static int udp_port_max = 65535;
static unsigned long max_autoclose_min = 0;
static unsigned long max_autoclose_max =
void *buffer, size_t *lenp, loff_t *ppos);
static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void *buffer,
size_t *lenp, loff_t *ppos);
+static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer,
+ size_t *lenp, loff_t *ppos);
static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
void *buffer, size_t *lenp, loff_t *ppos);
static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "udp_port",
+ .data = &init_net.sctp.udp_port,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_sctp_do_udp_port,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = &udp_port_max,
+ },
+ {
+ .procname = "encap_port",
+ .data = &init_net.sctp.encap_port,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = &udp_port_max,
+ },
{
.procname = "addr_scope_policy",
.data = &init_net.sctp.scope_policy,
return ret;
}
+static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct net *net = current->nsproxy->net_ns;
+ unsigned int min = *(unsigned int *)ctl->extra1;
+ unsigned int max = *(unsigned int *)ctl->extra2;
+ struct ctl_table tbl;
+ int ret, new_value;
+
+ memset(&tbl, 0, sizeof(struct ctl_table));
+ tbl.maxlen = sizeof(unsigned int);
+
+ if (write)
+ tbl.data = &new_value;
+ else
+ tbl.data = &net->sctp.udp_port;
+
+ ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+ if (write && ret == 0) {
+ struct sock *sk = net->sctp.ctl_sock;
+
+ if (new_value > max || new_value < min)
+ return -EINVAL;
+
+ net->sctp.udp_port = new_value;
+ sctp_udp_sock_stop(net);
+ if (new_value) {
+ ret = sctp_udp_sock_start(net);
+ if (ret)
+ net->sctp.udp_port = 0;
+ }
+
+ /* Update the value in the control socket */
+ lock_sock(sk);
+ sctp_sk(sk)->udp_port = htons(net->sctp.udp_port);
+ release_sock(sk);
+ }
+
+ return ret;
+}
+
int sctp_sysctl_net_register(struct net *net)
{
struct ctl_table *table;
*
* This file is part of the SCTP kernel implementation
*
- * This module provides the abstraction for an SCTP tranport representing
+ * This module provides the abstraction for an SCTP transport representing
* a remote transport address. For local transport addresses, we just use
* union sctp_addr.
*
/* Delete the T3_rtx timer if it's active.
* There is no point in not doing this now and letting
* structure hang around in memory since we know
- * the tranport is going away.
+ * the transport is going away.
*/
if (del_timer(&transport->T3_rtx_timer))
sctp_transport_put(transport);
obj-$(CONFIG_SMC) += smc.o
obj-$(CONFIG_SMC_DIAG) += smc_diag.o
smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o
-smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o
+smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o
#include "smc_ib.h"
#include "smc_ism.h"
#include "smc_pnet.h"
+#include "smc_netlink.h"
#include "smc_tx.h"
#include "smc_rx.h"
#include "smc_close.h"
return smc_connect_fallback(smc, reason_code);
}
-/* abort connecting */
-static void smc_connect_abort(struct smc_sock *smc, int local_first)
+static void smc_conn_abort(struct smc_sock *smc, int local_first)
{
if (local_first)
smc_lgr_cleanup_early(&smc->conn);
ini->smc_type_v1 = SMC_TYPE_N;
} /* else RDMA is supported for this connection */
}
- if (smc_ism_v2_capable && smc_find_ism_v2_device_clnt(smc, ini))
+ if (smc_ism_is_v2_capable() && smc_find_ism_v2_device_clnt(smc, ini))
ini->smc_type_v2 = SMC_TYPE_N;
/* if neither ISM nor RDMA are supported, fallback */
return 0;
connect_abort:
- smc_connect_abort(smc, ini->first_contact_local);
+ smc_conn_abort(smc, ini->first_contact_local);
mutex_unlock(&smc_client_lgr_pending);
smc->connect_nonblock = 0;
return 0;
connect_abort:
- smc_connect_abort(smc, ini->first_contact_local);
+ smc_conn_abort(smc, ini->first_contact_local);
mutex_unlock(&smc_server_lgr_pending);
smc->connect_nonblock = 0;
/* perform steps before actually connecting */
static int __smc_connect(struct smc_sock *smc)
{
- u8 version = smc_ism_v2_capable ? SMC_V2 : SMC_V1;
+ u8 version = smc_ism_is_v2_capable() ? SMC_V2 : SMC_V1;
struct smc_clc_msg_accept_confirm_v2 *aclc2;
struct smc_clc_msg_accept_confirm *aclc;
struct smc_init_info *ini = NULL;
version);
ini->smcd_version = SMC_V1;
- ini->smcd_version |= smc_ism_v2_capable ? SMC_V2 : 0;
+ ini->smcd_version |= smc_ism_is_v2_capable() ? SMC_V2 : 0;
ini->smc_type_v1 = SMC_TYPE_B;
- ini->smc_type_v2 = smc_ism_v2_capable ? SMC_TYPE_D : SMC_TYPE_N;
+ ini->smc_type_v2 = smc_ism_is_v2_capable() ? SMC_TYPE_D : SMC_TYPE_N;
/* get vlan id from IP device */
if (smc_vlan_by_tcpsk(smc->clcsock, ini)) {
int local_first, u8 version)
{
/* RDMA setup failed, switch back to TCP */
- if (local_first)
- smc_lgr_cleanup_early(&new_smc->conn);
- else
- smc_conn_free(&new_smc->conn);
+ smc_conn_abort(new_smc, local_first);
if (reason_code < 0) { /* error, no fallback possible */
smc_listen_out_err(new_smc);
return;
{
struct smc_clc_smcd_v2_extension *pclc_smcd_v2_ext;
struct smc_clc_v2_extension *pclc_v2_ext;
+ int rc = SMC_CLC_DECL_PEERNOSMC;
ini->smc_type_v1 = pclc->hdr.typev1;
ini->smc_type_v2 = pclc->hdr.typev2;
if (pclc->hdr.version > SMC_V1)
ini->smcd_version |=
ini->smc_type_v2 != SMC_TYPE_N ? SMC_V2 : 0;
- if (!smc_ism_v2_capable) {
+ if (!(ini->smcd_version & SMC_V2)) {
+ rc = SMC_CLC_DECL_PEERNOSMC;
+ goto out;
+ }
+ if (!smc_ism_is_v2_capable()) {
ini->smcd_version &= ~SMC_V2;
+ rc = SMC_CLC_DECL_NOISM2SUPP;
goto out;
}
pclc_v2_ext = smc_get_clc_v2_ext(pclc);
if (!pclc_v2_ext) {
ini->smcd_version &= ~SMC_V2;
+ rc = SMC_CLC_DECL_NOV2EXT;
goto out;
}
pclc_smcd_v2_ext = smc_get_clc_smcd_v2_ext(pclc_v2_ext);
- if (!pclc_smcd_v2_ext)
+ if (!pclc_smcd_v2_ext) {
ini->smcd_version &= ~SMC_V2;
+ rc = SMC_CLC_DECL_NOV2DEXT;
+ }
out:
- if (!ini->smcd_version) {
- if (pclc->hdr.typev1 == SMC_TYPE_B ||
- pclc->hdr.typev2 == SMC_TYPE_B)
- return SMC_CLC_DECL_NOSMCDEV;
- if (pclc->hdr.typev1 == SMC_TYPE_D ||
- pclc->hdr.typev2 == SMC_TYPE_D)
- return SMC_CLC_DECL_NOSMCDDEV;
- return SMC_CLC_DECL_NOSMCRDEV;
- }
+ if (!ini->smcd_version)
+ return rc;
return 0;
}
/* Create send and receive buffers */
rc = smc_buf_create(new_smc, true);
if (rc) {
- if (ini->first_contact_local)
- smc_lgr_cleanup_early(&new_smc->conn);
- else
- smc_conn_free(&new_smc->conn);
+ smc_conn_abort(new_smc, ini->first_contact_local);
return (rc == -ENOSPC) ? SMC_CLC_DECL_MAX_DMB :
SMC_CLC_DECL_MEM;
}
}
}
+static void smc_find_ism_store_rc(u32 rc, struct smc_init_info *ini)
+{
+ if (!ini->rc)
+ ini->rc = rc;
+}
+
static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
struct smc_clc_msg_proposal *pclc,
struct smc_init_info *ini)
unsigned int matches = 0;
u8 smcd_version;
u8 *eid = NULL;
- int i;
+ int i, rc;
if (!(ini->smcd_version & SMC_V2) || !smcd_indicated(ini->smc_type_v2))
goto not_found;
smc_v2_ext = smc_get_clc_v2_ext(pclc);
smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext);
if (!smcd_v2_ext ||
- !smc_v2_ext->hdr.flag.seid) /* no system EID support for SMCD */
+ !smc_v2_ext->hdr.flag.seid) { /* no system EID support for SMCD */
+ smc_find_ism_store_rc(SMC_CLC_DECL_NOSEID, ini);
goto not_found;
+ }
mutex_lock(&smcd_dev_list.mutex);
if (pclc_smcd->ism.chid)
ini->smcd_version = SMC_V2;
ini->is_smcd = true;
ini->ism_selected = i;
- if (smc_listen_ism_init(new_smc, ini))
+ rc = smc_listen_ism_init(new_smc, ini);
+ if (rc) {
+ smc_find_ism_store_rc(rc, ini);
/* try next active ISM device */
continue;
+ }
return; /* matching and usable V2 ISM device found */
}
/* no V2 ISM device could be initialized */
struct smc_init_info *ini)
{
struct smc_clc_msg_smcd *pclc_smcd = smc_get_clc_msg_smcd(pclc);
+ int rc = 0;
/* check if ISM V1 is available */
if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1))
goto not_found;
ini->is_smcd = true; /* prepare ISM check */
ini->ism_peer_gid[0] = ntohll(pclc_smcd->ism.gid);
- if (smc_find_ism_device(new_smc, ini))
+ rc = smc_find_ism_device(new_smc, ini);
+ if (rc)
goto not_found;
ini->ism_selected = 0;
- if (!smc_listen_ism_init(new_smc, ini))
+ rc = smc_listen_ism_init(new_smc, ini);
+ if (!rc)
return; /* V1 ISM device found */
not_found:
+ smc_find_ism_store_rc(rc, ini);
ini->ism_dev[0] = NULL;
ini->is_smcd = false;
}
return 0;
if (!(ini->smcd_version & SMC_V1))
- return SMC_CLC_DECL_NOSMCDEV;
+ return ini->rc ?: SMC_CLC_DECL_NOSMCD2DEV;
/* check for matching IP prefix and subnet length */
rc = smc_listen_prfx_check(new_smc, pclc);
if (rc)
- return rc;
+ return ini->rc ?: rc;
/* get vlan id from IP device */
if (smc_vlan_by_tcpsk(new_smc->clcsock, ini))
- return SMC_CLC_DECL_GETVLANERR;
+ return ini->rc ?: SMC_CLC_DECL_GETVLANERR;
/* check for ISM device matching V1 proposed device */
smc_find_ism_v1_device_serv(new_smc, pclc, ini);
return 0;
if (pclc->hdr.typev1 == SMC_TYPE_D)
- return SMC_CLC_DECL_NOSMCDDEV; /* skip RDMA and decline */
+ /* skip RDMA and decline */
+ return ini->rc ?: SMC_CLC_DECL_NOSMCDDEV;
/* check if RDMA is available */
- return smc_find_rdma_v1_device_serv(new_smc, pclc, ini);
+ rc = smc_find_rdma_v1_device_serv(new_smc, pclc, ini);
+ smc_find_ism_store_rc(rc, ini);
+
+ return (!rc) ? 0 : ini->rc;
}
/* listen worker: finish RDMA setup */
{
struct smc_sock *new_smc = container_of(work, struct smc_sock,
smc_listen_work);
- u8 version = smc_ism_v2_capable ? SMC_V2 : SMC_V1;
+ u8 version = smc_ism_is_v2_capable() ? SMC_V2 : SMC_V1;
struct socket *newclcsock = new_smc->clcsock;
struct smc_clc_msg_accept_confirm *cclc;
struct smc_clc_msg_proposal_area *buf;
smc_ism_init();
smc_clc_init();
- rc = smc_pnet_init();
+ rc = smc_nl_init();
if (rc)
goto out_pernet_subsys;
+ rc = smc_pnet_init();
+ if (rc)
+ goto out_nl;
+
rc = -ENOMEM;
smc_hs_wq = alloc_workqueue("smc_hs_wq", 0, 0);
if (!smc_hs_wq)
destroy_workqueue(smc_hs_wq);
out_pnet:
smc_pnet_exit();
+out_nl:
+ smc_nl_exit();
out_pernet_subsys:
unregister_pernet_subsys(&smc_net_ops);
proto_unregister(&smc_proto6);
proto_unregister(&smc_proto);
smc_pnet_exit();
+ smc_nl_exit();
unregister_pernet_subsys(&smc_net_ops);
rcu_barrier();
}
* Context:
* - tasklet context
*/
-static void smcd_cdc_rx_tsklet(unsigned long data)
+static void smcd_cdc_rx_tsklet(struct tasklet_struct *t)
{
- struct smc_connection *conn = (struct smc_connection *)data;
+ struct smc_connection *conn = from_tasklet(conn, t, rx_tsklet);
struct smcd_cdc_msg *data_cdc;
struct smcd_cdc_msg cdc;
struct smc_sock *smc;
*/
void smcd_cdc_rx_init(struct smc_connection *conn)
{
- tasklet_init(&conn->rx_tsklet, smcd_cdc_rx_tsklet, (unsigned long)conn);
+ tasklet_setup(&conn->rx_tsklet, smcd_cdc_rx_tsklet);
}
/***************************** init, exit, misc ******************************/
return len > 0 ? 0 : len;
}
+void smc_clc_get_hostname(u8 **host)
+{
+ *host = &smc_hostname[0];
+}
+
void __init smc_clc_init(void)
{
struct new_utsname *u;
#define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found (R or D) */
#define SMC_CLC_DECL_NOSMCDDEV 0x03030001 /* no SMC-D device found */
#define SMC_CLC_DECL_NOSMCRDEV 0x03030002 /* no SMC-R device found */
+#define SMC_CLC_DECL_NOISM2SUPP 0x03030003 /* hardware has no ISMv2 support */
+#define SMC_CLC_DECL_NOV2EXT 0x03030004 /* peer sent no clc v2 extension */
+#define SMC_CLC_DECL_NOV2DEXT 0x03030005 /* peer sent no clc SMC-Dv2 ext. */
+#define SMC_CLC_DECL_NOSEID 0x03030006 /* peer sent no SEID */
+#define SMC_CLC_DECL_NOSMCD2DEV 0x03030007 /* no SMC-Dv2 device found */
#define SMC_CLC_DECL_MODEUNSUPP 0x03040000 /* smc modes do not match (R or D)*/
#define SMC_CLC_DECL_RMBE_EC 0x03050000 /* peer has eyecatcher in RMBE */
#define SMC_CLC_DECL_OPTUNSUPP 0x03060000 /* fastopen sockopt not supported */
int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact,
u8 version);
void smc_clc_init(void) __init;
+void smc_clc_get_hostname(u8 **host);
#endif
#include <linux/wait.h>
#include <linux/reboot.h>
#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/smc.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <rdma/ib_verbs.h>
#include "smc_cdc.h"
#include "smc_close.h"
#include "smc_ism.h"
+#include "smc_netlink.h"
#define SMC_LGR_NUM_INCR 256
#define SMC_LGR_FREE_DELAY_SERV (600 * HZ)
#define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10 * HZ)
-static struct smc_lgr_list smc_lgr_list = { /* established link groups */
+struct smc_lgr_list smc_lgr_list = { /* established link groups */
.lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock),
.list = LIST_HEAD_INIT(smc_lgr_list.list),
.num = 0,
return &smc_lgr_list.list;
}
+static void smc_ibdev_cnt_inc(struct smc_link *lnk)
+{
+ atomic_inc(&lnk->smcibdev->lnk_cnt_by_port[lnk->ibport - 1]);
+}
+
+static void smc_ibdev_cnt_dec(struct smc_link *lnk)
+{
+ atomic_dec(&lnk->smcibdev->lnk_cnt_by_port[lnk->ibport - 1]);
+}
+
static void smc_lgr_schedule_free_work(struct smc_link_group *lgr)
{
/* client link group creation always follows the server link group
}
if (!conn->lnk)
return SMC_CLC_DECL_NOACTLINK;
+ atomic_inc(&conn->lnk->conn_cnt);
return 0;
}
struct smc_link_group *lgr = conn->lgr;
rb_erase(&conn->alert_node, &lgr->conns_all);
+ if (conn->lnk)
+ atomic_dec(&conn->lnk->conn_cnt);
lgr->conns_num--;
conn->alert_token_local = 0;
sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */
conn->lgr = NULL;
}
+int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+ char hostname[SMC_MAX_HOSTNAME_LEN + 1];
+ char smc_seid[SMC_MAX_EID_LEN + 1];
+ struct smcd_dev *smcd_dev;
+ struct nlattr *attrs;
+ u8 *seid = NULL;
+ u8 *host = NULL;
+ void *nlh;
+
+ nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+ &smc_gen_nl_family, NLM_F_MULTI,
+ SMC_NETLINK_GET_SYS_INFO);
+ if (!nlh)
+ goto errmsg;
+ if (cb_ctx->pos[0])
+ goto errout;
+ attrs = nla_nest_start(skb, SMC_GEN_SYS_INFO);
+ if (!attrs)
+ goto errout;
+ if (nla_put_u8(skb, SMC_NLA_SYS_VER, SMC_V2))
+ goto errattr;
+ if (nla_put_u8(skb, SMC_NLA_SYS_REL, SMC_RELEASE))
+ goto errattr;
+ if (nla_put_u8(skb, SMC_NLA_SYS_IS_ISM_V2, smc_ism_is_v2_capable()))
+ goto errattr;
+ smc_clc_get_hostname(&host);
+ if (host) {
+ snprintf(hostname, sizeof(hostname), "%s", host);
+ if (nla_put_string(skb, SMC_NLA_SYS_LOCAL_HOST, hostname))
+ goto errattr;
+ }
+ mutex_lock(&smcd_dev_list.mutex);
+ smcd_dev = list_first_entry_or_null(&smcd_dev_list.list,
+ struct smcd_dev, list);
+ if (smcd_dev)
+ smc_ism_get_system_eid(smcd_dev, &seid);
+ mutex_unlock(&smcd_dev_list.mutex);
+ if (seid && smc_ism_is_v2_capable()) {
+ snprintf(smc_seid, sizeof(smc_seid), "%s", seid);
+ if (nla_put_string(skb, SMC_NLA_SYS_SEID, smc_seid))
+ goto errattr;
+ }
+ nla_nest_end(skb, attrs);
+ genlmsg_end(skb, nlh);
+ cb_ctx->pos[0] = 1;
+ return skb->len;
+
+errattr:
+ nla_nest_cancel(skb, attrs);
+errout:
+ genlmsg_cancel(skb, nlh);
+errmsg:
+ return skb->len;
+}
+
+static int smc_nl_fill_lgr(struct smc_link_group *lgr,
+ struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ char smc_target[SMC_MAX_PNETID_LEN + 1];
+ struct nlattr *attrs;
+
+ attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCR);
+ if (!attrs)
+ goto errout;
+
+ if (nla_put_u32(skb, SMC_NLA_LGR_R_ID, *((u32 *)&lgr->id)))
+ goto errattr;
+ if (nla_put_u32(skb, SMC_NLA_LGR_R_CONNS_NUM, lgr->conns_num))
+ goto errattr;
+ if (nla_put_u8(skb, SMC_NLA_LGR_R_ROLE, lgr->role))
+ goto errattr;
+ if (nla_put_u8(skb, SMC_NLA_LGR_R_TYPE, lgr->type))
+ goto errattr;
+ if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id))
+ goto errattr;
+ snprintf(smc_target, sizeof(smc_target), "%s", lgr->pnet_id);
+ if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target))
+ goto errattr;
+
+ nla_nest_end(skb, attrs);
+ return 0;
+errattr:
+ nla_nest_cancel(skb, attrs);
+errout:
+ return -EMSGSIZE;
+}
+
+static int smc_nl_fill_lgr_link(struct smc_link_group *lgr,
+ struct smc_link *link,
+ struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ char smc_ibname[IB_DEVICE_NAME_MAX + 1];
+ u8 smc_gid_target[41];
+ struct nlattr *attrs;
+ u32 link_uid = 0;
+ void *nlh;
+
+ nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+ &smc_gen_nl_family, NLM_F_MULTI,
+ SMC_NETLINK_GET_LINK_SMCR);
+ if (!nlh)
+ goto errmsg;
+
+ attrs = nla_nest_start(skb, SMC_GEN_LINK_SMCR);
+ if (!attrs)
+ goto errout;
+
+ if (nla_put_u8(skb, SMC_NLA_LINK_ID, link->link_id))
+ goto errattr;
+ if (nla_put_u32(skb, SMC_NLA_LINK_STATE, link->state))
+ goto errattr;
+ if (nla_put_u32(skb, SMC_NLA_LINK_CONN_CNT,
+ atomic_read(&link->conn_cnt)))
+ goto errattr;
+ if (nla_put_u8(skb, SMC_NLA_LINK_IB_PORT, link->ibport))
+ goto errattr;
+ if (nla_put_u32(skb, SMC_NLA_LINK_NET_DEV, link->ndev_ifidx))
+ goto errattr;
+ snprintf(smc_ibname, sizeof(smc_ibname), "%s", link->ibname);
+ if (nla_put_string(skb, SMC_NLA_LINK_IB_DEV, smc_ibname))
+ goto errattr;
+ memcpy(&link_uid, link->link_uid, sizeof(link_uid));
+ if (nla_put_u32(skb, SMC_NLA_LINK_UID, link_uid))
+ goto errattr;
+ memcpy(&link_uid, link->peer_link_uid, sizeof(link_uid));
+ if (nla_put_u32(skb, SMC_NLA_LINK_PEER_UID, link_uid))
+ goto errattr;
+ memset(smc_gid_target, 0, sizeof(smc_gid_target));
+ smc_gid_be16_convert(smc_gid_target, link->gid);
+ if (nla_put_string(skb, SMC_NLA_LINK_GID, smc_gid_target))
+ goto errattr;
+ memset(smc_gid_target, 0, sizeof(smc_gid_target));
+ smc_gid_be16_convert(smc_gid_target, link->peer_gid);
+ if (nla_put_string(skb, SMC_NLA_LINK_PEER_GID, smc_gid_target))
+ goto errattr;
+
+ nla_nest_end(skb, attrs);
+ genlmsg_end(skb, nlh);
+ return 0;
+errattr:
+ nla_nest_cancel(skb, attrs);
+errout:
+ genlmsg_cancel(skb, nlh);
+errmsg:
+ return -EMSGSIZE;
+}
+
+static int smc_nl_handle_lgr(struct smc_link_group *lgr,
+ struct sk_buff *skb,
+ struct netlink_callback *cb,
+ bool list_links)
+{
+ void *nlh;
+ int i;
+
+ nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+ &smc_gen_nl_family, NLM_F_MULTI,
+ SMC_NETLINK_GET_LGR_SMCR);
+ if (!nlh)
+ goto errmsg;
+ if (smc_nl_fill_lgr(lgr, skb, cb))
+ goto errout;
+
+ genlmsg_end(skb, nlh);
+ if (!list_links)
+ goto out;
+ for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+ if (!smc_link_usable(&lgr->lnk[i]))
+ continue;
+ if (smc_nl_fill_lgr_link(lgr, &lgr->lnk[i], skb, cb))
+ goto errout;
+ }
+out:
+ return 0;
+
+errout:
+ genlmsg_cancel(skb, nlh);
+errmsg:
+ return -EMSGSIZE;
+}
+
+static void smc_nl_fill_lgr_list(struct smc_lgr_list *smc_lgr,
+ struct sk_buff *skb,
+ struct netlink_callback *cb,
+ bool list_links)
+{
+ struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+ struct smc_link_group *lgr;
+ int snum = cb_ctx->pos[0];
+ int num = 0;
+
+ spin_lock_bh(&smc_lgr->lock);
+ list_for_each_entry(lgr, &smc_lgr->list, list) {
+ if (num < snum)
+ goto next;
+ if (smc_nl_handle_lgr(lgr, skb, cb, list_links))
+ goto errout;
+next:
+ num++;
+ }
+errout:
+ spin_unlock_bh(&smc_lgr->lock);
+ cb_ctx->pos[0] = num;
+}
+
+static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
+ struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ char smc_host[SMC_MAX_HOSTNAME_LEN + 1];
+ char smc_pnet[SMC_MAX_PNETID_LEN + 1];
+ char smc_eid[SMC_MAX_EID_LEN + 1];
+ struct nlattr *v2_attrs;
+ struct nlattr *attrs;
+ void *nlh;
+
+ nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+ &smc_gen_nl_family, NLM_F_MULTI,
+ SMC_NETLINK_GET_LGR_SMCD);
+ if (!nlh)
+ goto errmsg;
+
+ attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCD);
+ if (!attrs)
+ goto errout;
+
+ if (nla_put_u32(skb, SMC_NLA_LGR_D_ID, *((u32 *)&lgr->id)))
+ goto errattr;
+ if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_GID, lgr->smcd->local_gid,
+ SMC_NLA_LGR_D_PAD))
+ goto errattr;
+ if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid,
+ SMC_NLA_LGR_D_PAD))
+ goto errattr;
+ if (nla_put_u8(skb, SMC_NLA_LGR_D_VLAN_ID, lgr->vlan_id))
+ goto errattr;
+ if (nla_put_u32(skb, SMC_NLA_LGR_D_CONNS_NUM, lgr->conns_num))
+ goto errattr;
+ if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd)))
+ goto errattr;
+ snprintf(smc_pnet, sizeof(smc_pnet), "%s", lgr->smcd->pnetid);
+ if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet))
+ goto errattr;
+
+ v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_V2);
+ if (!v2_attrs)
+ goto errattr;
+ if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version))
+ goto errv2attr;
+ if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release))
+ goto errv2attr;
+ if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os))
+ goto errv2attr;
+ snprintf(smc_host, sizeof(smc_host), "%s", lgr->peer_hostname);
+ if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host))
+ goto errv2attr;
+ snprintf(smc_eid, sizeof(smc_eid), "%s", lgr->negotiated_eid);
+ if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid))
+ goto errv2attr;
+
+ nla_nest_end(skb, v2_attrs);
+ nla_nest_end(skb, attrs);
+ genlmsg_end(skb, nlh);
+ return 0;
+
+errv2attr:
+ nla_nest_cancel(skb, v2_attrs);
+errattr:
+ nla_nest_cancel(skb, attrs);
+errout:
+ genlmsg_cancel(skb, nlh);
+errmsg:
+ return -EMSGSIZE;
+}
+
+static int smc_nl_handle_smcd_lgr(struct smcd_dev *dev,
+ struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+ struct smc_link_group *lgr;
+ int snum = cb_ctx->pos[1];
+ int rc = 0, num = 0;
+
+ spin_lock_bh(&dev->lgr_lock);
+ list_for_each_entry(lgr, &dev->lgr_list, list) {
+ if (!lgr->is_smcd)
+ continue;
+ if (num < snum)
+ goto next;
+ rc = smc_nl_fill_smcd_lgr(lgr, skb, cb);
+ if (rc)
+ goto errout;
+next:
+ num++;
+ }
+errout:
+ spin_unlock_bh(&dev->lgr_lock);
+ cb_ctx->pos[1] = num;
+ return rc;
+}
+
+static int smc_nl_fill_smcd_dev(struct smcd_dev_list *dev_list,
+ struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+ struct smcd_dev *smcd_dev;
+ int snum = cb_ctx->pos[0];
+ int rc = 0, num = 0;
+
+ mutex_lock(&dev_list->mutex);
+ list_for_each_entry(smcd_dev, &dev_list->list, list) {
+ if (list_empty(&smcd_dev->lgr_list))
+ continue;
+ if (num < snum)
+ goto next;
+ rc = smc_nl_handle_smcd_lgr(smcd_dev, skb, cb);
+ if (rc)
+ goto errout;
+next:
+ num++;
+ }
+errout:
+ mutex_unlock(&dev_list->mutex);
+ cb_ctx->pos[0] = num;
+ return rc;
+}
+
+int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ bool list_links = false;
+
+ smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links);
+ return skb->len;
+}
+
+int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ bool list_links = true;
+
+ smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links);
+ return skb->len;
+}
+
+int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ smc_nl_fill_smcd_dev(&smcd_dev_list, skb, cb);
+ return skb->len;
+}
+
void smc_lgr_cleanup_early(struct smc_connection *conn)
{
struct smc_link_group *lgr = conn->lgr;
return link_id;
}
+static void smcr_copy_dev_info_to_link(struct smc_link *link)
+{
+ struct smc_ib_device *smcibdev = link->smcibdev;
+
+ snprintf(link->ibname, sizeof(link->ibname), "%s",
+ smcibdev->ibdev->name);
+ link->ndev_ifidx = smcibdev->ndev_ifidx[link->ibport - 1];
+}
+
int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
u8 link_idx, struct smc_init_info *ini)
{
lnk->link_idx = link_idx;
lnk->smcibdev = ini->ib_dev;
lnk->ibport = ini->ib_port;
+ smc_ibdev_cnt_inc(lnk);
+ smcr_copy_dev_info_to_link(lnk);
lnk->path_mtu = ini->ib_dev->pattr[ini->ib_port - 1].active_mtu;
+ atomic_set(&lnk->conn_cnt, 0);
smc_llc_link_set_uid(lnk);
INIT_WORK(&lnk->link_down_wrk, smc_link_down_work);
if (!ini->ib_dev->initialized) {
clear_llc_lnk:
smc_llc_link_clear(lnk, false);
out:
+ smc_ibdev_cnt_dec(lnk);
put_device(&ini->ib_dev->ibdev->dev);
memset(lnk, 0, sizeof(struct smc_link));
lnk->state = SMC_LNK_UNUSED;
return rc;
}
+static void smc_switch_link_and_count(struct smc_connection *conn,
+ struct smc_link *to_lnk)
+{
+ atomic_dec(&conn->lnk->conn_cnt);
+ conn->lnk = to_lnk;
+ atomic_inc(&conn->lnk->conn_cnt);
+}
+
struct smc_link *smc_switch_conns(struct smc_link_group *lgr,
struct smc_link *from_lnk, bool is_dev_err)
{
smc->sk.sk_state == SMC_PEERABORTWAIT ||
smc->sk.sk_state == SMC_PROCESSABORT) {
spin_lock_bh(&conn->send_lock);
- conn->lnk = to_lnk;
+ smc_switch_link_and_count(conn, to_lnk);
spin_unlock_bh(&conn->send_lock);
continue;
}
}
/* avoid race with smcr_tx_sndbuf_nonempty() */
spin_lock_bh(&conn->send_lock);
- conn->lnk = to_lnk;
+ smc_switch_link_and_count(conn, to_lnk);
rc = smc_switch_cursor(smc, pend, wr_buf);
spin_unlock_bh(&conn->send_lock);
sock_put(&smc->sk);
smc_ib_destroy_queue_pair(lnk);
smc_ib_dealloc_protection_domain(lnk);
smc_wr_free_link_mem(lnk);
+ smc_ibdev_cnt_dec(lnk);
put_device(&lnk->smcibdev->ibdev->dev);
smcibdev = lnk->smcibdev;
memset(lnk, 0, sizeof(struct smc_link));
#define _SMC_CORE_H
#include <linux/atomic.h>
+#include <linux/smc.h>
+#include <linux/pci.h>
#include <rdma/ib_verbs.h>
+#include <net/genetlink.h>
#include "smc.h"
#include "smc_ib.h"
u8 link_is_asym; /* is link asymmetric? */
struct smc_link_group *lgr; /* parent link group */
struct work_struct link_down_wrk; /* wrk to bring link down */
+ char ibname[IB_DEVICE_NAME_MAX]; /* ib device name */
+ int ndev_ifidx; /* network device ifindex */
enum smc_link_state state; /* state of link */
struct delayed_work llc_testlink_wrk; /* testlink worker */
struct completion llc_testlink_resp; /* wait for rx of testlink */
int llc_testlink_time; /* testlink interval */
+ atomic_t conn_cnt; /* connections on this link */
};
/* For now we just allow one parallel link per link group. The SMC protocol
u8 first_contact_peer;
u8 first_contact_local;
unsigned short vlan_id;
+ u32 rc;
/* SMC-R */
struct smc_clc_msg_local *ib_lcl;
struct smc_ib_device *ib_dev;
return lnk->state == SMC_LNK_ACTIVE;
}
+static inline void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw)
+{
+ sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x",
+ be16_to_cpu(((__be16 *)gid_raw)[0]),
+ be16_to_cpu(((__be16 *)gid_raw)[1]),
+ be16_to_cpu(((__be16 *)gid_raw)[2]),
+ be16_to_cpu(((__be16 *)gid_raw)[3]),
+ be16_to_cpu(((__be16 *)gid_raw)[4]),
+ be16_to_cpu(((__be16 *)gid_raw)[5]),
+ be16_to_cpu(((__be16 *)gid_raw)[6]),
+ be16_to_cpu(((__be16 *)gid_raw)[7]));
+}
+
+struct smc_pci_dev {
+ __u32 pci_fid;
+ __u16 pci_pchid;
+ __u16 pci_vendor;
+ __u16 pci_device;
+ __u8 pci_id[SMC_PCI_ID_STR_LEN];
+};
+
+static inline void smc_set_pci_values(struct pci_dev *pci_dev,
+ struct smc_pci_dev *smc_dev)
+{
+ smc_dev->pci_vendor = pci_dev->vendor;
+ smc_dev->pci_device = pci_dev->device;
+ snprintf(smc_dev->pci_id, sizeof(smc_dev->pci_id), "%s",
+ pci_name(pci_dev));
+#if IS_ENABLED(CONFIG_S390)
+ { /* Set s390 specific PCI information */
+ struct zpci_dev *zdev;
+
+ zdev = to_zpci(pci_dev);
+ smc_dev->pci_fid = zdev->fid;
+ smc_dev->pci_pchid = zdev->pchid;
+ }
+#endif
+}
+
struct smc_sock;
struct smc_clc_msg_accept_confirm;
struct smc_clc_msg_local;
struct smc_link *from_lnk, bool is_dev_err);
void smcr_link_down_cond(struct smc_link *lnk);
void smcr_link_down_cond_sched(struct smc_link *lnk);
+int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb);
+int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb);
+int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb);
+int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb);
static inline struct smc_link_group *smc_get_lgr(struct smc_link *link)
{
return (struct smc_diag_dump_ctx *)cb->ctx;
}
-static void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw)
-{
- sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x",
- be16_to_cpu(((__be16 *)gid_raw)[0]),
- be16_to_cpu(((__be16 *)gid_raw)[1]),
- be16_to_cpu(((__be16 *)gid_raw)[2]),
- be16_to_cpu(((__be16 *)gid_raw)[3]),
- be16_to_cpu(((__be16 *)gid_raw)[4]),
- be16_to_cpu(((__be16 *)gid_raw)[5]),
- be16_to_cpu(((__be16 *)gid_raw)[6]),
- be16_to_cpu(((__be16 *)gid_raw)[7]));
-}
-
static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk)
{
struct smc_sock *smc = smc_sk(sk);
!list_empty(&smc->conn.lgr->list)) {
struct smc_diag_lgrinfo linfo = {
.role = smc->conn.lgr->role,
- .lnk[0].ibport = smc->conn.lgr->lnk[0].ibport,
- .lnk[0].link_id = smc->conn.lgr->lnk[0].link_id,
+ .lnk[0].ibport = smc->conn.lnk->ibport,
+ .lnk[0].link_id = smc->conn.lnk->link_id,
};
memcpy(linfo.lnk[0].ibname,
smc->conn.lgr->lnk[0].smcibdev->ibdev->name,
- sizeof(smc->conn.lgr->lnk[0].smcibdev->ibdev->name));
+ sizeof(smc->conn.lnk->smcibdev->ibdev->name));
smc_gid_be16_convert(linfo.lnk[0].gid,
- smc->conn.lgr->lnk[0].gid);
+ smc->conn.lnk->gid);
smc_gid_be16_convert(linfo.lnk[0].peer_gid,
- smc->conn.lgr->lnk[0].peer_gid);
+ smc->conn.lnk->peer_gid);
if (nla_put(skb, SMC_DIAG_LGRINFO, sizeof(linfo), &linfo) < 0)
goto errout;
#include "smc_core.h"
#include "smc_wr.h"
#include "smc.h"
+#include "smc_netlink.h"
#define SMC_MAX_CQE 32766 /* max. # of completion queue elements */
return rc;
}
+static bool smcr_diag_is_dev_critical(struct smc_lgr_list *smc_lgr,
+ struct smc_ib_device *smcibdev)
+{
+ struct smc_link_group *lgr;
+ bool rc = false;
+ int i;
+
+ spin_lock_bh(&smc_lgr->lock);
+ list_for_each_entry(lgr, &smc_lgr->list, list) {
+ if (lgr->is_smcd)
+ continue;
+ for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+ if (lgr->lnk[i].state == SMC_LNK_UNUSED ||
+ lgr->lnk[i].smcibdev != smcibdev)
+ continue;
+ if (lgr->type == SMC_LGR_SINGLE ||
+ lgr->type == SMC_LGR_ASYMMETRIC_LOCAL) {
+ rc = true;
+ goto out;
+ }
+ }
+ }
+out:
+ spin_unlock_bh(&smc_lgr->lock);
+ return rc;
+}
+
+static int smc_nl_handle_dev_port(struct sk_buff *skb,
+ struct ib_device *ibdev,
+ struct smc_ib_device *smcibdev,
+ int port)
+{
+ char smc_pnet[SMC_MAX_PNETID_LEN + 1];
+ struct nlattr *port_attrs;
+ unsigned char port_state;
+ int lnk_count = 0;
+
+ port_attrs = nla_nest_start(skb, SMC_NLA_DEV_PORT + port);
+ if (!port_attrs)
+ goto errout;
+
+ if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR,
+ smcibdev->pnetid_by_user[port]))
+ goto errattr;
+ snprintf(smc_pnet, sizeof(smc_pnet), "%s",
+ (char *)&smcibdev->pnetid[port]);
+ if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet))
+ goto errattr;
+ if (nla_put_u32(skb, SMC_NLA_DEV_PORT_NETDEV,
+ smcibdev->ndev_ifidx[port]))
+ goto errattr;
+ if (nla_put_u8(skb, SMC_NLA_DEV_PORT_VALID, 1))
+ goto errattr;
+ port_state = smc_ib_port_active(smcibdev, port + 1);
+ if (nla_put_u8(skb, SMC_NLA_DEV_PORT_STATE, port_state))
+ goto errattr;
+ lnk_count = atomic_read(&smcibdev->lnk_cnt_by_port[port]);
+ if (nla_put_u32(skb, SMC_NLA_DEV_PORT_LNK_CNT, lnk_count))
+ goto errattr;
+ nla_nest_end(skb, port_attrs);
+ return 0;
+errattr:
+ nla_nest_cancel(skb, port_attrs);
+errout:
+ return -EMSGSIZE;
+}
+
+static int smc_nl_handle_smcr_dev(struct smc_ib_device *smcibdev,
+ struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ char smc_ibname[IB_DEVICE_NAME_MAX + 1];
+ struct smc_pci_dev smc_pci_dev;
+ struct pci_dev *pci_dev;
+ unsigned char is_crit;
+ struct nlattr *attrs;
+ void *nlh;
+ int i;
+
+ nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+ &smc_gen_nl_family, NLM_F_MULTI,
+ SMC_NETLINK_GET_DEV_SMCR);
+ if (!nlh)
+ goto errmsg;
+ attrs = nla_nest_start(skb, SMC_GEN_DEV_SMCR);
+ if (!attrs)
+ goto errout;
+ is_crit = smcr_diag_is_dev_critical(&smc_lgr_list, smcibdev);
+ if (nla_put_u8(skb, SMC_NLA_DEV_IS_CRIT, is_crit))
+ goto errattr;
+ memset(&smc_pci_dev, 0, sizeof(smc_pci_dev));
+ pci_dev = to_pci_dev(smcibdev->ibdev->dev.parent);
+ smc_set_pci_values(pci_dev, &smc_pci_dev);
+ if (nla_put_u32(skb, SMC_NLA_DEV_PCI_FID, smc_pci_dev.pci_fid))
+ goto errattr;
+ if (nla_put_u16(skb, SMC_NLA_DEV_PCI_CHID, smc_pci_dev.pci_pchid))
+ goto errattr;
+ if (nla_put_u16(skb, SMC_NLA_DEV_PCI_VENDOR, smc_pci_dev.pci_vendor))
+ goto errattr;
+ if (nla_put_u16(skb, SMC_NLA_DEV_PCI_DEVICE, smc_pci_dev.pci_device))
+ goto errattr;
+ if (nla_put_string(skb, SMC_NLA_DEV_PCI_ID, smc_pci_dev.pci_id))
+ goto errattr;
+ snprintf(smc_ibname, sizeof(smc_ibname), "%s", smcibdev->ibdev->name);
+ if (nla_put_string(skb, SMC_NLA_DEV_IB_NAME, smc_ibname))
+ goto errattr;
+ for (i = 1; i <= SMC_MAX_PORTS; i++) {
+ if (!rdma_is_port_valid(smcibdev->ibdev, i))
+ continue;
+ if (smc_nl_handle_dev_port(skb, smcibdev->ibdev,
+ smcibdev, i - 1))
+ goto errattr;
+ }
+
+ nla_nest_end(skb, attrs);
+ genlmsg_end(skb, nlh);
+ return 0;
+
+errattr:
+ nla_nest_cancel(skb, attrs);
+errout:
+ genlmsg_cancel(skb, nlh);
+errmsg:
+ return -EMSGSIZE;
+}
+
+static void smc_nl_prep_smcr_dev(struct smc_ib_devices *dev_list,
+ struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+ struct smc_ib_device *smcibdev;
+ int snum = cb_ctx->pos[0];
+ int num = 0;
+
+ mutex_lock(&dev_list->mutex);
+ list_for_each_entry(smcibdev, &dev_list->list, list) {
+ if (num < snum)
+ goto next;
+ if (smc_nl_handle_smcr_dev(smcibdev, skb, cb))
+ goto errout;
+next:
+ num++;
+ }
+errout:
+ mutex_unlock(&dev_list->mutex);
+ cb_ctx->pos[0] = num;
+}
+
+int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ smc_nl_prep_smcr_dev(&smc_ib_devices, skb, cb);
+ return skb->len;
+}
+
static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv)
{
struct smc_link *lnk = (struct smc_link *)priv;
static struct ib_client smc_ib_client;
+static void smc_copy_netdev_ifindex(struct smc_ib_device *smcibdev, int port)
+{
+ struct ib_device *ibdev = smcibdev->ibdev;
+ struct net_device *ndev;
+
+ if (!ibdev->ops.get_netdev)
+ return;
+ ndev = ibdev->ops.get_netdev(ibdev, port + 1);
+ if (ndev) {
+ smcibdev->ndev_ifidx[port] = ndev->ifindex;
+ dev_put(ndev);
+ }
+}
+
+void smc_ib_ndev_change(struct net_device *ndev, unsigned long event)
+{
+ struct smc_ib_device *smcibdev;
+ struct ib_device *libdev;
+ struct net_device *lndev;
+ u8 port_cnt;
+ int i;
+
+ mutex_lock(&smc_ib_devices.mutex);
+ list_for_each_entry(smcibdev, &smc_ib_devices.list, list) {
+ port_cnt = smcibdev->ibdev->phys_port_cnt;
+ for (i = 0; i < min_t(size_t, port_cnt, SMC_MAX_PORTS); i++) {
+ libdev = smcibdev->ibdev;
+ if (!libdev->ops.get_netdev)
+ continue;
+ lndev = libdev->ops.get_netdev(libdev, i + 1);
+ if (lndev)
+ dev_put(lndev);
+ if (lndev != ndev)
+ continue;
+ if (event == NETDEV_REGISTER)
+ smcibdev->ndev_ifidx[i] = ndev->ifindex;
+ if (event == NETDEV_UNREGISTER)
+ smcibdev->ndev_ifidx[i] = 0;
+ }
+ }
+ mutex_unlock(&smc_ib_devices.mutex);
+}
+
/* callback function for ib_register_client() */
static int smc_ib_add_dev(struct ib_device *ibdev)
{
if (smc_pnetid_by_dev_port(ibdev->dev.parent, i,
smcibdev->pnetid[i]))
smc_pnetid_by_table_ib(smcibdev, i + 1);
+ smc_copy_netdev_ifindex(smcibdev, i);
pr_warn_ratelimited("smc: ib device %s port %d has pnetid "
"%.16s%s\n",
smcibdev->ibdev->name, i + 1,
};
extern struct smc_ib_devices smc_ib_devices; /* list of smc ib devices */
+extern struct smc_lgr_list smc_lgr_list; /* list of linkgroups */
struct smc_ib_device { /* ib-device infos for smc */
struct list_head list;
atomic_t lnk_cnt; /* number of links on ibdev */
wait_queue_head_t lnks_deleted; /* wait 4 removal of all links*/
struct mutex mutex; /* protect dev setup+cleanup */
+ atomic_t lnk_cnt_by_port[SMC_MAX_PORTS];
+ /* number of links per port */
+ int ndev_ifidx[SMC_MAX_PORTS]; /* ndev if indexes */
};
struct smc_buf_desc;
struct smc_link;
+void smc_ib_ndev_change(struct net_device *ndev, unsigned long event);
int smc_ib_register_client(void) __init;
void smc_ib_unregister_client(void);
bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport);
int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
unsigned short vlan_id, u8 gid[], u8 *sgid_index);
bool smc_ib_is_valid_local_systemid(void);
+int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb);
#endif
#include "smc_core.h"
#include "smc_ism.h"
#include "smc_pnet.h"
+#include "smc_netlink.h"
struct smcd_dev_list smcd_dev_list = {
.list = LIST_HEAD_INIT(smcd_dev_list.list),
.mutex = __MUTEX_INITIALIZER(smcd_dev_list.mutex)
};
-bool smc_ism_v2_capable;
+static bool smc_ism_v2_capable;
/* Test if an ISM communication is possible - same CPC */
int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd)
return smcd->ops->get_chid(smcd);
}
+/* HW supports ISM V2 and thus System EID is defined */
+bool smc_ism_is_v2_capable(void)
+{
+ return smc_ism_v2_capable;
+}
+
/* Set a connection using this DMBE. */
void smc_ism_set_conn(struct smc_connection *conn)
{
return rc;
}
+static int smc_nl_handle_smcd_dev(struct smcd_dev *smcd,
+ struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ char smc_pnet[SMC_MAX_PNETID_LEN + 1];
+ struct smc_pci_dev smc_pci_dev;
+ struct nlattr *port_attrs;
+ struct nlattr *attrs;
+ int use_cnt = 0;
+ void *nlh;
+
+ nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+ &smc_gen_nl_family, NLM_F_MULTI,
+ SMC_NETLINK_GET_DEV_SMCD);
+ if (!nlh)
+ goto errmsg;
+ attrs = nla_nest_start(skb, SMC_GEN_DEV_SMCD);
+ if (!attrs)
+ goto errout;
+ use_cnt = atomic_read(&smcd->lgr_cnt);
+ if (nla_put_u32(skb, SMC_NLA_DEV_USE_CNT, use_cnt))
+ goto errattr;
+ if (nla_put_u8(skb, SMC_NLA_DEV_IS_CRIT, use_cnt > 0))
+ goto errattr;
+ memset(&smc_pci_dev, 0, sizeof(smc_pci_dev));
+ smc_set_pci_values(to_pci_dev(smcd->dev.parent), &smc_pci_dev);
+ if (nla_put_u32(skb, SMC_NLA_DEV_PCI_FID, smc_pci_dev.pci_fid))
+ goto errattr;
+ if (nla_put_u16(skb, SMC_NLA_DEV_PCI_CHID, smc_pci_dev.pci_pchid))
+ goto errattr;
+ if (nla_put_u16(skb, SMC_NLA_DEV_PCI_VENDOR, smc_pci_dev.pci_vendor))
+ goto errattr;
+ if (nla_put_u16(skb, SMC_NLA_DEV_PCI_DEVICE, smc_pci_dev.pci_device))
+ goto errattr;
+ if (nla_put_string(skb, SMC_NLA_DEV_PCI_ID, smc_pci_dev.pci_id))
+ goto errattr;
+
+ port_attrs = nla_nest_start(skb, SMC_NLA_DEV_PORT);
+ if (!port_attrs)
+ goto errattr;
+ if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR, smcd->pnetid_by_user))
+ goto errportattr;
+ snprintf(smc_pnet, sizeof(smc_pnet), "%s", smcd->pnetid);
+ if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet))
+ goto errportattr;
+
+ nla_nest_end(skb, port_attrs);
+ nla_nest_end(skb, attrs);
+ genlmsg_end(skb, nlh);
+ return 0;
+
+errportattr:
+ nla_nest_cancel(skb, port_attrs);
+errattr:
+ nla_nest_cancel(skb, attrs);
+errout:
+ nlmsg_cancel(skb, nlh);
+errmsg:
+ return -EMSGSIZE;
+}
+
+static void smc_nl_prep_smcd_dev(struct smcd_dev_list *dev_list,
+ struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+ int snum = cb_ctx->pos[0];
+ struct smcd_dev *smcd;
+ int num = 0;
+
+ mutex_lock(&dev_list->mutex);
+ list_for_each_entry(smcd, &dev_list->list, list) {
+ if (num < snum)
+ goto next;
+ if (smc_nl_handle_smcd_dev(smcd, skb, cb))
+ goto errout;
+next:
+ num++;
+ }
+errout:
+ mutex_unlock(&dev_list->mutex);
+ cb_ctx->pos[0] = num;
+}
+
+int smcd_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ smc_nl_prep_smcd_dev(&smcd_dev_list, skb, cb);
+ return skb->len;
+}
+
struct smc_ism_event_work {
struct work_struct work;
struct smcd_dev *smcd;
#define SMCD_ISM_H
#include <linux/uio.h>
+#include <linux/types.h>
#include <linux/mutex.h>
#include "smc.h"
};
extern struct smcd_dev_list smcd_dev_list; /* list of smcd devices */
-extern bool smc_ism_v2_capable; /* HW supports ISM V2 and thus
- * System EID is defined
- */
struct smc_ism_vlanid { /* VLAN id set on ISM device */
struct list_head list;
int smc_ism_signal_shutdown(struct smc_link_group *lgr);
void smc_ism_get_system_eid(struct smcd_dev *dev, u8 **eid);
u16 smc_ism_get_chid(struct smcd_dev *dev);
+bool smc_ism_is_v2_capable(void);
void smc_ism_init(void);
+int smcd_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb);
#endif
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Generic netlink support functions to interact with SMC module
+ *
+ * Copyright IBM Corp. 2020
+ *
+ * Author(s): Guvenc Gulce <guvenc@linux.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/ctype.h>
+#include <linux/mutex.h>
+#include <linux/if.h>
+#include <linux/smc.h>
+
+#include "smc_core.h"
+#include "smc_ism.h"
+#include "smc_ib.h"
+#include "smc_netlink.h"
+
+#define SMC_CMD_MAX_ATTR 1
+
+/* SMC_GENL generic netlink operation definition */
+static const struct genl_ops smc_gen_nl_ops[] = {
+ {
+ .cmd = SMC_NETLINK_GET_SYS_INFO,
+ /* can be retrieved by unprivileged users */
+ .dumpit = smc_nl_get_sys_info,
+ },
+ {
+ .cmd = SMC_NETLINK_GET_LGR_SMCR,
+ /* can be retrieved by unprivileged users */
+ .dumpit = smcr_nl_get_lgr,
+ },
+ {
+ .cmd = SMC_NETLINK_GET_LINK_SMCR,
+ /* can be retrieved by unprivileged users */
+ .dumpit = smcr_nl_get_link,
+ },
+ {
+ .cmd = SMC_NETLINK_GET_LGR_SMCD,
+ /* can be retrieved by unprivileged users */
+ .dumpit = smcd_nl_get_lgr,
+ },
+ {
+ .cmd = SMC_NETLINK_GET_DEV_SMCD,
+ /* can be retrieved by unprivileged users */
+ .dumpit = smcd_nl_get_device,
+ },
+ {
+ .cmd = SMC_NETLINK_GET_DEV_SMCR,
+ /* can be retrieved by unprivileged users */
+ .dumpit = smcr_nl_get_device,
+ },
+};
+
+static const struct nla_policy smc_gen_nl_policy[2] = {
+ [SMC_CMD_MAX_ATTR] = { .type = NLA_REJECT, },
+};
+
+/* SMC_GENL family definition */
+struct genl_family smc_gen_nl_family __ro_after_init = {
+ .hdrsize = 0,
+ .name = SMC_GENL_FAMILY_NAME,
+ .version = SMC_GENL_FAMILY_VERSION,
+ .maxattr = SMC_CMD_MAX_ATTR,
+ .policy = smc_gen_nl_policy,
+ .netnsok = true,
+ .module = THIS_MODULE,
+ .ops = smc_gen_nl_ops,
+ .n_ops = ARRAY_SIZE(smc_gen_nl_ops)
+};
+
+int __init smc_nl_init(void)
+{
+ return genl_register_family(&smc_gen_nl_family);
+}
+
+void smc_nl_exit(void)
+{
+ genl_unregister_family(&smc_gen_nl_family);
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * SMC Generic netlink operations
+ *
+ * Copyright IBM Corp. 2020
+ *
+ * Author(s): Guvenc Gulce <guvenc@linux.ibm.com>
+ */
+
+#ifndef _SMC_NETLINK_H
+#define _SMC_NETLINK_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+extern struct genl_family smc_gen_nl_family;
+
+struct smc_nl_dmp_ctx {
+ int pos[2];
+};
+
+static inline struct smc_nl_dmp_ctx *smc_nl_dmp_ctx(struct netlink_callback *c)
+{
+ return (struct smc_nl_dmp_ctx *)c->ctx;
+}
+
+int smc_nl_init(void) __init;
+void smc_nl_exit(void);
+
+#endif
case NETDEV_REBOOT:
case NETDEV_UNREGISTER:
smc_pnet_remove_by_ndev(event_dev);
+ smc_ib_ndev_change(event_dev, event);
return NOTIFY_OK;
case NETDEV_REGISTER:
smc_pnet_add_by_ndev(event_dev);
+ smc_ib_ndev_change(event_dev, event);
return NOTIFY_OK;
case NETDEV_UP:
smc_pnet_add_base_pnetid(net, event_dev, ndev_pnetid);
wake_up(&link->wr_tx_wait);
}
-static void smc_wr_tx_tasklet_fn(unsigned long data)
+static void smc_wr_tx_tasklet_fn(struct tasklet_struct *t)
{
- struct smc_ib_device *dev = (struct smc_ib_device *)data;
+ struct smc_ib_device *dev = from_tasklet(dev, t, send_tasklet);
struct ib_wc wc[SMC_WR_MAX_POLL_CQE];
int i = 0, rc;
int polled = 0;
}
}
-static void smc_wr_rx_tasklet_fn(unsigned long data)
+static void smc_wr_rx_tasklet_fn(struct tasklet_struct *t)
{
- struct smc_ib_device *dev = (struct smc_ib_device *)data;
+ struct smc_ib_device *dev = from_tasklet(dev, t, recv_tasklet);
struct ib_wc wc[SMC_WR_MAX_POLL_CQE];
int polled = 0;
int rc;
void smc_wr_add_dev(struct smc_ib_device *smcibdev)
{
- tasklet_init(&smcibdev->recv_tasklet, smc_wr_rx_tasklet_fn,
- (unsigned long)smcibdev);
- tasklet_init(&smcibdev->send_tasklet, smc_wr_tx_tasklet_fn,
- (unsigned long)smcibdev);
+ tasklet_setup(&smcibdev->recv_tasklet, smc_wr_rx_tasklet_fn);
+ tasklet_setup(&smcibdev->send_tasklet, smc_wr_tx_tasklet_fn);
}
int smc_wr_create_link(struct smc_link *lnk)
* Based upon Swansea University Computer Society NET3.039
*/
+#include <linux/ethtool.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/file.h>
#include <linux/seq_file.h>
#include <linux/mutex.h>
#include <linux/if_bridge.h>
-#include <linux/if_frad.h>
#include <linux/if_vlan.h>
#include <linux/ptp_classify.h>
#include <linux/init.h>
}
EXPORT_SYMBOL(vlan_ioctl_set);
-static DEFINE_MUTEX(dlci_ioctl_mutex);
-static int (*dlci_ioctl_hook) (unsigned int, void __user *);
-
-void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
-{
- mutex_lock(&dlci_ioctl_mutex);
- dlci_ioctl_hook = hook;
- mutex_unlock(&dlci_ioctl_mutex);
-}
-EXPORT_SYMBOL(dlci_ioctl_set);
-
static long sock_do_ioctl(struct net *net, struct socket *sock,
unsigned int cmd, unsigned long arg)
{
err = vlan_ioctl_hook(net, argp);
mutex_unlock(&vlan_ioctl_mutex);
break;
- case SIOCADDDLCI:
- case SIOCDELDLCI:
- err = -ENOPKG;
- if (!dlci_ioctl_hook)
- request_module("dlci");
-
- mutex_lock(&dlci_ioctl_mutex);
- if (dlci_ioctl_hook)
- err = dlci_ioctl_hook(cmd, argp);
- mutex_unlock(&dlci_ioctl_mutex);
- break;
case SIOCGSKNS:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
case SIOCBRDELBR:
case SIOCGIFVLAN:
case SIOCSIFVLAN:
- case SIOCADDDLCI:
- case SIOCDELDLCI:
case SIOCGSKNS:
case SIOCGSTAMP_NEW:
case SIOCGSTAMPNS_NEW:
}
/**
- * rpc_mkpipe - make an rpc_pipefs file for kernel<->userspace communication
+ * rpc_mkpipe_dentry - make an rpc_pipefs file for kernel<->userspace
+ * communication
* @parent: dentry of directory to create new "pipe" in
* @name: name of pipe
* @private: private data to associate with the pipe, for the caller's use
void tipc_set_node_id(struct net *net, u8 *id)
{
struct tipc_net *tn = tipc_net(net);
- u32 *tmp = (u32 *)id;
memcpy(tn->node_id, id, NODE_ID_LEN);
tipc_nodeid2string(tn->node_id_string, id);
- tn->trial_addr = tmp[0] ^ tmp[1] ^ tmp[2] ^ tmp[3];
- pr_info("Own node identity %s, cluster identity %u\n",
+ tn->trial_addr = hash128to32(id);
+ pr_info("Node identity %s, cluster identity %u\n",
tipc_own_id_string(net), tn->net_id);
}
}
tn->trial_addr = addr;
tn->addr_trial_end = jiffies;
- pr_info("32-bit node address hash set to %x\n", addr);
+ pr_info("Node number set to %u\n", addr);
}
char *tipc_nodeid2string(char *str, u8 *id)
*
* Copyright (c) 2000-2006, 2018, Ericsson AB
* Copyright (c) 2004-2005, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
/**
* tipc_media_find - locates specified media object by name
+ * @name: name to locate
*/
struct tipc_media *tipc_media_find(const char *name)
{
/**
* media_find_id - locates specified media object by type identifier
+ * @type: type identifier to locate
*/
static struct tipc_media *media_find_id(u8 type)
{
/**
* tipc_media_addr_printf - record media address in print buffer
+ * @buf: output buffer
+ * @len: output buffer size remaining
+ * @a: input media address
*/
int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a)
{
* @name: ptr to bearer name string
* @name_parts: ptr to area for bearer name components (or NULL if not needed)
*
- * Returns 1 if bearer name is valid, otherwise 0.
+ * Return: 1 if bearer name is valid, otherwise 0.
*/
static int bearer_name_validate(const char *name,
struct tipc_bearer_names *name_parts)
u32 if_len;
/* copy bearer name & ensure length is OK */
- name_copy[TIPC_MAX_BEARER_NAME - 1] = 0;
- /* need above in case non-Posix strncpy() doesn't pad with nulls */
- strncpy(name_copy, name, TIPC_MAX_BEARER_NAME);
- if (name_copy[TIPC_MAX_BEARER_NAME - 1] != 0)
+ if (strscpy(name_copy, name, TIPC_MAX_BEARER_NAME) < 0)
return 0;
/* ensure all component parts of bearer name are present */
/**
* tipc_bearer_find - locates bearer object with matching bearer name
+ * @net: the applicable net namespace
+ * @name: bearer name to locate
*/
struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name)
{
/**
* tipc_enable_bearer - enable bearer with the given name
+ * @net: the applicable net namespace
+ * @name: bearer name to enable
+ * @disc_domain: bearer domain
+ * @prio: bearer priority
+ * @attr: nlattr array
*/
static int tipc_enable_bearer(struct net *net, const char *name,
u32 disc_domain, u32 prio,
/**
* tipc_reset_bearer - Reset all links established over this bearer
+ * @net: the applicable net namespace
+ * @b: the target bearer
*/
static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b)
{
}
/**
- * bearer_disable
+ * bearer_disable - disable this bearer
+ * @net: the applicable net namespace
+ * @b: the bearer to disable
*
* Note: This routine assumes caller holds RTNL lock.
*/
}
/* tipc_disable_l2_media - detach TIPC bearer from an L2 interface
+ * @b: the target bearer
*
* Mark L2 bearer as inactive so that incoming buffers are thrown away
*/
/**
* tipc_l2_send_msg - send a TIPC packet out over an L2 interface
+ * @net: the associated network namespace
* @skb: the packet to be sent
* @b: the bearer through which the packet is to be sent
* @dest: peer destination address
* @raw2addr: convert from raw addr format to media addr format
* @priority: default link (and bearer) priority
* @tolerance: default time (in ms) before declaring link failure
- * @window: default window (in packets) before declaring link congestion
+ * @min_win: minimum window (in packets) before declaring link congestion
+ * @max_win: maximum window (in packets) before declaring link congestion
* @mtu: max packet size bearer can support for media type not dependent on
* underlying device MTU
* @type_id: TIPC media identifier
* @pt: packet type for bearer
* @rcu: rcu struct for tipc_bearer
* @priority: default link priority for bearer
- * @window: default window size for bearer
+ * @min_win: minimum window (in packets) before declaring link congestion
+ * @max_win: maximum window (in packets) before declaring link congestion
* @tolerance: default link tolerance for bearer
* @domain: network domain to which links can be established
* @identity: array index of this bearer within TIPC bearer array
- * @link_req: ptr to (optional) structure making periodic link setup requests
+ * @disc: ptr to link setup request
* @net_plane: network plane ('A' through 'H') currently associated with bearer
+ * @up: bearer up flag (bit 0)
+ * @refcnt: tipc_bearer reference counter
*
* Note: media-specific code is responsible for initialization of the fields
* indicated below when a bearer is enabled; TIPC's generic bearer code takes
if (err)
goto out_nametbl;
- INIT_LIST_HEAD(&tn->dist_queue);
-
err = tipc_bcast_init(net);
if (err)
goto out_bclink;
*
* Copyright (c) 2005-2006, 2013-2018 Ericsson AB
* Copyright (c) 2005-2007, 2010-2013, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
spinlock_t nametbl_lock;
struct name_table *nametbl;
- /* Name dist queue */
- struct list_head dist_queue;
-
/* Topology subscription server */
struct tipc_topsrv *topsrv;
atomic_t subscription_count;
return net_hash_mix(&init_net) ^ net_hash_mix(net) ^ tn_rand;
}
+static inline u32 hash128to32(char *bytes)
+{
+ __be32 *tmp = (__be32 *)bytes;
+ u32 res;
+
+ res = ntohl(tmp[0] ^ tmp[1] ^ tmp[2] ^ tmp[3]);
+ if (likely(res))
+ return res;
+ return ntohl(tmp[0] | tmp[1] | tmp[2] | tmp[3]);
+}
+
#ifdef CONFIG_SYSCTL
int tipc_register_sysctl(void);
void tipc_unregister_sysctl(void);
// SPDX-License-Identifier: GPL-2.0
-/**
+/*
* net/tipc/crypto.c: TIPC crypto for key handling & packet en/decryption
*
* Copyright (c) 2019, Ericsson AB
#define TIPC_REKEYING_INTV_DEF (60 * 24) /* default: 1 day */
-/**
+/*
* TIPC Key ids
*/
enum {
KEY_MAX = KEY_3,
};
-/**
+/*
* TIPC Crypto statistics
*/
enum {
/* Key exchange switch, default: on */
int sysctl_tipc_key_exchange_enabled __read_mostly = 1;
-/**
+/*
* struct tipc_key - TIPC keys' status indicator
*
* 7 6 5 4 3 2 1 0
/**
* struct tipc_tfm - TIPC TFM structure to form a list of TFMs
+ * @tfm: cipher handle/key
+ * @list: linked list of TFMs
*/
struct tipc_tfm {
struct crypto_aead *tfm;
* @salt: the key's SALT value
* @authsize: authentication tag size (max = 16)
* @mode: crypto mode is applied to the key
- * @hint[]: a hint for user key
+ * @hint: a hint for user key
* @rcu: struct rcu_head
* @key: the aead key
* @gen: the key's generation
/**
* struct tipc_crypto_stats - TIPC Crypto statistics
+ * @stat: array of crypto statistics
*/
struct tipc_crypto_stats {
unsigned int stat[MAX_STATS];
* @key_master: flag indicates if master key exists
* @legacy_user: flag indicates if a peer joins w/o master key (for bwd comp.)
* @nokey: no key indication
+ * @flags: combined flags field
* @lock: tipc_key lock
*/
struct tipc_crypto {
/**
* tipc_aead_key_validate - Validate a AEAD user key
+ * @ukey: pointer to user key data
+ * @info: netlink info pointer
*/
int tipc_aead_key_validate(struct tipc_aead_key *ukey, struct genl_info *info)
{
/**
* tipc_aead_tfm_next - Move TFM entry to the next one in list and return it
+ * @aead: the AEAD key pointer
*/
static struct crypto_aead *tipc_aead_tfm_next(struct tipc_aead *aead)
{
* @__dnode: TIPC dest node if "known"
*
* Return:
- * 0 : if the encryption has completed
- * -EINPROGRESS/-EBUSY : if a callback will be performed
- * < 0 : the encryption has failed
+ * * 0 : if the encryption has completed
+ * * -EINPROGRESS/-EBUSY : if a callback will be performed
+ * * < 0 : the encryption has failed
*/
static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb,
struct tipc_bearer *b,
* @b: TIPC bearer where the message has been received
*
* Return:
- * 0 : if the decryption has completed
- * -EINPROGRESS/-EBUSY : if a callback will be performed
- * < 0 : the decryption has failed
+ * * 0 : if the decryption has completed
+ * * -EINPROGRESS/-EBUSY : if a callback will be performed
+ * * < 0 : the decryption has failed
*/
static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead,
struct sk_buff *skb, struct tipc_bearer *b)
* tipc_ehdr_validate - Validate an encryption message
* @skb: the message buffer
*
- * Returns "true" if this is a valid encryption message, otherwise "false"
+ * Return: "true" if this is a valid encryption message, otherwise "false"
*/
bool tipc_ehdr_validate(struct sk_buff *skb)
{
* Otherwise, the skb is freed!
*
* Return:
- * 0 : the encryption has succeeded (or no encryption)
- * -EINPROGRESS/-EBUSY : the encryption is ongoing, a callback will be made
- * -ENOKEK : the encryption has failed due to no key
- * -EKEYREVOKED : the encryption has failed due to key revoked
- * -ENOMEM : the encryption has failed due to no memory
- * < 0 : the encryption has failed due to other reasons
+ * * 0 : the encryption has succeeded (or no encryption)
+ * * -EINPROGRESS/-EBUSY : the encryption is ongoing, a callback will be made
+ * * -ENOKEK : the encryption has failed due to no key
+ * * -EKEYREVOKED : the encryption has failed due to key revoked
+ * * -ENOMEM : the encryption has failed due to no memory
+ * * < 0 : the encryption has failed due to other reasons
*/
int tipc_crypto_xmit(struct net *net, struct sk_buff **skb,
struct tipc_bearer *b, struct tipc_media_addr *dst,
* cluster key(s) can be taken for decryption (- recursive).
*
* Return:
- * 0 : the decryption has successfully completed
- * -EINPROGRESS/-EBUSY : the decryption is ongoing, a callback will be made
- * -ENOKEY : the decryption has failed due to no key
- * -EBADMSG : the decryption has failed due to bad message
- * -ENOMEM : the decryption has failed due to no memory
- * < 0 : the decryption has failed due to other reasons
+ * * 0 : the decryption has successfully completed
+ * * -EINPROGRESS/-EBUSY : the decryption is ongoing, a callback will be made
+ * * -ENOKEY : the decryption has failed due to no key
+ * * -EBADMSG : the decryption has failed due to bad message
+ * * -ENOMEM : the decryption has failed due to no memory
+ * * < 0 : the decryption has failed due to other reasons
*/
int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx,
struct sk_buff **skb, struct tipc_bearer *b)
/* SPDX-License-Identifier: GPL-2.0 */
-/**
+/*
* net/tipc/crypto.h: Include file for TIPC crypto
*
* Copyright (c) 2019, Ericsson AB
#define TIPC_AES_GCM_IV_SIZE 12
#define TIPC_AES_GCM_TAG_SIZE 16
-/**
+/*
* TIPC crypto modes:
* - CLUSTER_KEY:
* One single key is used for both TX & RX in all nodes in the cluster.
extern int sysctl_tipc_max_tfms __read_mostly;
extern int sysctl_tipc_key_exchange_enabled __read_mostly;
-/**
+/*
* TIPC encryption message format:
*
* 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0
/**
* tipc_disc_init_msg - initialize a link setup message
* @net: the applicable net namespace
+ * @skb: buffer containing message
* @mtyp: message type (request or response)
* @b: ptr to bearer issuing message
*/
* @dest: destination address for request messages
* @skb: pointer to created frame
*
- * Returns 0 if successful, otherwise -errno.
+ * Return: 0 if successful, otherwise -errno.
*/
int tipc_disc_create(struct net *net, struct tipc_bearer *b,
struct tipc_media_addr *dest, struct sk_buff **skb)
/**
* tipc_disc_delete - destroy object sending periodic link setup requests
- * @d: ptr to link duest structure
+ * @d: ptr to link dest structure
*/
void tipc_disc_delete(struct tipc_discoverer *d)
{
* net/tipc/group.c: TIPC group messaging code
*
* Copyright (c) 2017, Ericsson AB
+ * Copyright (c) 2020, Red Hat Inc
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
return &grp->dests;
}
-void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq,
+void tipc_group_self(struct tipc_group *grp, struct tipc_service_range *seq,
int *scope)
{
seq->type = grp->type;
* net/tipc/group.h: Include file for TIPC group unicast/multicast functions
*
* Copyright (c) 2017, Ericsson AB
+ * Copyright (c) 2020, Red Hat Inc
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
void tipc_group_add_member(struct tipc_group *grp, u32 node,
u32 port, u32 instance);
struct tipc_nlist *tipc_group_dests(struct tipc_group *grp);
-void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq,
+void tipc_group_self(struct tipc_group *grp, struct tipc_service_range *seq,
int *scope);
u32 tipc_group_exclude(struct tipc_group *grp);
void tipc_group_filter_msg(struct tipc_group *grp,
* @reasm_buf: head of partially reassembled inbound message fragments
* @bc_rcvr: marks that this is a broadcast receiver link
* @stats: collects statistics regarding link activity
+ * @session: session to be used by link
+ * @snd_nxt_state: next send seq number
+ * @rcv_nxt_state: next rcv seq number
+ * @in_session: have received ACTIVATE_MSG from peer
+ * @active: link is active
+ * @if_name: associated interface name
+ * @rst_cnt: link reset counter
+ * @drop_point: seq number for failover handling (FIXME)
+ * @failover_reasm_skb: saved failover msg ptr (FIXME)
+ * @failover_deferdq: deferred message queue for failover processing (FIXME)
+ * @transmq: the link's transmit queue
+ * @backlog: link's backlog by priority (importance)
+ * @snd_nxt: next sequence number to be used
+ * @rcv_unacked: # messages read by user, but not yet acked back to peer
+ * @deferdq: deferred receive queue
+ * @window: sliding window size for congestion handling
+ * @min_win: minimal send window to be used by link
+ * @ssthresh: slow start threshold for congestion handling
+ * @max_win: maximal send window to be used by link
+ * @cong_acks: congestion acks for congestion avoidance (FIXME)
+ * @checkpoint: seq number for congestion window size handling
+ * @reasm_tnlmsg: fragmentation/reassembly area for tunnel protocol message
+ * @last_gap: last gap ack blocks for bcast (FIXME)
+ * @last_ga: ptr to gap ack blocks
+ * @bc_rcvlink: the peer specific link used for broadcast reception
+ * @bc_sndlink: the namespace global link used for broadcast sending
+ * @nack_state: bcast nack state
+ * @bc_peer_is_up: peer has acked the bcast init msg
*/
struct tipc_link {
u32 addr;
* @min_win: minimal send window to be used by link
* @max_win: maximal send window to be used by link
* @session: session to be used by link
- * @ownnode: identity of own node
* @peer: node id of peer node
* @peer_caps: bitmap describing peer node capabilities
* @bc_sndlink: the namespace global link used for broadcast sending
* @inputq: queue to put messages ready for delivery
* @namedq: queue to put binding table update messages ready for delivery
* @link: return value, pointer to put the created link
+ * @self: local unicast link id
+ * @peer_id: 128-bit ID of peer
*
- * Returns true if link was created, otherwise false
+ * Return: true if link was created, otherwise false
*/
bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
int tolerance, char net_plane, u32 mtu, int priority,
* @inputq: queue to put messages ready for delivery
* @namedq: queue to put binding table update messages ready for delivery
* @link: return value, pointer to put the created link
+ * @ownnode: identity of own node
+ * @peer: node id of peer node
+ * @peer_id: 128-bit ID of peer
+ * @peer_caps: bitmap describing peer node capabilities
+ * @bc_sndlink: the namespace global link used for broadcast sending
*
- * Returns true if link was created, otherwise false
+ * Return: true if link was created, otherwise false
*/
bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, u8 *peer_id,
int mtu, u32 min_win, u32 max_win, u16 peer_caps,
* tipc_link_too_silent - check if link is "too silent"
* @l: tipc link to be checked
*
- * Returns true if the link 'silent_intv_cnt' is about to reach the
+ * Return: true if the link 'silent_intv_cnt' is about to reach the
* 'abort_limit' value, otherwise false
*/
bool tipc_link_too_silent(struct tipc_link *l)
* @xmitq: returned list of packets to be sent by caller
*
* Consumes the buffer chain.
- * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS
* Messages at TIPC_SYSTEM_IMPORTANCE are always accepted
+ * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS
*/
int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
struct sk_buff_head *xmitq)
pr_warn("Dropping received illegal msg type\n");
kfree_skb(skb);
return true;
- };
+ }
}
/* tipc_link_input - process packet that has passed link protocol check
if (!msg_peer_node_is_up(hdr))
return rc;
- /* Open when peer ackowledges our bcast init msg (pkt #1) */
+ /* Open when peer acknowledges our bcast init msg (pkt #1) */
if (msg_ack(hdr))
l->bc_peer_is_up = true;
/**
* tipc_buf_acquire - creates a TIPC message buffer
* @size: message size (including TIPC header)
+ * @gfp: memory allocation flags
*
- * Returns a new buffer with data pointers set to the specified size.
+ * Return: a new buffer with data pointers set to the specified size.
*
- * NOTE: Headroom is reserved to allow prepending of a data link header.
- * There may also be unrequested tailroom present at the buffer's end.
+ * NOTE:
+ * Headroom is reserved to allow prepending of a data link header.
+ * There may also be unrequested tailroom present at the buffer's end.
*/
struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp)
{
* @m: the data to be appended
* @mss: max allowable size of buffer
* @dlen: size of data to be appended
- * @txq: queue to appand to
- * Returns the number og 1k blocks appended or errno value
+ * @txq: queue to append to
+ *
+ * Return: the number of 1k blocks appended or errno value
*/
int tipc_msg_append(struct tipc_msg *_hdr, struct msghdr *m, int dlen,
int mss, struct sk_buff_head *txq)
* @pktmax: max size of a fragment incl. the header
* @frags: returned fragment skb list
*
- * Returns 0 if the fragmentation is successful, otherwise: -EINVAL
+ * Return: 0 if the fragmentation is successful, otherwise: -EINVAL
* or -ENOMEM
*/
int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr,
* tipc_msg_build - create buffer chain containing specified header and data
* @mhdr: Message header, to be prepended to data
* @m: User message
+ * @offset: buffer offset for fragmented messages (FIXME)
* @dsz: Total length of user data
* @pktmax: Max packet size that can be used
* @list: Buffer or chain of buffers to be returned to caller
* Note that the recursive call we are making here is safe, since it can
* logically go only one further level down.
*
- * Returns message data size or errno: -ENOMEM, -EFAULT
+ * Return: message data size or errno: -ENOMEM, -EFAULT
*/
int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset,
int dsz, int pktmax, struct sk_buff_head *list)
* @msg: message to be appended
* @max: max allowable size for the bundle buffer
*
- * Returns "true" if bundling has been performed, otherwise "false"
+ * Return: "true" if bundling has been performed, otherwise "false"
*/
static bool tipc_msg_bundle(struct sk_buff *bskb, struct tipc_msg *msg,
u32 max)
* @skb: buffer to be extracted from.
* @iskb: extracted inner buffer, to be returned
* @pos: position in outer message of msg to be extracted.
- * Returns position of next msg
+ * Returns position of next msg.
* Consumes outer buffer when last packet extracted
- * Returns true when there is an extracted buffer, otherwise false
+ * Return: true when there is an extracted buffer, otherwise false
*/
bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos)
{
* @skb: buffer containing message to be reversed; will be consumed
* @err: error code to be set in message, if any
* Replaces consumed buffer with new one when successful
- * Returns true if success, otherwise false
+ * Return: true if success, otherwise false
*/
bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err)
{
/**
* tipc_msg_lookup_dest(): try to find new destination for named message
+ * @net: pointer to associated network namespace
* @skb: the buffer containing the message.
* @err: error code to be used by caller if lookup fails
* Does not consume buffer
- * Returns true if a destination is found, false otherwise
+ * Return: true if a destination is found, false otherwise
*/
bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err)
{
/**
* publ_to_item - add publication info to a publication message
+ * @p: publication info
+ * @i: location of item in the message
*/
static void publ_to_item(struct distr_item *i, struct publication *p)
{
/**
* named_prepare_buf - allocate & initialize a publication message
+ * @net: the associated network namespace
+ * @type: message type
+ * @size: payload size
+ * @dest: destination node
*
* The buffer returned is of size INT_H_SIZE + payload size
*/
/**
* tipc_named_publish - tell other nodes about a new publication by this node
+ * @net: the associated network namespace
+ * @publ: the new publication
*/
struct sk_buff *tipc_named_publish(struct net *net, struct publication *publ)
{
/**
* tipc_named_withdraw - tell other nodes about a withdrawn publication by this node
+ * @net: the associated network namespace
+ * @publ: the withdrawn publication
*/
struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ)
{
/**
* named_distribute - prepare name info for bulk distribution to another node
+ * @net: the associated network namespace
* @list: list of messages (buffers) to be returned from this function
* @dnode: node to be updated
* @pls: linked list of publication items to be packed into buffer chain
+ * @seqno: sequence number for this message
*/
static void named_distribute(struct net *net, struct sk_buff_head *list,
u32 dnode, struct list_head *pls, u16 seqno)
/**
* tipc_named_node_up - tell specified node about all publications by this node
+ * @net: the associated network namespace
+ * @dnode: destination node
+ * @capabilities: peer node's capabilities
*/
void tipc_named_node_up(struct net *net, u32 dnode, u16 capabilities)
{
/**
* tipc_publ_purge - remove publication associated with a failed node
+ * @net: the associated network namespace
+ * @publ: the publication to remove
+ * @addr: failed node's address
*
* Invoked for each publication issued by a newly failed node.
* Removes publication structure from name table & deletes it.
kfree_rcu(p, rcu);
}
-/**
- * tipc_dist_queue_purge - remove deferred updates from a node that went down
- */
-static void tipc_dist_queue_purge(struct net *net, u32 addr)
-{
- struct tipc_net *tn = net_generic(net, tipc_net_id);
- struct distr_queue_item *e, *tmp;
-
- spin_lock_bh(&tn->nametbl_lock);
- list_for_each_entry_safe(e, tmp, &tn->dist_queue, next) {
- if (e->node != addr)
- continue;
- list_del(&e->next);
- kfree(e);
- }
- spin_unlock_bh(&tn->nametbl_lock);
-}
-
void tipc_publ_notify(struct net *net, struct list_head *nsub_list,
u32 addr, u16 capabilities)
{
list_for_each_entry_safe(publ, tmp, nsub_list, binding_node)
tipc_publ_purge(net, publ, addr);
- tipc_dist_queue_purge(net, addr);
spin_lock_bh(&tn->nametbl_lock);
if (!(capabilities & TIPC_NAMED_BCAST))
nt->rc_dests--;
/**
* tipc_update_nametbl - try to process a nametable update and notify
* subscribers
+ * @net: the associated network namespace
+ * @i: location of item in the message
+ * @node: node address
+ * @dtype: name distributor message type
*
* tipc_nametbl_lock must be held.
- * Returns the publication item if successful, otherwise NULL.
+ * Return: the publication item if successful, otherwise NULL.
*/
static bool tipc_update_nametbl(struct net *net, struct distr_item *i,
u32 node, u32 dtype)
/**
* tipc_named_rcv - process name table update messages sent by another node
+ * @net: the associated network namespace
+ * @namedq: queue to receive from
+ * @rcv_nxt: store last received seqno here
+ * @open: last bulk msg was received (FIXME)
*/
void tipc_named_rcv(struct net *net, struct sk_buff_head *namedq,
u16 *rcv_nxt, bool *open)
/**
* tipc_named_reinit - re-initialize local publications
+ * @net: the associated network namespace
*
* This routine is called whenever TIPC networking is enabled.
* All name table entries published by this node are updated to reflect
* @type: name sequence type
* @lower: name sequence lower bound
* @upper: name sequence upper bound
- * @ref: publishing port reference
+ * @port: publishing port reference
* @key: publication key
*
* ===> All fields are stored in network byte order. <===
*
* Copyright (c) 2000-2006, 2014-2018, Ericsson AB
* Copyright (c) 2004-2008, 2010-2014, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* range match
* @sr: the service range pointer as a loop cursor
* @sc: the pointer to tipc service which holds the service range rbtree
- * @start, end: the range (end >= start) for matching
+ * @start: beginning of the search range (end >= start) for matching
+ * @end: end of the search range (end >= start) for matching
*/
#define service_range_foreach_match(sr, sc, start, end) \
for (sr = service_range_match_first((sc)->ranges.rb_node, \
/**
* service_range_match_first - find first service range matching a range
* @n: the root node of service range rbtree for searching
- * @start, end: the range (end >= start) for matching
+ * @start: beginning of the search range (end >= start) for matching
+ * @end: end of the search range (end >= start) for matching
*
* Return: the leftmost service range node in the rbtree that overlaps the
* specific range if any. Otherwise, returns NULL.
/**
* service_range_match_next - find next service range matching a range
* @n: a node in service range rbtree from which the searching starts
- * @start, end: the range (end >= start) for matching
+ * @start: beginning of the search range (end >= start) for matching
+ * @end: end of the search range (end >= start) for matching
*
* Return: the next service range node to the given node in the rbtree that
* overlaps the specific range if any. Otherwise, returns NULL.
/**
* tipc_publ_create - create a publication structure
+ * @type: name sequence type
+ * @lower: name sequence lower bound
+ * @upper: name sequence upper bound
+ * @scope: publication scope
+ * @node: network address of publishing socket
+ * @port: publishing port
+ * @key: publication key
*/
static struct publication *tipc_publ_create(u32 type, u32 lower, u32 upper,
u32 scope, u32 node, u32 port,
/**
* tipc_service_create - create a service structure for the specified 'type'
+ * @type: service type
+ * @hd: name_table services list
*
* Allocates a single range structure and sets it to all 0's.
*/
/**
* tipc_service_remove_publ - remove a publication from a service
+ * @sr: service_range to remove publication from
+ * @node: target node
+ * @key: target publication key
*/
static struct publication *tipc_service_remove_publ(struct service_range *sr,
u32 node, u32 key)
return NULL;
}
-/**
+/*
* Code reused: time_after32() for the same purpose
*/
#define publication_after(pa, pb) time_after32((pa)->id, (pb)->id)
* tipc_service_subscribe - attach a subscription, and optionally
* issue the prescribed number of events if there is any service
* range overlapping with the requested range
+ * @service: the tipc_service to attach the @sub to
+ * @sub: the subscription to attach
*/
static void tipc_service_subscribe(struct tipc_service *service,
struct tipc_subscription *sub)
struct publication *p, *first, *tmp;
struct list_head publ_list;
struct service_range *sr;
- struct tipc_name_seq ns;
+ struct tipc_service_range r;
u32 filter;
- ns.type = tipc_sub_read(sb, seq.type);
- ns.lower = tipc_sub_read(sb, seq.lower);
- ns.upper = tipc_sub_read(sb, seq.upper);
+ r.type = tipc_sub_read(sb, seq.type);
+ r.lower = tipc_sub_read(sb, seq.lower);
+ r.upper = tipc_sub_read(sb, seq.upper);
filter = tipc_sub_read(sb, filter);
tipc_sub_get(sub);
return;
INIT_LIST_HEAD(&publ_list);
- service_range_foreach_match(sr, service, ns.lower, ns.upper) {
+ service_range_foreach_match(sr, service, r.lower, r.upper) {
first = NULL;
list_for_each_entry(p, &sr->all_publ, all_publ) {
if (filter & TIPC_SUB_PORTS)
/**
* tipc_nametbl_translate - perform service instance to socket translation
- *
- * On entry, 'dnode' is the search domain used during translation.
+ * @net: network namespace
+ * @type: message type
+ * @instance: message instance
+ * @dnode: the search domain used during translation
*
* On exit:
* - if translation is deferred to another node, leave 'dnode' unchanged and
- * return 0
+ * return 0
* - if translation is attempted and succeeds, set 'dnode' to the publishing
- * node and return the published (non-zero) port number
+ * node and return the published (non-zero) port number
* - if translation is attempted and fails, set 'dnode' to 0 and return 0
*
* Note that for legacy users (node configured with Z.C.N address format) the
/**
* tipc_nametbl_withdraw - withdraw a service binding
+ * @net: network namespace
+ * @type: service type
+ * @lower: service range lower bound
+ * @upper: service range upper bound
+ * @key: target publication key
*/
int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower,
u32 upper, u32 key)
/**
* tipc_nametbl_subscribe - add a subscription object to the name table
+ * @sub: subscription to add
*/
bool tipc_nametbl_subscribe(struct tipc_subscription *sub)
{
/**
* tipc_nametbl_unsubscribe - remove a subscription object from name table
+ * @sub: subscription to remove
*/
void tipc_nametbl_unsubscribe(struct tipc_subscription *sub)
{
}
/**
- * tipc_service_delete - purge all publications for a service and delete it
+ * tipc_service_delete - purge all publications for a service and delete it
+ * @net: the associated network namespace
+ * @sc: tipc_service to delete
*/
static void tipc_service_delete(struct net *net, struct tipc_service *sc)
{
* @key: publication key, unique across the cluster
* @id: publication id
* @binding_node: all publications from the same node which bound this one
- * - Remote publications: in node->publ_list
- * Used by node/name distr to withdraw publications when node is lost
+ * - Remote publications: in node->publ_list;
+ * Used by node/name distr to withdraw publications when node is lost
* - Local/node scope publications: in name_table->node_scope list
* - Local/cluster scope publications: in name_table->cluster_scope list
* @binding_sock: all publications from the same socket which bound this one
/**
* struct name_table - table containing all existing port name publications
- * @seq_hlist: name sequence hash lists
+ * @services: name sequence hash lists
* @node_scope: all local publications with node scope
* - used by name_distr during re-init of name table
* @cluster_scope: all local publications with cluster scope
* - used by name_distr to send bulk updates to new nodes
* - used by name_distr during re-init of name table
+ * @cluster_scope_lock: lock for accessing @cluster_scope
* @local_publ_count: number of publications issued by this node
+ * @rc_dests: destination node counter
+ * @snd_nxt: next sequence number to be used
*/
struct name_table {
struct hlist_head services[TIPC_NAMETBL_SIZE];
tipc_named_reinit(net);
tipc_sk_reinit(net);
tipc_mon_reinit_self(net);
- tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
+ tipc_nametbl_publish(net, TIPC_NODE_STATE, addr, addr,
TIPC_CLUSTER_SCOPE, 0, addr);
}
skb_put(skb, sizeof(struct tlv_desc));
}
-static int tipc_tlv_sprintf(struct sk_buff *skb, const char *fmt, ...)
+static __printf(2, 3) int tipc_tlv_sprintf(struct sk_buff *skb,
+ const char *fmt, ...)
{
int n;
u16 len;
return 0;
tipc_tlv_sprintf(msg->rep, "\nLink <%s>\n",
- nla_data(link[TIPC_NLA_LINK_NAME]));
+ (char *)nla_data(link[TIPC_NLA_LINK_NAME]));
if (link[TIPC_NLA_LINK_BROADCAST]) {
__fill_bc_link_stat(msg, prop, stats);
link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
- nla_strlcpy(link_info.str, link[TIPC_NLA_LINK_NAME],
+ nla_strscpy(link_info.str, link[TIPC_NLA_LINK_NAME],
TIPC_MAX_LINK_NAME);
return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,
/**
* struct tipc_node - TIPC node structure
* @addr: network address of node
- * @ref: reference counter to node object
+ * @kref: reference counter to node object
* @lock: rwlock governing access to structure
* @net: the applicable net namespace
* @hash: links to adjacent nodes in unsorted hash chain
* @namedq: pointer to name table input queue with name table messages
* @active_links: bearer ids of active links, used as index into links[] array
* @links: array containing references to all links to node
+ * @bc_entry: broadcast link entry
* @action_flags: bit mask of different types of node actions
* @state: connectivity state vs peer node
* @preliminary: a preliminary node or not
+ * @failover_sent: failover sent or not
* @sync_point: sequence number where synch/failover is finished
* @list: links to adjacent nodes in sorted list of cluster's nodes
* @working_links: number of working links to node (both active and standby)
* @capabilities: bitmap, indicating peer node's functional capabilities
* @signature: node instance identifier
* @link_id: local and remote bearer ids of changing link, if any
+ * @peer_id: 128-bit ID of peer
+ * @peer_id_string: ID string of peer
* @publ_list: list of publications
+ * @conn_sks: list of connections (FIXME)
+ * @timer: node's keepalive timer
+ * @keepalive_intv: keepalive interval in milliseconds
* @rcu: rcu struct for tipc_node
* @delete_at: indicates the time for deleting a down node
+ * @peer_net: peer's net namespace
+ * @peer_hash_mix: hash for this peer (FIXME)
* @crypto_rx: RX crypto handler
*/
struct tipc_node {
#ifdef CONFIG_TIPC_CRYPTO
/**
* tipc_node_crypto_rx - Retrieve crypto RX handle from node
+ * @__n: target tipc_node
* Note: node ref counter must be held first!
*/
struct tipc_crypto *tipc_node_crypto_rx(struct tipc_node *__n)
/**
* __tipc_node_link_up - handle addition of link
+ * @n: target tipc_node
+ * @bearer_id: id of the bearer
+ * @xmitq: queue for messages to be xmited on
* Node lock must be held by caller
* Link becomes active (alone or shared) or standby, depending on its priority.
*/
/**
* tipc_node_link_up - handle addition of link
+ * @n: target tipc_node
+ * @bearer_id: id of the bearer
+ * @xmitq: queue for messages to be xmited on
*
* Link becomes active (alone or shared) or standby, depending on its priority.
*/
*
* This function is only called in a very special situation where link
* failover can be already started on peer node but not on this node.
- * This can happen when e.g.
+ * This can happen when e.g.::
+ *
* 1. Both links <1A-2A>, <1B-2B> down
* 2. Link endpoint 2A up, but 1A still down (e.g. due to network
- * disturbance, wrong session, etc.)
+ * disturbance, wrong session, etc.)
* 3. Link <1B-2B> up
* 4. Link endpoint 2A down (e.g. due to link tolerance timeout)
* 5. Node 2 starts failover onto link <1B-2B>
/**
* __tipc_node_link_down - handle loss of link
+ * @n: target tipc_node
+ * @bearer_id: id of the bearer
+ * @xmitq: queue for messages to be xmited on
+ * @maddr: output media address of the bearer
*/
static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
struct sk_buff_head *xmitq,
/**
* tipc_node_get_linkname - get the name of a link
*
+ * @net: the applicable net namespace
* @bearer_id: id of the bearer
* @addr: peer node address
* @linkname: link name output buffer
+ * @len: size of @linkname output buffer
*
- * Returns 0 on success
+ * Return: 0 on success
*/
int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr,
char *linkname, size_t len)
return;
default:
return;
- };
+ }
}
/**
* @dnode: address of destination node
* @selector: a number used for deterministic link selection
* Consumes the buffer chain.
- * Returns 0 if success, otherwise: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE,-ENOBUF
+ * Return: 0 if success, otherwise: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE,-ENOBUF
*/
int tipc_node_xmit(struct net *net, struct sk_buff_head *list,
u32 dnode, int selector)
/**
* tipc_node_check_state - check and if necessary update node state
+ * @n: target tipc_node
* @skb: TIPC packet
* @bearer_id: identity of bearer delivering the packet
- * Returns true if state and msg are ok, otherwise false
+ * @xmitq: queue for messages to be xmited on
+ * Return: true if state and msg are ok, otherwise false
*/
static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
int bearer_id, struct sk_buff_head *xmitq)
/*
* net/tipc/socket.c: TIPC socket API
*
- * Copyright (c) 2001-2007, 2012-2017, Ericsson AB
+ * Copyright (c) 2001-2007, 2012-2019, Ericsson AB
* Copyright (c) 2004-2008, 2010-2013, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* @maxnagle: maximum size of msg which can be subject to nagle
* @portid: unique port identity in TIPC socket hash table
* @phdr: preformatted message header used when sending messages
- * #cong_links: list of congested links
+ * @cong_links: list of congested links
* @publications: list of publications for port
* @blocking_link: address of the congested link we are currently sleeping on
* @pub_count: total # of publications port has made during its lifetime
* @conn_timeout: the time we can wait for an unresponded setup request
+ * @probe_unacked: probe has not received ack yet
* @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
* @cong_link_cnt: number of congested links
* @snt_unacked: # messages sent by socket, and not yet acked by peer
+ * @snd_win: send window size
+ * @peer_caps: peer capabilities mask
* @rcv_unacked: # messages read by user, but not yet acked back to peer
+ * @rcv_win: receive window size
* @peer: 'connected' peer for dgram/rdm
* @node: hash table node
* @mc_method: cookie for use between socket and broadcast layer
* @rcu: rcu struct for tipc_sock
+ * @group: TIPC communications group
+ * @oneway: message count in one direction (FIXME)
+ * @nagle_start: current nagle value
+ * @snd_backlog: send backlog count
+ * @msg_acc: messages accepted; used in managing backlog and nagle
+ * @pkt_cnt: TIPC socket packet count
+ * @expect_ack: whether this TIPC socket is expecting an ack
+ * @nodelay: setsockopt() TIPC_NODELAY setting
+ * @group_is_open: TIPC socket group is fully open (FIXME)
*/
struct tipc_sock {
struct sock sk;
bool kern);
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);
+ struct tipc_service_range const *seq);
static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
- struct tipc_name_seq const *seq);
+ struct tipc_service_range 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);
/**
* tsk_advance_rx_queue - discard first buffer in socket receive queue
+ * @sk: network socket
*
* Caller must hold socket lock
*/
/**
* tsk_rej_rx_queue - reject all buffers in socket receive queue
+ * @sk: network socket
+ * @error: response error code
*
* Caller must hold socket lock
*/
* This routine creates additional data structures used by the TIPC socket,
* initializes them, and links them together.
*
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
*/
static int tipc_sk_create(struct net *net, struct socket *sock,
int protocol, int kern)
* are returned or discarded according to the "destination droppable" setting
* specified for the message by the sender.
*
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
*/
static int tipc_release(struct socket *sock)
{
}
/**
- * tipc_bind - associate or disassocate TIPC name(s) with a socket
+ * __tipc_bind - associate or disassocate TIPC name(s) with a socket
* @sock: socket structure
- * @uaddr: socket address describing name(s) and desired operation
- * @uaddr_len: size of socket address data structure
+ * @skaddr: socket address describing name(s) and desired operation
+ * @alen: size of socket address data structure
*
* Name and name sequence binding is indicated using a positive scope value;
* a negative scope value unbinds the specified name. Specifying no name
* (i.e. a socket address length of 0) unbinds all names from the socket.
*
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
*
* NOTE: This routine doesn't need to take the socket lock since it doesn't
* access any non-constant socket information.
*/
-static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
- int uaddr_len)
+static int __tipc_bind(struct socket *sock, struct sockaddr *skaddr, int alen)
{
- struct sock *sk = sock->sk;
- struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
- struct tipc_sock *tsk = tipc_sk(sk);
- int res = -EINVAL;
+ struct sockaddr_tipc *addr = (struct sockaddr_tipc *)skaddr;
+ struct tipc_sock *tsk = tipc_sk(sock->sk);
- lock_sock(sk);
- if (unlikely(!uaddr_len)) {
- 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;
- }
- if (addr->family != AF_TIPC) {
- res = -EAFNOSUPPORT;
- goto exit;
- }
+ if (unlikely(!alen))
+ return tipc_sk_withdraw(tsk, 0, NULL);
- if (addr->addrtype == TIPC_ADDR_NAME)
+ if (addr->addrtype == TIPC_SERVICE_ADDR)
addr->addr.nameseq.upper = addr->addr.nameseq.lower;
- else if (addr->addrtype != TIPC_ADDR_NAMESEQ) {
- res = -EAFNOSUPPORT;
- goto exit;
- }
- if ((addr->addr.nameseq.type < TIPC_RESERVED_TYPES) &&
- (addr->addr.nameseq.type != TIPC_TOP_SRV) &&
- (addr->addr.nameseq.type != TIPC_CFG_SRV)) {
- res = -EACCES;
- goto exit;
- }
+ if (tsk->group)
+ return -EACCES;
- res = (addr->scope >= 0) ?
- tipc_sk_publish(tsk, addr->scope, &addr->addr.nameseq) :
- tipc_sk_withdraw(tsk, -addr->scope, &addr->addr.nameseq);
-exit:
- release_sock(sk);
+ if (addr->scope >= 0)
+ return tipc_sk_publish(tsk, addr->scope, &addr->addr.nameseq);
+ else
+ return tipc_sk_withdraw(tsk, -addr->scope, &addr->addr.nameseq);
+}
+
+int tipc_sk_bind(struct socket *sock, struct sockaddr *skaddr, int alen)
+{
+ int res;
+
+ lock_sock(sock->sk);
+ res = __tipc_bind(sock, skaddr, alen);
+ release_sock(sock->sk);
return res;
}
+static int tipc_bind(struct socket *sock, struct sockaddr *skaddr, int alen)
+{
+ struct sockaddr_tipc *addr = (struct sockaddr_tipc *)skaddr;
+
+ if (alen) {
+ if (alen < sizeof(struct sockaddr_tipc))
+ return -EINVAL;
+ if (addr->family != AF_TIPC)
+ return -EAFNOSUPPORT;
+ if (addr->addrtype > TIPC_SERVICE_ADDR)
+ return -EAFNOSUPPORT;
+ if (addr->addr.nameseq.type < TIPC_RESERVED_TYPES) {
+ pr_warn_once("Can't bind to reserved service type %u\n",
+ addr->addr.nameseq.type);
+ return -EACCES;
+ }
+ }
+ return tipc_sk_bind(sock, skaddr, alen);
+}
+
/**
* tipc_getname - get port ID of socket or peer socket
* @sock: socket structure
* @uaddr: area for returned socket address
* @peer: 0 = own ID, 1 = current peer ID, 2 = current/former peer ID
*
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
*
* NOTE: This routine doesn't need to take the socket lock since it only
* accesses socket information that is unchanging (or which changes in
addr->addr.id.node = tipc_own_addr(sock_net(sk));
}
- addr->addrtype = TIPC_ADDR_ID;
+ addr->addrtype = TIPC_SOCKET_ADDR;
addr->family = AF_TIPC;
addr->scope = 0;
addr->addr.name.domain = 0;
* @sock: socket for which to calculate the poll bits
* @wait: ???
*
- * Returns pollmask value
+ * Return: pollmask value
*
* COMMENTARY:
* It appears that the usual socket locking mechanisms are not useful here
* @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
+ * Return: the number of bytes sent on success, or errno
*/
-static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq,
+static int tipc_sendmcast(struct socket *sock, struct tipc_service_range *seq,
struct msghdr *msg, size_t dlen, long timeout)
{
struct sock *sk = sock->sk;
/**
* tipc_send_group_msg - send a message to a member in the group
* @net: network namespace
+ * @tsk: tipc socket
* @m: message to send
* @mb: group member
* @dnode: destination node
* @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
+ * Return: 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)
* @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
+ * Return: 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)
* @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
+ * Return: 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)
* @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
+ * Return: 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)
/**
* tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets
+ * @net: the associated network namespace
* @arrvq: queue with arriving messages, to be cloned after destination lookup
* @inputq: queue with cloned messages, delivered to socket after dest lookup
*
* tipc_sk_conn_proto_rcv - receive a connection mng protocol message
* @tsk: receiving socket
* @skb: pointer to message buffer.
+ * @inputq: buffer list containing the buffers
+ * @xmitq: output message area
*/
static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
struct sk_buff_head *inputq,
* and for 'SYN' messages on SOCK_SEQPACKET and SOCK_STREAM connections.
* (Note: 'SYN+' is prohibited on SOCK_STREAM.)
*
- * Returns the number of bytes sent on success, or errno otherwise
+ * Return: the number of bytes sent on success, or errno otherwise
*/
static int tipc_sendmsg(struct socket *sock,
struct msghdr *m, size_t dsz)
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 tipc_service_range *seq;
struct sk_buff_head pkts;
u32 dport = 0, dnode = 0;
u32 type = 0, inst = 0;
if (grp) {
if (!dest)
return tipc_send_group_bcast(sock, m, dlen, timeout);
- if (dest->addrtype == TIPC_ADDR_NAME)
+ if (dest->addrtype == TIPC_SERVICE_ADDR)
return tipc_send_group_anycast(sock, m, dlen, timeout);
- if (dest->addrtype == TIPC_ADDR_ID)
+ if (dest->addrtype == TIPC_SOCKET_ADDR)
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 -EISCONN;
if (tsk->published)
return -EOPNOTSUPP;
- if (dest->addrtype == TIPC_ADDR_NAME) {
+ if (dest->addrtype == TIPC_SERVICE_ADDR) {
tsk->conn_type = dest->addr.name.name.type;
tsk->conn_instance = dest->addr.name.name.instance;
}
if (dest->addrtype == TIPC_ADDR_MCAST)
return tipc_sendmcast(sock, seq, m, dlen, timeout);
- if (dest->addrtype == TIPC_ADDR_NAME) {
+ if (dest->addrtype == TIPC_SERVICE_ADDR) {
type = dest->addr.name.name.type;
inst = dest->addr.name.name.instance;
dnode = dest->addr.name.domain;
dport = tipc_nametbl_translate(net, type, inst, &dnode);
if (unlikely(!dport && !dnode))
return -EHOSTUNREACH;
- } else if (dest->addrtype == TIPC_ADDR_ID) {
+ } else if (dest->addrtype == TIPC_SOCKET_ADDR) {
dnode = dest->addr.id.node;
} else {
return -EINVAL;
if (unlikely(rc))
return rc;
- if (dest->addrtype == TIPC_ADDR_NAME) {
+ if (dest->addrtype == TIPC_SERVICE_ADDR) {
msg_set_type(hdr, TIPC_NAMED_MSG);
msg_set_hdr_sz(hdr, NAMED_H_SIZE);
msg_set_nametype(hdr, type);
msg_set_lookup_scope(hdr, tipc_node2scope(dnode));
msg_set_destnode(hdr, dnode);
msg_set_destport(hdr, dport);
- } else { /* TIPC_ADDR_ID */
+ } else { /* TIPC_SOCKET_ADDR */
msg_set_type(hdr, TIPC_DIRECT_MSG);
msg_set_lookup_scope(hdr, 0);
msg_set_destnode(hdr, dnode);
*
* Used for SOCK_STREAM data.
*
- * Returns the number of bytes sent on success (or partial success),
+ * Return: the number of bytes sent on success (or partial success),
* or errno if no data sent
*/
static int tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz)
*
* Used for SOCK_SEQPACKET messages.
*
- * Returns the number of bytes sent on success, or errno otherwise
+ * Return: the number of bytes sent on success, or errno otherwise
*/
static int tipc_send_packet(struct socket *sock, struct msghdr *m, size_t dsz)
{
return;
srcaddr->sock.family = AF_TIPC;
- srcaddr->sock.addrtype = TIPC_ADDR_ID;
+ srcaddr->sock.addrtype = TIPC_SOCKET_ADDR;
srcaddr->sock.scope = 0;
srcaddr->sock.addr.id.ref = msg_origport(hdr);
srcaddr->sock.addr.id.node = msg_orignode(hdr);
/* 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.addrtype = TIPC_SERVICE_ADDR;
srcaddr->member.scope = 0;
srcaddr->member.addr.name.name.type = msg_nametype(hdr);
srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member;
*
* Note: Ancillary data is not captured if not requested by receiver.
*
- * Returns 0 if successful, otherwise errno
+ * Return: 0 if successful, otherwise errno
*/
static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb,
struct tipc_sock *tsk)
/**
* tipc_recvmsg - receive packet-oriented message
+ * @sock: network socket
* @m: descriptor for message info
* @buflen: length of user buffer area
* @flags: receive flags
* Used for SOCK_DGRAM, SOCK_RDM, and SOCK_SEQPACKET messages.
* If the complete message doesn't fit in user area, truncate it.
*
- * Returns size of returned message data, errno otherwise
+ * Return: size of returned message data, errno otherwise
*/
static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
size_t buflen, int flags)
/**
* tipc_recvstream - receive stream-oriented data
+ * @sock: network socket
* @m: descriptor for message info
* @buflen: total size of user buffer area
* @flags: receive flags
* Used for SOCK_STREAM messages only. If not enough data is available
* will optionally wait for more; never truncates data.
*
- * Returns size of returned message data, errno otherwise
+ * Return: size of returned message data, errno otherwise
*/
static int tipc_recvstream(struct socket *sock, struct msghdr *m,
size_t buflen, int flags)
* @tsk: TIPC socket
* @skb: pointer to message buffer.
* @xmitq: for Nagle ACK if any
- * Returns true if message should be added to receive queue, false otherwise
+ * Return: true if message should be added to receive queue, false otherwise
*/
static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb,
struct sk_buff_head *xmitq)
* TIPC_HIGH_IMPORTANCE (8 MB)
* TIPC_CRITICAL_IMPORTANCE (16 MB)
*
- * Returns overload limit according to corresponding message importance
+ * Return: overload limit according to corresponding message importance
*/
static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
{
* tipc_sk_filter_rcv - validate incoming message
* @sk: socket
* @skb: pointer to message.
+ * @xmitq: output message area (FIXME)
*
* Enqueues message on receive queue if acceptable; optionally handles
* disconnect indication for a connected socket.
*
* Called with socket lock already taken
- *
*/
static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
struct sk_buff_head *xmitq)
* @inputq: list of incoming buffers with potentially different destinations
* @sk: socket where the buffers should be enqueued
* @dport: port number for the socket
+ * @xmitq: output queue
*
* Caller must hold socket lock
*/
/**
* tipc_sk_rcv - handle a chain of incoming buffers
+ * @net: the associated network namespace
* @inputq: buffer list containing the buffers
* Consumes all buffers in list until inputq is empty
* Note: may be called in multiple threads referring to the same queue
* @destlen: size of socket address data structure
* @flags: file-related flags associated with socket
*
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
*/
static int tipc_connect(struct socket *sock, struct sockaddr *dest,
int destlen, int flags)
* @sock: socket structure
* @len: (unused)
*
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
*/
static int tipc_listen(struct socket *sock, int len)
{
* @sock: listening socket
* @new_sock: new socket that is to be connected
* @flags: file-related flags associated with socket
+ * @kern: caused by kernel or by userspace?
*
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
*/
static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
bool kern)
*
* Terminates connection (if necessary), then purges socket's receive queue.
*
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
*/
static int tipc_shutdown(struct socket *sock, int how)
{
}
static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
- struct tipc_name_seq const *seq)
+ struct tipc_service_range const *seq)
{
struct sock *sk = &tsk->sk;
struct net *net = sock_net(sk);
}
static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
- struct tipc_name_seq const *seq)
+ struct tipc_service_range const *seq)
{
struct net *net = sock_net(&tsk->sk);
struct publication *publ;
struct net *net = sock_net(&tsk->sk);
struct tipc_group *grp = tsk->group;
struct tipc_msg *hdr = &tsk->phdr;
- struct tipc_name_seq seq;
+ struct tipc_service_range seq;
int rc;
if (mreq->type < TIPC_RESERVED_TYPES)
{
struct net *net = sock_net(&tsk->sk);
struct tipc_group *grp = tsk->group;
- struct tipc_name_seq seq;
+ struct tipc_service_range seq;
int scope;
if (!grp)
* For stream sockets only, accepts and ignores all IPPROTO_TCP options
* (to ease compatibility).
*
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
*/
static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
sockptr_t ov, unsigned int ol)
* For stream sockets only, returns 0 length result for all IPPROTO_TCP options
* (to ease compatibility).
*
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
*/
static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
char __user *ov, int __user *ol)
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
- struct tipc_name_seq seq;
+ struct tipc_service_range seq;
int len, scope;
u32 value;
int res;
u32 onode = tipc_own_addr(sock_net(sock1->sk));
tsk1->peer.family = AF_TIPC;
- tsk1->peer.addrtype = TIPC_ADDR_ID;
+ tsk1->peer.addrtype = TIPC_SOCKET_ADDR;
tsk1->peer.scope = TIPC_NODE_SCOPE;
tsk1->peer.addr.id.ref = tsk2->portid;
tsk1->peer.addr.id.node = onode;
tsk2->peer.family = AF_TIPC;
- tsk2->peer.addrtype = TIPC_ADDR_ID;
+ tsk2->peer.addrtype = TIPC_SOCKET_ADDR;
tsk2->peer.scope = TIPC_NODE_SCOPE;
tsk2->peer.addr.id.ref = tsk1->portid;
tsk2->peer.addr.id.node = onode;
/**
* tipc_socket_init - initialize TIPC socket interface
*
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
*/
int tipc_socket_init(void)
{
/**
* tipc_sk_filtering - check if a socket should be traced
* @sk: the socket to be examined
- * @sysctl_tipc_sk_filter[]: the socket tuple for filtering,
- * (portid, sock type, name type, name lower, name upper)
*
- * Returns true if the socket meets the socket tuple data
+ * @sysctl_tipc_sk_filter is used as the socket tuple for filtering:
+ * (portid, sock type, name type, name lower, name upper)
+ *
+ * Return: true if the socket meets the socket tuple data
* (value 0 = 'any') or when there is no tuple set (all = 0),
* otherwise false
*/
* @sk: tipc sk to be checked
* @skb: tipc msg to be checked
*
- * Returns true if the socket rx queue allocation is > 90%, otherwise false
+ * Return: true if the socket rx queue allocation is > 90%, otherwise false
*/
bool tipc_sk_overlimit1(struct sock *sk, struct sk_buff *skb)
* @sk: tipc sk to be checked
* @skb: tipc msg to be checked
*
- * Returns true if the socket rx queue allocation is > 90%, otherwise false
+ * Return: true if the socket rx queue allocation is > 90%, otherwise false
*/
bool tipc_sk_overlimit2(struct sock *sk, struct sk_buff *skb)
u32 tipc_sock_get_portid(struct sock *sk);
bool tipc_sk_overlimit1(struct sock *sk, struct sk_buff *skb);
bool tipc_sk_overlimit2(struct sock *sk, struct sk_buff *skb);
-
+int tipc_sk_bind(struct socket *sock, struct sockaddr *skaddr, int alen);
int tsk_set_importance(struct sock *sk, int imp);
#endif
*
* Copyright (c) 2000-2017, Ericsson AB
* Copyright (c) 2005-2007, 2010-2013, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
}
/**
- * tipc_sub_check_overlap - test for subscription overlap with the
- * given values
+ * tipc_sub_check_overlap - test for subscription overlap with the given values
+ * @seq: tipc_name_seq to check
+ * @found_lower: lower value to test
+ * @found_upper: upper value to test
*
- * Returns 1 if there is overlap, otherwise 0.
+ * Return: 1 if there is overlap, otherwise 0.
*/
-int tipc_sub_check_overlap(struct tipc_name_seq *seq, u32 found_lower,
+int tipc_sub_check_overlap(struct tipc_service_range *seq, u32 found_lower,
u32 found_upper)
{
if (found_lower < seq->lower)
{
struct tipc_subscr *s = &sub->evt.s;
u32 filter = tipc_sub_read(s, filter);
- struct tipc_name_seq seq;
+ struct tipc_service_range seq;
seq.type = tipc_sub_read(s, seq.type);
seq.lower = tipc_sub_read(s, seq.lower);
*
* Copyright (c) 2003-2017, Ericsson AB
* Copyright (c) 2005-2007, 2012-2013, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
/**
* struct tipc_subscription - TIPC network topology subscription object
- * @subscriber: pointer to its subscriber
- * @seq: name sequence associated with subscription
+ * @kref: reference count for this subscription
+ * @net: network namespace associated with subscription
* @timer: timer governing subscription duration (optional)
- * @nameseq_list: adjacent subscriptions in name sequence's subscription list
+ * @service_list: adjacent subscriptions in name sequence's subscription list
* @sub_list: adjacent subscriptions in subscriber's subscription list
* @evt: template for events generated by subscription
+ * @conid: connection identifier of topology server
+ * @inactive: true if this subscription is inactive
+ * @lock: serialize up/down and timer events
*/
struct tipc_subscription {
struct kref kref;
struct tipc_event evt;
int conid;
bool inactive;
- spinlock_t lock; /* serialize up/down and timer events */
+ spinlock_t lock;
};
struct tipc_subscription *tipc_sub_subscribe(struct net *net,
int conid);
void tipc_sub_unsubscribe(struct tipc_subscription *sub);
-int tipc_sub_check_overlap(struct tipc_name_seq *seq, u32 found_lower,
- u32 found_upper);
+int tipc_sub_check_overlap(struct tipc_service_range *seq,
+ u32 found_lower, u32 found_upper);
void tipc_sub_report_overlap(struct tipc_subscription *sub,
u32 found_lower, u32 found_upper,
u32 event, u32 port, u32 node,
goto err;
saddr.family = AF_TIPC;
- saddr.addrtype = TIPC_ADDR_NAMESEQ;
- saddr.addr.nameseq.type = TIPC_TOP_SRV;
+ saddr.addrtype = TIPC_SERVICE_RANGE;
+ saddr.addr.nameseq.type = TIPC_TOP_SRV;
saddr.addr.nameseq.lower = TIPC_TOP_SRV;
saddr.addr.nameseq.upper = TIPC_TOP_SRV;
saddr.scope = TIPC_NODE_SCOPE;
- rc = kernel_bind(lsock, (struct sockaddr *)&saddr, sizeof(saddr));
+ rc = tipc_sk_bind(lsock, (struct sockaddr *)&saddr, sizeof(saddr));
if (rc < 0)
goto err;
rc = kernel_listen(lsock, 0);
#define CREATE_TRACE_POINTS
#include "trace.h"
-/**
+/*
* socket tuples for filtering in socket traces:
* (portid, sock type, name type, name lower, name upper)
*/
*
* This is the bearer level originating address used in neighbor discovery
* messages, and all fields should be in network byte order
+ *
+ * @proto: Ethernet protocol in use
+ * @port: port being used
+ * @ipv4: IPv4 address of neighbor
+ * @ipv6: IPv6 address of neighbor
*/
struct udp_media_addr {
__be16 proto;
* @ubsock: bearer associated socket
* @ifindex: local address scope
* @work: used to schedule deferred work on a bearer
+ * @rcast: associated udp_replicast container
*/
struct udp_bearer {
struct tipc_bearer __rcu *bearer;
if (err)
goto free;
- /**
+ /*
* The bcast media address port is used for all peers and the ip
* is used if it's a multicast address.
*/
/* fill prepend */
tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]),
record->len - prot->overhead_size,
- record_type, prot->version);
+ record_type);
return ret;
}
int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
{
- u16 nonce_size, tag_size, iv_size, rec_seq_size;
+ u16 nonce_size, tag_size, iv_size, rec_seq_size, salt_size;
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct tls_record_info *start_marker_record;
iv_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
iv = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->iv;
rec_seq_size = TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE;
+ salt_size = TLS_CIPHER_AES_GCM_128_SALT_SIZE;
rec_seq =
((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq;
break;
prot->tag_size = tag_size;
prot->overhead_size = prot->prepend_size + prot->tag_size;
prot->iv_size = iv_size;
+ prot->salt_size = salt_size;
ctx->tx.iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
GFP_KERNEL);
if (!ctx->tx.iv) {
struct crypto_aead *aead, char *aad,
char *iv, __be64 rcd_sn,
struct scatter_walk *in,
- struct scatter_walk *out, int *in_len)
+ struct scatter_walk *out, int *in_len,
+ struct tls_prot_info *prot)
{
unsigned char buf[TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE];
struct scatterlist sg_in[3];
len -= TLS_CIPHER_AES_GCM_128_IV_SIZE;
tls_make_aad(aad, len - TLS_CIPHER_AES_GCM_128_TAG_SIZE,
- (char *)&rcd_sn, sizeof(rcd_sn), buf[0],
- TLS_1_2_VERSION);
+ (char *)&rcd_sn, buf[0], prot);
memcpy(iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, buf + TLS_HEADER_SIZE,
TLS_CIPHER_AES_GCM_128_IV_SIZE);
static int tls_enc_records(struct aead_request *aead_req,
struct crypto_aead *aead, struct scatterlist *sg_in,
struct scatterlist *sg_out, char *aad, char *iv,
- u64 rcd_sn, int len)
+ u64 rcd_sn, int len, struct tls_prot_info *prot)
{
struct scatter_walk out, in;
int rc;
do {
rc = tls_enc_record(aead_req, aead, aad, iv,
- cpu_to_be64(rcd_sn), &in, &out, &len);
+ cpu_to_be64(rcd_sn), &in, &out, &len, prot);
rcd_sn++;
} while (rc == 0 && len);
payload_len, sync_size, dummy_buf);
if (tls_enc_records(aead_req, ctx->aead_send, sg_in, sg_out, aad, iv,
- rcd_sn, sync_size + payload_len) < 0)
+ rcd_sn, sync_size + payload_len,
+ &tls_ctx->prot_info) < 0)
goto free_nskb;
complete_skb(nskb, skb, tcp_payload_offset);
case TLS_CIPHER_AES_CCM_128:
optsize = sizeof(struct tls12_crypto_info_aes_ccm_128);
break;
+ case TLS_CIPHER_CHACHA20_POLY1305:
+ optsize = sizeof(struct tls12_crypto_info_chacha20_poly1305);
+ break;
default:
rc = -EINVAL;
goto err_crypto_info;
memcpy(&rec->iv_data[iv_offset], tls_ctx->tx.iv,
prot->iv_size + prot->salt_size);
- xor_iv_with_seq(prot->version, rec->iv_data, tls_ctx->tx.rec_seq);
+ xor_iv_with_seq(prot, rec->iv_data, tls_ctx->tx.rec_seq);
sge->offset += prot->prepend_size;
sge->length -= prot->prepend_size;
sg_chain(rec->sg_aead_out, 2, &msg_en->sg.data[i]);
tls_make_aad(rec->aad_space, msg_pl->sg.size + prot->tail_size,
- tls_ctx->tx.rec_seq, prot->rec_seq_size,
- record_type, prot->version);
+ tls_ctx->tx.rec_seq, record_type, prot);
tls_fill_prepend(tls_ctx,
page_address(sg_page(&msg_en->sg.data[i])) +
msg_en->sg.data[i].offset,
msg_pl->sg.size + prot->tail_size,
- record_type, prot->version);
+ record_type);
tls_ctx->pending_open_record_frags = false;
kfree(mem);
return err;
}
- if (prot->version == TLS_1_3_VERSION)
+ if (prot->version == TLS_1_3_VERSION ||
+ prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305)
memcpy(iv + iv_offset, tls_ctx->rx.iv,
crypto_aead_ivsize(ctx->aead_recv));
else
memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size);
- xor_iv_with_seq(prot->version, iv, tls_ctx->rx.rec_seq);
+ xor_iv_with_seq(prot, iv, tls_ctx->rx.rec_seq);
/* Prepare AAD */
tls_make_aad(aad, rxm->full_len - prot->overhead_size +
prot->tail_size,
- tls_ctx->rx.rec_seq, prot->rec_seq_size,
- ctx->control, prot->version);
+ tls_ctx->rx.rec_seq, ctx->control, prot);
/* Prepare sgin */
sg_init_table(sgin, n_sgin);
data_len = ((header[4] & 0xFF) | (header[3] << 8));
cipher_overhead = prot->tag_size;
- if (prot->version != TLS_1_3_VERSION)
+ if (prot->version != TLS_1_3_VERSION &&
+ prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305)
cipher_overhead += prot->iv_size;
if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead +
struct tls12_crypto_info_aes_gcm_128 *gcm_128_info;
struct tls12_crypto_info_aes_gcm_256 *gcm_256_info;
struct tls12_crypto_info_aes_ccm_128 *ccm_128_info;
+ struct tls12_crypto_info_chacha20_poly1305 *chacha20_poly1305_info;
struct tls_sw_context_tx *sw_ctx_tx = NULL;
struct tls_sw_context_rx *sw_ctx_rx = NULL;
struct cipher_context *cctx;
cipher_name = "ccm(aes)";
break;
}
+ case TLS_CIPHER_CHACHA20_POLY1305: {
+ chacha20_poly1305_info = (void *)crypto_info;
+ nonce_size = 0;
+ tag_size = TLS_CIPHER_CHACHA20_POLY1305_TAG_SIZE;
+ iv_size = TLS_CIPHER_CHACHA20_POLY1305_IV_SIZE;
+ iv = chacha20_poly1305_info->iv;
+ rec_seq_size = TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE;
+ rec_seq = chacha20_poly1305_info->rec_seq;
+ keysize = TLS_CIPHER_CHACHA20_POLY1305_KEY_SIZE;
+ key = chacha20_poly1305_info->key;
+ salt = chacha20_poly1305_info->salt;
+ salt_size = TLS_CIPHER_CHACHA20_POLY1305_SALT_SIZE;
+ cipher_name = "rfc7539(chacha20,poly1305)";
+ break;
+ }
default:
rc = -EINVAL;
goto free_priv;
break;
default:
- pr_err("Unknown ioctl %d\n", cmd);
- retval = -EINVAL;
+ retval = -ENOIOCTLCMD;
}
return retval;
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# WiMAX LAN device configuration
-#
-
-menuconfig WIMAX
- tristate "WiMAX Wireless Broadband support"
- depends on RFKILL || !RFKILL
- help
-
- Select to configure support for devices that provide
- wireless broadband connectivity using the WiMAX protocol
- (IEEE 802.16).
-
- Please note that most of these devices require signing up
- for a service plan with a provider.
-
- The different WiMAX drivers can be enabled in the menu entry
-
- Device Drivers > Network device support > WiMAX Wireless
- Broadband devices
-
- If unsure, it is safe to select M (module).
-
-config WIMAX_DEBUG_LEVEL
- int "WiMAX debug level"
- depends on WIMAX
- default 8
- help
-
- Select the maximum debug verbosity level to be compiled into
- the WiMAX stack code.
-
- By default, debug messages are disabled at runtime and can
- be selectively enabled for different parts of the code using
- the sysfs debug-levels file.
-
- If set at zero, this will compile out all the debug code.
-
- It is recommended that it is left at 8.
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0
-
-obj-$(CONFIG_WIMAX) += wimax.o
-
-wimax-y := \
- id-table.o \
- op-msg.o \
- op-reset.o \
- op-rfkill.o \
- op-state-get.o \
- stack.o
-
-wimax-$(CONFIG_DEBUG_FS) += debugfs.o
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Linux WiMAX Stack
- * Debug levels control file for the wimax module
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-#ifndef __debug_levels__h__
-#define __debug_levels__h__
-
-/* Maximum compile and run time debug level for all submodules */
-#define D_MODULENAME wimax
-#define D_MASTER CONFIG_WIMAX_DEBUG_LEVEL
-
-#include <linux/wimax/debug.h>
-
-/* List of all the enabled modules */
-enum d_module {
- D_SUBMODULE_DECLARE(debugfs),
- D_SUBMODULE_DECLARE(id_table),
- D_SUBMODULE_DECLARE(op_msg),
- D_SUBMODULE_DECLARE(op_reset),
- D_SUBMODULE_DECLARE(op_rfkill),
- D_SUBMODULE_DECLARE(op_state_get),
- D_SUBMODULE_DECLARE(stack),
-};
-
-#endif /* #ifndef __debug_levels__h__ */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Debugfs support
- *
- * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-#include <linux/debugfs.h>
-#include <linux/wimax.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE debugfs
-#include "debug-levels.h"
-
-void wimax_debugfs_add(struct wimax_dev *wimax_dev)
-{
- struct net_device *net_dev = wimax_dev->net_dev;
- struct dentry *dentry;
- char buf[128];
-
- snprintf(buf, sizeof(buf), "wimax:%s", net_dev->name);
- dentry = debugfs_create_dir(buf, NULL);
- wimax_dev->debugfs_dentry = dentry;
-
- d_level_register_debugfs("wimax_dl_", debugfs, dentry);
- d_level_register_debugfs("wimax_dl_", id_table, dentry);
- d_level_register_debugfs("wimax_dl_", op_msg, dentry);
- d_level_register_debugfs("wimax_dl_", op_reset, dentry);
- d_level_register_debugfs("wimax_dl_", op_rfkill, dentry);
- d_level_register_debugfs("wimax_dl_", op_state_get, dentry);
- d_level_register_debugfs("wimax_dl_", stack, dentry);
-}
-
-void wimax_debugfs_rm(struct wimax_dev *wimax_dev)
-{
- debugfs_remove_recursive(wimax_dev->debugfs_dentry);
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Mappping of generic netlink family IDs to net devices
- *
- * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * We assign a single generic netlink family ID to each device (to
- * simplify lookup).
- *
- * We need a way to map family ID to a wimax_dev pointer.
- *
- * The idea is to use a very simple lookup. Using a netlink attribute
- * with (for example) the interface name implies a heavier search over
- * all the network devices; seemed kind of a waste given that we know
- * we are looking for a WiMAX device and that most systems will have
- * just a single WiMAX adapter.
- *
- * We put all the WiMAX devices in the system in a linked list and
- * match the generic link family ID against the list.
- *
- * By using a linked list, the case of a single adapter in the system
- * becomes (almost) no overhead, while still working for many more. If
- * it ever goes beyond two, I'll be surprised.
- */
-#include <linux/device.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-#include <linux/list.h>
-#include <linux/wimax.h>
-#include "wimax-internal.h"
-
-
-#define D_SUBMODULE id_table
-#include "debug-levels.h"
-
-
-static DEFINE_SPINLOCK(wimax_id_table_lock);
-static struct list_head wimax_id_table = LIST_HEAD_INIT(wimax_id_table);
-
-
-/*
- * wimax_id_table_add - add a gennetlink familiy ID / wimax_dev mapping
- *
- * @wimax_dev: WiMAX device descriptor to associate to the Generic
- * Netlink family ID.
- *
- * Look for an empty spot in the ID table; if none found, double the
- * table's size and get the first spot.
- */
-void wimax_id_table_add(struct wimax_dev *wimax_dev)
-{
- d_fnstart(3, NULL, "(wimax_dev %p)\n", wimax_dev);
- spin_lock(&wimax_id_table_lock);
- list_add(&wimax_dev->id_table_node, &wimax_id_table);
- spin_unlock(&wimax_id_table_lock);
- d_fnend(3, NULL, "(wimax_dev %p)\n", wimax_dev);
-}
-
-
-/*
- * wimax_get_netdev_by_info - lookup a wimax_dev from the gennetlink info
- *
- * The generic netlink family ID has been filled out in the
- * nlmsghdr->nlmsg_type field, so we pull it from there, look it up in
- * the mapping table and reference the wimax_dev.
- *
- * When done, the reference should be dropped with
- * 'dev_put(wimax_dev->net_dev)'.
- */
-struct wimax_dev *wimax_dev_get_by_genl_info(
- struct genl_info *info, int ifindex)
-{
- struct wimax_dev *wimax_dev = NULL;
-
- d_fnstart(3, NULL, "(info %p ifindex %d)\n", info, ifindex);
- spin_lock(&wimax_id_table_lock);
- list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) {
- if (wimax_dev->net_dev->ifindex == ifindex) {
- dev_hold(wimax_dev->net_dev);
- goto found;
- }
- }
- wimax_dev = NULL;
- d_printf(1, NULL, "wimax: no devices found with ifindex %d\n",
- ifindex);
-found:
- spin_unlock(&wimax_id_table_lock);
- d_fnend(3, NULL, "(info %p ifindex %d) = %p\n",
- info, ifindex, wimax_dev);
- return wimax_dev;
-}
-
-
-/*
- * wimax_id_table_rm - Remove a gennetlink familiy ID / wimax_dev mapping
- *
- * @id: family ID to remove from the table
- */
-void wimax_id_table_rm(struct wimax_dev *wimax_dev)
-{
- spin_lock(&wimax_id_table_lock);
- list_del_init(&wimax_dev->id_table_node);
- spin_unlock(&wimax_id_table_lock);
-}
-
-
-/*
- * Release the gennetlink family id / mapping table
- *
- * On debug, verify that the table is empty upon removal. We want the
- * code always compiled, to ensure it doesn't bit rot. It will be
- * compiled out if CONFIG_BUG is disabled.
- */
-void wimax_id_table_release(void)
-{
- struct wimax_dev *wimax_dev;
-
-#ifndef CONFIG_BUG
- return;
-#endif
- spin_lock(&wimax_id_table_lock);
- list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) {
- pr_err("BUG: %s wimax_dev %p ifindex %d not cleared\n",
- __func__, wimax_dev, wimax_dev->net_dev->ifindex);
- WARN_ON(1);
- }
- spin_unlock(&wimax_id_table_lock);
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Generic messaging interface between userspace and driver/device
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements a direct communication channel between user space and
- * the driver/device, by which free form messages can be sent back and
- * forth.
- *
- * This is intended for device-specific features, vendor quirks, etc.
- *
- * See include/net/wimax.h
- *
- * GENERIC NETLINK ENCODING AND CAPACITY
- *
- * A destination "pipe name" is added to each message; it is up to the
- * drivers to assign or use those names (if using them at all).
- *
- * Messages are encoded as a binary netlink attribute using nla_put()
- * using type NLA_UNSPEC (as some versions of libnl still in
- * deployment don't yet understand NLA_BINARY).
- *
- * The maximum capacity of this transport is PAGESIZE per message (so
- * the actual payload will be bit smaller depending on the
- * netlink/generic netlink attributes and headers).
- *
- * RECEPTION OF MESSAGES
- *
- * When a message is received from user space, it is passed verbatim
- * to the driver calling wimax_dev->op_msg_from_user(). The return
- * value from this function is passed back to user space as an ack
- * over the generic netlink protocol.
- *
- * The stack doesn't do any processing or interpretation of these
- * messages.
- *
- * SENDING MESSAGES
- *
- * Messages can be sent with wimax_msg().
- *
- * If the message delivery needs to happen on a different context to
- * that of its creation, wimax_msg_alloc() can be used to get a
- * pointer to the message that can be delivered later on with
- * wimax_msg_send().
- *
- * ROADMAP
- *
- * wimax_gnl_doit_msg_from_user() Process a message from user space
- * wimax_dev_get_by_genl_info()
- * wimax_dev->op_msg_from_user() Delivery of message to the driver
- *
- * wimax_msg() Send a message to user space
- * wimax_msg_alloc()
- * wimax_msg_send()
- */
-#include <linux/device.h>
-#include <linux/slab.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include <linux/export.h>
-#include "wimax-internal.h"
-
-
-#define D_SUBMODULE op_msg
-#include "debug-levels.h"
-
-
-/**
- * wimax_msg_alloc - Create a new skb for sending a message to userspace
- *
- * @wimax_dev: WiMAX device descriptor
- * @pipe_name: "named pipe" the message will be sent to
- * @msg: pointer to the message data to send
- * @size: size of the message to send (in bytes), including the header.
- * @gfp_flags: flags for memory allocation.
- *
- * Returns: %0 if ok, negative errno code on error
- *
- * Description:
- *
- * Allocates an skb that will contain the message to send to user
- * space over the messaging pipe and initializes it, copying the
- * payload.
- *
- * Once this call is done, you can deliver it with
- * wimax_msg_send().
- *
- * IMPORTANT:
- *
- * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as
- * wimax_msg_send() depends on skb->data being placed at the
- * beginning of the user message.
- *
- * Unlike other WiMAX stack calls, this call can be used way early,
- * even before wimax_dev_add() is called, as long as the
- * wimax_dev->net_dev pointer is set to point to a proper
- * net_dev. This is so that drivers can use it early in case they need
- * to send stuff around or communicate with user space.
- */
-struct sk_buff *wimax_msg_alloc(struct wimax_dev *wimax_dev,
- const char *pipe_name,
- const void *msg, size_t size,
- gfp_t gfp_flags)
-{
- int result;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- size_t msg_size;
- void *genl_msg;
- struct sk_buff *skb;
-
- msg_size = nla_total_size(size)
- + nla_total_size(sizeof(u32))
- + (pipe_name ? nla_total_size(strlen(pipe_name)) : 0);
- result = -ENOMEM;
- skb = genlmsg_new(msg_size, gfp_flags);
- if (skb == NULL)
- goto error_new;
- genl_msg = genlmsg_put(skb, 0, 0, &wimax_gnl_family,
- 0, WIMAX_GNL_OP_MSG_TO_USER);
- if (genl_msg == NULL) {
- dev_err(dev, "no memory to create generic netlink message\n");
- goto error_genlmsg_put;
- }
- result = nla_put_u32(skb, WIMAX_GNL_MSG_IFIDX,
- wimax_dev->net_dev->ifindex);
- if (result < 0) {
- dev_err(dev, "no memory to add ifindex attribute\n");
- goto error_nla_put;
- }
- if (pipe_name) {
- result = nla_put_string(skb, WIMAX_GNL_MSG_PIPE_NAME,
- pipe_name);
- if (result < 0) {
- dev_err(dev, "no memory to add pipe_name attribute\n");
- goto error_nla_put;
- }
- }
- result = nla_put(skb, WIMAX_GNL_MSG_DATA, size, msg);
- if (result < 0) {
- dev_err(dev, "no memory to add payload (msg %p size %zu) in "
- "attribute: %d\n", msg, size, result);
- goto error_nla_put;
- }
- genlmsg_end(skb, genl_msg);
- return skb;
-
-error_nla_put:
-error_genlmsg_put:
-error_new:
- nlmsg_free(skb);
- return ERR_PTR(result);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_alloc);
-
-
-/**
- * wimax_msg_data_len - Return a pointer and size of a message's payload
- *
- * @msg: Pointer to a message created with wimax_msg_alloc()
- * @size: Pointer to where to store the message's size
- *
- * Returns the pointer to the message data.
- */
-const void *wimax_msg_data_len(struct sk_buff *msg, size_t *size)
-{
- struct nlmsghdr *nlh = (void *) msg->head;
- struct nlattr *nla;
-
- nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
- WIMAX_GNL_MSG_DATA);
- if (nla == NULL) {
- pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
- return NULL;
- }
- *size = nla_len(nla);
- return nla_data(nla);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_data_len);
-
-
-/**
- * wimax_msg_data - Return a pointer to a message's payload
- *
- * @msg: Pointer to a message created with wimax_msg_alloc()
- */
-const void *wimax_msg_data(struct sk_buff *msg)
-{
- struct nlmsghdr *nlh = (void *) msg->head;
- struct nlattr *nla;
-
- nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
- WIMAX_GNL_MSG_DATA);
- if (nla == NULL) {
- pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
- return NULL;
- }
- return nla_data(nla);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_data);
-
-
-/**
- * wimax_msg_len - Return a message's payload length
- *
- * @msg: Pointer to a message created with wimax_msg_alloc()
- */
-ssize_t wimax_msg_len(struct sk_buff *msg)
-{
- struct nlmsghdr *nlh = (void *) msg->head;
- struct nlattr *nla;
-
- nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
- WIMAX_GNL_MSG_DATA);
- if (nla == NULL) {
- pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
- return -EINVAL;
- }
- return nla_len(nla);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_len);
-
-
-/**
- * wimax_msg_send - Send a pre-allocated message to user space
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @skb: &struct sk_buff returned by wimax_msg_alloc(). Note the
- * ownership of @skb is transferred to this function.
- *
- * Returns: 0 if ok, < 0 errno code on error
- *
- * Description:
- *
- * Sends a free-form message that was preallocated with
- * wimax_msg_alloc() and filled up.
- *
- * Assumes that once you pass an skb to this function for sending, it
- * owns it and will release it when done (on success).
- *
- * IMPORTANT:
- *
- * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as
- * wimax_msg_send() depends on skb->data being placed at the
- * beginning of the user message.
- *
- * Unlike other WiMAX stack calls, this call can be used way early,
- * even before wimax_dev_add() is called, as long as the
- * wimax_dev->net_dev pointer is set to point to a proper
- * net_dev. This is so that drivers can use it early in case they need
- * to send stuff around or communicate with user space.
- */
-int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb)
-{
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- void *msg = skb->data;
- size_t size = skb->len;
- might_sleep();
-
- d_printf(1, dev, "CTX: wimax msg, %zu bytes\n", size);
- d_dump(2, dev, msg, size);
- genlmsg_multicast(&wimax_gnl_family, skb, 0, 0, GFP_KERNEL);
- d_printf(1, dev, "CTX: genl multicast done\n");
- return 0;
-}
-EXPORT_SYMBOL_GPL(wimax_msg_send);
-
-
-/**
- * wimax_msg - Send a message to user space
- *
- * @wimax_dev: WiMAX device descriptor (properly referenced)
- * @pipe_name: "named pipe" the message will be sent to
- * @buf: pointer to the message to send.
- * @size: size of the buffer pointed to by @buf (in bytes).
- * @gfp_flags: flags for memory allocation.
- *
- * Returns: %0 if ok, negative errno code on error.
- *
- * Description:
- *
- * Sends a free-form message to user space on the device @wimax_dev.
- *
- * NOTES:
- *
- * Once the @skb is given to this function, who will own it and will
- * release it when done (unless it returns error).
- */
-int wimax_msg(struct wimax_dev *wimax_dev, const char *pipe_name,
- const void *buf, size_t size, gfp_t gfp_flags)
-{
- int result = -ENOMEM;
- struct sk_buff *skb;
-
- skb = wimax_msg_alloc(wimax_dev, pipe_name, buf, size, gfp_flags);
- if (IS_ERR(skb))
- result = PTR_ERR(skb);
- else
- result = wimax_msg_send(wimax_dev, skb);
- return result;
-}
-EXPORT_SYMBOL_GPL(wimax_msg);
-
-/*
- * Relays a message from user space to the driver
- *
- * The skb is passed to the driver-specific function with the netlink
- * and generic netlink headers already stripped.
- *
- * This call will block while handling/relaying the message.
- */
-int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info)
-{
- int result, ifindex;
- struct wimax_dev *wimax_dev;
- struct device *dev;
- struct nlmsghdr *nlh = info->nlhdr;
- char *pipe_name;
- void *msg_buf;
- size_t msg_len;
-
- might_sleep();
- d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
- result = -ENODEV;
- if (info->attrs[WIMAX_GNL_MSG_IFIDX] == NULL) {
- pr_err("WIMAX_GNL_MSG_FROM_USER: can't find IFIDX attribute\n");
- goto error_no_wimax_dev;
- }
- ifindex = nla_get_u32(info->attrs[WIMAX_GNL_MSG_IFIDX]);
- wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
- if (wimax_dev == NULL)
- goto error_no_wimax_dev;
- dev = wimax_dev_to_dev(wimax_dev);
-
- /* Unpack arguments */
- result = -EINVAL;
- if (info->attrs[WIMAX_GNL_MSG_DATA] == NULL) {
- dev_err(dev, "WIMAX_GNL_MSG_FROM_USER: can't find MSG_DATA "
- "attribute\n");
- goto error_no_data;
- }
- msg_buf = nla_data(info->attrs[WIMAX_GNL_MSG_DATA]);
- msg_len = nla_len(info->attrs[WIMAX_GNL_MSG_DATA]);
-
- if (info->attrs[WIMAX_GNL_MSG_PIPE_NAME] == NULL)
- pipe_name = NULL;
- else {
- struct nlattr *attr = info->attrs[WIMAX_GNL_MSG_PIPE_NAME];
- size_t attr_len = nla_len(attr);
- /* libnl-1.1 does not yet support NLA_NUL_STRING */
- result = -ENOMEM;
- pipe_name = kstrndup(nla_data(attr), attr_len + 1, GFP_KERNEL);
- if (pipe_name == NULL)
- goto error_alloc;
- pipe_name[attr_len] = 0;
- }
- mutex_lock(&wimax_dev->mutex);
- result = wimax_dev_is_ready(wimax_dev);
- if (result == -ENOMEDIUM)
- result = 0;
- if (result < 0)
- goto error_not_ready;
- result = -ENOSYS;
- if (wimax_dev->op_msg_from_user == NULL)
- goto error_noop;
-
- d_printf(1, dev,
- "CRX: nlmsghdr len %u type %u flags 0x%04x seq 0x%x pid %u\n",
- nlh->nlmsg_len, nlh->nlmsg_type, nlh->nlmsg_flags,
- nlh->nlmsg_seq, nlh->nlmsg_pid);
- d_printf(1, dev, "CRX: wimax message %zu bytes\n", msg_len);
- d_dump(2, dev, msg_buf, msg_len);
-
- result = wimax_dev->op_msg_from_user(wimax_dev, pipe_name,
- msg_buf, msg_len, info);
-error_noop:
-error_not_ready:
- mutex_unlock(&wimax_dev->mutex);
-error_alloc:
- kfree(pipe_name);
-error_no_data:
- dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
- d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
- return result;
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Implement and export a method for resetting a WiMAX device
- *
- * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements a simple synchronous call to reset a WiMAX device.
- *
- * Resets aim at being warm, keeping the device handles active;
- * however, when that fails, it falls back to a cold reset (that will
- * disconnect and reconnect the device).
- */
-
-#include <net/wimax.h>
-#include <net/genetlink.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include <linux/export.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE op_reset
-#include "debug-levels.h"
-
-
-/**
- * wimax_reset - Reset a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * Returns:
- *
- * %0 if ok and a warm reset was done (the device still exists in
- * the system).
- *
- * -%ENODEV if a cold/bus reset had to be done (device has
- * disconnected and reconnected, so current handle is not valid
- * any more).
- *
- * -%EINVAL if the device is not even registered.
- *
- * Any other negative error code shall be considered as
- * non-recoverable.
- *
- * Description:
- *
- * Called when wanting to reset the device for any reason. Device is
- * taken back to power on status.
- *
- * This call blocks; on successful return, the device has completed the
- * reset process and is ready to operate.
- */
-int wimax_reset(struct wimax_dev *wimax_dev)
-{
- int result = -EINVAL;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- enum wimax_st state;
-
- might_sleep();
- d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
- mutex_lock(&wimax_dev->mutex);
- dev_hold(wimax_dev->net_dev);
- state = wimax_dev->state;
- mutex_unlock(&wimax_dev->mutex);
-
- if (state >= WIMAX_ST_DOWN) {
- mutex_lock(&wimax_dev->mutex_reset);
- result = wimax_dev->op_reset(wimax_dev);
- mutex_unlock(&wimax_dev->mutex_reset);
- }
- dev_put(wimax_dev->net_dev);
-
- d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
- return result;
-}
-EXPORT_SYMBOL(wimax_reset);
-
-
-/*
- * Exporting to user space over generic netlink
- *
- * Parse the reset command from user space, return error code.
- *
- * No attributes.
- */
-int wimax_gnl_doit_reset(struct sk_buff *skb, struct genl_info *info)
-{
- int result, ifindex;
- struct wimax_dev *wimax_dev;
-
- d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
- result = -ENODEV;
- if (info->attrs[WIMAX_GNL_RESET_IFIDX] == NULL) {
- pr_err("WIMAX_GNL_OP_RFKILL: can't find IFIDX attribute\n");
- goto error_no_wimax_dev;
- }
- ifindex = nla_get_u32(info->attrs[WIMAX_GNL_RESET_IFIDX]);
- wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
- if (wimax_dev == NULL)
- goto error_no_wimax_dev;
- /* Execute the operation and send the result back to user space */
- result = wimax_reset(wimax_dev);
- dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
- d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
- return result;
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * RF-kill framework integration
- *
- * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This integrates into the Linux Kernel rfkill susbystem so that the
- * drivers just have to do the bare minimal work, which is providing a
- * method to set the software RF-Kill switch and to report changes in
- * the software and hardware switch status.
- *
- * A non-polled generic rfkill device is embedded into the WiMAX
- * subsystem's representation of a device.
- *
- * FIXME: Need polled support? Let drivers provide a poll routine
- * and hand it to rfkill ops then?
- *
- * All device drivers have to do is after wimax_dev_init(), call
- * wimax_report_rfkill_hw() and wimax_report_rfkill_sw() to update
- * initial state and then every time it changes. See wimax.h:struct
- * wimax_dev for more information.
- *
- * ROADMAP
- *
- * wimax_gnl_doit_rfkill() User space calling wimax_rfkill()
- * wimax_rfkill() Kernel calling wimax_rfkill()
- * __wimax_rf_toggle_radio()
- *
- * wimax_rfkill_set_radio_block() RF-Kill subsystem calling
- * __wimax_rf_toggle_radio()
- *
- * __wimax_rf_toggle_radio()
- * wimax_dev->op_rfkill_sw_toggle() Driver backend
- * __wimax_state_change()
- *
- * wimax_report_rfkill_sw() Driver reports state change
- * __wimax_state_change()
- *
- * wimax_report_rfkill_hw() Driver reports state change
- * __wimax_state_change()
- *
- * wimax_rfkill_add() Initialize/shutdown rfkill support
- * wimax_rfkill_rm() [called by wimax_dev_add/rm()]
- */
-
-#include <net/wimax.h>
-#include <net/genetlink.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include <linux/rfkill.h>
-#include <linux/export.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE op_rfkill
-#include "debug-levels.h"
-
-/**
- * wimax_report_rfkill_hw - Reports changes in the hardware RF switch
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @state: New state of the RF Kill switch. %WIMAX_RF_ON radio on,
- * %WIMAX_RF_OFF radio off.
- *
- * When the device detects a change in the state of thehardware RF
- * switch, it must call this function to let the WiMAX kernel stack
- * know that the state has changed so it can be properly propagated.
- *
- * The WiMAX stack caches the state (the driver doesn't need to). As
- * well, as the change is propagated it will come back as a request to
- * change the software state to mirror the hardware state.
- *
- * If the device doesn't have a hardware kill switch, just report
- * it on initialization as always on (%WIMAX_RF_ON, radio on).
- */
-void wimax_report_rfkill_hw(struct wimax_dev *wimax_dev,
- enum wimax_rf_state state)
-{
- int result;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- enum wimax_st wimax_state;
-
- d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
- BUG_ON(state == WIMAX_RF_QUERY);
- BUG_ON(state != WIMAX_RF_ON && state != WIMAX_RF_OFF);
-
- mutex_lock(&wimax_dev->mutex);
- result = wimax_dev_is_ready(wimax_dev);
- if (result < 0)
- goto error_not_ready;
-
- if (state != wimax_dev->rf_hw) {
- wimax_dev->rf_hw = state;
- if (wimax_dev->rf_hw == WIMAX_RF_ON &&
- wimax_dev->rf_sw == WIMAX_RF_ON)
- wimax_state = WIMAX_ST_READY;
- else
- wimax_state = WIMAX_ST_RADIO_OFF;
-
- result = rfkill_set_hw_state(wimax_dev->rfkill,
- state == WIMAX_RF_OFF);
-
- __wimax_state_change(wimax_dev, wimax_state);
- }
-error_not_ready:
- mutex_unlock(&wimax_dev->mutex);
- d_fnend(3, dev, "(wimax_dev %p state %u) = void [%d]\n",
- wimax_dev, state, result);
-}
-EXPORT_SYMBOL_GPL(wimax_report_rfkill_hw);
-
-
-/**
- * wimax_report_rfkill_sw - Reports changes in the software RF switch
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @state: New state of the RF kill switch. %WIMAX_RF_ON radio on,
- * %WIMAX_RF_OFF radio off.
- *
- * Reports changes in the software RF switch state to the WiMAX stack.
- *
- * The main use is during initialization, so the driver can query the
- * device for its current software radio kill switch state and feed it
- * to the system.
- *
- * On the side, the device does not change the software state by
- * itself. In practice, this can happen, as the device might decide to
- * switch (in software) the radio off for different reasons.
- */
-void wimax_report_rfkill_sw(struct wimax_dev *wimax_dev,
- enum wimax_rf_state state)
-{
- int result;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- enum wimax_st wimax_state;
-
- d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
- BUG_ON(state == WIMAX_RF_QUERY);
- BUG_ON(state != WIMAX_RF_ON && state != WIMAX_RF_OFF);
-
- mutex_lock(&wimax_dev->mutex);
- result = wimax_dev_is_ready(wimax_dev);
- if (result < 0)
- goto error_not_ready;
-
- if (state != wimax_dev->rf_sw) {
- wimax_dev->rf_sw = state;
- if (wimax_dev->rf_hw == WIMAX_RF_ON &&
- wimax_dev->rf_sw == WIMAX_RF_ON)
- wimax_state = WIMAX_ST_READY;
- else
- wimax_state = WIMAX_ST_RADIO_OFF;
- __wimax_state_change(wimax_dev, wimax_state);
- rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF);
- }
-error_not_ready:
- mutex_unlock(&wimax_dev->mutex);
- d_fnend(3, dev, "(wimax_dev %p state %u) = void [%d]\n",
- wimax_dev, state, result);
-}
-EXPORT_SYMBOL_GPL(wimax_report_rfkill_sw);
-
-
-/*
- * Callback for the RF Kill toggle operation
- *
- * This function is called by:
- *
- * - The rfkill subsystem when the RF-Kill key is pressed in the
- * hardware and the driver notifies through
- * wimax_report_rfkill_hw(). The rfkill subsystem ends up calling back
- * here so the software RF Kill switch state is changed to reflect
- * the hardware switch state.
- *
- * - When the user sets the state through sysfs' rfkill/state file
- *
- * - When the user calls wimax_rfkill().
- *
- * This call blocks!
- *
- * WARNING! When we call rfkill_unregister(), this will be called with
- * state 0!
- *
- * WARNING: wimax_dev must be locked
- */
-static
-int __wimax_rf_toggle_radio(struct wimax_dev *wimax_dev,
- enum wimax_rf_state state)
-{
- int result = 0;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- enum wimax_st wimax_state;
-
- might_sleep();
- d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
- if (wimax_dev->rf_sw == state)
- goto out_no_change;
- if (wimax_dev->op_rfkill_sw_toggle != NULL)
- result = wimax_dev->op_rfkill_sw_toggle(wimax_dev, state);
- else if (state == WIMAX_RF_OFF) /* No op? can't turn off */
- result = -ENXIO;
- else /* No op? can turn on */
- result = 0; /* should never happen tho */
- if (result >= 0) {
- result = 0;
- wimax_dev->rf_sw = state;
- wimax_state = state == WIMAX_RF_ON ?
- WIMAX_ST_READY : WIMAX_ST_RADIO_OFF;
- __wimax_state_change(wimax_dev, wimax_state);
- }
-out_no_change:
- d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n",
- wimax_dev, state, result);
- return result;
-}
-
-
-/*
- * Translate from rfkill state to wimax state
- *
- * NOTE: Special state handling rules here
- *
- * Just pretend the call didn't happen if we are in a state where
- * we know for sure it cannot be handled (WIMAX_ST_DOWN or
- * __WIMAX_ST_QUIESCING). rfkill() needs it to register and
- * unregister, as it will run this path.
- *
- * NOTE: This call will block until the operation is completed.
- */
-static int wimax_rfkill_set_radio_block(void *data, bool blocked)
-{
- int result;
- struct wimax_dev *wimax_dev = data;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- enum wimax_rf_state rf_state;
-
- d_fnstart(3, dev, "(wimax_dev %p blocked %u)\n", wimax_dev, blocked);
- rf_state = WIMAX_RF_ON;
- if (blocked)
- rf_state = WIMAX_RF_OFF;
- mutex_lock(&wimax_dev->mutex);
- if (wimax_dev->state <= __WIMAX_ST_QUIESCING)
- result = 0;
- else
- result = __wimax_rf_toggle_radio(wimax_dev, rf_state);
- mutex_unlock(&wimax_dev->mutex);
- d_fnend(3, dev, "(wimax_dev %p blocked %u) = %d\n",
- wimax_dev, blocked, result);
- return result;
-}
-
-static const struct rfkill_ops wimax_rfkill_ops = {
- .set_block = wimax_rfkill_set_radio_block,
-};
-
-/**
- * wimax_rfkill - Set the software RF switch state for a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @state: New RF state.
- *
- * Returns:
- *
- * >= 0 toggle state if ok, < 0 errno code on error. The toggle state
- * is returned as a bitmap, bit 0 being the hardware RF state, bit 1
- * the software RF state.
- *
- * 0 means disabled (%WIMAX_RF_ON, radio on), 1 means enabled radio
- * off (%WIMAX_RF_OFF).
- *
- * Description:
- *
- * Called by the user when he wants to request the WiMAX radio to be
- * switched on (%WIMAX_RF_ON) or off (%WIMAX_RF_OFF). With
- * %WIMAX_RF_QUERY, just the current state is returned.
- *
- * NOTE:
- *
- * This call will block until the operation is complete.
- */
-int wimax_rfkill(struct wimax_dev *wimax_dev, enum wimax_rf_state state)
-{
- int result;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
-
- d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
- mutex_lock(&wimax_dev->mutex);
- result = wimax_dev_is_ready(wimax_dev);
- if (result < 0) {
- /* While initializing, < 1.4.3 wimax-tools versions use
- * this call to check if the device is a valid WiMAX
- * device; so we allow it to proceed always,
- * considering the radios are all off. */
- if (result == -ENOMEDIUM && state == WIMAX_RF_QUERY)
- result = WIMAX_RF_OFF << 1 | WIMAX_RF_OFF;
- goto error_not_ready;
- }
- switch (state) {
- case WIMAX_RF_ON:
- case WIMAX_RF_OFF:
- result = __wimax_rf_toggle_radio(wimax_dev, state);
- if (result < 0)
- goto error;
- rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF);
- break;
- case WIMAX_RF_QUERY:
- break;
- default:
- result = -EINVAL;
- goto error;
- }
- result = wimax_dev->rf_sw << 1 | wimax_dev->rf_hw;
-error:
-error_not_ready:
- mutex_unlock(&wimax_dev->mutex);
- d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n",
- wimax_dev, state, result);
- return result;
-}
-EXPORT_SYMBOL(wimax_rfkill);
-
-
-/*
- * Register a new WiMAX device's RF Kill support
- *
- * WARNING: wimax_dev->mutex must be unlocked
- */
-int wimax_rfkill_add(struct wimax_dev *wimax_dev)
-{
- int result;
- struct rfkill *rfkill;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
-
- d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
- /* Initialize RF Kill */
- result = -ENOMEM;
- rfkill = rfkill_alloc(wimax_dev->name, dev, RFKILL_TYPE_WIMAX,
- &wimax_rfkill_ops, wimax_dev);
- if (rfkill == NULL)
- goto error_rfkill_allocate;
-
- d_printf(1, dev, "rfkill %p\n", rfkill);
-
- wimax_dev->rfkill = rfkill;
-
- rfkill_init_sw_state(rfkill, 1);
- result = rfkill_register(wimax_dev->rfkill);
- if (result < 0)
- goto error_rfkill_register;
-
- /* If there is no SW toggle op, SW RFKill is always on */
- if (wimax_dev->op_rfkill_sw_toggle == NULL)
- wimax_dev->rf_sw = WIMAX_RF_ON;
-
- d_fnend(3, dev, "(wimax_dev %p) = 0\n", wimax_dev);
- return 0;
-
-error_rfkill_register:
- rfkill_destroy(wimax_dev->rfkill);
-error_rfkill_allocate:
- d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
- return result;
-}
-
-
-/*
- * Deregister a WiMAX device's RF Kill support
- *
- * Ick, we can't call rfkill_free() after rfkill_unregister()...oh
- * well.
- *
- * WARNING: wimax_dev->mutex must be unlocked
- */
-void wimax_rfkill_rm(struct wimax_dev *wimax_dev)
-{
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
- rfkill_unregister(wimax_dev->rfkill);
- rfkill_destroy(wimax_dev->rfkill);
- d_fnend(3, dev, "(wimax_dev %p)\n", wimax_dev);
-}
-
-
-/*
- * Exporting to user space over generic netlink
- *
- * Parse the rfkill command from user space, return a combination
- * value that describe the states of the different toggles.
- *
- * Only one attribute: the new state requested (on, off or no change,
- * just query).
- */
-
-int wimax_gnl_doit_rfkill(struct sk_buff *skb, struct genl_info *info)
-{
- int result, ifindex;
- struct wimax_dev *wimax_dev;
- struct device *dev;
- enum wimax_rf_state new_state;
-
- d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
- result = -ENODEV;
- if (info->attrs[WIMAX_GNL_RFKILL_IFIDX] == NULL) {
- pr_err("WIMAX_GNL_OP_RFKILL: can't find IFIDX attribute\n");
- goto error_no_wimax_dev;
- }
- ifindex = nla_get_u32(info->attrs[WIMAX_GNL_RFKILL_IFIDX]);
- wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
- if (wimax_dev == NULL)
- goto error_no_wimax_dev;
- dev = wimax_dev_to_dev(wimax_dev);
- result = -EINVAL;
- if (info->attrs[WIMAX_GNL_RFKILL_STATE] == NULL) {
- dev_err(dev, "WIMAX_GNL_RFKILL: can't find RFKILL_STATE "
- "attribute\n");
- goto error_no_pid;
- }
- new_state = nla_get_u32(info->attrs[WIMAX_GNL_RFKILL_STATE]);
-
- /* Execute the operation and send the result back to user space */
- result = wimax_rfkill(wimax_dev, new_state);
-error_no_pid:
- dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
- d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
- return result;
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Implement and export a method for getting a WiMAX device current state
- *
- * Copyright (C) 2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
- *
- * Based on previous WiMAX core work by:
- * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-
-#include <net/wimax.h>
-#include <net/genetlink.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE op_state_get
-#include "debug-levels.h"
-
-
-/*
- * Exporting to user space over generic netlink
- *
- * Parse the state get command from user space, return a combination
- * value that describe the current state.
- *
- * No attributes.
- */
-int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info)
-{
- int result, ifindex;
- struct wimax_dev *wimax_dev;
-
- d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
- result = -ENODEV;
- if (info->attrs[WIMAX_GNL_STGET_IFIDX] == NULL) {
- pr_err("WIMAX_GNL_OP_STATE_GET: can't find IFIDX attribute\n");
- goto error_no_wimax_dev;
- }
- ifindex = nla_get_u32(info->attrs[WIMAX_GNL_STGET_IFIDX]);
- wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
- if (wimax_dev == NULL)
- goto error_no_wimax_dev;
- /* Execute the operation and send the result back to user space */
- result = wimax_state_get(wimax_dev);
- dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
- d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
- return result;
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Initialization, addition and removal of wimax devices
- *
- * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements:
- *
- * - basic life cycle of 'struct wimax_dev' [wimax_dev_*()]; on
- * addition/registration initialize all subfields and allocate
- * generic netlink resources for user space communication. On
- * removal/unregistration, undo all that.
- *
- * - device state machine [wimax_state_change()] and support to send
- * reports to user space when the state changes
- * [wimax_gnl_re_state_change*()].
- *
- * See include/net/wimax.h for rationales and design.
- *
- * ROADMAP
- *
- * [__]wimax_state_change() Called by drivers to update device's state
- * wimax_gnl_re_state_change_alloc()
- * wimax_gnl_re_state_change_send()
- *
- * wimax_dev_init() Init a device
- * wimax_dev_add() Register
- * wimax_rfkill_add()
- * wimax_gnl_add() Register all the generic netlink resources.
- * wimax_id_table_add()
- * wimax_dev_rm() Unregister
- * wimax_id_table_rm()
- * wimax_gnl_rm()
- * wimax_rfkill_rm()
- */
-#include <linux/device.h>
-#include <linux/gfp.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-#include <linux/wimax.h>
-#include <linux/module.h>
-#include "wimax-internal.h"
-
-
-#define D_SUBMODULE stack
-#include "debug-levels.h"
-
-static char wimax_debug_params[128];
-module_param_string(debug, wimax_debug_params, sizeof(wimax_debug_params),
- 0644);
-MODULE_PARM_DESC(debug,
- "String of space-separated NAME:VALUE pairs, where NAMEs "
- "are the different debug submodules and VALUE are the "
- "initial debug value to set.");
-
-/*
- * Authoritative source for the RE_STATE_CHANGE attribute policy
- *
- * We don't really use it here, but /me likes to keep the definition
- * close to where the data is generated.
- */
-/*
-static const struct nla_policy wimax_gnl_re_status_change[WIMAX_GNL_ATTR_MAX + 1] = {
- [WIMAX_GNL_STCH_STATE_OLD] = { .type = NLA_U8 },
- [WIMAX_GNL_STCH_STATE_NEW] = { .type = NLA_U8 },
-};
-*/
-
-
-/*
- * Allocate a Report State Change message
- *
- * @header: save it, you need it for _send()
- *
- * Creates and fills a basic state change message; different code
- * paths can then add more attributes to the message as needed.
- *
- * Use wimax_gnl_re_state_change_send() to send the returned skb.
- *
- * Returns: skb with the genl message if ok, IS_ERR() ptr on error
- * with an errno code.
- */
-static
-struct sk_buff *wimax_gnl_re_state_change_alloc(
- struct wimax_dev *wimax_dev,
- enum wimax_st new_state, enum wimax_st old_state,
- void **header)
-{
- int result;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- void *data;
- struct sk_buff *report_skb;
-
- d_fnstart(3, dev, "(wimax_dev %p new_state %u old_state %u)\n",
- wimax_dev, new_state, old_state);
- result = -ENOMEM;
- report_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (report_skb == NULL) {
- dev_err(dev, "RE_STCH: can't create message\n");
- goto error_new;
- }
- /* FIXME: sending a group ID as the seq is wrong */
- data = genlmsg_put(report_skb, 0, wimax_gnl_family.mcgrp_offset,
- &wimax_gnl_family, 0, WIMAX_GNL_RE_STATE_CHANGE);
- if (data == NULL) {
- dev_err(dev, "RE_STCH: can't put data into message\n");
- goto error_put;
- }
- *header = data;
-
- result = nla_put_u8(report_skb, WIMAX_GNL_STCH_STATE_OLD, old_state);
- if (result < 0) {
- dev_err(dev, "RE_STCH: Error adding OLD attr: %d\n", result);
- goto error_put;
- }
- result = nla_put_u8(report_skb, WIMAX_GNL_STCH_STATE_NEW, new_state);
- if (result < 0) {
- dev_err(dev, "RE_STCH: Error adding NEW attr: %d\n", result);
- goto error_put;
- }
- result = nla_put_u32(report_skb, WIMAX_GNL_STCH_IFIDX,
- wimax_dev->net_dev->ifindex);
- if (result < 0) {
- dev_err(dev, "RE_STCH: Error adding IFINDEX attribute\n");
- goto error_put;
- }
- d_fnend(3, dev, "(wimax_dev %p new_state %u old_state %u) = %p\n",
- wimax_dev, new_state, old_state, report_skb);
- return report_skb;
-
-error_put:
- nlmsg_free(report_skb);
-error_new:
- d_fnend(3, dev, "(wimax_dev %p new_state %u old_state %u) = %d\n",
- wimax_dev, new_state, old_state, result);
- return ERR_PTR(result);
-}
-
-
-/*
- * Send a Report State Change message (as created with _alloc).
- *
- * @report_skb: as returned by wimax_gnl_re_state_change_alloc()
- * @header: as returned by wimax_gnl_re_state_change_alloc()
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * If the message is NULL, pretend it didn't happen.
- */
-static
-int wimax_gnl_re_state_change_send(
- struct wimax_dev *wimax_dev, struct sk_buff *report_skb,
- void *header)
-{
- int result = 0;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- d_fnstart(3, dev, "(wimax_dev %p report_skb %p)\n",
- wimax_dev, report_skb);
- if (report_skb == NULL) {
- result = -ENOMEM;
- goto out;
- }
- genlmsg_end(report_skb, header);
- genlmsg_multicast(&wimax_gnl_family, report_skb, 0, 0, GFP_KERNEL);
-out:
- d_fnend(3, dev, "(wimax_dev %p report_skb %p) = %d\n",
- wimax_dev, report_skb, result);
- return result;
-}
-
-
-static
-void __check_new_state(enum wimax_st old_state, enum wimax_st new_state,
- unsigned int allowed_states_bm)
-{
- if (WARN_ON(((1 << new_state) & allowed_states_bm) == 0)) {
- pr_err("SW BUG! Forbidden state change %u -> %u\n",
- old_state, new_state);
- }
-}
-
-
-/*
- * Set the current state of a WiMAX device [unlocking version of
- * wimax_state_change().
- */
-void __wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
-{
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- enum wimax_st old_state = wimax_dev->state;
- struct sk_buff *stch_skb;
- void *header;
-
- d_fnstart(3, dev, "(wimax_dev %p new_state %u [old %u])\n",
- wimax_dev, new_state, old_state);
-
- if (WARN_ON(new_state >= __WIMAX_ST_INVALID)) {
- dev_err(dev, "SW BUG: requesting invalid state %u\n",
- new_state);
- goto out;
- }
- if (old_state == new_state)
- goto out;
- header = NULL; /* gcc complains? can't grok why */
- stch_skb = wimax_gnl_re_state_change_alloc(
- wimax_dev, new_state, old_state, &header);
-
- /* Verify the state transition and do exit-from-state actions */
- switch (old_state) {
- case __WIMAX_ST_NULL:
- __check_new_state(old_state, new_state,
- 1 << WIMAX_ST_DOWN);
- break;
- case WIMAX_ST_DOWN:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_UNINITIALIZED
- | 1 << WIMAX_ST_RADIO_OFF);
- break;
- case __WIMAX_ST_QUIESCING:
- __check_new_state(old_state, new_state, 1 << WIMAX_ST_DOWN);
- break;
- case WIMAX_ST_UNINITIALIZED:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_RADIO_OFF);
- break;
- case WIMAX_ST_RADIO_OFF:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_READY);
- break;
- case WIMAX_ST_READY:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_RADIO_OFF
- | 1 << WIMAX_ST_SCANNING
- | 1 << WIMAX_ST_CONNECTING
- | 1 << WIMAX_ST_CONNECTED);
- break;
- case WIMAX_ST_SCANNING:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_RADIO_OFF
- | 1 << WIMAX_ST_READY
- | 1 << WIMAX_ST_CONNECTING
- | 1 << WIMAX_ST_CONNECTED);
- break;
- case WIMAX_ST_CONNECTING:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_RADIO_OFF
- | 1 << WIMAX_ST_READY
- | 1 << WIMAX_ST_SCANNING
- | 1 << WIMAX_ST_CONNECTED);
- break;
- case WIMAX_ST_CONNECTED:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_RADIO_OFF
- | 1 << WIMAX_ST_READY);
- netif_tx_disable(wimax_dev->net_dev);
- netif_carrier_off(wimax_dev->net_dev);
- break;
- case __WIMAX_ST_INVALID:
- default:
- dev_err(dev, "SW BUG: wimax_dev %p is in unknown state %u\n",
- wimax_dev, wimax_dev->state);
- WARN_ON(1);
- goto out;
- }
-
- /* Execute the actions of entry to the new state */
- switch (new_state) {
- case __WIMAX_ST_NULL:
- dev_err(dev, "SW BUG: wimax_dev %p entering NULL state "
- "from %u\n", wimax_dev, wimax_dev->state);
- WARN_ON(1); /* Nobody can enter this state */
- break;
- case WIMAX_ST_DOWN:
- break;
- case __WIMAX_ST_QUIESCING:
- break;
- case WIMAX_ST_UNINITIALIZED:
- break;
- case WIMAX_ST_RADIO_OFF:
- break;
- case WIMAX_ST_READY:
- break;
- case WIMAX_ST_SCANNING:
- break;
- case WIMAX_ST_CONNECTING:
- break;
- case WIMAX_ST_CONNECTED:
- netif_carrier_on(wimax_dev->net_dev);
- netif_wake_queue(wimax_dev->net_dev);
- break;
- case __WIMAX_ST_INVALID:
- default:
- BUG();
- }
- __wimax_state_set(wimax_dev, new_state);
- if (!IS_ERR(stch_skb))
- wimax_gnl_re_state_change_send(wimax_dev, stch_skb, header);
-out:
- d_fnend(3, dev, "(wimax_dev %p new_state %u [old %u]) = void\n",
- wimax_dev, new_state, old_state);
-}
-
-
-/**
- * wimax_state_change - Set the current state of a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor (properly referenced)
- * @new_state: New state to switch to
- *
- * This implements the state changes for the wimax devices. It will
- *
- * - verify that the state transition is legal (for now it'll just
- * print a warning if not) according to the table in
- * linux/wimax.h's documentation for 'enum wimax_st'.
- *
- * - perform the actions needed for leaving the current state and
- * whichever are needed for entering the new state.
- *
- * - issue a report to user space indicating the new state (and an
- * optional payload with information about the new state).
- *
- * NOTE: @wimax_dev must be locked
- */
-void wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
-{
- /*
- * A driver cannot take the wimax_dev out of the
- * __WIMAX_ST_NULL state unless by calling wimax_dev_add(). If
- * the wimax_dev's state is still NULL, we ignore any request
- * to change its state because it means it hasn't been yet
- * registered.
- *
- * There is no need to complain about it, as routines that
- * call this might be shared from different code paths that
- * are called before or after wimax_dev_add() has done its
- * job.
- */
- mutex_lock(&wimax_dev->mutex);
- if (wimax_dev->state > __WIMAX_ST_NULL)
- __wimax_state_change(wimax_dev, new_state);
- mutex_unlock(&wimax_dev->mutex);
-}
-EXPORT_SYMBOL_GPL(wimax_state_change);
-
-
-/**
- * wimax_state_get() - Return the current state of a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * Returns: Current state of the device according to its driver.
- */
-enum wimax_st wimax_state_get(struct wimax_dev *wimax_dev)
-{
- enum wimax_st state;
- mutex_lock(&wimax_dev->mutex);
- state = wimax_dev->state;
- mutex_unlock(&wimax_dev->mutex);
- return state;
-}
-EXPORT_SYMBOL_GPL(wimax_state_get);
-
-
-/**
- * wimax_dev_init - initialize a newly allocated instance
- *
- * @wimax_dev: WiMAX device descriptor to initialize.
- *
- * Initializes fields of a freshly allocated @wimax_dev instance. This
- * function assumes that after allocation, the memory occupied by
- * @wimax_dev was zeroed.
- */
-void wimax_dev_init(struct wimax_dev *wimax_dev)
-{
- INIT_LIST_HEAD(&wimax_dev->id_table_node);
- __wimax_state_set(wimax_dev, __WIMAX_ST_NULL);
- mutex_init(&wimax_dev->mutex);
- mutex_init(&wimax_dev->mutex_reset);
-}
-EXPORT_SYMBOL_GPL(wimax_dev_init);
-
-static const struct nla_policy wimax_gnl_policy[WIMAX_GNL_ATTR_MAX + 1] = {
- [WIMAX_GNL_RESET_IFIDX] = { .type = NLA_U32, },
- [WIMAX_GNL_RFKILL_IFIDX] = { .type = NLA_U32, },
- [WIMAX_GNL_RFKILL_STATE] = {
- .type = NLA_U32 /* enum wimax_rf_state */
- },
- [WIMAX_GNL_STGET_IFIDX] = { .type = NLA_U32, },
- [WIMAX_GNL_MSG_IFIDX] = { .type = NLA_U32, },
- [WIMAX_GNL_MSG_DATA] = {
- .type = NLA_UNSPEC, /* libnl doesn't grok BINARY yet */
- },
-};
-
-static const struct genl_small_ops wimax_gnl_ops[] = {
- {
- .cmd = WIMAX_GNL_OP_MSG_FROM_USER,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM,
- .doit = wimax_gnl_doit_msg_from_user,
- },
- {
- .cmd = WIMAX_GNL_OP_RESET,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM,
- .doit = wimax_gnl_doit_reset,
- },
- {
- .cmd = WIMAX_GNL_OP_RFKILL,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM,
- .doit = wimax_gnl_doit_rfkill,
- },
- {
- .cmd = WIMAX_GNL_OP_STATE_GET,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM,
- .doit = wimax_gnl_doit_state_get,
- },
-};
-
-
-static
-size_t wimax_addr_scnprint(char *addr_str, size_t addr_str_size,
- unsigned char *addr, size_t addr_len)
-{
- unsigned int cnt, total;
-
- for (total = cnt = 0; cnt < addr_len; cnt++)
- total += scnprintf(addr_str + total, addr_str_size - total,
- "%02x%c", addr[cnt],
- cnt == addr_len - 1 ? '\0' : ':');
- return total;
-}
-
-
-/**
- * wimax_dev_add - Register a new WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor (as embedded in your @net_dev's
- * priv data). You must have called wimax_dev_init() on it before.
- *
- * @net_dev: net device the @wimax_dev is associated with. The
- * function expects SET_NETDEV_DEV() and register_netdev() were
- * already called on it.
- *
- * Registers the new WiMAX device, sets up the user-kernel control
- * interface (generic netlink) and common WiMAX infrastructure.
- *
- * Note that the parts that will allow interaction with user space are
- * setup at the very end, when the rest is in place, as once that
- * happens, the driver might get user space control requests via
- * netlink or from debugfs that might translate into calls into
- * wimax_dev->op_*().
- */
-int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev)
-{
- int result;
- struct device *dev = net_dev->dev.parent;
- char addr_str[32];
-
- d_fnstart(3, dev, "(wimax_dev %p net_dev %p)\n", wimax_dev, net_dev);
-
- /* Do the RFKILL setup before locking, as RFKILL will call
- * into our functions.
- */
- wimax_dev->net_dev = net_dev;
- result = wimax_rfkill_add(wimax_dev);
- if (result < 0)
- goto error_rfkill_add;
-
- /* Set up user-space interaction */
- mutex_lock(&wimax_dev->mutex);
- wimax_id_table_add(wimax_dev);
- wimax_debugfs_add(wimax_dev);
-
- __wimax_state_set(wimax_dev, WIMAX_ST_DOWN);
- mutex_unlock(&wimax_dev->mutex);
-
- wimax_addr_scnprint(addr_str, sizeof(addr_str),
- net_dev->dev_addr, net_dev->addr_len);
- dev_err(dev, "WiMAX interface %s (%s) ready\n",
- net_dev->name, addr_str);
- d_fnend(3, dev, "(wimax_dev %p net_dev %p) = 0\n", wimax_dev, net_dev);
- return 0;
-
-error_rfkill_add:
- d_fnend(3, dev, "(wimax_dev %p net_dev %p) = %d\n",
- wimax_dev, net_dev, result);
- return result;
-}
-EXPORT_SYMBOL_GPL(wimax_dev_add);
-
-
-/**
- * wimax_dev_rm - Unregister an existing WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * Unregisters a WiMAX device previously registered for use with
- * wimax_add_rm().
- *
- * IMPORTANT! Must call before calling unregister_netdev().
- *
- * After this function returns, you will not get any more user space
- * control requests (via netlink or debugfs) and thus to wimax_dev->ops.
- *
- * Reentrancy control is ensured by setting the state to
- * %__WIMAX_ST_QUIESCING. rfkill operations coming through
- * wimax_*rfkill*() will be stopped by the quiescing state; ops coming
- * from the rfkill subsystem will be stopped by the support being
- * removed by wimax_rfkill_rm().
- */
-void wimax_dev_rm(struct wimax_dev *wimax_dev)
-{
- d_fnstart(3, NULL, "(wimax_dev %p)\n", wimax_dev);
-
- mutex_lock(&wimax_dev->mutex);
- __wimax_state_change(wimax_dev, __WIMAX_ST_QUIESCING);
- wimax_debugfs_rm(wimax_dev);
- wimax_id_table_rm(wimax_dev);
- __wimax_state_change(wimax_dev, WIMAX_ST_DOWN);
- mutex_unlock(&wimax_dev->mutex);
- wimax_rfkill_rm(wimax_dev);
- d_fnend(3, NULL, "(wimax_dev %p) = void\n", wimax_dev);
-}
-EXPORT_SYMBOL_GPL(wimax_dev_rm);
-
-
-/* Debug framework control of debug levels */
-struct d_level D_LEVEL[] = {
- D_SUBMODULE_DEFINE(debugfs),
- D_SUBMODULE_DEFINE(id_table),
- D_SUBMODULE_DEFINE(op_msg),
- D_SUBMODULE_DEFINE(op_reset),
- D_SUBMODULE_DEFINE(op_rfkill),
- D_SUBMODULE_DEFINE(op_state_get),
- D_SUBMODULE_DEFINE(stack),
-};
-size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
-
-
-static const struct genl_multicast_group wimax_gnl_mcgrps[] = {
- { .name = "msg", },
-};
-
-struct genl_family wimax_gnl_family __ro_after_init = {
- .name = "WiMAX",
- .version = WIMAX_GNL_VERSION,
- .hdrsize = 0,
- .maxattr = WIMAX_GNL_ATTR_MAX,
- .policy = wimax_gnl_policy,
- .module = THIS_MODULE,
- .small_ops = wimax_gnl_ops,
- .n_small_ops = ARRAY_SIZE(wimax_gnl_ops),
- .mcgrps = wimax_gnl_mcgrps,
- .n_mcgrps = ARRAY_SIZE(wimax_gnl_mcgrps),
-};
-
-
-
-/* Shutdown the wimax stack */
-static
-int __init wimax_subsys_init(void)
-{
- int result;
-
- d_fnstart(4, NULL, "()\n");
- d_parse_params(D_LEVEL, D_LEVEL_SIZE, wimax_debug_params,
- "wimax.debug");
-
- result = genl_register_family(&wimax_gnl_family);
- if (unlikely(result < 0)) {
- pr_err("cannot register generic netlink family: %d\n", result);
- goto error_register_family;
- }
-
- d_fnend(4, NULL, "() = 0\n");
- return 0;
-
-error_register_family:
- d_fnend(4, NULL, "() = %d\n", result);
- return result;
-
-}
-module_init(wimax_subsys_init);
-
-
-/* Shutdown the wimax stack */
-static
-void __exit wimax_subsys_exit(void)
-{
- wimax_id_table_release();
- genl_unregister_family(&wimax_gnl_family);
-}
-module_exit(wimax_subsys_exit);
-
-MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
-MODULE_DESCRIPTION("Linux WiMAX stack");
-MODULE_LICENSE("GPL");
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Linux WiMAX
- * Internal API for kernel space WiMAX stack
- *
- * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This header file is for declarations and definitions internal to
- * the WiMAX stack. For public APIs and documentation, see
- * include/net/wimax.h and include/linux/wimax.h.
- */
-
-#ifndef __WIMAX_INTERNAL_H__
-#define __WIMAX_INTERNAL_H__
-#ifdef __KERNEL__
-
-#ifdef pr_fmt
-#undef pr_fmt
-#endif
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/device.h>
-#include <net/wimax.h>
-
-
-/*
- * Decide if a (locked) device is ready for use
- *
- * Before using the device structure, it must be locked
- * (wimax_dev->mutex). As well, most operations need to call this
- * function to check if the state is the right one.
- *
- * An error value will be returned if the state is not the right
- * one. In that case, the caller should not attempt to use the device
- * and just unlock it.
- */
-static inline __must_check
-int wimax_dev_is_ready(struct wimax_dev *wimax_dev)
-{
- if (wimax_dev->state == __WIMAX_ST_NULL)
- return -EINVAL; /* Device is not even registered! */
- if (wimax_dev->state == WIMAX_ST_DOWN)
- return -ENOMEDIUM;
- if (wimax_dev->state == __WIMAX_ST_QUIESCING)
- return -ESHUTDOWN;
- return 0;
-}
-
-
-static inline
-void __wimax_state_set(struct wimax_dev *wimax_dev, enum wimax_st state)
-{
- wimax_dev->state = state;
-}
-void __wimax_state_change(struct wimax_dev *, enum wimax_st);
-
-#ifdef CONFIG_DEBUG_FS
-void wimax_debugfs_add(struct wimax_dev *);
-void wimax_debugfs_rm(struct wimax_dev *);
-#else
-static inline void wimax_debugfs_add(struct wimax_dev *wimax_dev) {}
-static inline void wimax_debugfs_rm(struct wimax_dev *wimax_dev) {}
-#endif
-
-void wimax_id_table_add(struct wimax_dev *);
-struct wimax_dev *wimax_dev_get_by_genl_info(struct genl_info *, int);
-void wimax_id_table_rm(struct wimax_dev *);
-void wimax_id_table_release(void);
-
-int wimax_rfkill_add(struct wimax_dev *);
-void wimax_rfkill_rm(struct wimax_dev *);
-
-/* generic netlink */
-extern struct genl_family wimax_gnl_family;
-
-/* ops */
-int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info);
-int wimax_gnl_doit_reset(struct sk_buff *skb, struct genl_info *info);
-int wimax_gnl_doit_rfkill(struct sk_buff *skb, struct genl_info *info);
-int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info);
-
-#endif /* #ifdef __KERNEL__ */
-#endif /* #ifndef __WIMAX_INTERNAL_H__ */
case NL80211_IFTYPE_P2P_CLIENT:
case NL80211_IFTYPE_MONITOR:
case NL80211_IFTYPE_AP_VLAN:
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_P2P_DEVICE:
case NL80211_IFTYPE_NAN:
break;
+ case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_UNSPECIFIED:
case NUM_NL80211_IFTYPES:
WARN_ON(1);
case NL80211_IFTYPE_P2P_CLIENT:
case NL80211_IFTYPE_MONITOR:
case NL80211_IFTYPE_AP_VLAN:
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_P2P_DEVICE:
/* Can NAN type be considered as beaconing interface? */
case NL80211_IFTYPE_NAN:
break;
case NL80211_IFTYPE_UNSPECIFIED:
+ case NL80211_IFTYPE_WDS:
case NUM_NL80211_IFTYPES:
WARN_ON(1);
}
break;
case NL80211_IFTYPE_MONITOR:
case NL80211_IFTYPE_AP_VLAN:
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_P2P_DEVICE:
case NL80211_IFTYPE_NAN:
/* these interface types don't really have a channel */
return;
case NL80211_IFTYPE_UNSPECIFIED:
+ case NL80211_IFTYPE_WDS:
case NUM_NL80211_IFTYPES:
WARN_ON(1);
}
return -EINVAL;
}
-#ifndef CONFIG_WIRELESS_WDS
if (WARN_ON(all_iftypes & BIT(NL80211_IFTYPE_WDS)))
return -EINVAL;
-#endif
/* You can't even choose that many! */
if (WARN_ON(cnt < c->max_interfaces))
!(wiphy->nan_supported_bands & BIT(NL80211_BAND_2GHZ)))))
return -EINVAL;
-#ifndef CONFIG_WIRELESS_WDS
if (WARN_ON(wiphy->interface_modes & BIT(NL80211_IFTYPE_WDS)))
return -EINVAL;
-#endif
if (WARN_ON(wiphy->pmsr_capa && !wiphy->pmsr_capa->ftm.supported))
return -EINVAL;
case NL80211_IFTYPE_OCB:
__cfg80211_leave_ocb(rdev, dev);
break;
- case NL80211_IFTYPE_WDS:
- /* must be handled by mac80211/driver, has no APIs */
- break;
case NL80211_IFTYPE_P2P_DEVICE:
case NL80211_IFTYPE_NAN:
/* cannot happen, has no netdev */
/* nothing to do */
break;
case NL80211_IFTYPE_UNSPECIFIED:
+ case NL80211_IFTYPE_WDS:
case NUM_NL80211_IFTYPES:
/* invalid */
break;
NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN),
[NL80211_ATTR_S1G_CAPABILITY_MASK] =
NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN),
+ [NL80211_ATTR_SAE_PWE] =
+ NLA_POLICY_RANGE(NLA_U8, NL80211_SAE_PWE_HUNT_AND_PECK,
+ NL80211_SAE_PWE_BOTH),
};
/* policy for the key attributes */
if (nla_put_u32(msg, i, NL80211_CMD_SET_CHANNEL))
goto nla_put_failure;
}
- CMD(set_wds_peer, SET_WDS_PEER);
if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) {
CMD(tdls_mgmt, TDLS_MGMT);
CMD(tdls_oper, TDLS_OPER);
static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev)
{
/*
- * You can only set the channel explicitly for WDS interfaces,
- * all others have their channel managed via their respective
+ * You can only set the channel explicitly for some interfaces,
+ * most have their channel managed via their respective
* "establish a connection" command (connect, join, ...)
*
* For AP/GO and mesh mode, the channel can be set with the
return __nl80211_set_channel(rdev, netdev, info);
}
-static int nl80211_set_wds_peer(struct sk_buff *skb, struct genl_info *info)
-{
- struct cfg80211_registered_device *rdev = info->user_ptr[0];
- struct net_device *dev = info->user_ptr[1];
- struct wireless_dev *wdev = dev->ieee80211_ptr;
- const u8 *bssid;
-
- if (!info->attrs[NL80211_ATTR_MAC])
- return -EINVAL;
-
- if (netif_running(dev))
- return -EBUSY;
-
- if (!rdev->ops->set_wds_peer)
- return -EOPNOTSUPP;
-
- if (wdev->iftype != NL80211_IFTYPE_WDS)
- return -EOPNOTSUPP;
-
- bssid = nla_data(info->attrs[NL80211_ATTR_MAC]);
- return rdev_set_wds_peer(rdev, dev, bssid);
-}
-
static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
{
struct cfg80211_registered_device *rdev;
struct nlattr *attrs[],
enum nl80211_attrs attr,
struct cfg80211_bitrate_mask *mask,
- struct net_device *dev)
+ struct net_device *dev,
+ bool default_all_enabled)
{
struct nlattr *tb[NL80211_TXRATE_MAX + 1];
struct cfg80211_registered_device *rdev = info->user_ptr[0];
for (i = 0; i < NUM_NL80211_BANDS; i++) {
const struct ieee80211_sta_he_cap *he_cap;
+ if (!default_all_enabled)
+ break;
+
sband = rdev->wiphy.bands[i];
if (!sband)
mask->control[band].ht_mcs))
return -EINVAL;
}
+
if (tb[NL80211_TXRATE_VHT]) {
if (!vht_set_mcs_mask(
sband,
mask->control[band].vht_mcs))
return -EINVAL;
}
+
if (tb[NL80211_TXRATE_GI]) {
mask->control[band].gi =
nla_get_u8(tb[NL80211_TXRATE_GI]);
nla_data(tb[NL80211_TXRATE_HE]),
mask->control[band].he_mcs))
return -EINVAL;
+
if (tb[NL80211_TXRATE_HE_GI])
mask->control[band].he_gi =
nla_get_u8(tb[NL80211_TXRATE_HE_GI]);
enum nl80211_band band,
struct cfg80211_bitrate_mask *beacon_rate)
{
- u32 count_ht, count_vht, i;
+ u32 count_ht, count_vht, count_he, i;
u32 rate = beacon_rate->control[band].legacy;
/* Allow only one rate */
return -EINVAL;
}
- if ((count_ht && count_vht) || (!rate && !count_ht && !count_vht))
+ count_he = 0;
+ for (i = 0; i < NL80211_HE_NSS_MAX; i++) {
+ if (hweight16(beacon_rate->control[band].he_mcs[i]) > 1) {
+ return -EINVAL;
+ } else if (beacon_rate->control[band].he_mcs[i]) {
+ count_he++;
+ if (count_he > 1)
+ return -EINVAL;
+ }
+ if (count_he && rate)
+ return -EINVAL;
+ }
+
+ if ((count_ht && count_vht && count_he) ||
+ (!rate && !count_ht && !count_vht && !count_he))
return -EINVAL;
if (rate &&
!wiphy_ext_feature_isset(&rdev->wiphy,
NL80211_EXT_FEATURE_BEACON_RATE_VHT))
return -EINVAL;
+ if (count_he &&
+ !wiphy_ext_feature_isset(&rdev->wiphy,
+ NL80211_EXT_FEATURE_BEACON_RATE_HE))
+ return -EINVAL;
return 0;
}
err = nl80211_parse_tx_bitrate_mask(info, info->attrs,
NL80211_ATTR_TX_RATES,
¶ms.beacon_rate,
- dev);
+ dev, false);
if (err)
return err;
nla_len(info->attrs[NL80211_ATTR_SAE_PASSWORD]);
}
+ if (info->attrs[NL80211_ATTR_SAE_PWE])
+ settings->sae_pwe =
+ nla_get_u8(info->attrs[NL80211_ATTR_SAE_PWE]);
+ else
+ settings->sae_pwe = NL80211_SAE_PWE_UNSPECIFIED;
+
return 0;
}
err = nl80211_parse_tx_bitrate_mask(info, info->attrs,
NL80211_ATTR_TX_RATES, &mask,
- dev);
+ dev, true);
if (err)
return err;
err = nl80211_parse_tx_bitrate_mask(info, info->attrs,
NL80211_ATTR_TX_RATES,
&setup.beacon_rate,
- dev);
+ dev, false);
if (err)
return err;
if (tid_conf->txrate_type != NL80211_TX_RATE_AUTOMATIC) {
attr = NL80211_TID_CONFIG_ATTR_TX_RATE;
err = nl80211_parse_tx_bitrate_mask(info, attrs, attr,
- &tid_conf->txrate_mask, dev);
+ &tid_conf->txrate_mask, dev,
+ true);
if (err)
return err;
.internal_flags = NL80211_FLAG_NEED_NETDEV |
NL80211_FLAG_NEED_RTNL,
},
- {
- .cmd = NL80211_CMD_SET_WDS_PEER,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .doit = nl80211_set_wds_peer,
- .flags = GENL_UNS_ADMIN_PERM,
- .internal_flags = NL80211_FLAG_NEED_NETDEV |
- NL80211_FLAG_NEED_RTNL,
- },
{
.cmd = NL80211_CMD_JOIN_MESH,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
return ret;
}
-static inline int rdev_set_wds_peer(struct cfg80211_registered_device *rdev,
- struct net_device *dev, const u8 *addr)
-{
- int ret;
- trace_rdev_set_wds_peer(&rdev->wiphy, dev, addr);
- ret = rdev->ops->set_wds_peer(&rdev->wiphy, dev, addr);
- trace_rdev_return_int(&rdev->wiphy, ret);
- return ret;
-}
-
static inline int
rdev_set_multicast_to_unicast(struct cfg80211_registered_device *rdev,
struct net_device *dev,
static bool cfg80211_find_ssid_match(struct cfg80211_colocated_ap *ap,
struct cfg80211_scan_request *request)
{
- u8 i;
+ int i;
u32 s_ssid;
for (i = 0; i < request->n_ssids; i++) {
TP_ARGS(wiphy, netdev, mac)
);
-DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_set_wds_peer,
- TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *mac),
- TP_ARGS(wiphy, netdev, mac)
-);
-
TRACE_EVENT(rdev_dump_station,
TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int _idx,
u8 *mac),
return -1;
break;
case cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS):
- if (unlikely(iftype != NL80211_IFTYPE_WDS &&
- iftype != NL80211_IFTYPE_MESH_POINT &&
+ if (unlikely(iftype != NL80211_IFTYPE_MESH_POINT &&
iftype != NL80211_IFTYPE_AP_VLAN &&
iftype != NL80211_IFTYPE_STATION))
return -1;
case NL80211_IFTYPE_P2P_GO:
case NL80211_IFTYPE_AP:
case NL80211_IFTYPE_AP_VLAN:
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_MESH_POINT:
/* bridging OK */
break;
/* not happening */
break;
case NL80211_IFTYPE_P2P_DEVICE:
+ case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_NAN:
WARN_ON(1);
break;
static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate)
{
-#define SCALE 2048
- u16 mcs_divisors[12] = {
- 34133, /* 16.666666... */
- 17067, /* 8.333333... */
- 11378, /* 5.555555... */
- 8533, /* 4.166666... */
- 5689, /* 2.777777... */
- 4267, /* 2.083333... */
- 3923, /* 1.851851... */
- 3413, /* 1.666666... */
- 2844, /* 1.388888... */
- 2560, /* 1.250000... */
- 2276, /* 1.111111... */
- 2048, /* 1.000000... */
+#define SCALE 6144
+ u32 mcs_divisors[14] = {
+ 102399, /* 16.666666... */
+ 51201, /* 8.333333... */
+ 34134, /* 5.555555... */
+ 25599, /* 4.166666... */
+ 17067, /* 2.777777... */
+ 12801, /* 2.083333... */
+ 11769, /* 1.851851... */
+ 10239, /* 1.666666... */
+ 8532, /* 1.388888... */
+ 7680, /* 1.250000... */
+ 6828, /* 1.111111... */
+ 6144, /* 1.000000... */
+ 5690, /* 0.926106... */
+ 5120, /* 0.833333... */
};
u32 rates_160M[3] = { 960777777, 907400000, 816666666 };
u32 rates_969[3] = { 480388888, 453700000, 408333333 };
u64 tmp;
u32 result;
- if (WARN_ON_ONCE(rate->mcs > 11))
+ if (WARN_ON_ONCE(rate->mcs > 13))
return 0;
if (WARN_ON_ONCE(rate->he_gi > NL80211_RATE_INFO_HE_GI_3_2))
case IW_MODE_ADHOC:
type = NL80211_IFTYPE_ADHOC;
break;
- case IW_MODE_REPEAT:
- type = NL80211_IFTYPE_WDS;
- break;
case IW_MODE_MONITOR:
type = NL80211_IFTYPE_MONITOR;
break;
return 0;
}
-static int cfg80211_wds_wext_siwap(struct net_device *dev,
- struct iw_request_info *info,
- struct sockaddr *addr, char *extra)
-{
- struct wireless_dev *wdev = dev->ieee80211_ptr;
- struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
- int err;
-
- if (WARN_ON(wdev->iftype != NL80211_IFTYPE_WDS))
- return -EINVAL;
-
- if (addr->sa_family != ARPHRD_ETHER)
- return -EINVAL;
-
- if (netif_running(dev))
- return -EBUSY;
-
- if (!rdev->ops->set_wds_peer)
- return -EOPNOTSUPP;
-
- err = rdev_set_wds_peer(rdev, dev, (u8 *)&addr->sa_data);
- if (err)
- return err;
-
- memcpy(&wdev->wext.bssid, (u8 *) &addr->sa_data, ETH_ALEN);
-
- return 0;
-}
-
-static int cfg80211_wds_wext_giwap(struct net_device *dev,
- struct iw_request_info *info,
- struct sockaddr *addr, char *extra)
-{
- struct wireless_dev *wdev = dev->ieee80211_ptr;
-
- if (WARN_ON(wdev->iftype != NL80211_IFTYPE_WDS))
- return -EINVAL;
-
- addr->sa_family = ARPHRD_ETHER;
- memcpy(&addr->sa_data, wdev->wext.bssid, ETH_ALEN);
-
- return 0;
-}
-
static int cfg80211_wext_siwrate(struct net_device *dev,
struct iw_request_info *info,
struct iw_param *rate, char *extra)
return cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra);
case NL80211_IFTYPE_STATION:
return cfg80211_mgd_wext_siwap(dev, info, ap_addr, extra);
- case NL80211_IFTYPE_WDS:
- return cfg80211_wds_wext_siwap(dev, info, ap_addr, extra);
default:
return -EOPNOTSUPP;
}
return cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra);
case NL80211_IFTYPE_STATION:
return cfg80211_mgd_wext_giwap(dev, info, ap_addr, extra);
- case NL80211_IFTYPE_WDS:
- return cfg80211_wds_wext_giwap(dev, info, ap_addr, extra);
default:
return -EOPNOTSUPP;
}
write_unlock_bh(&x25_list_lock);
}
-/*
- * Kill all bound sockets on a dropped device.
- */
-static void x25_kill_by_device(struct net_device *dev)
-{
- struct sock *s;
-
- write_lock_bh(&x25_list_lock);
-
- sk_for_each(s, &x25_list)
- if (x25_sk(s)->neighbour && x25_sk(s)->neighbour->dev == dev)
- x25_disconnect(s, ENETUNREACH, 0, 0);
-
- write_unlock_bh(&x25_list_lock);
-}
-
/*
* Handle device status changes.
*/
#endif
) {
switch (event) {
- case NETDEV_UP:
+ case NETDEV_REGISTER:
+ case NETDEV_POST_TYPE_CHANGE:
x25_link_device_up(dev);
break;
- case NETDEV_GOING_DOWN:
+ case NETDEV_DOWN:
nb = x25_get_neigh(dev);
if (nb) {
- x25_terminate_link(nb);
+ x25_link_terminated(nb);
x25_neigh_put(nb);
}
- break;
- case NETDEV_DOWN:
- x25_kill_by_device(dev);
x25_route_device_down(dev);
+ break;
+ case NETDEV_PRE_TYPE_CHANGE:
+ case NETDEV_UNREGISTER:
x25_link_device_down(dev);
break;
+ case NETDEV_CHANGE:
+ if (!netif_carrier_ok(dev)) {
+ nb = x25_get_neigh(dev);
+ if (nb) {
+ x25_link_terminated(nb);
+ x25_neigh_put(nb);
+ }
+ }
+ break;
}
}
switch (frametype) {
case X25_RESTART_REQUEST:
- confirm = !x25_t20timer_pending(nb);
- x25_stop_t20timer(nb);
- nb->state = X25_LINK_STATE_3;
- if (confirm)
+ switch (nb->state) {
+ case X25_LINK_STATE_2:
+ confirm = !x25_t20timer_pending(nb);
+ x25_stop_t20timer(nb);
+ nb->state = X25_LINK_STATE_3;
+ if (confirm)
+ x25_transmit_restart_confirmation(nb);
+ break;
+ case X25_LINK_STATE_3:
+ /* clear existing virtual calls */
+ x25_kill_by_neigh(nb);
+
x25_transmit_restart_confirmation(nb);
+ break;
+ }
break;
case X25_RESTART_CONFIRMATION:
- x25_stop_t20timer(nb);
- nb->state = X25_LINK_STATE_3;
+ switch (nb->state) {
+ case X25_LINK_STATE_2:
+ if (x25_t20timer_pending(nb)) {
+ x25_stop_t20timer(nb);
+ nb->state = X25_LINK_STATE_3;
+ } else {
+ x25_transmit_restart_request(nb);
+ x25_start_t20timer(nb);
+ }
+ break;
+ case X25_LINK_STATE_3:
+ /* clear existing virtual calls */
+ x25_kill_by_neigh(nb);
+
+ x25_transmit_restart_request(nb);
+ nb->state = X25_LINK_STATE_2;
+ x25_start_t20timer(nb);
+ break;
+ }
break;
case X25_DIAGNOSTIC:
{
switch (nb->state) {
case X25_LINK_STATE_0:
- nb->state = X25_LINK_STATE_2;
- break;
case X25_LINK_STATE_1:
x25_transmit_restart_request(nb);
nb->state = X25_LINK_STATE_2;
void x25_link_terminated(struct x25_neigh *nb)
{
nb->state = X25_LINK_STATE_0;
+ skb_queue_purge(&nb->queue);
+ x25_stop_t20timer(nb);
+
/* Out of order: clear existing virtual calls (X.25 03/93 4.6.3) */
x25_kill_by_neigh(nb);
}
*/
static void __x25_remove_neigh(struct x25_neigh *nb)
{
- skb_queue_purge(&nb->queue);
- x25_stop_t20timer(nb);
-
if (nb->node.next) {
list_del(&nb->node);
x25_neigh_put(nb);
__x25_remove_route(rt);
}
write_unlock_bh(&x25_route_list_lock);
-
- /* Remove any related forwarding */
- x25_clear_forward_by_dev(dev);
}
/*
}
EXPORT_SYMBOL(xfrm_input_resume);
-static void xfrm_trans_reinject(unsigned long data)
+static void xfrm_trans_reinject(struct tasklet_struct *t)
{
- struct xfrm_trans_tasklet *trans = (void *)data;
+ struct xfrm_trans_tasklet *trans = from_tasklet(trans, t, tasklet);
struct sk_buff_head queue;
struct sk_buff *skb;
trans = &per_cpu(xfrm_trans_tasklet, i);
__skb_queue_head_init(&trans->queue);
- tasklet_init(&trans->tasklet, xfrm_trans_reinject,
- (unsigned long)trans);
+ tasklet_setup(&trans->tasklet, xfrm_trans_reinject);
}
}
err = dst_output(xi->net, skb->sk, skb);
if (net_xmit_eval(err) == 0) {
- struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
-
- u64_stats_update_begin(&tstats->syncp);
- tstats->tx_bytes += length;
- tstats->tx_packets++;
- u64_stats_update_end(&tstats->syncp);
+ dev_sw_netstats_tx_add(dev, 1, length);
} else {
stats->tx_errors++;
stats->tx_aborted_errors++;
return err;
}
-static void xfrmi_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *s)
-{
- dev_fetch_sw_netstats(s, dev->tstats);
-
- s->rx_dropped = dev->stats.rx_dropped;
- s->tx_dropped = dev->stats.tx_dropped;
-}
-
static int xfrmi_get_iflink(const struct net_device *dev)
{
struct xfrm_if *xi = netdev_priv(dev);
return xi->p.link;
}
-
static const struct net_device_ops xfrmi_netdev_ops = {
.ndo_init = xfrmi_dev_init,
.ndo_uninit = xfrmi_dev_uninit,
.ndo_start_xmit = xfrmi_xmit,
- .ndo_get_stats64 = xfrmi_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = xfrmi_get_iflink,
};
#include "cgroup_helpers.h"
#include "hbm.h"
#include "bpf_util.h"
-#include <bpf/bpf.h>
#include <bpf/libbpf.h>
bool outFlag = true;
+++ /dev/null
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-function config_device {
- ip netns add at_ns0
- ip netns add at_ns1
- ip netns add at_ns2
- ip link add veth0 type veth peer name veth0b
- ip link add veth1 type veth peer name veth1b
- ip link add veth2 type veth peer name veth2b
- ip link set veth0b up
- ip link set veth1b up
- ip link set veth2b up
- ip link set dev veth0b mtu 1500
- ip link set dev veth1b mtu 1500
- ip link set dev veth2b mtu 1500
- ip link set veth0 netns at_ns0
- ip link set veth1 netns at_ns1
- ip link set veth2 netns at_ns2
- ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
- ip netns exec at_ns0 ip addr add 2401:db00::1/64 dev veth0 nodad
- ip netns exec at_ns0 ip link set dev veth0 up
- ip netns exec at_ns1 ip addr add 172.16.1.101/24 dev veth1
- ip netns exec at_ns1 ip addr add 2401:db00::2/64 dev veth1 nodad
- ip netns exec at_ns1 ip link set dev veth1 up
- ip netns exec at_ns2 ip addr add 172.16.1.200/24 dev veth2
- ip netns exec at_ns2 ip addr add 2401:db00::3/64 dev veth2 nodad
- ip netns exec at_ns2 ip link set dev veth2 up
- ip link add br0 type bridge
- ip link set br0 up
- ip link set dev br0 mtu 1500
- ip link set veth0b master br0
- ip link set veth1b master br0
- ip link set veth2b master br0
-}
-
-function add_ipip_tunnel {
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type ipip local 172.16.1.100 remote 172.16.1.200
- ip netns exec at_ns0 ip link set dev $DEV_NS up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
- ip netns exec at_ns1 \
- ip link add dev $DEV_NS type ipip local 172.16.1.101 remote 172.16.1.200
- ip netns exec at_ns1 ip link set dev $DEV_NS up
- # same inner IP address in at_ns0 and at_ns1
- ip netns exec at_ns1 ip addr add dev $DEV_NS 10.1.1.100/24
-
- ip netns exec at_ns2 ip link add dev $DEV type ipip external
- ip netns exec at_ns2 ip link set dev $DEV up
- ip netns exec at_ns2 ip addr add dev $DEV 10.1.1.200/24
-}
-
-function add_ipip6_tunnel {
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type ip6tnl mode ipip6 local 2401:db00::1/64 remote 2401:db00::3/64
- ip netns exec at_ns0 ip link set dev $DEV_NS up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
- ip netns exec at_ns1 \
- ip link add dev $DEV_NS type ip6tnl mode ipip6 local 2401:db00::2/64 remote 2401:db00::3/64
- ip netns exec at_ns1 ip link set dev $DEV_NS up
- # same inner IP address in at_ns0 and at_ns1
- ip netns exec at_ns1 ip addr add dev $DEV_NS 10.1.1.100/24
-
- ip netns exec at_ns2 ip link add dev $DEV type ip6tnl mode ipip6 external
- ip netns exec at_ns2 ip link set dev $DEV up
- ip netns exec at_ns2 ip addr add dev $DEV 10.1.1.200/24
-}
-
-function add_ip6ip6_tunnel {
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type ip6tnl mode ip6ip6 local 2401:db00::1/64 remote 2401:db00::3/64
- ip netns exec at_ns0 ip link set dev $DEV_NS up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 2601:646::1/64
- ip netns exec at_ns1 \
- ip link add dev $DEV_NS type ip6tnl mode ip6ip6 local 2401:db00::2/64 remote 2401:db00::3/64
- ip netns exec at_ns1 ip link set dev $DEV_NS up
- # same inner IP address in at_ns0 and at_ns1
- ip netns exec at_ns1 ip addr add dev $DEV_NS 2601:646::1/64
-
- ip netns exec at_ns2 ip link add dev $DEV type ip6tnl mode ip6ip6 external
- ip netns exec at_ns2 ip link set dev $DEV up
- ip netns exec at_ns2 ip addr add dev $DEV 2601:646::2/64
-}
-
-function attach_bpf {
- DEV=$1
- SET_TUNNEL=$2
- GET_TUNNEL=$3
- ip netns exec at_ns2 tc qdisc add dev $DEV clsact
- ip netns exec at_ns2 tc filter add dev $DEV egress bpf da obj tcbpf2_kern.o sec $SET_TUNNEL
- ip netns exec at_ns2 tc filter add dev $DEV ingress bpf da obj tcbpf2_kern.o sec $GET_TUNNEL
-}
-
-function test_ipip {
- DEV_NS=ipip_std
- DEV=ipip_bpf
- config_device
-# tcpdump -nei br0 &
- cat /sys/kernel/debug/tracing/trace_pipe &
-
- add_ipip_tunnel
- attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel
-
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- ip netns exec at_ns2 ping -c 1 10.1.1.100
- ip netns exec at_ns0 iperf -sD -p 5200 > /dev/null
- ip netns exec at_ns1 iperf -sD -p 5201 > /dev/null
- sleep 0.2
- # tcp check _same_ IP over different tunnels
- ip netns exec at_ns2 iperf -c 10.1.1.100 -n 5k -p 5200
- ip netns exec at_ns2 iperf -c 10.1.1.100 -n 5k -p 5201
- cleanup
-}
-
-# IPv4 over IPv6 tunnel
-function test_ipip6 {
- DEV_NS=ipip_std
- DEV=ipip_bpf
- config_device
-# tcpdump -nei br0 &
- cat /sys/kernel/debug/tracing/trace_pipe &
-
- add_ipip6_tunnel
- attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel
-
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- ip netns exec at_ns2 ping -c 1 10.1.1.100
- ip netns exec at_ns0 iperf -sD -p 5200 > /dev/null
- ip netns exec at_ns1 iperf -sD -p 5201 > /dev/null
- sleep 0.2
- # tcp check _same_ IP over different tunnels
- ip netns exec at_ns2 iperf -c 10.1.1.100 -n 5k -p 5200
- ip netns exec at_ns2 iperf -c 10.1.1.100 -n 5k -p 5201
- cleanup
-}
-
-# IPv6 over IPv6 tunnel
-function test_ip6ip6 {
- DEV_NS=ipip_std
- DEV=ipip_bpf
- config_device
-# tcpdump -nei br0 &
- cat /sys/kernel/debug/tracing/trace_pipe &
-
- add_ip6ip6_tunnel
- attach_bpf $DEV ip6ip6_set_tunnel ip6ip6_get_tunnel
-
- ip netns exec at_ns0 ping -6 -c 1 2601:646::2
- ip netns exec at_ns2 ping -6 -c 1 2601:646::1
- ip netns exec at_ns0 iperf -6sD -p 5200 > /dev/null
- ip netns exec at_ns1 iperf -6sD -p 5201 > /dev/null
- sleep 0.2
- # tcp check _same_ IP over different tunnels
- ip netns exec at_ns2 iperf -6c 2601:646::1 -n 5k -p 5200
- ip netns exec at_ns2 iperf -6c 2601:646::1 -n 5k -p 5201
- cleanup
-}
-
-function cleanup {
- set +ex
- pkill iperf
- ip netns delete at_ns0
- ip netns delete at_ns1
- ip netns delete at_ns2
- ip link del veth0
- ip link del veth1
- ip link del veth2
- ip link del br0
- pkill tcpdump
- pkill cat
- set -ex
-}
-
-cleanup
-echo "Testing IP tunnels..."
-test_ipip
-test_ipip6
-test_ip6ip6
-echo "*** PASS ***"
PHONY := __modfinal
__modfinal:
+include include/config/auto.conf
include $(srctree)/scripts/Kbuild.include
# for c_flags
-T scripts/module.lds -o $@ $(filter %.o, $^); \
$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
-$(modules): %.ko: %.o %.mod.o scripts/module.lds FORCE
- +$(call if_changed,ld_ko_o)
+quiet_cmd_btf_ko = BTF [M] $@
+ cmd_btf_ko = LLVM_OBJCOPY=$(OBJCOPY) $(PAHOLE) -J --btf_base vmlinux $@
+
+# Same as newer-prereqs, but allows to exclude specified extra dependencies
+newer_prereqs_except = $(filter-out $(PHONY) $(1),$?)
+
+# Same as if_changed, but allows to exclude specified extra dependencies
+if_changed_except = $(if $(call newer_prereqs_except,$(2))$(cmd-check), \
+ $(cmd); \
+ printf '%s\n' 'cmd_$@ := $(make-cmd)' > $(dot-target).cmd, @:)
+
+# Re-generate module BTFs if either module's .ko or vmlinux changed
+$(modules): %.ko: %.o %.mod.o scripts/module.lds vmlinux FORCE
+ +$(call if_changed_except,ld_ko_o,vmlinux)
+ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+ +$(if $(newer-prereqs),$(call cmd,btf_ko))
+endif
targets += $(modules) $(modules:.ko=.mod.o)
struct socket *sock);
int apparmor_secmark_check(struct aa_label *label, char *op, u32 request,
- u32 secid, struct sock *sk);
+ u32 secid, const struct sock *sk);
#endif /* __AA_NET_H */
}
#ifdef CONFIG_NETWORK_SECMARK
-static int apparmor_inet_conn_request(struct sock *sk, struct sk_buff *skb,
+static int apparmor_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req)
{
struct aa_sk_ctx *ctx = SK_CTX(sk);
}
static int aa_secmark_perm(struct aa_profile *profile, u32 request, u32 secid,
- struct common_audit_data *sa, struct sock *sk)
+ struct common_audit_data *sa)
{
int i, ret;
struct aa_perms perms = { };
}
int apparmor_secmark_check(struct aa_label *label, char *op, u32 request,
- u32 secid, struct sock *sk)
+ u32 secid, const struct sock *sk)
{
struct aa_profile *profile;
DEFINE_AUDIT_SK(sa, op, sk);
return fn_for_each_confined(label, profile,
aa_secmark_perm(profile, request, secid,
- &sa, sk));
+ &sa));
}
#endif
#include <linux/lsm_hook_defs.h>
#undef LSM_HOOK
LSM_HOOK_INIT(inode_free_security, bpf_inode_storage_free),
+ LSM_HOOK_INIT(task_free, bpf_task_storage_free),
};
static int __init bpf_lsm_init(void)
struct lsm_blob_sizes bpf_lsm_blob_sizes __lsm_ro_after_init = {
.lbs_inode = sizeof(struct bpf_storage_blob),
+ .lbs_task = sizeof(struct bpf_storage_blob),
};
DEFINE_LSM(bpf) = {
int ret;
memset(&prep, 0, sizeof(prep));
+ prep.orig_description = key->description;
prep.data = data;
prep.datalen = datalen;
prep.quotalen = key->type->def_datalen;
goto error_put_type;
memset(&prep, 0, sizeof(prep));
+ prep.orig_description = description;
prep.data = payload;
prep.datalen = plen;
prep.quotalen = index_key.type->def_datalen;
static inline void print_ipv6_addr(struct audit_buffer *ab,
- struct in6_addr *addr, __be16 port,
+ const struct in6_addr *addr, __be16 port,
char *name1, char *name2)
{
if (!ipv6_addr_any(addr))
}
case LSM_AUDIT_DATA_NET:
if (a->u.net->sk) {
- struct sock *sk = a->u.net->sk;
+ const struct sock *sk = a->u.net->sk;
struct unix_sock *u;
struct unix_address *addr;
int len = 0;
}
EXPORT_SYMBOL(security_sock_graft);
-int security_inet_conn_request(struct sock *sk,
+int security_inet_conn_request(const struct sock *sk,
struct sk_buff *skb, struct request_sock *req)
{
return call_int_hook(inet_conn_request, 0, sk, skb, req);
selinux_netlbl_sctp_sk_clone(sk, newsk);
}
-static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb,
+static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req)
{
struct sk_security_struct *sksec = sk->sk_security;
*
* Returns smack_known of the IP options or NULL if that won't work.
*/
-static struct smack_known *smack_from_netlbl(struct sock *sk, u16 family,
+static struct smack_known *smack_from_netlbl(const struct sock *sk, u16 family,
struct sk_buff *skb)
{
struct netlbl_lsm_secattr secattr;
* Returns 0 if a task with the packet label could write to
* the socket, otherwise an error code
*/
-static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb,
+static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req)
{
u16 family = sk->sk_family;
# SPDX-License-Identifier: GPL-2.0-only
*.d
-/bpftool-bootstrap
+/bootstrap/
/bpftool
bpftool*.8
bpf-helpers.*
| | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps**
| | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash**
| | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage**
-| | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** }
+| | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage**
+ | **task_storage** }
DESCRIPTION
===========
ifneq ($(OUTPUT),)
LIBBPF_OUTPUT = $(OUTPUT)/libbpf/
LIBBPF_PATH = $(LIBBPF_OUTPUT)
+ BOOTSTRAP_OUTPUT = $(OUTPUT)/bootstrap/
else
+ LIBBPF_OUTPUT =
LIBBPF_PATH = $(BPF_DIR)
+ BOOTSTRAP_OUTPUT = $(CURDIR)/bootstrap/
endif
LIBBPF = $(LIBBPF_PATH)libbpf.a
+LIBBPF_BOOTSTRAP_OUTPUT = $(BOOTSTRAP_OUTPUT)libbpf/
+LIBBPF_BOOTSTRAP = $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a
-BPFTOOL_VERSION ?= $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
+ifeq ($(BPFTOOL_VERSION),)
+BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
+endif
+
+$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT):
+ $(QUIET_MKDIR)mkdir -p $@
-$(LIBBPF): FORCE
- $(if $(LIBBPF_OUTPUT),@mkdir -p $(LIBBPF_OUTPUT))
+$(LIBBPF): FORCE | $(LIBBPF_OUTPUT)
$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) $(LIBBPF_OUTPUT)libbpf.a
-$(LIBBPF)-clean:
+$(LIBBPF_BOOTSTRAP): FORCE | $(LIBBPF_BOOTSTRAP_OUTPUT)
+ $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \
+ ARCH= CC=$(HOSTCC) LD=$(HOSTLD) $@
+
+$(LIBBPF)-clean: FORCE | $(LIBBPF_OUTPUT)
$(call QUIET_CLEAN, libbpf)
$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) clean >/dev/null
+$(LIBBPF_BOOTSTRAP)-clean: FORCE | $(LIBBPF_BOOTSTRAP_OUTPUT)
+ $(call QUIET_CLEAN, libbpf-bootstrap)
+ $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) clean >/dev/null
+
prefix ?= /usr/local
bash_compdir ?= /usr/share/bash-completion/completions
endif
LIBS = $(LIBBPF) -lelf -lz
+LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf -lz
ifeq ($(feature-libcap), 1)
CFLAGS += -DUSE_LIBCAP
LIBS += -lcap
SRCS += $(BFD_SRCS)
endif
-BPFTOOL_BOOTSTRAP := $(if $(OUTPUT),$(OUTPUT)bpftool-bootstrap,./bpftool-bootstrap)
+BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool
-BOOTSTRAP_OBJS = $(addprefix $(OUTPUT),main.o common.o json_writer.o gen.o btf.o)
+BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o)
OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \
$(OUTPUT)feature.o: | zdep
-$(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF)
- $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(BOOTSTRAP_OBJS) $(LIBS)
+$(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP)
+ $(QUIET_LINK)$(HOSTCC) $(CFLAGS) $(LDFLAGS) -o $@ $(BOOTSTRAP_OBJS) \
+ $(LIBS_BOOTSTRAP)
$(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJS) $(LIBS)
+$(BOOTSTRAP_OUTPUT)%.o: %.c | $(BOOTSTRAP_OUTPUT)
+ $(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD -o $@ $<
+
$(OUTPUT)%.o: %.c
$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $<
$(call QUIET_CLEAN, feature-detect)
$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
-clean: $(LIBBPF)-clean feature-detect-clean
+clean: $(LIBBPF)-clean $(LIBBPF_BOOTSTRAP)-clean feature-detect-clean
$(call QUIET_CLEAN, bpftool)
$(Q)$(RM) -- $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d
- $(Q)$(RM) -- $(BPFTOOL_BOOTSTRAP) $(OUTPUT)*.skel.h $(OUTPUT)vmlinux.h
- $(Q)$(RM) -r -- $(OUTPUT)libbpf/
+ $(Q)$(RM) -- $(OUTPUT)*.skel.h $(OUTPUT)vmlinux.h
+ $(Q)$(RM) -r -- $(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT)
$(call QUIET_CLEAN, core-gen)
$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool
$(Q)$(RM) -r -- $(OUTPUT)feature/
hash_of_maps devmap devmap_hash sockmap cpumap \
xskmap sockhash cgroup_storage reuseport_sockarray \
percpu_cgroup_storage queue stack sk_storage \
- struct_ops inode_storage' -- \
+ struct_ops inode_storage task_storage' -- \
"$cur" ) )
return 0
;;
}
} else {
int cnt = btf__get_nr_types(btf);
+ int start_id = 1;
- for (i = 1; i <= cnt; i++) {
+ if (base_btf)
+ start_id = btf__get_nr_types(base_btf) + 1;
+
+ for (i = start_id; i <= cnt; i++) {
t = btf__type_by_id(btf, i);
dump_btf_type(btf, i, t);
}
return -1;
}
src = GET_ARG();
-
if (is_prefix(src, "map")) {
struct bpf_map_info info = {};
__u32 len = sizeof(info);
}
NEXT_ARG();
} else if (is_prefix(src, "file")) {
- btf = btf__parse(*argv, NULL);
+ btf = btf__parse_split(*argv, base_btf);
if (IS_ERR(btf)) {
err = -PTR_ERR(btf);
btf = NULL;
struct btf_attach_table *btf_map_table)
{
struct btf_attach_point *obj;
+ const char *name = u64_to_ptr(info->name);
int n;
printf("%u: ", info->id);
+ if (info->kernel_btf)
+ printf("name [%s] ", name);
+ else if (name && name[0])
+ printf("name %s ", name);
printf("size %uB", info->btf_size);
n = 0;
struct btf_attach_table *btf_map_table)
{
struct btf_attach_point *obj;
+ const char *name = u64_to_ptr(info->name);
jsonw_start_object(json_wtr); /* btf object */
jsonw_uint_field(json_wtr, "id", info->id);
emit_obj_refs_json(&refs_table, info->id, json_wtr); /* pids */
+ jsonw_bool_field(json_wtr, "kernel", info->kernel_btf);
+
+ if (name && name[0])
+ jsonw_string_field(json_wtr, "name", name);
+
jsonw_end_object(json_wtr); /* btf object */
}
show_btf(int fd, struct btf_attach_table *btf_prog_table,
struct btf_attach_table *btf_map_table)
{
- struct bpf_btf_info info = {};
+ struct bpf_btf_info info;
__u32 len = sizeof(info);
+ char name[64];
int err;
+ memset(&info, 0, sizeof(info));
err = bpf_obj_get_info_by_fd(fd, &info, &len);
if (err) {
p_err("can't get BTF object info: %s", strerror(errno));
return -1;
}
+ /* if kernel support emitting BTF object name, pass name pointer */
+ if (info.name_len) {
+ memset(&info, 0, sizeof(info));
+ info.name_len = sizeof(name);
+ info.name = ptr_to_u64(name);
+ len = sizeof(info);
+
+ err = bpf_obj_get_info_by_fd(fd, &info, &len);
+ if (err) {
+ p_err("can't get BTF object info: %s", strerror(errno));
+ return -1;
+ }
+ }
if (json_output)
show_btf_json(&info, fd, btf_prog_table, btf_map_table);
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
+#include <bpf/btf.h>
#include "main.h"
bool block_mount;
bool verifier_logs;
bool relaxed_maps;
+struct btf *base_btf;
struct pinned_obj_table prog_table;
struct pinned_obj_table map_table;
struct pinned_obj_table link_table;
{ "mapcompat", no_argument, NULL, 'm' },
{ "nomount", no_argument, NULL, 'n' },
{ "debug", no_argument, NULL, 'd' },
+ { "base-btf", required_argument, NULL, 'B' },
{ 0 }
};
int opt, ret;
hash_init(link_table.table);
opterr = 0;
- while ((opt = getopt_long(argc, argv, "Vhpjfmnd",
+ while ((opt = getopt_long(argc, argv, "VhpjfmndB:",
options, NULL)) >= 0) {
switch (opt) {
case 'V':
libbpf_set_print(print_all_levels);
verifier_logs = true;
break;
+ case 'B':
+ base_btf = btf__parse(optarg, NULL);
+ if (libbpf_get_error(base_btf)) {
+ p_err("failed to parse base BTF at '%s': %ld\n",
+ optarg, libbpf_get_error(base_btf));
+ base_btf = NULL;
+ return -1;
+ }
+ break;
default:
p_err("unrecognized option '%s'", argv[optind - 1]);
if (json_output)
delete_pinned_obj_table(&map_table);
delete_pinned_obj_table(&link_table);
}
+ btf__free(base_btf);
return ret;
}
extern bool block_mount;
extern bool verifier_logs;
extern bool relaxed_maps;
+extern struct btf *base_btf;
extern struct pinned_obj_table prog_table;
extern struct pinned_obj_table map_table;
extern struct pinned_obj_table link_table;
[BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops",
[BPF_MAP_TYPE_RINGBUF] = "ringbuf",
[BPF_MAP_TYPE_INODE_STORAGE] = "inode_storage",
+ [BPF_MAP_TYPE_TASK_STORAGE] = "task_storage",
};
const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
" lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n"
" devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n"
" cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n"
- " queue | stack | sk_storage | struct_ops | ringbuf | inode_storage }\n"
+ " queue | stack | sk_storage | struct_ops | ringbuf | inode_storage |\n"
+ " task_storage }\n"
" " HELP_SPEC_OPTIONS "\n"
"",
bin_name, argv[-2]);
endif
# always use the host compiler
-ifneq ($(LLVM),)
-HOSTAR ?= llvm-ar
-HOSTCC ?= clang
-HOSTLD ?= ld.lld
-else
-HOSTAR ?= ar
-HOSTCC ?= gcc
-HOSTLD ?= ld
-endif
AR = $(HOSTAR)
CC = $(HOSTCC)
LD = $(HOSTLD)
# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-OUTPUT := .output
+include ../../scripts/Makefile.include
+
+OUTPUT ?= $(abspath .output)/
+
CLANG ?= clang
LLC ?= llc
LLVM_STRIP ?= llvm-strip
-DEFAULT_BPFTOOL := $(OUTPUT)/sbin/bpftool
+BPFTOOL_OUTPUT := $(OUTPUT)bpftool/
+DEFAULT_BPFTOOL := $(BPFTOOL_OUTPUT)bpftool
BPFTOOL ?= $(DEFAULT_BPFTOOL)
LIBBPF_SRC := $(abspath ../../lib/bpf)
-BPFOBJ := $(OUTPUT)/libbpf.a
-BPF_INCLUDE := $(OUTPUT)
+BPFOBJ_OUTPUT := $(OUTPUT)libbpf/
+BPFOBJ := $(BPFOBJ_OUTPUT)libbpf.a
+BPF_INCLUDE := $(BPFOBJ_OUTPUT)
INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../lib) \
-I$(abspath ../../include/uapi)
CFLAGS := -g -Wall
VMLINUX_BTF_PATH := $(or $(VMLINUX_BTF),$(firstword \
$(wildcard $(VMLINUX_BTF_PATHS))))
-abs_out := $(abspath $(OUTPUT))
ifeq ($(V),1)
Q =
-msg =
else
Q = @
-msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))";
MAKEFLAGS += --no-print-directory
submake_extras := feature_display=0
endif
runqslower: $(OUTPUT)/runqslower
clean:
- $(call msg,CLEAN)
- $(Q)rm -rf $(OUTPUT) runqslower
+ $(call QUIET_CLEAN, runqslower)
+ $(Q)$(RM) -r $(BPFOBJ_OUTPUT) $(BPFTOOL_OUTPUT)
+ $(Q)$(RM) $(OUTPUT)*.o $(OUTPUT)*.d
+ $(Q)$(RM) $(OUTPUT)*.skel.h $(OUTPUT)vmlinux.h
+ $(Q)$(RM) $(OUTPUT)runqslower
+ $(Q)$(RM) -r .output
$(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ)
- $(call msg,BINARY,$@)
- $(Q)$(CC) $(CFLAGS) $^ -lelf -lz -o $@
+ $(QUIET_LINK)$(CC) $(CFLAGS) $^ -lelf -lz -o $@
$(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h \
$(OUTPUT)/runqslower.bpf.o
$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h
$(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL)
- $(call msg,GEN-SKEL,$@)
- $(Q)$(BPFTOOL) gen skeleton $< > $@
+ $(QUIET_GEN)$(BPFTOOL) gen skeleton $< > $@
$(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT)
- $(call msg,BPF,$@)
- $(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES) \
+ $(QUIET_GEN)$(CLANG) -g -O2 -target bpf $(INCLUDES) \
-c $(filter %.c,$^) -o $@ && \
$(LLVM_STRIP) -g $@
$(OUTPUT)/%.o: %.c | $(OUTPUT)
- $(call msg,CC,$@)
- $(Q)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@
+ $(QUIET_CC)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@
-$(OUTPUT):
- $(call msg,MKDIR,$@)
- $(Q)mkdir -p $(OUTPUT)
+$(OUTPUT) $(BPFOBJ_OUTPUT) $(BPFTOOL_OUTPUT):
+ $(QUIET_MKDIR)mkdir -p $@
$(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL)
- $(call msg,GEN,$@)
$(Q)if [ ! -e "$(VMLINUX_BTF_PATH)" ] ; then \
echo "Couldn't find kernel BTF; set VMLINUX_BTF to" \
"specify its location." >&2; \
exit 1;\
fi
- $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@
+ $(QUIET_GEN)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@
-$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT)
- $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) \
- OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
+$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OUTPUT)
+ $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(BPFOBJ_OUTPUT) $@
-$(DEFAULT_BPFTOOL):
- $(Q)$(MAKE) $(submake_extras) -C ../bpftool \
- prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install
+$(DEFAULT_BPFTOOL): | $(BPFTOOL_OUTPUT)
+ $(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT) \
+ CC=$(HOSTCC) LD=$(HOSTLD)
$(call allow-override,CC,$(CROSS_COMPILE)gcc)
$(call allow-override,LD,$(CROSS_COMPILE)ld)
-HOSTCC ?= gcc
-HOSTLD ?= ld
-HOSTAR ?= ar
-
export HOSTCC HOSTLD HOSTAR
ifeq ($(V),1)
BPF_MAP_TYPE_STRUCT_OPS,
BPF_MAP_TYPE_RINGBUF,
BPF_MAP_TYPE_INODE_STORAGE,
+ BPF_MAP_TYPE_TASK_STORAGE,
};
/* Note that tracing related programs such as
* Return
* The helper returns **TC_ACT_REDIRECT** on success or
* **TC_ACT_SHOT** on error.
+ *
+ * void *bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from the *task*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *task* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
+ * helper enforces the key must be an task_struct and the map must also
+ * be a **BPF_MAP_TYPE_TASK_STORAGE**.
+ *
+ * Underneath, the value is stored locally at *task* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf_local_storage residing at *task*.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * long bpf_task_storage_delete(struct bpf_map *map, struct task_struct *task)
+ * Description
+ * Delete a bpf_local_storage from a *task*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * struct task_struct *bpf_get_current_task_btf(void)
+ * Description
+ * Return a BTF pointer to the "current" task.
+ * This pointer can also be used in helpers that accept an
+ * *ARG_PTR_TO_BTF_ID* of type *task_struct*.
+ * Return
+ * Pointer to the current task.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
FN(bpf_per_cpu_ptr), \
FN(bpf_this_cpu_ptr), \
FN(redirect_peer), \
+ FN(task_storage_get), \
+ FN(task_storage_delete), \
+ FN(get_current_task_btf), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
__aligned_u64 btf;
__u32 btf_size;
__u32 id;
+ __aligned_u64 name;
+ __u32 name_len;
+ __u32 kernel_btf;
} __attribute__((aligned(8)));
struct bpf_link_info {
IFLA_MACVLAN_MACADDR,
IFLA_MACVLAN_MACADDR_DATA,
IFLA_MACVLAN_MACADDR_COUNT,
+ IFLA_MACVLAN_BC_QUEUE_LEN,
+ IFLA_MACVLAN_BC_QUEUE_LEN_USED,
__IFLA_MACVLAN_MAX,
};
void *types_data;
size_t types_data_cap; /* used size stored in hdr->type_len */
- /* type ID to `struct btf_type *` lookup index */
+ /* type ID to `struct btf_type *` lookup index
+ * type_offs[0] corresponds to the first non-VOID type:
+ * - for base BTF it's type [1];
+ * - for split BTF it's the first non-base BTF type.
+ */
__u32 *type_offs;
size_t type_offs_cap;
+ /* number of types in this BTF instance:
+ * - doesn't include special [0] void type;
+ * - for split BTF counts number of types added on top of base BTF.
+ */
__u32 nr_types;
+ /* if not NULL, points to the base BTF on top of which the current
+ * split BTF is based
+ */
+ struct btf *base_btf;
+ /* BTF type ID of the first type in this BTF instance:
+ * - for base BTF it's equal to 1;
+ * - for split BTF it's equal to biggest type ID of base BTF plus 1.
+ */
+ int start_id;
+ /* logical string offset of this BTF instance:
+ * - for base BTF it's equal to 0;
+ * - for split BTF it's equal to total size of base BTF's string section size.
+ */
+ int start_str_off;
void *strs_data;
size_t strs_data_cap; /* used size stored in hdr->str_len */
struct hashmap *strs_hash;
/* whether strings are already deduplicated */
bool strs_deduped;
+ /* extra indirection layer to make strings hashmap work with stable
+ * string offsets and ability to transparently choose between
+ * btf->strs_data or btf_dedup->strs_data as a source of strings.
+ * This is used for BTF strings dedup to transfer deduplicated strings
+ * data back to struct btf without re-building strings index.
+ */
+ void **strs_data_ptr;
+
/* BTF object FD, if loaded into kernel */
int fd;
__u32 *p;
p = btf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
- btf->nr_types + 1, BTF_MAX_NR_TYPES, 1);
+ btf->nr_types, BTF_MAX_NR_TYPES, 1);
if (!p)
return -ENOMEM;
return -EINVAL;
}
- if (meta_left < hdr->type_off) {
- pr_debug("Invalid BTF type section offset:%u\n", hdr->type_off);
- return -EINVAL;
- }
-
- if (meta_left < hdr->str_off) {
- pr_debug("Invalid BTF string section offset:%u\n", hdr->str_off);
+ if (meta_left < hdr->str_off + hdr->str_len) {
+ pr_debug("Invalid BTF total size:%u\n", btf->raw_size);
return -EINVAL;
}
- if (hdr->type_off >= hdr->str_off) {
- pr_debug("BTF type section offset >= string section offset. No type?\n");
+ if (hdr->type_off + hdr->type_len > hdr->str_off) {
+ pr_debug("Invalid BTF data sections layout: type data at %u + %u, strings data at %u + %u\n",
+ hdr->type_off, hdr->type_len, hdr->str_off, hdr->str_len);
return -EINVAL;
}
- if (hdr->type_off & 0x02) {
+ if (hdr->type_off % 4) {
pr_debug("BTF type section is not aligned to 4 bytes\n");
return -EINVAL;
}
const char *start = btf->strs_data;
const char *end = start + btf->hdr->str_len;
- if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET ||
- start[0] || end[-1]) {
+ if (btf->base_btf && hdr->str_len == 0)
+ return 0;
+ if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET || end[-1]) {
+ pr_debug("Invalid BTF string section\n");
+ return -EINVAL;
+ }
+ if (!btf->base_btf && start[0]) {
pr_debug("Invalid BTF string section\n");
return -EINVAL;
}
-
return 0;
}
struct btf_header *hdr = btf->hdr;
void *next_type = btf->types_data;
void *end_type = next_type + hdr->type_len;
- int err, i = 0, type_size;
-
- /* VOID (type_id == 0) is specially handled by btf__get_type_by_id(),
- * so ensure we can never properly use its offset from index by
- * setting it to a large value
- */
- err = btf_add_type_idx_entry(btf, UINT_MAX);
- if (err)
- return err;
+ int err, type_size;
while (next_type + sizeof(struct btf_type) <= end_type) {
- i++;
-
if (btf->swapped_endian)
btf_bswap_type_base(next_type);
if (type_size < 0)
return type_size;
if (next_type + type_size > end_type) {
- pr_warn("BTF type [%d] is malformed\n", i);
+ pr_warn("BTF type [%d] is malformed\n", btf->start_id + btf->nr_types);
return -EINVAL;
}
__u32 btf__get_nr_types(const struct btf *btf)
{
- return btf->nr_types;
+ return btf->start_id + btf->nr_types - 1;
}
/* internal helper returning non-const pointer to a type */
{
if (type_id == 0)
return &btf_void;
-
- return btf->types_data + btf->type_offs[type_id];
+ if (type_id < btf->start_id)
+ return btf_type_by_id(btf->base_btf, type_id);
+ return btf->types_data + btf->type_offs[type_id - btf->start_id];
}
const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
{
- if (type_id > btf->nr_types)
+ if (type_id >= btf->start_id + btf->nr_types)
return NULL;
return btf_type_by_id((struct btf *)btf, type_id);
}
{
const struct btf_type *t;
const char *name;
- int i;
+ int i, n;
- for (i = 1; i <= btf->nr_types; i++) {
+ if (btf->base_btf && btf->base_btf->ptr_sz > 0)
+ return btf->base_btf->ptr_sz;
+
+ n = btf__get_nr_types(btf);
+ for (i = 1; i <= n; i++) {
t = btf__type_by_id(btf, i);
if (!btf_is_int(t))
continue;
free(btf);
}
-struct btf *btf__new_empty(void)
+static struct btf *btf_new_empty(struct btf *base_btf)
{
struct btf *btf;
if (!btf)
return ERR_PTR(-ENOMEM);
+ btf->nr_types = 0;
+ btf->start_id = 1;
+ btf->start_str_off = 0;
btf->fd = -1;
btf->ptr_sz = sizeof(void *);
btf->swapped_endian = false;
+ if (base_btf) {
+ btf->base_btf = base_btf;
+ btf->start_id = btf__get_nr_types(base_btf) + 1;
+ btf->start_str_off = base_btf->hdr->str_len;
+ }
+
/* +1 for empty string at offset 0 */
- btf->raw_size = sizeof(struct btf_header) + 1;
+ btf->raw_size = sizeof(struct btf_header) + (base_btf ? 0 : 1);
btf->raw_data = calloc(1, btf->raw_size);
if (!btf->raw_data) {
free(btf);
btf->types_data = btf->raw_data + btf->hdr->hdr_len;
btf->strs_data = btf->raw_data + btf->hdr->hdr_len;
- btf->hdr->str_len = 1; /* empty string at offset 0 */
+ btf->hdr->str_len = base_btf ? 0 : 1; /* empty string at offset 0 */
return btf;
}
-struct btf *btf__new(const void *data, __u32 size)
+struct btf *btf__new_empty(void)
+{
+ return btf_new_empty(NULL);
+}
+
+struct btf *btf__new_empty_split(struct btf *base_btf)
+{
+ return btf_new_empty(base_btf);
+}
+
+static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
{
struct btf *btf;
int err;
if (!btf)
return ERR_PTR(-ENOMEM);
+ btf->nr_types = 0;
+ btf->start_id = 1;
+ btf->start_str_off = 0;
+
+ if (base_btf) {
+ btf->base_btf = base_btf;
+ btf->start_id = btf__get_nr_types(base_btf) + 1;
+ btf->start_str_off = base_btf->hdr->str_len;
+ }
+
btf->raw_data = malloc(size);
if (!btf->raw_data) {
err = -ENOMEM;
return btf;
}
-struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
+struct btf *btf__new(const void *data, __u32 size)
+{
+ return btf_new(data, size, NULL);
+}
+
+static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
+ struct btf_ext **btf_ext)
{
Elf_Data *btf_data = NULL, *btf_ext_data = NULL;
int err = 0, fd = -1, idx = 0;
err = -ENOENT;
goto done;
}
- btf = btf__new(btf_data->d_buf, btf_data->d_size);
+ btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf);
if (IS_ERR(btf))
goto done;
return btf;
}
-struct btf *btf__parse_raw(const char *path)
+struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
+{
+ return btf_parse_elf(path, NULL, btf_ext);
+}
+
+struct btf *btf__parse_elf_split(const char *path, struct btf *base_btf)
+{
+ return btf_parse_elf(path, base_btf, NULL);
+}
+
+static struct btf *btf_parse_raw(const char *path, struct btf *base_btf)
{
struct btf *btf = NULL;
void *data = NULL;
}
/* finally parse BTF data */
- btf = btf__new(data, sz);
+ btf = btf_new(data, sz, base_btf);
err_out:
free(data);
return err ? ERR_PTR(err) : btf;
}
-struct btf *btf__parse(const char *path, struct btf_ext **btf_ext)
+struct btf *btf__parse_raw(const char *path)
+{
+ return btf_parse_raw(path, NULL);
+}
+
+struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf)
+{
+ return btf_parse_raw(path, base_btf);
+}
+
+static struct btf *btf_parse(const char *path, struct btf *base_btf, struct btf_ext **btf_ext)
{
struct btf *btf;
if (btf_ext)
*btf_ext = NULL;
- btf = btf__parse_raw(path);
+ btf = btf_parse_raw(path, base_btf);
if (!IS_ERR(btf) || PTR_ERR(btf) != -EPROTO)
return btf;
- return btf__parse_elf(path, btf_ext);
+ return btf_parse_elf(path, base_btf, btf_ext);
+}
+
+struct btf *btf__parse(const char *path, struct btf_ext **btf_ext)
+{
+ return btf_parse(path, NULL, btf_ext);
+}
+
+struct btf *btf__parse_split(const char *path, struct btf *base_btf)
+{
+ return btf_parse(path, base_btf, NULL);
}
static int compare_vsi_off(const void *_a, const void *_b)
memcpy(p, btf->types_data, hdr->type_len);
if (swap_endian) {
- for (i = 1; i <= btf->nr_types; i++) {
- t = p + btf->type_offs[i];
+ for (i = 0; i < btf->nr_types; i++) {
+ t = p + btf->type_offs[i];
/* btf_bswap_type_rest() relies on native t->info, so
* we swap base type info after we swapped all the
* additional information
const char *btf__str_by_offset(const struct btf *btf, __u32 offset)
{
- if (offset < btf->hdr->str_len)
- return btf->strs_data + offset;
+ if (offset < btf->start_str_off)
+ return btf__str_by_offset(btf->base_btf, offset);
+ else if (offset - btf->start_str_off < btf->hdr->str_len)
+ return btf->strs_data + (offset - btf->start_str_off);
else
return NULL;
}
static size_t strs_hash_fn(const void *key, void *ctx)
{
- struct btf *btf = ctx;
- const char *str = btf->strs_data + (long)key;
+ const struct btf *btf = ctx;
+ const char *strs = *btf->strs_data_ptr;
+ const char *str = strs + (long)key;
return str_hash(str);
}
static bool strs_hash_equal_fn(const void *key1, const void *key2, void *ctx)
{
- struct btf *btf = ctx;
- const char *str1 = btf->strs_data + (long)key1;
- const char *str2 = btf->strs_data + (long)key2;
+ const struct btf *btf = ctx;
+ const char *strs = *btf->strs_data_ptr;
+ const char *str1 = strs + (long)key1;
+ const char *str2 = strs + (long)key2;
return strcmp(str1, str2) == 0;
}
memcpy(types, btf->types_data, btf->hdr->type_len);
memcpy(strs, btf->strs_data, btf->hdr->str_len);
+ /* make hashmap below use btf->strs_data as a source of strings */
+ btf->strs_data_ptr = &btf->strs_data;
+
/* build lookup index for all strings */
hash = hashmap__new(strs_hash_fn, strs_hash_equal_fn, btf);
if (IS_ERR(hash)) {
/* if BTF was created from scratch, all strings are guaranteed to be
* unique and deduplicated
*/
- btf->strs_deduped = btf->hdr->str_len <= 1;
+ if (btf->hdr->str_len == 0)
+ btf->strs_deduped = true;
+ if (!btf->base_btf && btf->hdr->str_len == 1)
+ btf->strs_deduped = true;
/* invalidate raw_data representation */
btf_invalidate_raw_data(btf);
long old_off, new_off, len;
void *p;
+ if (btf->base_btf) {
+ int ret;
+
+ ret = btf__find_str(btf->base_btf, s);
+ if (ret != -ENOENT)
+ return ret;
+ }
+
/* BTF needs to be in a modifiable state to build string lookup index */
if (btf_ensure_modifiable(btf))
return -ENOMEM;
memcpy(p, s, len);
if (hashmap__find(btf->strs_hash, (void *)new_off, (void **)&old_off))
- return old_off;
+ return btf->start_str_off + old_off;
return -ENOENT;
}
void *p;
int err;
+ if (btf->base_btf) {
+ int ret;
+
+ ret = btf__find_str(btf->base_btf, s);
+ if (ret != -ENOENT)
+ return ret;
+ }
+
if (btf_ensure_modifiable(btf))
return -ENOMEM;
err = hashmap__insert(btf->strs_hash, (void *)new_off, (void *)new_off,
HASHMAP_ADD, (const void **)&old_off, NULL);
if (err == -EEXIST)
- return old_off; /* duplicated string, return existing offset */
+ return btf->start_str_off + old_off; /* duplicated string, return existing offset */
if (err)
return err;
btf->hdr->str_len += len; /* new unique string, adjust data length */
- return new_off;
+ return btf->start_str_off + new_off;
}
static void *btf_add_type_mem(struct btf *btf, size_t add_sz)
t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, btf_kflag(t));
}
+static int btf_commit_type(struct btf *btf, int data_sz)
+{
+ int err;
+
+ err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+ if (err)
+ return err;
+
+ btf->hdr->type_len += data_sz;
+ btf->hdr->str_off += data_sz;
+ btf->nr_types++;
+ return btf->start_id + btf->nr_types - 1;
+}
+
/*
* Append new BTF_KIND_INT type with:
* - *name* - non-empty, non-NULL type name;
int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding)
{
struct btf_type *t;
- int sz, err, name_off;
+ int sz, name_off;
/* non-empty name */
if (!name || !name[0])
/* set INT info, we don't allow setting legacy bit offset/size */
*(__u32 *)(t + 1) = (encoding << 24) | (byte_sz * 8);
- err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
- if (err)
- return err;
-
- btf->hdr->type_len += sz;
- btf->hdr->str_off += sz;
- btf->nr_types++;
- return btf->nr_types;
+ return btf_commit_type(btf, sz);
}
/* it's completely legal to append BTF types with type IDs pointing forward to
static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id)
{
struct btf_type *t;
- int sz, name_off = 0, err;
+ int sz, name_off = 0;
if (validate_type_id(ref_type_id))
return -EINVAL;
t->info = btf_type_info(kind, 0, 0);
t->type = ref_type_id;
- err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
- if (err)
- return err;
-
- btf->hdr->type_len += sz;
- btf->hdr->str_off += sz;
- btf->nr_types++;
- return btf->nr_types;
+ return btf_commit_type(btf, sz);
}
/*
{
struct btf_type *t;
struct btf_array *a;
- int sz, err;
+ int sz;
if (validate_type_id(index_type_id) || validate_type_id(elem_type_id))
return -EINVAL;
a->index_type = index_type_id;
a->nelems = nr_elems;
- err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
- if (err)
- return err;
-
- btf->hdr->type_len += sz;
- btf->hdr->str_off += sz;
- btf->nr_types++;
- return btf->nr_types;
+ return btf_commit_type(btf, sz);
}
/* generic STRUCT/UNION append function */
static int btf_add_composite(struct btf *btf, int kind, const char *name, __u32 bytes_sz)
{
struct btf_type *t;
- int sz, err, name_off = 0;
+ int sz, name_off = 0;
if (btf_ensure_modifiable(btf))
return -ENOMEM;
t->info = btf_type_info(kind, 0, 0);
t->size = bytes_sz;
- err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
- if (err)
- return err;
-
- btf->hdr->type_len += sz;
- btf->hdr->str_off += sz;
- btf->nr_types++;
- return btf->nr_types;
+ return btf_commit_type(btf, sz);
}
/*
return btf_add_composite(btf, BTF_KIND_UNION, name, byte_sz);
}
+static struct btf_type *btf_last_type(struct btf *btf)
+{
+ return btf_type_by_id(btf, btf__get_nr_types(btf));
+}
+
/*
* Append new field for the current STRUCT/UNION type with:
* - *name* - name of the field, can be NULL or empty for anonymous field;
/* last type should be union/struct */
if (btf->nr_types == 0)
return -EINVAL;
- t = btf_type_by_id(btf, btf->nr_types);
+ t = btf_last_type(btf);
if (!btf_is_composite(t))
return -EINVAL;
m->offset = bit_offset | (bit_size << 24);
/* btf_add_type_mem can invalidate t pointer */
- t = btf_type_by_id(btf, btf->nr_types);
+ t = btf_last_type(btf);
/* update parent type's vlen and kflag */
t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, is_bitfield || btf_kflag(t));
int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz)
{
struct btf_type *t;
- int sz, err, name_off = 0;
+ int sz, name_off = 0;
/* byte_sz must be power of 2 */
if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 8)
t->info = btf_type_info(BTF_KIND_ENUM, 0, 0);
t->size = byte_sz;
- err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
- if (err)
- return err;
-
- btf->hdr->type_len += sz;
- btf->hdr->str_off += sz;
- btf->nr_types++;
- return btf->nr_types;
+ return btf_commit_type(btf, sz);
}
/*
/* last type should be BTF_KIND_ENUM */
if (btf->nr_types == 0)
return -EINVAL;
- t = btf_type_by_id(btf, btf->nr_types);
+ t = btf_last_type(btf);
if (!btf_is_enum(t))
return -EINVAL;
v->val = value;
/* update parent type's vlen */
- t = btf_type_by_id(btf, btf->nr_types);
+ t = btf_last_type(btf);
btf_type_inc_vlen(t);
btf->hdr->type_len += sz;
int btf__add_func_proto(struct btf *btf, int ret_type_id)
{
struct btf_type *t;
- int sz, err;
+ int sz;
if (validate_type_id(ret_type_id))
return -EINVAL;
t->info = btf_type_info(BTF_KIND_FUNC_PROTO, 0, 0);
t->type = ret_type_id;
- err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
- if (err)
- return err;
-
- btf->hdr->type_len += sz;
- btf->hdr->str_off += sz;
- btf->nr_types++;
- return btf->nr_types;
+ return btf_commit_type(btf, sz);
}
/*
/* last type should be BTF_KIND_FUNC_PROTO */
if (btf->nr_types == 0)
return -EINVAL;
- t = btf_type_by_id(btf, btf->nr_types);
+ t = btf_last_type(btf);
if (!btf_is_func_proto(t))
return -EINVAL;
p->type = type_id;
/* update parent type's vlen */
- t = btf_type_by_id(btf, btf->nr_types);
+ t = btf_last_type(btf);
btf_type_inc_vlen(t);
btf->hdr->type_len += sz;
{
struct btf_type *t;
struct btf_var *v;
- int sz, err, name_off;
+ int sz, name_off;
/* non-empty name */
if (!name || !name[0])
v = btf_var(t);
v->linkage = linkage;
- err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
- if (err)
- return err;
-
- btf->hdr->type_len += sz;
- btf->hdr->str_off += sz;
- btf->nr_types++;
- return btf->nr_types;
+ return btf_commit_type(btf, sz);
}
/*
int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz)
{
struct btf_type *t;
- int sz, err, name_off;
+ int sz, name_off;
/* non-empty name */
if (!name || !name[0])
t->info = btf_type_info(BTF_KIND_DATASEC, 0, 0);
t->size = byte_sz;
- err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
- if (err)
- return err;
-
- btf->hdr->type_len += sz;
- btf->hdr->str_off += sz;
- btf->nr_types++;
- return btf->nr_types;
+ return btf_commit_type(btf, sz);
}
/*
/* last type should be BTF_KIND_DATASEC */
if (btf->nr_types == 0)
return -EINVAL;
- t = btf_type_by_id(btf, btf->nr_types);
+ t = btf_last_type(btf);
if (!btf_is_datasec(t))
return -EINVAL;
v->size = byte_sz;
/* update parent type's vlen */
- t = btf_type_by_id(btf, btf->nr_types);
+ t = btf_last_type(btf);
btf_type_inc_vlen(t);
btf->hdr->type_len += sz;
static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
const struct btf_dedup_opts *opts);
static void btf_dedup_free(struct btf_dedup *d);
+static int btf_dedup_prep(struct btf_dedup *d);
static int btf_dedup_strings(struct btf_dedup *d);
static int btf_dedup_prim_types(struct btf_dedup *d);
static int btf_dedup_struct_types(struct btf_dedup *d);
if (btf_ensure_modifiable(btf))
return -ENOMEM;
+ err = btf_dedup_prep(d);
+ if (err) {
+ pr_debug("btf_dedup_prep failed:%d\n", err);
+ goto done;
+ }
err = btf_dedup_strings(d);
if (err < 0) {
pr_debug("btf_dedup_strings failed:%d\n", err);
__u32 *hypot_list;
size_t hypot_cnt;
size_t hypot_cap;
+ /* Whether hypothetical mapping, if successful, would need to adjust
+ * already canonicalized types (due to a new forward declaration to
+ * concrete type resolution). In such case, during split BTF dedup
+ * candidate type would still be considered as different, because base
+ * BTF is considered to be immutable.
+ */
+ bool hypot_adjust_canon;
/* Various option modifying behavior of algorithm */
struct btf_dedup_opts opts;
-};
-
-struct btf_str_ptr {
- const char *str;
- __u32 new_off;
- bool used;
-};
-
-struct btf_str_ptrs {
- struct btf_str_ptr *ptrs;
- const char *data;
- __u32 cnt;
- __u32 cap;
+ /* temporary strings deduplication state */
+ void *strs_data;
+ size_t strs_cap;
+ size_t strs_len;
+ struct hashmap* strs_hash;
};
static long hash_combine(long h, long value)
for (i = 0; i < d->hypot_cnt; i++)
d->hypot_map[d->hypot_list[i]] = BTF_UNPROCESSED_ID;
d->hypot_cnt = 0;
+ d->hypot_adjust_canon = false;
}
static void btf_dedup_free(struct btf_dedup *d)
{
struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup));
hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn;
- int i, err = 0;
+ int i, err = 0, type_cnt;
if (!d)
return ERR_PTR(-ENOMEM);
goto done;
}
- d->map = malloc(sizeof(__u32) * (1 + btf->nr_types));
+ type_cnt = btf__get_nr_types(btf) + 1;
+ d->map = malloc(sizeof(__u32) * type_cnt);
if (!d->map) {
err = -ENOMEM;
goto done;
}
/* special BTF "void" type is made canonical immediately */
d->map[0] = 0;
- for (i = 1; i <= btf->nr_types; i++) {
+ for (i = 1; i < type_cnt; i++) {
struct btf_type *t = btf_type_by_id(d->btf, i);
/* VAR and DATASEC are never deduped and are self-canonical */
d->map[i] = BTF_UNPROCESSED_ID;
}
- d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types));
+ d->hypot_map = malloc(sizeof(__u32) * type_cnt);
if (!d->hypot_map) {
err = -ENOMEM;
goto done;
}
- for (i = 0; i <= btf->nr_types; i++)
+ for (i = 0; i < type_cnt; i++)
d->hypot_map[i] = BTF_UNPROCESSED_ID;
done:
int i, j, r, rec_size;
struct btf_type *t;
- for (i = 1; i <= d->btf->nr_types; i++) {
- t = btf_type_by_id(d->btf, i);
+ for (i = 0; i < d->btf->nr_types; i++) {
+ t = btf_type_by_id(d->btf, d->btf->start_id + i);
r = fn(&t->name_off, ctx);
if (r)
return r;
return 0;
}
-static int str_sort_by_content(const void *a1, const void *a2)
+static int strs_dedup_remap_str_off(__u32 *str_off_ptr, void *ctx)
{
- const struct btf_str_ptr *p1 = a1;
- const struct btf_str_ptr *p2 = a2;
-
- return strcmp(p1->str, p2->str);
-}
-
-static int str_sort_by_offset(const void *a1, const void *a2)
-{
- const struct btf_str_ptr *p1 = a1;
- const struct btf_str_ptr *p2 = a2;
-
- if (p1->str != p2->str)
- return p1->str < p2->str ? -1 : 1;
- return 0;
-}
-
-static int btf_dedup_str_ptr_cmp(const void *str_ptr, const void *pelem)
-{
- const struct btf_str_ptr *p = pelem;
-
- if (str_ptr != p->str)
- return (const char *)str_ptr < p->str ? -1 : 1;
- return 0;
-}
-
-static int btf_str_mark_as_used(__u32 *str_off_ptr, void *ctx)
-{
- struct btf_str_ptrs *strs;
- struct btf_str_ptr *s;
+ struct btf_dedup *d = ctx;
+ __u32 str_off = *str_off_ptr;
+ long old_off, new_off, len;
+ const char *s;
+ void *p;
+ int err;
- if (*str_off_ptr == 0)
+ /* don't touch empty string or string in main BTF */
+ if (str_off == 0 || str_off < d->btf->start_str_off)
return 0;
- strs = ctx;
- s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt,
- sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp);
- if (!s)
- return -EINVAL;
- s->used = true;
- return 0;
-}
+ s = btf__str_by_offset(d->btf, str_off);
+ if (d->btf->base_btf) {
+ err = btf__find_str(d->btf->base_btf, s);
+ if (err >= 0) {
+ *str_off_ptr = err;
+ return 0;
+ }
+ if (err != -ENOENT)
+ return err;
+ }
-static int btf_str_remap_offset(__u32 *str_off_ptr, void *ctx)
-{
- struct btf_str_ptrs *strs;
- struct btf_str_ptr *s;
+ len = strlen(s) + 1;
- if (*str_off_ptr == 0)
- return 0;
+ new_off = d->strs_len;
+ p = btf_add_mem(&d->strs_data, &d->strs_cap, 1, new_off, BTF_MAX_STR_OFFSET, len);
+ if (!p)
+ return -ENOMEM;
- strs = ctx;
- s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt,
- sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp);
- if (!s)
- return -EINVAL;
- *str_off_ptr = s->new_off;
+ memcpy(p, s, len);
+
+ /* Now attempt to add the string, but only if the string with the same
+ * contents doesn't exist already (HASHMAP_ADD strategy). If such
+ * string exists, we'll get its offset in old_off (that's old_key).
+ */
+ err = hashmap__insert(d->strs_hash, (void *)new_off, (void *)new_off,
+ HASHMAP_ADD, (const void **)&old_off, NULL);
+ if (err == -EEXIST) {
+ *str_off_ptr = d->btf->start_str_off + old_off;
+ } else if (err) {
+ return err;
+ } else {
+ *str_off_ptr = d->btf->start_str_off + new_off;
+ d->strs_len += len;
+ }
return 0;
}
*/
static int btf_dedup_strings(struct btf_dedup *d)
{
- char *start = d->btf->strs_data;
- char *end = start + d->btf->hdr->str_len;
- char *p = start, *tmp_strs = NULL;
- struct btf_str_ptrs strs = {
- .cnt = 0,
- .cap = 0,
- .ptrs = NULL,
- .data = start,
- };
- int i, j, err = 0, grp_idx;
- bool grp_used;
+ char *s;
+ int err;
if (d->btf->strs_deduped)
return 0;
- /* build index of all strings */
- while (p < end) {
- if (strs.cnt + 1 > strs.cap) {
- struct btf_str_ptr *new_ptrs;
-
- strs.cap += max(strs.cnt / 2, 16U);
- new_ptrs = libbpf_reallocarray(strs.ptrs, strs.cap, sizeof(strs.ptrs[0]));
- if (!new_ptrs) {
- err = -ENOMEM;
- goto done;
- }
- strs.ptrs = new_ptrs;
- }
-
- strs.ptrs[strs.cnt].str = p;
- strs.ptrs[strs.cnt].used = false;
-
- p += strlen(p) + 1;
- strs.cnt++;
- }
+ /* temporarily switch to use btf_dedup's strs_data for strings for hash
+ * functions; later we'll just transfer hashmap to struct btf as is,
+ * along the strs_data
+ */
+ d->btf->strs_data_ptr = &d->strs_data;
- /* temporary storage for deduplicated strings */
- tmp_strs = malloc(d->btf->hdr->str_len);
- if (!tmp_strs) {
- err = -ENOMEM;
- goto done;
+ d->strs_hash = hashmap__new(strs_hash_fn, strs_hash_equal_fn, d->btf);
+ if (IS_ERR(d->strs_hash)) {
+ err = PTR_ERR(d->strs_hash);
+ d->strs_hash = NULL;
+ goto err_out;
}
- /* mark all used strings */
- strs.ptrs[0].used = true;
- err = btf_for_each_str_off(d, btf_str_mark_as_used, &strs);
- if (err)
- goto done;
-
- /* sort strings by context, so that we can identify duplicates */
- qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_content);
-
- /*
- * iterate groups of equal strings and if any instance in a group was
- * referenced, emit single instance and remember new offset
- */
- p = tmp_strs;
- grp_idx = 0;
- grp_used = strs.ptrs[0].used;
- /* iterate past end to avoid code duplication after loop */
- for (i = 1; i <= strs.cnt; i++) {
- /*
- * when i == strs.cnt, we want to skip string comparison and go
- * straight to handling last group of strings (otherwise we'd
- * need to handle last group after the loop w/ duplicated code)
- */
- if (i < strs.cnt &&
- !strcmp(strs.ptrs[i].str, strs.ptrs[grp_idx].str)) {
- grp_used = grp_used || strs.ptrs[i].used;
- continue;
- }
+ if (!d->btf->base_btf) {
+ s = btf_add_mem(&d->strs_data, &d->strs_cap, 1, d->strs_len, BTF_MAX_STR_OFFSET, 1);
+ if (!s)
+ return -ENOMEM;
+ /* initial empty string */
+ s[0] = 0;
+ d->strs_len = 1;
- /*
- * this check would have been required after the loop to handle
- * last group of strings, but due to <= condition in a loop
- * we avoid that duplication
+ /* insert empty string; we won't be looking it up during strings
+ * dedup, but it's good to have it for generic BTF string lookups
*/
- if (grp_used) {
- int new_off = p - tmp_strs;
- __u32 len = strlen(strs.ptrs[grp_idx].str);
-
- memmove(p, strs.ptrs[grp_idx].str, len + 1);
- for (j = grp_idx; j < i; j++)
- strs.ptrs[j].new_off = new_off;
- p += len + 1;
- }
-
- if (i < strs.cnt) {
- grp_idx = i;
- grp_used = strs.ptrs[i].used;
- }
+ err = hashmap__insert(d->strs_hash, (void *)0, (void *)0,
+ HASHMAP_ADD, NULL, NULL);
+ if (err)
+ goto err_out;
}
- /* replace original strings with deduped ones */
- d->btf->hdr->str_len = p - tmp_strs;
- memmove(start, tmp_strs, d->btf->hdr->str_len);
- end = start + d->btf->hdr->str_len;
-
- /* restore original order for further binary search lookups */
- qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_offset);
-
/* remap string offsets */
- err = btf_for_each_str_off(d, btf_str_remap_offset, &strs);
+ err = btf_for_each_str_off(d, strs_dedup_remap_str_off, d);
if (err)
- goto done;
+ goto err_out;
- d->btf->hdr->str_len = end - start;
+ /* replace BTF string data and hash with deduped ones */
+ free(d->btf->strs_data);
+ hashmap__free(d->btf->strs_hash);
+ d->btf->strs_data = d->strs_data;
+ d->btf->strs_data_cap = d->strs_cap;
+ d->btf->hdr->str_len = d->strs_len;
+ d->btf->strs_hash = d->strs_hash;
+ /* now point strs_data_ptr back to btf->strs_data */
+ d->btf->strs_data_ptr = &d->btf->strs_data;
+
+ d->strs_data = d->strs_hash = NULL;
+ d->strs_len = d->strs_cap = 0;
d->btf->strs_deduped = true;
+ return 0;
+
+err_out:
+ free(d->strs_data);
+ hashmap__free(d->strs_hash);
+ d->strs_data = d->strs_hash = NULL;
+ d->strs_len = d->strs_cap = 0;
+
+ /* restore strings pointer for existing d->btf->strs_hash back */
+ d->btf->strs_data_ptr = &d->strs_data;
-done:
- free(tmp_strs);
- free(strs.ptrs);
return err;
}
return true;
}
+/* Prepare split BTF for deduplication by calculating hashes of base BTF's
+ * types and initializing the rest of the state (canonical type mapping) for
+ * the fixed base BTF part.
+ */
+static int btf_dedup_prep(struct btf_dedup *d)
+{
+ struct btf_type *t;
+ int type_id;
+ long h;
+
+ if (!d->btf->base_btf)
+ return 0;
+
+ for (type_id = 1; type_id < d->btf->start_id; type_id++) {
+ t = btf_type_by_id(d->btf, type_id);
+
+ /* all base BTF types are self-canonical by definition */
+ d->map[type_id] = type_id;
+
+ switch (btf_kind(t)) {
+ case BTF_KIND_VAR:
+ case BTF_KIND_DATASEC:
+ /* VAR and DATASEC are never hash/deduplicated */
+ continue;
+ case BTF_KIND_CONST:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_PTR:
+ case BTF_KIND_FWD:
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_FUNC:
+ h = btf_hash_common(t);
+ break;
+ case BTF_KIND_INT:
+ h = btf_hash_int(t);
+ break;
+ case BTF_KIND_ENUM:
+ h = btf_hash_enum(t);
+ break;
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ h = btf_hash_struct(t);
+ break;
+ case BTF_KIND_ARRAY:
+ h = btf_hash_array(t);
+ break;
+ case BTF_KIND_FUNC_PROTO:
+ h = btf_hash_fnproto(t);
+ break;
+ default:
+ pr_debug("unknown kind %d for type [%d]\n", btf_kind(t), type_id);
+ return -EINVAL;
+ }
+ if (btf_dedup_table_add(d, h, type_id))
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
/*
* Deduplicate primitive types, that can't reference other types, by calculating
* their type signature hash and comparing them with any possible canonical
{
int i, err;
- for (i = 1; i <= d->btf->nr_types; i++) {
- err = btf_dedup_prim_type(d, i);
+ for (i = 0; i < d->btf->nr_types; i++) {
+ err = btf_dedup_prim_type(d, d->btf->start_id + i);
if (err)
return err;
}
return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT;
}
+/* Check if given two types are identical ARRAY definitions */
+static int btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2)
+{
+ struct btf_type *t1, *t2;
+
+ t1 = btf_type_by_id(d->btf, id1);
+ t2 = btf_type_by_id(d->btf, id2);
+ if (!btf_is_array(t1) || !btf_is_array(t2))
+ return 0;
+
+ return btf_equal_array(t1, t2);
+}
+
/*
* Check equivalence of BTF type graph formed by candidate struct/union (we'll
* call it "candidate graph" in this description for brevity) to a type graph
canon_id = resolve_fwd_id(d, canon_id);
hypot_type_id = d->hypot_map[canon_id];
- if (hypot_type_id <= BTF_MAX_NR_TYPES)
- return hypot_type_id == cand_id;
+ if (hypot_type_id <= BTF_MAX_NR_TYPES) {
+ /* In some cases compiler will generate different DWARF types
+ * for *identical* array type definitions and use them for
+ * different fields within the *same* struct. This breaks type
+ * equivalence check, which makes an assumption that candidate
+ * types sub-graph has a consistent and deduped-by-compiler
+ * types within a single CU. So work around that by explicitly
+ * allowing identical array types here.
+ */
+ return hypot_type_id == cand_id ||
+ btf_dedup_identical_arrays(d, hypot_type_id, cand_id);
+ }
if (btf_dedup_hypot_map_add(d, canon_id, cand_id))
return -ENOMEM;
} else {
real_kind = cand_kind;
fwd_kind = btf_fwd_kind(canon_type);
+ /* we'd need to resolve base FWD to STRUCT/UNION */
+ if (fwd_kind == real_kind && canon_id < d->btf->start_id)
+ d->hypot_adjust_canon = true;
}
return fwd_kind == real_kind;
}
return 0;
cand_arr = btf_array(cand_type);
canon_arr = btf_array(canon_type);
- eq = btf_dedup_is_equiv(d,
- cand_arr->index_type, canon_arr->index_type);
+ eq = btf_dedup_is_equiv(d, cand_arr->index_type, canon_arr->index_type);
if (eq <= 0)
return eq;
return btf_dedup_is_equiv(d, cand_arr->type, canon_arr->type);
*/
static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
{
- __u32 cand_type_id, targ_type_id;
+ __u32 canon_type_id, targ_type_id;
__u16 t_kind, c_kind;
__u32 t_id, c_id;
int i;
for (i = 0; i < d->hypot_cnt; i++) {
- cand_type_id = d->hypot_list[i];
- targ_type_id = d->hypot_map[cand_type_id];
+ canon_type_id = d->hypot_list[i];
+ targ_type_id = d->hypot_map[canon_type_id];
t_id = resolve_type_id(d, targ_type_id);
- c_id = resolve_type_id(d, cand_type_id);
+ c_id = resolve_type_id(d, canon_type_id);
t_kind = btf_kind(btf__type_by_id(d->btf, t_id));
c_kind = btf_kind(btf__type_by_id(d->btf, c_id));
/*
* stability is not a requirement for STRUCT/UNION equivalence
* checks, though.
*/
+
+ /* if it's the split BTF case, we still need to point base FWD
+ * to STRUCT/UNION in a split BTF, because FWDs from split BTF
+ * will be resolved against base FWD. If we don't point base
+ * canonical FWD to the resolved STRUCT/UNION, then all the
+ * FWDs in split BTF won't be correctly resolved to a proper
+ * STRUCT/UNION.
+ */
if (t_kind != BTF_KIND_FWD && c_kind == BTF_KIND_FWD)
d->map[c_id] = t_id;
- else if (t_kind == BTF_KIND_FWD && c_kind != BTF_KIND_FWD)
+
+ /* if graph equivalence determined that we'd need to adjust
+ * base canonical types, then we need to only point base FWDs
+ * to STRUCTs/UNIONs and do no more modifications. For all
+ * other purposes the type graphs were not equivalent.
+ */
+ if (d->hypot_adjust_canon)
+ continue;
+
+ if (t_kind == BTF_KIND_FWD && c_kind != BTF_KIND_FWD)
d->map[t_id] = c_id;
if ((t_kind == BTF_KIND_STRUCT || t_kind == BTF_KIND_UNION) &&
return eq;
if (!eq)
continue;
- new_id = cand_id;
btf_dedup_merge_hypot_map(d);
+ if (d->hypot_adjust_canon) /* not really equivalent */
+ continue;
+ new_id = cand_id;
break;
}
{
int i, err;
- for (i = 1; i <= d->btf->nr_types; i++) {
- err = btf_dedup_struct_type(d, i);
+ for (i = 0; i < d->btf->nr_types; i++) {
+ err = btf_dedup_struct_type(d, d->btf->start_id + i);
if (err)
return err;
}
{
int i, err;
- for (i = 1; i <= d->btf->nr_types; i++) {
- err = btf_dedup_ref_type(d, i);
+ for (i = 0; i < d->btf->nr_types; i++) {
+ err = btf_dedup_ref_type(d, d->btf->start_id + i);
if (err < 0)
return err;
}
static int btf_dedup_compact_types(struct btf_dedup *d)
{
__u32 *new_offs;
- __u32 next_type_id = 1;
+ __u32 next_type_id = d->btf->start_id;
+ const struct btf_type *t;
void *p;
- int i, len;
+ int i, id, len;
/* we are going to reuse hypot_map to store compaction remapping */
d->hypot_map[0] = 0;
- for (i = 1; i <= d->btf->nr_types; i++)
- d->hypot_map[i] = BTF_UNPROCESSED_ID;
+ /* base BTF types are not renumbered */
+ for (id = 1; id < d->btf->start_id; id++)
+ d->hypot_map[id] = id;
+ for (i = 0, id = d->btf->start_id; i < d->btf->nr_types; i++, id++)
+ d->hypot_map[id] = BTF_UNPROCESSED_ID;
p = d->btf->types_data;
- for (i = 1; i <= d->btf->nr_types; i++) {
- if (d->map[i] != i)
+ for (i = 0, id = d->btf->start_id; i < d->btf->nr_types; i++, id++) {
+ if (d->map[id] != id)
continue;
- len = btf_type_size(btf__type_by_id(d->btf, i));
+ t = btf__type_by_id(d->btf, id);
+ len = btf_type_size(t);
if (len < 0)
return len;
- memmove(p, btf__type_by_id(d->btf, i), len);
- d->hypot_map[i] = next_type_id;
- d->btf->type_offs[next_type_id] = p - d->btf->types_data;
+ memmove(p, t, len);
+ d->hypot_map[id] = next_type_id;
+ d->btf->type_offs[next_type_id - d->btf->start_id] = p - d->btf->types_data;
p += len;
next_type_id++;
}
/* shrink struct btf's internal types index and update btf_header */
- d->btf->nr_types = next_type_id - 1;
- d->btf->type_offs_cap = d->btf->nr_types + 1;
+ d->btf->nr_types = next_type_id - d->btf->start_id;
+ d->btf->type_offs_cap = d->btf->nr_types;
d->btf->hdr->type_len = p - d->btf->types_data;
new_offs = libbpf_reallocarray(d->btf->type_offs, d->btf->type_offs_cap,
sizeof(*new_offs));
- if (!new_offs)
+ if (d->btf->type_offs_cap && !new_offs)
return -ENOMEM;
d->btf->type_offs = new_offs;
d->btf->hdr->str_off = d->btf->hdr->type_len;
{
int i, r;
- for (i = 1; i <= d->btf->nr_types; i++) {
- r = btf_dedup_remap_type(d, i);
+ for (i = 0; i < d->btf->nr_types; i++) {
+ r = btf_dedup_remap_type(d, d->btf->start_id + i);
if (r < 0)
return r;
}
};
LIBBPF_API void btf__free(struct btf *btf);
+
LIBBPF_API struct btf *btf__new(const void *data, __u32 size);
+LIBBPF_API struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf);
LIBBPF_API struct btf *btf__new_empty(void);
+LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf);
+
LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext);
+LIBBPF_API struct btf *btf__parse_split(const char *path, struct btf *base_btf);
LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext);
+LIBBPF_API struct btf *btf__parse_elf_split(const char *path, struct btf *base_btf);
LIBBPF_API struct btf *btf__parse_raw(const char *path);
+LIBBPF_API struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf);
+
LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
LIBBPF_API int btf__load(struct btf *btf);
LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
perf_buffer__consume_buffer;
xsk_socket__create_shared;
} LIBBPF_0.1.0;
+
+LIBBPF_0.3.0 {
+ global:
+ btf__parse_elf_split;
+ btf__parse_raw_split;
+ btf__parse_split;
+ btf__new_empty_split;
+ btf__new_split;
+} LIBBPF_0.2.0;
break;
case BPF_MAP_TYPE_SK_STORAGE:
case BPF_MAP_TYPE_INODE_STORAGE:
+ case BPF_MAP_TYPE_TASK_STORAGE:
btf_key_type_id = 1;
btf_value_type_id = 3;
value_size = 8;
include ../scripts/Makefile.arch
# always use the host compiler
-ifneq ($(LLVM),)
-HOSTAR ?= llvm-ar
-HOSTCC ?= clang
-HOSTLD ?= ld.lld
-else
-HOSTAR ?= ar
-HOSTCC ?= gcc
-HOSTLD ?= ld
-endif
AR = $(HOSTAR)
CC = $(HOSTCC)
LD = $(HOSTLD)
LD += $(EXTRA_LDFLAGS)
-HOSTCC ?= gcc
-HOSTLD ?= ld
-HOSTAR ?= ar
-
PKG_CONFIG = $(CROSS_COMPILE)pkg-config
LLVM_CONFIG ?= llvm-config
CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc-
CROSS_COMPILE ?= $(CROSS)
LD = $(CC)
-HOSTCC = gcc
# check if compiler option is supported
cc-supports = ${shell if $(CC) ${1} -S -o /dev/null -x c /dev/null > /dev/null 2>&1; then echo "$(1)"; fi;}
$(call allow-override,CXX,$(CROSS_COMPILE)g++)
$(call allow-override,STRIP,$(CROSS_COMPILE)strip)
+ifneq ($(LLVM),)
+HOSTAR ?= llvm-ar
+HOSTCC ?= clang
+HOSTLD ?= ld.lld
+else
+HOSTAR ?= ar
+HOSTCC ?= gcc
+HOSTLD ?= ld
+endif
+
ifeq ($(CC_NO_CLANG), 1)
EXTRA_WARNINGS += -Wstrict-aliasing=3
endif
fixdep
test_dev_cgroup
/test_progs*
-test_tcpbpf_user
test_verifier_log
feature
test_sock
# Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
- test_verifier_log test_dev_cgroup test_tcpbpf_user \
+ test_verifier_log test_dev_cgroup \
test_sock test_sockmap get_cgroup_id_user test_socket_cookie \
test_cgroup_storage \
test_netcnt test_tcpnotify_user test_sysctl \
$(OUTPUT)/test_sock_addr: cgroup_helpers.c
$(OUTPUT)/test_socket_cookie: cgroup_helpers.c
$(OUTPUT)/test_sockmap: cgroup_helpers.c
-$(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
$(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c
$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
$(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
TRUNNER_BPF_PROGS_DIR := progs
TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \
network_helpers.c testing_helpers.c \
- flow_dissector_load.h
+ btf_helpers.c flow_dissector_load.h
TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \
$(wildcard progs/btf_dump_test_case_*.c)
TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <stdio.h>
+#include <errno.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include "test_progs.h"
+
+static const char * const btf_kind_str_mapping[] = {
+ [BTF_KIND_UNKN] = "UNKNOWN",
+ [BTF_KIND_INT] = "INT",
+ [BTF_KIND_PTR] = "PTR",
+ [BTF_KIND_ARRAY] = "ARRAY",
+ [BTF_KIND_STRUCT] = "STRUCT",
+ [BTF_KIND_UNION] = "UNION",
+ [BTF_KIND_ENUM] = "ENUM",
+ [BTF_KIND_FWD] = "FWD",
+ [BTF_KIND_TYPEDEF] = "TYPEDEF",
+ [BTF_KIND_VOLATILE] = "VOLATILE",
+ [BTF_KIND_CONST] = "CONST",
+ [BTF_KIND_RESTRICT] = "RESTRICT",
+ [BTF_KIND_FUNC] = "FUNC",
+ [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO",
+ [BTF_KIND_VAR] = "VAR",
+ [BTF_KIND_DATASEC] = "DATASEC",
+};
+
+static const char *btf_kind_str(__u16 kind)
+{
+ if (kind > BTF_KIND_DATASEC)
+ return "UNKNOWN";
+ return btf_kind_str_mapping[kind];
+}
+
+static const char *btf_int_enc_str(__u8 encoding)
+{
+ switch (encoding) {
+ case 0:
+ return "(none)";
+ case BTF_INT_SIGNED:
+ return "SIGNED";
+ case BTF_INT_CHAR:
+ return "CHAR";
+ case BTF_INT_BOOL:
+ return "BOOL";
+ default:
+ return "UNKN";
+ }
+}
+
+static const char *btf_var_linkage_str(__u32 linkage)
+{
+ switch (linkage) {
+ case BTF_VAR_STATIC:
+ return "static";
+ case BTF_VAR_GLOBAL_ALLOCATED:
+ return "global-alloc";
+ default:
+ return "(unknown)";
+ }
+}
+
+static const char *btf_func_linkage_str(const struct btf_type *t)
+{
+ switch (btf_vlen(t)) {
+ case BTF_FUNC_STATIC:
+ return "static";
+ case BTF_FUNC_GLOBAL:
+ return "global";
+ case BTF_FUNC_EXTERN:
+ return "extern";
+ default:
+ return "(unknown)";
+ }
+}
+
+static const char *btf_str(const struct btf *btf, __u32 off)
+{
+ if (!off)
+ return "(anon)";
+ return btf__str_by_offset(btf, off) ?: "(invalid)";
+}
+
+int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id)
+{
+ const struct btf_type *t;
+ int kind, i;
+ __u32 vlen;
+
+ t = btf__type_by_id(btf, id);
+ if (!t)
+ return -EINVAL;
+
+ vlen = btf_vlen(t);
+ kind = btf_kind(t);
+
+ fprintf(out, "[%u] %s '%s'", id, btf_kind_str(kind), btf_str(btf, t->name_off));
+
+ switch (kind) {
+ case BTF_KIND_INT:
+ fprintf(out, " size=%u bits_offset=%u nr_bits=%u encoding=%s",
+ t->size, btf_int_offset(t), btf_int_bits(t),
+ btf_int_enc_str(btf_int_encoding(t)));
+ break;
+ case BTF_KIND_PTR:
+ case BTF_KIND_CONST:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_TYPEDEF:
+ fprintf(out, " type_id=%u", t->type);
+ break;
+ case BTF_KIND_ARRAY: {
+ const struct btf_array *arr = btf_array(t);
+
+ fprintf(out, " type_id=%u index_type_id=%u nr_elems=%u",
+ arr->type, arr->index_type, arr->nelems);
+ break;
+ }
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ const struct btf_member *m = btf_members(t);
+
+ fprintf(out, " size=%u vlen=%u", t->size, vlen);
+ for (i = 0; i < vlen; i++, m++) {
+ __u32 bit_off, bit_sz;
+
+ bit_off = btf_member_bit_offset(t, i);
+ bit_sz = btf_member_bitfield_size(t, i);
+ fprintf(out, "\n\t'%s' type_id=%u bits_offset=%u",
+ btf_str(btf, m->name_off), m->type, bit_off);
+ if (bit_sz)
+ fprintf(out, " bitfield_size=%u", bit_sz);
+ }
+ break;
+ }
+ case BTF_KIND_ENUM: {
+ const struct btf_enum *v = btf_enum(t);
+
+ fprintf(out, " size=%u vlen=%u", t->size, vlen);
+ for (i = 0; i < vlen; i++, v++) {
+ fprintf(out, "\n\t'%s' val=%u",
+ btf_str(btf, v->name_off), v->val);
+ }
+ break;
+ }
+ case BTF_KIND_FWD:
+ fprintf(out, " fwd_kind=%s", btf_kflag(t) ? "union" : "struct");
+ break;
+ case BTF_KIND_FUNC:
+ fprintf(out, " type_id=%u linkage=%s", t->type, btf_func_linkage_str(t));
+ break;
+ case BTF_KIND_FUNC_PROTO: {
+ const struct btf_param *p = btf_params(t);
+
+ fprintf(out, " ret_type_id=%u vlen=%u", t->type, vlen);
+ for (i = 0; i < vlen; i++, p++) {
+ fprintf(out, "\n\t'%s' type_id=%u",
+ btf_str(btf, p->name_off), p->type);
+ }
+ break;
+ }
+ case BTF_KIND_VAR:
+ fprintf(out, " type_id=%u, linkage=%s",
+ t->type, btf_var_linkage_str(btf_var(t)->linkage));
+ break;
+ case BTF_KIND_DATASEC: {
+ const struct btf_var_secinfo *v = btf_var_secinfos(t);
+
+ fprintf(out, " size=%u vlen=%u", t->size, vlen);
+ for (i = 0; i < vlen; i++, v++) {
+ fprintf(out, "\n\ttype_id=%u offset=%u size=%u",
+ v->type, v->offset, v->size);
+ }
+ break;
+ }
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+/* Print raw BTF type dump into a local buffer and return string pointer back.
+ * Buffer *will* be overwritten by subsequent btf_type_raw_dump() calls
+ */
+const char *btf_type_raw_dump(const struct btf *btf, int type_id)
+{
+ static char buf[16 * 1024];
+ FILE *buf_file;
+
+ buf_file = fmemopen(buf, sizeof(buf) - 1, "w");
+ if (!buf_file) {
+ fprintf(stderr, "Failed to open memstream: %d\n", errno);
+ return NULL;
+ }
+
+ fprintf_btf_type_raw(buf_file, btf, type_id);
+ fflush(buf_file);
+ fclose(buf_file);
+
+ return buf;
+}
+
+int btf_validate_raw(struct btf *btf, int nr_types, const char *exp_types[])
+{
+ int i;
+ bool ok = true;
+
+ ASSERT_EQ(btf__get_nr_types(btf), nr_types, "btf_nr_types");
+
+ for (i = 1; i <= nr_types; i++) {
+ if (!ASSERT_STREQ(btf_type_raw_dump(btf, i), exp_types[i - 1], "raw_dump"))
+ ok = false;
+ }
+
+ return ok;
+}
+
+static void btf_dump_printf(void *ctx, const char *fmt, va_list args)
+{
+ vfprintf(ctx, fmt, args);
+}
+
+/* Print BTF-to-C dump into a local buffer and return string pointer back.
+ * Buffer *will* be overwritten by subsequent btf_type_raw_dump() calls
+ */
+const char *btf_type_c_dump(const struct btf *btf)
+{
+ static char buf[16 * 1024];
+ FILE *buf_file;
+ struct btf_dump *d = NULL;
+ struct btf_dump_opts opts = {};
+ int err, i;
+
+ buf_file = fmemopen(buf, sizeof(buf) - 1, "w");
+ if (!buf_file) {
+ fprintf(stderr, "Failed to open memstream: %d\n", errno);
+ return NULL;
+ }
+
+ opts.ctx = buf_file;
+ d = btf_dump__new(btf, NULL, &opts, btf_dump_printf);
+ if (libbpf_get_error(d)) {
+ fprintf(stderr, "Failed to create btf_dump instance: %ld\n", libbpf_get_error(d));
+ return NULL;
+ }
+
+ for (i = 1; i <= btf__get_nr_types(btf); i++) {
+ err = btf_dump__dump_type(d, i);
+ if (err) {
+ fprintf(stderr, "Failed to dump type [%d]: %d\n", i, err);
+ return NULL;
+ }
+ }
+
+ fflush(buf_file);
+ fclose(buf_file);
+ return buf;
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+#ifndef __BTF_HELPERS_H
+#define __BTF_HELPERS_H
+
+#include <stdio.h>
+#include <bpf/btf.h>
+
+int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id);
+const char *btf_type_raw_dump(const struct btf *btf, int type_id);
+int btf_validate_raw(struct btf *btf, int nr_types, const char *exp_types[]);
+
+#define VALIDATE_RAW_BTF(btf, raw_types...) \
+ btf_validate_raw(btf, \
+ sizeof((const char *[]){raw_types})/sizeof(void *),\
+ (const char *[]){raw_types})
+
+const char *btf_type_c_dump(const struct btf *btf);
+#endif
const void *test_btf_data, *expect_btf_data;
const char *ret_test_next_str, *ret_expect_next_str;
const char *test_strs, *expect_strs;
- const char *test_str_cur, *test_str_end;
+ const char *test_str_cur;
const char *expect_str_cur, *expect_str_end;
unsigned int raw_btf_size;
void *raw_btf;
goto done;
}
- test_str_cur = test_strs;
- test_str_end = test_strs + test_hdr->str_len;
expect_str_cur = expect_strs;
expect_str_end = expect_strs + expect_hdr->str_len;
- while (test_str_cur < test_str_end && expect_str_cur < expect_str_end) {
+ while (expect_str_cur < expect_str_end) {
size_t test_len, expect_len;
+ int off;
+
+ off = btf__find_str(test_btf, expect_str_cur);
+ if (CHECK(off < 0, "exp str '%s' not found: %d\n", expect_str_cur, off)) {
+ err = -1;
+ goto done;
+ }
+ test_str_cur = btf__str_by_offset(test_btf, off);
test_len = strlen(test_str_cur);
expect_len = strlen(expect_str_cur);
err = -1;
goto done;
}
- test_str_cur += test_len + 1;
expect_str_cur += expect_len + 1;
}
- if (CHECK(test_str_cur != test_str_end,
- "test_str_cur:%p != test_str_end:%p",
- test_str_cur, test_str_end)) {
- err = -1;
- goto done;
- }
test_nr_types = btf__get_nr_types(test_btf);
expect_nr_types = btf__get_nr_types(expect_btf);
err = -1;
goto done;
}
- if (CHECK(memcmp((void *)test_type,
- (void *)expect_type,
- test_size),
- "type #%d: contents differ", i)) {
+ if (CHECK(btf_kind(test_type) != btf_kind(expect_type),
+ "type %d kind: exp %d != got %u\n",
+ i, btf_kind(expect_type), btf_kind(test_type))) {
+ err = -1;
+ goto done;
+ }
+ if (CHECK(test_type->info != expect_type->info,
+ "type %d info: exp %d != got %u\n",
+ i, expect_type->info, test_type->info)) {
+ err = -1;
+ goto done;
+ }
+ if (CHECK(test_type->size != expect_type->size,
+ "type %d size/type: exp %d != got %u\n",
+ i, expect_type->size, test_type->size)) {
err = -1;
goto done;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "btf_helpers.h"
+
+static void test_split_simple() {
+ const struct btf_type *t;
+ struct btf *btf1, *btf2;
+ int str_off, err;
+
+ btf1 = btf__new_empty();
+ if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+ return;
+
+ btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+ btf__add_int(btf1, "int", 4, BTF_INT_SIGNED); /* [1] int */
+ btf__add_ptr(btf1, 1); /* [2] ptr to int */
+ btf__add_struct(btf1, "s1", 4); /* [3] struct s1 { */
+ btf__add_field(btf1, "f1", 1, 0, 0); /* int f1; */
+ /* } */
+
+ VALIDATE_RAW_BTF(
+ btf1,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=1",
+ "[3] STRUCT 's1' size=4 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0");
+
+ ASSERT_STREQ(btf_type_c_dump(btf1), "\
+struct s1 {\n\
+ int f1;\n\
+};\n\n", "c_dump");
+
+ btf2 = btf__new_empty_split(btf1);
+ if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+ goto cleanup;
+
+ /* pointer size should be "inherited" from main BTF */
+ ASSERT_EQ(btf__pointer_size(btf2), 8, "inherit_ptr_sz");
+
+ str_off = btf__find_str(btf2, "int");
+ ASSERT_NEQ(str_off, -ENOENT, "str_int_missing");
+
+ t = btf__type_by_id(btf2, 1);
+ if (!ASSERT_OK_PTR(t, "int_type"))
+ goto cleanup;
+ ASSERT_EQ(btf_is_int(t), true, "int_kind");
+ ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "int", "int_name");
+
+ btf__add_struct(btf2, "s2", 16); /* [4] struct s2 { */
+ btf__add_field(btf2, "f1", 6, 0, 0); /* struct s1 f1; */
+ btf__add_field(btf2, "f2", 5, 32, 0); /* int f2; */
+ btf__add_field(btf2, "f3", 2, 64, 0); /* int *f3; */
+ /* } */
+
+ /* duplicated int */
+ btf__add_int(btf2, "int", 4, BTF_INT_SIGNED); /* [5] int */
+
+ /* duplicated struct s1 */
+ btf__add_struct(btf2, "s1", 4); /* [6] struct s1 { */
+ btf__add_field(btf2, "f1", 5, 0, 0); /* int f1; */
+ /* } */
+
+ VALIDATE_RAW_BTF(
+ btf2,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=1",
+ "[3] STRUCT 's1' size=4 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0",
+ "[4] STRUCT 's2' size=16 vlen=3\n"
+ "\t'f1' type_id=6 bits_offset=0\n"
+ "\t'f2' type_id=5 bits_offset=32\n"
+ "\t'f3' type_id=2 bits_offset=64",
+ "[5] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[6] STRUCT 's1' size=4 vlen=1\n"
+ "\t'f1' type_id=5 bits_offset=0");
+
+ ASSERT_STREQ(btf_type_c_dump(btf2), "\
+struct s1 {\n\
+ int f1;\n\
+};\n\
+\n\
+struct s1___2 {\n\
+ int f1;\n\
+};\n\
+\n\
+struct s2 {\n\
+ struct s1___2 f1;\n\
+ int f2;\n\
+ int *f3;\n\
+};\n\n", "c_dump");
+
+ err = btf__dedup(btf2, NULL, NULL);
+ if (!ASSERT_OK(err, "btf_dedup"))
+ goto cleanup;
+
+ VALIDATE_RAW_BTF(
+ btf2,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=1",
+ "[3] STRUCT 's1' size=4 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0",
+ "[4] STRUCT 's2' size=16 vlen=3\n"
+ "\t'f1' type_id=3 bits_offset=0\n"
+ "\t'f2' type_id=1 bits_offset=32\n"
+ "\t'f3' type_id=2 bits_offset=64");
+
+ ASSERT_STREQ(btf_type_c_dump(btf2), "\
+struct s1 {\n\
+ int f1;\n\
+};\n\
+\n\
+struct s2 {\n\
+ struct s1 f1;\n\
+ int f2;\n\
+ int *f3;\n\
+};\n\n", "c_dump");
+
+cleanup:
+ btf__free(btf2);
+ btf__free(btf1);
+}
+
+static void test_split_fwd_resolve() {
+ struct btf *btf1, *btf2;
+ int err;
+
+ btf1 = btf__new_empty();
+ if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+ return;
+
+ btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+ btf__add_int(btf1, "int", 4, BTF_INT_SIGNED); /* [1] int */
+ btf__add_ptr(btf1, 4); /* [2] ptr to struct s1 */
+ btf__add_ptr(btf1, 5); /* [3] ptr to struct s2 */
+ btf__add_struct(btf1, "s1", 16); /* [4] struct s1 { */
+ btf__add_field(btf1, "f1", 2, 0, 0); /* struct s1 *f1; */
+ btf__add_field(btf1, "f2", 3, 64, 0); /* struct s2 *f2; */
+ /* } */
+ btf__add_struct(btf1, "s2", 4); /* [5] struct s2 { */
+ btf__add_field(btf1, "f1", 1, 0, 0); /* int f1; */
+ /* } */
+
+ VALIDATE_RAW_BTF(
+ btf1,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=4",
+ "[3] PTR '(anon)' type_id=5",
+ "[4] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=2 bits_offset=0\n"
+ "\t'f2' type_id=3 bits_offset=64",
+ "[5] STRUCT 's2' size=4 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0");
+
+ btf2 = btf__new_empty_split(btf1);
+ if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+ goto cleanup;
+
+ btf__add_int(btf2, "int", 4, BTF_INT_SIGNED); /* [6] int */
+ btf__add_ptr(btf2, 10); /* [7] ptr to struct s1 */
+ btf__add_fwd(btf2, "s2", BTF_FWD_STRUCT); /* [8] fwd for struct s2 */
+ btf__add_ptr(btf2, 8); /* [9] ptr to fwd struct s2 */
+ btf__add_struct(btf2, "s1", 16); /* [10] struct s1 { */
+ btf__add_field(btf2, "f1", 7, 0, 0); /* struct s1 *f1; */
+ btf__add_field(btf2, "f2", 9, 64, 0); /* struct s2 *f2; */
+ /* } */
+
+ VALIDATE_RAW_BTF(
+ btf2,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=4",
+ "[3] PTR '(anon)' type_id=5",
+ "[4] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=2 bits_offset=0\n"
+ "\t'f2' type_id=3 bits_offset=64",
+ "[5] STRUCT 's2' size=4 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0",
+ "[6] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[7] PTR '(anon)' type_id=10",
+ "[8] FWD 's2' fwd_kind=struct",
+ "[9] PTR '(anon)' type_id=8",
+ "[10] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=7 bits_offset=0\n"
+ "\t'f2' type_id=9 bits_offset=64");
+
+ err = btf__dedup(btf2, NULL, NULL);
+ if (!ASSERT_OK(err, "btf_dedup"))
+ goto cleanup;
+
+ VALIDATE_RAW_BTF(
+ btf2,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=4",
+ "[3] PTR '(anon)' type_id=5",
+ "[4] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=2 bits_offset=0\n"
+ "\t'f2' type_id=3 bits_offset=64",
+ "[5] STRUCT 's2' size=4 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0");
+
+cleanup:
+ btf__free(btf2);
+ btf__free(btf1);
+}
+
+static void test_split_struct_duped() {
+ struct btf *btf1, *btf2;
+ int err;
+
+ btf1 = btf__new_empty();
+ if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+ return;
+
+ btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+ btf__add_int(btf1, "int", 4, BTF_INT_SIGNED); /* [1] int */
+ btf__add_ptr(btf1, 5); /* [2] ptr to struct s1 */
+ btf__add_fwd(btf1, "s2", BTF_FWD_STRUCT); /* [3] fwd for struct s2 */
+ btf__add_ptr(btf1, 3); /* [4] ptr to fwd struct s2 */
+ btf__add_struct(btf1, "s1", 16); /* [5] struct s1 { */
+ btf__add_field(btf1, "f1", 2, 0, 0); /* struct s1 *f1; */
+ btf__add_field(btf1, "f2", 4, 64, 0); /* struct s2 *f2; */
+ /* } */
+
+ VALIDATE_RAW_BTF(
+ btf1,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=5",
+ "[3] FWD 's2' fwd_kind=struct",
+ "[4] PTR '(anon)' type_id=3",
+ "[5] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=2 bits_offset=0\n"
+ "\t'f2' type_id=4 bits_offset=64");
+
+ btf2 = btf__new_empty_split(btf1);
+ if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+ goto cleanup;
+
+ btf__add_int(btf2, "int", 4, BTF_INT_SIGNED); /* [6] int */
+ btf__add_ptr(btf2, 10); /* [7] ptr to struct s1 */
+ btf__add_fwd(btf2, "s2", BTF_FWD_STRUCT); /* [8] fwd for struct s2 */
+ btf__add_ptr(btf2, 11); /* [9] ptr to struct s2 */
+ btf__add_struct(btf2, "s1", 16); /* [10] struct s1 { */
+ btf__add_field(btf2, "f1", 7, 0, 0); /* struct s1 *f1; */
+ btf__add_field(btf2, "f2", 9, 64, 0); /* struct s2 *f2; */
+ /* } */
+ btf__add_struct(btf2, "s2", 40); /* [11] struct s2 { */
+ btf__add_field(btf2, "f1", 7, 0, 0); /* struct s1 *f1; */
+ btf__add_field(btf2, "f2", 9, 64, 0); /* struct s2 *f2; */
+ btf__add_field(btf2, "f3", 6, 128, 0); /* int f3; */
+ btf__add_field(btf2, "f4", 10, 192, 0); /* struct s1 f4; */
+ /* } */
+ btf__add_ptr(btf2, 8); /* [12] ptr to fwd struct s2 */
+ btf__add_struct(btf2, "s3", 8); /* [13] struct s3 { */
+ btf__add_field(btf2, "f1", 12, 0, 0); /* struct s2 *f1; (fwd) */
+ /* } */
+
+ VALIDATE_RAW_BTF(
+ btf2,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=5",
+ "[3] FWD 's2' fwd_kind=struct",
+ "[4] PTR '(anon)' type_id=3",
+ "[5] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=2 bits_offset=0\n"
+ "\t'f2' type_id=4 bits_offset=64",
+ "[6] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[7] PTR '(anon)' type_id=10",
+ "[8] FWD 's2' fwd_kind=struct",
+ "[9] PTR '(anon)' type_id=11",
+ "[10] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=7 bits_offset=0\n"
+ "\t'f2' type_id=9 bits_offset=64",
+ "[11] STRUCT 's2' size=40 vlen=4\n"
+ "\t'f1' type_id=7 bits_offset=0\n"
+ "\t'f2' type_id=9 bits_offset=64\n"
+ "\t'f3' type_id=6 bits_offset=128\n"
+ "\t'f4' type_id=10 bits_offset=192",
+ "[12] PTR '(anon)' type_id=8",
+ "[13] STRUCT 's3' size=8 vlen=1\n"
+ "\t'f1' type_id=12 bits_offset=0");
+
+ err = btf__dedup(btf2, NULL, NULL);
+ if (!ASSERT_OK(err, "btf_dedup"))
+ goto cleanup;
+
+ VALIDATE_RAW_BTF(
+ btf2,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=5",
+ "[3] FWD 's2' fwd_kind=struct",
+ "[4] PTR '(anon)' type_id=3",
+ "[5] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=2 bits_offset=0\n"
+ "\t'f2' type_id=4 bits_offset=64",
+ "[6] PTR '(anon)' type_id=8",
+ "[7] PTR '(anon)' type_id=9",
+ "[8] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=6 bits_offset=0\n"
+ "\t'f2' type_id=7 bits_offset=64",
+ "[9] STRUCT 's2' size=40 vlen=4\n"
+ "\t'f1' type_id=6 bits_offset=0\n"
+ "\t'f2' type_id=7 bits_offset=64\n"
+ "\t'f3' type_id=1 bits_offset=128\n"
+ "\t'f4' type_id=8 bits_offset=192",
+ "[10] STRUCT 's3' size=8 vlen=1\n"
+ "\t'f1' type_id=7 bits_offset=0");
+
+cleanup:
+ btf__free(btf2);
+ btf__free(btf1);
+}
+
+void test_btf_dedup_split()
+{
+ if (test__start_subtest("split_simple"))
+ test_split_simple();
+ if (test__start_subtest("split_struct_duped"))
+ test_split_struct_duped();
+ if (test__start_subtest("split_fwd_resolve"))
+ test_split_fwd_resolve();
+}
#include "test_btf_skc_cls_ingress.skel.h"
static struct test_btf_skc_cls_ingress *skel;
-struct sockaddr_in6 srv_sa6;
+static struct sockaddr_in6 srv_sa6;
static __u32 duration;
#define PROG_PIN_FILE "/sys/fs/bpf/btf_skc_cls_ingress"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+static char *dump_buf;
+static size_t dump_buf_sz;
+static FILE *dump_buf_file;
+
+static void btf_dump_printf(void *ctx, const char *fmt, va_list args)
+{
+ vfprintf(ctx, fmt, args);
+}
+
+void test_btf_split() {
+ struct btf_dump_opts opts;
+ struct btf_dump *d = NULL;
+ const struct btf_type *t;
+ struct btf *btf1, *btf2;
+ int str_off, i, err;
+
+ btf1 = btf__new_empty();
+ if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+ return;
+
+ btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+ btf__add_int(btf1, "int", 4, BTF_INT_SIGNED); /* [1] int */
+ btf__add_ptr(btf1, 1); /* [2] ptr to int */
+
+ btf__add_struct(btf1, "s1", 4); /* [3] struct s1 { */
+ btf__add_field(btf1, "f1", 1, 0, 0); /* int f1; */
+ /* } */
+
+ btf2 = btf__new_empty_split(btf1);
+ if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+ goto cleanup;
+
+ /* pointer size should be "inherited" from main BTF */
+ ASSERT_EQ(btf__pointer_size(btf2), 8, "inherit_ptr_sz");
+
+ str_off = btf__find_str(btf2, "int");
+ ASSERT_NEQ(str_off, -ENOENT, "str_int_missing");
+
+ t = btf__type_by_id(btf2, 1);
+ if (!ASSERT_OK_PTR(t, "int_type"))
+ goto cleanup;
+ ASSERT_EQ(btf_is_int(t), true, "int_kind");
+ ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "int", "int_name");
+
+ btf__add_struct(btf2, "s2", 16); /* [4] struct s2 { */
+ btf__add_field(btf2, "f1", 3, 0, 0); /* struct s1 f1; */
+ btf__add_field(btf2, "f2", 1, 32, 0); /* int f2; */
+ btf__add_field(btf2, "f3", 2, 64, 0); /* int *f3; */
+ /* } */
+
+ t = btf__type_by_id(btf1, 4);
+ ASSERT_NULL(t, "split_type_in_main");
+
+ t = btf__type_by_id(btf2, 4);
+ if (!ASSERT_OK_PTR(t, "split_struct_type"))
+ goto cleanup;
+ ASSERT_EQ(btf_is_struct(t), true, "split_struct_kind");
+ ASSERT_EQ(btf_vlen(t), 3, "split_struct_vlen");
+ ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "s2", "split_struct_name");
+
+ /* BTF-to-C dump of split BTF */
+ dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz);
+ if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream"))
+ return;
+ opts.ctx = dump_buf_file;
+ d = btf_dump__new(btf2, NULL, &opts, btf_dump_printf);
+ if (!ASSERT_OK_PTR(d, "btf_dump__new"))
+ goto cleanup;
+ for (i = 1; i <= btf__get_nr_types(btf2); i++) {
+ err = btf_dump__dump_type(d, i);
+ ASSERT_OK(err, "dump_type_ok");
+ }
+ fflush(dump_buf_file);
+ dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */
+ ASSERT_STREQ(dump_buf,
+"struct s1 {\n"
+" int f1;\n"
+"};\n"
+"\n"
+"struct s2 {\n"
+" struct s1 f1;\n"
+" int f2;\n"
+" int *f3;\n"
+"};\n\n", "c_dump");
+
+cleanup:
+ if (dump_buf_file)
+ fclose(dump_buf_file);
+ free(dump_buf);
+ btf_dump__free(d);
+ btf__free(btf1);
+ btf__free(btf2);
+}
/* Copyright (c) 2020 Facebook */
#include <test_progs.h>
#include <bpf/btf.h>
+#include "btf_helpers.h"
static int duration = 0;
ASSERT_EQ(t->size, 4, "int_sz");
ASSERT_EQ(btf_int_encoding(t), BTF_INT_SIGNED, "int_enc");
ASSERT_EQ(btf_int_bits(t), 32, "int_bits");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 1),
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", "raw_dump");
/* invalid int size */
id = btf__add_int(btf, "bad sz int", 7, 0);
t = btf__type_by_id(btf, 2);
ASSERT_EQ(btf_kind(t), BTF_KIND_PTR, "ptr_kind");
ASSERT_EQ(t->type, 1, "ptr_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 2),
+ "[2] PTR '(anon)' type_id=1", "raw_dump");
id = btf__add_const(btf, 5); /* points forward to restrict */
ASSERT_EQ(id, 3, "const_id");
t = btf__type_by_id(btf, 3);
ASSERT_EQ(btf_kind(t), BTF_KIND_CONST, "const_kind");
ASSERT_EQ(t->type, 5, "const_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 3),
+ "[3] CONST '(anon)' type_id=5", "raw_dump");
id = btf__add_volatile(btf, 3);
ASSERT_EQ(id, 4, "volatile_id");
t = btf__type_by_id(btf, 4);
ASSERT_EQ(btf_kind(t), BTF_KIND_VOLATILE, "volatile_kind");
ASSERT_EQ(t->type, 3, "volatile_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 4),
+ "[4] VOLATILE '(anon)' type_id=3", "raw_dump");
id = btf__add_restrict(btf, 4);
ASSERT_EQ(id, 5, "restrict_id");
t = btf__type_by_id(btf, 5);
ASSERT_EQ(btf_kind(t), BTF_KIND_RESTRICT, "restrict_kind");
ASSERT_EQ(t->type, 4, "restrict_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 5),
+ "[5] RESTRICT '(anon)' type_id=4", "raw_dump");
/* ARRAY */
id = btf__add_array(btf, 1, 2, 10); /* int *[10] */
ASSERT_EQ(btf_array(t)->index_type, 1, "array_index_type");
ASSERT_EQ(btf_array(t)->type, 2, "array_elem_type");
ASSERT_EQ(btf_array(t)->nelems, 10, "array_nelems");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 6),
+ "[6] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=10", "raw_dump");
/* STRUCT */
err = btf__add_field(btf, "field", 1, 0, 0);
ASSERT_EQ(m->type, 1, "f2_type");
ASSERT_EQ(btf_member_bit_offset(t, 1), 32, "f2_bit_off");
ASSERT_EQ(btf_member_bitfield_size(t, 1), 16, "f2_bit_sz");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 7),
+ "[7] STRUCT 's1' size=8 vlen=2\n"
+ "\t'f1' type_id=1 bits_offset=0\n"
+ "\t'f2' type_id=1 bits_offset=32 bitfield_size=16", "raw_dump");
/* UNION */
id = btf__add_union(btf, "u1", 8);
ASSERT_EQ(m->type, 1, "f1_type");
ASSERT_EQ(btf_member_bit_offset(t, 0), 0, "f1_bit_off");
ASSERT_EQ(btf_member_bitfield_size(t, 0), 16, "f1_bit_sz");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 8),
+ "[8] UNION 'u1' size=8 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0 bitfield_size=16", "raw_dump");
/* ENUM */
id = btf__add_enum(btf, "e1", 4);
v = btf_enum(t) + 1;
ASSERT_STREQ(btf__str_by_offset(btf, v->name_off), "v2", "v2_name");
ASSERT_EQ(v->val, 2, "v2_val");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 9),
+ "[9] ENUM 'e1' size=4 vlen=2\n"
+ "\t'v1' val=1\n"
+ "\t'v2' val=2", "raw_dump");
/* FWDs */
id = btf__add_fwd(btf, "struct_fwd", BTF_FWD_STRUCT);
ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "struct_fwd", "fwd_name");
ASSERT_EQ(btf_kind(t), BTF_KIND_FWD, "fwd_kind");
ASSERT_EQ(btf_kflag(t), 0, "fwd_kflag");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 10),
+ "[10] FWD 'struct_fwd' fwd_kind=struct", "raw_dump");
id = btf__add_fwd(btf, "union_fwd", BTF_FWD_UNION);
ASSERT_EQ(id, 11, "union_fwd_id");
ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "union_fwd", "fwd_name");
ASSERT_EQ(btf_kind(t), BTF_KIND_FWD, "fwd_kind");
ASSERT_EQ(btf_kflag(t), 1, "fwd_kflag");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 11),
+ "[11] FWD 'union_fwd' fwd_kind=union", "raw_dump");
id = btf__add_fwd(btf, "enum_fwd", BTF_FWD_ENUM);
ASSERT_EQ(id, 12, "enum_fwd_id");
ASSERT_EQ(btf_kind(t), BTF_KIND_ENUM, "enum_fwd_kind");
ASSERT_EQ(btf_vlen(t), 0, "enum_fwd_kind");
ASSERT_EQ(t->size, 4, "enum_fwd_sz");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 12),
+ "[12] ENUM 'enum_fwd' size=4 vlen=0", "raw_dump");
/* TYPEDEF */
id = btf__add_typedef(btf, "typedef1", 1);
ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "typedef1", "typedef_name");
ASSERT_EQ(btf_kind(t), BTF_KIND_TYPEDEF, "typedef_kind");
ASSERT_EQ(t->type, 1, "typedef_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 13),
+ "[13] TYPEDEF 'typedef1' type_id=1", "raw_dump");
/* FUNC & FUNC_PROTO */
id = btf__add_func(btf, "func1", BTF_FUNC_GLOBAL, 15);
ASSERT_EQ(t->type, 15, "func_type");
ASSERT_EQ(btf_kind(t), BTF_KIND_FUNC, "func_kind");
ASSERT_EQ(btf_vlen(t), BTF_FUNC_GLOBAL, "func_vlen");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 14),
+ "[14] FUNC 'func1' type_id=15 linkage=global", "raw_dump");
id = btf__add_func_proto(btf, 1);
ASSERT_EQ(id, 15, "func_proto_id");
p = btf_params(t) + 1;
ASSERT_STREQ(btf__str_by_offset(btf, p->name_off), "p2", "p2_name");
ASSERT_EQ(p->type, 2, "p2_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 15),
+ "[15] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n"
+ "\t'p1' type_id=1\n"
+ "\t'p2' type_id=2", "raw_dump");
/* VAR */
id = btf__add_var(btf, "var1", BTF_VAR_GLOBAL_ALLOCATED, 1);
ASSERT_EQ(btf_kind(t), BTF_KIND_VAR, "var_kind");
ASSERT_EQ(t->type, 1, "var_type");
ASSERT_EQ(btf_var(t)->linkage, BTF_VAR_GLOBAL_ALLOCATED, "var_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 16),
+ "[16] VAR 'var1' type_id=1, linkage=global-alloc", "raw_dump");
/* DATASECT */
id = btf__add_datasec(btf, "datasec1", 12);
ASSERT_EQ(vi->type, 1, "v1_type");
ASSERT_EQ(vi->offset, 4, "v1_off");
ASSERT_EQ(vi->size, 8, "v1_sz");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 17),
+ "[17] DATASEC 'datasec1' size=12 vlen=1\n"
+ "\ttype_id=1 offset=4 size=8", "raw_dump");
btf__free(btf);
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_hash_large_key.skel.h"
+
+void test_hash_large_key(void)
+{
+ int err, value = 21, duration = 0, hash_map_fd;
+ struct test_hash_large_key *skel;
+
+ struct bigelement {
+ int a;
+ char b[4096];
+ long long c;
+ } key;
+ bzero(&key, sizeof(key));
+
+ skel = test_hash_large_key__open_and_load();
+ if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n"))
+ return;
+
+ hash_map_fd = bpf_map__fd(skel->maps.hash_map);
+ if (CHECK(hash_map_fd < 0, "bpf_map__fd", "failed\n"))
+ goto cleanup;
+
+ err = test_hash_large_key__attach(skel);
+ if (CHECK(err, "attach_raw_tp", "err %d\n", err))
+ goto cleanup;
+
+ err = bpf_map_update_elem(hash_map_fd, &key, &value, BPF_ANY);
+ if (CHECK(err, "bpf_map_update_elem", "errno=%d\n", errno))
+ goto cleanup;
+
+ key.c = 1;
+ err = bpf_map_lookup_elem(hash_map_fd, &key, &value);
+ if (CHECK(err, "bpf_map_lookup_elem", "errno=%d\n", errno))
+ goto cleanup;
+
+ CHECK_FAIL(value != 42);
+
+cleanup:
+ test_hash_large_key__destroy(skel);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <sys/types.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "test_sk_storage_trace_itself.skel.h"
+#include "test_sk_storage_tracing.skel.h"
+
+#define LO_ADDR6 "::1"
+#define TEST_COMM "test_progs"
+
+struct sk_stg {
+ __u32 pid;
+ __u32 last_notclose_state;
+ char comm[16];
+};
+
+static struct test_sk_storage_tracing *skel;
+static __u32 duration;
+static pid_t my_pid;
+
+static int check_sk_stg(int sk_fd, __u32 expected_state)
+{
+ struct sk_stg sk_stg;
+ int err;
+
+ err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sk_stg_map), &sk_fd,
+ &sk_stg);
+ if (!ASSERT_OK(err, "map_lookup(sk_stg_map)"))
+ return -1;
+
+ if (!ASSERT_EQ(sk_stg.last_notclose_state, expected_state,
+ "last_notclose_state"))
+ return -1;
+
+ if (!ASSERT_EQ(sk_stg.pid, my_pid, "pid"))
+ return -1;
+
+ if (!ASSERT_STREQ(sk_stg.comm, skel->bss->task_comm, "task_comm"))
+ return -1;
+
+ return 0;
+}
+
+static void do_test(void)
+{
+ int listen_fd = -1, passive_fd = -1, active_fd = -1, value = 1, err;
+ char abyte;
+
+ listen_fd = start_server(AF_INET6, SOCK_STREAM, LO_ADDR6, 0, 0);
+ if (CHECK(listen_fd == -1, "start_server",
+ "listen_fd:%d errno:%d\n", listen_fd, errno))
+ return;
+
+ active_fd = connect_to_fd(listen_fd, 0);
+ if (CHECK(active_fd == -1, "connect_to_fd", "active_fd:%d errno:%d\n",
+ active_fd, errno))
+ goto out;
+
+ err = bpf_map_update_elem(bpf_map__fd(skel->maps.del_sk_stg_map),
+ &active_fd, &value, 0);
+ if (!ASSERT_OK(err, "map_update(del_sk_stg_map)"))
+ goto out;
+
+ passive_fd = accept(listen_fd, NULL, 0);
+ if (CHECK(passive_fd == -1, "accept", "passive_fd:%d errno:%d\n",
+ passive_fd, errno))
+ goto out;
+
+ shutdown(active_fd, SHUT_WR);
+ err = read(passive_fd, &abyte, 1);
+ if (!ASSERT_OK(err, "read(passive_fd)"))
+ goto out;
+
+ shutdown(passive_fd, SHUT_WR);
+ err = read(active_fd, &abyte, 1);
+ if (!ASSERT_OK(err, "read(active_fd)"))
+ goto out;
+
+ err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.del_sk_stg_map),
+ &active_fd, &value);
+ if (!ASSERT_ERR(err, "map_lookup(del_sk_stg_map)"))
+ goto out;
+
+ err = check_sk_stg(listen_fd, BPF_TCP_LISTEN);
+ if (!ASSERT_OK(err, "listen_fd sk_stg"))
+ goto out;
+
+ err = check_sk_stg(active_fd, BPF_TCP_FIN_WAIT2);
+ if (!ASSERT_OK(err, "active_fd sk_stg"))
+ goto out;
+
+ err = check_sk_stg(passive_fd, BPF_TCP_LAST_ACK);
+ ASSERT_OK(err, "passive_fd sk_stg");
+
+out:
+ if (active_fd != -1)
+ close(active_fd);
+ if (passive_fd != -1)
+ close(passive_fd);
+ if (listen_fd != -1)
+ close(listen_fd);
+}
+
+void test_sk_storage_tracing(void)
+{
+ struct test_sk_storage_trace_itself *skel_itself;
+ int err;
+
+ my_pid = getpid();
+
+ skel_itself = test_sk_storage_trace_itself__open_and_load();
+
+ if (!ASSERT_NULL(skel_itself, "test_sk_storage_trace_itself")) {
+ test_sk_storage_trace_itself__destroy(skel_itself);
+ return;
+ }
+
+ skel = test_sk_storage_tracing__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_sk_storage_tracing"))
+ return;
+
+ err = test_sk_storage_tracing__attach(skel);
+ if (!ASSERT_OK(err, "test_sk_storage_tracing__attach")) {
+ test_sk_storage_tracing__destroy(skel);
+ return;
+ }
+
+ do_test();
+
+ test_sk_storage_tracing__destroy(skel);
+}
#define LO_ADDR6 "::1"
#define CG_NAME "/tcpbpf-hdr-opt-test"
-struct bpf_test_option exp_passive_estab_in;
-struct bpf_test_option exp_active_estab_in;
-struct bpf_test_option exp_passive_fin_in;
-struct bpf_test_option exp_active_fin_in;
-struct hdr_stg exp_passive_hdr_stg;
-struct hdr_stg exp_active_hdr_stg = { .active = true, };
+static struct bpf_test_option exp_passive_estab_in;
+static struct bpf_test_option exp_active_estab_in;
+static struct bpf_test_option exp_passive_fin_in;
+static struct bpf_test_option exp_active_fin_in;
+static struct hdr_stg exp_passive_hdr_stg;
+static struct hdr_stg exp_active_hdr_stg = { .active = true, };
static struct test_misc_tcp_hdr_options *misc_skel;
static struct test_tcp_hdr_options *skel;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "test_tcpbpf.h"
+#include "test_tcpbpf_kern.skel.h"
+
+#define LO_ADDR6 "::1"
+#define CG_NAME "/tcpbpf-user-test"
+
+static __u32 duration;
+
+static void verify_result(struct tcpbpf_globals *result)
+{
+ __u32 expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) |
+ (1 << BPF_SOCK_OPS_RWND_INIT) |
+ (1 << BPF_SOCK_OPS_TCP_CONNECT_CB) |
+ (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) |
+ (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) |
+ (1 << BPF_SOCK_OPS_NEEDS_ECN) |
+ (1 << BPF_SOCK_OPS_STATE_CB) |
+ (1 << BPF_SOCK_OPS_TCP_LISTEN_CB));
+
+ /* check global map */
+ CHECK(expected_events != result->event_map, "event_map",
+ "unexpected event_map: actual 0x%08x != expected 0x%08x\n",
+ result->event_map, expected_events);
+
+ ASSERT_EQ(result->bytes_received, 501, "bytes_received");
+ ASSERT_EQ(result->bytes_acked, 1002, "bytes_acked");
+ ASSERT_EQ(result->data_segs_in, 1, "data_segs_in");
+ ASSERT_EQ(result->data_segs_out, 1, "data_segs_out");
+ ASSERT_EQ(result->bad_cb_test_rv, 0x80, "bad_cb_test_rv");
+ ASSERT_EQ(result->good_cb_test_rv, 0, "good_cb_test_rv");
+ ASSERT_EQ(result->num_listen, 1, "num_listen");
+
+ /* 3 comes from one listening socket + both ends of the connection */
+ ASSERT_EQ(result->num_close_events, 3, "num_close_events");
+
+ /* check setsockopt for SAVE_SYN */
+ ASSERT_EQ(result->tcp_save_syn, 0, "tcp_save_syn");
+
+ /* check getsockopt for SAVED_SYN */
+ ASSERT_EQ(result->tcp_saved_syn, 1, "tcp_saved_syn");
+}
+
+static void run_test(struct tcpbpf_globals *result)
+{
+ int listen_fd = -1, cli_fd = -1, accept_fd = -1;
+ char buf[1000];
+ int err = -1;
+ int i, rv;
+
+ listen_fd = start_server(AF_INET6, SOCK_STREAM, LO_ADDR6, 0, 0);
+ if (CHECK(listen_fd == -1, "start_server", "listen_fd:%d errno:%d\n",
+ listen_fd, errno))
+ goto done;
+
+ cli_fd = connect_to_fd(listen_fd, 0);
+ if (CHECK(cli_fd == -1, "connect_to_fd(listen_fd)",
+ "cli_fd:%d errno:%d\n", cli_fd, errno))
+ goto done;
+
+ accept_fd = accept(listen_fd, NULL, NULL);
+ if (CHECK(accept_fd == -1, "accept(listen_fd)",
+ "accept_fd:%d errno:%d\n", accept_fd, errno))
+ goto done;
+
+ /* Send 1000B of '+'s from cli_fd -> accept_fd */
+ for (i = 0; i < 1000; i++)
+ buf[i] = '+';
+
+ rv = send(cli_fd, buf, 1000, 0);
+ if (CHECK(rv != 1000, "send(cli_fd)", "rv:%d errno:%d\n", rv, errno))
+ goto done;
+
+ rv = recv(accept_fd, buf, 1000, 0);
+ if (CHECK(rv != 1000, "recv(accept_fd)", "rv:%d errno:%d\n", rv, errno))
+ goto done;
+
+ /* Send 500B of '.'s from accept_fd ->cli_fd */
+ for (i = 0; i < 500; i++)
+ buf[i] = '.';
+
+ rv = send(accept_fd, buf, 500, 0);
+ if (CHECK(rv != 500, "send(accept_fd)", "rv:%d errno:%d\n", rv, errno))
+ goto done;
+
+ rv = recv(cli_fd, buf, 500, 0);
+ if (CHECK(rv != 500, "recv(cli_fd)", "rv:%d errno:%d\n", rv, errno))
+ goto done;
+
+ /*
+ * shutdown accept first to guarantee correct ordering for
+ * bytes_received and bytes_acked when we go to verify the results.
+ */
+ shutdown(accept_fd, SHUT_WR);
+ err = recv(cli_fd, buf, 1, 0);
+ if (CHECK(err, "recv(cli_fd) for fin", "err:%d errno:%d\n", err, errno))
+ goto done;
+
+ shutdown(cli_fd, SHUT_WR);
+ err = recv(accept_fd, buf, 1, 0);
+ CHECK(err, "recv(accept_fd) for fin", "err:%d errno:%d\n", err, errno);
+done:
+ if (accept_fd != -1)
+ close(accept_fd);
+ if (cli_fd != -1)
+ close(cli_fd);
+ if (listen_fd != -1)
+ close(listen_fd);
+
+ if (!err)
+ verify_result(result);
+}
+
+void test_tcpbpf_user(void)
+{
+ struct test_tcpbpf_kern *skel;
+ int cg_fd = -1;
+
+ skel = test_tcpbpf_kern__open_and_load();
+ if (CHECK(!skel, "open and load skel", "failed"))
+ return;
+
+ cg_fd = test__join_cgroup(CG_NAME);
+ if (CHECK(cg_fd < 0, "test__join_cgroup(" CG_NAME ")",
+ "cg_fd:%d errno:%d", cg_fd, errno))
+ goto err;
+
+ skel->links.bpf_testcb = bpf_program__attach_cgroup(skel->progs.bpf_testcb, cg_fd);
+ if (!ASSERT_OK_PTR(skel->links.bpf_testcb, "attach_cgroup(bpf_testcb)"))
+ goto err;
+
+ run_test(&skel->bss->global);
+
+err:
+ if (cg_fd != -1)
+ close(cg_fd);
+ test_tcpbpf_kern__destroy(skel);
+}
* Copyright (C) 2020 Google LLC.
*/
+#include <asm-generic/errno-base.h>
+#include <sys/stat.h>
#include <test_progs.h>
#include <linux/limits.h>
#include "local_storage.skel.h"
#include "network_helpers.h"
-int create_and_unlink_file(void)
+#ifndef __NR_pidfd_open
+#define __NR_pidfd_open 434
+#endif
+
+static inline int sys_pidfd_open(pid_t pid, unsigned int flags)
+{
+ return syscall(__NR_pidfd_open, pid, flags);
+}
+
+static inline ssize_t copy_file_range(int fd_in, loff_t *off_in, int fd_out,
+ loff_t *off_out, size_t len,
+ unsigned int flags)
{
- char fname[PATH_MAX] = "/tmp/fileXXXXXX";
- int fd;
+ return syscall(__NR_copy_file_range, fd_in, off_in, fd_out, off_out,
+ len, flags);
+}
+
+static unsigned int duration;
- fd = mkstemp(fname);
- if (fd < 0)
- return fd;
+#define TEST_STORAGE_VALUE 0xbeefdead
- close(fd);
- unlink(fname);
- return 0;
+struct storage {
+ void *inode;
+ unsigned int value;
+ /* Lock ensures that spin locked versions of local stoage operations
+ * also work, most operations in this tests are still single threaded
+ */
+ struct bpf_spin_lock lock;
+};
+
+/* Copies an rm binary to a temp file. dest is a mkstemp template */
+static int copy_rm(char *dest)
+{
+ int fd_in, fd_out = -1, ret = 0;
+ struct stat stat;
+
+ fd_in = open("/bin/rm", O_RDONLY);
+ if (fd_in < 0)
+ return -errno;
+
+ fd_out = mkstemp(dest);
+ if (fd_out < 0) {
+ ret = -errno;
+ goto out;
+ }
+
+ ret = fstat(fd_in, &stat);
+ if (ret == -1) {
+ ret = -errno;
+ goto out;
+ }
+
+ ret = copy_file_range(fd_in, NULL, fd_out, NULL, stat.st_size, 0);
+ if (ret == -1) {
+ ret = -errno;
+ goto out;
+ }
+
+ /* Set executable permission on the copied file */
+ ret = chmod(dest, 0100);
+ if (ret == -1)
+ ret = -errno;
+
+out:
+ close(fd_in);
+ close(fd_out);
+ return ret;
+}
+
+/* Fork and exec the provided rm binary and return the exit code of the
+ * forked process and its pid.
+ */
+static int run_self_unlink(int *monitored_pid, const char *rm_path)
+{
+ int child_pid, child_status, ret;
+ int null_fd;
+
+ child_pid = fork();
+ if (child_pid == 0) {
+ null_fd = open("/dev/null", O_WRONLY);
+ dup2(null_fd, STDOUT_FILENO);
+ dup2(null_fd, STDERR_FILENO);
+ close(null_fd);
+
+ *monitored_pid = getpid();
+ /* Use the copied /usr/bin/rm to delete itself
+ * /tmp/copy_of_rm /tmp/copy_of_rm.
+ */
+ ret = execlp(rm_path, rm_path, rm_path, NULL);
+ if (ret)
+ exit(errno);
+ } else if (child_pid > 0) {
+ waitpid(child_pid, &child_status, 0);
+ return WEXITSTATUS(child_status);
+ }
+
+ return -EINVAL;
+}
+
+static bool check_syscall_operations(int map_fd, int obj_fd)
+{
+ struct storage val = { .value = TEST_STORAGE_VALUE, .lock = { 0 } },
+ lookup_val = { .value = 0, .lock = { 0 } };
+ int err;
+
+ /* Looking up an existing element should fail initially */
+ err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
+ BPF_F_LOCK);
+ if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
+ "err:%d errno:%d\n", err, errno))
+ return false;
+
+ /* Create a new element */
+ err = bpf_map_update_elem(map_fd, &obj_fd, &val,
+ BPF_NOEXIST | BPF_F_LOCK);
+ if (CHECK(err < 0, "bpf_map_update_elem", "err:%d errno:%d\n", err,
+ errno))
+ return false;
+
+ /* Lookup the newly created element */
+ err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
+ BPF_F_LOCK);
+ if (CHECK(err < 0, "bpf_map_lookup_elem", "err:%d errno:%d", err,
+ errno))
+ return false;
+
+ /* Check the value of the newly created element */
+ if (CHECK(lookup_val.value != val.value, "bpf_map_lookup_elem",
+ "value got = %x errno:%d", lookup_val.value, val.value))
+ return false;
+
+ err = bpf_map_delete_elem(map_fd, &obj_fd);
+ if (CHECK(err, "bpf_map_delete_elem()", "err:%d errno:%d\n", err,
+ errno))
+ return false;
+
+ /* The lookup should fail, now that the element has been deleted */
+ err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
+ BPF_F_LOCK);
+ if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
+ "err:%d errno:%d\n", err, errno))
+ return false;
+
+ return true;
}
void test_test_local_storage(void)
{
+ char tmp_exec_path[PATH_MAX] = "/tmp/copy_of_rmXXXXXX";
+ int err, serv_sk = -1, task_fd = -1, rm_fd = -1;
struct local_storage *skel = NULL;
- int err, duration = 0, serv_sk = -1;
skel = local_storage__open_and_load();
if (CHECK(!skel, "skel_load", "lsm skeleton failed\n"))
if (CHECK(err, "attach", "lsm attach failed: %d\n", err))
goto close_prog;
- skel->bss->monitored_pid = getpid();
+ task_fd = sys_pidfd_open(getpid(), 0);
+ if (CHECK(task_fd < 0, "pidfd_open",
+ "failed to get pidfd err:%d, errno:%d", task_fd, errno))
+ goto close_prog;
+
+ if (!check_syscall_operations(bpf_map__fd(skel->maps.task_storage_map),
+ task_fd))
+ goto close_prog;
+
+ err = copy_rm(tmp_exec_path);
+ if (CHECK(err < 0, "copy_rm", "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ rm_fd = open(tmp_exec_path, O_RDONLY);
+ if (CHECK(rm_fd < 0, "open", "failed to open %s err:%d, errno:%d",
+ tmp_exec_path, rm_fd, errno))
+ goto close_prog;
- err = create_and_unlink_file();
- if (CHECK(err < 0, "exec_cmd", "err %d errno %d\n", err, errno))
+ if (!check_syscall_operations(bpf_map__fd(skel->maps.inode_storage_map),
+ rm_fd))
goto close_prog;
+ /* Sets skel->bss->monitored_pid to the pid of the forked child
+ * forks a child process that executes tmp_exec_path and tries to
+ * unlink its executable. This operation should be denied by the loaded
+ * LSM program.
+ */
+ err = run_self_unlink(&skel->bss->monitored_pid, tmp_exec_path);
+ if (CHECK(err != EPERM, "run_self_unlink", "err %d want EPERM\n", err))
+ goto close_prog_unlink;
+
+ /* Set the process being monitored to be the current process */
+ skel->bss->monitored_pid = getpid();
+
+ /* Remove the temporary created executable */
+ err = unlink(tmp_exec_path);
+ if (CHECK(err != 0, "unlink", "unable to unlink %s: %d", tmp_exec_path,
+ errno))
+ goto close_prog_unlink;
+
CHECK(skel->data->inode_storage_result != 0, "inode_storage_result",
"inode_local_storage not set\n");
CHECK(skel->data->sk_storage_result != 0, "sk_storage_result",
"sk_local_storage not set\n");
- close(serv_sk);
+ if (!check_syscall_operations(bpf_map__fd(skel->maps.sk_storage_map),
+ serv_sk))
+ goto close_prog;
+close_prog_unlink:
+ unlink(tmp_exec_path);
close_prog:
+ close(serv_sk);
+ close(rm_fd);
+ close(task_fd);
local_storage__destroy(skel);
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "skb_pkt_end.skel.h"
+
+static int sanity_run(struct bpf_program *prog)
+{
+ __u32 duration, retval;
+ int err, prog_fd;
+
+ prog_fd = bpf_program__fd(prog);
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+ NULL, NULL, &retval, &duration);
+ if (CHECK(err || retval != 123, "test_run",
+ "err %d errno %d retval %d duration %d\n",
+ err, errno, retval, duration))
+ return -1;
+ return 0;
+}
+
+void test_test_skb_pkt_end(void)
+{
+ struct skb_pkt_end *skb_pkt_end_skel = NULL;
+ __u32 duration = 0;
+ int err;
+
+ skb_pkt_end_skel = skb_pkt_end__open_and_load();
+ if (CHECK(!skb_pkt_end_skel, "skb_pkt_end_skel_load", "skb_pkt_end skeleton failed\n"))
+ goto cleanup;
+
+ err = skb_pkt_end__attach(skb_pkt_end_skel);
+ if (CHECK(err, "skb_pkt_end_attach", "skb_pkt_end attach failed: %d\n", err))
+ goto cleanup;
+
+ if (sanity_run(skb_pkt_end_skel->progs.main_prog))
+ goto cleanup;
+
+cleanup:
+ skb_pkt_end__destroy(skb_pkt_end_skel);
+}
* Copyright 2020 Google LLC.
*/
+#include "vmlinux.h"
#include <errno.h>
-#include <linux/bpf.h>
-#include <stdbool.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
int inode_storage_result = -1;
int sk_storage_result = -1;
-struct dummy_storage {
+struct local_storage {
+ struct inode *exec_inode;
__u32 value;
+ struct bpf_spin_lock lock;
};
struct {
__uint(type, BPF_MAP_TYPE_INODE_STORAGE);
__uint(map_flags, BPF_F_NO_PREALLOC);
__type(key, int);
- __type(value, struct dummy_storage);
+ __type(value, struct local_storage);
} inode_storage_map SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_SK_STORAGE);
__uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE);
__type(key, int);
- __type(value, struct dummy_storage);
+ __type(value, struct local_storage);
} sk_storage_map SEC(".maps");
-/* TODO Use vmlinux.h once BTF pruning for embedded types is fixed.
- */
-struct sock {} __attribute__((preserve_access_index));
-struct sockaddr {} __attribute__((preserve_access_index));
-struct socket {
- struct sock *sk;
-} __attribute__((preserve_access_index));
-
-struct inode {} __attribute__((preserve_access_index));
-struct dentry {
- struct inode *d_inode;
-} __attribute__((preserve_access_index));
-struct file {
- struct inode *f_inode;
-} __attribute__((preserve_access_index));
-
+struct {
+ __uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct local_storage);
+} task_storage_map SEC(".maps");
SEC("lsm/inode_unlink")
int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
{
__u32 pid = bpf_get_current_pid_tgid() >> 32;
- struct dummy_storage *storage;
+ struct local_storage *storage;
+ bool is_self_unlink;
+ int err;
if (pid != monitored_pid)
return 0;
+ storage = bpf_task_storage_get(&task_storage_map,
+ bpf_get_current_task_btf(), 0, 0);
+ if (storage) {
+ /* Don't let an executable delete itself */
+ bpf_spin_lock(&storage->lock);
+ is_self_unlink = storage->exec_inode == victim->d_inode;
+ bpf_spin_unlock(&storage->lock);
+ if (is_self_unlink)
+ return -EPERM;
+ }
+
storage = bpf_inode_storage_get(&inode_storage_map, victim->d_inode, 0,
- BPF_SK_STORAGE_GET_F_CREATE);
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
if (!storage)
return 0;
- if (storage->value == DUMMY_STORAGE_VALUE)
+ bpf_spin_lock(&storage->lock);
+ if (storage->value != DUMMY_STORAGE_VALUE)
inode_storage_result = -1;
+ bpf_spin_unlock(&storage->lock);
- inode_storage_result =
- bpf_inode_storage_delete(&inode_storage_map, victim->d_inode);
+ err = bpf_inode_storage_delete(&inode_storage_map, victim->d_inode);
+ if (!err)
+ inode_storage_result = err;
return 0;
}
int addrlen)
{
__u32 pid = bpf_get_current_pid_tgid() >> 32;
- struct dummy_storage *storage;
+ struct local_storage *storage;
+ int err;
if (pid != monitored_pid)
return 0;
storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0,
- BPF_SK_STORAGE_GET_F_CREATE);
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
if (!storage)
return 0;
- if (storage->value == DUMMY_STORAGE_VALUE)
+ bpf_spin_lock(&storage->lock);
+ if (storage->value != DUMMY_STORAGE_VALUE)
sk_storage_result = -1;
+ bpf_spin_unlock(&storage->lock);
+
+ err = bpf_sk_storage_delete(&sk_storage_map, sock->sk);
+ if (!err)
+ sk_storage_result = err;
- sk_storage_result = bpf_sk_storage_delete(&sk_storage_map, sock->sk);
return 0;
}
int protocol, int kern)
{
__u32 pid = bpf_get_current_pid_tgid() >> 32;
- struct dummy_storage *storage;
+ struct local_storage *storage;
if (pid != monitored_pid)
return 0;
storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0,
- BPF_SK_STORAGE_GET_F_CREATE);
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
if (!storage)
return 0;
+ bpf_spin_lock(&storage->lock);
storage->value = DUMMY_STORAGE_VALUE;
+ bpf_spin_unlock(&storage->lock);
return 0;
}
int BPF_PROG(file_open, struct file *file)
{
__u32 pid = bpf_get_current_pid_tgid() >> 32;
- struct dummy_storage *storage;
+ struct local_storage *storage;
if (pid != monitored_pid)
return 0;
return 0;
storage = bpf_inode_storage_get(&inode_storage_map, file->f_inode, 0,
- BPF_LOCAL_STORAGE_GET_F_CREATE);
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
if (!storage)
return 0;
+ bpf_spin_lock(&storage->lock);
storage->value = DUMMY_STORAGE_VALUE;
+ bpf_spin_unlock(&storage->lock);
return 0;
}
+
+/* This uses the local storage to remember the inode of the binary that a
+ * process was originally executing.
+ */
+SEC("lsm/bprm_committed_creds")
+void BPF_PROG(exec, struct linux_binprm *bprm)
+{
+ struct local_storage *storage;
+
+ storage = bpf_task_storage_get(&task_storage_map,
+ bpf_get_current_task_btf(), 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (storage) {
+ bpf_spin_lock(&storage->lock);
+ storage->exec_inode = bprm->file->f_inode;
+ bpf_spin_unlock(&storage->lock);
+ }
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#define BPF_NO_PRESERVE_ACCESS_INDEX
+#include <vmlinux.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+
+#define NULL 0
+#define INLINE __always_inline
+
+#define skb_shorter(skb, len) ((void *)(long)(skb)->data + (len) > (void *)(long)skb->data_end)
+
+#define ETH_IPV4_TCP_SIZE (14 + sizeof(struct iphdr) + sizeof(struct tcphdr))
+
+static INLINE struct iphdr *get_iphdr(struct __sk_buff *skb)
+{
+ struct iphdr *ip = NULL;
+ struct ethhdr *eth;
+
+ if (skb_shorter(skb, ETH_IPV4_TCP_SIZE))
+ goto out;
+
+ eth = (void *)(long)skb->data;
+ ip = (void *)(eth + 1);
+
+out:
+ return ip;
+}
+
+SEC("classifier/cls")
+int main_prog(struct __sk_buff *skb)
+{
+ struct iphdr *ip = NULL;
+ struct tcphdr *tcp;
+ __u8 proto = 0;
+
+ if (!(ip = get_iphdr(skb)))
+ goto out;
+
+ proto = ip->protocol;
+
+ if (proto != IPPROTO_TCP)
+ goto out;
+
+ tcp = (void*)(ip + 1);
+ if (tcp->dest != 0)
+ goto out;
+ if (!tcp)
+ goto out;
+
+ return tcp->urg_ptr;
+out:
+ return -1;
+}
+char _license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 2);
+ __type(key, struct bigelement);
+ __type(value, __u32);
+} hash_map SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, struct bigelement);
+} key_map SEC(".maps");
+
+struct bigelement {
+ int a;
+ char b[4096];
+ long long c;
+};
+
+SEC("raw_tracepoint/sys_enter")
+int bpf_hash_large_key_test(void *ctx)
+{
+ int zero = 0, err = 1, value = 42;
+ struct bigelement *key;
+
+ key = bpf_map_lookup_elem(&key_map, &zero);
+ if (!key)
+ return 0;
+
+ key->c = 1;
+ if (bpf_map_update_elem(&hash_map, key, &value, BPF_ANY))
+ return 0;
+
+ return 0;
+}
+
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, int);
+} sk_stg_map SEC(".maps");
+
+SEC("fentry/bpf_sk_storage_free")
+int BPF_PROG(trace_bpf_sk_storage_free, struct sock *sk)
+{
+ int *value;
+
+ value = bpf_sk_storage_get(&sk_stg_map, sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+
+ if (value)
+ *value = 1;
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+
+struct sk_stg {
+ __u32 pid;
+ __u32 last_notclose_state;
+ char comm[16];
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct sk_stg);
+} sk_stg_map SEC(".maps");
+
+/* Testing delete */
+struct {
+ __uint(type, BPF_MAP_TYPE_SK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, int);
+} del_sk_stg_map SEC(".maps");
+
+char task_comm[16] = "";
+
+SEC("tp_btf/inet_sock_set_state")
+int BPF_PROG(trace_inet_sock_set_state, struct sock *sk, int oldstate,
+ int newstate)
+{
+ struct sk_stg *stg;
+
+ if (newstate == BPF_TCP_CLOSE)
+ return 0;
+
+ stg = bpf_sk_storage_get(&sk_stg_map, sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+ if (!stg)
+ return 0;
+
+ stg->last_notclose_state = newstate;
+
+ bpf_sk_storage_delete(&del_sk_stg_map, sk);
+
+ return 0;
+}
+
+static void set_task_info(struct sock *sk)
+{
+ struct task_struct *task;
+ struct sk_stg *stg;
+
+ stg = bpf_sk_storage_get(&sk_stg_map, sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+ if (!stg)
+ return;
+
+ stg->pid = bpf_get_current_pid_tgid();
+
+ task = (struct task_struct *)bpf_get_current_task();
+ bpf_core_read_str(&stg->comm, sizeof(stg->comm), &task->comm);
+ bpf_core_read_str(&task_comm, sizeof(task_comm), &task->comm);
+}
+
+SEC("fentry/inet_csk_listen_start")
+int BPF_PROG(trace_inet_csk_listen_start, struct sock *sk, int backlog)
+{
+ set_task_info(sk);
+
+ return 0;
+}
+
+SEC("fentry/tcp_connect")
+int BPF_PROG(trace_tcp_connect, struct sock *sk)
+{
+ set_task_info(sk);
+
+ return 0;
+}
+
+SEC("fexit/inet_csk_accept")
+int BPF_PROG(inet_csk_accept, struct sock *sk, int flags, int *err, bool kern,
+ struct sock *accepted_sk)
+{
+ set_task_info(accepted_sk);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
#include <bpf/bpf_endian.h>
#include "test_tcpbpf.h"
-struct {
- __uint(type, BPF_MAP_TYPE_ARRAY);
- __uint(max_entries, 4);
- __type(key, __u32);
- __type(value, struct tcpbpf_globals);
-} global_map SEC(".maps");
-
-struct {
- __uint(type, BPF_MAP_TYPE_ARRAY);
- __uint(max_entries, 2);
- __type(key, __u32);
- __type(value, int);
-} sockopt_results SEC(".maps");
-
-static inline void update_event_map(int event)
-{
- __u32 key = 0;
- struct tcpbpf_globals g, *gp;
-
- gp = bpf_map_lookup_elem(&global_map, &key);
- if (gp == NULL) {
- struct tcpbpf_globals g = {0};
-
- g.event_map |= (1 << event);
- bpf_map_update_elem(&global_map, &key, &g,
- BPF_ANY);
- } else {
- g = *gp;
- g.event_map |= (1 << event);
- bpf_map_update_elem(&global_map, &key, &g,
- BPF_ANY);
- }
-}
-
+struct tcpbpf_globals global = {};
int _version SEC("version") = 1;
SEC("sockops")
op = (int) skops->op;
- update_event_map(op);
+ global.event_map |= (1 << op);
switch (op) {
case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
/* Test failure to set largest cb flag (assumes not defined) */
- bad_call_rv = bpf_sock_ops_cb_flags_set(skops, 0x80);
+ global.bad_cb_test_rv = bpf_sock_ops_cb_flags_set(skops, 0x80);
/* Set callback */
- good_call_rv = bpf_sock_ops_cb_flags_set(skops,
+ global.good_cb_test_rv = bpf_sock_ops_cb_flags_set(skops,
BPF_SOCK_OPS_STATE_CB_FLAG);
- /* Update results */
- {
- __u32 key = 0;
- struct tcpbpf_globals g, *gp;
-
- gp = bpf_map_lookup_elem(&global_map, &key);
- if (!gp)
- break;
- g = *gp;
- g.bad_cb_test_rv = bad_call_rv;
- g.good_cb_test_rv = good_call_rv;
- bpf_map_update_elem(&global_map, &key, &g,
- BPF_ANY);
- }
break;
case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
skops->sk_txhash = 0x12345f;
thdr = (struct tcphdr *)(header + offset);
v = thdr->syn;
- __u32 key = 1;
- bpf_map_update_elem(&sockopt_results, &key, &v,
- BPF_ANY);
+ global.tcp_saved_syn = v;
}
}
break;
break;
case BPF_SOCK_OPS_STATE_CB:
if (skops->args[1] == BPF_TCP_CLOSE) {
- __u32 key = 0;
- struct tcpbpf_globals g, *gp;
-
- gp = bpf_map_lookup_elem(&global_map, &key);
- if (!gp)
- break;
- g = *gp;
if (skops->args[0] == BPF_TCP_LISTEN) {
- g.num_listen++;
+ global.num_listen++;
} else {
- g.total_retrans = skops->total_retrans;
- g.data_segs_in = skops->data_segs_in;
- g.data_segs_out = skops->data_segs_out;
- g.bytes_received = skops->bytes_received;
- g.bytes_acked = skops->bytes_acked;
+ global.total_retrans = skops->total_retrans;
+ global.data_segs_in = skops->data_segs_in;
+ global.data_segs_out = skops->data_segs_out;
+ global.bytes_received = skops->bytes_received;
+ global.bytes_acked = skops->bytes_acked;
}
- g.num_close_events++;
- bpf_map_update_elem(&global_map, &key, &g,
- BPF_ANY);
+ global.num_close_events++;
}
break;
case BPF_SOCK_OPS_TCP_LISTEN_CB:
v = bpf_setsockopt(skops, IPPROTO_TCP, TCP_SAVE_SYN,
&save_syn, sizeof(save_syn));
/* Update global map w/ result of setsock opt */
- __u32 key = 0;
-
- bpf_map_update_elem(&sockopt_results, &key, &v, BPF_ANY);
+ global.tcp_save_syn = v;
break;
default:
rv = -1;
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/types.h>
-#include <linux/tcp.h>
#include <linux/socket.h>
#include <linux/pkt_cls.h>
#include <linux/erspan.h>
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
struct iphdr *iph = data;
- struct tcphdr *tcp = data + sizeof(*iph);
void *data_end = (void *)(long)skb->data_end;
int ret;
/* single length check */
- if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
+ if (data + sizeof(*iph) > data_end) {
ERROR(1);
return TC_ACT_SHOT;
}
key.tunnel_ttl = 64;
if (iph->protocol == IPPROTO_ICMP) {
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
- } else {
- if (iph->protocol != IPPROTO_TCP || iph->ihl != 5)
- return TC_ACT_SHOT;
-
- if (tcp->dest == bpf_htons(5200))
- key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
- else if (tcp->dest == bpf_htons(5201))
- key.remote_ipv4 = 0xac100165; /* 172.16.1.101 */
- else
- return TC_ACT_SHOT;
}
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
struct iphdr *iph = data;
- struct tcphdr *tcp = data + sizeof(*iph);
void *data_end = (void *)(long)skb->data_end;
int ret;
/* single length check */
- if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
+ if (data + sizeof(*iph) > data_end) {
ERROR(1);
return TC_ACT_SHOT;
}
__builtin_memset(&key, 0x0, sizeof(key));
- key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_ttl = 64;
+ if (iph->protocol == IPPROTO_ICMP) {
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ }
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
struct ipv6hdr *iph = data;
- struct tcphdr *tcp = data + sizeof(*iph);
void *data_end = (void *)(long)skb->data_end;
int ret;
/* single length check */
- if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
+ if (data + sizeof(*iph) > data_end) {
ERROR(1);
return TC_ACT_SHOT;
}
- key.remote_ipv6[0] = bpf_htonl(0x2401db00);
key.tunnel_ttl = 64;
-
if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) {
- key.remote_ipv6[3] = bpf_htonl(1);
- } else {
- if (iph->nexthdr != 6 /* NEXTHDR_TCP */) {
- ERROR(iph->nexthdr);
- return TC_ACT_SHOT;
- }
-
- if (tcp->dest == bpf_htons(5200)) {
- key.remote_ipv6[3] = bpf_htonl(1);
- } else if (tcp->dest == bpf_htons(5201)) {
- key.remote_ipv6[3] = bpf_htonl(2);
- } else {
- ERROR(tcp->dest);
- return TC_ACT_SHOT;
- }
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
}
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+++ /dev/null
-#!/usr/bin/env python3
-#
-# SPDX-License-Identifier: GPL-2.0
-#
-
-import sys, os, os.path, getopt
-import socket, time
-import subprocess
-import select
-
-def read(sock, n):
- buf = b''
- while len(buf) < n:
- rem = n - len(buf)
- try: s = sock.recv(rem)
- except (socket.error) as e: return b''
- buf += s
- return buf
-
-def send(sock, s):
- total = len(s)
- count = 0
- while count < total:
- try: n = sock.send(s)
- except (socket.error) as e: n = 0
- if n == 0:
- return count;
- count += n
- return count
-
-
-serverPort = int(sys.argv[1])
-
-# create active socket
-sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
-try:
- sock.connect(('::1', serverPort))
-except socket.error as e:
- sys.exit(1)
-
-buf = b''
-n = 0
-while n < 1000:
- buf += b'+'
- n += 1
-
-sock.settimeout(1);
-n = send(sock, buf)
-n = read(sock, 500)
-sys.exit(0)
+++ /dev/null
-#!/usr/bin/env python3
-#
-# SPDX-License-Identifier: GPL-2.0
-#
-
-import sys, os, os.path, getopt
-import socket, time
-import subprocess
-import select
-
-def read(sock, n):
- buf = b''
- while len(buf) < n:
- rem = n - len(buf)
- try: s = sock.recv(rem)
- except (socket.error) as e: return b''
- buf += s
- return buf
-
-def send(sock, s):
- total = len(s)
- count = 0
- while count < total:
- try: n = sock.send(s)
- except (socket.error) as e: n = 0
- if n == 0:
- return count;
- count += n
- return count
-
-
-SERVER_PORT = 12877
-MAX_PORTS = 2
-
-serverPort = SERVER_PORT
-serverSocket = None
-
-# create passive socket
-serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
-
-try: serverSocket.bind(('::1', 0))
-except socket.error as msg:
- print('bind fails: ' + str(msg))
-
-sn = serverSocket.getsockname()
-serverPort = sn[1]
-
-cmdStr = ("./tcp_client.py %d &") % (serverPort)
-os.system(cmdStr)
-
-buf = b''
-n = 0
-while n < 500:
- buf += b'.'
- n += 1
-
-serverSocket.listen(MAX_PORTS)
-readList = [serverSocket]
-
-while True:
- readyRead, readyWrite, inError = \
- select.select(readList, [], [], 2)
-
- if len(readyRead) > 0:
- waitCount = 0
- for sock in readyRead:
- if sock == serverSocket:
- (clientSocket, address) = serverSocket.accept()
- address = str(address[0])
- readList.append(clientSocket)
- else:
- sock.settimeout(1);
- s = read(sock, 1000)
- n = send(sock, buf)
- sock.close()
- serverSocket.close()
- sys.exit(0)
- else:
- print('Select timeout!')
- sys.exit(1)
static void test_map_large(void)
{
+
struct bigkey {
int a;
- char b[116];
+ char b[4096];
long long c;
} key;
int fd, i, value;
___ok; \
})
+#define ASSERT_NEQ(actual, expected, name) ({ \
+ static int duration = 0; \
+ typeof(actual) ___act = (actual); \
+ typeof(expected) ___exp = (expected); \
+ bool ___ok = ___act != ___exp; \
+ CHECK(!___ok, (name), \
+ "unexpected %s: actual %lld == expected %lld\n", \
+ (name), (long long)(___act), (long long)(___exp)); \
+ ___ok; \
+})
+
#define ASSERT_STREQ(actual, expected, name) ({ \
static int duration = 0; \
const char *___act = actual; \
__u64 bytes_acked;
__u32 num_listen;
__u32 num_close_events;
+ __u32 tcp_save_syn;
+ __u32 tcp_saved_syn;
};
#endif
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-#include <inttypes.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <errno.h>
-#include <string.h>
-#include <linux/bpf.h>
-#include <sys/types.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "bpf_rlimit.h"
-#include "bpf_util.h"
-#include "cgroup_helpers.h"
-
-#include "test_tcpbpf.h"
-
-/* 3 comes from one listening socket + both ends of the connection */
-#define EXPECTED_CLOSE_EVENTS 3
-
-#define EXPECT_EQ(expected, actual, fmt) \
- do { \
- if ((expected) != (actual)) { \
- printf(" Value of: " #actual "\n" \
- " Actual: %" fmt "\n" \
- " Expected: %" fmt "\n", \
- (actual), (expected)); \
- ret--; \
- } \
- } while (0)
-
-int verify_result(const struct tcpbpf_globals *result)
-{
- __u32 expected_events;
- int ret = 0;
-
- expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) |
- (1 << BPF_SOCK_OPS_RWND_INIT) |
- (1 << BPF_SOCK_OPS_TCP_CONNECT_CB) |
- (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) |
- (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) |
- (1 << BPF_SOCK_OPS_NEEDS_ECN) |
- (1 << BPF_SOCK_OPS_STATE_CB) |
- (1 << BPF_SOCK_OPS_TCP_LISTEN_CB));
-
- EXPECT_EQ(expected_events, result->event_map, "#" PRIx32);
- EXPECT_EQ(501ULL, result->bytes_received, "llu");
- EXPECT_EQ(1002ULL, result->bytes_acked, "llu");
- EXPECT_EQ(1, result->data_segs_in, PRIu32);
- EXPECT_EQ(1, result->data_segs_out, PRIu32);
- EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32);
- EXPECT_EQ(0, result->good_cb_test_rv, PRIu32);
- EXPECT_EQ(1, result->num_listen, PRIu32);
- EXPECT_EQ(EXPECTED_CLOSE_EVENTS, result->num_close_events, PRIu32);
-
- return ret;
-}
-
-int verify_sockopt_result(int sock_map_fd)
-{
- __u32 key = 0;
- int ret = 0;
- int res;
- int rv;
-
- /* check setsockopt for SAVE_SYN */
- rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
- EXPECT_EQ(0, rv, "d");
- EXPECT_EQ(0, res, "d");
- key = 1;
- /* check getsockopt for SAVED_SYN */
- rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
- EXPECT_EQ(0, rv, "d");
- EXPECT_EQ(1, res, "d");
- return ret;
-}
-
-static int bpf_find_map(const char *test, struct bpf_object *obj,
- const char *name)
-{
- struct bpf_map *map;
-
- map = bpf_object__find_map_by_name(obj, name);
- if (!map) {
- printf("%s:FAIL:map '%s' not found\n", test, name);
- return -1;
- }
- return bpf_map__fd(map);
-}
-
-int main(int argc, char **argv)
-{
- const char *file = "test_tcpbpf_kern.o";
- int prog_fd, map_fd, sock_map_fd;
- struct tcpbpf_globals g = {0};
- const char *cg_path = "/foo";
- int error = EXIT_FAILURE;
- struct bpf_object *obj;
- int cg_fd = -1;
- int retry = 10;
- __u32 key = 0;
- int rv;
-
- cg_fd = cgroup_setup_and_join(cg_path);
- if (cg_fd < 0)
- goto err;
-
- if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
- printf("FAILED: load_bpf_file failed for: %s\n", file);
- goto err;
- }
-
- rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
- if (rv) {
- printf("FAILED: bpf_prog_attach: %d (%s)\n",
- error, strerror(errno));
- goto err;
- }
-
- if (system("./tcp_server.py")) {
- printf("FAILED: TCP server\n");
- goto err;
- }
-
- map_fd = bpf_find_map(__func__, obj, "global_map");
- if (map_fd < 0)
- goto err;
-
- sock_map_fd = bpf_find_map(__func__, obj, "sockopt_results");
- if (sock_map_fd < 0)
- goto err;
-
-retry_lookup:
- rv = bpf_map_lookup_elem(map_fd, &key, &g);
- if (rv != 0) {
- printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
- goto err;
- }
-
- if (g.num_close_events != EXPECTED_CLOSE_EVENTS && retry--) {
- printf("Unexpected number of close events (%d), retrying!\n",
- g.num_close_events);
- usleep(100);
- goto retry_lookup;
- }
-
- if (verify_result(&g)) {
- printf("FAILED: Wrong stats\n");
- goto err;
- }
-
- if (verify_sockopt_result(sock_map_fd)) {
- printf("FAILED: Wrong sockopt stats\n");
- goto err;
- }
-
- printf("PASSED!\n");
- error = 0;
-err:
- bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
- close(cg_fd);
- cleanup_cgroup_environment();
- return error;
-}
# Root namespace with metadata-mode tunnel + BPF
# Device names and addresses:
# veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay)
-# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200 (overlay)
+# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200, IPv6: 1::22 (overlay)
#
# Namespace at_ns0 with native tunnel
# Device names and addresses:
# veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay)
-# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100 (overlay)
+# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100, IPv6: 1::11 (overlay)
#
#
# End-to-end ping packet flow
ip addr add dev $DEV 10.1.1.200/24
}
-add_ipip6tnl_tunnel()
+add_ip6tnl_tunnel()
{
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip link add dev $DEV_NS type $TYPE \
local ::11 remote ::22
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 1::11/96
ip netns exec at_ns0 ip link set dev $DEV_NS up
# root namespace
ip link add dev $DEV type $TYPE external
ip addr add dev $DEV 10.1.1.200/24
+ ip addr add dev $DEV 1::22/96
ip link set dev $DEV up
}
check $TYPE
config_device
- add_ipip6tnl_tunnel
+ add_ip6tnl_tunnel
ip link set dev veth1 mtu 1500
attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel
# underlay
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
+test_ip6ip6()
+{
+ TYPE=ip6tnl
+ DEV_NS=ip6ip6tnl00
+ DEV=ip6ip6tnl11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6tnl_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ip6ip6_set_tunnel ip6ip6_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # ip6 over ip6
+ ping6 $PING_ARG 1::11
+ check_err $?
+ ip netns exec at_ns0 ping6 $PING_ARG 1::22
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: ip6$TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
+}
+
setup_xfrm_tunnel()
{
auth=0x$(printf '1%.0s' {1..40})
ip link del veth1 2> /dev/null
ip link del ipip11 2> /dev/null
ip link del ipip6tnl11 2> /dev/null
+ ip link del ip6ip6tnl11 2> /dev/null
ip link del gretap11 2> /dev/null
ip link del ip6gre11 2> /dev/null
ip link del ip6gretap11 2> /dev/null
test_ipip6
errors=$(( $errors + $? ))
+ echo "Testing IP6IP6 tunnel..."
+ test_ip6ip6
+ errors=$(( $errors + $? ))
+
echo "Testing IPSec tunnel..."
test_xfrm_tunnel
errors=$(( $errors + $? ))
.errstr_unpriv = "R1 leaks addr",
.result = REJECT,
},
+{
+ "pkt > pkt_end taken check",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, // 0. r2 = *(u32 *)(r1 + data_end)
+ offsetof(struct __sk_buff, data_end)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, // 1. r4 = *(u32 *)(r1 + data)
+ offsetof(struct __sk_buff, data)),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_4), // 2. r3 = r4
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 42), // 3. r3 += 42
+ BPF_MOV64_IMM(BPF_REG_1, 0), // 4. r1 = 0
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 2), // 5. if r3 > r2 goto 8
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 14), // 6. r4 += 14
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_4), // 7. r1 = r4
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 1), // 8. if r3 > r2 goto 10
+ BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1, 9), // 9. r2 = *(u8 *)(r1 + 9)
+ BPF_MOV64_IMM(BPF_REG_0, 0), // 10. r0 = 0
+ BPF_EXIT_INSN(), // 11. exit
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SK_SKB,
+},
+{
+ "pkt_end < pkt taken check",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, // 0. r2 = *(u32 *)(r1 + data_end)
+ offsetof(struct __sk_buff, data_end)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, // 1. r4 = *(u32 *)(r1 + data)
+ offsetof(struct __sk_buff, data)),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_4), // 2. r3 = r4
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 42), // 3. r3 += 42
+ BPF_MOV64_IMM(BPF_REG_1, 0), // 4. r1 = 0
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 2), // 5. if r3 > r2 goto 8
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 14), // 6. r4 += 14
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_4), // 7. r1 = r4
+ BPF_JMP_REG(BPF_JLT, BPF_REG_2, BPF_REG_3, 1), // 8. if r2 < r3 goto 10
+ BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1, 9), // 9. r2 = *(u8 *)(r1 + 9)
+ BPF_MOV64_IMM(BPF_REG_0, 0), // 10. r0 = 0
+ BPF_EXIT_INSN(), // 11. exit
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SK_SKB,
+},
blackhole_route_test
irif_disabled_test
erif_disabled_test
+ blackhole_nexthop_test
"
NUM_NETIFS=4
devlink_trap_action_set $trap_name "drop"
}
+__blackhole_nexthop_test()
+{
+ local flags=$1; shift
+ local subnet=$1; shift
+ local proto=$1; shift
+ local dip=$1; shift
+ local trap_name="blackhole_nexthop"
+ local mz_pid
+
+ RET=0
+
+ ip -$flags nexthop add id 1 blackhole
+ ip -$flags route add $subnet nhid 1
+ tc filter add dev $rp2 egress protocol $proto pref 1 handle 101 \
+ flower skip_hw dst_ip $dip ip_proto udp action drop
+
+ # Generate packets to the blackhole nexthop
+ $MZ $h1 -$flags -t udp "sp=54321,dp=12345" -c 0 -p 100 -b $rp1mac \
+ -B $dip -d 1msec -q &
+ mz_pid=$!
+
+ devlink_trap_drop_test $trap_name $rp2 101
+ log_test "Blackhole nexthop: IPv$flags"
+
+ devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101
+ ip -$flags route del $subnet
+ ip -$flags nexthop del id 1
+}
+
+blackhole_nexthop_test()
+{
+ __blackhole_nexthop_test "4" "198.51.100.0/30" "ip" $h2_ipv4
+ __blackhole_nexthop_test "6" "2001:db8:2::/120" "ipv6" $h2_ipv6
+}
+
trap cleanup EXIT
setup_prepare
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ create_8021ad_vlan_upper_on_top_front_panel_port
+ create_8021ad_vlan_upper_on_top_bridge_port
+ create_8021ad_vlan_upper_on_top_lag
+ create_8021ad_vlan_upper_on_top_bridge
+ create_8021ad_vlan_upper_on_top_8021ad_bridge
+ create_vlan_upper_on_top_8021ad_bridge
+ create_vlan_upper_on_top_front_panel_enslaved_to_8021ad_bridge
+ create_vlan_upper_on_top_lag_enslaved_to_8021ad_bridge
+ enslave_front_panel_with_vlan_upper_to_8021ad_bridge
+ enslave_lag_with_vlan_upper_to_8021ad_bridge
+ add_ip_address_to_8021ad_bridge
+ switch_bridge_protocol_from_8021q_to_8021ad
+"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+
+setup_prepare()
+{
+ swp1=${NETIFS[p1]}
+ swp2=${NETIFS[p2]}
+
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+
+ sleep 10
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+}
+
+create_vlan_upper_on_top_of_bridge()
+{
+ RET=0
+
+ local bridge_proto=$1; shift
+ local netdev_proto=$1; shift
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol $bridge_proto vlan_default_pvid 0 mcast_snooping 0
+
+ ip link set dev br0 up
+ ip link set dev $swp1 master br0
+
+ ip link add name br0.100 link br0 type vlan \
+ protocol $netdev_proto id 100 2>/dev/null
+ check_fail $? "$netdev_proto vlan upper creation on top of an $bridge_proto bridge not rejected"
+
+ ip link add name br0.100 link br0 type vlan \
+ protocol $netdev_proto id 100 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "$netdev_proto vlan upper creation on top of an $bridge_proto bridge rejected without extack"
+
+ log_test "create $netdev_proto vlan upper on top $bridge_proto bridge"
+
+ ip link del dev br0
+}
+
+create_8021ad_vlan_upper_on_top_front_panel_port()
+{
+ RET=0
+
+ ip link add name $swp1.100 link $swp1 type vlan \
+ protocol 802.1ad id 100 2>/dev/null
+ check_fail $? "802.1ad vlan upper creation on top of a front panel not rejected"
+
+ ip link add name $swp1.100 link $swp1 type vlan \
+ protocol 802.1ad id 100 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "802.1ad vlan upper creation on top of a front panel rejected without extack"
+
+ log_test "create 802.1ad vlan upper on top of a front panel"
+}
+
+create_8021ad_vlan_upper_on_top_bridge_port()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_default_pvid 0 mcast_snooping 0
+
+ ip link set dev $swp1 master br0
+ ip link set dev br0 up
+
+ ip link add name $swp1.100 link $swp1 type vlan \
+ protocol 802.1ad id 100 2>/dev/null
+ check_fail $? "802.1ad vlan upper creation on top of a bridge port not rejected"
+
+ ip link add name $swp1.100 link $swp1 type vlan \
+ protocol 802.1ad id 100 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "802.1ad vlan upper creation on top of a bridge port rejected without extack"
+
+ log_test "create 802.1ad vlan upper on top of a bridge port"
+
+ ip link del dev br0
+}
+
+create_8021ad_vlan_upper_on_top_lag()
+{
+ RET=0
+
+ ip link add name bond1 type bond mode 802.3ad
+ ip link set dev $swp1 down
+ ip link set dev $swp1 master bond1
+
+ ip link add name bond1.100 link bond1 type vlan \
+ protocol 802.1ad id 100 2>/dev/null
+ check_fail $? "802.1ad vlan upper creation on top of a lag not rejected"
+
+ ip link add name bond1.100 link bond1 type vlan \
+ protocol 802.1ad id 100 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "802.1ad vlan upper creation on top of a lag rejected without extack"
+
+ log_test "create 802.1ad vlan upper on top of a lag"
+
+ ip link del dev bond1
+}
+
+create_8021ad_vlan_upper_on_top_bridge()
+{
+ RET=0
+
+ create_vlan_upper_on_top_of_bridge "802.1q" "802.1ad"
+}
+
+create_8021ad_vlan_upper_on_top_8021ad_bridge()
+{
+ RET=0
+
+ create_vlan_upper_on_top_of_bridge "802.1ad" "802.1ad"
+}
+
+create_vlan_upper_on_top_8021ad_bridge()
+{
+ RET=0
+
+ create_vlan_upper_on_top_of_bridge "802.1ad" "802.1q"
+}
+
+create_vlan_upper_on_top_front_panel_enslaved_to_8021ad_bridge()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+ ip link set dev br0 up
+
+ ip link set dev $swp1 master br0
+
+ ip link add name $swp1.100 link $swp1 type vlan id 100 2>/dev/null
+ check_fail $? "vlan upper creation on top of front panel enslaved to 802.1ad bridge not rejected"
+
+ ip link add name $swp1.100 link $swp1 type vlan id 100 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "vlan upper creation on top of front panel enslaved to 802.1ad bridge rejected without extack"
+
+ log_test "create vlan upper on top of front panel enslaved to 802.1ad bridge"
+
+ ip link del dev br0
+}
+
+create_vlan_upper_on_top_lag_enslaved_to_8021ad_bridge()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+ ip link set dev br0 up
+
+ ip link add name bond1 type bond mode 802.3ad
+ ip link set dev $swp1 down
+ ip link set dev $swp1 master bond1
+ ip link set dev bond1 master br0
+
+ ip link add name bond1.100 link bond1 type vlan id 100 2>/dev/null
+ check_fail $? "vlan upper creation on top of lag enslaved to 802.1ad bridge not rejected"
+
+ ip link add name bond1.100 link bond1 type vlan id 100 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "vlan upper creation on top of lag enslaved to 802.1ad bridge rejected without extack"
+
+ log_test "create vlan upper on top of lag enslaved to 802.1ad bridge"
+
+ ip link del dev bond1
+ ip link del dev br0
+}
+
+enslave_front_panel_with_vlan_upper_to_8021ad_bridge()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+ ip link set dev br0 up
+
+ ip link add name $swp1.100 link $swp1 type vlan id 100
+
+ ip link set dev $swp1 master br0 2>/dev/null
+ check_fail $? "front panel with vlan upper enslavemnt to 802.1ad bridge not rejected"
+
+ ip link set dev $swp1 master br0 2>&1 >/dev/null | grep -q mlxsw_spectrum
+ check_err $? "front panel with vlan upper enslavemnt to 802.1ad bridge rejected without extack"
+
+ log_test "enslave front panel with vlan upper to 802.1ad bridge"
+
+ ip link del dev $swp1.100
+ ip link del dev br0
+}
+
+enslave_lag_with_vlan_upper_to_8021ad_bridge()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+ ip link set dev br0 up
+
+ ip link add name bond1 type bond mode 802.3ad
+ ip link set dev $swp1 down
+ ip link set dev $swp1 master bond1
+ ip link add name bond1.100 link bond1 type vlan id 100
+
+ ip link set dev bond1 master br0 2>/dev/null
+ check_fail $? "lag with vlan upper enslavemnt to 802.1ad bridge not rejected"
+
+ ip link set dev bond1 master br0 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "lag with vlan upper enslavemnt to 802.1ad bridge rejected without extack"
+
+ log_test "enslave lag with vlan upper to 802.1ad bridge"
+
+ ip link del dev bond1
+ ip link del dev br0
+}
+
+
+add_ip_address_to_8021ad_bridge()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+
+ ip link set dev br0 up
+ ip link set dev $swp1 master br0
+
+ ip addr add dev br0 192.0.2.17/28 2>/dev/null
+ check_fail $? "IP address addition to 802.1ad bridge not rejected"
+
+ ip addr add dev br0 192.0.2.17/28 2>&1 >/dev/null | grep -q mlxsw_spectrum
+ check_err $? "IP address addition to 802.1ad bridge rejected without extack"
+
+ log_test "IP address addition to 802.1ad bridge"
+
+ ip link del dev br0
+}
+
+switch_bridge_protocol_from_8021q_to_8021ad()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+
+ ip link set dev br0 up
+ ip link set dev $swp1 master br0
+
+ ip link set dev br0 type bridge vlan_protocol 802.1q 2>/dev/null
+ check_fail $? "switching bridge protocol from 802.1q to 802.1ad not rejected"
+
+ log_test "switch bridge protocol"
+
+ ip link del dev br0
+}
+
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
bridge_extern_learn_test
neigh_offload_test
nexthop_offload_test
+ nexthop_obj_invalid_test
+ nexthop_obj_offload_test
+ nexthop_obj_group_offload_test
+ nexthop_obj_blackhole_offload_test
+ nexthop_obj_route_offload_test
devlink_reload_test
"
NUM_NETIFS=2
sysctl_restore net.ipv6.conf.$swp2.keep_addr_on_down
}
+nexthop_obj_invalid_test()
+{
+ # Test that invalid nexthop object configurations are rejected
+ RET=0
+
+ simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+ simple_if_init $swp2 192.0.2.2/24 2001:db8:1::2/64
+ setup_wait
+
+ ip nexthop add id 1 via 192.0.2.3 fdb
+ check_fail $? "managed to configure an FDB nexthop when should not"
+
+ ip nexthop add id 1 encap mpls 200/300 via 192.0.2.3 dev $swp1
+ check_fail $? "managed to configure a nexthop with MPLS encap when should not"
+
+ ip nexthop add id 1 dev $swp1
+ ip nexthop add id 2 dev $swp1
+ ip nexthop add id 10 group 1/2
+ check_fail $? "managed to configure a nexthop group with device-only nexthops when should not"
+
+ log_test "nexthop objects - invalid configurations"
+
+ ip nexthop del id 2
+ ip nexthop del id 1
+
+ simple_if_fini $swp2 192.0.2.2/24 2001:db8:1::2/64
+ simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+nexthop_obj_offload_test()
+{
+ # Test offload indication of nexthop objects
+ RET=0
+
+ simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+ simple_if_init $swp2
+ setup_wait
+
+ ip nexthop add id 1 via 192.0.2.2 dev $swp1
+ ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "nexthop not marked as offloaded when should"
+
+ ip neigh replace 192.0.2.2 nud failed dev $swp1
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "nexthop marked as offloaded after setting neigh to failed state"
+
+ ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "nexthop not marked as offloaded after neigh replace"
+
+ ip nexthop replace id 1 via 192.0.2.3 dev $swp1
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "nexthop marked as offloaded after replacing to use an invalid address"
+
+ ip nexthop replace id 1 via 192.0.2.2 dev $swp1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "nexthop not marked as offloaded after replacing to use a valid address"
+
+ log_test "nexthop objects offload indication"
+
+ ip neigh del 192.0.2.2 dev $swp1
+ ip nexthop del id 1
+
+ simple_if_fini $swp2
+ simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+nexthop_obj_group_offload_test()
+{
+ # Test offload indication of nexthop group objects
+ RET=0
+
+ simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+ simple_if_init $swp2
+ setup_wait
+
+ ip nexthop add id 1 via 192.0.2.2 dev $swp1
+ ip nexthop add id 2 via 2001:db8:1::2 dev $swp1
+ ip nexthop add id 10 group 1/2
+ ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+ ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+ ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "IPv4 nexthop not marked as offloaded when should"
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 2
+ check_err $? "IPv6 nexthop not marked as offloaded when should"
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 10
+ check_err $? "nexthop group not marked as offloaded when should"
+
+ # Invalidate nexthop id 1
+ ip neigh replace 192.0.2.2 nud failed dev $swp1
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip nexthop show id 10
+ check_fail $? "nexthop group not marked as offloaded with one valid nexthop"
+
+ # Invalidate nexthop id 2
+ ip neigh replace 2001:db8:1::2 nud failed dev $swp1
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip nexthop show id 10
+ check_err $? "nexthop group marked as offloaded when should not"
+
+ # Revalidate nexthop id 1
+ ip nexthop replace id 1 via 192.0.2.3 dev $swp1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 10
+ check_err $? "nexthop group not marked as offloaded after revalidating nexthop"
+
+ log_test "nexthop group objects offload indication"
+
+ ip neigh del 2001:db8:1::2 dev $swp1
+ ip neigh del 192.0.2.3 dev $swp1
+ ip neigh del 192.0.2.2 dev $swp1
+ ip nexthop del id 10
+ ip nexthop del id 2
+ ip nexthop del id 1
+
+ simple_if_fini $swp2
+ simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+nexthop_obj_blackhole_offload_test()
+{
+ # Test offload indication of blackhole nexthop objects
+ RET=0
+
+ ip nexthop add id 1 blackhole
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "Blackhole nexthop not marked as offloaded when should"
+
+ ip nexthop add id 10 group 1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 10
+ check_err $? "Nexthop group not marked as offloaded when should"
+
+ log_test "blackhole nexthop objects offload indication"
+
+ ip nexthop del id 10
+ ip nexthop del id 1
+}
+
+nexthop_obj_route_offload_test()
+{
+ # Test offload indication of routes using nexthop objects
+ RET=0
+
+ simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+ simple_if_init $swp2
+ setup_wait
+
+ ip nexthop add id 1 via 192.0.2.2 dev $swp1
+ ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+ ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+
+ ip route replace 198.51.100.0/24 nhid 1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show 198.51.100.0/24
+ check_err $? "route not marked as offloaded when using valid nexthop"
+
+ ip nexthop replace id 1 via 192.0.2.3 dev $swp1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show 198.51.100.0/24
+ check_err $? "route not marked as offloaded after replacing valid nexthop with a valid one"
+
+ ip nexthop replace id 1 via 192.0.2.4 dev $swp1
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip route show 198.51.100.0/24
+ check_err $? "route marked as offloaded after replacing valid nexthop with an invalid one"
+
+ ip nexthop replace id 1 via 192.0.2.2 dev $swp1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show 198.51.100.0/24
+ check_err $? "route not marked as offloaded after replacing invalid nexthop with a valid one"
+
+ log_test "routes using nexthop objects offload indication"
+
+ ip route del 198.51.100.0/24
+ ip neigh del 192.0.2.3 dev $swp1
+ ip neigh del 192.0.2.2 dev $swp1
+ ip nexthop del id 1
+
+ simple_if_fini $swp2
+ simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
devlink_reload_test()
{
# Test that after executing all the above configuration tests, a
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source ethtool-common.sh
+
+function get_value {
+ local query="${SETTINGS_MAP[$1]}"
+
+ echo $(ethtool -c $NSIM_NETDEV | \
+ awk -F':' -v pattern="$query:" '$0 ~ pattern {gsub(/[ \t]/, "", $2); print $2}')
+}
+
+function update_current_settings {
+ for key in ${!SETTINGS_MAP[@]}; do
+ CURRENT_SETTINGS[$key]=$(get_value $key)
+ done
+ echo ${CURRENT_SETTINGS[@]}
+}
+
+if ! ethtool -h | grep -q coalesce; then
+ echo "SKIP: No --coalesce support in ethtool"
+ exit 4
+fi
+
+NSIM_NETDEV=$(make_netdev)
+
+set -o pipefail
+
+declare -A SETTINGS_MAP=(
+ ["rx-frames-low"]="rx-frame-low"
+ ["tx-frames-low"]="tx-frame-low"
+ ["rx-frames-high"]="rx-frame-high"
+ ["tx-frames-high"]="tx-frame-high"
+ ["rx-usecs"]="rx-usecs"
+ ["rx-frames"]="rx-frames"
+ ["rx-usecs-irq"]="rx-usecs-irq"
+ ["rx-frames-irq"]="rx-frames-irq"
+ ["tx-usecs"]="tx-usecs"
+ ["tx-frames"]="tx-frames"
+ ["tx-usecs-irq"]="tx-usecs-irq"
+ ["tx-frames-irq"]="tx-frames-irq"
+ ["stats-block-usecs"]="stats-block-usecs"
+ ["pkt-rate-low"]="pkt-rate-low"
+ ["rx-usecs-low"]="rx-usecs-low"
+ ["tx-usecs-low"]="tx-usecs-low"
+ ["pkt-rate-high"]="pkt-rate-high"
+ ["rx-usecs-high"]="rx-usecs-high"
+ ["tx-usecs-high"]="tx-usecs-high"
+ ["sample-interval"]="sample-interval"
+)
+
+declare -A CURRENT_SETTINGS=(
+ ["rx-frames-low"]=""
+ ["tx-frames-low"]=""
+ ["rx-frames-high"]=""
+ ["tx-frames-high"]=""
+ ["rx-usecs"]=""
+ ["rx-frames"]=""
+ ["rx-usecs-irq"]=""
+ ["rx-frames-irq"]=""
+ ["tx-usecs"]=""
+ ["tx-frames"]=""
+ ["tx-usecs-irq"]=""
+ ["tx-frames-irq"]=""
+ ["stats-block-usecs"]=""
+ ["pkt-rate-low"]=""
+ ["rx-usecs-low"]=""
+ ["tx-usecs-low"]=""
+ ["pkt-rate-high"]=""
+ ["rx-usecs-high"]=""
+ ["tx-usecs-high"]=""
+ ["sample-interval"]=""
+)
+
+declare -A EXPECTED_SETTINGS=(
+ ["rx-frames-low"]=""
+ ["tx-frames-low"]=""
+ ["rx-frames-high"]=""
+ ["tx-frames-high"]=""
+ ["rx-usecs"]=""
+ ["rx-frames"]=""
+ ["rx-usecs-irq"]=""
+ ["rx-frames-irq"]=""
+ ["tx-usecs"]=""
+ ["tx-frames"]=""
+ ["tx-usecs-irq"]=""
+ ["tx-frames-irq"]=""
+ ["stats-block-usecs"]=""
+ ["pkt-rate-low"]=""
+ ["rx-usecs-low"]=""
+ ["tx-usecs-low"]=""
+ ["pkt-rate-high"]=""
+ ["rx-usecs-high"]=""
+ ["tx-usecs-high"]=""
+ ["sample-interval"]=""
+)
+
+# populate the expected settings map
+for key in ${!SETTINGS_MAP[@]}; do
+ EXPECTED_SETTINGS[$key]=$(get_value $key)
+done
+
+# test
+for key in ${!SETTINGS_MAP[@]}; do
+ value=$((RANDOM % $((2**32-1))))
+
+ ethtool -C $NSIM_NETDEV "$key" "$value"
+
+ EXPECTED_SETTINGS[$key]="$value"
+ expected=${EXPECTED_SETTINGS[@]}
+ current=$(update_current_settings)
+
+ check $? "$current" "$expected"
+ set +x
+done
+
+# bool settings which ethtool displays on the same line
+ethtool -C $NSIM_NETDEV adaptive-rx on
+s=$(ethtool -c $NSIM_NETDEV | grep -q "Adaptive RX: on TX: off")
+check $? "$s" ""
+
+ethtool -C $NSIM_NETDEV adaptive-tx on
+s=$(ethtool -c $NSIM_NETDEV | grep -q "Adaptive RX: on TX: on")
+check $? "$s" ""
+
+if [ $num_errors -eq 0 ]; then
+ echo "PASSED all $((num_passes)) checks"
+ exit 0
+else
+ echo "FAILED $num_errors/$((num_errors+num_passes)) checks"
+ exit 1
+fi
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+NSIM_ID=$((RANDOM % 1024))
+NSIM_DEV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_ID
+NSIM_DEV_DFS=/sys/kernel/debug/netdevsim/netdevsim$NSIM_ID/ports/0
+NSIM_NETDEV=
+num_passes=0
+num_errors=0
+
+function cleanup_nsim {
+ if [ -e $NSIM_DEV_SYS ]; then
+ echo $NSIM_ID > /sys/bus/netdevsim/del_device
+ fi
+}
+
+function cleanup {
+ cleanup_nsim
+}
+
+trap cleanup EXIT
+
+function check {
+ local code=$1
+ local str=$2
+ local exp_str=$3
+
+ if [ $code -ne 0 ]; then
+ ((num_errors++))
+ return
+ fi
+
+ if [ "$str" != "$exp_str" ]; then
+ echo -e "Expected: '$exp_str', got '$str'"
+ ((num_errors++))
+ return
+ fi
+
+ ((num_passes++))
+}
+
+function make_netdev {
+ # Make a netdevsim
+ old_netdevs=$(ls /sys/class/net)
+
+ if ! $(lsmod | grep -q netdevsim); then
+ modprobe netdevsim
+ fi
+
+ echo $NSIM_ID > /sys/bus/netdevsim/new_device
+ # get new device name
+ ls /sys/bus/netdevsim/devices/netdevsim${NSIM_ID}/net/
+}
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0-only
-NSIM_ID=$((RANDOM % 1024))
-NSIM_DEV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_ID
-NSIM_DEV_DFS=/sys/kernel/debug/netdevsim/netdevsim$NSIM_ID/ports/0
-NSIM_NETDEV=
-num_passes=0
-num_errors=0
-
-function cleanup_nsim {
- if [ -e $NSIM_DEV_SYS ]; then
- echo $NSIM_ID > /sys/bus/netdevsim/del_device
- fi
-}
-
-function cleanup {
- cleanup_nsim
-}
-
-trap cleanup EXIT
-
-function get_netdev_name {
- local -n old=$1
-
- new=$(ls /sys/class/net)
-
- for netdev in $new; do
- for check in $old; do
- [ $netdev == $check ] && break
- done
-
- if [ $netdev != $check ]; then
- echo $netdev
- break
- fi
- done
-}
-
-function check {
- local code=$1
- local str=$2
- local exp_str=$3
-
- if [ $code -ne 0 ]; then
- ((num_errors++))
- return
- fi
-
- if [ "$str" != "$exp_str" ]; then
- echo -e "Expected: '$exp_str', got '$str'"
- ((num_errors++))
- return
- fi
-
- ((num_passes++))
-}
+source ethtool-common.sh
# Bail if ethtool is too old
if ! ethtool -h | grep include-stat 2>&1 >/dev/null; then
exit 4
fi
-# Make a netdevsim
-old_netdevs=$(ls /sys/class/net)
-
-modprobe netdevsim
-echo $NSIM_ID > /sys/bus/netdevsim/new_device
-
-NSIM_NETDEV=`get_netdev_name old_netdevs`
+NSIM_NETDEV=$(make_netdev)
set -o pipefail
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source ethtool-common.sh
+
+function get_value {
+ local query="${SETTINGS_MAP[$1]}"
+
+ echo $(ethtool -g $NSIM_NETDEV | \
+ tail -n +$CURR_SETT_LINE | \
+ awk -F':' -v pattern="$query:" '$0 ~ pattern {gsub(/[\t ]/, "", $2); print $2}')
+}
+
+function update_current_settings {
+ for key in ${!SETTINGS_MAP[@]}; do
+ CURRENT_SETTINGS[$key]=$(get_value $key)
+ done
+ echo ${CURRENT_SETTINGS[@]}
+}
+
+if ! ethtool -h | grep -q set-ring >/dev/null; then
+ echo "SKIP: No --set-ring support in ethtool"
+ exit 4
+fi
+
+NSIM_NETDEV=$(make_netdev)
+
+set -o pipefail
+
+declare -A SETTINGS_MAP=(
+ ["rx"]="RX"
+ ["rx-mini"]="RX Mini"
+ ["rx-jumbo"]="RX Jumbo"
+ ["tx"]="TX"
+)
+
+declare -A EXPECTED_SETTINGS=(
+ ["rx"]=""
+ ["rx-mini"]=""
+ ["rx-jumbo"]=""
+ ["tx"]=""
+)
+
+declare -A CURRENT_SETTINGS=(
+ ["rx"]=""
+ ["rx-mini"]=""
+ ["rx-jumbo"]=""
+ ["tx"]=""
+)
+
+MAX_VALUE=$((RANDOM % $((2**32-1))))
+RING_MAX_LIST=$(ls $NSIM_DEV_DFS/ethtool/ring/)
+
+for ring_max_entry in $RING_MAX_LIST; do
+ echo $MAX_VALUE > $NSIM_DEV_DFS/ethtool/ring/$ring_max_entry
+done
+
+CURR_SETT_LINE=$(ethtool -g $NSIM_NETDEV | grep -i -m1 -n 'Current hardware settings' | cut -f1 -d:)
+
+# populate the expected settings map
+for key in ${!SETTINGS_MAP[@]}; do
+ EXPECTED_SETTINGS[$key]=$(get_value $key)
+done
+
+# test
+for key in ${!SETTINGS_MAP[@]}; do
+ value=$((RANDOM % $MAX_VALUE))
+
+ ethtool -G $NSIM_NETDEV "$key" "$value"
+
+ EXPECTED_SETTINGS[$key]="$value"
+ expected=${EXPECTED_SETTINGS[@]}
+ current=$(update_current_settings)
+
+ check $? "$current" "$expected"
+ set +x
+done
+
+if [ $num_errors -eq 0 ]; then
+ echo "PASSED all $((num_passes)) checks"
+ exit 0
+else
+ echo "FAILED $num_errors/$((num_errors+num_passes)) checks"
+ exit 1
+fi
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test is for checking the nexthop offload API. It makes use of netdevsim
+# which registers a listener to the nexthop notification chain.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ nexthop_single_add_test
+ nexthop_single_add_err_test
+ nexthop_group_add_test
+ nexthop_group_add_err_test
+ nexthop_group_replace_test
+ nexthop_group_replace_err_test
+ nexthop_single_replace_test
+ nexthop_single_replace_err_test
+ nexthop_single_in_group_replace_test
+ nexthop_single_in_group_replace_err_test
+ nexthop_single_in_group_delete_test
+ nexthop_single_in_group_delete_err_test
+ nexthop_replay_test
+ nexthop_replay_err_test
+"
+NETDEVSIM_PATH=/sys/bus/netdevsim/
+DEV_ADDR=1337
+DEV=netdevsim${DEV_ADDR}
+DEVLINK_DEV=netdevsim/${DEV}
+SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/
+NUM_NETIFS=0
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+nexthop_check()
+{
+ local nharg="$1"; shift
+ local expected="$1"; shift
+
+ out=$($IP nexthop show ${nharg} | sed -e 's/ *$//')
+ if [[ "$out" != "$expected" ]]; then
+ return 1
+ fi
+
+ return 0
+}
+
+nexthop_resource_check()
+{
+ local expected_occ=$1; shift
+
+ occ=$($DEVLINK -jp resource show $DEVLINK_DEV \
+ | jq '.[][][] | select(.name=="nexthops") | .["occ"]')
+
+ if [ $expected_occ -ne $occ ]; then
+ return 1
+ fi
+
+ return 0
+}
+
+nexthop_resource_set()
+{
+ local size=$1; shift
+
+ $DEVLINK resource set $DEVLINK_DEV path nexthops size $size
+ $DEVLINK dev reload $DEVLINK_DEV
+}
+
+nexthop_single_add_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+ check_err $? "Unexpected nexthop entry"
+
+ nexthop_resource_check 1
+ check_err $? "Wrong nexthop occupancy"
+
+ $IP nexthop del id 1
+ nexthop_resource_check 0
+ check_err $? "Wrong nexthop occupancy after delete"
+
+ log_test "Single nexthop add and delete"
+}
+
+nexthop_single_add_err_test()
+{
+ RET=0
+
+ nexthop_resource_set 1
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1 &> /dev/null
+ check_fail $? "Nexthop addition succeeded when should fail"
+
+ nexthop_resource_check 1
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Single nexthop add failure"
+
+ $IP nexthop flush &> /dev/null
+ nexthop_resource_set 9999
+}
+
+nexthop_group_add_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+ $IP nexthop add id 10 group 1/2
+ nexthop_check "id 10" "id 10 group 1/2 trap"
+ check_err $? "Unexpected nexthop group entry"
+
+ nexthop_resource_check 4
+ check_err $? "Wrong nexthop occupancy"
+
+ $IP nexthop del id 10
+ nexthop_resource_check 2
+ check_err $? "Wrong nexthop occupancy after delete"
+
+ $IP nexthop add id 10 group 1,20/2,39
+ nexthop_check "id 10" "id 10 group 1,20/2,39 trap"
+ check_err $? "Unexpected weighted nexthop group entry"
+
+ nexthop_resource_check 61
+ check_err $? "Wrong weighted nexthop occupancy"
+
+ $IP nexthop del id 10
+ nexthop_resource_check 2
+ check_err $? "Wrong nexthop occupancy after delete"
+
+ log_test "Nexthop group add and delete"
+
+ $IP nexthop flush &> /dev/null
+}
+
+nexthop_group_add_err_test()
+{
+ RET=0
+
+ nexthop_resource_set 2
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+ $IP nexthop add id 10 group 1/2 &> /dev/null
+ check_fail $? "Nexthop group addition succeeded when should fail"
+
+ nexthop_resource_check 2
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Nexthop group add failure"
+
+ $IP nexthop flush &> /dev/null
+ nexthop_resource_set 9999
+}
+
+nexthop_group_replace_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 3 via 192.0.2.4 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ $IP nexthop replace id 10 group 1/2/3
+ nexthop_check "id 10" "id 10 group 1/2/3 trap"
+ check_err $? "Unexpected nexthop group entry"
+
+ nexthop_resource_check 6
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Nexthop group replace"
+
+ $IP nexthop flush &> /dev/null
+}
+
+nexthop_group_replace_err_test()
+{
+ RET=0
+
+ nexthop_resource_set 5
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 3 via 192.0.2.4 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ $IP nexthop replace id 10 group 1/2/3 &> /dev/null
+ check_fail $? "Nexthop group replacement succeeded when should fail"
+
+ nexthop_check "id 10" "id 10 group 1/2 trap"
+ check_err $? "Unexpected nexthop group entry after failure"
+
+ nexthop_resource_check 5
+ check_err $? "Wrong nexthop occupancy after failure"
+
+ log_test "Nexthop group replace failure"
+
+ $IP nexthop flush &> /dev/null
+ nexthop_resource_set 9999
+}
+
+nexthop_single_replace_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+
+ $IP nexthop replace id 1 via 192.0.2.3 dev dummy1
+ nexthop_check "id 1" "id 1 via 192.0.2.3 dev dummy1 scope link trap"
+ check_err $? "Unexpected nexthop entry"
+
+ nexthop_resource_check 1
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Single nexthop replace"
+
+ $IP nexthop flush &> /dev/null
+}
+
+nexthop_single_replace_err_test()
+{
+ RET=0
+
+ # This is supposed to cause the replace to fail because the new nexthop
+ # is programmed before deleting the replaced one.
+ nexthop_resource_set 1
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+
+ $IP nexthop replace id 1 via 192.0.2.3 dev dummy1 &> /dev/null
+ check_fail $? "Nexthop replace succeeded when should fail"
+
+ nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+ check_err $? "Unexpected nexthop entry after failure"
+
+ nexthop_resource_check 1
+ check_err $? "Wrong nexthop occupancy after failure"
+
+ log_test "Single nexthop replace failure"
+
+ $IP nexthop flush &> /dev/null
+ nexthop_resource_set 9999
+}
+
+nexthop_single_in_group_replace_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ $IP nexthop replace id 1 via 192.0.2.4 dev dummy1
+ check_err $? "Failed to replace nexthop when should not"
+
+ nexthop_check "id 10" "id 10 group 1/2 trap"
+ check_err $? "Unexpected nexthop group entry"
+
+ nexthop_resource_check 4
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Single nexthop replace while in group"
+
+ $IP nexthop flush &> /dev/null
+}
+
+nexthop_single_in_group_replace_err_test()
+{
+ RET=0
+
+ nexthop_resource_set 5
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ $IP nexthop replace id 1 via 192.0.2.4 dev dummy1 &> /dev/null
+ check_fail $? "Nexthop replacement succeeded when should fail"
+
+ nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+ check_err $? "Unexpected nexthop entry after failure"
+
+ nexthop_check "id 10" "id 10 group 1/2 trap"
+ check_err $? "Unexpected nexthop group entry after failure"
+
+ nexthop_resource_check 4
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Single nexthop replace while in group failure"
+
+ $IP nexthop flush &> /dev/null
+ nexthop_resource_set 9999
+}
+
+nexthop_single_in_group_delete_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ $IP nexthop del id 1
+ nexthop_check "id 10" "id 10 group 2 trap"
+ check_err $? "Unexpected nexthop group entry"
+
+ nexthop_resource_check 2
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Single nexthop delete while in group"
+
+ $IP nexthop flush &> /dev/null
+}
+
+nexthop_single_in_group_delete_err_test()
+{
+ RET=0
+
+ # First, nexthop 1 will be deleted, which will reduce the occupancy to
+ # 5. Afterwards, a replace notification will be sent for nexthop group
+ # 10 with only two nexthops. Since the new group is allocated before
+ # the old is deleted, the replacement will fail as it will result in an
+ # occupancy of 7.
+ nexthop_resource_set 6
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 3 via 192.0.2.4 dev dummy1
+ $IP nexthop add id 10 group 1/2/3
+
+ $IP nexthop del id 1
+
+ nexthop_resource_check 5
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Single nexthop delete while in group failure"
+
+ $IP nexthop flush &> /dev/null
+ nexthop_resource_set 9999
+}
+
+nexthop_replay_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ $DEVLINK dev reload $DEVLINK_DEV
+ check_err $? "Failed to reload when should not"
+
+ nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+ check_err $? "Unexpected nexthop entry after reload"
+
+ nexthop_check "id 2" "id 2 via 192.0.2.3 dev dummy1 scope link trap"
+ check_err $? "Unexpected nexthop entry after reload"
+
+ nexthop_check "id 10" "id 10 group 1/2 trap"
+ check_err $? "Unexpected nexthop group entry after reload"
+
+ nexthop_resource_check 4
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Nexthop replay"
+
+ $IP nexthop flush &> /dev/null
+}
+
+nexthop_replay_err_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ # Reduce size of nexthop resource so that reload will fail.
+ $DEVLINK resource set $DEVLINK_DEV path nexthops size 3
+ $DEVLINK dev reload $DEVLINK_DEV &> /dev/null
+ check_fail $? "Reload succeeded when should fail"
+
+ $DEVLINK resource set $DEVLINK_DEV path nexthops size 9999
+ $DEVLINK dev reload $DEVLINK_DEV
+ check_err $? "Failed to reload when should not"
+
+ log_test "Nexthop replay failure"
+
+ $IP nexthop flush &> /dev/null
+}
+
+setup_prepare()
+{
+ local netdev
+
+ modprobe netdevsim &> /dev/null
+
+ echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device
+ while [ ! -d $SYSFS_NET_DIR ] ; do :; done
+
+ set -e
+
+ ip netns add testns1
+ devlink dev reload $DEVLINK_DEV netns testns1
+
+ IP="ip -netns testns1"
+ DEVLINK="devlink -N testns1"
+
+ $IP link add name dummy1 up type dummy
+ $IP address add 192.0.2.1/24 dev dummy1
+
+ set +e
+}
+
+cleanup()
+{
+ pre_cleanup
+ ip netns del testns1
+ echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device
+ modprobe -r netdevsim &> /dev/null
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS
TEST_PROGS += devlink_port_split.py
TEST_PROGS += drop_monitor_tests.sh
TEST_PROGS += vrf_route_leaking.sh
+TEST_PROGS += bareudp.sh
TEST_PROGS_EXTENDED := in_netns.sh
TEST_GEN_FILES = socket nettest
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+# Test various bareudp tunnel configurations.
+#
+# The bareudp module allows to tunnel network protocols like IP or MPLS over
+# UDP, without adding any intermediate header. This scripts tests several
+# configurations of bareudp (using IPv4 or IPv6 as underlay and transporting
+# IPv4, IPv6 or MPLS packets on the overlay).
+#
+# Network topology:
+#
+# * A chain of 4 network namespaces, connected with veth pairs. Each veth
+# is assigned an IPv4 and an IPv6 address. A host-route allows a veth to
+# join its peer.
+#
+# * NS0 and NS3 are at the extremities of the chain. They have additional
+# IPv4 and IPv6 addresses on their loopback device. Routes are added in NS0
+# and NS3, so that they can communicate using these overlay IP addresses.
+# For IPv4 and IPv6 reachability tests, the route simply sets the peer's
+# veth address as gateway. For MPLS reachability tests, an MPLS header is
+# also pushed before the IP header.
+#
+# * NS1 and NS2 are the intermediate namespaces. They use a bareudp device to
+# encapsulate the traffic into UDP.
+#
+# +-----------------------------------------------------------------------+
+# | NS0 |
+# | |
+# | lo: |
+# | * IPv4 address: 192.0.2.100/32 |
+# | * IPv6 address: 2001:db8::100/128 |
+# | * IPv6 address: 2001:db8::200/128 |
+# | * IPv4 route: 192.0.2.103/32 reachable via 192.0.2.11 |
+# | * IPv6 route: 2001:db8::103/128 reachable via 2001:db8::11 |
+# | * IPv6 route: 2001:db8::203/128 reachable via 2001:db8::11 |
+# | (encapsulated with MPLS label 203) |
+# | |
+# | veth01: |
+# | ^ * IPv4 address: 192.0.2.10, peer 192.0.2.11/32 |
+# | | * IPv6 address: 2001:db8::10, peer 2001:db8::11/128 |
+# | | |
+# +---+-------------------------------------------------------------------+
+# |
+# | Traffic type: IP or MPLS (depending on test)
+# |
+# +---+-------------------------------------------------------------------+
+# | | NS1 |
+# | | |
+# | v |
+# | veth10: |
+# | * IPv4 address: 192.0.2.11, peer 192.0.2.10/32 |
+# | * IPv6 address: 2001:db8::11, peer 2001:db8::10/128 |
+# | |
+# | bareudp_ns1: |
+# | * Encapsulate IP or MPLS packets received on veth10 into UDP |
+# | and send the resulting packets through veth12. |
+# | * Decapsulate bareudp packets (either IP or MPLS, over UDP) |
+# | received on veth12 and send the inner packets through veth10. |
+# | |
+# | veth12: |
+# | ^ * IPv4 address: 192.0.2.21, peer 192.0.2.22/32 |
+# | | * IPv6 address: 2001:db8::21, peer 2001:db8::22/128 |
+# | | |
+# +---+-------------------------------------------------------------------+
+# |
+# | Traffic type: IP or MPLS (depending on test), over UDP
+# |
+# +---+-------------------------------------------------------------------+
+# | | NS2 |
+# | | |
+# | v |
+# | veth21: |
+# | * IPv4 address: 192.0.2.22, peer 192.0.2.21/32 |
+# | * IPv6 address: 2001:db8::22, peer 2001:db8::21/128 |
+# | |
+# | bareudp_ns2: |
+# | * Decapsulate bareudp packets (either IP or MPLS, over UDP) |
+# | received on veth21 and send the inner packets through veth23. |
+# | * Encapsulate IP or MPLS packets received on veth23 into UDP |
+# | and send the resulting packets through veth21. |
+# | |
+# | veth23: |
+# | ^ * IPv4 address: 192.0.2.32, peer 192.0.2.33/32 |
+# | | * IPv6 address: 2001:db8::32, peer 2001:db8::33/128 |
+# | | |
+# +---+-------------------------------------------------------------------+
+# |
+# | Traffic type: IP or MPLS (depending on test)
+# |
+# +---+-------------------------------------------------------------------+
+# | | NS3 |
+# | v |
+# | veth32: |
+# | * IPv4 address: 192.0.2.33, peer 192.0.2.32/32 |
+# | * IPv6 address: 2001:db8::33, peer 2001:db8::32/128 |
+# | |
+# | lo: |
+# | * IPv4 address: 192.0.2.103/32 |
+# | * IPv6 address: 2001:db8::103/128 |
+# | * IPv6 address: 2001:db8::203/128 |
+# | * IPv4 route: 192.0.2.100/32 reachable via 192.0.2.32 |
+# | * IPv6 route: 2001:db8::100/128 reachable via 2001:db8::32 |
+# | * IPv6 route: 2001:db8::200/128 reachable via 2001:db8::32 |
+# | (encapsulated with MPLS label 200) |
+# | |
+# +-----------------------------------------------------------------------+
+
+ERR=4 # Return 4 by default, which is the SKIP code for kselftest
+PING6="ping"
+PAUSE_ON_FAIL="no"
+
+readonly NS0=$(mktemp -u ns0-XXXXXXXX)
+readonly NS1=$(mktemp -u ns1-XXXXXXXX)
+readonly NS2=$(mktemp -u ns2-XXXXXXXX)
+readonly NS3=$(mktemp -u ns3-XXXXXXXX)
+
+# Exit the script after having removed the network namespaces it created
+#
+# Parameters:
+#
+# * The list of network namespaces to delete before exiting.
+#
+exit_cleanup()
+{
+ for ns in "$@"; do
+ ip netns delete "${ns}" 2>/dev/null || true
+ done
+
+ if [ "${ERR}" -eq 4 ]; then
+ echo "Error: Setting up the testing environment failed." >&2
+ fi
+
+ exit "${ERR}"
+}
+
+# Create the four network namespaces used by the script (NS0, NS1, NS2 and NS3)
+#
+# New namespaces are cleaned up manually in case of error, to ensure that only
+# namespaces created by this script are deleted.
+create_namespaces()
+{
+ ip netns add "${NS0}" || exit_cleanup
+ ip netns add "${NS1}" || exit_cleanup "${NS0}"
+ ip netns add "${NS2}" || exit_cleanup "${NS0}" "${NS1}"
+ ip netns add "${NS3}" || exit_cleanup "${NS0}" "${NS1}" "${NS2}"
+}
+
+# The trap function handler
+#
+exit_cleanup_all()
+{
+ exit_cleanup "${NS0}" "${NS1}" "${NS2}" "${NS3}"
+}
+
+# Configure a network interface using a host route
+#
+# Parameters
+#
+# * $1: the netns the network interface resides in,
+# * $2: the network interface name,
+# * $3: the local IPv4 address to assign to this interface,
+# * $4: the IPv4 address of the remote network interface,
+# * $5: the local IPv6 address to assign to this interface,
+# * $6: the IPv6 address of the remote network interface.
+#
+iface_config()
+{
+ local NS="${1}"; readonly NS
+ local DEV="${2}"; readonly DEV
+ local LOCAL_IP4="${3}"; readonly LOCAL_IP4
+ local PEER_IP4="${4}"; readonly PEER_IP4
+ local LOCAL_IP6="${5}"; readonly LOCAL_IP6
+ local PEER_IP6="${6}"; readonly PEER_IP6
+
+ ip -netns "${NS}" link set dev "${DEV}" up
+ ip -netns "${NS}" address add dev "${DEV}" "${LOCAL_IP4}" peer "${PEER_IP4}"
+ ip -netns "${NS}" address add dev "${DEV}" "${LOCAL_IP6}" peer "${PEER_IP6}" nodad
+}
+
+# Create base networking topology:
+#
+# * set up the loopback device in all network namespaces (NS0..NS3),
+# * set up a veth pair to connect each netns in sequence (NS0 with NS1,
+# NS1 with NS2, etc.),
+# * add and IPv4 and an IPv6 address on each veth interface,
+# * prepare the ingress qdiscs in the intermediate namespaces.
+#
+setup_underlay()
+{
+ for ns in "${NS0}" "${NS1}" "${NS2}" "${NS3}"; do
+ ip -netns "${ns}" link set dev lo up
+ done;
+
+ ip link add name veth01 netns "${NS0}" type veth peer name veth10 netns "${NS1}"
+ ip link add name veth12 netns "${NS1}" type veth peer name veth21 netns "${NS2}"
+ ip link add name veth23 netns "${NS2}" type veth peer name veth32 netns "${NS3}"
+ iface_config "${NS0}" veth01 192.0.2.10 192.0.2.11/32 2001:db8::10 2001:db8::11/128
+ iface_config "${NS1}" veth10 192.0.2.11 192.0.2.10/32 2001:db8::11 2001:db8::10/128
+ iface_config "${NS1}" veth12 192.0.2.21 192.0.2.22/32 2001:db8::21 2001:db8::22/128
+ iface_config "${NS2}" veth21 192.0.2.22 192.0.2.21/32 2001:db8::22 2001:db8::21/128
+ iface_config "${NS2}" veth23 192.0.2.32 192.0.2.33/32 2001:db8::32 2001:db8::33/128
+ iface_config "${NS3}" veth32 192.0.2.33 192.0.2.32/32 2001:db8::33 2001:db8::32/128
+
+ tc -netns "${NS1}" qdisc add dev veth10 ingress
+ tc -netns "${NS2}" qdisc add dev veth23 ingress
+}
+
+# Set up the IPv4, IPv6 and MPLS overlays.
+#
+# Configuration is similar for all protocols:
+#
+# * add an overlay IP address on the loopback interface of each edge
+# namespace,
+# * route these IP addresses via the intermediate namespaces (for the MPLS
+# tests, this is also where MPLS encapsulation is done),
+# * add routes for these IP addresses (or MPLS labels) in the intermediate
+# namespaces.
+#
+# The bareudp encapsulation isn't configured in setup_overlay_*(). That will be
+# done just before running the reachability tests.
+
+setup_overlay_ipv4()
+{
+ # Add the overlay IP addresses and route them through the veth devices
+ ip -netns "${NS0}" address add 192.0.2.100/32 dev lo
+ ip -netns "${NS3}" address add 192.0.2.103/32 dev lo
+ ip -netns "${NS0}" route add 192.0.2.103/32 src 192.0.2.100 via 192.0.2.11
+ ip -netns "${NS3}" route add 192.0.2.100/32 src 192.0.2.103 via 192.0.2.32
+
+ # Route the overlay addresses in the intermediate namespaces
+ # (used after bareudp decapsulation)
+ ip netns exec "${NS1}" sysctl -qw net.ipv4.ip_forward=1
+ ip netns exec "${NS2}" sysctl -qw net.ipv4.ip_forward=1
+ ip -netns "${NS1}" route add 192.0.2.100/32 via 192.0.2.10
+ ip -netns "${NS2}" route add 192.0.2.103/32 via 192.0.2.33
+
+ # The intermediate namespaces don't have routes for the reverse path,
+ # as it will be handled by tc. So we need to ensure that rp_filter is
+ # not going to block the traffic.
+ ip netns exec "${NS1}" sysctl -qw net.ipv4.conf.all.rp_filter=0
+ ip netns exec "${NS2}" sysctl -qw net.ipv4.conf.all.rp_filter=0
+ ip netns exec "${NS1}" sysctl -qw net.ipv4.conf.default.rp_filter=0
+ ip netns exec "${NS2}" sysctl -qw net.ipv4.conf.default.rp_filter=0
+}
+
+setup_overlay_ipv6()
+{
+ # Add the overlay IP addresses and route them through the veth devices
+ ip -netns "${NS0}" address add 2001:db8::100/128 dev lo
+ ip -netns "${NS3}" address add 2001:db8::103/128 dev lo
+ ip -netns "${NS0}" route add 2001:db8::103/128 src 2001:db8::100 via 2001:db8::11
+ ip -netns "${NS3}" route add 2001:db8::100/128 src 2001:db8::103 via 2001:db8::32
+
+ # Route the overlay addresses in the intermediate namespaces
+ # (used after bareudp decapsulation)
+ ip netns exec "${NS1}" sysctl -qw net.ipv6.conf.all.forwarding=1
+ ip netns exec "${NS2}" sysctl -qw net.ipv6.conf.all.forwarding=1
+ ip -netns "${NS1}" route add 2001:db8::100/128 via 2001:db8::10
+ ip -netns "${NS2}" route add 2001:db8::103/128 via 2001:db8::33
+}
+
+setup_overlay_mpls()
+{
+ # Add specific overlay IP addresses, routed over MPLS
+ ip -netns "${NS0}" address add 2001:db8::200/128 dev lo
+ ip -netns "${NS3}" address add 2001:db8::203/128 dev lo
+ ip -netns "${NS0}" route add 2001:db8::203/128 src 2001:db8::200 encap mpls 203 via 2001:db8::11
+ ip -netns "${NS3}" route add 2001:db8::200/128 src 2001:db8::203 encap mpls 200 via 2001:db8::32
+
+ # Route the MPLS packets in the intermediate namespaces
+ # (used after bareudp decapsulation)
+ ip netns exec "${NS1}" sysctl -qw net.mpls.platform_labels=256
+ ip netns exec "${NS2}" sysctl -qw net.mpls.platform_labels=256
+ ip -netns "${NS1}" -family mpls route add 200 via inet6 2001:db8::10
+ ip -netns "${NS2}" -family mpls route add 203 via inet6 2001:db8::33
+}
+
+# Run "ping" from NS0 and print the result
+#
+# Parameters:
+#
+# * $1: the variant of ping to use (normally either "ping" or "ping6"),
+# * $2: the IP address to ping,
+# * $3: a human readable description of the purpose of the test.
+#
+# If the test fails and PAUSE_ON_FAIL is active, the user is given the
+# possibility to continue with the next test or to quit immediately.
+#
+ping_test_one()
+{
+ local PING="$1"; readonly PING
+ local IP="$2"; readonly IP
+ local MSG="$3"; readonly MSG
+ local RET
+
+ printf "TEST: %-60s " "${MSG}"
+
+ set +e
+ ip netns exec "${NS0}" "${PING}" -w 5 -c 1 "${IP}" > /dev/null 2>&1
+ RET=$?
+ set -e
+
+ if [ "${RET}" -eq 0 ]; then
+ printf "[ OK ]\n"
+ else
+ ERR=1
+ printf "[FAIL]\n"
+ if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+ printf "\nHit enter to continue, 'q' to quit\n"
+ read a
+ if [ "$a" = "q" ]; then
+ exit 1
+ fi
+ fi
+ fi
+}
+
+# Run reachability tests
+#
+# Parameters:
+#
+# * $1: human readable string describing the underlay protocol.
+#
+# $IPV4, $IPV6, $MPLS_UC and $MULTIPROTO are inherited from the calling
+# function.
+#
+ping_test()
+{
+ local UNDERLAY="$1"; readonly UNDERLAY
+ local MODE
+ local MSG
+
+ if [ "${MULTIPROTO}" = "multiproto" ]; then
+ MODE=" (multiproto mode)"
+ else
+ MODE=""
+ fi
+
+ if [ $IPV4 ]; then
+ ping_test_one "ping" "192.0.2.103" "IPv4 packets over ${UNDERLAY}${MODE}"
+ fi
+ if [ $IPV6 ]; then
+ ping_test_one "${PING6}" "2001:db8::103" "IPv6 packets over ${UNDERLAY}${MODE}"
+ fi
+ if [ $MPLS_UC ]; then
+ ping_test_one "${PING6}" "2001:db8::203" "Unicast MPLS packets over ${UNDERLAY}${MODE}"
+ fi
+}
+
+# Set up a bareudp overlay and run reachability tests over IPv4 and IPv6
+#
+# Parameters:
+#
+# * $1: the packet type (protocol) to be handled by bareudp,
+# * $2: a flag to activate or deactivate bareudp's "multiproto" mode.
+#
+test_overlay()
+{
+ local ETHERTYPE="$1"; readonly ETHERTYPE
+ local MULTIPROTO="$2"; readonly MULTIPROTO
+ local IPV4
+ local IPV6
+ local MPLS_UC
+
+ case "${ETHERTYPE}" in
+ "ipv4")
+ IPV4="ipv4"
+ if [ "${MULTIPROTO}" = "multiproto" ]; then
+ IPV6="ipv6"
+ else
+ IPV6=""
+ fi
+ MPLS_UC=""
+ ;;
+ "ipv6")
+ IPV6="ipv6"
+ IPV4=""
+ MPLS_UC=""
+ ;;
+ "mpls_uc")
+ MPLS_UC="mpls_uc"
+ IPV4=""
+ IPV6=""
+ ;;
+ *)
+ exit 1
+ ;;
+ esac
+ readonly IPV4
+ readonly IPV6
+ readonly MPLS_UC
+
+ # Create the bareudp devices in the intermediate namespaces
+ ip -netns "${NS1}" link add name bareudp_ns1 up type bareudp dstport 6635 ethertype "${ETHERTYPE}" "${MULTIPROTO}"
+ ip -netns "${NS2}" link add name bareudp_ns2 up type bareudp dstport 6635 ethertype "${ETHERTYPE}" "${MULTIPROTO}"
+
+ # IPv4 over UDPv4
+ if [ $IPV4 ]; then
+ # Encapsulation instructions for bareudp over IPv4
+ tc -netns "${NS1}" filter add dev veth10 ingress protocol ipv4 \
+ flower dst_ip 192.0.2.103/32 \
+ action tunnel_key set src_ip 192.0.2.21 dst_ip 192.0.2.22 id 0 \
+ action mirred egress redirect dev bareudp_ns1
+ tc -netns "${NS2}" filter add dev veth23 ingress protocol ipv4 \
+ flower dst_ip 192.0.2.100/32 \
+ action tunnel_key set src_ip 192.0.2.22 dst_ip 192.0.2.21 id 0 \
+ action mirred egress redirect dev bareudp_ns2
+ fi
+
+ # IPv6 over UDPv4
+ if [ $IPV6 ]; then
+ # Encapsulation instructions for bareudp over IPv4
+ tc -netns "${NS1}" filter add dev veth10 ingress protocol ipv6 \
+ flower dst_ip 2001:db8::103/128 \
+ action tunnel_key set src_ip 192.0.2.21 dst_ip 192.0.2.22 id 0 \
+ action mirred egress redirect dev bareudp_ns1
+ tc -netns "${NS2}" filter add dev veth23 ingress protocol ipv6 \
+ flower dst_ip 2001:db8::100/128 \
+ action tunnel_key set src_ip 192.0.2.22 dst_ip 192.0.2.21 id 0 \
+ action mirred egress redirect dev bareudp_ns2
+ fi
+
+ # MPLS (unicast) over UDPv4
+ if [ $MPLS_UC ]; then
+ ip netns exec "${NS1}" sysctl -qw net.mpls.conf.bareudp_ns1.input=1
+ ip netns exec "${NS2}" sysctl -qw net.mpls.conf.bareudp_ns2.input=1
+
+ # Encapsulation instructions for bareudp over IPv4
+ tc -netns "${NS1}" filter add dev veth10 ingress protocol mpls_uc \
+ flower mpls_label 203 \
+ action tunnel_key set src_ip 192.0.2.21 dst_ip 192.0.2.22 id 0 \
+ action mirred egress redirect dev bareudp_ns1
+ tc -netns "${NS2}" filter add dev veth23 ingress protocol mpls_uc \
+ flower mpls_label 200 \
+ action tunnel_key set src_ip 192.0.2.22 dst_ip 192.0.2.21 id 0 \
+ action mirred egress redirect dev bareudp_ns2
+ fi
+
+ # Test IPv4 underlay
+ ping_test "UDPv4"
+
+ # Cleanup bareudp encapsulation instructions, as they were specific to
+ # the IPv4 underlay, before setting up and testing the IPv6 underlay
+ tc -netns "${NS1}" filter delete dev veth10 ingress
+ tc -netns "${NS2}" filter delete dev veth23 ingress
+
+ # IPv4 over UDPv6
+ if [ $IPV4 ]; then
+ # New encapsulation instructions for bareudp over IPv6
+ tc -netns "${NS1}" filter add dev veth10 ingress protocol ipv4 \
+ flower dst_ip 192.0.2.103/32 \
+ action tunnel_key set src_ip 2001:db8::21 dst_ip 2001:db8::22 id 0 \
+ action mirred egress redirect dev bareudp_ns1
+ tc -netns "${NS2}" filter add dev veth23 ingress protocol ipv4 \
+ flower dst_ip 192.0.2.100/32 \
+ action tunnel_key set src_ip 2001:db8::22 dst_ip 2001:db8::21 id 0 \
+ action mirred egress redirect dev bareudp_ns2
+ fi
+
+ # IPv6 over UDPv6
+ if [ $IPV6 ]; then
+ # New encapsulation instructions for bareudp over IPv6
+ tc -netns "${NS1}" filter add dev veth10 ingress protocol ipv6 \
+ flower dst_ip 2001:db8::103/128 \
+ action tunnel_key set src_ip 2001:db8::21 dst_ip 2001:db8::22 id 0 \
+ action mirred egress redirect dev bareudp_ns1
+ tc -netns "${NS2}" filter add dev veth23 ingress protocol ipv6 \
+ flower dst_ip 2001:db8::100/128 \
+ action tunnel_key set src_ip 2001:db8::22 dst_ip 2001:db8::21 id 0 \
+ action mirred egress redirect dev bareudp_ns2
+ fi
+
+ # MPLS (unicast) over UDPv6
+ if [ $MPLS_UC ]; then
+ # New encapsulation instructions for bareudp over IPv6
+ tc -netns "${NS1}" filter add dev veth10 ingress protocol mpls_uc \
+ flower mpls_label 203 \
+ action tunnel_key set src_ip 2001:db8::21 dst_ip 2001:db8::22 id 0 \
+ action mirred egress redirect dev bareudp_ns1
+ tc -netns "${NS2}" filter add dev veth23 ingress protocol mpls_uc \
+ flower mpls_label 200 \
+ action tunnel_key set src_ip 2001:db8::22 dst_ip 2001:db8::21 id 0 \
+ action mirred egress redirect dev bareudp_ns2
+ fi
+
+ # Test IPv6 underlay
+ ping_test "UDPv6"
+
+ tc -netns "${NS1}" filter delete dev veth10 ingress
+ tc -netns "${NS2}" filter delete dev veth23 ingress
+ ip -netns "${NS1}" link delete bareudp_ns1
+ ip -netns "${NS2}" link delete bareudp_ns2
+}
+
+check_features()
+{
+ ip link help 2>&1 | grep -q bareudp
+ if [ $? -ne 0 ]; then
+ echo "Missing bareudp support in iproute2" >&2
+ exit_cleanup
+ fi
+
+ # Use ping6 on systems where ping doesn't handle IPv6
+ ping -w 1 -c 1 ::1 > /dev/null 2>&1 || PING6="ping6"
+}
+
+usage()
+{
+ echo "Usage: $0 [-p]"
+ exit 1
+}
+
+while getopts :p o
+do
+ case $o in
+ p) PAUSE_ON_FAIL="yes";;
+ *) usage;;
+ esac
+done
+
+check_features
+
+# Create namespaces before setting up the exit trap.
+# Otherwise, exit_cleanup_all() could delete namespaces that were not created
+# by this script.
+create_namespaces
+
+set -e
+trap exit_cleanup_all EXIT
+
+setup_underlay
+setup_overlay_ipv4
+setup_overlay_ipv6
+setup_overlay_mpls
+
+test_overlay ipv4 nomultiproto
+test_overlay ipv6 nomultiproto
+test_overlay ipv4 multiproto
+test_overlay mpls_uc nomultiproto
+
+if [ "${ERR}" -eq 1 ]; then
+ echo "Some tests failed." >&2
+else
+ ERR=0
+fi
CONFIG_NET_DROP_MONITOR=m
CONFIG_NETDEVSIM=m
CONFIG_NET_FOU=m
+CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_SCH_INGRESS=m
+CONFIG_NET_CLS_FLOWER=m
+CONFIG_NET_ACT_TUNNEL_KEY=m
+CONFIG_NET_ACT_MIRRED=m
+CONFIG_BAREUDP=m
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="reportleave_test"
+ALL_TESTS="v2reportleave_test v3include_test v3inc_allow_test v3inc_is_include_test \
+ v3inc_is_exclude_test v3inc_to_exclude_test v3exc_allow_test v3exc_is_include_test \
+ v3exc_is_exclude_test v3exc_to_exclude_test v3inc_block_test v3exc_block_test \
+ v3exc_timeout_test v3star_ex_auto_add_test"
NUM_NETIFS=4
CHECK_TC="yes"
TEST_GROUP="239.10.10.10"
TEST_GROUP_MAC="01:00:5e:0a:0a:0a"
+
+ALL_GROUP="224.0.0.1"
+ALL_MAC="01:00:5e:00:00:01"
+
+# IGMPv3 is_in report: grp 239.10.10.10 is_include 192.0.2.1,192.0.2.2,192.0.2.3
+MZPKT_IS_INC="22:00:9d:de:00:00:00:01:01:00:00:03:ef:0a:0a:0a:c0:00:02:01:c0:00:02:02:c0:00:02:03"
+# IGMPv3 is_in report: grp 239.10.10.10 is_include 192.0.2.10,192.0.2.11,192.0.2.12
+MZPKT_IS_INC2="22:00:9d:c3:00:00:00:01:01:00:00:03:ef:0a:0a:0a:c0:00:02:0a:c0:00:02:0b:c0:00:02:0c"
+# IGMPv3 is_in report: grp 239.10.10.10 is_include 192.0.2.20,192.0.2.30
+MZPKT_IS_INC3="22:00:5f:b4:00:00:00:01:01:00:00:02:ef:0a:0a:0a:c0:00:02:14:c0:00:02:1e"
+# IGMPv3 allow report: grp 239.10.10.10 allow 192.0.2.10,192.0.2.11,192.0.2.12
+MZPKT_ALLOW="22:00:99:c3:00:00:00:01:05:00:00:03:ef:0a:0a:0a:c0:00:02:0a:c0:00:02:0b:c0:00:02:0c"
+# IGMPv3 allow report: grp 239.10.10.10 allow 192.0.2.20,192.0.2.30
+MZPKT_ALLOW2="22:00:5b:b4:00:00:00:01:05:00:00:02:ef:0a:0a:0a:c0:00:02:14:c0:00:02:1e"
+# IGMPv3 is_ex report: grp 239.10.10.10 is_exclude 192.0.2.1,192.0.2.2,192.0.2.20,192.0.2.21
+MZPKT_IS_EXC="22:00:da:b6:00:00:00:01:02:00:00:04:ef:0a:0a:0a:c0:00:02:01:c0:00:02:02:c0:00:02:14:c0:00:02:15"
+# IGMPv3 is_ex report: grp 239.10.10.10 is_exclude 192.0.2.20,192.0.2.30
+MZPKT_IS_EXC2="22:00:5e:b4:00:00:00:01:02:00:00:02:ef:0a:0a:0a:c0:00:02:14:c0:00:02:1e"
+# IGMPv3 to_ex report: grp 239.10.10.10 to_exclude 192.0.2.1,192.0.2.20,192.0.2.30
+MZPKT_TO_EXC="22:00:9a:b1:00:00:00:01:04:00:00:03:ef:0a:0a:0a:c0:00:02:01:c0:00:02:14:c0:00:02:1e"
+# IGMPv3 block report: grp 239.10.10.10 block 192.0.2.1,192.0.2.20,192.0.2.30
+MZPKT_BLOCK="22:00:98:b1:00:00:00:01:06:00:00:03:ef:0a:0a:0a:c0:00:02:01:c0:00:02:14:c0:00:02:1e"
+
source lib.sh
h1_create()
vrf_cleanup
}
-# return 0 if the packet wasn't seen on host2_if or 1 if it was
-mcast_packet_test()
-{
- local mac=$1
- local ip=$2
- local host1_if=$3
- local host2_if=$4
- local seen=0
-
- # Add an ACL on `host2_if` which will tell us whether the packet
- # was received by it or not.
- tc qdisc add dev $host2_if ingress
- tc filter add dev $host2_if ingress protocol ip pref 1 handle 101 \
- flower dst_mac $mac action drop
-
- $MZ $host1_if -c 1 -p 64 -b $mac -B $ip -t udp "dp=4096,sp=2048" -q
- sleep 1
-
- tc -j -s filter show dev $host2_if ingress \
- | jq -e ".[] | select(.options.handle == 101) \
- | select(.options.actions[0].stats.packets == 1)" &> /dev/null
- if [[ $? -eq 0 ]]; then
- seen=1
- fi
-
- tc filter del dev $host2_if ingress protocol ip pref 1 handle 101 flower
- tc qdisc del dev $host2_if ingress
-
- return $seen
-}
-
-reportleave_test()
+v2reportleave_test()
{
RET=0
ip address add dev $h2 $TEST_GROUP/32 autojoin
sleep 5
bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null
- check_err $? "Report didn't create mdb entry for $TEST_GROUP"
+ check_err $? "IGMPv2 report didn't create mdb entry for $TEST_GROUP"
- mcast_packet_test $TEST_GROUP_MAC $TEST_GROUP $h1 $h2
+ mcast_packet_test $TEST_GROUP_MAC 192.0.2.1 $TEST_GROUP $h1 $h2
check_fail $? "Traffic to $TEST_GROUP wasn't forwarded"
- log_test "IGMP report $TEST_GROUP"
+ log_test "IGMPv2 report $TEST_GROUP"
RET=0
bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null
bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null
check_fail $? "Leave didn't delete mdb entry for $TEST_GROUP"
- mcast_packet_test $TEST_GROUP_MAC $TEST_GROUP $h1 $h2
+ mcast_packet_test $TEST_GROUP_MAC 192.0.2.1 $TEST_GROUP $h1 $h2
check_err $? "Traffic to $TEST_GROUP was forwarded without mdb entry"
- log_test "IGMP leave $TEST_GROUP"
+ log_test "IGMPv2 leave $TEST_GROUP"
+}
+
+v3include_prepare()
+{
+ local host1_if=$1
+ local mac=$2
+ local group=$3
+ local X=("192.0.2.1" "192.0.2.2" "192.0.2.3")
+
+ ip link set dev br0 type bridge mcast_igmp_version 3
+ check_err $? "Could not change bridge IGMP version to 3"
+
+ $MZ $host1_if -b $mac -c 1 -B $group -t ip "proto=2,p=$MZPKT_IS_INC" -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .source_list != null)" &>/dev/null
+ check_err $? "Missing *,G entry with source list"
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"include\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+ brmcast_check_sg_entries "is_include" "${X[@]}"
+}
+
+v3exclude_prepare()
+{
+ local host1_if=$1
+ local mac=$2
+ local group=$3
+ local pkt=$4
+ local X=("192.0.2.1" "192.0.2.2")
+ local Y=("192.0.2.20" "192.0.2.21")
+
+ v3include_prepare $host1_if $mac $group
+
+ $MZ $host1_if -c 1 -b $mac -B $group -t ip "proto=2,p=$MZPKT_IS_EXC" -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"exclude\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+
+ brmcast_check_sg_entries "is_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"192.0.2.3\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 192.0.2.3 entry still exists"
+}
+
+v3cleanup()
+{
+ local port=$1
+ local group=$2
+
+ bridge mdb del dev br0 port $port grp $group
+ ip link set dev br0 type bridge mcast_igmp_version 2
+}
+
+v3include_test()
+{
+ RET=0
+ local X=("192.0.2.1" "192.0.2.2" "192.0.2.3")
+
+ v3include_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "192.0.2.100"
+
+ log_test "IGMPv3 report $TEST_GROUP is_include"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3inc_allow_test()
+{
+ RET=0
+ local X=("192.0.2.10" "192.0.2.11" "192.0.2.12")
+
+ v3include_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW" -q
+ sleep 1
+ brmcast_check_sg_entries "allow" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "192.0.2.100"
+
+ log_test "IGMPv3 report $TEST_GROUP include -> allow"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3inc_is_include_test()
+{
+ RET=0
+ local X=("192.0.2.10" "192.0.2.11" "192.0.2.12")
+
+ v3include_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_IS_INC2" -q
+ sleep 1
+ brmcast_check_sg_entries "is_include" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "192.0.2.100"
+
+ log_test "IGMPv3 report $TEST_GROUP include -> is_include"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3inc_is_exclude_test()
+{
+ RET=0
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP include -> is_exclude"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3inc_to_exclude_test()
+{
+ RET=0
+ local X=("192.0.2.1")
+ local Y=("192.0.2.20" "192.0.2.30")
+
+ v3include_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ ip link set dev br0 type bridge mcast_last_member_interval 500
+ check_err $? "Could not change mcast_last_member_interval to 5s"
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_TO_EXC" -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"exclude\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+
+ brmcast_check_sg_entries "to_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"192.0.2.2\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 192.0.2.2 entry still exists"
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"192.0.2.21\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 192.0.2.21 entry still exists"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP include -> to_exclude"
+
+ ip link set dev br0 type bridge mcast_last_member_interval 100
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3exc_allow_test()
+{
+ RET=0
+ local X=("192.0.2.1" "192.0.2.2" "192.0.2.20" "192.0.2.30")
+ local Y=("192.0.2.21")
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW2" -q
+ sleep 1
+ brmcast_check_sg_entries "allow" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP exclude -> allow"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3exc_is_include_test()
+{
+ RET=0
+ local X=("192.0.2.1" "192.0.2.2" "192.0.2.20" "192.0.2.30")
+ local Y=("192.0.2.21")
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_IS_INC3" -q
+ sleep 1
+ brmcast_check_sg_entries "is_include" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP exclude -> is_include"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3exc_is_exclude_test()
+{
+ RET=0
+ local X=("192.0.2.30")
+ local Y=("192.0.2.20")
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_IS_EXC2" -q
+ sleep 1
+ brmcast_check_sg_entries "is_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP exclude -> is_exclude"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3exc_to_exclude_test()
+{
+ RET=0
+ local X=("192.0.2.1" "192.0.2.30")
+ local Y=("192.0.2.20")
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ ip link set dev br0 type bridge mcast_last_member_interval 500
+ check_err $? "Could not change mcast_last_member_interval to 5s"
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_TO_EXC" -q
+ sleep 1
+ brmcast_check_sg_entries "to_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP exclude -> to_exclude"
+
+ ip link set dev br0 type bridge mcast_last_member_interval 100
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3inc_block_test()
+{
+ RET=0
+ local X=("192.0.2.2" "192.0.2.3")
+
+ v3include_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_BLOCK" -q
+ # make sure the lowered timers have expired (by default 2 seconds)
+ sleep 3
+ brmcast_check_sg_entries "block" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"192.0.2.1\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 192.0.2.1 entry still exists"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "192.0.2.100"
+
+ log_test "IGMPv3 report $TEST_GROUP include -> block"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3exc_block_test()
+{
+ RET=0
+ local X=("192.0.2.1" "192.0.2.2" "192.0.2.30")
+ local Y=("192.0.2.20" "192.0.2.21")
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ ip link set dev br0 type bridge mcast_last_member_interval 500
+ check_err $? "Could not change mcast_last_member_interval to 5s"
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_BLOCK" -q
+ sleep 1
+ brmcast_check_sg_entries "block" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP exclude -> block"
+
+ ip link set dev br0 type bridge mcast_last_member_interval 100
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3exc_timeout_test()
+{
+ RET=0
+ local X=("192.0.2.20" "192.0.2.30")
+
+ # GMI should be 3 seconds
+ ip link set dev br0 type bridge mcast_query_interval 100 mcast_query_response_interval 100
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+ ip link set dev br0 type bridge mcast_query_interval 500 mcast_query_response_interval 500
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW2" -q
+ sleep 3
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"include\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"192.0.2.1\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 192.0.2.1 entry still exists"
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"192.0.2.2\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 192.0.2.2 entry still exists"
+
+ brmcast_check_sg_entries "allow" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 192.0.2.100
+
+ log_test "IGMPv3 group $TEST_GROUP exclude timeout"
+
+ ip link set dev br0 type bridge mcast_query_interval 12500 \
+ mcast_query_response_interval 1000
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3star_ex_auto_add_test()
+{
+ RET=0
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h2 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_IS_INC" -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .src == \"192.0.2.3\" and \
+ .port == \"$swp1\")" &>/dev/null
+ check_err $? "S,G entry for *,G port doesn't exist"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .src == \"192.0.2.3\" and \
+ .port == \"$swp1\" and \
+ .flags[] == \"added_by_star_ex\")" &>/dev/null
+ check_err $? "Auto-added S,G entry doesn't have added_by_star_ex flag"
+
+ brmcast_check_sg_fwding 1 192.0.2.3
+
+ log_test "IGMPv3 S,G port entry automatic add to a *,G port"
+
+ v3cleanup $swp1 $TEST_GROUP
+ v3cleanup $swp2 $TEST_GROUP
}
trap cleanup EXIT
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="mldv2include_test mldv2inc_allow_test mldv2inc_is_include_test mldv2inc_is_exclude_test \
+ mldv2inc_to_exclude_test mldv2exc_allow_test mldv2exc_is_include_test \
+ mldv2exc_is_exclude_test mldv2exc_to_exclude_test mldv2inc_block_test \
+ mldv2exc_block_test mldv2exc_timeout_test mldv2star_ex_auto_add_test"
+NUM_NETIFS=4
+CHECK_TC="yes"
+TEST_GROUP="ff02::cc"
+TEST_GROUP_MAC="33:33:00:00:00:cc"
+
+# MLDv2 is_in report: grp ff02::cc is_include 2001:db8:1::1,2001:db8:1::2,2001:db8:1::3
+MZPKT_IS_INC="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:\
+00:00:00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:\
+00:05:02:00:00:00:00:8f:00:8e:d9:00:00:00:01:01:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:\
+00:00:00:00:cc:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01:20:01:0d:b8:00:01:00:00:00:\
+00:00:00:00:00:00:02:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:03"
+# MLDv2 is_in report: grp ff02::cc is_include 2001:db8:1::10,2001:db8:1::11,2001:db8:1::12
+MZPKT_IS_INC2="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:\
+00:00:00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:\
+05:02:00:00:00:00:8f:00:8e:ac:00:00:00:01:01:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:00:00:\
+00:00:cc:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:10:20:01:0d:b8:00:01:00:00:00:00:00:00:\
+00:00:00:11:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:12"
+# MLDv2 is_in report: grp ff02::cc is_include 2001:db8:1::20,2001:db8:1::30
+MZPKT_IS_INC3="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:44:00:01:fe:80:00:00:00:\
+00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\
+00:00:00:8f:00:bc:5a:00:00:00:01:01:00:00:02:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:30"
+# MLDv2 allow report: grp ff02::cc allow 2001:db8:1::10,2001:db8:1::11,2001:db8:1::12
+MZPKT_ALLOW="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:00:\
+00:00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:\
+02:00:00:00:00:8f:00:8a:ac:00:00:00:01:05:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:\
+00:cc:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:10:20:01:0d:b8:00:01:00:00:00:00:00:00:00:\
+00:00:11:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:12"
+# MLDv2 allow report: grp ff02::cc allow 2001:db8:1::20,2001:db8:1::30
+MZPKT_ALLOW2="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:44:00:01:fe:80:00:00:00:\
+00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\
+00:00:00:8f:00:b8:5a:00:00:00:01:05:00:00:02:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:30"
+# MLDv2 is_ex report: grp ff02::cc is_exclude 2001:db8:1::1,2001:db8:1::2,2001:db8:1::20,2001:db8:1::21
+MZPKT_IS_EXC="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:64:00:01:fe:80:00:00:00:\
+00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\
+00:00:00:8f:00:5f:d0:00:00:00:01:02:00:00:04:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:02:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:21"
+# MLDv2 is_ex report: grp ff02::cc is_exclude 2001:db8:1::20,2001:db8:1::30
+MZPKT_IS_EXC2="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:44:00:01:fe:80:00:00:00:\
+00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\
+00:00:00:8f:00:bb:5a:00:00:00:01:02:00:00:02:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:30"
+# MLDv2 to_ex report: grp ff02::cc to_exclude 2001:db8:1::1,2001:db8:1::20,2001:db8:1::30
+MZPKT_TO_EXC="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:00:00:\
+00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\
+00:00:00:8f:00:8b:8e:00:00:00:01:04:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:30"
+# MLDv2 block report: grp ff02::cc block 2001:db8:1::1,2001:db8:1::20,2001:db8:1::30
+MZPKT_BLOCK="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:00:00:00:\
+00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:00:\
+00:00:8f:00:89:8e:00:00:00:01:06:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:01:\
+0d:b8:00:01:00:00:00:00:00:00:00:00:00:01:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:\
+0d:b8:00:01:00:00:00:00:00:00:00:00:00:30"
+
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 2001:db8:1::1/64
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 2001:db8:1::1/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 2001:db8:1::2/64
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 2001:db8:1::2/64
+}
+
+switch_create()
+{
+ ip link add dev br0 type bridge mcast_snooping 1 mcast_query_response_interval 100 \
+ mcast_mld_version 2 mcast_startup_query_interval 300 \
+ mcast_querier 1
+
+ ip link set dev $swp1 master br0
+ ip link set dev $swp2 master br0
+
+ ip link set dev br0 up
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+
+ # make sure a query has been generated
+ sleep 5
+}
+
+switch_destroy()
+{
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+
+ ip link del dev br0
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+mldv2include_prepare()
+{
+ local host1_if=$1
+ local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::3")
+
+ ip link set dev br0 type bridge mcast_mld_version 2
+ check_err $? "Could not change bridge MLD version to 2"
+
+ $MZ $host1_if $MZPKT_IS_INC -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .source_list != null)" &>/dev/null
+ check_err $? "Missing *,G entry with source list"
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"include\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+ brmcast_check_sg_entries "is_include" "${X[@]}"
+}
+
+mldv2exclude_prepare()
+{
+ local host1_if=$1
+ local mac=$2
+ local group=$3
+ local pkt=$4
+ local X=("2001:db8:1::1" "2001:db8:1::2")
+ local Y=("2001:db8:1::20" "2001:db8:1::21")
+
+ mldv2include_prepare $h1
+
+ $MZ $host1_if -c 1 $MZPKT_IS_EXC -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"exclude\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+
+ brmcast_check_sg_entries "is_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"2001:db8:1::3\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 2001:db8:1::3 entry still exists"
+}
+
+mldv2cleanup()
+{
+ local port=$1
+
+ bridge mdb del dev br0 port $port grp $TEST_GROUP
+ ip link set dev br0 type bridge mcast_mld_version 1
+}
+
+mldv2include_test()
+{
+ RET=0
+ local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::3")
+
+ mldv2include_prepare $h1
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "2001:db8:1::100"
+
+ log_test "MLDv2 report $TEST_GROUP is_include"
+
+ mldv2cleanup $swp1
+}
+
+mldv2inc_allow_test()
+{
+ RET=0
+ local X=("2001:db8:1::10" "2001:db8:1::11" "2001:db8:1::12")
+
+ mldv2include_prepare $h1
+
+ $MZ $h1 -c 1 $MZPKT_ALLOW -q
+ sleep 1
+ brmcast_check_sg_entries "allow" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "2001:db8:1::100"
+
+ log_test "MLDv2 report $TEST_GROUP include -> allow"
+
+ mldv2cleanup $swp1
+}
+
+mldv2inc_is_include_test()
+{
+ RET=0
+ local X=("2001:db8:1::10" "2001:db8:1::11" "2001:db8:1::12")
+
+ mldv2include_prepare $h1
+
+ $MZ $h1 -c 1 $MZPKT_IS_INC2 -q
+ sleep 1
+ brmcast_check_sg_entries "is_include" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "2001:db8:1::100"
+
+ log_test "MLDv2 report $TEST_GROUP include -> is_include"
+
+ mldv2cleanup $swp1
+}
+
+mldv2inc_is_exclude_test()
+{
+ RET=0
+
+ mldv2exclude_prepare $h1
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP include -> is_exclude"
+
+ mldv2cleanup $swp1
+}
+
+mldv2inc_to_exclude_test()
+{
+ RET=0
+ local X=("2001:db8:1::1")
+ local Y=("2001:db8:1::20" "2001:db8:1::30")
+
+ mldv2include_prepare $h1
+
+ ip link set dev br0 type bridge mcast_last_member_interval 500
+ check_err $? "Could not change mcast_last_member_interval to 5s"
+
+ $MZ $h1 -c 1 $MZPKT_TO_EXC -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"exclude\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+
+ brmcast_check_sg_entries "to_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"2001:db8:1::2\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 2001:db8:1::2 entry still exists"
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"2001:db8:1::21\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 2001:db8:1::21 entry still exists"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP include -> to_exclude"
+
+ ip link set dev br0 type bridge mcast_last_member_interval 100
+
+ mldv2cleanup $swp1
+}
+
+mldv2exc_allow_test()
+{
+ RET=0
+ local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::20" "2001:db8:1::30")
+ local Y=("2001:db8:1::21")
+
+ mldv2exclude_prepare $h1
+
+ $MZ $h1 -c 1 $MZPKT_ALLOW2 -q
+ sleep 1
+ brmcast_check_sg_entries "allow" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP exclude -> allow"
+
+ mldv2cleanup $swp1
+}
+
+mldv2exc_is_include_test()
+{
+ RET=0
+ local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::20" "2001:db8:1::30")
+ local Y=("2001:db8:1::21")
+
+ mldv2exclude_prepare $h1
+
+ $MZ $h1 -c 1 $MZPKT_IS_INC3 -q
+ sleep 1
+ brmcast_check_sg_entries "is_include" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP exclude -> is_include"
+
+ mldv2cleanup $swp1
+}
+
+mldv2exc_is_exclude_test()
+{
+ RET=0
+ local X=("2001:db8:1::30")
+ local Y=("2001:db8:1::20")
+
+ mldv2exclude_prepare $h1
+
+ $MZ $h1 -c 1 $MZPKT_IS_EXC2 -q
+ sleep 1
+ brmcast_check_sg_entries "is_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP exclude -> is_exclude"
+
+ mldv2cleanup $swp1
+}
+
+mldv2exc_to_exclude_test()
+{
+ RET=0
+ local X=("2001:db8:1::1" "2001:db8:1::30")
+ local Y=("2001:db8:1::20")
+
+ mldv2exclude_prepare $h1
+
+ ip link set dev br0 type bridge mcast_last_member_interval 500
+ check_err $? "Could not change mcast_last_member_interval to 5s"
+
+ $MZ $h1 -c 1 $MZPKT_TO_EXC -q
+ sleep 1
+ brmcast_check_sg_entries "to_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP exclude -> to_exclude"
+
+ ip link set dev br0 type bridge mcast_last_member_interval 100
+
+ mldv2cleanup $swp1
+}
+
+mldv2inc_block_test()
+{
+ RET=0
+ local X=("2001:db8:1::2" "2001:db8:1::3")
+
+ mldv2include_prepare $h1
+
+ $MZ $h1 -c 1 $MZPKT_BLOCK -q
+ # make sure the lowered timers have expired (by default 2 seconds)
+ sleep 3
+ brmcast_check_sg_entries "block" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"2001:db8:1::1\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 2001:db8:1::1 entry still exists"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 2001:db8:1::100
+
+ log_test "MLDv2 report $TEST_GROUP include -> block"
+
+ mldv2cleanup $swp1
+}
+
+mldv2exc_block_test()
+{
+ RET=0
+ local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::30")
+ local Y=("2001:db8:1::20" "2001:db8:1::21")
+
+ mldv2exclude_prepare $h1
+
+ ip link set dev br0 type bridge mcast_last_member_interval 500
+ check_err $? "Could not change mcast_last_member_interval to 5s"
+
+ $MZ $h1 -c 1 $MZPKT_BLOCK -q
+ sleep 1
+ brmcast_check_sg_entries "block" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP exclude -> block"
+
+ ip link set dev br0 type bridge mcast_last_member_interval 100
+
+ mldv2cleanup $swp1
+}
+
+mldv2exc_timeout_test()
+{
+ RET=0
+ local X=("2001:db8:1::20" "2001:db8:1::30")
+
+ # GMI should be 3 seconds
+ ip link set dev br0 type bridge mcast_query_interval 100 mcast_query_response_interval 100
+
+ mldv2exclude_prepare $h1
+ ip link set dev br0 type bridge mcast_query_interval 500 mcast_query_response_interval 500
+ $MZ $h1 -c 1 $MZPKT_ALLOW2 -q
+ sleep 3
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"include\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"2001:db8:1::1\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 2001:db8:1::1 entry still exists"
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"2001:db8:1::2\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 2001:db8:1::2 entry still exists"
+
+ brmcast_check_sg_entries "allow" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 2001:db8:1::100
+
+ log_test "MLDv2 group $TEST_GROUP exclude timeout"
+
+ ip link set dev br0 type bridge mcast_query_interval 12500 \
+ mcast_query_response_interval 1000
+
+ mldv2cleanup $swp1
+}
+
+mldv2star_ex_auto_add_test()
+{
+ RET=0
+
+ mldv2exclude_prepare $h1
+
+ $MZ $h2 -c 1 $MZPKT_IS_INC -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .src == \"2001:db8:1::3\" and \
+ .port == \"$swp1\")" &>/dev/null
+ check_err $? "S,G entry for *,G port doesn't exist"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .src == \"2001:db8:1::3\" and \
+ .port == \"$swp1\" and \
+ .flags[] == \"added_by_star_ex\")" &>/dev/null
+ check_err $? "Auto-added S,G entry doesn't have added_by_star_ex flag"
+
+ brmcast_check_sg_fwding 1 2001:db8:1::3
+
+ log_test "MLDv2 S,G port entry automatic add to a *,G port"
+
+ mldv2cleanup $swp1
+ mldv2cleanup $swp2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test traffic distribution when a wECMP route forwards traffic to two GRE
+# tunnels.
+#
+# +-------------------------+
+# | H1 |
+# | $h1 + |
+# | 192.0.2.1/28 | |
+# | 2001:db8:1::1/64 | |
+# +-------------------|-----+
+# |
+# +-------------------|------------------------+
+# | SW1 | |
+# | $ol1 + |
+# | 192.0.2.2/28 |
+# | 2001:db8:1::2/64 |
+# | |
+# | + g1a (gre) + g1b (gre) |
+# | loc=192.0.2.65 loc=192.0.2.81 |
+# | rem=192.0.2.66 --. rem=192.0.2.82 --. |
+# | tos=inherit | tos=inherit | |
+# | .------------------' | |
+# | | .------------------' |
+# | v v |
+# | + $ul1.111 (vlan) + $ul1.222 (vlan) |
+# | | 192.0.2.129/28 | 192.0.2.145/28 |
+# | \ / |
+# | \________________/ |
+# | | |
+# | + $ul1 |
+# +------------|-------------------------------+
+# |
+# +------------|-------------------------------+
+# | SW2 + $ul2 |
+# | _______|________ |
+# | / \ |
+# | / \ |
+# | + $ul2.111 (vlan) + $ul2.222 (vlan) |
+# | ^ 192.0.2.130/28 ^ 192.0.2.146/28 |
+# | | | |
+# | | '------------------. |
+# | '------------------. | |
+# | + g2a (gre) | + g2b (gre) | |
+# | loc=192.0.2.66 | loc=192.0.2.82 | |
+# | rem=192.0.2.65 --' rem=192.0.2.81 --' |
+# | tos=inherit tos=inherit |
+# | |
+# | $ol2 + |
+# | 192.0.2.17/28 | |
+# | 2001:db8:2::1/64 | |
+# +-------------------|------------------------+
+# |
+# +-------------------|-----+
+# | H2 | |
+# | $h2 + |
+# | 192.0.2.18/28 |
+# | 2001:db8:2::2/64 |
+# +-------------------------+
+
+ALL_TESTS="
+ ping_ipv4
+ ping_ipv6
+ multipath_ipv4
+ multipath_ipv6
+ multipath_ipv6_l4
+"
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+ ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2
+ ip route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+ ip route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+ ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2
+ simple_if_fini $h1 192.0.2.1/28
+}
+
+sw1_create()
+{
+ simple_if_init $ol1 192.0.2.2/28 2001:db8:1::2/64
+ __simple_if_init $ul1 v$ol1
+ vlan_create $ul1 111 v$ol1 192.0.2.129/28
+ vlan_create $ul1 222 v$ol1 192.0.2.145/28
+
+ tunnel_create g1a gre 192.0.2.65 192.0.2.66 tos inherit dev v$ol1
+ __simple_if_init g1a v$ol1 192.0.2.65/32
+ ip route add vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+
+ tunnel_create g1b gre 192.0.2.81 192.0.2.82 tos inherit dev v$ol1
+ __simple_if_init g1b v$ol1 192.0.2.81/32
+ ip route add vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+
+ ip -6 nexthop add id 101 dev g1a
+ ip -6 nexthop add id 102 dev g1b
+ ip nexthop add id 103 group 101/102
+
+ ip route add vrf v$ol1 192.0.2.16/28 nhid 103
+ ip route add vrf v$ol1 2001:db8:2::/64 nhid 103
+}
+
+sw1_destroy()
+{
+ ip route del vrf v$ol1 2001:db8:2::/64
+ ip route del vrf v$ol1 192.0.2.16/28
+
+ ip nexthop del id 103
+ ip -6 nexthop del id 102
+ ip -6 nexthop del id 101
+
+ ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+ __simple_if_fini g1b 192.0.2.81/32
+ tunnel_destroy g1b
+
+ ip route del vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+ __simple_if_fini g1a 192.0.2.65/32
+ tunnel_destroy g1a
+
+ vlan_destroy $ul1 222
+ vlan_destroy $ul1 111
+ __simple_if_fini $ul1
+ simple_if_fini $ol1 192.0.2.2/28 2001:db8:1::2/64
+}
+
+sw2_create()
+{
+ simple_if_init $ol2 192.0.2.17/28 2001:db8:2::1/64
+ __simple_if_init $ul2 v$ol2
+ vlan_create $ul2 111 v$ol2 192.0.2.130/28
+ vlan_create $ul2 222 v$ol2 192.0.2.146/28
+
+ tunnel_create g2a gre 192.0.2.66 192.0.2.65 tos inherit dev v$ol2
+ __simple_if_init g2a v$ol2 192.0.2.66/32
+ ip route add vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+
+ tunnel_create g2b gre 192.0.2.82 192.0.2.81 tos inherit dev v$ol2
+ __simple_if_init g2b v$ol2 192.0.2.82/32
+ ip route add vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+
+ ip -6 nexthop add id 201 dev g2a
+ ip -6 nexthop add id 202 dev g2b
+ ip nexthop add id 203 group 201/202
+
+ ip route add vrf v$ol2 192.0.2.0/28 nhid 203
+ ip route add vrf v$ol2 2001:db8:1::/64 nhid 203
+
+ tc qdisc add dev $ul2 clsact
+ tc filter add dev $ul2 ingress pref 111 prot 802.1Q \
+ flower vlan_id 111 action pass
+ tc filter add dev $ul2 ingress pref 222 prot 802.1Q \
+ flower vlan_id 222 action pass
+}
+
+sw2_destroy()
+{
+ tc qdisc del dev $ul2 clsact
+
+ ip route del vrf v$ol2 2001:db8:1::/64
+ ip route del vrf v$ol2 192.0.2.0/28
+
+ ip nexthop del id 203
+ ip -6 nexthop del id 202
+ ip -6 nexthop del id 201
+
+ ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+ __simple_if_fini g2b 192.0.2.82/32
+ tunnel_destroy g2b
+
+ ip route del vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+ __simple_if_fini g2a 192.0.2.66/32
+ tunnel_destroy g2a
+
+ vlan_destroy $ul2 222
+ vlan_destroy $ul2 111
+ __simple_if_fini $ul2
+ simple_if_fini $ol2 192.0.2.17/28 2001:db8:2::1/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.18/28 2001:db8:2::2/64
+ ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17
+ ip route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+ ip route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+ ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17
+ simple_if_fini $h2 192.0.2.18/28 2001:db8:2::2/64
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ ol1=${NETIFS[p2]}
+
+ ul1=${NETIFS[p3]}
+ ul2=${NETIFS[p4]}
+
+ ol2=${NETIFS[p5]}
+ h2=${NETIFS[p6]}
+
+ vrf_prepare
+ h1_create
+ sw1_create
+ sw2_create
+ h2_create
+
+ forwarding_enable
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ forwarding_restore
+
+ h2_destroy
+ sw2_destroy
+ sw1_destroy
+ h1_destroy
+ vrf_cleanup
+}
+
+multipath4_test()
+{
+ local what=$1; shift
+ local weight1=$1; shift
+ local weight2=$1; shift
+
+ sysctl_set net.ipv4.fib_multipath_hash_policy 1
+ ip nexthop replace id 103 group 101,$weight1/102,$weight2
+
+ local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+ ip vrf exec v$h1 \
+ $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \
+ -d 1msec -t udp "sp=1024,dp=0-32768"
+
+ local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+ local d111=$((t1_111 - t0_111))
+ local d222=$((t1_222 - t0_222))
+ multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+ ip nexthop replace id 103 group 101/102
+ sysctl_restore net.ipv4.fib_multipath_hash_policy
+}
+
+multipath6_test()
+{
+ local what=$1; shift
+ local weight1=$1; shift
+ local weight2=$1; shift
+
+ sysctl_set net.ipv6.fib_multipath_hash_policy 0
+ ip nexthop replace id 103 group 101,$weight1/102,$weight2
+
+ local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+ # Generate 16384 echo requests, each with a random flow label.
+ for ((i=0; i < 16384; ++i)); do
+ ip vrf exec v$h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null
+ done
+
+ local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+ local d111=$((t1_111 - t0_111))
+ local d222=$((t1_222 - t0_222))
+ multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+ ip nexthop replace id 103 group 101/102
+ sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+multipath6_l4_test()
+{
+ local what=$1; shift
+ local weight1=$1; shift
+ local weight2=$1; shift
+
+ sysctl_set net.ipv6.fib_multipath_hash_policy 1
+ ip nexthop replace id 103 group 101,$weight1/102,$weight2
+
+ local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+ ip vrf exec v$h1 \
+ $MZ $h1 -6 -q -p 64 -A 2001:db8:1::1 -B 2001:db8:2::2 \
+ -d 1msec -t udp "sp=1024,dp=0-32768"
+
+ local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+ local d111=$((t1_111 - t0_111))
+ local d222=$((t1_222 - t0_222))
+ multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+ ip nexthop replace id 103 group 101/102
+ sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.18
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:2::2
+}
+
+multipath_ipv4()
+{
+ log_info "Running IPv4 multipath tests"
+ multipath4_test "ECMP" 1 1
+ multipath4_test "Weighted MP 2:1" 2 1
+ multipath4_test "Weighted MP 11:45" 11 45
+}
+
+multipath_ipv6()
+{
+ log_info "Running IPv6 multipath tests"
+ multipath6_test "ECMP" 1 1
+ multipath6_test "Weighted MP 2:1" 2 1
+ multipath6_test "Weighted MP 11:45" 11 45
+}
+
+multipath_ipv6_l4()
+{
+ log_info "Running IPv6 L4 hash multipath tests"
+ multipath6_l4_test "ECMP" 1 1
+ multipath6_l4_test "Weighted MP 2:1" 2 1
+ multipath6_l4_test "Weighted MP 11:45" 11 45
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
{
tcpdump -e -n -r $capfile 2>&1
}
+
+# return 0 if the packet wasn't seen on host2_if or 1 if it was
+mcast_packet_test()
+{
+ local mac=$1
+ local src_ip=$2
+ local ip=$3
+ local host1_if=$4
+ local host2_if=$5
+ local seen=0
+ local tc_proto="ip"
+ local mz_v6arg=""
+
+ # basic check to see if we were passed an IPv4 address, if not assume IPv6
+ if [[ ! $ip =~ ^[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}$ ]]; then
+ tc_proto="ipv6"
+ mz_v6arg="-6"
+ fi
+
+ # Add an ACL on `host2_if` which will tell us whether the packet
+ # was received by it or not.
+ tc qdisc add dev $host2_if ingress
+ tc filter add dev $host2_if ingress protocol $tc_proto pref 1 handle 101 \
+ flower ip_proto udp dst_mac $mac action drop
+
+ $MZ $host1_if $mz_v6arg -c 1 -p 64 -b $mac -A $src_ip -B $ip -t udp "dp=4096,sp=2048" -q
+ sleep 1
+
+ tc -j -s filter show dev $host2_if ingress \
+ | jq -e ".[] | select(.options.handle == 101) \
+ | select(.options.actions[0].stats.packets == 1)" &> /dev/null
+ if [[ $? -eq 0 ]]; then
+ seen=1
+ fi
+
+ tc filter del dev $host2_if ingress protocol $tc_proto pref 1 handle 101 flower
+ tc qdisc del dev $host2_if ingress
+
+ return $seen
+}
+
+brmcast_check_sg_entries()
+{
+ local report=$1; shift
+ local slist=("$@")
+ local sarg=""
+
+ for src in "${slist[@]}"; do
+ sarg="${sarg} and .source_list[].address == \"$src\""
+ done
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .source_list != null $sarg)" &>/dev/null
+ check_err $? "Wrong *,G entry source list after $report report"
+
+ for sgent in "${slist[@]}"; do
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .src == \"$sgent\")" &>/dev/null
+ check_err $? "Missing S,G entry ($sgent, $TEST_GROUP)"
+ done
+}
+
+brmcast_check_sg_fwding()
+{
+ local should_fwd=$1; shift
+ local sources=("$@")
+
+ for src in "${sources[@]}"; do
+ local retval=0
+
+ mcast_packet_test $TEST_GROUP_MAC $src $TEST_GROUP $h2 $h1
+ retval=$?
+ if [ $should_fwd -eq 1 ]; then
+ check_fail $retval "Didn't forward traffic from S,G ($src, $TEST_GROUP)"
+ else
+ check_err $retval "Forwarded traffic for blocked S,G ($src, $TEST_GROUP)"
+ fi
+ done
+}
+
+brmcast_check_sg_state()
+{
+ local is_blocked=$1; shift
+ local sources=("$@")
+ local should_fail=1
+
+ if [ $is_blocked -eq 1 ]; then
+ should_fail=0
+ fi
+
+ for src in "${sources[@]}"; do
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .source_list != null) |
+ .source_list[] |
+ select(.address == \"$src\") |
+ select(.timer == \"0.00\")" &>/dev/null
+ check_err_fail $should_fail $? "Entry $src has zero timer"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .src == \"$src\" and \
+ .flags[] == \"blocked\")" &>/dev/null
+ check_err_fail $should_fail $? "Entry $src has blocked flag"
+ done
+}
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="ping_ipv4 ping_ipv6 multipath_test"
+ALL_TESTS="
+ ping_ipv4
+ ping_ipv6
+ multipath_test
+ ping_ipv4_blackhole
+ ping_ipv6_blackhole
+"
NUM_NETIFS=8
source lib.sh
multipath4_test "Weighted MP 2:1" 2 1
multipath4_test "Weighted MP 11:45" 11 45
+ log_info "Running IPv4 multipath tests with IPv6 link-local nexthops"
+ ip nexthop replace id 101 via fe80:2::22 dev $rp12
+ ip nexthop replace id 102 via fe80:3::23 dev $rp13
+
+ multipath4_test "ECMP" 1 1
+ multipath4_test "Weighted MP 2:1" 2 1
+ multipath4_test "Weighted MP 11:45" 11 45
+
+ ip nexthop replace id 102 via 169.254.3.23 dev $rp13
+ ip nexthop replace id 101 via 169.254.2.22 dev $rp12
+
log_info "Running IPv6 multipath tests"
multipath6_test "ECMP" 1 1
multipath6_test "Weighted MP 2:1" 2 1
multipath6_l4_test "Weighted MP 11:45" 11 45
}
+ping_ipv4_blackhole()
+{
+ RET=0
+
+ ip nexthop add id 1001 blackhole
+ ip nexthop add id 1002 group 1001
+
+ ip route replace 198.51.100.0/24 vrf vrf-r1 nhid 1001
+ ping_do $h1 198.51.100.2
+ check_fail $? "ping did not fail when using a blackhole nexthop"
+
+ ip route replace 198.51.100.0/24 vrf vrf-r1 nhid 1002
+ ping_do $h1 198.51.100.2
+ check_fail $? "ping did not fail when using a blackhole nexthop group"
+
+ ip route replace 198.51.100.0/24 vrf vrf-r1 nhid 103
+ ping_do $h1 198.51.100.2
+ check_err $? "ping failed with a valid nexthop"
+
+ log_test "IPv4 blackhole ping"
+
+ ip nexthop del id 1002
+ ip nexthop del id 1001
+}
+
+ping_ipv6_blackhole()
+{
+ RET=0
+
+ ip -6 nexthop add id 1001 blackhole
+ ip nexthop add id 1002 group 1001
+
+ ip route replace 2001:db8:2::/64 vrf vrf-r1 nhid 1001
+ ping6_do $h1 2001:db8:2::2
+ check_fail $? "ping did not fail when using a blackhole nexthop"
+
+ ip route replace 2001:db8:2::/64 vrf vrf-r1 nhid 1002
+ ping6_do $h1 2001:db8:2::2
+ check_fail $? "ping did not fail when using a blackhole nexthop group"
+
+ ip route replace 2001:db8:2::/64 vrf vrf-r1 nhid 106
+ ping6_do $h1 2001:db8:2::2
+ check_err $? "ping failed with a valid nexthop"
+
+ log_test "IPv6 blackhole ping"
+
+ ip nexthop del id 1002
+ ip -6 nexthop del id 1001
+}
+
setup_prepare()
{
h1=${NETIFS[p1]}
router1_create
router2_create
- routing_nh_obj
forwarding_enable
}
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+ ping_ipv4
+ ping_ipv6
+"
+
+NUM_NETIFS=4
+source lib.sh
+source tc_common.sh
+
+h1_create()
+{
+ vrf_create "vrf-h1"
+ ip link set dev $h1 master vrf-h1
+
+ ip link set dev vrf-h1 up
+ ip link set dev $h1 up
+
+ ip address add 192.0.2.2/24 dev $h1
+ ip address add 2001:db8:1::2/64 dev $h1
+
+ ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+ ip route add 2001:db8:2::/64 vrf vrf-h1 nexthop via 2001:db8:1::1
+}
+
+h1_destroy()
+{
+ ip route del 2001:db8:2::/64 vrf vrf-h1
+ ip route del 198.51.100.0/24 vrf vrf-h1
+
+ ip address del 2001:db8:1::2/64 dev $h1
+ ip address del 192.0.2.2/24 dev $h1
+
+ ip link set dev $h1 down
+ vrf_destroy "vrf-h1"
+}
+
+h2_create()
+{
+ vrf_create "vrf-h2"
+ ip link set dev $h2 master vrf-h2
+
+ ip link set dev vrf-h2 up
+ ip link set dev $h2 up
+
+ ip address add 198.51.100.2/24 dev $h2
+ ip address add 2001:db8:2::2/64 dev $h2
+
+ ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+ ip route add 2001:db8:1::/64 vrf vrf-h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+ ip route del 2001:db8:1::/64 vrf vrf-h2
+ ip route del 192.0.2.0/24 vrf vrf-h2
+
+ ip address del 2001:db8:2::2/64 dev $h2
+ ip address del 198.51.100.2/24 dev $h2
+
+ ip link set dev $h2 down
+ vrf_destroy "vrf-h2"
+}
+
+router_create()
+{
+ ip link set dev $rp1 up
+ ip link set dev $rp2 up
+
+ tc qdisc add dev $rp2 clsact
+
+ ip address add 192.0.2.1/24 dev $rp1
+ ip address add 2001:db8:1::1/64 dev $rp1
+
+ ip address add 198.51.100.1/24 dev $rp2
+ ip address add 2001:db8:2::1/64 dev $rp2
+}
+
+router_destroy()
+{
+ ip address del 2001:db8:2::1/64 dev $rp2
+ ip address del 198.51.100.1/24 dev $rp2
+
+ ip address del 2001:db8:1::1/64 dev $rp1
+ ip address del 192.0.2.1/24 dev $rp1
+
+ tc qdisc del dev $rp2 clsact
+
+ ip link set dev $rp2 down
+ ip link set dev $rp1 down
+}
+
+routing_nh_obj()
+{
+ # Create the nexthops as AF_INET6, so that IPv4 and IPv6 routes could
+ # use them.
+ ip -6 nexthop add id 101 dev $rp1
+ ip -6 nexthop add id 102 dev $rp2
+
+ ip route replace 192.0.2.0/24 nhid 101
+ ip route replace 2001:db8:1::/64 nhid 101
+ ip route replace 198.51.100.0/24 nhid 102
+ ip route replace 2001:db8:2::/64 nhid 102
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ rp1=${NETIFS[p2]}
+
+ rp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ rp1mac=$(mac_get $rp1)
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+
+ router_create
+
+ forwarding_enable
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ forwarding_restore
+
+ router_destroy
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+ping_ipv4()
+{
+ ping_test $h1 198.51.100.2
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+routing_nh_obj
+
+tests_run
+
+exit $EXIT_STATUS
CONFIG_INET_MPTCP_DIAG=m
CONFIG_VETH=y
CONFIG_NET_SCH_NETEM=m
+CONFIG_NETFILTER=y
+CONFIG_NETFILTER_ADVANCED=y
+CONFIG_NETFILTER_NETLINK=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_COMPAT=m
+CONFIG_NETFILTER_XTABLES=m
+CONFIG_NETFILTER_XT_MATCH_BPF=m
+CONFIG_NF_TABLES_IPV4=y
+CONFIG_NF_TABLES_IPV6=y
sin=""
sout=""
cin=""
+cinsent=""
cout=""
ksft_skip=4
timeout=30
TEST_COUNT=0
+# generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) ||
+# (ip6 && (ip6[74] & 0xf0) == 0x30)'"
+CBPF_MPTCP_SUBOPTION_ADD_ADDR="14,
+ 48 0 0 0,
+ 84 0 0 240,
+ 21 0 3 64,
+ 48 0 0 54,
+ 84 0 0 240,
+ 21 6 7 48,
+ 48 0 0 0,
+ 84 0 0 240,
+ 21 0 4 96,
+ 48 0 0 74,
+ 84 0 0 240,
+ 21 0 1 48,
+ 6 0 0 65535,
+ 6 0 0 0"
+
init()
{
capout=$(mktemp)
cleanup()
{
rm -f "$cin" "$cout"
- rm -f "$sin" "$sout"
+ rm -f "$sin" "$sout" "$cinsent"
cleanup_partial
}
done
}
+reset_with_add_addr_timeout()
+{
+ local ip="${1:-4}"
+ local tables
+
+ tables="iptables"
+ if [ $ip -eq 6 ]; then
+ tables="ip6tables"
+ fi
+
+ reset
+
+ ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1
+ ip netns exec $ns2 $tables -A OUTPUT -p tcp \
+ -m tcp --tcp-option 30 \
+ -m bpf --bytecode \
+ "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \
+ -j DROP
+}
+
for arg in "$@"; do
if [ "$arg" = "-c" ]; then
capture=1
exit $ksft_skip
fi
+iptables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run all tests without iptables tool"
+ exit $ksft_skip
+fi
+
+ip6tables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run all tests without ip6tables tool"
+ exit $ksft_skip
+fi
+
+print_file_err()
+{
+ ls -l "$1" 1>&2
+ echo "Trailing bytes are: "
+ tail -c 27 "$1"
+}
check_transfer()
{
echo "[ FAIL ] $what does not match (in, out):"
print_file_err "$in"
print_file_err "$out"
+ ret=1
return 1
fi
fi
}
+link_failure()
+{
+ ns="$1"
+
+ l=$((RANDOM%4))
+ l=$((l+1))
+
+ veth="ns1eth$l"
+ ip -net "$ns" link set "$veth" down
+}
+
+# $1: IP address
+is_v6()
+{
+ [ -z "${1##*:*}" ]
+}
+
do_transfer()
{
listener_ns="$1"
cl_proto="$3"
srv_proto="$4"
connect_addr="$5"
- rm_nr_ns1="$6"
- rm_nr_ns2="$7"
+ test_link_fail="$6"
+ rm_nr_ns1="$7"
+ rm_nr_ns2="$8"
+ speed="$9"
port=$((10000+$TEST_COUNT))
TEST_COUNT=$((TEST_COUNT+1))
sleep 1
fi
- if [[ $rm_nr_ns1 -eq 0 && $rm_nr_ns2 -eq 0 ]]; then
+ if [ $speed = "fast" ]; then
mptcp_connect="./mptcp_connect -j"
else
mptcp_connect="./mptcp_connect -r"
fi
- ip netns exec ${listener_ns} $mptcp_connect -t $timeout -l -p $port -s ${srv_proto} 0.0.0.0 < "$sin" > "$sout" &
+ local local_addr
+ if is_v6 "${connect_addr}"; then
+ local_addr="::"
+ else
+ local_addr="0.0.0.0"
+ fi
+
+ ip netns exec ${listener_ns} $mptcp_connect -t $timeout -l -p $port \
+ -s ${srv_proto} ${local_addr} < "$sin" > "$sout" &
spid=$!
sleep 1
- ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr < "$cin" > "$cout" &
+ if [ "$test_link_fail" -eq 0 ];then
+ ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr < "$cin" > "$cout" &
+ else
+ ( cat "$cin" ; sleep 2; link_failure $listener_ns ; cat "$cin" ) | tee "$cinsent" | \
+ ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr > "$cout" &
+ fi
cpid=$!
if [ $rm_nr_ns1 -gt 0 ]; then
ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port"
cat "$capout"
+ ret=1
return 1
fi
check_transfer $sin $cout "file received by client"
retc=$?
- check_transfer $cin $sout "file received by server"
+ if [ "$test_link_fail" -eq 0 ];then
+ check_transfer $cin $sout "file received by server"
+ else
+ check_transfer $cinsent $sout "file received by server"
+ fi
rets=$?
if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
{
name=$1
who=$2
+ size=$3
- SIZE=1
-
- dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null
+ dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null
echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
- echo "Created $name (size $SIZE KB) containing data sent by $who"
+ echo "Created $name (size $size KB) containing data sent by $who"
}
run_tests()
listener_ns="$1"
connector_ns="$2"
connect_addr="$3"
+ test_linkfail="${4:-0}"
+ rm_nr_ns1="${5:-0}"
+ rm_nr_ns2="${6:-0}"
+ speed="${7:-fast}"
lret=0
+ oldin=""
- do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} 0 0
- lret=$?
- if [ $lret -ne 0 ]; then
- ret=$lret
- return
- fi
-}
+ if [ "$test_linkfail" -eq 1 ];then
+ size=$((RANDOM%1024))
+ size=$((size+1))
+ size=$((size*128))
-run_remove_tests()
-{
- listener_ns="$1"
- connector_ns="$2"
- connect_addr="$3"
- rm_nr_ns1="$4"
- rm_nr_ns2="$5"
- lret=0
+ oldin=$(mktemp)
+ cp "$cin" "$oldin"
+ make_file "$cin" "client" $size
+ fi
- do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${rm_nr_ns1} ${rm_nr_ns2}
+ do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \
+ ${test_linkfail} ${rm_nr_ns1} ${rm_nr_ns2} ${speed}
lret=$?
+
+ if [ "$test_linkfail" -eq 1 ];then
+ cp "$oldin" "$cin"
+ rm -f "$oldin"
+ fi
+
if [ $lret -ne 0 ]; then
ret=$lret
return
sin=$(mktemp)
sout=$(mktemp)
cin=$(mktemp)
+cinsent=$(mktemp)
cout=$(mktemp)
init
-make_file "$cin" "client"
-make_file "$sin" "server"
+make_file "$cin" "client" 1
+make_file "$sin" "server" 1
trap cleanup EXIT
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr "multiple subflows and signal" 3 3 3
chk_add_nr 1 1
+# accept and use add_addr with additional subflows and link loss
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 3
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 3
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1 1
+chk_join_nr "multiple flows, signal, link failure" 3 3 3
+chk_add_nr 1 1
+
+# add_addr timeout
+reset_with_add_addr_timeout
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow
+chk_join_nr "signal address, ADD_ADDR timeout" 1 1 1
+chk_add_nr 4 0
+
# single subflow, remove
reset
ip netns exec $ns1 ./pm_nl_ctl limits 0 1
ip netns exec $ns2 ./pm_nl_ctl limits 0 1
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
-run_remove_tests $ns1 $ns2 10.0.1.1 0 1
+run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow
chk_join_nr "remove single subflow" 1 1 1
chk_rm_nr 1 1
ip netns exec $ns2 ./pm_nl_ctl limits 0 2
ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
-run_remove_tests $ns1 $ns2 10.0.1.1 0 2
+run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow
chk_join_nr "remove multiple subflows" 2 2 2
chk_rm_nr 2 2
ip netns exec $ns1 ./pm_nl_ctl limits 0 1
ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
ip netns exec $ns2 ./pm_nl_ctl limits 1 1
-run_remove_tests $ns1 $ns2 10.0.1.1 1 0
+run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow
chk_join_nr "remove single address" 1 1 1
chk_add_nr 1 1
chk_rm_nr 0 0
ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
ip netns exec $ns2 ./pm_nl_ctl limits 1 2
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
-run_remove_tests $ns1 $ns2 10.0.1.1 1 1
+run_tests $ns1 $ns2 10.0.1.1 0 1 1 slow
chk_join_nr "remove subflow and signal" 2 2 2
chk_add_nr 1 1
chk_rm_nr 1 1
ip netns exec $ns2 ./pm_nl_ctl limits 1 3
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
-run_remove_tests $ns1 $ns2 10.0.1.1 1 2
+run_tests $ns1 $ns2 10.0.1.1 0 1 2 slow
chk_join_nr "remove subflows and signal" 3 3 3
chk_add_nr 1 1
chk_rm_nr 2 2
+# subflow IPv6
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow
+run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
+chk_join_nr "single subflow IPv6" 1 1 1
+
+# add_address, unused IPv6
+reset
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
+chk_join_nr "unused signal address IPv6" 0 0 0
+chk_add_nr 1 1
+
+# signal address IPv6
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
+chk_join_nr "single address IPv6" 1 1 1
+chk_add_nr 1 1
+
+# add_addr timeout IPv6
+reset_with_add_addr_timeout 6
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
+chk_join_nr "signal address, ADD_ADDR6 timeout" 1 1 1
+chk_add_nr 4 0
+
+# single address IPv6, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+run_tests $ns1 $ns2 dead:beef:1::1 0 1 0 slow
+chk_join_nr "remove single address IPv6" 1 1 1
+chk_add_nr 1 1
+chk_rm_nr 0 0
+
+# subflow and signal IPv6, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 2
+ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow
+run_tests $ns1 $ns2 dead:beef:1::1 0 1 1 slow
+chk_join_nr "remove subflow and signal IPv6" 2 2 2
+chk_add_nr 1 1
+chk_rm_nr 1 1
+
# single subflow, syncookies
reset_with_cookies
ip netns exec $ns1 ./pm_nl_ctl limits 0 1
encap="${3}"
if [ "${outer}" = "4" ]; then
- modprobe fou || return 2
+ modprobe fou || return $ksft_skip
a_addr="${prefix4}.${a_r1}.1"
b_addr="${prefix4}.${b_r1}.1"
if [ "${inner}" = "4" ]; then
ipproto="41"
fi
else
- modprobe fou6 || return 2
+ modprobe fou6 || return $ksft_skip
a_addr="${prefix6}:${a_r1}::1"
b_addr="${prefix6}:${b_r1}::1"
if [ "${inner}" = "4" ]; then
fi
fi
- run_cmd ${ns_a} ip fou add port 5555 ipproto ${ipproto} || return 2
- run_cmd ${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return 2
+ run_cmd ${ns_a} ip fou add port 5555 ipproto ${ipproto} || return $ksft_skip
+ run_cmd ${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return $ksft_skip
run_cmd ${ns_b} ip fou add port 5556 ipproto ${ipproto}
run_cmd ${ns_b} ip link add ${encap}_b type ${type} ${mode} local ${b_addr} remote ${a_addr} encap ${encap} encap-sport auto encap-dport 5555
fi
fi
- run_cmd ${ns_a} ip link add ip_a type ${type} local ${a_addr} remote ${b_addr} mode ${mode} || return 2
+ run_cmd ${ns_a} ip link add ip_a type ${type} local ${a_addr} remote ${b_addr} mode ${mode} || return $ksft_skip
run_cmd ${ns_b} ip link add ip_b type ${type} local ${b_addr} remote ${a_addr} mode ${mode}
run_cmd ${ns_a} ip link set ip_a up
}
setup_bridge() {
- run_cmd ${ns_a} ip link add br0 type bridge || return 2
+ run_cmd ${ns_a} ip link add br0 type bridge || return $ksft_skip
run_cmd ${ns_a} ip link set br0 up
run_cmd ${ns_c} ip link add veth_C-A type veth peer name veth_A-C
}
setup_ovs_bridge() {
- run_cmd ovs-vsctl add-br ovs_br0 || return 2
+ run_cmd ovs-vsctl add-br ovs_br0 || return $ksft_skip
run_cmd ip link set ovs_br0 up
run_cmd ${ns_c} ip link add veth_C-A type veth peer name veth_A-C
test_pmtu_ipvX() {
family=${1}
- setup namespaces routing || return 2
+ setup namespaces routing || return $ksft_skip
trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
"${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \
"${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \
ll_mtu=4000
if [ ${outer_family} -eq 4 ]; then
- setup namespaces routing ${type}4 || return 2
+ setup namespaces routing ${type}4 || return $ksft_skip
# IPv4 header UDP header VXLAN/GENEVE header Ethernet header
exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14))
else
- setup namespaces routing ${type}6 || return 2
+ setup namespaces routing ${type}6 || return $ksft_skip
# IPv6 header UDP header VXLAN/GENEVE header Ethernet header
exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14))
fi
ll_mtu=4000
if [ ${outer_family} -eq 4 ]; then
- setup namespaces routing bridge bridged_${type}4 || return 2
+ setup namespaces routing bridge bridged_${type}4 || return $ksft_skip
# IPv4 header UDP header VXLAN/GENEVE header Ethernet header
exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14))
else
- setup namespaces routing bridge bridged_${type}6 || return 2
+ setup namespaces routing bridge bridged_${type}6 || return $ksft_skip
# IPv6 header UDP header VXLAN/GENEVE header Ethernet header
exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14))
fi
ll_mtu=4000
if [ ${outer_family} -eq 4 ]; then
- setup namespaces routing ovs_bridge ovs_${type}4 || return 2
+ setup namespaces routing ovs_bridge ovs_${type}4 || return $ksft_skip
# IPv4 header UDP header VXLAN/GENEVE header Ethernet header
exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14))
else
- setup namespaces routing ovs_bridge ovs_${type}6 || return 2
+ setup namespaces routing ovs_bridge ovs_${type}6 || return $ksft_skip
# IPv6 header UDP header VXLAN/GENEVE header Ethernet header
exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14))
fi
encap=${3}
ll_mtu=4000
- setup namespaces routing ${encap}${outer_family}${inner_family} || return 2
+ setup namespaces routing ${encap}${outer_family}${inner_family} || return $ksft_skip
trace "${ns_a}" ${encap}_a "${ns_b}" ${encap}_b \
"${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
"${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B
outer=${2}
ll_mtu=4000
- setup namespaces routing ip${inner}ip${outer} || return 2
+ setup namespaces routing ip${inner}ip${outer} || return $ksft_skip
trace "${ns_a}" ip_a "${ns_b}" ip_b \
"${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
}
test_pmtu_vti4_exception() {
- setup namespaces veth vti4 xfrm4 || return 2
+ setup namespaces veth vti4 xfrm4 || return $ksft_skip
trace "${ns_a}" veth_a "${ns_b}" veth_b \
"${ns_a}" vti4_a "${ns_b}" vti4_b
}
test_pmtu_vti6_exception() {
- setup namespaces veth vti6 xfrm6 || return 2
+ setup namespaces veth vti6 xfrm6 || return $ksft_skip
trace "${ns_a}" veth_a "${ns_b}" veth_b \
"${ns_a}" vti6_a "${ns_b}" vti6_b
fail=0
}
test_pmtu_vti4_default_mtu() {
- setup namespaces veth vti4 || return 2
+ setup namespaces veth vti4 || return $ksft_skip
# Check that MTU of vti device is MTU of veth minus IPv4 header length
veth_mtu="$(link_get_mtu "${ns_a}" veth_a)"
}
test_pmtu_vti6_default_mtu() {
- setup namespaces veth vti6 || return 2
+ setup namespaces veth vti6 || return $ksft_skip
# Check that MTU of vti device is MTU of veth minus IPv6 header length
veth_mtu="$(link_get_mtu "${ns_a}" veth_a)"
}
test_pmtu_vti4_link_add_mtu() {
- setup namespaces || return 2
+ setup namespaces || return $ksft_skip
run_cmd ${ns_a} ip link add vti4_a type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10
- [ $? -ne 0 ] && err " vti not supported" && return 2
+ [ $? -ne 0 ] && err " vti not supported" && return $ksft_skip
run_cmd ${ns_a} ip link del vti4_a
fail=0
}
test_pmtu_vti6_link_add_mtu() {
- setup namespaces || return 2
+ setup namespaces || return $ksft_skip
run_cmd ${ns_a} ip link add vti6_a type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
- [ $? -ne 0 ] && err " vti6 not supported" && return 2
+ [ $? -ne 0 ] && err " vti6 not supported" && return $ksft_skip
run_cmd ${ns_a} ip link del vti6_a
fail=0
}
test_pmtu_vti6_link_change_mtu() {
- setup namespaces || return 2
+ setup namespaces || return $ksft_skip
run_cmd ${ns_a} ip link add dummy0 mtu 1500 type dummy
- [ $? -ne 0 ] && err " dummy not supported" && return 2
+ [ $? -ne 0 ] && err " dummy not supported" && return $ksft_skip
run_cmd ${ns_a} ip link add dummy1 mtu 3000 type dummy
run_cmd ${ns_a} ip link set dummy0 up
run_cmd ${ns_a} ip link set dummy1 up
encap="vxlan"
ll_mtu=4000
- check_command taskset || return 2
+ check_command taskset || return $ksft_skip
cpu_list=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2)
- setup namespaces routing ${encap}${outer} || return 2
+ setup namespaces routing ${encap}${outer} || return $ksft_skip
trace "${ns_a}" ${encap}_a "${ns_b}" ${encap}_b \
"${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
"${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B
fi
err_flush
exit 1
- elif [ $ret -eq 2 ]; then
+ elif [ $ret -eq $ksft_skip ]; then
printf "TEST: %-60s [SKIP]\n" "${tdesc}"
err_flush
fi
return $ret
)
ret=$?
- [ $ret -ne 0 ] && exitcode=1
+ case $ret in
+ 0)
+ all_skipped=false
+ [ $exitcode=$ksft_skip ] && exitcode=0
+ ;;
+ $ksft_skip)
+ [ $all_skipped = true ] && exitcode=$ksft_skip
+ ;;
+ *)
+ all_skipped=false
+ exitcode=1
+ ;;
+ esac
return $ret
}
}
test_list_flush_ipv4_exception() {
- setup namespaces routing || return 2
+ setup namespaces routing || return $ksft_skip
trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
"${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \
"${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \
}
test_list_flush_ipv6_exception() {
- setup namespaces routing || return 2
+ setup namespaces routing || return $ksft_skip
trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
"${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \
"${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \
#
exitcode=0
desc=0
+all_skipped=true
while getopts :ptv o
do
if [ $run_this -eq 1 ]; then
run_test "${name}" "${desc}"
# if test was skipped no need to retry with nexthop objects
- [ $? -eq 2 ] && rerun_nh=0
+ [ $? -eq $ksft_skip ] && rerun_nh=0
if [ "${rerun_nh}" = "1" ]; then
run_test_nh "${name}" "${desc}"
#define RING_NUM_FRAMES 20
+static uint32_t cfg_max_num_members;
+
/* Open a socket in a given fanout mode.
* @return -1 if mode is bad, a valid socket otherwise */
static int sock_fanout_open(uint16_t typeflags, uint16_t group_id)
{
struct sockaddr_ll addr = {0};
- int fd, val;
+ struct fanout_args args;
+ int fd, val, err;
fd = socket(PF_PACKET, SOCK_RAW, 0);
if (fd < 0) {
exit(1);
}
- val = (((int) typeflags) << 16) | group_id;
- if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &val, sizeof(val))) {
+ if (cfg_max_num_members) {
+ args.id = group_id;
+ args.type_flags = typeflags;
+ args.max_num_members = cfg_max_num_members;
+ err = setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &args,
+ sizeof(args));
+ } else {
+ val = (((int) typeflags) << 16) | group_id;
+ err = setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &val,
+ sizeof(val));
+ }
+ if (err) {
if (close(fd)) {
perror("close packet");
exit(1);
}
}
+/* Test illegal max_num_members values */
+static void test_control_group_max_num_members(void)
+{
+ int fds[3];
+
+ fprintf(stderr, "test: control multiple sockets, max_num_members\n");
+
+ /* expected failure on greater than PACKET_FANOUT_MAX */
+ cfg_max_num_members = (1 << 16) + 1;
+ if (sock_fanout_open(PACKET_FANOUT_HASH, 0) != -1) {
+ fprintf(stderr, "ERROR: max_num_members > PACKET_FANOUT_MAX\n");
+ exit(1);
+ }
+
+ cfg_max_num_members = 256;
+ fds[0] = sock_fanout_open(PACKET_FANOUT_HASH, 0);
+ if (fds[0] == -1) {
+ fprintf(stderr, "ERROR: failed open\n");
+ exit(1);
+ }
+
+ /* expected failure on joining group with different max_num_members */
+ cfg_max_num_members = 257;
+ if (sock_fanout_open(PACKET_FANOUT_HASH, 0) != -1) {
+ fprintf(stderr, "ERROR: set different max_num_members\n");
+ exit(1);
+ }
+
+ /* success on joining group with same max_num_members */
+ cfg_max_num_members = 256;
+ fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, 0);
+ if (fds[1] == -1) {
+ fprintf(stderr, "ERROR: failed to join group\n");
+ exit(1);
+ }
+
+ /* success on joining group with max_num_members unspecified */
+ cfg_max_num_members = 0;
+ fds[2] = sock_fanout_open(PACKET_FANOUT_HASH, 0);
+ if (fds[2] == -1) {
+ fprintf(stderr, "ERROR: failed to join group\n");
+ exit(1);
+ }
+
+ if (close(fds[2]) || close(fds[1]) || close(fds[0])) {
+ fprintf(stderr, "ERROR: closing sockets\n");
+ exit(1);
+ }
+}
+
/* Test creating a unique fanout group ids */
static void test_unique_fanout_group_ids(void)
{
test_control_single();
test_control_group();
+ test_control_group_max_num_members();
test_unique_fanout_group_ids();
+ /* PACKET_FANOUT_MAX */
+ cfg_max_num_members = 1 << 16;
/* find a set of ports that do not collide onto the same socket */
ret = test_datapath(PACKET_FANOUT_HASH, port_off,
expect_hash[0], expect_hash[1]);
" SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n"
" SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n"
" SIOCGSTAMP - check last socket time stamp\n"
- " SIOCGSTAMPNS - more accurate socket time stamp\n");
+ " SIOCGSTAMPNS - more accurate socket time stamp\n"
+ " PTPV2 - use PTPv2 messages\n");
exit(1);
}
0x00, 0x00, 0x00, 0x00
};
-static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len)
+static const unsigned char sync_v2[] = {
+ 0x00, 0x02, 0x00, 0x2C,
+ 0x00, 0x00, 0x02, 0x00,
+ 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0xFF,
+ 0xFE, 0x00, 0x00, 0x00,
+ 0x00, 0x01, 0x00, 0x01,
+ 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00,
+};
+
+static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len, int ptpv2)
{
+ size_t sync_len = ptpv2 ? sizeof(sync_v2) : sizeof(sync);
+ const void *sync_p = ptpv2 ? sync_v2 : sync;
struct timeval now;
int res;
- res = sendto(sock, sync, sizeof(sync), 0,
- addr, addr_len);
+ res = sendto(sock, sync_p, sync_len, 0, addr, addr_len);
gettimeofday(&now, 0);
if (res < 0)
printf("%s: %s\n", "send", strerror(errno));
static void printpacket(struct msghdr *msg, int res,
char *data,
int sock, int recvmsg_flags,
- int siocgstamp, int siocgstampns)
+ int siocgstamp, int siocgstampns, int ptpv2)
{
struct sockaddr_in *from_addr = (struct sockaddr_in *)msg->msg_name;
+ size_t sync_len = ptpv2 ? sizeof(sync_v2) : sizeof(sync);
+ const void *sync_p = ptpv2 ? sync_v2 : sync;
struct cmsghdr *cmsg;
struct timeval tv;
struct timespec ts;
"probably SO_EE_ORIGIN_TIMESTAMPING"
#endif
);
- if (res < sizeof(sync))
+ if (res < sync_len)
printf(" => truncated data?!");
- else if (!memcmp(sync, data + res - sizeof(sync),
- sizeof(sync)))
+ else if (!memcmp(sync_p, data + res - sync_len, sync_len))
printf(" => GOT OUR DATA BACK (HURRAY!)");
break;
}
}
static void recvpacket(int sock, int recvmsg_flags,
- int siocgstamp, int siocgstampns)
+ int siocgstamp, int siocgstampns, int ptpv2)
{
char data[256];
struct msghdr msg;
} else {
printpacket(&msg, res, data,
sock, recvmsg_flags,
- siocgstamp, siocgstampns);
+ siocgstamp, siocgstampns, ptpv2);
}
}
int siocgstamp = 0;
int siocgstampns = 0;
int ip_multicast_loop = 0;
+ int ptpv2 = 0;
char *interface;
int i;
int enabled = 1;
siocgstampns = 1;
else if (!strcasecmp(argv[i], "IP_MULTICAST_LOOP"))
ip_multicast_loop = 1;
+ else if (!strcasecmp(argv[i], "PTPV2"))
+ ptpv2 = 1;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE"))
so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE"))
HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
hwconfig.rx_filter =
(so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ?
+ ptpv2 ? HWTSTAMP_FILTER_PTP_V2_L4_SYNC :
HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE;
hwconfig_requested = hwconfig;
if (ioctl(sock, SIOCSHWTSTAMP, &hwtstamp) < 0) {
printf("has error\n");
recvpacket(sock, 0,
siocgstamp,
- siocgstampns);
+ siocgstampns, ptpv2);
recvpacket(sock, MSG_ERRQUEUE,
siocgstamp,
- siocgstampns);
+ siocgstampns, ptpv2);
}
} else {
/* write one packet */
sendpacket(sock,
(struct sockaddr *)&addr,
- sizeof(addr));
+ sizeof(addr), ptpv2);
next.tv_sec += 5;
continue;
}
FIXTURE_VARIANT(tls)
{
- unsigned int tls_version;
+ u16 tls_version;
+ u16 cipher_type;
};
-FIXTURE_VARIANT_ADD(tls, 12)
+FIXTURE_VARIANT_ADD(tls, 12_gcm)
{
.tls_version = TLS_1_2_VERSION,
+ .cipher_type = TLS_CIPHER_AES_GCM_128,
};
-FIXTURE_VARIANT_ADD(tls, 13)
+FIXTURE_VARIANT_ADD(tls, 13_gcm)
{
.tls_version = TLS_1_3_VERSION,
+ .cipher_type = TLS_CIPHER_AES_GCM_128,
+};
+
+FIXTURE_VARIANT_ADD(tls, 12_chacha)
+{
+ .tls_version = TLS_1_2_VERSION,
+ .cipher_type = TLS_CIPHER_CHACHA20_POLY1305,
+};
+
+FIXTURE_VARIANT_ADD(tls, 13_chacha)
+{
+ .tls_version = TLS_1_3_VERSION,
+ .cipher_type = TLS_CIPHER_CHACHA20_POLY1305,
};
FIXTURE_SETUP(tls)
{
- struct tls12_crypto_info_aes_gcm_128 tls12;
+ union tls_crypto_context tls12;
struct sockaddr_in addr;
socklen_t len;
int sfd, ret;
+ size_t tls12_sz;
self->notls = false;
len = sizeof(addr);
memset(&tls12, 0, sizeof(tls12));
tls12.info.version = variant->tls_version;
- tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+ tls12.info.cipher_type = variant->cipher_type;
+ switch (variant->cipher_type) {
+ case TLS_CIPHER_CHACHA20_POLY1305:
+ tls12_sz = sizeof(tls12_crypto_info_chacha20_poly1305);
+ break;
+ case TLS_CIPHER_AES_GCM_128:
+ tls12_sz = sizeof(tls12_crypto_info_aes_gcm_128);
+ break;
+ default:
+ tls12_sz = 0;
+ }
addr.sin_family = AF_INET;
addr.sin_addr.s_addr = htonl(INADDR_ANY);
if (!self->notls) {
ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12,
- sizeof(tls12));
+ tls12_sz);
ASSERT_EQ(ret, 0);
}
ASSERT_EQ(ret, 0);
ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12,
- sizeof(tls12));
+ tls12_sz);
ASSERT_EQ(ret, 0);
}
projects / linux-2.6-microblaze.git / commitdiff